From 00b9de9c249f51f09c19aa41cbbb3e3eb4eea807 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 24 Jun 2009 17:53:33 +0900 Subject: serial: sh-sci: Move SCSCR_INIT in to platform data. This moves all of the SCSCR_INIT definitions in to the platform data, for future consolidation. Signed-off-by: Paul Mundt --- include/linux/serial_sci.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index 1c297dd..f722a22 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -7,6 +7,15 @@ * Generic header for SuperH SCI(F) (used by sh/sh64/h8300 and related parts) */ +#define SCSCR_TIE (1 << 7) +#define SCSCR_RIE (1 << 6) +#define SCSCR_TE (1 << 5) +#define SCSCR_RE (1 << 4) +#define SCSCR_REIE (1 << 3) +#define SCSCR_TOIE (1 << 2) /* not supported by all parts */ +#define SCSCR_CKE1 (1 << 1) +#define SCSCR_CKE0 (1 << 0) + /* Offsets into the sci_port->irqs array */ enum { SCIx_ERI_IRQ, @@ -26,6 +35,8 @@ struct plat_sci_port { unsigned int type; /* SCI / SCIF / IRDA */ upf_t flags; /* UPF_* flags */ char *clk; /* clock string */ + + unsigned int scscr; /* SCSCR initialization */ }; #endif /* __LINUX_SERIAL_SCI_H */ -- cgit v1.1 From 26c92f3728d738aaa7e4859d5581323cd68096dd Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Wed, 24 Jun 2009 18:23:52 +0900 Subject: serial: sh-sci: Move SCBRR calculation algo in to platform data. This permits each port to select its own SCBRR calculation algorithm, rather than having it all ifdef'ed in the header. There are presently only 5 different variations that all parts fall under. Signed-off-by: Paul Mundt --- include/linux/serial_sci.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index f722a22..ff856b5 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -7,6 +7,14 @@ * Generic header for SuperH SCI(F) (used by sh/sh64/h8300 and related parts) */ +enum { + SCBRR_ALGO_1, /* ((clk + 16 * bps) / (16 * bps) - 1) */ + SCBRR_ALGO_2, /* ((clk + 16 * bps) / (32 * bps) - 1) */ + SCBRR_ALGO_3, /* (((clk * 2) + 16 * bps) / (16 * bps) - 1) */ + SCBRR_ALGO_4, /* (((clk * 2) + 16 * bps) / (32 * bps) - 1) */ + SCBRR_ALGO_5, /* (((clk * 1000 / 32) / bps) - 1) */ +}; + #define SCSCR_TIE (1 << 7) #define SCSCR_RIE (1 << 6) #define SCSCR_TE (1 << 5) @@ -36,6 +44,7 @@ struct plat_sci_port { upf_t flags; /* UPF_* flags */ char *clk; /* clock string */ + unsigned int scbrr_algo_id; /* SCBRR calculation algo */ unsigned int scscr; /* SCSCR initialization */ }; -- cgit v1.1 From d0959024d8fb6555ba8bfdc6624cc7b7c2e675fd Mon Sep 17 00:00:00 2001 From: Richard Kennedy Date: Wed, 20 Oct 2010 15:57:30 -0700 Subject: timer_list: Remove alignment padding on 64 bit when CONFIG_TIMER_STATS Reorder struct timer_list to remove 8 bytes of alignment padding on 64 bit builds when CONFIG_TIMER_STATS is selected. timer_list is widely used across the kernel so many structures will benefit and shrink in size. For example, with my config on x86_64 per_cpu_dm_data shrinks from 136 to 128 bytes and ahci_port_priv shrinks from 1032 to 968 bytes. Signed-off-by: Richard Kennedy Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner --- include/linux/timer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/timer.h b/include/linux/timer.h index 38cf093..f3dccdb 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -24,9 +24,9 @@ struct timer_list { int slack; #ifdef CONFIG_TIMER_STATS + int start_pid; void *start_site; char start_comm[16]; - int start_pid; #endif #ifdef CONFIG_LOCKDEP struct lockdep_map lockdep_map; -- cgit v1.1 From aaabe31c25a439b92cc281b14ca18b85bae7e7a6 Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Wed, 20 Oct 2010 15:57:30 -0700 Subject: timer: Initialize the field slack of timer_list TIMER_INITIALIZER() should initialize the field slack of timer_list as __init_timer() does. Signed-off-by: Changli Gao Cc: Arjan van de Ven Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner --- include/linux/timer.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/timer.h b/include/linux/timer.h index f3dccdb..1794674 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -54,6 +54,7 @@ extern struct tvec_base boot_tvec_bases; .expires = (_expires), \ .data = (_data), \ .base = &boot_tvec_bases, \ + .slack = -1, \ __TIMER_LOCKDEP_MAP_INITIALIZER( \ __FILE__ ":" __stringify(__LINE__)) \ } -- cgit v1.1 From dd6414b50fa2b1cd247a8aa8f8bd42414b7453e1 Mon Sep 17 00:00:00 2001 From: Phil Carmody Date: Wed, 20 Oct 2010 15:57:33 -0700 Subject: timer: Permit statically-declared work with deferrable timers Currently, you have to just define a delayed_work uninitialised, and then initialise it before first use. That's a tad clumsy. At risk of playing mind-games with the compiler, fooling it into doing pointer arithmetic with compile-time-constants, this lets clients properly initialise delayed work with deferrable timers statically. This patch was inspired by the issues which lead Artem Bityutskiy to commit 8eab945c5616fc984 ("sunrpc: make the cache cleaner workqueue deferrable"). Signed-off-by: Phil Carmody Acked-by: Artem Bityutskiy Cc: Arjan van de Ven Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner --- include/linux/timer.h | 25 +++++++++++++++++++++++++ include/linux/workqueue.h | 8 ++++++++ 2 files changed, 33 insertions(+) (limited to 'include') diff --git a/include/linux/timer.h b/include/linux/timer.h index 1794674..cbfb7a3 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -48,6 +48,18 @@ extern struct tvec_base boot_tvec_bases; #define __TIMER_LOCKDEP_MAP_INITIALIZER(_kn) #endif +/* + * Note that all tvec_bases are 2 byte aligned and lower bit of + * base in timer_list is guaranteed to be zero. Use the LSB to + * indicate whether the timer is deferrable. + * + * A deferrable timer will work normally when the system is busy, but + * will not cause a CPU to come out of idle just to service it; instead, + * the timer will be serviced when the CPU eventually wakes up with a + * subsequent non-deferrable timer. + */ +#define TBASE_DEFERRABLE_FLAG (0x1) + #define TIMER_INITIALIZER(_function, _expires, _data) { \ .entry = { .prev = TIMER_ENTRY_STATIC }, \ .function = (_function), \ @@ -59,6 +71,19 @@ extern struct tvec_base boot_tvec_bases; __FILE__ ":" __stringify(__LINE__)) \ } +#define TBASE_MAKE_DEFERRED(ptr) ((struct tvec_base *) \ + ((unsigned char *)(ptr) + TBASE_DEFERRABLE_FLAG)) + +#define TIMER_DEFERRED_INITIALIZER(_function, _expires, _data) {\ + .entry = { .prev = TIMER_ENTRY_STATIC }, \ + .function = (_function), \ + .expires = (_expires), \ + .data = (_data), \ + .base = TBASE_MAKE_DEFERRED(&boot_tvec_bases), \ + __TIMER_LOCKDEP_MAP_INITIALIZER( \ + __FILE__ ":" __stringify(__LINE__)) \ + } + #define DEFINE_TIMER(_name, _function, _expires, _data) \ struct timer_list _name = \ TIMER_INITIALIZER(_function, _expires, _data) diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index f11100f..88238c1 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -127,12 +127,20 @@ struct execute_work { .timer = TIMER_INITIALIZER(NULL, 0, 0), \ } +#define __DEFERRED_WORK_INITIALIZER(n, f) { \ + .work = __WORK_INITIALIZER((n).work, (f)), \ + .timer = TIMER_DEFERRED_INITIALIZER(NULL, 0, 0), \ + } + #define DECLARE_WORK(n, f) \ struct work_struct n = __WORK_INITIALIZER(n, f) #define DECLARE_DELAYED_WORK(n, f) \ struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f) +#define DECLARE_DEFERRED_WORK(n, f) \ + struct delayed_work n = __DEFERRED_WORK_INITIALIZER(n, f) + /* * initialize a work item's function pointer */ -- cgit v1.1 From 6f1bc451e6a79470b122a37ee1fc6bbca450f444 Mon Sep 17 00:00:00 2001 From: Yong Zhang Date: Wed, 20 Oct 2010 15:57:31 -0700 Subject: timer: Make try_to_del_timer_sync() the same on SMP and UP On UP try_to_del_timer_sync() is mapped to del_timer() which does not take the running timer callback into account, so it has different semantics. Remove the SMP dependency of try_to_del_timer_sync() by using base->running_timer in the UP case as well. [ tglx: Removed set_running_timer() inline and tweaked the changelog ] Signed-off-by: Yong Zhang Cc: Ingo Molnar Cc: Peter Zijlstra Acked-by: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner --- include/linux/timer.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/timer.h b/include/linux/timer.h index cbfb7a3..6abd913 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -274,11 +274,11 @@ static inline void timer_stats_timer_clear_start_info(struct timer_list *timer) extern void add_timer(struct timer_list *timer); +extern int try_to_del_timer_sync(struct timer_list *timer); + #ifdef CONFIG_SMP - extern int try_to_del_timer_sync(struct timer_list *timer); extern int del_timer_sync(struct timer_list *timer); #else -# define try_to_del_timer_sync(t) del_timer(t) # define del_timer_sync(t) del_timer(t) #endif -- cgit v1.1 From fe7de49f9d4e53f24ec9ef762a503f70b562341c Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Wed, 20 Oct 2010 16:01:12 -0700 Subject: sched: Make sched_param argument static in sched_setscheduler() callers Andrew Morton pointed out almost all sched_setscheduler() callers are using fixed parameters and can be converted to static. It reduces runtime memory use a little. Signed-off-by: KOSAKI Motohiro Reported-by: Andrew Morton Acked-by: James Morris Cc: Ingo Molnar Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/sched.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 0383601..849c867 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1942,9 +1942,10 @@ extern int task_nice(const struct task_struct *p); extern int can_nice(const struct task_struct *p, const int nice); extern int task_curr(const struct task_struct *p); extern int idle_cpu(int cpu); -extern int sched_setscheduler(struct task_struct *, int, struct sched_param *); +extern int sched_setscheduler(struct task_struct *, int, + const struct sched_param *); extern int sched_setscheduler_nocheck(struct task_struct *, int, - struct sched_param *); + const struct sched_param *); extern struct task_struct *idle_task(int cpu); extern struct task_struct *curr_task(int cpu); extern void set_curr_task(int cpu, struct task_struct *p); -- cgit v1.1 From d935cc61d466f6cc7514032835f4fc379cb7e2ca Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 16 Sep 2010 15:13:11 +0200 Subject: drm_mm: add support for range-restricted fair-lru scans Signed-off-by: Daniel Vetter Signed-off-by: Chris Wilson --- include/drm/drm_mm.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/drm/drm_mm.h b/include/drm/drm_mm.h index bf01531..e391777 100644 --- a/include/drm/drm_mm.h +++ b/include/drm/drm_mm.h @@ -62,11 +62,14 @@ struct drm_mm { struct list_head unused_nodes; int num_unused; spinlock_t unused_lock; + unsigned int scan_check_range : 1; unsigned scan_alignment; unsigned long scan_size; unsigned long scan_hit_start; unsigned scan_hit_size; unsigned scanned_blocks; + unsigned long scan_start; + unsigned long scan_end; }; /* @@ -145,6 +148,10 @@ static inline struct drm_mm *drm_get_mm(struct drm_mm_node *block) void drm_mm_init_scan(struct drm_mm *mm, unsigned long size, unsigned alignment); +void drm_mm_init_scan_with_range(struct drm_mm *mm, unsigned long size, + unsigned alignment, + unsigned long start, + unsigned long end); int drm_mm_scan_add_block(struct drm_mm_node *node); int drm_mm_scan_remove_block(struct drm_mm_node *node); -- cgit v1.1 From a00b10c360b35d6431a94cbf130a4e162870d661 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 24 Sep 2010 21:15:47 +0100 Subject: drm/i915: Only enforce fence limits inside the GTT. So long as we adhere to the fence registers rules for alignment and no overlaps (including with unfenced accesses to linear memory) and account for the tiled access in our size allocation, we do not have to allocate the full fenced region for the object. This allows us to fight the bloat tiling imposed on pre-i965 chipsets and frees up RAM for real use. [Inside the GTT we still suffer the additional alignment constraints, so it doesn't magic allow us to render larger scenes without stalls -- we need the expanded GTT and fence pipelining to overcome those...] Signed-off-by: Chris Wilson --- include/drm/i915_drm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h index 8c641be..b20dbb2 100644 --- a/include/drm/i915_drm.h +++ b/include/drm/i915_drm.h @@ -287,6 +287,7 @@ typedef struct drm_i915_irq_wait { #define I915_PARAM_HAS_EXECBUF2 9 #define I915_PARAM_HAS_BSD 10 #define I915_PARAM_HAS_BLT 11 +#define I915_PARAM_HAS_RELAXED_FENCING 12 typedef struct drm_i915_getparam { int param; -- cgit v1.1 From 4b6ba8aacbb3185703b797286547d0f8f3859b02 Mon Sep 17 00:00:00 2001 From: David Daney Date: Tue, 26 Oct 2010 15:07:13 -0700 Subject: of/net: Move of_get_mac_address() to a common source file. There are two identical implementations of of_get_mac_address(), one each in arch/powerpc/kernel/prom_parse.c and arch/microblaze/kernel/prom_parse.c. Move this function to a new common file of_net.{c,h} and adjust all the callers to include the new header. Signed-off-by: David Daney [grant.likely@secretlab.ca: protect header with #ifdef] Signed-off-by: Grant Likely --- include/linux/of_net.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) create mode 100644 include/linux/of_net.h (limited to 'include') diff --git a/include/linux/of_net.h b/include/linux/of_net.h new file mode 100644 index 0000000..e913081 --- /dev/null +++ b/include/linux/of_net.h @@ -0,0 +1,15 @@ +/* + * OF helpers for network devices. + * + * This file is released under the GPLv2 + */ + +#ifndef __LINUX_OF_NET_H +#define __LINUX_OF_NET_H + +#ifdef CONFIG_OF_NET +#include +extern const void *of_get_mac_address(struct device_node *np); +#endif + +#endif /* __LINUX_OF_NET_H */ -- cgit v1.1 From 0f8c6d7ca9257d6a01671ab69b897860d3ae9bc0 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 1 Nov 2010 12:38:44 +0000 Subject: drm/i915: Move the invalidate|flush information out of the device struct ... and into a local structure scoped for the single function in which it is used. Signed-off-by: Chris Wilson --- include/drm/drmP.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/drm/drmP.h b/include/drm/drmP.h index 274eaaa..d4bc0f5 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -1041,8 +1041,6 @@ struct drm_device { /*@{ */ spinlock_t object_name_lock; struct idr object_name_idr; - uint32_t invalidate_domains; /* domains pending invalidation */ - uint32_t flush_domains; /* domains pending flush */ /*@} */ }; -- cgit v1.1 From b595076a180a56d1bb170e6eceda6eb9d76f4cd3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 1 Nov 2010 15:38:34 -0400 Subject: tree-wide: fix comment/printk typos MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit "gadget", "through", "command", "maintain", "maintain", "controller", "address", "between", "initiali[zs]e", "instead", "function", "select", "already", "equal", "access", "management", "hierarchy", "registration", "interest", "relative", "memory", "offset", "already", Signed-off-by: Uwe Kleine-König Signed-off-by: Jiri Kosina --- include/acpi/actbl1.h | 2 +- include/linux/cgroup.h | 2 +- include/linux/firewire-cdev.h | 2 +- include/linux/mfd/core.h | 2 +- include/net/sctp/user.h | 4 ++-- include/scsi/fc/fc_fcp.h | 4 ++-- 6 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index c637b75..cd77aa7 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -119,7 +119,7 @@ struct acpi_whea_header { struct acpi_table_bert { struct acpi_table_header header; /* Common ACPI table header */ u32 region_length; /* Length of the boot error region */ - u64 address; /* Physical addresss of the error region */ + u64 address; /* Physical address of the error region */ }; /* Boot Error Region (not a subtable, pointed to by Address field above) */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index ed4ba11..ce104e3 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -564,7 +564,7 @@ struct cgroup_iter { /* * To iterate across the tasks in a cgroup: * - * 1) call cgroup_iter_start to intialize an iterator + * 1) call cgroup_iter_start to initialize an iterator * * 2) call cgroup_iter_next() to retrieve member tasks until it * returns NULL or until you want to end the iteration diff --git a/include/linux/firewire-cdev.h b/include/linux/firewire-cdev.h index 68c642d..59ea406 100644 --- a/include/linux/firewire-cdev.h +++ b/include/linux/firewire-cdev.h @@ -273,7 +273,7 @@ struct fw_cdev_event_iso_interrupt { * @closure: See &fw_cdev_event_common; * set by %FW_CDEV_CREATE_ISO_CONTEXT ioctl * @type: %FW_CDEV_EVENT_ISO_INTERRUPT_MULTICHANNEL - * @completed: Offset into the receive buffer; data before this offest is valid + * @completed: Offset into the receive buffer; data before this offset is valid * * This event is sent in multichannel contexts (context type * %FW_CDEV_ISO_CONTEXT_RECEIVE_MULTICHANNEL) for &fw_cdev_iso_packet buffer diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index cb93d80..5582ab3 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -39,7 +39,7 @@ struct mfd_cell { size_t data_size; /* - * This resources can be specified relatievly to the parent device. + * This resources can be specified relatively to the parent device. * For accessing device you should use resources from device */ int num_resources; diff --git a/include/net/sctp/user.h b/include/net/sctp/user.h index 2b2769c..2a128c8 100644 --- a/include/net/sctp/user.h +++ b/include/net/sctp/user.h @@ -99,8 +99,8 @@ typedef __s32 sctp_assoc_t; #define SCTP_SOCKOPT_PEELOFF 102 /* peel off association. */ /* Options 104-106 are deprecated and removed. Do not use this space */ #define SCTP_SOCKOPT_CONNECTX_OLD 107 /* CONNECTX old requests. */ -#define SCTP_GET_PEER_ADDRS 108 /* Get all peer addresss. */ -#define SCTP_GET_LOCAL_ADDRS 109 /* Get all local addresss. */ +#define SCTP_GET_PEER_ADDRS 108 /* Get all peer address. */ +#define SCTP_GET_LOCAL_ADDRS 109 /* Get all local address. */ #define SCTP_SOCKOPT_CONNECTX 110 /* CONNECTX requests. */ #define SCTP_SOCKOPT_CONNECTX3 111 /* CONNECTX requests (updated) */ diff --git a/include/scsi/fc/fc_fcp.h b/include/scsi/fc/fc_fcp.h index 8e9b222..8a143ca 100644 --- a/include/scsi/fc/fc_fcp.h +++ b/include/scsi/fc/fc_fcp.h @@ -46,7 +46,7 @@ */ struct fcp_cmnd { __u8 fc_lun[8]; /* logical unit number */ - __u8 fc_cmdref; /* commmand reference number */ + __u8 fc_cmdref; /* command reference number */ __u8 fc_pri_ta; /* priority and task attribute */ __u8 fc_tm_flags; /* task management flags */ __u8 fc_flags; /* additional len & flags */ @@ -58,7 +58,7 @@ struct fcp_cmnd { struct fcp_cmnd32 { __u8 fc_lun[8]; /* logical unit number */ - __u8 fc_cmdref; /* commmand reference number */ + __u8 fc_cmdref; /* command reference number */ __u8 fc_pri_ta; /* priority and task attribute */ __u8 fc_tm_flags; /* task management flags */ __u8 fc_flags; /* additional len & flags */ -- cgit v1.1 From 4a92379bdfb48680a5e6775dd53a586df7b6b0b1 Mon Sep 17 00:00:00 2001 From: Richard Kennedy Date: Thu, 21 Oct 2010 10:29:19 +0100 Subject: slub tracing: move trace calls out of always inlined functions to reduce kernel code size Having the trace calls defined in the always inlined kmalloc functions in include/linux/slub_def.h causes a lot of code duplication as the trace functions get instantiated for each kamalloc call site. This can simply be removed by pushing the trace calls down into the functions in slub.c. On my x86_64 built this patch shrinks the code size of the kernel by approx 36K and also shrinks the code size of many modules -- too many to list here ;) size vmlinux (2.6.36) reports text data bss dec hex filename 5410611 743172 828928 6982711 6a8c37 vmlinux 5373738 744244 828928 6946910 6a005e vmlinux + patch The resulting kernel has had some testing & kmalloc trace still seems to work. This patch - moves trace_kmalloc out of the inlined kmalloc() and pushes it down into kmem_cache_alloc_trace() so this it only get instantiated once. - rename kmem_cache_alloc_notrace() to kmem_cache_alloc_trace() to indicate that now is does have tracing. (maybe this would better being called something like kmalloc_kmem_cache ?) - adds a new function kmalloc_order() to handle allocation and tracing of large allocations of page order. - removes tracing from the inlined kmalloc_large() replacing them with a call to kmalloc_order(); - move tracing out of inlined kmalloc_node() and pushing it down into kmem_cache_alloc_node_trace - rename kmem_cache_alloc_node_notrace() to kmem_cache_alloc_node_trace() - removes the include of trace/events/kmem.h from slub_def.h. v2 - keep kmalloc_order_trace inline when !CONFIG_TRACE Signed-off-by: Richard Kennedy Signed-off-by: Pekka Enberg --- include/linux/slub_def.h | 55 +++++++++++++++++++++++------------------------- 1 file changed, 26 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index e4f5ed1..8b6e8ae 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -10,9 +10,8 @@ #include #include #include -#include -#include +#include enum stat_item { ALLOC_FASTPATH, /* Allocation from cpu slab */ @@ -216,31 +215,40 @@ static __always_inline struct kmem_cache *kmalloc_slab(size_t size) void *kmem_cache_alloc(struct kmem_cache *, gfp_t); void *__kmalloc(size_t size, gfp_t flags); +static __always_inline void * +kmalloc_order(size_t size, gfp_t flags, unsigned int order) +{ + void *ret = (void *) __get_free_pages(flags | __GFP_COMP, order); + kmemleak_alloc(ret, size, 1, flags); + return ret; +} + #ifdef CONFIG_TRACING -extern void *kmem_cache_alloc_notrace(struct kmem_cache *s, gfp_t gfpflags); +extern void * +kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size); +extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order); #else static __always_inline void * -kmem_cache_alloc_notrace(struct kmem_cache *s, gfp_t gfpflags) +kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size) { return kmem_cache_alloc(s, gfpflags); } + +static __always_inline void * +kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) +{ + return kmalloc_order(size, flags, order); +} #endif static __always_inline void *kmalloc_large(size_t size, gfp_t flags) { unsigned int order = get_order(size); - void *ret = (void *) __get_free_pages(flags | __GFP_COMP, order); - - kmemleak_alloc(ret, size, 1, flags); - trace_kmalloc(_THIS_IP_, ret, size, PAGE_SIZE << order, flags); - - return ret; + return kmalloc_order_trace(size, flags, order); } static __always_inline void *kmalloc(size_t size, gfp_t flags) { - void *ret; - if (__builtin_constant_p(size)) { if (size > SLUB_MAX_SIZE) return kmalloc_large(size, flags); @@ -251,11 +259,7 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags) if (!s) return ZERO_SIZE_PTR; - ret = kmem_cache_alloc_notrace(s, flags); - - trace_kmalloc(_THIS_IP_, ret, size, s->size, flags); - - return ret; + return kmem_cache_alloc_trace(s, flags, size); } } return __kmalloc(size, flags); @@ -266,14 +270,14 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node); void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node); #ifdef CONFIG_TRACING -extern void *kmem_cache_alloc_node_notrace(struct kmem_cache *s, +extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, - int node); + int node, size_t size); #else static __always_inline void * -kmem_cache_alloc_node_notrace(struct kmem_cache *s, +kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, - int node) + int node, size_t size) { return kmem_cache_alloc_node(s, gfpflags, node); } @@ -281,8 +285,6 @@ kmem_cache_alloc_node_notrace(struct kmem_cache *s, static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { - void *ret; - if (__builtin_constant_p(size) && size <= SLUB_MAX_SIZE && !(flags & SLUB_DMA)) { struct kmem_cache *s = kmalloc_slab(size); @@ -290,12 +292,7 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) if (!s) return ZERO_SIZE_PTR; - ret = kmem_cache_alloc_node_notrace(s, flags, node); - - trace_kmalloc_node(_THIS_IP_, ret, - size, s->size, flags, node); - - return ret; + return kmem_cache_alloc_node_trace(s, flags, node, size); } return __kmalloc_node(size, flags, node); } -- cgit v1.1 From fc766e4c4965915ab52a1d1fa3c7a7b3e7bc07f0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 29 Oct 2010 03:09:24 +0000 Subject: decnet: RCU conversion and get rid of dev_base_lock While tracking dev_base_lock users, I found decnet used it in dnet_select_source(), but for a wrong purpose: Writers only hold RTNL, not dev_base_lock, so readers must use RCU if they cannot use RTNL. Adds an rcu_head in struct dn_ifaddr and handle proper RCU management. Adds __rcu annotation in dn_route as well. Signed-off-by: Eric Dumazet Acked-by: Steven Whitehouse Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- include/net/dn_dev.h | 27 ++++++++++++++++++--------- include/net/dst.h | 8 ++++---- 3 files changed, 23 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d8fd2c2..578debb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -951,7 +951,7 @@ struct net_device { #endif void *atalk_ptr; /* AppleTalk link */ struct in_device __rcu *ip_ptr; /* IPv4 specific data */ - void *dn_ptr; /* DECnet specific data */ + struct dn_dev __rcu *dn_ptr; /* DECnet specific data */ struct inet6_dev __rcu *ip6_ptr; /* IPv6 specific data */ void *ec_ptr; /* Econet specific data */ void *ax25_ptr; /* AX.25 specific data */ diff --git a/include/net/dn_dev.h b/include/net/dn_dev.h index 0916bbf..b9e32db 100644 --- a/include/net/dn_dev.h +++ b/include/net/dn_dev.h @@ -5,13 +5,14 @@ struct dn_dev; struct dn_ifaddr { - struct dn_ifaddr *ifa_next; + struct dn_ifaddr __rcu *ifa_next; struct dn_dev *ifa_dev; __le16 ifa_local; __le16 ifa_address; __u8 ifa_flags; __u8 ifa_scope; char ifa_label[IFNAMSIZ]; + struct rcu_head rcu; }; #define DN_DEV_S_RU 0 /* Run - working normally */ @@ -83,7 +84,7 @@ struct dn_dev_parms { struct dn_dev { - struct dn_ifaddr *ifa_list; + struct dn_ifaddr __rcu *ifa_list; struct net_device *dev; struct dn_dev_parms parms; char use_long; @@ -171,19 +172,27 @@ extern int unregister_dnaddr_notifier(struct notifier_block *nb); static inline int dn_dev_islocal(struct net_device *dev, __le16 addr) { - struct dn_dev *dn_db = dev->dn_ptr; + struct dn_dev *dn_db; struct dn_ifaddr *ifa; + int res = 0; + rcu_read_lock(); + dn_db = rcu_dereference(dev->dn_ptr); if (dn_db == NULL) { printk(KERN_DEBUG "dn_dev_islocal: Called for non DECnet device\n"); - return 0; + goto out; } - for(ifa = dn_db->ifa_list; ifa; ifa = ifa->ifa_next) - if ((addr ^ ifa->ifa_local) == 0) - return 1; - - return 0; + for (ifa = rcu_dereference(dn_db->ifa_list); + ifa != NULL; + ifa = rcu_dereference(ifa->ifa_next)) + if ((addr ^ ifa->ifa_local) == 0) { + res = 1; + break; + } +out: + rcu_read_unlock(); + return res; } #endif /* _NET_DN_DEV_H */ diff --git a/include/net/dst.h b/include/net/dst.h index ffe9cb7..a5bd726 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -94,10 +94,10 @@ struct dst_entry { int __use; unsigned long lastuse; union { - struct dst_entry *next; - struct rtable __rcu *rt_next; - struct rt6_info *rt6_next; - struct dn_route *dn_next; + struct dst_entry *next; + struct rtable __rcu *rt_next; + struct rt6_info *rt6_next; + struct dn_route __rcu *dn_next; }; }; -- cgit v1.1 From 1da4b1c6a4dfb5a13d7147a27c1ac53fed09befd Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Tue, 9 Nov 2010 11:22:58 +0000 Subject: x86/mrst: Add SFI platform device parsing code MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit SFI provides a series of tables. These describe the platform devices present including SPI and I²C devices, as well as various sensors, keypads and other glue as well as interfaces provided via the SCU IPC mechanism (intel_scu_ipc.c) This patch is a merge of the core elements and relevant fixes from the Intel development code by Feng, Alek, myself into a single coherent patch for upstream submission. It provides the needed infrastructure to register I2C, SPI and platform devices described by the tables, as well as handlers for some of the hardware already supported in kernel. The 0.8 firmware also provides GPIO tables. Devices are created at boot time or if they are SCU dependant at the point an SCU is discovered. The existing Linux device mechanisms will then handle the device binding. At an abstract level this is an SFI to Linux device translator. Device/platform specific setup/glue is in this file. This is done so that the drivers for the generic I²C and SPI bus devices remain cross platform as they should. (Updated from RFC version to correct the emc1403 name used by the firmware and a wrongly used #define) Signed-off-by: Alek Du LKML-Reference: <20101109112158.20013.6158.stgit@localhost.localdomain> [Clean ups, removal of 0.7 support] Signed-off-by: Feng Tang [Clean ups] Signed-off-by: Alan Cox Signed-off-by: Thomas Gleixner --- include/linux/sfi.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/sfi.h b/include/linux/sfi.h index 7f770c6..fe81791 100644 --- a/include/linux/sfi.h +++ b/include/linux/sfi.h @@ -77,6 +77,8 @@ #define SFI_OEM_ID_SIZE 6 #define SFI_OEM_TABLE_ID_SIZE 8 +#define SFI_NAME_LEN 16 + #define SFI_SYST_SEARCH_BEGIN 0x000E0000 #define SFI_SYST_SEARCH_END 0x000FFFFF @@ -156,13 +158,13 @@ struct sfi_device_table_entry { u16 addr; u8 irq; u32 max_freq; - char name[16]; + char name[SFI_NAME_LEN]; } __packed; struct sfi_gpio_table_entry { - char controller_name[16]; + char controller_name[SFI_NAME_LEN]; u16 pin_no; - char pin_name[16]; + char pin_name[SFI_NAME_LEN]; } __packed; typedef int (*sfi_table_handler) (struct sfi_table_header *table); -- cgit v1.1 From 751305d9b2fd3e03eaab7808e976241d85ca4353 Mon Sep 17 00:00:00 2001 From: Daniel Drake Date: Thu, 28 Oct 2010 18:23:01 +0100 Subject: viafb: General power management infrastructure Multiple devices need S/R hooks (framebuffer, GPIO, camera). Add infrastructure and convert existing framebuffer code to the new model. This patch should create no functional change. Based on earlier work by Jonathan Corbet. Signed-off-by: Daniel Drake Acked-by: Jonathan Corbet Signed-off-by: Florian Tobias Schandinat --- include/linux/via-core.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/via-core.h b/include/linux/via-core.h index 7ffb521..a4327a0 100644 --- a/include/linux/via-core.h +++ b/include/linux/via-core.h @@ -60,6 +60,21 @@ struct via_port_cfg { }; /* + * Allow subdevs to register suspend/resume hooks. + */ +#ifdef CONFIG_PM +struct viafb_pm_hooks { + struct list_head list; + int (*suspend)(void *private); + int (*resume)(void *private); + void *private; +}; + +void viafb_pm_register(struct viafb_pm_hooks *hooks); +void viafb_pm_unregister(struct viafb_pm_hooks *hooks); +#endif /* CONFIG_PM */ + +/* * This is the global viafb "device" containing stuff needed by * all subdevs. */ -- cgit v1.1 From 4d17aeb1c5b2375769446d13012a98e6d265ec13 Mon Sep 17 00:00:00 2001 From: Paul Walmsley Date: Tue, 21 Sep 2010 19:37:15 +0530 Subject: OMAP: I2C: split device registration and convert OMAP2+ to omap_device Split the OMAP1 and OMAP2+ platform_device build and register code. Convert the OMAP2+ variant to use omap_device. This patch was developed in collaboration with Rajendra Nayak . Signed-off-by: Paul Walmsley Signed-off-by: Rajendra Nayak Cc: Kevin Hilman Signed-off-by: Kevin Hilman --- include/linux/i2c-omap.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/i2c-omap.h b/include/linux/i2c-omap.h index 78ebf50..7472449 100644 --- a/include/linux/i2c-omap.h +++ b/include/linux/i2c-omap.h @@ -1,9 +1,14 @@ #ifndef __I2C_OMAP_H__ #define __I2C_OMAP_H__ +#include + struct omap_i2c_bus_platform_data { u32 clkrate; void (*set_mpu_wkup_lat)(struct device *dev, long set); + int (*device_enable) (struct platform_device *pdev); + int (*device_shutdown) (struct platform_device *pdev); + int (*device_idle) (struct platform_device *pdev); }; #endif -- cgit v1.1 From 074e61ec3751da9ab88ee66d3818574556c03489 Mon Sep 17 00:00:00 2001 From: James Morris Date: Wed, 10 Nov 2010 09:01:31 +1100 Subject: kernel: add roundup() code comment from akpm Add roundup() code comment from akpm. Signed-off-by: Andrew Morton Signed-off-by: James Morris --- include/linux/kernel.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index b526947..3f648d2 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -58,6 +58,8 @@ extern const char linux_proc_banner[]; #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) + +/* The `const' in roundup() prevents gcc-3.3 from calling __divdi3 */ #define roundup(x, y) ( \ { \ const typeof(y) __y = y; \ -- cgit v1.1 From c36940e678fc30779c99246c034deca1fed61ae4 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Tue, 2 Nov 2010 11:27:16 +0000 Subject: fbdev: sh_mobile_hdmi: add support for more precise HDMI clock configuration The HDMI clock has to be reconfigured for different video modes. However, the precision of the supplying SoC clock on SH-Mobile systems is often insufficient. This patch allows to additionally reconfigure the parent clock to achieve the optimal HDMI clock frequency, in case this is supported by the platform. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Paul Mundt --- include/video/sh_mobile_hdmi.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/video/sh_mobile_hdmi.h b/include/video/sh_mobile_hdmi.h index 1e1aa54..b569329 100644 --- a/include/video/sh_mobile_hdmi.h +++ b/include/video/sh_mobile_hdmi.h @@ -13,6 +13,7 @@ struct sh_mobile_lcdc_chan_cfg; struct device; +struct clk; /* * flags format @@ -33,6 +34,8 @@ struct sh_mobile_hdmi_info { struct sh_mobile_lcdc_chan_cfg *lcd_chan; struct device *lcd_dev; unsigned int flags; + long (*clk_optimize_parent)(unsigned long target, unsigned long *best_freq, + unsigned long *parent_freq); }; #endif -- cgit v1.1 From f6cd24777513fcc673d432cc29ef59881d3e4df1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 4 Nov 2010 11:13:48 +0100 Subject: irq: Better struct irqaction layout We currently use kmalloc-96 slab for struct irqaction allocations on 64bit arches. This is unfortunate because of possible false sharing and two cache lines accesses. Move 'name' and 'dir' fields at the end of the structure, and force a suitable alignement. Hot path fields now use one cache line on x86_64. Signed-off-by: Eric Dumazet Reviewed-by: Andi Kleen Cc: Peter Zijlstra LKML-Reference: <1288865628.2659.69.camel@edumazet-laptop> Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 79d0c4f..55e0d42 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -114,15 +114,15 @@ typedef irqreturn_t (*irq_handler_t)(int, void *); struct irqaction { irq_handler_t handler; unsigned long flags; - const char *name; void *dev_id; struct irqaction *next; int irq; - struct proc_dir_entry *dir; irq_handler_t thread_fn; struct task_struct *thread; unsigned long thread_flags; -}; + const char *name; + struct proc_dir_entry *dir; +} ____cacheline_internodealigned_in_smp; extern irqreturn_t no_action(int cpl, void *dev_id); -- cgit v1.1 From da1d39e3903bc35be2b5e8d2116fdd5d337244d4 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Tue, 9 Nov 2010 17:47:02 +0900 Subject: mmc, sh: Move constants to sh_mmcif.h This moves some constants from sh_mmcif.c to sh_mmcif.h so that they can be used in sh_mmcif_boot_init(). It also alters the definition of SOFT_RST_OFF from (0 << 31) to ~SOFT_RST_ON (= ~(1 << 31)). The former seems bogus. The latter is consistent with the code in sh_mmcif_boot_init(). Cc: Yusuke Goda Cc: Magnus Damm Signed-off-by: Simon Horman Signed-off-by: Paul Mundt --- include/linux/mmc/sh_mmcif.h | 39 ++++++++++++++++++++++++++++++++++----- 1 file changed, 34 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/mmc/sh_mmcif.h index 5c99da1..a6bfa52 100644 --- a/include/linux/mmc/sh_mmcif.h +++ b/include/linux/mmc/sh_mmcif.h @@ -59,6 +59,29 @@ struct sh_mmcif_plat_data { #define MMCIF_CE_HOST_STS2 0x0000004C #define MMCIF_CE_VERSION 0x0000007C +/* CE_BUF_ACC */ +#define BUF_ACC_DMAWEN (1 << 25) +#define BUF_ACC_DMAREN (1 << 24) +#define BUF_ACC_BUSW_32 (0 << 17) +#define BUF_ACC_BUSW_16 (1 << 17) +#define BUF_ACC_ATYP (1 << 16) + +/* CE_CLK_CTRL */ +#define CLK_ENABLE (1 << 24) /* 1: output mmc clock */ +#define CLK_CLEAR ((1 << 19) | (1 << 18) | (1 << 17) | (1 << 16)) +#define CLK_SUP_PCLK ((1 << 19) | (1 << 18) | (1 << 17) | (1 << 16)) +#define SRSPTO_256 ((1 << 13) | (0 << 12)) /* resp timeout */ +#define SRBSYTO_29 ((1 << 11) | (1 << 10) | \ + (1 << 9) | (1 << 8)) /* resp busy timeout */ +#define SRWDTO_29 ((1 << 7) | (1 << 6) | \ + (1 << 5) | (1 << 4)) /* read/write timeout */ +#define SCCSTO_29 ((1 << 3) | (1 << 2) | \ + (1 << 1) | (1 << 0)) /* ccs timeout */ + +/* CE_VERSION */ +#define SOFT_RST_ON (1 << 31) +#define SOFT_RST_OFF ~SOFT_RST_ON + static inline u32 sh_mmcif_readl(void __iomem *addr, int reg) { return readl(addr + reg); @@ -149,17 +172,23 @@ static inline void sh_mmcif_boot_init(void __iomem *base) /* reset */ tmp = sh_mmcif_readl(base, MMCIF_CE_VERSION); - sh_mmcif_writel(base, MMCIF_CE_VERSION, tmp | 0x80000000); - sh_mmcif_writel(base, MMCIF_CE_VERSION, tmp & ~0x80000000); + sh_mmcif_writel(base, MMCIF_CE_VERSION, tmp | SOFT_RST_ON); + sh_mmcif_writel(base, MMCIF_CE_VERSION, tmp & SOFT_RST_OFF); /* byte swap */ - sh_mmcif_writel(base, MMCIF_CE_BUF_ACC, 0x00010000); + sh_mmcif_writel(base, MMCIF_CE_BUF_ACC, BUF_ACC_ATYP); /* Set block size in MMCIF hardware */ sh_mmcif_writel(base, MMCIF_CE_BLOCK_SET, SH_MMCIF_BBS); - /* Enable the clock, set it to Bus clock/256 (about 325Khz)*/ - sh_mmcif_writel(base, MMCIF_CE_CLK_CTRL, 0x01072fff); + /* Enable the clock, set it to Bus clock/256 (about 325Khz). + * It is unclear where 0x70000 comes from or if it is even needed. + * It is there for byte-compatibility with code that is known to + * work. + */ + sh_mmcif_writel(base, MMCIF_CE_CLK_CTRL, + CLK_ENABLE | SRSPTO_256 | SRBSYTO_29 | SRWDTO_29 | + SCCSTO_29 | 0x70000); /* CMD0 */ sh_mmcif_boot_cmd(base, 0x00000040, 0); -- cgit v1.1 From 5e4f083f78d03e9f8d2e327daccde16976f9bb00 Mon Sep 17 00:00:00 2001 From: Yong Zhang Date: Sun, 24 Oct 2010 11:50:53 +0800 Subject: hrtimer: Remove stale comment on curr_timer curr_timer doesn't resident in struct hrtimer_cpu_base anymore. Signed-off-by: Yong Zhang LKML-Reference: <1287892253-2587-1-git-send-email-yong.zhang0@gmail.com> Signed-off-by: Thomas Gleixner --- include/linux/hrtimer.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index fd0c1b8..dd9954b 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -158,7 +158,6 @@ struct hrtimer_clock_base { * @lock: lock protecting the base and associated clock bases * and timers * @clock_base: array of clock bases for this cpu - * @curr_timer: the timer which is executing a callback right now * @expires_next: absolute time of the next event which was scheduled * via clock_set_next_event() * @hres_active: State of high resolution mode -- cgit v1.1 From 0eadcc09203349b11ca477ec367079b23d32ab91 Mon Sep 17 00:00:00 2001 From: Tatyana Brokhman Date: Mon, 1 Nov 2010 18:18:24 +0200 Subject: usb: USB3.0 ch11 definitions Adding hub SuperSpeed usb definitions as defined by ch10 of the USB3.0 spec. Signed-off-by: Tatyana Brokhman Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/ch11.h | 47 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/usb/hcd.h | 4 ++++ 2 files changed, 51 insertions(+) (limited to 'include') diff --git a/include/linux/usb/ch11.h b/include/linux/usb/ch11.h index 119194c..10ec069 100644 --- a/include/linux/usb/ch11.h +++ b/include/linux/usb/ch11.h @@ -28,6 +28,13 @@ #define HUB_STOP_TT 11 /* + * Hub class additional requests defined by USB 3.0 spec + * See USB 3.0 spec Table 10-6 + */ +#define HUB_SET_DEPTH 12 +#define HUB_GET_PORT_ERR_COUNT 13 + +/* * Hub Class feature numbers * See USB 2.0 spec Table 11-17 */ @@ -56,6 +63,20 @@ #define USB_PORT_FEAT_C_PORT_L1 23 /* + * Port feature selectors added by USB 3.0 spec. + * See USB 3.0 spec Table 10-7 + */ +#define USB_PORT_FEAT_LINK_STATE 5 +#define USB_PORT_FEAT_U1_TIMEOUT 23 +#define USB_PORT_FEAT_U2_TIMEOUT 24 +#define USB_PORT_FEAT_C_LINK_STATE 25 +#define USB_PORT_FEAT_C_CONFIG_ERR 26 +#define USB_PORT_FEAT_REMOTE_WAKE_MASK 27 +#define USB_PORT_FEAT_BH_PORT_RESET 28 +#define USB_PORT_FEAT_C_BH_PORT_RESET 29 +#define USB_PORT_FEAT_FORCE_LINKPM_ACCEPT 30 + +/* * Hub Status and Hub Change results * See USB 2.0 spec Table 11-19 and Table 11-20 */ @@ -84,6 +105,32 @@ struct usb_port_status { #define USB_PORT_STAT_SUPER_SPEED 0x8000 /* Linux-internal */ /* + * Additions to wPortStatus bit field from USB 3.0 + * See USB 3.0 spec Table 10-10 + */ +#define USB_PORT_STAT_LINK_STATE 0x01e0 +#define USB_SS_PORT_STAT_POWER 0x0200 +#define USB_PORT_STAT_SPEED_5GBPS 0x0000 +/* Valid only if port is enabled */ + +/* + * Definitions for PORT_LINK_STATE values + * (bits 5-8) in wPortStatus + */ +#define USB_SS_PORT_LS_U0 0x0000 +#define USB_SS_PORT_LS_U1 0x0020 +#define USB_SS_PORT_LS_U2 0x0040 +#define USB_SS_PORT_LS_U3 0x0060 +#define USB_SS_PORT_LS_SS_DISABLED 0x0080 +#define USB_SS_PORT_LS_RX_DETECT 0x00a0 +#define USB_SS_PORT_LS_SS_INACTIVE 0x00c0 +#define USB_SS_PORT_LS_POLLING 0x00e0 +#define USB_SS_PORT_LS_RECOVERY 0x0100 +#define USB_SS_PORT_LS_HOT_RESET 0x0120 +#define USB_SS_PORT_LS_COMP_MOD 0x0140 +#define USB_SS_PORT_LS_LOOPBACK 0x0160 + +/* * wPortChange bit field * See USB 2.0 spec Table 11-22 * Bits 0 to 4 shown, bits 5 to 15 are reserved diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 0b6e751..dd6ee49 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -471,6 +471,10 @@ extern void usb_ep0_reinit(struct usb_device *); /*-------------------------------------------------------------------------*/ +/* class requests from USB 3.0 hub spec, table 10-5 */ +#define SetHubDepth (0x3000 | HUB_SET_DEPTH) +#define GetPortErrorCount (0x8000 | HUB_GET_PORT_ERR_COUNT) + /* * Generic bandwidth allocation constants/support */ -- cgit v1.1 From 46b13fc5c0f239f36e84665c73087d5fa86bfd86 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 11 Nov 2010 06:57:19 +0000 Subject: neigh: reorder struct neighbour It is important to move nud_state outside of the often modified cache line (because of refcnt), to reduce false sharing in neigh_event_send() This is a followup of commit 0ed8ddf4045f (neigh: Protect neigh->ha[] with a seqlock) This gives a 7% speedup on routing test with IP route cache disabled. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/neighbour.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 55590ab..815b2ce 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -96,16 +96,16 @@ struct neighbour { struct neigh_parms *parms; unsigned long confirmed; unsigned long updated; - __u8 flags; - __u8 nud_state; - __u8 type; - __u8 dead; + rwlock_t lock; atomic_t refcnt; struct sk_buff_head arp_queue; struct timer_list timer; unsigned long used; atomic_t probes; - rwlock_t lock; + __u8 flags; + __u8 nud_state; + __u8 type; + __u8 dead; seqlock_t ha_lock; unsigned char ha[ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))]; struct hh_cache *hh; -- cgit v1.1 From 72cdd1d971c0deb1619c5c339270570c43647a78 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 11 Nov 2010 07:14:07 +0000 Subject: net: get rid of rtable->idev It seems idev field in struct rtable has no special purpose, but adding extra atomic ops. We hold refcounts on the device itself (using percpu data, so pretty cheap in current kernel). infiniband case is solved using dst.dev instead of idev->dev Removal of this field means routing without route cache is now using shared data, percpu data, and only potential contention is a pair of atomic ops on struct neighbour per forwarded packet. About 5% speedup on routing test. Signed-off-by: Eric Dumazet Cc: Herbert Xu Cc: Roland Dreier Cc: Sean Hefty Cc: Hal Rosenstock Signed-off-by: David S. Miller --- include/net/route.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/net/route.h b/include/net/route.h index 7e5e73b..cea533e 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -55,8 +55,6 @@ struct rtable { /* Cache lookup keys */ struct flowi fl; - struct in_device *idev; - int rt_genid; unsigned rt_flags; __u16 rt_type; -- cgit v1.1 From af3b8881f4c9852eefe9c7f1a997b3ecf580561b Mon Sep 17 00:00:00 2001 From: Russ Gorby Date: Tue, 26 Oct 2010 14:13:52 +0100 Subject: ifx6x60: SPI protocol driver for Infineon 6x60 modem Prototype driver for the IFX6x60 series of SPI attached modems by Jim Stanley and Russ Gorby Signed-off-by: Russ Gorby [Some reworking and a major cleanup] Signed-off-by: Alan Cox Signed-off-by: Greg Kroah-Hartman --- include/linux/spi/ifx_modem.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100644 include/linux/spi/ifx_modem.h (limited to 'include') diff --git a/include/linux/spi/ifx_modem.h b/include/linux/spi/ifx_modem.h new file mode 100644 index 0000000..a68f3b1 --- /dev/null +++ b/include/linux/spi/ifx_modem.h @@ -0,0 +1,14 @@ +#ifndef LINUX_IFX_MODEM_H +#define LINUX_IFX_MODEM_H + +struct ifx_modem_platform_data { + unsigned short rst_out; /* modem reset out */ + unsigned short pwr_on; /* power on */ + unsigned short rst_pmu; /* reset modem */ + unsigned short tx_pwr; /* modem power threshold */ + unsigned short srdy; /* SRDY */ + unsigned short mrdy; /* MRDY */ + unsigned short is_6160; /* Modem type */ +}; + +#endif -- cgit v1.1 From 304e12665a4a7b8b25dfe8c64fa4fd56a04a67ea Mon Sep 17 00:00:00 2001 From: Alexey Charkov Date: Mon, 8 Nov 2010 20:33:20 +0300 Subject: serial: Add support for UART on VIA VT8500 and compatibles This adds a driver for the serial ports found in VIA and WonderMedia Systems-on-Chip. Interrupt-driven FIFO operation is implemented. The hardware also supports pure register-based operation (which is slower) and DMA-based FIFO operation. As the FIFOs are only 16 bytes long, DMA operation is probably not worth the hassle. Signed-off-by: Alexey Charkov Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 212eb4c..41603d6 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -199,6 +199,9 @@ /* TI OMAP-UART */ #define PORT_OMAP 96 +/* VIA VT8500 SoC */ +#define PORT_VT8500 97 + #ifdef __KERNEL__ #include -- cgit v1.1 From c753796769e4fb0cd813b6e5801b3c01f4681d4f Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 11 Nov 2010 17:07:48 -0800 Subject: ipv4: Make rt->fl.iif tests lest obscure. When we test rt->fl.iif against zero, we're seeing if it's an output or an input route. Make that explicit with some helper functions. Signed-off-by: David S. Miller --- include/net/dn_route.h | 10 ++++++++++ include/net/route.h | 10 ++++++++++ 2 files changed, 20 insertions(+) (limited to 'include') diff --git a/include/net/dn_route.h b/include/net/dn_route.h index ccadab3..9b185df 100644 --- a/include/net/dn_route.h +++ b/include/net/dn_route.h @@ -80,6 +80,16 @@ struct dn_route { unsigned rt_type; }; +static inline bool dn_is_input_route(struct dn_route *rt) +{ + return rt->fl.iif != 0; +} + +static inline bool dn_is_output_route(struct dn_route *rt) +{ + return rt->fl.iif == 0; +} + extern void dn_route_init(void); extern void dn_route_cleanup(void); diff --git a/include/net/route.h b/include/net/route.h index cea533e..5cd46d1 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -71,6 +71,16 @@ struct rtable { struct inet_peer *peer; /* long-living peer info */ }; +static inline bool rt_is_input_route(struct rtable *rt) +{ + return rt->fl.iif != 0; +} + +static inline bool rt_is_output_route(struct rtable *rt) +{ + return rt->fl.iif == 0; +} + struct ip_rt_acct { __u32 o_bytes; __u32 o_packets; -- cgit v1.1 From 1d7138de878d1d4210727c1200193e69596f93b3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 12 Nov 2010 05:46:50 +0000 Subject: igmp: RCU conversion of in_dev->mc_list MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit in_dev->mc_list is protected by one rwlock (in_dev->mc_list_lock). This can easily be converted to a RCU protection. Writers hold RTNL, so mc_list_lock is removed, not replaced by a spinlock. Signed-off-by: Eric Dumazet Cc: Cypher Wu Cc: Américo Wang Signed-off-by: David S. Miller --- include/linux/igmp.h | 12 ++++++++---- include/linux/inetdevice.h | 5 ++--- include/net/inet_sock.h | 2 +- 3 files changed, 11 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 93fc244..7d16467 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -167,10 +167,10 @@ struct ip_sf_socklist { */ struct ip_mc_socklist { - struct ip_mc_socklist *next; + struct ip_mc_socklist __rcu *next_rcu; struct ip_mreqn multi; unsigned int sfmode; /* MCAST_{INCLUDE,EXCLUDE} */ - struct ip_sf_socklist *sflist; + struct ip_sf_socklist __rcu *sflist; struct rcu_head rcu; }; @@ -186,11 +186,14 @@ struct ip_sf_list { struct ip_mc_list { struct in_device *interface; __be32 multiaddr; + unsigned int sfmode; struct ip_sf_list *sources; struct ip_sf_list *tomb; - unsigned int sfmode; unsigned long sfcount[2]; - struct ip_mc_list *next; + union { + struct ip_mc_list *next; + struct ip_mc_list __rcu *next_rcu; + }; struct timer_list timer; int users; atomic_t refcnt; @@ -201,6 +204,7 @@ struct ip_mc_list { char loaded; unsigned char gsquery; /* check source marks? */ unsigned char crcount; + struct rcu_head rcu; }; /* V3 exponential field decoding */ diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index ccd5b07..380ba6b 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -52,9 +52,8 @@ struct in_device { atomic_t refcnt; int dead; struct in_ifaddr *ifa_list; /* IP ifaddr chain */ - rwlock_t mc_list_lock; - struct ip_mc_list *mc_list; /* IP multicast filter chain */ - int mc_count; /* Number of installed mcasts */ + struct ip_mc_list __rcu *mc_list; /* IP multicast filter chain */ + int mc_count; /* Number of installed mcasts */ spinlock_t mc_tomb_lock; struct ip_mc_list *mc_tomb; unsigned long mr_v1_seen; diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 1989cfd..8945f9f 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -141,7 +141,7 @@ struct inet_sock { nodefrag:1; int mc_index; __be32 mc_addr; - struct ip_mc_socklist *mc_list; + struct ip_mc_socklist __rcu *mc_list; struct { unsigned int flags; unsigned int fragsize; -- cgit v1.1 From e09b457bdb7e8d23fc54dcef0930ac697d8de895 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 13 Nov 2010 11:55:17 +0100 Subject: block: simplify holder symlink handling Code to manage symlinks in /sys/block/*/{holders|slaves} are overly complex with multiple holder considerations, redundant extra references to all involved kobjects, unused generic kobject holder support and unnecessary mixup with bd_claim/release functionalities. Strip it down to what's necessary (single gendisk holder) and make it use a separate interface. This is a step for cleaning up bd_claim/release. This patch makes dm-table slightly more complex but it will be simplified again with further changes. Signed-off-by: Tejun Heo Acked-by: Neil Brown Acked-by: Mike Snitzer Cc: dm-devel@redhat.com --- include/linux/fs.h | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 334d68a..66b7f2c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -663,7 +663,7 @@ struct block_device { void * bd_holder; int bd_holders; #ifdef CONFIG_SYSFS - struct list_head bd_holder_list; + struct gendisk * bd_holder_disk; /* for sysfs slave linkng */ #endif struct block_device * bd_contains; unsigned bd_block_size; @@ -2042,11 +2042,17 @@ extern int blkdev_put(struct block_device *, fmode_t); extern int bd_claim(struct block_device *, void *); extern void bd_release(struct block_device *); #ifdef CONFIG_SYSFS -extern int bd_claim_by_disk(struct block_device *, void *, struct gendisk *); -extern void bd_release_from_disk(struct block_device *, struct gendisk *); +extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); +extern void bd_unlink_disk_holder(struct block_device *bdev); #else -#define bd_claim_by_disk(bdev, holder, disk) bd_claim(bdev, holder) -#define bd_release_from_disk(bdev, disk) bd_release(bdev) +static inline int bd_link_disk_holder(struct block_device *bdev, + struct gendisk *disk) +{ + return 0; +} +static inline void bd_unlink_disk_holder(struct block_device *bdev) +{ +} #endif #endif -- cgit v1.1 From e525fd89d380c4a94c0d63913a1dd1a593ed25e7 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 13 Nov 2010 11:55:17 +0100 Subject: block: make blkdev_get/put() handle exclusive access Over time, block layer has accumulated a set of APIs dealing with bdev open, close, claim and release. * blkdev_get/put() are the primary open and close functions. * bd_claim/release() deal with exclusive open. * open/close_bdev_exclusive() are combination of open and claim and the other way around, respectively. * bd_link/unlink_disk_holder() to create and remove holder/slave symlinks. * open_by_devnum() wraps bdget() + blkdev_get(). The interface is a bit confusing and the decoupling of open and claim makes it impossible to properly guarantee exclusive access as in-kernel open + claim sequence can disturb the existing exclusive open even before the block layer knows the current open if for another exclusive access. Reorganize the interface such that, * blkdev_get() is extended to include exclusive access management. @holder argument is added and, if is @FMODE_EXCL specified, it will gain exclusive access atomically w.r.t. other exclusive accesses. * blkdev_put() is similarly extended. It now takes @mode argument and if @FMODE_EXCL is set, it releases an exclusive access. Also, when the last exclusive claim is released, the holder/slave symlinks are removed automatically. * bd_claim/release() and close_bdev_exclusive() are no longer necessary and either made static or removed. * bd_link_disk_holder() remains the same but bd_unlink_disk_holder() is no longer necessary and removed. * open_bdev_exclusive() becomes a simple wrapper around lookup_bdev() and blkdev_get(). It also has an unexpected extra bdev_read_only() test which probably should be moved into blkdev_get(). * open_by_devnum() is modified to take @holder argument and pass it to blkdev_get(). Most of bdev open/close operations are unified into blkdev_get/put() and most exclusive accesses are tested atomically at the open time (as it should). This cleans up code and removes some, both valid and invalid, but unnecessary all the same, corner cases. open_bdev_exclusive() and open_by_devnum() can use further cleanup - rename to blkdev_get_by_path() and blkdev_get_by_devt() and drop special features. Well, let's leave them for another day. Most conversions are straight-forward. drbd conversion is a bit more involved as there was some reordering, but the logic should stay the same. Signed-off-by: Tejun Heo Acked-by: Neil Brown Acked-by: Ryusuke Konishi Acked-by: Mike Snitzer Acked-by: Philipp Reisner Cc: Peter Osterlund Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Jan Kara Cc: Andrew Morton Cc: Andreas Dilger Cc: "Theodore Ts'o" Cc: Mark Fasheh Cc: Joel Becker Cc: Alex Elder Cc: Christoph Hellwig Cc: dm-devel@redhat.com Cc: drbd-dev@lists.linbit.com Cc: Leo Chen Cc: Scott Branden Cc: Chris Mason Cc: Steven Whitehouse Cc: Dave Kleikamp Cc: Joern Engel Cc: reiserfs-devel@vger.kernel.org Cc: Alexander Viro --- include/linux/fs.h | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 66b7f2c..1a033e8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2006,7 +2006,8 @@ extern struct block_device *bdgrab(struct block_device *bdev); extern void bd_set_size(struct block_device *, loff_t size); extern void bd_forget(struct inode *inode); extern void bdput(struct block_device *); -extern struct block_device *open_by_devnum(dev_t, fmode_t); +extern struct block_device *open_by_devnum(dev_t dev, fmode_t mode, + void *holder); extern void invalidate_bdev(struct block_device *); extern int sync_blockdev(struct block_device *bdev); extern struct super_block *freeze_bdev(struct block_device *); @@ -2037,22 +2038,16 @@ extern const struct file_operations def_fifo_fops; extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long); extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long); extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); -extern int blkdev_get(struct block_device *, fmode_t); -extern int blkdev_put(struct block_device *, fmode_t); -extern int bd_claim(struct block_device *, void *); -extern void bd_release(struct block_device *); +extern int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder); +extern int blkdev_put(struct block_device *bdev, fmode_t mode); #ifdef CONFIG_SYSFS extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); -extern void bd_unlink_disk_holder(struct block_device *bdev); #else static inline int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) { return 0; } -static inline void bd_unlink_disk_holder(struct block_device *bdev) -{ -} #endif #endif @@ -2089,7 +2084,6 @@ extern const char *__bdevname(dev_t, char *buffer); extern const char *bdevname(struct block_device *bdev, char *buffer); extern struct block_device *lookup_bdev(const char *); extern struct block_device *open_bdev_exclusive(const char *, fmode_t, void *); -extern void close_bdev_exclusive(struct block_device *, fmode_t); extern void blkdev_show(struct seq_file *,off_t); #else -- cgit v1.1 From d4d77629953eabd3c14f6fa5746f6b28babfc55f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 13 Nov 2010 11:55:18 +0100 Subject: block: clean up blkdev_get() wrappers and their users After recent blkdev_get() modifications, open_by_devnum() and open_bdev_exclusive() are simple wrappers around blkdev_get(). Replace them with blkdev_get_by_dev() and blkdev_get_by_path(). blkdev_get_by_dev() is identical to open_by_devnum(). blkdev_get_by_path() is slightly different in that it doesn't automatically add %FMODE_EXCL to @mode. All users are converted. Most conversions are mechanical and don't introduce any behavior difference. There are several exceptions. * btrfs now sets FMODE_EXCL in btrfs_device->mode, so there's no reason to OR it explicitly on blkdev_put(). * gfs2, nilfs2 and the generic mount_bdev() now set FMODE_EXCL in sb->s_mode. * With the above changes, sb->s_mode now always should contain FMODE_EXCL. WARN_ON_ONCE() added to kill_block_super() to detect errors. The new blkdev_get_*() functions are with proper docbook comments. While at it, add function description to blkdev_get() too. Signed-off-by: Tejun Heo Cc: Philipp Reisner Cc: Neil Brown Cc: Mike Snitzer Cc: Joern Engel Cc: Chris Mason Cc: Jan Kara Cc: "Theodore Ts'o" Cc: KONISHI Ryusuke Cc: reiserfs-devel@vger.kernel.org Cc: xfs-masters@oss.sgi.com Cc: Alexander Viro --- include/linux/fs.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 1a033e8..f485015 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2006,8 +2006,6 @@ extern struct block_device *bdgrab(struct block_device *bdev); extern void bd_set_size(struct block_device *, loff_t size); extern void bd_forget(struct inode *inode); extern void bdput(struct block_device *); -extern struct block_device *open_by_devnum(dev_t dev, fmode_t mode, - void *holder); extern void invalidate_bdev(struct block_device *); extern int sync_blockdev(struct block_device *bdev); extern struct super_block *freeze_bdev(struct block_device *); @@ -2039,6 +2037,10 @@ extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long); extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long); extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); extern int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder); +extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, + void *holder); +extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, + void *holder); extern int blkdev_put(struct block_device *bdev, fmode_t mode); #ifdef CONFIG_SYSFS extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); @@ -2083,7 +2085,6 @@ static inline void unregister_chrdev(unsigned int major, const char *name) extern const char *__bdevname(dev_t, char *buffer); extern const char *bdevname(struct block_device *bdev, char *buffer); extern struct block_device *lookup_bdev(const char *); -extern struct block_device *open_bdev_exclusive(const char *, fmode_t, void *); extern void blkdev_show(struct seq_file *,off_t); #else -- cgit v1.1 From 9fbbdde93231ad7f35c217aa6bbbc7995133f483 Mon Sep 17 00:00:00 2001 From: Erik Gilling Date: Thu, 11 Nov 2010 15:44:43 +0100 Subject: video: add fb_edid_add_monspecs for parsing extended edid information Modern monitors/tvs have more extended EDID information blocks which can contain extra detailed modes. This adds a fb_edid_add_monspecs function which drivers can use to parse those additions blocks. Signed-off-by: Erik Gilling Signed-off-by: Guennadi Liakhovetski Signed-off-by: Paul Mundt --- include/linux/fb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/fb.h b/include/linux/fb.h index 7fca3dc..6f0274d 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -1092,6 +1092,8 @@ extern int fb_parse_edid(unsigned char *edid, struct fb_var_screeninfo *var); extern const unsigned char *fb_firmware_edid(struct device *device); extern void fb_edid_to_monspecs(unsigned char *edid, struct fb_monspecs *specs); +extern void fb_edid_add_monspecs(unsigned char *edid, + struct fb_monspecs *specs); extern void fb_destroy_modedb(struct fb_videomode *modedb); extern int fb_find_mode_cvt(struct fb_videomode *mode, int margins, int rb); extern unsigned char *fb_ddc_read(struct i2c_adapter *adapter); -- cgit v1.1 From 0ad83f6882c41df1a7fa387086029e162038c1f2 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Thu, 11 Nov 2010 15:45:04 +0100 Subject: fbdev: when parsing E-EDID blocks, also use SVD entries Add parsing of E-EDID SVD entries. In this first version only a few CEA/EIA-861E modes are implemented, more can be added as needed. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Paul Mundt --- include/linux/fb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fb.h b/include/linux/fb.h index 6f0274d..e154a79 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -1151,6 +1151,7 @@ struct fb_videomode { extern const char *fb_mode_option; extern const struct fb_videomode vesa_modes[]; +extern const struct fb_videomode cea_modes[64]; struct fb_modelist { struct list_head list; -- cgit v1.1 From d83447f0944e73d690218d79c07762ffa4ceb9e4 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Sun, 14 Nov 2010 17:25:46 +0100 Subject: dccp ccid-2: Schedule Sync as out-of-band mechanism The problem with Ack Vectors is that i) their length is variable and can in principle grow quite large, ii) it is hard to predict exactly how large they will be. Due to the second point it seems not a good idea to reduce the MPS; in particular when on average there is enough room for the Ack Vector and an increase in length is momentarily due to some burst loss, after which the Ack Vector returns to its normal/average length. The solution taken by this patch is to subtract a minimum-expected Ack Vector length from the MPS, and to defer any larger Ack Vectors onto a separate Sync - but only if indeed there is no space left on the skb. This patch provides the infrastructure to schedule Sync-packets for transporting (urgent) out-of-band data. Its signalling is quicker than scheduling an Ack, since it does not need to wait for new application data. Signed-off-by: Gerrit Renker --- include/linux/dccp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 749f01c..eed52bc 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -462,6 +462,7 @@ struct dccp_ackvec; * @dccps_hc_rx_insert_options - receiver wants to add options when acking * @dccps_hc_tx_insert_options - sender wants to add options when sending * @dccps_server_timewait - server holds timewait state on close (RFC 4340, 8.3) + * @dccps_sync_scheduled - flag which signals "send out-of-band message soon" * @dccps_xmitlet - tasklet scheduled by the TX CCID to dequeue data packets * @dccps_xmit_timer - used by the TX CCID to delay sending (rate-based pacing) * @dccps_syn_rtt - RTT sample from Request/Response exchange (in usecs) @@ -503,6 +504,7 @@ struct dccp_sock { __u8 dccps_hc_rx_insert_options:1; __u8 dccps_hc_tx_insert_options:1; __u8 dccps_server_timewait:1; + __u8 dccps_sync_scheduled:1; struct tasklet_struct dccps_xmitlet; struct timer_list dccps_xmit_timer; }; -- cgit v1.1 From 58e998c6d23988490162cef0784b19ea274d90bb Mon Sep 17 00:00:00 2001 From: Jesse Gross Date: Fri, 29 Oct 2010 12:14:55 +0000 Subject: offloading: Force software GSO for multiple vlan tags. We currently use vlan_features to check for TSO support if there is a vlan tag. However, it's quite likely that the NIC is not able to do TSO when there is an arbitrary number of tags. Therefore if there is more than one tag (in-band or out-of-band), fall back to software emulation. Signed-off-by: Jesse Gross CC: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 578debb..6e4cfbc 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2239,6 +2239,8 @@ unsigned long netdev_fix_features(unsigned long features, const char *name); void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev); +int netif_get_vlan_features(struct sk_buff *skb, struct net_device *dev); + static inline int net_gso_ok(int features, int gso_type) { int feature = gso_type << NETIF_F_GSO_SHIFT; @@ -2254,10 +2256,7 @@ static inline int skb_gso_ok(struct sk_buff *skb, int features) static inline int netif_needs_gso(struct net_device *dev, struct sk_buff *skb) { if (skb_is_gso(skb)) { - int features = dev->features; - - if (skb->protocol == htons(ETH_P_8021Q) || skb->vlan_tci) - features &= dev->vlan_features; + int features = netif_get_vlan_features(skb, dev); return (!skb_gso_ok(skb, features) || unlikely(skb->ip_summed != CHECKSUM_PARTIAL)); -- cgit v1.1 From 2e48928d8a0f38c1b5c81eb3f1294de8a6382c68 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Wed, 20 Oct 2010 10:16:58 -0700 Subject: rfkill: remove dead code The following code is defined but never used. Signed-off-by: Stephen Hemminger Signed-off-by: John W. Linville --- include/linux/rfkill.h | 31 ------------------------------- 1 file changed, 31 deletions(-) (limited to 'include') diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h index 08c32e4..c6c6084 100644 --- a/include/linux/rfkill.h +++ b/include/linux/rfkill.h @@ -354,37 +354,6 @@ static inline bool rfkill_blocked(struct rfkill *rfkill) } #endif /* RFKILL || RFKILL_MODULE */ - -#ifdef CONFIG_RFKILL_LEDS -/** - * rfkill_get_led_trigger_name - Get the LED trigger name for the button's LED. - * This function might return a NULL pointer if registering of the - * LED trigger failed. Use this as "default_trigger" for the LED. - */ -const char *rfkill_get_led_trigger_name(struct rfkill *rfkill); - -/** - * rfkill_set_led_trigger_name -- set the LED trigger name - * @rfkill: rfkill struct - * @name: LED trigger name - * - * This function sets the LED trigger name of the radio LED - * trigger that rfkill creates. It is optional, but if called - * must be called before rfkill_register() to be effective. - */ -void rfkill_set_led_trigger_name(struct rfkill *rfkill, const char *name); -#else -static inline const char *rfkill_get_led_trigger_name(struct rfkill *rfkill) -{ - return NULL; -} - -static inline void -rfkill_set_led_trigger_name(struct rfkill *rfkill, const char *name) -{ -} -#endif - #endif /* __KERNEL__ */ #endif /* RFKILL_H */ -- cgit v1.1 From 749b527b21465fb079796c03ffb4302584dc31c1 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Wed, 20 Oct 2010 10:18:54 -0700 Subject: cfg80211: fix allowing country IEs for WIPHY_FLAG_STRICT_REGULATORY We should be enabling country IE hints for WIPHY_FLAG_STRICT_REGULATORY even if we haven't yet recieved regulatory domain hint for the driver if it needed one. Without this Country IEs are not passed on to drivers that have set WIPHY_FLAG_STRICT_REGULATORY, today this is just all Atheros chipset drivers: ath5k, ath9k, ar9170, carl9170. This was part of the original design, however it was completely overlooked... Cc: Easwar Krishnan Cc: stable@kernel.org Signed-off-by: Luis R. Rodriguez Signed-off-by: John W. Linville --- include/net/cfg80211.h | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 2a7936d..e5702f5 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1321,13 +1321,14 @@ struct cfg80211_ops { * initiator is %REGDOM_SET_BY_CORE). * @WIPHY_FLAG_STRICT_REGULATORY: tells us the driver for this device will * ignore regulatory domain settings until it gets its own regulatory - * domain via its regulatory_hint(). After its gets its own regulatory - * domain it will only allow further regulatory domain settings to - * further enhance compliance. For example if channel 13 and 14 are - * disabled by this regulatory domain no user regulatory domain can - * enable these channels at a later time. This can be used for devices - * which do not have calibration information gauranteed for frequencies - * or settings outside of its regulatory domain. + * domain via its regulatory_hint() unless the regulatory hint is + * from a country IE. After its gets its own regulatory domain it will + * only allow further regulatory domain settings to further enhance + * compliance. For example if channel 13 and 14 are disabled by this + * regulatory domain no user regulatory domain can enable these channels + * at a later time. This can be used for devices which do not have + * calibration information guaranteed for frequencies or settings + * outside of its regulatory domain. * @WIPHY_FLAG_DISABLE_BEACON_HINTS: enable this if your driver needs to ensure * that passive scan flags and beaconing flags may not be lifted by * cfg80211 due to regulatory beacon hints. For more information on beacon -- cgit v1.1 From ca4ffe8f2848169a8ded0ea8a60b2d81925564c9 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Wed, 20 Oct 2010 10:18:55 -0700 Subject: cfg80211: fix disabling channels based on hints After a module loads you will have loaded the world roaming regulatory domain or a custom regulatory domain. Further regulatory hints are welcomed and should be respected unless the regulatory hint is coming from a country IE as the IEEE spec allows for a country IE to be a subset of what is allowed by the local regulatory agencies. So disable all channels that do not fit a regulatory domain sent from a unless the hint is from a country IE and the country IE had no information about the band we are currently processing. This fixes a few regulatory issues, for example for drivers that depend on CRDA and had no 5 GHz freqencies allowed were not properly disabling 5 GHz at all, furthermore it also allows users to restrict devices further as was intended. If you recieve a country IE upon association we will also disable the channels that are not allowed if the country IE had at least one channel on the respective band we are procesing. This was the original intention behind this design but it was completely overlooked... Cc: David Quan Cc: Jouni Malinen cc: Easwar Krishnan Cc: stable@kernel.org Signed-off-by: Luis R. Rodriguez Signed-off-by: John W. Linville --- include/linux/nl80211.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 0edb256..fb877b5 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -1307,7 +1307,11 @@ enum nl80211_bitrate_attr { * wireless core it thinks its knows the regulatory domain we should be in. * @NL80211_REGDOM_SET_BY_COUNTRY_IE: the wireless core has received an * 802.11 country information element with regulatory information it - * thinks we should consider. + * thinks we should consider. cfg80211 only processes the country + * code from the IE, and relies on the regulatory domain information + * structure pased by userspace (CRDA) from our wireless-regdb. + * If a channel is enabled but the country code indicates it should + * be disabled we disable the channel and re-enable it upon disassociation. */ enum nl80211_reg_initiator { NL80211_REGDOM_SET_BY_CORE, -- cgit v1.1 From c8aea565e8f715d9f10064b1cbfbc15bf75df501 Mon Sep 17 00:00:00 2001 From: Gery Kahn Date: Tue, 5 Oct 2010 16:09:05 +0200 Subject: wl1271: ref_clock cosmetic changes Cosmetic cleanup for ref_clock code while configured by board. Signed-off-by: Gery Kahn Signed-off-by: Luciano Coelho --- include/linux/wl12xx.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/wl12xx.h b/include/linux/wl12xx.h index 4f902e1..bebb8ef 100644 --- a/include/linux/wl12xx.h +++ b/include/linux/wl12xx.h @@ -24,6 +24,14 @@ #ifndef _LINUX_WL12XX_H #define _LINUX_WL12XX_H +/* The board reference clock values */ +enum { + WL12XX_REFCLOCK_19 = 0, /* 19.2 MHz */ + WL12XX_REFCLOCK_26 = 1, /* 26 MHz */ + WL12XX_REFCLOCK_38 = 2, /* 38.4 MHz */ + WL12XX_REFCLOCK_54 = 3, /* 54 MHz */ +}; + struct wl12xx_platform_data { void (*set_power)(bool enable); /* SDIO only: IRQ number if WLAN_IRQ line is used, 0 for SDIO IRQs */ -- cgit v1.1 From 7919a57bc608140aa8614c19eac40c6916fb61d2 Mon Sep 17 00:00:00 2001 From: Andreas Herrmann Date: Mon, 30 Aug 2010 19:04:01 +0000 Subject: bitops: Provide generic sign_extend32 function This patch moves code out from wireless drivers where two different functions are defined in three code locations for the same purpose and provides a common function to sign extend a 32-bit value. Signed-off-by: Andreas Herrmann Signed-off-by: John W. Linville --- include/linux/bitops.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 827cc95..2184c6b 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -109,6 +109,17 @@ static inline __u8 ror8(__u8 word, unsigned int shift) return (word >> shift) | (word << (8 - shift)); } +/** + * sign_extend32 - sign extend a 32-bit value using specified bit as sign-bit + * @value: value to sign extend + * @index: 0 based bit index (0<=index<32) to sign bit + */ +static inline __s32 sign_extend32(__u32 value, int index) +{ + __u8 shift = 31 - index; + return (__s32)(value << shift) >> shift; +} + static inline unsigned fls_long(unsigned long l) { if (sizeof(l) == 4) -- cgit v1.1 From cc9ff19da9bf76a2f70bcb80225a1c587c162e52 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timo=20Ter=C3=A4s?= Date: Wed, 3 Nov 2010 04:41:38 +0000 Subject: xfrm: use gre key as flow upper protocol info MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The GRE Key field is intended to be used for identifying an individual traffic flow within a tunnel. It is useful to be able to have XFRM policy selector matches to have different policies for different GRE tunnels. Signed-off-by: Timo Teräs Signed-off-by: David S. Miller --- include/net/flow.h | 2 ++ include/net/xfrm.h | 6 ++++++ 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/include/net/flow.h b/include/net/flow.h index 0ac3fb5..7196e68 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -67,6 +67,7 @@ struct flowi { } dnports; __be32 spi; + __be32 gre_key; struct { __u8 type; @@ -78,6 +79,7 @@ struct flowi { #define fl_icmp_code uli_u.icmpt.code #define fl_ipsec_spi uli_u.spi #define fl_mh_type uli_u.mht.type +#define fl_gre_key uli_u.gre_key __u32 secid; /* used by xfrm; see secid.txt */ } __attribute__((__aligned__(BITS_PER_LONG/8))); diff --git a/include/net/xfrm.h b/include/net/xfrm.h index bcfb6b2..54b2832 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -805,6 +805,9 @@ __be16 xfrm_flowi_sport(struct flowi *fl) case IPPROTO_MH: port = htons(fl->fl_mh_type); break; + case IPPROTO_GRE: + port = htonl(fl->fl_gre_key) >> 16; + break; default: port = 0; /*XXX*/ } @@ -826,6 +829,9 @@ __be16 xfrm_flowi_dport(struct flowi *fl) case IPPROTO_ICMPV6: port = htons(fl->fl_icmp_code); break; + case IPPROTO_GRE: + port = htonl(fl->fl_gre_key) & 0xffff; + break; default: port = 0; /*XXX*/ } -- cgit v1.1 From fe8222406c8277a21172479d3a8283d31c209028 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Tue, 9 Nov 2010 10:47:38 +0000 Subject: net: Simplify RX queue allocation This patch move RX queue allocation to alloc_netdev_mq and freeing of the queues to free_netdev (symmetric to TX queue allocation). Each kobject RX queue takes a reference to the queue's device so that the device can't be freed before all the kobjects have been released-- this obviates the need for reference counts specific to RX queues. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6e4cfbc..fccb11f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -592,8 +592,7 @@ struct netdev_rx_queue { struct rps_map __rcu *rps_map; struct rps_dev_flow_table __rcu *rps_flow_table; struct kobject kobj; - struct netdev_rx_queue *first; - atomic_t count; + struct net_device *dev; } ____cacheline_aligned_in_smp; #endif /* CONFIG_RPS */ -- cgit v1.1 From c59504ebc5baa628706d10c2d3c7e1f4bc3c2147 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Sun, 14 Nov 2010 17:04:57 +0000 Subject: include/linux/if_macvlan.h: Remove unnecessary semicolons Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- include/linux/if_macvlan.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 8a2fd66..ac96a2d 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -69,7 +69,7 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan, rx_stats = this_cpu_ptr(vlan->rx_stats); if (likely(success)) { u64_stats_update_begin(&rx_stats->syncp); - rx_stats->rx_packets++;; + rx_stats->rx_packets++; rx_stats->rx_bytes += len; if (multicast) rx_stats->rx_multicast++; -- cgit v1.1 From d577f1ccdd8ae8bfbe6063eb2ba2a350259e9031 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Sun, 14 Nov 2010 17:04:58 +0000 Subject: include/net/caif/cfctrl.h: Remove unnecessary semicolons Signed-off-by: Joe Perches Acked-by: Sjur Braendeland Signed-off-by: David S. Miller --- include/net/caif/cfctrl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/caif/cfctrl.h b/include/net/caif/cfctrl.h index 9402543..e54f639 100644 --- a/include/net/caif/cfctrl.h +++ b/include/net/caif/cfctrl.h @@ -51,7 +51,7 @@ struct cfctrl_rsp { void (*restart_rsp)(void); void (*radioset_rsp)(void); void (*reject_rsp)(struct cflayer *layer, u8 linkid, - struct cflayer *client_layer);; + struct cflayer *client_layer); }; /* Link Setup Parameters for CAIF-Links. */ -- cgit v1.1 From a386f99025f13b32502fe5dedf223c20d7283826 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 15 Nov 2010 06:38:11 +0000 Subject: bridge: add proper RCU annotation to should_route_hook Add br_should_route_hook_t typedef, this is the only way we can get a clean RCU implementation for function pointer. Move route_hook to location where it is used. Signed-off-by: Eric Dumazet Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/if_bridge.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 0d241a5..f7e73c3 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -102,7 +102,9 @@ struct __fdb_entry { #include extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *)); -extern int (*br_should_route_hook)(struct sk_buff *skb); + +typedef int (*br_should_route_hook_t)(struct sk_buff *skb); +extern br_should_route_hook_t __rcu *br_should_route_hook; #endif -- cgit v1.1 From 61391cde9eefac5cfcf6d214aa80c77e58b1626b Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 15 Nov 2010 06:38:12 +0000 Subject: netdev: add rcu annotations to receive handler hook Suggested by Eric's bridge RCU changes. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fccb11f..b45c1b8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -994,8 +994,8 @@ struct net_device { unsigned int real_num_rx_queues; #endif - rx_handler_func_t *rx_handler; - void *rx_handler_data; + rx_handler_func_t __rcu *rx_handler; + void __rcu *rx_handler_data; struct netdev_queue __rcu *ingress_queue; -- cgit v1.1 From 96f8d864afd646e4a52ea55462b7d83e3b94fd5c Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Tue, 16 Nov 2010 14:00:24 +0900 Subject: fbdev: move udlfb out of staging. udlfb has undergone a fair bit of cleanup recently and is effectively at the point where it can be liberated from staging purgatory and promoted to a real driver. The outstanding cleanups are all minor, with some of them dependent on drivers/video headers, so these will be done incrementally from udlfb's new home. Requested-by: Bernie Thompson Signed-off-by: Paul Mundt --- include/video/udlfb.h | 117 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 117 insertions(+) create mode 100644 include/video/udlfb.h (limited to 'include') diff --git a/include/video/udlfb.h b/include/video/udlfb.h new file mode 100644 index 0000000..6f9785e --- /dev/null +++ b/include/video/udlfb.h @@ -0,0 +1,117 @@ +#ifndef UDLFB_H +#define UDLFB_H + +/* + * TODO: Propose standard fb.h ioctl for reporting damage, + * using _IOWR() and one of the existing area structs from fb.h + * Consider these ioctls deprecated, but they're still used by the + * DisplayLink X server as yet - need both to be modified in tandem + * when new ioctl(s) are ready. + */ +#define DLFB_IOCTL_RETURN_EDID 0xAD +#define DLFB_IOCTL_REPORT_DAMAGE 0xAA +struct dloarea { + int x, y; + int w, h; + int x2, y2; +}; + +struct urb_node { + struct list_head entry; + struct dlfb_data *dev; + struct delayed_work release_urb_work; + struct urb *urb; +}; + +struct urb_list { + struct list_head list; + spinlock_t lock; + struct semaphore limit_sem; + int available; + int count; + size_t size; +}; + +struct dlfb_data { + struct usb_device *udev; + struct device *gdev; /* &udev->dev */ + struct fb_info *info; + struct urb_list urbs; + struct kref kref; + char *backing_buffer; + int fb_count; + bool virtualized; /* true when physical usb device not present */ + struct delayed_work free_framebuffer_work; + atomic_t usb_active; /* 0 = update virtual buffer, but no usb traffic */ + atomic_t lost_pixels; /* 1 = a render op failed. Need screen refresh */ + char *edid; /* null until we read edid from hw or get from sysfs */ + size_t edid_size; + int sku_pixel_limit; + int base16; + int base8; + u32 pseudo_palette[256]; + /* blit-only rendering path metrics, exposed through sysfs */ + atomic_t bytes_rendered; /* raw pixel-bytes driver asked to render */ + atomic_t bytes_identical; /* saved effort with backbuffer comparison */ + atomic_t bytes_sent; /* to usb, after compression including overhead */ + atomic_t cpu_kcycles_used; /* transpired during pixel processing */ +}; + +#define NR_USB_REQUEST_I2C_SUB_IO 0x02 +#define NR_USB_REQUEST_CHANNEL 0x12 + +/* -BULK_SIZE as per usb-skeleton. Can we get full page and avoid overhead? */ +#define BULK_SIZE 512 +#define MAX_TRANSFER (PAGE_SIZE*16 - BULK_SIZE) +#define WRITES_IN_FLIGHT (4) + +#define MIN_EDID_SIZE 128 +#define MAX_EDID_SIZE 128 + +#define MAX_VENDOR_DESCRIPTOR_SIZE 256 + +#define GET_URB_TIMEOUT HZ +#define FREE_URB_TIMEOUT (HZ*2) + +#define BPP 2 +#define MAX_CMD_PIXELS 255 + +#define RLX_HEADER_BYTES 7 +#define MIN_RLX_PIX_BYTES 4 +#define MIN_RLX_CMD_BYTES (RLX_HEADER_BYTES + MIN_RLX_PIX_BYTES) + +#define RLE_HEADER_BYTES 6 +#define MIN_RLE_PIX_BYTES 3 +#define MIN_RLE_CMD_BYTES (RLE_HEADER_BYTES + MIN_RLE_PIX_BYTES) + +#define RAW_HEADER_BYTES 6 +#define MIN_RAW_PIX_BYTES 2 +#define MIN_RAW_CMD_BYTES (RAW_HEADER_BYTES + MIN_RAW_PIX_BYTES) + +#define DL_DEFIO_WRITE_DELAY 5 /* fb_deferred_io.delay in jiffies */ +#define DL_DEFIO_WRITE_DISABLE (HZ*60) /* "disable" with long delay */ + +/* remove these once align.h patch is taken into kernel */ +#define DL_ALIGN_UP(x, a) ALIGN(x, a) +#define DL_ALIGN_DOWN(x, a) ALIGN(x-(a-1), a) + +/* remove once this gets added to sysfs.h */ +#define __ATTR_RW(attr) __ATTR(attr, 0644, attr##_show, attr##_store) + +/* + * udlfb is both a usb device, and a framebuffer device. + * They may exist at the same time, but during various stages + * inactivity, teardown, or "virtual" operation, only one or the + * other will exist (one will outlive the other). So we can't + * call the dev_*() macros, because we don't have a stable dev object. + */ +#define dl_err(format, arg...) \ + pr_err("udlfb: " format, ## arg) +#define dl_warn(format, arg...) \ + pr_warning("udlfb: " format, ## arg) +#define dl_notice(format, arg...) \ + pr_notice("udlfb: " format, ## arg) +#define dl_info(format, arg...) \ + pr_info("udlfb: " format, ## arg) + +#endif -- cgit v1.1 From d07335e51df0c6dec202d315fc4f1f7e100eec4e Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Tue, 16 Nov 2010 12:52:38 +0100 Subject: block: Rename "block_remap" tracepoint to "block_bio_remap" to clarify the event. Signed-off-by: Kiyoshi Ueda Signed-off-by: Jun'ichi Nomura Signed-off-by: Mike Snitzer Signed-off-by: Jens Axboe --- include/trace/events/block.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/trace/events/block.h b/include/trace/events/block.h index d8ce278..b56c65d 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -486,16 +486,16 @@ TRACE_EVENT(block_split, ); /** - * block_remap - map request for a partition to the raw device + * block_bio_remap - map request for a logical device to the raw device * @q: queue holding the operation * @bio: revised operation * @dev: device for the operation * @from: original sector for the operation * - * An operation for a partition on a block device has been mapped to the + * An operation for a logical device has been mapped to the * raw block device. */ -TRACE_EVENT(block_remap, +TRACE_EVENT(block_bio_remap, TP_PROTO(struct request_queue *q, struct bio *bio, dev_t dev, sector_t from), -- cgit v1.1 From 073ef1f6e508688392580e4f35dcad9aabd1e100 Mon Sep 17 00:00:00 2001 From: Lionel Debroux Date: Tue, 9 Nov 2010 21:48:49 +0100 Subject: hibernation: constify platform_hibernation_ops Patch against mainline. Changes since v1: added one hunk; no longer adding "const" qualifier to pointers in platform_hibernation_ops after seeing b4144e4f6e3b448d322095ca08af393682a69e33. Signed-off-by: Jiri Kosina --- include/linux/suspend.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 2669751..40ead94 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -245,7 +245,7 @@ extern void swsusp_set_page_free(struct page *); extern void swsusp_unset_page_free(struct page *); extern unsigned long get_safe_page(gfp_t gfp_mask); -extern void hibernation_set_ops(struct platform_hibernation_ops *ops); +extern void hibernation_set_ops(const struct platform_hibernation_ops *ops); extern int hibernate(void); extern bool system_entering_hibernation(void); #else /* CONFIG_HIBERNATION */ @@ -253,7 +253,7 @@ static inline int swsusp_page_is_forbidden(struct page *p) { return 0; } static inline void swsusp_set_page_free(struct page *p) {} static inline void swsusp_unset_page_free(struct page *p) {} -static inline void hibernation_set_ops(struct platform_hibernation_ops *ops) {} +static inline void hibernation_set_ops(const struct platform_hibernation_ops *ops) {} static inline int hibernate(void) { return -ENOSYS; } static inline bool system_entering_hibernation(void) { return false; } #endif /* CONFIG_HIBERNATION */ -- cgit v1.1 From 2f55ac072f5344519348c0c94b3d2f4cca46847b Mon Sep 17 00:00:00 2001 From: Lionel Debroux Date: Tue, 16 Nov 2010 14:14:02 +0100 Subject: suspend: constify platform_suspend_ops While at it, fix two checkpatch errors. Several non-const struct instances constified by this patch were added after the introduction of platform_suspend_ops in checkpatch.pl's list of "should be const" structs (79404849e90a41ea2109bd0e2f7c7164b0c4ce73). Patch against mainline. Inspired by hunks of the grsecurity patch, updated for newer kernels. Signed-off-by: Lionel Debroux Acked-by: Ingo Molnar Signed-off-by: Jiri Kosina --- include/linux/suspend.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 40ead94..f45f3cc 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -122,7 +122,7 @@ struct platform_suspend_ops { * suspend_set_ops - set platform dependent suspend operations * @ops: The new suspend operations to set. */ -extern void suspend_set_ops(struct platform_suspend_ops *ops); +extern void suspend_set_ops(const struct platform_suspend_ops *ops); extern int suspend_valid_only_mem(suspend_state_t state); /** @@ -147,7 +147,7 @@ extern int pm_suspend(suspend_state_t state); #else /* !CONFIG_SUSPEND */ #define suspend_valid_only_mem NULL -static inline void suspend_set_ops(struct platform_suspend_ops *ops) {} +static inline void suspend_set_ops(const struct platform_suspend_ops *ops) {} static inline int pm_suspend(suspend_state_t state) { return -ENOSYS; } #endif /* !CONFIG_SUSPEND */ -- cgit v1.1 From 3654654f7aa79a37dde130afb7409c55b11807e7 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Tue, 16 Nov 2010 09:52:32 -0800 Subject: netlink: let nlmsg and nla functions take pointer-to-const args The changed functions do not modify the NL messages and/or attributes at all. They should use const (similar to strchr), so that callers which have a const nlmsg/nlattr around can make use of them without casting. While at it, constify a data array. Signed-off-by: Jan Engelhardt Signed-off-by: David S. Miller --- include/net/netlink.h | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/netlink.h b/include/net/netlink.h index 9801c55..373f1a9 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -225,13 +225,15 @@ extern int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 pid, unsigned int group, int report, gfp_t flags); -extern int nla_validate(struct nlattr *head, int len, int maxtype, +extern int nla_validate(const struct nlattr *head, + int len, int maxtype, const struct nla_policy *policy); -extern int nla_parse(struct nlattr *tb[], int maxtype, - struct nlattr *head, int len, +extern int nla_parse(struct nlattr **tb, int maxtype, + const struct nlattr *head, int len, const struct nla_policy *policy); extern int nla_policy_len(const struct nla_policy *, int); -extern struct nlattr * nla_find(struct nlattr *head, int len, int attrtype); +extern struct nlattr * nla_find(const struct nlattr *head, + int len, int attrtype); extern size_t nla_strlcpy(char *dst, const struct nlattr *nla, size_t dstsize); extern int nla_memcpy(void *dest, const struct nlattr *src, int count); @@ -346,7 +348,8 @@ static inline int nlmsg_ok(const struct nlmsghdr *nlh, int remaining) * Returns the next netlink message in the message stream and * decrements remaining by the size of the current message. */ -static inline struct nlmsghdr *nlmsg_next(struct nlmsghdr *nlh, int *remaining) +static inline struct nlmsghdr * +nlmsg_next(const struct nlmsghdr *nlh, int *remaining) { int totlen = NLMSG_ALIGN(nlh->nlmsg_len); @@ -398,7 +401,8 @@ static inline struct nlattr *nlmsg_find_attr(const struct nlmsghdr *nlh, * @maxtype: maximum attribute type to be expected * @policy: validation policy */ -static inline int nlmsg_validate(struct nlmsghdr *nlh, int hdrlen, int maxtype, +static inline int nlmsg_validate(const struct nlmsghdr *nlh, + int hdrlen, int maxtype, const struct nla_policy *policy) { if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) @@ -727,7 +731,8 @@ static inline struct nlattr *nla_next(const struct nlattr *nla, int *remaining) * * Returns the first attribute which matches the specified type. */ -static inline struct nlattr *nla_find_nested(struct nlattr *nla, int attrtype) +static inline struct nlattr * +nla_find_nested(const struct nlattr *nla, int attrtype) { return nla_find(nla_data(nla), nla_len(nla), attrtype); } @@ -1032,7 +1037,7 @@ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start) * * Returns 0 on success or a negative error code. */ -static inline int nla_validate_nested(struct nlattr *start, int maxtype, +static inline int nla_validate_nested(const struct nlattr *start, int maxtype, const struct nla_policy *policy) { return nla_validate(nla_data(start), nla_len(start), maxtype, policy); -- cgit v1.1 From 8ffab51b3dfc54876f145f15b351c41f3f703195 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 10 Nov 2010 21:14:04 +0000 Subject: macvlan: lockless tx path macvlan is a stacked device, like tunnels. We should use the lockless mechanism we are using in tunnels and loopback. This patch completely removes locking in TX path. tx stat counters are added into existing percpu stat structure, renamed from rx_stats to pcpu_stats. Note : this reverts commit 2c11455321f37 (macvlan: add multiqueue capability) Note : rx_errors converted to a 32bit counter, like tx_dropped, since they dont need 64bit range. Signed-off-by: Eric Dumazet Cc: Patrick McHardy Cc: Ben Greear Cc: Ben Hutchings Acked-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/if_macvlan.h | 34 ++++++++++++++++++++-------------- 1 file changed, 20 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index ac96a2d..e28b2e4 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -25,19 +25,25 @@ struct macvlan_port; struct macvtap_queue; /** - * struct macvlan_rx_stats - MACVLAN percpu rx stats + * struct macvlan_pcpu_stats - MACVLAN percpu stats * @rx_packets: number of received packets * @rx_bytes: number of received bytes * @rx_multicast: number of received multicast packets + * @tx_packets: number of transmitted packets + * @tx_bytes: number of transmitted bytes * @syncp: synchronization point for 64bit counters - * @rx_errors: number of errors + * @rx_errors: number of rx errors + * @tx_dropped: number of tx dropped packets */ -struct macvlan_rx_stats { +struct macvlan_pcpu_stats { u64 rx_packets; u64 rx_bytes; u64 rx_multicast; + u64 tx_packets; + u64 tx_bytes; struct u64_stats_sync syncp; - unsigned long rx_errors; + u32 rx_errors; + u32 tx_dropped; }; /* @@ -52,7 +58,7 @@ struct macvlan_dev { struct hlist_node hlist; struct macvlan_port *port; struct net_device *lowerdev; - struct macvlan_rx_stats __percpu *rx_stats; + struct macvlan_pcpu_stats __percpu *pcpu_stats; enum macvlan_mode mode; int (*receive)(struct sk_buff *skb); int (*forward)(struct net_device *dev, struct sk_buff *skb); @@ -64,18 +70,18 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan, unsigned int len, bool success, bool multicast) { - struct macvlan_rx_stats *rx_stats; - - rx_stats = this_cpu_ptr(vlan->rx_stats); if (likely(success)) { - u64_stats_update_begin(&rx_stats->syncp); - rx_stats->rx_packets++; - rx_stats->rx_bytes += len; + struct macvlan_pcpu_stats *pcpu_stats; + + pcpu_stats = this_cpu_ptr(vlan->pcpu_stats); + u64_stats_update_begin(&pcpu_stats->syncp); + pcpu_stats->rx_packets++; + pcpu_stats->rx_bytes += len; if (multicast) - rx_stats->rx_multicast++; - u64_stats_update_end(&rx_stats->syncp); + pcpu_stats->rx_multicast++; + u64_stats_update_end(&pcpu_stats->syncp); } else { - rx_stats->rx_errors++; + this_cpu_inc(vlan->pcpu_stats->rx_errors); } } -- cgit v1.1 From c31504dc0d1dc853dcee509d9999169a9097a717 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 15 Nov 2010 19:58:26 +0000 Subject: udp: use atomic_inc_not_zero_hint UDP sockets refcount is usually 2, unless an incoming frame is going to be queued in receive or backlog queue. Using atomic_inc_not_zero_hint() permits to reduce latency, because processor issues less memory transactions. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index a6338d0..eb0c1f5 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -57,7 +57,7 @@ #include #include -#include +#include #include #include -- cgit v1.1 From b178bb3dfc30d9555bdd2401e95af98e23e83e10 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 16 Nov 2010 05:56:04 +0000 Subject: net: reorder struct sock fields Right now, fields in struct sock are not optimally ordered, because each path (RX softirq, TX completion, RX user, TX user) has to touch fields that are contained in many different cache lines. The really critical thing is to shrink number of cache lines that are used at RX softirq time : CPU handling softirqs for a device can receive many frames per second for many sockets. If load is too big, we can drop frames at NIC level. RPS or multiqueue cards can help, but better reduce latency if possible. This patch starts with UDP protocol, then additional patches will try to reduce latencies of other ones as well. At RX softirq time, fields of interest for UDP protocol are : (not counting ones in inet struct for the lookup) Read/Written: sk_refcnt (atomic increment/decrement) sk_rmem_alloc & sk_backlog.len (to check if there is room in queues) sk_receive_queue sk_backlog (if socket locked by user program) sk_rxhash sk_forward_alloc sk_drops Read only: sk_rcvbuf (sk_rcvqueues_full()) sk_filter sk_wq sk_policy[0] sk_flags Additional notes : - sk_backlog has one hole on 64bit arches. We can fill it to save 8 bytes. - sk_backlog is used only if RX sofirq handler finds the socket while locked by user. - sk_rxhash is written only once per flow. - sk_drops is written only if queues are full Final layout : [1] One section grouping all read/write fields, but placing rxhash and sk_backlog at the end of this section. [2] One section grouping all read fields in RX handler (sk_filter, sk_rcv_buf, sk_wq) [3] Section used by other paths I'll post a patch on its own to put sk_refcnt at the end of struct sock_common so that it shares same cache line than section [1] New offsets on 64bit arch : sizeof(struct sock)=0x268 offsetof(struct sock, sk_refcnt) =0x10 offsetof(struct sock, sk_lock) =0x48 offsetof(struct sock, sk_receive_queue)=0x68 offsetof(struct sock, sk_backlog)=0x80 offsetof(struct sock, sk_rmem_alloc)=0x80 offsetof(struct sock, sk_forward_alloc)=0x98 offsetof(struct sock, sk_rxhash)=0x9c offsetof(struct sock, sk_rcvbuf)=0xa4 offsetof(struct sock, sk_drops) =0xa0 offsetof(struct sock, sk_filter)=0xa8 offsetof(struct sock, sk_wq)=0xb0 offsetof(struct sock, sk_policy)=0xd0 offsetof(struct sock, sk_flags) =0xe0 Instead of : sizeof(struct sock)=0x270 offsetof(struct sock, sk_refcnt) =0x10 offsetof(struct sock, sk_lock) =0x50 offsetof(struct sock, sk_receive_queue)=0xc0 offsetof(struct sock, sk_backlog)=0x70 offsetof(struct sock, sk_rmem_alloc)=0xac offsetof(struct sock, sk_forward_alloc)=0x10c offsetof(struct sock, sk_rxhash)=0x128 offsetof(struct sock, sk_rcvbuf)=0x4c offsetof(struct sock, sk_drops) =0x16c offsetof(struct sock, sk_filter)=0x198 offsetof(struct sock, sk_wq)=0x88 offsetof(struct sock, sk_policy)=0x98 offsetof(struct sock, sk_flags) =0x130 Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 55 ++++++++++++++++++++++++++++++------------------------ 1 file changed, 31 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index eb0c1f5..5557dfb 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -241,59 +241,67 @@ struct sock { #define sk_bind_node __sk_common.skc_bind_node #define sk_prot __sk_common.skc_prot #define sk_net __sk_common.skc_net - kmemcheck_bitfield_begin(flags); - unsigned int sk_shutdown : 2, - sk_no_check : 2, - sk_userlocks : 4, - sk_protocol : 8, - sk_type : 16; - kmemcheck_bitfield_end(flags); - int sk_rcvbuf; socket_lock_t sk_lock; + struct sk_buff_head sk_receive_queue; /* * The backlog queue is special, it is always used with * the per-socket spinlock held and requires low latency * access. Therefore we special case it's implementation. + * Note : rmem_alloc is in this structure to fill a hole + * on 64bit arches, not because its logically part of + * backlog. */ struct { - struct sk_buff *head; - struct sk_buff *tail; - int len; + atomic_t rmem_alloc; + int len; + struct sk_buff *head; + struct sk_buff *tail; } sk_backlog; +#define sk_rmem_alloc sk_backlog.rmem_alloc + int sk_forward_alloc; +#ifdef CONFIG_RPS + __u32 sk_rxhash; +#endif + atomic_t sk_drops; + int sk_rcvbuf; + + struct sk_filter __rcu *sk_filter; struct socket_wq *sk_wq; - struct dst_entry *sk_dst_cache; + +#ifdef CONFIG_NET_DMA + struct sk_buff_head sk_async_wait_queue; +#endif + #ifdef CONFIG_XFRM struct xfrm_policy *sk_policy[2]; #endif + unsigned long sk_flags; + struct dst_entry *sk_dst_cache; spinlock_t sk_dst_lock; - atomic_t sk_rmem_alloc; atomic_t sk_wmem_alloc; atomic_t sk_omem_alloc; int sk_sndbuf; - struct sk_buff_head sk_receive_queue; struct sk_buff_head sk_write_queue; -#ifdef CONFIG_NET_DMA - struct sk_buff_head sk_async_wait_queue; -#endif + kmemcheck_bitfield_begin(flags); + unsigned int sk_shutdown : 2, + sk_no_check : 2, + sk_userlocks : 4, + sk_protocol : 8, + sk_type : 16; + kmemcheck_bitfield_end(flags); int sk_wmem_queued; - int sk_forward_alloc; gfp_t sk_allocation; int sk_route_caps; int sk_route_nocaps; int sk_gso_type; unsigned int sk_gso_max_size; int sk_rcvlowat; -#ifdef CONFIG_RPS - __u32 sk_rxhash; -#endif - unsigned long sk_flags; unsigned long sk_lingertime; struct sk_buff_head sk_error_queue; struct proto *sk_prot_creator; rwlock_t sk_callback_lock; int sk_err, sk_err_soft; - atomic_t sk_drops; unsigned short sk_ack_backlog; unsigned short sk_max_ack_backlog; __u32 sk_priority; @@ -301,7 +309,6 @@ struct sock { const struct cred *sk_peer_cred; long sk_rcvtimeo; long sk_sndtimeo; - struct sk_filter __rcu *sk_filter; void *sk_protinfo; struct timer_list sk_timer; ktime_t sk_stamp; -- cgit v1.1 From a75d946f42ae1771424a9582129fc5182ff48a1b Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 4 Nov 2010 16:20:20 +0100 Subject: console: move for_each_console to linux/console.h Move it out of printk.c so that we can use it all over the code. There are some potential users which will be converted to that macro in next patches. Signed-off-by: Jiri Slaby Signed-off-by: Greg Kroah-Hartman --- include/linux/console.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/console.h b/include/linux/console.h index 95cf6f0..875cfb1 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -126,6 +126,12 @@ struct console { struct console *next; }; +/* + * for_each_console() allows you to iterate on each console + */ +#define for_each_console(con) \ + for (con = console_drivers; con != NULL; con = con->next) + extern int console_set_on_cmdline; extern int add_preferred_console(char *name, int idx, char *options); -- cgit v1.1 From 3dfbd044d0d99cad2fe50e4f6c79845703fa0558 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 4 Nov 2010 16:20:23 +0100 Subject: TTY: include termios.h in tty_driver.h We reference termios and termiox in tty_driver.h, but we do not include linux/termios.h where these are defined. Add the #include properly. Otherwise when we include tty_driver.h, we get compile errors. Signed-off-by: Jiri Slaby Cc: Alan Cox Cc: Greg KH Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index db2d227..09678ed 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -235,6 +235,7 @@ #include #include #include +#include struct tty_struct; struct tty_driver; -- cgit v1.1 From e44dcb6c377529805bbaae505d5b333daab69111 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Fri, 12 Nov 2010 19:47:47 +0100 Subject: serial: mpc52xx: make printout for type more generic The printout for the type should be just "5xxx", so 512x users won't wonder why they have a mpc52xx-type UART. Signed-off-by: Wolfram Sang Cc: Grant Likely Cc: Greg Kroah-Hartman Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 41603d6..9ff9b7d 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -95,7 +95,7 @@ /* PPC CPM type number */ #define PORT_CPM 58 -/* MPC52xx type numbers */ +/* MPC52xx (and MPC512x) type numbers */ #define PORT_MPC52xx 59 /* IBM icom */ -- cgit v1.1 From f23a478075659db8a4fd62fa6e264a8bb052cc5b Mon Sep 17 00:00:00 2001 From: Arik Nemtsov Date: Mon, 8 Nov 2010 11:51:06 +0200 Subject: mac80211: support hardware TX fragmentation offload The lower driver is notified when the fragmentation threshold changes and upon a reconfig of the interface. If the driver supports hardware TX fragmentation, don't fragment packets in the stack. Signed-off-by: Arik Nemtsov Signed-off-by: John W. Linville --- include/net/mac80211.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 9fdf982..6122e8a 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1652,6 +1652,11 @@ enum ieee80211_ampdu_mlme_action { * and IV16) for the given key from hardware. * The callback must be atomic. * + * @set_frag_threshold: Configuration of fragmentation threshold. Assign this + * if the device does fragmentation by itself; if this callback is + * implemented then the stack will not do fragmentation. + * The callback can sleep. + * * @set_rts_threshold: Configuration of RTS threshold (if device needs it) * The callback can sleep. * @@ -1765,6 +1770,7 @@ struct ieee80211_ops { struct ieee80211_low_level_stats *stats); void (*get_tkip_seq)(struct ieee80211_hw *hw, u8 hw_key_idx, u32 *iv32, u16 *iv16); + int (*set_frag_threshold)(struct ieee80211_hw *hw, u32 value); int (*set_rts_threshold)(struct ieee80211_hw *hw, u32 value); int (*sta_add)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); -- cgit v1.1 From afe0cbf87500f0585d217deb8c6fd329793a7957 Mon Sep 17 00:00:00 2001 From: Bruno Randolf Date: Wed, 10 Nov 2010 12:50:50 +0900 Subject: cfg80211: Add nl80211 antenna configuration Allow setting of TX and RX antennas configuration via nl80211. The antenna configuration is defined as a bitmap of allowed antennas to use. This API can be used to mask out antennas which are not attached or should not be used for other reasons like regulatory concerns or special setups. Separate bitmaps are used for RX and TX to allow configuring different antennas for receiving and transmitting. Each bitmap is 32 bit long, each bit representing one antenna, starting with antenna 1 at the first bit. If an antenna bit is set, this means the driver is allowed to use this antenna for RX or TX respectively; if the bit is not set the hardware is not allowed to use this antenna. Using bitmaps has the benefit of allowing for a flexible configuration interface which can support many different configurations and which can be used for 802.11n as well as non-802.11n devices. Instead of relying on some hardware specific assumptions, drivers can use this information to know which antennas are actually attached to the system and derive their capabilities based on that. 802.11n devices should enable or disable chains, based on which antennas are present (If all antennas belonging to a particular chain are disabled, the entire chain should be disabled). HT capabilities (like STBC, TX Beamforming, Antenna selection) should be calculated based on the available chains after applying the antenna masks. Should a 802.11n device have diversity antennas attached to one of their chains, diversity can be enabled or disabled based on the antenna information. Non-802.11n drivers can use the antenna masks to select RX and TX antennas and to enable or disable antenna diversity. While covering chainmasks for 802.11n and the standard "legacy" modes "fixed antenna 1", "fixed antenna 2" and "diversity" this API also allows more rare, but useful configurations as follows: 1) Send on antenna 1, receive on antenna 2 (or vice versa). This can be used to have a low gain antenna for TX in order to keep within the regulatory constraints and a high gain antenna for RX in order to receive weaker signals ("speak softly, but listen harder"). This can be useful for building long-shot outdoor links. Another usage of this setup is having a low-noise pre-amplifier on antenna 1 and a power amplifier on the other antenna. This way transmit noise is mostly kept out of the low noise receive channel. (This would be bitmaps: tx 1 rx 2). 2) Another similar setup is: Use RX diversity on both antennas, but always send on antenna 1. Again that would allow us to benefit from a higher gain RX antenna, while staying within the legal limits. (This would be: tx 0 rx 3). 3) And finally there can be special experimental setups in research and development even with pre 802.11n hardware where more than 2 antennas are available. It's good to keep the API simple, yet flexible. Signed-off-by: Bruno Randolf -- v7: Made bitmasks 32 bit wide and rebased to latest wireless-testing. Signed-off-by: John W. Linville --- include/linux/nl80211.h | 25 +++++++++++++++++++++++++ include/net/cfg80211.h | 3 +++ 2 files changed, 28 insertions(+) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index fb877b5..17c5c88 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -804,6 +804,28 @@ enum nl80211_commands { * @NL80211_ATTR_SUPPORT_IBSS_RSN: The device supports IBSS RSN, which mostly * means support for per-station GTKs. * + * @NL80211_ATTR_WIPHY_ANTENNA_TX: Bitmap of allowed antennas for transmitting. + * This can be used to mask out antennas which are not attached or should + * not be used for transmitting. If an antenna is not selected in this + * bitmap the hardware is not allowed to transmit on this antenna. + * + * Each bit represents one antenna, starting with antenna 1 at the first + * bit. Depending on which antennas are selected in the bitmap, 802.11n + * drivers can derive which chainmasks to use (if all antennas belonging to + * a particular chain are disabled this chain should be disabled) and if + * a chain has diversity antennas wether diversity should be used or not. + * HT capabilities (STBC, TX Beamforming, Antenna selection) can be + * derived from the available chains after applying the antenna mask. + * Non-802.11n drivers can derive wether to use diversity or not. + * Drivers may reject configurations or RX/TX mask combinations they cannot + * support by returning -EINVAL. + * + * @NL80211_ATTR_WIPHY_ANTENNA_RX: Bitmap of allowed antennas for receiving. + * This can be used to mask out antennas which are not attached or should + * not be used for receiving. If an antenna is not selected in this bitmap + * the hardware should not be configured to receive on this antenna. + * For a more detailed descripton see @NL80211_ATTR_WIPHY_ANTENNA_TX. + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -973,6 +995,9 @@ enum nl80211_attrs { NL80211_ATTR_SUPPORT_IBSS_RSN, + NL80211_ATTR_WIPHY_ANTENNA_TX, + NL80211_ATTR_WIPHY_ANTENNA_RX, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index e5702f5..07425e6 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1304,6 +1304,9 @@ struct cfg80211_ops { void (*mgmt_frame_register)(struct wiphy *wiphy, struct net_device *dev, u16 frame_type, bool reg); + + int (*set_antenna)(struct wiphy *wiphy, u32 tx_ant, u32 rx_ant); + int (*get_antenna)(struct wiphy *wiphy, u32 *tx_ant, u32 *rx_ant); }; /* -- cgit v1.1 From 15d967532148a5fcda075282b82a271b6595a386 Mon Sep 17 00:00:00 2001 From: Bruno Randolf Date: Wed, 10 Nov 2010 12:50:56 +0900 Subject: mac80211: Add antenna configuration Allow antenna configuration by calling driver's function for it. We disallow antenna configuration if the wiphy is already running, mainly to make life easier for 802.11n drivers which need to recalculate HT capabilites. Signed-off-by: Bruno Randolf Signed-off-by: John W. Linville --- include/net/mac80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 6122e8a..a7323ec 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1799,6 +1799,8 @@ struct ieee80211_ops { void (*channel_switch)(struct ieee80211_hw *hw, struct ieee80211_channel_switch *ch_switch); int (*napi_poll)(struct ieee80211_hw *hw, int budget); + int (*set_antenna)(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant); + int (*get_antenna)(struct ieee80211_hw *hw, u32 *tx_ant, u32 *rx_ant); }; /** -- cgit v1.1 From a619a4c0e1fd4e8c360c63d0df3fa0a401107d69 Mon Sep 17 00:00:00 2001 From: Juuso Oikarinen Date: Thu, 11 Nov 2010 08:50:18 +0200 Subject: mac80211: Add function to get probe request template for current AP Chipsets with hardware based connection monitoring need to autonomically send directed probe-request frames to the AP (in the event of beacon loss, for example.) For the hardware to be able to do this, it requires a template for the frame to transmit to the AP, filled in with the BSSID and SSID of the AP, but also the supported rate IE's. This patch adds a function to mac80211, which allows the hardware driver to fetch this template after association, so it can be configured to the hardware. Signed-off-by: Juuso Oikarinen Acked-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index a7323ec..af7e841 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2509,6 +2509,21 @@ void ieee80211_sta_block_awake(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, bool block); /** + * ieee80211_ap_probereq_get - retrieve a Probe Request template + * @hw: pointer obtained from ieee80211_alloc_hw(). + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * + * Creates a Probe Request template which can, for example, be uploaded to + * hardware. The template is filled with bssid, ssid and supported rate + * information. This function must only be called from within the + * .bss_info_changed callback function and only in managed mode. The function + * is only useful when the interface is associated, otherwise it will return + * NULL. + */ +struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw, + struct ieee80211_vif *vif); + +/** * ieee80211_beacon_loss - inform hardware does not receive beacons * * @vif: &struct ieee80211_vif pointer from the add_interface callback. -- cgit v1.1 From 885a46d0f7942d76c2f3860acb45f75237d3bb42 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Thu, 11 Nov 2010 15:07:22 +0100 Subject: cfg80211: add support for setting the ad-hoc multicast rate Signed-off-by: Felix Fietkau Signed-off-by: John W. Linville --- include/linux/nl80211.h | 4 ++++ include/net/cfg80211.h | 2 ++ 2 files changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 17c5c88..037b4e4 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -826,6 +826,8 @@ enum nl80211_commands { * the hardware should not be configured to receive on this antenna. * For a more detailed descripton see @NL80211_ATTR_WIPHY_ANTENNA_TX. * + * @NL80211_ATTR_MCAST_RATE: Multicast tx rate (in 100 kbps) for IBSS + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -998,6 +1000,8 @@ enum nl80211_attrs { NL80211_ATTR_WIPHY_ANTENNA_TX, NL80211_ATTR_WIPHY_ANTENNA_RX, + NL80211_ATTR_MCAST_RATE, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 07425e6..8fd9eeb 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -923,6 +923,7 @@ struct cfg80211_disassoc_request { * @privacy: this is a protected network, keys will be configured * after joining * @basic_rates: bitmap of basic rates to use when creating the IBSS + * @mcast_rate: multicast tx rate (in 100 kbps) */ struct cfg80211_ibss_params { u8 *ssid; @@ -934,6 +935,7 @@ struct cfg80211_ibss_params { u32 basic_rates; bool channel_fixed; bool privacy; + int mcast_rate; }; /** -- cgit v1.1 From 8f0729b16ae354f9db89394fc1d2d65003455d56 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Thu, 11 Nov 2010 15:07:23 +0100 Subject: mac80211: add support for setting the ad-hoc multicast rate Signed-off-by: Felix Fietkau Signed-off-by: John W. Linville --- include/net/mac80211.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index af7e841..1248369 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -205,6 +205,7 @@ enum ieee80211_bss_change { * @basic_rates: bitmap of basic rates, each bit stands for an * index into the rate table configured by the driver in * the current band. + * @mcast_rate: multicast rate for AP and Ad-Hoc (in 100 kbps) * @bssid: The BSSID for this BSS * @enable_beacon: whether beaconing should be enabled or not * @channel_type: Channel type for this BSS -- the hardware might be @@ -244,6 +245,7 @@ struct ieee80211_bss_conf { u16 assoc_capability; u64 timestamp; u32 basic_rates; + u32 mcast_rate; u16 ht_operation_mode; s32 cqm_rssi_thold; u32 cqm_rssi_hyst; @@ -2663,7 +2665,7 @@ enum rate_control_changed { * @rate_idx_mask: user-requested rate mask (not MCS for now) * @skb: the skb that will be transmitted, the control information in it needs * to be filled in - * @ap: whether this frame is sent out in AP mode + * @bss: whether this frame is sent out in AP or IBSS mode */ struct ieee80211_tx_rate_control { struct ieee80211_hw *hw; @@ -2674,7 +2676,7 @@ struct ieee80211_tx_rate_control { bool rts, short_preamble; u8 max_rate_idx; u32 rate_idx_mask; - bool ap; + bool bss; }; struct rate_control_ops { -- cgit v1.1 From 6ddf27cdbc218a412d7e993fdc08e30eec2042ce Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 15 Nov 2010 15:57:30 -0500 Subject: USB: make usb_mark_last_busy use pm_runtime_mark_last_busy Since the runtime-PM core already defines a .last_busy field in device.power, this patch uses it to replace the .last_busy field defined in usb_device and uses pm_runtime_mark_last_busy to implement usb_mark_last_busy. Signed-off-by: Ming Lei Reviewed-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/usb.h b/include/linux/usb.h index 35fe6ab..7d22b33 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -20,6 +20,7 @@ #include /* for struct completion */ #include /* for current && schedule_timeout */ #include /* for struct mutex */ +#include /* for runtime PM */ struct usb_device; struct usb_driver; @@ -407,7 +408,6 @@ struct usb_tt; * @quirks: quirks of the whole device * @urbnum: number of URBs submitted for the whole device * @active_duration: total time device is not suspended - * @last_busy: time of last use * @autosuspend_delay: in jiffies * @connect_time: time device was first connected * @do_remote_wakeup: remote wakeup should be enabled @@ -481,7 +481,6 @@ struct usb_device { unsigned long active_duration; #ifdef CONFIG_PM - unsigned long last_busy; int autosuspend_delay; unsigned long connect_time; @@ -527,7 +526,7 @@ extern void usb_autopm_put_interface_no_suspend(struct usb_interface *intf); static inline void usb_mark_last_busy(struct usb_device *udev) { - udev->last_busy = jiffies; + pm_runtime_mark_last_busy(&udev->dev); } #else -- cgit v1.1 From fcc4a01eb8661226e80632327673f67bf6a5840b Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 15 Nov 2010 15:57:51 -0500 Subject: USB: use the runtime-PM autosuspend implementation This patch (as1428) converts USB over to the new runtime-PM core autosuspend framework. One slightly awkward aspect of the conversion is that USB devices will now have two suspend-delay attributes: the old power/autosuspend file and the new power/autosuspend_delay_ms file. One expresses the delay time in seconds and the other in milliseconds, but otherwise they do the same thing. The old attribute can be deprecated and then removed eventually. Signed-off-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/usb.h b/include/linux/usb.h index 7d22b33..5ee2223 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -408,7 +408,6 @@ struct usb_tt; * @quirks: quirks of the whole device * @urbnum: number of URBs submitted for the whole device * @active_duration: total time device is not suspended - * @autosuspend_delay: in jiffies * @connect_time: time device was first connected * @do_remote_wakeup: remote wakeup should be enabled * @reset_resume: needs reset instead of resume @@ -481,7 +480,6 @@ struct usb_device { unsigned long active_duration; #ifdef CONFIG_PM - int autosuspend_delay; unsigned long connect_time; unsigned do_remote_wakeup:1; -- cgit v1.1 From da6836500414ae734cd9873c2d553db594f831e9 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Tue, 16 Nov 2010 11:52:38 +0000 Subject: netfilter: allow hooks to pass error code back up the stack SELinux would like to pass certain fatal errors back up the stack. This patch implements the generic netfilter support for this functionality. Based-on-patch-by: Patrick McHardy Signed-off-by: Eric Paris Signed-off-by: David S. Miller --- include/linux/netfilter.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 03317c8..1893837 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -33,6 +33,8 @@ #define NF_QUEUE_NR(x) ((((x) << NF_VERDICT_BITS) & NF_VERDICT_QMASK) | NF_QUEUE) +#define NF_DROP_ERR(x) (((-x) << NF_VERDICT_BITS) | NF_DROP) + /* only for userspace compatibility */ #ifndef __KERNEL__ /* Generic cache responses from hook functions. -- cgit v1.1 From f8ff182c716c6f11ca3061961f5722f26a14e101 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 16 Nov 2010 04:30:14 +0000 Subject: rtnetlink: Link address family API Each net_device contains address family specific data such as per device settings and statistics. We already expose this data via procfs/sysfs and partially netlink. The netlink method requires the requester to send one RTM_GETLINK request for each address family it wishes to receive data of and then merge this data itself. This patch implements a new API which combines all address family specific link data in a new netlink attribute IFLA_AF_SPEC. IFLA_AF_SPEC contains a sequence of nested attributes, one for each address family which in turn defines the structure of its own attribute. Example: [IFLA_AF_SPEC] = { [AF_INET] = { [IFLA_INET_CONF] = ..., }, [AF_INET6] = { [IFLA_INET6_FLAGS] = ..., [IFLA_INET6_CONF] = ..., } } The API also allows for address families to implement a function which parses the IFLA_AF_SPEC attribute sent by userspace to implement address family specific link options. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/if_link.h | 19 +++++++++++++++++++ include/net/rtnetlink.h | 31 +++++++++++++++++++++++++++++++ 2 files changed, 50 insertions(+) (limited to 'include') diff --git a/include/linux/if_link.h b/include/linux/if_link.h index 2fc66dd..443d04a 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -80,6 +80,24 @@ struct rtnl_link_ifmap { __u8 port; }; +/* + * IFLA_AF_SPEC + * Contains nested attributes for address family specific attributes. + * Each address family may create a attribute with the address family + * number as type and create its own attribute structure in it. + * + * Example: + * [IFLA_AF_SPEC] = { + * [AF_INET] = { + * [IFLA_INET_CONF] = ..., + * }, + * [AF_INET6] = { + * [IFLA_INET6_FLAGS] = ..., + * [IFLA_INET6_CONF] = ..., + * } + * } + */ + enum { IFLA_UNSPEC, IFLA_ADDRESS, @@ -116,6 +134,7 @@ enum { IFLA_STATS64, IFLA_VF_PORTS, IFLA_PORT_SELF, + IFLA_AF_SPEC, __IFLA_MAX }; diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index e013c68..35be0bb 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -83,6 +83,37 @@ extern void __rtnl_link_unregister(struct rtnl_link_ops *ops); extern int rtnl_link_register(struct rtnl_link_ops *ops); extern void rtnl_link_unregister(struct rtnl_link_ops *ops); +/** + * struct rtnl_af_ops - rtnetlink address family operations + * + * @list: Used internally + * @family: Address family + * @fill_link_af: Function to fill IFLA_AF_SPEC with address family + * specific netlink attributes. + * @get_link_af_size: Function to calculate size of address family specific + * netlink attributes exlusive the container attribute. + * @parse_link_af: Function to parse a IFLA_AF_SPEC attribute and modify + * net_device accordingly. + */ +struct rtnl_af_ops { + struct list_head list; + int family; + + int (*fill_link_af)(struct sk_buff *skb, + const struct net_device *dev); + size_t (*get_link_af_size)(const struct net_device *dev); + + int (*parse_link_af)(struct net_device *dev, + const struct nlattr *attr); +}; + +extern int __rtnl_af_register(struct rtnl_af_ops *ops); +extern void __rtnl_af_unregister(struct rtnl_af_ops *ops); + +extern int rtnl_af_register(struct rtnl_af_ops *ops); +extern void rtnl_af_unregister(struct rtnl_af_ops *ops); + + extern struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]); extern struct net_device *rtnl_create_link(struct net *src_net, struct net *net, char *ifname, const struct rtnl_link_ops *ops, struct nlattr *tb[]); -- cgit v1.1 From ca7479ebbd9f7621646bf2792cb7143647f035bb Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 16 Nov 2010 04:31:20 +0000 Subject: inet: Define IPV4_DEVCONF_MAX Define IPV4_DEVCONF_MAX to get rid of MAX - 1 notation. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 380ba6b..2b86eaf 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -41,10 +41,12 @@ enum __IPV4_DEVCONF_MAX }; +#define IPV4_DEVCONF_MAX (__IPV4_DEVCONF_MAX - 1) + struct ipv4_devconf { void *sysctl; - int data[__IPV4_DEVCONF_MAX - 1]; - DECLARE_BITMAP(state, __IPV4_DEVCONF_MAX - 1); + int data[IPV4_DEVCONF_MAX]; + DECLARE_BITMAP(state, IPV4_DEVCONF_MAX); }; struct in_device { @@ -90,7 +92,7 @@ static inline void ipv4_devconf_set(struct in_device *in_dev, int index, static inline void ipv4_devconf_setall(struct in_device *in_dev) { - bitmap_fill(in_dev->cnf.state, __IPV4_DEVCONF_MAX - 1); + bitmap_fill(in_dev->cnf.state, IPV4_DEVCONF_MAX); } #define IN_DEV_CONF_GET(in_dev, attr) \ -- cgit v1.1 From 9f0f7272ac9506f4c8c05cc597b7e376b0b9f3e4 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 16 Nov 2010 04:32:48 +0000 Subject: ipv4: AF_INET link address family Implements the AF_INET link address family exposing the per device configuration settings via netlink using the attribute IFLA_INET_CONF. The format of IFLA_INET_CONF differs depending on the direction the attribute is sent. The attribute sent by the kernel consists of a u32 array, basically a 1:1 copy of in_device->cnf.data[]. The attribute expected by the kernel must consist of a sequence of nested u32 attributes, each representing a change request, e.g. [IFLA_INET_CONF] = { [IPV4_DEVCONF_FORWARDING] = 1, [IPV4_DEVCONF_NOXFRM] = 0, } libnl userspace API documentation and example available from: http://www.infradead.org/~tgr/libnl/doc-git/group__link__inet.html Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/if_link.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/if_link.h b/include/linux/if_link.h index 443d04a..2e02e4d 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -147,6 +147,14 @@ enum { #define IFLA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifinfomsg)) #endif +enum { + IFLA_INET_UNSPEC, + IFLA_INET_CONF, + __IFLA_INET_MAX, +}; + +#define IFLA_INET_MAX (__IFLA_INET_MAX - 1) + /* ifi_flags. IFF_* flags. -- cgit v1.1 From 5811662b15db018c740c57d037523683fd3e6123 Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Fri, 12 Nov 2010 18:43:55 +0000 Subject: net: use the macros defined for the members of flowi Use the macros defined for the members of flowi to clean the code up. Signed-off-by: Changli Gao Signed-off-by: David S. Miller --- include/net/route.h | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/route.h b/include/net/route.h index 5cd46d1..b8c1f77 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -169,14 +169,12 @@ static inline int ip_route_connect(struct rtable **rp, __be32 dst, { struct flowi fl = { .oif = oif, .mark = sk->sk_mark, - .nl_u = { .ip4_u = { .daddr = dst, - .saddr = src, - .tos = tos } }, + .fl4_dst = dst, + .fl4_src = src, + .fl4_tos = tos, .proto = protocol, - .uli_u = { .ports = - { .sport = sport, - .dport = dport } } }; - + .fl_ip_sport = sport, + .fl_ip_dport = dport }; int err; struct net *net = sock_net(sk); -- cgit v1.1 From 4bce22b9b84032c77c7e038b07b24fcc706dfc10 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 16 Nov 2010 11:49:58 -0800 Subject: mac80211: defines for AC numbers In many places we've just hardcoded the AC numbers -- which is a relic from the original mac80211 (d80211). Add constants for them so we know what we're talking about. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 1248369..5b0fff2 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -97,6 +97,20 @@ enum ieee80211_max_queues { }; /** + * enum ieee80211_ac_numbers - AC numbers as used in mac80211 + * @IEEE80211_AC_VO: voice + * @IEEE80211_AC_VI: video + * @IEEE80211_AC_BE: best effort + * @IEEE80211_AC_BK: background + */ +enum ieee80211_ac_numbers { + IEEE80211_AC_VO = 0, + IEEE80211_AC_VI = 1, + IEEE80211_AC_BE = 2, + IEEE80211_AC_BK = 3, +}; + +/** * struct ieee80211_tx_queue_params - transmit queue configuration * * The information provided in this structure is required for QoS -- cgit v1.1 From 6b6e39a6a8da7234c538d14c43d3583da8875f9c Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Mon, 15 Nov 2010 23:13:18 +0100 Subject: driver-core: merge private parts of class and bus As classes and busses are pretty much the same thing, and we want to merge them together into a 'subsystem' in the future, let us share the same private data parts to make that merge easier. Signed-off-by: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index dd48953..1e2d335 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -30,9 +30,8 @@ struct device_private; struct device_driver; struct driver_private; struct class; -struct class_private; +struct subsys_private; struct bus_type; -struct bus_type_private; struct device_node; struct bus_attribute { @@ -65,7 +64,7 @@ struct bus_type { const struct dev_pm_ops *pm; - struct bus_type_private *p; + struct subsys_private *p; }; extern int __must_check bus_register(struct bus_type *bus); @@ -213,7 +212,7 @@ struct class { const struct dev_pm_ops *pm; - struct class_private *p; + struct subsys_private *p; }; struct class_dev_iter { -- cgit v1.1 From b2c0710c464ede15e1fc52fb1e7ee9ba54cea186 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 9 Sep 2010 13:40:39 -0700 Subject: rcu: move TINY_RCU from softirq to kthread If RCU priority boosting is to be meaningful, callback invocation must be boosted in addition to preempted RCU readers. Otherwise, in presence of CPU real-time threads, the grace period ends, but the callbacks don't get invoked. If the callbacks don't get invoked, the associated memory doesn't get freed, so the system is still subject to OOM. But it is not reasonable to priority-boost RCU_SOFTIRQ, so this commit moves the callback invocations to a kthread, which can be boosted easily. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 1 - include/linux/rcutiny.h | 8 +++----- include/linux/rcutree.h | 1 + 3 files changed, 4 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 03cda7b..7142ee3 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -118,7 +118,6 @@ static inline int rcu_preempt_depth(void) #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ /* Internal to kernel */ -extern void rcu_init(void); extern void rcu_sched_qs(int cpu); extern void rcu_bh_qs(int cpu); extern void rcu_check_callbacks(int cpu, int user); diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 13877cb..ea025a6 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -27,7 +27,9 @@ #include -#define rcu_init_sched() do { } while (0) +static inline void rcu_init(void) +{ +} #ifdef CONFIG_TINY_RCU @@ -125,16 +127,12 @@ static inline void rcu_cpu_stall_reset(void) } #ifdef CONFIG_DEBUG_LOCK_ALLOC - extern int rcu_scheduler_active __read_mostly; extern void rcu_scheduler_starting(void); - #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ - static inline void rcu_scheduler_starting(void) { } - #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #endif /* __LINUX_RCUTINY_H */ diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 95518e6..c0e9683 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -30,6 +30,7 @@ #ifndef __LINUX_RCUTREE_H #define __LINUX_RCUTREE_H +extern void rcu_init(void); extern void rcu_note_context_switch(int cpu); extern int rcu_needs_cpu(int cpu); extern void rcu_cpu_stall_reset(void); -- cgit v1.1 From 5f2b0ba4d94b3ac23cbc4b7f675d98eb677a760a Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Fri, 12 Nov 2010 11:22:23 -0500 Subject: x86, nmi_watchdog: Remove the old nmi_watchdog Now that we have a new nmi_watchdog that is more generic and sits on top of the perf subsystem, we really do not need the old nmi_watchdog any more. In addition, the old nmi_watchdog doesn't really work if you are using the default clocksource, hpet. The old nmi_watchdog code relied on local apic interrupts to determine if the cpu is still alive. With hpet as the clocksource, these interrupts don't increment any more and the old nmi_watchdog triggers false postives. This piece removes the old nmi_watchdog code and stubs out any variables and functions calls. The stubs are the same ones used by the new nmi_watchdog code, so it should be well tested. Signed-off-by: Don Zickus Cc: fweisbec@gmail.com Cc: gorcunov@openvz.org LKML-Reference: <1289578944-28564-2-git-send-email-dzickus@redhat.com> Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 06aab5e..0cb3e5c 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -16,10 +16,7 @@ */ #ifdef ARCH_HAS_NMI_WATCHDOG #include -extern void touch_nmi_watchdog(void); -extern void acpi_nmi_disable(void); -extern void acpi_nmi_enable(void); -#else +#endif #ifndef CONFIG_HARDLOCKUP_DETECTOR static inline void touch_nmi_watchdog(void) { @@ -30,7 +27,6 @@ extern void touch_nmi_watchdog(void); #endif static inline void acpi_nmi_disable(void) { } static inline void acpi_nmi_enable(void) { } -#endif /* * Create trigger_all_cpu_backtrace() out of the arch-provided -- cgit v1.1 From 072b198a4ad48bd722ec6d203d65422a4698eae7 Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Fri, 12 Nov 2010 11:22:24 -0500 Subject: x86, nmi_watchdog: Remove all stub function calls from old nmi_watchdog Now that the bulk of the old nmi_watchdog is gone, remove all the stub variables and hooks associated with it. This touches lots of files mainly because of how the io_apic nmi_watchdog was implemented. Now that the io_apic nmi_watchdog is forever gone, remove all its fingers. Most of this code was not being exercised by virtue of nmi_watchdog != NMI_IO_APIC, so there shouldn't be anything to risky here. Signed-off-by: Don Zickus Cc: fweisbec@gmail.com Cc: gorcunov@openvz.org LKML-Reference: <1289578944-28564-3-git-send-email-dzickus@redhat.com> Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 0cb3e5c..1c451e6 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -25,8 +25,6 @@ static inline void touch_nmi_watchdog(void) #else extern void touch_nmi_watchdog(void); #endif -static inline void acpi_nmi_disable(void) { } -static inline void acpi_nmi_enable(void) { } /* * Create trigger_all_cpu_backtrace() out of the arch-provided -- cgit v1.1 From 48c5ccae88dcd989d9de507e8510313c6cbd352b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sat, 13 Nov 2010 19:32:29 +0100 Subject: sched: Simplify cpu-hot-unplug task migration While discussing the need for sched_idle_next(), Oleg remarked that since try_to_wake_up() ensures sleeping tasks will end up running on a sane cpu, we can do away with migrate_live_tasks(). If we then extend the existing hack of migrating current from CPU_DYING to migrating the full rq worth of tasks from CPU_DYING, the need for the sched_idle_next() abomination disappears as well, since idle will be the only possible thread left after the migration thread stops. This greatly simplifies the hot-unplug task migration path, as can be seen from the resulting code reduction (and about half the new lines are comments). Suggested-by: Oleg Nesterov Signed-off-by: Peter Zijlstra LKML-Reference: <1289851597.2109.547.camel@laptop> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 3cd70cf..29d953a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1871,14 +1871,11 @@ extern void sched_clock_idle_sleep_event(void); extern void sched_clock_idle_wakeup_event(u64 delta_ns); #ifdef CONFIG_HOTPLUG_CPU -extern void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p); extern void idle_task_exit(void); #else static inline void idle_task_exit(void) {} #endif -extern void sched_idle_next(void); - #if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP) extern void wake_up_idle_cpu(int cpu); #else -- cgit v1.1 From 2069dd75c7d0f49355939e5586daf5a9ab216db7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 15 Nov 2010 15:47:00 -0800 Subject: sched: Rewrite tg_shares_up) By tracking a per-cpu load-avg for each cfs_rq and folding it into a global task_group load on each tick we can rework tg_shares_up to be strictly per-cpu. This should improve cpu-cgroup performance for smp systems significantly. [ Paul: changed to use queueing cfs_rq + bug fixes ] Signed-off-by: Paul Turner Signed-off-by: Peter Zijlstra LKML-Reference: <20101115234937.580480400@google.com> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 29d953a..8abb8aa 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1885,8 +1885,6 @@ static inline void wake_up_idle_cpu(int cpu) { } extern unsigned int sysctl_sched_latency; extern unsigned int sysctl_sched_min_granularity; extern unsigned int sysctl_sched_wakeup_granularity; -extern unsigned int sysctl_sched_shares_ratelimit; -extern unsigned int sysctl_sched_shares_thresh; extern unsigned int sysctl_sched_child_runs_first; enum sched_tunable_scaling { -- cgit v1.1 From a7a4f8a752ec734b2eab904fc863d5dc873de338 Mon Sep 17 00:00:00 2001 From: Paul Turner Date: Mon, 15 Nov 2010 15:47:06 -0800 Subject: sched: Add sysctl_sched_shares_window Introduce a new sysctl for the shares window and disambiguate it from sched_time_avg. A 10ms window appears to be a good compromise between accuracy and performance. Signed-off-by: Paul Turner Signed-off-by: Peter Zijlstra LKML-Reference: <20101115234938.112173964@google.com> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 8abb8aa..840f127 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1900,6 +1900,7 @@ extern unsigned int sysctl_sched_migration_cost; extern unsigned int sysctl_sched_nr_migrate; extern unsigned int sysctl_sched_time_avg; extern unsigned int sysctl_timer_migration; +extern unsigned int sysctl_sched_shares_window; int sched_proc_update_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, -- cgit v1.1 From 84e1c6bb38eb318e456558b610396d9f1afaabf0 Mon Sep 17 00:00:00 2001 From: matthieu castet Date: Tue, 16 Nov 2010 22:35:16 +0100 Subject: x86: Add RO/NX protection for loadable kernel modules This patch is a logical extension of the protection provided by CONFIG_DEBUG_RODATA to LKMs. The protection is provided by splitting module_core and module_init into three logical parts each and setting appropriate page access permissions for each individual section: 1. Code: RO+X 2. RO data: RO+NX 3. RW data: RW+NX In order to achieve proper protection, layout_sections() have been modified to align each of the three parts mentioned above onto page boundary. Next, the corresponding page access permissions are set right before successful exit from load_module(). Further, free_module() and sys_init_module have been modified to set module_core and module_init as RW+NX right before calling module_free(). By default, the original section layout and access flags are preserved. When compiled with CONFIG_DEBUG_SET_MODULE_RONX=y, the patch will page-align each group of sections to ensure that each page contains only one type of content and will enforce RO/NX for each group of pages. -v1: Initial proof-of-concept patch. -v2: The patch have been re-written to reduce the number of #ifdefs and to make it architecture-agnostic. Code formatting has also been corrected. -v3: Opportunistic RO/NX protection is now unconditional. Section page-alignment is enabled when CONFIG_DEBUG_RODATA=y. -v4: Removed most macros and improved coding style. -v5: Changed page-alignment and RO/NX section size calculation -v6: Fixed comments. Restricted RO/NX enforcement to x86 only -v7: Introduced CONFIG_DEBUG_SET_MODULE_RONX, added calls to set_all_modules_text_rw() and set_all_modules_text_ro() in ftrace -v8: updated for compatibility with linux 2.6.33-rc5 -v9: coding style fixes -v10: more coding style fixes -v11: minor adjustments for -tip -v12: minor adjustments for v2.6.35-rc2-tip -v13: minor adjustments for v2.6.37-rc1-tip Signed-off-by: Siarhei Liakh Signed-off-by: Xuxian Jiang Acked-by: Arjan van de Ven Reviewed-by: James Morris Signed-off-by: H. Peter Anvin Cc: Andi Kleen Cc: Rusty Russell Cc: Stephen Rothwell Cc: Dave Jones Cc: Kees Cook Cc: Linus Torvalds LKML-Reference: <4CE2F914.9070106@free.fr> [ minor cleanliness edits, -v14: build failure fix ] Signed-off-by: Ingo Molnar --- include/linux/module.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index b29e745..ddaa689 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -308,6 +308,9 @@ struct module /* The size of the executable code in each section. */ unsigned int init_text_size, core_text_size; + /* Size of RO sections of the module (text+rodata) */ + unsigned int init_ro_size, core_ro_size; + /* Arch-specific module values */ struct mod_arch_specific arch; @@ -672,7 +675,6 @@ static inline int module_get_iter_tracepoints(struct tracepoint_iter *iter) { return 0; } - #endif /* CONFIG_MODULES */ #ifdef CONFIG_SYSFS @@ -687,6 +689,13 @@ extern int module_sysfs_initialized; #define __MODULE_STRING(x) __stringify(x) +#ifdef CONFIG_DEBUG_SET_MODULE_RONX +extern void set_all_modules_text_rw(void); +extern void set_all_modules_text_ro(void); +#else +static inline void set_all_modules_text_rw(void) { } +static inline void set_all_modules_text_ro(void) { } +#endif #ifdef CONFIG_GENERIC_BUG void module_bug_finalize(const Elf_Ehdr *, const Elf_Shdr *, -- cgit v1.1 From 9c0729dc8062bed96189bd14ac6d4920f3958743 Mon Sep 17 00:00:00 2001 From: Soeren Sandmann Pedersen Date: Fri, 5 Nov 2010 05:59:39 -0400 Subject: x86: Eliminate bp argument from the stack tracing routines The various stack tracing routines take a 'bp' argument in which the caller is supposed to provide the base pointer to use, or 0 if doesn't have one. Since bp is garbage whenever CONFIG_FRAME_POINTER is not defined, this means all callers in principle should either always pass 0, or be conditional on CONFIG_FRAME_POINTER. However, there are only really three use cases for stack tracing: (a) Trace the current task, including IRQ stack if any (b) Trace the current task, but skip IRQ stack (c) Trace some other task In all cases, if CONFIG_FRAME_POINTER is not defined, bp should just be 0. If it _is_ defined, then - in case (a) bp should be gotten directly from the CPU's register, so the caller should pass NULL for regs, - in case (b) the caller should should pass the IRQ registers to dump_trace(), - in case (c) bp should be gotten from the top of the task's stack, so the caller should pass NULL for regs. Hence, the bp argument is not necessary because the combination of task and regs is sufficient to determine an appropriate value for bp. This patch introduces a new inline function stack_frame(task, regs) that computes the desired bp. This function is then called from the two versions of dump_stack(). Signed-off-by: Soren Sandmann Acked-by: Steven Rostedt Cc: Thomas Gleixner Cc: Ingo Molnar Cc: H. Peter Anvin Cc: Peter Zijlstra Cc: Arjan van de Ven , Cc: Frederic Weisbecker , Cc: Arnaldo Carvalho de Melo , LKML-Reference: > Signed-off-by: Frederic Weisbecker --- include/linux/stacktrace.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h index 51efbef..25310f1 100644 --- a/include/linux/stacktrace.h +++ b/include/linux/stacktrace.h @@ -2,6 +2,7 @@ #define __LINUX_STACKTRACE_H struct task_struct; +struct pt_regs; #ifdef CONFIG_STACKTRACE struct task_struct; @@ -13,7 +14,8 @@ struct stack_trace { }; extern void save_stack_trace(struct stack_trace *trace); -extern void save_stack_trace_bp(struct stack_trace *trace, unsigned long bp); +extern void save_stack_trace_regs(struct stack_trace *trace, + struct pt_regs *regs); extern void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace); -- cgit v1.1 From 61c32659b12c44e62de32fbf99f7e4ca783dc38b Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 18 Nov 2010 01:39:17 +0100 Subject: tracing: New flag to allow non privileged users to use a trace event This adds a new trace event internal flag that allows them to be used in perf by non privileged users in case of task bound tracing. This is desired for syscalls tracepoint because they don't leak global system informations, like some other tracepoints. Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Thomas Gleixner Cc: Steven Rostedt Cc: Li Zefan Cc: Jason Baron --- include/linux/ftrace_event.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 8beabb9..312dce7 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -154,12 +154,14 @@ enum { TRACE_EVENT_FL_ENABLED_BIT, TRACE_EVENT_FL_FILTERED_BIT, TRACE_EVENT_FL_RECORDED_CMD_BIT, + TRACE_EVENT_FL_CAP_ANY_BIT, }; enum { TRACE_EVENT_FL_ENABLED = (1 << TRACE_EVENT_FL_ENABLED_BIT), TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT), TRACE_EVENT_FL_RECORDED_CMD = (1 << TRACE_EVENT_FL_RECORDED_CMD_BIT), + TRACE_EVENT_FL_CAP_ANY = (1 << TRACE_EVENT_FL_CAP_ANY_BIT), }; struct ftrace_event_call { -- cgit v1.1 From 1ed0c5971159974185653170543a764cc061c857 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 18 Nov 2010 01:46:57 +0100 Subject: tracing: New macro to set up initial event flags value This introduces the new TRACE_EVENT_FLAGS() macro in order to set up initial event flags value. This macro must simply follow the definition of a trace event and take the event name and the flag value as parameters: TRACE_EVENT(my_event, ..... .... ); TRACE_EVENT_FLAGS(my_event, 1) This will set up 1 as the initial my_event->flags value. Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Thomas Gleixner Cc: Steven Rostedt Cc: Li Zefan Cc: Jason Baron --- include/linux/tracepoint.h | 4 ++++ include/trace/ftrace.h | 12 ++++++++++++ 2 files changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index a4a90b6..5a6074f 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -234,6 +234,8 @@ do_trace: \ PARAMS(void *__data, proto), \ PARAMS(__data, args)) +#define TRACE_EVENT_FLAGS(event, flag) + #endif /* DECLARE_TRACE */ #ifndef TRACE_EVENT @@ -354,4 +356,6 @@ do_trace: \ assign, print, reg, unreg) \ DECLARE_TRACE(name, PARAMS(proto), PARAMS(args)) +#define TRACE_EVENT_FLAGS(event, flag) + #endif /* ifdef TRACE_EVENT (see note above) */ diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index a9377c0..6f54012 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -82,6 +82,15 @@ TRACE_EVENT(name, PARAMS(proto), PARAMS(args), \ PARAMS(tstruct), PARAMS(assign), PARAMS(print)) \ +#undef TRACE_EVENT_FLAGS +#define TRACE_EVENT_FLAGS(name, value) \ + static int __init trace_init_flags_##name(void) \ + { \ + event_##name.flags = value; \ + return 0; \ + } \ + early_initcall(trace_init_flags_##name); + #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) @@ -129,6 +138,9 @@ #define DEFINE_EVENT_PRINT(template, name, proto, args, print) \ DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args)) +#undef TRACE_EVENT_FLAGS +#define TRACE_EVENT_FLAGS(event, flag) + #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) /* -- cgit v1.1 From fe5542030dce3b951f9eaf3ecb9a7bc5fa7bfed1 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 18 Nov 2010 01:52:06 +0100 Subject: tracing: Allow raw syscall trace events for non privileged users This allows non privileged users to use the raw syscall trace events for task bound tracing in perf. It is safe because raw syscall trace events don't leak system wide informations. Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Thomas Gleixner Cc: Steven Rostedt Cc: Li Zefan Cc: Jason Baron --- include/trace/events/syscalls.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/trace/events/syscalls.h b/include/trace/events/syscalls.h index fb726ac..5a4c04a 100644 --- a/include/trace/events/syscalls.h +++ b/include/trace/events/syscalls.h @@ -40,6 +40,8 @@ TRACE_EVENT_FN(sys_enter, syscall_regfunc, syscall_unregfunc ); +TRACE_EVENT_FLAGS(sys_enter, TRACE_EVENT_FL_CAP_ANY) + TRACE_EVENT_FN(sys_exit, TP_PROTO(struct pt_regs *regs, long ret), @@ -62,6 +64,8 @@ TRACE_EVENT_FN(sys_exit, syscall_regfunc, syscall_unregfunc ); +TRACE_EVENT_FLAGS(sys_exit, TRACE_EVENT_FL_CAP_ANY) + #endif /* CONFIG_HAVE_SYSCALL_TRACEPOINTS */ #endif /* _TRACE_EVENTS_SYSCALLS_H */ -- cgit v1.1 From 53cf810b1934f08a68e131aeeb16267a778f43df Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 18 Nov 2010 02:11:42 +0100 Subject: tracing: Allow syscall trace events for non privileged users As for the raw syscalls events, individual syscall events won't leak system wide information on task bound tracing. Allow non privileged users to use them in such workflow. Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Thomas Gleixner Cc: Steven Rostedt Cc: Li Zefan Cc: Jason Baron --- include/linux/ftrace_event.h | 8 ++++++++ include/linux/syscalls.h | 6 ++++-- include/trace/ftrace.h | 7 +------ 3 files changed, 13 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 312dce7..725bf6b 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -198,6 +198,14 @@ struct ftrace_event_call { #endif }; +#define __TRACE_EVENT_FLAGS(name, value) \ + static int __init trace_init_flags_##name(void) \ + { \ + event_##name.flags = value; \ + return 0; \ + } \ + early_initcall(trace_init_flags_##name); + #define PERF_MAX_TRACE_SIZE 2048 #define MAX_FILTER_PRED 32 diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index cacc27a..13b9731d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -137,7 +137,8 @@ extern struct trace_event_functions exit_syscall_print_funcs; .class = &event_class_syscall_enter, \ .event.funcs = &enter_syscall_print_funcs, \ .data = (void *)&__syscall_meta_##sname,\ - } + }; \ + __TRACE_EVENT_FLAGS(enter_##sname, TRACE_EVENT_FL_CAP_ANY) #define SYSCALL_TRACE_EXIT_EVENT(sname) \ static struct syscall_metadata \ @@ -152,7 +153,8 @@ extern struct trace_event_functions exit_syscall_print_funcs; .class = &event_class_syscall_exit, \ .event.funcs = &exit_syscall_print_funcs, \ .data = (void *)&__syscall_meta_##sname,\ - } + }; \ + __TRACE_EVENT_FLAGS(exit_##sname, TRACE_EVENT_FL_CAP_ANY) #define SYSCALL_METADATA(sname, nb) \ SYSCALL_TRACE_ENTER_EVENT(sname); \ diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index 6f54012..e718a91 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -84,12 +84,7 @@ #undef TRACE_EVENT_FLAGS #define TRACE_EVENT_FLAGS(name, value) \ - static int __init trace_init_flags_##name(void) \ - { \ - event_##name.flags = value; \ - return 0; \ - } \ - early_initcall(trace_init_flags_##name); + __TRACE_EVENT_FLAGS(name, value) #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) -- cgit v1.1 From 423478cde453eebdfcfebf4b8d378d8f5d49b853 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 18 Nov 2010 02:21:26 +0100 Subject: tracing: Remove useless syscall ftrace_event_call declaration It is defined right after, which makes the declaration completely useless. Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Thomas Gleixner Cc: Steven Rostedt Cc: Li Zefan Cc: Jason Baron --- include/linux/syscalls.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 13b9731d..18cd068 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -127,8 +127,6 @@ extern struct trace_event_functions exit_syscall_print_funcs; #define SYSCALL_TRACE_ENTER_EVENT(sname) \ static struct syscall_metadata \ __attribute__((__aligned__(4))) __syscall_meta_##sname; \ - static struct ftrace_event_call \ - __attribute__((__aligned__(4))) event_enter_##sname; \ static struct ftrace_event_call __used \ __attribute__((__aligned__(4))) \ __attribute__((section("_ftrace_events"))) \ @@ -143,8 +141,6 @@ extern struct trace_event_functions exit_syscall_print_funcs; #define SYSCALL_TRACE_EXIT_EVENT(sname) \ static struct syscall_metadata \ __attribute__((__aligned__(4))) __syscall_meta_##sname; \ - static struct ftrace_event_call \ - __attribute__((__aligned__(4))) event_exit_##sname; \ static struct ftrace_event_call __used \ __attribute__((__aligned__(4))) \ __attribute__((section("_ftrace_events"))) \ -- cgit v1.1 From 5070437cd99511f69ae561f2ab417142a47a85ec Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Thu, 21 Oct 2010 17:55:01 +0200 Subject: power_supply: Add gpio charger driver This patch adds a simple driver for chargers indicating their online status through a GPIO pin. Signed-off-by: Lars-Peter Clausen Signed-off-by: Anton Vorontsov --- include/linux/power/gpio-charger.h | 41 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) create mode 100644 include/linux/power/gpio-charger.h (limited to 'include') diff --git a/include/linux/power/gpio-charger.h b/include/linux/power/gpio-charger.h new file mode 100644 index 0000000..de1dfe0 --- /dev/null +++ b/include/linux/power/gpio-charger.h @@ -0,0 +1,41 @@ +/* + * Copyright (C) 2010, Lars-Peter Clausen + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 675 Mass Ave, Cambridge, MA 02139, USA. + * + */ + +#ifndef __LINUX_POWER_GPIO_CHARGER_H__ +#define __LINUX_POWER_GPIO_CHARGER_H__ + +#include +#include + +/** + * struct gpio_charger_platform_data - platform_data for gpio_charger devices + * @name: Name for the chargers power_supply device + * @type: Type of the charger + * @gpio: GPIO which is used to indicate the chargers status + * @gpio_active_low: Should be set to 1 if the GPIO is active low otherwise 0 + * @supplied_to: Array of battery names to which this chargers supplies power + * @num_supplicants: Number of entries in the supplied_to array + */ +struct gpio_charger_platform_data { + const char *name; + enum power_supply_type type; + + int gpio; + int gpio_active_low; + + char **supplied_to; + size_t num_supplicants; +}; + +#endif -- cgit v1.1 From 866f3b25a2eb60d7529c227a0ecd80c3aba443fd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 18 Nov 2010 09:33:19 -0800 Subject: bonding: IGMP handling cleanup Instead of iterating in_dev->mc_list from bonding driver, its better to call a helper function provided by igmp.c Details of implementation (locking) are private to igmp code. ip_mc_rejoin_group(struct ip_mc_list *im) becomes ip_mc_rejoin_groups(struct in_device *in_dev); Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/igmp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 7d16467..c4987f2 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -238,7 +238,7 @@ extern void ip_mc_unmap(struct in_device *); extern void ip_mc_remap(struct in_device *); extern void ip_mc_dec_group(struct in_device *in_dev, __be32 addr); extern void ip_mc_inc_group(struct in_device *in_dev, __be32 addr); -extern void ip_mc_rejoin_group(struct ip_mc_list *im); +extern void ip_mc_rejoin_groups(struct in_device *in_dev); #endif #endif -- cgit v1.1 From 4c3710afbc333c33100739dec10662b4ee64e219 Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Tue, 16 Nov 2010 20:28:24 +0000 Subject: net: move definitions of BPF_S_* to net/core/filter.c BPF_S_* are used internally, should not be exposed to the others. Signed-off-by: Changli Gao Acked-by: Eric Dumazet Acked-by: Hagen Paul Pfeifer Signed-off-by: David S. Miller --- include/linux/filter.h | 48 ------------------------------------------------ 1 file changed, 48 deletions(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 69b43db..151f5d7 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -91,54 +91,6 @@ struct sock_fprog { /* Required for SO_ATTACH_FILTER. */ #define BPF_TAX 0x00 #define BPF_TXA 0x80 -enum { - BPF_S_RET_K = 0, - BPF_S_RET_A, - BPF_S_ALU_ADD_K, - BPF_S_ALU_ADD_X, - BPF_S_ALU_SUB_K, - BPF_S_ALU_SUB_X, - BPF_S_ALU_MUL_K, - BPF_S_ALU_MUL_X, - BPF_S_ALU_DIV_X, - BPF_S_ALU_AND_K, - BPF_S_ALU_AND_X, - BPF_S_ALU_OR_K, - BPF_S_ALU_OR_X, - BPF_S_ALU_LSH_K, - BPF_S_ALU_LSH_X, - BPF_S_ALU_RSH_K, - BPF_S_ALU_RSH_X, - BPF_S_ALU_NEG, - BPF_S_LD_W_ABS, - BPF_S_LD_H_ABS, - BPF_S_LD_B_ABS, - BPF_S_LD_W_LEN, - BPF_S_LD_W_IND, - BPF_S_LD_H_IND, - BPF_S_LD_B_IND, - BPF_S_LD_IMM, - BPF_S_LDX_W_LEN, - BPF_S_LDX_B_MSH, - BPF_S_LDX_IMM, - BPF_S_MISC_TAX, - BPF_S_MISC_TXA, - BPF_S_ALU_DIV_K, - BPF_S_LD_MEM, - BPF_S_LDX_MEM, - BPF_S_ST, - BPF_S_STX, - BPF_S_JMP_JA, - BPF_S_JMP_JEQ_K, - BPF_S_JMP_JEQ_X, - BPF_S_JMP_JGE_K, - BPF_S_JMP_JGE_X, - BPF_S_JMP_JGT_K, - BPF_S_JMP_JGT_X, - BPF_S_JMP_JSET_K, - BPF_S_JMP_JSET_X, -}; - #ifndef BPF_MAXINSNS #define BPF_MAXINSNS 4096 #endif -- cgit v1.1 From c5485a7e7569ab32eea240c850198519e2a765ef Mon Sep 17 00:00:00 2001 From: Bruno Randolf Date: Tue, 16 Nov 2010 10:58:37 +0900 Subject: lib: Add generic exponentially weighted moving average (EWMA) function This adds generic functions for calculating Exponentially Weighted Moving Averages (EWMA). This implementation makes use of a structure which keeps the EWMA parameters and a scaled up internal representation to reduce rounding errors. The original idea for this implementation came from the rt2x00 driver (rt2x00link.c). I would like to use it in several places in the mac80211 and ath5k code and I hope it can be useful in many other places in the kernel code. Signed-off-by: Bruno Randolf Reviewed-by: KOSAKI Motohiro Signed-off-by: John W. Linville --- include/linux/average.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) create mode 100644 include/linux/average.h (limited to 'include') diff --git a/include/linux/average.h b/include/linux/average.h new file mode 100644 index 0000000..7706e40 --- /dev/null +++ b/include/linux/average.h @@ -0,0 +1,32 @@ +#ifndef _LINUX_AVERAGE_H +#define _LINUX_AVERAGE_H + +#include + +/* Exponentially weighted moving average (EWMA) */ + +/* For more documentation see lib/average.c */ + +struct ewma { + unsigned long internal; + unsigned long factor; + unsigned long weight; +}; + +extern void ewma_init(struct ewma *avg, unsigned long factor, + unsigned long weight); + +extern struct ewma *ewma_add(struct ewma *avg, unsigned long val); + +/** + * ewma_read() - Get average value + * @avg: Average structure + * + * Returns the average value held in @avg. + */ +static inline unsigned long ewma_read(const struct ewma *avg) +{ + return DIV_ROUND_CLOSEST(avg->internal, avg->factor); +} + +#endif /* _LINUX_AVERAGE_H */ -- cgit v1.1 From 86107fd170bc379869250eb7e1bd393a3a70e8ae Mon Sep 17 00:00:00 2001 From: Bruno Randolf Date: Tue, 16 Nov 2010 10:58:48 +0900 Subject: nl80211/mac80211: Report signal average Extend nl80211 to report an exponential weighted moving average (EWMA) of the signal value. Since the signal value usually fluctuates between different packets, an average can be more useful than the value of the last packet. This uses the recently added generic EWMA library function. Signed-off-by: Bruno Randolf Signed-off-by: John W. Linville --- include/linux/nl80211.h | 2 ++ include/net/cfg80211.h | 4 ++++ 2 files changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 037b4e4..1ce3775 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -1161,6 +1161,7 @@ enum nl80211_rate_info { * @__NL80211_STA_INFO_AFTER_LAST: internal * @NL80211_STA_INFO_MAX: highest possible station info attribute * @NL80211_STA_INFO_SIGNAL: signal strength of last received PPDU (u8, dBm) + * @NL80211_STA_INFO_SIGNAL_AVG: signal strength average (u8, dBm) * @NL80211_STA_INFO_TX_BITRATE: current unicast tx rate, nested attribute * containing info as possible, see &enum nl80211_sta_info_txrate. * @NL80211_STA_INFO_RX_PACKETS: total received packet (u32, from this station) @@ -1178,6 +1179,7 @@ enum nl80211_sta_info { NL80211_STA_INFO_PLID, NL80211_STA_INFO_PLINK_STATE, NL80211_STA_INFO_SIGNAL, + NL80211_STA_INFO_SIGNAL_AVG, NL80211_STA_INFO_TX_BITRATE, NL80211_STA_INFO_RX_PACKETS, NL80211_STA_INFO_TX_PACKETS, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 8fd9eeb..69e2364 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -424,6 +424,7 @@ struct station_parameters { * @STATION_INFO_TX_RETRIES: @tx_retries filled * @STATION_INFO_TX_FAILED: @tx_failed filled * @STATION_INFO_RX_DROP_MISC: @rx_dropped_misc filled + * @STATION_INFO_SIGNAL_AVG: @signal_avg filled */ enum station_info_flags { STATION_INFO_INACTIVE_TIME = 1<<0, @@ -439,6 +440,7 @@ enum station_info_flags { STATION_INFO_TX_RETRIES = 1<<10, STATION_INFO_TX_FAILED = 1<<11, STATION_INFO_RX_DROP_MISC = 1<<12, + STATION_INFO_SIGNAL_AVG = 1<<13, }; /** @@ -485,6 +487,7 @@ struct rate_info { * @plid: mesh peer link id * @plink_state: mesh peer link state * @signal: signal strength of last received packet in dBm + * @signal_avg: signal strength average in dBm * @txrate: current unicast bitrate to this station * @rx_packets: packets received from this station * @tx_packets: packets transmitted to this station @@ -505,6 +508,7 @@ struct station_info { u16 plid; u8 plink_state; s8 signal; + s8 signal_avg; struct rate_info txrate; u32 rx_packets; u32 tx_packets; -- cgit v1.1 From c2f9bff5ace07fbea03a53c6c3253f6c3a81e9f9 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 19 Oct 2010 21:04:42 +0800 Subject: net - Add AF_ALG macros This patch adds the socket family/level macros for the yet-to-be-born AF_ALG family. The AF_ALG family provides the user-space interface for the kernel crypto API. Signed-off-by: Herbert Xu Acked-by: David S. Miller --- include/linux/socket.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/socket.h b/include/linux/socket.h index 5146b50..ebc081b 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -193,7 +193,8 @@ struct ucred { #define AF_PHONET 35 /* Phonet sockets */ #define AF_IEEE802154 36 /* IEEE802154 sockets */ #define AF_CAIF 37 /* CAIF sockets */ -#define AF_MAX 38 /* For now.. */ +#define AF_ALG 38 /* Algorithm sockets */ +#define AF_MAX 39 /* For now.. */ /* Protocol families, same as address families. */ #define PF_UNSPEC AF_UNSPEC @@ -234,6 +235,7 @@ struct ucred { #define PF_PHONET AF_PHONET #define PF_IEEE802154 AF_IEEE802154 #define PF_CAIF AF_CAIF +#define PF_ALG AF_ALG #define PF_MAX AF_MAX /* Maximum queue length specifiable by listen. */ @@ -307,6 +309,7 @@ struct ucred { #define SOL_RDS 276 #define SOL_IUCV 277 #define SOL_CAIF 278 +#define SOL_ALG 279 /* IPX options */ #define IPX_TYPE 1 -- cgit v1.1 From 03c8efc1ffeb6b82a22c1af8dd908af349563314 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 19 Oct 2010 21:12:39 +0800 Subject: crypto: af_alg - User-space interface for Crypto API This patch creates the backbone of the user-space interface for the Crypto API, through a new socket family AF_ALG. Each session corresponds to one or more connections obtained from that socket. The number depends on the number of inputs/outputs of that particular type of operation. For most types there will be a s ingle connection/file descriptor that is used for both input and output. AEAD is one of the few that require two inputs. Each algorithm type will provide its own implementation that plugs into af_alg. They're keyed using a string such as "skcipher" or "hash". IOW this patch only contains the boring bits that is required to hold everything together. Thakns to Miloslav Trmac for reviewing this and contributing fixes and improvements. Signed-off-by: Herbert Xu Acked-by: David S. Miller Tested-by: Martin Willi --- include/crypto/if_alg.h | 92 +++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/if_alg.h | 40 +++++++++++++++++++++ 2 files changed, 132 insertions(+) create mode 100644 include/crypto/if_alg.h create mode 100644 include/linux/if_alg.h (limited to 'include') diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h new file mode 100644 index 0000000..c5813c8 --- /dev/null +++ b/include/crypto/if_alg.h @@ -0,0 +1,92 @@ +/* + * if_alg: User-space algorithm interface + * + * Copyright (c) 2010 Herbert Xu + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + */ + +#ifndef _CRYPTO_IF_ALG_H +#define _CRYPTO_IF_ALG_H + +#include +#include +#include +#include +#include + +#define ALG_MAX_PAGES 16 + +struct crypto_async_request; + +struct alg_sock { + /* struct sock must be the first member of struct alg_sock */ + struct sock sk; + + struct sock *parent; + + const struct af_alg_type *type; + void *private; +}; + +struct af_alg_completion { + struct completion completion; + int err; +}; + +struct af_alg_control { + struct af_alg_iv *iv; + int op; +}; + +struct af_alg_type { + void *(*bind)(const char *name, u32 type, u32 mask); + void (*release)(void *private); + int (*setkey)(void *private, const u8 *key, unsigned int keylen); + int (*accept)(void *private, struct sock *sk); + + struct proto_ops *ops; + struct module *owner; + char name[14]; +}; + +struct af_alg_sgl { + struct scatterlist sg[ALG_MAX_PAGES]; + struct page *pages[ALG_MAX_PAGES]; +}; + +int af_alg_register_type(const struct af_alg_type *type); +int af_alg_unregister_type(const struct af_alg_type *type); + +int af_alg_release(struct socket *sock); +int af_alg_accept(struct sock *sk, struct socket *newsock); + +int af_alg_make_sg(struct af_alg_sgl *sgl, void __user *addr, int len, + int write); +void af_alg_free_sg(struct af_alg_sgl *sgl); + +int af_alg_cmsg_send(struct msghdr *msg, struct af_alg_control *con); + +int af_alg_wait_for_completion(int err, struct af_alg_completion *completion); +void af_alg_complete(struct crypto_async_request *req, int err); + +static inline struct alg_sock *alg_sk(struct sock *sk) +{ + return (struct alg_sock *)sk; +} + +static inline void af_alg_release_parent(struct sock *sk) +{ + sock_put(alg_sk(sk)->parent); +} + +static inline void af_alg_init_completion(struct af_alg_completion *completion) +{ + init_completion(&completion->completion); +} + +#endif /* _CRYPTO_IF_ALG_H */ diff --git a/include/linux/if_alg.h b/include/linux/if_alg.h new file mode 100644 index 0000000..0f9acce --- /dev/null +++ b/include/linux/if_alg.h @@ -0,0 +1,40 @@ +/* + * if_alg: User-space algorithm interface + * + * Copyright (c) 2010 Herbert Xu + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + */ + +#ifndef _LINUX_IF_ALG_H +#define _LINUX_IF_ALG_H + +#include + +struct sockaddr_alg { + __u16 salg_family; + __u8 salg_type[14]; + __u32 salg_feat; + __u32 salg_mask; + __u8 salg_name[64]; +}; + +struct af_alg_iv { + __u32 ivlen; + __u8 iv[0]; +}; + +/* Socket options */ +#define ALG_SET_KEY 1 +#define ALG_SET_IV 2 +#define ALG_SET_OP 3 + +/* Operations */ +#define ALG_OP_DECRYPT 0 +#define ALG_OP_ENCRYPT 1 + +#endif /* _LINUX_IF_ALG_H */ -- cgit v1.1 From 042957801626465492b9428860de39a3cb2a8219 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 12 Nov 2010 22:32:11 -0500 Subject: tracing/events: Show real number in array fields Currently we have in something like the sched_switch event: field:char prev_comm[TASK_COMM_LEN]; offset:12; size:16; signed:1; When a userspace tool such as perf tries to parse this, the TASK_COMM_LEN is meaningless. This is done because the TRACE_EVENT() macro simply uses a #len to show the string of the length. When the length is an enum, we get a string that means nothing for tools. By adding a static buffer and a mutex to protect it, we can store the string into that buffer with snprintf and show the actual number. Now we get: field:char prev_comm[16]; offset:12; size:16; signed:1; Something much more useful. Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 4 ++++ include/trace/ftrace.h | 14 ++++++++++---- 2 files changed, 14 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 725bf6b..47e3997 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -225,6 +225,10 @@ enum { FILTER_PTR_STRING, }; +#define EVENT_STORAGE_SIZE 128 +extern struct mutex event_storage_mutex; +extern char event_storage[EVENT_STORAGE_SIZE]; + extern int trace_event_raw_init(struct ftrace_event_call *call); extern int trace_define_field(struct ftrace_event_call *call, const char *type, const char *name, int offset, int size, diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index e718a91..e16610c 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -296,13 +296,19 @@ static struct trace_event_functions ftrace_event_type_funcs_##call = { \ #undef __array #define __array(type, item, len) \ - BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ - ret = trace_define_field(event_call, #type "[" #len "]", #item, \ + do { \ + mutex_lock(&event_storage_mutex); \ + BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ + snprintf(event_storage, sizeof(event_storage), \ + "%s[%d]", #type, len); \ + ret = trace_define_field(event_call, event_storage, #item, \ offsetof(typeof(field), item), \ sizeof(field.item), \ is_signed_type(type), FILTER_OTHER); \ - if (ret) \ - return ret; + mutex_unlock(&event_storage_mutex); \ + if (ret) \ + return ret; \ + } while (0); #undef __dynamic_array #define __dynamic_array(type, item, len) \ -- cgit v1.1 From 93aaae2e01e57483256b7da05c9a7ebd65ad4686 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 19 Nov 2010 09:49:59 -0800 Subject: filter: optimize sk_run_filter Remove pc variable to avoid arithmetic to compute fentry at each filter instruction. Jumps directly manipulate fentry pointer. As the last instruction of filter[] is guaranteed to be a RETURN, and all jumps are before the last instruction, we dont need to check filter bounds (number of instructions in filter array) at each iteration, so we remove it from sk_run_filter() params. On x86_32 remove f_k var introduced in commit 57fe93b374a6b871 (filter: make sure filters dont read uninitialized memory) Note : We could use a CONFIG_ARCH_HAS_{FEW|MANY}_REGISTERS in order to avoid too many ifdefs in this code. This helps compiler to use cpu registers to hold fentry and A accumulator. On x86_32, this saves 401 bytes, and more important, sk_run_filter() runs much faster because less register pressure (One less conditional branch per BPF instruction) # size net/core/filter.o net/core/filter_pre.o text data bss dec hex filename 2948 0 0 2948 b84 net/core/filter.o 3349 0 0 3349 d15 net/core/filter_pre.o on x86_64 : # size net/core/filter.o net/core/filter_pre.o text data bss dec hex filename 5173 0 0 5173 1435 net/core/filter.o 5224 0 0 5224 1468 net/core/filter_pre.o Signed-off-by: Eric Dumazet Acked-by: Changli Gao Signed-off-by: David S. Miller --- include/linux/filter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 151f5d7..447a775 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -147,7 +147,7 @@ struct sock; extern int sk_filter(struct sock *sk, struct sk_buff *skb); extern unsigned int sk_run_filter(struct sk_buff *skb, - struct sock_filter *filter, int flen); + const struct sock_filter *filter); extern int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); extern int sk_detach_filter(struct sock *sk); extern int sk_chk_filter(struct sock_filter *filter, int flen); -- cgit v1.1 From 20a95a2169d1cd3da50cf65ba882d0e27a4a2d4f Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Sat, 20 Nov 2010 18:07:21 +0000 Subject: netns: let net_generic take pointer-to-const args This commit is same in nature as v2.6.37-rc1-755-g3654654; the network namespace itself is not modified when calling net_generic, so the parameter can be const. Signed-off-by: Jan Engelhardt Signed-off-by: David S. Miller --- include/net/netns/generic.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netns/generic.h b/include/net/netns/generic.h index 81a31c0..3419bf5 100644 --- a/include/net/netns/generic.h +++ b/include/net/netns/generic.h @@ -30,7 +30,7 @@ struct net_generic { void *ptr[0]; }; -static inline void *net_generic(struct net *net, int id) +static inline void *net_generic(const struct net *net, int id) { struct net_generic *ng; void *ptr; -- cgit v1.1 From 27641c3f003e7f3b6585c01d8a788883603eb262 Mon Sep 17 00:00:00 2001 From: Mario Kleiner Date: Sat, 23 Oct 2010 04:20:23 +0200 Subject: drm/vblank: Add support for precise vblank timestamping. The DRI2 swap & sync implementation needs precise vblank counts and precise timestamps corresponding to those vblank counts. For conformance to the OpenML OML_sync_control extension specification the DRM timestamp associated with a vblank count should correspond to the start of video scanout of the first scanline of the video frame following the vblank interval for that vblank count. Therefore we need to carry around precise timestamps for vblanks. Currently the DRM and KMS drivers generate timestamps ad-hoc via do_gettimeofday() in some places. The resulting timestamps are sometimes not very precise due to interrupt handling delays, they don't conform to OML_sync_control and some are wrong, as they aren't taken synchronized to the vblank. This patch implements support inside the drm core for precise and robust timestamping. It consists of the following interrelated pieces. 1. Vblank timestamp caching: A per-crtc ringbuffer stores the most recent vblank timestamps corresponding to vblank counts. The ringbuffer can be read out lock-free via the accessor function: struct timeval timestamp; vblankcount = drm_vblank_count_and_time(dev, crtcid, ×tamp). The function returns the current vblank count and the corresponding timestamp for start of video scanout following the vblank interval. It can be used anywhere between enclosing drm_vblank_get(dev, crtcid) and drm_vblank_put(dev,crtcid) statements. It is used inside the drmWaitVblank ioctl and in the vblank event queueing and handling. It should be used by kms drivers for timestamping of bufferswap completion. The timestamp ringbuffer is reinitialized each time vblank irq's get reenabled in drm_vblank_get()/ drm_update_vblank_count(). It is invalidated when vblank irq's get disabled. The ringbuffer is updated inside drm_handle_vblank() at each vblank irq. 2. Calculation of precise vblank timestamps: drm_get_last_vbltimestamp() is used to compute the timestamp for the end of the most recent vblank (if inside active scanout), or the expected end of the current vblank interval (if called inside a vblank interval). The function calls into a new optional kms driver entry point dev->driver->get_vblank_timestamp() which is supposed to provide the precise timestamp. If a kms driver doesn't implement the entry point or if the call fails, a simple do_gettimeofday() timestamp is returned as crude approximation of the true vblank time. A new drm module parameter drm.timestamp_precision_usec allows to disable high precision timestamps (if set to zero) or to specify the maximum acceptable error in the timestamps in microseconds. Kms drivers could implement their get_vblank_timestamp() function in a gpu specific way, as long as returned timestamps conform to OML_sync_control, e.g., by use of gpu specific hardware timestamps. Optionally, kms drivers can simply wrap and use the new utility function drm_calc_vbltimestamp_from_scanoutpos(). This function calls a new optional kms driver function dev->driver->get_scanout_position() which returns the current horizontal and vertical video scanout position of the crtc. The scanout position together with the drm_display_timing of the current video mode is used to calculate elapsed time relative to start of active scanout for the current video frame. This elapsed time is subtracted from the current do_gettimeofday() time to get the timestamp corresponding to start of video scanout. Currently non-interlaced, non-doublescan video modes, with or without panel scaling are handled correctly. Interlaced/ doublescan modes are tbd in a future patch. 3. Filtering of redundant vblank irq's and removal of some race-conditions in the vblank irq enable/disable path: Some gpu's (e.g., Radeon R500/R600) send spurious vblank irq's outside the vblank if vblank irq's get reenabled. These get detected by use of the vblank timestamps and filtered out to avoid miscounting of vblanks. Some race-conditions between the vblank irq enable/disable functions, the vblank irq handler and the gpu itself (updating its hardware vblank counter in the "wrong" moment) are fixed inside vblank_disable_and_save() and drm_update_vblank_count() by use of the vblank timestamps and a new spinlock dev->vblank_time_lock. The time until vblank irq disable is now configurable via a new drm module parameter drm.vblankoffdelay to allow experimentation with timeouts that are much shorter than the current 5 seconds and should allow longer vblank off periods for better power savings. Followup patches will use these new functions to implement precise timestamping for the intel and radeon kms drivers. Signed-off-by: Mario Kleiner Signed-off-by: Dave Airlie --- include/drm/drmP.h | 93 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/drm/drm_crtc.h | 9 +++++ 2 files changed, 102 insertions(+) (limited to 'include') diff --git a/include/drm/drmP.h b/include/drm/drmP.h index 274eaaa..2b33980 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -683,6 +683,21 @@ struct drm_master { void *driver_priv; /**< Private structure for driver to use */ }; +/* Size of ringbuffer for vblank timestamps. Just double-buffer + * in initial implementation. + */ +#define DRM_VBLANKTIME_RBSIZE 2 + +/* Flags and return codes for get_vblank_timestamp() driver function. */ +#define DRM_CALLED_FROM_VBLIRQ 1 +#define DRM_VBLANKTIME_SCANOUTPOS_METHOD (1 << 0) +#define DRM_VBLANKTIME_INVBL (1 << 1) + +/* get_scanout_position() return flags */ +#define DRM_SCANOUTPOS_VALID (1 << 0) +#define DRM_SCANOUTPOS_INVBL (1 << 1) +#define DRM_SCANOUTPOS_ACCURATE (1 << 2) + /** * DRM driver structure. This structure represent the common code for * a family of cards. There will one drm_device for each card present @@ -760,6 +775,68 @@ struct drm_driver { */ int (*device_is_agp) (struct drm_device *dev); + /** + * Called by vblank timestamping code. + * + * Return the current display scanout position from a crtc. + * + * \param dev DRM device. + * \param crtc Id of the crtc to query. + * \param *vpos Target location for current vertical scanout position. + * \param *hpos Target location for current horizontal scanout position. + * + * Returns vpos as a positive number while in active scanout area. + * Returns vpos as a negative number inside vblank, counting the number + * of scanlines to go until end of vblank, e.g., -1 means "one scanline + * until start of active scanout / end of vblank." + * + * \return Flags, or'ed together as follows: + * + * DRM_SCANOUTPOS_VALID = Query successfull. + * DRM_SCANOUTPOS_INVBL = Inside vblank. + * DRM_SCANOUTPOS_ACCURATE = Returned position is accurate. A lack of + * this flag means that returned position may be offset by a constant + * but unknown small number of scanlines wrt. real scanout position. + * + */ + int (*get_scanout_position) (struct drm_device *dev, int crtc, + int *vpos, int *hpos); + + /** + * Called by \c drm_get_last_vbltimestamp. Should return a precise + * timestamp when the most recent VBLANK interval ended or will end. + * + * Specifically, the timestamp in @vblank_time should correspond as + * closely as possible to the time when the first video scanline of + * the video frame after the end of VBLANK will start scanning out, + * the time immmediately after end of the VBLANK interval. If the + * @crtc is currently inside VBLANK, this will be a time in the future. + * If the @crtc is currently scanning out a frame, this will be the + * past start time of the current scanout. This is meant to adhere + * to the OpenML OML_sync_control extension specification. + * + * \param dev dev DRM device handle. + * \param crtc crtc for which timestamp should be returned. + * \param *max_error Maximum allowable timestamp error in nanoseconds. + * Implementation should strive to provide timestamp + * with an error of at most *max_error nanoseconds. + * Returns true upper bound on error for timestamp. + * \param *vblank_time Target location for returned vblank timestamp. + * \param flags 0 = Defaults, no special treatment needed. + * \param DRM_CALLED_FROM_VBLIRQ = Function is called from vblank + * irq handler. Some drivers need to apply some workarounds + * for gpu-specific vblank irq quirks if flag is set. + * + * \returns + * Zero if timestamping isn't supported in current display mode or a + * negative number on failure. A positive status code on success, + * which describes how the vblank_time timestamp was computed. + */ + int (*get_vblank_timestamp) (struct drm_device *dev, int crtc, + int *max_error, + struct timeval *vblank_time, + unsigned flags); + /* these have to be filled in */ irqreturn_t(*irq_handler) (DRM_IRQ_ARGS); @@ -983,6 +1060,8 @@ struct drm_device { wait_queue_head_t *vbl_queue; /**< VBLANK wait queue */ atomic_t *_vblank_count; /**< number of VBLANK interrupts (driver must alloc the right number of counters) */ + struct timeval *_vblank_time; /**< timestamp of current vblank_count (drivers must alloc right number of fields) */ + spinlock_t vblank_time_lock; /**< Protects vblank count and time updates during vblank enable/disable */ spinlock_t vbl_lock; atomic_t *vblank_refcount; /* number of users of vblank interruptsper crtc */ u32 *last_vblank; /* protected by dev->vbl_lock, used */ @@ -1284,11 +1363,22 @@ extern int drm_wait_vblank(struct drm_device *dev, void *data, struct drm_file *filp); extern int drm_vblank_wait(struct drm_device *dev, unsigned int *vbl_seq); extern u32 drm_vblank_count(struct drm_device *dev, int crtc); +extern u32 drm_vblank_count_and_time(struct drm_device *dev, int crtc, + struct timeval *vblanktime); extern void drm_handle_vblank(struct drm_device *dev, int crtc); extern int drm_vblank_get(struct drm_device *dev, int crtc); extern void drm_vblank_put(struct drm_device *dev, int crtc); extern void drm_vblank_off(struct drm_device *dev, int crtc); extern void drm_vblank_cleanup(struct drm_device *dev); +extern u32 drm_get_last_vbltimestamp(struct drm_device *dev, int crtc, + struct timeval *tvblank, unsigned flags); +extern int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, + int crtc, int *max_error, + struct timeval *vblank_time, + unsigned flags, + struct drm_crtc *refcrtc); +extern void drm_calc_timestamping_constants(struct drm_crtc *crtc); + /* Modesetting support */ extern void drm_vblank_pre_modeset(struct drm_device *dev, int crtc); extern void drm_vblank_post_modeset(struct drm_device *dev, int crtc); @@ -1340,6 +1430,9 @@ extern void drm_put_dev(struct drm_device *dev); extern int drm_put_minor(struct drm_minor **minor); extern unsigned int drm_debug; +extern unsigned int drm_vblank_offdelay; +extern unsigned int drm_timestamp_precision; + extern struct class *drm_class; extern struct proc_dir_entry *drm_proc_root; extern struct dentry *drm_debugfs_root; diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h index 029aa68..acd7fad 100644 --- a/include/drm/drm_crtc.h +++ b/include/drm/drm_crtc.h @@ -351,8 +351,14 @@ struct drm_crtc { bool enabled; + /* Requested mode from modesetting. */ struct drm_display_mode mode; + /* Programmed mode in hw, after adjustments for encoders, + * crtc, panel scaling etc. Needed for timestamping etc. + */ + struct drm_display_mode hwmode; + int x, y; const struct drm_crtc_funcs *funcs; @@ -360,6 +366,9 @@ struct drm_crtc { uint32_t gamma_size; uint16_t *gamma_store; + /* Constants needed for precise vblank and swap timestamping. */ + s64 framedur_ns, linedur_ns, pixeldur_ns; + /* if you are using the helper */ void *helper_private; }; -- cgit v1.1 From d6ea88865d3e5b0c62040531310c1f2c6a994f46 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Mon, 22 Nov 2010 13:24:40 +1000 Subject: drm/ttm: Add a bo list reserve fastpath (v2) Makes it possible to reserve a list of buffer objects with a single spin lock / unlock if there is no contention. Should improve cpu usage on SMP kernels. v2: Initialize private list members on reserve and don't call ttm_bo_list_ref_sub() with zero put_count. Signed-off-by: Thomas Hellstrom Signed-off-by: Dave Airlie --- include/drm/ttm/ttm_bo_api.h | 38 ++++++++++++++++++++++++++++++++++++++ include/drm/ttm/ttm_bo_driver.h | 14 ++++++++++++++ include/drm/ttm/ttm_execbuf_util.h | 6 +++++- 3 files changed, 57 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index beafc15..b0fc9c1 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -364,6 +364,44 @@ extern int ttm_bo_validate(struct ttm_buffer_object *bo, */ extern void ttm_bo_unref(struct ttm_buffer_object **bo); + +/** + * ttm_bo_list_ref_sub + * + * @bo: The buffer object. + * @count: The number of references with which to decrease @bo::list_kref; + * @never_free: The refcount should not reach zero with this operation. + * + * Release @count lru list references to this buffer object. + */ +extern void ttm_bo_list_ref_sub(struct ttm_buffer_object *bo, int count, + bool never_free); + +/** + * ttm_bo_add_to_lru + * + * @bo: The buffer object. + * + * Add this bo to the relevant mem type lru and, if it's backed by + * system pages (ttms) to the swap list. + * This function must be called with struct ttm_bo_global::lru_lock held, and + * is typically called immediately prior to unreserving a bo. + */ +extern void ttm_bo_add_to_lru(struct ttm_buffer_object *bo); + +/** + * ttm_bo_del_from_lru + * + * @bo: The buffer object. + * + * Remove this bo from all lru lists used to lookup and reserve an object. + * This function must be called with struct ttm_bo_global::lru_lock held, + * and is usually called just immediately after the bo has been reserved to + * avoid recursive reservation from lru lists. + */ +extern int ttm_bo_del_from_lru(struct ttm_buffer_object *bo); + + /** * ttm_bo_lock_delayed_workqueue * diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 8e0c848..95068e6 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -864,6 +864,20 @@ extern int ttm_bo_reserve(struct ttm_buffer_object *bo, bool interruptible, bool no_wait, bool use_sequence, uint32_t sequence); + +/** + * ttm_bo_reserve_locked: + * + * Similar to ttm_bo_reserve, but must be called with the glob::lru_lock + * spinlock held, and will not remove reserved buffers from the lru lists. + * The function may release the LRU spinlock if it needs to sleep. + */ + +extern int ttm_bo_reserve_locked(struct ttm_buffer_object *bo, + bool interruptible, + bool no_wait, bool use_sequence, + uint32_t sequence); + /** * ttm_bo_unreserve * diff --git a/include/drm/ttm/ttm_execbuf_util.h b/include/drm/ttm/ttm_execbuf_util.h index cd2c475..fd09b84 100644 --- a/include/drm/ttm/ttm_execbuf_util.h +++ b/include/drm/ttm/ttm_execbuf_util.h @@ -41,7 +41,9 @@ * @bo: refcounted buffer object pointer. * @new_sync_obj_arg: New sync_obj_arg for @bo, to be used once * adding a new sync object. - * @reservied: Indicates whether @bo has been reserved for validation. + * @reserved: Indicates whether @bo has been reserved for validation. + * @removed: Indicates whether @bo has been removed from lru lists. + * @put_count: Number of outstanding references on bo::list_kref. */ struct ttm_validate_buffer { @@ -49,6 +51,8 @@ struct ttm_validate_buffer { struct ttm_buffer_object *bo; void *new_sync_obj_arg; bool reserved; + bool removed; + int put_count; }; /** -- cgit v1.1 From ecf7ace9a8450303a987aa8364e53860cd50e554 Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Tue, 16 Nov 2010 15:21:07 +0100 Subject: kref: Add a kref_sub function Makes it possible to optimize batched multiple unrefs. Initial user will be drivers/gpu/ttm which accumulates unrefs to be processed outside of atomic code. Signed-off-by: Thomas Hellstrom Signed-off-by: Dave Airlie --- include/linux/kref.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/kref.h b/include/linux/kref.h index 6cc38fc..d4a62ab 100644 --- a/include/linux/kref.h +++ b/include/linux/kref.h @@ -24,5 +24,7 @@ struct kref { void kref_init(struct kref *kref); void kref_get(struct kref *kref); int kref_put(struct kref *kref, void (*release) (struct kref *kref)); +int kref_sub(struct kref *kref, unsigned int count, + void (*release) (struct kref *kref)); #endif /* _KREF_H_ */ -- cgit v1.1 From 96726fe50feae74812a2ccf5d5da23cb01c0a413 Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Wed, 17 Nov 2010 12:28:28 +0000 Subject: drm/ttm: Don't deadlock on recursive multi-bo reservations Add an aid for the driver to detect deadlocks on multi-bo reservations Update documentation. Signed-off-by: Thomas Hellstrom Reviewed-by: Jerome Glisse Signed-off-by: Dave Airlie --- include/drm/ttm/ttm_bo_driver.h | 25 ++++++++++++++++++++++--- 1 file changed, 22 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 95068e6..1e25a40 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -859,6 +859,9 @@ extern void ttm_bo_unmap_virtual(struct ttm_buffer_object *bo); * try again. (only if use_sequence == 1). * -ERESTARTSYS: A wait for the buffer to become unreserved was interrupted by * a signal. Release all buffer reservations and return to user-space. + * -EBUSY: The function needed to sleep, but @no_wait was true + * -EDEADLK: Bo already reserved using @sequence. This error code will only + * be returned if @use_sequence is set to true. */ extern int ttm_bo_reserve(struct ttm_buffer_object *bo, bool interruptible, @@ -868,11 +871,27 @@ extern int ttm_bo_reserve(struct ttm_buffer_object *bo, /** * ttm_bo_reserve_locked: * - * Similar to ttm_bo_reserve, but must be called with the glob::lru_lock - * spinlock held, and will not remove reserved buffers from the lru lists. + * @bo: A pointer to a struct ttm_buffer_object. + * @interruptible: Sleep interruptible if waiting. + * @no_wait: Don't sleep while trying to reserve, rather return -EBUSY. + * @use_sequence: If @bo is already reserved, Only sleep waiting for + * it to become unreserved if @sequence < (@bo)->sequence. + * + * Must be called with struct ttm_bo_global::lru_lock held, + * and will not remove reserved buffers from the lru lists. * The function may release the LRU spinlock if it needs to sleep. + * Otherwise identical to ttm_bo_reserve. + * + * Returns: + * -EAGAIN: The reservation may cause a deadlock. + * Release all buffer reservations, wait for @bo to become unreserved and + * try again. (only if use_sequence == 1). + * -ERESTARTSYS: A wait for the buffer to become unreserved was interrupted by + * a signal. Release all buffer reservations and return to user-space. + * -EBUSY: The function needed to sleep, but @no_wait was true + * -EDEADLK: Bo already reserved using @sequence. This error code will only + * be returned if @use_sequence is set to true. */ - extern int ttm_bo_reserve_locked(struct ttm_buffer_object *bo, bool interruptible, bool no_wait, bool use_sequence, -- cgit v1.1 From 702adba22433c175e8429a47760f35ca16caf1cd Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Wed, 17 Nov 2010 12:28:29 +0000 Subject: drm/ttm/radeon/nouveau: Kill the bo lock in favour of a bo device fence_lock The bo lock used only to protect the bo sync object members, and since it is a per bo lock, fencing a buffer list will see a lot of locks and unlocks. Replace it with a per-device lock that protects the sync object members on *all* bos. Reading and setting these members will always be very quick, so the risc of heavy lock contention is microscopic. Note that waiting for sync objects will always take place outside of this lock. The bo device fence lock will eventually be replaced with a seqlock / rcu mechanism so we can determine that a bo is idle under a rcu / read seqlock. However this change will allow us to batch fencing and unreserving of buffers with a minimal amount of locking. Signed-off-by: Thomas Hellstrom Reviewed-by: Jerome Glisse Signed-off-by: Dave Airlie --- include/drm/ttm/ttm_bo_api.h | 6 ++---- include/drm/ttm/ttm_bo_driver.h | 3 +++ 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index b0fc9c1..edacd48 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -154,7 +154,6 @@ struct ttm_tt; * keeps one refcount. When this refcount reaches zero, * the object is destroyed. * @event_queue: Queue for processes waiting on buffer object status change. - * @lock: spinlock protecting mostly synchronization members. * @mem: structure describing current placement. * @persistant_swap_storage: Usually the swap storage is deleted for buffers * pinned in physical memory. If this behaviour is not desired, this member @@ -213,7 +212,6 @@ struct ttm_buffer_object { struct kref kref; struct kref list_kref; wait_queue_head_t event_queue; - spinlock_t lock; /** * Members protected by the bo::reserved lock. @@ -248,10 +246,10 @@ struct ttm_buffer_object { atomic_t reserved; /** - * Members protected by the bo::lock + * Members protected by struct buffer_object_device::fence_lock * In addition, setting sync_obj to anything else * than NULL requires bo::reserved to be held. This allows for - * checking NULL while reserved but not holding bo::lock. + * checking NULL while reserved but not holding the mentioned lock. */ void *sync_obj_arg; diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 1e25a40..ca8131e 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -510,6 +510,8 @@ struct ttm_bo_global { * * @driver: Pointer to a struct ttm_bo_driver struct setup by the driver. * @man: An array of mem_type_managers. + * @fence_lock: Protects the synchronizing members on *all* bos belonging + * to this device. * @addr_space_mm: Range manager for the device address space. * lru_lock: Spinlock that protects the buffer+device lru lists and * ddestroy lists. @@ -531,6 +533,7 @@ struct ttm_bo_device { struct ttm_bo_driver *driver; rwlock_t vm_lock; struct ttm_mem_type_manager man[TTM_NUM_MEM_TYPES]; + spinlock_t fence_lock; /* * Protected by the vm lock. */ -- cgit v1.1 From 95762c2b34069bf4adb7929969f1f5f5fc8a38df Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Wed, 17 Nov 2010 12:28:30 +0000 Subject: drm/ttm: Improved fencing of buffer object lists Drastically reduce the number of spin lock / unlock operations by performing unreserving and fencing under global locks. Signed-off-by: Thomas Hellstrom Reviewed-by: Jerome Glisse Signed-off-by: Dave Airlie --- include/drm/ttm/ttm_bo_driver.h | 10 ++++++++++ include/drm/ttm/ttm_execbuf_util.h | 2 ++ 2 files changed, 12 insertions(+) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index ca8131e..cfb9ca4 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -910,6 +910,16 @@ extern int ttm_bo_reserve_locked(struct ttm_buffer_object *bo, extern void ttm_bo_unreserve(struct ttm_buffer_object *bo); /** + * ttm_bo_unreserve_locked + * + * @bo: A pointer to a struct ttm_buffer_object. + * + * Unreserve a previous reservation of @bo. + * Needs to be called with struct ttm_bo_global::lru_lock held. + */ +extern void ttm_bo_unreserve_locked(struct ttm_buffer_object *bo); + +/** * ttm_bo_wait_unreserved * * @bo: A pointer to a struct ttm_buffer_object. diff --git a/include/drm/ttm/ttm_execbuf_util.h b/include/drm/ttm/ttm_execbuf_util.h index fd09b84..535ab00 100644 --- a/include/drm/ttm/ttm_execbuf_util.h +++ b/include/drm/ttm/ttm_execbuf_util.h @@ -44,6 +44,7 @@ * @reserved: Indicates whether @bo has been reserved for validation. * @removed: Indicates whether @bo has been removed from lru lists. * @put_count: Number of outstanding references on bo::list_kref. + * @old_sync_obj: Pointer to a sync object about to be unreferenced */ struct ttm_validate_buffer { @@ -53,6 +54,7 @@ struct ttm_validate_buffer { bool reserved; bool removed; int put_count; + void *old_sync_obj; }; /** -- cgit v1.1 From 65705962025df490d13df59ec57c5329d1bd0a16 Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Wed, 17 Nov 2010 12:28:31 +0000 Subject: drm/ttm/vmwgfx: Have TTM manage the validation sequence. Rather than having the driver supply the validation sequence, leave that responsibility to TTM. This saves some confusion and a function argument. Signed-off-by: Thomas Hellstrom Signed-off-by: Dave Airlie --- include/drm/ttm/ttm_bo_driver.h | 2 ++ include/drm/ttm/ttm_execbuf_util.h | 3 +-- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index cfb9ca4..e3b2e24 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -515,6 +515,7 @@ struct ttm_bo_global { * @addr_space_mm: Range manager for the device address space. * lru_lock: Spinlock that protects the buffer+device lru lists and * ddestroy lists. + * @val_seq: Current validation sequence. * @nice_mode: Try nicely to wait for buffer idle when cleaning a manager. * If a GPU lockup has been detected, this is forced to 0. * @dev_mapping: A pointer to the struct address_space representing the @@ -544,6 +545,7 @@ struct ttm_bo_device { * Protected by the global:lru lock. */ struct list_head ddestroy; + uint32_t val_seq; /* * Protected by load / firstopen / lastclose /unload sync. diff --git a/include/drm/ttm/ttm_execbuf_util.h b/include/drm/ttm/ttm_execbuf_util.h index 535ab00..26cc7f9 100644 --- a/include/drm/ttm/ttm_execbuf_util.h +++ b/include/drm/ttm/ttm_execbuf_util.h @@ -72,7 +72,6 @@ extern void ttm_eu_backoff_reservation(struct list_head *list); * function ttm_eu_reserve_buffers * * @list: thread private list of ttm_validate_buffer structs. - * @val_seq: A unique sequence number. * * Tries to reserve bos pointed to by the list entries for validation. * If the function returns 0, all buffers are marked as "unfenced", @@ -94,7 +93,7 @@ extern void ttm_eu_backoff_reservation(struct list_head *list); * has failed. */ -extern int ttm_eu_reserve_buffers(struct list_head *list, uint32_t val_seq); +extern int ttm_eu_reserve_buffers(struct list_head *list); /** * function ttm_eu_fence_buffer_objects. -- cgit v1.1 From eba67093f535322cb4f1c4b737319c0907a0c81d Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Thu, 11 Nov 2010 09:41:57 +0100 Subject: drm/ttm: Fix up io_mem_reserve / io_mem_free calling This patch attempts to fix up shortcomings with the current calling sequences. 1) There's a fastpath where no locking occurs and only io_mem_reserved is called to obtain needed info for mapping. The fastpath is set per memory type manager. 2) If the fastpath is disabled, io_mem_reserve and io_mem_free will be exactly balanced and not called recursively for the same struct ttm_mem_reg. 3) Optionally the driver can choose to enable a per memory type manager LRU eviction mechanism that, when io_mem_reserve returns -EAGAIN will attempt to kill user-space mappings of memory in that manager to free up needed resources Signed-off-by: Thomas Hellstrom Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie --- include/drm/ttm/ttm_bo_api.h | 6 ++- include/drm/ttm/ttm_bo_driver.h | 104 +++++++++++++++++++++------------------- 2 files changed, 60 insertions(+), 50 deletions(-) (limited to 'include') diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index edacd48..50852aa 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -74,6 +74,8 @@ struct ttm_placement { * @is_iomem: is this io memory ? * @size: size in byte * @offset: offset from the base address + * @io_reserved_vm: The VM system has a refcount in @io_reserved_count + * @io_reserved_count: Refcounting the numbers of callers to ttm_mem_io_reserve * * Structure indicating the bus placement of an object. */ @@ -83,7 +85,8 @@ struct ttm_bus_placement { unsigned long size; unsigned long offset; bool is_iomem; - bool io_reserved; + bool io_reserved_vm; + uint64_t io_reserved_count; }; @@ -235,6 +238,7 @@ struct ttm_buffer_object { struct list_head lru; struct list_head ddestroy; struct list_head swap; + struct list_head io_reserve_lru; uint32_t val_seq; bool seq_valid; diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index e3b2e24..1da8af6 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -179,30 +179,6 @@ struct ttm_tt { #define TTM_MEMTYPE_FLAG_MAPPABLE (1 << 1) /* Memory mappable */ #define TTM_MEMTYPE_FLAG_CMA (1 << 3) /* Can't map aperture */ -/** - * struct ttm_mem_type_manager - * - * @has_type: The memory type has been initialized. - * @use_type: The memory type is enabled. - * @flags: TTM_MEMTYPE_XX flags identifying the traits of the memory - * managed by this memory type. - * @gpu_offset: If used, the GPU offset of the first managed page of - * fixed memory or the first managed location in an aperture. - * @size: Size of the managed region. - * @available_caching: A mask of available caching types, TTM_PL_FLAG_XX, - * as defined in ttm_placement_common.h - * @default_caching: The default caching policy used for a buffer object - * placed in this memory type if the user doesn't provide one. - * @manager: The range manager used for this memory type. FIXME: If the aperture - * has a page size different from the underlying system, the granularity - * of this manager should take care of this. But the range allocating code - * in ttm_bo.c needs to be modified for this. - * @lru: The lru list for this memory type. - * - * This structure is used to identify and manage memory types for a device. - * It's set up by the ttm_bo_driver::init_mem_type method. - */ - struct ttm_mem_type_manager; struct ttm_mem_type_manager_func { @@ -287,6 +263,36 @@ struct ttm_mem_type_manager_func { void (*debug)(struct ttm_mem_type_manager *man, const char *prefix); }; +/** + * struct ttm_mem_type_manager + * + * @has_type: The memory type has been initialized. + * @use_type: The memory type is enabled. + * @flags: TTM_MEMTYPE_XX flags identifying the traits of the memory + * managed by this memory type. + * @gpu_offset: If used, the GPU offset of the first managed page of + * fixed memory or the first managed location in an aperture. + * @size: Size of the managed region. + * @available_caching: A mask of available caching types, TTM_PL_FLAG_XX, + * as defined in ttm_placement_common.h + * @default_caching: The default caching policy used for a buffer object + * placed in this memory type if the user doesn't provide one. + * @func: structure pointer implementing the range manager. See above + * @priv: Driver private closure for @func. + * @io_reserve_mutex: Mutex optionally protecting shared io_reserve structures + * @use_io_reserve_lru: Use an lru list to try to unreserve io_mem_regions + * reserved by the TTM vm system. + * @io_reserve_lru: Optional lru list for unreserving io mem regions. + * @io_reserve_fastpath: Only use bdev::driver::io_mem_reserve to obtain + * static information. bdev::driver::io_mem_free is never used. + * @lru: The lru list for this memory type. + * + * This structure is used to identify and manage memory types for a device. + * It's set up by the ttm_bo_driver::init_mem_type method. + */ + + + struct ttm_mem_type_manager { struct ttm_bo_device *bdev; @@ -303,6 +309,15 @@ struct ttm_mem_type_manager { uint32_t default_caching; const struct ttm_mem_type_manager_func *func; void *priv; + struct mutex io_reserve_mutex; + bool use_io_reserve_lru; + bool io_reserve_fastpath; + + /* + * Protected by @io_reserve_mutex: + */ + + struct list_head io_reserve_lru; /* * Protected by the global->lru_lock. @@ -758,31 +773,6 @@ extern void ttm_bo_mem_put_locked(struct ttm_buffer_object *bo, extern int ttm_bo_wait_cpu(struct ttm_buffer_object *bo, bool no_wait); -/** - * ttm_bo_pci_offset - Get the PCI offset for the buffer object memory. - * - * @bo Pointer to a struct ttm_buffer_object. - * @bus_base On return the base of the PCI region - * @bus_offset On return the byte offset into the PCI region - * @bus_size On return the byte size of the buffer object or zero if - * the buffer object memory is not accessible through a PCI region. - * - * Returns: - * -EINVAL if the buffer object is currently not mappable. - * 0 otherwise. - */ - -extern int ttm_bo_pci_offset(struct ttm_bo_device *bdev, - struct ttm_mem_reg *mem, - unsigned long *bus_base, - unsigned long *bus_offset, - unsigned long *bus_size); - -extern int ttm_mem_io_reserve(struct ttm_bo_device *bdev, - struct ttm_mem_reg *mem); -extern void ttm_mem_io_free(struct ttm_bo_device *bdev, - struct ttm_mem_reg *mem); - extern void ttm_bo_global_release(struct drm_global_reference *ref); extern int ttm_bo_global_init(struct drm_global_reference *ref); @@ -815,6 +805,22 @@ extern int ttm_bo_device_init(struct ttm_bo_device *bdev, extern void ttm_bo_unmap_virtual(struct ttm_buffer_object *bo); /** + * ttm_bo_unmap_virtual + * + * @bo: tear down the virtual mappings for this BO + * + * The caller must take ttm_mem_io_lock before calling this function. + */ +extern void ttm_bo_unmap_virtual_locked(struct ttm_buffer_object *bo); + +extern int ttm_mem_io_reserve_vm(struct ttm_buffer_object *bo); +extern void ttm_mem_io_free_vm(struct ttm_buffer_object *bo); +extern int ttm_mem_io_lock(struct ttm_mem_type_manager *man, + bool interruptible); +extern void ttm_mem_io_unlock(struct ttm_mem_type_manager *man); + + +/** * ttm_bo_reserve: * * @bo: A pointer to a struct ttm_buffer_object. -- cgit v1.1 From ab69a4904b5dd4d7cd6996587ba066bca8d13838 Mon Sep 17 00:00:00 2001 From: Clemens Ladisch Date: Mon, 15 Nov 2010 10:46:23 +0100 Subject: ALSA: pcm: support for period wakeup disabling This patch allows to disable period interrupts which are not needed when the application relies on a system timer to wake-up and refill the ring buffer. The behavior of the driver is left unchanged, and interrupts are only disabled if the application requests this configuration. The behavior in case of underruns is slightly different, instead of being detected during the period interrupts the underruns are detected when the application calls snd_pcm_update_avail, which in turns forces a refresh of the hw pointer and shows the buffer is empty. More specifically this patch makes a lot of sense when PulseAudio relies on timer-based scheduling to access audio devices such as HDAudio or Intel SST. Disabling interrupts removes two unwanted wake-ups due to period elapsed events in low-power playback modes. It also simplifies PulseAudio voice modules used for speech calls. To quote Lennart "This patch looks very interesting and desirable. This is something have long been waiting for." Support for this in hardware drivers is optional. Signed-off-by: Pierre-Louis Bossart Signed-off-by: Clemens Ladisch Signed-off-by: Takashi Iwai --- include/sound/asound.h | 3 +++ include/sound/pcm.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/sound/asound.h b/include/sound/asound.h index a1803ec..5d6074f 100644 --- a/include/sound/asound.h +++ b/include/sound/asound.h @@ -259,6 +259,7 @@ typedef int __bitwise snd_pcm_subformat_t; #define SNDRV_PCM_INFO_HALF_DUPLEX 0x00100000 /* only half duplex */ #define SNDRV_PCM_INFO_JOINT_DUPLEX 0x00200000 /* playback and capture stream are somewhat correlated */ #define SNDRV_PCM_INFO_SYNC_START 0x00400000 /* pcm support some kind of sync go */ +#define SNDRV_PCM_INFO_NO_PERIOD_WAKEUP 0x00800000 /* period wakeup can be disabled */ #define SNDRV_PCM_INFO_FIFO_IN_FRAMES 0x80000000 /* internal kernel flag - FIFO size is in frames */ typedef int __bitwise snd_pcm_state_t; @@ -334,6 +335,8 @@ typedef int snd_pcm_hw_param_t; #define SNDRV_PCM_HW_PARAM_LAST_INTERVAL SNDRV_PCM_HW_PARAM_TICK_TIME #define SNDRV_PCM_HW_PARAMS_NORESAMPLE (1<<0) /* avoid rate resampling */ +#define SNDRV_PCM_HW_PARAMS_EXPORT_BUFFER (1<<1) /* export buffer */ +#define SNDRV_PCM_HW_PARAMS_NO_PERIOD_WAKEUP (1<<2) /* disable period wakeups */ struct snd_interval { unsigned int min, max; diff --git a/include/sound/pcm.h b/include/sound/pcm.h index dfd9b76..e731f8d 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -297,6 +297,7 @@ struct snd_pcm_runtime { unsigned int info; unsigned int rate_num; unsigned int rate_den; + unsigned int no_period_wakeup: 1; /* -- SW params -- */ int tstamp_mode; /* mmap timestamp is updated */ -- cgit v1.1 From eb06acdc85585f28864261f28659157848762ee4 Mon Sep 17 00:00:00 2001 From: Sridhar Samudrala Date: Thu, 28 Oct 2010 13:10:50 +0000 Subject: macvlan: Introduce 'passthru' mode to takeover the underlying device With the current default 'vepa' mode, a KVM guest using virtio with macvtap backend has the following limitations. - cannot change/add a mac address on the guest virtio-net - cannot create a vlan device on the guest virtio-net - cannot enable promiscuous mode on guest virtio-net To address these limitations, this patch introduces a new mode called 'passthru' when creating a macvlan device which allows takeover of the underlying device and passing it to a guest using virtio with macvtap backend. Only one macvlan device is allowed in passthru mode and it inherits the mac address from the underlying device and sets it in promiscuous mode to receive and forward all the packets. Signed-off-by: Sridhar Samudrala ------------------------------------------------------------------------- Signed-off-by: David S. Miller --- include/linux/if_link.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/if_link.h b/include/linux/if_link.h index 2e02e4d..6485d2a 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -259,6 +259,7 @@ enum macvlan_mode { MACVLAN_MODE_PRIVATE = 1, /* don't talk to other macvlans */ MACVLAN_MODE_VEPA = 2, /* talk to other ports through ext bridge */ MACVLAN_MODE_BRIDGE = 4, /* talk to bridge ports directly */ + MACVLAN_MODE_PASSTHRU = 8,/* take over the underlying device */ }; /* SR-IOV virtual function management section */ -- cgit v1.1 From b2e253cf300c5e33f49b7dd8b593bfc722177401 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Wed, 17 Nov 2010 21:46:09 -0800 Subject: cfg80211: Fix regulatory bug with multiple cards and delays When two cards are connected with the same regulatory domain if CRDA had a delayed response then cfg80211's own set regulatory domain would still be the world regulatory domain. There was a bug on cfg80211's logic such that it assumed that once you pegged a request as the last request it was already the currently set regulatory domain. This would mean we would race setting a stale regulatory domain to secondary cards which had the same regulatory domain since the alpha2 would match. We fix this by processing each regulatory request atomically, and only move on to the next one once we get it fully processed. In the case CRDA is not present we will simply world roam. This issue is only present when you have a slow system and the CRDA processing is delayed. Because of this it is not a known regression. Without this fix when a delay is present with CRDA the second card would end up with an intersected regulatory domain and not allow it to use the channels it really is designed for. When two cards with two different regulatory domains were inserted you'd end up rejecting the second card's regulatory domain request. This fails with mac80211_hswim's regtest=2 (two requests, same alpha2) and regtest=3 (two requests, different alpha2) module parameter options. This was reproduced and tested against mac80211_hwsim using this CRDA delayer: #!/bin/bash echo $COUNTRY >> /tmp/log sleep 2 /sbin/crda.orig And these regulatory tests: modprobe mac80211_hwsim regtest=2 modprobe mac80211_hwsim regtest=3 Reported-by: Mark Mentovai Signed-off-by: Luis R. Rodriguez Tested-by: Mark Mentovai Tested-by: Bruno Randolf Signed-off-by: John W. Linville --- include/net/regulatory.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/regulatory.h b/include/net/regulatory.h index 9e103a4..356d6e3 100644 --- a/include/net/regulatory.h +++ b/include/net/regulatory.h @@ -43,6 +43,12 @@ enum environment_cap { * @intersect: indicates whether the wireless core should intersect * the requested regulatory domain with the presently set regulatory * domain. + * @processed: indicates whether or not this requests has already been + * processed. When the last request is processed it means that the + * currently regulatory domain set on cfg80211 is updated from + * CRDA and can be used by other regulatory requests. When a + * the last request is not yet processed we must yield until it + * is processed before processing any new requests. * @country_ie_checksum: checksum of the last processed and accepted * country IE * @country_ie_env: lets us know if the AP is telling us we are outdoor, @@ -54,6 +60,7 @@ struct regulatory_request { enum nl80211_reg_initiator initiator; char alpha2[2]; bool intersect; + bool processed; enum environment_cap country_ie_env; struct list_head list; }; -- cgit v1.1 From 11fa1618e327af7f08085e134b3325de9caf7a94 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 22 Nov 2010 17:56:37 -0500 Subject: drm/radeon/kms: add Ontario Fusion APU pci ids Signed-off-by: Alex Deucher Signed-off-by: Dave Airlie --- include/drm/drm_pciids.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h index 883c1d4..e6b28a3 100644 --- a/include/drm/drm_pciids.h +++ b/include/drm/drm_pciids.h @@ -419,6 +419,10 @@ {0x1002, 0x9713, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x9714, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x9715, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9802, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9803, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9804, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9805, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0, 0, 0} #define r128_PCI_IDS \ -- cgit v1.1 From c64f7ba5f1006d8c20eacafecf98d4d00a6902a0 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Tue, 23 Nov 2010 14:24:24 +0000 Subject: agp/intel: Remove confusion of stolen entries not stolen memory Signed-off-by: Chris Wilson --- include/drm/intel-gtt.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/drm/intel-gtt.h b/include/drm/intel-gtt.h index d3c8194..020f8aa 100644 --- a/include/drm/intel-gtt.h +++ b/include/drm/intel-gtt.h @@ -2,17 +2,16 @@ #ifndef _DRM_INTEL_GTT_H #define _DRM_INTEL_GTT_H -struct intel_gtt { - /* Number of stolen gtt entries at the beginning. */ - unsigned int gtt_stolen_entries; + +const struct intel_gtt { + /* Size of memory reserved for graphics by the BIOS */ + unsigned int stolen_size; /* Total number of gtt entries. */ unsigned int gtt_total_entries; /* Part of the gtt that is mappable by the cpu, for those chips where * this is not the full gtt. */ unsigned int gtt_mappable_entries; -}; - -struct intel_gtt *intel_gtt_get(void); +} *intel_gtt_get(void); #endif -- cgit v1.1 From 23ed992a5ebe6964ebe312b54142fbc5e8185cdc Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 5 Nov 2010 18:04:52 +0100 Subject: drm/i915|intel-gtt: consolidate intel-gtt.h headers ... and a few other defines. Signed-off-by: Daniel Vetter Signed-off-by: Chris Wilson --- include/drm/intel-gtt.h | 12 ++++++++++++ include/linux/intel-gtt.h | 20 -------------------- 2 files changed, 12 insertions(+), 20 deletions(-) delete mode 100644 include/linux/intel-gtt.h (limited to 'include') diff --git a/include/drm/intel-gtt.h b/include/drm/intel-gtt.h index 020f8aa..9f91cbe 100644 --- a/include/drm/intel-gtt.h +++ b/include/drm/intel-gtt.h @@ -13,5 +13,17 @@ const struct intel_gtt { unsigned int gtt_mappable_entries; } *intel_gtt_get(void); + +/* Special gtt memory types */ +#define AGP_DCACHE_MEMORY 1 +#define AGP_PHYS_MEMORY 2 + +/* New caching attributes for gen6/sandybridge */ +#define AGP_USER_CACHED_MEMORY_LLC_MLC (AGP_USER_TYPES + 2) +#define AGP_USER_UNCACHED_MEMORY (AGP_USER_TYPES + 4) + +/* flag for GFDT type */ +#define AGP_USER_CACHED_MEMORY_GFDT (1 << 3) + #endif diff --git a/include/linux/intel-gtt.h b/include/linux/intel-gtt.h deleted file mode 100644 index 1d19ab2..0000000 --- a/include/linux/intel-gtt.h +++ /dev/null @@ -1,20 +0,0 @@ -/* - * Common Intel AGPGART and GTT definitions. - */ -#ifndef _INTEL_GTT_H -#define _INTEL_GTT_H - -#include - -/* This is for Intel only GTT controls. - * - * Sandybridge: AGP_USER_CACHED_MEMORY default to LLC only - */ - -#define AGP_USER_CACHED_MEMORY_LLC_MLC (AGP_USER_TYPES + 2) -#define AGP_USER_UNCACHED_MEMORY (AGP_USER_TYPES + 4) - -/* flag for GFDT type */ -#define AGP_USER_CACHED_MEMORY_GFDT (1 << 3) - -#endif -- cgit v1.1 From 40ce6575102b23e432932b5ce41c44bf7cc5023b Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 5 Nov 2010 18:12:18 +0100 Subject: drm/i915/gtt: call chipset flush directly Signed-off-by: Daniel Vetter Signed-off-by: Chris Wilson --- include/drm/intel-gtt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/intel-gtt.h b/include/drm/intel-gtt.h index 9f91cbe..c35817a 100644 --- a/include/drm/intel-gtt.h +++ b/include/drm/intel-gtt.h @@ -13,6 +13,7 @@ const struct intel_gtt { unsigned int gtt_mappable_entries; } *intel_gtt_get(void); +void intel_gtt_chipset_flush(void); /* Special gtt memory types */ #define AGP_DCACHE_MEMORY 1 @@ -26,4 +27,3 @@ const struct intel_gtt { #define AGP_USER_CACHED_MEMORY_GFDT (1 << 3) #endif - -- cgit v1.1 From 4af72e2865a23ac090884a421bd1a8b19e247a22 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 5 Nov 2010 18:13:43 +0100 Subject: drm: kill drm_agp_chipset_flush No longer used. Cc: Dave Airlie Signed-off-by: Daniel Vetter Signed-off-by: Chris Wilson --- include/drm/drmP.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/drm/drmP.h b/include/drm/drmP.h index d4bc0f5..628f767 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -1319,7 +1319,6 @@ extern int drm_agp_unbind_ioctl(struct drm_device *dev, void *data, extern int drm_agp_bind(struct drm_device *dev, struct drm_agp_binding *request); extern int drm_agp_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); -extern void drm_agp_chipset_flush(struct drm_device *dev); /* Stub support (drm_stub.h) */ extern int drm_setmaster_ioctl(struct drm_device *dev, void *data, -- cgit v1.1 From f050a8abbda0efcd597c6b1825e3b9ce4d613383 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 5 Nov 2010 18:40:56 +0100 Subject: agp: kill agp_flush_chipset and corresponding ioctl The intel drm calls the chipset functions now directly. Userspace never called the corresponding ioctl, hence it can be killed, too. Cc: Dave Airlie Signed-off-by: Daniel Vetter Signed-off-by: Chris Wilson --- include/linux/agp_backend.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/agp_backend.h b/include/linux/agp_backend.h index 09ea4a1..a479b48 100644 --- a/include/linux/agp_backend.h +++ b/include/linux/agp_backend.h @@ -106,6 +106,5 @@ extern int agp_rebind_memory(void); extern void agp_enable(struct agp_bridge_data *, u32); extern struct agp_bridge_data *agp_backend_acquire(struct pci_dev *); extern void agp_backend_release(struct agp_bridge_data *); -extern void agp_flush_chipset(struct agp_bridge_data *); #endif /* _AGP_BACKEND_H */ -- cgit v1.1 From cb16b67b5cb33b7d6732e0c416d29d933eea13ce Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Fri, 5 Nov 2010 22:27:10 +0100 Subject: agp: kill agp_rebind_memory Its only user, intel-gtt.c is now gone. Cc: Dave Airlie Signed-off-by: Daniel Vetter Signed-off-by: Chris Wilson --- include/linux/agp_backend.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/agp_backend.h b/include/linux/agp_backend.h index a479b48..eaf6cd7 100644 --- a/include/linux/agp_backend.h +++ b/include/linux/agp_backend.h @@ -102,7 +102,6 @@ extern struct agp_memory *agp_allocate_memory(struct agp_bridge_data *, size_t, extern int agp_copy_info(struct agp_bridge_data *, struct agp_kern_info *); extern int agp_bind_memory(struct agp_memory *, off_t); extern int agp_unbind_memory(struct agp_memory *); -extern int agp_rebind_memory(void); extern void agp_enable(struct agp_bridge_data *, u32); extern struct agp_bridge_data *agp_backend_acquire(struct pci_dev *); extern void agp_backend_release(struct agp_bridge_data *); -- cgit v1.1 From 4080775b60cc26044e7c4aba5e76e5041b0d7004 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Sat, 6 Nov 2010 11:18:58 +0100 Subject: intel-gtt: export api for drm/i915 Just some minor shuffling to get rid of any agp traces in the exported functions. Signed-off-by: Daniel Vetter Signed-off-by: Chris Wilson --- include/drm/intel-gtt.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/drm/intel-gtt.h b/include/drm/intel-gtt.h index c35817a..9e343c0 100644 --- a/include/drm/intel-gtt.h +++ b/include/drm/intel-gtt.h @@ -11,9 +11,21 @@ const struct intel_gtt { /* Part of the gtt that is mappable by the cpu, for those chips where * this is not the full gtt. */ unsigned int gtt_mappable_entries; + /* Whether i915 needs to use the dmar apis or not. */ + unsigned int needs_dmar : 1; } *intel_gtt_get(void); void intel_gtt_chipset_flush(void); +void intel_gtt_unmap_memory(struct scatterlist *sg_list, int num_sg); +void intel_gtt_clear_range(unsigned int first_entry, unsigned int num_entries); +int intel_gtt_map_memory(struct page **pages, unsigned int num_entries, + struct scatterlist **sg_list, int *num_sg); +void intel_gtt_insert_sg_entries(struct scatterlist *sg_list, + unsigned int sg_len, + unsigned int pg_start, + unsigned int flags); +void intel_gtt_insert_pages(unsigned int first_entry, unsigned int num_entries, + struct page **pages, unsigned int flags); /* Special gtt memory types */ #define AGP_DCACHE_MEMORY 1 -- cgit v1.1 From 03cfe6f57dc5c13ccdd235c23c80e3fa170f03d1 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Tue, 23 Nov 2010 17:43:19 +0100 Subject: ALSA: support module on-demand loading for seq and timer If CONFIG_SND_DYNAMIC_MINORS is used, assign /dev/snd/seq and /dev/snd/timer the usual static minors, and export specific module aliases to generate udev module on-demand loading instructions: $ cat /lib/modules/2.6.33.4-smp/modules.devname # Device nodes to trigger on-demand module loading. microcode cpu/microcode c10:184 fuse fuse c10:229 ppp_generic ppp c108:0 tun net/tun c10:200 uinput uinput c10:223 dm_mod mapper/control c10:236 snd_timer snd/timer c116:33 snd_seq snd/seq c116:1 The last two lines instruct udev to create device nodes, even when the modules are not loaded at that time. As soon as userspace accesses any of these nodes, the in-kernel module-loader will load the module, and the device can be used. The header file minor calculation needed to be simplified to make __stringify() (supports only two indirections) in the MODULE_ALIAS macro work. This is part of systemd's effort to get rid of unconditional module load instructions and needless init scripts. Cc: Lennart Poettering Signed-off-by: Kay Sievers Signed-off-by: Clemens Ladisch Signed-off-by: Takashi Iwai --- include/sound/minors.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/sound/minors.h b/include/sound/minors.h index a81798a..8f76420 100644 --- a/include/sound/minors.h +++ b/include/sound/minors.h @@ -31,8 +31,8 @@ /* these minors can still be used for autoloading devices (/dev/aload*) */ #define SNDRV_MINOR_CONTROL 0 /* 0 */ #define SNDRV_MINOR_GLOBAL 1 /* 1 */ -#define SNDRV_MINOR_SEQUENCER (SNDRV_MINOR_GLOBAL + 0 * 32) -#define SNDRV_MINOR_TIMER (SNDRV_MINOR_GLOBAL + 1 * 32) +#define SNDRV_MINOR_SEQUENCER 1 /* SNDRV_MINOR_GLOBAL + 0 * 32 */ +#define SNDRV_MINOR_TIMER 33 /* SNDRV_MINOR_GLOBAL + 1 * 32 */ #ifndef CONFIG_SND_DYNAMIC_MINORS /* 2 - 3 (reserved) */ -- cgit v1.1 From 293bb1c41b728d4aa248fe8a0acd2b9066ff5c34 Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Wed, 24 Nov 2010 02:38:05 +0000 Subject: stmmac: add init/exit callback in plat_stmmacenet_data struct This patch adds in the plat_stmmacenet_data the init and exit callbacks that can be used for invoking specific platform functions. For example, on ST targets, these call the PAD manager functions to set PIO lines and syscfg registers. The patch removes the stmmac_claim_resource only used on STM Kernels as well. Signed-off-by: Giuseppe Cavallaro Signed-off-by: David S. Miller --- include/linux/stmmac.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index d66c617..e103529 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -40,9 +40,9 @@ struct plat_stmmacenet_data { int pmt; void (*fix_mac_speed)(void *priv, unsigned int speed); void (*bus_setup)(void __iomem *ioaddr); -#ifdef CONFIG_STM_DRIVERS - struct stm_pad_config *pad_config; -#endif + int (*init)(struct platform_device *pdev); + void (*exit)(struct platform_device *pdev); + void *custom_cfg; void *bsp_priv; }; -- cgit v1.1 From 456b61bca8ee324ab6c18b065e632c9a8c88aa39 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 23 Nov 2010 13:12:15 +0000 Subject: ipv6: mcast: RCU conversion ipv6_sk_mc_lock rwlock becomes a spinlock. readers (inet6_mc_check()) now takes rcu_read_lock() instead of read lock. Writers dont need to disable BH anymore. struct ipv6_mc_socklist objects are reclaimed after one RCU grace period. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/ipv6.h | 2 +- include/net/if_inet6.h | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 8e429d0..0c99776 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -364,7 +364,7 @@ struct ipv6_pinfo { __u32 dst_cookie; - struct ipv6_mc_socklist *ipv6_mc_list; + struct ipv6_mc_socklist __rcu *ipv6_mc_list; struct ipv6_ac_socklist *ipv6_ac_list; struct ipv6_fl_socklist *ipv6_fl_list; diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index f95ff8d..04977ee 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -89,10 +89,11 @@ struct ip6_sf_socklist { struct ipv6_mc_socklist { struct in6_addr addr; int ifindex; - struct ipv6_mc_socklist *next; + struct ipv6_mc_socklist __rcu *next; rwlock_t sflock; unsigned int sfmode; /* MCAST_{INCLUDE,EXCLUDE} */ struct ip6_sf_socklist *sflist; + struct rcu_head rcu; }; struct ip6_sf_list { -- cgit v1.1 From bba14de98753cb6599a2dae0e520714b2153522d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 23 Nov 2010 14:09:15 +0000 Subject: scm: lower SCM_MAX_FD Lower SCM_MAX_FD from 255 to 253 so that allocations for scm_fp_list are halved. (commit f8d570a4 added two pointers in this structure) scm_fp_dup() should not copy whole structure (and trigger kmemcheck warnings), but only the used part. While we are at it, only allocate needed size. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/scm.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/scm.h b/include/net/scm.h index 3165650..745460f 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -10,11 +10,12 @@ /* Well, we should have at least one descriptor open * to accept passed FDs 8) */ -#define SCM_MAX_FD 255 +#define SCM_MAX_FD 253 struct scm_fp_list { struct list_head list; - int count; + short count; + short max; struct file *fp[SCM_MAX_FD]; }; -- cgit v1.1 From 3853b5841c01a3f492fe137afaad9c209e5162c6 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Sun, 21 Nov 2010 13:17:29 +0000 Subject: xps: Improvements in TX queue selection In dev_pick_tx, don't do work in calculating queue index or setting the index in the sock unless the device has more than one queue. This allows the sock to be set only with a queue index of a multi-queue device which is desirable if device are stacked like in a tunnel. We also allow the mapping of a socket to queue to be changed. To maintain in order packet transmission a flag (ooo_okay) has been added to the sk_buff structure. If a transport layer sets this flag on a packet, the transmit queue can be changed for the socket. Presumably, the transport would set this if there was no possbility of creating OOO packets (for instance, there are no packets in flight for the socket). This patch includes the modification in TCP output for setting this flag. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e6ba898..19f37a6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -386,9 +386,10 @@ struct sk_buff { #else __u8 deliver_no_wcard:1; #endif + __u8 ooo_okay:1; kmemcheck_bitfield_end(flags2); - /* 0/14 bit hole */ + /* 0/13 bit hole */ #ifdef CONFIG_NET_DMA dma_cookie_t dma_cookie; -- cgit v1.1 From 1d24eb4815d1e0e8b451ecc546645f8ef1176d4f Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Sun, 21 Nov 2010 13:17:27 +0000 Subject: xps: Transmit Packet Steering This patch implements transmit packet steering (XPS) for multiqueue devices. XPS selects a transmit queue during packet transmission based on configuration. This is done by mapping the CPU transmitting the packet to a queue. This is the transmit side analogue to RPS-- where RPS is selecting a CPU based on receive queue, XPS selects a queue based on the CPU (previously there was an XPS patch from Eric Dumazet, but that might more appropriately be called transmit completion steering). Each transmit queue can be associated with a number of CPUs which will use the queue to send packets. This is configured as a CPU mask on a per queue basis in: /sys/class/net/eth/queues/tx-/xps_cpus The mappings are stored per device in an inverted data structure that maps CPUs to queues. In the netdevice structure this is an array of num_possible_cpu structures where each structure holds and array of queue_indexes for queues which that CPU can use. The benefits of XPS are improved locality in the per queue data structures. Also, transmit completions are more likely to be done nearer to the sending thread, so this should promote locality back to the socket on free (e.g. UDP). The benefits of XPS are dependent on cache hierarchy, application load, and other factors. XPS would nominally be configured so that a queue would only be shared by CPUs which are sharing a cache, the degenerative configuration woud be that each CPU has it's own queue. Below are some benchmark results which show the potential benfit of this patch. The netperf test has 500 instances of netperf TCP_RR test with 1 byte req. and resp. bnx2x on 16 core AMD XPS (16 queues, 1 TX queue per CPU) 1234K at 100% CPU No XPS (16 queues) 996K at 100% CPU Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b45c1b8..badf928 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -503,6 +503,10 @@ struct netdev_queue { struct Qdisc *qdisc; unsigned long state; struct Qdisc *qdisc_sleeping; +#ifdef CONFIG_RPS + struct kobject kobj; +#endif + /* * write mostly part */ @@ -530,6 +534,30 @@ struct rps_map { #define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + (_num * sizeof(u16))) /* + * This structure holds an XPS map which can be of variable length. The + * map is an array of queues. + */ +struct xps_map { + unsigned int len; + unsigned int alloc_len; + struct rcu_head rcu; + u16 queues[0]; +}; +#define XPS_MAP_SIZE(_num) (sizeof(struct xps_map) + (_num * sizeof(u16))) +#define XPS_MIN_MAP_ALLOC ((L1_CACHE_BYTES - sizeof(struct xps_map)) \ + / sizeof(u16)) + +/* + * This structure holds all XPS maps for device. Maps are indexed by CPU. + */ +struct xps_dev_maps { + struct rcu_head rcu; + struct xps_map *cpu_map[0]; +}; +#define XPS_DEV_MAPS_SIZE (sizeof(struct xps_dev_maps) + \ + (nr_cpu_ids * sizeof(struct xps_map *))) + +/* * The rps_dev_flow structure contains the mapping of a flow to a CPU and the * tail pointer for that CPU's input queue at the time of last enqueue. */ @@ -1016,6 +1044,8 @@ struct net_device { unsigned long tx_queue_len; /* Max frames per queue allowed */ spinlock_t tx_global_lock; + struct xps_dev_maps *xps_maps; + /* These may be needed for future network-power-down code. */ /* -- cgit v1.1 From ccb14354017272ddac002e859a2711610b6af174 Mon Sep 17 00:00:00 2001 From: "John W. Linville" Date: Wed, 24 Nov 2010 16:18:36 -0500 Subject: Revert "nl80211/mac80211: Report signal average" This reverts commit 86107fd170bc379869250eb7e1bd393a3a70e8ae. This patch inadvertantly changed the userland ABI. Signed-off-by: John W. Linville --- include/linux/nl80211.h | 2 -- include/net/cfg80211.h | 4 ---- 2 files changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 1ce3775..037b4e4 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -1161,7 +1161,6 @@ enum nl80211_rate_info { * @__NL80211_STA_INFO_AFTER_LAST: internal * @NL80211_STA_INFO_MAX: highest possible station info attribute * @NL80211_STA_INFO_SIGNAL: signal strength of last received PPDU (u8, dBm) - * @NL80211_STA_INFO_SIGNAL_AVG: signal strength average (u8, dBm) * @NL80211_STA_INFO_TX_BITRATE: current unicast tx rate, nested attribute * containing info as possible, see &enum nl80211_sta_info_txrate. * @NL80211_STA_INFO_RX_PACKETS: total received packet (u32, from this station) @@ -1179,7 +1178,6 @@ enum nl80211_sta_info { NL80211_STA_INFO_PLID, NL80211_STA_INFO_PLINK_STATE, NL80211_STA_INFO_SIGNAL, - NL80211_STA_INFO_SIGNAL_AVG, NL80211_STA_INFO_TX_BITRATE, NL80211_STA_INFO_RX_PACKETS, NL80211_STA_INFO_TX_PACKETS, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 69e2364..8fd9eeb 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -424,7 +424,6 @@ struct station_parameters { * @STATION_INFO_TX_RETRIES: @tx_retries filled * @STATION_INFO_TX_FAILED: @tx_failed filled * @STATION_INFO_RX_DROP_MISC: @rx_dropped_misc filled - * @STATION_INFO_SIGNAL_AVG: @signal_avg filled */ enum station_info_flags { STATION_INFO_INACTIVE_TIME = 1<<0, @@ -440,7 +439,6 @@ enum station_info_flags { STATION_INFO_TX_RETRIES = 1<<10, STATION_INFO_TX_FAILED = 1<<11, STATION_INFO_RX_DROP_MISC = 1<<12, - STATION_INFO_SIGNAL_AVG = 1<<13, }; /** @@ -487,7 +485,6 @@ struct rate_info { * @plid: mesh peer link id * @plink_state: mesh peer link state * @signal: signal strength of last received packet in dBm - * @signal_avg: signal strength average in dBm * @txrate: current unicast bitrate to this station * @rx_packets: packets received from this station * @tx_packets: packets transmitted to this station @@ -508,7 +505,6 @@ struct station_info { u16 plid; u8 plink_state; s8 signal; - s8 signal_avg; struct rate_info txrate; u32 rx_packets; u32 tx_packets; -- cgit v1.1 From dd5b4cc71cd09c33e1579cc6d5720656e94e52de Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Mon, 22 Nov 2010 20:58:24 +0100 Subject: cfg80211/mac80211: improve ad-hoc multicast rate handling - store the multicast rate as an index instead of the rate value (reduces cpu overhead in a hotpath) - validate the rate values (must match a bitrate in at least one sband) Signed-off-by: Felix Fietkau Signed-off-by: John W. Linville --- include/net/cfg80211.h | 4 ++-- include/net/mac80211.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 91f0995..dd4c43f 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -923,7 +923,7 @@ struct cfg80211_disassoc_request { * @privacy: this is a protected network, keys will be configured * after joining * @basic_rates: bitmap of basic rates to use when creating the IBSS - * @mcast_rate: multicast tx rate (in 100 kbps) + * @mcast_rate: per-band multicast rate index + 1 (0: disabled) */ struct cfg80211_ibss_params { u8 *ssid; @@ -935,7 +935,7 @@ struct cfg80211_ibss_params { u32 basic_rates; bool channel_fixed; bool privacy; - int mcast_rate; + int mcast_rate[IEEE80211_NUM_BANDS]; }; /** diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 5b0fff2..08e97e5 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -219,7 +219,7 @@ enum ieee80211_bss_change { * @basic_rates: bitmap of basic rates, each bit stands for an * index into the rate table configured by the driver in * the current band. - * @mcast_rate: multicast rate for AP and Ad-Hoc (in 100 kbps) + * @mcast_rate: per-band multicast rate index + 1 (0: disabled) * @bssid: The BSSID for this BSS * @enable_beacon: whether beaconing should be enabled or not * @channel_type: Channel type for this BSS -- the hardware might be @@ -259,7 +259,7 @@ struct ieee80211_bss_conf { u16 assoc_capability; u64 timestamp; u32 basic_rates; - u32 mcast_rate; + int mcast_rate[IEEE80211_NUM_BANDS]; u16 ht_operation_mode; s32 cqm_rssi_thold; u32 cqm_rssi_hyst; -- cgit v1.1 From 79b1c460a0b55e55981c25c56597c4d5d2872de3 Mon Sep 17 00:00:00 2001 From: Bruno Randolf Date: Wed, 24 Nov 2010 14:34:41 +0900 Subject: cfg80211: Add documentation for antenna ops Signed-off-by: Bruno Randolf Signed-off-by: John W. Linville --- include/net/mac80211.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 08e97e5..eaa4aff 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1745,6 +1745,13 @@ enum ieee80211_ampdu_mlme_action { * completion of the channel switch. * * @napi_poll: Poll Rx queue for incoming data frames. + * + * @set_antenna: Set antenna configuration (tx_ant, rx_ant) on the device. + * Parameters are bitmaps of allowed antennas to use for TX/RX. Drivers may + * reject TX/RX mask combinations they cannot support by returning -EINVAL + * (also see nl80211.h @NL80211_ATTR_WIPHY_ANTENNA_TX). + * + * @get_antenna: Get current antenna configuration from device (tx_ant, rx_ant). */ struct ieee80211_ops { int (*tx)(struct ieee80211_hw *hw, struct sk_buff *skb); -- cgit v1.1 From c063dbf52b998b852122dff07a8b8dd430b38437 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 24 Nov 2010 08:10:05 +0100 Subject: cfg80211: allow using CQM event to notify packet loss This adds the ability for drivers to use CQM events to notify about packet loss for specific stations (which could be the AP for the managed mode case). Since the threshold might be determined by the driver (it isn't passed in right now) it will be passed out of the driver to userspace in the event. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 3 +++ include/net/cfg80211.h | 12 ++++++++++++ 2 files changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 037b4e4..d706bf3 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -1819,6 +1819,8 @@ enum nl80211_ps_state { * the minimum amount the RSSI level must change after an event before a * new event may be issued (to reduce effects of RSSI oscillation). * @NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT: RSSI threshold event + * @NL80211_ATTR_CQM_PKT_LOSS_EVENT: a u32 value indicating that this many + * consecutive packets were not acknowledged by the peer * @__NL80211_ATTR_CQM_AFTER_LAST: internal * @NL80211_ATTR_CQM_MAX: highest key attribute */ @@ -1827,6 +1829,7 @@ enum nl80211_attr_cqm { NL80211_ATTR_CQM_RSSI_THOLD, NL80211_ATTR_CQM_RSSI_HYST, NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT, + NL80211_ATTR_CQM_PKT_LOSS_EVENT, /* keep last */ __NL80211_ATTR_CQM_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index dd4c43f..0663945 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2601,6 +2601,18 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev, enum nl80211_cqm_rssi_threshold_event rssi_event, gfp_t gfp); +/** + * cfg80211_cqm_pktloss_notify - notify userspace about packetloss to peer + * @dev: network device + * @peer: peer's MAC address + * @num_packets: how many packets were lost -- should be a fixed threshold + * but probably no less than maybe 50, or maybe a throughput dependent + * threshold (to account for temporary interference) + * @gfp: context flags + */ +void cfg80211_cqm_pktloss_notify(struct net_device *dev, + const u8 *peer, u32 num_packets, gfp_t gfp); + /* Logging, debugging and troubleshooting/diagnostic helpers. */ /* wiphy_printk helpers, similar to dev_printk */ -- cgit v1.1 From a782d688e9c6f9ca9a7a9a28e8e2876969ddef53 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Wed, 24 Nov 2010 10:05:22 +0000 Subject: mmc: sh_mmcif: add DMA support The MMCIF controller on sh-mobile platforms can use the DMA controller for data transfers. Interface to the SH dmaengine driver to enable DMA. We also have to lower the maximum number of segments to match with the number od DMA descriptors on SuperH, this doesn't significantly affect driver's PIO performance. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Paul Mundt --- include/linux/mmc/sh_mmcif.h | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/mmc/sh_mmcif.h index a6bfa52..f216a88 100644 --- a/include/linux/mmc/sh_mmcif.h +++ b/include/linux/mmc/sh_mmcif.h @@ -14,8 +14,9 @@ #ifndef __SH_MMCIF_H__ #define __SH_MMCIF_H__ -#include #include +#include +#include /* * MMCIF : CE_CLK_CTRL [19:16] @@ -31,13 +32,19 @@ * 1111 : Peripheral clock (sup_pclk set '1') */ +struct sh_mmcif_dma { + struct sh_dmae_slave chan_priv_tx; + struct sh_dmae_slave chan_priv_rx; +}; + struct sh_mmcif_plat_data { void (*set_pwr)(struct platform_device *pdev, int state); void (*down_pwr)(struct platform_device *pdev); int (*get_cd)(struct platform_device *pdef); - u8 sup_pclk; /* 1 :SH7757, 0: SH7724/SH7372 */ - unsigned long caps; - u32 ocr; + struct sh_mmcif_dma *dma; + u8 sup_pclk; /* 1 :SH7757, 0: SH7724/SH7372 */ + unsigned long caps; + u32 ocr; }; #define MMCIF_CE_CMD_SET 0x00000000 -- cgit v1.1 From 6d803ba736abb5e122dede70a4720e4843dd6df4 Mon Sep 17 00:00:00 2001 From: Jean-Christop PLAGNIOL-VILLARD Date: Wed, 17 Nov 2010 10:04:33 +0100 Subject: ARM: 6483/1: arm & sh: factorised duplicated clkdev.c factorise some generic infrastructure to assist looking up struct clks for the ARM & SH architecture. as the code is identical at 99% put the arch specific code for allocation as example in asm/clkdev.h Signed-off-by: Jean-Christophe PLAGNIOL-VILLARD Acked-by: Paul Mundt Signed-off-by: Russell King --- include/linux/clkdev.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 include/linux/clkdev.h (limited to 'include') diff --git a/include/linux/clkdev.h b/include/linux/clkdev.h new file mode 100644 index 0000000..457bcb0 --- /dev/null +++ b/include/linux/clkdev.h @@ -0,0 +1,36 @@ +/* + * include/linux/clkdev.h + * + * Copyright (C) 2008 Russell King. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Helper for the clk API to assist looking up a struct clk. + */ +#ifndef __CLKDEV_H +#define __CLKDEV_H + +#include + +struct clk; +struct device; + +struct clk_lookup { + struct list_head node; + const char *dev_id; + const char *con_id; + struct clk *clk; +}; + +struct clk_lookup *clkdev_alloc(struct clk *clk, const char *con_id, + const char *dev_fmt, ...); + +void clkdev_add(struct clk_lookup *cl); +void clkdev_drop(struct clk_lookup *cl); + +void clkdev_add_table(struct clk_lookup *, size_t); +int clk_add_alias(const char *, const char *, char *, struct device *); + +#endif -- cgit v1.1 From 65500fa94aaeb3475e39c0c5180f188014164ca4 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 4 Nov 2010 13:06:59 +0100 Subject: ARM: 6467/1: amba: optional PrimeCell core voltage switch On some contemporary sub-micron SoCs, peripherals on the chip have power domain switches, i.e. the voltage to the core may be turned off to conserve power. In the Ux500 we have this for out PrimeCell derivates. This patch makes it possible to specify an (optional) regulator to handle the voltage domain switch on AMBA PrimeCells, modeled very similar to how block clocks are handled. Additional amba_vcore_[enable|disable] calls are supplied to make it possible introduce optional powering off of the core voltage. Using this will require code to spool/unspool any core HW state. Cc: Rabin Vincent Cc: Bengt Jonsson Cc: Jonas Aaberg Signed-off-by: Linus Walleij Signed-off-by: Russell King --- include/linux/amba/bus.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index c6454cc..9e7f259 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -18,6 +18,7 @@ #include #include #include +#include #define AMBA_NR_IRQS 2 #define AMBA_CID 0xb105f00d @@ -28,6 +29,7 @@ struct amba_device { struct device dev; struct resource res; struct clk *pclk; + struct regulator *vcore; u64 dma_mask; unsigned int periphid; unsigned int irq[AMBA_NR_IRQS]; @@ -71,6 +73,12 @@ void amba_release_regions(struct amba_device *); #define amba_pclk_disable(d) \ do { if (!IS_ERR((d)->pclk)) clk_disable((d)->pclk); } while (0) +#define amba_vcore_enable(d) \ + (IS_ERR((d)->vcore) ? 0 : regulator_enable((d)->vcore)) + +#define amba_vcore_disable(d) \ + do { if (!IS_ERR((d)->vcore)) regulator_disable((d)->vcore); } while (0) + /* Some drivers don't use the struct amba_device */ #define AMBA_CONFIG_BITS(a) (((a) >> 24) & 0xff) #define AMBA_REV_BITS(a) (((a) >> 20) & 0x0f) -- cgit v1.1 From 335d7afbfb71faac833734a94240c1e07cf0ead8 Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Mon, 22 Nov 2010 15:47:36 +0100 Subject: mutexes, sched: Introduce arch_mutex_cpu_relax() The spinning mutex implementation uses cpu_relax() in busy loops as a compiler barrier. Depending on the architecture, cpu_relax() may do more than needed in this specific mutex spin loops. On System z we also give up the time slice of the virtual cpu in cpu_relax(), which prevents effective spinning on the mutex. This patch replaces cpu_relax() in the spinning mutex code with arch_mutex_cpu_relax(), which can be defined by each architecture that selects HAVE_ARCH_MUTEX_CPU_RELAX. The default is still cpu_relax(), so this patch should not affect other architectures than System z for now. Signed-off-by: Gerald Schaefer Signed-off-by: Peter Zijlstra LKML-Reference: <1290437256.7455.4.camel@thinkpad> Signed-off-by: Ingo Molnar --- include/linux/mutex.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/mutex.h b/include/linux/mutex.h index f363bc8..94b48bd 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -160,4 +160,8 @@ extern int mutex_trylock(struct mutex *lock); extern void mutex_unlock(struct mutex *lock); extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); +#ifndef CONFIG_HAVE_ARCH_MUTEX_CPU_RELAX +#define arch_mutex_cpu_relax() cpu_relax() +#endif + #endif -- cgit v1.1 From 6c7e550f13f8ad82efb6a5653ae628c2543c1768 Mon Sep 17 00:00:00 2001 From: Franck Bui-Huu Date: Tue, 23 Nov 2010 16:21:43 +0100 Subject: perf: Introduce is_sampling_event() and use it when appropriate. Signed-off-by: Franck Bui-Huu Signed-off-by: Peter Zijlstra LKML-Reference: <1290525705-6265-1-git-send-email-fbuihuu@gmail.com> Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index de2c417..cbf04cc 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -969,6 +969,11 @@ extern int perf_event_overflow(struct perf_event *event, int nmi, struct perf_sample_data *data, struct pt_regs *regs); +static inline bool is_sampling_event(struct perf_event *event) +{ + return event->attr.sample_period != 0; +} + /* * Return 1 for a software event, 0 for a hardware event */ -- cgit v1.1 From 004417a6d468e24399e383645c068b498eed84ad Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 25 Nov 2010 18:38:29 +0100 Subject: perf, arch: Cleanup perf-pmu init vs lockup-detector The perf hardware pmu got initialized at various points in the boot, some before early_initcall() some after (notably arch_initcall). The problem is that the NMI lockup detector is ran from early_initcall() and expects the hardware pmu to be present. Sanitize this by moving all architecture hardware pmu implementations to initialize at early_initcall() and move the lockup detector to an explicit initcall right after that. Cc: paulus Cc: davem Cc: Michael Cree Cc: Deng-Cheng Zhu Acked-by: Paul Mundt Acked-by: Will Deacon Signed-off-by: Peter Zijlstra LKML-Reference: <1290707759.2145.119.camel@laptop> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2c79e92..d2e63d1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -316,6 +316,7 @@ extern int proc_dowatchdog_thresh(struct ctl_table *table, int write, size_t *lenp, loff_t *ppos); extern unsigned int softlockup_panic; extern int softlockup_thresh; +void lockup_detector_init(void); #else static inline void touch_softlockup_watchdog(void) { @@ -326,6 +327,9 @@ static inline void touch_softlockup_watchdog_sync(void) static inline void touch_all_softlockup_watchdogs(void) { } +static inline void lockup_detector_init(void) +{ +} #endif #ifdef CONFIG_DETECT_HUNG_TASK -- cgit v1.1 From cf7afbfeb8ceb0187348d0a1a0db61305e25f05f Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Mon, 22 Nov 2010 01:31:54 +0000 Subject: rtnl: make link af-specific updates atomic As David pointed out correctly, updates to af-specific attributes are currently not atomic. If multiple changes are requested and one of them fails, previous updates may have been applied already leaving the link behind in a undefined state. This patch splits the function parse_link_af() into two functions validate_link_af() and set_link_at(). validate_link_af() is placed to validate_linkmsg() check for errors as early as possible before any changes to the link have been made. set_link_af() is called to commit the changes later. This method is not fail proof, while it is currently sufficient to make set_link_af() inerrable and thus 100% atomic, the validation function method will not be able to detect all error scenarios in the future, there will likely always be errors depending on states which are f.e. not protected by rtnl_mutex and thus may change between validation and setting. Also, instead of silently ignoring unknown address families and config blocks for address families which did not register a set function the errors EAFNOSUPPORT respectively EOPNOSUPPORT are returned to avoid comitting 4 out of 5 update requests without notifying the user. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/net/rtnetlink.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 35be0bb..4093ca7 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -92,8 +92,10 @@ extern void rtnl_link_unregister(struct rtnl_link_ops *ops); * specific netlink attributes. * @get_link_af_size: Function to calculate size of address family specific * netlink attributes exlusive the container attribute. - * @parse_link_af: Function to parse a IFLA_AF_SPEC attribute and modify - * net_device accordingly. + * @validate_link_af: Validate a IFLA_AF_SPEC attribute, must check attr + * for invalid configuration settings. + * @set_link_af: Function to parse a IFLA_AF_SPEC attribute and modify + * net_device accordingly. */ struct rtnl_af_ops { struct list_head list; @@ -103,8 +105,10 @@ struct rtnl_af_ops { const struct net_device *dev); size_t (*get_link_af_size)(const struct net_device *dev); - int (*parse_link_af)(struct net_device *dev, - const struct nlattr *attr); + int (*validate_link_af)(const struct net_device *dev, + const struct nlattr *attr); + int (*set_link_af)(struct net_device *dev, + const struct nlattr *attr); }; extern int __rtnl_af_register(struct rtnl_af_ops *ops); -- cgit v1.1 From 5584b8078a60e34ec7d37c9b67a0f3d389a1a2f6 Mon Sep 17 00:00:00 2001 From: Shan Wei Date: Mon, 22 Nov 2010 23:00:42 +0000 Subject: sctp: kill unused macro definition These macros have been existed for several years since v2.6.12-rc2. But they never be used. So remove them now. Signed-off-by: Shan Wei Signed-off-by: David S. Miller --- include/net/sctp/constants.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include') diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index 6390884..c70d8cc 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -61,7 +61,6 @@ enum { SCTP_DEFAULT_INSTREAMS = SCTP_MAX_STREAM }; * symbols. CIDs are dense through SCTP_CID_BASE_MAX. */ #define SCTP_CID_BASE_MAX SCTP_CID_SHUTDOWN_COMPLETE -#define SCTP_CID_MAX SCTP_CID_ASCONF_ACK #define SCTP_NUM_BASE_CHUNK_TYPES (SCTP_CID_BASE_MAX + 1) @@ -86,9 +85,6 @@ typedef enum { } sctp_event_t; -#define SCTP_EVENT_T_MAX SCTP_EVENT_T_PRIMITIVE -#define SCTP_EVENT_T_NUM (SCTP_EVENT_T_MAX + 1) - /* As a convenience for the state machine, we append SCTP_EVENT_* and * SCTP_ULP_* to the list of possible chunks. */ @@ -162,9 +158,6 @@ SCTP_SUBTYPE_CONSTRUCTOR(PRIMITIVE, sctp_event_primitive_t, primitive) - (unsigned long)(c->chunk_hdr)\ - sizeof(sctp_data_chunk_t))) -#define SCTP_MAX_ERROR_CAUSE SCTP_ERROR_NONEXIST_IP -#define SCTP_NUM_ERROR_CAUSE 10 - /* Internal error codes */ typedef enum { @@ -266,7 +259,6 @@ enum { SCTP_ARBITRARY_COOKIE_ECHO_LEN = 200 }; #define SCTP_TSN_MAP_INITIAL BITS_PER_LONG #define SCTP_TSN_MAP_INCREMENT SCTP_TSN_MAP_INITIAL #define SCTP_TSN_MAP_SIZE 4096 -#define SCTP_TSN_MAX_GAP 65535 /* We will not record more than this many duplicate TSNs between two * SACKs. The minimum PMTU is 576. Remove all the headers and there @@ -301,9 +293,6 @@ enum { SCTP_MAX_GABS = 16 }; #define SCTP_CLOCK_GRANULARITY 1 /* 1 jiffy */ -#define SCTP_DEF_MAX_INIT 6 -#define SCTP_DEF_MAX_SEND 10 - #define SCTP_DEFAULT_COOKIE_LIFE (60 * 1000) /* 60 seconds */ #define SCTP_DEFAULT_MINWINDOW 1500 /* default minimum rwnd size */ @@ -317,9 +306,6 @@ enum { SCTP_MAX_GABS = 16 }; */ #define SCTP_DEFAULT_MINSEGMENT 512 /* MTU size ... if no mtu disc */ #define SCTP_HOW_MANY_SECRETS 2 /* How many secrets I keep */ -#define SCTP_HOW_LONG_COOKIE_LIVE 3600 /* How many seconds the current - * secret will live? - */ #define SCTP_SECRET_SIZE 32 /* Number of octets in a 256 bits. */ #define SCTP_SIGNATURE_SIZE 20 /* size of a SLA-1 signature */ -- cgit v1.1 From 5a0d2268d259886f0c87131639d19eb4a67b4532 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 23 Nov 2010 10:42:02 +0000 Subject: net: add netif_tx_queue_frozen_or_stopped When testing struct netdev_queue state against FROZEN bit, we also test XOFF bit. We can test both bits at once and save some cycles. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index badf928..7c6ae2f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -493,6 +493,8 @@ static inline void napi_synchronize(const struct napi_struct *n) enum netdev_queue_state_t { __QUEUE_STATE_XOFF, __QUEUE_STATE_FROZEN, +#define QUEUE_STATE_XOFF_OR_FROZEN ((1 << __QUEUE_STATE_XOFF) | \ + (1 << __QUEUE_STATE_FROZEN)) }; struct netdev_queue { @@ -1629,9 +1631,9 @@ static inline int netif_queue_stopped(const struct net_device *dev) return netif_tx_queue_stopped(netdev_get_tx_queue(dev, 0)); } -static inline int netif_tx_queue_frozen(const struct netdev_queue *dev_queue) +static inline int netif_tx_queue_frozen_or_stopped(const struct netdev_queue *dev_queue) { - return test_bit(__QUEUE_STATE_FROZEN, &dev_queue->state); + return dev_queue->state & QUEUE_STATE_XOFF_OR_FROZEN; } /** -- cgit v1.1 From 5595a1a5997953dbd8c5df7c2f7d4b3a2eb2be4b Mon Sep 17 00:00:00 2001 From: andrew hendry Date: Thu, 25 Nov 2010 02:18:15 +0000 Subject: X25 remove bkl in subscription ioctls Signed-off-by: Andrew Hendry Signed-off-by: David S. Miller --- include/net/x25.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/x25.h b/include/net/x25.h index 1479cb4..a06119a 100644 --- a/include/net/x25.h +++ b/include/net/x25.h @@ -315,6 +315,8 @@ extern struct list_head x25_route_list; extern rwlock_t x25_route_list_lock; extern struct list_head x25_forward_list; extern rwlock_t x25_forward_list_lock; +extern struct list_head x25_neigh_list; +extern rwlock_t x25_neigh_list_lock; extern int x25_proc_init(void); extern void x25_proc_exit(void); -- cgit v1.1 From 85beb5869a4f6abb52a7cf8e01de6fa57e9ee47d Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 24 Nov 2010 16:23:34 -0500 Subject: tracing/slab: Move kmalloc tracepoint out of inline code The tracepoint for kmalloc is in the slab inlined code which causes every instance of kmalloc to have the tracepoint. This patch moves the tracepoint out of the inline code to the slab C file, which removes a large number of inlined trace points. objdump -dr vmlinux.slab| grep 'jmpq.* Signed-off-by: Pekka Enberg --- include/linux/slab_def.h | 33 +++++++++++++-------------------- 1 file changed, 13 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 791a502..83203ae 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -138,11 +138,12 @@ void *kmem_cache_alloc(struct kmem_cache *, gfp_t); void *__kmalloc(size_t size, gfp_t flags); #ifdef CONFIG_TRACING -extern void *kmem_cache_alloc_notrace(struct kmem_cache *cachep, gfp_t flags); +extern void *kmem_cache_alloc_trace(size_t size, + struct kmem_cache *cachep, gfp_t flags); extern size_t slab_buffer_size(struct kmem_cache *cachep); #else static __always_inline void * -kmem_cache_alloc_notrace(struct kmem_cache *cachep, gfp_t flags) +kmem_cache_alloc_trace(size_t size, struct kmem_cache *cachep, gfp_t flags) { return kmem_cache_alloc(cachep, flags); } @@ -179,10 +180,7 @@ found: #endif cachep = malloc_sizes[i].cs_cachep; - ret = kmem_cache_alloc_notrace(cachep, flags); - - trace_kmalloc(_THIS_IP_, ret, - size, slab_buffer_size(cachep), flags); + ret = kmem_cache_alloc_trace(size, cachep, flags); return ret; } @@ -194,14 +192,16 @@ extern void *__kmalloc_node(size_t size, gfp_t flags, int node); extern void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node); #ifdef CONFIG_TRACING -extern void *kmem_cache_alloc_node_notrace(struct kmem_cache *cachep, - gfp_t flags, - int nodeid); +extern void *kmem_cache_alloc_node_trace(size_t size, + struct kmem_cache *cachep, + gfp_t flags, + int nodeid); #else static __always_inline void * -kmem_cache_alloc_node_notrace(struct kmem_cache *cachep, - gfp_t flags, - int nodeid) +kmem_cache_alloc_node_trace(size_t size, + struct kmem_cache *cachep, + gfp_t flags, + int nodeid) { return kmem_cache_alloc_node(cachep, flags, nodeid); } @@ -210,7 +210,6 @@ kmem_cache_alloc_node_notrace(struct kmem_cache *cachep, static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { struct kmem_cache *cachep; - void *ret; if (__builtin_constant_p(size)) { int i = 0; @@ -234,13 +233,7 @@ found: #endif cachep = malloc_sizes[i].cs_cachep; - ret = kmem_cache_alloc_node_notrace(cachep, flags, node); - - trace_kmalloc_node(_THIS_IP_, ret, - size, slab_buffer_size(cachep), - flags, node); - - return ret; + return kmem_cache_alloc_node_trace(size, cachep, flags, node); } return __kmalloc_node(size, flags, node); } -- cgit v1.1 From aa285b1740f5b13e5a2606a927f3129954583d78 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timo=20Ter=C3=A4s?= Date: Tue, 23 Nov 2010 04:03:45 +0000 Subject: xfrm: fix gre key endianess MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit fl->fl_gre_key is network byte order contrary to fl->fl_icmp_*. Make xfrm_flowi_{s|d}port return network byte order values for gre key too. Signed-off-by: Timo Teräs Signed-off-by: David S. Miller --- include/net/xfrm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 54b2832..7fa5b00 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -806,7 +806,7 @@ __be16 xfrm_flowi_sport(struct flowi *fl) port = htons(fl->fl_mh_type); break; case IPPROTO_GRE: - port = htonl(fl->fl_gre_key) >> 16; + port = htons(ntohl(fl->fl_gre_key) >> 16); break; default: port = 0; /*XXX*/ @@ -830,7 +830,7 @@ __be16 xfrm_flowi_dport(struct flowi *fl) port = htons(fl->fl_icmp_code); break; case IPPROTO_GRE: - port = htonl(fl->fl_gre_key) & 0xffff; + port = htons(ntohl(fl->fl_gre_key) & 0xffff); break; default: port = 0; /*XXX*/ -- cgit v1.1 From ce6ada35bdf710d16582cc4869c26722547e6f11 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Thu, 25 Nov 2010 17:11:32 +0000 Subject: security: Define CAP_SYSLOG Privileged syslog operations currently require CAP_SYS_ADMIN. Split this off into a new CAP_SYSLOG privilege which we can sanely take away from a container through the capability bounding set. With this patch, an lxc container can be prevented from messing with the host's syslog (i.e. dmesg -c). Changelog: mar 12 2010: add selinux capability2:cap_syslog perm Changelog: nov 22 2010: . port to new kernel . add a WARN_ONCE if userspace isn't using CAP_SYSLOG Signed-off-by: Serge Hallyn Acked-by: Andrew G. Morgan Acked-By: Kees Cook Cc: James Morris Cc: Michael Kerrisk Cc: Stephen Smalley Cc: "Christopher J. PeBenito" Cc: Eric Paris Signed-off-by: James Morris --- include/linux/capability.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/capability.h b/include/linux/capability.h index 90012b9..fb16a36 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -246,7 +246,6 @@ struct cpu_vfs_cap_data { /* Allow configuration of the secure attention key */ /* Allow administration of the random device */ /* Allow examination and configuration of disk quotas */ -/* Allow configuring the kernel's syslog (printk behaviour) */ /* Allow setting the domainname */ /* Allow setting the hostname */ /* Allow calling bdflush() */ @@ -352,7 +351,11 @@ struct cpu_vfs_cap_data { #define CAP_MAC_ADMIN 33 -#define CAP_LAST_CAP CAP_MAC_ADMIN +/* Allow configuring the kernel's syslog (printk behaviour) */ + +#define CAP_SYSLOG 34 + +#define CAP_LAST_CAP CAP_SYSLOG #define cap_valid(x) ((x) >= 0 && (x) <= CAP_LAST_CAP) -- cgit v1.1 From dc88e46029486ed475c71fe1bb696d39511ac8fe Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Tue, 23 Nov 2010 17:50:31 -0500 Subject: lib: hex2bin converts ascii hexadecimal string to binary Similar to the kgdb_hex2mem() code, hex2bin converts a string to binary using the hex_to_bin() library call. Changelog: - Replace parameter names with src/dst (based on David Howell's comment) - Add 'const' where needed (based on David Howell's comment) - Replace int with size_t (based on David Howell's comment) Signed-off-by: Mimi Zohar Acked-by: Serge E. Hallyn Acked-by: David Howells Signed-off-by: James Morris --- include/linux/kernel.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index a35b4f7..d0fbc04 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -265,6 +265,7 @@ static inline char *pack_hex_byte(char *buf, u8 byte) } extern int hex_to_bin(char ch); +extern void hex2bin(u8 *dst, const char *src, size_t count); /* * General tracing related utility functions - trace_printk(), -- cgit v1.1 From c749ba912e87ccebd674ae24b97462176c63732e Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Tue, 23 Nov 2010 18:54:16 -0500 Subject: key: add tpm_send command Add internal kernel tpm_send() command used to seal/unseal keys. Changelog: - replaced module_put in tpm_send() with new tpm_chip_put() wrapper (suggested by David Howells) - Make tpm_send() cmd argument a 'void *' (suggested by David Howells) Signed-off-by: David Safford Signed-off-by: Mimi Zohar Acked-by: David Howells Acked-by: Serge E. Hallyn Signed-off-by: James Morris --- include/linux/tpm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/tpm.h b/include/linux/tpm.h index ac5d1c1..fdc718a 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -31,6 +31,7 @@ extern int tpm_pcr_read(u32 chip_num, int pcr_idx, u8 *res_buf); extern int tpm_pcr_extend(u32 chip_num, int pcr_idx, const u8 *hash); +extern int tpm_send(u32 chip_num, void *cmd, size_t buflen); #else static inline int tpm_pcr_read(u32 chip_num, int pcr_idx, u8 *res_buf) { return -ENODEV; @@ -38,5 +39,8 @@ static inline int tpm_pcr_read(u32 chip_num, int pcr_idx, u8 *res_buf) { static inline int tpm_pcr_extend(u32 chip_num, int pcr_idx, const u8 *hash) { return -ENODEV; } +static inline int tpm_send(u32 chip_num, void *cmd, size_t buflen) { + return -ENODEV; +} #endif #endif -- cgit v1.1 From d00a1c72f7f4661212299e6cb132dfa58030bcdb Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Tue, 23 Nov 2010 17:50:34 -0500 Subject: keys: add new trusted key-type Define a new kernel key-type called 'trusted'. Trusted keys are random number symmetric keys, generated and RSA-sealed by the TPM. The TPM only unseals the keys, if the boot PCRs and other criteria match. Userspace can only ever see encrypted blobs. Based on suggestions by Jason Gunthorpe, several new options have been added to support additional usages. The new options are: migratable= designates that the key may/may not ever be updated (resealed under a new key, new pcrinfo or new auth.) pcrlock=n extends the designated PCR 'n' with a random value, so that a key sealed to that PCR may not be unsealed again until after a reboot. keyhandle= specifies the sealing/unsealing key handle. keyauth= specifies the sealing/unsealing key auth. blobauth= specifies the sealed data auth. Implementation of a kernel reserved locality for trusted keys will be investigated for a possible future extension. Changelog: - Updated and added examples to Documentation/keys-trusted-encrypted.txt - Moved generic TPM constants to include/linux/tpm_command.h (David Howell's suggestion.) - trusted_defined.c: replaced kzalloc with kmalloc, added pcrlock failure error handling, added const qualifiers where appropriate. - moved to late_initcall - updated from hash to shash (suggestion by David Howells) - reduced worst stack usage (tpm_seal) from 530 to 312 bytes - moved documentation to Documentation directory (suggestion by David Howells) - all the other code cleanups suggested by David Howells - Add pcrlock CAP_SYS_ADMIN dependency (based on comment by Jason Gunthorpe) - New options: migratable, pcrlock, keyhandle, keyauth, blobauth (based on discussions with Jason Gunthorpe) - Free payload on failure to create key(reported/fixed by Roberto Sassu) - Updated Kconfig and other descriptions (based on Serge Hallyn's suggestion) - Replaced kzalloc() with kmalloc() (reported by Serge Hallyn) Signed-off-by: David Safford Signed-off-by: Mimi Zohar Signed-off-by: James Morris --- include/keys/trusted-type.h | 31 +++++++++++++++++++++++++++++++ include/linux/tpm_command.h | 28 ++++++++++++++++++++++++++++ 2 files changed, 59 insertions(+) create mode 100644 include/keys/trusted-type.h create mode 100644 include/linux/tpm_command.h (limited to 'include') diff --git a/include/keys/trusted-type.h b/include/keys/trusted-type.h new file mode 100644 index 0000000..56f82e5 --- /dev/null +++ b/include/keys/trusted-type.h @@ -0,0 +1,31 @@ +/* + * Copyright (C) 2010 IBM Corporation + * Author: David Safford + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, version 2 of the License. + */ + +#ifndef _KEYS_TRUSTED_TYPE_H +#define _KEYS_TRUSTED_TYPE_H + +#include +#include + +#define MIN_KEY_SIZE 32 +#define MAX_KEY_SIZE 128 +#define MAX_BLOB_SIZE 320 + +struct trusted_key_payload { + struct rcu_head rcu; + unsigned int key_len; + unsigned int blob_len; + unsigned char migratable; + unsigned char key[MAX_KEY_SIZE + 1]; + unsigned char blob[MAX_BLOB_SIZE]; +}; + +extern struct key_type key_type_trusted; + +#endif /* _KEYS_TRUSTED_TYPE_H */ diff --git a/include/linux/tpm_command.h b/include/linux/tpm_command.h new file mode 100644 index 0000000..727512e --- /dev/null +++ b/include/linux/tpm_command.h @@ -0,0 +1,28 @@ +#ifndef __LINUX_TPM_COMMAND_H__ +#define __LINUX_TPM_COMMAND_H__ + +/* + * TPM Command constants from specifications at + * http://www.trustedcomputinggroup.org + */ + +/* Command TAGS */ +#define TPM_TAG_RQU_COMMAND 193 +#define TPM_TAG_RQU_AUTH1_COMMAND 194 +#define TPM_TAG_RQU_AUTH2_COMMAND 195 +#define TPM_TAG_RSP_COMMAND 196 +#define TPM_TAG_RSP_AUTH1_COMMAND 197 +#define TPM_TAG_RSP_AUTH2_COMMAND 198 + +/* Command Ordinals */ +#define TPM_ORD_GETRANDOM 70 +#define TPM_ORD_OSAP 11 +#define TPM_ORD_OIAP 10 +#define TPM_ORD_SEAL 23 +#define TPM_ORD_UNSEAL 24 + +/* Other constants */ +#define SRKHANDLE 0x40000000 +#define TPM_NONCE_SIZE 20 + +#endif -- cgit v1.1 From 7e70cb4978507cf31d76b90e4cfb4c28cad87f0c Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Tue, 23 Nov 2010 18:55:35 -0500 Subject: keys: add new key-type encrypted Define a new kernel key-type called 'encrypted'. Encrypted keys are kernel generated random numbers, which are encrypted/decrypted with a 'trusted' symmetric key. Encrypted keys are created/encrypted/decrypted in the kernel. Userspace only ever sees/stores encrypted blobs. Changelog: - bug fix: replaced master-key rcu based locking with semaphore (reported by David Howells) - Removed memset of crypto_shash_digest() digest output - Replaced verification of 'key-type:key-desc' using strcspn(), with one based on string constants. - Moved documentation to Documentation/keys-trusted-encrypted.txt - Replace hash with shash (based on comments by David Howells) - Make lengths/counts size_t where possible (based on comments by David Howells) Could not convert most lengths, as crypto expects 'unsigned int' (size_t: on 32 bit is defined as unsigned int, but on 64 bit is unsigned long) - Add 'const' where possible (based on comments by David Howells) - allocate derived_buf dynamically to support arbitrary length master key (fixed by Roberto Sassu) - wait until late_initcall for crypto libraries to be registered - cleanup security/Kconfig - Add missing 'update' keyword (reported/fixed by Roberto Sassu) - Free epayload on failure to create key (reported/fixed by Roberto Sassu) - Increase the data size limit (requested by Roberto Sassu) - Crypto return codes are always 0 on success and negative on failure, remove unnecessary tests. - Replaced kzalloc() with kmalloc() Signed-off-by: Mimi Zohar Signed-off-by: David Safford Reviewed-by: Roberto Sassu Signed-off-by: James Morris --- include/keys/encrypted-type.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) create mode 100644 include/keys/encrypted-type.h (limited to 'include') diff --git a/include/keys/encrypted-type.h b/include/keys/encrypted-type.h new file mode 100644 index 0000000..9585501 --- /dev/null +++ b/include/keys/encrypted-type.h @@ -0,0 +1,29 @@ +/* + * Copyright (C) 2010 IBM Corporation + * Author: Mimi Zohar + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, version 2 of the License. + */ + +#ifndef _KEYS_ENCRYPTED_TYPE_H +#define _KEYS_ENCRYPTED_TYPE_H + +#include +#include + +struct encrypted_key_payload { + struct rcu_head rcu; + char *master_desc; /* datablob: master key name */ + char *datalen; /* datablob: decrypted key length */ + u8 *iv; /* datablob: iv */ + u8 *encrypted_data; /* datablob: encrypted data */ + unsigned short datablob_len; /* length of datablob */ + unsigned short decrypted_datalen; /* decrypted data length */ + u8 decrypted_data[0]; /* decrypted data + datablob + hmac */ +}; + +extern struct key_type key_type_encrypted; + +#endif /* _KEYS_ENCRYPTED_TYPE_H */ -- cgit v1.1 From fa9f90be745d3b600a9d97a063be404c5e5d9071 Mon Sep 17 00:00:00 2001 From: Jesper Juhl Date: Sun, 28 Nov 2010 21:39:34 +0100 Subject: =?UTF-8?q?Kill=20off=20a=20bunch=20of=20warning:=20=E2=80=98inlin?= =?UTF-8?q?e=E2=80=99=20is=20not=20at=20beginning=20of=20declaration?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These warnings are spewed during a build of a 'allnoconfig' kernel (especially the ones from u64_stats_sync.h show up a lot) when building with -Wextra (which I often do).. They are a) annoying b) easy to get rid of. This patch kills them off. include/linux/u64_stats_sync.h:70:1: warning: ‘inline’ is not at beginning of declaration include/linux/u64_stats_sync.h:77:1: warning: ‘inline’ is not at beginning of declaration include/linux/u64_stats_sync.h:84:1: warning: ‘inline’ is not at beginning of declaration include/linux/u64_stats_sync.h:96:1: warning: ‘inline’ is not at beginning of declaration include/linux/u64_stats_sync.h:115:1: warning: ‘inline’ is not at beginning of declaration include/linux/u64_stats_sync.h:127:1: warning: ‘inline’ is not at beginning of declaration kernel/time.c:241:1: warning: ‘inline’ is not at beginning of declaration kernel/time.c:257:1: warning: ‘inline’ is not at beginning of declaration kernel/perf_event.c:4513:1: warning: ‘inline’ is not at beginning of declaration mm/page_alloc.c:4012:1: warning: ‘inline’ is not at beginning of declaration Signed-off-by: Jesper Juhl Signed-off-by: Jiri Kosina --- include/linux/u64_stats_sync.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index fa261a0..8da8c4e 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -67,21 +67,21 @@ struct u64_stats_sync { #endif }; -static void inline u64_stats_update_begin(struct u64_stats_sync *syncp) +static inline void u64_stats_update_begin(struct u64_stats_sync *syncp) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) write_seqcount_begin(&syncp->seq); #endif } -static void inline u64_stats_update_end(struct u64_stats_sync *syncp) +static inline void u64_stats_update_end(struct u64_stats_sync *syncp) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) write_seqcount_end(&syncp->seq); #endif } -static unsigned int inline u64_stats_fetch_begin(const struct u64_stats_sync *syncp) +static inline unsigned int u64_stats_fetch_begin(const struct u64_stats_sync *syncp) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) return read_seqcount_begin(&syncp->seq); @@ -93,7 +93,7 @@ static unsigned int inline u64_stats_fetch_begin(const struct u64_stats_sync *sy #endif } -static bool inline u64_stats_fetch_retry(const struct u64_stats_sync *syncp, +static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp, unsigned int start) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) @@ -112,7 +112,7 @@ static bool inline u64_stats_fetch_retry(const struct u64_stats_sync *syncp, * - UP 32bit must disable BH. * - 64bit have no problem atomically reading u64 values, irq safe. */ -static unsigned int inline u64_stats_fetch_begin_bh(const struct u64_stats_sync *syncp) +static inline unsigned int u64_stats_fetch_begin_bh(const struct u64_stats_sync *syncp) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) return read_seqcount_begin(&syncp->seq); @@ -124,7 +124,7 @@ static unsigned int inline u64_stats_fetch_begin_bh(const struct u64_stats_sync #endif } -static bool inline u64_stats_fetch_retry_bh(const struct u64_stats_sync *syncp, +static inline bool u64_stats_fetch_retry_bh(const struct u64_stats_sync *syncp, unsigned int start) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) -- cgit v1.1 From bf26414510103448ad3dc069c7422462f03ea3d7 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Fri, 26 Nov 2010 08:36:09 +0000 Subject: xps: Add CONFIG_XPS This patch adds XPS_CONFIG option to enable and disable XPS. This is done in the same manner as RPS_CONFIG. This is also fixes build failure in XPS code when SMP is not enabled. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 52 +++++++++++++++++++++++++---------------------- 1 file changed, 28 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7c6ae2f..9ae4544 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -536,30 +536,6 @@ struct rps_map { #define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + (_num * sizeof(u16))) /* - * This structure holds an XPS map which can be of variable length. The - * map is an array of queues. - */ -struct xps_map { - unsigned int len; - unsigned int alloc_len; - struct rcu_head rcu; - u16 queues[0]; -}; -#define XPS_MAP_SIZE(_num) (sizeof(struct xps_map) + (_num * sizeof(u16))) -#define XPS_MIN_MAP_ALLOC ((L1_CACHE_BYTES - sizeof(struct xps_map)) \ - / sizeof(u16)) - -/* - * This structure holds all XPS maps for device. Maps are indexed by CPU. - */ -struct xps_dev_maps { - struct rcu_head rcu; - struct xps_map *cpu_map[0]; -}; -#define XPS_DEV_MAPS_SIZE (sizeof(struct xps_dev_maps) + \ - (nr_cpu_ids * sizeof(struct xps_map *))) - -/* * The rps_dev_flow structure contains the mapping of a flow to a CPU and the * tail pointer for that CPU's input queue at the time of last enqueue. */ @@ -626,6 +602,32 @@ struct netdev_rx_queue { } ____cacheline_aligned_in_smp; #endif /* CONFIG_RPS */ +#ifdef CONFIG_XPS +/* + * This structure holds an XPS map which can be of variable length. The + * map is an array of queues. + */ +struct xps_map { + unsigned int len; + unsigned int alloc_len; + struct rcu_head rcu; + u16 queues[0]; +}; +#define XPS_MAP_SIZE(_num) (sizeof(struct xps_map) + (_num * sizeof(u16))) +#define XPS_MIN_MAP_ALLOC ((L1_CACHE_BYTES - sizeof(struct xps_map)) \ + / sizeof(u16)) + +/* + * This structure holds all XPS maps for device. Maps are indexed by CPU. + */ +struct xps_dev_maps { + struct rcu_head rcu; + struct xps_map *cpu_map[0]; +}; +#define XPS_DEV_MAPS_SIZE (sizeof(struct xps_dev_maps) + \ + (nr_cpu_ids * sizeof(struct xps_map *))) +#endif /* CONFIG_XPS */ + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -1046,7 +1048,9 @@ struct net_device { unsigned long tx_queue_len; /* Max frames per queue allowed */ spinlock_t tx_global_lock; +#ifdef CONFIG_XPS struct xps_dev_maps *xps_maps; +#endif /* These may be needed for future network-power-down code. */ -- cgit v1.1 From 1ae0affedce1d3e401991fbe7f2674753f0a7641 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Fri, 26 Nov 2010 23:02:58 +0000 Subject: mmc, sh: Correct value for reset This resolves a regression that I introduced in "mmc, sh: Move constants to sh_mmcif.h". Having examined the manual and tested the code on an AP4EVB board it seems that the correct sequence is. 1) Write 1 to bit 31 and zeros to all other bits 2) Write zero to all bits Cc: Yusuke Goda Cc: Magnus Damm Signed-off-by: Simon Horman Signed-off-by: Paul Mundt --- include/linux/mmc/sh_mmcif.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/mmc/sh_mmcif.h index a6bfa52..342ec1a 100644 --- a/include/linux/mmc/sh_mmcif.h +++ b/include/linux/mmc/sh_mmcif.h @@ -80,7 +80,7 @@ struct sh_mmcif_plat_data { /* CE_VERSION */ #define SOFT_RST_ON (1 << 31) -#define SOFT_RST_OFF ~SOFT_RST_ON +#define SOFT_RST_OFF 0 static inline u32 sh_mmcif_readl(void __iomem *addr, int reg) { @@ -168,12 +168,9 @@ static inline int sh_mmcif_boot_do_read(void __iomem *base, static inline void sh_mmcif_boot_init(void __iomem *base) { - unsigned long tmp; - /* reset */ - tmp = sh_mmcif_readl(base, MMCIF_CE_VERSION); - sh_mmcif_writel(base, MMCIF_CE_VERSION, tmp | SOFT_RST_ON); - sh_mmcif_writel(base, MMCIF_CE_VERSION, tmp & SOFT_RST_OFF); + sh_mmcif_writel(base, MMCIF_CE_VERSION, SOFT_RST_ON); + sh_mmcif_writel(base, MMCIF_CE_VERSION, SOFT_RST_OFF); /* byte swap */ sh_mmcif_writel(base, MMCIF_CE_BUF_ACC, BUF_ACC_ATYP); -- cgit v1.1 From 22efa0fee32d9e7f6f6fbc396a872b5708d86048 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Sat, 27 Nov 2010 00:11:55 +0000 Subject: sh, mmc: Use defines when setting CE_CLK_CTRL The 16-19th bits of CE_CLK_CTRL set the MMC clock frequency. Cc: Yusuke Goda Cc: Magnus Damm Signed-off-by: Simon Horman Signed-off-by: Paul Mundt --- include/linux/mmc/sh_mmcif.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/mmc/sh_mmcif.h index 342ec1a..ffabf8c 100644 --- a/include/linux/mmc/sh_mmcif.h +++ b/include/linux/mmc/sh_mmcif.h @@ -70,6 +70,9 @@ struct sh_mmcif_plat_data { #define CLK_ENABLE (1 << 24) /* 1: output mmc clock */ #define CLK_CLEAR ((1 << 19) | (1 << 18) | (1 << 17) | (1 << 16)) #define CLK_SUP_PCLK ((1 << 19) | (1 << 18) | (1 << 17) | (1 << 16)) +#define CLKDIV_4 (1<<16) /* mmc clock frequency. + * n: bus clock/(2^(n+1)) */ +#define CLKDIV_256 (7<<16) /* mmc clock frequency. (see above) */ #define SRSPTO_256 ((1 << 13) | (0 << 12)) /* resp timeout */ #define SRBSYTO_29 ((1 << 11) | (1 << 10) | \ (1 << 9) | (1 << 8)) /* resp busy timeout */ @@ -178,14 +181,10 @@ static inline void sh_mmcif_boot_init(void __iomem *base) /* Set block size in MMCIF hardware */ sh_mmcif_writel(base, MMCIF_CE_BLOCK_SET, SH_MMCIF_BBS); - /* Enable the clock, set it to Bus clock/256 (about 325Khz). - * It is unclear where 0x70000 comes from or if it is even needed. - * It is there for byte-compatibility with code that is known to - * work. - */ + /* Enable the clock, set it to Bus clock/256 (about 325Khz). */ sh_mmcif_writel(base, MMCIF_CE_CLK_CTRL, - CLK_ENABLE | SRSPTO_256 | SRBSYTO_29 | SRWDTO_29 | - SCCSTO_29 | 0x70000); + CLK_ENABLE | CLKDIV_256 | SRSPTO_256 | + SRBSYTO_29 | SRWDTO_29 | SCCSTO_29); /* CMD0 */ sh_mmcif_boot_cmd(base, 0x00000040, 0); @@ -210,7 +209,9 @@ static inline void sh_mmcif_boot_slurp(void __iomem *base, unsigned long tmp; /* In data transfer mode: Set clock to Bus clock/4 (about 20Mhz) */ - sh_mmcif_writel(base, MMCIF_CE_CLK_CTRL, 0x01012fff); + sh_mmcif_writel(base, MMCIF_CE_CLK_CTRL, + CLK_ENABLE | CLKDIV_4 | SRSPTO_256 | + SRBSYTO_29 | SRWDTO_29 | SCCSTO_29); /* CMD9 - Get CSD */ sh_mmcif_boot_cmd(base, 0x09806000, 0x00010000); -- cgit v1.1 From 49b4a6546fac02f58784f0744e0f99a6562ccc03 Mon Sep 17 00:00:00 2001 From: Shan Wei Date: Mon, 29 Nov 2010 00:14:58 +0000 Subject: sctp: kill unused macros in head file 1. SCTP_CMD_NUM_VERBS,SCTP_CMD_MAX These two macros have never been used for several years since v2.6.12-rc2. 2.sctp_port_rover,sctp_port_alloc_lock The commit 063930 abandoned global variables of port_rover and port_alloc_lock, but still keep two macros to refer to them. So, remove them now. commit 06393009000779b00a558fd2f280882cc7dc2008 Author: Stephen Hemminger Date: Wed Oct 10 17:30:18 2007 -0700 [SCTP]: port randomization Signed-off-by: Shan Wei Signed-off-by: David S. Miller --- include/net/sctp/command.h | 3 --- include/net/sctp/structs.h | 2 -- 2 files changed, 5 deletions(-) (limited to 'include') diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h index 2c55a7e..c01dc99 100644 --- a/include/net/sctp/command.h +++ b/include/net/sctp/command.h @@ -111,9 +111,6 @@ typedef enum { SCTP_CMD_LAST } sctp_verb_t; -#define SCTP_CMD_MAX (SCTP_CMD_LAST - 1) -#define SCTP_CMD_NUM_VERBS (SCTP_CMD_MAX + 1) - /* How many commands can you put in an sctp_cmd_seq_t? * This is a rather arbitrary number, ideally derived from a careful * analysis of the state functions, but in reality just taken from diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 69fef4f..cc9185c 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -261,8 +261,6 @@ extern struct sctp_globals { #define sctp_assoc_hashsize (sctp_globals.assoc_hashsize) #define sctp_assoc_hashtable (sctp_globals.assoc_hashtable) #define sctp_port_hashsize (sctp_globals.port_hashsize) -#define sctp_port_rover (sctp_globals.port_rover) -#define sctp_port_alloc_lock (sctp_globals.port_alloc_lock) #define sctp_port_hashtable (sctp_globals.port_hashtable) #define sctp_local_addr_list (sctp_globals.local_addr_list) #define sctp_local_addr_lock (sctp_globals.addr_list_lock) -- cgit v1.1 From a41778694806ac1ccd4b1dafed1abef8d5ba98ac Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 28 Nov 2010 21:43:02 +0000 Subject: xps: add __rcu annotations Avoid sparse warnings : add __rcu annotations and use rcu_dereference_protected() where necessary. Signed-off-by: Eric Dumazet Cc: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9ae4544..4b0c7f3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -622,7 +622,7 @@ struct xps_map { */ struct xps_dev_maps { struct rcu_head rcu; - struct xps_map *cpu_map[0]; + struct xps_map __rcu *cpu_map[0]; }; #define XPS_DEV_MAPS_SIZE (sizeof(struct xps_dev_maps) + \ (nr_cpu_ids * sizeof(struct xps_map *))) @@ -1049,7 +1049,7 @@ struct net_device { spinlock_t tx_global_lock; #ifdef CONFIG_XPS - struct xps_dev_maps *xps_maps; + struct xps_dev_maps __rcu *xps_maps; #endif /* These may be needed for future network-power-down code. */ -- cgit v1.1 From 62a8c3a32e4143812ed8e0f3783ef1ea40dc87e4 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Wed, 24 Nov 2010 19:33:43 +0000 Subject: Staging: sep: handle the rar definition stuff in the header SEP isn't the only driver that may need to handle both cases easily Signed-off-by: Alan Cox Signed-off-by: Greg Kroah-Hartman --- include/linux/rar_register.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/rar_register.h b/include/linux/rar_register.h index ffa8057..5c61181 100644 --- a/include/linux/rar_register.h +++ b/include/linux/rar_register.h @@ -34,11 +34,27 @@ struct rar_device; +#if defined(CONFIG_RAR_REGISTER) int register_rar(int num, int (*callback)(unsigned long data), unsigned long data); void unregister_rar(int num); int rar_get_address(int rar_index, dma_addr_t *start, dma_addr_t *end); int rar_lock(int rar_index); +#else +extern void unregister_rar(int num) { } +extern int rar_lock(int rar_index) { return -EIO; } + +extern inline int register_rar(int num, + int (*callback)(unsigned long data), unsigned long data) +{ + return -ENODEV; +} + +extern int rar_get_address(int rar_index, dma_addr_t *start, dma_addr_t *end) +{ + return -ENODEV; +} +#endif /* RAR_REGISTER */ #endif /* __KERNEL__ */ #endif /* _RAR_REGISTER_H */ -- cgit v1.1 From f7ca38dfe58c20cb1aa2ed9643187e8b194b5bae Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 25 Nov 2010 10:02:29 +0100 Subject: nl80211/cfg80211: extend mgmt-tx API for off-channel With p2p, it is sometimes necessary to transmit a frame (typically an action frame) on another channel than the current channel. Enable this through the CMD_FRAME API, and allow it to wait for a response. A new command allows that wait to be aborted. However, allow userspace to specify whether or not it wants to allow off-channel TX, it may actually want to use the same channel only. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 25 ++++++++++++++++++++----- include/net/cfg80211.h | 11 ++++++++--- 2 files changed, 28 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index d706bf3..5cfa579 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -358,11 +358,16 @@ * user space application). %NL80211_ATTR_FRAME is used to specify the * frame contents (including header). %NL80211_ATTR_WIPHY_FREQ (and * optionally %NL80211_ATTR_WIPHY_CHANNEL_TYPE) is used to indicate on - * which channel the frame is to be transmitted or was received. This - * channel has to be the current channel (remain-on-channel or the - * operational channel). When called, this operation returns a cookie - * (%NL80211_ATTR_COOKIE) that will be included with the TX status event - * pertaining to the TX request. + * which channel the frame is to be transmitted or was received. If this + * channel is not the current channel (remain-on-channel or the + * operational channel) the device will switch to the given channel and + * transmit the frame, optionally waiting for a response for the time + * specified using %NL80211_ATTR_DURATION. When called, this operation + * returns a cookie (%NL80211_ATTR_COOKIE) that will be included with the + * TX status event pertaining to the TX request. + * @NL80211_CMD_FRAME_WAIT_CANCEL: When an off-channel TX was requested, this + * command may be used with the corresponding cookie to cancel the wait + * time if it is known that it is no longer necessary. * @NL80211_CMD_ACTION: Alias for @NL80211_CMD_FRAME for backward compatibility. * @NL80211_CMD_FRAME_TX_STATUS: Report TX status of a management frame * transmitted with %NL80211_CMD_FRAME. %NL80211_ATTR_COOKIE identifies @@ -493,6 +498,8 @@ enum nl80211_commands { NL80211_CMD_SET_CHANNEL, NL80211_CMD_SET_WDS_PEER, + NL80211_CMD_FRAME_WAIT_CANCEL, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -828,6 +835,12 @@ enum nl80211_commands { * * @NL80211_ATTR_MCAST_RATE: Multicast tx rate (in 100 kbps) for IBSS * + * @NL80211_ATTR_OFFCHANNEL_TX_OK: For management frame TX, the frame may be + * transmitted on another channel when the channel given doesn't match + * the current channel. If the current channel doesn't match and this + * flag isn't set, the frame will be rejected. This is also used as an + * nl80211 capability flag. + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -1002,6 +1015,8 @@ enum nl80211_attrs { NL80211_ATTR_MCAST_RATE, + NL80211_ATTR_OFFCHANNEL_TX_OK, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 0663945..49a7c53 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1134,7 +1134,9 @@ struct cfg80211_pmksa { * @cancel_remain_on_channel: Cancel an on-going remain-on-channel operation. * This allows the operation to be terminated prior to timeout based on * the duration value. - * @mgmt_tx: Transmit a management frame + * @mgmt_tx: Transmit a management frame. + * @mgmt_tx_cancel_wait: Cancel the wait time from transmitting a management + * frame on another channel * * @testmode_cmd: run a test mode command * @@ -1291,10 +1293,13 @@ struct cfg80211_ops { u64 cookie); int (*mgmt_tx)(struct wiphy *wiphy, struct net_device *dev, - struct ieee80211_channel *chan, + struct ieee80211_channel *chan, bool offchan, enum nl80211_channel_type channel_type, - bool channel_type_valid, + bool channel_type_valid, unsigned int wait, const u8 *buf, size_t len, u64 *cookie); + int (*mgmt_tx_cancel_wait)(struct wiphy *wiphy, + struct net_device *dev, + u64 cookie); int (*set_power_mgmt)(struct wiphy *wiphy, struct net_device *dev, bool enabled, int timeout); -- cgit v1.1 From 24278d148316d2180be6df40e06db013d8b232b8 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 27 Sep 2010 17:25:23 -0700 Subject: rcu: priority boosting for TINY_PREEMPT_RCU Add priority boosting, but only for TINY_PREEMPT_RCU. This is enabled by the default-off RCU_BOOST kernel parameter. The priority to which to boost preempted RCU readers is controlled by the RCU_BOOST_PRIO kernel parameter (defaulting to real-time priority 1) and the time to wait before boosting the readers blocking a given grace period is controlled by the RCU_BOOST_DELAY kernel parameter (defaulting to 500 milliseconds). Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- include/linux/init_task.h | 9 ++++++++- include/linux/sched.h | 11 +++++++++-- 2 files changed, 17 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 2fea6c8..69f91aa 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -81,6 +81,12 @@ extern struct group_info init_groups; */ # define CAP_INIT_BSET CAP_FULL_SET +#ifdef CONFIG_RCU_BOOST +#define INIT_TASK_RCU_BOOST() \ + .rcu_boost_mutex = NULL, +#else +#define INIT_TASK_RCU_BOOST() +#endif #ifdef CONFIG_TREE_PREEMPT_RCU #define INIT_TASK_RCU_TREE_PREEMPT() \ .rcu_blocked_node = NULL, @@ -92,7 +98,8 @@ extern struct group_info init_groups; .rcu_read_lock_nesting = 0, \ .rcu_read_unlock_special = 0, \ .rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry), \ - INIT_TASK_RCU_TREE_PREEMPT() + INIT_TASK_RCU_TREE_PREEMPT() \ + INIT_TASK_RCU_BOOST() #else #define INIT_TASK_RCU_PREEMPT(tsk) #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index e18473f..ed1a9bc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1210,6 +1210,9 @@ struct task_struct { #ifdef CONFIG_TREE_PREEMPT_RCU struct rcu_node *rcu_blocked_node; #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ +#ifdef CONFIG_RCU_BOOST + struct rt_mutex *rcu_boost_mutex; +#endif /* #ifdef CONFIG_RCU_BOOST */ #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) struct sched_info sched_info; @@ -1745,7 +1748,8 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * #ifdef CONFIG_PREEMPT_RCU #define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */ -#define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */ +#define RCU_READ_UNLOCK_BOOSTED (1 << 1) /* boosted while in RCU read-side. */ +#define RCU_READ_UNLOCK_NEED_QS (1 << 2) /* RCU core needs CPU response. */ static inline void rcu_copy_process(struct task_struct *p) { @@ -1753,7 +1757,10 @@ static inline void rcu_copy_process(struct task_struct *p) p->rcu_read_unlock_special = 0; #ifdef CONFIG_TREE_PREEMPT_RCU p->rcu_blocked_node = NULL; -#endif +#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ +#ifdef CONFIG_RCU_BOOST + p->rcu_boost_mutex = NULL; +#endif /* #ifdef CONFIG_RCU_BOOST */ INIT_LIST_HEAD(&p->rcu_node_entry); } -- cgit v1.1 From 7b27d5475f86186914e54e4a6bb994e9a985337b Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 21 Oct 2010 11:29:05 +0800 Subject: rcu,cleanup: move synchronize_sched_expedited() out of sched.c The first version of synchronize_sched_expedited() used the migration code in the scheduler, and was therefore implemented in kernel/sched.c. However, the more recent version of this code no longer uses the migration code, so this commit moves it to the main RCU source files. Signed-off-by: Lai Jiangshan Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 1 - include/linux/rcutiny.h | 5 +++++ include/linux/rcutree.h | 1 + 3 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 7142ee3..49e8e16 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -66,7 +66,6 @@ extern void call_rcu_sched(struct rcu_head *head, extern void synchronize_sched(void); extern void rcu_barrier_bh(void); extern void rcu_barrier_sched(void); -extern void synchronize_sched_expedited(void); extern int sched_expedited_torture_stats(char *page); static inline void __rcu_read_lock_bh(void) diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index ea025a6..30ebd7c 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -60,6 +60,11 @@ static inline void synchronize_rcu_bh_expedited(void) synchronize_sched(); } +static inline void synchronize_sched_expedited(void) +{ + synchronize_sched(); +} + #ifdef CONFIG_TINY_RCU static inline void rcu_preempt_note_context_switch(void) diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index c0e9683..3a93348 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -48,6 +48,7 @@ static inline void exit_rcu(void) #endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */ extern void synchronize_rcu_bh(void); +extern void synchronize_sched_expedited(void); extern void synchronize_rcu_expedited(void); static inline void synchronize_rcu_bh_expedited(void) -- cgit v1.1 From 9833c39400c3e6ee19daeded6910df648741611e Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Fri, 19 Nov 2010 09:29:24 +0100 Subject: ARM: 6485/5: proc/vmcore - allow archs to override vmcore_elf_check_arch() Allow architectures to redefine this macro if needed. This is useful for example in architectures where 64-bit ELF vmcores are not supported. Specifying zero vmcore_elf64_check_arch() allows compiler to optimize away unnecessary parts of parse_crash_elf64_headers(). We also rename the macro to vmcore_elf64_check_arch() to reflect that it is used for 64-bit vmcores only. Signed-off-by: Mika Westerberg Signed-off-by: Russell King --- include/linux/crash_dump.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 0026f26..088cd4a 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -20,7 +20,14 @@ extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, #define vmcore_elf_check_arch_cross(x) 0 #endif -#define vmcore_elf_check_arch(x) (elf_check_arch(x) || vmcore_elf_check_arch_cross(x)) +/* + * Architecture code can redefine this if there are any special checks + * needed for 64-bit ELF vmcores. In case of 32-bit only architecture, + * this can be set to zero. + */ +#ifndef vmcore_elf64_check_arch +#define vmcore_elf64_check_arch(x) (elf_check_arch(x) || vmcore_elf_check_arch_cross(x)) +#endif /* * is_kdump_kernel() checks whether this kernel is booting after a panic of -- cgit v1.1 From 5091faa449ee0b7d73bc296a93bca9540fc51d0a Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Tue, 30 Nov 2010 14:18:03 +0100 Subject: sched: Add 'autogroup' scheduling feature: automated per session task groups A recurring complaint from CFS users is that parallel kbuild has a negative impact on desktop interactivity. This patch implements an idea from Linus, to automatically create task groups. Currently, only per session autogroups are implemented, but the patch leaves the way open for enhancement. Implementation: each task's signal struct contains an inherited pointer to a refcounted autogroup struct containing a task group pointer, the default for all tasks pointing to the init_task_group. When a task calls setsid(), a new task group is created, the process is moved into the new task group, and a reference to the preveious task group is dropped. Child processes inherit this task group thereafter, and increase it's refcount. When the last thread of a process exits, the process's reference is dropped, such that when the last process referencing an autogroup exits, the autogroup is destroyed. At runqueue selection time, IFF a task has no cgroup assignment, its current autogroup is used. Autogroup bandwidth is controllable via setting it's nice level through the proc filesystem: cat /proc//autogroup Displays the task's group and the group's nice level. echo > /proc//autogroup Sets the task group's shares to the weight of nice task. Setting nice level is rate limited for !admin users due to the abuse risk of task group locking. The feature is enabled from boot by default if CONFIG_SCHED_AUTOGROUP=y is selected, but can be disabled via the boot option noautogroup, and can also be turned on/off on the fly via: echo [01] > /proc/sys/kernel/sched_autogroup_enabled ... which will automatically move tasks to/from the root task group. Signed-off-by: Mike Galbraith Acked-by: Linus Torvalds Acked-by: Peter Zijlstra Cc: Markus Trippelsdorf Cc: Mathieu Desnoyers Cc: Paul Turner Cc: Oleg Nesterov [ Removed the task_group_path() debug code, and fixed !EVENTFD build failure. ] Signed-off-by: Ingo Molnar LKML-Reference: <1290281700.28711.9.camel@maggy.simson.net> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index a5b92c7..9c2d46d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -509,6 +509,8 @@ struct thread_group_cputimer { spinlock_t lock; }; +struct autogroup; + /* * NOTE! "signal_struct" does not have it's own * locking, because a shared signal_struct always @@ -576,6 +578,9 @@ struct signal_struct { struct tty_struct *tty; /* NULL if no tty */ +#ifdef CONFIG_SCHED_AUTOGROUP + struct autogroup *autogroup; +#endif /* * Cumulative resource counters for dead threads in the group, * and for reaped dead child processes forked by this group. @@ -1927,6 +1932,24 @@ int sched_rt_handler(struct ctl_table *table, int write, extern unsigned int sysctl_sched_compat_yield; +#ifdef CONFIG_SCHED_AUTOGROUP +extern unsigned int sysctl_sched_autogroup_enabled; + +extern void sched_autogroup_create_attach(struct task_struct *p); +extern void sched_autogroup_detach(struct task_struct *p); +extern void sched_autogroup_fork(struct signal_struct *sig); +extern void sched_autogroup_exit(struct signal_struct *sig); +#ifdef CONFIG_PROC_FS +extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m); +extern int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice); +#endif +#else +static inline void sched_autogroup_create_attach(struct task_struct *p) { } +static inline void sched_autogroup_detach(struct task_struct *p) { } +static inline void sched_autogroup_fork(struct signal_struct *sig) { } +static inline void sched_autogroup_exit(struct signal_struct *sig) { } +#endif + #ifdef CONFIG_RT_MUTEXES extern int rt_mutex_getprio(struct task_struct *p); extern void rt_mutex_setprio(struct task_struct *p, int prio); -- cgit v1.1 From 20ed3166c84d145589a89d8cde12aa32cf2d17f4 Mon Sep 17 00:00:00 2001 From: Johannes Stezenbach Date: Tue, 30 Nov 2010 16:49:23 +0100 Subject: mac80211/rt2x00: add ieee80211_tx_status_ni() All rt2x00 drivers except rt2800pci call ieee80211_tx_status() from a workqueue, which causes "NOHZ: local_softirq_pending 08" messages. To fix it, add ieee80211_tx_status_ni() similar to ieee80211_rx_ni() which can be called from process context, and call it from rt2x00lib_txdone(). For the rt2800pci special case a driver flag is introduced. Signed-off-by: Johannes Stezenbach Signed-off-by: John W. Linville --- include/net/mac80211.h | 28 ++++++++++++++++++++++++---- 1 file changed, 24 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index eaa4aff..e411cf8 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2055,8 +2055,8 @@ static inline void ieee80211_rx_ni(struct ieee80211_hw *hw, * * This function may not be called in IRQ context. Calls to this function * for a single hardware must be synchronized against each other. Calls - * to this function and ieee80211_tx_status_irqsafe() may not be mixed - * for a single hardware. + * to this function, ieee80211_tx_status_ni() and ieee80211_tx_status_irqsafe() + * may not be mixed for a single hardware. * * @hw: the hardware the frame was transmitted by * @skb: the frame that was transmitted, owned by mac80211 after this call @@ -2065,13 +2065,33 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb); /** + * ieee80211_tx_status_ni - transmit status callback (in process context) + * + * Like ieee80211_tx_status() but can be called in process context. + * + * Calls to this function, ieee80211_tx_status() and + * ieee80211_tx_status_irqsafe() may not be mixed + * for a single hardware. + * + * @hw: the hardware the frame was transmitted by + * @skb: the frame that was transmitted, owned by mac80211 after this call + */ +static inline void ieee80211_tx_status_ni(struct ieee80211_hw *hw, + struct sk_buff *skb) +{ + local_bh_disable(); + ieee80211_tx_status(hw, skb); + local_bh_enable(); +} + +/** * ieee80211_tx_status_irqsafe - IRQ-safe transmit status callback * * Like ieee80211_tx_status() but can be called in IRQ context * (internally defers to a tasklet.) * - * Calls to this function and ieee80211_tx_status() may not be mixed for a - * single hardware. + * Calls to this function, ieee80211_tx_status() and + * ieee80211_tx_status_ni() may not be mixed for a single hardware. * * @hw: the hardware the frame was transmitted by * @skb: the frame that was transmitted, owned by mac80211 after this call -- cgit v1.1 From 582a72da9a41be9227dc931d728ae2906880a589 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 30 Nov 2010 11:53:55 -0800 Subject: inetpeer: Introduce inet_peer_address_t. Currently only the v4 aspect is used, but this will change. Signed-off-by: David S. Miller --- include/net/inetpeer.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index fe239bf..d7e6079 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -13,10 +13,18 @@ #include #include +typedef struct { + union { + __be32 a4; + __be32 a6[4]; + }; + __u16 family; +} inet_peer_address_t; + struct inet_peer { /* group together avl_left,avl_right,v4daddr to speedup lookups */ struct inet_peer __rcu *avl_left, *avl_right; - __be32 v4daddr; /* peer's address */ + inet_peer_address_t daddr; __u32 avl_height; struct list_head unused; __u32 dtime; /* the time of last use of not -- cgit v1.1 From b534ecf1cd26f094497da6ae28a6ab64cdbe1617 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 30 Nov 2010 11:54:19 -0800 Subject: inetpeer: Make inet_getpeer() take an inet_peer_adress_t pointer. And make an inet_getpeer_v4() helper, update callers. Signed-off-by: David S. Miller --- include/net/inetpeer.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index d7e6079..834f045 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -50,7 +50,16 @@ struct inet_peer { void inet_initpeers(void) __init; /* can be called with or without local BH being disabled */ -struct inet_peer *inet_getpeer(__be32 daddr, int create); +struct inet_peer *inet_getpeer(inet_peer_address_t *daddr, int create); + +static inline struct inet_peer *inet_getpeer_v4(__be32 v4daddr, int create) +{ + inet_peer_address_t daddr; + + daddr.a4 = v4daddr; + daddr.family = AF_INET; + return inet_getpeer(&daddr, create); +} /* can be called from BH context or outside */ extern void inet_putpeer(struct inet_peer *p); -- cgit v1.1 From 672f007d65f50468a4a1e55825fe58e5b035324d Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 30 Nov 2010 12:20:00 -0800 Subject: inetpeer: Add inet_getpeer_v6() Now that all of the infrastructure is in place, we can add the ipv6 shorthand for peer creation. Signed-off-by: David S. Miller --- include/net/inetpeer.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 834f045..fb8aeb1 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -11,6 +11,7 @@ #include #include #include +#include #include typedef struct { @@ -61,6 +62,15 @@ static inline struct inet_peer *inet_getpeer_v4(__be32 v4daddr, int create) return inet_getpeer(&daddr, create); } +static inline struct inet_peer *inet_getpeer_v6(struct in6_addr *v6daddr, int create) +{ + inet_peer_address_t daddr; + + ipv6_addr_copy((struct in6_addr *)daddr.a6, v6daddr); + daddr.family = AF_INET6; + return inet_getpeer(&daddr, create); +} + /* can be called from BH context or outside */ extern void inet_putpeer(struct inet_peer *p); -- cgit v1.1 From b3419363808f2481b24a817f491878e1795db4c7 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 30 Nov 2010 12:27:11 -0800 Subject: ipv6: Add infrastructure to bind inet_peer objects to routes. They are only allowed on cached ipv6 routes. Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 2 ++ include/net/ip6_route.h | 3 +++ 2 files changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 062a823..708ff7c 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -21,6 +21,7 @@ #include #include #include +#include #ifdef CONFIG_IPV6_MULTIPLE_TABLES #define FIB6_TABLE_HASHSZ 256 @@ -109,6 +110,7 @@ struct rt6_info { u32 rt6i_metric; struct inet6_dev *rt6i_idev; + struct inet_peer *rt6i_peer; #ifdef CONFIG_XFRM u32 rt6i_flow_cache_genid; diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 278312c..23fed28 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -56,6 +56,9 @@ static inline unsigned int rt6_flags2srcprefs(int flags) return (flags >> 3) & 7; } +extern void rt6_bind_peer(struct rt6_info *rt, + int create); + extern void ip6_route_input(struct sk_buff *skb); extern struct dst_entry * ip6_route_output(struct net *net, -- cgit v1.1 From 3f419d2d487821093ee46e898b5f8747f9edc9cd Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 29 Nov 2010 13:37:14 -0800 Subject: inet: Turn ->remember_stamp into ->get_peer in connection AF ops. Then we can make a completely generic tcp_remember_stamp() that uses ->get_peer() as a helper, minimizing the AF specific code and minimizing the eventual code duplication when we implement the ipv6 side of TW recycling. Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 2 +- include/net/tcp.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index e4f494b..6c93a56 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -43,7 +43,7 @@ struct inet_connection_sock_af_ops { struct sock *(*syn_recv_sock)(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst); - int (*remember_stamp)(struct sock *sk); + struct inet_peer *(*get_peer)(struct sock *sk, bool *release_it); u16 net_header_len; u16 sockaddr_len; int (*setsockopt)(struct sock *sk, int level, int optname, diff --git a/include/net/tcp.h b/include/net/tcp.h index e36c874..3e23964 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -312,7 +312,7 @@ extern void tcp_shutdown (struct sock *sk, int how); extern int tcp_v4_rcv(struct sk_buff *skb); -extern int tcp_v4_remember_stamp(struct sock *sk); +extern struct inet_peer *tcp_v4_get_peer(struct sock *sk, bool *release_it); extern int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw); extern int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t size); -- cgit v1.1 From c320c7b7d380e630f595de1236d9d085b035d5b4 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 20 Oct 2010 12:50:11 -0200 Subject: perf events: Precalculate the header space for PERF_SAMPLE_ fields MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit PERF_SAMPLE_{CALLCHAIN,RAW} have variable lenghts per sample, but the others can be precalculated, reducing a bit the per sample cost. Acked-by: Peter Zijlstra Cc: Frédéric Weisbecker Cc: Ian Munsie Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Stephane Eranian LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index cbf04cc..adf6d99 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -758,6 +758,8 @@ struct perf_event { u64 shadow_ctx_time; struct perf_event_attr attr; + u16 header_size; + u16 read_size; struct hw_perf_event hw; struct perf_event_context *ctx; -- cgit v1.1 From 498cb95175c29ed96bf32f30df2d11ec1c7f3879 Mon Sep 17 00:00:00 2001 From: Andrei Emeltchenko Date: Tue, 30 Nov 2010 14:11:49 -0800 Subject: OMAP: Serial: Define OMAP uart MDR1 reg and remove magic numbers Define MDR1 register serial definitions used in serial and bluetooth drivers. Change magic number to ones defined in serial_reg for omap1/2 serial driver. Remove redefined MDR1 register definitions in omap-serial driver. Signed-off-by: Andrei Emeltchenko Acked-by: G, Manjunath Kondaiah Acked-by: Govindraj.R Acked-by: Greg Kroah-Hartman Signed-off-by: Tony Lindgren --- include/linux/serial_reg.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/serial_reg.h b/include/linux/serial_reg.h index c7a0ce1..6f38234 100644 --- a/include/linux/serial_reg.h +++ b/include/linux/serial_reg.h @@ -341,5 +341,17 @@ #define UART_OMAP_SYSS 0x16 /* System status register */ #define UART_OMAP_WER 0x17 /* Wake-up enable register */ +/* + * These are the definitions for the MDR1 register + */ +#define UART_OMAP_MDR1_16X_MODE 0x00 /* UART 16x mode */ +#define UART_OMAP_MDR1_SIR_MODE 0x01 /* SIR mode */ +#define UART_OMAP_MDR1_16X_ABAUD_MODE 0x02 /* UART 16x auto-baud */ +#define UART_OMAP_MDR1_13X_MODE 0x03 /* UART 13x mode */ +#define UART_OMAP_MDR1_MIR_MODE 0x04 /* MIR mode */ +#define UART_OMAP_MDR1_FIR_MODE 0x05 /* FIR mode */ +#define UART_OMAP_MDR1_CIR_MODE 0x06 /* CIR mode */ +#define UART_OMAP_MDR1_DISABLE 0x07 /* Disable (default state) */ + #endif /* _LINUX_SERIAL_REG_H */ -- cgit v1.1 From 662b083a87a3489f3f19c6e0651c1b99b0de5df0 Mon Sep 17 00:00:00 2001 From: Andrei Emeltchenko Date: Tue, 30 Nov 2010 14:11:49 -0800 Subject: omap: Serial: Define register access modes in LCR MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Access to some registers depends on register access mode Three different modes are available for OMAP (at least) • Operational mode LCR_REG[7] = 0x0 • Configuration mode A LCR_REG[7] = 0x1 and LCR_REG[7:0]! = 0xBF • Configuration mode B LCR_REG[7] = 0x1 and LCR_REG[7:0] = 0xBF Define access modes and remove redefinitions and magic numbers in serial drivers (and later in bluetooth driver). Signed-off-by: Andrei Emeltchenko Acked-by: Govindraj.R Acked-by: Greg Kroah-Hartman Signed-off-by: Tony Lindgren --- include/linux/serial_reg.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/serial_reg.h b/include/linux/serial_reg.h index 6f38234..3ecb71a 100644 --- a/include/linux/serial_reg.h +++ b/include/linux/serial_reg.h @@ -99,6 +99,13 @@ #define UART_LCR_WLEN7 0x02 /* Wordlength: 7 bits */ #define UART_LCR_WLEN8 0x03 /* Wordlength: 8 bits */ +/* + * Access to some registers depends on register access / configuration + * mode. + */ +#define UART_LCR_CONF_MODE_A UART_LCR_DLAB /* Configutation mode A */ +#define UART_LCR_CONF_MODE_B 0xBF /* Configutation mode B */ + #define UART_MCR 4 /* Out: Modem Control Register */ #define UART_MCR_CLKSEL 0x80 /* Divide clock by 4 (TI16C752, EFR[4]=1) */ #define UART_MCR_TCRTLR 0x40 /* Access TCR/TLR (TI16C752, EFR[4]=1) */ -- cgit v1.1 From ad9c2b048b605fbc8d50526e330b88abdd631ab2 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Tue, 30 Nov 2010 11:06:47 +0900 Subject: security: Fix comment of security_key_permission Comment for return value of security_key_permission() has been wrong since it was added in 2.6.15. Signed-off-by: Tetsuo Handa Signed-off-by: James Morris --- include/linux/security.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/security.h b/include/linux/security.h index fd4d55f..e7d89b0 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1058,8 +1058,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * @cred points to the credentials to provide the context against which to * evaluate the security data on the key. * @perm describes the combination of permissions required of this key. - * Return 1 if permission granted, 0 if permission denied and -ve it the - * normal permissions model should be effected. + * Return 0 if permission is granted, -ve error otherwise. * @key_getsecurity: * Get a textual representation of the security context attached to a key * for the purposes of honouring KEYCTL_GETSECURITY. This function -- cgit v1.1 From c41ab6a1b9028de33e74101cb0aae13098a56fdb Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Mon, 29 Nov 2010 15:47:09 -0500 Subject: flex_array: fix flex_array_put_ptr macro to be valid C MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Using flex_array_put_ptr() results in a compile error "error: lvalue required as unary ‘&’ operand" fix the casting order to fix this. Signed-off-by: Eric Paris --- include/linux/flex_array.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/flex_array.h b/include/linux/flex_array.h index 631b77f..70e4efa 100644 --- a/include/linux/flex_array.h +++ b/include/linux/flex_array.h @@ -71,7 +71,7 @@ void *flex_array_get(struct flex_array *fa, unsigned int element_nr); int flex_array_shrink(struct flex_array *fa); #define flex_array_put_ptr(fa, nr, src, gfp) \ - flex_array_put(fa, nr, &(void *)(src), gfp) + flex_array_put(fa, nr, (void *)&(src), gfp) void *flex_array_get_ptr(struct flex_array *fa, unsigned int element_nr); -- cgit v1.1 From 5b275ce27077d6463ca28c9671dce7c2c1f622e2 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Thu, 11 Nov 2010 15:27:29 +0000 Subject: thermal: make ops constant And while touching that function definition do something about the disaster of formatting there. Signed-off-by: Alan Cox Acked-by: Zhang Rui Signed-off-by: Len Brown --- include/linux/thermal.h | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 1de8b9e..0662690 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -77,7 +77,7 @@ struct thermal_cooling_device { char type[THERMAL_NAME_LENGTH]; struct device device; void *devdata; - struct thermal_cooling_device_ops *ops; + const struct thermal_cooling_device_ops *ops; struct list_head node; }; @@ -114,7 +114,7 @@ struct thermal_zone_device { int last_temperature; bool passive; unsigned int forced_passive; - struct thermal_zone_device_ops *ops; + const struct thermal_zone_device_ops *ops; struct list_head cooling_devices; struct idr idr; struct mutex lock; /* protect cooling devices list */ @@ -129,11 +129,8 @@ struct thermal_zone_device { }; struct thermal_zone_device *thermal_zone_device_register(char *, int, void *, - struct - thermal_zone_device_ops - *, int tc1, int tc2, - int passive_freq, - int polling_freq); + const struct thermal_zone_device_ops *, int tc1, int tc2, + int passive_freq, int polling_freq); void thermal_zone_device_unregister(struct thermal_zone_device *); int thermal_zone_bind_cooling_device(struct thermal_zone_device *, int, @@ -142,9 +139,7 @@ int thermal_zone_unbind_cooling_device(struct thermal_zone_device *, int, struct thermal_cooling_device *); void thermal_zone_device_update(struct thermal_zone_device *); struct thermal_cooling_device *thermal_cooling_device_register(char *, void *, - struct - thermal_cooling_device_ops - *); + const struct thermal_cooling_device_ops *); void thermal_cooling_device_unregister(struct thermal_cooling_device *); #endif /* __THERMAL_H__ */ -- cgit v1.1 From 7fc56f0d9908fe140a01387d59954e3d0a2e7744 Mon Sep 17 00:00:00 2001 From: Luo Andy Date: Tue, 23 Nov 2010 10:41:21 +0800 Subject: usb: gadget: langwell_udc: add usb test mode support This patch adds test mode support for Langwell gadget driver. Signed-off-by: Henry Yuan Signed-off-by: Andy Luo Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/ch9.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/usb/ch9.h b/include/linux/usb/ch9.h index f917bbb..ab46194 100644 --- a/include/linux/usb/ch9.h +++ b/include/linux/usb/ch9.h @@ -124,6 +124,16 @@ #define USB_DEVICE_DEBUG_MODE 6 /* (special devices only) */ /* + * Test Mode Selectors + * See USB 2.0 spec Table 9-7 + */ +#define TEST_J 1 +#define TEST_K 2 +#define TEST_SE0_NAK 3 +#define TEST_PACKET 4 +#define TEST_FORCE_EN 5 + +/* * New Feature Selectors as added by USB 3.0 * See USB 3.0 spec Table 9-6 */ -- cgit v1.1 From b029ffafe89cf4b97cf39e0225a5205cbbf9e02f Mon Sep 17 00:00:00 2001 From: Hemanth V Date: Tue, 30 Nov 2010 23:03:54 -0800 Subject: Input: add CMA3000 accelerometer driver Add support for CMA3000 Tri-axis accelerometer, which supports Motion detect, Measurement and Free fall modes. CMA3000 supports both I2C/SPI bus for communication, currently the driver supports I2C based communication. Signed-off-by: Hemanth V Reviewed-by: Jonathan Cameron Reviewed-by: Sergio Aguirre Reviewed-by: Shubhrajyoti Signed-off-by: Dmitry Torokhov --- include/linux/input/cma3000.h | 59 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 59 insertions(+) create mode 100644 include/linux/input/cma3000.h (limited to 'include') diff --git a/include/linux/input/cma3000.h b/include/linux/input/cma3000.h new file mode 100644 index 0000000..cbbaac2 --- /dev/null +++ b/include/linux/input/cma3000.h @@ -0,0 +1,59 @@ +/* + * VTI CMA3000_Dxx Accelerometer driver + * + * Copyright (C) 2010 Texas Instruments + * Author: Hemanth V + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see . + */ + +#ifndef _LINUX_CMA3000_H +#define _LINUX_CMA3000_H + +#define CMAMODE_DEFAULT 0 +#define CMAMODE_MEAS100 1 +#define CMAMODE_MEAS400 2 +#define CMAMODE_MEAS40 3 +#define CMAMODE_MOTDET 4 +#define CMAMODE_FF100 5 +#define CMAMODE_FF400 6 +#define CMAMODE_POFF 7 + +#define CMARANGE_2G 2000 +#define CMARANGE_8G 8000 + +/** + * struct cma3000_i2c_platform_data - CMA3000 Platform data + * @fuzz_x: Noise on X Axis + * @fuzz_y: Noise on Y Axis + * @fuzz_z: Noise on Z Axis + * @g_range: G range in milli g i.e 2000 or 8000 + * @mode: Operating mode + * @mdthr: Motion detect threshold value + * @mdfftmr: Motion detect and free fall time value + * @ffthr: Free fall threshold value + */ + +struct cma3000_platform_data { + int fuzz_x; + int fuzz_y; + int fuzz_z; + int g_range; + uint8_t mode; + uint8_t mdthr; + uint8_t mdfftmr; + uint8_t ffthr; + unsigned long irqflags; +}; + +#endif -- cgit v1.1 From 0417596f66dd6621f4fd46563c7c56a95311dbe8 Mon Sep 17 00:00:00 2001 From: Bastien Nocera Date: Mon, 29 Nov 2010 23:33:05 -0800 Subject: Input: add keycodes for touchpad on/off keys Some laptops will have a "touchpad toggle" soft button, which expects user-space to turn off the touchpad themselves, some other devices will do this in hardware, but send key events telling us that the touchpad has been turned off/on. KEY_TOUCHPAD_ON/KEY_TOUCHPAD_OFF will be used by user-space to show a popup with the status of the touchpad. Signed-off-by: Bastien Nocera Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/input.h b/include/linux/input.h index 6ef4446..a50046f 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -624,6 +624,10 @@ struct input_keymap_entry { #define KEY_CAMERA_FOCUS 0x210 #define KEY_WPS_BUTTON 0x211 /* WiFi Protected Setup key */ +#define KEY_TOUCHPAD_TOGGLE 0x212 /* Request switch touchpad on or off */ +#define KEY_TOUCHPAD_ON 0x213 +#define KEY_TOUCHPAD_OFF 0x214 + #define BTN_TRIGGER_HAPPY 0x2c0 #define BTN_TRIGGER_HAPPY1 0x2c0 #define BTN_TRIGGER_HAPPY2 0x2c1 -- cgit v1.1 From 86b17f76f462db460d6d916e105a4c44cb353e36 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Mon, 29 Nov 2010 23:33:04 -0800 Subject: Input: document struct input_absinfo Add documentation for struct input_absinfo that is used in EVIOCGABS and EVIOCSABS ioctl and specify units of measure used for reporting resolution for an axis. Acked-by: Henrik Rydberg Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/input.h b/include/linux/input.h index a50046f..a8af21d 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -47,6 +47,25 @@ struct input_id { __u16 version; }; +/** + * struct input_absinfo - used by EVIOCGABS/EVIOCSABS ioctls + * @value: latest reported value for the axis. + * @minimum: specifies minimum value for the axis. + * @maximum: specifies maximum value for the axis. + * @fuzz: specifies fuzz value that is used to filter noise from + * the event stream. + * @flat: values that are within this value will be discarded by + * joydev interface and reported as 0 instead. + * @resolution: specifies resolution for the values reported for + * the axis. + * + * Note that input core does not clamp reported values to the + * [minimum, maximum] limits, such task is left to userspace. + * + * Resolution for main axes (ABS_X, ABS_Y, ABS_Z) is reported in + * units per millimeter (units/mm), resolution for rotational axes + * (ABS_RX, ABS_RY, ABS_RZ) is reported in units per radian. + */ struct input_absinfo { __s32 value; __s32 minimum; @@ -1134,7 +1153,7 @@ struct input_mt_slot { * of tracked contacts * @mtsize: number of MT slots the device uses * @slot: MT slot currently being transmitted - * @absinfo: array of &struct absinfo elements holding information + * @absinfo: array of &struct input_absinfo elements holding information * about absolute axes (current value, min, max, flat, fuzz, * resolution) * @key: reflects current state of device's keys/buttons -- cgit v1.1 From 28b26e15533e60970a014582d812d471ad63bcd0 Mon Sep 17 00:00:00 2001 From: Florian Faber Date: Wed, 1 Dec 2010 12:14:47 +0100 Subject: ALSA: hdsp - Add support for RPM io box Add support for the RME HDSP RPM IO box. Changes have been made in the identification of the IO box and the neccessary controls have been added. Signed-off-by: Florian Faber Signed-off-by: Takashi Iwai --- include/sound/hdsp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/sound/hdsp.h b/include/sound/hdsp.h index d98a78d..0909a38 100644 --- a/include/sound/hdsp.h +++ b/include/sound/hdsp.h @@ -28,6 +28,7 @@ enum HDSP_IO_Type { Multiface, H9652, H9632, + RPM, Undefined, }; -- cgit v1.1 From 8348c259dd6a6019a8fa01b0a3443409480f7b9d Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 22 Nov 2010 17:12:15 -0800 Subject: arm/pxa2xx: reorgazine SSP and SPI header files The PXA-SPI driver relies on some files / defines which are arm specific and are within the ARM tree. The CE4100 SoC which is x86 has also the SPI core. This patch moves the ssp and spi files from arm/mach-pxa and plat-pxa to include/linux where the CE4100 can access them. This move got verified by building the following defconfigs: cm_x2xx_defconfig corgi_defconfig em_x270_defconfig ezx_defconfig imote2_defconfig pxa3xx_defconfig spitz_defconfig zeus_defconfig raumfeld_defconfig magician_defconfig Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Dirk Brandewie --- include/linux/pxa2xx_ssp.h | 187 +++++++++++++++++++++++++++++++++++++++++ include/linux/spi/pxa2xx_spi.h | 49 +++++++++++ 2 files changed, 236 insertions(+) create mode 100644 include/linux/pxa2xx_ssp.h create mode 100644 include/linux/spi/pxa2xx_spi.h (limited to 'include') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h new file mode 100644 index 0000000..84465d4 --- /dev/null +++ b/include/linux/pxa2xx_ssp.h @@ -0,0 +1,187 @@ +/* + * pxa2xx_ssp.h + * + * Copyright (C) 2003 Russell King, All Rights Reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This driver supports the following PXA CPU/SSP ports:- + * + * PXA250 SSP + * PXA255 SSP, NSSP + * PXA26x SSP, NSSP, ASSP + * PXA27x SSP1, SSP2, SSP3 + * PXA3xx SSP1, SSP2, SSP3, SSP4 + */ + +#ifndef __LINUX_SSP_H +#define __LINUX_SSP_H + +#include +#include + +/* + * SSP Serial Port Registers + * PXA250, PXA255, PXA26x and PXA27x SSP controllers are all slightly different. + * PXA255, PXA26x and PXA27x have extra ports, registers and bits. + */ + +#define SSCR0 (0x00) /* SSP Control Register 0 */ +#define SSCR1 (0x04) /* SSP Control Register 1 */ +#define SSSR (0x08) /* SSP Status Register */ +#define SSITR (0x0C) /* SSP Interrupt Test Register */ +#define SSDR (0x10) /* SSP Data Write/Data Read Register */ + +#define SSTO (0x28) /* SSP Time Out Register */ +#define SSPSP (0x2C) /* SSP Programmable Serial Protocol */ +#define SSTSA (0x30) /* SSP Tx Timeslot Active */ +#define SSRSA (0x34) /* SSP Rx Timeslot Active */ +#define SSTSS (0x38) /* SSP Timeslot Status */ +#define SSACD (0x3C) /* SSP Audio Clock Divider */ +#define SSACDD (0x40) /* SSP Audio Clock Dither Divider */ + +/* Common PXA2xx bits first */ +#define SSCR0_DSS (0x0000000f) /* Data Size Select (mask) */ +#define SSCR0_DataSize(x) ((x) - 1) /* Data Size Select [4..16] */ +#define SSCR0_FRF (0x00000030) /* FRame Format (mask) */ +#define SSCR0_Motorola (0x0 << 4) /* Motorola's Serial Peripheral Interface (SPI) */ +#define SSCR0_TI (0x1 << 4) /* Texas Instruments' Synchronous Serial Protocol (SSP) */ +#define SSCR0_National (0x2 << 4) /* National Microwire */ +#define SSCR0_ECS (1 << 6) /* External clock select */ +#define SSCR0_SSE (1 << 7) /* Synchronous Serial Port Enable */ +#define SSCR0_SCR(x) ((x) << 8) /* Serial Clock Rate (mask) */ + +/* PXA27x, PXA3xx */ +#define SSCR0_EDSS (1 << 20) /* Extended data size select */ +#define SSCR0_NCS (1 << 21) /* Network clock select */ +#define SSCR0_RIM (1 << 22) /* Receive FIFO overrrun interrupt mask */ +#define SSCR0_TUM (1 << 23) /* Transmit FIFO underrun interrupt mask */ +#define SSCR0_FRDC (0x07000000) /* Frame rate divider control (mask) */ +#define SSCR0_SlotsPerFrm(x) (((x) - 1) << 24) /* Time slots per frame [1..8] */ +#define SSCR0_FPCKE (1 << 29) /* FIFO packing enable */ +#define SSCR0_ACS (1 << 30) /* Audio clock select */ +#define SSCR0_MOD (1 << 31) /* Mode (normal or network) */ + + +#define SSCR1_RIE (1 << 0) /* Receive FIFO Interrupt Enable */ +#define SSCR1_TIE (1 << 1) /* Transmit FIFO Interrupt Enable */ +#define SSCR1_LBM (1 << 2) /* Loop-Back Mode */ +#define SSCR1_SPO (1 << 3) /* Motorola SPI SSPSCLK polarity setting */ +#define SSCR1_SPH (1 << 4) /* Motorola SPI SSPSCLK phase setting */ +#define SSCR1_MWDS (1 << 5) /* Microwire Transmit Data Size */ +#define SSCR1_TFT (0x000003c0) /* Transmit FIFO Threshold (mask) */ +#define SSCR1_TxTresh(x) (((x) - 1) << 6) /* level [1..16] */ +#define SSCR1_RFT (0x00003c00) /* Receive FIFO Threshold (mask) */ +#define SSCR1_RxTresh(x) (((x) - 1) << 10) /* level [1..16] */ + +#define SSSR_TNF (1 << 2) /* Transmit FIFO Not Full */ +#define SSSR_RNE (1 << 3) /* Receive FIFO Not Empty */ +#define SSSR_BSY (1 << 4) /* SSP Busy */ +#define SSSR_TFS (1 << 5) /* Transmit FIFO Service Request */ +#define SSSR_RFS (1 << 6) /* Receive FIFO Service Request */ +#define SSSR_ROR (1 << 7) /* Receive FIFO Overrun */ +#define SSSR_TFL_MASK (0xf << 8) /* Transmit FIFO Level mask */ +#define SSSR_RFL_MASK (0xf << 12) /* Receive FIFO Level mask */ + +/* extra bits in PXA255, PXA26x and PXA27x SSP ports */ +#define SSCR0_TISSP (1 << 4) /* TI Sync Serial Protocol */ +#define SSCR0_PSP (3 << 4) /* PSP - Programmable Serial Protocol */ +#define SSCR1_TTELP (1 << 31) /* TXD Tristate Enable Last Phase */ +#define SSCR1_TTE (1 << 30) /* TXD Tristate Enable */ +#define SSCR1_EBCEI (1 << 29) /* Enable Bit Count Error interrupt */ +#define SSCR1_SCFR (1 << 28) /* Slave Clock free Running */ +#define SSCR1_ECRA (1 << 27) /* Enable Clock Request A */ +#define SSCR1_ECRB (1 << 26) /* Enable Clock request B */ +#define SSCR1_SCLKDIR (1 << 25) /* Serial Bit Rate Clock Direction */ +#define SSCR1_SFRMDIR (1 << 24) /* Frame Direction */ +#define SSCR1_RWOT (1 << 23) /* Receive Without Transmit */ +#define SSCR1_TRAIL (1 << 22) /* Trailing Byte */ +#define SSCR1_TSRE (1 << 21) /* Transmit Service Request Enable */ +#define SSCR1_RSRE (1 << 20) /* Receive Service Request Enable */ +#define SSCR1_TINTE (1 << 19) /* Receiver Time-out Interrupt enable */ +#define SSCR1_PINTE (1 << 18) /* Peripheral Trailing Byte Interupt Enable */ +#define SSCR1_IFS (1 << 16) /* Invert Frame Signal */ +#define SSCR1_STRF (1 << 15) /* Select FIFO or EFWR */ +#define SSCR1_EFWR (1 << 14) /* Enable FIFO Write/Read */ + +#define SSSR_BCE (1 << 23) /* Bit Count Error */ +#define SSSR_CSS (1 << 22) /* Clock Synchronisation Status */ +#define SSSR_TUR (1 << 21) /* Transmit FIFO Under Run */ +#define SSSR_EOC (1 << 20) /* End Of Chain */ +#define SSSR_TINT (1 << 19) /* Receiver Time-out Interrupt */ +#define SSSR_PINT (1 << 18) /* Peripheral Trailing Byte Interrupt */ + + +#define SSPSP_SCMODE(x) ((x) << 0) /* Serial Bit Rate Clock Mode */ +#define SSPSP_SFRMP (1 << 2) /* Serial Frame Polarity */ +#define SSPSP_ETDS (1 << 3) /* End of Transfer data State */ +#define SSPSP_STRTDLY(x) ((x) << 4) /* Start Delay */ +#define SSPSP_DMYSTRT(x) ((x) << 7) /* Dummy Start */ +#define SSPSP_SFRMDLY(x) ((x) << 9) /* Serial Frame Delay */ +#define SSPSP_SFRMWDTH(x) ((x) << 16) /* Serial Frame Width */ +#define SSPSP_DMYSTOP(x) ((x) << 23) /* Dummy Stop */ +#define SSPSP_FSRT (1 << 25) /* Frame Sync Relative Timing */ + +/* PXA3xx */ +#define SSPSP_EDMYSTRT(x) ((x) << 26) /* Extended Dummy Start */ +#define SSPSP_EDMYSTOP(x) ((x) << 28) /* Extended Dummy Stop */ +#define SSPSP_TIMING_MASK (0x7f8001f0) + +#define SSACD_SCDB (1 << 3) /* SSPSYSCLK Divider Bypass */ +#define SSACD_ACPS(x) ((x) << 4) /* Audio clock PLL select */ +#define SSACD_ACDS(x) ((x) << 0) /* Audio clock divider select */ +#define SSACD_SCDX8 (1 << 7) /* SYSCLK division ratio select */ + +enum pxa_ssp_type { + SSP_UNDEFINED = 0, + PXA25x_SSP, /* pxa 210, 250, 255, 26x */ + PXA25x_NSSP, /* pxa 255, 26x (including ASSP) */ + PXA27x_SSP, + PXA168_SSP, +}; + +struct ssp_device { + struct platform_device *pdev; + struct list_head node; + + struct clk *clk; + void __iomem *mmio_base; + unsigned long phys_base; + + const char *label; + int port_id; + int type; + int use_count; + int irq; + int drcmr_rx; + int drcmr_tx; +}; + +/** + * pxa_ssp_write_reg - Write to a SSP register + * + * @dev: SSP device to access + * @reg: Register to write to + * @val: Value to be written. + */ +static inline void pxa_ssp_write_reg(struct ssp_device *dev, u32 reg, u32 val) +{ + __raw_writel(val, dev->mmio_base + reg); +} + +/** + * pxa_ssp_read_reg - Read from a SSP register + * + * @dev: SSP device to access + * @reg: Register to read from + */ +static inline u32 pxa_ssp_read_reg(struct ssp_device *dev, u32 reg) +{ + return __raw_readl(dev->mmio_base + reg); +} + +struct ssp_device *pxa_ssp_request(int port, const char *label); +void pxa_ssp_free(struct ssp_device *); +#endif diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h new file mode 100644 index 0000000..471ed68 --- /dev/null +++ b/include/linux/spi/pxa2xx_spi.h @@ -0,0 +1,49 @@ +/* + * Copyright (C) 2005 Stephen Street / StreetFire Sound Labs + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ +#ifndef __linux_pxa2xx_spi_h +#define __linux_pxa2xx_spi_h + +#include +#include + +#define PXA2XX_CS_ASSERT (0x01) +#define PXA2XX_CS_DEASSERT (0x02) + +/* device.platform_data for SSP controller devices */ +struct pxa2xx_spi_master { + u32 clock_enable; + u16 num_chipselect; + u8 enable_dma; +}; + +/* spi_board_info.controller_data for SPI slave devices, + * copied to spi_device.platform_data ... mostly for dma tuning + */ +struct pxa2xx_spi_chip { + u8 tx_threshold; + u8 rx_threshold; + u8 dma_burst_size; + u32 timeout; + u8 enable_loopback; + int gpio_cs; + void (*cs_control)(u32 command); +}; + +extern void pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_master *info); + +#endif -- cgit v1.1 From d6ea3df0d470fb9260db93883f97764cf9f0e562 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 24 Nov 2010 10:17:14 +0100 Subject: spi/pxa2xx: Add CE4100 support Sodaville's SPI controller is very much the same as in PXA25x. The difference: - The RX/TX FIFO is only 4 words deep instead of 16 - No DMA support - The SPI controller offers a CS functionality Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Dirk Brandewie --- include/linux/spi/pxa2xx_spi.h | 105 ++++++++++++++++++++++++++++++++++++++++- 1 file changed, 104 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h index 471ed68..d3e1075 100644 --- a/include/linux/spi/pxa2xx_spi.h +++ b/include/linux/spi/pxa2xx_spi.h @@ -19,7 +19,6 @@ #define __linux_pxa2xx_spi_h #include -#include #define PXA2XX_CS_ASSERT (0x01) #define PXA2XX_CS_DEASSERT (0x02) @@ -44,6 +43,110 @@ struct pxa2xx_spi_chip { void (*cs_control)(u32 command); }; +#ifdef CONFIG_ARCH_PXA + +#include +#include + extern void pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_master *info); +#else +/* + * This is the implemtation for CE4100 on x86. ARM defines them in mach/ or + * plat/ include path. + * The CE4100 does not provide DMA support. This bits are here to let the driver + * compile and will never be used. Maybe we get DMA support at a later point in + * time. + */ + +#define DCSR(n) (n) +#define DSADR(n) (n) +#define DTADR(n) (n) +#define DCMD(n) (n) +#define DRCMR(n) (n) + +#define DCSR_RUN (1 << 31) /* Run Bit */ +#define DCSR_NODESC (1 << 30) /* No-Descriptor Fetch */ +#define DCSR_STOPIRQEN (1 << 29) /* Stop Interrupt Enable */ +#define DCSR_REQPEND (1 << 8) /* Request Pending (read-only) */ +#define DCSR_STOPSTATE (1 << 3) /* Stop State (read-only) */ +#define DCSR_ENDINTR (1 << 2) /* End Interrupt */ +#define DCSR_STARTINTR (1 << 1) /* Start Interrupt */ +#define DCSR_BUSERR (1 << 0) /* Bus Error Interrupt */ + +#define DCSR_EORIRQEN (1 << 28) /* End of Receive Interrupt Enable */ +#define DCSR_EORJMPEN (1 << 27) /* Jump to next descriptor on EOR */ +#define DCSR_EORSTOPEN (1 << 26) /* STOP on an EOR */ +#define DCSR_SETCMPST (1 << 25) /* Set Descriptor Compare Status */ +#define DCSR_CLRCMPST (1 << 24) /* Clear Descriptor Compare Status */ +#define DCSR_CMPST (1 << 10) /* The Descriptor Compare Status */ +#define DCSR_EORINTR (1 << 9) /* The end of Receive */ + +#define DRCMR_MAPVLD (1 << 7) /* Map Valid */ +#define DRCMR_CHLNUM 0x1f /* mask for Channel Number */ + +#define DDADR_DESCADDR 0xfffffff0 /* Address of next descriptor */ +#define DDADR_STOP (1 << 0) /* Stop */ + +#define DCMD_INCSRCADDR (1 << 31) /* Source Address Increment Setting. */ +#define DCMD_INCTRGADDR (1 << 30) /* Target Address Increment Setting. */ +#define DCMD_FLOWSRC (1 << 29) /* Flow Control by the source. */ +#define DCMD_FLOWTRG (1 << 28) /* Flow Control by the target. */ +#define DCMD_STARTIRQEN (1 << 22) /* Start Interrupt Enable */ +#define DCMD_ENDIRQEN (1 << 21) /* End Interrupt Enable */ +#define DCMD_ENDIAN (1 << 18) /* Device Endian-ness. */ +#define DCMD_BURST8 (1 << 16) /* 8 byte burst */ +#define DCMD_BURST16 (2 << 16) /* 16 byte burst */ +#define DCMD_BURST32 (3 << 16) /* 32 byte burst */ +#define DCMD_WIDTH1 (1 << 14) /* 1 byte width */ +#define DCMD_WIDTH2 (2 << 14) /* 2 byte width (HalfWord) */ +#define DCMD_WIDTH4 (3 << 14) /* 4 byte width (Word) */ +#define DCMD_LENGTH 0x01fff /* length mask (max = 8K - 1) */ + +/* + * Descriptor structure for PXA's DMA engine + * Note: this structure must always be aligned to a 16-byte boundary. + */ + +typedef enum { + DMA_PRIO_HIGH = 0, + DMA_PRIO_MEDIUM = 1, + DMA_PRIO_LOW = 2 +} pxa_dma_prio; + +/* + * DMA registration + */ + +static inline int pxa_request_dma(char *name, + pxa_dma_prio prio, + void (*irq_handler)(int, void *), + void *data) +{ + return -ENODEV; +} + +static inline void pxa_free_dma(int dma_ch) +{ +} + +/* + * The CE4100 does not have the clk framework implemented and SPI clock can + * not be switched on/off or the divider changed. + */ +static inline void clk_disable(struct clk *clk) +{ +} + +static inline int clk_enable(struct clk *clk) +{ + return 0; +} + +static inline unsigned long clk_get_rate(struct clk *clk) +{ + return 3686400; +} + +#endif #endif -- cgit v1.1 From d0777f2c3eda180e3fc549e0efbe741014f17689 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 22 Nov 2010 17:12:16 -0800 Subject: spi/pxa2xx: Consider CE4100's FIFO depth For PXA the default threshold is FIFO_DEPTH / 2. Adjust this value for CE4100. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Dirk Brandewie --- include/linux/pxa2xx_ssp.h | 32 ++++++++++++++++++++++++++------ 1 file changed, 26 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index 84465d4..c3aa334 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -71,10 +71,6 @@ #define SSCR1_SPO (1 << 3) /* Motorola SPI SSPSCLK polarity setting */ #define SSCR1_SPH (1 << 4) /* Motorola SPI SSPSCLK phase setting */ #define SSCR1_MWDS (1 << 5) /* Microwire Transmit Data Size */ -#define SSCR1_TFT (0x000003c0) /* Transmit FIFO Threshold (mask) */ -#define SSCR1_TxTresh(x) (((x) - 1) << 6) /* level [1..16] */ -#define SSCR1_RFT (0x00003c00) /* Receive FIFO Threshold (mask) */ -#define SSCR1_RxTresh(x) (((x) - 1) << 10) /* level [1..16] */ #define SSSR_TNF (1 << 2) /* Transmit FIFO Not Full */ #define SSSR_RNE (1 << 3) /* Receive FIFO Not Empty */ @@ -82,8 +78,32 @@ #define SSSR_TFS (1 << 5) /* Transmit FIFO Service Request */ #define SSSR_RFS (1 << 6) /* Receive FIFO Service Request */ #define SSSR_ROR (1 << 7) /* Receive FIFO Overrun */ -#define SSSR_TFL_MASK (0xf << 8) /* Transmit FIFO Level mask */ -#define SSSR_RFL_MASK (0xf << 12) /* Receive FIFO Level mask */ + +#ifdef CONFIG_ARCH_PXA +#define RX_THRESH_DFLT 8 +#define TX_THRESH_DFLT 8 + +#define SSSR_TFL_MASK (0xf << 8) /* Transmit FIFO Level mask */ +#define SSSR_RFL_MASK (0xf << 12) /* Receive FIFO Level mask */ + +#define SSCR1_TFT (0x000003c0) /* Transmit FIFO Threshold (mask) */ +#define SSCR1_TxTresh(x) (((x) - 1) << 6) /* level [1..16] */ +#define SSCR1_RFT (0x00003c00) /* Receive FIFO Threshold (mask) */ +#define SSCR1_RxTresh(x) (((x) - 1) << 10) /* level [1..16] */ + +#else + +#define RX_THRESH_DFLT 2 +#define TX_THRESH_DFLT 2 + +#define SSSR_TFL_MASK (0x3 << 8) /* Transmit FIFO Level mask */ +#define SSSR_RFL_MASK (0x3 << 12) /* Receive FIFO Level mask */ + +#define SSCR1_TFT (0x000000c0) /* Transmit FIFO Threshold (mask) */ +#define SSCR1_TxTresh(x) (((x) - 1) << 6) /* level [1..4] */ +#define SSCR1_RFT (0x00000c00) /* Receive FIFO Threshold (mask) */ +#define SSCR1_RxTresh(x) (((x) - 1) << 10) /* level [1..4] */ +#endif /* extra bits in PXA255, PXA26x and PXA27x SSP ports */ #define SSCR0_TISSP (1 << 4) /* TI Sync Serial Protocol */ -- cgit v1.1 From f2cd2d3e9b3ef960612e362f0ad129d735452df2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 29 Nov 2010 08:14:37 +0000 Subject: net sched: use xps information for qdisc NUMA affinity Allocate qdisc memory according to NUMA properties of cpus included in xps map. To be effective, qdisc should be (re)setup after changes of /sys/class/net/eth/queues/tx-/xps_cpus I added a numa_node field in struct netdev_queue, containing NUMA node if all cpus included in xps_cpus share same node, else -1. Signed-off-by: Eric Dumazet Cc: Ben Hutchings Cc: Tom Herbert Signed-off-by: David S. Miller --- include/linux/netdevice.h | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4b0c7f3..a9ac5dc 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -508,7 +508,9 @@ struct netdev_queue { #ifdef CONFIG_RPS struct kobject kobj; #endif - +#if defined(CONFIG_XPS) && defined(CONFIG_NUMA) + int numa_node; +#endif /* * write mostly part */ @@ -523,6 +525,22 @@ struct netdev_queue { u64 tx_dropped; } ____cacheline_aligned_in_smp; +static inline int netdev_queue_numa_node_read(const struct netdev_queue *q) +{ +#if defined(CONFIG_XPS) && defined(CONFIG_NUMA) + return q->numa_node; +#else + return -1; +#endif +} + +static inline void netdev_queue_numa_node_write(struct netdev_queue *q, int node) +{ +#if defined(CONFIG_XPS) && defined(CONFIG_NUMA) + q->numa_node = node; +#endif +} + #ifdef CONFIG_RPS /* * This structure holds an RPS map which can be of variable length. The -- cgit v1.1 From 879aa24d6394aa04b690a600a41ff500441ad384 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 26 Nov 2010 06:47:28 -0300 Subject: [media] V4L: improve the BKL replacement heuristic The BKL replacement mutex had some serious performance side-effects on V4L drivers. It is replaced by a better heuristic that works around the worst of the side-effects. Read the v4l2-dev.c comments for the whole sorry story. This is a temporary measure only until we can convert all v4l drivers to use unlocked_ioctl. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/media/v4l2-device.h b/include/media/v4l2-device.h index 6648036..b16f307 100644 --- a/include/media/v4l2-device.h +++ b/include/media/v4l2-device.h @@ -51,6 +51,8 @@ struct v4l2_device { unsigned int notification, void *arg); /* The control handler. May be NULL. */ struct v4l2_ctrl_handler *ctrl_handler; + /* BKL replacement mutex. Temporary solution only. */ + struct mutex ioctl_lock; }; /* Initialize v4l2_dev and make dev->driver_data point to v4l2_dev. -- cgit v1.1 From 735cbc4784a084b7a76c43c69f9dba683bb3b48b Mon Sep 17 00:00:00 2001 From: Andrei Emeltchenko Date: Wed, 1 Dec 2010 16:58:22 +0200 Subject: Bluetooth: clean up sco code Do not use assignments in IF condition, remove extra spaces Signed-off-by: Andrei Emeltchenko Signed-off-by: Gustavo F. Padovan --- include/net/bluetooth/sco.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/sco.h b/include/net/bluetooth/sco.h index e28a2a7..ea5c664 100644 --- a/include/net/bluetooth/sco.h +++ b/include/net/bluetooth/sco.h @@ -55,11 +55,11 @@ struct sco_conninfo { struct sco_conn { struct hci_conn *hcon; - bdaddr_t *dst; - bdaddr_t *src; - + bdaddr_t *dst; + bdaddr_t *src; + spinlock_t lock; - struct sock *sk; + struct sock *sk; unsigned int mtu; }; -- cgit v1.1 From 285b4e90318dcf421a00b2ac3fe8ab713f3281e3 Mon Sep 17 00:00:00 2001 From: Andrei Emeltchenko Date: Wed, 1 Dec 2010 16:58:23 +0200 Subject: Bluetooth: clean up rfcomm code Remove extra spaces, assignments in if statement, zeroing static variables, extra braces. Fix includes. Signed-off-by: Andrei Emeltchenko Signed-off-by: Gustavo F. Padovan --- include/net/bluetooth/rfcomm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/rfcomm.h b/include/net/bluetooth/rfcomm.h index 71047bc..2e78756 100644 --- a/include/net/bluetooth/rfcomm.h +++ b/include/net/bluetooth/rfcomm.h @@ -105,7 +105,7 @@ struct rfcomm_hdr { u8 addr; u8 ctrl; - u8 len; // Actual size can be 2 bytes + u8 len; /* Actual size can be 2 bytes */ } __packed; struct rfcomm_cmd { @@ -228,7 +228,7 @@ struct rfcomm_dlc { /* ---- RFCOMM SEND RPN ---- */ int rfcomm_send_rpn(struct rfcomm_session *s, int cr, u8 dlci, u8 bit_rate, u8 data_bits, u8 stop_bits, - u8 parity, u8 flow_ctrl_settings, + u8 parity, u8 flow_ctrl_settings, u8 xon_char, u8 xoff_char, u16 param_mask); /* ---- RFCOMM DLCs (channels) ---- */ -- cgit v1.1 From 894718a6be69d8cfd191dc291b42be32a1e4851b Mon Sep 17 00:00:00 2001 From: Andrei Emeltchenko Date: Wed, 1 Dec 2010 16:58:24 +0200 Subject: Bluetooth: clean up l2cap code Do not initialize static vars to zero, macros with complex values shall be enclosed with (), remove unneeded braces. Signed-off-by: Andrei Emeltchenko Signed-off-by: Gustavo F. Padovan --- include/net/bluetooth/l2cap.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index c819c8b..217bb91 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -417,11 +417,11 @@ static inline int l2cap_tx_window_full(struct sock *sk) return sub == pi->remote_tx_win; } -#define __get_txseq(ctrl) ((ctrl) & L2CAP_CTRL_TXSEQ) >> 1 -#define __get_reqseq(ctrl) ((ctrl) & L2CAP_CTRL_REQSEQ) >> 8 -#define __is_iframe(ctrl) !((ctrl) & L2CAP_CTRL_FRAME_TYPE) -#define __is_sframe(ctrl) (ctrl) & L2CAP_CTRL_FRAME_TYPE -#define __is_sar_start(ctrl) ((ctrl) & L2CAP_CTRL_SAR) == L2CAP_SDU_START +#define __get_txseq(ctrl) (((ctrl) & L2CAP_CTRL_TXSEQ) >> 1) +#define __get_reqseq(ctrl) (((ctrl) & L2CAP_CTRL_REQSEQ) >> 8) +#define __is_iframe(ctrl) (!((ctrl) & L2CAP_CTRL_FRAME_TYPE)) +#define __is_sframe(ctrl) ((ctrl) & L2CAP_CTRL_FRAME_TYPE) +#define __is_sar_start(ctrl) (((ctrl) & L2CAP_CTRL_SAR) == L2CAP_SDU_START) void l2cap_load(void); -- cgit v1.1 From 70f23020e6d89155504b5b39f22505f4aec6fa6f Mon Sep 17 00:00:00 2001 From: Andrei Emeltchenko Date: Wed, 1 Dec 2010 16:58:25 +0200 Subject: Bluetooth: clean up hci code Do not use assignment in IF condition, remove extra spaces, fixing typos, simplify code. Signed-off-by: Andrei Emeltchenko Signed-off-by: Gustavo F. Padovan --- include/net/bluetooth/hci.h | 4 ++-- include/net/bluetooth/hci_core.h | 14 +++++++------- 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index e30e008..e9527c5 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -489,7 +489,7 @@ struct hci_rp_read_local_name { #define HCI_OP_WRITE_PG_TIMEOUT 0x0c18 -#define HCI_OP_WRITE_SCAN_ENABLE 0x0c1a +#define HCI_OP_WRITE_SCAN_ENABLE 0x0c1a #define SCAN_DISABLED 0x00 #define SCAN_INQUIRY 0x01 #define SCAN_PAGE 0x02 @@ -874,7 +874,7 @@ struct hci_ev_si_security { struct hci_command_hdr { __le16 opcode; /* OCF & OGF */ - __u8 plen; + __u8 plen; } __packed; struct hci_event_hdr { diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index ebec8c9..9c08625 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -44,15 +44,15 @@ struct inquiry_data { }; struct inquiry_entry { - struct inquiry_entry *next; + struct inquiry_entry *next; __u32 timestamp; struct inquiry_data data; }; struct inquiry_cache { - spinlock_t lock; + spinlock_t lock; __u32 timestamp; - struct inquiry_entry *list; + struct inquiry_entry *list; }; struct hci_conn_hash { @@ -141,7 +141,7 @@ struct hci_dev { void *driver_data; void *core_data; - atomic_t promisc; + atomic_t promisc; struct dentry *debugfs; @@ -150,7 +150,7 @@ struct hci_dev { struct rfkill *rfkill; - struct module *owner; + struct module *owner; int (*open)(struct hci_dev *hdev); int (*close)(struct hci_dev *hdev); @@ -215,8 +215,8 @@ extern rwlock_t hci_dev_list_lock; extern rwlock_t hci_cb_list_lock; /* ----- Inquiry cache ----- */ -#define INQUIRY_CACHE_AGE_MAX (HZ*30) // 30 seconds -#define INQUIRY_ENTRY_AGE_MAX (HZ*60) // 60 seconds +#define INQUIRY_CACHE_AGE_MAX (HZ*30) /* 30 seconds */ +#define INQUIRY_ENTRY_AGE_MAX (HZ*60) /* 60 seconds */ #define inquiry_cache_lock(c) spin_lock(&c->lock) #define inquiry_cache_unlock(c) spin_unlock(&c->lock) -- cgit v1.1 From be21871f24b0fcd8d0d09c8090385c9cec80efa3 Mon Sep 17 00:00:00 2001 From: Andrei Emeltchenko Date: Wed, 1 Dec 2010 16:58:26 +0200 Subject: Bluetooth: clean up legal text Remove extra spaces from legal text so that legal stuff looks the same for all bluetooth code. Signed-off-by: Andrei Emeltchenko Signed-off-by: Gustavo F. Padovan --- include/net/bluetooth/hci.h | 12 ++++++------ include/net/bluetooth/l2cap.h | 12 ++++++------ include/net/bluetooth/rfcomm.h | 14 +++++++------- include/net/bluetooth/sco.h | 12 ++++++------ 4 files changed, 25 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index e9527c5..f3c5ed6 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -1,4 +1,4 @@ -/* +/* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated @@ -12,13 +12,13 @@ OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY - CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES - WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN - ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF + CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES + WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN + ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. - ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, - COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS + ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, + COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 217bb91..7ad25ca 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -1,4 +1,4 @@ -/* +/* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated Copyright (C) 2009-2010 Gustavo F. Padovan @@ -14,13 +14,13 @@ OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY - CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES - WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN - ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF + CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES + WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN + ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. - ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, - COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS + ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, + COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ diff --git a/include/net/bluetooth/rfcomm.h b/include/net/bluetooth/rfcomm.h index 2e78756..6eac4a7 100644 --- a/include/net/bluetooth/rfcomm.h +++ b/include/net/bluetooth/rfcomm.h @@ -1,5 +1,5 @@ -/* - RFCOMM implementation for Linux Bluetooth stack (BlueZ). +/* + RFCOMM implementation for Linux Bluetooth stack (BlueZ) Copyright (C) 2002 Maxim Krasnyansky Copyright (C) 2002 Marcel Holtmann @@ -11,13 +11,13 @@ OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY - CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES - WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN - ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF + CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES + WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN + ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. - ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, - COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS + ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, + COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ diff --git a/include/net/bluetooth/sco.h b/include/net/bluetooth/sco.h index ea5c664..1e35c43 100644 --- a/include/net/bluetooth/sco.h +++ b/include/net/bluetooth/sco.h @@ -1,4 +1,4 @@ -/* +/* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated @@ -12,13 +12,13 @@ OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY - CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES - WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN - ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF + CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES + WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN + ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. - ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, - COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS + ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, + COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ -- cgit v1.1 From 8790ca172a1550949804a2ad59ccea310f680c9f Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 1 Dec 2010 17:28:18 -0800 Subject: inetpeer: Kill use of inet_peer_address_t typedef. They are verboten these days. Signed-off-by: David S. Miller --- include/net/inetpeer.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index fb8aeb1..5161bfd 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -14,18 +14,18 @@ #include #include -typedef struct { +struct inetpeer_addr { union { __be32 a4; __be32 a6[4]; }; __u16 family; -} inet_peer_address_t; +}; struct inet_peer { /* group together avl_left,avl_right,v4daddr to speedup lookups */ struct inet_peer __rcu *avl_left, *avl_right; - inet_peer_address_t daddr; + struct inetpeer_addr daddr; __u32 avl_height; struct list_head unused; __u32 dtime; /* the time of last use of not @@ -51,11 +51,11 @@ struct inet_peer { void inet_initpeers(void) __init; /* can be called with or without local BH being disabled */ -struct inet_peer *inet_getpeer(inet_peer_address_t *daddr, int create); +struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create); static inline struct inet_peer *inet_getpeer_v4(__be32 v4daddr, int create) { - inet_peer_address_t daddr; + struct inetpeer_addr daddr; daddr.a4 = v4daddr; daddr.family = AF_INET; @@ -64,7 +64,7 @@ static inline struct inet_peer *inet_getpeer_v4(__be32 v4daddr, int create) static inline struct inet_peer *inet_getpeer_v6(struct in6_addr *v6daddr, int create) { - inet_peer_address_t daddr; + struct inetpeer_addr daddr; ipv6_addr_copy((struct in6_addr *)daddr.a6, v6daddr); daddr.family = AF_INET6; -- cgit v1.1 From 4399ce402c7c837dec80bf9fb40d079b39b9265a Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 1 Dec 2010 17:29:08 -0800 Subject: inetpeer: Fix incorrect comment about inetpeer struct size. Now with ipv6 support it is no longer less than 64 bytes. Signed-off-by: David S. Miller --- include/net/inetpeer.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 5161bfd..599d96e 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -35,7 +35,6 @@ struct inet_peer { * Once inet_peer is queued for deletion (refcnt == -1), following fields * are not available: rid, ip_id_count, tcp_ts, tcp_ts_stamp * We can share memory with rcu_head to keep inet_peer small - * (less then 64 bytes) */ union { struct { -- cgit v1.1 From ccb7c410ddc054b8c1ae780319bc98ae092d3854 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 1 Dec 2010 18:09:13 -0800 Subject: timewait_sock: Create and use getpeer op. The only thing AF-specific about remembering the timestamp for a time-wait TCP socket is getting the peer. Abstract that behind a new timewait_sock_ops vector. Support for real IPV6 sockets is not filled in yet, but curiously this makes timewait recycling start to work for v4-mapped ipv6 sockets. Signed-off-by: David S. Miller --- include/net/tcp.h | 1 + include/net/timewait_sock.h | 8 ++++++++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 3e23964..4097320 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -313,6 +313,7 @@ extern void tcp_shutdown (struct sock *sk, int how); extern int tcp_v4_rcv(struct sk_buff *skb); extern struct inet_peer *tcp_v4_get_peer(struct sock *sk, bool *release_it); +extern void *tcp_v4_tw_get_peer(struct sock *sk); extern int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw); extern int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t size); diff --git a/include/net/timewait_sock.h b/include/net/timewait_sock.h index 97c3b14..053b3cf 100644 --- a/include/net/timewait_sock.h +++ b/include/net/timewait_sock.h @@ -21,6 +21,7 @@ struct timewait_sock_ops { int (*twsk_unique)(struct sock *sk, struct sock *sktw, void *twp); void (*twsk_destructor)(struct sock *sk); + void *(*twsk_getpeer)(struct sock *sk); }; static inline int twsk_unique(struct sock *sk, struct sock *sktw, void *twp) @@ -39,4 +40,11 @@ static inline void twsk_destructor(struct sock *sk) sk->sk_prot->twsk_prot->twsk_destructor(sk); } +static inline void *twsk_getpeer(struct sock *sk) +{ + if (sk->sk_prot->twsk_prot->twsk_getpeer) + return sk->sk_prot->twsk_prot->twsk_getpeer(sk); + return NULL; +} + #endif /* _TIMEWAIT_SOCK_H */ -- cgit v1.1 From a757ee2216211278680dd8ac869aabe7b4a9970d Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 2 Dec 2010 01:57:03 -0200 Subject: [media] Don't export format_by_forcc on two different drivers Drivers should append their name on exported symbols, to avoid conflicts with allyesconfig: drivers/staging/built-in.o: In function `format_by_fourcc': /home/v4l/work_trees/linus/drivers/staging/cx25821/cx25821-video.c:96: multiple definition of `format_by_fourcc' drivers/media/built-in.o:/home/v4l/work_trees/linus/drivers/media/common/saa7146_video.c:88: first defined here Let's rename both occurences with a small shellscript: for i in drivers/staging/cx25821/*.[ch]; do sed s,format_by_fourcc,cx25821_format_by_fourcc,g <$i >a && mv a $i; done for i in drivers/media/common/saa7146*.[ch]; do sed s,format_by_fourcc,saa7146_format_by_fourcc,g <$i >a && mv a $i; done for i in include/media/saa7146*.[ch]; do sed s,format_by_fourcc,saa7146_format_by_fourcc,g <$i >a && mv a $i; done Signed-off-by: Mauro Carvalho Chehab --- include/media/saa7146.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/saa7146.h b/include/media/saa7146.h index 7a9f76e..ac7ce00 100644 --- a/include/media/saa7146.h +++ b/include/media/saa7146.h @@ -161,7 +161,7 @@ extern struct list_head saa7146_devices; extern struct mutex saa7146_devices_lock; int saa7146_register_extension(struct saa7146_extension*); int saa7146_unregister_extension(struct saa7146_extension*); -struct saa7146_format* format_by_fourcc(struct saa7146_dev *dev, int fourcc); +struct saa7146_format* saa7146_format_by_fourcc(struct saa7146_dev *dev, int fourcc); int saa7146_pgtable_alloc(struct pci_dev *pci, struct saa7146_pgtable *pt); void saa7146_pgtable_free(struct pci_dev *pci, struct saa7146_pgtable *pt); int saa7146_pgtable_build_single(struct pci_dev *pci, struct saa7146_pgtable *pt, struct scatterlist *list, int length ); -- cgit v1.1 From 079f2f7485648c1397a35575fae45908a0db5ba6 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Mon, 22 Nov 2010 11:25:50 +0100 Subject: crypto: scatterwalk - Add scatterwalk_crypto_chain helper A lot of crypto algorithms implement their own chaining function. So add a generic one that can be used from all the algorithms that need scatterlist chaining. Signed-off-by: Steffen Klassert Signed-off-by: Herbert Xu --- include/crypto/scatterwalk.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/crypto/scatterwalk.h b/include/crypto/scatterwalk.h index 833d208..4fd95a3 100644 --- a/include/crypto/scatterwalk.h +++ b/include/crypto/scatterwalk.h @@ -68,6 +68,21 @@ static inline struct scatterlist *scatterwalk_sg_next(struct scatterlist *sg) return (++sg)->length ? sg : (void *)sg_page(sg); } +static inline void scatterwalk_crypto_chain(struct scatterlist *head, + struct scatterlist *sg, + int chain, int num) +{ + if (chain) { + head->length += sg->length; + sg = scatterwalk_sg_next(sg); + } + + if (sg) + scatterwalk_sg_chain(head, num, sg); + else + sg_mark_end(head); +} + static inline unsigned long scatterwalk_samebuf(struct scatter_walk *walk_in, struct scatter_walk *walk_out) { -- cgit v1.1 From 676dac4b1bee0469d6932f698aeb77e8489f5861 Mon Sep 17 00:00:00 2001 From: Casey Schaufler Date: Thu, 2 Dec 2010 06:43:39 -0800 Subject: This patch adds a new security attribute to Smack called SMACK64EXEC. It defines label that is used while task is running. Exception: in smack_task_wait() child task is checked for write access to parent task using label inherited from the task that forked it. Fixed issues from previous submit: - SMACK64EXEC was not read when SMACK64 was not set. - inode security blob was not updated after setting SMACK64EXEC - inode security blob was not updated when removing SMACK64EXEC --- include/linux/xattr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/xattr.h b/include/linux/xattr.h index f1e5bde..351c790 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -40,9 +40,11 @@ #define XATTR_SMACK_SUFFIX "SMACK64" #define XATTR_SMACK_IPIN "SMACK64IPIN" #define XATTR_SMACK_IPOUT "SMACK64IPOUT" +#define XATTR_SMACK_EXEC "SMACK64EXEC" #define XATTR_NAME_SMACK XATTR_SECURITY_PREFIX XATTR_SMACK_SUFFIX #define XATTR_NAME_SMACKIPIN XATTR_SECURITY_PREFIX XATTR_SMACK_IPIN #define XATTR_NAME_SMACKIPOUT XATTR_SECURITY_PREFIX XATTR_SMACK_IPOUT +#define XATTR_NAME_SMACKEXEC XATTR_SECURITY_PREFIX XATTR_SMACK_EXEC #define XATTR_CAPS_SUFFIX "capability" #define XATTR_NAME_CAPS XATTR_SECURITY_PREFIX XATTR_CAPS_SUFFIX -- cgit v1.1 From 6072d13c429373c5d63b69dadbbef40a9b035552 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 1 Dec 2010 13:35:19 -0500 Subject: Call the filesystem back whenever a page is removed from the page cache NFS needs to be able to release objects that are stored in the page cache once the page itself is no longer visible from the page cache. This patch adds a callback to the address space operations that allows filesystems to perform page cleanups once the page has been removed from the page cache. Original patch by: Linus Torvalds [trondmy: cover the cases of invalidate_inode_pages2() and truncate_inode_pages()] Signed-off-by: Trond Myklebust --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index c9e06cc..090f0ea 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -602,6 +602,7 @@ struct address_space_operations { sector_t (*bmap)(struct address_space *, sector_t); void (*invalidatepage) (struct page *, unsigned long); int (*releasepage) (struct page *, gfp_t); + void (*freepage)(struct page *); ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov, loff_t offset, unsigned long nr_segs); int (*get_xip_mem)(struct address_space *, pgoff_t, int, -- cgit v1.1 From 11de3b11e08cac26d59e88efaf4e316701883552 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 1 Dec 2010 14:17:06 -0500 Subject: NFS: Fix a memory leak in nfs_readdir We need to ensure that the entries in the nfs_cache_array get cleared when the page is removed from the page cache. To do so, we use the freepage address_space operation. Change nfs_readdir_clear_array to use kmap_atomic(), so that the function can be safely called from all contexts. Finally, modify the cache_page_release helper to call nfs_readdir_clear_array directly, when dealing with an anonymous page from 'uncached_readdir'. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index c66fdb7..29d504d 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -401,6 +401,7 @@ extern const struct inode_operations nfs3_file_inode_operations; #endif /* CONFIG_NFS_V3 */ extern const struct file_operations nfs_file_operations; extern const struct address_space_operations nfs_file_aops; +extern const struct address_space_operations nfs_dir_aops; static inline struct nfs_open_context *nfs_file_open_context(struct file *filp) { -- cgit v1.1 From 2a8626a9e2d86d114a2d9f813a1acebf9d53dd10 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 22 Nov 2010 17:12:17 -0800 Subject: spi/pxa2xx: Add chipselect support for Sodaville The SPI core on Sodaville supports chip selects. Its configuration moved into the SSSR register at bit 0 and 1. Thus Sodaville can be hooked up with up to 4 devices. This patch ensures that the bits which are otherwiese reserved are only touched on Sodaville and not on any other PXAs. Also it makes sure that the status register does not lose the CS information while clearing the ROR bit. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Dirk Brandewie --- include/linux/pxa2xx_ssp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index c3aa334..2f691e4 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -72,6 +72,7 @@ #define SSCR1_SPH (1 << 4) /* Motorola SPI SSPSCLK phase setting */ #define SSCR1_MWDS (1 << 5) /* Microwire Transmit Data Size */ +#define SSSR_ALT_FRM_MASK 3 /* Masks the SFRM signal number */ #define SSSR_TNF (1 << 2) /* Transmit FIFO Not Full */ #define SSSR_RNE (1 << 3) /* Receive FIFO Not Empty */ #define SSSR_BSY (1 << 4) /* SSP Busy */ @@ -160,6 +161,7 @@ enum pxa_ssp_type { PXA25x_NSSP, /* pxa 255, 26x (including ASSP) */ PXA27x_SSP, PXA168_SSP, + CE4100_SSP, }; struct ssp_device { -- cgit v1.1 From 15c054251ab84895ec043e90826612c1a3d6d4f1 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 2 Dec 2010 10:16:06 -0800 Subject: ipv6: Add rt6_get_peer() helper. To go along side ipv4's rt_get_peer(). Signed-off-by: David S. Miller --- include/net/ip6_route.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 23fed28..67d154a 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -59,6 +59,15 @@ static inline unsigned int rt6_flags2srcprefs(int flags) extern void rt6_bind_peer(struct rt6_info *rt, int create); +static inline struct inet_peer *rt6_get_peer(struct rt6_info *rt) +{ + if (rt->rt6i_peer) + return rt->rt6i_peer; + + rt6_bind_peer(rt, 0); + return rt->rt6i_peer; +} + extern void ip6_route_input(struct sk_buff *skb); extern struct dst_entry * ip6_route_output(struct net *net, -- cgit v1.1 From ae4694b2d3e4c0f47c0e804a68417be57e5daf85 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 2 Dec 2010 10:59:22 -0800 Subject: ipv6: Create inet6_csk_route_req(). Brother of ipv4's inet_csk_route_req(). Signed-off-by: David S. Miller --- include/net/inet6_connection_sock.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h index aae08f6..ff01350 100644 --- a/include/net/inet6_connection_sock.h +++ b/include/net/inet6_connection_sock.h @@ -25,6 +25,9 @@ struct sockaddr; extern int inet6_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb); +extern struct dst_entry* inet6_csk_route_req(struct sock *sk, + const struct request_sock *req); + extern struct request_sock *inet6_csk_search_req(const struct sock *sk, struct request_sock ***prevp, const __be16 rport, -- cgit v1.1 From 172c69a47675dc1ca9c7243c031d8d77701bccc0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Sun, 28 Nov 2010 10:39:35 +0100 Subject: ssb: extract indexes for power tables MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Rafał Miłecki Acked-by: Michael Buesch Signed-off-by: John W. Linville --- include/linux/ssb/ssb.h | 4 ++++ include/linux/ssb/ssb_regs.h | 40 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 44 insertions(+) (limited to 'include') diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 623b704..9659eff 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -55,6 +55,10 @@ struct ssb_sprom { u8 tri5gl; /* 5.2GHz TX isolation */ u8 tri5g; /* 5.3GHz TX isolation */ u8 tri5gh; /* 5.8GHz TX isolation */ + u8 txpid2g[4]; /* 2GHz TX power index */ + u8 txpid5gl[4]; /* 4.9 - 5.1GHz TX power index */ + u8 txpid5g[4]; /* 5.1 - 5.5GHz TX power index */ + u8 txpid5gh[4]; /* 5.5 - ...GHz TX power index */ u8 rxpo2g; /* 2GHz RX power offset */ u8 rxpo5g; /* 5GHz RX power offset */ u8 rssisav2g; /* 2GHz RSSI params */ diff --git a/include/linux/ssb/ssb_regs.h b/include/linux/ssb/ssb_regs.h index 11daf9c..489f7b6 100644 --- a/include/linux/ssb/ssb_regs.h +++ b/include/linux/ssb/ssb_regs.h @@ -299,6 +299,46 @@ #define SSB_SPROM4_AGAIN2_SHIFT 0 #define SSB_SPROM4_AGAIN3 0xFF00 /* Antenna 3 */ #define SSB_SPROM4_AGAIN3_SHIFT 8 +#define SSB_SPROM4_TXPID2G01 0x0062 /* TX Power Index 2GHz */ +#define SSB_SPROM4_TXPID2G0 0x00FF +#define SSB_SPROM4_TXPID2G0_SHIFT 0 +#define SSB_SPROM4_TXPID2G1 0xFF00 +#define SSB_SPROM4_TXPID2G1_SHIFT 8 +#define SSB_SPROM4_TXPID2G23 0x0064 /* TX Power Index 2GHz */ +#define SSB_SPROM4_TXPID2G2 0x00FF +#define SSB_SPROM4_TXPID2G2_SHIFT 0 +#define SSB_SPROM4_TXPID2G3 0xFF00 +#define SSB_SPROM4_TXPID2G3_SHIFT 8 +#define SSB_SPROM4_TXPID5G01 0x0066 /* TX Power Index 5GHz middle subband */ +#define SSB_SPROM4_TXPID5G0 0x00FF +#define SSB_SPROM4_TXPID5G0_SHIFT 0 +#define SSB_SPROM4_TXPID5G1 0xFF00 +#define SSB_SPROM4_TXPID5G1_SHIFT 8 +#define SSB_SPROM4_TXPID5G23 0x0068 /* TX Power Index 5GHz middle subband */ +#define SSB_SPROM4_TXPID5G2 0x00FF +#define SSB_SPROM4_TXPID5G2_SHIFT 0 +#define SSB_SPROM4_TXPID5G3 0xFF00 +#define SSB_SPROM4_TXPID5G3_SHIFT 8 +#define SSB_SPROM4_TXPID5GL01 0x006A /* TX Power Index 5GHz low subband */ +#define SSB_SPROM4_TXPID5GL0 0x00FF +#define SSB_SPROM4_TXPID5GL0_SHIFT 0 +#define SSB_SPROM4_TXPID5GL1 0xFF00 +#define SSB_SPROM4_TXPID5GL1_SHIFT 8 +#define SSB_SPROM4_TXPID5GL23 0x006C /* TX Power Index 5GHz low subband */ +#define SSB_SPROM4_TXPID5GL2 0x00FF +#define SSB_SPROM4_TXPID5GL2_SHIFT 0 +#define SSB_SPROM4_TXPID5GL3 0xFF00 +#define SSB_SPROM4_TXPID5GL3_SHIFT 8 +#define SSB_SPROM4_TXPID5GH01 0x006E /* TX Power Index 5GHz high subband */ +#define SSB_SPROM4_TXPID5GH0 0x00FF +#define SSB_SPROM4_TXPID5GH0_SHIFT 0 +#define SSB_SPROM4_TXPID5GH1 0xFF00 +#define SSB_SPROM4_TXPID5GH1_SHIFT 8 +#define SSB_SPROM4_TXPID5GH23 0x0070 /* TX Power Index 5GHz high subband */ +#define SSB_SPROM4_TXPID5GH2 0x00FF +#define SSB_SPROM4_TXPID5GH2_SHIFT 0 +#define SSB_SPROM4_TXPID5GH3 0xFF00 +#define SSB_SPROM4_TXPID5GH3_SHIFT 8 #define SSB_SPROM4_MAXP_BG 0x0080 /* Max Power BG in path 1 */ #define SSB_SPROM4_MAXP_BG_MASK 0x00FF /* Mask for Max Power BG */ #define SSB_SPROM4_ITSSI_BG 0xFF00 /* Mask for path 1 itssi_bg */ -- cgit v1.1 From 547025d5d4d1056fb4b5a0c9c3c0d5c2fe22c082 Mon Sep 17 00:00:00 2001 From: Bruno Randolf Date: Thu, 2 Dec 2010 16:23:12 +0900 Subject: cfg80211: Add documentation for antenna ops The last patch with the same title was for mac80211 ops, accidentally. Signed-off-by: Bruno Randolf Signed-off-by: John W. Linville --- include/net/cfg80211.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 49a7c53..6b2af7a 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1154,6 +1154,13 @@ struct cfg80211_pmksa { * @mgmt_frame_register: Notify driver that a management frame type was * registered. Note that this callback may not sleep, and cannot run * concurrently with itself. + * + * @set_antenna: Set antenna configuration (tx_ant, rx_ant) on the device. + * Parameters are bitmaps of allowed antennas to use for TX/RX. Drivers may + * reject TX/RX mask combinations they cannot support by returning -EINVAL + * (also see nl80211.h @NL80211_ATTR_WIPHY_ANTENNA_TX). + * + * @get_antenna: Get current antenna configuration from device (tx_ant, rx_ant). */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy); -- cgit v1.1 From a9527a3b621e507c85b639c183c3aa22afd4eb61 Mon Sep 17 00:00:00 2001 From: Shan Wei Date: Wed, 1 Dec 2010 18:04:43 +0000 Subject: net: snmp: fix the wrong ICMP_MIB_MAX value __ICMP_MIB_MAX is equal to the total number of icmp mib, So no need to add 1. This wastes 4/8 bytes memory. Change it to be same as ICMP6_MIB_MAX, TCP_MIB_MAX, UDP_MIB_MAX. Signed-off-by: Shan Wei Signed-off-by: David S. Miller --- include/net/snmp.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/snmp.h b/include/net/snmp.h index a0e6180..aebb553 100644 --- a/include/net/snmp.h +++ b/include/net/snmp.h @@ -61,8 +61,7 @@ struct ipstats_mib { /* ICMP */ #define ICMP_MIB_DUMMY __ICMP_MIB_MAX -#define ICMP_MIB_MAX (__ICMP_MIB_MAX + 1) - +#define ICMP_MIB_MAX __ICMP_MIB_MAX struct icmp_mib { unsigned long mibs[ICMP_MIB_MAX]; }; -- cgit v1.1 From dca9b2404a6d6579828da2425c051462701efd3f Mon Sep 17 00:00:00 2001 From: Shan Wei Date: Wed, 1 Dec 2010 18:05:17 +0000 Subject: net: kill unused macros from head file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These macros have been defined for several years since v2.6.12-rc2（tracing by git）, but never be used. So remove them. Signed-off-by: Shan Wei Signed-off-by: David S. Miller --- include/net/addrconf.h | 2 -- include/net/ip6_route.h | 1 - include/net/ndisc.h | 3 --- include/net/snmp.h | 1 - include/net/sock.h | 3 --- include/net/tcp.h | 6 ------ 6 files changed, 16 deletions(-) (limited to 'include') diff --git a/include/net/addrconf.h b/include/net/addrconf.h index a944124..23710aa 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -1,8 +1,6 @@ #ifndef _ADDRCONF_H #define _ADDRCONF_H -#define RETRANS_TIMER HZ - #define MAX_RTR_SOLICITATIONS 3 #define RTR_SOLICITATION_INTERVAL (4*HZ) diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 67d154a..e06e0ca 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -3,7 +3,6 @@ #define IP6_RT_PRIO_USER 1024 #define IP6_RT_PRIO_ADDRCONF 256 -#define IP6_RT_PRIO_KERN 512 struct route_info { __u8 type; diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 895997b..e0e594f 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -42,9 +42,6 @@ enum { #define ND_REACHABLE_TIME (30*HZ) #define ND_RETRANS_TIMER HZ -#define ND_MIN_RANDOM_FACTOR (1/2) -#define ND_MAX_RANDOM_FACTOR (3/2) - #ifdef __KERNEL__ #include diff --git a/include/net/snmp.h b/include/net/snmp.h index aebb553..762e2ab 100644 --- a/include/net/snmp.h +++ b/include/net/snmp.h @@ -60,7 +60,6 @@ struct ipstats_mib { }; /* ICMP */ -#define ICMP_MIB_DUMMY __ICMP_MIB_MAX #define ICMP_MIB_MAX __ICMP_MIB_MAX struct icmp_mib { unsigned long mibs[ICMP_MIB_MAX]; diff --git a/include/net/sock.h b/include/net/sock.h index 5557dfb..717cfbf 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -516,9 +516,6 @@ static __inline__ void sk_add_bind_node(struct sock *sk, #define sk_nulls_for_each_from(__sk, node) \ if (__sk && ({ node = &(__sk)->sk_nulls_node; 1; })) \ hlist_nulls_for_each_entry_from(__sk, node, sk_nulls_node) -#define sk_for_each_continue(__sk, node) \ - if (__sk && ({ node = &(__sk)->sk_node; 1; })) \ - hlist_for_each_entry_continue(__sk, node, sk_node) #define sk_for_each_safe(__sk, node, tmp, list) \ hlist_for_each_entry_safe(__sk, node, tmp, list, sk_node) #define sk_for_each_bound(__sk, node, list) \ diff --git a/include/net/tcp.h b/include/net/tcp.h index 4097320..3f227ba 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -100,12 +100,6 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCP_SYNACK_RETRIES 5 /* number of times to retry passive opening a * connection: ~180sec is RFC minimum */ - -#define TCP_ORPHAN_RETRIES 7 /* number of times to retry on an orphaned - * socket. 7 is ~50sec-16min. - */ - - #define TCP_TIMEWAIT_LEN (60*HZ) /* how long to wait to destroy TIME-WAIT * state, about 60 seconds */ #define TCP_FIN_TIMEOUT TCP_TIMEWAIT_LEN -- cgit v1.1 From d265fef6ddf9042195aae551e1fde211c2a1588b Mon Sep 17 00:00:00 2001 From: Allan Stephens Date: Tue, 30 Nov 2010 12:00:53 +0000 Subject: tipc: Remove obsolete native API files and exports As part of the removal of TIPC's native API support it is no longer necessary for TIPC to export symbols for routines that can be called by kernel-based applications, nor for it to have header files that kernel-based applications can include to access the declarations for those routines. This commit eliminates the exporting of symbols by TIPC and migrates the contents of each obsolete native API include file into its corresponding non-native API equivalent. The code which was migrated in this commit was migrated intact, in that there are no technical changes combined with the relocation. Signed-off-by: Allan Stephens Signed-off-by: Paul Gortmaker Signed-off-by: David S. Miller --- include/net/tipc/tipc.h | 186 ------------------------------------ include/net/tipc/tipc_bearer.h | 138 --------------------------- include/net/tipc/tipc_msg.h | 207 ----------------------------------------- include/net/tipc/tipc_port.h | 101 -------------------- 4 files changed, 632 deletions(-) delete mode 100644 include/net/tipc/tipc.h delete mode 100644 include/net/tipc/tipc_bearer.h delete mode 100644 include/net/tipc/tipc_msg.h delete mode 100644 include/net/tipc/tipc_port.h (limited to 'include') diff --git a/include/net/tipc/tipc.h b/include/net/tipc/tipc.h deleted file mode 100644 index 1e0645e..0000000 --- a/include/net/tipc/tipc.h +++ /dev/null @@ -1,186 +0,0 @@ -/* - * include/net/tipc/tipc.h: Main include file for TIPC users - * - * Copyright (c) 2003-2006, Ericsson AB - * Copyright (c) 2005,2010 Wind River Systems - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the names of the copyright holders nor the names of its - * contributors may be used to endorse or promote products derived from - * this software without specific prior written permission. - * - * Alternatively, this software may be distributed under the terms of the - * GNU General Public License ("GPL") version 2 as published by the Free - * Software Foundation. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" - * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE - * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS - * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN - * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE - * POSSIBILITY OF SUCH DAMAGE. - */ - -#ifndef _NET_TIPC_H_ -#define _NET_TIPC_H_ - -#ifdef __KERNEL__ - -#include -#include - -/* - * Native API - */ - -/* - * TIPC operating mode routines - */ - -#define TIPC_NOT_RUNNING 0 -#define TIPC_NODE_MODE 1 -#define TIPC_NET_MODE 2 - -typedef void (*tipc_mode_event)(void *usr_handle, int mode, u32 addr); - -int tipc_attach(unsigned int *userref, tipc_mode_event, void *usr_handle); - -void tipc_detach(unsigned int userref); - -/* - * TIPC port manipulation routines - */ - -typedef void (*tipc_msg_err_event) (void *usr_handle, - u32 portref, - struct sk_buff **buf, - unsigned char const *data, - unsigned int size, - int reason, - struct tipc_portid const *attmpt_destid); - -typedef void (*tipc_named_msg_err_event) (void *usr_handle, - u32 portref, - struct sk_buff **buf, - unsigned char const *data, - unsigned int size, - int reason, - struct tipc_name_seq const *attmpt_dest); - -typedef void (*tipc_conn_shutdown_event) (void *usr_handle, - u32 portref, - struct sk_buff **buf, - unsigned char const *data, - unsigned int size, - int reason); - -typedef void (*tipc_msg_event) (void *usr_handle, - u32 portref, - struct sk_buff **buf, - unsigned char const *data, - unsigned int size, - unsigned int importance, - struct tipc_portid const *origin); - -typedef void (*tipc_named_msg_event) (void *usr_handle, - u32 portref, - struct sk_buff **buf, - unsigned char const *data, - unsigned int size, - unsigned int importance, - struct tipc_portid const *orig, - struct tipc_name_seq const *dest); - -typedef void (*tipc_conn_msg_event) (void *usr_handle, - u32 portref, - struct sk_buff **buf, - unsigned char const *data, - unsigned int size); - -typedef void (*tipc_continue_event) (void *usr_handle, - u32 portref); - -int tipc_createport(unsigned int tipc_user, - void *usr_handle, - unsigned int importance, - tipc_msg_err_event error_cb, - tipc_named_msg_err_event named_error_cb, - tipc_conn_shutdown_event conn_error_cb, - tipc_msg_event message_cb, - tipc_named_msg_event named_message_cb, - tipc_conn_msg_event conn_message_cb, - tipc_continue_event continue_event_cb, - u32 *portref); - -int tipc_deleteport(u32 portref); - -int tipc_ownidentity(u32 portref, struct tipc_portid *port); - -int tipc_portimportance(u32 portref, unsigned int *importance); -int tipc_set_portimportance(u32 portref, unsigned int importance); - -int tipc_portunreliable(u32 portref, unsigned int *isunreliable); -int tipc_set_portunreliable(u32 portref, unsigned int isunreliable); - -int tipc_portunreturnable(u32 portref, unsigned int *isunreturnable); -int tipc_set_portunreturnable(u32 portref, unsigned int isunreturnable); - -int tipc_publish(u32 portref, unsigned int scope, - struct tipc_name_seq const *name_seq); -int tipc_withdraw(u32 portref, unsigned int scope, - struct tipc_name_seq const *name_seq); - -int tipc_connect2port(u32 portref, struct tipc_portid const *port); - -int tipc_disconnect(u32 portref); - -int tipc_shutdown(u32 ref); - -/* - * TIPC messaging routines - */ - -#define TIPC_PORT_IMPORTANCE 100 /* send using current port setting */ - - -int tipc_send(u32 portref, - unsigned int num_sect, - struct iovec const *msg_sect); - -int tipc_send2name(u32 portref, - struct tipc_name const *name, - u32 domain, - unsigned int num_sect, - struct iovec const *msg_sect); - -int tipc_send2port(u32 portref, - struct tipc_portid const *dest, - unsigned int num_sect, - struct iovec const *msg_sect); - -int tipc_send_buf2port(u32 portref, - struct tipc_portid const *dest, - struct sk_buff *buf, - unsigned int dsz); - -int tipc_multicast(u32 portref, - struct tipc_name_seq const *seq, - u32 domain, /* currently unused */ - unsigned int section_count, - struct iovec const *msg); -#endif - -#endif diff --git a/include/net/tipc/tipc_bearer.h b/include/net/tipc/tipc_bearer.h deleted file mode 100644 index ee2f304..0000000 --- a/include/net/tipc/tipc_bearer.h +++ /dev/null @@ -1,138 +0,0 @@ -/* - * include/net/tipc/tipc_bearer.h: Include file for privileged access to TIPC bearers - * - * Copyright (c) 2003-2006, Ericsson AB - * Copyright (c) 2005, Wind River Systems - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the names of the copyright holders nor the names of its - * contributors may be used to endorse or promote products derived from - * this software without specific prior written permission. - * - * Alternatively, this software may be distributed under the terms of the - * GNU General Public License ("GPL") version 2 as published by the Free - * Software Foundation. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" - * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE - * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS - * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN - * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE - * POSSIBILITY OF SUCH DAMAGE. - */ - -#ifndef _NET_TIPC_BEARER_H_ -#define _NET_TIPC_BEARER_H_ - -#ifdef __KERNEL__ - -#include -#include -#include - -/* - * Identifiers of supported TIPC media types - */ - -#define TIPC_MEDIA_TYPE_ETH 1 - -/* - * Destination address structure used by TIPC bearers when sending messages - * - * IMPORTANT: The fields of this structure MUST be stored using the specified - * byte order indicated below, as the structure is exchanged between nodes - * as part of a link setup process. - */ - -struct tipc_media_addr { - __be32 type; /* bearer type (network byte order) */ - union { - __u8 eth_addr[6]; /* 48 bit Ethernet addr (byte array) */ -#if 0 - /* Prototypes for other possible bearer types */ - - struct { - __u16 sin_family; - __u16 sin_port; - struct { - __u32 s_addr; - } sin_addr; - char pad[4]; - } addr_in; /* IP-based bearer */ - __u16 sock_descr; /* generic socket bearer */ -#endif - } dev_addr; -}; - -/** - * struct tipc_bearer - TIPC bearer info available to privileged users - * @usr_handle: pointer to additional user-defined information about bearer - * @mtu: max packet size bearer can support - * @blocked: non-zero if bearer is blocked - * @lock: spinlock for controlling access to bearer - * @addr: media-specific address associated with bearer - * @name: bearer name (format = media:interface) - * - * Note: TIPC initializes "name" and "lock" fields; user is responsible for - * initialization all other fields when a bearer is enabled. - */ - -struct tipc_bearer { - void *usr_handle; - u32 mtu; - int blocked; - spinlock_t lock; - struct tipc_media_addr addr; - char name[TIPC_MAX_BEARER_NAME]; -}; - -/* - * TIPC routines available to supported media types - */ - -int tipc_register_media(u32 media_type, - char *media_name, - int (*enable)(struct tipc_bearer *), - void (*disable)(struct tipc_bearer *), - int (*send_msg)(struct sk_buff *, - struct tipc_bearer *, - struct tipc_media_addr *), - char *(*addr2str)(struct tipc_media_addr *a, - char *str_buf, - int str_size), - struct tipc_media_addr *bcast_addr, - const u32 bearer_priority, - const u32 link_tolerance, /* [ms] */ - const u32 send_window_limit); - -void tipc_recv_msg(struct sk_buff *buf, struct tipc_bearer *tb_ptr); - -int tipc_block_bearer(const char *name); -void tipc_continue(struct tipc_bearer *tb_ptr); - -int tipc_enable_bearer(const char *bearer_name, u32 bcast_scope, u32 priority); -int tipc_disable_bearer(const char *name); - -/* - * Routines made available to TIPC by supported media types - */ - -int tipc_eth_media_start(void); -void tipc_eth_media_stop(void); - -#endif - -#endif diff --git a/include/net/tipc/tipc_msg.h b/include/net/tipc/tipc_msg.h deleted file mode 100644 index ffe50b4..0000000 --- a/include/net/tipc/tipc_msg.h +++ /dev/null @@ -1,207 +0,0 @@ -/* - * include/net/tipc/tipc_msg.h: Include file for privileged access to TIPC message headers - * - * Copyright (c) 2003-2006, Ericsson AB - * Copyright (c) 2005, Wind River Systems - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the names of the copyright holders nor the names of its - * contributors may be used to endorse or promote products derived from - * this software without specific prior written permission. - * - * Alternatively, this software may be distributed under the terms of the - * GNU General Public License ("GPL") version 2 as published by the Free - * Software Foundation. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" - * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE - * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS - * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN - * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE - * POSSIBILITY OF SUCH DAMAGE. - */ - -#ifndef _NET_TIPC_MSG_H_ -#define _NET_TIPC_MSG_H_ - -#ifdef __KERNEL__ - -struct tipc_msg { - __be32 hdr[15]; -}; - - -/* - TIPC user data message header format, version 2: - - - 1 0 9 8 7 6 5 4|3 2 1 0 9 8 7 6|5 4 3 2 1 0 9 8|7 6 5 4 3 2 1 0 - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - w0:|vers | user |hdr sz |n|d|s|-| message size | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - w1:|mstyp| error |rer cnt|lsc|opt p| broadcast ack no | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - w2:| link level ack no | broadcast/link level seq no | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - w3:| previous node | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - w4:| originating port | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - w5:| destination port | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - w6:| originating node | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - w7:| destination node | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - w8:| name type / transport sequence number | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - w9:| name instance/multicast lower bound | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - wA:| multicast upper bound | - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - / / - \ options \ - / / - +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - -*/ - -#define TIPC_CONN_MSG 0 -#define TIPC_MCAST_MSG 1 -#define TIPC_NAMED_MSG 2 -#define TIPC_DIRECT_MSG 3 - - -static inline u32 msg_word(struct tipc_msg *m, u32 pos) -{ - return ntohl(m->hdr[pos]); -} - -static inline u32 msg_bits(struct tipc_msg *m, u32 w, u32 pos, u32 mask) -{ - return (msg_word(m, w) >> pos) & mask; -} - -static inline u32 msg_importance(struct tipc_msg *m) -{ - return msg_bits(m, 0, 25, 0xf); -} - -static inline u32 msg_hdr_sz(struct tipc_msg *m) -{ - return msg_bits(m, 0, 21, 0xf) << 2; -} - -static inline int msg_short(struct tipc_msg *m) -{ - return msg_hdr_sz(m) == 24; -} - -static inline u32 msg_size(struct tipc_msg *m) -{ - return msg_bits(m, 0, 0, 0x1ffff); -} - -static inline u32 msg_data_sz(struct tipc_msg *m) -{ - return msg_size(m) - msg_hdr_sz(m); -} - -static inline unchar *msg_data(struct tipc_msg *m) -{ - return ((unchar *)m) + msg_hdr_sz(m); -} - -static inline u32 msg_type(struct tipc_msg *m) -{ - return msg_bits(m, 1, 29, 0x7); -} - -static inline u32 msg_named(struct tipc_msg *m) -{ - return msg_type(m) == TIPC_NAMED_MSG; -} - -static inline u32 msg_mcast(struct tipc_msg *m) -{ - return msg_type(m) == TIPC_MCAST_MSG; -} - -static inline u32 msg_connected(struct tipc_msg *m) -{ - return msg_type(m) == TIPC_CONN_MSG; -} - -static inline u32 msg_errcode(struct tipc_msg *m) -{ - return msg_bits(m, 1, 25, 0xf); -} - -static inline u32 msg_prevnode(struct tipc_msg *m) -{ - return msg_word(m, 3); -} - -static inline u32 msg_origport(struct tipc_msg *m) -{ - return msg_word(m, 4); -} - -static inline u32 msg_destport(struct tipc_msg *m) -{ - return msg_word(m, 5); -} - -static inline u32 msg_mc_netid(struct tipc_msg *m) -{ - return msg_word(m, 5); -} - -static inline u32 msg_orignode(struct tipc_msg *m) -{ - if (likely(msg_short(m))) - return msg_prevnode(m); - return msg_word(m, 6); -} - -static inline u32 msg_destnode(struct tipc_msg *m) -{ - return msg_word(m, 7); -} - -static inline u32 msg_nametype(struct tipc_msg *m) -{ - return msg_word(m, 8); -} - -static inline u32 msg_nameinst(struct tipc_msg *m) -{ - return msg_word(m, 9); -} - -static inline u32 msg_namelower(struct tipc_msg *m) -{ - return msg_nameinst(m); -} - -static inline u32 msg_nameupper(struct tipc_msg *m) -{ - return msg_word(m, 10); -} - -#endif - -#endif diff --git a/include/net/tipc/tipc_port.h b/include/net/tipc/tipc_port.h deleted file mode 100644 index 1893aaf..0000000 --- a/include/net/tipc/tipc_port.h +++ /dev/null @@ -1,101 +0,0 @@ -/* - * include/net/tipc/tipc_port.h: Include file for privileged access to TIPC ports - * - * Copyright (c) 1994-2007, Ericsson AB - * Copyright (c) 2005-2008, Wind River Systems - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the names of the copyright holders nor the names of its - * contributors may be used to endorse or promote products derived from - * this software without specific prior written permission. - * - * Alternatively, this software may be distributed under the terms of the - * GNU General Public License ("GPL") version 2 as published by the Free - * Software Foundation. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" - * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE - * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS - * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN - * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE - * POSSIBILITY OF SUCH DAMAGE. - */ - -#ifndef _NET_TIPC_PORT_H_ -#define _NET_TIPC_PORT_H_ - -#ifdef __KERNEL__ - -#include -#include -#include - -#define TIPC_FLOW_CONTROL_WIN 512 - -/** - * struct tipc_port - native TIPC port info available to privileged users - * @usr_handle: pointer to additional user-defined information about port - * @lock: pointer to spinlock for controlling access to port - * @connected: non-zero if port is currently connected to a peer port - * @conn_type: TIPC type used when connection was established - * @conn_instance: TIPC instance used when connection was established - * @conn_unacked: number of unacknowledged messages received from peer port - * @published: non-zero if port has one or more associated names - * @congested: non-zero if cannot send because of link or port congestion - * @max_pkt: maximum packet size "hint" used when building messages sent by port - * @ref: unique reference to port in TIPC object registry - * @phdr: preformatted message header used when sending messages - */ - -struct tipc_port { - void *usr_handle; - spinlock_t *lock; - int connected; - u32 conn_type; - u32 conn_instance; - u32 conn_unacked; - int published; - u32 congested; - u32 max_pkt; - u32 ref; - struct tipc_msg phdr; -}; - - -struct tipc_port *tipc_createport_raw(void *usr_handle, - u32 (*dispatcher)(struct tipc_port *, struct sk_buff *), - void (*wakeup)(struct tipc_port *), - const u32 importance); - -int tipc_reject_msg(struct sk_buff *buf, u32 err); - -int tipc_send_buf_fast(struct sk_buff *buf, u32 destnode); - -void tipc_acknowledge(u32 port_ref,u32 ack); - -struct tipc_port *tipc_get_port(const u32 ref); - -/* - * The following routines require that the port be locked on entry - */ - -int tipc_disconnect_port(struct tipc_port *tp_ptr); - - -#endif - -#endif - -- cgit v1.1 From 87de5ac782761a3ebf806e434e8c9cc205a87274 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Mon, 20 Sep 2010 17:42:46 -0700 Subject: timers: Introduce timerlist infrastructure. The timerlist infrastructure is a thin layer over the rbtree code that implements a simple list of timers sorted by an expires value, and a getnext function that provides a pointer to the earliest timer. This infrastructure allows drivers and other kernel infrastructure to easily implement timers without duplicating code. Signed-off-by: John Stultz LKML Reference: <1290136329-18291-2-git-send-email-john.stultz@linaro.org> Reviewed-by: Thomas Gleixner CC: Alessandro Zummo CC: Thomas Gleixner CC: Richard Cochran --- include/linux/timerlist.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) create mode 100644 include/linux/timerlist.h (limited to 'include') diff --git a/include/linux/timerlist.h b/include/linux/timerlist.h new file mode 100644 index 0000000..c46b28a --- /dev/null +++ b/include/linux/timerlist.h @@ -0,0 +1,37 @@ +#ifndef _LINUX_TIMERLIST_H +#define _LINUX_TIMERLIST_H + +#include +#include + + +struct timerlist_node { + struct rb_node node; + ktime_t expires; +}; + +struct timerlist_head { + struct rb_root head; + struct timerlist_node *next; +}; + + +extern void timerlist_add(struct timerlist_head *head, + struct timerlist_node *node); +extern void timerlist_del(struct timerlist_head *head, + struct timerlist_node *node); +extern struct timerlist_node *timerlist_getnext(struct timerlist_head *head); +extern struct timerlist_node *timerlist_iterate_next( + struct timerlist_node *node); + +static inline void timerlist_init(struct timerlist_node *node) +{ + RB_CLEAR_NODE(&node->node); +} + +static inline void timerlist_init_head(struct timerlist_head *head) +{ + head->head = RB_ROOT; + head->next = NULL; +} +#endif /* _LINUX_TIMERLIST_H */ -- cgit v1.1 From 21e86c1c8a844bf978f8fc431a59c9f5a578812d Mon Sep 17 00:00:00 2001 From: Ben Skeggs Date: Mon, 11 Oct 2010 11:48:45 +1000 Subject: drm/nouveau: remove cpu_writers lock No other driver uses this, and userspace should be responsible for handling locking between them if they share BOs. Signed-off-by: Ben Skeggs --- include/drm/nouveau_drm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/drm/nouveau_drm.h b/include/drm/nouveau_drm.h index bc5590b..60a7b3e 100644 --- a/include/drm/nouveau_drm.h +++ b/include/drm/nouveau_drm.h @@ -171,7 +171,6 @@ struct drm_nouveau_gem_pushbuf { }; #define NOUVEAU_GEM_CPU_PREP_NOWAIT 0x00000001 -#define NOUVEAU_GEM_CPU_PREP_NOBLOCK 0x00000002 #define NOUVEAU_GEM_CPU_PREP_WRITE 0x00000004 struct drm_nouveau_gem_cpu_prep { uint32_t handle; -- cgit v1.1 From 332b242f47786d1a43bd7a19a0513dd5d493db8e Mon Sep 17 00:00:00 2001 From: Francisco Jerez Date: Wed, 20 Oct 2010 23:35:40 +0200 Subject: drm/nouveau: Implement the pageflip ioctl. nv0x-nv4x should be mostly fine, nv50 doesn't work yet. Signed-off-by: Francisco Jerez Signed-off-by: Ben Skeggs --- include/drm/nouveau_drm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/drm/nouveau_drm.h b/include/drm/nouveau_drm.h index 60a7b3e..39aa0fd 100644 --- a/include/drm/nouveau_drm.h +++ b/include/drm/nouveau_drm.h @@ -81,6 +81,7 @@ struct drm_nouveau_gpuobj_free { #define NOUVEAU_GETPARAM_GRAPH_UNITS 13 #define NOUVEAU_GETPARAM_PTIMER_TIME 14 #define NOUVEAU_GETPARAM_HAS_BO_USAGE 15 +#define NOUVEAU_GETPARAM_HAS_PAGEFLIP 16 struct drm_nouveau_getparam { uint64_t param; uint64_t value; -- cgit v1.1 From 6d6c5a157af45a5bd50ab913b07d826811a9ea0a Mon Sep 17 00:00:00 2001 From: Ben Skeggs Date: Tue, 16 Nov 2010 10:17:53 +1000 Subject: drm/nouveau: remove some useless GETPARAMs These have been unused since UMS support was ripped out, so lets remove them completely. Signed-off-by: Ben Skeggs --- include/drm/nouveau_drm.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/drm/nouveau_drm.h b/include/drm/nouveau_drm.h index 39aa0fd..e2cfe80 100644 --- a/include/drm/nouveau_drm.h +++ b/include/drm/nouveau_drm.h @@ -71,11 +71,8 @@ struct drm_nouveau_gpuobj_free { #define NOUVEAU_GETPARAM_PCI_VENDOR 3 #define NOUVEAU_GETPARAM_PCI_DEVICE 4 #define NOUVEAU_GETPARAM_BUS_TYPE 5 -#define NOUVEAU_GETPARAM_FB_PHYSICAL 6 -#define NOUVEAU_GETPARAM_AGP_PHYSICAL 7 #define NOUVEAU_GETPARAM_FB_SIZE 8 #define NOUVEAU_GETPARAM_AGP_SIZE 9 -#define NOUVEAU_GETPARAM_PCI_PHYSICAL 10 #define NOUVEAU_GETPARAM_CHIPSET_ID 11 #define NOUVEAU_GETPARAM_VM_VRAM_BASE 12 #define NOUVEAU_GETPARAM_GRAPH_UNITS 13 -- cgit v1.1 From f689b34bfbd2154a8fa255060dd872a6db3b4742 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Miloslav=20Trma=C4=8D?= Date: Fri, 3 Dec 2010 13:51:52 +0800 Subject: include: Install linux/if_alg.h for user-space crypto API MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Miloslav Trmač Signed-off-by: Herbert Xu --- include/linux/Kbuild | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 831c463..b3cca8c 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -154,6 +154,7 @@ header-y += icmpv6.h header-y += if.h header-y += if_addr.h header-y += if_addrlabel.h +header-y += if_alg.h header-y += if_arcnet.h header-y += if_arp.h header-y += if_bonding.h -- cgit v1.1 From 287050d390264402e11bea8b811859e42e8faa29 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 2 Dec 2010 16:46:18 -0500 Subject: tracing: Add TRACE_EVENT_CONDITIONAL() There are instances in the kernel that we only want to trace a tracepoint when a certain condition is set. But we do not want to test for that condition in the core kernel. If we test for that condition before calling the tracepoin, then we will be performing that test even when tracing is not enabled. This is 99.99% of the time. We currently can just filter out on that condition, but that happens after we write to the trace buffer. We just wasted time writing to the ring buffer for an event we never cared about. This patch adds: TRACE_EVENT_CONDITION() and DEFINE_EVENT_CONDITION() These have a new TP_CONDITION() argument that comes right after the TP_ARGS(). This condition can use the parameters of TP_ARGS() in the TRACE_EVENT() to determine if the tracepoint should be traced or not. The TP_CONDITION() will be placed in a if (cond) trace; For example, for the tracepoint sched_wakeup, it is useless to trace a wakeup event where the caller never actually wakes anything up (where success == 0). So adding: TP_CONDITION(success), which uses the "success" parameter of the wakeup tracepoint will have it only trace when we have successfully woken up a task. Acked-by: Mathieu Desnoyers Acked-by: Frederic Weisbecker Cc: Arjan van de Ven Cc: Thomas Gleixner Signed-off-by: Steven Rostedt --- include/linux/tracepoint.h | 29 +++++++++++++++++++++++------ include/trace/define_trace.h | 15 +++++++++++++++ 2 files changed, 38 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 5a6074f..d3e4f87 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -106,6 +106,7 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin, #define TP_PROTO(args...) args #define TP_ARGS(args...) args +#define TP_CONDITION(args...) args #ifdef CONFIG_TRACEPOINTS @@ -119,12 +120,14 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin, * as "(void *, void)". The DECLARE_TRACE_NOARGS() will pass in just * "void *data", where as the DECLARE_TRACE() will pass in "void *data, proto". */ -#define __DO_TRACE(tp, proto, args) \ +#define __DO_TRACE(tp, proto, args, cond) \ do { \ struct tracepoint_func *it_func_ptr; \ void *it_func; \ void *__data; \ \ + if (!(cond)) \ + return; \ rcu_read_lock_sched_notrace(); \ it_func_ptr = rcu_dereference_sched((tp)->funcs); \ if (it_func_ptr) { \ @@ -142,7 +145,7 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin, * not add unwanted padding between the beginning of the section and the * structure. Force alignment to the same alignment as the section start. */ -#define __DECLARE_TRACE(name, proto, args, data_proto, data_args) \ +#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \ extern struct tracepoint __tracepoint_##name; \ static inline void trace_##name(proto) \ { \ @@ -151,7 +154,8 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin, do_trace: \ __DO_TRACE(&__tracepoint_##name, \ TP_PROTO(data_proto), \ - TP_ARGS(data_args)); \ + TP_ARGS(data_args), \ + TP_CONDITION(cond)); \ } \ static inline int \ register_trace_##name(void (*probe)(data_proto), void *data) \ @@ -186,7 +190,7 @@ do_trace: \ EXPORT_SYMBOL(__tracepoint_##name) #else /* !CONFIG_TRACEPOINTS */ -#define __DECLARE_TRACE(name, proto, args, data_proto, data_args) \ +#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \ static inline void trace_##name(proto) \ { } \ static inline int \ @@ -227,13 +231,18 @@ do_trace: \ * "void *__data, proto" as the callback prototype. */ #define DECLARE_TRACE_NOARGS(name) \ - __DECLARE_TRACE(name, void, , void *__data, __data) + __DECLARE_TRACE(name, void, , 1, void *__data, __data) #define DECLARE_TRACE(name, proto, args) \ - __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), \ + __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), 1, \ PARAMS(void *__data, proto), \ PARAMS(__data, args)) +#define DECLARE_TRACE_CONDITION(name, proto, args, cond) \ + __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), PARAMS(cond), \ + PARAMS(void *__data, proto), \ + PARAMS(__data, args)) + #define TRACE_EVENT_FLAGS(event, flag) #endif /* DECLARE_TRACE */ @@ -349,12 +358,20 @@ do_trace: \ DECLARE_TRACE(name, PARAMS(proto), PARAMS(args)) #define DEFINE_EVENT_PRINT(template, name, proto, args, print) \ DECLARE_TRACE(name, PARAMS(proto), PARAMS(args)) +#define DEFINE_EVENT_CONDITION(template, name, proto, \ + args, cond) \ + DECLARE_TRACE_CONDITION(name, PARAMS(proto), \ + PARAMS(args), PARAMS(cond)) #define TRACE_EVENT(name, proto, args, struct, assign, print) \ DECLARE_TRACE(name, PARAMS(proto), PARAMS(args)) #define TRACE_EVENT_FN(name, proto, args, struct, \ assign, print, reg, unreg) \ DECLARE_TRACE(name, PARAMS(proto), PARAMS(args)) +#define TRACE_EVENT_CONDITION(name, proto, args, cond, \ + struct, assign, print) \ + DECLARE_TRACE_CONDITION(name, PARAMS(proto), \ + PARAMS(args), PARAMS(cond)) #define TRACE_EVENT_FLAGS(event, flag) diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h index 1dfab54..b0b4eb2 100644 --- a/include/trace/define_trace.h +++ b/include/trace/define_trace.h @@ -26,6 +26,15 @@ #define TRACE_EVENT(name, proto, args, tstruct, assign, print) \ DEFINE_TRACE(name) +#undef TRACE_EVENT_CONDITION +#define TRACE_EVENT_CONDITION(name, proto, args, cond, tstruct, assign, print) \ + TRACE_EVENT(name, \ + PARAMS(proto), \ + PARAMS(args), \ + PARAMS(tstruct), \ + PARAMS(assign), \ + PARAMS(print)) + #undef TRACE_EVENT_FN #define TRACE_EVENT_FN(name, proto, args, tstruct, \ assign, print, reg, unreg) \ @@ -39,6 +48,10 @@ #define DEFINE_EVENT_PRINT(template, name, proto, args, print) \ DEFINE_TRACE(name) +#undef DEFINE_EVENT_CONDITION +#define DEFINE_EVENT_CONDITION(template, name, proto, args, cond) \ + DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args)) + #undef DECLARE_TRACE #define DECLARE_TRACE(name, proto, args) \ DEFINE_TRACE(name) @@ -75,9 +88,11 @@ #undef TRACE_EVENT #undef TRACE_EVENT_FN +#undef TRACE_EVENT_CONDITION #undef DECLARE_EVENT_CLASS #undef DEFINE_EVENT #undef DEFINE_EVENT_PRINT +#undef DEFINE_EVENT_CONDITION #undef TRACE_HEADER_MULTI_READ #undef DECLARE_TRACE -- cgit v1.1 From 3e3198f1adda8e0fbd499bde806781237d6c841f Mon Sep 17 00:00:00 2001 From: Roman Tereshonkov Date: Wed, 3 Nov 2010 12:55:19 +0200 Subject: mtd: onenand: add option and variable for cache program feature A new option is added for cache program feature. A new variable ongoing is introduced for onenand_chip to handle the multi-command cache program operation. Signed-off-by: Roman Tereshonkov Acked-by: Kyungmin Park Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/onenand.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/mtd/onenand.h b/include/linux/mtd/onenand.h index 0c8815b..6da3fe3 100644 --- a/include/linux/mtd/onenand.h +++ b/include/linux/mtd/onenand.h @@ -137,6 +137,14 @@ struct onenand_chip { void *bbm; void *priv; + + /* + * Shows that the current operation is composed + * of sequence of commands. For example, cache program. + * Such command status OnGo bit is checked at the end of + * sequence. + */ + unsigned int ongoing; }; /* @@ -171,6 +179,9 @@ struct onenand_chip { #define ONENAND_IS_2PLANE(this) (0) #endif +#define ONENAND_IS_CACHE_PROGRAM(this) \ + (this->options & ONENAND_HAS_CACHE_PROGRAM) + /* Check byte access in OneNAND */ #define ONENAND_CHECK_BYTE_ACCESS(addr) (addr & 0x1) @@ -181,6 +192,7 @@ struct onenand_chip { #define ONENAND_HAS_UNLOCK_ALL (0x0002) #define ONENAND_HAS_2PLANE (0x0004) #define ONENAND_HAS_4KB_PAGE (0x0008) +#define ONENAND_HAS_CACHE_PROGRAM (0x0010) #define ONENAND_SKIP_UNLOCK_CHECK (0x0100) #define ONENAND_PAGEBUF_ALLOC (0x1000) #define ONENAND_OOBBUF_ALLOC (0x2000) -- cgit v1.1 From 65ab220c30bc2120eaa39753cadec68616e3f906 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Mon, 8 Nov 2010 11:17:54 +0530 Subject: mtd: fsmc.h: including linux/io.h for definition of readl Signed-off-by: Viresh Kumar Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/fsmc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mtd/fsmc.h b/include/linux/mtd/fsmc.h index 5d25567..e210b87 100644 --- a/include/linux/mtd/fsmc.h +++ b/include/linux/mtd/fsmc.h @@ -16,6 +16,7 @@ #ifndef __MTD_FSMC_H #define __MTD_FSMC_H +#include #include #include #include -- cgit v1.1 From cc31822250236ec173bb2aa149ebe2ba35405db2 Mon Sep 17 00:00:00 2001 From: Guillaume LECERF Date: Wed, 17 Nov 2010 12:35:50 +0100 Subject: mtd: cfi_fixup: remove unused 'param' parameter The 'param' parameter has never been used since its introduction, so simply remove it. Signed-off-by: Guillaume LECERF Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/cfi.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h index 4dd0c2c..a9baee6 100644 --- a/include/linux/mtd/cfi.h +++ b/include/linux/mtd/cfi.h @@ -527,8 +527,7 @@ struct cfi_extquery *cfi_read_pri(struct map_info *map, uint16_t adr, uint16_t s struct cfi_fixup { uint16_t mfr; uint16_t id; - void (*fixup)(struct mtd_info *mtd, void* param); - void* param; + void (*fixup)(struct mtd_info *mtd); }; #define CFI_MFR_ANY 0xFFFF -- cgit v1.1 From 1534b8b09757190ce6e97fa97f9ad77c49082cd8 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 18 Nov 2010 15:02:21 -0800 Subject: mtd: fix nand kernel-doc warnings Warning(include/linux/mtd/nand.h:543): No description found for parameter 'badblockbits' Warning(drivers/mtd/nand/nand_bbt.c:1101): No description found for parameter 'mtd' Signed-off-by: Randy Dunlap Cc: David Woodhouse Cc: linux-mtd@lists.infradead.org Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/nand.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 63e17d0..1f489b2 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -448,6 +448,8 @@ struct nand_buffers { * See the defines for further explanation. * @badblockpos: [INTERN] position of the bad block marker in the oob * area. + * @badblockbits: [INTERN] number of bits to left-shift the bad block + * number * @cellinfo: [INTERN] MLC/multichip data from chip ident * @numchips: [INTERN] number of physical chips * @chipsize: [INTERN] the size of one chip for multichip arrays -- cgit v1.1 From a7e93dcd9aacb3ef4acfcc4310577f3ae0741821 Mon Sep 17 00:00:00 2001 From: Roman Tereshonkov Date: Tue, 23 Nov 2010 14:17:17 +0200 Subject: mtd: fix master device identification for mtd repartition Function mtd_has_master renamed as mtd_is_partition to follow the function logic. The patch fixes the problem of checking the right mtd device for partition creation. To delete partition checking is not needed here so as it is done in mtd_del_partition. By master we consider the mtd device which does not belong to any partition. Signed-off-by: Roman Tereshonkov Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/partitions.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index 2b54316..4a0a8ba 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -89,7 +89,7 @@ static inline int mtd_has_cmdlinepart(void) { return 1; } static inline int mtd_has_cmdlinepart(void) { return 0; } #endif -int mtd_is_master(struct mtd_info *mtd); +int mtd_is_partition(struct mtd_info *mtd); int mtd_add_partition(struct mtd_info *master, char *name, long long offset, long long length); int mtd_del_partition(struct mtd_info *master, int partno); -- cgit v1.1 From 593cd8711221c9661dbf9beb2fb42fecca03e693 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 29 Nov 2010 13:52:19 +0100 Subject: mtd: FSMC NAND use the PrimeCell identifier macros The FSMC actually has a standard ARM PrimeCell ID register, and the "revision" part of that register contains the thing that the code is looking at. Reuse the infrastructure from the AMBA bus abstraction and rid local defines. Signed-off-by: Linus Walleij Signed-off-by: David Woodhouse --- include/linux/mtd/fsmc.h | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/fsmc.h b/include/linux/mtd/fsmc.h index e210b87..96e8e67 100644 --- a/include/linux/mtd/fsmc.h +++ b/include/linux/mtd/fsmc.h @@ -115,25 +115,6 @@ struct fsmc_regs { #define FSMC_THOLD_4 (4 << 16) #define FSMC_THIZ_1 (1 << 24) -/* peripid2 register definitions */ -#define FSMC_REVISION_MSK (0xf) -#define FSMC_REVISION_SHFT (0x4) - -#define FSMC_VER1 1 -#define FSMC_VER2 2 -#define FSMC_VER3 3 -#define FSMC_VER4 4 -#define FSMC_VER5 5 -#define FSMC_VER6 6 -#define FSMC_VER7 7 -#define FSMC_VER8 8 - -static inline uint32_t get_fsmc_version(struct fsmc_regs *regs) -{ - return (readl(®s->peripid2) >> FSMC_REVISION_SHFT) & - FSMC_REVISION_MSK; -} - /* * There are 13 bytes of ecc for every 512 byte block in FSMC version 8 * and it has to be read consecutively and immediately after the 512 -- cgit v1.1 From b5602e86432aaf0cc90dd207bf74e3a2bfb5078b Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 29 Nov 2010 13:52:27 +0100 Subject: mtd: FSMC NAND fix obvious speling errors Fix spelling in the interface file. Signed-off-by: Linus Walleij Signed-off-by: David Woodhouse --- include/linux/mtd/fsmc.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mtd/fsmc.h b/include/linux/mtd/fsmc.h index 96e8e67..6987995 100644 --- a/include/linux/mtd/fsmc.h +++ b/include/linux/mtd/fsmc.h @@ -28,7 +28,7 @@ /* * The placement of the Command Latch Enable (CLE) and - * Address Latch Enable (ALE) is twised around in the + * Address Latch Enable (ALE) is twisted around in the * SPEAR310 implementation. */ #if defined(CONFIG_MACH_SPEAR310) @@ -63,7 +63,7 @@ struct fsmc_nor_bank_regs { /* ctrl_tim register definitions */ -struct fsms_nand_bank_regs { +struct fsmc_nand_bank_regs { uint32_t pc; uint32_t sts; uint32_t comm; @@ -79,7 +79,7 @@ struct fsms_nand_bank_regs { struct fsmc_regs { struct fsmc_nor_bank_regs nor_bank_regs[FSMC_MAX_NOR_BANKS]; uint8_t reserved_1[0x40 - 0x20]; - struct fsms_nand_bank_regs bank_regs[FSMC_MAX_NAND_BANKS]; + struct fsmc_nand_bank_regs bank_regs[FSMC_MAX_NAND_BANKS]; uint8_t reserved_2[0xfe0 - 0xc0]; uint32_t peripid0; /* 0xfe0 */ uint32_t peripid1; /* 0xfe4 */ -- cgit v1.1 From 6844c09d849aeb00e8ddfe9525e8567a531c22d0 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 3 Dec 2010 16:36:35 -0200 Subject: perf events: Separate the routines handling the PERF_SAMPLE_ identity fields MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Those will be made available in sample like events like MMAP, EXEC, etc in a followup patch. So precalculate the extra id header space and have a separate routine to fill them up. V2: Thomas noticed that the id header needs to be precalculated at inherit_events too: LKML-Reference: Tested-by: Thomas Gleixner Reviewed-by: Thomas Gleixner Acked-by: Ian Munsie Acked-by: Peter Zijlstra Acked-by: Thomas Gleixner Cc: Frédéric Weisbecker Cc: Ian Munsie Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Stephane Eranian Cc: Thomas Gleixner LKML-Reference: <1291318772-30880-2-git-send-email-acme@infradead.org> Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index adf6d99..b9950b1 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -759,6 +759,7 @@ struct perf_event { struct perf_event_attr attr; u16 header_size; + u16 id_header_size; u16 read_size; struct hw_perf_event hw; -- cgit v1.1 From c980d1091810df13f21aabbce545fd98f545bbf7 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sat, 4 Dec 2010 23:02:20 -0200 Subject: perf events: Make sample_type identity fields available in all PERF_RECORD_ events MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If perf_event_attr.sample_id_all is set it will add the PERF_SAMPLE_ identity info: TID, TIME, ID, CPU, STREAM_ID As a trailer, so that older perf tools can process new files, just ignoring the extra payload. With this its possible to do further analysis on problems in the event stream, like detecting reordering of MMAP and FORK events, etc. V2: Fixup header size in comm, mmap and task processing, as we have to take into account different sample_types for each matching event, noticed by Thomas Gleixner. Thomas also noticed a problem in v2 where if we didn't had space in the buffer we wouldn't restore the header size. Tested-by: Thomas Gleixner Reviewed-by: Thomas Gleixner Acked-by: Ian Munsie Acked-by: Peter Zijlstra Acked-by: Thomas Gleixner Cc: Frédéric Weisbecker Cc: Ian Munsie Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Stephane Eranian Cc: Thomas Gleixner LKML-Reference: Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index b9950b1..2814ead 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -215,8 +215,9 @@ struct perf_event_attr { */ precise_ip : 2, /* skid constraint */ mmap_data : 1, /* non-exec mmap data */ + sample_id_all : 1, /* sample_type all events */ - __reserved_1 : 46; + __reserved_1 : 45; union { __u32 wakeup_events; /* wakeup every n events */ @@ -327,6 +328,15 @@ struct perf_event_header { enum perf_event_type { /* + * If perf_event_attr.sample_id_all is set then all event types will + * have the sample_type selected fields related to where/when + * (identity) an event took place (TID, TIME, ID, CPU, STREAM_ID) + * described in PERF_RECORD_SAMPLE below, it will be stashed just after + * the perf_event_header and the fields already present for the existing + * fields, i.e. at the end of the payload. That way a newer perf.data + * file will be supported by older perf tools, with these new optional + * fields being ignored. + * * The MMAP events record the PROT_EXEC mappings so that we can * correlate userspace IPs to code. They have the following structure: * -- cgit v1.1 From bbf0c6b3620b3872929ef7d3c392ce436889110f Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Sun, 5 Dec 2010 11:30:40 +0100 Subject: drm/i915: announce to userspace that the bsd ring is coherent Otherwise we can't really fix the abi-braindeadness of forcing libva to manually wait for rendering when switching rings. Which in turn makes implementing hw semaphores a pointless exercise (at least for ironlake). [Also added the relaxed fencing param to explain the jump in numbering - relaxed fencing is in -next.] Signed-off-by: Daniel Vetter Signed-off-by: Chris Wilson --- include/drm/i915_drm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h index 8c641be..a2776e2 100644 --- a/include/drm/i915_drm.h +++ b/include/drm/i915_drm.h @@ -287,6 +287,8 @@ typedef struct drm_i915_irq_wait { #define I915_PARAM_HAS_EXECBUF2 9 #define I915_PARAM_HAS_BSD 10 #define I915_PARAM_HAS_BLT 11 +#define I915_PARAM_HAS_RELAXED_FENCING 12 +#define I915_PARAM_HAS_COHERENT_RINGS 13 typedef struct drm_i915_getparam { int param; -- cgit v1.1 From cd7ebe2298ff1c3112232878678ce5fe6be8a15b Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 3 Dec 2010 18:54:28 +0900 Subject: kprobes: Use text_poke_smp_batch for optimizing Use text_poke_smp_batch() in optimization path for reducing the number of stop_machine() issues. If the number of optimizing probes is more than MAX_OPTIMIZE_PROBES(=256), kprobes optimizes first MAX_OPTIMIZE_PROBES probes and kicks optimizer for remaining probes. Changes in v5: - Use kick_kprobe_optimizer() instead of directly calling schedule_delayed_work(). - Rescheduling optimizer outside of kprobe mutex lock. Changes in v2: - Allocate code buffer and parameters in arch_init_kprobes() instead of using static arraies. - Merge previous max optimization limit patch into this patch. So, this patch introduces upper limit of optimization at once. Signed-off-by: Masami Hiramatsu Cc: Rusty Russell Cc: Frederic Weisbecker Cc: Ananth N Mavinakayanahalli Cc: Jason Baron Cc: Mathieu Desnoyers Cc: 2nddept-manager@sdl.hitachi.co.jp Cc: Peter Zijlstra Cc: Steven Rostedt LKML-Reference: <20101203095428.2961.8994.stgit@ltc236.sdl.hitachi.co.jp> Signed-off-by: Ingo Molnar --- include/linux/kprobes.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index e7d1b2e..fe157ba 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -275,7 +275,7 @@ extern int arch_prepared_optinsn(struct arch_optimized_insn *optinsn); extern int arch_check_optimized_kprobe(struct optimized_kprobe *op); extern int arch_prepare_optimized_kprobe(struct optimized_kprobe *op); extern void arch_remove_optimized_kprobe(struct optimized_kprobe *op); -extern int arch_optimize_kprobe(struct optimized_kprobe *op); +extern void arch_optimize_kprobes(struct list_head *oplist); extern void arch_unoptimize_kprobe(struct optimized_kprobe *op); extern kprobe_opcode_t *get_optinsn_slot(void); extern void free_optinsn_slot(kprobe_opcode_t *slot, int dirty); -- cgit v1.1 From f984ba4eb575e4a27ed28a76d4126d2aa9233c32 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 3 Dec 2010 18:54:34 +0900 Subject: kprobes: Use text_poke_smp_batch for unoptimizing Use text_poke_smp_batch() on unoptimization path for reducing the number of stop_machine() issues. If the number of unoptimizing probes is more than MAX_OPTIMIZE_PROBES(=256), kprobes unoptimizes first MAX_OPTIMIZE_PROBES probes and kicks optimizer for remaining probes. Signed-off-by: Masami Hiramatsu Cc: Rusty Russell Cc: Frederic Weisbecker Cc: Ananth N Mavinakayanahalli Cc: Jason Baron Cc: Mathieu Desnoyers Cc: 2nddept-manager@sdl.hitachi.co.jp Cc: Peter Zijlstra Cc: Steven Rostedt LKML-Reference: <20101203095434.2961.22657.stgit@ltc236.sdl.hitachi.co.jp> Signed-off-by: Ingo Molnar --- include/linux/kprobes.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index fe157ba..b78edb5 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -276,6 +276,8 @@ extern int arch_check_optimized_kprobe(struct optimized_kprobe *op); extern int arch_prepare_optimized_kprobe(struct optimized_kprobe *op); extern void arch_remove_optimized_kprobe(struct optimized_kprobe *op); extern void arch_optimize_kprobes(struct list_head *oplist); +extern void arch_unoptimize_kprobes(struct list_head *oplist, + struct list_head *done_list); extern void arch_unoptimize_kprobe(struct optimized_kprobe *op); extern kprobe_opcode_t *get_optinsn_slot(void); extern void free_optinsn_slot(kprobe_opcode_t *slot, int dirty); -- cgit v1.1 From 46bcf14f44d8f31ecfdc8b6708ec15a3b33316d9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 6 Dec 2010 09:29:43 -0800 Subject: filter: fix sk_filter rcu handling Pavel Emelyanov tried to fix a race between sk_filter_(de|at)tach and sk_clone() in commit 47e958eac280c263397 Problem is we can have several clones sharing a common sk_filter, and these clones might want to sk_filter_attach() their own filters at the same time, and can overwrite old_filter->rcu, corrupting RCU queues. We can not use filter->rcu without being sure no other thread could do the same thing. Switch code to a more conventional ref-counting technique : Do the atomic decrement immediately and queue one rcu call back when last reference is released. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index a6338d0..659d968 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1155,6 +1155,8 @@ extern void sk_common_release(struct sock *sk); /* Initialise core socket variables */ extern void sock_init_data(struct socket *sock, struct sock *sk); +extern void sk_filter_release_rcu(struct rcu_head *rcu); + /** * sk_filter_release - release a socket filter * @fp: filter to remove @@ -1165,7 +1167,7 @@ extern void sock_init_data(struct socket *sock, struct sock *sk); static inline void sk_filter_release(struct sk_filter *fp) { if (atomic_dec_and_test(&fp->refcnt)) - kfree(fp); + call_rcu_bh(&fp->rcu, sk_filter_release_rcu); } static inline void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp) -- cgit v1.1 From 3110f5f5545a645c50ef66b1f705d08dfd1df404 Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Mon, 6 Dec 2010 08:28:50 +0000 Subject: tg3: Move EEE definitions into mdio.h In commit 52b02d04c801fff51ca49ad033210846d1713253 entitled "tg3: Add EEE support", Ben Hutchings had commented that the EEE advertisement register will be in a standard location. This patch moves that definition into mdio.h and changes the code to use it. Signed-off-by: Matt Carlson Reviewed-by: Benjamin Li Signed-off-by: David S. Miller --- include/linux/mdio.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index c779b49..b1494ac 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -55,6 +55,7 @@ #define MDIO_PCS_10GBRT_STAT2 33 /* 10GBASE-R/-T PCS status 2 */ #define MDIO_AN_10GBT_CTRL 32 /* 10GBASE-T auto-negotiation control */ #define MDIO_AN_10GBT_STAT 33 /* 10GBASE-T auto-negotiation status */ +#define MDIO_AN_EEE_ADV 60 /* EEE advertisement */ /* LASI (Link Alarm Status Interrupt) registers, defined by XENPAK MSA. */ #define MDIO_PMA_LASI_RXCTRL 0x9000 /* RX_ALARM control */ @@ -235,6 +236,10 @@ #define MDIO_AN_10GBT_STAT_MS 0x4000 /* Master/slave config */ #define MDIO_AN_10GBT_STAT_MSFLT 0x8000 /* Master/slave config fault */ +/* AN EEE Advertisement register. */ +#define MDIO_AN_EEE_ADV_100TX 0x0002 /* Advertise 100TX EEE cap */ +#define MDIO_AN_EEE_ADV_1000T 0x0004 /* Advertise 1000T EEE cap */ + /* LASI RX_ALARM control/status registers. */ #define MDIO_PMA_LASI_RX_PHYXSLFLT 0x0001 /* PHY XS RX local fault */ #define MDIO_PMA_LASI_RX_PCSLFLT 0x0008 /* PCS RX local fault */ -- cgit v1.1 From af5568843594fb71055debe36e521fa8072fcecc Mon Sep 17 00:00:00 2001 From: Bruno Randolf Date: Thu, 2 Dec 2010 19:50:37 +0900 Subject: lib: Improve EWMA efficiency by using bitshifts Using bitshifts instead of division and multiplication should improve performance. That requires weight and factor to be powers of two, but i think this is something we can live with. Thanks to Peter Zijlstra for the improved formula! Signed-off-by: Bruno Randolf -- v2: use log2.h functions Signed-off-by: John W. Linville --- include/linux/average.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/average.h b/include/linux/average.h index 7706e40..c6028fd 100644 --- a/include/linux/average.h +++ b/include/linux/average.h @@ -1,8 +1,6 @@ #ifndef _LINUX_AVERAGE_H #define _LINUX_AVERAGE_H -#include - /* Exponentially weighted moving average (EWMA) */ /* For more documentation see lib/average.c */ @@ -26,7 +24,7 @@ extern struct ewma *ewma_add(struct ewma *avg, unsigned long val); */ static inline unsigned long ewma_read(const struct ewma *avg) { - return DIV_ROUND_CLOSEST(avg->internal, avg->factor); + return avg->internal >> avg->factor; } #endif /* _LINUX_AVERAGE_H */ -- cgit v1.1 From 073285fd392f6dc901da7c698d46e1e2a7e26436 Mon Sep 17 00:00:00 2001 From: Alexey Orishko Date: Mon, 29 Nov 2010 23:23:27 +0000 Subject: usbnet: changes for upcoming cdc_ncm driver Changes: include/linux/usb/usbnet.h: - a new flag to indicate driver's capability to accumulate IP packets in Tx direction and extract several packets from single skb in Rx direction. drivers/net/usb/usbnet.c: - the procedure of counting packets in usbnet was updated due to the accumulating of IP packets in the driver - no short packets are sent if indicated by the flag in driver_info structure Signed-off-by: Alexey Orishko Signed-off-by: David S. Miller --- include/linux/usb/usbnet.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index 7ae27a4..44842c8 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -97,6 +97,12 @@ struct driver_info { #define FLAG_LINK_INTR 0x0800 /* updates link (carrier) status */ +/* + * Indicates to usbnet, that USB driver accumulates multiple IP packets. + * Affects statistic (counters) and short packet handling. + */ +#define FLAG_MULTI_PACKET 0x1000 + /* init device ... can sleep, or cause probe() failure */ int (*bind)(struct usbnet *, struct usb_interface *); -- cgit v1.1 From da2033c282264bfba4e339b7cb3df62adb5c5fc8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 30 Nov 2010 21:45:56 +0000 Subject: filter: add SKF_AD_RXHASH and SKF_AD_CPU Add SKF_AD_RXHASH and SKF_AD_CPU to filter ancillary mechanism, to be able to build advanced filters. This can help spreading packets on several sockets with a fast selection, after RPS dispatch to N cpus for example, or to catch a percentage of flows in one queue. tcpdump -s 500 "cpu = 1" : [0] ld CPU [1] jeq #1 jt 2 jf 3 [2] ret #500 [3] ret #0 # take 12.5 % of flows (average) tcpdump -s 1000 "rxhash & 7 = 2" : [0] ld RXHASH [1] and #7 [2] jeq #2 jt 3 jf 4 [3] ret #1000 [4] ret #0 Signed-off-by: Eric Dumazet Cc: Rui Acked-by: Changli Gao Signed-off-by: David S. Miller --- include/linux/filter.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 447a775..5334ada 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -124,7 +124,9 @@ struct sock_fprog { /* Required for SO_ATTACH_FILTER. */ #define SKF_AD_MARK 20 #define SKF_AD_QUEUE 24 #define SKF_AD_HATYPE 28 -#define SKF_AD_MAX 32 +#define SKF_AD_RXHASH 32 +#define SKF_AD_CPU 36 +#define SKF_AD_MAX 40 #define SKF_NET_OFF (-0x100000) #define SKF_LL_OFF (-0x200000) -- cgit v1.1 From 06a9701f4b3e3381dea96fee1cc8a3bb41b0a1f1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 1 Dec 2010 01:37:42 +0000 Subject: __in_dev_get_rtnl() can use rtnl_dereference() If caller holds RTNL, we dont need a memory barrier (smp_read_barrier_depends) included in rcu_dereference(). Just use rtnl_dereference() to properly document the assertions. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 2b86eaf..ae8fdc5 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -222,7 +222,7 @@ static inline struct in_device *in_dev_get(const struct net_device *dev) static inline struct in_device *__in_dev_get_rtnl(const struct net_device *dev) { - return rcu_dereference_check(dev->ip_ptr, lockdep_rtnl_is_held()); + return rtnl_dereference(dev->ip_ptr); } extern void in_dev_finish_destroy(struct in_device *idev); -- cgit v1.1 From 45904f21655cf4f0ae7d0fab5906fe51bf56ecf4 Mon Sep 17 00:00:00 2001 From: Javier Cardona Date: Fri, 3 Dec 2010 09:20:40 +0100 Subject: nl80211/mac80211: define and allow configuring mesh element TTL The TTL in path selection information elements is different from the mesh ttl used in mesh data frames. Version 7.03 of the 11s draft calls this ttl 'Element TTL'. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 4 ++++ include/net/cfg80211.h | 2 ++ 2 files changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 5cfa579..9e54145 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -1547,6 +1547,9 @@ enum nl80211_mntr_flags { * @NL80211_MESHCONF_TTL: specifies the value of TTL field set at a source mesh * point. * + * @NL80211_MESHCONF_ELEMENT_TTL: specifies the value of TTL field set at a + * source mesh point for path selection elements. + * * @NL80211_MESHCONF_AUTO_OPEN_PLINKS: whether we should automatically * open peer links when we detect compatible mesh peers. * @@ -1593,6 +1596,7 @@ enum nl80211_meshconf_params { NL80211_MESHCONF_HWMP_PREQ_MIN_INTERVAL, NL80211_MESHCONF_HWMP_NET_DIAM_TRVS_TIME, NL80211_MESHCONF_HWMP_ROOTMODE, + NL80211_MESHCONF_ELEMENT_TTL, /* keep last */ __NL80211_MESHCONF_ATTR_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 6b2af7a..93a4b20 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -624,6 +624,8 @@ struct mesh_config { u16 dot11MeshMaxPeerLinks; u8 dot11MeshMaxRetries; u8 dot11MeshTTL; + /* ttl used in path selection information elements */ + u8 element_ttl; bool auto_open_plinks; /* HWMP parameters */ u8 dot11MeshHWMPmaxPREQretries; -- cgit v1.1 From f9e10ce4cf86945eb5efcab31284c971877ed012 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 3 Dec 2010 09:20:42 +0100 Subject: cfg80211: require add_virtual_intf to return new dev cfg80211 used to do all its bookkeeping in the notifier, but some new stuff will have to use local variables so make the callback return the netdev pointer. Tested-by: Javier Cardona Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/cfg80211.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 93a4b20..902895d 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1033,7 +1033,8 @@ struct cfg80211_pmksa { * * @add_virtual_intf: create a new virtual interface with the given name, * must set the struct wireless_dev's iftype. Beware: You must create - * the new netdev in the wiphy's network namespace! + * the new netdev in the wiphy's network namespace! Returns the netdev, + * or an ERR_PTR. * * @del_virtual_intf: remove the virtual interface determined by ifindex. * @@ -1168,9 +1169,11 @@ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy); int (*resume)(struct wiphy *wiphy); - int (*add_virtual_intf)(struct wiphy *wiphy, char *name, - enum nl80211_iftype type, u32 *flags, - struct vif_params *params); + struct net_device * (*add_virtual_intf)(struct wiphy *wiphy, + char *name, + enum nl80211_iftype type, + u32 *flags, + struct vif_params *params); int (*del_virtual_intf)(struct wiphy *wiphy, struct net_device *dev); int (*change_virtual_intf)(struct wiphy *wiphy, struct net_device *dev, -- cgit v1.1 From 29cbe68c516a48a9a88b3226878570c6cbd83c02 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 3 Dec 2010 09:20:44 +0100 Subject: cfg80211/mac80211: add mesh join/leave commands Instead of tying mesh activity to interface up, add join and leave commands for mesh. Since we must be backward compatible, let cfg80211 handle joining a mesh if a mesh ID was pre-configured when the device goes up. Note that this therefore must modify mac80211 as well since mac80211 needs to lose the logic to start the mesh on interface up. We now allow querying mesh parameters before the mesh is connected, which simply returns defaults. Setting them (internally renamed to "update") is only allowed while connected. Specify them with the new mesh join command instead where needed. In mac80211, beaconing must now also follow the mesh enabled/not enabled state, which is done by testing the mesh ID. Signed-off-by: Javier Cardona Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 8 ++++++++ include/net/cfg80211.h | 38 +++++++++++++++++++++++++++++--------- 2 files changed, 37 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 9e54145..410a06e 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -394,6 +394,11 @@ * * @NL80211_CMD_SET_WDS_PEER: Set the MAC address of the peer on a WDS interface. * + * @NL80211_CMD_JOIN_MESH: Join a mesh. The mesh ID must be given, and initial + * mesh config parameters may be given. + * @NL80211_CMD_LEAVE_MESH: Leave the mesh network -- no special arguments, the + * network is determined by the network interface. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -500,6 +505,9 @@ enum nl80211_commands { NL80211_CMD_FRAME_WAIT_CANCEL, + NL80211_CMD_JOIN_MESH, + NL80211_CMD_LEAVE_MESH, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 902895d..788c398 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -258,13 +258,9 @@ struct ieee80211_supported_band { /** * struct vif_params - describes virtual interface parameters - * @mesh_id: mesh ID to use - * @mesh_id_len: length of the mesh ID * @use_4addr: use 4-address frames */ struct vif_params { - u8 *mesh_id; - int mesh_id_len; int use_4addr; }; @@ -615,6 +611,11 @@ struct bss_parameters { int ap_isolate; }; +/* + * struct mesh_config - 802.11s mesh configuration + * + * These parameters can be changed while the mesh is active. + */ struct mesh_config { /* Timeouts in ms */ /* Mesh plink management parameters */ @@ -638,6 +639,18 @@ struct mesh_config { }; /** + * struct mesh_setup - 802.11s mesh setup configuration + * @mesh_id: the mesh ID + * @mesh_id_len: length of the mesh ID, at least 1 and at most 32 bytes + * + * These parameters are fixed when the mesh is created. + */ +struct mesh_setup { + const u8 *mesh_id; + u8 mesh_id_len; +}; + +/** * struct ieee80211_txq_params - TX queue parameters * @queue: TX queue identifier (NL80211_TXQ_Q_*) * @txop: Maximum burst time in units of 32 usecs, 0 meaning disabled @@ -1078,7 +1091,7 @@ struct cfg80211_pmksa { * * @get_mesh_params: Put the current mesh parameters into *params * - * @set_mesh_params: Set mesh parameters. + * @update_mesh_params: Update mesh parameters on a running mesh. * The mask is a bitfield which tells us which parameters to * set, and which to leave alone. * @@ -1229,9 +1242,14 @@ struct cfg80211_ops { int (*get_mesh_params)(struct wiphy *wiphy, struct net_device *dev, struct mesh_config *conf); - int (*set_mesh_params)(struct wiphy *wiphy, - struct net_device *dev, - const struct mesh_config *nconf, u32 mask); + int (*update_mesh_params)(struct wiphy *wiphy, + struct net_device *dev, u32 mask, + const struct mesh_config *nconf); + int (*join_mesh)(struct wiphy *wiphy, struct net_device *dev, + const struct mesh_config *conf, + const struct mesh_setup *setup); + int (*leave_mesh)(struct wiphy *wiphy, struct net_device *dev); + int (*change_bss)(struct wiphy *wiphy, struct net_device *dev, struct bss_parameters *params); @@ -1647,6 +1665,8 @@ struct cfg80211_cached_keys; * @bssid: (private) Used by the internal configuration code * @ssid: (private) Used by the internal configuration code * @ssid_len: (private) Used by the internal configuration code + * @mesh_id_len: (private) Used by the internal configuration code + * @mesh_id_up_len: (private) Used by the internal configuration code * @wext: (private) Used by the internal wireless extensions compat code * @use_4addr: indicates 4addr mode is used on this interface, must be * set by driver (if supported) on add_interface BEFORE registering the @@ -1676,7 +1696,7 @@ struct wireless_dev { /* currently used for IBSS and SME - might be rearranged later */ u8 ssid[IEEE80211_MAX_SSID_LEN]; - u8 ssid_len; + u8 ssid_len, mesh_id_len, mesh_id_up_len; enum { CFG80211_SME_IDLE, CFG80211_SME_CONNECTING, -- cgit v1.1 From 0e7d0c860a0dee49dacb7bbb248d1eba637075ad Mon Sep 17 00:00:00 2001 From: Gabor Juhos Date: Mon, 6 Dec 2010 17:14:47 -0800 Subject: Input: add input driver for polled GPIO buttons The existing gpio-keys driver can be usable only for GPIO lines with interrupt support. Several devices have buttons connected to a GPIO line which is not capable to generate interrupts. This patch adds a new input driver using the generic GPIO layer and the input-polldev to support such buttons. [Ben Gardiner Signed-off-by: Ben Gardiner Tested-by: Ben Gardiner Signed-off-by: Dmitry Torokhov --- include/linux/gpio_keys.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/gpio_keys.h b/include/linux/gpio_keys.h index ce73a30..dd1a56f 100644 --- a/include/linux/gpio_keys.h +++ b/include/linux/gpio_keys.h @@ -16,6 +16,8 @@ struct gpio_keys_button { struct gpio_keys_platform_data { struct gpio_keys_button *buttons; int nbuttons; + unsigned int poll_interval; /* polling interval in msecs - + for polling driver only */ unsigned int rep:1; /* enable input subsystem auto repeat */ int (*enable)(struct device *dev); void (*disable)(struct device *dev); -- cgit v1.1 From 871a2c16c21b988688b4ab1a78eadd969765c0a3 Mon Sep 17 00:00:00 2001 From: Tomasz Grobelny Date: Sat, 4 Dec 2010 13:38:01 +0100 Subject: dccp: Policy-based packet dequeueing infrastructure This patch adds a generic infrastructure for policy-based dequeueing of TX packets and provides two policies: * a simple FIFO policy (which is the default) and * a priority based policy (set via socket options). Both policies honour the tx_qlen sysctl for the maximum size of the write queue (can be overridden via socket options). The priority policy uses skb->priority internally to assign an u32 priority identifier, using the same ranking as SO_PRIORITY. The skb->priority field is set to 0 when the packet leaves DCCP. The priority is supplied as ancillary data using cmsg(3), the patch also provides the requisite parsing routines. Signed-off-by: Tomasz Grobelny Signed-off-by: Gerrit Renker --- include/linux/dccp.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index eed52bc..010e2d8 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -197,6 +197,21 @@ enum dccp_feature_numbers { DCCPF_MAX_CCID_SPECIFIC = 255, }; +/* DCCP socket control message types for cmsg */ +enum dccp_cmsg_type { + DCCP_SCM_PRIORITY = 1, + DCCP_SCM_QPOLICY_MAX = 0xFFFF, + /* ^-- Up to here reserved exclusively for qpolicy parameters */ + DCCP_SCM_MAX +}; + +/* DCCP priorities for outgoing/queued packets */ +enum dccp_packet_dequeueing_policy { + DCCPQ_POLICY_SIMPLE, + DCCPQ_POLICY_PRIO, + DCCPQ_POLICY_MAX +}; + /* DCCP socket options */ #define DCCP_SOCKOPT_PACKET_SIZE 1 /* XXX deprecated, without effect */ #define DCCP_SOCKOPT_SERVICE 2 @@ -210,6 +225,8 @@ enum dccp_feature_numbers { #define DCCP_SOCKOPT_CCID 13 #define DCCP_SOCKOPT_TX_CCID 14 #define DCCP_SOCKOPT_RX_CCID 15 +#define DCCP_SOCKOPT_QPOLICY_ID 16 +#define DCCP_SOCKOPT_QPOLICY_TXQLEN 17 #define DCCP_SOCKOPT_CCID_RX_INFO 128 #define DCCP_SOCKOPT_CCID_TX_INFO 192 @@ -458,6 +475,8 @@ struct dccp_ackvec; * @dccps_hc_rx_ccid - CCID used for the receiver (or receiving half-connection) * @dccps_hc_tx_ccid - CCID used for the sender (or sending half-connection) * @dccps_options_received - parsed set of retrieved options + * @dccps_qpolicy - TX dequeueing policy, one of %dccp_packet_dequeueing_policy + * @dccps_tx_qlen - maximum length of the TX queue * @dccps_role - role of this sock, one of %dccp_role * @dccps_hc_rx_insert_options - receiver wants to add options when acking * @dccps_hc_tx_insert_options - sender wants to add options when sending @@ -500,6 +519,8 @@ struct dccp_sock { struct ccid *dccps_hc_rx_ccid; struct ccid *dccps_hc_tx_ccid; struct dccp_options_received dccps_options_received; + __u8 dccps_qpolicy; + __u32 dccps_tx_qlen; enum dccp_role dccps_role:2; __u8 dccps_hc_rx_insert_options:1; __u8 dccps_hc_tx_insert_options:1; -- cgit v1.1 From 02c048b919455aaa38628563cdcc2e691c8a9f53 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 7 Dec 2010 20:16:56 +0100 Subject: fuse: allow batching of FORGET requests Terje Malmedal reports that a fuse filesystem with 32 million inodes on a machine with lots of memory can take up to 30 minutes to process FORGET requests when all those inodes are evicted from the icache. To solve this, create a BATCH_FORGET request that allows up to about 8000 FORGET requests to be sent in a single message. This request is only sent if userspace supports interface version 7.16 or later, otherwise fall back to sending individual FORGET messages. Reported-by: Terje Malmedal Signed-off-by: Miklos Szeredi --- include/linux/fuse.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fuse.h b/include/linux/fuse.h index c3c578e..cf11881 100644 --- a/include/linux/fuse.h +++ b/include/linux/fuse.h @@ -41,6 +41,9 @@ * 7.15 * - add store notify * - add retrieve notify + * + * 7.16 + * - add BATCH_FORGET request */ #ifndef _LINUX_FUSE_H @@ -72,7 +75,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 15 +#define FUSE_KERNEL_MINOR_VERSION 16 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -256,6 +259,7 @@ enum fuse_opcode { FUSE_IOCTL = 39, FUSE_POLL = 40, FUSE_NOTIFY_REPLY = 41, + FUSE_BATCH_FORGET = 42, /* CUSE specific operations */ CUSE_INIT = 4096, @@ -290,6 +294,16 @@ struct fuse_forget_in { __u64 nlookup; }; +struct fuse_forget_one { + __u64 nodeid; + __u64 nlookup; +}; + +struct fuse_batch_forget_in { + __u32 count; + __u32 dummy; +}; + struct fuse_getattr_in { __u32 getattr_flags; __u32 dummy; -- cgit v1.1 From 1baa26b2be92fe9917e2f7ef46d423b5dfa4da71 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 7 Dec 2010 20:16:56 +0100 Subject: fuse: fix ioctl ABI In kernel ABI version 7.16 and later FUSE_IOCTL_RETRY reply from a unrestricted IOCTL request shall return with an array of 'struct fuse_ioctl_iovec' instead of 'struct iovec'. This fixes the ABI ambiguity of 32bit vs. 64bit. Reported-by: "ccmail111" Signed-off-by: Miklos Szeredi CC: Tejun Heo --- include/linux/fuse.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/fuse.h b/include/linux/fuse.h index cf11881..d464de5 100644 --- a/include/linux/fuse.h +++ b/include/linux/fuse.h @@ -44,6 +44,9 @@ * * 7.16 * - add BATCH_FORGET request + * - FUSE_IOCTL_UNRESTRICTED shall now return with array of 'struct + * fuse_ioctl_iovec' instead of ambiguous 'struct iovec' + * - add FUSE_IOCTL_32BIT flag */ #ifndef _LINUX_FUSE_H @@ -203,12 +206,14 @@ struct fuse_file_lock { * FUSE_IOCTL_COMPAT: 32bit compat ioctl on 64bit machine * FUSE_IOCTL_UNRESTRICTED: not restricted to well-formed ioctls, retry allowed * FUSE_IOCTL_RETRY: retry with new iovecs + * FUSE_IOCTL_32BIT: 32bit ioctl * * FUSE_IOCTL_MAX_IOV: maximum of in_iovecs + out_iovecs */ #define FUSE_IOCTL_COMPAT (1 << 0) #define FUSE_IOCTL_UNRESTRICTED (1 << 1) #define FUSE_IOCTL_RETRY (1 << 2) +#define FUSE_IOCTL_32BIT (1 << 3) #define FUSE_IOCTL_MAX_IOV 256 @@ -524,6 +529,11 @@ struct fuse_ioctl_in { __u32 out_size; }; +struct fuse_ioctl_iovec { + __u64 base; + __u64 len; +}; + struct fuse_ioctl_out { __s32 result; __u32 flags; -- cgit v1.1 From 541a45a142df281c974d74eac2066138fc107b23 Mon Sep 17 00:00:00 2001 From: Bruno Randolf Date: Thu, 2 Dec 2010 19:12:43 +0900 Subject: nl80211/mac80211: Report signal average Extend nl80211 to report an exponential weighted moving average (EWMA) of the signal value. Since the signal value usually fluctuates between different packets, an average can be more useful than the value of the last packet. This uses the recently added generic EWMA library function. -- v2: fix ABI breakage and change factor to be a power of 2. Signed-off-by: Bruno Randolf Signed-off-by: John W. Linville --- include/linux/nl80211.h | 2 ++ include/net/cfg80211.h | 4 ++++ 2 files changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 410a06e..8e28053 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -1191,6 +1191,7 @@ enum nl80211_rate_info { * station) * @NL80211_STA_INFO_TX_RETRIES: total retries (u32, to this station) * @NL80211_STA_INFO_TX_FAILED: total failed packets (u32, to this station) + * @NL80211_STA_INFO_SIGNAL_AVG: signal strength average (u8, dBm) */ enum nl80211_sta_info { __NL80211_STA_INFO_INVALID, @@ -1206,6 +1207,7 @@ enum nl80211_sta_info { NL80211_STA_INFO_TX_PACKETS, NL80211_STA_INFO_TX_RETRIES, NL80211_STA_INFO_TX_FAILED, + NL80211_STA_INFO_SIGNAL_AVG, /* keep last */ __NL80211_STA_INFO_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 788c398..8764c9a 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -420,6 +420,7 @@ struct station_parameters { * @STATION_INFO_TX_RETRIES: @tx_retries filled * @STATION_INFO_TX_FAILED: @tx_failed filled * @STATION_INFO_RX_DROP_MISC: @rx_dropped_misc filled + * @STATION_INFO_SIGNAL_AVG: @signal_avg filled */ enum station_info_flags { STATION_INFO_INACTIVE_TIME = 1<<0, @@ -435,6 +436,7 @@ enum station_info_flags { STATION_INFO_TX_RETRIES = 1<<10, STATION_INFO_TX_FAILED = 1<<11, STATION_INFO_RX_DROP_MISC = 1<<12, + STATION_INFO_SIGNAL_AVG = 1<<13, }; /** @@ -481,6 +483,7 @@ struct rate_info { * @plid: mesh peer link id * @plink_state: mesh peer link state * @signal: signal strength of last received packet in dBm + * @signal_avg: signal strength average in dBm * @txrate: current unicast bitrate to this station * @rx_packets: packets received from this station * @tx_packets: packets transmitted to this station @@ -501,6 +504,7 @@ struct station_info { u16 plid; u8 plink_state; s8 signal; + s8 signal_avg; struct rate_info txrate; u32 rx_packets; u32 tx_packets; -- cgit v1.1 From 88d60c32765716289abeb362c44adf6c35c6824c Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Mon, 8 Nov 2010 18:19:22 -0500 Subject: fanotify: remove packed from access response message Since fanotify has decided to be careful about alignment and packing rather than rely on __attribute__((packed)) for multiarch support. Since this attribute isn't doing anything on fanotify_response we just drop it. This does not break API/ABI. Suggested-by: Tvrtko Ursulin Signed-off-by: Eric Paris --- include/linux/fanotify.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 0f01214..bdbf9bb 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -96,7 +96,7 @@ struct fanotify_event_metadata { struct fanotify_response { __s32 fd; __u32 response; -} __attribute__ ((packed)); +}; /* Legit userspace responses to a _PERM event */ #define FAN_ALLOW 0x01 -- cgit v1.1 From b1085ba80cd2784400a7beec3fda5099198ed01c Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Fri, 5 Nov 2010 17:05:27 +0100 Subject: fanotify: if set by user unset FMODE_NONOTIFY before fsnotify_perm() is called Unsetting FMODE_NONOTIFY in fsnotify_open() is too late, since fsnotify_perm() is called before. If FMODE_NONOTIFY is set fsnotify_perm() will skip permission checks, so a user can still disable permission checks by setting this flag in an open() call. This patch corrects this by unsetting the flag before fsnotify_perm is called. Signed-off-by: Lino Sanfilippo Signed-off-by: Eric Paris --- include/linux/fsnotify.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 5c185fa..b10bcde 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -235,9 +235,6 @@ static inline void fsnotify_open(struct file *file) if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; - /* FMODE_NONOTIFY must never be set from user */ - file->f_mode &= ~FMODE_NONOTIFY; - fsnotify_parent(path, NULL, mask); fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); } -- cgit v1.1 From 09e5f14e57c70f9d357862bb56e57026c51092a1 Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Fri, 19 Nov 2010 10:58:07 +0100 Subject: fanotify: on group destroy allow all waiters to bypass permission check When fanotify_release() is called, there may still be processes waiting for access permission. Currently only processes for which an event has already been queued into the groups access list will be woken up. Processes for which no event has been queued will continue to sleep and thus cause a deadlock when fsnotify_put_group() is called. Furthermore there is a race allowing further processes to be waiting on the access wait queue after wake_up (if they arrive before clear_marks_by_group() is called). This patch corrects this by setting a flag to inform processes that the group is about to be destroyed and thus not to wait for access permission. [additional changelog from eparis] Lets think about the 4 relevant code paths from the PoV of the 'operator' 'listener' 'responder' and 'closer'. Where operator is the process doing an action (like open/read) which could require permission. Listener is the task (or in this case thread) slated with reading from the fanotify file descriptor. The 'responder' is the thread responsible for responding to access requests. 'Closer' is the thread attempting to close the fanotify file descriptor. The 'operator' is going to end up in: fanotify_handle_event() get_response_from_access() (THIS BLOCKS WAITING ON USERSPACE) The 'listener' interesting code path fanotify_read() copy_event_to_user() prepare_for_access_response() (THIS CREATES AN fanotify_response_event) The 'responder' code path: fanotify_write() process_access_response() (REMOVE A fanotify_response_event, SET RESPONSE, WAKE UP 'operator') The 'closer': fanotify_release() (SUPPOSED TO CLEAN UP THE REST OF THIS MESS) What we have today is that in the closer we remove all of the fanotify_response_events and set a bit so no more response events are ever created in prepare_for_access_response(). The bug is that we never wake all of the operators up and tell them to move along. You fix that in fanotify_get_response_from_access(). You also fix other operators which haven't gotten there yet. So I agree that's a good fix. [/additional changelog from eparis] [remove additional changes to minimize patch size] [move initialization so it was inside CONFIG_FANOTIFY_PERMISSION] Signed-off-by: Lino Sanfilippo Signed-off-by: Eric Paris --- include/linux/fsnotify_backend.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 0a68f92..7380763 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -166,7 +166,7 @@ struct fsnotify_group { struct mutex access_mutex; struct list_head access_list; wait_queue_head_t access_waitq; - bool bypass_perm; /* protected by access_mutex */ + atomic_t bypass_perm; #endif /* CONFIG_FANOTIFY_ACCESS_PERMISSIONS */ int f_flags; unsigned int max_marks; -- cgit v1.1 From e9a3854fd4ff3907e6c200a3980e19365ee695e9 Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Wed, 24 Nov 2010 18:22:09 +0100 Subject: fanotify: Introduce FAN_NOFD FAN_NOFD is used in fanotify events that do not provide an open file descriptor (like the overflow_event). Signed-off-by: Lino Sanfilippo Signed-off-by: Eric Paris --- include/linux/fanotify.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index bdbf9bb..c732243 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -101,6 +101,8 @@ struct fanotify_response { /* Legit userspace responses to a _PERM event */ #define FAN_ALLOW 0x01 #define FAN_DENY 0x02 +/* No fd set in event */ +#define FAN_NOFD -1 /* Helper functions to deal with fanotify_event_metadata buffers */ #define FAN_EVENT_METADATA_LEN (sizeof(struct fanotify_event_metadata)) -- cgit v1.1 From 5c6d1125f8dbd1bfef39e38fbc2837003be78a59 Mon Sep 17 00:00:00 2001 From: Jarkko Sakkinen Date: Tue, 7 Dec 2010 13:34:01 +0200 Subject: Smack: Transmute labels on specified directories In a situation where Smack access rules allow processes with multiple labels to write to a directory it is easy to get into a situation where the directory gets cluttered with files that the owner can't deal with because while they could be written to the directory a process at the label of the directory can't write them. This is generally the desired behavior, but when it isn't it is a real issue. This patch introduces a new attribute SMACK64TRANSMUTE that instructs Smack to create the file with the label of the directory under certain circumstances. A new access mode, "t" for transmute, is made available to Smack access rules, which are expanded from "rwxa" to "rwxat". If a file is created in a directory marked as transmutable and if access was granted to perform the operation by a rule that included the transmute mode, then the file gets the Smack label of the directory instead of the Smack label of the creating process. Note that this is equivalent to creating an empty file at the label of the directory and then having the other process write to it. The transmute scheme requires that both the access rule allows transmutation and that the directory be explicitly marked. Signed-off-by: Jarkko Sakkinen Signed-off-by: Casey Schaufler --- include/linux/xattr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 351c790..e6131ef 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -41,10 +41,12 @@ #define XATTR_SMACK_IPIN "SMACK64IPIN" #define XATTR_SMACK_IPOUT "SMACK64IPOUT" #define XATTR_SMACK_EXEC "SMACK64EXEC" +#define XATTR_SMACK_TRANSMUTE "SMACK64TRANSMUTE" #define XATTR_NAME_SMACK XATTR_SECURITY_PREFIX XATTR_SMACK_SUFFIX #define XATTR_NAME_SMACKIPIN XATTR_SECURITY_PREFIX XATTR_SMACK_IPIN #define XATTR_NAME_SMACKIPOUT XATTR_SECURITY_PREFIX XATTR_SMACK_IPOUT #define XATTR_NAME_SMACKEXEC XATTR_SECURITY_PREFIX XATTR_SMACK_EXEC +#define XATTR_NAME_SMACKTRANSMUTE XATTR_SECURITY_PREFIX XATTR_SMACK_TRANSMUTE #define XATTR_CAPS_SUFFIX "capability" #define XATTR_NAME_CAPS XATTR_SECURITY_PREFIX XATTR_CAPS_SUFFIX -- cgit v1.1 From c02178d22b3ef2d18c38c96151600ee1c7ed94f0 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Wed, 8 Dec 2010 00:21:05 +0200 Subject: Bluetooth: Add Bluetooth Management interface definitions Add initial definitions for the new Bluetooth Management interface to the bluetooth headers. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann Signed-off-by: Gustavo F. Padovan --- include/net/bluetooth/hci.h | 4 ++++ include/net/bluetooth/hci_core.h | 1 + include/net/bluetooth/mgmt.h | 46 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 51 insertions(+) create mode 100644 include/net/bluetooth/mgmt.h (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index f3c5ed6..29a7a8c 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -934,9 +934,13 @@ static inline struct hci_sco_hdr *hci_sco_hdr(const struct sk_buff *skb) struct sockaddr_hci { sa_family_t hci_family; unsigned short hci_dev; + unsigned short hci_channel; }; #define HCI_DEV_NONE 0xffff +#define HCI_CHANNEL_RAW 0 +#define HCI_CHANNEL_CONTROL 1 + struct hci_filter { unsigned long type_mask; unsigned long event_mask[2]; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 9c08625..3e34359 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -668,6 +668,7 @@ struct hci_pinfo { struct hci_dev *hdev; struct hci_filter filter; __u32 cmsg_mask; + unsigned short channel; }; /* HCI security filter */ diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h new file mode 100644 index 0000000..95974da --- /dev/null +++ b/include/net/bluetooth/mgmt.h @@ -0,0 +1,46 @@ +/* + BlueZ - Bluetooth protocol stack for Linux + + Copyright (C) 2010 Nokia Corporation + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License version 2 as + published by the Free Software Foundation; + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS + OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. + IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY + CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES + WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN + ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF + OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + + ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, + COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS + SOFTWARE IS DISCLAIMED. +*/ + +struct mgmt_hdr { + __le16 opcode; + __le16 len; +} __packed; +#define MGMT_HDR_SIZE 4 + +#define MGMT_EV_CMD_COMPLETE 0x0001 +struct mgmt_ev_cmd_complete { + __le16 opcode; + __u8 data[0]; +} __packed; + +#define MGMT_EV_CMD_STATUS 0x0002 +struct mgmt_ev_cmd_status { + __u8 status; + __le16 opcode; +} __packed; + +#define MGMT_EV_CONTROLLER_ERROR 0x0003 +struct mgmt_ev_controller_error { + __le16 index; + __u8 error_code; +} __packed; -- cgit v1.1 From 0381101fd6a73c7d6b545044dc1472d019fc64e3 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Wed, 8 Dec 2010 00:21:06 +0200 Subject: Bluetooth: Add initial Bluetooth Management interface callbacks Add initial code for handling Bluetooth Management interface messages. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann Acked-by: Andrei Emeltchenko Signed-off-by: Gustavo F. Padovan --- include/net/bluetooth/hci_core.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 3e34359..1992fac 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -660,6 +660,9 @@ void hci_si_event(struct hci_dev *hdev, int type, int dlen, void *data); /* ----- HCI Sockets ----- */ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb); +/* Management interface */ +int mgmt_control(struct sock *sk, struct msghdr *msg, size_t len); + /* HCI info for socket */ #define hci_pi(sk) ((struct hci_pinfo *) sk) -- cgit v1.1 From a40c406cbdd28dcca3483065bc2ba794cf5aaab7 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Wed, 8 Dec 2010 00:21:07 +0200 Subject: Bluetooth: Make hci_send_to_sock usable for management control sockets In order to send data to management control sockets the function should: - skip checks intended for raw HCI data and stack internal events - make sure RAW HCI data or stack internal events don't go to management control sockets In order to accomplish this the patch adds a new member to the bluetooth skb private data to flag skb's that are destined for management control sockets. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann Signed-off-by: Gustavo F. Padovan --- include/net/bluetooth/bluetooth.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index d81ea79..0c5e725 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -144,6 +144,7 @@ struct bt_skb_cb { __u8 tx_seq; __u8 retries; __u8 sar; + unsigned short channel; }; #define bt_cb(skb) ((struct bt_skb_cb *)((skb)->cb)) -- cgit v1.1 From 2df485a774ba59c3f43bfe84107672c1d9b731a0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 7 Dec 2010 22:39:17 -0500 Subject: nfs: remove extraneous and problematic calls to nfs_clear_request When a nfs_page is freed, nfs_free_request is called which also calls nfs_clear_request to clean out the lock and open contexts and free the pagecache page. However, a couple of places in the nfs code call nfs_clear_request themselves. What happens here if the refcount on the request is still high? We'll be releasing contexts and freeing pointers while the request is possibly still in use. Remove those bare calls to nfs_clear_context. That should only be done when the request is being freed. Note that when doing this, we need to watch out for tests of req->wb_page. Previously, nfs_set_page_tag_locked() and nfs_clear_page_tag_locked() would check the value of req->wb_page to figure out if the page is mapped into the nfsi->nfs_page_tree. We now indicate the page is mapped using the new bit PG_MAPPED in req->wb_flags . Reported-by: Jeff Layton Signed-off-by: Trond Myklebust --- include/linux/nfs_page.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index f8b60e7..d55cee7 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -29,6 +29,7 @@ */ enum { PG_BUSY = 0, + PG_MAPPED, PG_CLEAN, PG_NEED_COMMIT, PG_NEED_RESCHED, -- cgit v1.1 From 9f843706bb87837b823228467f4f83973fd110e9 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Mon, 6 Dec 2010 00:12:44 +0000 Subject: mmc, sh: Move MMCIF_PROGRESS_* into sh_mmcif.h Allow MMCIF_PROGRESS_* to be shared. Cc: Magnus Damm Signed-off-by: Simon Horman Signed-off-by: Paul Mundt --- include/linux/mmc/sh_mmcif.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/mmc/sh_mmcif.h index ffabf8c..6a98e97 100644 --- a/include/linux/mmc/sh_mmcif.h +++ b/include/linux/mmc/sh_mmcif.h @@ -97,6 +97,9 @@ static inline void sh_mmcif_writel(void __iomem *addr, int reg, u32 val) #define SH_MMCIF_BBS 512 /* boot block size */ +enum { MMCIF_PROGRESS_ENTER, MMCIF_PROGRESS_INIT, + MMCIF_PROGRESS_LOAD, MMCIF_PROGRESS_DONE }; + static inline void sh_mmcif_boot_cmd_send(void __iomem *base, unsigned long cmd, unsigned long arg) { -- cgit v1.1 From 54b384634f7083bcacf9a9ed2e6f4c3d0a246e49 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Mon, 6 Dec 2010 00:12:45 +0000 Subject: mmc, sh: Remove sh_mmcif_boot_slurp() As the only caller of sh_mmcif_boot_do_read() is sh_mmcif_boot_slurp() the configuration portion of sh_mmcif_boot_slurp() can be merged into sh_mmcif_boot_do_read(). Once this is done sh_mmcif_boot_slurp() is only a call to sh_mmcif_boot_do_read() with platform specific information - the offset that images are stored on MMC. So make the sh_mmcif_boot_do_read() call directly from platform code and remove sh_mmcif_boot_slurp() altogether. Cc: Magnus Damm Signed-off-by: Simon Horman Signed-off-by: Paul Mundt --- include/linux/mmc/sh_mmcif.h | 34 +++++++++++----------------------- 1 file changed, 11 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/mmc/sh_mmcif.h index 6a98e97..cfcc6e3 100644 --- a/include/linux/mmc/sh_mmcif.h +++ b/include/linux/mmc/sh_mmcif.h @@ -162,6 +162,17 @@ static inline int sh_mmcif_boot_do_read(void __iomem *base, unsigned long k; int ret = 0; + /* In data transfer mode: Set clock to Bus clock/4 (about 20Mhz) */ + sh_mmcif_writel(base, MMCIF_CE_CLK_CTRL, + CLK_ENABLE | CLKDIV_4 | SRSPTO_256 | + SRBSYTO_29 | SRWDTO_29 | SCCSTO_29); + + /* CMD9 - Get CSD */ + sh_mmcif_boot_cmd(base, 0x09806000, 0x00010000); + + /* CMD7 - Select the card */ + sh_mmcif_boot_cmd(base, 0x07400000, 0x00010000); + /* CMD16 - Set the block size */ sh_mmcif_boot_cmd(base, 0x10400000, SH_MMCIF_BBS); @@ -205,27 +216,4 @@ static inline void sh_mmcif_boot_init(void __iomem *base) sh_mmcif_boot_cmd(base, 0x03400040, 0x00010000); } -static inline void sh_mmcif_boot_slurp(void __iomem *base, - unsigned char *buf, - unsigned long no_bytes) -{ - unsigned long tmp; - - /* In data transfer mode: Set clock to Bus clock/4 (about 20Mhz) */ - sh_mmcif_writel(base, MMCIF_CE_CLK_CTRL, - CLK_ENABLE | CLKDIV_4 | SRSPTO_256 | - SRBSYTO_29 | SRWDTO_29 | SCCSTO_29); - - /* CMD9 - Get CSD */ - sh_mmcif_boot_cmd(base, 0x09806000, 0x00010000); - - /* CMD7 - Select the card */ - sh_mmcif_boot_cmd(base, 0x07400000, 0x00010000); - - tmp = no_bytes / SH_MMCIF_BBS; - tmp += (no_bytes % SH_MMCIF_BBS) ? 1 : 0; - - sh_mmcif_boot_do_read(base, 512, tmp, buf); -} - #endif /* __SH_MMCIF_H__ */ -- cgit v1.1 From 5bea7660bba973dc5e8e9d92b11fb1dd5b524ebf Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Tue, 7 Dec 2010 23:02:48 -0800 Subject: HID: add hid_hw_open/close/power() handlers Instead of exposing the guts of hid->ll_driver relationship to HID sub-drivers provide these helpers to encapsulate the details. Signed-off-by: Dmitry Torokhov Signed-off-by: Jiri Kosina --- include/linux/hid.h | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) (limited to 'include') diff --git a/include/linux/hid.h b/include/linux/hid.h index bb0f56f..e2af195 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -820,6 +820,49 @@ static inline void hid_hw_stop(struct hid_device *hdev) hdev->ll_driver->stop(hdev); } +/** + * hid_hw_open - signal underlaying HW to start delivering events + * + * @hdev: hid device + * + * Tell underlying HW to start delivering events from the device. + * This function should be called sometime after successful call + * to hid_hiw_start(). + */ +static inline int __must_check hid_hw_open(struct hid_device *hdev) +{ + return hdev->ll_driver->open(hdev); +} + +/** + * hid_hw_close - signal underlaying HW to stop delivering events + * + * @hdev: hid device + * + * This function indicates that we are not interested in the events + * from this device anymore. Delivery of events may or may not stop, + * depending on the number of users still outstanding. + */ +static inline void hid_hw_close(struct hid_device *hdev) +{ + hdev->ll_driver->close(hdev); +} + +/** + * hid_hw_power - requests underlying HW to go into given power mode + * + * @hdev: hid device + * @level: requested power level (one of %PM_HINT_* defines) + * + * This function requests underlying hardware to enter requested power + * mode. + */ + +static inline int hid_hw_power(struct hid_device *hdev, int level) +{ + return hdev->ll_driver->power ? hdev->ll_driver->power(hdev, level) : 0; +} + void hid_report_raw_event(struct hid_device *hid, int type, u8 *data, int size, int interrupt); -- cgit v1.1 From 941666c2e3e0f9f6a1cb5808d02352d445bd702c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 5 Dec 2010 01:23:53 +0000 Subject: net: RCU conversion of dev_getbyhwaddr() and arp_ioctl() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Le dimanche 05 décembre 2010 à 09:19 +0100, Eric Dumazet a écrit : > Hmm.. > > If somebody can explain why RTNL is held in arp_ioctl() (and therefore > in arp_req_delete()), we might first remove RTNL use in arp_ioctl() so > that your patch can be applied. > > Right now it is not good, because RTNL wont be necessarly held when you > are going to call arp_invalidate() ? While doing this analysis, I found a refcount bug in llc, I'll send a patch for net-2.6 Meanwhile, here is the patch for net-next-2.6 Your patch then can be applied after mine. Thanks [PATCH] net: RCU conversion of dev_getbyhwaddr() and arp_ioctl() dev_getbyhwaddr() was called under RTNL. Rename it to dev_getbyhwaddr_rcu() and change all its caller to now use RCU locking instead of RTNL. Change arp_ioctl() to use RCU instead of RTNL locking. Note: this fix a dev refcount bug in llc Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a9ac5dc..d31bc3c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1360,7 +1360,8 @@ static inline struct net_device *first_net_device(struct net *net) extern int netdev_boot_setup_check(struct net_device *dev); extern unsigned long netdev_boot_base(const char *prefix, int unit); -extern struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, char *hwaddr); +extern struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, + const char *hwaddr); extern struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type); extern struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type); extern void dev_add_pack(struct packet_type *pt); -- cgit v1.1 From 62ab0812137ec4f9884dd7de346238841ac03283 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 6 Dec 2010 20:50:09 +0000 Subject: filter: constify sk_run_filter() sk_run_filter() doesnt write on skb, change its prototype to reflect this. Fix two af_packet comments. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/filter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index 5334ada..45266b7 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -148,7 +148,7 @@ struct sk_buff; struct sock; extern int sk_filter(struct sock *sk, struct sk_buff *skb); -extern unsigned int sk_run_filter(struct sk_buff *skb, +extern unsigned int sk_run_filter(const struct sk_buff *skb, const struct sock_filter *filter); extern int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); extern int sk_detach_filter(struct sock *sk); -- cgit v1.1 From 5167695753c63444a9e6cbbef136200a16c7a225 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 7 Dec 2010 14:18:20 +0100 Subject: perf: Fix duplicate events with multiple-pmu vs software events Because the multi-pmu bits can share contexts between struct pmu instances we could get duplicate events by iterating the pmu list. Signed-off-by: Peter Zijlstra Signed-off-by: Thomas Gleixner LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index de2c417..4f1279e 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -887,6 +887,7 @@ struct perf_cpu_context { int exclusive; struct list_head rotation_list; int jiffies_interval; + struct pmu *active_pmu; }; struct perf_output_handle { -- cgit v1.1 From 0f004f5a696a9434b7214d0d3cbd0525ee77d428 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 30 Nov 2010 19:48:45 +0100 Subject: sched: Cure more NO_HZ load average woes There's a long-running regression that proved difficult to fix and which is hitting certain people and is rather annoying in its effects. Damien reported that after 74f5187ac8 (sched: Cure load average vs NO_HZ woes) his load average is unnaturally high, he also noted that even with that patch reverted the load avgerage numbers are not correct. The problem is that the previous patch only solved half the NO_HZ problem, it addressed the part of going into NO_HZ mode, not of comming out of NO_HZ mode. This patch implements that missing half. When comming out of NO_HZ mode there are two important things to take care of: - Folding the pending idle delta into the global active count. - Correctly aging the averages for the idle-duration. So with this patch the NO_HZ interaction should be complete and behaviour between CONFIG_NO_HZ=[yn] should be equivalent. Furthermore, this patch slightly changes the load average computation by adding a rounding term to the fixed point multiplication. Reported-by: Damien Wyart Reported-by: Tim McGrath Tested-by: Damien Wyart Tested-by: Orion Poplawski Tested-by: Kyle McMartin Signed-off-by: Peter Zijlstra Cc: stable@kernel.org Cc: Chase Douglas LKML-Reference: <1291129145.32004.874.camel@laptop> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2c79e92..2238745 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -143,7 +143,7 @@ extern unsigned long nr_iowait_cpu(int cpu); extern unsigned long this_cpu_load(void); -extern void calc_global_load(void); +extern void calc_global_load(unsigned long ticks); extern unsigned long get_parent_ip(unsigned long addr); -- cgit v1.1 From 806c09a7db457be3758e14b1f152761135d89af5 Mon Sep 17 00:00:00 2001 From: Dario Faggioli Date: Tue, 30 Nov 2010 19:51:33 +0100 Subject: sched: Make pushable_tasks CONFIG_SMP dependant As noted by Peter Zijlstra at https://lkml.org/lkml/2010/11/10/391 (while reviewing other stuff, though), tracking pushable tasks only makes sense on SMP systems. Signed-off-by: Dario Faggioli Acked-by: Steven Rostedt Acked-by: Gregory Haskins Signed-off-by: Peter Zijlstra LKML-Reference: <1291143093.2697.298.camel@Palantir> Signed-off-by: Ingo Molnar --- include/linux/init_task.h | 9 ++++++++- include/linux/sched.h | 2 ++ 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 1f8c06c..6ed8812 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -12,6 +12,13 @@ #include #include +#ifdef CONFIG_SMP +# define INIT_PUSHABLE_TASKS(tsk) \ + .pushable_tasks = PLIST_NODE_INIT(tsk.pushable_tasks, MAX_PRIO), +#else +# define INIT_PUSHABLE_TASKS(tsk) +#endif + extern struct files_struct init_files; extern struct fs_struct init_fs; @@ -137,7 +144,7 @@ extern struct cred init_cred; .nr_cpus_allowed = NR_CPUS, \ }, \ .tasks = LIST_HEAD_INIT(tsk.tasks), \ - .pushable_tasks = PLIST_NODE_INIT(tsk.pushable_tasks, MAX_PRIO), \ + INIT_PUSHABLE_TASKS(tsk) \ .ptraced = LIST_HEAD_INIT(tsk.ptraced), \ .ptrace_entry = LIST_HEAD_INIT(tsk.ptrace_entry), \ .real_parent = &tsk, \ diff --git a/include/linux/sched.h b/include/linux/sched.h index 9c2d46d..4f92a23 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1240,7 +1240,9 @@ struct task_struct { #endif struct list_head tasks; +#ifdef CONFIG_SMP struct plist_node pushable_tasks; +#endif struct mm_struct *mm, *active_mm; #if defined(SPLIT_RSS_COUNTING) -- cgit v1.1 From 67631510a318d5a930055fe927607f483716e100 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Wed, 8 Dec 2010 12:16:33 -0800 Subject: tcp: Replace time wait bucket msg by counter Rather than printing the message to the log, use a mib counter to keep track of the count of occurences of time wait bucket overflow. Reduces spam in logs. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/snmp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/snmp.h b/include/linux/snmp.h index ebb0c80..12b2b18 100644 --- a/include/linux/snmp.h +++ b/include/linux/snmp.h @@ -230,6 +230,7 @@ enum LINUX_MIB_TCPMINTTLDROP, /* RFC 5082 */ LINUX_MIB_TCPDEFERACCEPTDROP, LINUX_MIB_IPRPFILTER, /* IP Reverse Path Filter (rp_filter) */ + LINUX_MIB_TCPTIMEWAITOVERFLOW, /* TCPTimeWaitOverflow */ __LINUX_MIB_MAX }; -- cgit v1.1 From 50b12f597be354a5a224f05c65c54c0667e57aec Mon Sep 17 00:00:00 2001 From: Helmut Schaa Date: Fri, 19 Nov 2010 12:40:25 +0100 Subject: cfg80211: Add new BSS attribute ht_opmode Add a new BSS attribute to allow hostapd to set the current HT opmode. Otherwise drivers won't be able to set up protection for HT rates in AP mode. Cc: Johannes Berg Signed-off-by: Helmut Schaa Signed-off-by: John W. Linville --- include/linux/nl80211.h | 4 ++++ include/net/cfg80211.h | 3 +++ 2 files changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 8e28053..3804212 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -849,6 +849,8 @@ enum nl80211_commands { * flag isn't set, the frame will be rejected. This is also used as an * nl80211 capability flag. * + * @NL80211_ATTR_BSS_HTOPMODE: HT operation mode (u16) + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -1025,6 +1027,8 @@ enum nl80211_attrs { NL80211_ATTR_OFFCHANNEL_TX_OK, + NL80211_ATTR_BSS_HT_OPMODE, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 8764c9a..0d59799 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -605,6 +605,8 @@ struct mpath_info { * (or NULL for no change) * @basic_rates_len: number of basic rates * @ap_isolate: do not forward packets between connected stations + * @ht_opmode: HT Operation mode + * (u16 = opmode, -1 = do not change) */ struct bss_parameters { int use_cts_prot; @@ -613,6 +615,7 @@ struct bss_parameters { u8 *basic_rates; u8 basic_rates_len; int ap_isolate; + int ht_opmode; }; /* -- cgit v1.1 From b7e8941b2df518186d9f7679c007f6b619bb4e89 Mon Sep 17 00:00:00 2001 From: Amitkumar Karwar Date: Tue, 7 Dec 2010 13:43:03 -0800 Subject: cfg80211: add some element IDs in enum ieee80211_eid 1)WLAN_EID_BSS_COEX_2040 2)WLAN_EID_OVERLAP_BSS_SCAN_PARAM 3)WLAN_EID_EXT_CAPABILITY Signed-off-by: Amitkumar Karwar Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index ed5a03c..351c0ab 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1223,6 +1223,9 @@ enum ieee80211_eid { WLAN_EID_BSS_AC_ACCESS_DELAY = 68, WLAN_EID_RRM_ENABLED_CAPABILITIES = 70, WLAN_EID_MULTIPLE_BSSID = 71, + WLAN_EID_BSS_COEX_2040 = 72, + WLAN_EID_OVERLAP_BSS_SCAN_PARAM = 74, + WLAN_EID_EXT_CAPABILITY = 127, WLAN_EID_MOBILITY_DOMAIN = 54, WLAN_EID_FAST_BSS_TRANSITION = 55, -- cgit v1.1 From defb3519a64141608725e2dac5a5aa9a3c644bae Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 8 Dec 2010 21:16:57 -0800 Subject: net: Abstract away all dst_entry metrics accesses. Use helper functions to hide all direct accesses, especially writes, to dst_entry metrics values. This will allow us to: 1) More easily change how the metrics are stored. 2) Implement COW for metrics. In particular this will help us put metrics into the inetpeer cache if that is what we end up doing. We can make the _metrics member a pointer instead of an array, initially have it point at the read-only metrics in the FIB, and then on the first set grab an inetpeer entry and point the _metrics member there. Signed-off-by: David S. Miller Acked-by: Eric Dumazet --- include/net/dst.h | 26 +++++++++++++++++++++++--- 1 file changed, 23 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/dst.h b/include/net/dst.h index a5bd726..85dee3a 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -70,7 +70,7 @@ struct dst_entry { struct dst_ops *ops; - u32 metrics[RTAX_MAX]; + u32 _metrics[RTAX_MAX]; #ifdef CONFIG_NET_CLS_ROUTE __u32 tclassid; @@ -106,7 +106,27 @@ struct dst_entry { static inline u32 dst_metric(const struct dst_entry *dst, int metric) { - return dst->metrics[metric-1]; + return dst->_metrics[metric-1]; +} + +static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val) +{ + dst->_metrics[metric-1] = val; +} + +static inline void dst_import_metrics(struct dst_entry *dst, const u32 *src_metrics) +{ + memcpy(dst->_metrics, src_metrics, RTAX_MAX * sizeof(u32)); +} + +static inline void dst_copy_metrics(struct dst_entry *dest, const struct dst_entry *src) +{ + dst_import_metrics(dest, src->_metrics); +} + +static inline u32 *dst_metrics_ptr(struct dst_entry *dst) +{ + return dst->_metrics; } static inline u32 @@ -134,7 +154,7 @@ static inline unsigned long dst_metric_rtt(const struct dst_entry *dst, int metr static inline void set_dst_metric_rtt(struct dst_entry *dst, int metric, unsigned long rtt) { - dst->metrics[metric-1] = jiffies_to_msecs(rtt); + dst_metric_set(dst, metric, jiffies_to_msecs(rtt)); } static inline u32 -- cgit v1.1 From 96a84c20d635fb1e98ab92f9fc517c4441f5c424 Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Mon, 29 Nov 2010 17:07:16 -0500 Subject: lockup detector: Compile fixes from removing the old x86 nmi watchdog My patch that removed the old x86 nmi watchdog broke other arches. This change reverts a piece of that patch and puts the change in the correct spot. Signed-off-by: Don Zickus Reviewed-by: Cyrill Gorcunov Cc: fweisbec@gmail.com Cc: yinghai@kernel.org LKML-Reference: <1291068437-5331-2-git-send-email-dzickus@redhat.com> Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 1c451e6..17ccf44 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -16,7 +16,8 @@ */ #ifdef ARCH_HAS_NMI_WATCHDOG #include -#endif +extern void touch_nmi_watchdog(void); +#else #ifndef CONFIG_HARDLOCKUP_DETECTOR static inline void touch_nmi_watchdog(void) { @@ -25,6 +26,7 @@ static inline void touch_nmi_watchdog(void) #else extern void touch_nmi_watchdog(void); #endif +#endif /* * Create trigger_all_cpu_backtrace() out of the arch-provided -- cgit v1.1 From 68835aba4d9b74e2f94106d13b6a4bddc447c4c8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 30 Nov 2010 19:04:07 +0000 Subject: net: optimize INET input path further Followup of commit b178bb3dfc30 (net: reorder struct sock fields) Optimize INET input path a bit further, by : 1) moving sk_refcnt close to sk_lock. This reduces number of dirtied cache lines by one on 64bit arches (and 64 bytes cache line size). 2) moving inet_daddr & inet_rcv_saddr at the beginning of sk (same cache line than hash / family / bound_dev_if / nulls_node) This reduces number of accessed cache lines in lookups by one, and dont increase size of inet and timewait socks. inet and tw sockets now share same place-holder for these fields. Before patch : offsetof(struct sock, sk_refcnt) = 0x10 offsetof(struct sock, sk_lock) = 0x40 offsetof(struct sock, sk_receive_queue) = 0x60 offsetof(struct inet_sock, inet_daddr) = 0x270 offsetof(struct inet_sock, inet_rcv_saddr) = 0x274 After patch : offsetof(struct sock, sk_refcnt) = 0x44 offsetof(struct sock, sk_lock) = 0x48 offsetof(struct sock, sk_receive_queue) = 0x68 offsetof(struct inet_sock, inet_daddr) = 0x0 offsetof(struct inet_sock, inet_rcv_saddr) = 0x4 compute_score() (udp or tcp) now use a single cache line per ignored item, instead of two. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_sock.h | 5 +++-- include/net/inet_timewait_sock.h | 20 +++++++------------- include/net/sock.h | 37 ++++++++++++++++++++++++------------- 3 files changed, 34 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 8945f9f..8181498 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -116,8 +116,9 @@ struct inet_sock { struct ipv6_pinfo *pinet6; #endif /* Socket demultiplex comparisons on incoming packets. */ - __be32 inet_daddr; - __be32 inet_rcv_saddr; +#define inet_daddr sk.__sk_common.skc_daddr +#define inet_rcv_saddr sk.__sk_common.skc_rcv_saddr + __be16 inet_dport; __u16 inet_num; __be32 inet_saddr; diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index a066fdd..17404b5 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -88,12 +88,6 @@ extern void inet_twdr_hangman(unsigned long data); extern void inet_twdr_twkill_work(struct work_struct *work); extern void inet_twdr_twcal_tick(unsigned long data); -#if (BITS_PER_LONG == 64) -#define INET_TIMEWAIT_ADDRCMP_ALIGN_BYTES 8 -#else -#define INET_TIMEWAIT_ADDRCMP_ALIGN_BYTES 4 -#endif - struct inet_bind_bucket; /* @@ -117,15 +111,15 @@ struct inet_timewait_sock { #define tw_hash __tw_common.skc_hash #define tw_prot __tw_common.skc_prot #define tw_net __tw_common.skc_net +#define tw_daddr __tw_common.skc_daddr +#define tw_rcv_saddr __tw_common.skc_rcv_saddr int tw_timeout; volatile unsigned char tw_substate; - /* 3 bits hole, try to pack */ unsigned char tw_rcv_wscale; + /* Socket demultiplex comparisons on incoming packets. */ - /* these five are in inet_sock */ + /* these three are in inet_sock */ __be16 tw_sport; - __be32 tw_daddr __attribute__((aligned(INET_TIMEWAIT_ADDRCMP_ALIGN_BYTES))); - __be32 tw_rcv_saddr; __be16 tw_dport; __u16 tw_num; kmemcheck_bitfield_begin(flags); @@ -191,10 +185,10 @@ static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk) return (struct inet_timewait_sock *)sk; } -static inline __be32 inet_rcv_saddr(const struct sock *sk) +static inline __be32 sk_rcv_saddr(const struct sock *sk) { - return likely(sk->sk_state != TCP_TIME_WAIT) ? - inet_sk(sk)->inet_rcv_saddr : inet_twsk(sk)->tw_rcv_saddr; +/* both inet_sk() and inet_twsk() store rcv_saddr in skc_rcv_saddr */ + return sk->__sk_common.skc_rcv_saddr; } extern void inet_twsk_put(struct inet_timewait_sock *tw); diff --git a/include/net/sock.h b/include/net/sock.h index 3482004..82e8603 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -105,10 +105,8 @@ struct net; /** * struct sock_common - minimal network layer representation of sockets - * @skc_node: main hash linkage for various protocol lookup tables - * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol - * @skc_refcnt: reference count - * @skc_tx_queue_mapping: tx queue number for this connection + * @skc_daddr: Foreign IPv4 addr + * @skc_rcv_saddr: Bound local IPv4 addr * @skc_hash: hash value used with various protocol lookup tables * @skc_u16hashes: two u16 hash values used by UDP lookup tables * @skc_family: network address family @@ -119,20 +117,20 @@ struct net; * @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol * @skc_prot: protocol handlers inside a network family * @skc_net: reference to the network namespace of this socket + * @skc_node: main hash linkage for various protocol lookup tables + * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol + * @skc_tx_queue_mapping: tx queue number for this connection + * @skc_refcnt: reference count * * This is the minimal network layer representation of sockets, the header * for struct sock and struct inet_timewait_sock. */ struct sock_common { - /* - * first fields are not copied in sock_copy() + /* skc_daddr and skc_rcv_saddr must be grouped : + * cf INET_MATCH() and INET_TW_MATCH() */ - union { - struct hlist_node skc_node; - struct hlist_nulls_node skc_nulls_node; - }; - atomic_t skc_refcnt; - int skc_tx_queue_mapping; + __be32 skc_daddr; + __be32 skc_rcv_saddr; union { unsigned int skc_hash; @@ -150,6 +148,18 @@ struct sock_common { #ifdef CONFIG_NET_NS struct net *skc_net; #endif + /* + * fields between dontcopy_begin/dontcopy_end + * are not copied in sock_copy() + */ + int skc_dontcopy_begin[0]; + union { + struct hlist_node skc_node; + struct hlist_nulls_node skc_nulls_node; + }; + int skc_tx_queue_mapping; + atomic_t skc_refcnt; + int skc_dontcopy_end[0]; }; /** @@ -232,7 +242,8 @@ struct sock { #define sk_refcnt __sk_common.skc_refcnt #define sk_tx_queue_mapping __sk_common.skc_tx_queue_mapping -#define sk_copy_start __sk_common.skc_hash +#define sk_dontcopy_begin __sk_common.skc_dontcopy_begin +#define sk_dontcopy_end __sk_common.skc_dontcopy_end #define sk_hash __sk_common.skc_hash #define sk_family __sk_common.skc_family #define sk_state __sk_common.skc_state -- cgit v1.1 From 60d509c823cca21e77d537bd356785f7cfe8f0d1 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Fri, 3 Dec 2010 02:39:01 +0000 Subject: The new jhash implementation The current jhash.h implements the lookup2() hash function by Bob Jenkins. However, lookup2() is outdated as Bob wrote a new hash function called lookup3(). The patch replaces the lookup2() implementation of the 'jhash*' functions with that of lookup3(). You can read a longer comparison of the two and other hash functions at http://burtleburtle.net/bob/hash/doobs.html. Signed-off-by: Jozsef Kadlecsik Acked-by: Rusty Russell Signed-off-by: David S. Miller --- include/linux/jhash.h | 183 +++++++++++++++++++++++++++++--------------------- 1 file changed, 105 insertions(+), 78 deletions(-) (limited to 'include') diff --git a/include/linux/jhash.h b/include/linux/jhash.h index ced1159..47cb09e 100644 --- a/include/linux/jhash.h +++ b/include/linux/jhash.h @@ -3,129 +3,156 @@ /* jhash.h: Jenkins hash support. * - * Copyright (C) 1996 Bob Jenkins (bob_jenkins@burtleburtle.net) + * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net) * * http://burtleburtle.net/bob/hash/ * * These are the credits from Bob's sources: * - * lookup2.c, by Bob Jenkins, December 1996, Public Domain. - * hash(), hash2(), hash3, and mix() are externally useful functions. - * Routines to test the hash are included if SELF_TEST is defined. - * You can use this free for any purpose. It has no warranty. + * lookup3.c, by Bob Jenkins, May 2006, Public Domain. * - * Copyright (C) 2003 David S. Miller (davem@redhat.com) + * These are functions for producing 32-bit hashes for hash table lookup. + * hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final() + * are externally useful functions. Routines to test the hash are included + * if SELF_TEST is defined. You can use this free for any purpose. It's in + * the public domain. It has no warranty. + * + * Copyright (C) 2009-2010 Jozsef Kadlecsik (kadlec@blackhole.kfki.hu) * * I've modified Bob's hash to be useful in the Linux kernel, and - * any bugs present are surely my fault. -DaveM + * any bugs present are my fault. + * Jozsef */ +#include +#include + +/* Best hash sizes are of power of two */ +#define jhash_size(n) ((u32)1<<(n)) +/* Mask the hash value, i.e (value & jhash_mask(n)) instead of (value % n) */ +#define jhash_mask(n) (jhash_size(n)-1) + +/* __jhash_mix -- mix 3 32-bit values reversibly. */ +#define __jhash_mix(a, b, c) \ +{ \ + a -= c; a ^= rol32(c, 4); c += b; \ + b -= a; b ^= rol32(a, 6); a += c; \ + c -= b; c ^= rol32(b, 8); b += a; \ + a -= c; a ^= rol32(c, 16); c += b; \ + b -= a; b ^= rol32(a, 19); a += c; \ + c -= b; c ^= rol32(b, 4); b += a; \ +} -/* NOTE: Arguments are modified. */ -#define __jhash_mix(a, b, c) \ -{ \ - a -= b; a -= c; a ^= (c>>13); \ - b -= c; b -= a; b ^= (a<<8); \ - c -= a; c -= b; c ^= (b>>13); \ - a -= b; a -= c; a ^= (c>>12); \ - b -= c; b -= a; b ^= (a<<16); \ - c -= a; c -= b; c ^= (b>>5); \ - a -= b; a -= c; a ^= (c>>3); \ - b -= c; b -= a; b ^= (a<<10); \ - c -= a; c -= b; c ^= (b>>15); \ +/* __jhash_final - final mixing of 3 32-bit values (a,b,c) into c */ +#define __jhash_final(a, b, c) \ +{ \ + c ^= b; c -= rol32(b, 14); \ + a ^= c; a -= rol32(c, 11); \ + b ^= a; b -= rol32(a, 25); \ + c ^= b; c -= rol32(b, 16); \ + a ^= c; a -= rol32(c, 4); \ + b ^= a; b -= rol32(a, 14); \ + c ^= b; c -= rol32(b, 24); \ } -/* The golden ration: an arbitrary value */ -#define JHASH_GOLDEN_RATIO 0x9e3779b9 +/* An arbitrary initial parameter */ +#define JHASH_INITVAL 0xdeadbeef -/* The most generic version, hashes an arbitrary sequence - * of bytes. No alignment or length assumptions are made about - * the input key. +/* jhash - hash an arbitrary key + * @k: sequence of bytes as key + * @length: the length of the key + * @initval: the previous hash, or an arbitray value + * + * The generic version, hashes an arbitrary sequence of bytes. + * No alignment or length assumptions are made about the input key. + * + * Returns the hash value of the key. The result depends on endianness. */ static inline u32 jhash(const void *key, u32 length, u32 initval) { - u32 a, b, c, len; + u32 a, b, c; const u8 *k = key; - len = length; - a = b = JHASH_GOLDEN_RATIO; - c = initval; - - while (len >= 12) { - a += (k[0] +((u32)k[1]<<8) +((u32)k[2]<<16) +((u32)k[3]<<24)); - b += (k[4] +((u32)k[5]<<8) +((u32)k[6]<<16) +((u32)k[7]<<24)); - c += (k[8] +((u32)k[9]<<8) +((u32)k[10]<<16)+((u32)k[11]<<24)); - - __jhash_mix(a,b,c); + /* Set up the internal state */ + a = b = c = JHASH_INITVAL + length + initval; + /* All but the last block: affect some 32 bits of (a,b,c) */ + while (length > 12) { + a += __get_unaligned_cpu32(k); + b += __get_unaligned_cpu32(k + 4); + c += __get_unaligned_cpu32(k + 8); + __jhash_mix(a, b, c); + length -= 12; k += 12; - len -= 12; } - - c += length; - switch (len) { - case 11: c += ((u32)k[10]<<24); - case 10: c += ((u32)k[9]<<16); - case 9 : c += ((u32)k[8]<<8); - case 8 : b += ((u32)k[7]<<24); - case 7 : b += ((u32)k[6]<<16); - case 6 : b += ((u32)k[5]<<8); - case 5 : b += k[4]; - case 4 : a += ((u32)k[3]<<24); - case 3 : a += ((u32)k[2]<<16); - case 2 : a += ((u32)k[1]<<8); - case 1 : a += k[0]; - }; - - __jhash_mix(a,b,c); + /* Last block: affect all 32 bits of (c) */ + /* All the case statements fall through */ + switch (length) { + case 12: c += (u32)k[11]<<24; + case 11: c += (u32)k[10]<<16; + case 10: c += (u32)k[9]<<8; + case 9: c += k[8]; + case 8: b += (u32)k[7]<<24; + case 7: b += (u32)k[6]<<16; + case 6: b += (u32)k[5]<<8; + case 5: b += k[4]; + case 4: a += (u32)k[3]<<24; + case 3: a += (u32)k[2]<<16; + case 2: a += (u32)k[1]<<8; + case 1: a += k[0]; + __jhash_final(a, b, c); + case 0: /* Nothing left to add */ + break; + } return c; } -/* A special optimized version that handles 1 or more of u32s. - * The length parameter here is the number of u32s in the key. +/* jhash2 - hash an array of u32's + * @k: the key which must be an array of u32's + * @length: the number of u32's in the key + * @initval: the previous hash, or an arbitray value + * + * Returns the hash value of the key. */ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) { - u32 a, b, c, len; + u32 a, b, c; - a = b = JHASH_GOLDEN_RATIO; - c = initval; - len = length; + /* Set up the internal state */ + a = b = c = JHASH_INITVAL + (length<<2) + initval; - while (len >= 3) { + /* Handle most of the key */ + while (length > 3) { a += k[0]; b += k[1]; c += k[2]; __jhash_mix(a, b, c); - k += 3; len -= 3; + length -= 3; + k += 3; } - c += length * 4; - - switch (len) { - case 2 : b += k[1]; - case 1 : a += k[0]; - }; - - __jhash_mix(a,b,c); + /* Handle the last 3 u32's: all the case statements fall through */ + switch (length) { + case 3: c += k[2]; + case 2: b += k[1]; + case 1: a += k[0]; + __jhash_final(a, b, c); + case 0: /* Nothing left to add */ + break; + } return c; } -/* A special ultra-optimized versions that knows they are hashing exactly - * 3, 2 or 1 word(s). - * - * NOTE: In particular the "c += length; __jhash_mix(a,b,c);" normally - * done at the end is not done here. - */ +/* jhash_3words - hash exactly 3, 2 or 1 word(s) */ static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval) { - a += JHASH_GOLDEN_RATIO; - b += JHASH_GOLDEN_RATIO; + a += JHASH_INITVAL; + b += JHASH_INITVAL; c += initval; - __jhash_mix(a, b, c); + __jhash_final(a, b, c); return c; } -- cgit v1.1 From 05ac10dd6862a3fcce33d2203fbb2ef285e3ca87 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Thu, 2 Dec 2010 08:49:26 +0200 Subject: usb: musb: trivial search and replace patch change all ocurrences of musb_hdrc to musb-hdrc. We will call glue layer drivers musb-, so in order to keep things somewhat standard, let's change the underscore into a dash. Signed-off-by: Felipe Balbi --- include/linux/usb/musb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/usb/musb.h b/include/linux/usb/musb.h index ee2dd1d..e2191d4 100644 --- a/include/linux/usb/musb.h +++ b/include/linux/usb/musb.h @@ -3,7 +3,7 @@ * Inventra (Multidrop) Highspeed Dual-Role Controllers: (M)HDRC. * * Board initialization should put one of these into dev->platform_data, - * probably on some platform_device named "musb_hdrc". It encapsulates + * probably on some platform_device named "musb-hdrc". It encapsulates * key configuration differences between boards. */ -- cgit v1.1 From f7ec94370f417fedad4db1054228ef958d48b926 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Thu, 2 Dec 2010 09:48:58 +0200 Subject: usb: musb: pass platform_ops via platform_data ... then we don't need to export any symbols from glue layer to musb_core. Signed-off-by: Felipe Balbi --- include/linux/usb/musb.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/usb/musb.h b/include/linux/usb/musb.h index e2191d4..6f4e501 100644 --- a/include/linux/usb/musb.h +++ b/include/linux/usb/musb.h @@ -126,6 +126,9 @@ struct musb_hdrc_platform_data { /* Architecture specific board data */ void *board_data; + + /* Platform specific struct musb_ops pointer */ + const void *platform_ops; }; -- cgit v1.1 From 3b7029670d39d22f288ece95254e9ba5ceddd6ba Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Thu, 2 Dec 2010 09:51:00 +0200 Subject: usb: musb: mark ->set_clock deprecated ... we will completely drop that need by moving clock handling to platform glue layer. Marking as deprecated will allow us to catch all users easily. Signed-off-by: Felipe Balbi --- include/linux/usb/musb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/usb/musb.h b/include/linux/usb/musb.h index 6f4e501..0b72b57 100644 --- a/include/linux/usb/musb.h +++ b/include/linux/usb/musb.h @@ -119,7 +119,7 @@ struct musb_hdrc_platform_data { int (*set_power)(int state); /* Turn device clock on or off */ - int (*set_clock)(struct clk *clock, int is_on); + int (*set_clock)(struct clk *clock, int is_on) __deprecated; /* MUSB configuration-specific details */ struct musb_hdrc_config *config; -- cgit v1.1 From fa56df915d101770a495569473b4c13b1904087b Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Thu, 2 Dec 2010 10:55:29 +0200 Subject: usb: musb: drop the set_clock magic now that platform glue layer handles clock completely, that function is completely useless for us. Drop it. Signed-off-by: Felipe Balbi --- include/linux/usb/musb.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/usb/musb.h b/include/linux/usb/musb.h index 0b72b57..0b0e383 100644 --- a/include/linux/usb/musb.h +++ b/include/linux/usb/musb.h @@ -118,9 +118,6 @@ struct musb_hdrc_platform_data { /* Power the device on or off */ int (*set_power)(int state); - /* Turn device clock on or off */ - int (*set_clock)(struct clk *clock, int is_on) __deprecated; - /* MUSB configuration-specific details */ struct musb_hdrc_config *config; -- cgit v1.1 From e70357e35c522776d9f56f6800af4ed7a5bdbaaf Mon Sep 17 00:00:00 2001 From: Hema HK Date: Fri, 10 Dec 2010 18:09:52 +0530 Subject: mfd: TWL6030: OMAP4: Registering the TWL6030-usb device Registering the twl6030-usb transceiver device as a child to twl6030 core. Removed the NOP transceiver init call from board file. Populated twl4030_usb_data platform data structure with the function pointers for OMAP4430 internal PHY operation to be used by twl630-usb driver. Signed-off-by: Hema HK Cc: Samuel Ortiz Cc: Tony Lindgren Signed-off-by: Felipe Balbi --- include/linux/i2c/twl.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/i2c/twl.h b/include/linux/i2c/twl.h index c760991..61b9609 100644 --- a/include/linux/i2c/twl.h +++ b/include/linux/i2c/twl.h @@ -593,6 +593,13 @@ enum twl4030_usb_mode { struct twl4030_usb_data { enum twl4030_usb_mode usb_mode; + + int (*phy_init)(struct device *dev); + int (*phy_exit)(struct device *dev); + /* Power on/off the PHY */ + int (*phy_power)(struct device *dev, int iD, int on); + /* enable/disable phy clocks */ + int (*phy_set_clock)(struct device *dev, int on); }; struct twl4030_ins { -- cgit v1.1 From dac36dd87de10d1fd81dc7b7a40256cb2e965abc Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 10 Dec 2010 01:57:07 +0900 Subject: poll: fix a typo in comment Convert duplicated sys_poll to select. As Kosaki suggests, sys_poll() and sys_select() are now hidden by SYSCALL_DEFINEx() macros so it would be better to use plain select/poll syscall name. Signed-off-by: Namhyung Kim Reviewed-by: KOSAKI Motohiro Signed-off-by: Jiri Kosina --- include/linux/poll.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/poll.h b/include/linux/poll.h index 56e76af..1a2ccd6 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -57,7 +57,7 @@ struct poll_table_entry { }; /* - * Structures and helpers for sys_poll/sys_poll + * Structures and helpers for select/poll syscall */ struct poll_wqueues { poll_table pt; -- cgit v1.1 From 4291ee305e9bb0699504a66f0e2b7aefcf0512a5 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 9 Dec 2010 19:29:03 -0800 Subject: HID: Add and use hid_: dev_ equivalents Neaten current uses of dev_ by adding and using hid specific hid_ macros. Convert existing uses of dev_ uses to hid_. Convert hid-pidff printk uses to hid_. Remove err_hid and use hid_err instead. Add missing newlines to logging messages where necessary. Coalesce format strings. Add and use pr_fmt(fmt) KBUILD_MODNAME ": " fmt Other miscellaneous changes: Add const struct hid_device * argument to hid-core functions extract() and implement() so hid_ can be used by them. Fix bad indentation in hid-core hid_input_field function that calls extract() function above. Signed-off-by: Joe Perches Signed-off-by: Jiri Kosina --- include/linux/hid.h | 32 ++++++++++++++++++++++++++------ 1 file changed, 26 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/hid.h b/include/linux/hid.h index e2af195..20b9801 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -881,12 +881,32 @@ int hid_pidff_init(struct hid_device *hid); #define hid_pidff_init NULL #endif -#define dbg_hid(format, arg...) if (hid_debug) \ - printk(KERN_DEBUG "%s: " format ,\ - __FILE__ , ## arg) -#define err_hid(format, arg...) printk(KERN_ERR "%s: " format "\n" , \ - __FILE__ , ## arg) -#endif /* HID_FF */ +#define dbg_hid(format, arg...) \ +do { \ + if (hid_debug) \ + printk(KERN_DEBUG "%s: " format, __FILE__, ##arg); \ +} while (0) + +#define hid_printk(level, hid, fmt, arg...) \ + dev_printk(level, &(hid)->dev, fmt, ##arg) +#define hid_emerg(hid, fmt, arg...) \ + dev_emerg(&(hid)->dev, fmt, ##arg) +#define hid_crit(hid, fmt, arg...) \ + dev_crit(&(hid)->dev, fmt, ##arg) +#define hid_alert(hid, fmt, arg...) \ + dev_alert(&(hid)->dev, fmt, ##arg) +#define hid_err(hid, fmt, arg...) \ + dev_err(&(hid)->dev, fmt, ##arg) +#define hid_notice(hid, fmt, arg...) \ + dev_notice(&(hid)->dev, fmt, ##arg) +#define hid_warn(hid, fmt, arg...) \ + dev_warn(&(hid)->dev, fmt, ##arg) +#define hid_info(hid, fmt, arg...) \ + dev_info(&(hid)->dev, fmt, ##arg) +#define hid_dbg(hid, fmt, arg...) \ + dev_dbg(&(hid)->dev, fmt, ##arg) + +#endif /* __KERNEL__ */ #endif -- cgit v1.1 From 1f5a24794a54588ea3a9efd521be31d826e0b9d7 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 9 Dec 2010 12:02:18 -0800 Subject: timers: Rename timerlist infrastructure to timerqueue Thomas pointed out a namespace collision between the new timerlist infrastructure I introduced and the existing timer_list.c So to avoid confusion, I've renamed the timerlist infrastructure to timerqueue. Reported-by: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/timerlist.h | 37 ------------------------------------- include/linux/timerqueue.h | 37 +++++++++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+), 37 deletions(-) delete mode 100644 include/linux/timerlist.h create mode 100644 include/linux/timerqueue.h (limited to 'include') diff --git a/include/linux/timerlist.h b/include/linux/timerlist.h deleted file mode 100644 index c46b28a..0000000 --- a/include/linux/timerlist.h +++ /dev/null @@ -1,37 +0,0 @@ -#ifndef _LINUX_TIMERLIST_H -#define _LINUX_TIMERLIST_H - -#include -#include - - -struct timerlist_node { - struct rb_node node; - ktime_t expires; -}; - -struct timerlist_head { - struct rb_root head; - struct timerlist_node *next; -}; - - -extern void timerlist_add(struct timerlist_head *head, - struct timerlist_node *node); -extern void timerlist_del(struct timerlist_head *head, - struct timerlist_node *node); -extern struct timerlist_node *timerlist_getnext(struct timerlist_head *head); -extern struct timerlist_node *timerlist_iterate_next( - struct timerlist_node *node); - -static inline void timerlist_init(struct timerlist_node *node) -{ - RB_CLEAR_NODE(&node->node); -} - -static inline void timerlist_init_head(struct timerlist_head *head) -{ - head->head = RB_ROOT; - head->next = NULL; -} -#endif /* _LINUX_TIMERLIST_H */ diff --git a/include/linux/timerqueue.h b/include/linux/timerqueue.h new file mode 100644 index 0000000..406b103 --- /dev/null +++ b/include/linux/timerqueue.h @@ -0,0 +1,37 @@ +#ifndef _LINUX_TIMERQUEUE_H +#define _LINUX_TIMERQUEUE_H + +#include +#include + + +struct timerqueue_node { + struct rb_node node; + ktime_t expires; +}; + +struct timerqueue_head { + struct rb_root head; + struct timerqueue_node *next; +}; + + +extern void timerqueue_add(struct timerqueue_head *head, + struct timerqueue_node *node); +extern void timerqueue_del(struct timerqueue_head *head, + struct timerqueue_node *node); +extern struct timerqueue_node *timerqueue_getnext(struct timerqueue_head *head); +extern struct timerqueue_node *timerqueue_iterate_next( + struct timerqueue_node *node); + +static inline void timerqueue_init(struct timerqueue_node *node) +{ + RB_CLEAR_NODE(&node->node); +} + +static inline void timerqueue_init_head(struct timerqueue_head *head) +{ + head->head = RB_ROOT; + head->next = NULL; +} +#endif /* _LINUX_TIMERQUEUE_H */ -- cgit v1.1 From 998adc3dda59f811966b3ccb21eb223680b25ec4 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Mon, 20 Sep 2010 19:19:17 -0700 Subject: hrtimers: Convert hrtimers to use timerlist infrastructure Converts the hrtimer code to use the new timerlist infrastructure Signed-off-by: John Stultz LKML Reference: <1290136329-18291-3-git-send-email-john.stultz@linaro.org> Reviewed-by: Thomas Gleixner CC: Alessandro Zummo CC: Thomas Gleixner CC: Richard Cochran --- include/linux/hrtimer.h | 32 +++++++++++++++----------------- 1 file changed, 15 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index dd9954b..330586f 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -22,7 +22,7 @@ #include #include #include - +#include struct hrtimer_clock_base; struct hrtimer_cpu_base; @@ -79,8 +79,8 @@ enum hrtimer_restart { /** * struct hrtimer - the basic hrtimer structure - * @node: red black tree node for time ordered insertion - * @_expires: the absolute expiry time in the hrtimers internal + * @node: timerqueue node, which also manages node.expires, + * the absolute expiry time in the hrtimers internal * representation. The time is related to the clock on * which the timer is based. Is setup by adding * slack to the _softexpires value. For non range timers @@ -101,8 +101,7 @@ enum hrtimer_restart { * The hrtimer structure must be initialized by hrtimer_init() */ struct hrtimer { - struct rb_node node; - ktime_t _expires; + struct timerqueue_node node; ktime_t _softexpires; enum hrtimer_restart (*function)(struct hrtimer *); struct hrtimer_clock_base *base; @@ -141,8 +140,7 @@ struct hrtimer_sleeper { struct hrtimer_clock_base { struct hrtimer_cpu_base *cpu_base; clockid_t index; - struct rb_root active; - struct rb_node *first; + struct timerqueue_head active; ktime_t resolution; ktime_t (*get_time)(void); ktime_t softirq_time; @@ -183,43 +181,43 @@ struct hrtimer_cpu_base { static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time) { - timer->_expires = time; + timer->node.expires = time; timer->_softexpires = time; } static inline void hrtimer_set_expires_range(struct hrtimer *timer, ktime_t time, ktime_t delta) { timer->_softexpires = time; - timer->_expires = ktime_add_safe(time, delta); + timer->node.expires = ktime_add_safe(time, delta); } static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, unsigned long delta) { timer->_softexpires = time; - timer->_expires = ktime_add_safe(time, ns_to_ktime(delta)); + timer->node.expires = ktime_add_safe(time, ns_to_ktime(delta)); } static inline void hrtimer_set_expires_tv64(struct hrtimer *timer, s64 tv64) { - timer->_expires.tv64 = tv64; + timer->node.expires.tv64 = tv64; timer->_softexpires.tv64 = tv64; } static inline void hrtimer_add_expires(struct hrtimer *timer, ktime_t time) { - timer->_expires = ktime_add_safe(timer->_expires, time); + timer->node.expires = ktime_add_safe(timer->node.expires, time); timer->_softexpires = ktime_add_safe(timer->_softexpires, time); } static inline void hrtimer_add_expires_ns(struct hrtimer *timer, u64 ns) { - timer->_expires = ktime_add_ns(timer->_expires, ns); + timer->node.expires = ktime_add_ns(timer->node.expires, ns); timer->_softexpires = ktime_add_ns(timer->_softexpires, ns); } static inline ktime_t hrtimer_get_expires(const struct hrtimer *timer) { - return timer->_expires; + return timer->node.expires; } static inline ktime_t hrtimer_get_softexpires(const struct hrtimer *timer) @@ -229,7 +227,7 @@ static inline ktime_t hrtimer_get_softexpires(const struct hrtimer *timer) static inline s64 hrtimer_get_expires_tv64(const struct hrtimer *timer) { - return timer->_expires.tv64; + return timer->node.expires.tv64; } static inline s64 hrtimer_get_softexpires_tv64(const struct hrtimer *timer) { @@ -238,12 +236,12 @@ static inline s64 hrtimer_get_softexpires_tv64(const struct hrtimer *timer) static inline s64 hrtimer_get_expires_ns(const struct hrtimer *timer) { - return ktime_to_ns(timer->_expires); + return ktime_to_ns(timer->node.expires); } static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer) { - return ktime_sub(timer->_expires, timer->base->get_time()); + return ktime_sub(timer->node.expires, timer->base->get_time()); } #ifdef CONFIG_HIGH_RES_TIMERS -- cgit v1.1 From 352a337832774a6929c16b569abe9cedc3db01cc Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Thu, 9 Dec 2010 22:46:29 +0100 Subject: USB: otg: fix link breakage, when the NOP USB Xceiver is a module If the NOP USB OTG transceiver driver is built as a module, the otg.h header declares external functions, but if they are referenced from the kernel proper, as, e.g., in the OMAP3 case, where the omap3evm board is calling the usb_nop_xceiv_register() function, linkage breaks. This patch fixes this problem. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/otg.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/usb/otg.h b/include/linux/usb/otg.h index 0a5b371..a1a1e7a 100644 --- a/include/linux/usb/otg.h +++ b/include/linux/usb/otg.h @@ -116,7 +116,7 @@ struct otg_transceiver { /* for board-specific init logic */ extern int otg_set_transceiver(struct otg_transceiver *); -#if defined(CONFIG_NOP_USB_XCEIV) || defined(CONFIG_NOP_USB_XCEIV_MODULE) +#if defined(CONFIG_NOP_USB_XCEIV) || (defined(CONFIG_NOP_USB_XCEIV_MODULE) && defined(MODULE)) /* sometimes transceivers are accessed only through e.g. ULPI */ extern void usb_nop_xceiv_register(void); extern void usb_nop_xceiv_unregister(void); -- cgit v1.1 From e0c201f339fe7fc38d1b0f6f4755ff627686c7e0 Mon Sep 17 00:00:00 2001 From: Pavankumar Kondeti Date: Tue, 7 Dec 2010 17:53:55 +0530 Subject: USB: Add MSM OTG Controller driver This driver implements PHY initialization, clock management, ULPI IO ops and simple OTG state machine to kick host/peripheral based on Id/VBUS line status. VBUS/Id lines are tied to a reference voltage on some boards. Hence provide debugfs interface to select host/peripheral mode. Signed-off-by: Pavankumar Kondeti Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/msm_hsusb.h | 108 +++++++++++++++++++++++++++++++++++++++ include/linux/usb/msm_hsusb_hw.h | 56 ++++++++++++++++++++ 2 files changed, 164 insertions(+) create mode 100644 include/linux/usb/msm_hsusb.h create mode 100644 include/linux/usb/msm_hsusb_hw.h (limited to 'include') diff --git a/include/linux/usb/msm_hsusb.h b/include/linux/usb/msm_hsusb.h new file mode 100644 index 0000000..b796df9 --- /dev/null +++ b/include/linux/usb/msm_hsusb.h @@ -0,0 +1,108 @@ +/* linux/include/asm-arm/arch-msm/hsusb.h + * + * Copyright (C) 2008 Google, Inc. + * Author: Brian Swetland + * Copyright (c) 2009-2010, Code Aurora Forum. All rights reserved. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#ifndef __ASM_ARCH_MSM_HSUSB_H +#define __ASM_ARCH_MSM_HSUSB_H + +#include +#include + +/** + * Supported USB modes + * + * USB_PERIPHERAL Only peripheral mode is supported. + * USB_HOST Only host mode is supported. + * USB_OTG OTG mode is supported. + * + */ +enum usb_mode_type { + USB_NONE = 0, + USB_PERIPHERAL, + USB_HOST, + USB_OTG, +}; + +/** + * OTG control + * + * OTG_NO_CONTROL Id/VBUS notifications not required. Useful in host + * only configuration. + * OTG_PHY_CONTROL Id/VBUS notifications comes form USB PHY. + * OTG_PMIC_CONTROL Id/VBUS notifications comes from PMIC hardware. + * OTG_USER_CONTROL Id/VBUS notifcations comes from User via sysfs. + * + */ +enum otg_control_type { + OTG_NO_CONTROL = 0, + OTG_PHY_CONTROL, + OTG_PMIC_CONTROL, + OTG_USER_CONTROL, +}; + +/** + * struct msm_otg_platform_data - platform device data + * for msm72k_otg driver. + * @phy_init_seq: PHY configuration sequence. val, reg pairs + * terminated by -1. + * @vbus_power: VBUS power on/off routine. + * @power_budget: VBUS power budget in mA (0 will be treated as 500mA). + * @mode: Supported mode (OTG/peripheral/host). + * @otg_control: OTG switch controlled by user/Id pin + * @default_mode: Default operational mode. Applicable only if + * OTG switch is controller by user. + * + */ +struct msm_otg_platform_data { + int *phy_init_seq; + void (*vbus_power)(bool on); + unsigned power_budget; + enum usb_mode_type mode; + enum otg_control_type otg_control; + enum usb_mode_type default_mode; + void (*setup_gpio)(enum usb_otg_state state); +}; + +/** + * struct msm_otg: OTG driver data. Shared by HCD and DCD. + * @otg: USB OTG Transceiver structure. + * @pdata: otg device platform data. + * @irq: IRQ number assigned for HSUSB controller. + * @clk: clock struct of usb_hs_clk. + * @pclk: clock struct of usb_hs_pclk. + * @phy_reset_clk: clock struct of usb_phy_clk. + * @core_clk: clock struct of usb_hs_core_clk. + * @regs: ioremapped register base address. + * @inputs: OTG state machine inputs(Id, SessValid etc). + * @sm_work: OTG state machine work. + * + */ +struct msm_otg { + struct otg_transceiver otg; + struct msm_otg_platform_data *pdata; + int irq; + struct clk *clk; + struct clk *pclk; + struct clk *phy_reset_clk; + struct clk *core_clk; + void __iomem *regs; +#define ID 0 +#define B_SESS_VLD 1 + unsigned long inputs; + struct work_struct sm_work; +}; + +#endif diff --git a/include/linux/usb/msm_hsusb_hw.h b/include/linux/usb/msm_hsusb_hw.h new file mode 100644 index 0000000..b061cff --- /dev/null +++ b/include/linux/usb/msm_hsusb_hw.h @@ -0,0 +1,56 @@ +/* + * Copyright (C) 2007 Google, Inc. + * Author: Brian Swetland + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#ifndef __LINUX_USB_GADGET_MSM72K_UDC_H__ +#define __LINUX_USB_GADGET_MSM72K_UDC_H__ + +#ifdef CONFIG_ARCH_MSM7X00A +#define USB_SBUSCFG (MSM_USB_BASE + 0x0090) +#else +#define USB_AHBBURST (MSM_USB_BASE + 0x0090) +#define USB_AHBMODE (MSM_USB_BASE + 0x0098) +#endif +#define USB_CAPLENGTH (MSM_USB_BASE + 0x0100) /* 8 bit */ + +#define USB_USBCMD (MSM_USB_BASE + 0x0140) +#define USB_PORTSC (MSM_USB_BASE + 0x0184) +#define USB_OTGSC (MSM_USB_BASE + 0x01A4) +#define USB_USBMODE (MSM_USB_BASE + 0x01A8) + +#define USBCMD_RESET 2 +#define USB_USBINTR (MSM_USB_BASE + 0x0148) + +#define PORTSC_PHCD (1 << 23) /* phy suspend mode */ +#define PORTSC_PTS_MASK (3 << 30) +#define PORTSC_PTS_ULPI (3 << 30) + +#define USB_ULPI_VIEWPORT (MSM_USB_BASE + 0x0170) +#define ULPI_RUN (1 << 30) +#define ULPI_WRITE (1 << 29) +#define ULPI_READ (0 << 29) +#define ULPI_ADDR(n) (((n) & 255) << 16) +#define ULPI_DATA(n) ((n) & 255) +#define ULPI_DATA_READ(n) (((n) >> 8) & 255) + +/* OTG definitions */ +#define OTGSC_INTSTS_MASK (0x7f << 16) +#define OTGSC_ID (1 << 8) +#define OTGSC_BSV (1 << 11) +#define OTGSC_IDIS (1 << 16) +#define OTGSC_BSVIS (1 << 19) +#define OTGSC_IDIE (1 << 24) +#define OTGSC_BSVIE (1 << 27) + +#endif /* __LINUX_USB_GADGET_MSM72K_UDC_H__ */ -- cgit v1.1 From 87c0104af742af2acfcbd685f2b9a40f33770dc0 Mon Sep 17 00:00:00 2001 From: Pavankumar Kondeti Date: Tue, 7 Dec 2010 17:53:58 +0530 Subject: USB: OTG: msm: Add support for power management Implement runtime and system pm ops to put hardware into low power mode (LPM). As part of LPM, USB clocks are turned off, PHY is put into suspend state and PHY comparators are turned off if VBUS/Id notifications are not required from PHY. Signed-off-by: Pavankumar Kondeti Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/msm_hsusb.h | 4 ++++ include/linux/usb/msm_hsusb_hw.h | 3 +++ 2 files changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/usb/msm_hsusb.h b/include/linux/usb/msm_hsusb.h index b796df9..3675e03 100644 --- a/include/linux/usb/msm_hsusb.h +++ b/include/linux/usb/msm_hsusb.h @@ -88,6 +88,8 @@ struct msm_otg_platform_data { * @regs: ioremapped register base address. * @inputs: OTG state machine inputs(Id, SessValid etc). * @sm_work: OTG state machine work. + * @in_lpm: indicates low power mode (LPM) state. + * @async_int: Async interrupt arrived. * */ struct msm_otg { @@ -103,6 +105,8 @@ struct msm_otg { #define B_SESS_VLD 1 unsigned long inputs; struct work_struct sm_work; + atomic_t in_lpm; + int async_int; }; #endif diff --git a/include/linux/usb/msm_hsusb_hw.h b/include/linux/usb/msm_hsusb_hw.h index b061cff..b92e173 100644 --- a/include/linux/usb/msm_hsusb_hw.h +++ b/include/linux/usb/msm_hsusb_hw.h @@ -44,6 +44,9 @@ #define ULPI_DATA(n) ((n) & 255) #define ULPI_DATA_READ(n) (((n) >> 8) & 255) +#define ASYNC_INTR_CTRL (1 << 29) /* Enable async interrupt */ +#define ULPI_STP_CTRL (1 << 30) /* Block communication with PHY */ + /* OTG definitions */ #define OTGSC_INTSTS_MASK (0x7f << 16) #define OTGSC_ID (1 << 8) -- cgit v1.1 From 35d2856b4693e8de5d616307b56cef296b839157 Mon Sep 17 00:00:00 2001 From: Martin Willi Date: Wed, 8 Dec 2010 04:37:49 +0000 Subject: xfrm: Add Traffic Flow Confidentiality padding XFRM attribute The XFRMA_TFCPAD attribute for XFRM state installation configures Traffic Flow Confidentiality by padding ESP packets to a specified length. Signed-off-by: Martin Willi Acked-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/xfrm.h | 1 + include/net/xfrm.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index b971e38..930fdd2 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -283,6 +283,7 @@ enum xfrm_attr_type_t { XFRMA_KMADDRESS, /* struct xfrm_user_kmaddress */ XFRMA_ALG_AUTH_TRUNC, /* struct xfrm_algo_auth */ XFRMA_MARK, /* struct xfrm_mark */ + XFRMA_TFCPAD, /* __u32 */ __XFRMA_MAX #define XFRMA_MAX (__XFRMA_MAX - 1) diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 7fa5b00..b9f385d 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -143,6 +143,7 @@ struct xfrm_state { struct xfrm_id id; struct xfrm_selector sel; struct xfrm_mark mark; + u32 tfcpad; u32 genid; -- cgit v1.1 From a3ae0fc34f58e7163b7724feb3d77aa4603f0dc3 Mon Sep 17 00:00:00 2001 From: Jamie Iles Date: Wed, 1 Dec 2010 23:39:36 +0000 Subject: 8250: add a UPIO_DWAPB32 for 32 bit accesses Some platforms contain a Synopsys DesignWare APB UART that is attached to a 32-bit APB bus where sub-word accesses are not allowed. Add a new IO type (UPIO_DWAPB32) that performs 32 bit acccesses to the UART. v2: - don't test for 32 bit in the output fast path, provide a separate dwabp32_serial_out() function. Refactor dwabp_serial_out() so that we can reuse the LCR saving code. v3: - rebased on top of "8250: use container_of() instead of casting" Signed-off-by: Jamie Iles Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 9ff9b7d..7a6daf1 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -314,6 +314,7 @@ struct uart_port { #define UPIO_TSI (5) /* Tsi108/109 type IO */ #define UPIO_DWAPB (6) /* DesignWare APB UART */ #define UPIO_RM9000 (7) /* RM9000 type IO */ +#define UPIO_DWAPB32 (8) /* DesignWare APB UART (32 bit accesses) */ unsigned int read_status_mask; /* driver specific */ unsigned int ignore_status_mask; /* driver specific */ -- cgit v1.1 From d9ca676bcb26e1fdff9265a3e70f697cd381c889 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 8 Dec 2010 19:40:47 +0000 Subject: atm: correct sysfs 'device' link creation and parent relationships The ATM subsystem was incorrectly creating the 'device' link for ATM nodes in sysfs. This led to incorrect device/parent relationships exposed by sysfs and udev. Instead of rolling the 'device' link by hand in the generic ATM code, pass each ATM driver's bus device down to the sysfs code and let sysfs do this stuff correctly. Signed-off-by: Dan Williams Signed-off-by: David S. Miller --- include/linux/atmdev.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h index a8e4e83..475f8c4 100644 --- a/include/linux/atmdev.h +++ b/include/linux/atmdev.h @@ -427,8 +427,10 @@ extern rwlock_t vcc_sklist_lock; #define ATM_SKB(skb) (((struct atm_skb_data *) (skb)->cb)) -struct atm_dev *atm_dev_register(const char *type,const struct atmdev_ops *ops, - int number,unsigned long *flags); /* number == -1: pick first available */ +struct atm_dev *atm_dev_register(const char *type, struct device *parent, + const struct atmdev_ops *ops, + int number, /* -1 == pick first available */ + unsigned long *flags); struct atm_dev *atm_dev_lookup(int number); void atm_dev_deregister(struct atm_dev *dev); -- cgit v1.1 From e596e6e4d578f2639416e620d367a3af34814a40 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Thu, 9 Dec 2010 12:08:35 +0000 Subject: ethtool: Report link-down while interface is down While an interface is down, many implementations of ethtool_ops::get_link, including the default, ethtool_op_get_link(), will report the last link state seen while the interface was up. In general the current physical link state is not available if the interface is down. Define ETHTOOL_GLINK to reflect whether the interface *and* any physical port have a working link, and consistently return 0 when the interface is down. Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/ethtool.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 6628a50..1908929 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -691,7 +691,9 @@ struct ethtool_ops { #define ETHTOOL_GMSGLVL 0x00000007 /* Get driver message level */ #define ETHTOOL_SMSGLVL 0x00000008 /* Set driver msg level. */ #define ETHTOOL_NWAY_RST 0x00000009 /* Restart autonegotiation. */ -#define ETHTOOL_GLINK 0x0000000a /* Get link status (ethtool_value) */ +/* Get link status for host, i.e. whether the interface *and* the + * physical port (if there is one) are up (ethtool_value). */ +#define ETHTOOL_GLINK 0x0000000a #define ETHTOOL_GEEPROM 0x0000000b /* Get EEPROM data */ #define ETHTOOL_SEEPROM 0x0000000c /* Set EEPROM data. */ #define ETHTOOL_GCOALESCE 0x0000000e /* Get coalesce config */ -- cgit v1.1 From 6610e0893b8bc6f59b14fed7f089c5997f035f88 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 23 Sep 2010 15:07:34 -0700 Subject: RTC: Rework RTC code to use timerqueue for events This patch reworks a large portion of the generic RTC code to in-effect virtualize the rtc interrupt code. The current RTC interface is very much a raw hardware interface. Via the proc, /dev/, or sysfs interfaces, applciations can set the hardware to trigger interrupts in one of three modes: AIE: Alarm interrupt UIE: Update interrupt (ie: once per second) PIE: Periodic interrupt (sub-second irqs) The problem with this interface is that it limits the RTC hardware so it can only be used by one application at a time. The purpose of this patch is to extend the RTC code so that we can multiplex multiple applications event needs onto a single RTC device. This is done by utilizing the timerqueue infrastructure to manage a list of events, which cause the RTC hardware to be programmed to fire an interrupt for the next event in the list. In order to preserve the functionality of the exsting proc,/dev/ and sysfs interfaces, we emulate the different interrupt modes as follows: AIE: We create a rtc_timer dedicated to AIE mode interrupts. There is only one per device, so we don't change existing interface semantics. UIE: Again, a dedicated rtc_timer, set for periodic mode, is used to emulate UIE interrupts. Again, only one per device. PIE: Since PIE mode interrupts fire faster then the RTC's clock read granularity, we emulate PIE mode interrupts using a hrtimer. Again, one per device. With this patch, the rtctest.c application in Documentation/rtc.txt passes fine on x86 hardware. However, there may very well still be bugs, so greatly I'd appreciate any feedback or testing! Signed-off-by: John Stultz LKML Reference: <1290136329-18291-4-git-send-email-john.stultz@linaro.org> Acked-by: Alessandro Zummo Reviewed-by: Thomas Gleixner CC: Alessandro Zummo CC: Thomas Gleixner CC: Richard Cochran --- include/linux/rtc.h | 43 ++++++++++++++++++++++++++++++++++++++----- 1 file changed, 38 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 14dbc83..a3421ab 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -107,12 +107,17 @@ extern int rtc_year_days(unsigned int day, unsigned int month, unsigned int year extern int rtc_valid_tm(struct rtc_time *tm); extern int rtc_tm_to_time(struct rtc_time *tm, unsigned long *time); extern void rtc_time_to_tm(unsigned long time, struct rtc_time *tm); +ktime_t rtc_tm_to_ktime(struct rtc_time tm); +struct rtc_time rtc_ktime_to_tm(ktime_t kt); + #include #include #include #include #include +#include +#include extern struct class *rtc_class; @@ -151,7 +156,19 @@ struct rtc_class_ops { }; #define RTC_DEVICE_NAME_SIZE 20 -struct rtc_task; +typedef struct rtc_task { + void (*func)(void *private_data); + void *private_data; +} rtc_task_t; + + +struct rtc_timer { + struct rtc_task task; + struct timerqueue_node node; + ktime_t period; + int enabled; +}; + /* flags */ #define RTC_DEV_BUSY 0 @@ -179,6 +196,15 @@ struct rtc_device spinlock_t irq_task_lock; int irq_freq; int max_user_freq; + + struct timerqueue_head timerqueue; + struct rtc_timer aie_timer; + struct rtc_timer uie_rtctimer; + struct hrtimer pie_timer; /* sub second exp, so needs hrtimer */ + int pie_enabled; + struct work_struct irqwork; + + #ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL struct work_struct uie_task; struct timer_list uie_timer; @@ -224,15 +250,22 @@ extern int rtc_alarm_irq_enable(struct rtc_device *rtc, unsigned int enabled); extern int rtc_dev_update_irq_enable_emul(struct rtc_device *rtc, unsigned int enabled); -typedef struct rtc_task { - void (*func)(void *private_data); - void *private_data; -} rtc_task_t; +void rtc_aie_update_irq(void *private); +void rtc_uie_update_irq(void *private); +enum hrtimer_restart rtc_pie_update_irq(struct hrtimer *timer); int rtc_register(rtc_task_t *task); int rtc_unregister(rtc_task_t *task); int rtc_control(rtc_task_t *t, unsigned int cmd, unsigned long arg); +void rtctimer_enqueue(struct rtc_device *rtc, struct rtc_timer *timer); +void rtctimer_remove(struct rtc_device *rtc, struct rtc_timer *timer); +void rtctimer_init(struct rtc_timer *timer, void (*f)(void* p), void* data); +int rtctimer_start(struct rtc_device *rtc, struct rtc_timer* timer, + ktime_t expires, ktime_t period); +int rtctimer_cancel(struct rtc_device *rtc, struct rtc_timer* timer); +void rtctimer_do_work(struct work_struct *work); + static inline bool is_leap_year(unsigned int year) { return (!(year % 4) && (year % 100)) || !(year % 400); -- cgit v1.1 From 042620a018afcfba1d678062b62e463b9e43a68d Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 14 Oct 2010 16:22:33 -0700 Subject: RTC: Remove UIE emulation Since we provide UIE interrupts via a rtc_timer, the old emulation code can be removed. Signed-off-by: John Stultz LKML Reference: <1290136329-18291-5-git-send-email-john.stultz@linaro.org> Acked-by: Alessandro Zummo Reviewed-by: Thomas Gleixner CC: Alessandro Zummo CC: Thomas Gleixner CC: Richard Cochran --- include/linux/rtc.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index a3421ab..44e18a2 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -203,18 +203,6 @@ struct rtc_device struct hrtimer pie_timer; /* sub second exp, so needs hrtimer */ int pie_enabled; struct work_struct irqwork; - - -#ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL - struct work_struct uie_task; - struct timer_list uie_timer; - /* Those fields are protected by rtc->irq_lock */ - unsigned int oldsecs; - unsigned int uie_irq_active:1; - unsigned int stop_uie_polling:1; - unsigned int uie_task_active:1; - unsigned int uie_timer_active:1; -#endif }; #define to_rtc_device(d) container_of(d, struct rtc_device, dev) -- cgit v1.1 From d90aa92c0c1625d7f02050e4d2924805840cda3d Mon Sep 17 00:00:00 2001 From: Lin Ming Date: Thu, 9 Dec 2010 16:50:52 +0800 Subject: acpi: fix _OSI string setup regression commit b0ed7a91(ACPICA/ACPI: Add new host interfaces for _OSI suppor) introduced a regression that _OSI string setup fails. There are 2 paths to setup _OSI string. DMI: acpi_dmi_osi_linux -> set_osi_linux -> acpi_osi_setup -> copy _OSI string to osi_setup_string Boot command line: acpi_osi_setup -> copy _OSI string to osi_setup_string Later, acpi_osi_setup_late will be called to handle osi_setup_string. If _OSI string is "Linux" or "!Linux", then the call path is, acpi_osi_setup_late -> acpi_cmdline_osi_linux -> set_osi_linux -> acpi_osi_setup -> copy _OSI string to osi_setup_string This actually never installs _OSI string(acpi_install_interface not called), but just copy the _OSI string to osi_setup_string. This patch fixes the regression. Reported-and-tested-by: Lukas Hejtmanek Signed-off-by: Lin Ming Signed-off-by: Len Brown --- include/linux/acpi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 050a7bc..67c91b4 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -219,7 +219,7 @@ static inline int acpi_video_display_switch_support(void) extern int acpi_blacklisted(void); extern void acpi_dmi_osi_linux(int enable, const struct dmi_system_id *d); -extern int acpi_osi_setup(char *str); +extern void acpi_osi_setup(char *str); #ifdef CONFIG_ACPI_NUMA int acpi_get_pxm(acpi_handle handle); -- cgit v1.1 From 3353bebe7c89725ab2f476b9d8d618259402d52e Mon Sep 17 00:00:00 2001 From: Len Brown Date: Tue, 30 Nov 2010 18:21:46 -0500 Subject: ACPI: video: fix build for VIDEO_OUTPUT_CONTROL=n drivers/built-in.o: In function `acpi_video_bus_put_devices': video.c:(.text+0x79663): undefined reference to `video_output_unregister' drivers/built-in.o: In function `acpi_video_bus_add': video.c:(.text+0x7b0b3): undefined reference to `video_output_register' Signed-off-by: Len Brown --- include/linux/video_output.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/video_output.h b/include/linux/video_output.h index 2fb46bc..ed5cdeb 100644 --- a/include/linux/video_output.h +++ b/include/linux/video_output.h @@ -23,6 +23,7 @@ #ifndef _LINUX_VIDEO_OUTPUT_H #define _LINUX_VIDEO_OUTPUT_H #include +#include struct output_device; struct output_properties { int (*set_state)(struct output_device *); @@ -34,9 +35,23 @@ struct output_device { struct device dev; }; #define to_output_device(obj) container_of(obj, struct output_device, dev) +#if defined(CONFIG_VIDEO_OUTPUT_CONTROL) || defined(CONFIG_VIDEO_OUTPUT_CONTROL_MODULE) struct output_device *video_output_register(const char *name, struct device *dev, void *devdata, struct output_properties *op); void video_output_unregister(struct output_device *dev); +#else +static struct output_device *video_output_register(const char *name, + struct device *dev, + void *devdata, + struct output_properties *op) +{ + return ERR_PTR(-ENODEV); +} +static void video_output_unregister(struct output_device *dev) +{ + return; +} +#endif #endif -- cgit v1.1 From b72512ed706efb26087fcbbc5f98ed64ac1230d5 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Sun, 5 Sep 2010 14:51:49 +0100 Subject: ACPI: video: fix build for CONFIG_ACPI=n MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In file included from drivers/gpu/drm/i915/intel_opregion.c:30: include/acpi/video.h:22: warning: ‘struct acpi_device’ declared inside parameter list ... include/acpi/video.h:24: error: ‘ENODEV’ undeclared (first use in this function) Signed-off-by: Chris Wilson Signed-off-by: Len Brown --- include/acpi/video.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/video.h b/include/acpi/video.h index 551793c..0e98e67 100644 --- a/include/acpi/video.h +++ b/include/acpi/video.h @@ -1,6 +1,10 @@ #ifndef __ACPI_VIDEO_H #define __ACPI_VIDEO_H +#include /* for ENODEV */ + +struct acpi_device; + #define ACPI_VIDEO_DISPLAY_CRT 1 #define ACPI_VIDEO_DISPLAY_TV 2 #define ACPI_VIDEO_DISPLAY_DVI 3 @@ -26,4 +30,3 @@ static inline int acpi_video_get_edid(struct acpi_device *device, int type, #endif #endif - -- cgit v1.1 From 45f74264e18449cf3c93cccaf098ee6e9524ab78 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 11 Dec 2010 12:34:34 +0100 Subject: timerqueue: Make timerqueue_getnext() static inline No point in calling a function just to dereference a pointer. Signed-off-by: Thomas Gleixner Cc: John Stultz --- include/linux/timerqueue.h | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/timerqueue.h b/include/linux/timerqueue.h index 406b103..d24aaba 100644 --- a/include/linux/timerqueue.h +++ b/include/linux/timerqueue.h @@ -20,10 +20,23 @@ extern void timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node); extern void timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node); -extern struct timerqueue_node *timerqueue_getnext(struct timerqueue_head *head); extern struct timerqueue_node *timerqueue_iterate_next( struct timerqueue_node *node); +/** + * timerqueue_getnext - Returns the timer with the earlies expiration time + * + * @head: head of timerqueue + * + * Returns a pointer to the timer node that has the + * earliest expiration time. + */ +static inline +struct timerqueue_node *timerqueue_getnext(struct timerqueue_head *head) +{ + return head->next; +} + static inline void timerqueue_init(struct timerqueue_node *node) { RB_CLEAR_NODE(&node->node); -- cgit v1.1 From 5170ae824ddf1988a63fb12cbedcff817634c444 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sun, 12 Dec 2010 21:35:57 -0800 Subject: net: Abstract RTAX_HOPLIMIT metric accesses behind helper. Signed-off-by: David S. Miller --- include/net/dst.h | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dst.h b/include/net/dst.h index 85dee3a..9208b50 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -104,11 +104,24 @@ struct dst_entry { #ifdef __KERNEL__ static inline u32 -dst_metric(const struct dst_entry *dst, int metric) +dst_metric_raw(const struct dst_entry *dst, const int metric) { return dst->_metrics[metric-1]; } +static inline u32 +dst_metric(const struct dst_entry *dst, const int metric) +{ + WARN_ON_ONCE(metric == RTAX_HOPLIMIT); + return dst_metric_raw(dst, metric); +} + +static inline u32 +dst_metric_hoplimit(const struct dst_entry *dst) +{ + return dst_metric_raw(dst, RTAX_HOPLIMIT); +} + static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val) { dst->_metrics[metric-1] = val; -- cgit v1.1 From 323e126f0c5995f779d7df7fd035f6e8fed8764d Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sun, 12 Dec 2010 21:55:08 -0800 Subject: ipv4: Don't pre-seed hoplimit metric. Always go through a new ip4_dst_hoplimit() helper, just like ipv6. This allowed several simplifications: 1) The interim dst_metric_hoplimit() can go as it's no longer userd. 2) The sysctl_ip_default_ttl entry no longer needs to use ipv4_doint_and_flush, since the sysctl is not cached in routing cache metrics any longer. 3) ipv4_doint_and_flush no longer needs to be exported and therefore can be marked static. When ipv4_doint_and_flush_strategy was removed some time ago, the external declaration in ip.h was mistakenly left around so kill that off too. We have to move the sysctl_ip_default_ttl declaration into ipv4's route cache definition header net/route.h, because currently net/ip.h (where the declaration lives now) has a back dependency on net/route.h Signed-off-by: David S. Miller --- include/net/dst.h | 6 ------ include/net/ip.h | 10 ---------- include/net/route.h | 11 +++++++++++ 3 files changed, 11 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/net/dst.h b/include/net/dst.h index 9208b50..755ac6c 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -116,12 +116,6 @@ dst_metric(const struct dst_entry *dst, const int metric) return dst_metric_raw(dst, metric); } -static inline u32 -dst_metric_hoplimit(const struct dst_entry *dst) -{ - return dst_metric_raw(dst, RTAX_HOPLIMIT); -} - static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val) { dst->_metrics[metric-1] = val; diff --git a/include/net/ip.h b/include/net/ip.h index 86e2b18..67fac78 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -201,7 +201,6 @@ static inline int inet_is_reserved_local_port(int port) return test_bit(port, sysctl_local_reserved_ports); } -extern int sysctl_ip_default_ttl; extern int sysctl_ip_nonlocal_bind; extern struct ctl_path net_core_path[]; @@ -428,15 +427,6 @@ extern void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, extern void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport, u32 info); -/* sysctl helpers - any sysctl which holds a value that ends up being - * fed into the routing cache should use these handlers. - */ -int ipv4_doint_and_flush(ctl_table *ctl, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos); -int ipv4_doint_and_flush_strategy(ctl_table *table, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen); #ifdef CONFIG_PROC_FS extern int ip_misc_proc_init(void); #endif diff --git a/include/net/route.h b/include/net/route.h index b8c1f77..2700236 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -231,4 +231,15 @@ static inline int inet_iif(const struct sk_buff *skb) return skb_rtable(skb)->rt_iif; } +extern int sysctl_ip_default_ttl; + +static inline int ip4_dst_hoplimit(const struct dst_entry *dst) +{ + int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT); + + if (hoplimit == 0) + hoplimit = sysctl_ip_default_ttl; + return hoplimit; +} + #endif /* _ROUTE_H */ -- cgit v1.1 From a7ffac9591a2a0ee74c431396ae475a8d0caa51e Mon Sep 17 00:00:00 2001 From: Bruno Randolf Date: Wed, 8 Dec 2010 13:59:24 +0900 Subject: cfg80211: Add antenna availability information Add a field to wiphy for the hardware to report the availble antennas for configuration. Only if this is set to something bigger than zero, will the anntenna configuration ops be executed. Allthough this could be a simple number of antennas, I defined it as a bitmap of antennas which are available for configuration, since it's more consistent with the rest of the antenna API and there could be cases where the hardware allows only configuration of certain antennas. As it does not make much of a difference in size or normal usage, I think it's better to be able to support this, in case the need arises. The antenna configuration is now also checked against the availabe antennas and rejected if it does not match. Signed-off-by: Bruno Randolf -- v3: always apply available antenna mask (for "all" antennas case). v2: reject antenna configurations which don't match the available antennas Signed-off-by: John W. Linville --- include/net/cfg80211.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 0d59799..4d5acb0 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1468,6 +1468,9 @@ struct ieee80211_txrx_stypes { * @mgmt_stypes: bitmasks of frame subtypes that can be subscribed to or * transmitted through nl80211, points to an array indexed by interface * type + * + * @available_antennas: bitmap of antennas which are available to configure. + * antenna configuration commands will be rejected unless this is set. */ struct wiphy { /* assign these fields before you register the wiphy */ @@ -1507,6 +1510,8 @@ struct wiphy { u8 max_num_pmkids; + u32 available_antennas; + /* If multiple wiphys are registered and you're handed e.g. * a regular netdev with assigned ieee80211_ptr, you won't * know whether it points to a wiphy your driver has registered -- cgit v1.1 From dbd2fd656f2060abfd3a16257f8b51ec60f6d2ed Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 9 Dec 2010 19:58:59 +0100 Subject: cfg80211/nl80211: separate unicast/multicast default TX keys Allow userspace to specify that a given key is default only for unicast and/or multicast transmissions. Only WEP keys are for both, WPA/RSN keys set here are GTKs for multicast only. For more future flexibility, allow to specify all combiations. Wireless extensions can only set both so use nl80211; WEP keys (connect keys) must be set as default for both (but 802.1X WEP is still possible). Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 27 +++++++++++++++++++++++++++ include/net/cfg80211.h | 5 ++++- 2 files changed, 31 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 3804212..b8fa25d 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -851,6 +851,10 @@ enum nl80211_commands { * * @NL80211_ATTR_BSS_HTOPMODE: HT operation mode (u16) * + * @NL80211_ATTR_KEY_DEFAULT_TYPES: A nested attribute containing flags + * attributes, specifying what a key should be set as default as. + * See &enum nl80211_key_default_types. + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -1029,6 +1033,8 @@ enum nl80211_attrs { NL80211_ATTR_BSS_HT_OPMODE, + NL80211_ATTR_KEY_DEFAULT_TYPES, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -1775,6 +1781,23 @@ enum nl80211_wpa_versions { }; /** + * enum nl80211_key_default_types - key default types + * @__NL80211_KEY_DEFAULT_TYPE_INVALID: invalid + * @NL80211_KEY_DEFAULT_TYPE_UNICAST: key should be used as default + * unicast key + * @NL80211_KEY_DEFAULT_TYPE_MULTICAST: key should be used as default + * multicast key + * @NUM_NL80211_KEY_DEFAULT_TYPES: number of default types + */ +enum nl80211_key_default_types { + __NL80211_KEY_DEFAULT_TYPE_INVALID, + NL80211_KEY_DEFAULT_TYPE_UNICAST, + NL80211_KEY_DEFAULT_TYPE_MULTICAST, + + NUM_NL80211_KEY_DEFAULT_TYPES +}; + +/** * enum nl80211_key_attributes - key attributes * @__NL80211_KEY_INVALID: invalid * @NL80211_KEY_DATA: (temporal) key data; for TKIP this consists of @@ -1790,6 +1813,9 @@ enum nl80211_wpa_versions { * @NL80211_KEY_TYPE: the key type from enum nl80211_key_type, if not * specified the default depends on whether a MAC address was * given with the command using the key or not (u32) + * @NL80211_KEY_DEFAULT_TYPES: A nested attribute containing flags + * attributes, specifying what a key should be set as default as. + * See &enum nl80211_key_default_types. * @__NL80211_KEY_AFTER_LAST: internal * @NL80211_KEY_MAX: highest key attribute */ @@ -1802,6 +1828,7 @@ enum nl80211_key_attributes { NL80211_KEY_DEFAULT, NL80211_KEY_DEFAULT_MGMT, NL80211_KEY_TYPE, + NL80211_KEY_DEFAULT_TYPES, /* keep last */ __NL80211_KEY_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 4d5acb0..22be7c6 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1211,7 +1211,7 @@ struct cfg80211_ops { u8 key_index, bool pairwise, const u8 *mac_addr); int (*set_default_key)(struct wiphy *wiphy, struct net_device *netdev, - u8 key_index); + u8 key_index, bool unicast, bool multicast); int (*set_default_mgmt_key)(struct wiphy *wiphy, struct net_device *netdev, u8 key_index); @@ -1393,6 +1393,8 @@ struct cfg80211_ops { * control port protocol ethertype. The device also honours the * control_port_no_encrypt flag. * @WIPHY_FLAG_IBSS_RSN: The device supports IBSS RSN. + * @WIPHY_FLAG_SUPPORTS_SEPARATE_DEFAULT_KEYS: The device supports separate + * unicast and multicast TX keys. */ enum wiphy_flags { WIPHY_FLAG_CUSTOM_REGULATORY = BIT(0), @@ -1404,6 +1406,7 @@ enum wiphy_flags { WIPHY_FLAG_4ADDR_STATION = BIT(6), WIPHY_FLAG_CONTROL_PORT_PROTOCOL = BIT(7), WIPHY_FLAG_IBSS_RSN = BIT(8), + WIPHY_FLAG_SUPPORTS_SEPARATE_DEFAULT_KEYS= BIT(9), }; struct mac_address { -- cgit v1.1 From 44316cb1e97a1e7f76eb3f07e5b0ba91d72e9693 Mon Sep 17 00:00:00 2001 From: Bing Zhao Date: Thu, 9 Dec 2010 18:24:41 -0800 Subject: ieee80211: add Parameter Set Count bitmask WMM IE QoS Info field lower 4 bits: Parameter Set Count Signed-off-by: Bing Zhao Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 351c0ab..7f23545 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -122,6 +122,7 @@ /* U-APSD queue for WMM IEs sent by AP */ #define IEEE80211_WMM_IE_AP_QOSINFO_UAPSD (1<<7) +#define IEEE80211_WMM_IE_AP_QOSINFO_PARAM_SET_CNT_MASK 0x0f /* U-APSD queues for WMM IEs sent by STA */ #define IEEE80211_WMM_IE_STA_QOSINFO_AC_VO (1<<0) -- cgit v1.1 From 0dbaee3b37e118a96bb7b8eb0d9bbaeeb46264be Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 13 Dec 2010 12:52:14 -0800 Subject: net: Abstract default ADVMSS behind an accessor. Make all RTAX_ADVMSS metric accesses go through a new helper function, dst_metric_advmss(). Leave the actual default metric as "zero" in the real metric slot, and compute the actual default value dynamically via a new dst_ops AF specific callback. For stacked IPSEC routes, we use the advmss of the path which preserves existing behavior. Unlike ipv4/ipv6, DecNET ties the advmss to the mtu and thus updates advmss on pmtu updates. This inconsistency in advmss handling results in more raw metric accesses than I wish we ended up with. Signed-off-by: David S. Miller --- include/net/dst.h | 14 +++++++++++++- include/net/dst_ops.h | 1 + 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dst.h b/include/net/dst.h index 755ac6c..03a1c3d 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -112,10 +112,22 @@ dst_metric_raw(const struct dst_entry *dst, const int metric) static inline u32 dst_metric(const struct dst_entry *dst, const int metric) { - WARN_ON_ONCE(metric == RTAX_HOPLIMIT); + WARN_ON_ONCE(metric == RTAX_HOPLIMIT || + metric == RTAX_ADVMSS); return dst_metric_raw(dst, metric); } +static inline u32 +dst_metric_advmss(const struct dst_entry *dst) +{ + u32 advmss = dst_metric_raw(dst, RTAX_ADVMSS); + + if (!advmss) + advmss = dst->ops->default_advmss(dst); + + return advmss; +} + static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val) { dst->_metrics[metric-1] = val; diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 51665b3..15fb7af 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -16,6 +16,7 @@ struct dst_ops { int (*gc)(struct dst_ops *ops); struct dst_entry * (*check)(struct dst_entry *, __u32 cookie); + unsigned int (*default_advmss)(const struct dst_entry *); void (*destroy)(struct dst_entry *); void (*ifdown)(struct dst_entry *, struct net_device *dev, int how); -- cgit v1.1 From 96c8f06a0fb359a9a89701a7afab6d837e466ab0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 13 Dec 2010 22:45:48 +0100 Subject: rtc: Namespace fixup rtctimer_* is already occupied by sound/core/rtctimer.c. Instead of fiddling with that, rename the new functions to rtc_timer_* which reads nicer anyway. Signed-off-by: Thomas Gleixner Cc: John Stultz --- include/linux/rtc.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 44e18a2..3c995b4 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -246,13 +246,13 @@ int rtc_register(rtc_task_t *task); int rtc_unregister(rtc_task_t *task); int rtc_control(rtc_task_t *t, unsigned int cmd, unsigned long arg); -void rtctimer_enqueue(struct rtc_device *rtc, struct rtc_timer *timer); -void rtctimer_remove(struct rtc_device *rtc, struct rtc_timer *timer); -void rtctimer_init(struct rtc_timer *timer, void (*f)(void* p), void* data); -int rtctimer_start(struct rtc_device *rtc, struct rtc_timer* timer, +void rtc_timer_enqueue(struct rtc_device *rtc, struct rtc_timer *timer); +void rtc_timer_remove(struct rtc_device *rtc, struct rtc_timer *timer); +void rtc_timer_init(struct rtc_timer *timer, void (*f)(void* p), void* data); +int rtc_timer_start(struct rtc_device *rtc, struct rtc_timer* timer, ktime_t expires, ktime_t period); -int rtctimer_cancel(struct rtc_device *rtc, struct rtc_timer* timer); -void rtctimer_do_work(struct work_struct *work); +int rtc_timer_cancel(struct rtc_device *rtc, struct rtc_timer* timer); +void rtc_timer_do_work(struct work_struct *work); static inline bool is_leap_year(unsigned int year) { -- cgit v1.1 From 53dde5f385bc56e312f78b7cb25ffaf8efd4735d Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Tue, 16 Nov 2010 13:23:50 -0800 Subject: bootmem: Add alloc_bootmem_align() Add an alloc_bootmem_align() interface to allocate bootmem with specified alignment. This is necessary to be able to allocate the xsave area in a subsequent patch. Signed-off-by: Suresh Siddha LKML-Reference: <20101116212441.977574826@sbsiddha-MOBL3.sc.intel.com> Acked-by: H. Peter Anvin Signed-off-by: H. Peter Anvin Cc: --- include/linux/bootmem.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 266ab92..499dfe9 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -105,6 +105,8 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, #define alloc_bootmem(x) \ __alloc_bootmem(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) +#define alloc_bootmem_align(x, align) \ + __alloc_bootmem(x, align, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_nopanic(x) \ __alloc_bootmem_nopanic(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)) #define alloc_bootmem_pages(x) \ -- cgit v1.1 From c9aa308fd5c373faeda588cfb02b04f116904613 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Tue, 7 Dec 2010 10:22:29 +0800 Subject: Add CPER PCIe error section structure and constants definition On some machine, PCIe error is reported via APEI (ACPI Platform Error Interface). The error data is passed from firmware to Linux via CPER PCIe error section structure. This patch adds CPER PCIe error section structure and constants definition. Signed-off-by: Huang Ying Signed-off-by: Len Brown --- include/linux/cper.h | 86 +++++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 82 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/cper.h b/include/linux/cper.h index bf972f8..3104aaf 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -39,10 +39,12 @@ * Severity difinition for error_severity in struct cper_record_header * and section_severity in struct cper_section_descriptor */ -#define CPER_SEV_RECOVERABLE 0x0 -#define CPER_SEV_FATAL 0x1 -#define CPER_SEV_CORRECTED 0x2 -#define CPER_SEV_INFORMATIONAL 0x3 +enum { + CPER_SEV_RECOVERABLE, + CPER_SEV_FATAL, + CPER_SEV_CORRECTED, + CPER_SEV_INFORMATIONAL, +}; /* * Validation bits difinition for validation_bits in struct @@ -201,6 +203,47 @@ UUID_LE(0x036F84E1, 0x7F37, 0x428c, 0xA7, 0x9E, 0x57, 0x5F, \ 0xDF, 0xAA, 0x84, 0xEC) +#define CPER_PROC_VALID_TYPE 0x0001 +#define CPER_PROC_VALID_ISA 0x0002 +#define CPER_PROC_VALID_ERROR_TYPE 0x0004 +#define CPER_PROC_VALID_OPERATION 0x0008 +#define CPER_PROC_VALID_FLAGS 0x0010 +#define CPER_PROC_VALID_LEVEL 0x0020 +#define CPER_PROC_VALID_VERSION 0x0040 +#define CPER_PROC_VALID_BRAND_INFO 0x0080 +#define CPER_PROC_VALID_ID 0x0100 +#define CPER_PROC_VALID_TARGET_ADDRESS 0x0200 +#define CPER_PROC_VALID_REQUESTOR_ID 0x0400 +#define CPER_PROC_VALID_RESPONDER_ID 0x0800 +#define CPER_PROC_VALID_IP 0x1000 + +#define CPER_MEM_VALID_ERROR_STATUS 0x0001 +#define CPER_MEM_VALID_PHYSICAL_ADDRESS 0x0002 +#define CPER_MEM_VALID_PHYSICAL_ADDRESS_MASK 0x0004 +#define CPER_MEM_VALID_NODE 0x0008 +#define CPER_MEM_VALID_CARD 0x0010 +#define CPER_MEM_VALID_MODULE 0x0020 +#define CPER_MEM_VALID_BANK 0x0040 +#define CPER_MEM_VALID_DEVICE 0x0080 +#define CPER_MEM_VALID_ROW 0x0100 +#define CPER_MEM_VALID_COLUMN 0x0200 +#define CPER_MEM_VALID_BIT_POSITION 0x0400 +#define CPER_MEM_VALID_REQUESTOR_ID 0x0800 +#define CPER_MEM_VALID_RESPONDER_ID 0x1000 +#define CPER_MEM_VALID_TARGET_ID 0x2000 +#define CPER_MEM_VALID_ERROR_TYPE 0x4000 + +#define CPER_PCIE_VALID_PORT_TYPE 0x0001 +#define CPER_PCIE_VALID_VERSION 0x0002 +#define CPER_PCIE_VALID_COMMAND_STATUS 0x0004 +#define CPER_PCIE_VALID_DEVICE_ID 0x0008 +#define CPER_PCIE_VALID_SERIAL_NUMBER 0x0010 +#define CPER_PCIE_VALID_BRIDGE_CONTROL_STATUS 0x0020 +#define CPER_PCIE_VALID_CAPABILITY 0x0040 +#define CPER_PCIE_VALID_AER_INFO 0x0080 + +#define CPER_PCIE_SLOT_SHIFT 3 + /* * All tables and structs must be byte-packed to match CPER * specification, since the tables are provided by the system BIOS @@ -306,6 +349,41 @@ struct cper_sec_mem_err { __u8 error_type; }; +struct cper_sec_pcie { + __u64 validation_bits; + __u32 port_type; + struct { + __u8 minor; + __u8 major; + __u8 reserved[2]; + } version; + __u16 command; + __u16 status; + __u32 reserved; + struct { + __u16 vendor_id; + __u16 device_id; + __u8 class_code[3]; + __u8 function; + __u8 device; + __u16 segment; + __u8 bus; + __u8 secondary_bus; + __u16 slot; + __u8 reserved; + } device_id; + struct { + __u32 lower; + __u32 upper; + } serial_number; + struct { + __u16 secondary_status; + __u16 control; + } bridge; + __u8 capability[60]; + __u8 aer_info[96]; +}; + /* Reset to default packing */ #pragma pack() -- cgit v1.1 From 16f4232ce4d6855361b4eb56262f4a202295c978 Mon Sep 17 00:00:00 2001 From: Zhao Yakui Date: Wed, 8 Dec 2010 10:10:16 +0800 Subject: IPMI: Add one interface to get more info of low-level IPMI device The IPMI smi_watcher will be used to catch the IPMI interface as they come or go. In order to communicate with the correct IPMI device, it should be confirmed whether it is what we wanted especially on the system with multiple IPMI devices. But the new_smi callback function of smi_watcher provides very limited info(only the interface number and dev pointer) and there is no detailed info about the low level interface. For example: which mechansim registers the IPMI interface(ACPI, PCI, DMI and so on). This is to add one interface that can get more info of low-level IPMI device. For example: the ACPI device handle will be returned for the pnp_acpi IPMI device. Signed-off-by: Zhao Yakui Signed-off-by: Corey Minyard Signed-off-by: Len Brown --- include/linux/ipmi.h | 38 ++++++++++++++++++++++++++++++++++++++ include/linux/ipmi_smi.h | 8 ++++++++ 2 files changed, 46 insertions(+) (limited to 'include') diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index 65aae34..045f2f2 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -454,6 +454,44 @@ unsigned int ipmi_addr_length(int addr_type); /* Validate that the given IPMI address is valid. */ int ipmi_validate_addr(struct ipmi_addr *addr, int len); +/* + * How did the IPMI driver find out about the device? + */ +enum ipmi_addr_src { + SI_INVALID = 0, SI_HOTMOD, SI_HARDCODED, SI_SPMI, SI_ACPI, SI_SMBIOS, + SI_PCI, SI_DEVICETREE, SI_DEFAULT +}; + +union ipmi_smi_info_union { + /* + * the acpi_info element is defined for the SI_ACPI + * address type + */ + struct { + void *acpi_handle; + } acpi_info; +}; + +struct ipmi_smi_info { + enum ipmi_addr_src addr_src; + + /* + * Base device for the interface. Don't forget to put this when + * you are done. + */ + struct device *dev; + + /* + * The addr_info provides more detailed info for some IPMI + * devices, depending on the addr_src. Currently only SI_ACPI + * info is provided. + */ + union ipmi_smi_info_union addr_info; +}; + +/* This is to get the private info of ipmi_smi_t */ +extern int ipmi_get_smi_info(int if_num, struct ipmi_smi_info *data); + #endif /* __KERNEL__ */ diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index 4b48318..906590a 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -39,6 +39,7 @@ #include #include #include +#include /* This files describes the interface for IPMI system management interface drivers to bind into the IPMI message handler. */ @@ -86,6 +87,13 @@ struct ipmi_smi_handlers { int (*start_processing)(void *send_info, ipmi_smi_t new_intf); + /* + * Get the detailed private info of the low level interface and store + * it into the structure of ipmi_smi_data. For example: the + * ACPI device handle will be returned for the pnp_acpi IPMI device. + */ + int (*get_smi_info)(void *send_info, struct ipmi_smi_info *data); + /* Called to enqueue an SMI message to be sent. This operation is not allowed to fail. If an error occurs, it should report back the error in a received message. It may -- cgit v1.1 From d33e455337ea2c71d09d7f4367d6ad6dd32b6965 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 14 Dec 2010 13:01:14 -0800 Subject: net: Abstract default MTU metric calculation behind an accessor. Like RTAX_ADVMSS, make the default calculation go through a dst_ops method rather than caching the computation in the routing cache entries. Now dst metrics are pretty much left as-is when new entries are created, thus optimizing metric sharing becomes a real possibility. Signed-off-by: David S. Miller --- include/net/dst.h | 15 ++++++++------- include/net/dst_ops.h | 1 + 2 files changed, 9 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/dst.h b/include/net/dst.h index 03a1c3d..93b0310 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -113,7 +113,8 @@ static inline u32 dst_metric(const struct dst_entry *dst, const int metric) { WARN_ON_ONCE(metric == RTAX_HOPLIMIT || - metric == RTAX_ADVMSS); + metric == RTAX_ADVMSS || + metric == RTAX_MTU); return dst_metric_raw(dst, metric); } @@ -156,11 +157,11 @@ dst_feature(const struct dst_entry *dst, u32 feature) static inline u32 dst_mtu(const struct dst_entry *dst) { - u32 mtu = dst_metric(dst, RTAX_MTU); - /* - * Alexey put it here, so ask him about it :) - */ - barrier(); + u32 mtu = dst_metric_raw(dst, RTAX_MTU); + + if (!mtu) + mtu = dst->ops->default_mtu(dst); + return mtu; } @@ -186,7 +187,7 @@ dst_allfrag(const struct dst_entry *dst) } static inline int -dst_metric_locked(struct dst_entry *dst, int metric) +dst_metric_locked(const struct dst_entry *dst, int metric) { return dst_metric(dst, RTAX_LOCK) & (1< Date: Mon, 13 Dec 2010 19:10:29 +0200 Subject: kbuild: export linux/{a.out,kvm,kvm_para}.h on headers_install_all Export linux/a.out.h, linux/kvm.h and linux/kvm_para.h on headers_install_all if at least one architecture has appropriate files in arch-dependent headers. Signed-off-by: Kirill A. Shutemov Signed-off-by: Michal Marek --- include/linux/Kbuild | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 97319a8..ae31f95 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -20,15 +20,18 @@ header-y += wimax/ objhdr-y += version.h ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/asm/a.out.h \ - $(srctree)/include/asm-$(SRCARCH)/a.out.h),) + $(srctree)/include/asm-$(SRCARCH)/a.out.h \ + $(INSTALL_HDR_PATH)/include/asm-*/a.out.h),) header-y += a.out.h endif ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/asm/kvm.h \ - $(srctree)/include/asm-$(SRCARCH)/kvm.h),) + $(srctree)/include/asm-$(SRCARCH)/kvm.h \ + $(INSTALL_HDR_PATH)/include/asm-*/kvm.h),) header-y += kvm.h endif ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/asm/kvm_para.h \ - $(srctree)/include/asm-$(SRCARCH)/kvm_para.h),) + $(srctree)/include/asm-$(SRCARCH)/kvm_para.h \ + $(INSTALL_HDR_PATH)/include/asm-*/kvm_para.h),) header-y += kvm_para.h endif -- cgit v1.1 From ab4e0192196b8d4e43a3945742d4996da934a86f Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Tue, 14 Dec 2010 23:53:21 -0800 Subject: Input: define separate EVIOCGKEYCODE_V2/EVIOCSKEYCODE_V2 The desire to keep old names for the EVIOCGKEYCODE/EVIOCSKEYCODE while extending them to support large scancodes was a mistake. While we tried to keep ABI intact (and we succeeded in doing that, programs compiled on older kernels will work on newer ones) there is still a problem with recompiling existing software with newer kernel headers. New kernel headers will supply updated ioctl numbers and kernel will expect that userspace will use struct input_keymap_entry to set and retrieve keymap data. But since the names of ioctls are still the same userspace will happily compile even if not adjusted to make use of the new structure and will start miraculously fail in the field. To avoid this issue let's revert EVIOCGKEYCODE/EVIOCSKEYCODE definitions and add EVIOCGKEYCODE_V2/EVIOCSKEYCODE_V2 so that userspace can explicitly select the style of ioctls it wants to employ. Reviewed-by: Henrik Rydberg Acked-by: Jarod Wilson Acked-by: Mauro Carvalho Chehab Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/input.h b/include/linux/input.h index a8af21d..9777668 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -104,8 +104,10 @@ struct input_keymap_entry { #define EVIOCGREP _IOR('E', 0x03, unsigned int[2]) /* get repeat settings */ #define EVIOCSREP _IOW('E', 0x03, unsigned int[2]) /* set repeat settings */ -#define EVIOCGKEYCODE _IOR('E', 0x04, struct input_keymap_entry) /* get keycode */ -#define EVIOCSKEYCODE _IOW('E', 0x04, struct input_keymap_entry) /* set keycode */ +#define EVIOCGKEYCODE _IOR('E', 0x04, unsigned int[2]) /* get keycode */ +#define EVIOCGKEYCODE_V2 _IOR('E', 0x04, struct input_keymap_entry) +#define EVIOCSKEYCODE _IOW('E', 0x04, unsigned int[2]) /* set keycode */ +#define EVIOCSKEYCODE_V2 _IOW('E', 0x04, struct input_keymap_entry) #define EVIOCGNAME(len) _IOC(_IOC_READ, 'E', 0x06, len) /* get device name */ #define EVIOCGPHYS(len) _IOC(_IOC_READ, 'E', 0x07, len) /* get physical location */ -- cgit v1.1 From ed41390fa57a21d06e6e3a3c4bc238bab8957fbb Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 14 Dec 2010 16:23:10 +0100 Subject: workqueue: deprecate cancel_rearming_delayed_work[queue]() There's no in-kernel user left for these two obsolete functions. Mark them deprecated and schedule for removal during 2.6.39 cycle. Signed-off-by: Tejun Heo Acked-by: David S. Miller --- include/linux/workqueue.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 0c0771f..6b5193d 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -401,7 +401,7 @@ static inline bool __cancel_delayed_work(struct delayed_work *work) } /* Obsolete. use cancel_delayed_work_sync() */ -static inline +static inline __deprecated void cancel_rearming_delayed_workqueue(struct workqueue_struct *wq, struct delayed_work *work) { @@ -409,7 +409,7 @@ void cancel_rearming_delayed_workqueue(struct workqueue_struct *wq, } /* Obsolete. use cancel_delayed_work_sync() */ -static inline +static inline __deprecated void cancel_rearming_delayed_work(struct delayed_work *work) { cancel_delayed_work_sync(work); -- cgit v1.1 From 62731fa0c893515dc6cbc3e0a2879a92793c735f Mon Sep 17 00:00:00 2001 From: Alexey Zaytsev Date: Mon, 22 Nov 2010 00:33:03 +0000 Subject: fanotify: split version into version and metadata_len To implement per event type optional headers we are interested in knowing how long the metadata structure is. This patch slits the __u32 version field into a __u8 version and a __u16 metadata_len field (with __u8 left over). This should allow for backwards compat ABI. Signed-off-by: Alexey Zaytsev [rewrote descrtion and changed object sizes and ordering - eparis] Signed-off-by: Eric Paris --- include/linux/fanotify.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index c732243..6c6133f 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -83,11 +83,13 @@ FAN_ALL_PERM_EVENTS |\ FAN_Q_OVERFLOW) -#define FANOTIFY_METADATA_VERSION 2 +#define FANOTIFY_METADATA_VERSION 3 struct fanotify_event_metadata { __u32 event_len; - __u32 vers; + __u8 vers; + __u8 reserved; + __u16 metadata_len; __aligned_u64 mask; __s32 fd; __s32 pid; -- cgit v1.1 From 667c78afaec0ac500908e191e8f236e9578d7b1f Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Wed, 8 Dec 2010 12:39:12 -0800 Subject: xen: Provide a variant of __RING_SIZE() that is an integer constant expression Without this, gcc 4.5 won't compile xen-netfront and xen-blkfront, where this is being used to specify array sizes. Signed-off-by: Jan Beulich Signed-off-by: Jeremy Fitzhardinge Cc: Jens Axboe Cc: David Miller Cc: Stable Kernel Signed-off-by: Linus Torvalds --- include/xen/interface/io/ring.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/xen/interface/io/ring.h b/include/xen/interface/io/ring.h index e8cbf43..75271b9 100644 --- a/include/xen/interface/io/ring.h +++ b/include/xen/interface/io/ring.h @@ -24,8 +24,15 @@ typedef unsigned int RING_IDX; * A ring contains as many entries as will fit, rounded down to the nearest * power of two (so we can mask with (size-1) to loop around). */ -#define __RING_SIZE(_s, _sz) \ - (__RD32(((_sz) - (long)&(_s)->ring + (long)(_s)) / sizeof((_s)->ring[0]))) +#define __CONST_RING_SIZE(_s, _sz) \ + (__RD32(((_sz) - offsetof(struct _s##_sring, ring)) / \ + sizeof(((struct _s##_sring *)0)->ring[0]))) + +/* + * The same for passing in an actual pointer instead of a name tag. + */ +#define __RING_SIZE(_s, _sz) \ + (__RD32(((_sz) - (long)&(_s)->ring + (long)(_s)) / sizeof((_s)->ring[0]))) /* * Macros to make the correct C datatypes for a new kind of ring. -- cgit v1.1 From a293911d4fd5e8593dbf478399a77f990d466269 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 14 Dec 2010 17:54:28 +0100 Subject: nl80211: advertise maximum remain-on-channel duration With the upcoming hardware offload implementation, some devices will have a different maximum duration for the remain-on-channel command. Advertise the maximum duration in mac80211, and make mac80211 set it. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 5 +++++ include/net/cfg80211.h | 5 +++++ 2 files changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index b8fa25d..1cee56b 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -773,6 +773,9 @@ enum nl80211_commands { * cache, a wiphy attribute. * * @NL80211_ATTR_DURATION: Duration of an operation in milliseconds, u32. + * @NL80211_ATTR_MAX_REMAIN_ON_CHANNEL_DURATION: Device attribute that + * specifies the maximum duration that can be requested with the + * remain-on-channel operation, in milliseconds, u32. * * @NL80211_ATTR_COOKIE: Generic 64-bit cookie to identify objects. * @@ -1035,6 +1038,8 @@ enum nl80211_attrs { NL80211_ATTR_KEY_DEFAULT_TYPES, + NL80211_ATTR_MAX_REMAIN_ON_CHANNEL_DURATION, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 22be7c6..f45e15f 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1474,6 +1474,9 @@ struct ieee80211_txrx_stypes { * * @available_antennas: bitmap of antennas which are available to configure. * antenna configuration commands will be rejected unless this is set. + * + * @max_remain_on_channel_duration: Maximum time a remain-on-channel operation + * may request, if implemented. */ struct wiphy { /* assign these fields before you register the wiphy */ @@ -1511,6 +1514,8 @@ struct wiphy { char fw_version[ETHTOOL_BUSINFO_LEN]; u32 hw_version; + u16 max_remain_on_channel_duration; + u8 max_num_pmkids; u32 available_antennas; -- cgit v1.1 From bd2ce6e43f65127bc723e7fcc044758cf8113260 Mon Sep 17 00:00:00 2001 From: Sujith Manoharan Date: Wed, 15 Dec 2010 07:47:10 +0530 Subject: mac80211: Add timeout to BA session start API Allow drivers or rate control algorithms to specify BlockAck session timeout when initiating an ADDBA transaction. This is useful in cases where maintaining persistent BA sessions does not incur any overhead. The current timeout value of 5000 TUs is retained for all non ath9k/ath9k_htc drivers. Signed-off-by: Sujith Manoharan Reviewed-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index e411cf8..69ded1e 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2435,6 +2435,7 @@ void ieee80211_queue_delayed_work(struct ieee80211_hw *hw, * ieee80211_start_tx_ba_session - Start a tx Block Ack session. * @sta: the station for which to start a BA session * @tid: the TID to BA on. + * @timeout: session timeout value (in TUs) * * Return: success if addBA request was sent, failure otherwise * @@ -2442,7 +2443,8 @@ void ieee80211_queue_delayed_work(struct ieee80211_hw *hw, * the need to start aggregation on a certain RA/TID, the session level * will be managed by the mac80211. */ -int ieee80211_start_tx_ba_session(struct ieee80211_sta *sta, u16 tid); +int ieee80211_start_tx_ba_session(struct ieee80211_sta *sta, u16 tid, + u16 timeout); /** * ieee80211_start_tx_ba_cb_irqsafe - low level driver ready to aggregate. -- cgit v1.1 From 47c78e891323513e9909729b44033e2c6649e2b7 Mon Sep 17 00:00:00 2001 From: Henrik Rydberg Date: Sat, 27 Nov 2010 09:16:48 +0100 Subject: input: mt: Break out slots handling In preparation for common code to handle a larger set of MT slots devices, move the slots handling over to a separate file. Signed-off-by: Henrik Rydberg --- include/linux/input.h | 16 ---------------- include/linux/input/mt.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 44 insertions(+), 16 deletions(-) create mode 100644 include/linux/input/mt.h (limited to 'include') diff --git a/include/linux/input.h b/include/linux/input.h index 51af441..99e2a52 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -1083,14 +1083,6 @@ struct ff_effect { #include /** - * struct input_mt_slot - represents the state of an input MT slot - * @abs: holds current values of ABS_MT axes for this slot - */ -struct input_mt_slot { - int abs[ABS_MT_LAST - ABS_MT_FIRST + 1]; -}; - -/** * struct input_dev - represents an input device * @name: name of the device * @phys: physical path to the device in the system hierarchy @@ -1461,11 +1453,6 @@ static inline void input_mt_sync(struct input_dev *dev) input_event(dev, EV_SYN, SYN_MT_REPORT, 0); } -static inline void input_mt_slot(struct input_dev *dev, int slot) -{ - input_event(dev, EV_ABS, ABS_MT_SLOT, slot); -} - void input_set_capability(struct input_dev *dev, unsigned int type, unsigned int code); /** @@ -1578,8 +1565,5 @@ int input_ff_erase(struct input_dev *dev, int effect_id, struct file *file); int input_ff_create_memless(struct input_dev *dev, void *data, int (*play_effect)(struct input_dev *, void *, struct ff_effect *)); -int input_mt_create_slots(struct input_dev *dev, unsigned int num_slots); -void input_mt_destroy_slots(struct input_dev *dev); - #endif #endif diff --git a/include/linux/input/mt.h b/include/linux/input/mt.h new file mode 100644 index 0000000..4f5e9d0 --- /dev/null +++ b/include/linux/input/mt.h @@ -0,0 +1,44 @@ +#ifndef _INPUT_MT_H +#define _INPUT_MT_H + +/* + * Input Multitouch Library + * + * Copyright (c) 2010 Henrik Rydberg + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include + +/** + * struct input_mt_slot - represents the state of an input MT slot + * @abs: holds current values of ABS_MT axes for this slot + */ +struct input_mt_slot { + int abs[ABS_MT_LAST - ABS_MT_FIRST + 1]; +}; + +static inline void input_mt_set_value(struct input_mt_slot *slot, + unsigned code, int value) +{ + slot->abs[code - ABS_MT_FIRST] = value; +} + +static inline int input_mt_get_value(const struct input_mt_slot *slot, + unsigned code) +{ + return slot->abs[code - ABS_MT_FIRST]; +} + +int input_mt_create_slots(struct input_dev *dev, unsigned int num_slots); +void input_mt_destroy_slots(struct input_dev *dev); + +static inline void input_mt_slot(struct input_dev *dev, int slot) +{ + input_event(dev, EV_ABS, ABS_MT_SLOT, slot); +} + +#endif -- cgit v1.1 From 8cde81001626c4c60b26ef2eb5fc522885ed9fd0 Mon Sep 17 00:00:00 2001 From: Henrik Rydberg Date: Sat, 27 Nov 2010 10:50:54 +0100 Subject: input: mt: Collect slots initialization code The MT slots devices all follow the same initialization pattern of creating slots and hinting about buffer size. Let drivers call an initialization function instead, and make sure it can be called repeatedly without side effects. Signed-off-by: Henrik Rydberg --- include/linux/input/mt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/input/mt.h b/include/linux/input/mt.h index 4f5e9d0..d7f6518 100644 --- a/include/linux/input/mt.h +++ b/include/linux/input/mt.h @@ -33,7 +33,7 @@ static inline int input_mt_get_value(const struct input_mt_slot *slot, return slot->abs[code - ABS_MT_FIRST]; } -int input_mt_create_slots(struct input_dev *dev, unsigned int num_slots); +int input_mt_init_slots(struct input_dev *dev, unsigned int num_slots); void input_mt_destroy_slots(struct input_dev *dev); static inline void input_mt_slot(struct input_dev *dev, int slot) -- cgit v1.1 From c5f4dec1ceb6ab773bbbefbe64a7c990c7d6b17f Mon Sep 17 00:00:00 2001 From: Henrik Rydberg Date: Wed, 15 Dec 2010 13:50:34 +0100 Subject: input: mt: Move tracking and pointer emulation to input-mt The drivers using the type B protocol all report tracking information the same way. The contact id is semantically equivalent to ABS_MT_SLOT, and the handling of ABS_MT_TRACKING_ID only complicates the driver. The situation can be improved upon by providing a common pointer emulation code, thereby removing the need for the tracking id in the driver. This patch moves all tracking event handling over to the input core, simplifying both the existing drivers and the ones currently in preparation. Acked-by: Ping Cheng Acked-by: Jiri Kosina Signed-off-by: Henrik Rydberg --- include/linux/input.h | 3 +++ include/linux/input/mt.h | 13 +++++++++++++ 2 files changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/input.h b/include/linux/input.h index 99e2a52..6de145d 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -848,6 +848,7 @@ struct input_keymap_entry { */ #define MT_TOOL_FINGER 0 #define MT_TOOL_PEN 1 +#define MT_TOOL_MAX 1 /* * Values describing the status of a force-feedback effect @@ -1122,6 +1123,7 @@ struct ff_effect { * of tracked contacts * @mtsize: number of MT slots the device uses * @slot: MT slot currently being transmitted + * @trkid: stores MT tracking ID for the current contact * @absinfo: array of &struct absinfo elements holding information * about absolute axes (current value, min, max, flat, fuzz, * resolution) @@ -1206,6 +1208,7 @@ struct input_dev { struct input_mt_slot *mt; int mtsize; int slot; + int trkid; struct input_absinfo *absinfo; diff --git a/include/linux/input/mt.h b/include/linux/input/mt.h index d7f6518..b3ac06a 100644 --- a/include/linux/input/mt.h +++ b/include/linux/input/mt.h @@ -13,6 +13,8 @@ #include +#define TRKID_MAX 0xffff + /** * struct input_mt_slot - represents the state of an input MT slot * @abs: holds current values of ABS_MT axes for this slot @@ -36,9 +38,20 @@ static inline int input_mt_get_value(const struct input_mt_slot *slot, int input_mt_init_slots(struct input_dev *dev, unsigned int num_slots); void input_mt_destroy_slots(struct input_dev *dev); +static inline int input_mt_new_trkid(struct input_dev *dev) +{ + return dev->trkid++ & TRKID_MAX; +} + static inline void input_mt_slot(struct input_dev *dev, int slot) { input_event(dev, EV_ABS, ABS_MT_SLOT, slot); } +void input_mt_report_slot_state(struct input_dev *dev, + unsigned int tool_type, bool active); + +void input_mt_report_finger_count(struct input_dev *dev, int count); +void input_mt_report_pointer_emulation(struct input_dev *dev, bool use_count); + #endif -- cgit v1.1 From e42a98b520bb22535687ead3120e80edc268279a Mon Sep 17 00:00:00 2001 From: Henrik Rydberg Date: Mon, 6 Dec 2010 10:05:43 +0100 Subject: input: mt: Add hovering distance axis Touch devices capable of hovering, i.e., fingers detected a distance from the surface, are not supported by the current input MT protocol. This patch adds ABS_MT_DISTANCE, which may be used to indicate the distance between the contact and the surface. Signed-off-by: Henrik Rydberg --- include/linux/input.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/input.h b/include/linux/input.h index 6de145d..b3a1e02 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -733,11 +733,12 @@ struct input_keymap_entry { #define ABS_MT_BLOB_ID 0x38 /* Group a set of packets as a blob */ #define ABS_MT_TRACKING_ID 0x39 /* Unique ID of initiated contact */ #define ABS_MT_PRESSURE 0x3a /* Pressure on contact area */ +#define ABS_MT_DISTANCE 0x3b /* Contact hover distance */ #ifdef __KERNEL__ /* Implementation details, userspace should not care about these */ #define ABS_MT_FIRST ABS_MT_TOUCH_MAJOR -#define ABS_MT_LAST ABS_MT_PRESSURE +#define ABS_MT_LAST ABS_MT_DISTANCE #endif #define ABS_MAX 0x3f -- cgit v1.1 From 2e80a82a49c4c7eca4e35734380f28298ba5db19 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 17 Nov 2010 23:17:36 +0100 Subject: perf: Dynamic pmu types Extend the perf_pmu_register() interface to allow for named and dynamic pmu types. Because we need to support the existing static types we cannot use dynamic types for everything, hence provide a type argument. If we want to enumerate the PMUs they need a name, provide one. Signed-off-by: Peter Zijlstra LKML-Reference: <20101117222056.259707703@chello.nl> Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 30e50e2..21206d2 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -588,6 +588,9 @@ struct perf_event; struct pmu { struct list_head entry; + char *name; + int type; + int * __percpu pmu_disable_count; struct perf_cpu_context * __percpu pmu_cpu_context; int task_ctx_nr; @@ -916,7 +919,7 @@ struct perf_output_handle { #ifdef CONFIG_PERF_EVENTS -extern int perf_pmu_register(struct pmu *pmu); +extern int perf_pmu_register(struct pmu *pmu, char *name, int type); extern void perf_pmu_unregister(struct pmu *pmu); extern int perf_num_counters(void); -- cgit v1.1 From abe43400579d5de0078c2d3a760e6598e183f871 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 17 Nov 2010 23:17:37 +0100 Subject: perf: Sysfs enumeration Simple sysfs emumeration of the PMUs. Use a "event_source" bus, and add PMU devices using their name. Each PMU device has a type attribute which contrains the value needed for perf_event_attr::type to identify this PMU. This is the minimal stub needed to start using this interface, we'll consider extending the sysfs usage later. Cc: Kay Sievers Cc: Greg KH Signed-off-by: Peter Zijlstra LKML-Reference: <20101117222056.316982569@chello.nl> Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 21206d2..dda5b0a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -588,6 +588,7 @@ struct perf_event; struct pmu { struct list_head entry; + struct device *dev; char *name; int type; -- cgit v1.1 From f08f5a0add20834d3f3d876dfe08005a5df656db Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 16 Dec 2010 17:11:58 +0100 Subject: PM / Runtime: Fix pm_runtime_suspended() There are some situations (e.g. in __pm_generic_call()), where pm_runtime_suspended() is used to decide whether or not to execute a device's (system) ->suspend() callback. The callback is not executed if pm_runtime_suspended() returns true, but it does so for devices that don't even support runtime PM, because the power.disable_depth device field is ignored by it. This leads to problems (i.e. devices are not suspened when they should), so rework pm_runtime_suspended() so that it returns false if the device's power.disable_depth field is different from zero. Signed-off-by: Rafael J. Wysocki Cc: stable@kernel.org --- include/linux/pm_runtime.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 3ec2358..d19f1cc 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -77,7 +77,8 @@ static inline void device_set_run_wake(struct device *dev, bool enable) static inline bool pm_runtime_suspended(struct device *dev) { - return dev->power.runtime_status == RPM_SUSPENDED; + return dev->power.runtime_status == RPM_SUSPENDED + && !dev->power.disable_depth; } static inline void pm_runtime_mark_last_busy(struct device *dev) -- cgit v1.1 From dddd9dc340ae1a41d90e084529ca979c77c4ecfe Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 8 Dec 2010 20:57:35 +0100 Subject: block: kill genhd_media_change_notify() There's no user of the facility. Kill it. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 7a7b9c1..5e4e692 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -173,7 +173,6 @@ struct gendisk { struct timer_rand_state *random; atomic_t sync_io; /* RAID */ - struct work_struct async_notify; #ifdef CONFIG_BLK_DEV_INTEGRITY struct blk_integrity *integrity; #endif -- cgit v1.1 From d2bf1b6723ed0eab378363649d15b7893bf14e91 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 8 Dec 2010 20:57:36 +0100 Subject: block: move register_disk() and del_gendisk() to block/genhd.c There's no reason for register_disk() and del_gendisk() to be in fs/partitions/check.c. Move both to genhd.c. While at it, collapse unlink_gendisk(), which was artificially in a separate function due to genhd.c / check.c split, into del_gendisk(). Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - include/linux/genhd.h | 1 - 2 files changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index aae86fd..83031bc 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -643,7 +643,6 @@ static inline void rq_flush_dcache_pages(struct request *rq) extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); -extern void register_disk(struct gendisk *dev); extern void generic_make_request(struct bio *bio); extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_put_request(struct request *); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 5e4e692..56e17ed 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -394,7 +394,6 @@ extern void part_round_stats(int cpu, struct hd_struct *part); /* block/genhd.c */ extern void add_disk(struct gendisk *disk); extern void del_gendisk(struct gendisk *gp); -extern void unlink_gendisk(struct gendisk *gp); extern struct gendisk *get_gendisk(dev_t dev, int *partno); extern struct block_device *bdget_disk(struct gendisk *disk, int partno); -- cgit v1.1 From 77ea887e433ad8389d416826936c110fa7910f80 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 8 Dec 2010 20:57:37 +0100 Subject: implement in-kernel gendisk events handling Currently, media presence polling for removeable block devices is done from userland. There are several issues with this. * Polling is done by periodically opening the device. For SCSI devices, the command sequence generated by such action involves a few different commands including TEST_UNIT_READY. This behavior, while perfectly legal, is different from Windows which only issues single command, GET_EVENT_STATUS_NOTIFICATION. Unfortunately, some ATAPI devices lock up after being periodically queried such command sequences. * There is no reliable and unintrusive way for a userland program to tell whether the target device is safe for media presence polling. For example, polling for media presence during an on-going burning session can make it fail. The polling program can avoid this by opening the device with O_EXCL but then it risks making a valid exclusive user of the device fail w/ -EBUSY. * Userland polling is unnecessarily heavy and in-kernel implementation is lighter and better coordinated (workqueue, timer slack). This patch implements framework for in-kernel disk event handling, which includes media presence polling. * bdops->check_events() is added, which supercedes ->media_changed(). It should check whether there's any pending event and return if so. Currently, two events are defined - DISK_EVENT_MEDIA_CHANGE and DISK_EVENT_EJECT_REQUEST. ->check_events() is guaranteed not to be called parallelly. * gendisk->events and ->async_events are added. These should be initialized by block driver before passing the device to add_disk(). The former contains the mask of all supported events and the latter the mask of all events which the device can report without polling. /sys/block/*/events[_async] export these to userland. * Kernel parameter block.events_dfl_poll_msecs controls the system polling interval (default is 0 which means disable) and /sys/block/*/events_poll_msecs control polling intervals for individual devices (default is -1 meaning use system setting). Note that if a device can report all supported events asynchronously and its polling interval isn't explicitly set, the device won't be polled regardless of the system polling interval. * If a device is opened exclusively with write access, event checking is automatically disabled until all write exclusive accesses are released. * There are event 'clearing' events. For example, both of currently defined events are cleared after the device has been successfully opened. This information is passed to ->check_events() callback using @clearing argument as a hint. * Event checking is always performed from system_nrt_wq and timer slack is set to 25% for polling. * Nothing changes for drivers which implement ->media_changed() but not ->check_events(). Going forward, all drivers will be converted to ->check_events() and ->media_change() will be dropped. Signed-off-by: Tejun Heo Cc: Kay Sievers Cc: Jan Kara Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 +++ include/linux/fs.h | 1 + include/linux/genhd.h | 18 +++++++++++++++++- 3 files changed, 21 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 83031bc..05667e6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1251,6 +1251,9 @@ struct block_device_operations { int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*direct_access) (struct block_device *, sector_t, void **, unsigned long *); + unsigned int (*check_events) (struct gendisk *disk, + unsigned int clearing); + /* ->media_changed() is DEPRECATED, use ->check_events() instead */ int (*media_changed) (struct gendisk *); void (*unlock_native_capacity) (struct gendisk *); int (*revalidate_disk) (struct gendisk *); diff --git a/include/linux/fs.h b/include/linux/fs.h index f485015..997d22e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -662,6 +662,7 @@ struct block_device { void * bd_claiming; void * bd_holder; int bd_holders; + bool bd_write_holder; #ifdef CONFIG_SYSFS struct gendisk * bd_holder_disk; /* for sysfs slave linkng */ #endif diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 56e17ed..13893aa 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -127,6 +127,11 @@ struct hd_struct { #define GENHD_FL_EXT_DEVT 64 /* allow extended devt */ #define GENHD_FL_NATIVE_CAPACITY 128 +enum { + DISK_EVENT_MEDIA_CHANGE = 1 << 0, /* media changed */ + DISK_EVENT_EJECT_REQUEST = 1 << 1, /* eject requested */ +}; + #define BLK_SCSI_MAX_CMDS (256) #define BLK_SCSI_CMD_PER_LONG (BLK_SCSI_MAX_CMDS / (sizeof(long) * 8)) @@ -143,6 +148,8 @@ struct disk_part_tbl { struct hd_struct __rcu *part[]; }; +struct disk_events; + struct gendisk { /* major, first_minor and minors are input parameters only, * don't use directly. Use disk_devt() and disk_max_parts(). @@ -154,6 +161,10 @@ struct gendisk { char disk_name[DISK_NAME_LEN]; /* name of major driver */ char *(*devnode)(struct gendisk *gd, mode_t *mode); + + unsigned int events; /* supported events */ + unsigned int async_events; /* async events, subset of all */ + /* Array of pointers to partitions indexed by partno. * Protected with matching bdev lock but stat and other * non-critical accesses use RCU. Always access through @@ -171,8 +182,8 @@ struct gendisk { struct kobject *slave_dir; struct timer_rand_state *random; - atomic_t sync_io; /* RAID */ + struct disk_events *ev; #ifdef CONFIG_BLK_DEV_INTEGRITY struct blk_integrity *integrity; #endif @@ -405,6 +416,11 @@ static inline int get_disk_ro(struct gendisk *disk) return disk->part0.policy; } +extern void disk_block_events(struct gendisk *disk); +extern void disk_unblock_events(struct gendisk *disk); +extern void disk_check_events(struct gendisk *disk); +extern unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask); + /* drivers/char/random.c */ extern void add_disk_randomness(struct gendisk *disk); extern void rand_initialize_disk(struct gendisk *disk); -- cgit v1.1 From 2d9217296bfa6fdc0d3707264076e5296faffdbd Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 8 Dec 2010 20:57:38 +0100 Subject: cdrom: add ->check_events() support In principle, cdrom just needs to pass through ->check_events() but CDROM_MEDIA_CHANGED ioctl makes things a bit more complex. Just as with ->media_changed() support, cdrom code needs to buffer the events and serve them to ioctl and vfs as requested. As the code has to deal with both ->check_events() and ->media_changed(), and vfs and ioctl event buffering, this patch adds check_events caching on top of the existing cdi->mc_flags buffering. It may be a good idea to deprecate CDROM_MEDIA_CHANGED ioctl and remove all this mess. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/cdrom.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 78e9047..35eae4b 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -946,6 +946,8 @@ struct cdrom_device_info { /* device-related storage */ unsigned int options : 30; /* options flags */ unsigned mc_flags : 2; /* media change buffer flags */ + unsigned int vfs_events; /* cached events for vfs path */ + unsigned int ioctl_events; /* cached events for ioctl path */ int use_count; /* number of times device opened */ char name[20]; /* name of the device type */ /* per-device flags */ @@ -965,6 +967,8 @@ struct cdrom_device_ops { int (*open) (struct cdrom_device_info *, int); void (*release) (struct cdrom_device_info *); int (*drive_status) (struct cdrom_device_info *, int); + unsigned int (*check_events) (struct cdrom_device_info *cdi, + unsigned int clearing, int slot); int (*media_changed) (struct cdrom_device_info *, int); int (*tray_move) (struct cdrom_device_info *, int); int (*lock_door) (struct cdrom_device_info *, int); @@ -993,6 +997,8 @@ extern int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev, extern void cdrom_release(struct cdrom_device_info *cdi, fmode_t mode); extern int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); +extern unsigned int cdrom_check_events(struct cdrom_device_info *cdi, + unsigned int clearing); extern int cdrom_media_changed(struct cdrom_device_info *); extern int register_cdrom(struct cdrom_device_info *cdi); -- cgit v1.1 From 93aae17af1172c40c6f74b7294e93a90c3cfaa5d Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 16 Dec 2010 17:52:17 +0100 Subject: sr: implement sr_check_events() Replace sr_media_change() with sr_check_events(). It normally only uses GET_EVENT_STATUS_NOTIFICATION to check both media change and eject request. If @clearing includes DISK_EVENT_MEDIA_CHANGE, it issues TUR and compares whether media presence has changed. The SCSI specific media change uevent is kept for compatibility. sr_media_change() was doing both media change check and revalidation. The revalidation part is split into sr_block_revalidate_disk(). Signed-off-by: Tejun Heo Cc: Kay Sievers Signed-off-by: Jens Axboe --- include/scsi/scsi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h index 216af85..8675861 100644 --- a/include/scsi/scsi.h +++ b/include/scsi/scsi.h @@ -104,6 +104,7 @@ struct scsi_cmnd; #define UNMAP 0x42 #define READ_TOC 0x43 #define READ_HEADER 0x44 +#define GET_EVENT_STATUS_NOTIFICATION 0x4a #define LOG_SELECT 0x4c #define LOG_SENSE 0x4d #define XDWRITEREAD_10 0x53 -- cgit v1.1 From d9c407b138926132e1f93c01fb2dee50eb0bb615 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 14 Dec 2010 14:55:50 +0000 Subject: NFS: Introduce new-style XDR encoding functions for NFSv3 We're interested in taking advantage of the safety benefits of xdr_streams. These data structures allow more careful checking for buffer overflow while encoding. More careful type checking is also introduced in the new functions. For efficiency, we also eventually want to be able to pass xdr_streams from call_encode() to all XDR encoding functions, rather than building an xdr_stream in every XDR encoding function in the kernel. To do this means all encoders must be ready to handle a passed-in xdr_stream. The new encoders follow the modern paradigm for XDR encoders: BUG on error, and always return a zero status code. Static helper functions are left without the "inline" directive. This allows the compiler to choose automatically how to optimize these for size or speed. Signed-off-by: Chuck Lever Tested-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/nfs3.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/nfs3.h b/include/linux/nfs3.h index ac33806..e2ee14f 100644 --- a/include/linux/nfs3.h +++ b/include/linux/nfs3.h @@ -11,6 +11,8 @@ #define NFS3_MAXGROUPS 16 #define NFS3_FHSIZE 64 #define NFS3_COOKIESIZE 4 +#define NFS3_CREATEVERFSIZE 8 +#define NFS3_COOKIEVERFSIZE 8 #define NFS3_FIFO_DEV (-1) #define NFS3MODE_FMT 0170000 #define NFS3MODE_DIR 0040000 -- cgit v1.1 From e4f9323409369a3aeb01885c0c4409d2eeec794a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 14 Dec 2010 14:56:30 +0000 Subject: NFS: Introduce new-style XDR decoding functions for NFSv2 We'd like to prevent local buffer overflows caused by malicious or broken servers. New xdr_stream style decoders can do that. For efficiency, we also eventually want to be able to pass xdr_streams from call_decode() to all XDR decoding functions, rather than building an xdr_stream in every XDR decoding function in the kernel. Static helper functions are left without the "inline" directive. This allows the compiler to choose automatically how to optimize these for size or speed. Signed-off-by: Chuck Lever Tested-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/nfs3.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nfs3.h b/include/linux/nfs3.h index e2ee14f..6ccfe3b 100644 --- a/include/linux/nfs3.h +++ b/include/linux/nfs3.h @@ -13,6 +13,7 @@ #define NFS3_COOKIESIZE 4 #define NFS3_CREATEVERFSIZE 8 #define NFS3_COOKIEVERFSIZE 8 +#define NFS3_WRITEVERFSIZE 8 #define NFS3_FIFO_DEV (-1) #define NFS3MODE_FMT 0170000 #define NFS3MODE_DIR 0040000 -- cgit v1.1 From d8367c504e39528a057a5d7a267b6724f7fdb4b8 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 14 Dec 2010 14:57:52 +0000 Subject: lockd: Move nlmdbg_cookie2a() to svclock.c Clean up. nlmdbg_cookie2a() is used only in svclock.c. Signed-off-by: Chuck Lever Tested-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/lockd/debug.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include') diff --git a/include/linux/lockd/debug.h b/include/linux/lockd/debug.h index 34b2b7f..257d377 100644 --- a/include/linux/lockd/debug.h +++ b/include/linux/lockd/debug.h @@ -44,14 +44,4 @@ #define NLMDBG_XDR 0x0100 #define NLMDBG_ALL 0x7fff - -/* - * Support for printing NLM cookies in dprintk() - */ -#ifdef RPC_DEBUG -struct nlm_cookie; -/* Call this function with the BKL held (it uses a static buffer) */ -extern const char *nlmdbg_cookie2a(const struct nlm_cookie *); -#endif - #endif /* LINUX_LOCKD_DEBUG_H */ -- cgit v1.1 From 573c4e1ef53a6b891b73cc2257e1604da754a2e4 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 14 Dec 2010 14:58:11 +0000 Subject: NFS: Simplify ->decode_dirent() calling sequence Clean up. The pointer returned by ->decode_dirent() is no longer used as a pointer. The only call site (xdr_decode() in fs/nfs/dir.c) simply extracts the errno value encoded in the pointer. Replace the returned pointer with a standard integer errno return value. Also, pass the "server" argument as part of the nfs_entry instead of as a separate parameter. It's faster to derive "server" in nfs_readdir_xdr_to_array() since we already have the directory's inode handy. "server" ought to be invariant for a set of entries in the same directory, right? The legacy versions of decode_dirent() don't use "server" anyway, so it's wasted work for them to derive and pass "server" for each entry. Signed-off-by: Chuck Lever Tested-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 80f0719..236e7e4 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -484,6 +484,7 @@ struct nfs_entry { struct nfs_fh * fh; struct nfs_fattr * fattr; unsigned char d_type; + struct nfs_server * server; }; /* @@ -1089,7 +1090,7 @@ struct nfs_rpc_ops { int (*pathconf) (struct nfs_server *, struct nfs_fh *, struct nfs_pathconf *); int (*set_capabilities)(struct nfs_server *, struct nfs_fh *); - __be32 *(*decode_dirent)(struct xdr_stream *, struct nfs_entry *, struct nfs_server *, int plus); + int (*decode_dirent)(struct xdr_stream *, struct nfs_entry *, int); void (*read_setup) (struct nfs_read_data *, struct rpc_message *); int (*read_done) (struct rpc_task *, struct nfs_read_data *); void (*write_setup) (struct nfs_write_data *, struct rpc_message *); -- cgit v1.1 From 9f06c719f474be7003763284a990bed6377bb0d4 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 14 Dec 2010 14:59:18 +0000 Subject: SUNRPC: New xdr_streams XDR encoder API Now that all client-side XDR encoder routines use xdr_streams, there should be no need to support the legacy calling sequence [rpc_rqst *, __be32 *, RPC arg *] anywhere. We can construct an xdr_stream in the generic RPC code, instead of in each encoder function. Also, all the client-side encoder functions return 0 now, making a return value superfluous. Take this opportunity to convert them to return void instead. This is a refactoring change. It should not cause different behavior. Signed-off-by: Chuck Lever Tested-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 4 ++-- include/linux/sunrpc/clnt.h | 2 +- include/linux/sunrpc/xdr.h | 9 +++++++-- 3 files changed, 10 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index b202475..d88cffb 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -110,7 +110,7 @@ struct rpc_credops { __be32 * (*crmarshal)(struct rpc_task *, __be32 *); int (*crrefresh)(struct rpc_task *); __be32 * (*crvalidate)(struct rpc_task *, __be32 *); - int (*crwrap_req)(struct rpc_task *, kxdrproc_t, + int (*crwrap_req)(struct rpc_task *, kxdreproc_t, void *, __be32 *, void *); int (*crunwrap_resp)(struct rpc_task *, kxdrproc_t, void *, __be32 *, void *); @@ -139,7 +139,7 @@ struct rpc_cred * rpcauth_generic_bind_cred(struct rpc_task *, struct rpc_cred * void put_rpccred(struct rpc_cred *); __be32 * rpcauth_marshcred(struct rpc_task *, __be32 *); __be32 * rpcauth_checkverf(struct rpc_task *, __be32 *); -int rpcauth_wrap_req(struct rpc_task *task, kxdrproc_t encode, void *rqstp, __be32 *data, void *obj); +int rpcauth_wrap_req(struct rpc_task *task, kxdreproc_t encode, void *rqstp, __be32 *data, void *obj); int rpcauth_unwrap_resp(struct rpc_task *task, kxdrproc_t decode, void *rqstp, __be32 *data, void *obj); int rpcauth_refreshcred(struct rpc_task *); void rpcauth_invalcred(struct rpc_task *); diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index a5a55f2..7b19c4e 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -89,7 +89,7 @@ struct rpc_version { */ struct rpc_procinfo { u32 p_proc; /* RPC procedure number */ - kxdrproc_t p_encode; /* XDR encode function */ + kxdreproc_t p_encode; /* XDR encode function */ kxdrproc_t p_decode; /* XDR decode function */ unsigned int p_arglen; /* argument hdr length (u32) */ unsigned int p_replen; /* reply hdr length (u32) */ diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 498ab93..a21cf53 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -33,8 +33,8 @@ struct xdr_netobj { }; /* - * This is the generic XDR function. rqstp is either a rpc_rqst (client - * side) or svc_rqst pointer (server side). + * This is the legacy generic XDR function. rqstp is either a rpc_rqst + * (client side) or svc_rqst pointer (server side). * Encode functions always assume there's enough room in the buffer. */ typedef int (*kxdrproc_t)(void *rqstp, __be32 *data, void *obj); @@ -203,6 +203,11 @@ struct xdr_stream { struct kvec *iov; /* pointer to the current kvec */ }; +/* + * This is the xdr_stream style generic XDR function. + */ +typedef void (*kxdreproc_t)(void *rqstp, struct xdr_stream *xdr, void *obj); + extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p); extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes); extern void xdr_write_pages(struct xdr_stream *xdr, struct page **pages, -- cgit v1.1 From bf2695516db982e90a22fc94f93491b481796bb1 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 14 Dec 2010 14:59:29 +0000 Subject: SUNRPC: New xdr_streams XDR decoder API Now that all client-side XDR decoder routines use xdr_streams, there should be no need to support the legacy calling sequence [rpc_rqst *, __be32 *, RPC res *] anywhere. We can construct an xdr_stream in the generic RPC code, instead of in each decoder function. This is a refactoring change. It should not cause different behavior. Signed-off-by: Chuck Lever Tested-by: J. Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/sunrpc/auth.h | 4 ++-- include/linux/sunrpc/clnt.h | 2 +- include/linux/sunrpc/xdr.h | 3 ++- 3 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index d88cffb..8521067 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -112,7 +112,7 @@ struct rpc_credops { __be32 * (*crvalidate)(struct rpc_task *, __be32 *); int (*crwrap_req)(struct rpc_task *, kxdreproc_t, void *, __be32 *, void *); - int (*crunwrap_resp)(struct rpc_task *, kxdrproc_t, + int (*crunwrap_resp)(struct rpc_task *, kxdrdproc_t, void *, __be32 *, void *); }; @@ -140,7 +140,7 @@ void put_rpccred(struct rpc_cred *); __be32 * rpcauth_marshcred(struct rpc_task *, __be32 *); __be32 * rpcauth_checkverf(struct rpc_task *, __be32 *); int rpcauth_wrap_req(struct rpc_task *task, kxdreproc_t encode, void *rqstp, __be32 *data, void *obj); -int rpcauth_unwrap_resp(struct rpc_task *task, kxdrproc_t decode, void *rqstp, __be32 *data, void *obj); +int rpcauth_unwrap_resp(struct rpc_task *task, kxdrdproc_t decode, void *rqstp, __be32 *data, void *obj); int rpcauth_refreshcred(struct rpc_task *); void rpcauth_invalcred(struct rpc_task *); int rpcauth_uptodatecred(struct rpc_task *); diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 7b19c4e..ef9476a 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -90,7 +90,7 @@ struct rpc_version { struct rpc_procinfo { u32 p_proc; /* RPC procedure number */ kxdreproc_t p_encode; /* XDR encode function */ - kxdrproc_t p_decode; /* XDR decode function */ + kxdrdproc_t p_decode; /* XDR decode function */ unsigned int p_arglen; /* argument hdr length (u32) */ unsigned int p_replen; /* reply hdr length (u32) */ unsigned int p_count; /* call count */ diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index a21cf53..9a21e81 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -204,9 +204,10 @@ struct xdr_stream { }; /* - * This is the xdr_stream style generic XDR function. + * These are the xdr_stream style generic XDR encode and decode functions. */ typedef void (*kxdreproc_t)(void *rqstp, struct xdr_stream *xdr, void *obj); +typedef int (*kxdrdproc_t)(void *rqstp, struct xdr_stream *xdr, void *obj); extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p); extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes); -- cgit v1.1 From 7db836d4a427c3c64406b00b6d8d745d6335d72a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 14 Dec 2010 15:05:42 +0000 Subject: lockd: Split nlm_release_call() The nlm_release_call() function is invoked from both the server and the client side. We're about to introduce a distinct server- and client-side nlm_release_host(), so nlm_release_call() must first be split into a client-side and a server-side version. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/lockd/lockd.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 2dee05e..a32ba62 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -202,9 +202,9 @@ extern u32 nsm_local_state; * Lockd client functions */ struct nlm_rqst * nlm_alloc_call(struct nlm_host *host); -void nlm_release_call(struct nlm_rqst *); int nlm_async_call(struct nlm_rqst *, u32, const struct rpc_call_ops *); int nlm_async_reply(struct nlm_rqst *, u32, const struct rpc_call_ops *); +void nlmclnt_release_call(struct nlm_rqst *); struct nlm_wait * nlmclnt_prepare_block(struct nlm_host *host, struct file_lock *fl); void nlmclnt_finish_block(struct nlm_wait *block); int nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout); @@ -267,6 +267,7 @@ unsigned long nlmsvc_retry_blocked(void); void nlmsvc_traverse_blocks(struct nlm_host *, struct nlm_file *, nlm_host_match_fn_t match); void nlmsvc_grant_reply(struct nlm_cookie *, __be32); +void nlmsvc_release_call(struct nlm_rqst *); /* * File handling for the server personality -- cgit v1.1 From 8ea6ecc8b0759756a766c05dc7c98c51ec90de37 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 14 Dec 2010 15:05:52 +0000 Subject: lockd: Create client-side nlm_host cache NFS clients don't need the garbage collection processing that is performed on nlm_host structures. The client picks up an nlm_host at mount time and holds a reference to it until the file system is unmounted. Servers, on the other hand, don't have a precise way to tell when an nlm_host is no longer being used, so zero refcount nlm_host entries are left to expire in the cache after a time. Basically there's nothing holding a reference to an nlm_host between individual server-side NLM requests, but we can't afford the expense of recreating them for every new NLM request from a client. The nlm_host cache adds some lifetime hysteresis to entries in the cache so the next time a particular nlm_host is needed, it's likely to be discovered by a lookup rather than created from whole cloth. With the new implementation, client nlm_host cache items are no longer garbage collected, and are destroyed directly by a new release function specialized for client entries, nlmclnt_release_host(). They are cached in their own data structure, and have their own lookup logic, simplified and specialized for client nlm_host entries. However, the client nlm_host cache still shares reboot recovery logic with the server nlm_host cache. The NSM "peer rebooted" downcall for clients and servers still come through the same RPC call. This is a legacy formal API that would be difficult to alter, and besides, the user space NSM implementation can't tell the difference between peers that are clients or servers. For this reason, the client cache continues to share the nlm_host_mutex (and reboot recovery logic) with the server cache. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/lockd/lockd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index a32ba62..6c2a0e2 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -223,6 +223,7 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap, const u32 version, const char *hostname, int noresvport); +void nlmclnt_release_host(struct nlm_host *); struct nlm_host *nlmsvc_lookup_host(const struct svc_rqst *rqstp, const char *hostname, const size_t hostname_len); -- cgit v1.1 From 67216b94d498f5880d8bba2a6b841880739dd524 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 14 Dec 2010 15:06:12 +0000 Subject: lockd: Clean up nlmsvc_lookup_host() Clean up. Change nlmsvc_lookup_host() to be purpose-built for server-side nlm_host management. This replaces the generic nlm_lookup_host() helper function, just like on the client side. The lookup logic is specialized for server host lookups. The server side cache also gets its own specialized equivalent of the nlm_release_host() function. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/lockd/lockd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 6c2a0e2..ff9abff 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -227,10 +227,10 @@ void nlmclnt_release_host(struct nlm_host *); struct nlm_host *nlmsvc_lookup_host(const struct svc_rqst *rqstp, const char *hostname, const size_t hostname_len); +void nlmsvc_release_host(struct nlm_host *); struct rpc_clnt * nlm_bind_host(struct nlm_host *); void nlm_rebind_host(struct nlm_host *); struct nlm_host * nlm_get_host(struct nlm_host *); -void nlm_release_host(struct nlm_host *); void nlm_shutdown_hosts(void); void nlm_host_rebooted(const struct nlm_reboot *); -- cgit v1.1 From 3f84622d7c7818077f5e6cf4b8a0d1b10dc65147 Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Sat, 27 Nov 2010 19:26:32 +0100 Subject: SSB: Fix nvram_get on BCM47xx platform The nvram_get function was never in the mainline kernel, it only existed in an external OpenWrt patch. Use nvram_getenv function, which is in mainline and use an include instead of an extra function declaration. et0macaddr contains the mac address in text from like 00:11:22:33:44:55. We have to parse it before adding it into macaddr. nvram_parse_macaddr will be merged into asm/mach-bcm47xx/nvram.h through the MIPS git tree and will be available soon. It will not build now without nvram_parse_macaddr, but it hasn't before either. Signed-off-by: Hauke Mehrtens To: linux-mips@linux-mips.org Cc: mb@bu3sch.de Cc: netdev@vger.kernel.org Cc: Hauke Mehrtens Acked-by: Michael Buesch Patchwork: https://patchwork.linux-mips.org/patch/1849/ Signed-off-by: Ralf Baechle --- include/linux/ssb/ssb_driver_gige.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/ssb/ssb_driver_gige.h b/include/linux/ssb/ssb_driver_gige.h index 942e387..eba52a1 100644 --- a/include/linux/ssb/ssb_driver_gige.h +++ b/include/linux/ssb/ssb_driver_gige.h @@ -96,16 +96,21 @@ static inline bool ssb_gige_must_flush_posted_writes(struct pci_dev *pdev) return 0; } -extern char * nvram_get(const char *name); +#ifdef CONFIG_BCM47XX +#include /* Get the device MAC address */ static inline void ssb_gige_get_macaddr(struct pci_dev *pdev, u8 *macaddr) { -#ifdef CONFIG_BCM47XX - char *res = nvram_get("et0macaddr"); - if (res) - memcpy(macaddr, res, 6); -#endif + char buf[20]; + if (nvram_getenv("et0macaddr", buf, sizeof(buf)) < 0) + return; + nvram_parse_macaddr(buf, macaddr); } +#else +static inline void ssb_gige_get_macaddr(struct pci_dev *pdev, u8 *macaddr) +{ +} +#endif extern int ssb_gige_pcibios_plat_dev_init(struct ssb_device *sdev, struct pci_dev *pdev); -- cgit v1.1 From cf4e594ea7e55555e81647b74a3a8e8b2826a529 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 16 Dec 2010 00:52:40 +0200 Subject: nl80211: Add notification for dropped Deauth/Disassoc Add a new notification to indicate that a received, unprotected Deauthentication or Disassociation frame was dropped due to management frame protection being in use. This notification is needed to allow user space (e.g., wpa_supplicant) to implement SA Query procedure to recover from association state mismatch between an AP and STA. This is needed to avoid getting stuck in non-working state when MFP (IEEE 802.11w) is used and a protected Deauthentication or Disassociation frame is dropped for any reason. After that, the station would silently discard any unprotected Deauthentication or Disassociation frame that could be indicating that the AP does not have association for the STA (when the Reason Code would be 6 or 7). IEEE Std 802.11w-2009, 11.13 describes this recovery mechanism. Signed-off-by: Jouni Malinen Signed-off-by: John W. Linville --- include/linux/nl80211.h | 10 ++++++++++ include/net/cfg80211.h | 26 ++++++++++++++++++++++++++ 2 files changed, 36 insertions(+) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 1cee56b..7483a89 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -399,6 +399,13 @@ * @NL80211_CMD_LEAVE_MESH: Leave the mesh network -- no special arguments, the * network is determined by the network interface. * + * @NL80211_CMD_UNPROT_DEAUTHENTICATE: Unprotected deauthentication frame + * notification. This event is used to indicate that an unprotected + * deauthentication frame was dropped when MFP is in use. + * @NL80211_CMD_UNPROT_DISASSOCIATE: Unprotected disassociation frame + * notification. This event is used to indicate that an unprotected + * disassociation frame was dropped when MFP is in use. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -508,6 +515,9 @@ enum nl80211_commands { NL80211_CMD_JOIN_MESH, NL80211_CMD_LEAVE_MESH, + NL80211_CMD_UNPROT_DEAUTHENTICATE, + NL80211_CMD_UNPROT_DISASSOCIATE, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f45e15f..3d1c09b 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2360,6 +2360,32 @@ void __cfg80211_send_disassoc(struct net_device *dev, const u8 *buf, size_t len); /** + * cfg80211_send_unprot_deauth - notification of unprotected deauthentication + * @dev: network device + * @buf: deauthentication frame (header + body) + * @len: length of the frame data + * + * This function is called whenever a received Deauthentication frame has been + * dropped in station mode because of MFP being used but the Deauthentication + * frame was not protected. This function may sleep. + */ +void cfg80211_send_unprot_deauth(struct net_device *dev, const u8 *buf, + size_t len); + +/** + * cfg80211_send_unprot_disassoc - notification of unprotected disassociation + * @dev: network device + * @buf: disassociation frame (header + body) + * @len: length of the frame data + * + * This function is called whenever a received Disassociation frame has been + * dropped in station mode because of MFP being used but the Disassociation + * frame was not protected. This function may sleep. + */ +void cfg80211_send_unprot_disassoc(struct net_device *dev, const u8 *buf, + size_t len); + +/** * cfg80211_michael_mic_failure - notification of Michael MIC failure (TKIP) * @dev: network device * @addr: The source MAC address of the frame -- cgit v1.1 From 2784fe915cd25adf23ea28534019308d8a144721 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Wed, 15 Dec 2010 19:24:11 -0800 Subject: cfg80211: fix null pointer dereference with a custom regulatory request Once we moved the core regulatory request to the queue and let the scheduler process it last_request will have been left NULL until the schedular decides to process the first request. When this happens and we are loading a driver with a custom regulatory request like all Atheros drivers we end up with a NULL pointer dereference. We fix this by checking if the request was a custom one. BUG: unable to handle kernel NULL pointer dereference at 0000000000000004 IP: [] freq_reg_info_regd.clone.2+0x27/0x130 [cfg80211] PGD 71f91067 PUD 712b2067 PMD 0 Oops: 0000 [#1] PREEMPT SMP last sysfs file: /sys/devices/pci0000:00/0000:00:1d.7/usb2/2-1/firmware/2-1/loading CPU 0 Modules linked in: ath9k_htc(+) ath9k_common ath9k_hw ath Pid: 3094, comm: insmod Tainted: G W 2.6.37-rc5-wl #16 INVALID/28427ZQ RIP: 0010:[] [] freq_reg_info_regd.clone.2+0x27/0x130 [cfg80211] RSP: 0018:ffff88007045db78 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffffffffa047d9a0 RCX: ffff88007045dbd0 RDX: 0000000000004e20 RSI: 000000000024cde0 RDI: ffff8800700483e0 RBP: ffff88007045db98 R08: ffffffffa02f5b40 R09: 0000000000000001 R10: 000000000000000e R11: 0000000000000001 R12: 0000000000000000 R13: ffff88007004e3b0 R14: 0000000000000000 R15: ffff880070048340 FS: 00007f635a707700(0000) GS:ffff880077400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000004 CR3: 00000000708a9000 CR4: 00000000000006f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process insmod (pid: 3094, threadinfo ffff88007045c000, task ffff8800713e3ec0) Stack: ffffffffa047d9a0 0000000000000000 ffff88007004e3b0 0000000000000000 ffff88007045dc08 ffffffffa016e147 000000007045dc08 0000000000000002 ffff8800700483e0 ffffffffa02f5b40 ffff88007045dbd8 0000000000000000 Call Trace: [] wiphy_apply_custom_regulatory+0x137/0x1d0 [cfg80211] [] ? ath9k_reg_notifier+0x0/0x50 [ath9k_htc] [] ath_regd_init+0x347/0x430 [ath] [] ath9k_htc_probe_device+0x6c5/0x960 [ath9k_htc] [] ath9k_htc_hw_init+0xc/0x30 [ath9k_htc] [] ath9k_hif_usb_probe+0x216/0x3b0 [ath9k_htc] [] usb_probe_interface+0x10c/0x210 [usbcore] [] driver_probe_device+0x96/0x1c0 [] __driver_attach+0xa3/0xb0 [] ? __driver_attach+0x0/0xb0 [] bus_for_each_dev+0x5e/0x90 [] driver_attach+0x19/0x20 [] bus_add_driver+0x168/0x320 [] driver_register+0x71/0x140 [] ? __raw_spin_lock_init+0x38/0x70 [] usb_register_driver+0xdc/0x190 [usbcore] [] ? ath9k_htc_init+0x0/0x4f [ath9k_htc] [] ath9k_hif_usb_init+0x1e/0x20 [ath9k_htc] [] ath9k_htc_init+0x2b/0x4f [ath9k_htc] [] do_one_initcall+0x3f/0x180 [] sys_init_module+0xbb/0x200 [] system_call_fastpath+0x16/0x1b Code: RIP [] freq_reg_info_regd.clone.2+0x27/0x130 [cfg80211] RSP CR2: 0000000000000004 ---[ end trace 79e4193601c8b713 ]--- Reported-by: Sujith Manoharan Signed-off-by: Luis R. Rodriguez Signed-off-by: John W. Linville --- include/net/cfg80211.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 3d1c09b..6dc665a 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1419,7 +1419,9 @@ struct ieee80211_txrx_stypes { /** * struct wiphy - wireless hardware description - * @reg_notifier: the driver's regulatory notification callback + * @reg_notifier: the driver's regulatory notification callback, + * note that if your driver uses wiphy_apply_custom_regulatory() + * the reg_notifier's request can be passed as NULL * @regd: the driver's regulatory domain, if one was requested via * the regulatory_hint() API. This can be used by the driver * on the reg_notifier() if it chooses to ignore future -- cgit v1.1 From 6ce5b1ce5f6922db32599e73bcb22f5cdcbf241f Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Mon, 13 Dec 2010 14:08:53 -0600 Subject: tty: fix typos/errors in tty_driver.h comments Fix various typos and other errors in comments of tty_driver.h. The most significant is the wrong name of a function for the description of TTY_DRIVER_DYNAMIC_DEV. Signed-off-by: Timur Tabi Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_driver.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 09678ed..c3d43eb 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -102,7 +102,7 @@ * unsigned int cmd, unsigned long arg); * * This routine allows the tty driver to implement - * device-specific ioctl's. If the ioctl number passed in cmd + * device-specific ioctls. If the ioctl number passed in cmd * is not recognized by the driver, it should return ENOIOCTLCMD. * * Optional @@ -167,12 +167,12 @@ * * void (*hangup)(struct tty_struct *tty); * - * This routine notifies the tty driver that it should hangup the + * This routine notifies the tty driver that it should hang up the * tty device. * * Optional: * - * int (*break_ctl)(struct tty_stuct *tty, int state); + * int (*break_ctl)(struct tty_struct *tty, int state); * * This optional routine requests the tty driver to turn on or * off BREAK status on the RS-232 port. If state is -1, @@ -358,7 +358,7 @@ static inline struct tty_driver *tty_driver_kref_get(struct tty_driver *d) * overruns, either.) * * TTY_DRIVER_DYNAMIC_DEV --- if set, the individual tty devices need - * to be registered with a call to tty_register_driver() when the + * to be registered with a call to tty_register_device() when the * device is found in the system and unregistered with a call to * tty_unregister_device() so the devices will be show up * properly in sysfs. If not set, driver->num entries will be -- cgit v1.1 From 3f960dbb9dfe29ff283810624c4340c79fde87f5 Mon Sep 17 00:00:00 2001 From: "Govindraj.R" Date: Thu, 16 Dec 2010 18:12:47 +0530 Subject: Serial: Avoid unbalanced IRQ wake disable during resume To avoid unbalanced IRQ wake disable, ensure that wakeups are disabled only when wakeups have been successfully enabled. Tested on OMAP3630SDP/ZOOM3. Signed-off-by: Govindraj.R Reported-by: Paul Walmsley Cc: Santosh Shilimkar Acked-by: Kevin Hilman Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 7a6daf1..a23fa29 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -365,6 +365,7 @@ struct uart_port { struct device *dev; /* parent device */ unsigned char hub6; /* this should be in the 8250 driver */ unsigned char suspended; + unsigned char irq_wake; unsigned char unused[2]; void *private_data; /* generic platform data pointer */ }; -- cgit v1.1 From a3d22a68d752ccc1a01bb0a64dd70b7a98bf9e23 Mon Sep 17 00:00:00 2001 From: Vladislav Zolotarov Date: Mon, 13 Dec 2010 06:27:10 +0000 Subject: bnx2x: Take the distribution range definition out of skb_tx_hash() Move the calcualation of the Tx hash for a given hash range into a separate function and define the skb_tx_hash(), which calculates a Tx hash for a [0; dev->real_num_tx_queues - 1] hash values range, using this function (__skb_tx_hash()). Signed-off-by: Vladislav Zolotarov Signed-off-by: Eilon Greenstein Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 ++++++++++ include/linux/skbuff.h | 5 +++-- 2 files changed, 13 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d31bc3c..445e682 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1747,6 +1747,16 @@ static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index) __netif_schedule(txq->qdisc); } +/* + * Returns a Tx hash for the given packet when dev->real_num_tx_queues is used + * as a distribution range limit for the returned value. + */ +static inline u16 skb_tx_hash(const struct net_device *dev, + const struct sk_buff *skb) +{ + return __skb_tx_hash(dev, skb, dev->real_num_tx_queues); +} + /** * netif_is_multiqueue - test if device has multiple transmit queues * @dev: network device diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 19f37a6..4c4bec6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2165,8 +2165,9 @@ static inline bool skb_rx_queue_recorded(const struct sk_buff *skb) return skb->queue_mapping != 0; } -extern u16 skb_tx_hash(const struct net_device *dev, - const struct sk_buff *skb); +extern u16 __skb_tx_hash(const struct net_device *dev, + const struct sk_buff *skb, + unsigned int num_tx_queues); #ifdef CONFIG_XFRM static inline struct sec_path *skb_sec_path(struct sk_buff *skb) -- cgit v1.1 From b236da6931e2482bfe44a7865dd4e7bb036f3496 Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Tue, 14 Dec 2010 03:09:15 +0000 Subject: net: use NUMA_NO_NODE instead of the magic number -1 Signed-off-by: Changli Gao Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 445e682..cc916c5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -530,7 +530,7 @@ static inline int netdev_queue_numa_node_read(const struct netdev_queue *q) #if defined(CONFIG_XPS) && defined(CONFIG_NUMA) return q->numa_node; #else - return -1; + return NUMA_NO_NODE; #endif } -- cgit v1.1 From 443457242beb6716b43db4d62fe148eab5515505 Mon Sep 17 00:00:00 2001 From: Octavian Purdila Date: Mon, 13 Dec 2010 12:44:07 +0000 Subject: net: factorize sync-rcu call in unregister_netdevice_many Add dev_close_many and dev_deactivate_many to factorize another sync-rcu operation on the netdevice unregister path. $ modprobe dummy numdummies=10000 $ ip link set dev dummy* up $ time rmmod dummy Without the patch With the patch real 0m 24.63s real 0m 5.15s user 0m 0.00s user 0m 0.00s sys 0m 6.05s sys 0m 5.14s Signed-off-by: Octavian Purdila Signed-off-by: David S. Miller --- include/net/sch_generic.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index ea1f8a8..786cc39 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -321,6 +321,7 @@ extern void dev_init_scheduler(struct net_device *dev); extern void dev_shutdown(struct net_device *dev); extern void dev_activate(struct net_device *dev); extern void dev_deactivate(struct net_device *dev); +extern void dev_deactivate_many(struct list_head *head); extern struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, struct Qdisc *qdisc); extern void qdisc_reset(struct Qdisc *qdisc); -- cgit v1.1 From bc2ce894e113ed95b92541134b002fdc641e8080 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Dec 2010 14:08:34 -0800 Subject: tcp: relax tcp_paws_check() Some windows versions have wrong RFC1323 implementations, with SYN and SYNACKS messages containing zero tcp timestamps. We relaxed in commit fc1ad92dfc4e363 the passive connection case (Windows connects to a linux machine), but the reverse case (linux connects to a Windows machine) has an analogue problem when tsvals from windows machine are 'negative' (high order bit set) : PAWS triggers and we drops incoming messages. Fix this by making zero ts_recent value special, allowing frame to be processed. Based on a report and initial patch from Dmitiy Balakin Bugzilla reference : https://bugzilla.kernel.org/show_bug.cgi?id=24842 Reported-by: dmitriy.balakin@nicneiron.ru Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 3f227ba..2ab6c9c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1038,7 +1038,13 @@ static inline int tcp_paws_check(const struct tcp_options_received *rx_opt, return 1; if (unlikely(get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS)) return 1; - + /* + * Some OSes send SYN and SYNACK messages with tsval=0 tsecr=0, + * then following tcp messages have valid values. Ignore 0 value, + * or else 'negative' tsval might forbid us to accept their packets. + */ + if (!rx_opt->ts_recent) + return 1; return 0; } -- cgit v1.1 From fcbdf09d9652c8919dcf47072e3ae7dcb4eb98ac Mon Sep 17 00:00:00 2001 From: Octavian Purdila Date: Thu, 16 Dec 2010 14:26:56 -0800 Subject: net: fix nulls list corruptions in sk_prot_alloc Special care is taken inside sk_port_alloc to avoid overwriting skc_node/skc_nulls_node. We should also avoid overwriting skc_bind_node/skc_portaddr_node. The patch fixes the following crash: BUG: unable to handle kernel paging request at fffffffffffffff0 IP: [] udp4_lib_lookup2+0xad/0x370 [] __udp4_lib_lookup+0x282/0x360 [] __udp4_lib_rcv+0x31e/0x700 [] ? ip_local_deliver_finish+0x65/0x190 [] ? ip_local_deliver+0x88/0xa0 [] udp_rcv+0x15/0x20 [] ip_local_deliver_finish+0x65/0x190 [] ip_local_deliver+0x88/0xa0 [] ip_rcv_finish+0x32d/0x6f0 [] ? netif_receive_skb+0x99c/0x11c0 [] ip_rcv+0x2bb/0x350 [] netif_receive_skb+0x99c/0x11c0 Signed-off-by: Leonard Crestez Signed-off-by: Octavian Purdila Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 659d968..7d3f7ce 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -754,6 +754,7 @@ struct proto { void (*unhash)(struct sock *sk); void (*rehash)(struct sock *sk); int (*get_port)(struct sock *sk, unsigned short snum); + void (*clear_sk)(struct sock *sk, int size); /* Keeping track of sockets in use */ #ifdef CONFIG_PROC_FS @@ -852,6 +853,8 @@ static inline void __sk_prot_rehash(struct sock *sk) sk->sk_prot->hash(sk); } +void sk_prot_clear_portaddr_nulls(struct sock *sk, int size); + /* About 10 seconds */ #define SOCK_DESTROY_TIME (10*HZ) -- cgit v1.1 From 04fb451eff978ca059399eab83d5594b073caf6f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Miros=C5=82aw?= Date: Tue, 14 Dec 2010 15:24:08 +0000 Subject: net: Introduce skb_checksum_start_offset() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce skb_checksum_start_offset() to replace repetitive calculation. Signed-off-by: Michał Mirosław Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4c4bec6..20ec0a64 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1355,6 +1355,11 @@ static inline void skb_set_mac_header(struct sk_buff *skb, const int offset) } #endif /* NET_SKBUFF_DATA_USES_OFFSET */ +static inline int skb_checksum_start_offset(const struct sk_buff *skb) +{ + return skb->csum_start - skb_headroom(skb); +} + static inline int skb_transport_offset(const struct sk_buff *skb) { return skb_transport_header(skb) - skb->data; -- cgit v1.1 From fbc92a3455577ab17615cbcb91826399061bd789 Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Wed, 1 Dec 2010 18:51:05 +0100 Subject: tty: add 'active' sysfs attribute to tty0 and console device tty: add 'active' sysfs attribute to tty0 and console device Userspace can query the actual virtual console, and the configured console devices behind /dev/tt0 and /dev/console. The last entry in the list of devices is the active device, analog to the console= kernel command line option. The attribute supports poll(), which is raised when the virtual console is changed or /dev/console is reconfigured. Signed-off-by: Kay Sievers Signed-off-by: Greg Kroah-Hartman index 0000000..b138b66 --- include/linux/console.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/console.h b/include/linux/console.h index 875cfb1..9774fe6 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -151,7 +151,7 @@ extern int is_console_locked(void); extern int braille_register_console(struct console *, int index, char *console_options, char *braille_options); extern int braille_unregister_console(struct console *); - +extern void console_sysfs_notify(void); extern int console_suspend_enabled; /* Suspend and resume console messages over PM events */ -- cgit v1.1 From b7b8de087384cc1954a8cd075af3f9e5977caa2e Mon Sep 17 00:00:00 2001 From: Werner Fink Date: Fri, 3 Dec 2010 12:48:23 +0100 Subject: TTY: Add tty ioctl to figure device node of the system console. This has been in the SuSE kernels for a very long time. Signed-off-by: Werner Fink Signed-off-by: Greg Kroah-Hartman --- include/asm-generic/ioctls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/asm-generic/ioctls.h b/include/asm-generic/ioctls.h index a321665..3f3f2d1 100644 --- a/include/asm-generic/ioctls.h +++ b/include/asm-generic/ioctls.h @@ -67,6 +67,7 @@ #endif #define TIOCGPTN _IOR('T', 0x30, unsigned int) /* Get Pty Number (of pty-mux device) */ #define TIOCSPTLCK _IOW('T', 0x31, int) /* Lock/unlock Pty */ +#define TIOCGDEV _IOR('T', 0x32, unsigned int) /* Get primary device node of /dev/console */ #define TCGETX 0x5432 /* SYS5 TCGETX compatibility */ #define TCSETX 0x5433 #define TCSETXF 0x5434 -- cgit v1.1 From e692cb668fdd5a712c6ed2a2d6f2a36ee83997b4 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Wed, 1 Dec 2010 19:41:49 +0100 Subject: block: Deprecate QUEUE_FLAG_CLUSTER and use queue_limits instead When stacking devices, a request_queue is not always available. This forced us to have a no_cluster flag in the queue_limits that could be used as a carrier until the request_queue had been set up for a metadevice. There were several problems with that approach. First of all it was up to the stacking device to remember to set queue flag after stacking had completed. Also, the queue flag and the queue limits had to be kept in sync at all times. We got that wrong, which could lead to us issuing commands that went beyond the max scatterlist limit set by the driver. The proper fix is to avoid having two flags for tracking the same thing. We deprecate QUEUE_FLAG_CLUSTER and use the queue limit directly in the block layer merging functions. The queue_limit 'no_cluster' is turned into 'cluster' to avoid double negatives and to ease stacking. Clustering defaults to being enabled as before. The queue flag logic is removed from the stacking function, and explicitly setting the cluster flag is no longer necessary in DM and MD. Reported-by: Ed Lin Signed-off-by: Martin K. Petersen Acked-by: Mike Snitzer Cc: stable@kernel.org Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index aae86fd..95aeeeb 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -250,7 +250,7 @@ struct queue_limits { unsigned char misaligned; unsigned char discard_misaligned; - unsigned char no_cluster; + unsigned char cluster; signed char discard_zeroes_data; }; @@ -380,7 +380,6 @@ struct request_queue #endif }; -#define QUEUE_FLAG_CLUSTER 0 /* cluster several segments into 1 */ #define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */ #define QUEUE_FLAG_STOPPED 2 /* queue is stopped */ #define QUEUE_FLAG_SYNCFULL 3 /* read queue has been filled */ @@ -403,7 +402,6 @@ struct request_queue #define QUEUE_FLAG_SECDISCARD 19 /* supports SECDISCARD */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ - (1 << QUEUE_FLAG_CLUSTER) | \ (1 << QUEUE_FLAG_STACKABLE) | \ (1 << QUEUE_FLAG_SAME_COMP) | \ (1 << QUEUE_FLAG_ADD_RANDOM)) @@ -510,6 +508,11 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define rq_data_dir(rq) ((rq)->cmd_flags & 1) +static inline unsigned int blk_queue_cluster(struct request_queue *q) +{ + return q->limits.cluster; +} + /* * We regard a request as sync, if either a read or a sync write */ -- cgit v1.1 From 72d4cd9f38b5ed96b75df4c622be25e1c2648dd3 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 17 Dec 2010 08:34:20 +0100 Subject: block: max hardware sectors limit wrapper Implement blk_limits_max_hw_sectors() and make blk_queue_max_hw_sectors() a wrapper around it. DM needs this to avoid setting queue_limits' max_hw_sectors and max_sectors directly. dm_set_device_limits() now leverages blk_limits_max_hw_sectors() logic to establish the appropriate max_hw_sectors minimum (PAGE_SIZE). Fixes issue where DM was incorrectly setting max_sectors rather than max_hw_sectors (which caused dm_merge_bvec()'s max_hw_sectors check to be ineffective). Signed-off-by: Mike Snitzer Cc: stable@kernel.org Acked-by: Martin K. Petersen Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 95aeeeb..36ab42c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -808,6 +808,7 @@ extern struct request_queue *blk_init_allocated_queue(struct request_queue *, extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_make_request(struct request_queue *, make_request_fn *); extern void blk_queue_bounce_limit(struct request_queue *, u64); +extern void blk_limits_max_hw_sectors(struct queue_limits *, unsigned int); extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_segments(struct request_queue *, unsigned short); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); -- cgit v1.1 From b76834bc1b6db0a0923eed85c81b1113021b0612 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 6 Dec 2010 11:16:25 -0600 Subject: kprobes: Use this_cpu_ops Use this_cpu ops in various places to optimize per cpu data access. Cc: Jason Baron Cc: Namhyung Kim Acked-by: H. Peter Anvin Signed-off-by: Christoph Lameter Signed-off-by: Tejun Heo --- include/linux/kprobes.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index e7d1b2e..0c251e9 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -303,12 +303,12 @@ struct hlist_head * kretprobe_inst_table_head(struct task_struct *tsk); /* kprobe_running() will just return the current_kprobe on this CPU */ static inline struct kprobe *kprobe_running(void) { - return (__get_cpu_var(current_kprobe)); + return (__this_cpu_read(current_kprobe)); } static inline void reset_current_kprobe(void) { - __get_cpu_var(current_kprobe) = NULL; + __this_cpu_write(current_kprobe, NULL); } static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void) -- cgit v1.1 From 909ea96468096b07fbb41aaf69be060d92bd9271 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 8 Dec 2010 16:22:55 +0100 Subject: core: Replace __get_cpu_var with __this_cpu_read if not used for an address. __get_cpu_var() can be replaced with this_cpu_read and will then use a single read instruction with implied address calculation to access the correct per cpu instance. However, the address of a per cpu variable passed to __this_cpu_read() cannot be determined (since it's an implied address conversion through segment prefixes). Therefore apply this only to uses of __get_cpu_var where the address of the variable is not used. Cc: Pekka Enberg Cc: Hugh Dickins Cc: Thomas Gleixner Acked-by: H. Peter Anvin Signed-off-by: Christoph Lameter Signed-off-by: Tejun Heo --- include/asm-generic/irq_regs.h | 8 ++++---- include/linux/elevator.h | 12 +++--------- include/linux/kernel_stat.h | 2 +- 3 files changed, 8 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/asm-generic/irq_regs.h b/include/asm-generic/irq_regs.h index 5ae1d07..6bf9355 100644 --- a/include/asm-generic/irq_regs.h +++ b/include/asm-generic/irq_regs.h @@ -22,15 +22,15 @@ DECLARE_PER_CPU(struct pt_regs *, __irq_regs); static inline struct pt_regs *get_irq_regs(void) { - return __get_cpu_var(__irq_regs); + return __this_cpu_read(__irq_regs); } static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs) { - struct pt_regs *old_regs, **pp_regs = &__get_cpu_var(__irq_regs); + struct pt_regs *old_regs; - old_regs = *pp_regs; - *pp_regs = new_regs; + old_regs = __this_cpu_read(__irq_regs); + __this_cpu_write(__irq_regs, new_regs); return old_regs; } diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 4fd978e..4d85797 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -195,15 +195,9 @@ enum { /* * io context count accounting */ -#define elv_ioc_count_mod(name, __val) \ - do { \ - preempt_disable(); \ - __get_cpu_var(name) += (__val); \ - preempt_enable(); \ - } while (0) - -#define elv_ioc_count_inc(name) elv_ioc_count_mod(name, 1) -#define elv_ioc_count_dec(name) elv_ioc_count_mod(name, -1) +#define elv_ioc_count_mod(name, __val) this_cpu_add(name, __val) +#define elv_ioc_count_inc(name) this_cpu_inc(name) +#define elv_ioc_count_dec(name) this_cpu_dec(name) #define elv_ioc_count_read(name) \ ({ \ diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index ad54c84..44e83ba 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -47,7 +47,7 @@ extern unsigned long long nr_context_switches(void); #ifndef CONFIG_GENERIC_HARDIRQS #define kstat_irqs_this_cpu(irq) \ - (kstat_this_cpu.irqs[irq]) + (this_cpu_read(kstat.irqs[irq]) struct irq_desc; -- cgit v1.1 From a663ffff1d2e94a7c549a37d08ed9169ce83bdd6 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 6 Dec 2010 11:39:59 -0600 Subject: percpu: Generic support for this_cpu_add, sub, dec, inc_return Introduce generic support for this_cpu_add_return etc. The fallback is to realize these operations with simpler __this_cpu_ops. tj: - Reformatted __cpu_size_call_return2() to make it more consistent with its neighbors. - Dropped unnecessary temp variable ret__ from __this_cpu_generic_add_return(). Reviewed-by: Tejun Heo Reviewed-by: Mathieu Desnoyers Acked-by: H. Peter Anvin Signed-off-by: Christoph Lameter Signed-off-by: Tejun Heo --- include/linux/percpu.h | 71 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 71 insertions(+) (limited to 'include') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 5095b83..4d593de 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -240,6 +240,21 @@ extern void __bad_size_call_parameter(void); pscr_ret__; \ }) +#define __pcpu_size_call_return2(stem, variable, ...) \ +({ \ + typeof(variable) pscr2_ret__; \ + __verify_pcpu_ptr(&(variable)); \ + switch(sizeof(variable)) { \ + case 1: pscr2_ret__ = stem##1(variable, __VA_ARGS__); break; \ + case 2: pscr2_ret__ = stem##2(variable, __VA_ARGS__); break; \ + case 4: pscr2_ret__ = stem##4(variable, __VA_ARGS__); break; \ + case 8: pscr2_ret__ = stem##8(variable, __VA_ARGS__); break; \ + default: \ + __bad_size_call_parameter(); break; \ + } \ + pscr2_ret__; \ +}) + #define __pcpu_size_call(stem, variable, ...) \ do { \ __verify_pcpu_ptr(&(variable)); \ @@ -529,6 +544,62 @@ do { \ # define __this_cpu_xor(pcp, val) __pcpu_size_call(__this_cpu_xor_, (pcp), (val)) #endif +#define _this_cpu_generic_add_return(pcp, val) \ +({ \ + typeof(pcp) ret__; \ + preempt_disable(); \ + __this_cpu_add(pcp, val); \ + ret__ = __this_cpu_read(pcp); \ + preempt_enable(); \ + ret__; \ +}) + +#ifndef this_cpu_add_return +# ifndef this_cpu_add_return_1 +# define this_cpu_add_return_1(pcp, val) _this_cpu_generic_add_return(pcp, val) +# endif +# ifndef this_cpu_add_return_2 +# define this_cpu_add_return_2(pcp, val) _this_cpu_generic_add_return(pcp, val) +# endif +# ifndef this_cpu_add_return_4 +# define this_cpu_add_return_4(pcp, val) _this_cpu_generic_add_return(pcp, val) +# endif +# ifndef this_cpu_add_return_8 +# define this_cpu_add_return_8(pcp, val) _this_cpu_generic_add_return(pcp, val) +# endif +# define this_cpu_add_return(pcp, val) __pcpu_size_call_return2(this_cpu_add_return_, pcp, val) +#endif + +#define this_cpu_sub_return(pcp, val) this_cpu_add_return(pcp, -(val)) +#define this_cpu_inc_return(pcp) this_cpu_add_return(pcp, 1) +#define this_cpu_dec_return(pcp) this_cpu_add_return(pcp, -1) + +#define __this_cpu_generic_add_return(pcp, val) \ +({ \ + __this_cpu_add(pcp, val); \ + __this_cpu_read(pcp); \ +}) + +#ifndef __this_cpu_add_return +# ifndef __this_cpu_add_return_1 +# define __this_cpu_add_return_1(pcp, val) __this_cpu_generic_add_return(pcp, val) +# endif +# ifndef __this_cpu_add_return_2 +# define __this_cpu_add_return_2(pcp, val) __this_cpu_generic_add_return(pcp, val) +# endif +# ifndef __this_cpu_add_return_4 +# define __this_cpu_add_return_4(pcp, val) __this_cpu_generic_add_return(pcp, val) +# endif +# ifndef __this_cpu_add_return_8 +# define __this_cpu_add_return_8(pcp, val) __this_cpu_generic_add_return(pcp, val) +# endif +# define __this_cpu_add_return(pcp, val) __pcpu_size_call_return2(this_cpu_add_return_, pcp, val) +#endif + +#define __this_cpu_sub_return(pcp, val) this_cpu_add_return(pcp, -(val)) +#define __this_cpu_inc_return(pcp) this_cpu_add_return(pcp, 1) +#define __this_cpu_dec_return(pcp) this_cpu_add_return(pcp, -1) + /* * IRQ safe versions of the per cpu RMW operations. Note that these operations * are *not* safe against modification of the same variable from another -- cgit v1.1 From cfb824349556904b319464139be5c75fce983b0d Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 6 Dec 2010 11:40:03 -0600 Subject: highmem: Use this_cpu_xx_return() operations Use this_cpu operations to optimize access primitives for highmem. The main effect is the avoidance of address calculations through the use of a segment prefix. V3->V4 - kmap_atomic_idx: Do not return a value. - Use __this_cpu_dec without HIGHMEM_DEBUG Cc: Peter Zijlstra Cc: Catalin Marinas Acked-by: H. Peter Anvin Signed-off-by: Christoph Lameter Signed-off-by: Tejun Heo --- include/linux/highmem.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index b676c58..3a93f73 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -81,7 +81,8 @@ DECLARE_PER_CPU(int, __kmap_atomic_idx); static inline int kmap_atomic_idx_push(void) { - int idx = __get_cpu_var(__kmap_atomic_idx)++; + int idx = __this_cpu_inc_return(__kmap_atomic_idx) - 1; + #ifdef CONFIG_DEBUG_HIGHMEM WARN_ON_ONCE(in_irq() && !irqs_disabled()); BUG_ON(idx > KM_TYPE_NR); @@ -91,16 +92,18 @@ static inline int kmap_atomic_idx_push(void) static inline int kmap_atomic_idx(void) { - return __get_cpu_var(__kmap_atomic_idx) - 1; + return __this_cpu_read(__kmap_atomic_idx) - 1; } -static inline int kmap_atomic_idx_pop(void) +static inline void kmap_atomic_idx_pop(void) { - int idx = --__get_cpu_var(__kmap_atomic_idx); #ifdef CONFIG_DEBUG_HIGHMEM + int idx = __this_cpu_dec_return(__kmap_atomic_idx); + BUG_ON(idx < 0); +#else + __this_cpu_dec(__kmap_atomic_idx); #endif - return idx; } #endif -- cgit v1.1 From 403047754cf690b012369b8fb563b738b88086e6 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 17 Dec 2010 15:47:04 +0100 Subject: percpu,x86: relocate this_cpu_add_return() and friends - include/linux/percpu.h: this_cpu_add_return() and friends were located next to __this_cpu_add_return(). However, the overall organization is to first group by preemption safeness. Relocate this_cpu_add_return() and friends to preemption-safe area. - arch/x86/include/asm/percpu.h: Relocate percpu_add_return_op() after other more basic operations. Relocate [__]this_cpu_add_return_8() so that they're first grouped by preemption safeness. Signed-off-by: Tejun Heo Cc: Christoph Lameter --- include/linux/percpu.h | 60 +++++++++++++++++++++++++------------------------- 1 file changed, 30 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 4d593de..3484e88 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -417,6 +417,36 @@ do { \ # define this_cpu_xor(pcp, val) __pcpu_size_call(this_cpu_or_, (pcp), (val)) #endif +#define _this_cpu_generic_add_return(pcp, val) \ +({ \ + typeof(pcp) ret__; \ + preempt_disable(); \ + __this_cpu_add(pcp, val); \ + ret__ = __this_cpu_read(pcp); \ + preempt_enable(); \ + ret__; \ +}) + +#ifndef this_cpu_add_return +# ifndef this_cpu_add_return_1 +# define this_cpu_add_return_1(pcp, val) _this_cpu_generic_add_return(pcp, val) +# endif +# ifndef this_cpu_add_return_2 +# define this_cpu_add_return_2(pcp, val) _this_cpu_generic_add_return(pcp, val) +# endif +# ifndef this_cpu_add_return_4 +# define this_cpu_add_return_4(pcp, val) _this_cpu_generic_add_return(pcp, val) +# endif +# ifndef this_cpu_add_return_8 +# define this_cpu_add_return_8(pcp, val) _this_cpu_generic_add_return(pcp, val) +# endif +# define this_cpu_add_return(pcp, val) __pcpu_size_call_return2(this_cpu_add_return_, pcp, val) +#endif + +#define this_cpu_sub_return(pcp, val) this_cpu_add_return(pcp, -(val)) +#define this_cpu_inc_return(pcp) this_cpu_add_return(pcp, 1) +#define this_cpu_dec_return(pcp) this_cpu_add_return(pcp, -1) + /* * Generic percpu operations that do not require preemption handling. * Either we do not care about races or the caller has the @@ -544,36 +574,6 @@ do { \ # define __this_cpu_xor(pcp, val) __pcpu_size_call(__this_cpu_xor_, (pcp), (val)) #endif -#define _this_cpu_generic_add_return(pcp, val) \ -({ \ - typeof(pcp) ret__; \ - preempt_disable(); \ - __this_cpu_add(pcp, val); \ - ret__ = __this_cpu_read(pcp); \ - preempt_enable(); \ - ret__; \ -}) - -#ifndef this_cpu_add_return -# ifndef this_cpu_add_return_1 -# define this_cpu_add_return_1(pcp, val) _this_cpu_generic_add_return(pcp, val) -# endif -# ifndef this_cpu_add_return_2 -# define this_cpu_add_return_2(pcp, val) _this_cpu_generic_add_return(pcp, val) -# endif -# ifndef this_cpu_add_return_4 -# define this_cpu_add_return_4(pcp, val) _this_cpu_generic_add_return(pcp, val) -# endif -# ifndef this_cpu_add_return_8 -# define this_cpu_add_return_8(pcp, val) _this_cpu_generic_add_return(pcp, val) -# endif -# define this_cpu_add_return(pcp, val) __pcpu_size_call_return2(this_cpu_add_return_, pcp, val) -#endif - -#define this_cpu_sub_return(pcp, val) this_cpu_add_return(pcp, -(val)) -#define this_cpu_inc_return(pcp) this_cpu_add_return(pcp, 1) -#define this_cpu_dec_return(pcp) this_cpu_add_return(pcp, -1) - #define __this_cpu_generic_add_return(pcp, val) \ ({ \ __this_cpu_add(pcp, val); \ -- cgit v1.1 From b6aa5901c7a2bd90d0b6b9866300d2648b2568f3 Mon Sep 17 00:00:00 2001 From: Henry C Chang Date: Wed, 15 Dec 2010 20:45:41 -0800 Subject: ceph: mark user pages dirty on direct-io reads For read operation, we have to set the argument _write_ of get_user_pages to 1 since we will write data to pages. Also, we need to SetPageDirty before releasing these pages. Signed-off-by: Henry C Chang Signed-off-by: Sage Weil --- include/linux/ceph/libceph.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 9e76d35..72c72bf 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -227,8 +227,10 @@ extern int ceph_open_session(struct ceph_client *client); extern void ceph_release_page_vector(struct page **pages, int num_pages); extern struct page **ceph_get_direct_page_vector(const char __user *data, - int num_pages); -extern void ceph_put_page_vector(struct page **pages, int num_pages); + int num_pages, + bool write_page); +extern void ceph_put_page_vector(struct page **pages, int num_pages, + bool dirty); extern void ceph_release_page_vector(struct page **pages, int num_pages); extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags); extern int ceph_copy_user_to_page_vector(struct page **pages, -- cgit v1.1 From c0f5ac5426f7fd82b23dd5c6a1e633b290294a08 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 16 Dec 2010 10:38:41 -0700 Subject: Revert "resources: support allocating space within a region from the top down" This reverts commit e7f8567db9a7f6b3151b0b275e245c1cef0d9c70. Acked-by: H. Peter Anvin Signed-off-by: Bjorn Helgaas Signed-off-by: Jesse Barnes --- include/linux/ioport.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index d377ea8..b227902 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -112,7 +112,6 @@ struct resource_list { /* PC/ISA/whatever - the normal PC address spaces: IO and memory */ extern struct resource ioport_resource; extern struct resource iomem_resource; -extern int resource_alloc_from_bottom; extern struct resource *request_resource_conflict(struct resource *root, struct resource *new); extern int request_resource(struct resource *root, struct resource *new); -- cgit v1.1 From fcb119183c73bf0781009713f303e28b1fb13d3e Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 16 Dec 2010 10:38:46 -0700 Subject: resources: add arch hook for preventing allocation in reserved areas This adds arch_remove_reservations(), which an arch can implement if it needs to protect part of the address space from allocation. Sometimes that can be done by just putting a region in the resource tree, but there are cases where that doesn't work well. For example, x86 BIOS E820 reservations are not related to devices, so they may overlap part of, all of, or more than a device resource, so they may not end up at the correct spot in the resource tree. Acked-by: H. Peter Anvin Signed-off-by: Bjorn Helgaas Signed-off-by: Jesse Barnes --- include/linux/ioport.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index b227902..e9bb22c 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -123,6 +123,7 @@ extern void reserve_region_with_split(struct resource *root, extern struct resource *insert_resource_conflict(struct resource *parent, struct resource *new); extern int insert_resource(struct resource *parent, struct resource *new); extern void insert_resource_expand_to_fit(struct resource *root, struct resource *new); +extern void arch_remove_reservations(struct resource *avail); extern int allocate_resource(struct resource *root, struct resource *new, resource_size_t size, resource_size_t min, resource_size_t max, resource_size_t align, -- cgit v1.1 From 4b8fe66300acb2fba8b16d62606e0d30204022fc Mon Sep 17 00:00:00 2001 From: "Dmitry V. Levin" Date: Fri, 17 Dec 2010 12:03:14 -0800 Subject: netlink: fix gcc -Wconversion compilation warning $ cat << EOF | gcc -Wconversion -xc -S -o/dev/null - unsigned f(void) {return NLMSG_HDRLEN;} EOF : In function 'f': :3:26: warning: negative integer implicitly converted to unsigned type Signed-off-by: Dmitry V. Levin Signed-off-by: Kirill A. Shutemov Signed-off-by: David S. Miller --- include/linux/netlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 1235669..e2b9e63 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -70,7 +70,7 @@ struct nlmsghdr { Check NLM_F_EXCL */ -#define NLMSG_ALIGNTO 4 +#define NLMSG_ALIGNTO 4U #define NLMSG_ALIGN(len) ( ((len)+NLMSG_ALIGNTO-1) & ~(NLMSG_ALIGNTO-1) ) #define NLMSG_HDRLEN ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr))) #define NLMSG_LENGTH(len) ((len)+NLMSG_ALIGN(NLMSG_HDRLEN)) -- cgit v1.1 From e27fc9641e8ddc8146f8e01f06e5eba2469698de Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 22 Nov 2010 21:36:11 -0800 Subject: rcu: increase synchronize_sched_expedited() batching The fix in commit #6a0cc49 requires more than three concurrent instances of synchronize_sched_expedited() before batching is possible. This patch uses a ticket-counter-like approach that is also not unrelated to Lai Jiangshan's Ring RCU to allow sharing of expedited grace periods even when there are only two concurrent instances of synchronize_sched_expedited(). This commit builds on Tejun's original posting, which may be found at http://lkml.org/lkml/2010/11/9/204, adding memory barriers, avoiding overflow of signed integers (other than via atomic_t), and fixing the detection of batching. Signed-off-by: Tejun Heo Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 49e8e16..af56148 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -47,6 +47,8 @@ extern int rcutorture_runnable; /* for sysctl */ #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */ +#define UINT_CMP_GE(a, b) (UINT_MAX / 2 >= (a) - (b)) +#define UINT_CMP_LT(a, b) (UINT_MAX / 2 < (a) - (b)) #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) -- cgit v1.1 From 8a9c1cee26c0ece23b38c45b92b724438878f842 Mon Sep 17 00:00:00 2001 From: Mariusz Kozlowski Date: Wed, 15 Dec 2010 23:11:12 +0100 Subject: rculist: fix borked __list_for_each_rcu() macro This restores parentheses blance. Signed-off-by: Mariusz Kozlowski Signed-off-by: Paul E. McKenney --- include/linux/rculist.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index f31ef61..70d3ba5 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -244,7 +244,7 @@ static inline void list_splice_init_rcu(struct list_head *list, #define __list_for_each_rcu(pos, head) \ for (pos = rcu_dereference_raw(list_next_rcu(head)); \ pos != (head); \ - pos = rcu_dereference_raw(list_next_rcu((pos))) + pos = rcu_dereference_raw(list_next_rcu(pos))) /** * list_for_each_entry_rcu - iterate over rcu list of given type -- cgit v1.1 From 3c2dcf2aed5ea22ecf65a9a871c4963faec421b3 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 15 Dec 2010 21:12:15 -0800 Subject: rcu: remove unused __list_for_each_rcu() macro Signed-off-by: Paul E. McKenney --- include/linux/rculist.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 70d3ba5..2dea94f 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -241,11 +241,6 @@ static inline void list_splice_init_rcu(struct list_head *list, #define list_first_entry_rcu(ptr, type, member) \ list_entry_rcu((ptr)->next, type, member) -#define __list_for_each_rcu(pos, head) \ - for (pos = rcu_dereference_raw(list_next_rcu(head)); \ - pos != (head); \ - pos = rcu_dereference_raw(list_next_rcu(pos))) - /** * list_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. -- cgit v1.1 From 7c96aef75949a56ec427fc6a2522dace2af33605 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 15 Nov 2010 11:27:01 +1100 Subject: sunrpc: remove xpt_pool The xpt_pool field is only used for reporting BUGs. And it isn't used correctly. In particular, when it is cleared in svc_xprt_received before XPT_BUSY is cleared, there is no guarantee that either the compiler or the CPU might not re-order to two assignments, just setting xpt_pool to NULL after XPT_BUSY is cleared. If a different cpu were running svc_xprt_enqueue at this moment, it might see XPT_BUSY clear and then xpt_pool non-NULL, and so BUG. This could be fixed by calling smp_mb__before_clear_bit() before the clear_bit. However as xpt_pool isn't really used, it seems safest to simply remove xpt_pool. Another alternate would be to change the clear_bit to clear_bit_unlock, and the test_and_set_bit to test_and_set_bit_lock. Signed-off-by: NeilBrown Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_xprt.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index aea0d438..c8f81da 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -63,7 +63,6 @@ struct svc_xprt { #define XPT_LISTENER 11 /* listening endpoint */ #define XPT_CACHE_AUTH 12 /* cache auth info */ - struct svc_pool *xpt_pool; /* current pool iff queued */ struct svc_serv *xpt_server; /* service for transport */ atomic_t xpt_reserved; /* space on outq that is rsvd */ struct mutex xpt_mutex; /* to serialize sending data */ -- cgit v1.1 From 04f4ad16b231abbfde34c762697ad035a3af0b5f Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Thu, 16 Dec 2010 09:51:13 -0500 Subject: nfsd4: implement secinfo_no_name Implementation of this operation is mandatory for NFSv4.1. Signed-off-by: J. Bruce Fields --- include/linux/nfs4.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 4925b22..26afa30 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -136,6 +136,9 @@ #define SEQ4_STATUS_CB_PATH_DOWN_SESSION 0x00000200 #define SEQ4_STATUS_BACKCHANNEL_FAULT 0x00000400 +#define NFS4_SECINFO_STYLE4_CURRENT_FH 0 +#define NFS4_SECINFO_STYLE4_PARENT 1 + #define NFS4_MAX_UINT64 (~(u64)0) /* An NFS4 sessions server must support at least NFS4_MAX_OPS operations. -- cgit v1.1 From 2b7124428561c7c3cfa4a58cc4c6feea53f3148e Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Sat, 18 Dec 2010 15:54:04 +0100 Subject: percpu: Generic this_cpu_cmpxchg() and this_cpu_xchg support Generic code to provide new per cpu atomic features this_cpu_cmpxchg this_cpu_xchg Fallback occurs to functions using interrupts disable/enable to ensure correct per cpu atomicity. Fallback to regular cmpxchg and xchg is not possible since per cpu atomic semantics include the guarantee that the current cpus per cpu data is accessed atomically. Use of regular cmpxchg and xchg requires the determination of the address of the per cpu data before regular cmpxchg or xchg which therefore cannot be atomically included in an xchg or cmpxchg without segment override. tj: - Relocated new ops to conform better to the general organization. - This patch contains a trivial comment fix. Signed-off-by: Christoph Lameter Signed-off-by: Tejun Heo --- include/linux/percpu.h | 134 ++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 133 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 3484e88..27c3c6f 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -447,6 +447,59 @@ do { \ #define this_cpu_inc_return(pcp) this_cpu_add_return(pcp, 1) #define this_cpu_dec_return(pcp) this_cpu_add_return(pcp, -1) +#define _this_cpu_generic_xchg(pcp, nval) \ +({ typeof(pcp) ret__; \ + preempt_disable(); \ + ret__ = __this_cpu_read(pcp); \ + __this_cpu_write(pcp, nval); \ + preempt_enable(); \ + ret__; \ +}) + +#ifndef this_cpu_xchg +# ifndef this_cpu_xchg_1 +# define this_cpu_xchg_1(pcp, nval) _this_cpu_generic_xchg(pcp, nval) +# endif +# ifndef this_cpu_xchg_2 +# define this_cpu_xchg_2(pcp, nval) _this_cpu_generic_xchg(pcp, nval) +# endif +# ifndef this_cpu_xchg_4 +# define this_cpu_xchg_4(pcp, nval) _this_cpu_generic_xchg(pcp, nval) +# endif +# ifndef this_cpu_xchg_8 +# define this_cpu_xchg_8(pcp, nval) _this_cpu_generic_xchg(pcp, nval) +# endif +# define this_cpu_xchg(pcp, nval) \ + __pcpu_size_call_return2(this_cpu_xchg_, (pcp), nval) +#endif + +#define _this_cpu_generic_cmpxchg(pcp, oval, nval) \ +({ typeof(pcp) ret__; \ + preempt_disable(); \ + ret__ = __this_cpu_read(pcp); \ + if (ret__ == (oval)) \ + __this_cpu_write(pcp, nval); \ + preempt_enable(); \ + ret__; \ +}) + +#ifndef this_cpu_cmpxchg +# ifndef this_cpu_cmpxchg_1 +# define this_cpu_cmpxchg_1(pcp, oval, nval) _this_cpu_generic_cmpxchg(pcp, oval, nval) +# endif +# ifndef this_cpu_cmpxchg_2 +# define this_cpu_cmpxchg_2(pcp, oval, nval) _this_cpu_generic_cmpxchg(pcp, oval, nval) +# endif +# ifndef this_cpu_cmpxchg_4 +# define this_cpu_cmpxchg_4(pcp, oval, nval) _this_cpu_generic_cmpxchg(pcp, oval, nval) +# endif +# ifndef this_cpu_cmpxchg_8 +# define this_cpu_cmpxchg_8(pcp, oval, nval) _this_cpu_generic_cmpxchg(pcp, oval, nval) +# endif +# define this_cpu_cmpxchg(pcp, oval, nval) \ + __pcpu_size_call_return2(this_cpu_cmpxchg_, pcp, oval, nval) +#endif + /* * Generic percpu operations that do not require preemption handling. * Either we do not care about races or the caller has the @@ -600,11 +653,61 @@ do { \ #define __this_cpu_inc_return(pcp) this_cpu_add_return(pcp, 1) #define __this_cpu_dec_return(pcp) this_cpu_add_return(pcp, -1) +#define __this_cpu_generic_xchg(pcp, nval) \ +({ typeof(pcp) ret__; \ + ret__ = __this_cpu_read(pcp); \ + __this_cpu_write(pcp, nval); \ + ret__; \ +}) + +#ifndef __this_cpu_xchg +# ifndef __this_cpu_xchg_1 +# define __this_cpu_xchg_1(pcp, nval) __this_cpu_generic_xchg(pcp, nval) +# endif +# ifndef __this_cpu_xchg_2 +# define __this_cpu_xchg_2(pcp, nval) __this_cpu_generic_xchg(pcp, nval) +# endif +# ifndef __this_cpu_xchg_4 +# define __this_cpu_xchg_4(pcp, nval) __this_cpu_generic_xchg(pcp, nval) +# endif +# ifndef __this_cpu_xchg_8 +# define __this_cpu_xchg_8(pcp, nval) __this_cpu_generic_xchg(pcp, nval) +# endif +# define __this_cpu_xchg(pcp, nval) \ + __pcpu_size_call_return2(__this_cpu_xchg_, (pcp), nval) +#endif + +#define __this_cpu_generic_cmpxchg(pcp, oval, nval) \ +({ \ + typeof(pcp) ret__; \ + ret__ = __this_cpu_read(pcp); \ + if (ret__ == (oval)) \ + __this_cpu_write(pcp, nval); \ + ret__; \ +}) + +#ifndef __this_cpu_cmpxchg +# ifndef __this_cpu_cmpxchg_1 +# define __this_cpu_cmpxchg_1(pcp, oval, nval) __this_cpu_generic_cmpxchg(pcp, oval, nval) +# endif +# ifndef __this_cpu_cmpxchg_2 +# define __this_cpu_cmpxchg_2(pcp, oval, nval) __this_cpu_generic_cmpxchg(pcp, oval, nval) +# endif +# ifndef __this_cpu_cmpxchg_4 +# define __this_cpu_cmpxchg_4(pcp, oval, nval) __this_cpu_generic_cmpxchg(pcp, oval, nval) +# endif +# ifndef __this_cpu_cmpxchg_8 +# define __this_cpu_cmpxchg_8(pcp, oval, nval) __this_cpu_generic_cmpxchg(pcp, oval, nval) +# endif +# define __this_cpu_cmpxchg(pcp, oval, nval) \ + __pcpu_size_call_return2(__this_cpu_cmpxchg_, pcp, oval, nval) +#endif + /* * IRQ safe versions of the per cpu RMW operations. Note that these operations * are *not* safe against modification of the same variable from another * processors (which one gets when using regular atomic operations) - . They are guaranteed to be atomic vs. local interrupts and + * They are guaranteed to be atomic vs. local interrupts and * preemption only. */ #define irqsafe_cpu_generic_to_op(pcp, val, op) \ @@ -691,4 +794,33 @@ do { \ # define irqsafe_cpu_xor(pcp, val) __pcpu_size_call(irqsafe_cpu_xor_, (val)) #endif +#define irqsafe_cpu_generic_cmpxchg(pcp, oval, nval) \ +({ \ + typeof(pcp) ret__; \ + unsigned long flags; \ + local_irq_save(flags); \ + ret__ = __this_cpu_read(pcp); \ + if (ret__ == (oval)) \ + __this_cpu_write(pcp, nval); \ + local_irq_restore(flags); \ + ret__; \ +}) + +#ifndef irqsafe_cpu_cmpxchg +# ifndef irqsafe_cpu_cmpxchg_1 +# define irqsafe_cpu_cmpxchg_1(pcp, oval, nval) irqsafe_cpu_generic_cmpxchg(pcp, oval, nval) +# endif +# ifndef irqsafe_cpu_cmpxchg_2 +# define irqsafe_cpu_cmpxchg_2(pcp, oval, nval) irqsafe_cpu_generic_cmpxchg(pcp, oval, nval) +# endif +# ifndef irqsafe_cpu_cmpxchg_4 +# define irqsafe_cpu_cmpxchg_4(pcp, oval, nval) irqsafe_cpu_generic_cmpxchg(pcp, oval, nval) +# endif +# ifndef irqsafe_cpu_cmpxchg_8 +# define irqsafe_cpu_cmpxchg_8(pcp, oval, nval) irqsafe_cpu_generic_cmpxchg(pcp, oval, nval) +# endif +# define irqsafe_cpu_cmpxchg(pcp, oval, nval) \ + __pcpu_size_call_return2(irqsafe_cpu_cmpxchg_, (pcp), oval, nval) +#endif + #endif /* __LINUX_PERCPU_H */ -- cgit v1.1 From c6eda6c5eeb357ff231121619fb49d2bc0605faf Mon Sep 17 00:00:00 2001 From: Sundar Iyer Date: Mon, 13 Dec 2010 09:33:12 +0530 Subject: mfd/tc35892: rename tc35892 header to tc3589x Rename the header file to include further variants within the same mfd core driver Acked-by: Samuel Ortiz Signed-off-by: Sundar Iyer Signed-off-by: Linus Walleij --- include/linux/mfd/tc35892.h | 136 -------------------------------------------- include/linux/mfd/tc3589x.h | 136 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 136 insertions(+), 136 deletions(-) delete mode 100644 include/linux/mfd/tc35892.h create mode 100644 include/linux/mfd/tc3589x.h (limited to 'include') diff --git a/include/linux/mfd/tc35892.h b/include/linux/mfd/tc35892.h deleted file mode 100644 index eff3094..0000000 --- a/include/linux/mfd/tc35892.h +++ /dev/null @@ -1,136 +0,0 @@ -/* - * Copyright (C) ST-Ericsson SA 2010 - * - * License Terms: GNU General Public License, version 2 - */ - -#ifndef __LINUX_MFD_TC35892_H -#define __LINUX_MFD_TC35892_H - -#include - -#define TC35892_RSTCTRL_IRQRST (1 << 4) -#define TC35892_RSTCTRL_TIMRST (1 << 3) -#define TC35892_RSTCTRL_ROTRST (1 << 2) -#define TC35892_RSTCTRL_KBDRST (1 << 1) -#define TC35892_RSTCTRL_GPIRST (1 << 0) - -#define TC35892_IRQST 0x91 - -#define TC35892_MANFCODE_MAGIC 0x03 -#define TC35892_MANFCODE 0x80 -#define TC35892_VERSION 0x81 -#define TC35892_IOCFG 0xA7 - -#define TC35892_CLKMODE 0x88 -#define TC35892_CLKCFG 0x89 -#define TC35892_CLKEN 0x8A - -#define TC35892_RSTCTRL 0x82 -#define TC35892_EXTRSTN 0x83 -#define TC35892_RSTINTCLR 0x84 - -#define TC35892_GPIOIS0 0xC9 -#define TC35892_GPIOIS1 0xCA -#define TC35892_GPIOIS2 0xCB -#define TC35892_GPIOIBE0 0xCC -#define TC35892_GPIOIBE1 0xCD -#define TC35892_GPIOIBE2 0xCE -#define TC35892_GPIOIEV0 0xCF -#define TC35892_GPIOIEV1 0xD0 -#define TC35892_GPIOIEV2 0xD1 -#define TC35892_GPIOIE0 0xD2 -#define TC35892_GPIOIE1 0xD3 -#define TC35892_GPIOIE2 0xD4 -#define TC35892_GPIORIS0 0xD6 -#define TC35892_GPIORIS1 0xD7 -#define TC35892_GPIORIS2 0xD8 -#define TC35892_GPIOMIS0 0xD9 -#define TC35892_GPIOMIS1 0xDA -#define TC35892_GPIOMIS2 0xDB -#define TC35892_GPIOIC0 0xDC -#define TC35892_GPIOIC1 0xDD -#define TC35892_GPIOIC2 0xDE - -#define TC35892_GPIODATA0 0xC0 -#define TC35892_GPIOMASK0 0xc1 -#define TC35892_GPIODATA1 0xC2 -#define TC35892_GPIOMASK1 0xc3 -#define TC35892_GPIODATA2 0xC4 -#define TC35892_GPIOMASK2 0xC5 - -#define TC35892_GPIODIR0 0xC6 -#define TC35892_GPIODIR1 0xC7 -#define TC35892_GPIODIR2 0xC8 - -#define TC35892_GPIOSYNC0 0xE6 -#define TC35892_GPIOSYNC1 0xE7 -#define TC35892_GPIOSYNC2 0xE8 - -#define TC35892_GPIOWAKE0 0xE9 -#define TC35892_GPIOWAKE1 0xEA -#define TC35892_GPIOWAKE2 0xEB - -#define TC35892_GPIOODM0 0xE0 -#define TC35892_GPIOODE0 0xE1 -#define TC35892_GPIOODM1 0xE2 -#define TC35892_GPIOODE1 0xE3 -#define TC35892_GPIOODM2 0xE4 -#define TC35892_GPIOODE2 0xE5 - -#define TC35892_INT_GPIIRQ 0 -#define TC35892_INT_TI0IRQ 1 -#define TC35892_INT_TI1IRQ 2 -#define TC35892_INT_TI2IRQ 3 -#define TC35892_INT_ROTIRQ 5 -#define TC35892_INT_KBDIRQ 6 -#define TC35892_INT_PORIRQ 7 - -#define TC35892_NR_INTERNAL_IRQS 8 -#define TC35892_INT_GPIO(x) (TC35892_NR_INTERNAL_IRQS + (x)) - -struct tc35892 { - struct mutex lock; - struct device *dev; - struct i2c_client *i2c; - - int irq_base; - int num_gpio; - struct tc35892_platform_data *pdata; -}; - -extern int tc35892_reg_write(struct tc35892 *tc35892, u8 reg, u8 data); -extern int tc35892_reg_read(struct tc35892 *tc35892, u8 reg); -extern int tc35892_block_read(struct tc35892 *tc35892, u8 reg, u8 length, - u8 *values); -extern int tc35892_block_write(struct tc35892 *tc35892, u8 reg, u8 length, - const u8 *values); -extern int tc35892_set_bits(struct tc35892 *tc35892, u8 reg, u8 mask, u8 val); - -/** - * struct tc35892_gpio_platform_data - TC35892 GPIO platform data - * @gpio_base: first gpio number assigned to TC35892. A maximum of - * %TC35892_NR_GPIOS GPIOs will be allocated. - * @setup: callback for board-specific initialization - * @remove: callback for board-specific teardown - */ -struct tc35892_gpio_platform_data { - int gpio_base; - void (*setup)(struct tc35892 *tc35892, unsigned gpio_base); - void (*remove)(struct tc35892 *tc35892, unsigned gpio_base); -}; - -/** - * struct tc35892_platform_data - TC35892 platform data - * @irq_base: base IRQ number. %TC35892_NR_IRQS irqs will be used. - * @gpio: GPIO-specific platform data - */ -struct tc35892_platform_data { - int irq_base; - struct tc35892_gpio_platform_data *gpio; -}; - -#define TC35892_NR_GPIOS 24 -#define TC35892_NR_IRQS TC35892_INT_GPIO(TC35892_NR_GPIOS) - -#endif diff --git a/include/linux/mfd/tc3589x.h b/include/linux/mfd/tc3589x.h new file mode 100644 index 0000000..eff3094 --- /dev/null +++ b/include/linux/mfd/tc3589x.h @@ -0,0 +1,136 @@ +/* + * Copyright (C) ST-Ericsson SA 2010 + * + * License Terms: GNU General Public License, version 2 + */ + +#ifndef __LINUX_MFD_TC35892_H +#define __LINUX_MFD_TC35892_H + +#include + +#define TC35892_RSTCTRL_IRQRST (1 << 4) +#define TC35892_RSTCTRL_TIMRST (1 << 3) +#define TC35892_RSTCTRL_ROTRST (1 << 2) +#define TC35892_RSTCTRL_KBDRST (1 << 1) +#define TC35892_RSTCTRL_GPIRST (1 << 0) + +#define TC35892_IRQST 0x91 + +#define TC35892_MANFCODE_MAGIC 0x03 +#define TC35892_MANFCODE 0x80 +#define TC35892_VERSION 0x81 +#define TC35892_IOCFG 0xA7 + +#define TC35892_CLKMODE 0x88 +#define TC35892_CLKCFG 0x89 +#define TC35892_CLKEN 0x8A + +#define TC35892_RSTCTRL 0x82 +#define TC35892_EXTRSTN 0x83 +#define TC35892_RSTINTCLR 0x84 + +#define TC35892_GPIOIS0 0xC9 +#define TC35892_GPIOIS1 0xCA +#define TC35892_GPIOIS2 0xCB +#define TC35892_GPIOIBE0 0xCC +#define TC35892_GPIOIBE1 0xCD +#define TC35892_GPIOIBE2 0xCE +#define TC35892_GPIOIEV0 0xCF +#define TC35892_GPIOIEV1 0xD0 +#define TC35892_GPIOIEV2 0xD1 +#define TC35892_GPIOIE0 0xD2 +#define TC35892_GPIOIE1 0xD3 +#define TC35892_GPIOIE2 0xD4 +#define TC35892_GPIORIS0 0xD6 +#define TC35892_GPIORIS1 0xD7 +#define TC35892_GPIORIS2 0xD8 +#define TC35892_GPIOMIS0 0xD9 +#define TC35892_GPIOMIS1 0xDA +#define TC35892_GPIOMIS2 0xDB +#define TC35892_GPIOIC0 0xDC +#define TC35892_GPIOIC1 0xDD +#define TC35892_GPIOIC2 0xDE + +#define TC35892_GPIODATA0 0xC0 +#define TC35892_GPIOMASK0 0xc1 +#define TC35892_GPIODATA1 0xC2 +#define TC35892_GPIOMASK1 0xc3 +#define TC35892_GPIODATA2 0xC4 +#define TC35892_GPIOMASK2 0xC5 + +#define TC35892_GPIODIR0 0xC6 +#define TC35892_GPIODIR1 0xC7 +#define TC35892_GPIODIR2 0xC8 + +#define TC35892_GPIOSYNC0 0xE6 +#define TC35892_GPIOSYNC1 0xE7 +#define TC35892_GPIOSYNC2 0xE8 + +#define TC35892_GPIOWAKE0 0xE9 +#define TC35892_GPIOWAKE1 0xEA +#define TC35892_GPIOWAKE2 0xEB + +#define TC35892_GPIOODM0 0xE0 +#define TC35892_GPIOODE0 0xE1 +#define TC35892_GPIOODM1 0xE2 +#define TC35892_GPIOODE1 0xE3 +#define TC35892_GPIOODM2 0xE4 +#define TC35892_GPIOODE2 0xE5 + +#define TC35892_INT_GPIIRQ 0 +#define TC35892_INT_TI0IRQ 1 +#define TC35892_INT_TI1IRQ 2 +#define TC35892_INT_TI2IRQ 3 +#define TC35892_INT_ROTIRQ 5 +#define TC35892_INT_KBDIRQ 6 +#define TC35892_INT_PORIRQ 7 + +#define TC35892_NR_INTERNAL_IRQS 8 +#define TC35892_INT_GPIO(x) (TC35892_NR_INTERNAL_IRQS + (x)) + +struct tc35892 { + struct mutex lock; + struct device *dev; + struct i2c_client *i2c; + + int irq_base; + int num_gpio; + struct tc35892_platform_data *pdata; +}; + +extern int tc35892_reg_write(struct tc35892 *tc35892, u8 reg, u8 data); +extern int tc35892_reg_read(struct tc35892 *tc35892, u8 reg); +extern int tc35892_block_read(struct tc35892 *tc35892, u8 reg, u8 length, + u8 *values); +extern int tc35892_block_write(struct tc35892 *tc35892, u8 reg, u8 length, + const u8 *values); +extern int tc35892_set_bits(struct tc35892 *tc35892, u8 reg, u8 mask, u8 val); + +/** + * struct tc35892_gpio_platform_data - TC35892 GPIO platform data + * @gpio_base: first gpio number assigned to TC35892. A maximum of + * %TC35892_NR_GPIOS GPIOs will be allocated. + * @setup: callback for board-specific initialization + * @remove: callback for board-specific teardown + */ +struct tc35892_gpio_platform_data { + int gpio_base; + void (*setup)(struct tc35892 *tc35892, unsigned gpio_base); + void (*remove)(struct tc35892 *tc35892, unsigned gpio_base); +}; + +/** + * struct tc35892_platform_data - TC35892 platform data + * @irq_base: base IRQ number. %TC35892_NR_IRQS irqs will be used. + * @gpio: GPIO-specific platform data + */ +struct tc35892_platform_data { + int irq_base; + struct tc35892_gpio_platform_data *gpio; +}; + +#define TC35892_NR_GPIOS 24 +#define TC35892_NR_IRQS TC35892_INT_GPIO(TC35892_NR_GPIOS) + +#endif -- cgit v1.1 From 20406ebff4a298e6e3abbc1717a90bb3e55dc820 Mon Sep 17 00:00:00 2001 From: Sundar Iyer Date: Mon, 13 Dec 2010 09:33:14 +0530 Subject: mfd/tc3589x: rename tc35892 structs/registers to tc359x Most of the register layout, client IRQ numbers on the TC35892 is shared also by other variants. Make this generic as tc3589x Acked-by: Samuel Ortiz Signed-off-by: Sundar Iyer Signed-off-by: Linus Walleij --- include/linux/mfd/tc3589x.h | 202 ++++++++++++++++++++++---------------------- 1 file changed, 101 insertions(+), 101 deletions(-) (limited to 'include') diff --git a/include/linux/mfd/tc3589x.h b/include/linux/mfd/tc3589x.h index eff3094..ea19188 100644 --- a/include/linux/mfd/tc3589x.h +++ b/include/linux/mfd/tc3589x.h @@ -4,133 +4,133 @@ * License Terms: GNU General Public License, version 2 */ -#ifndef __LINUX_MFD_TC35892_H -#define __LINUX_MFD_TC35892_H +#ifndef __LINUX_MFD_TC3589x_H +#define __LINUX_MFD_TC3589x_H #include -#define TC35892_RSTCTRL_IRQRST (1 << 4) -#define TC35892_RSTCTRL_TIMRST (1 << 3) -#define TC35892_RSTCTRL_ROTRST (1 << 2) -#define TC35892_RSTCTRL_KBDRST (1 << 1) -#define TC35892_RSTCTRL_GPIRST (1 << 0) - -#define TC35892_IRQST 0x91 - -#define TC35892_MANFCODE_MAGIC 0x03 -#define TC35892_MANFCODE 0x80 -#define TC35892_VERSION 0x81 -#define TC35892_IOCFG 0xA7 - -#define TC35892_CLKMODE 0x88 -#define TC35892_CLKCFG 0x89 -#define TC35892_CLKEN 0x8A - -#define TC35892_RSTCTRL 0x82 -#define TC35892_EXTRSTN 0x83 -#define TC35892_RSTINTCLR 0x84 - -#define TC35892_GPIOIS0 0xC9 -#define TC35892_GPIOIS1 0xCA -#define TC35892_GPIOIS2 0xCB -#define TC35892_GPIOIBE0 0xCC -#define TC35892_GPIOIBE1 0xCD -#define TC35892_GPIOIBE2 0xCE -#define TC35892_GPIOIEV0 0xCF -#define TC35892_GPIOIEV1 0xD0 -#define TC35892_GPIOIEV2 0xD1 -#define TC35892_GPIOIE0 0xD2 -#define TC35892_GPIOIE1 0xD3 -#define TC35892_GPIOIE2 0xD4 -#define TC35892_GPIORIS0 0xD6 -#define TC35892_GPIORIS1 0xD7 -#define TC35892_GPIORIS2 0xD8 -#define TC35892_GPIOMIS0 0xD9 -#define TC35892_GPIOMIS1 0xDA -#define TC35892_GPIOMIS2 0xDB -#define TC35892_GPIOIC0 0xDC -#define TC35892_GPIOIC1 0xDD -#define TC35892_GPIOIC2 0xDE - -#define TC35892_GPIODATA0 0xC0 -#define TC35892_GPIOMASK0 0xc1 -#define TC35892_GPIODATA1 0xC2 -#define TC35892_GPIOMASK1 0xc3 -#define TC35892_GPIODATA2 0xC4 -#define TC35892_GPIOMASK2 0xC5 - -#define TC35892_GPIODIR0 0xC6 -#define TC35892_GPIODIR1 0xC7 -#define TC35892_GPIODIR2 0xC8 - -#define TC35892_GPIOSYNC0 0xE6 -#define TC35892_GPIOSYNC1 0xE7 -#define TC35892_GPIOSYNC2 0xE8 - -#define TC35892_GPIOWAKE0 0xE9 -#define TC35892_GPIOWAKE1 0xEA -#define TC35892_GPIOWAKE2 0xEB - -#define TC35892_GPIOODM0 0xE0 -#define TC35892_GPIOODE0 0xE1 -#define TC35892_GPIOODM1 0xE2 -#define TC35892_GPIOODE1 0xE3 -#define TC35892_GPIOODM2 0xE4 -#define TC35892_GPIOODE2 0xE5 - -#define TC35892_INT_GPIIRQ 0 -#define TC35892_INT_TI0IRQ 1 -#define TC35892_INT_TI1IRQ 2 -#define TC35892_INT_TI2IRQ 3 -#define TC35892_INT_ROTIRQ 5 -#define TC35892_INT_KBDIRQ 6 -#define TC35892_INT_PORIRQ 7 - -#define TC35892_NR_INTERNAL_IRQS 8 -#define TC35892_INT_GPIO(x) (TC35892_NR_INTERNAL_IRQS + (x)) - -struct tc35892 { +#define TC3589x_RSTCTRL_IRQRST (1 << 4) +#define TC3589x_RSTCTRL_TIMRST (1 << 3) +#define TC3589x_RSTCTRL_ROTRST (1 << 2) +#define TC3589x_RSTCTRL_KBDRST (1 << 1) +#define TC3589x_RSTCTRL_GPIRST (1 << 0) + +#define TC3589x_IRQST 0x91 + +#define TC3589x_MANFCODE_MAGIC 0x03 +#define TC3589x_MANFCODE 0x80 +#define TC3589x_VERSION 0x81 +#define TC3589x_IOCFG 0xA7 + +#define TC3589x_CLKMODE 0x88 +#define TC3589x_CLKCFG 0x89 +#define TC3589x_CLKEN 0x8A + +#define TC3589x_RSTCTRL 0x82 +#define TC3589x_EXTRSTN 0x83 +#define TC3589x_RSTINTCLR 0x84 + +#define TC3589x_GPIOIS0 0xC9 +#define TC3589x_GPIOIS1 0xCA +#define TC3589x_GPIOIS2 0xCB +#define TC3589x_GPIOIBE0 0xCC +#define TC3589x_GPIOIBE1 0xCD +#define TC3589x_GPIOIBE2 0xCE +#define TC3589x_GPIOIEV0 0xCF +#define TC3589x_GPIOIEV1 0xD0 +#define TC3589x_GPIOIEV2 0xD1 +#define TC3589x_GPIOIE0 0xD2 +#define TC3589x_GPIOIE1 0xD3 +#define TC3589x_GPIOIE2 0xD4 +#define TC3589x_GPIORIS0 0xD6 +#define TC3589x_GPIORIS1 0xD7 +#define TC3589x_GPIORIS2 0xD8 +#define TC3589x_GPIOMIS0 0xD9 +#define TC3589x_GPIOMIS1 0xDA +#define TC3589x_GPIOMIS2 0xDB +#define TC3589x_GPIOIC0 0xDC +#define TC3589x_GPIOIC1 0xDD +#define TC3589x_GPIOIC2 0xDE + +#define TC3589x_GPIODATA0 0xC0 +#define TC3589x_GPIOMASK0 0xc1 +#define TC3589x_GPIODATA1 0xC2 +#define TC3589x_GPIOMASK1 0xc3 +#define TC3589x_GPIODATA2 0xC4 +#define TC3589x_GPIOMASK2 0xC5 + +#define TC3589x_GPIODIR0 0xC6 +#define TC3589x_GPIODIR1 0xC7 +#define TC3589x_GPIODIR2 0xC8 + +#define TC3589x_GPIOSYNC0 0xE6 +#define TC3589x_GPIOSYNC1 0xE7 +#define TC3589x_GPIOSYNC2 0xE8 + +#define TC3589x_GPIOWAKE0 0xE9 +#define TC3589x_GPIOWAKE1 0xEA +#define TC3589x_GPIOWAKE2 0xEB + +#define TC3589x_GPIOODM0 0xE0 +#define TC3589x_GPIOODE0 0xE1 +#define TC3589x_GPIOODM1 0xE2 +#define TC3589x_GPIOODE1 0xE3 +#define TC3589x_GPIOODM2 0xE4 +#define TC3589x_GPIOODE2 0xE5 + +#define TC3589x_INT_GPIIRQ 0 +#define TC3589x_INT_TI0IRQ 1 +#define TC3589x_INT_TI1IRQ 2 +#define TC3589x_INT_TI2IRQ 3 +#define TC3589x_INT_ROTIRQ 5 +#define TC3589x_INT_KBDIRQ 6 +#define TC3589x_INT_PORIRQ 7 + +#define TC3589x_NR_INTERNAL_IRQS 8 +#define TC3589x_INT_GPIO(x) (TC3589x_NR_INTERNAL_IRQS + (x)) + +struct tc3589x { struct mutex lock; struct device *dev; struct i2c_client *i2c; int irq_base; int num_gpio; - struct tc35892_platform_data *pdata; + struct tc3589x_platform_data *pdata; }; -extern int tc35892_reg_write(struct tc35892 *tc35892, u8 reg, u8 data); -extern int tc35892_reg_read(struct tc35892 *tc35892, u8 reg); -extern int tc35892_block_read(struct tc35892 *tc35892, u8 reg, u8 length, +extern int tc3589x_reg_write(struct tc3589x *tc3589x, u8 reg, u8 data); +extern int tc3589x_reg_read(struct tc3589x *tc3589x, u8 reg); +extern int tc3589x_block_read(struct tc3589x *tc3589x, u8 reg, u8 length, u8 *values); -extern int tc35892_block_write(struct tc35892 *tc35892, u8 reg, u8 length, +extern int tc3589x_block_write(struct tc3589x *tc3589x, u8 reg, u8 length, const u8 *values); -extern int tc35892_set_bits(struct tc35892 *tc35892, u8 reg, u8 mask, u8 val); +extern int tc3589x_set_bits(struct tc3589x *tc3589x, u8 reg, u8 mask, u8 val); /** - * struct tc35892_gpio_platform_data - TC35892 GPIO platform data - * @gpio_base: first gpio number assigned to TC35892. A maximum of - * %TC35892_NR_GPIOS GPIOs will be allocated. + * struct tc3589x_gpio_platform_data - TC3589x GPIO platform data + * @gpio_base: first gpio number assigned to TC3589x. A maximum of + * %TC3589x_NR_GPIOS GPIOs will be allocated. * @setup: callback for board-specific initialization * @remove: callback for board-specific teardown */ -struct tc35892_gpio_platform_data { +struct tc3589x_gpio_platform_data { int gpio_base; - void (*setup)(struct tc35892 *tc35892, unsigned gpio_base); - void (*remove)(struct tc35892 *tc35892, unsigned gpio_base); + void (*setup)(struct tc3589x *tc3589x, unsigned gpio_base); + void (*remove)(struct tc3589x *tc3589x, unsigned gpio_base); }; /** - * struct tc35892_platform_data - TC35892 platform data - * @irq_base: base IRQ number. %TC35892_NR_IRQS irqs will be used. + * struct tc3589x_platform_data - TC3589x platform data + * @irq_base: base IRQ number. %TC3589x_NR_IRQS irqs will be used. * @gpio: GPIO-specific platform data */ -struct tc35892_platform_data { +struct tc3589x_platform_data { int irq_base; - struct tc35892_gpio_platform_data *gpio; + struct tc3589x_gpio_platform_data *gpio; }; -#define TC35892_NR_GPIOS 24 -#define TC35892_NR_IRQS TC35892_INT_GPIO(TC35892_NR_GPIOS) +#define TC3589x_NR_GPIOS 24 +#define TC3589x_NR_IRQS TC3589x_INT_GPIO(TC3589x_NR_GPIOS) #endif -- cgit v1.1 From 611b7590afa6e6c6b0942b1d3efef17fbb348ef5 Mon Sep 17 00:00:00 2001 From: Sundar Iyer Date: Mon, 13 Dec 2010 09:33:15 +0530 Subject: mfd/tc3589x: add block identifier for multiple child devices Add block identifier to be able to add multiple mfd clients to the mfd core Acked-by: Samuel Ortiz Signed-off-by: Sundar Iyer Signed-off-by: Linus Walleij --- include/linux/mfd/tc3589x.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/tc3589x.h b/include/linux/mfd/tc3589x.h index ea19188..da00958 100644 --- a/include/linux/mfd/tc3589x.h +++ b/include/linux/mfd/tc3589x.h @@ -9,6 +9,11 @@ #include +enum tx3589x_block { + TC3589x_BLOCK_GPIO = 1 << 0, + TC3589x_BLOCK_KEYPAD = 1 << 1, +}; + #define TC3589x_RSTCTRL_IRQRST (1 << 4) #define TC3589x_RSTCTRL_TIMRST (1 << 3) #define TC3589x_RSTCTRL_ROTRST (1 << 2) @@ -122,10 +127,12 @@ struct tc3589x_gpio_platform_data { /** * struct tc3589x_platform_data - TC3589x platform data + * @block: bitmask of blocks to enable (use TC3589x_BLOCK_*) * @irq_base: base IRQ number. %TC3589x_NR_IRQS irqs will be used. * @gpio: GPIO-specific platform data */ struct tc3589x_platform_data { + unsigned int block; int irq_base; struct tc3589x_gpio_platform_data *gpio; }; -- cgit v1.1 From ad0081e43af6de3fecf308b0d098f9611835766b Mon Sep 17 00:00:00 2001 From: David Stevens Date: Fri, 17 Dec 2010 11:42:42 +0000 Subject: ipv6: Fragment locally generated tunnel-mode IPSec6 packets as needed. This patch modifies IPsec6 to fragment IPv6 packets that are locally generated as needed. This version of the patch only fragments in tunnel mode, so that fragment headers will not be obscured by ESP in transport mode. Signed-off-by: David L Stevens Acked-by: Herbert Xu Signed-off-by: David S. Miller --- include/net/ip6_route.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 278312c..2ab9268 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -164,5 +164,15 @@ static inline int ipv6_unicast_destination(struct sk_buff *skb) return rt->rt6i_flags & RTF_LOCAL; } +int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)); + +static inline int ip6_skb_dst_mtu(struct sk_buff *skb) +{ + struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL; + + return (np && np->pmtudisc == IPV6_PMTUDISC_PROBE) ? + skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb)); +} + #endif #endif -- cgit v1.1 From 4c306a9291a077879fc3e933326caac3bc319caa Mon Sep 17 00:00:00 2001 From: Shan Wei Date: Sun, 19 Dec 2010 21:59:35 -0800 Subject: net: kill unused macros These macros never be used, so remove them. Signed-off-by: Shan Wei Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 1 - include/net/tcp.h | 2 -- 2 files changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 6c93a56..6ac4e3b 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -132,7 +132,6 @@ struct inet_connection_sock { #define ICSK_TIME_RETRANS 1 /* Retransmit timer */ #define ICSK_TIME_DACK 2 /* Delayed ack timer */ #define ICSK_TIME_PROBE0 3 /* Zero window probe timer */ -#define ICSK_TIME_KEEPOPEN 4 /* Keepalive timer */ static inline struct inet_connection_sock *inet_csk(const struct sock *sk) { diff --git a/include/net/tcp.h b/include/net/tcp.h index 2ab6c9c..b448030 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1158,8 +1158,6 @@ struct tcp_md5sig_pool { union tcp_md5sum_block md5_blk; }; -#define TCP_MD5SIG_MAXKEYS (~(u32)0) /* really?! */ - /* - functions */ extern int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, struct sock *sk, struct request_sock *req, -- cgit v1.1 From 85b7720039fc000b561c20fe2aaa3b54cddae4a7 Mon Sep 17 00:00:00 2001 From: Henrik Rydberg Date: Sat, 18 Dec 2010 20:51:13 +0100 Subject: Input: introduce device properties Today, userspace sets up an input device based on the data it emits. This is not always enough; a tablet and a touchscreen may emit exactly the same data, for instance, but the former should be set up with a pointer whereas the latter does not need to. Recently, a new type of touchpad has emerged where the buttons are under the pad, which changes logic without changing the emitted data. This patch introduces a new ioctl, EVIOCGPROP, which enables user access to a set of device properties useful during setup. The properties are given as a bitmap in the same fashion as the event types, and are also made available via sysfs, uevent and /proc/bus/input/devices. Acked-by: Ping Cheng Acked-by: Chase Douglas Acked-by: Dmitry Torokhov Signed-off-by: Henrik Rydberg --- include/linux/input.h | 16 ++++++++++++++++ include/linux/uinput.h | 1 + 2 files changed, 17 insertions(+) (limited to 'include') diff --git a/include/linux/input.h b/include/linux/input.h index b3a1e02..8d9c76c 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -91,6 +91,7 @@ struct input_keymap_entry { #define EVIOCGNAME(len) _IOC(_IOC_READ, 'E', 0x06, len) /* get device name */ #define EVIOCGPHYS(len) _IOC(_IOC_READ, 'E', 0x07, len) /* get physical location */ #define EVIOCGUNIQ(len) _IOC(_IOC_READ, 'E', 0x08, len) /* get unique identifier */ +#define EVIOCGPROP(len) _IOC(_IOC_READ, 'E', 0x09, len) /* get device properties */ #define EVIOCGKEY(len) _IOC(_IOC_READ, 'E', 0x18, len) /* get global key state */ #define EVIOCGLED(len) _IOC(_IOC_READ, 'E', 0x19, len) /* get all LEDs */ @@ -108,6 +109,18 @@ struct input_keymap_entry { #define EVIOCGRAB _IOW('E', 0x90, int) /* Grab/Release device */ /* + * Device properties and quirks + */ + +#define INPUT_PROP_POINTER 0x00 /* needs a pointer */ +#define INPUT_PROP_DIRECT 0x01 /* direct input devices */ +#define INPUT_PROP_BUTTONPAD 0x02 /* has button(s) under pad */ +#define INPUT_PROP_SEMI_MT 0x03 /* touch rectangle only */ + +#define INPUT_PROP_MAX 0x1f +#define INPUT_PROP_CNT (INPUT_PROP_MAX + 1) + +/* * Event types */ @@ -1090,6 +1103,7 @@ struct ff_effect { * @phys: physical path to the device in the system hierarchy * @uniq: unique identification code for the device (if device has it) * @id: id of the device (struct input_id) + * @propbit: bitmap of device properties and quirks * @evbit: bitmap of types of events supported by the device (EV_KEY, * EV_REL, etc.) * @keybit: bitmap of keys/buttons this device has @@ -1173,6 +1187,8 @@ struct input_dev { const char *uniq; struct input_id id; + unsigned long propbit[BITS_TO_LONGS(INPUT_PROP_CNT)]; + unsigned long evbit[BITS_TO_LONGS(EV_CNT)]; unsigned long keybit[BITS_TO_LONGS(KEY_CNT)]; unsigned long relbit[BITS_TO_LONGS(REL_CNT)]; diff --git a/include/linux/uinput.h b/include/linux/uinput.h index 05f7fed2..d28c726 100644 --- a/include/linux/uinput.h +++ b/include/linux/uinput.h @@ -104,6 +104,7 @@ struct uinput_ff_erase { #define UI_SET_FFBIT _IOW(UINPUT_IOCTL_BASE, 107, int) #define UI_SET_PHYS _IOW(UINPUT_IOCTL_BASE, 108, char*) #define UI_SET_SWBIT _IOW(UINPUT_IOCTL_BASE, 109, int) +#define UI_SET_PROPBIT _IOW(UINPUT_IOCTL_BASE, 110, int) #define UI_BEGIN_FF_UPLOAD _IOWR(UINPUT_IOCTL_BASE, 200, struct uinput_ff_upload) #define UI_END_FF_UPLOAD _IOW(UINPUT_IOCTL_BASE, 201, struct uinput_ff_upload) -- cgit v1.1 From 72bfa19c8deb4d1db5ad068c34fd580cb295cbe8 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Sun, 19 Dec 2010 11:42:05 +0000 Subject: drm/i915: Allow the application to choose the constant addressing mode The relative-to-general state default is useless as it means having to rewrite the streaming kernels for each batch. Relative-to-surface is more useful, as that stream usually needs to be rewritten for each batch. And absolute addressing mode, vital if you start streaming state, is also only available by adjusting the register... Signed-off-by: Chris Wilson --- include/drm/i915_drm.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h index a2776e2..0039f1f 100644 --- a/include/drm/i915_drm.h +++ b/include/drm/i915_drm.h @@ -289,6 +289,7 @@ typedef struct drm_i915_irq_wait { #define I915_PARAM_HAS_BLT 11 #define I915_PARAM_HAS_RELAXED_FENCING 12 #define I915_PARAM_HAS_COHERENT_RINGS 13 +#define I915_PARAM_HAS_EXEC_CONSTANTS 14 typedef struct drm_i915_getparam { int param; @@ -635,6 +636,17 @@ struct drm_i915_gem_execbuffer2 { #define I915_EXEC_RENDER (1<<0) #define I915_EXEC_BSD (2<<0) #define I915_EXEC_BLT (3<<0) + +/* Used for switching the constants addressing mode on gen4+ RENDER ring. + * Gen6+ only supports relative addressing to dynamic state (default) and + * absolute addressing. + * + * These flags are ignored for the BSD and BLT rings. + */ +#define I915_EXEC_CONSTANTS_MASK (3<<6) +#define I915_EXEC_CONSTANTS_REL_GENERAL (0<<6) /* default */ +#define I915_EXEC_CONSTANTS_ABSOLUTE (1<<6) +#define I915_EXEC_CONSTANTS_REL_SURFACE (2<<6) /* gen4/5 only */ __u64 flags; __u64 rsvd1; __u64 rsvd2; -- cgit v1.1 From 521bc83b0fcda6f323f1de0e7bf137401a8145a2 Mon Sep 17 00:00:00 2001 From: Andres Salomon Date: Fri, 17 Dec 2010 19:00:13 -0800 Subject: s1d13xxxfb: drop unused code MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Silence warnings such as - drivers/video/s1d13xxxfb.c:421: warning: ‘bltbit_wait_bitset’ defined but not used Just drop the unused code. Signed-off-by: Andres Salomon Signed-off-by: Paul Mundt --- include/video/s1d13xxxfb.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/video/s1d13xxxfb.h b/include/video/s1d13xxxfb.h index f0736cf..55f5344 100644 --- a/include/video/s1d13xxxfb.h +++ b/include/video/s1d13xxxfb.h @@ -136,12 +136,6 @@ #define S1DREG_DELAYOFF 0xFFFE #define S1DREG_DELAYON 0xFFFF -#define BBLT_FIFO_EMPTY 0x00 -#define BBLT_FIFO_NOT_EMPTY 0x40 -#define BBLT_FIFO_NOT_FULL 0x30 -#define BBLT_FIFO_HALF_FULL 0x20 -#define BBLT_FIFO_FULL 0x10 - #define BBLT_SOLID_FILL 0x0c -- cgit v1.1 From b8da46d3d55807037b58f14621a0949f18053bde Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Mon, 20 Dec 2010 00:29:32 -0500 Subject: clarify a usage constraint for cnt32_to_63() The cnt32_to_63 algorithm relies on proper counter data evaluation ordering to work properly. This was missing from the provided documentation. Let's augment the documentation with the missing usage constraint and fix the only instance that got it wrong. Signed-off-by: Nicolas Pitre Acked-by: David Howells Signed-off-by: Linus Torvalds --- include/linux/cnt32_to_63.h | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/cnt32_to_63.h b/include/linux/cnt32_to_63.h index 7605fdd..e3d8bf2 100644 --- a/include/linux/cnt32_to_63.h +++ b/include/linux/cnt32_to_63.h @@ -61,13 +61,31 @@ union cnt32_to_63 { * * 2) this code must not be preempted for a duration longer than the * 32-bit counter half period minus the longest period between two - * calls to this code. + * calls to this code; * * Those requirements ensure proper update to the state bit in memory. * This is usually not a problem in practice, but if it is then a kernel * timer should be scheduled to manage for this code to be executed often * enough. * + * And finally: + * + * 3) the cnt_lo argument must be seen as a globally incrementing value, + * meaning that it should be a direct reference to the counter data which + * can be evaluated according to a specific ordering within the macro, + * and not the result of a previous evaluation stored in a variable. + * + * For example, this is wrong: + * + * u32 partial = get_hw_count(); + * u64 full = cnt32_to_63(partial); + * return full; + * + * This is fine: + * + * u64 full = cnt32_to_63(get_hw_count()); + * return full; + * * Note that the top bit (bit 63) in the returned value should be considered * as garbage. It is not cleared here because callers are likely to use a * multiplier on the returned value which can get rid of the top bit -- cgit v1.1 From 173021072e86a0a5b3d2271347493a3e0d5f68e8 Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Mon, 20 Dec 2010 04:35:30 +0000 Subject: net_sched: always clone skbs Pawel reported a panic related to handling shared skbs in ixgbe incorrectly. So we need to revert my previous patch to work around this bug. Instead of reverting the patch completely, I just revert the essential lines, so we can add the previous optimization back more easily in future. commit 3511c9132f8b1e1b5634e41a3331c44b0c13be70 Author: Changli Gao Date: Sat Oct 16 13:04:08 2010 +0000 net_sched: remove the unused parameter of qdisc_create_dflt() Reported-by: Pawel Staszewski Signed-off-by: Changli Gao Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sch_generic.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index ea1f8a8..79f34e2 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -610,11 +610,7 @@ static inline struct sk_buff *skb_act_clone(struct sk_buff *skb, gfp_t gfp_mask, { struct sk_buff *n; - if ((action == TC_ACT_STOLEN || action == TC_ACT_QUEUED) && - !skb_shared(skb)) - n = skb_get(skb); - else - n = skb_clone(skb, gfp_mask); + n = skb_clone(skb, gfp_mask); if (n) { n->tc_verd = SET_TC_VERD(n->tc_verd, 0); -- cgit v1.1 From 6561a3b12d62ed5317e6ac32182d87a03f62c8dc Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sun, 19 Dec 2010 21:11:20 -0800 Subject: ipv4: Flush per-ns routing cache more sanely. Flush the routing cache only of entries that match the network namespace in which the purge event occurred. Signed-off-by: David S. Miller Acked-by: Eric Dumazet --- include/net/route.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/route.h b/include/net/route.h index 2700236..93e10c4 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -114,7 +114,7 @@ extern int ip_rt_init(void); extern void ip_rt_redirect(__be32 old_gw, __be32 dst, __be32 new_gw, __be32 src, struct net_device *dev); extern void rt_cache_flush(struct net *net, int how); -extern void rt_cache_flush_batch(void); +extern void rt_cache_flush_batch(struct net *net); extern int __ip_route_output_key(struct net *, struct rtable **, const struct flowi *flp); extern int ip_route_output_key(struct net *, struct rtable **, struct flowi *flp); extern int ip_route_output_flow(struct net *, struct rtable **rp, struct flowi *flp, struct sock *sk, int flags); -- cgit v1.1 From 9f333281a7da4c3a59bccc0cb53f7590eb850d93 Mon Sep 17 00:00:00 2001 From: Johannes Stezenbach Date: Tue, 30 Nov 2010 16:49:23 +0100 Subject: mac80211/rt2x00: add ieee80211_tx_status_ni() All rt2x00 drivers except rt2800pci call ieee80211_tx_status() from a workqueue, which causes "NOHZ: local_softirq_pending 08" messages. To fix it, add ieee80211_tx_status_ni() similar to ieee80211_rx_ni() which can be called from process context, and call it from rt2x00lib_txdone(). For the rt2800pci special case a driver flag is introduced. https://bugzilla.kernel.org/show_bug.cgi?id=24892 Signed-off-by: Johannes Stezenbach Signed-off-by: John W. Linville --- include/net/mac80211.h | 28 ++++++++++++++++++++++++---- 1 file changed, 24 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 9fdf982..365359b 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2024,8 +2024,8 @@ static inline void ieee80211_rx_ni(struct ieee80211_hw *hw, * * This function may not be called in IRQ context. Calls to this function * for a single hardware must be synchronized against each other. Calls - * to this function and ieee80211_tx_status_irqsafe() may not be mixed - * for a single hardware. + * to this function, ieee80211_tx_status_ni() and ieee80211_tx_status_irqsafe() + * may not be mixed for a single hardware. * * @hw: the hardware the frame was transmitted by * @skb: the frame that was transmitted, owned by mac80211 after this call @@ -2034,13 +2034,33 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb); /** + * ieee80211_tx_status_ni - transmit status callback (in process context) + * + * Like ieee80211_tx_status() but can be called in process context. + * + * Calls to this function, ieee80211_tx_status() and + * ieee80211_tx_status_irqsafe() may not be mixed + * for a single hardware. + * + * @hw: the hardware the frame was transmitted by + * @skb: the frame that was transmitted, owned by mac80211 after this call + */ +static inline void ieee80211_tx_status_ni(struct ieee80211_hw *hw, + struct sk_buff *skb) +{ + local_bh_disable(); + ieee80211_tx_status(hw, skb); + local_bh_enable(); +} + +/** * ieee80211_tx_status_irqsafe - IRQ-safe transmit status callback * * Like ieee80211_tx_status() but can be called in IRQ context * (internally defers to a tasklet.) * - * Calls to this function and ieee80211_tx_status() may not be mixed for a - * single hardware. + * Calls to this function, ieee80211_tx_status() and + * ieee80211_tx_status_ni() may not be mixed for a single hardware. * * @hw: the hardware the frame was transmitted by * @skb: the frame that was transmitted, owned by mac80211 after this call -- cgit v1.1 From 24bdd9f4c9af75b33b438d60381a67626de0128d Mon Sep 17 00:00:00 2001 From: Javier Cardona Date: Thu, 16 Dec 2010 17:37:48 -0800 Subject: mac80211: Rename mesh_params to mesh_config to prepare for mesh_setup Mesh parameters can be to setup a mesh or to configure it. This patch renames the ambiguous name mesh_params to mesh_config in preparation for mesh_setup. Signed-off-by: Javier Cardona Signed-off-by: John W. Linville --- include/linux/nl80211.h | 15 ++++++++++----- include/net/cfg80211.h | 8 ++++---- 2 files changed, 14 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 7483a89..11a1de6 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -172,10 +172,10 @@ * to the specified ISO/IEC 3166-1 alpha2 country code. The core will * store this as a valid request and then query userspace for it. * - * @NL80211_CMD_GET_MESH_PARAMS: Get mesh networking properties for the + * @NL80211_CMD_GET_MESH_CONFIG: Get mesh networking properties for the * interface identified by %NL80211_ATTR_IFINDEX * - * @NL80211_CMD_SET_MESH_PARAMS: Set mesh networking properties for the + * @NL80211_CMD_SET_MESH_CONFIG: Set mesh networking properties for the * interface identified by %NL80211_ATTR_IFINDEX * * @NL80211_CMD_SET_MGMT_EXTRA_IE: Set extra IEs for management frames. The @@ -448,8 +448,8 @@ enum nl80211_commands { NL80211_CMD_SET_REG, NL80211_CMD_REQ_SET_REG, - NL80211_CMD_GET_MESH_PARAMS, - NL80211_CMD_SET_MESH_PARAMS, + NL80211_CMD_GET_MESH_CONFIG, + NL80211_CMD_SET_MESH_CONFIG, NL80211_CMD_SET_MGMT_EXTRA_IE /* reserved; not used */, @@ -538,6 +538,10 @@ enum nl80211_commands { #define NL80211_CMD_DISASSOCIATE NL80211_CMD_DISASSOCIATE #define NL80211_CMD_REG_BEACON_HINT NL80211_CMD_REG_BEACON_HINT +/* source-level API compatibility */ +#define NL80211_CMD_GET_MESH_PARAMS NL80211_CMD_GET_MESH_CONFIG +#define NL80211_CMD_SET_MESH_PARAMS NL80211_CMD_SET_MESH_CONFIG + /** * enum nl80211_attrs - nl80211 netlink attributes * @@ -922,7 +926,7 @@ enum nl80211_attrs { NL80211_ATTR_REG_ALPHA2, NL80211_ATTR_REG_RULES, - NL80211_ATTR_MESH_PARAMS, + NL80211_ATTR_MESH_CONFIG, NL80211_ATTR_BSS_BASIC_RATES, @@ -1058,6 +1062,7 @@ enum nl80211_attrs { /* source-level API compatibility */ #define NL80211_ATTR_SCAN_GENERATION NL80211_ATTR_GENERATION +#define NL80211_ATTR_MESH_PARAMS NL80211_ATTR_MESH_CONFIG /* * Allow user space programs to use #ifdef on new attributes by defining them diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 6dc665a..7283496 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1096,9 +1096,9 @@ struct cfg80211_pmksa { * @get_mpath: get a mesh path for the given parameters * @dump_mpath: dump mesh path callback -- resume dump at index @idx * - * @get_mesh_params: Put the current mesh parameters into *params + * @get_mesh_config: Get the current mesh configuration * - * @update_mesh_params: Update mesh parameters on a running mesh. + * @update_mesh_config: Update mesh parameters on a running mesh. * The mask is a bitfield which tells us which parameters to * set, and which to leave alone. * @@ -1246,10 +1246,10 @@ struct cfg80211_ops { int (*dump_mpath)(struct wiphy *wiphy, struct net_device *dev, int idx, u8 *dst, u8 *next_hop, struct mpath_info *pinfo); - int (*get_mesh_params)(struct wiphy *wiphy, + int (*get_mesh_config)(struct wiphy *wiphy, struct net_device *dev, struct mesh_config *conf); - int (*update_mesh_params)(struct wiphy *wiphy, + int (*update_mesh_config)(struct wiphy *wiphy, struct net_device *dev, u32 mask, const struct mesh_config *nconf); int (*join_mesh)(struct wiphy *wiphy, struct net_device *dev, -- cgit v1.1 From c80d545da3f7c0e534ccd4a780f322f80a92cff1 Mon Sep 17 00:00:00 2001 From: Javier Cardona Date: Thu, 16 Dec 2010 17:37:49 -0800 Subject: mac80211: Let userspace enable and configure vendor specific path selection. Userspace will now be allowed to toggle between the default path selection algorithm (HWMP, implemented in the kernel), and a vendor specific alternative. Also in the same patch, allow userspace to add information elements to mesh beacons. This is accordance with the Extensible Path Selection Framework specified in version 7.0 of the 802.11s draft. Signed-off-by: Javier Cardona Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 25 +++++++++++++++++++++++++ include/linux/nl80211.h | 47 +++++++++++++++++++++++++++++++++++++++++++---- include/net/cfg80211.h | 8 ++++++++ 3 files changed, 76 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 7f23545..cd68168 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1291,6 +1291,31 @@ enum ieee80211_key_len { WLAN_KEY_LEN_AES_CMAC = 16, }; +/** + * enum - mesh path selection protocol identifier + * + * @IEEE80211_PATH_PROTOCOL_HWMP: the default path selection protocol + * @IEEE80211_PATH_PROTOCOL_VENDOR: a vendor specific protocol that will + * be specified in a vendor specific information element + */ +enum { + IEEE80211_PATH_PROTOCOL_HWMP = 0, + IEEE80211_PATH_PROTOCOL_VENDOR = 255, +}; + +/** + * enum - mesh path selection metric identifier + * + * @IEEE80211_PATH_METRIC_AIRTIME: the default path selection metric + * @IEEE80211_PATH_METRIC_VENDOR: a vendor specific metric that will be + * specified in a vendor specific information element + */ +enum { + IEEE80211_PATH_METRIC_AIRTIME = 0, + IEEE80211_PATH_METRIC_VENDOR = 255, +}; + + /* * IEEE 802.11-2007 7.3.2.9 Country information element * diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 11a1de6..69eacca 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -872,6 +872,9 @@ enum nl80211_commands { * attributes, specifying what a key should be set as default as. * See &enum nl80211_key_default_types. * + * @NL80211_ATTR_MESH_SETUP: Optional mesh setup parameters. These cannot be + * changed once the mesh is active. + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -1054,6 +1057,8 @@ enum nl80211_attrs { NL80211_ATTR_MAX_REMAIN_ON_CHANNEL_DURATION, + NL80211_ATTR_MESH_SETUP, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -1564,7 +1569,8 @@ enum nl80211_mntr_flags { /** * enum nl80211_meshconf_params - mesh configuration parameters * - * Mesh configuration parameters + * Mesh configuration parameters. These can be changed while the mesh is + * active. * * @__NL80211_MESHCONF_INVALID: internal use * @@ -1587,9 +1593,6 @@ enum nl80211_mntr_flags { * @NL80211_MESHCONF_TTL: specifies the value of TTL field set at a source mesh * point. * - * @NL80211_MESHCONF_ELEMENT_TTL: specifies the value of TTL field set at a - * source mesh point for path selection elements. - * * @NL80211_MESHCONF_AUTO_OPEN_PLINKS: whether we should automatically * open peer links when we detect compatible mesh peers. * @@ -1616,6 +1619,9 @@ enum nl80211_mntr_flags { * * @NL80211_MESHCONF_ROOTMODE: whether root mode is enabled or not * + * @NL80211_MESHCONF_ELEMENT_TTL: specifies the value of TTL field set at a + * source mesh point for path selection elements. + * * @NL80211_MESHCONF_ATTR_MAX: highest possible mesh configuration attribute * * @__NL80211_MESHCONF_ATTR_AFTER_LAST: internal use @@ -1644,6 +1650,39 @@ enum nl80211_meshconf_params { }; /** + * enum nl80211_mesh_setup_params - mesh setup parameters + * + * Mesh setup parameters. These are used to start/join a mesh and cannot be + * changed while the mesh is active. + * + * @__NL80211_MESH_SETUP_INVALID: Internal use + * + * @NL80211_MESH_SETUP_ENABLE_VENDOR_PATH_SEL: Enable this option to use a + * vendor specific path selection algorithm or disable it to use the default + * HWMP. + * + * @NL80211_MESH_SETUP_ENABLE_VENDOR_METRIC: Enable this option to use a + * vendor specific path metric or disable it to use the default Airtime + * metric. + * + * @NL80211_MESH_SETUP_VENDOR_PATH_SEL_IE: A vendor specific information + * element that vendors will use to identify the path selection methods and + * metrics in use. + * + * @__NL80211_MESH_SETUP_ATTR_AFTER_LAST: Internal use + */ +enum nl80211_mesh_setup_params { + __NL80211_MESH_SETUP_INVALID, + NL80211_MESH_SETUP_ENABLE_VENDOR_PATH_SEL, + NL80211_MESH_SETUP_ENABLE_VENDOR_METRIC, + NL80211_MESH_SETUP_VENDOR_PATH_SEL_IE, + + /* keep last */ + __NL80211_MESH_SETUP_ATTR_AFTER_LAST, + NL80211_MESH_SETUP_ATTR_MAX = __NL80211_MESH_SETUP_ATTR_AFTER_LAST - 1 +}; + +/** * enum nl80211_txq_attr - TX queue parameter attributes * @__NL80211_TXQ_ATTR_INVALID: Attribute number 0 is reserved * @NL80211_TXQ_ATTR_QUEUE: TX queue identifier (NL80211_TXQ_Q_*) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 7283496..924d603 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -649,12 +649,20 @@ struct mesh_config { * struct mesh_setup - 802.11s mesh setup configuration * @mesh_id: the mesh ID * @mesh_id_len: length of the mesh ID, at least 1 and at most 32 bytes + * @path_sel_proto: which path selection protocol to use + * @path_metric: which metric to use + * @vendor_ie: vendor information elements (optional) + * @vendor_ie_len: length of vendor information elements * * These parameters are fixed when the mesh is created. */ struct mesh_setup { const u8 *mesh_id; u8 mesh_id_len; + u8 path_sel_proto; + u8 path_metric; + const u8 *vendor_ie; + u8 vendor_ie_len; }; /** -- cgit v1.1 From 7f531e03abf0162df3966c4fa5fa6fdd9302cb6b Mon Sep 17 00:00:00 2001 From: Bruno Randolf Date: Thu, 16 Dec 2010 11:30:22 +0900 Subject: cfg80211: Separate available antennas for RX and TX As has been pointed out by Daniel Halperin some devices (e.g. Intel IWL5100) can only TX from a subset of RX antennas, so use separate availability masks for RX and TX. Signed-off-by: Bruno Randolf Signed-off-by: John W. Linville --- include/net/cfg80211.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 924d603..bcc9f44 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1482,8 +1482,13 @@ struct ieee80211_txrx_stypes { * transmitted through nl80211, points to an array indexed by interface * type * - * @available_antennas: bitmap of antennas which are available to configure. - * antenna configuration commands will be rejected unless this is set. + * @available_antennas_tx: bitmap of antennas which are available to be + * configured as TX antennas. Antenna configuration commands will be + * rejected unless this or @available_antennas_rx is set. + * + * @available_antennas_rx: bitmap of antennas which are available to be + * configured as RX antennas. Antenna configuration commands will be + * rejected unless this or @available_antennas_tx is set. * * @max_remain_on_channel_duration: Maximum time a remain-on-channel operation * may request, if implemented. @@ -1528,7 +1533,8 @@ struct wiphy { u8 max_num_pmkids; - u32 available_antennas; + u32 available_antennas_tx; + u32 available_antennas_rx; /* If multiple wiphys are registered and you're handed e.g. * a regular netdev with assigned ieee80211_ptr, you won't -- cgit v1.1 From 39fd5de4472b7b222c6cec78d72b069133f694e4 Mon Sep 17 00:00:00 2001 From: Bruno Randolf Date: Thu, 16 Dec 2010 11:30:28 +0900 Subject: nl80211: Export available antennas Export the information which antennas are available for configuration as TX or RX antennas via nl80211. Signed-off-by: Bruno Randolf Signed-off-by: John W. Linville --- include/linux/nl80211.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 69eacca..2b89b71 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -858,6 +858,12 @@ enum nl80211_commands { * the hardware should not be configured to receive on this antenna. * For a more detailed descripton see @NL80211_ATTR_WIPHY_ANTENNA_TX. * + * @NL80211_ATTR_WIPHY_ANTENNA_AVAIL_TX: Bitmap of antennas which are available + * for configuration as TX antennas via the above parameters. + * + * @NL80211_ATTR_WIPHY_ANTENNA_AVAIL_RX: Bitmap of antennas which are available + * for configuration as RX antennas via the above parameters. + * * @NL80211_ATTR_MCAST_RATE: Multicast tx rate (in 100 kbps) for IBSS * * @NL80211_ATTR_OFFCHANNEL_TX_OK: For management frame TX, the frame may be @@ -1059,6 +1065,9 @@ enum nl80211_attrs { NL80211_ATTR_MESH_SETUP, + NL80211_ATTR_WIPHY_ANTENNA_AVAIL_TX, + NL80211_ATTR_WIPHY_ANTENNA_AVAIL_RX, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, -- cgit v1.1 From 61ad5394590c5c5338ab4ec50553d809a9996d50 Mon Sep 17 00:00:00 2001 From: Javier Cardona Date: Thu, 16 Dec 2010 17:23:34 -0800 Subject: mac80211: Remove unused third address from mesh address extension header. The Mesh Control header only includes 0, 1 or 2 addresses. If there is one address, it should be interpreted as Address 4. If there are 2, they are interpreted as Addresses 5 and 6 (Address 4 being the 4th address in the 802.11 header). The address extension used to hold up to 3 addresses instead of the current 2. I'm not sure which draft version changed this, but it is very unlikely that it will change again given the state of the approval process of this draft. See section 7.1.3.6.3 in current draft (8.0). Also, note that the extra address that I'm removing was not being used, so this change has no effect on over-the-air frame formats. But I thought I better remove it before someone does start using it. Signed-off-by: Javier Cardona Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index cd68168..6042228 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -536,7 +536,6 @@ struct ieee80211s_hdr { __le32 seqnum; u8 eaddr1[6]; u8 eaddr2[6]; - u8 eaddr3[6]; } __attribute__ ((packed)); /* Mesh flags */ -- cgit v1.1 From 356f039822b8d802138f7121c80d2a9286976dbd Mon Sep 17 00:00:00 2001 From: Nandita Dukkipati Date: Mon, 20 Dec 2010 14:15:56 +0000 Subject: TCP: increase default initial receive window. This patch changes the default initial receive window to 10 mss (defined constant). The default window is limited to the maximum of 10*1460 and 2*mss (when mss > 1460). draft-ietf-tcpm-initcwnd-00 is a proposal to the IETF that recommends increasing TCP's initial congestion window to 10 mss or about 15KB. Leading up to this proposal were several large-scale live Internet experiments with an initial congestion window of 10 mss (IW10), where we showed that the average latency of HTTP responses improved by approximately 10%. This was accompanied by a slight increase in retransmission rate (0.5%), most of which is coming from applications opening multiple simultaneous connections. To understand the extreme worst case scenarios, and fairness issues (IW10 versus IW3), we further conducted controlled testbed experiments. We came away finding minimal negative impact even under low link bandwidths (dial-ups) and small buffers. These results are extremely encouraging to adopting IW10. However, an initial congestion window of 10 mss is useless unless a TCP receiver advertises an initial receive window of at least 10 mss. Fortunately, in the large-scale Internet experiments we found that most widely used operating systems advertised large initial receive windows of 64KB, allowing us to experiment with a wide range of initial congestion windows. Linux systems were among the few exceptions that advertised a small receive window of 6KB. The purpose of this patch is to fix this shortcoming. References: 1. A comprehensive list of all IW10 references to date. http://code.google.com/speed/protocols/tcpm-IW10.html 2. Paper describing results from large-scale Internet experiments with IW10. http://ccr.sigcomm.org/drupal/?q=node/621 3. Controlled testbed experiments under worst case scenarios and a fairness study. http://www.ietf.org/proceedings/79/slides/tcpm-0.pdf 4. Raw test data from testbed experiments (Linux senders/receivers) with initial congestion and receive windows of both 10 mss. http://research.csc.ncsu.edu/netsrv/?q=content/iw10 5. Internet-Draft. Increasing TCP's Initial Window. https://datatracker.ietf.org/doc/draft-ietf-tcpm-initcwnd/ Signed-off-by: Nandita Dukkipati Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index b448030..38509f0 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -60,6 +60,9 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); */ #define MAX_TCP_WINDOW 32767U +/* Offer an initial receive window of 10 mss. */ +#define TCP_DEFAULT_INIT_RCVWND 10 + /* Minimal accepted MSS. It is (60+60+8) - (20+20). */ #define TCP_MIN_MSS 88U -- cgit v1.1 From 00f0254ed9b19164d416dc2e3c2e81eda55a6faf Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 1 Oct 2010 13:55:52 -0700 Subject: [SCSI] libsas: fix definition of wideport, include local sas address To date libsas has only looked at the attached sas address when determining the formation of wide ports. The specification and some hardware expects that phys with different addresses will not form a wide port unless the local peer phys also match each other. Introduce a flag to select stricter behavior at sas_register_ha() time. The flag can be dropped once it is known that all libsas users expect the same behavior. Current drivers just initialize this field to zero and get the traditional behavior. Reported-by: Patrick Thomson Signed-off-by: Dan Williams Signed-off-by: James Bottomley --- include/scsi/libsas.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h index 90ce527..8f6bb9c 100644 --- a/include/scsi/libsas.h +++ b/include/scsi/libsas.h @@ -361,6 +361,8 @@ struct sas_ha_struct { /* The class calls this to send a task for execution. */ int lldd_max_execute_num; int lldd_queue_size; + int strict_wide_ports; /* both sas_addr and attached_sas_addr must match + * their siblings when forming wide ports */ /* LLDD calls these to notify the class of an event. */ void (*notify_ha_event)(struct sas_ha_struct *, enum ha_event); -- cgit v1.1 From 8eea2f55a65b9471276e78e5c86ddd19c4c0365c Mon Sep 17 00:00:00 2001 From: Eddie Wai Date: Tue, 23 Nov 2010 15:29:21 -0800 Subject: [SCSI] bnx2i: Added fix for NOP-Out response panic from unsolicited NOP-In The patch fixes the following situations where NOP-Out pkt is called for: - local unsolicited NOP-Out requests (requesting no NOP-In response) - local NOP-Out responses to unsolicited NOP-In requests kernel panic is observed due to double session spin_lock requests; one in the bnx2i_process_nopin_local_cmpl routine in bnx2i_hwi.c and the other in the iscsi_put_task routine in libiscsi.c The proposed fix is to export the currently static __iscsi_put_task() routine and have bnx2i call it directly instead of the iscsi_put_task() routine which holds the session spin lock. Signed-off-by: Eddie Wai Reviewed-by: Michael Chan Reviewed-by: Anil Veerabhadrappa Acked-by: Benjamin Li Reviewed-by: Mike Christie Signed-off-by: James Bottomley --- include/scsi/libiscsi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index b81d969..68e951d 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -419,6 +419,7 @@ extern struct iscsi_task *iscsi_itt_to_ctask(struct iscsi_conn *, itt_t); extern struct iscsi_task *iscsi_itt_to_task(struct iscsi_conn *, itt_t); extern void iscsi_requeue_task(struct iscsi_task *task); extern void iscsi_put_task(struct iscsi_task *task); +extern void __iscsi_put_task(struct iscsi_task *task); extern void __iscsi_get_task(struct iscsi_task *task); extern void iscsi_complete_scsi_task(struct iscsi_task *task, uint32_t exp_cmdsn, uint32_t max_cmdsn); -- cgit v1.1 From 05fee645e96e732a79ad083cab8ddd4efd108e2c Mon Sep 17 00:00:00 2001 From: john fastabend Date: Tue, 30 Nov 2010 16:18:49 -0800 Subject: [SCSI] libfc: remove tgt_flags from fc_fcp_pkt struct We can easily remove the tgt_flags from fc_fcp_pkt struct and use rpriv->tgt_flags directly where needed. Signed-off-by: John Fastabend Signed-off-by: Robert Love Signed-off-by: James Bottomley --- include/scsi/libfc.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/scsi/libfc.h b/include/scsi/libfc.h index 5c4c167..3eb3915 100644 --- a/include/scsi/libfc.h +++ b/include/scsi/libfc.h @@ -263,7 +263,6 @@ struct fc_seq_els_data { * struct fc_fcp_pkt - FCP request structure (one for each scsi_cmnd request) * @lp: The associated local port * @state: The state of the I/O - * @tgt_flags: Target's flags * @ref_cnt: Reference count * @scsi_pkt_lock: Lock to protect the SCSI packet (must be taken before the * host_lock if both are to be held at the same time) @@ -298,7 +297,6 @@ struct fc_fcp_pkt { /* Housekeeping information */ struct fc_lport *lp; u16 state; - u16 tgt_flags; atomic_t ref_cnt; spinlock_t scsi_pkt_lock; -- cgit v1.1 From 794d98e77f5901ceded697f1633463e88f078038 Mon Sep 17 00:00:00 2001 From: Joe Eykholt Date: Tue, 30 Nov 2010 16:19:56 -0800 Subject: [SCSI] libfcoe: retry rejected FLOGI to another FCF if possible Switches using multiple-FCFs may reject FLOGI in order to balance the load between multiple FCFs. Even though the FCF was available, it may have more load at the point we actually send the FLOGI. If the FLOGI fails, select a different FCF if possible, among those with the same priority. If no other FCF is available, just deliver the reject to libfc for retry. Signed-off-by: Joe Eykholt Signed-off-by: Robert Love Signed-off-by: James Bottomley --- include/scsi/libfcoe.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/scsi/libfcoe.h b/include/scsi/libfcoe.h index 06f1b5a..feb6a94 100644 --- a/include/scsi/libfcoe.h +++ b/include/scsi/libfcoe.h @@ -92,10 +92,12 @@ enum fip_state { * @timer_work: &work_struct for doing keep-alives and resets. * @recv_work: &work_struct for receiving FIP frames. * @fip_recv_list: list of received FIP frames. + * @flogi_req: clone of FLOGI request sent * @rnd_state: state for pseudo-random number generator. * @port_id: proposed or selected local-port ID. * @user_mfs: configured maximum FC frame size, including FC header. * @flogi_oxid: exchange ID of most recent fabric login. + * @flogi_req_send: send of FLOGI requested * @flogi_count: number of FLOGI attempts in AUTO mode. * @map_dest: use the FC_MAP mode for destination MAC addresses. * @spma: supports SPMA server-provided MACs mode @@ -106,6 +108,7 @@ enum fip_state { * @update_mac: LLD-supplied function to handle changes to MAC addresses. * @get_src_addr: LLD-supplied function to supply a source MAC address. * @ctlr_mutex: lock protecting this structure. + * @ctlr_lock: spinlock covering flogi_req * * This structure is used by all FCoE drivers. It contains information * needed by all FCoE low-level drivers (LLDs) as well as internal state @@ -126,12 +129,14 @@ struct fcoe_ctlr { struct work_struct timer_work; struct work_struct recv_work; struct sk_buff_head fip_recv_list; + struct sk_buff *flogi_req; struct rnd_state rnd_state; u32 port_id; u16 user_mfs; u16 flogi_oxid; + u8 flogi_req_send; u8 flogi_count; u8 map_dest; u8 spma; @@ -143,6 +148,7 @@ struct fcoe_ctlr { void (*update_mac)(struct fc_lport *, u8 *addr); u8 * (*get_src_addr)(struct fc_lport *); struct mutex ctlr_mutex; + spinlock_t ctlr_lock; }; /** @@ -155,6 +161,7 @@ struct fcoe_ctlr { * @fcf_mac: Ethernet address of the FCF * @vfid: virtual fabric ID * @pri: selection priority, smaller values are better + * @flogi_sent: current FLOGI sent to this FCF * @flags: flags received from advertisement * @fka_period: keep-alive period, in jiffies * @@ -176,6 +183,7 @@ struct fcoe_fcf { u8 fcf_mac[ETH_ALEN]; u8 pri; + u8 flogi_sent; u16 flags; u32 fka_period; u8 fd_flags:1; -- cgit v1.1 From 5f0e385fdafb7d6c8ded6464fa6421c735d96caf Mon Sep 17 00:00:00 2001 From: Joe Eykholt Date: Tue, 30 Nov 2010 16:20:18 -0800 Subject: [SCSI] libfc: fix statistics for FCP input/output megabytes The statistics for InputMegabytes and OutputMegabytes are misnamed. They're accumulating bytes, not megabytes. The statistic returned via /sys must be in megabytes, however, which is what the HBA-API wants. The FCP code needs to accumulate it in bytes and then divide by 1,000,000 (not 2^20) before it presented via sysfs. This affects fcoe.ko only, not fnic. The fnic driver correctly by accumulating bytes and then converts to megabytes. I checked that libhbalinux is using the /sys file directly without conversion. BTW, qla2xxx does divide by 2^20, which I'm not fixing here. Signed-off-by: Joe Eykholt Signed-off-by: Robert Love Signed-off-by: James Bottomley --- include/scsi/libfc.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/scsi/libfc.h b/include/scsi/libfc.h index 3eb3915..f53c8e3 100644 --- a/include/scsi/libfc.h +++ b/include/scsi/libfc.h @@ -221,8 +221,8 @@ struct fc_rport_priv { * @InputRequests: Number of input requests * @OutputRequests: Number of output requests * @ControlRequests: Number of control requests - * @InputMegabytes: Number of received megabytes - * @OutputMegabytes: Number of transmitted megabytes + * @InputBytes: Number of received bytes + * @OutputBytes: Number of transmitted bytes * @VLinkFailureCount: Number of virtual link failures * @MissDiscAdvCount: Number of missing FIP discovery advertisement */ @@ -241,8 +241,8 @@ struct fcoe_dev_stats { u64 InputRequests; u64 OutputRequests; u64 ControlRequests; - u64 InputMegabytes; - u64 OutputMegabytes; + u64 InputBytes; + u64 OutputBytes; u64 VLinkFailureCount; u64 MissDiscAdvCount; }; -- cgit v1.1 From e9ccc998b70fbe59626f393bb0328402159c6b5c Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Fri, 17 Dec 2010 13:11:16 -0800 Subject: [SCSI] Add missing SPC-4 CDB and MAINTENANCE_[IN,OUT] service action definitions This patch adds a handful of missing CDBs defs that are used by TCM persistent reservation logic in the SPC-4 defined CDB exclusion table for registrations and reservations. This includes a number of missing MI_* and MO_* prefixed service actions defs for MAINTENANCE_IN and MAINTENANCE_OUT that are mentioned wrt to persistent registration and reservation status for the SCSI Initiator Port. Signed-off-by: Nicholas A. Bellinger Signed-off-by: James Bottomley --- include/scsi/scsi.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include') diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h index 216af85..1651fef 100644 --- a/include/scsi/scsi.h +++ b/include/scsi/scsi.h @@ -115,33 +115,61 @@ struct scsi_cmnd; #define PERSISTENT_RESERVE_OUT 0x5f #define VARIABLE_LENGTH_CMD 0x7f #define REPORT_LUNS 0xa0 +#define SECURITY_PROTOCOL_IN 0xa2 #define MAINTENANCE_IN 0xa3 #define MAINTENANCE_OUT 0xa4 #define MOVE_MEDIUM 0xa5 #define EXCHANGE_MEDIUM 0xa6 #define READ_12 0xa8 #define WRITE_12 0xaa +#define READ_MEDIA_SERIAL_NUMBER 0xab #define WRITE_VERIFY_12 0xae #define VERIFY_12 0xaf #define SEARCH_HIGH_12 0xb0 #define SEARCH_EQUAL_12 0xb1 #define SEARCH_LOW_12 0xb2 +#define SECURITY_PROTOCOL_OUT 0xb5 #define READ_ELEMENT_STATUS 0xb8 #define SEND_VOLUME_TAG 0xb6 #define WRITE_LONG_2 0xea +#define EXTENDED_COPY 0x83 +#define RECEIVE_COPY_RESULTS 0x84 +#define ACCESS_CONTROL_IN 0x86 +#define ACCESS_CONTROL_OUT 0x87 #define READ_16 0x88 #define WRITE_16 0x8a +#define READ_ATTRIBUTE 0x8c +#define WRITE_ATTRIBUTE 0x8d #define VERIFY_16 0x8f #define WRITE_SAME_16 0x93 #define SERVICE_ACTION_IN 0x9e /* values for service action in */ #define SAI_READ_CAPACITY_16 0x10 #define SAI_GET_LBA_STATUS 0x12 +/* values for VARIABLE_LENGTH_CMD service action codes + * see spc4r17 Section D.3.5, table D.7 and D.8 */ +#define VLC_SA_RECEIVE_CREDENTIAL 0x1800 /* values for maintenance in */ +#define MI_REPORT_IDENTIFYING_INFORMATION 0x05 #define MI_REPORT_TARGET_PGS 0x0a +#define MI_REPORT_ALIASES 0x0b +#define MI_REPORT_SUPPORTED_OPERATION_CODES 0x0c +#define MI_REPORT_SUPPORTED_TASK_MANAGEMENT_FUNCTIONS 0x0d +#define MI_REPORT_PRIORITY 0x0e +#define MI_REPORT_TIMESTAMP 0x0f +#define MI_MANAGEMENT_PROTOCOL_IN 0x10 /* values for maintenance out */ +#define MO_SET_IDENTIFYING_INFORMATION 0x06 #define MO_SET_TARGET_PGS 0x0a +#define MO_CHANGE_ALIASES 0x0b +#define MO_SET_PRIORITY 0x0e +#define MO_SET_TIMESTAMP 0x0f +#define MO_MANAGEMENT_PROTOCOL_OUT 0x10 /* values for variable length command */ +#define XDREAD_32 0x03 +#define XDWRITE_32 0x04 +#define XPWRITE_32 0x06 +#define XDWRITEREAD_32 0x07 #define READ_32 0x09 #define VERIFY_32 0x0a #define WRITE_32 0x0b -- cgit v1.1 From da521b2c4f046383bc8941604174bc0e8bffb430 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 21 Dec 2010 12:43:16 -0800 Subject: net: Fix range checks in tcf_valid_offset(). This function has three bugs: 1) The offset should be valid most of the time, this is just a sanity check, therefore we should use "likely" not "unlikely" 2) This is the only place where we can check for arithmetic overflow of the pointer plus the length. 3) The existing range checks are off by one, the valid range is skb->head to skb_tail_pointer(), inclusive. Based almost entirely upon a patch by Ralph Loader. Reported-by: Ralph Loader Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index dd3031a..9fcc680 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -323,7 +323,9 @@ static inline unsigned char * tcf_get_base_ptr(struct sk_buff *skb, int layer) static inline int tcf_valid_offset(const struct sk_buff *skb, const unsigned char *ptr, const int len) { - return unlikely((ptr + len) < skb_tail_pointer(skb) && ptr > skb->head); + return likely((ptr + len) <= skb_tail_pointer(skb) && + ptr >= skb->head && + (ptr <= (ptr + len))); } #ifdef CONFIG_NET_CLS_IND -- cgit v1.1 From c66ae9bb4dcaac78cc5e30d0ce7ff2bf3dcb48d9 Mon Sep 17 00:00:00 2001 From: Vasily Khoruzhick Date: Mon, 13 Dec 2010 12:26:21 +0200 Subject: s3c_adc_battery: Add gpio_inverted field to pdata Add support for inverted gpio_charge_finished values. This change is necessary for H1940 support. Signed-off-by: Vasily Khoruzhick Signed-off-by: Anton Vorontsov --- include/linux/s3c_adc_battery.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/s3c_adc_battery.h b/include/linux/s3c_adc_battery.h index dbce22f..fbe58b7 100644 --- a/include/linux/s3c_adc_battery.h +++ b/include/linux/s3c_adc_battery.h @@ -14,6 +14,7 @@ struct s3c_adc_bat_pdata { void (*disable_charger)(void); int gpio_charge_finished; + int gpio_inverted; const struct s3c_adc_bat_thresh *lut_noac; unsigned int lut_noac_cnt; -- cgit v1.1 From 4f32e9b1f812fd6c00cc85a127583fefbdedaedc Mon Sep 17 00:00:00 2001 From: Yong Zhang Date: Wed, 22 Dec 2010 10:27:53 +0100 Subject: kthread_work: make lockdep happy spinlock in kthread_worker and wait_queue_head in kthread_work both should be lockdep sensible, so change the interface to make it suiltable for CONFIG_LOCKDEP. tj: comment update Reported-by: Nicolas Signed-off-by: Yong Zhang Signed-off-by: Andy Walls Tested-by: Andy Walls Cc: Tejun Heo Cc: Andrew Morton Signed-off-by: Tejun Heo --- include/linux/kthread.h | 45 +++++++++++++++++++++++++++++++++++---------- 1 file changed, 35 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 685ea65..ce0775a 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -81,16 +81,41 @@ struct kthread_work { #define DEFINE_KTHREAD_WORK(work, fn) \ struct kthread_work work = KTHREAD_WORK_INIT(work, fn) -static inline void init_kthread_worker(struct kthread_worker *worker) -{ - *worker = (struct kthread_worker)KTHREAD_WORKER_INIT(*worker); -} - -static inline void init_kthread_work(struct kthread_work *work, - kthread_work_func_t fn) -{ - *work = (struct kthread_work)KTHREAD_WORK_INIT(*work, fn); -} +/* + * kthread_worker.lock and kthread_work.done need their own lockdep class + * keys if they are defined on stack with lockdep enabled. Use the + * following macros when defining them on stack. + */ +#ifdef CONFIG_LOCKDEP +# define KTHREAD_WORKER_INIT_ONSTACK(worker) \ + ({ init_kthread_worker(&worker); worker; }) +# define DEFINE_KTHREAD_WORKER_ONSTACK(worker) \ + struct kthread_worker worker = KTHREAD_WORKER_INIT_ONSTACK(worker) +# define KTHREAD_WORK_INIT_ONSTACK(work, fn) \ + ({ init_kthread_work((&work), fn); work; }) +# define DEFINE_KTHREAD_WORK_ONSTACK(work, fn) \ + struct kthread_work work = KTHREAD_WORK_INIT_ONSTACK(work, fn) +#else +# define DEFINE_KTHREAD_WORKER_ONSTACK(worker) DEFINE_KTHREAD_WORKER(worker) +# define DEFINE_KTHREAD_WORK_ONSTACK(work, fn) DEFINE_KTHREAD_WORK(work, fn) +#endif + +extern void __init_kthread_worker(struct kthread_worker *worker, + const char *name, struct lock_class_key *key); + +#define init_kthread_worker(worker) \ + do { \ + static struct lock_class_key __key; \ + __init_kthread_worker((worker), "("#worker")->lock", &__key); \ + } while (0) + +#define init_kthread_work(work, fn) \ + do { \ + memset((work), 0, sizeof(struct kthread_work)); \ + INIT_LIST_HEAD(&(work)->node); \ + (work)->func = (fn); \ + init_waitqueue_head(&(work)->done); \ + } while (0) int kthread_worker_fn(void *worker_ptr); -- cgit v1.1 From da1f026b532ce944d74461497dc6d8c16456466e Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Mon, 20 Dec 2010 21:09:22 +0000 Subject: Keyboard: omap-keypad: use matrix_keypad.h Most keypad drivers make use of the defined macros, structures and inline functions. Convert omap-keypad driver to use those as well, as suggested by a compile time warning, hardcoded into the OMAP . Created against linux-2.6.37-rc5. Tested on Amstrad Delta. Compile tested with omap1_defconfig and omap2plus_defconfig shrinked to board-h4. Signed-off-by: Janusz Krzysztofik Reviewed-by: Aaro Koskinen Acked-by: Dmitry Torokhov Signed-off-by: Tony Lindgren --- include/linux/input/matrix_keypad.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/input/matrix_keypad.h b/include/linux/input/matrix_keypad.h index 80352ad..6974746 100644 --- a/include/linux/input/matrix_keypad.h +++ b/include/linux/input/matrix_keypad.h @@ -9,7 +9,7 @@ #define KEY(row, col, val) ((((row) & (MATRIX_MAX_ROWS - 1)) << 24) |\ (((col) & (MATRIX_MAX_COLS - 1)) << 16) |\ - (val & 0xffff)) + ((val) & 0xffff)) #define KEY_ROW(k) (((k) >> 24) & 0xff) #define KEY_COL(k) (((k) >> 16) & 0xff) -- cgit v1.1 From e1e5406854378dfada3f33c7192b012083a5b8e0 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 30 Nov 2010 08:58:45 +0100 Subject: mac80211: add throughput based LED blink trigger iwlwifi and other drivers like to blink their LED based on throughput. Implement this generically in mac80211, based on a throughput table the driver specifies. That way, drivers can set the blink frequencies depending on their desired behaviour and max throughput. All the drivers need to do is provide an LED class device, best with blink hardware offload. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 69ded1e..40a93d5 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1852,11 +1852,26 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, */ int ieee80211_register_hw(struct ieee80211_hw *hw); +/** + * struct ieee80211_tpt_blink - throughput blink description + * @throughput: throughput in Kbit/sec + * @blink_time: blink time in milliseconds + * (full cycle, ie. one off + one on period) + */ +struct ieee80211_tpt_blink { + int throughput; + int blink_time; +}; + #ifdef CONFIG_MAC80211_LEDS extern char *__ieee80211_get_tx_led_name(struct ieee80211_hw *hw); extern char *__ieee80211_get_rx_led_name(struct ieee80211_hw *hw); extern char *__ieee80211_get_assoc_led_name(struct ieee80211_hw *hw); extern char *__ieee80211_get_radio_led_name(struct ieee80211_hw *hw); +extern char *__ieee80211_create_tpt_led_trigger( + struct ieee80211_hw *hw, + const struct ieee80211_tpt_blink *blink_table, + unsigned int blink_table_len); #endif /** * ieee80211_get_tx_led_name - get name of TX LED @@ -1935,6 +1950,29 @@ static inline char *ieee80211_get_radio_led_name(struct ieee80211_hw *hw) } /** + * ieee80211_create_tpt_led_trigger - create throughput LED trigger + * @hw: the hardware to create the trigger for + * @blink_table: the blink table -- needs to be ordered by throughput + * @blink_table_len: size of the blink table + * + * This function returns %NULL (in case of error, or if no LED + * triggers are configured) or the name of the new trigger. + * This function must be called before ieee80211_register_hw(). + */ +static inline char * +ieee80211_create_tpt_led_trigger(struct ieee80211_hw *hw, + const struct ieee80211_tpt_blink *blink_table, + unsigned int blink_table_len) +{ +#ifdef CONFIG_MAC80211_LEDS + return __ieee80211_create_tpt_led_trigger(hw, blink_table, + blink_table_len); +#else + return NULL; +#endif +} + +/** * ieee80211_unregister_hw - Unregister a hardware device * * This function instructs mac80211 to free allocated resources -- cgit v1.1 From 67408c8c7b9daf28b50e33be3541334c07d15789 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 30 Nov 2010 08:59:23 +0100 Subject: mac80211: selective throughput LED trigger active The throughput LED trigger was always active when the radio was enabled. In most cases that's likely the desired behaviour, but iwlwifi requires it to be only active when one of the virtual interfaces is actually "connected" in some way. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 40a93d5..479c35e 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1863,13 +1863,26 @@ struct ieee80211_tpt_blink { int blink_time; }; +/** + * enum ieee80211_tpt_led_trigger_flags - throughput trigger flags + * @IEEE80211_TPT_LEDTRIG_FL_RADIO: enable blinking with radio + * @IEEE80211_TPT_LEDTRIG_FL_WORK: enable blinking when working + * @IEEE80211_TPT_LEDTRIG_FL_CONNECTED: enable blinking when at least one + * interface is connected in some way, including being an AP + */ +enum ieee80211_tpt_led_trigger_flags { + IEEE80211_TPT_LEDTRIG_FL_RADIO = BIT(0), + IEEE80211_TPT_LEDTRIG_FL_WORK = BIT(1), + IEEE80211_TPT_LEDTRIG_FL_CONNECTED = BIT(2), +}; + #ifdef CONFIG_MAC80211_LEDS extern char *__ieee80211_get_tx_led_name(struct ieee80211_hw *hw); extern char *__ieee80211_get_rx_led_name(struct ieee80211_hw *hw); extern char *__ieee80211_get_assoc_led_name(struct ieee80211_hw *hw); extern char *__ieee80211_get_radio_led_name(struct ieee80211_hw *hw); extern char *__ieee80211_create_tpt_led_trigger( - struct ieee80211_hw *hw, + struct ieee80211_hw *hw, unsigned int flags, const struct ieee80211_tpt_blink *blink_table, unsigned int blink_table_len); #endif @@ -1952,6 +1965,7 @@ static inline char *ieee80211_get_radio_led_name(struct ieee80211_hw *hw) /** * ieee80211_create_tpt_led_trigger - create throughput LED trigger * @hw: the hardware to create the trigger for + * @flags: trigger flags, see &enum ieee80211_tpt_led_trigger_flags * @blink_table: the blink table -- needs to be ordered by throughput * @blink_table_len: size of the blink table * @@ -1960,12 +1974,12 @@ static inline char *ieee80211_get_radio_led_name(struct ieee80211_hw *hw) * This function must be called before ieee80211_register_hw(). */ static inline char * -ieee80211_create_tpt_led_trigger(struct ieee80211_hw *hw, +ieee80211_create_tpt_led_trigger(struct ieee80211_hw *hw, unsigned int flags, const struct ieee80211_tpt_blink *blink_table, unsigned int blink_table_len) { #ifdef CONFIG_MAC80211_LEDS - return __ieee80211_create_tpt_led_trigger(hw, blink_table, + return __ieee80211_create_tpt_led_trigger(hw, flags, blink_table, blink_table_len); #else return NULL; -- cgit v1.1 From 4a7863cc2eb5f9804f1c4e9156619a801cd7f14f Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Wed, 22 Dec 2010 14:00:03 -0500 Subject: x86, nmi_watchdog: Remove ARCH_HAS_NMI_WATCHDOG and rely on CONFIG_HARDLOCKUP_DETECTOR The x86 arch has shifted its use of the nmi_watchdog from a local implementation to the global one provide by kernel/watchdog.c. This shift has caused a whole bunch of compile problems under different config options. I attempt to simplify things with the patch below. In order to simplify things, I had to come to terms with the meaning of two terms ARCH_HAS_NMI_WATCHDOG and CONFIG_HARDLOCKUP_DETECTOR. Basically they mean the same thing, the former on a local level and the latter on a global level. With the old x86 nmi watchdog gone, there is no need to rely on defining the ARCH_HAS_NMI_WATCHDOG variable because it doesn't make sense any more. x86 will now use the global implementation. The changes below do a few things. First it changes the few places that relied on ARCH_HAS_NMI_WATCHDOG to use CONFIG_X86_LOCAL_APIC (the former was an alias for the latter anyway, so nothing unusual here). Those pieces of code were relying more on local apic functionality the nmi watchdog functionality, so the change should make sense. Second, I removed the x86 implementation of touch_nmi_watchdog(). It isn't need now, instead x86 will rely on kernel/watchdog.c's implementation. Third, I removed the #define ARCH_HAS_NMI_WATCHDOG itself from x86. And tweaked the include/linux/nmi.h file to tell users to look for an externally defined touch_nmi_watchdog in the case of ARCH_HAS_NMI_WATCHDOG _or_ CONFIG_HARDLOCKUP_DETECTOR. This changes removes some of the ugliness in that file. Finally, I added a Kconfig dependency for CONFIG_HARDLOCKUP_DETECTOR that said you can't have ARCH_HAS_NMI_WATCHDOG _and_ CONFIG_HARDLOCKUP_DETECTOR. You can only have one nmi_watchdog. Tested with ARCH=i386: allnoconfig, defconfig, allyesconfig, (various broken configs) ARCH=x86_64: allnoconfig, defconfig, allyesconfig, (various broken configs) Hopefully, after this patch I won't get any more compile broken emails. :-) v3: changed a couple of 'linux/nmi.h' -> 'asm/nmi.h' to pick-up correct function prototypes when CONFIG_HARDLOCKUP_DETECTOR is not set. Signed-off-by: Don Zickus Cc: Peter Zijlstra Cc: fweisbec@gmail.com LKML-Reference: <1293044403-14117-1-git-send-email-dzickus@redhat.com> Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 17ccf44..c536f85 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -14,18 +14,14 @@ * may be used to reset the timeout - for code which intentionally * disables interrupts for a long time. This call is stateless. */ -#ifdef ARCH_HAS_NMI_WATCHDOG +#if defined(ARCH_HAS_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) #include extern void touch_nmi_watchdog(void); #else -#ifndef CONFIG_HARDLOCKUP_DETECTOR static inline void touch_nmi_watchdog(void) { touch_softlockup_watchdog(); } -#else -extern void touch_nmi_watchdog(void); -#endif #endif /* -- cgit v1.1 From 02d981292ad3149e8e5f37cffbccedab1a8576d8 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Mon, 13 Dec 2010 21:07:04 +0200 Subject: Bluetooth: Add read_version management command This patch implements the initial read_version command that userspace will use before any other management interface operations. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann Signed-off-by: Gustavo F. Padovan --- include/net/bluetooth/mgmt.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 95974da..d353d64 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -27,6 +27,12 @@ struct mgmt_hdr { } __packed; #define MGMT_HDR_SIZE 4 +#define MGMT_OP_READ_VERSION 0x0001 +struct mgmt_rp_read_version { + __u8 version; + __le16 revision; +} __packed; + #define MGMT_EV_CMD_COMPLETE 0x0001 struct mgmt_ev_cmd_complete { __le16 opcode; -- cgit v1.1 From faba42eb2a8cf905ed26d540c3c93d429e327224 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Mon, 13 Dec 2010 21:07:05 +0200 Subject: Bluetooth: Add read_index_list management command This patch implements the read_index_list command through which userspace can get a list of current adapter indices. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann Signed-off-by: Gustavo F. Padovan --- include/net/bluetooth/mgmt.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index d353d64..c2b4c83 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -33,6 +33,12 @@ struct mgmt_rp_read_version { __le16 revision; } __packed; +#define MGMT_OP_READ_INDEX_LIST 0x0003 +struct mgmt_rp_read_index_list { + __le16 num_controllers; + __le16 index[0]; +} __packed; + #define MGMT_EV_CMD_COMPLETE 0x0001 struct mgmt_ev_cmd_complete { __le16 opcode; -- cgit v1.1 From f7b64e69c7c75c8e9f2d5e23edec8de1ce883bcc Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Mon, 13 Dec 2010 21:07:06 +0200 Subject: Bluetooth: Add read_info management command This patch implements the read_info command which is used to fetch basic info about an adapter. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann Signed-off-by: Gustavo F. Padovan --- include/net/bluetooth/mgmt.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index c2b4c83..70985aa 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -39,6 +39,25 @@ struct mgmt_rp_read_index_list { __le16 index[0]; } __packed; +#define MGMT_OP_READ_INFO 0x0004 +struct mgmt_cp_read_info { + __le16 index; +} __packed; +struct mgmt_rp_read_info { + __le16 index; + __u8 type; + __u8 powered; + __u8 discoverable; + __u8 pairable; + __u8 sec_mode; + bdaddr_t bdaddr; + __u8 dev_class[3]; + __u8 features[8]; + __u16 manufacturer; + __u8 hci_ver; + __u16 hci_rev; +} __packed; + #define MGMT_EV_CMD_COMPLETE 0x0001 struct mgmt_ev_cmd_complete { __le16 opcode; -- cgit v1.1 From c71e97bfaadfa727669fcfcf12301744fd169091 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Mon, 13 Dec 2010 21:07:07 +0200 Subject: Bluetooth: Add management events for controller addition & removal This patch adds Bluetooth Management interface events for controller addition and removal. The events correspond to the existing HCI_DEV_REG and HCI_DEV_UNREG stack internal events. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann Signed-off-by: Gustavo F. Padovan --- include/net/bluetooth/hci_core.h | 2 ++ include/net/bluetooth/mgmt.h | 10 ++++++++++ 2 files changed, 12 insertions(+) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 1992fac..3786ee8 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -662,6 +662,8 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb); /* Management interface */ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t len); +int mgmt_index_added(u16 index); +int mgmt_index_removed(u16 index); /* HCI info for socket */ #define hci_pi(sk) ((struct hci_pinfo *) sk) diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 70985aa..ca29c13 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -75,3 +75,13 @@ struct mgmt_ev_controller_error { __le16 index; __u8 error_code; } __packed; + +#define MGMT_EV_INDEX_ADDED 0x0004 +struct mgmt_ev_index_added { + __le16 index; +} __packed; + +#define MGMT_EV_INDEX_REMOVED 0x0005 +struct mgmt_ev_index_removed { + __le16 index; +} __packed; -- cgit v1.1 From 23bb57633df97ede067ea26f3cdc8a7ba2cd8109 Mon Sep 17 00:00:00 2001 From: Johan Hedberg Date: Tue, 21 Dec 2010 23:01:27 +0200 Subject: Bluetooth: Fix __hci_request synchronization for hci_open_dev The initialization function used by hci_open_dev (hci_init_req) sends many different HCI commands. The __hci_request function should only return when all of these commands have completed (or a timeout occurs). Several of these commands cause hci_req_complete to be called which causes __hci_request to return prematurely. This patch fixes the issue by adding a new hdev->req_last_cmd variable which is set during the initialization procedure. The hci_req_complete function will no longer mark the request as complete until the command matching hdev->req_last_cmd completes. Signed-off-by: Johan Hedberg Acked-by: Marcel Holtmann Signed-off-by: Gustavo F. Padovan --- include/net/bluetooth/hci_core.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 3786ee8..a29feb0 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -129,6 +129,7 @@ struct hci_dev { wait_queue_head_t req_wait_q; __u32 req_status; __u32 req_result; + __u16 req_last_cmd; struct inquiry_cache inq_cache; struct hci_conn_hash conn_hash; @@ -693,6 +694,6 @@ struct hci_sec_filter { #define hci_req_lock(d) mutex_lock(&d->req_lock) #define hci_req_unlock(d) mutex_unlock(&d->req_lock) -void hci_req_complete(struct hci_dev *hdev, int result); +void hci_req_complete(struct hci_dev *hdev, __u16 cmd, int result); #endif /* __HCI_CORE_H */ -- cgit v1.1 From 4e06fd14d5fa78826397c891654a37e5a36ee827 Mon Sep 17 00:00:00 2001 From: Will Newton Date: Tue, 21 Dec 2010 17:24:29 -0800 Subject: include/linux/unaligned: pack the whole struct rather than just the field The current packed struct implementation of unaligned access adds the packed attribute only to the field within the unaligned struct rather than to the struct as a whole. This is not sufficient to enforce proper behaviour on architectures with a default struct alignment of more than one byte. For example, the current implementation of __get_unaligned_cpu16 when compiled for arm with gcc -O1 -mstructure-size-boundary=32 assumes the struct is on a 4 byte boundary so performs the load of the 16bit packed field as if it were on a 4 byte boundary: __get_unaligned_cpu16: ldrh r0, [r0, #0] bx lr Moving the packed attribute to the struct rather than the field causes the proper unaligned access code to be generated: __get_unaligned_cpu16: ldrb r3, [r0, #0] @ zero_extendqisi2 ldrb r0, [r0, #1] @ zero_extendqisi2 orr r0, r3, r0, asl #8 bx lr Signed-off-by: Will Newton Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/unaligned/packed_struct.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/unaligned/packed_struct.h b/include/linux/unaligned/packed_struct.h index 2498bb9..c9a6abd 100644 --- a/include/linux/unaligned/packed_struct.h +++ b/include/linux/unaligned/packed_struct.h @@ -3,9 +3,9 @@ #include -struct __una_u16 { u16 x __attribute__((packed)); }; -struct __una_u32 { u32 x __attribute__((packed)); }; -struct __una_u64 { u64 x __attribute__((packed)); }; +struct __una_u16 { u16 x; } __attribute__((packed)); +struct __una_u32 { u32 x; } __attribute__((packed)); +struct __una_u64 { u64 x; } __attribute__((packed)); static inline u16 __get_unaligned_cpu16(const void *p) { -- cgit v1.1 From 4be2c95d1f7706ca0e74499f2bd118e1cee19669 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Tue, 21 Dec 2010 17:24:30 -0800 Subject: taskstats: pad taskstats netlink response for aligment issues on ia64 The taskstats structure is internally aligned on 8 byte boundaries but the layout of the aggregrate reply, with two NLA headers and the pid (each 4 bytes), actually force the entire structure to be unaligned. This causes the kernel to issue unaligned access warnings on some architectures like ia64. Unfortunately, some software out there doesn't properly unroll the NLA packet and assumes that the start of the taskstats structure will always be 20 bytes from the start of the netlink payload. Aligning the start of the taskstats structure breaks this software, which we don't want. So, for now the alignment only happens on architectures that require it and those users will have to update to fixed versions of those packages. Space is reserved in the packet only when needed. This ifdef should be removed in several years e.g. 2012 once we can be confident that fixed versions are installed on most systems. We add the padding before the aggregate since the aggregate is already a defined type. Commit 85893120 ("delayacct: align to 8 byte boundary on 64-bit systems") previously addressed the alignment issues by padding out the pid field. This was supposed to be a compatible change but the circumstances described above mean that it wasn't. This patch backs out that change, since it was a hack, and introduces a new NULL attribute type to provide the padding. Padding the response with 4 bytes avoids allocating an aligned taskstats structure and copying it back. Since the structure weighs in at 328 bytes, it's too big to do it on the stack. Signed-off-by: Jeff Mahoney Reported-by: Brian Rogers Cc: Jeff Mahoney Cc: Guillaume Chazarain Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/taskstats.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/taskstats.h b/include/linux/taskstats.h index 341dddb..2466e55 100644 --- a/include/linux/taskstats.h +++ b/include/linux/taskstats.h @@ -33,7 +33,7 @@ */ -#define TASKSTATS_VERSION 7 +#define TASKSTATS_VERSION 8 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -188,6 +188,7 @@ enum { TASKSTATS_TYPE_STATS, /* taskstats structure */ TASKSTATS_TYPE_AGGR_PID, /* contains pid + stats */ TASKSTATS_TYPE_AGGR_TGID, /* contains tgid + stats */ + TASKSTATS_TYPE_NULL, /* contains nothing */ __TASKSTATS_TYPE_MAX, }; -- cgit v1.1 From e058464990c2ef1f3ecd6b83a154913c3c06f02a Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Thu, 23 Dec 2010 12:03:57 -0800 Subject: Revert "ipv4: Allow configuring subnets as local addresses" This reverts commit 4465b469008bc03b98a1b8df4e9ae501b6c69d4b. Conflicts: net/ipv4/fib_frontend.c As reported by Ben Greear, this causes regressions: > Change 4465b469008bc03b98a1b8df4e9ae501b6c69d4b caused rules > to stop matching the input device properly because the > FLOWI_FLAG_MATCH_ANY_IIF is always defined in ip_dev_find(). > > This breaks rules such as: > > ip rule add pref 512 lookup local > ip rule del pref 0 lookup local > ip link set eth2 up > ip -4 addr add 172.16.0.102/24 broadcast 172.16.0.255 dev eth2 > ip rule add to 172.16.0.102 iif eth2 lookup local pref 10 > ip rule add iif eth2 lookup 10001 pref 20 > ip route add 172.16.0.0/24 dev eth2 table 10001 > ip route add unreachable 0/0 table 10001 > > If you had a second interface 'eth0' that was on a different > subnet, pinging a system on that interface would fail: > > [root@ct503-60 ~]# ping 192.168.100.1 > connect: Invalid argument Reported-by: Ben Greear Signed-off-by: David S. Miller --- include/net/flow.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/flow.h b/include/net/flow.h index 0ac3fb5..bb08692 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -49,7 +49,6 @@ struct flowi { __u8 proto; __u8 flags; #define FLOWI_FLAG_ANYSRC 0x01 -#define FLOWI_FLAG_MATCH_ANY_IIF 0x02 union { struct { __be16 sport; -- cgit v1.1 From 00aaaef9a51a1a25c5d6d52ce510772f149a0eb0 Mon Sep 17 00:00:00 2001 From: Sheng Yang Date: Thu, 11 Nov 2010 15:46:54 +0800 Subject: PCI: MSI: Move MSI-X entry definition to pci_regs.h Then it can be used by others. Reviewed-by: Hidetoshi Seto Reviewed-by: Matthew Wilcox Signed-off-by: Sheng Yang Signed-off-by: Jesse Barnes --- include/linux/pci_regs.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h index af83076..b21d33e 100644 --- a/include/linux/pci_regs.h +++ b/include/linux/pci_regs.h @@ -309,6 +309,13 @@ #define PCI_MSIX_PBA 8 #define PCI_MSIX_FLAGS_BIRMASK (7 << 0) +/* MSI-X entry's format */ +#define PCI_MSIX_ENTRY_SIZE 16 +#define PCI_MSIX_ENTRY_LOWER_ADDR 0 +#define PCI_MSIX_ENTRY_UPPER_ADDR 4 +#define PCI_MSIX_ENTRY_DATA 8 +#define PCI_MSIX_ENTRY_VECTOR_CTRL 12 + /* CompactPCI Hotswap Register */ #define PCI_CHSWP_CSR 2 /* Control and Status Register */ -- cgit v1.1 From 8d805286968811223cca002134ba3d81244d5313 Mon Sep 17 00:00:00 2001 From: Sheng Yang Date: Thu, 11 Nov 2010 15:46:55 +0800 Subject: PCI: Add mask bit definition for MSI-X table Then we can use it instead of magic number 1. Reviewed-by: Hidetoshi Seto Cc: Matthew Wilcox Signed-off-by: Sheng Yang Signed-off-by: Jesse Barnes --- include/linux/pci_regs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h index b21d33e..d4f2c80 100644 --- a/include/linux/pci_regs.h +++ b/include/linux/pci_regs.h @@ -315,6 +315,7 @@ #define PCI_MSIX_ENTRY_UPPER_ADDR 4 #define PCI_MSIX_ENTRY_DATA 8 #define PCI_MSIX_ENTRY_VECTOR_CTRL 12 +#define PCI_MSIX_ENTRY_CTRL_MASKBIT 1 /* CompactPCI Hotswap Register */ -- cgit v1.1 From 2f671e2dbff6eb5ef4e2600adbec550c13b8fe72 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Mon, 6 Dec 2010 14:00:56 -0500 Subject: PCI: Disable ASPM if BIOS asks us to We currently refuse to touch the ASPM registers if the BIOS tells us that ASPM isn't supported. This can cause problems if the BIOS has (for any reason) enabled ASPM on some devices anyway. Change the code such that we explicitly clear ASPM if the FADT indicates that ASPM isn't supported, and make sure we tidy up appropriately on device removal in order to deal with the hotplug case. If ASPM is disabled because the BIOS doesn't hand over control then we won't touch the registers. Signed-off-by: Matthew Garrett Signed-off-by: Jesse Barnes --- include/linux/pci-aspm.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pci-aspm.h b/include/linux/pci-aspm.h index 91ba0b3..ce68105 100644 --- a/include/linux/pci-aspm.h +++ b/include/linux/pci-aspm.h @@ -27,6 +27,7 @@ extern void pcie_aspm_init_link_state(struct pci_dev *pdev); extern void pcie_aspm_exit_link_state(struct pci_dev *pdev); extern void pcie_aspm_pm_state_change(struct pci_dev *pdev); extern void pci_disable_link_state(struct pci_dev *pdev, int state); +extern void pcie_clear_aspm(void); extern void pcie_no_aspm(void); #else static inline void pcie_aspm_init_link_state(struct pci_dev *pdev) @@ -41,7 +42,9 @@ static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev) static inline void pci_disable_link_state(struct pci_dev *pdev, int state) { } - +static inline void pcie_clear_aspm(void) +{ +} static inline void pcie_no_aspm(void) { } -- cgit v1.1 From 1d3c16a818e992c199844954d95c17fd7ce6cbba Mon Sep 17 00:00:00 2001 From: Jon Mason Date: Tue, 30 Nov 2010 17:43:26 -0600 Subject: PCI: make pci_restore_state return void pci_restore_state only ever returns 0, thus there is no benefit in having it return any value. Also, a large majority of the callers do not check the return code of pci_restore_state. Make the pci_restore_state a void return and avoid the overhead. Acked-by: Mauro Carvalho Chehab Signed-off-by: Jon Mason Signed-off-by: Jesse Barnes --- include/linux/pci.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 7454408..63cbadc 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -806,7 +806,7 @@ size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size); /* Power management related routines */ int pci_save_state(struct pci_dev *dev); -int pci_restore_state(struct pci_dev *dev); +void pci_restore_state(struct pci_dev *dev); int __pci_complete_power_transition(struct pci_dev *dev, pci_power_t state); int pci_set_power_state(struct pci_dev *dev, pci_power_t state); pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state); @@ -1168,10 +1168,8 @@ static inline int pci_save_state(struct pci_dev *dev) return 0; } -static inline int pci_restore_state(struct pci_dev *dev) -{ - return 0; -} +static inline void pci_restore_state(struct pci_dev *dev) +{ } static inline int pci_set_power_state(struct pci_dev *dev, pci_power_t state) { -- cgit v1.1 From 9b444b36fee16d2aaae9cc91ce594ecb15d922a9 Mon Sep 17 00:00:00 2001 From: Seth Heasley Date: Wed, 17 Nov 2010 12:12:08 -0700 Subject: x86/PCI: irq and pci_ids patch for Intel Patsburg This patch adds an additional LPC Controller DeviceID for the Intel Patsburg PCH. Signed-off-by: Seth Heasley Signed-off-by: Jesse Barnes --- include/linux/pci_ids.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index cb845c1..d830106 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2468,7 +2468,8 @@ #define PCI_DEVICE_ID_INTEL_COUGARPOINT_LPC_MIN 0x1c41 #define PCI_DEVICE_ID_INTEL_COUGARPOINT_LPC_MAX 0x1c5f #define PCI_DEVICE_ID_INTEL_PATSBURG_SMBUS 0x1d22 -#define PCI_DEVICE_ID_INTEL_PATSBURG_LPC 0x1d40 +#define PCI_DEVICE_ID_INTEL_PATSBURG_LPC_0 0x1d40 +#define PCI_DEVICE_ID_INTEL_PATSBURG_LPC_1 0x1d41 #define PCI_DEVICE_ID_INTEL_82801AA_0 0x2410 #define PCI_DEVICE_ID_INTEL_82801AA_1 0x2411 #define PCI_DEVICE_ID_INTEL_82801AA_3 0x2413 -- cgit v1.1 From fe31e69740eddc7316071ed5165fed6703c8cd12 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 19 Dec 2010 15:57:16 +0100 Subject: PCI/PCIe: Clear Root PME Status bits early during system resume I noticed that PCI Express PMEs don't work on my Toshiba Portege R500 after the system has been woken up from a sleep state by a PME (through Wake-on-LAN). After some investigation it turned out that the BIOS didn't clear the Root PME Status bit in the root port that received the wakeup PME and since the Requester ID was also set in the port's Root Status register, any subsequent PMEs didn't trigger interrupts. This problem can be avoided by clearing the Root PME Status bits in all PCI Express root ports during early resume. For this purpose, add an early resume routine to the PCIe port driver and make this driver be always registered, even if pci_ports_disable is set (in which case the driver's only function is to provide the early resume callback). Signed-off-by: Rafael J. Wysocki Signed-off-by: Jesse Barnes --- include/linux/pci_regs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h index d4f2c80..5b7e6b1 100644 --- a/include/linux/pci_regs.h +++ b/include/linux/pci_regs.h @@ -504,6 +504,8 @@ #define PCI_EXP_RTCTL_CRSSVE 0x10 /* CRS Software Visibility Enable */ #define PCI_EXP_RTCAP 30 /* Root Capabilities */ #define PCI_EXP_RTSTA 32 /* Root Status */ +#define PCI_EXP_RTSTA_PME 0x10000 /* PME status */ +#define PCI_EXP_RTSTA_PENDING 0x20000 /* PME pending */ #define PCI_EXP_DEVCAP2 36 /* Device Capabilities 2 */ #define PCI_EXP_DEVCAP2_ARI 0x20 /* Alternative Routing-ID */ #define PCI_EXP_DEVCTL2 40 /* Device Control 2 */ -- cgit v1.1 From aab94339cd85d726abeae78fc02351fc1910e6a4 Mon Sep 17 00:00:00 2001 From: Dirk Brandewie Date: Wed, 22 Dec 2010 11:57:26 -0800 Subject: of: Add support for linking device tree blobs into vmlinux This patch adds support for linking device tree blob(s) into vmlinux. Modifies asm-generic/vmlinux.lds.h to add linking .dtb sections into vmlinux. To maintain compatiblity with the of/fdt driver code platforms MUST copy the blob to a non-init memory location before the kernel frees the .init.* sections in the image. Modifies scripts/Makefile.lib to add a kbuild command to compile DTS files to device tree blobs and a rule to create objects to wrap the blobs for linking. STRUCT_ALIGNMENT is defined in vmlinux.lds.h for use in the rule to create wrapper objects for the dtb in Makefile.lib. The STRUCT_ALIGN() macro in vmlinux.lds.h is modified to use the STRUCT_ALIGNMENT definition. The DTB's are placed on 32 byte boundries to allow parsing the blob with driver/of/fdt.c during early boot without having to copy the blob to get the structure alignment GCC expects. A DTB is linked in by adding the DTB object to the list of objects to be linked into vmlinux in the archtecture specific Makefile using obj-y += foo.dtb.o Signed-off-by: Dirk Brandewie Acked-by: Michal Marek [grant.likely@secretlab.ca: cleaned up whitespace inconsistencies] Signed-off-by: Grant Likely --- include/asm-generic/vmlinux.lds.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index bd69d79..05cbad0 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -67,7 +67,8 @@ * Align to a 32 byte boundary equal to the * alignment gcc 4.5 uses for a struct */ -#define STRUCT_ALIGN() . = ALIGN(32) +#define STRUCT_ALIGNMENT 32 +#define STRUCT_ALIGN() . = ALIGN(STRUCT_ALIGNMENT) /* The actual configuration determine if the init/exit sections * are handled as text/data or they can be discarded (which @@ -146,6 +147,13 @@ #define TRACE_SYSCALLS() #endif + +#define KERNEL_DTB() \ + STRUCT_ALIGN(); \ + VMLINUX_SYMBOL(__dtb_start) = .; \ + *(.dtb.init.rodata) \ + VMLINUX_SYMBOL(__dtb_end) = .; + /* .data section */ #define DATA_DATA \ *(.data) \ @@ -468,7 +476,8 @@ MCOUNT_REC() \ DEV_DISCARD(init.rodata) \ CPU_DISCARD(init.rodata) \ - MEM_DISCARD(init.rodata) + MEM_DISCARD(init.rodata) \ + KERNEL_DTB() #define INIT_TEXT \ *(.init.text) \ -- cgit v1.1 From 0131d8973c8b9bd9d40fee8fae24eab24821efdb Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 1 Dec 2010 10:54:46 +0100 Subject: of/address: use proper endianess in get_flags This patch changes u32 to __be32 for all "ranges", "prop" and "addr" and such. Those variables are pointing to the device tree which contains integers in big endian format. Most functions are doing it right because of_read_number() is doing the right thing for them. of_bus_isa_get_flags(), of_bus_pci_get_flags() and of_bus_isa_map() were accessing the data directly and were doing it wrong. Signed-off-by: Sebastian Andrzej Siewior Acked-by: Benjamin Herrenschmidt Signed-off-by: Grant Likely --- include/linux/of_address.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/of_address.h b/include/linux/of_address.h index 8aea06f..2feda6e 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -3,7 +3,7 @@ #include #include -extern u64 of_translate_address(struct device_node *np, const u32 *addr); +extern u64 of_translate_address(struct device_node *np, const __be32 *addr); extern int of_address_to_resource(struct device_node *dev, int index, struct resource *r); extern void __iomem *of_iomap(struct device_node *device, int index); @@ -21,7 +21,7 @@ static inline unsigned long pci_address_to_pio(phys_addr_t addr) { return -1; } #endif #ifdef CONFIG_PCI -extern const u32 *of_get_pci_address(struct device_node *dev, int bar_no, +extern const __be32 *of_get_pci_address(struct device_node *dev, int bar_no, u64 *size, unsigned int *flags); extern int of_pci_address_to_resource(struct device_node *dev, int bar, struct resource *r); @@ -32,7 +32,7 @@ static inline int of_pci_address_to_resource(struct device_node *dev, int bar, return -ENOSYS; } -static inline const u32 *of_get_pci_address(struct device_node *dev, +static inline const __be32 *of_get_pci_address(struct device_node *dev, int bar_no, u64 *size, unsigned int *flags) { return NULL; -- cgit v1.1 From 7063c0d942a1af2993531fbe52b4c74c1db818c4 Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Fri, 24 Dec 2010 13:59:11 +0800 Subject: spi/dw_spi: add DMA support dw_spi driver in upstream only supports PIO mode, and this patch will support it to cowork with the Designware dma controller used on Intel Moorestown platform, at the same time it provides a general framework to support dw_spi core to cowork with dma controllers on other platforms It has been tested with a Option GTM501L 3G modem and Infenion 60x60 modem. To use DMA mode, DMA controller 2 of Moorestown has to be enabled Also change the dma interface suggested by Linus Walleij. Acked-by: Linus Walleij Signed-off-by: Feng Tang [Typo fix and renames to match intel_mid_dma renaming] Signed-off-by: Vinod Koul Signed-off-by: Alan Cox Signed-off-by: Grant Likely --- include/linux/spi/dw_spi.h | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/spi/dw_spi.h b/include/linux/spi/dw_spi.h index c91302f..6cd10f6 100644 --- a/include/linux/spi/dw_spi.h +++ b/include/linux/spi/dw_spi.h @@ -1,5 +1,6 @@ #ifndef DW_SPI_HEADER_H #define DW_SPI_HEADER_H + #include /* Bit fields in CTRLR0 */ @@ -82,6 +83,13 @@ struct dw_spi_reg { though only low 16 bits matters */ } __packed; +struct dw_spi; +struct dw_spi_dma_ops { + int (*dma_init)(struct dw_spi *dws); + void (*dma_exit)(struct dw_spi *dws); + int (*dma_transfer)(struct dw_spi *dws, int cs_change); +}; + struct dw_spi { struct spi_master *master; struct spi_device *cur_dev; @@ -136,13 +144,15 @@ struct dw_spi { /* Dma info */ int dma_inited; struct dma_chan *txchan; + struct scatterlist tx_sgl; struct dma_chan *rxchan; - int txdma_done; - int rxdma_done; - u64 tx_param; - u64 rx_param; + struct scatterlist rx_sgl; + int dma_chan_done; struct device *dma_dev; - dma_addr_t dma_addr; + dma_addr_t dma_addr; /* phy address of the Data register */ + struct dw_spi_dma_ops *dma_ops; + void *dma_priv; /* platform relate info */ + struct pci_dev *dmac; /* Bus interface info */ void *priv; @@ -216,4 +226,8 @@ extern int dw_spi_add_host(struct dw_spi *dws); extern void dw_spi_remove_host(struct dw_spi *dws); extern int dw_spi_suspend_host(struct dw_spi *dws); extern int dw_spi_resume_host(struct dw_spi *dws); +extern void dw_spi_xfer_done(struct dw_spi *dws); + +/* platform related setup */ +extern int dw_spi_mid_init(struct dw_spi *dws); /* Intel MID platforms */ #endif /* DW_SPI_HEADER_H */ -- cgit v1.1 From c7b61de5b7b17f0df34dc7d2f8b9576f8bd36fce Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Wed, 1 Dec 2010 00:14:42 +0100 Subject: PM / Runtime: Add synchronous runtime interface for interrupt handlers (v3) This patch (as1431c) makes the synchronous runtime-PM interface suitable for use in interrupt handlers. Subsystems can call the new pm_runtime_irq_safe() function to tell the PM core that a device's runtime_suspend and runtime_resume callbacks should be invoked with interrupts disabled and the spinlock held. This permits the pm_runtime_get_sync() and the new pm_runtime_put_sync_suspend() routines to be called from within interrupt handlers. When a device is declared irq-safe in this way, the PM core increments the parent's usage count, so the parent will never be runtime suspended. This prevents difficult situations in which an irq-safe device can't resume because it is forced to wait for its non-irq-safe parent. Signed-off-by: Alan Stern Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 1 + include/linux/pm_runtime.h | 7 +++++++ 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/pm.h b/include/linux/pm.h index 40f3f45..61f2066 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -486,6 +486,7 @@ struct dev_pm_info { unsigned int run_wake:1; unsigned int runtime_auto:1; unsigned int no_callbacks:1; + unsigned int irq_safe:1; unsigned int use_autosuspend:1; unsigned int timer_autosuspends:1; enum rpm_request request; diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index d19f1cc..e9cc049 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -40,6 +40,7 @@ extern int pm_generic_runtime_idle(struct device *dev); extern int pm_generic_runtime_suspend(struct device *dev); extern int pm_generic_runtime_resume(struct device *dev); extern void pm_runtime_no_callbacks(struct device *dev); +extern void pm_runtime_irq_safe(struct device *dev); extern void __pm_runtime_use_autosuspend(struct device *dev, bool use); extern void pm_runtime_set_autosuspend_delay(struct device *dev, int delay); extern unsigned long pm_runtime_autosuspend_expiration(struct device *dev); @@ -124,6 +125,7 @@ static inline int pm_generic_runtime_idle(struct device *dev) { return 0; } static inline int pm_generic_runtime_suspend(struct device *dev) { return 0; } static inline int pm_generic_runtime_resume(struct device *dev) { return 0; } static inline void pm_runtime_no_callbacks(struct device *dev) {} +static inline void pm_runtime_irq_safe(struct device *dev) {} static inline void pm_runtime_mark_last_busy(struct device *dev) {} static inline void __pm_runtime_use_autosuspend(struct device *dev, @@ -196,6 +198,11 @@ static inline int pm_runtime_put_sync(struct device *dev) return __pm_runtime_idle(dev, RPM_GET_PUT); } +static inline int pm_runtime_put_sync_suspend(struct device *dev) +{ + return __pm_runtime_suspend(dev, RPM_GET_PUT); +} + static inline int pm_runtime_put_sync_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_AUTO); -- cgit v1.1 From a2867e08c8e3bdbc00caf56bc3bdde19ccc058e3 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 3 Dec 2010 22:58:31 +0100 Subject: PM / Wakeup: Replace pm_check_wakeup_events() with pm_wakeup_pending() To avoid confusion with the meaning and return value of pm_check_wakeup_events() replace it with pm_wakeup_pending() that will work the other way around (ie. return true when system-wide power transition should be aborted). Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 2669751..144b34b 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -292,7 +292,7 @@ extern int unregister_pm_notifier(struct notifier_block *nb); /* drivers/base/power/wakeup.c */ extern bool events_check_enabled; -extern bool pm_check_wakeup_events(void); +extern bool pm_wakeup_pending(void); extern bool pm_get_wakeup_count(unsigned int *count); extern bool pm_save_wakeup_count(unsigned int count); #else /* !CONFIG_PM_SLEEP */ @@ -309,7 +309,7 @@ static inline int unregister_pm_notifier(struct notifier_block *nb) #define pm_notifier(fn, pri) do { (void)(fn); } while (0) -static inline bool pm_check_wakeup_events(void) { return true; } +static inline bool pm_wakeup_pending(void) { return false; } #endif /* !CONFIG_PM_SLEEP */ extern struct mutex pm_mutex; -- cgit v1.1 From b8c76f6aed0ab7df73a6410f3f82de2c831bb144 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 16 Dec 2010 00:51:21 +0100 Subject: PM: Replace the device power.status field with a bit field The device power.status field is too complicated for its purpose (storing the information about whether or not the device is in the "active" state from the PM core's point of view), so replace it with a bit field and modify all of its users accordingly. Signed-off-by: Rafael J. Wysocki --- include/linux/device.h | 4 ++-- include/linux/pm.h | 43 ++----------------------------------------- 2 files changed, 4 insertions(+), 43 deletions(-) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index dd48953..45bc8c1 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -508,13 +508,13 @@ static inline int device_is_registered(struct device *dev) static inline void device_enable_async_suspend(struct device *dev) { - if (dev->power.status == DPM_ON) + if (!dev->power.in_suspend) dev->power.async_suspend = true; } static inline void device_disable_async_suspend(struct device *dev) { - if (dev->power.status == DPM_ON) + if (!dev->power.in_suspend) dev->power.async_suspend = false; } diff --git a/include/linux/pm.h b/include/linux/pm.h index 61f2066..c1756df 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -367,45 +367,6 @@ extern struct dev_pm_ops generic_subsys_pm_ops; { .event = PM_EVENT_AUTO_RESUME, }) /** - * Device power management states - * - * These state labels are used internally by the PM core to indicate the current - * status of a device with respect to the PM core operations. - * - * DPM_ON Device is regarded as operational. Set this way - * initially and when ->complete() is about to be called. - * Also set when ->prepare() fails. - * - * DPM_PREPARING Device is going to be prepared for a PM transition. Set - * when ->prepare() is about to be called. - * - * DPM_RESUMING Device is going to be resumed. Set when ->resume(), - * ->thaw(), or ->restore() is about to be called. - * - * DPM_SUSPENDING Device has been prepared for a power transition. Set - * when ->prepare() has just succeeded. - * - * DPM_OFF Device is regarded as inactive. Set immediately after - * ->suspend(), ->freeze(), or ->poweroff() has succeeded. - * Also set when ->resume()_noirq, ->thaw_noirq(), or - * ->restore_noirq() is about to be called. - * - * DPM_OFF_IRQ Device is in a "deep sleep". Set immediately after - * ->suspend_noirq(), ->freeze_noirq(), or - * ->poweroff_noirq() has just succeeded. - */ - -enum dpm_state { - DPM_INVALID, - DPM_ON, - DPM_PREPARING, - DPM_RESUMING, - DPM_SUSPENDING, - DPM_OFF, - DPM_OFF_IRQ, -}; - -/** * Device run-time power management status. * * These status labels are used internally by the PM core to indicate the @@ -463,8 +424,8 @@ struct wakeup_source; struct dev_pm_info { pm_message_t power_state; unsigned int can_wakeup:1; - unsigned async_suspend:1; - enum dpm_state status; /* Owned by the PM core */ + unsigned int async_suspend:1; + unsigned int in_suspend:1; /* Owned by the PM core */ spinlock_t lock; #ifdef CONFIG_PM_SLEEP struct list_head entry; -- cgit v1.1 From 4b31db8a16fa0d4d6a0fa42d044e7a4f4dad3641 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 24 Dec 2010 15:04:06 +0100 Subject: PM / Runtime: Generic resume shouldn't set RPM_ACTIVE unconditionally The __pm_generic_resume() function changes the given device's runtime PM status to RPM_ACTIVE if its driver's callback returns 0, but it only should do that if the rumtime PM is enabled for the device. Signed-off-by: Rafael J. Wysocki --- include/linux/pm_runtime.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index e9cc049..d34f067 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -82,6 +82,11 @@ static inline bool pm_runtime_suspended(struct device *dev) && !dev->power.disable_depth; } +static inline bool pm_runtime_enabled(struct device *dev) +{ + return !dev->power.disable_depth; +} + static inline void pm_runtime_mark_last_busy(struct device *dev) { ACCESS_ONCE(dev->power.last_busy) = jiffies; @@ -120,6 +125,7 @@ static inline void pm_runtime_put_noidle(struct device *dev) {} static inline bool device_run_wake(struct device *dev) { return false; } static inline void device_set_run_wake(struct device *dev, bool enable) {} static inline bool pm_runtime_suspended(struct device *dev) { return false; } +static inline bool pm_runtime_enabled(struct device *dev) { return false; } static inline int pm_generic_runtime_idle(struct device *dev) { return 0; } static inline int pm_generic_runtime_suspend(struct device *dev) { return 0; } -- cgit v1.1 From 62bcb91573425975d6ad2389d7ab1d8feca88ab4 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 24 Dec 2010 15:04:41 +0100 Subject: PM: Prototype the pm_generic_ operations The pm_generic_ operations are all exported but are not prototyped in any header file for direct use. Do so. [rjw: Added extern.] Signed-off-by: Mark Brown Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/pm.h b/include/linux/pm.h index c1756df..dd9c7ab 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -572,4 +572,11 @@ extern unsigned int pm_flags; #define PM_APM 1 #define PM_ACPI 2 +extern int pm_generic_suspend(struct device *dev); +extern int pm_generic_resume(struct device *dev); +extern int pm_generic_freeze(struct device *dev); +extern int pm_generic_thaw(struct device *dev); +extern int pm_generic_restore(struct device *dev); +extern int pm_generic_poweroff(struct device *dev); + #endif /* _LINUX_PM_H */ -- cgit v1.1 From 00df055ae315c9c8792dc4d012e6ad9c4d527e87 Mon Sep 17 00:00:00 2001 From: Jarkko Nikula Date: Fri, 29 Oct 2010 11:31:39 -0300 Subject: [media] radio-si4713: Add regulator framework support Convert the driver to use regulator framework instead of set_power callback. This with gpio_reset platform data provide cleaner way to manage chip VIO, VDD and reset signal inside the driver. Signed-off-by: Jarkko Nikula Cc: Eduardo Valentin Signed-off-by: Mauro Carvalho Chehab --- include/media/si4713.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/si4713.h b/include/media/si4713.h index 99850a5..ed7353e 100644 --- a/include/media/si4713.h +++ b/include/media/si4713.h @@ -23,8 +23,7 @@ * Platform dependent definition */ struct si4713_platform_data { - /* Set power state, zero is off, non-zero is on. */ - int (*set_power)(int power); + int gpio_reset; /* < 0 if not used */ }; /* -- cgit v1.1 From 2997137be8eba5bf9c07a24d5fda1f4225f9ca7d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?David=20H=C3=A4rdeman?= Date: Fri, 29 Oct 2010 16:08:02 -0300 Subject: [media] ir-core: convert drivers/media/video/cx88 to ir-core MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch converts the cx88 driver (for sampling hw) to use the decoders provided by ir-core instead of the separate ones provided by ir-functions (and gets rid of those). The value for MO_DDS_IO had a comment saying it corresponded to a 4kHz samplerate. That comment was unfortunately misleading. The actual samplerate was something like 3250Hz. The current value has been derived by analyzing the elapsed time between interrupts for different values (knowing that each interrupt corresponds to 32 samples). Thanks to Mariusz Bialonczyk for testing my patches (about one a day for two weeks!) on actual hardware. Signed-off-by: David Härdeman Acked-by: Jarod Wilson Signed-off-by: Mauro Carvalho Chehab --- include/media/ir-common.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/media/ir-common.h b/include/media/ir-common.h index 528050e..4152420 100644 --- a/include/media/ir-common.h +++ b/include/media/ir-common.h @@ -96,9 +96,6 @@ void ir_input_nokey(struct input_dev *dev, struct ir_input_state *ir); void ir_input_keydown(struct input_dev *dev, struct ir_input_state *ir, u32 ir_key); u32 ir_extract_bits(u32 data, u32 mask); -int ir_dump_samples(u32 *samples, int count); -int ir_decode_biphase(u32 *samples, int count, int low, int high); -int ir_decode_pulsedistance(u32 *samples, int count, int low, int high); u32 ir_rc5_decode(unsigned int code); void ir_rc5_timer_end(unsigned long data); -- cgit v1.1 From 62c6503125389763a74911408d984c5dd09eeb97 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?David=20H=C3=83=C2=A4rdeman?= Date: Fri, 29 Oct 2010 16:08:07 -0300 Subject: [media] ir-core: remove remaining users of the ir-functions keyhandlers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch removes the remaining usages of the ir_input_nokey() and ir_input_keydown() functions provided by drivers/media/IR/ir-functions.c by using the corresponding functionality in ir-core instead. Signed-off-by: David Härdeman Acked-by: Jarod Wilson Signed-off-by: Mauro Carvalho Chehab --- include/media/ir-common.h | 31 +++---------------------------- include/media/ir-core.h | 3 ++- include/media/ir-kbd-i2c.h | 4 ++-- 3 files changed, 7 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/include/media/ir-common.h b/include/media/ir-common.h index 4152420..4a32e89 100644 --- a/include/media/ir-common.h +++ b/include/media/ir-common.h @@ -1,7 +1,7 @@ /* - * - * some common structs and functions to handle infrared remotes via - * input layer ... + * some common functions to handle infrared remote protocol decoding for + * drivers which have not yet been (or can't be) converted to use the + * regular protocol decoders... * * (c) 2003 Gerd Knorr [SuSE Labs] * @@ -33,30 +33,17 @@ #define RC5_ADDR(x) (((x)>>6)&31) #define RC5_INSTR(x) ((x)&63) -struct ir_input_state { - /* configuration */ - u64 ir_type; - - /* key info */ - u32 ir_key; /* ir scancode */ - u32 keycode; /* linux key code */ - int keypressed; /* current state */ -}; - /* this was saa7134_ir and bttv_ir, moved here for * rc5 decoding. */ struct card_ir { struct input_dev *dev; - struct ir_input_state ir; char name[32]; char phys[32]; int users; - u32 running:1; struct ir_dev_props props; /* Usual gpio signalling */ - u32 mask_keycode; u32 mask_keydown; u32 mask_keyup; @@ -65,7 +52,6 @@ struct card_ir { int shift_by; int start; // What should RC5_START() be int addr; // What RC5_ADDR() should be. - int rc5_key_timeout; int rc5_remote_gap; struct work_struct work; struct timer_list timer; @@ -73,8 +59,6 @@ struct card_ir { /* RC5 gpio */ u32 rc5_gpio; struct timer_list timer_end; /* timer_end for code completion */ - struct timer_list timer_keyup; /* timer_end for key release */ - u32 last_rc5; /* last good rc5 code */ u32 last_bit; /* last raw bit seen */ u32 code; /* raw code under construction */ struct timeval base_time; /* time of last seen code */ @@ -89,16 +73,7 @@ struct card_ir { }; /* Routines from ir-functions.c */ - -int ir_input_init(struct input_dev *dev, struct ir_input_state *ir, - const u64 ir_type); -void ir_input_nokey(struct input_dev *dev, struct ir_input_state *ir); -void ir_input_keydown(struct input_dev *dev, struct ir_input_state *ir, - u32 ir_key); u32 ir_extract_bits(u32 data, u32 mask); -u32 ir_rc5_decode(unsigned int code); - void ir_rc5_timer_end(unsigned long data); -void ir_rc5_timer_keyup(unsigned long data); #endif diff --git a/include/media/ir-core.h b/include/media/ir-core.h index 6dc37fa..bff75f2 100644 --- a/include/media/ir-core.h +++ b/include/media/ir-core.h @@ -159,7 +159,8 @@ void ir_input_unregister(struct input_dev *input_dev); void ir_repeat(struct input_dev *dev); void ir_keydown(struct input_dev *dev, int scancode, u8 toggle); -void ir_keyup(struct ir_input_dev *ir); +void ir_keydown_notimeout(struct input_dev *dev, int scancode, u8 toggle); +void ir_keyup(struct input_dev *dev); u32 ir_g_keycode_from_table(struct input_dev *input_dev, u32 scancode); /* From ir-raw-event.c */ diff --git a/include/media/ir-kbd-i2c.h b/include/media/ir-kbd-i2c.h index 557c676..8c37b5e 100644 --- a/include/media/ir-kbd-i2c.h +++ b/include/media/ir-kbd-i2c.h @@ -12,8 +12,7 @@ struct IR_i2c { struct i2c_client *c; struct input_dev *input; - struct ir_input_state ir; - u64 ir_type; + /* Used to avoid fast repeating */ unsigned char old; @@ -41,6 +40,7 @@ struct IR_i2c_init_data { const char *name; u64 type; /* IR_TYPE_RC5, etc */ u32 polling_interval; /* 0 means DEFAULT_POLLING_INTERVAL */ + /* * Specify either a function pointer or a value indicating one of * ir_kbd_i2c's internal get_key functions -- cgit v1.1 From 3ffea4988be3f3fa65f2104ba31eff2b5e0e82a0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?David=20H=C3=83=C2=A4rdeman?= Date: Fri, 29 Oct 2010 16:08:12 -0300 Subject: [media] ir-core: more cleanups of ir-functions.c MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit cx88 only depends on VIDEO_IR because it needs ir_extract_bits(). Move that function to ir-core.h and make it inline. Lots of drivers had dependencies on VIDEO_IR when they really wanted IR_CORE. The only remaining drivers to depend on VIDEO_IR are bt8xx and saa7134 (ir_rc5_timer_end is the only function exported by ir-functions). Rename VIDEO_IR -> IR_LEGACY to give a hint to anyone writing or converting drivers to IR_CORE that they do not want a dependency on IR_LEGACY. Signed-off-by: David Härdeman Acked-by: Jarod Wilson Signed-off-by: Mauro Carvalho Chehab --- include/media/ir-common.h | 1 - include/media/ir-core.h | 19 +++++++++++++++++++ 2 files changed, 19 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/ir-common.h b/include/media/ir-common.h index 4a32e89..d1ae869 100644 --- a/include/media/ir-common.h +++ b/include/media/ir-common.h @@ -73,7 +73,6 @@ struct card_ir { }; /* Routines from ir-functions.c */ -u32 ir_extract_bits(u32 data, u32 mask); void ir_rc5_timer_end(unsigned long data); #endif diff --git a/include/media/ir-core.h b/include/media/ir-core.h index bff75f2..53048a2 100644 --- a/include/media/ir-core.h +++ b/include/media/ir-core.h @@ -212,4 +212,23 @@ static inline void ir_raw_event_reset(struct input_dev *input_dev) ir_raw_event_handle(input_dev); } + +/* extract mask bits out of data and pack them into the result */ +static inline u32 ir_extract_bits(u32 data, u32 mask) +{ + u32 vbit = 1, value = 0; + + do { + if (mask & 1) { + if (data & 1) + value |= vbit; + vbit <<= 1; + } + data >>= 1; + } while (mask >>= 1); + + return value; +} + + #endif /* _IR_CORE */ -- cgit v1.1 From 4c7b355df6e7f05304e05f6b7a286e59a5f1cc54 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?David=20H=C3=A4rdeman?= Date: Wed, 10 Nov 2010 11:04:19 -0300 Subject: [media] rc-core: Code cleanup after merging rc-sysfs and rc-map into rc-main MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [mchehab@redhat.com: this patch were originally bundled with some renaming stuff and with the file merges, as seen at: https://patchwork.kernel.org/patch/291092/. Instead of using the original approach, I wrote the rename patches and the code merge as separate changes, then applied the difference on this patch. This way, it is easier to see the real changes at the code, and will be easier to merge upstream, especially if some conflict rises on the renaming patches] Signed-off-by: David Härdeman Acked-by: Jarod Wilson Tested-by: Jarod Wilson Signed-off-by: Mauro Carvalho Chehab --- include/media/ir-core.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/media/ir-core.h b/include/media/ir-core.h index 53048a2..d41502d 100644 --- a/include/media/ir-core.h +++ b/include/media/ir-core.h @@ -117,7 +117,6 @@ enum raw_event_type { #define to_ir_input_dev(_attr) container_of(_attr, struct ir_input_dev, attr) -/* From ir-keytable.c */ int __ir_input_register(struct input_dev *dev, const struct ir_scancode_table *ir_codes, struct ir_dev_props *props, @@ -164,7 +163,6 @@ void ir_keyup(struct input_dev *dev); u32 ir_g_keycode_from_table(struct input_dev *input_dev, u32 scancode); /* From ir-raw-event.c */ - struct ir_raw_event { union { u32 duration; -- cgit v1.1 From d8b4b5822f51e2142b731b42c81e3f03eec475b2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?David=20H=C3=83=C2=A4rdeman?= Date: Fri, 29 Oct 2010 16:08:23 -0300 Subject: [media] ir-core: make struct rc_dev the primary interface MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch merges the ir_input_dev and ir_dev_props structs into a single struct called rc_dev. The drivers and various functions in rc-core used by the drivers are also changed to use rc_dev as the primary interface when dealing with rc-core. This means that the input_dev is abstracted away from the drivers which is necessary if we ever want to support multiple input devs per rc device. The new API is similar to what the input subsystem uses, i.e: rc_device_alloc() rc_device_free() rc_device_register() rc_device_unregister() [mchehab@redhat.com: Fix compilation on mceusb and cx231xx, due to merge conflicts] Signed-off-by: David Härdeman Acked-by: Jarod Wilson Tested-by: Jarod Wilson Signed-off-by: Mauro Carvalho Chehab --- include/media/ir-common.h | 3 +- include/media/ir-core.h | 181 ++++++++++++++++++++------------------------- include/media/ir-kbd-i2c.h | 3 +- 3 files changed, 82 insertions(+), 105 deletions(-) (limited to 'include') diff --git a/include/media/ir-common.h b/include/media/ir-common.h index d1ae869..41fefd9 100644 --- a/include/media/ir-common.h +++ b/include/media/ir-common.h @@ -36,12 +36,11 @@ /* this was saa7134_ir and bttv_ir, moved here for * rc5 decoding. */ struct card_ir { - struct input_dev *dev; + struct rc_dev *dev; char name[32]; char phys[32]; int users; u32 running:1; - struct ir_dev_props props; /* Usual gpio signalling */ u32 mask_keycode; diff --git a/include/media/ir-core.h b/include/media/ir-core.h index d41502d..c590998 100644 --- a/include/media/ir-core.h +++ b/include/media/ir-core.h @@ -32,21 +32,38 @@ enum rc_driver_type { }; /** - * struct ir_dev_props - Allow caller drivers to set special properties - * @driver_type: specifies if the driver or hardware have already a decoder, - * or if it needs to use the IR raw event decoders to produce a scancode + * struct rc_dev - represents a remote control device + * @dev: driver model's view of this device + * @input_name: name of the input child device + * @input_phys: physical path to the input child device + * @input_id: id of the input child device (struct input_id) + * @driver_name: name of the hardware driver which registered this device + * @map_name: name of the default keymap + * @rc_tab: current scan/key table + * @devno: unique remote control device number + * @raw: additional data for raw pulse/space devices + * @input_dev: the input child device used to communicate events to userspace + * @driver_type: specifies if protocol decoding is done in hardware or software + * @idle: used to keep track of RX state * @allowed_protos: bitmask with the supported IR_TYPE_* protocols * @scanmask: some hardware decoders are not capable of providing the full * scancode to the application. As this is a hardware limit, we can't do * anything with it. Yet, as the same keycode table can be used with other * devices, a mask is provided to allow its usage. Drivers should generally * leave this field in blank + * @priv: driver-specific data + * @keylock: protects the remaining members of the struct + * @keypressed: whether a key is currently pressed + * @keyup_jiffies: time (in jiffies) when the current keypress should be released + * @timer_keyup: timer for releasing a keypress + * @last_keycode: keycode of last keypress + * @last_scancode: scancode of last keypress + * @last_toggle: toggle value of last command * @timeout: optional time after which device stops sending data * @min_timeout: minimum timeout supported by device * @max_timeout: maximum timeout supported by device * @rx_resolution : resolution (in ns) of input sampler * @tx_resolution: resolution (in ns) of output sampler - * @priv: driver-specific data, to be used on the callbacks * @change_protocol: allow changing the protocol used on hardware decoders * @open: callback to allow drivers to enable polling/irq when IR input device * is opened. @@ -57,55 +74,50 @@ enum rc_driver_type { * @s_tx_duty_cycle: set transmit duty cycle (0% - 100%) * @s_rx_carrier: inform driver about carrier it is expected to handle * @tx_ir: transmit IR - * @s_idle: optional: enable/disable hardware idle mode, upon which, - device doesn't interrupt host until it sees IR pulses + * @s_idle: enable/disable hardware idle mode, upon which, + * device doesn't interrupt host until it sees IR pulses * @s_learning_mode: enable wide band receiver used for learning * @s_carrier_report: enable carrier reports */ -struct ir_dev_props { - enum rc_driver_type driver_type; - unsigned long allowed_protos; - u32 scanmask; - - u32 timeout; - u32 min_timeout; - u32 max_timeout; - - u32 rx_resolution; - u32 tx_resolution; - - void *priv; - int (*change_protocol)(void *priv, u64 ir_type); - int (*open)(void *priv); - void (*close)(void *priv); - int (*s_tx_mask)(void *priv, u32 mask); - int (*s_tx_carrier)(void *priv, u32 carrier); - int (*s_tx_duty_cycle)(void *priv, u32 duty_cycle); - int (*s_rx_carrier_range)(void *priv, u32 min, u32 max); - int (*tx_ir)(void *priv, int *txbuf, u32 n); - void (*s_idle)(void *priv, bool enable); - int (*s_learning_mode)(void *priv, int enable); - int (*s_carrier_report) (void *priv, int enable); -}; - -struct ir_input_dev { - struct device dev; /* device */ - char *driver_name; /* Name of the driver module */ - struct ir_scancode_table rc_tab; /* scan/key table */ - unsigned long devno; /* device number */ - struct ir_dev_props *props; /* Device properties */ - struct ir_raw_event_ctrl *raw; /* for raw pulse/space events */ - struct input_dev *input_dev; /* the input device associated with this device */ +struct rc_dev { + struct device dev; + const char *input_name; + const char *input_phys; + struct input_id input_id; + char *driver_name; + const char *map_name; + struct ir_scancode_table rc_tab; + unsigned long devno; + struct ir_raw_event_ctrl *raw; + struct input_dev *input_dev; + enum rc_driver_type driver_type; bool idle; - - /* key info - needed by IR keycode handlers */ - spinlock_t keylock; /* protects the below members */ - bool keypressed; /* current state */ - unsigned long keyup_jiffies; /* when should the current keypress be released? */ - struct timer_list timer_keyup; /* timer for releasing a keypress */ - u32 last_keycode; /* keycode of last command */ - u32 last_scancode; /* scancode of last command */ - u8 last_toggle; /* toggle of last command */ + u64 allowed_protos; + u32 scanmask; + void *priv; + spinlock_t keylock; + bool keypressed; + unsigned long keyup_jiffies; + struct timer_list timer_keyup; + u32 last_keycode; + u32 last_scancode; + u8 last_toggle; + u32 timeout; + u32 min_timeout; + u32 max_timeout; + u32 rx_resolution; + u32 tx_resolution; + int (*change_protocol)(struct rc_dev *dev, u64 ir_type); + int (*open)(struct rc_dev *dev); + void (*close)(struct rc_dev *dev); + int (*s_tx_mask)(struct rc_dev *dev, u32 mask); + int (*s_tx_carrier)(struct rc_dev *dev, u32 carrier); + int (*s_tx_duty_cycle)(struct rc_dev *dev, u32 duty_cycle); + int (*s_rx_carrier_range)(struct rc_dev *dev, u32 min, u32 max); + int (*tx_ir)(struct rc_dev *dev, int *txbuf, u32 n); + void (*s_idle)(struct rc_dev *dev, bool enable); + int (*s_learning_mode)(struct rc_dev *dev, int enable); + int (*s_carrier_report) (struct rc_dev *dev, int enable); }; enum raw_event_type { @@ -115,52 +127,14 @@ enum raw_event_type { IR_STOP_EVENT = (1 << 3), }; -#define to_ir_input_dev(_attr) container_of(_attr, struct ir_input_dev, attr) - -int __ir_input_register(struct input_dev *dev, - const struct ir_scancode_table *ir_codes, - struct ir_dev_props *props, - const char *driver_name); - -static inline int ir_input_register(struct input_dev *dev, - const char *map_name, - struct ir_dev_props *props, - const char *driver_name) { - struct ir_scancode_table *ir_codes; - struct ir_input_dev *ir_dev; - int rc; - - if (!map_name) - return -EINVAL; - - ir_codes = get_rc_map(map_name); - if (!ir_codes) { - ir_codes = get_rc_map(RC_MAP_EMPTY); +#define to_rc_dev(d) container_of(d, struct rc_dev, dev) - if (!ir_codes) - return -EINVAL; - } - rc = __ir_input_register(dev, ir_codes, props, driver_name); - if (rc < 0) - return -EINVAL; - - ir_dev = input_get_drvdata(dev); - - if (!rc && ir_dev->props && ir_dev->props->change_protocol) - rc = ir_dev->props->change_protocol(ir_dev->props->priv, - ir_codes->ir_type); - - return rc; -} - -void ir_input_unregister(struct input_dev *input_dev); - -void ir_repeat(struct input_dev *dev); -void ir_keydown(struct input_dev *dev, int scancode, u8 toggle); -void ir_keydown_notimeout(struct input_dev *dev, int scancode, u8 toggle); -void ir_keyup(struct input_dev *dev); -u32 ir_g_keycode_from_table(struct input_dev *input_dev, u32 scancode); +void ir_repeat(struct rc_dev *dev); +void ir_keydown(struct rc_dev *dev, int scancode, u8 toggle); +void ir_keydown_notimeout(struct rc_dev *dev, int scancode, u8 toggle); +void ir_keyup(struct rc_dev *dev); +u32 ir_g_keycode_from_table(struct rc_dev *dev, u32 scancode); /* From ir-raw-event.c */ struct ir_raw_event { @@ -194,20 +168,25 @@ static inline void init_ir_raw_event(struct ir_raw_event *ev) #define IR_MAX_DURATION 0xFFFFFFFF /* a bit more than 4 seconds */ -void ir_raw_event_handle(struct input_dev *input_dev); -int ir_raw_event_store(struct input_dev *input_dev, struct ir_raw_event *ev); -int ir_raw_event_store_edge(struct input_dev *input_dev, enum raw_event_type type); -int ir_raw_event_store_with_filter(struct input_dev *input_dev, +struct rc_dev *rc_allocate_device(void); +void rc_free_device(struct rc_dev *dev); +int rc_register_device(struct rc_dev *dev); +void rc_unregister_device(struct rc_dev *dev); + +void ir_raw_event_handle(struct rc_dev *dev); +int ir_raw_event_store(struct rc_dev *dev, struct ir_raw_event *ev); +int ir_raw_event_store_edge(struct rc_dev *dev, enum raw_event_type type); +int ir_raw_event_store_with_filter(struct rc_dev *dev, struct ir_raw_event *ev); -void ir_raw_event_set_idle(struct input_dev *input_dev, bool idle); +void ir_raw_event_set_idle(struct rc_dev *dev, bool idle); -static inline void ir_raw_event_reset(struct input_dev *input_dev) +static inline void ir_raw_event_reset(struct rc_dev *dev) { DEFINE_IR_RAW_EVENT(ev); ev.reset = true; - ir_raw_event_store(input_dev, &ev); - ir_raw_event_handle(input_dev); + ir_raw_event_store(dev, &ev); + ir_raw_event_handle(dev); } diff --git a/include/media/ir-kbd-i2c.h b/include/media/ir-kbd-i2c.h index 8c37b5e..4ee9b42 100644 --- a/include/media/ir-kbd-i2c.h +++ b/include/media/ir-kbd-i2c.h @@ -9,9 +9,8 @@ struct IR_i2c; struct IR_i2c { char *ir_codes; - struct i2c_client *c; - struct input_dev *input; + struct rc_dev *rc; /* Used to avoid fast repeating */ unsigned char old; -- cgit v1.1 From 2eb258327722de3ed4d84ce1b9add2bad21a0ec4 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 12 Nov 2010 09:02:40 -0300 Subject: [media] ir-kbd-i2c: add rc_dev as a parameter to the driver There are several fields on rc_dev that drivers can benefit. Allow drivers to pass it as a parameter to the driver. For now, the rc_dev parameter is optional. If drivers don't pass it, create them internally. However, the best is to create rc_dev inside the drivers, in order to fill other fields, like open(), close(), driver_name, etc. So, a latter patch making it mandatory and changing the caller drivers is welcome. Signed-off-by: Mauro Carvalho Chehab --- include/media/ir-kbd-i2c.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/media/ir-kbd-i2c.h b/include/media/ir-kbd-i2c.h index 4ee9b42..aca015e 100644 --- a/include/media/ir-kbd-i2c.h +++ b/include/media/ir-kbd-i2c.h @@ -46,5 +46,7 @@ struct IR_i2c_init_data { */ int (*get_key)(struct IR_i2c*, u32*, u32*); enum ir_kbd_get_key_fn internal_get_key_func; + + struct rc_dev *rc_dev; }; #endif -- cgit v1.1 From 9eae42e5a216059a146b3fbbe24b4fdc0b10c723 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Richard=20R=C3=B6jfors?= Date: Mon, 8 Nov 2010 10:45:44 -0300 Subject: [media] media: Add timberdale video-in driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds the timberdale video-in driver. The video IP of timberdale delivers the video data via DMA. The driver uses the DMA api to handle DMA transfers, and make use of the V4L2 video buffers to handle buffers against user space. If available the driver uses an encoder to get/set the video standard Signed-off-by: Richard Röjfors Signed-off-by: Mauro Carvalho Chehab --- include/media/timb_radio.h | 1 - include/media/timb_video.h | 33 +++++++++++++++++++++++++++++++++ 2 files changed, 33 insertions(+), 1 deletion(-) create mode 100644 include/media/timb_video.h (limited to 'include') diff --git a/include/media/timb_radio.h b/include/media/timb_radio.h index fcd32a3..a59a848 100644 --- a/include/media/timb_radio.h +++ b/include/media/timb_radio.h @@ -24,7 +24,6 @@ struct timb_radio_platform_data { int i2c_adapter; /* I2C adapter where the tuner and dsp are attached */ struct { - const char *module_name; struct i2c_board_info *info; } tuner; struct { diff --git a/include/media/timb_video.h b/include/media/timb_video.h new file mode 100644 index 0000000..70ae439 --- /dev/null +++ b/include/media/timb_video.h @@ -0,0 +1,33 @@ +/* + * timb_video.h Platform struct for the Timberdale video driver + * Copyright (c) 2009-2010 Intel Corporation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#ifndef _TIMB_VIDEO_ +#define _TIMB_VIDEO_ 1 + +#include + +struct timb_video_platform_data { + int dma_channel; + int i2c_adapter; /* The I2C adapter where the encoder is attached */ + struct { + const char *module_name; + struct i2c_board_info *info; + } encoder; +}; + +#endif -- cgit v1.1 From a6e3b81f6198654207c4e972e7ed91931e53e93c Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 17 Nov 2010 10:05:29 -0300 Subject: [media] rc: Remove ir-common.h Signed-off-by: Mauro Carvalho Chehab --- include/media/ir-common.h | 77 ---------------------------------------------- include/media/ir-kbd-i2c.h | 2 +- 2 files changed, 1 insertion(+), 78 deletions(-) delete mode 100644 include/media/ir-common.h (limited to 'include') diff --git a/include/media/ir-common.h b/include/media/ir-common.h deleted file mode 100644 index 41fefd9..0000000 --- a/include/media/ir-common.h +++ /dev/null @@ -1,77 +0,0 @@ -/* - * some common functions to handle infrared remote protocol decoding for - * drivers which have not yet been (or can't be) converted to use the - * regular protocol decoders... - * - * (c) 2003 Gerd Knorr [SuSE Labs] - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#ifndef _IR_COMMON -#define _IR_COMMON - -#include -#include -#include -#include - -#define RC5_START(x) (((x)>>12)&3) -#define RC5_TOGGLE(x) (((x)>>11)&1) -#define RC5_ADDR(x) (((x)>>6)&31) -#define RC5_INSTR(x) ((x)&63) - -/* this was saa7134_ir and bttv_ir, moved here for - * rc5 decoding. */ -struct card_ir { - struct rc_dev *dev; - char name[32]; - char phys[32]; - int users; - u32 running:1; - - /* Usual gpio signalling */ - u32 mask_keycode; - u32 mask_keydown; - u32 mask_keyup; - u32 polling; - u32 last_gpio; - int shift_by; - int start; // What should RC5_START() be - int addr; // What RC5_ADDR() should be. - int rc5_remote_gap; - struct work_struct work; - struct timer_list timer; - - /* RC5 gpio */ - u32 rc5_gpio; - struct timer_list timer_end; /* timer_end for code completion */ - u32 last_bit; /* last raw bit seen */ - u32 code; /* raw code under construction */ - struct timeval base_time; /* time of last seen code */ - int active; /* building raw code */ - - /* NEC decoding */ - u32 nec_gpio; - struct tasklet_struct tlet; - - /* IR core raw decoding */ - u32 raw_decode; -}; - -/* Routines from ir-functions.c */ -void ir_rc5_timer_end(unsigned long data); - -#endif diff --git a/include/media/ir-kbd-i2c.h b/include/media/ir-kbd-i2c.h index aca015e..d27505f 100644 --- a/include/media/ir-kbd-i2c.h +++ b/include/media/ir-kbd-i2c.h @@ -1,7 +1,7 @@ #ifndef _IR_I2C #define _IR_I2C -#include +#include #define DEFAULT_POLLING_INTERVAL 100 /* ms */ -- cgit v1.1 From 6bda96447cef24fbf97a798b1ea664224d5fdc25 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 17 Nov 2010 13:28:38 -0300 Subject: [media] rc: rename the remaining things to rc_core The Remote Controller subsystem is meant to be used not only by Infra Red but also for similar types of Remote Controllers. The core is not specific to Infra Red. As such, rename: - ir-core.h to rc-core.h - IR_CORE to RC_CORE - namespace inside rc-core.c/rc-core.h To be consistent with the other changes. No functional change on this patch. Signed-off-by: Mauro Carvalho Chehab --- include/media/ir-core.h | 211 --------------------------------------------- include/media/ir-kbd-i2c.h | 2 +- include/media/rc-core.h | 211 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 212 insertions(+), 212 deletions(-) delete mode 100644 include/media/ir-core.h create mode 100644 include/media/rc-core.h (limited to 'include') diff --git a/include/media/ir-core.h b/include/media/ir-core.h deleted file mode 100644 index c590998..0000000 --- a/include/media/ir-core.h +++ /dev/null @@ -1,211 +0,0 @@ -/* - * Remote Controller core header - * - * Copyright (C) 2009-2010 by Mauro Carvalho Chehab - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation version 2 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ - -#ifndef _IR_CORE -#define _IR_CORE - -#include -#include -#include -#include -#include - -extern int ir_core_debug; -#define IR_dprintk(level, fmt, arg...) if (ir_core_debug >= level) \ - printk(KERN_DEBUG "%s: " fmt , __func__, ## arg) - -enum rc_driver_type { - RC_DRIVER_SCANCODE = 0, /* Driver or hardware generates a scancode */ - RC_DRIVER_IR_RAW, /* Needs a Infra-Red pulse/space decoder */ -}; - -/** - * struct rc_dev - represents a remote control device - * @dev: driver model's view of this device - * @input_name: name of the input child device - * @input_phys: physical path to the input child device - * @input_id: id of the input child device (struct input_id) - * @driver_name: name of the hardware driver which registered this device - * @map_name: name of the default keymap - * @rc_tab: current scan/key table - * @devno: unique remote control device number - * @raw: additional data for raw pulse/space devices - * @input_dev: the input child device used to communicate events to userspace - * @driver_type: specifies if protocol decoding is done in hardware or software - * @idle: used to keep track of RX state - * @allowed_protos: bitmask with the supported IR_TYPE_* protocols - * @scanmask: some hardware decoders are not capable of providing the full - * scancode to the application. As this is a hardware limit, we can't do - * anything with it. Yet, as the same keycode table can be used with other - * devices, a mask is provided to allow its usage. Drivers should generally - * leave this field in blank - * @priv: driver-specific data - * @keylock: protects the remaining members of the struct - * @keypressed: whether a key is currently pressed - * @keyup_jiffies: time (in jiffies) when the current keypress should be released - * @timer_keyup: timer for releasing a keypress - * @last_keycode: keycode of last keypress - * @last_scancode: scancode of last keypress - * @last_toggle: toggle value of last command - * @timeout: optional time after which device stops sending data - * @min_timeout: minimum timeout supported by device - * @max_timeout: maximum timeout supported by device - * @rx_resolution : resolution (in ns) of input sampler - * @tx_resolution: resolution (in ns) of output sampler - * @change_protocol: allow changing the protocol used on hardware decoders - * @open: callback to allow drivers to enable polling/irq when IR input device - * is opened. - * @close: callback to allow drivers to disable polling/irq when IR input device - * is opened. - * @s_tx_mask: set transmitter mask (for devices with multiple tx outputs) - * @s_tx_carrier: set transmit carrier frequency - * @s_tx_duty_cycle: set transmit duty cycle (0% - 100%) - * @s_rx_carrier: inform driver about carrier it is expected to handle - * @tx_ir: transmit IR - * @s_idle: enable/disable hardware idle mode, upon which, - * device doesn't interrupt host until it sees IR pulses - * @s_learning_mode: enable wide band receiver used for learning - * @s_carrier_report: enable carrier reports - */ -struct rc_dev { - struct device dev; - const char *input_name; - const char *input_phys; - struct input_id input_id; - char *driver_name; - const char *map_name; - struct ir_scancode_table rc_tab; - unsigned long devno; - struct ir_raw_event_ctrl *raw; - struct input_dev *input_dev; - enum rc_driver_type driver_type; - bool idle; - u64 allowed_protos; - u32 scanmask; - void *priv; - spinlock_t keylock; - bool keypressed; - unsigned long keyup_jiffies; - struct timer_list timer_keyup; - u32 last_keycode; - u32 last_scancode; - u8 last_toggle; - u32 timeout; - u32 min_timeout; - u32 max_timeout; - u32 rx_resolution; - u32 tx_resolution; - int (*change_protocol)(struct rc_dev *dev, u64 ir_type); - int (*open)(struct rc_dev *dev); - void (*close)(struct rc_dev *dev); - int (*s_tx_mask)(struct rc_dev *dev, u32 mask); - int (*s_tx_carrier)(struct rc_dev *dev, u32 carrier); - int (*s_tx_duty_cycle)(struct rc_dev *dev, u32 duty_cycle); - int (*s_rx_carrier_range)(struct rc_dev *dev, u32 min, u32 max); - int (*tx_ir)(struct rc_dev *dev, int *txbuf, u32 n); - void (*s_idle)(struct rc_dev *dev, bool enable); - int (*s_learning_mode)(struct rc_dev *dev, int enable); - int (*s_carrier_report) (struct rc_dev *dev, int enable); -}; - -enum raw_event_type { - IR_SPACE = (1 << 0), - IR_PULSE = (1 << 1), - IR_START_EVENT = (1 << 2), - IR_STOP_EVENT = (1 << 3), -}; - -#define to_rc_dev(d) container_of(d, struct rc_dev, dev) - - -void ir_repeat(struct rc_dev *dev); -void ir_keydown(struct rc_dev *dev, int scancode, u8 toggle); -void ir_keydown_notimeout(struct rc_dev *dev, int scancode, u8 toggle); -void ir_keyup(struct rc_dev *dev); -u32 ir_g_keycode_from_table(struct rc_dev *dev, u32 scancode); - -/* From ir-raw-event.c */ -struct ir_raw_event { - union { - u32 duration; - - struct { - u32 carrier; - u8 duty_cycle; - }; - }; - - unsigned pulse:1; - unsigned reset:1; - unsigned timeout:1; - unsigned carrier_report:1; -}; - -#define DEFINE_IR_RAW_EVENT(event) \ - struct ir_raw_event event = { \ - { .duration = 0 } , \ - .pulse = 0, \ - .reset = 0, \ - .timeout = 0, \ - .carrier_report = 0 } - -static inline void init_ir_raw_event(struct ir_raw_event *ev) -{ - memset(ev, 0, sizeof(*ev)); -} - -#define IR_MAX_DURATION 0xFFFFFFFF /* a bit more than 4 seconds */ - -struct rc_dev *rc_allocate_device(void); -void rc_free_device(struct rc_dev *dev); -int rc_register_device(struct rc_dev *dev); -void rc_unregister_device(struct rc_dev *dev); - -void ir_raw_event_handle(struct rc_dev *dev); -int ir_raw_event_store(struct rc_dev *dev, struct ir_raw_event *ev); -int ir_raw_event_store_edge(struct rc_dev *dev, enum raw_event_type type); -int ir_raw_event_store_with_filter(struct rc_dev *dev, - struct ir_raw_event *ev); -void ir_raw_event_set_idle(struct rc_dev *dev, bool idle); - -static inline void ir_raw_event_reset(struct rc_dev *dev) -{ - DEFINE_IR_RAW_EVENT(ev); - ev.reset = true; - - ir_raw_event_store(dev, &ev); - ir_raw_event_handle(dev); -} - - -/* extract mask bits out of data and pack them into the result */ -static inline u32 ir_extract_bits(u32 data, u32 mask) -{ - u32 vbit = 1, value = 0; - - do { - if (mask & 1) { - if (data & 1) - value |= vbit; - vbit <<= 1; - } - data >>= 1; - } while (mask >>= 1); - - return value; -} - - -#endif /* _IR_CORE */ diff --git a/include/media/ir-kbd-i2c.h b/include/media/ir-kbd-i2c.h index d27505f..f22b359 100644 --- a/include/media/ir-kbd-i2c.h +++ b/include/media/ir-kbd-i2c.h @@ -1,7 +1,7 @@ #ifndef _IR_I2C #define _IR_I2C -#include +#include #define DEFAULT_POLLING_INTERVAL 100 /* ms */ diff --git a/include/media/rc-core.h b/include/media/rc-core.h new file mode 100644 index 0000000..eedb2f0 --- /dev/null +++ b/include/media/rc-core.h @@ -0,0 +1,211 @@ +/* + * Remote Controller core header + * + * Copyright (C) 2009-2010 by Mauro Carvalho Chehab + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation version 2 of the License. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _IR_CORE +#define _IR_CORE + +#include +#include +#include +#include +#include + +extern int rc_core_debug; +#define IR_dprintk(level, fmt, arg...) if (rc_core_debug >= level) \ + printk(KERN_DEBUG "%s: " fmt , __func__, ## arg) + +enum rc_driver_type { + RC_DRIVER_SCANCODE = 0, /* Driver or hardware generates a scancode */ + RC_DRIVER_IR_RAW, /* Needs a Infra-Red pulse/space decoder */ +}; + +/** + * struct rc_dev - represents a remote control device + * @dev: driver model's view of this device + * @input_name: name of the input child device + * @input_phys: physical path to the input child device + * @input_id: id of the input child device (struct input_id) + * @driver_name: name of the hardware driver which registered this device + * @map_name: name of the default keymap + * @rc_tab: current scan/key table + * @devno: unique remote control device number + * @raw: additional data for raw pulse/space devices + * @input_dev: the input child device used to communicate events to userspace + * @driver_type: specifies if protocol decoding is done in hardware or software + * @idle: used to keep track of RX state + * @allowed_protos: bitmask with the supported IR_TYPE_* protocols + * @scanmask: some hardware decoders are not capable of providing the full + * scancode to the application. As this is a hardware limit, we can't do + * anything with it. Yet, as the same keycode table can be used with other + * devices, a mask is provided to allow its usage. Drivers should generally + * leave this field in blank + * @priv: driver-specific data + * @keylock: protects the remaining members of the struct + * @keypressed: whether a key is currently pressed + * @keyup_jiffies: time (in jiffies) when the current keypress should be released + * @timer_keyup: timer for releasing a keypress + * @last_keycode: keycode of last keypress + * @last_scancode: scancode of last keypress + * @last_toggle: toggle value of last command + * @timeout: optional time after which device stops sending data + * @min_timeout: minimum timeout supported by device + * @max_timeout: maximum timeout supported by device + * @rx_resolution : resolution (in ns) of input sampler + * @tx_resolution: resolution (in ns) of output sampler + * @change_protocol: allow changing the protocol used on hardware decoders + * @open: callback to allow drivers to enable polling/irq when IR input device + * is opened. + * @close: callback to allow drivers to disable polling/irq when IR input device + * is opened. + * @s_tx_mask: set transmitter mask (for devices with multiple tx outputs) + * @s_tx_carrier: set transmit carrier frequency + * @s_tx_duty_cycle: set transmit duty cycle (0% - 100%) + * @s_rx_carrier: inform driver about carrier it is expected to handle + * @tx_ir: transmit IR + * @s_idle: enable/disable hardware idle mode, upon which, + * device doesn't interrupt host until it sees IR pulses + * @s_learning_mode: enable wide band receiver used for learning + * @s_carrier_report: enable carrier reports + */ +struct rc_dev { + struct device dev; + const char *input_name; + const char *input_phys; + struct input_id input_id; + char *driver_name; + const char *map_name; + struct ir_scancode_table rc_tab; + unsigned long devno; + struct ir_raw_event_ctrl *raw; + struct input_dev *input_dev; + enum rc_driver_type driver_type; + bool idle; + u64 allowed_protos; + u32 scanmask; + void *priv; + spinlock_t keylock; + bool keypressed; + unsigned long keyup_jiffies; + struct timer_list timer_keyup; + u32 last_keycode; + u32 last_scancode; + u8 last_toggle; + u32 timeout; + u32 min_timeout; + u32 max_timeout; + u32 rx_resolution; + u32 tx_resolution; + int (*change_protocol)(struct rc_dev *dev, u64 ir_type); + int (*open)(struct rc_dev *dev); + void (*close)(struct rc_dev *dev); + int (*s_tx_mask)(struct rc_dev *dev, u32 mask); + int (*s_tx_carrier)(struct rc_dev *dev, u32 carrier); + int (*s_tx_duty_cycle)(struct rc_dev *dev, u32 duty_cycle); + int (*s_rx_carrier_range)(struct rc_dev *dev, u32 min, u32 max); + int (*tx_ir)(struct rc_dev *dev, int *txbuf, u32 n); + void (*s_idle)(struct rc_dev *dev, bool enable); + int (*s_learning_mode)(struct rc_dev *dev, int enable); + int (*s_carrier_report) (struct rc_dev *dev, int enable); +}; + +enum raw_event_type { + IR_SPACE = (1 << 0), + IR_PULSE = (1 << 1), + IR_START_EVENT = (1 << 2), + IR_STOP_EVENT = (1 << 3), +}; + +#define to_rc_dev(d) container_of(d, struct rc_dev, dev) + + +void ir_repeat(struct rc_dev *dev); +void ir_keydown(struct rc_dev *dev, int scancode, u8 toggle); +void ir_keydown_notimeout(struct rc_dev *dev, int scancode, u8 toggle); +void ir_keyup(struct rc_dev *dev); +u32 ir_g_keycode_from_table(struct rc_dev *dev, u32 scancode); + +/* From ir-raw-event.c */ +struct ir_raw_event { + union { + u32 duration; + + struct { + u32 carrier; + u8 duty_cycle; + }; + }; + + unsigned pulse:1; + unsigned reset:1; + unsigned timeout:1; + unsigned carrier_report:1; +}; + +#define DEFINE_IR_RAW_EVENT(event) \ + struct ir_raw_event event = { \ + { .duration = 0 } , \ + .pulse = 0, \ + .reset = 0, \ + .timeout = 0, \ + .carrier_report = 0 } + +static inline void init_ir_raw_event(struct ir_raw_event *ev) +{ + memset(ev, 0, sizeof(*ev)); +} + +#define IR_MAX_DURATION 0xFFFFFFFF /* a bit more than 4 seconds */ + +struct rc_dev *rc_allocate_device(void); +void rc_free_device(struct rc_dev *dev); +int rc_register_device(struct rc_dev *dev); +void rc_unregister_device(struct rc_dev *dev); + +void ir_raw_event_handle(struct rc_dev *dev); +int ir_raw_event_store(struct rc_dev *dev, struct ir_raw_event *ev); +int ir_raw_event_store_edge(struct rc_dev *dev, enum raw_event_type type); +int ir_raw_event_store_with_filter(struct rc_dev *dev, + struct ir_raw_event *ev); +void ir_raw_event_set_idle(struct rc_dev *dev, bool idle); + +static inline void ir_raw_event_reset(struct rc_dev *dev) +{ + DEFINE_IR_RAW_EVENT(ev); + ev.reset = true; + + ir_raw_event_store(dev, &ev); + ir_raw_event_handle(dev); +} + + +/* extract mask bits out of data and pack them into the result */ +static inline u32 ir_extract_bits(u32 data, u32 mask) +{ + u32 vbit = 1, value = 0; + + do { + if (mask & 1) { + if (data & 1) + value |= vbit; + vbit <<= 1; + } + data >>= 1; + } while (mask >>= 1); + + return value; +} + + +#endif /* _IR_CORE */ -- cgit v1.1 From ca86674b8a93ea11c4bb6f4dd0113b1adf1fa841 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 17 Nov 2010 13:53:11 -0300 Subject: [media] Rename all public generic RC functions from ir_ to rc_ Those functions are not InfraRed specific. So, rename them to properly reflect it. Signed-off-by: Mauro Carvalho Chehab --- include/media/rc-core.h | 49 +++++++++++++++++++++++++++++-------------------- 1 file changed, 29 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/media/rc-core.h b/include/media/rc-core.h index eedb2f0..170581b 100644 --- a/include/media/rc-core.h +++ b/include/media/rc-core.h @@ -13,8 +13,8 @@ * GNU General Public License for more details. */ -#ifndef _IR_CORE -#define _IR_CORE +#ifndef _RC_CORE +#define _RC_CORE #include #include @@ -120,6 +120,32 @@ struct rc_dev { int (*s_carrier_report) (struct rc_dev *dev, int enable); }; +#define to_rc_dev(d) container_of(d, struct rc_dev, dev) + +/* + * From rc-main.c + * Those functions can be used on any type of Remote Controller. They + * basically creates an input_dev and properly reports the device as a + * Remote Controller, at sys/class/rc. + */ + +struct rc_dev *rc_allocate_device(void); +void rc_free_device(struct rc_dev *dev); +int rc_register_device(struct rc_dev *dev); +void rc_unregister_device(struct rc_dev *dev); + +void rc_repeat(struct rc_dev *dev); +void rc_keydown(struct rc_dev *dev, int scancode, u8 toggle); +void rc_keydown_notimeout(struct rc_dev *dev, int scancode, u8 toggle); +void rc_keyup(struct rc_dev *dev); +u32 rc_g_keycode_from_table(struct rc_dev *dev, u32 scancode); + +/* + * From rc-raw.c + * The Raw interface is specific to InfraRed. It may be a good idea to + * split it later into a separate header. + */ + enum raw_event_type { IR_SPACE = (1 << 0), IR_PULSE = (1 << 1), @@ -127,16 +153,6 @@ enum raw_event_type { IR_STOP_EVENT = (1 << 3), }; -#define to_rc_dev(d) container_of(d, struct rc_dev, dev) - - -void ir_repeat(struct rc_dev *dev); -void ir_keydown(struct rc_dev *dev, int scancode, u8 toggle); -void ir_keydown_notimeout(struct rc_dev *dev, int scancode, u8 toggle); -void ir_keyup(struct rc_dev *dev); -u32 ir_g_keycode_from_table(struct rc_dev *dev, u32 scancode); - -/* From ir-raw-event.c */ struct ir_raw_event { union { u32 duration; @@ -168,11 +184,6 @@ static inline void init_ir_raw_event(struct ir_raw_event *ev) #define IR_MAX_DURATION 0xFFFFFFFF /* a bit more than 4 seconds */ -struct rc_dev *rc_allocate_device(void); -void rc_free_device(struct rc_dev *dev); -int rc_register_device(struct rc_dev *dev); -void rc_unregister_device(struct rc_dev *dev); - void ir_raw_event_handle(struct rc_dev *dev); int ir_raw_event_store(struct rc_dev *dev, struct ir_raw_event *ev); int ir_raw_event_store_edge(struct rc_dev *dev, enum raw_event_type type); @@ -189,7 +200,6 @@ static inline void ir_raw_event_reset(struct rc_dev *dev) ir_raw_event_handle(dev); } - /* extract mask bits out of data and pack them into the result */ static inline u32 ir_extract_bits(u32 data, u32 mask) { @@ -207,5 +217,4 @@ static inline u32 ir_extract_bits(u32 data, u32 mask) return value; } - -#endif /* _IR_CORE */ +#endif /* _RC_CORE */ -- cgit v1.1 From 52b661449aecc47e652a164c0d8078b31e10aca0 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 17 Nov 2010 14:20:52 -0300 Subject: [media] rc: Rename remote controller type to rc_type instead of ir_type for i in `find drivers/staging -type f -name *.[ch]` `find include/media -type f -name *.[ch]` `find drivers/media -type f -name *.[ch]`; do sed s,IR_TYPE,RC_TYPE,g <$i >a && mv a $i; done for i in `find drivers/staging -type f -name *.[ch]` `find include/media -type f -name *.[ch]` `find drivers/media -type f -name *.[ch]`; do sed s,ir_type,rc_type,g <$i >a && mv a $i; done Signed-off-by: Mauro Carvalho Chehab --- include/media/ir-kbd-i2c.h | 2 +- include/media/rc-core.h | 4 ++-- include/media/rc-map.h | 26 +++++++++++++------------- 3 files changed, 16 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/media/ir-kbd-i2c.h b/include/media/ir-kbd-i2c.h index f22b359..768aa77 100644 --- a/include/media/ir-kbd-i2c.h +++ b/include/media/ir-kbd-i2c.h @@ -37,7 +37,7 @@ enum ir_kbd_get_key_fn { struct IR_i2c_init_data { char *ir_codes; const char *name; - u64 type; /* IR_TYPE_RC5, etc */ + u64 type; /* RC_TYPE_RC5, etc */ u32 polling_interval; /* 0 means DEFAULT_POLLING_INTERVAL */ /* diff --git a/include/media/rc-core.h b/include/media/rc-core.h index 170581b..4254325 100644 --- a/include/media/rc-core.h +++ b/include/media/rc-core.h @@ -45,7 +45,7 @@ enum rc_driver_type { * @input_dev: the input child device used to communicate events to userspace * @driver_type: specifies if protocol decoding is done in hardware or software * @idle: used to keep track of RX state - * @allowed_protos: bitmask with the supported IR_TYPE_* protocols + * @allowed_protos: bitmask with the supported RC_TYPE_* protocols * @scanmask: some hardware decoders are not capable of providing the full * scancode to the application. As this is a hardware limit, we can't do * anything with it. Yet, as the same keycode table can be used with other @@ -107,7 +107,7 @@ struct rc_dev { u32 max_timeout; u32 rx_resolution; u32 tx_resolution; - int (*change_protocol)(struct rc_dev *dev, u64 ir_type); + int (*change_protocol)(struct rc_dev *dev, u64 rc_type); int (*open)(struct rc_dev *dev); void (*close)(struct rc_dev *dev); int (*s_tx_mask)(struct rc_dev *dev, u32 mask); diff --git a/include/media/rc-map.h b/include/media/rc-map.h index e0f17ed..c53351e 100644 --- a/include/media/rc-map.h +++ b/include/media/rc-map.h @@ -11,19 +11,19 @@ #include -#define IR_TYPE_UNKNOWN 0 -#define IR_TYPE_RC5 (1 << 0) /* Philips RC5 protocol */ -#define IR_TYPE_NEC (1 << 1) -#define IR_TYPE_RC6 (1 << 2) /* Philips RC6 protocol */ -#define IR_TYPE_JVC (1 << 3) /* JVC protocol */ -#define IR_TYPE_SONY (1 << 4) /* Sony12/15/20 protocol */ -#define IR_TYPE_RC5_SZ (1 << 5) /* RC5 variant used by Streamzap */ -#define IR_TYPE_LIRC (1 << 30) /* Pass raw IR to lirc userspace */ -#define IR_TYPE_OTHER (1u << 31) +#define RC_TYPE_UNKNOWN 0 +#define RC_TYPE_RC5 (1 << 0) /* Philips RC5 protocol */ +#define RC_TYPE_NEC (1 << 1) +#define RC_TYPE_RC6 (1 << 2) /* Philips RC6 protocol */ +#define RC_TYPE_JVC (1 << 3) /* JVC protocol */ +#define RC_TYPE_SONY (1 << 4) /* Sony12/15/20 protocol */ +#define RC_TYPE_RC5_SZ (1 << 5) /* RC5 variant used by Streamzap */ +#define RC_TYPE_LIRC (1 << 30) /* Pass raw IR to lirc userspace */ +#define RC_TYPE_OTHER (1u << 31) -#define IR_TYPE_ALL (IR_TYPE_RC5 | IR_TYPE_NEC | IR_TYPE_RC6 | \ - IR_TYPE_JVC | IR_TYPE_SONY | IR_TYPE_LIRC | \ - IR_TYPE_RC5_SZ | IR_TYPE_OTHER) +#define RC_TYPE_ALL (RC_TYPE_RC5 | RC_TYPE_NEC | RC_TYPE_RC6 | \ + RC_TYPE_JVC | RC_TYPE_SONY | RC_TYPE_LIRC | \ + RC_TYPE_RC5_SZ | RC_TYPE_OTHER) struct ir_scancode { u32 scancode; @@ -35,7 +35,7 @@ struct ir_scancode_table { unsigned int size; /* Max number of entries */ unsigned int len; /* Used number of entries */ unsigned int alloc; /* Size of *scan in bytes */ - u64 ir_type; + u64 rc_type; const char *name; spinlock_t lock; }; -- cgit v1.1 From b088ba658b3438056dab4d744701364db3f08b9a Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 17 Nov 2010 14:28:27 -0300 Subject: [media] rc: Properly name the rc_map struct The struct that describes a rc mapping had an weird and long name. We should properly name it, to make easier for developers to work with it, and to avoid confusion. Basically, generated by this script: for i in `find drivers/staging -type f -name *.[ch]` `find include/media -type f -name *.[ch]` `find drivers/media -type f -name *.[ch]`; do sed s,ir_scancode_table,rc_map,g <$i >a && mv a $i; done for i in `find drivers/staging -type f -name *.[ch]` `find include/media -type f -name *.[ch]` `find drivers/media -type f -name *.[ch]`; do sed s,rc_tab,rc_map,g <$i >a && mv a $i; done (and manually fixed where needed) Signed-off-by: Mauro Carvalho Chehab --- include/media/rc-core.h | 4 ++-- include/media/rc-map.h | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/media/rc-core.h b/include/media/rc-core.h index 4254325..affb93f 100644 --- a/include/media/rc-core.h +++ b/include/media/rc-core.h @@ -39,7 +39,7 @@ enum rc_driver_type { * @input_id: id of the input child device (struct input_id) * @driver_name: name of the hardware driver which registered this device * @map_name: name of the default keymap - * @rc_tab: current scan/key table + * @rc_map: current scan/key table * @devno: unique remote control device number * @raw: additional data for raw pulse/space devices * @input_dev: the input child device used to communicate events to userspace @@ -86,7 +86,7 @@ struct rc_dev { struct input_id input_id; char *driver_name; const char *map_name; - struct ir_scancode_table rc_tab; + struct rc_map rc_map; unsigned long devno; struct ir_raw_event_ctrl *raw; struct input_dev *input_dev; diff --git a/include/media/rc-map.h b/include/media/rc-map.h index c53351e..a6b2738f 100644 --- a/include/media/rc-map.h +++ b/include/media/rc-map.h @@ -30,7 +30,7 @@ struct ir_scancode { u32 keycode; }; -struct ir_scancode_table { +struct rc_map { struct ir_scancode *scan; unsigned int size; /* Max number of entries */ unsigned int len; /* Used number of entries */ @@ -42,14 +42,14 @@ struct ir_scancode_table { struct rc_keymap { struct list_head list; - struct ir_scancode_table map; + struct rc_map map; }; /* Routines from rc-map.c */ int ir_register_map(struct rc_keymap *map); void ir_unregister_map(struct rc_keymap *map); -struct ir_scancode_table *get_rc_map(const char *name); +struct rc_map *get_rc_map(const char *name); void rc_map_init(void); /* Names of the several keytables defined in-kernel */ -- cgit v1.1 From 2f4f58d689dd71dea67407b74405a3c43e797cb1 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 17 Nov 2010 15:46:09 -0300 Subject: [media] rc: Name RC keymap tables as rc_map_table Remote keytables had different names all over the place. Part of the fault is due to a bad naming when rc subsystem was created, but there were lots of old names that were still here. Use a common standard for everything. Patch generated by this script: for i in `find drivers/staging -type f -name *.[ch]` `find include/media -type f -name *.[ch]` `find drivers/media -type f -name *.[ch]`; do sed s,ir_scancode,rc_map_table,g <$i >a && mv a $i; done for i in `find drivers/staging -type f -name *.[ch]` `find include/media -type f -name *.[ch]` `find drivers/media -type f -name *.[ch]`; do sed s,ir_codes_,rc_map_,g <$i >a && mv a $i; done for i in `find drivers/staging -type f -name *.[ch]` `find include/media -type f -name *.[ch]` `find drivers/media -type f -name *.[ch]`; do sed s,rc_key_map,rc_map_table,g <$i >a && mv a $i; done for i in `find drivers/staging -type f -name *.[ch]` `find include/media -type f -name *.[ch]` `find drivers/media -type f -name *.[ch]`; do sed s,rc_map_table_size,rc_map_size,g <$i >a && mv a $i; done Signed-off-by: Mauro Carvalho Chehab --- include/media/rc-map.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/media/rc-map.h b/include/media/rc-map.h index a6b2738f..5e9c06a 100644 --- a/include/media/rc-map.h +++ b/include/media/rc-map.h @@ -25,13 +25,13 @@ RC_TYPE_JVC | RC_TYPE_SONY | RC_TYPE_LIRC | \ RC_TYPE_RC5_SZ | RC_TYPE_OTHER) -struct ir_scancode { +struct rc_map_table { u32 scancode; u32 keycode; }; struct rc_map { - struct ir_scancode *scan; + struct rc_map_table *scan; unsigned int size; /* Max number of entries */ unsigned int len; /* Used number of entries */ unsigned int alloc; /* Size of *scan in bytes */ -- cgit v1.1 From d100e659b61a735c3343b3d82c1c009b04072cdd Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 17 Nov 2010 15:56:53 -0300 Subject: [media] rc: use rc_map_ prefix for all rc map tables Signed-off-by: Mauro Carvalho Chehab --- include/media/rc-map.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/media/rc-map.h b/include/media/rc-map.h index 5e9c06a..1a3d51d 100644 --- a/include/media/rc-map.h +++ b/include/media/rc-map.h @@ -40,16 +40,16 @@ struct rc_map { spinlock_t lock; }; -struct rc_keymap { +struct rc_map_list { struct list_head list; struct rc_map map; }; /* Routines from rc-map.c */ -int ir_register_map(struct rc_keymap *map); -void ir_unregister_map(struct rc_keymap *map); -struct rc_map *get_rc_map(const char *name); +int rc_map_register(struct rc_map_list *map); +void rc_map_unregister(struct rc_map_list *map); +struct rc_map *rc_map_get(const char *name); void rc_map_init(void); /* Names of the several keytables defined in-kernel */ -- cgit v1.1 From 829ba9fe34246f1f5e813b6bf84171d36e776734 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?David=20H=C3=83=C2=A4rdeman?= Date: Fri, 19 Nov 2010 20:43:27 -0300 Subject: [media] rc-core: fix some leftovers from the renaming patches MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix some minor comments etc which are leftover from the old naming scheme. Signed-off-by: David Härdeman Signed-off-by: Mauro Carvalho Chehab --- include/media/rc-core.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/media/rc-core.h b/include/media/rc-core.h index affb93f..a23c1fc 100644 --- a/include/media/rc-core.h +++ b/include/media/rc-core.h @@ -206,12 +206,12 @@ static inline u32 ir_extract_bits(u32 data, u32 mask) u32 vbit = 1, value = 0; do { - if (mask & 1) { - if (data & 1) - value |= vbit; - vbit <<= 1; - } - data >>= 1; + if (mask & 1) { + if (data & 1) + value |= vbit; + vbit <<= 1; + } + data >>= 1; } while (mask >>= 1); return value; -- cgit v1.1 From 0e835087dfe7db19f1f072046f5e116d4ec6662b Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 17 Nov 2010 02:13:39 -0300 Subject: [media] lirc_dev: add some __user annotations Sparse complains because there are no __user annotations. drivers/media/rc/lirc_dev.c:156:27: warning: incorrect type in initializer (incompatible argument 2 (different address spaces)) drivers/media/rc/lirc_dev.c:156:27: expected int ( *read )( ... ) drivers/media/rc/lirc_dev.c:156:27: got int ( extern [toplevel] * )( ... ) Signed-off-by: Dan Carpenter Acked-by: Jarod Wilson Signed-off-by: Mauro Carvalho Chehab --- include/media/lirc_dev.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/media/lirc_dev.h b/include/media/lirc_dev.h index 54780a5..630e702 100644 --- a/include/media/lirc_dev.h +++ b/include/media/lirc_dev.h @@ -217,9 +217,9 @@ int lirc_dev_fop_open(struct inode *inode, struct file *file); int lirc_dev_fop_close(struct inode *inode, struct file *file); unsigned int lirc_dev_fop_poll(struct file *file, poll_table *wait); long lirc_dev_fop_ioctl(struct file *file, unsigned int cmd, unsigned long arg); -ssize_t lirc_dev_fop_read(struct file *file, char *buffer, size_t length, +ssize_t lirc_dev_fop_read(struct file *file, char __user *buffer, size_t length, loff_t *ppos); -ssize_t lirc_dev_fop_write(struct file *file, const char *buffer, size_t length, - loff_t *ppos); +ssize_t lirc_dev_fop_write(struct file *file, const char __user *buffer, + size_t length, loff_t *ppos); #endif -- cgit v1.1 From eac8ae087ac66b21de94fee3e920210b43d43076 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Mariusz=20Bia=C5=82o=C5=84czyk?= Date: Mon, 15 Nov 2010 15:50:13 -0300 Subject: [media] Fix rc-tbs-nec table after converting the cx88 driver to ir-core MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The patch fixes the rc-tbs-nec table after converting drivers/media/video/cx88 to ir-core (commit ba7e90c9f878e0ac3c0614a5446fe5c62ccc33ec). It is also adds two missing buttons (10- and 10+) with its definition (KEY_10CHANNELSUP and KEY_10CHANNELSDOWN). [mchehab@redhat.com: move keycode numbers to 0x1b8/0x1b9 as requested by the input Maintainer] Signed-off-by: Mariusz Białończyk Signed-off-by: Mauro Carvalho Chehab --- include/linux/input.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/input.h b/include/linux/input.h index 9777668..f7a6e19 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -590,6 +590,8 @@ struct input_keymap_entry { #define KEY_FRAMEFORWARD 0x1b5 #define KEY_CONTEXT_MENU 0x1b6 /* GenDesc - system context menu */ #define KEY_MEDIA_REPEAT 0x1b7 /* Consumer - transport control */ +#define KEY_10CHANNELSUP 0x1b8 /* 10 channels up (10+) */ +#define KEY_10CHANNELSDOWN 0x1b9 /* 10 channels down (10-) */ #define KEY_DEL_EOL 0x1c0 #define KEY_DEL_EOS 0x1c1 -- cgit v1.1 From 12007419b766b316998499bd07c6586928230729 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 17 Dec 2010 14:39:29 -0300 Subject: [media] Add a keymap for Pixelview 002-T remote Signed-off-by: Mauro Carvalho Chehab --- include/media/rc-map.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/media/rc-map.h b/include/media/rc-map.h index 1a3d51d..5d3a457 100644 --- a/include/media/rc-map.h +++ b/include/media/rc-map.h @@ -119,6 +119,7 @@ void rc_map_init(void); #define RC_MAP_PINNACLE_PCTV_HD "rc-pinnacle-pctv-hd" #define RC_MAP_PIXELVIEW_NEW "rc-pixelview-new" #define RC_MAP_PIXELVIEW "rc-pixelview" +#define RC_MAP_PIXELVIEW_002T "rc-pixelview-002t" #define RC_MAP_PIXELVIEW_MK12 "rc-pixelview-mk12" #define RC_MAP_POWERCOLOR_REAL_ANGEL "rc-powercolor-real-angel" #define RC_MAP_PROTEUS_2309 "rc-proteus-2309" -- cgit v1.1 From 383268a8e282fb549dabe3a33ccafc9434ab6006 Mon Sep 17 00:00:00 2001 From: Matti Aaltonen Date: Fri, 10 Dec 2010 11:41:33 -0300 Subject: [media] MFD: WL1273 FM Radio: MFD driver for the FM radio This is the core of the WL1273 FM radio driver, it connects the two child modules. The two child drivers are drivers/media/radio/radio-wl1273.c and sound/soc/codecs/wl1273.c. The radio-wl1273 driver implements the V4L2 interface and communicates with the device. The ALSA codec offers digital audio, without it only analog audio is available. Signed-off-by: Matti J. Aaltonen Acked-by: Samuel Ortiz Signed-off-by: Mauro Carvalho Chehab --- include/linux/mfd/wl1273-core.h | 288 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 288 insertions(+) create mode 100644 include/linux/mfd/wl1273-core.h (limited to 'include') diff --git a/include/linux/mfd/wl1273-core.h b/include/linux/mfd/wl1273-core.h new file mode 100644 index 0000000..9787293 --- /dev/null +++ b/include/linux/mfd/wl1273-core.h @@ -0,0 +1,288 @@ +/* + * include/linux/mfd/wl1273-core.h + * + * Some definitions for the wl1273 radio receiver/transmitter chip. + * + * Copyright (C) 2010 Nokia Corporation + * Author: Matti J. Aaltonen + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA + * 02110-1301 USA + */ + +#ifndef WL1273_CORE_H +#define WL1273_CORE_H + +#include +#include + +#define WL1273_FM_DRIVER_NAME "wl1273-fm" +#define RX71_FM_I2C_ADDR 0x22 + +#define WL1273_STEREO_GET 0 +#define WL1273_RSSI_LVL_GET 1 +#define WL1273_IF_COUNT_GET 2 +#define WL1273_FLAG_GET 3 +#define WL1273_RDS_SYNC_GET 4 +#define WL1273_RDS_DATA_GET 5 +#define WL1273_FREQ_SET 10 +#define WL1273_AF_FREQ_SET 11 +#define WL1273_MOST_MODE_SET 12 +#define WL1273_MOST_BLEND_SET 13 +#define WL1273_DEMPH_MODE_SET 14 +#define WL1273_SEARCH_LVL_SET 15 +#define WL1273_BAND_SET 16 +#define WL1273_MUTE_STATUS_SET 17 +#define WL1273_RDS_PAUSE_LVL_SET 18 +#define WL1273_RDS_PAUSE_DUR_SET 19 +#define WL1273_RDS_MEM_SET 20 +#define WL1273_RDS_BLK_B_SET 21 +#define WL1273_RDS_MSK_B_SET 22 +#define WL1273_RDS_PI_MASK_SET 23 +#define WL1273_RDS_PI_SET 24 +#define WL1273_RDS_SYSTEM_SET 25 +#define WL1273_INT_MASK_SET 26 +#define WL1273_SEARCH_DIR_SET 27 +#define WL1273_VOLUME_SET 28 +#define WL1273_AUDIO_ENABLE 29 +#define WL1273_PCM_MODE_SET 30 +#define WL1273_I2S_MODE_CONFIG_SET 31 +#define WL1273_POWER_SET 32 +#define WL1273_INTX_CONFIG_SET 33 +#define WL1273_PULL_EN_SET 34 +#define WL1273_HILO_SET 35 +#define WL1273_SWITCH2FREF 36 +#define WL1273_FREQ_DRIFT_REPORT 37 + +#define WL1273_PCE_GET 40 +#define WL1273_FIRM_VER_GET 41 +#define WL1273_ASIC_VER_GET 42 +#define WL1273_ASIC_ID_GET 43 +#define WL1273_MAN_ID_GET 44 +#define WL1273_TUNER_MODE_SET 45 +#define WL1273_STOP_SEARCH 46 +#define WL1273_RDS_CNTRL_SET 47 + +#define WL1273_WRITE_HARDWARE_REG 100 +#define WL1273_CODE_DOWNLOAD 101 +#define WL1273_RESET 102 + +#define WL1273_FM_POWER_MODE 254 +#define WL1273_FM_INTERRUPT 255 + +/* Transmitter API */ + +#define WL1273_CHANL_SET 55 +#define WL1273_SCAN_SPACING_SET 56 +#define WL1273_REF_SET 57 +#define WL1273_POWER_ENB_SET 90 +#define WL1273_POWER_ATT_SET 58 +#define WL1273_POWER_LEV_SET 59 +#define WL1273_AUDIO_DEV_SET 60 +#define WL1273_PILOT_DEV_SET 61 +#define WL1273_RDS_DEV_SET 62 +#define WL1273_PUPD_SET 91 +#define WL1273_AUDIO_IO_SET 63 +#define WL1273_PREMPH_SET 64 +#define WL1273_MONO_SET 66 +#define WL1273_MUTE 92 +#define WL1273_MPX_LMT_ENABLE 67 +#define WL1273_PI_SET 93 +#define WL1273_ECC_SET 69 +#define WL1273_PTY 70 +#define WL1273_AF 71 +#define WL1273_DISPLAY_MODE 74 +#define WL1273_RDS_REP_SET 77 +#define WL1273_RDS_CONFIG_DATA_SET 98 +#define WL1273_RDS_DATA_SET 99 +#define WL1273_RDS_DATA_ENB 94 +#define WL1273_TA_SET 78 +#define WL1273_TP_SET 79 +#define WL1273_DI_SET 80 +#define WL1273_MS_SET 81 +#define WL1273_PS_SCROLL_SPEED 82 +#define WL1273_TX_AUDIO_LEVEL_TEST 96 +#define WL1273_TX_AUDIO_LEVEL_TEST_THRESHOLD 73 +#define WL1273_TX_AUDIO_INPUT_LEVEL_RANGE_SET 54 +#define WL1273_RX_ANTENNA_SELECT 87 +#define WL1273_I2C_DEV_ADDR_SET 86 +#define WL1273_REF_ERR_CALIB_PARAM_SET 88 +#define WL1273_REF_ERR_CALIB_PERIODICITY_SET 89 +#define WL1273_SOC_INT_TRIGGER 52 +#define WL1273_SOC_AUDIO_PATH_SET 83 +#define WL1273_SOC_PCMI_OVERRIDE 84 +#define WL1273_SOC_I2S_OVERRIDE 85 +#define WL1273_RSSI_BLOCK_SCAN_FREQ_SET 95 +#define WL1273_RSSI_BLOCK_SCAN_START 97 +#define WL1273_RSSI_BLOCK_SCAN_DATA_GET 5 +#define WL1273_READ_FMANT_TUNE_VALUE 104 + +#define WL1273_RDS_OFF 0 +#define WL1273_RDS_ON 1 +#define WL1273_RDS_RESET 2 + +#define WL1273_AUDIO_DIGITAL 0 +#define WL1273_AUDIO_ANALOG 1 + +#define WL1273_MODE_RX BIT(0) +#define WL1273_MODE_TX BIT(1) +#define WL1273_MODE_OFF BIT(2) +#define WL1273_MODE_SUSPENDED BIT(3) + +#define WL1273_RADIO_CHILD BIT(0) +#define WL1273_CODEC_CHILD BIT(1) + +#define WL1273_RX_MONO 1 +#define WL1273_RX_STEREO 0 +#define WL1273_TX_MONO 0 +#define WL1273_TX_STEREO 1 + +#define WL1273_MAX_VOLUME 0xffff +#define WL1273_DEFAULT_VOLUME 0x78b8 + +/* I2S protocol, left channel first, data width 16 bits */ +#define WL1273_PCM_DEF_MODE 0x00 + +/* Rx */ +#define WL1273_AUDIO_ENABLE_I2S BIT(0) +#define WL1273_AUDIO_ENABLE_ANALOG BIT(1) + +/* Tx */ +#define WL1273_AUDIO_IO_SET_ANALOG 0 +#define WL1273_AUDIO_IO_SET_I2S 1 + +#define WL1273_PUPD_SET_OFF 0x00 +#define WL1273_PUPD_SET_ON 0x01 +#define WL1273_PUPD_SET_RETENTION 0x10 + +/* I2S mode */ +#define WL1273_IS2_WIDTH_32 0x0 +#define WL1273_IS2_WIDTH_40 0x1 +#define WL1273_IS2_WIDTH_22_23 0x2 +#define WL1273_IS2_WIDTH_23_22 0x3 +#define WL1273_IS2_WIDTH_48 0x4 +#define WL1273_IS2_WIDTH_50 0x5 +#define WL1273_IS2_WIDTH_60 0x6 +#define WL1273_IS2_WIDTH_64 0x7 +#define WL1273_IS2_WIDTH_80 0x8 +#define WL1273_IS2_WIDTH_96 0x9 +#define WL1273_IS2_WIDTH_128 0xa +#define WL1273_IS2_WIDTH 0xf + +#define WL1273_IS2_FORMAT_STD (0x0 << 4) +#define WL1273_IS2_FORMAT_LEFT (0x1 << 4) +#define WL1273_IS2_FORMAT_RIGHT (0x2 << 4) +#define WL1273_IS2_FORMAT_USER (0x3 << 4) + +#define WL1273_IS2_MASTER (0x0 << 6) +#define WL1273_IS2_SLAVEW (0x1 << 6) + +#define WL1273_IS2_TRI_AFTER_SENDING (0x0 << 7) +#define WL1273_IS2_TRI_ALWAYS_ACTIVE (0x1 << 7) + +#define WL1273_IS2_SDOWS_RR (0x0 << 8) +#define WL1273_IS2_SDOWS_RF (0x1 << 8) +#define WL1273_IS2_SDOWS_FR (0x2 << 8) +#define WL1273_IS2_SDOWS_FF (0x3 << 8) + +#define WL1273_IS2_TRI_OPT (0x0 << 10) +#define WL1273_IS2_TRI_ALWAYS (0x1 << 10) + +#define WL1273_IS2_RATE_48K (0x0 << 12) +#define WL1273_IS2_RATE_44_1K (0x1 << 12) +#define WL1273_IS2_RATE_32K (0x2 << 12) +#define WL1273_IS2_RATE_22_05K (0x4 << 12) +#define WL1273_IS2_RATE_16K (0x5 << 12) +#define WL1273_IS2_RATE_12K (0x8 << 12) +#define WL1273_IS2_RATE_11_025 (0x9 << 12) +#define WL1273_IS2_RATE_8K (0xa << 12) +#define WL1273_IS2_RATE (0xf << 12) + +#define WL1273_I2S_DEF_MODE (WL1273_IS2_WIDTH_32 | \ + WL1273_IS2_FORMAT_STD | \ + WL1273_IS2_MASTER | \ + WL1273_IS2_TRI_AFTER_SENDING | \ + WL1273_IS2_SDOWS_RR | \ + WL1273_IS2_TRI_OPT | \ + WL1273_IS2_RATE_48K) + +#define SCHAR_MIN (-128) +#define SCHAR_MAX 127 + +#define WL1273_FR_EVENT BIT(0) +#define WL1273_BL_EVENT BIT(1) +#define WL1273_RDS_EVENT BIT(2) +#define WL1273_BBLK_EVENT BIT(3) +#define WL1273_LSYNC_EVENT BIT(4) +#define WL1273_LEV_EVENT BIT(5) +#define WL1273_IFFR_EVENT BIT(6) +#define WL1273_PI_EVENT BIT(7) +#define WL1273_PD_EVENT BIT(8) +#define WL1273_STIC_EVENT BIT(9) +#define WL1273_MAL_EVENT BIT(10) +#define WL1273_POW_ENB_EVENT BIT(11) +#define WL1273_SCAN_OVER_EVENT BIT(12) +#define WL1273_ERROR_EVENT BIT(13) + +#define TUNER_MODE_STOP_SEARCH 0 +#define TUNER_MODE_PRESET 1 +#define TUNER_MODE_AUTO_SEEK 2 +#define TUNER_MODE_AF 3 +#define TUNER_MODE_AUTO_SEEK_PI 4 +#define TUNER_MODE_AUTO_SEEK_BULK 5 + +#define RDS_BLOCK_SIZE 3 + +struct wl1273_fm_platform_data { + int (*request_resources) (struct i2c_client *client); + void (*free_resources) (void); + void (*enable) (void); + void (*disable) (void); + + u8 forbidden_modes; + unsigned int children; +}; + +#define WL1273_FM_CORE_CELLS 2 + +#define WL1273_BAND_OTHER 0 +#define WL1273_BAND_JAPAN 1 + +#define WL1273_BAND_JAPAN_LOW 76000 +#define WL1273_BAND_JAPAN_HIGH 90000 +#define WL1273_BAND_OTHER_LOW 87500 +#define WL1273_BAND_OTHER_HIGH 108000 + +#define WL1273_BAND_TX_LOW 76000 +#define WL1273_BAND_TX_HIGH 108000 + +struct wl1273_core { + struct mfd_cell cells[WL1273_FM_CORE_CELLS]; + struct wl1273_fm_platform_data *pdata; + + unsigned int mode; + unsigned int i2s_mode; + unsigned int volume; + unsigned int audio_mode; + unsigned int channel_number; + struct mutex lock; /* for serializing fm radio operations */ + + struct i2c_client *client; + + int (*write)(struct wl1273_core *core, u8, u16); + int (*set_audio)(struct wl1273_core *core, unsigned int); + int (*set_volume)(struct wl1273_core *core, unsigned int); +}; + +#endif /* ifndef WL1273_CORE_H */ -- cgit v1.1 From 08af245de0cf6ab5f4ed008ee2bb99273774fce0 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 24 Dec 2010 10:33:19 -0300 Subject: [media] V4L: remove V4L1 compatibility mode Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev.h | 22 ++-------------------- include/media/v4l2-ioctl.h | 22 +++------------------- include/media/videobuf-core.h | 8 -------- 3 files changed, 5 insertions(+), 47 deletions(-) (limited to 'include') diff --git a/include/linux/videodev.h b/include/linux/videodev.h index b19eab1..8a7aead 100644 --- a/include/linux/videodev.h +++ b/include/linux/videodev.h @@ -16,24 +16,7 @@ #include #include -#if defined(__MIN_V4L1) && defined (__KERNEL__) - -/* - * Used by those V4L2 core functions that need a minimum V4L1 support, - * in order to allow V4L1 Compatibilty code compilation. - */ - -struct video_mbuf -{ - int size; /* Total memory to map */ - int frames; /* Frames */ - int offsets[VIDEO_MAX_FRAME]; -}; - -#define VIDIOCGMBUF _IOR('v',20, struct video_mbuf) /* Memory map buffer info */ - -#else -#if defined(CONFIG_VIDEO_V4L1_COMPAT) || !defined (__KERNEL__) +#if defined(CONFIG_VIDEO_V4L1) || defined(CONFIG_VIDEO_V4L1_MODULE) || !defined(__KERNEL__) #define VID_TYPE_CAPTURE 1 /* Can capture */ #define VID_TYPE_TUNER 2 /* Can tune */ @@ -328,8 +311,7 @@ struct video_code #define VID_PLAY_RESET 13 #define VID_PLAY_END_MARK 14 -#endif /* CONFIG_VIDEO_V4L1_COMPAT */ -#endif /* __MIN_V4L1 */ +#endif /* CONFIG_VIDEO_V4L1 */ #endif /* __LINUX_VIDEODEV_H */ diff --git a/include/media/v4l2-ioctl.h b/include/media/v4l2-ioctl.h index 06daa6e..67df375 100644 --- a/include/media/v4l2-ioctl.h +++ b/include/media/v4l2-ioctl.h @@ -14,12 +14,7 @@ #include #include #include /* need __user */ -#ifdef CONFIG_VIDEO_V4L1_COMPAT -#define __MIN_V4L1 -#include -#else #include -#endif struct v4l2_fh; @@ -113,10 +108,6 @@ struct v4l2_ioctl_ops { int (*vidioc_overlay) (struct file *file, void *fh, unsigned int i); -#ifdef CONFIG_VIDEO_V4L1_COMPAT - /* buffer type is struct vidio_mbuf * */ - int (*vidiocgmbuf) (struct file *file, void *fh, struct video_mbuf *p); -#endif int (*vidioc_g_fbuf) (struct file *file, void *fh, struct v4l2_framebuffer *a); int (*vidioc_s_fbuf) (struct file *file, void *fh, @@ -300,22 +291,15 @@ extern void v4l_printk_ioctl(unsigned int cmd); extern const char *v4l2_field_names[]; extern const char *v4l2_type_names[]; -/* Compatibility layer interface -- v4l1-compat module */ -typedef long (*v4l2_kioctl)(struct file *file, - unsigned int cmd, void *arg); -#ifdef CONFIG_VIDEO_V4L1_COMPAT -long v4l_compat_translate_ioctl(struct file *file, - int cmd, void *arg, v4l2_kioctl driver_ioctl); -#else -#define v4l_compat_translate_ioctl(file, cmd, arg, ioctl) (-EINVAL) -#endif - #ifdef CONFIG_COMPAT /* 32 Bits compatibility layer for 64 bits processors */ extern long v4l2_compat_ioctl32(struct file *file, unsigned int cmd, unsigned long arg); #endif +typedef long (*v4l2_kioctl)(struct file *file, + unsigned int cmd, void *arg); + /* Include support for obsoleted stuff */ extern long video_usercopy(struct file *file, unsigned int cmd, unsigned long arg, v4l2_kioctl func); diff --git a/include/media/videobuf-core.h b/include/media/videobuf-core.h index 1d3835f..90ed895 100644 --- a/include/media/videobuf-core.h +++ b/include/media/videobuf-core.h @@ -17,10 +17,6 @@ #define _VIDEOBUF_CORE_H #include -#ifdef CONFIG_VIDEO_V4L1_COMPAT -#define __MIN_V4L1 -#include -#endif #include #define UNSET (-1U) @@ -212,10 +208,6 @@ int videobuf_qbuf(struct videobuf_queue *q, struct v4l2_buffer *b); int videobuf_dqbuf(struct videobuf_queue *q, struct v4l2_buffer *b, int nonblocking); -#ifdef CONFIG_VIDEO_V4L1_COMPAT -int videobuf_cgmbuf(struct videobuf_queue *q, - struct video_mbuf *mbuf, int count); -#endif int videobuf_streamon(struct videobuf_queue *q); int videobuf_streamoff(struct videobuf_queue *q); -- cgit v1.1 From 58c66df3e38ffb1d59cc5162bb9e07c859288034 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 27 Dec 2010 07:38:48 -0300 Subject: [media] Remove VIDEO_V4L1 Kconfig option There's no sense on keeping VIDEO_V4L1 Kconfig option just because of two deprecated drivers moved to staging scheduled to die on 2.6.39. Reviewed-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/videodev.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/videodev.h b/include/linux/videodev.h index 8a7aead..f11efbe 100644 --- a/include/linux/videodev.h +++ b/include/linux/videodev.h @@ -16,8 +16,6 @@ #include #include -#if defined(CONFIG_VIDEO_V4L1) || defined(CONFIG_VIDEO_V4L1_MODULE) || !defined(__KERNEL__) - #define VID_TYPE_CAPTURE 1 /* Can capture */ #define VID_TYPE_TUNER 2 /* Can tune */ #define VID_TYPE_TELETEXT 4 /* Does teletext */ @@ -311,8 +309,6 @@ struct video_code #define VID_PLAY_RESET 13 #define VID_PLAY_END_MARK 14 -#endif /* CONFIG_VIDEO_V4L1 */ - #endif /* __LINUX_VIDEODEV_H */ /* -- cgit v1.1 From 88ae7624a6fe890e5a8ca57b25420f66e1389f8b Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 27 Dec 2010 07:47:54 -0300 Subject: [media] V4L1 removal: Remove linux/videodev.h There's no sense on keeping it on 2.6.38, as nobody is using it anymore, at the kernel tree, and installing it at the userspace API. As two deprecated drivers still need it, move it to their internal directories. Reviewed-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/linux/Kbuild | 1 - include/linux/videodev.h | 318 ---------------------------------------------- include/media/ovcamchip.h | 90 ------------- 3 files changed, 409 deletions(-) delete mode 100644 include/linux/videodev.h delete mode 100644 include/media/ovcamchip.h (limited to 'include') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 97319a8..a354c19 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -367,7 +367,6 @@ header-y += utime.h header-y += utsname.h header-y += veth.h header-y += vhost.h -header-y += videodev.h header-y += videodev2.h header-y += virtio_9p.h header-y += virtio_balloon.h diff --git a/include/linux/videodev.h b/include/linux/videodev.h deleted file mode 100644 index f11efbe..0000000 --- a/include/linux/videodev.h +++ /dev/null @@ -1,318 +0,0 @@ -/* - * Video for Linux version 1 - OBSOLETE - * - * Header file for v4l1 drivers and applications, for - * Linux kernels 2.2.x or 2.4.x. - * - * Provides header for legacy drivers and applications - * - * See http://linuxtv.org for more info - * - */ -#ifndef __LINUX_VIDEODEV_H -#define __LINUX_VIDEODEV_H - -#include -#include -#include - -#define VID_TYPE_CAPTURE 1 /* Can capture */ -#define VID_TYPE_TUNER 2 /* Can tune */ -#define VID_TYPE_TELETEXT 4 /* Does teletext */ -#define VID_TYPE_OVERLAY 8 /* Overlay onto frame buffer */ -#define VID_TYPE_CHROMAKEY 16 /* Overlay by chromakey */ -#define VID_TYPE_CLIPPING 32 /* Can clip */ -#define VID_TYPE_FRAMERAM 64 /* Uses the frame buffer memory */ -#define VID_TYPE_SCALES 128 /* Scalable */ -#define VID_TYPE_MONOCHROME 256 /* Monochrome only */ -#define VID_TYPE_SUBCAPTURE 512 /* Can capture subareas of the image */ -#define VID_TYPE_MPEG_DECODER 1024 /* Can decode MPEG streams */ -#define VID_TYPE_MPEG_ENCODER 2048 /* Can encode MPEG streams */ -#define VID_TYPE_MJPEG_DECODER 4096 /* Can decode MJPEG streams */ -#define VID_TYPE_MJPEG_ENCODER 8192 /* Can encode MJPEG streams */ - -struct video_capability -{ - char name[32]; - int type; - int channels; /* Num channels */ - int audios; /* Num audio devices */ - int maxwidth; /* Supported width */ - int maxheight; /* And height */ - int minwidth; /* Supported width */ - int minheight; /* And height */ -}; - - -struct video_channel -{ - int channel; - char name[32]; - int tuners; - __u32 flags; -#define VIDEO_VC_TUNER 1 /* Channel has a tuner */ -#define VIDEO_VC_AUDIO 2 /* Channel has audio */ - __u16 type; -#define VIDEO_TYPE_TV 1 -#define VIDEO_TYPE_CAMERA 2 - __u16 norm; /* Norm set by channel */ -}; - -struct video_tuner -{ - int tuner; - char name[32]; - unsigned long rangelow, rangehigh; /* Tuner range */ - __u32 flags; -#define VIDEO_TUNER_PAL 1 -#define VIDEO_TUNER_NTSC 2 -#define VIDEO_TUNER_SECAM 4 -#define VIDEO_TUNER_LOW 8 /* Uses KHz not MHz */ -#define VIDEO_TUNER_NORM 16 /* Tuner can set norm */ -#define VIDEO_TUNER_STEREO_ON 128 /* Tuner is seeing stereo */ -#define VIDEO_TUNER_RDS_ON 256 /* Tuner is seeing an RDS datastream */ -#define VIDEO_TUNER_MBS_ON 512 /* Tuner is seeing an MBS datastream */ - __u16 mode; /* PAL/NTSC/SECAM/OTHER */ -#define VIDEO_MODE_PAL 0 -#define VIDEO_MODE_NTSC 1 -#define VIDEO_MODE_SECAM 2 -#define VIDEO_MODE_AUTO 3 - __u16 signal; /* Signal strength 16bit scale */ -}; - -struct video_picture -{ - __u16 brightness; - __u16 hue; - __u16 colour; - __u16 contrast; - __u16 whiteness; /* Black and white only */ - __u16 depth; /* Capture depth */ - __u16 palette; /* Palette in use */ -#define VIDEO_PALETTE_GREY 1 /* Linear greyscale */ -#define VIDEO_PALETTE_HI240 2 /* High 240 cube (BT848) */ -#define VIDEO_PALETTE_RGB565 3 /* 565 16 bit RGB */ -#define VIDEO_PALETTE_RGB24 4 /* 24bit RGB */ -#define VIDEO_PALETTE_RGB32 5 /* 32bit RGB */ -#define VIDEO_PALETTE_RGB555 6 /* 555 15bit RGB */ -#define VIDEO_PALETTE_YUV422 7 /* YUV422 capture */ -#define VIDEO_PALETTE_YUYV 8 -#define VIDEO_PALETTE_UYVY 9 /* The great thing about standards is ... */ -#define VIDEO_PALETTE_YUV420 10 -#define VIDEO_PALETTE_YUV411 11 /* YUV411 capture */ -#define VIDEO_PALETTE_RAW 12 /* RAW capture (BT848) */ -#define VIDEO_PALETTE_YUV422P 13 /* YUV 4:2:2 Planar */ -#define VIDEO_PALETTE_YUV411P 14 /* YUV 4:1:1 Planar */ -#define VIDEO_PALETTE_YUV420P 15 /* YUV 4:2:0 Planar */ -#define VIDEO_PALETTE_YUV410P 16 /* YUV 4:1:0 Planar */ -#define VIDEO_PALETTE_PLANAR 13 /* start of planar entries */ -#define VIDEO_PALETTE_COMPONENT 7 /* start of component entries */ -}; - -struct video_audio -{ - int audio; /* Audio channel */ - __u16 volume; /* If settable */ - __u16 bass, treble; - __u32 flags; -#define VIDEO_AUDIO_MUTE 1 -#define VIDEO_AUDIO_MUTABLE 2 -#define VIDEO_AUDIO_VOLUME 4 -#define VIDEO_AUDIO_BASS 8 -#define VIDEO_AUDIO_TREBLE 16 -#define VIDEO_AUDIO_BALANCE 32 - char name[16]; -#define VIDEO_SOUND_MONO 1 -#define VIDEO_SOUND_STEREO 2 -#define VIDEO_SOUND_LANG1 4 -#define VIDEO_SOUND_LANG2 8 - __u16 mode; - __u16 balance; /* Stereo balance */ - __u16 step; /* Step actual volume uses */ -}; - -struct video_clip -{ - __s32 x,y; - __s32 width, height; - struct video_clip *next; /* For user use/driver use only */ -}; - -struct video_window -{ - __u32 x,y; /* Position of window */ - __u32 width,height; /* Its size */ - __u32 chromakey; - __u32 flags; - struct video_clip __user *clips; /* Set only */ - int clipcount; -#define VIDEO_WINDOW_INTERLACE 1 -#define VIDEO_WINDOW_CHROMAKEY 16 /* Overlay by chromakey */ -#define VIDEO_CLIP_BITMAP -1 -/* bitmap is 1024x625, a '1' bit represents a clipped pixel */ -#define VIDEO_CLIPMAP_SIZE (128 * 625) -}; - -struct video_capture -{ - __u32 x,y; /* Offsets into image */ - __u32 width, height; /* Area to capture */ - __u16 decimation; /* Decimation divider */ - __u16 flags; /* Flags for capture */ -#define VIDEO_CAPTURE_ODD 0 /* Temporal */ -#define VIDEO_CAPTURE_EVEN 1 -}; - -struct video_buffer -{ - void *base; - int height,width; - int depth; - int bytesperline; -}; - -struct video_mmap -{ - unsigned int frame; /* Frame (0 - n) for double buffer */ - int height,width; - unsigned int format; /* should be VIDEO_PALETTE_* */ -}; - -struct video_key -{ - __u8 key[8]; - __u32 flags; -}; - -struct video_mbuf -{ - int size; /* Total memory to map */ - int frames; /* Frames */ - int offsets[VIDEO_MAX_FRAME]; -}; - -#define VIDEO_NO_UNIT (-1) - -struct video_unit -{ - int video; /* Video minor */ - int vbi; /* VBI minor */ - int radio; /* Radio minor */ - int audio; /* Audio minor */ - int teletext; /* Teletext minor */ -}; - -struct vbi_format { - __u32 sampling_rate; /* in Hz */ - __u32 samples_per_line; - __u32 sample_format; /* VIDEO_PALETTE_RAW only (1 byte) */ - __s32 start[2]; /* starting line for each frame */ - __u32 count[2]; /* count of lines for each frame */ - __u32 flags; -#define VBI_UNSYNC 1 /* can distingues between top/bottom field */ -#define VBI_INTERLACED 2 /* lines are interlaced */ -}; - -/* video_info is biased towards hardware mpeg encode/decode */ -/* but it could apply generically to any hardware compressor/decompressor */ -struct video_info -{ - __u32 frame_count; /* frames output since decode/encode began */ - __u32 h_size; /* current unscaled horizontal size */ - __u32 v_size; /* current unscaled veritcal size */ - __u32 smpte_timecode; /* current SMPTE timecode (for current GOP) */ - __u32 picture_type; /* current picture type */ - __u32 temporal_reference; /* current temporal reference */ - __u8 user_data[256]; /* user data last found in compressed stream */ - /* user_data[0] contains user data flags, user_data[1] has count */ -}; - -/* generic structure for setting playback modes */ -struct video_play_mode -{ - int mode; - int p1; - int p2; -}; - -/* for loading microcode / fpga programming */ -struct video_code -{ - char loadwhat[16]; /* name or tag of file being passed */ - int datasize; - __u8 *data; -}; - -#define VIDIOCGCAP _IOR('v',1,struct video_capability) /* Get capabilities */ -#define VIDIOCGCHAN _IOWR('v',2,struct video_channel) /* Get channel info (sources) */ -#define VIDIOCSCHAN _IOW('v',3,struct video_channel) /* Set channel */ -#define VIDIOCGTUNER _IOWR('v',4,struct video_tuner) /* Get tuner abilities */ -#define VIDIOCSTUNER _IOW('v',5,struct video_tuner) /* Tune the tuner for the current channel */ -#define VIDIOCGPICT _IOR('v',6,struct video_picture) /* Get picture properties */ -#define VIDIOCSPICT _IOW('v',7,struct video_picture) /* Set picture properties */ -#define VIDIOCCAPTURE _IOW('v',8,int) /* Start, end capture */ -#define VIDIOCGWIN _IOR('v',9, struct video_window) /* Get the video overlay window */ -#define VIDIOCSWIN _IOW('v',10, struct video_window) /* Set the video overlay window - passes clip list for hardware smarts , chromakey etc */ -#define VIDIOCGFBUF _IOR('v',11, struct video_buffer) /* Get frame buffer */ -#define VIDIOCSFBUF _IOW('v',12, struct video_buffer) /* Set frame buffer - root only */ -#define VIDIOCKEY _IOR('v',13, struct video_key) /* Video key event - to dev 255 is to all - cuts capture on all DMA windows with this key (0xFFFFFFFF == all) */ -#define VIDIOCGFREQ _IOR('v',14, unsigned long) /* Set tuner */ -#define VIDIOCSFREQ _IOW('v',15, unsigned long) /* Set tuner */ -#define VIDIOCGAUDIO _IOR('v',16, struct video_audio) /* Get audio info */ -#define VIDIOCSAUDIO _IOW('v',17, struct video_audio) /* Audio source, mute etc */ -#define VIDIOCSYNC _IOW('v',18, int) /* Sync with mmap grabbing */ -#define VIDIOCMCAPTURE _IOW('v',19, struct video_mmap) /* Grab frames */ -#define VIDIOCGMBUF _IOR('v',20, struct video_mbuf) /* Memory map buffer info */ -#define VIDIOCGUNIT _IOR('v',21, struct video_unit) /* Get attached units */ -#define VIDIOCGCAPTURE _IOR('v',22, struct video_capture) /* Get subcapture */ -#define VIDIOCSCAPTURE _IOW('v',23, struct video_capture) /* Set subcapture */ -#define VIDIOCSPLAYMODE _IOW('v',24, struct video_play_mode) /* Set output video mode/feature */ -#define VIDIOCSWRITEMODE _IOW('v',25, int) /* Set write mode */ -#define VIDIOCGPLAYINFO _IOR('v',26, struct video_info) /* Get current playback info from hardware */ -#define VIDIOCSMICROCODE _IOW('v',27, struct video_code) /* Load microcode into hardware */ -#define VIDIOCGVBIFMT _IOR('v',28, struct vbi_format) /* Get VBI information */ -#define VIDIOCSVBIFMT _IOW('v',29, struct vbi_format) /* Set VBI information */ - - -#define BASE_VIDIOCPRIVATE 192 /* 192-255 are private */ - -/* VIDIOCSWRITEMODE */ -#define VID_WRITE_MPEG_AUD 0 -#define VID_WRITE_MPEG_VID 1 -#define VID_WRITE_OSD 2 -#define VID_WRITE_TTX 3 -#define VID_WRITE_CC 4 -#define VID_WRITE_MJPEG 5 - -/* VIDIOCSPLAYMODE */ -#define VID_PLAY_VID_OUT_MODE 0 - /* p1: = VIDEO_MODE_PAL, VIDEO_MODE_NTSC, etc ... */ -#define VID_PLAY_GENLOCK 1 - /* p1: 0 = OFF, 1 = ON */ - /* p2: GENLOCK FINE DELAY value */ -#define VID_PLAY_NORMAL 2 -#define VID_PLAY_PAUSE 3 -#define VID_PLAY_SINGLE_FRAME 4 -#define VID_PLAY_FAST_FORWARD 5 -#define VID_PLAY_SLOW_MOTION 6 -#define VID_PLAY_IMMEDIATE_NORMAL 7 -#define VID_PLAY_SWITCH_CHANNELS 8 -#define VID_PLAY_FREEZE_FRAME 9 -#define VID_PLAY_STILL_MODE 10 -#define VID_PLAY_MASTER_MODE 11 - /* p1: see below */ -#define VID_PLAY_MASTER_NONE 1 -#define VID_PLAY_MASTER_VIDEO 2 -#define VID_PLAY_MASTER_AUDIO 3 -#define VID_PLAY_ACTIVE_SCANLINES 12 - /* p1 = first active; p2 = last active */ -#define VID_PLAY_RESET 13 -#define VID_PLAY_END_MARK 14 - -#endif /* __LINUX_VIDEODEV_H */ - -/* - * Local variables: - * c-basic-offset: 8 - * End: - */ diff --git a/include/media/ovcamchip.h b/include/media/ovcamchip.h deleted file mode 100644 index 05b9569..0000000 --- a/include/media/ovcamchip.h +++ /dev/null @@ -1,90 +0,0 @@ -/* OmniVision* camera chip driver API - * - * Copyright (c) 1999-2004 Mark McClelland - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. NO WARRANTY OF ANY KIND is expressed or implied. - * - * * OmniVision is a trademark of OmniVision Technologies, Inc. This driver - * is not sponsored or developed by them. - */ - -#ifndef __LINUX_OVCAMCHIP_H -#define __LINUX_OVCAMCHIP_H - -#include -#include - -/* --------------------------------- */ -/* ENUMERATIONS */ -/* --------------------------------- */ - -/* Controls */ -enum { - OVCAMCHIP_CID_CONT, /* Contrast */ - OVCAMCHIP_CID_BRIGHT, /* Brightness */ - OVCAMCHIP_CID_SAT, /* Saturation */ - OVCAMCHIP_CID_HUE, /* Hue */ - OVCAMCHIP_CID_EXP, /* Exposure */ - OVCAMCHIP_CID_FREQ, /* Light frequency */ - OVCAMCHIP_CID_BANDFILT, /* Banding filter */ - OVCAMCHIP_CID_AUTOBRIGHT, /* Auto brightness */ - OVCAMCHIP_CID_AUTOEXP, /* Auto exposure */ - OVCAMCHIP_CID_BACKLIGHT, /* Back light compensation */ - OVCAMCHIP_CID_MIRROR, /* Mirror horizontally */ -}; - -/* Chip types */ -#define NUM_CC_TYPES 9 -enum { - CC_UNKNOWN, - CC_OV76BE, - CC_OV7610, - CC_OV7620, - CC_OV7620AE, - CC_OV6620, - CC_OV6630, - CC_OV6630AE, - CC_OV6630AF, -}; - -/* --------------------------------- */ -/* I2C ADDRESSES */ -/* --------------------------------- */ - -#define OV7xx0_SID (0x42 >> 1) -#define OV6xx0_SID (0xC0 >> 1) - -/* --------------------------------- */ -/* API */ -/* --------------------------------- */ - -struct ovcamchip_control { - __u32 id; - __s32 value; -}; - -struct ovcamchip_window { - int x; - int y; - int width; - int height; - int format; - int quarter; /* Scale width and height down 2x */ - - /* This stuff will be removed eventually */ - int clockdiv; /* Clock divisor setting */ -}; - -/* Commands */ -#define OVCAMCHIP_CMD_Q_SUBTYPE _IOR (0x88, 0x00, int) -#define OVCAMCHIP_CMD_INITIALIZE _IOW (0x88, 0x01, int) -/* You must call OVCAMCHIP_CMD_INITIALIZE before any of commands below! */ -#define OVCAMCHIP_CMD_S_CTRL _IOW (0x88, 0x02, struct ovcamchip_control) -#define OVCAMCHIP_CMD_G_CTRL _IOWR (0x88, 0x03, struct ovcamchip_control) -#define OVCAMCHIP_CMD_S_MODE _IOW (0x88, 0x04, struct ovcamchip_window) -#define OVCAMCHIP_MAX_CMD _IO (0x88, 0x3f) - -#endif -- cgit v1.1 From b7a0f2e793a52b306e682a0e2e9a0b6f0f0a730e Mon Sep 17 00:00:00 2001 From: Ramiro Morales Date: Sun, 26 Dec 2010 18:13:30 -0300 Subject: [media] saa7134: Add support for Compro VideoMate Vista M1F Signed-off-by: Pavel Osnova Signed-off-by: Ramiro Morales Signed-off-by: Mauro Carvalho Chehab --- include/media/rc-map.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/media/rc-map.h b/include/media/rc-map.h index 5d3a457..ee9e2f7 100644 --- a/include/media/rc-map.h +++ b/include/media/rc-map.h @@ -138,6 +138,7 @@ void rc_map_init(void); #define RC_MAP_TREKSTOR "rc-trekstor" #define RC_MAP_TT_1500 "rc-tt-1500" #define RC_MAP_TWINHAN_VP1027_DVBS "rc-twinhan1027" +#define RC_MAP_VIDEOMATE_M1F "rc-videomate-m1f" #define RC_MAP_VIDEOMATE_S350 "rc-videomate-s350" #define RC_MAP_VIDEOMATE_TV_PVR "rc-videomate-tv-pvr" #define RC_MAP_WINFAST "rc-winfast" -- cgit v1.1 From b9218f2f15cdff8991ba041993bf40962c49fdd0 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Mon, 27 Dec 2010 12:22:46 -0300 Subject: [media] saa6588: rename rds.h to saa6588.h The naming of the media/rds.h header suggested that it was a generic RDS header, when in fact it is just a saa6588 module API that is internal to the kernel. Rename the header and the struct and defines in it to make this clear. Also removed the header include in radio-si470x.h (not used anymore) and from ioctl-number.txt (it's internal to the kernel and never called from userspace). Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/rds.h | 44 -------------------------------------------- include/media/saa6588.h | 42 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 42 insertions(+), 44 deletions(-) delete mode 100644 include/media/rds.h create mode 100644 include/media/saa6588.h (limited to 'include') diff --git a/include/media/rds.h b/include/media/rds.h deleted file mode 100644 index a894266..0000000 --- a/include/media/rds.h +++ /dev/null @@ -1,44 +0,0 @@ -/* - - Types and defines needed for RDS. This is included by - saa6588.c and every driver (e.g. bttv-driver.c) that wants - to use the saa6588 module. - - Instead of having a separate rds.h, I'd prefer to include - this stuff in one of the already existing files like tuner.h - - (c) 2005 by Hans J. Koch - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - -*/ - -#ifndef _RDS_H -#define _RDS_H - -struct rds_command { - unsigned int block_count; - int result; - unsigned char __user *buffer; - struct file *instance; - poll_table *event_list; -}; - -#define RDS_CMD_OPEN _IOW('R',1,int) -#define RDS_CMD_CLOSE _IOW('R',2,int) -#define RDS_CMD_READ _IOR('R',3,int) -#define RDS_CMD_POLL _IOR('R',4,int) - -#endif diff --git a/include/media/saa6588.h b/include/media/saa6588.h new file mode 100644 index 0000000..2c3c442 --- /dev/null +++ b/include/media/saa6588.h @@ -0,0 +1,42 @@ +/* + + Types and defines needed for RDS. This is included by + saa6588.c and every driver (e.g. bttv-driver.c) that wants + to use the saa6588 module. + + (c) 2005 by Hans J. Koch + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + +*/ + +#ifndef _SAA6588_H +#define _SAA6588_H + +struct saa6588_command { + unsigned int block_count; + int result; + unsigned char __user *buffer; + struct file *instance; + poll_table *event_list; +}; + +/* These ioctls are internal to the kernel */ +#define SAA6588_CMD_OPEN _IOW('R', 1, int) +#define SAA6588_CMD_CLOSE _IOW('R', 2, int) +#define SAA6588_CMD_READ _IOR('R', 3, int) +#define SAA6588_CMD_POLL _IOR('R', 4, int) + +#endif -- cgit v1.1 From 66832aef0694807f487a8ccc8871cea4e80d78c5 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Mon, 27 Dec 2010 12:27:50 -0300 Subject: [media] bt819: the ioctls in the header are internal to the kernel Remove bt819.h from ioctl-number.txt and make a note in the header that these ioctls are for internal use only. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/bt819.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/bt819.h b/include/media/bt819.h index 38f666b..8025f4b 100644 --- a/include/media/bt819.h +++ b/include/media/bt819.h @@ -26,7 +26,10 @@ /* v4l2_device notifications. */ /* Needed to reset the FIFO buffer when changing the input - or the video standard. */ + or the video standard. + + Note: these ioctls that internal to the kernel and are never called + from userspace. */ #define BT819_FIFO_RESET_LOW _IO('b', 0) #define BT819_FIFO_RESET_HIGH _IO('b', 1) -- cgit v1.1 From 09c730a488c32c2cadb31cdb8dcc4df528441197 Mon Sep 17 00:00:00 2001 From: Sundar Iyer Date: Tue, 21 Dec 2010 15:53:31 +0530 Subject: input/tc3589x: add tc3589x keypad support Add support for the keypad controller module found on the TC3589X devices. This driver default adds the support for TC35893 device. Signed-off-by: Sundar Iyer Acked-by: Dmitry Torokhov [Some minor fixups for compilation] Signed-off-by: Linus Walleij --- include/linux/mfd/tc3589x.h | 52 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/tc3589x.h b/include/linux/mfd/tc3589x.h index da00958..16c76e1 100644 --- a/include/linux/mfd/tc3589x.h +++ b/include/linux/mfd/tc3589x.h @@ -20,6 +20,17 @@ enum tx3589x_block { #define TC3589x_RSTCTRL_KBDRST (1 << 1) #define TC3589x_RSTCTRL_GPIRST (1 << 0) +/* Keyboard Configuration Registers */ +#define TC3589x_KBDSETTLE_REG 0x01 +#define TC3589x_KBDBOUNCE 0x02 +#define TC3589x_KBDSIZE 0x03 +#define TC3589x_KBCFG_LSB 0x04 +#define TC3589x_KBCFG_MSB 0x05 +#define TC3589x_KBDIC 0x08 +#define TC3589x_KBDMSK 0x09 +#define TC3589x_EVTCODE_FIFO 0x10 +#define TC3589x_KBDMFS 0x8F + #define TC3589x_IRQST 0x91 #define TC3589x_MANFCODE_MAGIC 0x03 @@ -35,6 +46,14 @@ enum tx3589x_block { #define TC3589x_EXTRSTN 0x83 #define TC3589x_RSTINTCLR 0x84 +/* Pull up/down configuration registers */ +#define TC3589x_IOCFG 0xA7 +#define TC3589x_IOPULLCFG0_LSB 0xAA +#define TC3589x_IOPULLCFG0_MSB 0xAB +#define TC3589x_IOPULLCFG1_LSB 0xAC +#define TC3589x_IOPULLCFG1_MSB 0xAD +#define TC3589x_IOPULLCFG2_LSB 0xAE + #define TC3589x_GPIOIS0 0xC9 #define TC3589x_GPIOIS1 0xCA #define TC3589x_GPIOIS2 0xCB @@ -112,6 +131,37 @@ extern int tc3589x_block_write(struct tc3589x *tc3589x, u8 reg, u8 length, const u8 *values); extern int tc3589x_set_bits(struct tc3589x *tc3589x, u8 reg, u8 mask, u8 val); +/* + * Keypad related platform specific constants + * These values may be modified for fine tuning + */ +#define TC_KPD_ROWS 0x8 +#define TC_KPD_COLUMNS 0x8 +#define TC_KPD_DEBOUNCE_PERIOD 0xA3 +#define TC_KPD_SETTLE_TIME 0xA3 + +/** + * struct tc35893_platform_data - data structure for platform specific data + * @keymap_data: matrix scan code table for keycodes + * @krow: mask for available rows, value is 0xFF + * @kcol: mask for available columns, value is 0xFF + * @debounce_period: platform specific debounce time + * @settle_time: platform specific settle down time + * @irqtype: type of interrupt, falling or rising edge + * @enable_wakeup: specifies if keypad event can wake up system from sleep + * @no_autorepeat: flag for auto repetition + */ +struct tc3589x_keypad_platform_data { + const struct matrix_keymap_data *keymap_data; + u8 krow; + u8 kcol; + u8 debounce_period; + u8 settle_time; + unsigned long irqtype; + bool enable_wakeup; + bool no_autorepeat; +}; + /** * struct tc3589x_gpio_platform_data - TC3589x GPIO platform data * @gpio_base: first gpio number assigned to TC3589x. A maximum of @@ -130,11 +180,13 @@ struct tc3589x_gpio_platform_data { * @block: bitmask of blocks to enable (use TC3589x_BLOCK_*) * @irq_base: base IRQ number. %TC3589x_NR_IRQS irqs will be used. * @gpio: GPIO-specific platform data + * @keypad: keypad-specific platform data */ struct tc3589x_platform_data { unsigned int block; int irq_base; struct tc3589x_gpio_platform_data *gpio; + const struct tc3589x_keypad_platform_data *keypad; }; #define TC3589x_NR_GPIOS 24 -- cgit v1.1 From 9706a36e35c4ce04f28a62cfe1205b4e3b0dd13c Mon Sep 17 00:00:00 2001 From: Stephen Neuendorffer Date: Thu, 18 Nov 2010 15:54:59 -0800 Subject: of/flattree: Add non-boottime device tree functions In preparation for providing run-time handling of device trees, factor out some of the basic functions so that they take an arbitrary blob, rather than relying on the single boot-time tree. V2: - functions have of_fdt_* names - removed find_flat_dt_string - blob argument is first Signed-off-by: Stephen Neuendorffer Signed-off-by: Grant Likely --- include/linux/of_fdt.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index 7bbf5b3..70c5b73 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -58,6 +58,17 @@ struct boot_param_header { }; #if defined(CONFIG_OF_FLATTREE) + +/* For scanning an arbitrary device-tree at any time */ +extern char *of_fdt_get_string(struct boot_param_header *blob, u32 offset); +extern void *of_fdt_get_property(struct boot_param_header *blob, + unsigned long node, + const char *name, + unsigned long *size); +extern int of_fdt_is_compatible(struct boot_param_header *blob, + unsigned long node, + const char *compat); + /* TBD: Temporary export of fdt globals - remove when code fully merged */ extern int __initdata dt_root_addr_cells; extern int __initdata dt_root_size_cells; -- cgit v1.1 From fe14042358fac0673d4b6362a73796fd64379938 Mon Sep 17 00:00:00 2001 From: Stephen Neuendorffer Date: Thu, 18 Nov 2010 15:55:02 -0800 Subject: of/flattree: Refactor unflatten_device_tree and add fdt_unflatten_tree unflatten_device_tree has two dependencies on things that happen during boot time. Firstly, it references the initial device tree directly. Secondly, it allocates memory using the early boot allocator. This patch factors out these dependencies and uses the new __unflatten_device_tree function to implement a driver-visible fdt_unflatten_tree function, which can be used to unflatten a blob after boot time. V2: - remove extra __va() call - make dt_alloc functions return void *. This doesn't fix the general strangeness in this code that constantly casts back and forth between unsigned long and __be32 * Signed-off-by: Stephen Neuendorffer Signed-off-by: Grant Likely --- include/linux/of_fdt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index 70c5b73..9ce5dfd 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -68,6 +68,8 @@ extern void *of_fdt_get_property(struct boot_param_header *blob, extern int of_fdt_is_compatible(struct boot_param_header *blob, unsigned long node, const char *compat); +extern void of_fdt_unflatten_tree(unsigned long *blob, + struct device_node **mynodes); /* TBD: Temporary export of fdt globals - remove when code fully merged */ extern int __initdata dt_root_addr_cells; -- cgit v1.1 From 513521eaee4375a1a0da0b73c7131a165a9fe4d9 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 29 Dec 2010 14:25:52 -0300 Subject: [media] v4l2-ctrls: use const char * const * for the menu arrays This prevents checkpatch warnings generated when defining 'static const char *foo[]' arrays. It makes sense to use const char * const * anyway since the pointers in the array are indeed const. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/media/cx2341x.h | 2 +- include/media/v4l2-common.h | 6 +++--- include/media/v4l2-ctrls.h | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/media/cx2341x.h b/include/media/cx2341x.h index 8d08ebf..9635eeb 100644 --- a/include/media/cx2341x.h +++ b/include/media/cx2341x.h @@ -95,7 +95,7 @@ int cx2341x_update(void *priv, cx2341x_mbox_func func, const struct cx2341x_mpeg_params *new); int cx2341x_ctrl_query(const struct cx2341x_mpeg_params *params, struct v4l2_queryctrl *qctrl); -const char **cx2341x_ctrl_get_menu(const struct cx2341x_mpeg_params *p, u32 id); +const char * const *cx2341x_ctrl_get_menu(const struct cx2341x_mpeg_params *p, u32 id); int cx2341x_ext_ctrls(struct cx2341x_mpeg_params *params, int busy, struct v4l2_ext_controls *ctrls, unsigned int cmd); void cx2341x_fill_defaults(struct cx2341x_mpeg_params *p); diff --git a/include/media/v4l2-common.h b/include/media/v4l2-common.h index 239125a..2d65b35 100644 --- a/include/media/v4l2-common.h +++ b/include/media/v4l2-common.h @@ -98,12 +98,12 @@ int v4l2_prio_check(struct v4l2_prio_state *global, enum v4l2_priority local); /* Control helper functions */ int v4l2_ctrl_check(struct v4l2_ext_control *ctrl, struct v4l2_queryctrl *qctrl, - const char **menu_items); + const char * const *menu_items); const char *v4l2_ctrl_get_name(u32 id); -const char **v4l2_ctrl_get_menu(u32 id); +const char * const *v4l2_ctrl_get_menu(u32 id); int v4l2_ctrl_query_fill(struct v4l2_queryctrl *qctrl, s32 min, s32 max, s32 step, s32 def); int v4l2_ctrl_query_menu(struct v4l2_querymenu *qmenu, - struct v4l2_queryctrl *qctrl, const char **menu_items); + struct v4l2_queryctrl *qctrl, const char * const *menu_items); #define V4L2_CTRL_MENU_IDS_END (0xffffffff) int v4l2_ctrl_query_menu_valid_items(struct v4l2_querymenu *qmenu, const u32 *ids); diff --git a/include/media/v4l2-ctrls.h b/include/media/v4l2-ctrls.h index 9b7bea9..d69ab4a 100644 --- a/include/media/v4l2-ctrls.h +++ b/include/media/v4l2-ctrls.h @@ -112,7 +112,7 @@ struct v4l2_ctrl { u32 step; u32 menu_skip_mask; }; - const char **qmenu; + const char * const *qmenu; unsigned long flags; union { s32 val; @@ -202,7 +202,7 @@ struct v4l2_ctrl_config { s32 def; u32 flags; u32 menu_skip_mask; - const char **qmenu; + const char * const *qmenu; unsigned int is_private:1; unsigned int is_volatile:1; }; -- cgit v1.1 From 3153ac9c6208892ee237caccdbe2290f8247e236 Mon Sep 17 00:00:00 2001 From: Alberto Panizzo Date: Thu, 2 Dec 2010 11:53:28 -0300 Subject: [media] V4L2: Add a v4l2-subdev (soc-camera) driver for OmniVision OV2640 sensor Signed-off-by: Alberto Panizzo Signed-off-by: Guennadi Liakhovetski Signed-off-by: Mauro Carvalho Chehab --- include/media/v4l2-chip-ident.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/media/v4l2-chip-ident.h b/include/media/v4l2-chip-ident.h index 51e89f2..44fe44e 100644 --- a/include/media/v4l2-chip-ident.h +++ b/include/media/v4l2-chip-ident.h @@ -74,6 +74,7 @@ enum { V4L2_IDENT_SOI968 = 256, V4L2_IDENT_OV9640 = 257, V4L2_IDENT_OV6650 = 258, + V4L2_IDENT_OV2640 = 259, /* module saa7146: reserved range 300-309 */ V4L2_IDENT_SAA7146 = 300, -- cgit v1.1 From 96e442c1b2ef2ba9476e5da2607ba666ce09664d Mon Sep 17 00:00:00 2001 From: Alberto Panizzo Date: Thu, 2 Dec 2010 07:43:37 -0300 Subject: [media] soc_camera: Add the ability to bind regulators to soc_camedra devices In certain machines, camera devices are supplied directly by a number of regulators. This patch add the ability to drive these regulators directly by the soc_camera driver. Signed-off-by: Alberto Panizzo Signed-off-by: Guennadi Liakhovetski Signed-off-by: Mauro Carvalho Chehab --- include/media/soc_camera.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/media/soc_camera.h b/include/media/soc_camera.h index 86e3631..9386db8 100644 --- a/include/media/soc_camera.h +++ b/include/media/soc_camera.h @@ -97,6 +97,7 @@ struct soc_camera_host_ops { #define SOCAM_SENSOR_INVERT_DATA (1 << 4) struct i2c_board_info; +struct regulator_bulk_data; struct soc_camera_link { /* Camera bus id, used to match a camera and a bus */ @@ -108,6 +109,10 @@ struct soc_camera_link { const char *module_name; void *priv; + /* Optional regulators that have to be managed on power on/off events */ + struct regulator_bulk_data *regulators; + int num_regulators; + /* * For non-I2C devices platform platform has to provide methods to * add a device to the system and to remove -- cgit v1.1 From df4da5cdfca05b37b366b9c69925b68586969c1c Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 31 Dec 2010 02:22:18 -0600 Subject: [SCSI] libiscsi: add more informative failure message during iscsi scsi eh This adds a more informative error code and message for the iscsi scsi eh session drop paths. This allows you to distinguish if the session was dropped due to a connection failure vs the iscsi layer dropping the session due to scsi eh failure processing. Signed-off-by: Mike Christie Signed-off-by: James Bottomley --- include/scsi/iscsi_if.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/scsi/iscsi_if.h b/include/scsi/iscsi_if.h index a8631ac..c3e1cbc 100644 --- a/include/scsi/iscsi_if.h +++ b/include/scsi/iscsi_if.h @@ -263,6 +263,7 @@ enum iscsi_err { ISCSI_ERR_INVALID_HOST = ISCSI_ERR_BASE + 18, ISCSI_ERR_XMIT_FAILED = ISCSI_ERR_BASE + 19, ISCSI_ERR_TCP_CONN_CLOSE = ISCSI_ERR_BASE + 20, + ISCSI_ERR_SCSI_EH_SESSION_RST = ISCSI_ERR_BASE + 21, }; /* -- cgit v1.1 From f41d472179a0d7c8e8160c85180ab1124947068e Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Fri, 31 Dec 2010 02:22:21 -0600 Subject: [SCSI] libiscsi: do not take host lock in queuecommand iscsi_tcp, ib_iser, cxgb*, be2iscsi and bnx2i do not use the host lock and do not take the session lock against a irq, so this patch drops the DEF_SCSI_QCMD use. Instead we just take the session lock and disable bhs. Signed-off-by: Mike Christie Signed-off-by: James Bottomley --- include/scsi/libiscsi.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index 68e951d..748382b 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -89,6 +89,7 @@ enum { ISCSI_TASK_RUNNING, ISCSI_TASK_ABRT_TMF, /* aborted due to TMF */ ISCSI_TASK_ABRT_SESS_RECOV, /* aborted due to session recovery */ + ISCSI_TASK_REQUEUE_SCSIQ, /* qcmd requeueing to scsi-ml */ }; struct iscsi_r2t_info { @@ -341,7 +342,7 @@ extern int iscsi_eh_abort(struct scsi_cmnd *sc); extern int iscsi_eh_recover_target(struct scsi_cmnd *sc); extern int iscsi_eh_session_reset(struct scsi_cmnd *sc); extern int iscsi_eh_device_reset(struct scsi_cmnd *sc); -extern int iscsi_queuecommand(struct Scsi_Host *h, struct scsi_cmnd *sc); +extern int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc); /* * iSCSI host helpers. -- cgit v1.1 From 3e29027af43728c2a91fe3f735ab2822edaf54a8 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 30 Dec 2010 09:25:46 +0000 Subject: dcbnl: add support for ieee8021Qaz attributes The IEEE8021Qaz is the IEEE standard version of CEE. The standard has had enough significant changes from the CEE version that many of the CEE attributes have no meaning in the new spec or do not easily map to IEEE standards. Rather then attempt to create a complicated mapping between CEE and IEEE standards this patch adds a nested IEEE attribute to the list of DCB attributes. The policy is, [DCB_ATTR_IFNAME] [DCB_ATTR_STATE] ... [DCB_ATTR_IEEE] [DCB_ATTR_IEEE_ETS] [DCB_ATTR_IEEE_PFC] [DCB_ATTR_IEEE_APP_TABLE] [DCB_ATTR_IEEE_APP] ... The following dcbnl_rtnl_ops routines were added to handle the IEEE standard, int (*ieee_getets) (struct net_device *, struct ieee_ets *); int (*ieee_setets) (struct net_device *, struct ieee_ets *); int (*ieee_getpfc) (struct net_device *, struct ieee_pfc *); int (*ieee_setpfc) (struct net_device *, struct ieee_pfc *); int (*ieee_getapp) (struct net_device *, struct dcb_app *); int (*ieee_setapp) (struct net_device *, struct dcb_app *); Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/dcbnl.h | 106 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/net/dcbnl.h | 11 ++++++ 2 files changed, 117 insertions(+) (limited to 'include') diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h index 8723491..287b561 100644 --- a/include/linux/dcbnl.h +++ b/include/linux/dcbnl.h @@ -22,6 +22,87 @@ #include +/* IEEE 802.1Qaz std supported values */ +#define IEEE_8021QAZ_MAX_TCS 8 + +/* This structure contains the IEEE 802.1Qaz ETS managed object + * + * @willing: willing bit in ETS configuratin TLV + * @ets_cap: indicates supported capacity of ets feature + * @cbs: credit based shaper ets algorithm supported + * @tc_tx_bw: tc tx bandwidth indexed by traffic class + * @tc_rx_bw: tc rx bandwidth indexed by traffic class + * @tc_tsa: TSA Assignment table, indexed by traffic class + * @prio_tc: priority assignment table mapping 8021Qp to traffic class + * @tc_reco_bw: recommended tc bandwidth indexed by traffic class for TLV + * @tc_reco_tsa: recommended tc bandwidth indexed by traffic class for TLV + * @reco_prio_tc: recommended tc tx bandwidth indexed by traffic class for TLV + * + * Recommended values are used to set fields in the ETS recommendation TLV + * with hardware offloaded LLDP. + * + * ---- + * TSA Assignment 8 bit identifiers + * 0 strict priority + * 1 credit-based shaper + * 2 enhanced transmission selection + * 3-254 reserved + * 255 vendor specific + */ +struct ieee_ets { + __u8 willing; + __u8 ets_cap; + __u8 cbs; + __u8 tc_tx_bw[IEEE_8021QAZ_MAX_TCS]; + __u8 tc_rx_bw[IEEE_8021QAZ_MAX_TCS]; + __u8 tc_tsa[IEEE_8021QAZ_MAX_TCS]; + __u8 prio_tc[IEEE_8021QAZ_MAX_TCS]; + __u8 tc_reco_bw[IEEE_8021QAZ_MAX_TCS]; + __u8 tc_reco_tsa[IEEE_8021QAZ_MAX_TCS]; + __u8 reco_prio_tc[IEEE_8021QAZ_MAX_TCS]; +}; + +/* This structure contains the IEEE 802.1Qaz PFC managed object + * + * @pfc_cap: Indicates the number of traffic classes on the local device + * that may simultaneously have PFC enabled. + * @pfc_en: bitmap indicating pfc enabled traffic classes + * @mbc: enable macsec bypass capability + * @delay: the allowance made for a round-trip propagation delay of the + * link in bits. + * @requests: count of the sent pfc frames + * @indications: count of the received pfc frames + */ +struct ieee_pfc { + __u8 pfc_cap; + __u8 pfc_en; + __u8 mbc; + __u16 delay; + __u64 requests[IEEE_8021QAZ_MAX_TCS]; + __u64 indications[IEEE_8021QAZ_MAX_TCS]; +}; + +/* This structure contains the IEEE 802.1Qaz APP managed object + * + * @selector: protocol identifier type + * @protocol: protocol of type indicated + * @priority: 3-bit unsigned integer indicating priority + * + * ---- + * Selector field values + * 0 Reserved + * 1 Ethertype + * 2 Well known port number over TCP or SCTP + * 3 Well known port number over UDP or DCCP + * 4 Well known port number over TCP, SCTP, UDP, or DCCP + * 5-7 Reserved + */ +struct dcb_app { + __u8 selector; + __u32 protocol; + __u8 priority; +}; + struct dcbmsg { __u8 dcb_family; __u8 cmd; @@ -50,6 +131,8 @@ struct dcbmsg { * @DCB_CMD_SBCN: get backward congestion notification configration. * @DCB_CMD_GAPP: get application protocol configuration * @DCB_CMD_SAPP: set application protocol configuration + * @DCB_CMD_IEEE_SET: set IEEE 802.1Qaz configuration + * @DCB_CMD_IEEE_GET: get IEEE 802.1Qaz configuration */ enum dcbnl_commands { DCB_CMD_UNDEFINED, @@ -83,6 +166,9 @@ enum dcbnl_commands { DCB_CMD_GAPP, DCB_CMD_SAPP, + DCB_CMD_IEEE_SET, + DCB_CMD_IEEE_GET, + __DCB_CMD_ENUM_MAX, DCB_CMD_MAX = __DCB_CMD_ENUM_MAX - 1, }; @@ -102,6 +188,7 @@ enum dcbnl_commands { * @DCB_ATTR_CAP: DCB capabilities of the device (NLA_NESTED) * @DCB_ATTR_NUMTCS: number of traffic classes supported (NLA_NESTED) * @DCB_ATTR_BCN: backward congestion notification configuration (NLA_NESTED) + * @DCB_ATTR_IEEE: IEEE 802.1Qaz supported attributes (NLA_NESTED) */ enum dcbnl_attrs { DCB_ATTR_UNDEFINED, @@ -119,10 +206,29 @@ enum dcbnl_attrs { DCB_ATTR_BCN, DCB_ATTR_APP, + /* IEEE std attributes */ + DCB_ATTR_IEEE, + __DCB_ATTR_ENUM_MAX, DCB_ATTR_MAX = __DCB_ATTR_ENUM_MAX - 1, }; +enum ieee_attrs { + DCB_ATTR_IEEE_UNSPEC, + DCB_ATTR_IEEE_ETS, + DCB_ATTR_IEEE_PFC, + DCB_ATTR_IEEE_APP_TABLE, + __DCB_ATTR_IEEE_MAX +}; +#define DCB_ATTR_IEEE_MAX (__DCB_ATTR_IEEE_MAX - 1) + +enum ieee_attrs_app { + DCB_ATTR_IEEE_APP_UNSPEC, + DCB_ATTR_IEEE_APP, + __DCB_ATTR_IEEE_APP_MAX +}; +#define DCB_ATTR_IEEE_APP_MAX (__DCB_ATTR_IEEE_APP_MAX - 1) + /** * enum dcbnl_pfc_attrs - DCB Priority Flow Control user priority nested attrs * diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h index b36ac7e..e2d841e 100644 --- a/include/net/dcbnl.h +++ b/include/net/dcbnl.h @@ -20,11 +20,22 @@ #ifndef __NET_DCBNL_H__ #define __NET_DCBNL_H__ +#include + /* * Ops struct for the netlink callbacks. Used by DCB-enabled drivers through * the netdevice struct. */ struct dcbnl_rtnl_ops { + /* IEEE 802.1Qaz std */ + int (*ieee_getets) (struct net_device *, struct ieee_ets *); + int (*ieee_setets) (struct net_device *, struct ieee_ets *); + int (*ieee_getpfc) (struct net_device *, struct ieee_pfc *); + int (*ieee_setpfc) (struct net_device *, struct ieee_pfc *); + int (*ieee_getapp) (struct net_device *, struct dcb_app *); + int (*ieee_setapp) (struct net_device *, struct dcb_app *); + + /* CEE std */ u8 (*getstate)(struct net_device *); u8 (*setstate)(struct net_device *, u8); void (*getpermhwaddr)(struct net_device *, u8 *); -- cgit v1.1 From 9ab933ab2cc80f04690d6aa385b1110075c5e507 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 30 Dec 2010 09:26:31 +0000 Subject: dcbnl: add appliction tlv handlers This patch adds application tlv handlers. Networking stacks may use the application priority to set the skb priority of their stack using the negoatiated dcbx priority. This patch provides the dcb_{get|set}app() routines for the stack to query these parameters. Notice lower layer drivers can use the dcbnl_ops routines if additional handling is needed. Perhaps in the firmware case for example Signed-off-by: John Fastabend Signed-off-by: Shmulik Ravid Signed-off-by: David S. Miller --- include/linux/dcbnl.h | 4 +++- include/net/dcbnl.h | 9 +++++++++ 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h index 287b561..775bdb4 100644 --- a/include/linux/dcbnl.h +++ b/include/linux/dcbnl.h @@ -82,7 +82,9 @@ struct ieee_pfc { __u64 indications[IEEE_8021QAZ_MAX_TCS]; }; -/* This structure contains the IEEE 802.1Qaz APP managed object +/* This structure contains the IEEE 802.1Qaz APP managed object. This + * object is also used for the CEE std as well. There is no difference + * between the objects. * * @selector: protocol identifier type * @protocol: protocol of type indicated diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h index e2d841e..ab7d623 100644 --- a/include/net/dcbnl.h +++ b/include/net/dcbnl.h @@ -22,6 +22,15 @@ #include +struct dcb_app_type { + char name[IFNAMSIZ]; + struct dcb_app app; + struct list_head list; +}; + +u8 dcb_setapp(struct net_device *, struct dcb_app *); +u8 dcb_getapp(struct net_device *, struct dcb_app *); + /* * Ops struct for the netlink callbacks. Used by DCB-enabled drivers through * the netdevice struct. -- cgit v1.1 From 96b99684e365f28d49bdb1221ca022b75cb91a98 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 30 Dec 2010 09:26:37 +0000 Subject: net_dcb: add application notifiers DCBx applications priorities can be changed dynamically. If application stacks are expected to keep the skb priority consistent with the dcbx priority the stack will need to be notified when these changes occur. This patch adds application notifiers for the stack to register with. Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- include/net/dcbevent.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) create mode 100644 include/net/dcbevent.h (limited to 'include') diff --git a/include/net/dcbevent.h b/include/net/dcbevent.h new file mode 100644 index 0000000..bc1e7ef --- /dev/null +++ b/include/net/dcbevent.h @@ -0,0 +1,31 @@ +/* + * Copyright (c) 2010, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., 59 Temple + * Place - Suite 330, Boston, MA 02111-1307 USA. + * + * Author: John Fastabend + */ + +#ifndef _DCB_EVENT_H +#define _DCB_EVENT_H + +enum dcbevent_notif_type { + DCB_APP_EVENT = 1, +}; + +extern int register_dcbevent_notifier(struct notifier_block *nb); +extern int unregister_dcbevent_notifier(struct notifier_block *nb); +extern int call_dcbevent_notifiers(unsigned long val, void *v); + +#endif -- cgit v1.1 From 6241b6259b16aa390ff4bf50f520685b3801200b Mon Sep 17 00:00:00 2001 From: Shmulik Ravid Date: Thu, 30 Dec 2010 06:26:48 +0000 Subject: dcbnl: adding DCBX engine capability Adding an optional DCBX capability and a pair for get-set routines for setting the device DCBX mode. The DCBX capability is a bit field of supported attributes. The user is expected to set the DCBX mode with a subset of the advertised attributes. This patch is dependent on the following patches: [net-next-2.6 PATCH 1/3] dcbnl: add support for ieee8021Qaz attributes [net-next-2.6 PATCH 2/3] dcbnl: add appliction tlv handlers [net-next-2.6 PATCH 3/3] net_dcb: add application notifiers Signed-off-by: Shmulik Ravid Acked-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/dcbnl.h | 43 +++++++++++++++++++++++++++++++++++++++++++ include/net/dcbnl.h | 5 +++++ 2 files changed, 48 insertions(+) (limited to 'include') diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h index 775bdb4..16eea36 100644 --- a/include/linux/dcbnl.h +++ b/include/linux/dcbnl.h @@ -135,6 +135,8 @@ struct dcbmsg { * @DCB_CMD_SAPP: set application protocol configuration * @DCB_CMD_IEEE_SET: set IEEE 802.1Qaz configuration * @DCB_CMD_IEEE_GET: get IEEE 802.1Qaz configuration + * @DCB_CMD_GDCBX: get DCBX engine configuration + * @DCB_CMD_SDCBX: set DCBX engine configuration */ enum dcbnl_commands { DCB_CMD_UNDEFINED, @@ -171,6 +173,9 @@ enum dcbnl_commands { DCB_CMD_IEEE_SET, DCB_CMD_IEEE_GET, + DCB_CMD_GDCBX, + DCB_CMD_SDCBX, + __DCB_CMD_ENUM_MAX, DCB_CMD_MAX = __DCB_CMD_ENUM_MAX - 1, }; @@ -191,6 +196,7 @@ enum dcbnl_commands { * @DCB_ATTR_NUMTCS: number of traffic classes supported (NLA_NESTED) * @DCB_ATTR_BCN: backward congestion notification configuration (NLA_NESTED) * @DCB_ATTR_IEEE: IEEE 802.1Qaz supported attributes (NLA_NESTED) + * @DCB_ATTR_DCBX: DCBX engine configuration in the device (NLA_U8) */ enum dcbnl_attrs { DCB_ATTR_UNDEFINED, @@ -211,6 +217,8 @@ enum dcbnl_attrs { /* IEEE std attributes */ DCB_ATTR_IEEE, + DCB_ATTR_DCBX, + __DCB_ATTR_ENUM_MAX, DCB_ATTR_MAX = __DCB_ATTR_ENUM_MAX - 1, }; @@ -370,6 +378,8 @@ enum dcbnl_tc_attrs { * @DCB_CAP_ATTR_GSP: (NLA_U8) device supports group strict priority * @DCB_CAP_ATTR_BCN: (NLA_U8) device supports Backwards Congestion * Notification + * @DCB_CAP_ATTR_DCBX: (NLA_U8) device supports DCBX engine + * */ enum dcbnl_cap_attrs { DCB_CAP_ATTR_UNDEFINED, @@ -381,12 +391,45 @@ enum dcbnl_cap_attrs { DCB_CAP_ATTR_PFC_TCS, DCB_CAP_ATTR_GSP, DCB_CAP_ATTR_BCN, + DCB_CAP_ATTR_DCBX, __DCB_CAP_ATTR_ENUM_MAX, DCB_CAP_ATTR_MAX = __DCB_CAP_ATTR_ENUM_MAX - 1, }; /** + * DCBX capability flags + * + * @DCB_CAP_DCBX_HOST: DCBX negotiation is performed by the host LLDP agent. + * 'set' routines are used to configure the device with + * the negotiated parameters + * + * @DCB_CAP_DCBX_LLD_MANAGED: DCBX negotiation is not performed in the host but + * by another entity + * 'get' routines are used to retrieve the + * negotiated parameters + * 'set' routines can be used to set the initial + * negotiation configuration + * + * @DCB_CAP_DCBX_VER_CEE: for a non-host DCBX engine, indicates the engine + * supports the CEE protocol flavor + * + * @DCB_CAP_DCBX_VER_IEEE: for a non-host DCBX engine, indicates the engine + * supports the IEEE protocol flavor + * + * @DCB_CAP_DCBX_STATIC: for a non-host DCBX engine, indicates the engine + * supports static configuration (i.e no actual + * negotiation is performed negotiated parameters equal + * the initial configuration) + * + */ +#define DCB_CAP_DCBX_HOST 0x01 +#define DCB_CAP_DCBX_LLD_MANAGED 0x02 +#define DCB_CAP_DCBX_VER_CEE 0x04 +#define DCB_CAP_DCBX_VER_IEEE 0x08 +#define DCB_CAP_DCBX_STATIC 0x10 + +/** * enum dcbnl_numtcs_attrs - number of traffic classes * * @DCB_NUMTCS_ATTR_UNDEFINED: unspecified attribute to catch errors diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h index ab7d623..c65347b 100644 --- a/include/net/dcbnl.h +++ b/include/net/dcbnl.h @@ -70,6 +70,11 @@ struct dcbnl_rtnl_ops { void (*setbcnrp)(struct net_device *, int, u8); u8 (*setapp)(struct net_device *, u8, u16, u8); u8 (*getapp)(struct net_device *, u8, u16); + + /* DCBX configuration */ + u8 (*getdcbx)(struct net_device *); + u8 (*setdcbx)(struct net_device *, u8); + }; #endif /* __NET_DCBNL_H__ */ -- cgit v1.1 From ea45fe4e176a42d2396878f530cfdc8265bef37b Mon Sep 17 00:00:00 2001 From: Shmulik Ravid Date: Thu, 30 Dec 2010 06:26:55 +0000 Subject: dcbnl: adding DCBX feature flags get-set Adding a pair of set-get routines to dcbnl for setting the negotiation flags of the various DCB features. Conforms to the CEE flavor of DCBX The user sets these flags (enable, advertise, willing) for each feature to be used by the DCBX engine. The 'get' routine returns which of the features is enabled after the negotiation. This patch is dependent on the following patches: [net-next-2.6 PATCH 1/3] dcbnl: add support for ieee8021Qaz attributes [net-next-2.6 PATCH 2/3] dcbnl: add appliction tlv handlers [net-next-2.6 PATCH 3/3] net_dcb: add application notifiers Signed-off-by: Shmulik Ravid Signed-off-by: David S. Miller --- include/linux/dcbnl.h | 33 +++++++++++++++++++++++++++++++++ include/net/dcbnl.h | 3 +++ 2 files changed, 36 insertions(+) (limited to 'include') diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h index 16eea36..68cd248 100644 --- a/include/linux/dcbnl.h +++ b/include/linux/dcbnl.h @@ -137,6 +137,8 @@ struct dcbmsg { * @DCB_CMD_IEEE_GET: get IEEE 802.1Qaz configuration * @DCB_CMD_GDCBX: get DCBX engine configuration * @DCB_CMD_SDCBX: set DCBX engine configuration + * @DCB_CMD_GFEATCFG: get DCBX features flags + * @DCB_CMD_SFEATCFG: set DCBX features negotiation flags */ enum dcbnl_commands { DCB_CMD_UNDEFINED, @@ -176,6 +178,9 @@ enum dcbnl_commands { DCB_CMD_GDCBX, DCB_CMD_SDCBX, + DCB_CMD_GFEATCFG, + DCB_CMD_SFEATCFG, + __DCB_CMD_ENUM_MAX, DCB_CMD_MAX = __DCB_CMD_ENUM_MAX - 1, }; @@ -197,6 +202,7 @@ enum dcbnl_commands { * @DCB_ATTR_BCN: backward congestion notification configuration (NLA_NESTED) * @DCB_ATTR_IEEE: IEEE 802.1Qaz supported attributes (NLA_NESTED) * @DCB_ATTR_DCBX: DCBX engine configuration in the device (NLA_U8) + * @DCB_ATTR_FEATCFG: DCBX features flags (NLA_NESTED) */ enum dcbnl_attrs { DCB_ATTR_UNDEFINED, @@ -218,6 +224,7 @@ enum dcbnl_attrs { DCB_ATTR_IEEE, DCB_ATTR_DCBX, + DCB_ATTR_FEATCFG, __DCB_ATTR_ENUM_MAX, DCB_ATTR_MAX = __DCB_ATTR_ENUM_MAX - 1, @@ -506,4 +513,30 @@ enum dcbnl_app_attrs { DCB_APP_ATTR_MAX = __DCB_APP_ATTR_ENUM_MAX - 1, }; +/** + * enum dcbnl_featcfg_attrs - features conifiguration flags + * + * @DCB_FEATCFG_ATTR_UNDEFINED: unspecified attribute to catch errors + * @DCB_FEATCFG_ATTR_ALL: (NLA_FLAG) all features configuration attributes + * @DCB_FEATCFG_ATTR_PG: (NLA_U8) configuration flags for priority groups + * @DCB_FEATCFG_ATTR_PFC: (NLA_U8) configuration flags for priority + * flow control + * @DCB_FEATCFG_ATTR_APP: (NLA_U8) configuration flags for application TLV + * + */ +#define DCB_FEATCFG_ERROR 0x01 /* error in feature resolution */ +#define DCB_FEATCFG_ENABLE 0x02 /* enable feature */ +#define DCB_FEATCFG_WILLING 0x04 /* feature is willing */ +#define DCB_FEATCFG_ADVERTISE 0x08 /* advertise feature */ +enum dcbnl_featcfg_attrs { + DCB_FEATCFG_ATTR_UNDEFINED, + DCB_FEATCFG_ATTR_ALL, + DCB_FEATCFG_ATTR_PG, + DCB_FEATCFG_ATTR_PFC, + DCB_FEATCFG_ATTR_APP, + + __DCB_FEATCFG_ATTR_ENUM_MAX, + DCB_FEATCFG_ATTR_MAX = __DCB_FEATCFG_ATTR_ENUM_MAX - 1, +}; + #endif /* __LINUX_DCBNL_H__ */ diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h index c65347b..a8e7852 100644 --- a/include/net/dcbnl.h +++ b/include/net/dcbnl.h @@ -70,11 +70,14 @@ struct dcbnl_rtnl_ops { void (*setbcnrp)(struct net_device *, int, u8); u8 (*setapp)(struct net_device *, u8, u16, u8); u8 (*getapp)(struct net_device *, u8, u16); + u8 (*getfeatcfg)(struct net_device *, int, u8 *); + u8 (*setfeatcfg)(struct net_device *, int, u8); /* DCBX configuration */ u8 (*getdcbx)(struct net_device *); u8 (*setdcbx)(struct net_device *, u8); + }; #endif /* __NET_DCBNL_H__ */ -- cgit v1.1 From a4f740cf33f7f6c164bbde3c0cdbcc77b0c4997c Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Sat, 30 Oct 2010 11:49:09 -0400 Subject: of/flattree: Add of_flat_dt_match() helper function This patch adds of_flat_dt_match() which tests a node for compatibility with a list of values and converts the relevant powerpc platform code to use it. This approach simplifies the board support code a bit. Signed-off-by: Grant Likely Reviewed-by: Stephen Neuendorffer --- include/linux/of_fdt.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index 9ce5dfd..ee96091 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -68,6 +68,8 @@ extern void *of_fdt_get_property(struct boot_param_header *blob, extern int of_fdt_is_compatible(struct boot_param_header *blob, unsigned long node, const char *compat); +extern int of_fdt_match(struct boot_param_header *blob, unsigned long node, + const char **compat); extern void of_fdt_unflatten_tree(unsigned long *blob, struct device_node **mynodes); @@ -84,6 +86,7 @@ extern int of_scan_flat_dt(int (*it)(unsigned long node, const char *uname, extern void *of_get_flat_dt_prop(unsigned long node, const char *name, unsigned long *size); extern int of_flat_dt_is_compatible(unsigned long node, const char *name); +extern int of_flat_dt_match(unsigned long node, const char **matches); extern unsigned long of_get_flat_dt_root(void); extern int early_init_dt_scan_chosen(unsigned long node, const char *uname, -- cgit v1.1 From 51f98a8d70583b18cb08b19353aeed5efb0244af Mon Sep 17 00:00:00 2001 From: Allan Stephens Date: Fri, 31 Dec 2010 18:59:16 +0000 Subject: tipc: Remove prototype code for supporting multiple zones Eliminates routines, data structures, and files that were intended to allows TIPC to support a network containing multiple zones. Currently, TIPC supports only networks consisting of a single cluster within a single zone, so this code is unnecessary. Signed-off-by: Allan Stephens Signed-off-by: Paul Gortmaker Signed-off-by: David S. Miller --- include/linux/tipc_config.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/tipc_config.h b/include/linux/tipc_config.h index 9cde86c..fa3aeaa 100644 --- a/include/linux/tipc_config.h +++ b/include/linux/tipc_config.h @@ -94,7 +94,7 @@ #define TIPC_CMD_GET_MAX_PORTS 0x4004 /* tx none, rx unsigned */ #define TIPC_CMD_GET_MAX_PUBL 0x4005 /* tx none, rx unsigned */ #define TIPC_CMD_GET_MAX_SUBSCR 0x4006 /* tx none, rx unsigned */ -#define TIPC_CMD_GET_MAX_ZONES 0x4007 /* tx none, rx unsigned */ +#define TIPC_CMD_GET_MAX_ZONES 0x4007 /* obsoleted */ #define TIPC_CMD_GET_MAX_CLUSTERS 0x4008 /* tx none, rx unsigned */ #define TIPC_CMD_GET_MAX_NODES 0x4009 /* tx none, rx unsigned */ #define TIPC_CMD_GET_MAX_SLAVES 0x400A /* tx none, rx unsigned */ @@ -130,7 +130,7 @@ #define TIPC_CMD_SET_MAX_PORTS 0x8004 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_PUBL 0x8005 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_SUBSCR 0x8006 /* tx unsigned, rx none */ -#define TIPC_CMD_SET_MAX_ZONES 0x8007 /* tx unsigned, rx none */ +#define TIPC_CMD_SET_MAX_ZONES 0x8007 /* obsoleted */ #define TIPC_CMD_SET_MAX_CLUSTERS 0x8008 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_NODES 0x8009 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_SLAVES 0x800A /* tx unsigned, rx none */ -- cgit v1.1 From 08c80e9a031df0a8f0269477a32f5eae47d7a146 Mon Sep 17 00:00:00 2001 From: Allan Stephens Date: Fri, 31 Dec 2010 18:59:17 +0000 Subject: tipc: Remove prototype code for supporting slave nodes Simplifies routines and data structures that were intended to allow TIPC to support slave nodes (i.e. nodes that did not have links to all of the other nodes in its cluster, forcing TIPC to route messages that it could not deliver directly through a non-slave node). Currently, TIPC supports only networks containing non-slave nodes, so this code is unnecessary. Note: The latest edition of the TIPC 2.0 Specification has eliminated the concept of slave nodes entirely. Signed-off-by: Allan Stephens Signed-off-by: Paul Gortmaker Signed-off-by: David S. Miller --- include/linux/tipc_config.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/tipc_config.h b/include/linux/tipc_config.h index fa3aeaa..dcc2b87 100644 --- a/include/linux/tipc_config.h +++ b/include/linux/tipc_config.h @@ -97,7 +97,7 @@ #define TIPC_CMD_GET_MAX_ZONES 0x4007 /* obsoleted */ #define TIPC_CMD_GET_MAX_CLUSTERS 0x4008 /* tx none, rx unsigned */ #define TIPC_CMD_GET_MAX_NODES 0x4009 /* tx none, rx unsigned */ -#define TIPC_CMD_GET_MAX_SLAVES 0x400A /* tx none, rx unsigned */ +#define TIPC_CMD_GET_MAX_SLAVES 0x400A /* obsoleted */ #define TIPC_CMD_GET_NETID 0x400B /* tx none, rx unsigned */ #define TIPC_CMD_ENABLE_BEARER 0x4101 /* tx bearer_config, rx none */ @@ -133,7 +133,7 @@ #define TIPC_CMD_SET_MAX_ZONES 0x8007 /* obsoleted */ #define TIPC_CMD_SET_MAX_CLUSTERS 0x8008 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_NODES 0x8009 /* tx unsigned, rx none */ -#define TIPC_CMD_SET_MAX_SLAVES 0x800A /* tx unsigned, rx none */ +#define TIPC_CMD_SET_MAX_SLAVES 0x800A /* obsoleted */ #define TIPC_CMD_SET_NETID 0x800B /* tx unsigned, rx none */ /* -- cgit v1.1 From 51a8e4dee7653698ba4c6e7de71053665f075273 Mon Sep 17 00:00:00 2001 From: Allan Stephens Date: Fri, 31 Dec 2010 18:59:18 +0000 Subject: tipc: Remove prototype code for supporting inter-cluster routing Eliminates routines and data structures that were intended to allow TIPC to route messages to other clusters. Currently, TIPC supports only networks consisting of a single cluster within a single zone, so this code is unnecessary. Signed-off-by: Allan Stephens Signed-off-by: Paul Gortmaker Signed-off-by: David S. Miller --- include/linux/tipc_config.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/tipc_config.h b/include/linux/tipc_config.h index dcc2b87..1f38df1 100644 --- a/include/linux/tipc_config.h +++ b/include/linux/tipc_config.h @@ -254,11 +254,6 @@ struct tipc_link_create { struct tipc_media_addr peer_addr; char bearer_name[TIPC_MAX_BEARER_NAME]; }; - -struct tipc_route_info { - __u32 dest; - __u32 router; -}; #endif /* -- cgit v1.1 From 8f92df6ad49da958d97e171762d0a97a3dc738f1 Mon Sep 17 00:00:00 2001 From: Allan Stephens Date: Fri, 31 Dec 2010 18:59:19 +0000 Subject: tipc: Remove prototype code for supporting multiple clusters Eliminates routines, data structures, and files that were intended to allow TIPC to support a network containing multiple clusters. Currently, TIPC supports only networks consisting of a single cluster within a single zone, so this code is unnecessary. Signed-off-by: Allan Stephens Signed-off-by: Paul Gortmaker Signed-off-by: David S. Miller --- include/linux/tipc_config.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/tipc_config.h b/include/linux/tipc_config.h index 1f38df1..677aa13 100644 --- a/include/linux/tipc_config.h +++ b/include/linux/tipc_config.h @@ -95,7 +95,7 @@ #define TIPC_CMD_GET_MAX_PUBL 0x4005 /* tx none, rx unsigned */ #define TIPC_CMD_GET_MAX_SUBSCR 0x4006 /* tx none, rx unsigned */ #define TIPC_CMD_GET_MAX_ZONES 0x4007 /* obsoleted */ -#define TIPC_CMD_GET_MAX_CLUSTERS 0x4008 /* tx none, rx unsigned */ +#define TIPC_CMD_GET_MAX_CLUSTERS 0x4008 /* obsoleted */ #define TIPC_CMD_GET_MAX_NODES 0x4009 /* tx none, rx unsigned */ #define TIPC_CMD_GET_MAX_SLAVES 0x400A /* obsoleted */ #define TIPC_CMD_GET_NETID 0x400B /* tx none, rx unsigned */ @@ -131,7 +131,7 @@ #define TIPC_CMD_SET_MAX_PUBL 0x8005 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_SUBSCR 0x8006 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_ZONES 0x8007 /* obsoleted */ -#define TIPC_CMD_SET_MAX_CLUSTERS 0x8008 /* tx unsigned, rx none */ +#define TIPC_CMD_SET_MAX_CLUSTERS 0x8008 /* obsoleted */ #define TIPC_CMD_SET_MAX_NODES 0x8009 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_SLAVES 0x800A /* obsoleted */ #define TIPC_CMD_SET_NETID 0x800B /* tx unsigned, rx none */ -- cgit v1.1 From 0e65967e33be61e5f67727edd4ea829b47676fc0 Mon Sep 17 00:00:00 2001 From: Allan Stephens Date: Fri, 31 Dec 2010 18:59:32 +0000 Subject: tipc: cleanup various cosmetic whitespace issues Cleans up TIPC's source code to eliminate deviations from generally accepted coding conventions relating to leading/trailing white space and white space around commas, braces, cases, and sizeof. These changes are purely cosmetic and do not alter the operation of TIPC in any way. Signed-off-by: Allan Stephens Signed-off-by: Paul Gortmaker Signed-off-by: David S. Miller --- include/linux/tipc.h | 18 +++++++------- include/linux/tipc_config.h | 59 ++++++++++++++++++++++----------------------- 2 files changed, 38 insertions(+), 39 deletions(-) (limited to 'include') diff --git a/include/linux/tipc.h b/include/linux/tipc.h index d10614b..1eefa3f 100644 --- a/include/linux/tipc.h +++ b/include/linux/tipc.h @@ -1,6 +1,6 @@ /* * include/linux/tipc.h: Include file for TIPC socket interface - * + * * Copyright (c) 2003-2006, Ericsson AB * Copyright (c) 2005, Wind River Systems * All rights reserved. @@ -42,7 +42,7 @@ /* * TIPC addressing primitives */ - + struct tipc_portid { __u32 ref; __u32 node; @@ -89,7 +89,7 @@ static inline unsigned int tipc_node(__u32 addr) #define TIPC_TOP_SRV 1 /* topology service name type */ #define TIPC_RESERVED_TYPES 64 /* lowest user-publishable name type */ -/* +/* * Publication scopes when binding port names and port name sequences */ @@ -112,7 +112,7 @@ static inline unsigned int tipc_node(__u32 addr) #define TIPC_HIGH_IMPORTANCE 2 #define TIPC_CRITICAL_IMPORTANCE 3 -/* +/* * Msg rejection/connection shutdown reasons */ @@ -127,9 +127,9 @@ static inline unsigned int tipc_node(__u32 addr) * TIPC topology subscription service definitions */ -#define TIPC_SUB_PORTS 0x01 /* filter for port availability */ -#define TIPC_SUB_SERVICE 0x02 /* filter for service availability */ -#define TIPC_SUB_CANCEL 0x04 /* cancel a subscription */ +#define TIPC_SUB_PORTS 0x01 /* filter for port availability */ +#define TIPC_SUB_SERVICE 0x02 /* filter for service availability */ +#define TIPC_SUB_CANCEL 0x04 /* cancel a subscription */ #if 0 /* The following filter options are not currently implemented */ #define TIPC_SUB_NO_BIND_EVTS 0x04 /* filter out "publish" events */ @@ -137,12 +137,12 @@ static inline unsigned int tipc_node(__u32 addr) #define TIPC_SUB_SINGLE_EVT 0x10 /* expire after first event */ #endif -#define TIPC_WAIT_FOREVER ~0 /* timeout for permanent subscription */ +#define TIPC_WAIT_FOREVER (~0) /* timeout for permanent subscription */ struct tipc_subscr { struct tipc_name_seq seq; /* name sequence of interest */ __u32 timeout; /* subscription duration (in ms) */ - __u32 filter; /* bitmask of filter options */ + __u32 filter; /* bitmask of filter options */ char usr_handle[8]; /* available for subscriber use */ }; diff --git a/include/linux/tipc_config.h b/include/linux/tipc_config.h index 677aa13..7d42460a 100644 --- a/include/linux/tipc_config.h +++ b/include/linux/tipc_config.h @@ -1,6 +1,6 @@ /* * include/linux/tipc_config.h: Include file for TIPC configuration interface - * + * * Copyright (c) 2003-2006, Ericsson AB * Copyright (c) 2005-2007, Wind River Systems * All rights reserved. @@ -54,19 +54,19 @@ * which specify parameters or results for the operation. * * For many operations, the request and reply messages have a fixed number - * of TLVs (usually zero or one); however, some reply messages may return + * of TLVs (usually zero or one); however, some reply messages may return * a variable number of TLVs. A failed request is denoted by the presence * of an "error string" TLV in the reply message instead of the TLV(s) the * reply should contain if the request succeeds. */ - -/* + +/* * Public commands: * May be issued by any process. - * Accepted by own node, or by remote node only if remote management enabled. + * Accepted by own node, or by remote node only if remote management enabled. */ - -#define TIPC_CMD_NOOP 0x0000 /* tx none, rx none */ + +#define TIPC_CMD_NOOP 0x0000 /* tx none, rx none */ #define TIPC_CMD_GET_NODES 0x0001 /* tx net_addr, rx node_info(s) */ #define TIPC_CMD_GET_MEDIA_NAMES 0x0002 /* tx none, rx media_name(s) */ #define TIPC_CMD_GET_BEARER_NAMES 0x0003 /* tx none, rx bearer_name(s) */ @@ -83,11 +83,11 @@ #define TIPC_CMD_GET_LINK_PEER 0x000D /* tx link_name, rx ? */ #endif -/* +/* * Protected commands: * May only be issued by "network administration capable" process. * Accepted by own node, or by remote node only if remote management enabled - * and this node is zone manager. + * and this node is zone manager. */ #define TIPC_CMD_GET_REMOTE_MNG 0x4003 /* tx none, rx unsigned */ @@ -116,10 +116,10 @@ #define TIPC_CMD_UNBLOCK_LINK 0x4106 /* tx link_name, rx none */ #endif -/* +/* * Private commands: * May only be issued by "network administration capable" process. - * Accepted by own node only; cannot be used on a remote node. + * Accepted by own node only; cannot be used on a remote node. */ #define TIPC_CMD_SET_NODE_ADDR 0x8001 /* tx net_addr, rx none */ @@ -156,20 +156,20 @@ #define TIPC_TLV_ULTRA_STRING 5 /* char[32768] (max) */ #define TIPC_TLV_ERROR_STRING 16 /* char[128] containing "error code" */ -#define TIPC_TLV_NET_ADDR 17 /* 32-bit integer denoting */ +#define TIPC_TLV_NET_ADDR 17 /* 32-bit integer denoting */ #define TIPC_TLV_MEDIA_NAME 18 /* char[TIPC_MAX_MEDIA_NAME] */ #define TIPC_TLV_BEARER_NAME 19 /* char[TIPC_MAX_BEARER_NAME] */ #define TIPC_TLV_LINK_NAME 20 /* char[TIPC_MAX_LINK_NAME] */ #define TIPC_TLV_NODE_INFO 21 /* struct tipc_node_info */ #define TIPC_TLV_LINK_INFO 22 /* struct tipc_link_info */ -#define TIPC_TLV_BEARER_CONFIG 23 /* struct tipc_bearer_config */ -#define TIPC_TLV_LINK_CONFIG 24 /* struct tipc_link_config */ +#define TIPC_TLV_BEARER_CONFIG 23 /* struct tipc_bearer_config */ +#define TIPC_TLV_LINK_CONFIG 24 /* struct tipc_link_config */ #define TIPC_TLV_NAME_TBL_QUERY 25 /* struct tipc_name_table_query */ -#define TIPC_TLV_PORT_REF 26 /* 32-bit port reference */ +#define TIPC_TLV_PORT_REF 26 /* 32-bit port reference */ /* * Maximum sizes of TIPC bearer-related names (including terminating NUL) - */ + */ #define TIPC_MAX_MEDIA_NAME 16 /* format = media */ #define TIPC_MAX_IF_NAME 16 /* format = interface */ @@ -234,7 +234,7 @@ struct tipc_name_table_query { }; /* - * The error string TLV is a null-terminated string describing the cause + * The error string TLV is a null-terminated string describing the cause * of the request failure. To simplify error processing (and to save space) * the first character of the string can be a special error code character * (lying by the range 0x80 to 0xFF) which represents a pre-defined reason. @@ -258,7 +258,7 @@ struct tipc_link_create { /* * A TLV consists of a descriptor, followed by the TLV value. - * TLV descriptor fields are stored in network byte order; + * TLV descriptor fields are stored in network byte order; * TLV values must also be stored in network byte order (where applicable). * TLV descriptors must be aligned to addresses which are multiple of 4, * so up to 3 bytes of padding may exist at the end of the TLV value area. @@ -294,7 +294,7 @@ static inline int TLV_OK(const void *tlv, __u16 space) static inline int TLV_CHECK(const void *tlv, __u16 space, __u16 exp_type) { - return TLV_OK(tlv, space) && + return TLV_OK(tlv, space) && (ntohs(((struct tlv_desc *)tlv)->tlv_type) == exp_type); } @@ -313,7 +313,7 @@ static inline int TLV_SET(void *tlv, __u16 type, void *data, __u16 len) } /* - * A TLV list descriptor simplifies processing of messages + * A TLV list descriptor simplifies processing of messages * containing multiple TLVs. */ @@ -322,15 +322,15 @@ struct tlv_list_desc { __u32 tlv_space; /* # bytes from curr TLV to list end */ }; -static inline void TLV_LIST_INIT(struct tlv_list_desc *list, +static inline void TLV_LIST_INIT(struct tlv_list_desc *list, void *data, __u32 space) { list->tlv_ptr = (struct tlv_desc *)data; list->tlv_space = space; } - + static inline int TLV_LIST_EMPTY(struct tlv_list_desc *list) -{ +{ return (list->tlv_space == 0); } @@ -348,7 +348,7 @@ static inline void TLV_LIST_STEP(struct tlv_list_desc *list) { __u16 tlv_space = TLV_ALIGN(ntohs(list->tlv_ptr->tlv_len)); - list->tlv_ptr = (struct tlv_desc *)((char *)list->tlv_ptr + tlv_space); + list->tlv_ptr = (struct tlv_desc *)((char *)list->tlv_ptr + tlv_space); list->tlv_space -= tlv_space; } @@ -372,15 +372,14 @@ struct tipc_genlmsghdr { #define TIPC_GENL_HDRLEN NLMSG_ALIGN(sizeof(struct tipc_genlmsghdr)) /* - * Configuration messages exchanged via TIPC sockets use the TIPC configuration - * message header, which is defined below. This structure is analogous - * to the Netlink message header, but fields are stored in network byte order - * and no padding is permitted between the header and the message data + * Configuration messages exchanged via TIPC sockets use the TIPC configuration + * message header, which is defined below. This structure is analogous + * to the Netlink message header, but fields are stored in network byte order + * and no padding is permitted between the header and the message data * that follows. */ -struct tipc_cfg_msg_hdr -{ +struct tipc_cfg_msg_hdr { __be32 tcm_len; /* Message length (including header) */ __be16 tcm_type; /* Command type */ __be16 tcm_flags; /* Additional flags */ -- cgit v1.1 From 8f33d5277fada0291ea495f7fd44a3e7b7aa41d3 Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Wed, 22 Dec 2010 14:46:46 +0100 Subject: dmaengine: provide dummy functions for DMA_ENGINE=n This lets drivers, optionally using the dmaengine, build with DMA_ENGINE unselected. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 9d8688b..8cd00ad 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -824,6 +824,8 @@ enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie); #ifdef CONFIG_DMA_ENGINE enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx); void dma_issue_pending_all(void); +struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, void *fn_param); +void dma_release_channel(struct dma_chan *chan); #else static inline enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx) { @@ -831,7 +833,14 @@ static inline enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descript } static inline void dma_issue_pending_all(void) { - do { } while (0); +} +static inline struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, + dma_filter_fn fn, void *fn_param) +{ + return NULL; +} +static inline void dma_release_channel(struct dma_chan *chan) +{ } #endif @@ -842,8 +851,6 @@ void dma_async_device_unregister(struct dma_device *device); void dma_run_dependencies(struct dma_async_tx_descriptor *tx); struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type); #define dma_request_channel(mask, x, y) __dma_request_channel(&(mask), x, y) -struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, void *fn_param); -void dma_release_channel(struct dma_chan *chan); /* --- Helper iov-locking functions --- */ -- cgit v1.1 From 46e67acd5d4cacda758e871eebd15cef4e2c2665 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 3 Jan 2011 09:09:56 -0200 Subject: [media] wm8775: Revert changeset fcb9757333 to avoid a regression It seems that cx88 and ivtv use wm8775 on some different modes. The patch that added support for a board with wm8775 broke ivtv boards with this device. As we're too close to release 2.6.37, let's just revert it. Reported-by: Andy Walls Reported-by: Eric Sharkey Reported-by: Auric Reported by: David Gesswein Signed-off-by: Mauro Carvalho Chehab --- include/media/wm8775.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/media/wm8775.h b/include/media/wm8775.h index a1c4d41..60739c5 100644 --- a/include/media/wm8775.h +++ b/include/media/wm8775.h @@ -32,7 +32,4 @@ #define WM8775_AIN3 4 #define WM8775_AIN4 8 -/* subdev group ID */ -#define WM8775_GID (1 << 0) - #endif -- cgit v1.1 From eb78bd7d8a39415245a8d20ae3b464ddde68b20a Mon Sep 17 00:00:00 2001 From: "Justin P. Mattock" Date: Thu, 30 Dec 2010 15:08:03 -0800 Subject: media: comment typo fix diable -> disable. The below patch fixes a typo "diable" to "disable". Signed-off-by: Justin P. Mattock Acked-by: Mauro Carvalho Chehab Signed-off-by: Jiri Kosina --- include/media/davinci/vpss.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/media/davinci/vpss.h b/include/media/davinci/vpss.h index c59cc02..b586495 100644 --- a/include/media/davinci/vpss.h +++ b/include/media/davinci/vpss.h @@ -44,7 +44,7 @@ struct vpss_pg_frame_size { short pplen; }; -/* Used for enable/diable VPSS Clock */ +/* Used for enable/disable VPSS Clock */ enum vpss_clock_sel { /* DM355/DM365 */ VPSS_CCDC_CLOCK, -- cgit v1.1 From 68763c890eb2a60f9b50a061502f94e0cf20fdfe Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Sun, 2 Jan 2011 22:54:09 +0000 Subject: trivial: Fix typo fault in netdevice.h Signed-off-by: Michal Simek Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cc916c5..0f6b1c9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -732,7 +732,7 @@ struct xps_dev_maps { * neither operation. * * void (*ndo_vlan_rx_register)(struct net_device *dev, struct vlan_group *grp); - * If device support VLAN receive accleration + * If device support VLAN receive acceleration * (ie. dev->features & NETIF_F_HW_VLAN_RX), then this function is called * when vlan groups for the device changes. Note: grp is NULL * if no vlan's groups are being used. -- cgit v1.1 From 25e41933b58777f2d020c3b0186b430ea004ec28 Mon Sep 17 00:00:00 2001 From: Thomas Renninger Date: Mon, 3 Jan 2011 17:50:44 +0100 Subject: perf: Clean up power events by introducing new, more generic ones Add these new power trace events: power:cpu_idle power:cpu_frequency power:machine_suspend The old C-state/idle accounting events: power:power_start power:power_end Have now a replacement (but we are still keeping the old tracepoints for compatibility): power:cpu_idle and power:power_frequency is replaced with: power:cpu_frequency power:machine_suspend is newly introduced. Jean Pihet has a patch integrated into the generic layer (kernel/power/suspend.c) which will make use of it. the type= field got removed from both, it was never used and the type is differed by the event type itself. perf timechart userspace tool gets adjusted in a separate patch. Signed-off-by: Thomas Renninger Signed-off-by: Ingo Molnar Acked-by: Arjan van de Ven Acked-by: Jean Pihet Cc: Arnaldo Carvalho de Melo Cc: Peter Zijlstra Cc: Linus Torvalds Cc: rjw@sisk.pl LKML-Reference: <1294073445-14812-3-git-send-email-trenn@suse.de> Signed-off-by: Ingo Molnar LKML-Reference: <1290072314-31155-2-git-send-email-trenn@suse.de> --- include/trace/events/power.h | 98 ++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 89 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/trace/events/power.h b/include/trace/events/power.h index 286784d..1bcc2a8 100644 --- a/include/trace/events/power.h +++ b/include/trace/events/power.h @@ -7,16 +7,67 @@ #include #include -#ifndef _TRACE_POWER_ENUM_ -#define _TRACE_POWER_ENUM_ -enum { - POWER_NONE = 0, - POWER_CSTATE = 1, /* C-State */ - POWER_PSTATE = 2, /* Fequency change or DVFS */ - POWER_SSTATE = 3, /* Suspend */ -}; +DECLARE_EVENT_CLASS(cpu, + + TP_PROTO(unsigned int state, unsigned int cpu_id), + + TP_ARGS(state, cpu_id), + + TP_STRUCT__entry( + __field( u32, state ) + __field( u32, cpu_id ) + ), + + TP_fast_assign( + __entry->state = state; + __entry->cpu_id = cpu_id; + ), + + TP_printk("state=%lu cpu_id=%lu", (unsigned long)__entry->state, + (unsigned long)__entry->cpu_id) +); + +DEFINE_EVENT(cpu, cpu_idle, + + TP_PROTO(unsigned int state, unsigned int cpu_id), + + TP_ARGS(state, cpu_id) +); + +/* This file can get included multiple times, TRACE_HEADER_MULTI_READ at top */ +#ifndef _PWR_EVENT_AVOID_DOUBLE_DEFINING +#define _PWR_EVENT_AVOID_DOUBLE_DEFINING + +#define PWR_EVENT_EXIT -1 #endif +DEFINE_EVENT(cpu, cpu_frequency, + + TP_PROTO(unsigned int frequency, unsigned int cpu_id), + + TP_ARGS(frequency, cpu_id) +); + +TRACE_EVENT(machine_suspend, + + TP_PROTO(unsigned int state), + + TP_ARGS(state), + + TP_STRUCT__entry( + __field( u32, state ) + ), + + TP_fast_assign( + __entry->state = state; + ), + + TP_printk("state=%lu", (unsigned long)__entry->state) +); + +/* This code will be removed after deprecation time exceeded (2.6.41) */ +#ifdef CONFIG_EVENT_POWER_TRACING_DEPRECATED + /* * The power events are used for cpuidle & suspend (power_start, power_end) * and for cpufreq (power_frequency) @@ -75,6 +126,36 @@ TRACE_EVENT(power_end, ); +/* Deprecated dummy functions must be protected against multi-declartion */ +#ifndef _PWR_EVENT_AVOID_DOUBLE_DEFINING_DEPRECATED +#define _PWR_EVENT_AVOID_DOUBLE_DEFINING_DEPRECATED + +enum { + POWER_NONE = 0, + POWER_CSTATE = 1, + POWER_PSTATE = 2, +}; +#endif /* _PWR_EVENT_AVOID_DOUBLE_DEFINING_DEPRECATED */ + +#else /* CONFIG_EVENT_POWER_TRACING_DEPRECATED */ + +#ifndef _PWR_EVENT_AVOID_DOUBLE_DEFINING_DEPRECATED +#define _PWR_EVENT_AVOID_DOUBLE_DEFINING_DEPRECATED +enum { + POWER_NONE = 0, + POWER_CSTATE = 1, + POWER_PSTATE = 2, +}; + +/* These dummy declaration have to be ripped out when the deprecated + events get removed */ +static inline void trace_power_start(u64 type, u64 state, u64 cpuid) {}; +static inline void trace_power_end(u64 cpuid) {}; +static inline void trace_power_frequency(u64 type, u64 state, u64 cpuid) {}; +#endif /* _PWR_EVENT_AVOID_DOUBLE_DEFINING_DEPRECATED */ + +#endif /* CONFIG_EVENT_POWER_TRACING_DEPRECATED */ + /* * The clock events are used for clock enable/disable and for * clock rate change @@ -153,7 +234,6 @@ DEFINE_EVENT(power_domain, power_domain_target, TP_ARGS(name, state, cpu_id) ); - #endif /* _TRACE_POWER_H */ /* This part must be outside protection */ -- cgit v1.1 From 410cf2bd3dc6ec1ed9e1b36b25b9d7aa927ed14e Mon Sep 17 00:00:00 2001 From: Clemens Ladisch Date: Mon, 13 Dec 2010 14:56:02 +0100 Subject: firewire: use split transaction timeout only for split transactions Instead of starting the split transaction timeout timer when any request is submitted, start it only when the destination's ACK_PENDING has been received. This prevents us from using a timeout that is too short, and, if the controller's AT queue is emptying very slowly, from cancelling a packet that has not yet been sent. Signed-off-by: Clemens Ladisch Signed-off-by: Stefan Richter --- include/linux/firewire.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 1cd637e..9a3f5f9 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -302,9 +302,9 @@ struct fw_packet { struct fw_transaction { int node_id; /* The generation is implied; it is always the current. */ int tlabel; - int timestamp; struct list_head link; struct fw_card *card; + bool is_split_transaction; struct timer_list split_timeout_timer; struct fw_packet packet; -- cgit v1.1 From 7b26e5ebd8b27b0126a84ae7f9a42aa8293d6c48 Mon Sep 17 00:00:00 2001 From: Francois-Xavier Le Bail Date: Tue, 4 Jan 2011 09:10:20 +0000 Subject: net: typos in comments in include/linux/igmp.h There are typos in comments in include/linux/igmp.h: 83 #define IGMP_HOST_MEMBERSHIP_QUERY 0x11 /* From RFC1112 */ 84 #define IGMP_HOST_MEMBERSHIP_REPORT 0x12 /* Ditto */ [snip] 88 #define IGMPV2_HOST_MEMBERSHIP_REPORT 0x16 /* V2 version of 0x11 */ 89 #define IGMP_HOST_LEAVE_MESSAGE 0x17 90 #define IGMPV3_HOST_MEMBERSHIP_REPORT 0x22 /* V3 version of 0x11 */ The line 88 and 90 are about REPORT messages. The IGMP_HOST_MEMBERSHIP_REPORT (IGMP V1) value is 0x12. So the comment on line 88 must be /* V2 version of 0x12 */, and the comment on line 90 must be /* V3 version of 0x12 */. Signed-off-by: Francois-Xavier Le Bail Signed-off-by: David S. Miller --- include/linux/igmp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index c4987f2..74cfcff 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -85,9 +85,9 @@ struct igmpv3_query { #define IGMP_DVMRP 0x13 /* DVMRP routing */ #define IGMP_PIM 0x14 /* PIM routing */ #define IGMP_TRACE 0x15 -#define IGMPV2_HOST_MEMBERSHIP_REPORT 0x16 /* V2 version of 0x11 */ +#define IGMPV2_HOST_MEMBERSHIP_REPORT 0x16 /* V2 version of 0x12 */ #define IGMP_HOST_LEAVE_MESSAGE 0x17 -#define IGMPV3_HOST_MEMBERSHIP_REPORT 0x22 /* V3 version of 0x11 */ +#define IGMPV3_HOST_MEMBERSHIP_REPORT 0x22 /* V3 version of 0x12 */ #define IGMP_MTRACE_RESP 0x1e #define IGMP_MTRACE 0x1f -- cgit v1.1 From bdd5f05d91e8ae68075b812ce244c918d3d752cd Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Tue, 4 Jan 2011 13:31:45 -0500 Subject: SUNRPC: Remove more code when NFSD_DEPRECATED is not configured Signed-off-by: NeilBrown [bfields@redhat.com: moved svcauth_unix_purge outside ifdef's.] Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/cache.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 6950c98..c2aebe8 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -255,10 +255,13 @@ static inline time_t get_expiry(char **bpp) return rv - boot.tv_sec; } +#ifdef CONFIG_NFSD_DEPRECATED static inline void sunrpc_invalidate(struct cache_head *h, struct cache_detail *detail) { h->expiry_time = seconds_since_boot() - 1; detail->nextcheck = seconds_since_boot(); } +#endif /* CONFIG_NFSD_DEPRECATED */ + #endif /* _LINUX_SUNRPC_CACHE_H_ */ -- cgit v1.1 From 9e701c610923aaeac8b38b9202a686d1cc9ee35d Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Sun, 2 Jan 2011 21:56:36 -0500 Subject: svcrpc: simpler request dropping Currently we use -EAGAIN returns to determine when to drop a deferred request. On its own, that is error-prone, as it makes us treat -EAGAIN returns from other functions specially to prevent inadvertent dropping. So, use a flag on the request instead. Returning an error on request deferral is still required, to prevent further processing, but we no longer need worry that an error return on its own could result in a drop. Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 5a3085b..d45c482 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -269,6 +269,7 @@ struct svc_rqst { struct cache_req rq_chandle; /* handle passed to caches for * request delaying */ + bool rq_dropme; /* Catering to nfsd */ struct auth_domain * rq_client; /* RPC peer info */ struct auth_domain * rq_gssclient; /* "gss/"-style peer info */ -- cgit v1.1 From c45821d263a8a5109d69a9e8942b8d65bcd5f31a Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Sun, 31 Oct 2010 00:04:44 -0400 Subject: locks: eliminate fl_mylease callback The nfs server only supports read delegations for now, so we don't care how conflicts are determined. All we care is that unlocks are recognized as matching the leases they are meant to remove. After the last patch, a comparison of struct files will work for that purpose. So we no longer need this callback. Signed-off-by: J. Bruce Fields --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 090f0ea..73ce69f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1059,7 +1059,6 @@ struct lock_manager_operations { int (*fl_grant)(struct file_lock *, struct file_lock *, int); void (*fl_release_private)(struct file_lock *); void (*fl_break)(struct file_lock *); - int (*fl_mylease)(struct file_lock *, struct file_lock *); int (*fl_change)(struct file_lock **, int); }; -- cgit v1.1 From 2ca72e17e5acb1052c35c9faba609c2289ce7a92 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Tue, 4 Jan 2011 17:37:15 -0500 Subject: nfsd4: move idmap and acl header files into fs/nfsd These are internal nfsd interfaces. Signed-off-by: J. Bruce Fields --- include/linux/nfs4_acl.h | 61 ------------------------------------------- include/linux/nfsd_idmap.h | 64 ---------------------------------------------- 2 files changed, 125 deletions(-) delete mode 100644 include/linux/nfs4_acl.h delete mode 100644 include/linux/nfsd_idmap.h (limited to 'include') diff --git a/include/linux/nfs4_acl.h b/include/linux/nfs4_acl.h deleted file mode 100644 index c9c05a7..0000000 --- a/include/linux/nfs4_acl.h +++ /dev/null @@ -1,61 +0,0 @@ -/* - * include/linux/nfs4_acl.c - * - * Common NFSv4 ACL handling definitions. - * - * Copyright (c) 2002 The Regents of the University of Michigan. - * All rights reserved. - * - * Marius Aamodt Eriksen - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the name of the University nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED - * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF - * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE - * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE - * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR - * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF - * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING - * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -#ifndef LINUX_NFS4_ACL_H -#define LINUX_NFS4_ACL_H - -#include - -/* Maximum ACL we'll accept from client; chosen (somewhat arbitrarily) to - * fit in a page: */ -#define NFS4_ACL_MAX 170 - -struct nfs4_acl *nfs4_acl_new(int); -int nfs4_acl_get_whotype(char *, u32); -int nfs4_acl_write_who(int who, char *p); -int nfs4_acl_permission(struct nfs4_acl *acl, uid_t owner, gid_t group, - uid_t who, u32 mask); - -#define NFS4_ACL_TYPE_DEFAULT 0x01 -#define NFS4_ACL_DIR 0x02 -#define NFS4_ACL_OWNER 0x04 - -struct nfs4_acl *nfs4_acl_posix_to_nfsv4(struct posix_acl *, - struct posix_acl *, unsigned int flags); -int nfs4_acl_nfsv4_to_posix(struct nfs4_acl *, struct posix_acl **, - struct posix_acl **, unsigned int flags); - -#endif /* LINUX_NFS4_ACL_H */ diff --git a/include/linux/nfsd_idmap.h b/include/linux/nfsd_idmap.h deleted file mode 100644 index d4a2ac1..0000000 --- a/include/linux/nfsd_idmap.h +++ /dev/null @@ -1,64 +0,0 @@ -/* - * include/linux/nfsd_idmap.h - * - * Mapping of UID to name and vice versa. - * - * Copyright (c) 2002, 2003 The Regents of the University of - * Michigan. All rights reserved. -> * - * Marius Aamodt Eriksen - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the name of the University nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED - * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF - * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE - * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE - * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR - * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF - * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING - * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -#ifndef LINUX_NFSD_IDMAP_H -#define LINUX_NFSD_IDMAP_H - -#include -#include - -/* XXX from linux/nfs_idmap.h */ -#define IDMAP_NAMESZ 128 - -#ifdef CONFIG_NFSD_V4 -int nfsd_idmap_init(void); -void nfsd_idmap_shutdown(void); -#else -static inline int nfsd_idmap_init(void) -{ - return 0; -} -static inline void nfsd_idmap_shutdown(void) -{ -} -#endif - -int nfsd_map_name_to_uid(struct svc_rqst *, const char *, size_t, __u32 *); -int nfsd_map_name_to_gid(struct svc_rqst *, const char *, size_t, __u32 *); -int nfsd_map_uid_to_name(struct svc_rqst *, __u32, char *); -int nfsd_map_gid_to_name(struct svc_rqst *, __u32, char *); - -#endif /* LINUX_NFSD_IDMAP_H */ -- cgit v1.1 From 91aa5fadb831e7b6ea473a526a6b49c6dc4819ce Mon Sep 17 00:00:00 2001 From: Russell King - ARM Linux Date: Mon, 3 Jan 2011 22:31:04 +0000 Subject: ARM: PL08x: fix atomic_t usage and tx_submit() return value range The last_issued variable uses an atomic type, which is only incremented inside a protected region, and then read. Everywhere else only reads the value, so it isn't using atomic_t correctly, and it doesn't even need to. Moreover, the DMA engine code provides us with a variable for this already - chan.cookie. Use chan.cookie instead. Also, avoid negative dma_cookie_t values - negative returns from tx_submit() mean failure, yet in reality we always succeed. Restart from cookie 1, just like other DMA engine drivers do. Signed-off-by: Russell King Acked-by: Linus Walleij Signed-off-by: Dan Williams --- include/linux/amba/pl08x.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h index 521a0f8..4ae62b4 100644 --- a/include/linux/amba/pl08x.h +++ b/include/linux/amba/pl08x.h @@ -174,7 +174,6 @@ struct pl08x_dma_chan { struct pl08x_channel_data *cd; dma_addr_t runtime_addr; enum dma_data_direction runtime_direction; - atomic_t last_issued; dma_cookie_t lc; struct list_head desc_list; struct pl08x_txd *at; -- cgit v1.1 From 7cb72ad959b16ac594118977b7954a7d2ec7a052 Mon Sep 17 00:00:00 2001 From: Russell King - ARM Linux Date: Mon, 3 Jan 2011 22:35:28 +0000 Subject: ARM: PL08x: avoid 'void *' struct fields when we can type them properly Avoid using 'void *' struct fields when the structs are not defined in linux/amba/pl08x.h - instead, forward declare the struct names, and use these instead. This ensures we have proper typechecking. Signed-off-by: Russell King Acked-by: Linus Walleij Signed-off-by: Dan Williams --- include/linux/amba/pl08x.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h index 4ae62b4..3ecc20f 100644 --- a/include/linux/amba/pl08x.h +++ b/include/linux/amba/pl08x.h @@ -22,6 +22,9 @@ #include #include +struct pl08x_lli; +struct pl08x_driver_data; + /** * struct pl08x_channel_data - data structure to pass info between * platform and PL08x driver regarding channel configuration @@ -179,7 +182,7 @@ struct pl08x_dma_chan { struct pl08x_txd *at; unsigned long lockflags; spinlock_t lock; - void *host; + struct pl08x_driver_data *host; enum pl08x_dma_chan_state state; bool slave; struct pl08x_txd *waiting; -- cgit v1.1 From cace658572ba5d1075f3891e823130a66f3e330f Mon Sep 17 00:00:00 2001 From: Russell King - ARM Linux Date: Mon, 3 Jan 2011 22:37:31 +0000 Subject: ARM: PL08x: use 'size_t' for lengths Use size_t for variables denoting lengths throughout, and use the 'z' qualifier for printing the value. For safety, add a BUG_ON() in pl08x_fill_lli_for_desc() to catch the remainder potentially becoming negative. Signed-off-by: Russell King Acked-by: Linus Walleij Signed-off-by: Dan Williams --- include/linux/amba/pl08x.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h index 3ecc20f..2c834ed 100644 --- a/include/linux/amba/pl08x.h +++ b/include/linux/amba/pl08x.h @@ -77,7 +77,7 @@ struct pl08x_bus_data { dma_addr_t addr; u8 maxwidth; u8 buswidth; - u32 fill_bytes; + size_t fill_bytes; }; /** @@ -113,7 +113,7 @@ struct pl08x_txd { enum dma_data_direction direction; struct pl08x_bus_data srcbus; struct pl08x_bus_data dstbus; - int len; + size_t len; dma_addr_t llis_bus; void *llis_va; struct pl08x_channel_data *cd; -- cgit v1.1 From 19524d77ec34faf58d313ba34fb755ef6e159216 Mon Sep 17 00:00:00 2001 From: Russell King - ARM Linux Date: Mon, 3 Jan 2011 22:39:13 +0000 Subject: ARM: PL08x: avoid duplicating registers in txd and phychan structures As we now have all the code accessing the phychan {csrc,cdst,clli,cctl, ccfg} members in one function, there's no point storing the data into the struct. Get rid of the struct members. Re-order the register dump in the dev_dbg() to reflect the order we write the registers to the DMA device. The txd {csrc,cdst,clli,cctl} values are duplicates of the lli[0] values, so there's no point duplicating these either. Program the DMAC registers directly from the lli[0] values. Signed-off-by: Russell King Acked-by: Linus Walleij Signed-off-by: Dan Williams --- include/linux/amba/pl08x.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include') diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h index 2c834ed..29d9745 100644 --- a/include/linux/amba/pl08x.h +++ b/include/linux/amba/pl08x.h @@ -95,11 +95,6 @@ struct pl08x_phy_chan { spinlock_t lock; int signal; struct pl08x_dma_chan *serving; - u32 csrc; - u32 cdst; - u32 clli; - u32 cctl; - u32 ccfg; }; /** @@ -118,14 +113,6 @@ struct pl08x_txd { void *llis_va; struct pl08x_channel_data *cd; bool active; - /* - * Settings to be put into the physical channel when we - * trigger this txd - */ - u32 csrc; - u32 cdst; - u32 clli; - u32 cctl; }; /** -- cgit v1.1 From 4983a04fd2562986360b646b378f267308bc22c0 Mon Sep 17 00:00:00 2001 From: Russell King - ARM Linux Date: Mon, 3 Jan 2011 22:39:33 +0000 Subject: ARM: PL08x: move ccfg into txd structure The ccfg register is used to configure the channel parameters - the type and direction of transfer, the flow control signal and IRQ mask enables. The type and direction of transfer is known in the relevent prep_* function where a txd is created. The IRQ mask enables are always set, and the flow control signals are always set when we start processing a txd according to phychan->signal. If we store the ccfg value in the txd structure, we can avoid modifying platform data - and even having it in platform data at all. So, remove it from platform data too. Signed-off-by: Russell King Acked-by: Linus Walleij Signed-off-by: Dan Williams --- include/linux/amba/pl08x.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h index 29d9745..8e74cb1 100644 --- a/include/linux/amba/pl08x.h +++ b/include/linux/amba/pl08x.h @@ -58,7 +58,6 @@ struct pl08x_channel_data { int max_signal; u32 muxval; u32 cctl; - u32 ccfg; dma_addr_t addr; bool circular_buffer; bool single; @@ -113,6 +112,11 @@ struct pl08x_txd { void *llis_va; struct pl08x_channel_data *cd; bool active; + /* + * Settings to be put into the physical channel when we + * trigger this txd. Other registers are in llis_va[0]. + */ + u32 ccfg; }; /** -- cgit v1.1 From 70b5ed6b6d72cd8b1a3d4b7b878a0dd132bec7ba Mon Sep 17 00:00:00 2001 From: Russell King - ARM Linux Date: Mon, 3 Jan 2011 22:40:13 +0000 Subject: ARM: PL08x: move default cctl into txd structure Rather than modifying platform data while preparing a transfer, copy the cctl value into the txd structure and modify the value there. Signed-off-by: Russell King Acked-by: Linus Walleij Signed-off-by: Dan Williams --- include/linux/amba/pl08x.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h index 8e74cb1..8d90830 100644 --- a/include/linux/amba/pl08x.h +++ b/include/linux/amba/pl08x.h @@ -110,8 +110,9 @@ struct pl08x_txd { size_t len; dma_addr_t llis_bus; void *llis_va; - struct pl08x_channel_data *cd; bool active; + /* Default cctl value for LLIs */ + u32 cctl; /* * Settings to be put into the physical channel when we * trigger this txd. Other registers are in llis_va[0]. -- cgit v1.1 From 30749cb4a40f02a199640011e5ab5c5f60b8482e Mon Sep 17 00:00:00 2001 From: Russell King - ARM Linux Date: Mon, 3 Jan 2011 22:41:13 +0000 Subject: ARM: PL08x: allow AHB master port selection to be configured Platforms need to be able to control which AHB master interface is used, as each AHB master interface may be asymetric. Allow the interfaces used for fetching LLIs, memory, and each peripheral to be configured individually. Signed-off-by: Russell King Acked-by: Linus Walleij Signed-off-by: Dan Williams --- include/linux/amba/pl08x.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h index 8d90830..f858651 100644 --- a/include/linux/amba/pl08x.h +++ b/include/linux/amba/pl08x.h @@ -25,6 +25,12 @@ struct pl08x_lli; struct pl08x_driver_data; +/* Bitmasks for selecting AHB ports for DMA transfers */ +enum { + PL08X_AHB1 = (1 << 0), + PL08X_AHB2 = (1 << 1) +}; + /** * struct pl08x_channel_data - data structure to pass info between * platform and PL08x driver regarding channel configuration @@ -51,6 +57,8 @@ struct pl08x_driver_data; * round round round) * @single: the device connected to this channel will request single * DMA transfers, not bursts. (Bursts are default.) + * @periph_buses: the device connected to this channel is accessible via + * these buses (use PL08X_AHB1 | PL08X_AHB2). */ struct pl08x_channel_data { char *bus_id; @@ -61,6 +69,7 @@ struct pl08x_channel_data { dma_addr_t addr; bool circular_buffer; bool single; + u8 periph_buses; }; /** @@ -193,8 +202,8 @@ struct pl08x_dma_chan { * less than zero, else it returns the allocated signal number * @put_signal: indicate to the platform that this physical signal is not * running any DMA transfer and multiplexing can be recycled - * @bus_bit_lli: Bit[0] of the address indicated which AHB bus master the - * LLI addresses are on 0/1 Master 1/2. + * @lli_buses: buses which LLIs can be fetched from: PL08X_AHB1 | PL08X_AHB2 + * @mem_buses: buses which memory can be accessed from: PL08X_AHB1 | PL08X_AHB2 */ struct pl08x_platform_data { struct pl08x_channel_data *slave_channels; @@ -202,6 +211,8 @@ struct pl08x_platform_data { struct pl08x_channel_data memcpy_channel; int (*get_signal)(struct pl08x_dma_chan *); void (*put_signal)(struct pl08x_dma_chan *); + u8 lli_buses; + u8 mem_buses; }; #ifdef CONFIG_AMBA_PL08X -- cgit v1.1 From d7244e9a27a3da27d62aabf560ee828d7991493e Mon Sep 17 00:00:00 2001 From: Russell King - ARM Linux Date: Mon, 3 Jan 2011 22:43:35 +0000 Subject: ARM: PL08x: shrink srcbus/dstbus in txd structure We only need to store the dma address. Signed-off-by: Russell King Acked-by: Linus Walleij Signed-off-by: Dan Williams --- include/linux/amba/pl08x.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h index f858651..4e9e718 100644 --- a/include/linux/amba/pl08x.h +++ b/include/linux/amba/pl08x.h @@ -114,8 +114,8 @@ struct pl08x_txd { struct dma_async_tx_descriptor tx; struct list_head node; enum dma_data_direction direction; - struct pl08x_bus_data srcbus; - struct pl08x_bus_data dstbus; + dma_addr_t src_addr; + dma_addr_t dst_addr; size_t len; dma_addr_t llis_bus; void *llis_va; -- cgit v1.1 From 15c17232fbd1f7687c740c3c26f9e7f337bd9e36 Mon Sep 17 00:00:00 2001 From: Russell King - ARM Linux Date: Mon, 3 Jan 2011 22:44:36 +0000 Subject: ARM: PL08x: rename 'desc_list' as 'pend_list' This 'desc_list' is actually a list of pending descriptors, so name it after its function (pending list) rather than what it contains (descriptors). Signed-off-by: Russell King Acked-by: Linus Walleij Signed-off-by: Dan Williams --- include/linux/amba/pl08x.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h index 4e9e718..08a9024 100644 --- a/include/linux/amba/pl08x.h +++ b/include/linux/amba/pl08x.h @@ -158,7 +158,7 @@ enum pl08x_dma_chan_state { * @runtime_direction: current direction of this channel according to * runtime config * @lc: last completed transaction on this channel - * @desc_list: queued transactions pending on this channel + * @pend_list: queued transactions pending on this channel * @at: active transaction on this channel * @lockflags: sometimes we let a lock last between two function calls, * especially prep/submit, and then we need to store the IRQ flags @@ -179,7 +179,7 @@ struct pl08x_dma_chan { dma_addr_t runtime_addr; enum dma_data_direction runtime_direction; dma_cookie_t lc; - struct list_head desc_list; + struct list_head pend_list; struct pl08x_txd *at; unsigned long lockflags; spinlock_t lock; -- cgit v1.1 From 8087aacda040bdbf84940712d132ce80c30b9d5d Mon Sep 17 00:00:00 2001 From: Russell King - ARM Linux Date: Mon, 3 Jan 2011 22:45:17 +0000 Subject: ARM: PL08x: introduce 'phychan_hold' to hold on to physical channels Introduce 'phychan_hold' to hold on to physical DMA channels while we're preparing a new descriptor for it. This will be incremented when we allocate a physical channel and set the MUX registers during the preparation of the TXD, and will only be decremented when the TXD is submitted. This prevents the physical channel being given up before the new TXD is placed on the queue. Signed-off-by: Russell King Acked-by: Linus Walleij Signed-off-by: Dan Williams --- include/linux/amba/pl08x.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h index 08a9024..95b76ea 100644 --- a/include/linux/amba/pl08x.h +++ b/include/linux/amba/pl08x.h @@ -151,6 +151,8 @@ enum pl08x_dma_chan_state { * struct pl08x_dma_chan - this structure wraps a DMA ENGINE channel * @chan: wrappped abstract channel * @phychan: the physical channel utilized by this channel, if there is one + * @phychan_hold: if non-zero, hold on to the physical channel even if we + * have no pending entries * @tasklet: tasklet scheduled by the IRQ to handle actual work etc * @name: name of channel * @cd: channel platform data @@ -173,6 +175,7 @@ enum pl08x_dma_chan_state { struct pl08x_dma_chan { struct dma_chan chan; struct pl08x_phy_chan *phychan; + int phychan_hold; struct tasklet_struct tasklet; char *name; struct pl08x_channel_data *cd; -- cgit v1.1 From c370e594efe2993620d24d41a78f325102e99d1c Mon Sep 17 00:00:00 2001 From: Russell King - ARM Linux Date: Mon, 3 Jan 2011 22:45:37 +0000 Subject: ARM: PL08x: fix locking between prepare function and submit function The PL08x driver holds on to the channel lock with interrupts disabled between the prepare and the subsequent submit API functions. This means that the locking state when the prepare function returns is dependent on whether it suceeeds or not. It did this to ensure that the physical channel wasn't released, and as it used to add the descriptor onto the pending list at prepare time rather than submit time. Now that we have reorganized the code to remove those reasons, we can now safely release the spinlock at the end of preparation and reacquire it in our submit function. Signed-off-by: Russell King Acked-by: Linus Walleij Signed-off-by: Dan Williams --- include/linux/amba/pl08x.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h index 95b76ea..933b4ed 100644 --- a/include/linux/amba/pl08x.h +++ b/include/linux/amba/pl08x.h @@ -162,9 +162,6 @@ enum pl08x_dma_chan_state { * @lc: last completed transaction on this channel * @pend_list: queued transactions pending on this channel * @at: active transaction on this channel - * @lockflags: sometimes we let a lock last between two function calls, - * especially prep/submit, and then we need to store the IRQ flags - * in the channel state, here * @lock: a lock for this channel data * @host: a pointer to the host (internal use) * @state: whether the channel is idle, paused, running etc @@ -184,7 +181,6 @@ struct pl08x_dma_chan { dma_cookie_t lc; struct list_head pend_list; struct pl08x_txd *at; - unsigned long lockflags; spinlock_t lock; struct pl08x_driver_data *host; enum pl08x_dma_chan_state state; -- cgit v1.1 From 8d608aa6295242fe4c4b6105b8c59c6a5b232d89 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 7 Dec 2010 08:57:57 +1000 Subject: vga_switcheroo: add reprobe hook for fbcon to recheck connected outputs. This adds a hook after the mux is switched for the driver to reprobe the connected outputs. Signed-off-by: Dave Airlie --- include/linux/vga_switcheroo.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h index ae9ab13..f80fa9d 100644 --- a/include/linux/vga_switcheroo.h +++ b/include/linux/vga_switcheroo.h @@ -33,6 +33,7 @@ struct vga_switcheroo_handler { void vga_switcheroo_unregister_client(struct pci_dev *dev); int vga_switcheroo_register_client(struct pci_dev *dev, void (*set_gpu_state)(struct pci_dev *dev, enum vga_switcheroo_state), + void (*reprobe)(struct pci_dev *dev), bool (*can_switch)(struct pci_dev *dev)); void vga_switcheroo_client_fb_set(struct pci_dev *dev, -- cgit v1.1 From 5bcf719b7db0f9366cedaf102b081f99b1c325ae Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Tue, 7 Dec 2010 09:20:40 +1000 Subject: drm/switcheroo: track state of switch in drivers. We need to track the state of the switch in drivers, so that after s/r we don't resume the card we've explicitly switched off before. Also don't allow a userspace open to occur if we've switched the gpu off. Signed-off-by: Dave Airlie --- include/drm/drmP.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drmP.h b/include/drm/drmP.h index 0f14f94..a4694c6 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -1121,9 +1121,13 @@ struct drm_device { spinlock_t object_name_lock; struct idr object_name_idr; /*@} */ - + int switch_power_state; }; +#define DRM_SWITCH_POWER_ON 0 +#define DRM_SWITCH_POWER_OFF 1 +#define DRM_SWITCH_POWER_CHANGING 2 + static __inline__ int drm_core_check_feature(struct drm_device *dev, int feature) { -- cgit v1.1 From 38f3a8794236af422312d280bbe3801130cfa63b Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Wed, 29 Dec 2010 08:12:22 +0000 Subject: fbdev: sh_mipi_dsi: support different register layouts The register layout of the MIPI DSI unit on sh-mobile SoCs differ. Add platform parameters to support such variations. Signed-off-by: Guennadi Liakhovetski Signed-off-by: Paul Mundt --- include/video/sh_mipi_dsi.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/video/sh_mipi_dsi.h b/include/video/sh_mipi_dsi.h index 18bca08..6cb95c9 100644 --- a/include/video/sh_mipi_dsi.h +++ b/include/video/sh_mipi_dsi.h @@ -27,9 +27,15 @@ enum sh_mipi_dsi_data_fmt { struct sh_mobile_lcdc_chan_cfg; +#define SH_MIPI_DSI_HSABM (1 << 0) +#define SH_MIPI_DSI_HSPBM (1 << 1) + struct sh_mipi_dsi_info { enum sh_mipi_dsi_data_fmt data_format; struct sh_mobile_lcdc_chan_cfg *lcd_chan; + unsigned long flags; + u32 clksrc; + unsigned int vsynw_offset; }; #endif -- cgit v1.1 From 6bf4123760a5aece6e4829ce90b70b6ffd751d65 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 5 Jan 2011 12:50:16 +1100 Subject: sched: Change wait_for_completion_*_timeout() to return a signed long wait_for_completion_*_timeout() can return: 0: if the wait timed out -ve: if the wait was interrupted +ve: if the completion was completed. As they currently return an 'unsigned long', the last two cases are not easily distinguished which can easily result in buggy code, as is the case for the recently added wait_for_completion_interruptible_timeout() call in net/sunrpc/cache.c So change them both to return 'long'. As MAX_SCHEDULE_TIMEOUT is LONG_MAX, a large +ve return value should never overflow. Signed-off-by: NeilBrown Cc: Peter Zijlstra Cc: J. Bruce Fields Cc: Andrew Morton Cc: Linus Torvalds LKML-Reference: <20110105125016.64ccab0e@notabene.brown> Signed-off-by: Ingo Molnar --- include/linux/completion.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/completion.h b/include/linux/completion.h index 36d57f7..51494e6 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -81,10 +81,10 @@ extern int wait_for_completion_interruptible(struct completion *x); extern int wait_for_completion_killable(struct completion *x); extern unsigned long wait_for_completion_timeout(struct completion *x, unsigned long timeout); -extern unsigned long wait_for_completion_interruptible_timeout( - struct completion *x, unsigned long timeout); -extern unsigned long wait_for_completion_killable_timeout( - struct completion *x, unsigned long timeout); +extern long wait_for_completion_interruptible_timeout( + struct completion *x, unsigned long timeout); +extern long wait_for_completion_killable_timeout( + struct completion *x, unsigned long timeout); extern bool try_wait_for_completion(struct completion *x); extern bool completion_done(struct completion *x); -- cgit v1.1 From e4a683c899cd5a49f8d684a054c95bd115a0c005 Mon Sep 17 00:00:00 2001 From: Jerome Marchand Date: Wed, 5 Jan 2011 16:57:37 +0100 Subject: kref: add kref_test_and_get Add kref_test_and_get() function, which atomically add a reference only if refcount is not zero. This prevent to add a reference to an object that is already being removed. Signed-off-by: Jerome Marchand Cc: stable@kernel.org Signed-off-by: Jens Axboe --- include/linux/kref.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/kref.h b/include/linux/kref.h index 6cc38fc..90b9e44 100644 --- a/include/linux/kref.h +++ b/include/linux/kref.h @@ -23,6 +23,7 @@ struct kref { void kref_init(struct kref *kref); void kref_get(struct kref *kref); +int kref_test_and_get(struct kref *kref); int kref_put(struct kref *kref, void (*release) (struct kref *kref)); #endif /* _KREF_H_ */ -- cgit v1.1 From 09e099d4bafea3b15be003d548bdf94b4b6e0e17 Mon Sep 17 00:00:00 2001 From: Jerome Marchand Date: Wed, 5 Jan 2011 16:57:38 +0100 Subject: block: fix accounting bug on cross partition merges /proc/diskstats would display a strange output as follows. $ cat /proc/diskstats |grep sda 8 0 sda 90524 7579 102154 20464 0 0 0 0 0 14096 20089 8 1 sda1 19085 1352 21841 4209 0 0 0 0 4294967064 15689 4293424691 ~~~~~~~~~~ 8 2 sda2 71252 3624 74891 15950 0 0 0 0 232 23995 1562390 8 3 sda3 54 487 2188 92 0 0 0 0 0 88 92 8 4 sda4 4 0 8 0 0 0 0 0 0 0 0 8 5 sda5 81 2027 2130 138 0 0 0 0 0 87 137 Its reason is the wrong way of accounting hd_struct->in_flight. When a bio is merged into a request belongs to different partition by ELEVATOR_FRONT_MERGE. The detailed root cause is as follows. Assuming that there are two partition, sda1 and sda2. 1. A request for sda2 is in request_queue. Hence sda1's hd_struct->in_flight is 0 and sda2's one is 1. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 2. A bio belongs to sda1 is issued and is merged into the request mentioned on step1 by ELEVATOR_BACK_MERGE. The first sector of the request is changed from sda2 region to sda1 region. However the two partition's hd_struct->in_flight are not changed. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 3. The request is finished and blk_account_io_done() is called. In this case, sda2's hd_struct->in_flight, not a sda1's one, is decremented. | hd_struct->in_flight --------------------------- sda1 | -1 sda2 | 1 --------------------------- The patch fixes the problem by caching the partition lookup inside the request structure, hence making sure that the increment and decrement will always happen on the same partition struct. This also speeds up IO with accounting enabled, since it cuts down on the number of lookups we have to do. Also add a refcount to struct hd_struct to keep the partition in memory as long as users exist. We use kref_test_and_get() to ensure we don't add a reference to a partition which is going away. Signed-off-by: Jerome Marchand Signed-off-by: Yasuaki Ishimatsu Cc: stable@kernel.org Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 + include/linux/genhd.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index aae86fd..482a7fd 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -115,6 +115,7 @@ struct request { void *elevator_private3; struct gendisk *rq_disk; + struct hd_struct *part; unsigned long start_time; #ifdef CONFIG_BLK_CGROUP unsigned long long start_time_ns; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 7a7b9c1..2ba2792 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -116,6 +116,7 @@ struct hd_struct { struct disk_stats dkstats; #endif struct rcu_head rcu_head; + struct kref ref; }; #define GENHD_FL_REMOVABLE 1 @@ -583,6 +584,7 @@ extern struct hd_struct * __must_check add_partition(struct gendisk *disk, sector_t len, int flags, struct partition_meta_info *info); +extern void __delete_partition(struct kref *ref); extern void delete_partition(struct gendisk *, int); extern void printk_all_partitions(void); -- cgit v1.1 From 68b65f7305e54b822b2483c60de7d7b017526a92 Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 22 Dec 2010 17:24:39 +0000 Subject: ARM: PL011: Add support for transmit DMA Add DMA engine support for transmit to the PL011 driver. Based on a patch from Linus Walliej, with the following changes: - remove RX DMA support. As PL011 doesn't give us receive timeout interrupts, we only get notified of received data when the RX DMA has completed. This rather sucks for interactive use of the TTY. - remove abuse of completions. Completions are supposed to be for events, not to tell what condition buffers are in. Replace it with a simple 'queued' bool. - fix locking - it is only safe to access the circular buffer with the port lock held. - only map the DMA buffer when required - if we're ever behind an IOMMU this helps keep IOMMU usage down, and also ensures that we're legal when we change the scatterlist entry length. - fix XON/XOFF sending - we must send XON/XOFF characters out as soon as possible - waiting for up to 4095 characters in the DMA buffer to be sent first is not acceptable. - fix XON/XOFF receive handling - we need to stop DMA when instructed to by the TTY layer, and restart it again when instructed to. There is a subtle problem here: we must not completely empty the circular buffer with DMA, otherwise we will not be notified of XON. - change the 'enable_dma' flag into a 'using DMA' flag, and track whether we can use TX DMA by whether the channel pointer is non-NULL. This gives us more control over whether we use DMA in the driver. - we don't need to have the TX DMA buffer continually allocated for each port - instead, allocate it when the port starts up, and free it when it's shut down. Update the 'using DMA' flag if we get the buffer, and adjust the TTY FIFO size appropriately. - if we're going to use PIO to send characters, use the existing IRQ based functionality rather than reimplementing it. This also ensures we call uart_write_wakeup() at the appropriate time, otherwise we'll stall. - use DMA engine helper functions for type safety. - fix init when built as a module - we can't have to initcall functions, so we must settle on one. This means we can eliminate the deferred DMA initialization. - there is no need to terminate transfers on a failed prep_slave_sg() call - nothing has been setup, so nothing needs to be terminated. This avoids a potential deadlock in the DMA engine code (tasklet->callback->failed prepare->terminate->tasklet_disable which then ends up waiting for the tasklet to finish running.) - Dan says that the submission callback should not return an error: | dma_submit_error() is something I should have removed after commit | a0587bcf "ioat1: move descriptor allocation from submit to prep" all | errors should be notified by prep failing to return a descriptor | handle. Negative dma_cookie_t values are only returned by the | dma_async_memcpy* calls which translate a prep failure into -ENOMEM. So remove the error handling at that point. This also solves the potential deadlock mentioned in the previous comment. Acked-by: Linus Walleij Signed-off-by: Russell King --- include/linux/amba/serial.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/amba/serial.h b/include/linux/amba/serial.h index 6021588..577f22e 100644 --- a/include/linux/amba/serial.h +++ b/include/linux/amba/serial.h @@ -180,6 +180,13 @@ struct amba_device; /* in uncompress this is included but amba/bus.h is not */ struct amba_pl010_data { void (*set_mctrl)(struct amba_device *dev, void __iomem *base, unsigned int mctrl); }; + +struct dma_chan; +struct amba_pl011_data { + bool (*dma_filter)(struct dma_chan *chan, void *filter_param); + void *dma_rx_param; + void *dma_tx_param; +}; #endif #endif -- cgit v1.1 From 38d624361b2a82d6317c379aebf81b1b28210bb0 Mon Sep 17 00:00:00 2001 From: Russell King Date: Wed, 22 Dec 2010 17:59:16 +0000 Subject: ARM: PL011: add DMA burst threshold support for ST variants ST Micro variants has some specific dma burst threshold compensation, which allows them to make better use of a DMA controller. Add support to set this up. Based on a patch from Linus Walleij. Acked-by: Linus Walleij Signed-off-by: Russell King --- include/linux/amba/serial.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/linux/amba/serial.h b/include/linux/amba/serial.h index 577f22e..5479fdc 100644 --- a/include/linux/amba/serial.h +++ b/include/linux/amba/serial.h @@ -113,6 +113,21 @@ #define UART01x_LCRH_PEN 0x02 #define UART01x_LCRH_BRK 0x01 +#define ST_UART011_DMAWM_RX_1 (0 << 3) +#define ST_UART011_DMAWM_RX_2 (1 << 3) +#define ST_UART011_DMAWM_RX_4 (2 << 3) +#define ST_UART011_DMAWM_RX_8 (3 << 3) +#define ST_UART011_DMAWM_RX_16 (4 << 3) +#define ST_UART011_DMAWM_RX_32 (5 << 3) +#define ST_UART011_DMAWM_RX_48 (6 << 3) +#define ST_UART011_DMAWM_TX_1 0 +#define ST_UART011_DMAWM_TX_2 1 +#define ST_UART011_DMAWM_TX_4 2 +#define ST_UART011_DMAWM_TX_8 3 +#define ST_UART011_DMAWM_TX_16 4 +#define ST_UART011_DMAWM_TX_32 5 +#define ST_UART011_DMAWM_TX_48 6 + #define UART010_IIR_RTIS 0x08 #define UART010_IIR_TIS 0x04 #define UART010_IIR_RIS 0x02 -- cgit v1.1 From 21f83589644bb2ed98079bf1e2154c8e70ca6a6c Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sat, 18 Dec 2010 17:20:47 +0100 Subject: mac80211: implement hardware offload for remain-on-channel This allows drivers to support remain-on-channel offload if they implement smarter timing or need to use a device implementation like iwlwifi. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 479c35e..5b3fd5a 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -365,6 +365,7 @@ enum mac80211_tx_control_flags { IEEE80211_TX_INTFL_NL80211_FRAME_TX = BIT(21), IEEE80211_TX_CTL_LDPC = BIT(22), IEEE80211_TX_CTL_STBC = BIT(23) | BIT(24), + IEEE80211_TX_CTL_TX_OFFCHAN = BIT(25), }; #define IEEE80211_TX_CTL_STBC_SHIFT 23 @@ -1824,6 +1825,12 @@ struct ieee80211_ops { int (*napi_poll)(struct ieee80211_hw *hw, int budget); int (*set_antenna)(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant); int (*get_antenna)(struct ieee80211_hw *hw, u32 *tx_ant, u32 *rx_ant); + + int (*remain_on_channel)(struct ieee80211_hw *hw, + struct ieee80211_channel *chan, + enum nl80211_channel_type channel_type, + int duration); + int (*cancel_remain_on_channel)(struct ieee80211_hw *hw); }; /** @@ -2729,6 +2736,18 @@ void ieee80211_request_smps(struct ieee80211_vif *vif, */ void ieee80211_key_removed(struct ieee80211_key_conf *key_conf); +/** + * ieee80211_ready_on_channel - notification of remain-on-channel start + * @hw: pointer as obtained from ieee80211_alloc_hw() + */ +void ieee80211_ready_on_channel(struct ieee80211_hw *hw); + +/** + * ieee80211_remain_on_channel_expired - remain_on_channel duration expired + * @hw: pointer as obtained from ieee80211_alloc_hw() + */ +void ieee80211_remain_on_channel_expired(struct ieee80211_hw *hw); + /* Rate control API */ /** -- cgit v1.1 From df660251eb534649f90f9dcfe1da1cef4ea48a3e Mon Sep 17 00:00:00 2001 From: Ian Campbell Date: Mon, 9 Feb 2009 12:05:51 -0800 Subject: xen: add backend driver support Impact: backend device support Add the basic machinery to support backend drivers. Signed-off-by: Ian Campbell Signed-off-by: Jeremy Fitzhardinge [corresponds to 79727b851bac in git://git.kernel.org/pub/scm/linux/kernel/git/jeremy/xen.git] Signed-off-by: Konrad Rzeszutek Wilk --- include/xen/xenbus.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index 43e2d7d..7a1d15f 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -94,7 +94,7 @@ struct xenbus_driver { int (*remove)(struct xenbus_device *dev); int (*suspend)(struct xenbus_device *dev, pm_message_t state); int (*resume)(struct xenbus_device *dev); - int (*uevent)(struct xenbus_device *, char **, int, char *, int); + int (*uevent)(struct xenbus_device *, struct kobj_uevent_env *); struct device_driver driver; int (*read_otherend_details)(struct xenbus_device *dev); int (*is_ready)(struct xenbus_device *dev); -- cgit v1.1 From 3610cda53f247e176bcbb7a7cca64bc53b12acdb Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 5 Jan 2011 15:38:53 -0800 Subject: af_unix: Avoid socket->sk NULL OOPS in stream connect security hooks. unix_release() can asynchornously set socket->sk to NULL, and it does so without holding the unix_state_lock() on "other" during stream connects. However, the reverse mapping, sk->sk_socket, is only transitioned to NULL under the unix_state_lock(). Therefore make the security hooks follow the reverse mapping instead of the forward mapping. Reported-by: Jeremy Fitzhardinge Reported-by: Linus Torvalds Signed-off-by: David S. Miller --- include/linux/security.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/security.h b/include/linux/security.h index fd4d55f..d47a4c2 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -796,8 +796,9 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * @unix_stream_connect: * Check permissions before establishing a Unix domain stream connection * between @sock and @other. - * @sock contains the socket structure. - * @other contains the peer socket structure. + * @sock contains the sock structure. + * @other contains the peer sock structure. + * @newsk contains the new sock structure. * Return 0 if permission is granted. * @unix_may_send: * Check permissions before connecting or sending datagrams from @sock to @@ -1568,8 +1569,7 @@ struct security_operations { int (*inode_getsecctx)(struct inode *inode, void **ctx, u32 *ctxlen); #ifdef CONFIG_SECURITY_NETWORK - int (*unix_stream_connect) (struct socket *sock, - struct socket *other, struct sock *newsk); + int (*unix_stream_connect) (struct sock *sock, struct sock *other, struct sock *newsk); int (*unix_may_send) (struct socket *sock, struct socket *other); int (*socket_create) (int family, int type, int protocol, int kern); @@ -2525,8 +2525,7 @@ static inline int security_inode_getsecctx(struct inode *inode, void **ctx, u32 #ifdef CONFIG_SECURITY_NETWORK -int security_unix_stream_connect(struct socket *sock, struct socket *other, - struct sock *newsk); +int security_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk); int security_unix_may_send(struct socket *sock, struct socket *other); int security_socket_create(int family, int type, int protocol, int kern); int security_socket_post_create(struct socket *sock, int family, @@ -2567,8 +2566,8 @@ void security_tun_dev_post_create(struct sock *sk); int security_tun_dev_attach(struct sock *sk); #else /* CONFIG_SECURITY_NETWORK */ -static inline int security_unix_stream_connect(struct socket *sock, - struct socket *other, +static inline int security_unix_stream_connect(struct sock *sock, + struct sock *other, struct sock *newsk) { return 0; -- cgit v1.1 From b27dcfb0670ea7352a67137f4ff7947c2a9f6892 Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Wed, 17 Nov 2010 22:56:48 -0500 Subject: [libata] avoid needlessly passing around ptr to SCSI completion func It's stored in struct scsi_cmnd->scsi_done, making several 'done' parameters to functions redundant. Signed-off-by: Jeff Garzik --- include/linux/libata.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/libata.h b/include/linux/libata.h index d947b12..c9c5d7a 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -996,8 +996,7 @@ extern int ata_sas_port_init(struct ata_port *); extern int ata_sas_port_start(struct ata_port *ap); extern void ata_sas_port_stop(struct ata_port *ap); extern int ata_sas_slave_configure(struct scsi_device *, struct ata_port *); -extern int ata_sas_queuecmd(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *), - struct ata_port *ap); +extern int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap); extern int sata_scr_valid(struct ata_link *link); extern int sata_scr_read(struct ata_link *link, int reg, u32 *val); extern int sata_scr_write(struct ata_link *link, int reg, u32 val); @@ -1040,8 +1039,7 @@ extern unsigned int ata_do_dev_read_id(struct ata_device *dev, struct ata_taskfile *tf, u16 *id); extern void ata_qc_complete(struct ata_queued_cmd *qc); extern int ata_qc_complete_multiple(struct ata_port *ap, u32 qc_active); -extern void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd, - void (*done)(struct scsi_cmnd *)); +extern void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd); extern int ata_std_bios_param(struct scsi_device *sdev, struct block_device *bdev, sector_t capacity, int geom[]); -- cgit v1.1 From 9eba4a93ce520a627e876b0d1851d4f78a701c2b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Ol=C5=A1=C3=A1k?= Date: Wed, 5 Jan 2011 05:46:48 +0100 Subject: drm/radeon/kms: manage r300 CMASK RAM access and allow CMASK clear MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The CMASK RAM is for colorbuffer compression (used in conjunction with MSAA). Only one user (filp) can access it. The CMASK RAM access is managed in the same way as Hyper-Z, but there is a separate ioctl, because an app that uses MSAA does not necessarily have to use zbuffering. Signed-off-by: Marek Olšák Signed-off-by: Dave Airlie --- include/drm/radeon_drm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/drm/radeon_drm.h b/include/drm/radeon_drm.h index 10f8b53..e95a86b 100644 --- a/include/drm/radeon_drm.h +++ b/include/drm/radeon_drm.h @@ -906,6 +906,7 @@ struct drm_radeon_cs { #define RADEON_INFO_ACCEL_WORKING2 0x05 #define RADEON_INFO_TILING_CONFIG 0x06 #define RADEON_INFO_WANT_HYPERZ 0x07 +#define RADEON_INFO_WANT_CMASK 0x08 /* get access to CMASK on r300 */ struct drm_radeon_info { uint32_t request; -- cgit v1.1 From af5dd83b873efd4e1477f2265b6fa15a825aff26 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Thu, 6 Jan 2011 13:04:32 +1000 Subject: vga_switcheroo: fix build with non switcheroo enabled path. Signed-off-by: Dave Airlie --- include/linux/vga_switcheroo.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h index f80fa9d..4b9a7f5 100644 --- a/include/linux/vga_switcheroo.h +++ b/include/linux/vga_switcheroo.h @@ -49,6 +49,7 @@ int vga_switcheroo_process_delayed_switch(void); static inline void vga_switcheroo_unregister_client(struct pci_dev *dev) {} static inline int vga_switcheroo_register_client(struct pci_dev *dev, void (*set_gpu_state)(struct pci_dev *dev, enum vga_switcheroo_state), + void (*reprobe)(struct pci_dev *dev), bool (*can_switch)(struct pci_dev *dev)) { return 0; } static inline void vga_switcheroo_client_fb_set(struct pci_dev *dev, struct fb_info *info) {} static inline int vga_switcheroo_register_handler(struct vga_switcheroo_handler *handler) { return 0; } -- cgit v1.1 From b9f03a3cd06c6f8bbecfe08eae2a69cc0a13c690 Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Thu, 6 Jan 2011 18:04:02 +0900 Subject: video: udlfb: Kill off some magic constants for EDID sizing. The edid length is fixed, so use the standard definition consistently. Signed-off-by: Paul Mundt --- include/video/udlfb.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/video/udlfb.h b/include/video/udlfb.h index 6f9785e..bf85752 100644 --- a/include/video/udlfb.h +++ b/include/video/udlfb.h @@ -65,9 +65,6 @@ struct dlfb_data { #define MAX_TRANSFER (PAGE_SIZE*16 - BULK_SIZE) #define WRITES_IN_FLIGHT (4) -#define MIN_EDID_SIZE 128 -#define MAX_EDID_SIZE 128 - #define MAX_VENDOR_DESCRIPTOR_SIZE 256 #define GET_URB_TIMEOUT HZ @@ -95,9 +92,6 @@ struct dlfb_data { #define DL_ALIGN_UP(x, a) ALIGN(x, a) #define DL_ALIGN_DOWN(x, a) ALIGN(x-(a-1), a) -/* remove once this gets added to sysfs.h */ -#define __ATTR_RW(attr) __ATTR(attr, 0644, attr##_show, attr##_store) - /* * udlfb is both a usb device, and a framebuffer device. * They may exist at the same time, but during various stages -- cgit v1.1 From 81f6f3c1047392a22b9a20bbecf98c7f2d6f922a Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Thu, 6 Jan 2011 18:07:54 +0900 Subject: video: udlfb: Kill off special printk wrappers, use pr_fmt(). This kills off all of the dl_xxx() printk wrappers and simply stubs in a pr_fmt() definition to accomplish the same thing. Signed-off-by: Paul Mundt --- include/video/udlfb.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include') diff --git a/include/video/udlfb.h b/include/video/udlfb.h index bf85752..69d485a 100644 --- a/include/video/udlfb.h +++ b/include/video/udlfb.h @@ -92,20 +92,4 @@ struct dlfb_data { #define DL_ALIGN_UP(x, a) ALIGN(x, a) #define DL_ALIGN_DOWN(x, a) ALIGN(x-(a-1), a) -/* - * udlfb is both a usb device, and a framebuffer device. - * They may exist at the same time, but during various stages - * inactivity, teardown, or "virtual" operation, only one or the - * other will exist (one will outlive the other). So we can't - * call the dev_*() macros, because we don't have a stable dev object. - */ -#define dl_err(format, arg...) \ - pr_err("udlfb: " format, ## arg) -#define dl_warn(format, arg...) \ - pr_warning("udlfb: " format, ## arg) -#define dl_notice(format, arg...) \ - pr_notice("udlfb: " format, ## arg) -#define dl_info(format, arg...) \ - pr_info("udlfb: " format, ## arg) - #endif -- cgit v1.1 From cf24dc85ff29a41abd8e73730e5feb22b2666bd3 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 19 Feb 2010 15:39:52 +0100 Subject: mtd: OneNAND: add enable / disable methods to onenand_chip Add enable / disable methods called from get_device() / release_device(). These can be used, for example, to allow the driver to prevent the voltage regulator from being put to sleep while OneNAND is in use. Signed-off-by: Adrian Hunter Signed-off-by: David Woodhouse --- include/linux/mtd/onenand.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mtd/onenand.h b/include/linux/mtd/onenand.h index 6da3fe3..ae418e4 100644 --- a/include/linux/mtd/onenand.h +++ b/include/linux/mtd/onenand.h @@ -118,6 +118,8 @@ struct onenand_chip { int (*chip_probe)(struct mtd_info *mtd); int (*block_markbad)(struct mtd_info *mtd, loff_t ofs); int (*scan_bbt)(struct mtd_info *mtd); + int (*enable)(struct mtd_info *mtd); + int (*disable)(struct mtd_info *mtd); struct completion complete; int irq; -- cgit v1.1 From 0e4ca7e5101e7f4054452b8d71c535eec64a187b Mon Sep 17 00:00:00 2001 From: Anatolij Gustschin Date: Thu, 16 Dec 2010 23:42:14 +0100 Subject: mtd: add writebufsize field to mtd_info struct This field will be used to indicate the write buffer size of the MTD device. UBI will set it's minimal I/O unit size (min_io_size) to the indicated write buffer size. By this change we intend to fix failed recovery of UBIFS partitions we currently observe on NOR flash when mounting the partition after unclean unmount. Currently the min_io_size is set to mtd->writesize (which is 1 byte for NOR flash). But flash programming is often done from prepared write buffer containing multiple bytes and is performed in one programming operation which could be interrupted by a power cut or a system reset causing corrupted (partially written) areas in a flash sector. Knowing the size of potentially corrupted areas UBIFS scanning and recovery algorithms are able to perform successful recovery. In case of NOR flash minimal I/O size must be equal to the maximal size of the write buffer used by embedded flash programming algorithm. In case of NAND flash mtd->writebufsize should be equivalent to mtd->writesize. The subsequent patches will add mtd->writebufsize initialization where needed. Signed-off-by: Anatolij Gustschin Signed-off-by: Artem Bityutskiy Signed-off-by: David Woodhouse --- include/linux/mtd/mtd.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index fe8d77e..9d5306b 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -144,6 +144,17 @@ struct mtd_info { */ uint32_t writesize; + /* + * Size of the write buffer used by the MTD. MTD devices having a write + * buffer can write multiple writesize chunks at a time. E.g. while + * writing 4 * writesize bytes to a device with 2 * writesize bytes + * buffer the MTD driver can (but doesn't have to) do 2 writesize + * operations, but not 4. Currently, all NANDs have writebufsize + * equivalent to writesize (NAND page size). Some NOR flashes do have + * writebufsize greater than writesize. + */ + uint32_t writebufsize; + uint32_t oobsize; // Amount of OOB data per block (e.g. 16) uint32_t oobavail; // Available OOB bytes per block -- cgit v1.1 From 238c855805c853eaec95b0bc3065effb64f955a0 Mon Sep 17 00:00:00 2001 From: Henry Ptasinski Date: Tue, 4 Jan 2011 16:07:14 +0000 Subject: include/linux/if_ether.h: Add #define ETH_P_LINK_CTL for HPNA and wlan local tunnel Ethertype used by HPNA control protocols (LARQ, rate, link, etc) and by Broadcom wlan drivers for local signalling. Signed-off-by: Henry Ptasinski Signed-off-by: David S. Miller --- include/linux/if_ether.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index f9c3df0..be69043 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -72,6 +72,7 @@ #define ETH_P_MPLS_UC 0x8847 /* MPLS Unicast traffic */ #define ETH_P_MPLS_MC 0x8848 /* MPLS Multicast traffic */ #define ETH_P_ATMMPOA 0x884c /* MultiProtocol Over ATM */ +#define ETH_P_LINK_CTL 0x886c /* HPNA, wlan link local tunnel */ #define ETH_P_ATMFATE 0x8884 /* Frame-based ATM Transport * over Ethernet */ -- cgit v1.1 From f682cefa5ad204d3bfaa54a58046c66d2d035ac1 Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Wed, 5 Jan 2011 04:23:23 +0000 Subject: netfilter: fix the race when initializing nf_ct_expect_hash_rnd Since nf_ct_expect_dst_hash() may be called without nf_conntrack_lock locked, nf_ct_expect_hash_rnd should be initialized in the atomic way. In this patch, we use nf_conntrack_hash_rnd instead of nf_ct_expect_hash_rnd. Signed-off-by: Changli Gao Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/netfilter/nf_conntrack.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index caf17db..d85cff1 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -298,6 +298,8 @@ static inline int nf_ct_is_untracked(const struct nf_conn *ct) extern int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp); extern unsigned int nf_conntrack_htable_size; extern unsigned int nf_conntrack_max; +extern unsigned int nf_conntrack_hash_rnd; +void init_nf_conntrack_hash_rnd(void); #define NF_CT_STAT_INC(net, count) \ __this_cpu_inc((net)->ct.stat->count) -- cgit v1.1 From 2ad0d9d413abc3380fc1d89a9da7f8db59d9746b Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Thu, 6 Jan 2011 11:41:42 -0800 Subject: net: remove the duplicate #ifdef __KERNEL__ Since we are already in #ifdef __KERNEL__, we don't need to check it again. Signed-off-by: Changli Gao Signed-off-by: David S. Miller --- include/linux/socket.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/socket.h b/include/linux/socket.h index 86b652f..5f65f14 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -30,12 +30,10 @@ struct cred; #define __sockaddr_check_size(size) \ BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage))) -#ifdef __KERNEL__ -# ifdef CONFIG_PROC_FS +#ifdef CONFIG_PROC_FS struct seq_file; extern void socket_seq_show(struct seq_file *seq); -# endif -#endif /* __KERNEL__ */ +#endif typedef unsigned short sa_family_t; @@ -311,7 +309,6 @@ struct ucred { /* IPX options */ #define IPX_TYPE 1 -#ifdef __KERNEL__ extern void cred_to_ucred(struct pid *pid, const struct cred *cred, struct ucred *ucred); extern int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len); @@ -333,6 +330,5 @@ struct timespec; extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, struct timespec *timeout); -#endif #endif /* not kernel and not glibc */ #endif /* _LINUX_SOCKET_H */ -- cgit v1.1 From 1f11a034cdc4b45ee56d51b87a9e37cb776fb15b Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Thu, 6 Jan 2011 02:04:26 +0000 Subject: SUNRPC new transport for the NFSv4.1 shared back channel Move the current sock create and destroy routines into the new transport ops. Back channel socket will be destroyed by the svc_closs_all call in svc_destroy. Added check: only TCP supported on shared back channel. Signed-off-by: Andy Adamson Acked-by: Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/sunrpc/svcsock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index 1b353a7..3a45a80 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -45,6 +45,7 @@ int svc_sock_names(struct svc_serv *serv, char *buf, int svc_addsock(struct svc_serv *serv, const int fd, char *name_return, const size_t len); void svc_init_xprt_sock(void); +void svc_init_bc_xprt_sock(void); void svc_cleanup_xprt_sock(void); struct svc_xprt *svc_sock_create(struct svc_serv *serv, int prot); void svc_sock_destroy(struct svc_xprt *); -- cgit v1.1 From 16b2d1e1d12de000404d7c845d0db1226511f84d Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Thu, 6 Jan 2011 02:04:27 +0000 Subject: SUNRPC register and unregister the back channel transport Signed-off-by: Andy Adamson Signed-off-by: Trond Myklebust --- include/linux/sunrpc/svcsock.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index 3a45a80..1b353a7 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -45,7 +45,6 @@ int svc_sock_names(struct svc_serv *serv, char *buf, int svc_addsock(struct svc_serv *serv, const int fd, char *name_return, const size_t len); void svc_init_xprt_sock(void); -void svc_init_bc_xprt_sock(void); void svc_cleanup_xprt_sock(void); struct svc_xprt *svc_sock_create(struct svc_serv *serv, int prot); void svc_sock_destroy(struct svc_xprt *); -- cgit v1.1 From f4eecd5da3422e82e88e36c33cbd2595eebcacb1 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Thu, 6 Jan 2011 02:04:30 +0000 Subject: NFS implement v4.0 callback_ident Use the small id to pointer translator service to provide a unique callback identifier per SETCLIENTID call used to identify the v4.0 callback service associated with the clientid. Signed-off-by: Andy Adamson Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 452d964..1eaa054 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -71,6 +71,7 @@ struct nfs_client { */ char cl_ipaddr[48]; unsigned char cl_id_uniquifier; + u32 cl_cb_ident; /* v4.0 callback identifier */ const struct nfs4_minor_version_ops *cl_mvops; #endif /* CONFIG_NFS_V4 */ -- cgit v1.1 From 2c2618c6f29c41a0a966f14f05c8bf45fcabb750 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Thu, 6 Jan 2011 02:04:31 +0000 Subject: NFS associate sessionid with callback connection The sessions based callback service is started prior to the CREATE_SESSION call so that it can handle CB_NULL requests which can be sent before the CREATE_SESSION call returns and the session ID is known. Set the callback sessionid after a sucessful CREATE_SESSION. Signed-off-by: Andy Adamson Signed-off-by: Trond Myklebust --- include/linux/sunrpc/svc_xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index aea0d438..357da5e 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -78,6 +78,7 @@ struct svc_xprt { size_t xpt_remotelen; /* length of address */ struct rpc_wait_queue xpt_bc_pending; /* backchannel wait queue */ struct list_head xpt_users; /* callbacks on free */ + void *xpt_bc_sid; /* back channel session ID */ struct net *xpt_net; }; -- cgit v1.1 From c36fca52f5e4594ffd0ff175b328966b0d393184 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Thu, 6 Jan 2011 02:04:32 +0000 Subject: NFS refactor nfs_find_client and reference client across callback processing Fixes a bug where the nfs_client could be freed during callback processing. Refactor nfs_find_client to use minorversion specific means to locate the correct nfs_client structure. In the NFS layer, V4.0 clients are found using the callback_ident field in the CB_COMPOUND header. V4.1 clients are found using the sessionID in the CB_SEQUENCE operation which is also compared against the sessionID associated with the back channel thread after a successful CREATE_SESSION. Each of these methods finds the one an only nfs_client associated with the incoming callback request - so nfs_find_client_next is not needed. In the RPC layer, the pg_authenticate call needs to find the nfs_client. For the v4.0 callback service, the callback identifier has not been decoded so a search by address, version, and minorversion is used. The sessionid for the sessions based callback service has (usually) not been set for the pg_authenticate on a CB_NULL call which can be sent prior to the return of a CREATE_SESSION call, so the sessionid associated with the back channel thread is not used to find the client in pg_authenticate for CB_NULL calls. Pass the referenced nfs_client to each CB_COMPOUND operation being proceesed via the new cb_process_state structure. The reference is held across cb_compound processing. Use the new cb_process_state struct to move the NFS4ERR_RETRY_UNCACHED_REP processing from process_op into nfs4_callback_sequence where it belongs. Signed-off-by: Andy Adamson Signed-off-by: Trond Myklebust --- include/linux/sunrpc/bc_xprt.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h index 7c91260..2c60e09 100644 --- a/include/linux/sunrpc/bc_xprt.h +++ b/include/linux/sunrpc/bc_xprt.h @@ -47,6 +47,14 @@ static inline int svc_is_backchannel(const struct svc_rqst *rqstp) return 1; return 0; } +static inline struct nfs4_sessionid *bc_xprt_sid(struct svc_rqst *rqstp) +{ + if (svc_is_backchannel(rqstp)) + return (struct nfs4_sessionid *) + rqstp->rq_server->bc_xprt->xpt_bc_sid; + return NULL; +} + #else /* CONFIG_NFS_V4_1 */ static inline int xprt_setup_backchannel(struct rpc_xprt *xprt, unsigned int min_reqs) @@ -59,6 +67,11 @@ static inline int svc_is_backchannel(const struct svc_rqst *rqstp) return 0; } +static inline struct nfs4_sessionid *bc_xprt_sid(struct svc_rqst *rqstp) +{ + return NULL; +} + static inline void xprt_free_bc_request(struct rpc_rqst *req) { } -- cgit v1.1 From 42acd021824578fa0eeb6eb58d457c23ec5dc9c0 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Thu, 6 Jan 2011 02:04:34 +0000 Subject: NFS add session back channel draining Currently session draining only drains the fore channel. The back channel processing must also be drained. Use the back channel highest_slot_used to indicate that a callback is being processed by the callback thread. Move the session complete to be per channel. When the session is draininig, wait for any current back channel processing to complete and stop all new back channel processing by returning NFS4ERR_DELAY to the back channel client. Drain the back channel, then the fore channel. Signed-off-by: Andy Adamson Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 1eaa054..e93ada0 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -197,6 +197,7 @@ struct nfs4_slot_table { * op for dynamic resizing */ int target_max_slots; /* Set by CB_RECALL_SLOT as * the new max_slots */ + struct completion complete; }; static inline int slot_idx(struct nfs4_slot_table *tbl, struct nfs4_slot *sp) @@ -213,7 +214,6 @@ struct nfs4_session { unsigned long session_state; u32 hash_alg; u32 ssv_len; - struct completion complete; /* The fore and back channel */ struct nfs4_channel_attrs fc_attrs; -- cgit v1.1 From 4a19de0f4b693139bb10b7cc3cfe1f618576ba67 Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Thu, 6 Jan 2011 02:04:35 +0000 Subject: NFS rename client back channel transport field Differentiate from server backchannel Signed-off-by: Andy Adamson Acked-by: Bruce Fields Signed-off-by: Trond Myklebust --- include/linux/sunrpc/bc_xprt.h | 4 ++-- include/linux/sunrpc/svc.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h index 2c60e09..c50b458 100644 --- a/include/linux/sunrpc/bc_xprt.h +++ b/include/linux/sunrpc/bc_xprt.h @@ -43,7 +43,7 @@ int bc_send(struct rpc_rqst *req); */ static inline int svc_is_backchannel(const struct svc_rqst *rqstp) { - if (rqstp->rq_server->bc_xprt) + if (rqstp->rq_server->sv_bc_xprt) return 1; return 0; } @@ -51,7 +51,7 @@ static inline struct nfs4_sessionid *bc_xprt_sid(struct svc_rqst *rqstp) { if (svc_is_backchannel(rqstp)) return (struct nfs4_sessionid *) - rqstp->rq_server->bc_xprt->xpt_bc_sid; + rqstp->rq_server->sv_bc_xprt->xpt_bc_sid; return NULL; } diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 5a3085b..c81d4d8 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -99,7 +99,7 @@ struct svc_serv { spinlock_t sv_cb_lock; /* protects the svc_cb_list */ wait_queue_head_t sv_cb_waitq; /* sleep here if there are no * entries in the svc_cb_list */ - struct svc_xprt *bc_xprt; + struct svc_xprt *sv_bc_xprt; /* callback on fore channel */ #endif /* CONFIG_NFS_V4_1 */ }; -- cgit v1.1 From daaa82d1c72e10dc16cad3a810e225f9188dc7aa Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Thu, 6 Jan 2011 11:36:19 +0000 Subject: pnfs: remove unnecessary field lgp->status Signed-off-by: Fred Isaman Signed-off-by: Benny Halevy Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 236e7e4..8fcc542 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -223,7 +223,6 @@ struct nfs4_layoutget { struct nfs4_layoutget_args args; struct nfs4_layoutget_res res; struct pnfs_layout_segment **lsegpp; - int status; }; struct nfs4_getdeviceinfo_args { -- cgit v1.1 From cf7d63f1f9895713551df2e6d18b006f8af26e91 Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Thu, 6 Jan 2011 11:36:25 +0000 Subject: pnfs: serialize LAYOUTGET(openstateid) We shouldn't send a LAYOUTGET(openstateid) unless all outstanding RPCs using the previous stateid are completed. This requires choosing the stateid to encode earlier, so we can abort if one is not available (we want to use the open stateid, but a LAYOUTGET is already out using it), and adding a count of the number of outstanding rpc calls using layout state (which for now consist solely of LAYOUTGETs). Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 8fcc542..83d36d3 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -208,6 +208,7 @@ struct nfs4_layoutget_args { struct inode *inode; struct nfs_open_context *ctx; struct nfs4_sequence_args seq_args; + nfs4_stateid stateid; }; struct nfs4_layoutget_res { -- cgit v1.1 From f7e8917a67980924651a9e244510e63ef05c7755 Mon Sep 17 00:00:00 2001 From: Fred Isaman Date: Thu, 6 Jan 2011 11:36:32 +0000 Subject: pnfs: layout roc code A layout can request return-on-close. How this interacts with the forgetful model of never sending LAYOUTRETURNS is a bit ambiguous. We forget any layouts marked roc, and wait for them to be completely forgotten before continuing with the close. In addition, to compensate for races with any inflight LAYOUTGETs, and the fact that we do not get any layout stateid back from the server, we set the barrier to the worst case scenario of current_seqid + number of outstanding LAYOUTGETS. Signed-off-by: Fred Isaman Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index e93ada0..7f20c0b 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -149,6 +149,7 @@ struct nfs_server { that are supported on this filesystem */ struct pnfs_layoutdriver_type *pnfs_curr_ld; /* Active layout driver */ + struct rpc_wait_queue roc_rpcwaitq; #endif void (*destroy)(struct nfs_server *); -- cgit v1.1 From 24d292b894273495f9664bb495e575f8cb7e8cac Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 24 Dec 2010 01:32:43 +0000 Subject: NFS: Move cl_state_owners and related fields to the nfs_server struct NFSv4 migration needs to reassociate state owners from the source to the destination nfs_server data structures. To make that easier, move the cl_state_owners field to the nfs_server struct. cl_openowner_id and cl_lockowner_id accompany this move, as they are used in conjunction with cl_state_owners. The cl_lock field in the parent nfs_client continues to protect all three of these fields. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 7f20c0b..27255ff 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -47,11 +47,7 @@ struct nfs_client { u64 cl_clientid; /* constant */ unsigned long cl_state; - struct rb_root cl_openowner_id; - struct rb_root cl_lockowner_id; - struct list_head cl_delegations; - struct rb_root cl_state_owners; spinlock_t cl_lock; unsigned long cl_lease_time; @@ -150,6 +146,11 @@ struct nfs_server { filesystem */ struct pnfs_layoutdriver_type *pnfs_curr_ld; /* Active layout driver */ struct rpc_wait_queue roc_rpcwaitq; + + /* the following fields are protected by nfs_client->cl_lock */ + struct rb_root state_owners; + struct rb_root openowner_id; + struct rb_root lockowner_id; #endif void (*destroy)(struct nfs_server *); -- cgit v1.1 From d3978bb325510f0a26ebd92f211b36c5f98b2306 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 24 Dec 2010 01:33:04 +0000 Subject: NFS: Move cl_delegations to the nfs_server struct Delegations are per-inode, not per-nfs_client. When a server file system is migrated, delegations on the client must be moved from the source to the destination nfs_server. Make it easier to manage a mount point's delegation list across a migration event by moving the list to the nfs_server struct. Clean up: I added documenting comments to public functions I changed in this patch. For consistency I added comments to all the other public functions in fs/nfs/delegation.c. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/nfs_fs_sb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 27255ff..b197563 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -47,7 +47,6 @@ struct nfs_client { u64 cl_clientid; /* constant */ unsigned long cl_state; - struct list_head cl_delegations; spinlock_t cl_lock; unsigned long cl_lease_time; @@ -152,6 +151,7 @@ struct nfs_server { struct rb_root openowner_id; struct rb_root lockowner_id; #endif + struct list_head delegations; void (*destroy)(struct nfs_server *); atomic_t active; /* Keep trace of any activity to this server */ -- cgit v1.1 From d035c36c58dd9183ad6aa7875dea89893faedb55 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 21 Dec 2010 10:45:27 -0500 Subject: NFSv4: Ensure continued open and lockowner name uniqueness In order to enable migration support, we will want to move some of the structures that are subject to migration into the struct nfs_server. In particular, if we are to move the state_owner and state_owner_id to being a per-filesystem structure, then we should label the resulting open/lock owners with a per-filesytem label to ensure global uniqueness. This patch does so by adding the super block s_dev to the open/lock owner name. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 83d36d3..b006857 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -317,6 +317,7 @@ struct nfs_closeres { struct nfs_lowner { __u64 clientid; __u64 id; + dev_t s_dev; }; struct nfs_lock_args { -- cgit v1.1 From dfe63bb0ad9810db13aab0058caba97866e0a681 Mon Sep 17 00:00:00 2001 From: James Simmons Date: Thu, 23 Dec 2010 16:40:37 +0000 Subject: drm: Update fbdev fb_fix_screeninfo If you change the color depth via fbset or some other framebuffer aware userland application struct fb_fix_screeninfo is not updated to this new information. This patch fixes this issue. Also the function is changed to just pass in struct drm_framebuffer so in the future we could use more fields. I'm hoping some day fix->smem* could be set here :-) Signed-off-by: James Simmons Signed-off-by: Dave Airlie --- include/drm/drm_fb_helper.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h index f22e7fe..aac27bd 100644 --- a/include/drm/drm_fb_helper.h +++ b/include/drm/drm_fb_helper.h @@ -121,9 +121,6 @@ int drm_fb_helper_setcolreg(unsigned regno, void drm_fb_helper_restore(void); void drm_fb_helper_fill_var(struct fb_info *info, struct drm_fb_helper *fb_helper, uint32_t fb_width, uint32_t fb_height); -void drm_fb_helper_fill_fix(struct fb_info *info, uint32_t pitch, - uint32_t depth); - int drm_fb_helper_setcmap(struct fb_cmap *cmap, struct fb_info *info); bool drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper); -- cgit v1.1 From 21493088733e6e09dac6f54595a1b6b8ab1e68fd Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Fri, 7 Jan 2011 14:52:00 +1100 Subject: crypto: padlock - Move padlock.h into include/crypto This patch moves padlock.h from drivers/crypto into include/crypto so that it may be used by the via-rng driver. Signed-off-by: Herbert Xu --- include/crypto/padlock.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) create mode 100644 include/crypto/padlock.h (limited to 'include') diff --git a/include/crypto/padlock.h b/include/crypto/padlock.h new file mode 100644 index 0000000..d2cfa2e --- /dev/null +++ b/include/crypto/padlock.h @@ -0,0 +1,29 @@ +/* + * Driver for VIA PadLock + * + * Copyright (c) 2004 Michal Ludvig + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + */ + +#ifndef _CRYPTO_PADLOCK_H +#define _CRYPTO_PADLOCK_H + +#define PADLOCK_ALIGNMENT 16 + +#define PFX KBUILD_MODNAME ": " + +#define PADLOCK_CRA_PRIORITY 300 +#define PADLOCK_COMPOSITE_PRIORITY 400 + +#ifdef CONFIG_64BIT +#define STACK_ALIGN 16 +#else +#define STACK_ALIGN 4 +#endif + +#endif /* _CRYPTO_PADLOCK_H */ -- cgit v1.1 From 2b2fd604bda01bfea9f1657ca468c134448e03a5 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 6 Jan 2011 21:19:35 -0500 Subject: drm/radeon/kms: add NI pci ids Signed-off-by: Alex Deucher Signed-off-by: Dave Airlie --- include/drm/drm_pciids.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include') diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h index e6b28a3..fe29ae3 100644 --- a/include/drm/drm_pciids.h +++ b/include/drm/drm_pciids.h @@ -142,6 +142,42 @@ {0x1002, 0x5e4c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV410|RADEON_NEW_MEMMAP}, \ {0x1002, 0x5e4d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV410|RADEON_NEW_MEMMAP}, \ {0x1002, 0x5e4f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV410|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6720, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BARTS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6721, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BARTS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6722, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BARTS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6723, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BARTS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6724, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BARTS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6725, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BARTS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6726, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BARTS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6727, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BARTS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6728, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BARTS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6729, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BARTS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6738, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BARTS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6739, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BARTS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6740, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6741, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6742, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6743, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6744, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6745, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6746, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6747, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6748, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6749, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6750, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6758, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6759, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6760, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6761, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6762, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6763, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6764, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6765, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6766, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6767, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6768, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6770, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6779, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6880, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6888, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6889, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_NEW_MEMMAP}, \ -- cgit v1.1 From 26fcaf60fe3861409eb4c455c5c0d0f00f599b08 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 7 Jan 2011 01:42:31 +0100 Subject: PM: Fix oops in suspend/hibernate code related to failing ioremap() When ioremap() fails (which might happen for some reason), we nicely oops in suspend_nvs_save() due to NULL dereference by memcpy() in there. Fail gracefully instead. Signed-off-by: Jiri Slaby Signed-off-by: Rafael J. Wysocki Signed-off-by: Len Brown --- include/linux/suspend.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 2669751..acb7d91 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -262,7 +262,7 @@ static inline bool system_entering_hibernation(void) { return false; } extern int suspend_nvs_register(unsigned long start, unsigned long size); extern int suspend_nvs_alloc(void); extern void suspend_nvs_free(void); -extern void suspend_nvs_save(void); +extern int suspend_nvs_save(void); extern void suspend_nvs_restore(void); #else /* CONFIG_SUSPEND_NVS */ static inline int suspend_nvs_register(unsigned long a, unsigned long b) @@ -271,7 +271,7 @@ static inline int suspend_nvs_register(unsigned long a, unsigned long b) } static inline int suspend_nvs_alloc(void) { return 0; } static inline void suspend_nvs_free(void) {} -static inline void suspend_nvs_save(void) {} +static inline int suspend_nvs_save(void) {} static inline void suspend_nvs_restore(void) {} #endif /* CONFIG_SUSPEND_NVS */ -- cgit v1.1 From 976513dbfc1547c7b1822566923058655f0c32fd Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 7 Jan 2011 01:43:44 +0100 Subject: PM / ACPI: Move NVS saving and restoring code to drivers/acpi The saving of the ACPI NVS area during hibernation and suspend and restoring it during the subsequent resume is entirely specific to ACPI, so move it to drivers/acpi and drop the CONFIG_SUSPEND_NVS configuration option which is redundant. Signed-off-by: Rafael J. Wysocki Signed-off-by: Len Brown --- include/linux/acpi.h | 9 +++++++++ include/linux/suspend.h | 17 ----------------- 2 files changed, 9 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 67c91b4..fa7ed6a98 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -254,6 +254,15 @@ void __init acpi_old_suspend_ordering(void); void __init acpi_nvs_nosave(void); #endif /* CONFIG_PM_SLEEP */ +#ifdef CONFIG_ACPI_SLEEP +int suspend_nvs_register(unsigned long start, unsigned long size); +#else +static inline int suspend_nvs_register(unsigned long a, unsigned long b) +{ + return 0; +} +#endif + struct acpi_osc_context { char *uuid_str; /* uuid string */ int rev; diff --git a/include/linux/suspend.h b/include/linux/suspend.h index acb7d91..0e288e3 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -258,23 +258,6 @@ static inline int hibernate(void) { return -ENOSYS; } static inline bool system_entering_hibernation(void) { return false; } #endif /* CONFIG_HIBERNATION */ -#ifdef CONFIG_SUSPEND_NVS -extern int suspend_nvs_register(unsigned long start, unsigned long size); -extern int suspend_nvs_alloc(void); -extern void suspend_nvs_free(void); -extern int suspend_nvs_save(void); -extern void suspend_nvs_restore(void); -#else /* CONFIG_SUSPEND_NVS */ -static inline int suspend_nvs_register(unsigned long a, unsigned long b) -{ - return 0; -} -static inline int suspend_nvs_alloc(void) { return 0; } -static inline void suspend_nvs_free(void) {} -static inline int suspend_nvs_save(void) {} -static inline void suspend_nvs_restore(void) {} -#endif /* CONFIG_SUSPEND_NVS */ - #ifdef CONFIG_PM_SLEEP void save_processor_state(void); void restore_processor_state(void); -- cgit v1.1 From 7fa69baf29de8c77a6b32c054df2abb8f11f8aa4 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 6 Jan 2011 23:35:10 +0100 Subject: ACPI / PM: Drop special ACPI wakeup flags Drop special ACPI wakeup flags, wakeup.state.enabled and wakeup.flags.always_enabled, that aren't necessary any more after we've started to use standard device wakeup flags for handling ACPI wakeup devices. Signed-off-by: Rafael J. Wysocki Signed-off-by: Len Brown --- include/acpi/acpi_bus.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 359ef11..f2499f5 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -242,20 +242,14 @@ struct acpi_device_perf { struct acpi_device_wakeup_flags { u8 valid:1; /* Can successfully enable wakeup? */ u8 run_wake:1; /* Run-Wake GPE devices */ - u8 always_enabled:1; /* Run-wake devices that are always enabled */ u8 notifier_present:1; /* Wake-up notify handler has been installed */ }; -struct acpi_device_wakeup_state { - u8 enabled:1; -}; - struct acpi_device_wakeup { acpi_handle gpe_device; u64 gpe_number; u64 sleep_state; struct acpi_handle_list resources; - struct acpi_device_wakeup_state state; struct acpi_device_wakeup_flags flags; int prepare_count; int run_wake_count; -- cgit v1.1 From ccd35fb9f4da856b105ea0f1e0cab3702e8ae6ba Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:17 +1100 Subject: kernel: kmem_ptr_validate considered harmful This is a nasty and error prone API. It is no longer used, remove it. Signed-off-by: Nick Piggin --- include/linux/slab.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/slab.h b/include/linux/slab.h index 59260e2..fa90866 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -106,8 +106,6 @@ int kmem_cache_shrink(struct kmem_cache *); void kmem_cache_free(struct kmem_cache *, void *); unsigned int kmem_cache_size(struct kmem_cache *); const char *kmem_cache_name(struct kmem_cache *); -int kern_ptr_validate(const void *ptr, unsigned long size); -int kmem_ptr_validate(struct kmem_cache *cachep, const void *ptr); /* * Please use this macro to create slab caches. Simply specify the -- cgit v1.1 From 5eef7fa905c814826f518aca2d414ca77508ce30 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:22 +1100 Subject: fs: dcache documentation cleanup Remove redundant (and incorrect, since dcache RCU lookup) dentry locking documentation and point to the canonical document. Signed-off-by: Nick Piggin --- include/linux/dcache.h | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 6a4aea3..fff9755 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -141,22 +141,16 @@ struct dentry_operations { char *(*d_dname)(struct dentry *, char *, int); }; -/* the dentry parameter passed to d_hash and d_compare is the parent +/* + * Locking rules for dentry_operations callbacks are to be found in + * Documentation/filesystems/Locking. Keep it updated! + * + * the dentry parameter passed to d_hash and d_compare is the parent * directory of the entries to be compared. It is used in case these * functions need any directory specific information for determining * equivalency classes. Using the dentry itself might not work, as it * might be a negative dentry which has no information associated with - * it */ - -/* -locking rules: - big lock dcache_lock d_lock may block -d_revalidate: no no no yes -d_hash no no no yes -d_compare: no yes yes no -d_delete: no yes no no -d_release: no no no yes -d_iput: no no no yes + * it. */ /* d_flags entries */ -- cgit v1.1 From fe15ce446beb3a33583af81ffe6c9d01a75314ed Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:23 +1100 Subject: fs: change d_delete semantics Change d_delete from a dentry deletion notification to a dentry caching advise, more like ->drop_inode. Require it to be constant and idempotent, and not take d_lock. This is how all existing filesystems use the callback anyway. This makes fine grained dentry locking of dput and dentry lru scanning much simpler. Signed-off-by: Nick Piggin --- include/linux/dcache.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index fff9755..cbfc956 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -133,9 +133,9 @@ enum dentry_d_lock_class struct dentry_operations { int (*d_revalidate)(struct dentry *, struct nameidata *); - int (*d_hash) (struct dentry *, struct qstr *); - int (*d_compare) (struct dentry *, struct qstr *, struct qstr *); - int (*d_delete)(struct dentry *); + int (*d_hash)(struct dentry *, struct qstr *); + int (*d_compare)(struct dentry *, struct qstr *, struct qstr *); + int (*d_delete)(const struct dentry *); void (*d_release)(struct dentry *); void (*d_iput)(struct dentry *, struct inode *); char *(*d_dname)(struct dentry *, char *, int); -- cgit v1.1 From fb2d5b86aff355a27ebfc132d3c99f4a940cc3fe Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:26 +1100 Subject: fs: name case update method smpfs and ncpfs want to update a live dentry name in-place. Rather than have them open code the locking, provide a documented dcache API. Signed-off-by: Nick Piggin --- include/linux/dcache.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index cbfc956..6cdf499 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -290,6 +290,8 @@ static inline struct dentry *d_add_unique(struct dentry *entry, struct inode *in return res; } +extern void dentry_update_name_case(struct dentry *, struct qstr *); + /* used for rename() and baskets */ extern void d_move(struct dentry *, struct dentry *); extern struct dentry *d_ancestor(struct dentry *, struct dentry *); -- cgit v1.1 From 621e155a3591962420eacdd39f6f0aa29ceb221e Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:27 +1100 Subject: fs: change d_compare for rcu-walk Change d_compare so it may be called from lock-free RCU lookups. This does put significant restrictions on what may be done from the callback, however there don't seem to have been any problems with in-tree fses. If some strange use case pops up that _really_ cannot cope with the rcu-walk rules, we can just add new rcu-unaware callbacks, which would cause name lookup to drop out of rcu-walk mode. For in-tree filesystems, this is just a mechanical change. Signed-off-by: Nick Piggin --- include/linux/dcache.h | 12 +++++------- include/linux/ncp_fs.h | 4 ++-- 2 files changed, 7 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 6cdf499..75a072b 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -134,7 +134,9 @@ enum dentry_d_lock_class struct dentry_operations { int (*d_revalidate)(struct dentry *, struct nameidata *); int (*d_hash)(struct dentry *, struct qstr *); - int (*d_compare)(struct dentry *, struct qstr *, struct qstr *); + int (*d_compare)(const struct dentry *, const struct inode *, + const struct dentry *, const struct inode *, + unsigned int, const char *, const struct qstr *); int (*d_delete)(const struct dentry *); void (*d_release)(struct dentry *); void (*d_iput)(struct dentry *, struct inode *); @@ -145,12 +147,8 @@ struct dentry_operations { * Locking rules for dentry_operations callbacks are to be found in * Documentation/filesystems/Locking. Keep it updated! * - * the dentry parameter passed to d_hash and d_compare is the parent - * directory of the entries to be compared. It is used in case these - * functions need any directory specific information for determining - * equivalency classes. Using the dentry itself might not work, as it - * might be a negative dentry which has no information associated with - * it. + * FUrther descriptions are found in Documentation/filesystems/vfs.txt. + * Keep it updated too! */ /* d_flags entries */ diff --git a/include/linux/ncp_fs.h b/include/linux/ncp_fs.h index ef66306..1c27f20 100644 --- a/include/linux/ncp_fs.h +++ b/include/linux/ncp_fs.h @@ -184,13 +184,13 @@ struct ncp_entry_info { __u8 file_handle[6]; }; -static inline struct ncp_server *NCP_SBP(struct super_block *sb) +static inline struct ncp_server *NCP_SBP(const struct super_block *sb) { return sb->s_fs_info; } #define NCP_SERVER(inode) NCP_SBP((inode)->i_sb) -static inline struct ncp_inode_info *NCP_FINFO(struct inode *inode) +static inline struct ncp_inode_info *NCP_FINFO(const struct inode *inode) { return container_of(inode, struct ncp_inode_info, vfs_inode); } -- cgit v1.1 From b1e6a015a580ad145689ad1d6b4aa0e03e6c868b Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:28 +1100 Subject: fs: change d_hash for rcu-walk Change d_hash so it may be called from lock-free RCU lookups. See similar patch for d_compare for details. For in-tree filesystems, this is just a mechanical change. Signed-off-by: Nick Piggin --- include/linux/dcache.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 75a072b..1149e70 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -133,7 +133,8 @@ enum dentry_d_lock_class struct dentry_operations { int (*d_revalidate)(struct dentry *, struct nameidata *); - int (*d_hash)(struct dentry *, struct qstr *); + int (*d_hash)(const struct dentry *, const struct inode *, + struct qstr *); int (*d_compare)(const struct dentry *, const struct inode *, const struct dentry *, const struct inode *, unsigned int, const char *, const struct qstr *); -- cgit v1.1 From ec2447c278ee973d35f38e53ca16ba7f965ae33d Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:29 +1100 Subject: hostfs: simplify locking Remove dcache_lock locking from hostfs filesystem, and move it into dcache helpers. All that is required is a coherent path name. Protection from concurrent modification of the namespace after path name generation is not provided in current code, because dcache_lock is dropped before the path is used. Signed-off-by: Nick Piggin --- include/linux/dcache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 1149e70..cea27df 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -311,7 +311,7 @@ extern char *dynamic_dname(struct dentry *, char *, int, const char *, ...); extern char *__d_path(const struct path *path, struct path *root, char *, int); extern char *d_path(const struct path *, char *, int); extern char *d_path_with_unreachable(const struct path *, char *, int); -extern char *__dentry_path(struct dentry *, char *, int); +extern char *dentry_path_raw(struct dentry *, char *, int); extern char *dentry_path(struct dentry *, char *, int); /* Allocation counts.. */ -- cgit v1.1 From 789680d1ee9311cdf095241dc02bd9784d799cd1 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:30 +1100 Subject: fs: dcache scale hash Add a new lock, dcache_hash_lock, to protect the dcache hash table from concurrent modification. d_hash is also protected by d_lock. Signed-off-by: Nick Piggin --- include/linux/dcache.h | 35 ++--------------------------------- 1 file changed, 2 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index cea27df..2feb624 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -184,39 +184,6 @@ struct dentry_operations { extern spinlock_t dcache_lock; extern seqlock_t rename_lock; -/** - * d_drop - drop a dentry - * @dentry: dentry to drop - * - * d_drop() unhashes the entry from the parent dentry hashes, so that it won't - * be found through a VFS lookup any more. Note that this is different from - * deleting the dentry - d_delete will try to mark the dentry negative if - * possible, giving a successful _negative_ lookup, while d_drop will - * just make the cache lookup fail. - * - * d_drop() is used mainly for stuff that wants to invalidate a dentry for some - * reason (NFS timeouts or autofs deletes). - * - * __d_drop requires dentry->d_lock. - */ - -static inline void __d_drop(struct dentry *dentry) -{ - if (!(dentry->d_flags & DCACHE_UNHASHED)) { - dentry->d_flags |= DCACHE_UNHASHED; - hlist_del_rcu(&dentry->d_hash); - } -} - -static inline void d_drop(struct dentry *dentry) -{ - spin_lock(&dcache_lock); - spin_lock(&dentry->d_lock); - __d_drop(dentry); - spin_unlock(&dentry->d_lock); - spin_unlock(&dcache_lock); -} - static inline int dname_external(struct dentry *dentry) { return dentry->d_name.name != dentry->d_iname; @@ -228,6 +195,8 @@ static inline int dname_external(struct dentry *dentry) extern void d_instantiate(struct dentry *, struct inode *); extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *); extern struct dentry * d_materialise_unique(struct dentry *, struct inode *); +extern void __d_drop(struct dentry *dentry); +extern void d_drop(struct dentry *dentry); extern void d_delete(struct dentry *); /* allocate/de-allocate */ -- cgit v1.1 From b7ab39f631f505edc2bbdb86620d5493f995c9da Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:32 +1100 Subject: fs: dcache scale dentry refcount Make d_count non-atomic and protect it with d_lock. This allows us to ensure a 0 refcount dentry remains 0 without dcache_lock. It is also fairly natural when we start protecting many other dentry members with d_lock. Signed-off-by: Nick Piggin --- include/linux/dcache.h | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 2feb624..b0ade2d 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -87,7 +87,7 @@ full_name_hash(const unsigned char *name, unsigned int len) #endif struct dentry { - atomic_t d_count; + unsigned int d_count; /* protected by d_lock */ unsigned int d_flags; /* protected by d_lock */ spinlock_t d_lock; /* per dentry lock */ int d_mounted; @@ -297,17 +297,28 @@ extern char *dentry_path(struct dentry *, char *, int); * needs and they take necessary precautions) you should hold dcache_lock * and call dget_locked() instead of dget(). */ - +static inline struct dentry *dget_dlock(struct dentry *dentry) +{ + if (dentry) { + BUG_ON(!dentry->d_count); + dentry->d_count++; + } + return dentry; +} static inline struct dentry *dget(struct dentry *dentry) { if (dentry) { - BUG_ON(!atomic_read(&dentry->d_count)); - atomic_inc(&dentry->d_count); + spin_lock(&dentry->d_lock); + dget_dlock(dentry); + spin_unlock(&dentry->d_lock); } return dentry; } extern struct dentry * dget_locked(struct dentry *); +extern struct dentry * dget_locked_dlock(struct dentry *); + +extern struct dentry *dget_parent(struct dentry *dentry); /** * d_unhashed - is dentry hashed @@ -338,16 +349,6 @@ static inline void dont_mount(struct dentry *dentry) spin_unlock(&dentry->d_lock); } -static inline struct dentry *dget_parent(struct dentry *dentry) -{ - struct dentry *ret; - - spin_lock(&dentry->d_lock); - ret = dget(dentry->d_parent); - spin_unlock(&dentry->d_lock); - return ret; -} - extern void dput(struct dentry *); static inline int d_mountpoint(struct dentry *dentry) -- cgit v1.1 From 2fd6b7f50797f2e993eea59e0a0b8c6399c811dc Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:34 +1100 Subject: fs: dcache scale subdirs Protect d_subdirs and d_child with d_lock, except in filesystems that aren't using dcache_lock for these anyway (eg. using i_mutex). Note: if we change the locking rule in future so that ->d_child protection is provided only with ->d_parent->d_lock, it may allow us to reduce some locking. But it would be an exception to an otherwise regular locking scheme, so we'd have to see some good results. Probably not worthwhile. Signed-off-by: Nick Piggin --- include/linux/dcache.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index b0ade2d..ddf4f55 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -305,6 +305,7 @@ static inline struct dentry *dget_dlock(struct dentry *dentry) } return dentry; } + static inline struct dentry *dget(struct dentry *dentry) { if (dentry) { -- cgit v1.1 From b23fb0a60379a95e10c671f646b259ea2558421e Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:35 +1100 Subject: fs: scale inode alias list Add a new lock, dcache_inode_lock, to protect the inode's i_dentry list from concurrent modification. d_alias is also protected by d_lock. Signed-off-by: Nick Piggin --- include/linux/dcache.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index ddf4f55..bda5ec0 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -181,6 +181,7 @@ struct dentry_operations { #define DCACHE_CANT_MOUNT 0x0100 +extern spinlock_t dcache_inode_lock; extern spinlock_t dcache_lock; extern seqlock_t rename_lock; -- cgit v1.1 From 949854d02455080d20cd3e1db28a3a18daf7599d Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:37 +1100 Subject: fs: Use rename lock and RCU for multi-step operations The remaining usages for dcache_lock is to allow atomic, multi-step read-side operations over the directory tree by excluding modifications to the tree. Also, to walk in the leaf->root direction in the tree where we don't have a natural d_lock ordering. This could be accomplished by taking every d_lock, but this would mean a huge number of locks and actually gets very tricky. Solve this instead by using the rename seqlock for multi-step read-side operations, retry in case of a rename so we don't walk up the wrong parent. Concurrent dentry insertions are not serialised against. Concurrent deletes are tricky when walking up the directory: our parent might have been deleted when dropping locks so also need to check and retry for that. We can also use the rename lock in cases where livelock is a worry (and it is introduced in subsequent patch). Signed-off-by: Nick Piggin --- include/linux/dcache.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index bda5ec0..c963eba 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -180,6 +180,7 @@ struct dentry_operations { #define DCACHE_FSNOTIFY_PARENT_WATCHED 0x0080 /* Parent inode is watched by some fsnotify listener */ #define DCACHE_CANT_MOUNT 0x0100 +#define DCACHE_GENOCIDE 0x0200 extern spinlock_t dcache_inode_lock; extern spinlock_t dcache_lock; -- cgit v1.1 From b5c84bf6f6fa3a7dfdcb556023a62953574b60ee Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:38 +1100 Subject: fs: dcache remove dcache_lock dcache_lock no longer protects anything. remove it. Signed-off-by: Nick Piggin --- include/linux/dcache.h | 5 ++--- include/linux/fs.h | 6 +++++- include/linux/fsnotify.h | 2 -- include/linux/fsnotify_backend.h | 11 +++++++---- include/linux/namei.h | 1 - 5 files changed, 14 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index c963eba..a2ceb94 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -183,7 +183,6 @@ struct dentry_operations { #define DCACHE_GENOCIDE 0x0200 extern spinlock_t dcache_inode_lock; -extern spinlock_t dcache_lock; extern seqlock_t rename_lock; static inline int dname_external(struct dentry *dentry) @@ -296,8 +295,8 @@ extern char *dentry_path(struct dentry *, char *, int); * destroyed when it has references. dget() should never be * called for dentries with zero reference counter. For these cases * (preferably none, functions in dcache.c are sufficient for normal - * needs and they take necessary precautions) you should hold dcache_lock - * and call dget_locked() instead of dget(). + * needs and they take necessary precautions) you should hold d_lock + * and call dget_dlock() instead of dget(). */ static inline struct dentry *dget_dlock(struct dentry *dentry) { diff --git a/include/linux/fs.h b/include/linux/fs.h index 090f0ea..296cf2f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1378,7 +1378,7 @@ struct super_block { #else struct list_head s_files; #endif - /* s_dentry_lru and s_nr_dentry_unused are protected by dcache_lock */ + /* s_dentry_lru, s_nr_dentry_unused protected by dcache.c lru locks */ struct list_head s_dentry_lru; /* unused dentry lru */ int s_nr_dentry_unused; /* # of dentry on lru */ @@ -2446,6 +2446,10 @@ static inline ino_t parent_ino(struct dentry *dentry) { ino_t res; + /* + * Don't strictly need d_lock here? If the parent ino could change + * then surely we'd have a deeper race in the caller? + */ spin_lock(&dentry->d_lock); res = dentry->d_parent->d_inode->i_ino; spin_unlock(&dentry->d_lock); diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index b10bcde..2a53f10 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -17,7 +17,6 @@ /* * fsnotify_d_instantiate - instantiate a dentry for inode - * Called with dcache_lock held. */ static inline void fsnotify_d_instantiate(struct dentry *dentry, struct inode *inode) @@ -62,7 +61,6 @@ static inline int fsnotify_perm(struct file *file, int mask) /* * fsnotify_d_move - dentry has been moved - * Called with dcache_lock and dentry->d_lock held. */ static inline void fsnotify_d_move(struct dentry *dentry) { diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 7380763..69ad89b 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -329,9 +329,15 @@ static inline void __fsnotify_update_dcache_flags(struct dentry *dentry) { struct dentry *parent; - assert_spin_locked(&dcache_lock); assert_spin_locked(&dentry->d_lock); + /* + * Serialisation of setting PARENT_WATCHED on the dentries is provided + * by d_lock. If inotify_inode_watched changes after we have taken + * d_lock, the following __fsnotify_update_child_dentry_flags call will + * find our entry, so it will spin until we complete here, and update + * us with the new state. + */ parent = dentry->d_parent; if (parent->d_inode && fsnotify_inode_watches_children(parent->d_inode)) dentry->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED; @@ -341,15 +347,12 @@ static inline void __fsnotify_update_dcache_flags(struct dentry *dentry) /* * fsnotify_d_instantiate - instantiate a dentry for inode - * Called with dcache_lock held. */ static inline void __fsnotify_d_instantiate(struct dentry *dentry, struct inode *inode) { if (!inode) return; - assert_spin_locked(&dcache_lock); - spin_lock(&dentry->d_lock); __fsnotify_update_dcache_flags(dentry); spin_unlock(&dentry->d_lock); diff --git a/include/linux/namei.h b/include/linux/namei.h index 05b441d..aec730b 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -41,7 +41,6 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; * - require a directory * - ending slashes ok even for nonexistent files * - internal "there are more path components" flag - * - locked when lookup done with dcache_lock held * - dentry cache is untrusted; force a real lookup */ #define LOOKUP_FOLLOW 1 -- cgit v1.1 From dc0474be3e27463d4d4a2793f82366eed906f223 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:43 +1100 Subject: fs: dcache rationalise dget variants dget_locked was a shortcut to avoid the lazy lru manipulation when we already held dcache_lock (lru manipulation was relatively cheap at that point). However, how that the lru lock is an innermost one, we never hold it at any caller, so the lock cost can now be avoided. We already have well working lazy dcache LRU, so it should be fine to defer LRU manipulations to scan time. Signed-off-by: Nick Piggin --- include/linux/dcache.h | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index a2ceb94..ca64868 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -287,23 +287,17 @@ extern char *dentry_path(struct dentry *, char *, int); /* Allocation counts.. */ /** - * dget, dget_locked - get a reference to a dentry + * dget, dget_dlock - get a reference to a dentry * @dentry: dentry to get a reference to * * Given a dentry or %NULL pointer increment the reference count * if appropriate and return the dentry. A dentry will not be - * destroyed when it has references. dget() should never be - * called for dentries with zero reference counter. For these cases - * (preferably none, functions in dcache.c are sufficient for normal - * needs and they take necessary precautions) you should hold d_lock - * and call dget_dlock() instead of dget(). + * destroyed when it has references. */ static inline struct dentry *dget_dlock(struct dentry *dentry) { - if (dentry) { - BUG_ON(!dentry->d_count); + if (dentry) dentry->d_count++; - } return dentry; } @@ -317,9 +311,6 @@ static inline struct dentry *dget(struct dentry *dentry) return dentry; } -extern struct dentry * dget_locked(struct dentry *); -extern struct dentry * dget_locked_dlock(struct dentry *); - extern struct dentry *dget_parent(struct dentry *dentry); /** -- cgit v1.1 From fa0d7e3de6d6fc5004ad9dea0dd6b286af8f03e9 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:49 +1100 Subject: fs: icache RCU free inodes RCU free the struct inode. This will allow: - Subsequent store-free path walking patch. The inode must be consulted for permissions when walking, so an RCU inode reference is a must. - sb_inode_list_lock to be moved inside i_lock because sb list walkers who want to take i_lock no longer need to take sb_inode_list_lock to walk the list in the first place. This will simplify and optimize locking. - Could remove some nested trylock loops in dcache code - Could potentially simplify things a bit in VM land. Do not need to take the page lock to follow page->mapping. The downsides of this is the performance cost of using RCU. In a simple creat/unlink microbenchmark, performance drops by about 10% due to inability to reuse cache-hot slab objects. As iterations increase and RCU freeing starts kicking over, this increases to about 20%. In cases where inode lifetimes are longer (ie. many inodes may be allocated during the average life span of a single inode), a lot of this cache reuse is not applicable, so the regression caused by this patch is smaller. The cache-hot regression could largely be avoided by using SLAB_DESTROY_BY_RCU, however this adds some complexity to list walking and store-free path walking, so I prefer to implement this at a later date, if it is shown to be a win in real situations. I haven't found a regression in any non-micro benchmark so I doubt it will be a problem. Signed-off-by: Nick Piggin --- include/linux/fs.h | 5 ++++- include/linux/net.h | 1 - 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 296cf2f..1ff4d0a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -737,7 +737,10 @@ struct inode { struct list_head i_wb_list; /* backing dev IO list */ struct list_head i_lru; /* inode LRU list */ struct list_head i_sb_list; - struct list_head i_dentry; + union { + struct list_head i_dentry; + struct rcu_head i_rcu; + }; unsigned long i_ino; atomic_t i_count; unsigned int i_nlink; diff --git a/include/linux/net.h b/include/linux/net.h index 16faa13..06bde49 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -120,7 +120,6 @@ enum sock_shutdown_cmd { struct socket_wq { wait_queue_head_t wait; struct fasync_struct *fasync_list; - struct rcu_head rcu; } ____cacheline_aligned_in_smp; /** -- cgit v1.1 From ff0c7d15f9787b7e8c601533c015295cc68329f8 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:50 +1100 Subject: fs: avoid inode RCU freeing for pseudo fs Pseudo filesystems that don't put inode on RCU list or reachable by rcu-walk dentries do not need to RCU free their inodes. Signed-off-by: Nick Piggin --- include/linux/fs.h | 1 + include/linux/net.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 1ff4d0a..ea202ff 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2233,6 +2233,7 @@ extern void iget_failed(struct inode *); extern void end_writeback(struct inode *); extern void __destroy_inode(struct inode *); extern struct inode *new_inode(struct super_block *); +extern void free_inode_nonrcu(struct inode *inode); extern int should_remove_suid(struct dentry *); extern int file_remove_suid(struct file *); diff --git a/include/linux/net.h b/include/linux/net.h index 06bde49..16faa13 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -120,6 +120,7 @@ enum sock_shutdown_cmd { struct socket_wq { wait_queue_head_t wait; struct fasync_struct *fasync_list; + struct rcu_head rcu; } ____cacheline_aligned_in_smp; /** -- cgit v1.1 From 3c22cd5709e8143444a6d08682a87f4c57902df3 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:51 +1100 Subject: kernel: optimise seqlock Add branch annotations for seqlock read fastpath, and introduce __read_seqcount_begin and __read_seqcount_end functions, that can avoid the smp_rmb() if used carefully. These will be used by store-free path walking algorithm performance is critical and seqlocks are in use. Signed-off-by: Nick Piggin --- include/linux/seqlock.h | 80 ++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 73 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 632205c..e98cd2e 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -107,7 +107,7 @@ static __always_inline int read_seqretry(const seqlock_t *sl, unsigned start) { smp_rmb(); - return (sl->sequence != start); + return unlikely(sl->sequence != start); } @@ -125,14 +125,25 @@ typedef struct seqcount { #define SEQCNT_ZERO { 0 } #define seqcount_init(x) do { *(x) = (seqcount_t) SEQCNT_ZERO; } while (0) -/* Start of read using pointer to a sequence counter only. */ -static inline unsigned read_seqcount_begin(const seqcount_t *s) +/** + * __read_seqcount_begin - begin a seq-read critical section (without barrier) + * @s: pointer to seqcount_t + * Returns: count to be passed to read_seqcount_retry + * + * __read_seqcount_begin is like read_seqcount_begin, but has no smp_rmb() + * barrier. Callers should ensure that smp_rmb() or equivalent ordering is + * provided before actually loading any of the variables that are to be + * protected in this critical section. + * + * Use carefully, only in critical code, and comment how the barrier is + * provided. + */ +static inline unsigned __read_seqcount_begin(const seqcount_t *s) { unsigned ret; repeat: ret = s->sequence; - smp_rmb(); if (unlikely(ret & 1)) { cpu_relax(); goto repeat; @@ -140,14 +151,56 @@ repeat: return ret; } -/* - * Test if reader processed invalid data because sequence number has changed. +/** + * read_seqcount_begin - begin a seq-read critical section + * @s: pointer to seqcount_t + * Returns: count to be passed to read_seqcount_retry + * + * read_seqcount_begin opens a read critical section of the given seqcount. + * Validity of the critical section is tested by checking read_seqcount_retry + * function. + */ +static inline unsigned read_seqcount_begin(const seqcount_t *s) +{ + unsigned ret = __read_seqcount_begin(s); + smp_rmb(); + return ret; +} + +/** + * __read_seqcount_retry - end a seq-read critical section (without barrier) + * @s: pointer to seqcount_t + * @start: count, from read_seqcount_begin + * Returns: 1 if retry is required, else 0 + * + * __read_seqcount_retry is like read_seqcount_retry, but has no smp_rmb() + * barrier. Callers should ensure that smp_rmb() or equivalent ordering is + * provided before actually loading any of the variables that are to be + * protected in this critical section. + * + * Use carefully, only in critical code, and comment how the barrier is + * provided. + */ +static inline int __read_seqcount_retry(const seqcount_t *s, unsigned start) +{ + return unlikely(s->sequence != start); +} + +/** + * read_seqcount_retry - end a seq-read critical section + * @s: pointer to seqcount_t + * @start: count, from read_seqcount_begin + * Returns: 1 if retry is required, else 0 + * + * read_seqcount_retry closes a read critical section of the given seqcount. + * If the critical section was invalid, it must be ignored (and typically + * retried). */ static inline int read_seqcount_retry(const seqcount_t *s, unsigned start) { smp_rmb(); - return s->sequence != start; + return __read_seqcount_retry(s, start); } @@ -167,6 +220,19 @@ static inline void write_seqcount_end(seqcount_t *s) s->sequence++; } +/** + * write_seqcount_barrier - invalidate in-progress read-side seq operations + * @s: pointer to seqcount_t + * + * After write_seqcount_barrier, no read-side seq operations will complete + * successfully and see data older than this. + */ +static inline void write_seqcount_barrier(seqcount_t *s) +{ + smp_wmb(); + s->sequence+=2; +} + /* * Possible sw/hw IRQ protected versions of the interfaces. */ -- cgit v1.1 From 31e6b01f4183ff419a6d1f86177cbf4662347cec Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:52 +1100 Subject: fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin --- include/linux/dcache.h | 32 +++++++++++++++++++++++++++++--- include/linux/namei.h | 15 ++++++++++----- include/linux/security.h | 8 +++++++- 3 files changed, 46 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index ca64868..c2e7390 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -5,6 +5,7 @@ #include #include #include +#include #include #include @@ -90,6 +91,7 @@ struct dentry { unsigned int d_count; /* protected by d_lock */ unsigned int d_flags; /* protected by d_lock */ spinlock_t d_lock; /* per dentry lock */ + seqcount_t d_seq; /* per dentry seqlock */ int d_mounted; struct inode *d_inode; /* Where the name belongs to - NULL is * negative */ @@ -266,9 +268,33 @@ extern void d_move(struct dentry *, struct dentry *); extern struct dentry *d_ancestor(struct dentry *, struct dentry *); /* appendix may either be NULL or be used for transname suffixes */ -extern struct dentry * d_lookup(struct dentry *, struct qstr *); -extern struct dentry * __d_lookup(struct dentry *, struct qstr *); -extern struct dentry * d_hash_and_lookup(struct dentry *, struct qstr *); +extern struct dentry *d_lookup(struct dentry *, struct qstr *); +extern struct dentry *d_hash_and_lookup(struct dentry *, struct qstr *); +extern struct dentry *__d_lookup(struct dentry *, struct qstr *); +extern struct dentry *__d_lookup_rcu(struct dentry *parent, struct qstr *name, + unsigned *seq, struct inode **inode); + +/** + * __d_rcu_to_refcount - take a refcount on dentry if sequence check is ok + * @dentry: dentry to take a ref on + * @seq: seqcount to verify against + * @Returns: 0 on failure, else 1. + * + * __d_rcu_to_refcount operates on a dentry,seq pair that was returned + * by __d_lookup_rcu, to get a reference on an rcu-walk dentry. + */ +static inline int __d_rcu_to_refcount(struct dentry *dentry, unsigned seq) +{ + int ret = 0; + + assert_spin_locked(&dentry->d_lock); + if (!read_seqcount_retry(&dentry->d_seq, seq)) { + ret = 1; + dentry->d_count++; + } + + return ret; +} /* validate "insecure" dentry pointer */ extern int d_validate(struct dentry *, struct dentry *); diff --git a/include/linux/namei.h b/include/linux/namei.h index aec730b..18d06ad 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -19,7 +19,10 @@ struct nameidata { struct path path; struct qstr last; struct path root; + struct file *file; + struct inode *inode; /* path.dentry.d_inode */ unsigned int flags; + unsigned seq; int last_type; unsigned depth; char *saved_names[MAX_NESTED_LINKS + 1]; @@ -43,11 +46,13 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; * - internal "there are more path components" flag * - dentry cache is untrusted; force a real lookup */ -#define LOOKUP_FOLLOW 1 -#define LOOKUP_DIRECTORY 2 -#define LOOKUP_CONTINUE 4 -#define LOOKUP_PARENT 16 -#define LOOKUP_REVAL 64 +#define LOOKUP_FOLLOW 0x0001 +#define LOOKUP_DIRECTORY 0x0002 +#define LOOKUP_CONTINUE 0x0004 + +#define LOOKUP_PARENT 0x0010 +#define LOOKUP_REVAL 0x0020 +#define LOOKUP_RCU 0x0040 /* * Intent data */ diff --git a/include/linux/security.h b/include/linux/security.h index fd4d55f..ed95401 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -457,7 +457,6 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * called when the actual read/write operations are performed. * @inode contains the inode structure to check. * @mask contains the permission mask. - * @nd contains the nameidata (may be NULL). * Return 0 if permission is granted. * @inode_setattr: * Check permission before setting file attributes. Note that the kernel @@ -1713,6 +1712,7 @@ int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry, int security_inode_readlink(struct dentry *dentry); int security_inode_follow_link(struct dentry *dentry, struct nameidata *nd); int security_inode_permission(struct inode *inode, int mask); +int security_inode_exec_permission(struct inode *inode, unsigned int flags); int security_inode_setattr(struct dentry *dentry, struct iattr *attr); int security_inode_getattr(struct vfsmount *mnt, struct dentry *dentry); int security_inode_setxattr(struct dentry *dentry, const char *name, @@ -2102,6 +2102,12 @@ static inline int security_inode_permission(struct inode *inode, int mask) return 0; } +static inline int security_inode_exec_permission(struct inode *inode, + unsigned int flags) +{ + return 0; +} + static inline int security_inode_setattr(struct dentry *dentry, struct iattr *attr) { -- cgit v1.1 From c28cc36469554dc55540f059fbdc7fa22a2c31fc Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:53 +1100 Subject: fs: fs_struct use seqlock Use a seqlock in the fs_struct to enable us to take an atomic copy of the complete cwd and root paths. Use this in the RCU lookup path to avoid a thread-shared spinlock in RCU lookup operations. Multi-threaded apps may now perform path lookups with scalability matching multi-process apps. Operations such as stat(2) become very scalable for multi-threaded workload. Signed-off-by: Nick Piggin --- include/linux/fs_struct.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index a42b5bf..003dc0f 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -2,10 +2,13 @@ #define _LINUX_FS_STRUCT_H #include +#include +#include struct fs_struct { int users; spinlock_t lock; + seqcount_t seq; int umask; int in_exec; struct path root, pwd; -- cgit v1.1 From 5f57cbcc02cf18f6b22ef4066bb10afeb8f930ff Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:54 +1100 Subject: fs: dcache remove d_mounted Rather than keep a d_mounted count in the dentry, set a dentry flag instead. The flag can be cleared by checking the hash table to see if there are any mounts left, which is not time critical because it is performed at detach time. The mounted state of a dentry is only used to speculatively take a look in the mount hash table if it is set -- before following the mount, vfsmount lock is taken and mount re-checked without races. This saves 4 bytes on 32-bit, nothing on 64-bit but it does provide a hole I might use later (and some configs have larger than 32-bit spinlocks which might make use of the hole). Autofs4 conversion and changelog by Ian Kent : In autofs4, when expring direct (or offset) mounts we need to ensure that we block user path walks into the autofs mount, which is covered by another mount. To do this we clear the mounted status so that follows stop before walking into the mount and are essentially blocked until the expire is completed. The automount daemon still finds the correct dentry for the umount due to the follow mount logic in fs/autofs4/root.c:autofs4_follow_link(), which is set as an inode operation for direct and offset mounts only and is called following the lookup that stopped at the covered mount. At the end of the expire the covering mount probably has gone away so the mounted status need not be restored. But we need to check this and only restore the mounted status if the expire failed. XXX: autofs may not work right if we have other mounts go over the top of it? Signed-off-by: Nick Piggin --- include/linux/dcache.h | 42 +++++++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index c2e7390..e441469 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -92,7 +92,6 @@ struct dentry { unsigned int d_flags; /* protected by d_lock */ spinlock_t d_lock; /* per dentry lock */ seqcount_t d_seq; /* per dentry seqlock */ - int d_mounted; struct inode *d_inode; /* Where the name belongs to - NULL is * negative */ /* @@ -156,33 +155,34 @@ struct dentry_operations { /* d_flags entries */ #define DCACHE_AUTOFS_PENDING 0x0001 /* autofs: "under construction" */ -#define DCACHE_NFSFS_RENAMED 0x0002 /* this dentry has been "silly - * renamed" and has to be - * deleted on the last dput() - */ -#define DCACHE_DISCONNECTED 0x0004 - /* This dentry is possibly not currently connected to the dcache tree, - * in which case its parent will either be itself, or will have this - * flag as well. nfsd will not use a dentry with this bit set, but will - * first endeavour to clear the bit either by discovering that it is - * connected, or by performing lookup operations. Any filesystem which - * supports nfsd_operations MUST have a lookup function which, if it finds - * a directory inode with a DCACHE_DISCONNECTED dentry, will d_move - * that dentry into place and return that dentry rather than the passed one, - * typically using d_splice_alias. - */ +#define DCACHE_NFSFS_RENAMED 0x0002 + /* this dentry has been "silly renamed" and has to be deleted on the last + * dput() */ + +#define DCACHE_DISCONNECTED 0x0004 + /* This dentry is possibly not currently connected to the dcache tree, in + * which case its parent will either be itself, or will have this flag as + * well. nfsd will not use a dentry with this bit set, but will first + * endeavour to clear the bit either by discovering that it is connected, + * or by performing lookup operations. Any filesystem which supports + * nfsd_operations MUST have a lookup function which, if it finds a + * directory inode with a DCACHE_DISCONNECTED dentry, will d_move that + * dentry into place and return that dentry rather than the passed one, + * typically using d_splice_alias. */ #define DCACHE_REFERENCED 0x0008 /* Recently used, don't discard. */ #define DCACHE_UNHASHED 0x0010 - -#define DCACHE_INOTIFY_PARENT_WATCHED 0x0020 /* Parent inode is watched by inotify */ +#define DCACHE_INOTIFY_PARENT_WATCHED 0x0020 + /* Parent inode is watched by inotify */ #define DCACHE_COOKIE 0x0040 /* For use by dcookie subsystem */ - -#define DCACHE_FSNOTIFY_PARENT_WATCHED 0x0080 /* Parent inode is watched by some fsnotify listener */ +#define DCACHE_FSNOTIFY_PARENT_WATCHED 0x0080 + /* Parent inode is watched by some fsnotify listener */ #define DCACHE_CANT_MOUNT 0x0100 #define DCACHE_GENOCIDE 0x0200 +#define DCACHE_MOUNTED 0x0400 /* is a mountpoint */ + extern spinlock_t dcache_inode_lock; extern seqlock_t rename_lock; @@ -372,7 +372,7 @@ extern void dput(struct dentry *); static inline int d_mountpoint(struct dentry *dentry) { - return dentry->d_mounted; + return dentry->d_flags & DCACHE_MOUNTED; } extern struct vfsmount *lookup_mnt(struct path *); -- cgit v1.1 From fb045adb99d9b7c562dc7fef834857f78249daa1 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:55 +1100 Subject: fs: dcache reduce branches in lookup path Reduce some branches and memory accesses in dcache lookup by adding dentry flags to indicate common d_ops are set, rather than having to check them. This saves a pointer memory access (dentry->d_op) in common path lookup situations, and saves another pointer load and branch in cases where we have d_op but not the particular operation. Patched with: git grep -E '[.>]([[:space:]])*d_op([[:space:]])*=' | xargs sed -e 's/\([^\t ]*\)->d_op = \(.*\);/d_set_d_op(\1, \2);/' -e 's/\([^\t ]*\)\.d_op = \(.*\);/d_set_d_op(\&\1, \2);/' -i Signed-off-by: Nick Piggin --- include/linux/dcache.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index e441469..f4b40a7 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -183,6 +183,11 @@ struct dentry_operations { #define DCACHE_GENOCIDE 0x0200 #define DCACHE_MOUNTED 0x0400 /* is a mountpoint */ +#define DCACHE_OP_HASH 0x1000 +#define DCACHE_OP_COMPARE 0x2000 +#define DCACHE_OP_REVALIDATE 0x4000 +#define DCACHE_OP_DELETE 0x8000 + extern spinlock_t dcache_inode_lock; extern seqlock_t rename_lock; @@ -201,6 +206,7 @@ extern struct dentry * d_materialise_unique(struct dentry *, struct inode *); extern void __d_drop(struct dentry *dentry); extern void d_drop(struct dentry *dentry); extern void d_delete(struct dentry *); +extern void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op); /* allocate/de-allocate */ extern struct dentry * d_alloc(struct dentry *, const struct qstr *); -- cgit v1.1 From 44a7d7a878c9cbb74f236ea755b25b6b2e26a9a9 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:56 +1100 Subject: fs: cache optimise dentry and inode for rcu-walk Put dentry and inode fields into top of data structure. This allows RCU path traversal to perform an RCU dentry lookup in a path walk by touching only the first 56 bytes of the dentry. We also fit in 8 bytes of inline name in the first 64 bytes, so for short names, only 64 bytes needs to be touched to perform the lookup. We should get rid of the hash->prev pointer from the first 64 bytes, and fit 16 bytes of name in there, which will take care of 81% rather than 32% of the kernel tree. inode is also rearranged so that RCU lookup will only touch a single cacheline in the inode, plus one in the i_ops structure. This is important for directory component lookups in RCU path walking. In the kernel source, directory names average is around 6 chars, so this works. When we reach the last element of the lookup, we need to lock it and take its refcount which requires another cacheline access. Align dentry and inode operations structs, so members will be at predictable offsets and we can group common operations into head of structure. Signed-off-by: Nick Piggin --- include/linux/dcache.h | 36 +++++++++++++++++++----------------- include/linux/fs.h | 42 +++++++++++++++++++++++------------------- 2 files changed, 42 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index f4b40a7..b1aeda0 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -82,25 +82,33 @@ full_name_hash(const unsigned char *name, unsigned int len) * large memory footprint increase). */ #ifdef CONFIG_64BIT -#define DNAME_INLINE_LEN_MIN 32 /* 192 bytes */ +# define DNAME_INLINE_LEN 32 /* 192 bytes */ #else -#define DNAME_INLINE_LEN_MIN 40 /* 128 bytes */ +# ifdef CONFIG_SMP +# define DNAME_INLINE_LEN 36 /* 128 bytes */ +# else +# define DNAME_INLINE_LEN 40 /* 128 bytes */ +# endif #endif struct dentry { - unsigned int d_count; /* protected by d_lock */ + /* RCU lookup touched fields */ unsigned int d_flags; /* protected by d_lock */ - spinlock_t d_lock; /* per dentry lock */ seqcount_t d_seq; /* per dentry seqlock */ - struct inode *d_inode; /* Where the name belongs to - NULL is - * negative */ - /* - * The next three fields are touched by __d_lookup. Place them here - * so they all fit in a cache line. - */ struct hlist_node d_hash; /* lookup hash list */ struct dentry *d_parent; /* parent directory */ struct qstr d_name; + struct inode *d_inode; /* Where the name belongs to - NULL is + * negative */ + unsigned char d_iname[DNAME_INLINE_LEN]; /* small names */ + + /* Ref lookup also touches following */ + unsigned int d_count; /* protected by d_lock */ + spinlock_t d_lock; /* per dentry lock */ + const struct dentry_operations *d_op; + struct super_block *d_sb; /* The root of the dentry tree */ + unsigned long d_time; /* used by d_revalidate */ + void *d_fsdata; /* fs-specific data */ struct list_head d_lru; /* LRU list */ /* @@ -112,12 +120,6 @@ struct dentry { } d_u; struct list_head d_subdirs; /* our children */ struct list_head d_alias; /* inode alias list */ - unsigned long d_time; /* used by d_revalidate */ - const struct dentry_operations *d_op; - struct super_block *d_sb; /* The root of the dentry tree */ - void *d_fsdata; /* fs-specific data */ - - unsigned char d_iname[DNAME_INLINE_LEN_MIN]; /* small names */ }; /* @@ -143,7 +145,7 @@ struct dentry_operations { void (*d_release)(struct dentry *); void (*d_iput)(struct dentry *, struct inode *); char *(*d_dname)(struct dentry *, char *, int); -}; +} ____cacheline_aligned; /* * Locking rules for dentry_operations callbacks are to be found in diff --git a/include/linux/fs.h b/include/linux/fs.h index ea202ff..a04aa96 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -733,6 +733,20 @@ struct posix_acl; #define ACL_NOT_CACHED ((void *)(-1)) struct inode { + /* RCU path lookup touches following: */ + umode_t i_mode; + uid_t i_uid; + gid_t i_gid; + const struct inode_operations *i_op; + struct super_block *i_sb; + + spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ + unsigned int i_flags; + struct mutex i_mutex; + + unsigned long i_state; + unsigned long dirtied_when; /* jiffies of first dirtying */ + struct hlist_node i_hash; struct list_head i_wb_list; /* backing dev IO list */ struct list_head i_lru; /* inode LRU list */ @@ -744,8 +758,6 @@ struct inode { unsigned long i_ino; atomic_t i_count; unsigned int i_nlink; - uid_t i_uid; - gid_t i_gid; dev_t i_rdev; unsigned int i_blkbits; u64 i_version; @@ -758,13 +770,8 @@ struct inode { struct timespec i_ctime; blkcnt_t i_blocks; unsigned short i_bytes; - umode_t i_mode; - spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ - struct mutex i_mutex; struct rw_semaphore i_alloc_sem; - const struct inode_operations *i_op; const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ - struct super_block *i_sb; struct file_lock *i_flock; struct address_space *i_mapping; struct address_space i_data; @@ -785,11 +792,6 @@ struct inode { struct hlist_head i_fsnotify_marks; #endif - unsigned long i_state; - unsigned long dirtied_when; /* jiffies of first dirtying */ - - unsigned int i_flags; - #ifdef CONFIG_IMA /* protected by i_lock */ unsigned int i_readcount; /* struct files open RO */ @@ -1549,8 +1551,15 @@ struct file_operations { }; struct inode_operations { - int (*create) (struct inode *,struct dentry *,int, struct nameidata *); struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *); + void * (*follow_link) (struct dentry *, struct nameidata *); + int (*permission) (struct inode *, int); + int (*check_acl)(struct inode *, int); + + int (*readlink) (struct dentry *, char __user *,int); + void (*put_link) (struct dentry *, struct nameidata *, void *); + + int (*create) (struct inode *,struct dentry *,int, struct nameidata *); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct inode *,struct dentry *,const char *); @@ -1559,12 +1568,7 @@ struct inode_operations { int (*mknod) (struct inode *,struct dentry *,int,dev_t); int (*rename) (struct inode *, struct dentry *, struct inode *, struct dentry *); - int (*readlink) (struct dentry *, char __user *,int); - void * (*follow_link) (struct dentry *, struct nameidata *); - void (*put_link) (struct dentry *, struct nameidata *, void *); void (*truncate) (struct inode *); - int (*permission) (struct inode *, int); - int (*check_acl)(struct inode *, int); int (*setattr) (struct dentry *, struct iattr *); int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *); int (*setxattr) (struct dentry *, const char *,const void *,size_t,int); @@ -1576,7 +1580,7 @@ struct inode_operations { loff_t len); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); -}; +} ____cacheline_aligned; struct seq_file; -- cgit v1.1 From 34286d6662308d82aed891852d04c7c3a2649b16 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:57 +1100 Subject: fs: rcu-walk aware d_revalidate method Require filesystems be aware of .d_revalidate being called in rcu-walk mode (nd->flags & LOOKUP_RCU). For now do a simple push down, returning -ECHILD from all implementations. Signed-off-by: Nick Piggin --- include/linux/dcache.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index b1aeda0..8b2064d 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -190,7 +190,6 @@ struct dentry_operations { #define DCACHE_OP_REVALIDATE 0x4000 #define DCACHE_OP_DELETE 0x8000 - extern spinlock_t dcache_inode_lock; extern seqlock_t rename_lock; -- cgit v1.1 From b74c79e99389cd79b31fcc08f82c24e492e63c7e Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:58 +1100 Subject: fs: provide rcu-walk aware permission i_ops Signed-off-by: Nick Piggin --- include/linux/coda_linux.h | 2 +- include/linux/fs.h | 10 ++++++---- include/linux/generic_acl.h | 2 +- include/linux/nfs_fs.h | 2 +- include/linux/reiserfs_xattr.h | 2 +- 5 files changed, 10 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/coda_linux.h b/include/linux/coda_linux.h index 2e914d0..4ccc59c 100644 --- a/include/linux/coda_linux.h +++ b/include/linux/coda_linux.h @@ -37,7 +37,7 @@ extern const struct file_operations coda_ioctl_operations; /* operations shared over more than one file */ int coda_open(struct inode *i, struct file *f); int coda_release(struct inode *i, struct file *f); -int coda_permission(struct inode *inode, int mask); +int coda_permission(struct inode *inode, int mask, unsigned int flags); int coda_revalidate_inode(struct dentry *); int coda_getattr(struct vfsmount *, struct dentry *, struct kstat *); int coda_setattr(struct dentry *, struct iattr *); diff --git a/include/linux/fs.h b/include/linux/fs.h index a04aa96..d5a4d42 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1550,11 +1550,13 @@ struct file_operations { int (*setlease)(struct file *, long, struct file_lock **); }; +#define IPERM_FLAG_RCU 0x0001 + struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *); void * (*follow_link) (struct dentry *, struct nameidata *); - int (*permission) (struct inode *, int); - int (*check_acl)(struct inode *, int); + int (*permission) (struct inode *, int, unsigned int); + int (*check_acl)(struct inode *, int, unsigned int); int (*readlink) (struct dentry *, char __user *,int); void (*put_link) (struct dentry *, struct nameidata *, void *); @@ -2165,8 +2167,8 @@ extern sector_t bmap(struct inode *, sector_t); #endif extern int notify_change(struct dentry *, struct iattr *); extern int inode_permission(struct inode *, int); -extern int generic_permission(struct inode *, int, - int (*check_acl)(struct inode *, int)); +extern int generic_permission(struct inode *, int, unsigned int, + int (*check_acl)(struct inode *, int, unsigned int)); static inline bool execute_ok(struct inode *inode) { diff --git a/include/linux/generic_acl.h b/include/linux/generic_acl.h index 574bea4..0437e37 100644 --- a/include/linux/generic_acl.h +++ b/include/linux/generic_acl.h @@ -10,6 +10,6 @@ extern const struct xattr_handler generic_acl_default_handler; int generic_acl_init(struct inode *, struct inode *); int generic_acl_chmod(struct inode *); -int generic_check_acl(struct inode *inode, int mask); +int generic_check_acl(struct inode *inode, int mask, unsigned int flags); #endif /* LINUX_GENERIC_ACL_H */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 29d504d..0779bb8 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -351,7 +351,7 @@ extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *); extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_getattr(struct vfsmount *, struct dentry *, struct kstat *); -extern int nfs_permission(struct inode *, int); +extern int nfs_permission(struct inode *, int, unsigned int); extern int nfs_open(struct inode *, struct file *); extern int nfs_release(struct inode *, struct file *); extern int nfs_attribute_timeout(struct inode *inode); diff --git a/include/linux/reiserfs_xattr.h b/include/linux/reiserfs_xattr.h index b2cf208..3b94c91 100644 --- a/include/linux/reiserfs_xattr.h +++ b/include/linux/reiserfs_xattr.h @@ -41,7 +41,7 @@ int reiserfs_xattr_init(struct super_block *sb, int mount_flags); int reiserfs_lookup_privroot(struct super_block *sb); int reiserfs_delete_xattrs(struct inode *inode); int reiserfs_chown_xattrs(struct inode *inode, struct iattr *attrs); -int reiserfs_permission(struct inode *inode, int mask); +int reiserfs_permission(struct inode *inode, int mask, unsigned int flags); #ifdef CONFIG_REISERFS_FS_XATTR #define has_xattr_dir(inode) (REISERFS_I(inode)->i_flags & i_has_xattr_dir) -- cgit v1.1 From 1e1743ebe35ec7e3c1fa732408358fbc614cbbe5 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:59 +1100 Subject: fs: provide simple rcu-walk generic_check_acl implementation This simple implementation just checks for no ACLs on the inode, and if so, then the rcu-walk may proceed, otherwise fail it. This could easily be extended to put acls under RCU and check them under seqlock, if need be. But this implementation is enough to show the rcu-walk aware permissions code for path lookups is working, and will handle cases where there are no ACLs or ACLs in just the final element. This patch implicity converts tmpfs to rcu-aware permission check. Subsequent patches onvert ext*, xfs, and, btrfs. Each of these uses acl/permission code in a different way, so convert them all to provide templates and proof of concept. Signed-off-by: Nick Piggin --- include/linux/posix_acl.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 6760816..d68283a 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -108,6 +108,25 @@ static inline struct posix_acl *get_cached_acl(struct inode *inode, int type) return acl; } +static inline int negative_cached_acl(struct inode *inode, int type) +{ + struct posix_acl **p, *acl; + switch (type) { + case ACL_TYPE_ACCESS: + p = &inode->i_acl; + break; + case ACL_TYPE_DEFAULT: + p = &inode->i_default_acl; + break; + default: + BUG(); + } + acl = ACCESS_ONCE(*p); + if (acl) + return 0; + return 1; +} + static inline void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl) -- cgit v1.1 From 4e35e6070b1ceed89c3bba2af4216c286fb1dafd Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:50:03 +1100 Subject: kernel: add bl_list Introduce a type of hlist that can support the use of the lowest bit in the hlist_head. This will be subsequently used to implement per-bucket bit spinlock for inode and dentry hashes, and may be useful in other cases such as network hashes. Reviewed-by: Paul E. McKenney Signed-off-by: Nick Piggin --- include/linux/list_bl.h | 144 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/rculist_bl.h | 127 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 271 insertions(+) create mode 100644 include/linux/list_bl.h create mode 100644 include/linux/rculist_bl.h (limited to 'include') diff --git a/include/linux/list_bl.h b/include/linux/list_bl.h new file mode 100644 index 0000000..9ee97e7 --- /dev/null +++ b/include/linux/list_bl.h @@ -0,0 +1,144 @@ +#ifndef _LINUX_LIST_BL_H +#define _LINUX_LIST_BL_H + +#include + +/* + * Special version of lists, where head of the list has a lock in the lowest + * bit. This is useful for scalable hash tables without increasing memory + * footprint overhead. + * + * For modification operations, the 0 bit of hlist_bl_head->first + * pointer must be set. + * + * With some small modifications, this can easily be adapted to store several + * arbitrary bits (not just a single lock bit), if the need arises to store + * some fast and compact auxiliary data. + */ + +#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) +#define LIST_BL_LOCKMASK 1UL +#else +#define LIST_BL_LOCKMASK 0UL +#endif + +#ifdef CONFIG_DEBUG_LIST +#define LIST_BL_BUG_ON(x) BUG_ON(x) +#else +#define LIST_BL_BUG_ON(x) +#endif + + +struct hlist_bl_head { + struct hlist_bl_node *first; +}; + +struct hlist_bl_node { + struct hlist_bl_node *next, **pprev; +}; +#define INIT_HLIST_BL_HEAD(ptr) \ + ((ptr)->first = NULL) + +static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h) +{ + h->next = NULL; + h->pprev = NULL; +} + +#define hlist_bl_entry(ptr, type, member) container_of(ptr,type,member) + +static inline int hlist_bl_unhashed(const struct hlist_bl_node *h) +{ + return !h->pprev; +} + +static inline struct hlist_bl_node *hlist_bl_first(struct hlist_bl_head *h) +{ + return (struct hlist_bl_node *) + ((unsigned long)h->first & ~LIST_BL_LOCKMASK); +} + +static inline void hlist_bl_set_first(struct hlist_bl_head *h, + struct hlist_bl_node *n) +{ + LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); + LIST_BL_BUG_ON(!((unsigned long)h->first & LIST_BL_LOCKMASK)); + h->first = (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK); +} + +static inline int hlist_bl_empty(const struct hlist_bl_head *h) +{ + return !((unsigned long)h->first & ~LIST_BL_LOCKMASK); +} + +static inline void hlist_bl_add_head(struct hlist_bl_node *n, + struct hlist_bl_head *h) +{ + struct hlist_bl_node *first = hlist_bl_first(h); + + n->next = first; + if (first) + first->pprev = &n->next; + n->pprev = &h->first; + hlist_bl_set_first(h, n); +} + +static inline void __hlist_bl_del(struct hlist_bl_node *n) +{ + struct hlist_bl_node *next = n->next; + struct hlist_bl_node **pprev = n->pprev; + + LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); + + /* pprev may be `first`, so be careful not to lose the lock bit */ + *pprev = (struct hlist_bl_node *) + ((unsigned long)next | + ((unsigned long)*pprev & LIST_BL_LOCKMASK)); + if (next) + next->pprev = pprev; +} + +static inline void hlist_bl_del(struct hlist_bl_node *n) +{ + __hlist_bl_del(n); + n->next = LIST_POISON1; + n->pprev = LIST_POISON2; +} + +static inline void hlist_bl_del_init(struct hlist_bl_node *n) +{ + if (!hlist_bl_unhashed(n)) { + __hlist_bl_del(n); + INIT_HLIST_BL_NODE(n); + } +} + +/** + * hlist_bl_for_each_entry - iterate over list of given type + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct hlist_node to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the hlist_node within the struct. + * + */ +#define hlist_bl_for_each_entry(tpos, pos, head, member) \ + for (pos = hlist_bl_first(head); \ + pos && \ + ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \ + pos = pos->next) + +/** + * hlist_bl_for_each_entry_safe - iterate over list of given type safe against removal of list entry + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct hlist_node to use as a loop cursor. + * @n: another &struct hlist_node to use as temporary storage + * @head: the head for your list. + * @member: the name of the hlist_node within the struct. + */ +#define hlist_bl_for_each_entry_safe(tpos, pos, n, head, member) \ + for (pos = hlist_bl_first(head); \ + pos && ({ n = pos->next; 1; }) && \ + ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \ + pos = n) + +#endif diff --git a/include/linux/rculist_bl.h b/include/linux/rculist_bl.h new file mode 100644 index 0000000..b872b49 --- /dev/null +++ b/include/linux/rculist_bl.h @@ -0,0 +1,127 @@ +#ifndef _LINUX_RCULIST_BL_H +#define _LINUX_RCULIST_BL_H + +/* + * RCU-protected bl list version. See include/linux/list_bl.h. + */ +#include +#include + +static inline void hlist_bl_set_first_rcu(struct hlist_bl_head *h, + struct hlist_bl_node *n) +{ + LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); + LIST_BL_BUG_ON(!((unsigned long)h->first & LIST_BL_LOCKMASK)); + rcu_assign_pointer(h->first, + (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK)); +} + +static inline struct hlist_bl_node *hlist_bl_first_rcu(struct hlist_bl_head *h) +{ + return (struct hlist_bl_node *) + ((unsigned long)rcu_dereference(h->first) & ~LIST_BL_LOCKMASK); +} + +/** + * hlist_bl_del_init_rcu - deletes entry from hash list with re-initialization + * @n: the element to delete from the hash list. + * + * Note: hlist_bl_unhashed() on the node returns true after this. It is + * useful for RCU based read lockfree traversal if the writer side + * must know if the list entry is still hashed or already unhashed. + * + * In particular, it means that we can not poison the forward pointers + * that may still be used for walking the hash list and we can only + * zero the pprev pointer so list_unhashed() will return true after + * this. + * + * The caller must take whatever precautions are necessary (such as + * holding appropriate locks) to avoid racing with another + * list-mutation primitive, such as hlist_bl_add_head_rcu() or + * hlist_bl_del_rcu(), running on this same list. However, it is + * perfectly legal to run concurrently with the _rcu list-traversal + * primitives, such as hlist_bl_for_each_entry_rcu(). + */ +static inline void hlist_bl_del_init_rcu(struct hlist_bl_node *n) +{ + if (!hlist_bl_unhashed(n)) { + __hlist_bl_del(n); + n->pprev = NULL; + } +} + +/** + * hlist_bl_del_rcu - deletes entry from hash list without re-initialization + * @n: the element to delete from the hash list. + * + * Note: hlist_bl_unhashed() on entry does not return true after this, + * the entry is in an undefined state. It is useful for RCU based + * lockfree traversal. + * + * In particular, it means that we can not poison the forward + * pointers that may still be used for walking the hash list. + * + * The caller must take whatever precautions are necessary + * (such as holding appropriate locks) to avoid racing + * with another list-mutation primitive, such as hlist_bl_add_head_rcu() + * or hlist_bl_del_rcu(), running on this same list. + * However, it is perfectly legal to run concurrently with + * the _rcu list-traversal primitives, such as + * hlist_bl_for_each_entry(). + */ +static inline void hlist_bl_del_rcu(struct hlist_bl_node *n) +{ + __hlist_bl_del(n); + n->pprev = LIST_POISON2; +} + +/** + * hlist_bl_add_head_rcu + * @n: the element to add to the hash list. + * @h: the list to add to. + * + * Description: + * Adds the specified element to the specified hlist_bl, + * while permitting racing traversals. + * + * The caller must take whatever precautions are necessary + * (such as holding appropriate locks) to avoid racing + * with another list-mutation primitive, such as hlist_bl_add_head_rcu() + * or hlist_bl_del_rcu(), running on this same list. + * However, it is perfectly legal to run concurrently with + * the _rcu list-traversal primitives, such as + * hlist_bl_for_each_entry_rcu(), used to prevent memory-consistency + * problems on Alpha CPUs. Regardless of the type of CPU, the + * list-traversal primitive must be guarded by rcu_read_lock(). + */ +static inline void hlist_bl_add_head_rcu(struct hlist_bl_node *n, + struct hlist_bl_head *h) +{ + struct hlist_bl_node *first; + + /* don't need hlist_bl_first_rcu because we're under lock */ + first = hlist_bl_first(h); + + n->next = first; + if (first) + first->pprev = &n->next; + n->pprev = &h->first; + + /* need _rcu because we can have concurrent lock free readers */ + hlist_bl_set_first_rcu(h, n); +} +/** + * hlist_bl_for_each_entry_rcu - iterate over rcu list of given type + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct hlist_bl_node to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the hlist_bl_node within the struct. + * + */ +#define hlist_bl_for_each_entry_rcu(tpos, pos, head, member) \ + for (pos = hlist_bl_first_rcu(head); \ + pos && \ + ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1; }); \ + pos = rcu_dereference_raw(pos->next)) + +#endif -- cgit v1.1 From 626d607435617cc0f033522083e2bb195b81813c Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:50:04 +1100 Subject: bit_spinlock: add required includes Signed-off-by: Nick Piggin --- include/linux/bit_spinlock.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/bit_spinlock.h b/include/linux/bit_spinlock.h index 7113a32..e612575 100644 --- a/include/linux/bit_spinlock.h +++ b/include/linux/bit_spinlock.h @@ -1,6 +1,10 @@ #ifndef __LINUX_BIT_SPINLOCK_H #define __LINUX_BIT_SPINLOCK_H +#include +#include +#include + /* * bit-based spin_lock() * -- cgit v1.1 From ceb5bdc2d246f6d81cf61ed70f325308a11821d2 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:50:05 +1100 Subject: fs: dcache per-bucket dcache hash locking We can turn the dcache hash locking from a global dcache_hash_lock into per-bucket locking. Signed-off-by: Nick Piggin --- include/linux/dcache.h | 3 ++- include/linux/fs.h | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 8b2064d..5f0392e 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -4,6 +4,7 @@ #include #include #include +#include #include #include #include @@ -95,7 +96,7 @@ struct dentry { /* RCU lookup touched fields */ unsigned int d_flags; /* protected by d_lock */ seqcount_t d_seq; /* per dentry seqlock */ - struct hlist_node d_hash; /* lookup hash list */ + struct hlist_bl_node d_hash; /* lookup hash list */ struct dentry *d_parent; /* parent directory */ struct qstr d_name; struct inode *d_inode; /* Where the name belongs to - NULL is diff --git a/include/linux/fs.h b/include/linux/fs.h index d5a4d42..baf3e55 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -392,6 +392,7 @@ struct inodes_stat_t { #include #include #include +#include #include #include @@ -1377,7 +1378,7 @@ struct super_block { const struct xattr_handler **s_xattr; struct list_head s_inodes; /* all inodes */ - struct hlist_head s_anon; /* anonymous dentries for (nfs) exporting */ + struct hlist_bl_head s_anon; /* anonymous dentries for (nfs) exporting */ #ifdef CONFIG_SMP struct list_head __percpu *s_files; #else -- cgit v1.1 From 873feea09ebc980cbd3631b767356ce1eee65ec1 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:50:06 +1100 Subject: fs: dcache per-inode inode alias locking dcache_inode_lock can be replaced with per-inode locking. Use existing inode->i_lock for this. This is slightly non-trivial because we sometimes need to find the inode from the dentry, which requires d_inode to be stabilised (either with refcount or d_lock). Signed-off-by: Nick Piggin --- include/linux/dcache.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 5f0392e..d719e4d 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -191,7 +191,6 @@ struct dentry_operations { #define DCACHE_OP_REVALIDATE 0x4000 #define DCACHE_OP_DELETE 0x8000 -extern spinlock_t dcache_inode_lock; extern seqlock_t rename_lock; static inline int dname_external(struct dentry *dentry) -- cgit v1.1 From 4b936885ab04dc6e0bb0ef35e0e23c1a7364d9e5 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:50:07 +1100 Subject: fs: improve scalability of pseudo filesystems Regardless of how much we possibly try to scale dcache, there is likely always going to be some fundamental contention when adding or removing children under the same parent. Pseudo filesystems do not seem need to have connected dentries because by definition they are disconnected. Signed-off-by: Nick Piggin --- include/linux/dcache.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index d719e4d..c0a2ca9 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -211,6 +211,7 @@ extern void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op /* allocate/de-allocate */ extern struct dentry * d_alloc(struct dentry *, const struct qstr *); +extern struct dentry * d_alloc_pseudo(struct super_block *, const struct qstr *); extern struct dentry * d_splice_alias(struct inode *, struct dentry *); extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *); extern struct dentry * d_obtain_alias(struct inode *); -- cgit v1.1 From 9d55c369bb5e695e629bc35cba2ef607755b3bee Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:50:09 +1100 Subject: fs: implement faster dentry memcmp The standard memcmp function on a Westmere system shows up hot in profiles in the `git diff` workload (both parallel and single threaded), and it is likely due to the costs associated with trapping into microcode, and little opportunity to improve memory access (dentry name is not likely to take up more than a cacheline). So replace it with an open-coded byte comparison. This increases code size by 8 bytes in the critical __d_lookup_rcu function, but the speedup is huge, averaging 10 runs of each: git diff st user sys elapsed CPU before 1.15 2.57 3.82 97.1 after 1.14 2.35 3.61 96.8 git diff mt user sys elapsed CPU before 1.27 3.85 1.46 349 after 1.26 3.54 1.43 333 Elapsed time for single threaded git diff at 95.0% confidence: -0.21 +/- 0.01 -5.45% +/- 0.24% It's -0.66% +/- 0.06% elapsed time on my Opteron, so rep cmp costs on the fam10h seem to be relatively smaller, but there is still a win. Signed-off-by: Nick Piggin --- include/linux/dcache.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index c0a2ca9..bd07758 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -47,6 +47,27 @@ struct dentry_stat_t { }; extern struct dentry_stat_t dentry_stat; +/* + * Compare 2 name strings, return 0 if they match, otherwise non-zero. + * The strings are both count bytes long, and count is non-zero. + */ +static inline int dentry_cmp(const unsigned char *cs, size_t scount, + const unsigned char *ct, size_t tcount) +{ + int ret; + if (scount != tcount) + return 1; + do { + ret = (*cs != *ct); + if (ret) + break; + cs++; + ct++; + tcount--; + } while (tcount); + return ret; +} + /* Name hashing routines. Initial hash value */ /* Hash courtesy of the R5 hash in reiserfs modulo sign bits */ #define init_name_hash() 0 -- cgit v1.1 From b3e19d924b6eaf2ca7d22cba99a517c5171007b6 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:50:11 +1100 Subject: fs: scale mntget/mntput The problem that this patch aims to fix is vfsmount refcounting scalability. We need to take a reference on the vfsmount for every successful path lookup, which often go to the same mount point. The fundamental difficulty is that a "simple" reference count can never be made scalable, because any time a reference is dropped, we must check whether that was the last reference. To do that requires communication with all other CPUs that may have taken a reference count. We can make refcounts more scalable in a couple of ways, involving keeping distributed counters, and checking for the global-zero condition less frequently. - check the global sum once every interval (this will delay zero detection for some interval, so it's probably a showstopper for vfsmounts). - keep a local count and only taking the global sum when local reaches 0 (this is difficult for vfsmounts, because we can't hold preempt off for the life of a reference, so a counter would need to be per-thread or tied strongly to a particular CPU which requires more locking). - keep a local difference of increments and decrements, which allows us to sum the total difference and hence find the refcount when summing all CPUs. Then, keep a single integer "long" refcount for slow and long lasting references, and only take the global sum of local counters when the long refcount is 0. This last scheme is what I implemented here. Attached mounts and process root and working directory references are "long" references, and everything else is a short reference. This allows scalable vfsmount references during path walking over mounted subtrees and unattached (lazy umounted) mounts with processes still running in them. This results in one fewer atomic op in the fastpath: mntget is now just a per-CPU inc, rather than an atomic inc; and mntput just requires a spinlock and non-atomic decrement in the common case. However code is otherwise bigger and heavier, so single threaded performance is basically a wash. Signed-off-by: Nick Piggin --- include/linux/mount.h | 53 +++++++++++++++++---------------------------------- include/linux/path.h | 2 ++ 2 files changed, 19 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/include/linux/mount.h b/include/linux/mount.h index 5e7a594..1869ea2 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -13,6 +13,7 @@ #include #include #include +#include #include struct super_block; @@ -46,12 +47,24 @@ struct mnt_namespace; #define MNT_INTERNAL 0x4000 +struct mnt_pcp { + int mnt_count; + int mnt_writers; +}; + struct vfsmount { struct list_head mnt_hash; struct vfsmount *mnt_parent; /* fs we are mounted on */ struct dentry *mnt_mountpoint; /* dentry of mountpoint */ struct dentry *mnt_root; /* root of the mounted tree */ struct super_block *mnt_sb; /* pointer to superblock */ +#ifdef CONFIG_SMP + struct mnt_pcp __percpu *mnt_pcp; + atomic_t mnt_longrefs; +#else + int mnt_count; + int mnt_writers; +#endif struct list_head mnt_mounts; /* list of children, anchored here */ struct list_head mnt_child; /* and going through their mnt_child */ int mnt_flags; @@ -70,57 +83,25 @@ struct vfsmount { struct mnt_namespace *mnt_ns; /* containing namespace */ int mnt_id; /* mount identifier */ int mnt_group_id; /* peer group identifier */ - /* - * We put mnt_count & mnt_expiry_mark at the end of struct vfsmount - * to let these frequently modified fields in a separate cache line - * (so that reads of mnt_flags wont ping-pong on SMP machines) - */ - atomic_t mnt_count; int mnt_expiry_mark; /* true if marked for expiry */ int mnt_pinned; int mnt_ghosts; -#ifdef CONFIG_SMP - int __percpu *mnt_writers; -#else - int mnt_writers; -#endif }; -static inline int *get_mnt_writers_ptr(struct vfsmount *mnt) -{ -#ifdef CONFIG_SMP - return mnt->mnt_writers; -#else - return &mnt->mnt_writers; -#endif -} - -static inline struct vfsmount *mntget(struct vfsmount *mnt) -{ - if (mnt) - atomic_inc(&mnt->mnt_count); - return mnt; -} - struct file; /* forward dec */ extern int mnt_want_write(struct vfsmount *mnt); extern int mnt_want_write_file(struct file *file); extern int mnt_clone_write(struct vfsmount *mnt); extern void mnt_drop_write(struct vfsmount *mnt); -extern void mntput_no_expire(struct vfsmount *mnt); +extern void mntput(struct vfsmount *mnt); +extern struct vfsmount *mntget(struct vfsmount *mnt); +extern void mntput_long(struct vfsmount *mnt); +extern struct vfsmount *mntget_long(struct vfsmount *mnt); extern void mnt_pin(struct vfsmount *mnt); extern void mnt_unpin(struct vfsmount *mnt); extern int __mnt_is_readonly(struct vfsmount *mnt); -static inline void mntput(struct vfsmount *mnt) -{ - if (mnt) { - mnt->mnt_expiry_mark = 0; - mntput_no_expire(mnt); - } -} - extern struct vfsmount *do_kern_mount(const char *fstype, int flags, const char *name, void *data); diff --git a/include/linux/path.h b/include/linux/path.h index edc98de..a581e8c 100644 --- a/include/linux/path.h +++ b/include/linux/path.h @@ -10,7 +10,9 @@ struct path { }; extern void path_get(struct path *); +extern void path_get_long(struct path *); extern void path_put(struct path *); +extern void path_put_long(struct path *); static inline int path_equal(const struct path *path1, const struct path *path2) { -- cgit v1.1 From 6c23a9681c0fe7fb7dd331b39dda11926f43746e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 7 Jan 2011 08:43:37 +0100 Subject: block: add internal hd part table references We can't use krefs since it's apparently restricted to very basic reference counting. This reverts commit e4a683c8. Signed-off-by: Jens Axboe --- include/linux/genhd.h | 27 +++++++++++++++++++++++++-- include/linux/kref.h | 1 - 2 files changed, 25 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 2ba2792..2d04681 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -115,8 +115,8 @@ struct hd_struct { #else struct disk_stats dkstats; #endif + atomic_t ref; struct rcu_head rcu_head; - struct kref ref; }; #define GENHD_FL_REMOVABLE 1 @@ -584,7 +584,7 @@ extern struct hd_struct * __must_check add_partition(struct gendisk *disk, sector_t len, int flags, struct partition_meta_info *info); -extern void __delete_partition(struct kref *ref); +extern void __delete_partition(struct hd_struct *); extern void delete_partition(struct gendisk *, int); extern void printk_all_partitions(void); @@ -613,6 +613,29 @@ extern ssize_t part_fail_store(struct device *dev, const char *buf, size_t count); #endif /* CONFIG_FAIL_MAKE_REQUEST */ +static inline void hd_ref_init(struct hd_struct *part) +{ + atomic_set(&part->ref, 1); + smp_mb(); +} + +static inline void hd_struct_get(struct hd_struct *part) +{ + atomic_inc(&part->ref); + smp_mb__after_atomic_inc(); +} + +static inline int hd_struct_try_get(struct hd_struct *part) +{ + return atomic_inc_not_zero(&part->ref); +} + +static inline void hd_struct_put(struct hd_struct *part) +{ + if (atomic_dec_and_test(&part->ref)) + __delete_partition(part); +} + #else /* CONFIG_BLOCK */ static inline void printk_all_partitions(void) { } diff --git a/include/linux/kref.h b/include/linux/kref.h index 90b9e44..6cc38fc 100644 --- a/include/linux/kref.h +++ b/include/linux/kref.h @@ -23,7 +23,6 @@ struct kref { void kref_init(struct kref *kref); void kref_get(struct kref *kref); -int kref_test_and_get(struct kref *kref); int kref_put(struct kref *kref, void (*release) (struct kref *kref)); #endif /* _KREF_H_ */ -- cgit v1.1 From b7908c1035af7652cd613991b54dbff9c8b6bd3a Mon Sep 17 00:00:00 2001 From: Jeff Moyer Date: Thu, 6 Jan 2011 20:41:42 +0100 Subject: block: trace event block fix unassigned field The "error" field in block_bio_complete is not assigned, leaving the memory area uninitialized (keeping garbage data). Pass an additional tracepoint argument to this event to initialize this field. Signed-off-by: Jeff Moyer Signed-off-by: Mathieu Desnoyers CC: Steven Rostedt CC: Frederic Weisbecker CC: Ingo Molnar CC: Thomas Gleixner CC: Li Zefan CC: Alan.Brunelle@hp.com Signed-off-by: Jens Axboe --- include/trace/events/block.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/block.h b/include/trace/events/block.h index b56c65d..aba421d 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -206,15 +206,16 @@ TRACE_EVENT(block_bio_bounce, * block_bio_complete - completed all work on the block operation * @q: queue holding the block operation * @bio: block operation completed + * @error: io error value * * This tracepoint indicates there is no further work to do on this * block IO operation @bio. */ TRACE_EVENT(block_bio_complete, - TP_PROTO(struct request_queue *q, struct bio *bio), + TP_PROTO(struct request_queue *q, struct bio *bio, int error), - TP_ARGS(q, bio), + TP_ARGS(q, bio, error), TP_STRUCT__entry( __field( dev_t, dev ) @@ -228,6 +229,7 @@ TRACE_EVENT(block_bio_complete, __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_sector; __entry->nr_sector = bio->bi_size >> 9; + __entry->error = error; blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size); ), -- cgit v1.1 From ca86828ccd3128513f6d4e200b437deac95408db Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Thu, 6 Jan 2011 17:51:07 +0100 Subject: x86, AMD, PCI: Add AMD northbridge PCI device id for CPU families 12h and 14h This patch adds the PCI northbridge device id for AMD CPU families 12h and 14h. Both families have implemented the same PCI northbridge device. There are some future use cases that use this PCI device and we would like to clarify its naming. Signed-off-by: Robert Richter Cc: xen-devel@lists.xensource.com Cc: Keir Fraser Cc: Jan Beulich LKML-Reference: <20110106165107.GL4739@erda.amd.com> Signed-off-by: Ingo Molnar --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index cb845c1..dd7d4e2 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -518,6 +518,7 @@ #define PCI_DEVICE_ID_AMD_11H_NB_MISC 0x1303 #define PCI_DEVICE_ID_AMD_11H_NB_LINK 0x1304 #define PCI_DEVICE_ID_AMD_15H_NB_MISC 0x1603 +#define PCI_DEVICE_ID_AMD_CNB17H_F3 0x1703 #define PCI_DEVICE_ID_AMD_LANCE 0x2000 #define PCI_DEVICE_ID_AMD_LANCE_HOME 0x2001 #define PCI_DEVICE_ID_AMD_SCSI 0x2020 -- cgit v1.1 From 07e06b011db2b3300f6c975ebf293fc4c8c59942 Mon Sep 17 00:00:00 2001 From: Yong Zhang Date: Fri, 7 Jan 2011 15:17:36 +0800 Subject: sched: Consolidate the name of root_task_group and init_task_group root_task_group is the leftover of USER_SCHED, now it's always same to init_task_group. But as Mike suggested, root_task_group is maybe the suitable name to keep for a tree. So in this patch: init_task_group --> root_task_group init_task_group_load --> root_task_group_load INIT_TASK_GROUP_LOAD --> ROOT_TASK_GROUP_LOAD Suggested-by: Mike Galbraith Signed-off-by: Yong Zhang Signed-off-by: Peter Zijlstra LKML-Reference: <20110107071736.GA32635@windriver.com> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 777cd01..341acbb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2511,7 +2511,7 @@ extern void normalize_rt_tasks(void); #ifdef CONFIG_CGROUP_SCHED -extern struct task_group init_task_group; +extern struct task_group root_task_group; extern struct task_group *sched_create_group(struct task_group *parent); extern void sched_destroy_group(struct task_group *tg); -- cgit v1.1 From 3a9f987b3141f086de27832514aad9f50a53f754 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 7 Jan 2011 15:40:10 -0500 Subject: tracing: Include module.h in define_trace.h While doing some developing, Peter Zijlstra and I have found that if a CREATE_TRACE_POINTS include is done before module.h is included, it can break the build. We have been lucky so far that this has not broke the build since module.h is included in almost everything. Reported-by: Peter Zijlstra Signed-off-by: Steven Rostedt --- include/trace/define_trace.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h index b0b4eb2..da39b22 100644 --- a/include/trace/define_trace.h +++ b/include/trace/define_trace.h @@ -21,6 +21,16 @@ #undef CREATE_TRACE_POINTS #include +/* + * module.h includes tracepoints, and because ftrace.h + * pulls in module.h: + * trace/ftrace.h -> linux/ftrace_event.h -> linux/perf_event.h -> + * linux/ftrace.h -> linux/module.h + * we must include module.h here before we play with any of + * the TRACE_EVENT() macros, otherwise the tracepoints included + * by module.h may break the build. + */ +#include #undef TRACE_EVENT #define TRACE_EVENT(name, proto, args, tstruct, assign, print) \ -- cgit v1.1 From c97415a72521071c235e0879f9a600014afd87b1 Mon Sep 17 00:00:00 2001 From: Stefan Achatz Date: Fri, 26 Nov 2010 19:57:29 +0000 Subject: sysfs: Introducing binary attributes for struct class Added dev_bin_attrs to struct class similar to existing dev_attrs. Signed-off-by: Stefan Achatz Acked-by: Greg Kroah-Hartman Signed-off-by: Jiri Kosina --- include/linux/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index dd48953..032bdb5 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -197,6 +197,7 @@ struct class { struct class_attribute *class_attrs; struct device_attribute *dev_attrs; + struct bin_attribute *dev_bin_attrs; struct kobject *dev_kobj; int (*dev_uevent)(struct device *dev, struct kobj_uevent_env *env); -- cgit v1.1 From ec6e7c3ae39cb1dc279b5274aaaadd09ff8e224b Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Thu, 6 Jan 2011 13:45:32 -0500 Subject: tracing/trivial: Add missing comma in TRACE_EVENT comment Add missing comma within the TRACE_EVENT() example in tracepoint.h. Signed-off-by: Mathieu Desnoyers LKML-Reference: <20110106184532.GA2526@Krystal> CC: Frederic Weisbecker CC: Ingo Molnar CC: Thomas Gleixner Signed-off-by: Steven Rostedt --- include/linux/tracepoint.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index d3e4f87..899103c 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -326,7 +326,7 @@ do_trace: \ * memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN); * __entry->next_pid = next->pid; * __entry->next_prio = next->prio; - * ) + * ), * * * * * Formatted output of a trace record via TP_printk(). -- cgit v1.1 From 881fe4bdcdc899674524e30a76c76d298b447008 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Thu, 6 Jan 2011 12:53:19 -0500 Subject: tracing: remove duplicate null-pointer check in skb tracepoint The check for NULL skb in the kfree_skb trace event is a duplicate from the check already done in its only caller, kfree_skb(). Remove this duplicate check. Signed-off-by: Mathieu Desnoyers LKML-Reference: <20110106175319.GA30610@Krystal> Acked-by: Neil Horman Acked-by: David S. Miller CC: Steven Rostedt CC: Frederic Weisbecker CC: Ingo Molnar CC: Thomas Gleixner CC: Zhaolei Signed-off-by: Steven Rostedt --- include/trace/events/skb.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 75ce9d5..f10293c 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -25,9 +25,7 @@ TRACE_EVENT(kfree_skb, TP_fast_assign( __entry->skbaddr = skb; - if (skb) { - __entry->protocol = ntohs(skb->protocol); - } + __entry->protocol = ntohs(skb->protocol); __entry->location = location; ), -- cgit v1.1 From bd1c8b22b7b81c6f6c4f5c19cb2387da3d02fb0f Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Tue, 4 Jan 2011 16:06:09 +0800 Subject: tracepoint: Add __rcu annotation Add __rcu annotation to : (struct tracepoint)->funcs Acked-by: Mathieu Desnoyers Signed-off-by: Lai Jiangshan LKML-Reference: <4D22D4F1.50505@cn.fujitsu.com> Signed-off-by: Steven Rostedt --- include/linux/tracepoint.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 899103c..c681461 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -32,7 +32,7 @@ struct tracepoint { int state; /* State. */ void (*regfunc)(void); void (*unregfunc)(void); - struct tracepoint_func *funcs; + struct tracepoint_func __rcu *funcs; } __attribute__((aligned(32))); /* * Aligned on 32 bytes because it is * globally visible and gcc happily -- cgit v1.1 From 2d75af2f2a7a6103a6d539a492fe81deacabde44 Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Fri, 7 Jan 2011 13:36:58 -0500 Subject: dynamic debug: Fix build issue with older gcc On older gcc (3.3) dynamic debug fails to compile: include/net/inet_connection_sock.h: In function `inet_csk_reset_xmit_timer': include/net/inet_connection_sock.h:236: error: duplicate label declaration `do_printk' include/net/inet_connection_sock.h:219: error: this is a previous declaration include/net/inet_connection_sock.h:236: error: duplicate label declaration `out' include/net/inet_connection_sock.h:219: error: this is a previous declaration include/net/inet_connection_sock.h:236: error: duplicate label `do_printk' include/net/inet_connection_sock.h:236: error: duplicate label `out' Fix, by reverting the usage of JUMP_LABEL() in dynamic debug for now. Cc: Reported-by: Tetsuo Handa Tested-by: Tetsuo Handa Signed-off-by: Jason Baron Signed-off-by: Steven Rostedt --- include/linux/dynamic_debug.h | 18 ++++-------------- 1 file changed, 4 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index a90b389..1c70028 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -44,34 +44,24 @@ int ddebug_add_module(struct _ddebug *tab, unsigned int n, extern int ddebug_remove_module(const char *mod_name); #define dynamic_pr_debug(fmt, ...) do { \ - __label__ do_printk; \ - __label__ out; \ static struct _ddebug descriptor \ __used \ __attribute__((section("__verbose"), aligned(8))) = \ { KBUILD_MODNAME, __func__, __FILE__, fmt, __LINE__, \ _DPRINTK_FLAGS_DEFAULT }; \ - JUMP_LABEL(&descriptor.enabled, do_printk); \ - goto out; \ -do_printk: \ - printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ -out: ; \ + if (unlikely(descriptor.enabled)) \ + printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \ } while (0) #define dynamic_dev_dbg(dev, fmt, ...) do { \ - __label__ do_printk; \ - __label__ out; \ static struct _ddebug descriptor \ __used \ __attribute__((section("__verbose"), aligned(8))) = \ { KBUILD_MODNAME, __func__, __FILE__, fmt, __LINE__, \ _DPRINTK_FLAGS_DEFAULT }; \ - JUMP_LABEL(&descriptor.enabled, do_printk); \ - goto out; \ -do_printk: \ - dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); \ -out: ; \ + if (unlikely(descriptor.enabled)) \ + dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); \ } while (0) #else -- cgit v1.1 From 26daa1ed40c6b31b4220581431982814c47c608a Mon Sep 17 00:00:00 2001 From: Jennifer Li Date: Wed, 17 Nov 2010 23:01:59 -0500 Subject: mmc: sdhci: Disable ADMA on some O2Micro SD/MMC parts. This patch disables the broken ADMA on selected O2Micro devices. Signed-off-by: Jennifer Li Reviewed-by: Chris Ball Signed-off-by: Chris Ball --- include/linux/pci_ids.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index cb845c1..7a58875 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1650,6 +1650,11 @@ #define PCI_DEVICE_ID_O2_6836 0x6836 #define PCI_DEVICE_ID_O2_6812 0x6872 #define PCI_DEVICE_ID_O2_6933 0x6933 +#define PCI_DEVICE_ID_O2_8120 0x8120 +#define PCI_DEVICE_ID_O2_8220 0x8220 +#define PCI_DEVICE_ID_O2_8221 0x8221 +#define PCI_DEVICE_ID_O2_8320 0x8320 +#define PCI_DEVICE_ID_O2_8321 0x8321 #define PCI_VENDOR_ID_3DFX 0x121a #define PCI_DEVICE_ID_3DFX_VOODOO 0x0001 -- cgit v1.1 From 04566831a703ae3ef4b49a2deae261c9ed26e020 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 8 Nov 2010 21:36:50 -0500 Subject: mmc: Aggressive clock gating framework This patch modifies the MMC core code to optionally call the set_ios() operation on the driver with the clock frequency set to 0 (gate) after a grace period of at least 8 MCLK cycles, then restore it (ungate) before any new request. This gives the driver the option to shut down the MCI clock to the MMC/SD card when the clock frequency is 0, i.e. the core has stated that the MCI clock does not need to be generated. It is inspired by existing clock gating code found in the OMAP and Atmel drivers and brings this up to the host abstraction. Gating is performed before and after any MMC request. This patchset implements this for the MMCI/PL180 MMC/SD host controller, but it should be simple to switch OMAP/Atmel over to using this instead. mmc_set_{gated,ungated}() add variable protection to the state holders for the clock gating code. This is particularly important when ordinary .set_ios() calls would race with the .set_ios() call resulting from a delayed gate operation. Signed-off-by: Linus Walleij Reviewed-by: Chris Ball Tested-by: Chris Ball Signed-off-by: Chris Ball --- include/linux/mmc/host.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 30f6fad..381c77f 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -172,6 +172,16 @@ struct mmc_host { mmc_pm_flag_t pm_caps; /* supported pm features */ +#ifdef CONFIG_MMC_CLKGATE + int clk_requests; /* internal reference counter */ + unsigned int clk_delay; /* number of MCI clk hold cycles */ + bool clk_gated; /* clock gated */ + struct work_struct clk_gate_work; /* delayed clock gate */ + unsigned int clk_old; /* old clock value cache */ + spinlock_t clk_lock; /* lock for clk fields */ + struct mutex clk_gate_mutex; /* mutex for clock gating */ +#endif + /* host specific block data */ unsigned int max_seg_size; /* see blk_queue_max_segment_size */ unsigned short max_segs; /* see blk_queue_max_segments */ -- cgit v1.1 From 8f230f454fe04ba326ffaead3a6b88dcf44eaf4b Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 8 Dec 2010 10:04:30 +0100 Subject: mmc: Add support for JMicron 388 SD/MMC controller JMicron 388 SD/MMC combo controller supports the 1.8V low-voltage for SD, but MMC doesn't work with the low-voltage, resulting in an error at probing. This patch adds the support for multiple voltage mask per device type, so that SD works with 1.8V while MMC forces 3.3V. Here new ocr_avail_* fields for each device are introduced, so that the actual OCR mask is switched dynamically. Also, the restriction of low-voltage in core/sd.c is removed when the bit is allowed explicitly via ocr_avail_sd mask. This patch was rewritten from scratch based on Aries' original code. Signed-off-by: Aries Lee Signed-off-by: Takashi Iwai Reviewed-by: Chris Ball Signed-off-by: Chris Ball --- include/linux/mmc/host.h | 3 +++ include/linux/mmc/sdhci.h | 4 ++++ include/linux/pci_ids.h | 2 ++ 3 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 381c77f..4a9d9d25 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -131,6 +131,9 @@ struct mmc_host { unsigned int f_max; unsigned int f_init; u32 ocr_avail; + u32 ocr_avail_sdio; /* SDIO-specific OCR */ + u32 ocr_avail_sd; /* SD-specific OCR */ + u32 ocr_avail_mmc; /* MMC-specific OCR */ struct notifier_block pm_notify; #define MMC_VDD_165_195 0x00000080 /* VDD voltage 1.65 - 1.95 */ diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h index 1fdc673..0d953f5 100644 --- a/include/linux/mmc/sdhci.h +++ b/include/linux/mmc/sdhci.h @@ -139,6 +139,10 @@ struct sdhci_host { unsigned int caps; /* Alternative capabilities */ + unsigned int ocr_avail_sdio; /* OCR bit masks */ + unsigned int ocr_avail_sd; + unsigned int ocr_avail_mmc; + unsigned long private[0] ____cacheline_aligned; }; #endif /* __SDHCI_H */ diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 7a58875..2f17b4c 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2368,6 +2368,8 @@ #define PCI_DEVICE_ID_JMICRON_JMB38X_SD 0x2381 #define PCI_DEVICE_ID_JMICRON_JMB38X_MMC 0x2382 #define PCI_DEVICE_ID_JMICRON_JMB38X_MS 0x2383 +#define PCI_DEVICE_ID_JMICRON_JMB388_SD 0x2391 +#define PCI_DEVICE_ID_JMICRON_JMB388_ESD 0x2392 #define PCI_VENDOR_ID_KORENIX 0x1982 #define PCI_DEVICE_ID_KORENIX_JETCARDF0 0x1600 -- cgit v1.1 From 080bc9774b6f1e3866747b18631bad26f47c22ce Mon Sep 17 00:00:00 2001 From: Ohad Ben-Cohen Date: Sun, 28 Nov 2010 07:21:29 +0200 Subject: mmc: sdio: don't reinitialize nonremovable powered-resumed cards Upon system resume, SDIO core must reinitialize cards that were powered off during suspend. If the card had its power kept during suspend (and thus it is 'powered-resumed'), SDIO core performs only a limited reinitializing, mainly needed to make sure that the card wasn't removed/replaced. If a __nonremovable__ card is powered-resumed, we can safely skip the reinitializing phase. Note: 9b966aa (mmc: sdio: fully reconfigure oldcard on resume) removed the bus width reconfiguration since mmc_sdio_init_card already does it. It is brought back now in case mmc_sdio_init_card is skipped. Signed-off-by: Ohad Ben-Cohen Signed-off-by: Chris Ball --- include/linux/mmc/host.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 4a9d9d25..3a85e73 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -320,5 +320,10 @@ static inline int mmc_card_is_removable(struct mmc_host *host) return !(host->caps & MMC_CAP_NONREMOVABLE) && mmc_assume_removable; } +static inline int mmc_card_is_powered_resumed(struct mmc_host *host) +{ + return host->pm_flags & MMC_PM_KEEP_POWER; +} + #endif -- cgit v1.1 From a081748735c5feb96b1365e78a5ff0fb6ca7e3a4 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Sat, 8 Jan 2011 21:42:42 -0700 Subject: of/flattree: forward declare struct device_node in of_fdt.h This patch forward declares struct device_node to fix a compile error when of_fdt.h is included, but of.h is not. Alternately, including linux/of.h could have been added to of_fdt.h, but that pulls in a lot of unnecessary declarations when only working with the flattened form. Signed-off-by: Grant Likely --- include/linux/of_fdt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index ee96091..0ef22a1 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -59,6 +59,8 @@ struct boot_param_header { #if defined(CONFIG_OF_FLATTREE) +struct device_node; + /* For scanning an arbitrary device-tree at any time */ extern char *of_fdt_get_string(struct boot_param_header *blob, u32 offset); extern void *of_fdt_get_property(struct boot_param_header *blob, -- cgit v1.1 From 22113efd00491310da802f3b1a9a66cfcf415fac Mon Sep 17 00:00:00 2001 From: Aries Lee Date: Wed, 15 Dec 2010 08:14:24 +0100 Subject: mmc: Test bus-width for old MMC devices Some old MMC devices fail with the 4/8 bits the driver tries to use exclusively. This patch adds a test for the given bus setup and falls back to the lower bit mode (until 1-bit mode) when the test fails. [Major rework and refactoring by tiwai] [Quirk addition and many fixes by prakity] Signed-off-by: Aries Lee Signed-off-by: Takashi Iwai Signed-off-by: Philip Rakity Tested-by: Philip Rakity Signed-off-by: Chris Ball --- include/linux/mmc/host.h | 1 + include/linux/mmc/mmc.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 3a85e73..bcb793e 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -172,6 +172,7 @@ struct mmc_host { #define MMC_CAP_1_2V_DDR (1 << 12) /* can support */ /* DDR mode at 1.2V */ #define MMC_CAP_POWER_OFF_CARD (1 << 13) /* Can power off after boot */ +#define MMC_CAP_BUS_WIDTH_TEST (1 << 14) /* CMD14/CMD19 bus width ok */ mmc_pm_flag_t pm_caps; /* supported pm features */ diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index 956fbd87..612301f 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -40,7 +40,9 @@ #define MMC_READ_DAT_UNTIL_STOP 11 /* adtc [31:0] dadr R1 */ #define MMC_STOP_TRANSMISSION 12 /* ac R1b */ #define MMC_SEND_STATUS 13 /* ac [31:16] RCA R1 */ +#define MMC_BUS_TEST_R 14 /* adtc R1 */ #define MMC_GO_INACTIVE_STATE 15 /* ac [31:16] RCA */ +#define MMC_BUS_TEST_W 19 /* adtc R1 */ #define MMC_SPI_READ_OCR 58 /* spi spi_R3 */ #define MMC_SPI_CRC_ON_OFF 59 /* spi [0:0] flag spi_R1 */ -- cgit v1.1 From 30652aa36b58d57fcc1a0acce51e391bbb6edf5e Mon Sep 17 00:00:00 2001 From: Olof Johansson Date: Sat, 1 Jan 2011 18:37:32 -0600 Subject: mmc: sdhci: add quirk for max len ADMA descriptors Some controllers misparse segment length 0 as being 0, not 65536. Add a quirk to deal with it. Signed-off-by: Olof Johansson Reviewed-by: Chris Ball Signed-off-by: Chris Ball --- include/linux/mmc/sdhci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h index 0d953f5..83bd9f7 100644 --- a/include/linux/mmc/sdhci.h +++ b/include/linux/mmc/sdhci.h @@ -83,6 +83,8 @@ struct sdhci_host { #define SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12 (1<<28) /* Controller doesn't have HISPD bit field in HI-SPEED SD card */ #define SDHCI_QUIRK_NO_HISPD_BIT (1<<29) +/* Controller treats ADMA descriptors with length 0000h incorrectly */ +#define SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC (1<<30) int irq; /* Device IRQ */ void __iomem *ioaddr; /* Mapped address */ -- cgit v1.1 From f95f3850f7a9e1d49ebc5b6e72e7cc3ec3685b0b Mon Sep 17 00:00:00 2001 From: Will Newton Date: Sun, 2 Jan 2011 01:11:59 -0500 Subject: mmc: dw_mmc: Add Synopsys DesignWare mmc host driver. This adds the mmc host driver for the Synopsys DesignWare mmc host controller, found in a number of embedded SoC designs. Signed-off-by: Will Newton Reviewed-by: Matt Fleming Reviewed-by: Chris Ball Signed-off-by: Chris Ball --- include/linux/mmc/dw_mmc.h | 217 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 217 insertions(+) create mode 100644 include/linux/mmc/dw_mmc.h (limited to 'include') diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h new file mode 100644 index 0000000..16b0261 --- /dev/null +++ b/include/linux/mmc/dw_mmc.h @@ -0,0 +1,217 @@ +/* + * Synopsys DesignWare Multimedia Card Interface driver + * (Based on NXP driver for lpc 31xx) + * + * Copyright (C) 2009 NXP Semiconductors + * Copyright (C) 2009, 2010 Imagination Technologies Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef _LINUX_MMC_DW_MMC_H_ +#define _LINUX_MMC_DW_MMC_H_ + +#define MAX_MCI_SLOTS 2 + +enum dw_mci_state { + STATE_IDLE = 0, + STATE_SENDING_CMD, + STATE_SENDING_DATA, + STATE_DATA_BUSY, + STATE_SENDING_STOP, + STATE_DATA_ERROR, +}; + +enum { + EVENT_CMD_COMPLETE = 0, + EVENT_XFER_COMPLETE, + EVENT_DATA_COMPLETE, + EVENT_DATA_ERROR, + EVENT_XFER_ERROR +}; + +struct mmc_data; + +/** + * struct dw_mci - MMC controller state shared between all slots + * @lock: Spinlock protecting the queue and associated data. + * @regs: Pointer to MMIO registers. + * @sg: Scatterlist entry currently being processed by PIO code, if any. + * @pio_offset: Offset into the current scatterlist entry. + * @cur_slot: The slot which is currently using the controller. + * @mrq: The request currently being processed on @cur_slot, + * or NULL if the controller is idle. + * @cmd: The command currently being sent to the card, or NULL. + * @data: The data currently being transferred, or NULL if no data + * transfer is in progress. + * @use_dma: Whether DMA channel is initialized or not. + * @sg_dma: Bus address of DMA buffer. + * @sg_cpu: Virtual address of DMA buffer. + * @dma_ops: Pointer to platform-specific DMA callbacks. + * @cmd_status: Snapshot of SR taken upon completion of the current + * command. Only valid when EVENT_CMD_COMPLETE is pending. + * @data_status: Snapshot of SR taken upon completion of the current + * data transfer. Only valid when EVENT_DATA_COMPLETE or + * EVENT_DATA_ERROR is pending. + * @stop_cmdr: Value to be loaded into CMDR when the stop command is + * to be sent. + * @dir_status: Direction of current transfer. + * @tasklet: Tasklet running the request state machine. + * @card_tasklet: Tasklet handling card detect. + * @pending_events: Bitmask of events flagged by the interrupt handler + * to be processed by the tasklet. + * @completed_events: Bitmask of events which the state machine has + * processed. + * @state: Tasklet state. + * @queue: List of slots waiting for access to the controller. + * @bus_hz: The rate of @mck in Hz. This forms the basis for MMC bus + * rate and timeout calculations. + * @current_speed: Configured rate of the controller. + * @num_slots: Number of slots available. + * @pdev: Platform device associated with the MMC controller. + * @pdata: Platform data associated with the MMC controller. + * @slot: Slots sharing this MMC controller. + * @data_shift: log2 of FIFO item size. + * @push_data: Pointer to FIFO push function. + * @pull_data: Pointer to FIFO pull function. + * @quirks: Set of quirks that apply to specific versions of the IP. + * + * Locking + * ======= + * + * @lock is a softirq-safe spinlock protecting @queue as well as + * @cur_slot, @mrq and @state. These must always be updated + * at the same time while holding @lock. + * + * The @mrq field of struct dw_mci_slot is also protected by @lock, + * and must always be written at the same time as the slot is added to + * @queue. + * + * @pending_events and @completed_events are accessed using atomic bit + * operations, so they don't need any locking. + * + * None of the fields touched by the interrupt handler need any + * locking. However, ordering is important: Before EVENT_DATA_ERROR or + * EVENT_DATA_COMPLETE is set in @pending_events, all data-related + * interrupts must be disabled and @data_status updated with a + * snapshot of SR. Similarly, before EVENT_CMD_COMPLETE is set, the + * CMDRDY interupt must be disabled and @cmd_status updated with a + * snapshot of SR, and before EVENT_XFER_COMPLETE can be set, the + * bytes_xfered field of @data must be written. This is ensured by + * using barriers. + */ +struct dw_mci { + spinlock_t lock; + void __iomem *regs; + + struct scatterlist *sg; + unsigned int pio_offset; + + struct dw_mci_slot *cur_slot; + struct mmc_request *mrq; + struct mmc_command *cmd; + struct mmc_data *data; + + /* DMA interface members*/ + int use_dma; + + dma_addr_t sg_dma; + void *sg_cpu; + struct dw_mci_dma_ops *dma_ops; +#ifdef CONFIG_MMC_DW_IDMAC + unsigned int ring_size; +#else + struct dw_mci_dma_data *dma_data; +#endif + u32 cmd_status; + u32 data_status; + u32 stop_cmdr; + u32 dir_status; + struct tasklet_struct tasklet; + struct tasklet_struct card_tasklet; + unsigned long pending_events; + unsigned long completed_events; + enum dw_mci_state state; + struct list_head queue; + + u32 bus_hz; + u32 current_speed; + u32 num_slots; + struct platform_device *pdev; + struct dw_mci_board *pdata; + struct dw_mci_slot *slot[MAX_MCI_SLOTS]; + + /* FIFO push and pull */ + int data_shift; + void (*push_data)(struct dw_mci *host, void *buf, int cnt); + void (*pull_data)(struct dw_mci *host, void *buf, int cnt); + + /* Workaround flags */ + u32 quirks; +}; + +/* DMA ops for Internal/External DMAC interface */ +struct dw_mci_dma_ops { + /* DMA Ops */ + int (*init)(struct dw_mci *host); + void (*start)(struct dw_mci *host, unsigned int sg_len); + void (*complete)(struct dw_mci *host); + void (*stop)(struct dw_mci *host); + void (*cleanup)(struct dw_mci *host); + void (*exit)(struct dw_mci *host); +}; + +/* IP Quirks/flags. */ +/* No special quirks or flags to cater for */ +#define DW_MCI_QUIRK_NONE 0 +/* DTO fix for command transmission with IDMAC configured */ +#define DW_MCI_QUIRK_IDMAC_DTO 1 +/* delay needed between retries on some 2.11a implementations */ +#define DW_MCI_QUIRK_RETRY_DELAY 2 +/* High Speed Capable - Supports HS cards (upto 50MHz) */ +#define DW_MCI_QUIRK_HIGHSPEED 4 + + +struct dma_pdata; + +struct block_settings { + unsigned short max_segs; /* see blk_queue_max_segments */ + unsigned int max_blk_size; /* maximum size of one mmc block */ + unsigned int max_blk_count; /* maximum number of blocks in one req*/ + unsigned int max_req_size; /* maximum number of bytes in one req*/ + unsigned int max_seg_size; /* see blk_queue_max_segment_size */ +}; + +/* Board platform data */ +struct dw_mci_board { + u32 num_slots; + + u32 quirks; /* Workaround / Quirk flags */ + unsigned int bus_hz; /* Bus speed */ + + /* delay in mS before detecting cards after interrupt */ + u32 detect_delay_ms; + + int (*init)(u32 slot_id, irq_handler_t , void *); + int (*get_ro)(u32 slot_id); + int (*get_cd)(u32 slot_id); + int (*get_ocr)(u32 slot_id); + int (*get_bus_wd)(u32 slot_id); + /* + * Enable power to selected slot and set voltage to desired level. + * Voltage levels are specified using MMC_VDD_xxx defines defined + * in linux/mmc/host.h file. + */ + void (*setpower)(u32 slot_id, u32 volt); + void (*exit)(u32 slot_id); + void (*select_slot)(u32 slot_id); + + struct dw_mci_dma_ops *dma_ops; + struct dma_pdata *data; + struct block_settings *blk_settings; +}; + +#endif /* _LINUX_MMC_DW_MMC_H_ */ -- cgit v1.1 From 93173054f2979de41b1912b19f0b57edfb35fcdc Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Wed, 22 Dec 2010 12:02:15 +0100 Subject: mmc: tmio_mmc: implement a bounce buffer for unaligned DMA For example, with SDIO WLAN cards, some transfers happen with buffers at odd addresses, whereas the SH-Mobile DMA engine requires even addresses for SDHI. This patch extends the tmio driver with a bounce buffer, that is used for single entry scatter-gather lists both for sending and receiving. If we ever encounter unaligned transfers with multi-element sg lists, this patch will have to be extended. For now it just falls back to PIO in this and other unsupported cases. Signed-off-by: Guennadi Liakhovetski Acked-by: Samuel Ortiz Signed-off-by: Chris Ball --- include/linux/mfd/tmio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 085f041..dbfc053 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -66,6 +66,7 @@ void tmio_core_mmc_clk_div(void __iomem *cnf, int shift, int state); struct tmio_mmc_dma { void *chan_priv_tx; void *chan_priv_rx; + int alignment_shift; }; /* -- cgit v1.1 From 845ecd20239c28e97e766ff54078a58be19f3a91 Mon Sep 17 00:00:00 2001 From: Arnd Hannemann Date: Tue, 28 Dec 2010 23:22:31 +0100 Subject: mmc: tmio_mmc: implement SDIO IRQ support This patch implements SDIO IRQ support for mfds which announce the TMIO_MMC_SDIO_IRQ flag for tmio_mmc. If MMC_CAP_SDIO_IRQ is also set SDIO IRQ signalling is activated. Tested with a b43-based wireless SDIO card and sh_mobile_sdhi. Signed-off-by: Arnd Hannemann Signed-off-by: Chris Ball --- include/linux/mfd/tmio.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index dbfc053..8e70310 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -57,6 +57,10 @@ * is configured in 4-bit mode. */ #define TMIO_MMC_BLKSZ_2BYTES (1 << 1) +/* + * Some controllers can support SDIO IRQ signalling. + */ +#define TMIO_MMC_SDIO_IRQ (1 << 2) int tmio_core_mmc_enable(void __iomem *cnf, int shift, unsigned long base); int tmio_core_mmc_resume(void __iomem *cnf, int shift, unsigned long base); -- cgit v1.1 From 6099469805c24af14250e182bb9ca082b8a6b716 Mon Sep 17 00:00:00 2001 From: Roland Stigge Date: Sun, 9 Jan 2011 09:31:39 -0500 Subject: hwmon: Support for Dallas Semiconductor DS620 Driver for Dallas Semiconductor DS620 temperature sensor and thermostat Signed-off-by: Roland Stigge Signed-off-by: Guenter Roeck --- include/linux/i2c/ds620.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 include/linux/i2c/ds620.h (limited to 'include') diff --git a/include/linux/i2c/ds620.h b/include/linux/i2c/ds620.h new file mode 100644 index 0000000..736bb87 --- /dev/null +++ b/include/linux/i2c/ds620.h @@ -0,0 +1,21 @@ +#ifndef _LINUX_DS620_H +#define _LINUX_DS620_H + +#include +#include + +/* platform data for the DS620 temperature sensor and thermostat */ + +struct ds620_platform_data { + /* + * Thermostat output pin PO mode: + * 0 = always low (default) + * 1 = PO_LOW + * 2 = PO_HIGH + * + * (see Documentation/hwmon/ds620) + */ + int pomode; +}; + +#endif /* _LINUX_DS620_H */ -- cgit v1.1 From 49da97dcb6b00a6869bbc3fa6ec7fdfd8a6e41a3 Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Wed, 5 Jan 2011 21:13:11 +0000 Subject: net/fec: add mac field into platform data and consolidate fec_get_mac Add mac field into fec_platform_data and consolidate function fec_get_mac to get mac address in following order. 1) module parameter via kernel command line fec.macaddr=0x00,0x04,... 2) from flash in case of CONFIG_M5272 or fec_platform_data mac field for others, which typically have mac stored in fuse 3) fec mac address registers set by bootloader Signed-off-by: Shawn Guo Signed-off-by: David S. Miller --- include/linux/fec.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/fec.h b/include/linux/fec.h index 5d3523d..bcff455 100644 --- a/include/linux/fec.h +++ b/include/linux/fec.h @@ -3,6 +3,8 @@ * Copyright (c) 2009 Orex Computed Radiography * Baruch Siach * + * Copyright (C) 2010 Freescale Semiconductor, Inc. + * * Header file for the FEC platform data * * This program is free software; you can redistribute it and/or modify @@ -16,6 +18,7 @@ struct fec_platform_data { phy_interface_t phy; + unsigned char mac[ETH_ALEN]; }; #endif -- cgit v1.1 From 928c41e7a15d1164bb725f3445575f4651b5b9f0 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 8 Jan 2011 17:39:21 +0000 Subject: net/sock.h: make some fields private to fix kernel-doc warning(s) Fix new kernel-doc notation warning in sock.h by annotating skc_dontcopy_* as private fields. Warning(include/net/sock.h:163): No description found for parameter 'skc_dontcopy_end[0]' Signed-off-by: Randy Dunlap Signed-off-by: David S. Miller --- include/net/sock.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 21a02f7..d884d26 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -152,14 +152,18 @@ struct sock_common { * fields between dontcopy_begin/dontcopy_end * are not copied in sock_copy() */ + /* private: */ int skc_dontcopy_begin[0]; + /* public: */ union { struct hlist_node skc_node; struct hlist_nulls_node skc_nulls_node; }; int skc_tx_queue_mapping; atomic_t skc_refcnt; + /* private: */ int skc_dontcopy_end[0]; + /* public: */ }; /** -- cgit v1.1 From f01a5236bd4b140198fbcc550f085e8361fd73fa Mon Sep 17 00:00:00 2001 From: Jesse Gross Date: Sun, 9 Jan 2011 06:23:31 +0000 Subject: net offloading: Generalize netif_get_vlan_features(). MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit netif_get_vlan_features() is currently only used by netif_needs_gso(), so it only concerns itself with GSO features. However, several other places also should take into account the contents of the packet when deciding whether to offload to hardware. This generalizes the function to return features about all of the various forms of offloading. Since offloads tend to be linked together, this avoids duplicating the logic in each location (i.e. the scatter/gather code also needs the checksum logic). Suggested-by: Michał Mirosław Signed-off-by: Jesse Gross Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0f6b1c9..d4dac09 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2303,7 +2303,7 @@ unsigned long netdev_fix_features(unsigned long features, const char *name); void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev); -int netif_get_vlan_features(struct sk_buff *skb, struct net_device *dev); +int netif_skb_features(struct sk_buff *skb); static inline int net_gso_ok(int features, int gso_type) { @@ -2320,7 +2320,7 @@ static inline int skb_gso_ok(struct sk_buff *skb, int features) static inline int netif_needs_gso(struct net_device *dev, struct sk_buff *skb) { if (skb_is_gso(skb)) { - int features = netif_get_vlan_features(skb, dev); + int features = netif_skb_features(skb); return (!skb_gso_ok(skb, features) || unlikely(skb->ip_summed != CHECKSUM_PARTIAL)); -- cgit v1.1 From fc741216db156994c554ac31c1151fe0e00d8f0e Mon Sep 17 00:00:00 2001 From: Jesse Gross Date: Sun, 9 Jan 2011 06:23:32 +0000 Subject: net offloading: Pass features into netif_needs_gso(). Now that there is a single function that can compute the device features relevant to a packet, we don't want to run it for each offload. This converts netif_needs_gso() to take the features of the device, rather than computing them itself. Signed-off-by: Jesse Gross Signed-off-by: David S. Miller --- include/linux/netdevice.h | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d4dac09..de2bfe6 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2317,16 +2317,10 @@ static inline int skb_gso_ok(struct sk_buff *skb, int features) (!skb_has_frag_list(skb) || (features & NETIF_F_FRAGLIST)); } -static inline int netif_needs_gso(struct net_device *dev, struct sk_buff *skb) +static inline int netif_needs_gso(struct sk_buff *skb, int features) { - if (skb_is_gso(skb)) { - int features = netif_skb_features(skb); - - return (!skb_gso_ok(skb, features) || - unlikely(skb->ip_summed != CHECKSUM_PARTIAL)); - } - - return 0; + return skb_is_gso(skb) && (!skb_gso_ok(skb, features) || + unlikely(skb->ip_summed != CHECKSUM_PARTIAL)); } static inline void netif_set_gso_max_size(struct net_device *dev, -- cgit v1.1 From efb2d31c1c62de9a0e42b2b1981d1a90fc0b4618 Mon Sep 17 00:00:00 2001 From: Mike Frysinger Date: Tue, 26 Oct 2010 21:52:59 -0400 Subject: asm-generic/io.h: add reads[bwl]/writes[bwl] helpers A bunch of arches define reads[bwl]/writes[bwl] helpers for accessing memory mapped registers. Since the Blackfin ones aren't specific to Blackfin code, move them to the common asm-generic/io.h for people. Acked-by: Arnd Bergmann Signed-off-by: Mike Frysinger --- include/asm-generic/io.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include') diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index 3577ca1..4644c9a 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -211,6 +211,36 @@ static inline void outsl(unsigned long addr, const void *buffer, int count) } #endif +static inline void readsl(const void __iomem *addr, void *buf, int len) +{ + insl((unsigned long)addr, buf, len); +} + +static inline void readsw(const void __iomem *addr, void *buf, int len) +{ + insw((unsigned long)addr, buf, len); +} + +static inline void readsb(const void __iomem *addr, void *buf, int len) +{ + insb((unsigned long)addr, buf, len); +} + +static inline void writesl(const void __iomem *addr, const void *buf, int len) +{ + outsl((unsigned long)addr, buf, len); +} + +static inline void writesw(const void __iomem *addr, const void *buf, int len) +{ + outsw((unsigned long)addr, buf, len); +} + +static inline void writesb(const void __iomem *addr, const void *buf, int len) +{ + outsb((unsigned long)addr, buf, len); +} + #ifndef CONFIG_GENERIC_IOMAP #define ioread8(addr) readb(addr) #define ioread16(addr) readw(addr) -- cgit v1.1 From 2a8c0c68487a68441e701f493f43fd547d87c8df Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 8 Jan 2011 19:37:20 -0800 Subject: fs: fix dcache.h kernel-doc notation Fix new kernel-doc notation warning in dcache.h: Warning(include/linux/dcache.h:316): Excess function parameter 'Returns' description in '__d_rcu_to_refcount' Signed-off-by: Randy Dunlap Cc: Nick Piggin Signed-off-by: Linus Torvalds --- include/linux/dcache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index bd07758..59fcd24 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -307,7 +307,7 @@ extern struct dentry *__d_lookup_rcu(struct dentry *parent, struct qstr *name, * __d_rcu_to_refcount - take a refcount on dentry if sequence check is ok * @dentry: dentry to take a ref on * @seq: seqcount to verify against - * @Returns: 0 on failure, else 1. + * Returns: 0 on failure, else 1. * * __d_rcu_to_refcount operates on a dentry,seq pair that was returned * by __d_lookup_rcu, to get a reference on an rcu-walk dentry. -- cgit v1.1 From 175881db8916a5f5cdf920d32214caef588870fd Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 8 Jan 2011 19:38:02 -0800 Subject: hrtimer.h: fix kernel-doc warning Fix new kernel-doc notation warning in hrtimer.h: Warning(include/linux/hrtimer.h:150): Excess struct/union/enum/typedef member 'first' description in 'hrtimer_clock_base' Signed-off-by: Randy Dunlap Signed-off-by: Linus Torvalds --- include/linux/hrtimer.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 330586f..f376ddc 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -131,7 +131,6 @@ struct hrtimer_sleeper { * @index: clock type index for per_cpu support when moving a * timer to a base on another cpu. * @active: red black tree root node for the active timers - * @first: pointer to the timer node which expires first * @resolution: the resolution of the clock, in nanoseconds * @get_time: function to retrieve the current time of the clock * @softirq_time: the time when running the hrtimer queue in the softirq -- cgit v1.1 From 0dc1488527a3c01383a50e5df7187219567586a3 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 8 Jan 2011 19:40:33 -0800 Subject: pipe_fs_i.h: fix kernel-doc warning Fix kernel-doc notation warnings in pipe_fs_i.h: Warning(include/linux/pipe_fs_i.h:58): No description found for parameter 'buffers' Signed-off-by: Randy Dunlap Signed-off-by: Linus Torvalds --- include/linux/pipe_fs_i.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index bb27d7e..77257c9 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -30,6 +30,7 @@ struct pipe_buffer { * struct pipe_inode_info - a linux kernel pipe * @wait: reader/writer wait point in case of empty/full pipe * @nrbufs: the number of non-empty pipe buffers in this pipe + * @buffers: total number of buffers (should be a power of 2) * @curbuf: the current pipe buffer entry * @tmp_page: cached released page * @readers: number of current readers of this pipe -- cgit v1.1 From 9600732b6caba595f34acf2abd930098ec9a0b2b Mon Sep 17 00:00:00 2001 From: Clemens Ladisch Date: Mon, 10 Jan 2011 16:25:44 +0100 Subject: ALSA: core, oxygen, virtuoso: add an enum control info helper Introduce the helper function snd_ctl_enum_info() to fill out the elem_info fields for an enumerated control. Signed-off-by: Clemens Ladisch Signed-off-by: Takashi Iwai --- include/sound/control.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/control.h b/include/sound/control.h index 112374d..7715e6f 100644 --- a/include/sound/control.h +++ b/include/sound/control.h @@ -160,12 +160,14 @@ static inline struct snd_ctl_elem_id *snd_ctl_build_ioff(struct snd_ctl_elem_id } /* - * Frequently used control callbacks + * Frequently used control callbacks/helpers */ int snd_ctl_boolean_mono_info(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo); int snd_ctl_boolean_stereo_info(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_info *uinfo); +int snd_ctl_enum_info(struct snd_ctl_elem_info *info, unsigned int channels, + unsigned int items, const char *const names[]); /* * virtual master control -- cgit v1.1 From 37721e1b0cf98cb65895f234d8c500d270546529 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 10 Jan 2011 08:17:10 +0200 Subject: headers: path.h redux Remove path.h from sched.h and other files. Signed-off-by: Alexey Dobriyan Signed-off-by: Linus Torvalds --- include/linux/audit.h | 1 + include/linux/dcookies.h | 2 +- include/linux/sched.h | 1 - 3 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/audit.h b/include/linux/audit.h index 8b5c062..359df04 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -372,6 +372,7 @@ struct audit_buffer; struct audit_context; struct inode; struct netlink_skb_parms; +struct path; struct linux_binprm; struct mq_attr; struct mqstat; diff --git a/include/linux/dcookies.h b/include/linux/dcookies.h index 24c806f..5ac3bdd 100644 --- a/include/linux/dcookies.h +++ b/include/linux/dcookies.h @@ -13,10 +13,10 @@ #ifdef CONFIG_PROFILING #include -#include #include struct dcookie_user; +struct path; /** * dcookie_register - register a user of dcookies diff --git a/include/linux/sched.h b/include/linux/sched.h index 341acbb..c118a7f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -70,7 +70,6 @@ struct sched_param { #include #include #include -#include #include #include #include -- cgit v1.1 From 57cc7215b70856dc6bae8e55b00ecd7b1d7429b1 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Mon, 10 Jan 2011 08:18:25 +0200 Subject: headers: kobject.h redux Remove kobject.h from files which don't need it, notably, sched.h and fs.h. Signed-off-by: Alexey Dobriyan Signed-off-by: Linus Torvalds --- include/linux/firmware-map.h | 1 - include/linux/fs.h | 2 +- include/linux/sched.h | 1 - include/linux/sunrpc/cache.h | 1 + 4 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/firmware-map.h b/include/linux/firmware-map.h index c6dcc1d..43fe52fc 100644 --- a/include/linux/firmware-map.h +++ b/include/linux/firmware-map.h @@ -17,7 +17,6 @@ #define _LINUX_FIRMWARE_MAP_H #include -#include /* * provide a dummy interface if CONFIG_FIRMWARE_MEMMAP is disabled diff --git a/include/linux/fs.h b/include/linux/fs.h index baf3e55..f84d992 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -382,7 +382,6 @@ struct inodes_stat_t { #include #include #include -#include #include #include #include @@ -402,6 +401,7 @@ struct hd_geometry; struct iovec; struct nameidata; struct kiocb; +struct kobject; struct pipe_inode_info; struct poll_table_struct; struct kstatfs; diff --git a/include/linux/sched.h b/include/linux/sched.h index c118a7f..abc527a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -87,7 +87,6 @@ struct sched_param { #include #include #include -#include #include #include diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 6950c98..78aa104 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -13,6 +13,7 @@ #ifndef _LINUX_SUNRPC_CACHE_H_ #define _LINUX_SUNRPC_CACHE_H_ +#include #include #include #include -- cgit v1.1 From 1a7d946993aaf2a79e9c65abbe169a108e351bcb Mon Sep 17 00:00:00 2001 From: Mattia Dongili Date: Sat, 8 Jan 2011 18:47:29 +0900 Subject: sony-laptop: support new hotkeys on the P, Z and EC series Add new mappings for assist, VAIO, zoom and eject buttons present on refurbished P, Z and EC models. Reported-by: Gyorgy Jeney Reported-by: Stephan Mueller Cc: Dmitry Torokhov Cc: Matthew Garrett Signed-off-by: Mattia Dongili Signed-off-by: Matthew Garrett --- include/linux/sonypi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sonypi.h b/include/linux/sonypi.h index 4f95c1a..0e6dc38 100644 --- a/include/linux/sonypi.h +++ b/include/linux/sonypi.h @@ -112,6 +112,7 @@ #define SONYPI_EVENT_VOLUME_DEC_PRESSED 70 #define SONYPI_EVENT_BRIGHTNESS_PRESSED 71 #define SONYPI_EVENT_MEDIA_PRESSED 72 +#define SONYPI_EVENT_VENDOR_PRESSED 73 /* get/set brightness */ #define SONYPI_IOCGBRT _IOR('v', 0, __u8) -- cgit v1.1 From 8aefcd557d26d0023a36f9ec5afbf55e59f8f26b Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 10 Jan 2011 12:29:43 -0500 Subject: ext4: dynamically allocate the jbd2_inode in ext4_inode_info as necessary Replace the jbd2_inode structure (which is 48 bytes) with a pointer and only allocate the jbd2_inode when it is needed --- that is, when the file system has a journal present and the inode has been opened for writing. This allows us to further slim down the ext4_inode_info structure. Signed-off-by: "Theodore Ts'o" --- include/linux/jbd2.h | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 2ae86aa..27e79c2 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -94,7 +94,7 @@ extern void jbd2_free(void *ptr, size_t size); * * This is an opaque datatype. **/ -typedef struct handle_s handle_t; /* Atomic operation type */ +typedef struct jbd2_journal_handle handle_t; /* Atomic operation type */ /** @@ -416,7 +416,7 @@ struct jbd2_revoke_table_s; * in so it can be fixed later. */ -struct handle_s +struct jbd2_journal_handle { /* Which compound transaction is this update a part of? */ transaction_t *h_transaction; @@ -1158,6 +1158,22 @@ static inline void jbd2_free_handle(handle_t *handle) kmem_cache_free(jbd2_handle_cache, handle); } +/* + * jbd2_inode management (optional, for those file systems that want to use + * dynamically allocated jbd2_inode structures) + */ +extern struct kmem_cache *jbd2_inode_cache; + +static inline struct jbd2_inode *jbd2_alloc_inode(gfp_t gfp_flags) +{ + return kmem_cache_alloc(jbd2_inode_cache, gfp_flags); +} + +static inline void jbd2_free_inode(struct jbd2_inode *jinode) +{ + kmem_cache_free(jbd2_inode_cache, jinode); +} + /* Primary revoke support */ #define JOURNAL_REVOKE_DEFAULT_HASH 256 extern int jbd2_journal_init_revoke(journal_t *, int); -- cgit v1.1 From 5a344a505093dd65f82f338ffdb7208321b3630e Mon Sep 17 00:00:00 2001 From: Zhao Yakui Date: Mon, 10 Jan 2011 16:35:45 +0800 Subject: ACPI: Reevaluate whether the T-state is supported or not after cpu is online/offline After one CPU is offlined, it is unnecessary to switch T-state for it. So it will be better that the throttling is disabled after the cpu is offline. At the same time after one cpu is online, we should check whether the T-state is supported and then set the corresponding T-state flag. Signed-off-by: Zhao Yakui Signed-off-by: Len Brown --- include/acpi/processor.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/acpi/processor.h b/include/acpi/processor.h index 1b62102..55192ac 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -324,6 +324,12 @@ int acpi_processor_tstate_has_changed(struct acpi_processor *pr); int acpi_processor_get_throttling_info(struct acpi_processor *pr); extern int acpi_processor_set_throttling(struct acpi_processor *pr, int state, bool force); +/* + * Reevaluate whether the T-state is invalid after one cpu is + * onlined/offlined. In such case the flags.throttling will be updated. + */ +extern void acpi_processor_reevaluate_tstate(struct acpi_processor *pr, + unsigned long action); extern const struct file_operations acpi_processor_throttling_fops; extern void acpi_processor_throttling_init(void); /* in processor_idle.c */ -- cgit v1.1 From b853b96b1dbdc05fc8eae141a595366d8172962b Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Mon, 22 Nov 2010 12:29:17 +0100 Subject: ext3: Add batched discard support for ext3 Walk through allocation groups and trim all free extents. It can be invoked through FITRIM ioctl on the file system. The main idea is to provide a way to trim the whole file system if needed, since some SSD's may suffer from performance loss after the whole device was filled (it does not mean that fs is full!). It search for free extents in allocation groups specified by Byte range start -> start+len. When the free extent is within this range, blocks are marked as used and then trimmed. Afterwards these blocks are marked as free in per-group bitmap. [JK: Fixed up error handling and trimming of a single group] Signed-off-by: Lukas Czerner Reviewed-by: Jan Kara Reviewed-by: Dmitry Monakhov Signed-off-by: Jan Kara --- include/linux/ext3_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index 6ce1bca..a443965 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -856,6 +856,7 @@ extern struct ext3_group_desc * ext3_get_group_desc(struct super_block * sb, extern int ext3_should_retry_alloc(struct super_block *sb, int *retries); extern void ext3_init_block_alloc_info(struct inode *); extern void ext3_rsv_window_add(struct super_block *sb, struct ext3_reserve_window_node *rsv); +extern int ext3_trim_fs(struct super_block *sb, struct fstrim_range *range); /* dir.c */ extern int ext3_check_dir_entry(const char *, struct inode *, -- cgit v1.1 From 055adcbd7da75868697e767adc4f3272f6cae76c Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 23 Nov 2010 18:49:54 -0800 Subject: quota: Use %pV and __attribute__((format (printf in __quota_error and fix fallout Use %pV in __quota_error so a single printk can not be interleaved with other logging messages. Add __attribute__((format (printf, 3, 4))) so format and arguments can be verified by compiler. Make sure printk formats and arguments match. Block # needed a pointer dereference. Signed-off-by: Joe Perches Signed-off-by: Jan Kara --- include/linux/quotaops.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index d1a9193..223b14c 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -31,8 +31,9 @@ static inline bool is_quota_modification(struct inode *inode, struct iattr *ia) #define quota_error(sb, fmt, args...) \ __quota_error((sb), __func__, fmt , ## args) -extern void __quota_error(struct super_block *sb, const char *func, - const char *fmt, ...); +extern __attribute__((format (printf, 3, 4))) +void __quota_error(struct super_block *sb, const char *func, + const char *fmt, ...); /* * declaration of quota_function calls in kernel. -- cgit v1.1 From a4ae3094869f18e26ece25ad175bbe4cd740e60b Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Tue, 7 Dec 2010 11:55:27 -0600 Subject: ext3: speed up file creates by optimizing rec_len functions The addition of 64k block capability in the rec_len_from_disk and rec_len_to_disk functions added a bit of math overhead which slows down file create workloads needlessly when the architecture cannot even support 64k blocks, thanks to page size limits. Similar changes already exist in the ext4 codebase. The directory entry checking can also be optimized a bit by sprinkling in some unlikely() conditions to move the error handling out of line. bonnie++ sequential file creates on a 512MB ramdisk speeds up from about 77,000/s to about 82,000/s, about a 6% improvement. Signed-off-by: Eric Sandeen Signed-off-by: Jan Kara --- include/linux/ext3_fs.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index a443965..65990ef 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -724,21 +724,30 @@ struct ext3_dir_entry_2 { ~EXT3_DIR_ROUND) #define EXT3_MAX_REC_LEN ((1<<16)-1) +/* + * Tests against MAX_REC_LEN etc were put in place for 64k block + * sizes; if that is not possible on this arch, we can skip + * those tests and speed things up. + */ static inline unsigned ext3_rec_len_from_disk(__le16 dlen) { unsigned len = le16_to_cpu(dlen); +#if (PAGE_CACHE_SIZE >= 65536) if (len == EXT3_MAX_REC_LEN) return 1 << 16; +#endif return len; } static inline __le16 ext3_rec_len_to_disk(unsigned len) { +#if (PAGE_CACHE_SIZE >= 65536) if (len == (1 << 16)) return cpu_to_le16(EXT3_MAX_REC_LEN); else if (len > (1 << 16)) BUG(); +#endif return cpu_to_le16(len); } -- cgit v1.1 From d96336b05d718b03ff03c94c0dc0cc283a29d534 Mon Sep 17 00:00:00 2001 From: Josh Hunt Date: Mon, 27 Dec 2010 13:46:38 -0800 Subject: ext2: Resolve 'dereferencing pointer to incomplete type' when enabling EXT2_XATTR_DEBUG When I enable EXT2_XATTR_DEBUG in fs/ext2/xattr.c I get a build error stating the following: CC fs/ext2/xattr.o fs/ext2/xattr.c: In function 'ext2_xattr_cache_insert': fs/ext2/xattr.c:841: error: dereferencing pointer to incomplete type fs/ext2/xattr.c:846: error: dereferencing pointer to incomplete type make[2]: *** [fs/ext2/xattr.o] Error 1 make[1]: *** [fs/ext2] Error 2 make: *** [fs] Error 2 These lines reference ext2_xattr_cache->c_entry_count which is defined in struct mb_cache. struct mb_cache is currently only defined in fs/mbcache.c. Moving struct mb_cache definition to include/linux/mbcache.h to resolve the issue. Signed-off-by: Josh Hunt Signed-off-by: Jan Kara --- include/linux/mbcache.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/mbcache.h b/include/linux/mbcache.h index 54cbbac..5525d37 100644 --- a/include/linux/mbcache.h +++ b/include/linux/mbcache.h @@ -18,6 +18,17 @@ struct mb_cache_entry { } e_index; }; +struct mb_cache { + struct list_head c_cache_list; + const char *c_name; + atomic_t c_entry_count; + int c_max_entries; + int c_bucket_bits; + struct kmem_cache *c_entry_cache; + struct list_head *c_block_hash; + struct list_head *c_index_hash; +}; + /* Functions on caches */ struct mb_cache *mb_cache_create(const char *, int); -- cgit v1.1 From 9d084a3d5dffd076a9a006164ea0dbd9c495f2b0 Mon Sep 17 00:00:00 2001 From: Fabien Marteau Date: Mon, 10 Jan 2011 11:01:13 -0800 Subject: Input: add Austria Microsystem AS5011 joystick driver This is driver for EasyPoint AS5011 2 axis joystick chip. This chip is plugged on an I2C bus. Tested on ARM processor (i.MX27). Signed-off-by: Fabien Marteau Signed-off-by: Dmitry Torokhov --- include/linux/input/as5011.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) create mode 100644 include/linux/input/as5011.h (limited to 'include') diff --git a/include/linux/input/as5011.h b/include/linux/input/as5011.h new file mode 100644 index 0000000..1affd0d --- /dev/null +++ b/include/linux/input/as5011.h @@ -0,0 +1,20 @@ +#ifndef _AS5011_H +#define _AS5011_H + +/* + * Copyright (c) 2010, 2011 Fabien Marteau + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +struct as5011_platform_data { + unsigned int button_gpio; + unsigned int axis_irq; /* irq number */ + unsigned long axis_irqflags; + char xp, xn; /* threshold for x axis */ + char yp, yn; /* threshold for y axis */ +}; + +#endif /* _AS5011_H */ -- cgit v1.1 From 83723d60717f8da0f53f91cf42a845ed56c09662 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 10 Jan 2011 20:11:38 +0100 Subject: netfilter: x_tables: dont block BH while reading counters Using "iptables -L" with a lot of rules have a too big BH latency. Jesper mentioned ~6 ms and worried of frame drops. Switch to a per_cpu seqlock scheme, so that taking a snapshot of counters doesnt need to block BH (for this cpu, but also other cpus). This adds two increments on seqlock sequence per ipt_do_table() call, its a reasonable cost for allowing "iptables -L" not block BH processing. Reported-by: Jesper Dangaard Brouer Signed-off-by: Eric Dumazet CC: Patrick McHardy Acked-by: Stephen Hemminger Acked-by: Jesper Dangaard Brouer Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/x_tables.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 742bec0..6712e71 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -472,7 +472,7 @@ extern void xt_free_table_info(struct xt_table_info *info); * necessary for reading the counters. */ struct xt_info_lock { - spinlock_t lock; + seqlock_t lock; unsigned char readers; }; DECLARE_PER_CPU(struct xt_info_lock, xt_info_locks); @@ -497,7 +497,7 @@ static inline void xt_info_rdlock_bh(void) local_bh_disable(); lock = &__get_cpu_var(xt_info_locks); if (likely(!lock->readers++)) - spin_lock(&lock->lock); + write_seqlock(&lock->lock); } static inline void xt_info_rdunlock_bh(void) @@ -505,7 +505,7 @@ static inline void xt_info_rdunlock_bh(void) struct xt_info_lock *lock = &__get_cpu_var(xt_info_locks); if (likely(!--lock->readers)) - spin_unlock(&lock->lock); + write_sequnlock(&lock->lock); local_bh_enable(); } @@ -516,12 +516,12 @@ static inline void xt_info_rdunlock_bh(void) */ static inline void xt_info_wrlock(unsigned int cpu) { - spin_lock(&per_cpu(xt_info_locks, cpu).lock); + write_seqlock(&per_cpu(xt_info_locks, cpu).lock); } static inline void xt_info_wrunlock(unsigned int cpu) { - spin_unlock(&per_cpu(xt_info_locks, cpu).lock); + write_sequnlock(&per_cpu(xt_info_locks, cpu).lock); } /* -- cgit v1.1 From 6650239a4b01077e80d5a4468562756d77afaa59 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 8 Jan 2011 17:45:38 -0500 Subject: NFS: Don't use vm_map_ram() in readdir vm_map_ram() is not available on NOMMU platforms, and causes trouble on incoherrent architectures such as ARM when we access the page data through both the direct and the virtual mapping. The alternative is to use the direct mapping to access page data for the case when we are not crossing a page boundary, but to copy the data into a linear scratch buffer when we are accessing data that spans page boundaries. Signed-off-by: Trond Myklebust Tested-by: Marc Kleine-Budde Cc: stable@kernel.org [2.6.37] --- include/linux/sunrpc/xdr.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 498ab93..7783c68 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -201,6 +201,8 @@ struct xdr_stream { __be32 *end; /* end of available buffer space */ struct kvec *iov; /* pointer to the current kvec */ + struct kvec scratch; /* Scratch buffer */ + struct page **page_ptr; /* pointer to the current page */ }; extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p); @@ -208,7 +210,7 @@ extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes); extern void xdr_write_pages(struct xdr_stream *xdr, struct page **pages, unsigned int base, unsigned int len); extern void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p); -extern __be32 *xdr_inline_peek(struct xdr_stream *xdr, size_t nbytes); +extern void xdr_set_scratch_buffer(struct xdr_stream *xdr, void *buf, size_t buflen); extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes); extern void xdr_read_pages(struct xdr_stream *xdr, unsigned int len); extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len); -- cgit v1.1 From 4976b4eb9d083f035aa97afec560c7e1c16c6afd Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 4 Jan 2011 13:02:32 +0100 Subject: mac80211: add remain-on-channel docs Add documentation for the new callbacks that I forgot in the patch adding the callbacks. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 5b3fd5a..3ce8e1f 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1753,6 +1753,16 @@ enum ieee80211_ampdu_mlme_action { * (also see nl80211.h @NL80211_ATTR_WIPHY_ANTENNA_TX). * * @get_antenna: Get current antenna configuration from device (tx_ant, rx_ant). + * + * @remain_on_channel: Starts an off-channel period on the given channel, must + * call back to ieee80211_ready_on_channel() when on that channel. Note + * that normal channel traffic is not stopped as this is intended for hw + * offload. Frames to transmit on the off-channel channel are transmitted + * normally except for the %IEEE80211_TX_CTL_TX_OFFCHAN flag. When the + * duration (which will always be non-zero) expires, the driver must call + * ieee80211_remain_on_channel_expired(). This callback may sleep. + * @cancel_remain_on_channel: Requests that an ongoing off-channel period is + * aborted before it expires. This callback may sleep. */ struct ieee80211_ops { int (*tx)(struct ieee80211_hw *hw, struct sk_buff *skb); -- cgit v1.1 From 610dbc980f7ad886313278ce946287f24b44cf55 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 6 Jan 2011 22:36:44 +0100 Subject: mac80211: add missing docs for off-chan TX flag The flag is IEEE80211_TX_CTL_TX_OFFCHAN and I had added that in a previous patch but forgotten docs. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 3ce8e1f..62c0ce2 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -337,6 +337,10 @@ struct ieee80211_bss_conf { * @IEEE80211_TX_CTL_LDPC: tells the driver to use LDPC for this frame * @IEEE80211_TX_CTL_STBC: Enables Space-Time Block Coding (STBC) for this * frame and selects the maximum number of streams that it can use. + * @IEEE80211_TX_CTL_TX_OFFCHAN: Marks this packet to be transmitted on + * the off-channel channel when a remain-on-channel offload is done + * in hardware -- normal packets still flow and are expected to be + * handled properly by the device. * * Note: If you have to add new flags to the enumeration, then don't * forget to update %IEEE80211_TX_TEMPORARY_FLAGS when necessary. -- cgit v1.1 From f52555a4b2d229079155e6642ec09afa63d10cab Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 6 Jan 2011 22:36:45 +0100 Subject: cfg80211: add mesh join/leave callback docs When I made the patch to add mesh join/leave I didn't pay attention to docs because it was a proof of concept, and then when we actually did merge it I forgot -- add docs now. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/cfg80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index bcc9f44..1322695 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1103,6 +1103,8 @@ struct cfg80211_pmksa { * @change_mpath: change a given mesh path * @get_mpath: get a mesh path for the given parameters * @dump_mpath: dump mesh path callback -- resume dump at index @idx + * @join_mesh: join the mesh network with the specified parameters + * @leave_mesh: leave the current mesh network * * @get_mesh_config: Get the current mesh configuration * -- cgit v1.1 From 45007fd590c6b099cec5d36ea7056b00f8b4916a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 6 Jan 2011 22:36:46 +0100 Subject: nl80211: add/fix mesh docs Some mesh attribute/command docs are missing or have errors in the name so they don't match, fix all of them. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 2b89b71..821ffb9 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -148,6 +148,10 @@ * @NL80211_CMD_SET_MPATH: Set mesh path attributes for mesh path to * destination %NL80211_ATTR_MAC on the interface identified by * %NL80211_ATTR_IFINDEX. + * @NL80211_CMD_NEW_MPATH: Create a new mesh path for the destination given by + * %NL80211_ATTR_MAC via %NL80211_ATTR_MPATH_NEXT_HOP. + * @NL80211_CMD_DEL_MPATH: Delete a mesh path to the destination given by + * %NL80211_ATTR_MAC. * @NL80211_CMD_NEW_PATH: Add a mesh path with given attributes to the * the interface identified by %NL80211_ATTR_IFINDEX. * @NL80211_CMD_DEL_PATH: Remove a mesh path identified by %NL80211_ATTR_MAC @@ -612,7 +616,7 @@ enum nl80211_commands { * consisting of a nested array. * * @NL80211_ATTR_MESH_ID: mesh id (1-32 bytes). - * @NL80211_ATTR_PLINK_ACTION: action to perform on the mesh peer link. + * @NL80211_ATTR_STA_PLINK_ACTION: action to perform on the mesh peer link. * @NL80211_ATTR_MPATH_NEXT_HOP: MAC address of the next hop for a mesh path. * @NL80211_ATTR_MPATH_INFO: information about a mesh_path, part of mesh path * info given for %NL80211_CMD_GET_MPATH, nested attribute described at @@ -879,7 +883,9 @@ enum nl80211_commands { * See &enum nl80211_key_default_types. * * @NL80211_ATTR_MESH_SETUP: Optional mesh setup parameters. These cannot be - * changed once the mesh is active. + * changed once the mesh is active. + * @NL80211_ATTR_MESH_CONFIG: Mesh configuration parameters, a nested attribute + * containing attributes from &enum nl80211_meshconf_params. * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -1225,8 +1231,6 @@ enum nl80211_rate_info { * @NL80211_STA_INFO_INACTIVE_TIME: time since last activity (u32, msecs) * @NL80211_STA_INFO_RX_BYTES: total received bytes (u32, from this station) * @NL80211_STA_INFO_TX_BYTES: total transmitted bytes (u32, to this station) - * @__NL80211_STA_INFO_AFTER_LAST: internal - * @NL80211_STA_INFO_MAX: highest possible station info attribute * @NL80211_STA_INFO_SIGNAL: signal strength of last received PPDU (u8, dBm) * @NL80211_STA_INFO_TX_BITRATE: current unicast tx rate, nested attribute * containing info as possible, see &enum nl80211_sta_info_txrate. @@ -1236,6 +1240,11 @@ enum nl80211_rate_info { * @NL80211_STA_INFO_TX_RETRIES: total retries (u32, to this station) * @NL80211_STA_INFO_TX_FAILED: total failed packets (u32, to this station) * @NL80211_STA_INFO_SIGNAL_AVG: signal strength average (u8, dBm) + * @NL80211_STA_INFO_LLID: the station's mesh LLID + * @NL80211_STA_INFO_PLID: the station's mesh PLID + * @NL80211_STA_INFO_PLINK_STATE: peer link state for the station + * @__NL80211_STA_INFO_AFTER_LAST: internal + * @NL80211_STA_INFO_MAX: highest possible station info attribute */ enum nl80211_sta_info { __NL80211_STA_INFO_INVALID, @@ -1626,7 +1635,7 @@ enum nl80211_mntr_flags { * @NL80211_MESHCONF_HWMP_NET_DIAM_TRVS_TIME: The interval of time (in TUs) * that it takes for an HWMP information element to propagate across the mesh * - * @NL80211_MESHCONF_ROOTMODE: whether root mode is enabled or not + * @NL80211_MESHCONF_HWMP_ROOTMODE: whether root mode is enabled or not * * @NL80211_MESHCONF_ELEMENT_TTL: specifies the value of TTL field set at a * source mesh point for path selection elements. @@ -1678,6 +1687,7 @@ enum nl80211_meshconf_params { * element that vendors will use to identify the path selection methods and * metrics in use. * + * @NL80211_MESH_SETUP_ATTR_MAX: highest possible mesh setup attribute number * @__NL80211_MESH_SETUP_ATTR_AFTER_LAST: Internal use */ enum nl80211_mesh_setup_params { -- cgit v1.1 From 92ed1a76ca31774eb27de14b2215841367c68056 Mon Sep 17 00:00:00 2001 From: Peter Korsgaard Date: Mon, 10 Jan 2011 22:11:23 +0100 Subject: i2c: Add generic I2C multiplexer using GPIO API Add an i2c mux driver providing access to i2c bus segments using a hardware MUX sitting on a master bus and controlled through gpio pins. E.G. something like: ---------- ---------- Bus segment 1 - - - - - | | SCL/SDA | |-------------- | | | |------------| | | | | | Bus segment 2 | | | Linux | GPIO 1..N | MUX |--------------- Devices | |------------| | | | | | | | Bus segment M | | | |---------------| | ---------- ---------- - - - - - SCL/SDA of the master I2C bus is multiplexed to bus segment 1..M according to the settings of the GPIO pins 1..N. Signed-off-by: Peter Korsgaard Signed-off-by: Jean Delvare --- include/linux/gpio-i2cmux.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 include/linux/gpio-i2cmux.h (limited to 'include') diff --git a/include/linux/gpio-i2cmux.h b/include/linux/gpio-i2cmux.h new file mode 100644 index 0000000..4a333bb --- /dev/null +++ b/include/linux/gpio-i2cmux.h @@ -0,0 +1,38 @@ +/* + * gpio-i2cmux interface to platform code + * + * Peter Korsgaard + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _LINUX_GPIO_I2CMUX_H +#define _LINUX_GPIO_I2CMUX_H + +/* MUX has no specific idle mode */ +#define GPIO_I2CMUX_NO_IDLE ((unsigned)-1) + +/** + * struct gpio_i2cmux_platform_data - Platform-dependent data for gpio-i2cmux + * @parent: Parent I2C bus adapter number + * @base_nr: Base I2C bus number to number adapters from or zero for dynamic + * @values: Array of bitmasks of GPIO settings (low/high) for each + * position + * @n_values: Number of multiplexer positions (busses to instantiate) + * @gpios: Array of GPIO numbers used to control MUX + * @n_gpios: Number of GPIOs used to control MUX + * @idle: Bitmask to write to MUX when idle or GPIO_I2CMUX_NO_IDLE if not used + */ +struct gpio_i2cmux_platform_data { + int parent; + int base_nr; + const unsigned *values; + int n_values; + const unsigned *gpios; + int n_gpios; + unsigned idle; +}; + +#endif /* _LINUX_GPIO_I2CMUX_H */ -- cgit v1.1 From 0cc43a1806f078f7fd414850d8f1f1761696e4af Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Mon, 10 Jan 2011 22:11:23 +0100 Subject: i2c: Constify i2c_client where possible Helper functions for I2C and SMBus transactions don't modify the i2c_client that is passed to them, so it can be marked const. Signed-off-by: Jean Delvare --- include/linux/i2c.h | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 56cfe23..903576d 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -57,9 +57,10 @@ struct i2c_board_info; * transmit an arbitrary number of messages without interruption. * @count must be be less than 64k since msg.len is u16. */ -extern int i2c_master_send(struct i2c_client *client, const char *buf, +extern int i2c_master_send(const struct i2c_client *client, const char *buf, + int count); +extern int i2c_master_recv(const struct i2c_client *client, char *buf, int count); -extern int i2c_master_recv(struct i2c_client *client, char *buf, int count); /* Transfer num messages. */ @@ -78,23 +79,25 @@ extern s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, /* Now follow the 'nice' access routines. These also document the calling conventions of i2c_smbus_xfer. */ -extern s32 i2c_smbus_read_byte(struct i2c_client *client); -extern s32 i2c_smbus_write_byte(struct i2c_client *client, u8 value); -extern s32 i2c_smbus_read_byte_data(struct i2c_client *client, u8 command); -extern s32 i2c_smbus_write_byte_data(struct i2c_client *client, +extern s32 i2c_smbus_read_byte(const struct i2c_client *client); +extern s32 i2c_smbus_write_byte(const struct i2c_client *client, u8 value); +extern s32 i2c_smbus_read_byte_data(const struct i2c_client *client, + u8 command); +extern s32 i2c_smbus_write_byte_data(const struct i2c_client *client, u8 command, u8 value); -extern s32 i2c_smbus_read_word_data(struct i2c_client *client, u8 command); -extern s32 i2c_smbus_write_word_data(struct i2c_client *client, +extern s32 i2c_smbus_read_word_data(const struct i2c_client *client, + u8 command); +extern s32 i2c_smbus_write_word_data(const struct i2c_client *client, u8 command, u16 value); /* Returns the number of read bytes */ -extern s32 i2c_smbus_read_block_data(struct i2c_client *client, +extern s32 i2c_smbus_read_block_data(const struct i2c_client *client, u8 command, u8 *values); -extern s32 i2c_smbus_write_block_data(struct i2c_client *client, +extern s32 i2c_smbus_write_block_data(const struct i2c_client *client, u8 command, u8 length, const u8 *values); /* Returns the number of read bytes */ -extern s32 i2c_smbus_read_i2c_block_data(struct i2c_client *client, +extern s32 i2c_smbus_read_i2c_block_data(const struct i2c_client *client, u8 command, u8 length, u8 *values); -extern s32 i2c_smbus_write_i2c_block_data(struct i2c_client *client, +extern s32 i2c_smbus_write_i2c_block_data(const struct i2c_client *client, u8 command, u8 length, const u8 *values); #endif /* I2C */ -- cgit v1.1 From c599bd6b9ac8926b03e6bf332a8c14ae2ffb43a3 Mon Sep 17 00:00:00 2001 From: Mike Frysinger Date: Mon, 10 Jan 2011 02:54:32 +0000 Subject: netdev: bfin_mac: let boards set vlan masks Signed-off-by: Mike Frysinger Signed-off-by: David S. Miller --- include/linux/bfin_mac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bfin_mac.h b/include/linux/bfin_mac.h index 904dec7..a69554e 100644 --- a/include/linux/bfin_mac.h +++ b/include/linux/bfin_mac.h @@ -24,6 +24,7 @@ struct bfin_mii_bus_platform_data { const unsigned short *mac_peripherals; int phy_mode; unsigned int phy_mask; + unsigned short vlan1_mask, vlan2_mask; }; #endif -- cgit v1.1 From facb4edc1e0e849ea98e147a821e60d6d6272c0a Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 10 Jan 2011 04:06:58 +0000 Subject: phonet: some signedness bugs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Dan Rosenberg pointed out that there were some signed comparison bugs in the phonet protocol. http://marc.info/?l=full-disclosure&m=129424528425330&w=2 The problem is that we check for array overflows but "protocol" is signed and we don't check for array underflows. If you have already have CAP_SYS_ADMIN then you could use the bugs to get root, or someone could cause an oops by mistake. Signed-off-by: Dan Carpenter Acked-by: Rémi Denis-Courmont Signed-off-by: David S. Miller --- include/net/phonet/phonet.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/phonet/phonet.h b/include/net/phonet/phonet.h index d5df797..5395e09 100644 --- a/include/net/phonet/phonet.h +++ b/include/net/phonet/phonet.h @@ -107,8 +107,8 @@ struct phonet_protocol { int sock_type; }; -int phonet_proto_register(int protocol, struct phonet_protocol *pp); -void phonet_proto_unregister(int protocol, struct phonet_protocol *pp); +int phonet_proto_register(unsigned int protocol, struct phonet_protocol *pp); +void phonet_proto_unregister(unsigned int protocol, struct phonet_protocol *pp); int phonet_sysctl_init(void); void phonet_sysctl_exit(void); -- cgit v1.1 From 36909ea43814cba34f7c921e99cba33d770a54e1 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Sun, 9 Jan 2011 19:36:31 +0000 Subject: net: Add alloc_netdev_mqs function Added alloc_netdev_mqs function which allows the number of transmit and receive queues to be specified independenty. alloc_netdev_mq was changed to a macro to call the new function. Also added alloc_etherdev_mqs with same purpose. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 4 +++- include/linux/netdevice.h | 10 +++++++--- 2 files changed, 10 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index f16a010..bec8b82 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -48,8 +48,10 @@ extern int eth_validate_addr(struct net_device *dev); -extern struct net_device *alloc_etherdev_mq(int sizeof_priv, unsigned int queue_count); +extern struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs, + unsigned int rxqs); #define alloc_etherdev(sizeof_priv) alloc_etherdev_mq(sizeof_priv, 1) +#define alloc_etherdev_mq(sizeof_priv, count) alloc_etherdev_mqs(sizeof_priv, count, count) /** * is_zero_ether_addr - Determine if give Ethernet address is all zeros. diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index de2bfe6..be4957c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2191,11 +2191,15 @@ static inline void netif_addr_unlock_bh(struct net_device *dev) extern void ether_setup(struct net_device *dev); /* Support for loadable net-drivers */ -extern struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, +extern struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, void (*setup)(struct net_device *), - unsigned int queue_count); + unsigned int txqs, unsigned int rxqs); #define alloc_netdev(sizeof_priv, name, setup) \ - alloc_netdev_mq(sizeof_priv, name, setup, 1) + alloc_netdev_mqs(sizeof_priv, name, setup, 1, 1) + +#define alloc_netdev_mq(sizeof_priv, name, setup, count) \ + alloc_netdev_mqs(sizeof_priv, name, setup, count, count) + extern int register_netdev(struct net_device *dev); extern void unregister_netdev(struct net_device *dev); -- cgit v1.1 From bfe0d0298f2a67d94d58c39ea904a999aeeb7c3c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 9 Jan 2011 08:30:54 +0000 Subject: net_sched: factorize qdisc stats handling HTB takes into account skb is segmented in stats updates. Generalize this to all schedulers. They should use qdisc_bstats_update() helper instead of manipulating bstats.bytes and bstats.packets Add bstats_update() helper too for classes that use gnet_stats_basic_packed fields. Note : Right now, TCQ_F_CAN_BYPASS shortcurt can be taken only if no stab is setup on qdisc. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sch_generic.h | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 0af57eb..e9eee99 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -207,7 +207,7 @@ static inline int qdisc_qlen(struct Qdisc *q) return q->q.qlen; } -static inline struct qdisc_skb_cb *qdisc_skb_cb(struct sk_buff *skb) +static inline struct qdisc_skb_cb *qdisc_skb_cb(const struct sk_buff *skb) { return (struct qdisc_skb_cb *)skb->cb; } @@ -394,7 +394,7 @@ static inline bool qdisc_tx_is_noop(const struct net_device *dev) return true; } -static inline unsigned int qdisc_pkt_len(struct sk_buff *skb) +static inline unsigned int qdisc_pkt_len(const struct sk_buff *skb) { return qdisc_skb_cb(skb)->pkt_len; } @@ -426,10 +426,18 @@ static inline int qdisc_enqueue_root(struct sk_buff *skb, struct Qdisc *sch) return qdisc_enqueue(skb, sch) & NET_XMIT_MASK; } -static inline void __qdisc_update_bstats(struct Qdisc *sch, unsigned int len) + +static inline void bstats_update(struct gnet_stats_basic_packed *bstats, + const struct sk_buff *skb) +{ + bstats->bytes += qdisc_pkt_len(skb); + bstats->packets += skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1; +} + +static inline void qdisc_bstats_update(struct Qdisc *sch, + const struct sk_buff *skb) { - sch->bstats.bytes += len; - sch->bstats.packets++; + bstats_update(&sch->bstats, skb); } static inline int __qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch, @@ -437,7 +445,7 @@ static inline int __qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch, { __skb_queue_tail(list, skb); sch->qstats.backlog += qdisc_pkt_len(skb); - __qdisc_update_bstats(sch, qdisc_pkt_len(skb)); + qdisc_bstats_update(sch, skb); return NET_XMIT_SUCCESS; } -- cgit v1.1 From 545ecdc3b3a2fe0b54a3053bf8bf85321bbca7da Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Sat, 8 Jan 2011 13:57:12 +0000 Subject: arp: allow to invalidate specific ARP entries IPv4 over firewire needs to be able to remove ARP entries from the ARP cache that belong to nodes that are removed, because IPv4 over firewire uses ARP packets for private information about nodes. This information becomes invalid as soon as node drops off the bus and when it reconnects, its only possible to start talking to it after it responded to an ARP packet. But ARP cache prevents such packets from being sent. Signed-off-by: Maxim Levitsky Signed-off-by: David S. Miller --- include/net/arp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/arp.h b/include/net/arp.h index f4cf6ce..91f0568 100644 --- a/include/net/arp.h +++ b/include/net/arp.h @@ -25,5 +25,6 @@ extern struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, const unsigned char *src_hw, const unsigned char *target_hw); extern void arp_xmit(struct sk_buff *skb); +int arp_invalidate(struct net_device *dev, __be32 ip); #endif /* _ARP_H */ -- cgit v1.1 From 925268a06dc2b1ff7bfcc37419a6827a0e739639 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 11 Jan 2011 16:44:01 +0900 Subject: memory hotplug: one more lock on memory hotplug Now, memory_hotplug_(un)lock() is used for add/remove/offline pages for avoiding races with hibernation. But this should be held in online_pages(), too. It seems asymmetric. There are cases where one has to avoid a race with memory hotplug notifier and his own local code, and hotplug v.s. hotplug. This will add a generic solution for avoiding races. In other view, having lock here has no big impacts. online pages is tend to be done by udev script at el against each memory section one by one. Then, it's better to have lock here, too. Cc: # 2.6.37 Reviewed-by: Christoph Lameter Acked-by: David Rientjes Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Pekka Enberg --- include/linux/memory_hotplug.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 31c237a..12b9eb5 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -161,6 +161,12 @@ extern void register_page_bootmem_info_node(struct pglist_data *pgdat); extern void put_page_bootmem(struct page *page); #endif +/* + * Lock for memory hotplug guarantees 1) all callbacks for memory hotplug + * notifier will be called under this. 2) offline/online/add/remove memory + * will not run simultaneously. + */ + void lock_memory_hotplug(void); void unlock_memory_hotplug(void); -- cgit v1.1 From 357f54d6b38252737116a6d631f6ac28ded018ed Mon Sep 17 00:00:00 2001 From: Andy Adamson Date: Tue, 14 Dec 2010 10:11:57 -0500 Subject: NFS fix the setting of exchange id flag Indicate support for referrals. Do not set any PNFS roles. Check the flags returned by the server for validity. Do not use exchange flags from an old client ID instance when recovering a client ID. Update the EXCHID4_FLAG_XXX set to RFC 5661. Signed-off-by: Andy Adamson Signed-off-by: Trond Myklebust --- include/linux/nfs4.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 4925b22..9b46300 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -111,9 +111,13 @@ #define EXCHGID4_FLAG_SUPP_MOVED_REFER 0x00000001 #define EXCHGID4_FLAG_SUPP_MOVED_MIGR 0x00000002 +#define EXCHGID4_FLAG_BIND_PRINC_STATEID 0x00000100 + #define EXCHGID4_FLAG_USE_NON_PNFS 0x00010000 #define EXCHGID4_FLAG_USE_PNFS_MDS 0x00020000 #define EXCHGID4_FLAG_USE_PNFS_DS 0x00040000 +#define EXCHGID4_FLAG_MASK_PNFS 0x00070000 + #define EXCHGID4_FLAG_UPD_CONFIRMED_REC_A 0x40000000 #define EXCHGID4_FLAG_CONFIRMED_R 0x80000000 /* @@ -121,8 +125,8 @@ * they're set in the argument or response, have separate * invalid flag masks for arg (_A) and resp (_R). */ -#define EXCHGID4_FLAG_MASK_A 0x40070003 -#define EXCHGID4_FLAG_MASK_R 0x80070003 +#define EXCHGID4_FLAG_MASK_A 0x40070103 +#define EXCHGID4_FLAG_MASK_R 0x80070103 #define SEQ4_STATUS_CB_PATH_DOWN 0x00000001 #define SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRING 0x00000002 -- cgit v1.1 From f07745325cbd93afc5d8bcf7539a063d33134075 Mon Sep 17 00:00:00 2001 From: Ian Campbell Date: Mon, 9 Feb 2009 12:05:49 -0800 Subject: xen: define gnttab_set_map_op/unmap_op Impact: hypercall definitions These functions populate the gnttab data structures used by the granttab map and unmap ops and are used in the backend drivers. Originally xen-unstable.hg 9625:c3bb51c443a7 [ Include Stefano's fix for phys_addr_t ] Signed-off-by: Ian Campbell Signed-off-by: Stefano Stabellini Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Konrad Rzeszutek Wilk --- include/xen/grant_table.h | 39 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 38 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index 9a73170..1821aa1 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -37,10 +37,16 @@ #ifndef __ASM_GNTTAB_H__ #define __ASM_GNTTAB_H__ -#include +#include + +#include #include + +#include #include +#include + /* NR_GRANT_FRAMES must be less than or equal to that configured in Xen */ #define NR_GRANT_FRAMES 4 @@ -107,6 +113,37 @@ void gnttab_grant_foreign_access_ref(grant_ref_t ref, domid_t domid, void gnttab_grant_foreign_transfer_ref(grant_ref_t, domid_t domid, unsigned long pfn); +static inline void +gnttab_set_map_op(struct gnttab_map_grant_ref *map, phys_addr_t addr, + uint32_t flags, grant_ref_t ref, domid_t domid) +{ + if (flags & GNTMAP_contains_pte) + map->host_addr = addr; + else if (xen_feature(XENFEAT_auto_translated_physmap)) + map->host_addr = __pa(addr); + else + map->host_addr = addr; + + map->flags = flags; + map->ref = ref; + map->dom = domid; +} + +static inline void +gnttab_set_unmap_op(struct gnttab_unmap_grant_ref *unmap, phys_addr_t addr, + uint32_t flags, grant_handle_t handle) +{ + if (flags & GNTMAP_contains_pte) + unmap->host_addr = addr; + else if (xen_feature(XENFEAT_auto_translated_physmap)) + unmap->host_addr = __pa(addr); + else + unmap->host_addr = addr; + + unmap->handle = handle; + unmap->dev_bus_addr = 0; +} + int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes, unsigned long max_nr_gframes, struct grant_entry **__shared); -- cgit v1.1 From ab31523c2fcac557226bac72cbdf5fafe01f9a26 Mon Sep 17 00:00:00 2001 From: Gerd Hoffmann Date: Tue, 14 Dec 2010 18:40:46 +0000 Subject: xen/gntdev: allow usermode to map granted pages The gntdev driver allows usermode to map granted pages from other domains. This is typically used to implement a Xen backend driver in user mode. Signed-off-by: Gerd Hoffmann Signed-off-by: Stefano Stabellini Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Konrad Rzeszutek Wilk --- include/xen/gntdev.h | 119 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 119 insertions(+) create mode 100644 include/xen/gntdev.h (limited to 'include') diff --git a/include/xen/gntdev.h b/include/xen/gntdev.h new file mode 100644 index 0000000..eb23f41 --- /dev/null +++ b/include/xen/gntdev.h @@ -0,0 +1,119 @@ +/****************************************************************************** + * gntdev.h + * + * Interface to /dev/xen/gntdev. + * + * Copyright (c) 2007, D G Murray + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation; or, when distributed + * separately from the Linux kernel or incorporated into other + * software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef __LINUX_PUBLIC_GNTDEV_H__ +#define __LINUX_PUBLIC_GNTDEV_H__ + +struct ioctl_gntdev_grant_ref { + /* The domain ID of the grant to be mapped. */ + uint32_t domid; + /* The grant reference of the grant to be mapped. */ + uint32_t ref; +}; + +/* + * Inserts the grant references into the mapping table of an instance + * of gntdev. N.B. This does not perform the mapping, which is deferred + * until mmap() is called with @index as the offset. + */ +#define IOCTL_GNTDEV_MAP_GRANT_REF \ +_IOC(_IOC_NONE, 'G', 0, sizeof(struct ioctl_gntdev_map_grant_ref)) +struct ioctl_gntdev_map_grant_ref { + /* IN parameters */ + /* The number of grants to be mapped. */ + uint32_t count; + uint32_t pad; + /* OUT parameters */ + /* The offset to be used on a subsequent call to mmap(). */ + uint64_t index; + /* Variable IN parameter. */ + /* Array of grant references, of size @count. */ + struct ioctl_gntdev_grant_ref refs[1]; +}; + +/* + * Removes the grant references from the mapping table of an instance of + * of gntdev. N.B. munmap() must be called on the relevant virtual address(es) + * before this ioctl is called, or an error will result. + */ +#define IOCTL_GNTDEV_UNMAP_GRANT_REF \ +_IOC(_IOC_NONE, 'G', 1, sizeof(struct ioctl_gntdev_unmap_grant_ref)) +struct ioctl_gntdev_unmap_grant_ref { + /* IN parameters */ + /* The offset was returned by the corresponding map operation. */ + uint64_t index; + /* The number of pages to be unmapped. */ + uint32_t count; + uint32_t pad; +}; + +/* + * Returns the offset in the driver's address space that corresponds + * to @vaddr. This can be used to perform a munmap(), followed by an + * UNMAP_GRANT_REF ioctl, where no state about the offset is retained by + * the caller. The number of pages that were allocated at the same time as + * @vaddr is returned in @count. + * + * N.B. Where more than one page has been mapped into a contiguous range, the + * supplied @vaddr must correspond to the start of the range; otherwise + * an error will result. It is only possible to munmap() the entire + * contiguously-allocated range at once, and not any subrange thereof. + */ +#define IOCTL_GNTDEV_GET_OFFSET_FOR_VADDR \ +_IOC(_IOC_NONE, 'G', 2, sizeof(struct ioctl_gntdev_get_offset_for_vaddr)) +struct ioctl_gntdev_get_offset_for_vaddr { + /* IN parameters */ + /* The virtual address of the first mapped page in a range. */ + uint64_t vaddr; + /* OUT parameters */ + /* The offset that was used in the initial mmap() operation. */ + uint64_t offset; + /* The number of pages mapped in the VM area that begins at @vaddr. */ + uint32_t count; + uint32_t pad; +}; + +/* + * Sets the maximum number of grants that may mapped at once by this gntdev + * instance. + * + * N.B. This must be called before any other ioctl is performed on the device. + */ +#define IOCTL_GNTDEV_SET_MAX_GRANTS \ +_IOC(_IOC_NONE, 'G', 3, sizeof(struct ioctl_gntdev_set_max_grants)) +struct ioctl_gntdev_set_max_grants { + /* IN parameter */ + /* The maximum number of grants that may be mapped at once. */ + uint32_t count; +}; + +#endif /* __LINUX_PUBLIC_GNTDEV_H__ */ -- cgit v1.1 From 289b777eac19c811b474593b4d2fd14e46340c23 Mon Sep 17 00:00:00 2001 From: Stefano Stabellini Date: Fri, 10 Dec 2010 14:54:44 +0000 Subject: xen: introduce gnttab_map_refs and gnttab_unmap_refs gnttab_map_refs maps some grant refs and uses the new m2p override to set a proper m2p mapping for the granted pages. gnttab_unmap_refs unmaps the granted refs and removes th mappings from the m2p override. Signed-off-by: Stefano Stabellini Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Konrad Rzeszutek Wilk --- include/xen/grant_table.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index 1821aa1..b1fab6b 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -155,4 +155,9 @@ unsigned int gnttab_max_grant_frames(void); #define gnttab_map_vaddr(map) ((void *)(map.host_virt_addr)) +int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, + struct page **pages, unsigned int count); +int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, + struct page **pages, unsigned int count); + #endif /* __ASM_GNTTAB_H__ */ -- cgit v1.1 From 1d1bc8f2074f0b728dfca2a3c16f2f5a3f298ffc Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Mon, 4 Oct 2010 23:12:59 -0400 Subject: nfsd4: support BIND_CONN_TO_SESSION Basic xdr and processing for BIND_CONN_TO_SESSION. This adds a connection to the list of connections associated with a session. Signed-off-by: J. Bruce Fields --- include/linux/nfs4.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 26afa30..a591893 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -65,6 +65,9 @@ #define NFS4_CDFC4_FORE 0x1 #define NFS4_CDFC4_BACK 0x2 +#define NFS4_CDFC4_BOTH 0x3 +#define NFS4_CDFC4_FORE_OR_BOTH 0x3 +#define NFS4_CDFC4_BACK_OR_BOTH 0x7 #define NFS4_SET_TO_SERVER_TIME 0 #define NFS4_SET_TO_CLIENT_TIME 1 -- cgit v1.1 From d75faea330dbd1873c9094e9926ae306590c0998 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Tue, 30 Nov 2010 19:15:01 -0500 Subject: rpc: move sk_bc_xprt to svc_xprt This seems obviously transport-level information even if it's currently used only by the server socket code. Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_xprt.h | 1 + include/linux/sunrpc/svcsock.h | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index c8f81da..7ad9751 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -79,6 +79,7 @@ struct svc_xprt { struct list_head xpt_users; /* callbacks on free */ struct net *xpt_net; + struct rpc_xprt *xpt_bc_xprt; /* NFSv4.1 backchannel */ }; static inline void unregister_xpt_user(struct svc_xprt *xpt, struct svc_xpt_user *u) diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index 1b353a7..04dba23 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -28,7 +28,6 @@ struct svc_sock { /* private TCP part */ u32 sk_reclen; /* length of record */ u32 sk_tcplen; /* current read length */ - struct rpc_xprt *sk_bc_xprt; /* NFSv4.1 backchannel xprt */ }; /* -- cgit v1.1 From f0418aa4b1103f959d64dc18273efa04ee0140e9 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Wed, 8 Dec 2010 13:48:19 -0500 Subject: rpc: allow xprt_class->setup to return a preexisting xprt This allows us to reuse the xprt associated with a server connection if one has already been set up. Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 89d10d2..bef0f53 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -321,6 +321,7 @@ void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie); #define XPRT_CLOSING (6) #define XPRT_CONNECTION_ABORT (7) #define XPRT_CONNECTION_CLOSE (8) +#define XPRT_INITIALIZED (9) static inline void xprt_set_connected(struct rpc_xprt *xprt) { -- cgit v1.1 From 0d2689c0f054f6a8bf3115d6386bd9c2d65dc44b Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Fri, 7 Jan 2011 23:44:32 +0100 Subject: HID: add feature_mapping callback Currently hid doesn't export the features it knows to the specific modules. Some information can be really important in such features: MosArt and Cypress devices are by default not in a multitouch mode. We have to send the value 2 on the right feature. This patch exports to the module the features report so they can find the right feature to set up the correct mode. Signed-off-by: Benjamin Tissoires Acked-by: Henrik Rydberg Signed-off-by: Jiri Kosina --- include/linux/hid.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/hid.h b/include/linux/hid.h index bb0f56f..96bd792 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -593,6 +593,7 @@ struct hid_usage_id { * @report_fixup: called before report descriptor parsing (NULL means nop) * @input_mapping: invoked on input registering before mapping an usage * @input_mapped: invoked on input registering after mapping an usage + * @feature_mapping: invoked on feature registering * @suspend: invoked on suspend (NULL means nop) * @resume: invoked on resume if device was not reset (NULL means nop) * @reset_resume: invoked on resume if device was reset (NULL means nop) @@ -636,6 +637,9 @@ struct hid_driver { int (*input_mapped)(struct hid_device *hdev, struct hid_input *hidinput, struct hid_field *field, struct hid_usage *usage, unsigned long **bit, int *max); + void (*feature_mapping)(struct hid_device *hdev, + struct hid_input *hidinput, struct hid_field *field, + struct hid_usage *usage); #ifdef CONFIG_PM int (*suspend)(struct hid_device *hdev, pm_message_t message); int (*resume)(struct hid_device *hdev); -- cgit v1.1 From 281054ac8dfc083442c571be44f1c5b9821812ae Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Fri, 7 Jan 2011 23:45:11 +0100 Subject: HID: set HID_MAX_FIELD at 128 Stantums multitouch panels sends more than 64 reports and this results in not being able to handle all the touches given by this device. This patch is required to be able to include Stantum panels in the unified hid-multitouch driver. Signed-off-by: Benjamin Tissoires Acked-by: Henrik Rydberg Signed-off-by: Jiri Kosina --- include/linux/hid.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/hid.h b/include/linux/hid.h index 96bd792..1ebc6e3 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -402,7 +402,7 @@ struct hid_field { __u16 dpad; /* dpad input code */ }; -#define HID_MAX_FIELDS 64 +#define HID_MAX_FIELDS 128 struct hid_report { struct list_head list; -- cgit v1.1 From e44f391187495e0deaf7b9f0077e94f270837d1a Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Tue, 11 Jan 2011 08:06:19 +0000 Subject: ah: update maximum truncated ICV length For SHA256, RFC4868 requires to truncate ICV length to 128 bits, hence MAX_AH_AUTH_LEN should be updated to 16. Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/net/ah.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ah.h b/include/net/ah.h index f0129f7..be7798d 100644 --- a/include/net/ah.h +++ b/include/net/ah.h @@ -4,7 +4,7 @@ #include /* This is the maximum truncated ICV length that we know of. */ -#define MAX_AH_AUTH_LEN 12 +#define MAX_AH_AUTH_LEN 16 struct crypto_ahash; -- cgit v1.1 From 2f46e07995734a363608e974a82fd05d5b610750 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 11 Jan 2011 23:55:51 +0100 Subject: netfilter: ebtables: make broute table work again broute table init hook sets up the "br_should_route_hook" pointer, which then gets called from br_input. commit a386f99025f13b32502fe5dedf223c20d7283826 (bridge: add proper RCU annotation to should_route_hook) introduced a typedef, and then changed this to: br_should_route_hook_t *rhook; [..] rhook = rcu_dereference(br_should_route_hook); if (*rhook(skb)) problem is that "br_should_route_hook" contains the address of the function, so calling *rhook() results in kernel panic. Signed-off-by: Florian Westphal Acked-by: Eric Dumazet Signed-off-by: Pablo Neira Ayuso --- include/linux/if_bridge.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index f7e73c3..dd3f201 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -103,7 +103,7 @@ struct __fdb_entry { extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *)); -typedef int (*br_should_route_hook_t)(struct sk_buff *skb); +typedef int br_should_route_hook_t(struct sk_buff *skb); extern br_should_route_hook_t __rcu *br_should_route_hook; #endif -- cgit v1.1 From 4cb18728709683c91a5f6f8d5f337bfb498b089a Mon Sep 17 00:00:00 2001 From: "R.Durgadoss" Date: Wed, 27 Oct 2010 03:33:29 +0530 Subject: thermal: Add event notification to thermal framework This patch adds event notification support to the generic thermal sysfs framework in the kernel. The notification is in the form of a netlink event. Signed-off-by: R.Durgadoss Signed-off-by: Len Brown --- include/linux/thermal.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 1de8b9e..7846449 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -127,6 +127,37 @@ struct thermal_zone_device { struct thermal_hwmon_attr temp_crit; /* hwmon sys attr */ #endif }; +/* Adding event notification support elements */ +#define THERMAL_GENL_FAMILY_NAME "thermal_event" +#define THERMAL_GENL_VERSION 0x01 +#define THERMAL_GENL_MCAST_GROUP_NAME "thermal_mc_group" + +enum events { + THERMAL_AUX0, + THERMAL_AUX1, + THERMAL_CRITICAL, + THERMAL_DEV_FAULT, +}; + +struct thermal_genl_event { + u32 orig; + enum events event; +}; +/* attributes of thermal_genl_family */ +enum { + THERMAL_GENL_ATTR_UNSPEC, + THERMAL_GENL_ATTR_EVENT, + __THERMAL_GENL_ATTR_MAX, +}; +#define THERMAL_GENL_ATTR_MAX (__THERMAL_GENL_ATTR_MAX - 1) + +/* commands supported by the thermal_genl_family */ +enum { + THERMAL_GENL_CMD_UNSPEC, + THERMAL_GENL_CMD_EVENT, + __THERMAL_GENL_CMD_MAX, +}; +#define THERMAL_GENL_CMD_MAX (__THERMAL_GENL_CMD_MAX - 1) struct thermal_zone_device *thermal_zone_device_register(char *, int, void *, struct @@ -146,5 +177,6 @@ struct thermal_cooling_device *thermal_cooling_device_register(char *, void *, thermal_cooling_device_ops *); void thermal_cooling_device_unregister(struct thermal_cooling_device *); +extern int generate_netlink_event(u32 orig, enum events event); #endif /* __THERMAL_H__ */ -- cgit v1.1 From 50a88cb7eddb971077ae7dff76b116747c12c371 Mon Sep 17 00:00:00 2001 From: Jekyll Lai Date: Tue, 11 Jan 2011 21:53:55 -0800 Subject: Input: add SW_ROTATE_LOCK switch type This switch is used to signal that user want to disable screen transitions from portrait to landscape mode and back. Signed-off-by: Jekyll Lai Signed-off-by: Alan Cox Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/input.h b/include/linux/input.h index 6c407e5..4bdacad 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -775,6 +775,7 @@ struct input_keymap_entry { #define SW_CAMERA_LENS_COVER 0x09 /* set = lens covered */ #define SW_KEYPAD_SLIDE 0x0a /* set = keypad slide out */ #define SW_FRONT_PROXIMITY 0x0b /* set = front proximity sensor active */ +#define SW_ROTATE_LOCK 0x0c /* set = rotate locked/disabled */ #define SW_MAX 0x0f #define SW_CNT (SW_MAX+1) -- cgit v1.1 From af585b921e5d1e919947c4b1164b59507fe7cd7b Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Thu, 14 Oct 2010 11:22:46 +0200 Subject: KVM: Halt vcpu if page it tries to access is swapped out If a guest accesses swapped out memory do not swap it in from vcpu thread context. Schedule work to do swapping and put vcpu into halted state instead. Interrupts will still be delivered to the guest and if interrupt will cause reschedule guest will continue to run another task. [avi: remove call to get_user_pages_noio(), nacked by Linus; this makes everything synchrnous again] Acked-by: Rik van Riel Signed-off-by: Gleb Natapov Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 31 ++++++++++++++++ include/trace/events/kvm.h | 90 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 121 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index a055742..e56acc7 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -40,6 +40,7 @@ #define KVM_REQ_KICK 9 #define KVM_REQ_DEACTIVATE_FPU 10 #define KVM_REQ_EVENT 11 +#define KVM_REQ_APF_HALT 12 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 @@ -74,6 +75,26 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, struct kvm_io_device *dev); +#ifdef CONFIG_KVM_ASYNC_PF +struct kvm_async_pf { + struct work_struct work; + struct list_head link; + struct list_head queue; + struct kvm_vcpu *vcpu; + struct mm_struct *mm; + gva_t gva; + unsigned long addr; + struct kvm_arch_async_pf arch; + struct page *page; + bool done; +}; + +void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu); +void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu); +int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, + struct kvm_arch_async_pf *arch); +#endif + struct kvm_vcpu { struct kvm *kvm; #ifdef CONFIG_PREEMPT_NOTIFIERS @@ -104,6 +125,15 @@ struct kvm_vcpu { gpa_t mmio_phys_addr; #endif +#ifdef CONFIG_KVM_ASYNC_PF + struct { + u32 queued; + struct list_head queue; + struct list_head done; + spinlock_t lock; + } async_pf; +#endif + struct kvm_vcpu_arch arch; }; @@ -302,6 +332,7 @@ void kvm_set_page_accessed(struct page *page); pfn_t hva_to_pfn_atomic(struct kvm *kvm, unsigned long addr); pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn); +pfn_t gfn_to_pfn_async(struct kvm *kvm, gfn_t gfn, bool *async); pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); pfn_t gfn_to_pfn_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn); diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index 6dd3a51..a78a5e5 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -185,6 +185,96 @@ TRACE_EVENT(kvm_age_page, __entry->referenced ? "YOUNG" : "OLD") ); +#ifdef CONFIG_KVM_ASYNC_PF +TRACE_EVENT( + kvm_try_async_get_page, + TP_PROTO(bool async, u64 pfn), + TP_ARGS(async, pfn), + + TP_STRUCT__entry( + __field(__u64, pfn) + ), + + TP_fast_assign( + __entry->pfn = (!async) ? pfn : (u64)-1; + ), + + TP_printk("pfn %#llx", __entry->pfn) +); + +TRACE_EVENT( + kvm_async_pf_not_present, + TP_PROTO(u64 gva), + TP_ARGS(gva), + + TP_STRUCT__entry( + __field(__u64, gva) + ), + + TP_fast_assign( + __entry->gva = gva; + ), + + TP_printk("gva %#llx not present", __entry->gva) +); + +TRACE_EVENT( + kvm_async_pf_ready, + TP_PROTO(u64 gva), + TP_ARGS(gva), + + TP_STRUCT__entry( + __field(__u64, gva) + ), + + TP_fast_assign( + __entry->gva = gva; + ), + + TP_printk("gva %#llx ready", __entry->gva) +); + +TRACE_EVENT( + kvm_async_pf_completed, + TP_PROTO(unsigned long address, struct page *page, u64 gva), + TP_ARGS(address, page, gva), + + TP_STRUCT__entry( + __field(unsigned long, address) + __field(pfn_t, pfn) + __field(u64, gva) + ), + + TP_fast_assign( + __entry->address = address; + __entry->pfn = page ? page_to_pfn(page) : 0; + __entry->gva = gva; + ), + + TP_printk("gva %#llx address %#lx pfn %#llx", __entry->gva, + __entry->address, __entry->pfn) +); + +TRACE_EVENT( + kvm_async_pf_doublefault, + TP_PROTO(u64 gva, u64 gfn), + TP_ARGS(gva, gfn), + + TP_STRUCT__entry( + __field(u64, gva) + __field(u64, gfn) + ), + + TP_fast_assign( + __entry->gva = gva; + __entry->gfn = gfn; + ), + + TP_printk("gva = %#llx, gfn = %#llx", __entry->gva, __entry->gfn) +); + +#endif + #endif /* _TRACE_KVM_MAIN_H */ /* This part must be outside protection */ -- cgit v1.1 From 49c7754ce57063b819b01eb8a4290841ad0886c4 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Mon, 18 Oct 2010 15:22:23 +0200 Subject: KVM: Add memory slot versioning and use it to provide fast guest write interface Keep track of memslots changes by keeping generation number in memslots structure. Provide kvm_write_guest_cached() function that skips gfn_to_hva() translation if memslots was not changed since previous invocation. Acked-by: Rik van Riel Signed-off-by: Gleb Natapov Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 7 +++++++ include/linux/kvm_types.h | 7 +++++++ 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index e56acc7..e674820 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -199,6 +199,7 @@ struct kvm_irq_routing_table {}; struct kvm_memslots { int nmemslots; + u64 generation; struct kvm_memory_slot memslots[KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS]; }; @@ -352,12 +353,18 @@ int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, int offset, int len); int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, unsigned long len); +int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, + void *data, unsigned long len); +int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, + gpa_t gpa); int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len); int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len); struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); +void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot, + gfn_t gfn); void kvm_vcpu_block(struct kvm_vcpu *vcpu); void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu); diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 7ac0d4e..fa7cc72 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -67,4 +67,11 @@ struct kvm_lapic_irq { u32 dest_id; }; +struct gfn_to_hva_cache { + u64 generation; + gpa_t gpa; + unsigned long hva; + struct kvm_memory_slot *memslot; +}; + #endif /* __KVM_TYPES_H__ */ -- cgit v1.1 From 344d9588a9df06182684168be4f1408b55c7da3e Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Thu, 14 Oct 2010 11:22:50 +0200 Subject: KVM: Add PV MSR to enable asynchronous page faults delivery. Guest enables async PF vcpu functionality using this MSR. Reviewed-by: Rik van Riel Signed-off-by: Gleb Natapov Signed-off-by: Marcelo Tosatti --- include/linux/kvm.h | 1 + include/linux/kvm_host.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/kvm.h b/include/linux/kvm.h index 919ae53..ea2dc1a 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -540,6 +540,7 @@ struct kvm_ppc_pvinfo { #endif #define KVM_CAP_PPC_GET_PVINFO 57 #define KVM_CAP_PPC_IRQ_LEVEL 58 +#define KVM_CAP_ASYNC_PF 59 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index e674820..ee4314e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -93,6 +93,7 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu); void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu); int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, struct kvm_arch_async_pf *arch); +int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); #endif struct kvm_vcpu { -- cgit v1.1 From 7c90705bf2a373aa238661bdb6446f27299ef489 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Thu, 14 Oct 2010 11:22:53 +0200 Subject: KVM: Inject asynchronous page fault into a PV guest if page is swapped out. Send async page fault to a PV guest if it accesses swapped out memory. Guest will choose another task to run upon receiving the fault. Allow async page fault injection only when guest is in user mode since otherwise guest may be in non-sleepable context and will not be able to reschedule. Vcpu will be halted if guest will fault on the same page again or if vcpu executes kernel code. Acked-by: Rik van Riel Signed-off-by: Gleb Natapov Signed-off-by: Marcelo Tosatti --- include/trace/events/kvm.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index a78a5e5..9c2cc6a 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -204,34 +204,39 @@ TRACE_EVENT( TRACE_EVENT( kvm_async_pf_not_present, - TP_PROTO(u64 gva), - TP_ARGS(gva), + TP_PROTO(u64 token, u64 gva), + TP_ARGS(token, gva), TP_STRUCT__entry( + __field(__u64, token) __field(__u64, gva) ), TP_fast_assign( + __entry->token = token; __entry->gva = gva; ), - TP_printk("gva %#llx not present", __entry->gva) + TP_printk("token %#llx gva %#llx not present", __entry->token, + __entry->gva) ); TRACE_EVENT( kvm_async_pf_ready, - TP_PROTO(u64 gva), - TP_ARGS(gva), + TP_PROTO(u64 token, u64 gva), + TP_ARGS(token, gva), TP_STRUCT__entry( + __field(__u64, token) __field(__u64, gva) ), TP_fast_assign( + __entry->token = token; __entry->gva = gva; ), - TP_printk("gva %#llx ready", __entry->gva) + TP_printk("token %#llx gva %#llx ready", __entry->token, __entry->gva) ); TRACE_EVENT( -- cgit v1.1 From 3a37898d507794cfc68a092303e02651d3f01308 Mon Sep 17 00:00:00 2001 From: Lin Ming Date: Mon, 13 Dec 2010 13:36:15 +0800 Subject: ACPICA: Rename some function and variable names Some function and variable names are renamed to be consistent with ACPICA code base. acpi_raw_enable_gpe -> acpi_ev_add_gpe_reference acpi_raw_disable_gpe -> acpi_ev_remove_gpe_reference acpi_gpe_can_wake -> acpi_setup_gpe_for_wake acpi_gpe_wakeup -> acpi_set_gpe_wake_mask acpi_update_gpes -> acpi_update_all_gpes acpi_all_gpes_initialized -> acpi_gbl_all_gpes_initialized acpi_handler_info -> acpi_gpe_handler_info ... Signed-off-by: Lin Ming Signed-off-by: Len Brown --- include/acpi/acpixf.h | 6 +++--- include/acpi/actypes.h | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 53b7cfd..5f8ccf1 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -292,11 +292,11 @@ acpi_status acpi_enable_gpe(acpi_handle gpe_device, u32 gpe_number); acpi_status acpi_disable_gpe(acpi_handle gpe_device, u32 gpe_number); -acpi_status acpi_gpe_can_wake(acpi_handle gpe_device, u32 gpe_number); +acpi_status acpi_setup_gpe_for_wake(acpi_handle gpe_device, u32 gpe_number); acpi_status acpi_clear_gpe(acpi_handle gpe_device, u32 gpe_number); -acpi_status acpi_gpe_wakeup(acpi_handle gpe_device, u32 gpe_number, u8 action); +acpi_status acpi_set_gpe_wake_mask(acpi_handle gpe_device, u32 gpe_number, u8 action); acpi_status acpi_get_gpe_status(acpi_handle gpe_device, @@ -315,7 +315,7 @@ acpi_install_gpe_block(acpi_handle gpe_device, acpi_status acpi_remove_gpe_block(acpi_handle gpe_device); -acpi_status acpi_update_gpes(void); +acpi_status acpi_update_all_gpes(void); /* * Resource interfaces diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index 2b134b6..e738939 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -656,11 +656,11 @@ typedef u32 acpi_event_status; #define ACPI_GPE_MAX 0xFF #define ACPI_NUM_GPE 256 -/* Actions for acpi_gpe_wakeup, acpi_hw_low_set_gpe */ +/* Actions for acpi_set_gpe_wake_mask, acpi_hw_low_set_gpe */ #define ACPI_GPE_ENABLE 0 #define ACPI_GPE_DISABLE 1 -#define ACPI_GPE_COND_ENABLE 2 +#define ACPI_GPE_CONDITIONAL_ENABLE 2 /* * GPE info flags - Per GPE -- cgit v1.1 From 8b6cd8ad18def34bfc5045b2a0234329bf94cf78 Mon Sep 17 00:00:00 2001 From: Lin Ming Date: Mon, 13 Dec 2010 13:38:46 +0800 Subject: ACPICA: New GPE handler callback definition The new GPE handler callback has 2 additional parameters, gpe_device and gpe_number. typedef u32 (*acpi_gpe_handler) (acpi_handle gpe_device, u32 gpe_number, void *context); Signed-off-by: Lin Ming Signed-off-by: Len Brown --- include/acpi/acpixf.h | 4 ++-- include/acpi/actypes.h | 3 +++ 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 5f8ccf1..b806e56 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -258,11 +258,11 @@ acpi_remove_address_space_handler(acpi_handle device, acpi_status acpi_install_gpe_handler(acpi_handle gpe_device, u32 gpe_number, - u32 type, acpi_event_handler address, void *context); + u32 type, acpi_gpe_handler address, void *context); acpi_status acpi_remove_gpe_handler(acpi_handle gpe_device, - u32 gpe_number, acpi_event_handler address); + u32 gpe_number, acpi_gpe_handler address); #ifdef ACPI_FUTURE_USAGE acpi_status acpi_install_exception_handler(acpi_exception_handler handler); diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index e738939..b9575ad 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -897,6 +897,9 @@ typedef void typedef u32(*acpi_event_handler) (void *context); typedef +u32 (*acpi_gpe_handler) (acpi_handle gpe_device, u32 gpe_number, void *context); + +typedef void (*acpi_notify_handler) (acpi_handle device, u32 value, void *context); typedef -- cgit v1.1 From bba63a296ffab20e08d9e8252d2f0d99050ac859 Mon Sep 17 00:00:00 2001 From: Lin Ming Date: Mon, 13 Dec 2010 13:39:17 +0800 Subject: ACPICA: Implicit notify support This feature provides an automatic device notification for wake devices when a wakeup GPE occurs and there is no corresponding GPE method or handler. Rather than ignoring such a GPE, an implicit AML Notify operation is performed on the parent device object. This feature is not part of the ACPI specification and is provided for Windows compatibility only. Signed-off-by: Lin Ming Signed-off-by: Len Brown --- include/acpi/acpixf.h | 6 ++++-- include/acpi/actypes.h | 37 +++++++++++++++++++++---------------- 2 files changed, 25 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index b806e56..9de6a17 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -292,10 +292,12 @@ acpi_status acpi_enable_gpe(acpi_handle gpe_device, u32 gpe_number); acpi_status acpi_disable_gpe(acpi_handle gpe_device, u32 gpe_number); -acpi_status acpi_setup_gpe_for_wake(acpi_handle gpe_device, u32 gpe_number); - acpi_status acpi_clear_gpe(acpi_handle gpe_device, u32 gpe_number); +acpi_status +acpi_setup_gpe_for_wake(acpi_handle parent_device, + acpi_handle gpe_device, u32 gpe_number); + acpi_status acpi_set_gpe_wake_mask(acpi_handle gpe_device, u32 gpe_number, u8 action); acpi_status diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index b9575ad..d7274ee 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -664,25 +664,26 @@ typedef u32 acpi_event_status; /* * GPE info flags - Per GPE - * +-------+---+-+-+ - * | 7:4 |3:2|1|0| - * +-------+---+-+-+ - * | | | | - * | | | +--- Interrupt type: edge or level triggered - * | | +----- GPE can wake the system - * | +-------- Type of dispatch:to method, handler, or none - * +-------------- + * +-------+-+-+---+ + * | 7:4 |3|2|1:0| + * +-------+-+-+---+ + * | | | | + * | | | +-- Type of dispatch:to method, handler, notify, or none + * | | +----- Interrupt type: edge or level triggered + * | +------- Is a Wake GPE + * +------------ */ -#define ACPI_GPE_XRUPT_TYPE_MASK (u8) 0x01 -#define ACPI_GPE_LEVEL_TRIGGERED (u8) 0x01 -#define ACPI_GPE_EDGE_TRIGGERED (u8) 0x00 +#define ACPI_GPE_DISPATCH_NONE (u8) 0x00 +#define ACPI_GPE_DISPATCH_METHOD (u8) 0x01 +#define ACPI_GPE_DISPATCH_HANDLER (u8) 0x02 +#define ACPI_GPE_DISPATCH_NOTIFY (u8) 0x03 +#define ACPI_GPE_DISPATCH_MASK (u8) 0x03 -#define ACPI_GPE_CAN_WAKE (u8) 0x02 +#define ACPI_GPE_LEVEL_TRIGGERED (u8) 0x04 +#define ACPI_GPE_EDGE_TRIGGERED (u8) 0x00 +#define ACPI_GPE_XRUPT_TYPE_MASK (u8) 0x04 -#define ACPI_GPE_DISPATCH_MASK (u8) 0x0C -#define ACPI_GPE_DISPATCH_HANDLER (u8) 0x04 -#define ACPI_GPE_DISPATCH_METHOD (u8) 0x08 -#define ACPI_GPE_DISPATCH_NOT_USED (u8) 0x00 +#define ACPI_GPE_CAN_WAKE (u8) 0x08 /* * Flags for GPE and Lock interfaces @@ -954,6 +955,10 @@ u32 (*acpi_interface_handler) (acpi_string interface_name, u32 supported); #define ACPI_INTERRUPT_NOT_HANDLED 0x00 #define ACPI_INTERRUPT_HANDLED 0x01 +/* GPE handler return values */ + +#define ACPI_REENABLE_GPE 0x80 + /* Length of 32-bit EISAID values when converted back to a string */ #define ACPI_EISAID_STRING_SIZE 8 /* Includes null terminator */ -- cgit v1.1 From a0fcdb237fcd4eaa7e5009b28ef5be07415f287d Mon Sep 17 00:00:00 2001 From: Lin Ming Date: Mon, 13 Dec 2010 13:39:26 +0800 Subject: ACPICA: Global event handler The global event handler is called whenever a general purpose or fixed ACPI event occurs. Also update Linux OSL to collect events counter with global event handler. Signed-off-by: Lin Ming Signed-off-by: Len Brown --- include/acpi/acpixf.h | 4 ++++ include/acpi/actypes.h | 8 ++++++++ 2 files changed, 12 insertions(+) (limited to 'include') diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 9de6a17..e8142d5 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -229,6 +229,10 @@ acpi_status acpi_install_initialization_handler(acpi_init_handler handler, u32 function); acpi_status +acpi_install_global_event_handler(ACPI_GBL_EVENT_HANDLER handler, + void *context); + +acpi_status acpi_install_fixed_event_handler(u32 acpi_event, acpi_event_handler handler, void *context); diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index d7274ee..939a431 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -895,6 +895,14 @@ typedef void /* * Various handlers and callback procedures */ +typedef +void (*ACPI_GBL_EVENT_HANDLER) (u32 event_type, + acpi_handle device, + u32 event_number, void *context); + +#define ACPI_EVENT_TYPE_GPE 0 +#define ACPI_EVENT_TYPE_FIXED 1 + typedef u32(*acpi_event_handler) (void *context); typedef -- cgit v1.1 From 1ae5ec903f71c0ffa583ec54d17415892036ee18 Mon Sep 17 00:00:00 2001 From: Lin Ming Date: Mon, 27 Dec 2010 09:07:43 +0800 Subject: ACPICA: Update version to 20101209 Version 20101209. Signed-off-by: Bob Moore Signed-off-by: Lin Ming Signed-off-by: Len Brown --- include/acpi/acpixf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index e8142d5..241b8a0 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -47,7 +47,7 @@ /* Current ACPICA subsystem version in YYYYMMDD format */ -#define ACPI_CA_VERSION 0x20101013 +#define ACPI_CA_VERSION 0x20101209 #include "actypes.h" #include "actbl.h" -- cgit v1.1 From 612819c3c6e67bac8fceaa7cc402f13b1b63f7e4 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Fri, 22 Oct 2010 14:18:18 -0200 Subject: KVM: propagate fault r/w information to gup(), allow read-only memory As suggested by Andrea, pass r/w error code to gup(), upgrading read fault to writable if host pte allows it. Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ee4314e..462b982 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -334,8 +334,11 @@ void kvm_set_page_accessed(struct page *page); pfn_t hva_to_pfn_atomic(struct kvm *kvm, unsigned long addr); pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn); -pfn_t gfn_to_pfn_async(struct kvm *kvm, gfn_t gfn, bool *async); +pfn_t gfn_to_pfn_async(struct kvm *kvm, gfn_t gfn, bool *async, + bool write_fault, bool *writable); pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); +pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, + bool *writable); pfn_t gfn_to_pfn_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn); int memslot_id(struct kvm *kvm, gfn_t gfn); -- cgit v1.1 From 64be5007066173d11a4635eedd57d41a3b3a7027 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Sun, 24 Oct 2010 16:49:08 +0200 Subject: KVM: x86: trace "exit to userspace" event Add tracepoint for userspace exit. Signed-off-by: Gleb Natapov Signed-off-by: Marcelo Tosatti --- include/trace/events/kvm.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include') diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index 9c2cc6a..c86f4e8 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -6,6 +6,36 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm +#define ERSN(x) { KVM_EXIT_##x, "KVM_EXIT_" #x } + +#define kvm_trace_exit_reason \ + ERSN(UNKNOWN), ERSN(EXCEPTION), ERSN(IO), ERSN(HYPERCALL), \ + ERSN(DEBUG), ERSN(HLT), ERSN(MMIO), ERSN(IRQ_WINDOW_OPEN), \ + ERSN(SHUTDOWN), ERSN(FAIL_ENTRY), ERSN(INTR), ERSN(SET_TPR), \ + ERSN(TPR_ACCESS), ERSN(S390_SIEIC), ERSN(S390_RESET), ERSN(DCR),\ + ERSN(NMI), ERSN(INTERNAL_ERROR), ERSN(OSI) + +TRACE_EVENT(kvm_userspace_exit, + TP_PROTO(__u32 reason, int errno), + TP_ARGS(reason, errno), + + TP_STRUCT__entry( + __field( __u32, reason ) + __field( int, errno ) + ), + + TP_fast_assign( + __entry->reason = reason; + __entry->errno = errno; + ), + + TP_printk("reason %s (%d)", + __entry->errno < 0 ? + (__entry->errno == -EINTR ? "restart" : "error") : + __print_symbolic(__entry->reason, kvm_trace_exit_reason), + __entry->errno < 0 ? -__entry->errno : __entry->reason) +); + #if defined(__KVM_HAVE_IOAPIC) TRACE_EVENT(kvm_set_irq, TP_PROTO(unsigned int gsi, int level, int irq_source_id), -- cgit v1.1 From 515a01279a187415322a80736800a7d6325876ab Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Wed, 27 Oct 2010 18:23:54 +0900 Subject: KVM: pre-allocate one more dirty bitmap to avoid vmalloc() Currently x86's kvm_vm_ioctl_get_dirty_log() needs to allocate a bitmap by vmalloc() which will be used in the next logging and this has been causing bad effect to VGA and live-migration: vmalloc() consumes extra systime, triggers tlb flush, etc. This patch resolves this issue by pre-allocating one more bitmap and switching between two bitmaps during dirty logging. Performance improvement: I measured performance for the case of VGA update by trace-cmd. The result was 1.5 times faster than the original one. In the case of live migration, the improvement ratio depends on the workload and the guest memory size. In general, the larger the memory size is the more benefits we get. Note: This does not change other architectures's logic but the allocation size becomes twice. This will increase the actual memory consumption only when the new size changes the number of pages allocated by vmalloc(). Signed-off-by: Takuya Yoshikawa Signed-off-by: Fernando Luis Vazquez Cao Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 462b982..bcf71c7 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -150,6 +150,7 @@ struct kvm_memory_slot { unsigned long flags; unsigned long *rmap; unsigned long *dirty_bitmap; + unsigned long *dirty_bitmap_head; struct { unsigned long rmap_pde; int write_count; -- cgit v1.1 From c9b263d2be9c535b410f6617710534f798bf0ff0 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 1 Nov 2010 16:58:43 +0800 Subject: KVM: fix tracing kvm_try_async_get_page Tracing 'async' and *pfn is useless, since 'async' is always true, and '*pfn' is always "fault_pfn' We can trace 'gva' and 'gfn' instead, it can help us to see the life-cycle of an async_pf Signed-off-by: Xiao Guangrong Signed-off-by: Marcelo Tosatti --- include/trace/events/kvm.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index c86f4e8..d94d6c3 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -218,18 +218,20 @@ TRACE_EVENT(kvm_age_page, #ifdef CONFIG_KVM_ASYNC_PF TRACE_EVENT( kvm_try_async_get_page, - TP_PROTO(bool async, u64 pfn), - TP_ARGS(async, pfn), + TP_PROTO(u64 gva, u64 gfn), + TP_ARGS(gva, gfn), TP_STRUCT__entry( - __field(__u64, pfn) + __field(u64, gva) + __field(u64, gfn) ), TP_fast_assign( - __entry->pfn = (!async) ? pfn : (u64)-1; + __entry->gva = gva; + __entry->gfn = gfn; ), - TP_printk("pfn %#llx", __entry->pfn) + TP_printk("gva = %#llx, gfn = %#llx", __entry->gva, __entry->gfn) ); TRACE_EVENT( -- cgit v1.1 From 0730388b97d20cc568c25b42b9a23b28959b481f Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 1 Nov 2010 16:59:39 +0800 Subject: KVM: cleanup async_pf tracepoints Use 'DECLARE_EVENT_CLASS' to cleanup async_pf tracepoints Acked-by: Gleb Natapov Signed-off-by: Xiao Guangrong Signed-off-by: Marcelo Tosatti --- include/trace/events/kvm.h | 76 +++++++++++++++++++++------------------------- 1 file changed, 35 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index d94d6c3..46e3cd8 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -216,59 +216,71 @@ TRACE_EVENT(kvm_age_page, ); #ifdef CONFIG_KVM_ASYNC_PF -TRACE_EVENT( - kvm_try_async_get_page, +DECLARE_EVENT_CLASS(kvm_async_get_page_class, + TP_PROTO(u64 gva, u64 gfn), + TP_ARGS(gva, gfn), TP_STRUCT__entry( - __field(u64, gva) + __field(__u64, gva) __field(u64, gfn) - ), + ), TP_fast_assign( __entry->gva = gva; __entry->gfn = gfn; - ), + ), TP_printk("gva = %#llx, gfn = %#llx", __entry->gva, __entry->gfn) ); -TRACE_EVENT( - kvm_async_pf_not_present, +DEFINE_EVENT(kvm_async_get_page_class, kvm_try_async_get_page, + + TP_PROTO(u64 gva, u64 gfn), + + TP_ARGS(gva, gfn) +); + +DEFINE_EVENT(kvm_async_get_page_class, kvm_async_pf_doublefault, + + TP_PROTO(u64 gva, u64 gfn), + + TP_ARGS(gva, gfn) +); + +DECLARE_EVENT_CLASS(kvm_async_pf_nopresent_ready, + TP_PROTO(u64 token, u64 gva), + TP_ARGS(token, gva), TP_STRUCT__entry( __field(__u64, token) __field(__u64, gva) - ), + ), TP_fast_assign( __entry->token = token; __entry->gva = gva; - ), + ), + + TP_printk("token %#llx gva %#llx", __entry->token, __entry->gva) - TP_printk("token %#llx gva %#llx not present", __entry->token, - __entry->gva) ); -TRACE_EVENT( - kvm_async_pf_ready, +DEFINE_EVENT(kvm_async_pf_nopresent_ready, kvm_async_pf_not_present, + TP_PROTO(u64 token, u64 gva), - TP_ARGS(token, gva), - TP_STRUCT__entry( - __field(__u64, token) - __field(__u64, gva) - ), + TP_ARGS(token, gva) +); - TP_fast_assign( - __entry->token = token; - __entry->gva = gva; - ), +DEFINE_EVENT(kvm_async_pf_nopresent_ready, kvm_async_pf_ready, + + TP_PROTO(u64 token, u64 gva), - TP_printk("token %#llx gva %#llx ready", __entry->token, __entry->gva) + TP_ARGS(token, gva) ); TRACE_EVENT( @@ -292,24 +304,6 @@ TRACE_EVENT( __entry->address, __entry->pfn) ); -TRACE_EVENT( - kvm_async_pf_doublefault, - TP_PROTO(u64 gva, u64 gfn), - TP_ARGS(gva, gfn), - - TP_STRUCT__entry( - __field(u64, gva) - __field(u64, gfn) - ), - - TP_fast_assign( - __entry->gva = gva; - __entry->gfn = gfn; - ), - - TP_printk("gva = %#llx, gfn = %#llx", __entry->gva, __entry->gfn) -); - #endif #endif /* _TRACE_KVM_MAIN_H */ -- cgit v1.1 From d89f5eff70a31237ffa1e21c51d23ca532110aea Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Tue, 9 Nov 2010 17:02:49 +0100 Subject: KVM: Clean up vm creation and release IA64 support forces us to abstract the allocation of the kvm structure. But instead of mixing this up with arch-specific initialization and doing the same on destruction, split both steps. This allows to move generic destruction calls into generic code. It also fixes error clean-up on failures of kvm_create_vm for IA64. Signed-off-by: Jan Kiszka Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index bcf71c7..2d63f2c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -16,6 +16,7 @@ #include #include #include +#include #include #include @@ -441,7 +442,19 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); void kvm_free_physmem(struct kvm *kvm); -struct kvm *kvm_arch_create_vm(void); +#ifndef __KVM_HAVE_ARCH_VM_ALLOC +static inline struct kvm *kvm_arch_alloc_vm(void) +{ + return kzalloc(sizeof(struct kvm), GFP_KERNEL); +} + +static inline void kvm_arch_free_vm(struct kvm *kvm) +{ + kfree(kvm); +} +#endif + +int kvm_arch_init_vm(struct kvm *kvm); void kvm_arch_destroy_vm(struct kvm *kvm); void kvm_free_all_assigned_devices(struct kvm *kvm); void kvm_arch_sync_events(struct kvm *kvm); -- cgit v1.1 From 0645211c43df0b96c51e12980066b3227e10b164 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Tue, 16 Nov 2010 22:30:03 +0100 Subject: KVM: Switch assigned device IRQ forwarding to threaded handler This improves the IRQ forwarding for assigned devices: By using the kernel's threaded IRQ scheme, we can get rid of the latency-prone work queue and simplify the code in the same run. Moreover, we no longer have to hold assigned_dev_lock while raising the guest IRQ, which can be a lenghty operation as we may have to iterate over all VCPUs. The lock is now only used for synchronizing masking vs. unmasking of INTx-type IRQs, thus is renames to intx_lock. Acked-by: Alex Williamson Acked-by: Michael S. Tsirkin Signed-off-by: Jan Kiszka Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 2d63f2c..9fe7fef 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -470,16 +470,8 @@ struct kvm_irq_ack_notifier { void (*irq_acked)(struct kvm_irq_ack_notifier *kian); }; -#define KVM_ASSIGNED_MSIX_PENDING 0x1 -struct kvm_guest_msix_entry { - u32 vector; - u16 entry; - u16 flags; -}; - struct kvm_assigned_dev_kernel { struct kvm_irq_ack_notifier ack_notifier; - struct work_struct interrupt_work; struct list_head list; int assigned_dev_id; int host_segnr; @@ -490,13 +482,13 @@ struct kvm_assigned_dev_kernel { bool host_irq_disabled; struct msix_entry *host_msix_entries; int guest_irq; - struct kvm_guest_msix_entry *guest_msix_entries; + struct msix_entry *guest_msix_entries; unsigned long irq_requested_type; int irq_source_id; int flags; struct pci_dev *dev; struct kvm *kvm; - spinlock_t assigned_dev_lock; + spinlock_t intx_lock; }; struct kvm_irq_mask_notifier { -- cgit v1.1 From 1e001d49f9f9a0e3eb72939ad49d9a2c7754e9c1 Mon Sep 17 00:00:00 2001 From: Jan Kiszka Date: Tue, 16 Nov 2010 22:30:04 +0100 Subject: KVM: Refactor IRQ names of assigned devices Cosmetic change, but it helps to correlate IRQs with PCI devices. Acked-by: Alex Williamson Acked-by: Michael S. Tsirkin Signed-off-by: Jan Kiszka Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9fe7fef..4bd663d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -489,6 +489,7 @@ struct kvm_assigned_dev_kernel { struct pci_dev *dev; struct kvm *kvm; spinlock_t intx_lock; + char irq_name[32]; }; struct kvm_irq_mask_notifier { -- cgit v1.1 From bd2b53b20fcd0d6c4c815b54e6d464e34429d3a4 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Thu, 18 Nov 2010 19:09:08 +0200 Subject: KVM: fast-path msi injection with irqfd Store irq routing table pointer in the irqfd object, and use that to inject MSI directly without bouncing out to a kernel thread. While we touch this structure, rearrange irqfd fields to make fastpath better packed for better cache utilization. This also adds some comments about locking rules and rcu usage in code. Some notes on the design: - Use pointer into the rt instead of copying an entry, to make it possible to use rcu, thus side-stepping locking complexities. We also save some memory this way. - Old workqueue code is still used for level irqs. I don't think we DTRT with level anyway, however, it seems easier to keep the code around as it has been thought through and debugged, and fix level later than rip out and re-instate it later. Signed-off-by: Michael S. Tsirkin Acked-by: Marcelo Tosatti Acked-by: Gregory Haskins Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 4bd663d..f17beae 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -240,6 +241,10 @@ struct kvm { struct mutex irq_lock; #ifdef CONFIG_HAVE_KVM_IRQCHIP + /* + * Update side is protected by irq_lock and, + * if configured, irqfds.lock. + */ struct kvm_irq_routing_table __rcu *irq_routing; struct hlist_head mask_notifier_list; struct hlist_head irq_ack_notifier_list; @@ -511,6 +516,8 @@ void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic, unsigned long *deliver_bitmask); #endif int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level); +int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm, + int irq_source_id, int level); void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin); void kvm_register_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); @@ -652,17 +659,26 @@ static inline void kvm_free_irq_routing(struct kvm *kvm) {} void kvm_eventfd_init(struct kvm *kvm); int kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags); void kvm_irqfd_release(struct kvm *kvm); +void kvm_irq_routing_update(struct kvm *, struct kvm_irq_routing_table *); int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args); #else static inline void kvm_eventfd_init(struct kvm *kvm) {} + static inline int kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags) { return -EINVAL; } static inline void kvm_irqfd_release(struct kvm *kvm) {} + +static inline void kvm_irq_routing_update(struct kvm *kvm, + struct kvm_irq_routing_table *irq_rt) +{ + rcu_assign_pointer(kvm->irq_routing, irq_rt); +} + static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) { return -ENOSYS; -- cgit v1.1 From 27923eb19c5d1197bd9d1472abdc2e749f21387a Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Thu, 25 Nov 2010 10:25:44 +0100 Subject: KVM: PPC: Fix compile warning KVM compilation fails with the following warning: include/linux/kvm_host.h: In function 'kvm_irq_routing_update': include/linux/kvm_host.h:679:2: error: 'struct kvm' has no member named 'irq_routing' That function is only used and reasonable to have on systems that implement an in-kernel interrupt chip. PPC doesn't. Fix by #ifdef'ing it out when no irqchip is available. Signed-off-by: Alexander Graf Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f17beae..da0794f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -673,11 +673,13 @@ static inline int kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags) static inline void kvm_irqfd_release(struct kvm *kvm) {} +#ifdef CONFIG_HAVE_KVM_IRQCHIP static inline void kvm_irq_routing_update(struct kvm *kvm, struct kvm_irq_routing_table *irq_rt) { rcu_assign_pointer(kvm->irq_routing, irq_rt); } +#endif static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) { -- cgit v1.1 From a4ee1ca4a36e7857d90ae8c2b85f1bde9a042c10 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Tue, 23 Nov 2010 11:13:00 +0800 Subject: KVM: MMU: delay flush all tlbs on sync_page path Quote from Avi: | I don't think we need to flush immediately; set a "tlb dirty" bit somewhere | that is cleareded when we flush the tlb. kvm_mmu_notifier_invalidate_page() | can consult the bit and force a flush if set. Signed-off-by: Xiao Guangrong Signed-off-by: Marcelo Tosatti --- include/linux/kvm_host.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index da0794f..ac4e83a 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -254,6 +254,7 @@ struct kvm { struct mmu_notifier mmu_notifier; unsigned long mmu_notifier_seq; long mmu_notifier_count; + long tlbs_dirty; #endif }; @@ -382,6 +383,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu); void kvm_resched(struct kvm_vcpu *vcpu); void kvm_load_guest_fpu(struct kvm_vcpu *vcpu); void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); + void kvm_flush_remote_tlbs(struct kvm *kvm); void kvm_reload_remote_mmus(struct kvm *kvm); -- cgit v1.1 From d4dbf470096c51cb4785167ea59fdbdea87ccbe4 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Tue, 7 Dec 2010 12:59:07 +0900 Subject: KVM: MMU: Make the way of accessing lpage_info more generic Large page information has two elements but one of them, write_count, alone is accessed by a helper function. This patch replaces this helper function with more generic one which returns newly named kvm_lpage_info structure and use it to access the other element rmap_pde. Signed-off-by: Takuya Yoshikawa Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ac4e83a..bd0da8f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -146,6 +146,11 @@ struct kvm_vcpu { */ #define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1) +struct kvm_lpage_info { + unsigned long rmap_pde; + int write_count; +}; + struct kvm_memory_slot { gfn_t base_gfn; unsigned long npages; @@ -153,10 +158,7 @@ struct kvm_memory_slot { unsigned long *rmap; unsigned long *dirty_bitmap; unsigned long *dirty_bitmap_head; - struct { - unsigned long rmap_pde; - int write_count; - } *lpage_info[KVM_NR_PAGE_SIZES - 1]; + struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1]; unsigned long userspace_addr; int user_alloc; int id; -- cgit v1.1 From 5c663a1534d27d817e17eed06a83d08f497f9f4f Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Wed, 8 Dec 2010 18:04:51 +0200 Subject: KVM: Fix build error on s390 due to missing tlbs_dirty Make it available for all archs. Signed-off-by: Avi Kivity --- include/linux/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index bd0da8f..b5021db 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -256,8 +256,8 @@ struct kvm { struct mmu_notifier mmu_notifier; unsigned long mmu_notifier_seq; long mmu_notifier_count; - long tlbs_dirty; #endif + long tlbs_dirty; }; /* The guest did something we don't support. */ -- cgit v1.1 From 25eed40720fc9005c63a1f436e5f8a78836c26ff Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 25 Nov 2010 00:09:15 +0100 Subject: ACPI / PM: Add function for updating device power state consistently Add function acpi_bus_update_power() for reading the actual power state of an ACPI device and updating its device->power.state field in such a way that its power resources' reference counters will remain consistent with that field. For this purpose introduce __acpi_bus_set_power() setting the power state of an ACPI device without updating its device->power.state field and make acpi_bus_set_power() and acpi_bus_update_power() use it (acpi_bus_set_power() retains the current behavior for now). Signed-off-by: Rafael J. Wysocki Signed-off-by: Len Brown --- include/acpi/acpi_bus.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 359ef11..5d2c4c5 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -330,6 +330,7 @@ acpi_status acpi_bus_get_status_handle(acpi_handle handle, int acpi_bus_get_status(struct acpi_device *device); int acpi_bus_get_power(acpi_handle handle, int *state); int acpi_bus_set_power(acpi_handle handle, int state); +int acpi_bus_update_power(acpi_handle handle, int *state_p); bool acpi_bus_power_manageable(acpi_handle handle); bool acpi_bus_can_wakeup(acpi_handle handle); #ifdef CONFIG_ACPI_PROC_EVENT -- cgit v1.1 From 488a76c52606199100adf09c8eb7cbedbd94e9d9 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 25 Nov 2010 00:11:24 +0100 Subject: ACPI / Fan: Rework the handling of power resources Use the new function acpi_bus_update_power() for manipulating power resources used by ACPI fan devices, which allows them to be put into the right state during initialization and resume. Consequently, remove the flags.force_power_state field from struct acpi_device, which is not necessary any more. Signed-off-by: Rafael J. Wysocki Signed-off-by: Len Brown --- include/acpi/acpi_bus.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 5d2c4c5..8912580 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -149,8 +149,7 @@ struct acpi_device_flags { u32 power_manageable:1; u32 performance_manageable:1; u32 wake_capable:1; /* Wakeup(_PRW) supported? */ - u32 force_power_state:1; - u32 reserved:22; + u32 reserved:23; }; /* File System */ -- cgit v1.1 From f6767dcf2a4f6e62960912d0affec1e15a246191 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 11 Dec 2010 23:44:39 +0100 Subject: ACPI / PM: Drop acpi_bus_get_power() There are no more users of acpi_bus_get_power(), so it can be dropped. Moreover, it should be dropped, because it modifies the device->power.state field of an ACPI device without updating the reference counters of the device's power resources, which is wrong. Signed-off-by: Rafael J. Wysocki Signed-off-by: Len Brown --- include/acpi/acpi_bus.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 8912580..673a3f4 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -327,7 +327,6 @@ void acpi_bus_data_handler(acpi_handle handle, void *context); acpi_status acpi_bus_get_status_handle(acpi_handle handle, unsigned long long *sta); int acpi_bus_get_status(struct acpi_device *device); -int acpi_bus_get_power(acpi_handle handle, int *state); int acpi_bus_set_power(acpi_handle handle, int state); int acpi_bus_update_power(acpi_handle handle, int *state_p); bool acpi_bus_power_manageable(acpi_handle handle); -- cgit v1.1 From d57d09a480e1db38eeee7629c81289b00f338a15 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 6 Jan 2011 23:41:27 +0100 Subject: ACPI: Drop device flag wake_capable The wake_capable ACPI device flag is not necessary, because it is only used in scan.c for recording the information that _PRW is present for the given device. That information is only used by acpi_add_single_object() to decide whether or not to call acpi_bus_get_wakeup_device_flags(), so the flag may be dropped if the _PRW check is moved to acpi_bus_get_wakeup_device_flags(). Moreover, acpi_bus_get_wakeup_device_flags() always returns 0, so it really should be void. Signed-off-by: Rafael J. Wysocki Signed-off-by: Len Brown --- include/acpi/acpi_bus.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 20b05cd..78ca429 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -148,8 +148,7 @@ struct acpi_device_flags { u32 suprise_removal_ok:1; u32 power_manageable:1; u32 performance_manageable:1; - u32 wake_capable:1; /* Wakeup(_PRW) supported? */ - u32 reserved:23; + u32 reserved:24; }; /* File System */ -- cgit v1.1 From 3a93f2a9f4d8f73d74c0e552feb68a10f778a219 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 10 Nov 2010 14:38:29 +0000 Subject: regulator: Report actual configured voltage to set_voltage() Change the interface used by set_voltage() to report the selected value to the regulator core in terms of a selector used by list_voltage(). This allows the regulator core to know the voltage that was chosen without having to do an explict get_voltage(), which would be much more expensive as it will generally access hardware. Signed-off-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/regulator/driver.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 592cd7c..4275cd4 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -79,7 +79,8 @@ struct regulator_ops { int (*list_voltage) (struct regulator_dev *, unsigned selector); /* get/set regulator voltage */ - int (*set_voltage) (struct regulator_dev *, int min_uV, int max_uV); + int (*set_voltage) (struct regulator_dev *, int min_uV, int max_uV, + unsigned *selector); int (*get_voltage) (struct regulator_dev *); /* get/set regulator current */ -- cgit v1.1 From 02fa3ec01a0df7a8ccc356d8e245a9a1423b3596 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 10 Nov 2010 14:38:30 +0000 Subject: regulator: Add basic trace facilities Provide some basic trace facilities to the regulator API. We generate events on regulator enable, disable and voltage setting over the actual hardware operations (which are assumed to be the expensive ones which require interaction with the actual device). This is intended to facilitate debug of the performance and behaviour with consumers allowing unified traces to be generated including the regulator operations within the context of the other components of the system. For enable we log the explicit delay for the voltage ramp separately to the interaction with the hardware to highlight the time consumed in I/O. We should add a similar delay for voltage changes, though there the relatively small magnitude of the changes in the context of the I/O costs makes it much less critical for most regulators. Only hardware interactions are currently traced as the primary focus is on the performance and synchronisation of actual hardware interactions. Additional tracepoints for debugging of the logical operations can be added later if required. Signed-off-by: Mark Brown Signed-off-by: Liam Girdwood --- include/trace/events/regulator.h | 141 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 141 insertions(+) create mode 100644 include/trace/events/regulator.h (limited to 'include') diff --git a/include/trace/events/regulator.h b/include/trace/events/regulator.h new file mode 100644 index 0000000..37502a7 --- /dev/null +++ b/include/trace/events/regulator.h @@ -0,0 +1,141 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM regulator + +#if !defined(_TRACE_REGULATOR_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_REGULATOR_H + +#include +#include + +/* + * Events which just log themselves and the regulator name for enable/disable + * type tracking. + */ +DECLARE_EVENT_CLASS(regulator_basic, + + TP_PROTO(const char *name), + + TP_ARGS(name), + + TP_STRUCT__entry( + __string( name, name ) + ), + + TP_fast_assign( + __assign_str(name, name); + ), + + TP_printk("name=%s", __get_str(name)) + +); + +DEFINE_EVENT(regulator_basic, regulator_enable, + + TP_PROTO(const char *name), + + TP_ARGS(name) + +); + +DEFINE_EVENT(regulator_basic, regulator_enable_delay, + + TP_PROTO(const char *name), + + TP_ARGS(name) + +); + +DEFINE_EVENT(regulator_basic, regulator_enable_complete, + + TP_PROTO(const char *name), + + TP_ARGS(name) + +); + +DEFINE_EVENT(regulator_basic, regulator_disable, + + TP_PROTO(const char *name), + + TP_ARGS(name) + +); + +DEFINE_EVENT(regulator_basic, regulator_disable_complete, + + TP_PROTO(const char *name), + + TP_ARGS(name) + +); + +/* + * Events that take a range of numerical values, mostly for voltages + * and so on. + */ +DECLARE_EVENT_CLASS(regulator_range, + + TP_PROTO(const char *name, int min, int max), + + TP_ARGS(name, min, max), + + TP_STRUCT__entry( + __string( name, name ) + __field( int, min ) + __field( int, max ) + ), + + TP_fast_assign( + __assign_str(name, name); + __entry->min = min; + __entry->max = max; + ), + + TP_printk("name=%s (%d-%d)", __get_str(name), + (int)__entry->min, (int)__entry->max) +); + +DEFINE_EVENT(regulator_range, regulator_set_voltage, + + TP_PROTO(const char *name, int min, int max), + + TP_ARGS(name, min, max) + +); + + +/* + * Events that take a single value, mostly for readback and refcounts. + */ +DECLARE_EVENT_CLASS(regulator_value, + + TP_PROTO(const char *name, unsigned int val), + + TP_ARGS(name, val), + + TP_STRUCT__entry( + __string( name, name ) + __field( unsigned int, val ) + ), + + TP_fast_assign( + __assign_str(name, name); + __entry->val = val; + ), + + TP_printk("name=%s, val=%u", __get_str(name), + (int)__entry->val) +); + +DEFINE_EVENT(regulator_value, regulator_set_voltage_complete, + + TP_PROTO(const char *name, unsigned int value), + + TP_ARGS(name, value) + +); + +#endif /* _TRACE_POWER_H */ + +/* This part must be outside protection */ +#include -- cgit v1.1 From f8c12fe329c8da9f50d8b2b1183eeaa4d587e747 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 29 Nov 2010 15:55:17 +0000 Subject: regulator: Copy constraints from regulators when initialising them Currently the regulator API uses the constraints structure passed in to the core throughout the lifetime of the object. This means that it is not possible to mark the constraints as __initdata so if the kernel supports many boards the constraints for all of them are kept around throughout the lifetime of the system, consuming memory needlessly. By copying constraints that are actually used we allow the use of __initdata, saving memory when multiple boards are supported. This also means the constraints can be const. Signed-off-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/regulator/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 4275cd4..cce5753 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -192,7 +192,7 @@ struct regulator_dev { }; struct regulator_dev *regulator_register(struct regulator_desc *regulator_desc, - struct device *dev, struct regulator_init_data *init_data, + struct device *dev, const struct regulator_init_data *init_data, void *driver_data); void regulator_unregister(struct regulator_dev *rdev); -- cgit v1.1 From 476c2d83c7ffb2429b2a504fbdb4326fc8a9d0e8 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 10 Dec 2010 17:28:07 +0000 Subject: regulator: Allow drivers to report voltages as selectors Since drivers already have to provide an API for translating selectors into voltages they may as well just report the selector values directly to the core API rather than implement the lookup themselves. The old interface is left in place for now, but may be removed in future. Signed-off-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/regulator/driver.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index cce5753..bf3e653 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -43,6 +43,8 @@ enum regulator_status { * @set_voltage: Set the voltage for the regulator within the range specified. * The driver should select the voltage closest to min_uV. * @get_voltage: Return the currently configured voltage for the regulator. + * @get_voltage_sel: Return the currently configured voltage selector for the + * regulator. * @list_voltage: Return one of the supported voltages, in microvolts; zero * if the selector indicates a voltage that is unusable on this system; * or negative errno. Selectors range from zero to one less than @@ -82,6 +84,7 @@ struct regulator_ops { int (*set_voltage) (struct regulator_dev *, int min_uV, int max_uV, unsigned *selector); int (*get_voltage) (struct regulator_dev *); + int (*get_voltage_sel) (struct regulator_dev *); /* get/set regulator current */ int (*set_current_limit) (struct regulator_dev *, -- cgit v1.1 From cb189b07d57b574cc14382e2130960b0a0193c23 Mon Sep 17 00:00:00 2001 From: Bengt Jonsson Date: Fri, 10 Dec 2010 11:08:40 +0100 Subject: regulators: Moved define for number of regulators in ab8500 The define for number of regulators is moved from ab8500-core to ab8500-regulator so that the regulator driver can be updated independently of ab8500-core. This also changes the platform configuration structure of ab8500-core so that it contains a pointer to the regulator_init_data array plus number of regulators instead of an fixed size array of pointers to regulator_init_data. Signed-off-by: Bengt Jonsson Acked-by: Linus Walleij Acked-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/mfd/ab8500.h | 5 ++--- include/linux/regulator/ab8500.h | 24 +++++++++++++----------- 2 files changed, 15 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/mfd/ab8500.h b/include/linux/mfd/ab8500.h index d63b605..85cf2c2 100644 --- a/include/linux/mfd/ab8500.h +++ b/include/linux/mfd/ab8500.h @@ -99,8 +99,6 @@ #define AB8500_NR_IRQS 104 #define AB8500_NUM_IRQ_REGS 13 -#define AB8500_NUM_REGULATORS 15 - /** * struct ab8500 - ab8500 internal structure * @dev: parent device @@ -145,7 +143,8 @@ struct regulator_init_data; struct ab8500_platform_data { int irq_base; void (*init) (struct ab8500 *); - struct regulator_init_data *regulator[AB8500_NUM_REGULATORS]; + int num_regulator; + struct regulator_init_data *regulator; }; extern int __devinit ab8500_init(struct ab8500 *ab8500); diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h index f509877..6a210f1 100644 --- a/include/linux/regulator/ab8500.h +++ b/include/linux/regulator/ab8500.h @@ -11,15 +11,17 @@ #define __LINUX_MFD_AB8500_REGULATOR_H /* AB8500 regulators */ -#define AB8500_LDO_AUX1 0 -#define AB8500_LDO_AUX2 1 -#define AB8500_LDO_AUX3 2 -#define AB8500_LDO_INTCORE 3 -#define AB8500_LDO_TVOUT 4 -#define AB8500_LDO_AUDIO 5 -#define AB8500_LDO_ANAMIC1 6 -#define AB8500_LDO_ANAMIC2 7 -#define AB8500_LDO_DMIC 8 -#define AB8500_LDO_ANA 9 - +enum ab8500_regulator_id { + AB8500_LDO_AUX1, + AB8500_LDO_AUX2, + AB8500_LDO_AUX3, + AB8500_LDO_INTCORE, + AB8500_LDO_TVOUT, + AB8500_LDO_AUDIO, + AB8500_LDO_ANAMIC1, + AB8500_LDO_ANAMIC2, + AB8500_LDO_DMIC, + AB8500_LDO_ANA, + AB8500_NUM_REGULATORS, +}; #endif -- cgit v1.1 From 57c78e359a35c69eca4c88f107500f74ef7f0acf Mon Sep 17 00:00:00 2001 From: Yong Shen Date: Tue, 14 Dec 2010 14:00:53 +0800 Subject: Change the register name definitions for mc13783 To make mc13783 and mc13892 share code, the register names should be changed to fit the new macro definitions in the comming patch. Signed-off-by: Yong Shen Acked-by: Sascha Hauer Acked-by: Samuel Ortiz Acked-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/mfd/mc13783.h | 67 +++++++++++++++++++++++---------------------- 1 file changed, 34 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/include/linux/mfd/mc13783.h b/include/linux/mfd/mc13783.h index b4c741e..7d0f3d6 100644 --- a/include/linux/mfd/mc13783.h +++ b/include/linux/mfd/mc13783.h @@ -1,4 +1,5 @@ /* + * Copyright 2010 Yong Shen * Copyright 2009-2010 Pengutronix * Uwe Kleine-Koenig * @@ -122,39 +123,39 @@ int mc13783_adc_do_conversion(struct mc13783 *mc13783, unsigned int mode, unsigned int channel, unsigned int *sample); -#define MC13783_SW_SW1A 0 -#define MC13783_SW_SW1B 1 -#define MC13783_SW_SW2A 2 -#define MC13783_SW_SW2B 3 -#define MC13783_SW_SW3 4 -#define MC13783_SW_PLL 5 -#define MC13783_REGU_VAUDIO 6 -#define MC13783_REGU_VIOHI 7 -#define MC13783_REGU_VIOLO 8 -#define MC13783_REGU_VDIG 9 -#define MC13783_REGU_VGEN 10 -#define MC13783_REGU_VRFDIG 11 -#define MC13783_REGU_VRFREF 12 -#define MC13783_REGU_VRFCP 13 -#define MC13783_REGU_VSIM 14 -#define MC13783_REGU_VESIM 15 -#define MC13783_REGU_VCAM 16 -#define MC13783_REGU_VRFBG 17 -#define MC13783_REGU_VVIB 18 -#define MC13783_REGU_VRF1 19 -#define MC13783_REGU_VRF2 20 -#define MC13783_REGU_VMMC1 21 -#define MC13783_REGU_VMMC2 22 -#define MC13783_REGU_GPO1 23 -#define MC13783_REGU_GPO2 24 -#define MC13783_REGU_GPO3 25 -#define MC13783_REGU_GPO4 26 -#define MC13783_REGU_V1 27 -#define MC13783_REGU_V2 28 -#define MC13783_REGU_V3 29 -#define MC13783_REGU_V4 30 -#define MC13783_REGU_PWGT1SPI 31 -#define MC13783_REGU_PWGT2SPI 32 +#define MC13783_REG_SW1A 0 +#define MC13783_REG_SW1B 1 +#define MC13783_REG_SW2A 2 +#define MC13783_REG_SW2B 3 +#define MC13783_REG_SW3 4 +#define MC13783_REG_PLL 5 +#define MC13783_REG_VAUDIO 6 +#define MC13783_REG_VIOHI 7 +#define MC13783_REG_VIOLO 8 +#define MC13783_REG_VDIG 9 +#define MC13783_REG_VGEN 10 +#define MC13783_REG_VRFDIG 11 +#define MC13783_REG_VRFREF 12 +#define MC13783_REG_VRFCP 13 +#define MC13783_REG_VSIM 14 +#define MC13783_REG_VESIM 15 +#define MC13783_REG_VCAM 16 +#define MC13783_REG_VRFBG 17 +#define MC13783_REG_VVIB 18 +#define MC13783_REG_VRF1 19 +#define MC13783_REG_VRF2 20 +#define MC13783_REG_VMMC1 21 +#define MC13783_REG_VMMC2 22 +#define MC13783_REG_GPO1 23 +#define MC13783_REG_GPO2 24 +#define MC13783_REG_GPO3 25 +#define MC13783_REG_GPO4 26 +#define MC13783_REG_V1 27 +#define MC13783_REG_V2 28 +#define MC13783_REG_V3 29 +#define MC13783_REG_V4 30 +#define MC13783_REG_PWGT1SPI 31 +#define MC13783_REG_PWGT2SPI 32 #define MC13783_IRQ_ADCDONE MC13XXX_IRQ_ADCDONE #define MC13783_IRQ_ADCBISDONE MC13XXX_IRQ_ADCBISDONE -- cgit v1.1 From 5e428d5cecc3f109b52e993a1bd91f82137867b3 Mon Sep 17 00:00:00 2001 From: Yong Shen Date: Tue, 14 Dec 2010 14:00:55 +0800 Subject: regulator: support PMIC mc13892 add support for mc13892, tested on mx51 babbage board Signed-off-by: Arnaud Patard Signed-off-by: Yong Shen Acked-by: Sascha Hauer Acked-by: Samuel Ortiz Acked-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/mfd/mc13892.h | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) create mode 100644 include/linux/mfd/mc13892.h (limited to 'include') diff --git a/include/linux/mfd/mc13892.h b/include/linux/mfd/mc13892.h new file mode 100644 index 0000000..a00f2be --- /dev/null +++ b/include/linux/mfd/mc13892.h @@ -0,0 +1,39 @@ +/* + * Copyright 2010 Yong Shen + * + * This program is free software; you can redistribute it and/or modify it under + * the terms of the GNU General Public License version 2 as published by the + * Free Software Foundation. + */ + +#ifndef __LINUX_MFD_MC13892_H +#define __LINUX_MFD_MC13892_H + +#include + +#define MC13892_SW1 0 +#define MC13892_SW2 1 +#define MC13892_SW3 2 +#define MC13892_SW4 3 +#define MC13892_SWBST 4 +#define MC13892_VIOHI 5 +#define MC13892_VPLL 6 +#define MC13892_VDIG 7 +#define MC13892_VSD 8 +#define MC13892_VUSB2 9 +#define MC13892_VVIDEO 10 +#define MC13892_VAUDIO 11 +#define MC13892_VCAM 12 +#define MC13892_VGEN1 13 +#define MC13892_VGEN2 14 +#define MC13892_VGEN3 15 +#define MC13892_VUSB 16 +#define MC13892_GPO1 17 +#define MC13892_GPO2 18 +#define MC13892_GPO3 19 +#define MC13892_GPO4 20 +#define MC13892_PWGT1SPI 21 +#define MC13892_PWGT2SPI 22 +#define MC13892_VCOINCELL 23 + +#endif -- cgit v1.1 From e8eef82b2c652d031bee9dff9762325672f5a1e0 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Sun, 12 Dec 2010 14:36:17 +0000 Subject: regulator: Provide a selector based set_voltage_sel() operation Many regulator drivers implement voltage setting by looping through a table of possible values, normally because the set of available voltages can't be mapped onto selectors with simple calcuation. Factor out these loops by providing a variant of set_voltage() which takes a selector rather than a voltage range as an argument and implementing a loop through the available selectors in the core. This is not going to be suitable for use with all devices as when the regulator voltage can be mapped onto selector values with a simple calculation the linear scan through the available values will be more expensive than just doing the calculation, especially for regulators that provide fine grained voltage control. Signed-off-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/regulator/driver.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index bf3e653..975ae06 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -42,6 +42,8 @@ enum regulator_status { * * @set_voltage: Set the voltage for the regulator within the range specified. * The driver should select the voltage closest to min_uV. + * @set_voltage_sel: Set the voltage for the regulator using the specified + * selector. * @get_voltage: Return the currently configured voltage for the regulator. * @get_voltage_sel: Return the currently configured voltage selector for the * regulator. @@ -83,6 +85,7 @@ struct regulator_ops { /* get/set regulator voltage */ int (*set_voltage) (struct regulator_dev *, int min_uV, int max_uV, unsigned *selector); + int (*set_voltage_sel) (struct regulator_dev *, unsigned selector); int (*get_voltage) (struct regulator_dev *); int (*get_voltage_sel) (struct regulator_dev *); -- cgit v1.1 From 606a25628187ce863b48d43ca42bc0cbe8342de9 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 16 Dec 2010 15:49:36 +0000 Subject: regulator: Add API to re-apply voltage to hardware When cooperating with an external control source the regulator setup may be changed underneath the API. Currently consumers can just redo the regulator_set_voltage() to restore a previously set configuration but provide an explicit API for doing this as optimsations in the regulator_set_voltage() implementation will shortly prevent that. Signed-off-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/regulator/consumer.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index ebd7472..7954f6b 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -154,6 +154,7 @@ int regulator_is_supported_voltage(struct regulator *regulator, int min_uV, int max_uV); int regulator_set_voltage(struct regulator *regulator, int min_uV, int max_uV); int regulator_get_voltage(struct regulator *regulator); +int regulator_sync_voltage(struct regulator *regulator); int regulator_set_current_limit(struct regulator *regulator, int min_uA, int max_uA); int regulator_get_current_limit(struct regulator *regulator); -- cgit v1.1 From 1130e5b3ff4a7f3f54a48d46e9d0d81b47765bd8 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 21 Dec 2010 23:49:31 +0000 Subject: regulator: Add initial per-regulator debugfs support We only expose the use and open counts to userspace, providing a tiny bit of insight into what the API is up to. Signed-off-by: Mark Brown Signed-off-by: Liam Girdwood --- include/linux/regulator/driver.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 975ae06..b8ed16a 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -175,9 +175,9 @@ struct regulator_desc { */ struct regulator_dev { struct regulator_desc *desc; - int use_count; - int open_count; int exclusive; + u32 use_count; + u32 open_count; /* lists we belong to */ struct list_head list; /* list of all regulators */ @@ -195,6 +195,10 @@ struct regulator_dev { struct regulator_dev *supply; /* for tree */ void *reg_data; /* regulator_dev data */ + +#ifdef CONFIG_DEBUG_FS + struct dentry *debugfs; +#endif }; struct regulator_dev *regulator_register(struct regulator_desc *regulator_desc, -- cgit v1.1 From d247632c08c674864d438733280422ddb7130ff8 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Wed, 12 Jan 2011 02:34:59 -0500 Subject: cpuidle: delete NOP CPUIDLE_FLAG_POLL it serves no purpose Signed-off-by: Len Brown --- include/linux/cpuidle.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 1be416b..dee3285 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -48,7 +48,6 @@ struct cpuidle_state { /* Idle State Flags */ #define CPUIDLE_FLAG_TIME_VALID (0x01) /* is residency time measurable? */ #define CPUIDLE_FLAG_CHECK_BM (0x02) /* BM activity will exit state */ -#define CPUIDLE_FLAG_POLL (0x10) /* no latency, no savings */ #define CPUIDLE_FLAG_SHALLOW (0x20) /* low latency, minimal savings */ #define CPUIDLE_FLAG_BALANCED (0x40) /* medium latency, moderate savings */ #define CPUIDLE_FLAG_DEEP (0x80) /* high latency, large savings */ -- cgit v1.1 From 642f11c53f17aee991d97d14e6922172849ef227 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Wed, 12 Jan 2011 02:45:00 -0500 Subject: cpuidle: delete unused CPUIDLE_FLAG_SHALLOW, BALANCED, DEEP definitions Signed-off-by: Len Brown --- include/linux/cpuidle.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index dee3285..c252953 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -48,9 +48,6 @@ struct cpuidle_state { /* Idle State Flags */ #define CPUIDLE_FLAG_TIME_VALID (0x01) /* is residency time measurable? */ #define CPUIDLE_FLAG_CHECK_BM (0x02) /* BM activity will exit state */ -#define CPUIDLE_FLAG_SHALLOW (0x20) /* low latency, minimal savings */ -#define CPUIDLE_FLAG_BALANCED (0x40) /* medium latency, moderate savings */ -#define CPUIDLE_FLAG_DEEP (0x80) /* high latency, large savings */ #define CPUIDLE_FLAG_IGNORE (0x100) /* ignore during this idle period */ #define CPUIDLE_FLAG_TLB_FLUSHED (0x200) /* tlb will be flushed */ -- cgit v1.1 From 956d033fb2eb3f8818260cdf01644bf4dc1a9e33 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Wed, 12 Jan 2011 02:51:20 -0500 Subject: cpuidle: CPUIDLE_FLAG_TLB_FLUSHED is specific to intel_idle Signed-off-by: Len Brown --- include/linux/cpuidle.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index c252953..6be722c 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -49,7 +49,6 @@ struct cpuidle_state { #define CPUIDLE_FLAG_TIME_VALID (0x01) /* is residency time measurable? */ #define CPUIDLE_FLAG_CHECK_BM (0x02) /* BM activity will exit state */ #define CPUIDLE_FLAG_IGNORE (0x100) /* ignore during this idle period */ -#define CPUIDLE_FLAG_TLB_FLUSHED (0x200) /* tlb will be flushed */ #define CPUIDLE_DRIVER_FLAGS_MASK (0xFFFF0000) -- cgit v1.1 From 5392083748a340f68052c0b83a7ce28b10324972 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Wed, 12 Jan 2011 02:56:15 -0500 Subject: cpuidle: CPUIDLE_FLAG_CHECK_BM is omap3_idle specific Signed-off-by: Len Brown --- include/linux/cpuidle.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 6be722c..36719ea 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -47,7 +47,6 @@ struct cpuidle_state { /* Idle State Flags */ #define CPUIDLE_FLAG_TIME_VALID (0x01) /* is residency time measurable? */ -#define CPUIDLE_FLAG_CHECK_BM (0x02) /* BM activity will exit state */ #define CPUIDLE_FLAG_IGNORE (0x100) /* ignore during this idle period */ #define CPUIDLE_DRIVER_FLAGS_MASK (0xFFFF0000) -- cgit v1.1 From 2fc72c7b84002ffb3c66918e2a7b0ee607d8b5aa Mon Sep 17 00:00:00 2001 From: KOVACS Krisztian Date: Wed, 12 Jan 2011 20:25:08 +0100 Subject: netfilter: fix compilation when conntrack is disabled but tproxy is enabled The IPv6 tproxy patches split IPv6 defragmentation off of conntrack, but failed to update the #ifdef stanzas guarding the defragmentation related fields and code in skbuff and conntrack related code in nf_defrag_ipv6.c. This patch adds the required #ifdefs so that IPv6 tproxy can truly be used without connection tracking. Original report: http://marc.info/?l=linux-netdev&m=129010118516341&w=2 Reported-by: Randy Dunlap Acked-by: Randy Dunlap Signed-off-by: KOVACS Krisztian Signed-off-by: Pablo Neira Ayuso --- include/linux/skbuff.h | 15 +++++++++++++++ include/net/netfilter/ipv6/nf_conntrack_ipv6.h | 10 ---------- include/net/netfilter/ipv6/nf_defrag_ipv6.h | 10 ++++++++++ 3 files changed, 25 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 20ec0a64..bf221d6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -255,6 +255,11 @@ typedef unsigned int sk_buff_data_t; typedef unsigned char *sk_buff_data_t; #endif +#if defined(CONFIG_NF_DEFRAG_IPV4) || defined(CONFIG_NF_DEFRAG_IPV4_MODULE) || \ + defined(CONFIG_NF_DEFRAG_IPV6) || defined(CONFIG_NF_DEFRAG_IPV6_MODULE) +#define NET_SKBUFF_NF_DEFRAG_NEEDED 1 +#endif + /** * struct sk_buff - socket buffer * @next: Next buffer in list @@ -362,6 +367,8 @@ struct sk_buff { void (*destructor)(struct sk_buff *skb); #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) struct nf_conntrack *nfct; +#endif +#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED struct sk_buff *nfct_reasm; #endif #ifdef CONFIG_BRIDGE_NETFILTER @@ -2057,6 +2064,8 @@ static inline void nf_conntrack_get(struct nf_conntrack *nfct) if (nfct) atomic_inc(&nfct->use); } +#endif +#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED static inline void nf_conntrack_get_reasm(struct sk_buff *skb) { if (skb) @@ -2085,6 +2094,8 @@ static inline void nf_reset(struct sk_buff *skb) #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_conntrack_put(skb->nfct); skb->nfct = NULL; +#endif +#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED nf_conntrack_put_reasm(skb->nfct_reasm); skb->nfct_reasm = NULL; #endif @@ -2101,6 +2112,8 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src) dst->nfct = src->nfct; nf_conntrack_get(src->nfct); dst->nfctinfo = src->nfctinfo; +#endif +#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED dst->nfct_reasm = src->nfct_reasm; nf_conntrack_get_reasm(src->nfct_reasm); #endif @@ -2114,6 +2127,8 @@ static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_conntrack_put(dst->nfct); +#endif +#ifdef NET_SKBUFF_NF_DEFRAG_NEEDED nf_conntrack_put_reasm(dst->nfct_reasm); #endif #ifdef CONFIG_BRIDGE_NETFILTER diff --git a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h index 1ee717e..a4c9936 100644 --- a/include/net/netfilter/ipv6/nf_conntrack_ipv6.h +++ b/include/net/netfilter/ipv6/nf_conntrack_ipv6.h @@ -7,16 +7,6 @@ extern struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6; extern struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6; extern struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6; -extern int nf_ct_frag6_init(void); -extern void nf_ct_frag6_cleanup(void); -extern struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user); -extern void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb, - struct net_device *in, - struct net_device *out, - int (*okfn)(struct sk_buff *)); - -struct inet_frags_ctl; - #include extern struct ctl_table nf_ct_ipv6_sysctl_table[]; diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h index 94dd54d..fd79c9a 100644 --- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h +++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h @@ -3,4 +3,14 @@ extern void nf_defrag_ipv6_enable(void); +extern int nf_ct_frag6_init(void); +extern void nf_ct_frag6_cleanup(void); +extern struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user); +extern void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb, + struct net_device *in, + struct net_device *out, + int (*okfn)(struct sk_buff *)); + +struct inet_frags_ctl; + #endif /* _NF_DEFRAG_IPV6_H */ -- cgit v1.1 From 6fed05c9c9812b5882bc708f4da4fa8d5df2875c Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 12 Jan 2011 22:03:20 +0100 Subject: ACPI / PM: Fix build problems for !CONFIG_ACPI related to NVS rework The recent rework of the NVS saving/restoring code introduced two build issues for !CONFIG_ACPI, a warning in drivers/acpi/internal.h and an error in arch/x86/kernel/e820.c. Fix them by providing suitable static inline definitions of the relevant functions. Signed-off-by: Rafael J. Wysocki Acked-by: Randy Dunlap Signed-off-by: Len Brown --- include/linux/acpi.h | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index fa7ed6a98..eb176bb 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -254,15 +254,6 @@ void __init acpi_old_suspend_ordering(void); void __init acpi_nvs_nosave(void); #endif /* CONFIG_PM_SLEEP */ -#ifdef CONFIG_ACPI_SLEEP -int suspend_nvs_register(unsigned long start, unsigned long size); -#else -static inline int suspend_nvs_register(unsigned long a, unsigned long b) -{ - return 0; -} -#endif - struct acpi_osc_context { char *uuid_str; /* uuid string */ int rev; @@ -361,4 +352,14 @@ static inline int acpi_table_parse(char *id, return -1; } #endif /* !CONFIG_ACPI */ + +#ifdef CONFIG_ACPI_SLEEP +int suspend_nvs_register(unsigned long start, unsigned long size); +#else +static inline int suspend_nvs_register(unsigned long a, unsigned long b) +{ + return 0; +} +#endif + #endif /*_LINUX_ACPI_H*/ -- cgit v1.1 From da995a8aee044bc5d0847e19e351cd48a2cb8bcc Mon Sep 17 00:00:00 2001 From: Aleksey Senin Date: Thu, 2 Dec 2010 11:44:49 +0000 Subject: IB/mlx4: Handle protocol field in multicast table The newest device firmware stores IB vs. Ethernet protocol in two bits in members_count field of multicast group table (0: Infiniband, 1: Ethernet). When changing the QP members count for a multicast group, it important not to reset this information. When calling multicast attach first time, the protocol type should be specified. In this patch we always set it IB, but in the future we will handle Ethernet too. When looking for a QP, the protocol type shoud be checked too. Signed-off-by: Aleksey Senin Signed-off-by: Roland Dreier --- include/linux/mlx4/device.h | 10 ++++++++-- include/linux/mlx4/driver.h | 6 +----- 2 files changed, 9 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index a7b15bc..0492146 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -144,6 +144,11 @@ enum { MLX4_STAT_RATE_OFFSET = 5 }; +enum mlx4_protocol { + MLX4_PROTOCOL_IB, + MLX4_PROTOCOL_EN, +}; + enum { MLX4_MTT_FLAG_PRESENT = 1 }; @@ -500,8 +505,9 @@ int mlx4_INIT_PORT(struct mlx4_dev *dev, int port); int mlx4_CLOSE_PORT(struct mlx4_dev *dev, int port); int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], - int block_mcast_loopback); -int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16]); + int block_mcast_loopback, enum mlx4_protocol protocol); +int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], + enum mlx4_protocol protocol); int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *index); void mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, int index); diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index f407cd4..e1eebf7 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -34,6 +34,7 @@ #define MLX4_DRIVER_H #include +#include struct mlx4_dev; @@ -44,11 +45,6 @@ enum mlx4_dev_event { MLX4_DEV_EVENT_PORT_REINIT, }; -enum mlx4_protocol { - MLX4_PROTOCOL_IB, - MLX4_PROTOCOL_EN, -}; - struct mlx4_interface { void * (*add) (struct mlx4_dev *dev); void (*remove)(struct mlx4_dev *dev, void *context); -- cgit v1.1 From 6c0f3af72cb1622a66962a1180c36ef8c41be8e2 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Tue, 16 Nov 2010 11:14:34 -0800 Subject: ceph: add dir_layout to inode Add a ceph_dir_layout to the inode, and calculate dentry hash values based on the parent directory's specified dir_hash function. This is needed because the old default Linux dcache hash function is extremely week and leads to a poor distribution of files among dir fragments. Signed-off-by: Sage Weil --- include/linux/ceph/ceph_fs.h | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index c3c74ae..09dcc0c 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -43,6 +43,10 @@ #define CEPH_FEATURE_NOSRCADDR (1<<1) #define CEPH_FEATURE_MONCLOCKCHECK (1<<2) #define CEPH_FEATURE_FLOCK (1<<3) +#define CEPH_FEATURE_SUBSCRIBE2 (1<<4) +#define CEPH_FEATURE_MONNAMES (1<<5) +#define CEPH_FEATURE_RECONNECT_SEQ (1<<6) +#define CEPH_FEATURE_DIRLAYOUTHASH (1<<7) /* @@ -55,10 +59,10 @@ struct ceph_file_layout { __le32 fl_stripe_count; /* over this many objects */ __le32 fl_object_size; /* until objects are this big, then move to new objects */ - __le32 fl_cas_hash; /* 0 = none; 1 = sha256 */ + __le32 fl_cas_hash; /* UNUSED. 0 = none; 1 = sha256 */ /* pg -> disk layout */ - __le32 fl_object_stripe_unit; /* for per-object parity, if any */ + __le32 fl_object_stripe_unit; /* UNUSED. for per-object parity, if any */ /* object -> pg layout */ __le32 fl_pg_preferred; /* preferred primary for pg (-1 for none) */ @@ -69,6 +73,12 @@ struct ceph_file_layout { int ceph_file_layout_is_valid(const struct ceph_file_layout *layout); +struct ceph_dir_layout { + __u8 dl_dir_hash; /* see ceph_hash.h for ids */ + __u8 dl_unused1; + __u16 dl_unused2; + __u32 dl_unused3; +} __attribute__ ((packed)); /* crypto algorithms */ #define CEPH_CRYPTO_NONE 0x0 @@ -457,7 +467,7 @@ struct ceph_mds_reply_inode { struct ceph_timespec rctime; struct ceph_frag_tree_head fragtree; /* (must be at end of struct) */ } __attribute__ ((packed)); -/* followed by frag array, then symlink string, then xattr blob */ +/* followed by frag array, symlink string, dir layout, xattr blob */ /* reply_lease follows dname, and reply_inode */ struct ceph_mds_reply_lease { -- cgit v1.1 From f363e45fd1184219b472ea549cb7e192e24ef4d2 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 3 Jan 2011 14:49:46 +0100 Subject: net/ceph: make ceph_msgr_wq non-reentrant ceph messenger code does a rather complex dancing around multithread workqueue to make sure the same work item isn't executed concurrently on different CPUs. This restriction can be provided by workqueue with WQ_NON_REENTRANT. Make ceph_msgr_wq non-reentrant workqueue with the default concurrency level and remove the QUEUED/BUSY logic. * This removes backoff handling in con_work() but it couldn't reliably block execution of con_work() to begin with - queue_con() can be called after the work started but before BUSY is set. It seems that it was an optimization for a rather cold path and can be safely removed. * The number of concurrent work items is bound by the number of connections and connetions are independent from each other. With the default concurrency level, different connections will be executed independently. Signed-off-by: Tejun Heo Cc: Sage Weil Cc: ceph-devel@vger.kernel.org Signed-off-by: Sage Weil --- include/linux/ceph/messenger.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index a108b42..c3011be 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -110,17 +110,12 @@ struct ceph_msg_pos { /* * ceph_connection state bit flags - * - * QUEUED and BUSY are used together to ensure that only a single - * thread is currently opening, reading or writing data to the socket. */ #define LOSSYTX 0 /* we can close channel or drop messages on errors */ #define CONNECTING 1 #define NEGOTIATING 2 #define KEEPALIVE_PENDING 3 #define WRITE_PENDING 4 /* we have data ready to send */ -#define QUEUED 5 /* there is work queued on this connection */ -#define BUSY 6 /* work is being done */ #define STANDBY 8 /* no outgoing messages, socket closed. we keep * the ceph_connection around to maintain shared * state with the peer. */ -- cgit v1.1 From c8aebb0c9f8c7471643d5f8ba68328de8013005f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 18 Dec 2010 10:22:30 -0500 Subject: per-superblock default ->d_op Signed-off-by: Al Viro --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index f84d992..3e4c274 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1423,6 +1423,7 @@ struct super_block { * generic_show_options() */ char __rcu *s_options; + const struct dentry_operations *s_d_op; /* default d_op for dentries */ }; extern struct timespec current_fs_time(struct super_block *sb); -- cgit v1.1 From 9501e4c48e1561443e1a16c2c9917ec6c63118a4 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 12 Jan 2011 16:25:02 -0500 Subject: switch coda Coda ->d_revalidate() actually checks for root, ->d_delete() is irrelevant. So we can use the same d_op for all coda dentries Signed-off-by: Al Viro --- include/linux/coda_linux.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/coda_linux.h b/include/linux/coda_linux.h index 4ccc59c..490c56b 100644 --- a/include/linux/coda_linux.h +++ b/include/linux/coda_linux.h @@ -27,6 +27,8 @@ extern const struct inode_operations coda_dir_inode_operations; extern const struct inode_operations coda_file_inode_operations; extern const struct inode_operations coda_ioctl_inode_operations; +extern const struct dentry_operations coda_dentry_operations; + extern const struct address_space_operations coda_file_aops; extern const struct address_space_operations coda_symlink_aops; -- cgit v1.1 From 31a203df9c109480fc6d48ba0a68763e89199acb Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 12 Jan 2011 16:36:09 -0500 Subject: take coda-private headers out of include/linux Signed-off-by: Al Viro --- include/linux/coda_cache.h | 22 ---------- include/linux/coda_fs_i.h | 58 -------------------------- include/linux/coda_linux.h | 101 --------------------------------------------- 3 files changed, 181 deletions(-) delete mode 100644 include/linux/coda_cache.h delete mode 100644 include/linux/coda_fs_i.h delete mode 100644 include/linux/coda_linux.h (limited to 'include') diff --git a/include/linux/coda_cache.h b/include/linux/coda_cache.h deleted file mode 100644 index c910b5e..0000000 --- a/include/linux/coda_cache.h +++ /dev/null @@ -1,22 +0,0 @@ -/* Coda filesystem -- Linux Minicache - * - * Copyright (C) 1989 - 1997 Carnegie Mellon University - * - * Carnegie Mellon University encourages users of this software to - * contribute improvements to the Coda project. Contact Peter Braam - * - */ - -#ifndef _CFSNC_HEADER_ -#define _CFSNC_HEADER_ - -/* credential cache */ -void coda_cache_enter(struct inode *inode, int mask); -void coda_cache_clear_inode(struct inode *); -void coda_cache_clear_all(struct super_block *sb); -int coda_cache_check(struct inode *inode, int mask); - -/* for downcalls and attributes and lookups */ -void coda_flag_inode_children(struct inode *inode, int flag); - -#endif /* _CFSNC_HEADER_ */ diff --git a/include/linux/coda_fs_i.h b/include/linux/coda_fs_i.h deleted file mode 100644 index e35071b..0000000 --- a/include/linux/coda_fs_i.h +++ /dev/null @@ -1,58 +0,0 @@ -/* - * coda_fs_i.h - * - * Copyright (C) 1998 Carnegie Mellon University - * - */ - -#ifndef _LINUX_CODA_FS_I -#define _LINUX_CODA_FS_I - -#include -#include -#include -#include - -/* - * coda fs inode data - * c_lock protects accesses to c_flags, c_mapcount, c_cached_epoch, c_uid and - * c_cached_perm. - * vfs_inode is set only when the inode is created and never changes. - * c_fid is set when the inode is created and should be considered immutable. - */ -struct coda_inode_info { - struct CodaFid c_fid; /* Coda identifier */ - u_short c_flags; /* flags (see below) */ - unsigned int c_mapcount; /* nr of times this inode is mapped */ - unsigned int c_cached_epoch; /* epoch for cached permissions */ - vuid_t c_uid; /* fsuid for cached permissions */ - unsigned int c_cached_perm; /* cached access permissions */ - spinlock_t c_lock; - struct inode vfs_inode; -}; - -/* - * coda fs file private data - */ -#define CODA_MAGIC 0xC0DAC0DA -struct coda_file_info { - int cfi_magic; /* magic number */ - struct file *cfi_container; /* container file for this cnode */ - unsigned int cfi_mapcount; /* nr of times this file is mapped */ -}; - -#define CODA_FTOC(file) ((struct coda_file_info *)((file)->private_data)) - -/* flags */ -#define C_VATTR 0x1 /* Validity of vattr in inode */ -#define C_FLUSH 0x2 /* used after a flush */ -#define C_DYING 0x4 /* from venus (which died) */ -#define C_PURGE 0x8 - -int coda_cnode_make(struct inode **, struct CodaFid *, struct super_block *); -struct inode *coda_iget(struct super_block *sb, struct CodaFid *fid, struct coda_vattr *attr); -int coda_cnode_makectl(struct inode **inode, struct super_block *sb); -struct inode *coda_fid_to_inode(struct CodaFid *fid, struct super_block *sb); -void coda_replace_fid(struct inode *, struct CodaFid *, struct CodaFid *); - -#endif diff --git a/include/linux/coda_linux.h b/include/linux/coda_linux.h deleted file mode 100644 index 490c56b..0000000 --- a/include/linux/coda_linux.h +++ /dev/null @@ -1,101 +0,0 @@ -/* - * Coda File System, Linux Kernel module - * - * Original version, adapted from cfs_mach.c, (C) Carnegie Mellon University - * Linux modifications (C) 1996, Peter J. Braam - * Rewritten for Linux 2.1 (C) 1997 Carnegie Mellon University - * - * Carnegie Mellon University encourages users of this software to - * contribute improvements to the Coda project. - */ - -#ifndef _LINUX_CODA_FS -#define _LINUX_CODA_FS - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -/* operations */ -extern const struct inode_operations coda_dir_inode_operations; -extern const struct inode_operations coda_file_inode_operations; -extern const struct inode_operations coda_ioctl_inode_operations; - -extern const struct dentry_operations coda_dentry_operations; - -extern const struct address_space_operations coda_file_aops; -extern const struct address_space_operations coda_symlink_aops; - -extern const struct file_operations coda_dir_operations; -extern const struct file_operations coda_file_operations; -extern const struct file_operations coda_ioctl_operations; - -/* operations shared over more than one file */ -int coda_open(struct inode *i, struct file *f); -int coda_release(struct inode *i, struct file *f); -int coda_permission(struct inode *inode, int mask, unsigned int flags); -int coda_revalidate_inode(struct dentry *); -int coda_getattr(struct vfsmount *, struct dentry *, struct kstat *); -int coda_setattr(struct dentry *, struct iattr *); - -/* this file: heloers */ -char *coda_f2s(struct CodaFid *f); -int coda_isroot(struct inode *i); -int coda_iscontrol(const char *name, size_t length); - -void coda_vattr_to_iattr(struct inode *, struct coda_vattr *); -void coda_iattr_to_vattr(struct iattr *, struct coda_vattr *); -unsigned short coda_flags_to_cflags(unsigned short); - -/* sysctl.h */ -void coda_sysctl_init(void); -void coda_sysctl_clean(void); - -#define CODA_ALLOC(ptr, cast, size) do { \ - if (size < PAGE_SIZE) \ - ptr = kmalloc((unsigned long) size, GFP_KERNEL); \ - else \ - ptr = (cast)vmalloc((unsigned long) size); \ - if (!ptr) \ - printk("kernel malloc returns 0 at %s:%d\n", __FILE__, __LINE__); \ - else memset( ptr, 0, size ); \ -} while (0) - - -#define CODA_FREE(ptr,size) \ - do { if (size < PAGE_SIZE) kfree((ptr)); else vfree((ptr)); } while (0) - -/* inode to cnode access functions */ - -static inline struct coda_inode_info *ITOC(struct inode *inode) -{ - return list_entry(inode, struct coda_inode_info, vfs_inode); -} - -static __inline__ struct CodaFid *coda_i2f(struct inode *inode) -{ - return &(ITOC(inode)->c_fid); -} - -static __inline__ char *coda_i2s(struct inode *inode) -{ - return coda_f2s(&(ITOC(inode)->c_fid)); -} - -/* this will not zap the inode away */ -static __inline__ void coda_flag_inode(struct inode *inode, int flag) -{ - struct coda_inode_info *cii = ITOC(inode); - - spin_lock(&cii->c_lock); - cii->c_flags |= flag; - spin_unlock(&cii->c_lock); -} - -#endif -- cgit v1.1 From c74a1cbb3cac348f276fabc381758f5b0b4713b2 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 12 Jan 2011 16:59:34 -0500 Subject: pass default dentry_operations to mount_pseudo() Signed-off-by: Al Viro --- include/linux/fs.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3e4c274..c070128 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1835,7 +1835,9 @@ struct super_block *sget(struct file_system_type *type, int (*set)(struct super_block *,void *), void *data); extern struct dentry *mount_pseudo(struct file_system_type *, char *, - const struct super_operations *ops, unsigned long); + const struct super_operations *ops, + const struct dentry_operations *dops, + unsigned long); extern void simple_set_mnt(struct vfsmount *mnt, struct super_block *sb); static inline void sb_mark_dirty(struct super_block *sb) -- cgit v1.1 From 0378c4051a621303ae919f1cee832206a4c1aa68 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 12 Jan 2011 17:25:03 -0500 Subject: switch ncpfs merge dentry_operations for root and non-root Signed-off-by: Al Viro --- include/linux/ncp_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ncp_fs.h b/include/linux/ncp_fs.h index 1c27f20..2d79c8a 100644 --- a/include/linux/ncp_fs.h +++ b/include/linux/ncp_fs.h @@ -204,7 +204,7 @@ void ncp_update_inode2(struct inode *, struct ncp_entry_info *); /* linux/fs/ncpfs/dir.c */ extern const struct inode_operations ncp_dir_inode_operations; extern const struct file_operations ncp_dir_operations; -extern const struct dentry_operations ncp_root_dentry_operations; +extern const struct dentry_operations ncp_dentry_operations; int ncp_conn_logged_in(struct super_block *); int ncp_date_dos2unix(__le16 time, __le16 date); void ncp_date_unix2dos(int unix_date, __le16 * time, __le16 * date); -- cgit v1.1 From 32c419d95f3d1da891ab9bd032a214ee05b94ed4 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 12 Jan 2011 17:37:47 -0500 Subject: move internal-only parts of ncpfs headers to fs/ncpfs Signed-off-by: Al Viro --- include/linux/ncp_fs.h | 100 ---------------------------- include/linux/ncp_fs_i.h | 29 -------- include/linux/ncp_fs_sb.h | 164 ---------------------------------------------- include/linux/ncp_mount.h | 22 ------- 4 files changed, 315 deletions(-) delete mode 100644 include/linux/ncp_fs_i.h delete mode 100644 include/linux/ncp_fs_sb.h (limited to 'include') diff --git a/include/linux/ncp_fs.h b/include/linux/ncp_fs.h index 2d79c8a..e13eefe 100644 --- a/include/linux/ncp_fs.h +++ b/include/linux/ncp_fs.h @@ -143,104 +143,4 @@ struct ncp_nls_ioctl #define NCP_MAXPATHLEN 255 #define NCP_MAXNAMELEN 14 -#ifdef __KERNEL__ - -#include -#include - -/* define because it is easy to change PRINTK to {*}PRINTK */ -#define PRINTK(format, args...) printk(KERN_DEBUG format , ## args) - -#undef NCPFS_PARANOIA -#ifdef NCPFS_PARANOIA -#define PPRINTK(format, args...) PRINTK(format , ## args) -#else -#define PPRINTK(format, args...) -#endif - -#ifndef DEBUG_NCP -#define DEBUG_NCP 0 -#endif -#if DEBUG_NCP > 0 -#define DPRINTK(format, args...) PRINTK(format , ## args) -#else -#define DPRINTK(format, args...) -#endif -#if DEBUG_NCP > 1 -#define DDPRINTK(format, args...) PRINTK(format , ## args) -#else -#define DDPRINTK(format, args...) -#endif - -#define NCP_MAX_RPC_TIMEOUT (6*HZ) - - -struct ncp_entry_info { - struct nw_info_struct i; - ino_t ino; - int opened; - int access; - unsigned int volume; - __u8 file_handle[6]; -}; - -static inline struct ncp_server *NCP_SBP(const struct super_block *sb) -{ - return sb->s_fs_info; -} - -#define NCP_SERVER(inode) NCP_SBP((inode)->i_sb) -static inline struct ncp_inode_info *NCP_FINFO(const struct inode *inode) -{ - return container_of(inode, struct ncp_inode_info, vfs_inode); -} - -/* linux/fs/ncpfs/inode.c */ -int ncp_notify_change(struct dentry *, struct iattr *); -struct inode *ncp_iget(struct super_block *, struct ncp_entry_info *); -void ncp_update_inode(struct inode *, struct ncp_entry_info *); -void ncp_update_inode2(struct inode *, struct ncp_entry_info *); - -/* linux/fs/ncpfs/dir.c */ -extern const struct inode_operations ncp_dir_inode_operations; -extern const struct file_operations ncp_dir_operations; -extern const struct dentry_operations ncp_dentry_operations; -int ncp_conn_logged_in(struct super_block *); -int ncp_date_dos2unix(__le16 time, __le16 date); -void ncp_date_unix2dos(int unix_date, __le16 * time, __le16 * date); - -/* linux/fs/ncpfs/ioctl.c */ -long ncp_ioctl(struct file *, unsigned int, unsigned long); -long ncp_compat_ioctl(struct file *, unsigned int, unsigned long); - -/* linux/fs/ncpfs/sock.c */ -int ncp_request2(struct ncp_server *server, int function, - void* reply, int max_reply_size); -static inline int ncp_request(struct ncp_server *server, int function) { - return ncp_request2(server, function, server->packet, server->packet_size); -} -int ncp_connect(struct ncp_server *server); -int ncp_disconnect(struct ncp_server *server); -void ncp_lock_server(struct ncp_server *server); -void ncp_unlock_server(struct ncp_server *server); - -/* linux/fs/ncpfs/symlink.c */ -#if defined(CONFIG_NCPFS_EXTRAS) || defined(CONFIG_NCPFS_NFS_NS) -extern const struct address_space_operations ncp_symlink_aops; -int ncp_symlink(struct inode*, struct dentry*, const char*); -#endif - -/* linux/fs/ncpfs/file.c */ -extern const struct inode_operations ncp_file_inode_operations; -extern const struct file_operations ncp_file_operations; -int ncp_make_open(struct inode *, int); - -/* linux/fs/ncpfs/mmap.c */ -int ncp_mmap(struct file *, struct vm_area_struct *); - -/* linux/fs/ncpfs/ncplib_kernel.c */ -int ncp_make_closed(struct inode *); - -#endif /* __KERNEL__ */ - #endif /* _LINUX_NCP_FS_H */ diff --git a/include/linux/ncp_fs_i.h b/include/linux/ncp_fs_i.h deleted file mode 100644 index 4b0bec4..0000000 --- a/include/linux/ncp_fs_i.h +++ /dev/null @@ -1,29 +0,0 @@ -/* - * ncp_fs_i.h - * - * Copyright (C) 1995 Volker Lendecke - * - */ - -#ifndef _LINUX_NCP_FS_I -#define _LINUX_NCP_FS_I - -/* - * This is the ncpfs part of the inode structure. This must contain - * all the information we need to work with an inode after creation. - */ -struct ncp_inode_info { - __le32 dirEntNum; - __le32 DosDirNum; - __u8 volNumber; - __le32 nwattr; - struct mutex open_mutex; - atomic_t opened; - int access; - int flags; -#define NCPI_KLUDGE_SYMLINK 0x0001 - __u8 file_handle[6]; - struct inode vfs_inode; -}; - -#endif /* _LINUX_NCP_FS_I */ diff --git a/include/linux/ncp_fs_sb.h b/include/linux/ncp_fs_sb.h deleted file mode 100644 index d64b0e8..0000000 --- a/include/linux/ncp_fs_sb.h +++ /dev/null @@ -1,164 +0,0 @@ -/* - * ncp_fs_sb.h - * - * Copyright (C) 1995, 1996 by Volker Lendecke - * - */ - -#ifndef _NCP_FS_SB -#define _NCP_FS_SB - -#include -#include -#include -#include -#include - -#ifdef __KERNEL__ - -#include - -#define NCP_DEFAULT_OPTIONS 0 /* 2 for packet signatures */ - -struct sock; - -struct ncp_server { - - struct ncp_mount_data_kernel m; /* Nearly all of the mount data is of - interest for us later, so we store - it completely. */ - - __u8 name_space[NCP_NUMBER_OF_VOLUMES + 2]; - - struct file *ncp_filp; /* File pointer to ncp socket */ - struct socket *ncp_sock;/* ncp socket */ - struct file *info_filp; - struct socket *info_sock; - - u8 sequence; - u8 task; - u16 connection; /* Remote connection number */ - - u8 completion; /* Status message from server */ - u8 conn_status; /* Bit 4 = 1 ==> Server going down, no - requests allowed anymore. - Bit 0 = 1 ==> Server is down. */ - - int buffer_size; /* Negotiated bufsize */ - - int reply_size; /* Size of last reply */ - - int packet_size; - unsigned char *packet; /* Here we prepare requests and - receive replies */ - unsigned char *txbuf; /* Storage for current request */ - unsigned char *rxbuf; /* Storage for reply to current request */ - - int lock; /* To prevent mismatch in protocols. */ - struct mutex mutex; - - int current_size; /* for packet preparation */ - int has_subfunction; - int ncp_reply_size; - - int root_setuped; - struct mutex root_setup_lock; - - /* info for packet signing */ - int sign_wanted; /* 1=Server needs signed packets */ - int sign_active; /* 0=don't do signing, 1=do */ - char sign_root[8]; /* generated from password and encr. key */ - char sign_last[16]; - - /* Authentication info: NDS or BINDERY, username */ - struct { - int auth_type; - size_t object_name_len; - void* object_name; - int object_type; - } auth; - /* Password info */ - struct { - size_t len; - void* data; - } priv; - struct rw_semaphore auth_rwsem; - - /* nls info: codepage for volume and charset for I/O */ - struct nls_table *nls_vol; - struct nls_table *nls_io; - - /* maximum age in jiffies */ - atomic_t dentry_ttl; - - /* miscellaneous */ - unsigned int flags; - - spinlock_t requests_lock; /* Lock accesses to tx.requests, tx.creq and rcv.creq when STREAM mode */ - - void (*data_ready)(struct sock* sk, int len); - void (*error_report)(struct sock* sk); - void (*write_space)(struct sock* sk); /* STREAM mode only */ - struct { - struct work_struct tq; /* STREAM/DGRAM: data/error ready */ - struct ncp_request_reply* creq; /* STREAM/DGRAM: awaiting reply from this request */ - struct mutex creq_mutex; /* DGRAM only: lock accesses to rcv.creq */ - - unsigned int state; /* STREAM only: receiver state */ - struct { - __u32 magic __packed; - __u32 len __packed; - __u16 type __packed; - __u16 p1 __packed; - __u16 p2 __packed; - __u16 p3 __packed; - __u16 type2 __packed; - } buf; /* STREAM only: temporary buffer */ - unsigned char* ptr; /* STREAM only: pointer to data */ - size_t len; /* STREAM only: length of data to receive */ - } rcv; - struct { - struct list_head requests; /* STREAM only: queued requests */ - struct work_struct tq; /* STREAM only: transmitter ready */ - struct ncp_request_reply* creq; /* STREAM only: currently transmitted entry */ - } tx; - struct timer_list timeout_tm; /* DGRAM only: timeout timer */ - struct work_struct timeout_tq; /* DGRAM only: associated queue, we run timers from process context */ - int timeout_last; /* DGRAM only: current timeout length */ - int timeout_retries; /* DGRAM only: retries left */ - struct { - size_t len; - __u8 data[128]; - } unexpected_packet; - struct backing_dev_info bdi; -}; - -extern void ncp_tcp_rcv_proc(struct work_struct *work); -extern void ncp_tcp_tx_proc(struct work_struct *work); -extern void ncpdgram_rcv_proc(struct work_struct *work); -extern void ncpdgram_timeout_proc(struct work_struct *work); -extern void ncpdgram_timeout_call(unsigned long server); -extern void ncp_tcp_data_ready(struct sock* sk, int len); -extern void ncp_tcp_write_space(struct sock* sk); -extern void ncp_tcp_error_report(struct sock* sk); - -#define NCP_FLAG_UTF8 1 - -#define NCP_CLR_FLAG(server, flag) ((server)->flags &= ~(flag)) -#define NCP_SET_FLAG(server, flag) ((server)->flags |= (flag)) -#define NCP_IS_FLAG(server, flag) ((server)->flags & (flag)) - -static inline int ncp_conn_valid(struct ncp_server *server) -{ - return ((server->conn_status & 0x11) == 0); -} - -static inline void ncp_invalidate_conn(struct ncp_server *server) -{ - server->conn_status |= 0x01; -} - -#endif /* __KERNEL__ */ - -#endif - diff --git a/include/linux/ncp_mount.h b/include/linux/ncp_mount.h index a2b549e..dfcbea2 100644 --- a/include/linux/ncp_mount.h +++ b/include/linux/ncp_mount.h @@ -68,26 +68,4 @@ struct ncp_mount_data_v4 { #define NCP_MOUNT_VERSION_V5 (5) /* Text only */ -#ifdef __KERNEL__ - -struct ncp_mount_data_kernel { - unsigned long flags; /* NCP_MOUNT_* flags */ - unsigned int int_flags; /* internal flags */ -#define NCP_IMOUNT_LOGGEDIN_POSSIBLE 0x0001 - __kernel_uid32_t mounted_uid; /* Who may umount() this filesystem? */ - struct pid *wdog_pid; /* Who cares for our watchdog packets? */ - unsigned int ncp_fd; /* The socket to the ncp port */ - unsigned int time_out; /* How long should I wait after - sending a NCP request? */ - unsigned int retry_count; /* And how often should I retry? */ - unsigned char mounted_vol[NCP_VOLNAME_LEN + 1]; - __kernel_uid32_t uid; - __kernel_gid32_t gid; - __kernel_mode_t file_mode; - __kernel_mode_t dir_mode; - int info_fd; -}; - -#endif /* __KERNEL__ */ - #endif -- cgit v1.1 From 79124f18b335172e1916075c633745e12dae1dac Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 17 Nov 2010 20:46:15 -0500 Subject: fs: add hole punching to fallocate Hole punching has already been implemented by XFS and OCFS2, and has the potential to be implemented on both BTRFS and EXT4 so we need a generic way to get to this feature. The simplest way in my mind is to add FALLOC_FL_PUNCH_HOLE to fallocate() since it already looks like the normal fallocate() operation. I've tested this patch with XFS and BTRFS to make sure XFS did what it's supposed to do and that BTRFS failed like it was supposed to. Thank you, Signed-off-by: Josef Bacik Signed-off-by: Al Viro --- include/linux/falloc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/falloc.h b/include/linux/falloc.h index 3c15510..73e0b62 100644 --- a/include/linux/falloc.h +++ b/include/linux/falloc.h @@ -2,6 +2,7 @@ #define _FALLOC_H_ #define FALLOC_FL_KEEP_SIZE 0x01 /* default is extend size */ +#define FALLOC_FL_PUNCH_HOLE 0x02 /* de-allocates range */ #ifdef __KERNEL__ -- cgit v1.1 From 838b4dc6d8a6bd83a93077ebc6873712c65bf85e Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Wed, 12 Jan 2011 15:42:32 +0000 Subject: sched: remove unused backlog in RED stats The RED statistics structure includes backlog field which is not set or used by any code. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/net/red.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/red.h b/include/net/red.h index 995108e..3319f16 100644 --- a/include/net/red.h +++ b/include/net/red.h @@ -97,7 +97,6 @@ struct red_stats { u32 forced_mark; /* Forced marks, qavg > max_thresh */ u32 pdrop; /* Drops due to queue limits */ u32 other; /* Drops due to drop() calls */ - u32 backlog; }; struct red_parms { -- cgit v1.1 From 278ad4fd0e7517f1d74b8fc1c8347cad34a09b02 Mon Sep 17 00:00:00 2001 From: Samu Onkalo Date: Wed, 12 Jan 2011 16:59:17 -0800 Subject: leds: leds-lp5523: modify the way of setting led device name Currently all leds channels begins with string lp5523. Patch adds a possibility to provide name via platform data. This makes it possible to have several chips without overlapping sysfs names. Signed-off-by: Samu Onkalo Cc: Arun Murthy Cc: Ilkka Koskinen Cc: Richard Purdie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/leds-lp5523.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/leds-lp5523.h b/include/linux/leds-lp5523.h index 7967476..2694289 100644 --- a/include/linux/leds-lp5523.h +++ b/include/linux/leds-lp5523.h @@ -42,6 +42,7 @@ struct lp5523_platform_data { int (*setup_resources)(void); void (*release_resources)(void); void (*enable)(bool state); + const char *label; }; #endif /* __LINUX_LP5523_H */ -- cgit v1.1 From 61a83932b8b3f1624d753e06aab2fdf0a119e100 Mon Sep 17 00:00:00 2001 From: Arun Murthy Date: Wed, 12 Jan 2011 16:59:20 -0800 Subject: leds-lp5521: modify the way of setting led device name Currently the led device name is fetched from the device_type in I2C_BOARD_INFO which comes from the platform data. This name is in turn used to create an entry in sysfs. If there exists two or more lp5521 on a particular platform, the device_type in I2C_BOARD_INFO has to be the same, else lp5521 driver probe wont be called and if used so, results in run time warning "cannot create sysfs with same name" and hence a failure. The name that is used to create sysfs entry is to be passed by the struct led_platform_data. Hence adding an element of type const char * and change in lp5521 driver to use this name in creating the led device if present else use the name obtained by I2C_BOARD_INFO. Signed-off-by: Arun Murthy Acked-by: Samu Onkalo Cc: Ilkka Koskinen Cc: Richard Purdie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/leds-lp5521.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/leds-lp5521.h b/include/linux/leds-lp5521.h index 38368d7..fd548d2 100644 --- a/include/linux/leds-lp5521.h +++ b/include/linux/leds-lp5521.h @@ -42,6 +42,7 @@ struct lp5521_platform_data { int (*setup_resources)(void); void (*release_resources)(void); void (*enable)(bool state); + const char *label; }; #endif /* __LINUX_LP5521_H */ -- cgit v1.1 From 04c6862c055fb687c90d9652f32c11a063df15cf Mon Sep 17 00:00:00 2001 From: Seiji Aguchi Date: Wed, 12 Jan 2011 16:59:30 -0800 Subject: kmsg_dump: add kmsg_dump() calls to the reboot, halt, poweroff and emergency_restart paths We need to know the reason why system rebooted in support service. However, we can't inform our customers of the reason because final messages are lost on current Linux kernel. This patch improves the situation above because the final messages are saved by adding kmsg_dump() to reboot, halt, poweroff and emergency_restart path. Signed-off-by: Seiji Aguchi Cc: David Woodhouse Cc: Marco Stornelli Reviewed-by: Artem Bityutskiy Reviewed-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kmsg_dump.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h index 24b4414..2a0d7d6 100644 --- a/include/linux/kmsg_dump.h +++ b/include/linux/kmsg_dump.h @@ -18,6 +18,10 @@ enum kmsg_dump_reason { KMSG_DUMP_OOPS, KMSG_DUMP_PANIC, KMSG_DUMP_KEXEC, + KMSG_DUMP_RESTART, + KMSG_DUMP_HALT, + KMSG_DUMP_POWEROFF, + KMSG_DUMP_EMERG, }; /** -- cgit v1.1 From 71a9048448de302d1e968f336de01060d02fae71 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 12 Jan 2011 16:59:35 -0800 Subject: include/linux/kernel.h: abs(): fix handling of 32-bit unsigneds on 64-bit Michal reports: In the framebuffer subsystem the abs() macro is often used as a part of the calculation of a Manhattan metric, which in turn is used as a measure of similarity between video modes. The arguments of abs() are sometimes unsigned numbers. This worked fine until commit a49c59c0 ("Make sure the value in abs() does not get truncated if it is greater than 2^32:) , which changed the definition of abs() to prevent truncation. As a result of this change, in the following piece of code: u32 a = 0, b = 1; u32 c = abs(a - b); 'c' will end up with a value of 0xffffffff instead of the expected 0x1. A problem caused by this change and visible by the end user is that framebuffer drivers relying on functions from modedb.c will fail to find high resolution video modes similar to that explicitly requested by the user if an exact match cannot be found (see e.g. Fix this by special-casing `long' types within abs(). This patch reduces x86_64 code size a bit - drivers/video/uvesafb.o shrunk by 15 bytes, presumably because it is doing abs() on 4-byte quantities, and expanding those to 8-byte longs adds code. testcase: #define oldabs(x) ({ \ long __x = (x); \ (__x < 0) ? -__x : __x; \ }) #define newabs(x) ({ \ long ret; \ if (sizeof(x) == sizeof(long)) { \ long __x = (x); \ ret = (__x < 0) ? -__x : __x; \ } else { \ int __x = (x); \ ret = (__x < 0) ? -__x : __x; \ } \ ret; \ }) typedef unsigned int u32; main() { u32 a = 0; u32 b = 1; u32 oldc = oldabs(a - b); u32 newc = newabs(a - b); printf("%u %u\n", oldc, newc); } akpm:/home/akpm> gcc t.c akpm:/home/akpm> ./a.out 4294967295 1 Reported-by: Michal Januszewski Cc: Rolf Eike Beer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index d0fbc04..57dac70 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -143,9 +143,22 @@ extern int _cond_resched(void); #define might_sleep_if(cond) do { if (cond) might_sleep(); } while (0) -#define abs(x) ({ \ - long __x = (x); \ - (__x < 0) ? -__x : __x; \ +/* + * abs() handles unsigned and signed longs, ints, shorts and chars. For all + * input types abs() returns a signed long. + * abs() should not be used for 64-bit types (s64, u64, long long) - use abs64() + * for those. + */ +#define abs(x) ({ \ + long ret; \ + if (sizeof(x) == sizeof(long)) { \ + long __x = (x); \ + ret = (__x < 0) ? -__x : __x; \ + } else { \ + int __x = (x); \ + ret = (__x < 0) ? -__x : __x; \ + } \ + ret; \ }) #define abs64(x) ({ \ -- cgit v1.1 From 049763db6cd002cb447a5684b5a543a69d647d42 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Wed, 12 Jan 2011 16:59:35 -0800 Subject: toshiba.h: hide a function prototypes behind __KERNEL__ macro Currently, tosh_smm() prototype is present in a header file exported to userland. This patch fixes it. Signed-off-by: Alexander Shishkin Cc: Jonathan Buzzard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/toshiba.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/toshiba.h b/include/linux/toshiba.h index 6a7c4ed..772dedb 100644 --- a/include/linux/toshiba.h +++ b/include/linux/toshiba.h @@ -33,6 +33,8 @@ typedef struct { unsigned int edi __attribute__ ((packed)); } SMMRegisters; +#ifdef __KERNEL__ int tosh_smm(SMMRegisters *regs); +#endif /* __KERNEL__ */ #endif -- cgit v1.1 From 1725310324163f56fea71bb77c5d6e88f9ce4192 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 12 Jan 2011 16:59:37 -0800 Subject: include/linux/unaligned/packed_struct.h: use __packed Cc: Will Newton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/unaligned/packed_struct.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/unaligned/packed_struct.h b/include/linux/unaligned/packed_struct.h index c9a6abd..c0d817d 100644 --- a/include/linux/unaligned/packed_struct.h +++ b/include/linux/unaligned/packed_struct.h @@ -3,9 +3,9 @@ #include -struct __una_u16 { u16 x; } __attribute__((packed)); -struct __una_u32 { u32 x; } __attribute__((packed)); -struct __una_u64 { u64 x; } __attribute__((packed)); +struct __una_u16 { u16 x; } __packed; +struct __una_u32 { u32 x; } __packed; +struct __una_u64 { u64 x; } __packed; static inline u16 __get_unaligned_cpu16(const void *p) { -- cgit v1.1 From 8369744fc4418743d3d84a8490d576e3dbf01594 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 12 Jan 2011 16:59:38 -0800 Subject: include/asm-generic/vmlinux.lds.h: make readmostly section correctly align The readmostly section should end at a cacheline aligned address, otherwise the last several data might share cachline with other data and make the readmostly data still have cache bounce. For example, in ia64, secpath_cachep is the last readmostly data, and it shares cacheline with init_uts_ns. a000000100e80480 d secpath_cachep a000000100e80488 D init_uts_ns Signed-off-by: Shaohua Li Cc: "H. Peter Anvin" Cc: Eric Dumazet Acked-by: Tejun Heo Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/vmlinux.lds.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 05cbad0..6864933 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -200,7 +200,8 @@ #define READ_MOSTLY_DATA(align) \ . = ALIGN(align); \ - *(.data..read_mostly) + *(.data..read_mostly) \ + . = ALIGN(align); #define CACHELINE_ALIGNED_DATA(align) \ . = ALIGN(align); \ -- cgit v1.1 From 455cd5ab305c90ffc422dd2e0fb634730942b257 Mon Sep 17 00:00:00 2001 From: Dan Rosenberg Date: Wed, 12 Jan 2011 16:59:41 -0800 Subject: kptr_restrict for hiding kernel pointers from unprivileged users Add the %pK printk format specifier and the /proc/sys/kernel/kptr_restrict sysctl. The %pK format specifier is designed to hide exposed kernel pointers, specifically via /proc interfaces. Exposing these pointers provides an easy target for kernel write vulnerabilities, since they reveal the locations of writable structures containing easily triggerable function pointers. The behavior of %pK depends on the kptr_restrict sysctl. If kptr_restrict is set to 0, no deviation from the standard %p behavior occurs. If kptr_restrict is set to 1, the default, if the current user (intended to be a reader via seq_printf(), etc.) does not have CAP_SYSLOG (currently in the LSM tree), kernel pointers using %pK are printed as 0's. If kptr_restrict is set to 2, kernel pointers using %pK are printed as 0's regardless of privileges. Replacing with 0's was chosen over the default "(null)", which cannot be parsed by userland %p, which expects "(nil)". [akpm@linux-foundation.org: check for IRQ context when !kptr_restrict, save an indent level, s/WARN/WARN_ONCE/] [akpm@linux-foundation.org: coding-style fixup] [randy.dunlap@oracle.com: fix kernel/sysctl.c warning] Signed-off-by: Dan Rosenberg Signed-off-by: Randy Dunlap Cc: James Morris Cc: Eric Dumazet Cc: Thomas Graf Cc: Eugene Teo Cc: Kees Cook Cc: Ingo Molnar Cc: David S. Miller Cc: Peter Zijlstra Cc: Eric Paris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index b772ca5..9adfba6 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -83,6 +83,7 @@ extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, extern int printk_delay_msec; extern int dmesg_restrict; +extern int kptr_restrict; /* * Print a one-time message (analogous to WARN_ONCE() et al): -- cgit v1.1 From a9747cc3addf81e56ea9b8a4374fbdb9d1737eae Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jan 2011 16:59:43 -0800 Subject: include/linux/printk.h: move console functions and variables together There are many uses of printk_once(KERN_, so add pr__once macros to avoid printk_once(KERN_ pr_fmt(fmt). Add an #ifdef CONFIG_PRINTK for print_hex_dump and static inline void functions for the #else cases to reduce embedded code size. Neaten and organize the rest of the code. This patch: Move console functions and variables together. Signed-off-by: Joe Perches Cc: Matt Mackall Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index 9adfba6..bd43c72 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -29,6 +29,17 @@ extern int console_printk[]; #define minimum_console_loglevel (console_printk[2]) #define default_console_loglevel (console_printk[3]) +static inline void console_silent(void) +{ + console_loglevel = 0; +} + +static inline void console_verbose(void) +{ + if (console_loglevel) + console_loglevel = 15; +} + struct va_format { const char *fmt; va_list *va; @@ -131,17 +142,6 @@ extern void printk_tick(void); extern void asmlinkage __attribute__((format(printf, 1, 2))) early_printk(const char *fmt, ...); -static inline void console_silent(void) -{ - console_loglevel = 0; -} - -static inline void console_verbose(void) -{ - if (console_loglevel) - console_loglevel = 15; -} - extern void dump_stack(void) __cold; enum { -- cgit v1.1 From 7d1e91aeb317c3c747369d8594fc1b742c265a07 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jan 2011 16:59:45 -0800 Subject: include/linux/printk.h: use space after #define Signed-off-by: Joe Perches Cc: Matt Mackall Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index bd43c72..b711311 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -4,14 +4,14 @@ extern const char linux_banner[]; extern const char linux_proc_banner[]; -#define KERN_EMERG "<0>" /* system is unusable */ -#define KERN_ALERT "<1>" /* action must be taken immediately */ -#define KERN_CRIT "<2>" /* critical conditions */ -#define KERN_ERR "<3>" /* error conditions */ -#define KERN_WARNING "<4>" /* warning conditions */ -#define KERN_NOTICE "<5>" /* normal but significant condition */ -#define KERN_INFO "<6>" /* informational */ -#define KERN_DEBUG "<7>" /* debug-level messages */ +#define KERN_EMERG "<0>" /* system is unusable */ +#define KERN_ALERT "<1>" /* action must be taken immediately */ +#define KERN_CRIT "<2>" /* critical conditions */ +#define KERN_ERR "<3>" /* error conditions */ +#define KERN_WARNING "<4>" /* warning conditions */ +#define KERN_NOTICE "<5>" /* normal but significant condition */ +#define KERN_INFO "<6>" /* informational */ +#define KERN_DEBUG "<7>" /* debug-level messages */ /* Use the default kernel loglevel */ #define KERN_DEFAULT "" @@ -20,7 +20,7 @@ extern const char linux_proc_banner[]; * line that had no enclosing \n). Only to be used by core/arch code * during early bootup (a continued line is not SMP-safe otherwise). */ -#define KERN_CONT "" +#define KERN_CONT "" extern int console_printk[]; -- cgit v1.1 From 5264f2f75d8678f3e9683042a4639baa5884bda9 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jan 2011 16:59:45 -0800 Subject: include/linux/printk.h: use and neaten no_printk - Move no_printk above first CONFIG_PRINTK block so it can be used by printk_once. - Convert statement expression if (0) printk macros to no_printk. - Convert printk_once(x...) to more normally used (fmt, ...) fmt, ##__VA_ARGS__. - Standardize __attribute__ use. - Expand single line inline functions. - Remove space before pointer. Signed-off-by: Joe Perches Cc: Matt Mackall Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 75 +++++++++++++++++++++++++++++--------------------- 1 file changed, 43 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index b711311..4788c28 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -76,11 +76,27 @@ struct va_format { */ #define HW_ERR "[Hardware Error]: " +/* + * Dummy printk for disabled debugging statements to use whilst maintaining + * gcc's format and side-effect checking. + */ +static inline __attribute__ ((format (printf, 1, 2))) +int no_printk(const char *fmt, ...) +{ + return 0; +} + +extern asmlinkage __attribute__ ((format (printf, 1, 2))) +void early_printk(const char *fmt, ...); + +extern int printk_needs_cpu(int cpu); +extern void printk_tick(void); + #ifdef CONFIG_PRINTK -asmlinkage int vprintk(const char *fmt, va_list args) - __attribute__ ((format (printf, 1, 0))); -asmlinkage int printk(const char * fmt, ...) - __attribute__ ((format (printf, 1, 2))) __cold; +asmlinkage __attribute__ ((format (printf, 1, 0))) +int vprintk(const char *fmt, va_list args); +asmlinkage __attribute__ ((format (printf, 1, 2))) __cold +int printk(const char *fmt, ...); /* * Please don't use printk_ratelimit(), because it shares ratelimiting state @@ -110,38 +126,34 @@ extern int kptr_restrict; void log_buf_kexec_setup(void); #else -static inline int vprintk(const char *s, va_list args) - __attribute__ ((format (printf, 1, 0))); -static inline int vprintk(const char *s, va_list args) { return 0; } -static inline int printk(const char *s, ...) - __attribute__ ((format (printf, 1, 2))); -static inline int __cold printk(const char *s, ...) { return 0; } -static inline int printk_ratelimit(void) { return 0; } -static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies, \ - unsigned int interval_msec) \ - { return false; } +static inline __attribute__ ((format (printf, 1, 0))) +int vprintk(const char *s, va_list args) +{ + return 0; +} +static inline __attribute__ ((format (printf, 1, 2))) __cold +int printk(const char *s, ...) +{ + return 0; +} +static inline int printk_ratelimit(void) +{ + return 0; +} +static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies, + unsigned int interval_msec) +{ + return false; +} /* No effect, but we still get type checking even in the !PRINTK case: */ -#define printk_once(x...) printk(x) +#define printk_once(fmt, ...) no_printk(fmt, ##__VA_ARGS__) static inline void log_buf_kexec_setup(void) { } #endif -/* - * Dummy printk for disabled debugging statements to use whilst maintaining - * gcc's format and side-effect checking. - */ -static inline __attribute__ ((format (printf, 1, 2))) -int no_printk(const char *s, ...) { return 0; } - -extern int printk_needs_cpu(int cpu); -extern void printk_tick(void); - -extern void asmlinkage __attribute__((format(printf, 1, 2))) - early_printk(const char *fmt, ...); - extern void dump_stack(void) __cold; enum { @@ -186,7 +198,7 @@ extern void print_hex_dump_bytes(const char *prefix_str, int prefix_type, printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_devel(fmt, ...) \ - ({ if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); 0; }) + no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /* If you are writing a driver, please use dev_dbg instead */ @@ -199,7 +211,7 @@ extern void print_hex_dump_bytes(const char *prefix_str, int prefix_type, dynamic_pr_debug(fmt, ##__VA_ARGS__) #else #define pr_debug(fmt, ...) \ - ({ if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); 0; }) + no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /* @@ -242,8 +254,7 @@ extern void print_hex_dump_bytes(const char *prefix_str, int prefix_type, printk_ratelimited(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_debug_ratelimited(fmt, ...) \ - ({ if (0) printk_ratelimited(KERN_DEBUG pr_fmt(fmt), \ - ##__VA_ARGS__); 0; }) + no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif #endif -- cgit v1.1 From 16cb839f13324978bd58082e69de81a711802b11 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jan 2011 16:59:46 -0800 Subject: include/linux/printk.h: add pr__once macros - Move printk_once definitions and add an #ifdef CONFIG_PRINTK - Add pr__once so printks can use pr_fmt Signed-off-by: Joe Perches Cc: Matt Mackall Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 59 +++++++++++++++++++++++++++++++++++++------------- 1 file changed, 44 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index 4788c28..6442156 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -112,18 +112,6 @@ extern int printk_delay_msec; extern int dmesg_restrict; extern int kptr_restrict; -/* - * Print a one-time message (analogous to WARN_ONCE() et al): - */ -#define printk_once(x...) ({ \ - static bool __print_once; \ - \ - if (!__print_once) { \ - __print_once = true; \ - printk(x); \ - } \ -}) - void log_buf_kexec_setup(void); #else static inline __attribute__ ((format (printf, 1, 0))) @@ -146,9 +134,6 @@ static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies, return false; } -/* No effect, but we still get type checking even in the !PRINTK case: */ -#define printk_once(fmt, ...) no_printk(fmt, ##__VA_ARGS__) - static inline void log_buf_kexec_setup(void) { } @@ -215,6 +200,50 @@ extern void print_hex_dump_bytes(const char *prefix_str, int prefix_type, #endif /* + * Print a one-time message (analogous to WARN_ONCE() et al): + */ + +#ifdef CONFIG_PRINTK +#define printk_once(fmt, ...) \ +({ \ + static bool __print_once; \ + \ + if (!__print_once) { \ + __print_once = true; \ + printk(fmt, ##__VA_ARGS__); \ + } \ +}) +#else +#define printk_once(fmt, ...) \ + no_printk(fmt, ##__VA_ARGS__) +#endif + +#define pr_emerg_once(fmt, ...) \ + printk_once(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) +#define pr_alert_once(fmt, ...) \ + printk_once(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) +#define pr_crit_once(fmt, ...) \ + printk_once(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) +#define pr_err_once(fmt, ...) \ + printk_once(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) +#define pr_warn_once(fmt, ...) \ + printk_once(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) +#define pr_notice_once(fmt, ...) \ + printk_once(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) +#define pr_info_once(fmt, ...) \ + printk_once(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) +#define pr_cont_once(fmt, ...) \ + printk_once(KERN_CONT pr_fmt(fmt), ##__VA_ARGS__) +/* If you are writing a driver, please use dev_dbg instead */ +#if defined(DEBUG) +#define pr_debug_once(fmt, ...) \ + printk_once(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) +#else +#define pr_debug_once(fmt, ...) \ + no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) +#endif + +/* * ratelimited messages with local ratelimit_state, * no local ratelimit_state used in the !PRINTK case */ -- cgit v1.1 From ac83ed687837a44c6e46fb16411fb0d299fffd80 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jan 2011 16:59:47 -0800 Subject: include/linux/printk.h lib/hexdump.c: neatening and add CONFIG_PRINTK guard - Move prototypes and align arguments. - Add CONFIG_PRINTK guard for print_hex functions Signed-off-by: Joe Perches Cc: Matt Mackall Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 42 ++++++++++++++++++++++++++++-------------- 1 file changed, 28 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index 6442156..e96bd41 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -141,20 +141,6 @@ static inline void log_buf_kexec_setup(void) extern void dump_stack(void) __cold; -enum { - DUMP_PREFIX_NONE, - DUMP_PREFIX_ADDRESS, - DUMP_PREFIX_OFFSET -}; -extern void hex_dump_to_buffer(const void *buf, size_t len, - int rowsize, int groupsize, - char *linebuf, size_t linebuflen, bool ascii); -extern void print_hex_dump(const char *level, const char *prefix_str, - int prefix_type, int rowsize, int groupsize, - const void *buf, size_t len, bool ascii); -extern void print_hex_dump_bytes(const char *prefix_str, int prefix_type, - const void *buf, size_t len); - #ifndef pr_fmt #define pr_fmt(fmt) fmt #endif @@ -286,4 +272,32 @@ extern void print_hex_dump_bytes(const char *prefix_str, int prefix_type, no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif + +enum { + DUMP_PREFIX_NONE, + DUMP_PREFIX_ADDRESS, + DUMP_PREFIX_OFFSET +}; +extern void hex_dump_to_buffer(const void *buf, size_t len, + int rowsize, int groupsize, + char *linebuf, size_t linebuflen, bool ascii); +#ifdef CONFIG_PRINTK +extern void print_hex_dump(const char *level, const char *prefix_str, + int prefix_type, int rowsize, int groupsize, + const void *buf, size_t len, bool ascii); +extern void print_hex_dump_bytes(const char *prefix_str, int prefix_type, + const void *buf, size_t len); +#else +static inline void print_hex_dump(const char *level, const char *prefix_str, + int prefix_type, int rowsize, int groupsize, + const void *buf, size_t len, bool ascii) +{ +} +static inline void print_hex_dump_bytes(const char *prefix_str, int prefix_type, + const void *buf, size_t len) +{ +} + +#endif + #endif -- cgit v1.1 From 6ec42a56e258462cda510421aecc2680d3642e21 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jan 2011 16:59:47 -0800 Subject: include/linux/printk.h: organize printk_ratelimited macros - Use no_printk for !CONFIG_PRINTK printk_ratelimited. - Whitespace cleanup. Signed-off-by: Joe Perches Cc: Matt Mackall Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 25 ++++++++++++------------- 1 file changed, 12 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index e96bd41..d30f579 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -234,7 +234,8 @@ extern void dump_stack(void) __cold; * no local ratelimit_state used in the !PRINTK case */ #ifdef CONFIG_PRINTK -#define printk_ratelimited(fmt, ...) ({ \ +#define printk_ratelimited(fmt, ...) \ +({ \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ @@ -243,36 +244,34 @@ extern void dump_stack(void) __cold; printk(fmt, ##__VA_ARGS__); \ }) #else -/* No effect, but we still get type checking even in the !PRINTK case: */ -#define printk_ratelimited printk +#define printk_ratelimited(fmt, ...) \ + no_printk(fmt, ##__VA_ARGS__) #endif -#define pr_emerg_ratelimited(fmt, ...) \ +#define pr_emerg_ratelimited(fmt, ...) \ printk_ratelimited(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) -#define pr_alert_ratelimited(fmt, ...) \ +#define pr_alert_ratelimited(fmt, ...) \ printk_ratelimited(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) -#define pr_crit_ratelimited(fmt, ...) \ +#define pr_crit_ratelimited(fmt, ...) \ printk_ratelimited(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) -#define pr_err_ratelimited(fmt, ...) \ +#define pr_err_ratelimited(fmt, ...) \ printk_ratelimited(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) -#define pr_warning_ratelimited(fmt, ...) \ +#define pr_warn_ratelimited(fmt, ...) \ printk_ratelimited(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) -#define pr_warn_ratelimited pr_warning_ratelimited -#define pr_notice_ratelimited(fmt, ...) \ +#define pr_notice_ratelimited(fmt, ...) \ printk_ratelimited(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) -#define pr_info_ratelimited(fmt, ...) \ +#define pr_info_ratelimited(fmt, ...) \ printk_ratelimited(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) /* no pr_cont_ratelimited, don't do that... */ /* If you are writing a driver, please use dev_dbg instead */ #if defined(DEBUG) -#define pr_debug_ratelimited(fmt, ...) \ +#define pr_debug_ratelimited(fmt, ...) \ printk_ratelimited(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_debug_ratelimited(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif - enum { DUMP_PREFIX_NONE, DUMP_PREFIX_ADDRESS, -- cgit v1.1 From a3f938bf6f5746d39e013d03ba13118a393fee96 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 12 Jan 2011 16:59:48 -0800 Subject: include/linux/printk.h: use tab not spaces for indent Signed-off-by: Joe Perches Cc: Matt Mackall Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/printk.h b/include/linux/printk.h index d30f579..ee048e7 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -146,20 +146,20 @@ extern void dump_stack(void) __cold; #endif #define pr_emerg(fmt, ...) \ - printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) + printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) #define pr_alert(fmt, ...) \ - printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) + printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) #define pr_crit(fmt, ...) \ - printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) + printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) #define pr_err(fmt, ...) \ - printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) + printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) #define pr_warning(fmt, ...) \ - printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) + printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) #define pr_warn pr_warning #define pr_notice(fmt, ...) \ - printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) + printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) #define pr_info(fmt, ...) \ - printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) + printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) #define pr_cont(fmt, ...) \ printk(KERN_CONT fmt, ##__VA_ARGS__) -- cgit v1.1 From 52bd19f7691b2ea6433aef0ef94c08c57efd7e79 Mon Sep 17 00:00:00 2001 From: Robin Holt Date: Wed, 12 Jan 2011 17:00:01 -0800 Subject: epoll: convert max_user_watches to long On a 16TB machine, max_user_watches has an integer overflow. Convert it to use a long and handle the associated fallout. Signed-off-by: Robin Holt Cc: "Eric W. Biederman" Acked-by: Davide Libenzi Cc: Pekka Enberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index abc527a..96e2321 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -683,7 +683,7 @@ struct user_struct { atomic_t fanotify_listeners; #endif #ifdef CONFIG_EPOLL - atomic_t epoll_watches; /* The number of file descriptors currently watched */ + atomic_long_t epoll_watches; /* The number of file descriptors currently watched */ #endif #ifdef CONFIG_POSIX_MQUEUE /* protected by mq_lock */ -- cgit v1.1 From f670d0ecda73b7438eec9ed108680bc5f5362ad8 Mon Sep 17 00:00:00 2001 From: Mikael Pettersson Date: Wed, 12 Jan 2011 17:00:02 -0800 Subject: binfmt_elf: cleanups This cleans up a few bits in binfmt_elf.c and binfmts.h: - the hasvdso field in struct linux_binfmt is unused, so remove it and the only initialization of it - the elf_map CPP symbol is not defined anywhere in the kernel, so remove an unnecessary #ifndef elf_map - reduce excessive indentation in elf_format's initializer - add missing spaces, remove extraneous spaces No functional changes, but tested on x86 (32 and 64 bit), powerpc (32 and 64 bit), sparc64, arm, and alpha. Signed-off-by: Mikael Pettersson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/binfmts.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 64a7114..c3d6512 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -25,7 +25,7 @@ struct pt_regs; /* * This structure is used to hold the arguments that are used when loading binaries. */ -struct linux_binprm{ +struct linux_binprm { char buf[BINPRM_BUF_SIZE]; #ifdef CONFIG_MMU struct vm_area_struct *vma; @@ -93,7 +93,6 @@ struct linux_binfmt { int (*load_shlib)(struct file *); int (*core_dump)(struct coredump_params *cprm); unsigned long min_coredump; /* minimal dump size */ - int hasvdso; }; extern int __register_binfmt(struct linux_binfmt *fmt, int insert); @@ -113,7 +112,7 @@ extern void unregister_binfmt(struct linux_binfmt *); extern int prepare_binprm(struct linux_binprm *); extern int __must_check remove_arg_zero(struct linux_binprm *); -extern int search_binary_handler(struct linux_binprm *,struct pt_regs *); +extern int search_binary_handler(struct linux_binprm *, struct pt_regs *); extern int flush_old_exec(struct linux_binprm * bprm); extern void setup_new_exec(struct linux_binprm * bprm); -- cgit v1.1 From 1b912c1bca5c162e611384fe7d39c916e081701a Mon Sep 17 00:00:00 2001 From: Andres Salomon Date: Wed, 12 Jan 2011 17:00:10 -0800 Subject: drivers/gpio/cs5535-gpio.c: add some additional cs5535-specific GPIO functionality This adds (well, re-adds actually) handling for events/IRQs through cs5535 GPIOs. In the wild and wooly world of CS5535, setup_event() is for assigning an IRQ to a GPIO filter/event pair, and set_irq() sets up the pair to trigger IRQs. These should really only be used in highly platform-specific drivers (such as OLPC's DCON driver). Sadly, because set_irq() uses MSRs, this causes the driver to become X86-specific. Signed-off-by: Andres Salomon Signed-off-by: Daniel Drake Cc: Grant Likely Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cs5535.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/cs5535.h b/include/linux/cs5535.h index d5a1d48..213cc50 100644 --- a/include/linux/cs5535.h +++ b/include/linux/cs5535.h @@ -111,6 +111,8 @@ static inline int cs5535_has_vsa2(void) void cs5535_gpio_set(unsigned offset, unsigned int reg); void cs5535_gpio_clear(unsigned offset, unsigned int reg); int cs5535_gpio_isset(unsigned offset, unsigned int reg); +int cs5535_gpio_set_irq(unsigned group, unsigned irq); +void cs5535_gpio_setup_event(unsigned offset, int pair, int pme); /* MFGPTs */ -- cgit v1.1 From 7637c9259f7b6dd841471ccf1120d484b7364f99 Mon Sep 17 00:00:00 2001 From: Andres Salomon Date: Wed, 12 Jan 2011 17:00:11 -0800 Subject: drivers/staging/olpc_dcon: convert to new cs5535 gpio API Drop the old geode_gpio crud, as well as the raw outl() calls; instead, use the Linux GPIO API where possible, and the cs5535_gpio API in other places. Note that we don't actually clean up the driver properly yet (once loaded, it always remains loaded). That'll come later.. This patch is necessary for building the driver. Signed-off-by: Andres Salomon Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cs5535.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/cs5535.h b/include/linux/cs5535.h index 213cc50..6fe2114 100644 --- a/include/linux/cs5535.h +++ b/include/linux/cs5535.h @@ -103,11 +103,15 @@ static inline int cs5535_has_vsa2(void) #define GPIO_POSITIVE_EDGE_STS 0x48 #define GPIO_NEGATIVE_EDGE_STS 0x4C +#define GPIO_FLTR7_AMOUNT 0xD8 + #define GPIO_MAP_X 0xE0 #define GPIO_MAP_Y 0xE4 #define GPIO_MAP_Z 0xE8 #define GPIO_MAP_W 0xEC +#define GPIO_FE7_SEL 0xF7 + void cs5535_gpio_set(unsigned offset, unsigned int reg); void cs5535_gpio_clear(unsigned offset, unsigned int reg); int cs5535_gpio_isset(unsigned offset, unsigned int reg); -- cgit v1.1 From 0fdae42d361bbb431ca0ab0efed5126a94821177 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Wed, 12 Jan 2011 17:00:23 -0800 Subject: gpiolib: annotate gpio-intialization with __must_check Because GPIOs can have crucial functions especially in embedded systems, we are better safe than sorry regarding their configuration. For gpio_request, the documentation is simply enforced: "The return value of gpio_request() must be checked." For gpio_direction_* and gpio_request_*, we now act accordingly. Signed-off-by: Wolfram Sang Cc: David Brownell Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/gpio.h | 10 +++++----- include/linux/gpio.h | 6 +++--- 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h index ff5c660..6098cae 100644 --- a/include/asm-generic/gpio.h +++ b/include/asm-generic/gpio.h @@ -147,11 +147,11 @@ extern struct gpio_chip *gpiochip_find(void *data, /* Always use the library code for GPIO management calls, * or when sleeping may be involved. */ -extern int gpio_request(unsigned gpio, const char *label); +extern int __must_check gpio_request(unsigned gpio, const char *label); extern void gpio_free(unsigned gpio); -extern int gpio_direction_input(unsigned gpio); -extern int gpio_direction_output(unsigned gpio, int value); +extern int __must_check gpio_direction_input(unsigned gpio); +extern int __must_check gpio_direction_output(unsigned gpio, int value); extern int gpio_set_debounce(unsigned gpio, unsigned debounce); @@ -192,8 +192,8 @@ struct gpio { const char *label; }; -extern int gpio_request_one(unsigned gpio, unsigned long flags, const char *label); -extern int gpio_request_array(struct gpio *array, size_t num); +extern int __must_check gpio_request_one(unsigned gpio, unsigned long flags, const char *label); +extern int __must_check gpio_request_array(struct gpio *array, size_t num); extern void gpio_free_array(struct gpio *array, size_t num); #ifdef CONFIG_GPIO_SYSFS diff --git a/include/linux/gpio.h b/include/linux/gpio.h index e41f7dd..1d5214a 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -29,7 +29,7 @@ static inline int gpio_is_valid(int number) return 0; } -static inline int gpio_request(unsigned gpio, const char *label) +static inline int __must_check gpio_request(unsigned gpio, const char *label) { return -ENOSYS; } @@ -42,12 +42,12 @@ static inline void gpio_free(unsigned gpio) WARN_ON(1); } -static inline int gpio_direction_input(unsigned gpio) +static inline int __must_check gpio_direction_input(unsigned gpio) { return -ENOSYS; } -static inline int gpio_direction_output(unsigned gpio, int value) +static inline int __must_check gpio_direction_output(unsigned gpio, int value) { return -ENOSYS; } -- cgit v1.1 From 5f829e405ec4e96f711165a4a7b55c271d4363e2 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Wed, 12 Jan 2011 17:00:24 -0800 Subject: gpiolib: add missing functions to generic fallback Signed-off-by: Wolfram Sang Cc: David Brownell Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gpio.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 1d5214a..f79d67f 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -13,6 +13,7 @@ #include struct device; +struct gpio; struct gpio_chip; /* @@ -34,6 +35,17 @@ static inline int __must_check gpio_request(unsigned gpio, const char *label) return -ENOSYS; } +static inline int __must_check gpio_request_one(unsigned gpio, + unsigned long flags, const char *label) +{ + return -ENOSYS; +} + +static inline int __must_check gpio_request_array(struct gpio *array, size_t num) +{ + return -ENOSYS; +} + static inline void gpio_free(unsigned gpio) { might_sleep(); @@ -42,6 +54,14 @@ static inline void gpio_free(unsigned gpio) WARN_ON(1); } +static inline void gpio_free_array(struct gpio *array, size_t num) +{ + might_sleep(); + + /* GPIO can never have been requested */ + WARN_ON(1); +} + static inline int __must_check gpio_direction_input(unsigned gpio) { return -ENOSYS; -- cgit v1.1 From e6d7202b66d99bf514c8e901db68386b1fcd6d56 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 12 Jan 2011 17:00:37 -0800 Subject: fs/char_dev.c: remove unused cdev_index() Commit 66fa12c571d3 ("ieee1394: remove the old IEEE 1394 driver stack") eliminated the only user of cdev_index(). So it can be removed too. Signed-off-by: Namhyung Kim Cc: Stefan Richter Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/cdev.h b/include/linux/cdev.h index f389e31..fb45919 100644 --- a/include/linux/cdev.h +++ b/include/linux/cdev.h @@ -28,8 +28,6 @@ int cdev_add(struct cdev *, dev_t, unsigned); void cdev_del(struct cdev *); -int cdev_index(struct inode *inode); - void cd_forget(struct inode *); extern struct backing_dev_info directly_mappable_cdev_bdi; -- cgit v1.1 From a93192a5d245a262dc52fa426de5b20467308a77 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Wed, 12 Jan 2011 17:00:38 -0800 Subject: rapidio: use common destid storage for endpoints and switches Change code to use one storage location common for switches and endpoints. This eliminates unnecessary device type checks during basic access operations. Logic that assigns destid to RIO devices stays unchanged - as before, switches use an associated destid because they do not have their own. Signed-off-by: Alexandre Bounine Cc: Kumar Gala Cc: Matt Porter Cc: Li Yang Cc: Thomas Moll Cc: Micha Nelissen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio.h | 8 +++--- include/linux/rio_drv.h | 72 +++++++++---------------------------------------- 2 files changed, 15 insertions(+), 65 deletions(-) (limited to 'include') diff --git a/include/linux/rio.h b/include/linux/rio.h index 0bed941..f6e25b3 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -98,7 +98,8 @@ union rio_pw_msg; * @dev: Device model device * @riores: RIO resources this device owns * @pwcback: port-write callback function for this device - * @destid: Network destination ID + * @destid: Network destination ID (or associated destid for switch) + * @hopcount: Hopcount to this device * @prev: Previous RIO device connected to the current one */ struct rio_dev { @@ -126,6 +127,7 @@ struct rio_dev { struct resource riores[RIO_MAX_DEV_RESOURCES]; int (*pwcback) (struct rio_dev *rdev, union rio_pw_msg *msg, int step); u16 destid; + u8 hopcount; struct rio_dev *prev; }; @@ -229,8 +231,6 @@ struct rio_net { * @node: Node in global list of switches * @rdev: Associated RIO device structure * @switchid: Switch ID that is unique across a network - * @hopcount: Hopcount to this switch - * @destid: Associated destid in the path * @route_table: Copy of switch routing table * @port_ok: Status of each port (one bit per port) - OK=1 or UNINIT=0 * @add_entry: Callback for switch-specific route add function @@ -247,8 +247,6 @@ struct rio_switch { struct list_head node; struct rio_dev *rdev; u16 switchid; - u16 hopcount; - u16 destid; u8 *route_table; u32 port_ok; int (*add_entry) (struct rio_mport * mport, u16 destid, u8 hopcount, diff --git a/include/linux/rio_drv.h b/include/linux/rio_drv.h index edc55da..e09e565 100644 --- a/include/linux/rio_drv.h +++ b/include/linux/rio_drv.h @@ -150,16 +150,8 @@ static inline int rio_local_write_config_8(struct rio_mport *port, u32 offset, static inline int rio_read_config_32(struct rio_dev *rdev, u32 offset, u32 * data) { - u8 hopcount = 0xff; - u16 destid = rdev->destid; - - if (rdev->rswitch) { - destid = rdev->rswitch->destid; - hopcount = rdev->rswitch->hopcount; - } - - return rio_mport_read_config_32(rdev->net->hport, destid, hopcount, - offset, data); + return rio_mport_read_config_32(rdev->net->hport, rdev->destid, + rdev->hopcount, offset, data); }; /** @@ -174,16 +166,8 @@ static inline int rio_read_config_32(struct rio_dev *rdev, u32 offset, static inline int rio_write_config_32(struct rio_dev *rdev, u32 offset, u32 data) { - u8 hopcount = 0xff; - u16 destid = rdev->destid; - - if (rdev->rswitch) { - destid = rdev->rswitch->destid; - hopcount = rdev->rswitch->hopcount; - } - - return rio_mport_write_config_32(rdev->net->hport, destid, hopcount, - offset, data); + return rio_mport_write_config_32(rdev->net->hport, rdev->destid, + rdev->hopcount, offset, data); }; /** @@ -198,16 +182,8 @@ static inline int rio_write_config_32(struct rio_dev *rdev, u32 offset, static inline int rio_read_config_16(struct rio_dev *rdev, u32 offset, u16 * data) { - u8 hopcount = 0xff; - u16 destid = rdev->destid; - - if (rdev->rswitch) { - destid = rdev->rswitch->destid; - hopcount = rdev->rswitch->hopcount; - } - - return rio_mport_read_config_16(rdev->net->hport, destid, hopcount, - offset, data); + return rio_mport_read_config_16(rdev->net->hport, rdev->destid, + rdev->hopcount, offset, data); }; /** @@ -222,16 +198,8 @@ static inline int rio_read_config_16(struct rio_dev *rdev, u32 offset, static inline int rio_write_config_16(struct rio_dev *rdev, u32 offset, u16 data) { - u8 hopcount = 0xff; - u16 destid = rdev->destid; - - if (rdev->rswitch) { - destid = rdev->rswitch->destid; - hopcount = rdev->rswitch->hopcount; - } - - return rio_mport_write_config_16(rdev->net->hport, destid, hopcount, - offset, data); + return rio_mport_write_config_16(rdev->net->hport, rdev->destid, + rdev->hopcount, offset, data); }; /** @@ -245,16 +213,8 @@ static inline int rio_write_config_16(struct rio_dev *rdev, u32 offset, */ static inline int rio_read_config_8(struct rio_dev *rdev, u32 offset, u8 * data) { - u8 hopcount = 0xff; - u16 destid = rdev->destid; - - if (rdev->rswitch) { - destid = rdev->rswitch->destid; - hopcount = rdev->rswitch->hopcount; - } - - return rio_mport_read_config_8(rdev->net->hport, destid, hopcount, - offset, data); + return rio_mport_read_config_8(rdev->net->hport, rdev->destid, + rdev->hopcount, offset, data); }; /** @@ -268,16 +228,8 @@ static inline int rio_read_config_8(struct rio_dev *rdev, u32 offset, u8 * data) */ static inline int rio_write_config_8(struct rio_dev *rdev, u32 offset, u8 data) { - u8 hopcount = 0xff; - u16 destid = rdev->destid; - - if (rdev->rswitch) { - destid = rdev->rswitch->destid; - hopcount = rdev->rswitch->hopcount; - } - - return rio_mport_write_config_8(rdev->net->hport, destid, hopcount, - offset, data); + return rio_mport_write_config_8(rdev->net->hport, rdev->destid, + rdev->hopcount, offset, data); }; extern int rio_mport_send_doorbell(struct rio_mport *mport, u16 destid, -- cgit v1.1 From ded05782719d0f7e79af98be7cf88c7e23a90435 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Wed, 12 Jan 2011 17:00:39 -0800 Subject: rapidio: integrate rio_switch into rio_dev Convert RIO switches device structures (rio_dev + rio_switch) into a single allocation unit. This change is based on the fact that RIO switches are using common RIO device objects anyway. Allocating RIO switch objects as RIO devices with added space for switch information simplifies handling of RIO switch devices. Signed-off-by: Alexandre Bounine Cc: Kumar Gala Cc: Matt Porter Cc: Li Yang Cc: Thomas Moll Cc: Micha Nelissen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio.h | 82 ++++++++++++++++++++++++++--------------------------- 1 file changed, 41 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/include/linux/rio.h b/include/linux/rio.h index f6e25b3..9b55885 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -71,9 +71,47 @@ extern struct device rio_bus; extern struct list_head rio_devices; /* list of all devices */ struct rio_mport; +struct rio_dev; union rio_pw_msg; /** + * struct rio_switch - RIO switch info + * @node: Node in global list of switches + * @switchid: Switch ID that is unique across a network + * @route_table: Copy of switch routing table + * @port_ok: Status of each port (one bit per port) - OK=1 or UNINIT=0 + * @add_entry: Callback for switch-specific route add function + * @get_entry: Callback for switch-specific route get function + * @clr_table: Callback for switch-specific clear route table function + * @set_domain: Callback for switch-specific domain setting function + * @get_domain: Callback for switch-specific domain get function + * @em_init: Callback for switch-specific error management init function + * @em_handle: Callback for switch-specific error management handler function + * @sw_sysfs: Callback that initializes switch-specific sysfs attributes + * @nextdev: Array of per-port pointers to the next attached device + */ +struct rio_switch { + struct list_head node; + u16 switchid; + u8 *route_table; + u32 port_ok; + int (*add_entry) (struct rio_mport *mport, u16 destid, u8 hopcount, + u16 table, u16 route_destid, u8 route_port); + int (*get_entry) (struct rio_mport *mport, u16 destid, u8 hopcount, + u16 table, u16 route_destid, u8 *route_port); + int (*clr_table) (struct rio_mport *mport, u16 destid, u8 hopcount, + u16 table); + int (*set_domain) (struct rio_mport *mport, u16 destid, u8 hopcount, + u8 sw_domain); + int (*get_domain) (struct rio_mport *mport, u16 destid, u8 hopcount, + u8 *sw_domain); + int (*em_init) (struct rio_dev *dev); + int (*em_handle) (struct rio_dev *dev, u8 swport); + int (*sw_sysfs) (struct rio_dev *dev, int create); + struct rio_dev *nextdev[0]; +}; + +/** * struct rio_dev - RIO device info * @global_list: Node in list of all RIO devices * @net_list: Node in list of RIO devices in a network @@ -93,7 +131,6 @@ union rio_pw_msg; * @phys_efptr: RIO device extended features pointer * @em_efptr: RIO Error Management features pointer * @dma_mask: Mask of bits of RIO address this device implements - * @rswitch: Pointer to &struct rio_switch if valid for this device * @driver: Driver claiming this device * @dev: Device model device * @riores: RIO resources this device owns @@ -101,6 +138,7 @@ union rio_pw_msg; * @destid: Network destination ID (or associated destid for switch) * @hopcount: Hopcount to this device * @prev: Previous RIO device connected to the current one + * @rswitch: struct rio_switch (if valid for this device) */ struct rio_dev { struct list_head global_list; /* node in list of all RIO devices */ @@ -121,7 +159,6 @@ struct rio_dev { u32 phys_efptr; u32 em_efptr; u64 dma_mask; - struct rio_switch *rswitch; /* RIO switch info */ struct rio_driver *driver; /* RIO driver claiming this device */ struct device dev; /* LDM device structure */ struct resource riores[RIO_MAX_DEV_RESOURCES]; @@ -129,11 +166,13 @@ struct rio_dev { u16 destid; u8 hopcount; struct rio_dev *prev; + struct rio_switch rswitch[0]; /* RIO switch info */ }; #define rio_dev_g(n) list_entry(n, struct rio_dev, global_list) #define rio_dev_f(n) list_entry(n, struct rio_dev, net_list) #define to_rio_dev(n) container_of(n, struct rio_dev, dev) +#define sw_to_rio_dev(n) container_of(n, struct rio_dev, rswitch[0]) /** * struct rio_msg - RIO message event @@ -226,45 +265,6 @@ struct rio_net { #define RIO_SW_SYSFS_CREATE 1 /* Create switch attributes */ #define RIO_SW_SYSFS_REMOVE 0 /* Remove switch attributes */ -/** - * struct rio_switch - RIO switch info - * @node: Node in global list of switches - * @rdev: Associated RIO device structure - * @switchid: Switch ID that is unique across a network - * @route_table: Copy of switch routing table - * @port_ok: Status of each port (one bit per port) - OK=1 or UNINIT=0 - * @add_entry: Callback for switch-specific route add function - * @get_entry: Callback for switch-specific route get function - * @clr_table: Callback for switch-specific clear route table function - * @set_domain: Callback for switch-specific domain setting function - * @get_domain: Callback for switch-specific domain get function - * @em_init: Callback for switch-specific error management initialization function - * @em_handle: Callback for switch-specific error management handler function - * @sw_sysfs: Callback that initializes switch-specific sysfs attributes - * @nextdev: Array of per-port pointers to the next attached device - */ -struct rio_switch { - struct list_head node; - struct rio_dev *rdev; - u16 switchid; - u8 *route_table; - u32 port_ok; - int (*add_entry) (struct rio_mport * mport, u16 destid, u8 hopcount, - u16 table, u16 route_destid, u8 route_port); - int (*get_entry) (struct rio_mport * mport, u16 destid, u8 hopcount, - u16 table, u16 route_destid, u8 * route_port); - int (*clr_table) (struct rio_mport *mport, u16 destid, u8 hopcount, - u16 table); - int (*set_domain) (struct rio_mport *mport, u16 destid, u8 hopcount, - u8 sw_domain); - int (*get_domain) (struct rio_mport *mport, u16 destid, u8 hopcount, - u8 *sw_domain); - int (*em_init) (struct rio_dev *dev); - int (*em_handle) (struct rio_dev *dev, u8 swport); - int (*sw_sysfs) (struct rio_dev *dev, int create); - struct rio_dev *nextdev[0]; -}; - /* Low-level architecture-dependent routines */ /** -- cgit v1.1 From e6536927e64a2511864f2141d3e5b198b3f25ba6 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Wed, 12 Jan 2011 17:00:40 -0800 Subject: rapidio: add definitions of Component Tag fields Add definition of the unique device identifier field in the component tag. RIO_CTAG_UDEVID does not take all 32 bits of the component tag value to allow future extensions to the component tag use. Selected size of the RIO_CTAG_UDEVID field (17 bits) is sufficient to accommodate maximum number of endpoints in large RIO network (16-bit id) plus switches. Signed-off-by: Alexandre Bounine Cc: Kumar Gala Cc: Matt Porter Cc: Li Yang Cc: Thomas Moll Cc: Micha Nelissen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/rio.h b/include/linux/rio.h index 9b55885..ff681eb 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -66,6 +66,16 @@ #define RIO_PW_MSG_SIZE 64 +/* + * A component tag value (stored in the component tag CSR) is used as device's + * unique identifier assigned during enumeration. Besides being used for + * identifying switches (which do not have device ID register), it also is used + * by error management notification and therefore has to be assigned + * to endpoints as well. + */ +#define RIO_CTAG_RESRVD 0xfffe0000 /* Reserved */ +#define RIO_CTAG_UDEVID 0x0001ffff /* Unique device identifier */ + extern struct bus_type rio_bus_type; extern struct device rio_bus; extern struct list_head rio_devices; /* list of all devices */ -- cgit v1.1 From 2e9d4d84847b5b05c8a049b681f15906a91e0f78 Mon Sep 17 00:00:00 2001 From: Alexandre Bounine Date: Wed, 12 Jan 2011 17:00:43 -0800 Subject: rapidio: add new idt sRIO switches Add new sRIO switch device IDs and enable a basic support for them. Signed-off-by: Alexandre Bounine Cc: Kumar Gala Cc: Matt Porter Cc: Li Yang Cc: Thomas Moll Cc: Micha Nelissen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rio_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/rio_ids.h b/include/linux/rio_ids.h index ee7b6ad..7410d33 100644 --- a/include/linux/rio_ids.h +++ b/include/linux/rio_ids.h @@ -36,5 +36,7 @@ #define RIO_DID_IDTCPS10Q 0x035e #define RIO_DID_IDTCPS1848 0x0374 #define RIO_DID_IDTCPS1616 0x0379 +#define RIO_DID_IDTVPS1616 0x0377 +#define RIO_DID_IDTSPS1616 0x0378 #endif /* LINUX_RIO_IDS_H */ -- cgit v1.1 From 6164281ab7a4d3bd42588d6b25984e960a2e032f Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Wed, 12 Jan 2011 17:00:46 -0800 Subject: user_ns: improve the user_ns on-the-slab packaging Currently on 64-bit arch the user_namespace is 2096 and when being kmalloc-ed it resides on a 4k slab wasting 2003 bytes. If we allocate a separate cache for it and reduce the hash size from 128 to 64 chains the packaging becomes *much* better - the struct is 1072 bytes and the hole between is 98 bytes. [akpm@linux-foundation.org: s/__initcall/module_init/] Signed-off-by: Pavel Emelyanov Acked-by: Serge E. Hallyn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/user_namespace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 8178156..faf4679 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -6,7 +6,7 @@ #include #include -#define UIDHASH_BITS (CONFIG_BASE_SMALL ? 3 : 8) +#define UIDHASH_BITS (CONFIG_BASE_SMALL ? 3 : 7) #define UIDHASH_SZ (1 << UIDHASH_BITS) struct user_namespace { -- cgit v1.1 From 0329326e85aaa30fb8d427828c718d565c287385 Mon Sep 17 00:00:00 2001 From: "Matti J. Aaltonen" Date: Wed, 12 Jan 2011 17:00:47 -0800 Subject: NFC: Driver for NXP Semiconductors PN544 NFC chip. Creates a new "Near Field Communication" subsystem in drivers/nfc. http://en.wikipedia.org/wiki/Near_Field_Communication is useful ;) This is a driver for the pn544 NFC device. The driver transfers ETSI messages between the device and the user space. Signed-off-by: Matti J. Aaltonen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nfc/pn544.h | 97 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 97 insertions(+) create mode 100644 include/linux/nfc/pn544.h (limited to 'include') diff --git a/include/linux/nfc/pn544.h b/include/linux/nfc/pn544.h new file mode 100644 index 0000000..7ab8521 --- /dev/null +++ b/include/linux/nfc/pn544.h @@ -0,0 +1,97 @@ +/* + * Driver include for the PN544 NFC chip. + * + * Copyright (C) Nokia Corporation + * + * Author: Jari Vanhala + * Contact: Matti Aaltoenn + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifndef _PN544_H_ +#define _PN544_H_ + +#include + +#define PN544_DRIVER_NAME "pn544" +#define PN544_MAXWINDOW_SIZE 7 +#define PN544_WINDOW_SIZE 4 +#define PN544_RETRIES 10 +#define PN544_MAX_I2C_TRANSFER 0x0400 +#define PN544_MSG_MAX_SIZE 0x21 /* at normal HCI mode */ + +/* ioctl */ +#define PN544_CHAR_BASE 'P' +#define PN544_IOR(num, dtype) _IOR(PN544_CHAR_BASE, num, dtype) +#define PN544_IOW(num, dtype) _IOW(PN544_CHAR_BASE, num, dtype) +#define PN544_GET_FW_MODE PN544_IOW(1, unsigned int) +#define PN544_SET_FW_MODE PN544_IOW(2, unsigned int) +#define PN544_GET_DEBUG PN544_IOW(3, unsigned int) +#define PN544_SET_DEBUG PN544_IOW(4, unsigned int) + +/* Timing restrictions (ms) */ +#define PN544_RESETVEN_TIME 30 /* 7 */ +#define PN544_PVDDVEN_TIME 0 +#define PN544_VBATVEN_TIME 0 +#define PN544_GPIO4VEN_TIME 0 +#define PN544_WAKEUP_ACK 5 +#define PN544_WAKEUP_GUARD (PN544_WAKEUP_ACK + 1) +#define PN544_INACTIVITY_TIME 1000 +#define PN544_INTERFRAME_DELAY 200 /* us */ +#define PN544_BAUDRATE_CHANGE 150 /* us */ + +/* Debug bits */ +#define PN544_DEBUG_BUF 0x01 +#define PN544_DEBUG_READ 0x02 +#define PN544_DEBUG_WRITE 0x04 +#define PN544_DEBUG_IRQ 0x08 +#define PN544_DEBUG_CALLS 0x10 +#define PN544_DEBUG_MODE 0x20 + +/* Normal (HCI) mode */ +#define PN544_LLC_HCI_OVERHEAD 3 /* header + crc (to length) */ +#define PN544_LLC_MIN_SIZE (1 + PN544_LLC_HCI_OVERHEAD) /* length + */ +#define PN544_LLC_MAX_DATA (PN544_MSG_MAX_SIZE - 2) +#define PN544_LLC_MAX_HCI_SIZE (PN544_LLC_MAX_DATA - 2) + +struct pn544_llc_packet { + unsigned char length; /* of rest of packet */ + unsigned char header; + unsigned char data[PN544_LLC_MAX_DATA]; /* includes crc-ccitt */ +}; + +/* Firmware upgrade mode */ +#define PN544_FW_HEADER_SIZE 3 +/* max fw transfer is 1024bytes, but I2C limits it to 0xC0 */ +#define PN544_MAX_FW_DATA (PN544_MAX_I2C_TRANSFER - PN544_FW_HEADER_SIZE) + +struct pn544_fw_packet { + unsigned char command; /* status in answer */ + unsigned char length[2]; /* big-endian order (msf) */ + unsigned char data[PN544_MAX_FW_DATA]; +}; + +#ifdef __KERNEL__ +/* board config */ +struct pn544_nfc_platform_data { + int (*request_resources) (struct i2c_client *client); + void (*free_resources) (void); + void (*enable) (int fw); + int (*test) (void); + void (*disable) (void); +}; +#endif /* __KERNEL__ */ + +#endif /* _PN544_H_ */ -- cgit v1.1 From 7a21a3cc0be92e70474cc2ab06cb074f6a7c3f09 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 12 Jan 2011 17:00:49 -0800 Subject: pps: trivial fixes Here are some very trivial fixes combined: - add macro definitions to protect header file from including several times - remove declaration for an unexistent array - fix typos Signed-off-by: Alexander Gordeev Acked-by: Rodolfo Giometti Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pps_kernel.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pps_kernel.h b/include/linux/pps_kernel.h index e0a193f..23f63c3 100644 --- a/include/linux/pps_kernel.h +++ b/include/linux/pps_kernel.h @@ -18,6 +18,9 @@ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ +#ifndef LINUX_PPS_KERNEL_H +#define LINUX_PPS_KERNEL_H + #include #include @@ -71,7 +74,6 @@ struct pps_device { extern spinlock_t pps_idr_lock; extern struct idr pps_idr; -extern struct timespec pps_irq_ts[]; extern struct device_attribute pps_attrs[]; @@ -87,3 +89,5 @@ extern void pps_unregister_source(int source); extern int pps_register_cdev(struct pps_device *pps); extern void pps_unregister_cdev(struct pps_device *pps); extern void pps_event(int source, struct pps_ktime *ts, int event, void *data); + +#endif /* LINUX_PPS_KERNEL_H */ -- cgit v1.1 From 3003d55b59aa98aeaff2773df69732b27c0cbf6a Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 12 Jan 2011 17:00:50 -0800 Subject: pps: fix race in PPS_FETCH handler There was a race in PPS_FETCH ioctl handler when several processes want to obtain PPS data simultaneously using sleeping PPS_FETCH. They all sleep most of the time in the system call. With the old approach when the first process waiting on the pps queue is waken up it makes new system call right away and zeroes pps->go. So other processes continue to sleep. This is a clear race condition because of the global 'go' variable. With the new approach pps->last_ev holds some value increasing at each PPS event. PPS_FETCH ioctl handler saves current value to the local variable at the very beginning so it can safely check that there is a new event by just comparing both variables. Signed-off-by: Alexander Gordeev Acked-by: Rodolfo Giometti Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pps_kernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pps_kernel.h b/include/linux/pps_kernel.h index 23f63c3..65194fe 100644 --- a/include/linux/pps_kernel.h +++ b/include/linux/pps_kernel.h @@ -55,7 +55,7 @@ struct pps_device { struct pps_ktime clear_tu; int current_mode; /* PPS mode at event time */ - int go; /* PPS event is arrived? */ + unsigned int last_ev; /* last PPS event id */ wait_queue_head_t queue; /* PPS event queue */ unsigned int id; /* PPS source unique ID */ -- cgit v1.1 From 6f4229b51106cbc859e9d8209b22c8a2ec749e64 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 12 Jan 2011 17:00:50 -0800 Subject: pps: unify timestamp gathering Add a helper function to gather timestamps. This way clients don't have to duplicate it. Signed-off-by: Alexander Gordeev Acked-by: Rodolfo Giometti Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pps_kernel.h | 20 +++++++++++++++++++- include/linux/serial_core.h | 5 +++-- include/linux/tty_ldisc.h | 5 +++-- 3 files changed, 25 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/pps_kernel.h b/include/linux/pps_kernel.h index 65194fe..32aa676 100644 --- a/include/linux/pps_kernel.h +++ b/include/linux/pps_kernel.h @@ -43,6 +43,10 @@ struct pps_source_info { struct device *dev; }; +struct pps_event_time { + struct timespec ts_real; +}; + /* The main struct */ struct pps_device { struct pps_source_info info; /* PSS source info */ @@ -88,6 +92,20 @@ extern int pps_register_source(struct pps_source_info *info, extern void pps_unregister_source(int source); extern int pps_register_cdev(struct pps_device *pps); extern void pps_unregister_cdev(struct pps_device *pps); -extern void pps_event(int source, struct pps_ktime *ts, int event, void *data); +extern void pps_event(int source, struct pps_event_time *ts, int event, + void *data); + +static inline void timespec_to_pps_ktime(struct pps_ktime *kt, + struct timespec ts) +{ + kt->sec = ts.tv_sec; + kt->nsec = ts.tv_nsec; +} + +static inline void pps_get_ts(struct pps_event_time *ts) +{ + getnstimeofday(&ts->ts_real); +} #endif /* LINUX_PPS_KERNEL_H */ + diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index a23fa29..758c5b0 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -212,6 +212,7 @@ #include #include #include +#include struct uart_port; struct serial_struct; @@ -528,10 +529,10 @@ uart_handle_dcd_change(struct uart_port *uport, unsigned int status) struct uart_state *state = uport->state; struct tty_port *port = &state->port; struct tty_ldisc *ld = tty_ldisc_ref(port->tty); - struct timespec ts; + struct pps_event_time ts; if (ld && ld->ops->dcd_change) - getnstimeofday(&ts); + pps_get_ts(&ts); uport->icount.dcd++; #ifdef CONFIG_HARD_PPS diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index 526d66f..763e061 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -101,7 +101,7 @@ * any pending driver I/O is completed. * * void (*dcd_change)(struct tty_struct *tty, unsigned int status, - * struct timespec *ts) + * struct pps_event_time *ts) * * Tells the discipline that the DCD pin has changed its status and * the relative timestamp. Pointer ts can be NULL. @@ -109,6 +109,7 @@ #include #include +#include struct tty_ldisc_ops { int magic; @@ -143,7 +144,7 @@ struct tty_ldisc_ops { char *fp, int count); void (*write_wakeup)(struct tty_struct *); void (*dcd_change)(struct tty_struct *, unsigned int, - struct timespec *); + struct pps_event_time *); struct module *owner; -- cgit v1.1 From 5e196d34a776420278e4117b4742cd9d3f2350ed Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 12 Jan 2011 17:00:51 -0800 Subject: pps: access pps device by direct pointer Using device index as a pointer needs some unnecessary work to be done every time the pointer is needed (in irq handler for example). Using a direct pointer is much more easy (and safe as well). Signed-off-by: Alexander Gordeev Acked-by: Rodolfo Giometti Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pps_kernel.h | 23 +++++++++-------------- 1 file changed, 9 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/pps_kernel.h b/include/linux/pps_kernel.h index 32aa676..1aedf50 100644 --- a/include/linux/pps_kernel.h +++ b/include/linux/pps_kernel.h @@ -31,13 +31,16 @@ * Global defines */ +struct pps_device; + /* The specific PPS source info */ struct pps_source_info { char name[PPS_MAX_NAME_LEN]; /* simbolic name */ char path[PPS_MAX_NAME_LEN]; /* path of connected device */ int mode; /* PPS's allowed mode */ - void (*echo)(int source, int event, void *data); /* PPS echo function */ + void (*echo)(struct pps_device *pps, + int event, void *data); /* PPS echo function */ struct module *owner; struct device *dev; @@ -65,35 +68,27 @@ struct pps_device { unsigned int id; /* PPS source unique ID */ struct cdev cdev; struct device *dev; - int devno; struct fasync_struct *async_queue; /* fasync method */ spinlock_t lock; - - atomic_t usage; /* usage count */ }; /* * Global variables */ -extern spinlock_t pps_idr_lock; -extern struct idr pps_idr; - extern struct device_attribute pps_attrs[]; /* * Exported functions */ -struct pps_device *pps_get_source(int source); -extern void pps_put_source(struct pps_device *pps); -extern int pps_register_source(struct pps_source_info *info, - int default_params); -extern void pps_unregister_source(int source); +extern struct pps_device *pps_register_source( + struct pps_source_info *info, int default_params); +extern void pps_unregister_source(struct pps_device *pps); extern int pps_register_cdev(struct pps_device *pps); extern void pps_unregister_cdev(struct pps_device *pps); -extern void pps_event(int source, struct pps_event_time *ts, int event, - void *data); +extern void pps_event(struct pps_device *pps, + struct pps_event_time *ts, int event, void *data); static inline void timespec_to_pps_ktime(struct pps_ktime *kt, struct timespec ts) -- cgit v1.1 From 12f9b1f9c11700893a7b453705d95b260d78f268 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 12 Jan 2011 17:00:55 -0800 Subject: pps: timestamp is always passed to dcd_change() Remove the code that gatheres timestamp in pps_tty_dcd_change() in case passed ts parameter is NULL because it never happens in the current code. Fix comments as well. Signed-off-by: Alexander Gordeev Acked-by: Rodolfo Giometti Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/tty_ldisc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index 763e061..ff7dc08 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -104,7 +104,7 @@ * struct pps_event_time *ts) * * Tells the discipline that the DCD pin has changed its status and - * the relative timestamp. Pointer ts can be NULL. + * the relative timestamp. Pointer ts cannot be NULL. */ #include -- cgit v1.1 From 025b40abe715d638e60516a657d354e8560c1a85 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 12 Jan 2011 17:00:56 -0800 Subject: ntp: add hardpps implementation This commit adds hardpps() implementation based upon the original one from the NTPv4 reference kernel code from David Mills. However, it is highly optimized towards very fast syncronization and maximum stickness to PPS signal. The typical error is less then a microsecond. To make it sync faster I had to throw away exponential phase filter so that the full phase offset is corrected immediately. Then I also had to throw away median phase filter because it gives a bigger error itself if used without exponential filter. Maybe we will find an appropriate filtering scheme in the future but it's not necessary if the signal quality is ok. Signed-off-by: Alexander Gordeev Acked-by: John Stultz Cc: Rodolfo Giometti Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/timex.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/timex.h b/include/linux/timex.h index 32d852f..d23999f 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -268,6 +268,7 @@ extern u64 tick_length; extern void second_overflow(void); extern void update_ntp_one_tick(void); extern int do_adjtimex(struct timex *); +extern void hardpps(const struct timespec *, const struct timespec *); int read_current_timer(unsigned long *timer_val); -- cgit v1.1 From e2c18e49a0d4f822ffc29fb4958943beb1ff08b7 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 12 Jan 2011 17:00:57 -0800 Subject: pps: capture MONOTONIC_RAW timestamps as well MONOTONIC_RAW clock timestamps are ideally suited for frequency calculation and also fit well into the original NTP hardpps design. Now phase and frequency can be adjusted separately: the former based on REALTIME clock and the latter based on MONOTONIC_RAW clock. A new function getnstime_raw_and_real is added to timekeeping subsystem to capture both timestamps at the same time and atomically. Signed-off-by: Alexander Gordeev Acked-by: John Stultz Cc: Rodolfo Giometti Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pps_kernel.h | 14 ++++++++++++++ include/linux/time.h | 2 ++ 2 files changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/pps_kernel.h b/include/linux/pps_kernel.h index 1aedf50..9404854 100644 --- a/include/linux/pps_kernel.h +++ b/include/linux/pps_kernel.h @@ -47,6 +47,9 @@ struct pps_source_info { }; struct pps_event_time { +#ifdef CONFIG_NTP_PPS + struct timespec ts_raw; +#endif /* CONFIG_NTP_PPS */ struct timespec ts_real; }; @@ -97,10 +100,21 @@ static inline void timespec_to_pps_ktime(struct pps_ktime *kt, kt->nsec = ts.tv_nsec; } +#ifdef CONFIG_NTP_PPS + +static inline void pps_get_ts(struct pps_event_time *ts) +{ + getnstime_raw_and_real(&ts->ts_raw, &ts->ts_real); +} + +#else /* CONFIG_NTP_PPS */ + static inline void pps_get_ts(struct pps_event_time *ts) { getnstimeofday(&ts->ts_real); } +#endif /* CONFIG_NTP_PPS */ + #endif /* LINUX_PPS_KERNEL_H */ diff --git a/include/linux/time.h b/include/linux/time.h index 9f15ac7..1e6d3b5 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -158,6 +158,8 @@ extern unsigned int alarm_setitimer(unsigned int seconds); extern int do_getitimer(int which, struct itimerval *value); extern void getnstimeofday(struct timespec *tv); extern void getrawmonotonic(struct timespec *ts); +extern void getnstime_raw_and_real(struct timespec *ts_raw, + struct timespec *ts_real); extern void getboottime(struct timespec *ts); extern void monotonic_to_bootbased(struct timespec *ts); -- cgit v1.1 From 717c033669ed3ceaee8df57d4562fafcc1a6267a Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Wed, 12 Jan 2011 17:00:58 -0800 Subject: pps: add kernel consumer support Add an optional feature of PPSAPI, kernel consumer support, which uses the added hardpps() function. Signed-off-by: Alexander Gordeev Acked-by: Rodolfo Giometti Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pps.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/pps.h b/include/linux/pps.h index 0194ab0..a9bb1d9 100644 --- a/include/linux/pps.h +++ b/include/linux/pps.h @@ -114,11 +114,18 @@ struct pps_fdata { struct pps_ktime timeout; }; +struct pps_bind_args { + int tsformat; /* format of time stamps */ + int edge; /* selected event type */ + int consumer; /* selected kernel consumer */ +}; + #include #define PPS_GETPARAMS _IOR('p', 0xa1, struct pps_kparams *) #define PPS_SETPARAMS _IOW('p', 0xa2, struct pps_kparams *) #define PPS_GETCAP _IOR('p', 0xa3, int *) #define PPS_FETCH _IOWR('p', 0xa4, struct pps_fdata *) +#define PPS_KC_BIND _IOW('p', 0xa5, struct pps_bind_args *) #endif /* _PPS_H_ */ -- cgit v1.1 From 8930c8aa740b12ad69f44a35137bcc39bfa3dc41 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 12 Jan 2011 17:01:03 -0800 Subject: memstick: add support for JMicron JMB 385 and 390 controllers Signed-off-by: Aries Lee Signed-off-by: Takashi Iwai Cc: Alex Dubov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index ab47732..ae0dc45 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2369,8 +2369,10 @@ #define PCI_DEVICE_ID_JMICRON_JMB38X_SD 0x2381 #define PCI_DEVICE_ID_JMICRON_JMB38X_MMC 0x2382 #define PCI_DEVICE_ID_JMICRON_JMB38X_MS 0x2383 +#define PCI_DEVICE_ID_JMICRON_JMB385_MS 0x2388 #define PCI_DEVICE_ID_JMICRON_JMB388_SD 0x2391 #define PCI_DEVICE_ID_JMICRON_JMB388_ESD 0x2392 +#define PCI_DEVICE_ID_JMICRON_JMB390_MS 0x2393 #define PCI_VENDOR_ID_KORENIX 0x1982 #define PCI_DEVICE_ID_KORENIX_JETCARDF0 0x1600 -- cgit v1.1 From beeae05138baf615a0284fc4a9022c33271ee37c Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Wed, 12 Jan 2011 17:01:09 -0800 Subject: cramfs: hide function prototypes behind __KERNEL__ macro Currently, 3 kernel function prototypes are present in a header file exported to userland. This patch fixes it. Signed-off-by: Alexander Shishkin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cramfs_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/cramfs_fs.h b/include/linux/cramfs_fs.h index 6fc2bed..0e7bf27 100644 --- a/include/linux/cramfs_fs.h +++ b/include/linux/cramfs_fs.h @@ -84,9 +84,11 @@ struct cramfs_super { | CRAMFS_FLAG_WRONG_SIGNATURE \ | CRAMFS_FLAG_SHIFTED_ROOT_OFFSET ) +#ifdef __KERNEL__ /* Uncompression interfaces to the underlying zlib */ int cramfs_uncompress_block(void *dst, int dstlen, void *src, int srclen); int cramfs_uncompress_init(void); void cramfs_uncompress_exit(void); +#endif /* __KERNEL__ */ #endif -- cgit v1.1 From 8d0a1decb4a07bcb8ef5c4d7f693eafdebc2c41b Mon Sep 17 00:00:00 2001 From: Mike Frysinger Date: Wed, 12 Jan 2011 17:01:12 -0800 Subject: romfs: have romfs_fs.h pull in necessary headers This header uses things like __be32, so pull in linux/types.h. Further, it uses BLOCK_SIZE, so pull in linux/fs.h. Signed-off-by: Mike Frysinger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/romfs_fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/romfs_fs.h b/include/linux/romfs_fs.h index c490fbc..5f57f93 100644 --- a/include/linux/romfs_fs.h +++ b/include/linux/romfs_fs.h @@ -1,6 +1,9 @@ #ifndef __LINUX_ROMFS_FS_H #define __LINUX_ROMFS_FS_H +#include +#include + /* The basic structures of the romfs filesystem */ #define ROMBSIZE BLOCK_SIZE -- cgit v1.1 From 93685ad247ef65b7d6f90ffe97b44f5cfeaf40d3 Mon Sep 17 00:00:00 2001 From: Lasse Collin Date: Wed, 12 Jan 2011 17:01:14 -0800 Subject: Decompressors: get rid of set_error_fn() macro set_error_fn() has become a useless complication after c1e7c3ae59 ("bzip2/lzma/gzip: pre-boot malloc doesn't return NULL on failure") fixed the use of error() in malloc(). Only decompress_unlzma.c had some use for it and that was easy to change too. This also gets rid of the static function pointer "error", which should have been marked as __initdata. Signed-off-by: Lasse Collin Cc: "H. Peter Anvin" Cc: Alain Knaff Cc: Albin Tonnerre Cc: Phillip Lougher Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/decompress/mm.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/decompress/mm.h b/include/linux/decompress/mm.h index ad5ec1d..a31e982 100644 --- a/include/linux/decompress/mm.h +++ b/include/linux/decompress/mm.h @@ -61,8 +61,6 @@ static void free(void *where) #define large_malloc(a) malloc(a) #define large_free(a) free(a) -#define set_error_fn(x) - #define INIT #else /* STATIC */ @@ -84,9 +82,6 @@ static void free(void *where) #define large_malloc(a) vmalloc(a) #define large_free(a) vfree(a) -static void(*error)(char *m); -#define set_error_fn(x) error = x; - #define INIT __init #define STATIC -- cgit v1.1 From 2b6b5caa6d05579bd1501006e34feec1b2aef8c4 Mon Sep 17 00:00:00 2001 From: Lasse Collin Date: Wed, 12 Jan 2011 17:01:15 -0800 Subject: Decompressors: include in Currently users of mm.h need to include to use the macros malloc() and free() provided by mm.h. This fixes it. Signed-off-by: Lasse Collin Cc: "H. Peter Anvin" Cc: Alain Knaff Cc: Albin Tonnerre Cc: Phillip Lougher Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/decompress/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/decompress/mm.h b/include/linux/decompress/mm.h index a31e982..4cb72b9 100644 --- a/include/linux/decompress/mm.h +++ b/include/linux/decompress/mm.h @@ -70,6 +70,7 @@ static void free(void *where) #include #include #include +#include #include /* Use defines rather than static inline in order to avoid spurious -- cgit v1.1 From 24fa0402a9b6a537e87e38341e78b7da86486846 Mon Sep 17 00:00:00 2001 From: Lasse Collin Date: Wed, 12 Jan 2011 17:01:22 -0800 Subject: decompressors: add XZ decompressor module In userspace, the .lzma format has become mostly a legacy file format that got superseded by the .xz format. Similarly, LZMA Utils was superseded by XZ Utils. These patches add support for XZ decompression into the kernel. Most of the code is as is from XZ Embedded . It was written for the Linux kernel but is usable in other projects too. Advantages of XZ over the current LZMA code in the kernel: - Nice API that can be used by other kernel modules; it's not limited to kernel, initramfs, and initrd decompression. - Integrity check support (CRC32) - BCJ filters improve compression of executable code on certain architectures. These together with LZMA2 can produce a few percent smaller kernel or Squashfs images than plain LZMA without making the decompression slower. This patch: Add the main decompression code (xz_dec), testing module (xz_dec_test), wrapper script (xz_wrap.sh) for the xz command line tool, and documentation. The xz_dec module is enough to have a usable XZ decompressor e.g. for Squashfs. Signed-off-by: Lasse Collin Cc: "H. Peter Anvin" Cc: Alain Knaff Cc: Albin Tonnerre Cc: Phillip Lougher Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/xz.h | 264 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 264 insertions(+) create mode 100644 include/linux/xz.h (limited to 'include') diff --git a/include/linux/xz.h b/include/linux/xz.h new file mode 100644 index 0000000..64cffa6 --- /dev/null +++ b/include/linux/xz.h @@ -0,0 +1,264 @@ +/* + * XZ decompressor + * + * Authors: Lasse Collin + * Igor Pavlov + * + * This file has been put into the public domain. + * You can do whatever you want with this file. + */ + +#ifndef XZ_H +#define XZ_H + +#ifdef __KERNEL__ +# include +# include +#else +# include +# include +#endif + +/* In Linux, this is used to make extern functions static when needed. */ +#ifndef XZ_EXTERN +# define XZ_EXTERN extern +#endif + +/** + * enum xz_mode - Operation mode + * + * @XZ_SINGLE: Single-call mode. This uses less RAM than + * than multi-call modes, because the LZMA2 + * dictionary doesn't need to be allocated as + * part of the decoder state. All required data + * structures are allocated at initialization, + * so xz_dec_run() cannot return XZ_MEM_ERROR. + * @XZ_PREALLOC: Multi-call mode with preallocated LZMA2 + * dictionary buffer. All data structures are + * allocated at initialization, so xz_dec_run() + * cannot return XZ_MEM_ERROR. + * @XZ_DYNALLOC: Multi-call mode. The LZMA2 dictionary is + * allocated once the required size has been + * parsed from the stream headers. If the + * allocation fails, xz_dec_run() will return + * XZ_MEM_ERROR. + * + * It is possible to enable support only for a subset of the above + * modes at compile time by defining XZ_DEC_SINGLE, XZ_DEC_PREALLOC, + * or XZ_DEC_DYNALLOC. The xz_dec kernel module is always compiled + * with support for all operation modes, but the preboot code may + * be built with fewer features to minimize code size. + */ +enum xz_mode { + XZ_SINGLE, + XZ_PREALLOC, + XZ_DYNALLOC +}; + +/** + * enum xz_ret - Return codes + * @XZ_OK: Everything is OK so far. More input or more + * output space is required to continue. This + * return code is possible only in multi-call mode + * (XZ_PREALLOC or XZ_DYNALLOC). + * @XZ_STREAM_END: Operation finished successfully. + * @XZ_UNSUPPORTED_CHECK: Integrity check type is not supported. Decoding + * is still possible in multi-call mode by simply + * calling xz_dec_run() again. + * Note that this return value is used only if + * XZ_DEC_ANY_CHECK was defined at build time, + * which is not used in the kernel. Unsupported + * check types return XZ_OPTIONS_ERROR if + * XZ_DEC_ANY_CHECK was not defined at build time. + * @XZ_MEM_ERROR: Allocating memory failed. This return code is + * possible only if the decoder was initialized + * with XZ_DYNALLOC. The amount of memory that was + * tried to be allocated was no more than the + * dict_max argument given to xz_dec_init(). + * @XZ_MEMLIMIT_ERROR: A bigger LZMA2 dictionary would be needed than + * allowed by the dict_max argument given to + * xz_dec_init(). This return value is possible + * only in multi-call mode (XZ_PREALLOC or + * XZ_DYNALLOC); the single-call mode (XZ_SINGLE) + * ignores the dict_max argument. + * @XZ_FORMAT_ERROR: File format was not recognized (wrong magic + * bytes). + * @XZ_OPTIONS_ERROR: This implementation doesn't support the requested + * compression options. In the decoder this means + * that the header CRC32 matches, but the header + * itself specifies something that we don't support. + * @XZ_DATA_ERROR: Compressed data is corrupt. + * @XZ_BUF_ERROR: Cannot make any progress. Details are slightly + * different between multi-call and single-call + * mode; more information below. + * + * In multi-call mode, XZ_BUF_ERROR is returned when two consecutive calls + * to XZ code cannot consume any input and cannot produce any new output. + * This happens when there is no new input available, or the output buffer + * is full while at least one output byte is still pending. Assuming your + * code is not buggy, you can get this error only when decoding a compressed + * stream that is truncated or otherwise corrupt. + * + * In single-call mode, XZ_BUF_ERROR is returned only when the output buffer + * is too small or the compressed input is corrupt in a way that makes the + * decoder produce more output than the caller expected. When it is + * (relatively) clear that the compressed input is truncated, XZ_DATA_ERROR + * is used instead of XZ_BUF_ERROR. + */ +enum xz_ret { + XZ_OK, + XZ_STREAM_END, + XZ_UNSUPPORTED_CHECK, + XZ_MEM_ERROR, + XZ_MEMLIMIT_ERROR, + XZ_FORMAT_ERROR, + XZ_OPTIONS_ERROR, + XZ_DATA_ERROR, + XZ_BUF_ERROR +}; + +/** + * struct xz_buf - Passing input and output buffers to XZ code + * @in: Beginning of the input buffer. This may be NULL if and only + * if in_pos is equal to in_size. + * @in_pos: Current position in the input buffer. This must not exceed + * in_size. + * @in_size: Size of the input buffer + * @out: Beginning of the output buffer. This may be NULL if and only + * if out_pos is equal to out_size. + * @out_pos: Current position in the output buffer. This must not exceed + * out_size. + * @out_size: Size of the output buffer + * + * Only the contents of the output buffer from out[out_pos] onward, and + * the variables in_pos and out_pos are modified by the XZ code. + */ +struct xz_buf { + const uint8_t *in; + size_t in_pos; + size_t in_size; + + uint8_t *out; + size_t out_pos; + size_t out_size; +}; + +/** + * struct xz_dec - Opaque type to hold the XZ decoder state + */ +struct xz_dec; + +/** + * xz_dec_init() - Allocate and initialize a XZ decoder state + * @mode: Operation mode + * @dict_max: Maximum size of the LZMA2 dictionary (history buffer) for + * multi-call decoding. This is ignored in single-call mode + * (mode == XZ_SINGLE). LZMA2 dictionary is always 2^n bytes + * or 2^n + 2^(n-1) bytes (the latter sizes are less common + * in practice), so other values for dict_max don't make sense. + * In the kernel, dictionary sizes of 64 KiB, 128 KiB, 256 KiB, + * 512 KiB, and 1 MiB are probably the only reasonable values, + * except for kernel and initramfs images where a bigger + * dictionary can be fine and useful. + * + * Single-call mode (XZ_SINGLE): xz_dec_run() decodes the whole stream at + * once. The caller must provide enough output space or the decoding will + * fail. The output space is used as the dictionary buffer, which is why + * there is no need to allocate the dictionary as part of the decoder's + * internal state. + * + * Because the output buffer is used as the workspace, streams encoded using + * a big dictionary are not a problem in single-call mode. It is enough that + * the output buffer is big enough to hold the actual uncompressed data; it + * can be smaller than the dictionary size stored in the stream headers. + * + * Multi-call mode with preallocated dictionary (XZ_PREALLOC): dict_max bytes + * of memory is preallocated for the LZMA2 dictionary. This way there is no + * risk that xz_dec_run() could run out of memory, since xz_dec_run() will + * never allocate any memory. Instead, if the preallocated dictionary is too + * small for decoding the given input stream, xz_dec_run() will return + * XZ_MEMLIMIT_ERROR. Thus, it is important to know what kind of data will be + * decoded to avoid allocating excessive amount of memory for the dictionary. + * + * Multi-call mode with dynamically allocated dictionary (XZ_DYNALLOC): + * dict_max specifies the maximum allowed dictionary size that xz_dec_run() + * may allocate once it has parsed the dictionary size from the stream + * headers. This way excessive allocations can be avoided while still + * limiting the maximum memory usage to a sane value to prevent running the + * system out of memory when decompressing streams from untrusted sources. + * + * On success, xz_dec_init() returns a pointer to struct xz_dec, which is + * ready to be used with xz_dec_run(). If memory allocation fails, + * xz_dec_init() returns NULL. + */ +XZ_EXTERN struct xz_dec *xz_dec_init(enum xz_mode mode, uint32_t dict_max); + +/** + * xz_dec_run() - Run the XZ decoder + * @s: Decoder state allocated using xz_dec_init() + * @b: Input and output buffers + * + * The possible return values depend on build options and operation mode. + * See enum xz_ret for details. + * + * Note that if an error occurs in single-call mode (return value is not + * XZ_STREAM_END), b->in_pos and b->out_pos are not modified and the + * contents of the output buffer from b->out[b->out_pos] onward are + * undefined. This is true even after XZ_BUF_ERROR, because with some filter + * chains, there may be a second pass over the output buffer, and this pass + * cannot be properly done if the output buffer is truncated. Thus, you + * cannot give the single-call decoder a too small buffer and then expect to + * get that amount valid data from the beginning of the stream. You must use + * the multi-call decoder if you don't want to uncompress the whole stream. + */ +XZ_EXTERN enum xz_ret xz_dec_run(struct xz_dec *s, struct xz_buf *b); + +/** + * xz_dec_reset() - Reset an already allocated decoder state + * @s: Decoder state allocated using xz_dec_init() + * + * This function can be used to reset the multi-call decoder state without + * freeing and reallocating memory with xz_dec_end() and xz_dec_init(). + * + * In single-call mode, xz_dec_reset() is always called in the beginning of + * xz_dec_run(). Thus, explicit call to xz_dec_reset() is useful only in + * multi-call mode. + */ +XZ_EXTERN void xz_dec_reset(struct xz_dec *s); + +/** + * xz_dec_end() - Free the memory allocated for the decoder state + * @s: Decoder state allocated using xz_dec_init(). If s is NULL, + * this function does nothing. + */ +XZ_EXTERN void xz_dec_end(struct xz_dec *s); + +/* + * Standalone build (userspace build or in-kernel build for boot time use) + * needs a CRC32 implementation. For normal in-kernel use, kernel's own + * CRC32 module is used instead, and users of this module don't need to + * care about the functions below. + */ +#ifndef XZ_INTERNAL_CRC32 +# ifdef __KERNEL__ +# define XZ_INTERNAL_CRC32 0 +# else +# define XZ_INTERNAL_CRC32 1 +# endif +#endif + +#if XZ_INTERNAL_CRC32 +/* + * This must be called before any other xz_* function to initialize + * the CRC32 lookup table. + */ +XZ_EXTERN void xz_crc32_init(void); + +/* + * Update CRC32 value using the polynomial from IEEE-802.3. To start a new + * calculation, the third argument must be zero. To continue the calculation, + * the previously returned value is passed as the third argument. + */ +XZ_EXTERN uint32_t xz_crc32(const uint8_t *buf, size_t size, uint32_t crc); +#endif +#endif -- cgit v1.1 From 3ebe12439ba7fc62e1d6ecb569b7287771716ca1 Mon Sep 17 00:00:00 2001 From: Lasse Collin Date: Wed, 12 Jan 2011 17:01:23 -0800 Subject: decompressors: add boot-time XZ support This implements the API defined in which is used for kernel, initramfs, and initrd decompression. This patch together with the first patch is enough for XZ-compressed initramfs and initrd; XZ-compressed kernel will need arch-specific changes. The buffering requirements described in decompress_unxz.c are stricter than with gzip, so the relevant changes should be done to the arch-specific code when adding support for XZ-compressed kernel. Similarly, the heap size in arch-specific pre-boot code may need to be increased (30 KiB is enough). The XZ decompressor needs memmove(), memeq() (memcmp() == 0), and memzero() (memset(ptr, 0, size)), which aren't available in all arch-specific pre-boot environments. I'm including simple versions in decompress_unxz.c, but a cleaner solution would naturally be nicer. Signed-off-by: Lasse Collin Cc: "H. Peter Anvin" Cc: Alain Knaff Cc: Albin Tonnerre Cc: Phillip Lougher Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/decompress/unxz.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100644 include/linux/decompress/unxz.h (limited to 'include') diff --git a/include/linux/decompress/unxz.h b/include/linux/decompress/unxz.h new file mode 100644 index 0000000..41728fc --- /dev/null +++ b/include/linux/decompress/unxz.h @@ -0,0 +1,19 @@ +/* + * Wrapper for decompressing XZ-compressed kernel, initramfs, and initrd + * + * Author: Lasse Collin + * + * This file has been put into the public domain. + * You can do whatever you want with this file. + */ + +#ifndef DECOMPRESS_UNXZ_H +#define DECOMPRESS_UNXZ_H + +int unxz(unsigned char *in, int in_size, + int (*fill)(void *dest, unsigned int size), + int (*flush)(void *src, unsigned int size), + unsigned char *out, int *in_used, + void (*error)(char *x)); + +#endif -- cgit v1.1 From 5cb2fad28fd8f95e911bed8c9342435a5b8e67de Mon Sep 17 00:00:00 2001 From: Lasse Collin Date: Wed, 12 Jan 2011 17:01:26 -0800 Subject: decompressors: remove unused constant from inflate.h Signed-off-by: Lasse Collin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/decompress/inflate.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/decompress/inflate.h b/include/linux/decompress/inflate.h index f9b06cc..8c0aef1 100644 --- a/include/linux/decompress/inflate.h +++ b/include/linux/decompress/inflate.h @@ -1,9 +1,6 @@ #ifndef INFLATE_H #define INFLATE_H -/* Other housekeeping constants */ -#define INBUFSIZ 4096 - int gunzip(unsigned char *inbuf, int len, int(*fill)(void*, unsigned int), int(*flush)(void*, unsigned int), -- cgit v1.1 From 84c89557a302e18414a011cc52b1abd034860743 Mon Sep 17 00:00:00 2001 From: Peter Jones Date: Thu, 13 Jan 2011 19:59:47 +0000 Subject: dm ioctl: allow rename to fill empty uuid Allow the uuid of a mapped device to be set after device creation. Previously the uuid (which is optional) could only be set by DM_DEV_CREATE. If no uuid was supplied it could not be set later. Sometimes it's necessary to create the device before the uuid is known, and in such cases the uuid must be filled in after the creation. This patch extends DM_DEV_RENAME to accept a uuid accompanied by a new flag DM_UUID_FLAG. This can only be done once and if no uuid was previously supplied. It cannot be used to change an existing uuid. DM_VERSION_MINOR is also bumped to 19 to indicate this interface extension is available. Signed-off-by: Peter Jones Signed-off-by: Jonathan Brassow Signed-off-by: Alasdair G Kergon --- include/linux/dm-ioctl.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/dm-ioctl.h b/include/linux/dm-ioctl.h index 49eab36..e453e11 100644 --- a/include/linux/dm-ioctl.h +++ b/include/linux/dm-ioctl.h @@ -44,7 +44,7 @@ * Remove a device, destroy any tables. * * DM_DEV_RENAME: - * Rename a device. + * Rename a device or set its uuid if none was previously supplied. * * DM_SUSPEND: * This performs both suspend and resume, depending which flag is @@ -267,9 +267,9 @@ enum { #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 18 +#define DM_VERSION_MINOR 19 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2010-06-29)" +#define DM_VERSION_EXTRA "-ioctl (2010-10-14)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ @@ -322,4 +322,10 @@ enum { */ #define DM_UEVENT_GENERATED_FLAG (1 << 13) /* Out */ +/* + * If set, rename changes the uuid not the name. Only permitted + * if no uuid was previously supplied: an existing uuid cannot be changed. + */ +#define DM_UUID_FLAG (1 << 14) /* In */ + #endif /* _LINUX_DM_IOCTL_H */ -- cgit v1.1 From 86a54a4802df10d23ccd655e2083e812fe990243 Mon Sep 17 00:00:00 2001 From: Jonathan Brassow Date: Thu, 13 Jan 2011 19:59:52 +0000 Subject: dm log userspace: add version number to comms This patch adds a 'version' field to the 'dm_ulog_request' structure. The 'version' field is taken from a portion of the unused 'padding' field in the 'dm_ulog_request' structure. This was done to avoid changing the size of the structure and possibly disrupting backwards compatibility. The version number will help notify user-space daemons when a change has been made to the kernel/userspace log API. Signed-off-by: Jonathan Brassow Signed-off-by: Mike Snitzer Signed-off-by: Alasdair G Kergon --- include/linux/dm-log-userspace.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dm-log-userspace.h b/include/linux/dm-log-userspace.h index 0c3c3a2..eeace7d 100644 --- a/include/linux/dm-log-userspace.h +++ b/include/linux/dm-log-userspace.h @@ -370,6 +370,16 @@ #define DM_ULOG_REQUEST_TYPE(request_type) \ (DM_ULOG_REQUEST_MASK & (request_type)) +/* + * DM_ULOG_REQUEST_VERSION is incremented when there is a + * change to the way information is passed between kernel + * and userspace. This could be a structure change of + * dm_ulog_request or a change in the way requests are + * issued/handled. Changes are outlined here: + * version 1: Initial implementation + */ +#define DM_ULOG_REQUEST_VERSION 1 + struct dm_ulog_request { /* * The local unique identifier (luid) and the universally unique @@ -383,8 +393,9 @@ struct dm_ulog_request { */ uint64_t luid; char uuid[DM_UUID_LEN]; - char padding[7]; /* Padding because DM_UUID_LEN = 129 */ + char padding[3]; /* Padding because DM_UUID_LEN = 129 */ + uint32_t version; /* See DM_ULOG_REQUEST_VERSION */ int32_t error; /* Used to report back processing errors */ uint32_t seq; /* Sequence number for request */ -- cgit v1.1 From 9c4376de98719d2768dd919553843de34bb094a6 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 13 Jan 2011 19:59:58 +0000 Subject: dm: use non reentrant workqueues if equivalent kmirrord_wq, kcopyd_work and md->wq are created per dm instance and serve only a single work item from the dm instance, so non-reentrant workqueues would provide the same ordering guarantees as ordered ones while allowing CPU affinity and use of the workqueues for other purposes. Switch them to non-reentrant workqueues. Signed-off-by: Tejun Heo Signed-off-by: Mike Snitzer Signed-off-by: Alasdair G Kergon --- include/linux/dm-ioctl.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/dm-ioctl.h b/include/linux/dm-ioctl.h index e453e11..78bbf47 100644 --- a/include/linux/dm-ioctl.h +++ b/include/linux/dm-ioctl.h @@ -268,8 +268,8 @@ enum { #define DM_VERSION_MAJOR 4 #define DM_VERSION_MINOR 19 -#define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2010-10-14)" +#define DM_VERSION_PATCHLEVEL 1 +#define DM_VERSION_EXTRA "-ioctl (2011-01-07)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ -- cgit v1.1 From 9d357b0787bb3c91835d5e658c3bda178f9ca419 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 13 Jan 2011 20:00:01 +0000 Subject: dm: introduce target callbacks and congestion callback DM currently implements congestion checking by checking on congestion in each component device. For raid456 we need to also check if the stripe cache is congested. Add per-target congestion checker callback support. Extending the target_callbacks structure with additional callback functions allows for establishing multiple callbacks per-target (a callback is also needed for unplug). Cc: linux-raid@vger.kernel.org Signed-off-by: NeilBrown Signed-off-by: Jonathan Brassow Signed-off-by: Mike Snitzer Signed-off-by: Alasdair G Kergon --- include/linux/device-mapper.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 2970022..4b1c63d 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -193,6 +193,12 @@ struct dm_target { char *error; }; +/* Each target can link one of these into the table */ +struct dm_target_callbacks { + struct list_head list; + int (*congested_fn) (struct dm_target_callbacks *, int); +}; + int dm_register_target(struct target_type *t); void dm_unregister_target(struct target_type *t); @@ -269,6 +275,11 @@ int dm_table_add_target(struct dm_table *t, const char *type, sector_t start, sector_t len, char *params); /* + * Target_ctr should call this if it needs to add any callbacks. + */ +void dm_table_add_target_callbacks(struct dm_table *t, struct dm_target_callbacks *cb); + +/* * Finally call this to make the table ready for use. */ int dm_table_complete(struct dm_table *t); -- cgit v1.1 From 99d03c141b40914b67d63c9d23b8da4386422ed7 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 13 Jan 2011 20:00:02 +0000 Subject: dm: per target unplug callback support Add per-target unplug callback support. Cc: linux-raid@vger.kernel.org Signed-off-by: NeilBrown Signed-off-by: Jonathan Brassow Signed-off-by: Mike Snitzer Signed-off-by: Alasdair G Kergon --- include/linux/device-mapper.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 4b1c63d..272496d 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -197,6 +197,7 @@ struct dm_target { struct dm_target_callbacks { struct list_head list; int (*congested_fn) (struct dm_target_callbacks *, int); + void (*unplug_fn)(struct dm_target_callbacks *); }; int dm_register_target(struct target_type *t); -- cgit v1.1 From d8a3515e2a9523f8ed56d1f4537d16338bda2bc2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 13 Jan 2011 17:26:46 -0800 Subject: Revert "gpiolib: annotate gpio-intialization with __must_check" This reverts commit 0fdae42d361bbb431ca0ab0efed5126a94821177, which wasn't really supposed to go in, and causes lots of annoying warnings. Quoth Andrew: "Complete brainfart - I meant to drop that patch ages ago." Quoth Greg: "Ick, yeah, that patch isn't ok to go in as-is, all of the callers need to be fixed up first, which is what I thought we had agreed on..." Reported-by: Stephen Rothwell Acked-by: Andrew Morton Acked-by: Greg KH Signed-off-by: Linus Torvalds --- include/asm-generic/gpio.h | 10 +++++----- include/linux/gpio.h | 6 +++--- 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h index 6098cae..ff5c660 100644 --- a/include/asm-generic/gpio.h +++ b/include/asm-generic/gpio.h @@ -147,11 +147,11 @@ extern struct gpio_chip *gpiochip_find(void *data, /* Always use the library code for GPIO management calls, * or when sleeping may be involved. */ -extern int __must_check gpio_request(unsigned gpio, const char *label); +extern int gpio_request(unsigned gpio, const char *label); extern void gpio_free(unsigned gpio); -extern int __must_check gpio_direction_input(unsigned gpio); -extern int __must_check gpio_direction_output(unsigned gpio, int value); +extern int gpio_direction_input(unsigned gpio); +extern int gpio_direction_output(unsigned gpio, int value); extern int gpio_set_debounce(unsigned gpio, unsigned debounce); @@ -192,8 +192,8 @@ struct gpio { const char *label; }; -extern int __must_check gpio_request_one(unsigned gpio, unsigned long flags, const char *label); -extern int __must_check gpio_request_array(struct gpio *array, size_t num); +extern int gpio_request_one(unsigned gpio, unsigned long flags, const char *label); +extern int gpio_request_array(struct gpio *array, size_t num); extern void gpio_free_array(struct gpio *array, size_t num); #ifdef CONFIG_GPIO_SYSFS diff --git a/include/linux/gpio.h b/include/linux/gpio.h index f79d67f..4b47ed9 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -30,7 +30,7 @@ static inline int gpio_is_valid(int number) return 0; } -static inline int __must_check gpio_request(unsigned gpio, const char *label) +static inline int gpio_request(unsigned gpio, const char *label) { return -ENOSYS; } @@ -62,12 +62,12 @@ static inline void gpio_free_array(struct gpio *array, size_t num) WARN_ON(1); } -static inline int __must_check gpio_direction_input(unsigned gpio) +static inline int gpio_direction_input(unsigned gpio) { return -ENOSYS; } -static inline int __must_check gpio_direction_output(unsigned gpio, int value) +static inline int gpio_direction_output(unsigned gpio, int value) { return -ENOSYS; } -- cgit v1.1 From 6c9ae009b298753a3baf71298d676a68b5a10c8f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 13 Jan 2011 15:45:38 -0800 Subject: irq: use per_cpu kstat_irqs Use modern per_cpu API to increment {soft|hard}irq counters, and use per_cpu allocation for (struct irq_desc)->kstats_irq instead of an array. This gives better SMP/NUMA locality and saves few instructions per irq. With small nr_cpuids values (8 for example), kstats_irq was a small array (less than L1_CACHE_BYTES), potentially source of false sharing. In the !CONFIG_SPARSE_IRQ case, remove the huge, NUMA/cache unfriendly kstat_irqs_all[NR_IRQS][NR_CPUS] array. Note: we still populate kstats_irq for all possible irqs in early_irq_init(). We probably could use on-demand allocations. (Code included in alloc_descs()). Problem is not all IRQS are used with a prior alloc_descs() call. kstat_irqs_this_cpu() is not used anymore, remove it. Signed-off-by: Eric Dumazet Reviewed-by: Christoph Lameter Cc: Ingo Molnar Cc: Andi Kleen Cc: Tejun Heo Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/irqdesc.h | 2 +- include/linux/kernel_stat.h | 19 +++++++++---------- 2 files changed, 10 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 979c68c..6a64c6f 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -57,7 +57,7 @@ struct irq_desc { #endif struct timer_rand_state *timer_rand_state; - unsigned int *kstat_irqs; + unsigned int __percpu *kstat_irqs; irq_flow_handler_t handle_irq; struct irqaction *action; /* IRQ action list */ unsigned int status; /* IRQ status */ diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 44e83ba..0cce2db 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -46,16 +46,14 @@ DECLARE_PER_CPU(struct kernel_stat, kstat); extern unsigned long long nr_context_switches(void); #ifndef CONFIG_GENERIC_HARDIRQS -#define kstat_irqs_this_cpu(irq) \ - (this_cpu_read(kstat.irqs[irq]) struct irq_desc; static inline void kstat_incr_irqs_this_cpu(unsigned int irq, struct irq_desc *desc) { - kstat_this_cpu.irqs[irq]++; - kstat_this_cpu.irqs_sum++; + __this_cpu_inc(kstat.irqs[irq]); + __this_cpu_inc(kstat.irqs_sum); } static inline unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) @@ -65,17 +63,18 @@ static inline unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) #else #include extern unsigned int kstat_irqs_cpu(unsigned int irq, int cpu); -#define kstat_irqs_this_cpu(DESC) \ - ((DESC)->kstat_irqs[smp_processor_id()]) -#define kstat_incr_irqs_this_cpu(irqno, DESC) do {\ - ((DESC)->kstat_irqs[smp_processor_id()]++);\ - kstat_this_cpu.irqs_sum++; } while (0) + +#define kstat_incr_irqs_this_cpu(irqno, DESC) \ +do { \ + __this_cpu_inc(*(DESC)->kstat_irqs); \ + __this_cpu_inc(kstat.irqs_sum); \ +} while (0) #endif static inline void kstat_incr_softirqs_this_cpu(unsigned int irq) { - kstat_this_cpu.softirqs[irq]++; + __this_cpu_inc(kstat.softirqs[irq]); } static inline unsigned int kstat_softirqs_cpu(unsigned int irq, int cpu) -- cgit v1.1 From 43bb40c9e3aa51a3b038c9df2c9afb4d4685614d Mon Sep 17 00:00:00 2001 From: Dave Jones Date: Thu, 13 Jan 2011 15:45:40 -0800 Subject: sched: remove long deprecated CLONE_STOPPED flag This warning was added in commit bdff746a3915 ("clone: prepare to recycle CLONE_STOPPED") three years ago. 2.6.26 came and went. As far as I know, no-one is actually using CLONE_STOPPED. Signed-off-by: Dave Jones Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 96e2321..0740253 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -21,7 +21,8 @@ #define CLONE_DETACHED 0x00400000 /* Unused, ignored */ #define CLONE_UNTRACED 0x00800000 /* set if the tracing process can't force CLONE_PTRACE on this clone */ #define CLONE_CHILD_SETTID 0x01000000 /* set the TID in the child */ -#define CLONE_STOPPED 0x02000000 /* Start in stopped state */ +/* 0x02000000 was previously the unused CLONE_STOPPED (Start in stopped state) + and is now available for re-use. */ #define CLONE_NEWUTS 0x04000000 /* New utsname group? */ #define CLONE_NEWIPC 0x08000000 /* New ipcs */ #define CLONE_NEWUSER 0x10000000 /* New user namespace */ -- cgit v1.1 From 88f5acf88ae6a9778f6d25d0d5d7ec2d57764a97 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 13 Jan 2011 15:45:41 -0800 Subject: mm: page allocator: adjust the per-cpu counter threshold when memory is low Commit aa45484 ("calculate a better estimate of NR_FREE_PAGES when memory is low") noted that watermarks were based on the vmstat NR_FREE_PAGES. To avoid synchronization overhead, these counters are maintained on a per-cpu basis and drained both periodically and when a threshold is above a threshold. On large CPU systems, the difference between the estimate and real value of NR_FREE_PAGES can be very high. The system can get into a case where pages are allocated far below the min watermark potentially causing livelock issues. The commit solved the problem by taking a better reading of NR_FREE_PAGES when memory was low. Unfortately, as reported by Shaohua Li this accurate reading can consume a large amount of CPU time on systems with many sockets due to cache line bouncing. This patch takes a different approach. For large machines where counter drift might be unsafe and while kswapd is awake, the per-cpu thresholds for the target pgdat are reduced to limit the level of drift to what should be a safe level. This incurs a performance penalty in heavy memory pressure by a factor that depends on the workload and the machine but the machine should function correctly without accidentally exhausting all memory on a node. There is an additional cost when kswapd wakes and sleeps but the event is not expected to be frequent - in Shaohua's test case, there was one recorded sleep and wake event at least. To ensure that kswapd wakes up, a safe version of zone_watermark_ok() is introduced that takes a more accurate reading of NR_FREE_PAGES when called from wakeup_kswapd, when deciding whether it is really safe to go back to sleep in sleeping_prematurely() and when deciding if a zone is really balanced or not in balance_pgdat(). We are still using an expensive function but limiting how often it is called. When the test case is reproduced, the time spent in the watermark functions is reduced. The following report is on the percentage of time spent cumulatively spent in the functions zone_nr_free_pages(), zone_watermark_ok(), __zone_watermark_ok(), zone_watermark_ok_safe(), zone_page_state_snapshot(), zone_page_state(). vanilla 11.6615% disable-threshold 0.2584% David said: : We had to pull aa454840 "mm: page allocator: calculate a better estimate : of NR_FREE_PAGES when memory is low and kswapd is awake" from 2.6.36 : internally because tests showed that it would cause the machine to stall : as the result of heavy kswapd activity. I merged it back with this fix as : it is pending in the -mm tree and it solves the issue we were seeing, so I : definitely think this should be pushed to -stable (and I would seriously : consider it for 2.6.37 inclusion even at this late date). Signed-off-by: Mel Gorman Reported-by: Shaohua Li Reviewed-by: Christoph Lameter Tested-by: Nicolas Bareil Cc: David Rientjes Cc: Kyle McMartin Cc: [2.6.37.1, 2.6.36.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 10 +++------- include/linux/vmstat.h | 5 +++++ 2 files changed, 8 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 39c24eb..4890662 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -458,12 +458,6 @@ static inline int zone_is_oom_locked(const struct zone *zone) return test_bit(ZONE_OOM_LOCKED, &zone->flags); } -#ifdef CONFIG_SMP -unsigned long zone_nr_free_pages(struct zone *zone); -#else -#define zone_nr_free_pages(zone) zone_page_state(zone, NR_FREE_PAGES) -#endif /* CONFIG_SMP */ - /* * The "priority" of VM scanning is how much of the queues we will scan in one * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the @@ -661,7 +655,9 @@ typedef struct pglist_data { extern struct mutex zonelists_mutex; void build_all_zonelists(void *data); void wakeup_kswapd(struct zone *zone, int order); -int zone_watermark_ok(struct zone *z, int order, unsigned long mark, +bool zone_watermark_ok(struct zone *z, int order, unsigned long mark, + int classzone_idx, int alloc_flags); +bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark, int classzone_idx, int alloc_flags); enum memmap_context { MEMMAP_EARLY, diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index eaaea37..e4cc21c 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -254,6 +254,8 @@ extern void dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_zone_state(struct zone *, enum zone_stat_item); void refresh_cpu_vm_stats(int); +void reduce_pgdat_percpu_threshold(pg_data_t *pgdat); +void restore_pgdat_percpu_threshold(pg_data_t *pgdat); #else /* CONFIG_SMP */ /* @@ -298,6 +300,9 @@ static inline void __dec_zone_page_state(struct page *page, #define dec_zone_page_state __dec_zone_page_state #define mod_zone_page_state __mod_zone_page_state +static inline void reduce_pgdat_percpu_threshold(pg_data_t *pgdat) { } +static inline void restore_pgdat_percpu_threshold(pg_data_t *pgdat) { } + static inline void refresh_cpu_vm_stats(int cpu) { } #endif -- cgit v1.1 From b44129b30652c8771db2265939bb8b463724043d Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 13 Jan 2011 15:45:43 -0800 Subject: mm: vmstat: use a single setter function and callback for adjusting percpu thresholds reduce_pgdat_percpu_threshold() and restore_pgdat_percpu_threshold() exist to adjust the per-cpu vmstat thresholds while kswapd is awake to avoid errors due to counter drift. The functions duplicate some code so this patch replaces them with a single set_pgdat_percpu_threshold() that takes a callback function to calculate the desired threshold as a parameter. [akpm@linux-foundation.org: readability tweak] [kosaki.motohiro@jp.fujitsu.com: set_pgdat_percpu_threshold(): don't use for_each_online_cpu] Signed-off-by: Mel Gorman Reviewed-by: Christoph Lameter Reviewed-by: KAMEZAWA Hiroyuki Signed-off-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index e4cc21c..833e676 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -254,8 +254,11 @@ extern void dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_zone_state(struct zone *, enum zone_stat_item); void refresh_cpu_vm_stats(int); -void reduce_pgdat_percpu_threshold(pg_data_t *pgdat); -void restore_pgdat_percpu_threshold(pg_data_t *pgdat); + +int calculate_pressure_threshold(struct zone *zone); +int calculate_normal_threshold(struct zone *zone); +void set_pgdat_percpu_threshold(pg_data_t *pgdat, + int (*calculate_pressure)(struct zone *)); #else /* CONFIG_SMP */ /* @@ -300,8 +303,7 @@ static inline void __dec_zone_page_state(struct page *page, #define dec_zone_page_state __dec_zone_page_state #define mod_zone_page_state __mod_zone_page_state -static inline void reduce_pgdat_percpu_threshold(pg_data_t *pgdat) { } -static inline void restore_pgdat_percpu_threshold(pg_data_t *pgdat) { } +#define set_pgdat_percpu_threshold(pgdat, callback) { } static inline void refresh_cpu_vm_stats(int cpu) { } #endif -- cgit v1.1 From 71927e84e0aebfbe5a91565c3b207af25a4e9162 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Thu, 13 Jan 2011 15:45:46 -0800 Subject: writeback: trace wakeup event for background writeback This tracks when balance_dirty_pages() tries to wakeup the flusher thread for background writeback (if it was not started already). Suggested-by: Christoph Hellwig Signed-off-by: Wu Fengguang Cc: Jan Kara Cc: Johannes Weiner Cc: Dave Chinner Cc: Jan Engelhardt Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/writeback.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 89a2b2d..4e249b9 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -81,6 +81,7 @@ DEFINE_EVENT(writeback_class, name, \ TP_ARGS(bdi)) DEFINE_WRITEBACK_EVENT(writeback_nowork); +DEFINE_WRITEBACK_EVENT(writeback_wake_background); DEFINE_WRITEBACK_EVENT(writeback_wake_thread); DEFINE_WRITEBACK_EVENT(writeback_wake_forker_thread); DEFINE_WRITEBACK_EVENT(writeback_bdi_register); -- cgit v1.1 From b7aba6984dc048503b69c2a885098cdd430832bf Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 13 Jan 2011 15:45:54 -0800 Subject: mm: compaction: add trace events for memory compaction activity In preparation for a patches promoting the use of memory compaction over lumpy reclaim, this patch adds trace points for memory compaction activity. Using them, we can monitor the scanning activity of the migration and free page scanners as well as the number and success rates of pages passed to page migration. Signed-off-by: Mel Gorman Cc: Andrea Arcangeli Cc: KOSAKI Motohiro Cc: Rik van Riel Cc: Johannes Weiner Cc: Andy Whitcroft Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/compaction.h | 74 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 74 insertions(+) create mode 100644 include/trace/events/compaction.h (limited to 'include') diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h new file mode 100644 index 0000000..388bcdd --- /dev/null +++ b/include/trace/events/compaction.h @@ -0,0 +1,74 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM compaction + +#if !defined(_TRACE_COMPACTION_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_COMPACTION_H + +#include +#include +#include "gfpflags.h" + +DECLARE_EVENT_CLASS(mm_compaction_isolate_template, + + TP_PROTO(unsigned long nr_scanned, + unsigned long nr_taken), + + TP_ARGS(nr_scanned, nr_taken), + + TP_STRUCT__entry( + __field(unsigned long, nr_scanned) + __field(unsigned long, nr_taken) + ), + + TP_fast_assign( + __entry->nr_scanned = nr_scanned; + __entry->nr_taken = nr_taken; + ), + + TP_printk("nr_scanned=%lu nr_taken=%lu", + __entry->nr_scanned, + __entry->nr_taken) +); + +DEFINE_EVENT(mm_compaction_isolate_template, mm_compaction_isolate_migratepages, + + TP_PROTO(unsigned long nr_scanned, + unsigned long nr_taken), + + TP_ARGS(nr_scanned, nr_taken) +); + +DEFINE_EVENT(mm_compaction_isolate_template, mm_compaction_isolate_freepages, + TP_PROTO(unsigned long nr_scanned, + unsigned long nr_taken), + + TP_ARGS(nr_scanned, nr_taken) +); + +TRACE_EVENT(mm_compaction_migratepages, + + TP_PROTO(unsigned long nr_migrated, + unsigned long nr_failed), + + TP_ARGS(nr_migrated, nr_failed), + + TP_STRUCT__entry( + __field(unsigned long, nr_migrated) + __field(unsigned long, nr_failed) + ), + + TP_fast_assign( + __entry->nr_migrated = nr_migrated; + __entry->nr_failed = nr_failed; + ), + + TP_printk("nr_migrated=%lu nr_failed=%lu", + __entry->nr_migrated, + __entry->nr_failed) +); + + +#endif /* _TRACE_COMPACTION_H */ + +/* This part must be outside protection */ +#include -- cgit v1.1 From ee64fc9354e515a79c7232cfde65c88ec627308b Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 13 Jan 2011 15:45:55 -0800 Subject: mm: vmscan: convert lumpy_mode into a bitmask Currently lumpy_mode is an enum and determines if lumpy reclaim is off, syncronous or asyncronous. In preparation for using compaction instead of lumpy reclaim, this patch converts the flags into a bitmap. Signed-off-by: Mel Gorman Cc: Andrea Arcangeli Cc: KOSAKI Motohiro Cc: Rik van Riel Cc: Johannes Weiner Cc: Andy Whitcroft Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/vmscan.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index c255fcc..be76429 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -25,13 +25,13 @@ #define trace_reclaim_flags(page, sync) ( \ (page_is_file_cache(page) ? RECLAIM_WB_FILE : RECLAIM_WB_ANON) | \ - (sync == LUMPY_MODE_SYNC ? RECLAIM_WB_SYNC : RECLAIM_WB_ASYNC) \ + (sync & LUMPY_MODE_SYNC ? RECLAIM_WB_SYNC : RECLAIM_WB_ASYNC) \ ) #define trace_shrink_flags(file, sync) ( \ - (sync == LUMPY_MODE_SYNC ? RECLAIM_WB_MIXED : \ + (sync & LUMPY_MODE_SYNC ? RECLAIM_WB_MIXED : \ (file ? RECLAIM_WB_FILE : RECLAIM_WB_ANON)) | \ - (sync == LUMPY_MODE_SYNC ? RECLAIM_WB_SYNC : RECLAIM_WB_ASYNC) \ + (sync & LUMPY_MODE_SYNC ? RECLAIM_WB_SYNC : RECLAIM_WB_ASYNC) \ ) TRACE_EVENT(mm_vmscan_kswapd_sleep, -- cgit v1.1 From 3e7d344970673c5334cf7b5bb27c8c0942b06126 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 13 Jan 2011 15:45:56 -0800 Subject: mm: vmscan: reclaim order-0 and use compaction instead of lumpy reclaim Lumpy reclaim is disruptive. It reclaims a large number of pages and ignores the age of the pages it reclaims. This can incur significant stalls and potentially increase the number of major faults. Compaction has reached the point where it is considered reasonably stable (meaning it has passed a lot of testing) and is a potential candidate for displacing lumpy reclaim. This patch introduces an alternative to lumpy reclaim whe compaction is available called reclaim/compaction. The basic operation is very simple - instead of selecting a contiguous range of pages to reclaim, a number of order-0 pages are reclaimed and then compaction is later by either kswapd (compact_zone_order()) or direct compaction (__alloc_pages_direct_compact()). [akpm@linux-foundation.org: fix build] [akpm@linux-foundation.org: use conventional task_struct naming] Signed-off-by: Mel Gorman Cc: Andrea Arcangeli Cc: KOSAKI Motohiro Cc: Rik van Riel Acked-by: Johannes Weiner Cc: Andy Whitcroft Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 14 ++++++++++++++ include/linux/kernel.h | 7 +++++++ 2 files changed, 21 insertions(+) (limited to 'include') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 5ac5155..2592883 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -22,6 +22,9 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write, extern int fragmentation_index(struct zone *zone, unsigned int order); extern unsigned long try_to_compact_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); +extern unsigned long compaction_suitable(struct zone *zone, int order); +extern unsigned long compact_zone_order(struct zone *zone, int order, + gfp_t gfp_mask); /* Do not skip compaction more than 64 times */ #define COMPACT_MAX_DEFER_SHIFT 6 @@ -59,6 +62,17 @@ static inline unsigned long try_to_compact_pages(struct zonelist *zonelist, return COMPACT_CONTINUE; } +static inline unsigned long compaction_suitable(struct zone *zone, int order) +{ + return COMPACT_SKIPPED; +} + +static inline unsigned long compact_zone_order(struct zone *zone, int order, + gfp_t gfp_mask) +{ + return 0; +} + static inline void defer_compaction(struct zone *zone) { } diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 57dac70..5a9d905 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -600,6 +600,13 @@ struct sysinfo { #define NUMA_BUILD 0 #endif +/* This helps us avoid #ifdef CONFIG_COMPACTION */ +#ifdef CONFIG_COMPACTION +#define COMPACTION_BUILD 1 +#else +#define COMPACTION_BUILD 0 +#endif + /* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */ #ifdef CONFIG_FTRACE_MCOUNT_RECORD # define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD -- cgit v1.1 From 77f1fe6b08b13a87391549c8a820ddc817b6f50e Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 13 Jan 2011 15:45:57 -0800 Subject: mm: migration: allow migration to operate asynchronously and avoid synchronous compaction in the faster path Migration synchronously waits for writeback if the initial passes fails. Callers of memory compaction do not necessarily want this behaviour if the caller is latency sensitive or expects that synchronous migration is not going to have a significantly better success rate. This patch adds a sync parameter to migrate_pages() allowing the caller to indicate if wait_on_page_writeback() is allowed within migration or not. For reclaim/compaction, try_to_compact_pages() is first called asynchronously, direct reclaim runs and then try_to_compact_pages() is called synchronously as there is a greater expectation that it'll succeed. [akpm@linux-foundation.org: build/merge fix] Signed-off-by: Mel Gorman Cc: Andrea Arcangeli Cc: KOSAKI Motohiro Cc: Rik van Riel Acked-by: Johannes Weiner Cc: Andy Whitcroft Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 10 ++++++---- include/linux/migrate.h | 12 ++++++++---- 2 files changed, 14 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 2592883..72cba40 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -21,10 +21,11 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write, extern int fragmentation_index(struct zone *zone, unsigned int order); extern unsigned long try_to_compact_pages(struct zonelist *zonelist, - int order, gfp_t gfp_mask, nodemask_t *mask); + int order, gfp_t gfp_mask, nodemask_t *mask, + bool sync); extern unsigned long compaction_suitable(struct zone *zone, int order); extern unsigned long compact_zone_order(struct zone *zone, int order, - gfp_t gfp_mask); + gfp_t gfp_mask, bool sync); /* Do not skip compaction more than 64 times */ #define COMPACT_MAX_DEFER_SHIFT 6 @@ -57,7 +58,8 @@ static inline bool compaction_deferred(struct zone *zone) #else static inline unsigned long try_to_compact_pages(struct zonelist *zonelist, - int order, gfp_t gfp_mask, nodemask_t *nodemask) + int order, gfp_t gfp_mask, nodemask_t *nodemask, + bool sync) { return COMPACT_CONTINUE; } @@ -68,7 +70,7 @@ static inline unsigned long compaction_suitable(struct zone *zone, int order) } static inline unsigned long compact_zone_order(struct zone *zone, int order, - gfp_t gfp_mask) + gfp_t gfp_mask, bool sync) { return 0; } diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 085527f..fa31902 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -13,9 +13,11 @@ extern void putback_lru_pages(struct list_head *l); extern int migrate_page(struct address_space *, struct page *, struct page *); extern int migrate_pages(struct list_head *l, new_page_t x, - unsigned long private, int offlining); + unsigned long private, int offlining, + bool sync); extern int migrate_huge_pages(struct list_head *l, new_page_t x, - unsigned long private, int offlining); + unsigned long private, int offlining, + bool sync); extern int fail_migrate_page(struct address_space *, struct page *, struct page *); @@ -33,9 +35,11 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, static inline void putback_lru_pages(struct list_head *l) {} static inline int migrate_pages(struct list_head *l, new_page_t x, - unsigned long private, int offlining) { return -ENOSYS; } + unsigned long private, int offlining, + bool sync) { return -ENOSYS; } static inline int migrate_huge_pages(struct list_head *l, new_page_t x, - unsigned long private, int offlining) { return -ENOSYS; } + unsigned long private, int offlining, + bool sync) { return -ENOSYS; } static inline int migrate_prep(void) { return -ENOSYS; } static inline int migrate_prep_local(void) { return -ENOSYS; } -- cgit v1.1 From 7f0f24967b0349798803260b2e4bf347cffa1990 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 13 Jan 2011 15:45:58 -0800 Subject: mm: migration: cleanup migrate_pages API by matching types for offlining and sync With the introduction of the boolean sync parameter, the API looks a little inconsistent as offlining is still an int. Convert offlining to a bool for the sake of being tidy. Signed-off-by: Mel Gorman Cc: Andrea Arcangeli Cc: KOSAKI Motohiro Cc: Rik van Riel Acked-by: Johannes Weiner Cc: Andy Whitcroft Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index fa31902..e39aeec 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -13,10 +13,10 @@ extern void putback_lru_pages(struct list_head *l); extern int migrate_page(struct address_space *, struct page *, struct page *); extern int migrate_pages(struct list_head *l, new_page_t x, - unsigned long private, int offlining, + unsigned long private, bool offlining, bool sync); extern int migrate_huge_pages(struct list_head *l, new_page_t x, - unsigned long private, int offlining, + unsigned long private, bool offlining, bool sync); extern int fail_migrate_page(struct address_space *, @@ -35,10 +35,10 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, static inline void putback_lru_pages(struct list_head *l) {} static inline int migrate_pages(struct list_head *l, new_page_t x, - unsigned long private, int offlining, + unsigned long private, bool offlining, bool sync) { return -ENOSYS; } static inline int migrate_huge_pages(struct list_head *l, new_page_t x, - unsigned long private, int offlining, + unsigned long private, bool offlining, bool sync) { return -ENOSYS; } static inline int migrate_prep(void) { return -ENOSYS; } -- cgit v1.1 From f3a310bc4e5ce7e55e1c8e25c31e63af017f3e50 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 13 Jan 2011 15:46:00 -0800 Subject: mm: vmscan: rename lumpy_mode to reclaim_mode With compaction being used instead of lumpy reclaim, the name lumpy_mode and associated variables is a bit misleading. Rename lumpy_mode to reclaim_mode which is a better fit. There is no functional change. Signed-off-by: Mel Gorman Cc: Andrea Arcangeli Cc: KOSAKI Motohiro Cc: Rik van Riel Acked-by: Johannes Weiner Cc: Andy Whitcroft Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/vmscan.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index be76429..ea422aa 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -25,13 +25,13 @@ #define trace_reclaim_flags(page, sync) ( \ (page_is_file_cache(page) ? RECLAIM_WB_FILE : RECLAIM_WB_ANON) | \ - (sync & LUMPY_MODE_SYNC ? RECLAIM_WB_SYNC : RECLAIM_WB_ASYNC) \ + (sync & RECLAIM_MODE_SYNC ? RECLAIM_WB_SYNC : RECLAIM_WB_ASYNC) \ ) #define trace_shrink_flags(file, sync) ( \ - (sync & LUMPY_MODE_SYNC ? RECLAIM_WB_MIXED : \ + (sync & RECLAIM_MODE_SYNC ? RECLAIM_WB_MIXED : \ (file ? RECLAIM_WB_FILE : RECLAIM_WB_ANON)) | \ - (sync & LUMPY_MODE_SYNC ? RECLAIM_WB_SYNC : RECLAIM_WB_ASYNC) \ + (sync & RECLAIM_MODE_SYNC ? RECLAIM_WB_SYNC : RECLAIM_WB_ASYNC) \ ) TRACE_EVENT(mm_vmscan_kswapd_sleep, -- cgit v1.1 From e5a5623b28198aa91ea71ee5d3846757fc76bc87 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Thu, 13 Jan 2011 15:46:00 -0800 Subject: mm: remove unused get_vm_area_node get_vm_area_node() is unused in the kernel and can thus be removed. Signed-off-by: David Rientjes Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 44b54f6..cb73c75 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -90,9 +90,6 @@ extern struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, void *caller); -extern struct vm_struct *get_vm_area_node(unsigned long size, - unsigned long flags, int node, - gfp_t gfp_mask); extern struct vm_struct *remove_vm_area(const void *addr); extern int map_vm_area(struct vm_struct *area, pgprot_t prot, -- cgit v1.1 From ec3f64fc9c196a304c4b7db3e1ff56d640628509 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Thu, 13 Jan 2011 15:46:01 -0800 Subject: mm: remove gfp mask from pcpu_get_vm_areas pcpu_get_vm_areas() only uses GFP_KERNEL allocations, so remove the gfp_t formal and use the mask internally. Signed-off-by: David Rientjes Cc: Christoph Lameter Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index cb73c75..c7348b8 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -117,7 +117,7 @@ extern __init void vm_area_register_early(struct vm_struct *vm, size_t align); #ifdef CONFIG_SMP struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, const size_t *sizes, int nr_vms, - size_t align, gfp_t gfp_mask); + size_t align); void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms); #endif -- cgit v1.1 From d0a21265dfb5fa8ae54e90d0fb6d1c215b10a28a Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Thu, 13 Jan 2011 15:46:02 -0800 Subject: mm: unify module_alloc code for vmalloc Four architectures (arm, mips, sparc, x86) use __vmalloc_area() for module_init(). Much of the code is duplicated and can be generalized in a globally accessible function, __vmalloc_node_range(). __vmalloc_node() now calls into __vmalloc_node_range() with a range of [VMALLOC_START, VMALLOC_END) for functionally equivalent behavior. Each architecture may then use __vmalloc_node_range() directly to remove the duplication of code. Signed-off-by: David Rientjes Cc: Christoph Lameter Cc: Russell King Cc: Ralf Baechle Cc: "David S. Miller" Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index c7348b8..4ed6fcd 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -59,8 +59,9 @@ extern void *vmalloc_exec(unsigned long size); extern void *vmalloc_32(unsigned long size); extern void *vmalloc_32_user(unsigned long size); extern void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot); -extern void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, - pgprot_t prot); +extern void *__vmalloc_node_range(unsigned long size, unsigned long align, + unsigned long start, unsigned long end, gfp_t gfp_mask, + pgprot_t prot, int node, void *caller); extern void vfree(const void *addr); extern void *vmap(struct page **pages, unsigned int count, -- cgit v1.1 From dabb16f639820267b3850d804571c70bd93d4e07 Mon Sep 17 00:00:00 2001 From: Mandeep Singh Baines Date: Thu, 13 Jan 2011 15:46:05 -0800 Subject: oom: allow a non-CAP_SYS_RESOURCE proces to oom_score_adj down We'd like to be able to oom_score_adj a process up/down as it enters/leaves the foreground. Currently, it is not possible to oom_adj down without CAP_SYS_RESOURCE. This patch allows a task to decrease its oom_score_adj back to the value that a CAP_SYS_RESOURCE thread set it to or its inherited value at fork. Assuming the thread that has forked it has oom_score_adj of 0, each process could decrease it back from 0 upon activation unless a CAP_SYS_RESOURCE thread elevated it to something higher. Alternative considered: * a setuid binary * a daemon with CAP_SYS_RESOURCE Since you don't wan't all processes to be able to reduce their oom_adj, a setuid or daemon implementation would be complex. The alternatives also have much higher overhead. This patch updated from original patch based on feedback from David Rientjes. Signed-off-by: Mandeep Singh Baines Acked-by: David Rientjes Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Cc: Rik van Riel Cc: Ying Han Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 0740253..f23b5bb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -634,6 +634,8 @@ struct signal_struct { int oom_adj; /* OOM kill score adjustment (bit shift) */ int oom_score_adj; /* OOM kill score adjustment */ + int oom_score_adj_min; /* OOM kill score adjustment minimum value. + * Only settable by CAP_SYS_RESOURCE. */ struct mutex cred_guard_mutex; /* guard against foreign influences on * credential calculations -- cgit v1.1 From 212260aa07135b327752dc02625c68cf4ce04caf Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Thu, 13 Jan 2011 15:46:06 -0800 Subject: mm: clear PageError bit in msync & fsync Temporary IO failures, eg. due to loss of both multipath paths, can permanently leave the PageError bit set on a page, resulting in msync or fsync returning -EIO over and over again, even if IO is now getting to the disk correctly. We already clear the AS_ENOSPC and AS_IO bits in mapping->flags in the filemap_fdatawait_range function. Also clearing the PageError bit on the page allows subsequent msync or fsync calls on this file to return without an error, if the subsequent IO succeeds. Unfortunately data written out in the msync or fsync call that returned -EIO can still get lost, because the page dirty bit appears to not get restored on IO error. However, the alternative could be potentially all of memory filling up with uncleanable dirty pages, hanging the system, so there is no nice choice here... Signed-off-by: Rik van Riel Acked-by: Valerie Aurora Acked-by: Jeff Layton Cc: Theodore Ts'o Acked-by: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 5f38c46..4805fde 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -198,7 +198,7 @@ static inline int __TestClearPage##uname(struct page *page) { return 0; } struct page; /* forward declaration */ TESTPAGEFLAG(Locked, locked) TESTSETFLAG(Locked, locked) -PAGEFLAG(Error, error) +PAGEFLAG(Error, error) TESTCLEARFLAG(Error, error) PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced) PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty) PAGEFLAG(LRU, lru) __CLEARPAGEFLAG(LRU, lru) -- cgit v1.1 From 110d74a921f4d272b47ef6104fcf937df808f4c8 Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Thu, 13 Jan 2011 15:46:11 -0800 Subject: mm: add FOLL_MLOCK follow_page flag. Move the code to mlock pages from __mlock_vma_pages_range() to follow_page(). This allows __mlock_vma_pages_range() to not have to break down work into 16-page batches. An additional motivation for doing this within the present patch series is that it'll make it easier for a later chagne to drop mmap_sem when blocking on disk (we'd like to be able to resume at the page that was read from disk instead of at the start of a 16-page batch). Signed-off-by: Michel Lespinasse Cc: Hugh Dickins Cc: Rik van Riel Cc: Peter Zijlstra Cc: Nick Piggin Cc: KOSAKI Motohiro Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Cc: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 721f451..9ade803 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1415,6 +1415,7 @@ struct page *follow_page(struct vm_area_struct *, unsigned long address, #define FOLL_GET 0x04 /* do get_page on page */ #define FOLL_DUMP 0x08 /* give error on hole if it would be zero */ #define FOLL_FORCE 0x10 /* get_user_pages read/write w/o permission */ +#define FOLL_MLOCK 0x40 /* mark page as mlocked */ typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, void *data); -- cgit v1.1 From 088e54658f559a13c2b988086512d76fe9e8f846 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 13 Jan 2011 15:46:16 -0800 Subject: mm: remove likely() from mapping_unevictable() The mapping_unevictable() has a likely() around the mapping parameter. This mapping parameter comes from page_mapping() which has an unlikely() that the page will be set as PAGE_MAPPING_ANON, and if so, it will return NULL. One would think that this unlikely() means that the mapping returned by page_mapping() would not be NULL, but where page_mapping() is used just above mapping_unevictable(), that unlikely() is incorrect most of the time. This means that the "likely(mapping)" in mapping_unevictable() is incorrect most of the time. Running the annotated branch profiler on my main box which runs firefox, evolution, xchat and is part of my distcc farm, I had this: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 12872836 1269443893 98 mapping_unevictable pagemap.h 51 35935762 1270265395 97 page_mapping mm.h 659 1306198001 143659 0 page_mapping mm.h 657 203131478 121586 0 page_mapping mm.h 657 5415491 1116 0 page_mapping mm.h 657 74899487 1116 0 page_mapping mm.h 657 203132845 224 0 page_mapping mm.h 659 5415464 27 0 page_mapping mm.h 659 13552 0 0 page_mapping mm.h 657 13552 0 0 page_mapping mm.h 659 242630 0 0 page_mapping mm.h 657 242630 0 0 page_mapping mm.h 659 74899487 0 0 page_mapping mm.h 659 The page_mapping() is a static inline, which is why it shows up multiple times. The mapping_unevictable() is also a static inline but seems to be used only once in my setup. The unlikely in page_mapping() was correct a total of 1909540379 times and incorrect 1270533123 times, with a 39% being incorrect. Perhaps this is enough to remove the unlikely from page_mapping() as well. Signed-off-by: Steven Rostedt Reviewed-by: KOSAKI Motohiro Acked-by: Nick Piggin Acked-by: Rik van Riel Cc: Lee Schermerhorn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 2d1ffe3..9c66e99 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -48,7 +48,7 @@ static inline void mapping_clear_unevictable(struct address_space *mapping) static inline int mapping_unevictable(struct address_space *mapping) { - if (likely(mapping)) + if (mapping) return test_bit(AS_UNEVICTABLE, &mapping->flags); return !!mapping; } -- cgit v1.1 From e20e87795834f2f14cb53baf657b91d9c39f92c8 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 13 Jan 2011 15:46:17 -0800 Subject: mm: remove unlikely() from page_mapping() page_mapping() has a unlikely that the mapping has PAGE_MAPPING_ANON set. But running the annotated branch profiler on a normal desktop system doing vairous tasks (xchat, evolution, firefox, distcc), it is not really that unlikely that the mapping here will have the PAGE_MAPPING_ANON flag set: correct incorrect % Function File Line ------- --------- - -------- ---- ---- 35935762 1270265395 97 page_mapping mm.h 659 1306198001 143659 0 page_mapping mm.h 657 203131478 121586 0 page_mapping mm.h 657 5415491 1116 0 page_mapping mm.h 657 74899487 1116 0 page_mapping mm.h 657 203132845 224 0 page_mapping mm.h 659 5415464 27 0 page_mapping mm.h 659 13552 0 0 page_mapping mm.h 657 13552 0 0 page_mapping mm.h 659 242630 0 0 page_mapping mm.h 657 242630 0 0 page_mapping mm.h 659 74899487 0 0 page_mapping mm.h 659 The page_mapping() is a static inline, which is why it shows up multiple times. The unlikely in page_mapping() was correct a total of 1909540379 times and incorrect 1270533123 times, with a 39% being incorrect. With this much of an error, it's best to simply remove the unlikely and have the compiler and branch prediction figure this out. Signed-off-by: Steven Rostedt Cc: KOSAKI Motohiro Cc: Nick Piggin Cc: Rik van Riel Cc: Lee Schermerhorn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9ade803..57e11b2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -657,7 +657,7 @@ static inline struct address_space *page_mapping(struct page *page) VM_BUG_ON(PageSlab(page)); if (unlikely(PageSwapCache(page))) mapping = &swapper_space; - else if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON)) + else if ((unsigned long)mapping & PAGE_MAPPING_ANON) mapping = NULL; return mapping; } -- cgit v1.1 From 9950474883e027e6e728cbcff25f7f2bf0c96530 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 13 Jan 2011 15:46:20 -0800 Subject: mm: kswapd: stop high-order balancing when any suitable zone is balanced Simon Kirby reported the following problem We're seeing cases on a number of servers where cache never fully grows to use all available memory. Sometimes we see servers with 4 GB of memory that never seem to have less than 1.5 GB free, even with a constantly-active VM. In some cases, these servers also swap out while this happens, even though they are constantly reading the working set into memory. We have been seeing this happening for a long time; I don't think it's anything recent, and it still happens on 2.6.36. After some debugging work by Simon, Dave Hansen and others, the prevaling theory became that kswapd is reclaiming order-3 pages requested by SLUB too aggressive about it. There are two apparent problems here. On the target machine, there is a small Normal zone in comparison to DMA32. As kswapd tries to balance all zones, it would continually try reclaiming for Normal even though DMA32 was balanced enough for callers. The second problem is that sleeping_prematurely() does not use the same logic as balance_pgdat() when deciding whether to sleep or not. This keeps kswapd artifically awake. A number of tests were run and the figures from previous postings will look very different for a few reasons. One, the old figures were forcing my network card to use GFP_ATOMIC in attempt to replicate Simon's problem. Second, I previous specified slub_min_order=3 again in an attempt to reproduce Simon's problem. In this posting, I'm depending on Simon to say whether his problem is fixed or not and these figures are to show the impact to the ordinary cases. Finally, the "vmscan" figures are taken from /proc/vmstat instead of the tracepoints. There is less information but recording is less disruptive. The first test of relevance was postmark with a process running in the background reading a large amount of anonymous memory in blocks. The objective was to vaguely simulate what was happening on Simon's machine and it's memory intensive enough to have kswapd awake. POSTMARK traceonly kanyzone Transactions per second: 156.00 ( 0.00%) 153.00 (-1.96%) Data megabytes read per second: 21.51 ( 0.00%) 21.52 ( 0.05%) Data megabytes written per second: 29.28 ( 0.00%) 29.11 (-0.58%) Files created alone per second: 250.00 ( 0.00%) 416.00 (39.90%) Files create/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) Files deleted alone per second: 520.00 ( 0.00%) 420.00 (-23.81%) Files delete/transact per second: 79.00 ( 0.00%) 76.00 (-3.95%) MMTests Statistics: duration User/Sys Time Running Test (seconds) 16.58 17.4 Total Elapsed Time (seconds) 218.48 222.47 VMstat Reclaim Statistics: vmscan Direct reclaims 0 4 Direct reclaim pages scanned 0 203 Direct reclaim pages reclaimed 0 184 Kswapd pages scanned 326631 322018 Kswapd pages reclaimed 312632 309784 Kswapd low wmark quickly 1 4 Kswapd high wmark quickly 122 475 Kswapd skip congestion_wait 1 0 Pages activated 700040 705317 Pages deactivated 212113 203922 Pages written 9875 6363 Total pages scanned 326631 322221 Total pages reclaimed 312632 309968 %age total pages scanned/reclaimed 95.71% 96.20% %age total pages scanned/written 3.02% 1.97% proc vmstat: Faults Major Faults 300 254 Minor Faults 645183 660284 Page ins 493588 486704 Page outs 4960088 4986704 Swap ins 1230 661 Swap outs 9869 6355 Performance is mildly affected because kswapd is no longer doing as much work and the background memory consumer process is getting in the way. Note that kswapd scanned and reclaimed fewer pages as it's less aggressive and overall fewer pages were scanned and reclaimed. Swap in/out is particularly reduced again reflecting kswapd throwing out fewer pages. The slight performance impact is unfortunate here but it looks like a direct result of kswapd being less aggressive. As the bug report is about too many pages being freed by kswapd, it may have to be accepted for now. The second test is a streaming IO benchmark that was previously used by Johannes to show regressions in page reclaim. MICRO traceonly kanyzone User/Sys Time Running Test (seconds) 29.29 28.87 Total Elapsed Time (seconds) 492.18 488.79 VMstat Reclaim Statistics: vmscan Direct reclaims 2128 1460 Direct reclaim pages scanned 2284822 1496067 Direct reclaim pages reclaimed 148919 110937 Kswapd pages scanned 15450014 16202876 Kswapd pages reclaimed 8503697 8537897 Kswapd low wmark quickly 3100 3397 Kswapd high wmark quickly 1860 7243 Kswapd skip congestion_wait 708 801 Pages activated 9635 9573 Pages deactivated 1432 1271 Pages written 223 1130 Total pages scanned 17734836 17698943 Total pages reclaimed 8652616 8648834 %age total pages scanned/reclaimed 48.79% 48.87% %age total pages scanned/written 0.00% 0.01% proc vmstat: Faults Major Faults 165 221 Minor Faults 9655785 9656506 Page ins 3880 7228 Page outs 37692940 37480076 Swap ins 0 69 Swap outs 19 15 Again fewer pages are scanned and reclaimed as expected and this time the test completed faster. Note that kswapd is hitting its watermarks faster (low and high wmark quickly) which I expect is due to kswapd reclaiming fewer pages. I also ran fs-mark, iozone and sysbench but there is nothing interesting to report in the figures. Performance is not significantly changed and the reclaim statistics look reasonable. Tgis patch: When the allocator enters its slow path, kswapd is woken up to balance the node. It continues working until all zones within the node are balanced. For order-0 allocations, this makes perfect sense but for higher orders it can have unintended side-effects. If the zone sizes are imbalanced, kswapd may reclaim heavily within a smaller zone discarding an excessive number of pages. The user-visible behaviour is that kswapd is awake and reclaiming even though plenty of pages are free from a suitable zone. This patch alters the "balance" logic for high-order reclaim allowing kswapd to stop if any suitable zone becomes balanced to reduce the number of pages it reclaims from other zones. kswapd still tries to ensure that order-0 watermarks for all zones are met before sleeping. Signed-off-by: Mel Gorman Reviewed-by: Minchan Kim Reviewed-by: KAMEZAWA Hiroyuki Reviewed-by: Eric B Munson Cc: Simon Kirby Cc: KOSAKI Motohiro Cc: Shaohua Li Cc: Dave Hansen Cc: Johannes Weiner Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 4890662..dad3612 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -639,6 +639,7 @@ typedef struct pglist_data { wait_queue_head_t kswapd_wait; struct task_struct *kswapd; int kswapd_max_order; + enum zone_type classzone_idx; } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) @@ -654,7 +655,7 @@ typedef struct pglist_data { extern struct mutex zonelists_mutex; void build_all_zonelists(void *data); -void wakeup_kswapd(struct zone *zone, int order); +void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx); bool zone_watermark_ok(struct zone *z, int order, unsigned long mark, int classzone_idx, int alloc_flags); bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark, -- cgit v1.1 From a826e422420b461a6247137c292ff83c4800354a Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:31 -0800 Subject: thp: mm: define MADV_HUGEPAGE Define MADV_HUGEPAGE. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Acked-by: Arnd Bergmann Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/mman-common.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/asm-generic/mman-common.h b/include/asm-generic/mman-common.h index 3da9e27..e91392f 100644 --- a/include/asm-generic/mman-common.h +++ b/include/asm-generic/mman-common.h @@ -45,6 +45,8 @@ #define MADV_MERGEABLE 12 /* KSM may merge identical pages */ #define MADV_UNMERGEABLE 13 /* KSM may not merge identical pages */ +#define MADV_HUGEPAGE 14 /* Worth backing with hugepages */ + /* compatibility flags */ #define MAP_FILE 0 -- cgit v1.1 From e9da73d67729b58bba256123e2b4651e0d8a01ac Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:32 -0800 Subject: thp: compound_lock Add a new compound_lock() needed to serialize put_page against __split_huge_page_refcount(). Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 34 ++++++++++++++++++++++++++++++++++ include/linux/page-flags.h | 12 +++++++++++- 2 files changed, 45 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 57e11b2..3b1754a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -14,6 +14,7 @@ #include #include #include +#include struct mempolicy; struct anon_vma; @@ -305,6 +306,39 @@ static inline int is_vmalloc_or_module_addr(const void *x) } #endif +static inline void compound_lock(struct page *page) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + bit_spin_lock(PG_compound_lock, &page->flags); +#endif +} + +static inline void compound_unlock(struct page *page) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + bit_spin_unlock(PG_compound_lock, &page->flags); +#endif +} + +static inline unsigned long compound_lock_irqsave(struct page *page) +{ + unsigned long uninitialized_var(flags); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + local_irq_save(flags); + compound_lock(page); +#endif + return flags; +} + +static inline void compound_unlock_irqrestore(struct page *page, + unsigned long flags) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + compound_unlock(page); + local_irq_restore(flags); +#endif +} + static inline struct page *compound_head(struct page *page) { if (unlikely(PageTail(page))) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 4805fde..5a743cc 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -108,6 +108,9 @@ enum pageflags { #ifdef CONFIG_MEMORY_FAILURE PG_hwpoison, /* hardware poisoned page. Don't touch */ #endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + PG_compound_lock, +#endif __NR_PAGEFLAGS, /* Filesystems */ @@ -397,6 +400,12 @@ static inline void __ClearPageTail(struct page *page) #define __PG_MLOCKED 0 #endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define __PG_COMPOUND_LOCK (1 << PG_compound_lock) +#else +#define __PG_COMPOUND_LOCK 0 +#endif + /* * Flags checked when a page is freed. Pages being freed should not have * these flags set. It they are, there is a problem. @@ -406,7 +415,8 @@ static inline void __ClearPageTail(struct page *page) 1 << PG_private | 1 << PG_private_2 | \ 1 << PG_buddy | 1 << PG_writeback | 1 << PG_reserved | \ 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \ - 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON) + 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON | \ + __PG_COMPOUND_LOCK) /* * Flags checked when a page is prepped for return by the page allocator. -- cgit v1.1 From 9180706344487700b40da9eca5dedd3d11cb33b4 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:32 -0800 Subject: thp: alter compound get_page/put_page Alter compound get_page/put_page to keep references on subpages too, in order to allow __split_huge_page_refcount to split an hugepage even while subpages have been pinned by one of the get_user_pages() variants. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3b1754a..a2718e1 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -353,9 +353,29 @@ static inline int page_count(struct page *page) static inline void get_page(struct page *page) { - page = compound_head(page); - VM_BUG_ON(atomic_read(&page->_count) == 0); + /* + * Getting a normal page or the head of a compound page + * requires to already have an elevated page->_count. Only if + * we're getting a tail page, the elevated page->_count is + * required only in the head page, so for tail pages the + * bugcheck only verifies that the page->_count isn't + * negative. + */ + VM_BUG_ON(atomic_read(&page->_count) < !PageTail(page)); atomic_inc(&page->_count); + /* + * Getting a tail page will elevate both the head and tail + * page->_count(s). + */ + if (unlikely(PageTail(page))) { + /* + * This is safe only because + * __split_huge_page_refcount can't run under + * get_page(). + */ + VM_BUG_ON(atomic_read(&page->first_page->_count) <= 0); + atomic_inc(&page->first_page->_count); + } } static inline struct page *virt_to_head_page(const void *x) -- cgit v1.1 From 14fd403f2146f740942d78af4e0ee59396ad8eab Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:37 -0800 Subject: thp: export maybe_mkwrite huge_memory.c needs it too when it fallbacks in copying hugepages into regular fragmented pages if hugepage allocation fails during COW. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index a2718e1..6bef67d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -430,6 +430,19 @@ static inline void set_compound_order(struct page *page, unsigned long order) } /* + * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when + * servicing faults for write access. In the normal case, do always want + * pte_mkwrite. But get_user_pages can cause write faults for mappings + * that do not have writing enabled, when used by access_process_vm. + */ +static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) +{ + if (likely(vma->vm_flags & VM_WRITE)) + pte = pte_mkwrite(pte); + return pte; +} + +/* * Multiple processes may "see" the same page. E.g. for untouched * mappings of /dev/null, all processes see the same page full of * zeroes, and text pages of executables and shared libraries have -- cgit v1.1 From 5f6e8da70a289d403975907371ce5738c726ad3f Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:40 -0800 Subject: thp: special pmd_trans_* functions These returns 0 at compile time when the config option is disabled, to allow gcc to eliminate the transparent hugepage function calls at compile time without additional #ifdefs (only the export of those functions have to be visible to gcc but they won't be required at link time and huge_memory.o can be not built at all). _PAGE_BIT_UNUSED1 is never used for pmd, only on pte. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/pgtable.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 6f3c6ae..0ab2cd2 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -348,6 +348,17 @@ extern void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn, unsigned long size); #endif +#ifndef CONFIG_TRANSPARENT_HUGEPAGE +static inline int pmd_trans_huge(pmd_t pmd) +{ + return 0; +} +static inline int pmd_trans_splitting(pmd_t pmd) +{ + return 0; +} +#endif + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_GENERIC_PGTABLE_H */ -- cgit v1.1 From e2cda322648122dc400c85ada80eaddbc612ef6a Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:40 -0800 Subject: thp: add pmd mangling generic functions Some are needed to build but not actually used on archs not supporting transparent hugepages. Others like pmdp_clear_flush are used by x86 too. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/pgtable.h | 214 ++++++++++++++++++++++++++++++------------ 1 file changed, 154 insertions(+), 60 deletions(-) (limited to 'include') diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 0ab2cd2..f1eddf7 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -5,67 +5,108 @@ #ifdef CONFIG_MMU #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS -/* - * Largely same as above, but only sets the access flags (dirty, - * accessed, and writable). Furthermore, we know it always gets set - * to a "more permissive" setting, which allows most architectures - * to optimize this. We return whether the PTE actually changed, which - * in turn instructs the caller to do things like update__mmu_cache. - * This used to be done in the caller, but sparc needs minor faults to - * force that call on sun4c so we changed this macro slightly - */ -#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \ -({ \ - int __changed = !pte_same(*(__ptep), __entry); \ - if (__changed) { \ - set_pte_at((__vma)->vm_mm, (__address), __ptep, __entry); \ - flush_tlb_page(__vma, __address); \ - } \ - __changed; \ -}) +extern int ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, + pte_t entry, int dirty); +#endif + +#ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS +extern int pmdp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + pmd_t entry, int dirty); #endif #ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -#define ptep_test_and_clear_young(__vma, __address, __ptep) \ -({ \ - pte_t __pte = *(__ptep); \ - int r = 1; \ - if (!pte_young(__pte)) \ - r = 0; \ - else \ - set_pte_at((__vma)->vm_mm, (__address), \ - (__ptep), pte_mkold(__pte)); \ - r; \ -}) +static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, + pte_t *ptep) +{ + pte_t pte = *ptep; + int r = 1; + if (!pte_young(pte)) + r = 0; + else + set_pte_at(vma->vm_mm, address, ptep, pte_mkold(pte)); + return r; +} +#endif + +#ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, + pmd_t *pmdp) +{ + pmd_t pmd = *pmdp; + int r = 1; + if (!pmd_young(pmd)) + r = 0; + else + set_pmd_at(vma->vm_mm, address, pmdp, pmd_mkold(pmd)); + return r; +} +#else /* CONFIG_TRANSPARENT_HUGEPAGE */ +static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, + pmd_t *pmdp) +{ + BUG(); + return 0; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH -#define ptep_clear_flush_young(__vma, __address, __ptep) \ -({ \ - int __young; \ - __young = ptep_test_and_clear_young(__vma, __address, __ptep); \ - if (__young) \ - flush_tlb_page(__vma, __address); \ - __young; \ -}) +int ptep_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep); +#endif + +#ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH +int pmdp_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); #endif #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR -#define ptep_get_and_clear(__mm, __address, __ptep) \ -({ \ - pte_t __pte = *(__ptep); \ - pte_clear((__mm), (__address), (__ptep)); \ - __pte; \ +static inline pte_t ptep_get_and_clear(struct mm_struct *mm, + unsigned long address, + pte_t *ptep) +{ + pte_t pte = *ptep; + pte_clear(mm, address, ptep); + return pte; +} +#endif + +#ifndef __HAVE_ARCH_PMDP_GET_AND_CLEAR +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm, + unsigned long address, + pmd_t *pmdp) +{ + pmd_t pmd = *pmdp; + pmd_clear(mm, address, pmdp); + return pmd; }) +#else /* CONFIG_TRANSPARENT_HUGEPAGE */ +static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm, + unsigned long address, + pmd_t *pmdp) +{ + BUG(); + return __pmd(0); +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL -#define ptep_get_and_clear_full(__mm, __address, __ptep, __full) \ -({ \ - pte_t __pte; \ - __pte = ptep_get_and_clear((__mm), (__address), (__ptep)); \ - __pte; \ -}) +static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, + unsigned long address, pte_t *ptep, + int full) +{ + pte_t pte; + pte = ptep_get_and_clear(mm, address, ptep); + return pte; +} #endif /* @@ -74,20 +115,25 @@ * not present, or in the process of an address space destruction. */ #ifndef __HAVE_ARCH_PTE_CLEAR_NOT_PRESENT_FULL -#define pte_clear_not_present_full(__mm, __address, __ptep, __full) \ -do { \ - pte_clear((__mm), (__address), (__ptep)); \ -} while (0) +static inline void pte_clear_not_present_full(struct mm_struct *mm, + unsigned long address, + pte_t *ptep, + int full) +{ + pte_clear(mm, address, ptep); +} #endif #ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH -#define ptep_clear_flush(__vma, __address, __ptep) \ -({ \ - pte_t __pte; \ - __pte = ptep_get_and_clear((__vma)->vm_mm, __address, __ptep); \ - flush_tlb_page(__vma, __address); \ - __pte; \ -}) +extern pte_t ptep_clear_flush(struct vm_area_struct *vma, + unsigned long address, + pte_t *ptep); +#endif + +#ifndef __HAVE_ARCH_PMDP_CLEAR_FLUSH +extern pmd_t pmdp_clear_flush(struct vm_area_struct *vma, + unsigned long address, + pmd_t *pmdp); #endif #ifndef __HAVE_ARCH_PTEP_SET_WRPROTECT @@ -99,8 +145,49 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres } #endif +#ifndef __HAVE_ARCH_PMDP_SET_WRPROTECT +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline void pmdp_set_wrprotect(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) +{ + pmd_t old_pmd = *pmdp; + set_pmd_at(mm, address, pmdp, pmd_wrprotect(old_pmd)); +} +#else /* CONFIG_TRANSPARENT_HUGEPAGE */ +static inline void pmdp_set_wrprotect(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) +{ + BUG(); +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif + +#ifndef __HAVE_ARCH_PMDP_SPLITTING_FLUSH +extern pmd_t pmdp_clear_flush(struct vm_area_struct *vma, + unsigned long address, + pmd_t *pmdp); +#endif + #ifndef __HAVE_ARCH_PTE_SAME -#define pte_same(A,B) (pte_val(A) == pte_val(B)) +static inline int pte_same(pte_t pte_a, pte_t pte_b) +{ + return pte_val(pte_a) == pte_val(pte_b); +} +#endif + +#ifndef __HAVE_ARCH_PMD_SAME +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) +{ + return pmd_val(pmd_a) == pmd_val(pmd_b); +} +#else /* CONFIG_TRANSPARENT_HUGEPAGE */ +static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) +{ + BUG(); + return 0; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef __HAVE_ARCH_PAGE_TEST_DIRTY @@ -357,6 +444,13 @@ static inline int pmd_trans_splitting(pmd_t pmd) { return 0; } +#ifndef __HAVE_ARCH_PMD_WRITE +static inline int pmd_write(pmd_t pmd) +{ + BUG(); + return 0; +} +#endif /* __HAVE_ARCH_PMD_WRITE */ #endif #endif /* !__ASSEMBLY__ */ -- cgit v1.1 From 8ac1f8320a0073f28cf9e0491af4cd98f504f92a Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:43 -0800 Subject: thp: pte alloc trans splitting pte alloc routines must wait for split_huge_page if the pmd is not present and not null (i.e. pmd_trans_splitting). The additional branches are optimized away at compile time by pmd_trans_splitting if the config option is off. However we must pass the vma down in order to know the anon_vma lock to wait for. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6bef67d..14ddd98 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1131,7 +1131,8 @@ static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud, int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); #endif -int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address); +int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, + pmd_t *pmd, unsigned long address); int __pte_alloc_kernel(pmd_t *pmd, unsigned long address); /* @@ -1200,16 +1201,18 @@ static inline void pgtable_page_dtor(struct page *page) pte_unmap(pte); \ } while (0) -#define pte_alloc_map(mm, pmd, address) \ - ((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \ - NULL: pte_offset_map(pmd, address)) +#define pte_alloc_map(mm, vma, pmd, address) \ + ((unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, vma, \ + pmd, address))? \ + NULL: pte_offset_map(pmd, address)) #define pte_alloc_map_lock(mm, pmd, address, ptlp) \ - ((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \ + ((unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, NULL, \ + pmd, address))? \ NULL: pte_offset_map_lock(mm, pmd, address, ptlp)) #define pte_alloc_kernel(pmd, address) \ - ((unlikely(!pmd_present(*(pmd))) && __pte_alloc_kernel(pmd, address))? \ + ((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd, address))? \ NULL: pte_offset_kernel(pmd, address)) extern void free_area_init(unsigned long * zones_size); -- cgit v1.1 From 91a4ee2670e0ee2b0630a0eb24fb9a87ea3acd0a Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:44 -0800 Subject: thp: add pmd mmu_notifier helpers Add mmu notifier helpers to handle pmd huge operations. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmu_notifier.h | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) (limited to 'include') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 43dcfbd..cbfab1e 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -243,6 +243,32 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) __pte; \ }) +#define pmdp_clear_flush_notify(__vma, __address, __pmdp) \ +({ \ + pmd_t __pmd; \ + struct vm_area_struct *___vma = __vma; \ + unsigned long ___address = __address; \ + VM_BUG_ON(__address & ~HPAGE_PMD_MASK); \ + mmu_notifier_invalidate_range_start(___vma->vm_mm, ___address, \ + (__address)+HPAGE_PMD_SIZE);\ + __pmd = pmdp_clear_flush(___vma, ___address, __pmdp); \ + mmu_notifier_invalidate_range_end(___vma->vm_mm, ___address, \ + (__address)+HPAGE_PMD_SIZE); \ + __pmd; \ +}) + +#define pmdp_splitting_flush_notify(__vma, __address, __pmdp) \ +({ \ + struct vm_area_struct *___vma = __vma; \ + unsigned long ___address = __address; \ + VM_BUG_ON(__address & ~HPAGE_PMD_MASK); \ + mmu_notifier_invalidate_range_start(___vma->vm_mm, ___address, \ + (__address)+HPAGE_PMD_SIZE);\ + pmdp_splitting_flush(___vma, ___address, __pmdp); \ + mmu_notifier_invalidate_range_end(___vma->vm_mm, ___address, \ + (__address)+HPAGE_PMD_SIZE); \ +}) + #define ptep_clear_flush_young_notify(__vma, __address, __ptep) \ ({ \ int __young; \ @@ -254,6 +280,17 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) __young; \ }) +#define pmdp_clear_flush_young_notify(__vma, __address, __pmdp) \ +({ \ + int __young; \ + struct vm_area_struct *___vma = __vma; \ + unsigned long ___address = __address; \ + __young = pmdp_clear_flush_young(___vma, ___address, __pmdp); \ + __young |= mmu_notifier_clear_flush_young(___vma->vm_mm, \ + ___address); \ + __young; \ +}) + #define set_pte_at_notify(__mm, __address, __ptep, __pte) \ ({ \ struct mm_struct *___mm = __mm; \ @@ -305,7 +342,10 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) } #define ptep_clear_flush_young_notify ptep_clear_flush_young +#define pmdp_clear_flush_young_notify pmdp_clear_flush_young #define ptep_clear_flush_notify ptep_clear_flush +#define pmdp_clear_flush_notify pmdp_clear_flush +#define pmdp_splitting_flush_notify pmdp_splitting_flush #define set_pte_at_notify set_pte_at #endif /* CONFIG_MMU_NOTIFIER */ -- cgit v1.1 From 4e6af67e970a2ac287739a4c526c857b5bda27ec Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:44 -0800 Subject: thp: clear page compound split_huge_page must transform a compound page to a regular page and needs ClearPageCompound. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Reviewed-by: Christoph Lameter Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 5a743cc..4835cae 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -347,7 +347,7 @@ static inline void set_page_writeback(struct page *page) * tests can be used in performance sensitive paths. PageCompound is * generally not used in hot code paths. */ -__PAGEFLAG(Head, head) +__PAGEFLAG(Head, head) CLEARPAGEFLAG(Head, head) __PAGEFLAG(Tail, tail) static inline int PageCompound(struct page *page) @@ -355,6 +355,13 @@ static inline int PageCompound(struct page *page) return page->flags & ((1L << PG_head) | (1L << PG_tail)); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline void ClearPageCompound(struct page *page) +{ + BUG_ON(!PageHead(page)); + ClearPageHead(page); +} +#endif #else /* * Reduce page flag use as much as possible by overlapping @@ -392,6 +399,14 @@ static inline void __ClearPageTail(struct page *page) page->flags &= ~PG_head_tail_mask; } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline void ClearPageCompound(struct page *page) +{ + BUG_ON((page->flags & PG_head_tail_mask) != (1 << PG_compound)); + clear_bit(PG_compound, &page->flags); +} +#endif + #endif /* !PAGEFLAGS_EXTENDED */ #ifdef CONFIG_MMU -- cgit v1.1 From e7a00c45f29c0155007aa150bf231a70fa470365 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:45 -0800 Subject: thp: add pmd_huge_pte to mm_struct This increase the size of the mm struct a bit but it is needed to preallocate one pte for each hugepage so that split_huge_page will not require a fail path. Guarantee of success is a fundamental property of split_huge_page to avoid decrasing swapping reliability and to avoid adding -ENOMEM fail paths that would otherwise force the hugepage-unaware VM code to learn rolling back in the middle of its pte mangling operations (if something we need it to learn handling pmd_trans_huge natively rather being capable of rollback). When split_huge_page runs a pte is needed to succeed the split, to map the newly splitted regular pages with a regular pte. This way all existing VM code remains backwards compatible by just adding a split_huge_page* one liner. The memory waste of those preallocated ptes is negligible and so it is worth it. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index bb7288a..26bc4e2 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -310,6 +310,9 @@ struct mm_struct { #ifdef CONFIG_MMU_NOTIFIER struct mmu_notifier_mm *mmu_notifier_mm; #endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + pgtable_t pmd_huge_pte; /* protected by page_table_lock */ +#endif /* How many tasks sharing this mm are OOM_DISABLE */ atomic_t oom_disable_count; }; -- cgit v1.1 From 47ad8475c000141eacb3ecda5e5ce4b43a9cd04d Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:47 -0800 Subject: thp: clear_copy_huge_page Move the copy/clear_huge_page functions to common code to share between hugetlb.c and huge_memory.c. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 14ddd98..cc6ab10 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1589,5 +1589,14 @@ static inline int is_hwpoison_address(unsigned long addr) extern void dump_page(struct page *page); +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) +extern void clear_huge_page(struct page *page, + unsigned long addr, + unsigned int pages_per_huge_page); +extern void copy_user_huge_page(struct page *dst, struct page *src, + unsigned long addr, struct vm_area_struct *vma, + unsigned int pages_per_huge_page); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ -- cgit v1.1 From 936a5fe6e6148c0b3ea0d792b903847d9b9931a1 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:48 -0800 Subject: thp: kvm mmu transparent hugepage support This should work for both hugetlbfs and transparent hugepages. [akpm@linux-foundation.org: bring forward PageTransCompound() addition for bisectability] Signed-off-by: Andrea Arcangeli Cc: Avi Kivity Cc: Marcelo Tosatti Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 4835cae..907f160 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -409,6 +409,18 @@ static inline void ClearPageCompound(struct page *page) #endif /* !PAGEFLAGS_EXTENDED */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline int PageTransCompound(struct page *page) +{ + return PageCompound(page); +} +#else +static inline int PageTransCompound(struct page *page) +{ + return 0; +} +#endif + #ifdef CONFIG_MMU #define __PG_MLOCKED (1 << PG_mlocked) #else -- cgit v1.1 From 32dba98e085f8b2b4345887df9abf5e0e93bfc12 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:49 -0800 Subject: thp: _GFP_NO_KSWAPD Transparent hugepage allocations must be allowed not to invoke kswapd or any other kind of indirect reclaim (especially when the defrag sysfs is control disabled). It's unacceptable to swap out anonymous pages (potentially anonymous transparent hugepages) in order to create new transparent hugepages. This is true for the MADV_HUGEPAGE areas too (swapping out a kvm virtual machine and so having it suffer an unbearable slowdown, so another one with guest physical memory marked MADV_HUGEPAGE can run 30% faster if it is running memory intensive workloads, makes no sense). If a transparent hugepage allocation fails the slowdown is minor and there is total fallback, so kswapd should never be asked to swapout memory to allow the high order allocation to succeed. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index f54adfc..49d2356 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -34,6 +34,7 @@ struct vm_area_struct; #else #define ___GFP_NOTRACK 0 #endif +#define ___GFP_NO_KSWAPD 0x400000u /* * GFP bitmasks.. @@ -81,13 +82,15 @@ struct vm_area_struct; #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) /* Page is reclaimable */ #define __GFP_NOTRACK ((__force gfp_t)___GFP_NOTRACK) /* Don't track with kmemcheck */ +#define __GFP_NO_KSWAPD ((__force gfp_t)___GFP_NO_KSWAPD) + /* * This may seem redundant, but it's a way of annotating false positives vs. * allocations that simply cannot be supported (e.g. page tables). */ #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK) -#define __GFP_BITS_SHIFT 22 /* Room for 22 __GFP_FOO bits */ +#define __GFP_BITS_SHIFT 23 /* Room for 23 __GFP_FOO bits */ #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /* This equals 0, but use constants in case they ever change */ -- cgit v1.1 From 71e3aac0724ffe8918992d76acfe3aad7d8724a5 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:52 -0800 Subject: thp: transparent hugepage core Lately I've been working to make KVM use hugepages transparently without the usual restrictions of hugetlbfs. Some of the restrictions I'd like to see removed: 1) hugepages have to be swappable or the guest physical memory remains locked in RAM and can't be paged out to swap 2) if a hugepage allocation fails, regular pages should be allocated instead and mixed in the same vma without any failure and without userland noticing 3) if some task quits and more hugepages become available in the buddy, guest physical memory backed by regular pages should be relocated on hugepages automatically in regions under madvise(MADV_HUGEPAGE) (ideally event driven by waking up the kernel deamon if the order=HPAGE_PMD_SHIFT-PAGE_SHIFT list becomes not null) 4) avoidance of reservation and maximization of use of hugepages whenever possible. Reservation (needed to avoid runtime fatal faliures) may be ok for 1 machine with 1 database with 1 database cache with 1 database cache size known at boot time. It's definitely not feasible with a virtualization hypervisor usage like RHEV-H that runs an unknown number of virtual machines with an unknown size of each virtual machine with an unknown amount of pagecache that could be potentially useful in the host for guest not using O_DIRECT (aka cache=off). hugepages in the virtualization hypervisor (and also in the guest!) are much more important than in a regular host not using virtualization, becasue with NPT/EPT they decrease the tlb-miss cacheline accesses from 24 to 19 in case only the hypervisor uses transparent hugepages, and they decrease the tlb-miss cacheline accesses from 19 to 15 in case both the linux hypervisor and the linux guest both uses this patch (though the guest will limit the addition speedup to anonymous regions only for now...). Even more important is that the tlb miss handler is much slower on a NPT/EPT guest than for a regular shadow paging or no-virtualization scenario. So maximizing the amount of virtual memory cached by the TLB pays off significantly more with NPT/EPT than without (even if there would be no significant speedup in the tlb-miss runtime). The first (and more tedious) part of this work requires allowing the VM to handle anonymous hugepages mixed with regular pages transparently on regular anonymous vmas. This is what this patch tries to achieve in the least intrusive possible way. We want hugepages and hugetlb to be used in a way so that all applications can benefit without changes (as usual we leverage the KVM virtualization design: by improving the Linux VM at large, KVM gets the performance boost too). The most important design choice is: always fallback to 4k allocation if the hugepage allocation fails! This is the _very_ opposite of some large pagecache patches that failed with -EIO back then if a 64k (or similar) allocation failed... Second important decision (to reduce the impact of the feature on the existing pagetable handling code) is that at any time we can split an hugepage into 512 regular pages and it has to be done with an operation that can't fail. This way the reliability of the swapping isn't decreased (no need to allocate memory when we are short on memory to swap) and it's trivial to plug a split_huge_page* one-liner where needed without polluting the VM. Over time we can teach mprotect, mremap and friends to handle pmd_trans_huge natively without calling split_huge_page*. The fact it can't fail isn't just for swap: if split_huge_page would return -ENOMEM (instead of the current void) we'd need to rollback the mprotect from the middle of it (ideally including undoing the split_vma) which would be a big change and in the very wrong direction (it'd likely be simpler not to call split_huge_page at all and to teach mprotect and friends to handle hugepages instead of rolling them back from the middle). In short the very value of split_huge_page is that it can't fail. The collapsing and madvise(MADV_HUGEPAGE) part will remain separated and incremental and it'll just be an "harmless" addition later if this initial part is agreed upon. It also should be noted that locking-wise replacing regular pages with hugepages is going to be very easy if compared to what I'm doing below in split_huge_page, as it will only happen when page_count(page) matches page_mapcount(page) if we can take the PG_lock and mmap_sem in write mode. collapse_huge_page will be a "best effort" that (unlike split_huge_page) can fail at the minimal sign of trouble and we can try again later. collapse_huge_page will be similar to how KSM works and the madvise(MADV_HUGEPAGE) will work similar to madvise(MADV_MERGEABLE). The default I like is that transparent hugepages are used at page fault time. This can be changed with /sys/kernel/mm/transparent_hugepage/enabled. The control knob can be set to three values "always", "madvise", "never" which mean respectively that hugepages are always used, or only inside madvise(MADV_HUGEPAGE) regions, or never used. /sys/kernel/mm/transparent_hugepage/defrag instead controls if the hugepage allocation should defrag memory aggressively "always", only inside "madvise" regions, or "never". The pmd_trans_splitting/pmd_trans_huge locking is very solid. The put_page (from get_user_page users that can't use mmu notifier like O_DIRECT) that runs against a __split_huge_page_refcount instead was a pain to serialize in a way that would result always in a coherent page count for both tail and head. I think my locking solution with a compound_lock taken only after the page_first is valid and is still a PageHead should be safe but it surely needs review from SMP race point of view. In short there is no current existing way to serialize the O_DIRECT final put_page against split_huge_page_refcount so I had to invent a new one (O_DIRECT loses knowledge on the mapping status by the time gup_fast returns so...). And I didn't want to impact all gup/gup_fast users for now, maybe if we change the gup interface substantially we can avoid this locking, I admit I didn't think too much about it because changing the gup unpinning interface would be invasive. If we ignored O_DIRECT we could stick to the existing compound refcounting code, by simply adding a get_user_pages_fast_flags(foll_flags) where KVM (and any other mmu notifier user) would call it without FOLL_GET (and if FOLL_GET isn't set we'd just BUG_ON if nobody registered itself in the current task mmu notifier list yet). But O_DIRECT is fundamental for decent performance of virtualized I/O on fast storage so we can't avoid it to solve the race of put_page against split_huge_page_refcount to achieve a complete hugepage feature for KVM. Swap and oom works fine (well just like with regular pages ;). MMU notifier is handled transparently too, with the exception of the young bit on the pmd, that didn't have a range check but I think KVM will be fine because the whole point of hugepages is that EPT/NPT will also use a huge pmd when they notice gup returns pages with PageCompound set, so they won't care of a range and there's just the pmd young bit to check in that case. NOTE: in some cases if the L2 cache is small, this may slowdown and waste memory during COWs because 4M of memory are accessed in a single fault instead of 8k (the payoff is that after COW the program can run faster). So we might want to switch the copy_huge_page (and clear_huge_page too) to not temporal stores. I also extensively researched ways to avoid this cache trashing with a full prefault logic that would cow in 8k/16k/32k/64k up to 1M (I can send those patches that fully implemented prefault) but I concluded they're not worth it and they add an huge additional complexity and they remove all tlb benefits until the full hugepage has been faulted in, to save a little bit of memory and some cache during app startup, but they still don't improve substantially the cache-trashing during startup if the prefault happens in >4k chunks. One reason is that those 4k pte entries copied are still mapped on a perfectly cache-colored hugepage, so the trashing is the worst one can generate in those copies (cow of 4k page copies aren't so well colored so they trashes less, but again this results in software running faster after the page fault). Those prefault patches allowed things like a pte where post-cow pages were local 4k regular anon pages and the not-yet-cowed pte entries were pointing in the middle of some hugepage mapped read-only. If it doesn't payoff substantially with todays hardware it will payoff even less in the future with larger l2 caches, and the prefault logic would blot the VM a lot. If one is emebdded transparent_hugepage can be disabled during boot with sysfs or with the boot commandline parameter transparent_hugepage=0 (or transparent_hugepage=2 to restrict hugepages inside madvise regions) that will ensure not a single hugepage is allocated at boot time. It is simple enough to just disable transparent hugepage globally and let transparent hugepages be allocated selectively by applications in the MADV_HUGEPAGE region (both at page fault time, and if enabled with the collapse_huge_page too through the kernel daemon). This patch supports only hugepages mapped in the pmd, archs that have smaller hugepages will not fit in this patch alone. Also some archs like power have certain tlb limits that prevents mixing different page size in the same regions so they will not fit in this framework that requires "graceful fallback" to basic PAGE_SIZE in case of physical memory fragmentation. hugetlbfs remains a perfect fit for those because its software limits happen to match the hardware limits. hugetlbfs also remains a perfect fit for hugepage sizes like 1GByte that cannot be hoped to be found not fragmented after a certain system uptime and that would be very expensive to defragment with relocation, so requiring reservation. hugetlbfs is the "reservation way", the point of transparent hugepages is not to have any reservation at all and maximizing the use of cache and hugepages at all times automatically. Some performance result: vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largep ages3 memset page fault 1566023 memset tlb miss 453854 memset second tlb miss 453321 random access tlb miss 41635 random access second tlb miss 41658 vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largepages3 memset page fault 1566471 memset tlb miss 453375 memset second tlb miss 453320 random access tlb miss 41636 random access second tlb miss 41637 vmx andrea # ./largepages3 memset page fault 1566642 memset tlb miss 453417 memset second tlb miss 453313 random access tlb miss 41630 random access second tlb miss 41647 vmx andrea # ./largepages3 memset page fault 1566872 memset tlb miss 453418 memset second tlb miss 453315 random access tlb miss 41618 random access second tlb miss 41659 vmx andrea # echo 0 > /proc/sys/vm/transparent_hugepage vmx andrea # ./largepages3 memset page fault 2182476 memset tlb miss 460305 memset second tlb miss 460179 random access tlb miss 44483 random access second tlb miss 44186 vmx andrea # ./largepages3 memset page fault 2182791 memset tlb miss 460742 memset second tlb miss 459962 random access tlb miss 43981 random access second tlb miss 43988 ============ #include #include #include #include #define SIZE (3UL*1024*1024*1024) int main() { char *p = malloc(SIZE), *p2; struct timeval before, after; gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset page fault %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); memset(p, 0, SIZE); gettimeofday(&after, NULL); printf("memset second tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); for (p2 = p; p2 < p+SIZE; p2 += 4096) *p2 = 0; gettimeofday(&after, NULL); printf("random access tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); gettimeofday(&before, NULL); for (p2 = p; p2 < p+SIZE; p2 += 4096) *p2 = 0; gettimeofday(&after, NULL); printf("random access second tlb miss %Lu\n", (after.tv_sec-before.tv_sec)*1000000UL + after.tv_usec-before.tv_usec); return 0; } ============ Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 3 ++ include/linux/huge_mm.h | 118 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/mm.h | 4 ++ include/linux/mm_inline.h | 11 ++++- include/linux/page-flags.h | 21 ++++++++ include/linux/rmap.h | 2 + include/linux/swap.h | 2 + 7 files changed, 159 insertions(+), 2 deletions(-) create mode 100644 include/linux/huge_mm.h (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 49d2356..d95082c 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -109,6 +109,9 @@ struct vm_area_struct; __GFP_HARDWALL | __GFP_HIGHMEM | \ __GFP_MOVABLE) #define GFP_IOFS (__GFP_IO | __GFP_FS) +#define GFP_TRANSHUGE (GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ + __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | \ + __GFP_NO_KSWAPD) #ifdef CONFIG_NUMA #define GFP_THISNODE (__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY) diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h new file mode 100644 index 0000000..9301824 --- /dev/null +++ b/include/linux/huge_mm.h @@ -0,0 +1,118 @@ +#ifndef _LINUX_HUGE_MM_H +#define _LINUX_HUGE_MM_H + +extern int do_huge_pmd_anonymous_page(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, + unsigned int flags); +extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, + struct vm_area_struct *vma); +extern int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, + pmd_t orig_pmd); +extern pgtable_t get_pmd_huge_pte(struct mm_struct *mm); +extern struct page *follow_trans_huge_pmd(struct mm_struct *mm, + unsigned long addr, + pmd_t *pmd, + unsigned int flags); +extern int zap_huge_pmd(struct mmu_gather *tlb, + struct vm_area_struct *vma, + pmd_t *pmd); + +enum transparent_hugepage_flag { + TRANSPARENT_HUGEPAGE_FLAG, + TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, + TRANSPARENT_HUGEPAGE_DEFRAG_FLAG, + TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, +#ifdef CONFIG_DEBUG_VM + TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG, +#endif +}; + +enum page_check_address_pmd_flag { + PAGE_CHECK_ADDRESS_PMD_FLAG, + PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG, + PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG, +}; +extern pmd_t *page_check_address_pmd(struct page *page, + struct mm_struct *mm, + unsigned long address, + enum page_check_address_pmd_flag flag); + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define HPAGE_PMD_SHIFT HPAGE_SHIFT +#define HPAGE_PMD_MASK HPAGE_MASK +#define HPAGE_PMD_SIZE HPAGE_SIZE + +#define transparent_hugepage_enabled(__vma) \ + (transparent_hugepage_flags & (1<vm_flags & VM_HUGEPAGE)) +#define transparent_hugepage_defrag(__vma) \ + ((transparent_hugepage_flags & \ + (1<vm_flags & VM_HUGEPAGE)) +#ifdef CONFIG_DEBUG_VM +#define transparent_hugepage_debug_cow() \ + (transparent_hugepage_flags & \ + (1<root->lock); \ + /* \ + * spin_unlock_wait() is just a loop in C and so the \ + * CPU can reorder anything around it. \ + */ \ + smp_mb(); \ + BUG_ON(pmd_trans_splitting(*____pmd) || \ + pmd_trans_huge(*____pmd)); \ + } while (0) +#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT) +#define HPAGE_PMD_NR (1< MAX_ORDER +#error "hugepages can't be allocated by the buddy allocator" +#endif +#else /* CONFIG_TRANSPARENT_HUGEPAGE */ +#define HPAGE_PMD_SHIFT ({ BUG(); 0; }) +#define HPAGE_PMD_MASK ({ BUG(); 0; }) +#define HPAGE_PMD_SIZE ({ BUG(); 0; }) + +#define transparent_hugepage_enabled(__vma) 0 + +#define transparent_hugepage_flags 0UL +static inline int split_huge_page(struct page *page) +{ + return 0; +} +#define split_huge_page_pmd(__mm, __pmd) \ + do { } while (0) +#define wait_split_huge_page(__anon_vma, __pmd) \ + do { } while (0) +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +#endif /* _LINUX_HUGE_MM_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index cc6ab10..78adec4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -111,6 +111,9 @@ extern unsigned int kobjsize(const void *objp); #define VM_SAO 0x20000000 /* Strong Access Ordering (powerpc) */ #define VM_PFN_AT_MMAP 0x40000000 /* PFNMAP vma that is fully mapped at mmap time */ #define VM_MERGEABLE 0x80000000 /* KSM may merge identical pages */ +#if BITS_PER_LONG > 32 +#define VM_HUGEPAGE 0x100000000UL /* MADV_HUGEPAGE marked this vma */ +#endif /* Bits set in the VMA until the stack is in its final location */ #define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ) @@ -243,6 +246,7 @@ struct inode; * files which need it (119 of them) */ #include +#include /* * Methods to modify the page usage count. diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 8835b87..650f31e 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -20,14 +20,21 @@ static inline int page_is_file_cache(struct page *page) } static inline void -add_page_to_lru_list(struct zone *zone, struct page *page, enum lru_list l) +__add_page_to_lru_list(struct zone *zone, struct page *page, enum lru_list l, + struct list_head *head) { - list_add(&page->lru, &zone->lru[l].list); + list_add(&page->lru, head); __inc_zone_state(zone, NR_LRU_BASE + l); mem_cgroup_add_lru_list(page, l); } static inline void +add_page_to_lru_list(struct zone *zone, struct page *page, enum lru_list l) +{ + __add_page_to_lru_list(zone, page, l, &zone->lru[l].list); +} + +static inline void del_page_from_lru_list(struct zone *zone, struct page *page, enum lru_list l) { list_del(&page->lru); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 907f160..4ca1241 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -410,11 +410,32 @@ static inline void ClearPageCompound(struct page *page) #endif /* !PAGEFLAGS_EXTENDED */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE +/* + * PageHuge() only returns true for hugetlbfs pages, but not for + * normal or transparent huge pages. + * + * PageTransHuge() returns true for both transparent huge and + * hugetlbfs pages, but not normal pages. PageTransHuge() can only be + * called only in the core VM paths where hugetlbfs pages can't exist. + */ +static inline int PageTransHuge(struct page *page) +{ + VM_BUG_ON(PageTail(page)); + return PageHead(page); +} + static inline int PageTransCompound(struct page *page) { return PageCompound(page); } + #else + +static inline int PageTransHuge(struct page *page) +{ + return 0; +} + static inline int PageTransCompound(struct page *page) { return 0; diff --git a/include/linux/rmap.h b/include/linux/rmap.h index bb83c0d..e9fd04c 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -198,6 +198,8 @@ enum ttu_flags { }; #define TTU_ACTION(x) ((x) & TTU_ACTION_MASK) +bool is_vma_temporary_stack(struct vm_area_struct *vma); + int try_to_unmap(struct page *, enum ttu_flags flags); int try_to_unmap_one(struct page *, struct vm_area_struct *, unsigned long address, enum ttu_flags flags); diff --git a/include/linux/swap.h b/include/linux/swap.h index eba53e7..4d55932 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -208,6 +208,8 @@ extern unsigned int nr_free_pagecache_pages(void); /* linux/mm/swap.c */ extern void __lru_cache_add(struct page *, enum lru_list lru); extern void lru_cache_add_lru(struct page *, enum lru_list lru); +extern void lru_add_page_tail(struct zone* zone, + struct page *page, struct page *page_tail); extern void activate_page(struct page *); extern void mark_page_accessed(struct page *); extern void lru_add_drain(void); -- cgit v1.1 From 0af4e98b6b095c74588af04872f83d333c958c32 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:55 -0800 Subject: thp: madvise(MADV_HUGEPAGE) Add madvise MADV_HUGEPAGE to mark regions that are important to be hugepage backed. Return -EINVAL if the vma is not of an anonymous type, or the feature isn't built into the kernel. Never silently return success. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 9301824..d9ab70d 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -97,6 +97,7 @@ extern void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd); #if HPAGE_PMD_ORDER > MAX_ORDER #error "hugepages can't be allocated by the buddy allocator" #endif +extern int hugepage_madvise(unsigned long *vm_flags); #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUG(); 0; }) #define HPAGE_PMD_MASK ({ BUG(); 0; }) @@ -113,6 +114,11 @@ static inline int split_huge_page(struct page *page) do { } while (0) #define wait_split_huge_page(__anon_vma, __pmd) \ do { } while (0) +static inline int hugepage_madvise(unsigned long *vm_flags) +{ + BUG(); + return 0; +} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* _LINUX_HUGE_MM_H */ -- cgit v1.1 From 500d65d471018d9a13b0d51b7e141ed2a3555c1d Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:55 -0800 Subject: thp: pmd_trans_huge migrate bugcheck No pmd_trans_huge should ever materialize in migration ptes areas, because we split the hugepage before migration ptes are instantiated. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 78adec4..2ec5138 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1490,6 +1490,7 @@ struct page *follow_page(struct vm_area_struct *, unsigned long address, #define FOLL_DUMP 0x08 /* give error on hole if it would be zero */ #define FOLL_FORCE 0x10 /* get_user_pages read/write w/o permission */ #define FOLL_MLOCK 0x40 /* mark page as mlocked */ +#define FOLL_SPLIT 0x80 /* don't return transhuge pages, split them */ typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, void *data); -- cgit v1.1 From 79134171df238171daa4c024a42b77b401ccb00b Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:58 -0800 Subject: thp: transparent hugepage vmstat Add hugepage stat information to /proc/vmstat and /proc/meminfo. Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index dad3612..02ecb01 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -114,6 +114,7 @@ enum zone_stat_item { NUMA_LOCAL, /* allocation from local node */ NUMA_OTHER, /* allocation from other node */ #endif + NR_ANON_TRANSPARENT_HUGEPAGES, NR_VM_ZONE_STAT_ITEMS }; /* -- cgit v1.1 From ba76149f47d8c939efa0acc07a191237af900471 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:46:58 -0800 Subject: thp: khugepaged Add khugepaged to relocate fragmented pages into hugepages if new hugepages become available. (this is indipendent of the defrag logic that will have to make new hugepages available) The fundamental reason why khugepaged is unavoidable, is that some memory can be fragmented and not everything can be relocated. So when a virtual machine quits and releases gigabytes of hugepages, we want to use those freely available hugepages to create huge-pmd in the other virtual machines that may be running on fragmented memory, to maximize the CPU efficiency at all times. The scan is slow, it takes nearly zero cpu time, except when it copies data (in which case it means we definitely want to pay for that cpu time) so it seems a good tradeoff. In addition to the hugepages being released by other process releasing memory, we have the strong suspicion that the performance impact of potentially defragmenting hugepages during or before each page fault could lead to more performance inconsistency than allocating small pages at first and having them collapsed into large pages later... if they prove themselfs to be long lived mappings (khugepaged scan is slow so short lived mappings have low probability to run into khugepaged if compared to long lived mappings). Signed-off-by: Andrea Arcangeli Acked-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 1 + include/linux/khugepaged.h | 66 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/sched.h | 1 + 3 files changed, 68 insertions(+) create mode 100644 include/linux/khugepaged.h (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index d9ab70d..43a694e 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -25,6 +25,7 @@ enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, + TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG, #ifdef CONFIG_DEBUG_VM TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG, #endif diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h new file mode 100644 index 0000000..552f318 --- /dev/null +++ b/include/linux/khugepaged.h @@ -0,0 +1,66 @@ +#ifndef _LINUX_KHUGEPAGED_H +#define _LINUX_KHUGEPAGED_H + +#include /* MMF_VM_HUGEPAGE */ + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +extern int __khugepaged_enter(struct mm_struct *mm); +extern void __khugepaged_exit(struct mm_struct *mm); +extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma); + +#define khugepaged_enabled() \ + (transparent_hugepage_flags & \ + ((1<flags)) + return __khugepaged_enter(mm); + return 0; +} + +static inline void khugepaged_exit(struct mm_struct *mm) +{ + if (test_bit(MMF_VM_HUGEPAGE, &mm->flags)) + __khugepaged_exit(mm); +} + +static inline int khugepaged_enter(struct vm_area_struct *vma) +{ + if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags)) + if (khugepaged_always() || + (khugepaged_req_madv() && + vma->vm_flags & VM_HUGEPAGE)) + if (__khugepaged_enter(vma->vm_mm)) + return -ENOMEM; + return 0; +} +#else /* CONFIG_TRANSPARENT_HUGEPAGE */ +static inline int khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm) +{ + return 0; +} +static inline void khugepaged_exit(struct mm_struct *mm) +{ +} +static inline int khugepaged_enter(struct vm_area_struct *vma) +{ + return 0; +} +static inline int khugepaged_enter_vma_merge(struct vm_area_struct *vma) +{ + return 0; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +#endif /* _LINUX_KHUGEPAGED_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index f23b5bb..d747f94 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -434,6 +434,7 @@ extern int get_dumpable(struct mm_struct *mm); #endif /* leave room for more dump flags */ #define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */ +#define MMF_VM_HUGEPAGE 17 /* set when VM_HUGEPAGE is set on vma */ #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK) -- cgit v1.1 From 5f24ce5fd34c3ca1b3d10d30da754732da64d5c0 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:47:00 -0800 Subject: thp: remove PG_buddy PG_buddy can be converted to _mapcount == -2. So the PG_compound_lock can be added to page->flags without overflowing (because of the sparse section bits increasing) with CONFIG_X86_PAE=y and CONFIG_X86_PAT=y. This also has to move the memory hotplug code from _mapcount to lru.next to avoid any risk of clashes. We can't use lru.next for PG_buddy removal, but memory hotplug can use lru.next even more easily than the mapcount instead. Signed-off-by: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 14 +++++++++----- include/linux/mm.h | 21 +++++++++++++++++++++ include/linux/page-flags.h | 7 +------ 3 files changed, 31 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 31c237a..24376fe 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -13,12 +13,16 @@ struct mem_section; #ifdef CONFIG_MEMORY_HOTPLUG /* - * Types for free bootmem. - * The normal smallest mapcount is -1. Here is smaller value than it. + * Types for free bootmem stored in page->lru.next. These have to be in + * some random range in unsigned long space for debugging purposes. */ -#define SECTION_INFO (-1 - 1) -#define MIX_SECTION_INFO (-1 - 2) -#define NODE_INFO (-1 - 3) +enum { + MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12, + SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE, + MIX_SECTION_INFO, + NODE_INFO, + MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO, +}; /* * pgdat resizing functions diff --git a/include/linux/mm.h b/include/linux/mm.h index 2ec5138..7ab7d2b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -397,6 +397,27 @@ static inline void init_page_count(struct page *page) atomic_set(&page->_count, 1); } +/* + * PageBuddy() indicate that the page is free and in the buddy system + * (see mm/page_alloc.c). + */ +static inline int PageBuddy(struct page *page) +{ + return atomic_read(&page->_mapcount) == -2; +} + +static inline void __SetPageBuddy(struct page *page) +{ + VM_BUG_ON(atomic_read(&page->_mapcount) != -1); + atomic_set(&page->_mapcount, -2); +} + +static inline void __ClearPageBuddy(struct page *page) +{ + VM_BUG_ON(!PageBuddy(page)); + atomic_set(&page->_mapcount, -1); +} + void put_page(struct page *page); void put_pages_list(struct list_head *pages); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 4ca1241..0db8037 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -48,9 +48,6 @@ * struct page (these bits with information) are always mapped into kernel * address space... * - * PG_buddy is set to indicate that the page is free and in the buddy system - * (see mm/page_alloc.c). - * * PG_hwpoison indicates that a page got corrupted in hardware and contains * data with incorrect ECC bits that triggered a machine check. Accessing is * not safe since it may cause another machine check. Don't touch! @@ -96,7 +93,6 @@ enum pageflags { PG_swapcache, /* Swap page: swp_entry_t in private */ PG_mappedtodisk, /* Has blocks allocated on-disk */ PG_reclaim, /* To be reclaimed asap */ - PG_buddy, /* Page is free, on buddy lists */ PG_swapbacked, /* Page is backed by RAM/swap */ PG_unevictable, /* Page is "unevictable" */ #ifdef CONFIG_MMU @@ -233,7 +229,6 @@ PAGEFLAG(OwnerPriv1, owner_priv_1) TESTCLEARFLAG(OwnerPriv1, owner_priv_1) * risky: they bypass page accounting. */ TESTPAGEFLAG(Writeback, writeback) TESTSCFLAG(Writeback, writeback) -__PAGEFLAG(Buddy, buddy) PAGEFLAG(MappedToDisk, mappedtodisk) /* PG_readahead is only used for file reads; PG_reclaim is only for writes */ @@ -461,7 +456,7 @@ static inline int PageTransCompound(struct page *page) #define PAGE_FLAGS_CHECK_AT_FREE \ (1 << PG_lru | 1 << PG_locked | \ 1 << PG_private | 1 << PG_private_2 | \ - 1 << PG_buddy | 1 << PG_writeback | 1 << PG_reserved | \ + 1 << PG_writeback | 1 << PG_reserved | \ 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \ 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON | \ __PG_COMPOUND_LOCK) -- cgit v1.1 From f2d6bfe9ff0acec30b713614260e78b03d20e909 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 13 Jan 2011 15:47:01 -0800 Subject: thp: add x86 32bit support Add support for transparent hugepages to x86 32bit. Share the same VM_ bitflag for VM_MAPPED_COPY. mm/nommu.c will never support transparent hugepages. Signed-off-by: Johannes Weiner Signed-off-by: Andrea Arcangeli Reviewed-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7ab7d2b..9c2695b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -102,7 +102,11 @@ extern unsigned int kobjsize(const void *objp); #define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */ +#ifndef CONFIG_TRANSPARENT_HUGEPAGE #define VM_MAPPED_COPY 0x01000000 /* T if mapped copy of data (nommu mmap) */ +#else +#define VM_HUGEPAGE 0x01000000 /* MADV_HUGEPAGE marked this vma */ +#endif #define VM_INSERTPAGE 0x02000000 /* The vma has had "vm_insert_page()" done on it */ #define VM_ALWAYSDUMP 0x04000000 /* Always include in core dumps */ @@ -111,9 +115,6 @@ extern unsigned int kobjsize(const void *objp); #define VM_SAO 0x20000000 /* Strong Access Ordering (powerpc) */ #define VM_PFN_AT_MMAP 0x40000000 /* PFNMAP vma that is fully mapped at mmap time */ #define VM_MERGEABLE 0x80000000 /* KSM may merge identical pages */ -#if BITS_PER_LONG > 32 -#define VM_HUGEPAGE 0x100000000UL /* MADV_HUGEPAGE marked this vma */ -#endif /* Bits set in the VMA until the stack is in its final location */ #define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ) -- cgit v1.1 From 0ca1634d4143c3579273ca53b993df19f5c98e92 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 13 Jan 2011 15:47:02 -0800 Subject: thp: mincore transparent hugepage support Handle transparent huge page pmd entries natively instead of splitting them into subpages. Signed-off-by: Johannes Weiner Signed-off-by: Andrea Arcangeli Reviewed-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 43a694e..25125fb 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -19,6 +19,9 @@ extern struct page *follow_trans_huge_pmd(struct mm_struct *mm, extern int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd); +extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long addr, unsigned long end, + unsigned char *vec); enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_FLAG, -- cgit v1.1 From cd7548ab360c462118568eebb8c6da3bc303b02e Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 13 Jan 2011 15:47:04 -0800 Subject: thp: mprotect: transparent huge page support Natively handle huge pmds when changing page tables on behalf of mprotect(). I left out update_mmu_cache() because we do not need it on x86 anyway but more importantly the interface works on ptes, not pmds. Signed-off-by: Johannes Weiner Signed-off-by: Andrea Arcangeli Reviewed-by: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 25125fb..c590b08 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -22,6 +22,8 @@ extern int zap_huge_pmd(struct mmu_gather *tlb, extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned char *vec); +extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long addr, pgprot_t newprot); enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_FLAG, -- cgit v1.1 From 0bbbc0b33d141f78a0d9218a54a47f50621220d3 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:47:05 -0800 Subject: thp: add numa awareness to hugepage allocations It's mostly a matter of replacing alloc_pages with alloc_pages_vma after introducing alloc_pages_vma. khugepaged needs special handling as the allocation has to happen inside collapse_huge_page where the vma is known and an error has to be returned to the outer loop to sleep alloc_sleep_millisecs in case of failure. But it retains the more efficient logic of handling allocation failures in khugepaged in case of CONFIG_NUMA=n. Signed-off-by: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index d95082c..a3b148a 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -331,14 +331,17 @@ alloc_pages(gfp_t gfp_mask, unsigned int order) { return alloc_pages_current(gfp_mask, order); } -extern struct page *alloc_page_vma(gfp_t gfp_mask, +extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr); #else #define alloc_pages(gfp_mask, order) \ alloc_pages_node(numa_node_id(), gfp_mask, order) -#define alloc_page_vma(gfp_mask, vma, addr) alloc_pages(gfp_mask, 0) +#define alloc_pages_vma(gfp_mask, order, vma, addr) \ + alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) +#define alloc_page_vma(gfp_mask, vma, addr) \ + alloc_pages_vma(gfp_mask, 0, vma, addr) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); -- cgit v1.1 From 94fcc585fb85ad7b059c70872489b50044d401f3 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:47:08 -0800 Subject: thp: avoid breaking huge pmd invariants in case of vma_adjust failures An huge pmd can only be mapped if the corresponding 2M virtual range is fully contained in the vma. At times the VM calls split_vma twice, if the first split_vma succeeds and the second fail, the first split_vma remains in effect and it's not rolled back. For split_vma or vma_adjust to fail an allocation failure is needed so it's a very unlikely event (the out of memory killer would normally fire before any allocation failure is visible to kernel and userland and if an out of memory condition happens it's unlikely to happen exactly here). Nevertheless it's safer to ensure that no huge pmd can be left around if the vma is adjusted in a way that can't fit hugepages anymore at the new vm_start/vm_end address. Signed-off-by: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index c590b08..8275952 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -104,6 +104,19 @@ extern void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd); #error "hugepages can't be allocated by the buddy allocator" #endif extern int hugepage_madvise(unsigned long *vm_flags); +extern void __vma_adjust_trans_huge(struct vm_area_struct *vma, + unsigned long start, + unsigned long end, + long adjust_next); +static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, + unsigned long start, + unsigned long end, + long adjust_next) +{ + if (!vma->anon_vma || vma->vm_ops || vma->vm_file) + return; + __vma_adjust_trans_huge(vma, start, end, adjust_next); +} #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUG(); 0; }) #define HPAGE_PMD_MASK ({ BUG(); 0; }) @@ -125,6 +138,12 @@ static inline int hugepage_madvise(unsigned long *vm_flags) BUG(); return 0; } +static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, + unsigned long start, + unsigned long end, + long adjust_next) +{ +} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* _LINUX_HUGE_MM_H */ -- cgit v1.1 From 8ee53820edfd1f3b6554c593f337148dd3d7fc91 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:47:10 -0800 Subject: thp: mmu_notifier_test_young For GRU and EPT, we need gup-fast to set referenced bit too (this is why it's correct to return 0 when shadow_access_mask is zero, it requires gup-fast to set the referenced bit). qemu-kvm access already sets the young bit in the pte if it isn't zero-copy, if it's zero copy or a shadow paging EPT minor fault we relay on gup-fast to signal the page is in use... We also need to check the young bits on the secondary pagetables for NPT and not nested shadow mmu as the data may never get accessed again by the primary pte. Without this closer accuracy, we'd have to remove the heuristic that avoids collapsing hugepages in hugepage virtual regions that have not even a single subpage in use. ->test_young is full backwards compatible with GRU and other usages that don't have young bits in pagetables set by the hardware and that should nuke the secondary mmu mappings when ->clear_flush_young runs just like EPT does. Removing the heuristic that checks the young bit in khugepaged/collapse_huge_page completely isn't so bad either probably but I thought it was worth it and this makes it reliable. Signed-off-by: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmu_notifier.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index cbfab1e..cc2e7df 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -62,6 +62,16 @@ struct mmu_notifier_ops { unsigned long address); /* + * test_young is called to check the young/accessed bitflag in + * the secondary pte. This is used to know if the page is + * frequently used without actually clearing the flag or tearing + * down the secondary mapping on the page. + */ + int (*test_young)(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long address); + + /* * change_pte is called in cases that pte mapping to page is changed: * for example, when ksm remaps pte to point to a new shared page. */ @@ -163,6 +173,8 @@ extern void __mmu_notifier_mm_destroy(struct mm_struct *mm); extern void __mmu_notifier_release(struct mm_struct *mm); extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long address); +extern int __mmu_notifier_test_young(struct mm_struct *mm, + unsigned long address); extern void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, pte_t pte); extern void __mmu_notifier_invalidate_page(struct mm_struct *mm, @@ -186,6 +198,14 @@ static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, return 0; } +static inline int mmu_notifier_test_young(struct mm_struct *mm, + unsigned long address) +{ + if (mm_has_notifiers(mm)) + return __mmu_notifier_test_young(mm, address); + return 0; +} + static inline void mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, pte_t pte) { @@ -313,6 +333,12 @@ static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, return 0; } +static inline int mmu_notifier_test_young(struct mm_struct *mm, + unsigned long address) +{ + return 0; +} + static inline void mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, pte_t pte) { -- cgit v1.1 From 5a03b051ed87e72b959f32a86054e1142ac4cf55 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:47:11 -0800 Subject: thp: use compaction in kswapd for GFP_ATOMIC order > 0 This takes advantage of memory compaction to properly generate pages of order > 0 if regular page reclaim fails and priority level becomes more severe and we don't reach the proper watermarks. Signed-off-by: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 72cba40..dfa2ed4 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -11,6 +11,9 @@ /* The full zone was compacted */ #define COMPACT_COMPLETE 3 +#define COMPACT_MODE_DIRECT_RECLAIM 0 +#define COMPACT_MODE_KSWAPD 1 + #ifdef CONFIG_COMPACTION extern int sysctl_compact_memory; extern int sysctl_compaction_handler(struct ctl_table *table, int write, @@ -25,7 +28,8 @@ extern unsigned long try_to_compact_pages(struct zonelist *zonelist, bool sync); extern unsigned long compaction_suitable(struct zone *zone, int order); extern unsigned long compact_zone_order(struct zone *zone, int order, - gfp_t gfp_mask, bool sync); + gfp_t gfp_mask, bool sync, + int compact_mode); /* Do not skip compaction more than 64 times */ #define COMPACT_MAX_DEFER_SHIFT 6 @@ -70,9 +74,10 @@ static inline unsigned long compaction_suitable(struct zone *zone, int order) } static inline unsigned long compact_zone_order(struct zone *zone, int order, - gfp_t gfp_mask, bool sync) + gfp_t gfp_mask, bool sync, + int compact_mode) { - return 0; + return COMPACT_CONTINUE; } static inline void defer_compaction(struct zone *zone) -- cgit v1.1 From 2c888cfbc1b45508a44763d85ba2e8ac43faff5f Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Thu, 13 Jan 2011 15:47:13 -0800 Subject: thp: fix anon memory statistics with transparent hugepages Count each transparent hugepage as HPAGE_PMD_NR pages in the LRU statistics, so the Active(anon) and Inactive(anon) statistics in /proc/meminfo are correct. Signed-off-by: Rik van Riel Signed-off-by: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 8 ++++++++ include/linux/mm_inline.h | 8 +++++--- 2 files changed, 13 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 8275952..9b48c24d 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -117,11 +117,19 @@ static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, return; __vma_adjust_trans_huge(vma, start, end, adjust_next); } +static inline int hpage_nr_pages(struct page *page) +{ + if (unlikely(PageTransHuge(page))) + return HPAGE_PMD_NR; + return 1; +} #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUG(); 0; }) #define HPAGE_PMD_MASK ({ BUG(); 0; }) #define HPAGE_PMD_SIZE ({ BUG(); 0; }) +#define hpage_nr_pages(x) 1 + #define transparent_hugepage_enabled(__vma) 0 #define transparent_hugepage_flags 0UL diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 650f31e..8f7d247 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -1,6 +1,8 @@ #ifndef LINUX_MM_INLINE_H #define LINUX_MM_INLINE_H +#include + /** * page_is_file_cache - should the page be on a file LRU or anon LRU? * @page: the page to test @@ -24,7 +26,7 @@ __add_page_to_lru_list(struct zone *zone, struct page *page, enum lru_list l, struct list_head *head) { list_add(&page->lru, head); - __inc_zone_state(zone, NR_LRU_BASE + l); + __mod_zone_page_state(zone, NR_LRU_BASE + l, hpage_nr_pages(page)); mem_cgroup_add_lru_list(page, l); } @@ -38,7 +40,7 @@ static inline void del_page_from_lru_list(struct zone *zone, struct page *page, enum lru_list l) { list_del(&page->lru); - __dec_zone_state(zone, NR_LRU_BASE + l); + __mod_zone_page_state(zone, NR_LRU_BASE + l, -hpage_nr_pages(page)); mem_cgroup_del_lru_list(page, l); } @@ -73,7 +75,7 @@ del_page_from_lru(struct zone *zone, struct page *page) l += LRU_ACTIVE; } } - __dec_zone_state(zone, NR_LRU_BASE + l); + __mod_zone_page_state(zone, NR_LRU_BASE + l, -hpage_nr_pages(page)); mem_cgroup_del_lru_list(page, l); } -- cgit v1.1 From 37c2ac7872a9387542616f658d20ac25f5bdb32e Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:47:16 -0800 Subject: thp: compound_trans_order Read compound_trans_order safe. Noop for CONFIG_TRANSPARENT_HUGEPAGE=n. Signed-off-by: Andrea Arcangeli Cc: Daisuke Nishimura Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9c2695b..ce97a2b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -450,6 +450,20 @@ static inline int compound_order(struct page *page) return (unsigned long)page[1].lru.prev; } +static inline int compound_trans_order(struct page *page) +{ + int order; + unsigned long flags; + + if (!PageHead(page)) + return 0; + + flags = compound_lock_irqsave(page); + order = compound_order(page); + compound_unlock_irqrestore(page, flags); + return order; +} + static inline void set_compound_order(struct page *page, unsigned long order) { page[1].lru.prev = (void *)order; -- cgit v1.1 From 1ddd6db43a08cba56c7ee920800980862086f1c3 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:47:17 -0800 Subject: thp: mm: define MADV_NOHUGEPAGE Define MADV_NOHUGEPAGE. Signed-off-by: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/mman-common.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/asm-generic/mman-common.h b/include/asm-generic/mman-common.h index e91392f..787abbb 100644 --- a/include/asm-generic/mman-common.h +++ b/include/asm-generic/mman-common.h @@ -46,6 +46,7 @@ #define MADV_UNMERGEABLE 13 /* KSM may not merge identical pages */ #define MADV_HUGEPAGE 14 /* Worth backing with hugepages */ +#define MADV_NOHUGEPAGE 15 /* Not worth backing with hugepages */ /* compatibility flags */ #define MAP_FILE 0 -- cgit v1.1 From a664b2d8555c659127bf8fe049a58449d394a707 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:47:17 -0800 Subject: thp: madvise(MADV_NOHUGEPAGE) Add madvise MADV_NOHUGEPAGE to mark regions that are not important to be hugepage backed. Return -EINVAL if the vma is not of an anonymous type, or the feature isn't built into the kernel. Never silently return success. Signed-off-by: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 14 ++++++++------ include/linux/khugepaged.h | 7 ++++--- include/linux/mm.h | 1 + 3 files changed, 13 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 9b48c24d..a8b7e42 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -52,10 +52,12 @@ extern pmd_t *page_check_address_pmd(struct page *page, #define HPAGE_PMD_SIZE HPAGE_SIZE #define transparent_hugepage_enabled(__vma) \ - (transparent_hugepage_flags & (1<vm_flags & VM_HUGEPAGE)) + ((transparent_hugepage_flags & \ + (1<vm_flags & VM_HUGEPAGE))) && \ + !((__vma)->vm_flags & VM_NOHUGEPAGE)) #define transparent_hugepage_defrag(__vma) \ ((transparent_hugepage_flags & \ (1< MAX_ORDER #error "hugepages can't be allocated by the buddy allocator" #endif -extern int hugepage_madvise(unsigned long *vm_flags); +extern int hugepage_madvise(unsigned long *vm_flags, int advice); extern void __vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, @@ -141,7 +143,7 @@ static inline int split_huge_page(struct page *page) do { } while (0) #define wait_split_huge_page(__anon_vma, __pmd) \ do { } while (0) -static inline int hugepage_madvise(unsigned long *vm_flags) +static inline int hugepage_madvise(unsigned long *vm_flags, int advice) { BUG(); return 0; diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index 552f318..6b394f0 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -38,9 +38,10 @@ static inline void khugepaged_exit(struct mm_struct *mm) static inline int khugepaged_enter(struct vm_area_struct *vma) { if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags)) - if (khugepaged_always() || - (khugepaged_req_madv() && - vma->vm_flags & VM_HUGEPAGE)) + if ((khugepaged_always() || + (khugepaged_req_madv() && + vma->vm_flags & VM_HUGEPAGE)) && + !(vma->vm_flags & VM_NOHUGEPAGE)) if (__khugepaged_enter(vma->vm_mm)) return -ENOMEM; return 0; diff --git a/include/linux/mm.h b/include/linux/mm.h index ce97a2b..956a355 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -83,6 +83,7 @@ extern unsigned int kobjsize(const void *objp); #define VM_GROWSUP 0x00000200 #else #define VM_GROWSUP 0x00000000 +#define VM_NOHUGEPAGE 0x00000200 /* MADV_NOHUGEPAGE marked this vma */ #endif #define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ #define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */ -- cgit v1.1 From 60ab3244ec85c44276c585a2a20d3750402e1cf4 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:47:18 -0800 Subject: thp: khugepaged: make khugepaged aware about madvise MADV_HUGEPAGE and MADV_NOHUGEPAGE were fully effective only if run after mmap and before touching the memory. While this is enough for most usages, it's little effort to make madvise more dynamic at runtime on an existing mapping by making khugepaged aware about madvise. MADV_HUGEPAGE: register in khugepaged immediately without waiting a page fault (that may not ever happen if all pages are already mapped and the "enabled" knob was set to madvise during the initial page faults). MADV_NOHUGEPAGE: skip vmas marked VM_NOHUGEPAGE in khugepaged to stop collapsing pages where not needed. [akpm@linux-foundation.org: tweak comment] Signed-off-by: Andrea Arcangeli Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index a8b7e42..bddfba1 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -105,7 +105,8 @@ extern void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd); #if HPAGE_PMD_ORDER > MAX_ORDER #error "hugepages can't be allocated by the buddy allocator" #endif -extern int hugepage_madvise(unsigned long *vm_flags, int advice); +extern int hugepage_madvise(struct vm_area_struct *vma, + unsigned long *vm_flags, int advice); extern void __vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, @@ -143,7 +144,8 @@ static inline int split_huge_page(struct page *page) do { } while (0) #define wait_split_huge_page(__anon_vma, __pmd) \ do { } while (0) -static inline int hugepage_madvise(unsigned long *vm_flags, int advice) +static inline int hugepage_madvise(struct vm_area_struct *vma, + unsigned long *vm_flags, int advice) { BUG(); return 0; -- cgit v1.1 From 22e5c47ee238abe636655c3862ed28d6eb084ad4 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:47:20 -0800 Subject: thp: add compound_trans_head() helper Cleanup some code with common compound_trans_head helper. Signed-off-by: Andrea Arcangeli Cc: Hugh Dickins Cc: Johannes Weiner Cc: Marcelo Tosatti Cc: Avi Kivity Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index bddfba1..8e6c8c4 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -126,6 +126,23 @@ static inline int hpage_nr_pages(struct page *page) return HPAGE_PMD_NR; return 1; } +static inline struct page *compound_trans_head(struct page *page) +{ + if (PageTail(page)) { + struct page *head; + head = page->first_page; + smp_rmb(); + /* + * head may be a dangling pointer. + * __split_huge_page_refcount clears PageTail before + * overwriting first_page, so if PageTail is still + * there it means the head pointer isn't dangling. + */ + if (PageTail(page)) + return head; + } + return page; +} #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUG(); 0; }) #define HPAGE_PMD_MASK ({ BUG(); 0; }) @@ -144,6 +161,7 @@ static inline int split_huge_page(struct page *page) do { } while (0) #define wait_split_huge_page(__anon_vma, __pmd) \ do { } while (0) +#define compound_trans_head(page) compound_head(page) static inline int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { -- cgit v1.1 From 29c1f677d424e8c5683a837fc4f03fc9f19201d7 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 13 Jan 2011 15:47:21 -0800 Subject: mm: migration: use rcu_dereference_protected when dereferencing the radix tree slot during file page migration migrate_pages() -> unmap_and_move() only calls rcu_read_lock() for anonymous pages, as introduced by git commit 989f89c57e6361e7d16fbd9572b5da7d313b073d ("fix rcu_read_lock() in page migraton"). The point of the RCU protection there is part of getting a stable reference to anon_vma and is only held for anon pages as file pages are locked which is sufficient protection against freeing. However, while a file page's mapping is being migrated, the radix tree is double checked to ensure it is the expected page. This uses radix_tree_deref_slot() -> rcu_dereference() without the RCU lock held triggering the following warning. [ 173.674290] =================================================== [ 173.676016] [ INFO: suspicious rcu_dereference_check() usage. ] [ 173.676016] --------------------------------------------------- [ 173.676016] include/linux/radix-tree.h:145 invoked rcu_dereference_check() without protection! [ 173.676016] [ 173.676016] other info that might help us debug this: [ 173.676016] [ 173.676016] [ 173.676016] rcu_scheduler_active = 1, debug_locks = 0 [ 173.676016] 1 lock held by hugeadm/2899: [ 173.676016] #0: (&(&inode->i_data.tree_lock)->rlock){..-.-.}, at: [] migrate_page_move_mapping+0x40/0x1ab [ 173.676016] [ 173.676016] stack backtrace: [ 173.676016] Pid: 2899, comm: hugeadm Not tainted 2.6.37-rc5-autobuild [ 173.676016] Call Trace: [ 173.676016] [] ? printk+0x14/0x1b [ 173.676016] [] lockdep_rcu_dereference+0x7d/0x86 [ 173.676016] [] migrate_page_move_mapping+0xca/0x1ab [ 173.676016] [] migrate_page+0x23/0x39 [ 173.676016] [] buffer_migrate_page+0x22/0x107 [ 173.676016] [] ? buffer_migrate_page+0x0/0x107 [ 173.676016] [] move_to_new_page+0x9a/0x1ae [ 173.676016] [] migrate_pages+0x1e7/0x2fa This patch introduces radix_tree_deref_slot_protected() which calls rcu_dereference_protected(). Users of it must pass in the mapping->tree_lock that is protecting this dereference. Holding the tree lock protects against parallel updaters of the radix tree meaning that rcu_dereference_protected is allowable. [akpm@linux-foundation.org: remove unneeded casts] Signed-off-by: Mel Gorman Cc: Minchan Kim Cc: KAMEZAWA Hiroyuki Cc: Milton Miller Cc: Nick Piggin Cc: Wu Fengguang Cc: [2.6.37.early] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index ab2baa5..23241c2 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -146,6 +146,22 @@ static inline void *radix_tree_deref_slot(void **pslot) } /** + * radix_tree_deref_slot_protected - dereference a slot without RCU lock but with tree lock held + * @pslot: pointer to slot, returned by radix_tree_lookup_slot + * Returns: item that was stored in that slot with any direct pointer flag + * removed. + * + * Similar to radix_tree_deref_slot but only used during migration when a pages + * mapping is being moved. The caller does not hold the RCU read lock but it + * must hold the tree lock to prevent parallel updates. + */ +static inline void *radix_tree_deref_slot_protected(void **pslot, + spinlock_t *treelock) +{ + return rcu_dereference_protected(*pslot, lockdep_is_held(treelock)); +} + +/** * radix_tree_deref_retry - check radix_tree_deref_slot * @arg: pointer returned by radix_tree_deref_slot * Returns: 0 if retry is not required, otherwise retry is required -- cgit v1.1 From db16d5ec1f87f17511599bc77857dd1662b5a22f Mon Sep 17 00:00:00 2001 From: Greg Thelen Date: Thu, 13 Jan 2011 15:47:35 -0800 Subject: memcg: add page_cgroup flags for dirty page tracking This patchset provides the ability for each cgroup to have independent dirty page limits. Limiting dirty memory is like fixing the max amount of dirty (hard to reclaim) page cache used by a cgroup. So, in case of multiple cgroup writers, they will not be able to consume more than their designated share of dirty pages and will be forced to perform write-out if they cross that limit. The patches are based on a series proposed by Andrea Righi in Mar 2010. Overview: - Add page_cgroup flags to record when pages are dirty, in writeback, or nfs unstable. - Extend mem_cgroup to record the total number of pages in each of the interesting dirty states (dirty, writeback, unstable_nfs). - Add dirty parameters similar to the system-wide /proc/sys/vm/dirty_* limits to mem_cgroup. The mem_cgroup dirty parameters are accessible via cgroupfs control files. - Consider both system and per-memcg dirty limits in page writeback when deciding to queue background writeback or block for foreground writeback. Known shortcomings: - When a cgroup dirty limit is exceeded, then bdi writeback is employed to writeback dirty inodes. Bdi writeback considers inodes from any cgroup, not just inodes contributing dirty pages to the cgroup exceeding its limit. - When memory.use_hierarchy is set, then dirty limits are disabled. This is a implementation detail. An enhanced implementation is needed to check the chain of parents to ensure that no dirty limit is exceeded. Performance data: - A page fault microbenchmark workload was used to measure performance, which can be called in read or write mode: f = open(foo. $cpu) truncate(f, 4096) alarm(60) while (1) { p = mmap(f, 4096) if (write) *p = 1 else x = *p munmap(p) } - The workload was called for several points in the patch series in different modes: - s_read is a single threaded reader - s_write is a single threaded writer - p_read is a 16 thread reader, each operating on a different file - p_write is a 16 thread writer, each operating on a different file - Measurements were collected on a 16 core non-numa system using "perf stat --repeat 3". The -a option was used for parallel (p_*) runs. - All numbers are page fault rate (M/sec). Higher is better. - To compare the performance of a kernel without non-memcg compare the first and last rows, neither has memcg configured. The first row does not include any of these memcg patches. - To compare the performance of using memcg dirty limits, compare the baseline (2nd row titled "w/ memcg") with the the code and memcg enabled (2nd to last row titled "all patches"). root_cgroup child_cgroup s_read s_write p_read p_write s_read s_write p_read p_write mmotm w/o memcg 0.428 0.390 0.429 0.388 mmotm w/ memcg 0.411 0.378 0.391 0.362 0.412 0.377 0.385 0.363 all patches 0.384 0.360 0.370 0.348 0.381 0.363 0.368 0.347 all patches 0.431 0.402 0.427 0.395 w/o memcg This patch: Add additional flags to page_cgroup to track dirty pages within a mem_cgroup. Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Andrea Righi Signed-off-by: Greg Thelen Acked-by: Daisuke Nishimura Cc: Balbir Singh Cc: Minchan Kim Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_cgroup.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include') diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h index b02195d..fdb5a92 100644 --- a/include/linux/page_cgroup.h +++ b/include/linux/page_cgroup.h @@ -40,6 +40,9 @@ enum { PCG_USED, /* this object is in use. */ PCG_ACCT_LRU, /* page has been accounted for */ PCG_FILE_MAPPED, /* page is accounted as "mapped" */ + PCG_FILE_DIRTY, /* page is dirty */ + PCG_FILE_WRITEBACK, /* page is under writeback */ + PCG_FILE_UNSTABLE_NFS, /* page is NFS unstable */ PCG_MIGRATION, /* under page migration */ }; @@ -59,6 +62,10 @@ static inline void ClearPageCgroup##uname(struct page_cgroup *pc) \ static inline int TestClearPageCgroup##uname(struct page_cgroup *pc) \ { return test_and_clear_bit(PCG_##lname, &pc->flags); } +#define TESTSETPCGFLAG(uname, lname) \ +static inline int TestSetPageCgroup##uname(struct page_cgroup *pc) \ + { return test_and_set_bit(PCG_##lname, &pc->flags); } + /* Cache flag is set only once (at allocation) */ TESTPCGFLAG(Cache, CACHE) CLEARPCGFLAG(Cache, CACHE) @@ -78,6 +85,22 @@ SETPCGFLAG(FileMapped, FILE_MAPPED) CLEARPCGFLAG(FileMapped, FILE_MAPPED) TESTPCGFLAG(FileMapped, FILE_MAPPED) +SETPCGFLAG(FileDirty, FILE_DIRTY) +CLEARPCGFLAG(FileDirty, FILE_DIRTY) +TESTPCGFLAG(FileDirty, FILE_DIRTY) +TESTCLEARPCGFLAG(FileDirty, FILE_DIRTY) +TESTSETPCGFLAG(FileDirty, FILE_DIRTY) + +SETPCGFLAG(FileWriteback, FILE_WRITEBACK) +CLEARPCGFLAG(FileWriteback, FILE_WRITEBACK) +TESTPCGFLAG(FileWriteback, FILE_WRITEBACK) + +SETPCGFLAG(FileUnstableNFS, FILE_UNSTABLE_NFS) +CLEARPCGFLAG(FileUnstableNFS, FILE_UNSTABLE_NFS) +TESTPCGFLAG(FileUnstableNFS, FILE_UNSTABLE_NFS) +TESTCLEARPCGFLAG(FileUnstableNFS, FILE_UNSTABLE_NFS) +TESTSETPCGFLAG(FileUnstableNFS, FILE_UNSTABLE_NFS) + SETPCGFLAG(Migration, MIGRATION) CLEARPCGFLAG(Migration, MIGRATION) TESTPCGFLAG(Migration, MIGRATION) -- cgit v1.1 From 2a7106f2cb0768d00fe8c1eb42a754a7d8518f08 Mon Sep 17 00:00:00 2001 From: Greg Thelen Date: Thu, 13 Jan 2011 15:47:37 -0800 Subject: memcg: create extensible page stat update routines Replace usage of the mem_cgroup_update_file_mapped() memcg statistic update routine with two new routines: * mem_cgroup_inc_page_stat() * mem_cgroup_dec_page_stat() As before, only the file_mapped statistic is managed. However, these more general interfaces allow for new statistics to be more easily added. New statistics are added with memcg dirty page accounting. Signed-off-by: Greg Thelen Signed-off-by: Andrea Righi Acked-by: KAMEZAWA Hiroyuki Acked-by: Daisuke Nishimura Cc: Balbir Singh Cc: Minchan Kim Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 31 ++++++++++++++++++++++++++++--- 1 file changed, 28 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 159a076..067115c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -25,6 +25,11 @@ struct page_cgroup; struct page; struct mm_struct; +/* Stats that can be updated by kernel. */ +enum mem_cgroup_page_stat_item { + MEMCG_NR_FILE_MAPPED, /* # of pages charged as file rss */ +}; + extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, struct list_head *dst, unsigned long *scanned, int order, @@ -121,7 +126,22 @@ static inline bool mem_cgroup_disabled(void) return false; } -void mem_cgroup_update_file_mapped(struct page *page, int val); +void mem_cgroup_update_page_stat(struct page *page, + enum mem_cgroup_page_stat_item idx, + int val); + +static inline void mem_cgroup_inc_page_stat(struct page *page, + enum mem_cgroup_page_stat_item idx) +{ + mem_cgroup_update_page_stat(page, idx, 1); +} + +static inline void mem_cgroup_dec_page_stat(struct page *page, + enum mem_cgroup_page_stat_item idx) +{ + mem_cgroup_update_page_stat(page, idx, -1); +} + unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, gfp_t gfp_mask); u64 mem_cgroup_get_limit(struct mem_cgroup *mem); @@ -293,8 +313,13 @@ mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) { } -static inline void mem_cgroup_update_file_mapped(struct page *page, - int val) +static inline void mem_cgroup_inc_page_stat(struct page *page, + enum mem_cgroup_page_stat_item idx) +{ +} + +static inline void mem_cgroup_dec_page_stat(struct page *page, + enum mem_cgroup_page_stat_item idx) { } -- cgit v1.1 From dbd4ea78f002df283c95d9774837041735fa1bf9 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Thu, 13 Jan 2011 15:47:38 -0800 Subject: memcg: add lock to synchronize page accounting and migration Introduce a new bit spin lock, PCG_MOVE_LOCK, to synchronize the page accounting and migration code. This reworks the locking scheme of _update_stat() and _move_account() by adding new lock bit PCG_MOVE_LOCK, which is always taken under IRQ disable. 1. If pages are being migrated from a memcg, then updates to that memcg page statistics are protected by grabbing PCG_MOVE_LOCK using move_lock_page_cgroup(). In an upcoming commit, memcg dirty page accounting will be updating memcg page accounting (specifically: num writeback pages) from IRQ context (softirq). Avoid a deadlocking nested spin lock attempt by disabling irq on the local processor when grabbing the PCG_MOVE_LOCK. 2. lock for update_page_stat is used only for avoiding race with move_account(). So, IRQ awareness of lock_page_cgroup() itself is not a problem. The problem is between mem_cgroup_update_page_stat() and mem_cgroup_move_account_page(). Trade-off: * Changing lock_page_cgroup() to always disable IRQ (or local_bh) has some impacts on performance and I think it's bad to disable IRQ when it's not necessary. * adding a new lock makes move_account() slower. Score is here. Performance Impact: moving a 8G anon process. Before: real 0m0.792s user 0m0.000s sys 0m0.780s After: real 0m0.854s user 0m0.000s sys 0m0.842s This score is bad but planned patches for optimization can reduce this impact. Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Greg Thelen Reviewed-by: Minchan Kim Acked-by: Daisuke Nishimura Cc: Andrea Righi Cc: Balbir Singh Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_cgroup.h | 31 ++++++++++++++++++++++++++++--- 1 file changed, 28 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h index fdb5a92..5b0c971 100644 --- a/include/linux/page_cgroup.h +++ b/include/linux/page_cgroup.h @@ -35,15 +35,18 @@ struct page_cgroup *lookup_page_cgroup(struct page *page); enum { /* flags for mem_cgroup */ - PCG_LOCK, /* page cgroup is locked */ + PCG_LOCK, /* Lock for pc->mem_cgroup and following bits. */ PCG_CACHE, /* charged as cache */ PCG_USED, /* this object is in use. */ - PCG_ACCT_LRU, /* page has been accounted for */ + PCG_MIGRATION, /* under page migration */ + /* flags for mem_cgroup and file and I/O status */ + PCG_MOVE_LOCK, /* For race between move_account v.s. following bits */ PCG_FILE_MAPPED, /* page is accounted as "mapped" */ PCG_FILE_DIRTY, /* page is dirty */ PCG_FILE_WRITEBACK, /* page is under writeback */ PCG_FILE_UNSTABLE_NFS, /* page is NFS unstable */ - PCG_MIGRATION, /* under page migration */ + /* No lock in page_cgroup */ + PCG_ACCT_LRU, /* page has been accounted for (under lru_lock) */ }; #define TESTPCGFLAG(uname, lname) \ @@ -117,6 +120,10 @@ static inline enum zone_type page_cgroup_zid(struct page_cgroup *pc) static inline void lock_page_cgroup(struct page_cgroup *pc) { + /* + * Don't take this lock in IRQ context. + * This lock is for pc->mem_cgroup, USED, CACHE, MIGRATION + */ bit_spin_lock(PCG_LOCK, &pc->flags); } @@ -130,6 +137,24 @@ static inline int page_is_cgroup_locked(struct page_cgroup *pc) return bit_spin_is_locked(PCG_LOCK, &pc->flags); } +static inline void move_lock_page_cgroup(struct page_cgroup *pc, + unsigned long *flags) +{ + /* + * We know updates to pc->flags of page cache's stats are from both of + * usual context or IRQ context. Disable IRQ to avoid deadlock. + */ + local_irq_save(*flags); + bit_spin_lock(PCG_MOVE_LOCK, &pc->flags); +} + +static inline void move_unlock_page_cgroup(struct page_cgroup *pc, + unsigned long *flags) +{ + bit_spin_unlock(PCG_MOVE_LOCK, &pc->flags); + local_irq_restore(*flags); +} + #else /* CONFIG_CGROUP_MEM_RES_CTLR */ struct page_cgroup; -- cgit v1.1 From 50de1dd967d4ba3b8a90ebe7a4f5feca24191317 Mon Sep 17 00:00:00 2001 From: Daisuke Nishimura Date: Thu, 13 Jan 2011 15:47:43 -0800 Subject: memcg: fix memory migration of shmem swapcache In the current implementation mem_cgroup_end_migration() decides whether the page migration has succeeded or not by checking "oldpage->mapping". But if we are tring to migrate a shmem swapcache, the page->mapping of it is NULL from the begining, so the check would be invalid. As a result, mem_cgroup_end_migration() assumes the migration has succeeded even if it's not, so "newpage" would be freed while it's not uncharged. This patch fixes it by passing mem_cgroup_end_migration() the result of the page migration. Signed-off-by: Daisuke Nishimura Reviewed-by: Minchan Kim Acked-by: KAMEZAWA Hiroyuki Acked-by: Balbir Singh Cc: Minchan Kim Reviewed-by: Johannes Weiner Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 067115c..6a576f9 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -98,7 +98,7 @@ extern int mem_cgroup_prepare_migration(struct page *page, struct page *newpage, struct mem_cgroup **ptr); extern void mem_cgroup_end_migration(struct mem_cgroup *mem, - struct page *oldpage, struct page *newpage); + struct page *oldpage, struct page *newpage, bool migration_ok); /* * For memory reclaim. @@ -251,8 +251,7 @@ mem_cgroup_prepare_migration(struct page *page, struct page *newpage, } static inline void mem_cgroup_end_migration(struct mem_cgroup *mem, - struct page *oldpage, - struct page *newpage) + struct page *oldpage, struct page *newpage, bool migration_ok) { } -- cgit v1.1 From 9ce137eee4febaabca81143be07d4205d2bd52d4 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Tue, 11 Jan 2011 14:07:12 -0500 Subject: nfsd: don't support msnfs export option We've long had these pointless #ifdef MSNFS's sprinkled throughout the code--pointless because MSNFS is always defined (and we give no config option to make that easy to change). So we could just remove the ifdef's and compile the resulting code unconditionally. But as long as we're there: why not just rip out this code entirely? The only purpose is to implement the "msnfs" export option which turns on Windows-like behavior in some cases, and: - the export option isn't documented anywhere; - the userland utilities (which would need to be able to parse "msnfs" in an export file) don't support it; - I don't know how to maintain this, as I don't know what the proper behavior is; and - google shows no evidence that anyone has ever used this. Signed-off-by: J. Bruce Fields --- include/linux/nfsd/export.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h index 8ae78a6..bd31615 100644 --- a/include/linux/nfsd/export.h +++ b/include/linux/nfsd/export.h @@ -35,7 +35,7 @@ #define NFSEXP_NOHIDE 0x0200 #define NFSEXP_NOSUBTREECHECK 0x0400 #define NFSEXP_NOAUTHNLM 0x0800 /* Don't authenticate NLM requests - just trust */ -#define NFSEXP_MSNFS 0x1000 /* do silly things that MS clients expect */ +#define NFSEXP_MSNFS 0x1000 /* do silly things that MS clients expect; no longer supported */ #define NFSEXP_FSID 0x2000 #define NFSEXP_CROSSMOUNT 0x4000 #define NFSEXP_NOACL 0x8000 /* reserved for possible ACL related use */ -- cgit v1.1 From 2c6755988afc003a0332406a134fb6a1626f9b28 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 14 Jan 2011 02:36:43 +0000 Subject: fs: hlist UP debug fixup Po-Yu Chuang noticed that hlist_bl_set_first could crash on a UP system when LIST_BL_LOCKMASK is 0, because LIST_BL_BUG_ON(!((unsigned long)h->first & LIST_BL_LOCKMASK)); always evaulates to true. Fix the expression, and also avoid a dependency between bit spinlock implementation and list bl code (list code shouldn't know anything except that bit 0 is set when adding and removing elements). Eventually if a good use case comes up, we might use this list to store 1 or more arbitrary bits of data, so it really shouldn't be tied to locking either, but for now they are helpful for debugging. Signed-off-by: Nick Piggin --- include/linux/list_bl.h | 5 +++-- include/linux/rculist_bl.h | 3 ++- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/list_bl.h b/include/linux/list_bl.h index 9ee97e7..b2adbb4 100644 --- a/include/linux/list_bl.h +++ b/include/linux/list_bl.h @@ -16,7 +16,7 @@ * some fast and compact auxiliary data. */ -#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) +#if defined(CONFIG_SMP) #define LIST_BL_LOCKMASK 1UL #else #define LIST_BL_LOCKMASK 0UL @@ -62,7 +62,8 @@ static inline void hlist_bl_set_first(struct hlist_bl_head *h, struct hlist_bl_node *n) { LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); - LIST_BL_BUG_ON(!((unsigned long)h->first & LIST_BL_LOCKMASK)); + LIST_BL_BUG_ON(((unsigned long)h->first & LIST_BL_LOCKMASK) != + LIST_BL_LOCKMASK); h->first = (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK); } diff --git a/include/linux/rculist_bl.h b/include/linux/rculist_bl.h index b872b49..cf1244f 100644 --- a/include/linux/rculist_bl.h +++ b/include/linux/rculist_bl.h @@ -11,7 +11,8 @@ static inline void hlist_bl_set_first_rcu(struct hlist_bl_head *h, struct hlist_bl_node *n) { LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); - LIST_BL_BUG_ON(!((unsigned long)h->first & LIST_BL_LOCKMASK)); + LIST_BL_BUG_ON(((unsigned long)h->first & LIST_BL_LOCKMASK) != + LIST_BL_LOCKMASK); rcu_assign_pointer(h->first, (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK)); } -- cgit v1.1 From 1ac9ad1394fa542ac7ae0dc943ee3cda678799fa Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 12 Jan 2011 12:13:14 +0000 Subject: net: remove dev_txq_stats_fold() After recent changes, (percpu stats on vlan/tunnels...), we dont need anymore per struct netdev_queue tx_bytes/tx_packets/tx_dropped counters. Only remaining users are ixgbe, sch_teql, gianfar & macvlan : 1) ixgbe can be converted to use existing tx_ring counters. 2) macvlan incremented txq->tx_dropped, it can use the dev->stats.tx_dropped counter. 3) sch_teql : almost revert ab35cd4b8f42 (Use net_device internal stats) Now we have ndo_get_stats64(), use it, even for "unsigned long" fields (No need to bring back a struct net_device_stats) 4) gianfar adds a stats structure per tx queue to hold tx_bytes/tx_packets This removes a lockdep warning (and possible lockup) in rndis gadget, calling dev_get_stats() from hard IRQ context. Ref: http://www.spinics.net/lists/netdev/msg149202.html Reported-by: Neil Jones Signed-off-by: Eric Dumazet CC: Jarek Poplawski CC: Alexander Duyck CC: Jeff Kirsher CC: Sandeep Gopalpet CC: Michal Nazarewicz Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index be4957c..d971346 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -520,9 +520,6 @@ struct netdev_queue { * please use this field instead of dev->trans_start */ unsigned long trans_start; - u64 tx_bytes; - u64 tx_packets; - u64 tx_dropped; } ____cacheline_aligned_in_smp; static inline int netdev_queue_numa_node_read(const struct netdev_queue *q) @@ -2265,8 +2262,6 @@ extern void dev_load(struct net *net, const char *name); extern void dev_mcast_init(void); extern struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, struct rtnl_link_stats64 *storage); -extern void dev_txq_stats_fold(const struct net_device *dev, - struct rtnl_link_stats64 *stats); extern int netdev_max_backlog; extern int netdev_tstamp_prequeue; -- cgit v1.1 From 78d07369462e9feeaa5db301b0aa70e9dcb40b48 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Thu, 13 Jan 2011 11:51:03 +0000 Subject: ipsec: update MAX_AH_AUTH_LEN to support sha512 icv_truncbits is set to 256 for sha512, so update MAX_AH_AUTH_LEN to 64. Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/net/ah.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ah.h b/include/net/ah.h index be7798d..ca95b98 100644 --- a/include/net/ah.h +++ b/include/net/ah.h @@ -4,7 +4,7 @@ #include /* This is the maximum truncated ICV length that we know of. */ -#define MAX_AH_AUTH_LEN 16 +#define MAX_AH_AUTH_LEN 64 struct crypto_ahash; -- cgit v1.1 From 51e7eed79c41180919ff94942895ba38467d9ad4 Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Wed, 12 Jan 2011 22:14:56 +0000 Subject: etherdevice.h: Add is_unicast_ether_addr function From a check for !is_multicast_ether_addr it is not always obvious that we're checking for a unicast address. So add this helper function to make those code paths easier to read. Signed-off-by: Tobias Klauser Acked-by: Chris Metcalf Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index bec8b82..ab68f78 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -99,6 +99,17 @@ static inline int is_broadcast_ether_addr(const u8 *addr) } /** + * is_unicast_ether_addr - Determine if the Ethernet address is unicast + * @addr: Pointer to a six-byte array containing the Ethernet address + * + * Return true if the address is a unicast address. + */ +static inline int is_unicast_ether_addr(const u8 *addr) +{ + return !is_multicast_ether_addr(addr); +} + +/** * is_valid_ether_addr - Determine if the given Ethernet address is valid * @addr: Pointer to a six-byte array containing the Ethernet address * -- cgit v1.1 From 412dc11d3fd01f96fdf4a8cbfbc5584a17dab7c8 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 24 Nov 2010 18:01:41 +0000 Subject: mfd: Add WM8326 support The WM8326 is a high performance variant of the WM832x series with no software visible differences. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/wm831x/core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mfd/wm831x/core.h b/include/linux/mfd/wm831x/core.h index a1239c4..903280d 100644 --- a/include/linux/mfd/wm831x/core.h +++ b/include/linux/mfd/wm831x/core.h @@ -245,6 +245,7 @@ enum wm831x_parent { WM8320 = 0x8320, WM8321 = 0x8321, WM8325 = 0x8325, + WM8326 = 0x8326, }; struct wm831x { -- cgit v1.1 From 4c90aa94f6b3e33f57faaf19ef9819195dff61d3 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 26 Nov 2010 17:19:34 +0000 Subject: mfd: Provide pm_runtime_no_callbacks flag in cell data Allow MFD cells to have pm_runtime_no_callbacks() called on them during registration. This causes the runtime PM framework to ignore them, allowing use of runtime PM to suspend the device as a whole even if not all drivers for the MFD can usefully implement runtime PM. For example, RTCs are likely to run continuously regardless of the power state of the system. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/core.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index 5582ab3..835996e 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -47,6 +47,12 @@ struct mfd_cell { /* don't check for resource conflicts */ bool ignore_resource_conflicts; + + /* + * Disable runtime PM callbacks for this subdevice - see + * pm_runtime_no_callbacks(). + */ + bool pm_runtime_no_callbacks; }; extern int mfd_add_devices(struct device *parent, int id, -- cgit v1.1 From e098aded79f24e2024139e82f778ff9db6dc142a Mon Sep 17 00:00:00 2001 From: Mattias Wallin Date: Thu, 2 Dec 2010 15:40:31 +0100 Subject: mfd: ab8500-core ioresources irq for subdrivers added This patch adds the ioresources used by subdrivers to retrieve their interrupt. Signed-off-by: Mattias Wallin Signed-off-by: Samuel Ortiz --- include/linux/mfd/ab8500.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mfd/ab8500.h b/include/linux/mfd/ab8500.h index 85cf2c2..1ad1696 100644 --- a/include/linux/mfd/ab8500.h +++ b/include/linux/mfd/ab8500.h @@ -91,8 +91,8 @@ #define AB8500_INT_ID_DET_R4F 93 #define AB8500_INT_USB_CHG_DET_DONE 94 #define AB8500_INT_USB_CH_TH_PROT_F 96 -#define AB8500_INT_USB_CH_TH_PROP_R 97 -#define AB8500_INT_MAIN_CH_TH_PROP_F 98 +#define AB8500_INT_USB_CH_TH_PROT_R 97 +#define AB8500_INT_MAIN_CH_TH_PROT_F 98 #define AB8500_INT_MAIN_CH_TH_PROT_R 99 #define AB8500_INT_USB_CHARGER_NOT_OKF 103 -- cgit v1.1 From cdd137c9c86c201ddb7f42ec978d2da45e7b7a17 Mon Sep 17 00:00:00 2001 From: MyungJoo Ham Date: Thu, 23 Dec 2010 17:53:36 +0900 Subject: mfd: MAX8998/LP3974 hibernation support This patch makes the driver to save and restore register values for hibernation. Signed-off-by: MyungJoo Ham Signed-off-by: Kyungmin Park Signed-off-by: Samuel Ortiz --- include/linux/mfd/max8998-private.h | 2 ++ include/linux/mfd/max8998.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/max8998-private.h b/include/linux/mfd/max8998-private.h index 7363dea..effa5d3 100644 --- a/include/linux/mfd/max8998-private.h +++ b/include/linux/mfd/max8998-private.h @@ -159,10 +159,12 @@ struct max8998_dev { u8 irq_masks_cur[MAX8998_NUM_IRQ_REGS]; u8 irq_masks_cache[MAX8998_NUM_IRQ_REGS]; int type; + bool wakeup; }; int max8998_irq_init(struct max8998_dev *max8998); void max8998_irq_exit(struct max8998_dev *max8998); +int max8998_irq_resume(struct max8998_dev *max8998); extern int max8998_read_reg(struct i2c_client *i2c, u8 reg, u8 *dest); extern int max8998_bulk_read(struct i2c_client *i2c, u8 reg, int count, diff --git a/include/linux/mfd/max8998.h b/include/linux/mfd/max8998.h index f8c9f88..686a744 100644 --- a/include/linux/mfd/max8998.h +++ b/include/linux/mfd/max8998.h @@ -88,6 +88,7 @@ struct max8998_platform_data { int buck1_set1; int buck1_set2; int buck2_set3; + bool wakeup; }; #endif /* __LINUX_MFD_MAX8998_H */ -- cgit v1.1 From 337ce5d1c5759644cea6c47220ce7e84f0398362 Mon Sep 17 00:00:00 2001 From: MyungJoo Ham Date: Tue, 4 Jan 2011 14:17:39 +0900 Subject: mfd: Support LP3974 RTC The first releases of LP3974 have a large delay in RTC registers, which requires 2 seconds of delay after writing to a rtc register (recommended by National Semiconductor's engineers) before reading it. If "rtc_delay" field of the platform data is true, the rtc driver assumes that such delays are required. Although we have not seen LP3974s without requiring such delays, we assume that such LP3974s will be released soon (or they have done so already) and they are supported by "lp3974" without setting "rtc_delay" at the platform data. This patch adds delays with msleep when writing values to RTC registers if the platform data has rtc_delay set. Signed-off-by: MyungJoo Ham Signed-off-by: Kyungmin Park Reviewed-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/max8998.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/mfd/max8998.h b/include/linux/mfd/max8998.h index 686a744..c22b9a4 100644 --- a/include/linux/mfd/max8998.h +++ b/include/linux/mfd/max8998.h @@ -76,6 +76,9 @@ struct max8998_regulator_data { * @buck1_set1: BUCK1 gpio pin 1 to set output voltage * @buck1_set2: BUCK1 gpio pin 2 to set output voltage * @buck2_set3: BUCK2 gpio pin to set output voltage + * @wakeup: Allow to wake up from suspend + * @rtc_delay: LP3974 RTC chip bug that requires delay after a register + * write before reading it. */ struct max8998_platform_data { struct max8998_regulator_data *regulators; @@ -89,6 +92,7 @@ struct max8998_platform_data { int buck1_set2; int buck2_set3; bool wakeup; + bool rtc_delay; }; #endif /* __LINUX_MFD_MAX8998_H */ -- cgit v1.1 From 735a3d9efdc5aeebe201008e6655b235c7f02aeb Mon Sep 17 00:00:00 2001 From: MyungJoo Ham Date: Tue, 11 Jan 2011 12:20:05 +0100 Subject: regulator: Support MAX8998/LP3974 DVS-GPIO The previous driver did not support BUCK1-DVS3, BUCK1-DVS4, and BUCK2-DVS2 modes. This patch adds such modes and an option to block setting buck1/2 voltages out of the preset values. Signed-off-by: MyungJoo Ham Signed-off-by: Kyungmin Park Acked-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/max8998.h | 26 ++++++++++++++++++++------ 1 file changed, 20 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/mfd/max8998.h b/include/linux/mfd/max8998.h index c22b9a4..61daa16 100644 --- a/include/linux/mfd/max8998.h +++ b/include/linux/mfd/max8998.h @@ -70,12 +70,20 @@ struct max8998_regulator_data { * @num_regulators: number of regultors used * @irq_base: base IRQ number for max8998, required for IRQs * @ono: power onoff IRQ number for max8998 - * @buck1_max_voltage1: BUCK1 maximum alowed voltage register 1 - * @buck1_max_voltage2: BUCK1 maximum alowed voltage register 2 - * @buck2_max_voltage: BUCK2 maximum alowed voltage + * @buck_voltage_lock: Do NOT change the values of the following six + * registers set by buck?_voltage?. The voltage of BUCK1/2 cannot + * be other than the preset values. + * @buck1_voltage1: BUCK1 DVS mode 1 voltage register + * @buck1_voltage2: BUCK1 DVS mode 2 voltage register + * @buck1_voltage3: BUCK1 DVS mode 3 voltage register + * @buck1_voltage4: BUCK1 DVS mode 4 voltage register + * @buck2_voltage1: BUCK2 DVS mode 1 voltage register + * @buck2_voltage2: BUCK2 DVS mode 2 voltage register * @buck1_set1: BUCK1 gpio pin 1 to set output voltage * @buck1_set2: BUCK1 gpio pin 2 to set output voltage + * @buck1_default_idx: Default for BUCK1 gpio pin 1, 2 * @buck2_set3: BUCK2 gpio pin to set output voltage + * @buck2_default_idx: Default for BUCK2 gpio pin. * @wakeup: Allow to wake up from suspend * @rtc_delay: LP3974 RTC chip bug that requires delay after a register * write before reading it. @@ -85,12 +93,18 @@ struct max8998_platform_data { int num_regulators; int irq_base; int ono; - int buck1_max_voltage1; - int buck1_max_voltage2; - int buck2_max_voltage; + bool buck_voltage_lock; + int buck1_voltage1; + int buck1_voltage2; + int buck1_voltage3; + int buck1_voltage4; + int buck2_voltage1; + int buck2_voltage2; int buck1_set1; int buck1_set2; + int buck1_default_idx; int buck2_set3; + int buck2_default_idx; bool wakeup; bool rtc_delay; }; -- cgit v1.1 From 92d50a4132977b932ed830fa58c05deeb5c524f0 Mon Sep 17 00:00:00 2001 From: Mattias Wallin Date: Tue, 7 Dec 2010 11:20:47 +0100 Subject: mfd: ab8500-core chip version cut 2.0 support This patch adds support for chip version 2.0 or cut 2.0. One new interrupt latch register - latch 12 - is introduced. Signed-off-by: Mattias Wallin Acked-by: Linus Walleij Signed-off-by: Samuel Ortiz --- include/linux/mfd/ab8500.h | 53 ++++++++++++++++++++++++++-------------------- 1 file changed, 30 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/linux/mfd/ab8500.h b/include/linux/mfd/ab8500.h index 1ad1696..37f56b7 100644 --- a/include/linux/mfd/ab8500.h +++ b/include/linux/mfd/ab8500.h @@ -74,30 +74,37 @@ #define AB8500_INT_ACC_DETECT_21DB_F 37 #define AB8500_INT_ACC_DETECT_21DB_R 38 #define AB8500_INT_GP_SW_ADC_CONV_END 39 -#define AB8500_INT_BTEMP_LOW 72 -#define AB8500_INT_BTEMP_LOW_MEDIUM 73 -#define AB8500_INT_BTEMP_MEDIUM_HIGH 74 -#define AB8500_INT_BTEMP_HIGH 75 -#define AB8500_INT_USB_CHARGER_NOT_OK 81 -#define AB8500_INT_ID_WAKEUP_R 82 -#define AB8500_INT_ID_DET_R1R 84 -#define AB8500_INT_ID_DET_R2R 85 -#define AB8500_INT_ID_DET_R3R 86 -#define AB8500_INT_ID_DET_R4R 87 -#define AB8500_INT_ID_WAKEUP_F 88 -#define AB8500_INT_ID_DET_R1F 90 -#define AB8500_INT_ID_DET_R2F 91 -#define AB8500_INT_ID_DET_R3F 92 -#define AB8500_INT_ID_DET_R4F 93 -#define AB8500_INT_USB_CHG_DET_DONE 94 -#define AB8500_INT_USB_CH_TH_PROT_F 96 -#define AB8500_INT_USB_CH_TH_PROT_R 97 -#define AB8500_INT_MAIN_CH_TH_PROT_F 98 -#define AB8500_INT_MAIN_CH_TH_PROT_R 99 -#define AB8500_INT_USB_CHARGER_NOT_OKF 103 +#define AB8500_INT_ADP_SOURCE_ERROR 72 +#define AB8500_INT_ADP_SINK_ERROR 73 +#define AB8500_INT_ADP_PROBE_PLUG 74 +#define AB8500_INT_ADP_PROBE_UNPLUG 75 +#define AB8500_INT_ADP_SENSE_OFF 76 +#define AB8500_INT_USB_PHY_POWER_ERR 78 +#define AB8500_INT_USB_LINK_STATUS 79 +#define AB8500_INT_BTEMP_LOW 80 +#define AB8500_INT_BTEMP_LOW_MEDIUM 81 +#define AB8500_INT_BTEMP_MEDIUM_HIGH 82 +#define AB8500_INT_BTEMP_HIGH 83 +#define AB8500_INT_USB_CHARGER_NOT_OK 89 +#define AB8500_INT_ID_WAKEUP_R 90 +#define AB8500_INT_ID_DET_R1R 92 +#define AB8500_INT_ID_DET_R2R 93 +#define AB8500_INT_ID_DET_R3R 94 +#define AB8500_INT_ID_DET_R4R 95 +#define AB8500_INT_ID_WAKEUP_F 96 +#define AB8500_INT_ID_DET_R1F 98 +#define AB8500_INT_ID_DET_R2F 99 +#define AB8500_INT_ID_DET_R3F 100 +#define AB8500_INT_ID_DET_R4F 101 +#define AB8500_INT_USB_CHG_DET_DONE 102 +#define AB8500_INT_USB_CH_TH_PROT_F 104 +#define AB8500_INT_USB_CH_TH_PROT_R 105 +#define AB8500_INT_MAIN_CH_TH_PROT_F 106 +#define AB8500_INT_MAIN_CH_TH_PROT_R 107 +#define AB8500_INT_USB_CHARGER_NOT_OKF 111 -#define AB8500_NR_IRQS 104 -#define AB8500_NUM_IRQ_REGS 13 +#define AB8500_NR_IRQS 112 +#define AB8500_NUM_IRQ_REGS 14 /** * struct ab8500 - ab8500 internal structure -- cgit v1.1 From 32385c7cf60a78375b63afc4f02001df84dfd1a0 Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 14 Jan 2011 13:12:45 +0000 Subject: kernel: fix hlist_bl again __d_rehash is dereferencing an almost-NULL pointer on my ARM926. CONFIG_SMP=n and CONFIG_DEBUG_SPINLOCK=y. The faulting instruction is: strne r3, [r2, #4] and as can be seen from the register dump below, r2 is 0x00000001, hence the faulting 0x00000005 address. __d_rehash is essentially: spin_lock_bucket(b); entry->d_flags &= ~DCACHE_UNHASHED; hlist_bl_add_head_rcu(&entry->d_hash, &b->head); spin_unlock_bucket(b); which is: bit_spin_lock(0, (unsigned long *)&b->head.first); entry->d_flags &= ~DCACHE_UNHASHED; hlist_bl_add_head_rcu(&entry->d_hash, &b->head); __bit_spin_unlock(0, (unsigned long *)&b->head.first); bit_spin_lock(0, ptr) sets bit 0 of *ptr, in this case b->head.first if CONFIG_SMP or CONFIG_DEBUG_SPINLOCK is set: #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) while (unlikely(test_and_set_bit_lock(bitnum, addr))) { while (test_bit(bitnum, addr)) { preempt_enable(); cpu_relax(); preempt_disable(); } } #endif So, b->head.first starts off NULL, and becomes a non-NULL (address 1). hlist_bl_add_head_rcu() does this: static inline void hlist_bl_add_head_rcu(struct hlist_bl_node *n, struct hlist_bl_head *h) { first = hlist_bl_first(h); n->next = first; if (first) first->pprev = &n->next; It is the store to first->pprev which is faulting. hlist_bl_first(): static inline struct hlist_bl_node *hlist_bl_first(struct hlist_bl_head *h) { return (struct hlist_bl_node *) ((unsigned long)h->first & ~LIST_BL_LOCKMASK); } but: #if defined(CONFIG_SMP) #define LIST_BL_LOCKMASK 1UL #else #define LIST_BL_LOCKMASK 0UL #endif So, we have one piece of code which sets bit 0 of addresses, and another bit of code which doesn't clear it before dereferencing the pointer if !CONFIG_SMP && CONFIG_DEBUG_SPINLOCK. With the patch below, I can again sucessfully boot the kernel on my Versatile PB/926 platform. Signed-off-by: Russell King --- include/linux/list_bl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/list_bl.h b/include/linux/list_bl.h index b2adbb4..5bad17d 100644 --- a/include/linux/list_bl.h +++ b/include/linux/list_bl.h @@ -16,7 +16,7 @@ * some fast and compact auxiliary data. */ -#if defined(CONFIG_SMP) +#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) #define LIST_BL_LOCKMASK 1UL #else #define LIST_BL_LOCKMASK 0UL -- cgit v1.1 From 359ab9f5b154cbd807a11e22792235f0f36b0cd5 Mon Sep 17 00:00:00 2001 From: MyungJoo Ham Date: Fri, 14 Jan 2011 14:46:11 +0900 Subject: power_supply: Add MAX17042 Fuel Gauge Driver The MAX17042 is a fuel gauge with an I2C interface for lithium-ion betteries. Unlike its predecessor MAX17040, MAX17042 uses 16bit registers. Besides, MAX17042 has much more features than MAX17040; e.g., a thermistor, current and current accumulation measurement, battery internal resistance estimate, average values of measurement, and others. This patch implements a driver for MAX17042. In this initial release, we have implemented the most basic features of a fuel gauge: measure the battery capacity and voltage. Signed-off-by: MyungJoo Ham Signed-off-by: Kyungmin Park Signed-off-by: Anton Vorontsov --- include/linux/power/max17042_battery.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) create mode 100644 include/linux/power/max17042_battery.h (limited to 'include') diff --git a/include/linux/power/max17042_battery.h b/include/linux/power/max17042_battery.h new file mode 100644 index 0000000..7995deb --- /dev/null +++ b/include/linux/power/max17042_battery.h @@ -0,0 +1,30 @@ +/* + * Fuel gauge driver for Maxim 17042 / 8966 / 8997 + * Note that Maxim 8966 and 8997 are mfd and this is its subdevice. + * + * Copyright (C) 2011 Samsung Electronics + * MyungJoo Ham + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifndef __MAX17042_BATTERY_H_ +#define __MAX17042_BATTERY_H_ + +struct max17042_platform_data { + bool enable_current_sense; +}; + +#endif /* __MAX17042_BATTERY_H_ */ -- cgit v1.1 From 836cb711ad7960e52625b24195d6e70b79ab0816 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Fri, 14 Jan 2011 14:56:53 +0900 Subject: Revert update for dirty_ratio for memcg. The flags added by commit db16d5ec1f87f17511599bc77857dd1662b5a22f has no user now. We believe we'll use it soon but considering patch reviewing, the change itself should be folded into incoming set of "dirty ratio for memcg" patches. So, it's better to drop this change from current mainline tree. Signed-off-by: KAMEZAWA Hiroyuki Reviewed-by: Greg Thelen Signed-off-by: Linus Torvalds --- include/linux/page_cgroup.h | 23 ----------------------- 1 file changed, 23 deletions(-) (limited to 'include') diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h index 5b0c971..6d6cb7a 100644 --- a/include/linux/page_cgroup.h +++ b/include/linux/page_cgroup.h @@ -42,9 +42,6 @@ enum { /* flags for mem_cgroup and file and I/O status */ PCG_MOVE_LOCK, /* For race between move_account v.s. following bits */ PCG_FILE_MAPPED, /* page is accounted as "mapped" */ - PCG_FILE_DIRTY, /* page is dirty */ - PCG_FILE_WRITEBACK, /* page is under writeback */ - PCG_FILE_UNSTABLE_NFS, /* page is NFS unstable */ /* No lock in page_cgroup */ PCG_ACCT_LRU, /* page has been accounted for (under lru_lock) */ }; @@ -65,10 +62,6 @@ static inline void ClearPageCgroup##uname(struct page_cgroup *pc) \ static inline int TestClearPageCgroup##uname(struct page_cgroup *pc) \ { return test_and_clear_bit(PCG_##lname, &pc->flags); } -#define TESTSETPCGFLAG(uname, lname) \ -static inline int TestSetPageCgroup##uname(struct page_cgroup *pc) \ - { return test_and_set_bit(PCG_##lname, &pc->flags); } - /* Cache flag is set only once (at allocation) */ TESTPCGFLAG(Cache, CACHE) CLEARPCGFLAG(Cache, CACHE) @@ -88,22 +81,6 @@ SETPCGFLAG(FileMapped, FILE_MAPPED) CLEARPCGFLAG(FileMapped, FILE_MAPPED) TESTPCGFLAG(FileMapped, FILE_MAPPED) -SETPCGFLAG(FileDirty, FILE_DIRTY) -CLEARPCGFLAG(FileDirty, FILE_DIRTY) -TESTPCGFLAG(FileDirty, FILE_DIRTY) -TESTCLEARPCGFLAG(FileDirty, FILE_DIRTY) -TESTSETPCGFLAG(FileDirty, FILE_DIRTY) - -SETPCGFLAG(FileWriteback, FILE_WRITEBACK) -CLEARPCGFLAG(FileWriteback, FILE_WRITEBACK) -TESTPCGFLAG(FileWriteback, FILE_WRITEBACK) - -SETPCGFLAG(FileUnstableNFS, FILE_UNSTABLE_NFS) -CLEARPCGFLAG(FileUnstableNFS, FILE_UNSTABLE_NFS) -TESTPCGFLAG(FileUnstableNFS, FILE_UNSTABLE_NFS) -TESTCLEARPCGFLAG(FileUnstableNFS, FILE_UNSTABLE_NFS) -TESTSETPCGFLAG(FileUnstableNFS, FILE_UNSTABLE_NFS) - SETPCGFLAG(Migration, MIGRATION) CLEARPCGFLAG(Migration, MIGRATION) TESTPCGFLAG(Migration, MIGRATION) -- cgit v1.1 From 323b7fe8f8f6d5ac6214382cf30e8b3a80b265c9 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Fri, 14 Jan 2011 09:34:29 +0100 Subject: include/gpio.h: remove remaining __must_check-annotiations Commit 5f829e405ec4e96f711165a4a7b55c271d4363e2 (gpiolib: add missing functions to generic fallback) also introduced two. Signed-off-by: Wolfram Sang Cc: Greg KH Cc: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gpio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 4b47ed9..32720ba 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -35,13 +35,13 @@ static inline int gpio_request(unsigned gpio, const char *label) return -ENOSYS; } -static inline int __must_check gpio_request_one(unsigned gpio, +static inline int gpio_request_one(unsigned gpio, unsigned long flags, const char *label) { return -ENOSYS; } -static inline int __must_check gpio_request_array(struct gpio *array, size_t num) +static inline int gpio_request_array(struct gpio *array, size_t num) { return -ENOSYS; } -- cgit v1.1 From c66ac9db8d4ad9994a02b3e933ea2ccc643e1fe5 Mon Sep 17 00:00:00 2001 From: Nicholas Bellinger Date: Fri, 17 Dec 2010 11:11:26 -0800 Subject: [SCSI] target: Add LIO target core v4.0.0-rc6 LIO target is a full featured in-kernel target framework with the following feature set: High-performance, non-blocking, multithreaded architecture with SIMD support. Advanced SCSI feature set: * Persistent Reservations (PRs) * Asymmetric Logical Unit Assignment (ALUA) * Protocol and intra-nexus multiplexing, load-balancing and failover (MC/S) * Full Error Recovery (ERL=0,1,2) * Active/active task migration and session continuation (ERL=2) * Thin LUN provisioning (UNMAP and WRITE_SAMExx) Multiprotocol target plugins Storage media independence: * Virtualization of all storage media; transparent mapping of IO to LUNs * No hard limits on number of LUNs per Target; maximum LUN size ~750 TB * Backstores: SATA, SAS, SCSI, BluRay, DVD, FLASH, USB, ramdisk, etc. Standards compliance: * Full compliance with IETF (RFC 3720) * Full implementation of SPC-4 PRs and ALUA Significant code cleanups done by Christoph Hellwig. [jejb: fix up for new block bdev exclusive interface. Minor fixes from Randy Dunlap and Dan Carpenter.] Signed-off-by: Nicholas A. Bellinger Signed-off-by: James Bottomley --- include/target/configfs_macros.h | 147 +++++ include/target/target_core_base.h | 937 +++++++++++++++++++++++++++ include/target/target_core_configfs.h | 52 ++ include/target/target_core_device.h | 61 ++ include/target/target_core_fabric_configfs.h | 106 +++ include/target/target_core_fabric_lib.h | 28 + include/target/target_core_fabric_ops.h | 100 +++ include/target/target_core_tmr.h | 43 ++ include/target/target_core_tpg.h | 35 + include/target/target_core_transport.h | 351 ++++++++++ 10 files changed, 1860 insertions(+) create mode 100644 include/target/configfs_macros.h create mode 100644 include/target/target_core_base.h create mode 100644 include/target/target_core_configfs.h create mode 100644 include/target/target_core_device.h create mode 100644 include/target/target_core_fabric_configfs.h create mode 100644 include/target/target_core_fabric_lib.h create mode 100644 include/target/target_core_fabric_ops.h create mode 100644 include/target/target_core_tmr.h create mode 100644 include/target/target_core_tpg.h create mode 100644 include/target/target_core_transport.h (limited to 'include') diff --git a/include/target/configfs_macros.h b/include/target/configfs_macros.h new file mode 100644 index 0000000..7fe7460 --- /dev/null +++ b/include/target/configfs_macros.h @@ -0,0 +1,147 @@ +/* -*- mode: c; c-basic-offset: 8; -*- + * vim: noexpandtab sw=8 ts=8 sts=0: + * + * configfs_macros.h - extends macros for configfs + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public + * License as published by the Free Software Foundation; either + * version 2 of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public + * License along with this program; if not, write to the + * Free Software Foundation, Inc., 59 Temple Place - Suite 330, + * Boston, MA 021110-1307, USA. + * + * Based on sysfs: + * sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel + * + * Based on kobject.h: + * Copyright (c) 2002-2003 Patrick Mochel + * Copyright (c) 2002-2003 Open Source Development Labs + * + * configfs Copyright (C) 2005 Oracle. All rights reserved. + * + * Added CONFIGFS_EATTR() macros from original configfs.h macros + * Copright (C) 2008-2009 Nicholas A. Bellinger + * + * Please read Documentation/filesystems/configfs.txt before using the + * configfs interface, ESPECIALLY the parts about reference counts and + * item destructors. + */ + +#ifndef _CONFIGFS_MACROS_H_ +#define _CONFIGFS_MACROS_H_ + +#include + +/* + * Users often need to create attribute structures for their configurable + * attributes, containing a configfs_attribute member and function pointers + * for the show() and store() operations on that attribute. If they don't + * need anything else on the extended attribute structure, they can use + * this macro to define it. The argument _name isends up as + * 'struct _name_attribute, as well as names of to CONFIGFS_ATTR_OPS() below. + * The argument _item is the name of the structure containing the + * struct config_item or struct config_group structure members + */ +#define CONFIGFS_EATTR_STRUCT(_name, _item) \ +struct _name##_attribute { \ + struct configfs_attribute attr; \ + ssize_t (*show)(struct _item *, char *); \ + ssize_t (*store)(struct _item *, const char *, size_t); \ +} + +/* + * With the extended attribute structure, users can use this macro + * (similar to sysfs' __ATTR) to make defining attributes easier. + * An example: + * #define MYITEM_EATTR(_name, _mode, _show, _store) \ + * struct myitem_attribute childless_attr_##_name = \ + * __CONFIGFS_EATTR(_name, _mode, _show, _store) + */ +#define __CONFIGFS_EATTR(_name, _mode, _show, _store) \ +{ \ + .attr = { \ + .ca_name = __stringify(_name), \ + .ca_mode = _mode, \ + .ca_owner = THIS_MODULE, \ + }, \ + .show = _show, \ + .store = _store, \ +} +/* Here is a readonly version, only requiring a show() operation */ +#define __CONFIGFS_EATTR_RO(_name, _show) \ +{ \ + .attr = { \ + .ca_name = __stringify(_name), \ + .ca_mode = 0444, \ + .ca_owner = THIS_MODULE, \ + }, \ + .show = _show, \ +} + +/* + * With these extended attributes, the simple show_attribute() and + * store_attribute() operations need to call the show() and store() of the + * attributes. This is a common pattern, so we provide a macro to define + * them. The argument _name is the name of the attribute defined by + * CONFIGFS_ATTR_STRUCT(). The argument _item is the name of the structure + * containing the struct config_item or struct config_group structure member. + * The argument _item_member is the actual name of the struct config_* struct + * in your _item structure. Meaning my_structure->some_config_group. + * ^^_item^^^^^ ^^_item_member^^^ + * This macro expects the attributes to be named "struct _attribute". + */ +#define CONFIGFS_EATTR_OPS_TO_FUNC(_name, _item, _item_member) \ +static struct _item *to_##_name(struct config_item *ci) \ +{ \ + return (ci) ? container_of(to_config_group(ci), struct _item, \ + _item_member) : NULL; \ +} + +#define CONFIGFS_EATTR_OPS_SHOW(_name, _item) \ +static ssize_t _name##_attr_show(struct config_item *item, \ + struct configfs_attribute *attr, \ + char *page) \ +{ \ + struct _item *_item = to_##_name(item); \ + struct _name##_attribute * _name##_attr = \ + container_of(attr, struct _name##_attribute, attr); \ + ssize_t ret = 0; \ + \ + if (_name##_attr->show) \ + ret = _name##_attr->show(_item, page); \ + return ret; \ +} + +#define CONFIGFS_EATTR_OPS_STORE(_name, _item) \ +static ssize_t _name##_attr_store(struct config_item *item, \ + struct configfs_attribute *attr, \ + const char *page, size_t count) \ +{ \ + struct _item *_item = to_##_name(item); \ + struct _name##_attribute * _name##_attr = \ + container_of(attr, struct _name##_attribute, attr); \ + ssize_t ret = -EINVAL; \ + \ + if (_name##_attr->store) \ + ret = _name##_attr->store(_item, page, count); \ + return ret; \ +} + +#define CONFIGFS_EATTR_OPS(_name, _item, _item_member) \ + CONFIGFS_EATTR_OPS_TO_FUNC(_name, _item, _item_member); \ + CONFIGFS_EATTR_OPS_SHOW(_name, _item); \ + CONFIGFS_EATTR_OPS_STORE(_name, _item); + +#define CONFIGFS_EATTR_OPS_RO(_name, _item, _item_member) \ + CONFIGFS_EATTR_OPS_TO_FUNC(_name, _item, _item_member); \ + CONFIGFS_EATTR_OPS_SHOW(_name, _item); + +#endif /* _CONFIGFS_MACROS_H_ */ diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h new file mode 100644 index 0000000..07fdfb6 --- /dev/null +++ b/include/target/target_core_base.h @@ -0,0 +1,937 @@ +#ifndef TARGET_CORE_BASE_H +#define TARGET_CORE_BASE_H + +#include +#include +#include +#include +#include +#include +#include +#include "target_core_mib.h" + +#define TARGET_CORE_MOD_VERSION "v4.0.0-rc6" +#define SHUTDOWN_SIGS (sigmask(SIGKILL)|sigmask(SIGINT)|sigmask(SIGABRT)) + +/* Used by transport_generic_allocate_iovecs() */ +#define TRANSPORT_IOV_DATA_BUFFER 5 +/* Maximum Number of LUNs per Target Portal Group */ +#define TRANSPORT_MAX_LUNS_PER_TPG 256 +/* + * By default we use 32-byte CDBs in TCM Core and subsystem plugin code. + * + * Note that both include/scsi/scsi_cmnd.h:MAX_COMMAND_SIZE and + * include/linux/blkdev.h:BLOCK_MAX_CDB as of v2.6.36-rc4 still use + * 16-byte CDBs by default and require an extra allocation for + * 32-byte CDBs to becasue of legacy issues. + * + * Within TCM Core there are no such legacy limitiations, so we go ahead + * use 32-byte CDBs by default and use include/scsi/scsi.h:scsi_command_size() + * within all TCM Core and subsystem plugin code. + */ +#define TCM_MAX_COMMAND_SIZE 32 +/* + * From include/scsi/scsi_cmnd.h:SCSI_SENSE_BUFFERSIZE, currently + * defined 96, but the real limit is 252 (or 260 including the header) + */ +#define TRANSPORT_SENSE_BUFFER SCSI_SENSE_BUFFERSIZE +/* Used by transport_send_check_condition_and_sense() */ +#define SPC_SENSE_KEY_OFFSET 2 +#define SPC_ASC_KEY_OFFSET 12 +#define SPC_ASCQ_KEY_OFFSET 13 +#define TRANSPORT_IQN_LEN 224 +/* Used by target_core_store_alua_lu_gp() and target_core_alua_lu_gp_show_attr_members() */ +#define LU_GROUP_NAME_BUF 256 +/* Used by core_alua_store_tg_pt_gp_info() and target_core_alua_tg_pt_gp_show_attr_members() */ +#define TG_PT_GROUP_NAME_BUF 256 +/* Used to parse VPD into struct t10_vpd */ +#define VPD_TMP_BUF_SIZE 128 +/* Used by transport_generic_cmd_sequencer() */ +#define READ_BLOCK_LEN 6 +#define READ_CAP_LEN 8 +#define READ_POSITION_LEN 20 +#define INQUIRY_LEN 36 +/* Used by transport_get_inquiry_vpd_serial() */ +#define INQUIRY_VPD_SERIAL_LEN 254 +/* Used by transport_get_inquiry_vpd_device_ident() */ +#define INQUIRY_VPD_DEVICE_IDENTIFIER_LEN 254 + +/* struct se_hba->hba_flags */ +enum hba_flags_table { + HBA_FLAGS_INTERNAL_USE = 0x01, + HBA_FLAGS_PSCSI_MODE = 0x02, +}; + +/* struct se_lun->lun_status */ +enum transport_lun_status_table { + TRANSPORT_LUN_STATUS_FREE = 0, + TRANSPORT_LUN_STATUS_ACTIVE = 1, +}; + +/* struct se_portal_group->se_tpg_type */ +enum transport_tpg_type_table { + TRANSPORT_TPG_TYPE_NORMAL = 0, + TRANSPORT_TPG_TYPE_DISCOVERY = 1, +}; + +/* Used for generate timer flags */ +enum timer_flags_table { + TF_RUNNING = 0x01, + TF_STOP = 0x02, +}; + +/* Special transport agnostic struct se_cmd->t_states */ +enum transport_state_table { + TRANSPORT_NO_STATE = 0, + TRANSPORT_NEW_CMD = 1, + TRANSPORT_DEFERRED_CMD = 2, + TRANSPORT_WRITE_PENDING = 3, + TRANSPORT_PROCESS_WRITE = 4, + TRANSPORT_PROCESSING = 5, + TRANSPORT_COMPLETE_OK = 6, + TRANSPORT_COMPLETE_FAILURE = 7, + TRANSPORT_COMPLETE_TIMEOUT = 8, + TRANSPORT_PROCESS_TMR = 9, + TRANSPORT_TMR_COMPLETE = 10, + TRANSPORT_ISTATE_PROCESSING = 11, + TRANSPORT_ISTATE_PROCESSED = 12, + TRANSPORT_KILL = 13, + TRANSPORT_REMOVE = 14, + TRANSPORT_FREE = 15, + TRANSPORT_NEW_CMD_MAP = 16, +}; + +/* Used for struct se_cmd->se_cmd_flags */ +enum se_cmd_flags_table { + SCF_SUPPORTED_SAM_OPCODE = 0x00000001, + SCF_TRANSPORT_TASK_SENSE = 0x00000002, + SCF_EMULATED_TASK_SENSE = 0x00000004, + SCF_SCSI_DATA_SG_IO_CDB = 0x00000008, + SCF_SCSI_CONTROL_SG_IO_CDB = 0x00000010, + SCF_SCSI_CONTROL_NONSG_IO_CDB = 0x00000020, + SCF_SCSI_NON_DATA_CDB = 0x00000040, + SCF_SCSI_CDB_EXCEPTION = 0x00000080, + SCF_SCSI_RESERVATION_CONFLICT = 0x00000100, + SCF_CMD_PASSTHROUGH_NOALLOC = 0x00000200, + SCF_SE_CMD_FAILED = 0x00000400, + SCF_SE_LUN_CMD = 0x00000800, + SCF_SE_ALLOW_EOO = 0x00001000, + SCF_SE_DISABLE_ONLINE_CHECK = 0x00002000, + SCF_SENT_CHECK_CONDITION = 0x00004000, + SCF_OVERFLOW_BIT = 0x00008000, + SCF_UNDERFLOW_BIT = 0x00010000, + SCF_SENT_DELAYED_TAS = 0x00020000, + SCF_ALUA_NON_OPTIMIZED = 0x00040000, + SCF_DELAYED_CMD_FROM_SAM_ATTR = 0x00080000, + SCF_PASSTHROUGH_SG_TO_MEM = 0x00100000, + SCF_PASSTHROUGH_CONTIG_TO_SG = 0x00200000, + SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC = 0x00400000, + SCF_EMULATE_SYNC_CACHE = 0x00800000, + SCF_EMULATE_CDB_ASYNC = 0x01000000, + SCF_EMULATE_SYNC_UNMAP = 0x02000000 +}; + +/* struct se_dev_entry->lun_flags and struct se_lun->lun_access */ +enum transport_lunflags_table { + TRANSPORT_LUNFLAGS_NO_ACCESS = 0x00, + TRANSPORT_LUNFLAGS_INITIATOR_ACCESS = 0x01, + TRANSPORT_LUNFLAGS_READ_ONLY = 0x02, + TRANSPORT_LUNFLAGS_READ_WRITE = 0x04, +}; + +/* struct se_device->dev_status */ +enum transport_device_status_table { + TRANSPORT_DEVICE_ACTIVATED = 0x01, + TRANSPORT_DEVICE_DEACTIVATED = 0x02, + TRANSPORT_DEVICE_QUEUE_FULL = 0x04, + TRANSPORT_DEVICE_SHUTDOWN = 0x08, + TRANSPORT_DEVICE_OFFLINE_ACTIVATED = 0x10, + TRANSPORT_DEVICE_OFFLINE_DEACTIVATED = 0x20, +}; + +/* + * Used by transport_send_check_condition_and_sense() and se_cmd->scsi_sense_reason + * to signal which ASC/ASCQ sense payload should be built. + */ +enum tcm_sense_reason_table { + TCM_NON_EXISTENT_LUN = 0x01, + TCM_UNSUPPORTED_SCSI_OPCODE = 0x02, + TCM_INCORRECT_AMOUNT_OF_DATA = 0x03, + TCM_UNEXPECTED_UNSOLICITED_DATA = 0x04, + TCM_SERVICE_CRC_ERROR = 0x05, + TCM_SNACK_REJECTED = 0x06, + TCM_SECTOR_COUNT_TOO_MANY = 0x07, + TCM_INVALID_CDB_FIELD = 0x08, + TCM_INVALID_PARAMETER_LIST = 0x09, + TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE = 0x0a, + TCM_UNKNOWN_MODE_PAGE = 0x0b, + TCM_WRITE_PROTECTED = 0x0c, + TCM_CHECK_CONDITION_ABORT_CMD = 0x0d, + TCM_CHECK_CONDITION_UNIT_ATTENTION = 0x0e, + TCM_CHECK_CONDITION_NOT_READY = 0x0f, +}; + +struct se_obj { + atomic_t obj_access_count; +} ____cacheline_aligned; + +/* + * Used by TCM Core internally to signal if ALUA emulation is enabled or + * disabled, or running in with TCM/pSCSI passthrough mode + */ +typedef enum { + SPC_ALUA_PASSTHROUGH, + SPC2_ALUA_DISABLED, + SPC3_ALUA_EMULATED +} t10_alua_index_t; + +/* + * Used by TCM Core internally to signal if SAM Task Attribute emulation + * is enabled or disabled, or running in with TCM/pSCSI passthrough mode + */ +typedef enum { + SAM_TASK_ATTR_PASSTHROUGH, + SAM_TASK_ATTR_UNTAGGED, + SAM_TASK_ATTR_EMULATED +} t10_task_attr_index_t; + +struct se_cmd; + +struct t10_alua { + t10_alua_index_t alua_type; + /* ALUA Target Port Group ID */ + u16 alua_tg_pt_gps_counter; + u32 alua_tg_pt_gps_count; + spinlock_t tg_pt_gps_lock; + struct se_subsystem_dev *t10_sub_dev; + /* Used for default ALUA Target Port Group */ + struct t10_alua_tg_pt_gp *default_tg_pt_gp; + /* Used for default ALUA Target Port Group ConfigFS group */ + struct config_group alua_tg_pt_gps_group; + int (*alua_state_check)(struct se_cmd *, unsigned char *, u8 *); + struct list_head tg_pt_gps_list; +} ____cacheline_aligned; + +struct t10_alua_lu_gp { + u16 lu_gp_id; + int lu_gp_valid_id; + u32 lu_gp_members; + atomic_t lu_gp_shutdown; + atomic_t lu_gp_ref_cnt; + spinlock_t lu_gp_lock; + struct config_group lu_gp_group; + struct list_head lu_gp_list; + struct list_head lu_gp_mem_list; +} ____cacheline_aligned; + +struct t10_alua_lu_gp_member { + int lu_gp_assoc:1; + atomic_t lu_gp_mem_ref_cnt; + spinlock_t lu_gp_mem_lock; + struct t10_alua_lu_gp *lu_gp; + struct se_device *lu_gp_mem_dev; + struct list_head lu_gp_mem_list; +} ____cacheline_aligned; + +struct t10_alua_tg_pt_gp { + u16 tg_pt_gp_id; + int tg_pt_gp_valid_id; + int tg_pt_gp_alua_access_status; + int tg_pt_gp_alua_access_type; + int tg_pt_gp_nonop_delay_msecs; + int tg_pt_gp_trans_delay_msecs; + int tg_pt_gp_pref; + int tg_pt_gp_write_metadata; + /* Used by struct t10_alua_tg_pt_gp->tg_pt_gp_md_buf_len */ +#define ALUA_MD_BUF_LEN 1024 + u32 tg_pt_gp_md_buf_len; + u32 tg_pt_gp_members; + atomic_t tg_pt_gp_alua_access_state; + atomic_t tg_pt_gp_ref_cnt; + spinlock_t tg_pt_gp_lock; + struct mutex tg_pt_gp_md_mutex; + struct se_subsystem_dev *tg_pt_gp_su_dev; + struct config_group tg_pt_gp_group; + struct list_head tg_pt_gp_list; + struct list_head tg_pt_gp_mem_list; +} ____cacheline_aligned; + +struct t10_alua_tg_pt_gp_member { + int tg_pt_gp_assoc:1; + atomic_t tg_pt_gp_mem_ref_cnt; + spinlock_t tg_pt_gp_mem_lock; + struct t10_alua_tg_pt_gp *tg_pt_gp; + struct se_port *tg_pt; + struct list_head tg_pt_gp_mem_list; +} ____cacheline_aligned; + +struct t10_vpd { + unsigned char device_identifier[INQUIRY_VPD_DEVICE_IDENTIFIER_LEN]; + int protocol_identifier_set; + u32 protocol_identifier; + u32 device_identifier_code_set; + u32 association; + u32 device_identifier_type; + struct list_head vpd_list; +} ____cacheline_aligned; + +struct t10_wwn { + unsigned char vendor[8]; + unsigned char model[16]; + unsigned char revision[4]; + unsigned char unit_serial[INQUIRY_VPD_SERIAL_LEN]; + spinlock_t t10_vpd_lock; + struct se_subsystem_dev *t10_sub_dev; + struct config_group t10_wwn_group; + struct list_head t10_vpd_list; +} ____cacheline_aligned; + + +/* + * Used by TCM Core internally to signal if >= SPC-3 peristent reservations + * emulation is enabled or disabled, or running in with TCM/pSCSI passthrough + * mode + */ +typedef enum { + SPC_PASSTHROUGH, + SPC2_RESERVATIONS, + SPC3_PERSISTENT_RESERVATIONS +} t10_reservations_index_t; + +struct t10_pr_registration { + /* Used for fabrics that contain WWN+ISID */ +#define PR_REG_ISID_LEN 16 + /* PR_REG_ISID_LEN + ',i,0x' */ +#define PR_REG_ISID_ID_LEN (PR_REG_ISID_LEN + 5) + char pr_reg_isid[PR_REG_ISID_LEN]; + /* Used during APTPL metadata reading */ +#define PR_APTPL_MAX_IPORT_LEN 256 + unsigned char pr_iport[PR_APTPL_MAX_IPORT_LEN]; + /* Used during APTPL metadata reading */ +#define PR_APTPL_MAX_TPORT_LEN 256 + unsigned char pr_tport[PR_APTPL_MAX_TPORT_LEN]; + /* For writing out live meta data */ + unsigned char *pr_aptpl_buf; + u16 pr_aptpl_rpti; + u16 pr_reg_tpgt; + /* Reservation effects all target ports */ + int pr_reg_all_tg_pt; + /* Activate Persistence across Target Power Loss */ + int pr_reg_aptpl; + int pr_res_holder; + int pr_res_type; + int pr_res_scope; + /* Used for fabric initiator WWPNs using a ISID */ + int isid_present_at_reg:1; + u32 pr_res_mapped_lun; + u32 pr_aptpl_target_lun; + u32 pr_res_generation; + u64 pr_reg_bin_isid; + u64 pr_res_key; + atomic_t pr_res_holders; + struct se_node_acl *pr_reg_nacl; + struct se_dev_entry *pr_reg_deve; + struct se_lun *pr_reg_tg_pt_lun; + struct list_head pr_reg_list; + struct list_head pr_reg_abort_list; + struct list_head pr_reg_aptpl_list; + struct list_head pr_reg_atp_list; + struct list_head pr_reg_atp_mem_list; +} ____cacheline_aligned; + +/* + * This set of function pointer ops is set based upon SPC3_PERSISTENT_RESERVATIONS, + * SPC2_RESERVATIONS or SPC_PASSTHROUGH in drivers/target/target_core_pr.c: + * core_setup_reservations() + */ +struct t10_reservation_ops { + int (*t10_reservation_check)(struct se_cmd *, u32 *); + int (*t10_seq_non_holder)(struct se_cmd *, unsigned char *, u32); + int (*t10_pr_register)(struct se_cmd *); + int (*t10_pr_clear)(struct se_cmd *); +}; + +struct t10_reservation_template { + /* Reservation effects all target ports */ + int pr_all_tg_pt; + /* Activate Persistence across Target Power Loss enabled + * for SCSI device */ + int pr_aptpl_active; + /* Used by struct t10_reservation_template->pr_aptpl_buf_len */ +#define PR_APTPL_BUF_LEN 8192 + u32 pr_aptpl_buf_len; + u32 pr_generation; + t10_reservations_index_t res_type; + spinlock_t registration_lock; + spinlock_t aptpl_reg_lock; + /* + * This will always be set by one individual I_T Nexus. + * However with all_tg_pt=1, other I_T Nexus from the + * same initiator can access PR reg/res info on a different + * target port. + * + * There is also the 'All Registrants' case, where there is + * a single *pr_res_holder of the reservation, but all + * registrations are considered reservation holders. + */ + struct se_node_acl *pr_res_holder; + struct list_head registration_list; + struct list_head aptpl_reg_list; + struct t10_reservation_ops pr_ops; +} ____cacheline_aligned; + +struct se_queue_req { + int state; + void *cmd; + struct list_head qr_list; +} ____cacheline_aligned; + +struct se_queue_obj { + atomic_t queue_cnt; + spinlock_t cmd_queue_lock; + struct list_head qobj_list; + wait_queue_head_t thread_wq; +} ____cacheline_aligned; + +/* + * Used one per struct se_cmd to hold all extra struct se_task + * metadata. This structure is setup and allocated in + * drivers/target/target_core_transport.c:__transport_alloc_se_cmd() + */ +struct se_transport_task { + unsigned char *t_task_cdb; + unsigned char __t_task_cdb[TCM_MAX_COMMAND_SIZE]; + unsigned long long t_task_lba; + int t_tasks_failed; + int t_tasks_fua; + int t_tasks_bidi:1; + u32 t_task_cdbs; + u32 t_tasks_check; + u32 t_tasks_no; + u32 t_tasks_sectors; + u32 t_tasks_se_num; + u32 t_tasks_se_bidi_num; + u32 t_tasks_sg_chained_no; + atomic_t t_fe_count; + atomic_t t_se_count; + atomic_t t_task_cdbs_left; + atomic_t t_task_cdbs_ex_left; + atomic_t t_task_cdbs_timeout_left; + atomic_t t_task_cdbs_sent; + atomic_t t_transport_aborted; + atomic_t t_transport_active; + atomic_t t_transport_complete; + atomic_t t_transport_queue_active; + atomic_t t_transport_sent; + atomic_t t_transport_stop; + atomic_t t_transport_timeout; + atomic_t transport_dev_active; + atomic_t transport_lun_active; + atomic_t transport_lun_fe_stop; + atomic_t transport_lun_stop; + spinlock_t t_state_lock; + struct completion t_transport_stop_comp; + struct completion transport_lun_fe_stop_comp; + struct completion transport_lun_stop_comp; + struct scatterlist *t_tasks_sg_chained; + struct scatterlist t_tasks_sg_bounce; + void *t_task_buf; + /* + * Used for pre-registered fabric SGL passthrough WRITE and READ + * with the special SCF_PASSTHROUGH_CONTIG_TO_SG case for TCM_Loop + * and other HW target mode fabric modules. + */ + struct scatterlist *t_task_pt_sgl; + struct list_head *t_mem_list; + /* Used for BIDI READ */ + struct list_head *t_mem_bidi_list; + struct list_head t_task_list; +} ____cacheline_aligned; + +struct se_task { + unsigned char task_sense; + struct scatterlist *task_sg; + struct scatterlist *task_sg_bidi; + u8 task_scsi_status; + u8 task_flags; + int task_error_status; + int task_state_flags; + int task_padded_sg:1; + unsigned long long task_lba; + u32 task_no; + u32 task_sectors; + u32 task_size; + u32 task_sg_num; + u32 task_sg_offset; + enum dma_data_direction task_data_direction; + struct se_cmd *task_se_cmd; + struct se_device *se_dev; + struct completion task_stop_comp; + atomic_t task_active; + atomic_t task_execute_queue; + atomic_t task_timeout; + atomic_t task_sent; + atomic_t task_stop; + atomic_t task_state_active; + struct timer_list task_timer; + struct se_device *se_obj_ptr; + struct list_head t_list; + struct list_head t_execute_list; + struct list_head t_state_list; +} ____cacheline_aligned; + +#define TASK_CMD(task) ((struct se_cmd *)task->task_se_cmd) +#define TASK_DEV(task) ((struct se_device *)task->se_dev) + +struct se_cmd { + /* SAM response code being sent to initiator */ + u8 scsi_status; + u8 scsi_asc; + u8 scsi_ascq; + u8 scsi_sense_reason; + u16 scsi_sense_length; + /* Delay for ALUA Active/NonOptimized state access in milliseconds */ + int alua_nonop_delay; + /* See include/linux/dma-mapping.h */ + enum dma_data_direction data_direction; + /* For SAM Task Attribute */ + int sam_task_attr; + /* Transport protocol dependent state, see transport_state_table */ + enum transport_state_table t_state; + /* Transport protocol dependent state for out of order CmdSNs */ + int deferred_t_state; + /* Transport specific error status */ + int transport_error_status; + /* See se_cmd_flags_table */ + u32 se_cmd_flags; + u32 se_ordered_id; + /* Total size in bytes associated with command */ + u32 data_length; + /* SCSI Presented Data Transfer Length */ + u32 cmd_spdtl; + u32 residual_count; + u32 orig_fe_lun; + /* Persistent Reservation key */ + u64 pr_res_key; + atomic_t transport_sent; + /* Used for sense data */ + void *sense_buffer; + struct list_head se_delayed_list; + struct list_head se_ordered_list; + struct list_head se_lun_list; + struct se_device *se_dev; + struct se_dev_entry *se_deve; + struct se_device *se_obj_ptr; + struct se_device *se_orig_obj_ptr; + struct se_lun *se_lun; + /* Only used for internal passthrough and legacy TCM fabric modules */ + struct se_session *se_sess; + struct se_tmr_req *se_tmr_req; + /* t_task is setup to t_task_backstore in transport_init_se_cmd() */ + struct se_transport_task *t_task; + struct se_transport_task t_task_backstore; + struct target_core_fabric_ops *se_tfo; + int (*transport_emulate_cdb)(struct se_cmd *); + void (*transport_split_cdb)(unsigned long long, u32 *, unsigned char *); + void (*transport_wait_for_tasks)(struct se_cmd *, int, int); + void (*transport_complete_callback)(struct se_cmd *); +} ____cacheline_aligned; + +#define T_TASK(cmd) ((struct se_transport_task *)(cmd->t_task)) +#define CMD_TFO(cmd) ((struct target_core_fabric_ops *)cmd->se_tfo) + +struct se_tmr_req { + /* Task Management function to be preformed */ + u8 function; + /* Task Management response to send */ + u8 response; + int call_transport; + /* Reference to ITT that Task Mgmt should be preformed */ + u32 ref_task_tag; + /* 64-bit encoded SAM LUN from $FABRIC_MOD TMR header */ + u64 ref_task_lun; + void *fabric_tmr_ptr; + struct se_cmd *task_cmd; + struct se_cmd *ref_cmd; + struct se_device *tmr_dev; + struct se_lun *tmr_lun; + struct list_head tmr_list; +} ____cacheline_aligned; + +struct se_ua { + u8 ua_asc; + u8 ua_ascq; + struct se_node_acl *ua_nacl; + struct list_head ua_dev_list; + struct list_head ua_nacl_list; +} ____cacheline_aligned; + +struct se_node_acl { + char initiatorname[TRANSPORT_IQN_LEN]; + /* Used to signal demo mode created ACL, disabled by default */ + int dynamic_node_acl:1; + u32 queue_depth; + u32 acl_index; + u64 num_cmds; + u64 read_bytes; + u64 write_bytes; + spinlock_t stats_lock; + /* Used for PR SPEC_I_PT=1 and REGISTER_AND_MOVE */ + atomic_t acl_pr_ref_count; + /* Used for MIB access */ + atomic_t mib_ref_count; + struct se_dev_entry *device_list; + struct se_session *nacl_sess; + struct se_portal_group *se_tpg; + spinlock_t device_list_lock; + spinlock_t nacl_sess_lock; + struct config_group acl_group; + struct config_group acl_attrib_group; + struct config_group acl_auth_group; + struct config_group acl_param_group; + struct config_group *acl_default_groups[4]; + struct list_head acl_list; + struct list_head acl_sess_list; +} ____cacheline_aligned; + +struct se_session { + /* Used for MIB access */ + atomic_t mib_ref_count; + u64 sess_bin_isid; + struct se_node_acl *se_node_acl; + struct se_portal_group *se_tpg; + void *fabric_sess_ptr; + struct list_head sess_list; + struct list_head sess_acl_list; +} ____cacheline_aligned; + +#define SE_SESS(cmd) ((struct se_session *)(cmd)->se_sess) +#define SE_NODE_ACL(sess) ((struct se_node_acl *)(sess)->se_node_acl) + +struct se_device; +struct se_transform_info; +struct scatterlist; + +struct se_lun_acl { + char initiatorname[TRANSPORT_IQN_LEN]; + u32 mapped_lun; + struct se_node_acl *se_lun_nacl; + struct se_lun *se_lun; + struct list_head lacl_list; + struct config_group se_lun_group; +} ____cacheline_aligned; + +struct se_dev_entry { + int def_pr_registered:1; + /* See transport_lunflags_table */ + u32 lun_flags; + u32 deve_cmds; + u32 mapped_lun; + u32 average_bytes; + u32 last_byte_count; + u32 total_cmds; + u32 total_bytes; + u64 pr_res_key; + u64 creation_time; + u32 attach_count; + u64 read_bytes; + u64 write_bytes; + atomic_t ua_count; + /* Used for PR SPEC_I_PT=1 and REGISTER_AND_MOVE */ + atomic_t pr_ref_count; + struct se_lun_acl *se_lun_acl; + spinlock_t ua_lock; + struct se_lun *se_lun; + struct list_head alua_port_list; + struct list_head ua_list; +} ____cacheline_aligned; + +struct se_dev_limits { + /* Max supported HW queue depth */ + u32 hw_queue_depth; + /* Max supported virtual queue depth */ + u32 queue_depth; + /* From include/linux/blkdev.h for the other HW/SW limits. */ + struct queue_limits limits; +} ____cacheline_aligned; + +struct se_dev_attrib { + int emulate_dpo; + int emulate_fua_write; + int emulate_fua_read; + int emulate_write_cache; + int emulate_ua_intlck_ctrl; + int emulate_tas; + int emulate_tpu; + int emulate_tpws; + int emulate_reservations; + int emulate_alua; + int enforce_pr_isids; + u32 hw_block_size; + u32 block_size; + u32 hw_max_sectors; + u32 max_sectors; + u32 optimal_sectors; + u32 hw_queue_depth; + u32 queue_depth; + u32 task_timeout; + u32 max_unmap_lba_count; + u32 max_unmap_block_desc_count; + u32 unmap_granularity; + u32 unmap_granularity_alignment; + struct se_subsystem_dev *da_sub_dev; + struct config_group da_group; +} ____cacheline_aligned; + +struct se_subsystem_dev { +/* Used for struct se_subsystem_dev-->se_dev_alias, must be less than PAGE_SIZE */ +#define SE_DEV_ALIAS_LEN 512 + unsigned char se_dev_alias[SE_DEV_ALIAS_LEN]; +/* Used for struct se_subsystem_dev->se_dev_udev_path[], must be less than PAGE_SIZE */ +#define SE_UDEV_PATH_LEN 512 + unsigned char se_dev_udev_path[SE_UDEV_PATH_LEN]; + u32 su_dev_flags; + struct se_hba *se_dev_hba; + struct se_device *se_dev_ptr; + struct se_dev_attrib se_dev_attrib; + /* T10 Asymmetric Logical Unit Assignment for Target Ports */ + struct t10_alua t10_alua; + /* T10 Inquiry and VPD WWN Information */ + struct t10_wwn t10_wwn; + /* T10 SPC-2 + SPC-3 Reservations */ + struct t10_reservation_template t10_reservation; + spinlock_t se_dev_lock; + void *se_dev_su_ptr; + struct list_head g_se_dev_list; + struct config_group se_dev_group; + /* For T10 Reservations */ + struct config_group se_dev_pr_group; +} ____cacheline_aligned; + +#define T10_ALUA(su_dev) (&(su_dev)->t10_alua) +#define T10_RES(su_dev) (&(su_dev)->t10_reservation) +#define T10_PR_OPS(su_dev) (&(su_dev)->t10_reservation.pr_ops) + +struct se_device { + /* Set to 1 if thread is NOT sleeping on thread_sem */ + u8 thread_active; + u8 dev_status_timer_flags; + /* RELATIVE TARGET PORT IDENTIFER Counter */ + u16 dev_rpti_counter; + /* Used for SAM Task Attribute ordering */ + u32 dev_cur_ordered_id; + u32 dev_flags; + u32 dev_port_count; + /* See transport_device_status_table */ + u32 dev_status; + u32 dev_tcq_window_closed; + /* Physical device queue depth */ + u32 queue_depth; + /* Used for SPC-2 reservations enforce of ISIDs */ + u64 dev_res_bin_isid; + t10_task_attr_index_t dev_task_attr_type; + /* Pointer to transport specific device structure */ + void *dev_ptr; + u32 dev_index; + u64 creation_time; + u32 num_resets; + u64 num_cmds; + u64 read_bytes; + u64 write_bytes; + spinlock_t stats_lock; + /* Active commands on this virtual SE device */ + atomic_t active_cmds; + atomic_t simple_cmds; + atomic_t depth_left; + atomic_t dev_ordered_id; + atomic_t dev_tur_active; + atomic_t execute_tasks; + atomic_t dev_status_thr_count; + atomic_t dev_hoq_count; + atomic_t dev_ordered_sync; + struct se_obj dev_obj; + struct se_obj dev_access_obj; + struct se_obj dev_export_obj; + struct se_queue_obj *dev_queue_obj; + struct se_queue_obj *dev_status_queue_obj; + spinlock_t delayed_cmd_lock; + spinlock_t ordered_cmd_lock; + spinlock_t execute_task_lock; + spinlock_t state_task_lock; + spinlock_t dev_alua_lock; + spinlock_t dev_reservation_lock; + spinlock_t dev_state_lock; + spinlock_t dev_status_lock; + spinlock_t dev_status_thr_lock; + spinlock_t se_port_lock; + spinlock_t se_tmr_lock; + /* Used for legacy SPC-2 reservationsa */ + struct se_node_acl *dev_reserved_node_acl; + /* Used for ALUA Logical Unit Group membership */ + struct t10_alua_lu_gp_member *dev_alua_lu_gp_mem; + /* Used for SPC-3 Persistent Reservations */ + struct t10_pr_registration *dev_pr_res_holder; + struct list_head dev_sep_list; + struct list_head dev_tmr_list; + struct timer_list dev_status_timer; + /* Pointer to descriptor for processing thread */ + struct task_struct *process_thread; + pid_t process_thread_pid; + struct task_struct *dev_mgmt_thread; + struct list_head delayed_cmd_list; + struct list_head ordered_cmd_list; + struct list_head execute_task_list; + struct list_head state_task_list; + /* Pointer to associated SE HBA */ + struct se_hba *se_hba; + struct se_subsystem_dev *se_sub_dev; + /* Pointer to template of function pointers for transport */ + struct se_subsystem_api *transport; + /* Linked list for struct se_hba struct se_device list */ + struct list_head dev_list; + /* Linked list for struct se_global->g_se_dev_list */ + struct list_head g_se_dev_list; +} ____cacheline_aligned; + +#define SE_DEV(cmd) ((struct se_device *)(cmd)->se_lun->lun_se_dev) +#define SU_DEV(dev) ((struct se_subsystem_dev *)(dev)->se_sub_dev) +#define DEV_ATTRIB(dev) (&(dev)->se_sub_dev->se_dev_attrib) +#define DEV_T10_WWN(dev) (&(dev)->se_sub_dev->t10_wwn) + +struct se_hba { + u16 hba_tpgt; + u32 hba_id; + /* See hba_flags_table */ + u32 hba_flags; + /* Virtual iSCSI devices attached. */ + u32 dev_count; + u32 hba_index; + atomic_t dev_mib_access_count; + atomic_t load_balance_queue; + atomic_t left_queue_depth; + /* Maximum queue depth the HBA can handle. */ + atomic_t max_queue_depth; + /* Pointer to transport specific host structure. */ + void *hba_ptr; + /* Linked list for struct se_device */ + struct list_head hba_dev_list; + struct list_head hba_list; + spinlock_t device_lock; + spinlock_t hba_queue_lock; + struct config_group hba_group; + struct mutex hba_access_mutex; + struct se_subsystem_api *transport; +} ____cacheline_aligned; + +#define SE_HBA(d) ((struct se_hba *)(d)->se_hba) + +struct se_lun { + /* See transport_lun_status_table */ + enum transport_lun_status_table lun_status; + u32 lun_access; + u32 lun_flags; + u32 unpacked_lun; + atomic_t lun_acl_count; + spinlock_t lun_acl_lock; + spinlock_t lun_cmd_lock; + spinlock_t lun_sep_lock; + struct completion lun_shutdown_comp; + struct list_head lun_cmd_list; + struct list_head lun_acl_list; + struct se_device *lun_se_dev; + struct config_group lun_group; + struct se_port *lun_sep; +} ____cacheline_aligned; + +#define SE_LUN(c) ((struct se_lun *)(c)->se_lun) + +struct se_port { + /* RELATIVE TARGET PORT IDENTIFER */ + u16 sep_rtpi; + int sep_tg_pt_secondary_stat; + int sep_tg_pt_secondary_write_md; + u32 sep_index; + struct scsi_port_stats sep_stats; + /* Used for ALUA Target Port Groups membership */ + atomic_t sep_tg_pt_gp_active; + atomic_t sep_tg_pt_secondary_offline; + /* Used for PR ALL_TG_PT=1 */ + atomic_t sep_tg_pt_ref_cnt; + spinlock_t sep_alua_lock; + struct mutex sep_tg_pt_md_mutex; + struct t10_alua_tg_pt_gp_member *sep_alua_tg_pt_gp_mem; + struct se_lun *sep_lun; + struct se_portal_group *sep_tpg; + struct list_head sep_alua_list; + struct list_head sep_list; +} ____cacheline_aligned; + +struct se_tpg_np { + struct config_group tpg_np_group; +} ____cacheline_aligned; + +struct se_portal_group { + /* Type of target portal group, see transport_tpg_type_table */ + enum transport_tpg_type_table se_tpg_type; + /* Number of ACLed Initiator Nodes for this TPG */ + u32 num_node_acls; + /* Used for PR SPEC_I_PT=1 and REGISTER_AND_MOVE */ + atomic_t tpg_pr_ref_count; + /* Spinlock for adding/removing ACLed Nodes */ + spinlock_t acl_node_lock; + /* Spinlock for adding/removing sessions */ + spinlock_t session_lock; + spinlock_t tpg_lun_lock; + /* Pointer to $FABRIC_MOD portal group */ + void *se_tpg_fabric_ptr; + struct list_head se_tpg_list; + /* linked list for initiator ACL list */ + struct list_head acl_node_list; + struct se_lun *tpg_lun_list; + struct se_lun tpg_virt_lun0; + /* List of TCM sessions assoicated wth this TPG */ + struct list_head tpg_sess_list; + /* Pointer to $FABRIC_MOD dependent code */ + struct target_core_fabric_ops *se_tpg_tfo; + struct se_wwn *se_tpg_wwn; + struct config_group tpg_group; + struct config_group *tpg_default_groups[6]; + struct config_group tpg_lun_group; + struct config_group tpg_np_group; + struct config_group tpg_acl_group; + struct config_group tpg_attrib_group; + struct config_group tpg_param_group; +} ____cacheline_aligned; + +#define TPG_TFO(se_tpg) ((struct target_core_fabric_ops *)(se_tpg)->se_tpg_tfo) + +struct se_wwn { + struct target_fabric_configfs *wwn_tf; + struct config_group wwn_group; +} ____cacheline_aligned; + +struct se_global { + u16 alua_lu_gps_counter; + int g_sub_api_initialized; + u32 in_shutdown; + u32 alua_lu_gps_count; + u32 g_hba_id_counter; + struct config_group target_core_hbagroup; + struct config_group alua_group; + struct config_group alua_lu_gps_group; + struct list_head g_lu_gps_list; + struct list_head g_se_tpg_list; + struct list_head g_hba_list; + struct list_head g_se_dev_list; + struct se_hba *g_lun0_hba; + struct se_subsystem_dev *g_lun0_su_dev; + struct se_device *g_lun0_dev; + struct t10_alua_lu_gp *default_lu_gp; + spinlock_t g_device_lock; + spinlock_t hba_lock; + spinlock_t se_tpg_lock; + spinlock_t lu_gps_lock; + spinlock_t plugin_class_lock; +} ____cacheline_aligned; + +#endif /* TARGET_CORE_BASE_H */ diff --git a/include/target/target_core_configfs.h b/include/target/target_core_configfs.h new file mode 100644 index 0000000..40e6e74 --- /dev/null +++ b/include/target/target_core_configfs.h @@ -0,0 +1,52 @@ +#define TARGET_CORE_CONFIGFS_VERSION TARGET_CORE_MOD_VERSION + +#define TARGET_CORE_CONFIG_ROOT "/sys/kernel/config" + +#define TARGET_CORE_NAME_MAX_LEN 64 +#define TARGET_FABRIC_NAME_SIZE 32 + +extern struct target_fabric_configfs *target_fabric_configfs_init( + struct module *, const char *); +extern void target_fabric_configfs_free(struct target_fabric_configfs *); +extern int target_fabric_configfs_register(struct target_fabric_configfs *); +extern void target_fabric_configfs_deregister(struct target_fabric_configfs *); + +struct target_fabric_configfs_template { + struct config_item_type tfc_discovery_cit; + struct config_item_type tfc_wwn_cit; + struct config_item_type tfc_tpg_cit; + struct config_item_type tfc_tpg_base_cit; + struct config_item_type tfc_tpg_lun_cit; + struct config_item_type tfc_tpg_port_cit; + struct config_item_type tfc_tpg_np_cit; + struct config_item_type tfc_tpg_np_base_cit; + struct config_item_type tfc_tpg_attrib_cit; + struct config_item_type tfc_tpg_param_cit; + struct config_item_type tfc_tpg_nacl_cit; + struct config_item_type tfc_tpg_nacl_base_cit; + struct config_item_type tfc_tpg_nacl_attrib_cit; + struct config_item_type tfc_tpg_nacl_auth_cit; + struct config_item_type tfc_tpg_nacl_param_cit; + struct config_item_type tfc_tpg_mappedlun_cit; +}; + +struct target_fabric_configfs { + char tf_name[TARGET_FABRIC_NAME_SIZE]; + atomic_t tf_access_cnt; + struct list_head tf_list; + struct config_group tf_group; + struct config_group tf_disc_group; + struct config_group *tf_default_groups[2]; + /* Pointer to fabric's config_item */ + struct config_item *tf_fabric; + /* Passed from fabric modules */ + struct config_item_type *tf_fabric_cit; + /* Pointer to target core subsystem */ + struct configfs_subsystem *tf_subsys; + /* Pointer to fabric's struct module */ + struct module *tf_module; + struct target_core_fabric_ops tf_ops; + struct target_fabric_configfs_template tf_cit_tmpl; +}; + +#define TF_CIT_TMPL(tf) (&(tf)->tf_cit_tmpl) diff --git a/include/target/target_core_device.h b/include/target/target_core_device.h new file mode 100644 index 0000000..52b18a5 --- /dev/null +++ b/include/target/target_core_device.h @@ -0,0 +1,61 @@ +#ifndef TARGET_CORE_DEVICE_H +#define TARGET_CORE_DEVICE_H + +extern int transport_get_lun_for_cmd(struct se_cmd *, unsigned char *, u32); +extern int transport_get_lun_for_tmr(struct se_cmd *, u32); +extern struct se_dev_entry *core_get_se_deve_from_rtpi( + struct se_node_acl *, u16); +extern int core_free_device_list_for_node(struct se_node_acl *, + struct se_portal_group *); +extern void core_dec_lacl_count(struct se_node_acl *, struct se_cmd *); +extern void core_update_device_list_access(u32, u32, struct se_node_acl *); +extern int core_update_device_list_for_node(struct se_lun *, struct se_lun_acl *, u32, + u32, struct se_node_acl *, + struct se_portal_group *, int); +extern void core_clear_lun_from_tpg(struct se_lun *, struct se_portal_group *); +extern int core_dev_export(struct se_device *, struct se_portal_group *, + struct se_lun *); +extern void core_dev_unexport(struct se_device *, struct se_portal_group *, + struct se_lun *); +extern int transport_core_report_lun_response(struct se_cmd *); +extern void se_release_device_for_hba(struct se_device *); +extern void se_release_vpd_for_dev(struct se_device *); +extern void se_clear_dev_ports(struct se_device *); +extern int se_free_virtual_device(struct se_device *, struct se_hba *); +extern int se_dev_check_online(struct se_device *); +extern int se_dev_check_shutdown(struct se_device *); +extern void se_dev_set_default_attribs(struct se_device *, struct se_dev_limits *); +extern int se_dev_set_task_timeout(struct se_device *, u32); +extern int se_dev_set_max_unmap_lba_count(struct se_device *, u32); +extern int se_dev_set_max_unmap_block_desc_count(struct se_device *, u32); +extern int se_dev_set_unmap_granularity(struct se_device *, u32); +extern int se_dev_set_unmap_granularity_alignment(struct se_device *, u32); +extern int se_dev_set_emulate_dpo(struct se_device *, int); +extern int se_dev_set_emulate_fua_write(struct se_device *, int); +extern int se_dev_set_emulate_fua_read(struct se_device *, int); +extern int se_dev_set_emulate_write_cache(struct se_device *, int); +extern int se_dev_set_emulate_ua_intlck_ctrl(struct se_device *, int); +extern int se_dev_set_emulate_tas(struct se_device *, int); +extern int se_dev_set_emulate_tpu(struct se_device *, int); +extern int se_dev_set_emulate_tpws(struct se_device *, int); +extern int se_dev_set_enforce_pr_isids(struct se_device *, int); +extern int se_dev_set_queue_depth(struct se_device *, u32); +extern int se_dev_set_max_sectors(struct se_device *, u32); +extern int se_dev_set_optimal_sectors(struct se_device *, u32); +extern int se_dev_set_block_size(struct se_device *, u32); +extern struct se_lun *core_dev_add_lun(struct se_portal_group *, struct se_hba *, + struct se_device *, u32); +extern int core_dev_del_lun(struct se_portal_group *, u32); +extern struct se_lun *core_get_lun_from_tpg(struct se_portal_group *, u32); +extern struct se_lun_acl *core_dev_init_initiator_node_lun_acl(struct se_portal_group *, + u32, char *, int *); +extern int core_dev_add_initiator_node_lun_acl(struct se_portal_group *, + struct se_lun_acl *, u32, u32); +extern int core_dev_del_initiator_node_lun_acl(struct se_portal_group *, + struct se_lun *, struct se_lun_acl *); +extern void core_dev_free_initiator_node_lun_acl(struct se_portal_group *, + struct se_lun_acl *lacl); +extern int core_dev_setup_virtual_lun0(void); +extern void core_dev_release_virtual_lun0(void); + +#endif /* TARGET_CORE_DEVICE_H */ diff --git a/include/target/target_core_fabric_configfs.h b/include/target/target_core_fabric_configfs.h new file mode 100644 index 0000000..a26fb75 --- /dev/null +++ b/include/target/target_core_fabric_configfs.h @@ -0,0 +1,106 @@ +/* + * Used for tfc_wwn_cit attributes + */ + +#include + +CONFIGFS_EATTR_STRUCT(target_fabric_nacl_attrib, se_node_acl); +#define TF_NACL_ATTRIB_ATTR(_fabric, _name, _mode) \ +static struct target_fabric_nacl_attrib_attribute _fabric##_nacl_attrib_##_name = \ + __CONFIGFS_EATTR(_name, _mode, \ + _fabric##_nacl_attrib_show_##_name, \ + _fabric##_nacl_attrib_store_##_name); + +CONFIGFS_EATTR_STRUCT(target_fabric_nacl_auth, se_node_acl); +#define TF_NACL_AUTH_ATTR(_fabric, _name, _mode) \ +static struct target_fabric_nacl_auth_attribute _fabric##_nacl_auth_##_name = \ + __CONFIGFS_EATTR(_name, _mode, \ + _fabric##_nacl_auth_show_##_name, \ + _fabric##_nacl_auth_store_##_name); + +#define TF_NACL_AUTH_ATTR_RO(_fabric, _name) \ +static struct target_fabric_nacl_auth_attribute _fabric##_nacl_auth_##_name = \ + __CONFIGFS_EATTR_RO(_name, \ + _fabric##_nacl_auth_show_##_name); + +CONFIGFS_EATTR_STRUCT(target_fabric_nacl_param, se_node_acl); +#define TF_NACL_PARAM_ATTR(_fabric, _name, _mode) \ +static struct target_fabric_nacl_param_attribute _fabric##_nacl_param_##_name = \ + __CONFIGFS_EATTR(_name, _mode, \ + _fabric##_nacl_param_show_##_name, \ + _fabric##_nacl_param_store_##_name); + +#define TF_NACL_PARAM_ATTR_RO(_fabric, _name) \ +static struct target_fabric_nacl_param_attribute _fabric##_nacl_param_##_name = \ + __CONFIGFS_EATTR_RO(_name, \ + _fabric##_nacl_param_show_##_name); + + +CONFIGFS_EATTR_STRUCT(target_fabric_nacl_base, se_node_acl); +#define TF_NACL_BASE_ATTR(_fabric, _name, _mode) \ +static struct target_fabric_nacl_base_attribute _fabric##_nacl_##_name = \ + __CONFIGFS_EATTR(_name, _mode, \ + _fabric##_nacl_show_##_name, \ + _fabric##_nacl_store_##_name); + +#define TF_NACL_BASE_ATTR_RO(_fabric, _name) \ +static struct target_fabric_nacl_base_attribute _fabric##_nacl_##_name = \ + __CONFIGFS_EATTR_RO(_name, \ + _fabric##_nacl_show_##_name); + +CONFIGFS_EATTR_STRUCT(target_fabric_np_base, se_tpg_np); +#define TF_NP_BASE_ATTR(_fabric, _name, _mode) \ +static struct target_fabric_np_base_attribute _fabric##_np_##_name = \ + __CONFIGFS_EATTR(_name, _mode, \ + _fabric##_np_show_##_name, \ + _fabric##_np_store_##_name); + +CONFIGFS_EATTR_STRUCT(target_fabric_tpg_attrib, se_portal_group); +#define TF_TPG_ATTRIB_ATTR(_fabric, _name, _mode) \ +static struct target_fabric_tpg_attrib_attribute _fabric##_tpg_attrib_##_name = \ + __CONFIGFS_EATTR(_name, _mode, \ + _fabric##_tpg_attrib_show_##_name, \ + _fabric##_tpg_attrib_store_##_name); + + +CONFIGFS_EATTR_STRUCT(target_fabric_tpg_param, se_portal_group); +#define TF_TPG_PARAM_ATTR(_fabric, _name, _mode) \ +static struct target_fabric_tpg_param_attribute _fabric##_tpg_param_##_name = \ + __CONFIGFS_EATTR(_name, _mode, \ + _fabric##_tpg_param_show_##_name, \ + _fabric##_tpg_param_store_##_name); + + +CONFIGFS_EATTR_STRUCT(target_fabric_tpg, se_portal_group); +#define TF_TPG_BASE_ATTR(_fabric, _name, _mode) \ +static struct target_fabric_tpg_attribute _fabric##_tpg_##_name = \ + __CONFIGFS_EATTR(_name, _mode, \ + _fabric##_tpg_show_##_name, \ + _fabric##_tpg_store_##_name); + + +CONFIGFS_EATTR_STRUCT(target_fabric_wwn, target_fabric_configfs); +#define TF_WWN_ATTR(_fabric, _name, _mode) \ +static struct target_fabric_wwn_attribute _fabric##_wwn_##_name = \ + __CONFIGFS_EATTR(_name, _mode, \ + _fabric##_wwn_show_attr_##_name, \ + _fabric##_wwn_store_attr_##_name); + +#define TF_WWN_ATTR_RO(_fabric, _name) \ +static struct target_fabric_wwn_attribute _fabric##_wwn_##_name = \ + __CONFIGFS_EATTR_RO(_name, \ + _fabric##_wwn_show_attr_##_name); + +CONFIGFS_EATTR_STRUCT(target_fabric_discovery, target_fabric_configfs); +#define TF_DISC_ATTR(_fabric, _name, _mode) \ +static struct target_fabric_discovery_attribute _fabric##_disc_##_name = \ + __CONFIGFS_EATTR(_name, _mode, \ + _fabric##_disc_show_##_name, \ + _fabric##_disc_store_##_name); + +#define TF_DISC_ATTR_RO(_fabric, _name) \ +static struct target_fabric_discovery_attribute _fabric##_disc_##_name = \ + __CONFIGFS_EATTR_RO(_name, \ + _fabric##_disc_show_##_name); + +extern int target_fabric_setup_cits(struct target_fabric_configfs *); diff --git a/include/target/target_core_fabric_lib.h b/include/target/target_core_fabric_lib.h new file mode 100644 index 0000000..c2f8d0e --- /dev/null +++ b/include/target/target_core_fabric_lib.h @@ -0,0 +1,28 @@ +#ifndef TARGET_CORE_FABRIC_LIB_H +#define TARGET_CORE_FABRIC_LIB_H + +extern u8 sas_get_fabric_proto_ident(struct se_portal_group *); +extern u32 sas_get_pr_transport_id(struct se_portal_group *, struct se_node_acl *, + struct t10_pr_registration *, int *, unsigned char *); +extern u32 sas_get_pr_transport_id_len(struct se_portal_group *, struct se_node_acl *, + struct t10_pr_registration *, int *); +extern char *sas_parse_pr_out_transport_id(struct se_portal_group *, + const char *, u32 *, char **); + +extern u8 fc_get_fabric_proto_ident(struct se_portal_group *); +extern u32 fc_get_pr_transport_id(struct se_portal_group *, struct se_node_acl *, + struct t10_pr_registration *, int *, unsigned char *); +extern u32 fc_get_pr_transport_id_len(struct se_portal_group *, struct se_node_acl *, + struct t10_pr_registration *, int *); +extern char *fc_parse_pr_out_transport_id(struct se_portal_group *, + const char *, u32 *, char **); + +extern u8 iscsi_get_fabric_proto_ident(struct se_portal_group *); +extern u32 iscsi_get_pr_transport_id(struct se_portal_group *, struct se_node_acl *, + struct t10_pr_registration *, int *, unsigned char *); +extern u32 iscsi_get_pr_transport_id_len(struct se_portal_group *, struct se_node_acl *, + struct t10_pr_registration *, int *); +extern char *iscsi_parse_pr_out_transport_id(struct se_portal_group *, + const char *, u32 *, char **); + +#endif /* TARGET_CORE_FABRIC_LIB_H */ diff --git a/include/target/target_core_fabric_ops.h b/include/target/target_core_fabric_ops.h new file mode 100644 index 0000000..f3ac12b --- /dev/null +++ b/include/target/target_core_fabric_ops.h @@ -0,0 +1,100 @@ +/* Defined in target_core_configfs.h */ +struct target_fabric_configfs; + +struct target_core_fabric_ops { + struct configfs_subsystem *tf_subsys; + /* + * Optional to signal struct se_task->task_sg[] padding entries + * for scatterlist chaining using transport_do_task_sg_link(), + * disabled by default + */ + int task_sg_chaining:1; + char *(*get_fabric_name)(void); + u8 (*get_fabric_proto_ident)(struct se_portal_group *); + char *(*tpg_get_wwn)(struct se_portal_group *); + u16 (*tpg_get_tag)(struct se_portal_group *); + u32 (*tpg_get_default_depth)(struct se_portal_group *); + u32 (*tpg_get_pr_transport_id)(struct se_portal_group *, + struct se_node_acl *, + struct t10_pr_registration *, int *, + unsigned char *); + u32 (*tpg_get_pr_transport_id_len)(struct se_portal_group *, + struct se_node_acl *, + struct t10_pr_registration *, int *); + char *(*tpg_parse_pr_out_transport_id)(struct se_portal_group *, + const char *, u32 *, char **); + int (*tpg_check_demo_mode)(struct se_portal_group *); + int (*tpg_check_demo_mode_cache)(struct se_portal_group *); + int (*tpg_check_demo_mode_write_protect)(struct se_portal_group *); + int (*tpg_check_prod_mode_write_protect)(struct se_portal_group *); + struct se_node_acl *(*tpg_alloc_fabric_acl)( + struct se_portal_group *); + void (*tpg_release_fabric_acl)(struct se_portal_group *, + struct se_node_acl *); + u32 (*tpg_get_inst_index)(struct se_portal_group *); + /* + * Optional function pointer for TCM to perform command map + * from TCM processing thread context, for those struct se_cmd + * initally allocated in interrupt context. + */ + int (*new_cmd_map)(struct se_cmd *); + /* + * Optional function pointer for TCM fabric modules that use + * Linux/NET sockets to allocate struct iovec array to struct se_cmd + */ + int (*alloc_cmd_iovecs)(struct se_cmd *); + /* + * Optional to release struct se_cmd and fabric dependent allocated + * I/O descriptor in transport_cmd_check_stop() + */ + void (*check_stop_free)(struct se_cmd *); + void (*release_cmd_to_pool)(struct se_cmd *); + void (*release_cmd_direct)(struct se_cmd *); + /* + * Called with spin_lock_bh(struct se_portal_group->session_lock held. + */ + int (*shutdown_session)(struct se_session *); + void (*close_session)(struct se_session *); + void (*stop_session)(struct se_session *, int, int); + void (*fall_back_to_erl0)(struct se_session *); + int (*sess_logged_in)(struct se_session *); + u32 (*sess_get_index)(struct se_session *); + /* + * Used only for SCSI fabrics that contain multi-value TransportIDs + * (like iSCSI). All other SCSI fabrics should set this to NULL. + */ + u32 (*sess_get_initiator_sid)(struct se_session *, + unsigned char *, u32); + int (*write_pending)(struct se_cmd *); + int (*write_pending_status)(struct se_cmd *); + void (*set_default_node_attributes)(struct se_node_acl *); + u32 (*get_task_tag)(struct se_cmd *); + int (*get_cmd_state)(struct se_cmd *); + void (*new_cmd_failure)(struct se_cmd *); + int (*queue_data_in)(struct se_cmd *); + int (*queue_status)(struct se_cmd *); + int (*queue_tm_rsp)(struct se_cmd *); + u16 (*set_fabric_sense_len)(struct se_cmd *, u32); + u16 (*get_fabric_sense_len)(void); + int (*is_state_remove)(struct se_cmd *); + u64 (*pack_lun)(unsigned int); + /* + * fabric module calls for target_core_fabric_configfs.c + */ + struct se_wwn *(*fabric_make_wwn)(struct target_fabric_configfs *, + struct config_group *, const char *); + void (*fabric_drop_wwn)(struct se_wwn *); + struct se_portal_group *(*fabric_make_tpg)(struct se_wwn *, + struct config_group *, const char *); + void (*fabric_drop_tpg)(struct se_portal_group *); + int (*fabric_post_link)(struct se_portal_group *, + struct se_lun *); + void (*fabric_pre_unlink)(struct se_portal_group *, + struct se_lun *); + struct se_tpg_np *(*fabric_make_np)(struct se_portal_group *, + struct config_group *, const char *); + void (*fabric_drop_np)(struct se_tpg_np *); + struct se_node_acl *(*fabric_make_nodeacl)(struct se_portal_group *, + struct config_group *, const char *); + void (*fabric_drop_nodeacl)(struct se_node_acl *); +}; diff --git a/include/target/target_core_tmr.h b/include/target/target_core_tmr.h new file mode 100644 index 0000000..6c8248b --- /dev/null +++ b/include/target/target_core_tmr.h @@ -0,0 +1,43 @@ +#ifndef TARGET_CORE_TMR_H +#define TARGET_CORE_TMR_H + +/* task management function values */ +#ifdef ABORT_TASK +#undef ABORT_TASK +#endif /* ABORT_TASK */ +#define ABORT_TASK 1 +#ifdef ABORT_TASK_SET +#undef ABORT_TASK_SET +#endif /* ABORT_TASK_SET */ +#define ABORT_TASK_SET 2 +#ifdef CLEAR_ACA +#undef CLEAR_ACA +#endif /* CLEAR_ACA */ +#define CLEAR_ACA 3 +#ifdef CLEAR_TASK_SET +#undef CLEAR_TASK_SET +#endif /* CLEAR_TASK_SET */ +#define CLEAR_TASK_SET 4 +#define LUN_RESET 5 +#define TARGET_WARM_RESET 6 +#define TARGET_COLD_RESET 7 +#define TASK_REASSIGN 8 + +/* task management response values */ +#define TMR_FUNCTION_COMPLETE 0 +#define TMR_TASK_DOES_NOT_EXIST 1 +#define TMR_LUN_DOES_NOT_EXIST 2 +#define TMR_TASK_STILL_ALLEGIANT 3 +#define TMR_TASK_FAILOVER_NOT_SUPPORTED 4 +#define TMR_TASK_MGMT_FUNCTION_NOT_SUPPORTED 5 +#define TMR_FUNCTION_AUTHORIZATION_FAILED 6 +#define TMR_FUNCTION_REJECTED 255 + +extern struct kmem_cache *se_tmr_req_cache; + +extern struct se_tmr_req *core_tmr_alloc_req(struct se_cmd *, void *, u8); +extern void core_tmr_release_req(struct se_tmr_req *); +extern int core_tmr_lun_reset(struct se_device *, struct se_tmr_req *, + struct list_head *, struct se_cmd *); + +#endif /* TARGET_CORE_TMR_H */ diff --git a/include/target/target_core_tpg.h b/include/target/target_core_tpg.h new file mode 100644 index 0000000..77e18729 --- /dev/null +++ b/include/target/target_core_tpg.h @@ -0,0 +1,35 @@ +#ifndef TARGET_CORE_TPG_H +#define TARGET_CORE_TPG_H + +extern struct se_node_acl *__core_tpg_get_initiator_node_acl(struct se_portal_group *tpg, + const char *); +extern struct se_node_acl *core_tpg_get_initiator_node_acl(struct se_portal_group *tpg, + unsigned char *); +extern void core_tpg_add_node_to_devs(struct se_node_acl *, + struct se_portal_group *); +extern struct se_node_acl *core_tpg_check_initiator_node_acl( + struct se_portal_group *, + unsigned char *); +extern void core_tpg_wait_for_nacl_pr_ref(struct se_node_acl *); +extern void core_tpg_wait_for_mib_ref(struct se_node_acl *); +extern void core_tpg_clear_object_luns(struct se_portal_group *); +extern struct se_node_acl *core_tpg_add_initiator_node_acl( + struct se_portal_group *, + struct se_node_acl *, + const char *, u32); +extern int core_tpg_del_initiator_node_acl(struct se_portal_group *, + struct se_node_acl *, int); +extern int core_tpg_set_initiator_node_queue_depth(struct se_portal_group *, + unsigned char *, u32, int); +extern int core_tpg_register(struct target_core_fabric_ops *, + struct se_wwn *, + struct se_portal_group *, void *, + int); +extern int core_tpg_deregister(struct se_portal_group *); +extern struct se_lun *core_tpg_pre_addlun(struct se_portal_group *, u32); +extern int core_tpg_post_addlun(struct se_portal_group *, struct se_lun *, u32, + void *); +extern struct se_lun *core_tpg_pre_dellun(struct se_portal_group *, u32, int *); +extern int core_tpg_post_dellun(struct se_portal_group *, struct se_lun *); + +#endif /* TARGET_CORE_TPG_H */ diff --git a/include/target/target_core_transport.h b/include/target/target_core_transport.h new file mode 100644 index 0000000..66f44e5 --- /dev/null +++ b/include/target/target_core_transport.h @@ -0,0 +1,351 @@ +#ifndef TARGET_CORE_TRANSPORT_H +#define TARGET_CORE_TRANSPORT_H + +#define TARGET_CORE_VERSION TARGET_CORE_MOD_VERSION + +/* Attempts before moving from SHORT to LONG */ +#define PYX_TRANSPORT_WINDOW_CLOSED_THRESHOLD 3 +#define PYX_TRANSPORT_WINDOW_CLOSED_WAIT_SHORT 3 /* In milliseconds */ +#define PYX_TRANSPORT_WINDOW_CLOSED_WAIT_LONG 10 /* In milliseconds */ + +#define PYX_TRANSPORT_STATUS_INTERVAL 5 /* In seconds */ + +#define PYX_TRANSPORT_SENT_TO_TRANSPORT 0 +#define PYX_TRANSPORT_WRITE_PENDING 1 + +#define PYX_TRANSPORT_UNKNOWN_SAM_OPCODE -1 +#define PYX_TRANSPORT_HBA_QUEUE_FULL -2 +#define PYX_TRANSPORT_REQ_TOO_MANY_SECTORS -3 +#define PYX_TRANSPORT_OUT_OF_MEMORY_RESOURCES -4 +#define PYX_TRANSPORT_INVALID_CDB_FIELD -5 +#define PYX_TRANSPORT_INVALID_PARAMETER_LIST -6 +#define PYX_TRANSPORT_LU_COMM_FAILURE -7 +#define PYX_TRANSPORT_UNKNOWN_MODE_PAGE -8 +#define PYX_TRANSPORT_WRITE_PROTECTED -9 +#define PYX_TRANSPORT_TASK_TIMEOUT -10 +#define PYX_TRANSPORT_RESERVATION_CONFLICT -11 +#define PYX_TRANSPORT_ILLEGAL_REQUEST -12 +#define PYX_TRANSPORT_USE_SENSE_REASON -13 + +#ifndef SAM_STAT_RESERVATION_CONFLICT +#define SAM_STAT_RESERVATION_CONFLICT 0x18 +#endif + +#define TRANSPORT_PLUGIN_FREE 0 +#define TRANSPORT_PLUGIN_REGISTERED 1 + +#define TRANSPORT_PLUGIN_PHBA_PDEV 1 +#define TRANSPORT_PLUGIN_VHBA_PDEV 2 +#define TRANSPORT_PLUGIN_VHBA_VDEV 3 + +/* For SE OBJ Plugins, in seconds */ +#define TRANSPORT_TIMEOUT_TUR 10 +#define TRANSPORT_TIMEOUT_TYPE_DISK 60 +#define TRANSPORT_TIMEOUT_TYPE_ROM 120 +#define TRANSPORT_TIMEOUT_TYPE_TAPE 600 +#define TRANSPORT_TIMEOUT_TYPE_OTHER 300 + +/* For se_task->task_state_flags */ +#define TSF_EXCEPTION_CLEARED 0x01 + +/* + * struct se_subsystem_dev->su_dev_flags +*/ +#define SDF_FIRMWARE_VPD_UNIT_SERIAL 0x00000001 +#define SDF_EMULATED_VPD_UNIT_SERIAL 0x00000002 +#define SDF_USING_UDEV_PATH 0x00000004 +#define SDF_USING_ALIAS 0x00000008 + +/* + * struct se_device->dev_flags + */ +#define DF_READ_ONLY 0x00000001 +#define DF_SPC2_RESERVATIONS 0x00000002 +#define DF_SPC2_RESERVATIONS_WITH_ISID 0x00000004 + +/* struct se_dev_attrib sanity values */ +/* 10 Minutes */ +#define DA_TASK_TIMEOUT_MAX 600 +/* Default max_unmap_lba_count */ +#define DA_MAX_UNMAP_LBA_COUNT 0 +/* Default max_unmap_block_desc_count */ +#define DA_MAX_UNMAP_BLOCK_DESC_COUNT 0 +/* Default unmap_granularity */ +#define DA_UNMAP_GRANULARITY_DEFAULT 0 +/* Default unmap_granularity_alignment */ +#define DA_UNMAP_GRANULARITY_ALIGNMENT_DEFAULT 0 +/* Emulation for Direct Page Out */ +#define DA_EMULATE_DPO 0 +/* Emulation for Forced Unit Access WRITEs */ +#define DA_EMULATE_FUA_WRITE 1 +/* Emulation for Forced Unit Access READs */ +#define DA_EMULATE_FUA_READ 0 +/* Emulation for WriteCache and SYNCHRONIZE_CACHE */ +#define DA_EMULATE_WRITE_CACHE 0 +/* Emulation for UNIT ATTENTION Interlock Control */ +#define DA_EMULATE_UA_INTLLCK_CTRL 0 +/* Emulation for TASK_ABORTED status (TAS) by default */ +#define DA_EMULATE_TAS 1 +/* Emulation for Thin Provisioning UNMAP using block/blk-lib.c:blkdev_issue_discard() */ +#define DA_EMULATE_TPU 0 +/* + * Emulation for Thin Provisioning WRITE_SAME w/ UNMAP=1 bit using + * block/blk-lib.c:blkdev_issue_discard() + */ +#define DA_EMULATE_TPWS 0 +/* No Emulation for PSCSI by default */ +#define DA_EMULATE_RESERVATIONS 0 +/* No Emulation for PSCSI by default */ +#define DA_EMULATE_ALUA 0 +/* Enforce SCSI Initiator Port TransportID with 'ISID' for PR */ +#define DA_ENFORCE_PR_ISIDS 1 +#define DA_STATUS_MAX_SECTORS_MIN 16 +#define DA_STATUS_MAX_SECTORS_MAX 8192 + +#define SE_MODE_PAGE_BUF 512 + +#define MOD_MAX_SECTORS(ms, bs) (ms % (PAGE_SIZE / bs)) + +struct se_mem; +struct se_subsystem_api; + +extern int init_se_global(void); +extern void release_se_global(void); +extern void transport_init_queue_obj(struct se_queue_obj *); +extern int transport_subsystem_check_init(void); +extern int transport_subsystem_register(struct se_subsystem_api *); +extern void transport_subsystem_release(struct se_subsystem_api *); +extern void transport_load_plugins(void); +extern struct se_session *transport_init_session(void); +extern void __transport_register_session(struct se_portal_group *, + struct se_node_acl *, + struct se_session *, void *); +extern void transport_register_session(struct se_portal_group *, + struct se_node_acl *, + struct se_session *, void *); +extern void transport_free_session(struct se_session *); +extern void transport_deregister_session_configfs(struct se_session *); +extern void transport_deregister_session(struct se_session *); +extern void transport_cmd_finish_abort(struct se_cmd *, int); +extern void transport_cmd_finish_abort_tmr(struct se_cmd *); +extern void transport_complete_sync_cache(struct se_cmd *, int); +extern void transport_complete_task(struct se_task *, int); +extern void transport_add_task_to_execute_queue(struct se_task *, + struct se_task *, + struct se_device *); +unsigned char *transport_dump_cmd_direction(struct se_cmd *); +extern void transport_dump_dev_state(struct se_device *, char *, int *); +extern void transport_dump_dev_info(struct se_device *, struct se_lun *, + unsigned long long, char *, int *); +extern void transport_dump_vpd_proto_id(struct t10_vpd *, + unsigned char *, int); +extern void transport_set_vpd_proto_id(struct t10_vpd *, unsigned char *); +extern int transport_dump_vpd_assoc(struct t10_vpd *, + unsigned char *, int); +extern int transport_set_vpd_assoc(struct t10_vpd *, unsigned char *); +extern int transport_dump_vpd_ident_type(struct t10_vpd *, + unsigned char *, int); +extern int transport_set_vpd_ident_type(struct t10_vpd *, unsigned char *); +extern int transport_dump_vpd_ident(struct t10_vpd *, + unsigned char *, int); +extern int transport_set_vpd_ident(struct t10_vpd *, unsigned char *); +extern struct se_device *transport_add_device_to_core_hba(struct se_hba *, + struct se_subsystem_api *, + struct se_subsystem_dev *, u32, + void *, struct se_dev_limits *, + const char *, const char *); +extern void transport_device_setup_cmd(struct se_cmd *); +extern void transport_init_se_cmd(struct se_cmd *, + struct target_core_fabric_ops *, + struct se_session *, u32, int, int, + unsigned char *); +extern void transport_free_se_cmd(struct se_cmd *); +extern int transport_generic_allocate_tasks(struct se_cmd *, unsigned char *); +extern int transport_generic_handle_cdb(struct se_cmd *); +extern int transport_generic_handle_cdb_map(struct se_cmd *); +extern int transport_generic_handle_data(struct se_cmd *); +extern void transport_new_cmd_failure(struct se_cmd *); +extern int transport_generic_handle_tmr(struct se_cmd *); +extern void __transport_stop_task_timer(struct se_task *, unsigned long *); +extern unsigned char transport_asciihex_to_binaryhex(unsigned char val[2]); +extern int transport_generic_map_mem_to_cmd(struct se_cmd *cmd, struct scatterlist *, u32, + struct scatterlist *, u32); +extern int transport_clear_lun_from_sessions(struct se_lun *); +extern int transport_check_aborted_status(struct se_cmd *, int); +extern int transport_send_check_condition_and_sense(struct se_cmd *, u8, int); +extern void transport_send_task_abort(struct se_cmd *); +extern void transport_release_cmd_to_pool(struct se_cmd *); +extern void transport_generic_free_cmd(struct se_cmd *, int, int, int); +extern void transport_generic_wait_for_cmds(struct se_cmd *, int); +extern u32 transport_calc_sg_num(struct se_task *, struct se_mem *, u32); +extern int transport_map_mem_to_sg(struct se_task *, struct list_head *, + void *, struct se_mem *, + struct se_mem **, u32 *, u32 *); +extern void transport_do_task_sg_chain(struct se_cmd *); +extern void transport_generic_process_write(struct se_cmd *); +extern int transport_generic_do_tmr(struct se_cmd *); +/* From target_core_alua.c */ +extern int core_alua_check_nonop_delay(struct se_cmd *); + +/* + * Each se_transport_task_t can have N number of possible struct se_task's + * for the storage transport(s) to possibly execute. + * Used primarily for splitting up CDBs that exceed the physical storage + * HBA's maximum sector count per task. + */ +struct se_mem { + struct page *se_page; + u32 se_len; + u32 se_off; + struct list_head se_list; +} ____cacheline_aligned; + +/* + * Each type of disk transport supported MUST have a template defined + * within its .h file. + */ +struct se_subsystem_api { + /* + * The Name. :-) + */ + char name[16]; + /* + * Transport Type. + */ + u8 transport_type; + /* + * struct module for struct se_hba references + */ + struct module *owner; + /* + * Used for global se_subsystem_api list_head + */ + struct list_head sub_api_list; + /* + * For SCF_SCSI_NON_DATA_CDB + */ + int (*cdb_none)(struct se_task *); + /* + * For SCF_SCSI_CONTROL_NONSG_IO_CDB + */ + int (*map_task_non_SG)(struct se_task *); + /* + * For SCF_SCSI_DATA_SG_IO_CDB and SCF_SCSI_CONTROL_SG_IO_CDB + */ + int (*map_task_SG)(struct se_task *); + /* + * attach_hba(): + */ + int (*attach_hba)(struct se_hba *, u32); + /* + * detach_hba(): + */ + void (*detach_hba)(struct se_hba *); + /* + * pmode_hba(): Used for TCM/pSCSI subsystem plugin HBA -> + * Linux/SCSI struct Scsi_Host passthrough + */ + int (*pmode_enable_hba)(struct se_hba *, unsigned long); + /* + * allocate_virtdevice(): + */ + void *(*allocate_virtdevice)(struct se_hba *, const char *); + /* + * create_virtdevice(): Only for Virtual HBAs + */ + struct se_device *(*create_virtdevice)(struct se_hba *, + struct se_subsystem_dev *, void *); + /* + * free_device(): + */ + void (*free_device)(void *); + + /* + * dpo_emulated(): + */ + int (*dpo_emulated)(struct se_device *); + /* + * fua_write_emulated(): + */ + int (*fua_write_emulated)(struct se_device *); + /* + * fua_read_emulated(): + */ + int (*fua_read_emulated)(struct se_device *); + /* + * write_cache_emulated(): + */ + int (*write_cache_emulated)(struct se_device *); + /* + * transport_complete(): + * + * Use transport_generic_complete() for majority of DAS transport + * drivers. Provided out of convenience. + */ + int (*transport_complete)(struct se_task *task); + struct se_task *(*alloc_task)(struct se_cmd *); + /* + * do_task(): + */ + int (*do_task)(struct se_task *); + /* + * Used by virtual subsystem plugins IBLOCK and FILEIO to emulate + * UNMAP and WRITE_SAME_* w/ UNMAP=1 <-> Linux/Block Discard + */ + int (*do_discard)(struct se_device *, sector_t, u32); + /* + * Used by virtual subsystem plugins IBLOCK and FILEIO to emulate + * SYNCHRONIZE_CACHE_* <-> Linux/Block blkdev_issue_flush() + */ + void (*do_sync_cache)(struct se_task *); + /* + * free_task(): + */ + void (*free_task)(struct se_task *); + /* + * check_configfs_dev_params(): + */ + ssize_t (*check_configfs_dev_params)(struct se_hba *, struct se_subsystem_dev *); + /* + * set_configfs_dev_params(): + */ + ssize_t (*set_configfs_dev_params)(struct se_hba *, struct se_subsystem_dev *, + const char *, ssize_t); + /* + * show_configfs_dev_params(): + */ + ssize_t (*show_configfs_dev_params)(struct se_hba *, struct se_subsystem_dev *, + char *); + /* + * get_cdb(): + */ + unsigned char *(*get_cdb)(struct se_task *); + /* + * get_device_rev(): + */ + u32 (*get_device_rev)(struct se_device *); + /* + * get_device_type(): + */ + u32 (*get_device_type)(struct se_device *); + /* + * Get the sector_t from a subsystem backstore.. + */ + sector_t (*get_blocks)(struct se_device *); + /* + * do_se_mem_map(): + */ + int (*do_se_mem_map)(struct se_task *, struct list_head *, void *, + struct se_mem *, struct se_mem **, u32 *, u32 *); + /* + * get_sense_buffer(): + */ + unsigned char *(*get_sense_buffer)(struct se_task *); +} ____cacheline_aligned; + +#define TRANSPORT(dev) ((dev)->transport) +#define HBA_TRANSPORT(hba) ((hba)->transport) + +extern struct se_global *se_global; + +#endif /* TARGET_CORE_TRANSPORT_H */ -- cgit v1.1 From c94fbe1d9e1e9b1a1f82eb0b53b1cf53bcf9712b Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 14 Jan 2011 11:25:58 -0500 Subject: tracing: Only process module tracepoints once The commit: 9f987b3141f086de27832514aad9f50a53f754 tracing: Include module.h in define_trace.h only solved half the problem. If the trace/events/module.h header is included at the time of define_trace.h (or in ftrace.h within it), the module.h TRACE_SYSTEM will override the current TRACE_SYSTEM macro. Since define_trace.h is included when CREATE_TRACE_POINTS is set, and the first thing it does is to #undef CREATE_TRACE_POINTS, by placing the module.h TRACE_SYSTEM inside a #ifdef CREATE_TRACE_POINTS we can prevent it from overriding the TRACE_SYSTEM that is being processed, and still process the module.h tracepoints when the module code defines CREATE_TRACE_POINTS and includes the trace/events/module.h header. As with commit 9f987b3141, this is only an issue if module.h is not included before the trace/events/.h file is included, which (luckily) has not happened yet. Reported-by: Peter Zijlstra Signed-off-by: Steven Rostedt --- include/trace/events/module.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/trace/events/module.h b/include/trace/events/module.h index c7bb2f0..c6bae36 100644 --- a/include/trace/events/module.h +++ b/include/trace/events/module.h @@ -1,5 +1,15 @@ +/* + * Because linux/module.h has tracepoints in the header, and ftrace.h + * eventually includes this file, define_trace.h includes linux/module.h + * But we do not want the module.h to override the TRACE_SYSTEM macro + * variable that define_trace.h is processing, so we only set it + * when module events are being processed, which would happen when + * CREATE_TRACE_POINTS is defined. + */ +#ifdef CREATE_TRACE_POINTS #undef TRACE_SYSTEM #define TRACE_SYSTEM module +#endif #if !defined(_TRACE_MODULE_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_MODULE_H -- cgit v1.1 From 415e12b2379239973feab91850b0dce985c6058a Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 7 Jan 2011 00:55:09 +0100 Subject: PCI/ACPI: Request _OSC control once for each root bridge (v3) Move the evaluation of acpi_pci_osc_control_set() (to request control of PCI Express native features) into acpi_pci_root_add() to avoid calling it many times for the same root complex with the same arguments. Additionally, check if all of the requisite _OSC support bits are set before calling acpi_pci_osc_control_set() for a given root complex. References: https://bugzilla.kernel.org/show_bug.cgi?id=20232 Reported-by: Ozan Caglayan Tested-by: Ozan Caglayan Signed-off-by: Rafael J. Wysocki Signed-off-by: Jesse Barnes --- include/acpi/apei.h | 6 ++++++ include/linux/pci-acpi.h | 6 ++++++ include/linux/pci.h | 11 +++++++++++ 3 files changed, 23 insertions(+) (limited to 'include') diff --git a/include/acpi/apei.h b/include/acpi/apei.h index b336502..c4dbb13 100644 --- a/include/acpi/apei.h +++ b/include/acpi/apei.h @@ -19,6 +19,12 @@ extern int hest_disable; extern int erst_disable; +#ifdef CONFIG_ACPI_APEI +void __init acpi_hest_init(void); +#else +static inline void acpi_hest_init(void) { return; } +#endif + typedef int (*apei_hest_func_t)(struct acpi_hest_header *hest_hdr, void *data); int apei_hest_parse(apei_hest_func_t func, void *data); diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index c8b6473..479d9bb 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -40,4 +40,10 @@ static inline acpi_handle acpi_find_root_bridge_handle(struct pci_dev *pdev) { return NULL; } #endif +#ifdef CONFIG_ACPI_APEI +extern bool aer_acpi_firmware_first(void); +#else +static inline bool aer_acpi_firmware_first(void) { return false; } +#endif + #endif /* _PCI_ACPI_H_ */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 63cbadc..12dd86a 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -994,6 +994,9 @@ extern void pci_restore_msi_state(struct pci_dev *dev); extern int pci_msi_enabled(void); #endif +extern bool pcie_ports_disabled; +extern bool pcie_ports_auto; + #ifndef CONFIG_PCIEASPM static inline int pcie_aspm_enabled(void) { @@ -1003,6 +1006,14 @@ static inline int pcie_aspm_enabled(void) extern int pcie_aspm_enabled(void); #endif +#ifdef CONFIG_PCIEAER +void pci_no_aer(void); +bool pci_aer_available(void); +#else +static inline void pci_no_aer(void) { } +static inline bool pci_aer_available(void) { return false; } +#endif + #ifndef CONFIG_PCIE_ECRC static inline void pcie_set_ecrc_checking(struct pci_dev *dev) { -- cgit v1.1 From b6e335aeeb114dccb07eaa09e8b62ff9510cf745 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 29 Dec 2010 13:21:23 +0100 Subject: PCI/PM: Use pm_wakeup_event() directly for reporting wakeup events After recent changes related to wakeup events pm_wakeup_event() automatically checks if the given device is configured to signal wakeup, so pci_wakeup_event() may be a static inline function calling pm_wakeup_event() directly. Signed-off-by: Rafael J. Wysocki Signed-off-by: Jesse Barnes --- include/linux/pci.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 12dd86a..9e67dcd 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -820,7 +820,6 @@ int pci_prepare_to_sleep(struct pci_dev *dev); int pci_back_from_sleep(struct pci_dev *dev); bool pci_dev_run_wake(struct pci_dev *dev); bool pci_check_pme_status(struct pci_dev *dev); -void pci_wakeup_event(struct pci_dev *dev); void pci_pme_wakeup_bus(struct pci_bus *bus); static inline int pci_enable_wake(struct pci_dev *dev, pci_power_t state, -- cgit v1.1 From 49731baa41df404c2c3f44555869ab387363af43 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 14 Jan 2011 18:43:57 +0100 Subject: block: restore multiple bd_link_disk_holder() support Commit e09b457b (block: simplify holder symlink handling) incorrectly assumed that there is only one link at maximum. dm may use multiple links and expects block layer to track reference count for each link, which is different from and unrelated to the exclusive device holder identified by @holder when the device is opened. Remove the single holder assumption and automatic removal of the link and revive the per-link reference count tracking. The code essentially behaves the same as before commit e09b457b sans the unnecessary kobject reference count dancing. While at it, note that this facility should not be used by anyone else than the current ones. Sysfs symlinks shouldn't be abused like this and the whole thing doesn't belong in the block layer at all. Signed-off-by: Tejun Heo Reported-by: Milan Broz Cc: Jun'ichi Nomura Cc: Neil Brown Cc: linux-raid@vger.kernel.org Cc: Kay Sievers Signed-off-by: Jens Axboe --- include/linux/fs.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3984f23..fb21903 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -666,7 +666,7 @@ struct block_device { int bd_holders; bool bd_write_holder; #ifdef CONFIG_SYSFS - struct gendisk * bd_holder_disk; /* for sysfs slave linkng */ + struct list_head bd_holder_disks; #endif struct block_device * bd_contains; unsigned bd_block_size; @@ -2058,12 +2058,18 @@ extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, extern int blkdev_put(struct block_device *bdev, fmode_t mode); #ifdef CONFIG_SYSFS extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); +extern void bd_unlink_disk_holder(struct block_device *bdev, + struct gendisk *disk); #else static inline int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) { return 0; } +static inline void bd_unlink_disk_holder(struct block_device *bdev, + struct gendisk *disk) +{ +} #endif #endif -- cgit v1.1 From 3e8b3b90fecedcf20d895c4e6ad01a379fe252bf Mon Sep 17 00:00:00 2001 From: Hanno Boeck Date: Fri, 14 Jan 2011 19:14:47 +0100 Subject: ALSA: constify functions in ac97 Signed-off-by: Hanno Boeck Signed-off-by: Takashi Iwai --- include/sound/ac97_codec.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/sound/ac97_codec.h b/include/sound/ac97_codec.h index 4940045..b602f47 100644 --- a/include/sound/ac97_codec.h +++ b/include/sound/ac97_codec.h @@ -477,7 +477,7 @@ struct snd_ac97_template { struct snd_ac97 { /* -- lowlevel (hardware) driver specific -- */ - struct snd_ac97_build_ops * build_ops; + const struct snd_ac97_build_ops *build_ops; void *private_data; void (*private_free) (struct snd_ac97 *ac97); /* --- */ -- cgit v1.1 From ab0724ffee24409a7f81afb539b2ac29090bff3e Mon Sep 17 00:00:00 2001 From: Markus Trippelsdorf Date: Sat, 15 Jan 2011 00:07:22 +0100 Subject: PCI / ACPI: Fix build issue in pci_root.c for !CONFIG_PCIEPORTBUS The compilation of drivers/acpi/pci_root.c fails if CONFIG_PCIEPORTBUS is unset. Fix the problem. Signed-off-by: Rafael J. Wysocki Signed-off-by: Linus Torvalds --- include/linux/pci.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index 9e67dcd..559d028 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -993,8 +993,13 @@ extern void pci_restore_msi_state(struct pci_dev *dev); extern int pci_msi_enabled(void); #endif +#ifdef CONFIG_PCIEPORTBUS extern bool pcie_ports_disabled; extern bool pcie_ports_auto; +#else +#define pcie_ports_disabled true +#define pcie_ports_auto false +#endif #ifndef CONFIG_PCIEASPM static inline int pcie_aspm_enabled(void) -- cgit v1.1 From 3632ef8909118db9584e1bed9538dc180adb32f8 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Sat, 15 Jan 2011 09:27:00 +1000 Subject: Revert "drm: Update fbdev fb_fix_screeninfo" This reverts commit dfe63bb0ad9810db13aab0058caba97866e0a681. This commit was causing nouveau not to work properly, for -rc1 I'd prefer it worked and we can look if this is useful for 2.6.39. Cc: James Simmons Signed-off-by: Dave Airlie Signed-off-by: Linus Torvalds --- include/drm/drm_fb_helper.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h index aac27bd..f22e7fe 100644 --- a/include/drm/drm_fb_helper.h +++ b/include/drm/drm_fb_helper.h @@ -121,6 +121,9 @@ int drm_fb_helper_setcolreg(unsigned regno, void drm_fb_helper_restore(void); void drm_fb_helper_fill_var(struct fb_info *info, struct drm_fb_helper *fb_helper, uint32_t fb_width, uint32_t fb_height); +void drm_fb_helper_fill_fix(struct fb_info *info, uint32_t pitch, + uint32_t depth); + int drm_fb_helper_setcmap(struct fb_cmap *cmap, struct fb_info *info); bool drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper); -- cgit v1.1 From 98d530fe246b65fbd3cdeeeca319a80c46cb4793 Mon Sep 17 00:00:00 2001 From: Russell King - ARM Linux Date: Sat, 1 Jan 2011 23:00:23 +0000 Subject: Fix dmaengine_submit() return type desc->tx_submit's return type is dma_cookie_t, not int. Therefore, dmaengine_submit() should match this return type as it's just wrapping this detail. Signed-off-by: Russell King Signed-off-by: Dan Williams --- include/linux/dmaengine.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 9d8688b..830935b 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -532,7 +532,7 @@ static inline int dmaengine_resume(struct dma_chan *chan) return dmaengine_device_control(chan, DMA_RESUME, 0); } -static inline int dmaengine_submit(struct dma_async_tx_descriptor *desc) +static inline dma_cookie_t dmaengine_submit(struct dma_async_tx_descriptor *desc) { return desc->tx_submit(desc); } -- cgit v1.1 From 96a608a4bfd8468c21881b3f92024923886eb015 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 14 Jan 2011 17:51:11 -0800 Subject: ARM: PL08x: fix a warning drivers/dma/amba-pl08x.c: In function 'pl08x_start_txd': drivers/dma/amba-pl08x.c:205: warning: dereferencing 'void *' pointer We never dereference llis_va aside from assigning it to a struct pl08x_lli pointer or calculating the address of array element 0. Signed-off-by: Dan Williams --- include/linux/amba/pl08x.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h index 933b4ed..5b87b6a 100644 --- a/include/linux/amba/pl08x.h +++ b/include/linux/amba/pl08x.h @@ -118,7 +118,7 @@ struct pl08x_txd { dma_addr_t dst_addr; size_t len; dma_addr_t llis_bus; - void *llis_va; + struct pl08x_lli *llis_va; bool active; /* Default cctl value for LLIs */ u32 cctl; -- cgit v1.1 From 9875cf806403fae66b2410a3c2cc820d97731e04 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 14 Jan 2011 18:45:21 +0000 Subject: Add a dentry op to handle automounting rather than abusing follow_link() Add a dentry op (d_automount) to handle automounting directories rather than abusing the follow_link() inode operation. The operation is keyed off a new dentry flag (DCACHE_NEED_AUTOMOUNT). This also makes it easier to add an AT_ flag to suppress terminal segment automount during pathwalk and removes the need for the kludge code in the pathwalk algorithm to handle directories with follow_link() semantics. The ->d_automount() dentry operation: struct vfsmount *(*d_automount)(struct path *mountpoint); takes a pointer to the directory to be mounted upon, which is expected to provide sufficient data to determine what should be mounted. If successful, it should return the vfsmount struct it creates (which it should also have added to the namespace using do_add_mount() or similar). If there's a collision with another automount attempt, NULL should be returned. If the directory specified by the parameter should be used directly rather than being mounted upon, -EISDIR should be returned. In any other case, an error code should be returned. The ->d_automount() operation is called with no locks held and may sleep. At this point the pathwalk algorithm will be in ref-walk mode. Within fs/namei.c itself, a new pathwalk subroutine (follow_automount()) is added to handle mountpoints. It will return -EREMOTE if the automount flag was set, but no d_automount() op was supplied, -ELOOP if we've encountered too many symlinks or mountpoints, -EISDIR if the walk point should be used without mounting and 0 if successful. The path will be updated to point to the mounted filesystem if a successful automount took place. __follow_mount() is replaced by follow_managed() which is more generic (especially with the patch that adds ->d_manage()). This handles transits from directories during pathwalk, including automounting and skipping over mountpoints (and holding processes with the next patch). __follow_mount_rcu() will jump out of RCU-walk mode if it encounters an automount point with nothing mounted on it. follow_dotdot*() does not handle automounts as you don't want to trigger them whilst following "..". I've also extracted the mount/don't-mount logic from autofs4 and included it here. It makes the mount go ahead anyway if someone calls open() or creat(), tries to traverse the directory, tries to chdir/chroot/etc. into the directory, or sticks a '/' on the end of the pathname. If they do a stat(), however, they'll only trigger the automount if they didn't also say O_NOFOLLOW. I've also added an inode flag (S_AUTOMOUNT) so that filesystems can mark their inodes as automount points. This flag is automatically propagated to the dentry as DCACHE_NEED_AUTOMOUNT by __d_instantiate(). This saves NFS and could save AFS a private flag bit apiece, but is not strictly necessary. It would be preferable to do the propagation in d_set_d_op(), but that doesn't normally have access to the inode. [AV: fixed breakage in case if __follow_mount_rcu() fails and nameidata_drop_rcu() succeeds in RCU case of do_lookup(); we need to fall through to non-RCU case after that, rather than just returning with ungrabbed *path] Signed-off-by: David Howells Was-Acked-by: Ian Kent Signed-off-by: Al Viro --- include/linux/dcache.h | 7 ++++++- include/linux/fs.h | 2 ++ 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 59fcd24..ee6c26d 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -167,6 +167,7 @@ struct dentry_operations { void (*d_release)(struct dentry *); void (*d_iput)(struct dentry *, struct inode *); char *(*d_dname)(struct dentry *, char *, int); + struct vfsmount *(*d_automount)(struct path *); } ____cacheline_aligned; /* @@ -205,13 +206,17 @@ struct dentry_operations { #define DCACHE_CANT_MOUNT 0x0100 #define DCACHE_GENOCIDE 0x0200 -#define DCACHE_MOUNTED 0x0400 /* is a mountpoint */ #define DCACHE_OP_HASH 0x1000 #define DCACHE_OP_COMPARE 0x2000 #define DCACHE_OP_REVALIDATE 0x4000 #define DCACHE_OP_DELETE 0x8000 +#define DCACHE_MOUNTED 0x10000 /* is a mountpoint */ +#define DCACHE_NEED_AUTOMOUNT 0x20000 /* handle automount on this dir */ +#define DCACHE_MANAGED_DENTRY \ + (DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT) + extern seqlock_t rename_lock; static inline int dname_external(struct dentry *dentry) diff --git a/include/linux/fs.h b/include/linux/fs.h index 3984f23..4c00ed5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -242,6 +242,7 @@ struct inodes_stat_t { #define S_SWAPFILE 256 /* Do not truncate: swapon got its bmaps */ #define S_PRIVATE 512 /* Inode is fs-internal */ #define S_IMA 1024 /* Inode has an associated IMA struct */ +#define S_AUTOMOUNT 2048 /* Automount/referral quasi-directory */ /* * Note that nosuid etc flags are inode-specific: setting some file-system @@ -277,6 +278,7 @@ struct inodes_stat_t { #define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE) #define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE) #define IS_IMA(inode) ((inode)->i_flags & S_IMA) +#define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT) /* the read-only stuff doesn't really belong here, but any other place is probably as bad and I don't want to create yet another include file. */ -- cgit v1.1 From cc53ce53c86924bfe98a12ea20b7465038a08792 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 14 Jan 2011 18:45:26 +0000 Subject: Add a dentry op to allow processes to be held during pathwalk transit Add a dentry op (d_manage) to permit a filesystem to hold a process and make it sleep when it tries to transit away from one of that filesystem's directories during a pathwalk. The operation is keyed off a new dentry flag (DCACHE_MANAGE_TRANSIT). The filesystem is allowed to be selective about which processes it holds and which it permits to continue on or prohibits from transiting from each flagged directory. This will allow autofs to hold up client processes whilst letting its userspace daemon through to maintain the directory or the stuff behind it or mounted upon it. The ->d_manage() dentry operation: int (*d_manage)(struct path *path, bool mounting_here); takes a pointer to the directory about to be transited away from and a flag indicating whether the transit is undertaken by do_add_mount() or do_move_mount() skipping through a pile of filesystems mounted on a mountpoint. It should return 0 if successful and to let the process continue on its way; -EISDIR to prohibit the caller from skipping to overmounted filesystems or automounting, and to use this directory; or some other error code to return to the user. ->d_manage() is called with namespace_sem writelocked if mounting_here is true and no other locks held, so it may sleep. However, if mounting_here is true, it may not initiate or wait for a mount or unmount upon the parameter directory, even if the act is actually performed by userspace. Within fs/namei.c, follow_managed() is extended to check with d_manage() first on each managed directory, before transiting away from it or attempting to automount upon it. follow_down() is renamed follow_down_one() and should only be used where the filesystem deliberately intends to avoid management steps (e.g. autofs). A new follow_down() is added that incorporates the loop done by all other callers of follow_down() (do_add/move_mount(), autofs and NFSD; whilst AFS, NFS and CIFS do use it, their use is removed by converting them to use d_automount()). The new follow_down() calls d_manage() as appropriate. It also takes an extra parameter to indicate if it is being called from mount code (with namespace_sem writelocked) which it passes to d_manage(). follow_down() ignores automount points so that it can be used to mount on them. __follow_mount_rcu() is made to abort rcu-walk mode if it hits a directory with DCACHE_MANAGE_TRANSIT set on the basis that we're probably going to have to sleep. It would be possible to enter d_manage() in rcu-walk mode too, and have that determine whether to abort or not itself. That would allow the autofs daemon to continue on in rcu-walk mode. Note that DCACHE_MANAGE_TRANSIT on a directory should be cleared when it isn't required as every tranist from that directory will cause d_manage() to be invoked. It can always be set again when necessary. ========================== WHAT THIS MEANS FOR AUTOFS ========================== Autofs currently uses the lookup() inode op and the d_revalidate() dentry op to trigger the automounting of indirect mounts, and both of these can be called with i_mutex held. autofs knows that the i_mutex will be held by the caller in lookup(), and so can drop it before invoking the daemon - but this isn't so for d_revalidate(), since the lock is only held on _some_ of the code paths that call it. This means that autofs can't risk dropping i_mutex from its d_revalidate() function before it calls the daemon. The bug could manifest itself as, for example, a process that's trying to validate an automount dentry that gets made to wait because that dentry is expired and needs cleaning up: mkdir S ffffffff8014e05a 0 32580 24956 Call Trace: [] :autofs4:autofs4_wait+0x674/0x897 [] avc_has_perm+0x46/0x58 [] autoremove_wake_function+0x0/0x2e [] :autofs4:autofs4_expire_wait+0x41/0x6b [] :autofs4:autofs4_revalidate+0x91/0x149 [] __lookup_hash+0xa0/0x12f [] lookup_create+0x46/0x80 [] sys_mkdirat+0x56/0xe4 versus the automount daemon which wants to remove that dentry, but can't because the normal process is holding the i_mutex lock: automount D ffffffff8014e05a 0 32581 1 32561 Call Trace: [] __mutex_lock_slowpath+0x60/0x9b [] do_path_lookup+0x2ca/0x2f1 [] .text.lock.mutex+0xf/0x14 [] do_rmdir+0x77/0xde [] tracesys+0x71/0xe0 [] tracesys+0xd5/0xe0 which means that the system is deadlocked. This patch allows autofs to hold up normal processes whilst the daemon goes ahead and does things to the dentry tree behind the automouter point without risking a deadlock as almost no locks are held in d_manage() and none in d_automount(). Signed-off-by: David Howells Was-Acked-by: Ian Kent Signed-off-by: Al Viro --- include/linux/dcache.h | 11 +++++++++-- include/linux/namei.h | 3 ++- 2 files changed, 11 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index ee6c26d..1a87760 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -168,6 +168,7 @@ struct dentry_operations { void (*d_iput)(struct dentry *, struct inode *); char *(*d_dname)(struct dentry *, char *, int); struct vfsmount *(*d_automount)(struct path *); + int (*d_manage)(struct dentry *, bool); } ____cacheline_aligned; /* @@ -214,8 +215,9 @@ struct dentry_operations { #define DCACHE_MOUNTED 0x10000 /* is a mountpoint */ #define DCACHE_NEED_AUTOMOUNT 0x20000 /* handle automount on this dir */ +#define DCACHE_MANAGE_TRANSIT 0x40000 /* manage transit from this dirent */ #define DCACHE_MANAGED_DENTRY \ - (DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT) + (DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT) extern seqlock_t rename_lock; @@ -404,7 +406,12 @@ static inline void dont_mount(struct dentry *dentry) extern void dput(struct dentry *); -static inline int d_mountpoint(struct dentry *dentry) +static inline bool d_managed(struct dentry *dentry) +{ + return dentry->d_flags & DCACHE_MANAGED_DENTRY; +} + +static inline bool d_mountpoint(struct dentry *dentry) { return dentry->d_flags & DCACHE_MOUNTED; } diff --git a/include/linux/namei.h b/include/linux/namei.h index 18d06ad..8ef2c78 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -79,7 +79,8 @@ extern struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry extern struct dentry *lookup_one_len(const char *, struct dentry *, int); -extern int follow_down(struct path *); +extern int follow_down_one(struct path *); +extern int follow_down(struct path *, bool); extern int follow_up(struct path *); extern struct dentry *lock_rename(struct dentry *, struct dentry *); -- cgit v1.1 From 6f45b65672c8017d5e210e338bb5858a938ef445 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 14 Jan 2011 18:45:31 +0000 Subject: Add an AT_NO_AUTOMOUNT flag to suppress terminal automount Add an AT_NO_AUTOMOUNT flag to suppress terminal automounting of automount point directories. This can be used by fstatat() users to permit the gathering of attributes on an automount point and also prevent mass-automounting of a directory of automount points by ls. Signed-off-by: David Howells Acked-by: Ian Kent Signed-off-by: Al Viro --- include/linux/fcntl.h | 1 + include/linux/namei.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h index afc00af..a562fa5 100644 --- a/include/linux/fcntl.h +++ b/include/linux/fcntl.h @@ -45,6 +45,7 @@ #define AT_REMOVEDIR 0x200 /* Remove directory instead of unlinking file. */ #define AT_SYMLINK_FOLLOW 0x400 /* Follow symbolic links. */ +#define AT_NO_AUTOMOUNT 0x800 /* Suppress terminal automount traversal */ #ifdef __KERNEL__ diff --git a/include/linux/namei.h b/include/linux/namei.h index 8ef2c78..f276d4f 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -45,6 +45,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; * - ending slashes ok even for nonexistent files * - internal "there are more path components" flag * - dentry cache is untrusted; force a real lookup + * - suppress terminal automount */ #define LOOKUP_FOLLOW 0x0001 #define LOOKUP_DIRECTORY 0x0002 @@ -53,6 +54,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_PARENT 0x0010 #define LOOKUP_REVAL 0x0020 #define LOOKUP_RCU 0x0040 +#define LOOKUP_NO_AUTOMOUNT 0x0080 /* * Intent data */ -- cgit v1.1 From 36d43a43761b004ad1879ac21471d8fc5f3157ec Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 14 Jan 2011 18:45:42 +0000 Subject: NFS: Use d_automount() rather than abusing follow_link() Make NFS use the new d_automount() dentry operation rather than abusing follow_link() on directories. Signed-off-by: David Howells Acked-by: Trond Myklebust Acked-by: Ian Kent Signed-off-by: Al Viro --- include/linux/nfs_fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 0779bb8..6023efa 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -215,7 +215,6 @@ struct nfs_inode { #define NFS_INO_ADVISE_RDPLUS (0) /* advise readdirplus */ #define NFS_INO_STALE (1) /* possible stale inode */ #define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */ -#define NFS_INO_MOUNTPOINT (3) /* inode is remote mountpoint */ #define NFS_INO_FLUSHING (4) /* inode is flushing out data */ #define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ #define NFS_INO_FSCACHE_LOCK (6) /* FS-Cache cookie management lock */ -- cgit v1.1 From 1972580bb4edea3ed6fe273b2ca72f44f10f8c86 Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Fri, 14 Jan 2011 18:46:40 +0000 Subject: autofs4: Bump version Increase the autofs module sub-version so we can tell what kernel implementation is being used from user space debug logging. Signed-off-by: Ian Kent Signed-off-by: David Howells Signed-off-by: Al Viro --- include/linux/auto_fs4.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/auto_fs4.h b/include/linux/auto_fs4.h index 8b49ac4..e02982f 100644 --- a/include/linux/auto_fs4.h +++ b/include/linux/auto_fs4.h @@ -24,7 +24,7 @@ #define AUTOFS_MIN_PROTO_VERSION 3 #define AUTOFS_MAX_PROTO_VERSION 5 -#define AUTOFS_PROTO_SUBVERSION 1 +#define AUTOFS_PROTO_SUBVERSION 2 /* Mask for expire behaviour */ #define AUTOFS_EXP_IMMEDIATE 1 -- cgit v1.1 From ab90911ff90cdab59b31c045c3f0ae480d14f29d Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 14 Jan 2011 18:46:51 +0000 Subject: Allow d_manage() to be used in RCU-walk mode Allow d_manage() to be called from pathwalk when it is in RCU-walk mode as well as when it is in Ref-walk mode. This permits __follow_mount_rcu() to call d_manage() directly. d_manage() needs a parameter to indicate that it is in RCU-walk mode as it isn't allowed to sleep if in that mode (but should return -ECHILD instead). autofs4_d_manage() can then be set to retain RCU-walk mode if the daemon accesses it and otherwise request dropping back to ref-walk mode. Signed-off-by: David Howells Signed-off-by: Al Viro --- include/linux/dcache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 1a87760..f958c19 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -168,7 +168,7 @@ struct dentry_operations { void (*d_iput)(struct dentry *, struct inode *); char *(*d_dname)(struct dentry *, char *, int); struct vfsmount *(*d_automount)(struct path *); - int (*d_manage)(struct dentry *, bool); + int (*d_manage)(struct dentry *, bool, bool); } ____cacheline_aligned; /* -- cgit v1.1 From ea5b778a8b98c85a87d66bf844904f9c3802b869 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 14 Jan 2011 19:10:03 +0000 Subject: Unexport do_add_mount() and add in follow_automount(), not ->d_automount() Unexport do_add_mount() and make ->d_automount() return the vfsmount to be added rather than calling do_add_mount() itself. follow_automount() will then do the addition. This slightly complicates things as ->d_automount() normally wants to add the new vfsmount to an expiration list and start an expiration timer. The problem with that is that the vfsmount will be deleted if it has a refcount of 1 and the timer will not repeat if the expiration list is empty. To this end, we require the vfsmount to be returned from d_automount() with a refcount of (at least) 2. One of these refs will be dropped unconditionally. In addition, follow_automount() must get a 3rd ref around the call to do_add_mount() lest it eat a ref and return an error, leaving the mount we have open to being expired as we would otherwise have only 1 ref on it. d_automount() should also add the the vfsmount to the expiration list (by calling mnt_set_expiry()) and start the expiration timer before returning, if this mechanism is to be used. The vfsmount will be unlinked from the expiration list by follow_automount() if do_add_mount() fails. This patch also fixes the call to do_add_mount() for AFS to propagate the mount flags from the parent vfsmount. Signed-off-by: David Howells Signed-off-by: Al Viro --- include/linux/mount.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/mount.h b/include/linux/mount.h index 1869ea2..af4765e 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -110,12 +110,7 @@ extern struct vfsmount *vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data); -struct nameidata; - -struct path; -extern int do_add_mount(struct vfsmount *newmnt, struct path *path, - int mnt_flags, struct list_head *fslist); - +extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list); extern void mark_mounts_for_expiry(struct list_head *mounts); extern dev_t name_to_dev_t(char *name); -- cgit v1.1 From 672c54466d24994eb9633f993862c89539504a42 Mon Sep 17 00:00:00 2001 From: Grant Likely Date: Thu, 13 Jan 2011 15:36:09 -0700 Subject: dt/flattree: Return virtual address from early_init_dt_alloc_memory_arch() The physical address is never used by the device tree code when allocating memory for unflattening. Change the architecture's alloc hook to return the virutal address instead. Signed-off-by: Grant Likely --- include/linux/of_fdt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index 0ef22a1..c84d900 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -97,7 +97,7 @@ extern void early_init_dt_check_for_initrd(unsigned long node); extern int early_init_dt_scan_memory(unsigned long node, const char *uname, int depth, void *data); extern void early_init_dt_add_memory_arch(u64 base, u64 size); -extern u64 early_init_dt_alloc_memory_arch(u64 size, u64 align); +extern void * early_init_dt_alloc_memory_arch(u64 size, u64 align); extern u64 dt_mem_next_cell(int s, __be32 **cellp); /* -- cgit v1.1 From f03c65993b98eeb909a4012ce7833c5857d74755 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 14 Jan 2011 22:30:21 -0500 Subject: sanitize vfsmount refcounting changes Instead of splitting refcount between (per-cpu) mnt_count and (SMP-only) mnt_longrefs, make all references contribute to mnt_count again and keep track of how many are longterm ones. Accounting rules for longterm count: * 1 for each fs_struct.root.mnt * 1 for each fs_struct.pwd.mnt * 1 for having non-NULL ->mnt_ns * decrement to 0 happens only under vfsmount lock exclusive That allows nice common case for mntput() - since we can't drop the final reference until after mnt_longterm has reached 0 due to the rules above, mntput() can grab vfsmount lock shared and check mnt_longterm. If it turns out to be non-zero (which is the common case), we know that this is not the final mntput() and can just blindly decrement percpu mnt_count. Otherwise we grab vfsmount lock exclusive and do usual decrement-and-check of percpu mnt_count. For fs_struct.c we have mnt_make_longterm() and mnt_make_shortterm(); namespace.c uses the latter in places where we don't already hold vfsmount lock exclusive and opencodes a few remaining spots where we need to manipulate mnt_longterm. Note that we mostly revert the code outside of fs/namespace.c back to what we used to have; in particular, normal code doesn't need to care about two kinds of references, etc. And we get to keep the optimization Nick's variant had bought us... Signed-off-by: Al Viro --- include/linux/mount.h | 4 +--- include/linux/path.h | 2 -- 2 files changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/mount.h b/include/linux/mount.h index af4765e..604f122 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -60,7 +60,7 @@ struct vfsmount { struct super_block *mnt_sb; /* pointer to superblock */ #ifdef CONFIG_SMP struct mnt_pcp __percpu *mnt_pcp; - atomic_t mnt_longrefs; + atomic_t mnt_longterm; /* how many of the refs are longterm */ #else int mnt_count; int mnt_writers; @@ -96,8 +96,6 @@ extern int mnt_clone_write(struct vfsmount *mnt); extern void mnt_drop_write(struct vfsmount *mnt); extern void mntput(struct vfsmount *mnt); extern struct vfsmount *mntget(struct vfsmount *mnt); -extern void mntput_long(struct vfsmount *mnt); -extern struct vfsmount *mntget_long(struct vfsmount *mnt); extern void mnt_pin(struct vfsmount *mnt); extern void mnt_unpin(struct vfsmount *mnt); extern int __mnt_is_readonly(struct vfsmount *mnt); diff --git a/include/linux/path.h b/include/linux/path.h index a581e8c..edc98de 100644 --- a/include/linux/path.h +++ b/include/linux/path.h @@ -10,9 +10,7 @@ struct path { }; extern void path_get(struct path *); -extern void path_get_long(struct path *); extern void path_put(struct path *); -extern void path_put_long(struct path *); static inline int path_equal(const struct path *path1, const struct path *path2) { -- cgit v1.1 From fc8fe1e992ae0326a88edbe4d6793e840bbdd4ff Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 16 Jan 2011 20:42:43 +0100 Subject: PCI / ACPI: Fix build of the AER driver for CONFIG_ACPI unset After commit 415e12b23792 ("PCI/ACPI: Request _OSC control once for each root bridge (v3)") include/linux/pci-acpi.h is included by drivers/pci/pcie/aer/aerdrv.c and if CONFIG_ACPI is unset, the bogus and unnecessary alternative definition of acpi_find_root_bridge_handle() causes a build error to occur. Remove the offending piece of garbage. Reported-and-tested-by: Stephen Rothwell Signed-off-by: Rafael J. Wysocki Signed-off-by: Linus Torvalds --- include/linux/pci-acpi.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index 479d9bb..4462350 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -35,9 +35,6 @@ static inline acpi_handle acpi_pci_get_bridge_handle(struct pci_bus *pbus) return acpi_get_pci_rootbridge_handle(pci_domain_nr(pbus), pbus->number); } -#else -static inline acpi_handle acpi_find_root_bridge_handle(struct pci_dev *pdev) -{ return NULL; } #endif #ifdef CONFIG_ACPI_APEI -- cgit v1.1 From b3697c0255d9d73eaaa4deb4512e3f0ff97b3b71 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Sun, 16 Jan 2011 13:10:39 -0800 Subject: fix non-x86 build failure in pmdp_get_and_clear pmdp_get_and_clear/pmdp_clear_flush/pmdp_splitting_flush were trapped as BUG() and they were defined only to diminish the risk of build issues on not-x86 archs and to be consistent with the generic pte methods previously defined in include/asm-generic/pgtable.h. But they are causing more trouble than they were supposed to solve, so it's simpler not to define them when THP is off. This is also correcting the export of pmdp_splitting_flush which is currently unused (x86 isn't using the generic implementation in mm/pgtable-generic.c and no other arch needs that [yet]). Signed-off-by: Andrea Arcangeli Sam Ravnborg Cc: Stephen Rothwell Cc: "David S. Miller" Cc: Benjamin Herrenschmidt Cc: "Luck, Tony" Cc: James Bottomley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/pgtable.h | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index f1eddf7..31b6188 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -87,14 +87,6 @@ static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm, pmd_clear(mm, address, pmdp); return pmd; }) -#else /* CONFIG_TRANSPARENT_HUGEPAGE */ -static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm, - unsigned long address, - pmd_t *pmdp) -{ - BUG(); - return __pmd(0); -} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif @@ -163,9 +155,9 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, #endif #ifndef __HAVE_ARCH_PMDP_SPLITTING_FLUSH -extern pmd_t pmdp_clear_flush(struct vm_area_struct *vma, - unsigned long address, - pmd_t *pmdp); +extern pmd_t pmdp_splitting_flush(struct vm_area_struct *vma, + unsigned long address, + pmd_t *pmdp); #endif #ifndef __HAVE_ARCH_PTE_SAME -- cgit v1.1 From 94ae85220a07d357d4937086c490854f63344de4 Mon Sep 17 00:00:00 2001 From: Russell King - ARM Linux Date: Sun, 16 Jan 2011 20:18:05 +0000 Subject: ARM: PL08x: cleanup comments Cleanup the formatting of comments, remove some which don't make sense anymore. Signed-off-by: Russell King [fix conflict with 96a608a4] Signed-off-by: Dan Williams --- include/linux/amba/pl08x.h | 43 ++++++++++++++++++++----------------------- 1 file changed, 20 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h index 5b87b6a..3111385 100644 --- a/include/linux/amba/pl08x.h +++ b/include/linux/amba/pl08x.h @@ -12,7 +12,6 @@ * * Please credit ARM.com * Documentation: ARM DDI 0196D - * */ #ifndef AMBA_PL08X_H @@ -55,8 +54,8 @@ enum { * @circular_buffer: whether the buffer passed in is circular and * shall simply be looped round round (like a record baby round * round round round) - * @single: the device connected to this channel will request single - * DMA transfers, not bursts. (Bursts are default.) + * @single: the device connected to this channel will request single DMA + * transfers, not bursts. (Bursts are default.) * @periph_buses: the device connected to this channel is accessible via * these buses (use PL08X_AHB1 | PL08X_AHB2). */ @@ -78,8 +77,7 @@ struct pl08x_channel_data { * @addr: current address * @maxwidth: the maximum width of a transfer on this bus * @buswidth: the width of this bus in bytes: 1, 2 or 4 - * @fill_bytes: bytes required to fill to the next bus memory - * boundary + * @fill_bytes: bytes required to fill to the next bus memory boundary */ struct pl08x_bus_data { dma_addr_t addr; @@ -92,10 +90,10 @@ struct pl08x_bus_data { * struct pl08x_phy_chan - holder for the physical channels * @id: physical index to this channel * @lock: a lock to use when altering an instance of this struct - * @signal: the physical signal (aka channel) serving this - * physical channel right now - * @serving: the virtual channel currently being served by this - * physical channel + * @signal: the physical signal (aka channel) serving this physical channel + * right now + * @serving: the virtual channel currently being served by this physical + * channel */ struct pl08x_phy_chan { unsigned int id; @@ -119,7 +117,6 @@ struct pl08x_txd { size_t len; dma_addr_t llis_bus; struct pl08x_lli *llis_va; - bool active; /* Default cctl value for LLIs */ u32 cctl; /* @@ -130,8 +127,8 @@ struct pl08x_txd { }; /** - * struct pl08x_dma_chan_state - holds the PL08x specific virtual - * channel states + * struct pl08x_dma_chan_state - holds the PL08x specific virtual channel + * states * @PL08X_CHAN_IDLE: the channel is idle * @PL08X_CHAN_RUNNING: the channel has allocated a physical transport * channel and is running a transfer on it @@ -152,7 +149,7 @@ enum pl08x_dma_chan_state { * @chan: wrappped abstract channel * @phychan: the physical channel utilized by this channel, if there is one * @phychan_hold: if non-zero, hold on to the physical channel even if we - * have no pending entries + * have no pending entries * @tasklet: tasklet scheduled by the IRQ to handle actual work etc * @name: name of channel * @cd: channel platform data @@ -166,8 +163,8 @@ enum pl08x_dma_chan_state { * @host: a pointer to the host (internal use) * @state: whether the channel is idle, paused, running etc * @slave: whether this channel is a device (slave) or for memcpy - * @waiting: a TX descriptor on this channel which is waiting for - * a physical channel to become available + * @waiting: a TX descriptor on this channel which is waiting for a physical + * channel to become available */ struct pl08x_dma_chan { struct dma_chan chan; @@ -189,16 +186,16 @@ struct pl08x_dma_chan { }; /** - * struct pl08x_platform_data - the platform configuration for the - * PL08x PrimeCells. + * struct pl08x_platform_data - the platform configuration for the PL08x + * PrimeCells. * @slave_channels: the channels defined for the different devices on the * platform, all inclusive, including multiplexed channels. The available - * physical channels will be multiplexed around these signals as they - * are requested, just enumerate all possible channels. - * @get_signal: request a physical signal to be used for a DMA - * transfer immediately: if there is some multiplexing or similar blocking - * the use of the channel the transfer can be denied by returning - * less than zero, else it returns the allocated signal number + * physical channels will be multiplexed around these signals as they are + * requested, just enumerate all possible channels. + * @get_signal: request a physical signal to be used for a DMA transfer + * immediately: if there is some multiplexing or similar blocking the use + * of the channel the transfer can be denied by returning less than zero, + * else it returns the allocated signal number * @put_signal: indicate to the platform that this physical signal is not * running any DMA transfer and multiplexing can be recycled * @lli_buses: buses which LLIs can be fetched from: PL08X_AHB1 | PL08X_AHB2 -- cgit v1.1 From f06267104dd9112f11586830d22501d0e26245ea Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 19 Oct 2010 15:24:36 +0000 Subject: RDMA: Update workqueue usage * ib_wq is added, which is used as the common workqueue for infiniband instead of the system workqueue. All system workqueue usages including flush_scheduled_work() callers are converted to use and flush ib_wq. * cancel_delayed_work() + flush_scheduled_work() converted to cancel_delayed_work_sync(). * qib_wq is removed and ib_wq is used instead. This is to prepare for deprecation of flush_scheduled_work(). Signed-off-by: Tejun Heo Signed-off-by: Roland Dreier --- include/rdma/ib_verbs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index e04c488..55cd0a0 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -47,10 +47,13 @@ #include #include #include +#include #include #include +extern struct workqueue_struct *ib_wq; + union ib_gid { u8 raw[16]; struct { -- cgit v1.1 From 2fe17c1075836b66678ed2a305fd09b6773883aa Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 14 Jan 2011 13:07:43 +0100 Subject: fallocate should be a file operation Currently all filesystems except XFS implement fallocate asynchronously, while XFS forced a commit. Both of these are suboptimal - in case of O_SYNC I/O we really want our allocation on disk, especially for the !KEEP_SIZE case where we actually grow the file with user-visible zeroes. On the other hand always commiting the transaction is a bad idea for fast-path uses of fallocate like for example in recent Samba versions. Given that block allocation is a data plane operation anyway change it from an inode operation to a file operation so that we have the file structure available that lets us check for O_SYNC. This also includes moving the code around for a few of the filesystems, and remove the already unnedded S_ISDIR checks given that we only wire up fallocate for regular files. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 177b4dde..09b5bd6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1552,6 +1552,8 @@ struct file_operations { ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); int (*setlease)(struct file *, long, struct file_lock **); + long (*fallocate)(struct file *file, int mode, loff_t offset, + loff_t len); }; #define IPERM_FLAG_RCU 0x0001 @@ -1582,8 +1584,6 @@ struct inode_operations { ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*removexattr) (struct dentry *, const char *); void (*truncate_range)(struct inode *, loff_t, loff_t); - long (*fallocate)(struct inode *inode, int mode, loff_t offset, - loff_t len); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); } ____cacheline_aligned; -- cgit v1.1 From c2b3e74b78b24cb367289a75a2bd30e569e56e0e Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 13 Dec 2010 19:38:08 -0500 Subject: fs: Remove unlikely() from fput_light() In fput_light(), there's an unlikely(fput_needed), which running on my normal desktop doing firefox, xchat, evolution and part of my distcc farm, and running the annotate branch profiler shows that the unlikely is not very unlikely. correct incorrect % Function File Line ------- --------- - -------- ---- ---- 0 48 100 fput_light file.h 26 115828710 897415279 88 fput_light file.h 26 865271179 5286128445 85 fput_light file.h 26 19568539 8923664 31 fput_light file.h 26 12353677 3562279 22 fput_light file.h 26 267691 67062 20 fput_light file.h 26 15014853 348172 2 fput_light file.h 26 209258 205 0 fput_light file.h 26 1364164 0 0 fput_light file.h 26 Which gives 1032903812 times it was correct and 6203351846 times it was incorrect, or 85% incorrect. Cc: Andrew Morton Signed-off-by: Steven Rostedt Signed-off-by: Al Viro --- include/linux/file.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/file.h b/include/linux/file.h index b1e1297..e85baeb 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -23,7 +23,7 @@ extern struct file *alloc_file(struct path *, fmode_t mode, static inline void fput_light(struct file *file, int fput_needed) { - if (unlikely(fput_needed)) + if (fput_needed) fput(file); } -- cgit v1.1 From ecf5632dd189ab4c366cef853d6e5fe7adfe52e5 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Sun, 16 Jan 2011 23:28:17 +0900 Subject: fs: fix address space warnings in ioctl_fiemap() The fi_extents_start field of struct fiemap_extent_info is a user pointer but was not marked as __user. This makes sparse emit following warnings: CHECK fs/ioctl.c fs/ioctl.c:114:26: warning: incorrect type in argument 1 (different address spaces) fs/ioctl.c:114:26: expected void [noderef] *dst fs/ioctl.c:114:26: got struct fiemap_extent *[assigned] dest fs/ioctl.c:202:14: warning: incorrect type in argument 1 (different address spaces) fs/ioctl.c:202:14: expected void const volatile [noderef] * fs/ioctl.c:202:14: got struct fiemap_extent *[assigned] fi_extents_start fs/ioctl.c:212:27: warning: incorrect type in argument 1 (different address spaces) fs/ioctl.c:212:27: expected void [noderef] *dst fs/ioctl.c:212:27: got char * Also add 'ufiemap' variable to eliminate unnecessary casts. Signed-off-by: Namhyung Kim Signed-off-by: Al Viro --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 09b5bd6..32b38cd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1483,8 +1483,8 @@ struct fiemap_extent_info { unsigned int fi_flags; /* Flags as passed from user */ unsigned int fi_extents_mapped; /* Number of mapped extents */ unsigned int fi_extents_max; /* Size of fiemap_extent array */ - struct fiemap_extent *fi_extents_start; /* Start of fiemap_extent - * array */ + struct fiemap_extent __user *fi_extents_start; /* Start of + fiemap_extent array */ }; int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical, u64 phys, u64 len, u32 flags); -- cgit v1.1 From 2a8652f4e0d11ee27b1d2870c600fd1300661a6e Mon Sep 17 00:00:00 2001 From: Roberto Sassu Date: Wed, 3 Nov 2010 11:11:15 +0100 Subject: ecryptfs: moved ECRYPTFS_SUPER_MAGIC definition to linux/magic.h The definition of ECRYPTFS_SUPER_MAGIC has been moved to the include file 'linux/magic.h' to become available to other kernel subsystems. Signed-off-by: Roberto Sassu Signed-off-by: Tyler Hicks --- include/linux/magic.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/magic.h b/include/linux/magic.h index ff690d0..62730ea 100644 --- a/include/linux/magic.h +++ b/include/linux/magic.h @@ -16,6 +16,7 @@ #define TMPFS_MAGIC 0x01021994 #define HUGETLBFS_MAGIC 0x958458f6 /* some random number */ #define SQUASHFS_MAGIC 0x73717368 +#define ECRYPTFS_SUPER_MAGIC 0xf15f #define EFS_SUPER_MAGIC 0x414A53 #define EXT2_SUPER_MAGIC 0xEF53 #define EXT3_SUPER_MAGIC 0xEF53 -- cgit v1.1