From 18cb2aef91b37dbce2bec2f39bb1dddd0e9dd838 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Sat, 7 Aug 2010 03:26:23 +0900 Subject: percpu: handle __percpu notations in UP accessors UP accessors didn't take care of __percpu notations leading to a lot of spurious sparse warnings on UP configurations. Fix it. Signed-off-by: Namhyung Kim Signed-off-by: Tejun Heo --- include/linux/percpu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index b8b9084..49466b1 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -149,7 +149,7 @@ extern void __init percpu_init_late(void); #else /* CONFIG_SMP */ -#define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); }) +#define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); VERIFY_PERCPU_PTR((ptr)); }) /* can't distinguish from other static vars, always false */ static inline bool is_kernel_percpu_address(unsigned long addr) -- cgit v1.1 From 92298e668372f2f6c8a79fb272f13d65161a4876 Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Fri, 13 Aug 2010 10:22:17 +1000 Subject: PCI: provide stub pci_domain_nr function for !CONFIG_PCI configs Allows the new PCI domain aware DRM code to compile on m68k. Reported-by: Geert Uytterhoeven Signed-off-by: Dave Airlie Signed-off-by: Jesse Barnes --- include/linux/pci.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index b1d1795..c8d95e3 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1214,6 +1214,9 @@ static inline struct pci_dev *pci_get_bus_and_slot(unsigned int bus, unsigned int devfn) { return NULL; } +static inline int pci_domain_nr(struct pci_bus *bus) +{ return 0; } + #define dev_is_pci(d) (false) #define dev_is_pf(d) (false) #define dev_num_vf(d) (0) -- cgit v1.1 From 5dd531a03ad721b41911ddb32e6e0481404e7aaf Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 23 Aug 2010 13:52:19 +0200 Subject: block: add function call to switch the IO scheduler from a driver Currently drivers must do an elevator_exit() + elevator_init() to switch IO schedulers. There are a few problems with this: - Since commit 1abec4fdbb142e3ccb6ce99832fae42129134a96, elevator_init() requires a zeroed out q->elevator pointer. The two existing in-kernel users don't do that. - It will only work at initialization time, since using the above two-staged construct does not properly quisce the queue. So add elevator_change() which takes care of this, and convert the elv_iosched_store() sysfs interface to use this helper as well. Reported-by: Peter Oberparleiter Reported-by: Kevin Vigor Signed-off-by: Jens Axboe --- include/linux/elevator.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 2c958f4..926b503 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -136,6 +136,7 @@ extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t); extern int elevator_init(struct request_queue *, char *); extern void elevator_exit(struct elevator_queue *); +extern int elevator_change(struct request_queue *, const char *); extern int elv_rq_merge_ok(struct request *, struct bio *); /* -- cgit v1.1 From e41e704bc4f49057fc68b643108366e6e6781aa3 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 24 Aug 2010 14:22:47 +0200 Subject: workqueue: improve destroy_workqueue() debuggability Now that the worklist is global, having works pending after wq destruction can easily lead to oops and destroy_workqueue() have several BUG_ON()s to catch these cases. Unfortunately, BUG_ON() doesn't tell much about how the work became pending after the final flush_workqueue(). This patch adds WQ_DYING which is set before the final flush begins. If a work is requested to be queued on a dying workqueue, WARN_ON_ONCE() is triggered and the request is ignored. This clearly indicates which caller is trying to queue a work on a dying workqueue and keeps the system working in most cases. Locking rule comment is updated such that the 'I' rule includes modifying the field from destruction path. Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 4f9d277..c959666 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -241,6 +241,8 @@ enum { WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu instensive workqueue */ + WQ_DYING = 1 << 6, /* internal: workqueue is dying */ + WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, -- cgit v1.1 From 75fb60f26befb59dbfa05cb122972642b7bdd219 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 23 Aug 2010 23:53:11 +0200 Subject: ACPI/PCI: Negotiate _OSC control bits before requesting them It is possible that the BIOS will not grant control of all _OSC features requested via acpi_pci_osc_control_set(), so it is recommended to negotiate the final set of _OSC features with the query flag set before calling _OSC to request control of these features. To implement it, rework acpi_pci_osc_control_set() so that the caller can specify the mask of _OSC control bits to negotiate and the mask of _OSC control bits that are absolutely necessary to it. Then, acpi_pci_osc_control_set() will run _OSC queries in a loop until the mask of _OSC control bits returned by the BIOS is equal to the mask passed to it. Also, before running the _OSC request acpi_pci_osc_control_set() will check if the caller's required control bits are present in the final mask. Using this mechanism we will be able to avoid situations in which the BIOS doesn't grant control of certain _OSC features, because they depend on some other _OSC features that have not been requested. Signed-off-by: Rafael J. Wysocki Signed-off-by: Jesse Barnes --- include/linux/acpi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index ccf94dc..c227757 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -304,8 +304,8 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); OSC_PCI_EXPRESS_PME_CONTROL | \ OSC_PCI_EXPRESS_AER_CONTROL | \ OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL) - -extern acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 flags); +extern acpi_status acpi_pci_osc_control_set(acpi_handle handle, + u32 *mask, u32 req); extern void acpi_early_init(void); #else /* !CONFIG_ACPI */ -- cgit v1.1 From 8a2e8e5dec7e29c56a46ba176c664ab6a3d04118 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 25 Aug 2010 10:33:56 +0200 Subject: workqueue: fix cwq->nr_active underflow cwq->nr_active is used to keep track of how many work items are active for the cpu workqueue, where 'active' is defined as either pending on global worklist or executing. This is used to implement the max_active limit and workqueue freezing. If a work item is queued after nr_active has already reached max_active, the work item doesn't increment nr_active and is put on the delayed queue and gets activated later as previous active work items retire. try_to_grab_pending() which is used in the cancellation path unconditionally decremented nr_active whether the work item being cancelled is currently active or delayed, so cancelling a delayed work item makes nr_active underflow. This breaks max_active enforcement and triggers BUG_ON() in destroy_workqueue() later on. This patch fixes this bug by adding a flag WORK_STRUCT_DELAYED, which is set while a work item in on the delayed list and making try_to_grab_pending() decrement nr_active iff the work item is currently active. The addition of the flag enlarges cwq alignment to 256 bytes which is getting a bit too large. It's scheduled to be reduced back to 128 bytes by merging WORK_STRUCT_PENDING and WORK_STRUCT_CWQ in the next devel cycle. Signed-off-by: Tejun Heo Reported-by: Johannes Berg --- include/linux/workqueue.h | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index c959666..f11100f 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -25,18 +25,20 @@ typedef void (*work_func_t)(struct work_struct *work); enum { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ - WORK_STRUCT_CWQ_BIT = 1, /* data points to cwq */ - WORK_STRUCT_LINKED_BIT = 2, /* next work is linked to this one */ + WORK_STRUCT_DELAYED_BIT = 1, /* work item is delayed */ + WORK_STRUCT_CWQ_BIT = 2, /* data points to cwq */ + WORK_STRUCT_LINKED_BIT = 3, /* next work is linked to this one */ #ifdef CONFIG_DEBUG_OBJECTS_WORK - WORK_STRUCT_STATIC_BIT = 3, /* static initializer (debugobjects) */ - WORK_STRUCT_COLOR_SHIFT = 4, /* color for workqueue flushing */ + WORK_STRUCT_STATIC_BIT = 4, /* static initializer (debugobjects) */ + WORK_STRUCT_COLOR_SHIFT = 5, /* color for workqueue flushing */ #else - WORK_STRUCT_COLOR_SHIFT = 3, /* color for workqueue flushing */ + WORK_STRUCT_COLOR_SHIFT = 4, /* color for workqueue flushing */ #endif WORK_STRUCT_COLOR_BITS = 4, WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, + WORK_STRUCT_DELAYED = 1 << WORK_STRUCT_DELAYED_BIT, WORK_STRUCT_CWQ = 1 << WORK_STRUCT_CWQ_BIT, WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT, #ifdef CONFIG_DEBUG_OBJECTS_WORK @@ -59,8 +61,8 @@ enum { /* * Reserve 7 bits off of cwq pointer w/ debugobjects turned - * off. This makes cwqs aligned to 128 bytes which isn't too - * excessive while allowing 15 workqueue flush colors. + * off. This makes cwqs aligned to 256 bytes and allows 15 + * workqueue flush colors. */ WORK_STRUCT_FLAG_BITS = WORK_STRUCT_COLOR_SHIFT + WORK_STRUCT_COLOR_BITS, -- cgit v1.1 From a28dec2f26013aad89446b1f708f948617bc28a2 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Sun, 8 Aug 2010 18:03:33 +0400 Subject: powerpc/85xx: Add P1021 PCI IDs and quirks This is needed for proper PCI-E support on P1021 SoCs. Signed-off-by: Anton Vorontsov Signed-off-by: Kumar Gala --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index f6a3b2d..10d3330 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2300,6 +2300,8 @@ #define PCI_DEVICE_ID_P2010 0x0079 #define PCI_DEVICE_ID_P1020E 0x0100 #define PCI_DEVICE_ID_P1020 0x0101 +#define PCI_DEVICE_ID_P1021E 0x0102 +#define PCI_DEVICE_ID_P1021 0x0103 #define PCI_DEVICE_ID_P1011E 0x0108 #define PCI_DEVICE_ID_P1011 0x0109 #define PCI_DEVICE_ID_P1022E 0x0110 -- cgit v1.1 From ef5dc121d5a0bb1fa477c5395277259f07d318a3 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 2 Sep 2010 15:48:16 -0700 Subject: mutex: Fix annotations to include it in kernel-locking docbook Fix kernel-doc notation in linux/mutex.h and kernel/mutex.c, then add these 2 files to the kernel-locking docbook as the Mutex API reference chapter. Add one API function to mutex-design.txt and correct a typo in that file. Signed-off-by: Randy Dunlap Cc: Rusty Russell LKML-Reference: <20100902154816.6cc2f9ad.randy.dunlap@oracle.com> Signed-off-by: Ingo Molnar --- include/linux/mutex.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 878cab4..f363bc8 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -78,6 +78,14 @@ struct mutex_waiter { # include #else # define __DEBUG_MUTEX_INITIALIZER(lockname) +/** + * mutex_init - initialize the mutex + * @mutex: the mutex to be initialized + * + * Initialize the mutex to unlocked state. + * + * It is not allowed to initialize an already locked mutex. + */ # define mutex_init(mutex) \ do { \ static struct lock_class_key __key; \ -- cgit v1.1 From 71cad0554956de87c3fc413b1eac9313887eb14f Mon Sep 17 00:00:00 2001 From: Philippe Langlais Date: Tue, 31 Aug 2010 14:19:09 +0200 Subject: serial: fix port type conflict between NS16550A & U6_16550A Bug seen by Dr. David Alan Gilbert with sparse Signed-off-by: Philippe Langlais Cc: stable Signed-off-by: Greg Kroah-Hartman --- include/linux/serial.h | 3 +-- include/linux/serial_core.h | 3 ++- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial.h b/include/linux/serial.h index 1ebc694..ef91406 100644 --- a/include/linux/serial.h +++ b/include/linux/serial.h @@ -77,8 +77,7 @@ struct serial_struct { #define PORT_16654 11 #define PORT_16850 12 #define PORT_RSA 13 /* RSA-DV II/S card */ -#define PORT_U6_16550A 14 -#define PORT_MAX 14 +#define PORT_MAX 13 #define SERIAL_IO_PORT 0 #define SERIAL_IO_HUB6 1 diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 64458a9..563e234 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -44,7 +44,8 @@ #define PORT_RM9000 16 /* PMC-Sierra RM9xxx internal UART */ #define PORT_OCTEON 17 /* Cavium OCTEON internal UART */ #define PORT_AR7 18 /* Texas Instruments AR7 internal UART */ -#define PORT_MAX_8250 18 /* max port ID */ +#define PORT_U6_16550A 19 /* ST-Ericsson U6xxx internal UART */ +#define PORT_MAX_8250 19 /* max port ID */ /* * ARM specific type numbers. These are not currently guaranteed -- cgit v1.1 From 29bc17ecb856ffb2b47c7009a71971c6f9334205 Mon Sep 17 00:00:00 2001 From: Francisco Jerez Date: Sat, 4 Sep 2010 22:56:44 +0200 Subject: io-mapping: Fix the address space annotations Fixes a bunch of sparse warnings in io-mapping.h because of the inconsistent __iomem usage. Signed-off-by: Francisco Jerez LKML-Reference: <1283633804-11749-2-git-send-email-currojerez@riseup.net> Cc: Andrew Morton Signed-off-by: Ingo Molnar --- include/linux/io-mapping.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index 0a6b3d5..7fb5927 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -79,7 +79,7 @@ io_mapping_free(struct io_mapping *mapping) } /* Atomic map/unmap */ -static inline void * +static inline void __iomem * io_mapping_map_atomic_wc(struct io_mapping *mapping, unsigned long offset, int slot) @@ -94,12 +94,12 @@ io_mapping_map_atomic_wc(struct io_mapping *mapping, } static inline void -io_mapping_unmap_atomic(void *vaddr, int slot) +io_mapping_unmap_atomic(void __iomem *vaddr, int slot) { iounmap_atomic(vaddr, slot); } -static inline void * +static inline void __iomem * io_mapping_map_wc(struct io_mapping *mapping, unsigned long offset) { resource_size_t phys_addr; @@ -111,7 +111,7 @@ io_mapping_map_wc(struct io_mapping *mapping, unsigned long offset) } static inline void -io_mapping_unmap(void *vaddr) +io_mapping_unmap(void __iomem *vaddr) { iounmap(vaddr); } @@ -125,38 +125,38 @@ struct io_mapping; static inline struct io_mapping * io_mapping_create_wc(resource_size_t base, unsigned long size) { - return (struct io_mapping *) ioremap_wc(base, size); + return (struct io_mapping __force *) ioremap_wc(base, size); } static inline void io_mapping_free(struct io_mapping *mapping) { - iounmap(mapping); + iounmap((void __force __iomem *) mapping); } /* Atomic map/unmap */ -static inline void * +static inline void __iomem * io_mapping_map_atomic_wc(struct io_mapping *mapping, unsigned long offset, int slot) { - return ((char *) mapping) + offset; + return ((char __force __iomem *) mapping) + offset; } static inline void -io_mapping_unmap_atomic(void *vaddr, int slot) +io_mapping_unmap_atomic(void __iomem *vaddr, int slot) { } /* Non-atomic map/unmap */ -static inline void * +static inline void __iomem * io_mapping_map_wc(struct io_mapping *mapping, unsigned long offset) { - return ((char *) mapping) + offset; + return ((char __force __iomem *) mapping) + offset; } static inline void -io_mapping_unmap(void *vaddr) +io_mapping_unmap(void __iomem *vaddr) { } -- cgit v1.1 From f8f235e5bbf4e61f3e0886a44afb1dc4cfe8f337 Mon Sep 17 00:00:00 2001 From: Zhenyu Wang Date: Fri, 27 Aug 2010 11:08:57 +0800 Subject: agp/intel: Fix cache control for Sandybridge Sandybridge GTT has new cache control bits in PTE, which controls graphics page cache in LLC or LLC/MLC, so we need to extend the mask function to respect the new bits. And set cache control to always LLC only by default on Gen6. Signed-off-by: Zhenyu Wang Cc: stable@kernel.org Signed-off-by: Chris Wilson --- include/linux/intel-gtt.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) create mode 100644 include/linux/intel-gtt.h (limited to 'include/linux') diff --git a/include/linux/intel-gtt.h b/include/linux/intel-gtt.h new file mode 100644 index 0000000..1d19ab2 --- /dev/null +++ b/include/linux/intel-gtt.h @@ -0,0 +1,20 @@ +/* + * 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 febc88c5948f81114f64c3412011d695aecae233 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 7 Sep 2010 14:46:37 +0200 Subject: semaphore: Add DEFINE_SEMAPHORE The full cleanup of init_MUTEX[_LOCKED] and DECLARE_MUTEX has not been done. Some of the users are real semaphores and we should name them as such instead of confusing everyone with "MUTEX". Provide the infrastructure to get finally rid of init_MUTEX[_LOCKED] and DECLARE_MUTEX. Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Christoph Hellwig LKML-Reference: <20100907125054.795929962@linutronix.de> --- include/linux/semaphore.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/semaphore.h b/include/linux/semaphore.h index 7415839..5310d27 100644 --- a/include/linux/semaphore.h +++ b/include/linux/semaphore.h @@ -26,6 +26,9 @@ struct semaphore { .wait_list = LIST_HEAD_INIT((name).wait_list), \ } +#define DEFINE_SEMAPHORE(name) \ + struct semaphore name = __SEMAPHORE_INITIALIZER(name, 1) + #define DECLARE_MUTEX(name) \ struct semaphore name = __SEMAPHORE_INITIALIZER(name, 1) -- cgit v1.1 From 39aa3cb3e8250db9188a6f1e3fb62ffa1a717678 Mon Sep 17 00:00:00 2001 From: Stefan Bader Date: Tue, 31 Aug 2010 15:52:27 +0200 Subject: mm: Move vma_stack_continue into mm.h So it can be used by all that need to check for that. Signed-off-by: Stefan Bader Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index e6b1210..74949fb 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -864,6 +864,12 @@ int set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); int clear_page_dirty_for_io(struct page *page); +/* Is the vma a continuation of the stack vma above it? */ +static inline int vma_stack_continue(struct vm_area_struct *vma, unsigned long addr) +{ + return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN); +} + extern unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len); -- cgit v1.1 From a73f8844e1fc54c3762555c1cf1f71774142ca91 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Wed, 8 Sep 2010 16:54:54 -0600 Subject: lglock: make lg_lock_global() actually lock globally lg_lock_global() currently only acquires spinlocks for online CPUs, but it's meant to lock all possible CPUs. Lglock-protected resources may be associated with removed CPUs - and, indeed, that could happen with the per-superblock open files lists. At Nick's suggestion, change for_each_online_cpu() to for_each_possible_cpu() to protect accesses to those resources. Cc: Al Viro Acked-by: Nick Piggin Signed-off-by: Jonathan Corbet Signed-off-by: Linus Torvalds --- include/linux/lglock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lglock.h b/include/linux/lglock.h index b288cb7..f549056 100644 --- a/include/linux/lglock.h +++ b/include/linux/lglock.h @@ -150,7 +150,7 @@ int i; \ preempt_disable(); \ rwlock_acquire(&name##_lock_dep_map, 0, 0, _RET_IP_); \ - for_each_online_cpu(i) { \ + for_each_possible_cpu(i) { \ arch_spinlock_t *lock; \ lock = &per_cpu(name##_lock, i); \ arch_spin_lock(lock); \ @@ -161,7 +161,7 @@ void name##_global_unlock(void) { \ int i; \ rwlock_release(&name##_lock_dep_map, 1, _RET_IP_); \ - for_each_online_cpu(i) { \ + for_each_possible_cpu(i) { \ arch_spinlock_t *lock; \ lock = &per_cpu(name##_lock, i); \ arch_spin_unlock(lock); \ -- cgit v1.1 From f3c65b2870f2481f3646bc410a58a12989ecc704 Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Thu, 9 Sep 2010 16:37:24 -0700 Subject: mmc: avoid getting CID on SDIO-only cards The introduction of support for SD combo cards breaks the initialization of all CSR SDIO chips. The GO_IDLE (CMD0) in mmc_sd_get_cid() causes CSR chips to be reset (this is non-standard behavior). When initializing an SDIO card check for a combo card by using the memory present bit in the R4 response to IO_SEND_OP_COND (CMD5). This avoids the call to mmc_sd_get_cid() on an SDIO-only card. Signed-off-by: David Vrabel Acked-by: Michal Mirolaw Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmc/sdio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio.h b/include/linux/mmc/sdio.h index 329a8fa..245cdac 100644 --- a/include/linux/mmc/sdio.h +++ b/include/linux/mmc/sdio.h @@ -38,6 +38,8 @@ * [8:0] Byte/block count */ +#define R4_MEMORY_PRESENT (1 << 27) + /* SDIO status in R5 Type -- cgit v1.1 From e0bf1024b36be90da241af3c2767311e055b612c Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Thu, 9 Sep 2010 16:37:26 -0700 Subject: kfifo: add parenthesis for macro parameter reference Some macro parameter references inside typeof() operator are not enclosed with parenthesis. It should be safer to add them. Signed-off-by: Huang Ying Acked-by: Stefani Seibold Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfifo.h | 58 +++++++++++++++++++++++++-------------------------- 1 file changed, 29 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index 4aa95f2..62dbee5 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -214,7 +214,7 @@ __kfifo_must_check_helper(unsigned int val) */ #define kfifo_reset(fifo) \ (void)({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ __tmp->kfifo.in = __tmp->kfifo.out = 0; \ }) @@ -228,7 +228,7 @@ __kfifo_must_check_helper(unsigned int val) */ #define kfifo_reset_out(fifo) \ (void)({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ __tmp->kfifo.out = __tmp->kfifo.in; \ }) @@ -238,7 +238,7 @@ __kfifo_must_check_helper(unsigned int val) */ #define kfifo_len(fifo) \ ({ \ - typeof(fifo + 1) __tmpl = (fifo); \ + typeof((fifo) + 1) __tmpl = (fifo); \ __tmpl->kfifo.in - __tmpl->kfifo.out; \ }) @@ -248,7 +248,7 @@ __kfifo_must_check_helper(unsigned int val) */ #define kfifo_is_empty(fifo) \ ({ \ - typeof(fifo + 1) __tmpq = (fifo); \ + typeof((fifo) + 1) __tmpq = (fifo); \ __tmpq->kfifo.in == __tmpq->kfifo.out; \ }) @@ -258,7 +258,7 @@ __kfifo_must_check_helper(unsigned int val) */ #define kfifo_is_full(fifo) \ ({ \ - typeof(fifo + 1) __tmpq = (fifo); \ + typeof((fifo) + 1) __tmpq = (fifo); \ kfifo_len(__tmpq) > __tmpq->kfifo.mask; \ }) @@ -269,7 +269,7 @@ __kfifo_must_check_helper(unsigned int val) #define kfifo_avail(fifo) \ __kfifo_must_check_helper( \ ({ \ - typeof(fifo + 1) __tmpq = (fifo); \ + typeof((fifo) + 1) __tmpq = (fifo); \ const size_t __recsize = sizeof(*__tmpq->rectype); \ unsigned int __avail = kfifo_size(__tmpq) - kfifo_len(__tmpq); \ (__recsize) ? ((__avail <= __recsize) ? 0 : \ @@ -284,7 +284,7 @@ __kfifo_must_check_helper( \ */ #define kfifo_skip(fifo) \ (void)({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ if (__recsize) \ @@ -302,7 +302,7 @@ __kfifo_must_check_helper( \ #define kfifo_peek_len(fifo) \ __kfifo_must_check_helper( \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ (!__recsize) ? kfifo_len(__tmp) * sizeof(*__tmp->type) : \ @@ -325,7 +325,7 @@ __kfifo_must_check_helper( \ #define kfifo_alloc(fifo, size, gfp_mask) \ __kfifo_must_check_helper( \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ __is_kfifo_ptr(__tmp) ? \ __kfifo_alloc(__kfifo, size, sizeof(*__tmp->type), gfp_mask) : \ @@ -339,7 +339,7 @@ __kfifo_must_check_helper( \ */ #define kfifo_free(fifo) \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ if (__is_kfifo_ptr(__tmp)) \ __kfifo_free(__kfifo); \ @@ -358,7 +358,7 @@ __kfifo_must_check_helper( \ */ #define kfifo_init(fifo, buffer, size) \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ __is_kfifo_ptr(__tmp) ? \ __kfifo_init(__kfifo, buffer, size, sizeof(*__tmp->type)) : \ @@ -379,8 +379,8 @@ __kfifo_must_check_helper( \ */ #define kfifo_put(fifo, val) \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ - typeof(val + 1) __val = (val); \ + typeof((fifo) + 1) __tmp = (fifo); \ + typeof((val) + 1) __val = (val); \ unsigned int __ret; \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ @@ -421,8 +421,8 @@ __kfifo_must_check_helper( \ #define kfifo_get(fifo, val) \ __kfifo_must_check_helper( \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ - typeof(val + 1) __val = (val); \ + typeof((fifo) + 1) __tmp = (fifo); \ + typeof((val) + 1) __val = (val); \ unsigned int __ret; \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ @@ -462,8 +462,8 @@ __kfifo_must_check_helper( \ #define kfifo_peek(fifo, val) \ __kfifo_must_check_helper( \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ - typeof(val + 1) __val = (val); \ + typeof((fifo) + 1) __tmp = (fifo); \ + typeof((val) + 1) __val = (val); \ unsigned int __ret; \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ @@ -501,8 +501,8 @@ __kfifo_must_check_helper( \ */ #define kfifo_in(fifo, buf, n) \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ - typeof(buf + 1) __buf = (buf); \ + typeof((fifo) + 1) __tmp = (fifo); \ + typeof((buf) + 1) __buf = (buf); \ unsigned long __n = (n); \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ @@ -554,8 +554,8 @@ __kfifo_must_check_helper( \ #define kfifo_out(fifo, buf, n) \ __kfifo_must_check_helper( \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ - typeof(buf + 1) __buf = (buf); \ + typeof((fifo) + 1) __tmp = (fifo); \ + typeof((buf) + 1) __buf = (buf); \ unsigned long __n = (n); \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ @@ -611,7 +611,7 @@ __kfifo_must_check_helper( \ #define kfifo_from_user(fifo, from, len, copied) \ __kfifo_must_check_helper( \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ const void __user *__from = (from); \ unsigned int __len = (len); \ unsigned int *__copied = (copied); \ @@ -639,7 +639,7 @@ __kfifo_must_check_helper( \ #define kfifo_to_user(fifo, to, len, copied) \ __kfifo_must_check_helper( \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ void __user *__to = (to); \ unsigned int __len = (len); \ unsigned int *__copied = (copied); \ @@ -666,7 +666,7 @@ __kfifo_must_check_helper( \ */ #define kfifo_dma_in_prepare(fifo, sgl, nents, len) \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ struct scatterlist *__sgl = (sgl); \ int __nents = (nents); \ unsigned int __len = (len); \ @@ -690,7 +690,7 @@ __kfifo_must_check_helper( \ */ #define kfifo_dma_in_finish(fifo, len) \ (void)({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ unsigned int __len = (len); \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ @@ -717,7 +717,7 @@ __kfifo_must_check_helper( \ */ #define kfifo_dma_out_prepare(fifo, sgl, nents, len) \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ struct scatterlist *__sgl = (sgl); \ int __nents = (nents); \ unsigned int __len = (len); \ @@ -741,7 +741,7 @@ __kfifo_must_check_helper( \ */ #define kfifo_dma_out_finish(fifo, len) \ (void)({ \ - typeof(fifo + 1) __tmp = (fifo); \ + typeof((fifo) + 1) __tmp = (fifo); \ unsigned int __len = (len); \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ @@ -766,8 +766,8 @@ __kfifo_must_check_helper( \ #define kfifo_out_peek(fifo, buf, n) \ __kfifo_must_check_helper( \ ({ \ - typeof(fifo + 1) __tmp = (fifo); \ - typeof(buf + 1) __buf = (buf); \ + typeof((fifo) + 1) __tmp = (fifo); \ + typeof((buf) + 1) __buf = (buf); \ unsigned long __n = (n); \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ -- cgit v1.1 From 31583bb0cf6cc40f2a468a4d2f3b9cbefd24f891 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Thu, 9 Sep 2010 16:37:37 -0700 Subject: cgroups: fix API thinko Add cgroup_attach_task_all() The existing cgroup_attach_task_current_cg() API is called by a thread to attach another thread to all of its cgroups; this is unsuitable for cases where a privileged task wants to attach itself to the cgroups of a less privileged one, since the call must be made from the context of the target task. This patch adds a more generic cgroup_attach_task_all() API that allows both the source task and to-be-moved task to be specified. cgroup_attach_task_current_cg() becomes a specialization of the more generic new function. [menage@google.com: rewrote changelog] [akpm@linux-foundation.org: address reviewer comments] Signed-off-by: Michael S. Tsirkin Tested-by: Alex Williamson Acked-by: Paul Menage Cc: Li Zefan Cc: Ben Blum Cc: Sridhar Samudrala Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index ed3e92e..0c99102 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -578,7 +578,12 @@ struct task_struct *cgroup_iter_next(struct cgroup *cgrp, void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it); int cgroup_scan_tasks(struct cgroup_scanner *scan); int cgroup_attach_task(struct cgroup *, struct task_struct *); -int cgroup_attach_task_current_cg(struct task_struct *); +int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); + +static inline int cgroup_attach_task_current_cg(struct task_struct *tsk) +{ + return cgroup_attach_task_all(current, tsk); +} /* * CSS ID is ID for cgroup_subsys_state structs under subsys. This only works @@ -636,6 +641,11 @@ static inline int cgroupstats_build(struct cgroupstats *stats, } /* No cgroups - nothing to do */ +static inline int cgroup_attach_task_all(struct task_struct *from, + struct task_struct *t) +{ + return 0; +} static inline int cgroup_attach_task_current_cg(struct task_struct *t) { return 0; -- cgit v1.1 From 4969c1192d15afa3389e7ae3302096ff684ba655 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 9 Sep 2010 16:37:52 -0700 Subject: mm: fix swapin race condition The pte_same check is reliable only if the swap entry remains pinned (by the page lock on swapcache). We've also to ensure the swapcache isn't removed before we take the lock as try_to_free_swap won't care about the page pin. One of the possible impacts of this patch is that a KSM-shared page can point to the anon_vma of another process, which could exit before the page is freed. This can leave a page with a pointer to a recycled anon_vma object, or worse, a pointer to something that is no longer an anon_vma. [riel@redhat.com: changelog help] Signed-off-by: Andrea Arcangeli Acked-by: Hugh Dickins Reviewed-by: Rik van Riel Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ksm.h | 20 +++++++++----------- 1 file changed, 9 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 74d691e..3319a69 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -16,6 +16,9 @@ struct stable_node; struct mem_cgroup; +struct page *ksm_does_need_to_copy(struct page *page, + struct vm_area_struct *vma, unsigned long address); + #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags); @@ -70,19 +73,14 @@ static inline void set_page_stable_node(struct page *page, * We'd like to make this conditional on vma->vm_flags & VM_MERGEABLE, * but what if the vma was unmerged while the page was swapped out? */ -struct page *ksm_does_need_to_copy(struct page *page, - struct vm_area_struct *vma, unsigned long address); -static inline struct page *ksm_might_need_to_copy(struct page *page, +static inline int ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address) { struct anon_vma *anon_vma = page_anon_vma(page); - if (!anon_vma || - (anon_vma->root == vma->anon_vma->root && - page->index == linear_page_index(vma, address))) - return page; - - return ksm_does_need_to_copy(page, vma, address); + return anon_vma && + (anon_vma->root != vma->anon_vma->root || + page->index != linear_page_index(vma, address)); } int page_referenced_ksm(struct page *page, @@ -115,10 +113,10 @@ static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start, return 0; } -static inline struct page *ksm_might_need_to_copy(struct page *page, +static inline int ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address) { - return page; + return 0; } static inline int page_referenced_ksm(struct page *page, -- cgit v1.1 From 5affb607720d734ca572b8a77c5c7d62d3042b6f Mon Sep 17 00:00:00 2001 From: Gregory Bean Date: Thu, 9 Sep 2010 16:38:02 -0700 Subject: gpio: sx150x: correct and refine reset-on-probe behavior Replace the arbitrary software-reset call from the device-probe method, because: - It is defective. To work correctly, it should be two byte writes, not a single word write. As it stands, it does nothing. - Some devices with sx150x expanders installed have their NRESET pins ganged on the same line, so resetting one causes the others to reset - not a nice thing to do arbitrarily! - The probe, usually taking place at boot, implies a recent hard-reset, so a software reset at this point is just a waste of energy anyway. Therefore, make it optional, defaulting to off, as this will match the common case of probing at powerup and also matches the current broken no-op behavior. Signed-off-by: Gregory Bean Reviewed-by: Jean Delvare Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/i2c/sx150x.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i2c/sx150x.h b/include/linux/i2c/sx150x.h index ee3049c..52baa79 100644 --- a/include/linux/i2c/sx150x.h +++ b/include/linux/i2c/sx150x.h @@ -63,6 +63,9 @@ * IRQ lines will appear. Similarly to gpio_base, the expander * will create a block of irqs beginning at this number. * This value is ignored if irq_summary is < 0. + * @reset_during_probe: If set to true, the driver will trigger a full + * reset of the chip at the beginning of the probe + * in order to place it in a known state. */ struct sx150x_platform_data { unsigned gpio_base; @@ -73,6 +76,7 @@ struct sx150x_platform_data { u16 io_polarity; int irq_summary; unsigned irq_base; + bool reset_during_probe; }; #endif /* __LINUX_I2C_SX150X_H */ -- cgit v1.1 From 910321ea817a202ff70fac666e37e2c8e2f88823 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 9 Sep 2010 16:38:07 -0700 Subject: swap: revert special hibernation allocation Please revert 2.6.36-rc commit d2997b1042ec150616c1963b5e5e919ffd0b0ebf "hibernation: freeze swap at hibernation". It complicated matters by adding a second swap allocation path, just for hibernation; without in any way fixing the issue that it was intended to address - page reclaim after fixing the hibernation image might free swap from a page already imaged as swapcache, letting its swap be reallocated to store a different page of the image: resulting in data corruption if the imaged page were freed as clean then swapped back in. Pages freed to si->swap_map were still in danger of being reallocated by the alternative allocation path. I guess it inadvertently fixed slow SSD swap allocation for hibernation, as reported by Nigel Cunningham: by missing out the discards that occur on the usual swap allocation path; but that was unintentional, and needs a separate fix. Signed-off-by: Hugh Dickins Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Cc: "Rafael J. Wysocki" Cc: Ondrej Zary Cc: Andrea Gelmini Cc: Balbir Singh Cc: Andrea Arcangeli Cc: Nigel Cunningham Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 2fee51a..bf4eb62 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -315,6 +315,7 @@ extern long nr_swap_pages; extern long total_swap_pages; extern void si_swapinfo(struct sysinfo *); extern swp_entry_t get_swap_page(void); +extern swp_entry_t get_swap_page_of_type(int); extern int valid_swaphandles(swp_entry_t, unsigned long *); extern int add_swap_count_continuation(swp_entry_t, gfp_t); extern void swap_shmem_alloc(swp_entry_t); @@ -331,13 +332,6 @@ extern int reuse_swap_page(struct page *); extern int try_to_free_swap(struct page *); struct backing_dev_info; -#ifdef CONFIG_HIBERNATION -void hibernation_freeze_swap(void); -void hibernation_thaw_swap(void); -swp_entry_t get_swap_for_hibernation(int type); -void swap_free_for_hibernation(swp_entry_t val); -#endif - /* linux/mm/thrash.c */ extern struct mm_struct *swap_token_mm; extern void grab_swap_token(struct mm_struct *); -- cgit v1.1 From 3399446632739fcd05fd8b272b476a69c6e6d14a Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 9 Sep 2010 16:38:11 -0700 Subject: swap: discard while swapping only if SWAP_FLAG_DISCARD Tests with recent firmware on Intel X25-M 80GB and OCZ Vertex 60GB SSDs show a shift since I last tested in December: in part because of firmware updates, in part because of the necessary move from barriers to awaiting completion at the block layer. While discard at swapon still shows as slightly beneficial on both, discarding 1MB swap cluster when allocating is now disadvanteous: adds 25% overhead on Intel, adds 230% on OCZ (YMMV). Surrender: discard as presently implemented is more hindrance than help for swap; but might prove useful on other devices, or with improvements. So continue to do the discard at swapon, but make discard while swapping conditional on a SWAP_FLAG_DISCARD to sys_swapon() (which has been using only the lower 16 bits of int flags). We can add a --discard or -d to swapon(8), and a "discard" to swap in /etc/fstab: matching the mount option for btrfs, ext4, fat, gfs2, nilfs2. Signed-off-by: Hugh Dickins Cc: Christoph Hellwig Cc: Nigel Cunningham Cc: Tejun Heo Cc: Jens Axboe Cc: James Bottomley Cc: "Martin K. Petersen" Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index bf4eb62..7cdd633 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -19,6 +19,7 @@ struct bio; #define SWAP_FLAG_PREFER 0x8000 /* set if swap priority specified */ #define SWAP_FLAG_PRIO_MASK 0x7fff #define SWAP_FLAG_PRIO_SHIFT 0 +#define SWAP_FLAG_DISCARD 0x10000 /* discard swap cluster after use */ static inline int current_is_kswapd(void) { @@ -142,7 +143,7 @@ struct swap_extent { enum { SWP_USED = (1 << 0), /* is slot in swap_info[] used? */ SWP_WRITEOK = (1 << 1), /* ok to write to this swap? */ - SWP_DISCARDABLE = (1 << 2), /* blkdev supports discard */ + SWP_DISCARDABLE = (1 << 2), /* swapon+blkdev support discard */ SWP_DISCARDING = (1 << 3), /* now discarding a free cluster */ SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */ SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */ -- cgit v1.1 From aa45484031ddee09b06350ab8528bfe5b2c76d1c Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 9 Sep 2010 16:38:17 -0700 Subject: mm: page allocator: calculate a better estimate of NR_FREE_PAGES when memory is low and kswapd is awake Ordinarily watermark checks are based on the vmstat NR_FREE_PAGES as it is cheaper than scanning a number of lists. To avoid synchronization overhead, counter deltas are maintained on a per-cpu basis and drained both periodically and when the delta is above a threshold. On large CPU systems, the difference between the estimated and real value of NR_FREE_PAGES can be very high. If NR_FREE_PAGES is much higher than number of real free page in buddy, the VM can allocate pages below min watermark, at worst reducing the real number of pages to zero. Even if the OOM killer kills some victim for freeing memory, it may not free memory if the exit path requires a new page resulting in livelock. This patch introduces a zone_page_state_snapshot() function (courtesy of Christoph) that takes a slightly more accurate view of an arbitrary vmstat counter. It is used to read NR_FREE_PAGES while kswapd is awake to avoid the watermark being accidentally broken. The estimate is not perfect and may result in cache line bounces but is expected to be lighter than the IPI calls necessary to continually drain the per-cpu counters while kswapd is awake. Signed-off-by: Christoph Lameter Signed-off-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 13 +++++++++++++ include/linux/vmstat.h | 22 ++++++++++++++++++++++ 2 files changed, 35 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 6e6e626..3984c4e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -284,6 +284,13 @@ struct zone { unsigned long watermark[NR_WMARK]; /* + * When free pages are below this point, additional steps are taken + * when reading the number of free pages to avoid per-cpu counter + * drift allowing watermarks to be breached + */ + unsigned long percpu_drift_mark; + + /* * We don't know if the memory that we're going to allocate will be freeable * or/and it will be released eventually, so to avoid totally wasting several * GB of ram we must reserve some of the lower zone memory (otherwise we risk @@ -441,6 +448,12 @@ 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 diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 7f43ccd..eaaea37 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -170,6 +170,28 @@ static inline unsigned long zone_page_state(struct zone *zone, return x; } +/* + * More accurate version that also considers the currently pending + * deltas. For that we need to loop over all cpus to find the current + * deltas. There is no synchronization so the result cannot be + * exactly accurate either. + */ +static inline unsigned long zone_page_state_snapshot(struct zone *zone, + enum zone_stat_item item) +{ + long x = atomic_long_read(&zone->vm_stat[item]); + +#ifdef CONFIG_SMP + int cpu; + for_each_online_cpu(cpu) + x += per_cpu_ptr(zone->pageset, cpu)->vm_stat_diff[item]; + + if (x < 0) + x = 0; +#endif + return x; +} + extern unsigned long global_reclaimable_pages(void); extern unsigned long zone_reclaimable_pages(struct zone *zone); -- cgit v1.1 From e2f3d75fc0e4a0d03c61872bad39ffa2e74a04ff Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 7 Sep 2010 14:05:31 +0200 Subject: libata: skip EH autopsy and recovery during suspend For some mysterious reason, certain hardware reacts badly to usual EH actions while the system is going for suspend. As the devices won't be needed until the system is resumed, ask EH to skip usual autopsy and recovery and proceed directly to suspend. Signed-off-by: Tejun Heo Tested-by: Stephan Diestelhorst Cc: stable@kernel.org Signed-off-by: Jeff Garzik --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index f010f18..7de282d 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -335,6 +335,7 @@ enum { ATA_EHI_HOTPLUGGED = (1 << 0), /* could have been hotplugged */ ATA_EHI_NO_AUTOPSY = (1 << 2), /* no autopsy */ ATA_EHI_QUIET = (1 << 3), /* be quiet */ + ATA_EHI_NO_RECOVERY = (1 << 4), /* no recovery */ ATA_EHI_DID_SOFTRESET = (1 << 16), /* already soft-reset this port */ ATA_EHI_DID_HARDRESET = (1 << 17), /* already soft-reset this port */ -- cgit v1.1 From ea3c64506ea7965f86f030155e6fdef381de10e2 Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Tue, 31 Aug 2010 16:20:36 -0700 Subject: libata-sff: Reenable Port Multiplier after libata-sff remodeling. Keep track of the link on the which the current request is in progress. It allows support of links behind port multiplier. Not all libata-sff is PMP compliant. Code for native BMDMA controller does not take in accound PMP. Tested on Marvell 7042 and Sil7526. Signed-off-by: Gwendal Grignou Signed-off-by: Jeff Garzik --- include/linux/libata.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 7de282d..45fb296 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -724,6 +724,7 @@ struct ata_port { struct ata_ioports ioaddr; /* ATA cmd/ctl/dma register blocks */ u8 ctl; /* cache of ATA control register */ u8 last_ctl; /* Cache last written value */ + struct ata_link* sff_pio_task_link; /* link currently used */ struct delayed_work sff_pio_task; #ifdef CONFIG_ATA_BMDMA struct ata_bmdma_prd *bmdma_prd; /* BMDMA SG list */ @@ -1595,7 +1596,7 @@ extern void ata_sff_irq_on(struct ata_port *ap); extern void ata_sff_irq_clear(struct ata_port *ap); extern int ata_sff_hsm_move(struct ata_port *ap, struct ata_queued_cmd *qc, u8 status, int in_wq); -extern void ata_sff_queue_pio_task(struct ata_port *ap, unsigned long delay); +extern void ata_sff_queue_pio_task(struct ata_link *link, unsigned long delay); extern unsigned int ata_sff_qc_issue(struct ata_queued_cmd *qc); extern bool ata_sff_qc_fill_rtf(struct ata_queued_cmd *qc); extern unsigned int ata_sff_port_intr(struct ata_port *ap, -- cgit v1.1 From 006abe887c5e637d059c44310de6c92f36aded3b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 12 Sep 2010 19:55:25 -0400 Subject: SUNRPC: Fix a race in rpc_info_open There is a race between rpc_info_open and rpc_release_client() in that nothing stops a process from opening the file after the clnt->cl_kref goes to zero. Fix this by using atomic_inc_unless_zero()... Reported-by: J. Bruce Fields Signed-off-by: Trond Myklebust Cc: stable@kernel.org --- include/linux/sunrpc/clnt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 569dc72..85f38a63 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -30,7 +30,7 @@ struct rpc_inode; * The high-level client handle */ struct rpc_clnt { - struct kref cl_kref; /* Number of references */ + atomic_t cl_count; /* Number of references */ struct list_head cl_clients; /* Global list of clients */ struct list_head cl_tasks; /* List of tasks */ spinlock_t cl_lock; /* spinlock */ -- cgit v1.1