diff options
Diffstat (limited to 'drivers/xen')
| -rw-r--r-- | drivers/xen/Kconfig | 21 | ||||
| -rw-r--r-- | drivers/xen/Makefile | 6 | ||||
| -rw-r--r-- | drivers/xen/balloon.c | 47 | ||||
| -rw-r--r-- | drivers/xen/cpu_hotplug.c | 3 | ||||
| -rw-r--r-- | drivers/xen/events.c | 120 | ||||
| -rw-r--r-- | drivers/xen/evtchn.c | 4 | ||||
| -rw-r--r-- | drivers/xen/grant-table.c | 79 | ||||
| -rw-r--r-- | drivers/xen/manage.c | 82 | ||||
| -rw-r--r-- | drivers/xen/platform-pci.c | 207 | ||||
| -rw-r--r-- | drivers/xen/sys-hypervisor.c | 4 | ||||
| -rw-r--r-- | drivers/xen/xenbus/xenbus_client.c | 1 | ||||
| -rw-r--r-- | drivers/xen/xenbus/xenbus_probe.c | 103 | ||||
| -rw-r--r-- | drivers/xen/xenbus/xenbus_xs.c | 2 | ||||
| -rw-r--r-- | drivers/xen/xencomm.c | 2 | ||||
| -rw-r--r-- | drivers/xen/xenfs/super.c | 6 | ||||
| -rw-r--r-- | drivers/xen/xenfs/xenbus.c | 2 |
16 files changed, 565 insertions, 124 deletions
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index cab100a..0a88269 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -1,6 +1,8 @@ +menu "Xen driver support" + depends on XEN + config XEN_BALLOON bool "Xen memory balloon driver" - depends on XEN default y help The balloon driver allows the Xen domain to request more memory from @@ -20,7 +22,6 @@ config XEN_SCRUB_PAGES config XEN_DEV_EVTCHN tristate "Xen /dev/xen/evtchn device" - depends on XEN default y help The evtchn driver allows a userspace process to triger event @@ -30,7 +31,6 @@ config XEN_DEV_EVTCHN config XENFS tristate "Xen filesystem" - depends on XEN default y help The xen filesystem provides a way for domains to share @@ -53,11 +53,22 @@ config XEN_COMPAT_XENFS config XEN_SYS_HYPERVISOR bool "Create xen entries under /sys/hypervisor" - depends on XEN && SYSFS + depends on SYSFS select SYS_HYPERVISOR default y help Create entries under /sys/hypervisor describing the Xen hypervisor environment. When running native or in another virtual environment, /sys/hypervisor will still be present, - but will have no xen contents.
\ No newline at end of file + but will have no xen contents. + +config XEN_PLATFORM_PCI + tristate "xen platform pci device driver" + depends on XEN_PVHVM + default m + help + Driver for the Xen PCI Platform device: it is responsible for + initializing xenbus and grant_table when running in a Xen HVM + domain. As a consequence this driver is required to run any Xen PV + frontend on Xen HVM. +endmenu diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile index ec2a39b..e392fb7 100644 --- a/drivers/xen/Makefile +++ b/drivers/xen/Makefile @@ -1,9 +1,13 @@ obj-y += grant-table.o features.o events.o manage.o obj-y += xenbus/ +nostackp := $(call cc-option, -fno-stack-protector) +CFLAGS_features.o := $(nostackp) + obj-$(CONFIG_HOTPLUG_CPU) += cpu_hotplug.o obj-$(CONFIG_XEN_XENCOMM) += xencomm.o obj-$(CONFIG_XEN_BALLOON) += balloon.o obj-$(CONFIG_XEN_DEV_EVTCHN) += evtchn.o obj-$(CONFIG_XENFS) += xenfs/ -obj-$(CONFIG_XEN_SYS_HYPERVISOR) += sys-hypervisor.o
\ No newline at end of file +obj-$(CONFIG_XEN_SYS_HYPERVISOR) += sys-hypervisor.o +obj-$(CONFIG_XEN_PLATFORM_PCI) += platform-pci.o diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index f5bbd9e..1a0d8c2 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -43,6 +43,7 @@ #include <linux/mutex.h> #include <linux/list.h> #include <linux/sysdev.h> +#include <linux/gfp.h> #include <asm/page.h> #include <asm/pgalloc.h> @@ -52,6 +53,8 @@ #include <asm/xen/hypervisor.h> #include <asm/xen/hypercall.h> + +#include <xen/xen.h> #include <xen/interface/xen.h> #include <xen/interface/memory.h> #include <xen/xenbus.h> @@ -66,8 +69,6 @@ struct balloon_stats { /* We aim for 'current allocation' == 'target allocation'. */ unsigned long current_pages; unsigned long target_pages; - /* We may hit the hard limit in Xen. If we do then we remember it. */ - unsigned long hard_limit; /* * Drivers may alter the memory reservation independently, but they * must inform the balloon driver so we avoid hitting the hard limit. @@ -96,11 +97,7 @@ static struct balloon_stats balloon_stats; /* We increase/decrease in batches which fit in a page */ static unsigned long frame_list[PAGE_SIZE / sizeof(unsigned long)]; -/* VM /proc information for memory */ -extern unsigned long totalram_pages; - #ifdef CONFIG_HIGHMEM -extern unsigned long totalhigh_pages; #define inc_totalhigh_pages() (totalhigh_pages++) #define dec_totalhigh_pages() (totalhigh_pages--) #else @@ -140,6 +137,8 @@ static void balloon_append(struct page *page) list_add(&page->lru, &ballooned_pages); balloon_stats.balloon_low++; } + + totalram_pages--; } /* balloon_retrieve: rescue a page from the balloon, if it is not empty. */ @@ -160,6 +159,8 @@ static struct page *balloon_retrieve(void) else balloon_stats.balloon_low--; + totalram_pages++; + return page; } @@ -185,7 +186,7 @@ static void balloon_alarm(unsigned long unused) static unsigned long current_target(void) { - unsigned long target = min(balloon_stats.target_pages, balloon_stats.hard_limit); + unsigned long target = balloon_stats.target_pages; target = min(target, balloon_stats.current_pages + @@ -214,30 +215,17 @@ static int increase_reservation(unsigned long nr_pages) page = balloon_first_page(); for (i = 0; i < nr_pages; i++) { BUG_ON(page == NULL); - frame_list[i] = page_to_pfn(page);; + frame_list[i] = page_to_pfn(page); page = balloon_next_page(page); } set_xen_guest_handle(reservation.extent_start, frame_list); reservation.nr_extents = nr_pages; rc = HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation); - if (rc < nr_pages) { - if (rc > 0) { - int ret; - - /* We hit the Xen hard limit: reprobe. */ - reservation.nr_extents = rc; - ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation, - &reservation); - BUG_ON(ret != rc); - } - if (rc >= 0) - balloon_stats.hard_limit = (balloon_stats.current_pages + rc - - balloon_stats.driver_pages); + if (rc < 0) goto out; - } - for (i = 0; i < nr_pages; i++) { + for (i = 0; i < rc; i++) { page = balloon_retrieve(); BUG_ON(page == NULL); @@ -263,13 +251,12 @@ static int increase_reservation(unsigned long nr_pages) __free_page(page); } - balloon_stats.current_pages += nr_pages; - totalram_pages = balloon_stats.current_pages; + balloon_stats.current_pages += rc; out: spin_unlock_irqrestore(&balloon_lock, flags); - return 0; + return rc < 0 ? rc : rc != nr_pages; } static int decrease_reservation(unsigned long nr_pages) @@ -327,7 +314,6 @@ static int decrease_reservation(unsigned long nr_pages) BUG_ON(ret != nr_pages); balloon_stats.current_pages -= nr_pages; - totalram_pages = balloon_stats.current_pages; spin_unlock_irqrestore(&balloon_lock, flags); @@ -371,7 +357,6 @@ static void balloon_process(struct work_struct *work) static void balloon_set_new_target(unsigned long target) { /* No need for lock. Not read-modify-write updates. */ - balloon_stats.hard_limit = ~0UL; balloon_stats.target_pages = target; schedule_work(&balloon_worker); } @@ -426,12 +411,10 @@ static int __init balloon_init(void) pr_info("xen_balloon: Initialising balloon driver.\n"); balloon_stats.current_pages = min(xen_start_info->nr_pages, max_pfn); - totalram_pages = balloon_stats.current_pages; balloon_stats.target_pages = balloon_stats.current_pages; balloon_stats.balloon_low = 0; balloon_stats.balloon_high = 0; balloon_stats.driver_pages = 0UL; - balloon_stats.hard_limit = ~0UL; init_timer(&balloon_timer); balloon_timer.data = 0; @@ -476,9 +459,6 @@ module_exit(balloon_exit); BALLOON_SHOW(current_kb, "%lu\n", PAGES2KB(balloon_stats.current_pages)); BALLOON_SHOW(low_kb, "%lu\n", PAGES2KB(balloon_stats.balloon_low)); BALLOON_SHOW(high_kb, "%lu\n", PAGES2KB(balloon_stats.balloon_high)); -BALLOON_SHOW(hard_limit_kb, - (balloon_stats.hard_limit!=~0UL) ? "%lu\n" : "???\n", - (balloon_stats.hard_limit!=~0UL) ? PAGES2KB(balloon_stats.hard_limit) : 0); BALLOON_SHOW(driver_kb, "%lu\n", PAGES2KB(balloon_stats.driver_pages)); static ssize_t show_target_kb(struct sys_device *dev, struct sysdev_attribute *attr, @@ -548,7 +528,6 @@ static struct attribute *balloon_info_attrs[] = { &attr_current_kb.attr, &attr_low_kb.attr, &attr_high_kb.attr, - &attr_hard_limit_kb.attr, &attr_driver_kb.attr, NULL }; diff --git a/drivers/xen/cpu_hotplug.c b/drivers/xen/cpu_hotplug.c index bdfd584..14e2d99 100644 --- a/drivers/xen/cpu_hotplug.c +++ b/drivers/xen/cpu_hotplug.c @@ -1,5 +1,6 @@ #include <linux/notifier.h> +#include <xen/xen.h> #include <xen/xenbus.h> #include <asm/xen/hypervisor.h> @@ -86,7 +87,7 @@ static int setup_cpu_watcher(struct notifier_block *notifier, for_each_possible_cpu(cpu) { if (vcpu_online(cpu) == 0) { (void)cpu_down(cpu); - cpu_clear(cpu, cpu_present_map); + set_cpu_present(cpu, false); } } diff --git a/drivers/xen/events.c b/drivers/xen/events.c index abad71b..5e1f348 100644 --- a/drivers/xen/events.c +++ b/drivers/xen/events.c @@ -27,7 +27,9 @@ #include <linux/module.h> #include <linux/string.h> #include <linux/bootmem.h> +#include <linux/slab.h> +#include <asm/desc.h> #include <asm/ptrace.h> #include <asm/irq.h> #include <asm/idle.h> @@ -35,10 +37,14 @@ #include <asm/xen/hypercall.h> #include <asm/xen/hypervisor.h> +#include <xen/xen.h> +#include <xen/hvm.h> #include <xen/xen-ops.h> #include <xen/events.h> #include <xen/interface/xen.h> #include <xen/interface/event_channel.h> +#include <xen/interface/hvm/hvm_op.h> +#include <xen/interface/hvm/params.h> /* * This lock protects updates to the following mapping and reference-count @@ -47,10 +53,10 @@ static DEFINE_SPINLOCK(irq_mapping_update_lock); /* IRQ <-> VIRQ mapping. */ -static DEFINE_PER_CPU(int, virq_to_irq[NR_VIRQS]) = {[0 ... NR_VIRQS-1] = -1}; +static DEFINE_PER_CPU(int [NR_VIRQS], virq_to_irq) = {[0 ... NR_VIRQS-1] = -1}; /* IRQ <-> IPI mapping */ -static DEFINE_PER_CPU(int, ipi_to_irq[XEN_NR_IPIS]) = {[0 ... XEN_NR_IPIS-1] = -1}; +static DEFINE_PER_CPU(int [XEN_NR_IPIS], ipi_to_irq) = {[0 ... XEN_NR_IPIS-1] = -1}; /* Interrupt types. */ enum xen_irq_type { @@ -334,9 +340,18 @@ static int find_unbound_irq(void) int irq; struct irq_desc *desc; - for (irq = 0; irq < nr_irqs; irq++) + for (irq = 0; irq < nr_irqs; irq++) { + desc = irq_to_desc(irq); + /* only 0->15 have init'd desc; handle irq > 16 */ + if (desc == NULL) + break; + if (desc->chip == &no_irq_chip) + break; + if (desc->chip != &xen_dynamic_chip) + continue; if (irq_info[irq].type == IRQT_UNBOUND) break; + } if (irq == nr_irqs) panic("No available IRQ to bind to: increase nr_irqs!\n"); @@ -345,7 +360,7 @@ static int find_unbound_irq(void) if (WARN_ON(desc == NULL)) return -1; - dynamic_irq_init(irq); + dynamic_irq_init_keep_chip_data(irq); return irq; } @@ -474,6 +489,9 @@ static void unbind_from_irq(unsigned int irq) bind_evtchn_to_cpu(evtchn, 0); evtchn_to_irq[evtchn] = -1; + } + + if (irq_info[irq].type != IRQT_UNBOUND) { irq_info[irq] = mk_unbound_info(); dynamic_irq_cleanup(irq); @@ -602,6 +620,8 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } +static DEFINE_PER_CPU(unsigned, xed_nesting_count); + /* * Search the CPUs pending events bitmasks. For each one found, map * the event number to an irq, and feed it into do_IRQ() for @@ -611,24 +631,19 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id) * a bitset of words which contain pending event bits. The second * level is a bitset of pending events themselves. */ -void xen_evtchn_do_upcall(struct pt_regs *regs) +static void __xen_evtchn_do_upcall(void) { int cpu = get_cpu(); - struct pt_regs *old_regs = set_irq_regs(regs); struct shared_info *s = HYPERVISOR_shared_info; struct vcpu_info *vcpu_info = __get_cpu_var(xen_vcpu); - static DEFINE_PER_CPU(unsigned, nesting_count); unsigned count; - exit_idle(); - irq_enter(); - do { unsigned long pending_words; vcpu_info->evtchn_upcall_pending = 0; - if (__get_cpu_var(nesting_count)++) + if (__get_cpu_var(xed_nesting_count)++) goto out; #ifndef CONFIG_X86 /* No need for a barrier -- XCHG is a barrier on x86. */ @@ -645,24 +660,45 @@ void xen_evtchn_do_upcall(struct pt_regs *regs) int bit_idx = __ffs(pending_bits); int port = (word_idx * BITS_PER_LONG) + bit_idx; int irq = evtchn_to_irq[port]; + struct irq_desc *desc; - if (irq != -1) - handle_irq(irq, regs); + if (irq != -1) { + desc = irq_to_desc(irq); + if (desc) + generic_handle_irq_desc(irq, desc); + } } } BUG_ON(!irqs_disabled()); - count = __get_cpu_var(nesting_count); - __get_cpu_var(nesting_count) = 0; - } while(count != 1); + count = __get_cpu_var(xed_nesting_count); + __get_cpu_var(xed_nesting_count) = 0; + } while (count != 1 || vcpu_info->evtchn_upcall_pending); out: + + put_cpu(); +} + +void xen_evtchn_do_upcall(struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + + exit_idle(); + irq_enter(); + + __xen_evtchn_do_upcall(); + irq_exit(); set_irq_regs(old_regs); +} - put_cpu(); +void xen_hvm_evtchn_do_upcall(void) +{ + __xen_evtchn_do_upcall(); } +EXPORT_SYMBOL_GPL(xen_hvm_evtchn_do_upcall); /* Rebind a new event channel to an existing irq. */ void rebind_evtchn_irq(int evtchn, int irq) @@ -699,7 +735,10 @@ static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu) struct evtchn_bind_vcpu bind_vcpu; int evtchn = evtchn_from_irq(irq); - if (!VALID_EVTCHN(evtchn)) + /* events delivered via platform PCI interrupts are always + * routed to vcpu 0 */ + if (!VALID_EVTCHN(evtchn) || + (xen_hvm_domain() && !xen_have_vector_callback)) return -1; /* Send future instances of this interrupt to other vcpu. */ @@ -924,6 +963,44 @@ static struct irq_chip xen_dynamic_chip __read_mostly = { .retrigger = retrigger_dynirq, }; +int xen_set_callback_via(uint64_t via) +{ + struct xen_hvm_param a; + a.domid = DOMID_SELF; + a.index = HVM_PARAM_CALLBACK_IRQ; + a.value = via; + return HYPERVISOR_hvm_op(HVMOP_set_param, &a); +} +EXPORT_SYMBOL_GPL(xen_set_callback_via); + +#ifdef CONFIG_XEN_PVHVM +/* Vector callbacks are better than PCI interrupts to receive event + * channel notifications because we can receive vector callbacks on any + * vcpu and we don't need PCI support or APIC interactions. */ +void xen_callback_vector(void) +{ + int rc; + uint64_t callback_via; + if (xen_have_vector_callback) { + callback_via = HVM_CALLBACK_VECTOR(XEN_HVM_EVTCHN_CALLBACK); + rc = xen_set_callback_via(callback_via); + if (rc) { + printk(KERN_ERR "Request for Xen HVM callback vector" + " failed.\n"); + xen_have_vector_callback = 0; + return; + } + printk(KERN_INFO "Xen HVM callback vector for event delivery is " + "enabled\n"); + /* in the restore case the vector has already been allocated */ + if (!test_bit(XEN_HVM_EVTCHN_CALLBACK, used_vectors)) + alloc_intr_gate(XEN_HVM_EVTCHN_CALLBACK, xen_hvm_callback_vector); + } +} +#else +void xen_callback_vector(void) {} +#endif + void __init xen_init_IRQ(void) { int i; @@ -938,5 +1015,10 @@ void __init xen_init_IRQ(void) for (i = 0; i < NR_EVENT_CHANNELS; i++) mask_evtchn(i); - irq_ctx_init(smp_processor_id()); + if (xen_hvm_domain()) { + xen_callback_vector(); + native_init_IRQ(); + } else { + irq_ctx_init(smp_processor_id()); + } } diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c index af03195..66e185c 100644 --- a/drivers/xen/evtchn.c +++ b/drivers/xen/evtchn.c @@ -38,7 +38,6 @@ #include <linux/string.h> #include <linux/errno.h> #include <linux/fs.h> -#include <linux/errno.h> #include <linux/miscdevice.h> #include <linux/major.h> #include <linux/proc_fs.h> @@ -46,9 +45,10 @@ #include <linux/poll.h> #include <linux/irq.h> #include <linux/init.h> -#include <linux/gfp.h> #include <linux/mutex.h> #include <linux/cpu.h> + +#include <xen/xen.h> #include <xen/events.h> #include <xen/evtchn.h> #include <asm/xen/hypervisor.h> diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 7d8f531..6c45318 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -34,12 +34,16 @@ #include <linux/module.h> #include <linux/sched.h> #include <linux/mm.h> +#include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> +#include <linux/io.h> +#include <xen/xen.h> #include <xen/interface/xen.h> #include <xen/page.h> #include <xen/grant_table.h> +#include <xen/interface/memory.h> #include <asm/xen/hypercall.h> #include <asm/pgtable.h> @@ -57,6 +61,8 @@ static unsigned int boot_max_nr_grant_frames; static int gnttab_free_count; static grant_ref_t gnttab_free_head; static DEFINE_SPINLOCK(gnttab_list_lock); +unsigned long xen_hvm_resume_frames; +EXPORT_SYMBOL_GPL(xen_hvm_resume_frames); static struct grant_entry *shared; @@ -431,7 +437,7 @@ static unsigned int __max_nr_grant_frames(void) return query.max_nr_frames; } -static inline unsigned int max_nr_grant_frames(void) +unsigned int gnttab_max_grant_frames(void) { unsigned int xen_max = __max_nr_grant_frames(); @@ -439,6 +445,7 @@ static inline unsigned int max_nr_grant_frames(void) return boot_max_nr_grant_frames; return xen_max; } +EXPORT_SYMBOL_GPL(gnttab_max_grant_frames); static int gnttab_map(unsigned int start_idx, unsigned int end_idx) { @@ -447,6 +454,30 @@ static int gnttab_map(unsigned int start_idx, unsigned int end_idx) unsigned int nr_gframes = end_idx + 1; int rc; + if (xen_hvm_domain()) { + struct xen_add_to_physmap xatp; + unsigned int i = end_idx; + rc = 0; + /* + * Loop backwards, so that the first hypercall has the largest + * index, ensuring that the table will grow only once. + */ + do { + xatp.domid = DOMID_SELF; + xatp.idx = i; + xatp.space = XENMAPSPACE_grant_table; + xatp.gpfn = (xen_hvm_resume_frames >> PAGE_SHIFT) + i; + rc = HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp); + if (rc != 0) { + printk(KERN_WARNING + "grant table add_to_physmap failed, err=%d\n", rc); + break; + } + } while (i-- > start_idx); + + return rc; + } + frames = kmalloc(nr_gframes * sizeof(unsigned long), GFP_ATOMIC); if (!frames) return -ENOMEM; @@ -463,7 +494,7 @@ static int gnttab_map(unsigned int start_idx, unsigned int end_idx) BUG_ON(rc || setup.status); - rc = arch_gnttab_map_shared(frames, nr_gframes, max_nr_grant_frames(), + rc = arch_gnttab_map_shared(frames, nr_gframes, gnttab_max_grant_frames(), &shared); BUG_ON(rc); @@ -474,9 +505,27 @@ static int gnttab_map(unsigned int start_idx, unsigned int end_idx) int gnttab_resume(void) { - if (max_nr_grant_frames() < nr_grant_frames) + unsigned int max_nr_gframes; + + max_nr_gframes = gnttab_max_grant_frames(); + if (max_nr_gframes < nr_grant_frames) return -ENOSYS; - return gnttab_map(0, nr_grant_frames - 1); + + if (xen_pv_domain()) + return gnttab_map(0, nr_grant_frames - 1); + + if (!shared) { + shared = ioremap(xen_hvm_resume_frames, PAGE_SIZE * max_nr_gframes); + if (shared == NULL) { + printk(KERN_WARNING + "Failed to ioremap gnttab share frames!"); + return -ENOMEM; + } + } + + gnttab_map(0, nr_grant_frames - 1); + + return 0; } int gnttab_suspend(void) @@ -493,7 +542,7 @@ static int gnttab_expand(unsigned int req_entries) cur = nr_grant_frames; extra = ((req_entries + (GREFS_PER_GRANT_FRAME-1)) / GREFS_PER_GRANT_FRAME); - if (cur + extra > max_nr_grant_frames()) + if (cur + extra > gnttab_max_grant_frames()) return -ENOSPC; rc = gnttab_map(cur, cur + extra - 1); @@ -503,15 +552,12 @@ static int gnttab_expand(unsigned int req_entries) return rc; } -static int __devinit gnttab_init(void) +int gnttab_init(void) { int i; unsigned int max_nr_glist_frames, nr_glist_frames; unsigned int nr_init_grefs; - if (!xen_domain()) - return -ENODEV; - nr_grant_frames = 1; boot_max_nr_grant_frames = __max_nr_grant_frames(); @@ -554,5 +600,18 @@ static int __devinit gnttab_init(void) kfree(gnttab_list); return -ENOMEM; } +EXPORT_SYMBOL_GPL(gnttab_init); + +static int __devinit __gnttab_init(void) +{ + /* Delay grant-table initialization in the PV on HVM case */ + if (xen_hvm_domain()) + return 0; + + if (!xen_pv_domain()) + return -ENODEV; + + return gnttab_init(); +} -core_initcall(gnttab_init); +core_initcall(__gnttab_init); diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index 10d03d7..1799bd8 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -3,11 +3,13 @@ */ #include <linux/kernel.h> #include <linux/err.h> +#include <linux/slab.h> #include <linux/reboot.h> #include <linux/sysrq.h> #include <linux/stop_machine.h> #include <linux/freezer.h> +#include <xen/xen.h> #include <xen/xenbus.h> #include <xen/grant_table.h> #include <xen/events.h> @@ -16,6 +18,7 @@ #include <asm/xen/hypercall.h> #include <asm/xen/page.h> +#include <asm/xen/hypervisor.h> enum shutdown_state { SHUTDOWN_INVALID = -1, @@ -32,10 +35,30 @@ enum shutdown_state { static enum shutdown_state shutting_down = SHUTDOWN_INVALID; #ifdef CONFIG_PM_SLEEP -static int xen_suspend(void *data) +static int xen_hvm_suspend(void *data) { + struct sched_shutdown r = { .reason = SHUTDOWN_suspend }; int *cancelled = data; + + BUG_ON(!irqs_disabled()); + + *cancelled = HYPERVISOR_sched_op(SCHEDOP_shutdown, &r); + + xen_hvm_post_suspend(*cancelled); + gnttab_resume(); + + if (!*cancelled) { + xen_irq_resume(); + xen_timer_resume(); + } + + return 0; +} + +static int xen_suspend(void *data) +{ int err; + int *cancelled = data; BUG_ON(!irqs_disabled()); @@ -43,7 +66,6 @@ static int xen_suspend(void *data) if (err) { printk(KERN_ERR "xen_suspend: sysdev_suspend failed: %d\n", err); - dpm_resume_noirq(PMSG_RESUME); return err; } @@ -69,7 +91,6 @@ static int xen_suspend(void *data) } sysdev_resume(); - dpm_resume_noirq(PMSG_RESUME); return 0; } @@ -88,14 +109,14 @@ static void do_suspend(void) err = freeze_processes(); if (err) { printk(KERN_ERR "xen suspend: freeze failed %d\n", err); - return; + goto out; } #endif err = dpm_suspend_start(PMSG_SUSPEND); if (err) { printk(KERN_ERR "xen suspend: dpm_suspend_start %d\n", err); - goto out; + goto out_thaw; } printk(KERN_DEBUG "suspending xenstore...\n"); @@ -104,31 +125,37 @@ static void do_suspend(void) err = dpm_suspend_noirq(PMSG_SUSPEND); if (err) { printk(KERN_ERR "dpm_suspend_noirq failed: %d\n", err); - goto resume_devices; + goto out_resume; } - err = stop_machine(xen_suspend, &cancelled, cpumask_of(0)); + if (xen_hvm_domain()) + err = stop_machine(xen_hvm_suspend, &cancelled, cpumask_of(0)); + else + err = stop_machine(xen_suspend, &cancelled, cpumask_of(0)); + + dpm_resume_noirq(PMSG_RESUME); + if (err) { printk(KERN_ERR "failed to start xen_suspend: %d\n", err); - goto out; + cancelled = 1; } +out_resume: if (!cancelled) { xen_arch_resume(); xs_resume(); } else xs_suspend_cancel(); - dpm_resume_noirq(PMSG_RESUME); - -resume_devices: dpm_resume_end(PMSG_RESUME); /* Make sure timer events get retriggered on all CPUs */ clock_was_set(); -out: + +out_thaw: #ifdef CONFIG_PREEMPT thaw_processes(); +out: #endif shutting_down = SHUTDOWN_INVALID; } @@ -183,6 +210,7 @@ static void shutdown_handler(struct xenbus_watch *watch, kfree(str); } +#ifdef CONFIG_MAGIC_SYSRQ static void sysrq_handler(struct xenbus_watch *watch, const char **vec, unsigned int len) { @@ -212,15 +240,16 @@ static void sysrq_handler(struct xenbus_watch *watch, const char **vec, handle_sysrq(sysrq_key, NULL); } -static struct xenbus_watch shutdown_watch = { - .node = "control/shutdown", - .callback = shutdown_handler -}; - static struct xenbus_watch sysrq_watch = { .node = "control/sysrq", .callback = sysrq_handler }; +#endif + +static struct xenbus_watch shutdown_watch = { + .node = "control/shutdown", + .callback = shutdown_handler +}; static int setup_shutdown_watcher(void) { @@ -232,11 +261,13 @@ static int setup_shutdown_watcher(void) return err; } +#ifdef CONFIG_MAGIC_SYSRQ err = register_xenbus_watch(&sysrq_watch); if (err) { printk(KERN_ERR "Failed to set sysrq watcher\n"); return err; } +#endif return 0; } @@ -249,7 +280,19 @@ static int shutdown_event(struct notifier_block *notifier, return NOTIFY_DONE; } -static int __init setup_shutdown_event(void) +static int __init __setup_shutdown_event(void) +{ + /* Delay initialization in the PV on HVM case */ + if (xen_hvm_domain()) + return 0; + + if (!xen_pv_domain()) + return -ENODEV; + + return xen_setup_shutdown_event(); +} + +int xen_setup_shutdown_event(void) { static struct notifier_block xenstore_notifier = { .notifier_call = shutdown_event @@ -258,5 +301,6 @@ static int __init setup_shutdown_event(void) return 0; } +EXPORT_SYMBOL_GPL(xen_setup_shutdown_event); -subsys_initcall(setup_shutdown_event); +subsys_initcall(__setup_shutdown_event); diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c new file mode 100644 index 0000000..c01b5dd --- /dev/null +++ b/drivers/xen/platform-pci.c @@ -0,0 +1,207 @@ +/****************************************************************************** + * platform-pci.c + * + * Xen platform PCI device driver + * Copyright (c) 2005, Intel Corporation. + * Copyright (c) 2007, XenSource Inc. + * Copyright (c) 2010, Citrix + * + * 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. + * + */ + + +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/pci.h> + +#include <xen/platform_pci.h> +#include <xen/grant_table.h> +#include <xen/xenbus.h> +#include <xen/events.h> +#include <xen/hvm.h> +#include <xen/xen-ops.h> + +#define DRV_NAME "xen-platform-pci" + +MODULE_AUTHOR("ssmith@xensource.com and stefano.stabellini@eu.citrix.com"); +MODULE_DESCRIPTION("Xen platform PCI device"); +MODULE_LICENSE("GPL"); + +static unsigned long platform_mmio; +static unsigned long platform_mmio_alloc; +static unsigned long platform_mmiolen; +static uint64_t callback_via; + +unsigned long alloc_xen_mmio(unsigned long len) +{ + unsigned long addr; + + addr = platform_mmio + platform_mmio_alloc; + platform_mmio_alloc += len; + BUG_ON(platform_mmio_alloc > platform_mmiolen); + + return addr; +} + +static uint64_t get_callback_via(struct pci_dev *pdev) +{ + u8 pin; + int irq; + + irq = pdev->irq; + if (irq < 16) + return irq; /* ISA IRQ */ + + pin = pdev->pin; + + /* We don't know the GSI. Specify the PCI INTx line instead. */ + return ((uint64_t)0x01 << 56) | /* PCI INTx identifier */ + ((uint64_t)pci_domain_nr(pdev->bus) << 32) | + ((uint64_t)pdev->bus->number << 16) | + ((uint64_t)(pdev->devfn & 0xff) << 8) | + ((uint64_t)(pin - 1) & 3); +} + +static irqreturn_t do_hvm_evtchn_intr(int irq, void *dev_id) +{ + xen_hvm_evtchn_do_upcall(); + return IRQ_HANDLED; +} + +static int xen_allocate_irq(struct pci_dev *pdev) +{ + return request_irq(pdev->irq, do_hvm_evtchn_intr, + IRQF_DISABLED | IRQF_NOBALANCING | IRQF_TRIGGER_RISING, + "xen-platform-pci", pdev); +} + +static int platform_pci_resume(struct pci_dev *pdev) +{ + int err; + if (xen_have_vector_callback) + return 0; + err = xen_set_callback_via(callback_via); + if (err) { + dev_err(&pdev->dev, "platform_pci_resume failure!\n"); + return err; + } + return 0; +} + +static int __devinit platform_pci_init(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + int i, ret; + long ioaddr, iolen; + long mmio_addr, mmio_len; + unsigned int max_nr_gframes; + + i = pci_enable_device(pdev); + if (i) + return i; + + ioaddr = pci_resource_start(pdev, 0); + iolen = pci_resource_len(pdev, 0); + + mmio_addr = pci_resource_start(pdev, 1); + mmio_len = pci_resource_len(pdev, 1); + + if (mmio_addr == 0 || ioaddr == 0) { + dev_err(&pdev->dev, "no resources found\n"); + ret = -ENOENT; + goto pci_out; + } + + if (request_mem_region(mmio_addr, mmio_len, DRV_NAME) == NULL) { + dev_err(&pdev->dev, "MEM I/O resource 0x%lx @ 0x%lx busy\n", + mmio_addr, mmio_len); + ret = -EBUSY; + goto pci_out; + } + + if (request_region(ioaddr, iolen, DRV_NAME) == NULL) { + dev_err(&pdev->dev, "I/O resource 0x%lx @ 0x%lx busy\n", + iolen, ioaddr); + ret = -EBUSY; + goto mem_out; + } + + platform_mmio = mmio_addr; + platform_mmiolen = mmio_len; + + if (!xen_have_vector_callback) { + ret = xen_allocate_irq(pdev); + if (ret) { + dev_warn(&pdev->dev, "request_irq failed err=%d\n", ret); + goto out; + } + callback_via = get_callback_via(pdev); + ret = xen_set_callback_via(callback_via); + if (ret) { + dev_warn(&pdev->dev, "Unable to set the evtchn callback " + "err=%d\n", ret); + goto out; + } + } + + max_nr_gframes = gnttab_max_grant_frames(); + xen_hvm_resume_frames = alloc_xen_mmio(PAGE_SIZE * max_nr_gframes); + ret = gnttab_init(); + if (ret) + goto out; + xenbus_probe(NULL); + ret = xen_setup_shutdown_event(); + if (ret) + goto out; + return 0; + +out: + release_region(ioaddr, iolen); +mem_out: + release_mem_region(mmio_addr, mmio_len); +pci_out: + pci_disable_device(pdev); + return ret; +} + +static struct pci_device_id platform_pci_tbl[] __devinitdata = { + {PCI_VENDOR_ID_XEN, PCI_DEVICE_ID_XEN_PLATFORM, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, + {0,} +}; + +MODULE_DEVICE_TABLE(pci, platform_pci_tbl); + +static struct pci_driver platform_driver = { + .name = DRV_NAME, + .probe = platform_pci_init, + .id_table = platform_pci_tbl, +#ifdef CONFIG_PM + .resume_early = platform_pci_resume, +#endif +}; + +static int __init platform_pci_module_init(void) +{ + /* no unplug has been done, IGNORE hasn't been specified: just + * return now */ + if (!xen_platform_pci_unplug) + return -ENODEV; + + return pci_register_driver(&platform_driver); +} + +module_init(platform_pci_module_init); diff --git a/drivers/xen/sys-hypervisor.c b/drivers/xen/sys-hypervisor.c index 88a60e0..60f1827 100644 --- a/drivers/xen/sys-hypervisor.c +++ b/drivers/xen/sys-hypervisor.c @@ -7,6 +7,7 @@ * published by the Free Software Foundation. */ +#include <linux/slab.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/kobject.h> @@ -14,6 +15,7 @@ #include <asm/xen/hypervisor.h> #include <asm/xen/hypercall.h> +#include <xen/xen.h> #include <xen/xenbus.h> #include <xen/interface/xen.h> #include <xen/interface/version.h> @@ -425,7 +427,7 @@ static ssize_t hyp_sysfs_store(struct kobject *kobj, return 0; } -static struct sysfs_ops hyp_sysfs_ops = { +static const struct sysfs_ops hyp_sysfs_ops = { .show = hyp_sysfs_show, .store = hyp_sysfs_store, }; diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c index 92a1ef8..7b3e973 100644 --- a/drivers/xen/xenbus/xenbus_client.c +++ b/drivers/xen/xenbus/xenbus_client.c @@ -30,6 +30,7 @@ * IN THE SOFTWARE. */ +#include <linux/slab.h> #include <linux/types.h> #include <linux/vmalloc.h> #include <asm/xen/hypervisor.h> diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index d42e25d..29bac51 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -45,14 +45,20 @@ #include <linux/kthread.h> #include <linux/mutex.h> #include <linux/io.h> +#include <linux/slab.h> #include <asm/page.h> #include <asm/pgtable.h> #include <asm/xen/hypervisor.h> + +#include <xen/xen.h> #include <xen/xenbus.h> #include <xen/events.h> #include <xen/page.h> +#include <xen/platform_pci.h> +#include <xen/hvm.h> + #include "xenbus_comms.h" #include "xenbus_probe.h" @@ -454,21 +460,21 @@ static ssize_t xendev_show_nodename(struct device *dev, { return sprintf(buf, "%s\n", to_xenbus_device(dev)->nodename); } -DEVICE_ATTR(nodename, S_IRUSR | S_IRGRP | S_IROTH, xendev_show_nodename, NULL); +static DEVICE_ATTR(nodename, S_IRUSR | S_IRGRP | S_IROTH, xendev_show_nodename, NULL); static ssize_t xendev_show_devtype(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "%s\n", to_xenbus_device(dev)->devicetype); } -DEVICE_ATTR(devtype, S_IRUSR | S_IRGRP | S_IROTH, xendev_show_devtype, NULL); +static DEVICE_ATTR(devtype, S_IRUSR | S_IRGRP | S_IROTH, xendev_show_devtype, NULL); static ssize_t xendev_show_modalias(struct device *dev, struct device_attribute *attr, char *buf) { return sprintf(buf, "xen:%s\n", to_xenbus_device(dev)->devicetype); } -DEVICE_ATTR(modalias, S_IRUSR | S_IRGRP | S_IROTH, xendev_show_modalias, NULL); +static DEVICE_ATTR(modalias, S_IRUSR | S_IRGRP | S_IROTH, xendev_show_modalias, NULL); int xenbus_probe_node(struct xen_bus_type *bus, const char *type, @@ -749,10 +755,7 @@ int register_xenstore_notifier(struct notifier_block *nb) { int ret = 0; - if (xenstored_ready > 0) - ret = nb->notifier_call(nb, 0, NULL); - else - blocking_notifier_chain_register(&xenstore_chain, nb); + blocking_notifier_chain_register(&xenstore_chain, nb); return ret; } @@ -776,8 +779,23 @@ void xenbus_probe(struct work_struct *unused) /* Notify others that xenstore is up */ blocking_notifier_call_chain(&xenstore_chain, 0, NULL); } +EXPORT_SYMBOL_GPL(xenbus_probe); -static int __init xenbus_probe_init(void) +static int __init xenbus_probe_initcall(void) +{ + if (!xen_domain()) + return -ENODEV; + + if (xen_initial_domain() || xen_hvm_domain()) + return 0; + + xenbus_probe(NULL); + return 0; +} + +device_initcall(xenbus_probe_initcall); + +static int __init xenbus_init(void) { int err = 0; @@ -802,11 +820,24 @@ static int __init xenbus_probe_init(void) if (xen_initial_domain()) { /* dom0 not yet supported */ } else { + if (xen_hvm_domain()) { + uint64_t v = 0; + err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v); + if (err) + goto out_error; + xen_store_evtchn = (int)v; + err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v); + if (err) + goto out_error; + xen_store_mfn = (unsigned long)v; + xen_store_interface = ioremap(xen_store_mfn << PAGE_SHIFT, PAGE_SIZE); + } else { + xen_store_evtchn = xen_start_info->store_evtchn; + xen_store_mfn = xen_start_info->store_mfn; + xen_store_interface = mfn_to_virt(xen_store_mfn); + } xenstored_ready = 1; - xen_store_evtchn = xen_start_info->store_evtchn; - xen_store_mfn = xen_start_info->store_mfn; } - xen_store_interface = mfn_to_virt(xen_store_mfn); /* Initialize the interface to xenstore. */ err = xs_init(); @@ -816,9 +847,6 @@ static int __init xenbus_probe_init(void) goto out_unreg_back; } - if (!xen_initial_domain()) - xenbus_probe(NULL); - #ifdef CONFIG_XEN_COMPAT_XENFS /* * Create xenfs mountpoint in /proc for compatibility with @@ -839,11 +867,11 @@ static int __init xenbus_probe_init(void) return err; } -postcore_initcall(xenbus_probe_init); +postcore_initcall(xenbus_init); MODULE_LICENSE("GPL"); -static int is_disconnected_device(struct device *dev, void *data) +static int is_device_connecting(struct device *dev, void *data) { struct xenbus_device *xendev = to_xenbus_device(dev); struct device_driver *drv = data; @@ -861,14 +889,15 @@ static int is_disconnected_device(struct device *dev, void *data) return 0; xendrv = to_xenbus_driver(dev->driver); - return (xendev->state != XenbusStateConnected || - (xendrv->is_ready && !xendrv->is_ready(xendev))); + return (xendev->state < XenbusStateConnected || + (xendev->state == XenbusStateConnected && + xendrv->is_ready && !xendrv->is_ready(xendev))); } -static int exists_disconnected_device(struct device_driver *drv) +static int exists_connecting_device(struct device_driver *drv) { return bus_for_each_dev(&xenbus_frontend.bus, NULL, drv, - is_disconnected_device); + is_device_connecting); } static int print_device_status(struct device *dev, void *data) @@ -884,10 +913,13 @@ static int print_device_status(struct device *dev, void *data) /* Information only: is this too noisy? */ printk(KERN_INFO "XENBUS: Device with no driver: %s\n", xendev->nodename); - } else if (xendev->state != XenbusStateConnected) { + } else if (xendev->state < XenbusStateConnected) { + enum xenbus_state rstate = XenbusStateUnknown; + if (xendev->otherend) + rstate = xenbus_read_driver_state(xendev->otherend); printk(KERN_WARNING "XENBUS: Timeout connecting " - "to device: %s (state %d)\n", - xendev->nodename, xendev->state); + "to device: %s (local state %d, remote state %d)\n", + xendev->nodename, xendev->state, rstate); } return 0; @@ -897,7 +929,7 @@ static int print_device_status(struct device *dev, void *data) static int ready_to_wait_for_devices; /* - * On a 10 second timeout, wait for all devices currently configured. We need + * On a 5-minute timeout, wait for all devices currently configured. We need * to do this to guarantee that the filesystems and / or network devices * needed for boot are available, before we can allow the boot to proceed. * @@ -912,18 +944,30 @@ static int ready_to_wait_for_devices; */ static void wait_for_devices(struct xenbus_driver *xendrv) { - unsigned long timeout = jiffies + 10*HZ; + unsigned long start = jiffies; struct device_driver *drv = xendrv ? &xendrv->driver : NULL; + unsigned int seconds_waited = 0; if (!ready_to_wait_for_devices || !xen_domain()) return; - while (exists_disconnected_device(drv)) { - if (time_after(jiffies, timeout)) - break; + while (exists_connecting_device(drv)) { + if (time_after(jiffies, start + (seconds_waited+5)*HZ)) { + if (!seconds_waited) + printk(KERN_WARNING "XENBUS: Waiting for " + "devices to initialise: "); + seconds_waited += 5; + printk("%us...", 300 - seconds_waited); + if (seconds_waited == 300) + break; + } + schedule_timeout_interruptible(HZ/10); } + if (seconds_waited) + printk("\n"); + bus_for_each_dev(&xenbus_frontend.bus, NULL, drv, print_device_status); } @@ -931,6 +975,9 @@ static void wait_for_devices(struct xenbus_driver *xendrv) #ifndef MODULE static int __init boot_wait_for_devices(void) { + if (xen_hvm_domain() && !xen_platform_pci_unplug) + return -ENODEV; + ready_to_wait_for_devices = 1; wait_for_devices(NULL); return 0; diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index 6f91e8c..5534690 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -534,7 +534,7 @@ int xenbus_printf(struct xenbus_transaction t, #define PRINTF_BUFFER_SIZE 4096 char *printf_buffer; - printf_buffer = kmalloc(PRINTF_BUFFER_SIZE, GFP_KERNEL); + printf_buffer = kmalloc(PRINTF_BUFFER_SIZE, GFP_NOIO | __GFP_HIGH); if (printf_buffer == NULL) return -ENOMEM; diff --git a/drivers/xen/xencomm.c b/drivers/xen/xencomm.c index a240b2c..b91f8ff 100644 --- a/drivers/xen/xencomm.c +++ b/drivers/xen/xencomm.c @@ -18,8 +18,8 @@ * Authors: Hollis Blanchard <hollisb@us.ibm.com> */ -#include <linux/gfp.h> #include <linux/mm.h> +#include <linux/slab.h> #include <asm/page.h> #include <xen/xencomm.h> #include <xen/interface/xen.h> diff --git a/drivers/xen/xenfs/super.c b/drivers/xen/xenfs/super.c index 6559e0c..78bfab0 100644 --- a/drivers/xen/xenfs/super.c +++ b/drivers/xen/xenfs/super.c @@ -13,6 +13,8 @@ #include <linux/fs.h> #include <linux/magic.h> +#include <xen/xen.h> + #include "xenfs.h" #include <asm/xen/hypervisor.h> @@ -63,7 +65,7 @@ static struct file_system_type xenfs_type = { static int __init xenfs_init(void) { - if (xen_pv_domain()) + if (xen_domain()) return register_filesystem(&xenfs_type); printk(KERN_INFO "XENFS: not registering filesystem on non-xen platform\n"); @@ -72,7 +74,7 @@ static int __init xenfs_init(void) static void __exit xenfs_exit(void) { - if (xen_pv_domain()) + if (xen_domain()) unregister_filesystem(&xenfs_type); } diff --git a/drivers/xen/xenfs/xenbus.c b/drivers/xen/xenfs/xenbus.c index 9d5b519..3b39c37 100644 --- a/drivers/xen/xenfs/xenbus.c +++ b/drivers/xen/xenfs/xenbus.c @@ -43,6 +43,7 @@ #include <linux/fs.h> #include <linux/poll.h> #include <linux/mutex.h> +#include <linux/sched.h> #include <linux/spinlock.h> #include <linux/mount.h> #include <linux/pagemap.h> @@ -50,6 +51,7 @@ #include <linux/init.h> #include <linux/namei.h> #include <linux/string.h> +#include <linux/slab.h> #include "xenfs.h" #include "../xenbus/xenbus_comms.h" |