diff options
Diffstat (limited to 'drivers/xen')
26 files changed, 564 insertions, 454 deletions
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index 79cc75096f42..61212fc7f0c7 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -106,27 +106,27 @@ config XENFS If in doubt, say yes. config XEN_COMPAT_XENFS - bool "Create compatibility mount point /proc/xen" - depends on XENFS - default y - help - The old xenstore userspace tools expect to find "xenbus" - under /proc/xen, but "xenbus" is now found at the root of the - xenfs filesystem. Selecting this causes the kernel to create - the compatibility mount point /proc/xen if it is running on - a xen platform. - If in doubt, say yes. + bool "Create compatibility mount point /proc/xen" + depends on XENFS + default y + help + The old xenstore userspace tools expect to find "xenbus" + under /proc/xen, but "xenbus" is now found at the root of the + xenfs filesystem. Selecting this causes the kernel to create + the compatibility mount point /proc/xen if it is running on + a xen platform. + If in doubt, say yes. config XEN_SYS_HYPERVISOR - bool "Create xen entries under /sys/hypervisor" - 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. + bool "Create xen entries under /sys/hypervisor" + 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. config XEN_XENBUS_FRONTEND tristate @@ -141,7 +141,8 @@ config XEN_GNTDEV config XEN_GNTDEV_DMABUF bool "Add support for dma-buf grant access device driver extension" - depends on XEN_GNTDEV && XEN_GRANT_DMA_ALLOC && DMA_SHARED_BUFFER + depends on XEN_GNTDEV && XEN_GRANT_DMA_ALLOC + select DMA_SHARED_BUFFER help Allows userspace processes and kernel modules to use Xen backed dma-buf implementation. With this extension grant references to @@ -270,7 +271,7 @@ config XEN_ACPI_PROCESSOR depends on XEN && XEN_DOM0 && X86 && ACPI_PROCESSOR && CPU_FREQ default m help - This ACPI processor uploads Power Management information to the Xen + This ACPI processor uploads Power Management information to the Xen hypervisor. To do that the driver parses the Power Management data and uploads @@ -279,19 +280,19 @@ config XEN_ACPI_PROCESSOR SMM so that other drivers (such as ACPI cpufreq scaling driver) will not load. - To compile this driver as a module, choose M here: the module will be + To compile this driver as a module, choose M here: the module will be called xen_acpi_processor If you do not know what to choose, select M here. If the CPUFREQ drivers are built in, select Y here. config XEN_MCE_LOG bool "Xen platform mcelog" - depends on XEN_DOM0 && X86_64 && X86_MCE + depends on XEN_DOM0 && X86_MCE help Allow kernel fetching MCE error from Xen platform and converting it into Linux mcelog format for mcelog tools config XEN_HAVE_PVMMU - bool + bool config XEN_EFI def_bool y @@ -308,15 +309,15 @@ config XEN_ACPI depends on X86 && ACPI config XEN_SYMS - bool "Xen symbols" - depends on X86 && XEN_DOM0 && XENFS - default y if KALLSYMS - help - Exports hypervisor symbols (along with their types and addresses) via - /proc/xen/xensyms file, similar to /proc/kallsyms + bool "Xen symbols" + depends on X86 && XEN_DOM0 && XENFS + default y if KALLSYMS + help + Exports hypervisor symbols (along with their types and addresses) via + /proc/xen/xensyms file, similar to /proc/kallsyms config XEN_HAVE_VPMU - bool + bool config XEN_FRONT_PGDIR_SHBUF tristate diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 4e11de6cde81..0c142bcab79d 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -156,8 +156,10 @@ static DECLARE_DELAYED_WORK(balloon_worker, balloon_process); (GFP_HIGHUSER | __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC) /* balloon_append: add the given page to the balloon. */ -static void __balloon_append(struct page *page) +static void balloon_append(struct page *page) { + __SetPageOffline(page); + /* Lowmem is re-populated first, so highmem pages go at list tail. */ if (PageHighMem(page)) { list_add_tail(&page->lru, &ballooned_pages); @@ -169,11 +171,6 @@ static void __balloon_append(struct page *page) wake_up(&balloon_wq); } -static void balloon_append(struct page *page) -{ - __balloon_append(page); -} - /* balloon_retrieve: rescue a page from the balloon, if it is not empty. */ static struct page *balloon_retrieve(bool require_lowmem) { @@ -192,6 +189,7 @@ static struct page *balloon_retrieve(bool require_lowmem) else balloon_stats.balloon_low--; + __ClearPageOffline(page); return page; } @@ -376,9 +374,7 @@ static void xen_online_page(struct page *page, unsigned int order) mutex_lock(&balloon_mutex); for (i = 0; i < size; i++) { p = pfn_to_page(start_pfn + i); - __online_page_set_limits(p); - __SetPageOffline(p); - __balloon_append(p); + balloon_append(p); } mutex_unlock(&balloon_mutex); } @@ -398,7 +394,8 @@ static struct notifier_block xen_memory_nb = { #else static enum bp_state reserve_additional_memory(void) { - balloon_stats.target_pages = balloon_stats.current_pages; + balloon_stats.target_pages = balloon_stats.current_pages + + balloon_stats.target_unpopulated; return BP_ECANCELED; } #endif /* CONFIG_XEN_BALLOON_MEMORY_HOTPLUG */ @@ -444,7 +441,6 @@ static enum bp_state increase_reservation(unsigned long nr_pages) xenmem_reservation_va_mapping_update(1, &page, &frame_list[i]); /* Relinquish the page back to the allocator. */ - __ClearPageOffline(page); free_reserved_page(page); } @@ -471,7 +467,6 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) state = BP_EAGAIN; break; } - __SetPageOffline(page); adjust_managed_page_count(page, -1); xenmem_reservation_scrub_page(page); list_add(&page->lru, &pages); @@ -611,7 +606,6 @@ int alloc_xenballooned_pages(int nr_pages, struct page **pages) while (pgno < nr_pages) { page = balloon_retrieve(true); if (page) { - __ClearPageOffline(page); pages[pgno++] = page; #ifdef CONFIG_XEN_HAVE_PVMMU /* @@ -653,10 +647,8 @@ void free_xenballooned_pages(int nr_pages, struct page **pages) mutex_lock(&balloon_mutex); for (i = 0; i < nr_pages; i++) { - if (pages[i]) { - __SetPageOffline(pages[i]); + if (pages[i]) balloon_append(pages[i]); - } } balloon_stats.target_unpopulated -= nr_pages; @@ -674,7 +666,6 @@ static void __init balloon_add_region(unsigned long start_pfn, unsigned long pages) { unsigned long pfn, extra_pfn_end; - struct page *page; /* * If the amount of usable memory has been limited (e.g., with @@ -684,11 +675,10 @@ static void __init balloon_add_region(unsigned long start_pfn, extra_pfn_end = min(max_pfn, start_pfn + pages); for (pfn = start_pfn; pfn < extra_pfn_end; pfn++) { - page = pfn_to_page(pfn); /* totalram_pages and totalhigh_pages do not include the boot-time balloon extension, so don't subtract from it. */ - __balloon_append(page); + balloon_append(pfn_to_page(pfn)); } balloon_stats.total_pages += extra_pfn_end - start_pfn; diff --git a/drivers/xen/efi.c b/drivers/xen/efi.c index 89d60f8e3c18..d1ff2186ebb4 100644 --- a/drivers/xen/efi.c +++ b/drivers/xen/efi.c @@ -40,7 +40,7 @@ #define efi_data(op) (op.u.efi_runtime_call) -efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) +static efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) { struct xen_platform_op op = INIT_EFI_OP(get_time); @@ -61,9 +61,8 @@ efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_get_time); -efi_status_t xen_efi_set_time(efi_time_t *tm) +static efi_status_t xen_efi_set_time(efi_time_t *tm) { struct xen_platform_op op = INIT_EFI_OP(set_time); @@ -75,10 +74,10 @@ efi_status_t xen_efi_set_time(efi_time_t *tm) return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_set_time); -efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending, - efi_time_t *tm) +static efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled, + efi_bool_t *pending, + efi_time_t *tm) { struct xen_platform_op op = INIT_EFI_OP(get_wakeup_time); @@ -98,9 +97,8 @@ efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending, return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_get_wakeup_time); -efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) +static efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) { struct xen_platform_op op = INIT_EFI_OP(set_wakeup_time); @@ -117,11 +115,10 @@ efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_set_wakeup_time); -efi_status_t xen_efi_get_variable(efi_char16_t *name, efi_guid_t *vendor, - u32 *attr, unsigned long *data_size, - void *data) +static efi_status_t xen_efi_get_variable(efi_char16_t *name, efi_guid_t *vendor, + u32 *attr, unsigned long *data_size, + void *data) { struct xen_platform_op op = INIT_EFI_OP(get_variable); @@ -141,11 +138,10 @@ efi_status_t xen_efi_get_variable(efi_char16_t *name, efi_guid_t *vendor, return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_get_variable); -efi_status_t xen_efi_get_next_variable(unsigned long *name_size, - efi_char16_t *name, - efi_guid_t *vendor) +static efi_status_t xen_efi_get_next_variable(unsigned long *name_size, + efi_char16_t *name, + efi_guid_t *vendor) { struct xen_platform_op op = INIT_EFI_OP(get_next_variable_name); @@ -165,11 +161,10 @@ efi_status_t xen_efi_get_next_variable(unsigned long *name_size, return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_get_next_variable); -efi_status_t xen_efi_set_variable(efi_char16_t *name, efi_guid_t *vendor, - u32 attr, unsigned long data_size, - void *data) +static efi_status_t xen_efi_set_variable(efi_char16_t *name, efi_guid_t *vendor, + u32 attr, unsigned long data_size, + void *data) { struct xen_platform_op op = INIT_EFI_OP(set_variable); @@ -186,11 +181,10 @@ efi_status_t xen_efi_set_variable(efi_char16_t *name, efi_guid_t *vendor, return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_set_variable); -efi_status_t xen_efi_query_variable_info(u32 attr, u64 *storage_space, - u64 *remaining_space, - u64 *max_variable_size) +static efi_status_t xen_efi_query_variable_info(u32 attr, u64 *storage_space, + u64 *remaining_space, + u64 *max_variable_size) { struct xen_platform_op op = INIT_EFI_OP(query_variable_info); @@ -208,9 +202,8 @@ efi_status_t xen_efi_query_variable_info(u32 attr, u64 *storage_space, return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_query_variable_info); -efi_status_t xen_efi_get_next_high_mono_count(u32 *count) +static efi_status_t xen_efi_get_next_high_mono_count(u32 *count) { struct xen_platform_op op = INIT_EFI_OP(get_next_high_monotonic_count); @@ -221,10 +214,9 @@ efi_status_t xen_efi_get_next_high_mono_count(u32 *count) return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_get_next_high_mono_count); -efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules, - unsigned long count, unsigned long sg_list) +static efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules, + unsigned long count, unsigned long sg_list) { struct xen_platform_op op = INIT_EFI_OP(update_capsule); @@ -241,11 +233,9 @@ efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules, return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_update_capsule); -efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules, - unsigned long count, u64 *max_size, - int *reset_type) +static efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules, + unsigned long count, u64 *max_size, int *reset_type) { struct xen_platform_op op = INIT_EFI_OP(query_capsule_capabilities); @@ -264,10 +254,9 @@ efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules, return efi_data(op).status; } -EXPORT_SYMBOL_GPL(xen_efi_query_capsule_caps); -void xen_efi_reset_system(int reset_type, efi_status_t status, - unsigned long data_size, efi_char16_t *data) +static void xen_efi_reset_system(int reset_type, efi_status_t status, + unsigned long data_size, efi_char16_t *data) { switch (reset_type) { case EFI_RESET_COLD: @@ -281,4 +270,25 @@ void xen_efi_reset_system(int reset_type, efi_status_t status, BUG(); } } -EXPORT_SYMBOL_GPL(xen_efi_reset_system); + +/* + * Set XEN EFI runtime services function pointers. Other fields of struct efi, + * e.g. efi.systab, will be set like normal EFI. + */ +void __init xen_efi_runtime_setup(void) +{ + efi.get_time = xen_efi_get_time; + efi.set_time = xen_efi_set_time; + efi.get_wakeup_time = xen_efi_get_wakeup_time; + efi.set_wakeup_time = xen_efi_set_wakeup_time; + efi.get_variable = xen_efi_get_variable; + efi.get_next_variable = xen_efi_get_next_variable; + efi.set_variable = xen_efi_set_variable; + efi.set_variable_nonblocking = xen_efi_set_variable; + efi.query_variable_info = xen_efi_query_variable_info; + efi.query_variable_info_nonblocking = xen_efi_query_variable_info; + efi.update_capsule = xen_efi_update_capsule; + efi.query_capsule_caps = xen_efi_query_capsule_caps; + efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count; + efi.reset_system = xen_efi_reset_system; +} diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 2e8570c09789..499eff7d3f65 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -247,7 +247,7 @@ static void xen_irq_info_cleanup(struct irq_info *info) */ unsigned int evtchn_from_irq(unsigned irq) { - if (unlikely(WARN(irq >= nr_irqs, "Invalid irq %d!\n", irq))) + if (WARN(irq >= nr_irqs, "Invalid irq %d!\n", irq)) return 0; return info_for_irq(irq)->evtchn; @@ -1213,31 +1213,21 @@ void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector) notify_remote_via_irq(irq); } -static DEFINE_PER_CPU(unsigned, xed_nesting_count); - static void __xen_evtchn_do_upcall(void) { struct vcpu_info *vcpu_info = __this_cpu_read(xen_vcpu); - int cpu = get_cpu(); - unsigned count; + int cpu = smp_processor_id(); do { vcpu_info->evtchn_upcall_pending = 0; - if (__this_cpu_inc_return(xed_nesting_count) - 1) - goto out; - xen_evtchn_handle_events(cpu); BUG_ON(!irqs_disabled()); - count = __this_cpu_read(xed_nesting_count); - __this_cpu_write(xed_nesting_count, 0); - } while (count != 1 || vcpu_info->evtchn_upcall_pending); - -out: + virt_rmb(); /* Hypervisor can set upcall pending. */ - put_cpu(); + } while (vcpu_info->evtchn_upcall_pending); } void xen_evtchn_do_upcall(struct pt_regs *regs) diff --git a/drivers/xen/gntdev-common.h b/drivers/xen/gntdev-common.h index 2f8b949c3eeb..9a3960ecff6c 100644 --- a/drivers/xen/gntdev-common.h +++ b/drivers/xen/gntdev-common.h @@ -21,15 +21,8 @@ struct gntdev_dmabuf_priv; struct gntdev_priv { /* Maps with visible offsets in the file descriptor. */ struct list_head maps; - /* - * Maps that are not visible; will be freed on munmap. - * Only populated if populate_freeable_maps == 1 - */ - struct list_head freeable_maps; /* lock protects maps and freeable_maps. */ struct mutex lock; - struct mm_struct *mm; - struct mmu_notifier mn; #ifdef CONFIG_XEN_GRANT_DMA_ALLOC /* Device for which DMA memory is allocated. */ @@ -49,6 +42,7 @@ struct gntdev_unmap_notify { }; struct gntdev_grant_map { + struct mmu_interval_notifier notifier; struct list_head next; struct vm_area_struct *vma; int index; @@ -87,7 +81,7 @@ void gntdev_add_map(struct gntdev_priv *priv, struct gntdev_grant_map *add); void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map); -bool gntdev_account_mapped_pages(int count); +bool gntdev_test_page_count(unsigned int count); int gntdev_map_grant_pages(struct gntdev_grant_map *map); diff --git a/drivers/xen/gntdev-dmabuf.c b/drivers/xen/gntdev-dmabuf.c index 2c4f324f8626..75d3bb948bf3 100644 --- a/drivers/xen/gntdev-dmabuf.c +++ b/drivers/xen/gntdev-dmabuf.c @@ -342,35 +342,12 @@ static void dmabuf_exp_ops_release(struct dma_buf *dma_buf) mutex_unlock(&priv->lock); } -static void *dmabuf_exp_ops_kmap(struct dma_buf *dma_buf, - unsigned long page_num) -{ - /* Not implemented. */ - return NULL; -} - -static void dmabuf_exp_ops_kunmap(struct dma_buf *dma_buf, - unsigned long page_num, void *addr) -{ - /* Not implemented. */ -} - -static int dmabuf_exp_ops_mmap(struct dma_buf *dma_buf, - struct vm_area_struct *vma) -{ - /* Not implemented. */ - return 0; -} - static const struct dma_buf_ops dmabuf_exp_ops = { .attach = dmabuf_exp_ops_attach, .detach = dmabuf_exp_ops_detach, .map_dma_buf = dmabuf_exp_ops_map_dma_buf, .unmap_dma_buf = dmabuf_exp_ops_unmap_dma_buf, .release = dmabuf_exp_ops_release, - .map = dmabuf_exp_ops_kmap, - .unmap = dmabuf_exp_ops_kunmap, - .mmap = dmabuf_exp_ops_mmap, }; struct gntdev_dmabuf_export_args { @@ -446,7 +423,7 @@ dmabuf_exp_alloc_backing_storage(struct gntdev_priv *priv, int dmabuf_flags, { struct gntdev_grant_map *map; - if (unlikely(count <= 0)) + if (unlikely(gntdev_test_page_count(count))) return ERR_PTR(-EINVAL); if ((dmabuf_flags & GNTDEV_DMA_FLAG_WC) && @@ -459,11 +436,6 @@ dmabuf_exp_alloc_backing_storage(struct gntdev_priv *priv, int dmabuf_flags, if (!map) return ERR_PTR(-ENOMEM); - if (unlikely(gntdev_account_mapped_pages(count))) { - pr_debug("can't map %d pages: over limit\n", count); - gntdev_put_map(NULL, map); - return ERR_PTR(-ENOMEM); - } return map; } @@ -771,7 +743,7 @@ long gntdev_ioctl_dmabuf_exp_from_refs(struct gntdev_priv *priv, int use_ptemod, if (copy_from_user(&op, u, sizeof(op)) != 0) return -EFAULT; - if (unlikely(op.count <= 0)) + if (unlikely(gntdev_test_page_count(op.count))) return -EINVAL; refs = kcalloc(op.count, sizeof(*refs), GFP_KERNEL); @@ -818,7 +790,7 @@ long gntdev_ioctl_dmabuf_imp_to_refs(struct gntdev_priv *priv, if (copy_from_user(&op, u, sizeof(op)) != 0) return -EFAULT; - if (unlikely(op.count <= 0)) + if (unlikely(gntdev_test_page_count(op.count))) return -EINVAL; gntdev_dmabuf = dmabuf_imp_to_refs(priv->dmabuf_priv, diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index a446a7221e13..0258415ca0b2 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -22,6 +22,7 @@ #define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt +#include <linux/dma-mapping.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/init.h> @@ -34,9 +35,6 @@ #include <linux/slab.h> #include <linux/highmem.h> #include <linux/refcount.h> -#ifdef CONFIG_XEN_GRANT_DMA_ALLOC -#include <linux/of_device.h> -#endif #include <xen/xen.h> #include <xen/grant_table.h> @@ -57,15 +55,12 @@ MODULE_AUTHOR("Derek G. Murray <Derek.Murray@cl.cam.ac.uk>, " "Gerd Hoffmann <kraxel@redhat.com>"); MODULE_DESCRIPTION("User-space granted page access driver"); -static int limit = 1024*1024; -module_param(limit, int, 0644); -MODULE_PARM_DESC(limit, "Maximum number of grants that may be mapped by " - "the gntdev device"); - -static atomic_t pages_mapped = ATOMIC_INIT(0); +static unsigned int limit = 64*1024; +module_param(limit, uint, 0644); +MODULE_PARM_DESC(limit, + "Maximum number of grants that may be mapped by one mapping request"); static int use_ptemod; -#define populate_freeable_maps use_ptemod static int unmap_grant_pages(struct gntdev_grant_map *map, int offset, int pages); @@ -74,9 +69,9 @@ static struct miscdevice gntdev_miscdev; /* ------------------------------------------------------------------ */ -bool gntdev_account_mapped_pages(int count) +bool gntdev_test_page_count(unsigned int count) { - return atomic_add_return(count, &pages_mapped) > limit; + return !count || count > limit; } static void gntdev_print_maps(struct gntdev_priv *priv, @@ -117,14 +112,14 @@ static void gntdev_free_map(struct gntdev_grant_map *map) gnttab_free_pages(map->count, map->pages); #ifdef CONFIG_XEN_GRANT_DMA_ALLOC - kfree(map->frames); + kvfree(map->frames); #endif - kfree(map->pages); - kfree(map->grants); - kfree(map->map_ops); - kfree(map->unmap_ops); - kfree(map->kmap_ops); - kfree(map->kunmap_ops); + kvfree(map->pages); + kvfree(map->grants); + kvfree(map->map_ops); + kvfree(map->unmap_ops); + kvfree(map->kmap_ops); + kvfree(map->kunmap_ops); kfree(map); } @@ -138,12 +133,13 @@ struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count, if (NULL == add) return NULL; - add->grants = kcalloc(count, sizeof(add->grants[0]), GFP_KERNEL); - add->map_ops = kcalloc(count, sizeof(add->map_ops[0]), GFP_KERNEL); - add->unmap_ops = kcalloc(count, sizeof(add->unmap_ops[0]), GFP_KERNEL); - add->kmap_ops = kcalloc(count, sizeof(add->kmap_ops[0]), GFP_KERNEL); - add->kunmap_ops = kcalloc(count, sizeof(add->kunmap_ops[0]), GFP_KERNEL); - add->pages = kcalloc(count, sizeof(add->pages[0]), GFP_KERNEL); + add->grants = kvcalloc(count, sizeof(add->grants[0]), GFP_KERNEL); + add->map_ops = kvcalloc(count, sizeof(add->map_ops[0]), GFP_KERNEL); + add->unmap_ops = kvcalloc(count, sizeof(add->unmap_ops[0]), GFP_KERNEL); + add->kmap_ops = kvcalloc(count, sizeof(add->kmap_ops[0]), GFP_KERNEL); + add->kunmap_ops = kvcalloc(count, + sizeof(add->kunmap_ops[0]), GFP_KERNEL); + add->pages = kvcalloc(count, sizeof(add->pages[0]), GFP_KERNEL); if (NULL == add->grants || NULL == add->map_ops || NULL == add->unmap_ops || @@ -162,8 +158,8 @@ struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count, if (dma_flags & (GNTDEV_DMA_FLAG_WC | GNTDEV_DMA_FLAG_COHERENT)) { struct gnttab_dma_alloc_args args; - add->frames = kcalloc(count, sizeof(add->frames[0]), - GFP_KERNEL); + add->frames = kvcalloc(count, sizeof(add->frames[0]), + GFP_KERNEL); if (!add->frames) goto err; @@ -244,19 +240,11 @@ void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map) if (!refcount_dec_and_test(&map->users)) return; - atomic_sub(map->count, &pages_mapped); - if (map->notify.flags & UNMAP_NOTIFY_SEND_EVENT) { notify_remote_via_evtchn(map->notify.event); evtchn_put(map->notify.event); } - if (populate_freeable_maps && priv) { - mutex_lock(&priv->lock); - list_del(&map->next); - mutex_unlock(&priv->lock); - } - if (map->pages && !use_ptemod) unmap_grant_pages(map, 0, map->count); gntdev_free_map(map); @@ -446,16 +434,9 @@ static void gntdev_vma_close(struct vm_area_struct *vma) pr_debug("gntdev_vma_close %p\n", vma); if (use_ptemod) { - /* It is possible that an mmu notifier could be running - * concurrently, so take priv->lock to ensure that the vma won't - * vanishing during the unmap_grant_pages call, since we will - * spin here until that completes. Such a concurrent call will - * not do any unmapping, since that has been done prior to - * closing the vma, but it may still iterate the unmap_ops list. - */ - mutex_lock(&priv->lock); + WARN_ON(map->vma != vma); + mmu_interval_notifier_remove(&map->notifier); map->vma = NULL; - mutex_unlock(&priv->lock); } vma->vm_private_data = NULL; gntdev_put_map(priv, map); @@ -477,109 +458,44 @@ static const struct vm_operations_struct gntdev_vmops = { /* ------------------------------------------------------------------ */ -static bool in_range(struct gntdev_grant_map *map, - unsigned long start, unsigned long end) -{ - if (!map->vma) - return false; - if (map->vma->vm_start >= end) - return false; - if (map->vma->vm_end <= start) - return false; - - return true; -} - -static int unmap_if_in_range(struct gntdev_grant_map *map, - unsigned long start, unsigned long end, - bool blockable) +static bool gntdev_invalidate(struct mmu_interval_notifier *mn, + const struct mmu_notifier_range *range, + unsigned long cur_seq) { + struct gntdev_grant_map *map = + container_of(mn, struct gntdev_grant_map, notifier); unsigned long mstart, mend; int err; - if (!in_range(map, start, end)) - return 0; + if (!mmu_notifier_range_blockable(range)) + return false; - if (!blockable) - return -EAGAIN; + /* + * If the VMA is split or otherwise changed the notifier is not + * updated, but we don't want to process VA's outside the modified + * VMA. FIXME: It would be much more understandable to just prevent + * modifying the VMA in the first place. + */ + if (map->vma->vm_start >= range->end || + map->vma->vm_end <= range->start) + return true; - mstart = max(start, map->vma->vm_start); - mend = min(end, map->vma->vm_end); + mstart = max(range->start, map->vma->vm_start); + mend = min(range->end, map->vma->vm_end); pr_debug("map %d+%d (%lx %lx), range %lx %lx, mrange %lx %lx\n", map->index, map->count, map->vma->vm_start, map->vma->vm_end, - start, end, mstart, mend); + range->start, range->end, mstart, mend); err = unmap_grant_pages(map, (mstart - map->vma->vm_start) >> PAGE_SHIFT, (mend - mstart) >> PAGE_SHIFT); WARN_ON(err); - return 0; -} - -static int mn_invl_range_start(struct mmu_notifier *mn, - const struct mmu_notifier_range *range) -{ - struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn); - struct gntdev_grant_map *map; - int ret = 0; - - if (mmu_notifier_range_blockable(range)) - mutex_lock(&priv->lock); - else if (!mutex_trylock(&priv->lock)) - return -EAGAIN; - - list_for_each_entry(map, &priv->maps, next) { - ret = unmap_if_in_range(map, range->start, range->end, - mmu_notifier_range_blockable(range)); - if (ret) - goto out_unlock; - } - list_for_each_entry(map, &priv->freeable_maps, next) { - ret = unmap_if_in_range(map, range->start, range->end, - mmu_notifier_range_blockable(range)); - if (ret) - goto out_unlock; - } - -out_unlock: - mutex_unlock(&priv->lock); - - return ret; -} - -static void mn_release(struct mmu_notifier *mn, - struct mm_struct *mm) -{ - struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn); - struct gntdev_grant_map *map; - int err; - - mutex_lock(&priv->lock); - list_for_each_entry(map, &priv->maps, next) { - if (!map->vma) - continue; - pr_debug("map %d+%d (%lx %lx)\n", - map->index, map->count, - map->vma->vm_start, map->vma->vm_end); - err = unmap_grant_pages(map, /* offset */ 0, map->count); - WARN_ON(err); - } - list_for_each_entry(map, &priv->freeable_maps, next) { - if (!map->vma) - continue; - pr_debug("map %d+%d (%lx %lx)\n", - map->index, map->count, - map->vma->vm_start, map->vma->vm_end); - err = unmap_grant_pages(map, /* offset */ 0, map->count); - WARN_ON(err); - } - mutex_unlock(&priv->lock); + return true; } -static const struct mmu_notifier_ops gntdev_mmu_ops = { - .release = mn_release, - .invalidate_range_start = mn_invl_range_start, +static const struct mmu_interval_notifier_ops gntdev_mmu_ops = { + .invalidate = gntdev_invalidate, }; /* ------------------------------------------------------------------ */ @@ -587,52 +503,28 @@ static const struct mmu_notifier_ops gntdev_mmu_ops = { static int gntdev_open(struct inode *inode, struct file *flip) { struct gntdev_priv *priv; - int ret = 0; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; INIT_LIST_HEAD(&priv->maps); - INIT_LIST_HEAD(&priv->freeable_maps); mutex_init(&priv->lock); #ifdef CONFIG_XEN_GNTDEV_DMABUF priv->dmabuf_priv = gntdev_dmabuf_init(flip); if (IS_ERR(priv->dmabuf_priv)) { - ret = PTR_ERR(priv->dmabuf_priv); - kfree(priv); - return ret; - } -#endif + int ret = PTR_ERR(priv->dmabuf_priv); - if (use_ptemod) { - priv->mm = get_task_mm(current); - if (!priv->mm) { - kfree(priv); - return -ENOMEM; - } - priv->mn.ops = &gntdev_mmu_ops; - ret = mmu_notifier_register(&priv->mn, priv->mm); - mmput(priv->mm); - } - - if (ret) { kfree(priv); return ret; } +#endif flip->private_data = priv; #ifdef CONFIG_XEN_GRANT_DMA_ALLOC priv->dma_dev = gntdev_miscdev.this_device; - - /* - * The device is not spawn from a device tree, so arch_setup_dma_ops - * is not called, thus leaving the device with dummy DMA ops. - * Fix this by calling of_dma_configure() with a NULL node to set - * default DMA ops. - */ - of_dma_configure(priv->dma_dev, NULL, true); + dma_coerce_mask_and_coherent(priv->dma_dev, DMA_BIT_MASK(64)); #endif pr_debug("priv %p\n", priv); @@ -653,16 +545,12 @@ static int gntdev_release(struct inode *inode, struct file *flip) list_del(&map->next); gntdev_put_map(NULL /* already removed */, map); } - WARN_ON(!list_empty(&priv->freeable_maps)); mutex_unlock(&priv->lock); #ifdef CONFIG_XEN_GNTDEV_DMABUF gntdev_dmabuf_fini(priv->dmabuf_priv); #endif - if (use_ptemod) - mmu_notifier_unregister(&priv->mn, priv->mm); - kfree(priv); return 0; } @@ -677,7 +565,7 @@ static long gntdev_ioctl_map_grant_ref(struct gntdev_priv *priv, if (copy_from_user(&op, u, sizeof(op)) != 0) return -EFAULT; pr_debug("priv %p, add %d\n", priv, op.count); - if (unlikely(op.count <= 0)) + if (unlikely(gntdev_test_page_count(op.count))) return -EINVAL; err = -ENOMEM; @@ -685,12 +573,6 @@ static long gntdev_ioctl_map_grant_ref(struct gntdev_priv *priv, if (!map) return err; - if (unlikely(gntdev_account_mapped_pages(op.count))) { - pr_debug("can't map: over limit\n"); - gntdev_put_map(NULL, map); - return err; - } - if (copy_from_user(map->grants, &u->refs, sizeof(map->grants[0]) * op.count) != 0) { gntdev_put_map(NULL, map); @@ -723,8 +605,6 @@ static long gntdev_ioctl_unmap_grant_ref(struct gntdev_priv *priv, map = gntdev_find_map_index(priv, op.index >> PAGE_SHIFT, op.count); if (map) { list_del(&map->next); - if (populate_freeable_maps) - list_add_tail(&map->next, &priv->freeable_maps); err = 0; } mutex_unlock(&priv->lock); @@ -1096,11 +976,6 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) goto unlock_out; if (use_ptemod && map->vma) goto unlock_out; - if (use_ptemod && priv->mm != vma->vm_mm) { - pr_warn("Huh? Other mm?\n"); - goto unlock_out; - } - refcount_inc(&map->users); vma->vm_ops = &gntdev_vmops; @@ -1111,10 +986,6 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) vma->vm_flags |= VM_DONTCOPY; vma->vm_private_data = map; - - if (use_ptemod) - map->vma = vma; - if (map->flags) { if ((vma->vm_flags & VM_WRITE) && (map->flags & GNTMAP_readonly)) @@ -1125,9 +996,29 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) map->flags |= GNTMAP_readonly; } + if (use_ptemod) { + map->vma = vma; + err = mmu_interval_notifier_insert_locked( + &map->notifier, vma->vm_mm, vma->vm_start, + vma->vm_end - vma->vm_start, &gntdev_mmu_ops); + if (err) + goto out_unlock_put; + } mutex_unlock(&priv->lock); if (use_ptemod) { + /* + * gntdev takes the address of the PTE in find_grant_ptes() and + * passes it to the hypervisor in gntdev_map_grant_pages(). The + * purpose of the notifier is to prevent the hypervisor pointer + * to the PTE from going stale. + * + * Since this vma's mappings can't be touched without the + * mmap_sem, and we are holding it now, there is no need for + * the notifier_range locking pattern. + */ + mmu_interval_read_begin(&map->notifier); + map->pages_vm_start = vma->vm_start; err = apply_to_page_range(vma->vm_mm, vma->vm_start, vma->vm_end - vma->vm_start, @@ -1175,8 +1066,11 @@ out_unlock_put: mutex_unlock(&priv->lock); out_put_map: if (use_ptemod) { - map->vma = NULL; unmap_grant_pages(map, 0, map->count); + if (map->vma) { + mmu_interval_notifier_remove(&map->notifier); + map->vma = NULL; + } } gntdev_put_map(priv, map); return err; diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 7ea6fb6a2e5d..7b36b51cdb9f 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -664,7 +664,6 @@ static int grow_gnttab_list(unsigned int more_frames) unsigned int nr_glist_frames, new_nr_glist_frames; unsigned int grefs_per_frame; - BUG_ON(gnttab_interface == NULL); grefs_per_frame = gnttab_interface->grefs_per_grant_frame; new_nr_grant_frames = nr_grant_frames + more_frames; @@ -1160,7 +1159,6 @@ EXPORT_SYMBOL_GPL(gnttab_unmap_refs_sync); static unsigned int nr_status_frames(unsigned int nr_grant_frames) { - BUG_ON(gnttab_interface == NULL); return gnttab_frames(nr_grant_frames, SPP); } @@ -1363,8 +1361,7 @@ static int gnttab_setup(void) if (xen_feature(XENFEAT_auto_translated_physmap) && gnttab_shared.addr == NULL) { gnttab_shared.addr = xen_auto_xlat_grant_frames.vaddr; if (gnttab_shared.addr == NULL) { - pr_warn("gnttab share frames (addr=0x%08lx) is not mapped!\n", - (unsigned long)xen_auto_xlat_grant_frames.vaddr); + pr_warn("gnttab share frames is not mapped!\n"); return -ENOMEM; } } @@ -1389,7 +1386,6 @@ static int gnttab_expand(unsigned int req_entries) int rc; unsigned int cur, extra; - BUG_ON(gnttab_interface == NULL); cur = nr_grant_frames; extra = ((req_entries + gnttab_interface->grefs_per_grant_frame - 1) / gnttab_interface->grefs_per_grant_frame); @@ -1424,7 +1420,6 @@ int gnttab_init(void) /* Determine the maximum number of frames required for the * grant reference free list on the current hypervisor. */ - BUG_ON(gnttab_interface == NULL); max_nr_glist_frames = (max_nr_grant_frames * gnttab_interface->grefs_per_grant_frame / RPP); diff --git a/drivers/xen/mcelog.c b/drivers/xen/mcelog.c index b8bf61abb65b..e9ac3b8c4167 100644 --- a/drivers/xen/mcelog.c +++ b/drivers/xen/mcelog.c @@ -222,7 +222,7 @@ static int convert_log(struct mc_info *mi) struct mcinfo_global *mc_global; struct mcinfo_bank *mc_bank; struct xen_mce m; - uint32_t i; + unsigned int i, j; mic = NULL; x86_mcinfo_lookup(&mic, mi, MC_TYPE_GLOBAL); @@ -248,7 +248,17 @@ static int convert_log(struct mc_info *mi) m.socketid = g_physinfo[i].mc_chipid; m.cpu = m.extcpu = g_physinfo[i].mc_cpunr; m.cpuvendor = (__u8)g_physinfo[i].mc_vendor; - m.mcgcap = g_physinfo[i].mc_msrvalues[__MC_MSR_MCGCAP].value; + for (j = 0; j < g_physinfo[i].mc_nmsrvals; ++j) + switch (g_physinfo[i].mc_msrvalues[j].reg) { + case MSR_IA32_MCG_CAP: + m.mcgcap = g_physinfo[i].mc_msrvalues[j].value; + break; + + case MSR_PPIN: + case MSR_AMD_PPIN: + m.ppin = g_physinfo[i].mc_msrvalues[j].value; + break; + } mic = NULL; x86_mcinfo_lookup(&mic, mi, MC_TYPE_BANK); diff --git a/drivers/xen/pci.c b/drivers/xen/pci.c index 3eeb9bea7630..224df03ce42e 100644 --- a/drivers/xen/pci.c +++ b/drivers/xen/pci.c @@ -17,6 +17,8 @@ #include "../pci/pci.h" #ifdef CONFIG_PCI_MMCONFIG #include <asm/pci_x86.h> + +static int xen_mcfg_late(void); #endif static bool __read_mostly pci_seg_supported = true; @@ -28,7 +30,18 @@ static int xen_add_device(struct device *dev) #ifdef CONFIG_PCI_IOV struct pci_dev *physfn = pci_dev->physfn; #endif - +#ifdef CONFIG_PCI_MMCONFIG + static bool pci_mcfg_reserved = false; + /* + * Reserve MCFG areas in Xen on first invocation due to this being + * potentially called from inside of acpi_init immediately after + * MCFG table has been finally parsed. + */ + if (!pci_mcfg_reserved) { + xen_mcfg_late(); + pci_mcfg_reserved = true; + } +#endif if (pci_seg_supported) { struct { struct physdev_pci_device_add add; @@ -201,7 +214,7 @@ static int __init register_xen_pci_notifier(void) arch_initcall(register_xen_pci_notifier); #ifdef CONFIG_PCI_MMCONFIG -static int __init xen_mcfg_late(void) +static int xen_mcfg_late(void) { struct pci_mmcfg_region *cfg; int rc; @@ -240,8 +253,4 @@ static int __init xen_mcfg_late(void) } return 0; } -/* - * Needs to be done after acpi_init which are subsys_initcall. - */ -subsys_initcall_sync(xen_mcfg_late); #endif diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c index 5e30602fdbad..59e85e408c23 100644 --- a/drivers/xen/platform-pci.c +++ b/drivers/xen/platform-pci.c @@ -74,7 +74,7 @@ static int xen_allocate_irq(struct pci_dev *pdev) "xen-platform-pci", pdev); } -static int platform_pci_resume(struct pci_dev *pdev) +static int platform_pci_resume(struct device *dev) { int err; @@ -83,7 +83,7 @@ static int platform_pci_resume(struct pci_dev *pdev) err = xen_set_callback_via(callback_via); if (err) { - dev_err(&pdev->dev, "platform_pci_resume failure!\n"); + dev_err(dev, "platform_pci_resume failure!\n"); return err; } return 0; @@ -168,13 +168,17 @@ static const struct pci_device_id platform_pci_tbl[] = { {0,} }; +static struct dev_pm_ops platform_pm_ops = { + .resume_noirq = platform_pci_resume, +}; + static struct pci_driver platform_driver = { .name = DRV_NAME, .probe = platform_pci_probe, .id_table = platform_pci_tbl, -#ifdef CONFIG_PM - .resume_early = platform_pci_resume, -#endif + .driver = { + .pm = &platform_pm_ops, + }, }; builtin_pci_driver(platform_driver); diff --git a/drivers/xen/preempt.c b/drivers/xen/preempt.c index 8b9919c26095..70650b248de5 100644 --- a/drivers/xen/preempt.c +++ b/drivers/xen/preempt.c @@ -8,7 +8,7 @@ #include <linux/sched.h> #include <xen/xen-ops.h> -#ifndef CONFIG_PREEMPT +#ifndef CONFIG_PREEMPTION /* * Some hypercalls issued by the toolstack can take many 10s of @@ -37,4 +37,4 @@ asmlinkage __visible void xen_maybe_preempt_hcall(void) __this_cpu_write(xen_in_preemptible_hcall, true); } } -#endif /* CONFIG_PREEMPT */ +#endif /* CONFIG_PREEMPTION */ diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c index 69a626b0e594..c57c71b7d53d 100644 --- a/drivers/xen/pvcalls-back.c +++ b/drivers/xen/pvcalls-back.c @@ -775,7 +775,7 @@ static int pvcalls_back_poll(struct xenbus_device *dev, mappass->reqcopy = *req; icsk = inet_csk(mappass->sock->sk); queue = &icsk->icsk_accept_queue; - data = queue->rskq_accept_head != NULL; + data = READ_ONCE(queue->rskq_accept_head) != NULL; if (data) { mappass->reqcopy.cmd = 0; ret = 0; diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index ae1df496bf38..b6d27762c6f8 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -28,6 +28,7 @@ #include <linux/memblock.h> #include <linux/dma-direct.h> +#include <linux/dma-noncoherent.h> #include <linux/export.h> #include <xen/swiotlb-xen.h> #include <xen/page.h> @@ -38,6 +39,7 @@ #include <asm/xen/page-coherent.h> #include <trace/events/swiotlb.h> +#define MAX_DMA_BITS 32 /* * Used to do a quick range check in swiotlb_tbl_unmap_single and * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this @@ -114,8 +116,6 @@ static int is_xen_swiotlb_buffer(dma_addr_t dma_addr) return 0; } -static int max_dma_bits = 32; - static int xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs) { @@ -135,7 +135,7 @@ xen_swiotlb_fixup(void *buf, size_t size, unsigned long nslabs) p + (i << IO_TLB_SHIFT), get_order(slabs << IO_TLB_SHIFT), dma_bits, &dma_handle); - } while (rc && dma_bits++ < max_dma_bits); + } while (rc && dma_bits++ < MAX_DMA_BITS); if (rc) return rc; @@ -375,7 +375,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, * we can safely return the device addr and not worry about bounce * buffering it. */ - if (dma_capable(dev, dev_addr, size) && + if (dma_capable(dev, dev_addr, size, true) && !range_straddles_page_boundary(phys, size) && !xen_arch_need_swiotlb(dev, phys, dev_addr) && swiotlb_force != SWIOTLB_FORCE) @@ -386,30 +386,26 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, */ trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force); - map = swiotlb_tbl_map_single(dev, start_dma_addr, phys, size, dir, - attrs); + map = swiotlb_tbl_map_single(dev, start_dma_addr, phys, + size, size, dir, attrs); if (map == (phys_addr_t)DMA_MAPPING_ERROR) return DMA_MAPPING_ERROR; + phys = map; dev_addr = xen_phys_to_bus(map); /* * Ensure that the address returned is DMA'ble */ - if (unlikely(!dma_capable(dev, dev_addr, size))) { - swiotlb_tbl_unmap_single(dev, map, size, dir, + if (unlikely(!dma_capable(dev, dev_addr, size, true))) { + swiotlb_tbl_unmap_single(dev, map, size, size, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC); return DMA_MAPPING_ERROR; } - page = pfn_to_page(map >> PAGE_SHIFT); - offset = map & ~PAGE_MASK; done: - /* - * we are not interested in the dma_addr returned by xen_dma_map_page, - * only in the potential cache flushes executed by the function. - */ - xen_dma_map_page(dev, page, dev_addr, offset, size, dir, attrs); + if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + xen_dma_sync_for_device(dev_addr, phys, size, dir); return dev_addr; } @@ -421,26 +417,19 @@ done: * After this call, reads by the cpu to the buffer are guaranteed to see * whatever the device wrote there. */ -static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir, - unsigned long attrs) +static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, + size_t size, enum dma_data_direction dir, unsigned long attrs) { phys_addr_t paddr = xen_bus_to_phys(dev_addr); BUG_ON(dir == DMA_NONE); - xen_dma_unmap_page(hwdev, dev_addr, size, dir, attrs); + if (!dev_is_dma_coherent(hwdev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + xen_dma_sync_for_cpu(dev_addr, paddr, size, dir); /* NOTE: We use dev_addr here, not paddr! */ if (is_xen_swiotlb_buffer(dev_addr)) - swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs); -} - -static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - xen_unmap_single(hwdev, dev_addr, size, dir, attrs); + swiotlb_tbl_unmap_single(hwdev, paddr, size, size, dir, attrs); } static void @@ -449,7 +438,8 @@ xen_swiotlb_sync_single_for_cpu(struct device *dev, dma_addr_t dma_addr, { phys_addr_t paddr = xen_bus_to_phys(dma_addr); - xen_dma_sync_single_for_cpu(dev, dma_addr, size, dir); + if (!dev_is_dma_coherent(dev)) + xen_dma_sync_for_cpu(dma_addr, paddr, size, dir); if (is_xen_swiotlb_buffer(dma_addr)) swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU); @@ -464,7 +454,8 @@ xen_swiotlb_sync_single_for_device(struct device *dev, dma_addr_t dma_addr, if (is_xen_swiotlb_buffer(dma_addr)) swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE); - xen_dma_sync_single_for_device(dev, dma_addr, size, dir); + if (!dev_is_dma_coherent(dev)) + xen_dma_sync_for_device(dma_addr, paddr, size, dir); } /* @@ -481,7 +472,8 @@ xen_swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems, BUG_ON(dir == DMA_NONE); for_each_sg(sgl, sg, nelems, i) - xen_unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir, attrs); + xen_swiotlb_unmap_page(hwdev, sg->dma_address, sg_dma_len(sg), + dir, attrs); } @@ -547,51 +539,6 @@ xen_swiotlb_dma_supported(struct device *hwdev, u64 mask) return xen_virt_to_bus(xen_io_tlb_end - 1) <= mask; } -/* - * Create userspace mapping for the DMA-coherent memory. - * This function should be called with the pages from the current domain only, - * passing pages mapped from other domains would lead to memory corruption. - */ -static int -xen_swiotlb_dma_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs) -{ -#ifdef CONFIG_ARM - if (xen_get_dma_ops(dev)->mmap) - return xen_get_dma_ops(dev)->mmap(dev, vma, cpu_addr, - dma_addr, size, attrs); -#endif - return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size, attrs); -} - -/* - * This function should be called with the pages from the current domain only, - * passing pages mapped from other domains would lead to memory corruption. - */ -static int -xen_swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt, - void *cpu_addr, dma_addr_t handle, size_t size, - unsigned long attrs) -{ -#ifdef CONFIG_ARM - if (xen_get_dma_ops(dev)->get_sgtable) { -#if 0 - /* - * This check verifies that the page belongs to the current domain and - * is not one mapped from another domain. - * This check is for debug only, and should not go to production build - */ - unsigned long bfn = PHYS_PFN(dma_to_phys(dev, handle)); - BUG_ON (!page_is_ram(bfn)); -#endif - return xen_get_dma_ops(dev)->get_sgtable(dev, sgt, cpu_addr, - handle, size, attrs); - } -#endif - return dma_common_get_sgtable(dev, sgt, cpu_addr, handle, size, attrs); -} - const struct dma_map_ops xen_swiotlb_dma_ops = { .alloc = xen_swiotlb_alloc_coherent, .free = xen_swiotlb_free_coherent, @@ -604,6 +551,6 @@ const struct dma_map_ops xen_swiotlb_dma_ops = { .map_page = xen_swiotlb_map_page, .unmap_page = xen_swiotlb_unmap_page, .dma_supported = xen_swiotlb_dma_supported, - .mmap = xen_swiotlb_dma_mmap, - .get_sgtable = xen_swiotlb_get_sgtable, + .mmap = dma_common_mmap, + .get_sgtable = dma_common_get_sgtable, }; diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c index 6d12fc368210..a8d24433c8e9 100644 --- a/drivers/xen/xen-balloon.c +++ b/drivers/xen/xen-balloon.c @@ -94,7 +94,7 @@ static void watch_target(struct xenbus_watch *watch, "%llu", &static_max) == 1)) static_max >>= PAGE_SHIFT - 10; else - static_max = new_target; + static_max = balloon_stats.current_pages; target_diff = (xen_pv_domain() || xen_initial_domain()) ? 0 : static_max - balloon_stats.target_pages; diff --git a/drivers/xen/xen-pciback/conf_space.c b/drivers/xen/xen-pciback/conf_space.c index 60111719b01f..b20e43e148ce 100644 --- a/drivers/xen/xen-pciback/conf_space.c +++ b/drivers/xen/xen-pciback/conf_space.c @@ -286,6 +286,43 @@ int xen_pcibk_config_write(struct pci_dev *dev, int offset, int size, u32 value) return xen_pcibios_err_to_errno(err); } +int xen_pcibk_get_interrupt_type(struct pci_dev *dev) +{ + int err; + u16 val; + int ret = 0; + + err = pci_read_config_word(dev, PCI_COMMAND, &val); + if (err) + return err; + if (!(val & PCI_COMMAND_INTX_DISABLE)) + ret |= INTERRUPT_TYPE_INTX; + + /* + * Do not trust dev->msi(x)_enabled here, as enabling could be done + * bypassing the pci_*msi* functions, by the qemu. + */ + if (dev->msi_cap) { + err = pci_read_config_word(dev, + dev->msi_cap + PCI_MSI_FLAGS, + &val); + if (err) + return err; + if (val & PCI_MSI_FLAGS_ENABLE) + ret |= INTERRUPT_TYPE_MSI; + } + if (dev->msix_cap) { + err = pci_read_config_word(dev, + dev->msix_cap + PCI_MSIX_FLAGS, + &val); + if (err) + return err; + if (val & PCI_MSIX_FLAGS_ENABLE) + ret |= INTERRUPT_TYPE_MSIX; + } + return ret; +} + void xen_pcibk_config_free_dyn_fields(struct pci_dev *dev) { struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev); diff --git a/drivers/xen/xen-pciback/conf_space.h b/drivers/xen/xen-pciback/conf_space.h index 22db630717ea..28c45180a12e 100644 --- a/drivers/xen/xen-pciback/conf_space.h +++ b/drivers/xen/xen-pciback/conf_space.h @@ -65,6 +65,11 @@ struct config_field_entry { void *data; }; +#define INTERRUPT_TYPE_NONE (1<<0) +#define INTERRUPT_TYPE_INTX (1<<1) +#define INTERRUPT_TYPE_MSI (1<<2) +#define INTERRUPT_TYPE_MSIX (1<<3) + extern bool xen_pcibk_permissive; #define OFFSET(cfg_entry) ((cfg_entry)->base_offset+(cfg_entry)->field->offset) @@ -126,4 +131,6 @@ int xen_pcibk_config_capability_init(void); int xen_pcibk_config_header_add_fields(struct pci_dev *dev); int xen_pcibk_config_capability_add_fields(struct pci_dev *dev); +int xen_pcibk_get_interrupt_type(struct pci_dev *dev); + #endif /* __XEN_PCIBACK_CONF_SPACE_H__ */ diff --git a/drivers/xen/xen-pciback/conf_space_capability.c b/drivers/xen/xen-pciback/conf_space_capability.c index e5694133ebe5..22f13abbe913 100644 --- a/drivers/xen/xen-pciback/conf_space_capability.c +++ b/drivers/xen/xen-pciback/conf_space_capability.c @@ -189,6 +189,85 @@ static const struct config_field caplist_pm[] = { {} }; +static struct msi_msix_field_config { + u16 enable_bit; /* bit for enabling MSI/MSI-X */ + unsigned int int_type; /* interrupt type for exclusiveness check */ +} msi_field_config = { + .enable_bit = PCI_MSI_FLAGS_ENABLE, + .int_type = INTERRUPT_TYPE_MSI, +}, msix_field_config = { + .enable_bit = PCI_MSIX_FLAGS_ENABLE, + .int_type = INTERRUPT_TYPE_MSIX, +}; + +static void *msi_field_init(struct pci_dev *dev, int offset) +{ + return &msi_field_config; +} + +static void *msix_field_init(struct pci_dev *dev, int offset) +{ + return &msix_field_config; +} + +static int msi_msix_flags_write(struct pci_dev *dev, int offset, u16 new_value, + void *data) +{ + int err; + u16 old_value; + const struct msi_msix_field_config *field_config = data; + const struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev); + + if (xen_pcibk_permissive || dev_data->permissive) + goto write; + + err = pci_read_config_word(dev, offset, &old_value); + if (err) + return err; + + if (new_value == old_value) + return 0; + + if (!dev_data->allow_interrupt_control || + (new_value ^ old_value) & ~field_config->enable_bit) + return PCIBIOS_SET_FAILED; + + if (new_value & field_config->enable_bit) { + /* don't allow enabling together with other interrupt types */ + int int_type = xen_pcibk_get_interrupt_type(dev); + + if (int_type == INTERRUPT_TYPE_NONE || + int_type == field_config->int_type) + goto write; + return PCIBIOS_SET_FAILED; + } + +write: + return pci_write_config_word(dev, offset, new_value); +} + +static const struct config_field caplist_msix[] = { + { + .offset = PCI_MSIX_FLAGS, + .size = 2, + .init = msix_field_init, + .u.w.read = xen_pcibk_read_config_word, + .u.w.write = msi_msix_flags_write, + }, + {} +}; + +static const struct config_field caplist_msi[] = { + { + .offset = PCI_MSI_FLAGS, + .size = 2, + .init = msi_field_init, + .u.w.read = xen_pcibk_read_config_word, + .u.w.write = msi_msix_flags_write, + }, + {} +}; + static struct xen_pcibk_config_capability xen_pcibk_config_capability_pm = { .capability = PCI_CAP_ID_PM, .fields = caplist_pm, @@ -197,11 +276,21 @@ static struct xen_pcibk_config_capability xen_pcibk_config_capability_vpd = { .capability = PCI_CAP_ID_VPD, .fields = caplist_vpd, }; +static struct xen_pcibk_config_capability xen_pcibk_config_capability_msi = { + .capability = PCI_CAP_ID_MSI, + .fields = caplist_msi, +}; +static struct xen_pcibk_config_capability xen_pcibk_config_capability_msix = { + .capability = PCI_CAP_ID_MSIX, + .fields = caplist_msix, +}; int xen_pcibk_config_capability_init(void) { register_capability(&xen_pcibk_config_capability_vpd); register_capability(&xen_pcibk_config_capability_pm); + register_capability(&xen_pcibk_config_capability_msi); + register_capability(&xen_pcibk_config_capability_msix); return 0; } diff --git a/drivers/xen/xen-pciback/conf_space_header.c b/drivers/xen/xen-pciback/conf_space_header.c index 10ae24b5a76e..fb4fccb4aecc 100644 --- a/drivers/xen/xen-pciback/conf_space_header.c +++ b/drivers/xen/xen-pciback/conf_space_header.c @@ -117,6 +117,25 @@ static int command_write(struct pci_dev *dev, int offset, u16 value, void *data) pci_clear_mwi(dev); } + if (dev_data && dev_data->allow_interrupt_control) { + if ((cmd->val ^ value) & PCI_COMMAND_INTX_DISABLE) { + if (value & PCI_COMMAND_INTX_DISABLE) { + pci_intx(dev, 0); + } else { + /* Do not allow enabling INTx together with MSI or MSI-X. */ + switch (xen_pcibk_get_interrupt_type(dev)) { + case INTERRUPT_TYPE_NONE: + pci_intx(dev, 1); + break; + case INTERRUPT_TYPE_INTX: + break; + default: + return PCIBIOS_SET_FAILED; + } + } + } + } + cmd->val = value; if (!xen_pcibk_permissive && (!dev_data || !dev_data->permissive)) diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c index 097410a7cdb7..7af93d65ed51 100644 --- a/drivers/xen/xen-pciback/pci_stub.c +++ b/drivers/xen/xen-pciback/pci_stub.c @@ -304,6 +304,8 @@ void pcistub_put_pci_dev(struct pci_dev *dev) xen_pcibk_config_reset_dev(dev); xen_pcibk_config_free_dyn_fields(dev); + dev_data->allow_interrupt_control = 0; + xen_unregister_device_domain_owner(dev); spin_lock_irqsave(&found_psdev->lock, flags); @@ -1431,6 +1433,65 @@ static ssize_t permissive_show(struct device_driver *drv, char *buf) } static DRIVER_ATTR_RW(permissive); +static ssize_t allow_interrupt_control_store(struct device_driver *drv, + const char *buf, size_t count) +{ + int domain, bus, slot, func; + int err; + struct pcistub_device *psdev; + struct xen_pcibk_dev_data *dev_data; + + err = str_to_slot(buf, &domain, &bus, &slot, &func); + if (err) + goto out; + + psdev = pcistub_device_find(domain, bus, slot, func); + if (!psdev) { + err = -ENODEV; + goto out; + } + + dev_data = pci_get_drvdata(psdev->dev); + /* the driver data for a device should never be null at this point */ + if (!dev_data) { + err = -ENXIO; + goto release; + } + dev_data->allow_interrupt_control = 1; +release: + pcistub_device_put(psdev); +out: + if (!err) + err = count; + return err; +} + +static ssize_t allow_interrupt_control_show(struct device_driver *drv, + char *buf) +{ + struct pcistub_device *psdev; + struct xen_pcibk_dev_data *dev_data; + size_t count = 0; + unsigned long flags; + + spin_lock_irqsave(&pcistub_devices_lock, flags); + list_for_each_entry(psdev, &pcistub_devices, dev_list) { + if (count >= PAGE_SIZE) + break; + if (!psdev->dev) + continue; + dev_data = pci_get_drvdata(psdev->dev); + if (!dev_data || !dev_data->allow_interrupt_control) + continue; + count += + scnprintf(buf + count, PAGE_SIZE - count, "%s\n", + pci_name(psdev->dev)); + } + spin_unlock_irqrestore(&pcistub_devices_lock, flags); + return count; +} +static DRIVER_ATTR_RW(allow_interrupt_control); + static void pcistub_exit(void) { driver_remove_file(&xen_pcibk_pci_driver.driver, &driver_attr_new_slot); @@ -1441,6 +1502,8 @@ static void pcistub_exit(void) driver_remove_file(&xen_pcibk_pci_driver.driver, &driver_attr_permissive); driver_remove_file(&xen_pcibk_pci_driver.driver, + &driver_attr_allow_interrupt_control); + driver_remove_file(&xen_pcibk_pci_driver.driver, &driver_attr_irq_handlers); driver_remove_file(&xen_pcibk_pci_driver.driver, &driver_attr_irq_handler_state); @@ -1530,6 +1593,9 @@ static int __init pcistub_init(void) if (!err) err = driver_create_file(&xen_pcibk_pci_driver.driver, &driver_attr_permissive); + if (!err) + err = driver_create_file(&xen_pcibk_pci_driver.driver, + &driver_attr_allow_interrupt_control); if (!err) err = driver_create_file(&xen_pcibk_pci_driver.driver, diff --git a/drivers/xen/xen-pciback/pciback.h b/drivers/xen/xen-pciback/pciback.h index 263c059bff90..ce1077e32466 100644 --- a/drivers/xen/xen-pciback/pciback.h +++ b/drivers/xen/xen-pciback/pciback.h @@ -45,6 +45,7 @@ struct xen_pcibk_dev_data { struct list_head config_fields; struct pci_saved_state *pci_saved_state; unsigned int permissive:1; + unsigned int allow_interrupt_control:1; unsigned int warned_on_write:1; unsigned int enable_intx:1; unsigned int isr_on:1; /* Whether the IRQ handler is installed. */ diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h index d75a2385b37c..5f5b8a7d5b80 100644 --- a/drivers/xen/xenbus/xenbus.h +++ b/drivers/xen/xenbus/xenbus.h @@ -116,8 +116,6 @@ int xenbus_probe_devices(struct xen_bus_type *bus); void xenbus_dev_changed(const char *node, struct xen_bus_type *bus); -void xenbus_dev_shutdown(struct device *_dev); - int xenbus_dev_suspend(struct device *dev); int xenbus_dev_resume(struct device *dev); int xenbus_dev_cancel(struct device *dev); diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 08adc590f631..597af455a522 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -55,6 +55,7 @@ #include <linux/string.h> #include <linux/slab.h> #include <linux/miscdevice.h> +#include <linux/workqueue.h> #include <xen/xenbus.h> #include <xen/xen.h> @@ -116,6 +117,8 @@ struct xenbus_file_priv { wait_queue_head_t read_waitq; struct kref kref; + + struct work_struct wq; }; /* Read out any raw xenbus messages queued up. */ @@ -300,14 +303,14 @@ static void watch_fired(struct xenbus_watch *watch, mutex_unlock(&adap->dev_data->reply_mutex); } -static void xenbus_file_free(struct kref *kref) +static void xenbus_worker(struct work_struct *wq) { struct xenbus_file_priv *u; struct xenbus_transaction_holder *trans, *tmp; struct watch_adapter *watch, *tmp_watch; struct read_buffer *rb, *tmp_rb; - u = container_of(kref, struct xenbus_file_priv, kref); + u = container_of(wq, struct xenbus_file_priv, wq); /* * No need for locking here because there are no other users, @@ -333,6 +336,18 @@ static void xenbus_file_free(struct kref *kref) kfree(u); } +static void xenbus_file_free(struct kref *kref) +{ + struct xenbus_file_priv *u; + + /* + * We might be called in xenbus_thread(). + * Use workqueue to avoid deadlock. + */ + u = container_of(kref, struct xenbus_file_priv, kref); + schedule_work(&u->wq); +} + static struct xenbus_transaction_holder *xenbus_get_transaction( struct xenbus_file_priv *u, uint32_t tx_id) { @@ -650,6 +665,7 @@ static int xenbus_file_open(struct inode *inode, struct file *filp) INIT_LIST_HEAD(&u->watches); INIT_LIST_HEAD(&u->read_buffers); init_waitqueue_head(&u->read_waitq); + INIT_WORK(&u->wq, xenbus_worker); mutex_init(&u->reply_mutex); mutex_init(&u->msgbuffer_mutex); diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index 5b471889d723..66975da4f3b6 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -232,9 +232,18 @@ int xenbus_dev_probe(struct device *_dev) return err; } + if (!try_module_get(drv->driver.owner)) { + dev_warn(&dev->dev, "failed to acquire module reference on '%s'\n", + drv->driver.name); + err = -ESRCH; + goto fail; + } + + spin_lock(&dev->reclaim_lock); err = drv->probe(dev, id); + spin_unlock(&dev->reclaim_lock); if (err) - goto fail; + goto fail_put; err = watch_otherend(dev); if (err) { @@ -244,9 +253,10 @@ int xenbus_dev_probe(struct device *_dev) } return 0; +fail_put: + module_put(drv->driver.owner); fail: xenbus_dev_error(dev, err, "xenbus_dev_probe on %s", dev->nodename); - xenbus_switch_state(dev, XenbusStateClosed); return err; } EXPORT_SYMBOL_GPL(xenbus_dev_probe); @@ -260,39 +270,30 @@ int xenbus_dev_remove(struct device *_dev) free_otherend_watch(dev); - if (drv->remove) + if (drv->remove) { + spin_lock(&dev->reclaim_lock); drv->remove(dev); + spin_unlock(&dev->reclaim_lock); + } + + module_put(drv->driver.owner); free_otherend_details(dev); - xenbus_switch_state(dev, XenbusStateClosed); + /* + * If the toolstack has forced the device state to closing then set + * the state to closed now to allow it to be cleaned up. + * Similarly, if the driver does not support re-bind, set the + * closed. + */ + if (!drv->allow_rebind || + xenbus_read_driver_state(dev->nodename) == XenbusStateClosing) + xenbus_switch_state(dev, XenbusStateClosed); + return 0; } EXPORT_SYMBOL_GPL(xenbus_dev_remove); -void xenbus_dev_shutdown(struct device *_dev) -{ - struct xenbus_device *dev = to_xenbus_device(_dev); - unsigned long timeout = 5*HZ; - - DPRINTK("%s", dev->nodename); - - get_device(&dev->dev); - if (dev->state != XenbusStateConnected) { - pr_info("%s: %s: %s != Connected, skipping\n", - __func__, dev->nodename, xenbus_strstate(dev->state)); - goto out; - } - xenbus_switch_state(dev, XenbusStateClosing); - timeout = wait_for_completion_timeout(&dev->down, timeout); - if (!timeout) - pr_info("%s: %s timeout closing device\n", - __func__, dev->nodename); - out: - put_device(&dev->dev); -} -EXPORT_SYMBOL_GPL(xenbus_dev_shutdown); - int xenbus_register_driver_common(struct xenbus_driver *drv, struct xen_bus_type *bus, struct module *owner, const char *mod_name) @@ -472,6 +473,7 @@ int xenbus_probe_node(struct xen_bus_type *bus, goto fail; dev_set_name(&xendev->dev, "%s", devname); + spin_lock_init(&xendev->reclaim_lock); /* Register with generic device framework. */ err = device_register(&xendev->dev); diff --git a/drivers/xen/xenbus/xenbus_probe_backend.c b/drivers/xen/xenbus/xenbus_probe_backend.c index b0bed4faf44c..791f6fe01e91 100644 --- a/drivers/xen/xenbus/xenbus_probe_backend.c +++ b/drivers/xen/xenbus/xenbus_probe_backend.c @@ -198,7 +198,6 @@ static struct xen_bus_type xenbus_backend = { .uevent = xenbus_uevent_backend, .probe = xenbus_dev_probe, .remove = xenbus_dev_remove, - .shutdown = xenbus_dev_shutdown, .dev_groups = xenbus_dev_groups, }, }; @@ -248,6 +247,41 @@ static int backend_probe_and_watch(struct notifier_block *notifier, return NOTIFY_DONE; } +static int backend_reclaim_memory(struct device *dev, void *data) +{ + const struct xenbus_driver *drv; + struct xenbus_device *xdev; + + if (!dev->driver) + return 0; + drv = to_xenbus_driver(dev->driver); + if (drv && drv->reclaim_memory) { + xdev = to_xenbus_device(dev); + if (!spin_trylock(&xdev->reclaim_lock)) + return 0; + drv->reclaim_memory(xdev); + spin_unlock(&xdev->reclaim_lock); + } + return 0; +} + +/* + * Returns 0 always because we are using shrinker to only detect memory + * pressure. + */ +static unsigned long backend_shrink_memory_count(struct shrinker *shrinker, + struct shrink_control *sc) +{ + bus_for_each_dev(&xenbus_backend.bus, NULL, NULL, + backend_reclaim_memory); + return 0; +} + +static struct shrinker backend_memory_shrinker = { + .count_objects = backend_shrink_memory_count, + .seeks = DEFAULT_SEEKS, +}; + static int __init xenbus_probe_backend_init(void) { static struct notifier_block xenstore_notifier = { @@ -264,6 +298,9 @@ static int __init xenbus_probe_backend_init(void) register_xenstore_notifier(&xenstore_notifier); + if (register_shrinker(&backend_memory_shrinker)) + pr_warn("shrinker registration failed\n"); + return 0; } subsys_initcall(xenbus_probe_backend_init); diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c index a7d90a719cea..8a1650bbe18f 100644 --- a/drivers/xen/xenbus/xenbus_probe_frontend.c +++ b/drivers/xen/xenbus/xenbus_probe_frontend.c @@ -126,6 +126,28 @@ static int xenbus_frontend_dev_probe(struct device *dev) return xenbus_dev_probe(dev); } +static void xenbus_frontend_dev_shutdown(struct device *_dev) +{ + struct xenbus_device *dev = to_xenbus_device(_dev); + unsigned long timeout = 5*HZ; + + DPRINTK("%s", dev->nodename); + + get_device(&dev->dev); + if (dev->state != XenbusStateConnected) { + pr_info("%s: %s: %s != Connected, skipping\n", + __func__, dev->nodename, xenbus_strstate(dev->state)); + goto out; + } + xenbus_switch_state(dev, XenbusStateClosing); + timeout = wait_for_completion_timeout(&dev->down, timeout); + if (!timeout) + pr_info("%s: %s timeout closing device\n", + __func__, dev->nodename); + out: + put_device(&dev->dev); +} + static const struct dev_pm_ops xenbus_pm_ops = { .suspend = xenbus_dev_suspend, .resume = xenbus_frontend_dev_resume, @@ -146,7 +168,7 @@ static struct xen_bus_type xenbus_frontend = { .uevent = xenbus_uevent_frontend, .probe = xenbus_frontend_dev_probe, .remove = xenbus_dev_remove, - .shutdown = xenbus_dev_shutdown, + .shutdown = xenbus_frontend_dev_shutdown, .dev_groups = xenbus_dev_groups, .pm = &xenbus_pm_ops, |
