diff options
author | Jiri Kosina <jkosina@suse.cz> | 2013-01-29 10:48:30 +0100 |
---|---|---|
committer | Jiri Kosina <jkosina@suse.cz> | 2013-01-29 10:48:30 +0100 |
commit | 617677295b53a40d0e54aac4cbbc216ffbc755dd (patch) | |
tree | 51b9e87213243ed5efff252c8e8d8fec4eebc588 /drivers/xen | |
parent | 5c8d1b68e01a144813e38795fe6dbe7ebb506131 (diff) | |
parent | 6abb7c25775b7fb2225ad0508236d63ca710e65f (diff) | |
download | op-kernel-dev-617677295b53a40d0e54aac4cbbc216ffbc755dd.zip op-kernel-dev-617677295b53a40d0e54aac4cbbc216ffbc755dd.tar.gz |
Merge branch 'master' into for-next
Conflicts:
drivers/devfreq/exynos4_bus.c
Sync with Linus' tree to be able to apply patches that are
against newer code (mvneta).
Diffstat (limited to 'drivers/xen')
-rw-r--r-- | drivers/xen/Kconfig | 3 | ||||
-rw-r--r-- | drivers/xen/Makefile | 8 | ||||
-rw-r--r-- | drivers/xen/balloon.c | 5 | ||||
-rw-r--r-- | drivers/xen/cpu_hotplug.c | 4 | ||||
-rw-r--r-- | drivers/xen/events.c | 2 | ||||
-rw-r--r-- | drivers/xen/fallback.c | 80 | ||||
-rw-r--r-- | drivers/xen/gntdev.c | 164 | ||||
-rw-r--r-- | drivers/xen/grant-table.c | 50 | ||||
-rw-r--r-- | drivers/xen/platform-pci.c | 6 | ||||
-rw-r--r-- | drivers/xen/privcmd.c | 151 | ||||
-rw-r--r-- | drivers/xen/swiotlb-xen.c | 25 | ||||
-rw-r--r-- | drivers/xen/xen-acpi-pad.c | 182 | ||||
-rw-r--r-- | drivers/xen/xen-pciback/pci_stub.c | 131 | ||||
-rw-r--r-- | drivers/xen/xen-pciback/pciback.h | 2 | ||||
-rw-r--r-- | drivers/xen/xen-selfballoon.c | 2 | ||||
-rw-r--r-- | drivers/xen/xenbus/xenbus_dev_frontend.c | 2 | ||||
-rw-r--r-- | drivers/xen/xenbus/xenbus_xs.c | 1 |
17 files changed, 614 insertions, 204 deletions
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index 126d8ce..cabfa97 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -206,4 +206,7 @@ config XEN_MCE_LOG Allow kernel fetching MCE error from Xen platform and converting it into Linux mcelog format for mcelog tools +config XEN_HAVE_PVMMU + bool + endmenu diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile index 0e863703..fb213cf 100644 --- a/drivers/xen/Makefile +++ b/drivers/xen/Makefile @@ -1,8 +1,9 @@ ifneq ($(CONFIG_ARM),y) -obj-y += manage.o balloon.o +obj-y += manage.o obj-$(CONFIG_HOTPLUG_CPU) += cpu_hotplug.o endif -obj-y += grant-table.o features.o events.o +obj-$(CONFIG_X86) += fallback.o +obj-y += grant-table.o features.o events.o balloon.o obj-y += xenbus/ nostackp := $(call cc-option, -fno-stack-protector) @@ -10,7 +11,8 @@ CFLAGS_features.o := $(nostackp) dom0-$(CONFIG_PCI) += pci.o dom0-$(CONFIG_USB_SUPPORT) += dbgp.o -dom0-$(CONFIG_ACPI) += acpi.o +dom0-$(CONFIG_ACPI) += acpi.o $(xen-pad-y) +xen-pad-$(CONFIG_X86) += xen-acpi-pad.o dom0-$(CONFIG_X86) += pcpu.o obj-$(CONFIG_XEN_DOM0) += $(dom0-y) obj-$(CONFIG_BLOCK) += biomerge.o diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index d6886d9..a56776d 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -359,6 +359,7 @@ static enum bp_state increase_reservation(unsigned long nr_pages) set_phys_to_machine(pfn, frame_list[i]); +#ifdef CONFIG_XEN_HAVE_PVMMU /* Link back into the page tables if not highmem. */ if (xen_pv_domain() && !PageHighMem(page)) { int ret; @@ -368,6 +369,7 @@ static enum bp_state increase_reservation(unsigned long nr_pages) 0); BUG_ON(ret); } +#endif /* Relinquish the page back to the allocator. */ ClearPageReserved(page); @@ -416,13 +418,14 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) scrub_page(page); +#ifdef CONFIG_XEN_HAVE_PVMMU if (xen_pv_domain() && !PageHighMem(page)) { ret = HYPERVISOR_update_va_mapping( (unsigned long)__va(pfn << PAGE_SHIFT), __pte_ma(0), 0); BUG_ON(ret); } - +#endif } /* Ensure that ballooned highmem pages don't have kmaps. */ diff --git a/drivers/xen/cpu_hotplug.c b/drivers/xen/cpu_hotplug.c index 4dcfced..084041d4 100644 --- a/drivers/xen/cpu_hotplug.c +++ b/drivers/xen/cpu_hotplug.c @@ -25,10 +25,10 @@ static void disable_hotplug_cpu(int cpu) static int vcpu_online(unsigned int cpu) { int err; - char dir[32], state[32]; + char dir[16], state[16]; sprintf(dir, "cpu/%u", cpu); - err = xenbus_scanf(XBT_NIL, dir, "availability", "%s", state); + err = xenbus_scanf(XBT_NIL, dir, "availability", "%15s", state); if (err != 1) { if (!xen_initial_domain()) printk(KERN_ERR "XENBUS: Unable to read cpu state\n"); diff --git a/drivers/xen/events.c b/drivers/xen/events.c index 912ac81..0be4df3 100644 --- a/drivers/xen/events.c +++ b/drivers/xen/events.c @@ -1395,10 +1395,10 @@ void xen_evtchn_do_upcall(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); + irq_enter(); #ifdef CONFIG_X86 exit_idle(); #endif - irq_enter(); __xen_evtchn_do_upcall(); diff --git a/drivers/xen/fallback.c b/drivers/xen/fallback.c new file mode 100644 index 0000000..0ef7c4d --- /dev/null +++ b/drivers/xen/fallback.c @@ -0,0 +1,80 @@ +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/bug.h> +#include <linux/export.h> +#include <asm/hypervisor.h> +#include <asm/xen/hypercall.h> + +int xen_event_channel_op_compat(int cmd, void *arg) +{ + struct evtchn_op op; + int rc; + + op.cmd = cmd; + memcpy(&op.u, arg, sizeof(op.u)); + rc = _hypercall1(int, event_channel_op_compat, &op); + + switch (cmd) { + case EVTCHNOP_close: + case EVTCHNOP_send: + case EVTCHNOP_bind_vcpu: + case EVTCHNOP_unmask: + /* no output */ + break; + +#define COPY_BACK(eop) \ + case EVTCHNOP_##eop: \ + memcpy(arg, &op.u.eop, sizeof(op.u.eop)); \ + break + + COPY_BACK(bind_interdomain); + COPY_BACK(bind_virq); + COPY_BACK(bind_pirq); + COPY_BACK(status); + COPY_BACK(alloc_unbound); + COPY_BACK(bind_ipi); +#undef COPY_BACK + + default: + WARN_ON(rc != -ENOSYS); + break; + } + + return rc; +} +EXPORT_SYMBOL_GPL(xen_event_channel_op_compat); + +int HYPERVISOR_physdev_op_compat(int cmd, void *arg) +{ + struct physdev_op op; + int rc; + + op.cmd = cmd; + memcpy(&op.u, arg, sizeof(op.u)); + rc = _hypercall1(int, physdev_op_compat, &op); + + switch (cmd) { + case PHYSDEVOP_IRQ_UNMASK_NOTIFY: + case PHYSDEVOP_set_iopl: + case PHYSDEVOP_set_iobitmap: + case PHYSDEVOP_apic_write: + /* no output */ + break; + +#define COPY_BACK(pop, fld) \ + case PHYSDEVOP_##pop: \ + memcpy(arg, &op.u.fld, sizeof(op.u.fld)); \ + break + + COPY_BACK(irq_status_query, irq_status_query); + COPY_BACK(apic_read, apic_op); + COPY_BACK(ASSIGN_VECTOR, irq_op); +#undef COPY_BACK + + default: + WARN_ON(rc != -ENOSYS); + break; + } + + return rc; +} diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 610bfc6be..3c8803f 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -56,10 +56,15 @@ MODULE_PARM_DESC(limit, "Maximum number of grants that may be mapped by " static atomic_t pages_mapped = ATOMIC_INIT(0); static int use_ptemod; +#define populate_freeable_maps use_ptemod struct gntdev_priv { + /* maps with visible offsets in the file descriptor */ struct list_head maps; - /* lock protects maps from concurrent changes */ + /* 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 */ spinlock_t lock; struct mm_struct *mm; struct mmu_notifier mn; @@ -105,6 +110,21 @@ static void gntdev_print_maps(struct gntdev_priv *priv, #endif } +static void gntdev_free_map(struct grant_map *map) +{ + if (map == NULL) + return; + + if (map->pages) + free_xenballooned_pages(map->count, map->pages); + kfree(map->pages); + kfree(map->grants); + kfree(map->map_ops); + kfree(map->unmap_ops); + kfree(map->kmap_ops); + kfree(map); +} + static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count) { struct grant_map *add; @@ -142,12 +162,7 @@ static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count) return add; err: - kfree(add->pages); - kfree(add->grants); - kfree(add->map_ops); - kfree(add->unmap_ops); - kfree(add->kmap_ops); - kfree(add); + gntdev_free_map(add); return NULL; } @@ -183,7 +198,7 @@ static struct grant_map *gntdev_find_map_index(struct gntdev_priv *priv, return NULL; } -static void gntdev_put_map(struct grant_map *map) +static void gntdev_put_map(struct gntdev_priv *priv, struct grant_map *map) { if (!map) return; @@ -198,17 +213,15 @@ static void gntdev_put_map(struct grant_map *map) evtchn_put(map->notify.event); } - if (map->pages) { - if (!use_ptemod) - unmap_grant_pages(map, 0, map->count); - - free_xenballooned_pages(map->count, map->pages); + if (populate_freeable_maps && priv) { + spin_lock(&priv->lock); + list_del(&map->next); + spin_unlock(&priv->lock); } - kfree(map->pages); - kfree(map->grants); - kfree(map->map_ops); - kfree(map->unmap_ops); - kfree(map); + + if (map->pages && !use_ptemod) + unmap_grant_pages(map, 0, map->count); + gntdev_free_map(map); } /* ------------------------------------------------------------------ */ @@ -299,17 +312,10 @@ static int __unmap_grant_pages(struct grant_map *map, int offset, int pages) if (map->notify.flags & UNMAP_NOTIFY_CLEAR_BYTE) { int pgno = (map->notify.addr >> PAGE_SHIFT); - if (pgno >= offset && pgno < offset + pages && use_ptemod) { - void __user *tmp = (void __user *) - map->vma->vm_start + map->notify.addr; - err = copy_to_user(tmp, &err, 1); - if (err) - return -EFAULT; - map->notify.flags &= ~UNMAP_NOTIFY_CLEAR_BYTE; - } else if (pgno >= offset && pgno < offset + pages) { - uint8_t *tmp = kmap(map->pages[pgno]); + if (pgno >= offset && pgno < offset + pages) { + /* No need for kmap, pages are in lowmem */ + uint8_t *tmp = pfn_to_kaddr(page_to_pfn(map->pages[pgno])); tmp[map->notify.addr & (PAGE_SIZE-1)] = 0; - kunmap(map->pages[pgno]); map->notify.flags &= ~UNMAP_NOTIFY_CLEAR_BYTE; } } @@ -374,11 +380,24 @@ static void gntdev_vma_open(struct vm_area_struct *vma) static void gntdev_vma_close(struct vm_area_struct *vma) { struct grant_map *map = vma->vm_private_data; + struct file *file = vma->vm_file; + struct gntdev_priv *priv = file->private_data; pr_debug("gntdev_vma_close %p\n", vma); - map->vma = NULL; + 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. + */ + spin_lock(&priv->lock); + map->vma = NULL; + spin_unlock(&priv->lock); + } vma->vm_private_data = NULL; - gntdev_put_map(map); + gntdev_put_map(priv, map); } static struct vm_operations_struct gntdev_vmops = { @@ -388,33 +407,43 @@ static struct vm_operations_struct gntdev_vmops = { /* ------------------------------------------------------------------ */ +static void unmap_if_in_range(struct grant_map *map, + unsigned long start, unsigned long end) +{ + unsigned long mstart, mend; + int err; + + if (!map->vma) + return; + if (map->vma->vm_start >= end) + return; + if (map->vma->vm_end <= start) + return; + mstart = max(start, map->vma->vm_start); + mend = min(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); + err = unmap_grant_pages(map, + (mstart - map->vma->vm_start) >> PAGE_SHIFT, + (mend - mstart) >> PAGE_SHIFT); + WARN_ON(err); +} + static void mn_invl_range_start(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end) { struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn); struct grant_map *map; - unsigned long mstart, mend; - int err; spin_lock(&priv->lock); list_for_each_entry(map, &priv->maps, next) { - if (!map->vma) - continue; - if (map->vma->vm_start >= end) - continue; - if (map->vma->vm_end <= start) - continue; - mstart = max(start, map->vma->vm_start); - mend = min(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); - err = unmap_grant_pages(map, - (mstart - map->vma->vm_start) >> PAGE_SHIFT, - (mend - mstart) >> PAGE_SHIFT); - WARN_ON(err); + unmap_if_in_range(map, start, end); + } + list_for_each_entry(map, &priv->freeable_maps, next) { + unmap_if_in_range(map, start, end); } spin_unlock(&priv->lock); } @@ -443,6 +472,15 @@ static void mn_release(struct mmu_notifier *mn, 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); + } spin_unlock(&priv->lock); } @@ -464,6 +502,7 @@ static int gntdev_open(struct inode *inode, struct file *flip) return -ENOMEM; INIT_LIST_HEAD(&priv->maps); + INIT_LIST_HEAD(&priv->freeable_maps); spin_lock_init(&priv->lock); if (use_ptemod) { @@ -498,8 +537,9 @@ static int gntdev_release(struct inode *inode, struct file *flip) while (!list_empty(&priv->maps)) { map = list_entry(priv->maps.next, struct grant_map, next); list_del(&map->next); - gntdev_put_map(map); + gntdev_put_map(NULL /* already removed */, map); } + WARN_ON(!list_empty(&priv->freeable_maps)); if (use_ptemod) mmu_notifier_unregister(&priv->mn, priv->mm); @@ -527,14 +567,14 @@ static long gntdev_ioctl_map_grant_ref(struct gntdev_priv *priv, if (unlikely(atomic_add_return(op.count, &pages_mapped) > limit)) { pr_debug("can't map: over limit\n"); - gntdev_put_map(map); + 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(map); - return err; + gntdev_put_map(NULL, map); + return -EFAULT; } spin_lock(&priv->lock); @@ -563,11 +603,13 @@ 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; } spin_unlock(&priv->lock); if (map) - gntdev_put_map(map); + gntdev_put_map(priv, map); return err; } @@ -577,25 +619,31 @@ static long gntdev_ioctl_get_offset_for_vaddr(struct gntdev_priv *priv, struct ioctl_gntdev_get_offset_for_vaddr op; struct vm_area_struct *vma; struct grant_map *map; + int rv = -EINVAL; if (copy_from_user(&op, u, sizeof(op)) != 0) return -EFAULT; pr_debug("priv %p, offset for vaddr %lx\n", priv, (unsigned long)op.vaddr); + down_read(¤t->mm->mmap_sem); vma = find_vma(current->mm, op.vaddr); if (!vma || vma->vm_ops != &gntdev_vmops) - return -EINVAL; + goto out_unlock; map = vma->vm_private_data; if (!map) - return -EINVAL; + goto out_unlock; op.offset = map->index << PAGE_SHIFT; op.count = map->count; + rv = 0; - if (copy_to_user(u, &op, sizeof(op)) != 0) + out_unlock: + up_read(¤t->mm->mmap_sem); + + if (rv == 0 && copy_to_user(u, &op, sizeof(op)) != 0) return -EFAULT; - return 0; + return rv; } static long gntdev_ioctl_notify(struct gntdev_priv *priv, void __user *u) @@ -776,7 +824,7 @@ out_unlock_put: out_put_map: if (use_ptemod) map->vma = NULL; - gntdev_put_map(map); + gntdev_put_map(priv, map); return err; } diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index b91f14e..157c0cc 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -56,10 +56,6 @@ /* External tools reserve first few grant table entries. */ #define NR_RESERVED_ENTRIES 8 #define GNTTAB_LIST_END 0xffffffff -#define GREFS_PER_GRANT_FRAME \ -(grant_table_version == 1 ? \ -(PAGE_SIZE / sizeof(struct grant_entry_v1)) : \ -(PAGE_SIZE / sizeof(union grant_entry_v2))) static grant_ref_t **gnttab_list; static unsigned int nr_grant_frames; @@ -154,6 +150,7 @@ static struct gnttab_ops *gnttab_interface; static grant_status_t *grstatus; static int grant_table_version; +static int grefs_per_grant_frame; static struct gnttab_free_callback *gnttab_free_callback_list; @@ -767,12 +764,14 @@ static int grow_gnttab_list(unsigned int more_frames) unsigned int new_nr_grant_frames, extra_entries, i; unsigned int nr_glist_frames, new_nr_glist_frames; + BUG_ON(grefs_per_grant_frame == 0); + new_nr_grant_frames = nr_grant_frames + more_frames; - extra_entries = more_frames * GREFS_PER_GRANT_FRAME; + extra_entries = more_frames * grefs_per_grant_frame; - nr_glist_frames = (nr_grant_frames * GREFS_PER_GRANT_FRAME + RPP - 1) / RPP; + nr_glist_frames = (nr_grant_frames * grefs_per_grant_frame + RPP - 1) / RPP; new_nr_glist_frames = - (new_nr_grant_frames * GREFS_PER_GRANT_FRAME + RPP - 1) / RPP; + (new_nr_grant_frames * grefs_per_grant_frame + RPP - 1) / RPP; for (i = nr_glist_frames; i < new_nr_glist_frames; i++) { gnttab_list[i] = (grant_ref_t *)__get_free_page(GFP_ATOMIC); if (!gnttab_list[i]) @@ -780,12 +779,12 @@ static int grow_gnttab_list(unsigned int more_frames) } - for (i = GREFS_PER_GRANT_FRAME * nr_grant_frames; - i < GREFS_PER_GRANT_FRAME * new_nr_grant_frames - 1; i++) + for (i = grefs_per_grant_frame * nr_grant_frames; + i < grefs_per_grant_frame * new_nr_grant_frames - 1; i++) gnttab_entry(i) = i + 1; gnttab_entry(i) = gnttab_free_head; - gnttab_free_head = GREFS_PER_GRANT_FRAME * nr_grant_frames; + gnttab_free_head = grefs_per_grant_frame * nr_grant_frames; gnttab_free_count += extra_entries; nr_grant_frames = new_nr_grant_frames; @@ -957,7 +956,8 @@ EXPORT_SYMBOL_GPL(gnttab_unmap_refs); static unsigned nr_status_frames(unsigned nr_grant_frames) { - return (nr_grant_frames * GREFS_PER_GRANT_FRAME + SPP - 1) / SPP; + BUG_ON(grefs_per_grant_frame == 0); + return (nr_grant_frames * grefs_per_grant_frame + SPP - 1) / SPP; } static int gnttab_map_frames_v1(xen_pfn_t *frames, unsigned int nr_gframes) @@ -1115,6 +1115,7 @@ static void gnttab_request_version(void) rc = HYPERVISOR_grant_table_op(GNTTABOP_set_version, &gsv, 1); if (rc == 0 && gsv.version == 2) { grant_table_version = 2; + grefs_per_grant_frame = PAGE_SIZE / sizeof(union grant_entry_v2); gnttab_interface = &gnttab_v2_ops; } else if (grant_table_version == 2) { /* @@ -1127,17 +1128,17 @@ static void gnttab_request_version(void) panic("we need grant tables version 2, but only version 1 is available"); } else { grant_table_version = 1; + grefs_per_grant_frame = PAGE_SIZE / sizeof(struct grant_entry_v1); gnttab_interface = &gnttab_v1_ops; } printk(KERN_INFO "Grant tables using version %d layout.\n", grant_table_version); } -int gnttab_resume(void) +static int gnttab_setup(void) { unsigned int max_nr_gframes; - gnttab_request_version(); max_nr_gframes = gnttab_max_grant_frames(); if (max_nr_gframes < nr_grant_frames) return -ENOSYS; @@ -1160,6 +1161,12 @@ int gnttab_resume(void) return 0; } +int gnttab_resume(void) +{ + gnttab_request_version(); + return gnttab_setup(); +} + int gnttab_suspend(void) { gnttab_interface->unmap_frames(); @@ -1171,9 +1178,10 @@ static int gnttab_expand(unsigned int req_entries) int rc; unsigned int cur, extra; + BUG_ON(grefs_per_grant_frame == 0); cur = nr_grant_frames; - extra = ((req_entries + (GREFS_PER_GRANT_FRAME-1)) / - GREFS_PER_GRANT_FRAME); + extra = ((req_entries + (grefs_per_grant_frame-1)) / + grefs_per_grant_frame); if (cur + extra > gnttab_max_grant_frames()) return -ENOSPC; @@ -1191,21 +1199,23 @@ int gnttab_init(void) unsigned int nr_init_grefs; int ret; + gnttab_request_version(); nr_grant_frames = 1; boot_max_nr_grant_frames = __max_nr_grant_frames(); /* Determine the maximum number of frames required for the * grant reference free list on the current hypervisor. */ + BUG_ON(grefs_per_grant_frame == 0); max_nr_glist_frames = (boot_max_nr_grant_frames * - GREFS_PER_GRANT_FRAME / RPP); + grefs_per_grant_frame / RPP); gnttab_list = kmalloc(max_nr_glist_frames * sizeof(grant_ref_t *), GFP_KERNEL); if (gnttab_list == NULL) return -ENOMEM; - nr_glist_frames = (nr_grant_frames * GREFS_PER_GRANT_FRAME + RPP - 1) / RPP; + nr_glist_frames = (nr_grant_frames * grefs_per_grant_frame + RPP - 1) / RPP; for (i = 0; i < nr_glist_frames; i++) { gnttab_list[i] = (grant_ref_t *)__get_free_page(GFP_KERNEL); if (gnttab_list[i] == NULL) { @@ -1214,12 +1224,12 @@ int gnttab_init(void) } } - if (gnttab_resume() < 0) { + if (gnttab_setup() < 0) { ret = -ENODEV; goto ini_nomem; } - nr_init_grefs = nr_grant_frames * GREFS_PER_GRANT_FRAME; + nr_init_grefs = nr_grant_frames * grefs_per_grant_frame; for (i = NR_RESERVED_ENTRIES; i < nr_init_grefs - 1; i++) gnttab_entry(i) = i + 1; @@ -1239,7 +1249,7 @@ int gnttab_init(void) } EXPORT_SYMBOL_GPL(gnttab_init); -static int __devinit __gnttab_init(void) +static int __gnttab_init(void) { /* Delay grant-table initialization in the PV on HVM case */ if (xen_hvm_domain()) diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c index 97ca359..99db9e1 100644 --- a/drivers/xen/platform-pci.c +++ b/drivers/xen/platform-pci.c @@ -101,8 +101,8 @@ static int platform_pci_resume(struct pci_dev *pdev) return 0; } -static int __devinit platform_pci_init(struct pci_dev *pdev, - const struct pci_device_id *ent) +static int platform_pci_init(struct pci_dev *pdev, + const struct pci_device_id *ent) { int i, ret; long ioaddr; @@ -170,7 +170,7 @@ pci_out: return ret; } -static struct pci_device_id platform_pci_tbl[] __devinitdata = { +static struct pci_device_id platform_pci_tbl[] = { {PCI_VENDOR_ID_XEN, PCI_DEVICE_ID_XEN_PLATFORM, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, {0,} diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index 8adb9cc..ca2b00e 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -33,11 +33,14 @@ #include <xen/features.h> #include <xen/page.h> #include <xen/xen-ops.h> +#include <xen/balloon.h> #include "privcmd.h" MODULE_LICENSE("GPL"); +#define PRIV_VMA_LOCKED ((void *)1) + #ifndef HAVE_ARCH_PRIVCMD_MMAP static int privcmd_enforce_singleshot_mapping(struct vm_area_struct *vma); #endif @@ -178,7 +181,7 @@ static int mmap_mfn_range(void *data, void *state) msg->va & PAGE_MASK, msg->mfn, msg->npages, vma->vm_page_prot, - st->domain); + st->domain, NULL); if (rc < 0) return rc; @@ -196,8 +199,9 @@ static long privcmd_ioctl_mmap(void __user *udata) LIST_HEAD(pagelist); struct mmap_mfn_state state; - if (!xen_initial_domain()) - return -EPERM; + /* We only support privcmd_ioctl_mmap_batch for auto translated. */ + if (xen_feature(XENFEAT_auto_translated_physmap)) + return -ENOSYS; if (copy_from_user(&mmapcmd, udata, sizeof(mmapcmd))) return -EFAULT; @@ -246,6 +250,7 @@ struct mmap_batch_state { domid_t domain; unsigned long va; struct vm_area_struct *vma; + int index; /* A tristate: * 0 for no errors * 1 if at least one error has happened (and no @@ -253,24 +258,47 @@ struct mmap_batch_state { * -ENOENT if at least 1 -ENOENT has happened. */ int global_error; - /* An array for individual errors */ - int *err; + int version; /* User-space mfn array to store errors in the second pass for V1. */ xen_pfn_t __user *user_mfn; + /* User-space int array to store errors in the second pass for V2. */ + int __user *user_err; }; +/* auto translated dom0 note: if domU being created is PV, then mfn is + * mfn(addr on bus). If it's auto xlated, then mfn is pfn (input to HAP). + */ static int mmap_batch_fn(void *data, void *state) { xen_pfn_t *mfnp = data; struct mmap_batch_state *st = state; + struct vm_area_struct *vma = st->vma; + struct page **pages = vma->vm_private_data; + struct page *cur_page = NULL; int ret; + if (xen_feature(XENFEAT_auto_translated_physmap)) + cur_page = pages[st->index++]; + ret = xen_remap_domain_mfn_range(st->vma, st->va & PAGE_MASK, *mfnp, 1, - st->vma->vm_page_prot, st->domain); + st->vma->vm_page_prot, st->domain, + &cur_page); /* Store error code for second pass. */ - *(st->err++) = ret; + if (st->version == 1) { + if (ret < 0) { + /* + * V1 encodes the error codes in the 32bit top nibble of the + * mfn (with its known limitations vis-a-vis 64 bit callers). + */ + *mfnp |= (ret == -ENOENT) ? + PRIVCMD_MMAPBATCH_PAGED_ERROR : + PRIVCMD_MMAPBATCH_MFN_ERROR; + } + } else { /* st->version == 2 */ + *((int *) mfnp) = ret; + } /* And see if it affects the global_error. */ if (ret < 0) { @@ -287,20 +315,51 @@ static int mmap_batch_fn(void *data, void *state) return 0; } -static int mmap_return_errors_v1(void *data, void *state) +static int mmap_return_errors(void *data, void *state) { - xen_pfn_t *mfnp = data; struct mmap_batch_state *st = state; - int err = *(st->err++); - /* - * V1 encodes the error codes in the 32bit top nibble of the - * mfn (with its known limitations vis-a-vis 64 bit callers). - */ - *mfnp |= (err == -ENOENT) ? - PRIVCMD_MMAPBATCH_PAGED_ERROR : - PRIVCMD_MMAPBATCH_MFN_ERROR; - return __put_user(*mfnp, st->user_mfn++); + if (st->version == 1) { + xen_pfn_t mfnp = *((xen_pfn_t *) data); + if (mfnp & PRIVCMD_MMAPBATCH_MFN_ERROR) + return __put_user(mfnp, st->user_mfn++); + else + st->user_mfn++; + } else { /* st->version == 2 */ + int err = *((int *) data); + if (err) + return __put_user(err, st->user_err++); + else + st->user_err++; + } + + return 0; +} + +/* Allocate pfns that are then mapped with gmfns from foreign domid. Update + * the vma with the page info to use later. + * Returns: 0 if success, otherwise -errno + */ +static int alloc_empty_pages(struct vm_area_struct *vma, int numpgs) +{ + int rc; + struct page **pages; + + pages = kcalloc(numpgs, sizeof(pages[0]), GFP_KERNEL); + if (pages == NULL) + return -ENOMEM; + + rc = alloc_xenballooned_pages(numpgs, pages, 0); + if (rc != 0) { + pr_warn("%s Could not alloc %d pfns rc:%d\n", __func__, + numpgs, rc); + kfree(pages); + return -ENOMEM; + } + BUG_ON(vma->vm_private_data != PRIV_VMA_LOCKED); + vma->vm_private_data = pages; + + return 0; } static struct vm_operations_struct privcmd_vm_ops; @@ -313,12 +372,8 @@ static long privcmd_ioctl_mmap_batch(void __user *udata, int version) struct vm_area_struct *vma; unsigned long nr_pages; LIST_HEAD(pagelist); - int *err_array = NULL; struct mmap_batch_state state; - if (!xen_initial_domain()) - return -EPERM; - switch (version) { case 1: if (copy_from_user(&m, udata, sizeof(struct privcmd_mmapbatch))) @@ -352,30 +407,40 @@ static long privcmd_ioctl_mmap_batch(void __user *udata, int version) goto out; } - err_array = kcalloc(m.num, sizeof(int), GFP_KERNEL); - if (err_array == NULL) { - ret = -ENOMEM; - goto out; + if (version == 2) { + /* Zero error array now to only copy back actual errors. */ + if (clear_user(m.err, sizeof(int) * m.num)) { + ret = -EFAULT; + goto out; + } } down_write(&mm->mmap_sem); vma = find_vma(mm, m.addr); - ret = -EINVAL; if (!vma || vma->vm_ops != &privcmd_vm_ops || (m.addr != vma->vm_start) || ((m.addr + (nr_pages << PAGE_SHIFT)) != vma->vm_end) || !privcmd_enforce_singleshot_mapping(vma)) { up_write(&mm->mmap_sem); + ret = -EINVAL; goto out; } + if (xen_feature(XENFEAT_auto_translated_physmap)) { + ret = alloc_empty_pages(vma, m.num); + if (ret < 0) { + up_write(&mm->mmap_sem); + goto out; + } + } state.domain = m.dom; state.vma = vma; state.va = m.addr; + state.index = 0; state.global_error = 0; - state.err = err_array; + state.version = version; /* mmap_batch_fn guarantees ret == 0 */ BUG_ON(traverse_pages(m.num, sizeof(xen_pfn_t), @@ -383,17 +448,14 @@ static long privcmd_ioctl_mmap_batch(void __user *udata, int version) up_write(&mm->mmap_sem); - if (state.global_error && (version == 1)) { + if (state.global_error) { /* Write back errors in second pass. */ state.user_mfn = (xen_pfn_t *)m.arr; - state.err = err_array; + state.user_err = m.err; ret = traverse_pages(m.num, sizeof(xen_pfn_t), - &pagelist, mmap_return_errors_v1, &state); - } else if (version == 2) { - ret = __copy_to_user(m.err, err_array, m.num * sizeof(int)); - if (ret) - ret = -EFAULT; - } + &pagelist, mmap_return_errors, &state); + } else + ret = 0; /* If we have not had any EFAULT-like global errors then set the global * error to -ENOENT if necessary. */ @@ -401,7 +463,6 @@ static long privcmd_ioctl_mmap_batch(void __user *udata, int version) ret = -ENOENT; out: - kfree(err_array); free_page_list(&pagelist); return ret; @@ -438,6 +499,19 @@ static long privcmd_ioctl(struct file *file, return ret; } +static void privcmd_close(struct vm_area_struct *vma) +{ + struct page **pages = vma->vm_private_data; + int numpgs = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; + + if (!xen_feature(XENFEAT_auto_translated_physmap || !numpgs || !pages)) + return; + + xen_unmap_domain_mfn_range(vma, numpgs, pages); + free_xenballooned_pages(numpgs, pages); + kfree(pages); +} + static int privcmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { printk(KERN_DEBUG "privcmd_fault: vma=%p %lx-%lx, pgoff=%lx, uv=%p\n", @@ -448,6 +522,7 @@ static int privcmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf) } static struct vm_operations_struct privcmd_vm_ops = { + .close = privcmd_close, .fault = privcmd_fault }; @@ -465,7 +540,7 @@ static int privcmd_mmap(struct file *file, struct vm_area_struct *vma) static int privcmd_enforce_singleshot_mapping(struct vm_area_struct *vma) { - return (xchg(&vma->vm_private_data, (void *)1) == NULL); + return !cmpxchg(&vma->vm_private_data, NULL, PRIV_VMA_LOCKED); } const struct file_operations xen_privcmd_fops = { diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 58db6df..af47e75 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -338,9 +338,8 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, enum dma_data_direction dir, struct dma_attrs *attrs) { - phys_addr_t phys = page_to_phys(page) + offset; + phys_addr_t map, phys = page_to_phys(page) + offset; dma_addr_t dev_addr = xen_phys_to_bus(phys); - void *map; BUG_ON(dir == DMA_NONE); /* @@ -356,10 +355,10 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, * Oh well, have to allocate and map a bounce buffer. */ map = swiotlb_tbl_map_single(dev, start_dma_addr, phys, size, dir); - if (!map) + if (map == SWIOTLB_MAP_ERROR) return DMA_ERROR_CODE; - dev_addr = xen_virt_to_bus(map); + dev_addr = xen_phys_to_bus(map); /* * Ensure that the address returned is DMA'ble @@ -389,7 +388,7 @@ static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr, /* NOTE: We use dev_addr here, not paddr! */ if (is_xen_swiotlb_buffer(dev_addr)) { - swiotlb_tbl_unmap_single(hwdev, phys_to_virt(paddr), size, dir); + swiotlb_tbl_unmap_single(hwdev, paddr, size, dir); return; } @@ -434,8 +433,7 @@ xen_swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr, /* NOTE: We use dev_addr here, not paddr! */ if (is_xen_swiotlb_buffer(dev_addr)) { - swiotlb_tbl_sync_single(hwdev, phys_to_virt(paddr), size, dir, - target); + swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target); return; } @@ -494,11 +492,12 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, if (swiotlb_force || !dma_capable(hwdev, dev_addr, sg->length) || range_straddles_page_boundary(paddr, sg->length)) { - void *map = swiotlb_tbl_map_single(hwdev, - start_dma_addr, - sg_phys(sg), - sg->length, dir); - if (!map) { + phys_addr_t map = swiotlb_tbl_map_single(hwdev, + start_dma_addr, + sg_phys(sg), + sg->length, + dir); + if (map == SWIOTLB_MAP_ERROR) { /* Don't panic here, we expect map_sg users to do proper error handling. */ xen_swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir, @@ -506,7 +505,7 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, sgl[0].dma_length = 0; return DMA_ERROR_CODE; } - sg->dma_address = xen_virt_to_bus(map); + sg->dma_address = xen_phys_to_bus(map); } else sg->dma_address = dev_addr; sg->dma_length = sg->length; diff --git a/drivers/xen/xen-acpi-pad.c b/drivers/xen/xen-acpi-pad.c new file mode 100644 index 0000000..da39191 --- /dev/null +++ b/drivers/xen/xen-acpi-pad.c @@ -0,0 +1,182 @@ +/* + * xen-acpi-pad.c - Xen pad interface + * + * Copyright (c) 2012, Intel Corporation. + * Author: Liu, Jinsong <jinsong.liu@intel.com> + * + * 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. + */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <acpi/acpi_bus.h> +#include <acpi/acpi_drivers.h> +#include <asm/xen/hypercall.h> +#include <xen/interface/version.h> +#include <xen/xen-ops.h> + +#define ACPI_PROCESSOR_AGGREGATOR_CLASS "acpi_pad" +#define ACPI_PROCESSOR_AGGREGATOR_DEVICE_NAME "Processor Aggregator" +#define ACPI_PROCESSOR_AGGREGATOR_NOTIFY 0x80 +static DEFINE_MUTEX(xen_cpu_lock); + +static int xen_acpi_pad_idle_cpus(unsigned int idle_nums) +{ + struct xen_platform_op op; + + op.cmd = XENPF_core_parking; + op.u.core_parking.type = XEN_CORE_PARKING_SET; + op.u.core_parking.idle_nums = idle_nums; + + return HYPERVISOR_dom0_op(&op); +} + +static int xen_acpi_pad_idle_cpus_num(void) +{ + struct xen_platform_op op; + + op.cmd = XENPF_core_parking; + op.u.core_parking.type = XEN_CORE_PARKING_GET; + + return HYPERVISOR_dom0_op(&op) + ?: op.u.core_parking.idle_nums; +} + +/* + * Query firmware how many CPUs should be idle + * return -1 on failure + */ +static int acpi_pad_pur(acpi_handle handle) +{ + struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL}; + union acpi_object *package; + int num = -1; + + if (ACPI_FAILURE(acpi_evaluate_object(handle, "_PUR", NULL, &buffer))) + return num; + + if (!buffer.length || !buffer.pointer) + return num; + + package = buffer.pointer; + + if (package->type == ACPI_TYPE_PACKAGE && + package->package.count == 2 && + package->package.elements[0].integer.value == 1) /* rev 1 */ + num = package->package.elements[1].integer.value; + + kfree(buffer.pointer); + return num; +} + +/* Notify firmware how many CPUs are idle */ +static void acpi_pad_ost(acpi_handle handle, int stat, + uint32_t idle_nums) +{ + union acpi_object params[3] = { + {.type = ACPI_TYPE_INTEGER,}, + {.type = ACPI_TYPE_INTEGER,}, + {.type = ACPI_TYPE_BUFFER,}, + }; + struct acpi_object_list arg_list = {3, params}; + + params[0].integer.value = ACPI_PROCESSOR_AGGREGATOR_NOTIFY; + params[1].integer.value = stat; + params[2].buffer.length = 4; + params[2].buffer.pointer = (void *)&idle_nums; + acpi_evaluate_object(handle, "_OST", &arg_list, NULL); +} + +static void acpi_pad_handle_notify(acpi_handle handle) +{ + int idle_nums; + + mutex_lock(&xen_cpu_lock); + idle_nums = acpi_pad_pur(handle); + if (idle_nums < 0) { + mutex_unlock(&xen_cpu_lock); + return; + } + + idle_nums = xen_acpi_pad_idle_cpus(idle_nums) + ?: xen_acpi_pad_idle_cpus_num(); + if (idle_nums >= 0) + acpi_pad_ost(handle, 0, idle_nums); + mutex_unlock(&xen_cpu_lock); +} + +static void acpi_pad_notify(acpi_handle handle, u32 event, + void *data) +{ + switch (event) { + case ACPI_PROCESSOR_AGGREGATOR_NOTIFY: + acpi_pad_handle_notify(handle); + break; + default: + pr_warn("Unsupported event [0x%x]\n", event); + break; + } +} + +static int acpi_pad_add(struct acpi_device *device) +{ + acpi_status status; + + strcpy(acpi_device_name(device), ACPI_PROCESSOR_AGGREGATOR_DEVICE_NAME); + strcpy(acpi_device_class(device), ACPI_PROCESSOR_AGGREGATOR_CLASS); + + status = acpi_install_notify_handler(device->handle, + ACPI_DEVICE_NOTIFY, acpi_pad_notify, device); + if (ACPI_FAILURE(status)) + return -ENODEV; + + return 0; +} + +static int acpi_pad_remove(struct acpi_device *device, + int type) +{ + mutex_lock(&xen_cpu_lock); + xen_acpi_pad_idle_cpus(0); + mutex_unlock(&xen_cpu_lock); + + acpi_remove_notify_handler(device->handle, + ACPI_DEVICE_NOTIFY, acpi_pad_notify); + return 0; +} + +static const struct acpi_device_id pad_device_ids[] = { + {"ACPI000C", 0}, + {"", 0}, +}; + +static struct acpi_driver acpi_pad_driver = { + .name = "processor_aggregator", + .class = ACPI_PROCESSOR_AGGREGATOR_CLASS, + .ids = pad_device_ids, + .ops = { + .add = acpi_pad_add, + .remove = acpi_pad_remove, + }, +}; + +static int __init xen_acpi_pad_init(void) +{ + /* Only DOM0 is responsible for Xen acpi pad */ + if (!xen_initial_domain()) + return -ENODEV; + + /* Only Xen4.2 or later support Xen acpi pad */ + if (!xen_running_on_version_or_later(4, 2)) + return -ENODEV; + + return acpi_bus_register_driver(&acpi_pad_driver); +} +subsys_initcall(xen_acpi_pad_init); diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c index 68dcc59..9204126 100644 --- a/drivers/xen/xen-pciback/pci_stub.c +++ b/drivers/xen/xen-pciback/pci_stub.c @@ -142,7 +142,8 @@ static struct pcistub_device *pcistub_device_find(int domain, int bus, if (psdev->dev != NULL && domain == pci_domain_nr(psdev->dev->bus) && bus == psdev->dev->bus->number - && PCI_DEVFN(slot, func) == psdev->dev->devfn) { + && slot == PCI_SLOT(psdev->dev->devfn) + && func == PCI_FUNC(psdev->dev->devfn)) { pcistub_device_get(psdev); goto out; } @@ -191,7 +192,8 @@ struct pci_dev *pcistub_get_pci_dev_by_slot(struct xen_pcibk_device *pdev, if (psdev->dev != NULL && domain == pci_domain_nr(psdev->dev->bus) && bus == psdev->dev->bus->number - && PCI_DEVFN(slot, func) == psdev->dev->devfn) { + && slot == PCI_SLOT(psdev->dev->devfn) + && func == PCI_FUNC(psdev->dev->devfn)) { found_dev = pcistub_device_get_pci_dev(pdev, psdev); break; } @@ -270,8 +272,8 @@ void pcistub_put_pci_dev(struct pci_dev *dev) up_write(&pcistub_sem); } -static int __devinit pcistub_match_one(struct pci_dev *dev, - struct pcistub_device_id *pdev_id) +static int pcistub_match_one(struct pci_dev *dev, + struct pcistub_device_id *pdev_id) { /* Match the specified device by domain, bus, slot, func and also if * any of the device's parent bridges match. @@ -290,7 +292,7 @@ static int __devinit pcistub_match_one(struct pci_dev *dev, return 0; } -static int __devinit pcistub_match(struct pci_dev *dev) +static int pcistub_match(struct pci_dev *dev) { struct pcistub_device_id *pdev_id; unsigned long flags; @@ -308,7 +310,7 @@ static int __devinit pcistub_match(struct pci_dev *dev) return found; } -static int __devinit pcistub_init_device(struct pci_dev *dev) +static int pcistub_init_device(struct pci_dev *dev) { struct xen_pcibk_dev_data *dev_data; int err = 0; @@ -426,7 +428,7 @@ static int __init pcistub_init_devices_late(void) return 0; } -static int __devinit pcistub_seize(struct pci_dev *dev) +static int pcistub_seize(struct pci_dev *dev) { struct pcistub_device *psdev; unsigned long flags; @@ -461,8 +463,7 @@ static int __devinit pcistub_seize(struct pci_dev *dev) return err; } -static int __devinit pcistub_probe(struct pci_dev *dev, - const struct pci_device_id *id) +static int pcistub_probe(struct pci_dev *dev, const struct pci_device_id *id) { int err = 0; @@ -897,42 +898,35 @@ static struct pci_driver xen_pcibk_pci_driver = { static inline int str_to_slot(const char *buf, int *domain, int *bus, int *slot, int *func) { - int err; - char wc = '*'; + int parsed = 0; - err = sscanf(buf, " %x:%x:%x.%x", domain, bus, slot, func); - switch (err) { + switch (sscanf(buf, " %x:%x:%x.%x %n", domain, bus, slot, func, + &parsed)) { case 3: *func = -1; - err = sscanf(buf, " %x:%x:%x.%c", domain, bus, slot, &wc); + sscanf(buf, " %x:%x:%x.* %n", domain, bus, slot, &parsed); break; case 2: *slot = *func = -1; - err = sscanf(buf, " %x:%x:*.%c", domain, bus, &wc); - if (err >= 2) - ++err; + sscanf(buf, " %x:%x:*.* %n", domain, bus, &parsed); break; } - if (err == 4 && wc == '*') + if (parsed && !buf[parsed]) return 0; - else if (err < 0) - return -EINVAL; /* try again without domain */ *domain = 0; - wc = '*'; - err = sscanf(buf, " %x:%x.%x", bus, slot, func); - switch (err) { + switch (sscanf(buf, " %x:%x.%x %n", bus, slot, func, &parsed)) { case 2: *func = -1; - err = sscanf(buf, " %x:%x.%c", bus, slot, &wc); + sscanf(buf, " %x:%x.* %n", bus, slot, &parsed); break; case 1: *slot = *func = -1; - err = sscanf(buf, " %x:*.%c", bus, &wc) + 1; + sscanf(buf, " %x:*.* %n", bus, &parsed); break; } - if (err == 3 && wc == '*') + if (parsed && !buf[parsed]) return 0; return -EINVAL; @@ -941,13 +935,20 @@ static inline int str_to_slot(const char *buf, int *domain, int *bus, static inline int str_to_quirk(const char *buf, int *domain, int *bus, int *slot, int *func, int *reg, int *size, int *mask) { - int err; + int parsed = 0; - err = - sscanf(buf, " %04x:%02x:%02x.%d-%08x:%1x:%08x", domain, bus, slot, - func, reg, size, mask); - if (err == 7) + sscanf(buf, " %x:%x:%x.%x-%x:%x:%x %n", domain, bus, slot, func, + reg, size, mask, &parsed); + if (parsed && !buf[parsed]) return 0; + + /* try again without domain */ + *domain = 0; + sscanf(buf, " %x:%x.%x-%x:%x:%x %n", bus, slot, func, reg, size, + mask, &parsed); + if (parsed && !buf[parsed]) + return 0; + return -EINVAL; } @@ -955,7 +956,7 @@ static int pcistub_device_id_add(int domain, int bus, int slot, int func) { struct pcistub_device_id *pci_dev_id; unsigned long flags; - int rc = 0; + int rc = 0, devfn = PCI_DEVFN(slot, func); if (slot < 0) { for (slot = 0; !rc && slot < 32; ++slot) @@ -969,13 +970,24 @@ static int pcistub_device_id_add(int domain, int bus, int slot, int func) return rc; } + if (( +#if !defined(MODULE) /* pci_domains_supported is not being exported */ \ + || !defined(CONFIG_PCI_DOMAINS) + !pci_domains_supported ? domain : +#endif + domain < 0 || domain > 0xffff) + || bus < 0 || bus > 0xff + || PCI_SLOT(devfn) != slot + || PCI_FUNC(devfn) != func) + return -EINVAL; + pci_dev_id = kmalloc(sizeof(*pci_dev_id), GFP_KERNEL); if (!pci_dev_id) return -ENOMEM; pci_dev_id->domain = domain; pci_dev_id->bus = bus; - pci_dev_id->devfn = PCI_DEVFN(slot, func); + pci_dev_id->devfn = devfn; pr_debug(DRV_NAME ": wants to seize %04x:%02x:%02x.%d\n", domain, bus, slot, func); @@ -1016,14 +1028,18 @@ static int pcistub_device_id_remove(int domain, int bus, int slot, int func) return err; } -static int pcistub_reg_add(int domain, int bus, int slot, int func, int reg, - int size, int mask) +static int pcistub_reg_add(int domain, int bus, int slot, int func, + unsigned int reg, unsigned int size, + unsigned int mask) { int err = 0; struct pcistub_device *psdev; struct pci_dev *dev; struct config_field *field; + if (reg > 0xfff || (size < 4 && (mask >> (size * 8)))) + return -EINVAL; + psdev = pcistub_device_find(domain, bus, slot, func); if (!psdev) { err = -ENODEV; @@ -1254,13 +1270,11 @@ static ssize_t permissive_add(struct device_driver *drv, const char *buf, 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; - if (slot < 0 || func < 0) { - err = -EINVAL; - goto out; - } + psdev = pcistub_device_find(domain, bus, slot, func); if (!psdev) { err = -ENODEV; @@ -1339,8 +1353,6 @@ static int __init pcistub_init(void) if (pci_devs_to_hide && *pci_devs_to_hide) { do { - char wc = '*'; - parsed = 0; err = sscanf(pci_devs_to_hide + pos, @@ -1349,51 +1361,48 @@ static int __init pcistub_init(void) switch (err) { case 3: func = -1; - err = sscanf(pci_devs_to_hide + pos, - " (%x:%x:%x.%c) %n", - &domain, &bus, &slot, &wc, - &parsed); + sscanf(pci_devs_to_hide + pos, + " (%x:%x:%x.*) %n", + &domain, &bus, &slot, &parsed); break; case 2: slot = func = -1; - err = sscanf(pci_devs_to_hide + pos, - " (%x:%x:*.%c) %n", - &domain, &bus, &wc, &parsed) + 1; + sscanf(pci_devs_to_hide + pos, + " (%x:%x:*.*) %n", + &domain, &bus, &parsed); break; } - if (err != 4 || wc != '*') { + if (!parsed) { domain = 0; - wc = '*'; err = sscanf(pci_devs_to_hide + pos, " (%x:%x.%x) %n", &bus, &slot, &func, &parsed); switch (err) { case 2: func = -1; - err = sscanf(pci_devs_to_hide + pos, - " (%x:%x.%c) %n", - &bus, &slot, &wc, - &parsed); + sscanf(pci_devs_to_hide + pos, + " (%x:%x.*) %n", + &bus, &slot, &parsed); break; case 1: slot = func = -1; - err = sscanf(pci_devs_to_hide + pos, - " (%x:*.%c) %n", - &bus, &wc, &parsed) + 1; + sscanf(pci_devs_to_hide + pos, + " (%x:*.*) %n", + &bus, &parsed); break; } - if (err != 3 || wc != '*') - goto parse_error; } + if (parsed <= 0) + goto parse_error; + err = pcistub_device_id_add(domain, bus, slot, func); if (err) goto out; - /* if parsed<=0, we've reached the end of the string */ pos += parsed; - } while (parsed > 0 && pci_devs_to_hide[pos]); + } while (pci_devs_to_hide[pos]); } /* If we're the first PCI Device Driver to register, we're the diff --git a/drivers/xen/xen-pciback/pciback.h b/drivers/xen/xen-pciback/pciback.h index a7def01..f72af87 100644 --- a/drivers/xen/xen-pciback/pciback.h +++ b/drivers/xen/xen-pciback/pciback.h @@ -124,7 +124,7 @@ static inline int xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev, static inline void xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev, struct pci_dev *dev) { - if (xen_pcibk_backend && xen_pcibk_backend->free) + if (xen_pcibk_backend && xen_pcibk_backend->release) return xen_pcibk_backend->release(pdev, dev); } diff --git a/drivers/xen/xen-selfballoon.c b/drivers/xen/xen-selfballoon.c index 7d041cb..2552d3e 100644 --- a/drivers/xen/xen-selfballoon.c +++ b/drivers/xen/xen-selfballoon.c @@ -222,7 +222,7 @@ static void selfballoon_process(struct work_struct *work) if (xen_selfballooning_enabled) { cur_pages = totalram_pages; tgt_pages = cur_pages; /* default is no change */ - goal_pages = percpu_counter_read_positive(&vm_committed_as) + + goal_pages = vm_memory_committed() + totalreserve_pages + MB2PAGES(selfballoon_reserved_mb); #ifdef CONFIG_FRONTSWAP diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 89f7625..ac72702 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -458,7 +458,7 @@ static ssize_t xenbus_file_write(struct file *filp, goto out; /* Can't write a xenbus message larger we can buffer */ - if ((len + u->len) > sizeof(u->u.buffer)) { + if (len > sizeof(u->u.buffer) - u->len) { /* On error, dump existing buffer */ u->len = 0; rc = -EINVAL; diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index acedeab..88e677b 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -48,7 +48,6 @@ #include <xen/xenbus.h> #include <xen/xen.h> #include "xenbus_comms.h" -#include <asm/xen/hypervisor.h> struct xs_stored_msg { struct list_head list; |