diff options
Diffstat (limited to 'drivers/xen')
| -rw-r--r-- | drivers/xen/Kconfig | 63 | ||||
| -rw-r--r-- | drivers/xen/balloon.c | 1 | ||||
| -rw-r--r-- | drivers/xen/gntdev-common.h | 8 | ||||
| -rw-r--r-- | drivers/xen/gntdev.c | 179 | ||||
| -rw-r--r-- | drivers/xen/mcelog.c | 14 | ||||
| -rw-r--r-- | drivers/xen/platform-pci.c | 14 | ||||
| -rw-r--r-- | drivers/xen/swiotlb-xen.c | 12 |
7 files changed, 108 insertions, 183 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 5bae515c8e25..4f2e78a5e4db 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -374,7 +374,6 @@ 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); balloon_append(p); } mutex_unlock(&balloon_mutex); diff --git a/drivers/xen/gntdev-common.h b/drivers/xen/gntdev-common.h index 2f8b949c3eeb..91e44c04f787 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; diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 81401f386c9c..a04ddf2a68af 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -63,7 +63,6 @@ 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 static int unmap_grant_pages(struct gntdev_grant_map *map, int offset, int pages); @@ -249,12 +248,6 @@ void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map) 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); @@ -444,16 +437,9 @@ 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); @@ -475,109 +461,44 @@ 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, }; /* ------------------------------------------------------------------ */ @@ -592,7 +513,6 @@ static int gntdev_open(struct inode *inode, struct file *flip) return -ENOMEM; INIT_LIST_HEAD(&priv->maps); - INIT_LIST_HEAD(&priv->freeable_maps); mutex_init(&priv->lock); #ifdef CONFIG_XEN_GNTDEV_DMABUF @@ -604,17 +524,6 @@ static int gntdev_open(struct inode *inode, struct file *flip) } #endif - 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; @@ -644,16 +553,12 @@ 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; } @@ -714,8 +619,6 @@ 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); @@ -1087,11 +990,6 @@ 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; @@ -1102,10 +1000,6 @@ 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)) @@ -1116,8 +1010,28 @@ 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); + /* + * 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); + if (use_ptemod) { map->pages_vm_start = vma->vm_start; err = apply_to_page_range(vma->vm_mm, vma->vm_start, @@ -1166,8 +1080,11 @@ 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/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/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/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index bd3a10dfac15..b6d27762c6f8 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -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) @@ -397,7 +397,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, /* * Ensure that the address returned is DMA'ble */ - if (unlikely(!dma_capable(dev, dev_addr, size))) { + 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; @@ -405,7 +405,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, done: if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - xen_dma_sync_for_device(dev, dev_addr, phys, size, dir); + xen_dma_sync_for_device(dev_addr, phys, size, dir); return dev_addr; } @@ -425,7 +425,7 @@ static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, BUG_ON(dir == DMA_NONE); if (!dev_is_dma_coherent(hwdev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - xen_dma_sync_for_cpu(hwdev, dev_addr, paddr, size, dir); + 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)) @@ -439,7 +439,7 @@ xen_swiotlb_sync_single_for_cpu(struct device *dev, dma_addr_t dma_addr, phys_addr_t paddr = xen_bus_to_phys(dma_addr); if (!dev_is_dma_coherent(dev)) - xen_dma_sync_for_cpu(dev, dma_addr, paddr, size, dir); + 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); @@ -455,7 +455,7 @@ xen_swiotlb_sync_single_for_device(struct device *dev, dma_addr_t dma_addr, swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE); if (!dev_is_dma_coherent(dev)) - xen_dma_sync_for_device(dev, dma_addr, paddr, size, dir); + xen_dma_sync_for_device(dma_addr, paddr, size, dir); } /* |