summaryrefslogtreecommitdiff
path: root/drivers/xen
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-11-30 21:33:14 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2019-11-30 21:33:14 +0300
commitaa32f1169148beb90d71494e2f2a1999ba7b5366 (patch)
treeec8c434bff07bf0beb2df08629089824927f62f9 /drivers/xen
parentd5bb349dbbe27537e90a03b9597deeb07723a86d (diff)
parent93f4e735b6d98ee4b7a1252d81e815a983e359f2 (diff)
downloadlinux-aa32f1169148beb90d71494e2f2a1999ba7b5366.tar.xz
Merge tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma
Pull hmm updates from Jason Gunthorpe: "This is another round of bug fixing and cleanup. This time the focus is on the driver pattern to use mmu notifiers to monitor a VA range. This code is lifted out of many drivers and hmm_mirror directly into the mmu_notifier core and written using the best ideas from all the driver implementations. This removes many bugs from the drivers and has a very pleasing diffstat. More drivers can still be converted, but that is for another cycle. - A shared branch with RDMA reworking the RDMA ODP implementation - New mmu_interval_notifier API. This is focused on the use case of monitoring a VA and simplifies the process for drivers - A common seq-count locking scheme built into the mmu_interval_notifier API usable by drivers that call get_user_pages() or hmm_range_fault() with the VA range - Conversion of mlx5 ODP, hfi1, radeon, nouveau, AMD GPU, and Xen GntDev drivers to the new API. This deletes a lot of wonky driver code. - Two improvements for hmm_range_fault(), from testing done by Ralph" * tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: mm/hmm: remove hmm_range_dma_map and hmm_range_dma_unmap mm/hmm: make full use of walk_page_range() xen/gntdev: use mmu_interval_notifier_insert mm/hmm: remove hmm_mirror and related drm/amdgpu: Use mmu_interval_notifier instead of hmm_mirror drm/amdgpu: Use mmu_interval_insert instead of hmm_mirror drm/amdgpu: Call find_vma under mmap_sem nouveau: use mmu_interval_notifier instead of hmm_mirror nouveau: use mmu_notifier directly for invalidate_range_start drm/radeon: use mmu_interval_notifier_insert RDMA/hfi1: Use mmu_interval_notifier_insert for user_exp_rcv RDMA/odp: Use mmu_interval_notifier_insert() mm/hmm: define the pre-processor related parts of hmm.h even if disabled mm/hmm: allow hmm_range to be used with a mmu_interval_notifier or hmm_mirror mm/mmu_notifier: add an interval tree notifier mm/mmu_notifier: define the header pre-processor parts even if disabled mm/hmm: allow snapshot of the special zero page
Diffstat (limited to 'drivers/xen')
-rw-r--r--drivers/xen/gntdev-common.h8
-rw-r--r--drivers/xen/gntdev.c179
2 files changed, 49 insertions, 138 deletions
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;