summaryrefslogtreecommitdiffstats
path: root/fs/userfaultfd.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/userfaultfd.c')
-rw-r--r--fs/userfaultfd.c86
1 files changed, 22 insertions, 64 deletions
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 13ef4e1fc1..292f5fd501 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -50,45 +50,6 @@ static struct ctl_table vm_userfaultfd_table[] = {
static struct kmem_cache *userfaultfd_ctx_cachep __ro_after_init;
-/*
- * Start with fault_pending_wqh and fault_wqh so they're more likely
- * to be in the same cacheline.
- *
- * Locking order:
- * fd_wqh.lock
- * fault_pending_wqh.lock
- * fault_wqh.lock
- * event_wqh.lock
- *
- * To avoid deadlocks, IRQs must be disabled when taking any of the above locks,
- * since fd_wqh.lock is taken by aio_poll() while it's holding a lock that's
- * also taken in IRQ context.
- */
-struct userfaultfd_ctx {
- /* waitqueue head for the pending (i.e. not read) userfaults */
- wait_queue_head_t fault_pending_wqh;
- /* waitqueue head for the userfaults */
- wait_queue_head_t fault_wqh;
- /* waitqueue head for the pseudo fd to wakeup poll/read */
- wait_queue_head_t fd_wqh;
- /* waitqueue head for events */
- wait_queue_head_t event_wqh;
- /* a refile sequence protected by fault_pending_wqh lock */
- seqcount_spinlock_t refile_seq;
- /* pseudo fd refcounting */
- refcount_t refcount;
- /* userfaultfd syscall flags */
- unsigned int flags;
- /* features requested from the userspace */
- unsigned int features;
- /* released */
- bool released;
- /* memory mappings are changing because of non-cooperative event */
- atomic_t mmap_changing;
- /* mm with one ore more vmas attached to this userfaultfd_ctx */
- struct mm_struct *mm;
-};
-
struct userfaultfd_fork_ctx {
struct userfaultfd_ctx *orig;
struct userfaultfd_ctx *new;
@@ -724,12 +685,15 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
ctx->flags = octx->flags;
ctx->features = octx->features;
ctx->released = false;
+ init_rwsem(&ctx->map_changing_lock);
atomic_set(&ctx->mmap_changing, 0);
ctx->mm = vma->vm_mm;
mmgrab(ctx->mm);
userfaultfd_ctx_get(octx);
+ down_write(&octx->map_changing_lock);
atomic_inc(&octx->mmap_changing);
+ up_write(&octx->map_changing_lock);
fctx->orig = octx;
fctx->new = ctx;
list_add_tail(&fctx->list, fcs);
@@ -776,7 +740,9 @@ void mremap_userfaultfd_prep(struct vm_area_struct *vma,
if (ctx->features & UFFD_FEATURE_EVENT_REMAP) {
vm_ctx->ctx = ctx;
userfaultfd_ctx_get(ctx);
+ down_write(&ctx->map_changing_lock);
atomic_inc(&ctx->mmap_changing);
+ up_write(&ctx->map_changing_lock);
} else {
/* Drop uffd context if remap feature not enabled */
vma_start_write(vma);
@@ -822,7 +788,9 @@ bool userfaultfd_remove(struct vm_area_struct *vma,
return true;
userfaultfd_ctx_get(ctx);
+ down_write(&ctx->map_changing_lock);
atomic_inc(&ctx->mmap_changing);
+ up_write(&ctx->map_changing_lock);
mmap_read_unlock(mm);
msg_init(&ewq.msg);
@@ -864,7 +832,9 @@ int userfaultfd_unmap_prep(struct vm_area_struct *vma, unsigned long start,
return -ENOMEM;
userfaultfd_ctx_get(ctx);
+ down_write(&ctx->map_changing_lock);
atomic_inc(&ctx->mmap_changing);
+ up_write(&ctx->map_changing_lock);
unmap_ctx->ctx = ctx;
unmap_ctx->start = start;
unmap_ctx->end = end;
@@ -1752,9 +1722,8 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
if (uffdio_copy.mode & UFFDIO_COPY_MODE_WP)
flags |= MFILL_ATOMIC_WP;
if (mmget_not_zero(ctx->mm)) {
- ret = mfill_atomic_copy(ctx->mm, uffdio_copy.dst, uffdio_copy.src,
- uffdio_copy.len, &ctx->mmap_changing,
- flags);
+ ret = mfill_atomic_copy(ctx, uffdio_copy.dst, uffdio_copy.src,
+ uffdio_copy.len, flags);
mmput(ctx->mm);
} else {
return -ESRCH;
@@ -1804,9 +1773,8 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
goto out;
if (mmget_not_zero(ctx->mm)) {
- ret = mfill_atomic_zeropage(ctx->mm, uffdio_zeropage.range.start,
- uffdio_zeropage.range.len,
- &ctx->mmap_changing);
+ ret = mfill_atomic_zeropage(ctx, uffdio_zeropage.range.start,
+ uffdio_zeropage.range.len);
mmput(ctx->mm);
} else {
return -ESRCH;
@@ -1861,9 +1829,8 @@ static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
return -EINVAL;
if (mmget_not_zero(ctx->mm)) {
- ret = mwriteprotect_range(ctx->mm, uffdio_wp.range.start,
- uffdio_wp.range.len, mode_wp,
- &ctx->mmap_changing);
+ ret = mwriteprotect_range(ctx, uffdio_wp.range.start,
+ uffdio_wp.range.len, mode_wp);
mmput(ctx->mm);
} else {
return -ESRCH;
@@ -1913,9 +1880,8 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
flags |= MFILL_ATOMIC_WP;
if (mmget_not_zero(ctx->mm)) {
- ret = mfill_atomic_continue(ctx->mm, uffdio_continue.range.start,
- uffdio_continue.range.len,
- &ctx->mmap_changing, flags);
+ ret = mfill_atomic_continue(ctx, uffdio_continue.range.start,
+ uffdio_continue.range.len, flags);
mmput(ctx->mm);
} else {
return -ESRCH;
@@ -1968,9 +1934,8 @@ static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long
goto out;
if (mmget_not_zero(ctx->mm)) {
- ret = mfill_atomic_poison(ctx->mm, uffdio_poison.range.start,
- uffdio_poison.range.len,
- &ctx->mmap_changing, 0);
+ ret = mfill_atomic_poison(ctx, uffdio_poison.range.start,
+ uffdio_poison.range.len, 0);
mmput(ctx->mm);
} else {
return -ESRCH;
@@ -2044,16 +2009,8 @@ static int userfaultfd_move(struct userfaultfd_ctx *ctx,
return -EINVAL;
if (mmget_not_zero(mm)) {
- mmap_read_lock(mm);
-
- /* Re-check after taking mmap_lock */
- if (likely(!atomic_read(&ctx->mmap_changing)))
- ret = move_pages(ctx, mm, uffdio_move.dst, uffdio_move.src,
- uffdio_move.len, uffdio_move.mode);
- else
- ret = -EINVAL;
-
- mmap_read_unlock(mm);
+ ret = move_pages(ctx, uffdio_move.dst, uffdio_move.src,
+ uffdio_move.len, uffdio_move.mode);
mmput(mm);
} else {
return -ESRCH;
@@ -2259,6 +2216,7 @@ static int new_userfaultfd(int flags)
ctx->flags = flags;
ctx->features = 0;
ctx->released = false;
+ init_rwsem(&ctx->map_changing_lock);
atomic_set(&ctx->mmap_changing, 0);
ctx->mm = current->mm;
/* prevent the mm struct to be freed */