Performing userfaultfd operations (like copy/move etc.) in critical
section of mmap_lock (read-mode) causes significant contention on the
lock when operations requiring the lock in write-mode are taking place
concurrently. We can use per-vma locks instead to significantly reduce
the contention issue.
Android runtime's Garbage Collector uses userfaultfd for concurrent
compaction. mmap-lock contention during compaction potentially causes
jittery experience for the user. During one such reproducible scenario,
we observed the following improvements with this patch-set:
- Wall clock time of compaction phase came down from ~3s to <500ms
- Uninterruptible sleep time (across all threads in the process) was
~10ms (none in mmap_lock) during compaction, instead of >20s
Changes since v5 [5]:
- Use abstract function names (like uffd_mfill_lock/uffd_mfill_unlock)
to avoid using too many #ifdef's, per Suren Baghdasaryan and Liam
Howlett
- Use 'unlikely' (as earlier) to anon_vma related checks, per Liam Howlett
- Eliminate redundant ptr->err->ptr conversion, per Liam Howlett
- Use 'int' instead of 'long' for error return type, per Liam Howlett
Changes since v4 [4]:
- Fix possible deadlock in find_and_lock_vmas() which may arise if
lock_vma() is used for both src and dst vmas.
- Ensure we lock vma only once if src and dst vmas are same.
- Fix error handling in move_pages() after successfully locking vmas.
- Introduce helper function for finding dst vma and preparing its
anon_vma when done in mmap_lock critical section, per Liam Howlett.
- Introduce helper function for finding dst and src vmas when done in
mmap_lock critical section.
Changes since v3 [3]:
- Rename function names to clearly reflect which lock is being taken,
per Liam Howlett.
- Have separate functions and abstractions in mm/userfaultfd.c to avoid
confusion around which lock is being acquired/released, per Liam Howlett.
- Prepare anon_vma for all private vmas, anonymous or file-backed,
per Jann Horn.
Changes since v2 [2]:
- Implement and use lock_vma() which uses mmap_lock critical section
to lock the VMA using per-vma lock if lock_vma_under_rcu() fails,
per Liam R. Howlett. This helps simplify the code and also avoids
performing the entire userfaultfd operation under mmap_lock.
Changes since v1 [1]:
- rebase patches on 'mm-unstable' branch
[1] https://lore.kernel.org/all/[email protected]/
[2] https://lore.kernel.org/all/[email protected]/
[3] https://lore.kernel.org/all/[email protected]/
[4] https://lore.kernel.org/all/[email protected]/
[5] https://lore.kernel.org/all/[email protected]/
Lokesh Gidra (3):
userfaultfd: move userfaultfd_ctx struct to header file
userfaultfd: protect mmap_changing with rw_sem in userfaulfd_ctx
userfaultfd: use per-vma locks in userfaultfd operations
fs/userfaultfd.c | 86 ++-----
include/linux/userfaultfd_k.h | 75 ++++--
mm/userfaultfd.c | 438 +++++++++++++++++++++++++---------
3 files changed, 405 insertions(+), 194 deletions(-)
--
2.43.0.687.g38aa6559b0-goog
All userfaultfd operations, except write-protect, opportunistically use
per-vma locks to lock vmas. On failure, attempt again inside mmap_lock
critical section.
Write-protect operation requires mmap_lock as it iterates over multiple
vmas.
Signed-off-by: Lokesh Gidra <[email protected]>
---
fs/userfaultfd.c | 13 +-
include/linux/userfaultfd_k.h | 5 +-
mm/userfaultfd.c | 380 ++++++++++++++++++++++++++--------
3 files changed, 296 insertions(+), 102 deletions(-)
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index c00a021bcce4..60dcfafdc11a 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -2005,17 +2005,8 @@ static int userfaultfd_move(struct userfaultfd_ctx *ctx,
return -EINVAL;
if (mmget_not_zero(mm)) {
- mmap_read_lock(mm);
-
- /* Re-check after taking map_changing_lock */
- down_read(&ctx->map_changing_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 = -EAGAIN;
- up_read(&ctx->map_changing_lock);
- 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;
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 3210c3552976..05d59f74fc88 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -138,9 +138,8 @@ extern long uffd_wp_range(struct vm_area_struct *vma,
/* move_pages */
void double_pt_lock(spinlock_t *ptl1, spinlock_t *ptl2);
void double_pt_unlock(spinlock_t *ptl1, spinlock_t *ptl2);
-ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
- unsigned long dst_start, unsigned long src_start,
- unsigned long len, __u64 flags);
+ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start,
+ unsigned long src_start, unsigned long len, __u64 flags);
int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pmd_t dst_pmdval,
struct vm_area_struct *dst_vma,
struct vm_area_struct *src_vma,
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 74aad0831e40..4744d6a96f96 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -20,19 +20,11 @@
#include "internal.h"
static __always_inline
-struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm,
- unsigned long dst_start,
- unsigned long len)
+bool validate_dst_vma(struct vm_area_struct *dst_vma, unsigned long dst_end)
{
- /*
- * Make sure that the dst range is both valid and fully within a
- * single existing vma.
- */
- struct vm_area_struct *dst_vma;
-
- dst_vma = find_vma(dst_mm, dst_start);
- if (!range_in_vma(dst_vma, dst_start, dst_start + len))
- return NULL;
+ /* Make sure that the dst range is fully within dst_vma. */
+ if (dst_end > dst_vma->vm_end)
+ return false;
/*
* Check the vma is registered in uffd, this is required to
@@ -40,11 +32,122 @@ struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm,
* time.
*/
if (!dst_vma->vm_userfaultfd_ctx.ctx)
- return NULL;
+ return false;
+
+ return true;
+}
+
+static __always_inline
+struct vm_area_struct *find_vma_and_prepare_anon(struct mm_struct *mm,
+ unsigned long addr)
+{
+ struct vm_area_struct *vma;
+
+ mmap_assert_locked(mm);
+ vma = vma_lookup(mm, addr);
+ if (!vma)
+ vma = ERR_PTR(-ENOENT);
+ else if (!(vma->vm_flags & VM_SHARED) &&
+ unlikely(anon_vma_prepare(vma)))
+ vma = ERR_PTR(-ENOMEM);
+
+ return vma;
+}
+
+#ifdef CONFIG_PER_VMA_LOCK
+/*
+ * lock_vma() - Lookup and lock vma corresponding to @address.
+ * @mm: mm to search vma in.
+ * @address: address that the vma should contain.
+ *
+ * Should be called without holding mmap_lock. vma should be unlocked after use
+ * with unlock_vma().
+ *
+ * Return: A locked vma containing @address, -ENOENT if no vma is found, or
+ * -ENOMEM if anon_vma couldn't be allocated.
+ */
+static struct vm_area_struct *lock_vma(struct mm_struct *mm,
+ unsigned long address)
+{
+ struct vm_area_struct *vma;
+
+ vma = lock_vma_under_rcu(mm, address);
+ if (vma) {
+ /*
+ * lock_vma_under_rcu() only checks anon_vma for private
+ * anonymous mappings. But we need to ensure it is assigned in
+ * private file-backed vmas as well.
+ */
+ if (!(vma->vm_flags & VM_SHARED) && unlikely(!vma->anon_vma))
+ vma_end_read(vma);
+ else
+ return vma;
+ }
+
+ mmap_read_lock(mm);
+ vma = find_vma_and_prepare_anon(mm, address);
+ if (!IS_ERR(vma)) {
+ /*
+ * We cannot use vma_start_read() as it may fail due to
+ * false locked (see comment in vma_start_read()). We
+ * can avoid that by directly locking vm_lock under
+ * mmap_lock, which guarantees that nobody can lock the
+ * vma for write (vma_start_write()) under us.
+ */
+ down_read(&vma->vm_lock->lock);
+ }
+
+ mmap_read_unlock(mm);
+ return vma;
+}
+
+static struct vm_area_struct *uffd_mfill_lock(struct mm_struct *dst_mm,
+ unsigned long dst_start,
+ unsigned long len)
+{
+ struct vm_area_struct *dst_vma;
+ dst_vma = lock_vma(dst_mm, dst_start);
+ if (IS_ERR(dst_vma) || validate_dst_vma(dst_vma, dst_start + len))
+ return dst_vma;
+
+ vma_end_read(dst_vma);
+ return ERR_PTR(-ENOENT);
+}
+
+static void uffd_mfill_unlock(struct vm_area_struct *vma)
+{
+ vma_end_read(vma);
+}
+
+#else
+
+static struct vm_area_struct *uffd_mfill_lock(struct mm_struct *dst_mm,
+ unsigned long dst_start,
+ unsigned long len)
+{
+ struct vm_area_struct *dst_vma;
+
+ mmap_read_lock(dst_mm);
+ dst_vma = find_vma_and_prepare_anon(dst_mm, dst_start);
+ if (IS_ERR(dst_vma))
+ goto out_unlock;
+
+ if (validate_dst_vma(dst_vma, dst_start + len))
+ return dst_vma;
+
+ dst_vma = ERR_PTR(-ENOENT);
+out_unlock:
+ mmap_read_unlock(dst_mm);
return dst_vma;
}
+static void uffd_mfill_unlock(struct vm_area_struct *vma)
+{
+ mmap_read_unlock(vma->vm_mm);
+}
+#endif
+
/* Check if dst_addr is outside of file's size. Must be called with ptl held. */
static bool mfill_file_over_size(struct vm_area_struct *dst_vma,
unsigned long dst_addr)
@@ -350,7 +453,8 @@ static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address)
#ifdef CONFIG_HUGETLB_PAGE
/*
* mfill_atomic processing for HUGETLB vmas. Note that this routine is
- * called with mmap_lock held, it will release mmap_lock before returning.
+ * called with either vma-lock or mmap_lock held, it will release the lock
+ * before returning.
*/
static __always_inline ssize_t mfill_atomic_hugetlb(
struct userfaultfd_ctx *ctx,
@@ -361,7 +465,6 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
uffd_flags_t flags)
{
struct mm_struct *dst_mm = dst_vma->vm_mm;
- int vm_shared = dst_vma->vm_flags & VM_SHARED;
ssize_t err;
pte_t *dst_pte;
unsigned long src_addr, dst_addr;
@@ -380,7 +483,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
*/
if (uffd_flags_mode_is(flags, MFILL_ATOMIC_ZEROPAGE)) {
up_read(&ctx->map_changing_lock);
- mmap_read_unlock(dst_mm);
+ uffd_mfill_unlock(dst_vma);
return -EINVAL;
}
@@ -403,24 +506,28 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
* retry, dst_vma will be set to NULL and we must lookup again.
*/
if (!dst_vma) {
+ dst_vma = uffd_mfill_lock(dst_mm, dst_start, len);
+ if (IS_ERR(dst_vma)) {
+ err = PTR_ERR(dst_vma);
+ goto out;
+ }
+
err = -ENOENT;
- dst_vma = find_dst_vma(dst_mm, dst_start, len);
- if (!dst_vma || !is_vm_hugetlb_page(dst_vma))
- goto out_unlock;
+ if (!is_vm_hugetlb_page(dst_vma))
+ goto out_unlock_vma;
err = -EINVAL;
if (vma_hpagesize != vma_kernel_pagesize(dst_vma))
- goto out_unlock;
-
- vm_shared = dst_vma->vm_flags & VM_SHARED;
- }
+ goto out_unlock_vma;
- /*
- * If not shared, ensure the dst_vma has a anon_vma.
- */
- err = -ENOMEM;
- if (!vm_shared) {
- if (unlikely(anon_vma_prepare(dst_vma)))
+ /*
+ * If memory mappings are changing because of non-cooperative
+ * operation (e.g. mremap) running in parallel, bail out and
+ * request the user to retry later
+ */
+ down_read(&ctx->map_changing_lock);
+ err = -EAGAIN;
+ if (atomic_read(&ctx->mmap_changing))
goto out_unlock;
}
@@ -465,7 +572,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
if (unlikely(err == -ENOENT)) {
up_read(&ctx->map_changing_lock);
- mmap_read_unlock(dst_mm);
+ uffd_mfill_unlock(dst_vma);
BUG_ON(!folio);
err = copy_folio_from_user(folio,
@@ -474,17 +581,6 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
err = -EFAULT;
goto out;
}
- mmap_read_lock(dst_mm);
- down_read(&ctx->map_changing_lock);
- /*
- * If memory mappings are changing because of non-cooperative
- * operation (e.g. mremap) running in parallel, bail out and
- * request the user to retry later
- */
- if (atomic_read(&ctx->mmap_changing)) {
- err = -EAGAIN;
- break;
- }
dst_vma = NULL;
goto retry;
@@ -505,7 +601,8 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
out_unlock:
up_read(&ctx->map_changing_lock);
- mmap_read_unlock(dst_mm);
+out_unlock_vma:
+ uffd_mfill_unlock(dst_vma);
out:
if (folio)
folio_put(folio);
@@ -597,7 +694,15 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
copied = 0;
folio = NULL;
retry:
- mmap_read_lock(dst_mm);
+ /*
+ * Make sure the vma is not shared, that the dst range is
+ * both valid and fully within a single existing vma.
+ */
+ dst_vma = uffd_mfill_lock(dst_mm, dst_start, len);
+ if (IS_ERR(dst_vma)) {
+ err = PTR_ERR(dst_vma);
+ goto out;
+ }
/*
* If memory mappings are changing because of non-cooperative
@@ -609,15 +714,6 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
if (atomic_read(&ctx->mmap_changing))
goto out_unlock;
- /*
- * Make sure the vma is not shared, that the dst range is
- * both valid and fully within a single existing vma.
- */
- err = -ENOENT;
- dst_vma = find_dst_vma(dst_mm, dst_start, len);
- if (!dst_vma)
- goto out_unlock;
-
err = -EINVAL;
/*
* shmem_zero_setup is invoked in mmap for MAP_ANONYMOUS|MAP_SHARED but
@@ -647,16 +743,6 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE))
goto out_unlock;
- /*
- * Ensure the dst_vma has a anon_vma or this page
- * would get a NULL anon_vma when moved in the
- * dst_vma.
- */
- err = -ENOMEM;
- if (!(dst_vma->vm_flags & VM_SHARED) &&
- unlikely(anon_vma_prepare(dst_vma)))
- goto out_unlock;
-
while (src_addr < src_start + len) {
pmd_t dst_pmdval;
@@ -699,7 +785,7 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
void *kaddr;
up_read(&ctx->map_changing_lock);
- mmap_read_unlock(dst_mm);
+ uffd_mfill_unlock(dst_vma);
BUG_ON(!folio);
kaddr = kmap_local_folio(folio, 0);
@@ -730,7 +816,7 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
out_unlock:
up_read(&ctx->map_changing_lock);
- mmap_read_unlock(dst_mm);
+ uffd_mfill_unlock(dst_vma);
out:
if (folio)
folio_put(folio);
@@ -1267,27 +1353,136 @@ static int validate_move_areas(struct userfaultfd_ctx *ctx,
if (!vma_is_anonymous(src_vma) || !vma_is_anonymous(dst_vma))
return -EINVAL;
+ return 0;
+}
+
+static __always_inline
+int find_vmas_mm_locked(struct mm_struct *mm,
+ unsigned long dst_start,
+ unsigned long src_start,
+ struct vm_area_struct **dst_vmap,
+ struct vm_area_struct **src_vmap)
+{
+ struct vm_area_struct *vma;
+
+ mmap_assert_locked(mm);
+ vma = find_vma_and_prepare_anon(mm, dst_start);
+ if (IS_ERR(vma))
+ return PTR_ERR(vma);
+
+ *dst_vmap = vma;
+ /* Skip finding src_vma if src_start is in dst_vma */
+ if (src_start >= vma->vm_start && src_start < vma->vm_end)
+ goto out_success;
+
+ vma = vma_lookup(mm, src_start);
+ if (!vma)
+ return -ENOENT;
+out_success:
+ *src_vmap = vma;
+ return 0;
+}
+
+#ifdef CONFIG_PER_VMA_LOCK
+static int uffd_move_lock(struct mm_struct *mm,
+ unsigned long dst_start,
+ unsigned long src_start,
+ struct vm_area_struct **dst_vmap,
+ struct vm_area_struct **src_vmap)
+{
+ struct vm_area_struct *vma;
+ int err;
+
+ vma = lock_vma(mm, dst_start);
+ if (IS_ERR(vma))
+ return PTR_ERR(vma);
+
+ *dst_vmap = vma;
/*
- * Ensure the dst_vma has a anon_vma or this page
- * would get a NULL anon_vma when moved in the
- * dst_vma.
+ * Skip finding src_vma if src_start is in dst_vma. This also ensures
+ * that we don't lock the same vma twice.
*/
- if (unlikely(anon_vma_prepare(dst_vma)))
- return -ENOMEM;
+ if (src_start >= vma->vm_start && src_start < vma->vm_end) {
+ *src_vmap = vma;
+ return 0;
+ }
- return 0;
+ /*
+ * Using lock_vma() to get src_vma can lead to following deadlock:
+ *
+ * Thread1 Thread2
+ * ------- -------
+ * vma_start_read(dst_vma)
+ * mmap_write_lock(mm)
+ * vma_start_write(src_vma)
+ * vma_start_read(src_vma)
+ * mmap_read_lock(mm)
+ * vma_start_write(dst_vma)
+ */
+ *src_vmap = lock_vma_under_rcu(mm, src_start);
+ if (likely(*src_vmap))
+ return 0;
+
+ /* Undo any locking and retry in mmap_lock critical section */
+ vma_end_read(*dst_vmap);
+
+ mmap_read_lock(mm);
+ err = find_vmas_mm_locked(mm, dst_start, src_start, dst_vmap, src_vmap);
+ if (!err) {
+ /*
+ * See comment in lock_vma() as to why not using
+ * vma_start_read() here.
+ */
+ down_read(&(*dst_vmap)->vm_lock->lock);
+ if (*dst_vmap != *src_vmap)
+ down_read(&(*src_vmap)->vm_lock->lock);
+ }
+ mmap_read_unlock(mm);
+ return err;
+}
+
+static void uffd_move_unlock(struct vm_area_struct *dst_vma,
+ struct vm_area_struct *src_vma)
+{
+ vma_end_read(src_vma);
+ if (src_vma != dst_vma)
+ vma_end_read(dst_vma);
}
+#else
+
+static int uffd_move_lock(struct mm_struct *mm,
+ unsigned long dst_start,
+ unsigned long src_start,
+ struct vm_area_struct **dst_vmap,
+ struct vm_area_struct **src_vmap)
+{
+ int err;
+
+ mmap_read_lock(mm);
+ err = find_vmas_mm_locked(mm, dst_start, src_start, dst_vmap, src_vmap);
+ if (err)
+ mmap_read_unlock(mm);
+ return err;
+}
+
+static void uffd_move_unlock(struct vm_area_struct *dst_vma,
+ struct vm_area_struct *src_vma)
+{
+ mmap_assert_locked(src_vma->vm_mm);
+ mmap_read_unlock(dst_vma->vm_mm);
+}
+#endif
+
/**
* move_pages - move arbitrary anonymous pages of an existing vma
* @ctx: pointer to the userfaultfd context
- * @mm: the address space to move pages
* @dst_start: start of the destination virtual memory range
* @src_start: start of the source virtual memory range
* @len: length of the virtual memory range
* @mode: flags from uffdio_move.mode
*
- * Must be called with mmap_lock held for read.
+ * It will either use the mmap_lock in read mode or per-vma locks
*
* move_pages() remaps arbitrary anonymous pages atomically in zero
* copy. It only works on non shared anonymous pages because those can
@@ -1355,10 +1550,10 @@ static int validate_move_areas(struct userfaultfd_ctx *ctx,
* could be obtained. This is the only additional complexity added to
* the rmap code to provide this anonymous page remapping functionality.
*/
-ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
- unsigned long dst_start, unsigned long src_start,
- unsigned long len, __u64 mode)
+ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start,
+ unsigned long src_start, unsigned long len, __u64 mode)
{
+ struct mm_struct *mm = ctx->mm;
struct vm_area_struct *src_vma, *dst_vma;
unsigned long src_addr, dst_addr;
pmd_t *src_pmd, *dst_pmd;
@@ -1376,28 +1571,34 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
WARN_ON_ONCE(dst_start + len <= dst_start))
goto out;
+ err = uffd_move_lock(mm, dst_start, src_start, &dst_vma, &src_vma);
+ if (err)
+ goto out;
+
+ /* Re-check after taking map_changing_lock */
+ err = -EAGAIN;
+ down_read(&ctx->map_changing_lock);
+ if (likely(atomic_read(&ctx->mmap_changing)))
+ goto out_unlock;
/*
* Make sure the vma is not shared, that the src and dst remap
* ranges are both valid and fully within a single existing
* vma.
*/
- src_vma = find_vma(mm, src_start);
- if (!src_vma || (src_vma->vm_flags & VM_SHARED))
- goto out;
- if (src_start < src_vma->vm_start ||
- src_start + len > src_vma->vm_end)
- goto out;
+ err = -EINVAL;
+ if (src_vma->vm_flags & VM_SHARED)
+ goto out_unlock;
+ if (src_start + len > src_vma->vm_end)
+ goto out_unlock;
- dst_vma = find_vma(mm, dst_start);
- if (!dst_vma || (dst_vma->vm_flags & VM_SHARED))
- goto out;
- if (dst_start < dst_vma->vm_start ||
- dst_start + len > dst_vma->vm_end)
- goto out;
+ if (dst_vma->vm_flags & VM_SHARED)
+ goto out_unlock;
+ if (dst_start + len > dst_vma->vm_end)
+ goto out_unlock;
err = validate_move_areas(ctx, src_vma, dst_vma);
if (err)
- goto out;
+ goto out_unlock;
for (src_addr = src_start, dst_addr = dst_start;
src_addr < src_start + len;) {
@@ -1514,6 +1715,9 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
moved += step_size;
}
+out_unlock:
+ up_read(&ctx->map_changing_lock);
+ uffd_move_unlock(dst_vma, src_vma);
out:
VM_WARN_ON(moved < 0);
VM_WARN_ON(err > 0);
--
2.43.0.687.g38aa6559b0-goog
Moving the struct to userfaultfd_k.h to be accessible from
mm/userfaultfd.c. There are no other changes in the struct.
This is required to prepare for using per-vma locks in userfaultfd
operations.
Signed-off-by: Lokesh Gidra <[email protected]>
Reviewed-by: Mike Rapoport (IBM) <[email protected]>
---
fs/userfaultfd.c | 39 -----------------------------------
include/linux/userfaultfd_k.h | 39 +++++++++++++++++++++++++++++++++++
2 files changed, 39 insertions(+), 39 deletions(-)
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 05c8e8a05427..58331b83d648 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;
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index e4056547fbe6..691d928ee864 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -36,6 +36,45 @@
#define UFFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK)
#define UFFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS)
+/*
+ * 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;
+};
+
extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason);
/* A combined operation mode + behavior flags. */
--
2.43.0.687.g38aa6559b0-goog
Increments and loads to mmap_changing are always in mmap_lock
critical section. This ensures that if userspace requests event
notification for non-cooperative operations (e.g. mremap), userfaultfd
operations don't occur concurrently.
This can be achieved by using a separate read-write semaphore in
userfaultfd_ctx such that increments are done in write-mode and loads
in read-mode, thereby eliminating the dependency on mmap_lock for this
purpose.
This is a preparatory step before we replace mmap_lock usage with
per-vma locks in fill/move ioctls.
Signed-off-by: Lokesh Gidra <[email protected]>
Reviewed-by: Mike Rapoport (IBM) <[email protected]>
---
fs/userfaultfd.c | 40 ++++++++++++----------
include/linux/userfaultfd_k.h | 31 ++++++++++--------
mm/userfaultfd.c | 62 ++++++++++++++++++++---------------
3 files changed, 75 insertions(+), 58 deletions(-)
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 58331b83d648..c00a021bcce4 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -685,12 +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);
@@ -737,7 +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);
@@ -783,7 +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);
@@ -825,7 +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;
@@ -1709,9 +1718,8 @@ 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;
@@ -1761,9 +1769,8 @@ 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;
@@ -1818,9 +1825,8 @@ 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;
@@ -1870,9 +1876,8 @@ 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;
@@ -1925,9 +1930,8 @@ 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;
@@ -2003,13 +2007,14 @@ static int userfaultfd_move(struct userfaultfd_ctx *ctx,
if (mmget_not_zero(mm)) {
mmap_read_lock(mm);
- /* Re-check after taking mmap_lock */
+ /* Re-check after taking map_changing_lock */
+ down_read(&ctx->map_changing_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 = -EAGAIN;
-
+ up_read(&ctx->map_changing_lock);
mmap_read_unlock(mm);
mmput(mm);
} else {
@@ -2216,6 +2221,7 @@ 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 */
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 691d928ee864..3210c3552976 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -69,6 +69,13 @@ struct userfaultfd_ctx {
unsigned int features;
/* released */
bool released;
+ /*
+ * Prevents userfaultfd operations (fill/move/wp) from happening while
+ * some non-cooperative event(s) is taking place. Increments are done
+ * in write-mode. Whereas, userfaultfd operations, which includes
+ * reading mmap_changing, is done under read-mode.
+ */
+ struct rw_semaphore map_changing_lock;
/* memory mappings are changing because of non-cooperative event */
atomic_t mmap_changing;
/* mm with one ore more vmas attached to this userfaultfd_ctx */
@@ -113,22 +120,18 @@ extern int mfill_atomic_install_pte(pmd_t *dst_pmd,
unsigned long dst_addr, struct page *page,
bool newly_allocated, uffd_flags_t flags);
-extern ssize_t mfill_atomic_copy(struct mm_struct *dst_mm, unsigned long dst_start,
+extern ssize_t mfill_atomic_copy(struct userfaultfd_ctx *ctx, unsigned long dst_start,
unsigned long src_start, unsigned long len,
- atomic_t *mmap_changing, uffd_flags_t flags);
-extern ssize_t mfill_atomic_zeropage(struct mm_struct *dst_mm,
+ uffd_flags_t flags);
+extern ssize_t mfill_atomic_zeropage(struct userfaultfd_ctx *ctx,
unsigned long dst_start,
- unsigned long len,
- atomic_t *mmap_changing);
-extern ssize_t mfill_atomic_continue(struct mm_struct *dst_mm, unsigned long dst_start,
- unsigned long len, atomic_t *mmap_changing,
- uffd_flags_t flags);
-extern ssize_t mfill_atomic_poison(struct mm_struct *dst_mm, unsigned long start,
- unsigned long len, atomic_t *mmap_changing,
- uffd_flags_t flags);
-extern int mwriteprotect_range(struct mm_struct *dst_mm,
- unsigned long start, unsigned long len,
- bool enable_wp, atomic_t *mmap_changing);
+ unsigned long len);
+extern ssize_t mfill_atomic_continue(struct userfaultfd_ctx *ctx, unsigned long dst_start,
+ unsigned long len, uffd_flags_t flags);
+extern ssize_t mfill_atomic_poison(struct userfaultfd_ctx *ctx, unsigned long start,
+ unsigned long len, uffd_flags_t flags);
+extern int mwriteprotect_range(struct userfaultfd_ctx *ctx, unsigned long start,
+ unsigned long len, bool enable_wp);
extern long uffd_wp_range(struct vm_area_struct *vma,
unsigned long start, unsigned long len, bool enable_wp);
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 9cc93cc1330b..74aad0831e40 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -353,11 +353,11 @@ static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address)
* called with mmap_lock held, it will release mmap_lock before returning.
*/
static __always_inline ssize_t mfill_atomic_hugetlb(
+ struct userfaultfd_ctx *ctx,
struct vm_area_struct *dst_vma,
unsigned long dst_start,
unsigned long src_start,
unsigned long len,
- atomic_t *mmap_changing,
uffd_flags_t flags)
{
struct mm_struct *dst_mm = dst_vma->vm_mm;
@@ -379,6 +379,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
* feature is not supported.
*/
if (uffd_flags_mode_is(flags, MFILL_ATOMIC_ZEROPAGE)) {
+ up_read(&ctx->map_changing_lock);
mmap_read_unlock(dst_mm);
return -EINVAL;
}
@@ -463,6 +464,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
cond_resched();
if (unlikely(err == -ENOENT)) {
+ up_read(&ctx->map_changing_lock);
mmap_read_unlock(dst_mm);
BUG_ON(!folio);
@@ -473,12 +475,13 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
goto out;
}
mmap_read_lock(dst_mm);
+ down_read(&ctx->map_changing_lock);
/*
* If memory mappings are changing because of non-cooperative
* operation (e.g. mremap) running in parallel, bail out and
* request the user to retry later
*/
- if (mmap_changing && atomic_read(mmap_changing)) {
+ if (atomic_read(&ctx->mmap_changing)) {
err = -EAGAIN;
break;
}
@@ -501,6 +504,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
}
out_unlock:
+ up_read(&ctx->map_changing_lock);
mmap_read_unlock(dst_mm);
out:
if (folio)
@@ -512,11 +516,11 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
}
#else /* !CONFIG_HUGETLB_PAGE */
/* fail at build time if gcc attempts to use this */
-extern ssize_t mfill_atomic_hugetlb(struct vm_area_struct *dst_vma,
+extern ssize_t mfill_atomic_hugetlb(struct userfaultfd_ctx *ctx,
+ struct vm_area_struct *dst_vma,
unsigned long dst_start,
unsigned long src_start,
unsigned long len,
- atomic_t *mmap_changing,
uffd_flags_t flags);
#endif /* CONFIG_HUGETLB_PAGE */
@@ -564,13 +568,13 @@ static __always_inline ssize_t mfill_atomic_pte(pmd_t *dst_pmd,
return err;
}
-static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm,
+static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
unsigned long dst_start,
unsigned long src_start,
unsigned long len,
- atomic_t *mmap_changing,
uffd_flags_t flags)
{
+ struct mm_struct *dst_mm = ctx->mm;
struct vm_area_struct *dst_vma;
ssize_t err;
pmd_t *dst_pmd;
@@ -600,8 +604,9 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm,
* operation (e.g. mremap) running in parallel, bail out and
* request the user to retry later
*/
+ down_read(&ctx->map_changing_lock);
err = -EAGAIN;
- if (mmap_changing && atomic_read(mmap_changing))
+ if (atomic_read(&ctx->mmap_changing))
goto out_unlock;
/*
@@ -633,8 +638,8 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm,
* If this is a HUGETLB vma, pass off to appropriate routine
*/
if (is_vm_hugetlb_page(dst_vma))
- return mfill_atomic_hugetlb(dst_vma, dst_start, src_start,
- len, mmap_changing, flags);
+ return mfill_atomic_hugetlb(ctx, dst_vma, dst_start,
+ src_start, len, flags);
if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma))
goto out_unlock;
@@ -693,6 +698,7 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm,
if (unlikely(err == -ENOENT)) {
void *kaddr;
+ up_read(&ctx->map_changing_lock);
mmap_read_unlock(dst_mm);
BUG_ON(!folio);
@@ -723,6 +729,7 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm,
}
out_unlock:
+ up_read(&ctx->map_changing_lock);
mmap_read_unlock(dst_mm);
out:
if (folio)
@@ -733,34 +740,33 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm,
return copied ? copied : err;
}
-ssize_t mfill_atomic_copy(struct mm_struct *dst_mm, unsigned long dst_start,
+ssize_t mfill_atomic_copy(struct userfaultfd_ctx *ctx, unsigned long dst_start,
unsigned long src_start, unsigned long len,
- atomic_t *mmap_changing, uffd_flags_t flags)
+ uffd_flags_t flags)
{
- return mfill_atomic(dst_mm, dst_start, src_start, len, mmap_changing,
+ return mfill_atomic(ctx, dst_start, src_start, len,
uffd_flags_set_mode(flags, MFILL_ATOMIC_COPY));
}
-ssize_t mfill_atomic_zeropage(struct mm_struct *dst_mm, unsigned long start,
- unsigned long len, atomic_t *mmap_changing)
+ssize_t mfill_atomic_zeropage(struct userfaultfd_ctx *ctx,
+ unsigned long start,
+ unsigned long len)
{
- return mfill_atomic(dst_mm, start, 0, len, mmap_changing,
+ return mfill_atomic(ctx, start, 0, len,
uffd_flags_set_mode(0, MFILL_ATOMIC_ZEROPAGE));
}
-ssize_t mfill_atomic_continue(struct mm_struct *dst_mm, unsigned long start,
- unsigned long len, atomic_t *mmap_changing,
- uffd_flags_t flags)
+ssize_t mfill_atomic_continue(struct userfaultfd_ctx *ctx, unsigned long start,
+ unsigned long len, uffd_flags_t flags)
{
- return mfill_atomic(dst_mm, start, 0, len, mmap_changing,
+ return mfill_atomic(ctx, start, 0, len,
uffd_flags_set_mode(flags, MFILL_ATOMIC_CONTINUE));
}
-ssize_t mfill_atomic_poison(struct mm_struct *dst_mm, unsigned long start,
- unsigned long len, atomic_t *mmap_changing,
- uffd_flags_t flags)
+ssize_t mfill_atomic_poison(struct userfaultfd_ctx *ctx, unsigned long start,
+ unsigned long len, uffd_flags_t flags)
{
- return mfill_atomic(dst_mm, start, 0, len, mmap_changing,
+ return mfill_atomic(ctx, start, 0, len,
uffd_flags_set_mode(flags, MFILL_ATOMIC_POISON));
}
@@ -793,10 +799,10 @@ long uffd_wp_range(struct vm_area_struct *dst_vma,
return ret;
}
-int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
- unsigned long len, bool enable_wp,
- atomic_t *mmap_changing)
+int mwriteprotect_range(struct userfaultfd_ctx *ctx, unsigned long start,
+ unsigned long len, bool enable_wp)
{
+ struct mm_struct *dst_mm = ctx->mm;
unsigned long end = start + len;
unsigned long _start, _end;
struct vm_area_struct *dst_vma;
@@ -820,8 +826,9 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
* operation (e.g. mremap) running in parallel, bail out and
* request the user to retry later
*/
+ down_read(&ctx->map_changing_lock);
err = -EAGAIN;
- if (mmap_changing && atomic_read(mmap_changing))
+ if (atomic_read(&ctx->mmap_changing))
goto out_unlock;
err = -ENOENT;
@@ -850,6 +857,7 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
err = 0;
}
out_unlock:
+ up_read(&ctx->map_changing_lock);
mmap_read_unlock(dst_mm);
return err;
}
--
2.43.0.687.g38aa6559b0-goog
* Lokesh Gidra <[email protected]> [240213 16:57]:
> Performing userfaultfd operations (like copy/move etc.) in critical
> section of mmap_lock (read-mode) causes significant contention on the
> lock when operations requiring the lock in write-mode are taking place
> concurrently. We can use per-vma locks instead to significantly reduce
> the contention issue.
>
> Android runtime's Garbage Collector uses userfaultfd for concurrent
> compaction. mmap-lock contention during compaction potentially causes
> jittery experience for the user. During one such reproducible scenario,
> we observed the following improvements with this patch-set:
>
> - Wall clock time of compaction phase came down from ~3s to <500ms
> - Uninterruptible sleep time (across all threads in the process) was
> ~10ms (none in mmap_lock) during compaction, instead of >20s
This series looks good, Thanks!
Reviewed-by: Liam R. Howlett <[email protected]>
>
> Changes since v5 [5]:
> - Use abstract function names (like uffd_mfill_lock/uffd_mfill_unlock)
> to avoid using too many #ifdef's, per Suren Baghdasaryan and Liam
> Howlett
> - Use 'unlikely' (as earlier) to anon_vma related checks, per Liam Howlett
> - Eliminate redundant ptr->err->ptr conversion, per Liam Howlett
> - Use 'int' instead of 'long' for error return type, per Liam Howlett
>
> Changes since v4 [4]:
> - Fix possible deadlock in find_and_lock_vmas() which may arise if
> lock_vma() is used for both src and dst vmas.
> - Ensure we lock vma only once if src and dst vmas are same.
> - Fix error handling in move_pages() after successfully locking vmas.
> - Introduce helper function for finding dst vma and preparing its
> anon_vma when done in mmap_lock critical section, per Liam Howlett.
> - Introduce helper function for finding dst and src vmas when done in
> mmap_lock critical section.
>
> Changes since v3 [3]:
> - Rename function names to clearly reflect which lock is being taken,
> per Liam Howlett.
> - Have separate functions and abstractions in mm/userfaultfd.c to avoid
> confusion around which lock is being acquired/released, per Liam Howlett.
> - Prepare anon_vma for all private vmas, anonymous or file-backed,
> per Jann Horn.
>
> Changes since v2 [2]:
> - Implement and use lock_vma() which uses mmap_lock critical section
> to lock the VMA using per-vma lock if lock_vma_under_rcu() fails,
> per Liam R. Howlett. This helps simplify the code and also avoids
> performing the entire userfaultfd operation under mmap_lock.
>
> Changes since v1 [1]:
> - rebase patches on 'mm-unstable' branch
>
> [1] https://lore.kernel.org/all/[email protected]/
> [2] https://lore.kernel.org/all/[email protected]/
> [3] https://lore.kernel.org/all/[email protected]/
> [4] https://lore.kernel.org/all/[email protected]/
> [5] https://lore.kernel.org/all/[email protected]/
>
> Lokesh Gidra (3):
> userfaultfd: move userfaultfd_ctx struct to header file
> userfaultfd: protect mmap_changing with rw_sem in userfaulfd_ctx
> userfaultfd: use per-vma locks in userfaultfd operations
>
> fs/userfaultfd.c | 86 ++-----
> include/linux/userfaultfd_k.h | 75 ++++--
> mm/userfaultfd.c | 438 +++++++++++++++++++++++++---------
> 3 files changed, 405 insertions(+), 194 deletions(-)
>
> --
> 2.43.0.687.g38aa6559b0-goog
>
On 13/02/2024 21:57, Lokesh Gidra wrote:
> All userfaultfd operations, except write-protect, opportunistically use
> per-vma locks to lock vmas. On failure, attempt again inside mmap_lock
> critical section.
>
> Write-protect operation requires mmap_lock as it iterates over multiple
> vmas.
Hi,
I'm seeing the below OOPS when running on arm64 against mm-unstable. It can be reliably reproduced by running the `uffd-unit-tests` mm selftest. Bisecting mm-unstable leads to this patch:
# bad: [649936c3db47f8f75b9b927e4edf5922a0f240a6] mm: add swappiness= arg to memory.reclaim
git bisect bad 649936c3db47f8f75b9b927e4edf5922a0f240a6
# good: [54be6c6c5ae8e0d93a6c4641cb7528eb0b6ba478] Linux 6.8-rc3
git bisect good 54be6c6c5ae8e0d93a6c4641cb7528eb0b6ba478
# good: [10794cd18bb46c91c75fac44e551201cfe006baf] mm: zswap: warn when referencing a dead entry
git bisect good 10794cd18bb46c91c75fac44e551201cfe006baf
# good: [cb769b427edc7f46c7c764daa3421725bffdf315] mm-memcg-use-larger-batches-for-proactive-reclaim-v4
git bisect good cb769b427edc7f46c7c764daa3421725bffdf315
# good: [cfc5c1be4010c9972bc3f3d991235e8ea6928672] mm/z3fold: remove unneeded spinlock
git bisect good cfc5c1be4010c9972bc3f3d991235e8ea6928672
# good: [31094bce101651acb4747ab25d614bc893d65c89] kasan/test: avoid gcc warning for intentional overflow
git bisect good 31094bce101651acb4747ab25d614bc893d65c89
# bad: [55be0b2cd1fbf00e036e2e48ee0999599135af66] zram: do not allocate physically contiguous strm buffers
git bisect bad 55be0b2cd1fbf00e036e2e48ee0999599135af66
# good: [b11ca4a0a13024c0175dde56f9bd848803eddcd2] mm/mglru: improve swappiness handling
git bisect good b11ca4a0a13024c0175dde56f9bd848803eddcd2
# good: [22e7ccd57a1220afcd7c4da1f3005fd04d70014e] userfaultfd: move userfaultfd_ctx struct to header file
git bisect good 22e7ccd57a1220afcd7c4da1f3005fd04d70014e
# bad: [0a0d05338f13e64c9fb7ccd8f8d1793aaf33ec7d] userfaultfd: use per-vma locks in userfaultfd operations
git bisect bad 0a0d05338f13e64c9fb7ccd8f8d1793aaf33ec7d
# good: [8459e1c7acbe4442c6c0eef59825da1339e0a3cf] userfaultfd: protect mmap_changing with rw_sem in userfaulfd_ctx
git bisect good 8459e1c7acbe4442c6c0eef59825da1339e0a3cf
# first bad commit: [0a0d05338f13e64c9fb7ccd8f8d1793aaf33ec7d] userfaultfd: use per-vma locks in userfaultfd operations
This is the oops:
[ 21.280142] mm ffff049340ed0000 task_size 281474976710656
[ 21.280142] get_unmapped_area ffffb3dbdc725e48
[ 21.280142] mmap_base 281474842492928 mmap_legacy_base 0
[ 21.280142] pgd ffff04935829a000 mm_users 3 mm_count 4 pgtables_bytes 98304 map_count 21
[ 21.280142] hiwater_rss 2167 hiwater_vm 8234 total_vm 4a44 locked_vm 0
[ 21.280142] pinned_vm 0 data_vm 4835 exec_vm 1c6 stack_vm 21
[ 21.280142] start_code aaaaaaaa0000 end_code aaaaaaab1b28 start_data aaaaaaac2a60 end_data aaaaaaac3410
[ 21.280142] start_brk aaaaaaac5000 brk aaaaaaae6000 start_stack fffffffff6b0
[ 21.280142] arg_start fffffffff8c7 arg_end fffffffff8e2 env_start fffffffff8e2 env_end ffffffffffdd
[ 21.280142] binfmt ffffb3dbdf2f8cf8 flags 82008d
[ 21.280142] ioctx_table 0000000000000000
[ 21.280142] owner ffff049311f02280 exe_file ffff049355314c00
[ 21.280142] notifier_subscriptions 0000000000000000
[ 21.280142] numa_next_scan 4294897864 numa_scan_offset 0 numa_scan_seq 0
[ 21.280142] tlb_flush_pending 0
[ 21.280142] def_flags: 0x0()
[ 21.283302] kernel BUG at include/linux/mmap_lock.h:66!
[ 21.283481] Internal error: Oops - BUG: 00000000f2000800 [#1] PREEMPT SMP
[ 21.283720] Modules linked in:
[ 21.283867] CPU: 3 PID: 1226 Comm: uffd-unit-tests Not tainted 6.8.0-rc3-00297-g0a0d05338f13 #19
[ 21.284306] Hardware name: linux,dummy-virt (DT)
[ 21.284495] pstate: 61400005 (nZCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
[ 21.284833] pc : move_pages_huge_pmd+0x4d0/0x8a8
[ 21.285072] lr : move_pages_huge_pmd+0x4d0/0x8a8
[ 21.285289] sp : ffff800088573b30
[ 21.285439] x29: ffff800088573b30 x28: ffff049358292d78 x27: fffffc0000000000
[ 21.285770] x26: ffff049358292d78 x25: 0000fffff5e00000 x24: ffff049359db3730
[ 21.286097] x23: 0000fffff6000000 x22: ffff049340ed0000 x21: ffff049359db3678
[ 21.286422] x20: 0000000000000002 x19: fffffc124d60a480 x18: 0000000000000006
[ 21.286747] x17: 626c740a30207165 x16: 735f6e6163735f61 x15: 6d756e2030207465
[ 21.287084] x14: 7366666f5f6e6163 x13: 2928307830203a73 x12: 67616c665f666564
[ 21.287417] x11: 0a3020676e69646e x10: ffffb3dbdf28bff8 x9 : ffffb3dbdc620f80
[ 21.287745] x8 : 00000000ffffefff x7 : ffffb3dbdf28bff8 x6 : 80000000fffff000
[ 21.288082] x5 : ffff04933ffdcd08 x4 : 0000000000000000 x3 : 0000000000000000
[ 21.288364] x2 : 0000000000000000 x1 : ffff049340106780 x0 : 0000000000000328
[ 21.288712] Call trace:
[ 21.288832] move_pages_huge_pmd+0x4d0/0x8a8
[ 21.289058] move_pages+0x8b8/0x13d8
[ 21.289205] userfaultfd_ioctl+0x11e0/0x1e90
[ 21.289411] __arm64_sys_ioctl+0xb4/0x100
[ 21.289579] invoke_syscall+0x50/0x128
[ 21.289738] el0_svc_common.constprop.0+0x48/0xf0
[ 21.289942] do_el0_svc+0x24/0x38
[ 21.290078] el0_svc+0x34/0xb8
[ 21.290219] el0t_64_sync_handler+0x100/0x130
[ 21.290387] el0t_64_sync+0x190/0x198
[ 21.290535] Code: 17ffff7e a90363f7 a9046bf9 97fde2a7 (d4210000)
[ 21.290776] ---[ end trace 0000000000000000 ]---
[ 21.290966] note: uffd-unit-tests[1226] exited with irqs disabled
[ 21.291254] note: uffd-unit-tests[1226] exited with preempt_count 2
[ 21.292864] ------------[ cut here ]------------
[ 21.293020] WARNING: CPU: 3 PID: 0 at kernel/context_tracking.c:128 ct_kernel_exit.constprop.0+0x108/0x120
[ 21.293711] Modules linked in:
[ 21.294070] CPU: 3 PID: 0 Comm: swapper/3 Tainted: G D 6.8.0-rc3-00297-g0a0d05338f13 #19
[ 21.295447] Hardware name: linux,dummy-virt (DT)
[ 21.295850] pstate: 214003c5 (nzCv DAIF +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
[ 21.296152] pc : ct_kernel_exit.constprop.0+0x108/0x120
[ 21.296685] lr : ct_idle_enter+0x10/0x20
[ 21.296848] sp : ffff8000801b3dc0
[ 21.296983] x29: ffff8000801b3dc0 x28: 0000000000000000 x27: 0000000000000000
[ 21.297255] x26: 0000000000000000 x25: ffff049301496780 x24: 0000000000000000
[ 21.297533] x23: 0000000000000000 x22: ffff049301496780 x21: ffffb3dbdf209ae0
[ 21.297844] x20: ffffb3dbdf209a20 x19: ffff04933ffeace0 x18: ffff800088573648
[ 21.298152] x17: ffffb3dbdf65def0 x16: 00000000d72145a7 x15: 00000000f1a17b35
[ 21.298439] x14: 0000000000000004 x13: ffffb3dbdf22c3a8 x12: 0000000000000000
[ 21.298738] x11: ffff0493541472a8 x10: 2b58349b7608bfc4 x9 : ffffb3dbdc57f43c
[ 21.299031] x8 : ffff049301497858 x7 : 00000000000001c1 x6 : 000000001eeeb49c
[ 21.299329] x5 : 4000000000000002 x4 : ffff50b7618d7000 x3 : ffff8000801b3dc0
[ 21.299615] x2 : ffffb3dbde713ce0 x1 : 4000000000000000 x0 : ffffb3dbde713ce0
[ 21.299900] Call trace:
[ 21.299998] ct_kernel_exit.constprop.0+0x108/0x120
[ 21.300460] ct_idle_enter+0x10/0x20
[ 21.300690] default_idle_call+0x3c/0x170
[ 21.300861] do_idle+0x218/0x278
[ 21.300992] cpu_startup_entry+0x3c/0x50
[ 21.301148] secondary_start_kernel+0x130/0x158
[ 21.301329] __secondary_switched+0xb8/0xc0
[ 21.301641] ---[ end trace 0000000000000000 ]---
Can this series be removed from mm-unstable until fixed, please?
Thanks,
Ryan
>
> Signed-off-by: Lokesh Gidra <[email protected]>
> ---
> fs/userfaultfd.c | 13 +-
> include/linux/userfaultfd_k.h | 5 +-
> mm/userfaultfd.c | 380 ++++++++++++++++++++++++++--------
> 3 files changed, 296 insertions(+), 102 deletions(-)
>
> diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
> index c00a021bcce4..60dcfafdc11a 100644
> --- a/fs/userfaultfd.c
> +++ b/fs/userfaultfd.c
> @@ -2005,17 +2005,8 @@ static int userfaultfd_move(struct userfaultfd_ctx *ctx,
> return -EINVAL;
>
> if (mmget_not_zero(mm)) {
> - mmap_read_lock(mm);
> -
> - /* Re-check after taking map_changing_lock */
> - down_read(&ctx->map_changing_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 = -EAGAIN;
> - up_read(&ctx->map_changing_lock);
> - 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;
> diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
> index 3210c3552976..05d59f74fc88 100644
> --- a/include/linux/userfaultfd_k.h
> +++ b/include/linux/userfaultfd_k.h
> @@ -138,9 +138,8 @@ extern long uffd_wp_range(struct vm_area_struct *vma,
> /* move_pages */
> void double_pt_lock(spinlock_t *ptl1, spinlock_t *ptl2);
> void double_pt_unlock(spinlock_t *ptl1, spinlock_t *ptl2);
> -ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
> - unsigned long dst_start, unsigned long src_start,
> - unsigned long len, __u64 flags);
> +ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start,
> + unsigned long src_start, unsigned long len, __u64 flags);
> int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pmd_t dst_pmdval,
> struct vm_area_struct *dst_vma,
> struct vm_area_struct *src_vma,
> diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
> index 74aad0831e40..4744d6a96f96 100644
> --- a/mm/userfaultfd.c
> +++ b/mm/userfaultfd.c
> @@ -20,19 +20,11 @@
> #include "internal.h"
>
> static __always_inline
> -struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm,
> - unsigned long dst_start,
> - unsigned long len)
> +bool validate_dst_vma(struct vm_area_struct *dst_vma, unsigned long dst_end)
> {
> - /*
> - * Make sure that the dst range is both valid and fully within a
> - * single existing vma.
> - */
> - struct vm_area_struct *dst_vma;
> -
> - dst_vma = find_vma(dst_mm, dst_start);
> - if (!range_in_vma(dst_vma, dst_start, dst_start + len))
> - return NULL;
> + /* Make sure that the dst range is fully within dst_vma. */
> + if (dst_end > dst_vma->vm_end)
> + return false;
>
> /*
> * Check the vma is registered in uffd, this is required to
> @@ -40,11 +32,122 @@ struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm,
> * time.
> */
> if (!dst_vma->vm_userfaultfd_ctx.ctx)
> - return NULL;
> + return false;
> +
> + return true;
> +}
> +
> +static __always_inline
> +struct vm_area_struct *find_vma_and_prepare_anon(struct mm_struct *mm,
> + unsigned long addr)
> +{
> + struct vm_area_struct *vma;
> +
> + mmap_assert_locked(mm);
> + vma = vma_lookup(mm, addr);
> + if (!vma)
> + vma = ERR_PTR(-ENOENT);
> + else if (!(vma->vm_flags & VM_SHARED) &&
> + unlikely(anon_vma_prepare(vma)))
> + vma = ERR_PTR(-ENOMEM);
> +
> + return vma;
> +}
> +
> +#ifdef CONFIG_PER_VMA_LOCK
> +/*
> + * lock_vma() - Lookup and lock vma corresponding to @address.
> + * @mm: mm to search vma in.
> + * @address: address that the vma should contain.
> + *
> + * Should be called without holding mmap_lock. vma should be unlocked after use
> + * with unlock_vma().
> + *
> + * Return: A locked vma containing @address, -ENOENT if no vma is found, or
> + * -ENOMEM if anon_vma couldn't be allocated.
> + */
> +static struct vm_area_struct *lock_vma(struct mm_struct *mm,
> + unsigned long address)
> +{
> + struct vm_area_struct *vma;
> +
> + vma = lock_vma_under_rcu(mm, address);
> + if (vma) {
> + /*
> + * lock_vma_under_rcu() only checks anon_vma for private
> + * anonymous mappings. But we need to ensure it is assigned in
> + * private file-backed vmas as well.
> + */
> + if (!(vma->vm_flags & VM_SHARED) && unlikely(!vma->anon_vma))
> + vma_end_read(vma);
> + else
> + return vma;
> + }
> +
> + mmap_read_lock(mm);
> + vma = find_vma_and_prepare_anon(mm, address);
> + if (!IS_ERR(vma)) {
> + /*
> + * We cannot use vma_start_read() as it may fail due to
> + * false locked (see comment in vma_start_read()). We
> + * can avoid that by directly locking vm_lock under
> + * mmap_lock, which guarantees that nobody can lock the
> + * vma for write (vma_start_write()) under us.
> + */
> + down_read(&vma->vm_lock->lock);
> + }
> +
> + mmap_read_unlock(mm);
> + return vma;
> +}
> +
> +static struct vm_area_struct *uffd_mfill_lock(struct mm_struct *dst_mm,
> + unsigned long dst_start,
> + unsigned long len)
> +{
> + struct vm_area_struct *dst_vma;
>
> + dst_vma = lock_vma(dst_mm, dst_start);
> + if (IS_ERR(dst_vma) || validate_dst_vma(dst_vma, dst_start + len))
> + return dst_vma;
> +
> + vma_end_read(dst_vma);
> + return ERR_PTR(-ENOENT);
> +}
> +
> +static void uffd_mfill_unlock(struct vm_area_struct *vma)
> +{
> + vma_end_read(vma);
> +}
> +
> +#else
> +
> +static struct vm_area_struct *uffd_mfill_lock(struct mm_struct *dst_mm,
> + unsigned long dst_start,
> + unsigned long len)
> +{
> + struct vm_area_struct *dst_vma;
> +
> + mmap_read_lock(dst_mm);
> + dst_vma = find_vma_and_prepare_anon(dst_mm, dst_start);
> + if (IS_ERR(dst_vma))
> + goto out_unlock;
> +
> + if (validate_dst_vma(dst_vma, dst_start + len))
> + return dst_vma;
> +
> + dst_vma = ERR_PTR(-ENOENT);
> +out_unlock:
> + mmap_read_unlock(dst_mm);
> return dst_vma;
> }
>
> +static void uffd_mfill_unlock(struct vm_area_struct *vma)
> +{
> + mmap_read_unlock(vma->vm_mm);
> +}
> +#endif
> +
> /* Check if dst_addr is outside of file's size. Must be called with ptl held. */
> static bool mfill_file_over_size(struct vm_area_struct *dst_vma,
> unsigned long dst_addr)
> @@ -350,7 +453,8 @@ static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address)
> #ifdef CONFIG_HUGETLB_PAGE
> /*
> * mfill_atomic processing for HUGETLB vmas. Note that this routine is
> - * called with mmap_lock held, it will release mmap_lock before returning.
> + * called with either vma-lock or mmap_lock held, it will release the lock
> + * before returning.
> */
> static __always_inline ssize_t mfill_atomic_hugetlb(
> struct userfaultfd_ctx *ctx,
> @@ -361,7 +465,6 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
> uffd_flags_t flags)
> {
> struct mm_struct *dst_mm = dst_vma->vm_mm;
> - int vm_shared = dst_vma->vm_flags & VM_SHARED;
> ssize_t err;
> pte_t *dst_pte;
> unsigned long src_addr, dst_addr;
> @@ -380,7 +483,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
> */
> if (uffd_flags_mode_is(flags, MFILL_ATOMIC_ZEROPAGE)) {
> up_read(&ctx->map_changing_lock);
> - mmap_read_unlock(dst_mm);
> + uffd_mfill_unlock(dst_vma);
> return -EINVAL;
> }
>
> @@ -403,24 +506,28 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
> * retry, dst_vma will be set to NULL and we must lookup again.
> */
> if (!dst_vma) {
> + dst_vma = uffd_mfill_lock(dst_mm, dst_start, len);
> + if (IS_ERR(dst_vma)) {
> + err = PTR_ERR(dst_vma);
> + goto out;
> + }
> +
> err = -ENOENT;
> - dst_vma = find_dst_vma(dst_mm, dst_start, len);
> - if (!dst_vma || !is_vm_hugetlb_page(dst_vma))
> - goto out_unlock;
> + if (!is_vm_hugetlb_page(dst_vma))
> + goto out_unlock_vma;
>
> err = -EINVAL;
> if (vma_hpagesize != vma_kernel_pagesize(dst_vma))
> - goto out_unlock;
> -
> - vm_shared = dst_vma->vm_flags & VM_SHARED;
> - }
> + goto out_unlock_vma;
>
> - /*
> - * If not shared, ensure the dst_vma has a anon_vma.
> - */
> - err = -ENOMEM;
> - if (!vm_shared) {
> - if (unlikely(anon_vma_prepare(dst_vma)))
> + /*
> + * If memory mappings are changing because of non-cooperative
> + * operation (e.g. mremap) running in parallel, bail out and
> + * request the user to retry later
> + */
> + down_read(&ctx->map_changing_lock);
> + err = -EAGAIN;
> + if (atomic_read(&ctx->mmap_changing))
> goto out_unlock;
> }
>
> @@ -465,7 +572,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
>
> if (unlikely(err == -ENOENT)) {
> up_read(&ctx->map_changing_lock);
> - mmap_read_unlock(dst_mm);
> + uffd_mfill_unlock(dst_vma);
> BUG_ON(!folio);
>
> err = copy_folio_from_user(folio,
> @@ -474,17 +581,6 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
> err = -EFAULT;
> goto out;
> }
> - mmap_read_lock(dst_mm);
> - down_read(&ctx->map_changing_lock);
> - /*
> - * If memory mappings are changing because of non-cooperative
> - * operation (e.g. mremap) running in parallel, bail out and
> - * request the user to retry later
> - */
> - if (atomic_read(&ctx->mmap_changing)) {
> - err = -EAGAIN;
> - break;
> - }
>
> dst_vma = NULL;
> goto retry;
> @@ -505,7 +601,8 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
>
> out_unlock:
> up_read(&ctx->map_changing_lock);
> - mmap_read_unlock(dst_mm);
> +out_unlock_vma:
> + uffd_mfill_unlock(dst_vma);
> out:
> if (folio)
> folio_put(folio);
> @@ -597,7 +694,15 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
> copied = 0;
> folio = NULL;
> retry:
> - mmap_read_lock(dst_mm);
> + /*
> + * Make sure the vma is not shared, that the dst range is
> + * both valid and fully within a single existing vma.
> + */
> + dst_vma = uffd_mfill_lock(dst_mm, dst_start, len);
> + if (IS_ERR(dst_vma)) {
> + err = PTR_ERR(dst_vma);
> + goto out;
> + }
>
> /*
> * If memory mappings are changing because of non-cooperative
> @@ -609,15 +714,6 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
> if (atomic_read(&ctx->mmap_changing))
> goto out_unlock;
>
> - /*
> - * Make sure the vma is not shared, that the dst range is
> - * both valid and fully within a single existing vma.
> - */
> - err = -ENOENT;
> - dst_vma = find_dst_vma(dst_mm, dst_start, len);
> - if (!dst_vma)
> - goto out_unlock;
> -
> err = -EINVAL;
> /*
> * shmem_zero_setup is invoked in mmap for MAP_ANONYMOUS|MAP_SHARED but
> @@ -647,16 +743,6 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
> uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE))
> goto out_unlock;
>
> - /*
> - * Ensure the dst_vma has a anon_vma or this page
> - * would get a NULL anon_vma when moved in the
> - * dst_vma.
> - */
> - err = -ENOMEM;
> - if (!(dst_vma->vm_flags & VM_SHARED) &&
> - unlikely(anon_vma_prepare(dst_vma)))
> - goto out_unlock;
> -
> while (src_addr < src_start + len) {
> pmd_t dst_pmdval;
>
> @@ -699,7 +785,7 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
> void *kaddr;
>
> up_read(&ctx->map_changing_lock);
> - mmap_read_unlock(dst_mm);
> + uffd_mfill_unlock(dst_vma);
> BUG_ON(!folio);
>
> kaddr = kmap_local_folio(folio, 0);
> @@ -730,7 +816,7 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
>
> out_unlock:
> up_read(&ctx->map_changing_lock);
> - mmap_read_unlock(dst_mm);
> + uffd_mfill_unlock(dst_vma);
> out:
> if (folio)
> folio_put(folio);
> @@ -1267,27 +1353,136 @@ static int validate_move_areas(struct userfaultfd_ctx *ctx,
> if (!vma_is_anonymous(src_vma) || !vma_is_anonymous(dst_vma))
> return -EINVAL;
>
> + return 0;
> +}
> +
> +static __always_inline
> +int find_vmas_mm_locked(struct mm_struct *mm,
> + unsigned long dst_start,
> + unsigned long src_start,
> + struct vm_area_struct **dst_vmap,
> + struct vm_area_struct **src_vmap)
> +{
> + struct vm_area_struct *vma;
> +
> + mmap_assert_locked(mm);
> + vma = find_vma_and_prepare_anon(mm, dst_start);
> + if (IS_ERR(vma))
> + return PTR_ERR(vma);
> +
> + *dst_vmap = vma;
> + /* Skip finding src_vma if src_start is in dst_vma */
> + if (src_start >= vma->vm_start && src_start < vma->vm_end)
> + goto out_success;
> +
> + vma = vma_lookup(mm, src_start);
> + if (!vma)
> + return -ENOENT;
> +out_success:
> + *src_vmap = vma;
> + return 0;
> +}
> +
> +#ifdef CONFIG_PER_VMA_LOCK
> +static int uffd_move_lock(struct mm_struct *mm,
> + unsigned long dst_start,
> + unsigned long src_start,
> + struct vm_area_struct **dst_vmap,
> + struct vm_area_struct **src_vmap)
> +{
> + struct vm_area_struct *vma;
> + int err;
> +
> + vma = lock_vma(mm, dst_start);
> + if (IS_ERR(vma))
> + return PTR_ERR(vma);
> +
> + *dst_vmap = vma;
> /*
> - * Ensure the dst_vma has a anon_vma or this page
> - * would get a NULL anon_vma when moved in the
> - * dst_vma.
> + * Skip finding src_vma if src_start is in dst_vma. This also ensures
> + * that we don't lock the same vma twice.
> */
> - if (unlikely(anon_vma_prepare(dst_vma)))
> - return -ENOMEM;
> + if (src_start >= vma->vm_start && src_start < vma->vm_end) {
> + *src_vmap = vma;
> + return 0;
> + }
>
> - return 0;
> + /*
> + * Using lock_vma() to get src_vma can lead to following deadlock:
> + *
> + * Thread1 Thread2
> + * ------- -------
> + * vma_start_read(dst_vma)
> + * mmap_write_lock(mm)
> + * vma_start_write(src_vma)
> + * vma_start_read(src_vma)
> + * mmap_read_lock(mm)
> + * vma_start_write(dst_vma)
> + */
> + *src_vmap = lock_vma_under_rcu(mm, src_start);
> + if (likely(*src_vmap))
> + return 0;
> +
> + /* Undo any locking and retry in mmap_lock critical section */
> + vma_end_read(*dst_vmap);
> +
> + mmap_read_lock(mm);
> + err = find_vmas_mm_locked(mm, dst_start, src_start, dst_vmap, src_vmap);
> + if (!err) {
> + /*
> + * See comment in lock_vma() as to why not using
> + * vma_start_read() here.
> + */
> + down_read(&(*dst_vmap)->vm_lock->lock);
> + if (*dst_vmap != *src_vmap)
> + down_read(&(*src_vmap)->vm_lock->lock);
> + }
> + mmap_read_unlock(mm);
> + return err;
> +}
> +
> +static void uffd_move_unlock(struct vm_area_struct *dst_vma,
> + struct vm_area_struct *src_vma)
> +{
> + vma_end_read(src_vma);
> + if (src_vma != dst_vma)
> + vma_end_read(dst_vma);
> }
>
> +#else
> +
> +static int uffd_move_lock(struct mm_struct *mm,
> + unsigned long dst_start,
> + unsigned long src_start,
> + struct vm_area_struct **dst_vmap,
> + struct vm_area_struct **src_vmap)
> +{
> + int err;
> +
> + mmap_read_lock(mm);
> + err = find_vmas_mm_locked(mm, dst_start, src_start, dst_vmap, src_vmap);
> + if (err)
> + mmap_read_unlock(mm);
> + return err;
> +}
> +
> +static void uffd_move_unlock(struct vm_area_struct *dst_vma,
> + struct vm_area_struct *src_vma)
> +{
> + mmap_assert_locked(src_vma->vm_mm);
> + mmap_read_unlock(dst_vma->vm_mm);
> +}
> +#endif
> +
> /**
> * move_pages - move arbitrary anonymous pages of an existing vma
> * @ctx: pointer to the userfaultfd context
> - * @mm: the address space to move pages
> * @dst_start: start of the destination virtual memory range
> * @src_start: start of the source virtual memory range
> * @len: length of the virtual memory range
> * @mode: flags from uffdio_move.mode
> *
> - * Must be called with mmap_lock held for read.
> + * It will either use the mmap_lock in read mode or per-vma locks
> *
> * move_pages() remaps arbitrary anonymous pages atomically in zero
> * copy. It only works on non shared anonymous pages because those can
> @@ -1355,10 +1550,10 @@ static int validate_move_areas(struct userfaultfd_ctx *ctx,
> * could be obtained. This is the only additional complexity added to
> * the rmap code to provide this anonymous page remapping functionality.
> */
> -ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
> - unsigned long dst_start, unsigned long src_start,
> - unsigned long len, __u64 mode)
> +ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start,
> + unsigned long src_start, unsigned long len, __u64 mode)
> {
> + struct mm_struct *mm = ctx->mm;
> struct vm_area_struct *src_vma, *dst_vma;
> unsigned long src_addr, dst_addr;
> pmd_t *src_pmd, *dst_pmd;
> @@ -1376,28 +1571,34 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
> WARN_ON_ONCE(dst_start + len <= dst_start))
> goto out;
>
> + err = uffd_move_lock(mm, dst_start, src_start, &dst_vma, &src_vma);
> + if (err)
> + goto out;
> +
> + /* Re-check after taking map_changing_lock */
> + err = -EAGAIN;
> + down_read(&ctx->map_changing_lock);
> + if (likely(atomic_read(&ctx->mmap_changing)))
> + goto out_unlock;
> /*
> * Make sure the vma is not shared, that the src and dst remap
> * ranges are both valid and fully within a single existing
> * vma.
> */
> - src_vma = find_vma(mm, src_start);
> - if (!src_vma || (src_vma->vm_flags & VM_SHARED))
> - goto out;
> - if (src_start < src_vma->vm_start ||
> - src_start + len > src_vma->vm_end)
> - goto out;
> + err = -EINVAL;
> + if (src_vma->vm_flags & VM_SHARED)
> + goto out_unlock;
> + if (src_start + len > src_vma->vm_end)
> + goto out_unlock;
>
> - dst_vma = find_vma(mm, dst_start);
> - if (!dst_vma || (dst_vma->vm_flags & VM_SHARED))
> - goto out;
> - if (dst_start < dst_vma->vm_start ||
> - dst_start + len > dst_vma->vm_end)
> - goto out;
> + if (dst_vma->vm_flags & VM_SHARED)
> + goto out_unlock;
> + if (dst_start + len > dst_vma->vm_end)
> + goto out_unlock;
>
> err = validate_move_areas(ctx, src_vma, dst_vma);
> if (err)
> - goto out;
> + goto out_unlock;
>
> for (src_addr = src_start, dst_addr = dst_start;
> src_addr < src_start + len;) {
> @@ -1514,6 +1715,9 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
> moved += step_size;
> }
>
> +out_unlock:
> + up_read(&ctx->map_changing_lock);
> + uffd_move_unlock(dst_vma, src_vma);
> out:
> VM_WARN_ON(moved < 0);
> VM_WARN_ON(err > 0);
On Wed, Feb 14, 2024 at 2:12 PM Ryan Roberts <[email protected]> wrote:
>
> On 13/02/2024 21:57, Lokesh Gidra wrote:
> > All userfaultfd operations, except write-protect, opportunistically use
> > per-vma locks to lock vmas. On failure, attempt again inside mmap_lock
> > critical section.
> >
> > Write-protect operation requires mmap_lock as it iterates over multiple
> > vmas.
>
> Hi,
>
> I'm seeing the below OOPS when running on arm64 against mm-unstable. It can be reliably reproduced by running the `uffd-unit-tests` mm selftest. Bisecting mm-unstable leads to this patch:
>
> # bad: [649936c3db47f8f75b9b927e4edf5922a0f240a6] mm: add swappiness= arg to memory.reclaim
> git bisect bad 649936c3db47f8f75b9b927e4edf5922a0f240a6
> # good: [54be6c6c5ae8e0d93a6c4641cb7528eb0b6ba478] Linux 6.8-rc3
> git bisect good 54be6c6c5ae8e0d93a6c4641cb7528eb0b6ba478
> # good: [10794cd18bb46c91c75fac44e551201cfe006baf] mm: zswap: warn when referencing a dead entry
> git bisect good 10794cd18bb46c91c75fac44e551201cfe006baf
> # good: [cb769b427edc7f46c7c764daa3421725bffdf315] mm-memcg-use-larger-batches-for-proactive-reclaim-v4
> git bisect good cb769b427edc7f46c7c764daa3421725bffdf315
> # good: [cfc5c1be4010c9972bc3f3d991235e8ea6928672] mm/z3fold: remove unneeded spinlock
> git bisect good cfc5c1be4010c9972bc3f3d991235e8ea6928672
> # good: [31094bce101651acb4747ab25d614bc893d65c89] kasan/test: avoid gcc warning for intentional overflow
> git bisect good 31094bce101651acb4747ab25d614bc893d65c89
> # bad: [55be0b2cd1fbf00e036e2e48ee0999599135af66] zram: do not allocate physically contiguous strm buffers
> git bisect bad 55be0b2cd1fbf00e036e2e48ee0999599135af66
> # good: [b11ca4a0a13024c0175dde56f9bd848803eddcd2] mm/mglru: improve swappiness handling
> git bisect good b11ca4a0a13024c0175dde56f9bd848803eddcd2
> # good: [22e7ccd57a1220afcd7c4da1f3005fd04d70014e] userfaultfd: move userfaultfd_ctx struct to header file
> git bisect good 22e7ccd57a1220afcd7c4da1f3005fd04d70014e
> # bad: [0a0d05338f13e64c9fb7ccd8f8d1793aaf33ec7d] userfaultfd: use per-vma locks in userfaultfd operations
> git bisect bad 0a0d05338f13e64c9fb7ccd8f8d1793aaf33ec7d
> # good: [8459e1c7acbe4442c6c0eef59825da1339e0a3cf] userfaultfd: protect mmap_changing with rw_sem in userfaulfd_ctx
> git bisect good 8459e1c7acbe4442c6c0eef59825da1339e0a3cf
> # first bad commit: [0a0d05338f13e64c9fb7ccd8f8d1793aaf33ec7d] userfaultfd: use per-vma locks in userfaultfd operations
>
> This is the oops:
That's a call to mmap_assert_locked() from inside
move_pages_huge_pmd(). Since move_pages() are now happening under VMA
lock this call should be replaced with vma_assert_locked().
>
> [ 21.280142] mm ffff049340ed0000 task_size 281474976710656
> [ 21.280142] get_unmapped_area ffffb3dbdc725e48
> [ 21.280142] mmap_base 281474842492928 mmap_legacy_base 0
> [ 21.280142] pgd ffff04935829a000 mm_users 3 mm_count 4 pgtables_bytes 98304 map_count 21
> [ 21.280142] hiwater_rss 2167 hiwater_vm 8234 total_vm 4a44 locked_vm 0
> [ 21.280142] pinned_vm 0 data_vm 4835 exec_vm 1c6 stack_vm 21
> [ 21.280142] start_code aaaaaaaa0000 end_code aaaaaaab1b28 start_data aaaaaaac2a60 end_data aaaaaaac3410
> [ 21.280142] start_brk aaaaaaac5000 brk aaaaaaae6000 start_stack fffffffff6b0
> [ 21.280142] arg_start fffffffff8c7 arg_end fffffffff8e2 env_start fffffffff8e2 env_end ffffffffffdd
> [ 21.280142] binfmt ffffb3dbdf2f8cf8 flags 82008d
> [ 21.280142] ioctx_table 0000000000000000
> [ 21.280142] owner ffff049311f02280 exe_file ffff049355314c00
> [ 21.280142] notifier_subscriptions 0000000000000000
> [ 21.280142] numa_next_scan 4294897864 numa_scan_offset 0 numa_scan_seq 0
> [ 21.280142] tlb_flush_pending 0
> [ 21.280142] def_flags: 0x0()
> [ 21.283302] kernel BUG at include/linux/mmap_lock.h:66!
> [ 21.283481] Internal error: Oops - BUG: 00000000f2000800 [#1] PREEMPT SMP
> [ 21.283720] Modules linked in:
> [ 21.283867] CPU: 3 PID: 1226 Comm: uffd-unit-tests Not tainted 6.8.0-rc3-00297-g0a0d05338f13 #19
> [ 21.284306] Hardware name: linux,dummy-virt (DT)
> [ 21.284495] pstate: 61400005 (nZCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
> [ 21.284833] pc : move_pages_huge_pmd+0x4d0/0x8a8
> [ 21.285072] lr : move_pages_huge_pmd+0x4d0/0x8a8
> [ 21.285289] sp : ffff800088573b30
> [ 21.285439] x29: ffff800088573b30 x28: ffff049358292d78 x27: fffffc0000000000
> [ 21.285770] x26: ffff049358292d78 x25: 0000fffff5e00000 x24: ffff049359db3730
> [ 21.286097] x23: 0000fffff6000000 x22: ffff049340ed0000 x21: ffff049359db3678
> [ 21.286422] x20: 0000000000000002 x19: fffffc124d60a480 x18: 0000000000000006
> [ 21.286747] x17: 626c740a30207165 x16: 735f6e6163735f61 x15: 6d756e2030207465
> [ 21.287084] x14: 7366666f5f6e6163 x13: 2928307830203a73 x12: 67616c665f666564
> [ 21.287417] x11: 0a3020676e69646e x10: ffffb3dbdf28bff8 x9 : ffffb3dbdc620f80
> [ 21.287745] x8 : 00000000ffffefff x7 : ffffb3dbdf28bff8 x6 : 80000000fffff000
> [ 21.288082] x5 : ffff04933ffdcd08 x4 : 0000000000000000 x3 : 0000000000000000
> [ 21.288364] x2 : 0000000000000000 x1 : ffff049340106780 x0 : 0000000000000328
> [ 21.288712] Call trace:
> [ 21.288832] move_pages_huge_pmd+0x4d0/0x8a8
> [ 21.289058] move_pages+0x8b8/0x13d8
> [ 21.289205] userfaultfd_ioctl+0x11e0/0x1e90
> [ 21.289411] __arm64_sys_ioctl+0xb4/0x100
> [ 21.289579] invoke_syscall+0x50/0x128
> [ 21.289738] el0_svc_common.constprop.0+0x48/0xf0
> [ 21.289942] do_el0_svc+0x24/0x38
> [ 21.290078] el0_svc+0x34/0xb8
> [ 21.290219] el0t_64_sync_handler+0x100/0x130
> [ 21.290387] el0t_64_sync+0x190/0x198
> [ 21.290535] Code: 17ffff7e a90363f7 a9046bf9 97fde2a7 (d4210000)
> [ 21.290776] ---[ end trace 0000000000000000 ]---
> [ 21.290966] note: uffd-unit-tests[1226] exited with irqs disabled
> [ 21.291254] note: uffd-unit-tests[1226] exited with preempt_count 2
> [ 21.292864] ------------[ cut here ]------------
> [ 21.293020] WARNING: CPU: 3 PID: 0 at kernel/context_tracking.c:128 ct_kernel_exit.constprop.0+0x108/0x120
> [ 21.293711] Modules linked in:
> [ 21.294070] CPU: 3 PID: 0 Comm: swapper/3 Tainted: G D 6.8.0-rc3-00297-g0a0d05338f13 #19
> [ 21.295447] Hardware name: linux,dummy-virt (DT)
> [ 21.295850] pstate: 214003c5 (nzCv DAIF +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
> [ 21.296152] pc : ct_kernel_exit.constprop.0+0x108/0x120
> [ 21.296685] lr : ct_idle_enter+0x10/0x20
> [ 21.296848] sp : ffff8000801b3dc0
> [ 21.296983] x29: ffff8000801b3dc0 x28: 0000000000000000 x27: 0000000000000000
> [ 21.297255] x26: 0000000000000000 x25: ffff049301496780 x24: 0000000000000000
> [ 21.297533] x23: 0000000000000000 x22: ffff049301496780 x21: ffffb3dbdf209ae0
> [ 21.297844] x20: ffffb3dbdf209a20 x19: ffff04933ffeace0 x18: ffff800088573648
> [ 21.298152] x17: ffffb3dbdf65def0 x16: 00000000d72145a7 x15: 00000000f1a17b35
> [ 21.298439] x14: 0000000000000004 x13: ffffb3dbdf22c3a8 x12: 0000000000000000
> [ 21.298738] x11: ffff0493541472a8 x10: 2b58349b7608bfc4 x9 : ffffb3dbdc57f43c
> [ 21.299031] x8 : ffff049301497858 x7 : 00000000000001c1 x6 : 000000001eeeb49c
> [ 21.299329] x5 : 4000000000000002 x4 : ffff50b7618d7000 x3 : ffff8000801b3dc0
> [ 21.299615] x2 : ffffb3dbde713ce0 x1 : 4000000000000000 x0 : ffffb3dbde713ce0
> [ 21.299900] Call trace:
> [ 21.299998] ct_kernel_exit.constprop.0+0x108/0x120
> [ 21.300460] ct_idle_enter+0x10/0x20
> [ 21.300690] default_idle_call+0x3c/0x170
> [ 21.300861] do_idle+0x218/0x278
> [ 21.300992] cpu_startup_entry+0x3c/0x50
> [ 21.301148] secondary_start_kernel+0x130/0x158
> [ 21.301329] __secondary_switched+0xb8/0xc0
> [ 21.301641] ---[ end trace 0000000000000000 ]---
>
>
> Can this series be removed from mm-unstable until fixed, please?
>
> Thanks,
> Ryan
>
>
> >
> > Signed-off-by: Lokesh Gidra <[email protected]>
> > ---
> > fs/userfaultfd.c | 13 +-
> > include/linux/userfaultfd_k.h | 5 +-
> > mm/userfaultfd.c | 380 ++++++++++++++++++++++++++--------
> > 3 files changed, 296 insertions(+), 102 deletions(-)
> >
> > diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
> > index c00a021bcce4..60dcfafdc11a 100644
> > --- a/fs/userfaultfd.c
> > +++ b/fs/userfaultfd.c
> > @@ -2005,17 +2005,8 @@ static int userfaultfd_move(struct userfaultfd_ctx *ctx,
> > return -EINVAL;
> >
> > if (mmget_not_zero(mm)) {
> > - mmap_read_lock(mm);
> > -
> > - /* Re-check after taking map_changing_lock */
> > - down_read(&ctx->map_changing_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 = -EAGAIN;
> > - up_read(&ctx->map_changing_lock);
> > - 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;
> > diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
> > index 3210c3552976..05d59f74fc88 100644
> > --- a/include/linux/userfaultfd_k.h
> > +++ b/include/linux/userfaultfd_k.h
> > @@ -138,9 +138,8 @@ extern long uffd_wp_range(struct vm_area_struct *vma,
> > /* move_pages */
> > void double_pt_lock(spinlock_t *ptl1, spinlock_t *ptl2);
> > void double_pt_unlock(spinlock_t *ptl1, spinlock_t *ptl2);
> > -ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
> > - unsigned long dst_start, unsigned long src_start,
> > - unsigned long len, __u64 flags);
> > +ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start,
> > + unsigned long src_start, unsigned long len, __u64 flags);
> > int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pmd_t dst_pmdval,
> > struct vm_area_struct *dst_vma,
> > struct vm_area_struct *src_vma,
> > diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
> > index 74aad0831e40..4744d6a96f96 100644
> > --- a/mm/userfaultfd.c
> > +++ b/mm/userfaultfd.c
> > @@ -20,19 +20,11 @@
> > #include "internal.h"
> >
> > static __always_inline
> > -struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm,
> > - unsigned long dst_start,
> > - unsigned long len)
> > +bool validate_dst_vma(struct vm_area_struct *dst_vma, unsigned long dst_end)
> > {
> > - /*
> > - * Make sure that the dst range is both valid and fully within a
> > - * single existing vma.
> > - */
> > - struct vm_area_struct *dst_vma;
> > -
> > - dst_vma = find_vma(dst_mm, dst_start);
> > - if (!range_in_vma(dst_vma, dst_start, dst_start + len))
> > - return NULL;
> > + /* Make sure that the dst range is fully within dst_vma. */
> > + if (dst_end > dst_vma->vm_end)
> > + return false;
> >
> > /*
> > * Check the vma is registered in uffd, this is required to
> > @@ -40,11 +32,122 @@ struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm,
> > * time.
> > */
> > if (!dst_vma->vm_userfaultfd_ctx.ctx)
> > - return NULL;
> > + return false;
> > +
> > + return true;
> > +}
> > +
> > +static __always_inline
> > +struct vm_area_struct *find_vma_and_prepare_anon(struct mm_struct *mm,
> > + unsigned long addr)
> > +{
> > + struct vm_area_struct *vma;
> > +
> > + mmap_assert_locked(mm);
> > + vma = vma_lookup(mm, addr);
> > + if (!vma)
> > + vma = ERR_PTR(-ENOENT);
> > + else if (!(vma->vm_flags & VM_SHARED) &&
> > + unlikely(anon_vma_prepare(vma)))
> > + vma = ERR_PTR(-ENOMEM);
> > +
> > + return vma;
> > +}
> > +
> > +#ifdef CONFIG_PER_VMA_LOCK
> > +/*
> > + * lock_vma() - Lookup and lock vma corresponding to @address.
> > + * @mm: mm to search vma in.
> > + * @address: address that the vma should contain.
> > + *
> > + * Should be called without holding mmap_lock. vma should be unlocked after use
> > + * with unlock_vma().
> > + *
> > + * Return: A locked vma containing @address, -ENOENT if no vma is found, or
> > + * -ENOMEM if anon_vma couldn't be allocated.
> > + */
> > +static struct vm_area_struct *lock_vma(struct mm_struct *mm,
> > + unsigned long address)
> > +{
> > + struct vm_area_struct *vma;
> > +
> > + vma = lock_vma_under_rcu(mm, address);
> > + if (vma) {
> > + /*
> > + * lock_vma_under_rcu() only checks anon_vma for private
> > + * anonymous mappings. But we need to ensure it is assigned in
> > + * private file-backed vmas as well.
> > + */
> > + if (!(vma->vm_flags & VM_SHARED) && unlikely(!vma->anon_vma))
> > + vma_end_read(vma);
> > + else
> > + return vma;
> > + }
> > +
> > + mmap_read_lock(mm);
> > + vma = find_vma_and_prepare_anon(mm, address);
> > + if (!IS_ERR(vma)) {
> > + /*
> > + * We cannot use vma_start_read() as it may fail due to
> > + * false locked (see comment in vma_start_read()). We
> > + * can avoid that by directly locking vm_lock under
> > + * mmap_lock, which guarantees that nobody can lock the
> > + * vma for write (vma_start_write()) under us.
> > + */
> > + down_read(&vma->vm_lock->lock);
> > + }
> > +
> > + mmap_read_unlock(mm);
> > + return vma;
> > +}
> > +
> > +static struct vm_area_struct *uffd_mfill_lock(struct mm_struct *dst_mm,
> > + unsigned long dst_start,
> > + unsigned long len)
> > +{
> > + struct vm_area_struct *dst_vma;
> >
> > + dst_vma = lock_vma(dst_mm, dst_start);
> > + if (IS_ERR(dst_vma) || validate_dst_vma(dst_vma, dst_start + len))
> > + return dst_vma;
> > +
> > + vma_end_read(dst_vma);
> > + return ERR_PTR(-ENOENT);
> > +}
> > +
> > +static void uffd_mfill_unlock(struct vm_area_struct *vma)
> > +{
> > + vma_end_read(vma);
> > +}
> > +
> > +#else
> > +
> > +static struct vm_area_struct *uffd_mfill_lock(struct mm_struct *dst_mm,
> > + unsigned long dst_start,
> > + unsigned long len)
> > +{
> > + struct vm_area_struct *dst_vma;
> > +
> > + mmap_read_lock(dst_mm);
> > + dst_vma = find_vma_and_prepare_anon(dst_mm, dst_start);
> > + if (IS_ERR(dst_vma))
> > + goto out_unlock;
> > +
> > + if (validate_dst_vma(dst_vma, dst_start + len))
> > + return dst_vma;
> > +
> > + dst_vma = ERR_PTR(-ENOENT);
> > +out_unlock:
> > + mmap_read_unlock(dst_mm);
> > return dst_vma;
> > }
> >
> > +static void uffd_mfill_unlock(struct vm_area_struct *vma)
> > +{
> > + mmap_read_unlock(vma->vm_mm);
> > +}
> > +#endif
> > +
> > /* Check if dst_addr is outside of file's size. Must be called with ptl held. */
> > static bool mfill_file_over_size(struct vm_area_struct *dst_vma,
> > unsigned long dst_addr)
> > @@ -350,7 +453,8 @@ static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address)
> > #ifdef CONFIG_HUGETLB_PAGE
> > /*
> > * mfill_atomic processing for HUGETLB vmas. Note that this routine is
> > - * called with mmap_lock held, it will release mmap_lock before returning.
> > + * called with either vma-lock or mmap_lock held, it will release the lock
> > + * before returning.
> > */
> > static __always_inline ssize_t mfill_atomic_hugetlb(
> > struct userfaultfd_ctx *ctx,
> > @@ -361,7 +465,6 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
> > uffd_flags_t flags)
> > {
> > struct mm_struct *dst_mm = dst_vma->vm_mm;
> > - int vm_shared = dst_vma->vm_flags & VM_SHARED;
> > ssize_t err;
> > pte_t *dst_pte;
> > unsigned long src_addr, dst_addr;
> > @@ -380,7 +483,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
> > */
> > if (uffd_flags_mode_is(flags, MFILL_ATOMIC_ZEROPAGE)) {
> > up_read(&ctx->map_changing_lock);
> > - mmap_read_unlock(dst_mm);
> > + uffd_mfill_unlock(dst_vma);
> > return -EINVAL;
> > }
> >
> > @@ -403,24 +506,28 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
> > * retry, dst_vma will be set to NULL and we must lookup again.
> > */
> > if (!dst_vma) {
> > + dst_vma = uffd_mfill_lock(dst_mm, dst_start, len);
> > + if (IS_ERR(dst_vma)) {
> > + err = PTR_ERR(dst_vma);
> > + goto out;
> > + }
> > +
> > err = -ENOENT;
> > - dst_vma = find_dst_vma(dst_mm, dst_start, len);
> > - if (!dst_vma || !is_vm_hugetlb_page(dst_vma))
> > - goto out_unlock;
> > + if (!is_vm_hugetlb_page(dst_vma))
> > + goto out_unlock_vma;
> >
> > err = -EINVAL;
> > if (vma_hpagesize != vma_kernel_pagesize(dst_vma))
> > - goto out_unlock;
> > -
> > - vm_shared = dst_vma->vm_flags & VM_SHARED;
> > - }
> > + goto out_unlock_vma;
> >
> > - /*
> > - * If not shared, ensure the dst_vma has a anon_vma.
> > - */
> > - err = -ENOMEM;
> > - if (!vm_shared) {
> > - if (unlikely(anon_vma_prepare(dst_vma)))
> > + /*
> > + * If memory mappings are changing because of non-cooperative
> > + * operation (e.g. mremap) running in parallel, bail out and
> > + * request the user to retry later
> > + */
> > + down_read(&ctx->map_changing_lock);
> > + err = -EAGAIN;
> > + if (atomic_read(&ctx->mmap_changing))
> > goto out_unlock;
> > }
> >
> > @@ -465,7 +572,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
> >
> > if (unlikely(err == -ENOENT)) {
> > up_read(&ctx->map_changing_lock);
> > - mmap_read_unlock(dst_mm);
> > + uffd_mfill_unlock(dst_vma);
> > BUG_ON(!folio);
> >
> > err = copy_folio_from_user(folio,
> > @@ -474,17 +581,6 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
> > err = -EFAULT;
> > goto out;
> > }
> > - mmap_read_lock(dst_mm);
> > - down_read(&ctx->map_changing_lock);
> > - /*
> > - * If memory mappings are changing because of non-cooperative
> > - * operation (e.g. mremap) running in parallel, bail out and
> > - * request the user to retry later
> > - */
> > - if (atomic_read(&ctx->mmap_changing)) {
> > - err = -EAGAIN;
> > - break;
> > - }
> >
> > dst_vma = NULL;
> > goto retry;
> > @@ -505,7 +601,8 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
> >
> > out_unlock:
> > up_read(&ctx->map_changing_lock);
> > - mmap_read_unlock(dst_mm);
> > +out_unlock_vma:
> > + uffd_mfill_unlock(dst_vma);
> > out:
> > if (folio)
> > folio_put(folio);
> > @@ -597,7 +694,15 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
> > copied = 0;
> > folio = NULL;
> > retry:
> > - mmap_read_lock(dst_mm);
> > + /*
> > + * Make sure the vma is not shared, that the dst range is
> > + * both valid and fully within a single existing vma.
> > + */
> > + dst_vma = uffd_mfill_lock(dst_mm, dst_start, len);
> > + if (IS_ERR(dst_vma)) {
> > + err = PTR_ERR(dst_vma);
> > + goto out;
> > + }
> >
> > /*
> > * If memory mappings are changing because of non-cooperative
> > @@ -609,15 +714,6 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
> > if (atomic_read(&ctx->mmap_changing))
> > goto out_unlock;
> >
> > - /*
> > - * Make sure the vma is not shared, that the dst range is
> > - * both valid and fully within a single existing vma.
> > - */
> > - err = -ENOENT;
> > - dst_vma = find_dst_vma(dst_mm, dst_start, len);
> > - if (!dst_vma)
> > - goto out_unlock;
> > -
> > err = -EINVAL;
> > /*
> > * shmem_zero_setup is invoked in mmap for MAP_ANONYMOUS|MAP_SHARED but
> > @@ -647,16 +743,6 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
> > uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE))
> > goto out_unlock;
> >
> > - /*
> > - * Ensure the dst_vma has a anon_vma or this page
> > - * would get a NULL anon_vma when moved in the
> > - * dst_vma.
> > - */
> > - err = -ENOMEM;
> > - if (!(dst_vma->vm_flags & VM_SHARED) &&
> > - unlikely(anon_vma_prepare(dst_vma)))
> > - goto out_unlock;
> > -
> > while (src_addr < src_start + len) {
> > pmd_t dst_pmdval;
> >
> > @@ -699,7 +785,7 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
> > void *kaddr;
> >
> > up_read(&ctx->map_changing_lock);
> > - mmap_read_unlock(dst_mm);
> > + uffd_mfill_unlock(dst_vma);
> > BUG_ON(!folio);
> >
> > kaddr = kmap_local_folio(folio, 0);
> > @@ -730,7 +816,7 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
> >
> > out_unlock:
> > up_read(&ctx->map_changing_lock);
> > - mmap_read_unlock(dst_mm);
> > + uffd_mfill_unlock(dst_vma);
> > out:
> > if (folio)
> > folio_put(folio);
> > @@ -1267,27 +1353,136 @@ static int validate_move_areas(struct userfaultfd_ctx *ctx,
> > if (!vma_is_anonymous(src_vma) || !vma_is_anonymous(dst_vma))
> > return -EINVAL;
> >
> > + return 0;
> > +}
> > +
> > +static __always_inline
> > +int find_vmas_mm_locked(struct mm_struct *mm,
> > + unsigned long dst_start,
> > + unsigned long src_start,
> > + struct vm_area_struct **dst_vmap,
> > + struct vm_area_struct **src_vmap)
> > +{
> > + struct vm_area_struct *vma;
> > +
> > + mmap_assert_locked(mm);
> > + vma = find_vma_and_prepare_anon(mm, dst_start);
> > + if (IS_ERR(vma))
> > + return PTR_ERR(vma);
> > +
> > + *dst_vmap = vma;
> > + /* Skip finding src_vma if src_start is in dst_vma */
> > + if (src_start >= vma->vm_start && src_start < vma->vm_end)
> > + goto out_success;
> > +
> > + vma = vma_lookup(mm, src_start);
> > + if (!vma)
> > + return -ENOENT;
> > +out_success:
> > + *src_vmap = vma;
> > + return 0;
> > +}
> > +
> > +#ifdef CONFIG_PER_VMA_LOCK
> > +static int uffd_move_lock(struct mm_struct *mm,
> > + unsigned long dst_start,
> > + unsigned long src_start,
> > + struct vm_area_struct **dst_vmap,
> > + struct vm_area_struct **src_vmap)
> > +{
> > + struct vm_area_struct *vma;
> > + int err;
> > +
> > + vma = lock_vma(mm, dst_start);
> > + if (IS_ERR(vma))
> > + return PTR_ERR(vma);
> > +
> > + *dst_vmap = vma;
> > /*
> > - * Ensure the dst_vma has a anon_vma or this page
> > - * would get a NULL anon_vma when moved in the
> > - * dst_vma.
> > + * Skip finding src_vma if src_start is in dst_vma. This also ensures
> > + * that we don't lock the same vma twice.
> > */
> > - if (unlikely(anon_vma_prepare(dst_vma)))
> > - return -ENOMEM;
> > + if (src_start >= vma->vm_start && src_start < vma->vm_end) {
> > + *src_vmap = vma;
> > + return 0;
> > + }
> >
> > - return 0;
> > + /*
> > + * Using lock_vma() to get src_vma can lead to following deadlock:
> > + *
> > + * Thread1 Thread2
> > + * ------- -------
> > + * vma_start_read(dst_vma)
> > + * mmap_write_lock(mm)
> > + * vma_start_write(src_vma)
> > + * vma_start_read(src_vma)
> > + * mmap_read_lock(mm)
> > + * vma_start_write(dst_vma)
> > + */
> > + *src_vmap = lock_vma_under_rcu(mm, src_start);
> > + if (likely(*src_vmap))
> > + return 0;
> > +
> > + /* Undo any locking and retry in mmap_lock critical section */
> > + vma_end_read(*dst_vmap);
> > +
> > + mmap_read_lock(mm);
> > + err = find_vmas_mm_locked(mm, dst_start, src_start, dst_vmap, src_vmap);
> > + if (!err) {
> > + /*
> > + * See comment in lock_vma() as to why not using
> > + * vma_start_read() here.
> > + */
> > + down_read(&(*dst_vmap)->vm_lock->lock);
> > + if (*dst_vmap != *src_vmap)
> > + down_read(&(*src_vmap)->vm_lock->lock);
> > + }
> > + mmap_read_unlock(mm);
> > + return err;
> > +}
> > +
> > +static void uffd_move_unlock(struct vm_area_struct *dst_vma,
> > + struct vm_area_struct *src_vma)
> > +{
> > + vma_end_read(src_vma);
> > + if (src_vma != dst_vma)
> > + vma_end_read(dst_vma);
> > }
> >
> > +#else
> > +
> > +static int uffd_move_lock(struct mm_struct *mm,
> > + unsigned long dst_start,
> > + unsigned long src_start,
> > + struct vm_area_struct **dst_vmap,
> > + struct vm_area_struct **src_vmap)
> > +{
> > + int err;
> > +
> > + mmap_read_lock(mm);
> > + err = find_vmas_mm_locked(mm, dst_start, src_start, dst_vmap, src_vmap);
> > + if (err)
> > + mmap_read_unlock(mm);
> > + return err;
> > +}
> > +
> > +static void uffd_move_unlock(struct vm_area_struct *dst_vma,
> > + struct vm_area_struct *src_vma)
> > +{
> > + mmap_assert_locked(src_vma->vm_mm);
> > + mmap_read_unlock(dst_vma->vm_mm);
> > +}
> > +#endif
> > +
> > /**
> > * move_pages - move arbitrary anonymous pages of an existing vma
> > * @ctx: pointer to the userfaultfd context
> > - * @mm: the address space to move pages
> > * @dst_start: start of the destination virtual memory range
> > * @src_start: start of the source virtual memory range
> > * @len: length of the virtual memory range
> > * @mode: flags from uffdio_move.mode
> > *
> > - * Must be called with mmap_lock held for read.
> > + * It will either use the mmap_lock in read mode or per-vma locks
> > *
> > * move_pages() remaps arbitrary anonymous pages atomically in zero
> > * copy. It only works on non shared anonymous pages because those can
> > @@ -1355,10 +1550,10 @@ static int validate_move_areas(struct userfaultfd_ctx *ctx,
> > * could be obtained. This is the only additional complexity added to
> > * the rmap code to provide this anonymous page remapping functionality.
> > */
> > -ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
> > - unsigned long dst_start, unsigned long src_start,
> > - unsigned long len, __u64 mode)
> > +ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start,
> > + unsigned long src_start, unsigned long len, __u64 mode)
> > {
> > + struct mm_struct *mm = ctx->mm;
> > struct vm_area_struct *src_vma, *dst_vma;
> > unsigned long src_addr, dst_addr;
> > pmd_t *src_pmd, *dst_pmd;
> > @@ -1376,28 +1571,34 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
> > WARN_ON_ONCE(dst_start + len <= dst_start))
> > goto out;
> >
> > + err = uffd_move_lock(mm, dst_start, src_start, &dst_vma, &src_vma);
> > + if (err)
> > + goto out;
> > +
> > + /* Re-check after taking map_changing_lock */
> > + err = -EAGAIN;
> > + down_read(&ctx->map_changing_lock);
> > + if (likely(atomic_read(&ctx->mmap_changing)))
> > + goto out_unlock;
> > /*
> > * Make sure the vma is not shared, that the src and dst remap
> > * ranges are both valid and fully within a single existing
> > * vma.
> > */
> > - src_vma = find_vma(mm, src_start);
> > - if (!src_vma || (src_vma->vm_flags & VM_SHARED))
> > - goto out;
> > - if (src_start < src_vma->vm_start ||
> > - src_start + len > src_vma->vm_end)
> > - goto out;
> > + err = -EINVAL;
> > + if (src_vma->vm_flags & VM_SHARED)
> > + goto out_unlock;
> > + if (src_start + len > src_vma->vm_end)
> > + goto out_unlock;
> >
> > - dst_vma = find_vma(mm, dst_start);
> > - if (!dst_vma || (dst_vma->vm_flags & VM_SHARED))
> > - goto out;
> > - if (dst_start < dst_vma->vm_start ||
> > - dst_start + len > dst_vma->vm_end)
> > - goto out;
> > + if (dst_vma->vm_flags & VM_SHARED)
> > + goto out_unlock;
> > + if (dst_start + len > dst_vma->vm_end)
> > + goto out_unlock;
> >
> > err = validate_move_areas(ctx, src_vma, dst_vma);
> > if (err)
> > - goto out;
> > + goto out_unlock;
> >
> > for (src_addr = src_start, dst_addr = dst_start;
> > src_addr < src_start + len;) {
> > @@ -1514,6 +1715,9 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
> > moved += step_size;
> > }
> >
> > +out_unlock:
> > + up_read(&ctx->map_changing_lock);
> > + uffd_move_unlock(dst_vma, src_vma);
> > out:
> > VM_WARN_ON(moved < 0);
> > VM_WARN_ON(err > 0);
>
> --
> To unsubscribe from this group and stop receiving emails from it, send an email to [email protected].
>
On Wed, Feb 14, 2024 at 2:20 PM Suren Baghdasaryan <[email protected]> wrote:
>
> On Wed, Feb 14, 2024 at 2:12 PM Ryan Roberts <[email protected]> wrote:
> >
> > On 13/02/2024 21:57, Lokesh Gidra wrote:
> > > All userfaultfd operations, except write-protect, opportunistically use
> > > per-vma locks to lock vmas. On failure, attempt again inside mmap_lock
> > > critical section.
> > >
> > > Write-protect operation requires mmap_lock as it iterates over multiple
> > > vmas.
> >
> > Hi,
> >
> > I'm seeing the below OOPS when running on arm64 against mm-unstable. It can be reliably reproduced by running the `uffd-unit-tests` mm selftest. Bisecting mm-unstable leads to this patch:
> >
> > # bad: [649936c3db47f8f75b9b927e4edf5922a0f240a6] mm: add swappiness= arg to memory.reclaim
> > git bisect bad 649936c3db47f8f75b9b927e4edf5922a0f240a6
> > # good: [54be6c6c5ae8e0d93a6c4641cb7528eb0b6ba478] Linux 6.8-rc3
> > git bisect good 54be6c6c5ae8e0d93a6c4641cb7528eb0b6ba478
> > # good: [10794cd18bb46c91c75fac44e551201cfe006baf] mm: zswap: warn when referencing a dead entry
> > git bisect good 10794cd18bb46c91c75fac44e551201cfe006baf
> > # good: [cb769b427edc7f46c7c764daa3421725bffdf315] mm-memcg-use-larger-batches-for-proactive-reclaim-v4
> > git bisect good cb769b427edc7f46c7c764daa3421725bffdf315
> > # good: [cfc5c1be4010c9972bc3f3d991235e8ea6928672] mm/z3fold: remove unneeded spinlock
> > git bisect good cfc5c1be4010c9972bc3f3d991235e8ea6928672
> > # good: [31094bce101651acb4747ab25d614bc893d65c89] kasan/test: avoid gcc warning for intentional overflow
> > git bisect good 31094bce101651acb4747ab25d614bc893d65c89
> > # bad: [55be0b2cd1fbf00e036e2e48ee0999599135af66] zram: do not allocate physically contiguous strm buffers
> > git bisect bad 55be0b2cd1fbf00e036e2e48ee0999599135af66
> > # good: [b11ca4a0a13024c0175dde56f9bd848803eddcd2] mm/mglru: improve swappiness handling
> > git bisect good b11ca4a0a13024c0175dde56f9bd848803eddcd2
> > # good: [22e7ccd57a1220afcd7c4da1f3005fd04d70014e] userfaultfd: move userfaultfd_ctx struct to header file
> > git bisect good 22e7ccd57a1220afcd7c4da1f3005fd04d70014e
> > # bad: [0a0d05338f13e64c9fb7ccd8f8d1793aaf33ec7d] userfaultfd: use per-vma locks in userfaultfd operations
> > git bisect bad 0a0d05338f13e64c9fb7ccd8f8d1793aaf33ec7d
> > # good: [8459e1c7acbe4442c6c0eef59825da1339e0a3cf] userfaultfd: protect mmap_changing with rw_sem in userfaulfd_ctx
> > git bisect good 8459e1c7acbe4442c6c0eef59825da1339e0a3cf
> > # first bad commit: [0a0d05338f13e64c9fb7ccd8f8d1793aaf33ec7d] userfaultfd: use per-vma locks in userfaultfd operations
> >
> > This is the oops:
>
> That's a call to mmap_assert_locked() from inside
> move_pages_huge_pmd(). Since move_pages() are now happening under VMA
> lock this call should be replaced with vma_assert_locked().
>
So sorry for missing this. I missed testing with CONFIG_DEBUG_VM
turned on. I'll fix and thoroughly test before sending the next
version.
> >
> > [ 21.280142] mm ffff049340ed0000 task_size 281474976710656
> > [ 21.280142] get_unmapped_area ffffb3dbdc725e48
> > [ 21.280142] mmap_base 281474842492928 mmap_legacy_base 0
> > [ 21.280142] pgd ffff04935829a000 mm_users 3 mm_count 4 pgtables_bytes 98304 map_count 21
> > [ 21.280142] hiwater_rss 2167 hiwater_vm 8234 total_vm 4a44 locked_vm 0
> > [ 21.280142] pinned_vm 0 data_vm 4835 exec_vm 1c6 stack_vm 21
> > [ 21.280142] start_code aaaaaaaa0000 end_code aaaaaaab1b28 start_data aaaaaaac2a60 end_data aaaaaaac3410
> > [ 21.280142] start_brk aaaaaaac5000 brk aaaaaaae6000 start_stack fffffffff6b0
> > [ 21.280142] arg_start fffffffff8c7 arg_end fffffffff8e2 env_start fffffffff8e2 env_end ffffffffffdd
> > [ 21.280142] binfmt ffffb3dbdf2f8cf8 flags 82008d
> > [ 21.280142] ioctx_table 0000000000000000
> > [ 21.280142] owner ffff049311f02280 exe_file ffff049355314c00
> > [ 21.280142] notifier_subscriptions 0000000000000000
> > [ 21.280142] numa_next_scan 4294897864 numa_scan_offset 0 numa_scan_seq 0
> > [ 21.280142] tlb_flush_pending 0
> > [ 21.280142] def_flags: 0x0()
> > [ 21.283302] kernel BUG at include/linux/mmap_lock.h:66!
> > [ 21.283481] Internal error: Oops - BUG: 00000000f2000800 [#1] PREEMPT SMP
> > [ 21.283720] Modules linked in:
> > [ 21.283867] CPU: 3 PID: 1226 Comm: uffd-unit-tests Not tainted 6.8.0-rc3-00297-g0a0d05338f13 #19
> > [ 21.284306] Hardware name: linux,dummy-virt (DT)
> > [ 21.284495] pstate: 61400005 (nZCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
> > [ 21.284833] pc : move_pages_huge_pmd+0x4d0/0x8a8
> > [ 21.285072] lr : move_pages_huge_pmd+0x4d0/0x8a8
> > [ 21.285289] sp : ffff800088573b30
> > [ 21.285439] x29: ffff800088573b30 x28: ffff049358292d78 x27: fffffc0000000000
> > [ 21.285770] x26: ffff049358292d78 x25: 0000fffff5e00000 x24: ffff049359db3730
> > [ 21.286097] x23: 0000fffff6000000 x22: ffff049340ed0000 x21: ffff049359db3678
> > [ 21.286422] x20: 0000000000000002 x19: fffffc124d60a480 x18: 0000000000000006
> > [ 21.286747] x17: 626c740a30207165 x16: 735f6e6163735f61 x15: 6d756e2030207465
> > [ 21.287084] x14: 7366666f5f6e6163 x13: 2928307830203a73 x12: 67616c665f666564
> > [ 21.287417] x11: 0a3020676e69646e x10: ffffb3dbdf28bff8 x9 : ffffb3dbdc620f80
> > [ 21.287745] x8 : 00000000ffffefff x7 : ffffb3dbdf28bff8 x6 : 80000000fffff000
> > [ 21.288082] x5 : ffff04933ffdcd08 x4 : 0000000000000000 x3 : 0000000000000000
> > [ 21.288364] x2 : 0000000000000000 x1 : ffff049340106780 x0 : 0000000000000328
> > [ 21.288712] Call trace:
> > [ 21.288832] move_pages_huge_pmd+0x4d0/0x8a8
> > [ 21.289058] move_pages+0x8b8/0x13d8
> > [ 21.289205] userfaultfd_ioctl+0x11e0/0x1e90
> > [ 21.289411] __arm64_sys_ioctl+0xb4/0x100
> > [ 21.289579] invoke_syscall+0x50/0x128
> > [ 21.289738] el0_svc_common.constprop.0+0x48/0xf0
> > [ 21.289942] do_el0_svc+0x24/0x38
> > [ 21.290078] el0_svc+0x34/0xb8
> > [ 21.290219] el0t_64_sync_handler+0x100/0x130
> > [ 21.290387] el0t_64_sync+0x190/0x198
> > [ 21.290535] Code: 17ffff7e a90363f7 a9046bf9 97fde2a7 (d4210000)
> > [ 21.290776] ---[ end trace 0000000000000000 ]---
> > [ 21.290966] note: uffd-unit-tests[1226] exited with irqs disabled
> > [ 21.291254] note: uffd-unit-tests[1226] exited with preempt_count 2
> > [ 21.292864] ------------[ cut here ]------------
> > [ 21.293020] WARNING: CPU: 3 PID: 0 at kernel/context_tracking.c:128 ct_kernel_exit.constprop.0+0x108/0x120
> > [ 21.293711] Modules linked in:
> > [ 21.294070] CPU: 3 PID: 0 Comm: swapper/3 Tainted: G D 6.8.0-rc3-00297-g0a0d05338f13 #19
> > [ 21.295447] Hardware name: linux,dummy-virt (DT)
> > [ 21.295850] pstate: 214003c5 (nzCv DAIF +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
> > [ 21.296152] pc : ct_kernel_exit.constprop.0+0x108/0x120
> > [ 21.296685] lr : ct_idle_enter+0x10/0x20
> > [ 21.296848] sp : ffff8000801b3dc0
> > [ 21.296983] x29: ffff8000801b3dc0 x28: 0000000000000000 x27: 0000000000000000
> > [ 21.297255] x26: 0000000000000000 x25: ffff049301496780 x24: 0000000000000000
> > [ 21.297533] x23: 0000000000000000 x22: ffff049301496780 x21: ffffb3dbdf209ae0
> > [ 21.297844] x20: ffffb3dbdf209a20 x19: ffff04933ffeace0 x18: ffff800088573648
> > [ 21.298152] x17: ffffb3dbdf65def0 x16: 00000000d72145a7 x15: 00000000f1a17b35
> > [ 21.298439] x14: 0000000000000004 x13: ffffb3dbdf22c3a8 x12: 0000000000000000
> > [ 21.298738] x11: ffff0493541472a8 x10: 2b58349b7608bfc4 x9 : ffffb3dbdc57f43c
> > [ 21.299031] x8 : ffff049301497858 x7 : 00000000000001c1 x6 : 000000001eeeb49c
> > [ 21.299329] x5 : 4000000000000002 x4 : ffff50b7618d7000 x3 : ffff8000801b3dc0
> > [ 21.299615] x2 : ffffb3dbde713ce0 x1 : 4000000000000000 x0 : ffffb3dbde713ce0
> > [ 21.299900] Call trace:
> > [ 21.299998] ct_kernel_exit.constprop.0+0x108/0x120
> > [ 21.300460] ct_idle_enter+0x10/0x20
> > [ 21.300690] default_idle_call+0x3c/0x170
> > [ 21.300861] do_idle+0x218/0x278
> > [ 21.300992] cpu_startup_entry+0x3c/0x50
> > [ 21.301148] secondary_start_kernel+0x130/0x158
> > [ 21.301329] __secondary_switched+0xb8/0xc0
> > [ 21.301641] ---[ end trace 0000000000000000 ]---
> >
> >
> > Can this series be removed from mm-unstable until fixed, please?
> >
> > Thanks,
> > Ryan
> >
> >
> > >
> > > Signed-off-by: Lokesh Gidra <[email protected]>
> > > ---
> > > fs/userfaultfd.c | 13 +-
> > > include/linux/userfaultfd_k.h | 5 +-
> > > mm/userfaultfd.c | 380 ++++++++++++++++++++++++++--------
> > > 3 files changed, 296 insertions(+), 102 deletions(-)
> > >
> > > diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
> > > index c00a021bcce4..60dcfafdc11a 100644
> > > --- a/fs/userfaultfd.c
> > > +++ b/fs/userfaultfd.c
> > > @@ -2005,17 +2005,8 @@ static int userfaultfd_move(struct userfaultfd_ctx *ctx,
> > > return -EINVAL;
> > >
> > > if (mmget_not_zero(mm)) {
> > > - mmap_read_lock(mm);
> > > -
> > > - /* Re-check after taking map_changing_lock */
> > > - down_read(&ctx->map_changing_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 = -EAGAIN;
> > > - up_read(&ctx->map_changing_lock);
> > > - 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;
> > > diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
> > > index 3210c3552976..05d59f74fc88 100644
> > > --- a/include/linux/userfaultfd_k.h
> > > +++ b/include/linux/userfaultfd_k.h
> > > @@ -138,9 +138,8 @@ extern long uffd_wp_range(struct vm_area_struct *vma,
> > > /* move_pages */
> > > void double_pt_lock(spinlock_t *ptl1, spinlock_t *ptl2);
> > > void double_pt_unlock(spinlock_t *ptl1, spinlock_t *ptl2);
> > > -ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
> > > - unsigned long dst_start, unsigned long src_start,
> > > - unsigned long len, __u64 flags);
> > > +ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start,
> > > + unsigned long src_start, unsigned long len, __u64 flags);
> > > int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pmd_t dst_pmdval,
> > > struct vm_area_struct *dst_vma,
> > > struct vm_area_struct *src_vma,
> > > diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
> > > index 74aad0831e40..4744d6a96f96 100644
> > > --- a/mm/userfaultfd.c
> > > +++ b/mm/userfaultfd.c
> > > @@ -20,19 +20,11 @@
> > > #include "internal.h"
> > >
> > > static __always_inline
> > > -struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm,
> > > - unsigned long dst_start,
> > > - unsigned long len)
> > > +bool validate_dst_vma(struct vm_area_struct *dst_vma, unsigned long dst_end)
> > > {
> > > - /*
> > > - * Make sure that the dst range is both valid and fully within a
> > > - * single existing vma.
> > > - */
> > > - struct vm_area_struct *dst_vma;
> > > -
> > > - dst_vma = find_vma(dst_mm, dst_start);
> > > - if (!range_in_vma(dst_vma, dst_start, dst_start + len))
> > > - return NULL;
> > > + /* Make sure that the dst range is fully within dst_vma. */
> > > + if (dst_end > dst_vma->vm_end)
> > > + return false;
> > >
> > > /*
> > > * Check the vma is registered in uffd, this is required to
> > > @@ -40,11 +32,122 @@ struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm,
> > > * time.
> > > */
> > > if (!dst_vma->vm_userfaultfd_ctx.ctx)
> > > - return NULL;
> > > + return false;
> > > +
> > > + return true;
> > > +}
> > > +
> > > +static __always_inline
> > > +struct vm_area_struct *find_vma_and_prepare_anon(struct mm_struct *mm,
> > > + unsigned long addr)
> > > +{
> > > + struct vm_area_struct *vma;
> > > +
> > > + mmap_assert_locked(mm);
> > > + vma = vma_lookup(mm, addr);
> > > + if (!vma)
> > > + vma = ERR_PTR(-ENOENT);
> > > + else if (!(vma->vm_flags & VM_SHARED) &&
> > > + unlikely(anon_vma_prepare(vma)))
> > > + vma = ERR_PTR(-ENOMEM);
> > > +
> > > + return vma;
> > > +}
> > > +
> > > +#ifdef CONFIG_PER_VMA_LOCK
> > > +/*
> > > + * lock_vma() - Lookup and lock vma corresponding to @address.
> > > + * @mm: mm to search vma in.
> > > + * @address: address that the vma should contain.
> > > + *
> > > + * Should be called without holding mmap_lock. vma should be unlocked after use
> > > + * with unlock_vma().
> > > + *
> > > + * Return: A locked vma containing @address, -ENOENT if no vma is found, or
> > > + * -ENOMEM if anon_vma couldn't be allocated.
> > > + */
> > > +static struct vm_area_struct *lock_vma(struct mm_struct *mm,
> > > + unsigned long address)
> > > +{
> > > + struct vm_area_struct *vma;
> > > +
> > > + vma = lock_vma_under_rcu(mm, address);
> > > + if (vma) {
> > > + /*
> > > + * lock_vma_under_rcu() only checks anon_vma for private
> > > + * anonymous mappings. But we need to ensure it is assigned in
> > > + * private file-backed vmas as well.
> > > + */
> > > + if (!(vma->vm_flags & VM_SHARED) && unlikely(!vma->anon_vma))
> > > + vma_end_read(vma);
> > > + else
> > > + return vma;
> > > + }
> > > +
> > > + mmap_read_lock(mm);
> > > + vma = find_vma_and_prepare_anon(mm, address);
> > > + if (!IS_ERR(vma)) {
> > > + /*
> > > + * We cannot use vma_start_read() as it may fail due to
> > > + * false locked (see comment in vma_start_read()). We
> > > + * can avoid that by directly locking vm_lock under
> > > + * mmap_lock, which guarantees that nobody can lock the
> > > + * vma for write (vma_start_write()) under us.
> > > + */
> > > + down_read(&vma->vm_lock->lock);
> > > + }
> > > +
> > > + mmap_read_unlock(mm);
> > > + return vma;
> > > +}
> > > +
> > > +static struct vm_area_struct *uffd_mfill_lock(struct mm_struct *dst_mm,
> > > + unsigned long dst_start,
> > > + unsigned long len)
> > > +{
> > > + struct vm_area_struct *dst_vma;
> > >
> > > + dst_vma = lock_vma(dst_mm, dst_start);
> > > + if (IS_ERR(dst_vma) || validate_dst_vma(dst_vma, dst_start + len))
> > > + return dst_vma;
> > > +
> > > + vma_end_read(dst_vma);
> > > + return ERR_PTR(-ENOENT);
> > > +}
> > > +
> > > +static void uffd_mfill_unlock(struct vm_area_struct *vma)
> > > +{
> > > + vma_end_read(vma);
> > > +}
> > > +
> > > +#else
> > > +
> > > +static struct vm_area_struct *uffd_mfill_lock(struct mm_struct *dst_mm,
> > > + unsigned long dst_start,
> > > + unsigned long len)
> > > +{
> > > + struct vm_area_struct *dst_vma;
> > > +
> > > + mmap_read_lock(dst_mm);
> > > + dst_vma = find_vma_and_prepare_anon(dst_mm, dst_start);
> > > + if (IS_ERR(dst_vma))
> > > + goto out_unlock;
> > > +
> > > + if (validate_dst_vma(dst_vma, dst_start + len))
> > > + return dst_vma;
> > > +
> > > + dst_vma = ERR_PTR(-ENOENT);
> > > +out_unlock:
> > > + mmap_read_unlock(dst_mm);
> > > return dst_vma;
> > > }
> > >
> > > +static void uffd_mfill_unlock(struct vm_area_struct *vma)
> > > +{
> > > + mmap_read_unlock(vma->vm_mm);
> > > +}
> > > +#endif
> > > +
> > > /* Check if dst_addr is outside of file's size. Must be called with ptl held. */
> > > static bool mfill_file_over_size(struct vm_area_struct *dst_vma,
> > > unsigned long dst_addr)
> > > @@ -350,7 +453,8 @@ static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address)
> > > #ifdef CONFIG_HUGETLB_PAGE
> > > /*
> > > * mfill_atomic processing for HUGETLB vmas. Note that this routine is
> > > - * called with mmap_lock held, it will release mmap_lock before returning.
> > > + * called with either vma-lock or mmap_lock held, it will release the lock
> > > + * before returning.
> > > */
> > > static __always_inline ssize_t mfill_atomic_hugetlb(
> > > struct userfaultfd_ctx *ctx,
> > > @@ -361,7 +465,6 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
> > > uffd_flags_t flags)
> > > {
> > > struct mm_struct *dst_mm = dst_vma->vm_mm;
> > > - int vm_shared = dst_vma->vm_flags & VM_SHARED;
> > > ssize_t err;
> > > pte_t *dst_pte;
> > > unsigned long src_addr, dst_addr;
> > > @@ -380,7 +483,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
> > > */
> > > if (uffd_flags_mode_is(flags, MFILL_ATOMIC_ZEROPAGE)) {
> > > up_read(&ctx->map_changing_lock);
> > > - mmap_read_unlock(dst_mm);
> > > + uffd_mfill_unlock(dst_vma);
> > > return -EINVAL;
> > > }
> > >
> > > @@ -403,24 +506,28 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
> > > * retry, dst_vma will be set to NULL and we must lookup again.
> > > */
> > > if (!dst_vma) {
> > > + dst_vma = uffd_mfill_lock(dst_mm, dst_start, len);
> > > + if (IS_ERR(dst_vma)) {
> > > + err = PTR_ERR(dst_vma);
> > > + goto out;
> > > + }
> > > +
> > > err = -ENOENT;
> > > - dst_vma = find_dst_vma(dst_mm, dst_start, len);
> > > - if (!dst_vma || !is_vm_hugetlb_page(dst_vma))
> > > - goto out_unlock;
> > > + if (!is_vm_hugetlb_page(dst_vma))
> > > + goto out_unlock_vma;
> > >
> > > err = -EINVAL;
> > > if (vma_hpagesize != vma_kernel_pagesize(dst_vma))
> > > - goto out_unlock;
> > > -
> > > - vm_shared = dst_vma->vm_flags & VM_SHARED;
> > > - }
> > > + goto out_unlock_vma;
> > >
> > > - /*
> > > - * If not shared, ensure the dst_vma has a anon_vma.
> > > - */
> > > - err = -ENOMEM;
> > > - if (!vm_shared) {
> > > - if (unlikely(anon_vma_prepare(dst_vma)))
> > > + /*
> > > + * If memory mappings are changing because of non-cooperative
> > > + * operation (e.g. mremap) running in parallel, bail out and
> > > + * request the user to retry later
> > > + */
> > > + down_read(&ctx->map_changing_lock);
> > > + err = -EAGAIN;
> > > + if (atomic_read(&ctx->mmap_changing))
> > > goto out_unlock;
> > > }
> > >
> > > @@ -465,7 +572,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
> > >
> > > if (unlikely(err == -ENOENT)) {
> > > up_read(&ctx->map_changing_lock);
> > > - mmap_read_unlock(dst_mm);
> > > + uffd_mfill_unlock(dst_vma);
> > > BUG_ON(!folio);
> > >
> > > err = copy_folio_from_user(folio,
> > > @@ -474,17 +581,6 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
> > > err = -EFAULT;
> > > goto out;
> > > }
> > > - mmap_read_lock(dst_mm);
> > > - down_read(&ctx->map_changing_lock);
> > > - /*
> > > - * If memory mappings are changing because of non-cooperative
> > > - * operation (e.g. mremap) running in parallel, bail out and
> > > - * request the user to retry later
> > > - */
> > > - if (atomic_read(&ctx->mmap_changing)) {
> > > - err = -EAGAIN;
> > > - break;
> > > - }
> > >
> > > dst_vma = NULL;
> > > goto retry;
> > > @@ -505,7 +601,8 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
> > >
> > > out_unlock:
> > > up_read(&ctx->map_changing_lock);
> > > - mmap_read_unlock(dst_mm);
> > > +out_unlock_vma:
> > > + uffd_mfill_unlock(dst_vma);
> > > out:
> > > if (folio)
> > > folio_put(folio);
> > > @@ -597,7 +694,15 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
> > > copied = 0;
> > > folio = NULL;
> > > retry:
> > > - mmap_read_lock(dst_mm);
> > > + /*
> > > + * Make sure the vma is not shared, that the dst range is
> > > + * both valid and fully within a single existing vma.
> > > + */
> > > + dst_vma = uffd_mfill_lock(dst_mm, dst_start, len);
> > > + if (IS_ERR(dst_vma)) {
> > > + err = PTR_ERR(dst_vma);
> > > + goto out;
> > > + }
> > >
> > > /*
> > > * If memory mappings are changing because of non-cooperative
> > > @@ -609,15 +714,6 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
> > > if (atomic_read(&ctx->mmap_changing))
> > > goto out_unlock;
> > >
> > > - /*
> > > - * Make sure the vma is not shared, that the dst range is
> > > - * both valid and fully within a single existing vma.
> > > - */
> > > - err = -ENOENT;
> > > - dst_vma = find_dst_vma(dst_mm, dst_start, len);
> > > - if (!dst_vma)
> > > - goto out_unlock;
> > > -
> > > err = -EINVAL;
> > > /*
> > > * shmem_zero_setup is invoked in mmap for MAP_ANONYMOUS|MAP_SHARED but
> > > @@ -647,16 +743,6 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
> > > uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE))
> > > goto out_unlock;
> > >
> > > - /*
> > > - * Ensure the dst_vma has a anon_vma or this page
> > > - * would get a NULL anon_vma when moved in the
> > > - * dst_vma.
> > > - */
> > > - err = -ENOMEM;
> > > - if (!(dst_vma->vm_flags & VM_SHARED) &&
> > > - unlikely(anon_vma_prepare(dst_vma)))
> > > - goto out_unlock;
> > > -
> > > while (src_addr < src_start + len) {
> > > pmd_t dst_pmdval;
> > >
> > > @@ -699,7 +785,7 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
> > > void *kaddr;
> > >
> > > up_read(&ctx->map_changing_lock);
> > > - mmap_read_unlock(dst_mm);
> > > + uffd_mfill_unlock(dst_vma);
> > > BUG_ON(!folio);
> > >
> > > kaddr = kmap_local_folio(folio, 0);
> > > @@ -730,7 +816,7 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
> > >
> > > out_unlock:
> > > up_read(&ctx->map_changing_lock);
> > > - mmap_read_unlock(dst_mm);
> > > + uffd_mfill_unlock(dst_vma);
> > > out:
> > > if (folio)
> > > folio_put(folio);
> > > @@ -1267,27 +1353,136 @@ static int validate_move_areas(struct userfaultfd_ctx *ctx,
> > > if (!vma_is_anonymous(src_vma) || !vma_is_anonymous(dst_vma))
> > > return -EINVAL;
> > >
> > > + return 0;
> > > +}
> > > +
> > > +static __always_inline
> > > +int find_vmas_mm_locked(struct mm_struct *mm,
> > > + unsigned long dst_start,
> > > + unsigned long src_start,
> > > + struct vm_area_struct **dst_vmap,
> > > + struct vm_area_struct **src_vmap)
> > > +{
> > > + struct vm_area_struct *vma;
> > > +
> > > + mmap_assert_locked(mm);
> > > + vma = find_vma_and_prepare_anon(mm, dst_start);
> > > + if (IS_ERR(vma))
> > > + return PTR_ERR(vma);
> > > +
> > > + *dst_vmap = vma;
> > > + /* Skip finding src_vma if src_start is in dst_vma */
> > > + if (src_start >= vma->vm_start && src_start < vma->vm_end)
> > > + goto out_success;
> > > +
> > > + vma = vma_lookup(mm, src_start);
> > > + if (!vma)
> > > + return -ENOENT;
> > > +out_success:
> > > + *src_vmap = vma;
> > > + return 0;
> > > +}
> > > +
> > > +#ifdef CONFIG_PER_VMA_LOCK
> > > +static int uffd_move_lock(struct mm_struct *mm,
> > > + unsigned long dst_start,
> > > + unsigned long src_start,
> > > + struct vm_area_struct **dst_vmap,
> > > + struct vm_area_struct **src_vmap)
> > > +{
> > > + struct vm_area_struct *vma;
> > > + int err;
> > > +
> > > + vma = lock_vma(mm, dst_start);
> > > + if (IS_ERR(vma))
> > > + return PTR_ERR(vma);
> > > +
> > > + *dst_vmap = vma;
> > > /*
> > > - * Ensure the dst_vma has a anon_vma or this page
> > > - * would get a NULL anon_vma when moved in the
> > > - * dst_vma.
> > > + * Skip finding src_vma if src_start is in dst_vma. This also ensures
> > > + * that we don't lock the same vma twice.
> > > */
> > > - if (unlikely(anon_vma_prepare(dst_vma)))
> > > - return -ENOMEM;
> > > + if (src_start >= vma->vm_start && src_start < vma->vm_end) {
> > > + *src_vmap = vma;
> > > + return 0;
> > > + }
> > >
> > > - return 0;
> > > + /*
> > > + * Using lock_vma() to get src_vma can lead to following deadlock:
> > > + *
> > > + * Thread1 Thread2
> > > + * ------- -------
> > > + * vma_start_read(dst_vma)
> > > + * mmap_write_lock(mm)
> > > + * vma_start_write(src_vma)
> > > + * vma_start_read(src_vma)
> > > + * mmap_read_lock(mm)
> > > + * vma_start_write(dst_vma)
> > > + */
> > > + *src_vmap = lock_vma_under_rcu(mm, src_start);
> > > + if (likely(*src_vmap))
> > > + return 0;
> > > +
> > > + /* Undo any locking and retry in mmap_lock critical section */
> > > + vma_end_read(*dst_vmap);
> > > +
> > > + mmap_read_lock(mm);
> > > + err = find_vmas_mm_locked(mm, dst_start, src_start, dst_vmap, src_vmap);
> > > + if (!err) {
> > > + /*
> > > + * See comment in lock_vma() as to why not using
> > > + * vma_start_read() here.
> > > + */
> > > + down_read(&(*dst_vmap)->vm_lock->lock);
> > > + if (*dst_vmap != *src_vmap)
> > > + down_read(&(*src_vmap)->vm_lock->lock);
> > > + }
> > > + mmap_read_unlock(mm);
> > > + return err;
> > > +}
> > > +
> > > +static void uffd_move_unlock(struct vm_area_struct *dst_vma,
> > > + struct vm_area_struct *src_vma)
> > > +{
> > > + vma_end_read(src_vma);
> > > + if (src_vma != dst_vma)
> > > + vma_end_read(dst_vma);
> > > }
> > >
> > > +#else
> > > +
> > > +static int uffd_move_lock(struct mm_struct *mm,
> > > + unsigned long dst_start,
> > > + unsigned long src_start,
> > > + struct vm_area_struct **dst_vmap,
> > > + struct vm_area_struct **src_vmap)
> > > +{
> > > + int err;
> > > +
> > > + mmap_read_lock(mm);
> > > + err = find_vmas_mm_locked(mm, dst_start, src_start, dst_vmap, src_vmap);
> > > + if (err)
> > > + mmap_read_unlock(mm);
> > > + return err;
> > > +}
> > > +
> > > +static void uffd_move_unlock(struct vm_area_struct *dst_vma,
> > > + struct vm_area_struct *src_vma)
> > > +{
> > > + mmap_assert_locked(src_vma->vm_mm);
> > > + mmap_read_unlock(dst_vma->vm_mm);
> > > +}
> > > +#endif
> > > +
> > > /**
> > > * move_pages - move arbitrary anonymous pages of an existing vma
> > > * @ctx: pointer to the userfaultfd context
> > > - * @mm: the address space to move pages
> > > * @dst_start: start of the destination virtual memory range
> > > * @src_start: start of the source virtual memory range
> > > * @len: length of the virtual memory range
> > > * @mode: flags from uffdio_move.mode
> > > *
> > > - * Must be called with mmap_lock held for read.
> > > + * It will either use the mmap_lock in read mode or per-vma locks
> > > *
> > > * move_pages() remaps arbitrary anonymous pages atomically in zero
> > > * copy. It only works on non shared anonymous pages because those can
> > > @@ -1355,10 +1550,10 @@ static int validate_move_areas(struct userfaultfd_ctx *ctx,
> > > * could be obtained. This is the only additional complexity added to
> > > * the rmap code to provide this anonymous page remapping functionality.
> > > */
> > > -ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
> > > - unsigned long dst_start, unsigned long src_start,
> > > - unsigned long len, __u64 mode)
> > > +ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start,
> > > + unsigned long src_start, unsigned long len, __u64 mode)
> > > {
> > > + struct mm_struct *mm = ctx->mm;
> > > struct vm_area_struct *src_vma, *dst_vma;
> > > unsigned long src_addr, dst_addr;
> > > pmd_t *src_pmd, *dst_pmd;
> > > @@ -1376,28 +1571,34 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
> > > WARN_ON_ONCE(dst_start + len <= dst_start))
> > > goto out;
> > >
> > > + err = uffd_move_lock(mm, dst_start, src_start, &dst_vma, &src_vma);
> > > + if (err)
> > > + goto out;
> > > +
> > > + /* Re-check after taking map_changing_lock */
> > > + err = -EAGAIN;
> > > + down_read(&ctx->map_changing_lock);
> > > + if (likely(atomic_read(&ctx->mmap_changing)))
> > > + goto out_unlock;
> > > /*
> > > * Make sure the vma is not shared, that the src and dst remap
> > > * ranges are both valid and fully within a single existing
> > > * vma.
> > > */
> > > - src_vma = find_vma(mm, src_start);
> > > - if (!src_vma || (src_vma->vm_flags & VM_SHARED))
> > > - goto out;
> > > - if (src_start < src_vma->vm_start ||
> > > - src_start + len > src_vma->vm_end)
> > > - goto out;
> > > + err = -EINVAL;
> > > + if (src_vma->vm_flags & VM_SHARED)
> > > + goto out_unlock;
> > > + if (src_start + len > src_vma->vm_end)
> > > + goto out_unlock;
> > >
> > > - dst_vma = find_vma(mm, dst_start);
> > > - if (!dst_vma || (dst_vma->vm_flags & VM_SHARED))
> > > - goto out;
> > > - if (dst_start < dst_vma->vm_start ||
> > > - dst_start + len > dst_vma->vm_end)
> > > - goto out;
> > > + if (dst_vma->vm_flags & VM_SHARED)
> > > + goto out_unlock;
> > > + if (dst_start + len > dst_vma->vm_end)
> > > + goto out_unlock;
> > >
> > > err = validate_move_areas(ctx, src_vma, dst_vma);
> > > if (err)
> > > - goto out;
> > > + goto out_unlock;
> > >
> > > for (src_addr = src_start, dst_addr = dst_start;
> > > src_addr < src_start + len;) {
> > > @@ -1514,6 +1715,9 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
> > > moved += step_size;
> > > }
> > >
> > > +out_unlock:
> > > + up_read(&ctx->map_changing_lock);
> > > + uffd_move_unlock(dst_vma, src_vma);
> > > out:
> > > VM_WARN_ON(moved < 0);
> > > VM_WARN_ON(err > 0);
> >
> > --
> > To unsubscribe from this group and stop receiving emails from it, send an email to [email protected].
> >
On 14/02/2024 22:27, Lokesh Gidra wrote:
> On Wed, Feb 14, 2024 at 2:20 PM Suren Baghdasaryan <[email protected]> wrote:
>>
>> On Wed, Feb 14, 2024 at 2:12 PM Ryan Roberts <[email protected]> wrote:
>>>
>>> On 13/02/2024 21:57, Lokesh Gidra wrote:
>>>> All userfaultfd operations, except write-protect, opportunistically use
>>>> per-vma locks to lock vmas. On failure, attempt again inside mmap_lock
>>>> critical section.
>>>>
>>>> Write-protect operation requires mmap_lock as it iterates over multiple
>>>> vmas.
>>>
>>> Hi,
>>>
>>> I'm seeing the below OOPS when running on arm64 against mm-unstable. It can be reliably reproduced by running the `uffd-unit-tests` mm selftest. Bisecting mm-unstable leads to this patch:
>>>
>>> # bad: [649936c3db47f8f75b9b927e4edf5922a0f240a6] mm: add swappiness= arg to memory.reclaim
>>> git bisect bad 649936c3db47f8f75b9b927e4edf5922a0f240a6
>>> # good: [54be6c6c5ae8e0d93a6c4641cb7528eb0b6ba478] Linux 6.8-rc3
>>> git bisect good 54be6c6c5ae8e0d93a6c4641cb7528eb0b6ba478
>>> # good: [10794cd18bb46c91c75fac44e551201cfe006baf] mm: zswap: warn when referencing a dead entry
>>> git bisect good 10794cd18bb46c91c75fac44e551201cfe006baf
>>> # good: [cb769b427edc7f46c7c764daa3421725bffdf315] mm-memcg-use-larger-batches-for-proactive-reclaim-v4
>>> git bisect good cb769b427edc7f46c7c764daa3421725bffdf315
>>> # good: [cfc5c1be4010c9972bc3f3d991235e8ea6928672] mm/z3fold: remove unneeded spinlock
>>> git bisect good cfc5c1be4010c9972bc3f3d991235e8ea6928672
>>> # good: [31094bce101651acb4747ab25d614bc893d65c89] kasan/test: avoid gcc warning for intentional overflow
>>> git bisect good 31094bce101651acb4747ab25d614bc893d65c89
>>> # bad: [55be0b2cd1fbf00e036e2e48ee0999599135af66] zram: do not allocate physically contiguous strm buffers
>>> git bisect bad 55be0b2cd1fbf00e036e2e48ee0999599135af66
>>> # good: [b11ca4a0a13024c0175dde56f9bd848803eddcd2] mm/mglru: improve swappiness handling
>>> git bisect good b11ca4a0a13024c0175dde56f9bd848803eddcd2
>>> # good: [22e7ccd57a1220afcd7c4da1f3005fd04d70014e] userfaultfd: move userfaultfd_ctx struct to header file
>>> git bisect good 22e7ccd57a1220afcd7c4da1f3005fd04d70014e
>>> # bad: [0a0d05338f13e64c9fb7ccd8f8d1793aaf33ec7d] userfaultfd: use per-vma locks in userfaultfd operations
>>> git bisect bad 0a0d05338f13e64c9fb7ccd8f8d1793aaf33ec7d
>>> # good: [8459e1c7acbe4442c6c0eef59825da1339e0a3cf] userfaultfd: protect mmap_changing with rw_sem in userfaulfd_ctx
>>> git bisect good 8459e1c7acbe4442c6c0eef59825da1339e0a3cf
>>> # first bad commit: [0a0d05338f13e64c9fb7ccd8f8d1793aaf33ec7d] userfaultfd: use per-vma locks in userfaultfd operations
>>>
>>> This is the oops:
>>
>> That's a call to mmap_assert_locked() from inside
>> move_pages_huge_pmd(). Since move_pages() are now happening under VMA
>> lock this call should be replaced with vma_assert_locked().
>>
> So sorry for missing this. I missed testing with CONFIG_DEBUG_VM
> turned on. I'll fix and thoroughly test before sending the next
> version.
No worries, I've reverted this patch in my branch and that's unblocked me, so
don't sweat it.
>
>>>
>>> [ 21.280142] mm ffff049340ed0000 task_size 281474976710656
>>> [ 21.280142] get_unmapped_area ffffb3dbdc725e48
>>> [ 21.280142] mmap_base 281474842492928 mmap_legacy_base 0
>>> [ 21.280142] pgd ffff04935829a000 mm_users 3 mm_count 4 pgtables_bytes 98304 map_count 21
>>> [ 21.280142] hiwater_rss 2167 hiwater_vm 8234 total_vm 4a44 locked_vm 0
>>> [ 21.280142] pinned_vm 0 data_vm 4835 exec_vm 1c6 stack_vm 21
>>> [ 21.280142] start_code aaaaaaaa0000 end_code aaaaaaab1b28 start_data aaaaaaac2a60 end_data aaaaaaac3410
>>> [ 21.280142] start_brk aaaaaaac5000 brk aaaaaaae6000 start_stack fffffffff6b0
>>> [ 21.280142] arg_start fffffffff8c7 arg_end fffffffff8e2 env_start fffffffff8e2 env_end ffffffffffdd
>>> [ 21.280142] binfmt ffffb3dbdf2f8cf8 flags 82008d
>>> [ 21.280142] ioctx_table 0000000000000000
>>> [ 21.280142] owner ffff049311f02280 exe_file ffff049355314c00
>>> [ 21.280142] notifier_subscriptions 0000000000000000
>>> [ 21.280142] numa_next_scan 4294897864 numa_scan_offset 0 numa_scan_seq 0
>>> [ 21.280142] tlb_flush_pending 0
>>> [ 21.280142] def_flags: 0x0()
>>> [ 21.283302] kernel BUG at include/linux/mmap_lock.h:66!
>>> [ 21.283481] Internal error: Oops - BUG: 00000000f2000800 [#1] PREEMPT SMP
>>> [ 21.283720] Modules linked in:
>>> [ 21.283867] CPU: 3 PID: 1226 Comm: uffd-unit-tests Not tainted 6.8.0-rc3-00297-g0a0d05338f13 #19
>>> [ 21.284306] Hardware name: linux,dummy-virt (DT)
>>> [ 21.284495] pstate: 61400005 (nZCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
>>> [ 21.284833] pc : move_pages_huge_pmd+0x4d0/0x8a8
>>> [ 21.285072] lr : move_pages_huge_pmd+0x4d0/0x8a8
>>> [ 21.285289] sp : ffff800088573b30
>>> [ 21.285439] x29: ffff800088573b30 x28: ffff049358292d78 x27: fffffc0000000000
>>> [ 21.285770] x26: ffff049358292d78 x25: 0000fffff5e00000 x24: ffff049359db3730
>>> [ 21.286097] x23: 0000fffff6000000 x22: ffff049340ed0000 x21: ffff049359db3678
>>> [ 21.286422] x20: 0000000000000002 x19: fffffc124d60a480 x18: 0000000000000006
>>> [ 21.286747] x17: 626c740a30207165 x16: 735f6e6163735f61 x15: 6d756e2030207465
>>> [ 21.287084] x14: 7366666f5f6e6163 x13: 2928307830203a73 x12: 67616c665f666564
>>> [ 21.287417] x11: 0a3020676e69646e x10: ffffb3dbdf28bff8 x9 : ffffb3dbdc620f80
>>> [ 21.287745] x8 : 00000000ffffefff x7 : ffffb3dbdf28bff8 x6 : 80000000fffff000
>>> [ 21.288082] x5 : ffff04933ffdcd08 x4 : 0000000000000000 x3 : 0000000000000000
>>> [ 21.288364] x2 : 0000000000000000 x1 : ffff049340106780 x0 : 0000000000000328
>>> [ 21.288712] Call trace:
>>> [ 21.288832] move_pages_huge_pmd+0x4d0/0x8a8
>>> [ 21.289058] move_pages+0x8b8/0x13d8
>>> [ 21.289205] userfaultfd_ioctl+0x11e0/0x1e90
>>> [ 21.289411] __arm64_sys_ioctl+0xb4/0x100
>>> [ 21.289579] invoke_syscall+0x50/0x128
>>> [ 21.289738] el0_svc_common.constprop.0+0x48/0xf0
>>> [ 21.289942] do_el0_svc+0x24/0x38
>>> [ 21.290078] el0_svc+0x34/0xb8
>>> [ 21.290219] el0t_64_sync_handler+0x100/0x130
>>> [ 21.290387] el0t_64_sync+0x190/0x198
>>> [ 21.290535] Code: 17ffff7e a90363f7 a9046bf9 97fde2a7 (d4210000)
>>> [ 21.290776] ---[ end trace 0000000000000000 ]---
>>> [ 21.290966] note: uffd-unit-tests[1226] exited with irqs disabled
>>> [ 21.291254] note: uffd-unit-tests[1226] exited with preempt_count 2
>>> [ 21.292864] ------------[ cut here ]------------
>>> [ 21.293020] WARNING: CPU: 3 PID: 0 at kernel/context_tracking.c:128 ct_kernel_exit.constprop.0+0x108/0x120
>>> [ 21.293711] Modules linked in:
>>> [ 21.294070] CPU: 3 PID: 0 Comm: swapper/3 Tainted: G D 6.8.0-rc3-00297-g0a0d05338f13 #19
>>> [ 21.295447] Hardware name: linux,dummy-virt (DT)
>>> [ 21.295850] pstate: 214003c5 (nzCv DAIF +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
>>> [ 21.296152] pc : ct_kernel_exit.constprop.0+0x108/0x120
>>> [ 21.296685] lr : ct_idle_enter+0x10/0x20
>>> [ 21.296848] sp : ffff8000801b3dc0
>>> [ 21.296983] x29: ffff8000801b3dc0 x28: 0000000000000000 x27: 0000000000000000
>>> [ 21.297255] x26: 0000000000000000 x25: ffff049301496780 x24: 0000000000000000
>>> [ 21.297533] x23: 0000000000000000 x22: ffff049301496780 x21: ffffb3dbdf209ae0
>>> [ 21.297844] x20: ffffb3dbdf209a20 x19: ffff04933ffeace0 x18: ffff800088573648
>>> [ 21.298152] x17: ffffb3dbdf65def0 x16: 00000000d72145a7 x15: 00000000f1a17b35
>>> [ 21.298439] x14: 0000000000000004 x13: ffffb3dbdf22c3a8 x12: 0000000000000000
>>> [ 21.298738] x11: ffff0493541472a8 x10: 2b58349b7608bfc4 x9 : ffffb3dbdc57f43c
>>> [ 21.299031] x8 : ffff049301497858 x7 : 00000000000001c1 x6 : 000000001eeeb49c
>>> [ 21.299329] x5 : 4000000000000002 x4 : ffff50b7618d7000 x3 : ffff8000801b3dc0
>>> [ 21.299615] x2 : ffffb3dbde713ce0 x1 : 4000000000000000 x0 : ffffb3dbde713ce0
>>> [ 21.299900] Call trace:
>>> [ 21.299998] ct_kernel_exit.constprop.0+0x108/0x120
>>> [ 21.300460] ct_idle_enter+0x10/0x20
>>> [ 21.300690] default_idle_call+0x3c/0x170
>>> [ 21.300861] do_idle+0x218/0x278
>>> [ 21.300992] cpu_startup_entry+0x3c/0x50
>>> [ 21.301148] secondary_start_kernel+0x130/0x158
>>> [ 21.301329] __secondary_switched+0xb8/0xc0
>>> [ 21.301641] ---[ end trace 0000000000000000 ]---
>>>
>>>
>>> Can this series be removed from mm-unstable until fixed, please?
>>>
>>> Thanks,
>>> Ryan
>>>
>>>
>>>>
>>>> Signed-off-by: Lokesh Gidra <[email protected]>
>>>> ---
>>>> fs/userfaultfd.c | 13 +-
>>>> include/linux/userfaultfd_k.h | 5 +-
>>>> mm/userfaultfd.c | 380 ++++++++++++++++++++++++++--------
>>>> 3 files changed, 296 insertions(+), 102 deletions(-)
>>>>
>>>> diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
>>>> index c00a021bcce4..60dcfafdc11a 100644
>>>> --- a/fs/userfaultfd.c
>>>> +++ b/fs/userfaultfd.c
>>>> @@ -2005,17 +2005,8 @@ static int userfaultfd_move(struct userfaultfd_ctx *ctx,
>>>> return -EINVAL;
>>>>
>>>> if (mmget_not_zero(mm)) {
>>>> - mmap_read_lock(mm);
>>>> -
>>>> - /* Re-check after taking map_changing_lock */
>>>> - down_read(&ctx->map_changing_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 = -EAGAIN;
>>>> - up_read(&ctx->map_changing_lock);
>>>> - 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;
>>>> diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
>>>> index 3210c3552976..05d59f74fc88 100644
>>>> --- a/include/linux/userfaultfd_k.h
>>>> +++ b/include/linux/userfaultfd_k.h
>>>> @@ -138,9 +138,8 @@ extern long uffd_wp_range(struct vm_area_struct *vma,
>>>> /* move_pages */
>>>> void double_pt_lock(spinlock_t *ptl1, spinlock_t *ptl2);
>>>> void double_pt_unlock(spinlock_t *ptl1, spinlock_t *ptl2);
>>>> -ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
>>>> - unsigned long dst_start, unsigned long src_start,
>>>> - unsigned long len, __u64 flags);
>>>> +ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start,
>>>> + unsigned long src_start, unsigned long len, __u64 flags);
>>>> int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pmd_t dst_pmdval,
>>>> struct vm_area_struct *dst_vma,
>>>> struct vm_area_struct *src_vma,
>>>> diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
>>>> index 74aad0831e40..4744d6a96f96 100644
>>>> --- a/mm/userfaultfd.c
>>>> +++ b/mm/userfaultfd.c
>>>> @@ -20,19 +20,11 @@
>>>> #include "internal.h"
>>>>
>>>> static __always_inline
>>>> -struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm,
>>>> - unsigned long dst_start,
>>>> - unsigned long len)
>>>> +bool validate_dst_vma(struct vm_area_struct *dst_vma, unsigned long dst_end)
>>>> {
>>>> - /*
>>>> - * Make sure that the dst range is both valid and fully within a
>>>> - * single existing vma.
>>>> - */
>>>> - struct vm_area_struct *dst_vma;
>>>> -
>>>> - dst_vma = find_vma(dst_mm, dst_start);
>>>> - if (!range_in_vma(dst_vma, dst_start, dst_start + len))
>>>> - return NULL;
>>>> + /* Make sure that the dst range is fully within dst_vma. */
>>>> + if (dst_end > dst_vma->vm_end)
>>>> + return false;
>>>>
>>>> /*
>>>> * Check the vma is registered in uffd, this is required to
>>>> @@ -40,11 +32,122 @@ struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm,
>>>> * time.
>>>> */
>>>> if (!dst_vma->vm_userfaultfd_ctx.ctx)
>>>> - return NULL;
>>>> + return false;
>>>> +
>>>> + return true;
>>>> +}
>>>> +
>>>> +static __always_inline
>>>> +struct vm_area_struct *find_vma_and_prepare_anon(struct mm_struct *mm,
>>>> + unsigned long addr)
>>>> +{
>>>> + struct vm_area_struct *vma;
>>>> +
>>>> + mmap_assert_locked(mm);
>>>> + vma = vma_lookup(mm, addr);
>>>> + if (!vma)
>>>> + vma = ERR_PTR(-ENOENT);
>>>> + else if (!(vma->vm_flags & VM_SHARED) &&
>>>> + unlikely(anon_vma_prepare(vma)))
>>>> + vma = ERR_PTR(-ENOMEM);
>>>> +
>>>> + return vma;
>>>> +}
>>>> +
>>>> +#ifdef CONFIG_PER_VMA_LOCK
>>>> +/*
>>>> + * lock_vma() - Lookup and lock vma corresponding to @address.
>>>> + * @mm: mm to search vma in.
>>>> + * @address: address that the vma should contain.
>>>> + *
>>>> + * Should be called without holding mmap_lock. vma should be unlocked after use
>>>> + * with unlock_vma().
>>>> + *
>>>> + * Return: A locked vma containing @address, -ENOENT if no vma is found, or
>>>> + * -ENOMEM if anon_vma couldn't be allocated.
>>>> + */
>>>> +static struct vm_area_struct *lock_vma(struct mm_struct *mm,
>>>> + unsigned long address)
>>>> +{
>>>> + struct vm_area_struct *vma;
>>>> +
>>>> + vma = lock_vma_under_rcu(mm, address);
>>>> + if (vma) {
>>>> + /*
>>>> + * lock_vma_under_rcu() only checks anon_vma for private
>>>> + * anonymous mappings. But we need to ensure it is assigned in
>>>> + * private file-backed vmas as well.
>>>> + */
>>>> + if (!(vma->vm_flags & VM_SHARED) && unlikely(!vma->anon_vma))
>>>> + vma_end_read(vma);
>>>> + else
>>>> + return vma;
>>>> + }
>>>> +
>>>> + mmap_read_lock(mm);
>>>> + vma = find_vma_and_prepare_anon(mm, address);
>>>> + if (!IS_ERR(vma)) {
>>>> + /*
>>>> + * We cannot use vma_start_read() as it may fail due to
>>>> + * false locked (see comment in vma_start_read()). We
>>>> + * can avoid that by directly locking vm_lock under
>>>> + * mmap_lock, which guarantees that nobody can lock the
>>>> + * vma for write (vma_start_write()) under us.
>>>> + */
>>>> + down_read(&vma->vm_lock->lock);
>>>> + }
>>>> +
>>>> + mmap_read_unlock(mm);
>>>> + return vma;
>>>> +}
>>>> +
>>>> +static struct vm_area_struct *uffd_mfill_lock(struct mm_struct *dst_mm,
>>>> + unsigned long dst_start,
>>>> + unsigned long len)
>>>> +{
>>>> + struct vm_area_struct *dst_vma;
>>>>
>>>> + dst_vma = lock_vma(dst_mm, dst_start);
>>>> + if (IS_ERR(dst_vma) || validate_dst_vma(dst_vma, dst_start + len))
>>>> + return dst_vma;
>>>> +
>>>> + vma_end_read(dst_vma);
>>>> + return ERR_PTR(-ENOENT);
>>>> +}
>>>> +
>>>> +static void uffd_mfill_unlock(struct vm_area_struct *vma)
>>>> +{
>>>> + vma_end_read(vma);
>>>> +}
>>>> +
>>>> +#else
>>>> +
>>>> +static struct vm_area_struct *uffd_mfill_lock(struct mm_struct *dst_mm,
>>>> + unsigned long dst_start,
>>>> + unsigned long len)
>>>> +{
>>>> + struct vm_area_struct *dst_vma;
>>>> +
>>>> + mmap_read_lock(dst_mm);
>>>> + dst_vma = find_vma_and_prepare_anon(dst_mm, dst_start);
>>>> + if (IS_ERR(dst_vma))
>>>> + goto out_unlock;
>>>> +
>>>> + if (validate_dst_vma(dst_vma, dst_start + len))
>>>> + return dst_vma;
>>>> +
>>>> + dst_vma = ERR_PTR(-ENOENT);
>>>> +out_unlock:
>>>> + mmap_read_unlock(dst_mm);
>>>> return dst_vma;
>>>> }
>>>>
>>>> +static void uffd_mfill_unlock(struct vm_area_struct *vma)
>>>> +{
>>>> + mmap_read_unlock(vma->vm_mm);
>>>> +}
>>>> +#endif
>>>> +
>>>> /* Check if dst_addr is outside of file's size. Must be called with ptl held. */
>>>> static bool mfill_file_over_size(struct vm_area_struct *dst_vma,
>>>> unsigned long dst_addr)
>>>> @@ -350,7 +453,8 @@ static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address)
>>>> #ifdef CONFIG_HUGETLB_PAGE
>>>> /*
>>>> * mfill_atomic processing for HUGETLB vmas. Note that this routine is
>>>> - * called with mmap_lock held, it will release mmap_lock before returning.
>>>> + * called with either vma-lock or mmap_lock held, it will release the lock
>>>> + * before returning.
>>>> */
>>>> static __always_inline ssize_t mfill_atomic_hugetlb(
>>>> struct userfaultfd_ctx *ctx,
>>>> @@ -361,7 +465,6 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
>>>> uffd_flags_t flags)
>>>> {
>>>> struct mm_struct *dst_mm = dst_vma->vm_mm;
>>>> - int vm_shared = dst_vma->vm_flags & VM_SHARED;
>>>> ssize_t err;
>>>> pte_t *dst_pte;
>>>> unsigned long src_addr, dst_addr;
>>>> @@ -380,7 +483,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
>>>> */
>>>> if (uffd_flags_mode_is(flags, MFILL_ATOMIC_ZEROPAGE)) {
>>>> up_read(&ctx->map_changing_lock);
>>>> - mmap_read_unlock(dst_mm);
>>>> + uffd_mfill_unlock(dst_vma);
>>>> return -EINVAL;
>>>> }
>>>>
>>>> @@ -403,24 +506,28 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
>>>> * retry, dst_vma will be set to NULL and we must lookup again.
>>>> */
>>>> if (!dst_vma) {
>>>> + dst_vma = uffd_mfill_lock(dst_mm, dst_start, len);
>>>> + if (IS_ERR(dst_vma)) {
>>>> + err = PTR_ERR(dst_vma);
>>>> + goto out;
>>>> + }
>>>> +
>>>> err = -ENOENT;
>>>> - dst_vma = find_dst_vma(dst_mm, dst_start, len);
>>>> - if (!dst_vma || !is_vm_hugetlb_page(dst_vma))
>>>> - goto out_unlock;
>>>> + if (!is_vm_hugetlb_page(dst_vma))
>>>> + goto out_unlock_vma;
>>>>
>>>> err = -EINVAL;
>>>> if (vma_hpagesize != vma_kernel_pagesize(dst_vma))
>>>> - goto out_unlock;
>>>> -
>>>> - vm_shared = dst_vma->vm_flags & VM_SHARED;
>>>> - }
>>>> + goto out_unlock_vma;
>>>>
>>>> - /*
>>>> - * If not shared, ensure the dst_vma has a anon_vma.
>>>> - */
>>>> - err = -ENOMEM;
>>>> - if (!vm_shared) {
>>>> - if (unlikely(anon_vma_prepare(dst_vma)))
>>>> + /*
>>>> + * If memory mappings are changing because of non-cooperative
>>>> + * operation (e.g. mremap) running in parallel, bail out and
>>>> + * request the user to retry later
>>>> + */
>>>> + down_read(&ctx->map_changing_lock);
>>>> + err = -EAGAIN;
>>>> + if (atomic_read(&ctx->mmap_changing))
>>>> goto out_unlock;
>>>> }
>>>>
>>>> @@ -465,7 +572,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
>>>>
>>>> if (unlikely(err == -ENOENT)) {
>>>> up_read(&ctx->map_changing_lock);
>>>> - mmap_read_unlock(dst_mm);
>>>> + uffd_mfill_unlock(dst_vma);
>>>> BUG_ON(!folio);
>>>>
>>>> err = copy_folio_from_user(folio,
>>>> @@ -474,17 +581,6 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
>>>> err = -EFAULT;
>>>> goto out;
>>>> }
>>>> - mmap_read_lock(dst_mm);
>>>> - down_read(&ctx->map_changing_lock);
>>>> - /*
>>>> - * If memory mappings are changing because of non-cooperative
>>>> - * operation (e.g. mremap) running in parallel, bail out and
>>>> - * request the user to retry later
>>>> - */
>>>> - if (atomic_read(&ctx->mmap_changing)) {
>>>> - err = -EAGAIN;
>>>> - break;
>>>> - }
>>>>
>>>> dst_vma = NULL;
>>>> goto retry;
>>>> @@ -505,7 +601,8 @@ static __always_inline ssize_t mfill_atomic_hugetlb(
>>>>
>>>> out_unlock:
>>>> up_read(&ctx->map_changing_lock);
>>>> - mmap_read_unlock(dst_mm);
>>>> +out_unlock_vma:
>>>> + uffd_mfill_unlock(dst_vma);
>>>> out:
>>>> if (folio)
>>>> folio_put(folio);
>>>> @@ -597,7 +694,15 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
>>>> copied = 0;
>>>> folio = NULL;
>>>> retry:
>>>> - mmap_read_lock(dst_mm);
>>>> + /*
>>>> + * Make sure the vma is not shared, that the dst range is
>>>> + * both valid and fully within a single existing vma.
>>>> + */
>>>> + dst_vma = uffd_mfill_lock(dst_mm, dst_start, len);
>>>> + if (IS_ERR(dst_vma)) {
>>>> + err = PTR_ERR(dst_vma);
>>>> + goto out;
>>>> + }
>>>>
>>>> /*
>>>> * If memory mappings are changing because of non-cooperative
>>>> @@ -609,15 +714,6 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
>>>> if (atomic_read(&ctx->mmap_changing))
>>>> goto out_unlock;
>>>>
>>>> - /*
>>>> - * Make sure the vma is not shared, that the dst range is
>>>> - * both valid and fully within a single existing vma.
>>>> - */
>>>> - err = -ENOENT;
>>>> - dst_vma = find_dst_vma(dst_mm, dst_start, len);
>>>> - if (!dst_vma)
>>>> - goto out_unlock;
>>>> -
>>>> err = -EINVAL;
>>>> /*
>>>> * shmem_zero_setup is invoked in mmap for MAP_ANONYMOUS|MAP_SHARED but
>>>> @@ -647,16 +743,6 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
>>>> uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE))
>>>> goto out_unlock;
>>>>
>>>> - /*
>>>> - * Ensure the dst_vma has a anon_vma or this page
>>>> - * would get a NULL anon_vma when moved in the
>>>> - * dst_vma.
>>>> - */
>>>> - err = -ENOMEM;
>>>> - if (!(dst_vma->vm_flags & VM_SHARED) &&
>>>> - unlikely(anon_vma_prepare(dst_vma)))
>>>> - goto out_unlock;
>>>> -
>>>> while (src_addr < src_start + len) {
>>>> pmd_t dst_pmdval;
>>>>
>>>> @@ -699,7 +785,7 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
>>>> void *kaddr;
>>>>
>>>> up_read(&ctx->map_changing_lock);
>>>> - mmap_read_unlock(dst_mm);
>>>> + uffd_mfill_unlock(dst_vma);
>>>> BUG_ON(!folio);
>>>>
>>>> kaddr = kmap_local_folio(folio, 0);
>>>> @@ -730,7 +816,7 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
>>>>
>>>> out_unlock:
>>>> up_read(&ctx->map_changing_lock);
>>>> - mmap_read_unlock(dst_mm);
>>>> + uffd_mfill_unlock(dst_vma);
>>>> out:
>>>> if (folio)
>>>> folio_put(folio);
>>>> @@ -1267,27 +1353,136 @@ static int validate_move_areas(struct userfaultfd_ctx *ctx,
>>>> if (!vma_is_anonymous(src_vma) || !vma_is_anonymous(dst_vma))
>>>> return -EINVAL;
>>>>
>>>> + return 0;
>>>> +}
>>>> +
>>>> +static __always_inline
>>>> +int find_vmas_mm_locked(struct mm_struct *mm,
>>>> + unsigned long dst_start,
>>>> + unsigned long src_start,
>>>> + struct vm_area_struct **dst_vmap,
>>>> + struct vm_area_struct **src_vmap)
>>>> +{
>>>> + struct vm_area_struct *vma;
>>>> +
>>>> + mmap_assert_locked(mm);
>>>> + vma = find_vma_and_prepare_anon(mm, dst_start);
>>>> + if (IS_ERR(vma))
>>>> + return PTR_ERR(vma);
>>>> +
>>>> + *dst_vmap = vma;
>>>> + /* Skip finding src_vma if src_start is in dst_vma */
>>>> + if (src_start >= vma->vm_start && src_start < vma->vm_end)
>>>> + goto out_success;
>>>> +
>>>> + vma = vma_lookup(mm, src_start);
>>>> + if (!vma)
>>>> + return -ENOENT;
>>>> +out_success:
>>>> + *src_vmap = vma;
>>>> + return 0;
>>>> +}
>>>> +
>>>> +#ifdef CONFIG_PER_VMA_LOCK
>>>> +static int uffd_move_lock(struct mm_struct *mm,
>>>> + unsigned long dst_start,
>>>> + unsigned long src_start,
>>>> + struct vm_area_struct **dst_vmap,
>>>> + struct vm_area_struct **src_vmap)
>>>> +{
>>>> + struct vm_area_struct *vma;
>>>> + int err;
>>>> +
>>>> + vma = lock_vma(mm, dst_start);
>>>> + if (IS_ERR(vma))
>>>> + return PTR_ERR(vma);
>>>> +
>>>> + *dst_vmap = vma;
>>>> /*
>>>> - * Ensure the dst_vma has a anon_vma or this page
>>>> - * would get a NULL anon_vma when moved in the
>>>> - * dst_vma.
>>>> + * Skip finding src_vma if src_start is in dst_vma. This also ensures
>>>> + * that we don't lock the same vma twice.
>>>> */
>>>> - if (unlikely(anon_vma_prepare(dst_vma)))
>>>> - return -ENOMEM;
>>>> + if (src_start >= vma->vm_start && src_start < vma->vm_end) {
>>>> + *src_vmap = vma;
>>>> + return 0;
>>>> + }
>>>>
>>>> - return 0;
>>>> + /*
>>>> + * Using lock_vma() to get src_vma can lead to following deadlock:
>>>> + *
>>>> + * Thread1 Thread2
>>>> + * ------- -------
>>>> + * vma_start_read(dst_vma)
>>>> + * mmap_write_lock(mm)
>>>> + * vma_start_write(src_vma)
>>>> + * vma_start_read(src_vma)
>>>> + * mmap_read_lock(mm)
>>>> + * vma_start_write(dst_vma)
>>>> + */
>>>> + *src_vmap = lock_vma_under_rcu(mm, src_start);
>>>> + if (likely(*src_vmap))
>>>> + return 0;
>>>> +
>>>> + /* Undo any locking and retry in mmap_lock critical section */
>>>> + vma_end_read(*dst_vmap);
>>>> +
>>>> + mmap_read_lock(mm);
>>>> + err = find_vmas_mm_locked(mm, dst_start, src_start, dst_vmap, src_vmap);
>>>> + if (!err) {
>>>> + /*
>>>> + * See comment in lock_vma() as to why not using
>>>> + * vma_start_read() here.
>>>> + */
>>>> + down_read(&(*dst_vmap)->vm_lock->lock);
>>>> + if (*dst_vmap != *src_vmap)
>>>> + down_read(&(*src_vmap)->vm_lock->lock);
>>>> + }
>>>> + mmap_read_unlock(mm);
>>>> + return err;
>>>> +}
>>>> +
>>>> +static void uffd_move_unlock(struct vm_area_struct *dst_vma,
>>>> + struct vm_area_struct *src_vma)
>>>> +{
>>>> + vma_end_read(src_vma);
>>>> + if (src_vma != dst_vma)
>>>> + vma_end_read(dst_vma);
>>>> }
>>>>
>>>> +#else
>>>> +
>>>> +static int uffd_move_lock(struct mm_struct *mm,
>>>> + unsigned long dst_start,
>>>> + unsigned long src_start,
>>>> + struct vm_area_struct **dst_vmap,
>>>> + struct vm_area_struct **src_vmap)
>>>> +{
>>>> + int err;
>>>> +
>>>> + mmap_read_lock(mm);
>>>> + err = find_vmas_mm_locked(mm, dst_start, src_start, dst_vmap, src_vmap);
>>>> + if (err)
>>>> + mmap_read_unlock(mm);
>>>> + return err;
>>>> +}
>>>> +
>>>> +static void uffd_move_unlock(struct vm_area_struct *dst_vma,
>>>> + struct vm_area_struct *src_vma)
>>>> +{
>>>> + mmap_assert_locked(src_vma->vm_mm);
>>>> + mmap_read_unlock(dst_vma->vm_mm);
>>>> +}
>>>> +#endif
>>>> +
>>>> /**
>>>> * move_pages - move arbitrary anonymous pages of an existing vma
>>>> * @ctx: pointer to the userfaultfd context
>>>> - * @mm: the address space to move pages
>>>> * @dst_start: start of the destination virtual memory range
>>>> * @src_start: start of the source virtual memory range
>>>> * @len: length of the virtual memory range
>>>> * @mode: flags from uffdio_move.mode
>>>> *
>>>> - * Must be called with mmap_lock held for read.
>>>> + * It will either use the mmap_lock in read mode or per-vma locks
>>>> *
>>>> * move_pages() remaps arbitrary anonymous pages atomically in zero
>>>> * copy. It only works on non shared anonymous pages because those can
>>>> @@ -1355,10 +1550,10 @@ static int validate_move_areas(struct userfaultfd_ctx *ctx,
>>>> * could be obtained. This is the only additional complexity added to
>>>> * the rmap code to provide this anonymous page remapping functionality.
>>>> */
>>>> -ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
>>>> - unsigned long dst_start, unsigned long src_start,
>>>> - unsigned long len, __u64 mode)
>>>> +ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start,
>>>> + unsigned long src_start, unsigned long len, __u64 mode)
>>>> {
>>>> + struct mm_struct *mm = ctx->mm;
>>>> struct vm_area_struct *src_vma, *dst_vma;
>>>> unsigned long src_addr, dst_addr;
>>>> pmd_t *src_pmd, *dst_pmd;
>>>> @@ -1376,28 +1571,34 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
>>>> WARN_ON_ONCE(dst_start + len <= dst_start))
>>>> goto out;
>>>>
>>>> + err = uffd_move_lock(mm, dst_start, src_start, &dst_vma, &src_vma);
>>>> + if (err)
>>>> + goto out;
>>>> +
>>>> + /* Re-check after taking map_changing_lock */
>>>> + err = -EAGAIN;
>>>> + down_read(&ctx->map_changing_lock);
>>>> + if (likely(atomic_read(&ctx->mmap_changing)))
>>>> + goto out_unlock;
>>>> /*
>>>> * Make sure the vma is not shared, that the src and dst remap
>>>> * ranges are both valid and fully within a single existing
>>>> * vma.
>>>> */
>>>> - src_vma = find_vma(mm, src_start);
>>>> - if (!src_vma || (src_vma->vm_flags & VM_SHARED))
>>>> - goto out;
>>>> - if (src_start < src_vma->vm_start ||
>>>> - src_start + len > src_vma->vm_end)
>>>> - goto out;
>>>> + err = -EINVAL;
>>>> + if (src_vma->vm_flags & VM_SHARED)
>>>> + goto out_unlock;
>>>> + if (src_start + len > src_vma->vm_end)
>>>> + goto out_unlock;
>>>>
>>>> - dst_vma = find_vma(mm, dst_start);
>>>> - if (!dst_vma || (dst_vma->vm_flags & VM_SHARED))
>>>> - goto out;
>>>> - if (dst_start < dst_vma->vm_start ||
>>>> - dst_start + len > dst_vma->vm_end)
>>>> - goto out;
>>>> + if (dst_vma->vm_flags & VM_SHARED)
>>>> + goto out_unlock;
>>>> + if (dst_start + len > dst_vma->vm_end)
>>>> + goto out_unlock;
>>>>
>>>> err = validate_move_areas(ctx, src_vma, dst_vma);
>>>> if (err)
>>>> - goto out;
>>>> + goto out_unlock;
>>>>
>>>> for (src_addr = src_start, dst_addr = dst_start;
>>>> src_addr < src_start + len;) {
>>>> @@ -1514,6 +1715,9 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, struct mm_struct *mm,
>>>> moved += step_size;
>>>> }
>>>>
>>>> +out_unlock:
>>>> + up_read(&ctx->map_changing_lock);
>>>> + uffd_move_unlock(dst_vma, src_vma);
>>>> out:
>>>> VM_WARN_ON(moved < 0);
>>>> VM_WARN_ON(err > 0);
>>>
>>> --
>>> To unsubscribe from this group and stop receiving emails from it, send an email to [email protected].
>>>