Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index ec57bbb..aef0da5 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -56,7 +56,7 @@ struct userfaultfd_ctx {
/* waitqueue head for events */
wait_queue_head_t event_wqh;
/* a refile sequence protected by fault_pending_wqh lock */
- struct seqcount refile_seq;
+ seqcount_spinlock_t refile_seq;
/* pseudo fd refcounting */
refcount_t refcount;
/* userfaultfd syscall flags */
@@ -235,7 +235,7 @@ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
pte_t *ptep, pte;
bool ret = true;
- VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
+ mmap_assert_locked(mm);
ptep = huge_pte_offset(mm, address, vma_mmu_pagesize(vma));
@@ -287,7 +287,7 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
pte_t *pte;
bool ret = true;
- VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
+ mmap_assert_locked(mm);
pgd = pgd_offset(mm, address);
if (!pgd_present(*pgd))
@@ -315,8 +315,11 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
if (!pmd_present(_pmd))
goto out;
- if (pmd_trans_huge(_pmd))
+ if (pmd_trans_huge(_pmd)) {
+ if (!pmd_write(_pmd) && (reason & VM_UFFD_WP))
+ ret = true;
goto out;
+ }
/*
* the pmd is stable (as in !pmd_trans_unstable) so we can re-read it
@@ -329,25 +332,38 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
*/
if (pte_none(*pte))
ret = true;
+ if (!pte_write(*pte) && (reason & VM_UFFD_WP))
+ ret = true;
pte_unmap(pte);
out:
return ret;
}
+static inline long userfaultfd_get_blocking_state(unsigned int flags)
+{
+ if (flags & FAULT_FLAG_INTERRUPTIBLE)
+ return TASK_INTERRUPTIBLE;
+
+ if (flags & FAULT_FLAG_KILLABLE)
+ return TASK_KILLABLE;
+
+ return TASK_UNINTERRUPTIBLE;
+}
+
/*
* The locking rules involved in returning VM_FAULT_RETRY depending on
* FAULT_FLAG_ALLOW_RETRY, FAULT_FLAG_RETRY_NOWAIT and
* FAULT_FLAG_KILLABLE are not straightforward. The "Caution"
* recommendation in __lock_page_or_retry is not an understatement.
*
- * If FAULT_FLAG_ALLOW_RETRY is set, the mmap_sem must be released
+ * If FAULT_FLAG_ALLOW_RETRY is set, the mmap_lock must be released
* before returning VM_FAULT_RETRY only if FAULT_FLAG_RETRY_NOWAIT is
* not set.
*
* If FAULT_FLAG_ALLOW_RETRY is set but FAULT_FLAG_KILLABLE is not
* set, VM_FAULT_RETRY can still be returned if and only if there are
- * fatal_signal_pending()s, and the mmap_sem must be released before
+ * fatal_signal_pending()s, and the mmap_lock must be released before
* returning it.
*/
vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
@@ -356,7 +372,7 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
struct userfaultfd_ctx *ctx;
struct userfaultfd_wait_queue uwq;
vm_fault_t ret = VM_FAULT_SIGBUS;
- bool must_wait, return_to_userland;
+ bool must_wait;
long blocking_state;
/*
@@ -368,16 +384,16 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
* FOLL_DUMP case, anon memory also checks for FOLL_DUMP with
* the no_page_table() helper in follow_page_mask(), but the
* shmem_vm_ops->fault method is invoked even during
- * coredumping without mmap_sem and it ends up here.
+ * coredumping without mmap_lock and it ends up here.
*/
if (current->flags & (PF_EXITING|PF_DUMPCORE))
goto out;
/*
- * Coredumping runs without mmap_sem so we can only check that
- * the mmap_sem is held, if PF_DUMPCORE was not set.
+ * Coredumping runs without mmap_lock so we can only check that
+ * the mmap_lock is held, if PF_DUMPCORE was not set.
*/
- WARN_ON_ONCE(!rwsem_is_locked(&mm->mmap_sem));
+ mmap_assert_locked(mm);
ctx = vmf->vma->vm_userfaultfd_ctx.ctx;
if (!ctx)
@@ -394,7 +410,7 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
/*
* If it's already released don't get it. This avoids to loop
* in __get_user_pages if userfaultfd_release waits on the
- * caller of handle_userfault to release the mmap_sem.
+ * caller of handle_userfault to release the mmap_lock.
*/
if (unlikely(READ_ONCE(ctx->released))) {
/*
@@ -453,7 +469,7 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
goto out;
- /* take the reference before dropping the mmap_sem */
+ /* take the reference before dropping the mmap_lock */
userfaultfd_ctx_get(ctx);
init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function);
@@ -463,11 +479,7 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
uwq.ctx = ctx;
uwq.waken = false;
- return_to_userland =
- (vmf->flags & (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE)) ==
- (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE);
- blocking_state = return_to_userland ? TASK_INTERRUPTIBLE :
- TASK_KILLABLE;
+ blocking_state = userfaultfd_get_blocking_state(vmf->flags);
spin_lock_irq(&ctx->fault_pending_wqh.lock);
/*
@@ -490,65 +502,15 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
must_wait = userfaultfd_huge_must_wait(ctx, vmf->vma,
vmf->address,
vmf->flags, reason);
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
- if (likely(must_wait && !READ_ONCE(ctx->released) &&
- (return_to_userland ? !signal_pending(current) :
- !fatal_signal_pending(current)))) {
+ if (likely(must_wait && !READ_ONCE(ctx->released))) {
wake_up_poll(&ctx->fd_wqh, EPOLLIN);
schedule();
- ret |= VM_FAULT_MAJOR;
-
- /*
- * False wakeups can orginate even from rwsem before
- * up_read() however userfaults will wait either for a
- * targeted wakeup on the specific uwq waitqueue from
- * wake_userfault() or for signals or for uffd
- * release.
- */
- while (!READ_ONCE(uwq.waken)) {
- /*
- * This needs the full smp_store_mb()
- * guarantee as the state write must be
- * visible to other CPUs before reading
- * uwq.waken from other CPUs.
- */
- set_current_state(blocking_state);
- if (READ_ONCE(uwq.waken) ||
- READ_ONCE(ctx->released) ||
- (return_to_userland ? signal_pending(current) :
- fatal_signal_pending(current)))
- break;
- schedule();
- }
}
__set_current_state(TASK_RUNNING);
- if (return_to_userland) {
- if (signal_pending(current) &&
- !fatal_signal_pending(current)) {
- /*
- * If we got a SIGSTOP or SIGCONT and this is
- * a normal userland page fault, just let
- * userland return so the signal will be
- * handled and gdb debugging works. The page
- * fault code immediately after we return from
- * this function is going to release the
- * mmap_sem and it's not depending on it
- * (unlike gup would if we were not to return
- * VM_FAULT_RETRY).
- *
- * If a fatal signal is pending we still take
- * the streamlined VM_FAULT_RETRY failure path
- * and there's no need to retake the mmap_sem
- * in such case.
- */
- down_read(&mm->mmap_sem);
- ret = VM_FAULT_NOPAGE;
- }
- }
-
/*
* Here we race with the list_del; list_add in
* userfaultfd_ctx_read(), however because we don't ever run
@@ -639,15 +601,13 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
struct mm_struct *mm = release_new_ctx->mm;
/* the various vma->vm_userfaultfd_ctx still points to it */
- down_write(&mm->mmap_sem);
- /* no task can run (and in turn coredump) yet */
- VM_WARN_ON(!mmget_still_valid(mm));
+ mmap_write_lock(mm);
for (vma = mm->mmap; vma; vma = vma->vm_next)
if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
}
- up_write(&mm->mmap_sem);
+ mmap_write_unlock(mm);
userfaultfd_ctx_put(release_new_ctx);
}
@@ -800,7 +760,7 @@ bool userfaultfd_remove(struct vm_area_struct *vma,
userfaultfd_ctx_get(ctx);
WRITE_ONCE(ctx->mmap_changing, true);
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
msg_init(&ewq.msg);
@@ -880,7 +840,6 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
/* len == 0 means wake all */
struct userfaultfd_wake_range range = { .len = 0, };
unsigned long new_flags;
- bool still_valid;
WRITE_ONCE(ctx->released, true);
@@ -891,12 +850,11 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
* Flush page faults out of all CPUs. NOTE: all page faults
* must be retried without returning VM_FAULT_SIGBUS if
* userfaultfd_ctx_get() succeeds but vma->vma_userfault_ctx
- * changes while handle_userfault released the mmap_sem. So
+ * changes while handle_userfault released the mmap_lock. So
* it's critical that released is set to true (above), before
- * taking the mmap_sem for writing.
+ * taking the mmap_lock for writing.
*/
- down_write(&mm->mmap_sem);
- still_valid = mmget_still_valid(mm);
+ mmap_write_lock(mm);
prev = NULL;
for (vma = mm->mmap; vma; vma = vma->vm_next) {
cond_resched();
@@ -907,21 +865,19 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
continue;
}
new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP);
- if (still_valid) {
- prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
- new_flags, vma->anon_vma,
- vma->vm_file, vma->vm_pgoff,
- vma_policy(vma),
- NULL_VM_UFFD_CTX);
- if (prev)
- vma = prev;
- else
- prev = vma;
- }
+ prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
+ new_flags, vma->anon_vma,
+ vma->vm_file, vma->vm_pgoff,
+ vma_policy(vma),
+ NULL_VM_UFFD_CTX);
+ if (prev)
+ vma = prev;
+ else
+ prev = vma;
vma->vm_flags = new_flags;
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
}
- up_write(&mm->mmap_sem);
+ mmap_write_unlock(mm);
mmput(mm);
wakeup:
/*
@@ -1244,7 +1200,7 @@ static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx,
/*
* To be sure waitqueue_active() is not reordered by the CPU
* before the pagetable update, use an explicit SMP memory
- * barrier here. PT lock release or up_read(mmap_sem) still
+ * barrier here. PT lock release or mmap_read_unlock(mm) still
* have release semantics that can allow the
* waitqueue_active() to be reordered before the pte update.
*/
@@ -1286,10 +1242,13 @@ static __always_inline int validate_range(struct mm_struct *mm,
return 0;
}
-static inline bool vma_can_userfault(struct vm_area_struct *vma)
+static inline bool vma_can_userfault(struct vm_area_struct *vma,
+ unsigned long vm_flags)
{
- return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) ||
- vma_is_shmem(vma);
+ /* FIXME: add WP support to hugetlbfs and shmem */
+ return vma_is_anonymous(vma) ||
+ ((is_vm_hugetlb_page(vma) || vma_is_shmem(vma)) &&
+ !(vm_flags & VM_UFFD_WP));
}
static int userfaultfd_register(struct userfaultfd_ctx *ctx,
@@ -1321,15 +1280,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
vm_flags = 0;
if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MISSING)
vm_flags |= VM_UFFD_MISSING;
- if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP) {
+ if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP)
vm_flags |= VM_UFFD_WP;
- /*
- * FIXME: remove the below error constraint by
- * implementing the wprotect tracking mode.
- */
- ret = -EINVAL;
- goto out;
- }
ret = validate_range(mm, uffdio_register.range.start,
uffdio_register.range.len);
@@ -1343,9 +1295,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
if (!mmget_not_zero(mm))
goto out;
- down_write(&mm->mmap_sem);
- if (!mmget_still_valid(mm))
- goto out_unlock;
+ mmap_write_lock(mm);
vma = find_vma_prev(mm, start, &prev);
if (!vma)
goto out_unlock;
@@ -1379,7 +1329,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
/* check not compatible vmas */
ret = -EINVAL;
- if (!vma_can_userfault(cur))
+ if (!vma_can_userfault(cur, vm_flags))
goto out_unlock;
/*
@@ -1407,6 +1357,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
if (end & (vma_hpagesize - 1))
goto out_unlock;
}
+ if ((vm_flags & VM_UFFD_WP) && !(cur->vm_flags & VM_MAYWRITE))
+ goto out_unlock;
/*
* Check that this vma isn't already owned by a
@@ -1436,7 +1388,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
do {
cond_resched();
- BUG_ON(!vma_can_userfault(vma));
+ BUG_ON(!vma_can_userfault(vma, vm_flags));
BUG_ON(vma->vm_userfaultfd_ctx.ctx &&
vma->vm_userfaultfd_ctx.ctx != ctx);
WARN_ON(!(vma->vm_flags & VM_MAYWRITE));
@@ -1453,7 +1405,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
start = vma->vm_start;
vma_end = min(end, vma->vm_end);
- new_flags = (vma->vm_flags & ~vm_flags) | vm_flags;
+ new_flags = (vma->vm_flags &
+ ~(VM_UFFD_MISSING|VM_UFFD_WP)) | vm_flags;
prev = vma_merge(mm, prev, start, vma_end, new_flags,
vma->anon_vma, vma->vm_file, vma->vm_pgoff,
vma_policy(vma),
@@ -1487,17 +1440,27 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
vma = vma->vm_next;
} while (vma && vma->vm_start < end);
out_unlock:
- up_write(&mm->mmap_sem);
+ mmap_write_unlock(mm);
mmput(mm);
if (!ret) {
+ __u64 ioctls_out;
+
+ ioctls_out = basic_ioctls ? UFFD_API_RANGE_IOCTLS_BASIC :
+ UFFD_API_RANGE_IOCTLS;
+
+ /*
+ * Declare the WP ioctl only if the WP mode is
+ * specified and all checks passed with the range
+ */
+ if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_WP))
+ ioctls_out &= ~((__u64)1 << _UFFDIO_WRITEPROTECT);
+
/*
* Now that we scanned all vmas we can already tell
* userland which ioctls methods are guaranteed to
* succeed on this range.
*/
- if (put_user(basic_ioctls ? UFFD_API_RANGE_IOCTLS_BASIC :
- UFFD_API_RANGE_IOCTLS,
- &user_uffdio_register->ioctls))
+ if (put_user(ioctls_out, &user_uffdio_register->ioctls))
ret = -EFAULT;
}
out:
@@ -1532,9 +1495,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
if (!mmget_not_zero(mm))
goto out;
- down_write(&mm->mmap_sem);
- if (!mmget_still_valid(mm))
- goto out_unlock;
+ mmap_write_lock(mm);
vma = find_vma_prev(mm, start, &prev);
if (!vma)
goto out_unlock;
@@ -1573,7 +1534,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
* provides for more strict behavior to notice
* unregistration errors.
*/
- if (!vma_can_userfault(cur))
+ if (!vma_can_userfault(cur, cur->vm_flags))
goto out_unlock;
found = true;
@@ -1587,7 +1548,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
do {
cond_resched();
- BUG_ON(!vma_can_userfault(vma));
+ BUG_ON(!vma_can_userfault(vma, vma->vm_flags));
/*
* Nothing to do: this vma is already registered into this
@@ -1649,7 +1610,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
vma = vma->vm_next;
} while (vma && vma->vm_start < end);
out_unlock:
- up_write(&mm->mmap_sem);
+ mmap_write_unlock(mm);
mmput(mm);
out:
return ret;
@@ -1722,11 +1683,12 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
ret = -EINVAL;
if (uffdio_copy.src + uffdio_copy.len <= uffdio_copy.src)
goto out;
- if (uffdio_copy.mode & ~UFFDIO_COPY_MODE_DONTWAKE)
+ if (uffdio_copy.mode & ~(UFFDIO_COPY_MODE_DONTWAKE|UFFDIO_COPY_MODE_WP))
goto out;
if (mmget_not_zero(ctx->mm)) {
ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src,
- uffdio_copy.len, &ctx->mmap_changing);
+ uffdio_copy.len, &ctx->mmap_changing,
+ uffdio_copy.mode);
mmput(ctx->mm);
} else {
return -ESRCH;
@@ -1799,6 +1761,59 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
return ret;
}
+static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
+ unsigned long arg)
+{
+ int ret;
+ struct uffdio_writeprotect uffdio_wp;
+ struct uffdio_writeprotect __user *user_uffdio_wp;
+ struct userfaultfd_wake_range range;
+ bool mode_wp, mode_dontwake;
+
+ if (READ_ONCE(ctx->mmap_changing))
+ return -EAGAIN;
+
+ user_uffdio_wp = (struct uffdio_writeprotect __user *) arg;
+
+ if (copy_from_user(&uffdio_wp, user_uffdio_wp,
+ sizeof(struct uffdio_writeprotect)))
+ return -EFAULT;
+
+ ret = validate_range(ctx->mm, uffdio_wp.range.start,
+ uffdio_wp.range.len);
+ if (ret)
+ return ret;
+
+ if (uffdio_wp.mode & ~(UFFDIO_WRITEPROTECT_MODE_DONTWAKE |
+ UFFDIO_WRITEPROTECT_MODE_WP))
+ return -EINVAL;
+
+ mode_wp = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_WP;
+ mode_dontwake = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_DONTWAKE;
+
+ if (mode_wp && mode_dontwake)
+ 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);
+ mmput(ctx->mm);
+ } else {
+ return -ESRCH;
+ }
+
+ if (ret)
+ return ret;
+
+ if (!mode_wp && !mode_dontwake) {
+ range.start = uffdio_wp.range.start;
+ range.len = uffdio_wp.range.len;
+ wake_userfault(ctx, &range);
+ }
+ return ret;
+}
+
static inline unsigned int uffd_ctx_features(__u64 user_features)
{
/*
@@ -1883,6 +1898,9 @@ static long userfaultfd_ioctl(struct file *file, unsigned cmd,
case UFFDIO_ZEROPAGE:
ret = userfaultfd_zeropage(ctx, arg);
break;
+ case UFFDIO_WRITEPROTECT:
+ ret = userfaultfd_writeprotect(ctx, arg);
+ break;
}
return ret;
}
@@ -1923,7 +1941,7 @@ static const struct file_operations userfaultfd_fops = {
.poll = userfaultfd_poll,
.read = userfaultfd_read,
.unlocked_ioctl = userfaultfd_ioctl,
- .compat_ioctl = userfaultfd_ioctl,
+ .compat_ioctl = compat_ptr_ioctl,
.llseek = noop_llseek,
};
@@ -1935,7 +1953,7 @@ static void init_once_userfaultfd_ctx(void *mem)
init_waitqueue_head(&ctx->fault_wqh);
init_waitqueue_head(&ctx->event_wqh);
init_waitqueue_head(&ctx->fd_wqh);
- seqcount_init(&ctx->refile_seq);
+ seqcount_spinlock_init(&ctx->refile_seq, &ctx->fault_pending_wqh.lock);
}
SYSCALL_DEFINE1(userfaultfd, int, flags)