userfaultfd: disable irqs when taking the waitqueue lock

userfaultfd contains howe-grown locking of the waitqueue lock, and does
not disable interrupts.  This relies on the fact that no one else takes it
from interrupt context and violates an invariat of the normal waitqueue
locking scheme.  With aio poll it is easy to trigger other locks that
disable interrupts (or are called from interrupt context).

Link: http://lkml.kernel.org/r/20181018154101.18750-1-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: <stable@vger.kernel.org>	[4.19.x]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index bfa0ec6..356d2b8 100644 (file)
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1026,7 +1026,7 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
        struct userfaultfd_ctx *fork_nctx = NULL;
 
        /* always take the fd_wqh lock before the fault_pending_wqh lock */
-       spin_lock(&ctx->fd_wqh.lock);
+       spin_lock_irq(&ctx->fd_wqh.lock);
        __add_wait_queue(&ctx->fd_wqh, &wait);
        for (;;) {
                set_current_state(TASK_INTERRUPTIBLE);
@@ -1112,13 +1112,13 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
                        ret = -EAGAIN;
                        break;
                }
-               spin_unlock(&ctx->fd_wqh.lock);
+               spin_unlock_irq(&ctx->fd_wqh.lock);
                schedule();
-               spin_lock(&ctx->fd_wqh.lock);
+               spin_lock_irq(&ctx->fd_wqh.lock);
        }
        __remove_wait_queue(&ctx->fd_wqh, &wait);
        __set_current_state(TASK_RUNNING);
-       spin_unlock(&ctx->fd_wqh.lock);
+       spin_unlock_irq(&ctx->fd_wqh.lock);
 
        if (!ret && msg->event == UFFD_EVENT_FORK) {
                ret = resolve_userfault_fork(ctx, fork_nctx, msg);