fuse: Dont call set_page_dirty_lock() for ITER_BVEC pages for async_dio

Commit 8fba54aebbdf ("fuse: direct-io: don't dirty ITER_BVEC pages") fixes
the ITER_BVEC page deadlock for direct io in fuse by checking in
fuse_direct_io(), whether the page is a bvec page or not, before locking
it.  However, this check is missed when the "async_dio" mount option is
enabled.  In this case, set_page_dirty_lock() is called from the req->end
callback in request_end(), when the fuse thread is returning from userspace
to respond to the read request.  This will cause the same deadlock because
the bvec condition is not checked in this path.

Here is the stack of the deadlocked thread, while returning from userspace:

[13706.656686] INFO: task glusterfs:3006 blocked for more than 120 seconds.
[13706.657808] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables
this message.
[13706.658788] glusterfs       D ffffffff816c80f0     0  3006      1
0x00000080
[13706.658797]  ffff8800d6713a58 0000000000000086 ffff8800d9ad7000
ffff8800d9ad5400
[13706.658799]  ffff88011ffd5cc0 ffff8800d6710008 ffff88011fd176c0
7fffffffffffffff
[13706.658801]  0000000000000002 ffffffff816c80f0 ffff8800d6713a78
ffffffff816c790e
[13706.658803] Call Trace:
[13706.658809]  [<ffffffff816c80f0>] ? bit_wait_io_timeout+0x80/0x80
[13706.658811]  [<ffffffff816c790e>] schedule+0x3e/0x90
[13706.658813]  [<ffffffff816ca7e5>] schedule_timeout+0x1b5/0x210
[13706.658816]  [<ffffffff81073ffb>] ? gup_pud_range+0x1db/0x1f0
[13706.658817]  [<ffffffff810668fe>] ? kvm_clock_read+0x1e/0x20
[13706.658819]  [<ffffffff81066909>] ? kvm_clock_get_cycles+0x9/0x10
[13706.658822]  [<ffffffff810f5792>] ? ktime_get+0x52/0xc0
[13706.658824]  [<ffffffff816c6f04>] io_schedule_timeout+0xa4/0x110
[13706.658826]  [<ffffffff816c8126>] bit_wait_io+0x36/0x50
[13706.658828]  [<ffffffff816c7d06>] __wait_on_bit_lock+0x76/0xb0
[13706.658831]  [<ffffffffa0545636>] ? lock_request+0x46/0x70 [fuse]
[13706.658834]  [<ffffffff8118800a>] __lock_page+0xaa/0xb0
[13706.658836]  [<ffffffff810c8500>] ? wake_atomic_t_function+0x40/0x40
[13706.658838]  [<ffffffff81194d08>] set_page_dirty_lock+0x58/0x60
[13706.658841]  [<ffffffffa054d968>] fuse_release_user_pages+0x58/0x70 [fuse]
[13706.658844]  [<ffffffffa0551430>] ? fuse_aio_complete+0x190/0x190 [fuse]
[13706.658847]  [<ffffffffa0551459>] fuse_aio_complete_req+0x29/0x90 [fuse]
[13706.658849]  [<ffffffffa05471e9>] request_end+0xd9/0x190 [fuse]
[13706.658852]  [<ffffffffa0549126>] fuse_dev_do_write+0x336/0x490 [fuse]
[13706.658854]  [<ffffffffa054963e>] fuse_dev_write+0x6e/0xa0 [fuse]
[13706.658857]  [<ffffffff812a9ef3>] ? security_file_permission+0x23/0x90
[13706.658859]  [<ffffffff81205300>] do_iter_readv_writev+0x60/0x90
[13706.658862]  [<ffffffffa05495d0>] ? fuse_dev_splice_write+0x350/0x350
[fuse]
[13706.658863]  [<ffffffff812062a1>] do_readv_writev+0x171/0x1f0
[13706.658866]  [<ffffffff810b3d00>] ? try_to_wake_up+0x210/0x210
[13706.658868]  [<ffffffff81206361>] vfs_writev+0x41/0x50
[13706.658870]  [<ffffffff81206496>] SyS_writev+0x56/0xf0
[13706.658872]  [<ffffffff810257a1>] ? syscall_trace_leave+0xf1/0x160
[13706.658874]  [<ffffffff816cbb2e>] system_call_fastpath+0x12/0x71

Fix this by making should_dirty a fuse_io_priv parameter that can be
checked in fuse_aio_complete_req().

Reported-by: Tiger Yang <tiger.yang@oracle.com>
Signed-off-by: Ashish Samant <ashish.samant@oracle.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 76eac2a554c45cbc87906974b8dd8774c99ea63e..810ed4f99e385416c269ba2965b9948a520f1ad6 100644 (file)
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -609,7 +609,7 @@ static void fuse_aio_complete_req(struct fuse_conn *fc, struct fuse_req *req)
        struct fuse_io_priv *io = req->io;
        ssize_t pos = -1;
 
-       fuse_release_user_pages(req, !io->write);
+       fuse_release_user_pages(req, io->should_dirty);
 
        if (io->write) {
                if (req->misc.write.in.size != req->misc.write.out.size)
@@ -1316,7 +1316,6 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
                       loff_t *ppos, int flags)
 {
        int write = flags & FUSE_DIO_WRITE;
-       bool should_dirty = !write && iter_is_iovec(iter);
        int cuse = flags & FUSE_DIO_CUSE;
        struct file *file = io->file;
        struct inode *inode = file->f_mapping->host;
@@ -1346,6 +1345,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
                        inode_unlock(inode);
        }
 
+       io->should_dirty = !write && iter_is_iovec(iter);
        while (count) {
                size_t nres;
                fl_owner_t owner = current->files;
@@ -1360,7 +1360,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
                        nres = fuse_send_read(req, io, pos, nbytes, owner);
 
                if (!io->async)
-                       fuse_release_user_pages(req, should_dirty);
+                       fuse_release_user_pages(req, io->should_dirty);
                if (req->out.h.error) {
                        err = req->out.h.error;
                        break;

diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 1bd7ffdad593977013c1ddd233b2a91093471471..bd4d2a3e1ec1b8cc0af29bcb8c26f13d82708804 100644 (file)
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -249,6 +249,7 @@ struct fuse_io_priv {
        size_t size;
        __u64 offset;
        bool write;
+       bool should_dirty;
        int err;
        struct kiocb *iocb;
        struct file *file;