ceph: ceph_pagelist_append might sleep while atomic
commit 39be95e9c8c0b5668c9f8806ffe29bf9f4bc0f40 upstream.
Ceph's encode_caps_cb() worked hard to not call __page_cache_alloc()
while holding a lock, but it's spoiled because ceph_pagelist_addpage()
always calls kmap(), which might sleep. Here's the result:
[13439.295457] ceph: mds0 reconnect start
[13439.300572] BUG: sleeping function called from invalid context at include/linux/highmem.h:58
[13439.309243] in_atomic(): 1, irqs_disabled(): 0, pid: 12059, name: kworker/1:1
. . .
[13439.376225] Call Trace:
[13439.378757] [<ffffffff81076f4c>] __might_sleep+0xfc/0x110
[13439.384353] [<ffffffffa03f4ce0>] ceph_pagelist_append+0x120/0x1b0 [libceph]
[13439.391491] [<ffffffffa0448fe9>] ceph_encode_locks+0x89/0x190 [ceph]
[13439.398035] [<ffffffff814ee849>] ? _raw_spin_lock+0x49/0x50
[13439.403775] [<ffffffff811cadf5>] ? lock_flocks+0x15/0x20
[13439.409277] [<ffffffffa045e2af>] encode_caps_cb+0x41f/0x4a0 [ceph]
[13439.415622] [<ffffffff81196748>] ? igrab+0x28/0x70
[13439.420610] [<ffffffffa045e9f8>] ? iterate_session_caps+0xe8/0x250 [ceph]
[13439.427584] [<ffffffffa045ea25>] iterate_session_caps+0x115/0x250 [ceph]
[13439.434499] [<ffffffffa045de90>] ? set_request_path_attr+0x2d0/0x2d0 [ceph]
[13439.441646] [<ffffffffa0462888>] send_mds_reconnect+0x238/0x450 [ceph]
[13439.448363] [<ffffffffa0464542>] ? ceph_mdsmap_decode+0x5e2/0x770 [ceph]
[13439.455250] [<ffffffffa0462e42>] check_new_map+0x352/0x500 [ceph]
[13439.461534] [<ffffffffa04631ad>] ceph_mdsc_handle_map+0x1bd/0x260 [ceph]
[13439.468432] [<ffffffff814ebc7e>] ? mutex_unlock+0xe/0x10
[13439.473934] [<ffffffffa043c612>] extra_mon_dispatch+0x22/0x30 [ceph]
[13439.480464] [<ffffffffa03f6c2c>] dispatch+0xbc/0x110 [libceph]
[13439.486492] [<ffffffffa03eec3d>] process_message+0x1ad/0x1d0 [libceph]
[13439.493190] [<ffffffffa03f1498>] ? read_partial_message+0x3e8/0x520 [libceph]
. . .
[13439.587132] ceph: mds0 reconnect success
[13490.720032] ceph: mds0 caps stale
[13501.235257] ceph: mds0 recovery completed
[13501.300419] ceph: mds0 caps renewed
Fix it up by encoding locks into a buffer first, and when the number
of encoded locks is stable, copy that into a ceph_pagelist.
[elder@inktank.com: abbreviated the stack info a bit.]
Signed-off-by: Jim Schutt <jaschut@sandia.gov>
Reviewed-by: Alex Elder <elder@inktank.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index e9960c8..bb5fb3d 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -191,29 +191,23 @@
}
/**
- * Encode the flock and fcntl locks for the given inode into the pagelist.
- * Format is: #fcntl locks, sequential fcntl locks, #flock locks,
- * sequential flock locks.
- * Must be called with lock_flocks() already held.
- * If we encounter more of a specific lock type than expected,
- * we return the value 1.
+ * Encode the flock and fcntl locks for the given inode into the ceph_filelock
+ * array. Must be called with lock_flocks() already held.
+ * If we encounter more of a specific lock type than expected, return -ENOSPC.
*/
-int ceph_encode_locks(struct inode *inode, struct ceph_pagelist *pagelist,
- int num_fcntl_locks, int num_flock_locks)
+int ceph_encode_locks_to_buffer(struct inode *inode,
+ struct ceph_filelock *flocks,
+ int num_fcntl_locks, int num_flock_locks)
{
struct file_lock *lock;
- struct ceph_filelock cephlock;
int err = 0;
int seen_fcntl = 0;
int seen_flock = 0;
- __le32 nlocks;
+ int l = 0;
dout("encoding %d flock and %d fcntl locks", num_flock_locks,
num_fcntl_locks);
- nlocks = cpu_to_le32(num_fcntl_locks);
- err = ceph_pagelist_append(pagelist, &nlocks, sizeof(nlocks));
- if (err)
- goto fail;
+
for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
if (lock->fl_flags & FL_POSIX) {
++seen_fcntl;
@@ -221,20 +215,12 @@
err = -ENOSPC;
goto fail;
}
- err = lock_to_ceph_filelock(lock, &cephlock);
+ err = lock_to_ceph_filelock(lock, &flocks[l]);
if (err)
goto fail;
- err = ceph_pagelist_append(pagelist, &cephlock,
- sizeof(struct ceph_filelock));
+ ++l;
}
- if (err)
- goto fail;
}
-
- nlocks = cpu_to_le32(num_flock_locks);
- err = ceph_pagelist_append(pagelist, &nlocks, sizeof(nlocks));
- if (err)
- goto fail;
for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
if (lock->fl_flags & FL_FLOCK) {
++seen_flock;
@@ -242,19 +228,51 @@
err = -ENOSPC;
goto fail;
}
- err = lock_to_ceph_filelock(lock, &cephlock);
+ err = lock_to_ceph_filelock(lock, &flocks[l]);
if (err)
goto fail;
- err = ceph_pagelist_append(pagelist, &cephlock,
- sizeof(struct ceph_filelock));
+ ++l;
}
- if (err)
- goto fail;
}
fail:
return err;
}
+/**
+ * Copy the encoded flock and fcntl locks into the pagelist.
+ * Format is: #fcntl locks, sequential fcntl locks, #flock locks,
+ * sequential flock locks.
+ * Returns zero on success.
+ */
+int ceph_locks_to_pagelist(struct ceph_filelock *flocks,
+ struct ceph_pagelist *pagelist,
+ int num_fcntl_locks, int num_flock_locks)
+{
+ int err = 0;
+ __le32 nlocks;
+
+ nlocks = cpu_to_le32(num_fcntl_locks);
+ err = ceph_pagelist_append(pagelist, &nlocks, sizeof(nlocks));
+ if (err)
+ goto out_fail;
+
+ err = ceph_pagelist_append(pagelist, flocks,
+ num_fcntl_locks * sizeof(*flocks));
+ if (err)
+ goto out_fail;
+
+ nlocks = cpu_to_le32(num_flock_locks);
+ err = ceph_pagelist_append(pagelist, &nlocks, sizeof(nlocks));
+ if (err)
+ goto out_fail;
+
+ err = ceph_pagelist_append(pagelist,
+ &flocks[num_fcntl_locks],
+ num_flock_locks * sizeof(*flocks));
+out_fail:
+ return err;
+}
+
/*
* Given a pointer to a lock, convert it to a ceph filelock
*/