linux/fs/btrfs/tree-defrag.c

143 lines
3.6 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2007 Oracle. All rights reserved.
*/
#include <linux/sched.h>
#include "ctree.h"
#include "disk-io.h"
#include "print-tree.h"
#include "transaction.h"
#include "locking.h"
/*
* Defrag all the leaves in a given btree.
* Read all the leaves and try to get key order to
* better reflect disk order
*/
int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
struct btrfs_path *path = NULL;
struct btrfs_key key;
int ret = 0;
int wret;
int level;
int next_key_ret = 0;
u64 last_ret = 0;
if (root->fs_info->extent_root == root) {
/*
* there's recursion here right now in the tree locking,
* we can't defrag the extent root without deadlock
*/
goto out;
}
if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state))
goto out;
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
level = btrfs_header_level(root->node);
if (level == 0)
goto out;
if (root->defrag_progress.objectid == 0) {
struct extent_buffer *root_node;
u32 nritems;
root_node = btrfs_lock_root_node(root);
Btrfs: Change btree locking to use explicit blocking points Most of the btrfs metadata operations can be protected by a spinlock, but some operations still need to schedule. So far, btrfs has been using a mutex along with a trylock loop, most of the time it is able to avoid going for the full mutex, so the trylock loop is a big performance gain. This commit is step one for getting rid of the blocking locks entirely. btrfs_tree_lock takes a spinlock, and the code explicitly switches to a blocking lock when it starts an operation that can schedule. We'll be able get rid of the blocking locks in smaller pieces over time. Tracing allows us to find the most common cause of blocking, so we can start with the hot spots first. The basic idea is: btrfs_tree_lock() returns with the spin lock held btrfs_set_lock_blocking() sets the EXTENT_BUFFER_BLOCKING bit in the extent buffer flags, and then drops the spin lock. The buffer is still considered locked by all of the btrfs code. If btrfs_tree_lock gets the spinlock but finds the blocking bit set, it drops the spin lock and waits on a wait queue for the blocking bit to go away. Much of the code that needs to set the blocking bit finishes without actually blocking a good percentage of the time. So, an adaptive spin is still used against the blocking bit to avoid very high context switch rates. btrfs_clear_lock_blocking() clears the blocking bit and returns with the spinlock held again. btrfs_tree_unlock() can be called on either blocking or spinning locks, it does the right thing based on the blocking bit. ctree.c has a helper function to set/clear all the locked buffers in a path as blocking. Signed-off-by: Chris Mason <chris.mason@oracle.com>
2009-02-04 22:25:08 +08:00
btrfs_set_lock_blocking(root_node);
nritems = btrfs_header_nritems(root_node);
root->defrag_max.objectid = 0;
/* from above we know this is not a leaf */
btrfs_node_key_to_cpu(root_node, &root->defrag_max,
nritems - 1);
btrfs_tree_unlock(root_node);
free_extent_buffer(root_node);
memset(&key, 0, sizeof(key));
} else {
memcpy(&key, &root->defrag_progress, sizeof(key));
}
path->keep_locks = 1;
ret = btrfs_search_forward(root, &key, path, BTRFS_OLDEST_GENERATION);
if (ret < 0)
goto out;
if (ret > 0) {
ret = 0;
goto out;
}
btrfs_release_path(path);
Btrfs: fix locking bugs when defragging leaves When running fstests btrfs/070, with a higher number of fsstress operations, I ran frequently into two different locking bugs when defragging directories. The first bug produced the following traces: [133860.229792] ------------[ cut here ]------------ [133860.251062] WARNING: CPU: 2 PID: 26057 at fs/btrfs/locking.c:46 btrfs_set_lock_blocking_rw+0x57/0xbd [btrfs]() [133860.253576] Modules linked in: btrfs crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc loop fuse parport_pc i2c_piix4 psmouse parport [133860.282566] CPU: 2 PID: 26057 Comm: btrfs Tainted: G W 4.3.0-rc5-btrfs-next-17+ #1 [133860.284393] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014 [133860.286827] 0000000000000000 ffff880207697b78 ffffffff812566f4 0000000000000000 [133860.288341] ffff880207697bb0 ffffffff8104d0a6 ffffffffa052d4c1 ffff880178f60e00 [133860.294219] ffff880178f60e00 0000000000000000 00000000000000f6 ffff880207697bc0 [133860.295831] Call Trace: [133860.306518] [<ffffffff812566f4>] dump_stack+0x4e/0x79 [133860.307473] [<ffffffff8104d0a6>] warn_slowpath_common+0x9f/0xb8 [133860.308619] [<ffffffffa052d4c1>] ? btrfs_set_lock_blocking_rw+0x57/0xbd [btrfs] [133860.310068] [<ffffffff8104d172>] warn_slowpath_null+0x1a/0x1c [133860.312552] [<ffffffffa052d4c1>] btrfs_set_lock_blocking_rw+0x57/0xbd [btrfs] [133860.314630] [<ffffffffa04d5787>] btrfs_set_lock_blocking+0xe/0x10 [btrfs] [133860.323596] [<ffffffffa04d99cb>] btrfs_realloc_node+0xb3/0x341 [btrfs] [133860.325233] [<ffffffffa050e396>] btrfs_defrag_leaves+0x239/0x2fa [btrfs] [133860.332427] [<ffffffffa04fc2ce>] btrfs_defrag_root+0x63/0xca [btrfs] [133860.337259] [<ffffffffa052a34e>] btrfs_ioctl_defrag+0x78/0x14e [btrfs] [133860.340147] [<ffffffffa052b00b>] btrfs_ioctl+0x746/0x24c6 [btrfs] [133860.344833] [<ffffffff81087481>] ? arch_local_irq_save+0x9/0xc [133860.346343] [<ffffffff8113ad61>] ? __might_fault+0x4c/0xa7 [133860.353248] [<ffffffff8113ad61>] ? __might_fault+0x4c/0xa7 [133860.354242] [<ffffffff8113adba>] ? __might_fault+0xa5/0xa7 [133860.355232] [<ffffffff81171139>] ? cp_new_stat+0x15d/0x174 [133860.356237] [<ffffffff8117c610>] do_vfs_ioctl+0x427/0x4e6 [133860.358587] [<ffffffff81171175>] ? SYSC_newfstat+0x25/0x2e [133860.360195] [<ffffffff8118574d>] ? __fget_light+0x4d/0x71 [133860.361380] [<ffffffff8117c726>] SyS_ioctl+0x57/0x79 [133860.363578] [<ffffffff8147cd97>] entry_SYSCALL_64_fastpath+0x12/0x6f [133860.366217] ---[ end trace 2cadb2f653437e49 ]--- [133860.367399] ------------[ cut here ]------------ [133860.368162] kernel BUG at fs/btrfs/locking.c:307! [133860.369430] invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC [133860.370205] Modules linked in: btrfs crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc loop fuse parport_pc i2c_piix4 psmouse parport [133860.370205] CPU: 2 PID: 26057 Comm: btrfs Tainted: G W 4.3.0-rc5-btrfs-next-17+ #1 [133860.370205] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014 [133860.370205] task: ffff8800aec6db40 ti: ffff880207694000 task.ti: ffff880207694000 [133860.370205] RIP: 0010:[<ffffffffa052d466>] [<ffffffffa052d466>] btrfs_assert_tree_locked+0x10/0x14 [btrfs] [133860.370205] RSP: 0018:ffff880207697bc0 EFLAGS: 00010246 [133860.370205] RAX: 0000000000000000 RBX: ffff880178f60e00 RCX: 0000000000000000 [133860.370205] RDX: ffff88023ec4fb50 RSI: 00000000ffffffff RDI: ffff880178f60e00 [133860.370205] RBP: ffff880207697bc0 R08: 0000000000000001 R09: 0000000000000000 [133860.370205] R10: 0000160000000000 R11: ffffffff81651000 R12: ffff880178f60e00 [133860.370205] R13: 0000000000000000 R14: 00000000000000f6 R15: ffff8801ff409000 [133860.370205] FS: 00007f763efd48c0(0000) GS:ffff88023ec40000(0000) knlGS:0000000000000000 [133860.370205] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [133860.370205] CR2: 0000000002158048 CR3: 000000003fd6c000 CR4: 00000000000006e0 [133860.370205] Stack: [133860.370205] ffff880207697bd8 ffffffffa052d4d0 0000000000000000 ffff880207697be8 [133860.370205] ffffffffa04d5787 ffff880207697c80 ffffffffa04d99cb ffff8801ff409590 [133860.370205] ffff880207697ca8 000000f507697c80 ffff880183c11bb8 0000000000000000 [133860.370205] Call Trace: [133860.370205] [<ffffffffa052d4d0>] btrfs_set_lock_blocking_rw+0x66/0xbd [btrfs] [133860.370205] [<ffffffffa04d5787>] btrfs_set_lock_blocking+0xe/0x10 [btrfs] [133860.370205] [<ffffffffa04d99cb>] btrfs_realloc_node+0xb3/0x341 [btrfs] [133860.370205] [<ffffffffa050e396>] btrfs_defrag_leaves+0x239/0x2fa [btrfs] [133860.370205] [<ffffffffa04fc2ce>] btrfs_defrag_root+0x63/0xca [btrfs] [133860.370205] [<ffffffffa052a34e>] btrfs_ioctl_defrag+0x78/0x14e [btrfs] [133860.370205] [<ffffffffa052b00b>] btrfs_ioctl+0x746/0x24c6 [btrfs] [133860.370205] [<ffffffff81087481>] ? arch_local_irq_save+0x9/0xc [133860.370205] [<ffffffff8113ad61>] ? __might_fault+0x4c/0xa7 [133860.370205] [<ffffffff8113ad61>] ? __might_fault+0x4c/0xa7 [133860.370205] [<ffffffff8113adba>] ? __might_fault+0xa5/0xa7 [133860.370205] [<ffffffff81171139>] ? cp_new_stat+0x15d/0x174 [133860.370205] [<ffffffff8117c610>] do_vfs_ioctl+0x427/0x4e6 [133860.370205] [<ffffffff81171175>] ? SYSC_newfstat+0x25/0x2e [133860.370205] [<ffffffff8118574d>] ? __fget_light+0x4d/0x71 [133860.370205] [<ffffffff8117c726>] SyS_ioctl+0x57/0x79 [133860.370205] [<ffffffff8147cd97>] entry_SYSCALL_64_fastpath+0x12/0x6f This bug happened because we assumed that by setting keep_locks to 1 in our search path, our path after a call to btrfs_search_slot() would have all nodes locked, which is not always true because unlock_up() (called by btrfs_search_slot()) will unlock a node in a path if the slot of the node below it doesn't point to the last item or beyond the last item. For example, when the tree has a heigth of 2 and path->slots[0] has a value smaller than btrfs_header_nritems(path->nodes[0]) - 1, the node at level 2 will be unlocked (also because lowest_unlock is set to 1 due to the fact that the value passed as ins_len to btrfs_search_slot is 0). This resulted in btrfs_find_next_key(), called before btrfs_realloc_node(), to release out path and call again btrfs_search_slot(), but this time with the cow parameter set to 0, meaning the resulting path got only read locks. Therefore when we called btrfs_realloc_node(), with path->nodes[1] having a read lock, it resulted in the warning and BUG_ON when calling btrfs_set_lock_blocking() against the node, as that function expects the node to have a write lock. The second bug happened often when the first bug didn't happen, and made us hang and hitting the following warning at fs/btrfs/locking.c: 251 void btrfs_tree_lock(struct extent_buffer *eb) 252 { 253 WARN_ON(eb->lock_owner == current->pid); This happened because the tree search we made at btrfs_defrag_leaves() before calling btrfs_find_next_key() locked a leaf and all the other nodes in the path, so btrfs_find_next_key() had no need to release the path and make a new search (with path->lowest_level set to 1). This made btrfs_realloc_node() attempt to write lock the same leaf again, resulting in a hang/deadlock. So fix these issues by calling btrfs_find_next_key() after calling btrfs_realloc_node() and setting the search path's lowest_level to 1 to avoid the hang/deadlock when attempting to write lock the leaves at btrfs_realloc_node(). Signed-off-by: Filipe Manana <fdmanana@suse.com>
2015-12-18 09:57:29 +08:00
/*
* We don't need a lock on a leaf. btrfs_realloc_node() will lock all
* leafs from path->nodes[1], so set lowest_level to 1 to avoid later
* a deadlock (attempting to write lock an already write locked leaf).
*/
path->lowest_level = 1;
wret = btrfs_search_slot(trans, root, &key, path, 0, 1);
if (wret < 0) {
ret = wret;
goto out;
}
if (!path->nodes[1]) {
ret = 0;
goto out;
}
Btrfs: fix locking bugs when defragging leaves When running fstests btrfs/070, with a higher number of fsstress operations, I ran frequently into two different locking bugs when defragging directories. The first bug produced the following traces: [133860.229792] ------------[ cut here ]------------ [133860.251062] WARNING: CPU: 2 PID: 26057 at fs/btrfs/locking.c:46 btrfs_set_lock_blocking_rw+0x57/0xbd [btrfs]() [133860.253576] Modules linked in: btrfs crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc loop fuse parport_pc i2c_piix4 psmouse parport [133860.282566] CPU: 2 PID: 26057 Comm: btrfs Tainted: G W 4.3.0-rc5-btrfs-next-17+ #1 [133860.284393] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014 [133860.286827] 0000000000000000 ffff880207697b78 ffffffff812566f4 0000000000000000 [133860.288341] ffff880207697bb0 ffffffff8104d0a6 ffffffffa052d4c1 ffff880178f60e00 [133860.294219] ffff880178f60e00 0000000000000000 00000000000000f6 ffff880207697bc0 [133860.295831] Call Trace: [133860.306518] [<ffffffff812566f4>] dump_stack+0x4e/0x79 [133860.307473] [<ffffffff8104d0a6>] warn_slowpath_common+0x9f/0xb8 [133860.308619] [<ffffffffa052d4c1>] ? btrfs_set_lock_blocking_rw+0x57/0xbd [btrfs] [133860.310068] [<ffffffff8104d172>] warn_slowpath_null+0x1a/0x1c [133860.312552] [<ffffffffa052d4c1>] btrfs_set_lock_blocking_rw+0x57/0xbd [btrfs] [133860.314630] [<ffffffffa04d5787>] btrfs_set_lock_blocking+0xe/0x10 [btrfs] [133860.323596] [<ffffffffa04d99cb>] btrfs_realloc_node+0xb3/0x341 [btrfs] [133860.325233] [<ffffffffa050e396>] btrfs_defrag_leaves+0x239/0x2fa [btrfs] [133860.332427] [<ffffffffa04fc2ce>] btrfs_defrag_root+0x63/0xca [btrfs] [133860.337259] [<ffffffffa052a34e>] btrfs_ioctl_defrag+0x78/0x14e [btrfs] [133860.340147] [<ffffffffa052b00b>] btrfs_ioctl+0x746/0x24c6 [btrfs] [133860.344833] [<ffffffff81087481>] ? arch_local_irq_save+0x9/0xc [133860.346343] [<ffffffff8113ad61>] ? __might_fault+0x4c/0xa7 [133860.353248] [<ffffffff8113ad61>] ? __might_fault+0x4c/0xa7 [133860.354242] [<ffffffff8113adba>] ? __might_fault+0xa5/0xa7 [133860.355232] [<ffffffff81171139>] ? cp_new_stat+0x15d/0x174 [133860.356237] [<ffffffff8117c610>] do_vfs_ioctl+0x427/0x4e6 [133860.358587] [<ffffffff81171175>] ? SYSC_newfstat+0x25/0x2e [133860.360195] [<ffffffff8118574d>] ? __fget_light+0x4d/0x71 [133860.361380] [<ffffffff8117c726>] SyS_ioctl+0x57/0x79 [133860.363578] [<ffffffff8147cd97>] entry_SYSCALL_64_fastpath+0x12/0x6f [133860.366217] ---[ end trace 2cadb2f653437e49 ]--- [133860.367399] ------------[ cut here ]------------ [133860.368162] kernel BUG at fs/btrfs/locking.c:307! [133860.369430] invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC [133860.370205] Modules linked in: btrfs crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc loop fuse parport_pc i2c_piix4 psmouse parport [133860.370205] CPU: 2 PID: 26057 Comm: btrfs Tainted: G W 4.3.0-rc5-btrfs-next-17+ #1 [133860.370205] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014 [133860.370205] task: ffff8800aec6db40 ti: ffff880207694000 task.ti: ffff880207694000 [133860.370205] RIP: 0010:[<ffffffffa052d466>] [<ffffffffa052d466>] btrfs_assert_tree_locked+0x10/0x14 [btrfs] [133860.370205] RSP: 0018:ffff880207697bc0 EFLAGS: 00010246 [133860.370205] RAX: 0000000000000000 RBX: ffff880178f60e00 RCX: 0000000000000000 [133860.370205] RDX: ffff88023ec4fb50 RSI: 00000000ffffffff RDI: ffff880178f60e00 [133860.370205] RBP: ffff880207697bc0 R08: 0000000000000001 R09: 0000000000000000 [133860.370205] R10: 0000160000000000 R11: ffffffff81651000 R12: ffff880178f60e00 [133860.370205] R13: 0000000000000000 R14: 00000000000000f6 R15: ffff8801ff409000 [133860.370205] FS: 00007f763efd48c0(0000) GS:ffff88023ec40000(0000) knlGS:0000000000000000 [133860.370205] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [133860.370205] CR2: 0000000002158048 CR3: 000000003fd6c000 CR4: 00000000000006e0 [133860.370205] Stack: [133860.370205] ffff880207697bd8 ffffffffa052d4d0 0000000000000000 ffff880207697be8 [133860.370205] ffffffffa04d5787 ffff880207697c80 ffffffffa04d99cb ffff8801ff409590 [133860.370205] ffff880207697ca8 000000f507697c80 ffff880183c11bb8 0000000000000000 [133860.370205] Call Trace: [133860.370205] [<ffffffffa052d4d0>] btrfs_set_lock_blocking_rw+0x66/0xbd [btrfs] [133860.370205] [<ffffffffa04d5787>] btrfs_set_lock_blocking+0xe/0x10 [btrfs] [133860.370205] [<ffffffffa04d99cb>] btrfs_realloc_node+0xb3/0x341 [btrfs] [133860.370205] [<ffffffffa050e396>] btrfs_defrag_leaves+0x239/0x2fa [btrfs] [133860.370205] [<ffffffffa04fc2ce>] btrfs_defrag_root+0x63/0xca [btrfs] [133860.370205] [<ffffffffa052a34e>] btrfs_ioctl_defrag+0x78/0x14e [btrfs] [133860.370205] [<ffffffffa052b00b>] btrfs_ioctl+0x746/0x24c6 [btrfs] [133860.370205] [<ffffffff81087481>] ? arch_local_irq_save+0x9/0xc [133860.370205] [<ffffffff8113ad61>] ? __might_fault+0x4c/0xa7 [133860.370205] [<ffffffff8113ad61>] ? __might_fault+0x4c/0xa7 [133860.370205] [<ffffffff8113adba>] ? __might_fault+0xa5/0xa7 [133860.370205] [<ffffffff81171139>] ? cp_new_stat+0x15d/0x174 [133860.370205] [<ffffffff8117c610>] do_vfs_ioctl+0x427/0x4e6 [133860.370205] [<ffffffff81171175>] ? SYSC_newfstat+0x25/0x2e [133860.370205] [<ffffffff8118574d>] ? __fget_light+0x4d/0x71 [133860.370205] [<ffffffff8117c726>] SyS_ioctl+0x57/0x79 [133860.370205] [<ffffffff8147cd97>] entry_SYSCALL_64_fastpath+0x12/0x6f This bug happened because we assumed that by setting keep_locks to 1 in our search path, our path after a call to btrfs_search_slot() would have all nodes locked, which is not always true because unlock_up() (called by btrfs_search_slot()) will unlock a node in a path if the slot of the node below it doesn't point to the last item or beyond the last item. For example, when the tree has a heigth of 2 and path->slots[0] has a value smaller than btrfs_header_nritems(path->nodes[0]) - 1, the node at level 2 will be unlocked (also because lowest_unlock is set to 1 due to the fact that the value passed as ins_len to btrfs_search_slot is 0). This resulted in btrfs_find_next_key(), called before btrfs_realloc_node(), to release out path and call again btrfs_search_slot(), but this time with the cow parameter set to 0, meaning the resulting path got only read locks. Therefore when we called btrfs_realloc_node(), with path->nodes[1] having a read lock, it resulted in the warning and BUG_ON when calling btrfs_set_lock_blocking() against the node, as that function expects the node to have a write lock. The second bug happened often when the first bug didn't happen, and made us hang and hitting the following warning at fs/btrfs/locking.c: 251 void btrfs_tree_lock(struct extent_buffer *eb) 252 { 253 WARN_ON(eb->lock_owner == current->pid); This happened because the tree search we made at btrfs_defrag_leaves() before calling btrfs_find_next_key() locked a leaf and all the other nodes in the path, so btrfs_find_next_key() had no need to release the path and make a new search (with path->lowest_level set to 1). This made btrfs_realloc_node() attempt to write lock the same leaf again, resulting in a hang/deadlock. So fix these issues by calling btrfs_find_next_key() after calling btrfs_realloc_node() and setting the search path's lowest_level to 1 to avoid the hang/deadlock when attempting to write lock the leaves at btrfs_realloc_node(). Signed-off-by: Filipe Manana <fdmanana@suse.com>
2015-12-18 09:57:29 +08:00
/*
* The node at level 1 must always be locked when our path has
* keep_locks set and lowest_level is 1, regardless of the value of
* path->slots[1].
*/
BUG_ON(path->locks[1] == 0);
ret = btrfs_realloc_node(trans, root,
path->nodes[1], 0,
&last_ret,
&root->defrag_progress);
if (ret) {
WARN_ON(ret == -EAGAIN);
goto out;
}
Btrfs: fix locking bugs when defragging leaves When running fstests btrfs/070, with a higher number of fsstress operations, I ran frequently into two different locking bugs when defragging directories. The first bug produced the following traces: [133860.229792] ------------[ cut here ]------------ [133860.251062] WARNING: CPU: 2 PID: 26057 at fs/btrfs/locking.c:46 btrfs_set_lock_blocking_rw+0x57/0xbd [btrfs]() [133860.253576] Modules linked in: btrfs crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc loop fuse parport_pc i2c_piix4 psmouse parport [133860.282566] CPU: 2 PID: 26057 Comm: btrfs Tainted: G W 4.3.0-rc5-btrfs-next-17+ #1 [133860.284393] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014 [133860.286827] 0000000000000000 ffff880207697b78 ffffffff812566f4 0000000000000000 [133860.288341] ffff880207697bb0 ffffffff8104d0a6 ffffffffa052d4c1 ffff880178f60e00 [133860.294219] ffff880178f60e00 0000000000000000 00000000000000f6 ffff880207697bc0 [133860.295831] Call Trace: [133860.306518] [<ffffffff812566f4>] dump_stack+0x4e/0x79 [133860.307473] [<ffffffff8104d0a6>] warn_slowpath_common+0x9f/0xb8 [133860.308619] [<ffffffffa052d4c1>] ? btrfs_set_lock_blocking_rw+0x57/0xbd [btrfs] [133860.310068] [<ffffffff8104d172>] warn_slowpath_null+0x1a/0x1c [133860.312552] [<ffffffffa052d4c1>] btrfs_set_lock_blocking_rw+0x57/0xbd [btrfs] [133860.314630] [<ffffffffa04d5787>] btrfs_set_lock_blocking+0xe/0x10 [btrfs] [133860.323596] [<ffffffffa04d99cb>] btrfs_realloc_node+0xb3/0x341 [btrfs] [133860.325233] [<ffffffffa050e396>] btrfs_defrag_leaves+0x239/0x2fa [btrfs] [133860.332427] [<ffffffffa04fc2ce>] btrfs_defrag_root+0x63/0xca [btrfs] [133860.337259] [<ffffffffa052a34e>] btrfs_ioctl_defrag+0x78/0x14e [btrfs] [133860.340147] [<ffffffffa052b00b>] btrfs_ioctl+0x746/0x24c6 [btrfs] [133860.344833] [<ffffffff81087481>] ? arch_local_irq_save+0x9/0xc [133860.346343] [<ffffffff8113ad61>] ? __might_fault+0x4c/0xa7 [133860.353248] [<ffffffff8113ad61>] ? __might_fault+0x4c/0xa7 [133860.354242] [<ffffffff8113adba>] ? __might_fault+0xa5/0xa7 [133860.355232] [<ffffffff81171139>] ? cp_new_stat+0x15d/0x174 [133860.356237] [<ffffffff8117c610>] do_vfs_ioctl+0x427/0x4e6 [133860.358587] [<ffffffff81171175>] ? SYSC_newfstat+0x25/0x2e [133860.360195] [<ffffffff8118574d>] ? __fget_light+0x4d/0x71 [133860.361380] [<ffffffff8117c726>] SyS_ioctl+0x57/0x79 [133860.363578] [<ffffffff8147cd97>] entry_SYSCALL_64_fastpath+0x12/0x6f [133860.366217] ---[ end trace 2cadb2f653437e49 ]--- [133860.367399] ------------[ cut here ]------------ [133860.368162] kernel BUG at fs/btrfs/locking.c:307! [133860.369430] invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC [133860.370205] Modules linked in: btrfs crc32c_generic xor raid6_pq nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace fscache sunrpc loop fuse parport_pc i2c_piix4 psmouse parport [133860.370205] CPU: 2 PID: 26057 Comm: btrfs Tainted: G W 4.3.0-rc5-btrfs-next-17+ #1 [133860.370205] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.1-0-g4adadbd-20150316_085822-nilsson.home.kraxel.org 04/01/2014 [133860.370205] task: ffff8800aec6db40 ti: ffff880207694000 task.ti: ffff880207694000 [133860.370205] RIP: 0010:[<ffffffffa052d466>] [<ffffffffa052d466>] btrfs_assert_tree_locked+0x10/0x14 [btrfs] [133860.370205] RSP: 0018:ffff880207697bc0 EFLAGS: 00010246 [133860.370205] RAX: 0000000000000000 RBX: ffff880178f60e00 RCX: 0000000000000000 [133860.370205] RDX: ffff88023ec4fb50 RSI: 00000000ffffffff RDI: ffff880178f60e00 [133860.370205] RBP: ffff880207697bc0 R08: 0000000000000001 R09: 0000000000000000 [133860.370205] R10: 0000160000000000 R11: ffffffff81651000 R12: ffff880178f60e00 [133860.370205] R13: 0000000000000000 R14: 00000000000000f6 R15: ffff8801ff409000 [133860.370205] FS: 00007f763efd48c0(0000) GS:ffff88023ec40000(0000) knlGS:0000000000000000 [133860.370205] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [133860.370205] CR2: 0000000002158048 CR3: 000000003fd6c000 CR4: 00000000000006e0 [133860.370205] Stack: [133860.370205] ffff880207697bd8 ffffffffa052d4d0 0000000000000000 ffff880207697be8 [133860.370205] ffffffffa04d5787 ffff880207697c80 ffffffffa04d99cb ffff8801ff409590 [133860.370205] ffff880207697ca8 000000f507697c80 ffff880183c11bb8 0000000000000000 [133860.370205] Call Trace: [133860.370205] [<ffffffffa052d4d0>] btrfs_set_lock_blocking_rw+0x66/0xbd [btrfs] [133860.370205] [<ffffffffa04d5787>] btrfs_set_lock_blocking+0xe/0x10 [btrfs] [133860.370205] [<ffffffffa04d99cb>] btrfs_realloc_node+0xb3/0x341 [btrfs] [133860.370205] [<ffffffffa050e396>] btrfs_defrag_leaves+0x239/0x2fa [btrfs] [133860.370205] [<ffffffffa04fc2ce>] btrfs_defrag_root+0x63/0xca [btrfs] [133860.370205] [<ffffffffa052a34e>] btrfs_ioctl_defrag+0x78/0x14e [btrfs] [133860.370205] [<ffffffffa052b00b>] btrfs_ioctl+0x746/0x24c6 [btrfs] [133860.370205] [<ffffffff81087481>] ? arch_local_irq_save+0x9/0xc [133860.370205] [<ffffffff8113ad61>] ? __might_fault+0x4c/0xa7 [133860.370205] [<ffffffff8113ad61>] ? __might_fault+0x4c/0xa7 [133860.370205] [<ffffffff8113adba>] ? __might_fault+0xa5/0xa7 [133860.370205] [<ffffffff81171139>] ? cp_new_stat+0x15d/0x174 [133860.370205] [<ffffffff8117c610>] do_vfs_ioctl+0x427/0x4e6 [133860.370205] [<ffffffff81171175>] ? SYSC_newfstat+0x25/0x2e [133860.370205] [<ffffffff8118574d>] ? __fget_light+0x4d/0x71 [133860.370205] [<ffffffff8117c726>] SyS_ioctl+0x57/0x79 [133860.370205] [<ffffffff8147cd97>] entry_SYSCALL_64_fastpath+0x12/0x6f This bug happened because we assumed that by setting keep_locks to 1 in our search path, our path after a call to btrfs_search_slot() would have all nodes locked, which is not always true because unlock_up() (called by btrfs_search_slot()) will unlock a node in a path if the slot of the node below it doesn't point to the last item or beyond the last item. For example, when the tree has a heigth of 2 and path->slots[0] has a value smaller than btrfs_header_nritems(path->nodes[0]) - 1, the node at level 2 will be unlocked (also because lowest_unlock is set to 1 due to the fact that the value passed as ins_len to btrfs_search_slot is 0). This resulted in btrfs_find_next_key(), called before btrfs_realloc_node(), to release out path and call again btrfs_search_slot(), but this time with the cow parameter set to 0, meaning the resulting path got only read locks. Therefore when we called btrfs_realloc_node(), with path->nodes[1] having a read lock, it resulted in the warning and BUG_ON when calling btrfs_set_lock_blocking() against the node, as that function expects the node to have a write lock. The second bug happened often when the first bug didn't happen, and made us hang and hitting the following warning at fs/btrfs/locking.c: 251 void btrfs_tree_lock(struct extent_buffer *eb) 252 { 253 WARN_ON(eb->lock_owner == current->pid); This happened because the tree search we made at btrfs_defrag_leaves() before calling btrfs_find_next_key() locked a leaf and all the other nodes in the path, so btrfs_find_next_key() had no need to release the path and make a new search (with path->lowest_level set to 1). This made btrfs_realloc_node() attempt to write lock the same leaf again, resulting in a hang/deadlock. So fix these issues by calling btrfs_find_next_key() after calling btrfs_realloc_node() and setting the search path's lowest_level to 1 to avoid the hang/deadlock when attempting to write lock the leaves at btrfs_realloc_node(). Signed-off-by: Filipe Manana <fdmanana@suse.com>
2015-12-18 09:57:29 +08:00
/*
* Now that we reallocated the node we can find the next key. Note that
* btrfs_find_next_key() can release our path and do another search
* without COWing, this is because even with path->keep_locks = 1,
* btrfs_search_slot() / ctree.c:unlock_up() does not keeps a lock on a
* node when path->slots[node_level - 1] does not point to the last
* item or a slot beyond the last item (ctree.c:unlock_up()). Therefore
* we search for the next key after reallocating our node.
*/
path->slots[1] = btrfs_header_nritems(path->nodes[1]);
next_key_ret = btrfs_find_next_key(root, path, &key, 1,
BTRFS_OLDEST_GENERATION);
if (next_key_ret == 0) {
memcpy(&root->defrag_progress, &key, sizeof(key));
ret = -EAGAIN;
}
out:
btrfs_free_path(path);
if (ret == -EAGAIN) {
if (root->defrag_max.objectid > root->defrag_progress.objectid)
goto done;
if (root->defrag_max.type > root->defrag_progress.type)
goto done;
if (root->defrag_max.offset > root->defrag_progress.offset)
goto done;
ret = 0;
}
done:
if (ret != -EAGAIN) {
memset(&root->defrag_progress, 0,
sizeof(root->defrag_progress));
root->defrag_trans_start = trans->transid;
}
return ret;
}