openkylin
/
linux
mirror of https://gitee.com/openkylin/linux.git
9
0
Fork 0
Code Issues Projects Releases Wiki Activity
linux/fs/btrfs/locking.h

132 lines
4.2 KiB
C
Raw Normal View History

btrfs: replace GPL boilerplate by SPDX -- headers Remove GPL boilerplate text (long, short, one-line) and keep the rest, ie. personal, company or original source copyright statements. Add the SPDX header. Unify the include protection macros to match the file names. Signed-off-by: David Sterba <dsterba@suse.com>
2018-04-04 01:16:55 +08:00
/* SPDX-License-Identifier: GPL-2.0 */
Btrfs: Start btree concurrency work. The allocation trees and the chunk trees are serialized via their own dedicated mutexes. This means allocation location is still not very fine grained. The main FS btree is protected by locks on each block in the btree. Locks are taken top / down, and as processing finishes on a given level of the tree, the lock is released after locking the lower level. The end result of a search is now a path where only the lowest level is locked. Releasing or freeing the path drops any locks held. Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-06-26 04:01:30 +08:00
/*
* Copyright (C) 2008 Oracle. All rights reserved.
*/
btrfs: replace GPL boilerplate by SPDX -- headers Remove GPL boilerplate text (long, short, one-line) and keep the rest, ie. personal, company or original source copyright statements. Add the SPDX header. Unify the include protection macros to match the file names. Signed-off-by: David Sterba <dsterba@suse.com>
2018-04-04 01:16:55 +08:00
#ifndef BTRFS_LOCKING_H
#define BTRFS_LOCKING_H
Btrfs: Start btree concurrency work. The allocation trees and the chunk trees are serialized via their own dedicated mutexes. This means allocation location is still not very fine grained. The main FS btree is protected by locks on each block in the btree. Locks are taken top / down, and as processing finishes on a given level of the tree, the lock is released after locking the lower level. The end result of a search is now a path where only the lowest level is locked. Releasing or freeing the path drops any locks held. Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-06-26 04:01:30 +08:00
btrfs: Implement DREW lock A (D)ouble (R)eader (W)riter (E)xclustion lock is a locking primitive that allows to have multiple readers or multiple writers but not multiple readers and writers holding it concurrently. The code is factored out from the existing open-coded locking scheme used to exclude pending snapshots from nocow writers and vice-versa. Current implementation actually favors Readers (that is snapshot creaters) to writers (nocow writers of the filesystem). The API provides lock/unlock/trylock for reads and writes. Formal specification for TLA+ provided by Valentin Schneider is at https://lore.kernel.org/linux-btrfs/2dcaf81c-f0d3-409e-cb29-733d8b3b4cc9@arm.com/ Signed-off-by: Nikolay Borisov <nborisov@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-01-30 20:59:44 +08:00
#include <linux/atomic.h>
#include <linux/wait.h>
#include <linux/percpu_counter.h>
btrfs: make btrfs_assert_tree_locked static inline The function btrfs_assert_tree_locked is used outside of the locking code so it is exported, however we can make it static inine as it's fairly trivial. This is the only locking assertion used in release builds, inlining improves the text size by 174 bytes and reduces stack consumption in the callers. Reviewed-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: David Sterba <dsterba@suse.com>
2019-09-25 00:44:24 +08:00
#include "extent_io.h"
Btrfs: switch the btrfs tree locks to reader/writer The btrfs metadata btree is the source of significant lock contention, especially in the root node. This commit changes our locking to use a reader/writer lock. The lock is built on top of rw spinlocks, and it extends the lock tracking to remember if we have a read lock or a write lock when we go to blocking. Atomics count the number of blocking readers or writers at any given time. It removes all of the adaptive spinning from the old code and uses only the spinning/blocking hints inside of btrfs to decide when it should continue spinning. In read heavy workloads this is dramatically faster. In write heavy workloads we're still faster because of less contention on the root node lock. We suffer slightly in dbench because we schedule more often during write locks, but all other benchmarks so far are improved. Signed-off-by: Chris Mason <chris.mason@oracle.com>
2011-07-17 03:23:14 +08:00
#define BTRFS_WRITE_LOCK 1
#define BTRFS_READ_LOCK 2
#define BTRFS_WRITE_LOCK_BLOCKING 3
#define BTRFS_READ_LOCK_BLOCKING 4
btrfs: add nesting tags to the locking helpers We will need these when we switch to an rwsem, so plumb in the infrastructure here to use later on. I violate the 80 character limit some here because it'll be cleaned up later. Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-08-20 23:46:02 +08:00
/*
* We are limited in number of subclasses by MAX_LOCKDEP_SUBCLASSES, which at
* the time of this patch is 8, which is how many we use. Keep this in mind if
* you decide you want to add another subclass.
*/
enum btrfs_lock_nesting {
BTRFS_NESTING_NORMAL,
btrfs: introduce BTRFS_NESTING_COW for cow'ing blocks When we COW a block we are holding a lock on the original block, and then we lock the new COW block. Because our lockdep maps are based on root + level, this will make lockdep complain. We need a way to indicate a subclass for locking the COW'ed block, so plumb through our btrfs_lock_nesting from btrfs_cow_block down to the btrfs_init_buffer, and then introduce BTRFS_NESTING_COW to be used for cow'ing blocks. The reason I've added all this extra infrastructure is because there will be need of different nesting classes in follow up patches. Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-08-20 23:46:03 +08:00
/*
* When we COW a block we are holding the lock on the original block,
* and since our lockdep maps are rootid+level, this confuses lockdep
* when we lock the newly allocated COW'd block. Handle this by having
* a subclass for COW'ed blocks so that lockdep doesn't complain.
*/
BTRFS_NESTING_COW,
btrfs: introduce BTRFS_NESTING_LEFT/BTRFS_NESTING_RIGHT Our lockdep maps are based on rootid+level, however in some cases we will lock adjacent blocks on the same level, namely in searching forward or in split/balance. Because of this lockdep will complain, so we need a separate subclass to indicate to lockdep that these are different locks. lock leaf -> BTRFS_NESTING_NORMAL cow leaf -> BTRFS_NESTING_COW split leaf lock left -> BTRFS_NESTING_LEFT lock right -> BTRFS_NESTING_RIGHT The above graph illustrates the need for this new nesting subclass. Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-08-20 23:46:04 +08:00
/*
* Oftentimes we need to lock adjacent nodes on the same level while
* still holding the lock on the original node we searched to, such as
* for searching forward or for split/balance.
*
* Because of this we need to indicate to lockdep that this is
* acceptable by having a different subclass for each of these
* operations.
*/
BTRFS_NESTING_LEFT,
BTRFS_NESTING_RIGHT,
btrfs: introduce BTRFS_NESTING_LEFT/RIGHT_COW For similar reasons as BTRFS_NESTING_COW, we need BTRFS_NESTING_LEFT/RIGHT_COW. The pattern is this lock leaf -> BTRFS_NESTING_NORMAL cow leaf -> BTRFS_NESTING_COW split leaf lock left -> BTRFS_NESTING_LEFT cow left -> BTRFS_NESTING_LEFT_COW We need this in order to indicate to lockdep that these locks are discrete and are being taken in a safe order. Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-08-20 23:46:05 +08:00
/*
* When splitting we will be holding a lock on the left/right node when
* we need to cow that node, thus we need a new set of subclasses for
* these two operations.
*/
BTRFS_NESTING_LEFT_COW,
BTRFS_NESTING_RIGHT_COW,
btrfs: add nesting tags to the locking helpers We will need these when we switch to an rwsem, so plumb in the infrastructure here to use later on. I violate the 80 character limit some here because it'll be cleaned up later. Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-08-20 23:46:02 +08:00
/*
* We are limited to MAX_LOCKDEP_SUBLCLASSES number of subclasses, so
* add this in here and add a static_assert to keep us from going over
* the limit. As of this writing we're limited to 8, and we're
* definitely using 8, hence this check to keep us from messing up in
* the future.
*/
BTRFS_NESTING_MAX,
};
static_assert(BTRFS_NESTING_MAX <= MAX_LOCKDEP_SUBCLASSES,
"too many lock subclasses defined");
btrfs: Implement DREW lock A (D)ouble (R)eader (W)riter (E)xclustion lock is a locking primitive that allows to have multiple readers or multiple writers but not multiple readers and writers holding it concurrently. The code is factored out from the existing open-coded locking scheme used to exclude pending snapshots from nocow writers and vice-versa. Current implementation actually favors Readers (that is snapshot creaters) to writers (nocow writers of the filesystem). The API provides lock/unlock/trylock for reads and writes. Formal specification for TLA+ provided by Valentin Schneider is at https://lore.kernel.org/linux-btrfs/2dcaf81c-f0d3-409e-cb29-733d8b3b4cc9@arm.com/ Signed-off-by: Nikolay Borisov <nborisov@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-01-30 20:59:44 +08:00
struct btrfs_path;
btrfs: add nesting tags to the locking helpers We will need these when we switch to an rwsem, so plumb in the infrastructure here to use later on. I violate the 80 character limit some here because it'll be cleaned up later. Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-08-20 23:46:02 +08:00
void __btrfs_tree_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest);
btrfs: return void in functions without error conditions Signed-off-by: Jeff Mahoney <jeffm@suse.com>
2012-03-01 21:56:26 +08:00
void btrfs_tree_lock(struct extent_buffer *eb);
void btrfs_tree_unlock(struct extent_buffer *eb);
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: add nesting tags to the locking helpers We will need these when we switch to an rwsem, so plumb in the infrastructure here to use later on. I violate the 80 character limit some here because it'll be cleaned up later. Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-08-20 23:46:02 +08:00
void __btrfs_tree_read_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest,
bool recurse);
Btrfs: switch the btrfs tree locks to reader/writer The btrfs metadata btree is the source of significant lock contention, especially in the root node. This commit changes our locking to use a reader/writer lock. The lock is built on top of rw spinlocks, and it extends the lock tracking to remember if we have a read lock or a write lock when we go to blocking. Atomics count the number of blocking readers or writers at any given time. It removes all of the adaptive spinning from the old code and uses only the spinning/blocking hints inside of btrfs to decide when it should continue spinning. In read heavy workloads this is dramatically faster. In write heavy workloads we're still faster because of less contention on the root node lock. We suffer slightly in dbench because we schedule more often during write locks, but all other benchmarks so far are improved. Signed-off-by: Chris Mason <chris.mason@oracle.com>
2011-07-17 03:23:14 +08:00
void btrfs_tree_read_lock(struct extent_buffer *eb);
void btrfs_tree_read_unlock(struct extent_buffer *eb);
void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb);
btrfs: split btrfs_set_lock_blocking_rw to read and write helpers There are many callers that hardcode the desired lock type so we can avoid the switch and call them directly. Split the current function to two but leave a helper that still takes the variable lock type to make current code compile. The call sites will be converted in followup patches. Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Signed-off-by: David Sterba <dsterba@suse.com>
2018-04-04 07:43:05 +08:00
void btrfs_set_lock_blocking_read(struct extent_buffer *eb);
void btrfs_set_lock_blocking_write(struct extent_buffer *eb);
Btrfs: switch the btrfs tree locks to reader/writer The btrfs metadata btree is the source of significant lock contention, especially in the root node. This commit changes our locking to use a reader/writer lock. The lock is built on top of rw spinlocks, and it extends the lock tracking to remember if we have a read lock or a write lock when we go to blocking. Atomics count the number of blocking readers or writers at any given time. It removes all of the adaptive spinning from the old code and uses only the spinning/blocking hints inside of btrfs to decide when it should continue spinning. In read heavy workloads this is dramatically faster. In write heavy workloads we're still faster because of less contention on the root node lock. We suffer slightly in dbench because we schedule more often during write locks, but all other benchmarks so far are improved. Signed-off-by: Chris Mason <chris.mason@oracle.com>
2011-07-17 03:23:14 +08:00
int btrfs_try_tree_read_lock(struct extent_buffer *eb);
int btrfs_try_tree_write_lock(struct extent_buffer *eb);
btrfs: fix lockups from btrfs_clear_path_blocking The fair reader/writer locks mean that btrfs_clear_path_blocking needs to strictly follow lock ordering rules even when we already have blocking locks on a given path. Before we can clear a blocking lock on the path, we need to make sure all of the locks have been converted to blocking. This will remove lock inversions against anyone spinning in write_lock() against the buffers we're trying to get read locks on. These inversions didn't exist before the fair read/writer locks, but now we need to be more careful. We papered over this deadlock in the past by changing btrfs_try_read_lock() to be a true trylock against both the spinlock and the blocking lock. This was slower, and not sufficient to fix all the deadlocks. This patch adds a btrfs_tree_read_lock_atomic(), which basically means get the spinlock but trylock on the blocking lock. Signed-off-by: Chris Mason <clm@fb.com> Signed-off-by: Josef Bacik <jbacik@fb.com> Reported-by: Patrick Schmid <schmid@phys.ethz.ch> cc: stable@vger.kernel.org #v3.15+
2014-11-20 02:25:09 +08:00
int btrfs_tree_read_lock_atomic(struct extent_buffer *eb);
btrfs: introduce btrfs_path::recurse Our current tree locking stuff allows us to recurse with read locks if we're already holding the write lock. This is necessary for the space cache inode, as we could be holding a lock on the root_tree root when we need to cache a block group, and thus need to be able to read down the root_tree to read in the inode cache. We can get away with this in our current locking, but we won't be able to with a rwsem. Handle this by purposefully annotating the places where we require recursion, so that in the future we can maybe come up with a way to avoid the recursion. In the case of the free space inode, this will be superseded by the free space tree. Signed-off-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-08-20 23:46:01 +08:00
struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root);
struct extent_buffer *__btrfs_read_lock_root_node(struct btrfs_root *root,
bool recurse);
static inline struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root)
{
return __btrfs_read_lock_root_node(root, false);
}
btrfs: fix lockups from btrfs_clear_path_blocking The fair reader/writer locks mean that btrfs_clear_path_blocking needs to strictly follow lock ordering rules even when we already have blocking locks on a given path. Before we can clear a blocking lock on the path, we need to make sure all of the locks have been converted to blocking. This will remove lock inversions against anyone spinning in write_lock() against the buffers we're trying to get read locks on. These inversions didn't exist before the fair read/writer locks, but now we need to be more careful. We papered over this deadlock in the past by changing btrfs_try_read_lock() to be a true trylock against both the spinlock and the blocking lock. This was slower, and not sufficient to fix all the deadlocks. This patch adds a btrfs_tree_read_lock_atomic(), which basically means get the spinlock but trylock on the blocking lock. Signed-off-by: Chris Mason <clm@fb.com> Signed-off-by: Josef Bacik <jbacik@fb.com> Reported-by: Patrick Schmid <schmid@phys.ethz.ch> cc: stable@vger.kernel.org #v3.15+
2014-11-20 02:25:09 +08:00
btrfs: make btrfs_assert_tree_locked static inline The function btrfs_assert_tree_locked is used outside of the locking code so it is exported, however we can make it static inine as it's fairly trivial. This is the only locking assertion used in release builds, inlining improves the text size by 174 bytes and reduces stack consumption in the callers. Reviewed-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: David Sterba <dsterba@suse.com>
2019-09-25 00:44:24 +08:00
#ifdef CONFIG_BTRFS_DEBUG
static inline void btrfs_assert_tree_locked(struct extent_buffer *eb) {
BUG_ON(!eb->write_locks);
}
#else
static inline void btrfs_assert_tree_locked(struct extent_buffer *eb) { }
#endif
Btrfs: switch the btrfs tree locks to reader/writer The btrfs metadata btree is the source of significant lock contention, especially in the root node. This commit changes our locking to use a reader/writer lock. The lock is built on top of rw spinlocks, and it extends the lock tracking to remember if we have a read lock or a write lock when we go to blocking. Atomics count the number of blocking readers or writers at any given time. It removes all of the adaptive spinning from the old code and uses only the spinning/blocking hints inside of btrfs to decide when it should continue spinning. In read heavy workloads this is dramatically faster. In write heavy workloads we're still faster because of less contention on the root node lock. We suffer slightly in dbench because we schedule more often during write locks, but all other benchmarks so far are improved. Signed-off-by: Chris Mason <chris.mason@oracle.com>
2011-07-17 03:23:14 +08:00
btrfs: move btrfs_set_path_blocking to other locking functions The function belongs to the family of locking functions, so move it there. The 'noinline' keyword is dropped as it's now an exported function that does not need it. Reviewed-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: David Sterba <dsterba@suse.com>
2019-09-25 01:17:17 +08:00
void btrfs_set_path_blocking(struct btrfs_path *p);
btrfs: move btrfs_unlock_up_safe to other locking functions The function belongs to the family of locking functions, so move it there. The 'noinline' keyword is dropped as it's now an exported function that does not need it. Reviewed-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: David Sterba <dsterba@suse.com>
2019-09-25 01:17:17 +08:00
void btrfs_unlock_up_safe(struct btrfs_path *path, int level);
btrfs: move btrfs_set_path_blocking to other locking functions The function belongs to the family of locking functions, so move it there. The 'noinline' keyword is dropped as it's now an exported function that does not need it. Reviewed-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: David Sterba <dsterba@suse.com>
2019-09-25 01:17:17 +08:00
Btrfs: switch the btrfs tree locks to reader/writer The btrfs metadata btree is the source of significant lock contention, especially in the root node. This commit changes our locking to use a reader/writer lock. The lock is built on top of rw spinlocks, and it extends the lock tracking to remember if we have a read lock or a write lock when we go to blocking. Atomics count the number of blocking readers or writers at any given time. It removes all of the adaptive spinning from the old code and uses only the spinning/blocking hints inside of btrfs to decide when it should continue spinning. In read heavy workloads this is dramatically faster. In write heavy workloads we're still faster because of less contention on the root node lock. We suffer slightly in dbench because we schedule more often during write locks, but all other benchmarks so far are improved. Signed-off-by: Chris Mason <chris.mason@oracle.com>
2011-07-17 03:23:14 +08:00
static inline void btrfs_tree_unlock_rw(struct extent_buffer *eb, int rw)
{
if (rw == BTRFS_WRITE_LOCK || rw == BTRFS_WRITE_LOCK_BLOCKING)
btrfs_tree_unlock(eb);
else if (rw == BTRFS_READ_LOCK_BLOCKING)
btrfs_tree_read_unlock_blocking(eb);
else if (rw == BTRFS_READ_LOCK)
btrfs_tree_read_unlock(eb);
else
BUG();
}
btrfs: Implement DREW lock A (D)ouble (R)eader (W)riter (E)xclustion lock is a locking primitive that allows to have multiple readers or multiple writers but not multiple readers and writers holding it concurrently. The code is factored out from the existing open-coded locking scheme used to exclude pending snapshots from nocow writers and vice-versa. Current implementation actually favors Readers (that is snapshot creaters) to writers (nocow writers of the filesystem). The API provides lock/unlock/trylock for reads and writes. Formal specification for TLA+ provided by Valentin Schneider is at https://lore.kernel.org/linux-btrfs/2dcaf81c-f0d3-409e-cb29-733d8b3b4cc9@arm.com/ Signed-off-by: Nikolay Borisov <nborisov@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-01-30 20:59:44 +08:00
struct btrfs_drew_lock {
atomic_t readers;
struct percpu_counter writers;
wait_queue_head_t pending_writers;
wait_queue_head_t pending_readers;
};
int btrfs_drew_lock_init(struct btrfs_drew_lock *lock);
void btrfs_drew_lock_destroy(struct btrfs_drew_lock *lock);
void btrfs_drew_write_lock(struct btrfs_drew_lock *lock);
bool btrfs_drew_try_write_lock(struct btrfs_drew_lock *lock);
void btrfs_drew_write_unlock(struct btrfs_drew_lock *lock);
void btrfs_drew_read_lock(struct btrfs_drew_lock *lock);
void btrfs_drew_read_unlock(struct btrfs_drew_lock *lock);
Btrfs: Start btree concurrency work. The allocation trees and the chunk trees are serialized via their own dedicated mutexes. This means allocation location is still not very fine grained. The main FS btree is protected by locks on each block in the btree. Locks are taken top / down, and as processing finishes on a given level of the tree, the lock is released after locking the lower level. The end result of a search is now a path where only the lowest level is locked. Releasing or freeing the path drops any locks held. Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-06-26 04:01:30 +08:00
#endif