linux/fs/btrfs/block-rsv.h

144 lines
4.3 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef BTRFS_BLOCK_RSV_H
#define BTRFS_BLOCK_RSV_H
#include <linux/types.h>
#include <linux/compiler.h>
#include <linux/spinlock.h>
struct btrfs_trans_handle;
struct btrfs_root;
struct btrfs_space_info;
struct btrfs_block_rsv;
struct btrfs_fs_info;
enum btrfs_reserve_flush_enum;
/*
* Types of block reserves
*/
enum btrfs_rsv_type {
BTRFS_BLOCK_RSV_GLOBAL,
BTRFS_BLOCK_RSV_DELALLOC,
BTRFS_BLOCK_RSV_TRANS,
BTRFS_BLOCK_RSV_CHUNK,
BTRFS_BLOCK_RSV_DELOPS,
BTRFS_BLOCK_RSV_DELREFS,
BTRFS_BLOCK_RSV_EMPTY,
BTRFS_BLOCK_RSV_TEMP,
};
struct btrfs_block_rsv {
u64 size;
u64 reserved;
struct btrfs_space_info *space_info;
spinlock_t lock;
bool full;
bool failfast;
/* Block reserve type, one of BTRFS_BLOCK_RSV_* */
enum btrfs_rsv_type type:8;
/*
* Qgroup equivalent for @size @reserved
*
* Unlike normal @size/@reserved for inode rsv, qgroup doesn't care
* about things like csum size nor how many tree blocks it will need to
* reserve.
*
* Qgroup cares more about net change of the extent usage.
*
* So for one newly inserted file extent, in worst case it will cause
* leaf split and level increase, nodesize for each file extent is
* already too much.
*
* In short, qgroup_size/reserved is the upper limit of possible needed
* qgroup metadata reservation.
*/
u64 qgroup_rsv_size;
u64 qgroup_rsv_reserved;
};
void btrfs_init_block_rsv(struct btrfs_block_rsv *rsv, enum btrfs_rsv_type type);
void btrfs_init_root_block_rsv(struct btrfs_root *root);
struct btrfs_block_rsv *btrfs_alloc_block_rsv(struct btrfs_fs_info *fs_info,
enum btrfs_rsv_type type);
void btrfs_init_metadata_block_rsv(struct btrfs_fs_info *fs_info,
struct btrfs_block_rsv *rsv,
enum btrfs_rsv_type type);
void btrfs_free_block_rsv(struct btrfs_fs_info *fs_info,
struct btrfs_block_rsv *rsv);
int btrfs_block_rsv_add(struct btrfs_fs_info *fs_info,
struct btrfs_block_rsv *block_rsv, u64 num_bytes,
enum btrfs_reserve_flush_enum flush);
int btrfs_block_rsv_check(struct btrfs_block_rsv *block_rsv, int min_percent);
int btrfs_block_rsv_refill(struct btrfs_fs_info *fs_info,
struct btrfs_block_rsv *block_rsv, u64 num_bytes,
enum btrfs_reserve_flush_enum flush);
int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv,
struct btrfs_block_rsv *dst_rsv, u64 num_bytes,
bool update_size);
int btrfs_block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv, u64 num_bytes);
void btrfs_block_rsv_add_bytes(struct btrfs_block_rsv *block_rsv,
u64 num_bytes, bool update_size);
u64 btrfs_block_rsv_release(struct btrfs_fs_info *fs_info,
struct btrfs_block_rsv *block_rsv,
u64 num_bytes, u64 *qgroup_to_release);
void btrfs_update_global_block_rsv(struct btrfs_fs_info *fs_info);
void btrfs_init_global_block_rsv(struct btrfs_fs_info *fs_info);
void btrfs_release_global_block_rsv(struct btrfs_fs_info *fs_info);
struct btrfs_block_rsv *btrfs_use_block_rsv(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
u32 blocksize);
int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info,
struct btrfs_block_rsv *rsv);
static inline void btrfs_unuse_block_rsv(struct btrfs_fs_info *fs_info,
struct btrfs_block_rsv *block_rsv,
u32 blocksize)
{
btrfs_block_rsv_add_bytes(block_rsv, blocksize, false);
btrfs_block_rsv_release(fs_info, block_rsv, 0, NULL);
}
/*
* Fast path to check if the reserve is full, may be carefully used outside of
* locks.
*/
static inline bool btrfs_block_rsv_full(const struct btrfs_block_rsv *rsv)
{
return data_race(rsv->full);
}
btrfs: fix data races when accessing the reserved amount of block reserves At space_info.c we have several places where we access the ->reserved field of a block reserve without taking the block reserve's spinlock first, which makes KCSAN warn about a data race since that field is always updated while holding the spinlock. The reports from KCSAN are like the following: [117.193526] BUG: KCSAN: data-race in btrfs_block_rsv_release [btrfs] / need_preemptive_reclaim [btrfs] [117.195148] read to 0x000000017f587190 of 8 bytes by task 6303 on cpu 3: [117.195172] need_preemptive_reclaim+0x222/0x2f0 [btrfs] [117.195992] __reserve_bytes+0xbb0/0xdc8 [btrfs] [117.196807] btrfs_reserve_metadata_bytes+0x4c/0x120 [btrfs] [117.197620] btrfs_block_rsv_add+0x78/0xa8 [btrfs] [117.198434] btrfs_delayed_update_inode+0x154/0x368 [btrfs] [117.199300] btrfs_update_inode+0x108/0x1c8 [btrfs] [117.200122] btrfs_dirty_inode+0xb4/0x140 [btrfs] [117.200937] btrfs_update_time+0x8c/0xb0 [btrfs] [117.201754] touch_atime+0x16c/0x1e0 [117.201789] filemap_read+0x674/0x728 [117.201823] btrfs_file_read_iter+0xf8/0x410 [btrfs] [117.202653] vfs_read+0x2b6/0x498 [117.203454] ksys_read+0xa2/0x150 [117.203473] __s390x_sys_read+0x68/0x88 [117.203495] do_syscall+0x1c6/0x210 [117.203517] __do_syscall+0xc8/0xf0 [117.203539] system_call+0x70/0x98 [117.203579] write to 0x000000017f587190 of 8 bytes by task 11 on cpu 0: [117.203604] btrfs_block_rsv_release+0x2e8/0x578 [btrfs] [117.204432] btrfs_delayed_inode_release_metadata+0x7c/0x1d0 [btrfs] [117.205259] __btrfs_update_delayed_inode+0x37c/0x5e0 [btrfs] [117.206093] btrfs_async_run_delayed_root+0x356/0x498 [btrfs] [117.206917] btrfs_work_helper+0x160/0x7a0 [btrfs] [117.207738] process_one_work+0x3b6/0x838 [117.207768] worker_thread+0x75e/0xb10 [117.207797] kthread+0x21a/0x230 [117.207830] __ret_from_fork+0x6c/0xb8 [117.207861] ret_from_fork+0xa/0x30 So add a helper to get the reserved amount of a block reserve while holding the lock. The value may be not be up to date anymore when used by need_preemptive_reclaim() and btrfs_preempt_reclaim_metadata_space(), but that's ok since the worst it can do is cause more reclaim work do be done sooner rather than later. Reading the field while holding the lock instead of using the data_race() annotation is used in order to prevent load tearing. Signed-off-by: Filipe Manana <fdmanana@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2024-02-20 03:41:23 +08:00
/*
* Get the reserved mount of a block reserve in a context where getting a stale
* value is acceptable, instead of accessing it directly and trigger data race
* warning from KCSAN.
*/
static inline u64 btrfs_block_rsv_reserved(struct btrfs_block_rsv *rsv)
{
u64 ret;
spin_lock(&rsv->lock);
ret = rsv->reserved;
spin_unlock(&rsv->lock);
return ret;
}
btrfs: fix data race at btrfs_use_block_rsv() when accessing block reserve At btrfs_use_block_rsv() we read the size of a block reserve without locking its spinlock, which makes KCSAN complain because the size of a block reserve is always updated while holding its spinlock. The report from KCSAN is the following: [653.313148] BUG: KCSAN: data-race in btrfs_update_delayed_refs_rsv [btrfs] / btrfs_use_block_rsv [btrfs] [653.314755] read to 0x000000017f5871b8 of 8 bytes by task 7519 on cpu 0: [653.314779] btrfs_use_block_rsv+0xe4/0x2f8 [btrfs] [653.315606] btrfs_alloc_tree_block+0xdc/0x998 [btrfs] [653.316421] btrfs_force_cow_block+0x220/0xe38 [btrfs] [653.317242] btrfs_cow_block+0x1ac/0x568 [btrfs] [653.318060] btrfs_search_slot+0xda2/0x19b8 [btrfs] [653.318879] btrfs_del_csums+0x1dc/0x798 [btrfs] [653.319702] __btrfs_free_extent.isra.0+0xc24/0x2028 [btrfs] [653.320538] __btrfs_run_delayed_refs+0xd3c/0x2390 [btrfs] [653.321340] btrfs_run_delayed_refs+0xae/0x290 [btrfs] [653.322140] flush_space+0x5e4/0x718 [btrfs] [653.322958] btrfs_preempt_reclaim_metadata_space+0x102/0x2f8 [btrfs] [653.323781] process_one_work+0x3b6/0x838 [653.323800] worker_thread+0x75e/0xb10 [653.323817] kthread+0x21a/0x230 [653.323836] __ret_from_fork+0x6c/0xb8 [653.323855] ret_from_fork+0xa/0x30 [653.323887] write to 0x000000017f5871b8 of 8 bytes by task 576 on cpu 3: [653.323906] btrfs_update_delayed_refs_rsv+0x1a4/0x250 [btrfs] [653.324699] btrfs_add_delayed_data_ref+0x468/0x6d8 [btrfs] [653.325494] btrfs_free_extent+0x76/0x120 [btrfs] [653.326280] __btrfs_mod_ref+0x6a8/0x6b8 [btrfs] [653.327064] btrfs_dec_ref+0x50/0x70 [btrfs] [653.327849] walk_up_proc+0x236/0xa50 [btrfs] [653.328633] walk_up_tree+0x21c/0x448 [btrfs] [653.329418] btrfs_drop_snapshot+0x802/0x1328 [btrfs] [653.330205] btrfs_clean_one_deleted_snapshot+0x184/0x238 [btrfs] [653.330995] cleaner_kthread+0x2b0/0x2f0 [btrfs] [653.331781] kthread+0x21a/0x230 [653.331800] __ret_from_fork+0x6c/0xb8 [653.331818] ret_from_fork+0xa/0x30 So add a helper to get the size of a block reserve while holding the lock. Reading the field while holding the lock instead of using the data_race() annotation is used in order to prevent load tearing. Signed-off-by: Filipe Manana <fdmanana@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2024-02-20 04:10:07 +08:00
/*
* Get the size of a block reserve in a context where getting a stale value is
* acceptable, instead of accessing it directly and trigger data race warning
* from KCSAN.
*/
static inline u64 btrfs_block_rsv_size(struct btrfs_block_rsv *rsv)
{
u64 ret;
spin_lock(&rsv->lock);
ret = rsv->size;
spin_unlock(&rsv->lock);
return ret;
}
#endif /* BTRFS_BLOCK_RSV_H */