mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-16 08:44:21 +08:00
d5c88131db
When a writer thread executes a chain of log intent items, the AG header buffer locks will cycle during a transaction roll to get from one intent item to the next in a chain. Although scrub takes all AG header buffer locks, this isn't sufficient to guard against scrub checking an AG while that writer thread is in the middle of finishing a chain because there's no higher level locking primitive guarding allocation groups. When there's a collision, cross-referencing between data structures (e.g. rmapbt and refcountbt) yields false corruption events; if repair is running, this results in incorrect repairs, which is catastrophic. Fix this by adding to the perag structure the count of active intents and make scrub wait until it has both AG header buffer locks and the intent counter reaches zero. One quirk of the drain code is that deferred bmap updates also bump and drop the intent counter. A fundamental decision made during the design phase of the reverse mapping feature is that updates to the rmapbt records are always made by the same code that updates the primary metadata. In other words, callers of bmapi functions expect that the bmapi functions will queue deferred rmap updates. Some parts of the reflink code queue deferred refcount (CUI) and bmap (BUI) updates in the same head transaction, but the deferred work manager completely finishes the CUI before the BUI work is started. As a result, the CUI drops the intent count long before the deferred rmap (RUI) update even has a chance to bump the intent count. The only way to keep the intent count elevated between the CUI and RUI is for the BUI to bump the counter until the RUI has been created. A second quirk of the intent drain code is that deferred work items must increment the intent counter as soon as the work item is added to the transaction. When a BUI completes and queues an RUI, the RUI must increment the counter before the BUI decrements it. The only way to accomplish this is to require that the counter be bumped as soon as the deferred work item is created in memory. In the next patches we'll improve on this facility, but this patch provides the basic functionality. Signed-off-by: Darrick J. Wong <djwong@kernel.org> Reviewed-by: Dave Chinner <dchinner@redhat.com>
260 lines
6.6 KiB
C
260 lines
6.6 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Copyright (c) 2000-2005 Silicon Graphics, Inc.
|
|
* All Rights Reserved.
|
|
*/
|
|
#ifndef __XFS_LINUX__
|
|
#define __XFS_LINUX__
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/uuid.h>
|
|
|
|
/*
|
|
* Kernel specific type declarations for XFS
|
|
*/
|
|
|
|
typedef __s64 xfs_off_t; /* <file offset> type */
|
|
typedef unsigned long long xfs_ino_t; /* <inode> type */
|
|
typedef __s64 xfs_daddr_t; /* <disk address> type */
|
|
typedef __u32 xfs_dev_t;
|
|
typedef __u32 xfs_nlink_t;
|
|
|
|
#include "xfs_types.h"
|
|
|
|
#include "kmem.h"
|
|
#include "mrlock.h"
|
|
|
|
#include <linux/semaphore.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/sched/mm.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/blkdev.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/crc32c.h>
|
|
#include <linux/module.h>
|
|
#include <linux/mutex.h>
|
|
#include <linux/file.h>
|
|
#include <linux/filelock.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/errno.h>
|
|
#include <linux/sched/signal.h>
|
|
#include <linux/bitops.h>
|
|
#include <linux/major.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/vfs.h>
|
|
#include <linux/seq_file.h>
|
|
#include <linux/init.h>
|
|
#include <linux/list.h>
|
|
#include <linux/proc_fs.h>
|
|
#include <linux/sort.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/delay.h>
|
|
#include <linux/log2.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/random.h>
|
|
#include <linux/ctype.h>
|
|
#include <linux/writeback.h>
|
|
#include <linux/capability.h>
|
|
#include <linux/kthread.h>
|
|
#include <linux/freezer.h>
|
|
#include <linux/list_sort.h>
|
|
#include <linux/ratelimit.h>
|
|
#include <linux/rhashtable.h>
|
|
#include <linux/xattr.h>
|
|
#include <linux/mnt_idmapping.h>
|
|
|
|
#include <asm/page.h>
|
|
#include <asm/div64.h>
|
|
#include <asm/param.h>
|
|
#include <linux/uaccess.h>
|
|
#include <asm/byteorder.h>
|
|
#include <asm/unaligned.h>
|
|
|
|
#include "xfs_fs.h"
|
|
#include "xfs_stats.h"
|
|
#include "xfs_sysctl.h"
|
|
#include "xfs_iops.h"
|
|
#include "xfs_aops.h"
|
|
#include "xfs_super.h"
|
|
#include "xfs_cksum.h"
|
|
#include "xfs_buf.h"
|
|
#include "xfs_message.h"
|
|
#include "xfs_drain.h"
|
|
|
|
#ifdef __BIG_ENDIAN
|
|
#define XFS_NATIVE_HOST 1
|
|
#else
|
|
#undef XFS_NATIVE_HOST
|
|
#endif
|
|
|
|
#define irix_sgid_inherit xfs_params.sgid_inherit.val
|
|
#define irix_symlink_mode xfs_params.symlink_mode.val
|
|
#define xfs_panic_mask xfs_params.panic_mask.val
|
|
#define xfs_error_level xfs_params.error_level.val
|
|
#define xfs_syncd_centisecs xfs_params.syncd_timer.val
|
|
#define xfs_stats_clear xfs_params.stats_clear.val
|
|
#define xfs_inherit_sync xfs_params.inherit_sync.val
|
|
#define xfs_inherit_nodump xfs_params.inherit_nodump.val
|
|
#define xfs_inherit_noatime xfs_params.inherit_noatim.val
|
|
#define xfs_inherit_nosymlinks xfs_params.inherit_nosym.val
|
|
#define xfs_rotorstep xfs_params.rotorstep.val
|
|
#define xfs_inherit_nodefrag xfs_params.inherit_nodfrg.val
|
|
#define xfs_fstrm_centisecs xfs_params.fstrm_timer.val
|
|
#define xfs_blockgc_secs xfs_params.blockgc_timer.val
|
|
|
|
#define current_cpu() (raw_smp_processor_id())
|
|
#define current_set_flags_nested(sp, f) \
|
|
(*(sp) = current->flags, current->flags |= (f))
|
|
#define current_restore_flags_nested(sp, f) \
|
|
(current->flags = ((current->flags & ~(f)) | (*(sp) & (f))))
|
|
|
|
#define NBBY 8 /* number of bits per byte */
|
|
|
|
/*
|
|
* Size of block device i/o is parameterized here.
|
|
* Currently the system supports page-sized i/o.
|
|
*/
|
|
#define BLKDEV_IOSHIFT PAGE_SHIFT
|
|
#define BLKDEV_IOSIZE (1<<BLKDEV_IOSHIFT)
|
|
/* number of BB's per block device block */
|
|
#define BLKDEV_BB BTOBB(BLKDEV_IOSIZE)
|
|
|
|
#define ENOATTR ENODATA /* Attribute not found */
|
|
#define EWRONGFS EINVAL /* Mount with wrong filesystem type */
|
|
#define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */
|
|
#define EFSBADCRC EBADMSG /* Bad CRC detected */
|
|
|
|
#define __return_address __builtin_return_address(0)
|
|
|
|
/*
|
|
* Return the address of a label. Use barrier() so that the optimizer
|
|
* won't reorder code to refactor the error jumpouts into a single
|
|
* return, which throws off the reported address.
|
|
*/
|
|
#define __this_address ({ __label__ __here; __here: barrier(); &&__here; })
|
|
|
|
#define XFS_PROJID_DEFAULT 0
|
|
|
|
#define howmany(x, y) (((x)+((y)-1))/(y))
|
|
|
|
static inline void delay(long ticks)
|
|
{
|
|
schedule_timeout_uninterruptible(ticks);
|
|
}
|
|
|
|
/*
|
|
* XFS wrapper structure for sysfs support. It depends on external data
|
|
* structures and is embedded in various internal data structures to implement
|
|
* the XFS sysfs object heirarchy. Define it here for broad access throughout
|
|
* the codebase.
|
|
*/
|
|
struct xfs_kobj {
|
|
struct kobject kobject;
|
|
struct completion complete;
|
|
};
|
|
|
|
struct xstats {
|
|
struct xfsstats __percpu *xs_stats;
|
|
struct xfs_kobj xs_kobj;
|
|
};
|
|
|
|
extern struct xstats xfsstats;
|
|
|
|
static inline dev_t xfs_to_linux_dev_t(xfs_dev_t dev)
|
|
{
|
|
return MKDEV(sysv_major(dev) & 0x1ff, sysv_minor(dev));
|
|
}
|
|
|
|
static inline xfs_dev_t linux_to_xfs_dev_t(dev_t dev)
|
|
{
|
|
return sysv_encode_dev(dev);
|
|
}
|
|
|
|
/*
|
|
* Various platform dependent calls that don't fit anywhere else
|
|
*/
|
|
#define xfs_sort(a,n,s,fn) sort(a,n,s,fn,NULL)
|
|
#define xfs_stack_trace() dump_stack()
|
|
|
|
static inline uint64_t rounddown_64(uint64_t x, uint32_t y)
|
|
{
|
|
do_div(x, y);
|
|
return x * y;
|
|
}
|
|
|
|
static inline uint64_t roundup_64(uint64_t x, uint32_t y)
|
|
{
|
|
x += y - 1;
|
|
do_div(x, y);
|
|
return x * y;
|
|
}
|
|
|
|
static inline uint64_t howmany_64(uint64_t x, uint32_t y)
|
|
{
|
|
x += y - 1;
|
|
do_div(x, y);
|
|
return x;
|
|
}
|
|
|
|
int xfs_rw_bdev(struct block_device *bdev, sector_t sector, unsigned int count,
|
|
char *data, enum req_op op);
|
|
|
|
#define ASSERT_ALWAYS(expr) \
|
|
(likely(expr) ? (void)0 : assfail(NULL, #expr, __FILE__, __LINE__))
|
|
|
|
#ifdef DEBUG
|
|
#define ASSERT(expr) \
|
|
(likely(expr) ? (void)0 : assfail(NULL, #expr, __FILE__, __LINE__))
|
|
|
|
#else /* !DEBUG */
|
|
|
|
#ifdef XFS_WARN
|
|
|
|
#define ASSERT(expr) \
|
|
(likely(expr) ? (void)0 : asswarn(NULL, #expr, __FILE__, __LINE__))
|
|
|
|
#else /* !DEBUG && !XFS_WARN */
|
|
|
|
#define ASSERT(expr) ((void)0)
|
|
|
|
#endif /* XFS_WARN */
|
|
#endif /* DEBUG */
|
|
|
|
#define XFS_IS_CORRUPT(mp, expr) \
|
|
(unlikely(expr) ? xfs_corruption_error(#expr, XFS_ERRLEVEL_LOW, (mp), \
|
|
NULL, 0, __FILE__, __LINE__, \
|
|
__this_address), \
|
|
true : false)
|
|
|
|
#define STATIC static noinline
|
|
|
|
#ifdef CONFIG_XFS_RT
|
|
|
|
/*
|
|
* make sure we ignore the inode flag if the filesystem doesn't have a
|
|
* configured realtime device.
|
|
*/
|
|
#define XFS_IS_REALTIME_INODE(ip) \
|
|
(((ip)->i_diflags & XFS_DIFLAG_REALTIME) && \
|
|
(ip)->i_mount->m_rtdev_targp)
|
|
#define XFS_IS_REALTIME_MOUNT(mp) ((mp)->m_rtdev_targp ? 1 : 0)
|
|
#else
|
|
#define XFS_IS_REALTIME_INODE(ip) (0)
|
|
#define XFS_IS_REALTIME_MOUNT(mp) (0)
|
|
#endif
|
|
|
|
/*
|
|
* Starting in Linux 4.15, the %p (raw pointer value) printk modifier
|
|
* prints a hashed version of the pointer to avoid leaking kernel
|
|
* pointers into dmesg. If we're trying to debug the kernel we want the
|
|
* raw values, so override this behavior as best we can.
|
|
*/
|
|
#ifdef DEBUG
|
|
# define PTR_FMT "%px"
|
|
#else
|
|
# define PTR_FMT "%p"
|
|
#endif
|
|
|
|
#endif /* __XFS_LINUX__ */
|