2018-06-06 10:42:14 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
2005-11-02 11:58:39 +08:00
|
|
|
* Copyright (c) 2000-2005 Silicon Graphics, Inc.
|
|
|
|
* All Rights Reserved.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
|
|
|
#ifndef __XFS_LINUX__
|
|
|
|
#define __XFS_LINUX__
|
|
|
|
|
|
|
|
#include <linux/types.h>
|
2017-05-05 15:53:09 +08:00
|
|
|
#include <linux/uuid.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2013-08-12 18:49:54 +08:00
|
|
|
/*
|
|
|
|
* 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;
|
|
|
|
|
2011-08-13 02:57:55 +08:00
|
|
|
#include "xfs_types.h"
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2011-08-13 02:57:55 +08:00
|
|
|
#include "kmem.h"
|
|
|
|
#include "mrlock.h"
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-08-13 14:42:10 +08:00
|
|
|
#include <linux/semaphore.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/mm.h>
|
2018-06-07 22:46:42 +08:00
|
|
|
#include <linux/sched/mm.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/blkdev.h>
|
|
|
|
#include <linux/slab.h>
|
2012-11-16 06:20:37 +08:00
|
|
|
#include <linux/crc32c.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/module.h>
|
2009-03-29 15:51:00 +08:00
|
|
|
#include <linux/mutex.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/file.h>
|
2022-11-20 22:15:34 +08:00
|
|
|
#include <linux/filelock.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/swap.h>
|
|
|
|
#include <linux/errno.h>
|
2017-02-03 02:15:33 +08:00
|
|
|
#include <linux/sched/signal.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#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>
|
2006-03-14 10:23:52 +08:00
|
|
|
#include <linux/cpu.h>
|
|
|
|
#include <linux/notifier.h>
|
2006-03-14 10:29:16 +08:00
|
|
|
#include <linux/delay.h>
|
2007-08-16 14:25:23 +08:00
|
|
|
#include <linux/log2.h>
|
2007-10-11 15:43:56 +08:00
|
|
|
#include <linux/spinlock.h>
|
2008-04-30 15:11:16 +08:00
|
|
|
#include <linux/random.h>
|
2008-05-21 14:58:55 +08:00
|
|
|
#include <linux/ctype.h>
|
2008-10-30 15:32:43 +08:00
|
|
|
#include <linux/writeback.h>
|
2010-10-07 02:41:17 +08:00
|
|
|
#include <linux/capability.h>
|
2011-10-11 23:14:10 +08:00
|
|
|
#include <linux/kthread.h>
|
|
|
|
#include <linux/freezer.h>
|
2011-04-25 03:06:17 +08:00
|
|
|
#include <linux/list_sort.h>
|
2013-03-27 22:26:49 +08:00
|
|
|
#include <linux/ratelimit.h>
|
2016-12-07 14:36:36 +08:00
|
|
|
#include <linux/rhashtable.h>
|
2020-02-27 09:30:42 +08:00
|
|
|
#include <linux/xattr.h>
|
2021-12-03 19:16:59 +08:00
|
|
|
#include <linux/mnt_idmapping.h>
|
2023-08-10 22:48:07 +08:00
|
|
|
#include <linux/debugfs.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#include <asm/page.h>
|
|
|
|
#include <asm/div64.h>
|
|
|
|
#include <asm/param.h>
|
2016-12-25 03:46:01 +08:00
|
|
|
#include <linux/uaccess.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <asm/byteorder.h>
|
|
|
|
#include <asm/unaligned.h>
|
|
|
|
|
2014-08-04 11:28:20 +08:00
|
|
|
#include "xfs_fs.h"
|
2011-08-13 02:57:55 +08:00
|
|
|
#include "xfs_stats.h"
|
|
|
|
#include "xfs_sysctl.h"
|
|
|
|
#include "xfs_iops.h"
|
|
|
|
#include "xfs_aops.h"
|
|
|
|
#include "xfs_super.h"
|
2014-02-27 12:17:27 +08:00
|
|
|
#include "xfs_cksum.h"
|
2011-08-13 02:57:55 +08:00
|
|
|
#include "xfs_buf.h"
|
|
|
|
#include "xfs_message.h"
|
xfs: allow queued AG intents to drain before scrubbing
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>
2023-04-12 09:59:58 +08:00
|
|
|
#include "xfs_drain.h"
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2011-07-08 20:35:58 +08:00
|
|
|
#ifdef __BIG_ENDIAN
|
|
|
|
#define XFS_NATIVE_HOST 1
|
|
|
|
#else
|
|
|
|
#undef XFS_NATIVE_HOST
|
|
|
|
#endif
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#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
|
2006-06-09 12:54:19 +08:00
|
|
|
#define xfs_inherit_nodefrag xfs_params.inherit_nodfrg.val
|
2007-07-11 09:09:12 +08:00
|
|
|
#define xfs_fstrm_centisecs xfs_params.fstrm_timer.val
|
2021-01-23 08:48:43 +08:00
|
|
|
#define xfs_blockgc_secs xfs_params.blockgc_timer.val
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-06-09 12:59:13 +08:00
|
|
|
#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))))
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#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.
|
|
|
|
*/
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
#define BLKDEV_IOSHIFT PAGE_SHIFT
|
2005-04-17 06:20:36 +08:00
|
|
|
#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 */
|
2006-06-20 11:01:38 +08:00
|
|
|
#define EWRONGFS EINVAL /* Mount with wrong filesystem type */
|
|
|
|
#define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */
|
2014-02-27 12:21:07 +08:00
|
|
|
#define EFSBADCRC EBADMSG /* Bad CRC detected */
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#define __return_address __builtin_return_address(0)
|
|
|
|
|
2017-10-18 12:37:33 +08:00
|
|
|
/*
|
|
|
|
* 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; })
|
|
|
|
|
2010-09-26 14:10:18 +08:00
|
|
|
#define XFS_PROJID_DEFAULT 0
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#define howmany(x, y) (((x)+((y)-1))/(y))
|
|
|
|
|
2014-10-02 07:18:13 +08:00
|
|
|
static inline void delay(long ticks)
|
|
|
|
{
|
|
|
|
schedule_timeout_uninterruptible(ticks);
|
|
|
|
}
|
|
|
|
|
2014-07-15 06:07:01 +08:00
|
|
|
/*
|
|
|
|
* 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;
|
|
|
|
};
|
|
|
|
|
2015-10-12 02:19:45 +08:00
|
|
|
struct xstats {
|
|
|
|
struct xfsstats __percpu *xs_stats;
|
|
|
|
struct xfs_kobj xs_kobj;
|
|
|
|
};
|
|
|
|
|
|
|
|
extern struct xstats xfsstats;
|
|
|
|
|
2017-11-21 00:56:52 +08:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2005-09-05 09:47:01 +08:00
|
|
|
/*
|
|
|
|
* Various platform dependent calls that don't fit anywhere else
|
|
|
|
*/
|
2005-11-02 08:43:18 +08:00
|
|
|
#define xfs_sort(a,n,s,fn) sort(a,n,s,fn,NULL)
|
2005-04-17 06:20:36 +08:00
|
|
|
#define xfs_stack_trace() dump_stack()
|
|
|
|
|
2020-10-10 07:42:59 +08:00
|
|
|
static inline uint64_t rounddown_64(uint64_t x, uint32_t y)
|
|
|
|
{
|
|
|
|
do_div(x, y);
|
|
|
|
return x * y;
|
|
|
|
}
|
|
|
|
|
2017-06-17 02:00:05 +08:00
|
|
|
static inline uint64_t roundup_64(uint64_t x, uint32_t y)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
x += y - 1;
|
|
|
|
do_div(x, y);
|
2014-06-22 13:03:54 +08:00
|
|
|
return x * y;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2017-06-17 02:00:05 +08:00
|
|
|
static inline uint64_t howmany_64(uint64_t x, uint32_t y)
|
2006-09-28 09:03:53 +08:00
|
|
|
{
|
|
|
|
x += y - 1;
|
|
|
|
do_div(x, y);
|
|
|
|
return x;
|
|
|
|
}
|
|
|
|
|
2019-06-29 10:27:26 +08:00
|
|
|
int xfs_rw_bdev(struct block_device *bdev, sector_t sector, unsigned int count,
|
2022-07-15 02:07:28 +08:00
|
|
|
char *data, enum req_op op);
|
2019-06-29 10:27:26 +08:00
|
|
|
|
2011-03-07 07:09:35 +08:00
|
|
|
#define ASSERT_ALWAYS(expr) \
|
2019-11-03 00:41:19 +08:00
|
|
|
(likely(expr) ? (void)0 : assfail(NULL, #expr, __FILE__, __LINE__))
|
2011-03-07 07:09:35 +08:00
|
|
|
|
2013-04-30 19:39:34 +08:00
|
|
|
#ifdef DEBUG
|
|
|
|
#define ASSERT(expr) \
|
2019-11-03 00:41:19 +08:00
|
|
|
(likely(expr) ? (void)0 : assfail(NULL, #expr, __FILE__, __LINE__))
|
2011-03-07 07:09:35 +08:00
|
|
|
|
2013-04-30 19:39:34 +08:00
|
|
|
#else /* !DEBUG */
|
|
|
|
|
|
|
|
#ifdef XFS_WARN
|
2011-03-07 07:09:35 +08:00
|
|
|
|
|
|
|
#define ASSERT(expr) \
|
2019-11-03 00:41:19 +08:00
|
|
|
(likely(expr) ? (void)0 : asswarn(NULL, #expr, __FILE__, __LINE__))
|
2011-03-07 07:09:35 +08:00
|
|
|
|
2013-04-30 19:39:34 +08:00
|
|
|
#else /* !DEBUG && !XFS_WARN */
|
|
|
|
|
2019-11-12 04:52:01 +08:00
|
|
|
#define ASSERT(expr) ((void)0)
|
2013-04-30 19:39:34 +08:00
|
|
|
|
|
|
|
#endif /* XFS_WARN */
|
2011-03-07 07:09:35 +08:00
|
|
|
#endif /* DEBUG */
|
|
|
|
|
2019-11-18 02:36:52 +08:00
|
|
|
#define XFS_IS_CORRUPT(mp, expr) \
|
|
|
|
(unlikely(expr) ? xfs_corruption_error(#expr, XFS_ERRLEVEL_LOW, (mp), \
|
|
|
|
NULL, 0, __FILE__, __LINE__, \
|
|
|
|
__this_address), \
|
|
|
|
true : false)
|
|
|
|
|
2017-11-07 03:53:58 +08:00
|
|
|
#define STATIC static noinline
|
|
|
|
|
2014-11-28 11:24:06 +08:00
|
|
|
#ifdef CONFIG_XFS_RT
|
2017-09-13 07:09:35 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* make sure we ignore the inode flag if the filesystem doesn't have a
|
|
|
|
* configured realtime device.
|
|
|
|
*/
|
|
|
|
#define XFS_IS_REALTIME_INODE(ip) \
|
2021-03-30 02:11:44 +08:00
|
|
|
(((ip)->i_diflags & XFS_DIFLAG_REALTIME) && \
|
2017-09-13 07:09:35 +08:00
|
|
|
(ip)->i_mount->m_rtdev_targp)
|
2018-01-09 02:41:33 +08:00
|
|
|
#define XFS_IS_REALTIME_MOUNT(mp) ((mp)->m_rtdev_targp ? 1 : 0)
|
2014-11-28 11:24:06 +08:00
|
|
|
#else
|
|
|
|
#define XFS_IS_REALTIME_INODE(ip) (0)
|
2018-01-09 02:41:33 +08:00
|
|
|
#define XFS_IS_REALTIME_MOUNT(mp) (0)
|
2014-11-28 11:24:06 +08:00
|
|
|
#endif
|
|
|
|
|
2018-01-10 04:02:55 +08:00
|
|
|
/*
|
|
|
|
* 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
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif /* __XFS_LINUX__ */
|