From e636c8d336489bf3eed5878299e6cc045bbad077 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:17:29 +0000
Subject: [PATCH] debug lk
---
kernel/fs/xfs/xfs_mount.h | 241 ++++++++++++++++++++++++------------------------
1 files changed, 120 insertions(+), 121 deletions(-)
diff --git a/kernel/fs/xfs/xfs_mount.h b/kernel/fs/xfs/xfs_mount.h
index 7e0bf95..3a6bc9d 100644
--- a/kernel/fs/xfs/xfs_mount.h
+++ b/kernel/fs/xfs/xfs_mount.h
@@ -9,10 +9,8 @@
struct xlog;
struct xfs_inode;
struct xfs_mru_cache;
-struct xfs_nameops;
struct xfs_ail;
struct xfs_quotainfo;
-struct xfs_dir_ops;
struct xfs_da_geometry;
/* dynamic preallocation free space thresholds, 5% down to 1% */
@@ -57,38 +55,25 @@
long retry_timeout; /* in jiffies, -1 = infinite */
};
+/*
+ * The struct xfsmount layout is optimised to separate read-mostly variables
+ * from variables that are frequently modified. We put the read-mostly variables
+ * first, then place all the other variables at the end.
+ *
+ * Typically, read-mostly variables are those that are set at mount time and
+ * never changed again, or only change rarely as a result of things like sysfs
+ * knobs being tweaked.
+ */
typedef struct xfs_mount {
- struct super_block *m_super;
- xfs_tid_t m_tid; /* next unused tid for fs */
- struct xfs_ail *m_ail; /* fs active log item list */
-
struct xfs_sb m_sb; /* copy of fs superblock */
- spinlock_t m_sb_lock; /* sb counter lock */
- struct percpu_counter m_icount; /* allocated inodes counter */
- struct percpu_counter m_ifree; /* free inodes counter */
- struct percpu_counter m_fdblocks; /* free block counter */
-
+ struct super_block *m_super;
+ struct xfs_ail *m_ail; /* fs active log item list */
struct xfs_buf *m_sb_bp; /* buffer for superblock */
- char *m_fsname; /* filesystem name */
- int m_fsname_len; /* strlen of fs name */
char *m_rtname; /* realtime device name */
char *m_logname; /* external log device name */
- int m_bsize; /* fs logical block size */
- xfs_agnumber_t m_agfrotor; /* last ag where space found */
- xfs_agnumber_t m_agirotor; /* last ag dir inode alloced */
- spinlock_t m_agirotor_lock;/* .. and lock protecting it */
- xfs_agnumber_t m_maxagi; /* highest inode alloc group */
- uint m_readio_log; /* min read size log bytes */
- uint m_readio_blocks; /* min read size blocks */
- uint m_writeio_log; /* min write size log bytes */
- uint m_writeio_blocks; /* min write size blocks */
struct xfs_da_geometry *m_dir_geo; /* directory block geometry */
struct xfs_da_geometry *m_attr_geo; /* attribute block geometry */
struct xlog *m_log; /* log specific stuff */
- int m_logbufs; /* number of log buffers */
- int m_logbsize; /* size of each log buffer */
- uint m_rsumlevels; /* rt summary levels */
- uint m_rsumsize; /* size of rt summary, bytes */
struct xfs_inode *m_rbmip; /* pointer to bitmap inode */
struct xfs_inode *m_rsumip; /* pointer to summary inode */
struct xfs_inode *m_rootip; /* pointer to root directory */
@@ -96,11 +81,26 @@
xfs_buftarg_t *m_ddev_targp; /* saves taking the address */
xfs_buftarg_t *m_logdev_targp;/* ptr to log device */
xfs_buftarg_t *m_rtdev_targp; /* ptr to rt device */
+ /*
+ * Optional cache of rt summary level per bitmap block with the
+ * invariant that m_rsum_cache[bbno] <= the minimum i for which
+ * rsum[i][bbno] != 0. Reads and writes are serialized by the rsumip
+ * inode lock.
+ */
+ uint8_t *m_rsum_cache;
+ struct xfs_mru_cache *m_filestream; /* per-mount filestream data */
+ struct workqueue_struct *m_buf_workqueue;
+ struct workqueue_struct *m_unwritten_workqueue;
+ struct workqueue_struct *m_cil_workqueue;
+ struct workqueue_struct *m_reclaim_workqueue;
+ struct workqueue_struct *m_eofblocks_workqueue;
+ struct workqueue_struct *m_sync_workqueue;
+
+ int m_bsize; /* fs logical block size */
uint8_t m_blkbit_log; /* blocklog + NBBY */
uint8_t m_blkbb_log; /* blocklog - BBSHIFT */
uint8_t m_agno_log; /* log #ag's */
- uint8_t m_agino_log; /* #bits for agino in inum */
- uint m_inode_cluster_size;/* min inode buf size */
+ uint8_t m_sectbb_log; /* sectlog - BBSHIFT */
uint m_blockmask; /* sb_blocksize-1 */
uint m_blockwsize; /* sb_blocksize in words */
uint m_blockwmask; /* blockwsize-1 */
@@ -108,69 +108,93 @@
uint m_alloc_mnr[2]; /* min alloc btree records */
uint m_bmap_dmxr[2]; /* max bmap btree records */
uint m_bmap_dmnr[2]; /* min bmap btree records */
- uint m_inobt_mxr[2]; /* max inobt btree records */
- uint m_inobt_mnr[2]; /* min inobt btree records */
uint m_rmap_mxr[2]; /* max rmap btree records */
uint m_rmap_mnr[2]; /* min rmap btree records */
uint m_refc_mxr[2]; /* max refc btree records */
uint m_refc_mnr[2]; /* min refc btree records */
uint m_ag_maxlevels; /* XFS_AG_MAXLEVELS */
uint m_bm_maxlevels[2]; /* XFS_BM_MAXLEVELS */
- uint m_in_maxlevels; /* max inobt btree levels. */
uint m_rmap_maxlevels; /* max rmap btree levels */
uint m_refc_maxlevels; /* max refcount btree level */
xfs_extlen_t m_ag_prealloc_blocks; /* reserved ag blocks */
uint m_alloc_set_aside; /* space we can't use */
uint m_ag_max_usable; /* max space per AG */
+ int m_dalign; /* stripe unit */
+ int m_swidth; /* stripe width */
+ xfs_agnumber_t m_maxagi; /* highest inode alloc group */
+ uint m_allocsize_log;/* min write size log bytes */
+ uint m_allocsize_blocks; /* min write size blocks */
+ int m_logbufs; /* number of log buffers */
+ int m_logbsize; /* size of each log buffer */
+ uint m_rsumlevels; /* rt summary levels */
+ uint m_rsumsize; /* size of rt summary, bytes */
+ int m_fixedfsid[2]; /* unchanged for life of FS */
+ uint m_qflags; /* quota status flags */
+ uint64_t m_flags; /* global mount flags */
+ int64_t m_low_space[XFS_LOWSP_MAX];
+ struct xfs_ino_geometry m_ino_geo; /* inode geometry */
+ struct xfs_trans_resv m_resv; /* precomputed res values */
+ /* low free space thresholds */
+ bool m_always_cow;
+ bool m_fail_unmount;
+ bool m_finobt_nores; /* no per-AG finobt resv. */
+ bool m_update_sb; /* sb needs update in mount */
+
+ /*
+ * Bitsets of per-fs metadata that have been checked and/or are sick.
+ * Callers must hold m_sb_lock to access these two fields.
+ */
+ uint8_t m_fs_checked;
+ uint8_t m_fs_sick;
+ /*
+ * Bitsets of rt metadata that have been checked and/or are sick.
+ * Callers must hold m_sb_lock to access this field.
+ */
+ uint8_t m_rt_checked;
+ uint8_t m_rt_sick;
+
+ /*
+ * End of read-mostly variables. Frequently written variables and locks
+ * should be placed below this comment from now on. The first variable
+ * here is marked as cacheline aligned so they it is separated from
+ * the read-mostly variables.
+ */
+
+ spinlock_t ____cacheline_aligned m_sb_lock; /* sb counter lock */
+ struct percpu_counter m_icount; /* allocated inodes counter */
+ struct percpu_counter m_ifree; /* free inodes counter */
+ struct percpu_counter m_fdblocks; /* free block counter */
+ /*
+ * Count of data device blocks reserved for delayed allocations,
+ * including indlen blocks. Does not include allocated CoW staging
+ * extents or anything related to the rt device.
+ */
+ struct percpu_counter m_delalloc_blks;
+
struct radix_tree_root m_perag_tree; /* per-ag accounting info */
spinlock_t m_perag_lock; /* lock for m_perag_tree */
- struct mutex m_growlock; /* growfs mutex */
- int m_fixedfsid[2]; /* unchanged for life of FS */
- uint64_t m_flags; /* global mount flags */
- bool m_finobt_nores; /* no per-AG finobt resv. */
- int m_ialloc_inos; /* inodes in inode allocation */
- int m_ialloc_blks; /* blocks in inode allocation */
- int m_ialloc_min_blks;/* min blocks in sparse inode
- * allocation */
- int m_inoalign_mask;/* mask sb_inoalignmt if used */
- uint m_qflags; /* quota status flags */
- struct xfs_trans_resv m_resv; /* precomputed res values */
- uint64_t m_maxicount; /* maximum inode count */
uint64_t m_resblks; /* total reserved blocks */
uint64_t m_resblks_avail;/* available reserved blocks */
uint64_t m_resblks_save; /* reserved blks @ remount,ro */
- int m_dalign; /* stripe unit */
- int m_swidth; /* stripe width */
- int m_sinoalign; /* stripe unit inode alignment */
- uint8_t m_sectbb_log; /* sectlog - BBSHIFT */
- const struct xfs_nameops *m_dirnameops; /* vector of dir name ops */
- const struct xfs_dir_ops *m_dir_inode_ops; /* vector of dir inode ops */
- const struct xfs_dir_ops *m_nondir_inode_ops; /* !dir inode ops */
- uint m_chsize; /* size of next field */
- atomic_t m_active_trans; /* number trans frozen */
- struct xfs_mru_cache *m_filestream; /* per-mount filestream data */
struct delayed_work m_reclaim_work; /* background inode reclaim */
struct delayed_work m_eofblocks_work; /* background eof blocks
trimming */
struct delayed_work m_cowblocks_work; /* background cow blocks
trimming */
- bool m_update_sb; /* sb needs update in mount */
- int64_t m_low_space[XFS_LOWSP_MAX];
- /* low free space thresholds */
struct xfs_kobj m_kobj;
struct xfs_kobj m_error_kobj;
struct xfs_kobj m_error_meta_kobj;
struct xfs_error_cfg m_error_cfg[XFS_ERR_CLASS_MAX][XFS_ERR_ERRNO_MAX];
struct xstats m_stats; /* per-fs stats */
+ xfs_agnumber_t m_agfrotor; /* last ag where space found */
+ xfs_agnumber_t m_agirotor; /* last ag dir inode alloced */
+ spinlock_t m_agirotor_lock;/* .. and lock protecting it */
- struct workqueue_struct *m_buf_workqueue;
- struct workqueue_struct *m_data_workqueue;
- struct workqueue_struct *m_unwritten_workqueue;
- struct workqueue_struct *m_cil_workqueue;
- struct workqueue_struct *m_reclaim_workqueue;
- struct workqueue_struct *m_log_workqueue;
- struct workqueue_struct *m_eofblocks_workqueue;
- struct workqueue_struct *m_sync_workqueue;
+ /*
+ * Workqueue item so that we can coalesce multiple inode flush attempts
+ * into a single flush.
+ */
+ struct work_struct m_flush_inodes_work;
/*
* Generation of the filesysyem layout. This is incremented by each
@@ -182,8 +206,8 @@
* to various other kinds of pain inflicted on the pNFS server.
*/
uint32_t m_generation;
+ struct mutex m_growlock; /* growfs mutex */
- bool m_fail_unmount;
#ifdef DEBUG
/*
* Frequency with which errors are injected. Replaces xfs_etest; the
@@ -195,6 +219,8 @@
#endif
} xfs_mount_t;
+#define M_IGEO(mp) (&(mp)->m_ino_geo)
+
/*
* Flags for m_flags.
*/
@@ -202,7 +228,6 @@
must be synchronous except
for space allocations */
#define XFS_MOUNT_UNMOUNTING (1ULL << 1) /* filesystem is unmounting */
-#define XFS_MOUNT_BAD_SUMMARY (1ULL << 2) /* summary counters are bad */
#define XFS_MOUNT_WAS_CLEAN (1ULL << 3)
#define XFS_MOUNT_FS_SHUTDOWN (1ULL << 4) /* atomic stop of all filesystem
operations, typically for
@@ -213,7 +238,7 @@
#define XFS_MOUNT_ATTR2 (1ULL << 8) /* allow use of attr2 format */
#define XFS_MOUNT_GRPID (1ULL << 9) /* group-ID assigned from directory */
#define XFS_MOUNT_NORECOVERY (1ULL << 10) /* no recovery - dirty fs */
-#define XFS_MOUNT_DFLT_IOSIZE (1ULL << 12) /* set default i/o size */
+#define XFS_MOUNT_ALLOCSIZE (1ULL << 12) /* specified allocation size */
#define XFS_MOUNT_SMALL_INUMS (1ULL << 14) /* user wants 32bit inodes */
#define XFS_MOUNT_32BITINODES (1ULL << 15) /* inode32 allocator active */
#define XFS_MOUNT_NOUUID (1ULL << 16) /* ignore uuid during mount */
@@ -222,20 +247,13 @@
* allocation */
#define XFS_MOUNT_RDONLY (1ULL << 20) /* read-only fs */
#define XFS_MOUNT_DIRSYNC (1ULL << 21) /* synchronous directory ops */
-#define XFS_MOUNT_COMPAT_IOSIZE (1ULL << 22) /* don't report large preferred
+#define XFS_MOUNT_LARGEIO (1ULL << 22) /* report large preferred
* I/O size in stat() */
#define XFS_MOUNT_FILESTREAMS (1ULL << 24) /* enable the filestreams
allocator */
#define XFS_MOUNT_NOATTR2 (1ULL << 25) /* disable use of attr2 format */
-
-#define XFS_MOUNT_DAX (1ULL << 62) /* TEST ONLY! */
-
-
-/*
- * Default minimum read and write sizes.
- */
-#define XFS_READIO_LOG_LARGE 16
-#define XFS_WRITEIO_LOG_LARGE 16
+#define XFS_MOUNT_DAX_ALWAYS (1ULL << 26)
+#define XFS_MOUNT_DAX_NEVER (1ULL << 27)
/*
* Max and min values for mount-option defined I/O
@@ -243,37 +261,6 @@
*/
#define XFS_MAX_IO_LOG 30 /* 1G */
#define XFS_MIN_IO_LOG PAGE_SHIFT
-
-/*
- * Synchronous read and write sizes. This should be
- * better for NFSv2 wsync filesystems.
- */
-#define XFS_WSYNC_READIO_LOG 15 /* 32k */
-#define XFS_WSYNC_WRITEIO_LOG 14 /* 16k */
-
-/*
- * Allow large block sizes to be reported to userspace programs if the
- * "largeio" mount option is used.
- *
- * If compatibility mode is specified, simply return the basic unit of caching
- * so that we don't get inefficient read/modify/write I/O from user apps.
- * Otherwise....
- *
- * If the underlying volume is a stripe, then return the stripe width in bytes
- * as the recommended I/O size. It is not a stripe and we've set a default
- * buffered I/O size, return that, otherwise return the compat default.
- */
-static inline unsigned long
-xfs_preferred_iosize(xfs_mount_t *mp)
-{
- if (mp->m_flags & XFS_MOUNT_COMPAT_IOSIZE)
- return PAGE_SIZE;
- return (mp->m_swidth ?
- (mp->m_swidth << mp->m_sb.sb_blocklog) :
- ((mp->m_flags & XFS_MOUNT_DFLT_IOSIZE) ?
- (1 << (int)max(mp->m_readio_log, mp->m_writeio_log)) :
- PAGE_SIZE));
-}
#define XFS_LAST_UNMOUNT_WAS_CLEAN(mp) \
((mp)->m_flags & XFS_MOUNT_WAS_CLEAN)
@@ -287,8 +274,6 @@
#define SHUTDOWN_LOG_IO_ERROR 0x0002 /* write attempt to the log failed */
#define SHUTDOWN_FORCE_UMOUNT 0x0004 /* shutdown from a forced unmount */
#define SHUTDOWN_CORRUPT_INCORE 0x0008 /* corrupt in-memory data structures */
-#define SHUTDOWN_REMOTE_REQ 0x0010 /* shutdown came from remote cell */
-#define SHUTDOWN_DEVICE_REQ 0x0020 /* failed all paths to the device */
/*
* Flags for xfs_mountfs
@@ -311,13 +296,6 @@
}
/* per-AG block reservation data structures*/
-enum xfs_ag_resv_type {
- XFS_AG_RESV_NONE = 0,
- XFS_AG_RESV_AGFL,
- XFS_AG_RESV_METADATA,
- XFS_AG_RESV_RMAPBT,
-};
-
struct xfs_ag_resv {
/* number of blocks originally reserved here */
xfs_extlen_t ar_orig_reserved;
@@ -357,6 +335,15 @@
xfs_agino_t pagl_pagino;
xfs_agino_t pagl_leftrec;
xfs_agino_t pagl_rightrec;
+
+ /*
+ * Bitsets of per-ag metadata that have been checked and/or are sick.
+ * Callers should hold pag_state_lock before accessing this field.
+ */
+ uint16_t pag_checked;
+ uint16_t pag_sick;
+ spinlock_t pag_state_lock;
+
spinlock_t pagb_lock; /* lock for pagb_tree */
struct rb_root pagb_tree; /* ordered tree of busy extents */
unsigned int pagb_gen; /* generation count for pagb_tree */
@@ -367,7 +354,6 @@
spinlock_t pag_ici_lock; /* incore inode cache lock */
struct radix_tree_root pag_ici_root; /* incore inode cache root */
int pag_ici_reclaimable; /* reclaimable inodes */
- struct mutex pag_ici_reclaim_lock; /* serialisation point */
unsigned long pag_ici_reclaim_cursor; /* reclaim restart point */
/* buffer cache index */
@@ -385,6 +371,13 @@
/* reference count */
uint8_t pagf_refcount_level;
+
+ /*
+ * Unlinked inode information. This incore information reflects
+ * data stored in the AGI, so callers must hold the AGI buffer lock
+ * or have some other means to control concurrency.
+ */
+ struct rhashtable pagi_unlinked_hash;
} xfs_perag_t;
static inline struct xfs_ag_resv *
@@ -413,13 +406,18 @@
xfs_agnumber_t *maxagi);
extern void xfs_unmountfs(xfs_mount_t *);
-extern int xfs_mod_icount(struct xfs_mount *mp, int64_t delta);
-extern int xfs_mod_ifree(struct xfs_mount *mp, int64_t delta);
+/* Accessor added for 5.10.y backport */
+static inline uint64_t
+xfs_fdblocks_unavailable(
+ struct xfs_mount *mp)
+{
+ return mp->m_alloc_set_aside;
+}
+
extern int xfs_mod_fdblocks(struct xfs_mount *mp, int64_t delta,
bool reserved);
extern int xfs_mod_frextents(struct xfs_mount *mp, int64_t delta);
-extern struct xfs_buf *xfs_getsb(xfs_mount_t *, int);
extern int xfs_readsb(xfs_mount_t *, int);
extern void xfs_freesb(xfs_mount_t *);
extern bool xfs_fs_writable(struct xfs_mount *mp, int level);
@@ -435,5 +433,6 @@
struct xfs_error_cfg * xfs_error_get_cfg(struct xfs_mount *mp,
int error_class, int error);
void xfs_force_summary_recalc(struct xfs_mount *mp);
+void xfs_mod_delalloc(struct xfs_mount *mp, int64_t delta);
#endif /* __XFS_MOUNT_H__ */
--
Gitblit v1.6.2