From: cem@kernel.org
To: linux-xfs@vger.kernel.org
Cc: djwong@kernel.org, hch@lst.de
Subject: [PATCH 40/67] xfs: repair inode fork block mapping data structures
Date: Mon, 22 Apr 2024 18:26:02 +0200 [thread overview]
Message-ID: <20240422163832.858420-42-cem@kernel.org> (raw)
In-Reply-To: <20240422163832.858420-2-cem@kernel.org>
From: "Darrick J. Wong" <djwong@kernel.org>
Source kernel commit: 8f71bede8efd820627ac05c19eac2758214bc896
Use the reverse-mapping btree information to rebuild an inode block map.
Update the btree bulk loading code as necessary to support inode rooted
btrees and fix some bitrot problems.
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
libxfs/xfs_bmap_btree.c | 121 +++++++++++++++++++++++++++++++------
libxfs/xfs_bmap_btree.h | 5 ++
libxfs/xfs_btree_staging.c | 11 +++-
libxfs/xfs_btree_staging.h | 2 +-
libxfs/xfs_iext_tree.c | 23 ++++---
libxfs/xfs_inode_fork.c | 1 +
libxfs/xfs_inode_fork.h | 3 +
7 files changed, 136 insertions(+), 30 deletions(-)
diff --git a/libxfs/xfs_bmap_btree.c b/libxfs/xfs_bmap_btree.c
index c4d5c8a64..73ba067df 100644
--- a/libxfs/xfs_bmap_btree.c
+++ b/libxfs/xfs_bmap_btree.c
@@ -15,6 +15,7 @@
#include "xfs_trans.h"
#include "xfs_alloc.h"
#include "xfs_btree.h"
+#include "xfs_btree_staging.h"
#include "xfs_bmap_btree.h"
#include "xfs_bmap.h"
#include "xfs_trace.h"
@@ -286,10 +287,7 @@ xfs_bmbt_get_minrecs(
int level)
{
if (level == cur->bc_nlevels - 1) {
- struct xfs_ifork *ifp;
-
- ifp = xfs_ifork_ptr(cur->bc_ino.ip,
- cur->bc_ino.whichfork);
+ struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur);
return xfs_bmbt_maxrecs(cur->bc_mp,
ifp->if_broot_bytes, level == 0) / 2;
@@ -304,10 +302,7 @@ xfs_bmbt_get_maxrecs(
int level)
{
if (level == cur->bc_nlevels - 1) {
- struct xfs_ifork *ifp;
-
- ifp = xfs_ifork_ptr(cur->bc_ino.ip,
- cur->bc_ino.whichfork);
+ struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur);
return xfs_bmbt_maxrecs(cur->bc_mp,
ifp->if_broot_bytes, level == 0);
@@ -541,23 +536,19 @@ static const struct xfs_btree_ops xfs_bmbt_ops = {
.keys_contiguous = xfs_bmbt_keys_contiguous,
};
-/*
- * Allocate a new bmap btree cursor.
- */
-struct xfs_btree_cur * /* new bmap btree cursor */
-xfs_bmbt_init_cursor(
- struct xfs_mount *mp, /* file system mount point */
- struct xfs_trans *tp, /* transaction pointer */
- struct xfs_inode *ip, /* inode owning the btree */
- int whichfork) /* data or attr fork */
+static struct xfs_btree_cur *
+xfs_bmbt_init_common(
+ struct xfs_mount *mp,
+ struct xfs_trans *tp,
+ struct xfs_inode *ip,
+ int whichfork)
{
- struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_btree_cur *cur;
+
ASSERT(whichfork != XFS_COW_FORK);
cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_BMAP,
mp->m_bm_maxlevels[whichfork], xfs_bmbt_cur_cache);
- cur->bc_nlevels = be16_to_cpu(ifp->if_broot->bb_level) + 1;
cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_bmbt_2);
cur->bc_ops = &xfs_bmbt_ops;
@@ -565,10 +556,30 @@ xfs_bmbt_init_cursor(
if (xfs_has_crc(mp))
cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
- cur->bc_ino.forksize = xfs_inode_fork_size(ip, whichfork);
cur->bc_ino.ip = ip;
cur->bc_ino.allocated = 0;
cur->bc_ino.flags = 0;
+
+ return cur;
+}
+
+/*
+ * Allocate a new bmap btree cursor.
+ */
+struct xfs_btree_cur *
+xfs_bmbt_init_cursor(
+ struct xfs_mount *mp,
+ struct xfs_trans *tp,
+ struct xfs_inode *ip,
+ int whichfork)
+{
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
+ struct xfs_btree_cur *cur;
+
+ cur = xfs_bmbt_init_common(mp, tp, ip, whichfork);
+
+ cur->bc_nlevels = be16_to_cpu(ifp->if_broot->bb_level) + 1;
+ cur->bc_ino.forksize = xfs_inode_fork_size(ip, whichfork);
cur->bc_ino.whichfork = whichfork;
return cur;
@@ -585,6 +596,76 @@ xfs_bmbt_block_maxrecs(
return blocklen / (sizeof(xfs_bmbt_key_t) + sizeof(xfs_bmbt_ptr_t));
}
+/*
+ * Allocate a new bmap btree cursor for reloading an inode block mapping data
+ * structure. Note that callers can use the staged cursor to reload extents
+ * format inode forks if they rebuild the iext tree and commit the staged
+ * cursor immediately.
+ */
+struct xfs_btree_cur *
+xfs_bmbt_stage_cursor(
+ struct xfs_mount *mp,
+ struct xfs_inode *ip,
+ struct xbtree_ifakeroot *ifake)
+{
+ struct xfs_btree_cur *cur;
+ struct xfs_btree_ops *ops;
+
+ /* data fork always has larger maxheight */
+ cur = xfs_bmbt_init_common(mp, NULL, ip, XFS_DATA_FORK);
+ cur->bc_nlevels = ifake->if_levels;
+ cur->bc_ino.forksize = ifake->if_fork_size;
+
+ /* Don't let anyone think we're attached to the real fork yet. */
+ cur->bc_ino.whichfork = -1;
+ xfs_btree_stage_ifakeroot(cur, ifake, &ops);
+ ops->update_cursor = NULL;
+ return cur;
+}
+
+/*
+ * Swap in the new inode fork root. Once we pass this point the newly rebuilt
+ * mappings are in place and we have to kill off any old btree blocks.
+ */
+void
+xfs_bmbt_commit_staged_btree(
+ struct xfs_btree_cur *cur,
+ struct xfs_trans *tp,
+ int whichfork)
+{
+ struct xbtree_ifakeroot *ifake = cur->bc_ino.ifake;
+ struct xfs_ifork *ifp;
+ static const short brootflag[2] = {XFS_ILOG_DBROOT, XFS_ILOG_ABROOT};
+ static const short extflag[2] = {XFS_ILOG_DEXT, XFS_ILOG_AEXT};
+ int flags = XFS_ILOG_CORE;
+
+ ASSERT(cur->bc_flags & XFS_BTREE_STAGING);
+ ASSERT(whichfork != XFS_COW_FORK);
+
+ /*
+ * Free any resources hanging off the real fork, then shallow-copy the
+ * staging fork's contents into the real fork to transfer everything
+ * we just built.
+ */
+ ifp = xfs_ifork_ptr(cur->bc_ino.ip, whichfork);
+ xfs_idestroy_fork(ifp);
+ memcpy(ifp, ifake->if_fork, sizeof(struct xfs_ifork));
+
+ switch (ifp->if_format) {
+ case XFS_DINODE_FMT_EXTENTS:
+ flags |= extflag[whichfork];
+ break;
+ case XFS_DINODE_FMT_BTREE:
+ flags |= brootflag[whichfork];
+ break;
+ default:
+ ASSERT(0);
+ break;
+ }
+ xfs_trans_log_inode(tp, cur->bc_ino.ip, flags);
+ xfs_btree_commit_ifakeroot(cur, tp, whichfork, &xfs_bmbt_ops);
+}
+
/*
* Calculate number of records in a bmap btree block.
*/
diff --git a/libxfs/xfs_bmap_btree.h b/libxfs/xfs_bmap_btree.h
index 3e7a40a83..151b8491f 100644
--- a/libxfs/xfs_bmap_btree.h
+++ b/libxfs/xfs_bmap_btree.h
@@ -11,6 +11,7 @@ struct xfs_btree_block;
struct xfs_mount;
struct xfs_inode;
struct xfs_trans;
+struct xbtree_ifakeroot;
/*
* Btree block header size depends on a superblock flag.
@@ -106,6 +107,10 @@ extern int xfs_bmbt_change_owner(struct xfs_trans *tp, struct xfs_inode *ip,
extern struct xfs_btree_cur *xfs_bmbt_init_cursor(struct xfs_mount *,
struct xfs_trans *, struct xfs_inode *, int);
+struct xfs_btree_cur *xfs_bmbt_stage_cursor(struct xfs_mount *mp,
+ struct xfs_inode *ip, struct xbtree_ifakeroot *ifake);
+void xfs_bmbt_commit_staged_btree(struct xfs_btree_cur *cur,
+ struct xfs_trans *tp, int whichfork);
extern unsigned long long xfs_bmbt_calc_size(struct xfs_mount *mp,
unsigned long long len);
diff --git a/libxfs/xfs_btree_staging.c b/libxfs/xfs_btree_staging.c
index d4164e37b..0ea44dcf1 100644
--- a/libxfs/xfs_btree_staging.c
+++ b/libxfs/xfs_btree_staging.c
@@ -405,7 +405,7 @@ xfs_btree_bload_prep_block(
ASSERT(*bpp == NULL);
/* Allocate a new incore btree root block. */
- new_size = bbl->iroot_size(cur, nr_this_block, priv);
+ new_size = bbl->iroot_size(cur, level, nr_this_block, priv);
ifp->if_broot = kmem_zalloc(new_size, 0);
ifp->if_broot_bytes = (int)new_size;
@@ -596,7 +596,14 @@ xfs_btree_bload_level_geometry(
unsigned int desired_npb;
unsigned int maxnr;
- maxnr = cur->bc_ops->get_maxrecs(cur, level);
+ /*
+ * Compute the absolute maximum number of records that we can store in
+ * the ondisk block or inode root.
+ */
+ if (cur->bc_ops->get_dmaxrecs)
+ maxnr = cur->bc_ops->get_dmaxrecs(cur, level);
+ else
+ maxnr = cur->bc_ops->get_maxrecs(cur, level);
/*
* Compute the number of blocks we need to fill each block with the
diff --git a/libxfs/xfs_btree_staging.h b/libxfs/xfs_btree_staging.h
index f0a500728..055ea43b1 100644
--- a/libxfs/xfs_btree_staging.h
+++ b/libxfs/xfs_btree_staging.h
@@ -53,7 +53,7 @@ typedef int (*xfs_btree_bload_get_records_fn)(struct xfs_btree_cur *cur,
typedef int (*xfs_btree_bload_claim_block_fn)(struct xfs_btree_cur *cur,
union xfs_btree_ptr *ptr, void *priv);
typedef size_t (*xfs_btree_bload_iroot_size_fn)(struct xfs_btree_cur *cur,
- unsigned int nr_this_level, void *priv);
+ unsigned int level, unsigned int nr_this_level, void *priv);
struct xfs_btree_bload {
/*
diff --git a/libxfs/xfs_iext_tree.c b/libxfs/xfs_iext_tree.c
index 7f5c4f403..5d0be2dc8 100644
--- a/libxfs/xfs_iext_tree.c
+++ b/libxfs/xfs_iext_tree.c
@@ -622,13 +622,11 @@ static inline void xfs_iext_inc_seq(struct xfs_ifork *ifp)
}
void
-xfs_iext_insert(
- struct xfs_inode *ip,
+xfs_iext_insert_raw(
+ struct xfs_ifork *ifp,
struct xfs_iext_cursor *cur,
- struct xfs_bmbt_irec *irec,
- int state)
+ struct xfs_bmbt_irec *irec)
{
- struct xfs_ifork *ifp = xfs_iext_state_to_fork(ip, state);
xfs_fileoff_t offset = irec->br_startoff;
struct xfs_iext_leaf *new = NULL;
int nr_entries, i;
@@ -662,12 +660,23 @@ xfs_iext_insert(
xfs_iext_set(cur_rec(cur), irec);
ifp->if_bytes += sizeof(struct xfs_iext_rec);
- trace_xfs_iext_insert(ip, cur, state, _RET_IP_);
-
if (new)
xfs_iext_insert_node(ifp, xfs_iext_leaf_key(new, 0), new, 2);
}
+void
+xfs_iext_insert(
+ struct xfs_inode *ip,
+ struct xfs_iext_cursor *cur,
+ struct xfs_bmbt_irec *irec,
+ int state)
+{
+ struct xfs_ifork *ifp = xfs_iext_state_to_fork(ip, state);
+
+ xfs_iext_insert_raw(ifp, cur, irec);
+ trace_xfs_iext_insert(ip, cur, state, _RET_IP_);
+}
+
static struct xfs_iext_node *
xfs_iext_rebalance_node(
struct xfs_iext_node *parent,
diff --git a/libxfs/xfs_inode_fork.c b/libxfs/xfs_inode_fork.c
index 3e2d7882a..80f4215d2 100644
--- a/libxfs/xfs_inode_fork.c
+++ b/libxfs/xfs_inode_fork.c
@@ -518,6 +518,7 @@ xfs_idata_realloc(
ifp->if_bytes = new_size;
}
+/* Free all memory and reset a fork back to its initial state. */
void
xfs_idestroy_fork(
struct xfs_ifork *ifp)
diff --git a/libxfs/xfs_inode_fork.h b/libxfs/xfs_inode_fork.h
index 96d307784..535be5c03 100644
--- a/libxfs/xfs_inode_fork.h
+++ b/libxfs/xfs_inode_fork.h
@@ -180,6 +180,9 @@ void xfs_init_local_fork(struct xfs_inode *ip, int whichfork,
const void *data, int64_t size);
xfs_extnum_t xfs_iext_count(struct xfs_ifork *ifp);
+void xfs_iext_insert_raw(struct xfs_ifork *ifp,
+ struct xfs_iext_cursor *cur,
+ struct xfs_bmbt_irec *irec);
void xfs_iext_insert(struct xfs_inode *, struct xfs_iext_cursor *cur,
struct xfs_bmbt_irec *, int);
void xfs_iext_remove(struct xfs_inode *, struct xfs_iext_cursor *,
--
2.44.0
next prev parent reply other threads:[~2024-04-22 16:40 UTC|newest]
Thread overview: 71+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-04-22 16:25 [PATCH 00/67] libxfs: Sync to Linux 6.8 cem
2024-04-22 16:25 ` [PATCH 01/67] xfs: use xfs_defer_pending objects to recover intent items cem
2024-04-22 16:25 ` [PATCH 02/67] xfs: recreate work items when recovering " cem
2024-04-22 16:25 ` [PATCH 03/67] xfs: use xfs_defer_finish_one to finish recovered work items cem
2024-04-22 16:25 ` [PATCH 04/67] xfs: move ->iop_recover to xfs_defer_op_type cem
2024-04-22 16:25 ` [PATCH 05/67] xfs: hoist intent done flag setting to ->finish_item callsite cem
2024-04-22 16:25 ` [PATCH 06/67] xfs: hoist ->create_intent boilerplate to its callsite cem
2024-04-22 16:25 ` [PATCH 07/67] xfs: use xfs_defer_create_done for the relogging operation cem
2024-04-22 16:25 ` [PATCH 08/67] xfs: clean out XFS_LI_DIRTY setting boilerplate from ->iop_relog cem
2024-04-22 16:25 ` [PATCH 09/67] xfs: hoist xfs_trans_add_item calls to defer ops functions cem
2024-04-22 16:25 ` [PATCH 10/67] xfs: move ->iop_relog to struct xfs_defer_op_type cem
2024-04-22 16:25 ` [PATCH 11/67] xfs: make rextslog computation consistent with mkfs cem
2024-04-22 16:25 ` [PATCH 12/67] xfs: fix 32-bit truncation in xfs_compute_rextslog cem
2024-04-22 16:25 ` [PATCH 13/67] xfs: don't allow overly small or large realtime volumes cem
2024-04-22 16:25 ` [PATCH 14/67] xfs: elide ->create_done calls for unlogged deferred work cem
2024-04-22 16:25 ` [PATCH 15/67] xfs: don't append work items to logged xfs_defer_pending objects cem
2024-04-22 16:25 ` [PATCH 16/67] xfs: allow pausing of pending deferred work items cem
2024-04-22 16:25 ` [PATCH 17/67] xfs: remove __xfs_free_extent_later cem
2024-04-22 16:25 ` [PATCH 18/67] xfs: automatic freeing of freshly allocated unwritten space cem
2024-04-22 16:25 ` [PATCH 19/67] xfs: remove unused fields from struct xbtree_ifakeroot cem
2024-04-22 16:25 ` [PATCH 20/67] xfs: force small EFIs for reaping btree extents cem
2024-04-22 16:25 ` [PATCH 21/67] xfs: ensure logflagsp is initialized in xfs_bmap_del_extent_real cem
2024-04-22 16:25 ` [PATCH 22/67] xfs: update dir3 leaf block metadata after swap cem
2024-04-22 16:25 ` [PATCH 23/67] xfs: extract xfs_da_buf_copy() helper function cem
2024-04-22 16:25 ` [PATCH 24/67] xfs: move xfs_ondisk.h to libxfs/ cem
2024-04-22 16:25 ` [PATCH 25/67] xfs: consolidate the xfs_attr_defer_* helpers cem
2024-04-22 16:25 ` [PATCH 26/67] xfs: store an ops pointer in struct xfs_defer_pending cem
2024-04-22 16:25 ` [PATCH 27/67] xfs: pass the defer ops instead of type to xfs_defer_start_recovery cem
2024-04-22 16:25 ` [PATCH 28/67] xfs: pass the defer ops directly to xfs_defer_add cem
2024-04-22 16:25 ` [PATCH 29/67] xfs: force all buffers to be written during btree bulk load cem
2024-04-22 16:25 ` [PATCH 30/67] xfs: set XBF_DONE on newly formatted btree block that are ready for writing cem
2024-04-22 16:25 ` [PATCH 31/67] xfs: read leaf blocks when computing keys for bulkloading into node blocks cem
2024-04-22 16:25 ` [PATCH 32/67] xfs: move btree bulkload record initialization to ->get_record implementations cem
2024-04-22 16:25 ` [PATCH 33/67] xfs: constrain dirty buffers while formatting a staged btree cem
2024-04-22 16:25 ` [PATCH 34/67] xfs: repair free space btrees cem
2024-04-22 16:25 ` [PATCH 35/67] xfs: repair inode btrees cem
2024-04-22 16:25 ` [PATCH 36/67] xfs: repair refcount btrees cem
2024-04-22 16:25 ` [PATCH 37/67] xfs: dont cast to char * for XFS_DFORK_*PTR macros cem
2024-04-22 16:26 ` [PATCH 38/67] xfs: set inode sick state flags when we zap either ondisk fork cem
2024-04-22 16:26 ` [PATCH 39/67] xfs: zap broken inode forks cem
2024-04-22 16:26 ` cem [this message]
2024-04-22 16:26 ` [PATCH 41/67] xfs: create a ranged query function for refcount btrees cem
2024-04-22 16:26 ` [PATCH 42/67] xfs: create a new inode fork block unmap helper cem
2024-04-22 16:26 ` [PATCH 43/67] xfs: improve dquot iteration for scrub cem
2024-04-22 16:26 ` [PATCH 44/67] xfs: add lock protection when remove perag from radix tree cem
2024-04-22 16:26 ` [PATCH 45/67] xfs: fix perag leak when growfs fails cem
2024-04-22 16:26 ` [PATCH 46/67] xfs: remove the xfs_alloc_arg argument to xfs_bmap_btalloc_accounting cem
2024-04-22 16:26 ` [PATCH 47/67] xfs: also use xfs_bmap_btalloc_accounting for RT allocations cem
2024-04-22 16:26 ` [PATCH 48/67] xfs: return -ENOSPC from xfs_rtallocate_* cem
2024-04-22 16:26 ` [PATCH 49/67] xfs: indicate if xfs_bmap_adjacent changed ap->blkno cem
2024-04-22 16:26 ` [PATCH 50/67] xfs: move xfs_rtget_summary to xfs_rtbitmap.c cem
2024-04-22 16:26 ` [PATCH 51/67] xfs: split xfs_rtmodify_summary_int cem
2024-04-22 16:26 ` [PATCH 52/67] xfs: remove rt-wrappers from xfs_format.h cem
2024-04-22 16:26 ` [PATCH 53/67] xfs: remove XFS_RTMIN/XFS_RTMAX cem
2024-04-22 16:26 ` [PATCH 54/67] xfs: make if_data a void pointer cem
2024-04-22 16:26 ` [PATCH 55/67] xfs: return if_data from xfs_idata_realloc cem
2024-04-22 16:26 ` [PATCH 56/67] xfs: move the xfs_attr_sf_lookup tracepoint cem
2024-04-22 16:26 ` [PATCH 57/67] xfs: simplify xfs_attr_sf_findname cem
2024-04-22 16:26 ` [PATCH 58/67] xfs: remove xfs_attr_shortform_lookup cem
2024-04-22 16:26 ` [PATCH 59/67] xfs: use xfs_attr_sf_findname in xfs_attr_shortform_getvalue cem
2024-04-22 16:26 ` [PATCH 60/67] xfs: remove struct xfs_attr_shortform cem
2024-04-22 16:26 ` [PATCH 61/67] xfs: remove xfs_attr_sf_hdr_t cem
2024-04-22 16:26 ` [PATCH 62/67] xfs: turn the XFS_DA_OP_REPLACE checks in xfs_attr_shortform_addname into asserts cem
2024-04-22 16:26 ` [PATCH 63/67] xfs: fix a use after free in xfs_defer_finish_recovery cem
2024-04-22 16:26 ` [PATCH 64/67] xfs: use the op name in trace_xlog_intent_recovery_failed cem
2024-04-22 16:26 ` [PATCH 65/67] xfs: fix backwards logic in xfs_bmap_alloc_account cem
2024-04-22 16:26 ` [PATCH 66/67] xfs: reset XFS_ATTR_INCOMPLETE filter on node removal cem
2024-04-22 16:26 ` [PATCH 67/67] xfs: remove conditional building of rt geometry validator functions cem
-- strict thread matches above, loose matches on Subject: below --
2024-04-17 21:16 [PATCHSET 04/11] libxfs: sync with 6.8 Darrick J. Wong
2024-04-17 21:32 ` [PATCH 40/67] xfs: repair inode fork block mapping data structures Darrick J. Wong
2024-03-26 2:55 [PATCHSET 02/18] libxfs: sync with 6.8 Darrick J. Wong
2024-03-26 3:13 ` [PATCH 40/67] xfs: repair inode fork block mapping data structures Darrick J. Wong
2024-03-13 1:47 [PATCHSET 02/10] libxfs: sync with 6.8 Darrick J. Wong
2024-03-13 2:03 ` [PATCH 40/67] xfs: repair inode fork block mapping data structures Darrick J. Wong
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240422163832.858420-42-cem@kernel.org \
--to=cem@kernel.org \
--cc=djwong@kernel.org \
--cc=hch@lst.de \
--cc=linux-xfs@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.