* [RFC PATCH v4 1/4] ocfs2: Add new ocfs2_map_blocks() to introduce iomap feature
2026-11-03 12:43 [RFC PATCH v4 0/4] migrates ocfs2 DIO from buffer_head to iomap Heming Zhao
@ 2026-11-03 12:43 ` Heming Zhao
2026-11-03 12:43 ` [RFC PATCH v4 2/4] ocfs2: switch DIO read path from buffer_head to iomap Heming Zhao
` (3 subsequent siblings)
4 siblings, 0 replies; 7+ messages in thread
From: Heming Zhao @ 2026-11-03 12:43 UTC (permalink / raw)
To: joseph.qi, mark, jlbec, hch; +Cc: Heming Zhao, ocfs2-devel, linux-kernel
As part of migrating OCFS2 DIO read/write code paths towards the modern
and performant iomap framework, here introduces ocfs2_map_blocks() to
replace the legacy, high-overhead buffer_head based block mapping
routines.
In addition, OCFS2_MAP_* flags are defined to gridge OCFS2 internal block
mapping flags with the iomap API requirements.
Subsequent iomap integration patches will build on this core block mapping
routine. The implementation draws inspiration from ext4_map_blocks().
Signed-off-by: Heming Zhao <heming.zhao@suse.com>
---
fs/ocfs2/aops.c | 79 +++++++++++++++++++++++++++++++++++++++
fs/ocfs2/aops.h | 2 +
fs/ocfs2/buffer_head_io.c | 12 ------
fs/ocfs2/ocfs2.h | 46 ++++++++++++++++++++++-
4 files changed, 126 insertions(+), 13 deletions(-)
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 4acdbb70882c..c612244690a1 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -126,6 +126,85 @@ static int ocfs2_lock_get_block(struct inode *inode, sector_t iblock,
return ret;
}
+int ocfs2_map_blocks(struct inode *inode, struct ocfs2_map_block *map,
+ int flags)
+{
+ int err = 0;
+ unsigned int ext_flags;
+ u64 max_blocks = map->len;
+ u64 p_blkno, count, past_eof;
+ struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+ int create = flags & OCFS2_GET_BLOCKS_CREATE;
+
+ if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_SYSTEM_FILE)
+ mlog(ML_NOTICE, "map_block on system inode 0x%p (%llu)\n",
+ inode, inode->i_ino);
+
+ map->flags = 0;
+ err = ocfs2_extent_map_get_blocks(inode, map->lblk, &p_blkno, &count,
+ &ext_flags);
+ if (err) {
+ mlog(ML_ERROR, "get_blocks() failed, inode: 0x%p, "
+ "block: %llu\n", inode, map->lblk);
+ goto bail;
+ }
+
+ if (max_blocks < count)
+ count = max_blocks;
+
+ map->pblk = p_blkno;
+ map->len = count;
+
+ /*
+ * ocfs2 never allocates in this function - the only time we
+ * need to use MAP_NEW is when we're extending i_size on a file
+ * system which doesn't support holes, in which case MAP_NEW
+ * allows __block_write_begin() to zero.
+ *
+ * If we see this on a sparse file system, then a truncate has
+ * raced us and removed the cluster. In this case, we clear
+ * the buffers dirty and uptodate bits and let the buffer code
+ * ignore it as a hole.
+ */
+ if (create && map->pblk == 0 && ocfs2_sparse_alloc(osb)) {
+ map->flags &= ~(OCFS2_MAP_DIRTY | OCFS2_MAP_UPTODATE);
+ goto bail;
+ }
+
+ if (p_blkno) {
+ if (ext_flags & OCFS2_EXT_UNWRITTEN) {
+ map->flags |= OCFS2_MAP_UNWRITTEN;
+ } else {
+ /* Treat the unwritten extent as a hole for zeroing purposes. */
+ map->flags |= OCFS2_MAP_MAPPED;
+ }
+ }
+
+ if (!ocfs2_sparse_alloc(osb)) {
+ if (map->pblk == 0) {
+ err = -EIO;
+ mlog(ML_ERROR,
+ "iblock = %llu p_blkno = %llu blkno=(%llu)\n",
+ (unsigned long long)map->lblk,
+ (unsigned long long)map->pblk,
+ (unsigned long long)OCFS2_I(inode)->ip_blkno);
+ mlog(ML_ERROR, "Size %llu, clusters %u\n",
+ (unsigned long long)i_size_read(inode),
+ OCFS2_I(inode)->ip_clusters);
+ dump_stack();
+ goto bail;
+ }
+ }
+
+ past_eof = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
+
+ if (create && (map->lblk >= past_eof))
+ map->flags |= OCFS2_MAP_NEW;
+
+bail:
+ return err;
+}
+
int ocfs2_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index 114efc9111e4..8dd6edd7c1a1 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -42,6 +42,8 @@ int ocfs2_size_fits_inline_data(struct buffer_head *di_bh, u64 new_size);
int ocfs2_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
+int ocfs2_map_blocks(struct inode *inode, struct ocfs2_map_block *map,
+ int flags);
/* all ocfs2_dio_end_io()'s fault */
#define ocfs2_iocb_is_rw_locked(iocb) \
test_bit(0, (unsigned long *)&iocb->private)
diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c
index 7bfe377af2df..493f2209cca5 100644
--- a/fs/ocfs2/buffer_head_io.c
+++ b/fs/ocfs2/buffer_head_io.c
@@ -23,18 +23,6 @@
#include "buffer_head_io.h"
#include "ocfs2_trace.h"
-/*
- * Bits on bh->b_state used by ocfs2.
- *
- * These MUST be after the JBD2 bits. Hence, we use BH_JBDPrivateStart.
- */
-enum ocfs2_state_bits {
- BH_NeedsValidate = BH_JBDPrivateStart,
-};
-
-/* Expand the magic b_state functions */
-BUFFER_FNS(NeedsValidate, needs_validate);
-
int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh,
struct ocfs2_caching_info *ci)
{
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 62cad6522c7a..88fe985e87c9 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -509,7 +509,51 @@ struct ocfs2_super
struct ocfs2_filecheck_sysfs_entry osb_fc_ent;
};
-#define OCFS2_SB(sb) ((struct ocfs2_super *)(sb)->s_fs_info)
+/*
+ * Bits on bh->b_state used by ocfs2.
+ *
+ * These MUST be after the JBD2 bits. Hence, we use BH_JBDPrivateStart.
+ */
+enum ocfs2_state_bits {
+ BH_NeedsValidate = BH_JBDPrivateStart,
+};
+
+/* Expand the magic b_state functions */
+BUFFER_FNS(NeedsValidate, needs_validate);
+
+/*
+ * Logical to physical block mapping, used by ocfs2_map_blocks()
+ *
+ * This structure is used to pass requests into ocfs2_map_blocks()
+ * as well as to store the information returned by ocfs2_map_blocks().
+ * It takes less room on the stack than a struct buffer_head.
+ */
+#define OCFS2_MAP_NEW BIT(BH_New)
+#define OCFS2_MAP_MAPPED BIT(BH_Mapped)
+#define OCFS2_MAP_UNWRITTEN BIT(BH_Unwritten)
+/* useless? #define OCFS2_MAP_BOUNDARY BIT(BH_Boundary) */
+/* useless? #define OCFS2_MAP_DELAYED BIT(BH_Delay) */
+#define OCFS2_MAP_DIRTY BIT(BH_Dirty)
+#define OCFS2_MAP_UPTODATE BIT(BH_Uptodate)
+#define OCFS2_MAP_NEEDS_VALIDATE BIT(BH_NeedsValidate)
+#define OCFS2_MAP_DEFER_COMPLETION BIT(BH_Defer_Completion)
+#define OCFS2_MAP_FLAGS (OCFS2_MAP_NEW | OCFS2_MAP_MAPPED |\
+ OCFS2_MAP_UNWRITTEN |\
+ OCFS2_MAP_DIRTY | OCFS2_MAP_UPTODATE |\
+ OCFS2_MAP_NEEDS_VALIDATE |\
+ OCFS2_MAP_DEFER_COMPLETION)
+
+struct ocfs2_map_block {
+ u64 pblk; /* physical block# */
+ u64 lblk; /* logical block# */
+ u64 len; /* number of block */
+ unsigned int flags;
+};
+
+/* Flags used by ocfs2_map_blocks() */
+#define OCFS2_GET_BLOCKS_CREATE (0x0001)
+
+#define OCFS2_SB(sb) ((struct ocfs2_super *)(sb)->s_fs_info)
/* Useful typedef for passing around journal access functions */
typedef int (*ocfs2_journal_access_func)(handle_t *handle,
--
2.55.0
^ permalink raw reply [flat|nested] 7+ messages in thread* [RFC PATCH v4 2/4] ocfs2: switch DIO read path from buffer_head to iomap
2026-11-03 12:43 [RFC PATCH v4 0/4] migrates ocfs2 DIO from buffer_head to iomap Heming Zhao
2026-11-03 12:43 ` [RFC PATCH v4 1/4] ocfs2: Add new ocfs2_map_blocks() to introduce iomap feature Heming Zhao
@ 2026-11-03 12:43 ` Heming Zhao
2026-11-03 12:43 ` [RFC PATCH v4 3/4] ocfs2: switch dio write " Heming Zhao
` (2 subsequent siblings)
4 siblings, 0 replies; 7+ messages in thread
From: Heming Zhao @ 2026-11-03 12:43 UTC (permalink / raw)
To: joseph.qi, mark, jlbec, hch; +Cc: Heming Zhao, ocfs2-devel, linux-kernel
Migrates the DIO read path from the legacy buffer_head infrastructure
to the modern and more efficient iomap framework.
Under the current code, ocfs2 holds a cluster lock during DIO via
ocfs2_iocb_set_rw_locked(), and releases the cluster lock in
ocfs2_dio_end_io() via ocfs2_iocb_clear_rw_locked(). The lock level is
stashed in iocb->private.
However, iomap DIO owns that field (it stores a bio there for polled I/O
and unconditionally clears it before calling ->end_io). Any side-channel
state packed into iocb->private is corrupted, which trips the end_io
lock-state check.
Instead, encode the unlock level by passing distinct iomap_dio_ops methods
(ocfs2_iomap_dio_ops_pr for PRMODE or ocfs2_iomap_dio_ops_ex for EXMODE).
Additionally, the *_iter() functions use the split __iomap_dio_rw() +
iomap_dio_complete() API so they can determine unambiguously, from the
return value, whether the completion handler already dropped the lock
(real I/O, sync or -EIOCBQUEUED) or whether the caller must drop it
(no I/O issued, or buffered fallback).
The new function ocfs2_iomap_begin() performs a similar role to
ocfs2_get_block(). While ocfs2_get_block() retrieves only one block per
call, ocfs2_iomap_begin() can handle multiple blocks at once. Limit the
map offset and length in ocfs2_iomap_begin() to OCFS2_MAX_LOGICAL_BLOCK
to avoid overflow issues.
Co-developed-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Signed-off-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Signed-off-by: Heming Zhao <heming.zhao@suse.com>
---
fs/ocfs2/Kconfig | 1 +
fs/ocfs2/aops.c | 111 ++++++++++++++++++++++++++++++++++++++++++++
fs/ocfs2/file.c | 63 +++++++++++++++++++++----
fs/ocfs2/ocfs2.h | 3 ++
fs/ocfs2/ocfs2_fs.h | 3 ++
5 files changed, 171 insertions(+), 10 deletions(-)
diff --git a/fs/ocfs2/Kconfig b/fs/ocfs2/Kconfig
index 2514d36cbe01..bf1678a5eb01 100644
--- a/fs/ocfs2/Kconfig
+++ b/fs/ocfs2/Kconfig
@@ -7,6 +7,7 @@ config OCFS2_FS
select CRC32
select QUOTA
select QUOTA_TREE
+ select FS_IOMAP
select FS_POSIX_ACL
select LEGACY_DIRECT_IO
help
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index c612244690a1..da53abe59ea0 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -4,6 +4,7 @@
*/
#include <linux/fs.h>
+#include <linux/iomap.h>
#include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
@@ -2541,6 +2542,116 @@ static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
ocfs2_dio_end_io, 0);
}
+static int ocfs2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
+ unsigned int flags, struct iomap *iomap, struct iomap *srcmap)
+{
+ int ret;
+ struct ocfs2_map_block map;
+ struct ocfs2_inode_info *oi = OCFS2_I(inode);
+ u8 blkbits = inode->i_blkbits;
+
+ if ((offset >> blkbits) > OCFS2_MAX_LOGICAL_BLOCK)
+ return -EINVAL;
+
+ /*
+ * Calculate the first and last logical blocks respectively.
+ */
+ map.lblk = offset >> blkbits;
+ map.len = min_t(loff_t, (offset + length - 1) >> blkbits,
+ OCFS2_MAX_LOGICAL_BLOCK) - map.lblk + 1;
+ map.flags = 0;
+
+ if (flags & IOMAP_WRITE) {
+ return -EOPNOTSUPP;
+ } else {
+ down_read(&oi->ip_alloc_sem);
+ ret = ocfs2_map_blocks(inode, &map, 0);
+ up_read(&oi->ip_alloc_sem);
+ }
+
+ if (ret < 0)
+ return ret;
+
+ /*
+ * Before returning to iomap, let's ensure the allocated mapping
+ * covers the entire requested length for atomic writes.
+ */
+ if (flags & IOMAP_ATOMIC) {
+ if (map.len < (length >> blkbits)) {
+ WARN_ON_ONCE(1);
+ return -EINVAL;
+ }
+ }
+
+ iomap->bdev = inode->i_sb->s_bdev;
+ iomap->offset = (u64)map.lblk << blkbits;
+ iomap->length = (u64)map.len << blkbits;
+
+ if (map.pblk == 0) {
+ iomap->type = IOMAP_HOLE;
+ iomap->addr = IOMAP_NULL_ADDR;
+ } else {
+ if (map.flags & OCFS2_MAP_UNWRITTEN) {
+ iomap->type = IOMAP_UNWRITTEN;
+ } else if (map.flags & OCFS2_MAP_MAPPED) {
+ iomap->type = IOMAP_MAPPED;
+ } else {
+ WARN_ON_ONCE(1);
+ return -EIO;
+ }
+ iomap->addr = (sector_t)map.pblk << blkbits;
+ }
+
+ if (map.flags & OCFS2_MAP_NEW)
+ iomap->flags |= IOMAP_F_NEW;
+
+ return 0;
+}
+
+const struct iomap_ops ocfs2_iomap_ops = {
+ .iomap_begin = ocfs2_iomap_begin,
+};
+
+/*
+ * Direct I/O completion. Like the old ocfs2_dio_end_io(), we use the rw_lock
+ * DLM lock to protect io on one node from truncation on another, and drop it
+ * here once the io has completed. iomap_dio_complete() always calls this,
+ * including on the buffered-fallback (-ENOTBLK) path, so the rw_lock taken in
+ * ocfs2_file_{read,write}_iter() is released exactly once.
+ */
+static int ocfs2_iomap_dio_end_io(struct kiocb *iocb, ssize_t size, int error,
+ int level)
+{
+ struct inode *inode = file_inode(iocb->ki_filp);
+
+ /*
+ * When iomap_dio_complete() calls us with size==0 and error==0, it
+ * means the mapping bounced back to buffered I/O. In that case leave
+ * the rw_lock ocfs2_file_{read,write}_iter() keeps it for the buffered
+ * retry and releases it in its own cleanup path.
+ */
+ if (size == 0 && error == 0)
+ return 0;
+
+ ocfs2_rw_unlock(inode, level);
+ return error;
+}
+
+static int ocfs2_dio_end_io_r_pr(struct kiocb *iocb, ssize_t size,
+ int error, unsigned int flags)
+{
+ if (error)
+ mlog_ratelimited(ML_ERROR, "Direct IO failed, bytes = %lld errno:%d",
+ (long long)size, error);
+
+ error = ocfs2_iomap_dio_end_io(iocb, size, error, 0);
+
+ return error;
+}
+
+const struct iomap_dio_ops ocfs2_iomap_dio_ops_r_pr = {
+ .end_io = ocfs2_dio_end_io_r_pr,
+};
const struct address_space_operations ocfs2_aops = {
.dirty_folio = block_dirty_folio,
.read_folio = ocfs2_read_folio,
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index d6e977ba6565..0ad4f08eb3e4 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -9,6 +9,7 @@
#include <linux/capability.h>
#include <linux/fs.h>
+#include <linux/iomap.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/highmem.h>
@@ -2374,6 +2375,19 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
return ret;
}
+static bool ocfs2_should_use_dio(struct kiocb *iocb, struct iov_iter *iter,
+ struct inode *inode)
+{
+ /*
+ * Fallback to buffered I/O if we see an inode without
+ * extents.
+ */
+ if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
+ return false;
+
+ return true;
+}
+
static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
struct iov_iter *from)
{
@@ -2548,7 +2562,6 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
filp->f_path.dentry->d_name.name,
to->nr_segs); /* GRRRRR */
-
if (!inode) {
ret = -EINVAL;
mlog_errno(ret);
@@ -2558,7 +2571,8 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
if (!direct_io && nowait)
return -EOPNOTSUPP;
- ocfs2_iocb_init_rw_locked(iocb);
+ if (!iov_iter_count(to))
+ return 0; /* skip atime */
/*
* buffered reads protect themselves in ->read_folio(). O_DIRECT reads
@@ -2576,8 +2590,6 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
goto bail;
}
rw_level = 0;
- /* communicate with ocfs2_dio_end_io */
- ocfs2_iocb_set_rw_locked(iocb, rw_level);
}
/*
@@ -2598,17 +2610,48 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
}
ocfs2_inode_unlock(inode, lock_level);
- ret = generic_file_read_iter(iocb, to);
+ if (direct_io && ocfs2_should_use_dio(iocb, to, inode)) {
+ /*
+ * Use the split iomap DIO API so we can tell who owns the
+ * rw_lock on return; reads always hold it at PR level, dropped
+ * by ocfs2_iomap_dio_end_io_pr(). Call it directly rather than
+ * through generic_file_read_iter(): iomap advances iocb->ki_pos
+ * itself, so the generic helper would advance ki_pos twice.
+ */
+ struct iomap_dio *dio;
+
+ dio = __iomap_dio_rw(iocb, to, &ocfs2_iomap_ops,
+ &ocfs2_iomap_dio_ops_r_pr, 0, NULL, 0);
+ if (dio == NULL) {
+ /* No I/O issued; rw_lock still held. */
+ ret = 0;
+ } else if (IS_ERR(dio)) {
+ ret = PTR_ERR(dio);
+ if (ret == -EIOCBQUEUED)
+ rw_level = -1;
+ } else {
+ ret = iomap_dio_complete(dio);
+ if (ret != 0)
+ rw_level = -1;
+ }
+ /*
+ * A 0 result means the mapping bounced us back to buffered I/O
+ * (e.g. inline data); the rw_lock is still held. Go to the
+ * buffered path rather than re-entering direct I/O.
+ */
+ if (ret == 0) {
+ iocb->ki_flags &= ~IOCB_DIRECT;
+ ret = generic_file_read_iter(iocb, to);
+ }
+ } else {
+ iocb->ki_flags &= ~IOCB_DIRECT;
+ ret = generic_file_read_iter(iocb, to);
+ }
trace_generic_file_read_iter_ret(ret);
/* buffered aio wouldn't have proper lock coverage today */
BUG_ON(ret == -EIOCBQUEUED && !direct_io);
- /* see ocfs2_file_write_iter */
- if (ret == -EIOCBQUEUED || !ocfs2_iocb_is_rw_locked(iocb)) {
- rw_level = -1;
- }
-
bail:
if (rw_level != -1)
ocfs2_rw_unlock(inode, rw_level);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 88fe985e87c9..58ad6f570536 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -550,6 +550,9 @@ struct ocfs2_map_block {
unsigned int flags;
};
+extern const struct iomap_ops ocfs2_iomap_ops;
+extern const struct iomap_dio_ops ocfs2_iomap_dio_ops_r_pr;
+
/* Flags used by ocfs2_map_blocks() */
#define OCFS2_GET_BLOCKS_CREATE (0x0001)
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index c501eb3cdcda..fe1b80531c45 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -314,6 +314,9 @@
*/
#define OCFS2_CLUSTER_O2CB_GLOBAL_HEARTBEAT (0x01)
+/* Max logical block we can support */
+#define OCFS2_MAX_LOGICAL_BLOCK (0xFFFFFFFF)
+
struct ocfs2_system_inode_info {
char *si_name;
int si_iflags;
--
2.55.0
^ permalink raw reply [flat|nested] 7+ messages in thread* [RFC PATCH v4 3/4] ocfs2: switch dio write path from buffer_head to iomap
2026-11-03 12:43 [RFC PATCH v4 0/4] migrates ocfs2 DIO from buffer_head to iomap Heming Zhao
2026-11-03 12:43 ` [RFC PATCH v4 1/4] ocfs2: Add new ocfs2_map_blocks() to introduce iomap feature Heming Zhao
2026-11-03 12:43 ` [RFC PATCH v4 2/4] ocfs2: switch DIO read path from buffer_head to iomap Heming Zhao
@ 2026-11-03 12:43 ` Heming Zhao
2026-11-03 12:43 ` [RFC PATCH v4 4/4] ocfs2: remove legacy blockdev direct-IO path APIs Heming Zhao
2026-11-03 13:59 ` [RFC PATCH v4 0/4] migrates ocfs2 DIO from buffer_head to iomap Heming Zhao
4 siblings, 0 replies; 7+ messages in thread
From: Heming Zhao @ 2026-11-03 12:43 UTC (permalink / raw)
To: joseph.qi, mark, jlbec, hch; +Cc: Heming Zhao, ocfs2-devel, linux-kernel
Converts OCFS2's DIO write path from the legacy buffer_head
infrastructure to the modern iomap framework.
Key modifications and designs are as follows:
Introduce ocfs2_dio_wr_map_blocks() to allocate and map direct write
blocks. This function is similar to the buffer_head path
ocfs2_dio_wr_get_block(), which still allocates one cluster per call.
Implement ocfs2_dio_write_end_io() and ocfs2_iomap_dio_end_io_write()
to handle IO completion. They convert UNWRITTEN extents, updates inode
size (EOF).
In the buffer_head path, ocfs2_dio_wr_get_block() stores dwc in
bh->b_private, enabling it to detect the first call for an IO chunk and
invoke ocfs2_add_inode_to_orphan() to protect the extent allocation.
However, iomap doesn't provide a similar private field. Therefore, moves
ocfs2_add_inode_to_orphan() from ocfs2_dio_wr_map_blocks(the buffer_head
counterpart to ocfs2_dio_wr_get_block()) to ocfs2_file_write_iter().
It is also impossible t pass The dwc to iomap_dio_ops.end_io, the iomap
->end_io callback cannot effectively distinguish between I/Os initiated
by different threads concurrently. For example, when multiple DIO write
threads operate on the same inode concurrently, the end_io callback
without the dwc context may incorrectly delete an orphan inode created
by another thread, leading to a crash. The fix is to move the orphan
inode deletion from end_io into ocfs2_file_write_iter(). In
ocfs2_file_write_iter(), inode_lock() serializes the write threads,
and IOMAP_DIO_FORCE_WAIT ensures that the function only returns after
the bio completes. This guarantees that i_size has already been
updated when ocfs2_dio_del_orphan() is called.
Doesn't like ocfs2_dio_wr_get_block(), move the zero operations from
ocfs2_dio_wr_map_blocks() to ocfs2_file_write_iter(). If do the zeroing
in ocfs2_dio_wr_map_blocks() would zero blocks that earlier mappings of
this same dio have already written, as i_size is only updated at dio
completion. this will makes xfstests generic/538 failure.
Assisted-by: LLM
Co-developed-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Signed-off-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Signed-off-by: Heming Zhao <heming.zhao@suse.com>
---
fs/ocfs2/aops.c | 442 +++++++++++++++++++++++++++++++++++++++++++++--
fs/ocfs2/aops.h | 1 +
fs/ocfs2/file.c | 137 +++++++++++++--
fs/ocfs2/ocfs2.h | 2 +
4 files changed, 545 insertions(+), 37 deletions(-)
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index da53abe59ea0..6f8890873b86 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -206,6 +206,19 @@ int ocfs2_map_blocks(struct inode *inode, struct ocfs2_map_block *map,
return err;
}
+static int ocfs2_lock_map_blocks(struct inode *inode,
+ struct ocfs2_map_block *map, int flags)
+{
+ int ret = 0;
+ struct ocfs2_inode_info *oi = OCFS2_I(inode);
+
+ down_read(&oi->ip_alloc_sem);
+ ret = ocfs2_map_blocks(inode, map, flags);
+ up_read(&oi->ip_alloc_sem);
+
+ return ret;
+}
+
int ocfs2_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
@@ -2343,6 +2356,160 @@ static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock,
return ret;
}
+/*
+ * Prepare the area between i_size and a direct write that starts or ends
+ * beyond it. Must be called once per dio, before any io is issued, with
+ * i_rwsem and the rw lock held.
+ */
+int ocfs2_dio_zero_eof(struct inode *inode, loff_t pos, size_t count)
+{
+ struct ocfs2_inode_info *oi = OCFS2_I(inode);
+ struct buffer_head *di_bh = NULL;
+ int ret;
+
+ if (pos + count <= i_size_read(inode))
+ return 0;
+
+ ret = ocfs2_inode_lock(inode, &di_bh, 1);
+ if (ret) {
+ mlog_errno(ret);
+ return ret;
+ }
+
+ down_write(&oi->ip_alloc_sem);
+ if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
+ ret = ocfs2_zero_tail(inode, di_bh, pos);
+ else
+ ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos, count,
+ NULL);
+ if (ret < 0)
+ mlog_errno(ret);
+ up_write(&oi->ip_alloc_sem);
+
+ ocfs2_inode_unlock(inode, 1);
+ brelse(di_bh);
+ return ret;
+}
+
+/* copy from ocfs2_dio_wr_get_block */
+static int ocfs2_dio_wr_map_blocks(struct inode *inode,
+ struct ocfs2_map_block *map, int create)
+{
+ struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+ struct ocfs2_inode_info *oi = OCFS2_I(inode);
+ struct ocfs2_write_ctxt *wc;
+ struct ocfs2_write_cluster_desc *desc = NULL;
+ struct buffer_head *di_bh = NULL;
+ u64 p_blkno;
+ sector_t iblock = map->lblk;
+ unsigned int i_blkbits = inode->i_sb->s_blocksize_bits;
+ loff_t pos = iblock << i_blkbits;
+ sector_t endblk = (i_size_read(inode) - 1) >> i_blkbits;
+ unsigned int len, total_len = map->len << i_blkbits;
+ int ret = 0;
+
+ len = osb->s_clustersize - (pos & (osb->s_clustersize - 1));
+ len = min(total_len, len);
+ /*
+ * map->len is count in ocfs2_iomap_begin according to write
+ * "pos" and "end", we need map twice to return different buffer state:
+ * 1. area in file size, not set NEW;
+ * 2. area out file size, set NEW.
+ *
+ * iblock endblk
+ * |--------|---------|---------|---------
+ * |<-------area in file------->|
+ */
+ if ((iblock <= endblk) &&
+ ((iblock + ((len - 1) >> i_blkbits)) > endblk))
+ len = (endblk - iblock + 1) << i_blkbits;
+
+ mlog(0, "get block of %llu at %llu:%u req %u\n",
+ inode->i_ino, pos, len, total_len);
+
+ /*
+ * Because we need to change file size in ocfs2_iomap_dio_end_io_write(),
+ * or we may need to add it to orphan dir. So can not fall to fast path
+ * while file size will be changed.
+ */
+ if (pos + total_len <= i_size_read(inode)) {
+ /* This is the fast path for re-write. */
+ ret = ocfs2_lock_map_blocks(inode, map, OCFS2_GET_BLOCKS_CREATE);
+ if ((map->flags & OCFS2_MAP_MAPPED) &&
+ !(map->flags & OCFS2_MAP_NEW) &&
+ ret == 0)
+ goto out;
+
+ /* Clear state set by ocfs2_map_blocks. */
+ map->flags = 0;
+ }
+
+ ret = ocfs2_inode_lock(inode, &di_bh, 1);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ down_write(&oi->ip_alloc_sem);
+
+ /*
+ * Note, Zeroing the gap between i_size and the write is done
+ * once per dio by ocfs2_dio_zero_eof() before the io is issued.
+ */
+ ret = ocfs2_write_begin_nolock(inode->i_mapping, pos, len,
+ OCFS2_WRITE_DIRECT, NULL,
+ (void **)&wc, di_bh, NULL);
+ if (ret) {
+ mlog_errno(ret);
+ goto unlock;
+ }
+
+ desc = &wc->w_desc[0];
+
+ p_blkno = ocfs2_clusters_to_blocks(inode->i_sb, desc->c_phys);
+ if (p_blkno == 0) {
+ ret = -EIO;
+ mlog_errno(ret);
+ goto unlock;
+ }
+ p_blkno += iblock & (u64)(ocfs2_clusters_to_blocks(inode->i_sb, 1) - 1);
+
+ map->pblk = p_blkno;
+ /*
+ * Only report the mapping as UNWRITTEN when the cluster is newly
+ * allocated or was already unwritten (desc->c_needs_zero).
+ */
+ map->flags |= desc->c_needs_zero ?
+ OCFS2_MAP_UNWRITTEN : OCFS2_MAP_MAPPED;
+ map->len = len >> i_blkbits;
+
+ if (desc->c_needs_zero)
+ map->flags |= OCFS2_MAP_NEW;
+
+ if (iblock > endblk)
+ map->flags |= OCFS2_MAP_NEW;
+
+ map->flags |= OCFS2_MAP_DEFER_COMPLETION;
+
+ ocfs2_free_unwritten_list(inode, &wc->w_unwritten_list);
+ /* Here returns only two types: len (success), errno (failure). */
+ ret = ocfs2_write_end_nolock(inode->i_mapping, pos, len, len, wc);
+ if (ret < 0) {
+ mlog_errno(ret);
+ goto unlock;
+ }
+ WARN_ON_ONCE(ret != len);
+ ret = 0;
+
+unlock:
+ up_write(&oi->ip_alloc_sem);
+ ocfs2_inode_unlock(inode, 1);
+ brelse(di_bh);
+
+out:
+ return ret;
+}
+
static int ocfs2_dio_end_io_write(struct inode *inode,
struct ocfs2_dio_write_ctxt *dwc,
loff_t offset,
@@ -2549,6 +2716,7 @@ static int ocfs2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
struct ocfs2_map_block map;
struct ocfs2_inode_info *oi = OCFS2_I(inode);
u8 blkbits = inode->i_blkbits;
+ unsigned int orig_mlen;
if ((offset >> blkbits) > OCFS2_MAX_LOGICAL_BLOCK)
return -EINVAL;
@@ -2560,9 +2728,32 @@ static int ocfs2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
map.len = min_t(loff_t, (offset + length - 1) >> blkbits,
OCFS2_MAX_LOGICAL_BLOCK) - map.lblk + 1;
map.flags = 0;
+ orig_mlen = map.len;
if (flags & IOMAP_WRITE) {
- return -EOPNOTSUPP;
+ /*
+ * We check here if the blocks are already allocated, then we
+ * don't need to start a journal txn and we can directly return
+ * the mapping information. This could boost performance
+ * especially in multi-threaded overwrite requests.
+ */
+ if (offset + length <= i_size_read(inode)) {
+ down_read(&oi->ip_alloc_sem);
+ ret = ocfs2_map_blocks(inode, &map, 0);
+ up_read(&oi->ip_alloc_sem);
+ /*
+ * For atomic writes the entire requested length should
+ * be mapped.
+ */
+ if (map.flags & OCFS2_MAP_MAPPED) {
+ if ((!(flags & IOMAP_ATOMIC) && map.len > 0) ||
+ ((flags & IOMAP_ATOMIC) && map.len >= orig_mlen)) {
+ goto out;
+ }
+ }
+ map.len = orig_mlen;
+ }
+ ret = ocfs2_dio_wr_map_blocks(inode, &map, 1);
} else {
down_read(&oi->ip_alloc_sem);
ret = ocfs2_map_blocks(inode, &map, 0);
@@ -2572,6 +2763,7 @@ static int ocfs2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
if (ret < 0)
return ret;
+out:
/*
* Before returning to iomap, let's ensure the allocated mapping
* covers the entire requested length for atomic writes.
@@ -2612,6 +2804,216 @@ const struct iomap_ops ocfs2_iomap_ops = {
.iomap_begin = ocfs2_iomap_begin,
};
+/* copy from ocfs2_dio_end_io_write */
+static int ocfs2_iomap_dio_end_io_write(struct inode *inode,
+ loff_t offset,
+ ssize_t bytes)
+{
+ struct ocfs2_cached_dealloc_ctxt dealloc;
+ struct ocfs2_extent_tree et;
+ struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+ struct ocfs2_inode_info *oi = OCFS2_I(inode);
+ struct buffer_head *di_bh = NULL;
+ struct ocfs2_dinode *di;
+ struct ocfs2_alloc_context *data_ac = NULL;
+ struct ocfs2_alloc_context *meta_ac = NULL;
+ handle_t *handle = NULL;
+ loff_t end = offset + bytes;
+ int ret = 0, credits = 0, batch = 0;
+ struct ocfs2_map_block map;
+ unsigned int blkbits = inode->i_blkbits;
+ unsigned int ue_cpos = 0, ue_phys = 0, ue_len = 0;
+ unsigned int curr_lblk, end_lblk;
+ u32 extents_to_split;
+
+ map.lblk = offset >> blkbits;
+
+ ocfs2_init_dealloc_ctxt(&dealloc);
+
+ ret = ocfs2_inode_lock(inode, &di_bh, 1);
+ if (ret < 0) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ down_write(&oi->ip_alloc_sem);
+ di = (struct ocfs2_dinode *)di_bh->b_data;
+
+ ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), di_bh);
+
+ /* Attach dealloc with extent tree in case that we may reuse extents
+ * which are already unlinked from current extent tree due to extent
+ * rotation and merging.
+ */
+ et.et_dealloc = &dealloc;
+
+ /*
+ * Currently, the slow path of ocfs2_dio_wr_map_blocks() only handles
+ * single-cluster cases. Because kiocb->private is cleared before the
+ * iomap_dio_ops end_io callback is invoked, this function cannot
+ * obtain the exact number of unwritten extents via dwc, unlike the
+ * buffered path function ocfs2_dio_end_io_write(). Consequently, the
+ * algorithm here may overestimate the actual number of unwritten
+ * extents; however, this only incurs additional allocator overhead and
+ * does not compromise the correctness of the results.
+ */
+ extents_to_split = DIV_ROUND_UP(bytes, 1 << osb->s_clustersize_bits);
+ ret = ocfs2_lock_allocators(inode, &et, 0, extents_to_split * 2,
+ &data_ac, &meta_ac);
+ if (ret) {
+ mlog_errno(ret);
+ goto unlock;
+ }
+
+ credits = ocfs2_calc_extend_credits(inode->i_sb, &di->id2.i_list);
+
+
+ curr_lblk = offset >> blkbits;
+ /*
+ * Round the end up so the final partial block (sub-block direct I/O)
+ * is included; otherwise the last, partially-written cluster is left
+ * unwritten and reads back as zero.
+ */
+ end_lblk = (offset + bytes + (1 << blkbits) - 1) >> blkbits;
+ while (ret >= 0 && curr_lblk < end_lblk) {
+ memset(&map, 0, sizeof(map));
+ map.lblk = curr_lblk;
+ map.len = end_lblk - curr_lblk;
+
+ if (!handle) {
+ handle = ocfs2_start_trans(osb, credits);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ mlog_errno(ret);
+ goto unlock;
+ }
+ ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
+ if (ret) {
+ mlog_errno(ret);
+ goto commit;
+ }
+ }
+ ret = ocfs2_assure_trans_credits(handle, credits);
+ if (ret < 0) {
+ mlog_errno(ret);
+ goto commit;
+ }
+
+ ret = ocfs2_map_blocks(inode, &map, 0);
+ if (ret < 0) {
+ mlog_errno(ret);
+ goto commit;
+ }
+ if (map.len == 0)
+ goto commit;
+
+ if (map.flags & OCFS2_MAP_UNWRITTEN) {
+ ue_cpos = ocfs2_blocks_to_clusters(inode->i_sb, map.lblk);
+ ue_phys = ocfs2_blocks_to_clusters(inode->i_sb, map.pblk);
+ ue_len = ocfs2_clusters_for_blocks(inode->i_sb,
+ map.lblk + map.len) - ue_cpos;
+
+ ret = ocfs2_mark_extent_written(inode, &et, handle,
+ ue_cpos, ue_len,
+ ue_phys,
+ meta_ac, &dealloc);
+ if (ret < 0) {
+ mlog_errno(ret);
+ goto commit;
+ }
+ }
+ curr_lblk += map.len;
+ if (++batch == OCFS2_DIO_MARK_EXTENT_BATCH) {
+ ocfs2_commit_trans(osb, handle);
+ handle = NULL;
+ batch = 0;
+ }
+ }
+
+ if (end > i_size_read(inode)) {
+ if (!handle) {
+ handle = ocfs2_start_trans(osb, credits);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ mlog_errno(ret);
+ goto unlock;
+ }
+ }
+ ret = ocfs2_set_inode_size(handle, inode, di_bh, end);
+ if (ret < 0)
+ mlog_errno(ret);
+ }
+
+commit:
+ if (handle)
+ ocfs2_commit_trans(osb, handle);
+
+unlock:
+ up_write(&oi->ip_alloc_sem);
+
+ if (data_ac) {
+ ocfs2_free_alloc_context(data_ac);
+ data_ac = NULL;
+ }
+ if (meta_ac) {
+ ocfs2_free_alloc_context(meta_ac);
+ meta_ac = NULL;
+ }
+
+ /*
+ * The orphan entry is removed by ocfs2_file_write_iter(), by the writer
+ * that added it. Other dios on this inode may complete here while it
+ * is still in flight, so they must not touch it.
+ */
+ ocfs2_inode_unlock(inode, 1);
+ brelse(di_bh);
+
+out:
+ ocfs2_run_deallocs(osb, &dealloc);
+ return ret;
+}
+
+/* See the comments from ocfs2_iomap_dio_end_io_r_pr(). */
+static int ocfs2_dio_write_end_io(struct kiocb *iocb, ssize_t size,
+ int error, unsigned int flags, int level)
+{
+ struct inode *inode = file_inode(iocb->ki_filp);
+ loff_t offset = iocb->ki_pos;
+ int ret = 0;
+
+ if (error)
+ mlog_ratelimited(ML_ERROR, "Direct IO failed, bytes = %lld errno:%d",
+ (long long)size, error);
+
+ /* bounced back to buffered I/O, leave the rw_lock held */
+ if (size == 0 && error == 0)
+ return 0;
+
+ if (size && ((flags & IOMAP_DIO_UNWRITTEN) ||
+ (offset + size > i_size_read(inode)))) {
+ ret = ocfs2_iomap_dio_end_io_write(inode, offset, size);
+ if (ret < 0)
+ mlog_errno(ret);
+ }
+
+ ocfs2_rw_unlock(inode, level);
+
+ return ret ? ret : error;
+}
+
+static int ocfs2_iomap_dio_end_io_w_pr(struct kiocb *iocb, ssize_t size,
+ int error, unsigned int flags)
+{
+ return ocfs2_dio_write_end_io(iocb, size, error, flags, 0);
+}
+
+static int ocfs2_iomap_dio_end_io_w_ex(struct kiocb *iocb, ssize_t size,
+ int error, unsigned int flags)
+{
+ return ocfs2_dio_write_end_io(iocb, size, error, flags, 1);
+}
+
/*
* Direct I/O completion. Like the old ocfs2_dio_end_io(), we use the rw_lock
* DLM lock to protect io on one node from truncation on another, and drop it
@@ -2619,38 +3021,40 @@ const struct iomap_ops ocfs2_iomap_ops = {
* including on the buffered-fallback (-ENOTBLK) path, so the rw_lock taken in
* ocfs2_file_{read,write}_iter() is released exactly once.
*/
-static int ocfs2_iomap_dio_end_io(struct kiocb *iocb, ssize_t size, int error,
- int level)
+static int ocfs2_iomap_dio_end_io_r_pr(struct kiocb *iocb, ssize_t size,
+ int error, unsigned int flags)
{
struct inode *inode = file_inode(iocb->ki_filp);
+ if (error)
+ mlog_ratelimited(ML_ERROR, "Direct IO failed, bytes = %lld errno:%d",
+ (long long)size, error);
+
/*
- * When iomap_dio_complete() calls us with size==0 and error==0, it
- * means the mapping bounced back to buffered I/O. In that case leave
- * the rw_lock ocfs2_file_{read,write}_iter() keeps it for the buffered
- * retry and releases it in its own cleanup path.
+ * iomap_dio_complete() calls us even when no I/O was issued because the
+ * mapping bounced us back to buffered I/O (reported as size == 0 and
+ * error == 0). In that case leave the rw_lock held so
+ * ocfs2_file_{read,write}_iter() keeps it for the buffered retry and
+ * releases it in its own cleanup path.
*/
if (size == 0 && error == 0)
return 0;
- ocfs2_rw_unlock(inode, level);
+ ocfs2_rw_unlock(inode, 0);
+
return error;
}
-static int ocfs2_dio_end_io_r_pr(struct kiocb *iocb, ssize_t size,
- int error, unsigned int flags)
-{
- if (error)
- mlog_ratelimited(ML_ERROR, "Direct IO failed, bytes = %lld errno:%d",
- (long long)size, error);
-
- error = ocfs2_iomap_dio_end_io(iocb, size, error, 0);
+const struct iomap_dio_ops ocfs2_iomap_dio_ops_w_pr = {
+ .end_io = ocfs2_iomap_dio_end_io_w_pr,
+};
- return error;
-}
+const struct iomap_dio_ops ocfs2_iomap_dio_ops_w_ex = {
+ .end_io = ocfs2_iomap_dio_end_io_w_ex,
+};
const struct iomap_dio_ops ocfs2_iomap_dio_ops_r_pr = {
- .end_io = ocfs2_dio_end_io_r_pr,
+ .end_io = ocfs2_iomap_dio_end_io_r_pr,
};
const struct address_space_operations ocfs2_aops = {
.dirty_folio = block_dirty_folio,
diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index 8dd6edd7c1a1..b46ba4df1428 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -42,6 +42,7 @@ int ocfs2_size_fits_inline_data(struct buffer_head *di_bh, u64 new_size);
int ocfs2_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
+int ocfs2_dio_zero_eof(struct inode *inode, loff_t pos, size_t count);
int ocfs2_map_blocks(struct inode *inode, struct ocfs2_map_block *map,
int flags);
/* all ocfs2_dio_end_io()'s fault */
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 0ad4f08eb3e4..83ad96e21fd0 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -48,6 +48,7 @@
#include "quota.h"
#include "refcounttree.h"
#include "ocfs2_trace.h"
+#include "namei.h"
#include "buffer_head_io.h"
@@ -2378,6 +2379,8 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
static bool ocfs2_should_use_dio(struct kiocb *iocb, struct iov_iter *iter,
struct inode *inode)
{
+ struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+
/*
* Fallback to buffered I/O if we see an inode without
* extents.
@@ -2385,9 +2388,43 @@ static bool ocfs2_should_use_dio(struct kiocb *iocb, struct iov_iter *iter,
if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
return false;
+ /* Fallback to buffered I/O if we do not support append dio. */
+ if (iocb->ki_pos + iter->count > i_size_read(inode) &&
+ !ocfs2_supports_append_dio(osb))
+ return false;
+
return true;
}
+/*
+ * Remove the inode from the orphan dir after an appending direct write.
+ * Only the writer that added the inode (under i_rwsem) may remove it;
+ */
+static int ocfs2_dio_del_orphan(struct inode *inode)
+{
+ struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+ struct buffer_head *di_bh = NULL;
+ struct ocfs2_dinode *di;
+ int ret;
+
+ ret = ocfs2_inode_lock(inode, &di_bh, 1);
+ if (ret < 0) {
+ mlog_errno(ret);
+ return ret;
+ }
+
+ di = (struct ocfs2_dinode *)di_bh->b_data;
+ if (di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL)) {
+ ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh, 0, 0);
+ if (ret < 0)
+ mlog_errno(ret);
+ }
+
+ ocfs2_inode_unlock(inode, 1);
+ brelse(di_bh);
+ return ret;
+}
+
static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
struct iov_iter *from)
{
@@ -2405,6 +2442,8 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
i_size_read(inode) ? 1 : 0);
int direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0;
int nowait = iocb->ki_flags & IOCB_NOWAIT ? 1 : 0;
+ int dio_flags = 0;
+ int orphaned = 0;
trace_ocfs2_file_write_iter(inode, file, file->f_path.dentry,
(unsigned long long)OCFS2_I(inode)->ip_blkno,
@@ -2424,8 +2463,6 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
} else
inode_lock(inode);
- ocfs2_iocb_init_rw_locked(iocb);
-
/*
* Concurrent O_DIRECT writes are allowed with
* mount_option "coherency=buffered".
@@ -2474,6 +2511,10 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
}
count = ret;
+ ret = kiocb_modified(iocb);
+ if (ret < 0)
+ goto out;
+
ret = ocfs2_prepare_inode_for_write(file, iocb->ki_pos, count, !nowait);
if (ret < 0) {
if (ret != -EAGAIN)
@@ -2489,26 +2530,79 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
saved_ki_complete = xchg(&iocb->ki_complete, NULL);
}
- /* communicate with ocfs2_dio_end_io */
- ocfs2_iocb_set_rw_locked(iocb, rw_level);
+ if (direct_io && ocfs2_should_use_dio(iocb, from, inode)) {
+ if (ocfs2_clusters_for_bytes(inode->i_sb, iocb->ki_pos + count) >
+ ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode))) {
+ /*
+ * when we are going to alloc extents beyond file size, add the
+ * inode to orphan dir, so we can recall those spaces when
+ * system crashed during write.
+ */
+ ret = ocfs2_add_inode_to_orphan(osb, inode);
+ if (ret < 0) {
+ mlog_errno(ret);
+ goto out;
+ }
+ orphaned = 1;
+ dio_flags = IOMAP_DIO_FORCE_WAIT;
+ }
+
+ ret = ocfs2_dio_zero_eof(inode, iocb->ki_pos, count);
+ if (ret < 0)
+ goto out;
- written = __generic_file_write_iter(iocb, from);
- /* buffered aio wouldn't have proper lock coverage today */
- BUG_ON(written == -EIOCBQUEUED && !direct_io);
+ const struct iomap_dio_ops *dops = rw_level ?
+ &ocfs2_iomap_dio_ops_w_ex : &ocfs2_iomap_dio_ops_w_pr;
+ struct iomap_dio *dio;
- /*
- * deep in g_f_a_w_n()->ocfs2_direct_IO we pass in a ocfs2_dio_end_io
- * function pointer which is called when o_direct io completes so that
- * it can unlock our rw lock.
- * Unfortunately there are error cases which call end_io and others
- * that don't. so we don't have to unlock the rw_lock if either an
- * async dio is going to do it in the future or an end_io after an
- * error has already done it.
- */
- if ((written == -EIOCBQUEUED) || (!ocfs2_iocb_is_rw_locked(iocb))) {
- rw_level = -1;
+ dio = __iomap_dio_rw(iocb, from, &ocfs2_iomap_ops,
+ dops, dio_flags, NULL, 0);
+ if (dio == NULL) {
+ /* No I/O issued; rw_lock still held. */
+ written = 0;
+ } else if (IS_ERR(dio)) {
+ written = PTR_ERR(dio);
+ /*
+ * -EIOCBQUEUED: async I/O; end_io will drop the lock on
+ * completion. Any other error means no I/O started and
+ * end_io was not called, so the cleanup path below drops
+ * the lock.
+ */
+ if (written == -EIOCBQUEUED)
+ rw_level = -1;
+ } else {
+ /*
+ * Synchronous completion. iomap_dio_complete() runs
+ * end_io, which drops the lock unless the mapping
+ * bounced us back to buffered I/O (returns 0, lock
+ * retained).
+ */
+ written = iomap_dio_complete(dio);
+ if (written != 0)
+ rw_level = -1;
+ }
+
+ /*
+ * __iomap_dio_rw() returns -ENOTBLK when it could not invalidate
+ * the page cache for the DIO range (e.g. racing buffered/mmap
+ * I/O on the same file, as exercised by generic/095). Fall back
+ * to a buffered write for the remaining data, the same way
+ * ext4/xfs do, instead of leaking -ENOTBLK to userspace.
+ */
+ if (written == -ENOTBLK)
+ written = 0;
+ if (written == 0 && iov_iter_count(from)) {
+ iocb->ki_flags &= ~IOCB_DIRECT;
+ written = __generic_file_write_iter(iocb, from);
+ }
+ } else {
+ iocb->ki_flags &= ~IOCB_DIRECT;
+ written = __generic_file_write_iter(iocb, from);
}
+ /* buffered aio wouldn't have proper lock coverage today */
+ BUG_ON(written == -EIOCBQUEUED && !direct_io);
+
if (unlikely(written <= 0))
goto out;
@@ -2533,6 +2627,13 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
}
out:
+ /*
+ * IOMAP_DIO_FORCE_WAIT made the dio complete synchronously, so its
+ * end_io has already updated i_size.
+ */
+ if (orphaned)
+ ocfs2_dio_del_orphan(inode);
+
if (saved_ki_complete)
xchg(&iocb->ki_complete, saved_ki_complete);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 58ad6f570536..e36130de2dd8 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -552,6 +552,8 @@ struct ocfs2_map_block {
extern const struct iomap_ops ocfs2_iomap_ops;
extern const struct iomap_dio_ops ocfs2_iomap_dio_ops_r_pr;
+extern const struct iomap_dio_ops ocfs2_iomap_dio_ops_w_pr;
+extern const struct iomap_dio_ops ocfs2_iomap_dio_ops_w_ex;
/* Flags used by ocfs2_map_blocks() */
#define OCFS2_GET_BLOCKS_CREATE (0x0001)
--
2.55.0
^ permalink raw reply [flat|nested] 7+ messages in thread* [RFC PATCH v4 4/4] ocfs2: remove legacy blockdev direct-IO path APIs
2026-11-03 12:43 [RFC PATCH v4 0/4] migrates ocfs2 DIO from buffer_head to iomap Heming Zhao
` (2 preceding siblings ...)
2026-11-03 12:43 ` [RFC PATCH v4 3/4] ocfs2: switch dio write " Heming Zhao
@ 2026-11-03 12:43 ` Heming Zhao
2026-11-03 13:59 ` [RFC PATCH v4 0/4] migrates ocfs2 DIO from buffer_head to iomap Heming Zhao
4 siblings, 0 replies; 7+ messages in thread
From: Heming Zhao @ 2026-11-03 12:43 UTC (permalink / raw)
To: joseph.qi, mark, jlbec, hch; +Cc: Heming Zhao, ocfs2-devel, linux-kernel
Since the DIO path already migrated from buffer_head mode (by
using a_ops->direct_IO method) to iomap mode, the VFS no longer
sets FMODE_CAN_ODIRECT automatically, so ocfs2_file_open() sets
it explicitly.
The now-unused blockdev get_block/end_io machinery
(ocfs2_lock_get_block(), ocfs2_dio_wr_get_block(), ocfs2_dio_end_io(),
ocfs2_dio_end_io_write(), and the ocfs2_dio_write_ctxt helpers)
is removed, and OCFS2_FS Kconfig removes LEGACY_DIRECT_IO.
Co-developed-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Signed-off-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Signed-off-by: Heming Zhao <heming.zhao@suse.com>
---
fs/ocfs2/Kconfig | 1 -
fs/ocfs2/aops.c | 416 +----------------------------------------------
fs/ocfs2/aops.h | 35 +---
fs/ocfs2/file.c | 14 +-
fs/ocfs2/ocfs2.h | 5 -
5 files changed, 19 insertions(+), 452 deletions(-)
diff --git a/fs/ocfs2/Kconfig b/fs/ocfs2/Kconfig
index bf1678a5eb01..74bc2008ef0b 100644
--- a/fs/ocfs2/Kconfig
+++ b/fs/ocfs2/Kconfig
@@ -9,7 +9,6 @@ config OCFS2_FS
select QUOTA_TREE
select FS_IOMAP
select FS_POSIX_ACL
- select LEGACY_DIRECT_IO
help
OCFS2 is a general purpose extent based shared disk cluster file
system with many similarities to ext3. It supports 64 bit inode
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 6f8890873b86..834fd401a883 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -114,19 +114,6 @@ static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
return err;
}
-static int ocfs2_lock_get_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
-{
- int ret = 0;
- struct ocfs2_inode_info *oi = OCFS2_I(inode);
-
- down_read(&oi->ip_alloc_sem);
- ret = ocfs2_get_block(inode, iblock, bh_result, create);
- up_read(&oi->ip_alloc_sem);
-
- return ret;
-}
-
int ocfs2_map_blocks(struct inode *inode, struct ocfs2_map_block *map,
int flags)
{
@@ -2159,203 +2146,6 @@ static int ocfs2_write_end(const struct kiocb *iocb,
return ret;
}
-struct ocfs2_dio_write_ctxt {
- struct list_head dw_zero_list;
- unsigned dw_zero_count;
- int dw_orphaned;
- pid_t dw_writer_pid;
-};
-
-static struct ocfs2_dio_write_ctxt *
-ocfs2_dio_alloc_write_ctx(struct buffer_head *bh, int *alloc)
-{
- struct ocfs2_dio_write_ctxt *dwc = NULL;
-
- if (bh->b_private)
- return bh->b_private;
-
- dwc = kmalloc_obj(struct ocfs2_dio_write_ctxt, GFP_NOFS);
- if (dwc == NULL)
- return NULL;
- INIT_LIST_HEAD(&dwc->dw_zero_list);
- dwc->dw_zero_count = 0;
- dwc->dw_orphaned = 0;
- dwc->dw_writer_pid = task_pid_nr(current);
- bh->b_private = dwc;
- *alloc = 1;
-
- return dwc;
-}
-
-static void ocfs2_dio_free_write_ctx(struct inode *inode,
- struct ocfs2_dio_write_ctxt *dwc)
-{
- ocfs2_free_unwritten_list(inode, &dwc->dw_zero_list);
- kfree(dwc);
-}
-
-/*
- * TODO: Make this into a generic get_blocks function.
- *
- * From do_direct_io in direct-io.c:
- * "So what we do is to permit the ->get_blocks function to populate
- * bh.b_size with the size of IO which is permitted at this offset and
- * this i_blkbits."
- *
- * This function is called directly from get_more_blocks in direct-io.c.
- *
- * called like this: dio->get_blocks(dio->inode, fs_startblk,
- * fs_count, map_bh, dio->rw == WRITE);
- */
-static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
-{
- struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
- struct ocfs2_inode_info *oi = OCFS2_I(inode);
- struct ocfs2_write_ctxt *wc;
- struct ocfs2_write_cluster_desc *desc = NULL;
- struct ocfs2_dio_write_ctxt *dwc = NULL;
- struct buffer_head *di_bh = NULL;
- u64 p_blkno;
- unsigned int i_blkbits = inode->i_sb->s_blocksize_bits;
- loff_t pos = iblock << i_blkbits;
- sector_t endblk = (i_size_read(inode) - 1) >> i_blkbits;
- unsigned len, total_len = bh_result->b_size;
- int ret = 0, first_get_block = 0;
-
- len = osb->s_clustersize - (pos & (osb->s_clustersize - 1));
- len = min(total_len, len);
-
- /*
- * bh_result->b_size is count in get_more_blocks according to write
- * "pos" and "end", we need map twice to return different buffer state:
- * 1. area in file size, not set NEW;
- * 2. area out file size, set NEW.
- *
- * iblock endblk
- * |--------|---------|---------|---------
- * |<-------area in file------->|
- */
-
- if ((iblock <= endblk) &&
- ((iblock + ((len - 1) >> i_blkbits)) > endblk))
- len = (endblk - iblock + 1) << i_blkbits;
-
- mlog(0, "get block of %llu at %llu:%u req %u\n",
- inode->i_ino, pos, len, total_len);
-
- /*
- * Because we need to change file size in ocfs2_dio_end_io_write(), or
- * we may need to add it to orphan dir. So can not fall to fast path
- * while file size will be changed.
- */
- if (pos + total_len <= i_size_read(inode)) {
-
- /* This is the fast path for re-write. */
- ret = ocfs2_lock_get_block(inode, iblock, bh_result, create);
- if (buffer_mapped(bh_result) &&
- !buffer_new(bh_result) &&
- ret == 0)
- goto out;
-
- /* Clear state set by ocfs2_get_block. */
- bh_result->b_state = 0;
- }
-
- dwc = ocfs2_dio_alloc_write_ctx(bh_result, &first_get_block);
- if (unlikely(dwc == NULL)) {
- ret = -ENOMEM;
- mlog_errno(ret);
- goto out;
- }
-
- if (ocfs2_clusters_for_bytes(inode->i_sb, pos + total_len) >
- ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode)) &&
- !dwc->dw_orphaned) {
- /*
- * when we are going to alloc extents beyond file size, add the
- * inode to orphan dir, so we can recall those spaces when
- * system crashed during write.
- */
- ret = ocfs2_add_inode_to_orphan(osb, inode);
- if (ret < 0) {
- mlog_errno(ret);
- goto out;
- }
- dwc->dw_orphaned = 1;
- }
-
- ret = ocfs2_inode_lock(inode, &di_bh, 1);
- if (ret) {
- mlog_errno(ret);
- goto out;
- }
-
- down_write(&oi->ip_alloc_sem);
-
- if (first_get_block) {
- if (ocfs2_sparse_alloc(osb))
- ret = ocfs2_zero_tail(inode, di_bh, pos);
- else
- ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos,
- total_len, NULL);
- if (ret < 0) {
- mlog_errno(ret);
- goto unlock;
- }
- }
-
- ret = ocfs2_write_begin_nolock(inode->i_mapping, pos, len,
- OCFS2_WRITE_DIRECT, NULL,
- (void **)&wc, di_bh, NULL);
- if (ret) {
- mlog_errno(ret);
- goto unlock;
- }
-
- desc = &wc->w_desc[0];
-
- p_blkno = ocfs2_clusters_to_blocks(inode->i_sb, desc->c_phys);
- BUG_ON(p_blkno == 0);
- p_blkno += iblock & (u64)(ocfs2_clusters_to_blocks(inode->i_sb, 1) - 1);
-
- map_bh(bh_result, inode->i_sb, p_blkno);
- bh_result->b_size = len;
- if (desc->c_needs_zero)
- set_buffer_new(bh_result);
-
- if (iblock > endblk)
- set_buffer_new(bh_result);
-
- /* May sleep in end_io. It should not happen in a irq context. So defer
- * it to dio work queue. */
- set_buffer_defer_completion(bh_result);
-
- if (!list_empty(&wc->w_unwritten_list)) {
- struct ocfs2_unwritten_extent *ue = NULL;
-
- ue = list_first_entry(&wc->w_unwritten_list,
- struct ocfs2_unwritten_extent,
- ue_node);
- BUG_ON(ue->ue_cpos != desc->c_cpos);
- /* The physical address may be 0, fill it. */
- ue->ue_phys = desc->c_phys;
-
- list_splice_tail_init(&wc->w_unwritten_list, &dwc->dw_zero_list);
- dwc->dw_zero_count += wc->w_unwritten_count;
- }
-
- ret = ocfs2_write_end_nolock(inode->i_mapping, pos, len, len, wc);
- BUG_ON(ret != len);
- ret = 0;
-unlock:
- up_write(&oi->ip_alloc_sem);
- ocfs2_inode_unlock(inode, 1);
- brelse(di_bh);
-out:
- return ret;
-}
-
/*
* Prepare the area between i_size and a direct write that starts or ends
* beyond it. Must be called once per dio, before any io is issued, with
@@ -2391,7 +2181,6 @@ int ocfs2_dio_zero_eof(struct inode *inode, loff_t pos, size_t count)
return ret;
}
-/* copy from ocfs2_dio_wr_get_block */
static int ocfs2_dio_wr_map_blocks(struct inode *inode,
struct ocfs2_map_block *map, int create)
{
@@ -2510,205 +2299,6 @@ static int ocfs2_dio_wr_map_blocks(struct inode *inode,
return ret;
}
-static int ocfs2_dio_end_io_write(struct inode *inode,
- struct ocfs2_dio_write_ctxt *dwc,
- loff_t offset,
- ssize_t bytes)
-{
- struct ocfs2_cached_dealloc_ctxt dealloc;
- struct ocfs2_extent_tree et;
- struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
- struct ocfs2_inode_info *oi = OCFS2_I(inode);
- struct ocfs2_unwritten_extent *ue = NULL;
- struct buffer_head *di_bh = NULL;
- struct ocfs2_dinode *di;
- struct ocfs2_alloc_context *data_ac = NULL;
- struct ocfs2_alloc_context *meta_ac = NULL;
- handle_t *handle = NULL;
- loff_t end = offset + bytes;
- int ret = 0, credits = 0, batch = 0;
-
- ocfs2_init_dealloc_ctxt(&dealloc);
-
- /* We do clear unwritten, delete orphan, change i_size here. If neither
- * of these happen, we can skip all this. */
- if (list_empty(&dwc->dw_zero_list) &&
- end <= i_size_read(inode) &&
- !dwc->dw_orphaned)
- goto out;
-
- ret = ocfs2_inode_lock(inode, &di_bh, 1);
- if (ret < 0) {
- mlog_errno(ret);
- goto out;
- }
-
- down_write(&oi->ip_alloc_sem);
- di = (struct ocfs2_dinode *)di_bh->b_data;
-
- ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), di_bh);
-
- /* Attach dealloc with extent tree in case that we may reuse extents
- * which are already unlinked from current extent tree due to extent
- * rotation and merging.
- */
- et.et_dealloc = &dealloc;
-
- ret = ocfs2_lock_allocators(inode, &et, 0, dwc->dw_zero_count*2,
- &data_ac, &meta_ac);
- if (ret) {
- mlog_errno(ret);
- goto unlock;
- }
-
- credits = ocfs2_calc_extend_credits(inode->i_sb, &di->id2.i_list);
-
- list_for_each_entry(ue, &dwc->dw_zero_list, ue_node) {
- if (!handle) {
- handle = ocfs2_start_trans(osb, credits);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- mlog_errno(ret);
- goto unlock;
- }
- ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
- OCFS2_JOURNAL_ACCESS_WRITE);
- if (ret) {
- mlog_errno(ret);
- goto commit;
- }
- }
- ret = ocfs2_assure_trans_credits(handle, credits);
- if (ret < 0) {
- mlog_errno(ret);
- goto commit;
- }
- ret = ocfs2_mark_extent_written(inode, &et, handle,
- ue->ue_cpos, 1,
- ue->ue_phys,
- meta_ac, &dealloc);
- if (ret < 0) {
- mlog_errno(ret);
- goto commit;
- }
-
- if (++batch == OCFS2_DIO_MARK_EXTENT_BATCH) {
- ocfs2_commit_trans(osb, handle);
- handle = NULL;
- batch = 0;
- }
- }
-
- if (end > i_size_read(inode)) {
- if (!handle) {
- handle = ocfs2_start_trans(osb, credits);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- mlog_errno(ret);
- goto unlock;
- }
- }
- ret = ocfs2_set_inode_size(handle, inode, di_bh, end);
- if (ret < 0)
- mlog_errno(ret);
- }
-
-commit:
- if (handle)
- ocfs2_commit_trans(osb, handle);
-unlock:
- up_write(&oi->ip_alloc_sem);
-
- if (data_ac) {
- ocfs2_free_alloc_context(data_ac);
- data_ac = NULL;
- }
- if (meta_ac) {
- ocfs2_free_alloc_context(meta_ac);
- meta_ac = NULL;
- }
-
- /* everything looks good, let's start the cleanup */
- if (!ret && dwc->dw_orphaned) {
- BUG_ON(dwc->dw_writer_pid != task_pid_nr(current));
-
- ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh, 0, 0);
- if (ret < 0)
- mlog_errno(ret);
- }
- ocfs2_inode_unlock(inode, 1);
- brelse(di_bh);
-out:
- ocfs2_run_deallocs(osb, &dealloc);
- ocfs2_dio_free_write_ctx(inode, dwc);
-
- return ret;
-}
-
-/*
- * ocfs2_dio_end_io is called by the dio core when a dio is finished. We're
- * particularly interested in the aio/dio case. We use the rw_lock DLM lock
- * to protect io on one node from truncation on another.
- */
-static int ocfs2_dio_end_io(struct kiocb *iocb,
- loff_t offset,
- ssize_t bytes,
- void *private)
-{
- struct inode *inode = file_inode(iocb->ki_filp);
- int level;
- int ret = 0;
-
- /* this io's submitter should not have unlocked this before we could */
- BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
-
- if (bytes <= 0)
- mlog_ratelimited(ML_ERROR, "Direct IO failed, bytes = %lld",
- (long long)bytes);
- if (private) {
- if (bytes > 0)
- ret = ocfs2_dio_end_io_write(inode, private, offset,
- bytes);
- else
- ocfs2_dio_free_write_ctx(inode, private);
- }
-
- ocfs2_iocb_clear_rw_locked(iocb);
-
- level = ocfs2_iocb_rw_locked_level(iocb);
- ocfs2_rw_unlock(inode, level);
- return ret;
-}
-
-static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
-{
- struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_mapping->host;
- struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
- get_block_t *get_block;
-
- /*
- * Fallback to buffered I/O if we see an inode without
- * extents.
- */
- if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
- return 0;
-
- /* Fallback to buffered I/O if we do not support append dio. */
- if (iocb->ki_pos + iter->count > i_size_read(inode) &&
- !ocfs2_supports_append_dio(osb))
- return 0;
-
- if (iov_iter_rw(iter) == READ)
- get_block = ocfs2_lock_get_block;
- else
- get_block = ocfs2_dio_wr_get_block;
-
- return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
- iter, get_block,
- ocfs2_dio_end_io, 0);
-}
-
static int ocfs2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
unsigned int flags, struct iomap *iomap, struct iomap *srcmap)
{
@@ -2804,7 +2394,6 @@ const struct iomap_ops ocfs2_iomap_ops = {
.iomap_begin = ocfs2_iomap_begin,
};
-/* copy from ocfs2_dio_end_io_write */
static int ocfs2_iomap_dio_end_io_write(struct inode *inode,
loff_t offset,
ssize_t bytes)
@@ -2852,8 +2441,8 @@ static int ocfs2_iomap_dio_end_io_write(struct inode *inode,
* single-cluster cases. Because kiocb->private is cleared before the
* iomap_dio_ops end_io callback is invoked, this function cannot
* obtain the exact number of unwritten extents via dwc, unlike the
- * buffered path function ocfs2_dio_end_io_write(). Consequently, the
- * algorithm here may overestimate the actual number of unwritten
+ * legacy buffered path function ocfs2_dio_end_io_write(). Consequently,
+ * the algorithm here may overestimate the actual number of unwritten
* extents; however, this only incurs additional allocator overhead and
* does not compromise the correctness of the results.
*/
@@ -3064,7 +2653,6 @@ const struct address_space_operations ocfs2_aops = {
.write_begin = ocfs2_write_begin,
.write_end = ocfs2_write_end,
.bmap = ocfs2_bmap,
- .direct_IO = ocfs2_direct_IO,
.invalidate_folio = block_invalidate_folio,
.release_folio = ocfs2_release_folio,
.migrate_folio = buffer_migrate_folio,
diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index b46ba4df1428..11100421d924 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -7,6 +7,12 @@
#define OCFS2_AOPS_H
#include <linux/fs.h>
+#include <linux/iomap.h>
+
+extern const struct iomap_ops ocfs2_iomap_ops;
+extern const struct iomap_dio_ops ocfs2_iomap_dio_ops_r_pr;
+extern const struct iomap_dio_ops ocfs2_iomap_dio_ops_w_pr;
+extern const struct iomap_dio_ops ocfs2_iomap_dio_ops_w_ex;
int ocfs2_map_folio_blocks(struct folio *folio, u64 *p_blkno,
struct inode *inode, unsigned int from,
@@ -45,34 +51,5 @@ int ocfs2_get_block(struct inode *inode, sector_t iblock,
int ocfs2_dio_zero_eof(struct inode *inode, loff_t pos, size_t count);
int ocfs2_map_blocks(struct inode *inode, struct ocfs2_map_block *map,
int flags);
-/* all ocfs2_dio_end_io()'s fault */
-#define ocfs2_iocb_is_rw_locked(iocb) \
- test_bit(0, (unsigned long *)&iocb->private)
-static inline void ocfs2_iocb_set_rw_locked(struct kiocb *iocb, int level)
-{
- set_bit(0, (unsigned long *)&iocb->private);
- if (level)
- set_bit(1, (unsigned long *)&iocb->private);
- else
- clear_bit(1, (unsigned long *)&iocb->private);
-}
-
-/*
- * Using a named enum representing lock types in terms of #N bit stored in
- * iocb->private, which is going to be used for communication between
- * ocfs2_dio_end_io() and ocfs2_file_write/read_iter().
- */
-enum ocfs2_iocb_lock_bits {
- OCFS2_IOCB_RW_LOCK = 0,
- OCFS2_IOCB_RW_LOCK_LEVEL,
- OCFS2_IOCB_NUM_LOCKS
-};
-
-#define ocfs2_iocb_init_rw_locked(iocb) \
- (iocb->private = NULL)
-#define ocfs2_iocb_clear_rw_locked(iocb) \
- clear_bit(OCFS2_IOCB_RW_LOCK, (unsigned long *)&iocb->private)
-#define ocfs2_iocb_rw_locked_level(iocb) \
- test_bit(OCFS2_IOCB_RW_LOCK_LEVEL, (unsigned long *)&iocb->private)
#endif /* OCFS2_FILE_H */
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 83ad96e21fd0..63111001cadd 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -129,6 +129,14 @@ static int ocfs2_file_open(struct inode *inode, struct file *file)
file->f_mode |= FMODE_NOWAIT;
+ /*
+ * Direct I/O is served through iomap_dio_rw() from
+ * ocfs2_file_{read,write}_iter() rather than an a_ops->direct_IO
+ * method, so advertise O_DIRECT capability explicitly here.
+ */
+ file->f_mode |= FMODE_CAN_ODIRECT;
+
+
leave:
return status;
}
@@ -1171,9 +1179,9 @@ int ocfs2_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
size_change = S_ISREG(inode->i_mode) && attr->ia_valid & ATTR_SIZE;
if (size_change) {
/*
- * Here we should wait dio to finish before inode lock
- * to avoid a deadlock between ocfs2_setattr() and
- * ocfs2_dio_end_io_write()
+ * Here we should wait for in-flight direct I/O to finish
+ * before taking the inode lock, to avoid a deadlock between
+ * ocfs2_setattr() and direct I/O completion.
*/
inode_dio_wait(inode);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index e36130de2dd8..88fe985e87c9 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -550,11 +550,6 @@ struct ocfs2_map_block {
unsigned int flags;
};
-extern const struct iomap_ops ocfs2_iomap_ops;
-extern const struct iomap_dio_ops ocfs2_iomap_dio_ops_r_pr;
-extern const struct iomap_dio_ops ocfs2_iomap_dio_ops_w_pr;
-extern const struct iomap_dio_ops ocfs2_iomap_dio_ops_w_ex;
-
/* Flags used by ocfs2_map_blocks() */
#define OCFS2_GET_BLOCKS_CREATE (0x0001)
--
2.55.0
^ permalink raw reply [flat|nested] 7+ messages in thread* Re: [RFC PATCH v4 0/4] migrates ocfs2 DIO from buffer_head to iomap
2026-11-03 12:43 [RFC PATCH v4 0/4] migrates ocfs2 DIO from buffer_head to iomap Heming Zhao
` (3 preceding siblings ...)
2026-11-03 12:43 ` [RFC PATCH v4 4/4] ocfs2: remove legacy blockdev direct-IO path APIs Heming Zhao
@ 2026-11-03 13:59 ` Heming Zhao
4 siblings, 0 replies; 7+ messages in thread
From: Heming Zhao @ 2026-11-03 13:59 UTC (permalink / raw)
To: joseph.qi, mark, jlbec, hch; +Cc: ocfs2-devel, linux-kernel
Hi List,
Please ignore this patch set, as it failed to apply on sashiko.
Thanks,
- Heming
On 11/3/26 20:43, Heming Zhao wrote:
> This patch set migrates ocfs2 Direct I/O (DIO) from buffer_head mode
> to iomap mode. And the code base is commit 4056b3c9d3c92ea, and also
> merge Joseph's code and ideas from [1]:
>
> v4 changelog:
>
> Fix several issues found during a sashiko review[2].
>
> To simplify iomap development, we currently adopt the simplest approach:
> retaining the buffer_head style, where only one cluster is allocated
> per iomap_begin() call.
>
> When creating a filesystem using "mkfs -b 2K -C 8K" (where the cluster
> size is greater than the page size), several xfstests cases crashed.
> The root cause was an incorrect return value from iomap end_io.
>
> Both the add and del of the orphan inode during write I/O are now placed
> in ocfs2_file_write_iter().
>
> Additionally, I attempted to implement .submit_io/.end_io in "struct
> iomap_dio_ops" to free dwc inside end_io. However, because ->bi_end_io
> runs in an interrupt context and ocfs2_iomap_dio_end_io_write() contains
> sleepable functions, this approach required scheduling a workqueue directly
> from the ->bi_end_io callback and calling ocfs2_iomap_dio_end_io_write()
> within the workqueue thread context. Furthermore, since iomap_dio_ops.end_io
> still cannot access any private data, it cannot accurately wait for the
> work to finish. Testing with xfstests triggered hangs and crashes.
>
>
> [1]:
> https://gitee.com/anolis/storage-cloud-kernel/commit/ea3fe75e2060118ba093e90b1cd34fa382914b29
>
> [2]:
> https://sashiko.dev/#/patchset/20261018143319.22329-1-heming.zhao%40suse.com
>
> v1 patch set:
> https://lore.kernel.org/ocfs2-devel/20260724052559.15409-1-heming.zhao@suse.com/
> v2 patch set:
> https://lore.kernel.org/ocfs2-devel/20260727061802.18485-1-heming.zhao@suse.com/
> v3 patch set:
> https://lore.kernel.org/ocfs2-devel/20261018143319.22329-1-heming.zhao@suse.com/
>
> --------------
> # test report
>
> This patch set has been tested on 7.3.0-rc7 kernel with the following test
> cases.
>
> ## ltp
>
> runltp -f dio -d /mnt/ocfs2/
>
> 1 fail: diotest4 9 TCONF : diotest4.c:346: Direct I/O on /dev/null is not supported
>
> This fail can be ignored.
>
> The test results: passed
>
> ## xfstests
>
> ./check -g quick -T -b -s ocfs2 -e generic/081 \
> -e generic/266 -e generic/272 -e generic/281 \
> -e generic/338 -e generic/347 -e generic/361 \
> -e generic/628 -e generic/629 -e generic/648 -e generic/650
>
> The test results are the same before and after the patch set.
>
> ```
> OCFS2_MKFS_LOCAL_OPT="-b 2K -C 4K --fs-features=local --fs-feature-level=max-features"
> Failures: generic/003 generic/091 generic/094 generic/177 generic/211
> generic/225 generic/263 generic/322 generic/329 generic/331 generic/370
> generic/376 generic/424 generic/448 generic/467 generic/477 generic/481
> generic/510 generic/513 generic/537 generic/552 generic/563 generic/578
> generic/607 generic/620 generic/630 generic/755 generic/760 generic/777
> generic/784
> Failed 30 of 632 tests
>
> OCFS2_MKFS_LOCAL_OPT="-b 4K -C 4K --fs-features=local --fs-feature-level=max-features"
> Failures: generic/003 generic/177 generic/211 generic/322 generic/329 generic/331 generic/370 generic/376 generic/420 generic/424 generic/448 generic/467 generic/477 generic/481 generic/510 generic/513 generic/537 generic/552 generic/563 generic/578 generic/607 generic/620 generic/630 generic/755 generic/777 generic/784
> Failed 26 of 632 tests
>
> OCFS2_MKFS_LOCAL_OPT="-b 2K -C 8K --fs-features=local --fs-feature-level=max-features"
> Failures: generic/003 generic/075 generic/091 generic/094 generic/112 generic/177 generic/211 generic/225 generic/263 generic/322 generic/329 generic/331 generic/370 generic/376 generic/424 generic/448 generic/467 generic/477 generic/481 generic/510 generic/513 generic/537 generic/552 generic/563 generic/564 generic/578 generic/607 generic/620 generic/630 generic/755 generic/759 generic/760 generic/777 generic/784 ocfs2/001
> Failed 35 of 632 tests
>
> OCFS2_MKFS_CLUSTER_OPT="-b 2K -C 4K -N 2 --fs-feature-level=max-features --cluster-stack pcmk --cluster-name hacluster"
> Failures: generic/001 generic/003 generic/091 generic/094 generic/211 generic/225 generic/263 generic/322 generic/329 generic/331 generic/370 generic/376 generic/424 generic/448 generic/467 generic/477 generic/510 generic/513 generic/537 generic/552 generic/563 generic/578 generic/607 generic/620 generic/630 generic/755 generic/760 generic/777 generic/784
> Failed 29 of 632 tests
>
> OCFS2_MKFS_CLUSTER_OPT="-b 4K -C 4K -N 2 --fs-feature-level=max-features --cluster-stack pcmk --cluster-name hacluster"
> Failures: generic/003 generic/211 generic/322 generic/329 generic/331 generic/370 generic/376 generic/420 generic/424 generic/448 generic/467 generic/477 generic/510 generic/513 generic/537 generic/552 generic/563 generic/578 generic/607 generic/620 generic/630 generic/755 generic/777 generic/784
> Failed 24 of 632 tests
>
> OCFS2_MKFS_CLUSTER_OPT="-b 2K -C 8K -N 2 --fs-feature-level=max-features --cluster-stack pcmk --cluster-name hacluster"
> Failures: generic/003 generic/075 generic/091 generic/094 generic/112 generic/211 generic/225 generic/263 generic/322 generic/329 generic/331 generic/370 generic/376 generic/424 generic/448 generic/467 generic/477 generic/510 generic/513 generic/537 generic/547 generic/552 generic/563 generic/564 generic/578 generic/607 generic/620 generic/630 generic/755 generic/759 generic/760 generic/777 generic/784
> Failed 33 of 632 tests
> ```
>
> ## fio on single node
>
> fio --direct=1 --iodepth=32 --rw=write --ioengine=libaio --bs=128k --size=1g \
> --numjobs=4 --runtime=100 --group_reporting --filename=/mnt/ocfs2/write.1g --name=tst
> - before patch write: IOPS=31.5k, BW=3935MiB/s (4126MB/s)(4096MiB/1041msec)
> - before path overwrite (don't remove write.1g, run above fio command):
> write: IOPS=39.5k, BW=4935MiB/s (5175MB/s)(4096MiB/830msec)
> - applied patch write: IOPS=37.4k, BW=4676MiB/s (4903MB/s)(4096MiB/876msec)
> - applied patch overwrite (don't remove write.1g, run above fio command):
> write: IOPS=39.4k, BW=4929MiB/s (5168MB/s)(4096MiB/831msec)
>
> fio --direct=1 --iodepth=32 --rw=read --ioengine=libaio --bs=128k --size=1g \
> --numjobs=4 --runtime=100 --group_reporting --filename=/mnt/ocfs2/write.1g --name=tst
> - before patch : IOPS=47.7k, BW=5962MiB/s (6252MB/s)(4096MiB/687msec)
> - applied patch: IOPS=48.2k, BW=6024MiB/s (6316MB/s)(4096MiB/680msec)
>
> fio --direct=1 --iodepth=32 --rw=randwrite --ioengine=libaio --bs=4k --size=1g \
> --numjobs=4 --runtime=100 --group_reporting --filename=/mnt/ocfs2/write.1g --name=tst
> - before patch
> - creating write : IOPS=3282, BW=12.8MiB/s (13.4MB/s)(1283MiB/100026msec)
> - overwriting write.1g: IOPS=41.8k, BW=163MiB/s (171MB/s)(4096MiB/25115msec)
> - applied patch
> - creating write : IOPS=3230, BW=12.6MiB/s (13.2MB/s)(1262MiB/100031msec)
> - overwriting write.1g: IOPS=40.5k, BW=158MiB/s (166MB/s)(4096MiB/25908msec)
>
> fio --direct=1 --iodepth=32 --rw=randread --ioengine=libaio --bs=4k --size=1g \
> --numjobs=4 --runtime=100 --group_reporting --filename=/mnt/ocfs2/write.1g --name=tst
> - before patch read: IOPS=361k, BW=1409MiB/s (1477MB/s)(4096MiB/2907msec)
> - applied patch read: IOPS=362k, BW=1416MiB/s (1485MB/s)(4096MiB/2893msec)
>
> ---------------------
>
> Heming Zhao (4):
> ocfs2: Add new ocfs2_map_blocks() to introduce iomap feature
> ocfs2: switch DIO read path from buffer_head to iomap
> ocfs2: switch dio write path from buffer_head to iomap
> ocfs2: remove legacy blockdev direct-IO path APIs
>
> fs/ocfs2/Kconfig | 2 +-
> fs/ocfs2/aops.c | 568 +++++++++++++++++++++++++-------------
> fs/ocfs2/aops.h | 38 +--
> fs/ocfs2/buffer_head_io.c | 12 -
> fs/ocfs2/file.c | 214 +++++++++++---
> fs/ocfs2/ocfs2.h | 46 ++-
> fs/ocfs2/ocfs2_fs.h | 3 +
> 7 files changed, 616 insertions(+), 267 deletions(-)
>
^ permalink raw reply [flat|nested] 7+ messages in thread
* [RFC PATCH v4 4/4] ocfs2: remove legacy blockdev direct-IO path APIs
2026-11-03 13:55 [RESEND RFC " Heming Zhao
@ 2026-11-03 13:56 ` Heming Zhao
0 siblings, 0 replies; 7+ messages in thread
From: Heming Zhao @ 2026-11-03 13:56 UTC (permalink / raw)
To: joseph.qi, mark, jlbec, hch; +Cc: Heming Zhao, ocfs2-devel, linux-kernel
Since the DIO path already migrated from buffer_head mode (by
using a_ops->direct_IO method) to iomap mode, the VFS no longer
sets FMODE_CAN_ODIRECT automatically, so ocfs2_file_open() sets
it explicitly.
The now-unused blockdev get_block/end_io machinery
(ocfs2_lock_get_block(), ocfs2_dio_wr_get_block(), ocfs2_dio_end_io(),
ocfs2_dio_end_io_write(), and the ocfs2_dio_write_ctxt helpers)
is removed, and OCFS2_FS Kconfig removes LEGACY_DIRECT_IO.
Co-developed-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Signed-off-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Signed-off-by: Heming Zhao <heming.zhao@suse.com>
---
fs/ocfs2/Kconfig | 1 -
fs/ocfs2/aops.c | 416 +----------------------------------------------
fs/ocfs2/aops.h | 35 +---
fs/ocfs2/file.c | 14 +-
fs/ocfs2/ocfs2.h | 5 -
5 files changed, 19 insertions(+), 452 deletions(-)
diff --git a/fs/ocfs2/Kconfig b/fs/ocfs2/Kconfig
index bf1678a5eb01..74bc2008ef0b 100644
--- a/fs/ocfs2/Kconfig
+++ b/fs/ocfs2/Kconfig
@@ -9,7 +9,6 @@ config OCFS2_FS
select QUOTA_TREE
select FS_IOMAP
select FS_POSIX_ACL
- select LEGACY_DIRECT_IO
help
OCFS2 is a general purpose extent based shared disk cluster file
system with many similarities to ext3. It supports 64 bit inode
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 6f8890873b86..834fd401a883 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -114,19 +114,6 @@ static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
return err;
}
-static int ocfs2_lock_get_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
-{
- int ret = 0;
- struct ocfs2_inode_info *oi = OCFS2_I(inode);
-
- down_read(&oi->ip_alloc_sem);
- ret = ocfs2_get_block(inode, iblock, bh_result, create);
- up_read(&oi->ip_alloc_sem);
-
- return ret;
-}
-
int ocfs2_map_blocks(struct inode *inode, struct ocfs2_map_block *map,
int flags)
{
@@ -2159,203 +2146,6 @@ static int ocfs2_write_end(const struct kiocb *iocb,
return ret;
}
-struct ocfs2_dio_write_ctxt {
- struct list_head dw_zero_list;
- unsigned dw_zero_count;
- int dw_orphaned;
- pid_t dw_writer_pid;
-};
-
-static struct ocfs2_dio_write_ctxt *
-ocfs2_dio_alloc_write_ctx(struct buffer_head *bh, int *alloc)
-{
- struct ocfs2_dio_write_ctxt *dwc = NULL;
-
- if (bh->b_private)
- return bh->b_private;
-
- dwc = kmalloc_obj(struct ocfs2_dio_write_ctxt, GFP_NOFS);
- if (dwc == NULL)
- return NULL;
- INIT_LIST_HEAD(&dwc->dw_zero_list);
- dwc->dw_zero_count = 0;
- dwc->dw_orphaned = 0;
- dwc->dw_writer_pid = task_pid_nr(current);
- bh->b_private = dwc;
- *alloc = 1;
-
- return dwc;
-}
-
-static void ocfs2_dio_free_write_ctx(struct inode *inode,
- struct ocfs2_dio_write_ctxt *dwc)
-{
- ocfs2_free_unwritten_list(inode, &dwc->dw_zero_list);
- kfree(dwc);
-}
-
-/*
- * TODO: Make this into a generic get_blocks function.
- *
- * From do_direct_io in direct-io.c:
- * "So what we do is to permit the ->get_blocks function to populate
- * bh.b_size with the size of IO which is permitted at this offset and
- * this i_blkbits."
- *
- * This function is called directly from get_more_blocks in direct-io.c.
- *
- * called like this: dio->get_blocks(dio->inode, fs_startblk,
- * fs_count, map_bh, dio->rw == WRITE);
- */
-static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
-{
- struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
- struct ocfs2_inode_info *oi = OCFS2_I(inode);
- struct ocfs2_write_ctxt *wc;
- struct ocfs2_write_cluster_desc *desc = NULL;
- struct ocfs2_dio_write_ctxt *dwc = NULL;
- struct buffer_head *di_bh = NULL;
- u64 p_blkno;
- unsigned int i_blkbits = inode->i_sb->s_blocksize_bits;
- loff_t pos = iblock << i_blkbits;
- sector_t endblk = (i_size_read(inode) - 1) >> i_blkbits;
- unsigned len, total_len = bh_result->b_size;
- int ret = 0, first_get_block = 0;
-
- len = osb->s_clustersize - (pos & (osb->s_clustersize - 1));
- len = min(total_len, len);
-
- /*
- * bh_result->b_size is count in get_more_blocks according to write
- * "pos" and "end", we need map twice to return different buffer state:
- * 1. area in file size, not set NEW;
- * 2. area out file size, set NEW.
- *
- * iblock endblk
- * |--------|---------|---------|---------
- * |<-------area in file------->|
- */
-
- if ((iblock <= endblk) &&
- ((iblock + ((len - 1) >> i_blkbits)) > endblk))
- len = (endblk - iblock + 1) << i_blkbits;
-
- mlog(0, "get block of %llu at %llu:%u req %u\n",
- inode->i_ino, pos, len, total_len);
-
- /*
- * Because we need to change file size in ocfs2_dio_end_io_write(), or
- * we may need to add it to orphan dir. So can not fall to fast path
- * while file size will be changed.
- */
- if (pos + total_len <= i_size_read(inode)) {
-
- /* This is the fast path for re-write. */
- ret = ocfs2_lock_get_block(inode, iblock, bh_result, create);
- if (buffer_mapped(bh_result) &&
- !buffer_new(bh_result) &&
- ret == 0)
- goto out;
-
- /* Clear state set by ocfs2_get_block. */
- bh_result->b_state = 0;
- }
-
- dwc = ocfs2_dio_alloc_write_ctx(bh_result, &first_get_block);
- if (unlikely(dwc == NULL)) {
- ret = -ENOMEM;
- mlog_errno(ret);
- goto out;
- }
-
- if (ocfs2_clusters_for_bytes(inode->i_sb, pos + total_len) >
- ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode)) &&
- !dwc->dw_orphaned) {
- /*
- * when we are going to alloc extents beyond file size, add the
- * inode to orphan dir, so we can recall those spaces when
- * system crashed during write.
- */
- ret = ocfs2_add_inode_to_orphan(osb, inode);
- if (ret < 0) {
- mlog_errno(ret);
- goto out;
- }
- dwc->dw_orphaned = 1;
- }
-
- ret = ocfs2_inode_lock(inode, &di_bh, 1);
- if (ret) {
- mlog_errno(ret);
- goto out;
- }
-
- down_write(&oi->ip_alloc_sem);
-
- if (first_get_block) {
- if (ocfs2_sparse_alloc(osb))
- ret = ocfs2_zero_tail(inode, di_bh, pos);
- else
- ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos,
- total_len, NULL);
- if (ret < 0) {
- mlog_errno(ret);
- goto unlock;
- }
- }
-
- ret = ocfs2_write_begin_nolock(inode->i_mapping, pos, len,
- OCFS2_WRITE_DIRECT, NULL,
- (void **)&wc, di_bh, NULL);
- if (ret) {
- mlog_errno(ret);
- goto unlock;
- }
-
- desc = &wc->w_desc[0];
-
- p_blkno = ocfs2_clusters_to_blocks(inode->i_sb, desc->c_phys);
- BUG_ON(p_blkno == 0);
- p_blkno += iblock & (u64)(ocfs2_clusters_to_blocks(inode->i_sb, 1) - 1);
-
- map_bh(bh_result, inode->i_sb, p_blkno);
- bh_result->b_size = len;
- if (desc->c_needs_zero)
- set_buffer_new(bh_result);
-
- if (iblock > endblk)
- set_buffer_new(bh_result);
-
- /* May sleep in end_io. It should not happen in a irq context. So defer
- * it to dio work queue. */
- set_buffer_defer_completion(bh_result);
-
- if (!list_empty(&wc->w_unwritten_list)) {
- struct ocfs2_unwritten_extent *ue = NULL;
-
- ue = list_first_entry(&wc->w_unwritten_list,
- struct ocfs2_unwritten_extent,
- ue_node);
- BUG_ON(ue->ue_cpos != desc->c_cpos);
- /* The physical address may be 0, fill it. */
- ue->ue_phys = desc->c_phys;
-
- list_splice_tail_init(&wc->w_unwritten_list, &dwc->dw_zero_list);
- dwc->dw_zero_count += wc->w_unwritten_count;
- }
-
- ret = ocfs2_write_end_nolock(inode->i_mapping, pos, len, len, wc);
- BUG_ON(ret != len);
- ret = 0;
-unlock:
- up_write(&oi->ip_alloc_sem);
- ocfs2_inode_unlock(inode, 1);
- brelse(di_bh);
-out:
- return ret;
-}
-
/*
* Prepare the area between i_size and a direct write that starts or ends
* beyond it. Must be called once per dio, before any io is issued, with
@@ -2391,7 +2181,6 @@ int ocfs2_dio_zero_eof(struct inode *inode, loff_t pos, size_t count)
return ret;
}
-/* copy from ocfs2_dio_wr_get_block */
static int ocfs2_dio_wr_map_blocks(struct inode *inode,
struct ocfs2_map_block *map, int create)
{
@@ -2510,205 +2299,6 @@ static int ocfs2_dio_wr_map_blocks(struct inode *inode,
return ret;
}
-static int ocfs2_dio_end_io_write(struct inode *inode,
- struct ocfs2_dio_write_ctxt *dwc,
- loff_t offset,
- ssize_t bytes)
-{
- struct ocfs2_cached_dealloc_ctxt dealloc;
- struct ocfs2_extent_tree et;
- struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
- struct ocfs2_inode_info *oi = OCFS2_I(inode);
- struct ocfs2_unwritten_extent *ue = NULL;
- struct buffer_head *di_bh = NULL;
- struct ocfs2_dinode *di;
- struct ocfs2_alloc_context *data_ac = NULL;
- struct ocfs2_alloc_context *meta_ac = NULL;
- handle_t *handle = NULL;
- loff_t end = offset + bytes;
- int ret = 0, credits = 0, batch = 0;
-
- ocfs2_init_dealloc_ctxt(&dealloc);
-
- /* We do clear unwritten, delete orphan, change i_size here. If neither
- * of these happen, we can skip all this. */
- if (list_empty(&dwc->dw_zero_list) &&
- end <= i_size_read(inode) &&
- !dwc->dw_orphaned)
- goto out;
-
- ret = ocfs2_inode_lock(inode, &di_bh, 1);
- if (ret < 0) {
- mlog_errno(ret);
- goto out;
- }
-
- down_write(&oi->ip_alloc_sem);
- di = (struct ocfs2_dinode *)di_bh->b_data;
-
- ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), di_bh);
-
- /* Attach dealloc with extent tree in case that we may reuse extents
- * which are already unlinked from current extent tree due to extent
- * rotation and merging.
- */
- et.et_dealloc = &dealloc;
-
- ret = ocfs2_lock_allocators(inode, &et, 0, dwc->dw_zero_count*2,
- &data_ac, &meta_ac);
- if (ret) {
- mlog_errno(ret);
- goto unlock;
- }
-
- credits = ocfs2_calc_extend_credits(inode->i_sb, &di->id2.i_list);
-
- list_for_each_entry(ue, &dwc->dw_zero_list, ue_node) {
- if (!handle) {
- handle = ocfs2_start_trans(osb, credits);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- mlog_errno(ret);
- goto unlock;
- }
- ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
- OCFS2_JOURNAL_ACCESS_WRITE);
- if (ret) {
- mlog_errno(ret);
- goto commit;
- }
- }
- ret = ocfs2_assure_trans_credits(handle, credits);
- if (ret < 0) {
- mlog_errno(ret);
- goto commit;
- }
- ret = ocfs2_mark_extent_written(inode, &et, handle,
- ue->ue_cpos, 1,
- ue->ue_phys,
- meta_ac, &dealloc);
- if (ret < 0) {
- mlog_errno(ret);
- goto commit;
- }
-
- if (++batch == OCFS2_DIO_MARK_EXTENT_BATCH) {
- ocfs2_commit_trans(osb, handle);
- handle = NULL;
- batch = 0;
- }
- }
-
- if (end > i_size_read(inode)) {
- if (!handle) {
- handle = ocfs2_start_trans(osb, credits);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- mlog_errno(ret);
- goto unlock;
- }
- }
- ret = ocfs2_set_inode_size(handle, inode, di_bh, end);
- if (ret < 0)
- mlog_errno(ret);
- }
-
-commit:
- if (handle)
- ocfs2_commit_trans(osb, handle);
-unlock:
- up_write(&oi->ip_alloc_sem);
-
- if (data_ac) {
- ocfs2_free_alloc_context(data_ac);
- data_ac = NULL;
- }
- if (meta_ac) {
- ocfs2_free_alloc_context(meta_ac);
- meta_ac = NULL;
- }
-
- /* everything looks good, let's start the cleanup */
- if (!ret && dwc->dw_orphaned) {
- BUG_ON(dwc->dw_writer_pid != task_pid_nr(current));
-
- ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh, 0, 0);
- if (ret < 0)
- mlog_errno(ret);
- }
- ocfs2_inode_unlock(inode, 1);
- brelse(di_bh);
-out:
- ocfs2_run_deallocs(osb, &dealloc);
- ocfs2_dio_free_write_ctx(inode, dwc);
-
- return ret;
-}
-
-/*
- * ocfs2_dio_end_io is called by the dio core when a dio is finished. We're
- * particularly interested in the aio/dio case. We use the rw_lock DLM lock
- * to protect io on one node from truncation on another.
- */
-static int ocfs2_dio_end_io(struct kiocb *iocb,
- loff_t offset,
- ssize_t bytes,
- void *private)
-{
- struct inode *inode = file_inode(iocb->ki_filp);
- int level;
- int ret = 0;
-
- /* this io's submitter should not have unlocked this before we could */
- BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
-
- if (bytes <= 0)
- mlog_ratelimited(ML_ERROR, "Direct IO failed, bytes = %lld",
- (long long)bytes);
- if (private) {
- if (bytes > 0)
- ret = ocfs2_dio_end_io_write(inode, private, offset,
- bytes);
- else
- ocfs2_dio_free_write_ctx(inode, private);
- }
-
- ocfs2_iocb_clear_rw_locked(iocb);
-
- level = ocfs2_iocb_rw_locked_level(iocb);
- ocfs2_rw_unlock(inode, level);
- return ret;
-}
-
-static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
-{
- struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_mapping->host;
- struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
- get_block_t *get_block;
-
- /*
- * Fallback to buffered I/O if we see an inode without
- * extents.
- */
- if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
- return 0;
-
- /* Fallback to buffered I/O if we do not support append dio. */
- if (iocb->ki_pos + iter->count > i_size_read(inode) &&
- !ocfs2_supports_append_dio(osb))
- return 0;
-
- if (iov_iter_rw(iter) == READ)
- get_block = ocfs2_lock_get_block;
- else
- get_block = ocfs2_dio_wr_get_block;
-
- return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
- iter, get_block,
- ocfs2_dio_end_io, 0);
-}
-
static int ocfs2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
unsigned int flags, struct iomap *iomap, struct iomap *srcmap)
{
@@ -2804,7 +2394,6 @@ const struct iomap_ops ocfs2_iomap_ops = {
.iomap_begin = ocfs2_iomap_begin,
};
-/* copy from ocfs2_dio_end_io_write */
static int ocfs2_iomap_dio_end_io_write(struct inode *inode,
loff_t offset,
ssize_t bytes)
@@ -2852,8 +2441,8 @@ static int ocfs2_iomap_dio_end_io_write(struct inode *inode,
* single-cluster cases. Because kiocb->private is cleared before the
* iomap_dio_ops end_io callback is invoked, this function cannot
* obtain the exact number of unwritten extents via dwc, unlike the
- * buffered path function ocfs2_dio_end_io_write(). Consequently, the
- * algorithm here may overestimate the actual number of unwritten
+ * legacy buffered path function ocfs2_dio_end_io_write(). Consequently,
+ * the algorithm here may overestimate the actual number of unwritten
* extents; however, this only incurs additional allocator overhead and
* does not compromise the correctness of the results.
*/
@@ -3064,7 +2653,6 @@ const struct address_space_operations ocfs2_aops = {
.write_begin = ocfs2_write_begin,
.write_end = ocfs2_write_end,
.bmap = ocfs2_bmap,
- .direct_IO = ocfs2_direct_IO,
.invalidate_folio = block_invalidate_folio,
.release_folio = ocfs2_release_folio,
.migrate_folio = buffer_migrate_folio,
diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index b46ba4df1428..11100421d924 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -7,6 +7,12 @@
#define OCFS2_AOPS_H
#include <linux/fs.h>
+#include <linux/iomap.h>
+
+extern const struct iomap_ops ocfs2_iomap_ops;
+extern const struct iomap_dio_ops ocfs2_iomap_dio_ops_r_pr;
+extern const struct iomap_dio_ops ocfs2_iomap_dio_ops_w_pr;
+extern const struct iomap_dio_ops ocfs2_iomap_dio_ops_w_ex;
int ocfs2_map_folio_blocks(struct folio *folio, u64 *p_blkno,
struct inode *inode, unsigned int from,
@@ -45,34 +51,5 @@ int ocfs2_get_block(struct inode *inode, sector_t iblock,
int ocfs2_dio_zero_eof(struct inode *inode, loff_t pos, size_t count);
int ocfs2_map_blocks(struct inode *inode, struct ocfs2_map_block *map,
int flags);
-/* all ocfs2_dio_end_io()'s fault */
-#define ocfs2_iocb_is_rw_locked(iocb) \
- test_bit(0, (unsigned long *)&iocb->private)
-static inline void ocfs2_iocb_set_rw_locked(struct kiocb *iocb, int level)
-{
- set_bit(0, (unsigned long *)&iocb->private);
- if (level)
- set_bit(1, (unsigned long *)&iocb->private);
- else
- clear_bit(1, (unsigned long *)&iocb->private);
-}
-
-/*
- * Using a named enum representing lock types in terms of #N bit stored in
- * iocb->private, which is going to be used for communication between
- * ocfs2_dio_end_io() and ocfs2_file_write/read_iter().
- */
-enum ocfs2_iocb_lock_bits {
- OCFS2_IOCB_RW_LOCK = 0,
- OCFS2_IOCB_RW_LOCK_LEVEL,
- OCFS2_IOCB_NUM_LOCKS
-};
-
-#define ocfs2_iocb_init_rw_locked(iocb) \
- (iocb->private = NULL)
-#define ocfs2_iocb_clear_rw_locked(iocb) \
- clear_bit(OCFS2_IOCB_RW_LOCK, (unsigned long *)&iocb->private)
-#define ocfs2_iocb_rw_locked_level(iocb) \
- test_bit(OCFS2_IOCB_RW_LOCK_LEVEL, (unsigned long *)&iocb->private)
#endif /* OCFS2_FILE_H */
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index d5ad96bd010a..9b98def091d1 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -136,6 +136,14 @@ static int ocfs2_file_open(struct inode *inode, struct file *file)
file->f_mode |= FMODE_NOWAIT;
+ /*
+ * Direct I/O is served through iomap_dio_rw() from
+ * ocfs2_file_{read,write}_iter() rather than an a_ops->direct_IO
+ * method, so advertise O_DIRECT capability explicitly here.
+ */
+ file->f_mode |= FMODE_CAN_ODIRECT;
+
+
leave:
return status;
}
@@ -1196,9 +1204,9 @@ int ocfs2_setattr(const struct mnt_idmap *idmap, struct dentry *dentry,
size_change = S_ISREG(inode->i_mode) && attr->ia_valid & ATTR_SIZE;
if (size_change) {
/*
- * Here we should wait dio to finish before inode lock
- * to avoid a deadlock between ocfs2_setattr() and
- * ocfs2_dio_end_io_write()
+ * Here we should wait for in-flight direct I/O to finish
+ * before taking the inode lock, to avoid a deadlock between
+ * ocfs2_setattr() and direct I/O completion.
*/
inode_dio_wait(inode);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index ef494a758011..7c75def1ef4c 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -555,11 +555,6 @@ struct ocfs2_map_block {
unsigned int flags;
};
-extern const struct iomap_ops ocfs2_iomap_ops;
-extern const struct iomap_dio_ops ocfs2_iomap_dio_ops_r_pr;
-extern const struct iomap_dio_ops ocfs2_iomap_dio_ops_w_pr;
-extern const struct iomap_dio_ops ocfs2_iomap_dio_ops_w_ex;
-
/* Flags used by ocfs2_map_blocks() */
#define OCFS2_GET_BLOCKS_CREATE (0x0001)
--
2.55.0
^ permalink raw reply [flat|nested] 7+ messages in thread