[PATCH v7 0/4] smb: fix fallocate and allocation accounting

[PATCH v7 0/4] smb: fix fallocate and allocation accounting

[Huiwen He]

From: Huiwen He <hehuiwen@kylinos.cn>

Changes in v7:

- Rework Patch 1 to keeps the duplicate-extents QueryInfo result valid in
  the inode cache, avoiding duplicate revalidation when userspace stats
  the cloned file.

- Rework Patch 3 to no longer uses FSCTL_QUERY_ALLOCATED_RANGES for small
  fallocate ranges that start at or beyond EOF. These ranges are now
  zero-written directly because there are no old allocated ranges to
  preserve there.

The following patch merged into #ksmbd-for-next-next is not resent:
  - smb/server: map SET_INFO ENOSPC to disk full

The following patches are already in upstream and are not resent:
  - 898d280f4e4d smb/client: name the default fallocate mode
  - 2a4b3d2db5c6 smb/client: preserve errors from smb2_set_sparse()
  - 99cd0a6eeb6c smb/client: do not account EOF extension as allocation

Link to v6:
https://lore.kernel.org/linux-cifs/20260701152157.822207-1-huiwen.he@linux.dev/

Thanks,
Huiwen

Huiwen He (4):
  smb/client: refresh allocation size after duplicate extents
  smb/client: reduce fallocate zero buffer allocation
  smb/client: emulate small EOF-extending mode 0 fallocate ranges
  smb/client: refresh allocation after EOF-extending fallocate

 fs/smb/client/cifsfs.c    |  10 ++-
 fs/smb/client/smb2ops.c   | 147 ++++++++++++++++++++++++++++++++++----
 fs/smb/client/smb2pdu.c   |  19 +++++
 fs/smb/client/smb2proto.h |   3 +
 fs/smb/common/fscc.h      |   5 ++
 fs/smb/server/smb2pdu.h   |   4 --
 6 files changed, 167 insertions(+), 21 deletions(-)

-- 
2.43.0

[PATCH v7 1/4] smb/client: refresh allocation size after duplicate extents

[Huiwen He]

From: Huiwen He <hehuiwen@kylinos.cn>

FSCTL_DUPLICATE_EXTENTS_TO_FILE changes the target file extents on the
server, but the client does not refresh the target AllocationSize/i_blocks.
Callers can observe or use the wrong st_blocks value immediately after the
clone, before a later attribute revalidation corrects it.

For example, create a reflinked file with a leading hole:

        xfs_io -f -c "pwrite -S 0x61 0 64k" src
        touch dst
        chmod 600 dst
        xfs_io -c "reflink src 0 1m 64k" dst
        mkswap dst
        swapon dst

The file still has a hole after mkswap:

        /mnt/scratch/dst:
          [0..7]:       allocated
          [8..2047]:    hole
          [2048..2175]: allocated

The server also reports only the allocated ranges:

        server dst size=1114112 blocks=144

but the client reported EOF-derived blocks:

        client dst size=1114112 blocks=2176

and swapon succeeded:

        swapon_result=success
        /mnt/scratch/dst 1.1M 0B -1

So EOF-derived i_blocks can let a sparse reflinked file pass the CIFS
swapfile hole check.

Fix this by querying FILE_ALL_INFORMATION on the target handle after a
successful duplicate extents request. Update i_blocks from AllocationSize
and keep the refreshed target inode attributes valid so a following stat
does not immediately revalidate again.

If the query fails, mark the cached inode attributes stale so a later
getattr can refresh them.

This also fixes the xfstests generic/370 regression introduced by the
i_blocks accounting change, as tested on a Samba "vfs objects = btrfs"
share.

Fixes: 99cd0a6eeb6c ("smb/client: do not account EOF extension as allocation")
Signed-off-by: Huiwen He <hehuiwen@kylinos.cn>
Reviewed-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
---
 fs/smb/client/cifsfs.c  | 10 +++++++---
 fs/smb/client/smb2ops.c | 30 ++++++++++++++++++++++++++++++
 2 files changed, 37 insertions(+), 3 deletions(-)

diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index ea4fc0fa68ca..7fc2b0ad950d 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -1478,9 +1478,13 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
 		}
 	}
 
-	/* force revalidate of size and timestamps of target file now
-	   that target is updated on the server */
-	CIFS_I(target_inode)->time = 0;
+	/*
+	 * On success, duplicate_extents already updated the target inode attrs
+	 * or marked them stale if the refresh failed.  On failure, mark attrs
+	 * stale because EOF may have changed before the clone failed.
+	 */
+	if (rc)
+		CIFS_I(target_inode)->time = 0;
 unlock:
 	/* although unlocking in the reverse order from locking is not
 	   strictly necessary here it is a little cleaner to be consistent */
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 06e9322a762a..26366098c4b7 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -2193,10 +2193,14 @@ smb2_duplicate_extents(const unsigned int xid,
 			u64 len, u64 dest_off)
 {
 	int rc;
+	int qrc;
 	unsigned int ret_data_len;
 	struct inode *inode;
+	struct smb2_file_all_info file_inf;
 	struct duplicate_extents_to_file dup_ext_buf;
+	struct timespec64 ts;
 	struct cifs_tcon *tcon = tlink_tcon(trgtfile->tlink);
+	u64 asize;
 
 	/* server fileays advertise duplicate extent support with this flag */
 	if ((le32_to_cpu(tcon->fsAttrInfo.Attributes) &
@@ -2232,6 +2236,32 @@ smb2_duplicate_extents(const unsigned int xid,
 	if (ret_data_len > 0)
 		cifs_dbg(FYI, "Non-zero response length in duplicate extents\n");
 
+	if (rc == 0) {
+		qrc = SMB2_query_info(xid, tcon, trgtfile->fid.persistent_fid,
+				      trgtfile->fid.volatile_fid, &file_inf);
+		spin_lock(&inode->i_lock);
+		if (qrc == 0) {
+			asize = le64_to_cpu(file_inf.AllocationSize);
+			CIFS_I(inode)->time = jiffies;
+			if (file_inf.LastWriteTime) {
+				ts = cifs_NTtimeToUnix(file_inf.LastWriteTime);
+				inode_set_mtime_to_ts(inode, ts);
+			}
+			if (file_inf.ChangeTime) {
+				ts = cifs_NTtimeToUnix(file_inf.ChangeTime);
+				inode_set_ctime_to_ts(inode, ts);
+			}
+			if (file_inf.LastAccessTime) {
+				ts = cifs_NTtimeToUnix(file_inf.LastAccessTime);
+				inode_set_atime_to_ts(inode, ts);
+			}
+			inode->i_blocks = CIFS_INO_BLOCKS(asize);
+		} else {
+			CIFS_I(inode)->time = 0; /* force reval */
+		}
+		spin_unlock(&inode->i_lock);
+	}
+
 duplicate_extents_out:
 	if (rc)
 		trace_smb3_clone_err(xid, srcfile->fid.volatile_fid,
-- 
2.43.0

[PATCH v7 2/4] smb/client: reduce fallocate zero buffer allocation

[Huiwen He]

From: Huiwen He <hehuiwen@kylinos.cn>

The fallocate emulation allocates a 1 MiB zero-filled buffer even
though each SMB2_write request is limited to SMB2_MAX_BUFFER_SIZE,
which is 64 KiB. A high-order 1 MiB allocation is more likely to
fail on a fragmented system.

Allocate only the smaller of the requested range and SMB2_MAX_BUFFER_SIZE,
and reuse that zero-filled buffer for every write request. Also reject
a successful write that makes no progress to avoid looping indefinitely.

This reduces the contiguous allocation required by fallocate emulation
without changing the written data or range semantics.

Signed-off-by: Huiwen He <hehuiwen@kylinos.cn>
Reviewed-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
---
 fs/smb/client/smb2ops.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 26366098c4b7..e6a7ac8cd99e 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -3573,7 +3573,7 @@ static int smb3_simple_fallocate_write_range(unsigned int xid,
 					     char *buf)
 {
 	struct cifs_io_parms io_parms = {0};
-	int nbytes;
+	unsigned int nbytes;
 	int rc = 0;
 	struct kvec iov[2];
 
@@ -3594,9 +3594,10 @@ static int smb3_simple_fallocate_write_range(unsigned int xid,
 		rc = SMB2_write(xid, &io_parms, &nbytes, iov, 1);
 		if (rc)
 			break;
+		if (!nbytes)
+			return -EIO;
 		if (nbytes > len)
 			return -EINVAL;
-		buf += nbytes;
 		off += nbytes;
 		len -= nbytes;
 	}
@@ -3625,7 +3626,7 @@ static int smb3_simple_fallocate_range(unsigned int xid,
 	if (rc)
 		goto out;
 
-	buf = kzalloc(1024 * 1024, GFP_KERNEL);
+	buf = kzalloc(min_t(loff_t, len, SMB2_MAX_BUFFER_SIZE), GFP_KERNEL);
 	if (buf == NULL) {
 		rc = -ENOMEM;
 		goto out;
-- 
2.43.0

[PATCH v7 3/4] smb/client: emulate small EOF-extending mode 0 fallocate ranges

[Huiwen He]

From: Huiwen He <hehuiwen@kylinos.cn>

When a mode 0 fallocate extends EOF from 1G to 2G + 1M, the client
currently sends SetEOF for 2G + 1M. This can make fallocate return
success without allocating the requested range, or allocate extra
space before that range.

For example, on a fresh file:

        xfs_io -f \
          -c "falloc 0 1G" \
          -c "falloc 2G 1M" \
          -c "truncate 3G" test

The second fallocate should allocate [2G, 2G + 1M), leaving [1G, 2G)
as a hole.

Before this change, the result depended on the server allocation policy.
With Samba "strict allocate = no", SetEOF could return success without
allocating [2G, 2G + 1M). With "strict allocate = yes":

	# filefrag -v test
        [0, 1G)             allocated
        [1G, 2G)            allocated unexpectedly
        [2G, 2G + 1M)       allocated

SMB cannot allocate that arbitrary range, so write zeroes to small
EOF-extending ranges instead. Limit this to 1 MiB to bound the
client-side I/O cost.

With "strict allocate = no", the requested range [2G, 2G + 1M) is
allocated by the writes. With "strict allocate = yes":

	# filefrag -v test
        [0, 1G)             allocated
        [1G, 2G)            hole
        [2G, 2G + 1M)       allocated

This fixes the small EOF-extending range case exercised by generic/213.

Signed-off-by: Huiwen He <hehuiwen@kylinos.cn>
Reviewed-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
---
 fs/smb/client/smb2ops.c | 69 +++++++++++++++++++++++++++++++++++------
 1 file changed, 60 insertions(+), 9 deletions(-)

diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index e6a7ac8cd99e..9ccc7eb52899 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -3610,11 +3610,24 @@ static int smb3_simple_fallocate_range(unsigned int xid,
 				       loff_t off, loff_t len)
 {
 	struct file_allocated_range_buffer in_data, *out_data = NULL, *tmp_data;
+	struct inode *inode = d_inode(cfile->dentry);
 	u32 out_data_len;
 	char *buf = NULL;
 	loff_t l;
 	int rc;
 
+	buf = kzalloc(min_t(loff_t, len, SMB2_MAX_BUFFER_SIZE), GFP_KERNEL);
+	if (!buf) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	if (off >= i_size_read(inode)) {
+		rc = smb3_simple_fallocate_write_range(xid, tcon, cfile,
+						       off, len, buf);
+		goto out;
+	}
+
 	in_data.file_offset = cpu_to_le64(off);
 	in_data.length = cpu_to_le64(len);
 	rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
@@ -3626,12 +3639,6 @@ static int smb3_simple_fallocate_range(unsigned int xid,
 	if (rc)
 		goto out;
 
-	buf = kzalloc(min_t(loff_t, len, SMB2_MAX_BUFFER_SIZE), GFP_KERNEL);
-	if (buf == NULL) {
-		rc = -ENOMEM;
-		goto out;
-	}
-
 	tmp_data = out_data;
 	while (len) {
 		/*
@@ -3696,18 +3703,22 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
 	struct cifsFileInfo *cfile = file->private_data;
 	long rc = -EOPNOTSUPP;
 	unsigned int xid;
-	loff_t new_eof;
+	loff_t old_eof, new_eof;
+	struct smb2_file_all_info file_inf;
+	u64 asize;
+	int qrc;
 
 	xid = get_xid();
 
 	inode = d_inode(cfile->dentry);
 	cifsi = CIFS_I(inode);
+	old_eof = i_size_read(inode);
 
 	trace_smb3_falloc_enter(xid, cfile->fid.persistent_fid, tcon->tid,
 				tcon->ses->Suid, off, len);
 	/* if file not oplocked can't be sure whether asking to extend size */
 	if (!CIFS_CACHE_READ(cifsi))
-		if (keep_size == false) {
+		if (!keep_size) {
 			trace_smb3_falloc_err(xid, cfile->fid.persistent_fid,
 				tcon->tid, tcon->ses->Suid, off, len, rc);
 			free_xid(xid);
@@ -3717,11 +3728,51 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
 	/*
 	 * Extending the file
 	 */
-	if ((keep_size == false) && i_size_read(inode) < off + len) {
+	if (!keep_size && old_eof < off + len) {
 		rc = inode_newsize_ok(inode, off + len);
 		if (rc)
 			goto out;
 
+		/*
+		 * A small range at or beyond EOF can be allocated by writing
+		 * zeroes.  For off > old_eof, this preserves the intervening
+		 * hole instead of allocating from offset 0.
+		 */
+		if (off > old_eof ||
+		    (off == old_eof && old_eof != 0 &&
+		     (cifsi->cifsAttrs & FILE_ATTRIBUTE_SPARSE_FILE))) {
+			if (len > 1024 * 1024) {
+				rc = -EOPNOTSUPP;
+				goto out;
+			}
+
+			rc = smb3_simple_fallocate_range(xid, tcon, cfile,
+							 off, len);
+			if (rc) {
+				spin_lock(&inode->i_lock);
+				cifsi->time = 0;
+				spin_unlock(&inode->i_lock);
+				goto out;
+			}
+
+			new_eof = off + len;
+			netfs_resize_file(&cifsi->netfs, new_eof, true);
+			cifs_setsize(inode, new_eof);
+
+			qrc = SMB2_query_info(xid, tcon,
+					      cfile->fid.persistent_fid,
+					      cfile->fid.volatile_fid, &file_inf);
+			spin_lock(&inode->i_lock);
+			if (qrc == 0) {
+				asize = le64_to_cpu(file_inf.AllocationSize);
+				inode->i_blocks = CIFS_INO_BLOCKS(asize);
+			} else {
+				cifsi->time = 0;
+			}
+			spin_unlock(&inode->i_lock);
+			goto out;
+		}
+
 		if (cifsi->cifsAttrs & FILE_ATTRIBUTE_SPARSE_FILE)
 			smb2_set_sparse(xid, tcon, cfile, inode, false);
 
-- 
2.43.0

[PATCH v7 4/4] smb/client: refresh allocation after EOF-extending fallocate

[Huiwen He]

From: Huiwen He <hehuiwen@kylinos.cn>

Before this change, xfstests generic/496 was not supported on ksmbd:

        generic/496 ... [not run] fallocated swap not supported here

ksmbd handles SetEOF as truncate, so EOF extension alone does not
allocate backing blocks. A fallocated swapfile can therefore still
look sparse to swapon.

Request allocation for EOF-extending fallocate ranges that can be
represented by FILE_ALLOCATION_INFORMATION, and refresh the allocation
state afterwards.

With this change, xfstests generic/496 and generic/701 pass on ksmbd.

However, Samba "strict allocate = no" now exposes the real generic/701
failure: the old pass came from inflated local i_blocks, not from
server allocation. generic/213 also fails in that case because an
oversized allocation request may not return ENOSPC.

Signed-off-by: Huiwen He <hehuiwen@kylinos.cn>
Reviewed-by: ChenXiaoSong <chenxiaosong@kylinos.cn>
---
 fs/smb/client/smb2ops.c   | 43 ++++++++++++++++++++++++++++++++++++---
 fs/smb/client/smb2pdu.c   | 19 +++++++++++++++++
 fs/smb/client/smb2proto.h |  3 +++
 fs/smb/common/fscc.h      |  5 +++++
 fs/smb/server/smb2pdu.h   |  4 ----
 5 files changed, 67 insertions(+), 7 deletions(-)

diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 9ccc7eb52899..a57367a03d0b 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -3777,12 +3777,49 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
 			smb2_set_sparse(xid, tcon, cfile, inode, false);
 
 		new_eof = off + len;
+
+		qrc = SMB2_query_info(xid, tcon,
+				      cfile->fid.persistent_fid,
+				      cfile->fid.volatile_fid, &file_inf);
+		if (qrc == 0)
+			asize = le64_to_cpu(file_inf.AllocationSize);
+
+		/*
+		 * FILE_ALLOCATION_INFORMATION can only describe allocation up to
+		 * new_eof. Some servers may accept it without allocating blocks,
+		 * so refresh AllocationSize before updating i_blocks.
+		 */
+		if (off == 0 || off == old_eof) {
+			if (qrc || asize < new_eof) {
+				rc = SMB2_set_allocation(xid, tcon,
+							 cfile->fid.persistent_fid,
+							 cfile->fid.volatile_fid,
+							 cfile->pid, new_eof);
+				if (rc)
+					goto out;
+			}
+		}
+
 		rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid,
 				  cfile->fid.volatile_fid, cfile->pid, new_eof);
-		if (rc == 0) {
-			netfs_resize_file(&cifsi->netfs, new_eof, true);
-			cifs_setsize(inode, new_eof);
+		if (rc)
+			goto out;
+
+		netfs_resize_file(&cifsi->netfs, new_eof, true);
+		cifs_setsize(inode, new_eof);
+
+		qrc = SMB2_query_info(xid, tcon,
+				      cfile->fid.persistent_fid,
+				      cfile->fid.volatile_fid, &file_inf);
+		spin_lock(&inode->i_lock);
+		if (qrc == 0) {
+			asize = le64_to_cpu(file_inf.AllocationSize);
+			if (asize >= new_eof)
+				inode->i_blocks = CIFS_INO_BLOCKS(asize);
+		} else {
+			cifsi->time = 0;
 		}
+		spin_unlock(&inode->i_lock);
 		goto out;
 	}
 
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index d058584b8f05..1374bbae627f 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -5947,6 +5947,25 @@ SMB2_set_eof(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 			0, 1, &data, &size);
 }
 
+int
+SMB2_set_allocation(const unsigned int xid, struct cifs_tcon *tcon,
+		    u64 persistent_fid, u64 volatile_fid, u32 pid,
+		    loff_t allocation_size)
+{
+	struct smb2_file_alloc_info info;
+	void *data;
+	unsigned int size;
+
+	info.AllocationSize = cpu_to_le64(allocation_size);
+
+	data = &info;
+	size = sizeof(struct smb2_file_alloc_info);
+
+	return send_set_info(xid, tcon, persistent_fid, volatile_fid,
+			pid, FILE_ALLOCATION_INFORMATION, SMB2_O_INFO_FILE,
+			0, 1, &data, &size);
+}
+
 int
 SMB2_set_acl(const unsigned int xid, struct cifs_tcon *tcon,
 		u64 persistent_fid, u64 volatile_fid,
diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h
index 78a4e1c340f9..16a02c1eb0a1 100644
--- a/fs/smb/client/smb2proto.h
+++ b/fs/smb/client/smb2proto.h
@@ -204,6 +204,9 @@ void SMB2_query_directory_free(struct smb_rqst *rqst);
 int SMB2_set_eof(const unsigned int xid, struct cifs_tcon *tcon,
 		 u64 persistent_fid, u64 volatile_fid, u32 pid,
 		 loff_t new_eof);
+int SMB2_set_allocation(const unsigned int xid, struct cifs_tcon *tcon,
+			u64 persistent_fid, u64 volatile_fid, u32 pid,
+			loff_t allocation_size);
 int SMB2_set_info_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server,
 		       struct smb_rqst *rqst, u64 persistent_fid,
 		       u64 volatile_fid, u32 pid, u8 info_class, u8 info_type,
diff --git a/fs/smb/common/fscc.h b/fs/smb/common/fscc.h
index 859849a42fec..941db5a95564 100644
--- a/fs/smb/common/fscc.h
+++ b/fs/smb/common/fscc.h
@@ -283,6 +283,11 @@ struct smb2_file_eof_info { /* encoding of request for level 10 */
 	__le64 EndOfFile; /* new end of file value */
 } __packed; /* level 20 Set */
 
+/* See MS-FSCC 2.4.4 */
+struct smb2_file_alloc_info { /* encoding of request for level 19 */
+	__le64 AllocationSize;
+} __packed;
+
 /* See MS-FSCC 2.4.15 */
 typedef struct {
 	__le32 NextEntryOffset;
diff --git a/fs/smb/server/smb2pdu.h b/fs/smb/server/smb2pdu.h
index c2512dbcdec8..aa06c8c905f1 100644
--- a/fs/smb/server/smb2pdu.h
+++ b/fs/smb/server/smb2pdu.h
@@ -212,10 +212,6 @@ struct smb2_file_ea_info {
 	__le32 EASize;
 } __packed;
 
-struct smb2_file_alloc_info {
-	__le64 AllocationSize;
-} __packed;
-
 struct smb2_file_disposition_info {
 	__u8 DeletePending;
 } __packed;
-- 
2.43.0