summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/affs/file.c9
-rw-r--r--fs/efivarfs/file.c10
-rw-r--r--fs/efivarfs/super.c3
-rw-r--r--fs/exfat/balloc.c10
-rw-r--r--fs/exfat/exfat_fs.h2
-rw-r--r--fs/exfat/fatent.c11
-rw-r--r--fs/exfat/file.c2
-rw-r--r--fs/exfat/namei.c7
-rw-r--r--fs/fuse/dev.c13
-rw-r--r--fs/pipe.c26
-rw-r--r--fs/smb/client/cifsacl.c34
-rw-r--r--fs/smb/client/cifssmb.c3
-rw-r--r--fs/smb/common/smbacl.h3
-rw-r--r--fs/smb/server/smb2pdu.c8
-rw-r--r--fs/smb/server/smbacl.c52
-rw-r--r--fs/smb/server/smbacl.h2
-rw-r--r--fs/smb/server/transport_ipc.c1
-rw-r--r--fs/xfs/xfs_buf.c182
-rw-r--r--fs/xfs/xfs_buf.h7
-rw-r--r--fs/xfs/xfs_buf_mem.c2
-rw-r--r--fs/xfs/xfs_log_recover.c2
-rw-r--r--fs/xfs/xfs_mount.c7
-rw-r--r--fs/xfs/xfs_rtalloc.c2
-rw-r--r--fs/xfs/xfs_trace.h1
24 files changed, 189 insertions, 210 deletions
diff --git a/fs/affs/file.c b/fs/affs/file.c
index a5a861dd5223..7a71018e3f67 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -596,7 +596,7 @@ affs_extent_file_ofs(struct inode *inode, u32 newsize)
BUG_ON(tmp > bsize);
AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA);
AFFS_DATA_HEAD(bh)->key = cpu_to_be32(inode->i_ino);
- AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx);
+ AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx + 1);
AFFS_DATA_HEAD(bh)->size = cpu_to_be32(tmp);
affs_fix_checksum(sb, bh);
bh->b_state &= ~(1UL << BH_New);
@@ -724,7 +724,8 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
tmp = min(bsize - boff, to - from);
BUG_ON(boff + tmp > bsize || tmp > bsize);
memcpy(AFFS_DATA(bh) + boff, data + from, tmp);
- be32_add_cpu(&AFFS_DATA_HEAD(bh)->size, tmp);
+ AFFS_DATA_HEAD(bh)->size = cpu_to_be32(
+ max(boff + tmp, be32_to_cpu(AFFS_DATA_HEAD(bh)->size)));
affs_fix_checksum(sb, bh);
mark_buffer_dirty_inode(bh, inode);
written += tmp;
@@ -746,7 +747,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
if (buffer_new(bh)) {
AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA);
AFFS_DATA_HEAD(bh)->key = cpu_to_be32(inode->i_ino);
- AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx);
+ AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx + 1);
AFFS_DATA_HEAD(bh)->size = cpu_to_be32(bsize);
AFFS_DATA_HEAD(bh)->next = 0;
bh->b_state &= ~(1UL << BH_New);
@@ -780,7 +781,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
if (buffer_new(bh)) {
AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA);
AFFS_DATA_HEAD(bh)->key = cpu_to_be32(inode->i_ino);
- AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx);
+ AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx + 1);
AFFS_DATA_HEAD(bh)->size = cpu_to_be32(tmp);
AFFS_DATA_HEAD(bh)->next = 0;
bh->b_state &= ~(1UL << BH_New);
diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c
index cb1b6d0c3454..c294a8fc566d 100644
--- a/fs/efivarfs/file.c
+++ b/fs/efivarfs/file.c
@@ -57,10 +57,11 @@ static ssize_t efivarfs_file_write(struct file *file,
if (bytes == -ENOENT) {
/*
- * zero size signals to release that the write deleted
- * the variable
+ * FIXME: temporary workaround for fwupdate, signal
+ * failed write with a 1 to keep created but not
+ * written files
*/
- i_size_write(inode, 0);
+ i_size_write(inode, 1);
} else {
i_size_write(inode, datasize + sizeof(attributes));
inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
@@ -124,7 +125,8 @@ static int efivarfs_file_release(struct inode *inode, struct file *file)
struct efivar_entry *var = inode->i_private;
inode_lock(inode);
- var->removed = (--var->open_count == 0 && i_size_read(inode) == 0);
+ /* FIXME: temporary work around for fwupdate */
+ var->removed = (--var->open_count == 0 && i_size_read(inode) == 1);
inode_unlock(inode);
if (var->removed)
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index 09fcf731e65d..6eae8cf655c1 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -367,6 +367,8 @@ static int efivarfs_fill_super(struct super_block *sb, struct fs_context *fc)
if (err)
return err;
+ register_pm_notifier(&sfi->pm_nb);
+
return efivar_init(efivarfs_callback, sb, true);
}
@@ -552,7 +554,6 @@ static int efivarfs_init_fs_context(struct fs_context *fc)
sfi->pm_nb.notifier_call = efivarfs_pm_notify;
sfi->pm_nb.priority = 0;
- register_pm_notifier(&sfi->pm_nb);
return 0;
}
diff --git a/fs/exfat/balloc.c b/fs/exfat/balloc.c
index ce9be95c9172..9ff825f1502d 100644
--- a/fs/exfat/balloc.c
+++ b/fs/exfat/balloc.c
@@ -141,7 +141,7 @@ int exfat_set_bitmap(struct inode *inode, unsigned int clu, bool sync)
return 0;
}
-void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync)
+int exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync)
{
int i, b;
unsigned int ent_idx;
@@ -150,13 +150,17 @@ void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync)
struct exfat_mount_options *opts = &sbi->options;
if (!is_valid_cluster(sbi, clu))
- return;
+ return -EIO;
ent_idx = CLUSTER_TO_BITMAP_ENT(clu);
i = BITMAP_OFFSET_SECTOR_INDEX(sb, ent_idx);
b = BITMAP_OFFSET_BIT_IN_SECTOR(sb, ent_idx);
+ if (!test_bit_le(b, sbi->vol_amap[i]->b_data))
+ return -EIO;
+
clear_bit_le(b, sbi->vol_amap[i]->b_data);
+
exfat_update_bh(sbi->vol_amap[i], sync);
if (opts->discard) {
@@ -171,6 +175,8 @@ void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync)
opts->discard = 0;
}
}
+
+ return 0;
}
/*
diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h
index 78be6964a8a0..d30ce18a88b7 100644
--- a/fs/exfat/exfat_fs.h
+++ b/fs/exfat/exfat_fs.h
@@ -456,7 +456,7 @@ int exfat_count_num_clusters(struct super_block *sb,
int exfat_load_bitmap(struct super_block *sb);
void exfat_free_bitmap(struct exfat_sb_info *sbi);
int exfat_set_bitmap(struct inode *inode, unsigned int clu, bool sync);
-void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync);
+int exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync);
unsigned int exfat_find_free_bitmap(struct super_block *sb, unsigned int clu);
int exfat_count_used_clusters(struct super_block *sb, unsigned int *ret_count);
int exfat_trim_fs(struct inode *inode, struct fstrim_range *range);
diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c
index 9e5492ac409b..6f3651c6ca91 100644
--- a/fs/exfat/fatent.c
+++ b/fs/exfat/fatent.c
@@ -175,6 +175,7 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain
BITMAP_OFFSET_SECTOR_INDEX(sb, CLUSTER_TO_BITMAP_ENT(clu));
if (p_chain->flags == ALLOC_NO_FAT_CHAIN) {
+ int err;
unsigned int last_cluster = p_chain->dir + p_chain->size - 1;
do {
bool sync = false;
@@ -189,7 +190,9 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain
cur_cmap_i = next_cmap_i;
}
- exfat_clear_bitmap(inode, clu, (sync && IS_DIRSYNC(inode)));
+ err = exfat_clear_bitmap(inode, clu, (sync && IS_DIRSYNC(inode)));
+ if (err)
+ break;
clu++;
num_clusters++;
} while (num_clusters < p_chain->size);
@@ -210,12 +213,13 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain
cur_cmap_i = next_cmap_i;
}
- exfat_clear_bitmap(inode, clu, (sync && IS_DIRSYNC(inode)));
+ if (exfat_clear_bitmap(inode, clu, (sync && IS_DIRSYNC(inode))))
+ break;
clu = n_clu;
num_clusters++;
if (err)
- goto dec_used_clus;
+ break;
if (num_clusters >= sbi->num_clusters - EXFAT_FIRST_CLUSTER) {
/*
@@ -229,7 +233,6 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain
} while (clu != EXFAT_EOF_CLUSTER);
}
-dec_used_clus:
sbi->used_clusters -= num_clusters;
return 0;
}
diff --git a/fs/exfat/file.c b/fs/exfat/file.c
index 05b51e721783..807349d8ea05 100644
--- a/fs/exfat/file.c
+++ b/fs/exfat/file.c
@@ -587,7 +587,7 @@ static ssize_t exfat_file_write_iter(struct kiocb *iocb, struct iov_iter *iter)
valid_size = ei->valid_size;
ret = generic_write_checks(iocb, iter);
- if (ret < 0)
+ if (ret <= 0)
goto unlock;
if (iocb->ki_flags & IOCB_DIRECT) {
diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c
index 691dd77b6ab5..8b30027d8251 100644
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -232,7 +232,7 @@ static int exfat_search_empty_slot(struct super_block *sb,
dentry = 0;
}
- while (dentry + num_entries < total_entries &&
+ while (dentry + num_entries <= total_entries &&
clu.dir != EXFAT_EOF_CLUSTER) {
i = dentry & (dentries_per_clu - 1);
@@ -646,6 +646,11 @@ static int exfat_find(struct inode *dir, struct qstr *qname,
info->valid_size = le64_to_cpu(ep2->dentry.stream.valid_size);
info->size = le64_to_cpu(ep2->dentry.stream.size);
+ if (unlikely(EXFAT_B_TO_CLU_ROUND_UP(info->size, sbi) > sbi->used_clusters)) {
+ exfat_fs_error(sb, "data size is invalid(%lld)", info->size);
+ return -EIO;
+ }
+
info->start_clu = le32_to_cpu(ep2->dentry.stream.start_clu);
if (!is_valid_cluster(sbi, info->start_clu) && info->size) {
exfat_warn(sb, "start_clu is invalid cluster(0x%x)",
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 2b2d1b755544..3c9caafca9e2 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -2107,7 +2107,7 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
struct file *out, loff_t *ppos,
size_t len, unsigned int flags)
{
- unsigned int head, tail, mask, count;
+ unsigned int head, tail, count;
unsigned nbuf;
unsigned idx;
struct pipe_buffer *bufs;
@@ -2124,8 +2124,7 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
head = pipe->head;
tail = pipe->tail;
- mask = pipe->ring_size - 1;
- count = head - tail;
+ count = pipe_occupancy(head, tail);
bufs = kvmalloc_array(count, sizeof(struct pipe_buffer), GFP_KERNEL);
if (!bufs) {
@@ -2135,8 +2134,8 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
nbuf = 0;
rem = 0;
- for (idx = tail; idx != head && rem < len; idx++)
- rem += pipe->bufs[idx & mask].len;
+ for (idx = tail; !pipe_empty(head, idx) && rem < len; idx++)
+ rem += pipe_buf(pipe, idx)->len;
ret = -EINVAL;
if (rem < len)
@@ -2147,10 +2146,10 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
struct pipe_buffer *ibuf;
struct pipe_buffer *obuf;
- if (WARN_ON(nbuf >= count || tail == head))
+ if (WARN_ON(nbuf >= count || pipe_empty(head, tail)))
goto out_free;
- ibuf = &pipe->bufs[tail & mask];
+ ibuf = pipe_buf(pipe, tail);
obuf = &bufs[nbuf];
if (rem >= ibuf->len) {
diff --git a/fs/pipe.c b/fs/pipe.c
index ce1af7592780..5c872775a6db 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -210,11 +210,10 @@ static const struct pipe_buf_operations anon_pipe_buf_ops = {
/* Done while waiting without holding the pipe lock - thus the READ_ONCE() */
static inline bool pipe_readable(const struct pipe_inode_info *pipe)
{
- unsigned int head = READ_ONCE(pipe->head);
- unsigned int tail = READ_ONCE(pipe->tail);
+ union pipe_index idx = { .head_tail = READ_ONCE(pipe->head_tail) };
unsigned int writers = READ_ONCE(pipe->writers);
- return !pipe_empty(head, tail) || !writers;
+ return !pipe_empty(idx.head, idx.tail) || !writers;
}
static inline unsigned int pipe_update_tail(struct pipe_inode_info *pipe,
@@ -417,11 +416,10 @@ static inline int is_packetized(struct file *file)
/* Done while waiting without holding the pipe lock - thus the READ_ONCE() */
static inline bool pipe_writable(const struct pipe_inode_info *pipe)
{
- unsigned int head = READ_ONCE(pipe->head);
- unsigned int tail = READ_ONCE(pipe->tail);
+ union pipe_index idx = { .head_tail = READ_ONCE(pipe->head_tail) };
unsigned int max_usage = READ_ONCE(pipe->max_usage);
- return !pipe_full(head, tail, max_usage) ||
+ return !pipe_full(idx.head, idx.tail, max_usage) ||
!READ_ONCE(pipe->readers);
}
@@ -616,7 +614,7 @@ out:
static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct pipe_inode_info *pipe = filp->private_data;
- unsigned int count, head, tail, mask;
+ unsigned int count, head, tail;
switch (cmd) {
case FIONREAD:
@@ -624,10 +622,9 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
count = 0;
head = pipe->head;
tail = pipe->tail;
- mask = pipe->ring_size - 1;
- while (tail != head) {
- count += pipe->bufs[tail & mask].len;
+ while (!pipe_empty(head, tail)) {
+ count += pipe_buf(pipe, tail)->len;
tail++;
}
mutex_unlock(&pipe->mutex);
@@ -659,7 +656,7 @@ pipe_poll(struct file *filp, poll_table *wait)
{
__poll_t mask;
struct pipe_inode_info *pipe = filp->private_data;
- unsigned int head, tail;
+ union pipe_index idx;
/* Epoll has some historical nasty semantics, this enables them */
WRITE_ONCE(pipe->poll_usage, true);
@@ -680,19 +677,18 @@ pipe_poll(struct file *filp, poll_table *wait)
* if something changes and you got it wrong, the poll
* table entry will wake you up and fix it.
*/
- head = READ_ONCE(pipe->head);
- tail = READ_ONCE(pipe->tail);
+ idx.head_tail = READ_ONCE(pipe->head_tail);
mask = 0;
if (filp->f_mode & FMODE_READ) {
- if (!pipe_empty(head, tail))
+ if (!pipe_empty(idx.head, idx.tail))
mask |= EPOLLIN | EPOLLRDNORM;
if (!pipe->writers && filp->f_pipe != pipe->w_counter)
mask |= EPOLLHUP;
}
if (filp->f_mode & FMODE_WRITE) {
- if (!pipe_full(head, tail, pipe->max_usage))
+ if (!pipe_full(idx.head, idx.tail, pipe->max_usage))
mask |= EPOLLOUT | EPOLLWRNORM;
/*
* Most Unices do not set EPOLLERR for FIFOs but on Linux they
diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c
index 699a3f76d083..64bd68f750f8 100644
--- a/fs/smb/client/cifsacl.c
+++ b/fs/smb/client/cifsacl.c
@@ -763,7 +763,7 @@ static void parse_dacl(struct smb_acl *pdacl, char *end_of_acl,
struct cifs_fattr *fattr, bool mode_from_special_sid)
{
int i;
- int num_aces = 0;
+ u16 num_aces = 0;
int acl_size;
char *acl_base;
struct smb_ace **ppace;
@@ -778,14 +778,15 @@ static void parse_dacl(struct smb_acl *pdacl, char *end_of_acl,
}
/* validate that we do not go past end of acl */
- if (end_of_acl < (char *)pdacl + le16_to_cpu(pdacl->size)) {
+ if (end_of_acl < (char *)pdacl + sizeof(struct smb_acl) ||
+ end_of_acl < (char *)pdacl + le16_to_cpu(pdacl->size)) {
cifs_dbg(VFS, "ACL too small to parse DACL\n");
return;
}
cifs_dbg(NOISY, "DACL revision %d size %d num aces %d\n",
le16_to_cpu(pdacl->revision), le16_to_cpu(pdacl->size),
- le32_to_cpu(pdacl->num_aces));
+ le16_to_cpu(pdacl->num_aces));
/* reset rwx permissions for user/group/other.
Also, if num_aces is 0 i.e. DACL has no ACEs,
@@ -795,12 +796,15 @@ static void parse_dacl(struct smb_acl *pdacl, char *end_of_acl,
acl_base = (char *)pdacl;
acl_size = sizeof(struct smb_acl);
- num_aces = le32_to_cpu(pdacl->num_aces);
+ num_aces = le16_to_cpu(pdacl->num_aces);
if (num_aces > 0) {
umode_t denied_mode = 0;
- if (num_aces > ULONG_MAX / sizeof(struct smb_ace *))
+ if (num_aces > (le16_to_cpu(pdacl->size) - sizeof(struct smb_acl)) /
+ (offsetof(struct smb_ace, sid) +
+ offsetof(struct smb_sid, sub_auth) + sizeof(__le16)))
return;
+
ppace = kmalloc_array(num_aces, sizeof(struct smb_ace *),
GFP_KERNEL);
if (!ppace)
@@ -937,12 +941,12 @@ unsigned int setup_special_user_owner_ACE(struct smb_ace *pntace)
static void populate_new_aces(char *nacl_base,
struct smb_sid *pownersid,
struct smb_sid *pgrpsid,
- __u64 *pnmode, u32 *pnum_aces, u16 *pnsize,
+ __u64 *pnmode, u16 *pnum_aces, u16 *pnsize,
bool modefromsid,
bool posix)
{
__u64 nmode;
- u32 num_aces = 0;
+ u16 num_aces = 0;
u16 nsize = 0;
__u64 user_mode;
__u64 group_mode;
@@ -1050,7 +1054,7 @@ static __u16 replace_sids_and_copy_aces(struct smb_acl *pdacl, struct smb_acl *p
u16 size = 0;
struct smb_ace *pntace = NULL;
char *acl_base = NULL;
- u32 src_num_aces = 0;
+ u16 src_num_aces = 0;
u16 nsize = 0;
struct smb_ace *pnntace = NULL;
char *nacl_base = NULL;
@@ -1058,7 +1062,7 @@ static __u16 replace_sids_and_copy_aces(struct smb_acl *pdacl, struct smb_acl *p
acl_base = (char *)pdacl;
size = sizeof(struct smb_acl);
- src_num_aces = le32_to_cpu(pdacl->num_aces);
+ src_num_aces = le16_to_cpu(pdacl->num_aces);
nacl_base = (char *)pndacl;
nsize = sizeof(struct smb_acl);
@@ -1090,11 +1094,11 @@ static int set_chmod_dacl(struct smb_acl *pdacl, struct smb_acl *pndacl,
u16 size = 0;
struct smb_ace *pntace = NULL;
char *acl_base = NULL;
- u32 src_num_aces = 0;
+ u16 src_num_aces = 0;
u16 nsize = 0;
struct smb_ace *pnntace = NULL;
char *nacl_base = NULL;
- u32 num_aces = 0;
+ u16 num_aces = 0;
bool new_aces_set = false;
/* Assuming that pndacl and pnmode are never NULL */
@@ -1112,7 +1116,7 @@ static int set_chmod_dacl(struct smb_acl *pdacl, struct smb_acl *pndacl,
acl_base = (char *)pdacl;
size = sizeof(struct smb_acl);
- src_num_aces = le32_to_cpu(pdacl->num_aces);
+ src_num_aces = le16_to_cpu(pdacl->num_aces);
/* Retain old ACEs which we can retain */
for (i = 0; i < src_num_aces; ++i) {
@@ -1158,7 +1162,7 @@ next_ace:
}
finalize_dacl:
- pndacl->num_aces = cpu_to_le32(num_aces);
+ pndacl->num_aces = cpu_to_le16(num_aces);
pndacl->size = cpu_to_le16(nsize);
return 0;
@@ -1293,7 +1297,7 @@ static int build_sec_desc(struct smb_ntsd *pntsd, struct smb_ntsd *pnntsd,
dacloffset ? dacl_ptr->revision : cpu_to_le16(ACL_REVISION);
ndacl_ptr->size = cpu_to_le16(0);
- ndacl_ptr->num_aces = cpu_to_le32(0);
+ ndacl_ptr->num_aces = cpu_to_le16(0);
rc = set_chmod_dacl(dacl_ptr, ndacl_ptr, owner_sid_ptr, group_sid_ptr,
pnmode, mode_from_sid, posix);
@@ -1653,7 +1657,7 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode,
dacl_ptr = (struct smb_acl *)((char *)pntsd + dacloffset);
if (mode_from_sid)
nsecdesclen +=
- le32_to_cpu(dacl_ptr->num_aces) * sizeof(struct smb_ace);
+ le16_to_cpu(dacl_ptr->num_aces) * sizeof(struct smb_ace);
else /* cifsacl */
nsecdesclen += le16_to_cpu(dacl_ptr->size);
}
diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
index 3feaa0f68169..d07682020c64 100644
--- a/fs/smb/client/cifssmb.c
+++ b/fs/smb/client/cifssmb.c
@@ -1338,7 +1338,8 @@ cifs_readv_callback(struct mid_q_entry *mid)
rdata->credits.value = 0;
rdata->subreq.error = rdata->result;
rdata->subreq.transferred += rdata->got_bytes;
- queue_work(cifsiod_wq, &rdata->subreq.work);
+ trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_progress);
+ netfs_read_subreq_terminated(&rdata->subreq);
release_mid(mid);
add_credits(server, &credits, 0);
}
diff --git a/fs/smb/common/smbacl.h b/fs/smb/common/smbacl.h
index 6a60698fc6f0..a624ec9e4a14 100644
--- a/fs/smb/common/smbacl.h
+++ b/fs/smb/common/smbacl.h
@@ -107,7 +107,8 @@ struct smb_sid {
struct smb_acl {
__le16 revision; /* revision level */
__le16 size;
- __le32 num_aces;
+ __le16 num_aces;
+ __le16 reserved;
} __attribute__((packed));
struct smb_ace {
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index f1efcd027475..c53121538990 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -7458,17 +7458,17 @@ out_check_cl:
}
no_check_cl:
+ flock = smb_lock->fl;
+ list_del(&smb_lock->llist);
+
if (smb_lock->zero_len) {
err = 0;
goto skip;
}
-
- flock = smb_lock->fl;
- list_del(&smb_lock->llist);
retry:
rc = vfs_lock_file(filp, smb_lock->cmd, flock, NULL);
skip:
- if (flags & SMB2_LOCKFLAG_UNLOCK) {
+ if (smb_lock->flags & SMB2_LOCKFLAG_UNLOCK) {
if (!rc) {
ksmbd_debug(SMB, "File unlocked\n");
} else if (rc == -ENOENT) {
diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c
index d39d3e553366..49b128698670 100644
--- a/fs/smb/server/smbacl.c
+++ b/fs/smb/server/smbacl.c
@@ -333,7 +333,7 @@ void posix_state_to_acl(struct posix_acl_state *state,
pace->e_perm = state->other.allow;
}
-int init_acl_state(struct posix_acl_state *state, int cnt)
+int init_acl_state(struct posix_acl_state *state, u16 cnt)
{
int alloc;
@@ -368,7 +368,7 @@ static void parse_dacl(struct mnt_idmap *idmap,
struct smb_fattr *fattr)
{
int i, ret;
- int num_aces = 0;
+ u16 num_aces = 0;
unsigned int acl_size;
char *acl_base;
struct smb_ace **ppace;
@@ -389,16 +389,18 @@ static void parse_dacl(struct mnt_idmap *idmap,
ksmbd_debug(SMB, "DACL revision %d size %d num aces %d\n",
le16_to_cpu(pdacl->revision), le16_to_cpu(pdacl->size),
- le32_to_cpu(pdacl->num_aces));
+ le16_to_cpu(pdacl->num_aces));
acl_base = (char *)pdacl;
acl_size = sizeof(struct smb_acl);
- num_aces = le32_to_cpu(pdacl->num_aces);
+ num_aces = le16_to_cpu(pdacl->num_aces);
if (num_aces <= 0)
return;
- if (num_aces > ULONG_MAX / sizeof(struct smb_ace *))
+ if (num_aces > (le16_to_cpu(pdacl->size) - sizeof(struct smb_acl)) /
+ (offsetof(struct smb_ace, sid) +
+ offsetof(struct smb_sid, sub_auth) + sizeof(__le16)))
return;
ret = init_acl_state(&acl_state, num_aces);
@@ -432,6 +434,7 @@ static void parse_dacl(struct mnt_idmap *idmap,
offsetof(struct smb_sid, sub_auth);
if (end_of_acl - acl_base < acl_size ||
+ ppace[i]->sid.num_subauth == 0 ||
ppace[i]->sid.num_subauth > SID_MAX_SUB_AUTHORITIES ||
(end_of_acl - acl_base <
acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth) ||
@@ -580,7 +583,7 @@ static void parse_dacl(struct mnt_idmap *idmap,
static void set_posix_acl_entries_dacl(struct mnt_idmap *idmap,
struct smb_ace *pndace,
- struct smb_fattr *fattr, u32 *num_aces,
+ struct smb_fattr *fattr, u16 *num_aces,
u16 *size, u32 nt_aces_num)
{
struct posix_acl_entry *pace;
@@ -701,7 +704,7 @@ static void set_ntacl_dacl(struct mnt_idmap *idmap,
struct smb_fattr *fattr)
{
struct smb_ace *ntace, *pndace;
- int nt_num_aces = le32_to_cpu(nt_dacl->num_aces), num_aces = 0;
+ u16 nt_num_aces = le16_to_cpu(nt_dacl->num_aces), num_aces = 0;
unsigned short size = 0;
int i;
@@ -728,7 +731,7 @@ static void set_ntacl_dacl(struct mnt_idmap *idmap,
set_posix_acl_entries_dacl(idmap, pndace, fattr,
&num_aces, &size, nt_num_aces);
- pndacl->num_aces = cpu_to_le32(num_aces);
+ pndacl->num_aces = cpu_to_le16(num_aces);
pndacl->size = cpu_to_le16(le16_to_cpu(pndacl->size) + size);
}
@@ -736,7 +739,7 @@ static void set_mode_dacl(struct mnt_idmap *idmap,
struct smb_acl *pndacl, struct smb_fattr *fattr)
{
struct smb_ace *pace, *pndace;
- u32 num_aces = 0;
+ u16 num_aces = 0;
u16 size = 0, ace_size = 0;
uid_t uid;
const struct smb_sid *sid;
@@ -792,7 +795,7 @@ static void set_mode_dacl(struct mnt_idmap *idmap,
fattr->cf_mode, 0007);
out:
- pndacl->num_aces = cpu_to_le32(num_aces);
+ pndacl->num_aces = cpu_to_le16(num_aces);
pndacl->size = cpu_to_le16(le16_to_cpu(pndacl->size) + size);
}
@@ -807,6 +810,13 @@ static int parse_sid(struct smb_sid *psid, char *end_of_acl)
return -EINVAL;
}
+ if (!psid->num_subauth)
+ return 0;
+
+ if (psid->num_subauth > SID_MAX_SUB_AUTHORITIES ||
+ end_of_acl < (char *)psid + 8 + sizeof(__le32) * psid->num_subauth)
+ return -EINVAL;
+
return 0;
}
@@ -848,6 +858,9 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd,
pntsd->type = cpu_to_le16(DACL_PRESENT);
if (pntsd->osidoffset) {
+ if (le32_to_cpu(pntsd->osidoffset) < sizeof(struct smb_ntsd))
+ return -EINVAL;
+
rc = parse_sid(owner_sid_ptr, end_of_acl);
if (rc) {
pr_err("%s: Error %d parsing Owner SID\n", __func__, rc);
@@ -863,6 +876,9 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd,
}
if (pntsd->gsidoffset) {
+ if (le32_to_cpu(pntsd->gsidoffset) < sizeof(struct smb_ntsd))
+ return -EINVAL;
+
rc = parse_sid(group_sid_ptr, end_of_acl);
if (rc) {
pr_err("%s: Error %d mapping Owner SID to gid\n",
@@ -884,6 +900,9 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd,
pntsd->type |= cpu_to_le16(DACL_PROTECTED);
if (dacloffset) {
+ if (dacloffset < sizeof(struct smb_ntsd))
+ return -EINVAL;
+
parse_dacl(idmap, dacl_ptr, end_of_acl,
owner_sid_ptr, group_sid_ptr, fattr);
}
@@ -1006,8 +1025,9 @@ int smb_inherit_dacl(struct ksmbd_conn *conn,
struct smb_sid owner_sid, group_sid;
struct dentry *parent = path->dentry->d_parent;
struct mnt_idmap *idmap = mnt_idmap(path->mnt);
- int inherited_flags = 0, flags = 0, i, ace_cnt = 0, nt_size = 0, pdacl_size;
- int rc = 0, num_aces, dacloffset, pntsd_type, pntsd_size, acl_len, aces_size;
+ int inherited_flags = 0, flags = 0, i, nt_size = 0, pdacl_size;
+ int rc = 0, dacloffset, pntsd_type, pntsd_size, acl_len, aces_size;
+ u16 num_aces, ace_cnt = 0;
char *aces_base;
bool is_dir = S_ISDIR(d_inode(path->dentry)->i_mode);
@@ -1023,7 +1043,7 @@ int smb_inherit_dacl(struct ksmbd_conn *conn,
parent_pdacl = (struct smb_acl *)((char *)parent_pntsd + dacloffset);
acl_len = pntsd_size - dacloffset;
- num_aces = le32_to_cpu(parent_pdacl->num_aces);
+ num_aces = le16_to_cpu(parent_pdacl->num_aces);
pntsd_type = le16_to_cpu(parent_pntsd->type);
pdacl_size = le16_to_cpu(parent_pdacl->size);
@@ -1183,7 +1203,7 @@ pass:
pdacl = (struct smb_acl *)((char *)pntsd + le32_to_cpu(pntsd->dacloffset));
pdacl->revision = cpu_to_le16(2);
pdacl->size = cpu_to_le16(sizeof(struct smb_acl) + nt_size);
- pdacl->num_aces = cpu_to_le32(ace_cnt);
+ pdacl->num_aces = cpu_to_le16(ace_cnt);
pace = (struct smb_ace *)((char *)pdacl + sizeof(struct smb_acl));
memcpy(pace, aces_base, nt_size);
pntsd_size += sizeof(struct smb_acl) + nt_size;
@@ -1264,7 +1284,7 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, const struct path *path,
ace = (struct smb_ace *)((char *)pdacl + sizeof(struct smb_acl));
aces_size = acl_size - sizeof(struct smb_acl);
- for (i = 0; i < le32_to_cpu(pdacl->num_aces); i++) {
+ for (i = 0; i < le16_to_cpu(pdacl->num_aces); i++) {
if (offsetof(struct smb_ace, access_req) > aces_size)
break;
ace_size = le16_to_cpu(ace->size);
@@ -1285,7 +1305,7 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, const struct path *path,
ace = (struct smb_ace *)((char *)pdacl + sizeof(struct smb_acl));
aces_size = acl_size - sizeof(struct smb_acl);
- for (i = 0; i < le32_to_cpu(pdacl->num_aces); i++) {
+ for (i = 0; i < le16_to_cpu(pdacl->num_aces); i++) {
if (offsetof(struct smb_ace, access_req) > aces_size)
break;
ace_size = le16_to_cpu(ace->size);
diff --git a/fs/smb/server/smbacl.h b/fs/smb/server/smbacl.h
index 24ce576fc292..355adaee39b8 100644
--- a/fs/smb/server/smbacl.h
+++ b/fs/smb/server/smbacl.h
@@ -86,7 +86,7 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd,
int build_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd,
struct smb_ntsd *ppntsd, int ppntsd_size, int addition_info,
__u32 *secdesclen, struct smb_fattr *fattr);
-int init_acl_state(struct posix_acl_state *state, int cnt);
+int init_acl_state(struct posix_acl_state *state, u16 cnt);
void free_acl_state(struct posix_acl_state *state);
void posix_state_to_acl(struct posix_acl_state *state,
struct posix_acl_entry *pace);
diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c
index 0460ebea6ff0..3f185ae60dc5 100644
--- a/fs/smb/server/transport_ipc.c
+++ b/fs/smb/server/transport_ipc.c
@@ -281,6 +281,7 @@ static int handle_response(int type, void *payload, size_t sz)
if (entry->type + 1 != type) {
pr_err("Waiting for IPC type %d, got %d. Ignore.\n",
entry->type + 1, type);
+ continue;
}
entry->response = kvzalloc(sz, KSMBD_DEFAULT_GFP);
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 15bb790359f8..5d560e9073f4 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -29,11 +29,6 @@ struct kmem_cache *xfs_buf_cache;
/*
* Locking orders
*
- * xfs_buf_ioacct_inc:
- * xfs_buf_ioacct_dec:
- * b_sema (caller holds)
- * b_lock
- *
* xfs_buf_stale:
* b_sema (caller holds)
* b_lock
@@ -82,51 +77,6 @@ xfs_buf_vmap_len(
}
/*
- * Bump the I/O in flight count on the buftarg if we haven't yet done so for
- * this buffer. The count is incremented once per buffer (per hold cycle)
- * because the corresponding decrement is deferred to buffer release. Buffers
- * can undergo I/O multiple times in a hold-release cycle and per buffer I/O
- * tracking adds unnecessary overhead. This is used for sychronization purposes
- * with unmount (see xfs_buftarg_drain()), so all we really need is a count of
- * in-flight buffers.
- *
- * Buffers that are never released (e.g., superblock, iclog buffers) must set
- * the XBF_NO_IOACCT flag before I/O submission. Otherwise, the buftarg count
- * never reaches zero and unmount hangs indefinitely.
- */
-static inline void
-xfs_buf_ioacct_inc(
- struct xfs_buf *bp)
-{
- if (bp->b_flags & XBF_NO_IOACCT)
- return;
-
- ASSERT(bp->b_flags & XBF_ASYNC);
- spin_lock(&bp->b_lock);
- if (!(bp->b_state & XFS_BSTATE_IN_FLIGHT)) {
- bp->b_state |= XFS_BSTATE_IN_FLIGHT;
- percpu_counter_inc(&bp->b_target->bt_io_count);
- }
- spin_unlock(&bp->b_lock);
-}
-
-/*
- * Clear the in-flight state on a buffer about to be released to the LRU or
- * freed and unaccount from the buftarg.
- */
-static inline void
-__xfs_buf_ioacct_dec(
- struct xfs_buf *bp)
-{
- lockdep_assert_held(&bp->b_lock);
-
- if (bp->b_state & XFS_BSTATE_IN_FLIGHT) {
- bp->b_state &= ~XFS_BSTATE_IN_FLIGHT;
- percpu_counter_dec(&bp->b_target->bt_io_count);
- }
-}
-
-/*
* When we mark a buffer stale, we remove the buffer from the LRU and clear the
* b_lru_ref count so that the buffer is freed immediately when the buffer
* reference count falls to zero. If the buffer is already on the LRU, we need
@@ -149,15 +99,7 @@ xfs_buf_stale(
*/
bp->b_flags &= ~_XBF_DELWRI_Q;
- /*
- * Once the buffer is marked stale and unlocked, a subsequent lookup
- * could reset b_flags. There is no guarantee that the buffer is
- * unaccounted (released to LRU) before that occurs. Drop in-flight
- * status now to preserve accounting consistency.
- */
spin_lock(&bp->b_lock);
- __xfs_buf_ioacct_dec(bp);
-
atomic_set(&bp->b_lru_ref, 0);
if (!(bp->b_state & XFS_BSTATE_DISPOSE) &&
(list_lru_del_obj(&bp->b_target->bt_lru, &bp->b_lru)))
@@ -794,18 +736,13 @@ out_put_perag:
int
_xfs_buf_read(
- struct xfs_buf *bp,
- xfs_buf_flags_t flags)
+ struct xfs_buf *bp)
{
- ASSERT(!(flags & XBF_WRITE));
ASSERT(bp->b_maps[0].bm_bn != XFS_BUF_DADDR_NULL);
bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD | XBF_DONE);
- bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD);
-
+ bp->b_flags |= XBF_READ;
xfs_buf_submit(bp);
- if (flags & XBF_ASYNC)
- return 0;
return xfs_buf_iowait(bp);
}
@@ -857,6 +794,8 @@ xfs_buf_read_map(
struct xfs_buf *bp;
int error;
+ ASSERT(!(flags & (XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD)));
+
flags |= XBF_READ;
*bpp = NULL;
@@ -870,21 +809,11 @@ xfs_buf_read_map(
/* Initiate the buffer read and wait. */
XFS_STATS_INC(target->bt_mount, xb_get_read);
bp->b_ops = ops;
- error = _xfs_buf_read(bp, flags);
-
- /* Readahead iodone already dropped the buffer, so exit. */
- if (flags & XBF_ASYNC)
- return 0;
+ error = _xfs_buf_read(bp);
} else {
/* Buffer already read; all we need to do is check it. */
error = xfs_buf_reverify(bp, ops);
- /* Readahead already finished; drop the buffer and exit. */
- if (flags & XBF_ASYNC) {
- xfs_buf_relse(bp);
- return 0;
- }
-
/* We do not want read in the flags */
bp->b_flags &= ~XBF_READ;
ASSERT(bp->b_ops != NULL || ops == NULL);
@@ -936,6 +865,7 @@ xfs_buf_readahead_map(
int nmaps,
const struct xfs_buf_ops *ops)
{
+ const xfs_buf_flags_t flags = XBF_READ | XBF_ASYNC | XBF_READ_AHEAD;
struct xfs_buf *bp;
/*
@@ -945,9 +875,21 @@ xfs_buf_readahead_map(
if (xfs_buftarg_is_mem(target))
return;
- xfs_buf_read_map(target, map, nmaps,
- XBF_TRYLOCK | XBF_ASYNC | XBF_READ_AHEAD, &bp, ops,
- __this_address);
+ if (xfs_buf_get_map(target, map, nmaps, flags | XBF_TRYLOCK, &bp))
+ return;
+ trace_xfs_buf_readahead(bp, 0, _RET_IP_);
+
+ if (bp->b_flags & XBF_DONE) {
+ xfs_buf_reverify(bp, ops);
+ xfs_buf_relse(bp);
+ return;
+ }
+ XFS_STATS_INC(target->bt_mount, xb_get_read);
+ bp->b_ops = ops;
+ bp->b_flags &= ~(XBF_WRITE | XBF_DONE);
+ bp->b_flags |= flags;
+ percpu_counter_inc(&target->bt_readahead_count);
+ xfs_buf_submit(bp);
}
/*
@@ -1003,10 +945,12 @@ xfs_buf_get_uncached(
struct xfs_buf *bp;
DEFINE_SINGLE_BUF_MAP(map, XFS_BUF_DADDR_NULL, numblks);
+ /* there are currently no valid flags for xfs_buf_get_uncached */
+ ASSERT(flags == 0);
+
*bpp = NULL;
- /* flags might contain irrelevant bits, pass only what we care about */
- error = _xfs_buf_alloc(target, &map, 1, flags & XBF_NO_IOACCT, &bp);
+ error = _xfs_buf_alloc(target, &map, 1, flags, &bp);
if (error)
return error;
@@ -1060,7 +1004,6 @@ xfs_buf_rele_uncached(
spin_unlock(&bp->b_lock);
return;
}
- __xfs_buf_ioacct_dec(bp);
spin_unlock(&bp->b_lock);
xfs_buf_free(bp);
}
@@ -1079,20 +1022,12 @@ xfs_buf_rele_cached(
spin_lock(&bp->b_lock);
ASSERT(bp->b_hold >= 1);
if (bp->b_hold > 1) {
- /*
- * Drop the in-flight state if the buffer is already on the LRU
- * and it holds the only reference. This is racy because we
- * haven't acquired the pag lock, but the use of _XBF_IN_FLIGHT
- * ensures the decrement occurs only once per-buf.
- */
- if (--bp->b_hold == 1 && !list_empty(&bp->b_lru))
- __xfs_buf_ioacct_dec(bp);
+ bp->b_hold--;
goto out_unlock;
}
/* we are asked to drop the last reference */
- __xfs_buf_ioacct_dec(bp);
- if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) {
+ if (atomic_read(&bp->b_lru_ref)) {
/*
* If the buffer is added to the LRU, keep the reference to the
* buffer for the LRU and clear the (now stale) dispose list
@@ -1345,6 +1280,7 @@ xfs_buf_ioend_handle_error(
resubmit:
xfs_buf_ioerror(bp, 0);
bp->b_flags |= (XBF_DONE | XBF_WRITE_FAIL);
+ reinit_completion(&bp->b_iowait);
xfs_buf_submit(bp);
return true;
out_stale:
@@ -1355,8 +1291,9 @@ out_stale:
return false;
}
-static void
-xfs_buf_ioend(
+/* returns false if the caller needs to resubmit the I/O, else true */
+static bool
+__xfs_buf_ioend(
struct xfs_buf *bp)
{
trace_xfs_buf_iodone(bp, _RET_IP_);
@@ -1369,6 +1306,8 @@ xfs_buf_ioend(
bp->b_ops->verify_read(bp);
if (!bp->b_error)
bp->b_flags |= XBF_DONE;
+ if (bp->b_flags & XBF_READ_AHEAD)
+ percpu_counter_dec(&bp->b_target->bt_readahead_count);
} else {
if (!bp->b_error) {
bp->b_flags &= ~XBF_WRITE_FAIL;
@@ -1376,7 +1315,7 @@ xfs_buf_ioend(
}
if (unlikely(bp->b_error) && xfs_buf_ioend_handle_error(bp))
- return;
+ return false;
/* clear the retry state */
bp->b_last_error = 0;
@@ -1397,7 +1336,15 @@ xfs_buf_ioend(
bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD |
_XBF_LOGRECOVERY);
+ return true;
+}
+static void
+xfs_buf_ioend(
+ struct xfs_buf *bp)
+{
+ if (!__xfs_buf_ioend(bp))
+ return;
if (bp->b_flags & XBF_ASYNC)
xfs_buf_relse(bp);
else
@@ -1411,15 +1358,8 @@ xfs_buf_ioend_work(
struct xfs_buf *bp =
container_of(work, struct xfs_buf, b_ioend_work);
- xfs_buf_ioend(bp);
-}
-
-static void
-xfs_buf_ioend_async(
- struct xfs_buf *bp)
-{
- INIT_WORK(&bp->b_ioend_work, xfs_buf_ioend_work);
- queue_work(bp->b_mount->m_buf_workqueue, &bp->b_ioend_work);
+ if (__xfs_buf_ioend(bp))
+ xfs_buf_relse(bp);
}
void
@@ -1491,7 +1431,13 @@ xfs_buf_bio_end_io(
XFS_TEST_ERROR(false, bp->b_mount, XFS_ERRTAG_BUF_IOERROR))
xfs_buf_ioerror(bp, -EIO);
- xfs_buf_ioend_async(bp);
+ if (bp->b_flags & XBF_ASYNC) {
+ INIT_WORK(&bp->b_ioend_work, xfs_buf_ioend_work);
+ queue_work(bp->b_mount->m_buf_workqueue, &bp->b_ioend_work);
+ } else {
+ complete(&bp->b_iowait);
+ }
+
bio_put(bio);
}
@@ -1568,9 +1514,11 @@ xfs_buf_iowait(
{
ASSERT(!(bp->b_flags & XBF_ASYNC));
- trace_xfs_buf_iowait(bp, _RET_IP_);
- wait_for_completion(&bp->b_iowait);
- trace_xfs_buf_iowait_done(bp, _RET_IP_);
+ do {
+ trace_xfs_buf_iowait(bp, _RET_IP_);
+ wait_for_completion(&bp->b_iowait);
+ trace_xfs_buf_iowait_done(bp, _RET_IP_);
+ } while (!__xfs_buf_ioend(bp));
return bp->b_error;
}
@@ -1648,9 +1596,6 @@ xfs_buf_submit(
*/
bp->b_error = 0;
- if (bp->b_flags & XBF_ASYNC)
- xfs_buf_ioacct_inc(bp);
-
if ((bp->b_flags & XBF_WRITE) && !xfs_buf_verify_write(bp)) {
xfs_force_shutdown(bp->b_mount, SHUTDOWN_CORRUPT_INCORE);
xfs_buf_ioend(bp);
@@ -1776,9 +1721,8 @@ xfs_buftarg_wait(
struct xfs_buftarg *btp)
{
/*
- * First wait on the buftarg I/O count for all in-flight buffers to be
- * released. This is critical as new buffers do not make the LRU until
- * they are released.
+ * First wait for all in-flight readahead buffers to be released. This is
+ * critical as new buffers do not make the LRU until they are released.
*
* Next, flush the buffer workqueue to ensure all completion processing
* has finished. Just waiting on buffer locks is not sufficient for
@@ -1787,7 +1731,7 @@ xfs_buftarg_wait(
* all reference counts have been dropped before we start walking the
* LRU list.
*/
- while (percpu_counter_sum(&btp->bt_io_count))
+ while (percpu_counter_sum(&btp->bt_readahead_count))
delay(100);
flush_workqueue(btp->bt_mount->m_buf_workqueue);
}
@@ -1904,8 +1848,8 @@ xfs_destroy_buftarg(
struct xfs_buftarg *btp)
{
shrinker_free(btp->bt_shrinker);
- ASSERT(percpu_counter_sum(&btp->bt_io_count) == 0);
- percpu_counter_destroy(&btp->bt_io_count);
+ ASSERT(percpu_counter_sum(&btp->bt_readahead_count) == 0);
+ percpu_counter_destroy(&btp->bt_readahead_count);
list_lru_destroy(&btp->bt_lru);
}
@@ -1959,7 +1903,7 @@ xfs_init_buftarg(
if (list_lru_init(&btp->bt_lru))
return -ENOMEM;
- if (percpu_counter_init(&btp->bt_io_count, 0, GFP_KERNEL))
+ if (percpu_counter_init(&btp->bt_readahead_count, 0, GFP_KERNEL))
goto out_destroy_lru;
btp->bt_shrinker =
@@ -1973,7 +1917,7 @@ xfs_init_buftarg(
return 0;
out_destroy_io_count:
- percpu_counter_destroy(&btp->bt_io_count);
+ percpu_counter_destroy(&btp->bt_readahead_count);
out_destroy_lru:
list_lru_destroy(&btp->bt_lru);
return -ENOMEM;
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 3b4ed42e11c0..80e06eecaf56 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -27,7 +27,6 @@ struct xfs_buf;
#define XBF_READ (1u << 0) /* buffer intended for reading from device */
#define XBF_WRITE (1u << 1) /* buffer intended for writing to device */
#define XBF_READ_AHEAD (1u << 2) /* asynchronous read-ahead */
-#define XBF_NO_IOACCT (1u << 3) /* bypass I/O accounting (non-LRU bufs) */
#define XBF_ASYNC (1u << 4) /* initiator will not wait for completion */
#define XBF_DONE (1u << 5) /* all pages in the buffer uptodate */
#define XBF_STALE (1u << 6) /* buffer has been staled, do not find it */
@@ -58,7 +57,6 @@ typedef unsigned int xfs_buf_flags_t;
{ XBF_READ, "READ" }, \
{ XBF_WRITE, "WRITE" }, \
{ XBF_READ_AHEAD, "READ_AHEAD" }, \
- { XBF_NO_IOACCT, "NO_IOACCT" }, \
{ XBF_ASYNC, "ASYNC" }, \
{ XBF_DONE, "DONE" }, \
{ XBF_STALE, "STALE" }, \
@@ -77,7 +75,6 @@ typedef unsigned int xfs_buf_flags_t;
* Internal state flags.
*/
#define XFS_BSTATE_DISPOSE (1 << 0) /* buffer being discarded */
-#define XFS_BSTATE_IN_FLIGHT (1 << 1) /* I/O in flight */
struct xfs_buf_cache {
struct rhashtable bc_hash;
@@ -116,7 +113,7 @@ struct xfs_buftarg {
struct shrinker *bt_shrinker;
struct list_lru bt_lru;
- struct percpu_counter bt_io_count;
+ struct percpu_counter bt_readahead_count;
struct ratelimit_state bt_ioerror_rl;
/* Atomic write unit values */
@@ -291,7 +288,7 @@ int xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks,
int xfs_buf_read_uncached(struct xfs_buftarg *target, xfs_daddr_t daddr,
size_t numblks, xfs_buf_flags_t flags, struct xfs_buf **bpp,
const struct xfs_buf_ops *ops);
-int _xfs_buf_read(struct xfs_buf *bp, xfs_buf_flags_t flags);
+int _xfs_buf_read(struct xfs_buf *bp);
void xfs_buf_hold(struct xfs_buf *bp);
/* Releasing Buffers */
diff --git a/fs/xfs/xfs_buf_mem.c b/fs/xfs/xfs_buf_mem.c
index 07bebbfb16ee..5b64a2b3b113 100644
--- a/fs/xfs/xfs_buf_mem.c
+++ b/fs/xfs/xfs_buf_mem.c
@@ -117,7 +117,7 @@ xmbuf_free(
struct xfs_buftarg *btp)
{
ASSERT(xfs_buftarg_is_mem(btp));
- ASSERT(percpu_counter_sum(&btp->bt_io_count) == 0);
+ ASSERT(percpu_counter_sum(&btp->bt_readahead_count) == 0);
trace_xmbuf_free(btp);
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index b3c27dbccce8..2f76531842f8 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -3380,7 +3380,7 @@ xlog_do_recover(
*/
xfs_buf_lock(bp);
xfs_buf_hold(bp);
- error = _xfs_buf_read(bp, XBF_READ);
+ error = _xfs_buf_read(bp);
if (error) {
if (!xlog_is_shutdown(log)) {
xfs_buf_ioerror_alert(bp, __this_address);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 477c5262cf91..b69356582b86 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -181,14 +181,11 @@ xfs_readsb(
/*
* Allocate a (locked) buffer to hold the superblock. This will be kept
- * around at all times to optimize access to the superblock. Therefore,
- * set XBF_NO_IOACCT to make sure it doesn't hold the buftarg count
- * elevated.
+ * around at all times to optimize access to the superblock.
*/
reread:
error = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
- BTOBB(sector_size), XBF_NO_IOACCT, &bp,
- buf_ops);
+ BTOBB(sector_size), 0, &bp, buf_ops);
if (error) {
if (loud)
xfs_warn(mp, "SB validate failed with error %d.", error);
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index d8e6d073d64d..57bef567e011 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -1407,7 +1407,7 @@ xfs_rtmount_readsb(
/* m_blkbb_log is not set up yet */
error = xfs_buf_read_uncached(mp->m_rtdev_targp, XFS_RTSB_DADDR,
- mp->m_sb.sb_blocksize >> BBSHIFT, XBF_NO_IOACCT, &bp,
+ mp->m_sb.sb_blocksize >> BBSHIFT, 0, &bp,
&xfs_rtsb_buf_ops);
if (error) {
xfs_warn(mp, "rt sb validate failed with error %d.", error);
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index b29462363b81..bfc2f1249022 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -593,6 +593,7 @@ DEFINE_EVENT(xfs_buf_flags_class, name, \
DEFINE_BUF_FLAGS_EVENT(xfs_buf_find);
DEFINE_BUF_FLAGS_EVENT(xfs_buf_get);
DEFINE_BUF_FLAGS_EVENT(xfs_buf_read);
+DEFINE_BUF_FLAGS_EVENT(xfs_buf_readahead);
TRACE_EVENT(xfs_buf_ioerror,
TP_PROTO(struct xfs_buf *bp, int error, xfs_failaddr_t caller_ip),
generated by cgit (git 2.34.1) at 2025-08-09 23:42:25 +0000