aboutsummaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/btrfs/extent_io.c40
-rw-r--r--fs/btrfs/inode.c12
-rw-r--r--fs/btrfs/qgroup.c6
-rw-r--r--fs/btrfs/super.c9
-rw-r--r--fs/btrfs/volumes.c5
-rw-r--r--fs/coredump.c4
-rw-r--r--fs/exec.c2
-rw-r--r--fs/fhandle.c8
-rw-r--r--fs/fuse/dev.c2
-rw-r--r--fs/fuse/dir.c3
-rw-r--r--fs/fuse/file.c5
-rw-r--r--fs/fuse/fuse_i.h14
-rw-r--r--fs/fuse/inode.c16
-rw-r--r--fs/fuse/passthrough.c5
-rw-r--r--fs/fuse/virtio_fs.c2
-rw-r--r--fs/kernfs/file.c58
-rw-r--r--fs/namespace.c2
-rw-r--r--fs/nfs/client.c2
-rw-r--r--fs/nfs/file.c40
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayout.c21
-rw-r--r--fs/nfs/inode.c13
-rw-r--r--fs/nfs/internal.h12
-rw-r--r--fs/nfs/io.c13
-rw-r--r--fs/nfs/localio.c21
-rw-r--r--fs/nfs/nfs42proc.c35
-rw-r--r--fs/nfs/nfs4file.c2
-rw-r--r--fs/nfs/nfs4proc.c7
-rw-r--r--fs/nfs/nfstrace.h1
-rw-r--r--fs/nfs/write.c53
-rw-r--r--fs/ocfs2/extent_map.c10
-rw-r--r--fs/proc/generic.c3
-rw-r--r--fs/smb/client/cifsglob.h13
-rw-r--r--fs/smb/client/file.c18
-rw-r--r--fs/smb/client/inode.c86
-rw-r--r--fs/smb/client/smb2glob.h3
-rw-r--r--fs/smb/client/smb2inode.c204
-rw-r--r--fs/smb/client/smb2ops.c32
-rw-r--r--fs/smb/client/smb2proto.h3
-rw-r--r--fs/smb/client/trace.h9
39 files changed, 581 insertions, 213 deletions
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index c953297aa89a..b21cb72835cc 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -111,6 +111,24 @@ struct btrfs_bio_ctrl {
*/
unsigned long submit_bitmap;
struct readahead_control *ractl;
+
+ /*
+ * The start offset of the last used extent map by a read operation.
+ *
+ * This is for proper compressed read merge.
+ * U64_MAX means we are starting the read and have made no progress yet.
+ *
+ * The current btrfs_bio_is_contig() only uses disk_bytenr as
+ * the condition to check if the read can be merged with previous
+ * bio, which is not correct. E.g. two file extents pointing to the
+ * same extent but with different offset.
+ *
+ * So here we need to do extra checks to only merge reads that are
+ * covered by the same extent map.
+ * Just extent_map::start will be enough, as they are unique
+ * inside the same inode.
+ */
+ u64 last_em_start;
};
static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl)
@@ -909,7 +927,7 @@ static void btrfs_readahead_expand(struct readahead_control *ractl,
* return 0 on success, otherwise return error
*/
static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached,
- struct btrfs_bio_ctrl *bio_ctrl, u64 *prev_em_start)
+ struct btrfs_bio_ctrl *bio_ctrl)
{
struct inode *inode = folio->mapping->host;
struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
@@ -1019,12 +1037,11 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached,
* non-optimal behavior (submitting 2 bios for the same extent).
*/
if (compress_type != BTRFS_COMPRESS_NONE &&
- prev_em_start && *prev_em_start != (u64)-1 &&
- *prev_em_start != em->start)
+ bio_ctrl->last_em_start != U64_MAX &&
+ bio_ctrl->last_em_start != em->start)
force_bio_submit = true;
- if (prev_em_start)
- *prev_em_start = em->start;
+ bio_ctrl->last_em_start = em->start;
btrfs_free_extent_map(em);
em = NULL;
@@ -1238,12 +1255,15 @@ int btrfs_read_folio(struct file *file, struct folio *folio)
const u64 start = folio_pos(folio);
const u64 end = start + folio_size(folio) - 1;
struct extent_state *cached_state = NULL;
- struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ };
+ struct btrfs_bio_ctrl bio_ctrl = {
+ .opf = REQ_OP_READ,
+ .last_em_start = U64_MAX,
+ };
struct extent_map *em_cached = NULL;
int ret;
lock_extents_for_read(inode, start, end, &cached_state);
- ret = btrfs_do_readpage(folio, &em_cached, &bio_ctrl, NULL);
+ ret = btrfs_do_readpage(folio, &em_cached, &bio_ctrl);
btrfs_unlock_extent(&inode->io_tree, start, end, &cached_state);
btrfs_free_extent_map(em_cached);
@@ -2583,7 +2603,8 @@ void btrfs_readahead(struct readahead_control *rac)
{
struct btrfs_bio_ctrl bio_ctrl = {
.opf = REQ_OP_READ | REQ_RAHEAD,
- .ractl = rac
+ .ractl = rac,
+ .last_em_start = U64_MAX,
};
struct folio *folio;
struct btrfs_inode *inode = BTRFS_I(rac->mapping->host);
@@ -2591,12 +2612,11 @@ void btrfs_readahead(struct readahead_control *rac)
const u64 end = start + readahead_length(rac) - 1;
struct extent_state *cached_state = NULL;
struct extent_map *em_cached = NULL;
- u64 prev_em_start = (u64)-1;
lock_extents_for_read(inode, start, end, &cached_state);
while ((folio = readahead_folio(rac)) != NULL)
- btrfs_do_readpage(folio, &em_cached, &bio_ctrl, &prev_em_start);
+ btrfs_do_readpage(folio, &em_cached, &bio_ctrl);
btrfs_unlock_extent(&inode->io_tree, start, end, &cached_state);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index dd82dcc7b2b7..e7218e78bff4 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5696,7 +5696,17 @@ static void btrfs_del_inode_from_root(struct btrfs_inode *inode)
bool empty = false;
xa_lock(&root->inodes);
- entry = __xa_erase(&root->inodes, btrfs_ino(inode));
+ /*
+ * This btrfs_inode is being freed and has already been unhashed at this
+ * point. It's possible that another btrfs_inode has already been
+ * allocated for the same inode and inserted itself into the root, so
+ * don't delete it in that case.
+ *
+ * Note that this shouldn't need to allocate memory, so the gfp flags
+ * don't really matter.
+ */
+ entry = __xa_cmpxchg(&root->inodes, btrfs_ino(inode), inode, NULL,
+ GFP_ATOMIC);
if (entry == inode)
empty = xa_empty(&root->inodes);
xa_unlock(&root->inodes);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index ccaa9a3cf1ce..da102da169fd 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1455,6 +1455,7 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root,
struct btrfs_qgroup *qgroup;
LIST_HEAD(qgroup_list);
u64 num_bytes = src->excl;
+ u64 num_bytes_cmpr = src->excl_cmpr;
int ret = 0;
qgroup = find_qgroup_rb(fs_info, ref_root);
@@ -1466,11 +1467,12 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root,
struct btrfs_qgroup_list *glist;
qgroup->rfer += sign * num_bytes;
- qgroup->rfer_cmpr += sign * num_bytes;
+ qgroup->rfer_cmpr += sign * num_bytes_cmpr;
WARN_ON(sign < 0 && qgroup->excl < num_bytes);
+ WARN_ON(sign < 0 && qgroup->excl_cmpr < num_bytes_cmpr);
qgroup->excl += sign * num_bytes;
- qgroup->excl_cmpr += sign * num_bytes;
+ qgroup->excl_cmpr += sign * num_bytes_cmpr;
if (sign > 0)
qgroup_rsv_add_by_qgroup(fs_info, qgroup, src);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index a262b494a89f..df1f6cc3fe21 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -299,9 +299,12 @@ static int btrfs_parse_compress(struct btrfs_fs_context *ctx,
btrfs_set_opt(ctx->mount_opt, COMPRESS);
btrfs_clear_opt(ctx->mount_opt, NODATACOW);
btrfs_clear_opt(ctx->mount_opt, NODATASUM);
- } else if (btrfs_match_compress_type(string, "lzo", false)) {
+ } else if (btrfs_match_compress_type(string, "lzo", true)) {
ctx->compress_type = BTRFS_COMPRESS_LZO;
- ctx->compress_level = 0;
+ ctx->compress_level = btrfs_compress_str2level(BTRFS_COMPRESS_LZO,
+ string + 3);
+ if (string[3] == ':' && string[4])
+ btrfs_warn(NULL, "Compression level ignored for LZO");
btrfs_set_opt(ctx->mount_opt, COMPRESS);
btrfs_clear_opt(ctx->mount_opt, NODATACOW);
btrfs_clear_opt(ctx->mount_opt, NODATASUM);
@@ -1079,7 +1082,7 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
seq_printf(seq, ",compress-force=%s", compress_type);
else
seq_printf(seq, ",compress=%s", compress_type);
- if (info->compress_level)
+ if (info->compress_level && info->compress_type != BTRFS_COMPRESS_LZO)
seq_printf(seq, ":%d", info->compress_level);
}
if (btrfs_test_opt(info, NOSSD))
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index fa7a929a0461..c6e3efd6f602 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2722,6 +2722,11 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
goto error;
}
+ if (bdev_nr_bytes(file_bdev(bdev_file)) <= BTRFS_DEVICE_RANGE_RESERVED) {
+ ret = -EINVAL;
+ goto error;
+ }
+
if (fs_devices->seeding) {
seeding_dev = true;
down_write(&sb->s_umount);
diff --git a/fs/coredump.c b/fs/coredump.c
index 5dce257c67fc..60bc9685e149 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -1466,11 +1466,15 @@ static int proc_dostring_coredump(const struct ctl_table *table, int write,
ssize_t retval;
char old_core_pattern[CORENAME_MAX_SIZE];
+ if (write)
+ return proc_dostring(table, write, buffer, lenp, ppos);
+
retval = strscpy(old_core_pattern, core_pattern, CORENAME_MAX_SIZE);
error = proc_dostring(table, write, buffer, lenp, ppos);
if (error)
return error;
+
if (!check_coredump_socket()) {
strscpy(core_pattern, old_core_pattern, retval + 1);
return -EINVAL;
diff --git a/fs/exec.c b/fs/exec.c
index 2a1e5e4042a1..e861a4b7ffda 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -2048,7 +2048,7 @@ static int proc_dointvec_minmax_coredump(const struct ctl_table *table, int writ
{
int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
- if (!error)
+ if (!error && !write)
validate_coredump_safety();
return error;
}
diff --git a/fs/fhandle.c b/fs/fhandle.c
index 68a7d2861c58..a907ddfac4d5 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -208,6 +208,14 @@ static int vfs_dentry_acceptable(void *context, struct dentry *dentry)
return 1;
/*
+ * Verify that the decoded dentry itself has a valid id mapping.
+ * In case the decoded dentry is the mountfd root itself, this
+ * verifies that the mountfd inode itself has a valid id mapping.
+ */
+ if (!privileged_wrt_inode_uidgid(user_ns, idmap, d_inode(dentry)))
+ return 0;
+
+ /*
* It's racy as we're not taking rename_lock but we're able to ignore
* permissions and we just need an approximation whether we were able
* to follow a path to the file.
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index e80cd8f2c049..5150aa25e64b 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1893,7 +1893,7 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
index = outarg->offset >> PAGE_SHIFT;
- while (num) {
+ while (num && ap->num_folios < num_pages) {
struct folio *folio;
unsigned int folio_offset;
unsigned int nr_bytes;
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 2d817d7cab26..5c569c3cb53f 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1199,7 +1199,7 @@ static void fuse_fillattr(struct mnt_idmap *idmap, struct inode *inode,
if (attr->blksize != 0)
blkbits = ilog2(attr->blksize);
else
- blkbits = inode->i_sb->s_blocksize_bits;
+ blkbits = fc->blkbits;
stat->blksize = 1 << blkbits;
}
@@ -1377,6 +1377,7 @@ retry:
generic_fillattr(idmap, request_mask, inode, stat);
stat->mode = fi->orig_i_mode;
stat->ino = fi->orig_ino;
+ stat->blksize = 1 << fi->cached_i_blkbits;
if (test_bit(FUSE_I_BTIME, &fi->state)) {
stat->btime = fi->i_btime;
stat->result_mask |= STATX_BTIME;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 5525a4520b0f..4adcf09d4b01 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2960,7 +2960,7 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in,
.nodeid_out = ff_out->nodeid,
.fh_out = ff_out->fh,
.off_out = pos_out,
- .len = len,
+ .len = min_t(size_t, len, UINT_MAX & PAGE_MASK),
.flags = flags
};
struct fuse_write_out outarg;
@@ -3026,6 +3026,9 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in,
fc->no_copy_file_range = 1;
err = -EOPNOTSUPP;
}
+ if (!err && outarg.size > len)
+ err = -EIO;
+
if (err)
goto out;
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index ec248d13c8bf..cc428d04be3e 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -210,6 +210,12 @@ struct fuse_inode {
/** Reference to backing file in passthrough mode */
struct fuse_backing *fb;
#endif
+
+ /*
+ * The underlying inode->i_blkbits value will not be modified,
+ * so preserve the blocksize specified by the server.
+ */
+ u8 cached_i_blkbits;
};
/** FUSE inode state bits */
@@ -969,6 +975,14 @@ struct fuse_conn {
/* Request timeout (in jiffies). 0 = no timeout */
unsigned int req_timeout;
} timeout;
+
+ /*
+ * This is a workaround until fuse uses iomap for reads.
+ * For fuseblk servers, this represents the blocksize passed in at
+ * mount time and for regular fuse servers, this is equivalent to
+ * inode->i_blkbits.
+ */
+ u8 blkbits;
};
/*
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 67c2318bfc42..7ddfd2b3cc9c 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -289,6 +289,11 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
}
}
+ if (attr->blksize)
+ fi->cached_i_blkbits = ilog2(attr->blksize);
+ else
+ fi->cached_i_blkbits = fc->blkbits;
+
/*
* Don't set the sticky bit in i_mode, unless we want the VFS
* to check permissions. This prevents failures due to the
@@ -1805,10 +1810,21 @@ int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx)
err = -EINVAL;
if (!sb_set_blocksize(sb, ctx->blksize))
goto err;
+ /*
+ * This is a workaround until fuse hooks into iomap for reads.
+ * Use PAGE_SIZE for the blocksize else if the writeback cache
+ * is enabled, buffered writes go through iomap and a read may
+ * overwrite partially written data if blocksize < PAGE_SIZE
+ */
+ fc->blkbits = sb->s_blocksize_bits;
+ if (ctx->blksize != PAGE_SIZE &&
+ !sb_set_blocksize(sb, PAGE_SIZE))
+ goto err;
#endif
} else {
sb->s_blocksize = PAGE_SIZE;
sb->s_blocksize_bits = PAGE_SHIFT;
+ fc->blkbits = sb->s_blocksize_bits;
}
sb->s_subtype = ctx->subtype;
diff --git a/fs/fuse/passthrough.c b/fs/fuse/passthrough.c
index 607ef735ad4a..eb97ac009e75 100644
--- a/fs/fuse/passthrough.c
+++ b/fs/fuse/passthrough.c
@@ -237,6 +237,11 @@ int fuse_backing_open(struct fuse_conn *fc, struct fuse_backing_map *map)
if (!file)
goto out;
+ /* read/write/splice/mmap passthrough only relevant for regular files */
+ res = d_is_dir(file->f_path.dentry) ? -EISDIR : -EINVAL;
+ if (!d_is_reg(file->f_path.dentry))
+ goto out_fput;
+
backing_sb = file_inode(file)->i_sb;
res = -ELOOP;
if (backing_sb->s_stack_depth >= fc->max_stack_depth)
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index c826e7ca49f5..76c8fd0bfc75 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -1016,7 +1016,7 @@ static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
if (kaddr)
*kaddr = fs->window_kaddr + offset;
if (pfn)
- *pfn = fs->window_phys_addr + offset;
+ *pfn = PHYS_PFN(fs->window_phys_addr + offset);
return nr_pages > max_nr_pages ? max_nr_pages : nr_pages;
}
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index a6c692cac616..9adf36e6364b 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -70,6 +70,24 @@ static struct kernfs_open_node *of_on(struct kernfs_open_file *of)
!list_empty(&of->list));
}
+/* Get active reference to kernfs node for an open file */
+static struct kernfs_open_file *kernfs_get_active_of(struct kernfs_open_file *of)
+{
+ /* Skip if file was already released */
+ if (unlikely(of->released))
+ return NULL;
+
+ if (!kernfs_get_active(of->kn))
+ return NULL;
+
+ return of;
+}
+
+static void kernfs_put_active_of(struct kernfs_open_file *of)
+{
+ return kernfs_put_active(of->kn);
+}
+
/**
* kernfs_deref_open_node_locked - Get kernfs_open_node corresponding to @kn
*
@@ -139,7 +157,7 @@ static void kernfs_seq_stop_active(struct seq_file *sf, void *v)
if (ops->seq_stop)
ops->seq_stop(sf, v);
- kernfs_put_active(of->kn);
+ kernfs_put_active_of(of);
}
static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos)
@@ -152,7 +170,7 @@ static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos)
* the ops aren't called concurrently for the same open file.
*/
mutex_lock(&of->mutex);
- if (!kernfs_get_active(of->kn))
+ if (!kernfs_get_active_of(of))
return ERR_PTR(-ENODEV);
ops = kernfs_ops(of->kn);
@@ -238,7 +256,7 @@ static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
* the ops aren't called concurrently for the same open file.
*/
mutex_lock(&of->mutex);
- if (!kernfs_get_active(of->kn)) {
+ if (!kernfs_get_active_of(of)) {
len = -ENODEV;
mutex_unlock(&of->mutex);
goto out_free;
@@ -252,7 +270,7 @@ static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
else
len = -EINVAL;
- kernfs_put_active(of->kn);
+ kernfs_put_active_of(of);
mutex_unlock(&of->mutex);
if (len < 0)
@@ -323,7 +341,7 @@ static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter)
* the ops aren't called concurrently for the same open file.
*/
mutex_lock(&of->mutex);
- if (!kernfs_get_active(of->kn)) {
+ if (!kernfs_get_active_of(of)) {
mutex_unlock(&of->mutex);
len = -ENODEV;
goto out_free;
@@ -335,7 +353,7 @@ static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter)
else
len = -EINVAL;
- kernfs_put_active(of->kn);
+ kernfs_put_active_of(of);
mutex_unlock(&of->mutex);
if (len > 0)
@@ -357,13 +375,13 @@ static void kernfs_vma_open(struct vm_area_struct *vma)
if (!of->vm_ops)
return;
- if (!kernfs_get_active(of->kn))
+ if (!kernfs_get_active_of(of))
return;
if (of->vm_ops->open)
of->vm_ops->open(vma);
- kernfs_put_active(of->kn);
+ kernfs_put_active_of(of);
}
static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf)
@@ -375,14 +393,14 @@ static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf)
if (!of->vm_ops)
return VM_FAULT_SIGBUS;
- if (!kernfs_get_active(of->kn))
+ if (!kernfs_get_active_of(of))
return VM_FAULT_SIGBUS;
ret = VM_FAULT_SIGBUS;
if (of->vm_ops->fault)
ret = of->vm_ops->fault(vmf);
- kernfs_put_active(of->kn);
+ kernfs_put_active_of(of);
return ret;
}
@@ -395,7 +413,7 @@ static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf)
if (!of->vm_ops)
return VM_FAULT_SIGBUS;
- if (!kernfs_get_active(of->kn))
+ if (!kernfs_get_active_of(of))
return VM_FAULT_SIGBUS;
ret = 0;
@@ -404,7 +422,7 @@ static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf)
else
file_update_time(file);
- kernfs_put_active(of->kn);
+ kernfs_put_active_of(of);
return ret;
}
@@ -418,14 +436,14 @@ static int kernfs_vma_access(struct vm_area_struct *vma, unsigned long addr,
if (!of->vm_ops)
return -EINVAL;
- if (!kernfs_get_active(of->kn))
+ if (!kernfs_get_active_of(of))
return -EINVAL;
ret = -EINVAL;
if (of->vm_ops->access)
ret = of->vm_ops->access(vma, addr, buf, len, write);
- kernfs_put_active(of->kn);
+ kernfs_put_active_of(of);
return ret;
}
@@ -455,7 +473,7 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma)
mutex_lock(&of->mutex);
rc = -ENODEV;
- if (!kernfs_get_active(of->kn))
+ if (!kernfs_get_active_of(of))
goto out_unlock;
ops = kernfs_ops(of->kn);
@@ -490,7 +508,7 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma)
}
vma->vm_ops = &kernfs_vm_ops;
out_put:
- kernfs_put_active(of->kn);
+ kernfs_put_active_of(of);
out_unlock:
mutex_unlock(&of->mutex);
@@ -852,7 +870,7 @@ static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait)
struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry);
__poll_t ret;
- if (!kernfs_get_active(kn))
+ if (!kernfs_get_active_of(of))
return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI;
if (kn->attr.ops->poll)
@@ -860,7 +878,7 @@ static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait)
else
ret = kernfs_generic_poll(of, wait);
- kernfs_put_active(kn);
+ kernfs_put_active_of(of);
return ret;
}
@@ -875,7 +893,7 @@ static loff_t kernfs_fop_llseek(struct file *file, loff_t offset, int whence)
* the ops aren't called concurrently for the same open file.
*/
mutex_lock(&of->mutex);
- if (!kernfs_get_active(of->kn)) {
+ if (!kernfs_get_active_of(of)) {
mutex_unlock(&of->mutex);
return -ENODEV;
}
@@ -886,7 +904,7 @@ static loff_t kernfs_fop_llseek(struct file *file, loff_t offset, int whence)
else
ret = generic_file_llseek(file, offset, whence);
- kernfs_put_active(of->kn);
+ kernfs_put_active_of(of);
mutex_unlock(&of->mutex);
return ret;
}
diff --git a/fs/namespace.c b/fs/namespace.c
index ae6d1312b184..51f77c65c0c6 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2455,7 +2455,7 @@ struct vfsmount *clone_private_mount(const struct path *path)
return ERR_PTR(-EINVAL);
}
- if (!ns_capable(old_mnt->mnt_ns->user_ns, CAP_SYS_ADMIN))
+ if (!ns_capable(old_mnt->mnt_ns->user_ns, CAP_SYS_ADMIN))
return ERR_PTR(-EPERM);
if (__has_locked_children(old_mnt, path->dentry))
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 8fb4a950dd55..4e3dcc157a83 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -888,6 +888,8 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
if (fsinfo->xattr_support)
server->caps |= NFS_CAP_XATTR;
+ else
+ server->caps &= ~NFS_CAP_XATTR;
#endif
}
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 86e36c630f09..8059ece82468 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -28,6 +28,7 @@
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/gfp.h>
+#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/compaction.h>
@@ -280,6 +281,37 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
}
EXPORT_SYMBOL_GPL(nfs_file_fsync);
+void nfs_truncate_last_folio(struct address_space *mapping, loff_t from,
+ loff_t to)
+{
+ struct folio *folio;
+
+ if (from >= to)
+ return;
+
+ folio = filemap_lock_folio(mapping, from >> PAGE_SHIFT);
+ if (IS_ERR(folio))
+ return;
+
+ if (folio_mkclean(folio))
+ folio_mark_dirty(folio);
+
+ if (folio_test_uptodate(folio)) {
+ loff_t fpos = folio_pos(folio);
+ size_t offset = from - fpos;
+ size_t end = folio_size(folio);
+
+ if (to - fpos < end)
+ end = to - fpos;
+ folio_zero_segment(folio, offset, end);
+ trace_nfs_size_truncate_folio(mapping->host, to);
+ }
+
+ folio_unlock(folio);
+ folio_put(folio);
+}
+EXPORT_SYMBOL_GPL(nfs_truncate_last_folio);
+
/*
* Decide whether a read/modify/write cycle may be more efficient
* then a modify/write/read cycle when writing to a page in the
@@ -356,6 +388,7 @@ static int nfs_write_begin(const struct kiocb *iocb,
dfprintk(PAGECACHE, "NFS: write_begin(%pD2(%lu), %u@%lld)\n",
file, mapping->host->i_ino, len, (long long) pos);
+ nfs_truncate_last_folio(mapping, i_size_read(mapping->host), pos);
fgp |= fgf_set_order(len);
start:
@@ -442,10 +475,11 @@ static void nfs_invalidate_folio(struct folio *folio, size_t offset,
dfprintk(PAGECACHE, "NFS: invalidate_folio(%lu, %zu, %zu)\n",
folio->index, offset, length);
- if (offset != 0 || length < folio_size(folio))
- return;
/* Cancel any unstarted writes on this page */
- nfs_wb_folio_cancel(inode, folio);
+ if (offset != 0 || length < folio_size(folio))
+ nfs_wb_folio(inode, folio);
+ else
+ nfs_wb_folio_cancel(inode, folio);
folio_wait_private_2(folio); /* [DEPRECATED] */
trace_nfs_invalidate_folio(inode, folio_pos(folio) + offset, length);
}
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 8dc921d83538..9edb5f9b0c4e 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -293,7 +293,7 @@ ff_lseg_match_mirrors(struct pnfs_layout_segment *l1,
struct pnfs_layout_segment *l2)
{
const struct nfs4_ff_layout_segment *fl1 = FF_LAYOUT_LSEG(l1);
- const struct nfs4_ff_layout_segment *fl2 = FF_LAYOUT_LSEG(l1);
+ const struct nfs4_ff_layout_segment *fl2 = FF_LAYOUT_LSEG(l2);
u32 i;
if (fl1->mirror_array_cnt != fl2->mirror_array_cnt)
@@ -773,8 +773,11 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg,
continue;
if (check_device &&
- nfs4_test_deviceid_unavailable(&mirror->mirror_ds->id_node))
+ nfs4_test_deviceid_unavailable(&mirror->mirror_ds->id_node)) {
+ // reinitialize the error state in case if this is the last iteration
+ ds = ERR_PTR(-EINVAL);
continue;
+ }
*best_idx = idx;
break;
@@ -804,7 +807,7 @@ ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg,
struct nfs4_pnfs_ds *ds;
ds = ff_layout_choose_valid_ds_for_read(lseg, start_idx, best_idx);
- if (ds)
+ if (!IS_ERR(ds))
return ds;
return ff_layout_choose_any_ds_for_read(lseg, start_idx, best_idx);
}
@@ -818,7 +821,7 @@ ff_layout_get_ds_for_read(struct nfs_pageio_descriptor *pgio,
ds = ff_layout_choose_best_ds_for_read(lseg, pgio->pg_mirror_idx,
best_idx);
- if (ds || !pgio->pg_mirror_idx)
+ if (!IS_ERR(ds) || !pgio->pg_mirror_idx)
return ds;
return ff_layout_choose_best_ds_for_read(lseg, 0, best_idx);
}
@@ -868,7 +871,7 @@ retry:
req->wb_nio = 0;
ds = ff_layout_get_ds_for_read(pgio, &ds_idx);
- if (!ds) {
+ if (IS_ERR(ds)) {
if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
goto out_mds;
pnfs_generic_pg_cleanup(pgio);
@@ -1072,11 +1075,13 @@ static void ff_layout_resend_pnfs_read(struct nfs_pgio_header *hdr)
{
u32 idx = hdr->pgio_mirror_idx + 1;
u32 new_idx = 0;
+ struct nfs4_pnfs_ds *ds;
- if (ff_layout_choose_any_ds_for_read(hdr->lseg, idx, &new_idx))
- ff_layout_send_layouterror(hdr->lseg);
- else
+ ds = ff_layout_choose_any_ds_for_read(hdr->lseg, idx, &new_idx);
+ if (IS_ERR(ds))
pnfs_error_mark_layout_for_return(hdr->inode, hdr->lseg);
+ else
+ ff_layout_send_layouterror(hdr->lseg);
pnfs_read_resend_pnfs(hdr, new_idx);
}
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 338ef77ae423..49df9debb1a6 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -716,6 +716,7 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
{
struct inode *inode = d_inode(dentry);
struct nfs_fattr *fattr;
+ loff_t oldsize = i_size_read(inode);
int error = 0;
nfs_inc_stats(inode, NFSIOS_VFSSETATTR);
@@ -731,7 +732,7 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
if (error)
return error;
- if (attr->ia_size == i_size_read(inode))
+ if (attr->ia_size == oldsize)
attr->ia_valid &= ~ATTR_SIZE;
}
@@ -767,8 +768,10 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
trace_nfs_setattr_enter(inode);
/* Write all dirty data */
- if (S_ISREG(inode->i_mode))
+ if (S_ISREG(inode->i_mode)) {
+ nfs_file_block_o_direct(NFS_I(inode));
nfs_sync_inode(inode);
+ }
fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode));
if (fattr == NULL) {
@@ -777,8 +780,12 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
}
error = NFS_PROTO(inode)->setattr(dentry, fattr, attr);
- if (error == 0)
+ if (error == 0) {
+ if (attr->ia_valid & ATTR_SIZE)
+ nfs_truncate_last_folio(inode->i_mapping, oldsize,
+ attr->ia_size);
error = nfs_refresh_inode(inode, fattr);
+ }
nfs_free_fattr(fattr);
out:
trace_nfs_setattr_exit(inode, error);
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 74d712b58423..c0a44f389f8f 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -437,6 +437,8 @@ int nfs_file_release(struct inode *, struct file *);
int nfs_lock(struct file *, int, struct file_lock *);
int nfs_flock(struct file *, int, struct file_lock *);
int nfs_check_flags(int);
+void nfs_truncate_last_folio(struct address_space *mapping, loff_t from,
+ loff_t to);
/* inode.c */
extern struct workqueue_struct *nfsiod_workqueue;
@@ -530,6 +532,16 @@ static inline bool nfs_file_io_is_buffered(struct nfs_inode *nfsi)
return test_bit(NFS_INO_ODIRECT, &nfsi->flags) == 0;
}
+/* Must be called with exclusively locked inode->i_rwsem */
+static inline void nfs_file_block_o_direct(struct nfs_inode *nfsi)
+{
+ if (test_bit(NFS_INO_ODIRECT, &nfsi->flags)) {
+ clear_bit(NFS_INO_ODIRECT, &nfsi->flags);
+ inode_dio_wait(&nfsi->vfs_inode);
+ }
+}
+
+
/* namespace.c */
#define NFS_PATH_CANONICAL 1
extern char *nfs_path(char **p, struct dentry *dentry,
diff --git a/fs/nfs/io.c b/fs/nfs/io.c
index 3388faf2acb9..d275b0a250bf 100644
--- a/fs/nfs/io.c
+++ b/fs/nfs/io.c
@@ -14,15 +14,6 @@
#include "internal.h"
-/* Call with exclusively locked inode->i_rwsem */
-static void nfs_block_o_direct(struct nfs_inode *nfsi, struct inode *inode)
-{
- if (test_bit(NFS_INO_ODIRECT, &nfsi->flags)) {
- clear_bit(NFS_INO_ODIRECT, &nfsi->flags);
- inode_dio_wait(inode);
- }
-}
-
/**
* nfs_start_io_read - declare the file is being used for buffered reads
* @inode: file inode
@@ -57,7 +48,7 @@ nfs_start_io_read(struct inode *inode)
err = down_write_killable(&inode->i_rwsem);
if (err)
return err;
- nfs_block_o_direct(nfsi, inode);
+ nfs_file_block_o_direct(nfsi);
downgrade_write(&inode->i_rwsem);
return 0;
@@ -90,7 +81,7 @@ nfs_start_io_write(struct inode *inode)
err = down_write_killable(&inode->i_rwsem);
if (!err)
- nfs_block_o_direct(NFS_I(inode), inode);
+ nfs_file_block_o_direct(NFS_I(inode));
return err;
}
diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c
index bd5fca285899..97abf62f109d 100644
--- a/fs/nfs/localio.c
+++ b/fs/nfs/localio.c
@@ -180,10 +180,8 @@ static void nfs_local_probe(struct nfs_client *clp)
return;
}
- if (nfs_client_is_local(clp)) {
- /* If already enabled, disable and re-enable */
- nfs_localio_disable_client(clp);
- }
+ if (nfs_client_is_local(clp))
+ return;
if (!nfs_uuid_begin(&clp->cl_uuid))
return;
@@ -244,7 +242,8 @@ __nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
case -ENOMEM:
case -ENXIO:
case -ENOENT:
- /* Revalidate localio, will disable if unsupported */
+ /* Revalidate localio */
+ nfs_localio_disable_client(clp);
nfs_local_probe(clp);
}
}
@@ -453,12 +452,13 @@ static void nfs_local_call_read(struct work_struct *work)
nfs_local_iter_init(&iter, iocb, READ);
status = filp->f_op->read_iter(&iocb->kiocb, &iter);
+
+ revert_creds(save_cred);
+
if (status != -EIOCBQUEUED) {
nfs_local_read_done(iocb, status);
nfs_local_pgio_release(iocb);
}
-
- revert_creds(save_cred);
}
static int
@@ -648,14 +648,15 @@ static void nfs_local_call_write(struct work_struct *work)
file_start_write(filp);
status = filp->f_op->write_iter(&iocb->kiocb, &iter);
file_end_write(filp);
+
+ revert_creds(save_cred);
+ current->flags = old_flags;
+
if (status != -EIOCBQUEUED) {
nfs_local_write_done(iocb, status);
nfs_local_vfs_getattr(iocb);
nfs_local_pgio_release(iocb);
}
-
- revert_creds(save_cred);
- current->flags = old_flags;
}
static int
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 01c01f45358b..6a0b5871ba3b 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -114,6 +114,7 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
exception.inode = inode;
exception.state = lock->open_context->state;
+ nfs_file_block_o_direct(NFS_I(inode));
err = nfs_sync_inode(inode);
if (err)
goto out;
@@ -137,6 +138,7 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len)
.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ALLOCATE],
};
struct inode *inode = file_inode(filep);
+ loff_t oldsize = i_size_read(inode);
int err;
if (!nfs_server_capable(inode, NFS_CAP_ALLOCATE))
@@ -145,7 +147,11 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len)
inode_lock(inode);
err = nfs42_proc_fallocate(&msg, filep, offset, len);
- if (err == -EOPNOTSUPP)
+
+ if (err == 0)
+ nfs_truncate_last_folio(inode->i_mapping, oldsize,
+ offset + len);
+ else if (err == -EOPNOTSUPP)
NFS_SERVER(inode)->caps &= ~(NFS_CAP_ALLOCATE |
NFS_CAP_ZERO_RANGE);
@@ -183,6 +189,7 @@ int nfs42_proc_zero_range(struct file *filep, loff_t offset, loff_t len)
.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ZERO_RANGE],
};
struct inode *inode = file_inode(filep);
+ loff_t oldsize = i_size_read(inode);
int err;
if (!nfs_server_capable(inode, NFS_CAP_ZERO_RANGE))
@@ -191,9 +198,11 @@ int nfs42_proc_zero_range(struct file *filep, loff_t offset, loff_t len)
inode_lock(inode);
err = nfs42_proc_fallocate(&msg, filep, offset, len);
- if (err == 0)
+ if (err == 0) {
+ nfs_truncate_last_folio(inode->i_mapping, oldsize,
+ offset + len);
truncate_pagecache_range(inode, offset, (offset + len) -1);
- if (err == -EOPNOTSUPP)
+ } else if (err == -EOPNOTSUPP)
NFS_SERVER(inode)->caps &= ~NFS_CAP_ZERO_RANGE;
inode_unlock(inode);
@@ -354,22 +363,27 @@ out:
/**
* nfs42_copy_dest_done - perform inode cache updates after clone/copy offload
- * @inode: pointer to destination inode
+ * @file: pointer to destination file
* @pos: destination offset
* @len: copy length
+ * @oldsize: length of the file prior to clone/copy
*
* Punch a hole in the inode page cache, so that the NFS client will
* know to retrieve new data.
* Update the file size if necessary, and then mark the inode as having
* invalid cached values for change attribute, ctime, mtime and space used.
*/
-static void nfs42_copy_dest_done(struct inode *inode, loff_t pos, loff_t len)
+static void nfs42_copy_dest_done(struct file *file, loff_t pos, loff_t len,
+ loff_t oldsize)
{
+ struct inode *inode = file_inode(file);
+ struct address_space *mapping = file->f_mapping;
loff_t newsize = pos + len;
loff_t end = newsize - 1;
- WARN_ON_ONCE(invalidate_inode_pages2_range(inode->i_mapping,
- pos >> PAGE_SHIFT, end >> PAGE_SHIFT));
+ nfs_truncate_last_folio(mapping, oldsize, pos);
+ WARN_ON_ONCE(invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT,
+ end >> PAGE_SHIFT));
spin_lock(&inode->i_lock);
if (newsize > i_size_read(inode))
@@ -402,6 +416,7 @@ static ssize_t _nfs42_proc_copy(struct file *src,
struct nfs_server *src_server = NFS_SERVER(src_inode);
loff_t pos_src = args->src_pos;
loff_t pos_dst = args->dst_pos;
+ loff_t oldsize_dst = i_size_read(dst_inode);
size_t count = args->count;
ssize_t status;
@@ -430,6 +445,7 @@ static ssize_t _nfs42_proc_copy(struct file *src,
return status;
}
+ nfs_file_block_o_direct(NFS_I(dst_inode));
status = nfs_sync_inode(dst_inode);
if (status)
return status;
@@ -475,7 +491,7 @@ static ssize_t _nfs42_proc_copy(struct file *src,
goto out;
}
- nfs42_copy_dest_done(dst_inode, pos_dst, res->write_res.count);
+ nfs42_copy_dest_done(dst, pos_dst, res->write_res.count, oldsize_dst);
nfs_invalidate_atime(src_inode);
status = res->write_res.count;
out:
@@ -1242,6 +1258,7 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f,
struct nfs42_clone_res res = {
.server = server,
};
+ loff_t oldsize_dst = i_size_read(dst_inode);
int status;
msg->rpc_argp = &args;
@@ -1276,7 +1293,7 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f,
/* a zero-length count means clone to EOF in src */
if (count == 0 && res.dst_fattr->valid & NFS_ATTR_FATTR_SIZE)
count = nfs_size_to_loff_t(res.dst_fattr->size) - dst_offset;
- nfs42_copy_dest_done(dst_inode, dst_offset, count);
+ nfs42_copy_dest_done(dst_f, dst_offset, count, oldsize_dst);
status = nfs_post_op_update_inode(dst_inode, res.dst_fattr);
}
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 1d6b5f4230c9..c9a0d1e420c6 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -278,9 +278,11 @@ static loff_t nfs42_remap_file_range(struct file *src_file, loff_t src_off,
lock_two_nondirectories(src_inode, dst_inode);
/* flush all pending writes on both src and dst so that server
* has the latest data */
+ nfs_file_block_o_direct(NFS_I(src_inode));
ret = nfs_sync_inode(src_inode);
if (ret)
goto out_unlock;
+ nfs_file_block_o_direct(NFS_I(dst_inode));
ret = nfs_sync_inode(dst_inode);
if (ret)
goto out_unlock;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 7d2b67e06cc3..ce61253efd45 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -4013,8 +4013,10 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
res.attr_bitmask[2];
}
memcpy(server->attr_bitmask, res.attr_bitmask, sizeof(server->attr_bitmask));
- server->caps &= ~(NFS_CAP_ACLS | NFS_CAP_HARDLINKS |
- NFS_CAP_SYMLINKS| NFS_CAP_SECURITY_LABEL);
+ server->caps &=
+ ~(NFS_CAP_ACLS | NFS_CAP_HARDLINKS | NFS_CAP_SYMLINKS |
+ NFS_CAP_SECURITY_LABEL | NFS_CAP_FS_LOCATIONS |
+ NFS_CAP_OPEN_XOR | NFS_CAP_DELEGTIME);
server->fattr_valid = NFS_ATTR_FATTR_V4;
if (res.attr_bitmask[0] & FATTR4_WORD0_ACL &&
res.acl_bitmask & ACL4_SUPPORT_ALLOW_ACL)
@@ -4092,7 +4094,6 @@ int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle)
};
int err;
- nfs_server_set_init_caps(server);
do {
err = nfs4_handle_exception(server,
_nfs4_server_capabilities(server, fhandle),
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 96b1323318c2..627115179795 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -272,6 +272,7 @@ DECLARE_EVENT_CLASS(nfs_update_size_class,
TP_ARGS(inode, new_size))
DEFINE_NFS_UPDATE_SIZE_EVENT(truncate);
+DEFINE_NFS_UPDATE_SIZE_EVENT(truncate_folio);
DEFINE_NFS_UPDATE_SIZE_EVENT(wcc);
DEFINE_NFS_UPDATE_SIZE_EVENT(update);
DEFINE_NFS_UPDATE_SIZE_EVENT(grow);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 8b7c04737967..647c53d1418a 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -237,59 +237,17 @@ static void nfs_mapping_set_error(struct folio *folio, int error)
}
/*
- * nfs_page_group_search_locked
- * @head - head request of page group
- * @page_offset - offset into page
+ * nfs_page_covers_folio
+ * @req: struct nfs_page
*
- * Search page group with head @head to find a request that contains the
- * page offset @page_offset.
- *
- * Returns a pointer to the first matching nfs request, or NULL if no
- * match is found.
- *
- * Must be called with the page group lock held
- */
-static struct nfs_page *
-nfs_page_group_search_locked(struct nfs_page *head, unsigned int page_offset)
-{
- struct nfs_page *req;
-
- req = head;
- do {
- if (page_offset >= req->wb_pgbase &&
- page_offset < (req->wb_pgbase + req->wb_bytes))
- return req;
-
- req = req->wb_this_page;
- } while (req != head);
-
- return NULL;
-}
-
-/*
- * nfs_page_group_covers_page
- * @head - head request of page group
- *
- * Return true if the page group with head @head covers the whole page,
- * returns false otherwise
+ * Return true if the request covers the whole folio.
+ * Note that the caller should ensure all subrequests have been joined
*/
static bool nfs_page_group_covers_page(struct nfs_page *req)
{
unsigned int len = nfs_folio_length(nfs_page_to_folio(req));
- struct nfs_page *tmp;
- unsigned int pos = 0;
-
- nfs_page_group_lock(req);
- for (;;) {
- tmp = nfs_page_group_search_locked(req->wb_head, pos);
- if (!tmp)
- break;
- pos = tmp->wb_pgbase + tmp->wb_bytes;
- }
-
- nfs_page_group_unlock(req);
- return pos >= len;
+ return req->wb_pgbase == 0 && req->wb_bytes == len;
}
/* We can set the PG_uptodate flag if we see that a write request
@@ -2045,6 +2003,7 @@ int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio)
* release it */
nfs_inode_remove_request(req);
nfs_unlock_and_release_request(req);
+ folio_cancel_dirty(folio);
}
return ret;
diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
index 930150ed5db1..ef147e8b3271 100644
--- a/fs/ocfs2/extent_map.c
+++ b/fs/ocfs2/extent_map.c
@@ -706,6 +706,8 @@ out:
* it not only handles the fiemap for inlined files, but also deals
* with the fast symlink, cause they have no difference for extent
* mapping per se.
+ *
+ * Must be called with ip_alloc_sem semaphore held.
*/
static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh,
struct fiemap_extent_info *fieinfo,
@@ -717,6 +719,7 @@ static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh,
u64 phys;
u32 flags = FIEMAP_EXTENT_DATA_INLINE|FIEMAP_EXTENT_LAST;
struct ocfs2_inode_info *oi = OCFS2_I(inode);
+ lockdep_assert_held_read(&oi->ip_alloc_sem);
di = (struct ocfs2_dinode *)di_bh->b_data;
if (ocfs2_inode_is_fast_symlink(inode))
@@ -732,8 +735,11 @@ static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh,
phys += offsetof(struct ocfs2_dinode,
id2.i_data.id_data);
+ /* Release the ip_alloc_sem to prevent deadlock on page fault */
+ up_read(&OCFS2_I(inode)->ip_alloc_sem);
ret = fiemap_fill_next_extent(fieinfo, 0, phys, id_count,
flags);
+ down_read(&OCFS2_I(inode)->ip_alloc_sem);
if (ret < 0)
return ret;
}
@@ -802,9 +808,11 @@ int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
len_bytes = (u64)le16_to_cpu(rec.e_leaf_clusters) << osb->s_clustersize_bits;
phys_bytes = le64_to_cpu(rec.e_blkno) << osb->sb->s_blocksize_bits;
virt_bytes = (u64)le32_to_cpu(rec.e_cpos) << osb->s_clustersize_bits;
-
+ /* Release the ip_alloc_sem to prevent deadlock on page fault */
+ up_read(&OCFS2_I(inode)->ip_alloc_sem);
ret = fiemap_fill_next_extent(fieinfo, virt_bytes, phys_bytes,
len_bytes, fe_flags);
+ down_read(&OCFS2_I(inode)->ip_alloc_sem);
if (ret)
break;
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index bd0c099cfdd2..176281112273 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -393,7 +393,8 @@ struct proc_dir_entry *proc_register(struct proc_dir_entry *dir,
if (proc_alloc_inum(&dp->low_ino))
goto out_free_entry;
- pde_set_flags(dp);
+ if (!S_ISDIR(dp->mode))
+ pde_set_flags(dp);
write_lock(&proc_subdir_lock);
dp->parent = dir;
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 1e64a4fb6af0..0fae95cf81c4 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -87,7 +87,7 @@
#define SMB_INTERFACE_POLL_INTERVAL 600
/* maximum number of PDUs in one compound */
-#define MAX_COMPOUND 7
+#define MAX_COMPOUND 10
/*
* Default number of credits to keep available for SMB3.
@@ -1882,9 +1882,12 @@ static inline bool is_replayable_error(int error)
/* cifs_get_writable_file() flags */
-#define FIND_WR_ANY 0
-#define FIND_WR_FSUID_ONLY 1
-#define FIND_WR_WITH_DELETE 2
+enum cifs_writable_file_flags {
+ FIND_WR_ANY = 0U,
+ FIND_WR_FSUID_ONLY = (1U << 0),
+ FIND_WR_WITH_DELETE = (1U << 1),
+ FIND_WR_NO_PENDING_DELETE = (1U << 2),
+};
#define MID_FREE 0
#define MID_REQUEST_ALLOCATED 1
@@ -2343,6 +2346,8 @@ struct smb2_compound_vars {
struct kvec qi_iov;
struct kvec io_iov[SMB2_IOCTL_IOV_SIZE];
struct kvec si_iov[SMB2_SET_INFO_IOV_SIZE];
+ struct kvec unlink_iov[SMB2_SET_INFO_IOV_SIZE];
+ struct kvec rename_iov[SMB2_SET_INFO_IOV_SIZE];
struct kvec close_iov;
struct smb2_file_rename_info_hdr rename_info;
struct smb2_file_link_info_hdr link_info;
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 186e061068be..cb907e18cc35 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -998,7 +998,10 @@ int cifs_open(struct inode *inode, struct file *file)
/* Get the cached handle as SMB2 close is deferred */
if (OPEN_FMODE(file->f_flags) & FMODE_WRITE) {
- rc = cifs_get_writable_path(tcon, full_path, FIND_WR_FSUID_ONLY, &cfile);
+ rc = cifs_get_writable_path(tcon, full_path,
+ FIND_WR_FSUID_ONLY |
+ FIND_WR_NO_PENDING_DELETE,
+ &cfile);
} else {
rc = cifs_get_readable_path(tcon, full_path, &cfile);
}
@@ -2530,6 +2533,9 @@ refind_writable:
continue;
if (with_delete && !(open_file->fid.access & DELETE))
continue;
+ if ((flags & FIND_WR_NO_PENDING_DELETE) &&
+ open_file->status_file_deleted)
+ continue;
if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) {
if (!open_file->invalidHandle) {
/* found a good writable file */
@@ -2647,6 +2653,16 @@ cifs_get_readable_path(struct cifs_tcon *tcon, const char *name,
spin_unlock(&tcon->open_file_lock);
free_dentry_path(page);
*ret_file = find_readable_file(cinode, 0);
+ if (*ret_file) {
+ spin_lock(&cinode->open_file_lock);
+ if ((*ret_file)->status_file_deleted) {
+ spin_unlock(&cinode->open_file_lock);
+ cifsFileInfo_put(*ret_file);
+ *ret_file = NULL;
+ } else {
+ spin_unlock(&cinode->open_file_lock);
+ }
+ }
return *ret_file ? 0 : -ENOENT;
}
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index fe453a4b3dc8..11d442e8b3d6 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -1931,7 +1931,7 @@ cifs_drop_nlink(struct inode *inode)
* but will return the EACCES to the caller. Note that the VFS does not call
* unlink on negative dentries currently.
*/
-int cifs_unlink(struct inode *dir, struct dentry *dentry)
+static int __cifs_unlink(struct inode *dir, struct dentry *dentry, bool sillyrename)
{
int rc = 0;
unsigned int xid;
@@ -2003,7 +2003,11 @@ retry_std_delete:
goto psx_del_no_retry;
}
- rc = server->ops->unlink(xid, tcon, full_path, cifs_sb, dentry);
+ if (sillyrename || (server->vals->protocol_id > SMB10_PROT_ID &&
+ d_is_positive(dentry) && d_count(dentry) > 2))
+ rc = -EBUSY;
+ else
+ rc = server->ops->unlink(xid, tcon, full_path, cifs_sb, dentry);
psx_del_no_retry:
if (!rc) {
@@ -2071,6 +2075,11 @@ unlink_out:
return rc;
}
+int cifs_unlink(struct inode *dir, struct dentry *dentry)
+{
+ return __cifs_unlink(dir, dentry, false);
+}
+
static int
cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode,
const char *full_path, struct cifs_sb_info *cifs_sb,
@@ -2358,14 +2367,16 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry)
rc = server->ops->rmdir(xid, tcon, full_path, cifs_sb);
cifs_put_tlink(tlink);
+ cifsInode = CIFS_I(d_inode(direntry));
+
if (!rc) {
+ set_bit(CIFS_INO_DELETE_PENDING, &cifsInode->flags);
spin_lock(&d_inode(direntry)->i_lock);
i_size_write(d_inode(direntry), 0);
clear_nlink(d_inode(direntry));
spin_unlock(&d_inode(direntry)->i_lock);
}
- cifsInode = CIFS_I(d_inode(direntry));
/* force revalidate to go get info when needed */
cifsInode->time = 0;
@@ -2458,8 +2469,11 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry,
}
#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
do_rename_exit:
- if (rc == 0)
+ if (rc == 0) {
d_move(from_dentry, to_dentry);
+ /* Force a new lookup */
+ d_drop(from_dentry);
+ }
cifs_put_tlink(tlink);
return rc;
}
@@ -2470,6 +2484,7 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir,
struct dentry *target_dentry, unsigned int flags)
{
const char *from_name, *to_name;
+ struct TCP_Server_Info *server;
void *page1, *page2;
struct cifs_sb_info *cifs_sb;
struct tcon_link *tlink;
@@ -2505,6 +2520,7 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir,
if (IS_ERR(tlink))
return PTR_ERR(tlink);
tcon = tlink_tcon(tlink);
+ server = tcon->ses->server;
page1 = alloc_dentry_path();
page2 = alloc_dentry_path();
@@ -2591,19 +2607,53 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir,
unlink_target:
#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
-
- /* Try unlinking the target dentry if it's not negative */
- if (d_really_is_positive(target_dentry) && (rc == -EACCES || rc == -EEXIST)) {
- if (d_is_dir(target_dentry))
- tmprc = cifs_rmdir(target_dir, target_dentry);
- else
- tmprc = cifs_unlink(target_dir, target_dentry);
- if (tmprc)
- goto cifs_rename_exit;
- rc = cifs_do_rename(xid, source_dentry, from_name,
- target_dentry, to_name);
- if (!rc)
- rehash = false;
+ if (d_really_is_positive(target_dentry)) {
+ if (!rc) {
+ struct inode *inode = d_inode(target_dentry);
+ /*
+ * Samba and ksmbd servers allow renaming a target
+ * directory that is open, so make sure to update
+ * ->i_nlink and then mark it as delete pending.
+ */
+ if (S_ISDIR(inode->i_mode)) {
+ drop_cached_dir_by_name(xid, tcon, to_name, cifs_sb);
+ spin_lock(&inode->i_lock);
+ i_size_write(inode, 0);
+ clear_nlink(inode);
+ spin_unlock(&inode->i_lock);
+ set_bit(CIFS_INO_DELETE_PENDING, &CIFS_I(inode)->flags);
+ CIFS_I(inode)->time = 0; /* force reval */
+ inode_set_ctime_current(inode);
+ inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
+ }
+ } else if (rc == -EACCES || rc == -EEXIST) {
+ /*
+ * Rename failed, possibly due to a busy target.
+ * Retry it by unliking the target first.
+ */
+ if (d_is_dir(target_dentry)) {
+ tmprc = cifs_rmdir(target_dir, target_dentry);
+ } else {
+ tmprc = __cifs_unlink(target_dir, target_dentry,
+ server->vals->protocol_id > SMB10_PROT_ID);
+ }
+ if (tmprc) {
+ /*
+ * Some servers will return STATUS_ACCESS_DENIED
+ * or STATUS_DIRECTORY_NOT_EMPTY when failing to
+ * rename a non-empty directory. Make sure to
+ * propagate the appropriate error back to
+ * userspace.
+ */
+ if (tmprc == -EEXIST || tmprc == -ENOTEMPTY)
+ rc = tmprc;
+ goto cifs_rename_exit;
+ }
+ rc = cifs_do_rename(xid, source_dentry, from_name,
+ target_dentry, to_name);
+ if (!rc)
+ rehash = false;
+ }
}
/* force revalidate to go get info when needed */
@@ -2629,6 +2679,8 @@ cifs_dentry_needs_reval(struct dentry *dentry)
struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
struct cached_fid *cfid = NULL;
+ if (test_bit(CIFS_INO_DELETE_PENDING, &cifs_i->flags))
+ return false;
if (cifs_i->time == 0)
return true;
diff --git a/fs/smb/client/smb2glob.h b/fs/smb/client/smb2glob.h
index 224495322a05..e56e4d402f13 100644
--- a/fs/smb/client/smb2glob.h
+++ b/fs/smb/client/smb2glob.h
@@ -30,10 +30,9 @@ enum smb2_compound_ops {
SMB2_OP_QUERY_DIR,
SMB2_OP_MKDIR,
SMB2_OP_RENAME,
- SMB2_OP_DELETE,
SMB2_OP_HARDLINK,
SMB2_OP_SET_EOF,
- SMB2_OP_RMDIR,
+ SMB2_OP_UNLINK,
SMB2_OP_POSIX_QUERY_INFO,
SMB2_OP_SET_REPARSE,
SMB2_OP_GET_REPARSE,
diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index 31c13fb5b85b..7cadc8ca4f55 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -346,9 +346,6 @@ replay_again:
trace_smb3_posix_query_info_compound_enter(xid, tcon->tid,
ses->Suid, full_path);
break;
- case SMB2_OP_DELETE:
- trace_smb3_delete_enter(xid, tcon->tid, ses->Suid, full_path);
- break;
case SMB2_OP_MKDIR:
/*
* Directories are created through parameters in the
@@ -356,23 +353,40 @@ replay_again:
*/
trace_smb3_mkdir_enter(xid, tcon->tid, ses->Suid, full_path);
break;
- case SMB2_OP_RMDIR:
- rqst[num_rqst].rq_iov = &vars->si_iov[0];
+ case SMB2_OP_UNLINK:
+ rqst[num_rqst].rq_iov = vars->unlink_iov;
rqst[num_rqst].rq_nvec = 1;
size[0] = 1; /* sizeof __u8 See MS-FSCC section 2.4.11 */
data[0] = &delete_pending[0];
- rc = SMB2_set_info_init(tcon, server,
- &rqst[num_rqst], COMPOUND_FID,
- COMPOUND_FID, current->tgid,
- FILE_DISPOSITION_INFORMATION,
- SMB2_O_INFO_FILE, 0, data, size);
- if (rc)
+ if (cfile) {
+ rc = SMB2_set_info_init(tcon, server,
+ &rqst[num_rqst],
+ cfile->fid.persistent_fid,
+ cfile->fid.volatile_fid,
+ current->tgid,
+ FILE_DISPOSITION_INFORMATION,
+ SMB2_O_INFO_FILE, 0,
+ data, size);
+ } else {
+ rc = SMB2_set_info_init(tcon, server,
+ &rqst[num_rqst],
+ COMPOUND_FID,
+ COMPOUND_FID,
+ current->tgid,
+ FILE_DISPOSITION_INFORMATION,
+ SMB2_O_INFO_FILE, 0,
+ data, size);
+ }
+ if (!rc && (!cfile || num_rqst > 1)) {
+ smb2_set_next_command(tcon, &rqst[num_rqst]);
+ smb2_set_related(&rqst[num_rqst]);
+ } else if (rc) {
goto finished;
- smb2_set_next_command(tcon, &rqst[num_rqst]);
- smb2_set_related(&rqst[num_rqst++]);
- trace_smb3_rmdir_enter(xid, tcon->tid, ses->Suid, full_path);
+ }
+ num_rqst++;
+ trace_smb3_unlink_enter(xid, tcon->tid, ses->Suid, full_path);
break;
case SMB2_OP_SET_EOF:
rqst[num_rqst].rq_iov = &vars->si_iov[0];
@@ -442,7 +456,7 @@ replay_again:
ses->Suid, full_path);
break;
case SMB2_OP_RENAME:
- rqst[num_rqst].rq_iov = &vars->si_iov[0];
+ rqst[num_rqst].rq_iov = vars->rename_iov;
rqst[num_rqst].rq_nvec = 2;
len = in_iov[i].iov_len;
@@ -732,19 +746,6 @@ finished:
trace_smb3_posix_query_info_compound_done(xid, tcon->tid,
ses->Suid);
break;
- case SMB2_OP_DELETE:
- if (rc)
- trace_smb3_delete_err(xid, tcon->tid, ses->Suid, rc);
- else {
- /*
- * If dentry (hence, inode) is NULL, lease break is going to
- * take care of degrading leases on handles for deleted files.
- */
- if (inode)
- cifs_mark_open_handles_for_deleted_file(inode, full_path);
- trace_smb3_delete_done(xid, tcon->tid, ses->Suid);
- }
- break;
case SMB2_OP_MKDIR:
if (rc)
trace_smb3_mkdir_err(xid, tcon->tid, ses->Suid, rc);
@@ -765,11 +766,11 @@ finished:
trace_smb3_rename_done(xid, tcon->tid, ses->Suid);
SMB2_set_info_free(&rqst[num_rqst++]);
break;
- case SMB2_OP_RMDIR:
- if (rc)
- trace_smb3_rmdir_err(xid, tcon->tid, ses->Suid, rc);
+ case SMB2_OP_UNLINK:
+ if (!rc)
+ trace_smb3_unlink_done(xid, tcon->tid, ses->Suid);
else
- trace_smb3_rmdir_done(xid, tcon->tid, ses->Suid);
+ trace_smb3_unlink_err(xid, tcon->tid, ses->Suid, rc);
SMB2_set_info_free(&rqst[num_rqst++]);
break;
case SMB2_OP_SET_EOF:
@@ -1166,7 +1167,7 @@ smb2_rmdir(const unsigned int xid, struct cifs_tcon *tcon, const char *name,
FILE_OPEN, CREATE_NOT_FILE, ACL_NO_MODE);
return smb2_compound_op(xid, tcon, cifs_sb,
name, &oparms, NULL,
- &(int){SMB2_OP_RMDIR}, 1,
+ &(int){SMB2_OP_UNLINK}, 1,
NULL, NULL, NULL, NULL);
}
@@ -1175,20 +1176,29 @@ smb2_unlink(const unsigned int xid, struct cifs_tcon *tcon, const char *name,
struct cifs_sb_info *cifs_sb, struct dentry *dentry)
{
struct cifs_open_parms oparms;
+ struct inode *inode = NULL;
+ int rc;
- oparms = CIFS_OPARMS(cifs_sb, tcon, name,
- DELETE, FILE_OPEN,
- CREATE_DELETE_ON_CLOSE | OPEN_REPARSE_POINT,
- ACL_NO_MODE);
- int rc = smb2_compound_op(xid, tcon, cifs_sb, name, &oparms,
- NULL, &(int){SMB2_OP_DELETE}, 1,
- NULL, NULL, NULL, dentry);
+ if (dentry)
+ inode = d_inode(dentry);
+
+ oparms = CIFS_OPARMS(cifs_sb, tcon, name, DELETE,
+ FILE_OPEN, OPEN_REPARSE_POINT, ACL_NO_MODE);
+ rc = smb2_compound_op(xid, tcon, cifs_sb, name, &oparms,
+ NULL, &(int){SMB2_OP_UNLINK},
+ 1, NULL, NULL, NULL, dentry);
if (rc == -EINVAL) {
cifs_dbg(FYI, "invalid lease key, resending request without lease");
rc = smb2_compound_op(xid, tcon, cifs_sb, name, &oparms,
- NULL, &(int){SMB2_OP_DELETE}, 1,
- NULL, NULL, NULL, NULL);
+ NULL, &(int){SMB2_OP_UNLINK},
+ 1, NULL, NULL, NULL, NULL);
}
+ /*
+ * If dentry (hence, inode) is NULL, lease break is going to
+ * take care of degrading leases on handles for deleted files.
+ */
+ if (!rc && inode)
+ cifs_mark_open_handles_for_deleted_file(inode, name);
return rc;
}
@@ -1441,3 +1451,113 @@ out:
cifs_free_open_info(&data);
return rc;
}
+
+static inline __le16 *utf16_smb2_path(struct cifs_sb_info *cifs_sb,
+ const char *name, size_t namelen)
+{
+ int len;
+
+ if (*name == '\\' ||
+ (cifs_sb_master_tlink(cifs_sb) &&
+ cifs_sb_master_tcon(cifs_sb)->posix_extensions && *name == '/'))
+ name++;
+ return cifs_strndup_to_utf16(name, namelen, &len,
+ cifs_sb->local_nls,
+ cifs_remap(cifs_sb));
+}
+
+int smb2_rename_pending_delete(const char *full_path,
+ struct dentry *dentry,
+ const unsigned int xid)
+{
+ struct cifs_sb_info *cifs_sb = CIFS_SB(d_inode(dentry)->i_sb);
+ struct cifsInodeInfo *cinode = CIFS_I(d_inode(dentry));
+ __le16 *utf16_path __free(kfree) = NULL;
+ __u32 co = file_create_options(dentry);
+ int cmds[] = {
+ SMB2_OP_SET_INFO,
+ SMB2_OP_RENAME,
+ SMB2_OP_UNLINK,
+ };
+ const int num_cmds = ARRAY_SIZE(cmds);
+ char *to_name __free(kfree) = NULL;
+ __u32 attrs = cinode->cifsAttrs;
+ struct cifs_open_parms oparms;
+ static atomic_t sillycounter;
+ struct cifsFileInfo *cfile;
+ struct tcon_link *tlink;
+ struct cifs_tcon *tcon;
+ struct kvec iov[2];
+ const char *ppath;
+ void *page;
+ size_t len;
+ int rc;
+
+ tlink = cifs_sb_tlink(cifs_sb);
+ if (IS_ERR(tlink))
+ return PTR_ERR(tlink);
+ tcon = tlink_tcon(tlink);
+
+ page = alloc_dentry_path();
+
+ ppath = build_path_from_dentry(dentry->d_parent, page);
+ if (IS_ERR(ppath)) {
+ rc = PTR_ERR(ppath);
+ goto out;
+ }
+
+ len = strlen(ppath) + strlen("/.__smb1234") + 1;
+ to_name = kmalloc(len, GFP_KERNEL);
+ if (!to_name) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ scnprintf(to_name, len, "%s%c.__smb%04X", ppath, CIFS_DIR_SEP(cifs_sb),
+ atomic_inc_return(&sillycounter) & 0xffff);
+
+ utf16_path = utf16_smb2_path(cifs_sb, to_name, len);
+ if (!utf16_path) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ drop_cached_dir_by_name(xid, tcon, full_path, cifs_sb);
+ oparms = CIFS_OPARMS(cifs_sb, tcon, full_path,
+ DELETE | FILE_WRITE_ATTRIBUTES,
+ FILE_OPEN, co, ACL_NO_MODE);
+
+ attrs &= ~ATTR_READONLY;
+ if (!attrs)
+ attrs = ATTR_NORMAL;
+ if (d_inode(dentry)->i_nlink <= 1)
+ attrs |= ATTR_HIDDEN;
+ iov[0].iov_base = &(FILE_BASIC_INFO) {
+ .Attributes = cpu_to_le32(attrs),
+ };
+ iov[0].iov_len = sizeof(FILE_BASIC_INFO);
+ iov[1].iov_base = utf16_path;
+ iov[1].iov_len = sizeof(*utf16_path) * UniStrlen((wchar_t *)utf16_path);
+
+ cifs_get_writable_path(tcon, full_path, FIND_WR_WITH_DELETE, &cfile);
+ rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, iov,
+ cmds, num_cmds, cfile, NULL, NULL, dentry);
+ if (rc == -EINVAL) {
+ cifs_dbg(FYI, "invalid lease key, resending request without lease\n");
+ cifs_get_writable_path(tcon, full_path,
+ FIND_WR_WITH_DELETE, &cfile);
+ rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, iov,
+ cmds, num_cmds, cfile, NULL, NULL, NULL);
+ }
+ if (!rc) {
+ set_bit(CIFS_INO_DELETE_PENDING, &cinode->flags);
+ } else {
+ cifs_tcon_dbg(FYI, "%s: failed to rename '%s' to '%s': %d\n",
+ __func__, full_path, to_name, rc);
+ rc = -EIO;
+ }
+out:
+ cifs_put_tlink(tlink);
+ free_dentry_path(page);
+ return rc;
+}
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 94b1d7a395d5..e586f3f4b5c9 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -2640,13 +2640,35 @@ smb2_set_next_command(struct cifs_tcon *tcon, struct smb_rqst *rqst)
}
/* SMB headers in a compound are 8 byte aligned. */
- if (!IS_ALIGNED(len, 8)) {
- num_padding = 8 - (len & 7);
+ if (IS_ALIGNED(len, 8))
+ goto out;
+
+ num_padding = 8 - (len & 7);
+ if (smb3_encryption_required(tcon)) {
+ int i;
+
+ /*
+ * Flatten request into a single buffer with required padding as
+ * the encryption layer can't handle the padding iovs.
+ */
+ for (i = 1; i < rqst->rq_nvec; i++) {
+ memcpy(rqst->rq_iov[0].iov_base +
+ rqst->rq_iov[0].iov_len,
+ rqst->rq_iov[i].iov_base,
+ rqst->rq_iov[i].iov_len);
+ rqst->rq_iov[0].iov_len += rqst->rq_iov[i].iov_len;
+ }
+ memset(rqst->rq_iov[0].iov_base + rqst->rq_iov[0].iov_len,
+ 0, num_padding);
+ rqst->rq_iov[0].iov_len += num_padding;
+ rqst->rq_nvec = 1;
+ } else {
rqst->rq_iov[rqst->rq_nvec].iov_base = smb2_padding;
rqst->rq_iov[rqst->rq_nvec].iov_len = num_padding;
rqst->rq_nvec++;
- len += num_padding;
}
+ len += num_padding;
+out:
shdr->NextCommand = cpu_to_le32(len);
}
@@ -5376,6 +5398,7 @@ struct smb_version_operations smb20_operations = {
.llseek = smb3_llseek,
.is_status_io_timeout = smb2_is_status_io_timeout,
.is_network_name_deleted = smb2_is_network_name_deleted,
+ .rename_pending_delete = smb2_rename_pending_delete,
};
#endif /* CIFS_ALLOW_INSECURE_LEGACY */
@@ -5481,6 +5504,7 @@ struct smb_version_operations smb21_operations = {
.llseek = smb3_llseek,
.is_status_io_timeout = smb2_is_status_io_timeout,
.is_network_name_deleted = smb2_is_network_name_deleted,
+ .rename_pending_delete = smb2_rename_pending_delete,
};
struct smb_version_operations smb30_operations = {
@@ -5597,6 +5621,7 @@ struct smb_version_operations smb30_operations = {
.llseek = smb3_llseek,
.is_status_io_timeout = smb2_is_status_io_timeout,
.is_network_name_deleted = smb2_is_network_name_deleted,
+ .rename_pending_delete = smb2_rename_pending_delete,
};
struct smb_version_operations smb311_operations = {
@@ -5713,6 +5738,7 @@ struct smb_version_operations smb311_operations = {
.llseek = smb3_llseek,
.is_status_io_timeout = smb2_is_status_io_timeout,
.is_network_name_deleted = smb2_is_network_name_deleted,
+ .rename_pending_delete = smb2_rename_pending_delete,
};
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h
index 6e805ece6a7b..b3f1398c9f79 100644
--- a/fs/smb/client/smb2proto.h
+++ b/fs/smb/client/smb2proto.h
@@ -317,5 +317,8 @@ int posix_info_sid_size(const void *beg, const void *end);
int smb2_make_nfs_node(unsigned int xid, struct inode *inode,
struct dentry *dentry, struct cifs_tcon *tcon,
const char *full_path, umode_t mode, dev_t dev);
+int smb2_rename_pending_delete(const char *full_path,
+ struct dentry *dentry,
+ const unsigned int xid);
#endif /* _SMB2PROTO_H */
diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h
index fe0e075bc63c..fd650e2afc76 100644
--- a/fs/smb/client/trace.h
+++ b/fs/smb/client/trace.h
@@ -669,13 +669,12 @@ DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(query_info_compound_enter);
DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(posix_query_info_compound_enter);
DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(hardlink_enter);
DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(rename_enter);
-DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(rmdir_enter);
+DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(unlink_enter);
DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_eof_enter);
DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_info_compound_enter);
DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_reparse_compound_enter);
DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(get_reparse_compound_enter);
DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(query_wsl_ea_compound_enter);
-DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(delete_enter);
DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(mkdir_enter);
DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(tdis_enter);
DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(mknod_enter);
@@ -710,13 +709,12 @@ DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(query_info_compound_done);
DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(posix_query_info_compound_done);
DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(hardlink_done);
DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(rename_done);
-DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(rmdir_done);
+DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(unlink_done);
DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(set_eof_done);
DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(set_info_compound_done);
DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(set_reparse_compound_done);
DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(get_reparse_compound_done);
DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(query_wsl_ea_compound_done);
-DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(delete_done);
DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(mkdir_done);
DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(tdis_done);
DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(mknod_done);
@@ -756,14 +754,13 @@ DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(query_info_compound_err);
DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(posix_query_info_compound_err);
DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(hardlink_err);
DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(rename_err);
-DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(rmdir_err);
+DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(unlink_err);
DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(set_eof_err);
DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(set_info_compound_err);
DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(set_reparse_compound_err);
DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(get_reparse_compound_err);
DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(query_wsl_ea_compound_err);
DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(mkdir_err);
-DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(delete_err);
DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(tdis_err);
DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(mknod_err);