summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/adfs/super.c186
-rw-r--r--fs/affs/super.c374
-rw-r--r--fs/aio.c1
-rw-r--r--fs/attr.c61
-rw-r--r--fs/bcachefs/backpointers.c17
-rw-r--r--fs/bcachefs/btree_gc.c2
-rw-r--r--fs/bcachefs/btree_io.c6
-rw-r--r--fs/bcachefs/btree_update_interior.c3
-rw-r--r--fs/bcachefs/btree_write_buffer.c30
-rw-r--r--fs/bcachefs/btree_write_buffer.h1
-rw-r--r--fs/bcachefs/extents.c5
-rw-r--r--fs/bcachefs/journal_io.c3
-rw-r--r--fs/bcachefs/recovery_passes.c6
-rw-r--r--fs/bcachefs/recovery_passes_types.h1
-rw-r--r--fs/bcachefs/sb-errors_format.h6
-rw-r--r--fs/bcachefs/sb-members.c4
-rw-r--r--fs/bcachefs/sb-members_format.h6
-rw-r--r--fs/bcachefs/super.c1
-rw-r--r--fs/befs/linuxvfs.c199
-rw-r--r--fs/btrfs/ctree.h13
-rw-r--r--fs/btrfs/delayed-ref.c2
-rw-r--r--fs/btrfs/extent_io.c7
-rw-r--r--fs/btrfs/file.c25
-rw-r--r--fs/btrfs/inode.c10
-rw-r--r--fs/btrfs/ioctl.c5
-rw-r--r--fs/btrfs/ordered-data.c4
-rw-r--r--fs/btrfs/super.c3
-rw-r--r--fs/buffer.c5
-rw-r--r--fs/cachefiles/interface.c14
-rw-r--r--fs/cachefiles/namei.c5
-rw-r--r--fs/cachefiles/ondemand.c38
-rw-r--r--fs/ceph/addr.c20
-rw-r--r--fs/char_dev.c2
-rw-r--r--fs/coredump.c1
-rw-r--r--fs/dcache.c16
-rw-r--r--fs/ecryptfs/crypto.c35
-rw-r--r--fs/ecryptfs/ecryptfs_kernel.h9
-rw-r--r--fs/ecryptfs/inode.c12
-rw-r--r--fs/ecryptfs/mmap.c136
-rw-r--r--fs/ecryptfs/read_write.c50
-rw-r--r--fs/efs/super.c43
-rw-r--r--fs/eventfd.c9
-rw-r--r--fs/eventpoll.c51
-rw-r--r--fs/ext4/balloc.c4
-rw-r--r--fs/ext4/dir.c7
-rw-r--r--fs/ext4/ext4.h22
-rw-r--r--fs/ext4/extents.c13
-rw-r--r--fs/ext4/extents_status.c8
-rw-r--r--fs/ext4/extents_status.h3
-rw-r--r--fs/ext4/fast_commit.c8
-rw-r--r--fs/ext4/file.c36
-rw-r--r--fs/ext4/fsmap.c54
-rw-r--r--fs/ext4/ialloc.c5
-rw-r--r--fs/ext4/indirect.c2
-rw-r--r--fs/ext4/inode.c109
-rw-r--r--fs/ext4/ioctl.c21
-rw-r--r--fs/ext4/mballoc.c22
-rw-r--r--fs/ext4/mballoc.h1
-rw-r--r--fs/ext4/mmp.c2
-rw-r--r--fs/ext4/move_extent.c2
-rw-r--r--fs/ext4/namei.c23
-rw-r--r--fs/ext4/page-io.c6
-rw-r--r--fs/ext4/resize.c2
-rw-r--r--fs/ext4/super.c113
-rw-r--r--fs/f2fs/data.c9
-rw-r--r--fs/f2fs/file.c15
-rw-r--r--fs/fcntl.c46
-rw-r--r--fs/fhandle.c5
-rw-r--r--fs/file.c288
-rw-r--r--fs/file_table.c50
-rw-r--r--fs/freevxfs/vxfs_dir.h2
-rw-r--r--fs/fs-writeback.c40
-rw-r--r--fs/fs_parser.c21
-rw-r--r--fs/fsopen.c19
-rw-r--r--fs/fuse/dev.c6
-rw-r--r--fs/gfs2/export.c1
-rw-r--r--fs/gfs2/file.c2
-rw-r--r--fs/gfs2/glock.c12
-rw-r--r--fs/hfs/super.c342
-rw-r--r--fs/hfsplus/hfsplus_fs.h7
-rw-r--r--fs/hfsplus/options.c263
-rw-r--r--fs/hfsplus/super.c84
-rw-r--r--fs/hfsplus/wrapper.c2
-rw-r--r--fs/hpfs/super.c414
-rw-r--r--fs/hugetlbfs/inode.c17
-rw-r--r--fs/inode.c313
-rw-r--r--fs/internal.h18
-rw-r--r--fs/ioctl.c23
-rw-r--r--fs/iomap/buffered-io.c2
-rw-r--r--fs/iomap/direct-io.c43
-rw-r--r--fs/iomap/trace.h3
-rw-r--r--fs/jbd2/commit.c4
-rw-r--r--fs/jbd2/journal.c15
-rw-r--r--fs/jbd2/recovery.c311
-rw-r--r--fs/jfs/jfs_filsys.h1
-rw-r--r--fs/jfs/super.c469
-rw-r--r--fs/kernel_read_file.c12
-rw-r--r--fs/libfs.c23
-rw-r--r--fs/lockd/svclock.c7
-rw-r--r--fs/locks.c15
-rw-r--r--fs/mpage.c2
-rw-r--r--fs/namei.c88
-rw-r--r--fs/namespace.c208
-rw-r--r--fs/netfs/buffered_read.c8
-rw-r--r--fs/netfs/buffered_write.c41
-rw-r--r--fs/netfs/fscache_volume.c3
-rw-r--r--fs/nfsd/nfs4state.c19
-rw-r--r--fs/nilfs2/btnode.c2
-rw-r--r--fs/nilfs2/gcinode.c4
-rw-r--r--fs/nilfs2/mdt.c1
-rw-r--r--fs/nilfs2/page.c24
-rw-r--r--fs/notify/dnotify/dnotify.c5
-rw-r--r--fs/notify/fanotify/fanotify.c1
-rw-r--r--fs/notify/fanotify/fanotify_user.c45
-rw-r--r--fs/notify/inotify/inotify_user.c38
-rw-r--r--fs/ocfs2/cluster/heartbeat.c24
-rw-r--r--fs/ocfs2/export.c1
-rw-r--r--fs/ocfs2/file.c2
-rw-r--r--fs/ocfs2/resize.c2
-rw-r--r--fs/ocfs2/super.c13
-rw-r--r--fs/open.c78
-rw-r--r--fs/overlayfs/copy_up.c1
-rw-r--r--fs/overlayfs/inode.c10
-rw-r--r--fs/overlayfs/overlayfs.h8
-rw-r--r--fs/overlayfs/params.c116
-rw-r--r--fs/pidfs.c86
-rw-r--r--fs/posix_acl.c13
-rw-r--r--fs/proc/base.c1
-rw-r--r--fs/proc/fd.c12
-rw-r--r--fs/proc/task_mmu.c4
-rw-r--r--fs/quota/quota.c12
-rw-r--r--fs/read_write.c161
-rw-r--r--fs/readdir.c28
-rw-r--r--fs/remap_range.c11
-rw-r--r--fs/select.c48
-rw-r--r--fs/seq_file.c2
-rw-r--r--fs/signalfd.c9
-rw-r--r--fs/smb/client/ioctl.c11
-rw-r--r--fs/splice.c78
-rw-r--r--fs/stat.c98
-rw-r--r--fs/statfs.c12
-rw-r--r--fs/sync.c29
-rw-r--r--fs/timerfd.c40
-rw-r--r--fs/ubifs/super.c399
-rw-r--r--fs/ufs/balloc.c107
-rw-r--r--fs/ufs/cylinder.c31
-rw-r--r--fs/ufs/dir.c29
-rw-r--r--fs/ufs/file.c1
-rw-r--r--fs/ufs/inode.c179
-rw-r--r--fs/ufs/namei.c39
-rw-r--r--fs/ufs/super.c49
-rw-r--r--fs/ufs/ufs.h12
-rw-r--r--fs/ufs/ufs_fs.h4
-rw-r--r--fs/ufs/util.c46
-rw-r--r--fs/ufs/util.h61
-rw-r--r--fs/unicode/utf8-core.c26
-rw-r--r--fs/unicode/utf8-selftest.c3
-rw-r--r--fs/utimes.c11
-rw-r--r--fs/xattr.c446
-rw-r--r--fs/xfs/libxfs/xfs_trans_inode.c6
-rw-r--r--fs/xfs/xfs_buf.c7
-rw-r--r--fs/xfs/xfs_buf.h4
-rw-r--r--fs/xfs/xfs_exchrange.c18
-rw-r--r--fs/xfs/xfs_file.c16
-rw-r--r--fs/xfs/xfs_handle.c16
-rw-r--r--fs/xfs/xfs_inode.h15
-rw-r--r--fs/xfs/xfs_ioctl.c69
-rw-r--r--fs/xfs/xfs_iops.c32
-rw-r--r--fs/xfs/xfs_super.c2
169 files changed, 4259 insertions, 3562 deletions
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index f0b999a4961b..017c48a80203 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -6,7 +6,8 @@
*/
#include <linux/module.h>
#include <linux/init.h>
-#include <linux/parser.h>
+#include <linux/fs_parser.h>
+#include <linux/fs_context.h>
#include <linux/mount.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
@@ -115,87 +116,61 @@ static int adfs_show_options(struct seq_file *seq, struct dentry *root)
return 0;
}
-enum {Opt_uid, Opt_gid, Opt_ownmask, Opt_othmask, Opt_ftsuffix, Opt_err};
+enum {Opt_uid, Opt_gid, Opt_ownmask, Opt_othmask, Opt_ftsuffix};
-static const match_table_t tokens = {
- {Opt_uid, "uid=%u"},
- {Opt_gid, "gid=%u"},
- {Opt_ownmask, "ownmask=%o"},
- {Opt_othmask, "othmask=%o"},
- {Opt_ftsuffix, "ftsuffix=%u"},
- {Opt_err, NULL}
+static const struct fs_parameter_spec adfs_param_spec[] = {
+ fsparam_uid ("uid", Opt_uid),
+ fsparam_gid ("gid", Opt_gid),
+ fsparam_u32oct ("ownmask", Opt_ownmask),
+ fsparam_u32oct ("othmask", Opt_othmask),
+ fsparam_u32 ("ftsuffix", Opt_ftsuffix),
+ {}
};
-static int parse_options(struct super_block *sb, struct adfs_sb_info *asb,
- char *options)
+static int adfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
- char *p;
- int option;
-
- if (!options)
- return 0;
-
- while ((p = strsep(&options, ",")) != NULL) {
- substring_t args[MAX_OPT_ARGS];
- int token;
- if (!*p)
- continue;
-
- token = match_token(p, tokens, args);
- switch (token) {
- case Opt_uid:
- if (match_int(args, &option))
- return -EINVAL;
- asb->s_uid = make_kuid(current_user_ns(), option);
- if (!uid_valid(asb->s_uid))
- return -EINVAL;
- break;
- case Opt_gid:
- if (match_int(args, &option))
- return -EINVAL;
- asb->s_gid = make_kgid(current_user_ns(), option);
- if (!gid_valid(asb->s_gid))
- return -EINVAL;
- break;
- case Opt_ownmask:
- if (match_octal(args, &option))
- return -EINVAL;
- asb->s_owner_mask = option;
- break;
- case Opt_othmask:
- if (match_octal(args, &option))
- return -EINVAL;
- asb->s_other_mask = option;
- break;
- case Opt_ftsuffix:
- if (match_int(args, &option))
- return -EINVAL;
- asb->s_ftsuffix = option;
- break;
- default:
- adfs_msg(sb, KERN_ERR,
- "unrecognised mount option \"%s\" or missing value",
- p);
- return -EINVAL;
- }
+ struct adfs_sb_info *asb = fc->s_fs_info;
+ struct fs_parse_result result;
+ int opt;
+
+ opt = fs_parse(fc, adfs_param_spec, param, &result);
+ if (opt < 0)
+ return opt;
+
+ switch (opt) {
+ case Opt_uid:
+ asb->s_uid = result.uid;
+ break;
+ case Opt_gid:
+ asb->s_gid = result.gid;
+ break;
+ case Opt_ownmask:
+ asb->s_owner_mask = result.uint_32;
+ break;
+ case Opt_othmask:
+ asb->s_other_mask = result.uint_32;
+ break;
+ case Opt_ftsuffix:
+ asb->s_ftsuffix = result.uint_32;
+ break;
+ default:
+ return -EINVAL;
}
return 0;
}
-static int adfs_remount(struct super_block *sb, int *flags, char *data)
+static int adfs_reconfigure(struct fs_context *fc)
{
- struct adfs_sb_info temp_asb;
- int ret;
+ struct adfs_sb_info *new_asb = fc->s_fs_info;
+ struct adfs_sb_info *asb = ADFS_SB(fc->root->d_sb);
- sync_filesystem(sb);
- *flags |= ADFS_SB_FLAGS;
+ sync_filesystem(fc->root->d_sb);
+ fc->sb_flags |= ADFS_SB_FLAGS;
- temp_asb = *ADFS_SB(sb);
- ret = parse_options(sb, &temp_asb, data);
- if (ret == 0)
- *ADFS_SB(sb) = temp_asb;
+ /* Structure copy newly parsed options */
+ *asb = *new_asb;
- return ret;
+ return 0;
}
static int adfs_statfs(struct dentry *dentry, struct kstatfs *buf)
@@ -273,7 +248,6 @@ static const struct super_operations adfs_sops = {
.write_inode = adfs_write_inode,
.put_super = adfs_put_super,
.statfs = adfs_statfs,
- .remount_fs = adfs_remount,
.show_options = adfs_show_options,
};
@@ -361,34 +335,21 @@ static int adfs_validate_dr0(struct super_block *sb, struct buffer_head *bh,
return 0;
}
-static int adfs_fill_super(struct super_block *sb, void *data, int silent)
+static int adfs_fill_super(struct super_block *sb, struct fs_context *fc)
{
struct adfs_discrecord *dr;
struct object_info root_obj;
- struct adfs_sb_info *asb;
+ struct adfs_sb_info *asb = sb->s_fs_info;
struct inode *root;
int ret = -EINVAL;
+ int silent = fc->sb_flags & SB_SILENT;
sb->s_flags |= ADFS_SB_FLAGS;
- asb = kzalloc(sizeof(*asb), GFP_KERNEL);
- if (!asb)
- return -ENOMEM;
-
sb->s_fs_info = asb;
sb->s_magic = ADFS_SUPER_MAGIC;
sb->s_time_gran = 10000000;
- /* set default options */
- asb->s_uid = GLOBAL_ROOT_UID;
- asb->s_gid = GLOBAL_ROOT_GID;
- asb->s_owner_mask = ADFS_DEFAULT_OWNER_MASK;
- asb->s_other_mask = ADFS_DEFAULT_OTHER_MASK;
- asb->s_ftsuffix = 0;
-
- if (parse_options(sb, asb, data))
- goto error;
-
/* Try to probe the filesystem boot block */
ret = adfs_probe(sb, ADFS_DISCRECORD, 1, adfs_validate_bblk);
if (ret == -EILSEQ)
@@ -453,18 +414,61 @@ error:
return ret;
}
-static struct dentry *adfs_mount(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data)
+static int adfs_get_tree(struct fs_context *fc)
+{
+ return get_tree_bdev(fc, adfs_fill_super);
+}
+
+static void adfs_free_fc(struct fs_context *fc)
{
- return mount_bdev(fs_type, flags, dev_name, data, adfs_fill_super);
+ struct adfs_context *asb = fc->s_fs_info;
+
+ kfree(asb);
+}
+
+static const struct fs_context_operations adfs_context_ops = {
+ .parse_param = adfs_parse_param,
+ .get_tree = adfs_get_tree,
+ .reconfigure = adfs_reconfigure,
+ .free = adfs_free_fc,
+};
+
+static int adfs_init_fs_context(struct fs_context *fc)
+{
+ struct adfs_sb_info *asb;
+
+ asb = kzalloc(sizeof(struct adfs_sb_info), GFP_KERNEL);
+ if (!asb)
+ return -ENOMEM;
+
+ if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) {
+ struct super_block *sb = fc->root->d_sb;
+ struct adfs_sb_info *old_asb = ADFS_SB(sb);
+
+ /* structure copy existing options before parsing */
+ *asb = *old_asb;
+ } else {
+ /* set default options */
+ asb->s_uid = GLOBAL_ROOT_UID;
+ asb->s_gid = GLOBAL_ROOT_GID;
+ asb->s_owner_mask = ADFS_DEFAULT_OWNER_MASK;
+ asb->s_other_mask = ADFS_DEFAULT_OTHER_MASK;
+ asb->s_ftsuffix = 0;
+ }
+
+ fc->ops = &adfs_context_ops;
+ fc->s_fs_info = asb;
+
+ return 0;
}
static struct file_system_type adfs_fs_type = {
.owner = THIS_MODULE,
.name = "adfs",
- .mount = adfs_mount,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
+ .init_fs_context = adfs_init_fs_context,
+ .parameters = adfs_param_spec,
};
MODULE_ALIAS_FS("adfs");
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 3c5821339609..2fa40337776d 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -14,7 +14,8 @@
#include <linux/module.h>
#include <linux/init.h>
#include <linux/statfs.h>
-#include <linux/parser.h>
+#include <linux/fs_parser.h>
+#include <linux/fs_context.h>
#include <linux/magic.h>
#include <linux/sched.h>
#include <linux/cred.h>
@@ -27,7 +28,6 @@
static int affs_statfs(struct dentry *dentry, struct kstatfs *buf);
static int affs_show_options(struct seq_file *m, struct dentry *root);
-static int affs_remount (struct super_block *sb, int *flags, char *data);
static void
affs_commit_super(struct super_block *sb, int wait)
@@ -155,140 +155,114 @@ static const struct super_operations affs_sops = {
.put_super = affs_put_super,
.sync_fs = affs_sync_fs,
.statfs = affs_statfs,
- .remount_fs = affs_remount,
.show_options = affs_show_options,
};
enum {
Opt_bs, Opt_mode, Opt_mufs, Opt_notruncate, Opt_prefix, Opt_protect,
Opt_reserved, Opt_root, Opt_setgid, Opt_setuid,
- Opt_verbose, Opt_volume, Opt_ignore, Opt_err,
+ Opt_verbose, Opt_volume, Opt_ignore,
};
-static const match_table_t tokens = {
- {Opt_bs, "bs=%u"},
- {Opt_mode, "mode=%o"},
- {Opt_mufs, "mufs"},
- {Opt_notruncate, "nofilenametruncate"},
- {Opt_prefix, "prefix=%s"},
- {Opt_protect, "protect"},
- {Opt_reserved, "reserved=%u"},
- {Opt_root, "root=%u"},
- {Opt_setgid, "setgid=%u"},
- {Opt_setuid, "setuid=%u"},
- {Opt_verbose, "verbose"},
- {Opt_volume, "volume=%s"},
- {Opt_ignore, "grpquota"},
- {Opt_ignore, "noquota"},
- {Opt_ignore, "quota"},
- {Opt_ignore, "usrquota"},
- {Opt_err, NULL},
+struct affs_context {
+ kuid_t uid; /* uid to override */
+ kgid_t gid; /* gid to override */
+ unsigned int mode; /* mode to override */
+ unsigned int reserved; /* Number of reserved blocks */
+ int root_block; /* FFS root block number */
+ int blocksize; /* Initial device blksize */
+ char *prefix; /* Prefix for volumes and assigns */
+ char volume[32]; /* Vol. prefix for absolute symlinks */
+ unsigned long mount_flags; /* Options */
};
-static int
-parse_options(char *options, kuid_t *uid, kgid_t *gid, int *mode, int *reserved, s32 *root,
- int *blocksize, char **prefix, char *volume, unsigned long *mount_opts)
+static const struct fs_parameter_spec affs_param_spec[] = {
+ fsparam_u32 ("bs", Opt_bs),
+ fsparam_u32oct ("mode", Opt_mode),
+ fsparam_flag ("mufs", Opt_mufs),
+ fsparam_flag ("nofilenametruncate", Opt_notruncate),
+ fsparam_string ("prefix", Opt_prefix),
+ fsparam_flag ("protect", Opt_protect),
+ fsparam_u32 ("reserved", Opt_reserved),
+ fsparam_u32 ("root", Opt_root),
+ fsparam_gid ("setgid", Opt_setgid),
+ fsparam_uid ("setuid", Opt_setuid),
+ fsparam_flag ("verbose", Opt_verbose),
+ fsparam_string ("volume", Opt_volume),
+ fsparam_flag ("grpquota", Opt_ignore),
+ fsparam_flag ("noquota", Opt_ignore),
+ fsparam_flag ("quota", Opt_ignore),
+ fsparam_flag ("usrquota", Opt_ignore),
+ {},
+};
+
+static int affs_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
- char *p;
- substring_t args[MAX_OPT_ARGS];
-
- /* Fill in defaults */
-
- *uid = current_uid();
- *gid = current_gid();
- *reserved = 2;
- *root = -1;
- *blocksize = -1;
- volume[0] = ':';
- volume[1] = 0;
- *mount_opts = 0;
- if (!options)
- return 1;
-
- while ((p = strsep(&options, ",")) != NULL) {
- int token, n, option;
- if (!*p)
- continue;
-
- token = match_token(p, tokens, args);
- switch (token) {
- case Opt_bs:
- if (match_int(&args[0], &n))
- return 0;
- if (n != 512 && n != 1024 && n != 2048
- && n != 4096) {
- pr_warn("Invalid blocksize (512, 1024, 2048, 4096 allowed)\n");
- return 0;
- }
- *blocksize = n;
- break;
- case Opt_mode:
- if (match_octal(&args[0], &option))
- return 0;
- *mode = option & 0777;
- affs_set_opt(*mount_opts, SF_SETMODE);
- break;
- case Opt_mufs:
- affs_set_opt(*mount_opts, SF_MUFS);
- break;
- case Opt_notruncate:
- affs_set_opt(*mount_opts, SF_NO_TRUNCATE);
- break;
- case Opt_prefix:
- kfree(*prefix);
- *prefix = match_strdup(&args[0]);
- if (!*prefix)
- return 0;
- affs_set_opt(*mount_opts, SF_PREFIX);
- break;
- case Opt_protect:
- affs_set_opt(*mount_opts, SF_IMMUTABLE);
- break;
- case Opt_reserved:
- if (match_int(&args[0], reserved))
- return 0;
- break;
- case Opt_root:
- if (match_int(&args[0], root))
- return 0;
- break;
- case Opt_setgid:
- if (match_int(&args[0], &option))
- return 0;
- *gid = make_kgid(current_user_ns(), option);
- if (!gid_valid(*gid))
- return 0;
- affs_set_opt(*mount_opts, SF_SETGID);
- break;
- case Opt_setuid:
- if (match_int(&args[0], &option))
- return 0;
- *uid = make_kuid(current_user_ns(), option);
- if (!uid_valid(*uid))
- return 0;
- affs_set_opt(*mount_opts, SF_SETUID);
- break;
- case Opt_verbose:
- affs_set_opt(*mount_opts, SF_VERBOSE);
- break;
- case Opt_volume: {
- char *vol = match_strdup(&args[0]);
- if (!vol)
- return 0;
- strscpy(volume, vol, 32);
- kfree(vol);
- break;
- }
- case Opt_ignore:
- /* Silently ignore the quota options */
- break;
- default:
- pr_warn("Unrecognized mount option \"%s\" or missing value\n",
- p);
- return 0;
+ struct affs_context *ctx = fc->fs_private;
+ struct fs_parse_result result;
+ int n;
+ int opt;
+
+ opt = fs_parse(fc, affs_param_spec, param, &result);
+ if (opt < 0)
+ return opt;
+
+ switch (opt) {
+ case Opt_bs:
+ n = result.uint_32;
+ if (n != 512 && n != 1024 && n != 2048
+ && n != 4096) {
+ pr_warn("Invalid blocksize (512, 1024, 2048, 4096 allowed)\n");
+ return -EINVAL;
}
+ ctx->blocksize = n;
+ break;
+ case Opt_mode:
+ ctx->mode = result.uint_32 & 0777;
+ affs_set_opt(ctx->mount_flags, SF_SETMODE);
+ break;
+ case Opt_mufs:
+ affs_set_opt(ctx->mount_flags, SF_MUFS);
+ break;
+ case Opt_notruncate:
+ affs_set_opt(ctx->mount_flags, SF_NO_TRUNCATE);
+ break;
+ case Opt_prefix:
+ kfree(ctx->prefix);
+ ctx->prefix = param->string;
+ param->string = NULL;
+ affs_set_opt(ctx->mount_flags, SF_PREFIX);
+ break;
+ case Opt_protect:
+ affs_set_opt(ctx->mount_flags, SF_IMMUTABLE);
+ break;
+ case Opt_reserved:
+ ctx->reserved = result.uint_32;
+ break;
+ case Opt_root:
+ ctx->root_block = result.uint_32;
+ break;
+ case Opt_setgid:
+ ctx->gid = result.gid;
+ affs_set_opt(ctx->mount_flags, SF_SETGID);
+ break;
+ case Opt_setuid:
+ ctx->uid = result.uid;
+ affs_set_opt(ctx->mount_flags, SF_SETUID);
+ break;
+ case Opt_verbose:
+ affs_set_opt(ctx->mount_flags, SF_VERBOSE);
+ break;
+ case Opt_volume:
+ strscpy(ctx->volume, param->string, 32);
+ break;
+ case Opt_ignore:
+ /* Silently ignore the quota options */
+ break;
+ default:
+ return -EINVAL;
}
- return 1;
+ return 0;
}
static int affs_show_options(struct seq_file *m, struct dentry *root)
@@ -329,27 +303,22 @@ static int affs_show_options(struct seq_file *m, struct dentry *root)
* hopefully have the guts to do so. Until then: sorry for the mess.
*/
-static int affs_fill_super(struct super_block *sb, void *data, int silent)
+static int affs_fill_super(struct super_block *sb, struct fs_context *fc)
{
struct affs_sb_info *sbi;
+ struct affs_context *ctx = fc->fs_private;
struct buffer_head *root_bh = NULL;
struct buffer_head *boot_bh;
struct inode *root_inode = NULL;
- s32 root_block;
+ int silent = fc->sb_flags & SB_SILENT;
int size, blocksize;
u32 chksum;
int num_bm;
int i, j;
- kuid_t uid;
- kgid_t gid;
- int reserved;
- unsigned long mount_flags;
int tmp_flags; /* fix remount prototype... */
u8 sig[4];
int ret;
- pr_debug("read_super(%s)\n", data ? (const char *)data : "no options");
-
sb->s_magic = AFFS_SUPER_MAGIC;
sb->s_op = &affs_sops;
sb->s_flags |= SB_NODIRATIME;
@@ -369,19 +338,16 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent)
spin_lock_init(&sbi->work_lock);
INIT_DELAYED_WORK(&sbi->sb_work, flush_superblock);
- if (!parse_options(data,&uid,&gid,&i,&reserved,&root_block,
- &blocksize,&sbi->s_prefix,
- sbi->s_volume, &mount_flags)) {
- pr_err("Error parsing options\n");
- return -EINVAL;
- }
- /* N.B. after this point s_prefix must be released */
+ sbi->s_flags = ctx->mount_flags;
+ sbi->s_mode = ctx->mode;
+ sbi->s_uid = ctx->uid;
+ sbi->s_gid = ctx->gid;
+ sbi->s_reserved = ctx->reserved;
+ sbi->s_prefix = ctx->prefix;
+ ctx->prefix = NULL;
+ memcpy(sbi->s_volume, ctx->volume, 32);
- sbi->s_flags = mount_flags;
- sbi->s_mode = i;
- sbi->s_uid = uid;
- sbi->s_gid = gid;
- sbi->s_reserved= reserved;
+ /* N.B. after this point s_prefix must be released */
/* Get the size of the device in 512-byte blocks.
* If we later see that the partition uses bigger
@@ -396,15 +362,16 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent)
i = bdev_logical_block_size(sb->s_bdev);
j = PAGE_SIZE;
+ blocksize = ctx->blocksize;
if (blocksize > 0) {
i = j = blocksize;
size = size / (blocksize / 512);
}
for (blocksize = i; blocksize <= j; blocksize <<= 1, size >>= 1) {
- sbi->s_root_block = root_block;
- if (root_block < 0)
- sbi->s_root_block = (reserved + size - 1) / 2;
+ sbi->s_root_block = ctx->root_block;
+ if (ctx->root_block < 0)
+ sbi->s_root_block = (ctx->reserved + size - 1) / 2;
pr_debug("setting blocksize to %d\n", blocksize);
affs_set_blocksize(sb, blocksize);
sbi->s_partition_size = size;
@@ -424,7 +391,7 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent)
"size=%d, reserved=%d\n",
sb->s_id,
sbi->s_root_block + num_bm,
- blocksize, size, reserved);
+ ctx->blocksize, size, ctx->reserved);
root_bh = affs_bread(sb, sbi->s_root_block + num_bm);
if (!root_bh)
continue;
@@ -447,7 +414,7 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent)
got_root:
/* Keep super block in cache */
sbi->s_root_bh = root_bh;
- root_block = sbi->s_root_block;
+ ctx->root_block = sbi->s_root_block;
/* Find out which kind of FS we have */
boot_bh = sb_bread(sb, 0);
@@ -506,7 +473,7 @@ got_root:
return -EINVAL;
}
- if (affs_test_opt(mount_flags, SF_VERBOSE)) {
+ if (affs_test_opt(ctx->mount_flags, SF_VERBOSE)) {
u8 len = AFFS_ROOT_TAIL(sb, root_bh)->disk_name[0];
pr_notice("Mounting volume \"%.*s\": Type=%.3s\\%c, Blocksize=%d\n",
len > 31 ? 31 : len,
@@ -528,7 +495,7 @@ got_root:
/* set up enough so that it can read an inode */
- root_inode = affs_iget(sb, root_block);
+ root_inode = affs_iget(sb, ctx->root_block);
if (IS_ERR(root_inode))
return PTR_ERR(root_inode);
@@ -548,56 +515,43 @@ got_root:
return 0;
}
-static int
-affs_remount(struct super_block *sb, int *flags, char *data)
+static int affs_reconfigure(struct fs_context *fc)
{
+ struct super_block *sb = fc->root->d_sb;
+ struct affs_context *ctx = fc->fs_private;
struct affs_sb_info *sbi = AFFS_SB(sb);
- int blocksize;
- kuid_t uid;
- kgid_t gid;
- int mode;
- int reserved;
- int root_block;
- unsigned long mount_flags;
int res = 0;
- char volume[32];
- char *prefix = NULL;
-
- pr_debug("%s(flags=0x%x,opts=\"%s\")\n", __func__, *flags, data);
sync_filesystem(sb);
- *flags |= SB_NODIRATIME;
-
- memcpy(volume, sbi->s_volume, 32);
- if (!parse_options(data, &uid, &gid, &mode, &reserved, &root_block,
- &blocksize, &prefix, volume,
- &mount_flags)) {
- kfree(prefix);
- return -EINVAL;
- }
+ fc->sb_flags |= SB_NODIRATIME;
flush_delayed_work(&sbi->sb_work);
- sbi->s_flags = mount_flags;
- sbi->s_mode = mode;
- sbi->s_uid = uid;
- sbi->s_gid = gid;
+ /*
+ * NB: Historically, only mount_flags, mode, uid, gic, prefix,
+ * and volume are accepted during remount.
+ */
+ sbi->s_flags = ctx->mount_flags;
+ sbi->s_mode = ctx->mode;
+ sbi->s_uid = ctx->uid;
+ sbi->s_gid = ctx->gid;
/* protect against readers */
spin_lock(&sbi->symlink_lock);
- if (prefix) {
+ if (ctx->prefix) {
kfree(sbi->s_prefix);
- sbi->s_prefix = prefix;
+ sbi->s_prefix = ctx->prefix;
+ ctx->prefix = NULL;
}
- memcpy(sbi->s_volume, volume, 32);
+ memcpy(sbi->s_volume, ctx->volume, 32);
spin_unlock(&sbi->symlink_lock);
- if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb))
+ if ((bool)(fc->sb_flags & SB_RDONLY) == sb_rdonly(sb))
return 0;
- if (*flags & SB_RDONLY)
+ if (fc->sb_flags & SB_RDONLY)
affs_free_bitmap(sb);
else
- res = affs_init_bitmap(sb, flags);
+ res = affs_init_bitmap(sb, &fc->sb_flags);
return res;
}
@@ -624,10 +578,9 @@ affs_statfs(struct dentry *dentry, struct kstatfs *buf)
return 0;
}
-static struct dentry *affs_mount(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data)
+static int affs_get_tree(struct fs_context *fc)
{
- return mount_bdev(fs_type, flags, dev_name, data, affs_fill_super);
+ return get_tree_bdev(fc, affs_fill_super);
}
static void affs_kill_sb(struct super_block *sb)
@@ -643,12 +596,61 @@ static void affs_kill_sb(struct super_block *sb)
}
}
+static void affs_free_fc(struct fs_context *fc)
+{
+ struct affs_context *ctx = fc->fs_private;
+
+ kfree(ctx->prefix);
+ kfree(ctx);
+}
+
+static const struct fs_context_operations affs_context_ops = {
+ .parse_param = affs_parse_param,
+ .get_tree = affs_get_tree,
+ .reconfigure = affs_reconfigure,
+ .free = affs_free_fc,
+};
+
+static int affs_init_fs_context(struct fs_context *fc)
+{
+ struct affs_context *ctx;
+
+ ctx = kzalloc(sizeof(struct affs_context), GFP_KERNEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) {
+ struct super_block *sb = fc->root->d_sb;
+ struct affs_sb_info *sbi = AFFS_SB(sb);
+
+ /*
+ * NB: historically, no options other than volume were
+ * preserved across a remount unless they were explicitly
+ * passed in.
+ */
+ memcpy(ctx->volume, sbi->s_volume, 32);
+ } else {
+ ctx->uid = current_uid();
+ ctx->gid = current_gid();
+ ctx->reserved = 2;
+ ctx->root_block = -1;
+ ctx->blocksize = -1;
+ ctx->volume[0] = ':';
+ }
+
+ fc->ops = &affs_context_ops;
+ fc->fs_private = ctx;
+
+ return 0;
+}
+
static struct file_system_type affs_fs_type = {
.owner = THIS_MODULE,
.name = "affs",
- .mount = affs_mount,
.kill_sb = affs_kill_sb,
.fs_flags = FS_REQUIRES_DEV,
+ .init_fs_context = affs_init_fs_context,
+ .parameters = affs_param_spec,
};
MODULE_ALIAS_FS("affs");
diff --git a/fs/aio.c b/fs/aio.c
index e8920178b50f..72e3970f4225 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -2191,7 +2191,6 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
return -EINVAL;
spin_lock_irq(&ctx->ctx_lock);
- /* TODO: use a hash or array, this sucks. */
list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) {
if (kiocb->ki_res.obj == obj) {
ret = kiocb->ki_cancel(&kiocb->rw);
diff --git a/fs/attr.c b/fs/attr.c
index c04d19b58f12..9caf63d20d03 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -272,6 +272,47 @@ out_big:
EXPORT_SYMBOL(inode_newsize_ok);
/**
+ * setattr_copy_mgtime - update timestamps for mgtime inodes
+ * @inode: inode timestamps to be updated
+ * @attr: attrs for the update
+ *
+ * With multigrain timestamps, take more care to prevent races when
+ * updating the ctime. Always update the ctime to the very latest using
+ * the standard mechanism, and use that to populate the atime and mtime
+ * appropriately (unless those are being set to specific values).
+ */
+static void setattr_copy_mgtime(struct inode *inode, const struct iattr *attr)
+{
+ unsigned int ia_valid = attr->ia_valid;
+ struct timespec64 now;
+
+ if (ia_valid & ATTR_CTIME) {
+ /*
+ * In the case of an update for a write delegation, we must respect
+ * the value in ia_ctime and not use the current time.
+ */
+ if (ia_valid & ATTR_DELEG)
+ now = inode_set_ctime_deleg(inode, attr->ia_ctime);
+ else
+ now = inode_set_ctime_current(inode);
+ } else {
+ /* If ATTR_CTIME isn't set, then ATTR_MTIME shouldn't be either. */
+ WARN_ON_ONCE(ia_valid & ATTR_MTIME);
+ now = current_time(inode);
+ }
+
+ if (ia_valid & ATTR_ATIME_SET)
+ inode_set_atime_to_ts(inode, attr->ia_atime);
+ else if (ia_valid & ATTR_ATIME)
+ inode_set_atime_to_ts(inode, now);
+
+ if (ia_valid & ATTR_MTIME_SET)
+ inode_set_mtime_to_ts(inode, attr->ia_mtime);
+ else if (ia_valid & ATTR_MTIME)
+ inode_set_mtime_to_ts(inode, now);
+}
+
+/**
* setattr_copy - copy simple metadata updates into the generic inode
* @idmap: idmap of the mount the inode was found from
* @inode: the inode to be updated
@@ -303,12 +344,6 @@ void setattr_copy(struct mnt_idmap *idmap, struct inode *inode,
i_uid_update(idmap, attr, inode);
i_gid_update(idmap, attr, inode);
- if (ia_valid & ATTR_ATIME)
- inode_set_atime_to_ts(inode, attr->ia_atime);
- if (ia_valid & ATTR_MTIME)
- inode_set_mtime_to_ts(inode, attr->ia_mtime);
- if (ia_valid & ATTR_CTIME)
- inode_set_ctime_to_ts(inode, attr->ia_ctime);
if (ia_valid & ATTR_MODE) {
umode_t mode = attr->ia_mode;
if (!in_group_or_capable(idmap, inode,
@@ -316,6 +351,20 @@ void setattr_copy(struct mnt_idmap *idmap, struct inode *inode,
mode &= ~S_ISGID;
inode->i_mode = mode;
}
+
+ if (is_mgtime(inode))
+ return setattr_copy_mgtime(inode, attr);
+
+ if (ia_valid & ATTR_ATIME)
+ inode_set_atime_to_ts(inode, attr->ia_atime);
+ if (ia_valid & ATTR_MTIME)
+ inode_set_mtime_to_ts(inode, attr->ia_mtime);
+ if (ia_valid & ATTR_CTIME) {
+ if (ia_valid & ATTR_DELEG)
+ inode_set_ctime_deleg(inode, attr->ia_ctime);
+ else
+ inode_set_ctime_to_ts(inode, attr->ia_ctime);
+ }
}
EXPORT_SYMBOL(setattr_copy);
diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c
index 47455a85c909..654a58132a4d 100644
--- a/fs/bcachefs/backpointers.c
+++ b/fs/bcachefs/backpointers.c
@@ -52,6 +52,12 @@ int bch2_backpointer_validate(struct bch_fs *c, struct bkey_s_c k,
enum bch_validate_flags flags)
{
struct bkey_s_c_backpointer bp = bkey_s_c_to_backpointer(k);
+ int ret = 0;
+
+ bkey_fsck_err_on(bp.v->level > BTREE_MAX_DEPTH,
+ c, backpointer_level_bad,
+ "backpointer level bad: %u >= %u",
+ bp.v->level, BTREE_MAX_DEPTH);
rcu_read_lock();
struct bch_dev *ca = bch2_dev_rcu_noerror(c, bp.k->p.inode);
@@ -64,7 +70,6 @@ int bch2_backpointer_validate(struct bch_fs *c, struct bkey_s_c k,
struct bpos bucket = bp_pos_to_bucket(ca, bp.k->p);
struct bpos bp_pos = bucket_pos_to_bp_noerror(ca, bucket, bp.v->bucket_offset);
rcu_read_unlock();
- int ret = 0;
bkey_fsck_err_on((bp.v->bucket_offset >> MAX_EXTENT_COMPRESS_RATIO_SHIFT) >= ca->mi.bucket_size ||
!bpos_eq(bp.k->p, bp_pos),
@@ -947,9 +952,13 @@ int bch2_check_extents_to_backpointers(struct bch_fs *c)
static int check_one_backpointer(struct btree_trans *trans,
struct bbpos start,
struct bbpos end,
- struct bkey_s_c_backpointer bp,
+ struct bkey_s_c bp_k,
struct bkey_buf *last_flushed)
{
+ if (bp_k.k->type != KEY_TYPE_backpointer)
+ return 0;
+
+ struct bkey_s_c_backpointer bp = bkey_s_c_to_backpointer(bp_k);
struct bch_fs *c = trans->c;
struct btree_iter iter;
struct bbpos pos = bp_to_bbpos(*bp.v);
@@ -1004,9 +1013,7 @@ static int bch2_check_backpointers_to_extents_pass(struct btree_trans *trans,
POS_MIN, BTREE_ITER_prefetch, k,
NULL, NULL, BCH_TRANS_COMMIT_no_enospc, ({
progress_update_iter(trans, &progress, &iter, "backpointers_to_extents");
- check_one_backpointer(trans, start, end,
- bkey_s_c_to_backpointer(k),
- &last_flushed);
+ check_one_backpointer(trans, start, end, k, &last_flushed);
}));
bch2_bkey_buf_exit(&last_flushed, c);
diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c
index 0ca3feeb42c8..81dcf9e512c0 100644
--- a/fs/bcachefs/btree_gc.c
+++ b/fs/bcachefs/btree_gc.c
@@ -182,7 +182,7 @@ static int set_node_max(struct bch_fs *c, struct btree *b, struct bpos new_max)
bch2_btree_node_drop_keys_outside_node(b);
mutex_lock(&c->btree_cache.lock);
- bch2_btree_node_hash_remove(&c->btree_cache, b);
+ __bch2_btree_node_hash_remove(&c->btree_cache, b);
bkey_copy(&b->key, &new->k_i);
ret = __bch2_btree_node_hash_insert(&c->btree_cache, b);
diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index 6296a11ccb09..839d68802e42 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -733,11 +733,8 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca,
c, ca, b, i, NULL,
bset_past_end_of_btree_node,
"bset past end of btree node (offset %u len %u but written %zu)",
- offset, sectors, ptr_written ?: btree_sectors(c))) {
+ offset, sectors, ptr_written ?: btree_sectors(c)))
i->u64s = 0;
- ret = 0;
- goto out;
- }
btree_err_on(offset && !i->u64s,
-BCH_ERR_btree_node_read_err_fixable,
@@ -829,7 +826,6 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca,
BSET_BIG_ENDIAN(i), write,
&bn->format);
}
-out:
fsck_err:
printbuf_exit(&buf2);
printbuf_exit(&buf1);
diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c
index 22740b605f0a..d596ef93239f 100644
--- a/fs/bcachefs/btree_update_interior.c
+++ b/fs/bcachefs/btree_update_interior.c
@@ -2398,7 +2398,8 @@ static int __bch2_btree_node_update_key(struct btree_trans *trans,
if (new_hash) {
mutex_lock(&c->btree_cache.lock);
bch2_btree_node_hash_remove(&c->btree_cache, new_hash);
- bch2_btree_node_hash_remove(&c->btree_cache, b);
+
+ __bch2_btree_node_hash_remove(&c->btree_cache, b);
bkey_copy(&b->key, new_key);
ret = __bch2_btree_node_hash_insert(&c->btree_cache, b);
diff --git a/fs/bcachefs/btree_write_buffer.c b/fs/bcachefs/btree_write_buffer.c
index 3f56b584f8ec..1639c60dffa0 100644
--- a/fs/bcachefs/btree_write_buffer.c
+++ b/fs/bcachefs/btree_write_buffer.c
@@ -277,6 +277,10 @@ static int bch2_btree_write_buffer_flush_locked(struct btree_trans *trans)
bool accounting_replay_done = test_bit(BCH_FS_accounting_replay_done, &c->flags);
int ret = 0;
+ ret = bch2_journal_error(&c->journal);
+ if (ret)
+ return ret;
+
bch2_trans_unlock(trans);
bch2_trans_begin(trans);
@@ -491,7 +495,8 @@ static int fetch_wb_keys_from_journal(struct bch_fs *c, u64 seq)
return ret;
}
-static int btree_write_buffer_flush_seq(struct btree_trans *trans, u64 seq)
+static int btree_write_buffer_flush_seq(struct btree_trans *trans, u64 seq,
+ bool *did_work)
{
struct bch_fs *c = trans->c;
struct btree_write_buffer *wb = &c->btree_write_buffer;
@@ -502,6 +507,8 @@ static int btree_write_buffer_flush_seq(struct btree_trans *trans, u64 seq)
fetch_from_journal_err = fetch_wb_keys_from_journal(c, seq);
+ *did_work |= wb->inc.keys.nr || wb->flushing.keys.nr;
+
/*
* On memory allocation failure, bch2_btree_write_buffer_flush_locked()
* is not guaranteed to empty wb->inc:
@@ -521,17 +528,34 @@ static int bch2_btree_write_buffer_journal_flush(struct journal *j,
struct journal_entry_pin *_pin, u64 seq)
{
struct bch_fs *c = container_of(j, struct bch_fs, journal);
+ bool did_work = false;
- return bch2_trans_run(c, btree_write_buffer_flush_seq(trans, seq));
+ return bch2_trans_run(c, btree_write_buffer_flush_seq(trans, seq, &did_work));
}
int bch2_btree_write_buffer_flush_sync(struct btree_trans *trans)
{
struct bch_fs *c = trans->c;
+ bool did_work = false;
trace_and_count(c, write_buffer_flush_sync, trans, _RET_IP_);
- return btree_write_buffer_flush_seq(trans, journal_cur_seq(&c->journal));
+ return btree_write_buffer_flush_seq(trans, journal_cur_seq(&c->journal), &did_work);
+}
+
+/*
+ * The write buffer requires flushing when going RO: keys in the journal for the
+ * write buffer don't have a journal pin yet
+ */
+bool bch2_btree_write_buffer_flush_going_ro(struct bch_fs *c)
+{
+ if (bch2_journal_error(&c->journal))
+ return false;
+
+ bool did_work = false;
+ bch2_trans_run(c, btree_write_buffer_flush_seq(trans,
+ journal_cur_seq(&c->journal), &did_work));
+ return did_work;
}
int bch2_btree_write_buffer_flush_nocheck_rw(struct btree_trans *trans)
diff --git a/fs/bcachefs/btree_write_buffer.h b/fs/bcachefs/btree_write_buffer.h
index 725e79654216..d535cea28bde 100644
--- a/fs/bcachefs/btree_write_buffer.h
+++ b/fs/bcachefs/btree_write_buffer.h
@@ -21,6 +21,7 @@ static inline bool bch2_btree_write_buffer_must_wait(struct bch_fs *c)
struct btree_trans;
int bch2_btree_write_buffer_flush_sync(struct btree_trans *);
+bool bch2_btree_write_buffer_flush_going_ro(struct bch_fs *);
int bch2_btree_write_buffer_flush_nocheck_rw(struct btree_trans *);
int bch2_btree_write_buffer_tryflush(struct btree_trans *);
diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c
index c4e91d123849..37e3d69bec06 100644
--- a/fs/bcachefs/extents.c
+++ b/fs/bcachefs/extents.c
@@ -1364,7 +1364,7 @@ void bch2_ptr_swab(struct bkey_s k)
for (entry = ptrs.start;
entry < ptrs.end;
entry = extent_entry_next(entry)) {
- switch (extent_entry_type(entry)) {
+ switch (__extent_entry_type(entry)) {
case BCH_EXTENT_ENTRY_ptr:
break;
case BCH_EXTENT_ENTRY_crc32:
@@ -1384,6 +1384,9 @@ void bch2_ptr_swab(struct bkey_s k)
break;
case BCH_EXTENT_ENTRY_rebalance:
break;
+ default:
+ /* Bad entry type: will be caught by validate() */
+ return;
}
}
}
diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c
index ccaafa90f4f4..fb35dd336331 100644
--- a/fs/bcachefs/journal_io.c
+++ b/fs/bcachefs/journal_io.c
@@ -708,6 +708,9 @@ static void journal_entry_dev_usage_to_text(struct printbuf *out, struct bch_fs
container_of(entry, struct jset_entry_dev_usage, entry);
unsigned i, nr_types = jset_entry_dev_usage_nr_types(u);
+ if (vstruct_bytes(entry) < sizeof(*u))
+ return;
+
prt_printf(out, "dev=%u", le32_to_cpu(u->dev));
printbuf_indent_add(out, 2);
diff --git a/fs/bcachefs/recovery_passes.c b/fs/bcachefs/recovery_passes.c
index 4bbeac9e0526..dff589ddc984 100644
--- a/fs/bcachefs/recovery_passes.c
+++ b/fs/bcachefs/recovery_passes.c
@@ -27,6 +27,12 @@ const char * const bch2_recovery_passes[] = {
NULL
};
+/* Fake recovery pass, so that scan_for_btree_nodes isn't 0: */
+static int bch2_recovery_pass_empty(struct bch_fs *c)
+{
+ return 0;
+}
+
static int bch2_set_may_go_rw(struct bch_fs *c)
{
struct journal_keys *keys = &c->journal_keys;
diff --git a/fs/bcachefs/recovery_passes_types.h b/fs/bcachefs/recovery_passes_types.h
index 9d96c06e365c..94dc20ca2065 100644
--- a/fs/bcachefs/recovery_passes_types.h
+++ b/fs/bcachefs/recovery_passes_types.h
@@ -13,6 +13,7 @@
* must never change:
*/
#define BCH_RECOVERY_PASSES() \
+ x(recovery_pass_empty, 41, PASS_SILENT) \
x(scan_for_btree_nodes, 37, 0) \
x(check_topology, 4, 0) \
x(accounting_read, 39, PASS_ALWAYS) \
diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h
index 937275d061fe..9feb6739f77a 100644
--- a/fs/bcachefs/sb-errors_format.h
+++ b/fs/bcachefs/sb-errors_format.h
@@ -136,7 +136,9 @@ enum bch_fsck_flags {
x(bucket_gens_nonzero_for_invalid_buckets, 122, FSCK_AUTOFIX) \
x(need_discard_freespace_key_to_invalid_dev_bucket, 123, 0) \
x(need_discard_freespace_key_bad, 124, 0) \
+ x(discarding_bucket_not_in_need_discard_btree, 291, 0) \
x(backpointer_bucket_offset_wrong, 125, 0) \
+ x(backpointer_level_bad, 294, 0) \
x(backpointer_to_missing_device, 126, 0) \
x(backpointer_to_missing_alloc, 127, 0) \
x(backpointer_to_missing_ptr, 128, 0) \
@@ -177,7 +179,9 @@ enum bch_fsck_flags {
x(ptr_stripe_redundant, 163, 0) \
x(reservation_key_nr_replicas_invalid, 164, 0) \
x(reflink_v_refcount_wrong, 165, 0) \
+ x(reflink_v_pos_bad, 292, 0) \
x(reflink_p_to_missing_reflink_v, 166, 0) \
+ x(reflink_refcount_underflow, 293, 0) \
x(stripe_pos_bad, 167, 0) \
x(stripe_val_size_bad, 168, 0) \
x(stripe_csum_granularity_bad, 290, 0) \
@@ -302,7 +306,7 @@ enum bch_fsck_flags {
x(accounting_key_replicas_devs_unsorted, 280, FSCK_AUTOFIX) \
x(accounting_key_version_0, 282, FSCK_AUTOFIX) \
x(logged_op_but_clean, 283, FSCK_AUTOFIX) \
- x(MAX, 291, 0)
+ x(MAX, 295, 0)
enum bch_sb_error_id {
#define x(t, n, ...) BCH_FSCK_ERR_##t = n,
diff --git a/fs/bcachefs/sb-members.c b/fs/bcachefs/sb-members.c
index fb08dd680dac..116131f95815 100644
--- a/fs/bcachefs/sb-members.c
+++ b/fs/bcachefs/sb-members.c
@@ -163,7 +163,7 @@ static int validate_member(struct printbuf *err,
return -BCH_ERR_invalid_sb_members;
}
- if (m.btree_bitmap_shift >= 64) {
+ if (m.btree_bitmap_shift >= BCH_MI_BTREE_BITMAP_SHIFT_MAX) {
prt_printf(err, "device %u: invalid btree_bitmap_shift %u", i, m.btree_bitmap_shift);
return -BCH_ERR_invalid_sb_members;
}
@@ -450,7 +450,7 @@ static void __bch2_dev_btree_bitmap_mark(struct bch_sb_field_members_v2 *mi, uns
m->btree_bitmap_shift += resize;
}
- BUG_ON(m->btree_bitmap_shift > 57);
+ BUG_ON(m->btree_bitmap_shift >= BCH_MI_BTREE_BITMAP_SHIFT_MAX);
BUG_ON(end > 64ULL << m->btree_bitmap_shift);
for (unsigned bit = start >> m->btree_bitmap_shift;
diff --git a/fs/bcachefs/sb-members_format.h b/fs/bcachefs/sb-members_format.h
index d727d2dfda08..2adf1221a440 100644
--- a/fs/bcachefs/sb-members_format.h
+++ b/fs/bcachefs/sb-members_format.h
@@ -66,6 +66,12 @@ struct bch_member {
};
/*
+ * btree_allocated_bitmap can represent sector addresses of a u64: it itself has
+ * 64 elements, so 64 - ilog2(64)
+ */
+#define BCH_MI_BTREE_BITMAP_SHIFT_MAX 58
+
+/*
* This limit comes from the bucket_gens array - it's a single allocation, and
* kernel allocation are limited to INT_MAX
*/
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index 657fd3759e7b..a6ed9a0bf1c7 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -272,6 +272,7 @@ static void __bch2_fs_read_only(struct bch_fs *c)
clean_passes++;
if (bch2_btree_interior_updates_flush(c) ||
+ bch2_btree_write_buffer_flush_going_ro(c) ||
bch2_journal_flush_all_pins(&c->journal) ||
bch2_btree_flush_all_writes(c) ||
seq != atomic64_read(&c->journal.seq)) {
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index f92f108840f5..8f430ff8e445 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -11,12 +11,13 @@
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/fs.h>
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
#include <linux/errno.h>
#include <linux/stat.h>
#include <linux/nls.h>
#include <linux/buffer_head.h>
#include <linux/vfs.h>
-#include <linux/parser.h>
#include <linux/namei.h>
#include <linux/sched.h>
#include <linux/cred.h>
@@ -54,22 +55,20 @@ static int befs_utf2nls(struct super_block *sb, const char *in, int in_len,
static int befs_nls2utf(struct super_block *sb, const char *in, int in_len,
char **out, int *out_len);
static void befs_put_super(struct super_block *);
-static int befs_remount(struct super_block *, int *, char *);
static int befs_statfs(struct dentry *, struct kstatfs *);
static int befs_show_options(struct seq_file *, struct dentry *);
-static int parse_options(char *, struct befs_mount_options *);
static struct dentry *befs_fh_to_dentry(struct super_block *sb,
struct fid *fid, int fh_len, int fh_type);
static struct dentry *befs_fh_to_parent(struct super_block *sb,
struct fid *fid, int fh_len, int fh_type);
static struct dentry *befs_get_parent(struct dentry *child);
+static void befs_free_fc(struct fs_context *fc);
static const struct super_operations befs_sops = {
.alloc_inode = befs_alloc_inode, /* allocate a new inode */
.free_inode = befs_free_inode, /* deallocate an inode */
.put_super = befs_put_super, /* uninit super */
.statfs = befs_statfs, /* statfs */
- .remount_fs = befs_remount,
.show_options = befs_show_options,
};
@@ -672,92 +671,53 @@ static struct dentry *befs_get_parent(struct dentry *child)
}
enum {
- Opt_uid, Opt_gid, Opt_charset, Opt_debug, Opt_err,
+ Opt_uid, Opt_gid, Opt_charset, Opt_debug,
};
-static const match_table_t befs_tokens = {
- {Opt_uid, "uid=%d"},
- {Opt_gid, "gid=%d"},
- {Opt_charset, "iocharset=%s"},
- {Opt_debug, "debug"},
- {Opt_err, NULL}
+static const struct fs_parameter_spec befs_param_spec[] = {
+ fsparam_uid ("uid", Opt_uid),
+ fsparam_gid ("gid", Opt_gid),
+ fsparam_string ("iocharset", Opt_charset),
+ fsparam_flag ("debug", Opt_debug),
+ {}
};
static int
-parse_options(char *options, struct befs_mount_options *opts)
+befs_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
- char *p;
- substring_t args[MAX_OPT_ARGS];
- int option;
- kuid_t uid;
- kgid_t gid;
-
- /* Initialize options */
- opts->uid = GLOBAL_ROOT_UID;
- opts->gid = GLOBAL_ROOT_GID;
- opts->use_uid = 0;
- opts->use_gid = 0;
- opts->iocharset = NULL;
- opts->debug = 0;
-
- if (!options)
- return 1;
-
- while ((p = strsep(&options, ",")) != NULL) {
- int token;
-
- if (!*p)
- continue;
-
- token = match_token(p, befs_tokens, args);
- switch (token) {
- case Opt_uid:
- if (match_int(&args[0], &option))
- return 0;
- uid = INVALID_UID;
- if (option >= 0)
- uid = make_kuid(current_user_ns(), option);
- if (!uid_valid(uid)) {
- pr_err("Invalid uid %d, "
- "using default\n", option);
- break;
- }
- opts->uid = uid;
- opts->use_uid = 1;
- break;
- case Opt_gid:
- if (match_int(&args[0], &option))
- return 0;
- gid = INVALID_GID;
- if (option >= 0)
- gid = make_kgid(current_user_ns(), option);
- if (!gid_valid(gid)) {
- pr_err("Invalid gid %d, "
- "using default\n", option);
- break;
- }
- opts->gid = gid;
- opts->use_gid = 1;
- break;
- case Opt_charset:
- kfree(opts->iocharset);
- opts->iocharset = match_strdup(&args[0]);
- if (!opts->iocharset) {
- pr_err("allocation failure for "
- "iocharset string\n");
- return 0;
- }
- break;
- case Opt_debug:
- opts->debug = 1;
- break;
- default:
- pr_err("Unrecognized mount option \"%s\" "
- "or missing value\n", p);
- return 0;
- }
+ struct befs_mount_options *opts = fc->fs_private;
+ int token;
+ struct fs_parse_result result;
+
+ /* befs ignores all options on remount */
+ if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE)
+ return 0;
+
+ token = fs_parse(fc, befs_param_spec, param, &result);
+ if (token < 0)
+ return token;
+
+ switch (token) {
+ case Opt_uid:
+ opts->uid = result.uid;
+ opts->use_uid = 1;
+ break;
+ case Opt_gid:
+ opts->gid = result.gid;
+ opts->use_gid = 1;
+ break;
+ case Opt_charset:
+ kfree(opts->iocharset);
+ opts->iocharset = param->string;
+ param->string = NULL;
+ break;
+ case Opt_debug:
+ opts->debug = 1;
+ break;
+ default:
+ return -EINVAL;
}
- return 1;
+ return 0;
}
static int befs_show_options(struct seq_file *m, struct dentry *root)
@@ -793,6 +753,21 @@ befs_put_super(struct super_block *sb)
sb->s_fs_info = NULL;
}
+/*
+ * Copy the parsed options into the sbi mount_options member
+ */
+static void
+befs_set_options(struct befs_sb_info *sbi, struct befs_mount_options *opts)
+{
+ sbi->mount_opts.uid = opts->uid;
+ sbi->mount_opts.gid = opts->gid;
+ sbi->mount_opts.use_uid = opts->use_uid;
+ sbi->mount_opts.use_gid = opts->use_gid;
+ sbi->mount_opts.debug = opts->debug;
+ sbi->mount_opts.iocharset = opts->iocharset;
+ opts->iocharset = NULL;
+}
+
/* Allocate private field of the superblock, fill it.
*
* Finish filling the public superblock fields
@@ -800,7 +775,7 @@ befs_put_super(struct super_block *sb)
* Load a set of NLS translations if needed.
*/
static int
-befs_fill_super(struct super_block *sb, void *data, int silent)
+befs_fill_super(struct super_block *sb, struct fs_context *fc)
{
struct buffer_head *bh;
struct befs_sb_info *befs_sb;
@@ -810,6 +785,8 @@ befs_fill_super(struct super_block *sb, void *data, int silent)
const unsigned long sb_block = 0;
const off_t x86_sb_off = 512;
int blocksize;
+ struct befs_mount_options *parsed_opts = fc->fs_private;
+ int silent = fc->sb_flags & SB_SILENT;
sb->s_fs_info = kzalloc(sizeof(*befs_sb), GFP_KERNEL);
if (sb->s_fs_info == NULL)
@@ -817,11 +794,7 @@ befs_fill_super(struct super_block *sb, void *data, int silent)
befs_sb = BEFS_SB(sb);
- if (!parse_options((char *) data, &befs_sb->mount_opts)) {
- if (!silent)
- befs_error(sb, "cannot parse mount options");
- goto unacquire_priv_sbp;
- }
+ befs_set_options(befs_sb, parsed_opts);
befs_debug(sb, "---> %s", __func__);
@@ -934,10 +907,10 @@ unacquire_none:
}
static int
-befs_remount(struct super_block *sb, int *flags, char *data)
+befs_reconfigure(struct fs_context *fc)
{
- sync_filesystem(sb);
- if (!(*flags & SB_RDONLY))
+ sync_filesystem(fc->root->d_sb);
+ if (!(fc->sb_flags & SB_RDONLY))
return -EINVAL;
return 0;
}
@@ -965,19 +938,51 @@ befs_statfs(struct dentry *dentry, struct kstatfs *buf)
return 0;
}
-static struct dentry *
-befs_mount(struct file_system_type *fs_type, int flags, const char *dev_name,
- void *data)
+static int befs_get_tree(struct fs_context *fc)
+{
+ return get_tree_bdev(fc, befs_fill_super);
+}
+
+static const struct fs_context_operations befs_context_ops = {
+ .parse_param = befs_parse_param,
+ .get_tree = befs_get_tree,
+ .reconfigure = befs_reconfigure,
+ .free = befs_free_fc,
+};
+
+static int befs_init_fs_context(struct fs_context *fc)
+{
+ struct befs_mount_options *opts;
+
+ opts = kzalloc(sizeof(*opts), GFP_KERNEL);
+ if (!opts)
+ return -ENOMEM;
+
+ /* Initialize options */
+ opts->uid = GLOBAL_ROOT_UID;
+ opts->gid = GLOBAL_ROOT_GID;
+
+ fc->fs_private = opts;
+ fc->ops = &befs_context_ops;
+
+ return 0;
+}
+
+static void befs_free_fc(struct fs_context *fc)
{
- return mount_bdev(fs_type, flags, dev_name, data, befs_fill_super);
+ struct befs_mount_options *opts = fc->fs_private;
+
+ kfree(opts->iocharset);
+ kfree(fc->fs_private);
}
static struct file_system_type befs_fs_type = {
.owner = THIS_MODULE,
.name = "befs",
- .mount = befs_mount,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
+ .init_fs_context = befs_init_fs_context,
+ .parameters = befs_param_spec,
};
MODULE_ALIAS_FS("befs");
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 317a3712270f..307dedf95c70 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -744,16 +744,11 @@ const char *btrfs_super_csum_driver(u16 csum_type);
size_t __attribute_const__ btrfs_get_num_csums(void);
/*
- * We use page status Private2 to indicate there is an ordered extent with
+ * We use folio flag owner_2 to indicate there is an ordered extent with
* unfinished IO.
- *
- * Rename the Private2 accessors to Ordered, to improve readability.
*/
-#define PageOrdered(page) PagePrivate2(page)
-#define SetPageOrdered(page) SetPagePrivate2(page)
-#define ClearPageOrdered(page) ClearPagePrivate2(page)
-#define folio_test_ordered(folio) folio_test_private_2(folio)
-#define folio_set_ordered(folio) folio_set_private_2(folio)
-#define folio_clear_ordered(folio) folio_clear_private_2(folio)
+#define folio_test_ordered(folio) folio_test_owner_2(folio)
+#define folio_set_ordered(folio) folio_set_owner_2(folio)
+#define folio_clear_ordered(folio) folio_clear_owner_2(folio)
#endif
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 4d2ad5b66928..0d878dbbabba 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -299,7 +299,7 @@ static int comp_refs(struct btrfs_delayed_ref_node *ref1,
if (ref1->ref_root < ref2->ref_root)
return -1;
if (ref1->ref_root > ref2->ref_root)
- return -1;
+ return 1;
if (ref1->type == BTRFS_EXTENT_DATA_REF_KEY)
ret = comp_data_refs(ref1, ref2);
}
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index e629d2ee152a..b923d0cec61c 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -786,7 +786,7 @@ static void submit_extent_folio(struct btrfs_bio_ctrl *bio_ctrl,
}
if (bio_ctrl->wbc)
- wbc_account_cgroup_owner(bio_ctrl->wbc, &folio->page,
+ wbc_account_cgroup_owner(bio_ctrl->wbc, folio,
len);
size -= len;
@@ -1752,7 +1752,7 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb,
ret = bio_add_folio(&bbio->bio, folio, eb->len,
eb->start - folio_pos(folio));
ASSERT(ret);
- wbc_account_cgroup_owner(wbc, folio_page(folio, 0), eb->len);
+ wbc_account_cgroup_owner(wbc, folio, eb->len);
folio_unlock(folio);
} else {
int num_folios = num_extent_folios(eb);
@@ -1766,8 +1766,7 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb,
folio_start_writeback(folio);
ret = bio_add_folio(&bbio->bio, folio, eb->folio_size, 0);
ASSERT(ret);
- wbc_account_cgroup_owner(wbc, folio_page(folio, 0),
- eb->folio_size);
+ wbc_account_cgroup_owner(wbc, folio, eb->folio_size);
wbc->nr_to_write -= folio_nr_pages(folio);
folio_unlock(folio);
}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index fbb753300071..588c353d2969 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1067,26 +1067,6 @@ void btrfs_check_nocow_unlock(struct btrfs_inode *inode)
btrfs_drew_write_unlock(&inode->root->snapshot_lock);
}
-static void update_time_for_write(struct inode *inode)
-{
- struct timespec64 now, ts;
-
- if (IS_NOCMTIME(inode))
- return;
-
- now = current_time(inode);
- ts = inode_get_mtime(inode);
- if (!timespec64_equal(&ts, &now))
- inode_set_mtime_to_ts(inode, now);
-
- ts = inode_get_ctime(inode);
- if (!timespec64_equal(&ts, &now))
- inode_set_ctime_to_ts(inode, now);
-
- if (IS_I_VERSION(inode))
- inode_inc_iversion(inode);
-}
-
int btrfs_write_check(struct kiocb *iocb, size_t count)
{
struct file *file = iocb->ki_filp;
@@ -1117,7 +1097,10 @@ int btrfs_write_check(struct kiocb *iocb, size_t count)
* need to start yet another transaction to update the inode as we will
* update the inode when we finish writing whatever data we write.
*/
- update_time_for_write(inode);
+ if (!IS_NOCMTIME(inode)) {
+ inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
+ inode_inc_iversion(inode);
+ }
start_pos = round_down(pos, fs_info->sectorsize);
oldsize = i_size_read(inode);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 22b8e2764619..03fe0de2cd0d 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1481,7 +1481,7 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
* (which the caller expects to stay locked), don't clear any
* dirty bits and don't set any writeback bits
*
- * Do set the Ordered (Private2) bit so we know this page was
+ * Do set the Ordered flag so we know this page was
* properly setup for writepage.
*/
page_ops = (keep_locked ? 0 : PAGE_UNLOCK);
@@ -1698,7 +1698,7 @@ static bool run_delalloc_compressed(struct btrfs_inode *inode,
* need full accuracy. Just account the whole thing
* against the first page.
*/
- wbc_account_cgroup_owner(wbc, &locked_folio->page,
+ wbc_account_cgroup_owner(wbc, locked_folio,
cur_end - start);
async_chunk[i].locked_folio = locked_folio;
locked_folio = NULL;
@@ -7274,7 +7274,7 @@ static void btrfs_invalidate_folio(struct folio *folio, size_t offset,
*
* But already submitted bio can still be finished on this folio.
* Furthermore, endio function won't skip folio which has Ordered
- * (Private2) already cleared, so it's possible for endio and
+ * already cleared, so it's possible for endio and
* invalidate_folio to do the same ordered extent accounting twice
* on one folio.
*
@@ -7340,7 +7340,7 @@ static void btrfs_invalidate_folio(struct folio *folio, size_t offset,
range_len = range_end + 1 - cur;
if (!btrfs_folio_test_ordered(fs_info, folio, cur, range_len)) {
/*
- * If Ordered (Private2) is cleared, it means endio has
+ * If Ordered is cleared, it means endio has
* already been executed for the range.
* We can't delete the extent states as
* btrfs_finish_ordered_io() may still use some of them.
@@ -7413,7 +7413,7 @@ next:
}
/*
* We have iterated through all ordered extents of the page, the page
- * should not have Ordered (Private2) anymore, or the above iteration
+ * should not have Ordered anymore, or the above iteration
* did something wrong.
*/
ASSERT(!folio_test_ordered(folio));
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 1fdeb216bf6c..c9302d193187 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1306,9 +1306,9 @@ static noinline int __btrfs_ioctl_snap_create(struct file *file,
ret = btrfs_mksubvol(&file->f_path, idmap, name,
namelen, NULL, readonly, inherit);
} else {
- struct fd src = fdget(fd);
+ CLASS(fd, src)(fd);
struct inode *src_inode;
- if (!fd_file(src)) {
+ if (fd_empty(src)) {
ret = -EINVAL;
goto out_drop_write;
}
@@ -1339,7 +1339,6 @@ static noinline int __btrfs_ioctl_snap_create(struct file *file,
BTRFS_I(src_inode)->root,
readonly, inherit);
}
- fdput(src);
}
out_drop_write:
mnt_drop_write_file(file);
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 2104d60c2161..95c8499a159a 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -346,10 +346,10 @@ static bool can_finish_ordered_extent(struct btrfs_ordered_extent *ordered,
ASSERT(file_offset + len <= folio_pos(folio) + folio_size(folio));
/*
- * Ordered (Private2) bit indicates whether we still have
+ * Ordered flag indicates whether we still have
* pending io unfinished for the ordered extent.
*
- * If there's no such bit, we need to skip to next range.
+ * If it's not set, we need to skip to next range.
*/
if (!btrfs_folio_test_ordered(fs_info, folio, file_offset, len))
return false;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 3381389ab93a..97a85d180b61 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -2189,7 +2189,8 @@ static struct file_system_type btrfs_fs_type = {
.init_fs_context = btrfs_init_fs_context,
.parameters = btrfs_fs_parameters,
.kill_sb = btrfs_kill_super,
- .fs_flags = FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA | FS_ALLOW_IDMAP,
+ .fs_flags = FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA |
+ FS_ALLOW_IDMAP | FS_MGTIME,
};
MODULE_ALIAS_FS("btrfs");
diff --git a/fs/buffer.c b/fs/buffer.c
index 1fc9a50def0b..bb4a31b9559d 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1649,6 +1649,7 @@ void block_invalidate_folio(struct folio *folio, size_t offset, size_t length)
if (length == folio_size(folio))
filemap_release_folio(folio, 0);
out:
+ folio_clear_mappedtodisk(folio);
return;
}
EXPORT_SYMBOL(block_invalidate_folio);
@@ -2803,7 +2804,7 @@ static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
bio->bi_write_hint = write_hint;
- __bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
+ bio_add_folio_nofail(bio, bh->b_folio, bh->b_size, bh_offset(bh));
bio->bi_end_io = end_bio_bh_io_sync;
bio->bi_private = bh;
@@ -2813,7 +2814,7 @@ static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
if (wbc) {
wbc_init_bio(wbc, bio);
- wbc_account_cgroup_owner(wbc, bh->b_page, bh->b_size);
+ wbc_account_cgroup_owner(wbc, bh->b_folio, bh->b_size);
}
submit_bio(bio);
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index 35ba2117a6f6..3e63cfe15874 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -327,6 +327,8 @@ static void cachefiles_commit_object(struct cachefiles_object *object,
static void cachefiles_clean_up_object(struct cachefiles_object *object,
struct cachefiles_cache *cache)
{
+ struct file *file;
+
if (test_bit(FSCACHE_COOKIE_RETIRED, &object->cookie->flags)) {
if (!test_bit(CACHEFILES_OBJECT_USING_TMPFILE, &object->flags)) {
cachefiles_see_object(object, cachefiles_obj_see_clean_delete);
@@ -342,10 +344,14 @@ static void cachefiles_clean_up_object(struct cachefiles_object *object,
}
cachefiles_unmark_inode_in_use(object, object->file);
- if (object->file) {
- fput(object->file);
- object->file = NULL;
- }
+
+ spin_lock(&object->lock);
+ file = object->file;
+ object->file = NULL;
+ spin_unlock(&object->lock);
+
+ if (file)
+ fput(file);
}
/*
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index 2b3f9935dbb4..7cf59713f0f7 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -691,11 +691,6 @@ bool cachefiles_commit_tmpfile(struct cachefiles_cache *cache,
}
if (!d_is_negative(dentry)) {
- if (d_backing_inode(dentry) == file_inode(object->file)) {
- success = true;
- goto out_dput;
- }
-
ret = cachefiles_unlink(volume->cache, object, fan, dentry,
FSCACHE_OBJECT_IS_STALE);
if (ret < 0)
diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c
index 470c96658385..fe3de9ad57bf 100644
--- a/fs/cachefiles/ondemand.c
+++ b/fs/cachefiles/ondemand.c
@@ -60,26 +60,36 @@ static ssize_t cachefiles_ondemand_fd_write_iter(struct kiocb *kiocb,
{
struct cachefiles_object *object = kiocb->ki_filp->private_data;
struct cachefiles_cache *cache = object->volume->cache;
- struct file *file = object->file;
- size_t len = iter->count;
+ struct file *file;
+ size_t len = iter->count, aligned_len = len;
loff_t pos = kiocb->ki_pos;
const struct cred *saved_cred;
int ret;
- if (!file)
+ spin_lock(&object->lock);
+ file = object->file;
+ if (!file) {
+ spin_unlock(&object->lock);
return -ENOBUFS;
+ }
+ get_file(file);
+ spin_unlock(&object->lock);
cachefiles_begin_secure(cache, &saved_cred);
- ret = __cachefiles_prepare_write(object, file, &pos, &len, len, true);
+ ret = __cachefiles_prepare_write(object, file, &pos, &aligned_len, len, true);
cachefiles_end_secure(cache, saved_cred);
if (ret < 0)
- return ret;
+ goto out;
trace_cachefiles_ondemand_fd_write(object, file_inode(file), pos, len);
ret = __cachefiles_write(object, file, pos, iter, NULL, NULL);
- if (!ret)
+ if (!ret) {
ret = len;
+ kiocb->ki_pos += ret;
+ }
+out:
+ fput(file);
return ret;
}
@@ -87,12 +97,22 @@ static loff_t cachefiles_ondemand_fd_llseek(struct file *filp, loff_t pos,
int whence)
{
struct cachefiles_object *object = filp->private_data;
- struct file *file = object->file;
+ struct file *file;
+ loff_t ret;
- if (!file)
+ spin_lock(&object->lock);
+ file = object->file;
+ if (!file) {
+ spin_unlock(&object->lock);
return -ENOBUFS;
+ }
+ get_file(file);
+ spin_unlock(&object->lock);
- return vfs_llseek(file, pos, whence);
+ ret = vfs_llseek(file, pos, whence);
+ fput(file);
+
+ return ret;
}
static long cachefiles_ondemand_fd_ioctl(struct file *filp, unsigned int ioctl,
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index c2a9e2cc03de..4c82348fe1e6 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1054,7 +1054,9 @@ get_more_pages:
if (!nr_folios && !locked_pages)
break;
for (i = 0; i < nr_folios && locked_pages < max_pages; i++) {
- page = &fbatch.folios[i]->page;
+ struct folio *folio = fbatch.folios[i];
+
+ page = &folio->page;
doutc(cl, "? %p idx %lu\n", page, page->index);
if (locked_pages == 0)
lock_page(page); /* first page */
@@ -1081,8 +1083,6 @@ get_more_pages:
continue;
}
if (page_offset(page) >= ceph_wbc.i_size) {
- struct folio *folio = page_folio(page);
-
doutc(cl, "folio at %lu beyond eof %llu\n",
folio->index, ceph_wbc.i_size);
if ((ceph_wbc.size_stable ||
@@ -1098,16 +1098,16 @@ get_more_pages:
unlock_page(page);
break;
}
- if (PageWriteback(page) ||
- PagePrivate2(page) /* [DEPRECATED] */) {
+ if (folio_test_writeback(folio) ||
+ folio_test_private_2(folio) /* [DEPRECATED] */) {
if (wbc->sync_mode == WB_SYNC_NONE) {
- doutc(cl, "%p under writeback\n", page);
- unlock_page(page);
+ doutc(cl, "%p under writeback\n", folio);
+ folio_unlock(folio);
continue;
}
- doutc(cl, "waiting on writeback %p\n", page);
- wait_on_page_writeback(page);
- folio_wait_private_2(page_folio(page)); /* [DEPRECATED] */
+ doutc(cl, "waiting on writeback %p\n", folio);
+ folio_wait_writeback(folio);
+ folio_wait_private_2(folio); /* [DEPRECATED] */
}
if (!clear_page_dirty_for_io(page)) {
diff --git a/fs/char_dev.c b/fs/char_dev.c
index 57cc096c498a..c2ddb998f3c9 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -562,8 +562,8 @@ int cdev_device_add(struct cdev *cdev, struct device *dev)
/**
* cdev_device_del() - inverse of cdev_device_add
- * @dev: the device structure
* @cdev: the cdev structure
+ * @dev: the device structure
*
* cdev_device_del() is a helper function to call cdev_del and device_del.
* It should be used whenever cdev_device_add is used.
diff --git a/fs/coredump.c b/fs/coredump.c
index 45737b43dda5..d48edb37bc35 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -951,6 +951,7 @@ int dump_user_range(struct coredump_params *cprm, unsigned long start,
} else {
dump_skip(cprm, PAGE_SIZE);
}
+ cond_resched();
}
dump_page_free(dump_page);
return 1;
diff --git a/fs/dcache.c b/fs/dcache.c
index 0f6b16ba30d0..0099077a2982 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -135,6 +135,7 @@ struct dentry_stat_t {
static DEFINE_PER_CPU(long, nr_dentry);
static DEFINE_PER_CPU(long, nr_dentry_unused);
static DEFINE_PER_CPU(long, nr_dentry_negative);
+static int dentry_negative_policy;
#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
/* Statistics gathering. */
@@ -199,6 +200,15 @@ static struct ctl_table fs_dcache_sysctls[] = {
.mode = 0444,
.proc_handler = proc_nr_dentry,
},
+ {
+ .procname = "dentry-negative",
+ .data = &dentry_negative_policy,
+ .maxlen = sizeof(dentry_negative_policy),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
+ },
};
static int __init init_fs_dcache_sysctls(void)
@@ -2039,8 +2049,8 @@ EXPORT_SYMBOL(d_obtain_root);
/**
* d_add_ci - lookup or allocate new dentry with case-exact name
- * @inode: the inode case-insensitive lookup has found
* @dentry: the negative dentry that was passed to the parent's lookup func
+ * @inode: the inode case-insensitive lookup has found
* @name: the case-exact name to be associated with the returned dentry
*
* This is to avoid filling the dcache with case-insensitive names to the
@@ -2093,8 +2103,8 @@ EXPORT_SYMBOL(d_add_ci);
/**
* d_same_name - compare dentry name with case-exact name
- * @parent: parent dentry
* @dentry: the negative dentry that was passed to the parent's lookup func
+ * @parent: parent dentry
* @name: the case-exact name to be associated with the returned dentry
*
* Return: true if names are same, or false
@@ -2401,6 +2411,8 @@ void d_delete(struct dentry * dentry)
* Are we the only user?
*/
if (dentry->d_lockref.count == 1) {
+ if (dentry_negative_policy)
+ __d_drop(dentry);
dentry->d_flags &= ~DCACHE_CANT_MOUNT;
dentry_unlink_inode(dentry);
} else {
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 827278525fd9..69536cacdea8 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -328,10 +328,10 @@ out:
* Convert an eCryptfs page index into a lower byte offset
*/
static loff_t lower_offset_for_page(struct ecryptfs_crypt_stat *crypt_stat,
- struct page *page)
+ struct folio *folio)
{
return ecryptfs_lower_header_size(crypt_stat) +
- ((loff_t)page->index << PAGE_SHIFT);
+ (loff_t)folio->index * PAGE_SIZE;
}
/**
@@ -340,6 +340,7 @@ static loff_t lower_offset_for_page(struct ecryptfs_crypt_stat *crypt_stat,
* encryption operation
* @dst_page: The page to write the result into
* @src_page: The page to read from
+ * @page_index: The offset in the file (in units of PAGE_SIZE)
* @extent_offset: Page extent offset for use in generating IV
* @op: ENCRYPT or DECRYPT to indicate the desired operation
*
@@ -350,9 +351,9 @@ static loff_t lower_offset_for_page(struct ecryptfs_crypt_stat *crypt_stat,
static int crypt_extent(struct ecryptfs_crypt_stat *crypt_stat,
struct page *dst_page,
struct page *src_page,
+ pgoff_t page_index,
unsigned long extent_offset, int op)
{
- pgoff_t page_index = op == ENCRYPT ? src_page->index : dst_page->index;
loff_t extent_base;
char extent_iv[ECRYPTFS_MAX_IV_BYTES];
struct scatterlist src_sg, dst_sg;
@@ -392,7 +393,7 @@ out:
/**
* ecryptfs_encrypt_page
- * @page: Page mapped from the eCryptfs inode for the file; contains
+ * @folio: Folio mapped from the eCryptfs inode for the file; contains
* decrypted content that needs to be encrypted (to a temporary
* page; not in place) and written out to the lower file
*
@@ -406,7 +407,7 @@ out:
*
* Returns zero on success; negative on error
*/
-int ecryptfs_encrypt_page(struct page *page)
+int ecryptfs_encrypt_page(struct folio *folio)
{
struct inode *ecryptfs_inode;
struct ecryptfs_crypt_stat *crypt_stat;
@@ -416,7 +417,7 @@ int ecryptfs_encrypt_page(struct page *page)
loff_t lower_offset;
int rc = 0;
- ecryptfs_inode = page->mapping->host;
+ ecryptfs_inode = folio->mapping->host;
crypt_stat =
&(ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat);
BUG_ON(!(crypt_stat->flags & ECRYPTFS_ENCRYPTED));
@@ -431,8 +432,9 @@ int ecryptfs_encrypt_page(struct page *page)
for (extent_offset = 0;
extent_offset < (PAGE_SIZE / crypt_stat->extent_size);
extent_offset++) {
- rc = crypt_extent(crypt_stat, enc_extent_page, page,
- extent_offset, ENCRYPT);
+ rc = crypt_extent(crypt_stat, enc_extent_page,
+ folio_page(folio, 0), folio->index,
+ extent_offset, ENCRYPT);
if (rc) {
printk(KERN_ERR "%s: Error encrypting extent; "
"rc = [%d]\n", __func__, rc);
@@ -440,7 +442,7 @@ int ecryptfs_encrypt_page(struct page *page)
}
}
- lower_offset = lower_offset_for_page(crypt_stat, page);
+ lower_offset = lower_offset_for_page(crypt_stat, folio);
enc_extent_virt = kmap_local_page(enc_extent_page);
rc = ecryptfs_write_lower(ecryptfs_inode, enc_extent_virt, lower_offset,
PAGE_SIZE);
@@ -461,7 +463,7 @@ out:
/**
* ecryptfs_decrypt_page
- * @page: Page mapped from the eCryptfs inode for the file; data read
+ * @folio: Folio mapped from the eCryptfs inode for the file; data read
* and decrypted from the lower file will be written into this
* page
*
@@ -475,7 +477,7 @@ out:
*
* Returns zero on success; negative on error
*/
-int ecryptfs_decrypt_page(struct page *page)
+int ecryptfs_decrypt_page(struct folio *folio)
{
struct inode *ecryptfs_inode;
struct ecryptfs_crypt_stat *crypt_stat;
@@ -484,13 +486,13 @@ int ecryptfs_decrypt_page(struct page *page)
loff_t lower_offset;
int rc = 0;
- ecryptfs_inode = page->mapping->host;
+ ecryptfs_inode = folio->mapping->host;
crypt_stat =
&(ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat);
BUG_ON(!(crypt_stat->flags & ECRYPTFS_ENCRYPTED));
- lower_offset = lower_offset_for_page(crypt_stat, page);
- page_virt = kmap_local_page(page);
+ lower_offset = lower_offset_for_page(crypt_stat, folio);
+ page_virt = kmap_local_folio(folio, 0);
rc = ecryptfs_read_lower(page_virt, lower_offset, PAGE_SIZE,
ecryptfs_inode);
kunmap_local(page_virt);
@@ -504,8 +506,9 @@ int ecryptfs_decrypt_page(struct page *page)
for (extent_offset = 0;
extent_offset < (PAGE_SIZE / crypt_stat->extent_size);
extent_offset++) {
- rc = crypt_extent(crypt_stat, page, page,
- extent_offset, DECRYPT);
+ struct page *page = folio_page(folio, 0);
+ rc = crypt_extent(crypt_stat, page, page, folio->index,
+ extent_offset, DECRYPT);
if (rc) {
printk(KERN_ERR "%s: Error decrypting extent; "
"rc = [%d]\n", __func__, rc);
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index c586c5db18b5..1f562e75d0e4 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -569,8 +569,8 @@ void ecryptfs_destroy_mount_crypt_stat(
struct ecryptfs_mount_crypt_stat *mount_crypt_stat);
int ecryptfs_init_crypt_ctx(struct ecryptfs_crypt_stat *crypt_stat);
int ecryptfs_write_inode_size_to_metadata(struct inode *ecryptfs_inode);
-int ecryptfs_encrypt_page(struct page *page);
-int ecryptfs_decrypt_page(struct page *page);
+int ecryptfs_encrypt_page(struct folio *folio);
+int ecryptfs_decrypt_page(struct folio *folio);
int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry,
struct inode *ecryptfs_inode);
int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry);
@@ -653,16 +653,15 @@ int ecryptfs_keyring_auth_tok_for_sig(struct key **auth_tok_key,
int ecryptfs_write_lower(struct inode *ecryptfs_inode, char *data,
loff_t offset, size_t size);
int ecryptfs_write_lower_page_segment(struct inode *ecryptfs_inode,
- struct page *page_for_lower,
+ struct folio *folio_for_lower,
size_t offset_in_page, size_t size);
int ecryptfs_write(struct inode *inode, char *data, loff_t offset, size_t size);
int ecryptfs_read_lower(char *data, loff_t offset, size_t size,
struct inode *ecryptfs_inode);
-int ecryptfs_read_lower_page_segment(struct page *page_for_ecryptfs,
+int ecryptfs_read_lower_page_segment(struct folio *folio_for_ecryptfs,
pgoff_t page_index,
size_t offset_in_page, size_t size,
struct inode *ecryptfs_inode);
-struct page *ecryptfs_get_locked_page(struct inode *inode, loff_t index);
int ecryptfs_parse_packet_length(unsigned char *data, size_t *size,
size_t *length_size);
int ecryptfs_write_packet_length(char *dest, size_t size,
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index cbdf82f0183f..a9819ddb1ab8 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -1008,14 +1008,6 @@ static int ecryptfs_getattr_link(struct mnt_idmap *idmap,
return rc;
}
-static int ecryptfs_do_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int flags)
-{
- if (flags & AT_GETATTR_NOSEC)
- return vfs_getattr_nosec(path, stat, request_mask, flags);
- return vfs_getattr(path, stat, request_mask, flags);
-}
-
static int ecryptfs_getattr(struct mnt_idmap *idmap,
const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int flags)
@@ -1024,8 +1016,8 @@ static int ecryptfs_getattr(struct mnt_idmap *idmap,
struct kstat lower_stat;
int rc;
- rc = ecryptfs_do_getattr(ecryptfs_dentry_to_lower_path(dentry),
- &lower_stat, request_mask, flags);
+ rc = vfs_getattr_nosec(ecryptfs_dentry_to_lower_path(dentry),
+ &lower_stat, request_mask, flags);
if (!rc) {
fsstack_copy_attr_all(d_inode(dentry),
ecryptfs_inode_to_lower(d_inode(dentry)));
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index ceda5555971a..60f0ac8744b5 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -23,47 +23,29 @@
#include "ecryptfs_kernel.h"
/*
- * ecryptfs_get_locked_page
- *
- * Get one page from cache or lower f/s, return error otherwise.
- *
- * Returns locked and up-to-date page (if ok), with increased
- * refcnt.
- */
-struct page *ecryptfs_get_locked_page(struct inode *inode, loff_t index)
-{
- struct page *page = read_mapping_page(inode->i_mapping, index, NULL);
- if (!IS_ERR(page))
- lock_page(page);
- return page;
-}
-
-/**
- * ecryptfs_writepage
- * @page: Page that is locked before this call is made
- * @wbc: Write-back control structure
- *
- * Returns zero on success; non-zero otherwise
- *
* This is where we encrypt the data and pass the encrypted data to
* the lower filesystem. In OpenPGP-compatible mode, we operate on
* entire underlying packets.
*/
-static int ecryptfs_writepage(struct page *page, struct writeback_control *wbc)
+static int ecryptfs_writepages(struct address_space *mapping,
+ struct writeback_control *wbc)
{
- int rc;
-
- rc = ecryptfs_encrypt_page(page);
- if (rc) {
- ecryptfs_printk(KERN_WARNING, "Error encrypting "
- "page (upper index [0x%.16lx])\n", page->index);
- ClearPageUptodate(page);
- goto out;
+ struct folio *folio = NULL;
+ int error;
+
+ while ((folio = writeback_iter(mapping, wbc, folio, &error))) {
+ error = ecryptfs_encrypt_page(folio);
+ if (error) {
+ ecryptfs_printk(KERN_WARNING,
+ "Error encrypting folio (index [0x%.16lx])\n",
+ folio->index);
+ folio_clear_uptodate(folio);
+ mapping_set_error(mapping, error);
+ }
+ folio_unlock(folio);
}
- SetPageUptodate(page);
-out:
- unlock_page(page);
- return rc;
+
+ return error;
}
static void strip_xattr_flag(char *page_virt,
@@ -97,7 +79,7 @@ static void strip_xattr_flag(char *page_virt,
/**
* ecryptfs_copy_up_encrypted_with_header
- * @page: Sort of a ``virtual'' representation of the encrypted lower
+ * @folio: Sort of a ``virtual'' representation of the encrypted lower
* file. The actual lower file does not have the metadata in
* the header. This is locked.
* @crypt_stat: The eCryptfs inode's cryptographic context
@@ -106,7 +88,7 @@ static void strip_xattr_flag(char *page_virt,
* seeing, with the header information inserted.
*/
static int
-ecryptfs_copy_up_encrypted_with_header(struct page *page,
+ecryptfs_copy_up_encrypted_with_header(struct folio *folio,
struct ecryptfs_crypt_stat *crypt_stat)
{
loff_t extent_num_in_page = 0;
@@ -115,9 +97,9 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page,
int rc = 0;
while (extent_num_in_page < num_extents_per_page) {
- loff_t view_extent_num = ((((loff_t)page->index)
+ loff_t view_extent_num = ((loff_t)folio->index
* num_extents_per_page)
- + extent_num_in_page);
+ + extent_num_in_page;
size_t num_header_extents_at_front =
(crypt_stat->metadata_size / crypt_stat->extent_size);
@@ -125,21 +107,21 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page,
/* This is a header extent */
char *page_virt;
- page_virt = kmap_local_page(page);
+ page_virt = kmap_local_folio(folio, 0);
memset(page_virt, 0, PAGE_SIZE);
/* TODO: Support more than one header extent */
if (view_extent_num == 0) {
size_t written;
rc = ecryptfs_read_xattr_region(
- page_virt, page->mapping->host);
+ page_virt, folio->mapping->host);
strip_xattr_flag(page_virt + 16, crypt_stat);
ecryptfs_write_header_metadata(page_virt + 20,
crypt_stat,
&written);
}
kunmap_local(page_virt);
- flush_dcache_page(page);
+ flush_dcache_folio(folio);
if (rc) {
printk(KERN_ERR "%s: Error reading xattr "
"region; rc = [%d]\n", __func__, rc);
@@ -152,9 +134,9 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page,
- crypt_stat->metadata_size);
rc = ecryptfs_read_lower_page_segment(
- page, (lower_offset >> PAGE_SHIFT),
+ folio, (lower_offset >> PAGE_SHIFT),
(lower_offset & ~PAGE_MASK),
- crypt_stat->extent_size, page->mapping->host);
+ crypt_stat->extent_size, folio->mapping->host);
if (rc) {
printk(KERN_ERR "%s: Error attempting to read "
"extent at offset [%lld] in the lower "
@@ -180,55 +162,50 @@ out:
*/
static int ecryptfs_read_folio(struct file *file, struct folio *folio)
{
- struct page *page = &folio->page;
+ struct inode *inode = folio->mapping->host;
struct ecryptfs_crypt_stat *crypt_stat =
- &ecryptfs_inode_to_private(page->mapping->host)->crypt_stat;
- int rc = 0;
+ &ecryptfs_inode_to_private(inode)->crypt_stat;
+ int err = 0;
if (!crypt_stat || !(crypt_stat->flags & ECRYPTFS_ENCRYPTED)) {
- rc = ecryptfs_read_lower_page_segment(page, page->index, 0,
- PAGE_SIZE,
- page->mapping->host);
+ err = ecryptfs_read_lower_page_segment(folio, folio->index, 0,
+ folio_size(folio), inode);
} else if (crypt_stat->flags & ECRYPTFS_VIEW_AS_ENCRYPTED) {
if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR) {
- rc = ecryptfs_copy_up_encrypted_with_header(page,
- crypt_stat);
- if (rc) {
+ err = ecryptfs_copy_up_encrypted_with_header(folio,
+ crypt_stat);
+ if (err) {
printk(KERN_ERR "%s: Error attempting to copy "
"the encrypted content from the lower "
"file whilst inserting the metadata "
- "from the xattr into the header; rc = "
- "[%d]\n", __func__, rc);
+ "from the xattr into the header; err = "
+ "[%d]\n", __func__, err);
goto out;
}
} else {
- rc = ecryptfs_read_lower_page_segment(
- page, page->index, 0, PAGE_SIZE,
- page->mapping->host);
- if (rc) {
- printk(KERN_ERR "Error reading page; rc = "
- "[%d]\n", rc);
+ err = ecryptfs_read_lower_page_segment(folio,
+ folio->index, 0, folio_size(folio),
+ inode);
+ if (err) {
+ printk(KERN_ERR "Error reading page; err = "
+ "[%d]\n", err);
goto out;
}
}
} else {
- rc = ecryptfs_decrypt_page(page);
- if (rc) {
+ err = ecryptfs_decrypt_page(folio);
+ if (err) {
ecryptfs_printk(KERN_ERR, "Error decrypting page; "
- "rc = [%d]\n", rc);
+ "err = [%d]\n", err);
goto out;
}
}
out:
- if (rc)
- ClearPageUptodate(page);
- else
- SetPageUptodate(page);
- ecryptfs_printk(KERN_DEBUG, "Unlocking page with index = [0x%.16lx]\n",
- page->index);
- unlock_page(page);
- return rc;
+ ecryptfs_printk(KERN_DEBUG, "Unlocking folio with index = [0x%.16lx]\n",
+ folio->index);
+ folio_end_read(folio, err == 0);
+ return err;
}
/*
@@ -285,7 +262,7 @@ static int ecryptfs_write_begin(struct file *file,
if (!(crypt_stat->flags & ECRYPTFS_ENCRYPTED)) {
rc = ecryptfs_read_lower_page_segment(
- &folio->page, index, 0, PAGE_SIZE, mapping->host);
+ folio, index, 0, PAGE_SIZE, mapping->host);
if (rc) {
printk(KERN_ERR "%s: Error attempting to read "
"lower page segment; rc = [%d]\n",
@@ -297,7 +274,7 @@ static int ecryptfs_write_begin(struct file *file,
} else if (crypt_stat->flags & ECRYPTFS_VIEW_AS_ENCRYPTED) {
if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR) {
rc = ecryptfs_copy_up_encrypted_with_header(
- &folio->page, crypt_stat);
+ folio, crypt_stat);
if (rc) {
printk(KERN_ERR "%s: Error attempting "
"to copy the encrypted content "
@@ -311,7 +288,7 @@ static int ecryptfs_write_begin(struct file *file,
folio_mark_uptodate(folio);
} else {
rc = ecryptfs_read_lower_page_segment(
- &folio->page, index, 0, PAGE_SIZE,
+ folio, index, 0, PAGE_SIZE,
mapping->host);
if (rc) {
printk(KERN_ERR "%s: Error reading "
@@ -328,7 +305,7 @@ static int ecryptfs_write_begin(struct file *file,
folio_zero_range(folio, 0, PAGE_SIZE);
folio_mark_uptodate(folio);
} else if (len < PAGE_SIZE) {
- rc = ecryptfs_decrypt_page(&folio->page);
+ rc = ecryptfs_decrypt_page(folio);
if (rc) {
printk(KERN_ERR "%s: Error decrypting "
"page at index [%ld]; "
@@ -477,7 +454,7 @@ static int ecryptfs_write_end(struct file *file,
"(page w/ index = [0x%.16lx], to = [%d])\n", index, to);
if (!(crypt_stat->flags & ECRYPTFS_ENCRYPTED)) {
rc = ecryptfs_write_lower_page_segment(ecryptfs_inode,
- &folio->page, 0, to);
+ folio, 0, to);
if (!rc) {
rc = copied;
fsstack_copy_inode_size(ecryptfs_inode,
@@ -499,7 +476,7 @@ static int ecryptfs_write_end(struct file *file,
"zeros in page with index = [0x%.16lx]\n", index);
goto out;
}
- rc = ecryptfs_encrypt_page(&folio->page);
+ rc = ecryptfs_encrypt_page(folio);
if (rc) {
ecryptfs_printk(KERN_WARNING, "Error encrypting page (upper "
"index [0x%.16lx])\n", index);
@@ -548,9 +525,10 @@ const struct address_space_operations ecryptfs_aops = {
.dirty_folio = block_dirty_folio,
.invalidate_folio = block_invalidate_folio,
#endif
- .writepage = ecryptfs_writepage,
+ .writepages = ecryptfs_writepages,
.read_folio = ecryptfs_read_folio,
.write_begin = ecryptfs_write_begin,
.write_end = ecryptfs_write_end,
+ .migrate_folio = filemap_migrate_folio,
.bmap = ecryptfs_bmap,
};
diff --git a/fs/ecryptfs/read_write.c b/fs/ecryptfs/read_write.c
index 3458f153a588..b3b451c2b941 100644
--- a/fs/ecryptfs/read_write.c
+++ b/fs/ecryptfs/read_write.c
@@ -41,30 +41,29 @@ int ecryptfs_write_lower(struct inode *ecryptfs_inode, char *data,
/**
* ecryptfs_write_lower_page_segment
* @ecryptfs_inode: The eCryptfs inode
- * @page_for_lower: The page containing the data to be written to the
+ * @folio_for_lower: The folio containing the data to be written to the
* lower file
- * @offset_in_page: The offset in the @page_for_lower from which to
+ * @offset_in_page: The offset in the @folio_for_lower from which to
* start writing the data
- * @size: The amount of data from @page_for_lower to write to the
+ * @size: The amount of data from @folio_for_lower to write to the
* lower file
*
* Determines the byte offset in the file for the given page and
* offset within the page, maps the page, and makes the call to write
- * the contents of @page_for_lower to the lower inode.
+ * the contents of @folio_for_lower to the lower inode.
*
* Returns zero on success; non-zero otherwise
*/
int ecryptfs_write_lower_page_segment(struct inode *ecryptfs_inode,
- struct page *page_for_lower,
+ struct folio *folio_for_lower,
size_t offset_in_page, size_t size)
{
char *virt;
loff_t offset;
int rc;
- offset = ((((loff_t)page_for_lower->index) << PAGE_SHIFT)
- + offset_in_page);
- virt = kmap_local_page(page_for_lower);
+ offset = (loff_t)folio_for_lower->index * PAGE_SIZE + offset_in_page;
+ virt = kmap_local_folio(folio_for_lower, 0);
rc = ecryptfs_write_lower(ecryptfs_inode, virt, offset, size);
if (rc > 0)
rc = 0;
@@ -93,7 +92,6 @@ int ecryptfs_write_lower_page_segment(struct inode *ecryptfs_inode,
int ecryptfs_write(struct inode *ecryptfs_inode, char *data, loff_t offset,
size_t size)
{
- struct page *ecryptfs_page;
struct ecryptfs_crypt_stat *crypt_stat;
char *ecryptfs_page_virt;
loff_t ecryptfs_file_size = i_size_read(ecryptfs_inode);
@@ -111,6 +109,7 @@ int ecryptfs_write(struct inode *ecryptfs_inode, char *data, loff_t offset,
else
pos = offset;
while (pos < (offset + size)) {
+ struct folio *ecryptfs_folio;
pgoff_t ecryptfs_page_idx = (pos >> PAGE_SHIFT);
size_t start_offset_in_page = (pos & ~PAGE_MASK);
size_t num_bytes = (PAGE_SIZE - start_offset_in_page);
@@ -130,17 +129,18 @@ int ecryptfs_write(struct inode *ecryptfs_inode, char *data, loff_t offset,
if (num_bytes > total_remaining_zeros)
num_bytes = total_remaining_zeros;
}
- ecryptfs_page = ecryptfs_get_locked_page(ecryptfs_inode,
- ecryptfs_page_idx);
- if (IS_ERR(ecryptfs_page)) {
- rc = PTR_ERR(ecryptfs_page);
+ ecryptfs_folio = read_mapping_folio(ecryptfs_inode->i_mapping,
+ ecryptfs_page_idx, NULL);
+ if (IS_ERR(ecryptfs_folio)) {
+ rc = PTR_ERR(ecryptfs_folio);
printk(KERN_ERR "%s: Error getting page at "
"index [%ld] from eCryptfs inode "
"mapping; rc = [%d]\n", __func__,
ecryptfs_page_idx, rc);
goto out;
}
- ecryptfs_page_virt = kmap_local_page(ecryptfs_page);
+ folio_lock(ecryptfs_folio);
+ ecryptfs_page_virt = kmap_local_folio(ecryptfs_folio, 0);
/*
* pos: where we're now writing, offset: where the request was
@@ -164,17 +164,17 @@ int ecryptfs_write(struct inode *ecryptfs_inode, char *data, loff_t offset,
data_offset += num_bytes;
}
kunmap_local(ecryptfs_page_virt);
- flush_dcache_page(ecryptfs_page);
- SetPageUptodate(ecryptfs_page);
- unlock_page(ecryptfs_page);
+ flush_dcache_folio(ecryptfs_folio);
+ folio_mark_uptodate(ecryptfs_folio);
+ folio_unlock(ecryptfs_folio);
if (crypt_stat->flags & ECRYPTFS_ENCRYPTED)
- rc = ecryptfs_encrypt_page(ecryptfs_page);
+ rc = ecryptfs_encrypt_page(ecryptfs_folio);
else
rc = ecryptfs_write_lower_page_segment(ecryptfs_inode,
- ecryptfs_page,
+ ecryptfs_folio,
start_offset_in_page,
data_offset);
- put_page(ecryptfs_page);
+ folio_put(ecryptfs_folio);
if (rc) {
printk(KERN_ERR "%s: Error encrypting "
"page; rc = [%d]\n", __func__, rc);
@@ -228,7 +228,7 @@ int ecryptfs_read_lower(char *data, loff_t offset, size_t size,
/**
* ecryptfs_read_lower_page_segment
- * @page_for_ecryptfs: The page into which data for eCryptfs will be
+ * @folio_for_ecryptfs: The folio into which data for eCryptfs will be
* written
* @page_index: Page index in @page_for_ecryptfs from which to start
* writing
@@ -243,7 +243,7 @@ int ecryptfs_read_lower(char *data, loff_t offset, size_t size,
*
* Returns zero on success; non-zero otherwise
*/
-int ecryptfs_read_lower_page_segment(struct page *page_for_ecryptfs,
+int ecryptfs_read_lower_page_segment(struct folio *folio_for_ecryptfs,
pgoff_t page_index,
size_t offset_in_page, size_t size,
struct inode *ecryptfs_inode)
@@ -252,12 +252,12 @@ int ecryptfs_read_lower_page_segment(struct page *page_for_ecryptfs,
loff_t offset;
int rc;
- offset = ((((loff_t)page_index) << PAGE_SHIFT) + offset_in_page);
- virt = kmap_local_page(page_for_ecryptfs);
+ offset = (loff_t)page_index * PAGE_SIZE + offset_in_page;
+ virt = kmap_local_folio(folio_for_ecryptfs, 0);
rc = ecryptfs_read_lower(virt, offset, size, ecryptfs_inode);
if (rc > 0)
rc = 0;
kunmap_local(virt);
- flush_dcache_page(page_for_ecryptfs);
+ flush_dcache_folio(folio_for_ecryptfs);
return rc;
}
diff --git a/fs/efs/super.c b/fs/efs/super.c
index e4421c10caeb..c59086b7eabf 100644
--- a/fs/efs/super.c
+++ b/fs/efs/super.c
@@ -15,7 +15,6 @@
#include <linux/vfs.h>
#include <linux/blkdev.h>
#include <linux/fs_context.h>
-#include <linux/fs_parser.h>
#include "efs.h"
#include <linux/efs_vh.h>
#include <linux/efs_fs_sb.h>
@@ -49,15 +48,6 @@ static struct pt_types sgi_pt_types[] = {
{0, NULL}
};
-enum {
- Opt_explicit_open,
-};
-
-static const struct fs_parameter_spec efs_param_spec[] = {
- fsparam_flag ("explicit-open", Opt_explicit_open),
- {}
-};
-
/*
* File system definition and registration.
*/
@@ -67,7 +57,6 @@ static struct file_system_type efs_fs_type = {
.kill_sb = efs_kill_sb,
.fs_flags = FS_REQUIRES_DEV,
.init_fs_context = efs_init_fs_context,
- .parameters = efs_param_spec,
};
MODULE_ALIAS_FS("efs");
@@ -265,7 +254,8 @@ static int efs_fill_super(struct super_block *s, struct fs_context *fc)
if (!sb_set_blocksize(s, EFS_BLOCKSIZE)) {
pr_err("device does not support %d byte blocks\n",
EFS_BLOCKSIZE);
- return -EINVAL;
+ return invalf(fc, "device does not support %d byte blocks\n",
+ EFS_BLOCKSIZE);
}
/* read the vh (volume header) block */
@@ -327,43 +317,22 @@ static int efs_fill_super(struct super_block *s, struct fs_context *fc)
return 0;
}
-static void efs_free_fc(struct fs_context *fc)
-{
- kfree(fc->fs_private);
-}
-
static int efs_get_tree(struct fs_context *fc)
{
return get_tree_bdev(fc, efs_fill_super);
}
-static int efs_parse_param(struct fs_context *fc, struct fs_parameter *param)
-{
- int token;
- struct fs_parse_result result;
-
- token = fs_parse(fc, efs_param_spec, param, &result);
- if (token < 0)
- return token;
- return 0;
-}
-
static int efs_reconfigure(struct fs_context *fc)
{
sync_filesystem(fc->root->d_sb);
+ fc->sb_flags |= SB_RDONLY;
return 0;
}
-struct efs_context {
- unsigned long s_mount_opts;
-};
-
static const struct fs_context_operations efs_context_opts = {
- .parse_param = efs_parse_param,
.get_tree = efs_get_tree,
.reconfigure = efs_reconfigure,
- .free = efs_free_fc,
};
/*
@@ -371,12 +340,6 @@ static const struct fs_context_operations efs_context_opts = {
*/
static int efs_init_fs_context(struct fs_context *fc)
{
- struct efs_context *ctx;
-
- ctx = kzalloc(sizeof(struct efs_context), GFP_KERNEL);
- if (!ctx)
- return -ENOMEM;
- fc->fs_private = ctx;
fc->ops = &efs_context_opts;
return 0;
diff --git a/fs/eventfd.c b/fs/eventfd.c
index 22c934f3a080..76129bfcd663 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -347,13 +347,10 @@ EXPORT_SYMBOL_GPL(eventfd_fget);
*/
struct eventfd_ctx *eventfd_ctx_fdget(int fd)
{
- struct eventfd_ctx *ctx;
- struct fd f = fdget(fd);
- if (!fd_file(f))
+ CLASS(fd, f)(fd);
+ if (fd_empty(f))
return ERR_PTR(-EBADF);
- ctx = eventfd_ctx_fileget(fd_file(f));
- fdput(f);
- return ctx;
+ return eventfd_ctx_fileget(fd_file(f));
}
EXPORT_SYMBOL_GPL(eventfd_ctx_fdget);
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 1ae4542f0bd8..62433cb3d2c2 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -823,7 +823,8 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force)
to_free = NULL;
head = file->f_ep;
if (head->first == &epi->fllink && !epi->fllink.next) {
- file->f_ep = NULL;
+ /* See eventpoll_release() for details. */
+ WRITE_ONCE(file->f_ep, NULL);
if (!is_file_epoll(file)) {
struct epitems_head *v;
v = container_of(head, struct epitems_head, epitems);
@@ -1002,7 +1003,7 @@ static struct file *epi_fget(const struct epitem *epi)
struct file *file;
file = epi->ffd.file;
- if (!atomic_long_inc_not_zero(&file->f_count))
+ if (!file_ref_get(&file->f_ref))
file = NULL;
return file;
}
@@ -1372,7 +1373,10 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v
break;
}
}
- wake_up(&ep->wq);
+ if (sync)
+ wake_up_sync(&ep->wq);
+ else
+ wake_up(&ep->wq);
}
if (waitqueue_active(&ep->poll_wait))
pwake++;
@@ -1603,7 +1607,8 @@ allocate:
spin_unlock(&file->f_lock);
goto allocate;
}
- file->f_ep = head;
+ /* See eventpoll_release() for details. */
+ WRITE_ONCE(file->f_ep, head);
to_free = NULL;
}
hlist_add_head_rcu(&epi->fllink, file->f_ep);
@@ -2254,25 +2259,22 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds,
{
int error;
int full_check = 0;
- struct fd f, tf;
struct eventpoll *ep;
struct epitem *epi;
struct eventpoll *tep = NULL;
- error = -EBADF;
- f = fdget(epfd);
- if (!fd_file(f))
- goto error_return;
+ CLASS(fd, f)(epfd);
+ if (fd_empty(f))
+ return -EBADF;
/* Get the "struct file *" for the target file */
- tf = fdget(fd);
- if (!fd_file(tf))
- goto error_fput;
+ CLASS(fd, tf)(fd);
+ if (fd_empty(tf))
+ return -EBADF;
/* The target file descriptor must support poll */
- error = -EPERM;
if (!file_can_poll(fd_file(tf)))
- goto error_tgt_fput;
+ return -EPERM;
/* Check if EPOLLWAKEUP is allowed */
if (ep_op_has_event(op))
@@ -2391,12 +2393,6 @@ error_tgt_fput:
loop_check_gen++;
mutex_unlock(&epnested_mutex);
}
-
- fdput(tf);
-error_fput:
- fdput(f);
-error_return:
-
return error;
}
@@ -2424,8 +2420,6 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
static int do_epoll_wait(int epfd, struct epoll_event __user *events,
int maxevents, struct timespec64 *to)
{
- int error;
- struct fd f;
struct eventpoll *ep;
/* The maximum number of event must be greater than zero */
@@ -2437,17 +2431,16 @@ static int do_epoll_wait(int epfd, struct epoll_event __user *events,
return -EFAULT;
/* Get the "struct file *" for the eventpoll file */
- f = fdget(epfd);
- if (!fd_file(f))
+ CLASS(fd, f)(epfd);
+ if (fd_empty(f))
return -EBADF;
/*
* We have to check that the file structure underneath the fd
* the user passed to us _is_ an eventpoll file.
*/
- error = -EINVAL;
if (!is_file_epoll(fd_file(f)))
- goto error_fput;
+ return -EINVAL;
/*
* At this point it is safe to assume that the "private_data" contains
@@ -2456,11 +2449,7 @@ static int do_epoll_wait(int epfd, struct epoll_event __user *events,
ep = fd_file(f)->private_data;
/* Time to fish for events ... */
- error = ep_poll(ep, events, maxevents, to);
-
-error_fput:
- fdput(f);
- return error;
+ return ep_poll(ep, events, maxevents, to);
}
SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events,
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 591fb3f710be..8042ad873808 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -550,7 +550,8 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group,
trace_ext4_read_block_bitmap_load(sb, block_group, ignore_locked);
ext4_read_bh_nowait(bh, REQ_META | REQ_PRIO |
(ignore_locked ? REQ_RAHEAD : 0),
- ext4_end_bitmap_read);
+ ext4_end_bitmap_read,
+ ext4_simulate_fail(sb, EXT4_SIM_BBITMAP_EIO));
return bh;
verify:
err = ext4_validate_block_bitmap(sb, desc, block_group, bh);
@@ -577,7 +578,6 @@ int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group,
if (!desc)
return -EFSCORRUPTED;
wait_on_buffer(bh);
- ext4_simulate_fail_bh(sb, bh, EXT4_SIM_BBITMAP_EIO);
if (!buffer_uptodate(bh)) {
ext4_error_err(sb, EIO, "Cannot read block bitmap - "
"block_group = %u, block_bitmap = %llu",
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index ef6a3c8f3a9a..02d47a64e8d1 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -418,7 +418,7 @@ struct fname {
__u32 inode;
__u8 name_len;
__u8 file_type;
- char name[];
+ char name[] __counted_by(name_len);
};
/*
@@ -471,14 +471,13 @@ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
struct rb_node **p, *parent = NULL;
struct fname *fname, *new_fn;
struct dir_private_info *info;
- int len;
info = dir_file->private_data;
p = &info->root.rb_node;
/* Create and allocate the fname structure */
- len = sizeof(struct fname) + ent_name->len + 1;
- new_fn = kzalloc(len, GFP_KERNEL);
+ new_fn = kzalloc(struct_size(new_fn, name, ent_name->len + 1),
+ GFP_KERNEL);
if (!new_fn)
return -ENOMEM;
new_fn->hash = hash;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 44b0d418143c..74f2071189b2 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1729,6 +1729,10 @@ struct ext4_sb_info {
*/
struct work_struct s_sb_upd_work;
+ /* Atomic write unit values in bytes */
+ unsigned int s_awu_min;
+ unsigned int s_awu_max;
+
/* Ext4 fast commit sub transaction ID */
atomic_t s_fc_subtid;
@@ -1865,14 +1869,6 @@ static inline bool ext4_simulate_fail(struct super_block *sb,
return false;
}
-static inline void ext4_simulate_fail_bh(struct super_block *sb,
- struct buffer_head *bh,
- unsigned long code)
-{
- if (!IS_ERR(bh) && ext4_simulate_fail(sb, code))
- clear_buffer_uptodate(bh);
-}
-
/*
* Error number codes for s_{first,last}_error_errno
*
@@ -3100,9 +3096,9 @@ extern struct buffer_head *ext4_sb_bread(struct super_block *sb,
extern struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb,
sector_t block);
extern void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags,
- bh_end_io_t *end_io);
+ bh_end_io_t *end_io, bool simu_fail);
extern int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags,
- bh_end_io_t *end_io);
+ bh_end_io_t *end_io, bool simu_fail);
extern int ext4_read_bh_lock(struct buffer_head *bh, blk_opf_t op_flags, bool wait);
extern void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block);
extern int ext4_seq_options_show(struct seq_file *seq, void *offset);
@@ -3855,6 +3851,12 @@ static inline int ext4_buffer_uptodate(struct buffer_head *bh)
return buffer_uptodate(bh);
}
+static inline bool ext4_inode_can_atomic_write(struct inode *inode)
+{
+
+ return S_ISREG(inode->i_mode) && EXT4_SB(inode->i_sb)->s_awu_min > 0;
+}
+
extern int ext4_block_write_begin(handle_t *handle, struct folio *folio,
loff_t pos, unsigned len,
get_block_t *get_block);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 34e25eee6521..a07a98a4b97a 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -568,7 +568,7 @@ __read_extent_tree_block(const char *function, unsigned int line,
if (!bh_uptodate_or_lock(bh)) {
trace_ext4_ext_load_extent(inode, pblk, _RET_IP_);
- err = ext4_read_bh(bh, 0, NULL);
+ err = ext4_read_bh(bh, 0, NULL, false);
if (err < 0)
goto errout;
}
@@ -3138,7 +3138,7 @@ static void ext4_zeroout_es(struct inode *inode, struct ext4_extent *ex)
return;
ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock,
- EXTENT_STATUS_WRITTEN, 0);
+ EXTENT_STATUS_WRITTEN, false);
}
/* FIXME!! we need to try to merge to left or right after zero-out */
@@ -4158,7 +4158,7 @@ insert_hole:
/* Put just found gap into cache to speed up subsequent requests */
ext_debug(inode, " -> %u:%u\n", hole_start, len);
ext4_es_insert_extent(inode, hole_start, len, ~0,
- EXTENT_STATUS_HOLE, 0);
+ EXTENT_STATUS_HOLE, false);
/* Update hole_len to reflect hole size after lblk */
if (hole_start != lblk)
@@ -4482,7 +4482,7 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
int depth = 0;
struct ext4_map_blocks map;
unsigned int credits;
- loff_t epos;
+ loff_t epos, old_size = i_size_read(inode);
BUG_ON(!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS));
map.m_lblk = offset;
@@ -4541,6 +4541,11 @@ retry:
if (ext4_update_inode_size(inode, epos) & 0x1)
inode_set_mtime_to_ts(inode,
inode_get_ctime(inode));
+ if (epos > old_size) {
+ pagecache_isize_extended(inode, old_size, epos);
+ ext4_zero_partial_blocks(handle, inode,
+ old_size, epos - old_size);
+ }
}
ret2 = ext4_mark_inode_dirty(handle, inode);
ext4_update_inode_fsync_trans(handle, inode, 1);
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index c786691dabd3..ae29832aab1e 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -848,7 +848,7 @@ out:
*/
void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len, ext4_fsblk_t pblk,
- unsigned int status, int flags)
+ unsigned int status, bool delalloc_reserve_used)
{
struct extent_status newes;
ext4_lblk_t end = lblk + len - 1;
@@ -863,8 +863,8 @@ void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
return;
- es_debug("add [%u/%u) %llu %x %x to extent status tree of inode %lu\n",
- lblk, len, pblk, status, flags, inode->i_ino);
+ es_debug("add [%u/%u) %llu %x %d to extent status tree of inode %lu\n",
+ lblk, len, pblk, status, delalloc_reserve_used, inode->i_ino);
if (!len)
return;
@@ -945,7 +945,7 @@ error:
resv_used += pending;
if (resv_used)
ext4_da_update_reserve_space(inode, resv_used,
- flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE);
+ delalloc_reserve_used);
if (err1 || err2 || err3 < 0)
goto retry;
diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h
index 4424232de298..8f9c008d11e8 100644
--- a/fs/ext4/extents_status.h
+++ b/fs/ext4/extents_status.h
@@ -135,7 +135,8 @@ extern void ext4_es_init_tree(struct ext4_es_tree *tree);
extern void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len, ext4_fsblk_t pblk,
- unsigned int status, int flags);
+ unsigned int status,
+ bool delalloc_reserve_used);
extern void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len, ext4_fsblk_t pblk,
unsigned int status);
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index b33664f6ce2a..26c4fc37edcf 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -291,9 +291,9 @@ void ext4_fc_del(struct inode *inode)
return;
restart:
- spin_lock(&EXT4_SB(inode->i_sb)->s_fc_lock);
+ spin_lock(&sbi->s_fc_lock);
if (list_empty(&ei->i_fc_list) && list_empty(&ei->i_fc_dilist)) {
- spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
+ spin_unlock(&sbi->s_fc_lock);
return;
}
@@ -357,9 +357,7 @@ void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handl
}
spin_lock(&sbi->s_fc_lock);
is_ineligible = ext4_test_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
- if (has_transaction &&
- (!is_ineligible ||
- (is_ineligible && tid_gt(tid, sbi->s_fc_ineligible_tid))))
+ if (has_transaction && (!is_ineligible || tid_gt(tid, sbi->s_fc_ineligible_tid)))
sbi->s_fc_ineligible_tid = tid;
ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
spin_unlock(&sbi->s_fc_lock);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index f14aed14b9cf..3bd96c3d4cd0 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -392,8 +392,9 @@ static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size,
*/
if (pos + size <= READ_ONCE(EXT4_I(inode)->i_disksize) &&
pos + size <= i_size_read(inode))
- return size;
- return ext4_handle_inode_extension(inode, pos, size, size);
+ return 0;
+ error = ext4_handle_inode_extension(inode, pos, size, size);
+ return error < 0 ? error : 0;
}
static const struct iomap_dio_ops ext4_dio_write_ops = {
@@ -564,12 +565,9 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
}
ret = ext4_orphan_add(handle, inode);
- if (ret) {
- ext4_journal_stop(handle);
- goto out;
- }
-
ext4_journal_stop(handle);
+ if (ret)
+ goto out;
}
if (ilock_shared && !unwritten)
@@ -599,6 +597,13 @@ out:
ssize_t err;
loff_t endbyte;
+ /*
+ * There is no support for atomic writes on buffered-io yet,
+ * we should never fallback to buffered-io for DIO atomic
+ * writes.
+ */
+ WARN_ON_ONCE(iocb->ki_flags & IOCB_ATOMIC);
+
offset = iocb->ki_pos;
err = ext4_buffered_write_iter(iocb, from);
if (err < 0)
@@ -692,6 +697,20 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
if (IS_DAX(inode))
return ext4_dax_write_iter(iocb, from);
#endif
+
+ if (iocb->ki_flags & IOCB_ATOMIC) {
+ size_t len = iov_iter_count(from);
+ int ret;
+
+ if (len < EXT4_SB(inode->i_sb)->s_awu_min ||
+ len > EXT4_SB(inode->i_sb)->s_awu_max)
+ return -EINVAL;
+
+ ret = generic_atomic_write_valid(iocb, from);
+ if (ret)
+ return ret;
+ }
+
if (iocb->ki_flags & IOCB_DIRECT)
return ext4_dio_write_iter(iocb, from);
else
@@ -884,6 +903,9 @@ static int ext4_file_open(struct inode *inode, struct file *filp)
return ret;
}
+ if (ext4_inode_can_atomic_write(inode))
+ filp->f_mode |= FMODE_CAN_ATOMIC_WRITE;
+
filp->f_mode |= FMODE_NOWAIT | FMODE_CAN_ODIRECT;
return dquot_file_open(inode, filp);
}
diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c
index df853c4d3a8c..383c6edea6dd 100644
--- a/fs/ext4/fsmap.c
+++ b/fs/ext4/fsmap.c
@@ -185,6 +185,56 @@ static inline ext4_fsblk_t ext4_fsmap_next_pblk(struct ext4_fsmap *fmr)
return fmr->fmr_physical + fmr->fmr_length;
}
+static int ext4_getfsmap_meta_helper(struct super_block *sb,
+ ext4_group_t agno, ext4_grpblk_t start,
+ ext4_grpblk_t len, void *priv)
+{
+ struct ext4_getfsmap_info *info = priv;
+ struct ext4_fsmap *p;
+ struct ext4_fsmap *tmp;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ ext4_fsblk_t fsb, fs_start, fs_end;
+ int error;
+
+ fs_start = fsb = (EXT4_C2B(sbi, start) +
+ ext4_group_first_block_no(sb, agno));
+ fs_end = fs_start + EXT4_C2B(sbi, len);
+
+ /* Return relevant extents from the meta_list */
+ list_for_each_entry_safe(p, tmp, &info->gfi_meta_list, fmr_list) {
+ if (p->fmr_physical < info->gfi_next_fsblk) {
+ list_del(&p->fmr_list);
+ kfree(p);
+ continue;
+ }
+ if (p->fmr_physical <= fs_start ||
+ p->fmr_physical + p->fmr_length <= fs_end) {
+ /* Emit the retained free extent record if present */
+ if (info->gfi_lastfree.fmr_owner) {
+ error = ext4_getfsmap_helper(sb, info,
+ &info->gfi_lastfree);
+ if (error)
+ return error;
+ info->gfi_lastfree.fmr_owner = 0;
+ }
+ error = ext4_getfsmap_helper(sb, info, p);
+ if (error)
+ return error;
+ fsb = p->fmr_physical + p->fmr_length;
+ if (info->gfi_next_fsblk < fsb)
+ info->gfi_next_fsblk = fsb;
+ list_del(&p->fmr_list);
+ kfree(p);
+ continue;
+ }
+ }
+ if (info->gfi_next_fsblk < fsb)
+ info->gfi_next_fsblk = fsb;
+
+ return 0;
+}
+
+
/* Transform a blockgroup's free record into a fsmap */
static int ext4_getfsmap_datadev_helper(struct super_block *sb,
ext4_group_t agno, ext4_grpblk_t start,
@@ -539,6 +589,7 @@ static int ext4_getfsmap_datadev(struct super_block *sb,
error = ext4_mballoc_query_range(sb, info->gfi_agno,
EXT4_B2C(sbi, info->gfi_low.fmr_physical),
EXT4_B2C(sbi, info->gfi_high.fmr_physical),
+ ext4_getfsmap_meta_helper,
ext4_getfsmap_datadev_helper, info);
if (error)
goto err;
@@ -560,7 +611,8 @@ static int ext4_getfsmap_datadev(struct super_block *sb,
/* Report any gaps at the end of the bg */
info->gfi_last = true;
- error = ext4_getfsmap_datadev_helper(sb, end_ag, last_cluster, 0, info);
+ error = ext4_getfsmap_datadev_helper(sb, end_ag, last_cluster + 1,
+ 0, info);
if (error)
goto err;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 7f1a5f90dbbd..21d228073d79 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -193,8 +193,9 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
* submit the buffer_head for reading
*/
trace_ext4_load_inode_bitmap(sb, block_group);
- ext4_read_bh(bh, REQ_META | REQ_PRIO, ext4_end_bitmap_read);
- ext4_simulate_fail_bh(sb, bh, EXT4_SIM_IBITMAP_EIO);
+ ext4_read_bh(bh, REQ_META | REQ_PRIO,
+ ext4_end_bitmap_read,
+ ext4_simulate_fail(sb, EXT4_SIM_IBITMAP_EIO));
if (!buffer_uptodate(bh)) {
put_bh(bh);
ext4_error_err(sb, EIO, "Cannot read inode bitmap - "
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 7404f0935c90..7de327fa7b1c 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -170,7 +170,7 @@ static Indirect *ext4_get_branch(struct inode *inode, int depth,
}
if (!bh_uptodate_or_lock(bh)) {
- if (ext4_read_bh(bh, 0, NULL) < 0) {
+ if (ext4_read_bh(bh, 0, NULL, false) < 0) {
put_bh(bh);
goto failure;
}
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 54bdd4884fe6..89aade6f45f6 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -483,7 +483,7 @@ static int ext4_map_query_blocks(handle_t *handle, struct inode *inode,
status = map->m_flags & EXT4_MAP_UNWRITTEN ?
EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
- map->m_pblk, status, 0);
+ map->m_pblk, status, false);
return retval;
}
@@ -563,8 +563,8 @@ static int ext4_map_create_blocks(handle_t *handle, struct inode *inode,
status = map->m_flags & EXT4_MAP_UNWRITTEN ?
EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
- ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
- map->m_pblk, status, flags);
+ ext4_es_insert_extent(inode, map->m_lblk, map->m_len, map->m_pblk,
+ status, flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE);
return retval;
}
@@ -856,7 +856,14 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
if (nowait)
return sb_find_get_block(inode->i_sb, map.m_pblk);
- bh = sb_getblk(inode->i_sb, map.m_pblk);
+ /*
+ * Since bh could introduce extra ref count such as referred by
+ * journal_head etc. Try to avoid using __GFP_MOVABLE here
+ * as it may fail the migration when journal_head remains.
+ */
+ bh = getblk_unmovable(inode->i_sb->s_bdev, map.m_pblk,
+ inode->i_sb->s_blocksize);
+
if (unlikely(!bh))
return ERR_PTR(-ENOMEM);
if (map.m_flags & EXT4_MAP_NEW) {
@@ -1307,8 +1314,10 @@ static int ext4_write_end(struct file *file,
folio_unlock(folio);
folio_put(folio);
- if (old_size < pos && !verity)
+ if (old_size < pos && !verity) {
pagecache_isize_extended(inode, old_size, pos);
+ ext4_zero_partial_blocks(handle, inode, old_size, pos - old_size);
+ }
/*
* Don't mark the inode dirty under folio lock. First, it unnecessarily
* makes the holding time of folio lock longer. Second, it forces lock
@@ -1423,8 +1432,10 @@ static int ext4_journalled_write_end(struct file *file,
folio_unlock(folio);
folio_put(folio);
- if (old_size < pos && !verity)
+ if (old_size < pos && !verity) {
pagecache_isize_extended(inode, old_size, pos);
+ ext4_zero_partial_blocks(handle, inode, old_size, pos - old_size);
+ }
if (size_changed) {
ret2 = ext4_mark_inode_dirty(handle, inode);
@@ -2985,7 +2996,8 @@ static int ext4_da_do_write_end(struct address_space *mapping,
struct inode *inode = mapping->host;
loff_t old_size = inode->i_size;
bool disksize_changed = false;
- loff_t new_i_size;
+ loff_t new_i_size, zero_len = 0;
+ handle_t *handle;
if (unlikely(!folio_buffers(folio))) {
folio_unlock(folio);
@@ -3029,18 +3041,21 @@ static int ext4_da_do_write_end(struct address_space *mapping,
folio_unlock(folio);
folio_put(folio);
- if (old_size < pos)
+ if (pos > old_size) {
pagecache_isize_extended(inode, old_size, pos);
+ zero_len = pos - old_size;
+ }
- if (disksize_changed) {
- handle_t *handle;
+ if (!disksize_changed && !zero_len)
+ return copied;
- handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
- if (IS_ERR(handle))
- return PTR_ERR(handle);
- ext4_mark_inode_dirty(handle, inode);
- ext4_journal_stop(handle);
- }
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+ if (zero_len)
+ ext4_zero_partial_blocks(handle, inode, old_size, zero_len);
+ ext4_mark_inode_dirty(handle, inode);
+ ext4_journal_stop(handle);
return copied;
}
@@ -3444,17 +3459,34 @@ static int ext4_iomap_overwrite_begin(struct inode *inode, loff_t offset,
return ret;
}
+static inline bool ext4_want_directio_fallback(unsigned flags, ssize_t written)
+{
+ /* must be a directio to fall back to buffered */
+ if ((flags & (IOMAP_WRITE | IOMAP_DIRECT)) !=
+ (IOMAP_WRITE | IOMAP_DIRECT))
+ return false;
+
+ /* atomic writes are all-or-nothing */
+ if (flags & IOMAP_ATOMIC)
+ return false;
+
+ /* can only try again if we wrote nothing */
+ return written == 0;
+}
+
static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length,
ssize_t written, unsigned flags, struct iomap *iomap)
{
/*
* Check to see whether an error occurred while writing out the data to
- * the allocated blocks. If so, return the magic error code so that we
- * fallback to buffered I/O and attempt to complete the remainder of
- * the I/O. Any blocks that may have been allocated in preparation for
- * the direct I/O will be reused during buffered I/O.
+ * the allocated blocks. If so, return the magic error code for
+ * non-atomic write so that we fallback to buffered I/O and attempt to
+ * complete the remainder of the I/O.
+ * For non-atomic writes, any blocks that may have been
+ * allocated in preparation for the direct I/O will be reused during
+ * buffered I/O. For atomic write, we never fallback to buffered-io.
*/
- if (flags & (IOMAP_WRITE | IOMAP_DIRECT) && written == 0)
+ if (ext4_want_directio_fallback(flags, written))
return -ENOTBLK;
return 0;
@@ -4497,10 +4529,10 @@ make_io:
* Read the block from disk.
*/
trace_ext4_load_inode(sb, ino);
- ext4_read_bh_nowait(bh, REQ_META | REQ_PRIO, NULL);
+ ext4_read_bh_nowait(bh, REQ_META | REQ_PRIO, NULL,
+ ext4_simulate_fail(sb, EXT4_SIM_INODE_EIO));
blk_finish_plug(&plug);
wait_on_buffer(bh);
- ext4_simulate_fail_bh(sb, bh, EXT4_SIM_INODE_EIO);
if (!buffer_uptodate(bh)) {
if (ret_block)
*ret_block = block;
@@ -5426,6 +5458,14 @@ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
}
if (attr->ia_size != inode->i_size) {
+ /* attach jbd2 jinode for EOF folio tail zeroing */
+ if (attr->ia_size & (inode->i_sb->s_blocksize - 1) ||
+ oldsize & (inode->i_sb->s_blocksize - 1)) {
+ error = ext4_inode_attach_jinode(inode);
+ if (error)
+ goto err_out;
+ }
+
handle = ext4_journal_start(inode, EXT4_HT_INODE, 3);
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
@@ -5436,12 +5476,17 @@ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
orphan = 1;
}
/*
- * Update c/mtime on truncate up, ext4_truncate() will
- * update c/mtime in shrink case below
+ * Update c/mtime and tail zero the EOF folio on
+ * truncate up. ext4_truncate() handles the shrink case
+ * below.
*/
- if (!shrink)
+ if (!shrink) {
inode_set_mtime_to_ts(inode,
inode_set_ctime_current(inode));
+ if (oldsize & (inode->i_sb->s_blocksize - 1))
+ ext4_block_truncate_page(handle,
+ inode->i_mapping, oldsize);
+ }
if (shrink)
ext4_fc_track_range(handle, inode,
@@ -5578,6 +5623,18 @@ int ext4_getattr(struct mnt_idmap *idmap, const struct path *path,
}
}
+ if ((request_mask & STATX_WRITE_ATOMIC) && S_ISREG(inode->i_mode)) {
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ unsigned int awu_min = 0, awu_max = 0;
+
+ if (ext4_inode_can_atomic_write(inode)) {
+ awu_min = sbi->s_awu_min;
+ awu_max = sbi->s_awu_max;
+ }
+
+ generic_fill_statx_atomic_writes(stat, awu_min, awu_max);
+ }
+
flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
if (flags & EXT4_APPEND_FL)
stat->attributes |= STATX_ATTR_APPEND;
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 1c77400bd88e..7b9ce71c1c81 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -1330,7 +1330,6 @@ group_extend_out:
case EXT4_IOC_MOVE_EXT: {
struct move_extent me;
- struct fd donor;
int err;
if (!(filp->f_mode & FMODE_READ) ||
@@ -1342,30 +1341,26 @@ group_extend_out:
return -EFAULT;
me.moved_len = 0;
- donor = fdget(me.donor_fd);
- if (!fd_file(donor))
+ CLASS(fd, donor)(me.donor_fd);
+ if (fd_empty(donor))
return -EBADF;
- if (!(fd_file(donor)->f_mode & FMODE_WRITE)) {
- err = -EBADF;
- goto mext_out;
- }
+ if (!(fd_file(donor)->f_mode & FMODE_WRITE))
+ return -EBADF;
if (ext4_has_feature_bigalloc(sb)) {
ext4_msg(sb, KERN_ERR,
"Online defrag not supported with bigalloc");
- err = -EOPNOTSUPP;
- goto mext_out;
+ return -EOPNOTSUPP;
} else if (IS_DAX(inode)) {
ext4_msg(sb, KERN_ERR,
"Online defrag not supported with DAX");
- err = -EOPNOTSUPP;
- goto mext_out;
+ return -EOPNOTSUPP;
}
err = mnt_want_write_file(filp);
if (err)
- goto mext_out;
+ return err;
err = ext4_move_extents(filp, fd_file(donor), me.orig_start,
me.donor_start, me.len, &me.moved_len);
@@ -1374,8 +1369,6 @@ group_extend_out:
if (copy_to_user((struct move_extent __user *)arg,
&me, sizeof(me)))
err = -EFAULT;
-mext_out:
- fdput(donor);
return err;
}
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index d73e38323879..b25a27c86696 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -5711,7 +5711,7 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac)
(unsigned long)ac->ac_b_ex.fe_logical,
(int)ac->ac_criteria);
mb_debug(sb, "%u found", ac->ac_found);
- mb_debug(sb, "used pa: %s, ", ac->ac_pa ? "yes" : "no");
+ mb_debug(sb, "used pa: %s, ", str_yes_no(ac->ac_pa));
if (ac->ac_pa)
mb_debug(sb, "pa_type %s\n", ac->ac_pa->pa_type == MB_GROUP_PA ?
"group pa" : "inode pa");
@@ -6056,7 +6056,7 @@ static bool ext4_mb_discard_preallocations_should_retry(struct super_block *sb,
}
out_dbg:
- mb_debug(sb, "freed %d, retry ? %s\n", freed, ret ? "yes" : "no");
+ mb_debug(sb, "freed %d, retry ? %s\n", freed, str_yes_no(ret));
return ret;
}
@@ -6999,13 +6999,14 @@ int
ext4_mballoc_query_range(
struct super_block *sb,
ext4_group_t group,
- ext4_grpblk_t start,
+ ext4_grpblk_t first,
ext4_grpblk_t end,
+ ext4_mballoc_query_range_fn meta_formatter,
ext4_mballoc_query_range_fn formatter,
void *priv)
{
void *bitmap;
- ext4_grpblk_t next;
+ ext4_grpblk_t start, next;
struct ext4_buddy e4b;
int error;
@@ -7016,10 +7017,19 @@ ext4_mballoc_query_range(
ext4_lock_group(sb, group);
- start = max(e4b.bd_info->bb_first_free, start);
+ start = max(e4b.bd_info->bb_first_free, first);
if (end >= EXT4_CLUSTERS_PER_GROUP(sb))
end = EXT4_CLUSTERS_PER_GROUP(sb) - 1;
-
+ if (meta_formatter && start != first) {
+ if (start > end)
+ start = end;
+ ext4_unlock_group(sb, group);
+ error = meta_formatter(sb, group, first, start - first,
+ priv);
+ if (error)
+ goto out_unload;
+ ext4_lock_group(sb, group);
+ }
while (start <= end) {
start = mb_find_next_zero_bit(bitmap, end + 1, start);
if (start > end)
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index d8553f1498d3..f8280de3e882 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -259,6 +259,7 @@ ext4_mballoc_query_range(
ext4_group_t agno,
ext4_grpblk_t start,
ext4_grpblk_t end,
+ ext4_mballoc_query_range_fn meta_formatter,
ext4_mballoc_query_range_fn formatter,
void *priv);
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index bd946d0c71b7..d64c04ed061a 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -94,7 +94,7 @@ static int read_mmp_block(struct super_block *sb, struct buffer_head **bh,
}
lock_buffer(*bh);
- ret = ext4_read_bh(*bh, REQ_META | REQ_PRIO, NULL);
+ ret = ext4_read_bh(*bh, REQ_META | REQ_PRIO, NULL, false);
if (ret)
goto warn_exit;
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index b64661ea6e0e..898443e98efc 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -213,7 +213,7 @@ static int mext_page_mkuptodate(struct folio *folio, size_t from, size_t to)
unlock_buffer(bh);
continue;
}
- ext4_read_bh_nowait(bh, 0, NULL);
+ ext4_read_bh_nowait(bh, 0, NULL, false);
nr++;
} while (block++, (bh = bh->b_this_page) != head);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 790db7eac6c2..bcf2737078b8 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1747,7 +1747,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir,
#endif
frame = dx_probe(fname, dir, NULL, frames);
if (IS_ERR(frame))
- return (struct buffer_head *) frame;
+ return ERR_CAST(frame);
do {
block = dx_get_block(frame->at);
bh = ext4_read_dirblock(dir, block, DIRENT_HTREE);
@@ -1952,7 +1952,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
if (IS_ERR(bh2)) {
brelse(*bh);
*bh = NULL;
- return (struct ext4_dir_entry_2 *) bh2;
+ return ERR_CAST(bh2);
}
BUFFER_TRACE(*bh, "get_write_access");
@@ -2000,8 +2000,17 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
else
split = count/2;
+ if (WARN_ON_ONCE(split == 0)) {
+ /* Should never happen, but avoid out-of-bounds access below */
+ ext4_error_inode_block(dir, (*bh)->b_blocknr, 0,
+ "bad indexed directory? hash=%08x:%08x count=%d move=%u",
+ hinfo->hash, hinfo->minor_hash, count, move);
+ err = -EFSCORRUPTED;
+ goto out;
+ }
+
hash2 = map[split].hash;
- continued = split > 0 ? hash2 == map[split - 1].hash : 0;
+ continued = hash2 == map[split - 1].hash;
dxtrace(printk(KERN_INFO "Split block %lu at %x, %i/%i\n",
(unsigned long)dx_get_block(frame->at),
hash2, split, count-split));
@@ -2043,10 +2052,11 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
return de;
journal_error:
+ ext4_std_error(dir->i_sb, err);
+out:
brelse(*bh);
brelse(bh2);
*bh = NULL;
- ext4_std_error(dir->i_sb, err);
return ERR_PTR(err);
}
@@ -2395,11 +2405,8 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
if (fscrypt_is_nokey_name(dentry))
return -ENOKEY;
-#if IS_ENABLED(CONFIG_UNICODE)
- if (sb_has_strict_encoding(sb) && IS_CASEFOLDED(dir) &&
- utf8_validate(sb->s_encoding, &dentry->d_name))
+ if (!generic_ci_validate_strict_name(dir, &dentry->d_name))
return -EINVAL;
-#endif
retval = ext4_fname_setup_filename(dir, &dentry->d_name, 0, &fname);
if (retval)
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index ad5543866d21..69b8a7221a2b 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -417,11 +417,13 @@ static void io_submit_add_bh(struct ext4_io_submit *io,
submit_and_retry:
ext4_io_submit(io);
}
- if (io->io_bio == NULL)
+ if (io->io_bio == NULL) {
io_submit_init_bio(io, bh);
+ io->io_bio->bi_write_hint = inode->i_write_hint;
+ }
if (!bio_add_folio(io->io_bio, io_folio, bh->b_size, bh_offset(bh)))
goto submit_and_retry;
- wbc_account_cgroup_owner(io->io_wbc, &folio->page, bh->b_size);
+ wbc_account_cgroup_owner(io->io_wbc, folio, bh->b_size);
io->io_next_block++;
}
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index a2704f064361..72f77f78ae8d 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1300,7 +1300,7 @@ static struct buffer_head *ext4_get_bitmap(struct super_block *sb, __u64 block)
if (unlikely(!bh))
return NULL;
if (!bh_uptodate_or_lock(bh)) {
- if (ext4_read_bh(bh, 0, NULL) < 0) {
+ if (ext4_read_bh(bh, 0, NULL, false) < 0) {
brelse(bh);
return NULL;
}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 16a4ce704460..785809f33ff4 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -161,8 +161,14 @@ MODULE_ALIAS("ext3");
static inline void __ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags,
- bh_end_io_t *end_io)
+ bh_end_io_t *end_io, bool simu_fail)
{
+ if (simu_fail) {
+ clear_buffer_uptodate(bh);
+ unlock_buffer(bh);
+ return;
+ }
+
/*
* buffer's verified bit is no longer valid after reading from
* disk again due to write out error, clear it to make sure we
@@ -176,7 +182,7 @@ static inline void __ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags,
}
void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags,
- bh_end_io_t *end_io)
+ bh_end_io_t *end_io, bool simu_fail)
{
BUG_ON(!buffer_locked(bh));
@@ -184,10 +190,11 @@ void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags,
unlock_buffer(bh);
return;
}
- __ext4_read_bh(bh, op_flags, end_io);
+ __ext4_read_bh(bh, op_flags, end_io, simu_fail);
}
-int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io)
+int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags,
+ bh_end_io_t *end_io, bool simu_fail)
{
BUG_ON(!buffer_locked(bh));
@@ -196,7 +203,7 @@ int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io
return 0;
}
- __ext4_read_bh(bh, op_flags, end_io);
+ __ext4_read_bh(bh, op_flags, end_io, simu_fail);
wait_on_buffer(bh);
if (buffer_uptodate(bh))
@@ -208,10 +215,10 @@ int ext4_read_bh_lock(struct buffer_head *bh, blk_opf_t op_flags, bool wait)
{
lock_buffer(bh);
if (!wait) {
- ext4_read_bh_nowait(bh, op_flags, NULL);
+ ext4_read_bh_nowait(bh, op_flags, NULL, false);
return 0;
}
- return ext4_read_bh(bh, op_flags, NULL);
+ return ext4_read_bh(bh, op_flags, NULL, false);
}
/*
@@ -266,7 +273,7 @@ void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block)
if (likely(bh)) {
if (trylock_buffer(bh))
- ext4_read_bh_nowait(bh, REQ_RAHEAD, NULL);
+ ext4_read_bh_nowait(bh, REQ_RAHEAD, NULL, false);
brelse(bh);
}
}
@@ -346,9 +353,9 @@ __u32 ext4_free_group_clusters(struct super_block *sb,
__u32 ext4_free_inodes_count(struct super_block *sb,
struct ext4_group_desc *bg)
{
- return le16_to_cpu(bg->bg_free_inodes_count_lo) |
+ return le16_to_cpu(READ_ONCE(bg->bg_free_inodes_count_lo)) |
(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
- (__u32)le16_to_cpu(bg->bg_free_inodes_count_hi) << 16 : 0);
+ (__u32)le16_to_cpu(READ_ONCE(bg->bg_free_inodes_count_hi)) << 16 : 0);
}
__u32 ext4_used_dirs_count(struct super_block *sb,
@@ -402,9 +409,9 @@ void ext4_free_group_clusters_set(struct super_block *sb,
void ext4_free_inodes_set(struct super_block *sb,
struct ext4_group_desc *bg, __u32 count)
{
- bg->bg_free_inodes_count_lo = cpu_to_le16((__u16)count);
+ WRITE_ONCE(bg->bg_free_inodes_count_lo, cpu_to_le16((__u16)count));
if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
- bg->bg_free_inodes_count_hi = cpu_to_le16(count >> 16);
+ WRITE_ONCE(bg->bg_free_inodes_count_hi, cpu_to_le16(count >> 16));
}
void ext4_used_dirs_set(struct super_block *sb,
@@ -2096,16 +2103,16 @@ static int ext4_parse_test_dummy_encryption(const struct fs_parameter *param,
}
#define EXT4_SET_CTX(name) \
-static inline void ctx_set_##name(struct ext4_fs_context *ctx, \
- unsigned long flag) \
+static inline __maybe_unused \
+void ctx_set_##name(struct ext4_fs_context *ctx, unsigned long flag) \
{ \
ctx->mask_s_##name |= flag; \
ctx->vals_s_##name |= flag; \
}
#define EXT4_CLEAR_CTX(name) \
-static inline void ctx_clear_##name(struct ext4_fs_context *ctx, \
- unsigned long flag) \
+static inline __maybe_unused \
+void ctx_clear_##name(struct ext4_fs_context *ctx, unsigned long flag) \
{ \
ctx->mask_s_##name |= flag; \
ctx->vals_s_##name &= ~flag; \
@@ -3030,6 +3037,9 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
SEQ_OPTS_PUTS("mb_optimize_scan=1");
}
+ if (nodefs && !test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS))
+ SEQ_OPTS_PUTS("prefetch_block_bitmaps");
+
ext4_show_quota_options(seq, sb);
return 0;
}
@@ -3709,12 +3719,12 @@ static int ext4_run_li_request(struct ext4_li_request *elr)
ret = 1;
if (!ret) {
- start_time = ktime_get_real_ns();
+ start_time = ktime_get_ns();
ret = ext4_init_inode_table(sb, group,
elr->lr_timeout ? 0 : 1);
trace_ext4_lazy_itable_init(sb, group);
if (elr->lr_timeout == 0) {
- elr->lr_timeout = nsecs_to_jiffies((ktime_get_real_ns() - start_time) *
+ elr->lr_timeout = nsecs_to_jiffies((ktime_get_ns() - start_time) *
EXT4_SB(elr->lr_super)->s_li_wait_mult);
}
elr->lr_next_sched = jiffies + elr->lr_timeout;
@@ -3774,8 +3784,9 @@ static int ext4_lazyinit_thread(void *arg)
cont_thread:
while (true) {
- next_wakeup = MAX_JIFFY_OFFSET;
+ bool next_wakeup_initialized = false;
+ next_wakeup = 0;
mutex_lock(&eli->li_list_mtx);
if (list_empty(&eli->li_request_list)) {
mutex_unlock(&eli->li_list_mtx);
@@ -3788,8 +3799,11 @@ cont_thread:
lr_request);
if (time_before(jiffies, elr->lr_next_sched)) {
- if (time_before(elr->lr_next_sched, next_wakeup))
+ if (!next_wakeup_initialized ||
+ time_before(elr->lr_next_sched, next_wakeup)) {
next_wakeup = elr->lr_next_sched;
+ next_wakeup_initialized = true;
+ }
continue;
}
if (down_read_trylock(&elr->lr_super->s_umount)) {
@@ -3817,16 +3831,18 @@ cont_thread:
elr->lr_next_sched = jiffies +
get_random_u32_below(EXT4_DEF_LI_MAX_START_DELAY * HZ);
}
- if (time_before(elr->lr_next_sched, next_wakeup))
+ if (!next_wakeup_initialized ||
+ time_before(elr->lr_next_sched, next_wakeup)) {
next_wakeup = elr->lr_next_sched;
+ next_wakeup_initialized = true;
+ }
}
mutex_unlock(&eli->li_list_mtx);
try_to_freeze();
cur = jiffies;
- if ((time_after_eq(cur, next_wakeup)) ||
- (MAX_JIFFY_OFFSET == next_wakeup)) {
+ if (!next_wakeup_initialized || time_after_eq(cur, next_wakeup)) {
cond_resched();
continue;
}
@@ -4425,6 +4441,36 @@ static int ext4_handle_clustersize(struct super_block *sb)
return 0;
}
+/*
+ * ext4_atomic_write_init: Initializes filesystem min & max atomic write units.
+ * @sb: super block
+ * TODO: Later add support for bigalloc
+ */
+static void ext4_atomic_write_init(struct super_block *sb)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct block_device *bdev = sb->s_bdev;
+
+ if (!bdev_can_atomic_write(bdev))
+ return;
+
+ if (!ext4_has_feature_extents(sb))
+ return;
+
+ sbi->s_awu_min = max(sb->s_blocksize,
+ bdev_atomic_write_unit_min_bytes(bdev));
+ sbi->s_awu_max = min(sb->s_blocksize,
+ bdev_atomic_write_unit_max_bytes(bdev));
+ if (sbi->s_awu_min && sbi->s_awu_max &&
+ sbi->s_awu_min <= sbi->s_awu_max) {
+ ext4_msg(sb, KERN_NOTICE, "Supports (experimental) DIO atomic writes awu_min: %u, awu_max: %u",
+ sbi->s_awu_min, sbi->s_awu_max);
+ } else {
+ sbi->s_awu_min = 0;
+ sbi->s_awu_max = 0;
+ }
+}
+
static void ext4_fast_commit_init(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -5336,6 +5382,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
spin_lock_init(&sbi->s_bdev_wb_lock);
+ ext4_atomic_write_init(sb);
ext4_fast_commit_init(sb);
sb->s_root = NULL;
@@ -6301,7 +6348,7 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (unlikely(ext4_forced_shutdown(sb)))
- return 0;
+ return -EIO;
trace_ext4_sync_fs(sb, wait);
flush_workqueue(sbi->rsv_conversion_wq);
@@ -6518,8 +6565,12 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb)
goto restore_opts;
}
- if (test_opt2(sb, ABORT))
- ext4_abort(sb, ESHUTDOWN, "Abort forced by user");
+ if ((old_opts.s_mount_opt & EXT4_MOUNT_DELALLOC) &&
+ !test_opt(sb, DELALLOC)) {
+ ext4_msg(sb, KERN_ERR, "can't disable delalloc during remount");
+ err = -EINVAL;
+ goto restore_opts;
+ }
sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
(test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0);
@@ -6689,6 +6740,14 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb)
if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb))
ext4_stop_mmpd(sbi);
+ /*
+ * Handle aborting the filesystem as the last thing during remount to
+ * avoid obsure errors during remount when some option changes fail to
+ * apply due to shutdown filesystem.
+ */
+ if (test_opt2(sb, ABORT))
+ ext4_abort(sb, ESHUTDOWN, "Abort forced by user");
+
return 0;
restore_opts:
@@ -7329,7 +7388,7 @@ static struct file_system_type ext4_fs_type = {
.init_fs_context = ext4_init_fs_context,
.parameters = ext4_param_specs,
.kill_sb = ext4_kill_sb,
- .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP,
+ .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME,
};
MODULE_ALIAS_FS("ext4");
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 94f7b084f601..e3ce763cce18 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -711,7 +711,8 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
}
if (fio->io_wbc && !is_read_io(fio->op))
- wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE);
+ wbc_account_cgroup_owner(fio->io_wbc, page_folio(fio->page),
+ PAGE_SIZE);
inc_page_count(fio->sbi, is_read_io(fio->op) ?
__read_io_type(page) : WB_DATA_TYPE(fio->page, false));
@@ -911,7 +912,8 @@ alloc_new:
}
if (fio->io_wbc)
- wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE);
+ wbc_account_cgroup_owner(fio->io_wbc, page_folio(fio->page),
+ PAGE_SIZE);
inc_page_count(fio->sbi, WB_DATA_TYPE(page, false));
@@ -1011,7 +1013,8 @@ alloc_new:
}
if (fio->io_wbc)
- wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE);
+ wbc_account_cgroup_owner(fio->io_wbc, page_folio(fio->page),
+ PAGE_SIZE);
io->last_block_in_bio = fio->new_blkaddr;
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 321d8ffbab6e..84447d5145aa 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -3038,32 +3038,27 @@ out:
static int __f2fs_ioc_move_range(struct file *filp,
struct f2fs_move_range *range)
{
- struct fd dst;
int err;
if (!(filp->f_mode & FMODE_READ) ||
!(filp->f_mode & FMODE_WRITE))
return -EBADF;
- dst = fdget(range->dst_fd);
- if (!fd_file(dst))
+ CLASS(fd, dst)(range->dst_fd);
+ if (fd_empty(dst))
return -EBADF;
- if (!(fd_file(dst)->f_mode & FMODE_WRITE)) {
- err = -EBADF;
- goto err_out;
- }
+ if (!(fd_file(dst)->f_mode & FMODE_WRITE))
+ return -EBADF;
err = mnt_want_write_file(filp);
if (err)
- goto err_out;
+ return err;
err = f2fs_move_file_range(filp, range->pos_in, fd_file(dst),
range->pos_out, range->len);
mnt_drop_write_file(filp);
-err_out:
- fdput(dst);
return err;
}
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 22dd9dcce7ec..ac77dd912412 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -12,7 +12,6 @@
#include <linux/fs.h>
#include <linux/filelock.h>
#include <linux/file.h>
-#include <linux/fdtable.h>
#include <linux/capability.h>
#include <linux/dnotify.h>
#include <linux/slab.h>
@@ -397,6 +396,9 @@ static long f_dupfd_query(int fd, struct file *filp)
{
CLASS(fd_raw, f)(fd);
+ if (fd_empty(f))
+ return -EBADF;
+
/*
* We can do the 'fdput()' immediately, as the only thing that
* matters is the pointer value which isn't changed by the fdput.
@@ -570,24 +572,21 @@ static int check_fcntl_cmd(unsigned cmd)
SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
{
- struct fd f = fdget_raw(fd);
- long err = -EBADF;
+ CLASS(fd_raw, f)(fd);
+ long err;
- if (!fd_file(f))
- goto out;
+ if (fd_empty(f))
+ return -EBADF;
if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) {
if (!check_fcntl_cmd(cmd))
- goto out1;
+ return -EBADF;
}
err = security_file_fcntl(fd_file(f), cmd, arg);
if (!err)
err = do_fcntl(fd, cmd, arg, fd_file(f));
-out1:
- fdput(f);
-out:
return err;
}
@@ -596,21 +595,21 @@ SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
unsigned long, arg)
{
void __user *argp = (void __user *)arg;
- struct fd f = fdget_raw(fd);
+ CLASS(fd_raw, f)(fd);
struct flock64 flock;
- long err = -EBADF;
+ long err;
- if (!fd_file(f))
- goto out;
+ if (fd_empty(f))
+ return -EBADF;
if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) {
if (!check_fcntl_cmd(cmd))
- goto out1;
+ return -EBADF;
}
err = security_file_fcntl(fd_file(f), cmd, arg);
if (err)
- goto out1;
+ return err;
switch (cmd) {
case F_GETLK64:
@@ -635,9 +634,6 @@ SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
err = do_fcntl(fd, cmd, arg, fd_file(f));
break;
}
-out1:
- fdput(f);
-out:
return err;
}
#endif
@@ -733,21 +729,21 @@ static int fixup_compat_flock(struct flock *flock)
static long do_compat_fcntl64(unsigned int fd, unsigned int cmd,
compat_ulong_t arg)
{
- struct fd f = fdget_raw(fd);
+ CLASS(fd_raw, f)(fd);
struct flock flock;
- long err = -EBADF;
+ long err;
- if (!fd_file(f))
- return err;
+ if (fd_empty(f))
+ return -EBADF;
if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) {
if (!check_fcntl_cmd(cmd))
- goto out_put;
+ return -EBADF;
}
err = security_file_fcntl(fd_file(f), cmd, arg);
if (err)
- goto out_put;
+ return err;
switch (cmd) {
case F_GETLK:
@@ -790,8 +786,6 @@ static long do_compat_fcntl64(unsigned int fd, unsigned int cmd,
err = do_fcntl(fd, cmd, arg, fd_file(f));
break;
}
-out_put:
- fdput(f);
return err;
}
diff --git a/fs/fhandle.c b/fs/fhandle.c
index 82df28d45cd7..5f801139358e 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -139,12 +139,11 @@ static int get_path_from_fd(int fd, struct path *root)
path_get(root);
spin_unlock(&fs->lock);
} else {
- struct fd f = fdget(fd);
- if (!fd_file(f))
+ CLASS(fd, f)(fd);
+ if (fd_empty(f))
return -EBADF;
*root = fd_file(f)->f_path;
path_get(root);
- fdput(f);
}
return 0;
diff --git a/fs/file.c b/fs/file.c
index eb093e736972..fb1011cf6b4a 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -20,10 +20,73 @@
#include <linux/spinlock.h>
#include <linux/rcupdate.h>
#include <linux/close_range.h>
+#include <linux/file_ref.h>
#include <net/sock.h>
#include "internal.h"
+/**
+ * __file_ref_put - Slowpath of file_ref_put()
+ * @ref: Pointer to the reference count
+ * @cnt: Current reference count
+ *
+ * Invoked when the reference count is outside of the valid zone.
+ *
+ * Return:
+ * True if this was the last reference with no future references
+ * possible. This signals the caller that it can safely schedule the
+ * object, which is protected by the reference counter, for
+ * deconstruction.
+ *
+ * False if there are still active references or the put() raced
+ * with a concurrent get()/put() pair. Caller is not allowed to
+ * deconstruct the protected object.
+ */
+bool __file_ref_put(file_ref_t *ref, unsigned long cnt)
+{
+ /* Did this drop the last reference? */
+ if (likely(cnt == FILE_REF_NOREF)) {
+ /*
+ * Carefully try to set the reference count to FILE_REF_DEAD.
+ *
+ * This can fail if a concurrent get() operation has
+ * elevated it again or the corresponding put() even marked
+ * it dead already. Both are valid situations and do not
+ * require a retry. If this fails the caller is not
+ * allowed to deconstruct the object.
+ */
+ if (!atomic_long_try_cmpxchg_release(&ref->refcnt, &cnt, FILE_REF_DEAD))
+ return false;
+
+ /*
+ * The caller can safely schedule the object for
+ * deconstruction. Provide acquire ordering.
+ */
+ smp_acquire__after_ctrl_dep();
+ return true;
+ }
+
+ /*
+ * If the reference count was already in the dead zone, then this
+ * put() operation is imbalanced. Warn, put the reference count back to
+ * DEAD and tell the caller to not deconstruct the object.
+ */
+ if (WARN_ONCE(cnt >= FILE_REF_RELEASED, "imbalanced put on file reference count")) {
+ atomic_long_set(&ref->refcnt, FILE_REF_DEAD);
+ return false;
+ }
+
+ /*
+ * This is a put() operation on a saturated refcount. Restore the
+ * mean saturation value and tell the caller to not deconstruct the
+ * object.
+ */
+ if (cnt > FILE_REF_MAXREF)
+ atomic_long_set(&ref->refcnt, FILE_REF_SATURATED);
+ return false;
+}
+EXPORT_SYMBOL_GPL(__file_ref_put);
+
unsigned int sysctl_nr_open __read_mostly = 1024*1024;
unsigned int sysctl_nr_open_min = BITS_PER_LONG;
/* our min() is unusable in constant expressions ;-/ */
@@ -89,18 +152,11 @@ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt)
* 'unsigned long' in some places, but simply because that is how the Linux
* kernel bitmaps are defined to work: they are not "bits in an array of bytes",
* they are very much "bits in an array of unsigned long".
- *
- * The ALIGN(nr, BITS_PER_LONG) here is for clarity: since we just multiplied
- * by that "1024/sizeof(ptr)" before, we already know there are sufficient
- * clear low bits. Clang seems to realize that, gcc ends up being confused.
- *
- * On a 128-bit machine, the ALIGN() would actually matter. In the meantime,
- * let's consider it documentation (and maybe a test-case for gcc to improve
- * its code generation ;)
*/
-static struct fdtable * alloc_fdtable(unsigned int nr)
+static struct fdtable *alloc_fdtable(unsigned int slots_wanted)
{
struct fdtable *fdt;
+ unsigned int nr;
void *data;
/*
@@ -108,22 +164,32 @@ static struct fdtable * alloc_fdtable(unsigned int nr)
* Allocation steps are keyed to the size of the fdarray, since it
* grows far faster than any of the other dynamic data. We try to fit
* the fdarray into comfortable page-tuned chunks: starting at 1024B
- * and growing in powers of two from there on.
+ * and growing in powers of two from there on. Since we called only
+ * with slots_wanted > BITS_PER_LONG (embedded instance in files->fdtab
+ * already gives BITS_PER_LONG slots), the above boils down to
+ * 1. use the smallest power of two large enough to give us that many
+ * slots.
+ * 2. on 32bit skip 64 and 128 - the minimal capacity we want there is
+ * 256 slots (i.e. 1Kb fd array).
+ * 3. on 64bit don't skip anything, 1Kb fd array means 128 slots there
+ * and we are never going to be asked for 64 or less.
*/
- nr /= (1024 / sizeof(struct file *));
- nr = roundup_pow_of_two(nr + 1);
- nr *= (1024 / sizeof(struct file *));
- nr = ALIGN(nr, BITS_PER_LONG);
+ if (IS_ENABLED(CONFIG_32BIT) && slots_wanted < 256)
+ nr = 256;
+ else
+ nr = roundup_pow_of_two(slots_wanted);
/*
* Note that this can drive nr *below* what we had passed if sysctl_nr_open
- * had been set lower between the check in expand_files() and here. Deal
- * with that in caller, it's cheaper that way.
+ * had been set lower between the check in expand_files() and here.
*
* We make sure that nr remains a multiple of BITS_PER_LONG - otherwise
* bitmaps handling below becomes unpleasant, to put it mildly...
*/
- if (unlikely(nr > sysctl_nr_open))
- nr = ((sysctl_nr_open - 1) | (BITS_PER_LONG - 1)) + 1;
+ if (unlikely(nr > sysctl_nr_open)) {
+ nr = round_down(sysctl_nr_open, BITS_PER_LONG);
+ if (nr < slots_wanted)
+ return ERR_PTR(-EMFILE);
+ }
fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL_ACCOUNT);
if (!fdt)
@@ -152,14 +218,14 @@ out_arr:
out_fdt:
kfree(fdt);
out:
- return NULL;
+ return ERR_PTR(-ENOMEM);
}
/*
* Expand the file descriptor table.
* This function will allocate a new fdtable and both fd array and fdset, of
* the given size.
- * Return <0 error code on error; 1 on successful completion.
+ * Return <0 error code on error; 0 on successful completion.
* The files->file_lock should be held on entry, and will be held on exit.
*/
static int expand_fdtable(struct files_struct *files, unsigned int nr)
@@ -169,7 +235,7 @@ static int expand_fdtable(struct files_struct *files, unsigned int nr)
struct fdtable *new_fdt, *cur_fdt;
spin_unlock(&files->file_lock);
- new_fdt = alloc_fdtable(nr);
+ new_fdt = alloc_fdtable(nr + 1);
/* make sure all fd_install() have seen resize_in_progress
* or have finished their rcu_read_lock_sched() section.
@@ -178,16 +244,8 @@ static int expand_fdtable(struct files_struct *files, unsigned int nr)
synchronize_rcu();
spin_lock(&files->file_lock);
- if (!new_fdt)
- return -ENOMEM;
- /*
- * extremely unlikely race - sysctl_nr_open decreased between the check in
- * caller and alloc_fdtable(). Cheaper to catch it here...
- */
- if (unlikely(new_fdt->max_fds <= nr)) {
- __free_fdtable(new_fdt);
- return -EMFILE;
- }
+ if (IS_ERR(new_fdt))
+ return PTR_ERR(new_fdt);
cur_fdt = files_fdtable(files);
BUG_ON(nr < cur_fdt->max_fds);
copy_fdtable(new_fdt, cur_fdt);
@@ -196,15 +254,14 @@ static int expand_fdtable(struct files_struct *files, unsigned int nr)
call_rcu(&cur_fdt->rcu, free_fdtable_rcu);
/* coupled with smp_rmb() in fd_install() */
smp_wmb();
- return 1;
+ return 0;
}
/*
* Expand files.
* This function will expand the file structures, if the requested size exceeds
* the current capacity and there is room for expansion.
- * Return <0 error code on error; 0 when nothing done; 1 when files were
- * expanded and execution may have blocked.
+ * Return <0 error code on error; 0 on success.
* The files->file_lock should be held on entry, and will be held on exit.
*/
static int expand_files(struct files_struct *files, unsigned int nr)
@@ -212,14 +269,14 @@ static int expand_files(struct files_struct *files, unsigned int nr)
__acquires(files->file_lock)
{
struct fdtable *fdt;
- int expanded = 0;
+ int error;
repeat:
fdt = files_fdtable(files);
/* Do we need to expand? */
if (nr < fdt->max_fds)
- return expanded;
+ return 0;
/* Can we expand? */
if (nr >= sysctl_nr_open)
@@ -227,7 +284,6 @@ repeat:
if (unlikely(files->resize_in_progress)) {
spin_unlock(&files->file_lock);
- expanded = 1;
wait_event(files->resize_wait, !files->resize_in_progress);
spin_lock(&files->file_lock);
goto repeat;
@@ -235,27 +291,28 @@ repeat:
/* All good, so we try */
files->resize_in_progress = true;
- expanded = expand_fdtable(files, nr);
+ error = expand_fdtable(files, nr);
files->resize_in_progress = false;
wake_up_all(&files->resize_wait);
- return expanded;
-}
-
-static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt)
-{
- __set_bit(fd, fdt->close_on_exec);
+ return error;
}
-static inline void __clear_close_on_exec(unsigned int fd, struct fdtable *fdt)
+static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt,
+ bool set)
{
- if (test_bit(fd, fdt->close_on_exec))
- __clear_bit(fd, fdt->close_on_exec);
+ if (set) {
+ __set_bit(fd, fdt->close_on_exec);
+ } else {
+ if (test_bit(fd, fdt->close_on_exec))
+ __clear_bit(fd, fdt->close_on_exec);
+ }
}
-static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt)
+static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt, bool set)
{
__set_bit(fd, fdt->open_fds);
+ __set_close_on_exec(fd, fdt, set);
fd /= BITS_PER_LONG;
if (!~fdt->open_fds[fd])
__set_bit(fd, fdt->full_fds_bits);
@@ -264,7 +321,9 @@ static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt)
static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt)
{
__clear_bit(fd, fdt->open_fds);
- __clear_bit(fd / BITS_PER_LONG, fdt->full_fds_bits);
+ fd /= BITS_PER_LONG;
+ if (test_bit(fd, fdt->full_fds_bits))
+ __clear_bit(fd, fdt->full_fds_bits);
}
static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt)
@@ -306,7 +365,6 @@ struct files_struct *dup_fd(struct files_struct *oldf, struct fd_range *punch_ho
struct file **old_fds, **new_fds;
unsigned int open_files, i;
struct fdtable *old_fdt, *new_fdt;
- int error;
newf = kmem_cache_alloc(files_cachep, GFP_KERNEL);
if (!newf)
@@ -338,17 +396,10 @@ struct files_struct *dup_fd(struct files_struct *oldf, struct fd_range *punch_ho
if (new_fdt != &newf->fdtab)
__free_fdtable(new_fdt);
- new_fdt = alloc_fdtable(open_files - 1);
- if (!new_fdt) {
- error = -ENOMEM;
- goto out_release;
- }
-
- /* beyond sysctl_nr_open; nothing to do */
- if (unlikely(new_fdt->max_fds < open_files)) {
- __free_fdtable(new_fdt);
- error = -EMFILE;
- goto out_release;
+ new_fdt = alloc_fdtable(open_files);
+ if (IS_ERR(new_fdt)) {
+ kmem_cache_free(files_cachep, newf);
+ return ERR_CAST(new_fdt);
}
/*
@@ -389,10 +440,6 @@ struct files_struct *dup_fd(struct files_struct *oldf, struct fd_range *punch_ho
rcu_assign_pointer(newf->fdt, new_fdt);
return newf;
-
-out_release:
- kmem_cache_free(files_cachep, newf);
- return ERR_PTR(error);
}
static struct fdtable *close_files(struct files_struct * files)
@@ -413,7 +460,7 @@ static struct fdtable *close_files(struct files_struct * files)
set = fdt->open_fds[j++];
while (set) {
if (set & 1) {
- struct file * file = xchg(&fdt->fd[i], NULL);
+ struct file *file = fdt->fd[i];
if (file) {
filp_close(file, files);
cond_resched();
@@ -470,6 +517,15 @@ static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start)
unsigned int maxfd = fdt->max_fds; /* always multiple of BITS_PER_LONG */
unsigned int maxbit = maxfd / BITS_PER_LONG;
unsigned int bitbit = start / BITS_PER_LONG;
+ unsigned int bit;
+
+ /*
+ * Try to avoid looking at the second level bitmap
+ */
+ bit = find_next_zero_bit(&fdt->open_fds[bitbit], BITS_PER_LONG,
+ start & (BITS_PER_LONG - 1));
+ if (bit < BITS_PER_LONG)
+ return bit + bitbit * BITS_PER_LONG;
bitbit = find_next_zero_bit(fdt->full_fds_bits, maxbit, bitbit) * BITS_PER_LONG;
if (bitbit >= maxfd)
@@ -496,7 +552,7 @@ repeat:
if (fd < files->next_fd)
fd = files->next_fd;
- if (fd < fdt->max_fds)
+ if (likely(fd < fdt->max_fds))
fd = find_next_fd(fdt, fd);
/*
@@ -504,36 +560,22 @@ repeat:
* will limit the total number of files that can be opened.
*/
error = -EMFILE;
- if (fd >= end)
+ if (unlikely(fd >= end))
goto out;
- error = expand_files(files, fd);
- if (error < 0)
- goto out;
+ if (unlikely(fd >= fdt->max_fds)) {
+ error = expand_files(files, fd);
+ if (error < 0)
+ goto out;
- /*
- * If we needed to expand the fs array we
- * might have blocked - try again.
- */
- if (error)
goto repeat;
+ }
if (start <= files->next_fd)
files->next_fd = fd + 1;
- __set_open_fd(fd, fdt);
- if (flags & O_CLOEXEC)
- __set_close_on_exec(fd, fdt);
- else
- __clear_close_on_exec(fd, fdt);
+ __set_open_fd(fd, fdt, flags & O_CLOEXEC);
error = fd;
-#if 1
- /* Sanity check */
- if (rcu_access_pointer(fdt->fd[fd]) != NULL) {
- printk(KERN_WARNING "alloc_fd: slot %d not NULL!\n", fd);
- rcu_assign_pointer(fdt->fd[fd], NULL);
- }
-#endif
out:
spin_unlock(&files->file_lock);
@@ -599,7 +641,7 @@ void fd_install(unsigned int fd, struct file *file)
rcu_read_unlock_sched();
spin_lock(&files->file_lock);
fdt = files_fdtable(files);
- BUG_ON(fdt->fd[fd] != NULL);
+ WARN_ON(fdt->fd[fd] != NULL);
rcu_assign_pointer(fdt->fd[fd], file);
spin_unlock(&files->file_lock);
return;
@@ -713,7 +755,7 @@ static inline void __range_close(struct files_struct *files, unsigned int fd,
}
/**
- * __close_range() - Close all file descriptors in a given range.
+ * sys_close_range() - Close all file descriptors in a given range.
*
* @fd: starting file descriptor to close
* @max_fd: last file descriptor to close
@@ -721,8 +763,10 @@ static inline void __range_close(struct files_struct *files, unsigned int fd,
*
* This closes a range of file descriptors. All file descriptors
* from @fd up to and including @max_fd are closed.
+ * Currently, errors to close a given file descriptor are ignored.
*/
-int __close_range(unsigned fd, unsigned max_fd, unsigned int flags)
+SYSCALL_DEFINE3(close_range, unsigned int, fd, unsigned int, max_fd,
+ unsigned int, flags)
{
struct task_struct *me = current;
struct files_struct *cur_fds = me->files, *fds = NULL;
@@ -839,7 +883,7 @@ static struct file *__get_file_rcu(struct file __rcu **f)
if (!file)
return NULL;
- if (unlikely(!atomic_long_inc_not_zero(&file->f_count)))
+ if (unlikely(!file_ref_get(&file->f_ref)))
return ERR_PTR(-EAGAIN);
file_reloaded = rcu_dereference_raw(*f);
@@ -853,8 +897,8 @@ static struct file *__get_file_rcu(struct file __rcu **f)
OPTIMIZER_HIDE_VAR(file_reloaded_cmp);
/*
- * atomic_long_inc_not_zero() above provided a full memory
- * barrier when we acquired a reference.
+ * file_ref_get() above provided a full memory barrier when we
+ * acquired a reference.
*
* This is paired with the write barrier from assigning to the
* __rcu protected file pointer so that if that pointer still
@@ -952,11 +996,11 @@ static inline struct file *__fget_files_rcu(struct files_struct *files,
* We need to confirm it by incrementing the refcount
* and then check the lookup again.
*
- * atomic_long_inc_not_zero() gives us a full memory
- * barrier. We only really need an 'acquire' one to
- * protect the loads below, but we don't have that.
+ * file_ref_get() gives us a full memory barrier. We
+ * only really need an 'acquire' one to protect the
+ * loads below, but we don't have that.
*/
- if (unlikely(!atomic_long_inc_not_zero(&file->f_count)))
+ if (unlikely(!file_ref_get(&file->f_ref)))
continue;
/*
@@ -1037,29 +1081,7 @@ struct file *fget_task(struct task_struct *task, unsigned int fd)
return file;
}
-struct file *lookup_fdget_rcu(unsigned int fd)
-{
- return __fget_files_rcu(current->files, fd, 0);
-
-}
-EXPORT_SYMBOL_GPL(lookup_fdget_rcu);
-
-struct file *task_lookup_fdget_rcu(struct task_struct *task, unsigned int fd)
-{
- /* Must be called with rcu_read_lock held */
- struct files_struct *files;
- struct file *file = NULL;
-
- task_lock(task);
- files = task->files;
- if (files)
- file = __fget_files_rcu(files, fd, 0);
- task_unlock(task);
-
- return file;
-}
-
-struct file *task_lookup_next_fdget_rcu(struct task_struct *task, unsigned int *ret_fd)
+struct file *fget_task_next(struct task_struct *task, unsigned int *ret_fd)
{
/* Must be called with rcu_read_lock held */
struct files_struct *files;
@@ -1069,17 +1091,19 @@ struct file *task_lookup_next_fdget_rcu(struct task_struct *task, unsigned int *
task_lock(task);
files = task->files;
if (files) {
+ rcu_read_lock();
for (; fd < files_fdtable(files)->max_fds; fd++) {
file = __fget_files_rcu(files, fd, 0);
if (file)
break;
}
+ rcu_read_unlock();
}
task_unlock(task);
*ret_fd = fd;
return file;
}
-EXPORT_SYMBOL(task_lookup_next_fdget_rcu);
+EXPORT_SYMBOL(fget_task_next);
/*
* Lightweight file lookup - no refcnt increment if fd table isn't shared.
@@ -1096,6 +1120,13 @@ EXPORT_SYMBOL(task_lookup_next_fdget_rcu);
*
* The fput_needed flag returned by fget_light should be passed to the
* corresponding fput_light.
+ *
+ * (As an exception to rule 2, you can call filp_close between fget_light and
+ * fput_light provided that you capture a real refcount with get_file before
+ * the call to filp_close, and ensure that this real refcount is fput *after*
+ * the fput_light call.)
+ *
+ * See also the documentation in rust/kernel/file.rs.
*/
static inline struct fd __fget_light(unsigned int fd, fmode_t mask)
{
@@ -1176,13 +1207,8 @@ void __f_unlock_pos(struct file *f)
void set_close_on_exec(unsigned int fd, int flag)
{
struct files_struct *files = current->files;
- struct fdtable *fdt;
spin_lock(&files->file_lock);
- fdt = files_fdtable(files);
- if (flag)
- __set_close_on_exec(fd, fdt);
- else
- __clear_close_on_exec(fd, fdt);
+ __set_close_on_exec(fd, files_fdtable(files), flag);
spin_unlock(&files->file_lock);
}
@@ -1223,11 +1249,7 @@ __releases(&files->file_lock)
goto Ebusy;
get_file(file);
rcu_assign_pointer(fdt->fd[fd], file);
- __set_open_fd(fd, fdt);
- if (flags & O_CLOEXEC)
- __set_close_on_exec(fd, fdt);
- else
- __clear_close_on_exec(fd, fdt);
+ __set_open_fd(fd, fdt, flags & O_CLOEXEC);
spin_unlock(&files->file_lock);
if (tofree)
diff --git a/fs/file_table.c b/fs/file_table.c
index eed5ffad9997..976736be47cb 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -9,7 +9,6 @@
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/file.h>
-#include <linux/fdtable.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/fs.h>
@@ -40,13 +39,17 @@ static struct files_stat_struct files_stat = {
/* SLAB cache for file structures */
static struct kmem_cache *filp_cachep __ro_after_init;
+static struct kmem_cache *bfilp_cachep __ro_after_init;
static struct percpu_counter nr_files __cacheline_aligned_in_smp;
/* Container for backing file with optional user path */
struct backing_file {
struct file file;
- struct path user_path;
+ union {
+ struct path user_path;
+ freeptr_t bf_freeptr;
+ };
};
static inline struct backing_file *backing_file(struct file *f)
@@ -68,7 +71,7 @@ static inline void file_free(struct file *f)
put_cred(f->f_cred);
if (unlikely(f->f_mode & FMODE_BACKING)) {
path_put(backing_file_user_path(f));
- kfree(backing_file(f));
+ kmem_cache_free(bfilp_cachep, backing_file(f));
} else {
kmem_cache_free(filp_cachep, f);
}
@@ -165,16 +168,32 @@ static int init_file(struct file *f, int flags, const struct cred *cred)
* the respective member when opening the file.
*/
mutex_init(&f->f_pos_lock);
- f->f_flags = flags;
- f->f_mode = OPEN_FMODE(flags);
- /* f->f_version: 0 */
+ memset(&f->f_path, 0, sizeof(f->f_path));
+ memset(&f->f_ra, 0, sizeof(f->f_ra));
+
+ f->f_flags = flags;
+ f->f_mode = OPEN_FMODE(flags);
+
+ f->f_op = NULL;
+ f->f_mapping = NULL;
+ f->private_data = NULL;
+ f->f_inode = NULL;
+ f->f_owner = NULL;
+#ifdef CONFIG_EPOLL
+ f->f_ep = NULL;
+#endif
+
+ f->f_iocb_flags = 0;
+ f->f_pos = 0;
+ f->f_wb_err = 0;
+ f->f_sb_err = 0;
/*
* We're SLAB_TYPESAFE_BY_RCU so initialize f_count last. While
* fget-rcu pattern users need to be able to handle spurious
* refcount bumps we should reinitialize the reused file first.
*/
- atomic_long_set(&f->f_count, 1);
+ file_ref_init(&f->f_ref, 1);
return 0;
}
@@ -206,7 +225,7 @@ struct file *alloc_empty_file(int flags, const struct cred *cred)
goto over;
}
- f = kmem_cache_zalloc(filp_cachep, GFP_KERNEL);
+ f = kmem_cache_alloc(filp_cachep, GFP_KERNEL);
if (unlikely(!f))
return ERR_PTR(-ENOMEM);
@@ -240,7 +259,7 @@ struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred)
struct file *f;
int error;
- f = kmem_cache_zalloc(filp_cachep, GFP_KERNEL);
+ f = kmem_cache_alloc(filp_cachep, GFP_KERNEL);
if (unlikely(!f))
return ERR_PTR(-ENOMEM);
@@ -267,13 +286,13 @@ struct file *alloc_empty_backing_file(int flags, const struct cred *cred)
struct backing_file *ff;
int error;
- ff = kzalloc(sizeof(struct backing_file), GFP_KERNEL);
+ ff = kmem_cache_alloc(bfilp_cachep, GFP_KERNEL);
if (unlikely(!ff))
return ERR_PTR(-ENOMEM);
error = init_file(&ff->file, flags, cred);
if (unlikely(error)) {
- kfree(ff);
+ kmem_cache_free(bfilp_cachep, ff);
return ERR_PTR(error);
}
@@ -479,7 +498,7 @@ static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput);
void fput(struct file *file)
{
- if (atomic_long_dec_and_test(&file->f_count)) {
+ if (file_ref_put(&file->f_ref)) {
struct task_struct *task = current;
if (unlikely(!(file->f_mode & (FMODE_BACKING | FMODE_OPENED)))) {
@@ -512,7 +531,7 @@ void fput(struct file *file)
*/
void __fput_sync(struct file *file)
{
- if (atomic_long_dec_and_test(&file->f_count))
+ if (file_ref_put(&file->f_ref))
__fput(file);
}
@@ -529,6 +548,11 @@ void __init files_init(void)
filp_cachep = kmem_cache_create("filp", sizeof(struct file), &args,
SLAB_HWCACHE_ALIGN | SLAB_PANIC |
SLAB_ACCOUNT | SLAB_TYPESAFE_BY_RCU);
+
+ args.freeptr_offset = offsetof(struct backing_file, bf_freeptr);
+ bfilp_cachep = kmem_cache_create("bfilp", sizeof(struct backing_file),
+ &args, SLAB_HWCACHE_ALIGN | SLAB_PANIC |
+ SLAB_ACCOUNT | SLAB_TYPESAFE_BY_RCU);
percpu_counter_init(&nr_files, 0, GFP_KERNEL);
}
diff --git a/fs/freevxfs/vxfs_dir.h b/fs/freevxfs/vxfs_dir.h
index fbcd603365ad..8c67627f2a3d 100644
--- a/fs/freevxfs/vxfs_dir.h
+++ b/fs/freevxfs/vxfs_dir.h
@@ -25,7 +25,7 @@
struct vxfs_dirblk {
__fs16 d_free; /* free space in dirblock */
__fs16 d_nhash; /* no of hash chains */
- __fs16 d_hash[1]; /* hash chain */
+ __fs16 d_hash[]; /* hash chain */
};
/*
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index d8bec3c1bb1f..3cd99e2dc6ac 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -290,7 +290,6 @@ void __inode_attach_wb(struct inode *inode, struct folio *folio)
if (unlikely(cmpxchg(&inode->i_wb, NULL, wb)))
wb_put(wb);
}
-EXPORT_SYMBOL_GPL(__inode_attach_wb);
/**
* inode_cgwb_move_to_attached - put the inode onto wb->b_attached list
@@ -731,8 +730,9 @@ bool cleanup_offline_cgwb(struct bdi_writeback *wb)
* writeback completion, wbc_detach_inode() should be called. This is used
* to track the cgroup writeback context.
*/
-void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
- struct inode *inode)
+static void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
+ struct inode *inode)
+ __releases(&inode->i_lock)
{
if (!inode_cgwb_enabled(inode)) {
spin_unlock(&inode->i_lock);
@@ -762,7 +762,24 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
if (unlikely(wb_dying(wbc->wb) && !css_is_dying(wbc->wb->memcg_css)))
inode_switch_wbs(inode, wbc->wb_id);
}
-EXPORT_SYMBOL_GPL(wbc_attach_and_unlock_inode);
+
+/**
+ * wbc_attach_fdatawrite_inode - associate wbc and inode for fdatawrite
+ * @wbc: writeback_control of interest
+ * @inode: target inode
+ *
+ * This function is to be used by __filemap_fdatawrite_range(), which is an
+ * alternative entry point into writeback code, and first ensures @inode is
+ * associated with a bdi_writeback and attaches it to @wbc.
+ */
+void wbc_attach_fdatawrite_inode(struct writeback_control *wbc,
+ struct inode *inode)
+{
+ spin_lock(&inode->i_lock);
+ inode_attach_wb(inode, NULL);
+ wbc_attach_and_unlock_inode(wbc, inode);
+}
+EXPORT_SYMBOL_GPL(wbc_attach_fdatawrite_inode);
/**
* wbc_detach_inode - disassociate wbc from inode and perform foreign detection
@@ -890,17 +907,16 @@ EXPORT_SYMBOL_GPL(wbc_detach_inode);
/**
* wbc_account_cgroup_owner - account writeback to update inode cgroup ownership
* @wbc: writeback_control of the writeback in progress
- * @page: page being written out
+ * @folio: folio being written out
* @bytes: number of bytes being written out
*
- * @bytes from @page are about to written out during the writeback
+ * @bytes from @folio are about to written out during the writeback
* controlled by @wbc. Keep the book for foreign inode detection. See
* wbc_detach_inode().
*/
-void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page,
+void wbc_account_cgroup_owner(struct writeback_control *wbc, struct folio *folio,
size_t bytes)
{
- struct folio *folio;
struct cgroup_subsys_state *css;
int id;
@@ -913,7 +929,6 @@ void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page,
if (!wbc->wb || wbc->no_cgroup_owner)
return;
- folio = page_folio(page);
css = mem_cgroup_css_from_folio(folio);
/* dead cgroups shouldn't contribute to inode ownership arbitration */
if (!(css->flags & CSS_ONLINE))
@@ -1227,6 +1242,13 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi,
}
}
+static inline void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
+ struct inode *inode)
+ __releases(&inode->i_lock)
+{
+ spin_unlock(&inode->i_lock);
+}
+
#endif /* CONFIG_CGROUP_WRITEBACK */
/*
diff --git a/fs/fs_parser.c b/fs/fs_parser.c
index 24727ec34e5a..16fa61ef56bf 100644
--- a/fs/fs_parser.c
+++ b/fs/fs_parser.c
@@ -156,6 +156,7 @@ int fs_lookup_param(struct fs_context *fc,
f = getname_kernel(param->string);
if (IS_ERR(f))
return PTR_ERR(f);
+ param->dirfd = AT_FDCWD;
put_f = true;
break;
case fs_value_is_filename:
@@ -308,6 +309,26 @@ int fs_param_is_fd(struct p_log *log, const struct fs_parameter_spec *p,
}
EXPORT_SYMBOL(fs_param_is_fd);
+int fs_param_is_file_or_string(struct p_log *log,
+ const struct fs_parameter_spec *p,
+ struct fs_parameter *param,
+ struct fs_parse_result *result)
+{
+ switch (param->type) {
+ case fs_value_is_string:
+ return fs_param_is_string(log, p, param, result);
+ case fs_value_is_file:
+ result->uint_32 = param->dirfd;
+ if (result->uint_32 <= INT_MAX)
+ return 0;
+ break;
+ default:
+ break;
+ }
+ return fs_param_bad_value(log, param);
+}
+EXPORT_SYMBOL(fs_param_is_file_or_string);
+
int fs_param_is_uid(struct p_log *log, const struct fs_parameter_spec *p,
struct fs_parameter *param, struct fs_parse_result *result)
{
diff --git a/fs/fsopen.c b/fs/fsopen.c
index 6cef3deccded..094a7f510edf 100644
--- a/fs/fsopen.c
+++ b/fs/fsopen.c
@@ -349,7 +349,6 @@ SYSCALL_DEFINE5(fsconfig,
int, aux)
{
struct fs_context *fc;
- struct fd f;
int ret;
int lookup_flags = 0;
@@ -392,12 +391,11 @@ SYSCALL_DEFINE5(fsconfig,
return -EOPNOTSUPP;
}
- f = fdget(fd);
- if (!fd_file(f))
+ CLASS(fd, f)(fd);
+ if (fd_empty(f))
return -EBADF;
- ret = -EINVAL;
if (fd_file(f)->f_op != &fscontext_fops)
- goto out_f;
+ return -EINVAL;
fc = fd_file(f)->private_data;
if (fc->ops == &legacy_fs_context_ops) {
@@ -407,17 +405,14 @@ SYSCALL_DEFINE5(fsconfig,
case FSCONFIG_SET_PATH_EMPTY:
case FSCONFIG_SET_FD:
case FSCONFIG_CMD_CREATE_EXCL:
- ret = -EOPNOTSUPP;
- goto out_f;
+ return -EOPNOTSUPP;
}
}
if (_key) {
param.key = strndup_user(_key, 256);
- if (IS_ERR(param.key)) {
- ret = PTR_ERR(param.key);
- goto out_f;
- }
+ if (IS_ERR(param.key))
+ return PTR_ERR(param.key);
}
switch (cmd) {
@@ -496,7 +491,5 @@ SYSCALL_DEFINE5(fsconfig,
}
out_key:
kfree(param.key);
-out_f:
- fdput(f);
return ret;
}
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 1f64ae6d7a69..0723c6344b20 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -2371,13 +2371,12 @@ static long fuse_dev_ioctl_clone(struct file *file, __u32 __user *argp)
int res;
int oldfd;
struct fuse_dev *fud = NULL;
- struct fd f;
if (get_user(oldfd, argp))
return -EFAULT;
- f = fdget(oldfd);
- if (!fd_file(f))
+ CLASS(fd, f)(oldfd);
+ if (fd_empty(f))
return -EINVAL;
/*
@@ -2394,7 +2393,6 @@ static long fuse_dev_ioctl_clone(struct file *file, __u32 __user *argp)
mutex_unlock(&fuse_mutex);
}
- fdput(f);
return res;
}
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
index d418d8b5367f..3334c394ce9c 100644
--- a/fs/gfs2/export.c
+++ b/fs/gfs2/export.c
@@ -190,6 +190,5 @@ const struct export_operations gfs2_export_ops = {
.fh_to_parent = gfs2_fh_to_parent,
.get_name = gfs2_get_name,
.get_parent = gfs2_get_parent,
- .flags = EXPORT_OP_ASYNC_LOCK,
};
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index f7dd64856c9b..1e73cf87ff88 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -1586,6 +1586,7 @@ const struct file_operations gfs2_file_fops = {
.splice_write = gfs2_file_splice_write,
.setlease = simple_nosetlease,
.fallocate = gfs2_fallocate,
+ .fop_flags = FOP_ASYNC_LOCK,
};
const struct file_operations gfs2_dir_fops = {
@@ -1598,6 +1599,7 @@ const struct file_operations gfs2_dir_fops = {
.lock = gfs2_lock,
.flock = gfs2_flock,
.llseek = default_llseek,
+ .fop_flags = FOP_ASYNC_LOCK,
};
#endif /* CONFIG_GFS2_FS_LOCKING_DLM */
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 269c3bc7fced..4701c4aafbf4 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -34,7 +34,6 @@
#include <linux/lockref.h>
#include <linux/rhashtable.h>
#include <linux/pid_namespace.h>
-#include <linux/fdtable.h>
#include <linux/file.h>
#include "gfs2.h"
@@ -2768,25 +2767,18 @@ static struct file *gfs2_glockfd_next_file(struct gfs2_glockfd_iter *i)
i->file = NULL;
}
- rcu_read_lock();
for(;; i->fd++) {
- struct inode *inode;
-
- i->file = task_lookup_next_fdget_rcu(i->task, &i->fd);
+ i->file = fget_task_next(i->task, &i->fd);
if (!i->file) {
i->fd = 0;
break;
}
- inode = file_inode(i->file);
- if (inode->i_sb == i->sb)
+ if (file_inode(i->file)->i_sb == i->sb)
break;
- rcu_read_unlock();
fput(i->file);
- rcu_read_lock();
}
- rcu_read_unlock();
return i->file;
}
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index eeac99765f0d..3bee9b5dba5e 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -15,10 +15,11 @@
#include <linux/module.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
#include <linux/mount.h>
#include <linux/init.h>
#include <linux/nls.h>
-#include <linux/parser.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/vfs.h>
@@ -111,21 +112,24 @@ static int hfs_statfs(struct dentry *dentry, struct kstatfs *buf)
return 0;
}
-static int hfs_remount(struct super_block *sb, int *flags, char *data)
+static int hfs_reconfigure(struct fs_context *fc)
{
+ struct super_block *sb = fc->root->d_sb;
+
sync_filesystem(sb);
- *flags |= SB_NODIRATIME;
- if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb))
+ fc->sb_flags |= SB_NODIRATIME;
+ if ((bool)(fc->sb_flags & SB_RDONLY) == sb_rdonly(sb))
return 0;
- if (!(*flags & SB_RDONLY)) {
+
+ if (!(fc->sb_flags & SB_RDONLY)) {
if (!(HFS_SB(sb)->mdb->drAtrb & cpu_to_be16(HFS_SB_ATTRIB_UNMNT))) {
pr_warn("filesystem was not cleanly unmounted, running fsck.hfs is recommended. leaving read-only.\n");
sb->s_flags |= SB_RDONLY;
- *flags |= SB_RDONLY;
+ fc->sb_flags |= SB_RDONLY;
} else if (HFS_SB(sb)->mdb->drAtrb & cpu_to_be16(HFS_SB_ATTRIB_SLOCK)) {
pr_warn("filesystem is marked locked, leaving read-only.\n");
sb->s_flags |= SB_RDONLY;
- *flags |= SB_RDONLY;
+ fc->sb_flags |= SB_RDONLY;
}
}
return 0;
@@ -180,7 +184,6 @@ static const struct super_operations hfs_super_operations = {
.put_super = hfs_put_super,
.sync_fs = hfs_sync_fs,
.statfs = hfs_statfs,
- .remount_fs = hfs_remount,
.show_options = hfs_show_options,
};
@@ -188,181 +191,112 @@ enum {
opt_uid, opt_gid, opt_umask, opt_file_umask, opt_dir_umask,
opt_part, opt_session, opt_type, opt_creator, opt_quiet,
opt_codepage, opt_iocharset,
- opt_err
};
-static const match_table_t tokens = {
- { opt_uid, "uid=%u" },
- { opt_gid, "gid=%u" },
- { opt_umask, "umask=%o" },
- { opt_file_umask, "file_umask=%o" },
- { opt_dir_umask, "dir_umask=%o" },
- { opt_part, "part=%u" },
- { opt_session, "session=%u" },
- { opt_type, "type=%s" },
- { opt_creator, "creator=%s" },
- { opt_quiet, "quiet" },
- { opt_codepage, "codepage=%s" },
- { opt_iocharset, "iocharset=%s" },
- { opt_err, NULL }
+static const struct fs_parameter_spec hfs_param_spec[] = {
+ fsparam_u32 ("uid", opt_uid),
+ fsparam_u32 ("gid", opt_gid),
+ fsparam_u32oct ("umask", opt_umask),
+ fsparam_u32oct ("file_umask", opt_file_umask),
+ fsparam_u32oct ("dir_umask", opt_dir_umask),
+ fsparam_u32 ("part", opt_part),
+ fsparam_u32 ("session", opt_session),
+ fsparam_string ("type", opt_type),
+ fsparam_string ("creator", opt_creator),
+ fsparam_flag ("quiet", opt_quiet),
+ fsparam_string ("codepage", opt_codepage),
+ fsparam_string ("iocharset", opt_iocharset),
+ {}
};
-static inline int match_fourchar(substring_t *arg, u32 *result)
-{
- if (arg->to - arg->from != 4)
- return -EINVAL;
- memcpy(result, arg->from, 4);
- return 0;
-}
-
/*
- * parse_options()
+ * hfs_parse_param()
*
- * adapted from linux/fs/msdos/inode.c written 1992,93 by Werner Almesberger
- * This function is called by hfs_read_super() to parse the mount options.
+ * This function is called by the vfs to parse the mount options.
*/
-static int parse_options(char *options, struct hfs_sb_info *hsb)
+static int hfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
- char *p;
- substring_t args[MAX_OPT_ARGS];
- int tmp, token;
-
- /* initialize the sb with defaults */
- hsb->s_uid = current_uid();
- hsb->s_gid = current_gid();
- hsb->s_file_umask = 0133;
- hsb->s_dir_umask = 0022;
- hsb->s_type = hsb->s_creator = cpu_to_be32(0x3f3f3f3f); /* == '????' */
- hsb->s_quiet = 0;
- hsb->part = -1;
- hsb->session = -1;
-
- if (!options)
- return 1;
-
- while ((p = strsep(&options, ",")) != NULL) {
- if (!*p)
- continue;
-
- token = match_token(p, tokens, args);
- switch (token) {
- case opt_uid:
- if (match_int(&args[0], &tmp)) {
- pr_err("uid requires an argument\n");
- return 0;
- }
- hsb->s_uid = make_kuid(current_user_ns(), (uid_t)tmp);
- if (!uid_valid(hsb->s_uid)) {
- pr_err("invalid uid %d\n", tmp);
- return 0;
- }
- break;
- case opt_gid:
- if (match_int(&args[0], &tmp)) {
- pr_err("gid requires an argument\n");
- return 0;
- }
- hsb->s_gid = make_kgid(current_user_ns(), (gid_t)tmp);
- if (!gid_valid(hsb->s_gid)) {
- pr_err("invalid gid %d\n", tmp);
- return 0;
- }
- break;
- case opt_umask:
- if (match_octal(&args[0], &tmp)) {
- pr_err("umask requires a value\n");
- return 0;
- }
- hsb->s_file_umask = (umode_t)tmp;
- hsb->s_dir_umask = (umode_t)tmp;
- break;
- case opt_file_umask:
- if (match_octal(&args[0], &tmp)) {
- pr_err("file_umask requires a value\n");
- return 0;
- }
- hsb->s_file_umask = (umode_t)tmp;
- break;
- case opt_dir_umask:
- if (match_octal(&args[0], &tmp)) {
- pr_err("dir_umask requires a value\n");
- return 0;
- }
- hsb->s_dir_umask = (umode_t)tmp;
- break;
- case opt_part:
- if (match_int(&args[0], &hsb->part)) {
- pr_err("part requires an argument\n");
- return 0;
- }
- break;
- case opt_session:
- if (match_int(&args[0], &hsb->session)) {
- pr_err("session requires an argument\n");
- return 0;
- }
- break;
- case opt_type:
- if (match_fourchar(&args[0], &hsb->s_type)) {
- pr_err("type requires a 4 character value\n");
- return 0;
- }
- break;
- case opt_creator:
- if (match_fourchar(&args[0], &hsb->s_creator)) {
- pr_err("creator requires a 4 character value\n");
- return 0;
- }
- break;
- case opt_quiet:
- hsb->s_quiet = 1;
- break;
- case opt_codepage:
- if (hsb->nls_disk) {
- pr_err("unable to change codepage\n");
- return 0;
- }
- p = match_strdup(&args[0]);
- if (p)
- hsb->nls_disk = load_nls(p);
- if (!hsb->nls_disk) {
- pr_err("unable to load codepage \"%s\"\n", p);
- kfree(p);
- return 0;
- }
- kfree(p);
- break;
- case opt_iocharset:
- if (hsb->nls_io) {
- pr_err("unable to change iocharset\n");
- return 0;
- }
- p = match_strdup(&args[0]);
- if (p)
- hsb->nls_io = load_nls(p);
- if (!hsb->nls_io) {
- pr_err("unable to load iocharset \"%s\"\n", p);
- kfree(p);
- return 0;
- }
- kfree(p);
- break;
- default:
- return 0;
- }
- }
+ struct hfs_sb_info *hsb = fc->s_fs_info;
+ struct fs_parse_result result;
+ int opt;
+
+ /* hfs does not honor any fs-specific options on remount */
+ if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE)
+ return 0;
- if (hsb->nls_disk && !hsb->nls_io) {
- hsb->nls_io = load_nls_default();
+ opt = fs_parse(fc, hfs_param_spec, param, &result);
+ if (opt < 0)
+ return opt;
+
+ switch (opt) {
+ case opt_uid:
+ hsb->s_uid = result.uid;
+ break;
+ case opt_gid:
+ hsb->s_gid = result.gid;
+ break;
+ case opt_umask:
+ hsb->s_file_umask = (umode_t)result.uint_32;
+ hsb->s_dir_umask = (umode_t)result.uint_32;
+ break;
+ case opt_file_umask:
+ hsb->s_file_umask = (umode_t)result.uint_32;
+ break;
+ case opt_dir_umask:
+ hsb->s_dir_umask = (umode_t)result.uint_32;
+ break;
+ case opt_part:
+ hsb->part = result.uint_32;
+ break;
+ case opt_session:
+ hsb->session = result.uint_32;
+ break;
+ case opt_type:
+ if (strlen(param->string) != 4) {
+ pr_err("type requires a 4 character value\n");
+ return -EINVAL;
+ }
+ memcpy(&hsb->s_type, param->string, 4);
+ break;
+ case opt_creator:
+ if (strlen(param->string) != 4) {
+ pr_err("creator requires a 4 character value\n");
+ return -EINVAL;
+ }
+ memcpy(&hsb->s_creator, param->string, 4);
+ break;
+ case opt_quiet:
+ hsb->s_quiet = 1;
+ break;
+ case opt_codepage:
+ if (hsb->nls_disk) {
+ pr_err("unable to change codepage\n");
+ return -EINVAL;
+ }
+ hsb->nls_disk = load_nls(param->string);
+ if (!hsb->nls_disk) {
+ pr_err("unable to load codepage \"%s\"\n",
+ param->string);
+ return -EINVAL;
+ }
+ break;
+ case opt_iocharset:
+ if (hsb->nls_io) {
+ pr_err("unable to change iocharset\n");
+ return -EINVAL;
+ }
+ hsb->nls_io = load_nls(param->string);
if (!hsb->nls_io) {
- pr_err("unable to load default iocharset\n");
- return 0;
+ pr_err("unable to load iocharset \"%s\"\n",
+ param->string);
+ return -EINVAL;
}
+ break;
+ default:
+ return -EINVAL;
}
- hsb->s_dir_umask &= 0777;
- hsb->s_file_umask &= 0577;
- return 1;
+ return 0;
}
/*
@@ -376,29 +310,25 @@ static int parse_options(char *options, struct hfs_sb_info *hsb)
* hfs_btree_init() to get the necessary data about the extents and
* catalog B-trees and, finally, reading the root inode into memory.
*/
-static int hfs_fill_super(struct super_block *sb, void *data, int silent)
+static int hfs_fill_super(struct super_block *sb, struct fs_context *fc)
{
- struct hfs_sb_info *sbi;
+ struct hfs_sb_info *sbi = HFS_SB(sb);
struct hfs_find_data fd;
hfs_cat_rec rec;
struct inode *root_inode;
+ int silent = fc->sb_flags & SB_SILENT;
int res;
- sbi = kzalloc(sizeof(struct hfs_sb_info), GFP_KERNEL);
- if (!sbi)
- return -ENOMEM;
+ /* load_nls_default does not fail */
+ if (sbi->nls_disk && !sbi->nls_io)
+ sbi->nls_io = load_nls_default();
+ sbi->s_dir_umask &= 0777;
+ sbi->s_file_umask &= 0577;
- sbi->sb = sb;
- sb->s_fs_info = sbi;
spin_lock_init(&sbi->work_lock);
INIT_DELAYED_WORK(&sbi->mdb_work, flush_mdb);
- res = -EINVAL;
- if (!parse_options((char *)data, sbi)) {
- pr_err("unable to parse mount options\n");
- goto bail;
- }
-
+ sbi->sb = sb;
sb->s_op = &hfs_super_operations;
sb->s_xattr = hfs_xattr_handlers;
sb->s_flags |= SB_NODIRATIME;
@@ -451,18 +381,56 @@ bail:
return res;
}
-static struct dentry *hfs_mount(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data)
+static int hfs_get_tree(struct fs_context *fc)
+{
+ return get_tree_bdev(fc, hfs_fill_super);
+}
+
+static void hfs_free_fc(struct fs_context *fc)
+{
+ kfree(fc->s_fs_info);
+}
+
+static const struct fs_context_operations hfs_context_ops = {
+ .parse_param = hfs_parse_param,
+ .get_tree = hfs_get_tree,
+ .reconfigure = hfs_reconfigure,
+ .free = hfs_free_fc,
+};
+
+static int hfs_init_fs_context(struct fs_context *fc)
{
- return mount_bdev(fs_type, flags, dev_name, data, hfs_fill_super);
+ struct hfs_sb_info *hsb;
+
+ hsb = kzalloc(sizeof(struct hfs_sb_info), GFP_KERNEL);
+ if (!hsb)
+ return -ENOMEM;
+
+ fc->s_fs_info = hsb;
+ fc->ops = &hfs_context_ops;
+
+ if (fc->purpose != FS_CONTEXT_FOR_RECONFIGURE) {
+ /* initialize options with defaults */
+ hsb->s_uid = current_uid();
+ hsb->s_gid = current_gid();
+ hsb->s_file_umask = 0133;
+ hsb->s_dir_umask = 0022;
+ hsb->s_type = cpu_to_be32(0x3f3f3f3f); /* == '????' */
+ hsb->s_creator = cpu_to_be32(0x3f3f3f3f); /* == '????' */
+ hsb->s_quiet = 0;
+ hsb->part = -1;
+ hsb->session = -1;
+ }
+
+ return 0;
}
static struct file_system_type hfs_fs_type = {
.owner = THIS_MODULE,
.name = "hfs",
- .mount = hfs_mount,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
+ .init_fs_context = hfs_init_fs_context,
};
MODULE_ALIAS_FS("hfs");
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 59ce81dca73f..2f089bff0095 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -21,6 +21,7 @@
#include <linux/mutex.h>
#include <linux/buffer_head.h>
#include <linux/blkdev.h>
+#include <linux/fs_context.h>
#include "hfsplus_raw.h"
#define DBG_BNODE_REFS 0x00000001
@@ -156,6 +157,7 @@ struct hfsplus_sb_info {
/* Runtime variables */
u32 blockoffset;
+ u32 min_io_size;
sector_t part_start;
sector_t sect_count;
int fs_shift;
@@ -307,7 +309,7 @@ struct hfsplus_readdir_data {
*/
static inline unsigned short hfsplus_min_io_size(struct super_block *sb)
{
- return max_t(unsigned short, bdev_logical_block_size(sb->s_bdev),
+ return max_t(unsigned short, HFSPLUS_SB(sb)->min_io_size,
HFSPLUS_SECTOR_SIZE);
}
@@ -496,8 +498,7 @@ long hfsplus_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
/* options.c */
void hfsplus_fill_defaults(struct hfsplus_sb_info *opts);
-int hfsplus_parse_options_remount(char *input, int *force);
-int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi);
+int hfsplus_parse_param(struct fs_context *fc, struct fs_parameter *param);
int hfsplus_show_options(struct seq_file *seq, struct dentry *root);
/* part_tbl.c */
diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c
index c94a58762ad6..a66a09a56bf7 100644
--- a/fs/hfsplus/options.c
+++ b/fs/hfsplus/options.c
@@ -12,7 +12,8 @@
#include <linux/string.h>
#include <linux/kernel.h>
#include <linux/sched.h>
-#include <linux/parser.h>
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
#include <linux/nls.h>
#include <linux/mount.h>
#include <linux/seq_file.h>
@@ -23,26 +24,23 @@ enum {
opt_creator, opt_type,
opt_umask, opt_uid, opt_gid,
opt_part, opt_session, opt_nls,
- opt_nodecompose, opt_decompose,
- opt_barrier, opt_nobarrier,
- opt_force, opt_err
+ opt_decompose, opt_barrier,
+ opt_force,
};
-static const match_table_t tokens = {
- { opt_creator, "creator=%s" },
- { opt_type, "type=%s" },
- { opt_umask, "umask=%o" },
- { opt_uid, "uid=%u" },
- { opt_gid, "gid=%u" },
- { opt_part, "part=%u" },
- { opt_session, "session=%u" },
- { opt_nls, "nls=%s" },
- { opt_decompose, "decompose" },
- { opt_nodecompose, "nodecompose" },
- { opt_barrier, "barrier" },
- { opt_nobarrier, "nobarrier" },
- { opt_force, "force" },
- { opt_err, NULL }
+static const struct fs_parameter_spec hfs_param_spec[] = {
+ fsparam_string ("creator", opt_creator),
+ fsparam_string ("type", opt_type),
+ fsparam_u32oct ("umask", opt_umask),
+ fsparam_u32 ("uid", opt_uid),
+ fsparam_u32 ("gid", opt_gid),
+ fsparam_u32 ("part", opt_part),
+ fsparam_u32 ("session", opt_session),
+ fsparam_string ("nls", opt_nls),
+ fsparam_flag_no ("decompose", opt_decompose),
+ fsparam_flag_no ("barrier", opt_barrier),
+ fsparam_flag ("force", opt_force),
+ {}
};
/* Initialize an options object to reasonable defaults */
@@ -60,162 +58,89 @@ void hfsplus_fill_defaults(struct hfsplus_sb_info *opts)
opts->session = -1;
}
-/* convert a "four byte character" to a 32 bit int with error checks */
-static inline int match_fourchar(substring_t *arg, u32 *result)
+/* Parse options from mount. Returns nonzero errno on failure */
+int hfsplus_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
- if (arg->to - arg->from != 4)
- return -EINVAL;
- memcpy(result, arg->from, 4);
- return 0;
-}
-
-int hfsplus_parse_options_remount(char *input, int *force)
-{
- char *p;
- substring_t args[MAX_OPT_ARGS];
- int token;
-
- if (!input)
- return 1;
-
- while ((p = strsep(&input, ",")) != NULL) {
- if (!*p)
- continue;
-
- token = match_token(p, tokens, args);
- switch (token) {
- case opt_force:
- *force = 1;
- break;
- default:
- break;
+ struct hfsplus_sb_info *sbi = fc->s_fs_info;
+ struct fs_parse_result result;
+ int opt;
+
+ /*
+ * Only the force option is examined during remount, all others
+ * are ignored.
+ */
+ if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE &&
+ strncmp(param->key, "force", 5))
+ return 0;
+
+ opt = fs_parse(fc, hfs_param_spec, param, &result);
+ if (opt < 0)
+ return opt;
+
+ switch (opt) {
+ case opt_creator:
+ if (strlen(param->string) != 4) {
+ pr_err("creator requires a 4 character value\n");
+ return -EINVAL;
}
- }
-
- return 1;
-}
-
-/* Parse options from mount. Returns 0 on failure */
-/* input is the options passed to mount() as a string */
-int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi)
-{
- char *p;
- substring_t args[MAX_OPT_ARGS];
- int tmp, token;
-
- if (!input)
- goto done;
-
- while ((p = strsep(&input, ",")) != NULL) {
- if (!*p)
- continue;
-
- token = match_token(p, tokens, args);
- switch (token) {
- case opt_creator:
- if (match_fourchar(&args[0], &sbi->creator)) {
- pr_err("creator requires a 4 character value\n");
- return 0;
- }
- break;
- case opt_type:
- if (match_fourchar(&args[0], &sbi->type)) {
- pr_err("type requires a 4 character value\n");
- return 0;
- }
- break;
- case opt_umask:
- if (match_octal(&args[0], &tmp)) {
- pr_err("umask requires a value\n");
- return 0;
- }
- sbi->umask = (umode_t)tmp;
- break;
- case opt_uid:
- if (match_int(&args[0], &tmp)) {
- pr_err("uid requires an argument\n");
- return 0;
- }
- sbi->uid = make_kuid(current_user_ns(), (uid_t)tmp);
- if (!uid_valid(sbi->uid)) {
- pr_err("invalid uid specified\n");
- return 0;
- } else {
- set_bit(HFSPLUS_SB_UID, &sbi->flags);
- }
- break;
- case opt_gid:
- if (match_int(&args[0], &tmp)) {
- pr_err("gid requires an argument\n");
- return 0;
- }
- sbi->gid = make_kgid(current_user_ns(), (gid_t)tmp);
- if (!gid_valid(sbi->gid)) {
- pr_err("invalid gid specified\n");
- return 0;
- } else {
- set_bit(HFSPLUS_SB_GID, &sbi->flags);
- }
- break;
- case opt_part:
- if (match_int(&args[0], &sbi->part)) {
- pr_err("part requires an argument\n");
- return 0;
- }
- break;
- case opt_session:
- if (match_int(&args[0], &sbi->session)) {
- pr_err("session requires an argument\n");
- return 0;
- }
- break;
- case opt_nls:
- if (sbi->nls) {
- pr_err("unable to change nls mapping\n");
- return 0;
- }
- p = match_strdup(&args[0]);
- if (p)
- sbi->nls = load_nls(p);
- if (!sbi->nls) {
- pr_err("unable to load nls mapping \"%s\"\n",
- p);
- kfree(p);
- return 0;
- }
- kfree(p);
- break;
- case opt_decompose:
- clear_bit(HFSPLUS_SB_NODECOMPOSE, &sbi->flags);
- break;
- case opt_nodecompose:
+ memcpy(&sbi->creator, param->string, 4);
+ break;
+ case opt_type:
+ if (strlen(param->string) != 4) {
+ pr_err("type requires a 4 character value\n");
+ return -EINVAL;
+ }
+ memcpy(&sbi->type, param->string, 4);
+ break;
+ case opt_umask:
+ sbi->umask = (umode_t)result.uint_32;
+ break;
+ case opt_uid:
+ sbi->uid = result.uid;
+ set_bit(HFSPLUS_SB_UID, &sbi->flags);
+ break;
+ case opt_gid:
+ sbi->gid = result.gid;
+ set_bit(HFSPLUS_SB_GID, &sbi->flags);
+ break;
+ case opt_part:
+ sbi->part = result.uint_32;
+ break;
+ case opt_session:
+ sbi->session = result.uint_32;
+ break;
+ case opt_nls:
+ if (sbi->nls) {
+ pr_err("unable to change nls mapping\n");
+ return -EINVAL;
+ }
+ sbi->nls = load_nls(param->string);
+ if (!sbi->nls) {
+ pr_err("unable to load nls mapping \"%s\"\n",
+ param->string);
+ return -EINVAL;
+ }
+ break;
+ case opt_decompose:
+ if (result.negated)
set_bit(HFSPLUS_SB_NODECOMPOSE, &sbi->flags);
- break;
- case opt_barrier:
- clear_bit(HFSPLUS_SB_NOBARRIER, &sbi->flags);
- break;
- case opt_nobarrier:
+ else
+ clear_bit(HFSPLUS_SB_NODECOMPOSE, &sbi->flags);
+ break;
+ case opt_barrier:
+ if (result.negated)
set_bit(HFSPLUS_SB_NOBARRIER, &sbi->flags);
- break;
- case opt_force:
- set_bit(HFSPLUS_SB_FORCE, &sbi->flags);
- break;
- default:
- return 0;
- }
- }
-
-done:
- if (!sbi->nls) {
- /* try utf8 first, as this is the old default behaviour */
- sbi->nls = load_nls("utf8");
- if (!sbi->nls)
- sbi->nls = load_nls_default();
- if (!sbi->nls)
- return 0;
+ else
+ clear_bit(HFSPLUS_SB_NOBARRIER, &sbi->flags);
+ break;
+ case opt_force:
+ set_bit(HFSPLUS_SB_FORCE, &sbi->flags);
+ break;
+ default:
+ return -EINVAL;
}
- return 1;
+ return 0;
}
int hfsplus_show_options(struct seq_file *seq, struct dentry *root)
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 97920202790f..948b8aaee33e 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -14,6 +14,7 @@
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/fs.h>
+#include <linux/fs_context.h>
#include <linux/slab.h>
#include <linux/vfs.h>
#include <linux/nls.h>
@@ -332,34 +333,33 @@ static int hfsplus_statfs(struct dentry *dentry, struct kstatfs *buf)
return 0;
}
-static int hfsplus_remount(struct super_block *sb, int *flags, char *data)
+static int hfsplus_reconfigure(struct fs_context *fc)
{
+ struct super_block *sb = fc->root->d_sb;
+
sync_filesystem(sb);
- if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb))
+ if ((bool)(fc->sb_flags & SB_RDONLY) == sb_rdonly(sb))
return 0;
- if (!(*flags & SB_RDONLY)) {
- struct hfsplus_vh *vhdr = HFSPLUS_SB(sb)->s_vhdr;
- int force = 0;
-
- if (!hfsplus_parse_options_remount(data, &force))
- return -EINVAL;
+ if (!(fc->sb_flags & SB_RDONLY)) {
+ struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
+ struct hfsplus_vh *vhdr = sbi->s_vhdr;
if (!(vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_UNMNT))) {
pr_warn("filesystem was not cleanly unmounted, running fsck.hfsplus is recommended. leaving read-only.\n");
sb->s_flags |= SB_RDONLY;
- *flags |= SB_RDONLY;
- } else if (force) {
+ fc->sb_flags |= SB_RDONLY;
+ } else if (test_bit(HFSPLUS_SB_FORCE, &sbi->flags)) {
/* nothing */
} else if (vhdr->attributes &
cpu_to_be32(HFSPLUS_VOL_SOFTLOCK)) {
pr_warn("filesystem is marked locked, leaving read-only.\n");
sb->s_flags |= SB_RDONLY;
- *flags |= SB_RDONLY;
+ fc->sb_flags |= SB_RDONLY;
} else if (vhdr->attributes &
cpu_to_be32(HFSPLUS_VOL_JOURNALED)) {
pr_warn("filesystem is marked journaled, leaving read-only.\n");
sb->s_flags |= SB_RDONLY;
- *flags |= SB_RDONLY;
+ fc->sb_flags |= SB_RDONLY;
}
}
return 0;
@@ -373,38 +373,33 @@ static const struct super_operations hfsplus_sops = {
.put_super = hfsplus_put_super,
.sync_fs = hfsplus_sync_fs,
.statfs = hfsplus_statfs,
- .remount_fs = hfsplus_remount,
.show_options = hfsplus_show_options,
};
-static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
+static int hfsplus_fill_super(struct super_block *sb, struct fs_context *fc)
{
struct hfsplus_vh *vhdr;
- struct hfsplus_sb_info *sbi;
+ struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
hfsplus_cat_entry entry;
struct hfs_find_data fd;
struct inode *root, *inode;
struct qstr str;
- struct nls_table *nls = NULL;
+ struct nls_table *nls;
u64 last_fs_block, last_fs_page;
+ int silent = fc->sb_flags & SB_SILENT;
int err;
- err = -ENOMEM;
- sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
- if (!sbi)
- goto out;
-
- sb->s_fs_info = sbi;
mutex_init(&sbi->alloc_mutex);
mutex_init(&sbi->vh_mutex);
spin_lock_init(&sbi->work_lock);
INIT_DELAYED_WORK(&sbi->sync_work, delayed_sync_fs);
- hfsplus_fill_defaults(sbi);
err = -EINVAL;
- if (!hfsplus_parse_options(data, sbi)) {
- pr_err("unable to parse mount options\n");
- goto out_unload_nls;
+ if (!sbi->nls) {
+ /* try utf8 first, as this is the old default behaviour */
+ sbi->nls = load_nls("utf8");
+ if (!sbi->nls)
+ sbi->nls = load_nls_default();
}
/* temporarily use utf8 to correctly find the hidden dir below */
@@ -616,7 +611,6 @@ out_unload_nls:
unload_nls(sbi->nls);
unload_nls(nls);
kfree(sbi);
-out:
return err;
}
@@ -641,18 +635,46 @@ static void hfsplus_free_inode(struct inode *inode)
#define HFSPLUS_INODE_SIZE sizeof(struct hfsplus_inode_info)
-static struct dentry *hfsplus_mount(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data)
+static int hfsplus_get_tree(struct fs_context *fc)
+{
+ return get_tree_bdev(fc, hfsplus_fill_super);
+}
+
+static void hfsplus_free_fc(struct fs_context *fc)
{
- return mount_bdev(fs_type, flags, dev_name, data, hfsplus_fill_super);
+ kfree(fc->s_fs_info);
+}
+
+static const struct fs_context_operations hfsplus_context_ops = {
+ .parse_param = hfsplus_parse_param,
+ .get_tree = hfsplus_get_tree,
+ .reconfigure = hfsplus_reconfigure,
+ .free = hfsplus_free_fc,
+};
+
+static int hfsplus_init_fs_context(struct fs_context *fc)
+{
+ struct hfsplus_sb_info *sbi;
+
+ sbi = kzalloc(sizeof(struct hfsplus_sb_info), GFP_KERNEL);
+ if (!sbi)
+ return -ENOMEM;
+
+ if (fc->purpose != FS_CONTEXT_FOR_RECONFIGURE)
+ hfsplus_fill_defaults(sbi);
+
+ fc->s_fs_info = sbi;
+ fc->ops = &hfsplus_context_ops;
+
+ return 0;
}
static struct file_system_type hfsplus_fs_type = {
.owner = THIS_MODULE,
.name = "hfsplus",
- .mount = hfsplus_mount,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
+ .init_fs_context = hfsplus_init_fs_context,
};
MODULE_ALIAS_FS("hfsplus");
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index 9592ffcb44e5..74801911bc1c 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -172,6 +172,8 @@ int hfsplus_read_wrapper(struct super_block *sb)
if (!blocksize)
goto out;
+ sbi->min_io_size = blocksize;
+
if (hfsplus_get_last_session(sb, &part_start, &part_size))
goto out;
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index e73717daa5f9..27567920abe4 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -9,7 +9,8 @@
#include "hpfs_fn.h"
#include <linux/module.h>
-#include <linux/parser.h>
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
#include <linux/init.h>
#include <linux/statfs.h>
#include <linux/magic.h>
@@ -90,7 +91,7 @@ void hpfs_error(struct super_block *s, const char *fmt, ...)
hpfs_sb(s)->sb_was_error = 1;
}
-/*
+/*
* A little trick to detect cycles in many hpfs structures and don't let the
* kernel crash on corrupted filesystem. When first called, set c2 to 0.
*
@@ -272,146 +273,70 @@ static void destroy_inodecache(void)
kmem_cache_destroy(hpfs_inode_cachep);
}
-/*
- * A tiny parser for option strings, stolen from dosfs.
- * Stolen again from read-only hpfs.
- * And updated for table-driven option parsing.
- */
-
enum {
- Opt_help, Opt_uid, Opt_gid, Opt_umask, Opt_case_lower, Opt_case_asis,
- Opt_check_none, Opt_check_normal, Opt_check_strict,
- Opt_err_cont, Opt_err_ro, Opt_err_panic,
- Opt_eas_no, Opt_eas_ro, Opt_eas_rw,
- Opt_chkdsk_no, Opt_chkdsk_errors, Opt_chkdsk_always,
- Opt_timeshift, Opt_err,
+ Opt_help, Opt_uid, Opt_gid, Opt_umask, Opt_case,
+ Opt_check, Opt_err, Opt_eas, Opt_chkdsk, Opt_timeshift,
};
-static const match_table_t tokens = {
- {Opt_help, "help"},
- {Opt_uid, "uid=%u"},
- {Opt_gid, "gid=%u"},
- {Opt_umask, "umask=%o"},
- {Opt_case_lower, "case=lower"},
- {Opt_case_asis, "case=asis"},
- {Opt_check_none, "check=none"},
- {Opt_check_normal, "check=normal"},
- {Opt_check_strict, "check=strict"},
- {Opt_err_cont, "errors=continue"},
- {Opt_err_ro, "errors=remount-ro"},
- {Opt_err_panic, "errors=panic"},
- {Opt_eas_no, "eas=no"},
- {Opt_eas_ro, "eas=ro"},
- {Opt_eas_rw, "eas=rw"},
- {Opt_chkdsk_no, "chkdsk=no"},
- {Opt_chkdsk_errors, "chkdsk=errors"},
- {Opt_chkdsk_always, "chkdsk=always"},
- {Opt_timeshift, "timeshift=%d"},
- {Opt_err, NULL},
+static const struct constant_table hpfs_param_case[] = {
+ {"asis", 0},
+ {"lower", 1},
+ {}
};
-static int parse_opts(char *opts, kuid_t *uid, kgid_t *gid, umode_t *umask,
- int *lowercase, int *eas, int *chk, int *errs,
- int *chkdsk, int *timeshift)
-{
- char *p;
- int option;
+static const struct constant_table hpfs_param_check[] = {
+ {"none", 0},
+ {"normal", 1},
+ {"strict", 2},
+ {}
+};
- if (!opts)
- return 1;
+static const struct constant_table hpfs_param_err[] = {
+ {"continue", 0},
+ {"remount-ro", 1},
+ {"panic", 2},
+ {}
+};
- /*pr_info("Parsing opts: '%s'\n",opts);*/
-
- while ((p = strsep(&opts, ",")) != NULL) {
- substring_t args[MAX_OPT_ARGS];
- int token;
- if (!*p)
- continue;
-
- token = match_token(p, tokens, args);
- switch (token) {
- case Opt_help:
- return 2;
- case Opt_uid:
- if (match_int(args, &option))
- return 0;
- *uid = make_kuid(current_user_ns(), option);
- if (!uid_valid(*uid))
- return 0;
- break;
- case Opt_gid:
- if (match_int(args, &option))
- return 0;
- *gid = make_kgid(current_user_ns(), option);
- if (!gid_valid(*gid))
- return 0;
- break;
- case Opt_umask:
- if (match_octal(args, &option))
- return 0;
- *umask = option;
- break;
- case Opt_case_lower:
- *lowercase = 1;
- break;
- case Opt_case_asis:
- *lowercase = 0;
- break;
- case Opt_check_none:
- *chk = 0;
- break;
- case Opt_check_normal:
- *chk = 1;
- break;
- case Opt_check_strict:
- *chk = 2;
- break;
- case Opt_err_cont:
- *errs = 0;
- break;
- case Opt_err_ro:
- *errs = 1;
- break;
- case Opt_err_panic:
- *errs = 2;
- break;
- case Opt_eas_no:
- *eas = 0;
- break;
- case Opt_eas_ro:
- *eas = 1;
- break;
- case Opt_eas_rw:
- *eas = 2;
- break;
- case Opt_chkdsk_no:
- *chkdsk = 0;
- break;
- case Opt_chkdsk_errors:
- *chkdsk = 1;
- break;
- case Opt_chkdsk_always:
- *chkdsk = 2;
- break;
- case Opt_timeshift:
- {
- int m = 1;
- char *rhs = args[0].from;
- if (!rhs || !*rhs)
- return 0;
- if (*rhs == '-') m = -1;
- if (*rhs == '+' || *rhs == '-') rhs++;
- *timeshift = simple_strtoul(rhs, &rhs, 0) * m;
- if (*rhs)
- return 0;
- break;
- }
- default:
- return 0;
- }
- }
- return 1;
-}
+static const struct constant_table hpfs_param_eas[] = {
+ {"no", 0},
+ {"ro", 1},
+ {"rw", 2},
+ {}
+};
+
+static const struct constant_table hpfs_param_chkdsk[] = {
+ {"no", 0},
+ {"errors", 1},
+ {"always", 2},
+ {}
+};
+
+static const struct fs_parameter_spec hpfs_param_spec[] = {
+ fsparam_flag ("help", Opt_help),
+ fsparam_uid ("uid", Opt_uid),
+ fsparam_gid ("gid", Opt_gid),
+ fsparam_u32oct ("umask", Opt_umask),
+ fsparam_enum ("case", Opt_case, hpfs_param_case),
+ fsparam_enum ("check", Opt_check, hpfs_param_check),
+ fsparam_enum ("errors", Opt_err, hpfs_param_err),
+ fsparam_enum ("eas", Opt_eas, hpfs_param_eas),
+ fsparam_enum ("chkdsk", Opt_chkdsk, hpfs_param_chkdsk),
+ fsparam_s32 ("timeshift", Opt_timeshift),
+ {}
+};
+
+struct hpfs_fc_context {
+ kuid_t uid;
+ kgid_t gid;
+ umode_t umask;
+ int lowercase;
+ int eas;
+ int chk;
+ int errs;
+ int chkdsk;
+ int timeshift;
+};
static inline void hpfs_help(void)
{
@@ -439,49 +364,92 @@ HPFS filesystem options:\n\
\n");
}
-static int hpfs_remount_fs(struct super_block *s, int *flags, char *data)
+static int hpfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
- kuid_t uid;
- kgid_t gid;
- umode_t umask;
- int lowercase, eas, chk, errs, chkdsk, timeshift;
- int o;
+ struct hpfs_fc_context *ctx = fc->fs_private;
+ struct fs_parse_result result;
+ int opt;
+
+ opt = fs_parse(fc, hpfs_param_spec, param, &result);
+ if (opt < 0)
+ return opt;
+
+ switch (opt) {
+ case Opt_help:
+ hpfs_help();
+ return -EINVAL;
+ case Opt_uid:
+ ctx->uid = result.uid;
+ break;
+ case Opt_gid:
+ ctx->gid = result.gid;
+ break;
+ case Opt_umask:
+ ctx->umask = result.uint_32;
+ break;
+ case Opt_case:
+ ctx->lowercase = result.uint_32;
+ break;
+ case Opt_check:
+ ctx->chk = result.uint_32;
+ break;
+ case Opt_err:
+ ctx->errs = result.uint_32;
+ break;
+ case Opt_eas:
+ ctx->eas = result.uint_32;
+ break;
+ case Opt_chkdsk:
+ ctx->chkdsk = result.uint_32;
+ break;
+ case Opt_timeshift:
+ {
+ int m = 1;
+ char *rhs = param->string;
+ int timeshift;
+
+ if (*rhs == '-') m = -1;
+ if (*rhs == '+' || *rhs == '-') rhs++;
+ timeshift = simple_strtoul(rhs, &rhs, 0) * m;
+ if (*rhs)
+ return -EINVAL;
+ ctx->timeshift = timeshift;
+ break;
+ }
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int hpfs_reconfigure(struct fs_context *fc)
+{
+ struct hpfs_fc_context *ctx = fc->fs_private;
+ struct super_block *s = fc->root->d_sb;
struct hpfs_sb_info *sbi = hpfs_sb(s);
sync_filesystem(s);
- *flags |= SB_NOATIME;
+ fc->sb_flags |= SB_NOATIME;
hpfs_lock(s);
- uid = sbi->sb_uid; gid = sbi->sb_gid;
- umask = 0777 & ~sbi->sb_mode;
- lowercase = sbi->sb_lowercase;
- eas = sbi->sb_eas; chk = sbi->sb_chk; chkdsk = sbi->sb_chkdsk;
- errs = sbi->sb_err; timeshift = sbi->sb_timeshift;
-
- if (!(o = parse_opts(data, &uid, &gid, &umask, &lowercase,
- &eas, &chk, &errs, &chkdsk, &timeshift))) {
- pr_err("bad mount options.\n");
- goto out_err;
- }
- if (o == 2) {
- hpfs_help();
- goto out_err;
- }
- if (timeshift != sbi->sb_timeshift) {
+
+ if (ctx->timeshift != sbi->sb_timeshift) {
pr_err("timeshift can't be changed using remount.\n");
goto out_err;
}
unmark_dirty(s);
- sbi->sb_uid = uid; sbi->sb_gid = gid;
- sbi->sb_mode = 0777 & ~umask;
- sbi->sb_lowercase = lowercase;
- sbi->sb_eas = eas; sbi->sb_chk = chk; sbi->sb_chkdsk = chkdsk;
- sbi->sb_err = errs; sbi->sb_timeshift = timeshift;
+ sbi->sb_uid = ctx->uid; sbi->sb_gid = ctx->gid;
+ sbi->sb_mode = 0777 & ~ctx->umask;
+ sbi->sb_lowercase = ctx->lowercase;
+ sbi->sb_eas = ctx->eas; sbi->sb_chk = ctx->chk;
+ sbi->sb_chkdsk = ctx->chkdsk;
+ sbi->sb_err = ctx->errs; sbi->sb_timeshift = ctx->timeshift;
- if (!(*flags & SB_RDONLY)) mark_dirty(s, 1);
+ if (!(fc->sb_flags & SB_RDONLY)) mark_dirty(s, 1);
hpfs_unlock(s);
return 0;
@@ -530,30 +498,24 @@ static const struct super_operations hpfs_sops =
.evict_inode = hpfs_evict_inode,
.put_super = hpfs_put_super,
.statfs = hpfs_statfs,
- .remount_fs = hpfs_remount_fs,
.show_options = hpfs_show_options,
};
-static int hpfs_fill_super(struct super_block *s, void *options, int silent)
+static int hpfs_fill_super(struct super_block *s, struct fs_context *fc)
{
+ struct hpfs_fc_context *ctx = fc->fs_private;
struct buffer_head *bh0, *bh1, *bh2;
struct hpfs_boot_block *bootblock;
struct hpfs_super_block *superblock;
struct hpfs_spare_block *spareblock;
struct hpfs_sb_info *sbi;
struct inode *root;
-
- kuid_t uid;
- kgid_t gid;
- umode_t umask;
- int lowercase, eas, chk, errs, chkdsk, timeshift;
+ int silent = fc->sb_flags & SB_SILENT;
dnode_secno root_dno;
struct hpfs_dirent *de = NULL;
struct quad_buffer_head qbh;
- int o;
-
sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
if (!sbi) {
return -ENOMEM;
@@ -563,26 +525,6 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent)
mutex_init(&sbi->hpfs_mutex);
hpfs_lock(s);
- uid = current_uid();
- gid = current_gid();
- umask = current_umask();
- lowercase = 0;
- eas = 2;
- chk = 1;
- errs = 1;
- chkdsk = 1;
- timeshift = 0;
-
- if (!(o = parse_opts(options, &uid, &gid, &umask, &lowercase,
- &eas, &chk, &errs, &chkdsk, &timeshift))) {
- pr_err("bad mount options.\n");
- goto bail0;
- }
- if (o==2) {
- hpfs_help();
- goto bail0;
- }
-
/*sbi->sb_mounting = 1;*/
sb_set_blocksize(s, 512);
sbi->sb_fs_size = -1;
@@ -622,17 +564,17 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent)
sbi->sb_dirband_start = le32_to_cpu(superblock->dir_band_start);
sbi->sb_dirband_size = le32_to_cpu(superblock->n_dir_band);
sbi->sb_dmap = le32_to_cpu(superblock->dir_band_bitmap);
- sbi->sb_uid = uid;
- sbi->sb_gid = gid;
- sbi->sb_mode = 0777 & ~umask;
+ sbi->sb_uid = ctx->uid;
+ sbi->sb_gid = ctx->gid;
+ sbi->sb_mode = 0777 & ~ctx->umask;
sbi->sb_n_free = -1;
sbi->sb_n_free_dnodes = -1;
- sbi->sb_lowercase = lowercase;
- sbi->sb_eas = eas;
- sbi->sb_chk = chk;
- sbi->sb_chkdsk = chkdsk;
- sbi->sb_err = errs;
- sbi->sb_timeshift = timeshift;
+ sbi->sb_lowercase = ctx->lowercase;
+ sbi->sb_eas = ctx->eas;
+ sbi->sb_chk = ctx->chk;
+ sbi->sb_chkdsk = ctx->chkdsk;
+ sbi->sb_err = ctx->errs;
+ sbi->sb_timeshift = ctx->timeshift;
sbi->sb_was_error = 0;
sbi->sb_cp_table = NULL;
sbi->sb_c_bitmap = -1;
@@ -653,7 +595,7 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent)
/* Check for general fs errors*/
if (spareblock->dirty && !spareblock->old_wrote) {
- if (errs == 2) {
+ if (sbi->sb_err == 2) {
pr_err("Improperly stopped, not mounted\n");
goto bail4;
}
@@ -667,16 +609,16 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent)
}
if (le32_to_cpu(spareblock->n_dnode_spares) != le32_to_cpu(spareblock->n_dnode_spares_free)) {
- if (errs >= 2) {
+ if (sbi->sb_err >= 2) {
pr_err("Spare dnodes used, try chkdsk\n");
mark_dirty(s, 0);
goto bail4;
}
hpfs_error(s, "warning: spare dnodes used, try chkdsk");
- if (errs == 0)
+ if (sbi->sb_err == 0)
pr_err("Proceeding, but your filesystem could be corrupted if you delete files or directories\n");
}
- if (chk) {
+ if (sbi->sb_chk) {
unsigned a;
if (le32_to_cpu(superblock->dir_band_end) - le32_to_cpu(superblock->dir_band_start) + 1 != le32_to_cpu(superblock->n_dir_band) ||
le32_to_cpu(superblock->dir_band_end) < le32_to_cpu(superblock->dir_band_start) || le32_to_cpu(superblock->n_dir_band) > 0x4000) {
@@ -755,18 +697,70 @@ bail0:
return -EINVAL;
}
-static struct dentry *hpfs_mount(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data)
+static int hpfs_get_tree(struct fs_context *fc)
+{
+ return get_tree_bdev(fc, hpfs_fill_super);
+}
+
+static void hpfs_free_fc(struct fs_context *fc)
{
- return mount_bdev(fs_type, flags, dev_name, data, hpfs_fill_super);
+ kfree(fc->fs_private);
}
+static const struct fs_context_operations hpfs_fc_context_ops = {
+ .parse_param = hpfs_parse_param,
+ .get_tree = hpfs_get_tree,
+ .reconfigure = hpfs_reconfigure,
+ .free = hpfs_free_fc,
+};
+
+static int hpfs_init_fs_context(struct fs_context *fc)
+{
+ struct hpfs_fc_context *ctx;
+
+ ctx = kzalloc(sizeof(struct hpfs_fc_context), GFP_KERNEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) {
+ struct super_block *sb = fc->root->d_sb;
+ struct hpfs_sb_info *sbi = hpfs_sb(sb);
+
+ ctx->uid = sbi->sb_uid;
+ ctx->gid = sbi->sb_gid;
+ ctx->umask = 0777 & ~sbi->sb_mode;
+ ctx->lowercase = sbi->sb_lowercase;
+ ctx->eas = sbi->sb_eas;
+ ctx->chk = sbi->sb_chk;
+ ctx->chkdsk = sbi->sb_chkdsk;
+ ctx->errs = sbi->sb_err;
+ ctx->timeshift = sbi->sb_timeshift;
+
+ } else {
+ ctx->uid = current_uid();
+ ctx->gid = current_gid();
+ ctx->umask = current_umask();
+ ctx->lowercase = 0;
+ ctx->eas = 2;
+ ctx->chk = 1;
+ ctx->errs = 1;
+ ctx->chkdsk = 1;
+ ctx->timeshift = 0;
+ }
+
+ fc->fs_private = ctx;
+ fc->ops = &hpfs_fc_context_ops;
+
+ return 0;
+};
+
static struct file_system_type hpfs_fs_type = {
.owner = THIS_MODULE,
.name = "hpfs",
- .mount = hpfs_mount,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
+ .init_fs_context = hpfs_init_fs_context,
+ .parameters = hpfs_param_spec,
};
MODULE_ALIAS_FS("hpfs");
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 5cf327337e22..2dea122e5b93 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -39,6 +39,9 @@
#include <linux/uaccess.h>
#include <linux/sched/mm.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/hugetlbfs.h>
+
static const struct address_space_operations hugetlbfs_aops;
static const struct file_operations hugetlbfs_file_operations;
static const struct inode_operations hugetlbfs_dir_inode_operations;
@@ -687,6 +690,7 @@ static void hugetlbfs_evict_inode(struct inode *inode)
{
struct resv_map *resv_map;
+ trace_hugetlbfs_evict_inode(inode);
remove_inode_hugepages(inode, 0, LLONG_MAX);
/*
@@ -814,8 +818,10 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
return -EOPNOTSUPP;
- if (mode & FALLOC_FL_PUNCH_HOLE)
- return hugetlbfs_punch_hole(inode, offset, len);
+ if (mode & FALLOC_FL_PUNCH_HOLE) {
+ error = hugetlbfs_punch_hole(inode, offset, len);
+ goto out_nolock;
+ }
/*
* Default preallocate case.
@@ -919,6 +925,9 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
inode_set_ctime_current(inode);
out:
inode_unlock(inode);
+
+out_nolock:
+ trace_hugetlbfs_fallocate(inode, mode, offset, len, error);
return error;
}
@@ -935,6 +944,8 @@ static int hugetlbfs_setattr(struct mnt_idmap *idmap,
if (error)
return error;
+ trace_hugetlbfs_setattr(inode, dentry, attr);
+
if (ia_valid & ATTR_SIZE) {
loff_t oldsize = inode->i_size;
loff_t newsize = attr->ia_size;
@@ -1033,6 +1044,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
break;
}
lockdep_annotate_inode_mutex_key(inode);
+ trace_hugetlbfs_alloc_inode(inode, dir, mode);
} else {
if (resv_map)
kref_put(&resv_map->refs, resv_map_release);
@@ -1272,6 +1284,7 @@ static struct inode *hugetlbfs_alloc_inode(struct super_block *sb)
static void hugetlbfs_free_inode(struct inode *inode)
{
+ trace_hugetlbfs_free_inode(inode);
kmem_cache_free(hugetlbfs_inode_cachep, HUGETLBFS_I(inode));
}
diff --git a/fs/inode.c b/fs/inode.c
index 8dabb224f941..b13b778257ae 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -21,7 +21,12 @@
#include <linux/list_lru.h>
#include <linux/iversion.h>
#include <linux/rw_hint.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
#include <trace/events/writeback.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/timestamp.h>
+
#include "internal.h"
/*
@@ -98,6 +103,70 @@ long get_nr_dirty_inodes(void)
return nr_dirty > 0 ? nr_dirty : 0;
}
+#ifdef CONFIG_DEBUG_FS
+static DEFINE_PER_CPU(long, mg_ctime_updates);
+static DEFINE_PER_CPU(long, mg_fine_stamps);
+static DEFINE_PER_CPU(long, mg_ctime_swaps);
+
+static unsigned long get_mg_ctime_updates(void)
+{
+ unsigned long sum = 0;
+ int i;
+
+ for_each_possible_cpu(i)
+ sum += data_race(per_cpu(mg_ctime_updates, i));
+ return sum;
+}
+
+static unsigned long get_mg_fine_stamps(void)
+{
+ unsigned long sum = 0;
+ int i;
+
+ for_each_possible_cpu(i)
+ sum += data_race(per_cpu(mg_fine_stamps, i));
+ return sum;
+}
+
+static unsigned long get_mg_ctime_swaps(void)
+{
+ unsigned long sum = 0;
+ int i;
+
+ for_each_possible_cpu(i)
+ sum += data_race(per_cpu(mg_ctime_swaps, i));
+ return sum;
+}
+
+#define mgtime_counter_inc(__var) this_cpu_inc(__var)
+
+static int mgts_show(struct seq_file *s, void *p)
+{
+ unsigned long ctime_updates = get_mg_ctime_updates();
+ unsigned long ctime_swaps = get_mg_ctime_swaps();
+ unsigned long fine_stamps = get_mg_fine_stamps();
+ unsigned long floor_swaps = timekeeping_get_mg_floor_swaps();
+
+ seq_printf(s, "%lu %lu %lu %lu\n",
+ ctime_updates, ctime_swaps, fine_stamps, floor_swaps);
+ return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mgts);
+
+static int __init mg_debugfs_init(void)
+{
+ debugfs_create_file("multigrain_timestamps", S_IFREG | S_IRUGO, NULL, NULL, &mgts_fops);
+ return 0;
+}
+late_initcall(mg_debugfs_init);
+
+#else /* ! CONFIG_DEBUG_FS */
+
+#define mgtime_counter_inc(__var) do { } while (0)
+
+#endif /* CONFIG_DEBUG_FS */
+
/*
* Handle nr_inode sysctl
*/
@@ -174,6 +243,8 @@ int inode_init_always_gfp(struct super_block *sb, struct inode *inode, gfp_t gfp
inode->i_opflags = 0;
if (sb->s_xattr)
inode->i_opflags |= IOP_XATTR;
+ if (sb->s_type->fs_flags & FS_MGTIME)
+ inode->i_opflags |= IOP_MGTIME;
i_uid_write(inode, 0);
i_gid_write(inode, 0);
atomic_set(&inode->i_writecount, 0);
@@ -748,7 +819,7 @@ static void evict(struct inode *inode)
* ___wait_var_event() either sees the bit cleared or
* waitqueue_active() check in wake_up_var() sees the waiter.
*/
- smp_mb();
+ smp_mb__after_spinlock();
inode_wake_up_bit(inode, __I_NEW);
BUG_ON(inode->i_state != (I_FREEING | I_CLEAR));
spin_unlock(&inode->i_lock);
@@ -1241,16 +1312,15 @@ EXPORT_SYMBOL(unlock_two_nondirectories);
* @data: opaque data pointer to pass to @test and @set
*
* Search for the inode specified by @hashval and @data in the inode cache,
- * and if present it is return it with an increased reference count. This is
- * a variant of iget5_locked() for callers that don't want to fail on memory
- * allocation of inode.
+ * and if present return it with an increased reference count. This is a
+ * variant of iget5_locked() that doesn't allocate an inode.
*
- * If the inode is not in cache, insert the pre-allocated inode to cache and
+ * If the inode is not present in the cache, insert the pre-allocated inode and
* return it locked, hashed, and with the I_NEW flag set. The file system gets
* to fill it in before unlocking it via unlock_new_inode().
*
- * Note both @test and @set are called with the inode_hash_lock held, so can't
- * sleep.
+ * Note that both @test and @set are called with the inode_hash_lock held, so
+ * they can't sleep.
*/
struct inode *inode_insert5(struct inode *inode, unsigned long hashval,
int (*test)(struct inode *, void *),
@@ -1314,16 +1384,16 @@ EXPORT_SYMBOL(inode_insert5);
* @data: opaque data pointer to pass to @test and @set
*
* Search for the inode specified by @hashval and @data in the inode cache,
- * and if present it is return it with an increased reference count. This is
- * a generalized version of iget_locked() for file systems where the inode
+ * and if present return it with an increased reference count. This is a
+ * generalized version of iget_locked() for file systems where the inode
* number is not sufficient for unique identification of an inode.
*
- * If the inode is not in cache, allocate a new inode and return it locked,
- * hashed, and with the I_NEW flag set. The file system gets to fill it in
- * before unlocking it via unlock_new_inode().
+ * If the inode is not present in the cache, allocate and insert a new inode
+ * and return it locked, hashed, and with the I_NEW flag set. The file system
+ * gets to fill it in before unlocking it via unlock_new_inode().
*
- * Note both @test and @set are called with the inode_hash_lock held, so can't
- * sleep.
+ * Note that both @test and @set are called with the inode_hash_lock held, so
+ * they can't sleep.
*/
struct inode *iget5_locked(struct super_block *sb, unsigned long hashval,
int (*test)(struct inode *, void *),
@@ -2211,19 +2281,58 @@ int file_remove_privs(struct file *file)
}
EXPORT_SYMBOL(file_remove_privs);
+/**
+ * current_time - Return FS time (possibly fine-grained)
+ * @inode: inode.
+ *
+ * Return the current time truncated to the time granularity supported by
+ * the fs, as suitable for a ctime/mtime change. If the ctime is flagged
+ * as having been QUERIED, get a fine-grained timestamp, but don't update
+ * the floor.
+ *
+ * For a multigrain inode, this is effectively an estimate of the timestamp
+ * that a file would receive. An actual update must go through
+ * inode_set_ctime_current().
+ */
+struct timespec64 current_time(struct inode *inode)
+{
+ struct timespec64 now;
+ u32 cns;
+
+ ktime_get_coarse_real_ts64_mg(&now);
+
+ if (!is_mgtime(inode))
+ goto out;
+
+ /* If nothing has queried it, then coarse time is fine */
+ cns = smp_load_acquire(&inode->i_ctime_nsec);
+ if (cns & I_CTIME_QUERIED) {
+ /*
+ * If there is no apparent change, then get a fine-grained
+ * timestamp.
+ */
+ if (now.tv_nsec == (cns & ~I_CTIME_QUERIED))
+ ktime_get_real_ts64(&now);
+ }
+out:
+ return timestamp_truncate(now, inode);
+}
+EXPORT_SYMBOL(current_time);
+
static int inode_needs_update_time(struct inode *inode)
{
+ struct timespec64 now, ts;
int sync_it = 0;
- struct timespec64 now = current_time(inode);
- struct timespec64 ts;
/* First try to exhaust all avenues to not sync */
if (IS_NOCMTIME(inode))
return 0;
+ now = current_time(inode);
+
ts = inode_get_mtime(inode);
if (!timespec64_equal(&ts, &now))
- sync_it = S_MTIME;
+ sync_it |= S_MTIME;
ts = inode_get_ctime(inode);
if (!timespec64_equal(&ts, &now))
@@ -2600,6 +2709,16 @@ void inode_nohighmem(struct inode *inode)
}
EXPORT_SYMBOL(inode_nohighmem);
+struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts)
+{
+ trace_inode_set_ctime_to_ts(inode, &ts);
+ set_normalized_timespec64(&ts, ts.tv_sec, ts.tv_nsec);
+ inode->i_ctime_sec = ts.tv_sec;
+ inode->i_ctime_nsec = ts.tv_nsec;
+ return ts;
+}
+EXPORT_SYMBOL(inode_set_ctime_to_ts);
+
/**
* timestamp_truncate - Truncate timespec to a granularity
* @t: Timespec
@@ -2632,39 +2751,159 @@ struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode)
EXPORT_SYMBOL(timestamp_truncate);
/**
- * current_time - Return FS time
- * @inode: inode.
+ * inode_set_ctime_current - set the ctime to current_time
+ * @inode: inode
*
- * Return the current time truncated to the time granularity supported by
- * the fs.
+ * Set the inode's ctime to the current value for the inode. Returns the
+ * current value that was assigned. If this is not a multigrain inode, then we
+ * set it to the later of the coarse time and floor value.
+ *
+ * If it is multigrain, then we first see if the coarse-grained timestamp is
+ * distinct from what is already there. If so, then use that. Otherwise, get a
+ * fine-grained timestamp.
*
- * Note that inode and inode->sb cannot be NULL.
- * Otherwise, the function warns and returns time without truncation.
+ * After that, try to swap the new value into i_ctime_nsec. Accept the
+ * resulting ctime, regardless of the outcome of the swap. If it has
+ * already been replaced, then that timestamp is later than the earlier
+ * unacceptable one, and is thus acceptable.
*/
-struct timespec64 current_time(struct inode *inode)
+struct timespec64 inode_set_ctime_current(struct inode *inode)
{
struct timespec64 now;
+ u32 cns, cur;
- ktime_get_coarse_real_ts64(&now);
- return timestamp_truncate(now, inode);
+ ktime_get_coarse_real_ts64_mg(&now);
+ now = timestamp_truncate(now, inode);
+
+ /* Just return that if this is not a multigrain fs */
+ if (!is_mgtime(inode)) {
+ inode_set_ctime_to_ts(inode, now);
+ goto out;
+ }
+
+ /*
+ * A fine-grained time is only needed if someone has queried
+ * for timestamps, and the current coarse grained time isn't
+ * later than what's already there.
+ */
+ cns = smp_load_acquire(&inode->i_ctime_nsec);
+ if (cns & I_CTIME_QUERIED) {
+ struct timespec64 ctime = { .tv_sec = inode->i_ctime_sec,
+ .tv_nsec = cns & ~I_CTIME_QUERIED };
+
+ if (timespec64_compare(&now, &ctime) <= 0) {
+ ktime_get_real_ts64_mg(&now);
+ now = timestamp_truncate(now, inode);
+ mgtime_counter_inc(mg_fine_stamps);
+ }
+ }
+ mgtime_counter_inc(mg_ctime_updates);
+
+ /* No need to cmpxchg if it's exactly the same */
+ if (cns == now.tv_nsec && inode->i_ctime_sec == now.tv_sec) {
+ trace_ctime_xchg_skip(inode, &now);
+ goto out;
+ }
+ cur = cns;
+retry:
+ /* Try to swap the nsec value into place. */
+ if (try_cmpxchg(&inode->i_ctime_nsec, &cur, now.tv_nsec)) {
+ /* If swap occurred, then we're (mostly) done */
+ inode->i_ctime_sec = now.tv_sec;
+ trace_ctime_ns_xchg(inode, cns, now.tv_nsec, cur);
+ mgtime_counter_inc(mg_ctime_swaps);
+ } else {
+ /*
+ * Was the change due to someone marking the old ctime QUERIED?
+ * If so then retry the swap. This can only happen once since
+ * the only way to clear I_CTIME_QUERIED is to stamp the inode
+ * with a new ctime.
+ */
+ if (!(cns & I_CTIME_QUERIED) && (cns | I_CTIME_QUERIED) == cur) {
+ cns = cur;
+ goto retry;
+ }
+ /* Otherwise, keep the existing ctime */
+ now.tv_sec = inode->i_ctime_sec;
+ now.tv_nsec = cur & ~I_CTIME_QUERIED;
+ }
+out:
+ return now;
}
-EXPORT_SYMBOL(current_time);
+EXPORT_SYMBOL(inode_set_ctime_current);
/**
- * inode_set_ctime_current - set the ctime to current_time
- * @inode: inode
+ * inode_set_ctime_deleg - try to update the ctime on a delegated inode
+ * @inode: inode to update
+ * @update: timespec64 to set the ctime
*
- * Set the inode->i_ctime to the current value for the inode. Returns
- * the current value that was assigned to i_ctime.
+ * Attempt to atomically update the ctime on behalf of a delegation holder.
+ *
+ * The nfs server can call back the holder of a delegation to get updated
+ * inode attributes, including the mtime. When updating the mtime, update
+ * the ctime to a value at least equal to that.
+ *
+ * This can race with concurrent updates to the inode, in which
+ * case the update is skipped.
+ *
+ * Note that this works even when multigrain timestamps are not enabled,
+ * so it is used in either case.
*/
-struct timespec64 inode_set_ctime_current(struct inode *inode)
+struct timespec64 inode_set_ctime_deleg(struct inode *inode, struct timespec64 update)
{
- struct timespec64 now = current_time(inode);
+ struct timespec64 now, cur_ts;
+ u32 cur, old;
- inode_set_ctime_to_ts(inode, now);
- return now;
+ /* pairs with try_cmpxchg below */
+ cur = smp_load_acquire(&inode->i_ctime_nsec);
+ cur_ts.tv_nsec = cur & ~I_CTIME_QUERIED;
+ cur_ts.tv_sec = inode->i_ctime_sec;
+
+ /* If the update is older than the existing value, skip it. */
+ if (timespec64_compare(&update, &cur_ts) <= 0)
+ return cur_ts;
+
+ ktime_get_coarse_real_ts64_mg(&now);
+
+ /* Clamp the update to "now" if it's in the future */
+ if (timespec64_compare(&update, &now) > 0)
+ update = now;
+
+ update = timestamp_truncate(update, inode);
+
+ /* No need to update if the values are already the same */
+ if (timespec64_equal(&update, &cur_ts))
+ return cur_ts;
+
+ /*
+ * Try to swap the nsec value into place. If it fails, that means
+ * it raced with an update due to a write or similar activity. That
+ * stamp takes precedence, so just skip the update.
+ */
+retry:
+ old = cur;
+ if (try_cmpxchg(&inode->i_ctime_nsec, &cur, update.tv_nsec)) {
+ inode->i_ctime_sec = update.tv_sec;
+ mgtime_counter_inc(mg_ctime_swaps);
+ return update;
+ }
+
+ /*
+ * Was the change due to another task marking the old ctime QUERIED?
+ *
+ * If so, then retry the swap. This can only happen once since
+ * the only way to clear I_CTIME_QUERIED is to stamp the inode
+ * with a new ctime.
+ */
+ if (!(old & I_CTIME_QUERIED) && (cur == (old | I_CTIME_QUERIED)))
+ goto retry;
+
+ /* Otherwise, it was a new timestamp. */
+ cur_ts.tv_sec = inode->i_ctime_sec;
+ cur_ts.tv_nsec = cur & ~I_CTIME_QUERIED;
+ return cur_ts;
}
-EXPORT_SYMBOL(inode_set_ctime_current);
+EXPORT_SYMBOL(inode_set_ctime_deleg);
/**
* in_group_or_capable - check whether caller is CAP_FSETID privileged
@@ -2672,7 +2911,7 @@ EXPORT_SYMBOL(inode_set_ctime_current);
* @inode: inode to check
* @vfsgid: the new/current vfsgid of @inode
*
- * Check wether @vfsgid is in the caller's group list or if the caller is
+ * Check whether @vfsgid is in the caller's group list or if the caller is
* privileged with CAP_FSETID over @inode. This can be used to determine
* whether the setgid bit can be kept or must be dropped.
*
diff --git a/fs/internal.h b/fs/internal.h
index 8c1b7acbbe8f..e7f02ae1e098 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -246,7 +246,6 @@ int open_namespace(struct ns_common *ns);
* fs/stat.c:
*/
-int getname_statx_lookup_flags(int flags);
int do_statx(int dfd, struct filename *filename, unsigned int flags,
unsigned int mask, struct statx __user *buffer);
int do_statx_fd(int fd, unsigned int flags, unsigned int mask,
@@ -267,7 +266,7 @@ struct xattr_name {
char name[XATTR_NAME_MAX + 1];
};
-struct xattr_ctx {
+struct kernel_xattr_ctx {
/* Value of attribute */
union {
const void __user *cvalue;
@@ -280,14 +279,15 @@ struct xattr_ctx {
unsigned int flags;
};
+ssize_t file_getxattr(struct file *file, struct kernel_xattr_ctx *ctx);
+ssize_t filename_getxattr(int dfd, struct filename *filename,
+ unsigned int lookup_flags, struct kernel_xattr_ctx *ctx);
+int file_setxattr(struct file *file, struct kernel_xattr_ctx *ctx);
+int filename_setxattr(int dfd, struct filename *filename,
+ unsigned int lookup_flags, struct kernel_xattr_ctx *ctx);
+int setxattr_copy(const char __user *name, struct kernel_xattr_ctx *ctx);
+int import_xattr_name(struct xattr_name *kname, const char __user *name);
-ssize_t do_getxattr(struct mnt_idmap *idmap,
- struct dentry *d,
- struct xattr_ctx *ctx);
-
-int setxattr_copy(const char __user *name, struct xattr_ctx *ctx);
-int do_setxattr(struct mnt_idmap *idmap, struct dentry *dentry,
- struct xattr_ctx *ctx);
int may_write_xattr(struct mnt_idmap *idmap, struct inode *inode);
#ifdef CONFIG_FS_POSIX_ACL
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 6e0c954388d4..638a36be31c1 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -231,11 +231,11 @@ static int ioctl_fiemap(struct file *filp, struct fiemap __user *ufiemap)
static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd,
u64 off, u64 olen, u64 destoff)
{
- struct fd src_file = fdget(srcfd);
+ CLASS(fd, src_file)(srcfd);
loff_t cloned;
int ret;
- if (!fd_file(src_file))
+ if (fd_empty(src_file))
return -EBADF;
cloned = vfs_clone_file_range(fd_file(src_file), off, dst_file, destoff,
olen, 0);
@@ -245,7 +245,6 @@ static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd,
ret = -EINVAL;
else
ret = 0;
- fdput(src_file);
return ret;
}
@@ -892,22 +891,20 @@ static int do_vfs_ioctl(struct file *filp, unsigned int fd,
SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg)
{
- struct fd f = fdget(fd);
+ CLASS(fd, f)(fd);
int error;
- if (!fd_file(f))
+ if (fd_empty(f))
return -EBADF;
error = security_file_ioctl(fd_file(f), cmd, arg);
if (error)
- goto out;
+ return error;
error = do_vfs_ioctl(fd_file(f), fd, cmd, arg);
if (error == -ENOIOCTLCMD)
error = vfs_ioctl(fd_file(f), cmd, arg);
-out:
- fdput(f);
return error;
}
@@ -950,15 +947,15 @@ EXPORT_SYMBOL(compat_ptr_ioctl);
COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd,
compat_ulong_t, arg)
{
- struct fd f = fdget(fd);
+ CLASS(fd, f)(fd);
int error;
- if (!fd_file(f))
+ if (fd_empty(f))
return -EBADF;
error = security_file_ioctl_compat(fd_file(f), cmd, arg);
if (error)
- goto out;
+ return error;
switch (cmd) {
/* FICLONE takes an int argument, so don't use compat_ptr() */
@@ -1009,10 +1006,6 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd,
error = -ENOTTY;
break;
}
-
- out:
- fdput(f);
-
return error;
}
#endif
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index ef0b68bccbb6..ce73d2a48c1e 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1784,7 +1784,7 @@ new_ioend:
if (ifs)
atomic_add(len, &ifs->write_bytes_pending);
wpc->ioend->io_size += len;
- wbc_account_cgroup_owner(wbc, &folio->page, len);
+ wbc_account_cgroup_owner(wbc, folio, len);
return 0;
}
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index f637aa0706a3..b521eb15759e 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -271,7 +271,7 @@ static int iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio,
* clearing the WRITE_THROUGH flag in the dio request.
*/
static inline blk_opf_t iomap_dio_bio_opflags(struct iomap_dio *dio,
- const struct iomap *iomap, bool use_fua)
+ const struct iomap *iomap, bool use_fua, bool atomic)
{
blk_opf_t opflags = REQ_SYNC | REQ_IDLE;
@@ -283,6 +283,8 @@ static inline blk_opf_t iomap_dio_bio_opflags(struct iomap_dio *dio,
opflags |= REQ_FUA;
else
dio->flags &= ~IOMAP_DIO_WRITE_THROUGH;
+ if (atomic)
+ opflags |= REQ_ATOMIC;
return opflags;
}
@@ -293,7 +295,8 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
const struct iomap *iomap = &iter->iomap;
struct inode *inode = iter->inode;
unsigned int fs_block_size = i_blocksize(inode), pad;
- loff_t length = iomap_length(iter);
+ const loff_t length = iomap_length(iter);
+ bool atomic = iter->flags & IOMAP_ATOMIC;
loff_t pos = iter->pos;
blk_opf_t bio_opf;
struct bio *bio;
@@ -303,6 +306,9 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
size_t copied = 0;
size_t orig_count;
+ if (atomic && length != fs_block_size)
+ return -EINVAL;
+
if ((pos | length) & (bdev_logical_block_size(iomap->bdev) - 1) ||
!bdev_iter_is_aligned(iomap->bdev, dio->submit.iter))
return -EINVAL;
@@ -377,12 +383,7 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
goto out;
}
- /*
- * Set the operation flags early so that bio_iov_iter_get_pages
- * can set up the page vector appropriately for a ZONE_APPEND
- * operation.
- */
- bio_opf = iomap_dio_bio_opflags(dio, iomap, use_fua);
+ bio_opf = iomap_dio_bio_opflags(dio, iomap, use_fua, atomic);
nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter, BIO_MAX_VECS);
do {
@@ -415,6 +416,17 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
}
n = bio->bi_iter.bi_size;
+ if (WARN_ON_ONCE(atomic && n != length)) {
+ /*
+ * This bio should have covered the complete length,
+ * which it doesn't, so error. We may need to zero out
+ * the tail (complete FS block), similar to when
+ * bio_iov_iter_get_pages() returns an error, above.
+ */
+ ret = -EINVAL;
+ bio_put(bio);
+ goto zero_tail;
+ }
if (dio->flags & IOMAP_DIO_WRITE) {
task_io_account_write(n);
} else {
@@ -598,6 +610,9 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
if (iocb->ki_flags & IOCB_NOWAIT)
iomi.flags |= IOMAP_NOWAIT;
+ if (iocb->ki_flags & IOCB_ATOMIC)
+ iomi.flags |= IOMAP_ATOMIC;
+
if (iov_iter_rw(iter) == READ) {
/* reads can always complete inline */
dio->flags |= IOMAP_DIO_INLINE_COMP;
@@ -659,7 +674,17 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
if (ret != -EAGAIN) {
trace_iomap_dio_invalidate_fail(inode, iomi.pos,
iomi.len);
- ret = -ENOTBLK;
+ if (iocb->ki_flags & IOCB_ATOMIC) {
+ /*
+ * folio invalidation failed, maybe
+ * this is transient, unlock and see if
+ * the caller tries again.
+ */
+ ret = -EAGAIN;
+ } else {
+ /* fall back to buffered write */
+ ret = -ENOTBLK;
+ }
}
goto out_free_dio;
}
diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h
index 0a991c4ce87d..4118a42cdab0 100644
--- a/fs/iomap/trace.h
+++ b/fs/iomap/trace.h
@@ -98,7 +98,8 @@ DEFINE_RANGE_EVENT(iomap_dio_rw_queued);
{ IOMAP_REPORT, "REPORT" }, \
{ IOMAP_FAULT, "FAULT" }, \
{ IOMAP_DIRECT, "DIRECT" }, \
- { IOMAP_NOWAIT, "NOWAIT" }
+ { IOMAP_NOWAIT, "NOWAIT" }, \
+ { IOMAP_ATOMIC, "ATOMIC" }
#define IOMAP_F_FLAGS_STRINGS \
{ IOMAP_F_NEW, "NEW" }, \
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 4305a1ac808a..9153ff3a08e7 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -662,10 +662,6 @@ void jbd2_journal_commit_transaction(journal_t *journal)
JBUFFER_TRACE(jh, "ph3: write metadata");
escape = jbd2_journal_write_metadata_buffer(commit_transaction,
jh, &wbuf[bufs], blocknr);
- if (escape < 0) {
- jbd2_journal_abort(journal, escape);
- continue;
- }
jbd2_file_log_bh(&io_bufs, wbuf[bufs]);
/* Record the new block's tag in the current descriptor
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 97f487c3d8fc..7e49d912b091 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -318,7 +318,6 @@ static inline void jbd2_data_do_escape(char *data)
*
*
* Return value:
- * <0: Error
* =0: Finished OK without escape
* =1: Finished OK with escape
*/
@@ -386,12 +385,7 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
goto escape_done;
spin_unlock(&jh_in->b_state_lock);
- tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS);
- if (!tmp) {
- brelse(new_bh);
- free_buffer_head(new_bh);
- return -ENOMEM;
- }
+ tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS | __GFP_NOFAIL);
spin_lock(&jh_in->b_state_lock);
if (jh_in->b_frozen_data) {
jbd2_free(tmp, bh_in->b_size);
@@ -1518,9 +1512,10 @@ static int journal_load_superblock(journal_t *journal)
* destroy journal_t structures, and to initialise and read existing
* journal blocks from disk. */
-/* First: create and setup a journal_t object in memory. We initialise
- * very few fields yet: that has to wait until we have created the
- * journal structures from from scratch, or loaded them from disk. */
+/* The journal_init_common() function creates and fills a journal_t object
+ * in memory. It calls journal_load_superblock() to load the on-disk journal
+ * superblock and initialize the journal_t object.
+ */
static journal_t *journal_init_common(struct block_device *bdev,
struct block_device *fs_dev,
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 667f67342c52..9192be7c19d8 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -485,6 +485,104 @@ static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag,
return tag->t_checksum == cpu_to_be16(csum32);
}
+static __always_inline int jbd2_do_replay(journal_t *journal,
+ struct recovery_info *info,
+ struct buffer_head *bh,
+ unsigned long *next_log_block,
+ unsigned int next_commit_ID)
+{
+ char *tagp;
+ int flags;
+ int ret = 0;
+ int tag_bytes = journal_tag_bytes(journal);
+ int descr_csum_size = 0;
+ unsigned long io_block;
+ journal_block_tag_t tag;
+ struct buffer_head *obh;
+ struct buffer_head *nbh;
+
+ if (jbd2_journal_has_csum_v2or3(journal))
+ descr_csum_size = sizeof(struct jbd2_journal_block_tail);
+
+ tagp = &bh->b_data[sizeof(journal_header_t)];
+ while (tagp - bh->b_data + tag_bytes <=
+ journal->j_blocksize - descr_csum_size) {
+ int err;
+
+ memcpy(&tag, tagp, sizeof(tag));
+ flags = be16_to_cpu(tag.t_flags);
+
+ io_block = (*next_log_block)++;
+ wrap(journal, *next_log_block);
+ err = jread(&obh, journal, io_block);
+ if (err) {
+ /* Recover what we can, but report failure at the end. */
+ ret = err;
+ pr_err("JBD2: IO error %d recovering block %lu in log\n",
+ err, io_block);
+ } else {
+ unsigned long long blocknr;
+
+ J_ASSERT(obh != NULL);
+ blocknr = read_tag_block(journal, &tag);
+
+ /* If the block has been revoked, then we're all done here. */
+ if (jbd2_journal_test_revoke(journal, blocknr,
+ next_commit_ID)) {
+ brelse(obh);
+ ++info->nr_revoke_hits;
+ goto skip_write;
+ }
+
+ /* Look for block corruption */
+ if (!jbd2_block_tag_csum_verify(journal, &tag,
+ (journal_block_tag3_t *)tagp,
+ obh->b_data, next_commit_ID)) {
+ brelse(obh);
+ ret = -EFSBADCRC;
+ pr_err("JBD2: Invalid checksum recovering data block %llu in journal block %lu\n",
+ blocknr, io_block);
+ goto skip_write;
+ }
+
+ /* Find a buffer for the new data being restored */
+ nbh = __getblk(journal->j_fs_dev, blocknr,
+ journal->j_blocksize);
+ if (nbh == NULL) {
+ pr_err("JBD2: Out of memory during recovery.\n");
+ brelse(obh);
+ return -ENOMEM;
+ }
+
+ lock_buffer(nbh);
+ memcpy(nbh->b_data, obh->b_data, journal->j_blocksize);
+ if (flags & JBD2_FLAG_ESCAPE) {
+ *((__be32 *)nbh->b_data) =
+ cpu_to_be32(JBD2_MAGIC_NUMBER);
+ }
+
+ BUFFER_TRACE(nbh, "marking dirty");
+ set_buffer_uptodate(nbh);
+ mark_buffer_dirty(nbh);
+ BUFFER_TRACE(nbh, "marking uptodate");
+ ++info->nr_replays;
+ unlock_buffer(nbh);
+ brelse(obh);
+ brelse(nbh);
+ }
+
+skip_write:
+ tagp += tag_bytes;
+ if (!(flags & JBD2_FLAG_SAME_UUID))
+ tagp += 16;
+
+ if (flags & JBD2_FLAG_LAST_TAG)
+ break;
+ }
+
+ return ret;
+}
+
static int do_one_pass(journal_t *journal,
struct recovery_info *info, enum passtype pass)
{
@@ -493,13 +591,10 @@ static int do_one_pass(journal_t *journal,
int err, success = 0;
journal_superblock_t * sb;
journal_header_t * tmp;
- struct buffer_head * bh;
+ struct buffer_head *bh = NULL;
unsigned int sequence;
int blocktype;
- int tag_bytes = journal_tag_bytes(journal);
__u32 crc32_sum = ~0; /* Transactional Checksums */
- int descr_csum_size = 0;
- int block_error = 0;
bool need_check_commit_time = false;
__u64 last_trans_commit_time = 0, commit_time;
@@ -528,12 +623,6 @@ static int do_one_pass(journal_t *journal,
*/
while (1) {
- int flags;
- char * tagp;
- journal_block_tag_t tag;
- struct buffer_head * obh;
- struct buffer_head * nbh;
-
cond_resched();
/* If we already know where to stop the log traversal,
@@ -552,6 +641,8 @@ static int do_one_pass(journal_t *journal,
* record. */
jbd2_debug(3, "JBD2: checking block %ld\n", next_log_block);
+ brelse(bh);
+ bh = NULL;
err = jread(&bh, journal, next_log_block);
if (err)
goto failed;
@@ -567,20 +658,16 @@ static int do_one_pass(journal_t *journal,
tmp = (journal_header_t *)bh->b_data;
- if (tmp->h_magic != cpu_to_be32(JBD2_MAGIC_NUMBER)) {
- brelse(bh);
+ if (tmp->h_magic != cpu_to_be32(JBD2_MAGIC_NUMBER))
break;
- }
blocktype = be32_to_cpu(tmp->h_blocktype);
sequence = be32_to_cpu(tmp->h_sequence);
jbd2_debug(3, "Found magic %d, sequence %d\n",
blocktype, sequence);
- if (sequence != next_commit_ID) {
- brelse(bh);
+ if (sequence != next_commit_ID)
break;
- }
/* OK, we have a valid descriptor block which matches
* all of the sequence number checks. What are we going
@@ -589,11 +676,7 @@ static int do_one_pass(journal_t *journal,
switch(blocktype) {
case JBD2_DESCRIPTOR_BLOCK:
/* Verify checksum first */
- if (jbd2_journal_has_csum_v2or3(journal))
- descr_csum_size =
- sizeof(struct jbd2_journal_block_tail);
- if (descr_csum_size > 0 &&
- !jbd2_descriptor_block_csum_verify(journal,
+ if (!jbd2_descriptor_block_csum_verify(journal,
bh->b_data)) {
/*
* PASS_SCAN can see stale blocks due to lazy
@@ -603,7 +686,6 @@ static int do_one_pass(journal_t *journal,
pr_err("JBD2: Invalid checksum recovering block %lu in log\n",
next_log_block);
err = -EFSBADCRC;
- brelse(bh);
goto failed;
}
need_check_commit_time = true;
@@ -619,125 +701,39 @@ static int do_one_pass(journal_t *journal,
if (pass != PASS_REPLAY) {
if (pass == PASS_SCAN &&
jbd2_has_feature_checksum(journal) &&
- !need_check_commit_time &&
!info->end_transaction) {
if (calc_chksums(journal, bh,
&next_log_block,
- &crc32_sum)) {
- put_bh(bh);
+ &crc32_sum))
break;
- }
- put_bh(bh);
continue;
}
next_log_block += count_tags(journal, bh);
wrap(journal, next_log_block);
- put_bh(bh);
continue;
}
- /* A descriptor block: we can now write all of
- * the data blocks. Yay, useful work is finally
- * getting done here! */
-
- tagp = &bh->b_data[sizeof(journal_header_t)];
- while ((tagp - bh->b_data + tag_bytes)
- <= journal->j_blocksize - descr_csum_size) {
- unsigned long io_block;
-
- memcpy(&tag, tagp, sizeof(tag));
- flags = be16_to_cpu(tag.t_flags);
-
- io_block = next_log_block++;
- wrap(journal, next_log_block);
- err = jread(&obh, journal, io_block);
- if (err) {
- /* Recover what we can, but
- * report failure at the end. */
- success = err;
- printk(KERN_ERR
- "JBD2: IO error %d recovering "
- "block %lu in log\n",
- err, io_block);
- } else {
- unsigned long long blocknr;
-
- J_ASSERT(obh != NULL);
- blocknr = read_tag_block(journal,
- &tag);
-
- /* If the block has been
- * revoked, then we're all done
- * here. */
- if (jbd2_journal_test_revoke
- (journal, blocknr,
- next_commit_ID)) {
- brelse(obh);
- ++info->nr_revoke_hits;
- goto skip_write;
- }
-
- /* Look for block corruption */
- if (!jbd2_block_tag_csum_verify(
- journal, &tag, (journal_block_tag3_t *)tagp,
- obh->b_data, be32_to_cpu(tmp->h_sequence))) {
- brelse(obh);
- success = -EFSBADCRC;
- printk(KERN_ERR "JBD2: Invalid "
- "checksum recovering "
- "data block %llu in "
- "journal block %lu\n",
- blocknr, io_block);
- block_error = 1;
- goto skip_write;
- }
-
- /* Find a buffer for the new
- * data being restored */
- nbh = __getblk(journal->j_fs_dev,
- blocknr,
- journal->j_blocksize);
- if (nbh == NULL) {
- printk(KERN_ERR
- "JBD2: Out of memory "
- "during recovery.\n");
- err = -ENOMEM;
- brelse(bh);
- brelse(obh);
- goto failed;
- }
-
- lock_buffer(nbh);
- memcpy(nbh->b_data, obh->b_data,
- journal->j_blocksize);
- if (flags & JBD2_FLAG_ESCAPE) {
- *((__be32 *)nbh->b_data) =
- cpu_to_be32(JBD2_MAGIC_NUMBER);
- }
-
- BUFFER_TRACE(nbh, "marking dirty");
- set_buffer_uptodate(nbh);
- mark_buffer_dirty(nbh);
- BUFFER_TRACE(nbh, "marking uptodate");
- ++info->nr_replays;
- unlock_buffer(nbh);
- brelse(obh);
- brelse(nbh);
- }
-
- skip_write:
- tagp += tag_bytes;
- if (!(flags & JBD2_FLAG_SAME_UUID))
- tagp += 16;
-
- if (flags & JBD2_FLAG_LAST_TAG)
- break;
+ /*
+ * A descriptor block: we can now write all of the
+ * data blocks. Yay, useful work is finally getting
+ * done here!
+ */
+ err = jbd2_do_replay(journal, info, bh, &next_log_block,
+ next_commit_ID);
+ if (err) {
+ if (err == -ENOMEM)
+ goto failed;
+ success = err;
}
- brelse(bh);
continue;
case JBD2_COMMIT_BLOCK:
+ if (pass != PASS_SCAN) {
+ next_commit_ID++;
+ continue;
+ }
+
/* How to differentiate between interrupted commit
* and journal corruption ?
*
@@ -782,7 +778,6 @@ static int do_one_pass(journal_t *journal,
pr_err("JBD2: Invalid checksum found in transaction %u\n",
next_commit_ID);
err = -EFSBADCRC;
- brelse(bh);
goto failed;
}
ignore_crc_mismatch:
@@ -792,7 +787,6 @@ static int do_one_pass(journal_t *journal,
*/
jbd2_debug(1, "JBD2: Invalid checksum ignored in transaction %u, likely stale data\n",
next_commit_ID);
- brelse(bh);
goto done;
}
@@ -802,8 +796,7 @@ static int do_one_pass(journal_t *journal,
* much to do other than move on to the next sequence
* number.
*/
- if (pass == PASS_SCAN &&
- jbd2_has_feature_checksum(journal)) {
+ if (jbd2_has_feature_checksum(journal)) {
struct commit_header *cbh =
(struct commit_header *)bh->b_data;
unsigned found_chksum =
@@ -812,7 +805,6 @@ static int do_one_pass(journal_t *journal,
if (info->end_transaction) {
journal->j_failed_commit =
info->end_transaction;
- brelse(bh);
break;
}
@@ -828,36 +820,33 @@ static int do_one_pass(journal_t *journal,
goto chksum_error;
crc32_sum = ~0;
+ goto chksum_ok;
}
- if (pass == PASS_SCAN &&
- !jbd2_commit_block_csum_verify(journal,
- bh->b_data)) {
- if (jbd2_commit_block_csum_verify_partial(
- journal,
- bh->b_data)) {
- pr_notice("JBD2: Find incomplete commit block in transaction %u block %lu\n",
- next_commit_ID, next_log_block);
- goto chksum_ok;
- }
- chksum_error:
- if (commit_time < last_trans_commit_time)
- goto ignore_crc_mismatch;
- info->end_transaction = next_commit_ID;
- info->head_block = head_block;
- if (!jbd2_has_feature_async_commit(journal)) {
- journal->j_failed_commit =
- next_commit_ID;
- brelse(bh);
- break;
- }
+ if (jbd2_commit_block_csum_verify(journal, bh->b_data))
+ goto chksum_ok;
+
+ if (jbd2_commit_block_csum_verify_partial(journal,
+ bh->b_data)) {
+ pr_notice("JBD2: Find incomplete commit block in transaction %u block %lu\n",
+ next_commit_ID, next_log_block);
+ goto chksum_ok;
}
- if (pass == PASS_SCAN) {
- chksum_ok:
- last_trans_commit_time = commit_time;
- head_block = next_log_block;
+
+chksum_error:
+ if (commit_time < last_trans_commit_time)
+ goto ignore_crc_mismatch;
+ info->end_transaction = next_commit_ID;
+ info->head_block = head_block;
+
+ if (!jbd2_has_feature_async_commit(journal)) {
+ journal->j_failed_commit = next_commit_ID;
+ break;
}
- brelse(bh);
+
+chksum_ok:
+ last_trans_commit_time = commit_time;
+ head_block = next_log_block;
next_commit_ID++;
continue;
@@ -876,14 +865,11 @@ static int do_one_pass(journal_t *journal,
/* If we aren't in the REVOKE pass, then we can
* just skip over this block. */
- if (pass != PASS_REVOKE) {
- brelse(bh);
+ if (pass != PASS_REVOKE)
continue;
- }
err = scan_revoke_records(journal, bh,
next_commit_ID, info);
- brelse(bh);
if (err)
goto failed;
continue;
@@ -891,12 +877,12 @@ static int do_one_pass(journal_t *journal,
default:
jbd2_debug(3, "Unrecognised magic %d, end of scan.\n",
blocktype);
- brelse(bh);
goto done;
}
}
done:
+ brelse(bh);
/*
* We broke out of the log scan loop: either we came to the
* known end of the log or we found an unexpected block in the
@@ -927,11 +913,10 @@ static int do_one_pass(journal_t *journal,
success = err;
}
- if (block_error && success == 0)
- success = -EIO;
return success;
failed:
+ brelse(bh);
return err;
}
diff --git a/fs/jfs/jfs_filsys.h b/fs/jfs/jfs_filsys.h
index 33ef13a0b110..8794281f8ffd 100644
--- a/fs/jfs/jfs_filsys.h
+++ b/fs/jfs/jfs_filsys.h
@@ -24,6 +24,7 @@
#define JFS_ERR_REMOUNT_RO 0x00000002 /* remount read-only */
#define JFS_ERR_CONTINUE 0x00000004 /* continue */
#define JFS_ERR_PANIC 0x00000008 /* panic */
+#define JFS_ERR_MASK (JFS_ERR_REMOUNT_RO|JFS_ERR_CONTINUE|JFS_ERR_PANIC)
/* Quota support */
#define JFS_USRQUOTA 0x00000010
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index e1be21ca5d6e..223d9ac59839 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -6,11 +6,11 @@
#include <linux/fs.h>
#include <linux/module.h>
-#include <linux/parser.h>
#include <linux/completion.h>
#include <linux/vfs.h>
#include <linux/quotaops.h>
-#include <linux/mount.h>
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
#include <linux/moduleparam.h>
#include <linux/kthread.h>
#include <linux/posix_acl.h>
@@ -210,240 +210,195 @@ enum {
Opt_discard, Opt_nodiscard, Opt_discard_minblk
};
-static const match_table_t tokens = {
- {Opt_integrity, "integrity"},
- {Opt_nointegrity, "nointegrity"},
- {Opt_iocharset, "iocharset=%s"},
- {Opt_resize, "resize=%u"},
- {Opt_resize_nosize, "resize"},
- {Opt_errors, "errors=%s"},
- {Opt_ignore, "noquota"},
- {Opt_quota, "quota"},
- {Opt_usrquota, "usrquota"},
- {Opt_grpquota, "grpquota"},
- {Opt_uid, "uid=%u"},
- {Opt_gid, "gid=%u"},
- {Opt_umask, "umask=%u"},
- {Opt_discard, "discard"},
- {Opt_nodiscard, "nodiscard"},
- {Opt_discard_minblk, "discard=%u"},
- {Opt_err, NULL}
+static const struct constant_table jfs_param_errors[] = {
+ {"continue", JFS_ERR_CONTINUE},
+ {"remount-ro", JFS_ERR_REMOUNT_RO},
+ {"panic", JFS_ERR_PANIC},
+ {}
};
-static int parse_options(char *options, struct super_block *sb, s64 *newLVSize,
- int *flag)
-{
- void *nls_map = (void *)-1; /* -1: no change; NULL: none */
- char *p;
- struct jfs_sb_info *sbi = JFS_SBI(sb);
+static const struct fs_parameter_spec jfs_param_spec[] = {
+ fsparam_flag_no ("integrity", Opt_integrity),
+ fsparam_string ("iocharset", Opt_iocharset),
+ fsparam_u64 ("resize", Opt_resize),
+ fsparam_flag ("resize", Opt_resize_nosize),
+ fsparam_enum ("errors", Opt_errors, jfs_param_errors),
+ fsparam_flag ("quota", Opt_quota),
+ fsparam_flag ("noquota", Opt_ignore),
+ fsparam_flag ("usrquota", Opt_usrquota),
+ fsparam_flag ("grpquota", Opt_grpquota),
+ fsparam_uid ("uid", Opt_uid),
+ fsparam_gid ("gid", Opt_gid),
+ fsparam_u32oct ("umask", Opt_umask),
+ fsparam_flag ("discard", Opt_discard),
+ fsparam_u32 ("discard", Opt_discard_minblk),
+ fsparam_flag ("nodiscard", Opt_nodiscard),
+ {}
+};
- *newLVSize = 0;
-
- if (!options)
- return 1;
-
- while ((p = strsep(&options, ",")) != NULL) {
- substring_t args[MAX_OPT_ARGS];
- int token;
- if (!*p)
- continue;
-
- token = match_token(p, tokens, args);
- switch (token) {
- case Opt_integrity:
- *flag &= ~JFS_NOINTEGRITY;
- break;
- case Opt_nointegrity:
- *flag |= JFS_NOINTEGRITY;
- break;
- case Opt_ignore:
- /* Silently ignore the quota options */
- /* Don't do anything ;-) */
- break;
- case Opt_iocharset:
- if (nls_map && nls_map != (void *) -1)
- unload_nls(nls_map);
- if (!strcmp(args[0].from, "none"))
- nls_map = NULL;
- else {
- nls_map = load_nls(args[0].from);
- if (!nls_map) {
- pr_err("JFS: charset not found\n");
- goto cleanup;
- }
- }
- break;
- case Opt_resize:
- {
- char *resize = args[0].from;
- int rc = kstrtoll(resize, 0, newLVSize);
+struct jfs_context {
+ int flag;
+ kuid_t uid;
+ kgid_t gid;
+ uint umask;
+ uint minblks_trim;
+ void *nls_map;
+ bool resize;
+ s64 newLVSize;
+};
- if (rc)
- goto cleanup;
- break;
- }
- case Opt_resize_nosize:
- {
- *newLVSize = sb_bdev_nr_blocks(sb);
- if (*newLVSize == 0)
- pr_err("JFS: Cannot determine volume size\n");
- break;
+static int jfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+ struct jfs_context *ctx = fc->fs_private;
+ int reconfigure = (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE);
+ struct fs_parse_result result;
+ struct nls_table *nls_map;
+ int opt;
+
+ opt = fs_parse(fc, jfs_param_spec, param, &result);
+ if (opt < 0)
+ return opt;
+
+ switch (opt) {
+ case Opt_integrity:
+ if (result.negated)
+ ctx->flag |= JFS_NOINTEGRITY;
+ else
+ ctx->flag &= ~JFS_NOINTEGRITY;
+ break;
+ case Opt_ignore:
+ /* Silently ignore the quota options */
+ /* Don't do anything ;-) */
+ break;
+ case Opt_iocharset:
+ if (ctx->nls_map && ctx->nls_map != (void *) -1) {
+ unload_nls(ctx->nls_map);
+ ctx->nls_map = NULL;
}
- case Opt_errors:
- {
- char *errors = args[0].from;
- if (!errors || !*errors)
- goto cleanup;
- if (!strcmp(errors, "continue")) {
- *flag &= ~JFS_ERR_REMOUNT_RO;
- *flag &= ~JFS_ERR_PANIC;
- *flag |= JFS_ERR_CONTINUE;
- } else if (!strcmp(errors, "remount-ro")) {
- *flag &= ~JFS_ERR_CONTINUE;
- *flag &= ~JFS_ERR_PANIC;
- *flag |= JFS_ERR_REMOUNT_RO;
- } else if (!strcmp(errors, "panic")) {
- *flag &= ~JFS_ERR_CONTINUE;
- *flag &= ~JFS_ERR_REMOUNT_RO;
- *flag |= JFS_ERR_PANIC;
- } else {
- pr_err("JFS: %s is an invalid error handler\n",
- errors);
- goto cleanup;
+ if (!strcmp(param->string, "none"))
+ ctx->nls_map = NULL;
+ else {
+ nls_map = load_nls(param->string);
+ if (!nls_map) {
+ pr_err("JFS: charset not found\n");
+ return -EINVAL;
}
- break;
+ ctx->nls_map = nls_map;
}
+ break;
+ case Opt_resize:
+ if (!reconfigure)
+ return -EINVAL;
+ ctx->resize = true;
+ ctx->newLVSize = result.uint_64;
+ break;
+ case Opt_resize_nosize:
+ if (!reconfigure)
+ return -EINVAL;
+ ctx->resize = true;
+ break;
+ case Opt_errors:
+ ctx->flag &= ~JFS_ERR_MASK;
+ ctx->flag |= result.uint_32;
+ break;
#ifdef CONFIG_QUOTA
- case Opt_quota:
- case Opt_usrquota:
- *flag |= JFS_USRQUOTA;
- break;
- case Opt_grpquota:
- *flag |= JFS_GRPQUOTA;
- break;
+ case Opt_quota:
+ case Opt_usrquota:
+ ctx->flag |= JFS_USRQUOTA;
+ break;
+ case Opt_grpquota:
+ ctx->flag |= JFS_GRPQUOTA;
+ break;
#else
- case Opt_usrquota:
- case Opt_grpquota:
- case Opt_quota:
- pr_err("JFS: quota operations not supported\n");
- break;
+ case Opt_usrquota:
+ case Opt_grpquota:
+ case Opt_quota:
+ pr_err("JFS: quota operations not supported\n");
+ break;
#endif
- case Opt_uid:
- {
- char *uid = args[0].from;
- uid_t val;
- int rc = kstrtouint(uid, 0, &val);
-
- if (rc)
- goto cleanup;
- sbi->uid = make_kuid(current_user_ns(), val);
- if (!uid_valid(sbi->uid))
- goto cleanup;
- break;
- }
-
- case Opt_gid:
- {
- char *gid = args[0].from;
- gid_t val;
- int rc = kstrtouint(gid, 0, &val);
-
- if (rc)
- goto cleanup;
- sbi->gid = make_kgid(current_user_ns(), val);
- if (!gid_valid(sbi->gid))
- goto cleanup;
- break;
+ case Opt_uid:
+ ctx->uid = result.uid;
+ break;
+
+ case Opt_gid:
+ ctx->gid = result.gid;
+ break;
+
+ case Opt_umask:
+ if (result.uint_32 & ~0777) {
+ pr_err("JFS: Invalid value of umask\n");
+ return -EINVAL;
}
+ ctx->umask = result.uint_32;
+ break;
- case Opt_umask:
- {
- char *umask = args[0].from;
- int rc = kstrtouint(umask, 8, &sbi->umask);
+ case Opt_discard:
+ /* if set to 1, even copying files will cause
+ * trimming :O
+ * -> user has more control over the online trimming
+ */
+ ctx->minblks_trim = 64;
+ ctx->flag |= JFS_DISCARD;
+ break;
- if (rc)
- goto cleanup;
- if (sbi->umask & ~0777) {
- pr_err("JFS: Invalid value of umask\n");
- goto cleanup;
- }
- break;
- }
+ case Opt_nodiscard:
+ ctx->flag &= ~JFS_DISCARD;
+ break;
- case Opt_discard:
- /* if set to 1, even copying files will cause
- * trimming :O
- * -> user has more control over the online trimming
- */
- sbi->minblks_trim = 64;
- if (bdev_max_discard_sectors(sb->s_bdev))
- *flag |= JFS_DISCARD;
- else
- pr_err("JFS: discard option not supported on device\n");
- break;
-
- case Opt_nodiscard:
- *flag &= ~JFS_DISCARD;
- break;
-
- case Opt_discard_minblk:
- {
- char *minblks_trim = args[0].from;
- int rc;
- if (bdev_max_discard_sectors(sb->s_bdev)) {
- *flag |= JFS_DISCARD;
- rc = kstrtouint(minblks_trim, 0,
- &sbi->minblks_trim);
- if (rc)
- goto cleanup;
- } else
- pr_err("JFS: discard option not supported on device\n");
- break;
- }
+ case Opt_discard_minblk:
+ ctx->minblks_trim = result.uint_32;
+ ctx->flag |= JFS_DISCARD;
+ break;
- default:
- printk("jfs: Unrecognized mount option \"%s\" or missing value\n",
- p);
- goto cleanup;
- }
- }
-
- if (nls_map != (void *) -1) {
- /* Discard old (if remount) */
- unload_nls(sbi->nls_tab);
- sbi->nls_tab = nls_map;
+ default:
+ return -EINVAL;
}
- return 1;
-cleanup:
- if (nls_map && nls_map != (void *) -1)
- unload_nls(nls_map);
return 0;
}
-static int jfs_remount(struct super_block *sb, int *flags, char *data)
+static int jfs_reconfigure(struct fs_context *fc)
{
- s64 newLVSize = 0;
+ struct jfs_context *ctx = fc->fs_private;
+ struct super_block *sb = fc->root->d_sb;
+ int readonly = fc->sb_flags & SB_RDONLY;
int rc = 0;
- int flag = JFS_SBI(sb)->flag;
+ int flag = ctx->flag;
int ret;
sync_filesystem(sb);
- if (!parse_options(data, sb, &newLVSize, &flag))
- return -EINVAL;
- if (newLVSize) {
+ /* Transfer results of parsing to the sbi */
+ JFS_SBI(sb)->flag = ctx->flag;
+ JFS_SBI(sb)->uid = ctx->uid;
+ JFS_SBI(sb)->gid = ctx->gid;
+ JFS_SBI(sb)->umask = ctx->umask;
+ JFS_SBI(sb)->minblks_trim = ctx->minblks_trim;
+ if (ctx->nls_map != (void *) -1) {
+ unload_nls(JFS_SBI(sb)->nls_tab);
+ JFS_SBI(sb)->nls_tab = ctx->nls_map;
+ }
+ ctx->nls_map = NULL;
+
+ if (ctx->resize) {
if (sb_rdonly(sb)) {
pr_err("JFS: resize requires volume to be mounted read-write\n");
return -EROFS;
}
- rc = jfs_extendfs(sb, newLVSize, 0);
+
+ if (!ctx->newLVSize) {
+ ctx->newLVSize = sb_bdev_nr_blocks(sb);
+ if (ctx->newLVSize == 0)
+ pr_err("JFS: Cannot determine volume size\n");
+ }
+
+ rc = jfs_extendfs(sb, ctx->newLVSize, 0);
if (rc)
return rc;
}
- if (sb_rdonly(sb) && !(*flags & SB_RDONLY)) {
+ if (sb_rdonly(sb) && !readonly) {
/*
* Invalidate any previously read metadata. fsck may have
* changed the on-disk data since we mounted r/o
@@ -459,7 +414,7 @@ static int jfs_remount(struct super_block *sb, int *flags, char *data)
dquot_resume(sb, -1);
return ret;
}
- if (!sb_rdonly(sb) && (*flags & SB_RDONLY)) {
+ if (!sb_rdonly(sb) && readonly) {
rc = dquot_suspend(sb, -1);
if (rc < 0)
return rc;
@@ -467,7 +422,7 @@ static int jfs_remount(struct super_block *sb, int *flags, char *data)
JFS_SBI(sb)->flag = flag;
return rc;
}
- if ((JFS_SBI(sb)->flag & JFS_NOINTEGRITY) != (flag & JFS_NOINTEGRITY))
+ if ((JFS_SBI(sb)->flag & JFS_NOINTEGRITY) != (flag & JFS_NOINTEGRITY)) {
if (!sb_rdonly(sb)) {
rc = jfs_umount_rw(sb);
if (rc)
@@ -477,18 +432,20 @@ static int jfs_remount(struct super_block *sb, int *flags, char *data)
ret = jfs_mount_rw(sb, 1);
return ret;
}
+ }
JFS_SBI(sb)->flag = flag;
return 0;
}
-static int jfs_fill_super(struct super_block *sb, void *data, int silent)
+static int jfs_fill_super(struct super_block *sb, struct fs_context *fc)
{
+ struct jfs_context *ctx = fc->fs_private;
+ int silent = fc->sb_flags & SB_SILENT;
struct jfs_sb_info *sbi;
struct inode *inode;
int rc;
- s64 newLVSize = 0;
- int flag, ret = -EINVAL;
+ int ret = -EINVAL;
jfs_info("In jfs_read_super: s_flags=0x%lx", sb->s_flags);
@@ -501,24 +458,34 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
sb->s_time_min = 0;
sb->s_time_max = U32_MAX;
sbi->sb = sb;
- sbi->uid = INVALID_UID;
- sbi->gid = INVALID_GID;
- sbi->umask = -1;
-
- /* initialize the mount flag and determine the default error handler */
- flag = JFS_ERR_REMOUNT_RO;
- if (!parse_options((char *) data, sb, &newLVSize, &flag))
- goto out_kfree;
- sbi->flag = flag;
+ /* Transfer results of parsing to the sbi */
+ sbi->flag = ctx->flag;
+ sbi->uid = ctx->uid;
+ sbi->gid = ctx->gid;
+ sbi->umask = ctx->umask;
+ if (ctx->nls_map != (void *) -1) {
+ unload_nls(sbi->nls_tab);
+ sbi->nls_tab = ctx->nls_map;
+ }
+ ctx->nls_map = NULL;
+
+ if (sbi->flag & JFS_DISCARD) {
+ if (!bdev_max_discard_sectors(sb->s_bdev)) {
+ pr_err("JFS: discard option not supported on device\n");
+ sbi->flag &= ~JFS_DISCARD;
+ } else {
+ sbi->minblks_trim = ctx->minblks_trim;
+ }
+ }
#ifdef CONFIG_JFS_POSIX_ACL
sb->s_flags |= SB_POSIXACL;
#endif
- if (newLVSize) {
+ if (ctx->resize) {
pr_err("resize option for remount only\n");
- goto out_kfree;
+ goto out_unload;
}
/*
@@ -608,7 +575,6 @@ out_mount_failed:
sbi->direct_inode = NULL;
out_unload:
unload_nls(sbi->nls_tab);
-out_kfree:
kfree(sbi);
return ret;
}
@@ -664,10 +630,9 @@ out:
return rc;
}
-static struct dentry *jfs_do_mount(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data)
+static int jfs_get_tree(struct fs_context *fc)
{
- return mount_bdev(fs_type, flags, dev_name, data, jfs_fill_super);
+ return get_tree_bdev(fc, jfs_fill_super);
}
static int jfs_sync_fs(struct super_block *sb, int wait)
@@ -886,7 +851,6 @@ static const struct super_operations jfs_super_operations = {
.freeze_fs = jfs_freeze,
.unfreeze_fs = jfs_unfreeze,
.statfs = jfs_statfs,
- .remount_fs = jfs_remount,
.show_options = jfs_show_options,
#ifdef CONFIG_QUOTA
.quota_read = jfs_quota_read,
@@ -902,12 +866,71 @@ static const struct export_operations jfs_export_operations = {
.get_parent = jfs_get_parent,
};
+static void jfs_init_options(struct fs_context *fc, struct jfs_context *ctx)
+{
+ if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) {
+ struct super_block *sb = fc->root->d_sb;
+
+ /* Copy over current option values and mount flags */
+ ctx->uid = JFS_SBI(sb)->uid;
+ ctx->gid = JFS_SBI(sb)->gid;
+ ctx->umask = JFS_SBI(sb)->umask;
+ ctx->nls_map = (void *)-1;
+ ctx->minblks_trim = JFS_SBI(sb)->minblks_trim;
+ ctx->flag = JFS_SBI(sb)->flag;
+
+ } else {
+ /*
+ * Initialize the mount flag and determine the default
+ * error handler
+ */
+ ctx->flag = JFS_ERR_REMOUNT_RO;
+ ctx->uid = INVALID_UID;
+ ctx->gid = INVALID_GID;
+ ctx->umask = -1;
+ ctx->nls_map = (void *)-1;
+ }
+}
+
+static void jfs_free_fc(struct fs_context *fc)
+{
+ struct jfs_context *ctx = fc->fs_private;
+
+ if (ctx->nls_map != (void *) -1)
+ unload_nls(ctx->nls_map);
+ kfree(ctx);
+}
+
+static const struct fs_context_operations jfs_context_ops = {
+ .parse_param = jfs_parse_param,
+ .get_tree = jfs_get_tree,
+ .reconfigure = jfs_reconfigure,
+ .free = jfs_free_fc,
+};
+
+static int jfs_init_fs_context(struct fs_context *fc)
+{
+ struct jfs_context *ctx;
+
+ ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ jfs_init_options(fc, ctx);
+
+ fc->fs_private = ctx;
+ fc->ops = &jfs_context_ops;
+
+ return 0;
+}
+
static struct file_system_type jfs_fs_type = {
.owner = THIS_MODULE,
.name = "jfs",
- .mount = jfs_do_mount,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
+ .init_fs_context = jfs_init_fs_context,
+ .parameters = jfs_param_spec,
};
MODULE_ALIAS_FS("jfs");
diff --git a/fs/kernel_read_file.c b/fs/kernel_read_file.c
index 9ff37ae650ea..de32c95d823d 100644
--- a/fs/kernel_read_file.c
+++ b/fs/kernel_read_file.c
@@ -175,15 +175,11 @@ ssize_t kernel_read_file_from_fd(int fd, loff_t offset, void **buf,
size_t buf_size, size_t *file_size,
enum kernel_read_file_id id)
{
- struct fd f = fdget(fd);
- ssize_t ret = -EBADF;
+ CLASS(fd, f)(fd);
- if (!fd_file(f) || !(fd_file(f)->f_mode & FMODE_READ))
- goto out;
+ if (fd_empty(f) || !(fd_file(f)->f_mode & FMODE_READ))
+ return -EBADF;
- ret = kernel_read_file(fd_file(f), offset, buf, buf_size, file_size, id);
-out:
- fdput(f);
- return ret;
+ return kernel_read_file(fd_file(f), offset, buf, buf_size, file_size, id);
}
EXPORT_SYMBOL_GPL(kernel_read_file_from_fd);
diff --git a/fs/libfs.c b/fs/libfs.c
index 46966fd8bcf9..748ac5923154 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -77,6 +77,10 @@ struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, unsigned
return ERR_PTR(-ENAMETOOLONG);
if (!dentry->d_sb->s_d_op)
d_set_d_op(dentry, &simple_dentry_operations);
+
+ if (IS_ENABLED(CONFIG_UNICODE) && IS_CASEFOLDED(dir))
+ return NULL;
+
d_add(dentry, NULL);
return NULL;
}
@@ -1711,15 +1715,6 @@ static struct dentry *empty_dir_lookup(struct inode *dir, struct dentry *dentry,
return ERR_PTR(-ENOENT);
}
-static int empty_dir_getattr(struct mnt_idmap *idmap,
- const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int query_flags)
-{
- struct inode *inode = d_inode(path->dentry);
- generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat);
- return 0;
-}
-
static int empty_dir_setattr(struct mnt_idmap *idmap,
struct dentry *dentry, struct iattr *attr)
{
@@ -1733,9 +1728,7 @@ static ssize_t empty_dir_listxattr(struct dentry *dentry, char *list, size_t siz
static const struct inode_operations empty_dir_inode_operations = {
.lookup = empty_dir_lookup,
- .permission = generic_permission,
.setattr = empty_dir_setattr,
- .getattr = empty_dir_getattr,
.listxattr = empty_dir_listxattr,
};
@@ -1791,8 +1784,8 @@ bool is_empty_dir_inode(struct inode *inode)
*
* Return: 0 if names match, 1 if mismatch, or -ERRNO
*/
-static int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
- const char *str, const struct qstr *name)
+int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
+ const char *str, const struct qstr *name)
{
const struct dentry *parent;
const struct inode *dir;
@@ -1835,6 +1828,7 @@ static int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
return utf8_strncasecmp(dentry->d_sb->s_encoding, name, &qstr);
}
+EXPORT_SYMBOL(generic_ci_d_compare);
/**
* generic_ci_d_hash - generic d_hash implementation for casefolding filesystems
@@ -1843,7 +1837,7 @@ static int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
*
* Return: 0 if hash was successful or unchanged, and -EINVAL on error
*/
-static int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
+int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
{
const struct inode *dir = READ_ONCE(dentry->d_inode);
struct super_block *sb = dentry->d_sb;
@@ -1858,6 +1852,7 @@ static int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
return -EINVAL;
return 0;
}
+EXPORT_SYMBOL(generic_ci_d_hash);
static const struct dentry_operations generic_ci_dentry_ops = {
.d_hash = generic_ci_d_hash,
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index 1f2149db10f2..2359347c9fbd 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -30,7 +30,6 @@
#include <linux/sunrpc/svc_xprt.h>
#include <linux/lockd/nlm.h>
#include <linux/lockd/lockd.h>
-#include <linux/exportfs.h>
#define NLMDBG_FACILITY NLMDBG_SVCLOCK
@@ -481,7 +480,7 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
struct nlm_host *host, struct nlm_lock *lock, int wait,
struct nlm_cookie *cookie, int reclaim)
{
- struct inode *inode = nlmsvc_file_inode(file);
+ struct inode *inode __maybe_unused = nlmsvc_file_inode(file);
struct nlm_block *block = NULL;
int error;
int mode;
@@ -496,7 +495,7 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
(long long)lock->fl.fl_end,
wait);
- if (!exportfs_lock_op_is_async(inode->i_sb->s_export_op)) {
+ if (!locks_can_async_lock(nlmsvc_file_file(file)->f_op)) {
async_block = wait;
wait = 0;
}
@@ -550,7 +549,7 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
* requests on the underlaying ->lock() implementation but
* only one nlm_block to being granted by lm_grant().
*/
- if (exportfs_lock_op_is_async(inode->i_sb->s_export_op) &&
+ if (locks_can_async_lock(nlmsvc_file_file(file)->f_op) &&
!list_empty(&block->b_list)) {
spin_unlock(&nlm_blocked_lock);
ret = nlm_lck_blocked;
diff --git a/fs/locks.c b/fs/locks.c
index 204847628f3e..25afc8d9c9d1 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -2136,7 +2136,6 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd)
{
int can_sleep, error, type;
struct file_lock fl;
- struct fd f;
/*
* LOCK_MAND locks were broken for a long time in that they never
@@ -2155,19 +2154,18 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd)
if (type < 0)
return type;
- error = -EBADF;
- f = fdget(fd);
- if (!fd_file(f))
- return error;
+ CLASS(fd, f)(fd);
+ if (fd_empty(f))
+ return -EBADF;
if (type != F_UNLCK && !(fd_file(f)->f_mode & (FMODE_READ | FMODE_WRITE)))
- goto out_putf;
+ return -EBADF;
flock_make_lock(fd_file(f), &fl, type);
error = security_file_lock(fd_file(f), fl.c.flc_type);
if (error)
- goto out_putf;
+ return error;
can_sleep = !(cmd & LOCK_NB);
if (can_sleep)
@@ -2181,9 +2179,6 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd)
error = locks_lock_file_wait(fd_file(f), &fl);
locks_release_private(&fl);
- out_putf:
- fdput(f);
-
return error;
}
diff --git a/fs/mpage.c b/fs/mpage.c
index b5b5ddf9d513..82aecf372743 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -606,7 +606,7 @@ alloc_new:
* the confused fail path above (OOM) will be very confused when
* it finds all bh marked clean (i.e. it will not write anything)
*/
- wbc_account_cgroup_owner(wbc, &folio->page, folio_size(folio));
+ wbc_account_cgroup_owner(wbc, folio, folio_size(folio));
length = first_unmapped << blkbits;
if (!bio_add_folio(bio, folio, length, 0)) {
bio = mpage_bio_submit_write(bio);
diff --git a/fs/namei.c b/fs/namei.c
index 4a4a22a08ac2..9d30c7aa9aa6 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -211,22 +211,38 @@ getname_flags(const char __user *filename, int flags)
return result;
}
-struct filename *
-getname_uflags(const char __user *filename, int uflags)
+struct filename *getname_uflags(const char __user *filename, int uflags)
{
int flags = (uflags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0;
return getname_flags(filename, flags);
}
-struct filename *
-getname(const char __user * filename)
+struct filename *getname(const char __user * filename)
{
return getname_flags(filename, 0);
}
-struct filename *
-getname_kernel(const char * filename)
+struct filename *__getname_maybe_null(const char __user *pathname)
+{
+ struct filename *name;
+ char c;
+
+ /* try to save on allocations; loss on um, though */
+ if (get_user(c, pathname))
+ return ERR_PTR(-EFAULT);
+ if (!c)
+ return NULL;
+
+ name = getname_flags(pathname, LOOKUP_EMPTY);
+ if (!IS_ERR(name) && !(name->name[0])) {
+ putname(name);
+ name = NULL;
+ }
+ return name;
+}
+
+struct filename *getname_kernel(const char * filename)
{
struct filename *result;
int len = strlen(filename) + 1;
@@ -264,7 +280,7 @@ EXPORT_SYMBOL(getname_kernel);
void putname(struct filename *name)
{
- if (IS_ERR(name))
+ if (IS_ERR_OR_NULL(name))
return;
if (WARN_ON_ONCE(!atomic_read(&name->refcnt)))
@@ -326,6 +342,25 @@ static int check_acl(struct mnt_idmap *idmap,
return -EAGAIN;
}
+/*
+ * Very quick optimistic "we know we have no ACL's" check.
+ *
+ * Note that this is purely for ACL_TYPE_ACCESS, and purely
+ * for the "we have cached that there are no ACLs" case.
+ *
+ * If this returns true, we know there are no ACLs. But if
+ * it returns false, we might still not have ACLs (it could
+ * be the is_uncached_acl() case).
+ */
+static inline bool no_acl_inode(struct inode *inode)
+{
+#ifdef CONFIG_FS_POSIX_ACL
+ return likely(!READ_ONCE(inode->i_acl));
+#else
+ return true;
+#endif
+}
+
/**
* acl_permission_check - perform basic UNIX permission checking
* @idmap: idmap of the mount the inode was found from
@@ -348,6 +383,28 @@ static int acl_permission_check(struct mnt_idmap *idmap,
unsigned int mode = inode->i_mode;
vfsuid_t vfsuid;
+ /*
+ * Common cheap case: everybody has the requested
+ * rights, and there are no ACLs to check. No need
+ * to do any owner/group checks in that case.
+ *
+ * - 'mask&7' is the requested permission bit set
+ * - multiplying by 0111 spreads them out to all of ugo
+ * - '& ~mode' looks for missing inode permission bits
+ * - the '!' is for "no missing permissions"
+ *
+ * After that, we just need to check that there are no
+ * ACL's on the inode - do the 'IS_POSIXACL()' check last
+ * because it will dereference the ->i_sb pointer and we
+ * want to avoid that if at all possible.
+ */
+ if (!((mask & 7) * 0111 & ~mode)) {
+ if (no_acl_inode(inode))
+ return 0;
+ if (!IS_POSIXACL(inode))
+ return 0;
+ }
+
/* Are we the owner? If so, ACL's don't matter */
vfsuid = i_uid_into_vfsuid(idmap, inode);
if (likely(vfsuid_eq_kuid(vfsuid, current_fsuid()))) {
@@ -588,6 +645,7 @@ struct nameidata {
unsigned seq;
} *stack, internal[EMBEDDED_LEVELS];
struct filename *name;
+ const char *pathname;
struct nameidata *saved;
unsigned root_seq;
int dfd;
@@ -606,6 +664,7 @@ static void __set_nameidata(struct nameidata *p, int dfd, struct filename *name)
p->depth = 0;
p->dfd = dfd;
p->name = name;
+ p->pathname = likely(name) ? name->name : "";
p->path.mnt = NULL;
p->path.dentry = NULL;
p->total_link_count = old ? old->total_link_count : 0;
@@ -2439,7 +2498,7 @@ OK:
static const char *path_init(struct nameidata *nd, unsigned flags)
{
int error;
- const char *s = nd->name->name;
+ const char *s = nd->pathname;
/* LOOKUP_CACHED requires RCU, ask caller to retry */
if ((flags & (LOOKUP_RCU | LOOKUP_CACHED)) == LOOKUP_CACHED)
@@ -2503,26 +2562,22 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
}
} else {
/* Caller must check execute permissions on the starting path component */
- struct fd f = fdget_raw(nd->dfd);
+ CLASS(fd_raw, f)(nd->dfd);
struct dentry *dentry;
- if (!fd_file(f))
+ if (fd_empty(f))
return ERR_PTR(-EBADF);
if (flags & LOOKUP_LINKAT_EMPTY) {
if (fd_file(f)->f_cred != current_cred() &&
- !ns_capable(fd_file(f)->f_cred->user_ns, CAP_DAC_READ_SEARCH)) {
- fdput(f);
+ !ns_capable(fd_file(f)->f_cred->user_ns, CAP_DAC_READ_SEARCH))
return ERR_PTR(-ENOENT);
- }
}
dentry = fd_file(f)->f_path.dentry;
- if (*s && unlikely(!d_can_lookup(dentry))) {
- fdput(f);
+ if (*s && unlikely(!d_can_lookup(dentry)))
return ERR_PTR(-ENOTDIR);
- }
nd->path = fd_file(f)->f_path;
if (flags & LOOKUP_RCU) {
@@ -2532,7 +2587,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
path_get(&nd->path);
nd->inode = nd->path.dentry->d_inode;
}
- fdput(f);
}
/* For scoped-lookups we need to set the root to the dirfd as well. */
diff --git a/fs/namespace.c b/fs/namespace.c
index d26f5e6d2ca3..6b0a17487d0f 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -3901,7 +3901,7 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool a
}
new_ns->ns.ops = &mntns_operations;
if (!anon)
- new_ns->seq = atomic64_add_return(1, &mnt_ns_seq);
+ new_ns->seq = atomic64_inc_return(&mnt_ns_seq);
refcount_set(&new_ns->ns.count, 1);
refcount_set(&new_ns->passive, 1);
new_ns->mounts = RB_ROOT;
@@ -4107,7 +4107,6 @@ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags,
struct file *file;
struct path newmount;
struct mount *mnt;
- struct fd f;
unsigned int mnt_flags = 0;
long ret;
@@ -4135,19 +4134,18 @@ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags,
return -EINVAL;
}
- f = fdget(fs_fd);
- if (!fd_file(f))
+ CLASS(fd, f)(fs_fd);
+ if (fd_empty(f))
return -EBADF;
- ret = -EINVAL;
if (fd_file(f)->f_op != &fscontext_fops)
- goto err_fsfd;
+ return -EINVAL;
fc = fd_file(f)->private_data;
ret = mutex_lock_interruptible(&fc->uapi_mutex);
if (ret < 0)
- goto err_fsfd;
+ return ret;
/* There must be a valid superblock or we can't mount it */
ret = -EINVAL;
@@ -4214,8 +4212,6 @@ err_path:
path_put(&newmount);
err_unlock:
mutex_unlock(&fc->uapi_mutex);
-err_fsfd:
- fdput(f);
return ret;
}
@@ -4670,10 +4666,8 @@ out:
static int build_mount_idmapped(const struct mount_attr *attr, size_t usize,
struct mount_kattr *kattr, unsigned int flags)
{
- int err = 0;
struct ns_common *ns;
struct user_namespace *mnt_userns;
- struct fd f;
if (!((attr->attr_set | attr->attr_clr) & MOUNT_ATTR_IDMAP))
return 0;
@@ -4689,20 +4683,16 @@ static int build_mount_idmapped(const struct mount_attr *attr, size_t usize,
if (attr->userns_fd > INT_MAX)
return -EINVAL;
- f = fdget(attr->userns_fd);
- if (!fd_file(f))
+ CLASS(fd, f)(attr->userns_fd);
+ if (fd_empty(f))
return -EBADF;
- if (!proc_ns_file(fd_file(f))) {
- err = -EINVAL;
- goto out_fput;
- }
+ if (!proc_ns_file(fd_file(f)))
+ return -EINVAL;
ns = get_proc_ns(file_inode(fd_file(f)));
- if (ns->ops->type != CLONE_NEWUSER) {
- err = -EINVAL;
- goto out_fput;
- }
+ if (ns->ops->type != CLONE_NEWUSER)
+ return -EINVAL;
/*
* The initial idmapping cannot be used to create an idmapped
@@ -4713,22 +4703,15 @@ static int build_mount_idmapped(const struct mount_attr *attr, size_t usize,
* result.
*/
mnt_userns = container_of(ns, struct user_namespace, ns);
- if (mnt_userns == &init_user_ns) {
- err = -EPERM;
- goto out_fput;
- }
+ if (mnt_userns == &init_user_ns)
+ return -EPERM;
/* We're not controlling the target namespace. */
- if (!ns_capable(mnt_userns, CAP_SYS_ADMIN)) {
- err = -EPERM;
- goto out_fput;
- }
+ if (!ns_capable(mnt_userns, CAP_SYS_ADMIN))
+ return -EPERM;
kattr->mnt_userns = get_user_ns(mnt_userns);
-
-out_fput:
- fdput(f);
- return err;
+ return 0;
}
static int build_mount_kattr(const struct mount_attr *attr, size_t usize,
@@ -5006,6 +4989,40 @@ static int statmount_fs_type(struct kstatmount *s, struct seq_file *seq)
return 0;
}
+static void statmount_fs_subtype(struct kstatmount *s, struct seq_file *seq)
+{
+ struct super_block *sb = s->mnt->mnt_sb;
+
+ if (sb->s_subtype)
+ seq_puts(seq, sb->s_subtype);
+}
+
+static int statmount_sb_source(struct kstatmount *s, struct seq_file *seq)
+{
+ struct super_block *sb = s->mnt->mnt_sb;
+ struct mount *r = real_mount(s->mnt);
+
+ if (sb->s_op->show_devname) {
+ size_t start = seq->count;
+ int ret;
+
+ ret = sb->s_op->show_devname(seq, s->mnt->mnt_root);
+ if (ret)
+ return ret;
+
+ if (unlikely(seq_has_overflowed(seq)))
+ return -EAGAIN;
+
+ /* Unescape the result */
+ seq->buf[seq->count] = '\0';
+ seq->count = start;
+ seq_commit(seq, string_unescape_inplace(seq->buf + start, UNESCAPE_OCTAL));
+ } else if (r->mnt_devname) {
+ seq_puts(seq, r->mnt_devname);
+ }
+ return 0;
+}
+
static void statmount_mnt_ns_id(struct kstatmount *s, struct mnt_namespace *ns)
{
s->sm.mask |= STATMOUNT_MNT_NS_ID;
@@ -5040,35 +5057,134 @@ static int statmount_mnt_opts(struct kstatmount *s, struct seq_file *seq)
return 0;
}
+static inline int statmount_opt_unescape(struct seq_file *seq, char *buf_start)
+{
+ char *buf_end, *opt_start, *opt_end;
+ int count = 0;
+
+ buf_end = seq->buf + seq->count;
+ *buf_end = '\0';
+ for (opt_start = buf_start + 1; opt_start < buf_end; opt_start = opt_end + 1) {
+ opt_end = strchrnul(opt_start, ',');
+ *opt_end = '\0';
+ buf_start += string_unescape(opt_start, buf_start, 0, UNESCAPE_OCTAL) + 1;
+ if (WARN_ON_ONCE(++count == INT_MAX))
+ return -EOVERFLOW;
+ }
+ seq->count = buf_start - 1 - seq->buf;
+ return count;
+}
+
+static int statmount_opt_array(struct kstatmount *s, struct seq_file *seq)
+{
+ struct vfsmount *mnt = s->mnt;
+ struct super_block *sb = mnt->mnt_sb;
+ size_t start = seq->count;
+ char *buf_start;
+ int err;
+
+ if (!sb->s_op->show_options)
+ return 0;
+
+ buf_start = seq->buf + start;
+ err = sb->s_op->show_options(seq, mnt->mnt_root);
+ if (err)
+ return err;
+
+ if (unlikely(seq_has_overflowed(seq)))
+ return -EAGAIN;
+
+ if (seq->count == start)
+ return 0;
+
+ err = statmount_opt_unescape(seq, buf_start);
+ if (err < 0)
+ return err;
+
+ s->sm.opt_num = err;
+ return 0;
+}
+
+static int statmount_opt_sec_array(struct kstatmount *s, struct seq_file *seq)
+{
+ struct vfsmount *mnt = s->mnt;
+ struct super_block *sb = mnt->mnt_sb;
+ size_t start = seq->count;
+ char *buf_start;
+ int err;
+
+ buf_start = seq->buf + start;
+
+ err = security_sb_show_options(seq, sb);
+ if (!err)
+ return err;
+
+ if (unlikely(seq_has_overflowed(seq)))
+ return -EAGAIN;
+
+ if (seq->count == start)
+ return 0;
+
+ err = statmount_opt_unescape(seq, buf_start);
+ if (err < 0)
+ return err;
+
+ s->sm.opt_sec_num = err;
+ return 0;
+}
+
static int statmount_string(struct kstatmount *s, u64 flag)
{
- int ret;
+ int ret = 0;
size_t kbufsize;
struct seq_file *seq = &s->seq;
struct statmount *sm = &s->sm;
+ u32 start = seq->count;
switch (flag) {
case STATMOUNT_FS_TYPE:
- sm->fs_type = seq->count;
+ sm->fs_type = start;
ret = statmount_fs_type(s, seq);
break;
case STATMOUNT_MNT_ROOT:
- sm->mnt_root = seq->count;
+ sm->mnt_root = start;
ret = statmount_mnt_root(s, seq);
break;
case STATMOUNT_MNT_POINT:
- sm->mnt_point = seq->count;
+ sm->mnt_point = start;
ret = statmount_mnt_point(s, seq);
break;
case STATMOUNT_MNT_OPTS:
- sm->mnt_opts = seq->count;
+ sm->mnt_opts = start;
ret = statmount_mnt_opts(s, seq);
break;
+ case STATMOUNT_OPT_ARRAY:
+ sm->opt_array = start;
+ ret = statmount_opt_array(s, seq);
+ break;
+ case STATMOUNT_OPT_SEC_ARRAY:
+ sm->opt_sec_array = start;
+ ret = statmount_opt_sec_array(s, seq);
+ break;
+ case STATMOUNT_FS_SUBTYPE:
+ sm->fs_subtype = start;
+ statmount_fs_subtype(s, seq);
+ break;
+ case STATMOUNT_SB_SOURCE:
+ sm->sb_source = start;
+ ret = statmount_sb_source(s, seq);
+ break;
default:
WARN_ON_ONCE(true);
return -EINVAL;
}
+ /*
+ * If nothing was emitted, return to avoid setting the flag
+ * and terminating the buffer.
+ */
+ if (seq->count == start)
+ return ret;
if (unlikely(check_add_overflow(sizeof(*sm), seq->count, &kbufsize)))
return -EOVERFLOW;
if (kbufsize >= s->bufsize)
@@ -5203,6 +5319,18 @@ static int do_statmount(struct kstatmount *s, u64 mnt_id, u64 mnt_ns_id,
if (!err && s->mask & STATMOUNT_MNT_OPTS)
err = statmount_string(s, STATMOUNT_MNT_OPTS);
+ if (!err && s->mask & STATMOUNT_OPT_ARRAY)
+ err = statmount_string(s, STATMOUNT_OPT_ARRAY);
+
+ if (!err && s->mask & STATMOUNT_OPT_SEC_ARRAY)
+ err = statmount_string(s, STATMOUNT_OPT_SEC_ARRAY);
+
+ if (!err && s->mask & STATMOUNT_FS_SUBTYPE)
+ err = statmount_string(s, STATMOUNT_FS_SUBTYPE);
+
+ if (!err && s->mask & STATMOUNT_SB_SOURCE)
+ err = statmount_string(s, STATMOUNT_SB_SOURCE);
+
if (!err && s->mask & STATMOUNT_MNT_NS_ID)
statmount_mnt_ns_id(s, ns);
@@ -5224,7 +5352,9 @@ static inline bool retry_statmount(const long ret, size_t *seq_size)
}
#define STATMOUNT_STRING_REQ (STATMOUNT_MNT_ROOT | STATMOUNT_MNT_POINT | \
- STATMOUNT_FS_TYPE | STATMOUNT_MNT_OPTS)
+ STATMOUNT_FS_TYPE | STATMOUNT_MNT_OPTS | \
+ STATMOUNT_FS_SUBTYPE | STATMOUNT_SB_SOURCE | \
+ STATMOUNT_OPT_ARRAY | STATMOUNT_OPT_SEC_ARRAY)
static int prepare_kstatmount(struct kstatmount *ks, struct mnt_id_req *kreq,
struct statmount __user *buf, size_t bufsize,
diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index af46a598f4d7..7ac34550c403 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -627,7 +627,7 @@ static bool netfs_skip_folio_read(struct folio *folio, loff_t pos, size_t len,
if (unlikely(always_fill)) {
if (pos - offset + len <= i_size)
return false; /* Page entirely before EOF */
- zero_user_segment(&folio->page, 0, plen);
+ folio_zero_segment(folio, 0, plen);
folio_mark_uptodate(folio);
return true;
}
@@ -646,7 +646,7 @@ static bool netfs_skip_folio_read(struct folio *folio, loff_t pos, size_t len,
return false;
zero_out:
- zero_user_segments(&folio->page, 0, offset, offset + len, plen);
+ folio_zero_segments(folio, 0, offset, offset + len, plen);
return true;
}
@@ -713,7 +713,7 @@ retry:
if (folio_test_uptodate(folio))
goto have_folio;
- /* If the page is beyond the EOF, we want to clear it - unless it's
+ /* If the folio is beyond the EOF, we want to clear it - unless it's
* within the cache granule containing the EOF, in which case we need
* to preload the granule.
*/
@@ -773,7 +773,7 @@ error:
EXPORT_SYMBOL(netfs_write_begin);
/*
- * Preload the data into a page we're proposing to write into.
+ * Preload the data into a folio we're proposing to write into.
*/
int netfs_prefetch_for_write(struct file *file, struct folio *folio,
size_t offset, size_t len)
diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index b3910dfcb56d..b4826360a411 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -83,13 +83,13 @@ static void netfs_update_i_size(struct netfs_inode *ctx, struct inode *inode,
* netfs_perform_write - Copy data into the pagecache.
* @iocb: The operation parameters
* @iter: The source buffer
- * @netfs_group: Grouping for dirty pages (eg. ceph snaps).
+ * @netfs_group: Grouping for dirty folios (eg. ceph snaps).
*
- * Copy data into pagecache pages attached to the inode specified by @iocb.
+ * Copy data into pagecache folios attached to the inode specified by @iocb.
* The caller must hold appropriate inode locks.
*
- * Dirty pages are tagged with a netfs_folio struct if they're not up to date
- * to indicate the range modified. Dirty pages may also be tagged with a
+ * Dirty folios are tagged with a netfs_folio struct if they're not up to date
+ * to indicate the range modified. Dirty folios may also be tagged with a
* netfs-specific grouping such that data from an old group gets flushed before
* a new one is started.
*/
@@ -223,11 +223,11 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
* we try to read it.
*/
if (fpos >= ctx->zero_point) {
- zero_user_segment(&folio->page, 0, offset);
+ folio_zero_segment(folio, 0, offset);
copied = copy_folio_from_iter_atomic(folio, offset, part, iter);
if (unlikely(copied == 0))
goto copy_failed;
- zero_user_segment(&folio->page, offset + copied, flen);
+ folio_zero_segment(folio, offset + copied, flen);
__netfs_set_group(folio, netfs_group);
folio_mark_uptodate(folio);
trace_netfs_folio(folio, netfs_modify_and_clear);
@@ -407,7 +407,7 @@ EXPORT_SYMBOL(netfs_perform_write);
* netfs_buffered_write_iter_locked - write data to a file
* @iocb: IO state structure (file, offset, etc.)
* @from: iov_iter with data to write
- * @netfs_group: Grouping for dirty pages (eg. ceph snaps).
+ * @netfs_group: Grouping for dirty folios (eg. ceph snaps).
*
* This function does all the work needed for actually writing data to a
* file. It does all basic checks, removes SUID from the file, updates
@@ -491,7 +491,9 @@ EXPORT_SYMBOL(netfs_file_write_iter);
/*
* Notification that a previously read-only page is about to become writable.
- * Note that the caller indicates a single page of a multipage folio.
+ * The caller indicates the precise page that needs to be written to, but
+ * we only track group on a per-folio basis, so we block more often than
+ * we might otherwise.
*/
vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group)
{
@@ -501,7 +503,7 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr
struct address_space *mapping = file->f_mapping;
struct inode *inode = file_inode(file);
struct netfs_inode *ictx = netfs_inode(inode);
- vm_fault_t ret = VM_FAULT_RETRY;
+ vm_fault_t ret = VM_FAULT_NOPAGE;
int err;
_enter("%lx", folio->index);
@@ -510,21 +512,15 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr
if (folio_lock_killable(folio) < 0)
goto out;
- if (folio->mapping != mapping) {
- folio_unlock(folio);
- ret = VM_FAULT_NOPAGE;
- goto out;
- }
-
- if (folio_wait_writeback_killable(folio)) {
- ret = VM_FAULT_LOCKED;
- goto out;
- }
+ if (folio->mapping != mapping)
+ goto unlock;
+ if (folio_wait_writeback_killable(folio) < 0)
+ goto unlock;
/* Can we see a streaming write here? */
if (WARN_ON(!folio_test_uptodate(folio))) {
- ret = VM_FAULT_SIGBUS | VM_FAULT_LOCKED;
- goto out;
+ ret = VM_FAULT_SIGBUS;
+ goto unlock;
}
group = netfs_folio_group(folio);
@@ -559,5 +555,8 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr
out:
sb_end_pagefault(inode->i_sb);
return ret;
+unlock:
+ folio_unlock(folio);
+ goto out;
}
EXPORT_SYMBOL(netfs_page_mkwrite);
diff --git a/fs/netfs/fscache_volume.c b/fs/netfs/fscache_volume.c
index cb75c07b5281..ced14ac78cc1 100644
--- a/fs/netfs/fscache_volume.c
+++ b/fs/netfs/fscache_volume.c
@@ -322,8 +322,7 @@ maybe_wait:
}
return;
no_wait:
- clear_bit_unlock(FSCACHE_VOLUME_CREATING, &volume->flags);
- wake_up_bit(&volume->flags, FSCACHE_VOLUME_CREATING);
+ clear_and_wake_up_bit(FSCACHE_VOLUME_CREATING, &volume->flags);
}
/*
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 551d2958ec29..d80406f8b568 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -8001,9 +8001,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
fp = lock_stp->st_stid.sc_file;
switch (lock->lk_type) {
case NFS4_READW_LT:
- if (nfsd4_has_session(cstate) ||
- exportfs_lock_op_is_async(sb->s_export_op))
- flags |= FL_SLEEP;
fallthrough;
case NFS4_READ_LT:
spin_lock(&fp->fi_lock);
@@ -8014,9 +8011,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
type = F_RDLCK;
break;
case NFS4_WRITEW_LT:
- if (nfsd4_has_session(cstate) ||
- exportfs_lock_op_is_async(sb->s_export_op))
- flags |= FL_SLEEP;
fallthrough;
case NFS4_WRITE_LT:
spin_lock(&fp->fi_lock);
@@ -8036,15 +8030,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
goto out;
}
- /*
- * Most filesystems with their own ->lock operations will block
- * the nfsd thread waiting to acquire the lock. That leads to
- * deadlocks (we don't want every nfsd thread tied up waiting
- * for file locks), so don't attempt blocking lock notifications
- * on those filesystems:
- */
- if (!exportfs_lock_op_is_async(sb->s_export_op))
- flags &= ~FL_SLEEP;
+ if (lock->lk_type & (NFS4_READW_LT | NFS4_WRITEW_LT) &&
+ nfsd4_has_session(cstate) &&
+ locks_can_async_lock(nf->nf_file->f_op))
+ flags |= FL_SLEEP;
nbl = find_or_allocate_block(lock_sop, &fp->fi_fhandle, nn);
if (!nbl) {
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index 57b4af5ad646..501ad7be5174 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -68,7 +68,6 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr)
goto failed;
}
memset(bh->b_data, 0, i_blocksize(inode));
- bh->b_bdev = inode->i_sb->s_bdev;
bh->b_blocknr = blocknr;
set_buffer_mapped(bh);
set_buffer_uptodate(bh);
@@ -133,7 +132,6 @@ int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr,
goto found;
}
set_buffer_mapped(bh);
- bh->b_bdev = inode->i_sb->s_bdev;
bh->b_blocknr = pblocknr; /* set block address for read */
bh->b_end_io = end_buffer_read_sync;
get_bh(bh);
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index 1c9ae36a03ab..ace22253fed0 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -83,10 +83,8 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff,
goto out;
}
- if (!buffer_mapped(bh)) {
- bh->b_bdev = inode->i_sb->s_bdev;
+ if (!buffer_mapped(bh))
set_buffer_mapped(bh);
- }
bh->b_blocknr = pbn;
bh->b_end_io = end_buffer_read_sync;
get_bh(bh);
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index ceb7dc0b5bad..2db6350b5ac2 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -89,7 +89,6 @@ static int nilfs_mdt_create_block(struct inode *inode, unsigned long block,
if (buffer_uptodate(bh))
goto failed_bh;
- bh->b_bdev = sb->s_bdev;
err = nilfs_mdt_insert_new_block(inode, block, bh, init_block);
if (likely(!err)) {
get_bh(bh);
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index 10def4b55995..9a849397c768 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -39,7 +39,6 @@ static struct buffer_head *__nilfs_get_folio_block(struct folio *folio,
first_block = (unsigned long)index << (PAGE_SHIFT - blkbits);
bh = get_nth_bh(bh, block - first_block);
- touch_buffer(bh);
wait_on_buffer(bh);
return bh;
}
@@ -64,6 +63,7 @@ struct buffer_head *nilfs_grab_buffer(struct inode *inode,
folio_put(folio);
return NULL;
}
+ bh->b_bdev = inode->i_sb->s_bdev;
return bh;
}
@@ -99,16 +99,16 @@ void nilfs_forget_buffer(struct buffer_head *bh)
*/
void nilfs_copy_buffer(struct buffer_head *dbh, struct buffer_head *sbh)
{
- void *kaddr0, *kaddr1;
+ void *saddr, *daddr;
unsigned long bits;
- struct page *spage = sbh->b_page, *dpage = dbh->b_page;
+ struct folio *sfolio = sbh->b_folio, *dfolio = dbh->b_folio;
struct buffer_head *bh;
- kaddr0 = kmap_local_page(spage);
- kaddr1 = kmap_local_page(dpage);
- memcpy(kaddr1 + bh_offset(dbh), kaddr0 + bh_offset(sbh), sbh->b_size);
- kunmap_local(kaddr1);
- kunmap_local(kaddr0);
+ saddr = kmap_local_folio(sfolio, bh_offset(sbh));
+ daddr = kmap_local_folio(dfolio, bh_offset(dbh));
+ memcpy(daddr, saddr, sbh->b_size);
+ kunmap_local(daddr);
+ kunmap_local(saddr);
dbh->b_state = sbh->b_state & NILFS_BUFFER_INHERENT_BITS;
dbh->b_blocknr = sbh->b_blocknr;
@@ -122,13 +122,13 @@ void nilfs_copy_buffer(struct buffer_head *dbh, struct buffer_head *sbh)
unlock_buffer(bh);
}
if (bits & BIT(BH_Uptodate))
- SetPageUptodate(dpage);
+ folio_mark_uptodate(dfolio);
else
- ClearPageUptodate(dpage);
+ folio_clear_uptodate(dfolio);
if (bits & BIT(BH_Mapped))
- SetPageMappedToDisk(dpage);
+ folio_set_mappedtodisk(dfolio);
else
- ClearPageMappedToDisk(dpage);
+ folio_clear_mappedtodisk(dfolio);
}
/**
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index d5dbef7f5c95..6004dfdfdf0f 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -16,7 +16,6 @@
#include <linux/security.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
-#include <linux/fdtable.h>
#include <linux/fsnotify_backend.h>
static int dir_notify_enable __read_mostly = 1;
@@ -347,9 +346,7 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg)
new_fsn_mark = NULL;
}
- rcu_read_lock();
- f = lookup_fdget_rcu(fd);
- rcu_read_unlock();
+ f = fget_raw(fd);
/* if (f != filp) means that we lost a race and another task/thread
* actually closed the fd we are still playing with before we grabbed
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 224bccaab4cc..24c7c5df4998 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -1,6 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/fanotify.h>
-#include <linux/fdtable.h>
#include <linux/fsnotify_backend.h>
#include <linux/init.h>
#include <linux/jiffies.h>
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 9644bc72e457..35159fa0b063 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -1,7 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/fanotify.h>
#include <linux/fcntl.h>
-#include <linux/fdtable.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/anon_inodes.h>
@@ -1003,22 +1002,17 @@ static int fanotify_find_path(int dfd, const char __user *filename,
dfd, filename, flags);
if (filename == NULL) {
- struct fd f = fdget(dfd);
+ CLASS(fd, f)(dfd);
- ret = -EBADF;
- if (!fd_file(f))
- goto out;
+ if (fd_empty(f))
+ return -EBADF;
- ret = -ENOTDIR;
if ((flags & FAN_MARK_ONLYDIR) &&
- !(S_ISDIR(file_inode(fd_file(f))->i_mode))) {
- fdput(f);
- goto out;
- }
+ !(S_ISDIR(file_inode(fd_file(f))->i_mode)))
+ return -ENOTDIR;
*path = fd_file(f)->f_path;
path_get(path);
- fdput(f);
} else {
unsigned int lookup_flags = 0;
@@ -1682,7 +1676,6 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
struct inode *inode = NULL;
struct vfsmount *mnt = NULL;
struct fsnotify_group *group;
- struct fd f;
struct path path;
struct fan_fsid __fsid, *fsid = NULL;
u32 valid_mask = FANOTIFY_EVENTS | FANOTIFY_EVENT_FLAGS;
@@ -1752,14 +1745,13 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
umask = FANOTIFY_EVENT_FLAGS;
}
- f = fdget(fanotify_fd);
- if (unlikely(!fd_file(f)))
+ CLASS(fd, f)(fanotify_fd);
+ if (fd_empty(f))
return -EBADF;
/* verify that this is indeed an fanotify instance */
- ret = -EINVAL;
if (unlikely(fd_file(f)->f_op != &fanotify_fops))
- goto fput_and_out;
+ return -EINVAL;
group = fd_file(f)->private_data;
/*
@@ -1767,23 +1759,21 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
* marks. This also includes setting up such marks by a group that
* was initialized by an unprivileged user.
*/
- ret = -EPERM;
if ((!capable(CAP_SYS_ADMIN) ||
FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV)) &&
mark_type != FAN_MARK_INODE)
- goto fput_and_out;
+ return -EPERM;
/*
* Permission events require minimum priority FAN_CLASS_CONTENT.
*/
- ret = -EINVAL;
if (mask & FANOTIFY_PERM_EVENTS &&
group->priority < FSNOTIFY_PRIO_CONTENT)
- goto fput_and_out;
+ return -EINVAL;
if (mask & FAN_FS_ERROR &&
mark_type != FAN_MARK_FILESYSTEM)
- goto fput_and_out;
+ return -EINVAL;
/*
* Evictable is only relevant for inode marks, because only inode object
@@ -1791,7 +1781,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
*/
if (flags & FAN_MARK_EVICTABLE &&
mark_type != FAN_MARK_INODE)
- goto fput_and_out;
+ return -EINVAL;
/*
* Events that do not carry enough information to report
@@ -1803,7 +1793,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
if (mask & ~(FANOTIFY_FD_EVENTS|FANOTIFY_EVENT_FLAGS) &&
(!fid_mode || mark_type == FAN_MARK_MOUNT))
- goto fput_and_out;
+ return -EINVAL;
/*
* FAN_RENAME uses special info type records to report the old and
@@ -1811,23 +1801,22 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
* useful and was not implemented.
*/
if (mask & FAN_RENAME && !(fid_mode & FAN_REPORT_NAME))
- goto fput_and_out;
+ return -EINVAL;
if (mark_cmd == FAN_MARK_FLUSH) {
- ret = 0;
if (mark_type == FAN_MARK_MOUNT)
fsnotify_clear_vfsmount_marks_by_group(group);
else if (mark_type == FAN_MARK_FILESYSTEM)
fsnotify_clear_sb_marks_by_group(group);
else
fsnotify_clear_inode_marks_by_group(group);
- goto fput_and_out;
+ return 0;
}
ret = fanotify_find_path(dfd, pathname, &path, flags,
(mask & ALL_FSNOTIFY_EVENTS), obj_type);
if (ret)
- goto fput_and_out;
+ return ret;
if (mark_cmd == FAN_MARK_ADD) {
ret = fanotify_events_supported(group, &path, mask, flags);
@@ -1906,8 +1895,6 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
path_put_and_out:
path_put(&path);
-fput_and_out:
- fdput(f);
return ret;
}
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 0794dcaf1e47..e0c48956608a 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -732,7 +732,6 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
struct fsnotify_group *group;
struct inode *inode;
struct path path;
- struct fd f;
int ret;
unsigned flags = 0;
@@ -752,21 +751,17 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
if (unlikely(!(mask & ALL_INOTIFY_BITS)))
return -EINVAL;
- f = fdget(fd);
- if (unlikely(!fd_file(f)))
+ CLASS(fd, f)(fd);
+ if (fd_empty(f))
return -EBADF;
/* IN_MASK_ADD and IN_MASK_CREATE don't make sense together */
- if (unlikely((mask & IN_MASK_ADD) && (mask & IN_MASK_CREATE))) {
- ret = -EINVAL;
- goto fput_and_out;
- }
+ if (unlikely((mask & IN_MASK_ADD) && (mask & IN_MASK_CREATE)))
+ return -EINVAL;
/* verify that this is indeed an inotify instance */
- if (unlikely(fd_file(f)->f_op != &inotify_fops)) {
- ret = -EINVAL;
- goto fput_and_out;
- }
+ if (unlikely(fd_file(f)->f_op != &inotify_fops))
+ return -EINVAL;
if (!(mask & IN_DONT_FOLLOW))
flags |= LOOKUP_FOLLOW;
@@ -776,7 +771,7 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
ret = inotify_find_inode(pathname, &path, flags,
(mask & IN_ALL_EVENTS));
if (ret)
- goto fput_and_out;
+ return ret;
/* inode held in place by reference to path; group by fget on fd */
inode = path.dentry->d_inode;
@@ -785,8 +780,6 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
/* create/update an inode mark */
ret = inotify_update_watch(group, inode, mask);
path_put(&path);
-fput_and_out:
- fdput(f);
return ret;
}
@@ -794,33 +787,26 @@ SYSCALL_DEFINE2(inotify_rm_watch, int, fd, __s32, wd)
{
struct fsnotify_group *group;
struct inotify_inode_mark *i_mark;
- struct fd f;
- int ret = -EINVAL;
+ CLASS(fd, f)(fd);
- f = fdget(fd);
- if (unlikely(!fd_file(f)))
+ if (fd_empty(f))
return -EBADF;
/* verify that this is indeed an inotify instance */
if (unlikely(fd_file(f)->f_op != &inotify_fops))
- goto out;
+ return -EINVAL;
group = fd_file(f)->private_data;
i_mark = inotify_idr_find(group, wd);
if (unlikely(!i_mark))
- goto out;
-
- ret = 0;
+ return -EINVAL;
fsnotify_destroy_mark(&i_mark->fsn_mark, group);
/* match ref taken by inotify_idr_find */
fsnotify_put_mark(&i_mark->fsn_mark);
-
-out:
- fdput(f);
- return ret;
+ return 0;
}
/*
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 4b9f45d7049e..4200a0341343 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -1765,42 +1765,41 @@ static ssize_t o2hb_region_dev_store(struct config_item *item,
long fd;
int sectsize;
char *p = (char *)page;
- struct fd f;
ssize_t ret = -EINVAL;
int live_threshold;
if (reg->hr_bdev_file)
- goto out;
+ return -EINVAL;
/* We can't heartbeat without having had our node number
* configured yet. */
if (o2nm_this_node() == O2NM_MAX_NODES)
- goto out;
+ return -EINVAL;
fd = simple_strtol(p, &p, 0);
if (!p || (*p && (*p != '\n')))
- goto out;
+ return -EINVAL;
if (fd < 0 || fd >= INT_MAX)
- goto out;
+ return -EINVAL;
- f = fdget(fd);
- if (fd_file(f) == NULL)
- goto out;
+ CLASS(fd, f)(fd);
+ if (fd_empty(f))
+ return -EINVAL;
if (reg->hr_blocks == 0 || reg->hr_start_block == 0 ||
reg->hr_block_bytes == 0)
- goto out2;
+ return -EINVAL;
if (!S_ISBLK(fd_file(f)->f_mapping->host->i_mode))
- goto out2;
+ return -EINVAL;
reg->hr_bdev_file = bdev_file_open_by_dev(fd_file(f)->f_mapping->host->i_rdev,
BLK_OPEN_WRITE | BLK_OPEN_READ, NULL, NULL);
if (IS_ERR(reg->hr_bdev_file)) {
ret = PTR_ERR(reg->hr_bdev_file);
reg->hr_bdev_file = NULL;
- goto out2;
+ return ret;
}
sectsize = bdev_logical_block_size(reg_bdev(reg));
@@ -1906,9 +1905,6 @@ out3:
fput(reg->hr_bdev_file);
reg->hr_bdev_file = NULL;
}
-out2:
- fdput(f);
-out:
return ret;
}
diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c
index 96b684763b39..b95724b767e1 100644
--- a/fs/ocfs2/export.c
+++ b/fs/ocfs2/export.c
@@ -280,5 +280,4 @@ const struct export_operations ocfs2_export_ops = {
.fh_to_dentry = ocfs2_fh_to_dentry,
.fh_to_parent = ocfs2_fh_to_parent,
.get_parent = ocfs2_get_parent,
- .flags = EXPORT_OP_ASYNC_LOCK,
};
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 06af21982c16..4fa6c840d20b 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2812,6 +2812,7 @@ const struct file_operations ocfs2_fops = {
.splice_write = iter_file_splice_write,
.fallocate = ocfs2_fallocate,
.remap_file_range = ocfs2_remap_file_range,
+ .fop_flags = FOP_ASYNC_LOCK,
};
WRAP_DIR_ITER(ocfs2_readdir) // FIXME!
@@ -2828,6 +2829,7 @@ const struct file_operations ocfs2_dops = {
#endif
.lock = ocfs2_lock,
.flock = ocfs2_flock,
+ .fop_flags = FOP_ASYNC_LOCK,
};
/*
diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c
index c4a4016d3866..b0733c08ed13 100644
--- a/fs/ocfs2/resize.c
+++ b/fs/ocfs2/resize.c
@@ -574,6 +574,8 @@ out_commit:
ocfs2_commit_trans(osb, handle);
out_free_group_bh:
+ if (ret < 0)
+ ocfs2_remove_from_cache(INODE_CACHE(inode), group_bh);
brelse(group_bh);
out_unlock:
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 3d404624bb96..c79b4291777f 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -2319,6 +2319,7 @@ static int ocfs2_verify_volume(struct ocfs2_dinode *di,
struct ocfs2_blockcheck_stats *stats)
{
int status = -EAGAIN;
+ u32 blksz_bits;
if (memcmp(di->i_signature, OCFS2_SUPER_BLOCK_SIGNATURE,
strlen(OCFS2_SUPER_BLOCK_SIGNATURE)) == 0) {
@@ -2333,11 +2334,15 @@ static int ocfs2_verify_volume(struct ocfs2_dinode *di,
goto out;
}
status = -EINVAL;
- if ((1 << le32_to_cpu(di->id2.i_super.s_blocksize_bits)) != blksz) {
+ /* Acceptable block sizes are 512 bytes, 1K, 2K and 4K. */
+ blksz_bits = le32_to_cpu(di->id2.i_super.s_blocksize_bits);
+ if (blksz_bits < 9 || blksz_bits > 12) {
mlog(ML_ERROR, "found superblock with incorrect block "
- "size: found %u, should be %u\n",
- 1 << le32_to_cpu(di->id2.i_super.s_blocksize_bits),
- blksz);
+ "size bits: found %u, should be 9, 10, 11, or 12\n",
+ blksz_bits);
+ } else if ((1 << le32_to_cpu(blksz_bits)) != blksz) {
+ mlog(ML_ERROR, "found superblock with incorrect block "
+ "size: found %u, should be %u\n", 1 << blksz_bits, blksz);
} else if (le16_to_cpu(di->id2.i_super.s_major_rev_level) !=
OCFS2_MAJOR_REV_LEVEL ||
le16_to_cpu(di->id2.i_super.s_minor_rev_level) !=
diff --git a/fs/open.c b/fs/open.c
index 5da4df2f9b18..4b37c5912e6c 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -187,19 +187,13 @@ long do_ftruncate(struct file *file, loff_t length, int small)
long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
{
- struct fd f;
- int error;
-
if (length < 0)
return -EINVAL;
- f = fdget(fd);
- if (!fd_file(f))
+ CLASS(fd, f)(fd);
+ if (fd_empty(f))
return -EBADF;
- error = do_ftruncate(fd_file(f), length, small);
-
- fdput(f);
- return error;
+ return do_ftruncate(fd_file(f), length, small);
}
SYSCALL_DEFINE2(ftruncate, unsigned int, fd, off_t, length)
@@ -349,14 +343,12 @@ EXPORT_SYMBOL_GPL(vfs_fallocate);
int ksys_fallocate(int fd, int mode, loff_t offset, loff_t len)
{
- struct fd f = fdget(fd);
- int error = -EBADF;
+ CLASS(fd, f)(fd);
- if (fd_file(f)) {
- error = vfs_fallocate(fd_file(f), mode, offset, len);
- fdput(f);
- }
- return error;
+ if (fd_empty(f))
+ return -EBADF;
+
+ return vfs_fallocate(fd_file(f), mode, offset, len);
}
SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len)
@@ -580,23 +572,18 @@ out:
SYSCALL_DEFINE1(fchdir, unsigned int, fd)
{
- struct fd f = fdget_raw(fd);
+ CLASS(fd_raw, f)(fd);
int error;
- error = -EBADF;
- if (!fd_file(f))
- goto out;
+ if (fd_empty(f))
+ return -EBADF;
- error = -ENOTDIR;
if (!d_can_lookup(fd_file(f)->f_path.dentry))
- goto out_putf;
+ return -ENOTDIR;
error = file_permission(fd_file(f), MAY_EXEC | MAY_CHDIR);
if (!error)
set_fs_pwd(current->fs, &fd_file(f)->f_path);
-out_putf:
- fdput(f);
-out:
return error;
}
@@ -671,14 +658,12 @@ int vfs_fchmod(struct file *file, umode_t mode)
SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode)
{
- struct fd f = fdget(fd);
- int err = -EBADF;
+ CLASS(fd, f)(fd);
- if (fd_file(f)) {
- err = vfs_fchmod(fd_file(f), mode);
- fdput(f);
- }
- return err;
+ if (fd_empty(f))
+ return -EBADF;
+
+ return vfs_fchmod(fd_file(f), mode);
}
static int do_fchmodat(int dfd, const char __user *filename, umode_t mode,
@@ -865,14 +850,12 @@ int vfs_fchown(struct file *file, uid_t user, gid_t group)
int ksys_fchown(unsigned int fd, uid_t user, gid_t group)
{
- struct fd f = fdget(fd);
- int error = -EBADF;
+ CLASS(fd, f)(fd);
- if (fd_file(f)) {
- error = vfs_fchown(fd_file(f), user, group);
- fdput(f);
- }
- return error;
+ if (fd_empty(f))
+ return -EBADF;
+
+ return vfs_fchown(fd_file(f), user, group);
}
SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group)
@@ -1576,23 +1559,6 @@ SYSCALL_DEFINE1(close, unsigned int, fd)
return retval;
}
-/**
- * sys_close_range() - Close all file descriptors in a given range.
- *
- * @fd: starting file descriptor to close
- * @max_fd: last file descriptor to close
- * @flags: reserved for future extensions
- *
- * This closes a range of file descriptors. All file descriptors
- * from @fd up to and including @max_fd are closed.
- * Currently, errors to close a given file descriptor are ignored.
- */
-SYSCALL_DEFINE3(close_range, unsigned int, fd, unsigned int, max_fd,
- unsigned int, flags)
-{
- return __close_range(fd, max_fd, flags);
-}
-
/*
* This routine simulates a hangup on the tty, to arrange that users
* are given clean terminals at login time.
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 2ed6ad641a20..ee2cbd044ce6 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -16,7 +16,6 @@
#include <linux/sched/signal.h>
#include <linux/cred.h>
#include <linux/namei.h>
-#include <linux/fdtable.h>
#include <linux/ratelimit.h>
#include <linux/exportfs.h>
#include "overlayfs.h"
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 35fd3e3e1778..8b31f44c12cd 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -170,7 +170,7 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path,
type = ovl_path_real(dentry, &realpath);
old_cred = ovl_override_creds(dentry->d_sb);
- err = ovl_do_getattr(&realpath, stat, request_mask, flags);
+ err = vfs_getattr_nosec(&realpath, stat, request_mask, flags);
if (err)
goto out;
@@ -195,8 +195,8 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path,
(!is_dir ? STATX_NLINK : 0);
ovl_path_lower(dentry, &realpath);
- err = ovl_do_getattr(&realpath, &lowerstat, lowermask,
- flags);
+ err = vfs_getattr_nosec(&realpath, &lowerstat, lowermask,
+ flags);
if (err)
goto out;
@@ -248,8 +248,8 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path,
ovl_path_lowerdata(dentry, &realpath);
if (realpath.dentry) {
- err = ovl_do_getattr(&realpath, &lowerdatastat,
- lowermask, flags);
+ err = vfs_getattr_nosec(&realpath, &lowerdatastat,
+ lowermask, flags);
if (err)
goto out;
} else {
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 0bfe35da4b7b..910dbbb2bb7b 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -412,14 +412,6 @@ static inline bool ovl_open_flags_need_copy_up(int flags)
return ((OPEN_FMODE(flags) & FMODE_WRITE) || (flags & O_TRUNC));
}
-static inline int ovl_do_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int flags)
-{
- if (flags & AT_GETATTR_NOSEC)
- return vfs_getattr_nosec(path, stat, request_mask, flags);
- return vfs_getattr(path, stat, request_mask, flags);
-}
-
/* util.c */
int ovl_get_write_access(struct dentry *dentry);
void ovl_put_write_access(struct dentry *dentry);
diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c
index e42546c6c5df..1115c22deca0 100644
--- a/fs/overlayfs/params.c
+++ b/fs/overlayfs/params.c
@@ -141,10 +141,10 @@ static int ovl_verity_mode_def(void)
const struct fs_parameter_spec ovl_parameter_spec[] = {
fsparam_string_empty("lowerdir", Opt_lowerdir),
- fsparam_string("lowerdir+", Opt_lowerdir_add),
- fsparam_string("datadir+", Opt_datadir_add),
- fsparam_string("upperdir", Opt_upperdir),
- fsparam_string("workdir", Opt_workdir),
+ fsparam_file_or_string("lowerdir+", Opt_lowerdir_add),
+ fsparam_file_or_string("datadir+", Opt_datadir_add),
+ fsparam_file_or_string("upperdir", Opt_upperdir),
+ fsparam_file_or_string("workdir", Opt_workdir),
fsparam_flag("default_permissions", Opt_default_permissions),
fsparam_enum("redirect_dir", Opt_redirect_dir, ovl_parameter_redirect_dir),
fsparam_enum("index", Opt_index, ovl_parameter_bool),
@@ -367,40 +367,100 @@ static void ovl_add_layer(struct fs_context *fc, enum ovl_opt layer,
}
}
-static int ovl_parse_layer(struct fs_context *fc, const char *layer_name, enum ovl_opt layer)
+static inline bool is_upper_layer(enum ovl_opt layer)
+{
+ return layer == Opt_upperdir || layer == Opt_workdir;
+}
+
+/* Handle non-file descriptor-based layer options that require path lookup. */
+static inline int ovl_kern_path(const char *layer_name, struct path *layer_path,
+ enum ovl_opt layer)
{
- char *name = kstrdup(layer_name, GFP_KERNEL);
- bool upper = (layer == Opt_upperdir || layer == Opt_workdir);
- struct path path;
int err;
+ switch (layer) {
+ case Opt_upperdir:
+ fallthrough;
+ case Opt_workdir:
+ fallthrough;
+ case Opt_lowerdir:
+ err = ovl_mount_dir(layer_name, layer_path);
+ break;
+ case Opt_lowerdir_add:
+ fallthrough;
+ case Opt_datadir_add:
+ err = ovl_mount_dir_noesc(layer_name, layer_path);
+ break;
+ default:
+ WARN_ON_ONCE(true);
+ err = -EINVAL;
+ }
+
+ return err;
+}
+
+static int ovl_do_parse_layer(struct fs_context *fc, const char *layer_name,
+ struct path *layer_path, enum ovl_opt layer)
+{
+ char *name __free(kfree) = kstrdup(layer_name, GFP_KERNEL);
+ bool upper;
+ int err = 0;
+
if (!name)
return -ENOMEM;
- if (upper || layer == Opt_lowerdir)
- err = ovl_mount_dir(name, &path);
- else
- err = ovl_mount_dir_noesc(name, &path);
+ upper = is_upper_layer(layer);
+ err = ovl_mount_dir_check(fc, layer_path, layer, name, upper);
if (err)
- goto out_free;
-
- err = ovl_mount_dir_check(fc, &path, layer, name, upper);
- if (err)
- goto out_put;
+ return err;
if (!upper) {
err = ovl_ctx_realloc_lower(fc);
if (err)
- goto out_put;
+ return err;
}
/* Store the user provided path string in ctx to show in mountinfo */
- ovl_add_layer(fc, layer, &path, &name);
+ ovl_add_layer(fc, layer, layer_path, &name);
+ return err;
+}
+
+static int ovl_parse_layer(struct fs_context *fc, struct fs_parameter *param,
+ enum ovl_opt layer)
+{
+ struct path layer_path __free(path_put) = {};
+ int err = 0;
+
+ switch (param->type) {
+ case fs_value_is_string:
+ err = ovl_kern_path(param->string, &layer_path, layer);
+ if (err)
+ return err;
+ err = ovl_do_parse_layer(fc, param->string, &layer_path, layer);
+ break;
+ case fs_value_is_file: {
+ char *buf __free(kfree);
+ char *layer_name;
+
+ buf = kmalloc(PATH_MAX, GFP_KERNEL_ACCOUNT);
+ if (!buf)
+ return -ENOMEM;
+
+ layer_path = param->file->f_path;
+ path_get(&layer_path);
+
+ layer_name = d_path(&layer_path, buf, PATH_MAX);
+ if (IS_ERR(layer_name))
+ return PTR_ERR(layer_name);
+
+ err = ovl_do_parse_layer(fc, layer_name, &layer_path, layer);
+ break;
+ }
+ default:
+ WARN_ON_ONCE(true);
+ err = -EINVAL;
+ }
-out_put:
- path_put(&path);
-out_free:
- kfree(name);
return err;
}
@@ -474,7 +534,13 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
iter = dup;
for (nr = 0; nr < nr_lower; nr++) {
- err = ovl_parse_layer(fc, iter, Opt_lowerdir);
+ struct path path __free(path_put) = {};
+
+ err = ovl_kern_path(iter, &path, Opt_lowerdir);
+ if (err)
+ goto out_err;
+
+ err = ovl_do_parse_layer(fc, iter, &path, Opt_lowerdir);
if (err)
goto out_err;
@@ -555,7 +621,7 @@ static int ovl_parse_param(struct fs_context *fc, struct fs_parameter *param)
case Opt_datadir_add:
case Opt_upperdir:
case Opt_workdir:
- err = ovl_parse_layer(fc, param->string, opt);
+ err = ovl_parse_layer(fc, param, opt);
break;
case Opt_default_permissions:
config->default_permissions = true;
diff --git a/fs/pidfs.c b/fs/pidfs.c
index 80675b6bf884..618abb1fa1b8 100644
--- a/fs/pidfs.c
+++ b/fs/pidfs.c
@@ -2,6 +2,7 @@
#include <linux/anon_inodes.h>
#include <linux/file.h>
#include <linux/fs.h>
+#include <linux/cgroup.h>
#include <linux/magic.h>
#include <linux/mount.h>
#include <linux/pid.h>
@@ -114,6 +115,81 @@ static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts)
return poll_flags;
}
+static long pidfd_info(struct task_struct *task, unsigned int cmd, unsigned long arg)
+{
+ struct pidfd_info __user *uinfo = (struct pidfd_info __user *)arg;
+ size_t usize = _IOC_SIZE(cmd);
+ struct pidfd_info kinfo = {};
+ struct user_namespace *user_ns;
+ const struct cred *c;
+ __u64 mask;
+#ifdef CONFIG_CGROUPS
+ struct cgroup *cgrp;
+#endif
+
+ if (!uinfo)
+ return -EINVAL;
+ if (usize < PIDFD_INFO_SIZE_VER0)
+ return -EINVAL; /* First version, no smaller struct possible */
+
+ if (copy_from_user(&mask, &uinfo->mask, sizeof(mask)))
+ return -EFAULT;
+
+ c = get_task_cred(task);
+ if (!c)
+ return -ESRCH;
+
+ /* Unconditionally return identifiers and credentials, the rest only on request */
+
+ user_ns = current_user_ns();
+ kinfo.ruid = from_kuid_munged(user_ns, c->uid);
+ kinfo.rgid = from_kgid_munged(user_ns, c->gid);
+ kinfo.euid = from_kuid_munged(user_ns, c->euid);
+ kinfo.egid = from_kgid_munged(user_ns, c->egid);
+ kinfo.suid = from_kuid_munged(user_ns, c->suid);
+ kinfo.sgid = from_kgid_munged(user_ns, c->sgid);
+ kinfo.fsuid = from_kuid_munged(user_ns, c->fsuid);
+ kinfo.fsgid = from_kgid_munged(user_ns, c->fsgid);
+ kinfo.mask |= PIDFD_INFO_CREDS;
+ put_cred(c);
+
+#ifdef CONFIG_CGROUPS
+ rcu_read_lock();
+ cgrp = task_dfl_cgroup(task);
+ kinfo.cgroupid = cgroup_id(cgrp);
+ kinfo.mask |= PIDFD_INFO_CGROUPID;
+ rcu_read_unlock();
+#endif
+
+ /*
+ * Copy pid/tgid last, to reduce the chances the information might be
+ * stale. Note that it is not possible to ensure it will be valid as the
+ * task might return as soon as the copy_to_user finishes, but that's ok
+ * and userspace expects that might happen and can act accordingly, so
+ * this is just best-effort. What we can do however is checking that all
+ * the fields are set correctly, or return ESRCH to avoid providing
+ * incomplete information. */
+
+ kinfo.ppid = task_ppid_nr_ns(task, NULL);
+ kinfo.tgid = task_tgid_vnr(task);
+ kinfo.pid = task_pid_vnr(task);
+ kinfo.mask |= PIDFD_INFO_PID;
+
+ if (kinfo.pid == 0 || kinfo.tgid == 0 || (kinfo.ppid == 0 && kinfo.pid != 1))
+ return -ESRCH;
+
+ /*
+ * If userspace and the kernel have the same struct size it can just
+ * be copied. If userspace provides an older struct, only the bits that
+ * userspace knows about will be copied. If userspace provides a new
+ * struct, only the bits that the kernel knows about will be copied.
+ */
+ if (copy_to_user(uinfo, &kinfo, min(usize, sizeof(kinfo))))
+ return -EFAULT;
+
+ return 0;
+}
+
static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
struct task_struct *task __free(put_task) = NULL;
@@ -122,13 +198,17 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
struct ns_common *ns_common = NULL;
struct pid_namespace *pid_ns;
- if (arg)
- return -EINVAL;
-
task = get_pid_task(pid, PIDTYPE_PID);
if (!task)
return -ESRCH;
+ /* Extensible IOCTL that does not open namespace FDs, take a shortcut */
+ if (_IOC_NR(cmd) == _IOC_NR(PIDFD_GET_INFO))
+ return pidfd_info(task, cmd, arg);
+
+ if (arg)
+ return -EINVAL;
+
scoped_guard(task_lock, task) {
nsp = task->nsproxy;
if (nsp)
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 6c66a37522d0..4050942ab52f 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -200,11 +200,11 @@ EXPORT_SYMBOL(posix_acl_init);
* Allocate a new ACL with the specified number of entries.
*/
struct posix_acl *
-posix_acl_alloc(int count, gfp_t flags)
+posix_acl_alloc(unsigned int count, gfp_t flags)
{
- const size_t size = sizeof(struct posix_acl) +
- count * sizeof(struct posix_acl_entry);
- struct posix_acl *acl = kmalloc(size, flags);
+ struct posix_acl *acl;
+
+ acl = kmalloc(struct_size(acl, a_entries, count), flags);
if (acl)
posix_acl_init(acl, count);
return acl;
@@ -220,9 +220,8 @@ posix_acl_clone(const struct posix_acl *acl, gfp_t flags)
struct posix_acl *clone = NULL;
if (acl) {
- int size = sizeof(struct posix_acl) + acl->a_count *
- sizeof(struct posix_acl_entry);
- clone = kmemdup(acl, size, flags);
+ clone = kmemdup(acl, struct_size(acl, a_entries, acl->a_count),
+ flags);
if (clone)
refcount_set(&clone->a_refcount, 1);
}
diff --git a/fs/proc/base.c b/fs/proc/base.c
index b31283d81c52..e9d7ddc52f69 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -58,7 +58,6 @@
#include <linux/init.h>
#include <linux/capability.h>
#include <linux/file.h>
-#include <linux/fdtable.h>
#include <linux/generic-radix-tree.h>
#include <linux/string.h>
#include <linux/seq_file.h>
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 5e391cbca7a3..24baf23e864f 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -116,9 +116,7 @@ static bool tid_fd_mode(struct task_struct *task, unsigned fd, fmode_t *mode)
{
struct file *file;
- rcu_read_lock();
- file = task_lookup_fdget_rcu(task, fd);
- rcu_read_unlock();
+ file = fget_task(task, fd);
if (file) {
*mode = file->f_mode;
fput(file);
@@ -258,19 +256,17 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx,
if (!dir_emit_dots(file, ctx))
goto out;
- rcu_read_lock();
for (fd = ctx->pos - 2;; fd++) {
struct file *f;
struct fd_data data;
char name[10 + 1];
unsigned int len;
- f = task_lookup_next_fdget_rcu(p, &fd);
+ f = fget_task_next(p, &fd);
ctx->pos = fd + 2LL;
if (!f)
break;
data.mode = f->f_mode;
- rcu_read_unlock();
fput(f);
data.fd = fd;
@@ -278,11 +274,9 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx,
if (!proc_fill_cache(file, ctx,
name, len, instantiate, p,
&data))
- goto out;
+ break;
cond_resched();
- rcu_read_lock();
}
- rcu_read_unlock();
out:
put_task_struct(p);
return 0;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index e52bd96137a6..7eb010de39fe 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -2665,8 +2665,10 @@ static int pagemap_scan_get_args(struct pm_scan_arg *arg,
return -EFAULT;
if (!arg->vec && arg->vec_len)
return -EINVAL;
+ if (UINT_MAX == SIZE_MAX && arg->vec_len > SIZE_MAX)
+ return -EINVAL;
if (arg->vec && !access_ok((void __user *)(long)arg->vec,
- arg->vec_len * sizeof(struct page_region)))
+ size_mul(arg->vec_len, sizeof(struct page_region))))
return -EFAULT;
/* Fixup default values */
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 290157bc7bec..7c2b75a44485 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -976,21 +976,19 @@ SYSCALL_DEFINE4(quotactl_fd, unsigned int, fd, unsigned int, cmd,
struct super_block *sb;
unsigned int cmds = cmd >> SUBCMDSHIFT;
unsigned int type = cmd & SUBCMDMASK;
- struct fd f;
+ CLASS(fd_raw, f)(fd);
int ret;
- f = fdget_raw(fd);
- if (!fd_file(f))
+ if (fd_empty(f))
return -EBADF;
- ret = -EINVAL;
if (type >= MAXQUOTAS)
- goto out;
+ return -EINVAL;
if (quotactl_cmd_write(cmds)) {
ret = mnt_want_write(fd_file(f)->f_path.mnt);
if (ret)
- goto out;
+ return ret;
}
sb = fd_file(f)->f_path.mnt->mnt_sb;
@@ -1008,7 +1006,5 @@ SYSCALL_DEFINE4(quotactl_fd, unsigned int, fd, unsigned int, cmd,
if (quotactl_cmd_write(cmds))
mnt_drop_write(fd_file(f)->f_path.mnt);
-out:
- fdput(f);
return ret;
}
diff --git a/fs/read_write.c b/fs/read_write.c
index 64dc24afdb3a..a6133241dfb8 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -386,8 +386,8 @@ EXPORT_SYMBOL(vfs_llseek);
static off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence)
{
off_t retval;
- struct fd f = fdget_pos(fd);
- if (!fd_file(f))
+ CLASS(fd_pos, f)(fd);
+ if (fd_empty(f))
return -EBADF;
retval = -EINVAL;
@@ -397,7 +397,6 @@ static off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence)
if (res != (loff_t)retval)
retval = -EOVERFLOW; /* LFS: should only happen on 32 bit platforms */
}
- fdput_pos(f);
return retval;
}
@@ -420,15 +419,14 @@ SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high,
unsigned int, whence)
{
int retval;
- struct fd f = fdget_pos(fd);
+ CLASS(fd_pos, f)(fd);
loff_t offset;
- if (!fd_file(f))
+ if (fd_empty(f))
return -EBADF;
- retval = -EINVAL;
if (whence > SEEK_MAX)
- goto out_putf;
+ return -EINVAL;
offset = vfs_llseek(fd_file(f), ((loff_t) offset_high << 32) | offset_low,
whence);
@@ -439,8 +437,6 @@ SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high,
if (!copy_to_user(result, &offset, sizeof(offset)))
retval = 0;
}
-out_putf:
- fdput_pos(f);
return retval;
}
#endif
@@ -700,10 +696,10 @@ static inline loff_t *file_ppos(struct file *file)
ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count)
{
- struct fd f = fdget_pos(fd);
+ CLASS(fd_pos, f)(fd);
ssize_t ret = -EBADF;
- if (fd_file(f)) {
+ if (!fd_empty(f)) {
loff_t pos, *ppos = file_ppos(fd_file(f));
if (ppos) {
pos = *ppos;
@@ -712,7 +708,6 @@ ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count)
ret = vfs_read(fd_file(f), buf, count, ppos);
if (ret >= 0 && ppos)
fd_file(f)->f_pos = pos;
- fdput_pos(f);
}
return ret;
}
@@ -724,10 +719,10 @@ SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count)
{
- struct fd f = fdget_pos(fd);
+ CLASS(fd_pos, f)(fd);
ssize_t ret = -EBADF;
- if (fd_file(f)) {
+ if (!fd_empty(f)) {
loff_t pos, *ppos = file_ppos(fd_file(f));
if (ppos) {
pos = *ppos;
@@ -736,7 +731,6 @@ ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count)
ret = vfs_write(fd_file(f), buf, count, ppos);
if (ret >= 0 && ppos)
fd_file(f)->f_pos = pos;
- fdput_pos(f);
}
return ret;
@@ -751,21 +745,17 @@ SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf,
ssize_t ksys_pread64(unsigned int fd, char __user *buf, size_t count,
loff_t pos)
{
- struct fd f;
- ssize_t ret = -EBADF;
-
if (pos < 0)
return -EINVAL;
- f = fdget(fd);
- if (fd_file(f)) {
- ret = -ESPIPE;
- if (fd_file(f)->f_mode & FMODE_PREAD)
- ret = vfs_read(fd_file(f), buf, count, &pos);
- fdput(f);
- }
+ CLASS(fd, f)(fd);
+ if (fd_empty(f))
+ return -EBADF;
- return ret;
+ if (fd_file(f)->f_mode & FMODE_PREAD)
+ return vfs_read(fd_file(f), buf, count, &pos);
+
+ return -ESPIPE;
}
SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf,
@@ -785,21 +775,17 @@ COMPAT_SYSCALL_DEFINE5(pread64, unsigned int, fd, char __user *, buf,
ssize_t ksys_pwrite64(unsigned int fd, const char __user *buf,
size_t count, loff_t pos)
{
- struct fd f;
- ssize_t ret = -EBADF;
-
if (pos < 0)
return -EINVAL;
- f = fdget(fd);
- if (fd_file(f)) {
- ret = -ESPIPE;
- if (fd_file(f)->f_mode & FMODE_PWRITE)
- ret = vfs_write(fd_file(f), buf, count, &pos);
- fdput(f);
- }
+ CLASS(fd, f)(fd);
+ if (fd_empty(f))
+ return -EBADF;
- return ret;
+ if (fd_file(f)->f_mode & FMODE_PWRITE)
+ return vfs_write(fd_file(f), buf, count, &pos);
+
+ return -ESPIPE;
}
SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf,
@@ -1075,10 +1061,10 @@ out:
static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec,
unsigned long vlen, rwf_t flags)
{
- struct fd f = fdget_pos(fd);
+ CLASS(fd_pos, f)(fd);
ssize_t ret = -EBADF;
- if (fd_file(f)) {
+ if (!fd_empty(f)) {
loff_t pos, *ppos = file_ppos(fd_file(f));
if (ppos) {
pos = *ppos;
@@ -1087,7 +1073,6 @@ static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec,
ret = vfs_readv(fd_file(f), vec, vlen, ppos, flags);
if (ret >= 0 && ppos)
fd_file(f)->f_pos = pos;
- fdput_pos(f);
}
if (ret > 0)
@@ -1099,10 +1084,10 @@ static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec,
static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec,
unsigned long vlen, rwf_t flags)
{
- struct fd f = fdget_pos(fd);
+ CLASS(fd_pos, f)(fd);
ssize_t ret = -EBADF;
- if (fd_file(f)) {
+ if (!fd_empty(f)) {
loff_t pos, *ppos = file_ppos(fd_file(f));
if (ppos) {
pos = *ppos;
@@ -1111,7 +1096,6 @@ static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec,
ret = vfs_writev(fd_file(f), vec, vlen, ppos, flags);
if (ret >= 0 && ppos)
fd_file(f)->f_pos = pos;
- fdput_pos(f);
}
if (ret > 0)
@@ -1129,18 +1113,16 @@ static inline loff_t pos_from_hilo(unsigned long high, unsigned long low)
static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec,
unsigned long vlen, loff_t pos, rwf_t flags)
{
- struct fd f;
ssize_t ret = -EBADF;
if (pos < 0)
return -EINVAL;
- f = fdget(fd);
- if (fd_file(f)) {
+ CLASS(fd, f)(fd);
+ if (!fd_empty(f)) {
ret = -ESPIPE;
if (fd_file(f)->f_mode & FMODE_PREAD)
ret = vfs_readv(fd_file(f), vec, vlen, &pos, flags);
- fdput(f);
}
if (ret > 0)
@@ -1152,18 +1134,16 @@ static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec,
static ssize_t do_pwritev(unsigned long fd, const struct iovec __user *vec,
unsigned long vlen, loff_t pos, rwf_t flags)
{
- struct fd f;
ssize_t ret = -EBADF;
if (pos < 0)
return -EINVAL;
- f = fdget(fd);
- if (fd_file(f)) {
+ CLASS(fd, f)(fd);
+ if (!fd_empty(f)) {
ret = -ESPIPE;
if (fd_file(f)->f_mode & FMODE_PWRITE)
ret = vfs_writev(fd_file(f), vec, vlen, &pos, flags);
- fdput(f);
}
if (ret > 0)
@@ -1315,7 +1295,6 @@ COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd,
static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
size_t count, loff_t max)
{
- struct fd in, out;
struct inode *in_inode, *out_inode;
struct pipe_inode_info *opipe;
loff_t pos;
@@ -1326,35 +1305,32 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
/*
* Get input file, and verify that it is ok..
*/
- retval = -EBADF;
- in = fdget(in_fd);
- if (!fd_file(in))
- goto out;
+ CLASS(fd, in)(in_fd);
+ if (fd_empty(in))
+ return -EBADF;
if (!(fd_file(in)->f_mode & FMODE_READ))
- goto fput_in;
- retval = -ESPIPE;
+ return -EBADF;
if (!ppos) {
pos = fd_file(in)->f_pos;
} else {
pos = *ppos;
if (!(fd_file(in)->f_mode & FMODE_PREAD))
- goto fput_in;
+ return -ESPIPE;
}
retval = rw_verify_area(READ, fd_file(in), &pos, count);
if (retval < 0)
- goto fput_in;
+ return retval;
if (count > MAX_RW_COUNT)
count = MAX_RW_COUNT;
/*
* Get output file, and verify that it is ok..
*/
- retval = -EBADF;
- out = fdget(out_fd);
- if (!fd_file(out))
- goto fput_in;
+ CLASS(fd, out)(out_fd);
+ if (fd_empty(out))
+ return -EBADF;
if (!(fd_file(out)->f_mode & FMODE_WRITE))
- goto fput_out;
+ return -EBADF;
in_inode = file_inode(fd_file(in));
out_inode = file_inode(fd_file(out));
out_pos = fd_file(out)->f_pos;
@@ -1363,9 +1339,8 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes);
if (unlikely(pos + count > max)) {
- retval = -EOVERFLOW;
if (pos >= max)
- goto fput_out;
+ return -EOVERFLOW;
count = max - pos;
}
@@ -1384,7 +1359,7 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
if (!opipe) {
retval = rw_verify_area(WRITE, fd_file(out), &out_pos, count);
if (retval < 0)
- goto fput_out;
+ return retval;
retval = do_splice_direct(fd_file(in), &pos, fd_file(out), &out_pos,
count, fl);
} else {
@@ -1410,12 +1385,6 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
inc_syscw(current);
if (pos > max)
retval = -EOVERFLOW;
-
-fput_out:
- fdput(out);
-fput_in:
- fdput(in);
-out:
return retval;
}
@@ -1671,36 +1640,32 @@ SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in,
{
loff_t pos_in;
loff_t pos_out;
- struct fd f_in;
- struct fd f_out;
ssize_t ret = -EBADF;
- f_in = fdget(fd_in);
- if (!fd_file(f_in))
- goto out2;
+ CLASS(fd, f_in)(fd_in);
+ if (fd_empty(f_in))
+ return -EBADF;
- f_out = fdget(fd_out);
- if (!fd_file(f_out))
- goto out1;
+ CLASS(fd, f_out)(fd_out);
+ if (fd_empty(f_out))
+ return -EBADF;
- ret = -EFAULT;
if (off_in) {
if (copy_from_user(&pos_in, off_in, sizeof(loff_t)))
- goto out;
+ return -EFAULT;
} else {
pos_in = fd_file(f_in)->f_pos;
}
if (off_out) {
if (copy_from_user(&pos_out, off_out, sizeof(loff_t)))
- goto out;
+ return -EFAULT;
} else {
pos_out = fd_file(f_out)->f_pos;
}
- ret = -EINVAL;
if (flags != 0)
- goto out;
+ return -EINVAL;
ret = vfs_copy_file_range(fd_file(f_in), pos_in, fd_file(f_out), pos_out, len,
flags);
@@ -1722,12 +1687,6 @@ SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in,
fd_file(f_out)->f_pos = pos_out;
}
}
-
-out:
- fdput(f_out);
-out1:
- fdput(f_in);
-out2:
return ret;
}
@@ -1830,18 +1789,22 @@ int generic_file_rw_checks(struct file *file_in, struct file *file_out)
return 0;
}
-bool generic_atomic_write_valid(struct iov_iter *iter, loff_t pos)
+int generic_atomic_write_valid(struct kiocb *iocb, struct iov_iter *iter)
{
size_t len = iov_iter_count(iter);
if (!iter_is_ubuf(iter))
- return false;
+ return -EINVAL;
if (!is_power_of_2(len))
- return false;
+ return -EINVAL;
- if (!IS_ALIGNED(pos, len))
- return false;
+ if (!IS_ALIGNED(iocb->ki_pos, len))
+ return -EINVAL;
- return true;
+ if (!(iocb->ki_flags & IOCB_DIRECT))
+ return -EOPNOTSUPP;
+
+ return 0;
}
+EXPORT_SYMBOL_GPL(generic_atomic_write_valid);
diff --git a/fs/readdir.c b/fs/readdir.c
index 6d29cab8576e..0038efda417b 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -219,20 +219,19 @@ SYSCALL_DEFINE3(old_readdir, unsigned int, fd,
struct old_linux_dirent __user *, dirent, unsigned int, count)
{
int error;
- struct fd f = fdget_pos(fd);
+ CLASS(fd_pos, f)(fd);
struct readdir_callback buf = {
.ctx.actor = fillonedir,
.dirent = dirent
};
- if (!fd_file(f))
+ if (fd_empty(f))
return -EBADF;
error = iterate_dir(fd_file(f), &buf.ctx);
if (buf.result)
error = buf.result;
- fdput_pos(f);
return error;
}
@@ -309,7 +308,7 @@ efault:
SYSCALL_DEFINE3(getdents, unsigned int, fd,
struct linux_dirent __user *, dirent, unsigned int, count)
{
- struct fd f;
+ CLASS(fd_pos, f)(fd);
struct getdents_callback buf = {
.ctx.actor = filldir,
.count = count,
@@ -317,8 +316,7 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd,
};
int error;
- f = fdget_pos(fd);
- if (!fd_file(f))
+ if (fd_empty(f))
return -EBADF;
error = iterate_dir(fd_file(f), &buf.ctx);
@@ -333,7 +331,6 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd,
else
error = count - buf.count;
}
- fdput_pos(f);
return error;
}
@@ -392,7 +389,7 @@ efault:
SYSCALL_DEFINE3(getdents64, unsigned int, fd,
struct linux_dirent64 __user *, dirent, unsigned int, count)
{
- struct fd f;
+ CLASS(fd_pos, f)(fd);
struct getdents_callback64 buf = {
.ctx.actor = filldir64,
.count = count,
@@ -400,8 +397,7 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd,
};
int error;
- f = fdget_pos(fd);
- if (!fd_file(f))
+ if (fd_empty(f))
return -EBADF;
error = iterate_dir(fd_file(f), &buf.ctx);
@@ -417,7 +413,6 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd,
else
error = count - buf.count;
}
- fdput_pos(f);
return error;
}
@@ -477,20 +472,19 @@ COMPAT_SYSCALL_DEFINE3(old_readdir, unsigned int, fd,
struct compat_old_linux_dirent __user *, dirent, unsigned int, count)
{
int error;
- struct fd f = fdget_pos(fd);
+ CLASS(fd_pos, f)(fd);
struct compat_readdir_callback buf = {
.ctx.actor = compat_fillonedir,
.dirent = dirent
};
- if (!fd_file(f))
+ if (fd_empty(f))
return -EBADF;
error = iterate_dir(fd_file(f), &buf.ctx);
if (buf.result)
error = buf.result;
- fdput_pos(f);
return error;
}
@@ -560,7 +554,7 @@ efault:
COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd,
struct compat_linux_dirent __user *, dirent, unsigned int, count)
{
- struct fd f;
+ CLASS(fd_pos, f)(fd);
struct compat_getdents_callback buf = {
.ctx.actor = compat_filldir,
.current_dir = dirent,
@@ -568,8 +562,7 @@ COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd,
};
int error;
- f = fdget_pos(fd);
- if (!fd_file(f))
+ if (fd_empty(f))
return -EBADF;
error = iterate_dir(fd_file(f), &buf.ctx);
@@ -584,7 +577,6 @@ COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd,
else
error = count - buf.count;
}
- fdput_pos(f);
return error;
}
#endif
diff --git a/fs/remap_range.c b/fs/remap_range.c
index 4403d5c68fcb..26afbbbfb10c 100644
--- a/fs/remap_range.c
+++ b/fs/remap_range.c
@@ -536,20 +536,19 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
}
for (i = 0, info = same->info; i < count; i++, info++) {
- struct fd dst_fd = fdget(info->dest_fd);
- struct file *dst_file = fd_file(dst_fd);
+ CLASS(fd, dst_fd)(info->dest_fd);
- if (!dst_file) {
+ if (fd_empty(dst_fd)) {
info->status = -EBADF;
goto next_loop;
}
if (info->reserved) {
info->status = -EINVAL;
- goto next_fdput;
+ goto next_loop;
}
- deduped = vfs_dedupe_file_range_one(file, off, dst_file,
+ deduped = vfs_dedupe_file_range_one(file, off, fd_file(dst_fd),
info->dest_offset, len,
REMAP_FILE_CAN_SHORTEN);
if (deduped == -EBADE)
@@ -559,8 +558,6 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
else
info->bytes_deduped = len;
-next_fdput:
- fdput(dst_fd);
next_loop:
if (fatal_signal_pending(current))
break;
diff --git a/fs/select.c b/fs/select.c
index a77907faf2b4..e223d1fe9d55 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -462,15 +462,22 @@ get_max:
EPOLLNVAL)
#define POLLEX_SET (EPOLLPRI | EPOLLNVAL)
-static inline void wait_key_set(poll_table *wait, unsigned long in,
+static inline __poll_t select_poll_one(int fd, poll_table *wait, unsigned long in,
unsigned long out, unsigned long bit,
__poll_t ll_flag)
{
+ CLASS(fd, f)(fd);
+
+ if (fd_empty(f))
+ return EPOLLNVAL;
+
wait->_key = POLLEX_SET | ll_flag;
if (in & bit)
wait->_key |= POLLIN_SET;
if (out & bit)
wait->_key |= POLLOUT_SET;
+
+ return vfs_poll(fd_file(f), wait);
}
static noinline_for_stack int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
@@ -522,20 +529,12 @@ static noinline_for_stack int do_select(int n, fd_set_bits *fds, struct timespec
}
for (j = 0; j < BITS_PER_LONG; ++j, ++i, bit <<= 1) {
- struct fd f;
if (i >= n)
break;
if (!(bit & all_bits))
continue;
- mask = EPOLLNVAL;
- f = fdget(i);
- if (fd_file(f)) {
- wait_key_set(wait, in, out, bit,
- busy_flag);
- mask = vfs_poll(fd_file(f), wait);
-
- fdput(f);
- }
+ mask = select_poll_one(i, wait, in, out, bit,
+ busy_flag);
if ((mask & POLLIN_SET) && (in & bit)) {
res_in |= bit;
retval++;
@@ -856,15 +855,14 @@ static inline __poll_t do_pollfd(struct pollfd *pollfd, poll_table *pwait,
__poll_t busy_flag)
{
int fd = pollfd->fd;
- __poll_t mask = 0, filter;
- struct fd f;
+ __poll_t mask, filter;
if (fd < 0)
- goto out;
- mask = EPOLLNVAL;
- f = fdget(fd);
- if (!fd_file(f))
- goto out;
+ return 0;
+
+ CLASS(fd, f)(fd);
+ if (fd_empty(f))
+ return EPOLLNVAL;
/* userland u16 ->events contains POLL... bitmap */
filter = demangle_poll(pollfd->events) | EPOLLERR | EPOLLHUP;
@@ -872,13 +870,7 @@ static inline __poll_t do_pollfd(struct pollfd *pollfd, poll_table *pwait,
mask = vfs_poll(fd_file(f), pwait);
if (mask & busy_flag)
*can_busy_poll = true;
- mask &= filter; /* Mask out unneeded events. */
- fdput(f);
-
-out:
- /* ... and so does ->revents */
- pollfd->revents = mangle_poll(mask);
- return mask;
+ return mask & filter; /* Mask out unneeded events. */
}
static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
@@ -910,6 +902,7 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
pfd = walk->entries;
pfd_end = pfd + walk->len;
for (; pfd != pfd_end; pfd++) {
+ __poll_t mask;
/*
* Fish for events. If we found one, record it
* and kill poll_table->_qproc, so we don't
@@ -917,8 +910,9 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
* this. They'll get immediately deregistered
* when we break out and return.
*/
- if (do_pollfd(pfd, pt, &can_busy_loop,
- busy_flag)) {
+ mask = do_pollfd(pfd, pt, &can_busy_loop, busy_flag);
+ pfd->revents = mangle_poll(mask);
+ if (mask) {
count++;
pt->_qproc = NULL;
/* found something, stop busy polling */
diff --git a/fs/seq_file.c b/fs/seq_file.c
index e676c8b0cf5d..8bbb1ad46335 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -343,8 +343,8 @@ EXPORT_SYMBOL(seq_lseek);
/**
* seq_release - free the structures associated with sequential file.
- * @file: file in question
* @inode: its inode
+ * @file: file in question
*
* Frees the structures associated with sequential file; can be used
* as ->f_op->release() if you don't have private data to destroy.
diff --git a/fs/signalfd.c b/fs/signalfd.c
index 736bebf93591..d1a5f43ce466 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -288,20 +288,17 @@ static int do_signalfd4(int ufd, sigset_t *mask, int flags)
fd_install(ufd, file);
} else {
- struct fd f = fdget(ufd);
- if (!fd_file(f))
+ CLASS(fd, f)(ufd);
+ if (fd_empty(f))
return -EBADF;
ctx = fd_file(f)->private_data;
- if (fd_file(f)->f_op != &signalfd_fops) {
- fdput(f);
+ if (fd_file(f)->f_op != &signalfd_fops)
return -EINVAL;
- }
spin_lock_irq(&current->sighand->siglock);
ctx->sigmask = *mask;
spin_unlock_irq(&current->sighand->siglock);
wake_up(&current->sighand->signalfd_wqh);
- fdput(f);
}
return ufd;
diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c
index 2ce193609d8b..56439da4f119 100644
--- a/fs/smb/client/ioctl.c
+++ b/fs/smb/client/ioctl.c
@@ -72,7 +72,6 @@ static long cifs_ioctl_copychunk(unsigned int xid, struct file *dst_file,
unsigned long srcfd)
{
int rc;
- struct fd src_file;
struct inode *src_inode;
cifs_dbg(FYI, "ioctl copychunk range\n");
@@ -89,8 +88,8 @@ static long cifs_ioctl_copychunk(unsigned int xid, struct file *dst_file,
return rc;
}
- src_file = fdget(srcfd);
- if (!fd_file(src_file)) {
+ CLASS(fd, src_file)(srcfd);
+ if (fd_empty(src_file)) {
rc = -EBADF;
goto out_drop_write;
}
@@ -98,20 +97,18 @@ static long cifs_ioctl_copychunk(unsigned int xid, struct file *dst_file,
if (fd_file(src_file)->f_op->unlocked_ioctl != cifs_ioctl) {
rc = -EBADF;
cifs_dbg(VFS, "src file seems to be from a different filesystem type\n");
- goto out_fput;
+ goto out_drop_write;
}
src_inode = file_inode(fd_file(src_file));
rc = -EINVAL;
if (S_ISDIR(src_inode->i_mode))
- goto out_fput;
+ goto out_drop_write;
rc = cifs_file_copychunk_range(xid, fd_file(src_file), 0, dst_file, 0,
src_inode->i_size, 0);
if (rc > 0)
rc = 0;
-out_fput:
- fdput(src_file);
out_drop_write:
mnt_drop_write_file(dst_file);
return rc;
diff --git a/fs/splice.c b/fs/splice.c
index 06232d7e505f..2898fa1e9e63 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1564,21 +1564,6 @@ static ssize_t vmsplice_to_pipe(struct file *file, struct iov_iter *iter,
return ret;
}
-static int vmsplice_type(struct fd f, int *type)
-{
- if (!fd_file(f))
- return -EBADF;
- if (fd_file(f)->f_mode & FMODE_WRITE) {
- *type = ITER_SOURCE;
- } else if (fd_file(f)->f_mode & FMODE_READ) {
- *type = ITER_DEST;
- } else {
- fdput(f);
- return -EBADF;
- }
- return 0;
-}
-
/*
* Note that vmsplice only really supports true splicing _from_ user memory
* to a pipe, not the other way around. Splicing from user memory is a simple
@@ -1602,21 +1587,25 @@ SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, uiov,
struct iovec *iov = iovstack;
struct iov_iter iter;
ssize_t error;
- struct fd f;
int type;
if (unlikely(flags & ~SPLICE_F_ALL))
return -EINVAL;
- f = fdget(fd);
- error = vmsplice_type(f, &type);
- if (error)
- return error;
+ CLASS(fd, f)(fd);
+ if (fd_empty(f))
+ return -EBADF;
+ if (fd_file(f)->f_mode & FMODE_WRITE)
+ type = ITER_SOURCE;
+ else if (fd_file(f)->f_mode & FMODE_READ)
+ type = ITER_DEST;
+ else
+ return -EBADF;
error = import_iovec(type, uiov, nr_segs,
ARRAY_SIZE(iovstack), &iov, &iter);
if (error < 0)
- goto out_fdput;
+ return error;
if (!iov_iter_count(&iter))
error = 0;
@@ -1626,8 +1615,6 @@ SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, uiov,
error = vmsplice_to_user(fd_file(f), &iter, flags);
kfree(iov);
-out_fdput:
- fdput(f);
return error;
}
@@ -1635,27 +1622,22 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in,
int, fd_out, loff_t __user *, off_out,
size_t, len, unsigned int, flags)
{
- struct fd in, out;
- ssize_t error;
-
if (unlikely(!len))
return 0;
if (unlikely(flags & ~SPLICE_F_ALL))
return -EINVAL;
- error = -EBADF;
- in = fdget(fd_in);
- if (fd_file(in)) {
- out = fdget(fd_out);
- if (fd_file(out)) {
- error = __do_splice(fd_file(in), off_in, fd_file(out), off_out,
+ CLASS(fd, in)(fd_in);
+ if (fd_empty(in))
+ return -EBADF;
+
+ CLASS(fd, out)(fd_out);
+ if (fd_empty(out))
+ return -EBADF;
+
+ return __do_splice(fd_file(in), off_in, fd_file(out), off_out,
len, flags);
- fdput(out);
- }
- fdput(in);
- }
- return error;
}
/*
@@ -2005,25 +1987,19 @@ ssize_t do_tee(struct file *in, struct file *out, size_t len,
SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags)
{
- struct fd in, out;
- ssize_t error;
-
if (unlikely(flags & ~SPLICE_F_ALL))
return -EINVAL;
if (unlikely(!len))
return 0;
- error = -EBADF;
- in = fdget(fdin);
- if (fd_file(in)) {
- out = fdget(fdout);
- if (fd_file(out)) {
- error = do_tee(fd_file(in), fd_file(out), len, flags);
- fdput(out);
- }
- fdput(in);
- }
+ CLASS(fd, in)(fdin);
+ if (fd_empty(in))
+ return -EBADF;
- return error;
+ CLASS(fd, out)(fdout);
+ if (fd_empty(out))
+ return -EBADF;
+
+ return do_tee(fd_file(in), fd_file(out), len, flags);
}
diff --git a/fs/stat.c b/fs/stat.c
index 41e598376d7e..0870e969a8a0 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -23,10 +23,46 @@
#include <linux/uaccess.h>
#include <asm/unistd.h>
+#include <trace/events/timestamp.h>
+
#include "internal.h"
#include "mount.h"
/**
+ * fill_mg_cmtime - Fill in the mtime and ctime and flag ctime as QUERIED
+ * @stat: where to store the resulting values
+ * @request_mask: STATX_* values requested
+ * @inode: inode from which to grab the c/mtime
+ *
+ * Given @inode, grab the ctime and mtime out if it and store the result
+ * in @stat. When fetching the value, flag it as QUERIED (if not already)
+ * so the next write will record a distinct timestamp.
+ *
+ * NB: The QUERIED flag is tracked in the ctime, but we set it there even
+ * if only the mtime was requested, as that ensures that the next mtime
+ * change will be distinct.
+ */
+void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode)
+{
+ atomic_t *pcn = (atomic_t *)&inode->i_ctime_nsec;
+
+ /* If neither time was requested, then don't report them */
+ if (!(request_mask & (STATX_CTIME|STATX_MTIME))) {
+ stat->result_mask &= ~(STATX_CTIME|STATX_MTIME);
+ return;
+ }
+
+ stat->mtime = inode_get_mtime(inode);
+ stat->ctime.tv_sec = inode->i_ctime_sec;
+ stat->ctime.tv_nsec = (u32)atomic_read(pcn);
+ if (!(stat->ctime.tv_nsec & I_CTIME_QUERIED))
+ stat->ctime.tv_nsec = ((u32)atomic_fetch_or(I_CTIME_QUERIED, pcn));
+ stat->ctime.tv_nsec &= ~I_CTIME_QUERIED;
+ trace_fill_mg_cmtime(inode, &stat->ctime, &stat->mtime);
+}
+EXPORT_SYMBOL(fill_mg_cmtime);
+
+/**
* generic_fillattr - Fill in the basic attributes from the inode struct
* @idmap: idmap of the mount the inode was found from
* @request_mask: statx request_mask
@@ -58,8 +94,14 @@ void generic_fillattr(struct mnt_idmap *idmap, u32 request_mask,
stat->rdev = inode->i_rdev;
stat->size = i_size_read(inode);
stat->atime = inode_get_atime(inode);
- stat->mtime = inode_get_mtime(inode);
- stat->ctime = inode_get_ctime(inode);
+
+ if (is_mgtime(inode)) {
+ fill_mg_cmtime(stat, request_mask, inode);
+ } else {
+ stat->ctime = inode_get_ctime(inode);
+ stat->mtime = inode_get_mtime(inode);
+ }
+
stat->blksize = i_blocksize(inode);
stat->blocks = inode->i_blocks;
@@ -165,7 +207,7 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat,
if (inode->i_op->getattr)
return inode->i_op->getattr(idmap, path, stat,
request_mask,
- query_flags | AT_GETATTR_NOSEC);
+ query_flags);
generic_fillattr(idmap, request_mask, inode, stat);
return 0;
@@ -198,9 +240,6 @@ int vfs_getattr(const struct path *path, struct kstat *stat,
{
int retval;
- if (WARN_ON_ONCE(query_flags & AT_GETATTR_NOSEC))
- return -EPERM;
-
retval = security_inode_getattr(path);
if (retval)
return retval;
@@ -220,18 +259,13 @@ EXPORT_SYMBOL(vfs_getattr);
*/
int vfs_fstat(int fd, struct kstat *stat)
{
- struct fd f;
- int error;
-
- f = fdget_raw(fd);
- if (!fd_file(f))
+ CLASS(fd_raw, f)(fd);
+ if (fd_empty(f))
return -EBADF;
- error = vfs_getattr(&fd_file(f)->f_path, stat, STATX_BASIC_STATS, 0);
- fdput(f);
- return error;
+ return vfs_getattr(&fd_file(f)->f_path, stat, STATX_BASIC_STATS, 0);
}
-int getname_statx_lookup_flags(int flags)
+static int statx_lookup_flags(int flags)
{
int lookup_flags = 0;
@@ -239,8 +273,6 @@ int getname_statx_lookup_flags(int flags)
lookup_flags |= LOOKUP_FOLLOW;
if (!(flags & AT_NO_AUTOMOUNT))
lookup_flags |= LOOKUP_AUTOMOUNT;
- if (flags & AT_EMPTY_PATH)
- lookup_flags |= LOOKUP_EMPTY;
return lookup_flags;
}
@@ -277,7 +309,7 @@ static int vfs_statx_fd(int fd, int flags, struct kstat *stat,
u32 request_mask)
{
CLASS(fd_raw, f)(fd);
- if (!fd_file(f))
+ if (fd_empty(f))
return -EBADF;
return vfs_statx_path(&fd_file(f)->f_path, flags, stat, request_mask);
}
@@ -301,7 +333,7 @@ static int vfs_statx(int dfd, struct filename *filename, int flags,
struct kstat *stat, u32 request_mask)
{
struct path path;
- unsigned int lookup_flags = getname_statx_lookup_flags(flags);
+ unsigned int lookup_flags = statx_lookup_flags(flags);
int error;
if (flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT | AT_EMPTY_PATH |
@@ -326,18 +358,11 @@ int vfs_fstatat(int dfd, const char __user *filename,
{
int ret;
int statx_flags = flags | AT_NO_AUTOMOUNT;
- struct filename *name;
+ struct filename *name = getname_maybe_null(filename, flags);
- /*
- * Work around glibc turning fstat() into fstatat(AT_EMPTY_PATH)
- *
- * If AT_EMPTY_PATH is set, we expect the common case to be that
- * empty path, and avoid doing all the extra pathname work.
- */
- if (flags == AT_EMPTY_PATH && vfs_empty_path(dfd, filename))
+ if (!name && dfd >= 0)
return vfs_fstat(dfd, stat);
- name = getname_flags(filename, getname_statx_lookup_flags(statx_flags));
ret = vfs_statx(dfd, name, statx_flags, stat, STATX_BASIC_STATS);
putname(name);
@@ -774,24 +799,11 @@ SYSCALL_DEFINE5(statx,
struct statx __user *, buffer)
{
int ret;
- unsigned lflags;
- struct filename *name;
+ struct filename *name = getname_maybe_null(filename, flags);
- /*
- * Short-circuit handling of NULL and "" paths.
- *
- * For a NULL path we require and accept only the AT_EMPTY_PATH flag
- * (possibly |'d with AT_STATX flags).
- *
- * However, glibc on 32-bit architectures implements fstatat as statx
- * with the "" pathname and AT_NO_AUTOMOUNT | AT_EMPTY_PATH flags.
- * Supporting this results in the uglification below.
- */
- lflags = flags & ~(AT_NO_AUTOMOUNT | AT_STATX_SYNC_TYPE);
- if (lflags == AT_EMPTY_PATH && vfs_empty_path(dfd, filename))
+ if (!name && dfd >= 0)
return do_statx_fd(dfd, flags & ~AT_NO_AUTOMOUNT, mask, buffer);
- name = getname_flags(filename, getname_statx_lookup_flags(flags));
ret = do_statx(dfd, name, flags, mask, buffer);
putname(name);
diff --git a/fs/statfs.c b/fs/statfs.c
index 9c7bb27e7932..a45ac85e6048 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -114,13 +114,11 @@ retry:
int fd_statfs(int fd, struct kstatfs *st)
{
- struct fd f = fdget_raw(fd);
- int error = -EBADF;
- if (fd_file(f)) {
- error = vfs_statfs(&fd_file(f)->f_path, st);
- fdput(f);
- }
- return error;
+ CLASS(fd_raw, f)(fd);
+
+ if (fd_empty(f))
+ return -EBADF;
+ return vfs_statfs(&fd_file(f)->f_path, st);
}
static int do_statfs_native(struct kstatfs *st, struct statfs __user *p)
diff --git a/fs/sync.c b/fs/sync.c
index 67df255eb189..2955cd4c77a3 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -148,11 +148,11 @@ void emergency_sync(void)
*/
SYSCALL_DEFINE1(syncfs, int, fd)
{
- struct fd f = fdget(fd);
+ CLASS(fd, f)(fd);
struct super_block *sb;
int ret, ret2;
- if (!fd_file(f))
+ if (fd_empty(f))
return -EBADF;
sb = fd_file(f)->f_path.dentry->d_sb;
@@ -162,7 +162,6 @@ SYSCALL_DEFINE1(syncfs, int, fd)
ret2 = errseq_check_and_advance(&sb->s_wb_err, &fd_file(f)->f_sb_err);
- fdput(f);
return ret ? ret : ret2;
}
@@ -205,14 +204,12 @@ EXPORT_SYMBOL(vfs_fsync);
static int do_fsync(unsigned int fd, int datasync)
{
- struct fd f = fdget(fd);
- int ret = -EBADF;
+ CLASS(fd, f)(fd);
- if (fd_file(f)) {
- ret = vfs_fsync(fd_file(f), datasync);
- fdput(f);
- }
- return ret;
+ if (fd_empty(f))
+ return -EBADF;
+
+ return vfs_fsync(fd_file(f), datasync);
}
SYSCALL_DEFINE1(fsync, unsigned int, fd)
@@ -355,16 +352,12 @@ out:
int ksys_sync_file_range(int fd, loff_t offset, loff_t nbytes,
unsigned int flags)
{
- int ret;
- struct fd f;
+ CLASS(fd, f)(fd);
- ret = -EBADF;
- f = fdget(fd);
- if (fd_file(f))
- ret = sync_file_range(fd_file(f), offset, nbytes, flags);
+ if (fd_empty(f))
+ return -EBADF;
- fdput(f);
- return ret;
+ return sync_file_range(fd_file(f), offset, nbytes, flags);
}
SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes,
diff --git a/fs/timerfd.c b/fs/timerfd.c
index 137523e0bb21..4c32244b0508 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -394,19 +394,6 @@ static const struct file_operations timerfd_fops = {
.unlocked_ioctl = timerfd_ioctl,
};
-static int timerfd_fget(int fd, struct fd *p)
-{
- struct fd f = fdget(fd);
- if (!fd_file(f))
- return -EBADF;
- if (fd_file(f)->f_op != &timerfd_fops) {
- fdput(f);
- return -EINVAL;
- }
- *p = f;
- return 0;
-}
-
SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags)
{
int ufd;
@@ -471,7 +458,6 @@ static int do_timerfd_settime(int ufd, int flags,
const struct itimerspec64 *new,
struct itimerspec64 *old)
{
- struct fd f;
struct timerfd_ctx *ctx;
int ret;
@@ -479,15 +465,17 @@ static int do_timerfd_settime(int ufd, int flags,
!itimerspec64_valid(new))
return -EINVAL;
- ret = timerfd_fget(ufd, &f);
- if (ret)
- return ret;
+ CLASS(fd, f)(ufd);
+ if (fd_empty(f))
+ return -EBADF;
+
+ if (fd_file(f)->f_op != &timerfd_fops)
+ return -EINVAL;
+
ctx = fd_file(f)->private_data;
- if (isalarm(ctx) && !capable(CAP_WAKE_ALARM)) {
- fdput(f);
+ if (isalarm(ctx) && !capable(CAP_WAKE_ALARM))
return -EPERM;
- }
timerfd_setup_cancel(ctx, flags);
@@ -535,17 +523,18 @@ static int do_timerfd_settime(int ufd, int flags,
ret = timerfd_setup(ctx, flags, new);
spin_unlock_irq(&ctx->wqh.lock);
- fdput(f);
return ret;
}
static int do_timerfd_gettime(int ufd, struct itimerspec64 *t)
{
- struct fd f;
struct timerfd_ctx *ctx;
- int ret = timerfd_fget(ufd, &f);
- if (ret)
- return ret;
+ CLASS(fd, f)(ufd);
+
+ if (fd_empty(f))
+ return -EBADF;
+ if (fd_file(f)->f_op != &timerfd_fops)
+ return -EINVAL;
ctx = fd_file(f)->private_data;
spin_lock_irq(&ctx->wqh.lock);
@@ -567,7 +556,6 @@ static int do_timerfd_gettime(int ufd, struct itimerspec64 *t)
t->it_value = ktime_to_timespec64(timerfd_get_remaining(ctx));
t->it_interval = ktime_to_timespec64(ctx->tintv);
spin_unlock_irq(&ctx->wqh.lock);
- fdput(f);
return 0;
}
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 291583005dd1..3fb308b6e167 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -19,9 +19,9 @@
#include <linux/module.h>
#include <linux/ctype.h>
#include <linux/kthread.h>
-#include <linux/parser.h>
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
#include <linux/seq_file.h>
-#include <linux/mount.h>
#include <linux/math64.h>
#include <linux/writeback.h>
#include "ubifs.h"
@@ -981,177 +981,120 @@ enum {
Opt_auth_key,
Opt_auth_hash_name,
Opt_ignore,
- Opt_err,
};
-static const match_table_t tokens = {
- {Opt_fast_unmount, "fast_unmount"},
- {Opt_norm_unmount, "norm_unmount"},
- {Opt_bulk_read, "bulk_read"},
- {Opt_no_bulk_read, "no_bulk_read"},
- {Opt_chk_data_crc, "chk_data_crc"},
- {Opt_no_chk_data_crc, "no_chk_data_crc"},
- {Opt_override_compr, "compr=%s"},
- {Opt_auth_key, "auth_key=%s"},
- {Opt_auth_hash_name, "auth_hash_name=%s"},
- {Opt_ignore, "ubi=%s"},
- {Opt_ignore, "vol=%s"},
- {Opt_assert, "assert=%s"},
- {Opt_err, NULL},
+static const struct constant_table ubifs_param_compr[] = {
+ { "none", UBIFS_COMPR_NONE },
+ { "lzo", UBIFS_COMPR_LZO },
+ { "zlib", UBIFS_COMPR_ZLIB },
+ { "zstd", UBIFS_COMPR_ZSTD },
+ {}
};
-/**
- * parse_standard_option - parse a standard mount option.
- * @option: the option to parse
- *
- * Normally, standard mount options like "sync" are passed to file-systems as
- * flags. However, when a "rootflags=" kernel boot parameter is used, they may
- * be present in the options string. This function tries to deal with this
- * situation and parse standard options. Returns 0 if the option was not
- * recognized, and the corresponding integer flag if it was.
- *
- * UBIFS is only interested in the "sync" option, so do not check for anything
- * else.
- */
-static int parse_standard_option(const char *option)
-{
+static const struct constant_table ubifs_param_assert[] = {
+ { "report", ASSACT_REPORT },
+ { "read-only", ASSACT_RO },
+ { "panic", ASSACT_PANIC },
+ {}
+};
- pr_notice("UBIFS: parse %s\n", option);
- if (!strcmp(option, "sync"))
- return SB_SYNCHRONOUS;
- return 0;
-}
+static const struct fs_parameter_spec ubifs_fs_param_spec[] = {
+ fsparam_flag ("fast_unmount", Opt_fast_unmount),
+ fsparam_flag ("norm_unmount", Opt_norm_unmount),
+ fsparam_flag ("bulk_read", Opt_bulk_read),
+ fsparam_flag ("no_bulk_read", Opt_no_bulk_read),
+ fsparam_flag ("chk_data_crc", Opt_chk_data_crc),
+ fsparam_flag ("no_chk_data_crc", Opt_no_chk_data_crc),
+ fsparam_enum ("compr", Opt_override_compr, ubifs_param_compr),
+ fsparam_enum ("assert", Opt_assert, ubifs_param_assert),
+ fsparam_string ("auth_key", Opt_auth_key),
+ fsparam_string ("auth_hash_name", Opt_auth_hash_name),
+ fsparam_string ("ubi", Opt_ignore),
+ fsparam_string ("vol", Opt_ignore),
+ {}
+};
+
+struct ubifs_fs_context {
+ struct ubifs_mount_opts mount_opts;
+ char *auth_key_name;
+ char *auth_hash_name;
+ unsigned int no_chk_data_crc:1;
+ unsigned int bulk_read:1;
+ unsigned int default_compr:2;
+ unsigned int assert_action:2;
+};
/**
- * ubifs_parse_options - parse mount parameters.
- * @c: UBIFS file-system description object
- * @options: parameters to parse
- * @is_remount: non-zero if this is FS re-mount
+ * ubifs_parse_param - parse a parameter.
+ * @fc: the filesystem context
+ * @param: the parameter to parse
*
* This function parses UBIFS mount options and returns zero in case success
* and a negative error code in case of failure.
*/
-static int ubifs_parse_options(struct ubifs_info *c, char *options,
- int is_remount)
+static int ubifs_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
- char *p;
- substring_t args[MAX_OPT_ARGS];
-
- if (!options)
- return 0;
+ struct ubifs_fs_context *ctx = fc->fs_private;
+ struct fs_parse_result result;
+ bool is_remount = (fc->purpose & FS_CONTEXT_FOR_RECONFIGURE);
+ int opt;
- while ((p = strsep(&options, ","))) {
- int token;
+ opt = fs_parse(fc, ubifs_fs_param_spec, param, &result);
+ if (opt < 0)
+ return opt;
- if (!*p)
- continue;
-
- token = match_token(p, tokens, args);
- switch (token) {
+ switch (opt) {
/*
* %Opt_fast_unmount and %Opt_norm_unmount options are ignored.
* We accept them in order to be backward-compatible. But this
* should be removed at some point.
*/
- case Opt_fast_unmount:
- c->mount_opts.unmount_mode = 2;
- break;
- case Opt_norm_unmount:
- c->mount_opts.unmount_mode = 1;
- break;
- case Opt_bulk_read:
- c->mount_opts.bulk_read = 2;
- c->bulk_read = 1;
- break;
- case Opt_no_bulk_read:
- c->mount_opts.bulk_read = 1;
- c->bulk_read = 0;
- break;
- case Opt_chk_data_crc:
- c->mount_opts.chk_data_crc = 2;
- c->no_chk_data_crc = 0;
- break;
- case Opt_no_chk_data_crc:
- c->mount_opts.chk_data_crc = 1;
- c->no_chk_data_crc = 1;
- break;
- case Opt_override_compr:
- {
- char *name = match_strdup(&args[0]);
-
- if (!name)
- return -ENOMEM;
- if (!strcmp(name, "none"))
- c->mount_opts.compr_type = UBIFS_COMPR_NONE;
- else if (!strcmp(name, "lzo"))
- c->mount_opts.compr_type = UBIFS_COMPR_LZO;
- else if (!strcmp(name, "zlib"))
- c->mount_opts.compr_type = UBIFS_COMPR_ZLIB;
- else if (!strcmp(name, "zstd"))
- c->mount_opts.compr_type = UBIFS_COMPR_ZSTD;
- else {
- ubifs_err(c, "unknown compressor \"%s\"", name); //FIXME: is c ready?
- kfree(name);
- return -EINVAL;
- }
- kfree(name);
- c->mount_opts.override_compr = 1;
- c->default_compr = c->mount_opts.compr_type;
- break;
- }
- case Opt_assert:
- {
- char *act = match_strdup(&args[0]);
-
- if (!act)
- return -ENOMEM;
- if (!strcmp(act, "report"))
- c->assert_action = ASSACT_REPORT;
- else if (!strcmp(act, "read-only"))
- c->assert_action = ASSACT_RO;
- else if (!strcmp(act, "panic"))
- c->assert_action = ASSACT_PANIC;
- else {
- ubifs_err(c, "unknown assert action \"%s\"", act);
- kfree(act);
- return -EINVAL;
- }
- kfree(act);
- break;
- }
- case Opt_auth_key:
- if (!is_remount) {
- c->auth_key_name = kstrdup(args[0].from,
- GFP_KERNEL);
- if (!c->auth_key_name)
- return -ENOMEM;
- }
- break;
- case Opt_auth_hash_name:
- if (!is_remount) {
- c->auth_hash_name = kstrdup(args[0].from,
- GFP_KERNEL);
- if (!c->auth_hash_name)
- return -ENOMEM;
- }
- break;
- case Opt_ignore:
- break;
- default:
- {
- unsigned long flag;
- struct super_block *sb = c->vfs_sb;
-
- flag = parse_standard_option(p);
- if (!flag) {
- ubifs_err(c, "unrecognized mount option \"%s\" or missing value",
- p);
- return -EINVAL;
- }
- sb->s_flags |= flag;
- break;
+ case Opt_fast_unmount:
+ ctx->mount_opts.unmount_mode = 2;
+ break;
+ case Opt_norm_unmount:
+ ctx->mount_opts.unmount_mode = 1;
+ break;
+ case Opt_bulk_read:
+ ctx->mount_opts.bulk_read = 2;
+ ctx->bulk_read = 1;
+ break;
+ case Opt_no_bulk_read:
+ ctx->mount_opts.bulk_read = 1;
+ ctx->bulk_read = 0;
+ break;
+ case Opt_chk_data_crc:
+ ctx->mount_opts.chk_data_crc = 2;
+ ctx->no_chk_data_crc = 0;
+ break;
+ case Opt_no_chk_data_crc:
+ ctx->mount_opts.chk_data_crc = 1;
+ ctx->no_chk_data_crc = 1;
+ break;
+ case Opt_override_compr:
+ ctx->mount_opts.compr_type = result.uint_32;
+ ctx->mount_opts.override_compr = 1;
+ ctx->default_compr = ctx->mount_opts.compr_type;
+ break;
+ case Opt_assert:
+ ctx->assert_action = result.uint_32;
+ break;
+ case Opt_auth_key:
+ if (!is_remount) {
+ kfree(ctx->auth_key_name);
+ ctx->auth_key_name = param->string;
+ param->string = NULL;
}
+ break;
+ case Opt_auth_hash_name:
+ if (!is_remount) {
+ kfree(ctx->auth_hash_name);
+ ctx->auth_hash_name = param->string;
+ param->string = NULL;
}
+ break;
+ case Opt_ignore:
+ break;
}
return 0;
@@ -2003,21 +1946,27 @@ static void ubifs_put_super(struct super_block *sb)
mutex_unlock(&c->umount_mutex);
}
-static int ubifs_remount_fs(struct super_block *sb, int *flags, char *data)
+static int ubifs_reconfigure(struct fs_context *fc)
{
+ struct ubifs_fs_context *ctx = fc->fs_private;
+ struct super_block *sb = fc->root->d_sb;
int err;
struct ubifs_info *c = sb->s_fs_info;
sync_filesystem(sb);
- dbg_gen("old flags %#lx, new flags %#x", sb->s_flags, *flags);
+ dbg_gen("old flags %#lx, new flags %#x", sb->s_flags, fc->sb_flags);
- err = ubifs_parse_options(c, data, 1);
- if (err) {
- ubifs_err(c, "invalid or unknown remount parameter");
- return err;
- }
+ /*
+ * Apply the mount option changes.
+ * auth_key_name and auth_hash_name are ignored on remount.
+ */
+ c->mount_opts = ctx->mount_opts;
+ c->bulk_read = ctx->bulk_read;
+ c->no_chk_data_crc = ctx->no_chk_data_crc;
+ c->default_compr = ctx->default_compr;
+ c->assert_action = ctx->assert_action;
- if (c->ro_mount && !(*flags & SB_RDONLY)) {
+ if (c->ro_mount && !(fc->sb_flags & SB_RDONLY)) {
if (c->ro_error) {
ubifs_msg(c, "cannot re-mount R/W due to prior errors");
return -EROFS;
@@ -2029,7 +1978,7 @@ static int ubifs_remount_fs(struct super_block *sb, int *flags, char *data)
err = ubifs_remount_rw(c);
if (err)
return err;
- } else if (!c->ro_mount && (*flags & SB_RDONLY)) {
+ } else if (!c->ro_mount && (fc->sb_flags & SB_RDONLY)) {
if (c->ro_error) {
ubifs_msg(c, "cannot re-mount R/O due to prior errors");
return -EROFS;
@@ -2062,14 +2011,13 @@ const struct super_operations ubifs_super_operations = {
.evict_inode = ubifs_evict_inode,
.statfs = ubifs_statfs,
.dirty_inode = ubifs_dirty_inode,
- .remount_fs = ubifs_remount_fs,
.show_options = ubifs_show_options,
.sync_fs = ubifs_sync_fs,
};
/**
* open_ubi - parse UBI device name string and open the UBI device.
- * @name: UBI volume name
+ * @fc: The filesystem context
* @mode: UBI volume open mode
*
* The primary method of mounting UBIFS is by specifying the UBI volume
@@ -2086,15 +2034,13 @@ const struct super_operations ubifs_super_operations = {
* returns UBI volume description object in case of success and a negative
* error code in case of failure.
*/
-static struct ubi_volume_desc *open_ubi(const char *name, int mode)
+static struct ubi_volume_desc *open_ubi(struct fs_context *fc, int mode)
{
struct ubi_volume_desc *ubi;
+ const char *name = fc->source;
int dev, vol;
char *endptr;
- if (!name || !*name)
- return ERR_PTR(-EINVAL);
-
/* First, try to open using the device node path method */
ubi = ubi_open_volume_path(name, mode);
if (!IS_ERR(ubi))
@@ -2102,14 +2048,14 @@ static struct ubi_volume_desc *open_ubi(const char *name, int mode)
/* Try the "nodev" method */
if (name[0] != 'u' || name[1] != 'b' || name[2] != 'i')
- return ERR_PTR(-EINVAL);
+ goto invalid_source;
/* ubi:NAME method */
if ((name[3] == ':' || name[3] == '!') && name[4] != '\0')
return ubi_open_volume_nm(0, name + 4, mode);
if (!isdigit(name[3]))
- return ERR_PTR(-EINVAL);
+ goto invalid_source;
dev = simple_strtoul(name + 3, &endptr, 0);
@@ -2121,7 +2067,7 @@ static struct ubi_volume_desc *open_ubi(const char *name, int mode)
if (*endptr == '_' && isdigit(endptr[1])) {
vol = simple_strtoul(endptr + 1, &endptr, 0);
if (*endptr != '\0')
- return ERR_PTR(-EINVAL);
+ goto invalid_source;
return ubi_open_volume(dev, vol, mode);
}
@@ -2129,7 +2075,8 @@ static struct ubi_volume_desc *open_ubi(const char *name, int mode)
if ((*endptr == ':' || *endptr == '!') && endptr[1] != '\0')
return ubi_open_volume_nm(dev, ++endptr, mode);
- return ERR_PTR(-EINVAL);
+invalid_source:
+ return ERR_PTR(invalf(fc, "Invalid source name"));
}
static struct ubifs_info *alloc_ubifs_info(struct ubi_volume_desc *ubi)
@@ -2181,9 +2128,10 @@ static struct ubifs_info *alloc_ubifs_info(struct ubi_volume_desc *ubi)
return c;
}
-static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
+static int ubifs_fill_super(struct super_block *sb, struct fs_context *fc)
{
struct ubifs_info *c = sb->s_fs_info;
+ struct ubifs_fs_context *ctx = fc->fs_private;
struct inode *root;
int err;
@@ -2195,9 +2143,18 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
goto out;
}
- err = ubifs_parse_options(c, data, 0);
- if (err)
- goto out_close;
+ /* Copy in parsed mount options */
+ c->mount_opts = ctx->mount_opts;
+ c->auth_key_name = ctx->auth_key_name;
+ c->auth_hash_name = ctx->auth_hash_name;
+ c->no_chk_data_crc = ctx->no_chk_data_crc;
+ c->bulk_read = ctx->bulk_read;
+ c->default_compr = ctx->default_compr;
+ c->assert_action = ctx->assert_action;
+
+ /* ubifs_info owns auth strings now */
+ ctx->auth_key_name = NULL;
+ ctx->auth_hash_name = NULL;
/*
* UBIFS provides 'backing_dev_info' in order to disable read-ahead. For
@@ -2264,41 +2221,38 @@ out:
return err;
}
-static int sb_test(struct super_block *sb, void *data)
+static int sb_test(struct super_block *sb, struct fs_context *fc)
{
- struct ubifs_info *c1 = data;
+ struct ubifs_info *c1 = fc->s_fs_info;
struct ubifs_info *c = sb->s_fs_info;
return c->vi.cdev == c1->vi.cdev;
}
-static int sb_set(struct super_block *sb, void *data)
-{
- sb->s_fs_info = data;
- return set_anon_super(sb, NULL);
-}
-
-static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags,
- const char *name, void *data)
+static int ubifs_get_tree(struct fs_context *fc)
{
struct ubi_volume_desc *ubi;
struct ubifs_info *c;
struct super_block *sb;
int err;
- dbg_gen("name %s, flags %#x", name, flags);
+ if (!fc->source || !*fc->source)
+ return invalf(fc, "No source specified");
+
+ dbg_gen("name %s, flags %#x", fc->source, fc->sb_flags);
/*
* Get UBI device number and volume ID. Mount it read-only so far
* because this might be a new mount point, and UBI allows only one
* read-write user at a time.
*/
- ubi = open_ubi(name, UBI_READONLY);
+ ubi = open_ubi(fc, UBI_READONLY);
if (IS_ERR(ubi)) {
- if (!(flags & SB_SILENT))
+ err = PTR_ERR(ubi);
+ if (!(fc->sb_flags & SB_SILENT))
pr_err("UBIFS error (pid: %d): cannot open \"%s\", error %d",
- current->pid, name, (int)PTR_ERR(ubi));
- return ERR_CAST(ubi);
+ current->pid, fc->source, err);
+ return err;
}
c = alloc_ubifs_info(ubi);
@@ -2306,10 +2260,11 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags,
err = -ENOMEM;
goto out_close;
}
+ fc->s_fs_info = c;
dbg_gen("opened ubi%d_%d", c->vi.ubi_num, c->vi.vol_id);
- sb = sget(fs_type, sb_test, sb_set, flags, c);
+ sb = sget_fc(fc, sb_test, set_anon_super_fc);
if (IS_ERR(sb)) {
err = PTR_ERR(sb);
kfree(c);
@@ -2321,12 +2276,12 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags,
kfree(c);
/* A new mount point for already mounted UBIFS */
dbg_gen("this ubi volume is already mounted");
- if (!!(flags & SB_RDONLY) != c1->ro_mount) {
+ if (!!(fc->sb_flags & SB_RDONLY) != c1->ro_mount) {
err = -EBUSY;
goto out_deact;
}
} else {
- err = ubifs_fill_super(sb, data, flags & SB_SILENT ? 1 : 0);
+ err = ubifs_fill_super(sb, fc);
if (err)
goto out_deact;
/* We do not support atime */
@@ -2340,13 +2295,14 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags,
/* 'fill_super()' opens ubi again so we must close it here */
ubi_close_volume(ubi);
- return dget(sb->s_root);
+ fc->root = dget(sb->s_root);
+ return 0;
out_deact:
deactivate_locked_super(sb);
out_close:
ubi_close_volume(ubi);
- return ERR_PTR(err);
+ return err;
}
static void kill_ubifs_super(struct super_block *s)
@@ -2356,10 +2312,61 @@ static void kill_ubifs_super(struct super_block *s)
kfree(c);
}
+static void ubifs_free_fc(struct fs_context *fc)
+{
+ struct ubifs_fs_context *ctx = fc->fs_private;
+
+ if (ctx) {
+ kfree(ctx->auth_key_name);
+ kfree(ctx->auth_hash_name);
+ kfree(ctx);
+ }
+}
+
+static const struct fs_context_operations ubifs_context_ops = {
+ .free = ubifs_free_fc,
+ .parse_param = ubifs_parse_param,
+ .get_tree = ubifs_get_tree,
+ .reconfigure = ubifs_reconfigure,
+};
+
+static int ubifs_init_fs_context(struct fs_context *fc)
+{
+ struct ubifs_fs_context *ctx;
+
+ ctx = kzalloc(sizeof(struct ubifs_fs_context), GFP_KERNEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ if (fc->purpose != FS_CONTEXT_FOR_RECONFIGURE) {
+ /* Iniitialize for first mount */
+ ctx->no_chk_data_crc = 1;
+ ctx->assert_action = ASSACT_RO;
+ } else {
+ struct ubifs_info *c = fc->root->d_sb->s_fs_info;
+
+ /*
+ * Preserve existing options across remounts.
+ * auth_key_name and auth_hash_name are not remountable.
+ */
+ ctx->mount_opts = c->mount_opts;
+ ctx->bulk_read = c->bulk_read;
+ ctx->no_chk_data_crc = c->no_chk_data_crc;
+ ctx->default_compr = c->default_compr;
+ ctx->assert_action = c->assert_action;
+ }
+
+ fc->ops = &ubifs_context_ops;
+ fc->fs_private = ctx;
+
+ return 0;
+}
+
static struct file_system_type ubifs_fs_type = {
.name = "ubifs",
.owner = THIS_MODULE,
- .mount = ubifs_mount,
+ .init_fs_context = ubifs_init_fs_context,
+ .parameters = ubifs_fs_param_spec,
.kill_sb = kill_ubifs_super,
};
MODULE_ALIAS_FS("ubifs");
diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c
index 53c11be2b2c1..194ed3ab945e 100644
--- a/fs/ufs/balloc.c
+++ b/fs/ufs/balloc.c
@@ -33,6 +33,29 @@ static u64 ufs_bitmap_search (struct super_block *, struct ufs_cg_private_info *
static unsigned char ufs_fragtable_8fpb[], ufs_fragtable_other[];
static void ufs_clusteracct(struct super_block *, struct ufs_cg_private_info *, unsigned, int);
+static void adjust_free_blocks(struct super_block *sb,
+ struct ufs_cylinder_group *ucg,
+ struct ufs_cg_private_info *ucpi,
+ unsigned fragment, int delta)
+{
+ struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi;
+
+ if ((UFS_SB(sb)->s_flags & UFS_CG_MASK) == UFS_CG_44BSD)
+ ufs_clusteracct(sb, ucpi, fragment, delta);
+
+ fs32_add(sb, &ucg->cg_cs.cs_nbfree, delta);
+ uspi->cs_total.cs_nbfree += delta;
+ fs32_add(sb, &UFS_SB(sb)->fs_cs(ucpi->c_cgx).cs_nbfree, delta);
+
+ if (uspi->fs_magic != UFS2_MAGIC) {
+ unsigned cylno = ufs_cbtocylno(fragment);
+
+ fs16_add(sb, &ubh_cg_blks(ucpi, cylno,
+ ufs_cbtorpos(fragment)), delta);
+ fs32_add(sb, &ubh_cg_blktot(ucpi, cylno), delta);
+ }
+}
+
/*
* Free 'count' fragments from fragment number 'fragment'
*/
@@ -43,7 +66,6 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count)
struct ufs_cg_private_info * ucpi;
struct ufs_cylinder_group * ucg;
unsigned cgno, bit, end_bit, bbase, blkmap, i;
- u64 blkno;
sb = inode->i_sb;
uspi = UFS_SB(sb)->s_uspi;
@@ -51,7 +73,7 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count)
UFSD("ENTER, fragment %llu, count %u\n",
(unsigned long long)fragment, count);
- if (ufs_fragnum(fragment) + count > uspi->s_fpg)
+ if (ufs_fragnum(fragment) + count > uspi->s_fpb)
ufs_error (sb, "ufs_free_fragments", "internal error");
mutex_lock(&UFS_SB(sb)->s_lock);
@@ -94,23 +116,11 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count)
/*
* Trying to reassemble free fragments into block
*/
- blkno = ufs_fragstoblks (bbase);
- if (ubh_isblockset(UCPI_UBH(ucpi), ucpi->c_freeoff, blkno)) {
+ if (ubh_isblockset(uspi, ucpi, bbase)) {
fs32_sub(sb, &ucg->cg_cs.cs_nffree, uspi->s_fpb);
uspi->cs_total.cs_nffree -= uspi->s_fpb;
fs32_sub(sb, &UFS_SB(sb)->fs_cs(cgno).cs_nffree, uspi->s_fpb);
- if ((UFS_SB(sb)->s_flags & UFS_CG_MASK) == UFS_CG_44BSD)
- ufs_clusteracct (sb, ucpi, blkno, 1);
- fs32_add(sb, &ucg->cg_cs.cs_nbfree, 1);
- uspi->cs_total.cs_nbfree++;
- fs32_add(sb, &UFS_SB(sb)->fs_cs(cgno).cs_nbfree, 1);
- if (uspi->fs_magic != UFS2_MAGIC) {
- unsigned cylno = ufs_cbtocylno (bbase);
-
- fs16_add(sb, &ubh_cg_blks(ucpi, cylno,
- ufs_cbtorpos(bbase)), 1);
- fs32_add(sb, &ubh_cg_blktot(ucpi, cylno), 1);
- }
+ adjust_free_blocks(sb, ucg, ucpi, bbase, 1);
}
ubh_mark_buffer_dirty (USPI_UBH(uspi));
@@ -139,7 +149,6 @@ void ufs_free_blocks(struct inode *inode, u64 fragment, unsigned count)
struct ufs_cg_private_info * ucpi;
struct ufs_cylinder_group * ucg;
unsigned overflow, cgno, bit, end_bit, i;
- u64 blkno;
sb = inode->i_sb;
uspi = UFS_SB(sb)->s_uspi;
@@ -181,26 +190,12 @@ do_more:
}
for (i = bit; i < end_bit; i += uspi->s_fpb) {
- blkno = ufs_fragstoblks(i);
- if (ubh_isblockset(UCPI_UBH(ucpi), ucpi->c_freeoff, blkno)) {
+ if (ubh_isblockset(uspi, ucpi, i)) {
ufs_error(sb, "ufs_free_blocks", "freeing free fragment");
}
- ubh_setblock(UCPI_UBH(ucpi), ucpi->c_freeoff, blkno);
+ ubh_setblock(uspi, ucpi, i);
inode_sub_bytes(inode, uspi->s_fpb << uspi->s_fshift);
- if ((UFS_SB(sb)->s_flags & UFS_CG_MASK) == UFS_CG_44BSD)
- ufs_clusteracct (sb, ucpi, blkno, 1);
-
- fs32_add(sb, &ucg->cg_cs.cs_nbfree, 1);
- uspi->cs_total.cs_nbfree++;
- fs32_add(sb, &UFS_SB(sb)->fs_cs(cgno).cs_nbfree, 1);
-
- if (uspi->fs_magic != UFS2_MAGIC) {
- unsigned cylno = ufs_cbtocylno(i);
-
- fs16_add(sb, &ubh_cg_blks(ucpi, cylno,
- ufs_cbtorpos(i)), 1);
- fs32_add(sb, &ubh_cg_blktot(ucpi, cylno), 1);
- }
+ adjust_free_blocks(sb, ucg, ucpi, i, 1);
}
ubh_mark_buffer_dirty (USPI_UBH(uspi));
@@ -234,13 +229,13 @@ failed:
* situated at the end of file.
*
* We can come here from ufs_writepage or ufs_prepare_write,
- * locked_page is argument of these functions, so we already lock it.
+ * locked_folio is argument of these functions, so we already lock it.
*/
static void ufs_change_blocknr(struct inode *inode, sector_t beg,
unsigned int count, sector_t oldb,
- sector_t newb, struct page *locked_page)
+ sector_t newb, struct folio *locked_folio)
{
- struct folio *folio, *locked_folio = page_folio(locked_page);
+ struct folio *folio;
const unsigned blks_per_page =
1 << (PAGE_SHIFT - inode->i_blkbits);
const unsigned mask = blks_per_page - 1;
@@ -337,7 +332,7 @@ static void ufs_clear_frags(struct inode *inode, sector_t beg, unsigned int n,
u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
u64 goal, unsigned count, int *err,
- struct page *locked_page)
+ struct folio *locked_folio)
{
struct super_block * sb;
struct ufs_sb_private_info * uspi;
@@ -417,7 +412,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
result = ufs_alloc_fragments (inode, cgno, goal, count, err);
if (result) {
ufs_clear_frags(inode, result + oldcount,
- newcount - oldcount, locked_page != NULL);
+ newcount - oldcount, locked_folio != NULL);
*err = 0;
write_seqlock(&UFS_I(inode)->meta_lock);
ufs_cpu_to_data_ptr(sb, p, result);
@@ -441,7 +436,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
fragment + count);
read_sequnlock_excl(&UFS_I(inode)->meta_lock);
ufs_clear_frags(inode, result + oldcount, newcount - oldcount,
- locked_page != NULL);
+ locked_folio != NULL);
mutex_unlock(&UFS_SB(sb)->s_lock);
UFSD("EXIT, result %llu\n", (unsigned long long)result);
return result;
@@ -462,11 +457,11 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
result = ufs_alloc_fragments (inode, cgno, goal, request, err);
if (result) {
ufs_clear_frags(inode, result + oldcount, newcount - oldcount,
- locked_page != NULL);
+ locked_folio != NULL);
mutex_unlock(&UFS_SB(sb)->s_lock);
ufs_change_blocknr(inode, fragment - oldcount, oldcount,
uspi->s_sbbase + tmp,
- uspi->s_sbbase + result, locked_page);
+ uspi->s_sbbase + result, locked_folio);
*err = 0;
write_seqlock(&UFS_I(inode)->meta_lock);
ufs_cpu_to_data_ptr(sb, p, result);
@@ -698,7 +693,7 @@ static u64 ufs_alloccg_block(struct inode *inode,
struct super_block * sb;
struct ufs_sb_private_info * uspi;
struct ufs_cylinder_group * ucg;
- u64 result, blkno;
+ u64 result;
UFSD("ENTER, goal %llu\n", (unsigned long long)goal);
@@ -716,7 +711,7 @@ static u64 ufs_alloccg_block(struct inode *inode,
/*
* If the requested block is available, use it.
*/
- if (ubh_isblockset(UCPI_UBH(ucpi), ucpi->c_freeoff, ufs_fragstoblks(goal))) {
+ if (ubh_isblockset(uspi, ucpi, goal)) {
result = goal;
goto gotit;
}
@@ -729,22 +724,8 @@ norot:
gotit:
if (!try_add_frags(inode, uspi->s_fpb))
return 0;
- blkno = ufs_fragstoblks(result);
- ubh_clrblock (UCPI_UBH(ucpi), ucpi->c_freeoff, blkno);
- if ((UFS_SB(sb)->s_flags & UFS_CG_MASK) == UFS_CG_44BSD)
- ufs_clusteracct (sb, ucpi, blkno, -1);
-
- fs32_sub(sb, &ucg->cg_cs.cs_nbfree, 1);
- uspi->cs_total.cs_nbfree--;
- fs32_sub(sb, &UFS_SB(sb)->fs_cs(ucpi->c_cgx).cs_nbfree, 1);
-
- if (uspi->fs_magic != UFS2_MAGIC) {
- unsigned cylno = ufs_cbtocylno((unsigned)result);
-
- fs16_sub(sb, &ubh_cg_blks(ucpi, cylno,
- ufs_cbtorpos((unsigned)result)), 1);
- fs32_sub(sb, &ubh_cg_blktot(ucpi, cylno), 1);
- }
+ ubh_clrblock(uspi, ucpi, result);
+ adjust_free_blocks(sb, ucg, ucpi, result, -1);
UFSD("EXIT, result %llu\n", (unsigned long long)result);
@@ -863,12 +844,12 @@ static u64 ufs_bitmap_search(struct super_block *sb,
}
static void ufs_clusteracct(struct super_block * sb,
- struct ufs_cg_private_info * ucpi, unsigned blkno, int cnt)
+ struct ufs_cg_private_info * ucpi, unsigned frag, int cnt)
{
- struct ufs_sb_private_info * uspi;
+ struct ufs_sb_private_info * uspi = UFS_SB(sb)->s_uspi;
int i, start, end, forw, back;
+ unsigned blkno = ufs_fragstoblks(frag);
- uspi = UFS_SB(sb)->s_uspi;
if (uspi->s_contigsumsize <= 0)
return;
diff --git a/fs/ufs/cylinder.c b/fs/ufs/cylinder.c
index 1abe5454de47..a2813270c303 100644
--- a/fs/ufs/cylinder.c
+++ b/fs/ufs/cylinder.c
@@ -26,7 +26,7 @@
* Read cylinder group into cache. The memory space for ufs_cg_private_info
* structure is already allocated during ufs_read_super.
*/
-static void ufs_read_cylinder (struct super_block * sb,
+static bool ufs_read_cylinder(struct super_block *sb,
unsigned cgno, unsigned bitmap_nr)
{
struct ufs_sb_info * sbi = UFS_SB(sb);
@@ -46,9 +46,11 @@ static void ufs_read_cylinder (struct super_block * sb,
* We have already the first fragment of cylinder group block in buffer
*/
UCPI_UBH(ucpi)->bh[0] = sbi->s_ucg[cgno];
- for (i = 1; i < UCPI_UBH(ucpi)->count; i++)
- if (!(UCPI_UBH(ucpi)->bh[i] = sb_bread(sb, UCPI_UBH(ucpi)->fragment + i)))
+ for (i = 1; i < UCPI_UBH(ucpi)->count; i++) {
+ UCPI_UBH(ucpi)->bh[i] = sb_bread(sb, UCPI_UBH(ucpi)->fragment + i);
+ if (!UCPI_UBH(ucpi)->bh[i])
goto failed;
+ }
sbi->s_cgno[bitmap_nr] = cgno;
ucpi->c_cgx = fs32_to_cpu(sb, ucg->cg_cgx);
@@ -67,13 +69,14 @@ static void ufs_read_cylinder (struct super_block * sb,
ucpi->c_clusteroff = fs32_to_cpu(sb, ucg->cg_u.cg_44.cg_clusteroff);
ucpi->c_nclusterblks = fs32_to_cpu(sb, ucg->cg_u.cg_44.cg_nclusterblks);
UFSD("EXIT\n");
- return;
+ return true;
failed:
for (j = 1; j < i; j++)
- brelse (sbi->s_ucg[j]);
+ brelse(UCPI_UBH(ucpi)->bh[j]);
sbi->s_cgno[bitmap_nr] = UFS_CGNO_EMPTY;
ufs_error (sb, "ufs_read_cylinder", "can't read cylinder group block %u", cgno);
+ return false;
}
/*
@@ -156,15 +159,14 @@ struct ufs_cg_private_info * ufs_load_cylinder (
UFSD("EXIT (FAILED)\n");
return NULL;
}
- else {
- UFSD("EXIT\n");
- return sbi->s_ucpi[cgno];
- }
} else {
- ufs_read_cylinder (sb, cgno, cgno);
- UFSD("EXIT\n");
- return sbi->s_ucpi[cgno];
+ if (unlikely(!ufs_read_cylinder (sb, cgno, cgno))) {
+ UFSD("EXIT (FAILED)\n");
+ return NULL;
+ }
}
+ UFSD("EXIT\n");
+ return sbi->s_ucpi[cgno];
}
/*
* Cylinder group number cg is in cache but it was not last used,
@@ -195,7 +197,10 @@ struct ufs_cg_private_info * ufs_load_cylinder (
sbi->s_ucpi[j] = sbi->s_ucpi[j-1];
}
sbi->s_ucpi[0] = ucpi;
- ufs_read_cylinder (sb, cgno, 0);
+ if (unlikely(!ufs_read_cylinder (sb, cgno, 0))) {
+ UFSD("EXIT (FAILED)\n");
+ return NULL;
+ }
}
UFSD("EXIT\n");
return sbi->s_ucpi[0];
diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c
index d6e6a2198971..88d0062cfdb9 100644
--- a/fs/ufs/dir.c
+++ b/fs/ufs/dir.c
@@ -81,10 +81,9 @@ ino_t ufs_inode_by_name(struct inode *dir, const struct qstr *qstr)
}
-/* Releases the page */
-void ufs_set_link(struct inode *dir, struct ufs_dir_entry *de,
- struct folio *folio, struct inode *inode,
- bool update_times)
+int ufs_set_link(struct inode *dir, struct ufs_dir_entry *de,
+ struct folio *folio, struct inode *inode,
+ bool update_times)
{
loff_t pos = folio_pos(folio) + offset_in_folio(folio, de);
unsigned len = fs16_to_cpu(dir->i_sb, de->d_reclen);
@@ -92,17 +91,19 @@ void ufs_set_link(struct inode *dir, struct ufs_dir_entry *de,
folio_lock(folio);
err = ufs_prepare_chunk(folio, pos, len);
- BUG_ON(err);
+ if (unlikely(err)) {
+ folio_unlock(folio);
+ return err;
+ }
de->d_ino = cpu_to_fs32(dir->i_sb, inode->i_ino);
ufs_set_de_type(dir->i_sb, de, inode->i_mode);
ufs_commit_chunk(folio, pos, len);
- folio_release_kmap(folio, de);
if (update_times)
inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
mark_inode_dirty(dir);
- ufs_handle_dirsync(dir);
+ return ufs_handle_dirsync(dir);
}
static bool ufs_check_folio(struct folio *folio, char *kaddr)
@@ -505,8 +506,7 @@ int ufs_delete_entry(struct inode *inode, struct ufs_dir_entry *dir,
if (de->d_reclen == 0) {
ufs_error(inode->i_sb, __func__,
"zero-length directory entry");
- err = -EIO;
- goto out;
+ return -EIO;
}
pde = de;
de = ufs_next_entry(sb, de);
@@ -516,18 +516,17 @@ int ufs_delete_entry(struct inode *inode, struct ufs_dir_entry *dir,
pos = folio_pos(folio) + from;
folio_lock(folio);
err = ufs_prepare_chunk(folio, pos, to - from);
- BUG_ON(err);
+ if (unlikely(err)) {
+ folio_unlock(folio);
+ return err;
+ }
if (pde)
pde->d_reclen = cpu_to_fs16(sb, to - from);
dir->d_ino = 0;
ufs_commit_chunk(folio, pos, to - from);
inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
mark_inode_dirty(inode);
- err = ufs_handle_dirsync(inode);
-out:
- folio_release_kmap(folio, kaddr);
- UFSD("EXIT\n");
- return err;
+ return ufs_handle_dirsync(inode);
}
int ufs_make_empty(struct inode * inode, struct inode *dir)
diff --git a/fs/ufs/file.c b/fs/ufs/file.c
index 6558882a89ef..487ad1fc2de6 100644
--- a/fs/ufs/file.c
+++ b/fs/ufs/file.c
@@ -42,4 +42,5 @@ const struct file_operations ufs_file_operations = {
.open = generic_file_open,
.fsync = generic_file_fsync,
.splice_read = filemap_splice_read,
+ .splice_write = iter_file_splice_write,
};
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index 5331ae7ebf3e..7dc38fdef2ea 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -220,7 +220,7 @@ changed:
*/
static bool
ufs_extend_tail(struct inode *inode, u64 writes_to,
- int *err, struct page *locked_page)
+ int *err, struct folio *locked_folio)
{
struct ufs_inode_info *ufsi = UFS_I(inode);
struct super_block *sb = inode->i_sb;
@@ -239,7 +239,7 @@ ufs_extend_tail(struct inode *inode, u64 writes_to,
p = ufs_get_direct_data_ptr(uspi, ufsi, block);
tmp = ufs_new_fragments(inode, p, lastfrag, ufs_data_ptr_to_cpu(sb, p),
new_size - (lastfrag & uspi->s_fpbmask), err,
- locked_page);
+ locked_folio);
return tmp != 0;
}
@@ -250,12 +250,11 @@ ufs_extend_tail(struct inode *inode, u64 writes_to,
* @new_fragment: number of new allocated fragment(s)
* @err: we set it if something wrong
* @new: we set it if we allocate new block
- * @locked_page: for ufs_new_fragments()
+ * @locked_folio: for ufs_new_fragments()
*/
-static u64
-ufs_inode_getfrag(struct inode *inode, unsigned index,
+static u64 ufs_inode_getfrag(struct inode *inode, unsigned index,
sector_t new_fragment, int *err,
- int *new, struct page *locked_page)
+ int *new, struct folio *locked_folio)
{
struct ufs_inode_info *ufsi = UFS_I(inode);
struct super_block *sb = inode->i_sb;
@@ -264,11 +263,6 @@ ufs_inode_getfrag(struct inode *inode, unsigned index,
unsigned nfrags = uspi->s_fpb;
void *p;
- /* TODO : to be done for write support
- if ( (flags & UFS_TYPE_MASK) == UFS_TYPE_UFS2)
- goto ufs2;
- */
-
p = ufs_get_direct_data_ptr(uspi, ufsi, index);
tmp = ufs_data_ptr_to_cpu(sb, p);
if (tmp)
@@ -288,7 +282,7 @@ ufs_inode_getfrag(struct inode *inode, unsigned index,
goal += uspi->s_fpb;
}
tmp = ufs_new_fragments(inode, p, ufs_blknum(new_fragment),
- goal, nfrags, err, locked_page);
+ goal, nfrags, err, locked_folio);
if (!tmp) {
*err = -ENOSPC;
@@ -303,21 +297,6 @@ ufs_inode_getfrag(struct inode *inode, unsigned index,
mark_inode_dirty(inode);
out:
return tmp + uspi->s_sbbase;
-
- /* This part : To be implemented ....
- Required only for writing, not required for READ-ONLY.
-ufs2:
-
- u2_block = ufs_fragstoblks(fragment);
- u2_blockoff = ufs_fragnum(fragment);
- p = ufsi->i_u1.u2_i_data + block;
- goal = 0;
-
-repeat2:
- tmp = fs32_to_cpu(sb, *p);
- lastfrag = ufsi->i_lastfrag;
-
- */
}
/**
@@ -329,12 +308,11 @@ repeat2:
* (block will hold this fragment and also uspi->s_fpb-1)
* @err: see ufs_inode_getfrag()
* @new: see ufs_inode_getfrag()
- * @locked_page: see ufs_inode_getfrag()
+ * @locked_folio: see ufs_inode_getfrag()
*/
-static u64
-ufs_inode_getblock(struct inode *inode, u64 ind_block,
- unsigned index, sector_t new_fragment, int *err,
- int *new, struct page *locked_page)
+static u64 ufs_inode_getblock(struct inode *inode, u64 ind_block,
+ unsigned index, sector_t new_fragment, int *err,
+ int *new, struct folio *locked_folio)
{
struct super_block *sb = inode->i_sb;
struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi;
@@ -369,7 +347,7 @@ ufs_inode_getblock(struct inode *inode, u64 ind_block,
else
goal = bh->b_blocknr + uspi->s_fpb;
tmp = ufs_new_fragments(inode, p, ufs_blknum(new_fragment), goal,
- uspi->s_fpb, err, locked_page);
+ uspi->s_fpb, err, locked_folio);
if (!tmp)
goto out;
@@ -434,14 +412,14 @@ static int ufs_getfrag_block(struct inode *inode, sector_t fragment, struct buff
unsigned tailfrags = lastfrag & uspi->s_fpbmask;
if (tailfrags && fragment >= lastfrag) {
if (!ufs_extend_tail(inode, fragment,
- &err, bh_result->b_page))
+ &err, bh_result->b_folio))
goto out;
}
}
if (depth == 1) {
phys64 = ufs_inode_getfrag(inode, offsets[0], fragment,
- &err, &new, bh_result->b_page);
+ &err, &new, bh_result->b_folio);
} else {
int i;
phys64 = ufs_inode_getfrag(inode, offsets[0], fragment,
@@ -450,7 +428,7 @@ static int ufs_getfrag_block(struct inode *inode, sector_t fragment, struct buff
phys64 = ufs_inode_getblock(inode, phys64, offsets[i],
fragment, &err, NULL, NULL);
phys64 = ufs_inode_getblock(inode, phys64, offsets[depth - 1],
- fragment, &err, &new, bh_result->b_page);
+ fragment, &err, &new, bh_result->b_folio);
}
out:
if (phys64) {
@@ -898,91 +876,84 @@ static inline void free_data(struct to_free *ctx, u64 from, unsigned count)
#define DIRECT_FRAGMENT ((inode->i_size + uspi->s_fsize - 1) >> uspi->s_fshift)
+/*
+ * used only for truncation down to direct blocks.
+ */
static void ufs_trunc_direct(struct inode *inode)
{
struct ufs_inode_info *ufsi = UFS_I(inode);
- struct super_block * sb;
- struct ufs_sb_private_info * uspi;
- void *p;
- u64 frag1, frag2, frag3, frag4, block1, block2;
+ struct super_block *sb = inode->i_sb;
+ struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi;
+ unsigned int new_frags, old_frags;
+ unsigned int old_slot, new_slot;
+ unsigned int old_tail, new_tail;
struct to_free ctx = {.inode = inode};
- unsigned i, tmp;
UFSD("ENTER: ino %lu\n", inode->i_ino);
- sb = inode->i_sb;
- uspi = UFS_SB(sb)->s_uspi;
-
- frag1 = DIRECT_FRAGMENT;
- frag4 = min_t(u64, UFS_NDIR_FRAGMENT, ufsi->i_lastfrag);
- frag2 = ((frag1 & uspi->s_fpbmask) ? ((frag1 | uspi->s_fpbmask) + 1) : frag1);
- frag3 = frag4 & ~uspi->s_fpbmask;
- block1 = block2 = 0;
- if (frag2 > frag3) {
- frag2 = frag4;
- frag3 = frag4 = 0;
- } else if (frag2 < frag3) {
- block1 = ufs_fragstoblks (frag2);
- block2 = ufs_fragstoblks (frag3);
- }
-
- UFSD("ino %lu, frag1 %llu, frag2 %llu, block1 %llu, block2 %llu,"
- " frag3 %llu, frag4 %llu\n", inode->i_ino,
- (unsigned long long)frag1, (unsigned long long)frag2,
- (unsigned long long)block1, (unsigned long long)block2,
- (unsigned long long)frag3, (unsigned long long)frag4);
-
- if (frag1 >= frag2)
- goto next1;
+ new_frags = DIRECT_FRAGMENT;
+ // new_frags = first fragment past the new EOF
+ old_frags = min_t(u64, UFS_NDIR_FRAGMENT, ufsi->i_lastfrag);
+ // old_frags = first fragment past the old EOF or covered by indirects
- /*
- * Free first free fragments
- */
- p = ufs_get_direct_data_ptr(uspi, ufsi, ufs_fragstoblks(frag1));
- tmp = ufs_data_ptr_to_cpu(sb, p);
- if (!tmp )
- ufs_panic (sb, "ufs_trunc_direct", "internal error");
- frag2 -= frag1;
- frag1 = ufs_fragnum (frag1);
+ if (new_frags >= old_frags) // expanding - nothing to free
+ goto done;
- ufs_free_fragments(inode, tmp + frag1, frag2);
+ old_tail = ufs_fragnum(old_frags);
+ old_slot = ufs_fragstoblks(old_frags);
+ new_tail = ufs_fragnum(new_frags);
+ new_slot = ufs_fragstoblks(new_frags);
-next1:
- /*
- * Free whole blocks
- */
- for (i = block1 ; i < block2; i++) {
- p = ufs_get_direct_data_ptr(uspi, ufsi, i);
- tmp = ufs_data_ptr_to_cpu(sb, p);
+ if (old_slot == new_slot) { // old_tail > 0
+ void *p = ufs_get_direct_data_ptr(uspi, ufsi, old_slot);
+ u64 tmp = ufs_data_ptr_to_cpu(sb, p);
if (!tmp)
- continue;
- write_seqlock(&ufsi->meta_lock);
- ufs_data_ptr_clear(uspi, p);
- write_sequnlock(&ufsi->meta_lock);
+ ufs_panic(sb, __func__, "internal error");
+ if (!new_tail) {
+ write_seqlock(&ufsi->meta_lock);
+ ufs_data_ptr_clear(uspi, p);
+ write_sequnlock(&ufsi->meta_lock);
+ }
+ ufs_free_fragments(inode, tmp + new_tail, old_tail - new_tail);
+ } else {
+ unsigned int slot = new_slot;
- free_data(&ctx, tmp, uspi->s_fpb);
- }
+ if (new_tail) {
+ void *p = ufs_get_direct_data_ptr(uspi, ufsi, slot++);
+ u64 tmp = ufs_data_ptr_to_cpu(sb, p);
+ if (!tmp)
+ ufs_panic(sb, __func__, "internal error");
- free_data(&ctx, 0, 0);
+ ufs_free_fragments(inode, tmp + new_tail,
+ uspi->s_fpb - new_tail);
+ }
+ while (slot < old_slot) {
+ void *p = ufs_get_direct_data_ptr(uspi, ufsi, slot++);
+ u64 tmp = ufs_data_ptr_to_cpu(sb, p);
+ if (!tmp)
+ continue;
+ write_seqlock(&ufsi->meta_lock);
+ ufs_data_ptr_clear(uspi, p);
+ write_sequnlock(&ufsi->meta_lock);
- if (frag3 >= frag4)
- goto next3;
+ free_data(&ctx, tmp, uspi->s_fpb);
+ }
- /*
- * Free last free fragments
- */
- p = ufs_get_direct_data_ptr(uspi, ufsi, ufs_fragstoblks(frag3));
- tmp = ufs_data_ptr_to_cpu(sb, p);
- if (!tmp )
- ufs_panic(sb, "ufs_truncate_direct", "internal error");
- frag4 = ufs_fragnum (frag4);
- write_seqlock(&ufsi->meta_lock);
- ufs_data_ptr_clear(uspi, p);
- write_sequnlock(&ufsi->meta_lock);
+ free_data(&ctx, 0, 0);
- ufs_free_fragments (inode, tmp, frag4);
- next3:
+ if (old_tail) {
+ void *p = ufs_get_direct_data_ptr(uspi, ufsi, slot);
+ u64 tmp = ufs_data_ptr_to_cpu(sb, p);
+ if (!tmp)
+ ufs_panic(sb, __func__, "internal error");
+ write_seqlock(&ufsi->meta_lock);
+ ufs_data_ptr_clear(uspi, p);
+ write_sequnlock(&ufsi->meta_lock);
+ ufs_free_fragments(inode, tmp, old_tail);
+ }
+ }
+done:
UFSD("EXIT: ino %lu\n", inode->i_ino);
}
diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c
index c8390976ab6a..38a024c8cccd 100644
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -210,20 +210,18 @@ static int ufs_unlink(struct inode *dir, struct dentry *dentry)
struct inode * inode = d_inode(dentry);
struct ufs_dir_entry *de;
struct folio *folio;
- int err = -ENOENT;
+ int err;
de = ufs_find_entry(dir, &dentry->d_name, &folio);
if (!de)
- goto out;
+ return -ENOENT;
err = ufs_delete_entry(dir, de, folio);
- if (err)
- goto out;
-
- inode_set_ctime_to_ts(inode, inode_get_ctime(dir));
- inode_dec_link_count(inode);
- err = 0;
-out:
+ if (!err) {
+ inode_set_ctime_to_ts(inode, inode_get_ctime(dir));
+ inode_dec_link_count(inode);
+ }
+ folio_release_kmap(folio, de);
return err;
}
@@ -253,14 +251,14 @@ static int ufs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
struct ufs_dir_entry * dir_de = NULL;
struct folio *old_folio;
struct ufs_dir_entry *old_de;
- int err = -ENOENT;
+ int err;
if (flags & ~RENAME_NOREPLACE)
return -EINVAL;
old_de = ufs_find_entry(old_dir, &old_dentry->d_name, &old_folio);
if (!old_de)
- goto out;
+ return -ENOENT;
if (S_ISDIR(old_inode->i_mode)) {
err = -EIO;
@@ -281,7 +279,10 @@ static int ufs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
new_de = ufs_find_entry(new_dir, &new_dentry->d_name, &new_folio);
if (!new_de)
goto out_dir;
- ufs_set_link(new_dir, new_de, new_folio, old_inode, 1);
+ err = ufs_set_link(new_dir, new_de, new_folio, old_inode, 1);
+ folio_release_kmap(new_folio, new_de);
+ if (err)
+ goto out_dir;
inode_set_ctime_current(new_inode);
if (dir_de)
drop_nlink(new_inode);
@@ -299,26 +300,20 @@ static int ufs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
* rename.
*/
inode_set_ctime_current(old_inode);
-
- ufs_delete_entry(old_dir, old_de, old_folio);
mark_inode_dirty(old_inode);
- if (dir_de) {
+ err = ufs_delete_entry(old_dir, old_de, old_folio);
+ if (!err && dir_de) {
if (old_dir != new_dir)
- ufs_set_link(old_inode, dir_de, dir_folio, new_dir, 0);
- else
- folio_release_kmap(dir_folio, dir_de);
+ err = ufs_set_link(old_inode, dir_de, dir_folio,
+ new_dir, 0);
inode_dec_link_count(old_dir);
}
- return 0;
-
-
out_dir:
if (dir_de)
folio_release_kmap(dir_folio, dir_de);
out_old:
folio_release_kmap(old_folio, old_de);
-out:
return err;
}
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index bc625788589c..762699c1bcf6 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -505,7 +505,6 @@ static int ufs_read_cylinder_structures(struct super_block *sb)
{
struct ufs_sb_info *sbi = UFS_SB(sb);
struct ufs_sb_private_info *uspi = sbi->s_uspi;
- struct ufs_buffer_head * ubh;
unsigned char * base, * space;
unsigned size, blks, i;
@@ -521,21 +520,13 @@ static int ufs_read_cylinder_structures(struct super_block *sb)
if (!base)
goto failed;
sbi->s_csp = (struct ufs_csum *)space;
- for (i = 0; i < blks; i += uspi->s_fpb) {
- size = uspi->s_bsize;
- if (i + uspi->s_fpb > blks)
- size = (blks - i) * uspi->s_fsize;
-
- ubh = ubh_bread(sb, uspi->s_csaddr + i, size);
-
- if (!ubh)
+ for (i = 0; i < blks; i++) {
+ struct buffer_head *bh = sb_bread(sb, uspi->s_csaddr + i);
+ if (!bh)
goto failed;
-
- ubh_ubhcpymem (space, ubh, size);
-
- space += size;
- ubh_brelse (ubh);
- ubh = NULL;
+ memcpy(space, bh->b_data, uspi->s_fsize);
+ space += uspi->s_fsize;
+ brelse (bh);
}
/*
@@ -645,7 +636,6 @@ static void ufs_put_super_internal(struct super_block *sb)
{
struct ufs_sb_info *sbi = UFS_SB(sb);
struct ufs_sb_private_info *uspi = sbi->s_uspi;
- struct ufs_buffer_head * ubh;
unsigned char * base, * space;
unsigned blks, size, i;
@@ -656,18 +646,17 @@ static void ufs_put_super_internal(struct super_block *sb)
size = uspi->s_cssize;
blks = (size + uspi->s_fsize - 1) >> uspi->s_fshift;
base = space = (char*) sbi->s_csp;
- for (i = 0; i < blks; i += uspi->s_fpb) {
- size = uspi->s_bsize;
- if (i + uspi->s_fpb > blks)
- size = (blks - i) * uspi->s_fsize;
-
- ubh = ubh_bread(sb, uspi->s_csaddr + i, size);
-
- ubh_memcpyubh (ubh, space, size);
- space += size;
- ubh_mark_buffer_uptodate (ubh, 1);
- ubh_mark_buffer_dirty (ubh);
- ubh_brelse (ubh);
+ for (i = 0; i < blks; i++, space += uspi->s_fsize) {
+ struct buffer_head *bh = sb_bread(sb, uspi->s_csaddr + i);
+
+ if (unlikely(!bh)) { // better than an oops...
+ ufs_panic(sb, __func__,
+ "can't write part of cylinder group summary");
+ continue;
+ }
+ memcpy(bh->b_data, space, uspi->s_fsize);
+ mark_buffer_dirty(bh);
+ brelse(bh);
}
for (i = 0; i < sbi->s_cg_loaded; i++) {
ufs_put_cylinder (sb, i);
@@ -1240,11 +1229,7 @@ magic_found:
else
uspi->s_apbshift = uspi->s_bshift - 2;
- uspi->s_2apbshift = uspi->s_apbshift * 2;
- uspi->s_3apbshift = uspi->s_apbshift * 3;
uspi->s_apb = 1 << uspi->s_apbshift;
- uspi->s_2apb = 1 << uspi->s_2apbshift;
- uspi->s_3apb = 1 << uspi->s_3apbshift;
uspi->s_apbmask = uspi->s_apb - 1;
uspi->s_nspfshift = uspi->s_fshift - UFS_SECTOR_BITS;
uspi->s_nspb = uspi->s_nspf << uspi->s_fpbshift;
diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h
index a2c762cb65a0..e7df65dd4351 100644
--- a/fs/ufs/ufs.h
+++ b/fs/ufs/ufs.h
@@ -88,10 +88,10 @@ struct ufs_inode_info {
#endif
/* balloc.c */
-extern void ufs_free_fragments (struct inode *, u64, unsigned);
-extern void ufs_free_blocks (struct inode *, u64, unsigned);
-extern u64 ufs_new_fragments(struct inode *, void *, u64, u64,
- unsigned, int *, struct page *);
+void ufs_free_fragments (struct inode *, u64 fragment, unsigned count);
+void ufs_free_blocks (struct inode *, u64 fragment, unsigned count);
+u64 ufs_new_fragments(struct inode *, void *, u64 fragment, u64 goal,
+ unsigned count, int *err, struct folio *);
/* cylinder.c */
extern struct ufs_cg_private_info * ufs_load_cylinder (struct super_block *, unsigned);
@@ -108,8 +108,8 @@ struct ufs_dir_entry *ufs_find_entry(struct inode *, const struct qstr *,
int ufs_delete_entry(struct inode *, struct ufs_dir_entry *, struct folio *);
int ufs_empty_dir(struct inode *);
struct ufs_dir_entry *ufs_dotdot(struct inode *, struct folio **);
-void ufs_set_link(struct inode *dir, struct ufs_dir_entry *de,
- struct folio *folio, struct inode *inode, bool update_times);
+int ufs_set_link(struct inode *dir, struct ufs_dir_entry *de,
+ struct folio *folio, struct inode *inode, bool update_times);
/* file.c */
extern const struct inode_operations ufs_file_inode_operations;
diff --git a/fs/ufs/ufs_fs.h b/fs/ufs/ufs_fs.h
index ef9ead44776a..0905f9a16b91 100644
--- a/fs/ufs/ufs_fs.h
+++ b/fs/ufs/ufs_fs.h
@@ -775,12 +775,8 @@ struct ufs_sb_private_info {
__u32 s_fpbmask; /* fragments per block mask */
__u32 s_apb; /* address per block */
- __u32 s_2apb; /* address per block^2 */
- __u32 s_3apb; /* address per block^3 */
__u32 s_apbmask; /* address per block mask */
__u32 s_apbshift; /* address per block shift */
- __u32 s_2apbshift; /* address per block shift * 2 */
- __u32 s_3apbshift; /* address per block shift * 3 */
__u32 s_nspfshift; /* number of sector per fragment shift */
__u32 s_nspb; /* number of sector per block */
__u32 s_inopf; /* inodes per fragment */
diff --git a/fs/ufs/util.c b/fs/ufs/util.c
index 2acf191eb89e..f0e906ab4ddd 100644
--- a/fs/ufs/util.c
+++ b/fs/ufs/util.c
@@ -99,20 +99,6 @@ void ubh_mark_buffer_dirty (struct ufs_buffer_head * ubh)
mark_buffer_dirty (ubh->bh[i]);
}
-void ubh_mark_buffer_uptodate (struct ufs_buffer_head * ubh, int flag)
-{
- unsigned i;
- if (!ubh)
- return;
- if (flag) {
- for ( i = 0; i < ubh->count; i++ )
- set_buffer_uptodate (ubh->bh[i]);
- } else {
- for ( i = 0; i < ubh->count; i++ )
- clear_buffer_uptodate (ubh->bh[i]);
- }
-}
-
void ubh_sync_block(struct ufs_buffer_head *ubh)
{
if (ubh) {
@@ -146,38 +132,6 @@ int ubh_buffer_dirty (struct ufs_buffer_head * ubh)
return result;
}
-void _ubh_ubhcpymem_(struct ufs_sb_private_info * uspi,
- unsigned char * mem, struct ufs_buffer_head * ubh, unsigned size)
-{
- unsigned len, bhno;
- if (size > (ubh->count << uspi->s_fshift))
- size = ubh->count << uspi->s_fshift;
- bhno = 0;
- while (size) {
- len = min_t(unsigned int, size, uspi->s_fsize);
- memcpy (mem, ubh->bh[bhno]->b_data, len);
- mem += uspi->s_fsize;
- size -= len;
- bhno++;
- }
-}
-
-void _ubh_memcpyubh_(struct ufs_sb_private_info * uspi,
- struct ufs_buffer_head * ubh, unsigned char * mem, unsigned size)
-{
- unsigned len, bhno;
- if (size > (ubh->count << uspi->s_fshift))
- size = ubh->count << uspi->s_fshift;
- bhno = 0;
- while (size) {
- len = min_t(unsigned int, size, uspi->s_fsize);
- memcpy (ubh->bh[bhno]->b_data, mem, len);
- mem += uspi->s_fsize;
- size -= len;
- bhno++;
- }
-}
-
dev_t
ufs_get_inode_dev(struct super_block *sb, struct ufs_inode_info *ufsi)
{
diff --git a/fs/ufs/util.h b/fs/ufs/util.h
index bf708b68f150..391bb4f11d74 100644
--- a/fs/ufs/util.h
+++ b/fs/ufs/util.h
@@ -263,14 +263,9 @@ extern struct ufs_buffer_head * ubh_bread_uspi(struct ufs_sb_private_info *, str
extern void ubh_brelse (struct ufs_buffer_head *);
extern void ubh_brelse_uspi (struct ufs_sb_private_info *);
extern void ubh_mark_buffer_dirty (struct ufs_buffer_head *);
-extern void ubh_mark_buffer_uptodate (struct ufs_buffer_head *, int);
extern void ubh_sync_block(struct ufs_buffer_head *);
extern void ubh_bforget (struct ufs_buffer_head *);
extern int ubh_buffer_dirty (struct ufs_buffer_head *);
-#define ubh_ubhcpymem(mem,ubh,size) _ubh_ubhcpymem_(uspi,mem,ubh,size)
-extern void _ubh_ubhcpymem_(struct ufs_sb_private_info *, unsigned char *, struct ufs_buffer_head *, unsigned);
-#define ubh_memcpyubh(ubh,mem,size) _ubh_memcpyubh_(uspi,ubh,mem,size)
-extern void _ubh_memcpyubh_(struct ufs_sb_private_info *, struct ufs_buffer_head *, unsigned char *, unsigned);
/* This functions works with cache pages*/
struct folio *ufs_get_locked_folio(struct address_space *mapping, pgoff_t index);
@@ -455,65 +450,69 @@ static inline unsigned _ubh_find_last_zero_bit_(
return (base << uspi->s_bpfshift) + pos - begin;
}
-#define ubh_isblockclear(ubh,begin,block) (!_ubh_isblockset_(uspi,ubh,begin,block))
-
-#define ubh_isblockset(ubh,begin,block) _ubh_isblockset_(uspi,ubh,begin,block)
-static inline int _ubh_isblockset_(struct ufs_sb_private_info * uspi,
- struct ufs_buffer_head * ubh, unsigned begin, unsigned block)
+static inline int ubh_isblockset(struct ufs_sb_private_info *uspi,
+ struct ufs_cg_private_info *ucpi, unsigned int frag)
{
+ struct ufs_buffer_head *ubh = UCPI_UBH(ucpi);
+ u8 *p = ubh_get_addr(ubh, ucpi->c_freeoff + (frag >> 3));
u8 mask;
+
switch (uspi->s_fpb) {
case 8:
- return (*ubh_get_addr (ubh, begin + block) == 0xff);
+ return *p == 0xff;
case 4:
- mask = 0x0f << ((block & 0x01) << 2);
- return (*ubh_get_addr (ubh, begin + (block >> 1)) & mask) == mask;
+ mask = 0x0f << (frag & 4);
+ return (*p & mask) == mask;
case 2:
- mask = 0x03 << ((block & 0x03) << 1);
- return (*ubh_get_addr (ubh, begin + (block >> 2)) & mask) == mask;
+ mask = 0x03 << (frag & 6);
+ return (*p & mask) == mask;
case 1:
- mask = 0x01 << (block & 0x07);
- return (*ubh_get_addr (ubh, begin + (block >> 3)) & mask) == mask;
+ mask = 0x01 << (frag & 7);
+ return (*p & mask) == mask;
}
return 0;
}
-#define ubh_clrblock(ubh,begin,block) _ubh_clrblock_(uspi,ubh,begin,block)
-static inline void _ubh_clrblock_(struct ufs_sb_private_info * uspi,
- struct ufs_buffer_head * ubh, unsigned begin, unsigned block)
+static inline void ubh_clrblock(struct ufs_sb_private_info *uspi,
+ struct ufs_cg_private_info *ucpi, unsigned int frag)
{
+ struct ufs_buffer_head *ubh = UCPI_UBH(ucpi);
+ u8 *p = ubh_get_addr(ubh, ucpi->c_freeoff + (frag >> 3));
+
switch (uspi->s_fpb) {
case 8:
- *ubh_get_addr (ubh, begin + block) = 0x00;
+ *p = 0x00;
return;
case 4:
- *ubh_get_addr (ubh, begin + (block >> 1)) &= ~(0x0f << ((block & 0x01) << 2));
+ *p &= ~(0x0f << (frag & 4));
return;
case 2:
- *ubh_get_addr (ubh, begin + (block >> 2)) &= ~(0x03 << ((block & 0x03) << 1));
+ *p &= ~(0x03 << (frag & 6));
return;
case 1:
- *ubh_get_addr (ubh, begin + (block >> 3)) &= ~(0x01 << ((block & 0x07)));
+ *p &= ~(0x01 << (frag & 7));
return;
}
}
-#define ubh_setblock(ubh,begin,block) _ubh_setblock_(uspi,ubh,begin,block)
-static inline void _ubh_setblock_(struct ufs_sb_private_info * uspi,
- struct ufs_buffer_head * ubh, unsigned begin, unsigned block)
+static inline void ubh_setblock(struct ufs_sb_private_info * uspi,
+ struct ufs_cg_private_info *ucpi, unsigned int frag)
{
+ struct ufs_buffer_head *ubh = UCPI_UBH(ucpi);
+ u8 *p = ubh_get_addr(ubh, ucpi->c_freeoff + (frag >> 3));
+
switch (uspi->s_fpb) {
case 8:
- *ubh_get_addr(ubh, begin + block) = 0xff;
+ *p = 0xff;
return;
case 4:
- *ubh_get_addr(ubh, begin + (block >> 1)) |= (0x0f << ((block & 0x01) << 2));
+ *p |= 0x0f << (frag & 4);
return;
case 2:
- *ubh_get_addr(ubh, begin + (block >> 2)) |= (0x03 << ((block & 0x03) << 1));
+ *p |= 0x03 << (frag & 6);
return;
case 1:
- *ubh_get_addr(ubh, begin + (block >> 3)) |= (0x01 << ((block & 0x07)));
+ *p |= 0x01 << (frag & 7);
return;
}
}
diff --git a/fs/unicode/utf8-core.c b/fs/unicode/utf8-core.c
index 8395066341a4..7f7cb14e01ce 100644
--- a/fs/unicode/utf8-core.c
+++ b/fs/unicode/utf8-core.c
@@ -214,3 +214,29 @@ void utf8_unload(struct unicode_map *um)
}
EXPORT_SYMBOL(utf8_unload);
+/**
+ * utf8_parse_version - Parse a UTF-8 version number from a string
+ *
+ * @version: input string
+ *
+ * Returns the parsed version on success, negative code on error
+ */
+int utf8_parse_version(char *version)
+{
+ substring_t args[3];
+ unsigned int maj, min, rev;
+ static const struct match_token token[] = {
+ {1, "%d.%d.%d"},
+ {0, NULL}
+ };
+
+ if (match_token(version, token, args) != 1)
+ return -EINVAL;
+
+ if (match_int(&args[0], &maj) || match_int(&args[1], &min) ||
+ match_int(&args[2], &rev))
+ return -EINVAL;
+
+ return UNICODE_AGE(maj, min, rev);
+}
+EXPORT_SYMBOL(utf8_parse_version);
diff --git a/fs/unicode/utf8-selftest.c b/fs/unicode/utf8-selftest.c
index 600e15efe9ed..5ddaf27b21a6 100644
--- a/fs/unicode/utf8-selftest.c
+++ b/fs/unicode/utf8-selftest.c
@@ -17,9 +17,6 @@
static unsigned int failed_tests;
static unsigned int total_tests;
-/* Tests will be based on this version. */
-#define UTF8_LATEST UNICODE_AGE(12, 1, 0)
-
#define _test(cond, func, line, fmt, ...) do { \
total_tests++; \
if (!cond) { \
diff --git a/fs/utimes.c b/fs/utimes.c
index 99b26f792b89..c7c7958e57b2 100644
--- a/fs/utimes.c
+++ b/fs/utimes.c
@@ -108,18 +108,13 @@ retry:
static int do_utimes_fd(int fd, struct timespec64 *times, int flags)
{
- struct fd f;
- int error;
-
if (flags)
return -EINVAL;
- f = fdget(fd);
- if (!fd_file(f))
+ CLASS(fd, f)(fd);
+ if (fd_empty(f))
return -EBADF;
- error = vfs_utimes(&fd_file(f)->f_path, times);
- fdput(f);
- return error;
+ return vfs_utimes(&fd_file(f)->f_path, times);
}
/*
diff --git a/fs/xattr.c b/fs/xattr.c
index 05ec7e7d9e87..02bee149ad96 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -586,25 +586,32 @@ retry_deleg:
}
EXPORT_SYMBOL_GPL(vfs_removexattr);
+int import_xattr_name(struct xattr_name *kname, const char __user *name)
+{
+ int error = strncpy_from_user(kname->name, name,
+ sizeof(kname->name));
+ if (error == 0 || error == sizeof(kname->name))
+ return -ERANGE;
+ if (error < 0)
+ return error;
+ return 0;
+}
+
/*
* Extended attribute SET operations
*/
-int setxattr_copy(const char __user *name, struct xattr_ctx *ctx)
+int setxattr_copy(const char __user *name, struct kernel_xattr_ctx *ctx)
{
int error;
if (ctx->flags & ~(XATTR_CREATE|XATTR_REPLACE))
return -EINVAL;
- error = strncpy_from_user(ctx->kname->name, name,
- sizeof(ctx->kname->name));
- if (error == 0 || error == sizeof(ctx->kname->name))
- return -ERANGE;
- if (error < 0)
+ error = import_xattr_name(ctx->kname, name);
+ if (error)
return error;
- error = 0;
if (ctx->size) {
if (ctx->size > XATTR_SIZE_MAX)
return -E2BIG;
@@ -619,8 +626,8 @@ int setxattr_copy(const char __user *name, struct xattr_ctx *ctx)
return error;
}
-int do_setxattr(struct mnt_idmap *idmap, struct dentry *dentry,
- struct xattr_ctx *ctx)
+static int do_setxattr(struct mnt_idmap *idmap, struct dentry *dentry,
+ struct kernel_xattr_ctx *ctx)
{
if (is_posix_acl_xattr(ctx->kname->name))
return do_set_acl(idmap, dentry, ctx->kname->name,
@@ -630,32 +637,32 @@ int do_setxattr(struct mnt_idmap *idmap, struct dentry *dentry,
ctx->kvalue, ctx->size, ctx->flags);
}
-static int path_setxattr(const char __user *pathname,
- const char __user *name, const void __user *value,
- size_t size, int flags, unsigned int lookup_flags)
+int file_setxattr(struct file *f, struct kernel_xattr_ctx *ctx)
+{
+ int error = mnt_want_write_file(f);
+
+ if (!error) {
+ audit_file(f);
+ error = do_setxattr(file_mnt_idmap(f), f->f_path.dentry, ctx);
+ mnt_drop_write_file(f);
+ }
+ return error;
+}
+
+/* unconditionally consumes filename */
+int filename_setxattr(int dfd, struct filename *filename,
+ unsigned int lookup_flags, struct kernel_xattr_ctx *ctx)
{
- struct xattr_name kname;
- struct xattr_ctx ctx = {
- .cvalue = value,
- .kvalue = NULL,
- .size = size,
- .kname = &kname,
- .flags = flags,
- };
struct path path;
int error;
- error = setxattr_copy(name, &ctx);
- if (error)
- return error;
-
retry:
- error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
+ error = filename_lookup(dfd, filename, lookup_flags, &path, NULL);
if (error)
goto out;
error = mnt_want_write(path.mnt);
if (!error) {
- error = do_setxattr(mnt_idmap(path.mnt), path.dentry, &ctx);
+ error = do_setxattr(mnt_idmap(path.mnt), path.dentry, ctx);
mnt_drop_write(path.mnt);
}
path_put(&path);
@@ -665,80 +672,121 @@ retry:
}
out:
+ putname(filename);
+ return error;
+}
+
+static int path_setxattrat(int dfd, const char __user *pathname,
+ unsigned int at_flags, const char __user *name,
+ const void __user *value, size_t size, int flags)
+{
+ struct xattr_name kname;
+ struct kernel_xattr_ctx ctx = {
+ .cvalue = value,
+ .kvalue = NULL,
+ .size = size,
+ .kname = &kname,
+ .flags = flags,
+ };
+ struct filename *filename;
+ unsigned int lookup_flags = 0;
+ int error;
+
+ if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
+ return -EINVAL;
+
+ if (!(at_flags & AT_SYMLINK_NOFOLLOW))
+ lookup_flags = LOOKUP_FOLLOW;
+
+ error = setxattr_copy(name, &ctx);
+ if (error)
+ return error;
+
+ filename = getname_maybe_null(pathname, at_flags);
+ if (!filename) {
+ CLASS(fd, f)(dfd);
+ if (fd_empty(f))
+ error = -EBADF;
+ else
+ error = file_setxattr(fd_file(f), &ctx);
+ } else {
+ error = filename_setxattr(dfd, filename, lookup_flags, &ctx);
+ }
kvfree(ctx.kvalue);
return error;
}
+SYSCALL_DEFINE6(setxattrat, int, dfd, const char __user *, pathname, unsigned int, at_flags,
+ const char __user *, name, const struct xattr_args __user *, uargs,
+ size_t, usize)
+{
+ struct xattr_args args = {};
+ int error;
+
+ BUILD_BUG_ON(sizeof(struct xattr_args) < XATTR_ARGS_SIZE_VER0);
+ BUILD_BUG_ON(sizeof(struct xattr_args) != XATTR_ARGS_SIZE_LATEST);
+
+ if (unlikely(usize < XATTR_ARGS_SIZE_VER0))
+ return -EINVAL;
+ if (usize > PAGE_SIZE)
+ return -E2BIG;
+
+ error = copy_struct_from_user(&args, sizeof(args), uargs, usize);
+ if (error)
+ return error;
+
+ return path_setxattrat(dfd, pathname, at_flags, name,
+ u64_to_user_ptr(args.value), args.size,
+ args.flags);
+}
+
SYSCALL_DEFINE5(setxattr, const char __user *, pathname,
const char __user *, name, const void __user *, value,
size_t, size, int, flags)
{
- return path_setxattr(pathname, name, value, size, flags, LOOKUP_FOLLOW);
+ return path_setxattrat(AT_FDCWD, pathname, 0, name, value, size, flags);
}
SYSCALL_DEFINE5(lsetxattr, const char __user *, pathname,
const char __user *, name, const void __user *, value,
size_t, size, int, flags)
{
- return path_setxattr(pathname, name, value, size, flags, 0);
+ return path_setxattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, name,
+ value, size, flags);
}
SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name,
const void __user *,value, size_t, size, int, flags)
{
- struct xattr_name kname;
- struct xattr_ctx ctx = {
- .cvalue = value,
- .kvalue = NULL,
- .size = size,
- .kname = &kname,
- .flags = flags,
- };
- int error;
-
- CLASS(fd, f)(fd);
- if (!fd_file(f))
- return -EBADF;
-
- audit_file(fd_file(f));
- error = setxattr_copy(name, &ctx);
- if (error)
- return error;
-
- error = mnt_want_write_file(fd_file(f));
- if (!error) {
- error = do_setxattr(file_mnt_idmap(fd_file(f)),
- fd_file(f)->f_path.dentry, &ctx);
- mnt_drop_write_file(fd_file(f));
- }
- kvfree(ctx.kvalue);
- return error;
+ return path_setxattrat(fd, NULL, AT_EMPTY_PATH, name,
+ value, size, flags);
}
/*
* Extended attribute GET operations
*/
-ssize_t
+static ssize_t
do_getxattr(struct mnt_idmap *idmap, struct dentry *d,
- struct xattr_ctx *ctx)
+ struct kernel_xattr_ctx *ctx)
{
ssize_t error;
char *kname = ctx->kname->name;
+ void *kvalue = NULL;
if (ctx->size) {
if (ctx->size > XATTR_SIZE_MAX)
ctx->size = XATTR_SIZE_MAX;
- ctx->kvalue = kvzalloc(ctx->size, GFP_KERNEL);
- if (!ctx->kvalue)
+ kvalue = kvzalloc(ctx->size, GFP_KERNEL);
+ if (!kvalue)
return -ENOMEM;
}
- if (is_posix_acl_xattr(ctx->kname->name))
- error = do_get_acl(idmap, d, kname, ctx->kvalue, ctx->size);
+ if (is_posix_acl_xattr(kname))
+ error = do_get_acl(idmap, d, kname, kvalue, ctx->size);
else
- error = vfs_getxattr(idmap, d, kname, ctx->kvalue, ctx->size);
+ error = vfs_getxattr(idmap, d, kname, kvalue, ctx->size);
if (error > 0) {
- if (ctx->size && copy_to_user(ctx->value, ctx->kvalue, error))
+ if (ctx->size && copy_to_user(ctx->value, kvalue, error))
error = -EFAULT;
} else if (error == -ERANGE && ctx->size >= XATTR_SIZE_MAX) {
/* The file system tried to returned a value bigger
@@ -746,79 +794,114 @@ do_getxattr(struct mnt_idmap *idmap, struct dentry *d,
error = -E2BIG;
}
+ kvfree(kvalue);
return error;
}
-static ssize_t
-getxattr(struct mnt_idmap *idmap, struct dentry *d,
- const char __user *name, void __user *value, size_t size)
+ssize_t file_getxattr(struct file *f, struct kernel_xattr_ctx *ctx)
{
+ audit_file(f);
+ return do_getxattr(file_mnt_idmap(f), f->f_path.dentry, ctx);
+}
+
+/* unconditionally consumes filename */
+ssize_t filename_getxattr(int dfd, struct filename *filename,
+ unsigned int lookup_flags, struct kernel_xattr_ctx *ctx)
+{
+ struct path path;
ssize_t error;
+retry:
+ error = filename_lookup(dfd, filename, lookup_flags, &path, NULL);
+ if (error)
+ goto out;
+ error = do_getxattr(mnt_idmap(path.mnt), path.dentry, ctx);
+ path_put(&path);
+ if (retry_estale(error, lookup_flags)) {
+ lookup_flags |= LOOKUP_REVAL;
+ goto retry;
+ }
+out:
+ putname(filename);
+ return error;
+}
+
+static ssize_t path_getxattrat(int dfd, const char __user *pathname,
+ unsigned int at_flags, const char __user *name,
+ void __user *value, size_t size)
+{
struct xattr_name kname;
- struct xattr_ctx ctx = {
+ struct kernel_xattr_ctx ctx = {
.value = value,
- .kvalue = NULL,
.size = size,
.kname = &kname,
.flags = 0,
};
+ struct filename *filename;
+ ssize_t error;
- error = strncpy_from_user(kname.name, name, sizeof(kname.name));
- if (error == 0 || error == sizeof(kname.name))
- error = -ERANGE;
- if (error < 0)
- return error;
+ if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
+ return -EINVAL;
- error = do_getxattr(idmap, d, &ctx);
+ error = import_xattr_name(&kname, name);
+ if (error)
+ return error;
- kvfree(ctx.kvalue);
- return error;
+ filename = getname_maybe_null(pathname, at_flags);
+ if (!filename) {
+ CLASS(fd, f)(dfd);
+ if (fd_empty(f))
+ return -EBADF;
+ return file_getxattr(fd_file(f), &ctx);
+ } else {
+ int lookup_flags = 0;
+ if (!(at_flags & AT_SYMLINK_NOFOLLOW))
+ lookup_flags = LOOKUP_FOLLOW;
+ return filename_getxattr(dfd, filename, lookup_flags, &ctx);
+ }
}
-static ssize_t path_getxattr(const char __user *pathname,
- const char __user *name, void __user *value,
- size_t size, unsigned int lookup_flags)
+SYSCALL_DEFINE6(getxattrat, int, dfd, const char __user *, pathname, unsigned int, at_flags,
+ const char __user *, name, struct xattr_args __user *, uargs, size_t, usize)
{
- struct path path;
- ssize_t error;
-retry:
- error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
+ struct xattr_args args = {};
+ int error;
+
+ BUILD_BUG_ON(sizeof(struct xattr_args) < XATTR_ARGS_SIZE_VER0);
+ BUILD_BUG_ON(sizeof(struct xattr_args) != XATTR_ARGS_SIZE_LATEST);
+
+ if (unlikely(usize < XATTR_ARGS_SIZE_VER0))
+ return -EINVAL;
+ if (usize > PAGE_SIZE)
+ return -E2BIG;
+
+ error = copy_struct_from_user(&args, sizeof(args), uargs, usize);
if (error)
return error;
- error = getxattr(mnt_idmap(path.mnt), path.dentry, name, value, size);
- path_put(&path);
- if (retry_estale(error, lookup_flags)) {
- lookup_flags |= LOOKUP_REVAL;
- goto retry;
- }
- return error;
+
+ if (args.flags != 0)
+ return -EINVAL;
+
+ return path_getxattrat(dfd, pathname, at_flags, name,
+ u64_to_user_ptr(args.value), args.size);
}
SYSCALL_DEFINE4(getxattr, const char __user *, pathname,
const char __user *, name, void __user *, value, size_t, size)
{
- return path_getxattr(pathname, name, value, size, LOOKUP_FOLLOW);
+ return path_getxattrat(AT_FDCWD, pathname, 0, name, value, size);
}
SYSCALL_DEFINE4(lgetxattr, const char __user *, pathname,
const char __user *, name, void __user *, value, size_t, size)
{
- return path_getxattr(pathname, name, value, size, 0);
+ return path_getxattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, name,
+ value, size);
}
SYSCALL_DEFINE4(fgetxattr, int, fd, const char __user *, name,
void __user *, value, size_t, size)
{
- struct fd f = fdget(fd);
- ssize_t error = -EBADF;
-
- if (!fd_file(f))
- return error;
- audit_file(fd_file(f));
- error = getxattr(file_mnt_idmap(fd_file(f)), fd_file(f)->f_path.dentry,
- name, value, size);
- fdput(f);
- return error;
+ return path_getxattrat(fd, NULL, AT_EMPTY_PATH, name, value, size);
}
/*
@@ -853,47 +936,80 @@ listxattr(struct dentry *d, char __user *list, size_t size)
return error;
}
-static ssize_t path_listxattr(const char __user *pathname, char __user *list,
- size_t size, unsigned int lookup_flags)
+static
+ssize_t file_listxattr(struct file *f, char __user *list, size_t size)
+{
+ audit_file(f);
+ return listxattr(f->f_path.dentry, list, size);
+}
+
+/* unconditionally consumes filename */
+static
+ssize_t filename_listxattr(int dfd, struct filename *filename,
+ unsigned int lookup_flags,
+ char __user *list, size_t size)
{
struct path path;
ssize_t error;
retry:
- error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
+ error = filename_lookup(dfd, filename, lookup_flags, &path, NULL);
if (error)
- return error;
+ goto out;
error = listxattr(path.dentry, list, size);
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
+out:
+ putname(filename);
return error;
}
+static ssize_t path_listxattrat(int dfd, const char __user *pathname,
+ unsigned int at_flags, char __user *list,
+ size_t size)
+{
+ struct filename *filename;
+ int lookup_flags;
+
+ if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
+ return -EINVAL;
+
+ filename = getname_maybe_null(pathname, at_flags);
+ if (!filename) {
+ CLASS(fd, f)(dfd);
+ if (fd_empty(f))
+ return -EBADF;
+ return file_listxattr(fd_file(f), list, size);
+ }
+
+ lookup_flags = (at_flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
+ return filename_listxattr(dfd, filename, lookup_flags, list, size);
+}
+
+SYSCALL_DEFINE5(listxattrat, int, dfd, const char __user *, pathname,
+ unsigned int, at_flags,
+ char __user *, list, size_t, size)
+{
+ return path_listxattrat(dfd, pathname, at_flags, list, size);
+}
+
SYSCALL_DEFINE3(listxattr, const char __user *, pathname, char __user *, list,
size_t, size)
{
- return path_listxattr(pathname, list, size, LOOKUP_FOLLOW);
+ return path_listxattrat(AT_FDCWD, pathname, 0, list, size);
}
SYSCALL_DEFINE3(llistxattr, const char __user *, pathname, char __user *, list,
size_t, size)
{
- return path_listxattr(pathname, list, size, 0);
+ return path_listxattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, list, size);
}
SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size)
{
- struct fd f = fdget(fd);
- ssize_t error = -EBADF;
-
- if (!fd_file(f))
- return error;
- audit_file(fd_file(f));
- error = listxattr(fd_file(f)->f_path.dentry, list, size);
- fdput(f);
- return error;
+ return path_listxattrat(fd, NULL, AT_EMPTY_PATH, list, size);
}
/*
@@ -907,25 +1023,33 @@ removexattr(struct mnt_idmap *idmap, struct dentry *d, const char *name)
return vfs_removexattr(idmap, d, name);
}
-static int path_removexattr(const char __user *pathname,
- const char __user *name, unsigned int lookup_flags)
+static int file_removexattr(struct file *f, struct xattr_name *kname)
+{
+ int error = mnt_want_write_file(f);
+
+ if (!error) {
+ audit_file(f);
+ error = removexattr(file_mnt_idmap(f),
+ f->f_path.dentry, kname->name);
+ mnt_drop_write_file(f);
+ }
+ return error;
+}
+
+/* unconditionally consumes filename */
+static int filename_removexattr(int dfd, struct filename *filename,
+ unsigned int lookup_flags, struct xattr_name *kname)
{
struct path path;
int error;
- char kname[XATTR_NAME_MAX + 1];
- error = strncpy_from_user(kname, name, sizeof(kname));
- if (error == 0 || error == sizeof(kname))
- error = -ERANGE;
- if (error < 0)
- return error;
retry:
- error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
+ error = filename_lookup(dfd, filename, lookup_flags, &path, NULL);
if (error)
- return error;
+ goto out;
error = mnt_want_write(path.mnt);
if (!error) {
- error = removexattr(mnt_idmap(path.mnt), path.dentry, kname);
+ error = removexattr(mnt_idmap(path.mnt), path.dentry, kname->name);
mnt_drop_write(path.mnt);
}
path_put(&path);
@@ -933,45 +1057,58 @@ retry:
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
+out:
+ putname(filename);
return error;
}
+static int path_removexattrat(int dfd, const char __user *pathname,
+ unsigned int at_flags, const char __user *name)
+{
+ struct xattr_name kname;
+ struct filename *filename;
+ unsigned int lookup_flags;
+ int error;
+
+ if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
+ return -EINVAL;
+
+ error = import_xattr_name(&kname, name);
+ if (error)
+ return error;
+
+ filename = getname_maybe_null(pathname, at_flags);
+ if (!filename) {
+ CLASS(fd, f)(dfd);
+ if (fd_empty(f))
+ return -EBADF;
+ return file_removexattr(fd_file(f), &kname);
+ }
+ lookup_flags = (at_flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
+ return filename_removexattr(dfd, filename, lookup_flags, &kname);
+}
+
+SYSCALL_DEFINE4(removexattrat, int, dfd, const char __user *, pathname,
+ unsigned int, at_flags, const char __user *, name)
+{
+ return path_removexattrat(dfd, pathname, at_flags, name);
+}
+
SYSCALL_DEFINE2(removexattr, const char __user *, pathname,
const char __user *, name)
{
- return path_removexattr(pathname, name, LOOKUP_FOLLOW);
+ return path_removexattrat(AT_FDCWD, pathname, 0, name);
}
SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname,
const char __user *, name)
{
- return path_removexattr(pathname, name, 0);
+ return path_removexattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, name);
}
SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name)
{
- struct fd f = fdget(fd);
- char kname[XATTR_NAME_MAX + 1];
- int error = -EBADF;
-
- if (!fd_file(f))
- return error;
- audit_file(fd_file(f));
-
- error = strncpy_from_user(kname, name, sizeof(kname));
- if (error == 0 || error == sizeof(kname))
- error = -ERANGE;
- if (error < 0)
- return error;
-
- error = mnt_want_write_file(fd_file(f));
- if (!error) {
- error = removexattr(file_mnt_idmap(fd_file(f)),
- fd_file(f)->f_path.dentry, kname);
- mnt_drop_write_file(fd_file(f));
- }
- fdput(f);
- return error;
+ return path_removexattrat(fd, NULL, AT_EMPTY_PATH, name);
}
int xattr_list_one(char **buffer, ssize_t *remaining_size, const char *name)
@@ -1005,9 +1142,10 @@ generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
{
const struct xattr_handler *handler, * const *handlers = dentry->d_sb->s_xattr;
ssize_t remaining_size = buffer_size;
- int err = 0;
for_each_xattr_handler(handlers, handler) {
+ int err;
+
if (!handler->name || (handler->list && !handler->list(dentry)))
continue;
err = xattr_list_one(&buffer, &remaining_size, handler->name);
@@ -1015,7 +1153,7 @@ generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
return err;
}
- return err ? err : buffer_size - remaining_size;
+ return buffer_size - remaining_size;
}
EXPORT_SYMBOL(generic_listxattr);
diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c
index 3c40f37e82c7..c962ad64b0c1 100644
--- a/fs/xfs/libxfs/xfs_trans_inode.c
+++ b/fs/xfs/libxfs/xfs_trans_inode.c
@@ -62,12 +62,12 @@ xfs_trans_ichgtime(
ASSERT(tp);
xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
- tv = current_time(inode);
+ /* If the mtime changes, then ctime must also change */
+ ASSERT(flags & XFS_ICHGTIME_CHG);
+ tv = inode_set_ctime_current(inode);
if (flags & XFS_ICHGTIME_MOD)
inode_set_mtime_to_ts(inode, tv);
- if (flags & XFS_ICHGTIME_CHG)
- inode_set_ctime_to_ts(inode, tv);
if (flags & XFS_ICHGTIME_ACCESS)
inode_set_atime_to_ts(inode, tv);
if (flags & XFS_ICHGTIME_CREATE)
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index aa4dbda7b536..e8196f5778e2 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -2115,6 +2115,13 @@ xfs_alloc_buftarg(
btp->bt_daxdev = fs_dax_get_by_bdev(btp->bt_bdev, &btp->bt_dax_part_off,
mp, ops);
+ if (bdev_can_atomic_write(btp->bt_bdev)) {
+ btp->bt_bdev_awu_min = bdev_atomic_write_unit_min_bytes(
+ btp->bt_bdev);
+ btp->bt_bdev_awu_max = bdev_atomic_write_unit_max_bytes(
+ btp->bt_bdev);
+ }
+
/*
* When allocating the buftargs we have not yet read the super block and
* thus don't know the file system sector size yet.
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 209a389f2abc..3d56bc7a35cc 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -124,6 +124,10 @@ struct xfs_buftarg {
struct percpu_counter bt_io_count;
struct ratelimit_state bt_ioerror_rl;
+ /* Atomic write unit values */
+ unsigned int bt_bdev_awu_min;
+ unsigned int bt_bdev_awu_max;
+
/* built-in cache, if we're not using the perag one */
struct xfs_buf_cache bt_cache[];
};
diff --git a/fs/xfs/xfs_exchrange.c b/fs/xfs/xfs_exchrange.c
index 75cb53f090d1..fa29c8b334d2 100644
--- a/fs/xfs/xfs_exchrange.c
+++ b/fs/xfs/xfs_exchrange.c
@@ -813,8 +813,6 @@ xfs_ioc_exchange_range(
.file2 = file,
};
struct xfs_exchange_range args;
- struct fd file1;
- int error;
if (copy_from_user(&args, argp, sizeof(args)))
return -EFAULT;
@@ -828,14 +826,12 @@ xfs_ioc_exchange_range(
fxr.length = args.length;
fxr.flags = args.flags;
- file1 = fdget(args.file1_fd);
- if (!fd_file(file1))
+ CLASS(fd, file1)(args.file1_fd);
+ if (fd_empty(file1))
return -EBADF;
fxr.file1 = fd_file(file1);
- error = xfs_exchange_range(&fxr);
- fdput(file1);
- return error;
+ return xfs_exchange_range(&fxr);
}
/* Opaque freshness blob for XFS_IOC_COMMIT_RANGE */
@@ -909,8 +905,6 @@ xfs_ioc_commit_range(
struct xfs_commit_range_fresh *kern_f;
struct xfs_inode *ip2 = XFS_I(file_inode(file));
struct xfs_mount *mp = ip2->i_mount;
- struct fd file1;
- int error;
kern_f = (struct xfs_commit_range_fresh *)&args.file2_freshness;
@@ -934,12 +928,10 @@ xfs_ioc_commit_range(
fxr.file2_ctime.tv_sec = kern_f->file2_ctime;
fxr.file2_ctime.tv_nsec = kern_f->file2_ctime_nsec;
- file1 = fdget(args.file1_fd);
+ CLASS(fd, file1)(args.file1_fd);
if (fd_empty(file1))
return -EBADF;
fxr.file1 = fd_file(file1);
- error = xfs_exchange_range(&fxr);
- fdput(file1);
- return error;
+ return xfs_exchange_range(&fxr);
}
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index b19916b11fd5..ca47cae5a40a 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -852,6 +852,20 @@ xfs_file_write_iter(
if (IS_DAX(inode))
return xfs_file_dax_write(iocb, from);
+ if (iocb->ki_flags & IOCB_ATOMIC) {
+ /*
+ * Currently only atomic writing of a single FS block is
+ * supported. It would be possible to atomic write smaller than
+ * a FS block, but there is no requirement to support this.
+ * Note that iomap also does not support this yet.
+ */
+ if (ocount != ip->i_mount->m_sb.sb_blocksize)
+ return -EINVAL;
+ ret = generic_atomic_write_valid(iocb, from);
+ if (ret)
+ return ret;
+ }
+
if (iocb->ki_flags & IOCB_DIRECT) {
/*
* Allow a directio write to fall back to a buffered
@@ -1239,6 +1253,8 @@ xfs_file_open(
if (xfs_is_shutdown(XFS_M(inode->i_sb)))
return -EIO;
file->f_mode |= FMODE_NOWAIT | FMODE_CAN_ODIRECT;
+ if (xfs_inode_can_atomicwrite(XFS_I(inode)))
+ file->f_mode |= FMODE_CAN_ATOMIC_WRITE;
return generic_file_open(inode, file);
}
diff --git a/fs/xfs/xfs_handle.c b/fs/xfs/xfs_handle.c
index 49e5e5f04e60..f19fce557354 100644
--- a/fs/xfs/xfs_handle.c
+++ b/fs/xfs/xfs_handle.c
@@ -85,22 +85,23 @@ xfs_find_handle(
int hsize;
xfs_handle_t handle;
struct inode *inode;
- struct fd f = EMPTY_FD;
struct path path;
int error;
struct xfs_inode *ip;
if (cmd == XFS_IOC_FD_TO_HANDLE) {
- f = fdget(hreq->fd);
- if (!fd_file(f))
+ CLASS(fd, f)(hreq->fd);
+
+ if (fd_empty(f))
return -EBADF;
- inode = file_inode(fd_file(f));
+ path = fd_file(f)->f_path;
+ path_get(&path);
} else {
error = user_path_at(AT_FDCWD, hreq->path, 0, &path);
if (error)
return error;
- inode = d_inode(path.dentry);
}
+ inode = d_inode(path.dentry);
ip = XFS_I(inode);
/*
@@ -134,10 +135,7 @@ xfs_find_handle(
error = 0;
out_put:
- if (cmd == XFS_IOC_FD_TO_HANDLE)
- fdput(f);
- else
- path_put(&path);
+ path_put(&path);
return error;
}
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 03944b6c5fba..a2a6b5fd2545 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -332,6 +332,21 @@ static inline bool xfs_inode_has_bigrtalloc(struct xfs_inode *ip)
(XFS_IS_REALTIME_INODE(ip) ? \
(ip)->i_mount->m_rtdev_targp : (ip)->i_mount->m_ddev_targp)
+static inline bool
+xfs_inode_can_atomicwrite(
+ struct xfs_inode *ip)
+{
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_buftarg *target = xfs_inode_buftarg(ip);
+
+ if (mp->m_sb.sb_blocksize < target->bt_bdev_awu_min)
+ return false;
+ if (mp->m_sb.sb_blocksize > target->bt_bdev_awu_max)
+ return false;
+
+ return true;
+}
+
/*
* In-core inode flags.
*/
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 2567fd2a0994..af1bb5db1c59 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -881,41 +881,29 @@ xfs_ioc_swapext(
xfs_swapext_t *sxp)
{
xfs_inode_t *ip, *tip;
- struct fd f, tmp;
- int error = 0;
/* Pull information for the target fd */
- f = fdget((int)sxp->sx_fdtarget);
- if (!fd_file(f)) {
- error = -EINVAL;
- goto out;
- }
+ CLASS(fd, f)((int)sxp->sx_fdtarget);
+ if (fd_empty(f))
+ return -EINVAL;
if (!(fd_file(f)->f_mode & FMODE_WRITE) ||
!(fd_file(f)->f_mode & FMODE_READ) ||
- (fd_file(f)->f_flags & O_APPEND)) {
- error = -EBADF;
- goto out_put_file;
- }
+ (fd_file(f)->f_flags & O_APPEND))
+ return -EBADF;
- tmp = fdget((int)sxp->sx_fdtmp);
- if (!fd_file(tmp)) {
- error = -EINVAL;
- goto out_put_file;
- }
+ CLASS(fd, tmp)((int)sxp->sx_fdtmp);
+ if (fd_empty(tmp))
+ return -EINVAL;
if (!(fd_file(tmp)->f_mode & FMODE_WRITE) ||
!(fd_file(tmp)->f_mode & FMODE_READ) ||
- (fd_file(tmp)->f_flags & O_APPEND)) {
- error = -EBADF;
- goto out_put_tmp_file;
- }
+ (fd_file(tmp)->f_flags & O_APPEND))
+ return -EBADF;
if (IS_SWAPFILE(file_inode(fd_file(f))) ||
- IS_SWAPFILE(file_inode(fd_file(tmp)))) {
- error = -EINVAL;
- goto out_put_tmp_file;
- }
+ IS_SWAPFILE(file_inode(fd_file(tmp))))
+ return -EINVAL;
/*
* We need to ensure that the fds passed in point to XFS inodes
@@ -923,37 +911,22 @@ xfs_ioc_swapext(
* control over what the user passes us here.
*/
if (fd_file(f)->f_op != &xfs_file_operations ||
- fd_file(tmp)->f_op != &xfs_file_operations) {
- error = -EINVAL;
- goto out_put_tmp_file;
- }
+ fd_file(tmp)->f_op != &xfs_file_operations)
+ return -EINVAL;
ip = XFS_I(file_inode(fd_file(f)));
tip = XFS_I(file_inode(fd_file(tmp)));
- if (ip->i_mount != tip->i_mount) {
- error = -EINVAL;
- goto out_put_tmp_file;
- }
-
- if (ip->i_ino == tip->i_ino) {
- error = -EINVAL;
- goto out_put_tmp_file;
- }
+ if (ip->i_mount != tip->i_mount)
+ return -EINVAL;
- if (xfs_is_shutdown(ip->i_mount)) {
- error = -EIO;
- goto out_put_tmp_file;
- }
+ if (ip->i_ino == tip->i_ino)
+ return -EINVAL;
- error = xfs_swap_extents(ip, tip, sxp);
+ if (xfs_is_shutdown(ip->i_mount))
+ return -EIO;
- out_put_tmp_file:
- fdput(tmp);
- out_put_file:
- fdput(f);
- out:
- return error;
+ return xfs_swap_extents(ip, tip, sxp);
}
static int
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index ee79cf161312..4084d26f0d78 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -570,6 +570,20 @@ xfs_stat_blksize(
return max_t(uint32_t, PAGE_SIZE, mp->m_sb.sb_blocksize);
}
+static void
+xfs_get_atomic_write_attr(
+ struct xfs_inode *ip,
+ unsigned int *unit_min,
+ unsigned int *unit_max)
+{
+ if (!xfs_inode_can_atomicwrite(ip)) {
+ *unit_min = *unit_max = 0;
+ return;
+ }
+
+ *unit_min = *unit_max = ip->i_mount->m_sb.sb_blocksize;
+}
+
STATIC int
xfs_vn_getattr(
struct mnt_idmap *idmap,
@@ -597,8 +611,9 @@ xfs_vn_getattr(
stat->gid = vfsgid_into_kgid(vfsgid);
stat->ino = ip->i_ino;
stat->atime = inode_get_atime(inode);
- stat->mtime = inode_get_mtime(inode);
- stat->ctime = inode_get_ctime(inode);
+
+ fill_mg_cmtime(stat, request_mask, inode);
+
stat->blocks = XFS_FSB_TO_BB(mp, ip->i_nblocks + ip->i_delayed_blks);
if (xfs_has_v3inodes(mp)) {
@@ -608,11 +623,6 @@ xfs_vn_getattr(
}
}
- if ((request_mask & STATX_CHANGE_COOKIE) && IS_I_VERSION(inode)) {
- stat->change_cookie = inode_query_iversion(inode);
- stat->result_mask |= STATX_CHANGE_COOKIE;
- }
-
/*
* Note: If you add another clause to set an attribute flag, please
* update attributes_mask below.
@@ -643,6 +653,14 @@ xfs_vn_getattr(
stat->dio_mem_align = bdev_dma_alignment(bdev) + 1;
stat->dio_offset_align = bdev_logical_block_size(bdev);
}
+ if (request_mask & STATX_WRITE_ATOMIC) {
+ unsigned int unit_min, unit_max;
+
+ xfs_get_atomic_write_attr(ip, &unit_min,
+ &unit_max);
+ generic_fill_statx_atomic_writes(stat,
+ unit_min, unit_max);
+ }
fallthrough;
default:
stat->blksize = xfs_stat_blksize(ip);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index fbb3a1594c0d..fda75db739b1 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -2063,7 +2063,7 @@ static struct file_system_type xfs_fs_type = {
.init_fs_context = xfs_init_fs_context,
.parameters = xfs_fs_parameters,
.kill_sb = xfs_kill_sb,
- .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP,
+ .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP | FS_MGTIME,
};
MODULE_ALIAS_FS("xfs");