summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/Makefile2
-rw-r--r--fs/attr.c74
-rw-r--r--fs/btrfs/check-integrity.c4
-rw-r--r--fs/btrfs/compression.c6
-rw-r--r--fs/btrfs/compression.h2
-rw-r--r--fs/btrfs/ctree.h18
-rw-r--r--fs/btrfs/delayed-inode.c84
-rw-r--r--fs/btrfs/disk-io.c179
-rw-r--r--fs/btrfs/extent-tree.c2
-rw-r--r--fs/btrfs/extent_io.c140
-rw-r--r--fs/btrfs/inode.c19
-rw-r--r--fs/btrfs/raid56.c4
-rw-r--r--fs/btrfs/send.c40
-rw-r--r--fs/btrfs/tests/btrfs-tests.c24
-rw-r--r--fs/btrfs/transaction.c112
-rw-r--r--fs/buffer.c61
-rw-r--r--fs/direct-io.c40
-rw-r--r--fs/dlm/Kconfig9
-rw-r--r--fs/dlm/Makefile2
-rw-r--r--fs/dlm/ast.c4
-rw-r--r--fs/dlm/config.c21
-rw-r--r--fs/dlm/config.h3
-rw-r--r--fs/dlm/dlm_internal.h32
-rw-r--r--fs/dlm/lock.c143
-rw-r--r--fs/dlm/lock.h17
-rw-r--r--fs/dlm/lockspace.c31
-rw-r--r--fs/dlm/lowcomms.c4
-rw-r--r--fs/dlm/member.c30
-rw-r--r--fs/dlm/plock.c51
-rw-r--r--fs/dlm/recoverd.c35
-rw-r--r--fs/dlm/user.c21
-rw-r--r--fs/erofs/compress.h2
-rw-r--r--fs/erofs/data.c39
-rw-r--r--fs/erofs/decompressor.c18
-rw-r--r--fs/erofs/decompressor_lzma.c1
-rw-r--r--fs/erofs/dir.c20
-rw-r--r--fs/erofs/zdata.c797
-rw-r--r--fs/erofs/zdata.h119
-rw-r--r--fs/erofs/zpvec.h159
-rw-r--r--fs/exec.c15
-rw-r--r--fs/ext2/inode.c8
-rw-r--r--fs/ext2/super.c18
-rw-r--r--fs/ext4/ext4.h8
-rw-r--r--fs/ext4/fast_commit.c4
-rw-r--r--fs/ext4/inode.c14
-rw-r--r--fs/ext4/mmp.c11
-rw-r--r--fs/ext4/super.c20
-rw-r--r--fs/f2fs/data.c11
-rw-r--r--fs/f2fs/f2fs.h6
-rw-r--r--fs/f2fs/file.c22
-rw-r--r--fs/f2fs/node.c2
-rw-r--r--fs/f2fs/recovery.c10
-rw-r--r--fs/f2fs/segment.c2
-rw-r--r--fs/fat/file.c9
-rw-r--r--fs/gfs2/bmap.c5
-rw-r--r--fs/gfs2/dir.c5
-rw-r--r--fs/gfs2/log.c4
-rw-r--r--fs/gfs2/log.h2
-rw-r--r--fs/gfs2/lops.c4
-rw-r--r--fs/gfs2/lops.h2
-rw-r--r--fs/gfs2/meta_io.c18
-rw-r--r--fs/gfs2/quota.c2
-rw-r--r--fs/hfsplus/hfsplus_fs.h2
-rw-r--r--fs/hfsplus/part_tbl.c5
-rw-r--r--fs/hfsplus/super.c4
-rw-r--r--fs/hfsplus/wrapper.c12
-rw-r--r--fs/inode.c168
-rw-r--r--fs/io-wq.c1424
-rw-r--r--fs/io-wq.h228
-rw-r--r--fs/io_uring.c13265
-rw-r--r--fs/iomap/buffered-io.c67
-rw-r--r--fs/iomap/direct-io.c12
-rw-r--r--fs/isofs/compress.c2
-rw-r--r--fs/jbd2/commit.c8
-rw-r--r--fs/jbd2/journal.c25
-rw-r--r--fs/jbd2/recovery.c4
-rw-r--r--fs/jfs/file.c4
-rw-r--r--fs/ksmbd/vfs.c2
-rw-r--r--fs/ksmbd/vfs.h2
-rw-r--r--fs/locks.c77
-rw-r--r--fs/mpage.c6
-rw-r--r--fs/nfs/blocklayout/blocklayout.c13
-rw-r--r--fs/nilfs2/btnode.c8
-rw-r--r--fs/nilfs2/btnode.h4
-rw-r--r--fs/nilfs2/btree.c6
-rw-r--r--fs/nilfs2/gcinode.c7
-rw-r--r--fs/nilfs2/mdt.c19
-rw-r--r--fs/notify/fanotify/fanotify.c19
-rw-r--r--fs/notify/fanotify/fanotify.h2
-rw-r--r--fs/notify/fanotify/fanotify_user.c110
-rw-r--r--fs/notify/fdinfo.c6
-rw-r--r--fs/notify/fsnotify.c23
-rw-r--r--fs/notify/inotify/inotify_user.c2
-rw-r--r--fs/ntfs/aops.c6
-rw-r--r--fs/ntfs/attrib.c8
-rw-r--r--fs/ntfs/compress.c2
-rw-r--r--fs/ntfs/file.c2
-rw-r--r--fs/ntfs/logfile.c2
-rw-r--r--fs/ntfs/mft.c4
-rw-r--r--fs/ntfs3/file.c2
-rw-r--r--fs/ntfs3/fsntfs.c2
-rw-r--r--fs/ntfs3/inode.c2
-rw-r--r--fs/ntfs3/ntfs_fs.h2
-rw-r--r--fs/ocfs2/aops.c2
-rw-r--r--fs/ocfs2/buffer_head_io.c8
-rw-r--r--fs/ocfs2/cluster/heartbeat.c75
-rw-r--r--fs/ocfs2/file.c2
-rw-r--r--fs/ocfs2/ocfs2.h4
-rw-r--r--fs/ocfs2/slot_map.c46
-rw-r--r--fs/ocfs2/super.c23
-rw-r--r--fs/open.c60
-rw-r--r--fs/overlayfs/copy_up.c4
-rw-r--r--fs/overlayfs/inode.c87
-rw-r--r--fs/overlayfs/overlayfs.h15
-rw-r--r--fs/overlayfs/super.c25
-rw-r--r--fs/posix_acl.c168
-rw-r--r--fs/pstore/platform.c63
-rw-r--r--fs/pstore/zone.c12
-rw-r--r--fs/quota/dquot.c17
-rw-r--r--fs/read_write.c7
-rw-r--r--fs/reiserfs/inode.c20
-rw-r--r--fs/reiserfs/journal.c12
-rw-r--r--fs/reiserfs/stree.c4
-rw-r--r--fs/reiserfs/super.c2
-rw-r--r--fs/udf/dir.c2
-rw-r--r--fs/udf/directory.c2
-rw-r--r--fs/udf/inode.c2
-rw-r--r--fs/ufs/balloc.c2
-rw-r--r--fs/userfaultfd.c12
-rw-r--r--fs/verity/Kconfig10
-rw-r--r--fs/xattr.c25
-rw-r--r--fs/xfs/xfs_bio_io.c2
-rw-r--r--fs/xfs/xfs_buf.c4
-rw-r--r--fs/xfs/xfs_file.c11
-rw-r--r--fs/xfs/xfs_iomap.c11
-rw-r--r--fs/xfs/xfs_iops.c14
-rw-r--r--fs/xfs/xfs_linux.h2
-rw-r--r--fs/xfs/xfs_log_recover.c2
-rw-r--r--fs/zonefs/super.c24
-rw-r--r--fs/zonefs/trace.h4
140 files changed, 2215 insertions, 16709 deletions
diff --git a/fs/Makefile b/fs/Makefile
index 208a74e0b00e..93b80529f8e8 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -34,8 +34,6 @@ obj-$(CONFIG_TIMERFD) += timerfd.o
obj-$(CONFIG_EVENTFD) += eventfd.o
obj-$(CONFIG_USERFAULTFD) += userfaultfd.o
obj-$(CONFIG_AIO) += aio.o
-obj-$(CONFIG_IO_URING) += io_uring.o
-obj-$(CONFIG_IO_WQ) += io-wq.o
obj-$(CONFIG_FS_DAX) += dax.o
obj-$(CONFIG_FS_ENCRYPTION) += crypto/
obj-$(CONFIG_FS_VERITY) += verity/
diff --git a/fs/attr.c b/fs/attr.c
index dbe996b0dedf..b5b8835ddf15 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -22,7 +22,7 @@
* chown_ok - verify permissions to chown inode
* @mnt_userns: user namespace of the mount @inode was found from
* @inode: inode to check permissions on
- * @uid: uid to chown @inode to
+ * @ia_vfsuid: uid to chown @inode to
*
* If the inode has been found through an idmapped mount the user namespace of
* the vfsmount must be passed through @mnt_userns. This function will then
@@ -31,15 +31,15 @@
* performed on the raw inode simply passs init_user_ns.
*/
static bool chown_ok(struct user_namespace *mnt_userns,
- const struct inode *inode,
- kuid_t uid)
+ const struct inode *inode, vfsuid_t ia_vfsuid)
{
- kuid_t kuid = i_uid_into_mnt(mnt_userns, inode);
- if (uid_eq(current_fsuid(), kuid) && uid_eq(uid, inode->i_uid))
+ vfsuid_t vfsuid = i_uid_into_vfsuid(mnt_userns, inode);
+ if (vfsuid_eq_kuid(vfsuid, current_fsuid()) &&
+ vfsuid_eq(ia_vfsuid, vfsuid))
return true;
if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN))
return true;
- if (uid_eq(kuid, INVALID_UID) &&
+ if (!vfsuid_valid(vfsuid) &&
ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN))
return true;
return false;
@@ -49,7 +49,7 @@ static bool chown_ok(struct user_namespace *mnt_userns,
* chgrp_ok - verify permissions to chgrp inode
* @mnt_userns: user namespace of the mount @inode was found from
* @inode: inode to check permissions on
- * @gid: gid to chown @inode to
+ * @ia_vfsgid: gid to chown @inode to
*
* If the inode has been found through an idmapped mount the user namespace of
* the vfsmount must be passed through @mnt_userns. This function will then
@@ -58,21 +58,19 @@ static bool chown_ok(struct user_namespace *mnt_userns,
* performed on the raw inode simply passs init_user_ns.
*/
static bool chgrp_ok(struct user_namespace *mnt_userns,
- const struct inode *inode, kgid_t gid)
+ const struct inode *inode, vfsgid_t ia_vfsgid)
{
- kgid_t kgid = i_gid_into_mnt(mnt_userns, inode);
- if (uid_eq(current_fsuid(), i_uid_into_mnt(mnt_userns, inode))) {
- kgid_t mapped_gid;
-
- if (gid_eq(gid, inode->i_gid))
+ vfsgid_t vfsgid = i_gid_into_vfsgid(mnt_userns, inode);
+ vfsuid_t vfsuid = i_uid_into_vfsuid(mnt_userns, inode);
+ if (vfsuid_eq_kuid(vfsuid, current_fsuid())) {
+ if (vfsgid_eq(ia_vfsgid, vfsgid))
return true;
- mapped_gid = mapped_kgid_fs(mnt_userns, i_user_ns(inode), gid);
- if (in_group_p(mapped_gid))
+ if (vfsgid_in_group_p(ia_vfsgid))
return true;
}
if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN))
return true;
- if (gid_eq(kgid, INVALID_GID) &&
+ if (!vfsgid_valid(vfsgid) &&
ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN))
return true;
return false;
@@ -120,28 +118,29 @@ int setattr_prepare(struct user_namespace *mnt_userns, struct dentry *dentry,
goto kill_priv;
/* Make sure a caller can chown. */
- if ((ia_valid & ATTR_UID) && !chown_ok(mnt_userns, inode, attr->ia_uid))
+ if ((ia_valid & ATTR_UID) &&
+ !chown_ok(mnt_userns, inode, attr->ia_vfsuid))
return -EPERM;
/* Make sure caller can chgrp. */
- if ((ia_valid & ATTR_GID) && !chgrp_ok(mnt_userns, inode, attr->ia_gid))
+ if ((ia_valid & ATTR_GID) &&
+ !chgrp_ok(mnt_userns, inode, attr->ia_vfsgid))
return -EPERM;
/* Make sure a caller can chmod. */
if (ia_valid & ATTR_MODE) {
- kgid_t mapped_gid;
+ vfsgid_t vfsgid;
if (!inode_owner_or_capable(mnt_userns, inode))
return -EPERM;
if (ia_valid & ATTR_GID)
- mapped_gid = mapped_kgid_fs(mnt_userns,
- i_user_ns(inode), attr->ia_gid);
+ vfsgid = attr->ia_vfsgid;
else
- mapped_gid = i_gid_into_mnt(mnt_userns, inode);
+ vfsgid = i_gid_into_vfsgid(mnt_userns, inode);
/* Also check the setgid bit! */
- if (!in_group_p(mapped_gid) &&
+ if (!vfsgid_in_group_p(vfsgid) &&
!capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID))
attr->ia_mode &= ~S_ISGID;
}
@@ -219,9 +218,7 @@ EXPORT_SYMBOL(inode_newsize_ok);
* setattr_copy must be called with i_mutex held.
*
* setattr_copy updates the inode's metadata with that specified
- * in attr on idmapped mounts. If file ownership is changed setattr_copy
- * doesn't map ia_uid and ia_gid. It will asssume the caller has already
- * provided the intended values. Necessary permission checks to determine
+ * in attr on idmapped mounts. Necessary permission checks to determine
* whether or not the S_ISGID property needs to be removed are performed with
* the correct idmapped mount permission helpers.
* Noticeably missing is inode size update, which is more complex
@@ -242,10 +239,8 @@ void setattr_copy(struct user_namespace *mnt_userns, struct inode *inode,
{
unsigned int ia_valid = attr->ia_valid;
- if (ia_valid & ATTR_UID)
- inode->i_uid = attr->ia_uid;
- if (ia_valid & ATTR_GID)
- inode->i_gid = attr->ia_gid;
+ i_uid_update(mnt_userns, attr, inode);
+ i_gid_update(mnt_userns, attr, inode);
if (ia_valid & ATTR_ATIME)
inode->i_atime = attr->ia_atime;
if (ia_valid & ATTR_MTIME)
@@ -254,8 +249,8 @@ void setattr_copy(struct user_namespace *mnt_userns, struct inode *inode,
inode->i_ctime = attr->ia_ctime;
if (ia_valid & ATTR_MODE) {
umode_t mode = attr->ia_mode;
- kgid_t kgid = i_gid_into_mnt(mnt_userns, inode);
- if (!in_group_p(kgid) &&
+ vfsgid_t vfsgid = i_gid_into_vfsgid(mnt_userns, inode);
+ if (!vfsgid_in_group_p(vfsgid) &&
!capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID))
mode &= ~S_ISGID;
inode->i_mode = mode;
@@ -306,9 +301,6 @@ EXPORT_SYMBOL(may_setattr);
* retry. Because breaking a delegation may take a long time, the
* caller should drop the i_mutex before doing so.
*
- * If file ownership is changed notify_change() doesn't map ia_uid and
- * ia_gid. It will asssume the caller has already provided the intended values.
- *
* Alternatively, a caller may pass NULL for delegated_inode. This may
* be appropriate for callers that expect the underlying filesystem not
* to be NFS exported. Also, passing NULL is fine for callers holding
@@ -397,23 +389,25 @@ int notify_change(struct user_namespace *mnt_userns, struct dentry *dentry,
* namespace of the superblock.
*/
if (ia_valid & ATTR_UID &&
- !kuid_has_mapping(inode->i_sb->s_user_ns, attr->ia_uid))
+ !vfsuid_has_fsmapping(mnt_userns, inode->i_sb->s_user_ns,
+ attr->ia_vfsuid))
return -EOVERFLOW;
if (ia_valid & ATTR_GID &&
- !kgid_has_mapping(inode->i_sb->s_user_ns, attr->ia_gid))
+ !vfsgid_has_fsmapping(mnt_userns, inode->i_sb->s_user_ns,
+ attr->ia_vfsgid))
return -EOVERFLOW;
/* Don't allow modifications of files with invalid uids or
* gids unless those uids & gids are being made valid.
*/
if (!(ia_valid & ATTR_UID) &&
- !uid_valid(i_uid_into_mnt(mnt_userns, inode)))
+ !vfsuid_valid(i_uid_into_vfsuid(mnt_userns, inode)))
return -EOVERFLOW;
if (!(ia_valid & ATTR_GID) &&
- !gid_valid(i_gid_into_mnt(mnt_userns, inode)))
+ !vfsgid_valid(i_gid_into_vfsgid(mnt_userns, inode)))
return -EOVERFLOW;
- error = security_inode_setattr(dentry, attr);
+ error = security_inode_setattr(mnt_userns, dentry, attr);
if (error)
return error;
error = try_break_deleg(inode, delegated_inode);
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index 5d20137b7b67..98c6e5feab19 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -152,7 +152,7 @@ struct btrfsic_block {
struct btrfsic_block *next_in_same_bio;
void *orig_bio_private;
bio_end_io_t *orig_bio_end_io;
- int submit_bio_bh_rw;
+ blk_opf_t submit_bio_bh_rw;
u64 flush_gen; /* only valid if !never_written */
};
@@ -1681,7 +1681,7 @@ static void btrfsic_process_written_block(struct btrfsic_dev_state *dev_state,
u64 dev_bytenr, char **mapped_datav,
unsigned int num_pages,
struct bio *bio, int *bio_is_patched,
- int submit_bio_bh_rw)
+ blk_opf_t submit_bio_bh_rw)
{
int is_metadata;
struct btrfsic_block *block;
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index f4564f32f6d9..a82b9f17f476 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -455,7 +455,7 @@ static blk_status_t submit_compressed_bio(struct btrfs_fs_info *fs_info,
static struct bio *alloc_compressed_bio(struct compressed_bio *cb, u64 disk_bytenr,
- unsigned int opf, bio_end_io_t endio_func,
+ blk_opf_t opf, bio_end_io_t endio_func,
u64 *next_stripe_start)
{
struct btrfs_fs_info *fs_info = btrfs_sb(cb->inode->i_sb);
@@ -505,7 +505,7 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
unsigned int compressed_len,
struct page **compressed_pages,
unsigned int nr_pages,
- unsigned int write_flags,
+ blk_opf_t write_flags,
struct cgroup_subsys_state *blkcg_css,
bool writeback)
{
@@ -517,7 +517,7 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
blk_status_t ret;
int skip_sum = inode->flags & BTRFS_INODE_NODATASUM;
const bool use_append = btrfs_use_zone_append(inode, disk_start);
- const unsigned int bio_op = use_append ? REQ_OP_ZONE_APPEND : REQ_OP_WRITE;
+ const enum req_op bio_op = use_append ? REQ_OP_ZONE_APPEND : REQ_OP_WRITE;
ASSERT(IS_ALIGNED(start, fs_info->sectorsize) &&
IS_ALIGNED(len, fs_info->sectorsize));
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 2707404389a5..2b56d63e01ce 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -99,7 +99,7 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
unsigned int compressed_len,
struct page **compressed_pages,
unsigned int nr_pages,
- unsigned int write_flags,
+ blk_opf_t write_flags,
struct cgroup_subsys_state *blkcg_css,
bool writeback);
void btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 415bf1823fb3..9c21e214d29e 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -675,9 +675,8 @@ struct btrfs_fs_info {
rwlock_t global_root_lock;
struct rb_root global_root_tree;
- /* The xarray that holds all the FS roots */
- spinlock_t fs_roots_lock;
- struct xarray fs_roots;
+ spinlock_t fs_roots_radix_lock;
+ struct radix_tree_root fs_roots_radix;
/* block group cache stuff */
rwlock_t block_group_cache_lock;
@@ -995,10 +994,10 @@ struct btrfs_fs_info {
struct btrfs_delayed_root *delayed_root;
- /* Extent buffer xarray */
+ /* Extent buffer radix tree */
spinlock_t buffer_lock;
/* Entries are eb->start / sectorsize */
- struct xarray extent_buffers;
+ struct radix_tree_root buffer_radix;
/* next backup root to be overwritten */
int backup_root_index;
@@ -1119,8 +1118,7 @@ enum {
*/
BTRFS_ROOT_SHAREABLE,
BTRFS_ROOT_TRACK_DIRTY,
- /* The root is tracked in fs_info::fs_roots */
- BTRFS_ROOT_REGISTERED,
+ BTRFS_ROOT_IN_RADIX,
BTRFS_ROOT_ORPHAN_ITEM_INSERTED,
BTRFS_ROOT_DEFRAG_RUNNING,
BTRFS_ROOT_FORCE_COW,
@@ -1224,10 +1222,10 @@ struct btrfs_root {
struct rb_root inode_tree;
/*
- * Xarray that keeps track of delayed nodes of every inode, protected
- * by inode_lock
+ * radix tree that keeps track of delayed nodes of every inode,
+ * protected by inode_lock
*/
- struct xarray delayed_nodes;
+ struct radix_tree_root delayed_nodes_tree;
/*
* right now this just gets used so that a root has its own devid
* for stat. It may be used for more later
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 66779ab3ed4a..748bf6b0d860 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -78,7 +78,7 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node(
}
spin_lock(&root->inode_lock);
- node = xa_load(&root->delayed_nodes, ino);
+ node = radix_tree_lookup(&root->delayed_nodes_tree, ino);
if (node) {
if (btrfs_inode->delayed_node) {
@@ -90,9 +90,9 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node(
/*
* It's possible that we're racing into the middle of removing
- * this node from the xarray. In this case, the refcount
+ * this node from the radix tree. In this case, the refcount
* was zero and it should never go back to one. Just return
- * NULL like it was never in the xarray at all; our release
+ * NULL like it was never in the radix at all; our release
* function is in the process of removing it.
*
* Some implementations of refcount_inc refuse to bump the
@@ -100,7 +100,7 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node(
* here, refcount_inc() may decide to just WARN_ONCE() instead
* of actually bumping the refcount.
*
- * If this node is properly in the xarray, we want to bump the
+ * If this node is properly in the radix, we want to bump the
* refcount twice, once for the inode and once for this get
* operation.
*/
@@ -128,30 +128,36 @@ static struct btrfs_delayed_node *btrfs_get_or_create_delayed_node(
u64 ino = btrfs_ino(btrfs_inode);
int ret;
- do {
- node = btrfs_get_delayed_node(btrfs_inode);
- if (node)
- return node;
+again:
+ node = btrfs_get_delayed_node(btrfs_inode);
+ if (node)
+ return node;
- node = kmem_cache_zalloc(delayed_node_cache, GFP_NOFS);
- if (!node)
- return ERR_PTR(-ENOMEM);
- btrfs_init_delayed_node(node, root, ino);
+ node = kmem_cache_zalloc(delayed_node_cache, GFP_NOFS);
+ if (!node)
+ return ERR_PTR(-ENOMEM);
+ btrfs_init_delayed_node(node, root, ino);
- /* Cached in the inode and can be accessed */
- refcount_set(&node->refs, 2);
+ /* cached in the btrfs inode and can be accessed */
+ refcount_set(&node->refs, 2);
- spin_lock(&root->inode_lock);
- ret = xa_insert(&root->delayed_nodes, ino, node, GFP_NOFS);
- if (ret) {
- spin_unlock(&root->inode_lock);
- kmem_cache_free(delayed_node_cache, node);
- if (ret != -EBUSY)
- return ERR_PTR(ret);
- }
- } while (ret);
+ ret = radix_tree_preload(GFP_NOFS);
+ if (ret) {
+ kmem_cache_free(delayed_node_cache, node);
+ return ERR_PTR(ret);
+ }
+
+ spin_lock(&root->inode_lock);
+ ret = radix_tree_insert(&root->delayed_nodes_tree, ino, node);
+ if (ret == -EEXIST) {
+ spin_unlock(&root->inode_lock);
+ kmem_cache_free(delayed_node_cache, node);
+ radix_tree_preload_end();
+ goto again;
+ }
btrfs_inode->delayed_node = node;
spin_unlock(&root->inode_lock);
+ radix_tree_preload_end();
return node;
}
@@ -270,7 +276,8 @@ static void __btrfs_release_delayed_node(
* back up. We can delete it now.
*/
ASSERT(refcount_read(&delayed_node->refs) == 0);
- xa_erase(&root->delayed_nodes, delayed_node->inode_id);
+ radix_tree_delete(&root->delayed_nodes_tree,
+ delayed_node->inode_id);
spin_unlock(&root->inode_lock);
kmem_cache_free(delayed_node_cache, delayed_node);
}
@@ -1863,35 +1870,34 @@ void btrfs_kill_delayed_inode_items(struct btrfs_inode *inode)
void btrfs_kill_all_delayed_nodes(struct btrfs_root *root)
{
- unsigned long index = 0;
- struct btrfs_delayed_node *delayed_node;
+ u64 inode_id = 0;
struct btrfs_delayed_node *delayed_nodes[8];
+ int i, n;
while (1) {
- int n = 0;
-
spin_lock(&root->inode_lock);
- if (xa_empty(&root->delayed_nodes)) {
+ n = radix_tree_gang_lookup(&root->delayed_nodes_tree,
+ (void **)delayed_nodes, inode_id,
+ ARRAY_SIZE(delayed_nodes));
+ if (!n) {
spin_unlock(&root->inode_lock);
- return;
+ break;
}
- xa_for_each_start(&root->delayed_nodes, index, delayed_node, index) {
+ inode_id = delayed_nodes[n - 1]->inode_id + 1;
+ for (i = 0; i < n; i++) {
/*
* Don't increase refs in case the node is dead and
* about to be removed from the tree in the loop below
*/
- if (refcount_inc_not_zero(&delayed_node->refs)) {
- delayed_nodes[n] = delayed_node;
- n++;
- }
- if (n >= ARRAY_SIZE(delayed_nodes))
- break;
+ if (!refcount_inc_not_zero(&delayed_nodes[i]->refs))
+ delayed_nodes[i] = NULL;
}
- index++;
spin_unlock(&root->inode_lock);
- for (int i = 0; i < n; i++) {
+ for (i = 0; i < n; i++) {
+ if (!delayed_nodes[i])
+ continue;
__btrfs_kill_delayed_node(delayed_nodes[i]);
btrfs_release_delayed_node(delayed_nodes[i]);
}
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 4ba005c41983..de440ebf5648 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -5,6 +5,7 @@
#include <linux/fs.h>
#include <linux/blkdev.h>
+#include <linux/radix-tree.h>
#include <linux/writeback.h>
#include <linux/workqueue.h>
#include <linux/kthread.h>
@@ -485,7 +486,7 @@ static int csum_dirty_subpage_buffers(struct btrfs_fs_info *fs_info,
uptodate = btrfs_subpage_test_uptodate(fs_info, page, cur,
fs_info->nodesize);
- /* A dirty eb shouldn't disappear from extent_buffers */
+ /* A dirty eb shouldn't disappear from buffer_radix */
if (WARN_ON(!eb))
return -EUCLEAN;
@@ -1158,7 +1159,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
root->nr_delalloc_inodes = 0;
root->nr_ordered_extents = 0;
root->inode_tree = RB_ROOT;
- xa_init_flags(&root->delayed_nodes, GFP_ATOMIC);
+ INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC);
btrfs_init_root_block_rsv(root);
@@ -1210,9 +1211,9 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
btrfs_qgroup_init_swapped_blocks(&root->swapped_blocks);
#ifdef CONFIG_BTRFS_DEBUG
INIT_LIST_HEAD(&root->leak_list);
- spin_lock(&fs_info->fs_roots_lock);
+ spin_lock(&fs_info->fs_roots_radix_lock);
list_add_tail(&root->leak_list, &fs_info->allocated_roots);
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
#endif
}
@@ -1659,11 +1660,12 @@ static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
{
struct btrfs_root *root;
- spin_lock(&fs_info->fs_roots_lock);
- root = xa_load(&fs_info->fs_roots, (unsigned long)root_id);
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ root = radix_tree_lookup(&fs_info->fs_roots_radix,
+ (unsigned long)root_id);
if (root)
root = btrfs_grab_root(root);
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
return root;
}
@@ -1705,14 +1707,20 @@ int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
{
int ret;
- spin_lock(&fs_info->fs_roots_lock);
- ret = xa_insert(&fs_info->fs_roots, (unsigned long)root->root_key.objectid,
- root, GFP_NOFS);
+ ret = radix_tree_preload(GFP_NOFS);
+ if (ret)
+ return ret;
+
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ ret = radix_tree_insert(&fs_info->fs_roots_radix,
+ (unsigned long)root->root_key.objectid,
+ root);
if (ret == 0) {
btrfs_grab_root(root);
- set_bit(BTRFS_ROOT_REGISTERED, &root->state);
+ set_bit(BTRFS_ROOT_IN_RADIX, &root->state);
}
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
+ radix_tree_preload_end();
return ret;
}
@@ -2342,9 +2350,9 @@ void btrfs_put_root(struct btrfs_root *root)
btrfs_drew_lock_destroy(&root->snapshot_lock);
free_root_extent_buffers(root);
#ifdef CONFIG_BTRFS_DEBUG
- spin_lock(&root->fs_info->fs_roots_lock);
+ spin_lock(&root->fs_info->fs_roots_radix_lock);
list_del_init(&root->leak_list);
- spin_unlock(&root->fs_info->fs_roots_lock);
+ spin_unlock(&root->fs_info->fs_roots_radix_lock);
#endif
kfree(root);
}
@@ -2352,21 +2360,28 @@ void btrfs_put_root(struct btrfs_root *root)
void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info)
{
- struct btrfs_root *root;
- unsigned long index = 0;
+ int ret;
+ struct btrfs_root *gang[8];
+ int i;
while (!list_empty(&fs_info->dead_roots)) {
- root = list_entry(fs_info->dead_roots.next,
- struct btrfs_root, root_list);
- list_del(&root->root_list);
+ gang[0] = list_entry(fs_info->dead_roots.next,
+ struct btrfs_root, root_list);
+ list_del(&gang[0]->root_list);
- if (test_bit(BTRFS_ROOT_REGISTERED, &root->state))
- btrfs_drop_and_free_fs_root(fs_info, root);
- btrfs_put_root(root);
+ if (test_bit(BTRFS_ROOT_IN_RADIX, &gang[0]->state))
+ btrfs_drop_and_free_fs_root(fs_info, gang[0]);
+ btrfs_put_root(gang[0]);
}
- xa_for_each(&fs_info->fs_roots, index, root) {
- btrfs_drop_and_free_fs_root(fs_info, root);
+ while (1) {
+ ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
+ (void **)gang, 0,
+ ARRAY_SIZE(gang));
+ if (!ret)
+ break;
+ for (i = 0; i < ret; i++)
+ btrfs_drop_and_free_fs_root(fs_info, gang[i]);
}
}
@@ -3134,8 +3149,8 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info)
void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
{
- xa_init_flags(&fs_info->fs_roots, GFP_ATOMIC);
- xa_init_flags(&fs_info->extent_buffers, GFP_ATOMIC);
+ INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC);
+ INIT_RADIX_TREE(&fs_info->buffer_radix, GFP_ATOMIC);
INIT_LIST_HEAD(&fs_info->trans_list);
INIT_LIST_HEAD(&fs_info->dead_roots);
INIT_LIST_HEAD(&fs_info->delayed_iputs);
@@ -3143,7 +3158,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
INIT_LIST_HEAD(&fs_info->caching_block_groups);
spin_lock_init(&fs_info->delalloc_root_lock);
spin_lock_init(&fs_info->trans_lock);
- spin_lock_init(&fs_info->fs_roots_lock);
+ spin_lock_init(&fs_info->fs_roots_radix_lock);
spin_lock_init(&fs_info->delayed_iput_lock);
spin_lock_init(&fs_info->defrag_inodes_lock);
spin_lock_init(&fs_info->super_lock);
@@ -3374,7 +3389,7 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
/*
* btrfs_find_orphan_roots() is responsible for finding all the dead
* roots (with 0 refs), flag them with BTRFS_ROOT_DEAD_TREE and load
- * them into the fs_info->fs_roots. This must be done before
+ * them into the fs_info->fs_roots_radix tree. This must be done before
* calling btrfs_orphan_cleanup() on the tree root. If we don't do it
* first, then btrfs_orphan_cleanup() will delete a dead root's orphan
* item before the root's tree is deleted - this means that if we unmount
@@ -4499,11 +4514,12 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
{
bool drop_ref = false;
- spin_lock(&fs_info->fs_roots_lock);
- xa_erase(&fs_info->fs_roots, (unsigned long)root->root_key.objectid);
- if (test_and_clear_bit(BTRFS_ROOT_REGISTERED, &root->state))
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ radix_tree_delete(&fs_info->fs_roots_radix,
+ (unsigned long)root->root_key.objectid);
+ if (test_and_clear_bit(BTRFS_ROOT_IN_RADIX, &root->state))
drop_ref = true;
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
if (BTRFS_FS_ERROR(fs_info)) {
ASSERT(root->log_root == NULL);
@@ -4519,48 +4535,50 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info)
{
- struct btrfs_root *roots[8];
- unsigned long index = 0;
- int i;
+ u64 root_objectid = 0;
+ struct btrfs_root *gang[8];
+ int i = 0;
int err = 0;
- int grabbed;
+ unsigned int ret = 0;
while (1) {
- struct btrfs_root *root;
-
- spin_lock(&fs_info->fs_roots_lock);
- if (!xa_find(&fs_info->fs_roots, &index, ULONG_MAX, XA_PRESENT)) {
- spin_unlock(&fs_info->fs_roots_lock);
- return err;
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
+ (void **)gang, root_objectid,
+ ARRAY_SIZE(gang));
+ if (!ret) {
+ spin_unlock(&fs_info->fs_roots_radix_lock);
+ break;
}
+ root_objectid = gang[ret - 1]->root_key.objectid + 1;
- grabbed = 0;
- xa_for_each_start(&fs_info->fs_roots, index, root, index) {
- /* Avoid grabbing roots in dead_roots */
- if (btrfs_root_refs(&root->root_item) > 0)
- roots[grabbed++] = btrfs_grab_root(root);
- if (grabbed >= ARRAY_SIZE(roots))
- break;
+ for (i = 0; i < ret; i++) {
+ /* Avoid to grab roots in dead_roots */
+ if (btrfs_root_refs(&gang[i]->root_item) == 0) {
+ gang[i] = NULL;
+ continue;
+ }
+ /* grab all the search result for later use */
+ gang[i] = btrfs_grab_root(gang[i]);
}
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
- for (i = 0; i < grabbed; i++) {
- if (!roots[i])
+ for (i = 0; i < ret; i++) {
+ if (!gang[i])
continue;
- index = roots[i]->root_key.objectid;
- err = btrfs_orphan_cleanup(roots[i]);
+ root_objectid = gang[i]->root_key.objectid;
+ err = btrfs_orphan_cleanup(gang[i]);
if (err)
- goto out;
- btrfs_put_root(roots[i]);
+ break;
+ btrfs_put_root(gang[i]);
}
- index++;
+ root_objectid++;
}
-out:
- /* Release the roots that remain uncleaned due to error */
- for (; i < grabbed; i++) {
- if (roots[i])
- btrfs_put_root(roots[i]);
+ /* release the uncleaned roots due to error */
+ for (; i < ret; i++) {
+ if (gang[i])
+ btrfs_put_root(gang[i]);
}
return err;
}
@@ -4879,28 +4897,31 @@ static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info)
static void btrfs_drop_all_logs(struct btrfs_fs_info *fs_info)
{
- unsigned long index = 0;
- int grabbed = 0;
- struct btrfs_root *roots[8];
+ struct btrfs_root *gang[8];
+ u64 root_objectid = 0;
+ int ret;
+
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ while ((ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
+ (void **)gang, root_objectid,
+ ARRAY_SIZE(gang))) != 0) {
+ int i;
- spin_lock(&fs_info->fs_roots_lock);
- while ((grabbed = xa_extract(&fs_info->fs_roots, (void **)roots, index,
- ULONG_MAX, 8, XA_PRESENT))) {
- for (int i = 0; i < grabbed; i++)
- roots[i] = btrfs_grab_root(roots[i]);
- spin_unlock(&fs_info->fs_roots_lock);
+ for (i = 0; i < ret; i++)
+ gang[i] = btrfs_grab_root(gang[i]);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
- for (int i = 0; i < grabbed; i++) {
- if (!roots[i])
+ for (i = 0; i < ret; i++) {
+ if (!gang[i])
continue;
- index = roots[i]->root_key.objectid;
- btrfs_free_log(NULL, roots[i]);
- btrfs_put_root(roots[i]);
+ root_objectid = gang[i]->root_key.objectid;
+ btrfs_free_log(NULL, gang[i]);
+ btrfs_put_root(gang[i]);
}
- index++;
- spin_lock(&fs_info->fs_roots_lock);
+ root_objectid++;
+ spin_lock(&fs_info->fs_roots_radix_lock);
}
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
btrfs_free_log_root_tree(NULL, fs_info);
}
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 4157ecc27d4b..a3afc15430ce 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -5829,7 +5829,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
btrfs_qgroup_convert_reserved_meta(root, INT_MAX);
btrfs_qgroup_free_meta_all_pertrans(root);
- if (test_bit(BTRFS_ROOT_REGISTERED, &root->state))
+ if (test_bit(BTRFS_ROOT_IN_RADIX, &root->state))
btrfs_add_dropped_root(trans, root);
else
btrfs_put_root(root);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 04e36343da3a..9eb3056b94d4 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2966,7 +2966,7 @@ static void begin_page_read(struct btrfs_fs_info *fs_info, struct page *page)
}
/*
- * Find extent buffer for a given bytenr.
+ * Find extent buffer for a givne bytenr.
*
* This is for end_bio_extent_readpage(), thus we can't do any unsafe locking
* in endio context.
@@ -2985,9 +2985,11 @@ static struct extent_buffer *find_extent_buffer_readpage(
return (struct extent_buffer *)page->private;
}
- /* For subpage case, we need to lookup extent buffer xarray */
- eb = xa_load(&fs_info->extent_buffers,
- bytenr >> fs_info->sectorsize_bits);
+ /* For subpage case, we need to lookup buffer radix tree */
+ rcu_read_lock();
+ eb = radix_tree_lookup(&fs_info->buffer_radix,
+ bytenr >> fs_info->sectorsize_bits);
+ rcu_read_unlock();
ASSERT(eb);
return eb;
}
@@ -3357,7 +3359,7 @@ static int calc_bio_boundaries(struct btrfs_bio_ctrl *bio_ctrl,
static int alloc_new_bio(struct btrfs_inode *inode,
struct btrfs_bio_ctrl *bio_ctrl,
struct writeback_control *wbc,
- unsigned int opf,
+ blk_opf_t opf,
bio_end_io_t end_io_func,
u64 disk_bytenr, u32 offset, u64 file_offset,
enum btrfs_compression_type compress_type)
@@ -3437,7 +3439,7 @@ error:
* @prev_bio_flags: flags of previous bio to see if we can merge the current one
* @compress_type: compress type for current bio
*/
-static int submit_extent_page(unsigned int opf,
+static int submit_extent_page(blk_opf_t opf,
struct writeback_control *wbc,
struct btrfs_bio_ctrl *bio_ctrl,
struct page *page, u64 disk_bytenr,
@@ -3615,7 +3617,7 @@ __get_extent_map(struct inode *inode, struct page *page, size_t pg_offset,
*/
static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
struct btrfs_bio_ctrl *bio_ctrl,
- unsigned int read_flags, u64 *prev_em_start)
+ blk_opf_t read_flags, u64 *prev_em_start)
{
struct inode *inode = page->mapping->host;
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
@@ -3983,8 +3985,8 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
int saved_ret = 0;
int ret = 0;
int nr = 0;
- u32 opf = REQ_OP_WRITE;
- const unsigned int write_flags = wbc_to_write_flags(wbc);
+ enum req_op op = REQ_OP_WRITE;
+ const blk_opf_t write_flags = wbc_to_write_flags(wbc);
bool has_error = false;
bool compressed;
@@ -4058,7 +4060,7 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
iosize = min(min(em_end, end + 1), dirty_range_end) - cur;
if (btrfs_use_zone_append(inode, em->block_start))
- opf = REQ_OP_ZONE_APPEND;
+ op = REQ_OP_ZONE_APPEND;
free_extent_map(em);
em = NULL;
@@ -4094,7 +4096,7 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
*/
btrfs_page_clear_dirty(fs_info, page, cur, iosize);
- ret = submit_extent_page(opf | write_flags, wbc,
+ ret = submit_extent_page(op | write_flags, wbc,
&epd->bio_ctrl, page,
disk_bytenr, iosize,
cur - page_offset(page),
@@ -4435,8 +4437,8 @@ static struct extent_buffer *find_extent_buffer_nolock(
struct extent_buffer *eb;
rcu_read_lock();
- eb = xa_load(&fs_info->extent_buffers,
- start >> fs_info->sectorsize_bits);
+ eb = radix_tree_lookup(&fs_info->buffer_radix,
+ start >> fs_info->sectorsize_bits);
if (eb && atomic_inc_not_zero(&eb->refs)) {
rcu_read_unlock();
return eb;
@@ -4575,7 +4577,7 @@ static int write_one_subpage_eb(struct extent_buffer *eb,
{
struct btrfs_fs_info *fs_info = eb->fs_info;
struct page *page = eb->pages[0];
- unsigned int write_flags = wbc_to_write_flags(wbc) | REQ_META;
+ blk_opf_t write_flags = wbc_to_write_flags(wbc) | REQ_META;
bool no_dirty_ebs = false;
int ret;
@@ -4620,7 +4622,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
{
u64 disk_bytenr = eb->start;
int i, num_pages;
- unsigned int write_flags = wbc_to_write_flags(wbc) | REQ_META;
+ blk_opf_t write_flags = wbc_to_write_flags(wbc) | REQ_META;
int ret = 0;
prepare_eb_write(eb);
@@ -6129,22 +6131,24 @@ struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
if (!eb)
return ERR_PTR(-ENOMEM);
eb->fs_info = fs_info;
-
- do {
- ret = xa_insert(&fs_info->extent_buffers,
- start >> fs_info->sectorsize_bits,
- eb, GFP_NOFS);
- if (ret == -ENOMEM) {
- exists = ERR_PTR(ret);
+again:
+ ret = radix_tree_preload(GFP_NOFS);
+ if (ret) {
+ exists = ERR_PTR(ret);
+ goto free_eb;
+ }
+ spin_lock(&fs_info->buffer_lock);
+ ret = radix_tree_insert(&fs_info->buffer_radix,
+ start >> fs_info->sectorsize_bits, eb);
+ spin_unlock(&fs_info->buffer_lock);
+ radix_tree_preload_end();
+ if (ret == -EEXIST) {
+ exists = find_extent_buffer(fs_info, start);
+ if (exists)
goto free_eb;
- }
- if (ret == -EBUSY) {
- exists = find_extent_buffer(fs_info, start);
- if (exists)
- goto free_eb;
- }
- } while (ret);
-
+ else
+ goto again;
+ }
check_buffer_tree_ref(eb);
set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags);
@@ -6319,22 +6323,25 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
}
if (uptodate)
set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
-
- do {
- ret = xa_insert(&fs_info->extent_buffers,
- start >> fs_info->sectorsize_bits,
- eb, GFP_NOFS);
- if (ret == -ENOMEM) {
- exists = ERR_PTR(ret);
+again:
+ ret = radix_tree_preload(GFP_NOFS);
+ if (ret) {
+ exists = ERR_PTR(ret);
+ goto free_eb;
+ }
+
+ spin_lock(&fs_info->buffer_lock);
+ ret = radix_tree_insert(&fs_info->buffer_radix,
+ start >> fs_info->sectorsize_bits, eb);
+ spin_unlock(&fs_info->buffer_lock);
+ radix_tree_preload_end();
+ if (ret == -EEXIST) {
+ exists = find_extent_buffer(fs_info, start);
+ if (exists)
goto free_eb;
- }
- if (ret == -EBUSY) {
- exists = find_extent_buffer(fs_info, start);
- if (exists)
- goto free_eb;
- }
- } while (ret);
-
+ else
+ goto again;
+ }
/* add one reference for the tree */
check_buffer_tree_ref(eb);
set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags);
@@ -6379,8 +6386,10 @@ static int release_extent_buffer(struct extent_buffer *eb)
spin_unlock(&eb->refs_lock);
- xa_erase(&fs_info->extent_buffers,
- eb->start >> fs_info->sectorsize_bits);
+ spin_lock(&fs_info->buffer_lock);
+ radix_tree_delete(&fs_info->buffer_radix,
+ eb->start >> fs_info->sectorsize_bits);
+ spin_unlock(&fs_info->buffer_lock);
} else {
spin_unlock(&eb->refs_lock);
}
@@ -7325,25 +7334,42 @@ void memmove_extent_buffer(const struct extent_buffer *dst,
}
}
+#define GANG_LOOKUP_SIZE 16
static struct extent_buffer *get_next_extent_buffer(
struct btrfs_fs_info *fs_info, struct page *page, u64 bytenr)
{
- struct extent_buffer *eb;
- unsigned long index;
+ struct extent_buffer *gang[GANG_LOOKUP_SIZE];
+ struct extent_buffer *found = NULL;
u64 page_start = page_offset(page);
+ u64 cur = page_start;
ASSERT(in_range(bytenr, page_start, PAGE_SIZE));
lockdep_assert_held(&fs_info->buffer_lock);
- xa_for_each_start(&fs_info->extent_buffers, index, eb,
- page_start >> fs_info->sectorsize_bits) {
- if (in_range(eb->start, page_start, PAGE_SIZE))
- return eb;
- else if (eb->start >= page_start + PAGE_SIZE)
- /* Already beyond page end */
- return NULL;
+ while (cur < page_start + PAGE_SIZE) {
+ int ret;
+ int i;
+
+ ret = radix_tree_gang_lookup(&fs_info->buffer_radix,
+ (void **)gang, cur >> fs_info->sectorsize_bits,
+ min_t(unsigned int, GANG_LOOKUP_SIZE,
+ PAGE_SIZE / fs_info->nodesize));
+ if (ret == 0)
+ goto out;
+ for (i = 0; i < ret; i++) {
+ /* Already beyond page end */
+ if (gang[i]->start >= page_start + PAGE_SIZE)
+ goto out;
+ /* Found one */
+ if (gang[i]->start >= bytenr) {
+ found = gang[i];
+ goto out;
+ }
+ }
+ cur = gang[ret - 1]->start + gang[ret - 1]->len;
}
- return NULL;
+out:
+ return found;
}
static int try_release_subpage_extent_buffer(struct page *page)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 0172f75e051a..57915bf2111f 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -485,7 +485,7 @@ struct async_chunk {
struct page *locked_page;
u64 start;
u64 end;
- unsigned int write_flags;
+ blk_opf_t write_flags;
struct list_head extents;
struct cgroup_subsys_state *blkcg_css;
struct btrfs_work work;
@@ -1435,7 +1435,7 @@ static int cow_file_range_async(struct btrfs_inode *inode,
int i;
bool should_compress;
unsigned nofs_flag;
- const unsigned int write_flags = wbc_to_write_flags(wbc);
+ const blk_opf_t write_flags = wbc_to_write_flags(wbc);
unlock_extent(&inode->io_tree, start, end);
@@ -3578,7 +3578,6 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
u64 last_objectid = 0;
int ret = 0, nr_unlink = 0;
- /* Bail out if the cleanup is already running. */
if (test_and_set_bit(BTRFS_ROOT_ORPHAN_CLEANUP, &root->state))
return 0;
@@ -3661,17 +3660,17 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
*
* btrfs_find_orphan_roots() ran before us, which has
* found all deleted roots and loaded them into
- * fs_info->fs_roots. So here we can find if an
+ * fs_info->fs_roots_radix. So here we can find if an
* orphan item corresponds to a deleted root by looking
- * up the root from that xarray.
+ * up the root from that radix tree.
*/
- spin_lock(&fs_info->fs_roots_lock);
- dead_root = xa_load(&fs_info->fs_roots,
- (unsigned long)found_key.objectid);
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ dead_root = radix_tree_lookup(&fs_info->fs_roots_radix,
+ (unsigned long)found_key.objectid);
if (dead_root && btrfs_root_refs(&dead_root->root_item) == 0)
is_dead_root = 1;
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
if (is_dead_root) {
/* prevent this orphan from being found again */
@@ -3911,7 +3910,7 @@ cache_index:
* cache.
*
* This is required for both inode re-read from disk and delayed inode
- * in the delayed_nodes xarray.
+ * in delayed_nodes_tree.
*/
if (BTRFS_I(inode)->last_trans == fs_info->generation)
set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index a5b623ee6fac..c520412d1f86 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1136,7 +1136,7 @@ static int rbio_add_io_sector(struct btrfs_raid_bio *rbio,
unsigned int stripe_nr,
unsigned int sector_nr,
unsigned long bio_max_len,
- unsigned int opf)
+ enum req_op op)
{
const u32 sectorsize = rbio->bioc->fs_info->sectorsize;
struct bio *last = bio_list->tail;
@@ -1181,7 +1181,7 @@ static int rbio_add_io_sector(struct btrfs_raid_bio *rbio,
/* put a new bio on the list */
bio = bio_alloc(stripe->dev->bdev, max(bio_max_len >> PAGE_SHIFT, 1UL),
- opf, GFP_NOFS);
+ op, GFP_NOFS);
bio->bi_iter.bi_sector = disk_start >> 9;
bio->bi_private = rbio;
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index fa56890ff81f..c7dea639a56f 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -10,6 +10,7 @@
#include <linux/mount.h>
#include <linux/xattr.h>
#include <linux/posix_acl_xattr.h>
+#include <linux/radix-tree.h>
#include <linux/vmalloc.h>
#include <linux/string.h>
#include <linux/compat.h>
@@ -127,7 +128,7 @@ struct send_ctx {
struct list_head new_refs;
struct list_head deleted_refs;
- struct xarray name_cache;
+ struct radix_tree_root name_cache;
struct list_head name_cache_list;
int name_cache_size;
@@ -268,13 +269,14 @@ struct orphan_dir_info {
struct name_cache_entry {
struct list_head list;
/*
- * On 32bit kernels, xarray has only 32bit indices, but we need to
- * handle 64bit inums. We use the lower 32bit of the 64bit inum to store
- * it in the tree. If more than one inum would fall into the same entry,
- * we use inum_aliases to store the additional entries. inum_aliases is
- * also used to store entries with the same inum but different generations.
+ * radix_tree has only 32bit entries but we need to handle 64bit inums.
+ * We use the lower 32bit of the 64bit inum to store it in the tree. If
+ * more then one inum would fall into the same entry, we use radix_list
+ * to store the additional entries. radix_list is also used to store
+ * entries where two entries have the same inum but different
+ * generations.
*/
- struct list_head inum_aliases;
+ struct list_head radix_list;
u64 ino;
u64 gen;
u64 parent_ino;
@@ -2024,9 +2026,9 @@ out:
}
/*
- * Insert a name cache entry. On 32bit kernels the xarray index is 32bit,
+ * Insert a name cache entry. On 32bit kernels the radix tree index is 32bit,
* so we need to do some special handling in case we have clashes. This function
- * takes care of this with the help of name_cache_entry::inum_aliases.
+ * takes care of this with the help of name_cache_entry::radix_list.
* In case of error, nce is kfreed.
*/
static int name_cache_insert(struct send_ctx *sctx,
@@ -2035,7 +2037,8 @@ static int name_cache_insert(struct send_ctx *sctx,
int ret = 0;
struct list_head *nce_head;
- nce_head = xa_load(&sctx->name_cache, (unsigned long)nce->ino);
+ nce_head = radix_tree_lookup(&sctx->name_cache,
+ (unsigned long)nce->ino);
if (!nce_head) {
nce_head = kmalloc(sizeof(*nce_head), GFP_KERNEL);
if (!nce_head) {
@@ -2044,14 +2047,14 @@ static int name_cache_insert(struct send_ctx *sctx,
}
INIT_LIST_HEAD(nce_head);
- ret = xa_insert(&sctx->name_cache, nce->ino, nce_head, GFP_KERNEL);
+ ret = radix_tree_insert(&sctx->name_cache, nce->ino, nce_head);
if (ret < 0) {
kfree(nce_head);
kfree(nce);
return ret;
}
}
- list_add_tail(&nce->inum_aliases, nce_head);
+ list_add_tail(&nce->radix_list, nce_head);
list_add_tail(&nce->list, &sctx->name_cache_list);
sctx->name_cache_size++;
@@ -2063,14 +2066,15 @@ static void name_cache_delete(struct send_ctx *sctx,
{
struct list_head *nce_head;
- nce_head = xa_load(&sctx->name_cache, (unsigned long)nce->ino);
+ nce_head = radix_tree_lookup(&sctx->name_cache,
+ (unsigned long)nce->ino);
if (!nce_head) {
btrfs_err(sctx->send_root->fs_info,
"name_cache_delete lookup failed ino %llu cache size %d, leaking memory",
nce->ino, sctx->name_cache_size);
}
- list_del(&nce->inum_aliases);
+ list_del(&nce->radix_list);
list_del(&nce->list);
sctx->name_cache_size--;
@@ -2078,7 +2082,7 @@ static void name_cache_delete(struct send_ctx *sctx,
* We may not get to the final release of nce_head if the lookup fails
*/
if (nce_head && list_empty(nce_head)) {
- xa_erase(&sctx->name_cache, (unsigned long)nce->ino);
+ radix_tree_delete(&sctx->name_cache, (unsigned long)nce->ino);
kfree(nce_head);
}
}
@@ -2089,11 +2093,11 @@ static struct name_cache_entry *name_cache_search(struct send_ctx *sctx,
struct list_head *nce_head;
struct name_cache_entry *cur;
- nce_head = xa_load(&sctx->name_cache, (unsigned long)ino);
+ nce_head = radix_tree_lookup(&sctx->name_cache, (unsigned long)ino);
if (!nce_head)
return NULL;
- list_for_each_entry(cur, nce_head, inum_aliases) {
+ list_for_each_entry(cur, nce_head, radix_list) {
if (cur->ino == ino && cur->gen == gen)
return cur;
}
@@ -7518,7 +7522,7 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg)
INIT_LIST_HEAD(&sctx->new_refs);
INIT_LIST_HEAD(&sctx->deleted_refs);
- xa_init_flags(&sctx->name_cache, GFP_KERNEL);
+ INIT_RADIX_TREE(&sctx->name_cache, GFP_KERNEL);
INIT_LIST_HEAD(&sctx->name_cache_list);
sctx->flags = arg->flags;
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index 1591bfa55bcc..d8e56edd6991 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -150,8 +150,8 @@ struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(u32 nodesize, u32 sectorsize)
void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info)
{
- unsigned long index;
- struct extent_buffer *eb;
+ struct radix_tree_iter iter;
+ void **slot;
struct btrfs_device *dev, *tmp;
if (!fs_info)
@@ -163,9 +163,25 @@ void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info)
test_mnt->mnt_sb->s_fs_info = NULL;
- xa_for_each(&fs_info->extent_buffers, index, eb) {
+ spin_lock(&fs_info->buffer_lock);
+ radix_tree_for_each_slot(slot, &fs_info->buffer_radix, &iter, 0) {
+ struct extent_buffer *eb;
+
+ eb = radix_tree_deref_slot_protected(slot, &fs_info->buffer_lock);
+ if (!eb)
+ continue;
+ /* Shouldn't happen but that kind of thinking creates CVE's */
+ if (radix_tree_exception(eb)) {
+ if (radix_tree_deref_retry(eb))
+ slot = radix_tree_iter_retry(&iter);
+ continue;
+ }
+ slot = radix_tree_iter_resume(slot, &iter);
+ spin_unlock(&fs_info->buffer_lock);
free_extent_buffer_stale(eb);
+ spin_lock(&fs_info->buffer_lock);
}
+ spin_unlock(&fs_info->buffer_lock);
btrfs_mapping_tree_free(&fs_info->mapping_tree);
list_for_each_entry_safe(dev, tmp, &fs_info->fs_devices->devices,
@@ -186,7 +202,7 @@ void btrfs_free_dummy_root(struct btrfs_root *root)
if (!root)
return;
/* Will be freed by btrfs_free_fs_roots */
- if (WARN_ON(test_bit(BTRFS_ROOT_REGISTERED, &root->state)))
+ if (WARN_ON(test_bit(BTRFS_ROOT_IN_RADIX, &root->state)))
return;
btrfs_global_root_delete(root);
btrfs_put_root(root);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 06c0a958d114..875b801ab3d7 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -23,7 +23,7 @@
#include "space-info.h"
#include "zoned.h"
-#define BTRFS_ROOT_TRANS_TAG XA_MARK_0
+#define BTRFS_ROOT_TRANS_TAG 0
/*
* Transaction states and transitions
@@ -437,15 +437,15 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans,
*/
smp_wmb();
- spin_lock(&fs_info->fs_roots_lock);
+ spin_lock(&fs_info->fs_roots_radix_lock);
if (root->last_trans == trans->transid && !force) {
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
return 0;
}
- xa_set_mark(&fs_info->fs_roots,
- (unsigned long)root->root_key.objectid,
- BTRFS_ROOT_TRANS_TAG);
- spin_unlock(&fs_info->fs_roots_lock);
+ radix_tree_tag_set(&fs_info->fs_roots_radix,
+ (unsigned long)root->root_key.objectid,
+ BTRFS_ROOT_TRANS_TAG);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
root->last_trans = trans->transid;
/* this is pretty tricky. We don't want to
@@ -487,9 +487,11 @@ void btrfs_add_dropped_root(struct btrfs_trans_handle *trans,
spin_unlock(&cur_trans->dropped_roots_lock);
/* Make sure we don't try to update the root at commit time */
- xa_clear_mark(&fs_info->fs_roots,
- (unsigned long)root->root_key.objectid,
- BTRFS_ROOT_TRANS_TAG);
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ radix_tree_tag_clear(&fs_info->fs_roots_radix,
+ (unsigned long)root->root_key.objectid,
+ BTRFS_ROOT_TRANS_TAG);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
}
int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
@@ -1402,8 +1404,9 @@ void btrfs_add_dead_root(struct btrfs_root *root)
static noinline int commit_fs_roots(struct btrfs_trans_handle *trans)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
- struct btrfs_root *root;
- unsigned long index;
+ struct btrfs_root *gang[8];
+ int i;
+ int ret;
/*
* At this point no one can be using this transaction to modify any tree
@@ -1411,46 +1414,57 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans)
*/
ASSERT(trans->transaction->state == TRANS_STATE_COMMIT_DOING);
- spin_lock(&fs_info->fs_roots_lock);
- xa_for_each_marked(&fs_info->fs_roots, index, root, BTRFS_ROOT_TRANS_TAG) {
- int ret;
-
- /*
- * At this point we can neither have tasks logging inodes
- * from a root nor trying to commit a log tree.
- */
- ASSERT(atomic_read(&root->log_writers) == 0);
- ASSERT(atomic_read(&root->log_commit[0]) == 0);
- ASSERT(atomic_read(&root->log_commit[1]) == 0);
-
- xa_clear_mark(&fs_info->fs_roots,
- (unsigned long)root->root_key.objectid,
- BTRFS_ROOT_TRANS_TAG);
- spin_unlock(&fs_info->fs_roots_lock);
-
- btrfs_free_log(trans, root);
- ret = btrfs_update_reloc_root(trans, root);
- if (ret)
- return ret;
-
- /* See comments in should_cow_block() */
- clear_bit(BTRFS_ROOT_FORCE_COW, &root->state);
- smp_mb__after_atomic();
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ while (1) {
+ ret = radix_tree_gang_lookup_tag(&fs_info->fs_roots_radix,
+ (void **)gang, 0,
+ ARRAY_SIZE(gang),
+ BTRFS_ROOT_TRANS_TAG);
+ if (ret == 0)
+ break;
+ for (i = 0; i < ret; i++) {
+ struct btrfs_root *root = gang[i];
+ int ret2;
+
+ /*
+ * At this point we can neither have tasks logging inodes
+ * from a root nor trying to commit a log tree.
+ */
+ ASSERT(atomic_read(&root->log_writers) == 0);
+ ASSERT(atomic_read(&root->log_commit[0]) == 0);
+ ASSERT(atomic_read(&root->log_commit[1]) == 0);
+
+ radix_tree_tag_clear(&fs_info->fs_roots_radix,
+ (unsigned long)root->root_key.objectid,
+ BTRFS_ROOT_TRANS_TAG);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
+
+ btrfs_free_log(trans, root);
+ ret2 = btrfs_update_reloc_root(trans, root);
+ if (ret2)
+ return ret2;
+
+ /* see comments in should_cow_block() */
+ clear_bit(BTRFS_ROOT_FORCE_COW, &root->state);
+ smp_mb__after_atomic();
+
+ if (root->commit_root != root->node) {
+ list_add_tail(&root->dirty_list,
+ &trans->transaction->switch_commits);
+ btrfs_set_root_node(&root->root_item,
+ root->node);
+ }
- if (root->commit_root != root->node) {
- list_add_tail(&root->dirty_list,
- &trans->transaction->switch_commits);
- btrfs_set_root_node(&root->root_item, root->node);
+ ret2 = btrfs_update_root(trans, fs_info->tree_root,
+ &root->root_key,
+ &root->root_item);
+ if (ret2)
+ return ret2;
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ btrfs_qgroup_free_meta_all_pertrans(root);
}
-
- ret = btrfs_update_root(trans, fs_info->tree_root,
- &root->root_key, &root->root_item);
- if (ret)
- return ret;
- spin_lock(&fs_info->fs_roots_lock);
- btrfs_qgroup_free_meta_all_pertrans(root);
}
- spin_unlock(&fs_info->fs_roots_lock);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
return 0;
}
diff --git a/fs/buffer.c b/fs/buffer.c
index 898c7f301b1b..82de136b83bb 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -52,7 +52,7 @@
#include "internal.h"
static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
-static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
+static int submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
struct writeback_control *wbc);
#define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers)
@@ -562,7 +562,7 @@ void write_boundary_block(struct block_device *bdev,
struct buffer_head *bh = __find_get_block(bdev, bblock + 1, blocksize);
if (bh) {
if (buffer_dirty(bh))
- ll_rw_block(REQ_OP_WRITE, 0, 1, &bh);
+ ll_rw_block(REQ_OP_WRITE, 1, &bh);
put_bh(bh);
}
}
@@ -1174,7 +1174,7 @@ static struct buffer_head *__bread_slow(struct buffer_head *bh)
} else {
get_bh(bh);
bh->b_end_io = end_buffer_read_sync;
- submit_bh(REQ_OP_READ, 0, bh);
+ submit_bh(REQ_OP_READ, bh);
wait_on_buffer(bh);
if (buffer_uptodate(bh))
return bh;
@@ -1342,7 +1342,7 @@ void __breadahead(struct block_device *bdev, sector_t block, unsigned size)
{
struct buffer_head *bh = __getblk(bdev, block, size);
if (likely(bh)) {
- ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, &bh);
+ ll_rw_block(REQ_OP_READ | REQ_RAHEAD, 1, &bh);
brelse(bh);
}
}
@@ -1353,7 +1353,7 @@ void __breadahead_gfp(struct block_device *bdev, sector_t block, unsigned size,
{
struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp);
if (likely(bh)) {
- ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, &bh);
+ ll_rw_block(REQ_OP_READ | REQ_RAHEAD, 1, &bh);
brelse(bh);
}
}
@@ -1716,7 +1716,7 @@ int __block_write_full_page(struct inode *inode, struct page *page,
struct buffer_head *bh, *head;
unsigned int blocksize, bbits;
int nr_underway = 0;
- int write_flags = wbc_to_write_flags(wbc);
+ blk_opf_t write_flags = wbc_to_write_flags(wbc);
head = create_page_buffers(page, inode,
(1 << BH_Dirty)|(1 << BH_Uptodate));
@@ -1804,7 +1804,7 @@ int __block_write_full_page(struct inode *inode, struct page *page,
do {
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
- submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, wbc);
+ submit_bh_wbc(REQ_OP_WRITE | write_flags, bh, wbc);
nr_underway++;
}
bh = next;
@@ -1858,7 +1858,7 @@ recover:
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
clear_buffer_dirty(bh);
- submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, wbc);
+ submit_bh_wbc(REQ_OP_WRITE | write_flags, bh, wbc);
nr_underway++;
}
bh = next;
@@ -2033,7 +2033,7 @@ int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len,
if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
!buffer_unwritten(bh) &&
(block_start < from || block_end > to)) {
- ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+ ll_rw_block(REQ_OP_READ, 1, &bh);
*wait_bh++=bh;
}
}
@@ -2334,7 +2334,7 @@ int block_read_full_folio(struct folio *folio, get_block_t *get_block)
if (buffer_uptodate(bh))
end_buffer_async_read(bh, 1);
else
- submit_bh(REQ_OP_READ, 0, bh);
+ submit_bh(REQ_OP_READ, bh);
}
return 0;
}
@@ -2665,7 +2665,7 @@ int nobh_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
if (block_start < from || block_end > to) {
lock_buffer(bh);
bh->b_end_io = end_buffer_read_nobh;
- submit_bh(REQ_OP_READ, 0, bh);
+ submit_bh(REQ_OP_READ, bh);
nr_reads++;
}
}
@@ -2915,7 +2915,7 @@ int block_truncate_page(struct address_space *mapping,
if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh)) {
err = -EIO;
- ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+ ll_rw_block(REQ_OP_READ, 1, &bh);
wait_on_buffer(bh);
/* Uhhuh. Read error. Complain and punt. */
if (!buffer_uptodate(bh))
@@ -2994,9 +2994,10 @@ static void end_bio_bh_io_sync(struct bio *bio)
bio_put(bio);
}
-static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
+static int submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
struct writeback_control *wbc)
{
+ const enum req_op op = opf & REQ_OP_MASK;
struct bio *bio;
BUG_ON(!buffer_locked(bh));
@@ -3012,11 +3013,11 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
clear_buffer_write_io_error(bh);
if (buffer_meta(bh))
- op_flags |= REQ_META;
+ opf |= REQ_META;
if (buffer_prio(bh))
- op_flags |= REQ_PRIO;
+ opf |= REQ_PRIO;
- bio = bio_alloc(bh->b_bdev, 1, op | op_flags, GFP_NOIO);
+ bio = bio_alloc(bh->b_bdev, 1, opf, GFP_NOIO);
fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO);
@@ -3040,22 +3041,21 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
return 0;
}
-int submit_bh(int op, int op_flags, struct buffer_head *bh)
+int submit_bh(blk_opf_t opf, struct buffer_head *bh)
{
- return submit_bh_wbc(op, op_flags, bh, NULL);
+ return submit_bh_wbc(opf, bh, NULL);
}
EXPORT_SYMBOL(submit_bh);
/**
* ll_rw_block: low-level access to block devices (DEPRECATED)
- * @op: whether to %READ or %WRITE
- * @op_flags: req_flag_bits
+ * @opf: block layer request operation and flags.
* @nr: number of &struct buffer_heads in the array
* @bhs: array of pointers to &struct buffer_head
*
* ll_rw_block() takes an array of pointers to &struct buffer_heads, and
* requests an I/O operation on them, either a %REQ_OP_READ or a %REQ_OP_WRITE.
- * @op_flags contains flags modifying the detailed I/O behavior, most notably
+ * @opf contains flags modifying the detailed I/O behavior, most notably
* %REQ_RAHEAD.
*
* This function drops any buffer that it cannot get a lock on (with the
@@ -3072,8 +3072,9 @@ EXPORT_SYMBOL(submit_bh);
* All of the buffers must be for the same device, and must also be a
* multiple of the current approved size for the device.
*/
-void ll_rw_block(int op, int op_flags, int nr, struct buffer_head *bhs[])
+void ll_rw_block(const blk_opf_t opf, int nr, struct buffer_head *bhs[])
{
+ const enum req_op op = opf & REQ_OP_MASK;
int i;
for (i = 0; i < nr; i++) {
@@ -3081,18 +3082,18 @@ void ll_rw_block(int op, int op_flags, int nr, struct buffer_head *bhs[])
if (!trylock_buffer(bh))
continue;
- if (op == WRITE) {
+ if (op == REQ_OP_WRITE) {
if (test_clear_buffer_dirty(bh)) {
bh->b_end_io = end_buffer_write_sync;
get_bh(bh);
- submit_bh(op, op_flags, bh);
+ submit_bh(opf, bh);
continue;
}
} else {
if (!buffer_uptodate(bh)) {
bh->b_end_io = end_buffer_read_sync;
get_bh(bh);
- submit_bh(op, op_flags, bh);
+ submit_bh(opf, bh);
continue;
}
}
@@ -3101,7 +3102,7 @@ void ll_rw_block(int op, int op_flags, int nr, struct buffer_head *bhs[])
}
EXPORT_SYMBOL(ll_rw_block);
-void write_dirty_buffer(struct buffer_head *bh, int op_flags)
+void write_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags)
{
lock_buffer(bh);
if (!test_clear_buffer_dirty(bh)) {
@@ -3110,7 +3111,7 @@ void write_dirty_buffer(struct buffer_head *bh, int op_flags)
}
bh->b_end_io = end_buffer_write_sync;
get_bh(bh);
- submit_bh(REQ_OP_WRITE, op_flags, bh);
+ submit_bh(REQ_OP_WRITE | op_flags, bh);
}
EXPORT_SYMBOL(write_dirty_buffer);
@@ -3119,7 +3120,7 @@ EXPORT_SYMBOL(write_dirty_buffer);
* and then start new I/O and then wait upon it. The caller must have a ref on
* the buffer_head.
*/
-int __sync_dirty_buffer(struct buffer_head *bh, int op_flags)
+int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags)
{
int ret = 0;
@@ -3137,7 +3138,7 @@ int __sync_dirty_buffer(struct buffer_head *bh, int op_flags)
get_bh(bh);
bh->b_end_io = end_buffer_write_sync;
- ret = submit_bh(REQ_OP_WRITE, op_flags, bh);
+ ret = submit_bh(REQ_OP_WRITE | op_flags, bh);
wait_on_buffer(bh);
if (!ret && !buffer_uptodate(bh))
ret = -EIO;
@@ -3365,7 +3366,7 @@ int bh_submit_read(struct buffer_head *bh)
get_bh(bh);
bh->b_end_io = end_buffer_read_sync;
- submit_bh(REQ_OP_READ, 0, bh);
+ submit_bh(REQ_OP_READ, bh);
wait_on_buffer(bh);
if (buffer_uptodate(bh))
return 0;
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 840752006f60..94b71440c332 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -117,8 +117,7 @@ struct dio_submit {
/* dio_state communicated between submission path and end_io */
struct dio {
int flags; /* doesn't change */
- int op;
- int op_flags;
+ blk_opf_t opf; /* request operation type and flags */
struct gendisk *bio_disk;
struct inode *inode;
loff_t i_size; /* i_size when submitted */
@@ -167,12 +166,13 @@ static inline unsigned dio_pages_present(struct dio_submit *sdio)
*/
static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio)
{
+ const enum req_op dio_op = dio->opf & REQ_OP_MASK;
ssize_t ret;
ret = iov_iter_get_pages(sdio->iter, dio->pages, LONG_MAX, DIO_PAGES,
&sdio->from);
- if (ret < 0 && sdio->blocks_available && (dio->op == REQ_OP_WRITE)) {
+ if (ret < 0 && sdio->blocks_available && dio_op == REQ_OP_WRITE) {
struct page *page = ZERO_PAGE(0);
/*
* A memory fault, but the filesystem has some outstanding
@@ -234,6 +234,7 @@ static inline struct page *dio_get_page(struct dio *dio,
*/
static ssize_t dio_complete(struct dio *dio, ssize_t ret, unsigned int flags)
{
+ const enum req_op dio_op = dio->opf & REQ_OP_MASK;
loff_t offset = dio->iocb->ki_pos;
ssize_t transferred = 0;
int err;
@@ -251,7 +252,7 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, unsigned int flags)
transferred = dio->result;
/* Check for short read case */
- if ((dio->op == REQ_OP_READ) &&
+ if (dio_op == REQ_OP_READ &&
((offset + transferred) > dio->i_size))
transferred = dio->i_size - offset;
/* ignore EFAULT if some IO has been done */
@@ -286,7 +287,7 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, unsigned int flags)
* zeros from unwritten extents.
*/
if (flags & DIO_COMPLETE_INVALIDATE &&
- ret > 0 && dio->op == REQ_OP_WRITE &&
+ ret > 0 && dio_op == REQ_OP_WRITE &&
dio->inode->i_mapping->nrpages) {
err = invalidate_inode_pages2_range(dio->inode->i_mapping,
offset >> PAGE_SHIFT,
@@ -305,7 +306,7 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, unsigned int flags)
*/
dio->iocb->ki_pos += transferred;
- if (ret > 0 && dio->op == REQ_OP_WRITE)
+ if (ret > 0 && dio_op == REQ_OP_WRITE)
ret = generic_write_sync(dio->iocb, ret);
dio->iocb->ki_complete(dio->iocb, ret);
}
@@ -329,6 +330,7 @@ static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio);
static void dio_bio_end_aio(struct bio *bio)
{
struct dio *dio = bio->bi_private;
+ const enum req_op dio_op = dio->opf & REQ_OP_MASK;
unsigned long remaining;
unsigned long flags;
bool defer_completion = false;
@@ -353,7 +355,7 @@ static void dio_bio_end_aio(struct bio *bio)
*/
if (dio->result)
defer_completion = dio->defer_completion ||
- (dio->op == REQ_OP_WRITE &&
+ (dio_op == REQ_OP_WRITE &&
dio->inode->i_mapping->nrpages);
if (defer_completion) {
INIT_WORK(&dio->complete_work, dio_aio_complete_work);
@@ -396,7 +398,7 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio,
* bio_alloc() is guaranteed to return a bio when allowed to sleep and
* we request a valid number of vectors.
*/
- bio = bio_alloc(bdev, nr_vecs, dio->op | dio->op_flags, GFP_KERNEL);
+ bio = bio_alloc(bdev, nr_vecs, dio->opf, GFP_KERNEL);
bio->bi_iter.bi_sector = first_sector;
if (dio->is_async)
bio->bi_end_io = dio_bio_end_aio;
@@ -415,6 +417,7 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio,
*/
static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio)
{
+ const enum req_op dio_op = dio->opf & REQ_OP_MASK;
struct bio *bio = sdio->bio;
unsigned long flags;
@@ -426,7 +429,7 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio)
dio->refcount++;
spin_unlock_irqrestore(&dio->bio_lock, flags);
- if (dio->is_async && dio->op == REQ_OP_READ && dio->should_dirty)
+ if (dio->is_async && dio_op == REQ_OP_READ && dio->should_dirty)
bio_set_pages_dirty(bio);
dio->bio_disk = bio->bi_bdev->bd_disk;
@@ -492,7 +495,8 @@ static struct bio *dio_await_one(struct dio *dio)
static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio)
{
blk_status_t err = bio->bi_status;
- bool should_dirty = dio->op == REQ_OP_READ && dio->should_dirty;
+ const enum req_op dio_op = dio->opf & REQ_OP_MASK;
+ bool should_dirty = dio_op == REQ_OP_READ && dio->should_dirty;
if (err) {
if (err == BLK_STS_AGAIN && (bio->bi_opf & REQ_NOWAIT))
@@ -619,6 +623,7 @@ static int dio_set_defer_completion(struct dio *dio)
static int get_more_blocks(struct dio *dio, struct dio_submit *sdio,
struct buffer_head *map_bh)
{
+ const enum req_op dio_op = dio->opf & REQ_OP_MASK;
int ret;
sector_t fs_startblk; /* Into file, in filesystem-sized blocks */
sector_t fs_endblk; /* Into file, in filesystem-sized blocks */
@@ -653,7 +658,7 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio,
* which may decide to handle it or also return an unmapped
* buffer head.
*/
- create = dio->op == REQ_OP_WRITE;
+ create = dio_op == REQ_OP_WRITE;
if (dio->flags & DIO_SKIP_HOLES) {
i_size = i_size_read(dio->inode);
if (i_size && fs_startblk <= (i_size - 1) >> i_blkbits)
@@ -801,10 +806,11 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page,
unsigned offset, unsigned len, sector_t blocknr,
struct buffer_head *map_bh)
{
+ const enum req_op dio_op = dio->opf & REQ_OP_MASK;
int ret = 0;
int boundary = sdio->boundary; /* dio_send_cur_page may clear it */
- if (dio->op == REQ_OP_WRITE) {
+ if (dio_op == REQ_OP_WRITE) {
/*
* Read accounting is performed in submit_bio()
*/
@@ -917,6 +923,7 @@ static inline void dio_zero_block(struct dio *dio, struct dio_submit *sdio,
static int do_direct_IO(struct dio *dio, struct dio_submit *sdio,
struct buffer_head *map_bh)
{
+ const enum req_op dio_op = dio->opf & REQ_OP_MASK;
const unsigned blkbits = sdio->blkbits;
const unsigned i_blkbits = blkbits + sdio->blkfactor;
int ret = 0;
@@ -992,7 +999,7 @@ do_holes:
loff_t i_size_aligned;
/* AKPM: eargh, -ENOTBLK is a hack */
- if (dio->op == REQ_OP_WRITE) {
+ if (dio_op == REQ_OP_WRITE) {
put_page(page);
return -ENOTBLK;
}
@@ -1196,12 +1203,11 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
dio->inode = inode;
if (iov_iter_rw(iter) == WRITE) {
- dio->op = REQ_OP_WRITE;
- dio->op_flags = REQ_SYNC | REQ_IDLE;
+ dio->opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
if (iocb->ki_flags & IOCB_NOWAIT)
- dio->op_flags |= REQ_NOWAIT;
+ dio->opf |= REQ_NOWAIT;
} else {
- dio->op = REQ_OP_READ;
+ dio->opf = REQ_OP_READ;
}
/*
diff --git a/fs/dlm/Kconfig b/fs/dlm/Kconfig
index ee92634196a8..1105ce3c80cb 100644
--- a/fs/dlm/Kconfig
+++ b/fs/dlm/Kconfig
@@ -9,6 +9,15 @@ menuconfig DLM
A general purpose distributed lock manager for kernel or userspace
applications.
+config DLM_DEPRECATED_API
+ bool "DLM deprecated API"
+ depends on DLM
+ help
+ Enables deprecated DLM timeout features that will be removed in
+ later Linux kernel releases.
+
+ If you are unsure, say N.
+
config DLM_DEBUG
bool "DLM debugging"
depends on DLM
diff --git a/fs/dlm/Makefile b/fs/dlm/Makefile
index 3545fdafc6fb..71dab733cf9a 100644
--- a/fs/dlm/Makefile
+++ b/fs/dlm/Makefile
@@ -9,7 +9,6 @@ dlm-y := ast.o \
member.o \
memory.o \
midcomms.o \
- netlink.o \
lowcomms.o \
plock.o \
rcom.o \
@@ -18,5 +17,6 @@ dlm-y := ast.o \
requestqueue.o \
user.o \
util.o
+dlm-$(CONFIG_DLM_DEPRECATED_API) += netlink.o
dlm-$(CONFIG_DLM_DEBUG) += debug_fs.o
diff --git a/fs/dlm/ast.c b/fs/dlm/ast.c
index bfac462dd3e8..19ef136f9e4f 100644
--- a/fs/dlm/ast.c
+++ b/fs/dlm/ast.c
@@ -255,13 +255,13 @@ void dlm_callback_work(struct work_struct *work)
if (callbacks[i].flags & DLM_CB_SKIP) {
continue;
} else if (callbacks[i].flags & DLM_CB_BAST) {
- bastfn(lkb->lkb_astparam, callbacks[i].mode);
trace_dlm_bast(ls, lkb, callbacks[i].mode);
+ bastfn(lkb->lkb_astparam, callbacks[i].mode);
} else if (callbacks[i].flags & DLM_CB_CAST) {
lkb->lkb_lksb->sb_status = callbacks[i].sb_status;
lkb->lkb_lksb->sb_flags = callbacks[i].sb_flags;
+ trace_dlm_ast(ls, lkb);
castfn(lkb->lkb_astparam);
- trace_dlm_ast(ls, lkb, lkb->lkb_lksb);
}
}
diff --git a/fs/dlm/config.c b/fs/dlm/config.c
index 42eee2783756..ac8b62106ce0 100644
--- a/fs/dlm/config.c
+++ b/fs/dlm/config.c
@@ -75,8 +75,9 @@ struct dlm_cluster {
unsigned int cl_log_info;
unsigned int cl_protocol;
unsigned int cl_mark;
+#ifdef CONFIG_DLM_DEPRECATED_API
unsigned int cl_timewarn_cs;
- unsigned int cl_waitwarn_us;
+#endif
unsigned int cl_new_rsb_count;
unsigned int cl_recover_callbacks;
char cl_cluster_name[DLM_LOCKSPACE_LEN];
@@ -102,8 +103,9 @@ enum {
CLUSTER_ATTR_LOG_INFO,
CLUSTER_ATTR_PROTOCOL,
CLUSTER_ATTR_MARK,
+#ifdef CONFIG_DLM_DEPRECATED_API
CLUSTER_ATTR_TIMEWARN_CS,
- CLUSTER_ATTR_WAITWARN_US,
+#endif
CLUSTER_ATTR_NEW_RSB_COUNT,
CLUSTER_ATTR_RECOVER_CALLBACKS,
CLUSTER_ATTR_CLUSTER_NAME,
@@ -224,8 +226,9 @@ CLUSTER_ATTR(log_debug, NULL);
CLUSTER_ATTR(log_info, NULL);
CLUSTER_ATTR(protocol, dlm_check_protocol_and_dlm_running);
CLUSTER_ATTR(mark, NULL);
+#ifdef CONFIG_DLM_DEPRECATED_API
CLUSTER_ATTR(timewarn_cs, dlm_check_zero);
-CLUSTER_ATTR(waitwarn_us, NULL);
+#endif
CLUSTER_ATTR(new_rsb_count, NULL);
CLUSTER_ATTR(recover_callbacks, NULL);
@@ -240,8 +243,9 @@ static struct configfs_attribute *cluster_attrs[] = {
[CLUSTER_ATTR_LOG_INFO] = &cluster_attr_log_info,
[CLUSTER_ATTR_PROTOCOL] = &cluster_attr_protocol,
[CLUSTER_ATTR_MARK] = &cluster_attr_mark,
+#ifdef CONFIG_DLM_DEPRECATED_API
[CLUSTER_ATTR_TIMEWARN_CS] = &cluster_attr_timewarn_cs,
- [CLUSTER_ATTR_WAITWARN_US] = &cluster_attr_waitwarn_us,
+#endif
[CLUSTER_ATTR_NEW_RSB_COUNT] = &cluster_attr_new_rsb_count,
[CLUSTER_ATTR_RECOVER_CALLBACKS] = &cluster_attr_recover_callbacks,
[CLUSTER_ATTR_CLUSTER_NAME] = &cluster_attr_cluster_name,
@@ -432,8 +436,9 @@ static struct config_group *make_cluster(struct config_group *g,
cl->cl_log_debug = dlm_config.ci_log_debug;
cl->cl_log_info = dlm_config.ci_log_info;
cl->cl_protocol = dlm_config.ci_protocol;
+#ifdef CONFIG_DLM_DEPRECATED_API
cl->cl_timewarn_cs = dlm_config.ci_timewarn_cs;
- cl->cl_waitwarn_us = dlm_config.ci_waitwarn_us;
+#endif
cl->cl_new_rsb_count = dlm_config.ci_new_rsb_count;
cl->cl_recover_callbacks = dlm_config.ci_recover_callbacks;
memcpy(cl->cl_cluster_name, dlm_config.ci_cluster_name,
@@ -954,8 +959,9 @@ int dlm_our_addr(struct sockaddr_storage *addr, int num)
#define DEFAULT_LOG_INFO 1
#define DEFAULT_PROTOCOL DLM_PROTO_TCP
#define DEFAULT_MARK 0
+#ifdef CONFIG_DLM_DEPRECATED_API
#define DEFAULT_TIMEWARN_CS 500 /* 5 sec = 500 centiseconds */
-#define DEFAULT_WAITWARN_US 0
+#endif
#define DEFAULT_NEW_RSB_COUNT 128
#define DEFAULT_RECOVER_CALLBACKS 0
#define DEFAULT_CLUSTER_NAME ""
@@ -971,8 +977,9 @@ struct dlm_config_info dlm_config = {
.ci_log_info = DEFAULT_LOG_INFO,
.ci_protocol = DEFAULT_PROTOCOL,
.ci_mark = DEFAULT_MARK,
+#ifdef CONFIG_DLM_DEPRECATED_API
.ci_timewarn_cs = DEFAULT_TIMEWARN_CS,
- .ci_waitwarn_us = DEFAULT_WAITWARN_US,
+#endif
.ci_new_rsb_count = DEFAULT_NEW_RSB_COUNT,
.ci_recover_callbacks = DEFAULT_RECOVER_CALLBACKS,
.ci_cluster_name = DEFAULT_CLUSTER_NAME
diff --git a/fs/dlm/config.h b/fs/dlm/config.h
index df92b0a07fc6..55c5f2c13ebd 100644
--- a/fs/dlm/config.h
+++ b/fs/dlm/config.h
@@ -37,8 +37,9 @@ struct dlm_config_info {
int ci_log_info;
int ci_protocol;
int ci_mark;
+#ifdef CONFIG_DLM_DEPRECATED_API
int ci_timewarn_cs;
- int ci_waitwarn_us;
+#endif
int ci_new_rsb_count;
int ci_recover_callbacks;
char ci_cluster_name[DLM_LOCKSPACE_LEN];
diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h
index 776c3ed519f0..8aca8085d24e 100644
--- a/fs/dlm/dlm_internal.h
+++ b/fs/dlm/dlm_internal.h
@@ -145,7 +145,9 @@ struct dlm_args {
void (*bastfn) (void *astparam, int mode);
int mode;
struct dlm_lksb *lksb;
+#ifdef CONFIG_DLM_DEPRECATED_API
unsigned long timeout;
+#endif
};
@@ -203,10 +205,20 @@ struct dlm_args {
#define DLM_IFL_OVERLAP_UNLOCK 0x00080000
#define DLM_IFL_OVERLAP_CANCEL 0x00100000
#define DLM_IFL_ENDOFLIFE 0x00200000
+#ifdef CONFIG_DLM_DEPRECATED_API
#define DLM_IFL_WATCH_TIMEWARN 0x00400000
#define DLM_IFL_TIMEOUT_CANCEL 0x00800000
+#endif
#define DLM_IFL_DEADLOCK_CANCEL 0x01000000
#define DLM_IFL_STUB_MS 0x02000000 /* magic number for m_flags */
+/* least significant 2 bytes are message changed, they are full transmitted
+ * but at receive side only the 2 bytes LSB will be set.
+ *
+ * Even wireshark dlm dissector does only evaluate the lower bytes and note
+ * that they may not be used on transceiver side, we assume the higher bytes
+ * are for internal use or reserved so long they are not parsed on receiver
+ * side.
+ */
#define DLM_IFL_USER 0x00000001
#define DLM_IFL_ORPHAN 0x00000002
@@ -249,10 +261,12 @@ struct dlm_lkb {
struct list_head lkb_rsb_lookup; /* waiting for rsb lookup */
struct list_head lkb_wait_reply; /* waiting for remote reply */
struct list_head lkb_ownqueue; /* list of locks for a process */
- struct list_head lkb_time_list;
ktime_t lkb_timestamp;
- ktime_t lkb_wait_time;
+
+#ifdef CONFIG_DLM_DEPRECATED_API
+ struct list_head lkb_time_list;
unsigned long lkb_timeout_cs;
+#endif
struct mutex lkb_cb_mutex;
struct work_struct lkb_cb_work;
@@ -568,8 +582,10 @@ struct dlm_ls {
struct mutex ls_orphans_mutex;
struct list_head ls_orphans;
+#ifdef CONFIG_DLM_DEPRECATED_API
struct mutex ls_timeout_mutex;
struct list_head ls_timeout;
+#endif
spinlock_t ls_new_rsb_spin;
int ls_new_rsb_count;
@@ -606,8 +622,8 @@ struct dlm_ls {
wait_queue_head_t ls_uevent_wait; /* user part of join/leave */
int ls_uevent_result;
- struct completion ls_members_done;
- int ls_members_result;
+ struct completion ls_recovery_done;
+ int ls_recovery_result;
struct miscdevice ls_device;
@@ -688,7 +704,9 @@ struct dlm_ls {
#define LSFL_RCOM_READY 5
#define LSFL_RCOM_WAIT 6
#define LSFL_UEVENT_WAIT 7
+#ifdef CONFIG_DLM_DEPRECATED_API
#define LSFL_TIMEWARN 8
+#endif
#define LSFL_CB_DELAY 9
#define LSFL_NODIR 10
@@ -741,9 +759,15 @@ static inline int dlm_no_directory(struct dlm_ls *ls)
return test_bit(LSFL_NODIR, &ls->ls_flags);
}
+#ifdef CONFIG_DLM_DEPRECATED_API
int dlm_netlink_init(void);
void dlm_netlink_exit(void);
void dlm_timeout_warn(struct dlm_lkb *lkb);
+#else
+static inline int dlm_netlink_init(void) { return 0; }
+static inline void dlm_netlink_exit(void) { };
+static inline void dlm_timeout_warn(struct dlm_lkb *lkb) { };
+#endif
int dlm_plock_init(void);
void dlm_plock_exit(void);
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index 226822f49d30..dac7eb75dba9 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -296,12 +296,14 @@ static void queue_cast(struct dlm_rsb *r, struct dlm_lkb *lkb, int rv)
DLM_ASSERT(lkb->lkb_lksb, dlm_print_lkb(lkb););
+#ifdef CONFIG_DLM_DEPRECATED_API
/* if the operation was a cancel, then return -DLM_ECANCEL, if a
timeout caused the cancel then return -ETIMEDOUT */
if (rv == -DLM_ECANCEL && (lkb->lkb_flags & DLM_IFL_TIMEOUT_CANCEL)) {
lkb->lkb_flags &= ~DLM_IFL_TIMEOUT_CANCEL;
rv = -ETIMEDOUT;
}
+#endif
if (rv == -DLM_ECANCEL && (lkb->lkb_flags & DLM_IFL_DEADLOCK_CANCEL)) {
lkb->lkb_flags &= ~DLM_IFL_DEADLOCK_CANCEL;
@@ -1210,7 +1212,9 @@ static int _create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret,
kref_init(&lkb->lkb_ref);
INIT_LIST_HEAD(&lkb->lkb_ownqueue);
INIT_LIST_HEAD(&lkb->lkb_rsb_lookup);
+#ifdef CONFIG_DLM_DEPRECATED_API
INIT_LIST_HEAD(&lkb->lkb_time_list);
+#endif
INIT_LIST_HEAD(&lkb->lkb_cb_list);
mutex_init(&lkb->lkb_cb_mutex);
INIT_WORK(&lkb->lkb_cb_work, dlm_callback_work);
@@ -1306,6 +1310,13 @@ static inline void hold_lkb(struct dlm_lkb *lkb)
kref_get(&lkb->lkb_ref);
}
+static void unhold_lkb_assert(struct kref *kref)
+{
+ struct dlm_lkb *lkb = container_of(kref, struct dlm_lkb, lkb_ref);
+
+ DLM_ASSERT(false, dlm_print_lkb(lkb););
+}
+
/* This is called when we need to remove a reference and are certain
it's not the last ref. e.g. del_lkb is always called between a
find_lkb/put_lkb and is always the inverse of a previous add_lkb.
@@ -1313,9 +1324,7 @@ static inline void hold_lkb(struct dlm_lkb *lkb)
static inline void unhold_lkb(struct dlm_lkb *lkb)
{
- int rv;
- rv = kref_put(&lkb->lkb_ref, kill_lkb);
- DLM_ASSERT(!rv, dlm_print_lkb(lkb););
+ kref_put(&lkb->lkb_ref, unhold_lkb_assert);
}
static void lkb_add_ordered(struct list_head *new, struct list_head *head,
@@ -1402,75 +1411,6 @@ static int msg_reply_type(int mstype)
return -1;
}
-static int nodeid_warned(int nodeid, int num_nodes, int *warned)
-{
- int i;
-
- for (i = 0; i < num_nodes; i++) {
- if (!warned[i]) {
- warned[i] = nodeid;
- return 0;
- }
- if (warned[i] == nodeid)
- return 1;
- }
- return 0;
-}
-
-void dlm_scan_waiters(struct dlm_ls *ls)
-{
- struct dlm_lkb *lkb;
- s64 us;
- s64 debug_maxus = 0;
- u32 debug_scanned = 0;
- u32 debug_expired = 0;
- int num_nodes = 0;
- int *warned = NULL;
-
- if (!dlm_config.ci_waitwarn_us)
- return;
-
- mutex_lock(&ls->ls_waiters_mutex);
-
- list_for_each_entry(lkb, &ls->ls_waiters, lkb_wait_reply) {
- if (!lkb->lkb_wait_time)
- continue;
-
- debug_scanned++;
-
- us = ktime_to_us(ktime_sub(ktime_get(), lkb->lkb_wait_time));
-
- if (us < dlm_config.ci_waitwarn_us)
- continue;
-
- lkb->lkb_wait_time = 0;
-
- debug_expired++;
- if (us > debug_maxus)
- debug_maxus = us;
-
- if (!num_nodes) {
- num_nodes = ls->ls_num_nodes;
- warned = kcalloc(num_nodes, sizeof(int), GFP_KERNEL);
- }
- if (!warned)
- continue;
- if (nodeid_warned(lkb->lkb_wait_nodeid, num_nodes, warned))
- continue;
-
- log_error(ls, "waitwarn %x %lld %d us check connection to "
- "node %d", lkb->lkb_id, (long long)us,
- dlm_config.ci_waitwarn_us, lkb->lkb_wait_nodeid);
- }
- mutex_unlock(&ls->ls_waiters_mutex);
- kfree(warned);
-
- if (debug_expired)
- log_debug(ls, "scan_waiters %u warn %u over %d us max %lld us",
- debug_scanned, debug_expired,
- dlm_config.ci_waitwarn_us, (long long)debug_maxus);
-}
-
/* add/remove lkb from global waiters list of lkb's waiting for
a reply from a remote node */
@@ -1514,7 +1454,6 @@ static int add_to_waiters(struct dlm_lkb *lkb, int mstype, int to_nodeid)
lkb->lkb_wait_count++;
lkb->lkb_wait_type = mstype;
- lkb->lkb_wait_time = ktime_get();
lkb->lkb_wait_nodeid = to_nodeid; /* for debugging */
hold_lkb(lkb);
list_add(&lkb->lkb_wait_reply, &ls->ls_waiters);
@@ -1842,6 +1781,7 @@ void dlm_scan_rsbs(struct dlm_ls *ls)
}
}
+#ifdef CONFIG_DLM_DEPRECATED_API
static void add_timeout(struct dlm_lkb *lkb)
{
struct dlm_ls *ls = lkb->lkb_resource->res_ls;
@@ -1962,17 +1902,11 @@ void dlm_adjust_timeouts(struct dlm_ls *ls)
list_for_each_entry(lkb, &ls->ls_timeout, lkb_time_list)
lkb->lkb_timestamp = ktime_add_us(lkb->lkb_timestamp, adj_us);
mutex_unlock(&ls->ls_timeout_mutex);
-
- if (!dlm_config.ci_waitwarn_us)
- return;
-
- mutex_lock(&ls->ls_waiters_mutex);
- list_for_each_entry(lkb, &ls->ls_waiters, lkb_wait_reply) {
- if (ktime_to_us(lkb->lkb_wait_time))
- lkb->lkb_wait_time = ktime_get();
- }
- mutex_unlock(&ls->ls_waiters_mutex);
}
+#else
+static void add_timeout(struct dlm_lkb *lkb) { }
+static void del_timeout(struct dlm_lkb *lkb) { }
+#endif
/* lkb is master or local copy */
@@ -2837,12 +2771,20 @@ static void confirm_master(struct dlm_rsb *r, int error)
}
}
+#ifdef CONFIG_DLM_DEPRECATED_API
static int set_lock_args(int mode, struct dlm_lksb *lksb, uint32_t flags,
int namelen, unsigned long timeout_cs,
void (*ast) (void *astparam),
void *astparam,
void (*bast) (void *astparam, int mode),
struct dlm_args *args)
+#else
+static int set_lock_args(int mode, struct dlm_lksb *lksb, uint32_t flags,
+ int namelen, void (*ast)(void *astparam),
+ void *astparam,
+ void (*bast)(void *astparam, int mode),
+ struct dlm_args *args)
+#endif
{
int rv = -EINVAL;
@@ -2895,7 +2837,9 @@ static int set_lock_args(int mode, struct dlm_lksb *lksb, uint32_t flags,
args->astfn = ast;
args->astparam = astparam;
args->bastfn = bast;
+#ifdef CONFIG_DLM_DEPRECATED_API
args->timeout = timeout_cs;
+#endif
args->mode = mode;
args->lksb = lksb;
rv = 0;
@@ -2951,7 +2895,9 @@ static int validate_lock_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
lkb->lkb_lksb = args->lksb;
lkb->lkb_lvbptr = args->lksb->sb_lvbptr;
lkb->lkb_ownpid = (int) current->pid;
+#ifdef CONFIG_DLM_DEPRECATED_API
lkb->lkb_timeout_cs = args->timeout;
+#endif
rv = 0;
out:
if (rv)
@@ -3472,10 +3418,15 @@ int dlm_lock(dlm_lockspace_t *lockspace,
if (error)
goto out;
- trace_dlm_lock_start(ls, lkb, mode, flags);
+ trace_dlm_lock_start(ls, lkb, name, namelen, mode, flags);
+#ifdef CONFIG_DLM_DEPRECATED_API
error = set_lock_args(mode, lksb, flags, namelen, 0, ast,
astarg, bast, &args);
+#else
+ error = set_lock_args(mode, lksb, flags, namelen, ast, astarg, bast,
+ &args);
+#endif
if (error)
goto out_put;
@@ -3487,7 +3438,7 @@ int dlm_lock(dlm_lockspace_t *lockspace,
if (error == -EINPROGRESS)
error = 0;
out_put:
- trace_dlm_lock_end(ls, lkb, mode, flags, error);
+ trace_dlm_lock_end(ls, lkb, name, namelen, mode, flags, error);
if (convert || error)
__put_lkb(ls, lkb);
@@ -5839,9 +5790,14 @@ int dlm_recover_process_copy(struct dlm_ls *ls, struct dlm_rcom *rc)
return 0;
}
+#ifdef CONFIG_DLM_DEPRECATED_API
int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua,
int mode, uint32_t flags, void *name, unsigned int namelen,
unsigned long timeout_cs)
+#else
+int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua,
+ int mode, uint32_t flags, void *name, unsigned int namelen)
+#endif
{
struct dlm_lkb *lkb;
struct dlm_args args;
@@ -5864,8 +5820,13 @@ int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua,
goto out;
}
}
+#ifdef CONFIG_DLM_DEPRECATED_API
error = set_lock_args(mode, &ua->lksb, flags, namelen, timeout_cs,
fake_astfn, ua, fake_bastfn, &args);
+#else
+ error = set_lock_args(mode, &ua->lksb, flags, namelen, fake_astfn, ua,
+ fake_bastfn, &args);
+#endif
if (error) {
kfree(ua->lksb.sb_lvbptr);
ua->lksb.sb_lvbptr = NULL;
@@ -5904,9 +5865,14 @@ int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua,
return error;
}
+#ifdef CONFIG_DLM_DEPRECATED_API
int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
int mode, uint32_t flags, uint32_t lkid, char *lvb_in,
unsigned long timeout_cs)
+#else
+int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
+ int mode, uint32_t flags, uint32_t lkid, char *lvb_in)
+#endif
{
struct dlm_lkb *lkb;
struct dlm_args args;
@@ -5941,8 +5907,13 @@ int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
ua->bastaddr = ua_tmp->bastaddr;
ua->user_lksb = ua_tmp->user_lksb;
+#ifdef CONFIG_DLM_DEPRECATED_API
error = set_lock_args(mode, &ua->lksb, flags, 0, timeout_cs,
fake_astfn, ua, fake_bastfn, &args);
+#else
+ error = set_lock_args(mode, &ua->lksb, flags, 0, fake_astfn, ua,
+ fake_bastfn, &args);
+#endif
if (error)
goto out_put;
@@ -5966,7 +5937,7 @@ int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
int dlm_user_adopt_orphan(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
int mode, uint32_t flags, void *name, unsigned int namelen,
- unsigned long timeout_cs, uint32_t *lkid)
+ uint32_t *lkid)
{
struct dlm_lkb *lkb = NULL, *iter;
struct dlm_user_args *ua;
diff --git a/fs/dlm/lock.h b/fs/dlm/lock.h
index 252a5898f908..a7b6474f009d 100644
--- a/fs/dlm/lock.h
+++ b/fs/dlm/lock.h
@@ -24,9 +24,15 @@ int dlm_put_lkb(struct dlm_lkb *lkb);
void dlm_scan_rsbs(struct dlm_ls *ls);
int dlm_lock_recovery_try(struct dlm_ls *ls);
void dlm_unlock_recovery(struct dlm_ls *ls);
-void dlm_scan_waiters(struct dlm_ls *ls);
+
+#ifdef CONFIG_DLM_DEPRECATED_API
void dlm_scan_timeout(struct dlm_ls *ls);
void dlm_adjust_timeouts(struct dlm_ls *ls);
+#else
+static inline void dlm_scan_timeout(struct dlm_ls *ls) { }
+static inline void dlm_adjust_timeouts(struct dlm_ls *ls) { }
+#endif
+
int dlm_master_lookup(struct dlm_ls *ls, int nodeid, char *name, int len,
unsigned int flags, int *r_nodeid, int *result);
@@ -41,15 +47,22 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls);
int dlm_recover_master_copy(struct dlm_ls *ls, struct dlm_rcom *rc);
int dlm_recover_process_copy(struct dlm_ls *ls, struct dlm_rcom *rc);
+#ifdef CONFIG_DLM_DEPRECATED_API
int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua, int mode,
uint32_t flags, void *name, unsigned int namelen,
unsigned long timeout_cs);
int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
int mode, uint32_t flags, uint32_t lkid, char *lvb_in,
unsigned long timeout_cs);
+#else
+int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua, int mode,
+ uint32_t flags, void *name, unsigned int namelen);
+int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
+ int mode, uint32_t flags, uint32_t lkid, char *lvb_in);
+#endif
int dlm_user_adopt_orphan(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
int mode, uint32_t flags, void *name, unsigned int namelen,
- unsigned long timeout_cs, uint32_t *lkid);
+ uint32_t *lkid);
int dlm_user_unlock(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
uint32_t flags, uint32_t lkid, char *lvb_in);
int dlm_user_cancel(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c
index 19ed41a5da93..3972f4d86c75 100644
--- a/fs/dlm/lockspace.c
+++ b/fs/dlm/lockspace.c
@@ -275,7 +275,6 @@ static int dlm_scand(void *data)
ls->ls_scan_time = jiffies;
dlm_scan_rsbs(ls);
dlm_scan_timeout(ls);
- dlm_scan_waiters(ls);
dlm_unlock_recovery(ls);
} else {
ls->ls_scan_time += HZ;
@@ -490,13 +489,28 @@ static int new_lockspace(const char *name, const char *cluster,
ls->ls_ops_arg = ops_arg;
}
- if (flags & DLM_LSFL_TIMEWARN)
+#ifdef CONFIG_DLM_DEPRECATED_API
+ if (flags & DLM_LSFL_TIMEWARN) {
+ pr_warn_once("===============================================================\n"
+ "WARNING: the dlm DLM_LSFL_TIMEWARN flag is being deprecated and\n"
+ " will be removed in v6.2!\n"
+ " Inclusive DLM_LSFL_TIMEWARN define in UAPI header!\n"
+ "===============================================================\n");
+
set_bit(LSFL_TIMEWARN, &ls->ls_flags);
+ }
/* ls_exflags are forced to match among nodes, and we don't
- need to require all nodes to have some flags set */
+ * need to require all nodes to have some flags set
+ */
ls->ls_exflags = (flags & ~(DLM_LSFL_TIMEWARN | DLM_LSFL_FS |
DLM_LSFL_NEWEXCL));
+#else
+ /* ls_exflags are forced to match among nodes, and we don't
+ * need to require all nodes to have some flags set
+ */
+ ls->ls_exflags = (flags & ~(DLM_LSFL_FS | DLM_LSFL_NEWEXCL));
+#endif
size = READ_ONCE(dlm_config.ci_rsbtbl_size);
ls->ls_rsbtbl_size = size;
@@ -527,8 +541,10 @@ static int new_lockspace(const char *name, const char *cluster,
mutex_init(&ls->ls_waiters_mutex);
INIT_LIST_HEAD(&ls->ls_orphans);
mutex_init(&ls->ls_orphans_mutex);
+#ifdef CONFIG_DLM_DEPRECATED_API
INIT_LIST_HEAD(&ls->ls_timeout);
mutex_init(&ls->ls_timeout_mutex);
+#endif
INIT_LIST_HEAD(&ls->ls_new_rsb);
spin_lock_init(&ls->ls_new_rsb_spin);
@@ -548,8 +564,8 @@ static int new_lockspace(const char *name, const char *cluster,
init_waitqueue_head(&ls->ls_uevent_wait);
ls->ls_uevent_result = 0;
- init_completion(&ls->ls_members_done);
- ls->ls_members_result = -1;
+ init_completion(&ls->ls_recovery_done);
+ ls->ls_recovery_result = -1;
mutex_init(&ls->ls_cb_mutex);
INIT_LIST_HEAD(&ls->ls_cb_delay);
@@ -645,8 +661,9 @@ static int new_lockspace(const char *name, const char *cluster,
if (error)
goto out_recoverd;
- wait_for_completion(&ls->ls_members_done);
- error = ls->ls_members_result;
+ /* wait until recovery is successful or failed */
+ wait_for_completion(&ls->ls_recovery_done);
+ error = ls->ls_recovery_result;
if (error)
goto out_members;
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 19e82f08c0e0..a4e84e8d94c8 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -529,7 +529,7 @@ static void lowcomms_write_space(struct sock *sk)
return;
if (!test_and_set_bit(CF_CONNECTED, &con->flags)) {
- log_print("successful connected to node %d", con->nodeid);
+ log_print("connected to node %d", con->nodeid);
queue_work(send_workqueue, &con->swork);
return;
}
@@ -1931,7 +1931,7 @@ static int dlm_sctp_connect(struct connection *con, struct socket *sock,
return ret;
if (!test_and_set_bit(CF_CONNECTED, &con->flags))
- log_print("successful connected to node %d", con->nodeid);
+ log_print("connected to node %d", con->nodeid);
return 0;
}
diff --git a/fs/dlm/member.c b/fs/dlm/member.c
index 98084e0cfccf..2af2ccfe43a9 100644
--- a/fs/dlm/member.c
+++ b/fs/dlm/member.c
@@ -534,7 +534,11 @@ int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv, int *neg_out)
int i, error, neg = 0, low = -1;
/* previously removed members that we've not finished removing need to
- count as a negative change so the "neg" recovery steps will happen */
+ * count as a negative change so the "neg" recovery steps will happen
+ *
+ * This functionality must report all member changes to lsops or
+ * midcomms layer and must never return before.
+ */
list_for_each_entry(memb, &ls->ls_nodes_gone, list) {
log_rinfo(ls, "prev removed member %d", memb->nodeid);
@@ -583,19 +587,6 @@ int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv, int *neg_out)
*neg_out = neg;
error = ping_members(ls);
- /* error -EINTR means that a new recovery action is triggered.
- * We ignore this recovery action and let run the new one which might
- * have new member configuration.
- */
- if (error == -EINTR)
- error = 0;
-
- /* new_lockspace() may be waiting to know if the config
- * is good or bad
- */
- ls->ls_members_result = error;
- complete(&ls->ls_members_done);
-
log_rinfo(ls, "dlm_recover_members %d nodes", ls->ls_num_nodes);
return error;
}
@@ -675,7 +666,16 @@ int dlm_ls_stop(struct dlm_ls *ls)
if (!ls->ls_recover_begin)
ls->ls_recover_begin = jiffies;
- dlm_lsop_recover_prep(ls);
+ /* call recover_prep ops only once and not multiple times
+ * for each possible dlm_ls_stop() when recovery is already
+ * stopped.
+ *
+ * If we successful was able to clear LSFL_RUNNING bit and
+ * it was set we know it is the first dlm_ls_stop() call.
+ */
+ if (new)
+ dlm_lsop_recover_prep(ls);
+
return 0;
}
diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c
index 0993eebf2060..737f185aad8d 100644
--- a/fs/dlm/plock.c
+++ b/fs/dlm/plock.c
@@ -29,6 +29,8 @@ struct plock_async_data {
struct plock_op {
struct list_head list;
int done;
+ /* if lock op got interrupted while waiting dlm_controld reply */
+ bool sigint;
struct dlm_plock_info info;
/* if set indicates async handling */
struct plock_async_data *data;
@@ -79,8 +81,7 @@ static void send_op(struct plock_op *op)
abandoned waiter. So, we have to insert the unlock-close when the
lock call is interrupted. */
-static void do_unlock_close(struct dlm_ls *ls, u64 number,
- struct file *file, struct file_lock *fl)
+static void do_unlock_close(const struct dlm_plock_info *info)
{
struct plock_op *op;
@@ -89,15 +90,12 @@ static void do_unlock_close(struct dlm_ls *ls, u64 number,
return;
op->info.optype = DLM_PLOCK_OP_UNLOCK;
- op->info.pid = fl->fl_pid;
- op->info.fsid = ls->ls_global_id;
- op->info.number = number;
+ op->info.pid = info->pid;
+ op->info.fsid = info->fsid;
+ op->info.number = info->number;
op->info.start = 0;
op->info.end = OFFSET_MAX;
- if (fl->fl_lmops && fl->fl_lmops->lm_grant)
- op->info.owner = (__u64) fl->fl_pid;
- else
- op->info.owner = (__u64)(long) fl->fl_owner;
+ op->info.owner = info->owner;
op->info.flags |= DLM_PLOCK_FL_CLOSE;
send_op(op);
@@ -161,16 +159,24 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
rv = wait_event_interruptible(recv_wq, (op->done != 0));
if (rv == -ERESTARTSYS) {
spin_lock(&ops_lock);
- list_del(&op->list);
+ /* recheck under ops_lock if we got a done != 0,
+ * if so this interrupt case should be ignored
+ */
+ if (op->done != 0) {
+ spin_unlock(&ops_lock);
+ goto do_lock_wait;
+ }
+
+ op->sigint = true;
spin_unlock(&ops_lock);
- log_print("%s: wait interrupted %x %llx, op removed",
+ log_debug(ls, "%s: wait interrupted %x %llx pid %d",
__func__, ls->ls_global_id,
- (unsigned long long)number);
- dlm_release_plock_op(op);
- do_unlock_close(ls, number, file, fl);
+ (unsigned long long)number, op->info.pid);
goto out;
}
+do_lock_wait:
+
WARN_ON(!list_empty(&op->list));
rv = op->info.rv;
@@ -378,7 +384,7 @@ static ssize_t dev_read(struct file *file, char __user *u, size_t count,
spin_lock(&ops_lock);
if (!list_empty(&send_list)) {
- op = list_entry(send_list.next, struct plock_op, list);
+ op = list_first_entry(&send_list, struct plock_op, list);
if (op->info.flags & DLM_PLOCK_FL_CLOSE)
list_del(&op->list);
else
@@ -425,6 +431,19 @@ static ssize_t dev_write(struct file *file, const char __user *u, size_t count,
if (iter->info.fsid == info.fsid &&
iter->info.number == info.number &&
iter->info.owner == info.owner) {
+ if (iter->sigint) {
+ list_del(&iter->list);
+ spin_unlock(&ops_lock);
+
+ pr_debug("%s: sigint cleanup %x %llx pid %d",
+ __func__, iter->info.fsid,
+ (unsigned long long)iter->info.number,
+ iter->info.pid);
+ do_unlock_close(&iter->info);
+ memcpy(&iter->info, &info, sizeof(info));
+ dlm_release_plock_op(iter);
+ return count;
+ }
list_del_init(&iter->list);
memcpy(&iter->info, &info, sizeof(info));
if (iter->data)
@@ -443,7 +462,7 @@ static ssize_t dev_write(struct file *file, const char __user *u, size_t count,
else
wake_up(&recv_wq);
} else
- log_print("%s: no op %x %llx - may got interrupted?", __func__,
+ log_print("%s: no op %x %llx", __func__,
info.fsid, (unsigned long long)info.number);
return count;
}
diff --git a/fs/dlm/recoverd.c b/fs/dlm/recoverd.c
index a55dfce705dd..e15eb511b04b 100644
--- a/fs/dlm/recoverd.c
+++ b/fs/dlm/recoverd.c
@@ -70,6 +70,10 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
/*
* Add or remove nodes from the lockspace's ls_nodes list.
+ *
+ * Due to the fact that we must report all membership changes to lsops
+ * or midcomms layer, it is not permitted to abort ls_recover() until
+ * this is done.
*/
error = dlm_recover_members(ls, rv, &neg);
@@ -239,14 +243,12 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
jiffies_to_msecs(jiffies - start));
mutex_unlock(&ls->ls_recoverd_active);
- dlm_lsop_recover_done(ls);
return 0;
fail:
dlm_release_root_list(ls);
- log_rinfo(ls, "dlm_recover %llu error %d",
- (unsigned long long)rv->seq, error);
mutex_unlock(&ls->ls_recoverd_active);
+
return error;
}
@@ -257,6 +259,7 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
static void do_ls_recovery(struct dlm_ls *ls)
{
struct dlm_recover *rv = NULL;
+ int error;
spin_lock(&ls->ls_recover_lock);
rv = ls->ls_recover_args;
@@ -266,7 +269,31 @@ static void do_ls_recovery(struct dlm_ls *ls)
spin_unlock(&ls->ls_recover_lock);
if (rv) {
- ls_recover(ls, rv);
+ error = ls_recover(ls, rv);
+ switch (error) {
+ case 0:
+ ls->ls_recovery_result = 0;
+ complete(&ls->ls_recovery_done);
+
+ dlm_lsop_recover_done(ls);
+ break;
+ case -EINTR:
+ /* if recovery was interrupted -EINTR we wait for the next
+ * ls_recover() iteration until it hopefully succeeds.
+ */
+ log_rinfo(ls, "%s %llu interrupted and should be queued to run again",
+ __func__, (unsigned long long)rv->seq);
+ break;
+ default:
+ log_rinfo(ls, "%s %llu error %d", __func__,
+ (unsigned long long)rv->seq, error);
+
+ /* let new_lockspace() get aware of critical error */
+ ls->ls_recovery_result = error;
+ complete(&ls->ls_recovery_done);
+ break;
+ }
+
kfree(rv->nodes);
kfree(rv);
}
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index 1060b24f18d4..99e8f0744513 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -250,6 +250,14 @@ static int device_user_lock(struct dlm_user_proc *proc,
goto out;
}
+#ifdef CONFIG_DLM_DEPRECATED_API
+ if (params->timeout)
+ pr_warn_once("========================================================\n"
+ "WARNING: the lkb timeout feature is being deprecated and\n"
+ " will be removed in v6.2!\n"
+ "========================================================\n");
+#endif
+
ua = kzalloc(sizeof(struct dlm_user_args), GFP_NOFS);
if (!ua)
goto out;
@@ -262,23 +270,34 @@ static int device_user_lock(struct dlm_user_proc *proc,
ua->xid = params->xid;
if (params->flags & DLM_LKF_CONVERT) {
+#ifdef CONFIG_DLM_DEPRECATED_API
error = dlm_user_convert(ls, ua,
params->mode, params->flags,
params->lkid, params->lvb,
(unsigned long) params->timeout);
+#else
+ error = dlm_user_convert(ls, ua,
+ params->mode, params->flags,
+ params->lkid, params->lvb);
+#endif
} else if (params->flags & DLM_LKF_ORPHAN) {
error = dlm_user_adopt_orphan(ls, ua,
params->mode, params->flags,
params->name, params->namelen,
- (unsigned long) params->timeout,
&lkid);
if (!error)
error = lkid;
} else {
+#ifdef CONFIG_DLM_DEPRECATED_API
error = dlm_user_request(ls, ua,
params->mode, params->flags,
params->name, params->namelen,
(unsigned long) params->timeout);
+#else
+ error = dlm_user_request(ls, ua,
+ params->mode, params->flags,
+ params->name, params->namelen);
+#endif
if (!error)
error = ua->lksb.sb_lkid;
}
diff --git a/fs/erofs/compress.h b/fs/erofs/compress.h
index 19e6c56a9f47..26fa170090b8 100644
--- a/fs/erofs/compress.h
+++ b/fs/erofs/compress.h
@@ -17,7 +17,7 @@ struct z_erofs_decompress_req {
/* indicate the algorithm will be used for decompression */
unsigned int alg;
- bool inplace_io, partial_decoding;
+ bool inplace_io, partial_decoding, fillgaps;
};
struct z_erofs_decompressor {
diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index fbb037ba326e..fe8ac0e163f7 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -366,42 +366,33 @@ static sector_t erofs_bmap(struct address_space *mapping, sector_t block)
return iomap_bmap(mapping, block, &erofs_iomap_ops);
}
-static int erofs_prepare_dio(struct kiocb *iocb, struct iov_iter *to)
+static ssize_t erofs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct inode *inode = file_inode(iocb->ki_filp);
- loff_t align = iocb->ki_pos | iov_iter_count(to) |
- iov_iter_alignment(to);
- struct block_device *bdev = inode->i_sb->s_bdev;
- unsigned int blksize_mask;
-
- if (bdev)
- blksize_mask = (1 << ilog2(bdev_logical_block_size(bdev))) - 1;
- else
- blksize_mask = (1 << inode->i_blkbits) - 1;
- if (align & blksize_mask)
- return -EINVAL;
- return 0;
-}
-
-static ssize_t erofs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
-{
/* no need taking (shared) inode lock since it's a ro filesystem */
if (!iov_iter_count(to))
return 0;
#ifdef CONFIG_FS_DAX
- if (IS_DAX(iocb->ki_filp->f_mapping->host))
+ if (IS_DAX(inode))
return dax_iomap_rw(iocb, to, &erofs_iomap_ops);
#endif
if (iocb->ki_flags & IOCB_DIRECT) {
- int err = erofs_prepare_dio(iocb, to);
+ struct block_device *bdev = inode->i_sb->s_bdev;
+ unsigned int blksize_mask;
+
+ if (bdev)
+ blksize_mask = bdev_logical_block_size(bdev) - 1;
+ else
+ blksize_mask = (1 << inode->i_blkbits) - 1;
+
+ if ((iocb->ki_pos | iov_iter_count(to) |
+ iov_iter_alignment(to)) & blksize_mask)
+ return -EINVAL;
- if (!err)
- return iomap_dio_rw(iocb, to, &erofs_iomap_ops,
- NULL, 0, NULL, 0);
- if (err < 0)
- return err;
+ return iomap_dio_rw(iocb, to, &erofs_iomap_ops,
+ NULL, 0, NULL, 0);
}
return filemap_read(iocb, to, 0);
}
diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c
index 6dca1900c733..2d55569f96ac 100644
--- a/fs/erofs/decompressor.c
+++ b/fs/erofs/decompressor.c
@@ -83,7 +83,7 @@ static int z_erofs_lz4_prepare_dstpages(struct z_erofs_lz4_decompress_ctx *ctx,
j = 0;
/* 'valid' bounced can only be tested after a complete round */
- if (test_bit(j, bounced)) {
+ if (!rq->fillgaps && test_bit(j, bounced)) {
DBG_BUGON(i < lz4_max_distance_pages);
DBG_BUGON(top >= lz4_max_distance_pages);
availables[top++] = rq->out[i - lz4_max_distance_pages];
@@ -91,14 +91,18 @@ static int z_erofs_lz4_prepare_dstpages(struct z_erofs_lz4_decompress_ctx *ctx,
if (page) {
__clear_bit(j, bounced);
- if (kaddr) {
- if (kaddr + PAGE_SIZE == page_address(page))
+ if (!PageHighMem(page)) {
+ if (!i) {
+ kaddr = page_address(page);
+ continue;
+ }
+ if (kaddr &&
+ kaddr + PAGE_SIZE == page_address(page)) {
kaddr += PAGE_SIZE;
- else
- kaddr = NULL;
- } else if (!i) {
- kaddr = page_address(page);
+ continue;
+ }
}
+ kaddr = NULL;
continue;
}
kaddr = NULL;
diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c
index 05a3063cf2bc..5e59b3f523eb 100644
--- a/fs/erofs/decompressor_lzma.c
+++ b/fs/erofs/decompressor_lzma.c
@@ -143,6 +143,7 @@ again:
DBG_BUGON(z_erofs_lzma_head);
z_erofs_lzma_head = head;
spin_unlock(&z_erofs_lzma_lock);
+ wake_up_all(&z_erofs_lzma_wq);
z_erofs_lzma_max_dictsize = dict_size;
mutex_unlock(&lzma_resize_mutex);
diff --git a/fs/erofs/dir.c b/fs/erofs/dir.c
index 18e59821c597..ecf28f66b97d 100644
--- a/fs/erofs/dir.c
+++ b/fs/erofs/dir.c
@@ -22,10 +22,9 @@ static void debug_one_dentry(unsigned char d_type, const char *de_name,
}
static int erofs_fill_dentries(struct inode *dir, struct dir_context *ctx,
- void *dentry_blk, unsigned int *ofs,
+ void *dentry_blk, struct erofs_dirent *de,
unsigned int nameoff, unsigned int maxsize)
{
- struct erofs_dirent *de = dentry_blk + *ofs;
const struct erofs_dirent *end = dentry_blk + nameoff;
while (de < end) {
@@ -59,9 +58,8 @@ static int erofs_fill_dentries(struct inode *dir, struct dir_context *ctx,
/* stopped by some reason */
return 1;
++de;
- *ofs += sizeof(struct erofs_dirent);
+ ctx->pos += sizeof(struct erofs_dirent);
}
- *ofs = maxsize;
return 0;
}
@@ -90,33 +88,33 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx)
nameoff = le16_to_cpu(de->nameoff);
if (nameoff < sizeof(struct erofs_dirent) ||
- nameoff >= PAGE_SIZE) {
+ nameoff >= EROFS_BLKSIZ) {
erofs_err(dir->i_sb,
"invalid de[0].nameoff %u @ nid %llu",
nameoff, EROFS_I(dir)->nid);
err = -EFSCORRUPTED;
- goto skip_this;
+ break;
}
maxsize = min_t(unsigned int,
- dirsize - ctx->pos + ofs, PAGE_SIZE);
+ dirsize - ctx->pos + ofs, EROFS_BLKSIZ);
/* search dirents at the arbitrary position */
if (initial) {
initial = false;
ofs = roundup(ofs, sizeof(struct erofs_dirent));
+ ctx->pos = blknr_to_addr(i) + ofs;
if (ofs >= nameoff)
goto skip_this;
}
- err = erofs_fill_dentries(dir, ctx, de, &ofs,
+ err = erofs_fill_dentries(dir, ctx, de, (void *)de + ofs,
nameoff, maxsize);
-skip_this:
- ctx->pos = blknr_to_addr(i) + ofs;
-
if (err)
break;
+skip_this:
+ ctx->pos = blknr_to_addr(i) + maxsize;
++i;
ofs = 0;
}
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 724bb57075f6..5792ca9e0d5e 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -2,6 +2,7 @@
/*
* Copyright (C) 2018 HUAWEI, Inc.
* https://www.huawei.com/
+ * Copyright (C) 2022 Alibaba Cloud
*/
#include "zdata.h"
#include "compress.h"
@@ -26,6 +27,82 @@ static struct z_erofs_pcluster_slab pcluster_pool[] __read_mostly = {
_PCLP(Z_EROFS_PCLUSTER_MAX_PAGES)
};
+struct z_erofs_bvec_iter {
+ struct page *bvpage;
+ struct z_erofs_bvset *bvset;
+ unsigned int nr, cur;
+};
+
+static struct page *z_erofs_bvec_iter_end(struct z_erofs_bvec_iter *iter)
+{
+ if (iter->bvpage)
+ kunmap_local(iter->bvset);
+ return iter->bvpage;
+}
+
+static struct page *z_erofs_bvset_flip(struct z_erofs_bvec_iter *iter)
+{
+ unsigned long base = (unsigned long)((struct z_erofs_bvset *)0)->bvec;
+ /* have to access nextpage in advance, otherwise it will be unmapped */
+ struct page *nextpage = iter->bvset->nextpage;
+ struct page *oldpage;
+
+ DBG_BUGON(!nextpage);
+ oldpage = z_erofs_bvec_iter_end(iter);
+ iter->bvpage = nextpage;
+ iter->bvset = kmap_local_page(nextpage);
+ iter->nr = (PAGE_SIZE - base) / sizeof(struct z_erofs_bvec);
+ iter->cur = 0;
+ return oldpage;
+}
+
+static void z_erofs_bvec_iter_begin(struct z_erofs_bvec_iter *iter,
+ struct z_erofs_bvset_inline *bvset,
+ unsigned int bootstrap_nr,
+ unsigned int cur)
+{
+ *iter = (struct z_erofs_bvec_iter) {
+ .nr = bootstrap_nr,
+ .bvset = (struct z_erofs_bvset *)bvset,
+ };
+
+ while (cur > iter->nr) {
+ cur -= iter->nr;
+ z_erofs_bvset_flip(iter);
+ }
+ iter->cur = cur;
+}
+
+static int z_erofs_bvec_enqueue(struct z_erofs_bvec_iter *iter,
+ struct z_erofs_bvec *bvec,
+ struct page **candidate_bvpage)
+{
+ if (iter->cur == iter->nr) {
+ if (!*candidate_bvpage)
+ return -EAGAIN;
+
+ DBG_BUGON(iter->bvset->nextpage);
+ iter->bvset->nextpage = *candidate_bvpage;
+ z_erofs_bvset_flip(iter);
+
+ iter->bvset->nextpage = NULL;
+ *candidate_bvpage = NULL;
+ }
+ iter->bvset->bvec[iter->cur++] = *bvec;
+ return 0;
+}
+
+static void z_erofs_bvec_dequeue(struct z_erofs_bvec_iter *iter,
+ struct z_erofs_bvec *bvec,
+ struct page **old_bvpage)
+{
+ if (iter->cur == iter->nr)
+ *old_bvpage = z_erofs_bvset_flip(iter);
+ else
+ *old_bvpage = NULL;
+ *bvec = iter->bvset->bvec[iter->cur++];
+}
+
static void z_erofs_destroy_pcluster_pool(void)
{
int i;
@@ -46,7 +123,7 @@ static int z_erofs_create_pcluster_pool(void)
for (pcs = pcluster_pool;
pcs < pcluster_pool + ARRAY_SIZE(pcluster_pool); ++pcs) {
- size = struct_size(a, compressed_pages, pcs->maxpages);
+ size = struct_size(a, compressed_bvecs, pcs->maxpages);
sprintf(pcs->name, "erofs_pcluster-%u", pcs->maxpages);
pcs->slab = kmem_cache_create(pcs->name, size, 0,
@@ -150,30 +227,29 @@ int __init z_erofs_init_zip_subsystem(void)
return err;
}
-enum z_erofs_collectmode {
- COLLECT_SECONDARY,
- COLLECT_PRIMARY,
+enum z_erofs_pclustermode {
+ Z_EROFS_PCLUSTER_INFLIGHT,
/*
- * The current collection was the tail of an exist chain, in addition
- * that the previous processed chained collections are all decided to
+ * The current pclusters was the tail of an exist chain, in addition
+ * that the previous processed chained pclusters are all decided to
* be hooked up to it.
- * A new chain will be created for the remaining collections which are
- * not processed yet, therefore different from COLLECT_PRIMARY_FOLLOWED,
- * the next collection cannot reuse the whole page safely in
- * the following scenario:
+ * A new chain will be created for the remaining pclusters which are
+ * not processed yet, so different from Z_EROFS_PCLUSTER_FOLLOWED,
+ * the next pcluster cannot reuse the whole page safely for inplace I/O
+ * in the following scenario:
* ________________________________________________________________
* | tail (partial) page | head (partial) page |
- * | (belongs to the next cl) | (belongs to the current cl) |
- * |_______PRIMARY_FOLLOWED_______|________PRIMARY_HOOKED___________|
+ * | (belongs to the next pcl) | (belongs to the current pcl) |
+ * |_______PCLUSTER_FOLLOWED______|________PCLUSTER_HOOKED__________|
*/
- COLLECT_PRIMARY_HOOKED,
+ Z_EROFS_PCLUSTER_HOOKED,
/*
- * a weak form of COLLECT_PRIMARY_FOLLOWED, the difference is that it
+ * a weak form of Z_EROFS_PCLUSTER_FOLLOWED, the difference is that it
* could be dispatched into bypass queue later due to uptodated managed
* pages. All related online pages cannot be reused for inplace I/O (or
- * pagevec) since it can be directly decoded without I/O submission.
+ * bvpage) since it can be directly decoded without I/O submission.
*/
- COLLECT_PRIMARY_FOLLOWED_NOINPLACE,
+ Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE,
/*
* The current collection has been linked with the owned chain, and
* could also be linked with the remaining collections, which means
@@ -184,39 +260,36 @@ enum z_erofs_collectmode {
* ________________________________________________________________
* | tail (partial) page | head (partial) page |
* | (of the current cl) | (of the previous collection) |
- * | PRIMARY_FOLLOWED or | |
- * |_____PRIMARY_HOOKED___|____________PRIMARY_FOLLOWED____________|
+ * | PCLUSTER_FOLLOWED or | |
+ * |_____PCLUSTER_HOOKED__|___________PCLUSTER_FOLLOWED____________|
*
* [ (*) the above page can be used as inplace I/O. ]
*/
- COLLECT_PRIMARY_FOLLOWED,
+ Z_EROFS_PCLUSTER_FOLLOWED,
};
struct z_erofs_decompress_frontend {
struct inode *const inode;
struct erofs_map_blocks map;
+ struct z_erofs_bvec_iter biter;
- struct z_erofs_pagevec_ctor vector;
-
+ struct page *candidate_bvpage;
struct z_erofs_pcluster *pcl, *tailpcl;
- /* a pointer used to pick up inplace I/O pages */
- struct page **icpage_ptr;
z_erofs_next_pcluster_t owned_head;
-
- enum z_erofs_collectmode mode;
+ enum z_erofs_pclustermode mode;
bool readahead;
/* used for applying cache strategy on the fly */
bool backmost;
erofs_off_t headoffset;
+
+ /* a pointer used to pick up inplace I/O pages */
+ unsigned int icur;
};
#define DECOMPRESS_FRONTEND_INIT(__i) { \
.inode = __i, .owned_head = Z_EROFS_PCLUSTER_TAIL, \
- .mode = COLLECT_PRIMARY_FOLLOWED, .backmost = true }
-
-static struct page *z_pagemap_global[Z_EROFS_VMAP_GLOBAL_PAGES];
-static DEFINE_MUTEX(z_pagemap_global_lock);
+ .mode = Z_EROFS_PCLUSTER_FOLLOWED, .backmost = true }
static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe,
enum z_erofs_cache_alloctype type,
@@ -231,24 +304,21 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe,
*/
gfp_t gfp = (mapping_gfp_mask(mc) & ~__GFP_DIRECT_RECLAIM) |
__GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN;
- struct page **pages;
- pgoff_t index;
+ unsigned int i;
- if (fe->mode < COLLECT_PRIMARY_FOLLOWED)
+ if (fe->mode < Z_EROFS_PCLUSTER_FOLLOWED)
return;
- pages = pcl->compressed_pages;
- index = pcl->obj.index;
- for (; index < pcl->obj.index + pcl->pclusterpages; ++index, ++pages) {
+ for (i = 0; i < pcl->pclusterpages; ++i) {
struct page *page;
compressed_page_t t;
struct page *newpage = NULL;
/* the compressed page was loaded before */
- if (READ_ONCE(*pages))
+ if (READ_ONCE(pcl->compressed_bvecs[i].page))
continue;
- page = find_get_page(mc, index);
+ page = find_get_page(mc, pcl->obj.index + i);
if (page) {
t = tag_compressed_page_justfound(page);
@@ -269,7 +339,8 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe,
}
}
- if (!cmpxchg_relaxed(pages, NULL, tagptr_cast_ptr(t)))
+ if (!cmpxchg_relaxed(&pcl->compressed_bvecs[i].page, NULL,
+ tagptr_cast_ptr(t)))
continue;
if (page)
@@ -283,7 +354,7 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe,
* managed cache since it can be moved to the bypass queue instead.
*/
if (standalone)
- fe->mode = COLLECT_PRIMARY_FOLLOWED_NOINPLACE;
+ fe->mode = Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE;
}
/* called by erofs_shrinker to get rid of all compressed_pages */
@@ -300,7 +371,7 @@ int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
* therefore no need to worry about available decompression users.
*/
for (i = 0; i < pcl->pclusterpages; ++i) {
- struct page *page = pcl->compressed_pages[i];
+ struct page *page = pcl->compressed_bvecs[i].page;
if (!page)
continue;
@@ -313,7 +384,7 @@ int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
continue;
/* barrier is implied in the following 'unlock_page' */
- WRITE_ONCE(pcl->compressed_pages[i], NULL);
+ WRITE_ONCE(pcl->compressed_bvecs[i].page, NULL);
detach_page_private(page);
unlock_page(page);
}
@@ -323,56 +394,59 @@ int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
int erofs_try_to_free_cached_page(struct page *page)
{
struct z_erofs_pcluster *const pcl = (void *)page_private(page);
- int ret = 0; /* 0 - busy */
+ int ret, i;
- if (erofs_workgroup_try_to_freeze(&pcl->obj, 1)) {
- unsigned int i;
+ if (!erofs_workgroup_try_to_freeze(&pcl->obj, 1))
+ return 0;
- DBG_BUGON(z_erofs_is_inline_pcluster(pcl));
- for (i = 0; i < pcl->pclusterpages; ++i) {
- if (pcl->compressed_pages[i] == page) {
- WRITE_ONCE(pcl->compressed_pages[i], NULL);
- ret = 1;
- break;
- }
+ ret = 0;
+ DBG_BUGON(z_erofs_is_inline_pcluster(pcl));
+ for (i = 0; i < pcl->pclusterpages; ++i) {
+ if (pcl->compressed_bvecs[i].page == page) {
+ WRITE_ONCE(pcl->compressed_bvecs[i].page, NULL);
+ ret = 1;
+ break;
}
- erofs_workgroup_unfreeze(&pcl->obj, 1);
-
- if (ret)
- detach_page_private(page);
}
+ erofs_workgroup_unfreeze(&pcl->obj, 1);
+ if (ret)
+ detach_page_private(page);
return ret;
}
-/* page_type must be Z_EROFS_PAGE_TYPE_EXCLUSIVE */
static bool z_erofs_try_inplace_io(struct z_erofs_decompress_frontend *fe,
- struct page *page)
+ struct z_erofs_bvec *bvec)
{
struct z_erofs_pcluster *const pcl = fe->pcl;
- while (fe->icpage_ptr > pcl->compressed_pages)
- if (!cmpxchg(--fe->icpage_ptr, NULL, page))
+ while (fe->icur > 0) {
+ if (!cmpxchg(&pcl->compressed_bvecs[--fe->icur].page,
+ NULL, bvec->page)) {
+ pcl->compressed_bvecs[fe->icur] = *bvec;
return true;
+ }
+ }
return false;
}
/* callers must be with pcluster lock held */
static int z_erofs_attach_page(struct z_erofs_decompress_frontend *fe,
- struct page *page, enum z_erofs_page_type type,
- bool pvec_safereuse)
+ struct z_erofs_bvec *bvec, bool exclusive)
{
int ret;
- /* give priority for inplaceio */
- if (fe->mode >= COLLECT_PRIMARY &&
- type == Z_EROFS_PAGE_TYPE_EXCLUSIVE &&
- z_erofs_try_inplace_io(fe, page))
- return 0;
-
- ret = z_erofs_pagevec_enqueue(&fe->vector, page, type,
- pvec_safereuse);
- fe->pcl->vcnt += (unsigned int)ret;
- return ret ? 0 : -EAGAIN;
+ if (exclusive) {
+ /* give priority for inplaceio to use file pages first */
+ if (z_erofs_try_inplace_io(fe, bvec))
+ return 0;
+ /* otherwise, check if it can be used as a bvpage */
+ if (fe->mode >= Z_EROFS_PCLUSTER_FOLLOWED &&
+ !fe->candidate_bvpage)
+ fe->candidate_bvpage = bvec->page;
+ }
+ ret = z_erofs_bvec_enqueue(&fe->biter, bvec, &fe->candidate_bvpage);
+ fe->pcl->vcnt += (ret >= 0);
+ return ret;
}
static void z_erofs_try_to_claim_pcluster(struct z_erofs_decompress_frontend *f)
@@ -385,7 +459,7 @@ static void z_erofs_try_to_claim_pcluster(struct z_erofs_decompress_frontend *f)
*owned_head) == Z_EROFS_PCLUSTER_NIL) {
*owned_head = &pcl->next;
/* so we can attach this pcluster to our submission chain. */
- f->mode = COLLECT_PRIMARY_FOLLOWED;
+ f->mode = Z_EROFS_PCLUSTER_FOLLOWED;
return;
}
@@ -393,66 +467,21 @@ static void z_erofs_try_to_claim_pcluster(struct z_erofs_decompress_frontend *f)
* type 2, link to the end of an existing open chain, be careful
* that its submission is controlled by the original attached chain.
*/
- if (cmpxchg(&pcl->next, Z_EROFS_PCLUSTER_TAIL,
+ if (*owned_head != &pcl->next && pcl != f->tailpcl &&
+ cmpxchg(&pcl->next, Z_EROFS_PCLUSTER_TAIL,
*owned_head) == Z_EROFS_PCLUSTER_TAIL) {
*owned_head = Z_EROFS_PCLUSTER_TAIL;
- f->mode = COLLECT_PRIMARY_HOOKED;
+ f->mode = Z_EROFS_PCLUSTER_HOOKED;
f->tailpcl = NULL;
return;
}
/* type 3, it belongs to a chain, but it isn't the end of the chain */
- f->mode = COLLECT_PRIMARY;
+ f->mode = Z_EROFS_PCLUSTER_INFLIGHT;
}
-static int z_erofs_lookup_pcluster(struct z_erofs_decompress_frontend *fe,
- struct inode *inode,
- struct erofs_map_blocks *map)
-{
- struct z_erofs_pcluster *pcl = fe->pcl;
- unsigned int length;
-
- /* to avoid unexpected loop formed by corrupted images */
- if (fe->owned_head == &pcl->next || pcl == fe->tailpcl) {
- DBG_BUGON(1);
- return -EFSCORRUPTED;
- }
-
- if (pcl->pageofs_out != (map->m_la & ~PAGE_MASK)) {
- DBG_BUGON(1);
- return -EFSCORRUPTED;
- }
-
- length = READ_ONCE(pcl->length);
- if (length & Z_EROFS_PCLUSTER_FULL_LENGTH) {
- if ((map->m_llen << Z_EROFS_PCLUSTER_LENGTH_BIT) > length) {
- DBG_BUGON(1);
- return -EFSCORRUPTED;
- }
- } else {
- unsigned int llen = map->m_llen << Z_EROFS_PCLUSTER_LENGTH_BIT;
-
- if (map->m_flags & EROFS_MAP_FULL_MAPPED)
- llen |= Z_EROFS_PCLUSTER_FULL_LENGTH;
-
- while (llen > length &&
- length != cmpxchg_relaxed(&pcl->length, length, llen)) {
- cpu_relax();
- length = READ_ONCE(pcl->length);
- }
- }
- mutex_lock(&pcl->lock);
- /* used to check tail merging loop due to corrupted images */
- if (fe->owned_head == Z_EROFS_PCLUSTER_TAIL)
- fe->tailpcl = pcl;
-
- z_erofs_try_to_claim_pcluster(fe);
- return 0;
-}
-
-static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe,
- struct inode *inode,
- struct erofs_map_blocks *map)
+static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe)
{
+ struct erofs_map_blocks *map = &fe->map;
bool ztailpacking = map->m_flags & EROFS_MAP_META;
struct z_erofs_pcluster *pcl;
struct erofs_workgroup *grp;
@@ -471,14 +500,13 @@ static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe,
atomic_set(&pcl->obj.refcount, 1);
pcl->algorithmformat = map->m_algorithmformat;
- pcl->length = (map->m_llen << Z_EROFS_PCLUSTER_LENGTH_BIT) |
- (map->m_flags & EROFS_MAP_FULL_MAPPED ?
- Z_EROFS_PCLUSTER_FULL_LENGTH : 0);
+ pcl->length = 0;
+ pcl->partial = true;
/* new pclusters should be claimed as type 1, primary and followed */
pcl->next = fe->owned_head;
pcl->pageofs_out = map->m_la & ~PAGE_MASK;
- fe->mode = COLLECT_PRIMARY_FOLLOWED;
+ fe->mode = Z_EROFS_PCLUSTER_FOLLOWED;
/*
* lock all primary followed works before visible to others
@@ -494,7 +522,7 @@ static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe,
} else {
pcl->obj.index = map->m_pa >> PAGE_SHIFT;
- grp = erofs_insert_workgroup(inode->i_sb, &pcl->obj);
+ grp = erofs_insert_workgroup(fe->inode->i_sb, &pcl->obj);
if (IS_ERR(grp)) {
err = PTR_ERR(grp);
goto err_out;
@@ -520,11 +548,10 @@ err_out:
return err;
}
-static int z_erofs_collector_begin(struct z_erofs_decompress_frontend *fe,
- struct inode *inode,
- struct erofs_map_blocks *map)
+static int z_erofs_collector_begin(struct z_erofs_decompress_frontend *fe)
{
- struct erofs_workgroup *grp;
+ struct erofs_map_blocks *map = &fe->map;
+ struct erofs_workgroup *grp = NULL;
int ret;
DBG_BUGON(fe->pcl);
@@ -533,38 +560,35 @@ static int z_erofs_collector_begin(struct z_erofs_decompress_frontend *fe,
DBG_BUGON(fe->owned_head == Z_EROFS_PCLUSTER_NIL);
DBG_BUGON(fe->owned_head == Z_EROFS_PCLUSTER_TAIL_CLOSED);
- if (map->m_flags & EROFS_MAP_META) {
- if ((map->m_pa & ~PAGE_MASK) + map->m_plen > PAGE_SIZE) {
- DBG_BUGON(1);
- return -EFSCORRUPTED;
- }
- goto tailpacking;
+ if (!(map->m_flags & EROFS_MAP_META)) {
+ grp = erofs_find_workgroup(fe->inode->i_sb,
+ map->m_pa >> PAGE_SHIFT);
+ } else if ((map->m_pa & ~PAGE_MASK) + map->m_plen > PAGE_SIZE) {
+ DBG_BUGON(1);
+ return -EFSCORRUPTED;
}
- grp = erofs_find_workgroup(inode->i_sb, map->m_pa >> PAGE_SHIFT);
if (grp) {
fe->pcl = container_of(grp, struct z_erofs_pcluster, obj);
+ ret = -EEXIST;
} else {
-tailpacking:
- ret = z_erofs_register_pcluster(fe, inode, map);
- if (!ret)
- goto out;
- if (ret != -EEXIST)
- return ret;
+ ret = z_erofs_register_pcluster(fe);
}
- ret = z_erofs_lookup_pcluster(fe, inode, map);
- if (ret) {
- erofs_workgroup_put(&fe->pcl->obj);
+ if (ret == -EEXIST) {
+ mutex_lock(&fe->pcl->lock);
+ /* used to check tail merging loop due to corrupted images */
+ if (fe->owned_head == Z_EROFS_PCLUSTER_TAIL)
+ fe->tailpcl = fe->pcl;
+
+ z_erofs_try_to_claim_pcluster(fe);
+ } else if (ret) {
return ret;
}
-
-out:
- z_erofs_pagevec_ctor_init(&fe->vector, Z_EROFS_NR_INLINE_PAGEVECS,
- fe->pcl->pagevec, fe->pcl->vcnt);
+ z_erofs_bvec_iter_begin(&fe->biter, &fe->pcl->bvset,
+ Z_EROFS_INLINE_BVECS, fe->pcl->vcnt);
/* since file-backed online pages are traversed in reverse order */
- fe->icpage_ptr = fe->pcl->compressed_pages +
- z_erofs_pclusterpages(fe->pcl);
+ fe->icur = z_erofs_pclusterpages(fe->pcl);
return 0;
}
@@ -593,14 +617,19 @@ static bool z_erofs_collector_end(struct z_erofs_decompress_frontend *fe)
if (!pcl)
return false;
- z_erofs_pagevec_ctor_exit(&fe->vector, false);
+ z_erofs_bvec_iter_end(&fe->biter);
mutex_unlock(&pcl->lock);
+ if (fe->candidate_bvpage) {
+ DBG_BUGON(z_erofs_is_shortlived_page(fe->candidate_bvpage));
+ fe->candidate_bvpage = NULL;
+ }
+
/*
* if all pending pages are added, don't hold its reference
* any longer if the pcluster isn't hosted by ourselves.
*/
- if (fe->mode < COLLECT_PRIMARY_FOLLOWED_NOINPLACE)
+ if (fe->mode < Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE)
erofs_workgroup_put(&pcl->obj);
fe->pcl = NULL;
@@ -628,11 +657,10 @@ static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe,
struct erofs_sb_info *const sbi = EROFS_I_SB(inode);
struct erofs_map_blocks *const map = &fe->map;
const loff_t offset = page_offset(page);
- bool tight = true;
+ bool tight = true, exclusive;
enum z_erofs_cache_alloctype cache_strategy;
- enum z_erofs_page_type page_type;
- unsigned int cur, end, spiltted, index;
+ unsigned int cur, end, spiltted;
int err = 0;
/* register locked file pages as online pages in pack */
@@ -653,7 +681,7 @@ repeat:
map->m_llen = 0;
err = z_erofs_map_blocks_iter(inode, map, 0);
if (err)
- goto err_out;
+ goto out;
} else {
if (fe->pcl)
goto hitted;
@@ -663,9 +691,9 @@ repeat:
if (!(map->m_flags & EROFS_MAP_MAPPED))
goto hitted;
- err = z_erofs_collector_begin(fe, inode, map);
+ err = z_erofs_collector_begin(fe);
if (err)
- goto err_out;
+ goto out;
if (z_erofs_is_inline_pcluster(fe->pcl)) {
void *mp;
@@ -676,11 +704,12 @@ repeat:
err = PTR_ERR(mp);
erofs_err(inode->i_sb,
"failed to get inline page, err %d", err);
- goto err_out;
+ goto out;
}
get_page(fe->map.buf.page);
- WRITE_ONCE(fe->pcl->compressed_pages[0], fe->map.buf.page);
- fe->mode = COLLECT_PRIMARY_FOLLOWED_NOINPLACE;
+ WRITE_ONCE(fe->pcl->compressed_bvecs[0].page,
+ fe->map.buf.page);
+ fe->mode = Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE;
} else {
/* bind cache first when cached decompression is preferred */
if (should_alloc_managed_pages(fe, sbi->opt.cache_strategy,
@@ -696,10 +725,10 @@ hitted:
* Ensure the current partial page belongs to this submit chain rather
* than other concurrent submit chains or the noio(bypass) chain since
* those chains are handled asynchronously thus the page cannot be used
- * for inplace I/O or pagevec (should be processed in strict order.)
+ * for inplace I/O or bvpage (should be processed in a strict order.)
*/
- tight &= (fe->mode >= COLLECT_PRIMARY_HOOKED &&
- fe->mode != COLLECT_PRIMARY_FOLLOWED_NOINPLACE);
+ tight &= (fe->mode >= Z_EROFS_PCLUSTER_HOOKED &&
+ fe->mode != Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE);
cur = end - min_t(unsigned int, offset + end - map->m_la, end);
if (!(map->m_flags & EROFS_MAP_MAPPED)) {
@@ -707,60 +736,59 @@ hitted:
goto next_part;
}
- /* let's derive page type */
- page_type = cur ? Z_EROFS_VLE_PAGE_TYPE_HEAD :
- (!spiltted ? Z_EROFS_PAGE_TYPE_EXCLUSIVE :
- (tight ? Z_EROFS_PAGE_TYPE_EXCLUSIVE :
- Z_EROFS_VLE_PAGE_TYPE_TAIL_SHARED));
-
+ exclusive = (!cur && (!spiltted || tight));
if (cur)
- tight &= (fe->mode >= COLLECT_PRIMARY_FOLLOWED);
+ tight &= (fe->mode >= Z_EROFS_PCLUSTER_FOLLOWED);
retry:
- err = z_erofs_attach_page(fe, page, page_type,
- fe->mode >= COLLECT_PRIMARY_FOLLOWED);
- /* should allocate an additional short-lived page for pagevec */
- if (err == -EAGAIN) {
- struct page *const newpage =
- alloc_page(GFP_NOFS | __GFP_NOFAIL);
-
- set_page_private(newpage, Z_EROFS_SHORTLIVED_PAGE);
- err = z_erofs_attach_page(fe, newpage,
- Z_EROFS_PAGE_TYPE_EXCLUSIVE, true);
- if (!err)
- goto retry;
+ err = z_erofs_attach_page(fe, &((struct z_erofs_bvec) {
+ .page = page,
+ .offset = offset - map->m_la,
+ .end = end,
+ }), exclusive);
+ /* should allocate an additional short-lived page for bvset */
+ if (err == -EAGAIN && !fe->candidate_bvpage) {
+ fe->candidate_bvpage = alloc_page(GFP_NOFS | __GFP_NOFAIL);
+ set_page_private(fe->candidate_bvpage,
+ Z_EROFS_SHORTLIVED_PAGE);
+ goto retry;
}
- if (err)
- goto err_out;
-
- index = page->index - (map->m_la >> PAGE_SHIFT);
-
- z_erofs_onlinepage_fixup(page, index, true);
+ if (err) {
+ DBG_BUGON(err == -EAGAIN && fe->candidate_bvpage);
+ goto out;
+ }
+ z_erofs_onlinepage_split(page);
/* bump up the number of spiltted parts of a page */
++spiltted;
- /* also update nr_pages */
- fe->pcl->nr_pages = max_t(pgoff_t, fe->pcl->nr_pages, index + 1);
+ if (fe->pcl->pageofs_out != (map->m_la & ~PAGE_MASK))
+ fe->pcl->multibases = true;
+
+ if ((map->m_flags & EROFS_MAP_FULL_MAPPED) &&
+ fe->pcl->length == map->m_llen)
+ fe->pcl->partial = false;
+ if (fe->pcl->length < offset + end - map->m_la) {
+ fe->pcl->length = offset + end - map->m_la;
+ fe->pcl->pageofs_out = map->m_la & ~PAGE_MASK;
+ }
next_part:
- /* can be used for verification */
+ /* shorten the remaining extent to update progress */
map->m_llen = offset + cur - map->m_la;
+ map->m_flags &= ~EROFS_MAP_FULL_MAPPED;
end = cur;
if (end > 0)
goto repeat;
out:
+ if (err)
+ z_erofs_page_mark_eio(page);
z_erofs_onlinepage_endio(page);
erofs_dbg("%s, finish page: %pK spiltted: %u map->m_llen %llu",
__func__, page, spiltted, map->m_llen);
return err;
-
- /* if some error occurred while processing this page */
-err_out:
- SetPageError(page);
- goto out;
}
static bool z_erofs_get_sync_decompress_policy(struct erofs_sb_info *sbi,
@@ -783,97 +811,137 @@ static bool z_erofs_page_is_invalidated(struct page *page)
return !page->mapping && !z_erofs_is_shortlived_page(page);
}
-static int z_erofs_decompress_pcluster(struct super_block *sb,
- struct z_erofs_pcluster *pcl,
- struct page **pagepool)
-{
- struct erofs_sb_info *const sbi = EROFS_SB(sb);
- unsigned int pclusterpages = z_erofs_pclusterpages(pcl);
- struct z_erofs_pagevec_ctor ctor;
- unsigned int i, inputsize, outputsize, llen, nr_pages;
- struct page *pages_onstack[Z_EROFS_VMAP_ONSTACK_PAGES];
- struct page **pages, **compressed_pages, *page;
+struct z_erofs_decompress_backend {
+ struct page *onstack_pages[Z_EROFS_ONSTACK_PAGES];
+ struct super_block *sb;
+ struct z_erofs_pcluster *pcl;
- enum z_erofs_page_type page_type;
- bool overlapped, partial;
- int err;
+ /* pages with the longest decompressed length for deduplication */
+ struct page **decompressed_pages;
+ /* pages to keep the compressed data */
+ struct page **compressed_pages;
- might_sleep();
- DBG_BUGON(!READ_ONCE(pcl->nr_pages));
+ struct list_head decompressed_secondary_bvecs;
+ struct page **pagepool;
+ unsigned int onstack_used, nr_pages;
+};
- mutex_lock(&pcl->lock);
- nr_pages = pcl->nr_pages;
+struct z_erofs_bvec_item {
+ struct z_erofs_bvec bvec;
+ struct list_head list;
+};
- if (nr_pages <= Z_EROFS_VMAP_ONSTACK_PAGES) {
- pages = pages_onstack;
- } else if (nr_pages <= Z_EROFS_VMAP_GLOBAL_PAGES &&
- mutex_trylock(&z_pagemap_global_lock)) {
- pages = z_pagemap_global;
- } else {
- gfp_t gfp_flags = GFP_KERNEL;
+static void z_erofs_do_decompressed_bvec(struct z_erofs_decompress_backend *be,
+ struct z_erofs_bvec *bvec)
+{
+ struct z_erofs_bvec_item *item;
- if (nr_pages > Z_EROFS_VMAP_GLOBAL_PAGES)
- gfp_flags |= __GFP_NOFAIL;
+ if (!((bvec->offset + be->pcl->pageofs_out) & ~PAGE_MASK)) {
+ unsigned int pgnr;
+ struct page *oldpage;
- pages = kvmalloc_array(nr_pages, sizeof(struct page *),
- gfp_flags);
+ pgnr = (bvec->offset + be->pcl->pageofs_out) >> PAGE_SHIFT;
+ DBG_BUGON(pgnr >= be->nr_pages);
+ oldpage = be->decompressed_pages[pgnr];
+ be->decompressed_pages[pgnr] = bvec->page;
- /* fallback to global pagemap for the lowmem scenario */
- if (!pages) {
- mutex_lock(&z_pagemap_global_lock);
- pages = z_pagemap_global;
- }
+ if (!oldpage)
+ return;
}
- for (i = 0; i < nr_pages; ++i)
- pages[i] = NULL;
-
- err = 0;
- z_erofs_pagevec_ctor_init(&ctor, Z_EROFS_NR_INLINE_PAGEVECS,
- pcl->pagevec, 0);
-
- for (i = 0; i < pcl->vcnt; ++i) {
- unsigned int pagenr;
+ /* (cold path) one pcluster is requested multiple times */
+ item = kmalloc(sizeof(*item), GFP_KERNEL | __GFP_NOFAIL);
+ item->bvec = *bvec;
+ list_add(&item->list, &be->decompressed_secondary_bvecs);
+}
- page = z_erofs_pagevec_dequeue(&ctor, &page_type);
+static void z_erofs_fill_other_copies(struct z_erofs_decompress_backend *be,
+ int err)
+{
+ unsigned int off0 = be->pcl->pageofs_out;
+ struct list_head *p, *n;
+
+ list_for_each_safe(p, n, &be->decompressed_secondary_bvecs) {
+ struct z_erofs_bvec_item *bvi;
+ unsigned int end, cur;
+ void *dst, *src;
+
+ bvi = container_of(p, struct z_erofs_bvec_item, list);
+ cur = bvi->bvec.offset < 0 ? -bvi->bvec.offset : 0;
+ end = min_t(unsigned int, be->pcl->length - bvi->bvec.offset,
+ bvi->bvec.end);
+ dst = kmap_local_page(bvi->bvec.page);
+ while (cur < end) {
+ unsigned int pgnr, scur, len;
+
+ pgnr = (bvi->bvec.offset + cur + off0) >> PAGE_SHIFT;
+ DBG_BUGON(pgnr >= be->nr_pages);
+
+ scur = bvi->bvec.offset + cur -
+ ((pgnr << PAGE_SHIFT) - off0);
+ len = min_t(unsigned int, end - cur, PAGE_SIZE - scur);
+ if (!be->decompressed_pages[pgnr]) {
+ err = -EFSCORRUPTED;
+ cur += len;
+ continue;
+ }
+ src = kmap_local_page(be->decompressed_pages[pgnr]);
+ memcpy(dst + cur, src + scur, len);
+ kunmap_local(src);
+ cur += len;
+ }
+ kunmap_local(dst);
+ if (err)
+ z_erofs_page_mark_eio(bvi->bvec.page);
+ z_erofs_onlinepage_endio(bvi->bvec.page);
+ list_del(p);
+ kfree(bvi);
+ }
+}
- /* all pages in pagevec ought to be valid */
- DBG_BUGON(!page);
- DBG_BUGON(z_erofs_page_is_invalidated(page));
+static void z_erofs_parse_out_bvecs(struct z_erofs_decompress_backend *be)
+{
+ struct z_erofs_pcluster *pcl = be->pcl;
+ struct z_erofs_bvec_iter biter;
+ struct page *old_bvpage;
+ int i;
- if (z_erofs_put_shortlivedpage(pagepool, page))
- continue;
+ z_erofs_bvec_iter_begin(&biter, &pcl->bvset, Z_EROFS_INLINE_BVECS, 0);
+ for (i = 0; i < pcl->vcnt; ++i) {
+ struct z_erofs_bvec bvec;
- if (page_type == Z_EROFS_VLE_PAGE_TYPE_HEAD)
- pagenr = 0;
- else
- pagenr = z_erofs_onlinepage_index(page);
+ z_erofs_bvec_dequeue(&biter, &bvec, &old_bvpage);
- DBG_BUGON(pagenr >= nr_pages);
+ if (old_bvpage)
+ z_erofs_put_shortlivedpage(be->pagepool, old_bvpage);
- /*
- * currently EROFS doesn't support multiref(dedup),
- * so here erroring out one multiref page.
- */
- if (pages[pagenr]) {
- DBG_BUGON(1);
- SetPageError(pages[pagenr]);
- z_erofs_onlinepage_endio(pages[pagenr]);
- err = -EFSCORRUPTED;
- }
- pages[pagenr] = page;
+ DBG_BUGON(z_erofs_page_is_invalidated(bvec.page));
+ z_erofs_do_decompressed_bvec(be, &bvec);
}
- z_erofs_pagevec_ctor_exit(&ctor, true);
- overlapped = false;
- compressed_pages = pcl->compressed_pages;
+ old_bvpage = z_erofs_bvec_iter_end(&biter);
+ if (old_bvpage)
+ z_erofs_put_shortlivedpage(be->pagepool, old_bvpage);
+}
+static int z_erofs_parse_in_bvecs(struct z_erofs_decompress_backend *be,
+ bool *overlapped)
+{
+ struct z_erofs_pcluster *pcl = be->pcl;
+ unsigned int pclusterpages = z_erofs_pclusterpages(pcl);
+ int i, err = 0;
+
+ *overlapped = false;
for (i = 0; i < pclusterpages; ++i) {
- unsigned int pagenr;
+ struct z_erofs_bvec *bvec = &pcl->compressed_bvecs[i];
+ struct page *page = bvec->page;
- page = compressed_pages[i];
- /* all compressed pages ought to be valid */
- DBG_BUGON(!page);
+ /* compressed pages ought to be present before decompressing */
+ if (!page) {
+ DBG_BUGON(1);
+ continue;
+ }
+ be->compressed_pages[i] = page;
if (z_erofs_is_inline_pcluster(pcl)) {
if (!PageUptodate(page))
@@ -883,109 +951,129 @@ static int z_erofs_decompress_pcluster(struct super_block *sb,
DBG_BUGON(z_erofs_page_is_invalidated(page));
if (!z_erofs_is_shortlived_page(page)) {
- if (erofs_page_is_managed(sbi, page)) {
+ if (erofs_page_is_managed(EROFS_SB(be->sb), page)) {
if (!PageUptodate(page))
err = -EIO;
continue;
}
+ z_erofs_do_decompressed_bvec(be, bvec);
+ *overlapped = true;
+ }
+ }
- /*
- * only if non-head page can be selected
- * for inplace decompression
- */
- pagenr = z_erofs_onlinepage_index(page);
-
- DBG_BUGON(pagenr >= nr_pages);
- if (pages[pagenr]) {
- DBG_BUGON(1);
- SetPageError(pages[pagenr]);
- z_erofs_onlinepage_endio(pages[pagenr]);
- err = -EFSCORRUPTED;
- }
- pages[pagenr] = page;
+ if (err)
+ return err;
+ return 0;
+}
- overlapped = true;
- }
+static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
+ int err)
+{
+ struct erofs_sb_info *const sbi = EROFS_SB(be->sb);
+ struct z_erofs_pcluster *pcl = be->pcl;
+ unsigned int pclusterpages = z_erofs_pclusterpages(pcl);
+ unsigned int i, inputsize;
+ int err2;
+ struct page *page;
+ bool overlapped;
- /* PG_error needs checking for all non-managed pages */
- if (PageError(page)) {
- DBG_BUGON(PageUptodate(page));
- err = -EIO;
- }
+ mutex_lock(&pcl->lock);
+ be->nr_pages = PAGE_ALIGN(pcl->length + pcl->pageofs_out) >> PAGE_SHIFT;
+
+ /* allocate (de)compressed page arrays if cannot be kept on stack */
+ be->decompressed_pages = NULL;
+ be->compressed_pages = NULL;
+ be->onstack_used = 0;
+ if (be->nr_pages <= Z_EROFS_ONSTACK_PAGES) {
+ be->decompressed_pages = be->onstack_pages;
+ be->onstack_used = be->nr_pages;
+ memset(be->decompressed_pages, 0,
+ sizeof(struct page *) * be->nr_pages);
}
+ if (pclusterpages + be->onstack_used <= Z_EROFS_ONSTACK_PAGES)
+ be->compressed_pages = be->onstack_pages + be->onstack_used;
+
+ if (!be->decompressed_pages)
+ be->decompressed_pages =
+ kvcalloc(be->nr_pages, sizeof(struct page *),
+ GFP_KERNEL | __GFP_NOFAIL);
+ if (!be->compressed_pages)
+ be->compressed_pages =
+ kvcalloc(pclusterpages, sizeof(struct page *),
+ GFP_KERNEL | __GFP_NOFAIL);
+
+ z_erofs_parse_out_bvecs(be);
+ err2 = z_erofs_parse_in_bvecs(be, &overlapped);
+ if (err2)
+ err = err2;
if (err)
goto out;
- llen = pcl->length >> Z_EROFS_PCLUSTER_LENGTH_BIT;
- if (nr_pages << PAGE_SHIFT >= pcl->pageofs_out + llen) {
- outputsize = llen;
- partial = !(pcl->length & Z_EROFS_PCLUSTER_FULL_LENGTH);
- } else {
- outputsize = (nr_pages << PAGE_SHIFT) - pcl->pageofs_out;
- partial = true;
- }
-
if (z_erofs_is_inline_pcluster(pcl))
inputsize = pcl->tailpacking_size;
else
inputsize = pclusterpages * PAGE_SIZE;
err = z_erofs_decompress(&(struct z_erofs_decompress_req) {
- .sb = sb,
- .in = compressed_pages,
- .out = pages,
+ .sb = be->sb,
+ .in = be->compressed_pages,
+ .out = be->decompressed_pages,
.pageofs_in = pcl->pageofs_in,
.pageofs_out = pcl->pageofs_out,
.inputsize = inputsize,
- .outputsize = outputsize,
+ .outputsize = pcl->length,
.alg = pcl->algorithmformat,
.inplace_io = overlapped,
- .partial_decoding = partial
- }, pagepool);
+ .partial_decoding = pcl->partial,
+ .fillgaps = pcl->multibases,
+ }, be->pagepool);
out:
/* must handle all compressed pages before actual file pages */
if (z_erofs_is_inline_pcluster(pcl)) {
- page = compressed_pages[0];
- WRITE_ONCE(compressed_pages[0], NULL);
+ page = pcl->compressed_bvecs[0].page;
+ WRITE_ONCE(pcl->compressed_bvecs[0].page, NULL);
put_page(page);
} else {
for (i = 0; i < pclusterpages; ++i) {
- page = compressed_pages[i];
+ page = pcl->compressed_bvecs[i].page;
if (erofs_page_is_managed(sbi, page))
continue;
/* recycle all individual short-lived pages */
- (void)z_erofs_put_shortlivedpage(pagepool, page);
- WRITE_ONCE(compressed_pages[i], NULL);
+ (void)z_erofs_put_shortlivedpage(be->pagepool, page);
+ WRITE_ONCE(pcl->compressed_bvecs[i].page, NULL);
}
}
+ if (be->compressed_pages < be->onstack_pages ||
+ be->compressed_pages >= be->onstack_pages + Z_EROFS_ONSTACK_PAGES)
+ kvfree(be->compressed_pages);
+ z_erofs_fill_other_copies(be, err);
- for (i = 0; i < nr_pages; ++i) {
- page = pages[i];
+ for (i = 0; i < be->nr_pages; ++i) {
+ page = be->decompressed_pages[i];
if (!page)
continue;
DBG_BUGON(z_erofs_page_is_invalidated(page));
/* recycle all individual short-lived pages */
- if (z_erofs_put_shortlivedpage(pagepool, page))
+ if (z_erofs_put_shortlivedpage(be->pagepool, page))
continue;
-
- if (err < 0)
- SetPageError(page);
-
+ if (err)
+ z_erofs_page_mark_eio(page);
z_erofs_onlinepage_endio(page);
}
- if (pages == z_pagemap_global)
- mutex_unlock(&z_pagemap_global_lock);
- else if (pages != pages_onstack)
- kvfree(pages);
+ if (be->decompressed_pages != be->onstack_pages)
+ kvfree(be->decompressed_pages);
- pcl->nr_pages = 0;
+ pcl->length = 0;
+ pcl->partial = true;
+ pcl->multibases = false;
+ pcl->bvset.nextpage = NULL;
pcl->vcnt = 0;
/* pcluster lock MUST be taken before the following line */
@@ -997,22 +1085,25 @@ out:
static void z_erofs_decompress_queue(const struct z_erofs_decompressqueue *io,
struct page **pagepool)
{
+ struct z_erofs_decompress_backend be = {
+ .sb = io->sb,
+ .pagepool = pagepool,
+ .decompressed_secondary_bvecs =
+ LIST_HEAD_INIT(be.decompressed_secondary_bvecs),
+ };
z_erofs_next_pcluster_t owned = io->head;
while (owned != Z_EROFS_PCLUSTER_TAIL_CLOSED) {
- struct z_erofs_pcluster *pcl;
-
- /* no possible that 'owned' equals Z_EROFS_WORK_TPTR_TAIL */
+ /* impossible that 'owned' equals Z_EROFS_WORK_TPTR_TAIL */
DBG_BUGON(owned == Z_EROFS_PCLUSTER_TAIL);
-
- /* no possible that 'owned' equals NULL */
+ /* impossible that 'owned' equals Z_EROFS_PCLUSTER_NIL */
DBG_BUGON(owned == Z_EROFS_PCLUSTER_NIL);
- pcl = container_of(owned, struct z_erofs_pcluster, next);
- owned = READ_ONCE(pcl->next);
+ be.pcl = container_of(owned, struct z_erofs_pcluster, next);
+ owned = READ_ONCE(be.pcl->next);
- z_erofs_decompress_pcluster(io->sb, pcl, pagepool);
- erofs_workgroup_put(&pcl->obj);
+ z_erofs_decompress_pcluster(&be, io->eio ? -EIO : 0);
+ erofs_workgroup_put(&be.pcl->obj);
}
}
@@ -1038,7 +1129,6 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io,
if (sync) {
if (!atomic_add_return(bios, &io->pending_bios))
complete(&io->u.done);
-
return;
}
@@ -1071,7 +1161,7 @@ static struct page *pickup_page_for_submission(struct z_erofs_pcluster *pcl,
int justfound;
repeat:
- page = READ_ONCE(pcl->compressed_pages[nr]);
+ page = READ_ONCE(pcl->compressed_bvecs[nr].page);
oldpage = page;
if (!page)
@@ -1087,7 +1177,7 @@ repeat:
* otherwise, it will go inplace I/O path instead.
*/
if (page->private == Z_EROFS_PREALLOCATED_PAGE) {
- WRITE_ONCE(pcl->compressed_pages[nr], page);
+ WRITE_ONCE(pcl->compressed_bvecs[nr].page, page);
set_page_private(page, 0);
tocache = true;
goto out_tocache;
@@ -1113,14 +1203,13 @@ repeat:
/* the page is still in manage cache */
if (page->mapping == mc) {
- WRITE_ONCE(pcl->compressed_pages[nr], page);
+ WRITE_ONCE(pcl->compressed_bvecs[nr].page, page);
- ClearPageError(page);
if (!PagePrivate(page)) {
/*
* impossible to be !PagePrivate(page) for
* the current restriction as well if
- * the page is already in compressed_pages[].
+ * the page is already in compressed_bvecs[].
*/
DBG_BUGON(!justfound);
@@ -1149,7 +1238,8 @@ repeat:
put_page(page);
out_allocpage:
page = erofs_allocpage(pagepool, gfp | __GFP_NOFAIL);
- if (oldpage != cmpxchg(&pcl->compressed_pages[nr], oldpage, page)) {
+ if (oldpage != cmpxchg(&pcl->compressed_bvecs[nr].page,
+ oldpage, page)) {
erofs_pagepool_add(pagepool, page);
cond_resched();
goto repeat;
@@ -1186,6 +1276,7 @@ fg_out:
q = fgq;
init_completion(&fgq->u.done);
atomic_set(&fgq->pending_bios, 0);
+ q->eio = false;
}
q->sb = sb;
q->head = Z_EROFS_PCLUSTER_TAIL_CLOSED;
@@ -1246,26 +1337,25 @@ static void z_erofs_decompressqueue_endio(struct bio *bio)
DBG_BUGON(PageUptodate(page));
DBG_BUGON(z_erofs_page_is_invalidated(page));
- if (err)
- SetPageError(page);
-
if (erofs_page_is_managed(EROFS_SB(q->sb), page)) {
if (!err)
SetPageUptodate(page);
unlock_page(page);
}
}
+ if (err)
+ q->eio = true;
z_erofs_decompress_kickoff(q, tagptr_unfold_tags(t), -1);
bio_put(bio);
}
-static void z_erofs_submit_queue(struct super_block *sb,
- struct z_erofs_decompress_frontend *f,
+static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
struct page **pagepool,
struct z_erofs_decompressqueue *fgq,
bool *force_fg)
{
- struct erofs_sb_info *const sbi = EROFS_SB(sb);
+ struct super_block *sb = f->inode->i_sb;
+ struct address_space *mc = MNGD_MAPPING(EROFS_SB(sb));
z_erofs_next_pcluster_t qtail[NR_JOBQUEUES];
struct z_erofs_decompressqueue *q[NR_JOBQUEUES];
void *bi_private;
@@ -1317,7 +1407,7 @@ static void z_erofs_submit_queue(struct super_block *sb,
struct page *page;
page = pickup_page_for_submission(pcl, i++, pagepool,
- MNGD_MAPPING(sbi));
+ mc);
if (!page)
continue;
@@ -1369,15 +1459,14 @@ submit_bio_retry:
z_erofs_decompress_kickoff(q[JQ_SUBMIT], *force_fg, nr_bios);
}
-static void z_erofs_runqueue(struct super_block *sb,
- struct z_erofs_decompress_frontend *f,
+static void z_erofs_runqueue(struct z_erofs_decompress_frontend *f,
struct page **pagepool, bool force_fg)
{
struct z_erofs_decompressqueue io[NR_JOBQUEUES];
if (f->owned_head == Z_EROFS_PCLUSTER_TAIL)
return;
- z_erofs_submit_queue(sb, f, pagepool, io, &force_fg);
+ z_erofs_submit_queue(f, pagepool, io, &force_fg);
/* handle bypass queue (no i/o pclusters) immediately */
z_erofs_decompress_queue(&io[JQ_BYPASS], pagepool);
@@ -1475,7 +1564,7 @@ static int z_erofs_read_folio(struct file *file, struct folio *folio)
(void)z_erofs_collector_end(&f);
/* if some compressed cluster ready, need submit them anyway */
- z_erofs_runqueue(inode->i_sb, &f, &pagepool,
+ z_erofs_runqueue(&f, &pagepool,
z_erofs_get_sync_decompress_policy(sbi, 0));
if (err)
@@ -1524,7 +1613,7 @@ static void z_erofs_readahead(struct readahead_control *rac)
z_erofs_pcluster_readmore(&f, rac, 0, &pagepool, false);
(void)z_erofs_collector_end(&f);
- z_erofs_runqueue(inode->i_sb, &f, &pagepool,
+ z_erofs_runqueue(&f, &pagepool,
z_erofs_get_sync_decompress_policy(sbi, nr_pages));
erofs_put_metabuf(&f.map.buf);
erofs_release_pages(&pagepool);
diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h
index 58053bb5066f..e7f04c4fbb81 100644
--- a/fs/erofs/zdata.h
+++ b/fs/erofs/zdata.h
@@ -7,13 +7,10 @@
#define __EROFS_FS_ZDATA_H
#include "internal.h"
-#include "zpvec.h"
+#include "tagptr.h"
#define Z_EROFS_PCLUSTER_MAX_PAGES (Z_EROFS_PCLUSTER_MAX_SIZE / PAGE_SIZE)
-#define Z_EROFS_NR_INLINE_PAGEVECS 3
-
-#define Z_EROFS_PCLUSTER_FULL_LENGTH 0x00000001
-#define Z_EROFS_PCLUSTER_LENGTH_BIT 1
+#define Z_EROFS_INLINE_BVECS 2
/*
* let's leave a type here in case of introducing
@@ -21,6 +18,21 @@
*/
typedef void *z_erofs_next_pcluster_t;
+struct z_erofs_bvec {
+ struct page *page;
+ int offset;
+ unsigned int end;
+};
+
+#define __Z_EROFS_BVSET(name, total) \
+struct name { \
+ /* point to the next page which contains the following bvecs */ \
+ struct page *nextpage; \
+ struct z_erofs_bvec bvec[total]; \
+}
+__Z_EROFS_BVSET(z_erofs_bvset,);
+__Z_EROFS_BVSET(z_erofs_bvset_inline, Z_EROFS_INLINE_BVECS);
+
/*
* Structure fields follow one of the following exclusion rules.
*
@@ -38,24 +50,21 @@ struct z_erofs_pcluster {
/* A: point to next chained pcluster or TAILs */
z_erofs_next_pcluster_t next;
- /* A: lower limit of decompressed length and if full length or not */
+ /* L: the maximum decompression size of this round */
unsigned int length;
+ /* L: total number of bvecs */
+ unsigned int vcnt;
+
/* I: page offset of start position of decompression */
unsigned short pageofs_out;
/* I: page offset of inline compressed data */
unsigned short pageofs_in;
- /* L: maximum relative page index in pagevec[] */
- unsigned short nr_pages;
-
- /* L: total number of pages in pagevec[] */
- unsigned int vcnt;
-
union {
- /* L: inline a certain number of pagevecs for bootstrap */
- erofs_vtptr_t pagevec[Z_EROFS_NR_INLINE_PAGEVECS];
+ /* L: inline a certain number of bvec for bootstrap */
+ struct z_erofs_bvset_inline bvset;
/* I: can be used to free the pcluster by RCU. */
struct rcu_head rcu;
@@ -72,8 +81,14 @@ struct z_erofs_pcluster {
/* I: compression algorithm format */
unsigned char algorithmformat;
- /* A: compressed pages (can be cached or inplaced pages) */
- struct page *compressed_pages[];
+ /* L: whether partial decompression or not */
+ bool partial;
+
+ /* L: indicate several pageofs_outs or not */
+ bool multibases;
+
+ /* A: compressed bvecs (can be cached or inplaced pages) */
+ struct z_erofs_bvec compressed_bvecs[];
};
/* let's avoid the valid 32-bit kernel addresses */
@@ -94,6 +109,8 @@ struct z_erofs_decompressqueue {
struct completion done;
struct work_struct work;
} u;
+
+ bool eio;
};
static inline bool z_erofs_is_inline_pcluster(struct z_erofs_pcluster *pcl)
@@ -108,38 +125,17 @@ static inline unsigned int z_erofs_pclusterpages(struct z_erofs_pcluster *pcl)
return pcl->pclusterpages;
}
-#define Z_EROFS_ONLINEPAGE_COUNT_BITS 2
-#define Z_EROFS_ONLINEPAGE_COUNT_MASK ((1 << Z_EROFS_ONLINEPAGE_COUNT_BITS) - 1)
-#define Z_EROFS_ONLINEPAGE_INDEX_SHIFT (Z_EROFS_ONLINEPAGE_COUNT_BITS)
-
/*
- * waiters (aka. ongoing_packs): # to unlock the page
- * sub-index: 0 - for partial page, >= 1 full page sub-index
+ * bit 31: I/O error occurred on this page
+ * bit 0 - 30: remaining parts to complete this page
*/
-typedef atomic_t z_erofs_onlinepage_t;
-
-/* type punning */
-union z_erofs_onlinepage_converter {
- z_erofs_onlinepage_t *o;
- unsigned long *v;
-};
-
-static inline unsigned int z_erofs_onlinepage_index(struct page *page)
-{
- union z_erofs_onlinepage_converter u;
-
- DBG_BUGON(!PagePrivate(page));
- u.v = &page_private(page);
-
- return atomic_read(u.o) >> Z_EROFS_ONLINEPAGE_INDEX_SHIFT;
-}
+#define Z_EROFS_PAGE_EIO (1 << 31)
static inline void z_erofs_onlinepage_init(struct page *page)
{
union {
- z_erofs_onlinepage_t o;
+ atomic_t o;
unsigned long v;
- /* keep from being unlocked in advance */
} u = { .o = ATOMIC_INIT(1) };
set_page_private(page, u.v);
@@ -147,49 +143,36 @@ static inline void z_erofs_onlinepage_init(struct page *page)
SetPagePrivate(page);
}
-static inline void z_erofs_onlinepage_fixup(struct page *page,
- uintptr_t index, bool down)
+static inline void z_erofs_onlinepage_split(struct page *page)
{
- union z_erofs_onlinepage_converter u = { .v = &page_private(page) };
- int orig, orig_index, val;
-
-repeat:
- orig = atomic_read(u.o);
- orig_index = orig >> Z_EROFS_ONLINEPAGE_INDEX_SHIFT;
- if (orig_index) {
- if (!index)
- return;
+ atomic_inc((atomic_t *)&page->private);
+}
- DBG_BUGON(orig_index != index);
- }
+static inline void z_erofs_page_mark_eio(struct page *page)
+{
+ int orig;
- val = (index << Z_EROFS_ONLINEPAGE_INDEX_SHIFT) |
- ((orig & Z_EROFS_ONLINEPAGE_COUNT_MASK) + (unsigned int)down);
- if (atomic_cmpxchg(u.o, orig, val) != orig)
- goto repeat;
+ do {
+ orig = atomic_read((atomic_t *)&page->private);
+ } while (atomic_cmpxchg((atomic_t *)&page->private, orig,
+ orig | Z_EROFS_PAGE_EIO) != orig);
}
static inline void z_erofs_onlinepage_endio(struct page *page)
{
- union z_erofs_onlinepage_converter u;
unsigned int v;
DBG_BUGON(!PagePrivate(page));
- u.v = &page_private(page);
-
- v = atomic_dec_return(u.o);
- if (!(v & Z_EROFS_ONLINEPAGE_COUNT_MASK)) {
+ v = atomic_dec_return((atomic_t *)&page->private);
+ if (!(v & ~Z_EROFS_PAGE_EIO)) {
set_page_private(page, 0);
ClearPagePrivate(page);
- if (!PageError(page))
+ if (!(v & Z_EROFS_PAGE_EIO))
SetPageUptodate(page);
unlock_page(page);
}
- erofs_dbg("%s, page %p value %x", __func__, page, atomic_read(u.o));
}
-#define Z_EROFS_VMAP_ONSTACK_PAGES \
- min_t(unsigned int, THREAD_SIZE / 8 / sizeof(struct page *), 96U)
-#define Z_EROFS_VMAP_GLOBAL_PAGES 2048
+#define Z_EROFS_ONSTACK_PAGES 32
#endif
diff --git a/fs/erofs/zpvec.h b/fs/erofs/zpvec.h
deleted file mode 100644
index b05464f4a808..000000000000
--- a/fs/erofs/zpvec.h
+++ /dev/null
@@ -1,159 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2018 HUAWEI, Inc.
- * https://www.huawei.com/
- */
-#ifndef __EROFS_FS_ZPVEC_H
-#define __EROFS_FS_ZPVEC_H
-
-#include "tagptr.h"
-
-/* page type in pagevec for decompress subsystem */
-enum z_erofs_page_type {
- /* including Z_EROFS_VLE_PAGE_TAIL_EXCLUSIVE */
- Z_EROFS_PAGE_TYPE_EXCLUSIVE,
-
- Z_EROFS_VLE_PAGE_TYPE_TAIL_SHARED,
-
- Z_EROFS_VLE_PAGE_TYPE_HEAD,
- Z_EROFS_VLE_PAGE_TYPE_MAX
-};
-
-extern void __compiletime_error("Z_EROFS_PAGE_TYPE_EXCLUSIVE != 0")
- __bad_page_type_exclusive(void);
-
-/* pagevec tagged pointer */
-typedef tagptr2_t erofs_vtptr_t;
-
-/* pagevec collector */
-struct z_erofs_pagevec_ctor {
- struct page *curr, *next;
- erofs_vtptr_t *pages;
-
- unsigned int nr, index;
-};
-
-static inline void z_erofs_pagevec_ctor_exit(struct z_erofs_pagevec_ctor *ctor,
- bool atomic)
-{
- if (!ctor->curr)
- return;
-
- if (atomic)
- kunmap_atomic(ctor->pages);
- else
- kunmap(ctor->curr);
-}
-
-static inline struct page *
-z_erofs_pagevec_ctor_next_page(struct z_erofs_pagevec_ctor *ctor,
- unsigned int nr)
-{
- unsigned int index;
-
- /* keep away from occupied pages */
- if (ctor->next)
- return ctor->next;
-
- for (index = 0; index < nr; ++index) {
- const erofs_vtptr_t t = ctor->pages[index];
- const unsigned int tags = tagptr_unfold_tags(t);
-
- if (tags == Z_EROFS_PAGE_TYPE_EXCLUSIVE)
- return tagptr_unfold_ptr(t);
- }
- DBG_BUGON(nr >= ctor->nr);
- return NULL;
-}
-
-static inline void
-z_erofs_pagevec_ctor_pagedown(struct z_erofs_pagevec_ctor *ctor,
- bool atomic)
-{
- struct page *next = z_erofs_pagevec_ctor_next_page(ctor, ctor->nr);
-
- z_erofs_pagevec_ctor_exit(ctor, atomic);
-
- ctor->curr = next;
- ctor->next = NULL;
- ctor->pages = atomic ?
- kmap_atomic(ctor->curr) : kmap(ctor->curr);
-
- ctor->nr = PAGE_SIZE / sizeof(struct page *);
- ctor->index = 0;
-}
-
-static inline void z_erofs_pagevec_ctor_init(struct z_erofs_pagevec_ctor *ctor,
- unsigned int nr,
- erofs_vtptr_t *pages,
- unsigned int i)
-{
- ctor->nr = nr;
- ctor->curr = ctor->next = NULL;
- ctor->pages = pages;
-
- if (i >= nr) {
- i -= nr;
- z_erofs_pagevec_ctor_pagedown(ctor, false);
- while (i > ctor->nr) {
- i -= ctor->nr;
- z_erofs_pagevec_ctor_pagedown(ctor, false);
- }
- }
- ctor->next = z_erofs_pagevec_ctor_next_page(ctor, i);
- ctor->index = i;
-}
-
-static inline bool z_erofs_pagevec_enqueue(struct z_erofs_pagevec_ctor *ctor,
- struct page *page,
- enum z_erofs_page_type type,
- bool pvec_safereuse)
-{
- if (!ctor->next) {
- /* some pages cannot be reused as pvec safely without I/O */
- if (type == Z_EROFS_PAGE_TYPE_EXCLUSIVE && !pvec_safereuse)
- type = Z_EROFS_VLE_PAGE_TYPE_TAIL_SHARED;
-
- if (type != Z_EROFS_PAGE_TYPE_EXCLUSIVE &&
- ctor->index + 1 == ctor->nr)
- return false;
- }
-
- if (ctor->index >= ctor->nr)
- z_erofs_pagevec_ctor_pagedown(ctor, false);
-
- /* exclusive page type must be 0 */
- if (Z_EROFS_PAGE_TYPE_EXCLUSIVE != (uintptr_t)NULL)
- __bad_page_type_exclusive();
-
- /* should remind that collector->next never equal to 1, 2 */
- if (type == (uintptr_t)ctor->next) {
- ctor->next = page;
- }
- ctor->pages[ctor->index++] = tagptr_fold(erofs_vtptr_t, page, type);
- return true;
-}
-
-static inline struct page *
-z_erofs_pagevec_dequeue(struct z_erofs_pagevec_ctor *ctor,
- enum z_erofs_page_type *type)
-{
- erofs_vtptr_t t;
-
- if (ctor->index >= ctor->nr) {
- DBG_BUGON(!ctor->next);
- z_erofs_pagevec_ctor_pagedown(ctor, true);
- }
-
- t = ctor->pages[ctor->index];
-
- *type = tagptr_unfold_tags(t);
-
- /* should remind that collector->next never equal to 1, 2 */
- if (*type == (uintptr_t)ctor->next)
- ctor->next = tagptr_unfold_ptr(t);
-
- ctor->pages[ctor->index++] = tagptr_fold(erofs_vtptr_t, NULL, 0);
- return tagptr_unfold_ptr(t);
-}
-#endif
diff --git a/fs/exec.c b/fs/exec.c
index 778123259e42..5fd73915c62c 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -65,6 +65,7 @@
#include <linux/io_uring.h>
#include <linux/syscall_user_dispatch.h>
#include <linux/coredump.h>
+#include <linux/time_namespace.h>
#include <linux/uaccess.h>
#include <asm/mmu_context.h>
@@ -630,7 +631,6 @@ int copy_string_kernel(const char *arg, struct linux_binprm *bprm)
unsigned int bytes_to_copy = min_t(unsigned int, len,
min_not_zero(offset_in_page(pos), PAGE_SIZE));
struct page *page;
- char *kaddr;
pos -= bytes_to_copy;
arg -= bytes_to_copy;
@@ -639,11 +639,8 @@ int copy_string_kernel(const char *arg, struct linux_binprm *bprm)
page = get_arg_page(bprm, pos, 1);
if (!page)
return -E2BIG;
- kaddr = kmap_atomic(page);
flush_arg_page(bprm, pos & PAGE_MASK, page);
- memcpy(kaddr + offset_in_page(pos), arg, bytes_to_copy);
- flush_dcache_page(page);
- kunmap_atomic(kaddr);
+ memcpy_to_page(page, offset_in_page(pos), arg, bytes_to_copy);
put_arg_page(page);
}
@@ -982,10 +979,12 @@ static int exec_mmap(struct mm_struct *mm)
{
struct task_struct *tsk;
struct mm_struct *old_mm, *active_mm;
+ bool vfork;
int ret;
/* Notify parent that we're no longer interested in the old VM */
tsk = current;
+ vfork = !!tsk->vfork_done;
old_mm = current->mm;
exec_mm_release(tsk, old_mm);
if (old_mm)
@@ -1030,6 +1029,10 @@ static int exec_mmap(struct mm_struct *mm)
tsk->mm->vmacache_seqnum = 0;
vmacache_flush(tsk);
task_unlock(tsk);
+
+ if (vfork)
+ timens_on_fork(tsk->nsproxy, tsk);
+
if (old_mm) {
mmap_read_unlock(old_mm);
BUG_ON(active_mm != old_mm);
@@ -1149,7 +1152,7 @@ static int de_thread(struct task_struct *tsk)
/*
* We are going to release_task()->ptrace_unlink() silently,
* the tracer can sleep in do_wait(). EXIT_DEAD guarantees
- * the tracer wont't block again waiting for this thread.
+ * the tracer won't block again waiting for this thread.
*/
if (unlikely(leader->ptrace))
__wake_up_parent(leader, leader->parent);
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index e6b932219803..7a192e4e7fa9 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -1679,14 +1679,14 @@ int ext2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
if (error)
return error;
- if (is_quota_modification(inode, iattr)) {
+ if (is_quota_modification(mnt_userns, inode, iattr)) {
error = dquot_initialize(inode);
if (error)
return error;
}
- if ((iattr->ia_valid & ATTR_UID && !uid_eq(iattr->ia_uid, inode->i_uid)) ||
- (iattr->ia_valid & ATTR_GID && !gid_eq(iattr->ia_gid, inode->i_gid))) {
- error = dquot_transfer(inode, iattr);
+ if (i_uid_needs_update(mnt_userns, iattr, inode) ||
+ i_gid_needs_update(mnt_userns, iattr, inode)) {
+ error = dquot_transfer(mnt_userns, inode, iattr);
if (error)
return error;
}
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index f6a19f6d9f6d..6f475d2e3b18 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1059,9 +1059,10 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_frags_per_group);
goto failed_mount;
}
- if (sbi->s_inodes_per_group > sb->s_blocksize * 8) {
+ if (sbi->s_inodes_per_group < sbi->s_inodes_per_block ||
+ sbi->s_inodes_per_group > sb->s_blocksize * 8) {
ext2_msg(sb, KERN_ERR,
- "error: #inodes per group too big: %lu",
+ "error: invalid #inodes per group: %lu",
sbi->s_inodes_per_group);
goto failed_mount;
}
@@ -1071,6 +1072,13 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) -
le32_to_cpu(es->s_first_data_block) - 1)
/ EXT2_BLOCKS_PER_GROUP(sb)) + 1;
+ if ((u64)sbi->s_groups_count * sbi->s_inodes_per_group !=
+ le32_to_cpu(es->s_inodes_count)) {
+ ext2_msg(sb, KERN_ERR, "error: invalid #inodes: %u vs computed %llu",
+ le32_to_cpu(es->s_inodes_count),
+ (u64)sbi->s_groups_count * sbi->s_inodes_per_group);
+ goto failed_mount;
+ }
db_count = (sbi->s_groups_count + EXT2_DESC_PER_BLOCK(sb) - 1) /
EXT2_DESC_PER_BLOCK(sb);
sbi->s_group_desc = kmalloc_array(db_count,
@@ -1490,8 +1498,7 @@ static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data,
len = i_size-off;
toread = len;
while (toread > 0) {
- tocopy = sb->s_blocksize - offset < toread ?
- sb->s_blocksize - offset : toread;
+ tocopy = min_t(size_t, sb->s_blocksize - offset, toread);
tmp_bh.b_state = 0;
tmp_bh.b_size = sb->s_blocksize;
@@ -1529,8 +1536,7 @@ static ssize_t ext2_quota_write(struct super_block *sb, int type,
struct buffer_head *bh;
while (towrite > 0) {
- tocopy = sb->s_blocksize - offset < towrite ?
- sb->s_blocksize - offset : towrite;
+ tocopy = min_t(size_t, sb->s_blocksize - offset, towrite);
tmp_bh.b_state = 0;
tmp_bh.b_size = sb->s_blocksize;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 75b8d81b2469..29fc575a4eb6 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -3058,14 +3058,14 @@ extern unsigned int ext4_list_backups(struct super_block *sb,
/* super.c */
extern struct buffer_head *ext4_sb_bread(struct super_block *sb,
- sector_t block, int op_flags);
+ sector_t block, blk_opf_t op_flags);
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, int op_flags,
+extern void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags,
bh_end_io_t *end_io);
-extern int ext4_read_bh(struct buffer_head *bh, int op_flags,
+extern int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags,
bh_end_io_t *end_io);
-extern int ext4_read_bh_lock(struct buffer_head *bh, int op_flags, bool wait);
+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);
extern int ext4_calculate_overhead(struct super_block *sb);
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 795a60ad1897..eb4c8ad1bb61 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -658,7 +658,7 @@ void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t star
static void ext4_fc_submit_bh(struct super_block *sb, bool is_tail)
{
- int write_flags = REQ_SYNC;
+ blk_opf_t write_flags = REQ_SYNC;
struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh;
/* Add REQ_FUA | REQ_PREFLUSH only its tail */
@@ -668,7 +668,7 @@ static void ext4_fc_submit_bh(struct super_block *sb, bool is_tail)
set_buffer_dirty(bh);
set_buffer_uptodate(bh);
bh->b_end_io = ext4_end_buffer_io_sync;
- submit_bh(REQ_OP_WRITE, write_flags, bh);
+ submit_bh(REQ_OP_WRITE | write_flags, bh);
EXT4_SB(sb)->s_fc_bh = NULL;
}
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 84c0eb55071d..3dcc1dd1f179 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5350,14 +5350,14 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
if (error)
return error;
- if (is_quota_modification(inode, attr)) {
+ if (is_quota_modification(mnt_userns, inode, attr)) {
error = dquot_initialize(inode);
if (error)
return error;
}
- if ((ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)) ||
- (ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) {
+ if (i_uid_needs_update(mnt_userns, attr, inode) ||
+ i_gid_needs_update(mnt_userns, attr, inode)) {
handle_t *handle;
/* (user+group)*(old+new) structure, inode write (sb,
@@ -5374,7 +5374,7 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
* counts xattr inode references.
*/
down_read(&EXT4_I(inode)->xattr_sem);
- error = dquot_transfer(inode, attr);
+ error = dquot_transfer(mnt_userns, inode, attr);
up_read(&EXT4_I(inode)->xattr_sem);
if (error) {
@@ -5383,10 +5383,8 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
}
/* Update corresponding info in inode so that everything is in
* one transaction */
- if (attr->ia_valid & ATTR_UID)
- inode->i_uid = attr->ia_uid;
- if (attr->ia_valid & ATTR_GID)
- inode->i_gid = attr->ia_gid;
+ i_uid_update(mnt_userns, attr, inode);
+ i_gid_update(mnt_userns, attr, inode);
error = ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
if (unlikely(error)) {
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 79d05e464c43..9af68a7ecdcf 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -52,7 +52,7 @@ static int write_mmp_block(struct super_block *sb, struct buffer_head *bh)
lock_buffer(bh);
bh->b_end_io = end_buffer_write_sync;
get_bh(bh);
- submit_bh(REQ_OP_WRITE, REQ_SYNC | REQ_META | REQ_PRIO, bh);
+ submit_bh(REQ_OP_WRITE | REQ_SYNC | REQ_META | REQ_PRIO, bh);
wait_on_buffer(bh);
sb_end_write(sb);
if (unlikely(!buffer_uptodate(bh)))
@@ -150,8 +150,6 @@ static int kmmpd(void *data)
mmp_check_interval = max(EXT4_MMP_CHECK_MULT * mmp_update_interval,
EXT4_MMP_MIN_CHECK_INTERVAL);
mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
- BUILD_BUG_ON(sizeof(mmp->mmp_bdevname) < BDEVNAME_SIZE);
- bdevname(bh->b_bdev, mmp->mmp_bdevname);
memcpy(mmp->mmp_nodename, init_utsname()->nodename,
sizeof(mmp->mmp_nodename));
@@ -372,13 +370,16 @@ skip:
EXT4_SB(sb)->s_mmp_bh = bh;
+ BUILD_BUG_ON(sizeof(mmp->mmp_bdevname) < BDEVNAME_SIZE);
+ snprintf(mmp->mmp_bdevname, sizeof(mmp->mmp_bdevname),
+ "%pg", bh->b_bdev);
+
/*
* Start a kernel thread to update the MMP block periodically.
*/
EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, sb, "kmmpd-%.*s",
(int)sizeof(mmp->mmp_bdevname),
- bdevname(bh->b_bdev,
- mmp->mmp_bdevname));
+ mmp->mmp_bdevname);
if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) {
EXT4_SB(sb)->s_mmp_tsk = NULL;
ext4_warning(sb, "Unable to create kmmpd thread for %s.",
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 845f2f8aee5f..2c68dec63e54 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -159,7 +159,7 @@ MODULE_ALIAS("ext3");
#define IS_EXT3_SB(sb) ((sb)->s_bdev->bd_holder == &ext3_fs_type)
-static inline void __ext4_read_bh(struct buffer_head *bh, int op_flags,
+static inline void __ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags,
bh_end_io_t *end_io)
{
/*
@@ -171,10 +171,10 @@ static inline void __ext4_read_bh(struct buffer_head *bh, int op_flags,
bh->b_end_io = end_io ? end_io : end_buffer_read_sync;
get_bh(bh);
- submit_bh(REQ_OP_READ, op_flags, bh);
+ submit_bh(REQ_OP_READ | op_flags, bh);
}
-void ext4_read_bh_nowait(struct buffer_head *bh, int op_flags,
+void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags,
bh_end_io_t *end_io)
{
BUG_ON(!buffer_locked(bh));
@@ -186,7 +186,7 @@ void ext4_read_bh_nowait(struct buffer_head *bh, int op_flags,
__ext4_read_bh(bh, op_flags, end_io);
}
-int ext4_read_bh(struct buffer_head *bh, int 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)
{
BUG_ON(!buffer_locked(bh));
@@ -203,7 +203,7 @@ int ext4_read_bh(struct buffer_head *bh, int op_flags, bh_end_io_t *end_io)
return -EIO;
}
-int ext4_read_bh_lock(struct buffer_head *bh, int op_flags, bool wait)
+int ext4_read_bh_lock(struct buffer_head *bh, blk_opf_t op_flags, bool wait)
{
if (trylock_buffer(bh)) {
if (wait)
@@ -227,8 +227,8 @@ int ext4_read_bh_lock(struct buffer_head *bh, int op_flags, bool wait)
* return.
*/
static struct buffer_head *__ext4_sb_bread_gfp(struct super_block *sb,
- sector_t block, int op_flags,
- gfp_t gfp)
+ sector_t block,
+ blk_opf_t op_flags, gfp_t gfp)
{
struct buffer_head *bh;
int ret;
@@ -248,7 +248,7 @@ static struct buffer_head *__ext4_sb_bread_gfp(struct super_block *sb,
}
struct buffer_head *ext4_sb_bread(struct super_block *sb, sector_t block,
- int op_flags)
+ blk_opf_t op_flags)
{
return __ext4_sb_bread_gfp(sb, block, op_flags, __GFP_MOVABLE);
}
@@ -5939,8 +5939,8 @@ static int ext4_commit_super(struct super_block *sb)
/* Clear potential dirty bit if it was journalled update */
clear_buffer_dirty(sbh);
sbh->b_end_io = end_buffer_write_sync;
- submit_bh(REQ_OP_WRITE,
- REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0), sbh);
+ submit_bh(REQ_OP_WRITE | REQ_SYNC |
+ (test_opt(sb, BARRIER) ? REQ_FUA : 0), sbh);
wait_on_buffer(sbh);
if (buffer_write_io_error(sbh)) {
ext4_msg(sb, KERN_ERR, "I/O error while writing "
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 7fcbcf979737..5c13ee321940 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -387,11 +387,11 @@ int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr)
return 0;
}
-static unsigned int f2fs_io_flags(struct f2fs_io_info *fio)
+static blk_opf_t f2fs_io_flags(struct f2fs_io_info *fio)
{
unsigned int temp_mask = (1 << NR_TEMP_TYPE) - 1;
unsigned int fua_flag, meta_flag, io_flag;
- unsigned int op_flags = 0;
+ blk_opf_t op_flags = 0;
if (fio->op != REQ_OP_WRITE)
return 0;
@@ -999,7 +999,7 @@ out:
}
static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
- unsigned nr_pages, unsigned op_flag,
+ unsigned nr_pages, blk_opf_t op_flag,
pgoff_t first_idx, bool for_write)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -1047,7 +1047,8 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
/* This can handle encryption stuffs */
static int f2fs_submit_page_read(struct inode *inode, struct page *page,
- block_t blkaddr, int op_flags, bool for_write)
+ block_t blkaddr, blk_opf_t op_flags,
+ bool for_write)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct bio *bio;
@@ -1181,7 +1182,7 @@ int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index)
}
struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
- int op_flags, bool for_write)
+ blk_opf_t op_flags, bool for_write)
{
struct address_space *mapping = inode->i_mapping;
struct dnode_of_data dn;
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index d9bbecd008d2..868170b72de9 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1183,8 +1183,8 @@ struct f2fs_io_info {
nid_t ino; /* inode number */
enum page_type type; /* contains DATA/NODE/META/META_FLUSH */
enum temp_type temp; /* contains HOT/WARM/COLD */
- int op; /* contains REQ_OP_ */
- int op_flags; /* req_flag_bits */
+ enum req_op op; /* contains REQ_OP_ */
+ blk_opf_t op_flags; /* req_flag_bits */
block_t new_blkaddr; /* new block address to be written */
block_t old_blkaddr; /* old block address before Cow */
struct page *page; /* page to be written */
@@ -3741,7 +3741,7 @@ int f2fs_reserve_new_block(struct dnode_of_data *dn);
int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index);
int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index);
struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
- int op_flags, bool for_write);
+ blk_opf_t op_flags, bool for_write);
struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index);
struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index,
bool for_write);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index bd14cef1b08f..d66e37d80a2d 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -861,10 +861,8 @@ static void __setattr_copy(struct user_namespace *mnt_userns,
{
unsigned int ia_valid = attr->ia_valid;
- if (ia_valid & ATTR_UID)
- inode->i_uid = attr->ia_uid;
- if (ia_valid & ATTR_GID)
- inode->i_gid = attr->ia_gid;
+ i_uid_update(mnt_userns, attr, inode);
+ i_gid_update(mnt_userns, attr, inode);
if (ia_valid & ATTR_ATIME)
inode->i_atime = attr->ia_atime;
if (ia_valid & ATTR_MTIME)
@@ -917,17 +915,15 @@ int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
if (err)
return err;
- if (is_quota_modification(inode, attr)) {
+ if (is_quota_modification(mnt_userns, inode, attr)) {
err = f2fs_dquot_initialize(inode);
if (err)
return err;
}
- if ((attr->ia_valid & ATTR_UID &&
- !uid_eq(attr->ia_uid, inode->i_uid)) ||
- (attr->ia_valid & ATTR_GID &&
- !gid_eq(attr->ia_gid, inode->i_gid))) {
+ if (i_uid_needs_update(mnt_userns, attr, inode) ||
+ i_gid_needs_update(mnt_userns, attr, inode)) {
f2fs_lock_op(F2FS_I_SB(inode));
- err = dquot_transfer(inode, attr);
+ err = dquot_transfer(mnt_userns, inode, attr);
if (err) {
set_sbi_flag(F2FS_I_SB(inode),
SBI_QUOTA_NEED_REPAIR);
@@ -938,10 +934,8 @@ int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
* update uid/gid under lock_op(), so that dquot and inode can
* be updated atomically.
*/
- if (attr->ia_valid & ATTR_UID)
- inode->i_uid = attr->ia_uid;
- if (attr->ia_valid & ATTR_GID)
- inode->i_gid = attr->ia_gid;
+ i_uid_update(mnt_userns, attr, inode);
+ i_gid_update(mnt_userns, attr, inode);
f2fs_mark_inode_dirty_sync(inode, true);
f2fs_unlock_op(F2FS_I_SB(inode));
}
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index cf6f7fc83c08..04a145f1dcfc 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1327,7 +1327,7 @@ fail:
* 0: f2fs_put_page(page, 0)
* LOCKED_PAGE or error: f2fs_put_page(page, 1)
*/
-static int read_node_page(struct page *page, int op_flags)
+static int read_node_page(struct page *page, blk_opf_t op_flags)
{
struct f2fs_sb_info *sbi = F2FS_P_SB(page);
struct node_info ni;
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 3cb7f8a43b4d..dcd0a1e35095 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -255,18 +255,18 @@ static int recover_quota_data(struct inode *inode, struct page *page)
memset(&attr, 0, sizeof(attr));
- attr.ia_uid = make_kuid(inode->i_sb->s_user_ns, i_uid);
- attr.ia_gid = make_kgid(inode->i_sb->s_user_ns, i_gid);
+ attr.ia_vfsuid = VFSUIDT_INIT(make_kuid(inode->i_sb->s_user_ns, i_uid));
+ attr.ia_vfsgid = VFSGIDT_INIT(make_kgid(inode->i_sb->s_user_ns, i_gid));
- if (!uid_eq(attr.ia_uid, inode->i_uid))
+ if (!vfsuid_eq(attr.ia_vfsuid, i_uid_into_vfsuid(&init_user_ns, inode)))
attr.ia_valid |= ATTR_UID;
- if (!gid_eq(attr.ia_gid, inode->i_gid))
+ if (!vfsgid_eq(attr.ia_vfsgid, i_gid_into_vfsgid(&init_user_ns, inode)))
attr.ia_valid |= ATTR_GID;
if (!attr.ia_valid)
return 0;
- err = dquot_transfer(inode, &attr);
+ err = dquot_transfer(&init_user_ns, inode, &attr);
if (err)
set_sbi_flag(F2FS_I_SB(inode), SBI_QUOTA_NEED_REPAIR);
return err;
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 874c1b9c41a2..c7afc588cf26 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -1082,7 +1082,7 @@ static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
struct list_head *wait_list = (dpolicy->type == DPOLICY_FSTRIM) ?
&(dcc->fstrim_list) : &(dcc->wait_list);
- int flag = dpolicy->sync ? REQ_SYNC : 0;
+ blk_opf_t flag = dpolicy->sync ? REQ_SYNC : 0;
block_t lstart, start, len, total_len;
int err = 0;
diff --git a/fs/fat/file.c b/fs/fat/file.c
index 3dae3ed60f3a..3e4eb3467cb4 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -90,7 +90,8 @@ static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr)
* out the RO attribute for checking by the security
* module, just because it maps to a file mode.
*/
- err = security_inode_setattr(file->f_path.dentry, &ia);
+ err = security_inode_setattr(file_mnt_user_ns(file),
+ file->f_path.dentry, &ia);
if (err)
goto out_unlock_inode;
@@ -516,9 +517,11 @@ int fat_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
}
if (((attr->ia_valid & ATTR_UID) &&
- (!uid_eq(attr->ia_uid, sbi->options.fs_uid))) ||
+ (!uid_eq(from_vfsuid(mnt_userns, i_user_ns(inode), attr->ia_vfsuid),
+ sbi->options.fs_uid))) ||
((attr->ia_valid & ATTR_GID) &&
- (!gid_eq(attr->ia_gid, sbi->options.fs_gid))) ||
+ (!gid_eq(from_vfsgid(mnt_userns, i_user_ns(inode), attr->ia_vfsgid),
+ sbi->options.fs_gid))) ||
((attr->ia_valid & ATTR_MODE) &&
(attr->ia_mode & ~FAT_VALID_MODE)))
error = -EPERM;
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index b6697333bb2b..3bdb2c668a71 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -310,9 +310,8 @@ static void gfs2_metapath_ra(struct gfs2_glock *gl, __be64 *start, __be64 *end)
if (trylock_buffer(rabh)) {
if (!buffer_uptodate(rabh)) {
rabh->b_end_io = end_buffer_read_sync;
- submit_bh(REQ_OP_READ,
- REQ_RAHEAD | REQ_META | REQ_PRIO,
- rabh);
+ submit_bh(REQ_OP_READ | REQ_RAHEAD | REQ_META |
+ REQ_PRIO, rabh);
continue;
}
unlock_buffer(rabh);
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index 42b7dfffb5e7..a0562dd1bada 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -1508,9 +1508,8 @@ static void gfs2_dir_readahead(struct inode *inode, unsigned hsize, u32 index,
continue;
}
bh->b_end_io = end_buffer_read_sync;
- submit_bh(REQ_OP_READ,
- REQ_RAHEAD | REQ_META | REQ_PRIO,
- bh);
+ submit_bh(REQ_OP_READ | REQ_RAHEAD | REQ_META |
+ REQ_PRIO, bh);
continue;
}
brelse(bh);
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index f0ee3ff6f9a8..eec4159b08aa 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -823,7 +823,7 @@ void gfs2_flush_revokes(struct gfs2_sbd *sdp)
void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
u64 seq, u32 tail, u32 lblock, u32 flags,
- int op_flags)
+ blk_opf_t op_flags)
{
struct gfs2_log_header *lh;
u32 hash, crc;
@@ -905,7 +905,7 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
static void log_write_header(struct gfs2_sbd *sdp, u32 flags)
{
- int op_flags = REQ_PREFLUSH | REQ_FUA | REQ_META | REQ_SYNC;
+ blk_opf_t op_flags = REQ_PREFLUSH | REQ_FUA | REQ_META | REQ_SYNC;
enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state);
gfs2_assert_withdraw(sdp, (state != SFS_FROZEN));
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index fc905c2af53c..653cffcbf869 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -82,7 +82,7 @@ extern void gfs2_log_reserve(struct gfs2_sbd *sdp, struct gfs2_trans *tr,
unsigned int *extra_revokes);
extern void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
u64 seq, u32 tail, u32 lblock, u32 flags,
- int op_flags);
+ blk_opf_t op_flags);
extern void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl,
u32 type);
extern void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *trans);
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 6ba51cbb94cf..90a2d7bc91c4 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -238,7 +238,7 @@ static void gfs2_end_log_write(struct bio *bio)
* there is no pending bio, then this is a no-op.
*/
-void gfs2_log_submit_bio(struct bio **biop, int opf)
+void gfs2_log_submit_bio(struct bio **biop, blk_opf_t opf)
{
struct bio *bio = *biop;
if (bio) {
@@ -292,7 +292,7 @@ static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno,
*/
static struct bio *gfs2_log_get_bio(struct gfs2_sbd *sdp, u64 blkno,
- struct bio **biop, int op,
+ struct bio **biop, enum req_op op,
bio_end_io_t *end_io, bool flush)
{
struct bio *bio = *biop;
diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h
index f707601597dc..1412ffba1d44 100644
--- a/fs/gfs2/lops.h
+++ b/fs/gfs2/lops.h
@@ -16,7 +16,7 @@ extern u64 gfs2_log_bmap(struct gfs2_jdesc *jd, unsigned int lbn);
extern void gfs2_log_write(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
struct page *page, unsigned size, unsigned offset,
u64 blkno);
-extern void gfs2_log_submit_bio(struct bio **biop, int opf);
+extern void gfs2_log_submit_bio(struct bio **biop, blk_opf_t opf);
extern void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh);
extern int gfs2_find_jhead(struct gfs2_jdesc *jd,
struct gfs2_log_header_host *head, bool keep_cache);
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 868dcc71b581..7e70e0ba5a6c 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -34,7 +34,7 @@ static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wb
{
struct buffer_head *bh, *head;
int nr_underway = 0;
- int write_flags = REQ_META | REQ_PRIO | wbc_to_write_flags(wbc);
+ blk_opf_t write_flags = REQ_META | REQ_PRIO | wbc_to_write_flags(wbc);
BUG_ON(!PageLocked(page));
BUG_ON(!page_has_buffers(page));
@@ -75,7 +75,7 @@ static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wb
do {
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
- submit_bh(REQ_OP_WRITE, write_flags, bh);
+ submit_bh(REQ_OP_WRITE | write_flags, bh);
nr_underway++;
}
bh = next;
@@ -217,14 +217,13 @@ static void gfs2_meta_read_endio(struct bio *bio)
* Submit several consecutive buffer head I/O requests as a single bio I/O
* request. (See submit_bh_wbc.)
*/
-static void gfs2_submit_bhs(int op, int op_flags, struct buffer_head *bhs[],
- int num)
+static void gfs2_submit_bhs(blk_opf_t opf, struct buffer_head *bhs[], int num)
{
while (num > 0) {
struct buffer_head *bh = *bhs;
struct bio *bio;
- bio = bio_alloc(bh->b_bdev, num, op | op_flags, GFP_NOIO);
+ bio = bio_alloc(bh->b_bdev, num, opf, GFP_NOIO);
bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
while (num > 0) {
bh = *bhs;
@@ -288,7 +287,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
}
}
- gfs2_submit_bhs(REQ_OP_READ, REQ_META | REQ_PRIO, bhs, num);
+ gfs2_submit_bhs(REQ_OP_READ | REQ_META | REQ_PRIO, bhs, num);
if (!(flags & DIO_WAIT))
return 0;
@@ -527,7 +526,7 @@ struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen)
if (buffer_uptodate(first_bh))
goto out;
if (!buffer_locked(first_bh))
- ll_rw_block(REQ_OP_READ, REQ_META | REQ_PRIO, 1, &first_bh);
+ ll_rw_block(REQ_OP_READ | REQ_META | REQ_PRIO, 1, &first_bh);
dblock++;
extlen--;
@@ -536,9 +535,8 @@ struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen)
bh = gfs2_getbuf(gl, dblock, CREATE);
if (!buffer_uptodate(bh) && !buffer_locked(bh))
- ll_rw_block(REQ_OP_READ,
- REQ_RAHEAD | REQ_META | REQ_PRIO,
- 1, &bh);
+ ll_rw_block(REQ_OP_READ | REQ_RAHEAD | REQ_META |
+ REQ_PRIO, 1, &bh);
brelse(bh);
dblock++;
extlen--;
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 59d727a4ae2c..c98a7faa67d3 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -746,7 +746,7 @@ static int gfs2_write_buf_to_page(struct gfs2_inode *ip, unsigned long index,
if (PageUptodate(page))
set_buffer_uptodate(bh);
if (!buffer_uptodate(bh)) {
- ll_rw_block(REQ_OP_READ, REQ_META | REQ_PRIO, 1, &bh);
+ ll_rw_block(REQ_OP_READ | REQ_META | REQ_PRIO, 1, &bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh))
goto unlock_out;
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 396e73aa0961..a5db2e3b2980 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -525,7 +525,7 @@ int hfsplus_compare_dentry(const struct dentry *dentry, unsigned int len,
/* wrapper.c */
int hfsplus_submit_bio(struct super_block *sb, sector_t sector, void *buf,
- void **data, int op, int op_flags);
+ void **data, blk_opf_t opf);
int hfsplus_read_wrapper(struct super_block *sb);
/*
diff --git a/fs/hfsplus/part_tbl.c b/fs/hfsplus/part_tbl.c
index 63164ebc52fa..9ec21664eda6 100644
--- a/fs/hfsplus/part_tbl.c
+++ b/fs/hfsplus/part_tbl.c
@@ -112,8 +112,7 @@ static int hfs_parse_new_pmap(struct super_block *sb, void *buf,
if ((u8 *)pm - (u8 *)buf >= buf_size) {
res = hfsplus_submit_bio(sb,
*part_start + HFS_PMAP_BLK + i,
- buf, (void **)&pm, REQ_OP_READ,
- 0);
+ buf, (void **)&pm, REQ_OP_READ);
if (res)
return res;
}
@@ -137,7 +136,7 @@ int hfs_part_find(struct super_block *sb,
return -ENOMEM;
res = hfsplus_submit_bio(sb, *part_start + HFS_PMAP_BLK,
- buf, &data, REQ_OP_READ, 0);
+ buf, &data, REQ_OP_READ);
if (res)
goto out;
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 8479add998b5..122ed89ebf9f 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -221,7 +221,7 @@ static int hfsplus_sync_fs(struct super_block *sb, int wait)
error2 = hfsplus_submit_bio(sb,
sbi->part_start + HFSPLUS_VOLHEAD_SECTOR,
- sbi->s_vhdr_buf, NULL, REQ_OP_WRITE,
+ sbi->s_vhdr_buf, NULL, REQ_OP_WRITE |
REQ_SYNC);
if (!error)
error = error2;
@@ -230,7 +230,7 @@ static int hfsplus_sync_fs(struct super_block *sb, int wait)
error2 = hfsplus_submit_bio(sb,
sbi->part_start + sbi->sect_count - 2,
- sbi->s_backup_vhdr_buf, NULL, REQ_OP_WRITE,
+ sbi->s_backup_vhdr_buf, NULL, REQ_OP_WRITE |
REQ_SYNC);
if (!error)
error2 = error;
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index 0b8ad6586df5..0b791adf02e5 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -45,8 +45,9 @@ struct hfsplus_wd {
* will work correctly.
*/
int hfsplus_submit_bio(struct super_block *sb, sector_t sector,
- void *buf, void **data, int op, int op_flags)
+ void *buf, void **data, blk_opf_t opf)
{
+ const enum req_op op = opf & REQ_OP_MASK;
struct bio *bio;
int ret = 0;
u64 io_size;
@@ -63,10 +64,10 @@ int hfsplus_submit_bio(struct super_block *sb, sector_t sector,
offset = start & (io_size - 1);
sector &= ~((io_size >> HFSPLUS_SECTOR_SHIFT) - 1);
- bio = bio_alloc(sb->s_bdev, 1, op | op_flags, GFP_NOIO);
+ bio = bio_alloc(sb->s_bdev, 1, opf, GFP_NOIO);
bio->bi_iter.bi_sector = sector;
- if (op != WRITE && data)
+ if (op != REQ_OP_WRITE && data)
*data = (u8 *)buf + offset;
while (io_size > 0) {
@@ -184,7 +185,7 @@ int hfsplus_read_wrapper(struct super_block *sb)
reread:
error = hfsplus_submit_bio(sb, part_start + HFSPLUS_VOLHEAD_SECTOR,
sbi->s_vhdr_buf, (void **)&sbi->s_vhdr,
- REQ_OP_READ, 0);
+ REQ_OP_READ);
if (error)
goto out_free_backup_vhdr;
@@ -216,8 +217,7 @@ reread:
error = hfsplus_submit_bio(sb, part_start + part_size - 2,
sbi->s_backup_vhdr_buf,
- (void **)&sbi->s_backup_vhdr, REQ_OP_READ,
- 0);
+ (void **)&sbi->s_backup_vhdr, REQ_OP_READ);
if (error)
goto out_free_backup_vhdr;
diff --git a/fs/inode.c b/fs/inode.c
index bd4da9c5207e..259ebf438893 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -2010,67 +2010,57 @@ static int __remove_privs(struct user_namespace *mnt_userns,
return notify_change(mnt_userns, dentry, &newattrs, NULL);
}
-/*
- * Remove special file priviledges (suid, capabilities) when file is written
- * to or truncated.
- */
-int file_remove_privs(struct file *file)
+static int __file_remove_privs(struct file *file, unsigned int flags)
{
struct dentry *dentry = file_dentry(file);
struct inode *inode = file_inode(file);
+ int error;
int kill;
- int error = 0;
- /*
- * Fast path for nothing security related.
- * As well for non-regular files, e.g. blkdev inodes.
- * For example, blkdev_write_iter() might get here
- * trying to remove privs which it is not allowed to.
- */
if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode))
return 0;
kill = dentry_needs_remove_privs(dentry);
- if (kill < 0)
+ if (kill <= 0)
return kill;
- if (kill)
- error = __remove_privs(file_mnt_user_ns(file), dentry, kill);
+
+ if (flags & IOCB_NOWAIT)
+ return -EAGAIN;
+
+ error = __remove_privs(file_mnt_user_ns(file), dentry, kill);
if (!error)
inode_has_no_xattr(inode);
return error;
}
-EXPORT_SYMBOL(file_remove_privs);
/**
- * file_update_time - update mtime and ctime time
- * @file: file accessed
+ * file_remove_privs - remove special file privileges (suid, capabilities)
+ * @file: file to remove privileges from
+ *
+ * When file is modified by a write or truncation ensure that special
+ * file privileges are removed.
*
- * Update the mtime and ctime members of an inode and mark the inode
- * for writeback. Note that this function is meant exclusively for
- * usage in the file write path of filesystems, and filesystems may
- * choose to explicitly ignore update via this function with the
- * S_NOCMTIME inode flag, e.g. for network filesystem where these
- * timestamps are handled by the server. This can return an error for
- * file systems who need to allocate space in order to update an inode.
+ * Return: 0 on success, negative errno on failure.
*/
+int file_remove_privs(struct file *file)
+{
+ return __file_remove_privs(file, 0);
+}
+EXPORT_SYMBOL(file_remove_privs);
-int file_update_time(struct file *file)
+static int inode_needs_update_time(struct inode *inode, struct timespec64 *now)
{
- struct inode *inode = file_inode(file);
- struct timespec64 now;
int sync_it = 0;
- int ret;
/* First try to exhaust all avenues to not sync */
if (IS_NOCMTIME(inode))
return 0;
- now = current_time(inode);
- if (!timespec64_equal(&inode->i_mtime, &now))
+ if (!timespec64_equal(&inode->i_mtime, now))
sync_it = S_MTIME;
- if (!timespec64_equal(&inode->i_ctime, &now))
+ if (!timespec64_equal(&inode->i_ctime, now))
sync_it |= S_CTIME;
if (IS_I_VERSION(inode) && inode_iversion_need_inc(inode))
@@ -2079,37 +2069,127 @@ int file_update_time(struct file *file)
if (!sync_it)
return 0;
- /* Finally allowed to write? Takes lock. */
- if (__mnt_want_write_file(file))
- return 0;
+ return sync_it;
+}
+
+static int __file_update_time(struct file *file, struct timespec64 *now,
+ int sync_mode)
+{
+ int ret = 0;
+ struct inode *inode = file_inode(file);
- ret = inode_update_time(inode, &now, sync_it);
- __mnt_drop_write_file(file);
+ /* try to update time settings */
+ if (!__mnt_want_write_file(file)) {
+ ret = inode_update_time(inode, now, sync_mode);
+ __mnt_drop_write_file(file);
+ }
return ret;
}
+
+/**
+ * file_update_time - update mtime and ctime time
+ * @file: file accessed
+ *
+ * Update the mtime and ctime members of an inode and mark the inode for
+ * writeback. Note that this function is meant exclusively for usage in
+ * the file write path of filesystems, and filesystems may choose to
+ * explicitly ignore updates via this function with the _NOCMTIME inode
+ * flag, e.g. for network filesystem where these imestamps are handled
+ * by the server. This can return an error for file systems who need to
+ * allocate space in order to update an inode.
+ *
+ * Return: 0 on success, negative errno on failure.
+ */
+int file_update_time(struct file *file)
+{
+ int ret;
+ struct inode *inode = file_inode(file);
+ struct timespec64 now = current_time(inode);
+
+ ret = inode_needs_update_time(inode, &now);
+ if (ret <= 0)
+ return ret;
+
+ return __file_update_time(file, &now, ret);
+}
EXPORT_SYMBOL(file_update_time);
-/* Caller must hold the file's inode lock */
-int file_modified(struct file *file)
+/**
+ * file_modified_flags - handle mandated vfs changes when modifying a file
+ * @file: file that was modified
+ * @flags: kiocb flags
+ *
+ * When file has been modified ensure that special
+ * file privileges are removed and time settings are updated.
+ *
+ * If IOCB_NOWAIT is set, special file privileges will not be removed and
+ * time settings will not be updated. It will return -EAGAIN.
+ *
+ * Context: Caller must hold the file's inode lock.
+ *
+ * Return: 0 on success, negative errno on failure.
+ */
+static int file_modified_flags(struct file *file, int flags)
{
- int err;
+ int ret;
+ struct inode *inode = file_inode(file);
+ struct timespec64 now = current_time(inode);
/*
* Clear the security bits if the process is not being run by root.
* This keeps people from modifying setuid and setgid binaries.
*/
- err = file_remove_privs(file);
- if (err)
- return err;
+ ret = __file_remove_privs(file, flags);
+ if (ret)
+ return ret;
if (unlikely(file->f_mode & FMODE_NOCMTIME))
return 0;
- return file_update_time(file);
+ ret = inode_needs_update_time(inode, &now);
+ if (ret <= 0)
+ return ret;
+ if (flags & IOCB_NOWAIT)
+ return -EAGAIN;
+
+ return __file_update_time(file, &now, ret);
+}
+
+/**
+ * file_modified - handle mandated vfs changes when modifying a file
+ * @file: file that was modified
+ *
+ * When file has been modified ensure that special
+ * file privileges are removed and time settings are updated.
+ *
+ * Context: Caller must hold the file's inode lock.
+ *
+ * Return: 0 on success, negative errno on failure.
+ */
+int file_modified(struct file *file)
+{
+ return file_modified_flags(file, 0);
}
EXPORT_SYMBOL(file_modified);
+/**
+ * kiocb_modified - handle mandated vfs changes when modifying a file
+ * @iocb: iocb that was modified
+ *
+ * When file has been modified ensure that special
+ * file privileges are removed and time settings are updated.
+ *
+ * Context: Caller must hold the file's inode lock.
+ *
+ * Return: 0 on success, negative errno on failure.
+ */
+int kiocb_modified(struct kiocb *iocb)
+{
+ return file_modified_flags(iocb->ki_filp, iocb->ki_flags);
+}
+EXPORT_SYMBOL_GPL(kiocb_modified);
+
int inode_needs_sync(struct inode *inode)
{
if (IS_SYNC(inode))
diff --git a/fs/io-wq.c b/fs/io-wq.c
deleted file mode 100644
index 824623bcf1a5..000000000000
--- a/fs/io-wq.c
+++ /dev/null
@@ -1,1424 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Basic worker thread pool for io_uring
- *
- * Copyright (C) 2019 Jens Axboe
- *
- */
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/errno.h>
-#include <linux/sched/signal.h>
-#include <linux/percpu.h>
-#include <linux/slab.h>
-#include <linux/rculist_nulls.h>
-#include <linux/cpu.h>
-#include <linux/task_work.h>
-#include <linux/audit.h>
-#include <uapi/linux/io_uring.h>
-
-#include "io-wq.h"
-
-#define WORKER_IDLE_TIMEOUT (5 * HZ)
-
-enum {
- IO_WORKER_F_UP = 1, /* up and active */
- IO_WORKER_F_RUNNING = 2, /* account as running */
- IO_WORKER_F_FREE = 4, /* worker on free list */
- IO_WORKER_F_BOUND = 8, /* is doing bounded work */
-};
-
-enum {
- IO_WQ_BIT_EXIT = 0, /* wq exiting */
-};
-
-enum {
- IO_ACCT_STALLED_BIT = 0, /* stalled on hash */
-};
-
-/*
- * One for each thread in a wqe pool
- */
-struct io_worker {
- refcount_t ref;
- unsigned flags;
- struct hlist_nulls_node nulls_node;
- struct list_head all_list;
- struct task_struct *task;
- struct io_wqe *wqe;
-
- struct io_wq_work *cur_work;
- struct io_wq_work *next_work;
- raw_spinlock_t lock;
-
- struct completion ref_done;
-
- unsigned long create_state;
- struct callback_head create_work;
- int create_index;
-
- union {
- struct rcu_head rcu;
- struct work_struct work;
- };
-};
-
-#if BITS_PER_LONG == 64
-#define IO_WQ_HASH_ORDER 6
-#else
-#define IO_WQ_HASH_ORDER 5
-#endif
-
-#define IO_WQ_NR_HASH_BUCKETS (1u << IO_WQ_HASH_ORDER)
-
-struct io_wqe_acct {
- unsigned nr_workers;
- unsigned max_workers;
- int index;
- atomic_t nr_running;
- raw_spinlock_t lock;
- struct io_wq_work_list work_list;
- unsigned long flags;
-};
-
-enum {
- IO_WQ_ACCT_BOUND,
- IO_WQ_ACCT_UNBOUND,
- IO_WQ_ACCT_NR,
-};
-
-/*
- * Per-node worker thread pool
- */
-struct io_wqe {
- raw_spinlock_t lock;
- struct io_wqe_acct acct[IO_WQ_ACCT_NR];
-
- int node;
-
- struct hlist_nulls_head free_list;
- struct list_head all_list;
-
- struct wait_queue_entry wait;
-
- struct io_wq *wq;
- struct io_wq_work *hash_tail[IO_WQ_NR_HASH_BUCKETS];
-
- cpumask_var_t cpu_mask;
-};
-
-/*
- * Per io_wq state
- */
-struct io_wq {
- unsigned long state;
-
- free_work_fn *free_work;
- io_wq_work_fn *do_work;
-
- struct io_wq_hash *hash;
-
- atomic_t worker_refs;
- struct completion worker_done;
-
- struct hlist_node cpuhp_node;
-
- struct task_struct *task;
-
- struct io_wqe *wqes[];
-};
-
-static enum cpuhp_state io_wq_online;
-
-struct io_cb_cancel_data {
- work_cancel_fn *fn;
- void *data;
- int nr_running;
- int nr_pending;
- bool cancel_all;
-};
-
-static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index);
-static void io_wqe_dec_running(struct io_worker *worker);
-static bool io_acct_cancel_pending_work(struct io_wqe *wqe,
- struct io_wqe_acct *acct,
- struct io_cb_cancel_data *match);
-static void create_worker_cb(struct callback_head *cb);
-static void io_wq_cancel_tw_create(struct io_wq *wq);
-
-static bool io_worker_get(struct io_worker *worker)
-{
- return refcount_inc_not_zero(&worker->ref);
-}
-
-static void io_worker_release(struct io_worker *worker)
-{
- if (refcount_dec_and_test(&worker->ref))
- complete(&worker->ref_done);
-}
-
-static inline struct io_wqe_acct *io_get_acct(struct io_wqe *wqe, bool bound)
-{
- return &wqe->acct[bound ? IO_WQ_ACCT_BOUND : IO_WQ_ACCT_UNBOUND];
-}
-
-static inline struct io_wqe_acct *io_work_get_acct(struct io_wqe *wqe,
- struct io_wq_work *work)
-{
- return io_get_acct(wqe, !(work->flags & IO_WQ_WORK_UNBOUND));
-}
-
-static inline struct io_wqe_acct *io_wqe_get_acct(struct io_worker *worker)
-{
- return io_get_acct(worker->wqe, worker->flags & IO_WORKER_F_BOUND);
-}
-
-static void io_worker_ref_put(struct io_wq *wq)
-{
- if (atomic_dec_and_test(&wq->worker_refs))
- complete(&wq->worker_done);
-}
-
-static void io_worker_cancel_cb(struct io_worker *worker)
-{
- struct io_wqe_acct *acct = io_wqe_get_acct(worker);
- struct io_wqe *wqe = worker->wqe;
- struct io_wq *wq = wqe->wq;
-
- atomic_dec(&acct->nr_running);
- raw_spin_lock(&worker->wqe->lock);
- acct->nr_workers--;
- raw_spin_unlock(&worker->wqe->lock);
- io_worker_ref_put(wq);
- clear_bit_unlock(0, &worker->create_state);
- io_worker_release(worker);
-}
-
-static bool io_task_worker_match(struct callback_head *cb, void *data)
-{
- struct io_worker *worker;
-
- if (cb->func != create_worker_cb)
- return false;
- worker = container_of(cb, struct io_worker, create_work);
- return worker == data;
-}
-
-static void io_worker_exit(struct io_worker *worker)
-{
- struct io_wqe *wqe = worker->wqe;
- struct io_wq *wq = wqe->wq;
-
- while (1) {
- struct callback_head *cb = task_work_cancel_match(wq->task,
- io_task_worker_match, worker);
-
- if (!cb)
- break;
- io_worker_cancel_cb(worker);
- }
-
- io_worker_release(worker);
- wait_for_completion(&worker->ref_done);
-
- raw_spin_lock(&wqe->lock);
- if (worker->flags & IO_WORKER_F_FREE)
- hlist_nulls_del_rcu(&worker->nulls_node);
- list_del_rcu(&worker->all_list);
- raw_spin_unlock(&wqe->lock);
- io_wqe_dec_running(worker);
- worker->flags = 0;
- preempt_disable();
- current->flags &= ~PF_IO_WORKER;
- preempt_enable();
-
- kfree_rcu(worker, rcu);
- io_worker_ref_put(wqe->wq);
- do_exit(0);
-}
-
-static inline bool io_acct_run_queue(struct io_wqe_acct *acct)
-{
- bool ret = false;
-
- raw_spin_lock(&acct->lock);
- if (!wq_list_empty(&acct->work_list) &&
- !test_bit(IO_ACCT_STALLED_BIT, &acct->flags))
- ret = true;
- raw_spin_unlock(&acct->lock);
-
- return ret;
-}
-
-/*
- * Check head of free list for an available worker. If one isn't available,
- * caller must create one.
- */
-static bool io_wqe_activate_free_worker(struct io_wqe *wqe,
- struct io_wqe_acct *acct)
- __must_hold(RCU)
-{
- struct hlist_nulls_node *n;
- struct io_worker *worker;
-
- /*
- * Iterate free_list and see if we can find an idle worker to
- * activate. If a given worker is on the free_list but in the process
- * of exiting, keep trying.
- */
- hlist_nulls_for_each_entry_rcu(worker, n, &wqe->free_list, nulls_node) {
- if (!io_worker_get(worker))
- continue;
- if (io_wqe_get_acct(worker) != acct) {
- io_worker_release(worker);
- continue;
- }
- if (wake_up_process(worker->task)) {
- io_worker_release(worker);
- return true;
- }
- io_worker_release(worker);
- }
-
- return false;
-}
-
-/*
- * We need a worker. If we find a free one, we're good. If not, and we're
- * below the max number of workers, create one.
- */
-static bool io_wqe_create_worker(struct io_wqe *wqe, struct io_wqe_acct *acct)
-{
- /*
- * Most likely an attempt to queue unbounded work on an io_wq that
- * wasn't setup with any unbounded workers.
- */
- if (unlikely(!acct->max_workers))
- pr_warn_once("io-wq is not configured for unbound workers");
-
- raw_spin_lock(&wqe->lock);
- if (acct->nr_workers >= acct->max_workers) {
- raw_spin_unlock(&wqe->lock);
- return true;
- }
- acct->nr_workers++;
- raw_spin_unlock(&wqe->lock);
- atomic_inc(&acct->nr_running);
- atomic_inc(&wqe->wq->worker_refs);
- return create_io_worker(wqe->wq, wqe, acct->index);
-}
-
-static void io_wqe_inc_running(struct io_worker *worker)
-{
- struct io_wqe_acct *acct = io_wqe_get_acct(worker);
-
- atomic_inc(&acct->nr_running);
-}
-
-static void create_worker_cb(struct callback_head *cb)
-{
- struct io_worker *worker;
- struct io_wq *wq;
- struct io_wqe *wqe;
- struct io_wqe_acct *acct;
- bool do_create = false;
-
- worker = container_of(cb, struct io_worker, create_work);
- wqe = worker->wqe;
- wq = wqe->wq;
- acct = &wqe->acct[worker->create_index];
- raw_spin_lock(&wqe->lock);
- if (acct->nr_workers < acct->max_workers) {
- acct->nr_workers++;
- do_create = true;
- }
- raw_spin_unlock(&wqe->lock);
- if (do_create) {
- create_io_worker(wq, wqe, worker->create_index);
- } else {
- atomic_dec(&acct->nr_running);
- io_worker_ref_put(wq);
- }
- clear_bit_unlock(0, &worker->create_state);
- io_worker_release(worker);
-}
-
-static bool io_queue_worker_create(struct io_worker *worker,
- struct io_wqe_acct *acct,
- task_work_func_t func)
-{
- struct io_wqe *wqe = worker->wqe;
- struct io_wq *wq = wqe->wq;
-
- /* raced with exit, just ignore create call */
- if (test_bit(IO_WQ_BIT_EXIT, &wq->state))
- goto fail;
- if (!io_worker_get(worker))
- goto fail;
- /*
- * create_state manages ownership of create_work/index. We should
- * only need one entry per worker, as the worker going to sleep
- * will trigger the condition, and waking will clear it once it
- * runs the task_work.
- */
- if (test_bit(0, &worker->create_state) ||
- test_and_set_bit_lock(0, &worker->create_state))
- goto fail_release;
-
- atomic_inc(&wq->worker_refs);
- init_task_work(&worker->create_work, func);
- worker->create_index = acct->index;
- if (!task_work_add(wq->task, &worker->create_work, TWA_SIGNAL)) {
- /*
- * EXIT may have been set after checking it above, check after
- * adding the task_work and remove any creation item if it is
- * now set. wq exit does that too, but we can have added this
- * work item after we canceled in io_wq_exit_workers().
- */
- if (test_bit(IO_WQ_BIT_EXIT, &wq->state))
- io_wq_cancel_tw_create(wq);
- io_worker_ref_put(wq);
- return true;
- }
- io_worker_ref_put(wq);
- clear_bit_unlock(0, &worker->create_state);
-fail_release:
- io_worker_release(worker);
-fail:
- atomic_dec(&acct->nr_running);
- io_worker_ref_put(wq);
- return false;
-}
-
-static void io_wqe_dec_running(struct io_worker *worker)
-{
- struct io_wqe_acct *acct = io_wqe_get_acct(worker);
- struct io_wqe *wqe = worker->wqe;
-
- if (!(worker->flags & IO_WORKER_F_UP))
- return;
-
- if (!atomic_dec_and_test(&acct->nr_running))
- return;
- if (!io_acct_run_queue(acct))
- return;
-
- atomic_inc(&acct->nr_running);
- atomic_inc(&wqe->wq->worker_refs);
- io_queue_worker_create(worker, acct, create_worker_cb);
-}
-
-/*
- * Worker will start processing some work. Move it to the busy list, if
- * it's currently on the freelist
- */
-static void __io_worker_busy(struct io_wqe *wqe, struct io_worker *worker)
-{
- if (worker->flags & IO_WORKER_F_FREE) {
- worker->flags &= ~IO_WORKER_F_FREE;
- raw_spin_lock(&wqe->lock);
- hlist_nulls_del_init_rcu(&worker->nulls_node);
- raw_spin_unlock(&wqe->lock);
- }
-}
-
-/*
- * No work, worker going to sleep. Move to freelist, and unuse mm if we
- * have one attached. Dropping the mm may potentially sleep, so we drop
- * the lock in that case and return success. Since the caller has to
- * retry the loop in that case (we changed task state), we don't regrab
- * the lock if we return success.
- */
-static void __io_worker_idle(struct io_wqe *wqe, struct io_worker *worker)
- __must_hold(wqe->lock)
-{
- if (!(worker->flags & IO_WORKER_F_FREE)) {
- worker->flags |= IO_WORKER_F_FREE;
- hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list);
- }
-}
-
-static inline unsigned int io_get_work_hash(struct io_wq_work *work)
-{
- return work->flags >> IO_WQ_HASH_SHIFT;
-}
-
-static bool io_wait_on_hash(struct io_wqe *wqe, unsigned int hash)
-{
- struct io_wq *wq = wqe->wq;
- bool ret = false;
-
- spin_lock_irq(&wq->hash->wait.lock);
- if (list_empty(&wqe->wait.entry)) {
- __add_wait_queue(&wq->hash->wait, &wqe->wait);
- if (!test_bit(hash, &wq->hash->map)) {
- __set_current_state(TASK_RUNNING);
- list_del_init(&wqe->wait.entry);
- ret = true;
- }
- }
- spin_unlock_irq(&wq->hash->wait.lock);
- return ret;
-}
-
-static struct io_wq_work *io_get_next_work(struct io_wqe_acct *acct,
- struct io_worker *worker)
- __must_hold(acct->lock)
-{
- struct io_wq_work_node *node, *prev;
- struct io_wq_work *work, *tail;
- unsigned int stall_hash = -1U;
- struct io_wqe *wqe = worker->wqe;
-
- wq_list_for_each(node, prev, &acct->work_list) {
- unsigned int hash;
-
- work = container_of(node, struct io_wq_work, list);
-
- /* not hashed, can run anytime */
- if (!io_wq_is_hashed(work)) {
- wq_list_del(&acct->work_list, node, prev);
- return work;
- }
-
- hash = io_get_work_hash(work);
- /* all items with this hash lie in [work, tail] */
- tail = wqe->hash_tail[hash];
-
- /* hashed, can run if not already running */
- if (!test_and_set_bit(hash, &wqe->wq->hash->map)) {
- wqe->hash_tail[hash] = NULL;
- wq_list_cut(&acct->work_list, &tail->list, prev);
- return work;
- }
- if (stall_hash == -1U)
- stall_hash = hash;
- /* fast forward to a next hash, for-each will fix up @prev */
- node = &tail->list;
- }
-
- if (stall_hash != -1U) {
- bool unstalled;
-
- /*
- * Set this before dropping the lock to avoid racing with new
- * work being added and clearing the stalled bit.
- */
- set_bit(IO_ACCT_STALLED_BIT, &acct->flags);
- raw_spin_unlock(&acct->lock);
- unstalled = io_wait_on_hash(wqe, stall_hash);
- raw_spin_lock(&acct->lock);
- if (unstalled) {
- clear_bit(IO_ACCT_STALLED_BIT, &acct->flags);
- if (wq_has_sleeper(&wqe->wq->hash->wait))
- wake_up(&wqe->wq->hash->wait);
- }
- }
-
- return NULL;
-}
-
-static bool io_flush_signals(void)
-{
- if (unlikely(test_thread_flag(TIF_NOTIFY_SIGNAL))) {
- __set_current_state(TASK_RUNNING);
- clear_notify_signal();
- if (task_work_pending(current))
- task_work_run();
- return true;
- }
- return false;
-}
-
-static void io_assign_current_work(struct io_worker *worker,
- struct io_wq_work *work)
-{
- if (work) {
- io_flush_signals();
- cond_resched();
- }
-
- raw_spin_lock(&worker->lock);
- worker->cur_work = work;
- worker->next_work = NULL;
- raw_spin_unlock(&worker->lock);
-}
-
-static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work);
-
-static void io_worker_handle_work(struct io_worker *worker)
-{
- struct io_wqe_acct *acct = io_wqe_get_acct(worker);
- struct io_wqe *wqe = worker->wqe;
- struct io_wq *wq = wqe->wq;
- bool do_kill = test_bit(IO_WQ_BIT_EXIT, &wq->state);
-
- do {
- struct io_wq_work *work;
-
- /*
- * If we got some work, mark us as busy. If we didn't, but
- * the list isn't empty, it means we stalled on hashed work.
- * Mark us stalled so we don't keep looking for work when we
- * can't make progress, any work completion or insertion will
- * clear the stalled flag.
- */
- raw_spin_lock(&acct->lock);
- work = io_get_next_work(acct, worker);
- raw_spin_unlock(&acct->lock);
- if (work) {
- __io_worker_busy(wqe, worker);
-
- /*
- * Make sure cancelation can find this, even before
- * it becomes the active work. That avoids a window
- * where the work has been removed from our general
- * work list, but isn't yet discoverable as the
- * current work item for this worker.
- */
- raw_spin_lock(&worker->lock);
- worker->next_work = work;
- raw_spin_unlock(&worker->lock);
- } else {
- break;
- }
- io_assign_current_work(worker, work);
- __set_current_state(TASK_RUNNING);
-
- /* handle a whole dependent link */
- do {
- struct io_wq_work *next_hashed, *linked;
- unsigned int hash = io_get_work_hash(work);
-
- next_hashed = wq_next_work(work);
-
- if (unlikely(do_kill) && (work->flags & IO_WQ_WORK_UNBOUND))
- work->flags |= IO_WQ_WORK_CANCEL;
- wq->do_work(work);
- io_assign_current_work(worker, NULL);
-
- linked = wq->free_work(work);
- work = next_hashed;
- if (!work && linked && !io_wq_is_hashed(linked)) {
- work = linked;
- linked = NULL;
- }
- io_assign_current_work(worker, work);
- if (linked)
- io_wqe_enqueue(wqe, linked);
-
- if (hash != -1U && !next_hashed) {
- /* serialize hash clear with wake_up() */
- spin_lock_irq(&wq->hash->wait.lock);
- clear_bit(hash, &wq->hash->map);
- clear_bit(IO_ACCT_STALLED_BIT, &acct->flags);
- spin_unlock_irq(&wq->hash->wait.lock);
- if (wq_has_sleeper(&wq->hash->wait))
- wake_up(&wq->hash->wait);
- }
- } while (work);
- } while (1);
-}
-
-static int io_wqe_worker(void *data)
-{
- struct io_worker *worker = data;
- struct io_wqe_acct *acct = io_wqe_get_acct(worker);
- struct io_wqe *wqe = worker->wqe;
- struct io_wq *wq = wqe->wq;
- bool last_timeout = false;
- char buf[TASK_COMM_LEN];
-
- worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING);
-
- snprintf(buf, sizeof(buf), "iou-wrk-%d", wq->task->pid);
- set_task_comm(current, buf);
-
- audit_alloc_kernel(current);
-
- while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) {
- long ret;
-
- set_current_state(TASK_INTERRUPTIBLE);
- while (io_acct_run_queue(acct))
- io_worker_handle_work(worker);
-
- raw_spin_lock(&wqe->lock);
- /* timed out, exit unless we're the last worker */
- if (last_timeout && acct->nr_workers > 1) {
- acct->nr_workers--;
- raw_spin_unlock(&wqe->lock);
- __set_current_state(TASK_RUNNING);
- break;
- }
- last_timeout = false;
- __io_worker_idle(wqe, worker);
- raw_spin_unlock(&wqe->lock);
- if (io_flush_signals())
- continue;
- ret = schedule_timeout(WORKER_IDLE_TIMEOUT);
- if (signal_pending(current)) {
- struct ksignal ksig;
-
- if (!get_signal(&ksig))
- continue;
- break;
- }
- last_timeout = !ret;
- }
-
- if (test_bit(IO_WQ_BIT_EXIT, &wq->state))
- io_worker_handle_work(worker);
-
- audit_free(current);
- io_worker_exit(worker);
- return 0;
-}
-
-/*
- * Called when a worker is scheduled in. Mark us as currently running.
- */
-void io_wq_worker_running(struct task_struct *tsk)
-{
- struct io_worker *worker = tsk->worker_private;
-
- if (!worker)
- return;
- if (!(worker->flags & IO_WORKER_F_UP))
- return;
- if (worker->flags & IO_WORKER_F_RUNNING)
- return;
- worker->flags |= IO_WORKER_F_RUNNING;
- io_wqe_inc_running(worker);
-}
-
-/*
- * Called when worker is going to sleep. If there are no workers currently
- * running and we have work pending, wake up a free one or create a new one.
- */
-void io_wq_worker_sleeping(struct task_struct *tsk)
-{
- struct io_worker *worker = tsk->worker_private;
-
- if (!worker)
- return;
- if (!(worker->flags & IO_WORKER_F_UP))
- return;
- if (!(worker->flags & IO_WORKER_F_RUNNING))
- return;
-
- worker->flags &= ~IO_WORKER_F_RUNNING;
- io_wqe_dec_running(worker);
-}
-
-static void io_init_new_worker(struct io_wqe *wqe, struct io_worker *worker,
- struct task_struct *tsk)
-{
- tsk->worker_private = worker;
- worker->task = tsk;
- set_cpus_allowed_ptr(tsk, wqe->cpu_mask);
- tsk->flags |= PF_NO_SETAFFINITY;
-
- raw_spin_lock(&wqe->lock);
- hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list);
- list_add_tail_rcu(&worker->all_list, &wqe->all_list);
- worker->flags |= IO_WORKER_F_FREE;
- raw_spin_unlock(&wqe->lock);
- wake_up_new_task(tsk);
-}
-
-static bool io_wq_work_match_all(struct io_wq_work *work, void *data)
-{
- return true;
-}
-
-static inline bool io_should_retry_thread(long err)
-{
- /*
- * Prevent perpetual task_work retry, if the task (or its group) is
- * exiting.
- */
- if (fatal_signal_pending(current))
- return false;
-
- switch (err) {
- case -EAGAIN:
- case -ERESTARTSYS:
- case -ERESTARTNOINTR:
- case -ERESTARTNOHAND:
- return true;
- default:
- return false;
- }
-}
-
-static void create_worker_cont(struct callback_head *cb)
-{
- struct io_worker *worker;
- struct task_struct *tsk;
- struct io_wqe *wqe;
-
- worker = container_of(cb, struct io_worker, create_work);
- clear_bit_unlock(0, &worker->create_state);
- wqe = worker->wqe;
- tsk = create_io_thread(io_wqe_worker, worker, wqe->node);
- if (!IS_ERR(tsk)) {
- io_init_new_worker(wqe, worker, tsk);
- io_worker_release(worker);
- return;
- } else if (!io_should_retry_thread(PTR_ERR(tsk))) {
- struct io_wqe_acct *acct = io_wqe_get_acct(worker);
-
- atomic_dec(&acct->nr_running);
- raw_spin_lock(&wqe->lock);
- acct->nr_workers--;
- if (!acct->nr_workers) {
- struct io_cb_cancel_data match = {
- .fn = io_wq_work_match_all,
- .cancel_all = true,
- };
-
- raw_spin_unlock(&wqe->lock);
- while (io_acct_cancel_pending_work(wqe, acct, &match))
- ;
- } else {
- raw_spin_unlock(&wqe->lock);
- }
- io_worker_ref_put(wqe->wq);
- kfree(worker);
- return;
- }
-
- /* re-create attempts grab a new worker ref, drop the existing one */
- io_worker_release(worker);
- schedule_work(&worker->work);
-}
-
-static void io_workqueue_create(struct work_struct *work)
-{
- struct io_worker *worker = container_of(work, struct io_worker, work);
- struct io_wqe_acct *acct = io_wqe_get_acct(worker);
-
- if (!io_queue_worker_create(worker, acct, create_worker_cont))
- kfree(worker);
-}
-
-static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index)
-{
- struct io_wqe_acct *acct = &wqe->acct[index];
- struct io_worker *worker;
- struct task_struct *tsk;
-
- __set_current_state(TASK_RUNNING);
-
- worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, wqe->node);
- if (!worker) {
-fail:
- atomic_dec(&acct->nr_running);
- raw_spin_lock(&wqe->lock);
- acct->nr_workers--;
- raw_spin_unlock(&wqe->lock);
- io_worker_ref_put(wq);
- return false;
- }
-
- refcount_set(&worker->ref, 1);
- worker->wqe = wqe;
- raw_spin_lock_init(&worker->lock);
- init_completion(&worker->ref_done);
-
- if (index == IO_WQ_ACCT_BOUND)
- worker->flags |= IO_WORKER_F_BOUND;
-
- tsk = create_io_thread(io_wqe_worker, worker, wqe->node);
- if (!IS_ERR(tsk)) {
- io_init_new_worker(wqe, worker, tsk);
- } else if (!io_should_retry_thread(PTR_ERR(tsk))) {
- kfree(worker);
- goto fail;
- } else {
- INIT_WORK(&worker->work, io_workqueue_create);
- schedule_work(&worker->work);
- }
-
- return true;
-}
-
-/*
- * Iterate the passed in list and call the specific function for each
- * worker that isn't exiting
- */
-static bool io_wq_for_each_worker(struct io_wqe *wqe,
- bool (*func)(struct io_worker *, void *),
- void *data)
-{
- struct io_worker *worker;
- bool ret = false;
-
- list_for_each_entry_rcu(worker, &wqe->all_list, all_list) {
- if (io_worker_get(worker)) {
- /* no task if node is/was offline */
- if (worker->task)
- ret = func(worker, data);
- io_worker_release(worker);
- if (ret)
- break;
- }
- }
-
- return ret;
-}
-
-static bool io_wq_worker_wake(struct io_worker *worker, void *data)
-{
- __set_notify_signal(worker->task);
- wake_up_process(worker->task);
- return false;
-}
-
-static void io_run_cancel(struct io_wq_work *work, struct io_wqe *wqe)
-{
- struct io_wq *wq = wqe->wq;
-
- do {
- work->flags |= IO_WQ_WORK_CANCEL;
- wq->do_work(work);
- work = wq->free_work(work);
- } while (work);
-}
-
-static void io_wqe_insert_work(struct io_wqe *wqe, struct io_wq_work *work)
-{
- struct io_wqe_acct *acct = io_work_get_acct(wqe, work);
- unsigned int hash;
- struct io_wq_work *tail;
-
- if (!io_wq_is_hashed(work)) {
-append:
- wq_list_add_tail(&work->list, &acct->work_list);
- return;
- }
-
- hash = io_get_work_hash(work);
- tail = wqe->hash_tail[hash];
- wqe->hash_tail[hash] = work;
- if (!tail)
- goto append;
-
- wq_list_add_after(&work->list, &tail->list, &acct->work_list);
-}
-
-static bool io_wq_work_match_item(struct io_wq_work *work, void *data)
-{
- return work == data;
-}
-
-static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
-{
- struct io_wqe_acct *acct = io_work_get_acct(wqe, work);
- struct io_cb_cancel_data match;
- unsigned work_flags = work->flags;
- bool do_create;
-
- /*
- * If io-wq is exiting for this task, or if the request has explicitly
- * been marked as one that should not get executed, cancel it here.
- */
- if (test_bit(IO_WQ_BIT_EXIT, &wqe->wq->state) ||
- (work->flags & IO_WQ_WORK_CANCEL)) {
- io_run_cancel(work, wqe);
- return;
- }
-
- raw_spin_lock(&acct->lock);
- io_wqe_insert_work(wqe, work);
- clear_bit(IO_ACCT_STALLED_BIT, &acct->flags);
- raw_spin_unlock(&acct->lock);
-
- raw_spin_lock(&wqe->lock);
- rcu_read_lock();
- do_create = !io_wqe_activate_free_worker(wqe, acct);
- rcu_read_unlock();
-
- raw_spin_unlock(&wqe->lock);
-
- if (do_create && ((work_flags & IO_WQ_WORK_CONCURRENT) ||
- !atomic_read(&acct->nr_running))) {
- bool did_create;
-
- did_create = io_wqe_create_worker(wqe, acct);
- if (likely(did_create))
- return;
-
- raw_spin_lock(&wqe->lock);
- if (acct->nr_workers) {
- raw_spin_unlock(&wqe->lock);
- return;
- }
- raw_spin_unlock(&wqe->lock);
-
- /* fatal condition, failed to create the first worker */
- match.fn = io_wq_work_match_item,
- match.data = work,
- match.cancel_all = false,
-
- io_acct_cancel_pending_work(wqe, acct, &match);
- }
-}
-
-void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work)
-{
- struct io_wqe *wqe = wq->wqes[numa_node_id()];
-
- io_wqe_enqueue(wqe, work);
-}
-
-/*
- * Work items that hash to the same value will not be done in parallel.
- * Used to limit concurrent writes, generally hashed by inode.
- */
-void io_wq_hash_work(struct io_wq_work *work, void *val)
-{
- unsigned int bit;
-
- bit = hash_ptr(val, IO_WQ_HASH_ORDER);
- work->flags |= (IO_WQ_WORK_HASHED | (bit << IO_WQ_HASH_SHIFT));
-}
-
-static bool __io_wq_worker_cancel(struct io_worker *worker,
- struct io_cb_cancel_data *match,
- struct io_wq_work *work)
-{
- if (work && match->fn(work, match->data)) {
- work->flags |= IO_WQ_WORK_CANCEL;
- __set_notify_signal(worker->task);
- return true;
- }
-
- return false;
-}
-
-static bool io_wq_worker_cancel(struct io_worker *worker, void *data)
-{
- struct io_cb_cancel_data *match = data;
-
- /*
- * Hold the lock to avoid ->cur_work going out of scope, caller
- * may dereference the passed in work.
- */
- raw_spin_lock(&worker->lock);
- if (__io_wq_worker_cancel(worker, match, worker->cur_work) ||
- __io_wq_worker_cancel(worker, match, worker->next_work))
- match->nr_running++;
- raw_spin_unlock(&worker->lock);
-
- return match->nr_running && !match->cancel_all;
-}
-
-static inline void io_wqe_remove_pending(struct io_wqe *wqe,
- struct io_wq_work *work,
- struct io_wq_work_node *prev)
-{
- struct io_wqe_acct *acct = io_work_get_acct(wqe, work);
- unsigned int hash = io_get_work_hash(work);
- struct io_wq_work *prev_work = NULL;
-
- if (io_wq_is_hashed(work) && work == wqe->hash_tail[hash]) {
- if (prev)
- prev_work = container_of(prev, struct io_wq_work, list);
- if (prev_work && io_get_work_hash(prev_work) == hash)
- wqe->hash_tail[hash] = prev_work;
- else
- wqe->hash_tail[hash] = NULL;
- }
- wq_list_del(&acct->work_list, &work->list, prev);
-}
-
-static bool io_acct_cancel_pending_work(struct io_wqe *wqe,
- struct io_wqe_acct *acct,
- struct io_cb_cancel_data *match)
-{
- struct io_wq_work_node *node, *prev;
- struct io_wq_work *work;
-
- raw_spin_lock(&acct->lock);
- wq_list_for_each(node, prev, &acct->work_list) {
- work = container_of(node, struct io_wq_work, list);
- if (!match->fn(work, match->data))
- continue;
- io_wqe_remove_pending(wqe, work, prev);
- raw_spin_unlock(&acct->lock);
- io_run_cancel(work, wqe);
- match->nr_pending++;
- /* not safe to continue after unlock */
- return true;
- }
- raw_spin_unlock(&acct->lock);
-
- return false;
-}
-
-static void io_wqe_cancel_pending_work(struct io_wqe *wqe,
- struct io_cb_cancel_data *match)
-{
- int i;
-retry:
- for (i = 0; i < IO_WQ_ACCT_NR; i++) {
- struct io_wqe_acct *acct = io_get_acct(wqe, i == 0);
-
- if (io_acct_cancel_pending_work(wqe, acct, match)) {
- if (match->cancel_all)
- goto retry;
- break;
- }
- }
-}
-
-static void io_wqe_cancel_running_work(struct io_wqe *wqe,
- struct io_cb_cancel_data *match)
-{
- rcu_read_lock();
- io_wq_for_each_worker(wqe, io_wq_worker_cancel, match);
- rcu_read_unlock();
-}
-
-enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel,
- void *data, bool cancel_all)
-{
- struct io_cb_cancel_data match = {
- .fn = cancel,
- .data = data,
- .cancel_all = cancel_all,
- };
- int node;
-
- /*
- * First check pending list, if we're lucky we can just remove it
- * from there. CANCEL_OK means that the work is returned as-new,
- * no completion will be posted for it.
- *
- * Then check if a free (going busy) or busy worker has the work
- * currently running. If we find it there, we'll return CANCEL_RUNNING
- * as an indication that we attempt to signal cancellation. The
- * completion will run normally in this case.
- *
- * Do both of these while holding the wqe->lock, to ensure that
- * we'll find a work item regardless of state.
- */
- for_each_node(node) {
- struct io_wqe *wqe = wq->wqes[node];
-
- io_wqe_cancel_pending_work(wqe, &match);
- if (match.nr_pending && !match.cancel_all)
- return IO_WQ_CANCEL_OK;
-
- raw_spin_lock(&wqe->lock);
- io_wqe_cancel_running_work(wqe, &match);
- raw_spin_unlock(&wqe->lock);
- if (match.nr_running && !match.cancel_all)
- return IO_WQ_CANCEL_RUNNING;
- }
-
- if (match.nr_running)
- return IO_WQ_CANCEL_RUNNING;
- if (match.nr_pending)
- return IO_WQ_CANCEL_OK;
- return IO_WQ_CANCEL_NOTFOUND;
-}
-
-static int io_wqe_hash_wake(struct wait_queue_entry *wait, unsigned mode,
- int sync, void *key)
-{
- struct io_wqe *wqe = container_of(wait, struct io_wqe, wait);
- int i;
-
- list_del_init(&wait->entry);
-
- rcu_read_lock();
- for (i = 0; i < IO_WQ_ACCT_NR; i++) {
- struct io_wqe_acct *acct = &wqe->acct[i];
-
- if (test_and_clear_bit(IO_ACCT_STALLED_BIT, &acct->flags))
- io_wqe_activate_free_worker(wqe, acct);
- }
- rcu_read_unlock();
- return 1;
-}
-
-struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
-{
- int ret, node, i;
- struct io_wq *wq;
-
- if (WARN_ON_ONCE(!data->free_work || !data->do_work))
- return ERR_PTR(-EINVAL);
- if (WARN_ON_ONCE(!bounded))
- return ERR_PTR(-EINVAL);
-
- wq = kzalloc(struct_size(wq, wqes, nr_node_ids), GFP_KERNEL);
- if (!wq)
- return ERR_PTR(-ENOMEM);
- ret = cpuhp_state_add_instance_nocalls(io_wq_online, &wq->cpuhp_node);
- if (ret)
- goto err_wq;
-
- refcount_inc(&data->hash->refs);
- wq->hash = data->hash;
- wq->free_work = data->free_work;
- wq->do_work = data->do_work;
-
- ret = -ENOMEM;
- for_each_node(node) {
- struct io_wqe *wqe;
- int alloc_node = node;
-
- if (!node_online(alloc_node))
- alloc_node = NUMA_NO_NODE;
- wqe = kzalloc_node(sizeof(struct io_wqe), GFP_KERNEL, alloc_node);
- if (!wqe)
- goto err;
- if (!alloc_cpumask_var(&wqe->cpu_mask, GFP_KERNEL))
- goto err;
- cpumask_copy(wqe->cpu_mask, cpumask_of_node(node));
- wq->wqes[node] = wqe;
- wqe->node = alloc_node;
- wqe->acct[IO_WQ_ACCT_BOUND].max_workers = bounded;
- wqe->acct[IO_WQ_ACCT_UNBOUND].max_workers =
- task_rlimit(current, RLIMIT_NPROC);
- INIT_LIST_HEAD(&wqe->wait.entry);
- wqe->wait.func = io_wqe_hash_wake;
- for (i = 0; i < IO_WQ_ACCT_NR; i++) {
- struct io_wqe_acct *acct = &wqe->acct[i];
-
- acct->index = i;
- atomic_set(&acct->nr_running, 0);
- INIT_WQ_LIST(&acct->work_list);
- raw_spin_lock_init(&acct->lock);
- }
- wqe->wq = wq;
- raw_spin_lock_init(&wqe->lock);
- INIT_HLIST_NULLS_HEAD(&wqe->free_list, 0);
- INIT_LIST_HEAD(&wqe->all_list);
- }
-
- wq->task = get_task_struct(data->task);
- atomic_set(&wq->worker_refs, 1);
- init_completion(&wq->worker_done);
- return wq;
-err:
- io_wq_put_hash(data->hash);
- cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node);
- for_each_node(node) {
- if (!wq->wqes[node])
- continue;
- free_cpumask_var(wq->wqes[node]->cpu_mask);
- kfree(wq->wqes[node]);
- }
-err_wq:
- kfree(wq);
- return ERR_PTR(ret);
-}
-
-static bool io_task_work_match(struct callback_head *cb, void *data)
-{
- struct io_worker *worker;
-
- if (cb->func != create_worker_cb && cb->func != create_worker_cont)
- return false;
- worker = container_of(cb, struct io_worker, create_work);
- return worker->wqe->wq == data;
-}
-
-void io_wq_exit_start(struct io_wq *wq)
-{
- set_bit(IO_WQ_BIT_EXIT, &wq->state);
-}
-
-static void io_wq_cancel_tw_create(struct io_wq *wq)
-{
- struct callback_head *cb;
-
- while ((cb = task_work_cancel_match(wq->task, io_task_work_match, wq)) != NULL) {
- struct io_worker *worker;
-
- worker = container_of(cb, struct io_worker, create_work);
- io_worker_cancel_cb(worker);
- }
-}
-
-static void io_wq_exit_workers(struct io_wq *wq)
-{
- int node;
-
- if (!wq->task)
- return;
-
- io_wq_cancel_tw_create(wq);
-
- rcu_read_lock();
- for_each_node(node) {
- struct io_wqe *wqe = wq->wqes[node];
-
- io_wq_for_each_worker(wqe, io_wq_worker_wake, NULL);
- }
- rcu_read_unlock();
- io_worker_ref_put(wq);
- wait_for_completion(&wq->worker_done);
-
- for_each_node(node) {
- spin_lock_irq(&wq->hash->wait.lock);
- list_del_init(&wq->wqes[node]->wait.entry);
- spin_unlock_irq(&wq->hash->wait.lock);
- }
- put_task_struct(wq->task);
- wq->task = NULL;
-}
-
-static void io_wq_destroy(struct io_wq *wq)
-{
- int node;
-
- cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node);
-
- for_each_node(node) {
- struct io_wqe *wqe = wq->wqes[node];
- struct io_cb_cancel_data match = {
- .fn = io_wq_work_match_all,
- .cancel_all = true,
- };
- io_wqe_cancel_pending_work(wqe, &match);
- free_cpumask_var(wqe->cpu_mask);
- kfree(wqe);
- }
- io_wq_put_hash(wq->hash);
- kfree(wq);
-}
-
-void io_wq_put_and_exit(struct io_wq *wq)
-{
- WARN_ON_ONCE(!test_bit(IO_WQ_BIT_EXIT, &wq->state));
-
- io_wq_exit_workers(wq);
- io_wq_destroy(wq);
-}
-
-struct online_data {
- unsigned int cpu;
- bool online;
-};
-
-static bool io_wq_worker_affinity(struct io_worker *worker, void *data)
-{
- struct online_data *od = data;
-
- if (od->online)
- cpumask_set_cpu(od->cpu, worker->wqe->cpu_mask);
- else
- cpumask_clear_cpu(od->cpu, worker->wqe->cpu_mask);
- return false;
-}
-
-static int __io_wq_cpu_online(struct io_wq *wq, unsigned int cpu, bool online)
-{
- struct online_data od = {
- .cpu = cpu,
- .online = online
- };
- int i;
-
- rcu_read_lock();
- for_each_node(i)
- io_wq_for_each_worker(wq->wqes[i], io_wq_worker_affinity, &od);
- rcu_read_unlock();
- return 0;
-}
-
-static int io_wq_cpu_online(unsigned int cpu, struct hlist_node *node)
-{
- struct io_wq *wq = hlist_entry_safe(node, struct io_wq, cpuhp_node);
-
- return __io_wq_cpu_online(wq, cpu, true);
-}
-
-static int io_wq_cpu_offline(unsigned int cpu, struct hlist_node *node)
-{
- struct io_wq *wq = hlist_entry_safe(node, struct io_wq, cpuhp_node);
-
- return __io_wq_cpu_online(wq, cpu, false);
-}
-
-int io_wq_cpu_affinity(struct io_wq *wq, cpumask_var_t mask)
-{
- int i;
-
- rcu_read_lock();
- for_each_node(i) {
- struct io_wqe *wqe = wq->wqes[i];
-
- if (mask)
- cpumask_copy(wqe->cpu_mask, mask);
- else
- cpumask_copy(wqe->cpu_mask, cpumask_of_node(i));
- }
- rcu_read_unlock();
- return 0;
-}
-
-/*
- * Set max number of unbounded workers, returns old value. If new_count is 0,
- * then just return the old value.
- */
-int io_wq_max_workers(struct io_wq *wq, int *new_count)
-{
- int prev[IO_WQ_ACCT_NR];
- bool first_node = true;
- int i, node;
-
- BUILD_BUG_ON((int) IO_WQ_ACCT_BOUND != (int) IO_WQ_BOUND);
- BUILD_BUG_ON((int) IO_WQ_ACCT_UNBOUND != (int) IO_WQ_UNBOUND);
- BUILD_BUG_ON((int) IO_WQ_ACCT_NR != 2);
-
- for (i = 0; i < IO_WQ_ACCT_NR; i++) {
- if (new_count[i] > task_rlimit(current, RLIMIT_NPROC))
- new_count[i] = task_rlimit(current, RLIMIT_NPROC);
- }
-
- for (i = 0; i < IO_WQ_ACCT_NR; i++)
- prev[i] = 0;
-
- rcu_read_lock();
- for_each_node(node) {
- struct io_wqe *wqe = wq->wqes[node];
- struct io_wqe_acct *acct;
-
- raw_spin_lock(&wqe->lock);
- for (i = 0; i < IO_WQ_ACCT_NR; i++) {
- acct = &wqe->acct[i];
- if (first_node)
- prev[i] = max_t(int, acct->max_workers, prev[i]);
- if (new_count[i])
- acct->max_workers = new_count[i];
- }
- raw_spin_unlock(&wqe->lock);
- first_node = false;
- }
- rcu_read_unlock();
-
- for (i = 0; i < IO_WQ_ACCT_NR; i++)
- new_count[i] = prev[i];
-
- return 0;
-}
-
-static __init int io_wq_init(void)
-{
- int ret;
-
- ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "io-wq/online",
- io_wq_cpu_online, io_wq_cpu_offline);
- if (ret < 0)
- return ret;
- io_wq_online = ret;
- return 0;
-}
-subsys_initcall(io_wq_init);
diff --git a/fs/io-wq.h b/fs/io-wq.h
deleted file mode 100644
index ba6eee76d028..000000000000
--- a/fs/io-wq.h
+++ /dev/null
@@ -1,228 +0,0 @@
-#ifndef INTERNAL_IO_WQ_H
-#define INTERNAL_IO_WQ_H
-
-#include <linux/refcount.h>
-
-struct io_wq;
-
-enum {
- IO_WQ_WORK_CANCEL = 1,
- IO_WQ_WORK_HASHED = 2,
- IO_WQ_WORK_UNBOUND = 4,
- IO_WQ_WORK_CONCURRENT = 16,
-
- IO_WQ_HASH_SHIFT = 24, /* upper 8 bits are used for hash key */
-};
-
-enum io_wq_cancel {
- IO_WQ_CANCEL_OK, /* cancelled before started */
- IO_WQ_CANCEL_RUNNING, /* found, running, and attempted cancelled */
- IO_WQ_CANCEL_NOTFOUND, /* work not found */
-};
-
-struct io_wq_work_node {
- struct io_wq_work_node *next;
-};
-
-struct io_wq_work_list {
- struct io_wq_work_node *first;
- struct io_wq_work_node *last;
-};
-
-#define wq_list_for_each(pos, prv, head) \
- for (pos = (head)->first, prv = NULL; pos; prv = pos, pos = (pos)->next)
-
-#define wq_list_for_each_resume(pos, prv) \
- for (; pos; prv = pos, pos = (pos)->next)
-
-#define wq_list_empty(list) (READ_ONCE((list)->first) == NULL)
-#define INIT_WQ_LIST(list) do { \
- (list)->first = NULL; \
-} while (0)
-
-static inline void wq_list_add_after(struct io_wq_work_node *node,
- struct io_wq_work_node *pos,
- struct io_wq_work_list *list)
-{
- struct io_wq_work_node *next = pos->next;
-
- pos->next = node;
- node->next = next;
- if (!next)
- list->last = node;
-}
-
-/**
- * wq_list_merge - merge the second list to the first one.
- * @list0: the first list
- * @list1: the second list
- * Return the first node after mergence.
- */
-static inline struct io_wq_work_node *wq_list_merge(struct io_wq_work_list *list0,
- struct io_wq_work_list *list1)
-{
- struct io_wq_work_node *ret;
-
- if (!list0->first) {
- ret = list1->first;
- } else {
- ret = list0->first;
- list0->last->next = list1->first;
- }
- INIT_WQ_LIST(list0);
- INIT_WQ_LIST(list1);
- return ret;
-}
-
-static inline void wq_list_add_tail(struct io_wq_work_node *node,
- struct io_wq_work_list *list)
-{
- node->next = NULL;
- if (!list->first) {
- list->last = node;
- WRITE_ONCE(list->first, node);
- } else {
- list->last->next = node;
- list->last = node;
- }
-}
-
-static inline void wq_list_add_head(struct io_wq_work_node *node,
- struct io_wq_work_list *list)
-{
- node->next = list->first;
- if (!node->next)
- list->last = node;
- WRITE_ONCE(list->first, node);
-}
-
-static inline void wq_list_cut(struct io_wq_work_list *list,
- struct io_wq_work_node *last,
- struct io_wq_work_node *prev)
-{
- /* first in the list, if prev==NULL */
- if (!prev)
- WRITE_ONCE(list->first, last->next);
- else
- prev->next = last->next;
-
- if (last == list->last)
- list->last = prev;
- last->next = NULL;
-}
-
-static inline void __wq_list_splice(struct io_wq_work_list *list,
- struct io_wq_work_node *to)
-{
- list->last->next = to->next;
- to->next = list->first;
- INIT_WQ_LIST(list);
-}
-
-static inline bool wq_list_splice(struct io_wq_work_list *list,
- struct io_wq_work_node *to)
-{
- if (!wq_list_empty(list)) {
- __wq_list_splice(list, to);
- return true;
- }
- return false;
-}
-
-static inline void wq_stack_add_head(struct io_wq_work_node *node,
- struct io_wq_work_node *stack)
-{
- node->next = stack->next;
- stack->next = node;
-}
-
-static inline void wq_list_del(struct io_wq_work_list *list,
- struct io_wq_work_node *node,
- struct io_wq_work_node *prev)
-{
- wq_list_cut(list, node, prev);
-}
-
-static inline
-struct io_wq_work_node *wq_stack_extract(struct io_wq_work_node *stack)
-{
- struct io_wq_work_node *node = stack->next;
-
- stack->next = node->next;
- return node;
-}
-
-struct io_wq_work {
- struct io_wq_work_node list;
- unsigned flags;
- int cancel_seq;
-};
-
-static inline struct io_wq_work *wq_next_work(struct io_wq_work *work)
-{
- if (!work->list.next)
- return NULL;
-
- return container_of(work->list.next, struct io_wq_work, list);
-}
-
-typedef struct io_wq_work *(free_work_fn)(struct io_wq_work *);
-typedef void (io_wq_work_fn)(struct io_wq_work *);
-
-struct io_wq_hash {
- refcount_t refs;
- unsigned long map;
- struct wait_queue_head wait;
-};
-
-static inline void io_wq_put_hash(struct io_wq_hash *hash)
-{
- if (refcount_dec_and_test(&hash->refs))
- kfree(hash);
-}
-
-struct io_wq_data {
- struct io_wq_hash *hash;
- struct task_struct *task;
- io_wq_work_fn *do_work;
- free_work_fn *free_work;
-};
-
-struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data);
-void io_wq_exit_start(struct io_wq *wq);
-void io_wq_put_and_exit(struct io_wq *wq);
-
-void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work);
-void io_wq_hash_work(struct io_wq_work *work, void *val);
-
-int io_wq_cpu_affinity(struct io_wq *wq, cpumask_var_t mask);
-int io_wq_max_workers(struct io_wq *wq, int *new_count);
-
-static inline bool io_wq_is_hashed(struct io_wq_work *work)
-{
- return work->flags & IO_WQ_WORK_HASHED;
-}
-
-typedef bool (work_cancel_fn)(struct io_wq_work *, void *);
-
-enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel,
- void *data, bool cancel_all);
-
-#if defined(CONFIG_IO_WQ)
-extern void io_wq_worker_sleeping(struct task_struct *);
-extern void io_wq_worker_running(struct task_struct *);
-#else
-static inline void io_wq_worker_sleeping(struct task_struct *tsk)
-{
-}
-static inline void io_wq_worker_running(struct task_struct *tsk)
-{
-}
-#endif
-
-static inline bool io_wq_current_is_worker(void)
-{
- return in_task() && (current->flags & PF_IO_WORKER) &&
- current->worker_private;
-}
-#endif
diff --git a/fs/io_uring.c b/fs/io_uring.c
deleted file mode 100644
index a01ea49f3017..000000000000
--- a/fs/io_uring.c
+++ /dev/null
@@ -1,13265 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Shared application/kernel submission and completion ring pairs, for
- * supporting fast/efficient IO.
- *
- * A note on the read/write ordering memory barriers that are matched between
- * the application and kernel side.
- *
- * After the application reads the CQ ring tail, it must use an
- * appropriate smp_rmb() to pair with the smp_wmb() the kernel uses
- * before writing the tail (using smp_load_acquire to read the tail will
- * do). It also needs a smp_mb() before updating CQ head (ordering the
- * entry load(s) with the head store), pairing with an implicit barrier
- * through a control-dependency in io_get_cqe (smp_store_release to
- * store head will do). Failure to do so could lead to reading invalid
- * CQ entries.
- *
- * Likewise, the application must use an appropriate smp_wmb() before
- * writing the SQ tail (ordering SQ entry stores with the tail store),
- * which pairs with smp_load_acquire in io_get_sqring (smp_store_release
- * to store the tail will do). And it needs a barrier ordering the SQ
- * head load before writing new SQ entries (smp_load_acquire to read
- * head will do).
- *
- * When using the SQ poll thread (IORING_SETUP_SQPOLL), the application
- * needs to check the SQ flags for IORING_SQ_NEED_WAKEUP *after*
- * updating the SQ tail; a full memory barrier smp_mb() is needed
- * between.
- *
- * Also see the examples in the liburing library:
- *
- * git://git.kernel.dk/liburing
- *
- * io_uring also uses READ/WRITE_ONCE() for _any_ store or load that happens
- * from data shared between the kernel and application. This is done both
- * for ordering purposes, but also to ensure that once a value is loaded from
- * data that the application could potentially modify, it remains stable.
- *
- * Copyright (C) 2018-2019 Jens Axboe
- * Copyright (c) 2018-2019 Christoph Hellwig
- */
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/errno.h>
-#include <linux/syscalls.h>
-#include <linux/compat.h>
-#include <net/compat.h>
-#include <linux/refcount.h>
-#include <linux/uio.h>
-#include <linux/bits.h>
-
-#include <linux/sched/signal.h>
-#include <linux/fs.h>
-#include <linux/file.h>
-#include <linux/fdtable.h>
-#include <linux/mm.h>
-#include <linux/mman.h>
-#include <linux/percpu.h>
-#include <linux/slab.h>
-#include <linux/blk-mq.h>
-#include <linux/bvec.h>
-#include <linux/net.h>
-#include <net/sock.h>
-#include <net/af_unix.h>
-#include <net/scm.h>
-#include <linux/anon_inodes.h>
-#include <linux/sched/mm.h>
-#include <linux/uaccess.h>
-#include <linux/nospec.h>
-#include <linux/sizes.h>
-#include <linux/hugetlb.h>
-#include <linux/highmem.h>
-#include <linux/namei.h>
-#include <linux/fsnotify.h>
-#include <linux/fadvise.h>
-#include <linux/eventpoll.h>
-#include <linux/splice.h>
-#include <linux/task_work.h>
-#include <linux/pagemap.h>
-#include <linux/io_uring.h>
-#include <linux/audit.h>
-#include <linux/security.h>
-#include <linux/xattr.h>
-
-#define CREATE_TRACE_POINTS
-#include <trace/events/io_uring.h>
-
-#include <uapi/linux/io_uring.h>
-
-#include "internal.h"
-#include "io-wq.h"
-
-#define IORING_MAX_ENTRIES 32768
-#define IORING_MAX_CQ_ENTRIES (2 * IORING_MAX_ENTRIES)
-#define IORING_SQPOLL_CAP_ENTRIES_VALUE 8
-
-/* only define max */
-#define IORING_MAX_FIXED_FILES (1U << 20)
-#define IORING_MAX_RESTRICTIONS (IORING_RESTRICTION_LAST + \
- IORING_REGISTER_LAST + IORING_OP_LAST)
-
-#define IO_RSRC_TAG_TABLE_SHIFT (PAGE_SHIFT - 3)
-#define IO_RSRC_TAG_TABLE_MAX (1U << IO_RSRC_TAG_TABLE_SHIFT)
-#define IO_RSRC_TAG_TABLE_MASK (IO_RSRC_TAG_TABLE_MAX - 1)
-
-#define IORING_MAX_REG_BUFFERS (1U << 14)
-
-#define SQE_COMMON_FLAGS (IOSQE_FIXED_FILE | IOSQE_IO_LINK | \
- IOSQE_IO_HARDLINK | IOSQE_ASYNC)
-
-#define SQE_VALID_FLAGS (SQE_COMMON_FLAGS | IOSQE_BUFFER_SELECT | \
- IOSQE_IO_DRAIN | IOSQE_CQE_SKIP_SUCCESS)
-
-#define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \
- REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \
- REQ_F_ASYNC_DATA)
-
-#define IO_REQ_CLEAN_SLOW_FLAGS (REQ_F_REFCOUNT | REQ_F_LINK | REQ_F_HARDLINK |\
- IO_REQ_CLEAN_FLAGS)
-
-#define IO_APOLL_MULTI_POLLED (REQ_F_APOLL_MULTISHOT | REQ_F_POLLED)
-
-#define IO_TCTX_REFS_CACHE_NR (1U << 10)
-
-struct io_uring {
- u32 head ____cacheline_aligned_in_smp;
- u32 tail ____cacheline_aligned_in_smp;
-};
-
-/*
- * This data is shared with the application through the mmap at offsets
- * IORING_OFF_SQ_RING and IORING_OFF_CQ_RING.
- *
- * The offsets to the member fields are published through struct
- * io_sqring_offsets when calling io_uring_setup.
- */
-struct io_rings {
- /*
- * Head and tail offsets into the ring; the offsets need to be
- * masked to get valid indices.
- *
- * The kernel controls head of the sq ring and the tail of the cq ring,
- * and the application controls tail of the sq ring and the head of the
- * cq ring.
- */
- struct io_uring sq, cq;
- /*
- * Bitmasks to apply to head and tail offsets (constant, equals
- * ring_entries - 1)
- */
- u32 sq_ring_mask, cq_ring_mask;
- /* Ring sizes (constant, power of 2) */
- u32 sq_ring_entries, cq_ring_entries;
- /*
- * Number of invalid entries dropped by the kernel due to
- * invalid index stored in array
- *
- * Written by the kernel, shouldn't be modified by the
- * application (i.e. get number of "new events" by comparing to
- * cached value).
- *
- * After a new SQ head value was read by the application this
- * counter includes all submissions that were dropped reaching
- * the new SQ head (and possibly more).
- */
- u32 sq_dropped;
- /*
- * Runtime SQ flags
- *
- * Written by the kernel, shouldn't be modified by the
- * application.
- *
- * The application needs a full memory barrier before checking
- * for IORING_SQ_NEED_WAKEUP after updating the sq tail.
- */
- atomic_t sq_flags;
- /*
- * Runtime CQ flags
- *
- * Written by the application, shouldn't be modified by the
- * kernel.
- */
- u32 cq_flags;
- /*
- * Number of completion events lost because the queue was full;
- * this should be avoided by the application by making sure
- * there are not more requests pending than there is space in
- * the completion queue.
- *
- * Written by the kernel, shouldn't be modified by the
- * application (i.e. get number of "new events" by comparing to
- * cached value).
- *
- * As completion events come in out of order this counter is not
- * ordered with any other data.
- */
- u32 cq_overflow;
- /*
- * Ring buffer of completion events.
- *
- * The kernel writes completion events fresh every time they are
- * produced, so the application is allowed to modify pending
- * entries.
- */
- struct io_uring_cqe cqes[] ____cacheline_aligned_in_smp;
-};
-
-struct io_mapped_ubuf {
- u64 ubuf;
- u64 ubuf_end;
- unsigned int nr_bvecs;
- unsigned long acct_pages;
- struct bio_vec bvec[];
-};
-
-struct io_ring_ctx;
-
-struct io_overflow_cqe {
- struct list_head list;
- struct io_uring_cqe cqe;
-};
-
-/*
- * FFS_SCM is only available on 64-bit archs, for 32-bit we just define it as 0
- * and define IO_URING_SCM_ALL. For this case, we use SCM for all files as we
- * can't safely always dereference the file when the task has exited and ring
- * cleanup is done. If a file is tracked and part of SCM, then unix gc on
- * process exit may reap it before __io_sqe_files_unregister() is run.
- */
-#define FFS_NOWAIT 0x1UL
-#define FFS_ISREG 0x2UL
-#if defined(CONFIG_64BIT)
-#define FFS_SCM 0x4UL
-#else
-#define IO_URING_SCM_ALL
-#define FFS_SCM 0x0UL
-#endif
-#define FFS_MASK ~(FFS_NOWAIT|FFS_ISREG|FFS_SCM)
-
-struct io_fixed_file {
- /* file * with additional FFS_* flags */
- unsigned long file_ptr;
-};
-
-struct io_rsrc_put {
- struct list_head list;
- u64 tag;
- union {
- void *rsrc;
- struct file *file;
- struct io_mapped_ubuf *buf;
- };
-};
-
-struct io_file_table {
- struct io_fixed_file *files;
- unsigned long *bitmap;
- unsigned int alloc_hint;
-};
-
-struct io_rsrc_node {
- struct percpu_ref refs;
- struct list_head node;
- struct list_head rsrc_list;
- struct io_rsrc_data *rsrc_data;
- struct llist_node llist;
- bool done;
-};
-
-typedef void (rsrc_put_fn)(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc);
-
-struct io_rsrc_data {
- struct io_ring_ctx *ctx;
-
- u64 **tags;
- unsigned int nr;
- rsrc_put_fn *do_put;
- atomic_t refs;
- struct completion done;
- bool quiesce;
-};
-
-#define IO_BUFFER_LIST_BUF_PER_PAGE (PAGE_SIZE / sizeof(struct io_uring_buf))
-struct io_buffer_list {
- /*
- * If ->buf_nr_pages is set, then buf_pages/buf_ring are used. If not,
- * then these are classic provided buffers and ->buf_list is used.
- */
- union {
- struct list_head buf_list;
- struct {
- struct page **buf_pages;
- struct io_uring_buf_ring *buf_ring;
- };
- };
- __u16 bgid;
-
- /* below is for ring provided buffers */
- __u16 buf_nr_pages;
- __u16 nr_entries;
- __u16 head;
- __u16 mask;
-};
-
-struct io_buffer {
- struct list_head list;
- __u64 addr;
- __u32 len;
- __u16 bid;
- __u16 bgid;
-};
-
-struct io_restriction {
- DECLARE_BITMAP(register_op, IORING_REGISTER_LAST);
- DECLARE_BITMAP(sqe_op, IORING_OP_LAST);
- u8 sqe_flags_allowed;
- u8 sqe_flags_required;
- bool registered;
-};
-
-enum {
- IO_SQ_THREAD_SHOULD_STOP = 0,
- IO_SQ_THREAD_SHOULD_PARK,
-};
-
-struct io_sq_data {
- refcount_t refs;
- atomic_t park_pending;
- struct mutex lock;
-
- /* ctx's that are using this sqd */
- struct list_head ctx_list;
-
- struct task_struct *thread;
- struct wait_queue_head wait;
-
- unsigned sq_thread_idle;
- int sq_cpu;
- pid_t task_pid;
- pid_t task_tgid;
-
- unsigned long state;
- struct completion exited;
-};
-
-#define IO_COMPL_BATCH 32
-#define IO_REQ_CACHE_SIZE 32
-#define IO_REQ_ALLOC_BATCH 8
-
-struct io_submit_link {
- struct io_kiocb *head;
- struct io_kiocb *last;
-};
-
-struct io_submit_state {
- /* inline/task_work completion list, under ->uring_lock */
- struct io_wq_work_node free_list;
- /* batch completion logic */
- struct io_wq_work_list compl_reqs;
- struct io_submit_link link;
-
- bool plug_started;
- bool need_plug;
- bool flush_cqes;
- unsigned short submit_nr;
- struct blk_plug plug;
-};
-
-struct io_ev_fd {
- struct eventfd_ctx *cq_ev_fd;
- unsigned int eventfd_async: 1;
- struct rcu_head rcu;
-};
-
-#define BGID_ARRAY 64
-
-struct io_ring_ctx {
- /* const or read-mostly hot data */
- struct {
- struct percpu_ref refs;
-
- struct io_rings *rings;
- unsigned int flags;
- enum task_work_notify_mode notify_method;
- unsigned int compat: 1;
- unsigned int drain_next: 1;
- unsigned int restricted: 1;
- unsigned int off_timeout_used: 1;
- unsigned int drain_active: 1;
- unsigned int drain_disabled: 1;
- unsigned int has_evfd: 1;
- unsigned int syscall_iopoll: 1;
- } ____cacheline_aligned_in_smp;
-
- /* submission data */
- struct {
- struct mutex uring_lock;
-
- /*
- * Ring buffer of indices into array of io_uring_sqe, which is
- * mmapped by the application using the IORING_OFF_SQES offset.
- *
- * This indirection could e.g. be used to assign fixed
- * io_uring_sqe entries to operations and only submit them to
- * the queue when needed.
- *
- * The kernel modifies neither the indices array nor the entries
- * array.
- */
- u32 *sq_array;
- struct io_uring_sqe *sq_sqes;
- unsigned cached_sq_head;
- unsigned sq_entries;
- struct list_head defer_list;
-
- /*
- * Fixed resources fast path, should be accessed only under
- * uring_lock, and updated through io_uring_register(2)
- */
- struct io_rsrc_node *rsrc_node;
- int rsrc_cached_refs;
- atomic_t cancel_seq;
- struct io_file_table file_table;
- unsigned nr_user_files;
- unsigned nr_user_bufs;
- struct io_mapped_ubuf **user_bufs;
-
- struct io_submit_state submit_state;
-
- struct io_buffer_list *io_bl;
- struct xarray io_bl_xa;
- struct list_head io_buffers_cache;
-
- struct list_head timeout_list;
- struct list_head ltimeout_list;
- struct list_head cq_overflow_list;
- struct list_head apoll_cache;
- struct xarray personalities;
- u32 pers_next;
- unsigned sq_thread_idle;
- } ____cacheline_aligned_in_smp;
-
- /* IRQ completion list, under ->completion_lock */
- struct io_wq_work_list locked_free_list;
- unsigned int locked_free_nr;
-
- const struct cred *sq_creds; /* cred used for __io_sq_thread() */
- struct io_sq_data *sq_data; /* if using sq thread polling */
-
- struct wait_queue_head sqo_sq_wait;
- struct list_head sqd_list;
-
- unsigned long check_cq;
-
- struct {
- /*
- * We cache a range of free CQEs we can use, once exhausted it
- * should go through a slower range setup, see __io_get_cqe()
- */
- struct io_uring_cqe *cqe_cached;
- struct io_uring_cqe *cqe_sentinel;
-
- unsigned cached_cq_tail;
- unsigned cq_entries;
- struct io_ev_fd __rcu *io_ev_fd;
- struct wait_queue_head cq_wait;
- unsigned cq_extra;
- atomic_t cq_timeouts;
- unsigned cq_last_tm_flush;
- } ____cacheline_aligned_in_smp;
-
- struct {
- spinlock_t completion_lock;
-
- spinlock_t timeout_lock;
-
- /*
- * ->iopoll_list is protected by the ctx->uring_lock for
- * io_uring instances that don't use IORING_SETUP_SQPOLL.
- * For SQPOLL, only the single threaded io_sq_thread() will
- * manipulate the list, hence no extra locking is needed there.
- */
- struct io_wq_work_list iopoll_list;
- struct hlist_head *cancel_hash;
- unsigned cancel_hash_bits;
- bool poll_multi_queue;
-
- struct list_head io_buffers_comp;
- } ____cacheline_aligned_in_smp;
-
- struct io_restriction restrictions;
-
- /* slow path rsrc auxilary data, used by update/register */
- struct {
- struct io_rsrc_node *rsrc_backup_node;
- struct io_mapped_ubuf *dummy_ubuf;
- struct io_rsrc_data *file_data;
- struct io_rsrc_data *buf_data;
-
- struct delayed_work rsrc_put_work;
- struct llist_head rsrc_put_llist;
- struct list_head rsrc_ref_list;
- spinlock_t rsrc_ref_lock;
-
- struct list_head io_buffers_pages;
- };
-
- /* Keep this last, we don't need it for the fast path */
- struct {
- #if defined(CONFIG_UNIX)
- struct socket *ring_sock;
- #endif
- /* hashed buffered write serialization */
- struct io_wq_hash *hash_map;
-
- /* Only used for accounting purposes */
- struct user_struct *user;
- struct mm_struct *mm_account;
-
- /* ctx exit and cancelation */
- struct llist_head fallback_llist;
- struct delayed_work fallback_work;
- struct work_struct exit_work;
- struct list_head tctx_list;
- struct completion ref_comp;
- u32 iowq_limits[2];
- bool iowq_limits_set;
- };
-};
-
-/*
- * Arbitrary limit, can be raised if need be
- */
-#define IO_RINGFD_REG_MAX 16
-
-struct io_uring_task {
- /* submission side */
- int cached_refs;
- struct xarray xa;
- struct wait_queue_head wait;
- const struct io_ring_ctx *last;
- struct io_wq *io_wq;
- struct percpu_counter inflight;
- atomic_t inflight_tracked;
- atomic_t in_idle;
-
- spinlock_t task_lock;
- struct io_wq_work_list task_list;
- struct io_wq_work_list prio_task_list;
- struct callback_head task_work;
- struct file **registered_rings;
- bool task_running;
-};
-
-/*
- * First field must be the file pointer in all the
- * iocb unions! See also 'struct kiocb' in <linux/fs.h>
- */
-struct io_poll_iocb {
- struct file *file;
- struct wait_queue_head *head;
- __poll_t events;
- struct wait_queue_entry wait;
-};
-
-struct io_poll_update {
- struct file *file;
- u64 old_user_data;
- u64 new_user_data;
- __poll_t events;
- bool update_events;
- bool update_user_data;
-};
-
-struct io_close {
- struct file *file;
- int fd;
- u32 file_slot;
-};
-
-struct io_timeout_data {
- struct io_kiocb *req;
- struct hrtimer timer;
- struct timespec64 ts;
- enum hrtimer_mode mode;
- u32 flags;
-};
-
-struct io_accept {
- struct file *file;
- struct sockaddr __user *addr;
- int __user *addr_len;
- int flags;
- u32 file_slot;
- unsigned long nofile;
-};
-
-struct io_socket {
- struct file *file;
- int domain;
- int type;
- int protocol;
- int flags;
- u32 file_slot;
- unsigned long nofile;
-};
-
-struct io_sync {
- struct file *file;
- loff_t len;
- loff_t off;
- int flags;
- int mode;
-};
-
-struct io_cancel {
- struct file *file;
- u64 addr;
- u32 flags;
- s32 fd;
-};
-
-struct io_timeout {
- struct file *file;
- u32 off;
- u32 target_seq;
- struct list_head list;
- /* head of the link, used by linked timeouts only */
- struct io_kiocb *head;
- /* for linked completions */
- struct io_kiocb *prev;
-};
-
-struct io_timeout_rem {
- struct file *file;
- u64 addr;
-
- /* timeout update */
- struct timespec64 ts;
- u32 flags;
- bool ltimeout;
-};
-
-struct io_rw {
- /* NOTE: kiocb has the file as the first member, so don't do it here */
- struct kiocb kiocb;
- u64 addr;
- u32 len;
- rwf_t flags;
-};
-
-struct io_connect {
- struct file *file;
- struct sockaddr __user *addr;
- int addr_len;
-};
-
-struct io_sr_msg {
- struct file *file;
- union {
- struct compat_msghdr __user *umsg_compat;
- struct user_msghdr __user *umsg;
- void __user *buf;
- };
- int msg_flags;
- size_t len;
- size_t done_io;
- unsigned int flags;
-};
-
-struct io_open {
- struct file *file;
- int dfd;
- u32 file_slot;
- struct filename *filename;
- struct open_how how;
- unsigned long nofile;
-};
-
-struct io_rsrc_update {
- struct file *file;
- u64 arg;
- u32 nr_args;
- u32 offset;
-};
-
-struct io_fadvise {
- struct file *file;
- u64 offset;
- u32 len;
- u32 advice;
-};
-
-struct io_madvise {
- struct file *file;
- u64 addr;
- u32 len;
- u32 advice;
-};
-
-struct io_epoll {
- struct file *file;
- int epfd;
- int op;
- int fd;
- struct epoll_event event;
-};
-
-struct io_splice {
- struct file *file_out;
- loff_t off_out;
- loff_t off_in;
- u64 len;
- int splice_fd_in;
- unsigned int flags;
-};
-
-struct io_provide_buf {
- struct file *file;
- __u64 addr;
- __u32 len;
- __u32 bgid;
- __u16 nbufs;
- __u16 bid;
-};
-
-struct io_statx {
- struct file *file;
- int dfd;
- unsigned int mask;
- unsigned int flags;
- struct filename *filename;
- struct statx __user *buffer;
-};
-
-struct io_shutdown {
- struct file *file;
- int how;
-};
-
-struct io_rename {
- struct file *file;
- int old_dfd;
- int new_dfd;
- struct filename *oldpath;
- struct filename *newpath;
- int flags;
-};
-
-struct io_unlink {
- struct file *file;
- int dfd;
- int flags;
- struct filename *filename;
-};
-
-struct io_mkdir {
- struct file *file;
- int dfd;
- umode_t mode;
- struct filename *filename;
-};
-
-struct io_symlink {
- struct file *file;
- int new_dfd;
- struct filename *oldpath;
- struct filename *newpath;
-};
-
-struct io_hardlink {
- struct file *file;
- int old_dfd;
- int new_dfd;
- struct filename *oldpath;
- struct filename *newpath;
- int flags;
-};
-
-struct io_msg {
- struct file *file;
- u64 user_data;
- u32 len;
-};
-
-struct io_async_connect {
- struct sockaddr_storage address;
-};
-
-struct io_async_msghdr {
- struct iovec fast_iov[UIO_FASTIOV];
- /* points to an allocated iov, if NULL we use fast_iov instead */
- struct iovec *free_iov;
- struct sockaddr __user *uaddr;
- struct msghdr msg;
- struct sockaddr_storage addr;
-};
-
-struct io_rw_state {
- struct iov_iter iter;
- struct iov_iter_state iter_state;
- struct iovec fast_iov[UIO_FASTIOV];
-};
-
-struct io_async_rw {
- struct io_rw_state s;
- const struct iovec *free_iovec;
- size_t bytes_done;
- struct wait_page_queue wpq;
-};
-
-struct io_xattr {
- struct file *file;
- struct xattr_ctx ctx;
- struct filename *filename;
-};
-
-enum {
- REQ_F_FIXED_FILE_BIT = IOSQE_FIXED_FILE_BIT,
- REQ_F_IO_DRAIN_BIT = IOSQE_IO_DRAIN_BIT,
- REQ_F_LINK_BIT = IOSQE_IO_LINK_BIT,
- REQ_F_HARDLINK_BIT = IOSQE_IO_HARDLINK_BIT,
- REQ_F_FORCE_ASYNC_BIT = IOSQE_ASYNC_BIT,
- REQ_F_BUFFER_SELECT_BIT = IOSQE_BUFFER_SELECT_BIT,
- REQ_F_CQE_SKIP_BIT = IOSQE_CQE_SKIP_SUCCESS_BIT,
-
- /* first byte is taken by user flags, shift it to not overlap */
- REQ_F_FAIL_BIT = 8,
- REQ_F_INFLIGHT_BIT,
- REQ_F_CUR_POS_BIT,
- REQ_F_NOWAIT_BIT,
- REQ_F_LINK_TIMEOUT_BIT,
- REQ_F_NEED_CLEANUP_BIT,
- REQ_F_POLLED_BIT,
- REQ_F_BUFFER_SELECTED_BIT,
- REQ_F_BUFFER_RING_BIT,
- REQ_F_COMPLETE_INLINE_BIT,
- REQ_F_REISSUE_BIT,
- REQ_F_CREDS_BIT,
- REQ_F_REFCOUNT_BIT,
- REQ_F_ARM_LTIMEOUT_BIT,
- REQ_F_ASYNC_DATA_BIT,
- REQ_F_SKIP_LINK_CQES_BIT,
- REQ_F_SINGLE_POLL_BIT,
- REQ_F_DOUBLE_POLL_BIT,
- REQ_F_PARTIAL_IO_BIT,
- REQ_F_CQE32_INIT_BIT,
- REQ_F_APOLL_MULTISHOT_BIT,
- /* keep async read/write and isreg together and in order */
- REQ_F_SUPPORT_NOWAIT_BIT,
- REQ_F_ISREG_BIT,
-
- /* not a real bit, just to check we're not overflowing the space */
- __REQ_F_LAST_BIT,
-};
-
-enum {
- /* ctx owns file */
- REQ_F_FIXED_FILE = BIT(REQ_F_FIXED_FILE_BIT),
- /* drain existing IO first */
- REQ_F_IO_DRAIN = BIT(REQ_F_IO_DRAIN_BIT),
- /* linked sqes */
- REQ_F_LINK = BIT(REQ_F_LINK_BIT),
- /* doesn't sever on completion < 0 */
- REQ_F_HARDLINK = BIT(REQ_F_HARDLINK_BIT),
- /* IOSQE_ASYNC */
- REQ_F_FORCE_ASYNC = BIT(REQ_F_FORCE_ASYNC_BIT),
- /* IOSQE_BUFFER_SELECT */
- REQ_F_BUFFER_SELECT = BIT(REQ_F_BUFFER_SELECT_BIT),
- /* IOSQE_CQE_SKIP_SUCCESS */
- REQ_F_CQE_SKIP = BIT(REQ_F_CQE_SKIP_BIT),
-
- /* fail rest of links */
- REQ_F_FAIL = BIT(REQ_F_FAIL_BIT),
- /* on inflight list, should be cancelled and waited on exit reliably */
- REQ_F_INFLIGHT = BIT(REQ_F_INFLIGHT_BIT),
- /* read/write uses file position */
- REQ_F_CUR_POS = BIT(REQ_F_CUR_POS_BIT),
- /* must not punt to workers */
- REQ_F_NOWAIT = BIT(REQ_F_NOWAIT_BIT),
- /* has or had linked timeout */
- REQ_F_LINK_TIMEOUT = BIT(REQ_F_LINK_TIMEOUT_BIT),
- /* needs cleanup */
- REQ_F_NEED_CLEANUP = BIT(REQ_F_NEED_CLEANUP_BIT),
- /* already went through poll handler */
- REQ_F_POLLED = BIT(REQ_F_POLLED_BIT),
- /* buffer already selected */
- REQ_F_BUFFER_SELECTED = BIT(REQ_F_BUFFER_SELECTED_BIT),
- /* buffer selected from ring, needs commit */
- REQ_F_BUFFER_RING = BIT(REQ_F_BUFFER_RING_BIT),
- /* completion is deferred through io_comp_state */
- REQ_F_COMPLETE_INLINE = BIT(REQ_F_COMPLETE_INLINE_BIT),
- /* caller should reissue async */
- REQ_F_REISSUE = BIT(REQ_F_REISSUE_BIT),
- /* supports async reads/writes */
- REQ_F_SUPPORT_NOWAIT = BIT(REQ_F_SUPPORT_NOWAIT_BIT),
- /* regular file */
- REQ_F_ISREG = BIT(REQ_F_ISREG_BIT),
- /* has creds assigned */
- REQ_F_CREDS = BIT(REQ_F_CREDS_BIT),
- /* skip refcounting if not set */
- REQ_F_REFCOUNT = BIT(REQ_F_REFCOUNT_BIT),
- /* there is a linked timeout that has to be armed */
- REQ_F_ARM_LTIMEOUT = BIT(REQ_F_ARM_LTIMEOUT_BIT),
- /* ->async_data allocated */
- REQ_F_ASYNC_DATA = BIT(REQ_F_ASYNC_DATA_BIT),
- /* don't post CQEs while failing linked requests */
- REQ_F_SKIP_LINK_CQES = BIT(REQ_F_SKIP_LINK_CQES_BIT),
- /* single poll may be active */
- REQ_F_SINGLE_POLL = BIT(REQ_F_SINGLE_POLL_BIT),
- /* double poll may active */
- REQ_F_DOUBLE_POLL = BIT(REQ_F_DOUBLE_POLL_BIT),
- /* request has already done partial IO */
- REQ_F_PARTIAL_IO = BIT(REQ_F_PARTIAL_IO_BIT),
- /* fast poll multishot mode */
- REQ_F_APOLL_MULTISHOT = BIT(REQ_F_APOLL_MULTISHOT_BIT),
- /* ->extra1 and ->extra2 are initialised */
- REQ_F_CQE32_INIT = BIT(REQ_F_CQE32_INIT_BIT),
-};
-
-struct async_poll {
- struct io_poll_iocb poll;
- struct io_poll_iocb *double_poll;
-};
-
-typedef void (*io_req_tw_func_t)(struct io_kiocb *req, bool *locked);
-
-struct io_task_work {
- union {
- struct io_wq_work_node node;
- struct llist_node fallback_node;
- };
- io_req_tw_func_t func;
-};
-
-enum {
- IORING_RSRC_FILE = 0,
- IORING_RSRC_BUFFER = 1,
-};
-
-struct io_cqe {
- __u64 user_data;
- __s32 res;
- /* fd initially, then cflags for completion */
- union {
- __u32 flags;
- int fd;
- };
-};
-
-enum {
- IO_CHECK_CQ_OVERFLOW_BIT,
- IO_CHECK_CQ_DROPPED_BIT,
-};
-
-/*
- * NOTE! Each of the iocb union members has the file pointer
- * as the first entry in their struct definition. So you can
- * access the file pointer through any of the sub-structs,
- * or directly as just 'file' in this struct.
- */
-struct io_kiocb {
- union {
- struct file *file;
- struct io_rw rw;
- struct io_poll_iocb poll;
- struct io_poll_update poll_update;
- struct io_accept accept;
- struct io_sync sync;
- struct io_cancel cancel;
- struct io_timeout timeout;
- struct io_timeout_rem timeout_rem;
- struct io_connect connect;
- struct io_sr_msg sr_msg;
- struct io_open open;
- struct io_close close;
- struct io_rsrc_update rsrc_update;
- struct io_fadvise fadvise;
- struct io_madvise madvise;
- struct io_epoll epoll;
- struct io_splice splice;
- struct io_provide_buf pbuf;
- struct io_statx statx;
- struct io_shutdown shutdown;
- struct io_rename rename;
- struct io_unlink unlink;
- struct io_mkdir mkdir;
- struct io_symlink symlink;
- struct io_hardlink hardlink;
- struct io_msg msg;
- struct io_xattr xattr;
- struct io_socket sock;
- struct io_uring_cmd uring_cmd;
- };
-
- u8 opcode;
- /* polled IO has completed */
- u8 iopoll_completed;
- /*
- * Can be either a fixed buffer index, or used with provided buffers.
- * For the latter, before issue it points to the buffer group ID,
- * and after selection it points to the buffer ID itself.
- */
- u16 buf_index;
- unsigned int flags;
-
- struct io_cqe cqe;
-
- struct io_ring_ctx *ctx;
- struct task_struct *task;
-
- struct io_rsrc_node *rsrc_node;
-
- union {
- /* store used ubuf, so we can prevent reloading */
- struct io_mapped_ubuf *imu;
-
- /* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */
- struct io_buffer *kbuf;
-
- /*
- * stores buffer ID for ring provided buffers, valid IFF
- * REQ_F_BUFFER_RING is set.
- */
- struct io_buffer_list *buf_list;
- };
-
- union {
- /* used by request caches, completion batching and iopoll */
- struct io_wq_work_node comp_list;
- /* cache ->apoll->events */
- __poll_t apoll_events;
- };
- atomic_t refs;
- atomic_t poll_refs;
- struct io_task_work io_task_work;
- /* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */
- union {
- struct hlist_node hash_node;
- struct {
- u64 extra1;
- u64 extra2;
- };
- };
- /* internal polling, see IORING_FEAT_FAST_POLL */
- struct async_poll *apoll;
- /* opcode allocated if it needs to store data for async defer */
- void *async_data;
- /* linked requests, IFF REQ_F_HARDLINK or REQ_F_LINK are set */
- struct io_kiocb *link;
- /* custom credentials, valid IFF REQ_F_CREDS is set */
- const struct cred *creds;
- struct io_wq_work work;
-};
-
-struct io_tctx_node {
- struct list_head ctx_node;
- struct task_struct *task;
- struct io_ring_ctx *ctx;
-};
-
-struct io_defer_entry {
- struct list_head list;
- struct io_kiocb *req;
- u32 seq;
-};
-
-struct io_cancel_data {
- struct io_ring_ctx *ctx;
- union {
- u64 data;
- struct file *file;
- };
- u32 flags;
- int seq;
-};
-
-/*
- * The URING_CMD payload starts at 'cmd' in the first sqe, and continues into
- * the following sqe if SQE128 is used.
- */
-#define uring_cmd_pdu_size(is_sqe128) \
- ((1 + !!(is_sqe128)) * sizeof(struct io_uring_sqe) - \
- offsetof(struct io_uring_sqe, cmd))
-
-struct io_op_def {
- /* needs req->file assigned */
- unsigned needs_file : 1;
- /* should block plug */
- unsigned plug : 1;
- /* hash wq insertion if file is a regular file */
- unsigned hash_reg_file : 1;
- /* unbound wq insertion if file is a non-regular file */
- unsigned unbound_nonreg_file : 1;
- /* set if opcode supports polled "wait" */
- unsigned pollin : 1;
- unsigned pollout : 1;
- unsigned poll_exclusive : 1;
- /* op supports buffer selection */
- unsigned buffer_select : 1;
- /* do prep async if is going to be punted */
- unsigned needs_async_setup : 1;
- /* opcode is not supported by this kernel */
- unsigned not_supported : 1;
- /* skip auditing */
- unsigned audit_skip : 1;
- /* supports ioprio */
- unsigned ioprio : 1;
- /* supports iopoll */
- unsigned iopoll : 1;
- /* size of async data needed, if any */
- unsigned short async_size;
-};
-
-static const struct io_op_def io_op_defs[] = {
- [IORING_OP_NOP] = {
- .audit_skip = 1,
- .iopoll = 1,
- },
- [IORING_OP_READV] = {
- .needs_file = 1,
- .unbound_nonreg_file = 1,
- .pollin = 1,
- .buffer_select = 1,
- .needs_async_setup = 1,
- .plug = 1,
- .audit_skip = 1,
- .ioprio = 1,
- .iopoll = 1,
- .async_size = sizeof(struct io_async_rw),
- },
- [IORING_OP_WRITEV] = {
- .needs_file = 1,
- .hash_reg_file = 1,
- .unbound_nonreg_file = 1,
- .pollout = 1,
- .needs_async_setup = 1,
- .plug = 1,
- .audit_skip = 1,
- .ioprio = 1,
- .iopoll = 1,
- .async_size = sizeof(struct io_async_rw),
- },
- [IORING_OP_FSYNC] = {
- .needs_file = 1,
- .audit_skip = 1,
- },
- [IORING_OP_READ_FIXED] = {
- .needs_file = 1,
- .unbound_nonreg_file = 1,
- .pollin = 1,
- .plug = 1,
- .audit_skip = 1,
- .ioprio = 1,
- .iopoll = 1,
- .async_size = sizeof(struct io_async_rw),
- },
- [IORING_OP_WRITE_FIXED] = {
- .needs_file = 1,
- .hash_reg_file = 1,
- .unbound_nonreg_file = 1,
- .pollout = 1,
- .plug = 1,
- .audit_skip = 1,
- .ioprio = 1,
- .iopoll = 1,
- .async_size = sizeof(struct io_async_rw),
- },
- [IORING_OP_POLL_ADD] = {
- .needs_file = 1,
- .unbound_nonreg_file = 1,
- .audit_skip = 1,
- },
- [IORING_OP_POLL_REMOVE] = {
- .audit_skip = 1,
- },
- [IORING_OP_SYNC_FILE_RANGE] = {
- .needs_file = 1,
- .audit_skip = 1,
- },
- [IORING_OP_SENDMSG] = {
- .needs_file = 1,
- .unbound_nonreg_file = 1,
- .pollout = 1,
- .needs_async_setup = 1,
- .ioprio = 1,
- .async_size = sizeof(struct io_async_msghdr),
- },
- [IORING_OP_RECVMSG] = {
- .needs_file = 1,
- .unbound_nonreg_file = 1,
- .pollin = 1,
- .buffer_select = 1,
- .needs_async_setup = 1,
- .ioprio = 1,
- .async_size = sizeof(struct io_async_msghdr),
- },
- [IORING_OP_TIMEOUT] = {
- .audit_skip = 1,
- .async_size = sizeof(struct io_timeout_data),
- },
- [IORING_OP_TIMEOUT_REMOVE] = {
- /* used by timeout updates' prep() */
- .audit_skip = 1,
- },
- [IORING_OP_ACCEPT] = {
- .needs_file = 1,
- .unbound_nonreg_file = 1,
- .pollin = 1,
- .poll_exclusive = 1,
- .ioprio = 1, /* used for flags */
- },
- [IORING_OP_ASYNC_CANCEL] = {
- .audit_skip = 1,
- },
- [IORING_OP_LINK_TIMEOUT] = {
- .audit_skip = 1,
- .async_size = sizeof(struct io_timeout_data),
- },
- [IORING_OP_CONNECT] = {
- .needs_file = 1,
- .unbound_nonreg_file = 1,
- .pollout = 1,
- .needs_async_setup = 1,
- .async_size = sizeof(struct io_async_connect),
- },
- [IORING_OP_FALLOCATE] = {
- .needs_file = 1,
- },
- [IORING_OP_OPENAT] = {},
- [IORING_OP_CLOSE] = {},
- [IORING_OP_FILES_UPDATE] = {
- .audit_skip = 1,
- .iopoll = 1,
- },
- [IORING_OP_STATX] = {
- .audit_skip = 1,
- },
- [IORING_OP_READ] = {
- .needs_file = 1,
- .unbound_nonreg_file = 1,
- .pollin = 1,
- .buffer_select = 1,
- .plug = 1,
- .audit_skip = 1,
- .ioprio = 1,
- .iopoll = 1,
- .async_size = sizeof(struct io_async_rw),
- },
- [IORING_OP_WRITE] = {
- .needs_file = 1,
- .hash_reg_file = 1,
- .unbound_nonreg_file = 1,
- .pollout = 1,
- .plug = 1,
- .audit_skip = 1,
- .ioprio = 1,
- .iopoll = 1,
- .async_size = sizeof(struct io_async_rw),
- },
- [IORING_OP_FADVISE] = {
- .needs_file = 1,
- .audit_skip = 1,
- },
- [IORING_OP_MADVISE] = {},
- [IORING_OP_SEND] = {
- .needs_file = 1,
- .unbound_nonreg_file = 1,
- .pollout = 1,
- .audit_skip = 1,
- .ioprio = 1,
- },
- [IORING_OP_RECV] = {
- .needs_file = 1,
- .unbound_nonreg_file = 1,
- .pollin = 1,
- .buffer_select = 1,
- .audit_skip = 1,
- .ioprio = 1,
- },
- [IORING_OP_OPENAT2] = {
- },
- [IORING_OP_EPOLL_CTL] = {
- .unbound_nonreg_file = 1,
- .audit_skip = 1,
- },
- [IORING_OP_SPLICE] = {
- .needs_file = 1,
- .hash_reg_file = 1,
- .unbound_nonreg_file = 1,
- .audit_skip = 1,
- },
- [IORING_OP_PROVIDE_BUFFERS] = {
- .audit_skip = 1,
- .iopoll = 1,
- },
- [IORING_OP_REMOVE_BUFFERS] = {
- .audit_skip = 1,
- .iopoll = 1,
- },
- [IORING_OP_TEE] = {
- .needs_file = 1,
- .hash_reg_file = 1,
- .unbound_nonreg_file = 1,
- .audit_skip = 1,
- },
- [IORING_OP_SHUTDOWN] = {
- .needs_file = 1,
- },
- [IORING_OP_RENAMEAT] = {},
- [IORING_OP_UNLINKAT] = {},
- [IORING_OP_MKDIRAT] = {},
- [IORING_OP_SYMLINKAT] = {},
- [IORING_OP_LINKAT] = {},
- [IORING_OP_MSG_RING] = {
- .needs_file = 1,
- .iopoll = 1,
- },
- [IORING_OP_FSETXATTR] = {
- .needs_file = 1
- },
- [IORING_OP_SETXATTR] = {},
- [IORING_OP_FGETXATTR] = {
- .needs_file = 1
- },
- [IORING_OP_GETXATTR] = {},
- [IORING_OP_SOCKET] = {
- .audit_skip = 1,
- },
- [IORING_OP_URING_CMD] = {
- .needs_file = 1,
- .plug = 1,
- .needs_async_setup = 1,
- .async_size = uring_cmd_pdu_size(1),
- },
-};
-
-/* requests with any of those set should undergo io_disarm_next() */
-#define IO_DISARM_MASK (REQ_F_ARM_LTIMEOUT | REQ_F_LINK_TIMEOUT | REQ_F_FAIL)
-#define IO_REQ_LINK_FLAGS (REQ_F_LINK | REQ_F_HARDLINK)
-
-static bool io_disarm_next(struct io_kiocb *req);
-static void io_uring_del_tctx_node(unsigned long index);
-static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
- struct task_struct *task,
- bool cancel_all);
-static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd);
-
-static void __io_req_complete_post(struct io_kiocb *req, s32 res, u32 cflags);
-static void io_dismantle_req(struct io_kiocb *req);
-static void io_queue_linked_timeout(struct io_kiocb *req);
-static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type,
- struct io_uring_rsrc_update2 *up,
- unsigned nr_args);
-static void io_clean_op(struct io_kiocb *req);
-static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
- unsigned issue_flags);
-static struct file *io_file_get_normal(struct io_kiocb *req, int fd);
-static void io_queue_sqe(struct io_kiocb *req);
-static void io_rsrc_put_work(struct work_struct *work);
-
-static void io_req_task_queue(struct io_kiocb *req);
-static void __io_submit_flush_completions(struct io_ring_ctx *ctx);
-static int io_req_prep_async(struct io_kiocb *req);
-
-static int io_install_fixed_file(struct io_kiocb *req, struct file *file,
- unsigned int issue_flags, u32 slot_index);
-static int __io_close_fixed(struct io_kiocb *req, unsigned int issue_flags,
- unsigned int offset);
-static inline int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags);
-
-static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer);
-static void io_eventfd_signal(struct io_ring_ctx *ctx);
-static void io_req_tw_post_queue(struct io_kiocb *req, s32 res, u32 cflags);
-
-static struct kmem_cache *req_cachep;
-
-static const struct file_operations io_uring_fops;
-
-const char *io_uring_get_opcode(u8 opcode)
-{
- switch ((enum io_uring_op)opcode) {
- case IORING_OP_NOP:
- return "NOP";
- case IORING_OP_READV:
- return "READV";
- case IORING_OP_WRITEV:
- return "WRITEV";
- case IORING_OP_FSYNC:
- return "FSYNC";
- case IORING_OP_READ_FIXED:
- return "READ_FIXED";
- case IORING_OP_WRITE_FIXED:
- return "WRITE_FIXED";
- case IORING_OP_POLL_ADD:
- return "POLL_ADD";
- case IORING_OP_POLL_REMOVE:
- return "POLL_REMOVE";
- case IORING_OP_SYNC_FILE_RANGE:
- return "SYNC_FILE_RANGE";
- case IORING_OP_SENDMSG:
- return "SENDMSG";
- case IORING_OP_RECVMSG:
- return "RECVMSG";
- case IORING_OP_TIMEOUT:
- return "TIMEOUT";
- case IORING_OP_TIMEOUT_REMOVE:
- return "TIMEOUT_REMOVE";
- case IORING_OP_ACCEPT:
- return "ACCEPT";
- case IORING_OP_ASYNC_CANCEL:
- return "ASYNC_CANCEL";
- case IORING_OP_LINK_TIMEOUT:
- return "LINK_TIMEOUT";
- case IORING_OP_CONNECT:
- return "CONNECT";
- case IORING_OP_FALLOCATE:
- return "FALLOCATE";
- case IORING_OP_OPENAT:
- return "OPENAT";
- case IORING_OP_CLOSE:
- return "CLOSE";
- case IORING_OP_FILES_UPDATE:
- return "FILES_UPDATE";
- case IORING_OP_STATX:
- return "STATX";
- case IORING_OP_READ:
- return "READ";
- case IORING_OP_WRITE:
- return "WRITE";
- case IORING_OP_FADVISE:
- return "FADVISE";
- case IORING_OP_MADVISE:
- return "MADVISE";
- case IORING_OP_SEND:
- return "SEND";
- case IORING_OP_RECV:
- return "RECV";
- case IORING_OP_OPENAT2:
- return "OPENAT2";
- case IORING_OP_EPOLL_CTL:
- return "EPOLL_CTL";
- case IORING_OP_SPLICE:
- return "SPLICE";
- case IORING_OP_PROVIDE_BUFFERS:
- return "PROVIDE_BUFFERS";
- case IORING_OP_REMOVE_BUFFERS:
- return "REMOVE_BUFFERS";
- case IORING_OP_TEE:
- return "TEE";
- case IORING_OP_SHUTDOWN:
- return "SHUTDOWN";
- case IORING_OP_RENAMEAT:
- return "RENAMEAT";
- case IORING_OP_UNLINKAT:
- return "UNLINKAT";
- case IORING_OP_MKDIRAT:
- return "MKDIRAT";
- case IORING_OP_SYMLINKAT:
- return "SYMLINKAT";
- case IORING_OP_LINKAT:
- return "LINKAT";
- case IORING_OP_MSG_RING:
- return "MSG_RING";
- case IORING_OP_FSETXATTR:
- return "FSETXATTR";
- case IORING_OP_SETXATTR:
- return "SETXATTR";
- case IORING_OP_FGETXATTR:
- return "FGETXATTR";
- case IORING_OP_GETXATTR:
- return "GETXATTR";
- case IORING_OP_SOCKET:
- return "SOCKET";
- case IORING_OP_URING_CMD:
- return "URING_CMD";
- case IORING_OP_LAST:
- return "INVALID";
- }
- return "INVALID";
-}
-
-struct sock *io_uring_get_socket(struct file *file)
-{
-#if defined(CONFIG_UNIX)
- if (file->f_op == &io_uring_fops) {
- struct io_ring_ctx *ctx = file->private_data;
-
- return ctx->ring_sock->sk;
- }
-#endif
- return NULL;
-}
-EXPORT_SYMBOL(io_uring_get_socket);
-
-#if defined(CONFIG_UNIX)
-static inline bool io_file_need_scm(struct file *filp)
-{
-#if defined(IO_URING_SCM_ALL)
- return true;
-#else
- return !!unix_get_socket(filp);
-#endif
-}
-#else
-static inline bool io_file_need_scm(struct file *filp)
-{
- return false;
-}
-#endif
-
-static void io_ring_submit_unlock(struct io_ring_ctx *ctx, unsigned issue_flags)
-{
- lockdep_assert_held(&ctx->uring_lock);
- if (issue_flags & IO_URING_F_UNLOCKED)
- mutex_unlock(&ctx->uring_lock);
-}
-
-static void io_ring_submit_lock(struct io_ring_ctx *ctx, unsigned issue_flags)
-{
- /*
- * "Normal" inline submissions always hold the uring_lock, since we
- * grab it from the system call. Same is true for the SQPOLL offload.
- * The only exception is when we've detached the request and issue it
- * from an async worker thread, grab the lock for that case.
- */
- if (issue_flags & IO_URING_F_UNLOCKED)
- mutex_lock(&ctx->uring_lock);
- lockdep_assert_held(&ctx->uring_lock);
-}
-
-static inline void io_tw_lock(struct io_ring_ctx *ctx, bool *locked)
-{
- if (!*locked) {
- mutex_lock(&ctx->uring_lock);
- *locked = true;
- }
-}
-
-#define io_for_each_link(pos, head) \
- for (pos = (head); pos; pos = pos->link)
-
-/*
- * Shamelessly stolen from the mm implementation of page reference checking,
- * see commit f958d7b528b1 for details.
- */
-#define req_ref_zero_or_close_to_overflow(req) \
- ((unsigned int) atomic_read(&(req->refs)) + 127u <= 127u)
-
-static inline bool req_ref_inc_not_zero(struct io_kiocb *req)
-{
- WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT));
- return atomic_inc_not_zero(&req->refs);
-}
-
-static inline bool req_ref_put_and_test(struct io_kiocb *req)
-{
- if (likely(!(req->flags & REQ_F_REFCOUNT)))
- return true;
-
- WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req));
- return atomic_dec_and_test(&req->refs);
-}
-
-static inline void req_ref_get(struct io_kiocb *req)
-{
- WARN_ON_ONCE(!(req->flags & REQ_F_REFCOUNT));
- WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req));
- atomic_inc(&req->refs);
-}
-
-static inline void io_submit_flush_completions(struct io_ring_ctx *ctx)
-{
- if (!wq_list_empty(&ctx->submit_state.compl_reqs))
- __io_submit_flush_completions(ctx);
-}
-
-static inline void __io_req_set_refcount(struct io_kiocb *req, int nr)
-{
- if (!(req->flags & REQ_F_REFCOUNT)) {
- req->flags |= REQ_F_REFCOUNT;
- atomic_set(&req->refs, nr);
- }
-}
-
-static inline void io_req_set_refcount(struct io_kiocb *req)
-{
- __io_req_set_refcount(req, 1);
-}
-
-#define IO_RSRC_REF_BATCH 100
-
-static void io_rsrc_put_node(struct io_rsrc_node *node, int nr)
-{
- percpu_ref_put_many(&node->refs, nr);
-}
-
-static inline void io_req_put_rsrc_locked(struct io_kiocb *req,
- struct io_ring_ctx *ctx)
- __must_hold(&ctx->uring_lock)
-{
- struct io_rsrc_node *node = req->rsrc_node;
-
- if (node) {
- if (node == ctx->rsrc_node)
- ctx->rsrc_cached_refs++;
- else
- io_rsrc_put_node(node, 1);
- }
-}
-
-static inline void io_req_put_rsrc(struct io_kiocb *req)
-{
- if (req->rsrc_node)
- io_rsrc_put_node(req->rsrc_node, 1);
-}
-
-static __cold void io_rsrc_refs_drop(struct io_ring_ctx *ctx)
- __must_hold(&ctx->uring_lock)
-{
- if (ctx->rsrc_cached_refs) {
- io_rsrc_put_node(ctx->rsrc_node, ctx->rsrc_cached_refs);
- ctx->rsrc_cached_refs = 0;
- }
-}
-
-static void io_rsrc_refs_refill(struct io_ring_ctx *ctx)
- __must_hold(&ctx->uring_lock)
-{
- ctx->rsrc_cached_refs += IO_RSRC_REF_BATCH;
- percpu_ref_get_many(&ctx->rsrc_node->refs, IO_RSRC_REF_BATCH);
-}
-
-static inline void io_req_set_rsrc_node(struct io_kiocb *req,
- struct io_ring_ctx *ctx,
- unsigned int issue_flags)
-{
- if (!req->rsrc_node) {
- req->rsrc_node = ctx->rsrc_node;
-
- if (!(issue_flags & IO_URING_F_UNLOCKED)) {
- lockdep_assert_held(&ctx->uring_lock);
- ctx->rsrc_cached_refs--;
- if (unlikely(ctx->rsrc_cached_refs < 0))
- io_rsrc_refs_refill(ctx);
- } else {
- percpu_ref_get(&req->rsrc_node->refs);
- }
- }
-}
-
-static unsigned int __io_put_kbuf(struct io_kiocb *req, struct list_head *list)
-{
- if (req->flags & REQ_F_BUFFER_RING) {
- if (req->buf_list)
- req->buf_list->head++;
- req->flags &= ~REQ_F_BUFFER_RING;
- } else {
- list_add(&req->kbuf->list, list);
- req->flags &= ~REQ_F_BUFFER_SELECTED;
- }
-
- return IORING_CQE_F_BUFFER | (req->buf_index << IORING_CQE_BUFFER_SHIFT);
-}
-
-static inline unsigned int io_put_kbuf_comp(struct io_kiocb *req)
-{
- lockdep_assert_held(&req->ctx->completion_lock);
-
- if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)))
- return 0;
- return __io_put_kbuf(req, &req->ctx->io_buffers_comp);
-}
-
-static inline unsigned int io_put_kbuf(struct io_kiocb *req,
- unsigned issue_flags)
-{
- unsigned int cflags;
-
- if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)))
- return 0;
-
- /*
- * We can add this buffer back to two lists:
- *
- * 1) The io_buffers_cache list. This one is protected by the
- * ctx->uring_lock. If we already hold this lock, add back to this
- * list as we can grab it from issue as well.
- * 2) The io_buffers_comp list. This one is protected by the
- * ctx->completion_lock.
- *
- * We migrate buffers from the comp_list to the issue cache list
- * when we need one.
- */
- if (req->flags & REQ_F_BUFFER_RING) {
- /* no buffers to recycle for this case */
- cflags = __io_put_kbuf(req, NULL);
- } else if (issue_flags & IO_URING_F_UNLOCKED) {
- struct io_ring_ctx *ctx = req->ctx;
-
- spin_lock(&ctx->completion_lock);
- cflags = __io_put_kbuf(req, &ctx->io_buffers_comp);
- spin_unlock(&ctx->completion_lock);
- } else {
- lockdep_assert_held(&req->ctx->uring_lock);
-
- cflags = __io_put_kbuf(req, &req->ctx->io_buffers_cache);
- }
-
- return cflags;
-}
-
-static struct io_buffer_list *io_buffer_get_list(struct io_ring_ctx *ctx,
- unsigned int bgid)
-{
- if (ctx->io_bl && bgid < BGID_ARRAY)
- return &ctx->io_bl[bgid];
-
- return xa_load(&ctx->io_bl_xa, bgid);
-}
-
-static void io_kbuf_recycle(struct io_kiocb *req, unsigned issue_flags)
-{
- struct io_ring_ctx *ctx = req->ctx;
- struct io_buffer_list *bl;
- struct io_buffer *buf;
-
- if (!(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)))
- return;
- /*
- * For legacy provided buffer mode, don't recycle if we already did
- * IO to this buffer. For ring-mapped provided buffer mode, we should
- * increment ring->head to explicitly monopolize the buffer to avoid
- * multiple use.
- */
- if ((req->flags & REQ_F_BUFFER_SELECTED) &&
- (req->flags & REQ_F_PARTIAL_IO))
- return;
-
- /*
- * We don't need to recycle for REQ_F_BUFFER_RING, we can just clear
- * the flag and hence ensure that bl->head doesn't get incremented.
- * If the tail has already been incremented, hang on to it.
- */
- if (req->flags & REQ_F_BUFFER_RING) {
- if (req->buf_list) {
- if (req->flags & REQ_F_PARTIAL_IO) {
- req->buf_list->head++;
- req->buf_list = NULL;
- } else {
- req->buf_index = req->buf_list->bgid;
- req->flags &= ~REQ_F_BUFFER_RING;
- }
- }
- return;
- }
-
- io_ring_submit_lock(ctx, issue_flags);
-
- buf = req->kbuf;
- bl = io_buffer_get_list(ctx, buf->bgid);
- list_add(&buf->list, &bl->buf_list);
- req->flags &= ~REQ_F_BUFFER_SELECTED;
- req->buf_index = buf->bgid;
-
- io_ring_submit_unlock(ctx, issue_flags);
-}
-
-static bool io_match_task(struct io_kiocb *head, struct task_struct *task,
- bool cancel_all)
- __must_hold(&req->ctx->timeout_lock)
-{
- struct io_kiocb *req;
-
- if (task && head->task != task)
- return false;
- if (cancel_all)
- return true;
-
- io_for_each_link(req, head) {
- if (req->flags & REQ_F_INFLIGHT)
- return true;
- }
- return false;
-}
-
-static bool io_match_linked(struct io_kiocb *head)
-{
- struct io_kiocb *req;
-
- io_for_each_link(req, head) {
- if (req->flags & REQ_F_INFLIGHT)
- return true;
- }
- return false;
-}
-
-/*
- * As io_match_task() but protected against racing with linked timeouts.
- * User must not hold timeout_lock.
- */
-static bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task,
- bool cancel_all)
-{
- bool matched;
-
- if (task && head->task != task)
- return false;
- if (cancel_all)
- return true;
-
- if (head->flags & REQ_F_LINK_TIMEOUT) {
- struct io_ring_ctx *ctx = head->ctx;
-
- /* protect against races with linked timeouts */
- spin_lock_irq(&ctx->timeout_lock);
- matched = io_match_linked(head);
- spin_unlock_irq(&ctx->timeout_lock);
- } else {
- matched = io_match_linked(head);
- }
- return matched;
-}
-
-static inline bool req_has_async_data(struct io_kiocb *req)
-{
- return req->flags & REQ_F_ASYNC_DATA;
-}
-
-static inline void req_set_fail(struct io_kiocb *req)
-{
- req->flags |= REQ_F_FAIL;
- if (req->flags & REQ_F_CQE_SKIP) {
- req->flags &= ~REQ_F_CQE_SKIP;
- req->flags |= REQ_F_SKIP_LINK_CQES;
- }
-}
-
-static inline void req_fail_link_node(struct io_kiocb *req, int res)
-{
- req_set_fail(req);
- req->cqe.res = res;
-}
-
-static inline void io_req_add_to_cache(struct io_kiocb *req, struct io_ring_ctx *ctx)
-{
- wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list);
-}
-
-static __cold void io_ring_ctx_ref_free(struct percpu_ref *ref)
-{
- struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs);
-
- complete(&ctx->ref_comp);
-}
-
-static inline bool io_is_timeout_noseq(struct io_kiocb *req)
-{
- return !req->timeout.off;
-}
-
-static __cold void io_fallback_req_func(struct work_struct *work)
-{
- struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx,
- fallback_work.work);
- struct llist_node *node = llist_del_all(&ctx->fallback_llist);
- struct io_kiocb *req, *tmp;
- bool locked = false;
-
- percpu_ref_get(&ctx->refs);
- llist_for_each_entry_safe(req, tmp, node, io_task_work.fallback_node)
- req->io_task_work.func(req, &locked);
-
- if (locked) {
- io_submit_flush_completions(ctx);
- mutex_unlock(&ctx->uring_lock);
- }
- percpu_ref_put(&ctx->refs);
-}
-
-static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
-{
- struct io_ring_ctx *ctx;
- int hash_bits;
-
- ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
- if (!ctx)
- return NULL;
-
- xa_init(&ctx->io_bl_xa);
-
- /*
- * Use 5 bits less than the max cq entries, that should give us around
- * 32 entries per hash list if totally full and uniformly spread.
- */
- hash_bits = ilog2(p->cq_entries);
- hash_bits -= 5;
- if (hash_bits <= 0)
- hash_bits = 1;
- ctx->cancel_hash_bits = hash_bits;
- ctx->cancel_hash = kmalloc((1U << hash_bits) * sizeof(struct hlist_head),
- GFP_KERNEL);
- if (!ctx->cancel_hash)
- goto err;
- __hash_init(ctx->cancel_hash, 1U << hash_bits);
-
- ctx->dummy_ubuf = kzalloc(sizeof(*ctx->dummy_ubuf), GFP_KERNEL);
- if (!ctx->dummy_ubuf)
- goto err;
- /* set invalid range, so io_import_fixed() fails meeting it */
- ctx->dummy_ubuf->ubuf = -1UL;
-
- if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free,
- PERCPU_REF_ALLOW_REINIT, GFP_KERNEL))
- goto err;
-
- ctx->flags = p->flags;
- init_waitqueue_head(&ctx->sqo_sq_wait);
- INIT_LIST_HEAD(&ctx->sqd_list);
- INIT_LIST_HEAD(&ctx->cq_overflow_list);
- INIT_LIST_HEAD(&ctx->io_buffers_cache);
- INIT_LIST_HEAD(&ctx->apoll_cache);
- init_completion(&ctx->ref_comp);
- xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1);
- mutex_init(&ctx->uring_lock);
- init_waitqueue_head(&ctx->cq_wait);
- spin_lock_init(&ctx->completion_lock);
- spin_lock_init(&ctx->timeout_lock);
- INIT_WQ_LIST(&ctx->iopoll_list);
- INIT_LIST_HEAD(&ctx->io_buffers_pages);
- INIT_LIST_HEAD(&ctx->io_buffers_comp);
- INIT_LIST_HEAD(&ctx->defer_list);
- INIT_LIST_HEAD(&ctx->timeout_list);
- INIT_LIST_HEAD(&ctx->ltimeout_list);
- spin_lock_init(&ctx->rsrc_ref_lock);
- INIT_LIST_HEAD(&ctx->rsrc_ref_list);
- INIT_DELAYED_WORK(&ctx->rsrc_put_work, io_rsrc_put_work);
- init_llist_head(&ctx->rsrc_put_llist);
- INIT_LIST_HEAD(&ctx->tctx_list);
- ctx->submit_state.free_list.next = NULL;
- INIT_WQ_LIST(&ctx->locked_free_list);
- INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func);
- INIT_WQ_LIST(&ctx->submit_state.compl_reqs);
- return ctx;
-err:
- kfree(ctx->dummy_ubuf);
- kfree(ctx->cancel_hash);
- kfree(ctx->io_bl);
- xa_destroy(&ctx->io_bl_xa);
- kfree(ctx);
- return NULL;
-}
-
-static void io_account_cq_overflow(struct io_ring_ctx *ctx)
-{
- struct io_rings *r = ctx->rings;
-
- WRITE_ONCE(r->cq_overflow, READ_ONCE(r->cq_overflow) + 1);
- ctx->cq_extra--;
-}
-
-static bool req_need_defer(struct io_kiocb *req, u32 seq)
-{
- if (unlikely(req->flags & REQ_F_IO_DRAIN)) {
- struct io_ring_ctx *ctx = req->ctx;
-
- return seq + READ_ONCE(ctx->cq_extra) != ctx->cached_cq_tail;
- }
-
- return false;
-}
-
-static inline bool io_req_ffs_set(struct io_kiocb *req)
-{
- return req->flags & REQ_F_FIXED_FILE;
-}
-
-static inline void io_req_track_inflight(struct io_kiocb *req)
-{
- if (!(req->flags & REQ_F_INFLIGHT)) {
- req->flags |= REQ_F_INFLIGHT;
- atomic_inc(&req->task->io_uring->inflight_tracked);
- }
-}
-
-static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req)
-{
- if (WARN_ON_ONCE(!req->link))
- return NULL;
-
- req->flags &= ~REQ_F_ARM_LTIMEOUT;
- req->flags |= REQ_F_LINK_TIMEOUT;
-
- /* linked timeouts should have two refs once prep'ed */
- io_req_set_refcount(req);
- __io_req_set_refcount(req->link, 2);
- return req->link;
-}
-
-static inline struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req)
-{
- if (likely(!(req->flags & REQ_F_ARM_LTIMEOUT)))
- return NULL;
- return __io_prep_linked_timeout(req);
-}
-
-static noinline void __io_arm_ltimeout(struct io_kiocb *req)
-{
- io_queue_linked_timeout(__io_prep_linked_timeout(req));
-}
-
-static inline void io_arm_ltimeout(struct io_kiocb *req)
-{
- if (unlikely(req->flags & REQ_F_ARM_LTIMEOUT))
- __io_arm_ltimeout(req);
-}
-
-static void io_prep_async_work(struct io_kiocb *req)
-{
- const struct io_op_def *def = &io_op_defs[req->opcode];
- struct io_ring_ctx *ctx = req->ctx;
-
- if (!(req->flags & REQ_F_CREDS)) {
- req->flags |= REQ_F_CREDS;
- req->creds = get_current_cred();
- }
-
- req->work.list.next = NULL;
- req->work.flags = 0;
- req->work.cancel_seq = atomic_read(&ctx->cancel_seq);
- if (req->flags & REQ_F_FORCE_ASYNC)
- req->work.flags |= IO_WQ_WORK_CONCURRENT;
-
- if (req->flags & REQ_F_ISREG) {
- if (def->hash_reg_file || (ctx->flags & IORING_SETUP_IOPOLL))
- io_wq_hash_work(&req->work, file_inode(req->file));
- } else if (!req->file || !S_ISBLK(file_inode(req->file)->i_mode)) {
- if (def->unbound_nonreg_file)
- req->work.flags |= IO_WQ_WORK_UNBOUND;
- }
-}
-
-static void io_prep_async_link(struct io_kiocb *req)
-{
- struct io_kiocb *cur;
-
- if (req->flags & REQ_F_LINK_TIMEOUT) {
- struct io_ring_ctx *ctx = req->ctx;
-
- spin_lock_irq(&ctx->timeout_lock);
- io_for_each_link(cur, req)
- io_prep_async_work(cur);
- spin_unlock_irq(&ctx->timeout_lock);
- } else {
- io_for_each_link(cur, req)
- io_prep_async_work(cur);
- }
-}
-
-static inline void io_req_add_compl_list(struct io_kiocb *req)
-{
- struct io_submit_state *state = &req->ctx->submit_state;
-
- if (!(req->flags & REQ_F_CQE_SKIP))
- state->flush_cqes = true;
- wq_list_add_tail(&req->comp_list, &state->compl_reqs);
-}
-
-static void io_queue_iowq(struct io_kiocb *req, bool *dont_use)
-{
- struct io_kiocb *link = io_prep_linked_timeout(req);
- struct io_uring_task *tctx = req->task->io_uring;
-
- BUG_ON(!tctx);
- BUG_ON(!tctx->io_wq);
-
- /* init ->work of the whole link before punting */
- io_prep_async_link(req);
-
- /*
- * Not expected to happen, but if we do have a bug where this _can_
- * happen, catch it here and ensure the request is marked as
- * canceled. That will make io-wq go through the usual work cancel
- * procedure rather than attempt to run this request (or create a new
- * worker for it).
- */
- if (WARN_ON_ONCE(!same_thread_group(req->task, current)))
- req->work.flags |= IO_WQ_WORK_CANCEL;
-
- trace_io_uring_queue_async_work(req->ctx, req, req->cqe.user_data,
- req->opcode, req->flags, &req->work,
- io_wq_is_hashed(&req->work));
- io_wq_enqueue(tctx->io_wq, &req->work);
- if (link)
- io_queue_linked_timeout(link);
-}
-
-static void io_kill_timeout(struct io_kiocb *req, int status)
- __must_hold(&req->ctx->completion_lock)
- __must_hold(&req->ctx->timeout_lock)
-{
- struct io_timeout_data *io = req->async_data;
-
- if (hrtimer_try_to_cancel(&io->timer) != -1) {
- if (status)
- req_set_fail(req);
- atomic_set(&req->ctx->cq_timeouts,
- atomic_read(&req->ctx->cq_timeouts) + 1);
- list_del_init(&req->timeout.list);
- io_req_tw_post_queue(req, status, 0);
- }
-}
-
-static __cold void io_queue_deferred(struct io_ring_ctx *ctx)
-{
- while (!list_empty(&ctx->defer_list)) {
- struct io_defer_entry *de = list_first_entry(&ctx->defer_list,
- struct io_defer_entry, list);
-
- if (req_need_defer(de->req, de->seq))
- break;
- list_del_init(&de->list);
- io_req_task_queue(de->req);
- kfree(de);
- }
-}
-
-static __cold void io_flush_timeouts(struct io_ring_ctx *ctx)
- __must_hold(&ctx->completion_lock)
-{
- u32 seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
- struct io_kiocb *req, *tmp;
-
- spin_lock_irq(&ctx->timeout_lock);
- list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) {
- u32 events_needed, events_got;
-
- if (io_is_timeout_noseq(req))
- break;
-
- /*
- * Since seq can easily wrap around over time, subtract
- * the last seq at which timeouts were flushed before comparing.
- * Assuming not more than 2^31-1 events have happened since,
- * these subtractions won't have wrapped, so we can check if
- * target is in [last_seq, current_seq] by comparing the two.
- */
- events_needed = req->timeout.target_seq - ctx->cq_last_tm_flush;
- events_got = seq - ctx->cq_last_tm_flush;
- if (events_got < events_needed)
- break;
-
- io_kill_timeout(req, 0);
- }
- ctx->cq_last_tm_flush = seq;
- spin_unlock_irq(&ctx->timeout_lock);
-}
-
-static inline void io_commit_cqring(struct io_ring_ctx *ctx)
-{
- /* order cqe stores with ring update */
- smp_store_release(&ctx->rings->cq.tail, ctx->cached_cq_tail);
-}
-
-static void __io_commit_cqring_flush(struct io_ring_ctx *ctx)
-{
- if (ctx->off_timeout_used || ctx->drain_active) {
- spin_lock(&ctx->completion_lock);
- if (ctx->off_timeout_used)
- io_flush_timeouts(ctx);
- if (ctx->drain_active)
- io_queue_deferred(ctx);
- io_commit_cqring(ctx);
- spin_unlock(&ctx->completion_lock);
- }
- if (ctx->has_evfd)
- io_eventfd_signal(ctx);
-}
-
-static inline bool io_sqring_full(struct io_ring_ctx *ctx)
-{
- struct io_rings *r = ctx->rings;
-
- return READ_ONCE(r->sq.tail) - ctx->cached_sq_head == ctx->sq_entries;
-}
-
-static inline unsigned int __io_cqring_events(struct io_ring_ctx *ctx)
-{
- return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head);
-}
-
-/*
- * writes to the cq entry need to come after reading head; the
- * control dependency is enough as we're using WRITE_ONCE to
- * fill the cq entry
- */
-static noinline struct io_uring_cqe *__io_get_cqe(struct io_ring_ctx *ctx)
-{
- struct io_rings *rings = ctx->rings;
- unsigned int off = ctx->cached_cq_tail & (ctx->cq_entries - 1);
- unsigned int shift = 0;
- unsigned int free, queued, len;
-
- if (ctx->flags & IORING_SETUP_CQE32)
- shift = 1;
-
- /* userspace may cheat modifying the tail, be safe and do min */
- queued = min(__io_cqring_events(ctx), ctx->cq_entries);
- free = ctx->cq_entries - queued;
- /* we need a contiguous range, limit based on the current array offset */
- len = min(free, ctx->cq_entries - off);
- if (!len)
- return NULL;
-
- ctx->cached_cq_tail++;
- ctx->cqe_cached = &rings->cqes[off];
- ctx->cqe_sentinel = ctx->cqe_cached + len;
- ctx->cqe_cached++;
- return &rings->cqes[off << shift];
-}
-
-static inline struct io_uring_cqe *io_get_cqe(struct io_ring_ctx *ctx)
-{
- if (likely(ctx->cqe_cached < ctx->cqe_sentinel)) {
- struct io_uring_cqe *cqe = ctx->cqe_cached;
-
- if (ctx->flags & IORING_SETUP_CQE32) {
- unsigned int off = ctx->cqe_cached - ctx->rings->cqes;
-
- cqe += off;
- }
-
- ctx->cached_cq_tail++;
- ctx->cqe_cached++;
- return cqe;
- }
-
- return __io_get_cqe(ctx);
-}
-
-static void io_eventfd_signal(struct io_ring_ctx *ctx)
-{
- struct io_ev_fd *ev_fd;
-
- rcu_read_lock();
- /*
- * rcu_dereference ctx->io_ev_fd once and use it for both for checking
- * and eventfd_signal
- */
- ev_fd = rcu_dereference(ctx->io_ev_fd);
-
- /*
- * Check again if ev_fd exists incase an io_eventfd_unregister call
- * completed between the NULL check of ctx->io_ev_fd at the start of
- * the function and rcu_read_lock.
- */
- if (unlikely(!ev_fd))
- goto out;
- if (READ_ONCE(ctx->rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED)
- goto out;
-
- if (!ev_fd->eventfd_async || io_wq_current_is_worker())
- eventfd_signal(ev_fd->cq_ev_fd, 1);
-out:
- rcu_read_unlock();
-}
-
-static inline void io_cqring_wake(struct io_ring_ctx *ctx)
-{
- /*
- * wake_up_all() may seem excessive, but io_wake_function() and
- * io_should_wake() handle the termination of the loop and only
- * wake as many waiters as we need to.
- */
- if (wq_has_sleeper(&ctx->cq_wait))
- wake_up_all(&ctx->cq_wait);
-}
-
-/*
- * This should only get called when at least one event has been posted.
- * Some applications rely on the eventfd notification count only changing
- * IFF a new CQE has been added to the CQ ring. There's no depedency on
- * 1:1 relationship between how many times this function is called (and
- * hence the eventfd count) and number of CQEs posted to the CQ ring.
- */
-static inline void io_cqring_ev_posted(struct io_ring_ctx *ctx)
-{
- if (unlikely(ctx->off_timeout_used || ctx->drain_active ||
- ctx->has_evfd))
- __io_commit_cqring_flush(ctx);
-
- io_cqring_wake(ctx);
-}
-
-static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx)
-{
- if (unlikely(ctx->off_timeout_used || ctx->drain_active ||
- ctx->has_evfd))
- __io_commit_cqring_flush(ctx);
-
- if (ctx->flags & IORING_SETUP_SQPOLL)
- io_cqring_wake(ctx);
-}
-
-/* Returns true if there are no backlogged entries after the flush */
-static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
-{
- bool all_flushed, posted;
- size_t cqe_size = sizeof(struct io_uring_cqe);
-
- if (!force && __io_cqring_events(ctx) == ctx->cq_entries)
- return false;
-
- if (ctx->flags & IORING_SETUP_CQE32)
- cqe_size <<= 1;
-
- posted = false;
- spin_lock(&ctx->completion_lock);
- while (!list_empty(&ctx->cq_overflow_list)) {
- struct io_uring_cqe *cqe = io_get_cqe(ctx);
- struct io_overflow_cqe *ocqe;
-
- if (!cqe && !force)
- break;
- ocqe = list_first_entry(&ctx->cq_overflow_list,
- struct io_overflow_cqe, list);
- if (cqe)
- memcpy(cqe, &ocqe->cqe, cqe_size);
- else
- io_account_cq_overflow(ctx);
-
- posted = true;
- list_del(&ocqe->list);
- kfree(ocqe);
- }
-
- all_flushed = list_empty(&ctx->cq_overflow_list);
- if (all_flushed) {
- clear_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq);
- atomic_andnot(IORING_SQ_CQ_OVERFLOW, &ctx->rings->sq_flags);
- }
-
- io_commit_cqring(ctx);
- spin_unlock(&ctx->completion_lock);
- if (posted)
- io_cqring_ev_posted(ctx);
- return all_flushed;
-}
-
-static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx)
-{
- bool ret = true;
-
- if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) {
- /* iopoll syncs against uring_lock, not completion_lock */
- if (ctx->flags & IORING_SETUP_IOPOLL)
- mutex_lock(&ctx->uring_lock);
- ret = __io_cqring_overflow_flush(ctx, false);
- if (ctx->flags & IORING_SETUP_IOPOLL)
- mutex_unlock(&ctx->uring_lock);
- }
-
- return ret;
-}
-
-static void __io_put_task(struct task_struct *task, int nr)
-{
- struct io_uring_task *tctx = task->io_uring;
-
- percpu_counter_sub(&tctx->inflight, nr);
- if (unlikely(atomic_read(&tctx->in_idle)))
- wake_up(&tctx->wait);
- put_task_struct_many(task, nr);
-}
-
-/* must to be called somewhat shortly after putting a request */
-static inline void io_put_task(struct task_struct *task, int nr)
-{
- if (likely(task == current))
- task->io_uring->cached_refs += nr;
- else
- __io_put_task(task, nr);
-}
-
-static void io_task_refs_refill(struct io_uring_task *tctx)
-{
- unsigned int refill = -tctx->cached_refs + IO_TCTX_REFS_CACHE_NR;
-
- percpu_counter_add(&tctx->inflight, refill);
- refcount_add(refill, &current->usage);
- tctx->cached_refs += refill;
-}
-
-static inline void io_get_task_refs(int nr)
-{
- struct io_uring_task *tctx = current->io_uring;
-
- tctx->cached_refs -= nr;
- if (unlikely(tctx->cached_refs < 0))
- io_task_refs_refill(tctx);
-}
-
-static __cold void io_uring_drop_tctx_refs(struct task_struct *task)
-{
- struct io_uring_task *tctx = task->io_uring;
- unsigned int refs = tctx->cached_refs;
-
- if (refs) {
- tctx->cached_refs = 0;
- percpu_counter_sub(&tctx->inflight, refs);
- put_task_struct_many(task, refs);
- }
-}
-
-static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data,
- s32 res, u32 cflags, u64 extra1,
- u64 extra2)
-{
- struct io_overflow_cqe *ocqe;
- size_t ocq_size = sizeof(struct io_overflow_cqe);
- bool is_cqe32 = (ctx->flags & IORING_SETUP_CQE32);
-
- if (is_cqe32)
- ocq_size += sizeof(struct io_uring_cqe);
-
- ocqe = kmalloc(ocq_size, GFP_ATOMIC | __GFP_ACCOUNT);
- trace_io_uring_cqe_overflow(ctx, user_data, res, cflags, ocqe);
- if (!ocqe) {
- /*
- * If we're in ring overflow flush mode, or in task cancel mode,
- * or cannot allocate an overflow entry, then we need to drop it
- * on the floor.
- */
- io_account_cq_overflow(ctx);
- set_bit(IO_CHECK_CQ_DROPPED_BIT, &ctx->check_cq);
- return false;
- }
- if (list_empty(&ctx->cq_overflow_list)) {
- set_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq);
- atomic_or(IORING_SQ_CQ_OVERFLOW, &ctx->rings->sq_flags);
-
- }
- ocqe->cqe.user_data = user_data;
- ocqe->cqe.res = res;
- ocqe->cqe.flags = cflags;
- if (is_cqe32) {
- ocqe->cqe.big_cqe[0] = extra1;
- ocqe->cqe.big_cqe[1] = extra2;
- }
- list_add_tail(&ocqe->list, &ctx->cq_overflow_list);
- return true;
-}
-
-static inline bool __io_fill_cqe_req(struct io_ring_ctx *ctx,
- struct io_kiocb *req)
-{
- struct io_uring_cqe *cqe;
-
- if (!(ctx->flags & IORING_SETUP_CQE32)) {
- trace_io_uring_complete(req->ctx, req, req->cqe.user_data,
- req->cqe.res, req->cqe.flags, 0, 0);
-
- /*
- * If we can't get a cq entry, userspace overflowed the
- * submission (by quite a lot). Increment the overflow count in
- * the ring.
- */
- cqe = io_get_cqe(ctx);
- if (likely(cqe)) {
- memcpy(cqe, &req->cqe, sizeof(*cqe));
- return true;
- }
-
- return io_cqring_event_overflow(ctx, req->cqe.user_data,
- req->cqe.res, req->cqe.flags,
- 0, 0);
- } else {
- u64 extra1 = 0, extra2 = 0;
-
- if (req->flags & REQ_F_CQE32_INIT) {
- extra1 = req->extra1;
- extra2 = req->extra2;
- }
-
- trace_io_uring_complete(req->ctx, req, req->cqe.user_data,
- req->cqe.res, req->cqe.flags, extra1, extra2);
-
- /*
- * If we can't get a cq entry, userspace overflowed the
- * submission (by quite a lot). Increment the overflow count in
- * the ring.
- */
- cqe = io_get_cqe(ctx);
- if (likely(cqe)) {
- memcpy(cqe, &req->cqe, sizeof(struct io_uring_cqe));
- WRITE_ONCE(cqe->big_cqe[0], extra1);
- WRITE_ONCE(cqe->big_cqe[1], extra2);
- return true;
- }
-
- return io_cqring_event_overflow(ctx, req->cqe.user_data,
- req->cqe.res, req->cqe.flags,
- extra1, extra2);
- }
-}
-
-static noinline bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data,
- s32 res, u32 cflags)
-{
- struct io_uring_cqe *cqe;
-
- ctx->cq_extra++;
- trace_io_uring_complete(ctx, NULL, user_data, res, cflags, 0, 0);
-
- /*
- * If we can't get a cq entry, userspace overflowed the
- * submission (by quite a lot). Increment the overflow count in
- * the ring.
- */
- cqe = io_get_cqe(ctx);
- if (likely(cqe)) {
- WRITE_ONCE(cqe->user_data, user_data);
- WRITE_ONCE(cqe->res, res);
- WRITE_ONCE(cqe->flags, cflags);
-
- if (ctx->flags & IORING_SETUP_CQE32) {
- WRITE_ONCE(cqe->big_cqe[0], 0);
- WRITE_ONCE(cqe->big_cqe[1], 0);
- }
- return true;
- }
- return io_cqring_event_overflow(ctx, user_data, res, cflags, 0, 0);
-}
-
-static void __io_req_complete_put(struct io_kiocb *req)
-{
- /*
- * If we're the last reference to this request, add to our locked
- * free_list cache.
- */
- if (req_ref_put_and_test(req)) {
- struct io_ring_ctx *ctx = req->ctx;
-
- if (req->flags & IO_REQ_LINK_FLAGS) {
- if (req->flags & IO_DISARM_MASK)
- io_disarm_next(req);
- if (req->link) {
- io_req_task_queue(req->link);
- req->link = NULL;
- }
- }
- io_req_put_rsrc(req);
- /*
- * Selected buffer deallocation in io_clean_op() assumes that
- * we don't hold ->completion_lock. Clean them here to avoid
- * deadlocks.
- */
- io_put_kbuf_comp(req);
- io_dismantle_req(req);
- io_put_task(req->task, 1);
- wq_list_add_head(&req->comp_list, &ctx->locked_free_list);
- ctx->locked_free_nr++;
- }
-}
-
-static void __io_req_complete_post(struct io_kiocb *req, s32 res,
- u32 cflags)
-{
- if (!(req->flags & REQ_F_CQE_SKIP)) {
- req->cqe.res = res;
- req->cqe.flags = cflags;
- __io_fill_cqe_req(req->ctx, req);
- }
- __io_req_complete_put(req);
-}
-
-static void io_req_complete_post(struct io_kiocb *req, s32 res, u32 cflags)
-{
- struct io_ring_ctx *ctx = req->ctx;
-
- spin_lock(&ctx->completion_lock);
- __io_req_complete_post(req, res, cflags);
- io_commit_cqring(ctx);
- spin_unlock(&ctx->completion_lock);
- io_cqring_ev_posted(ctx);
-}
-
-static inline void io_req_complete_state(struct io_kiocb *req, s32 res,
- u32 cflags)
-{
- req->cqe.res = res;
- req->cqe.flags = cflags;
- req->flags |= REQ_F_COMPLETE_INLINE;
-}
-
-static inline void __io_req_complete(struct io_kiocb *req, unsigned issue_flags,
- s32 res, u32 cflags)
-{
- if (issue_flags & IO_URING_F_COMPLETE_DEFER)
- io_req_complete_state(req, res, cflags);
- else
- io_req_complete_post(req, res, cflags);
-}
-
-static inline void io_req_complete(struct io_kiocb *req, s32 res)
-{
- if (res < 0)
- req_set_fail(req);
- __io_req_complete(req, 0, res, 0);
-}
-
-static void io_req_complete_failed(struct io_kiocb *req, s32 res)
-{
- req_set_fail(req);
- io_req_complete_post(req, res, io_put_kbuf(req, IO_URING_F_UNLOCKED));
-}
-
-/*
- * Don't initialise the fields below on every allocation, but do that in
- * advance and keep them valid across allocations.
- */
-static void io_preinit_req(struct io_kiocb *req, struct io_ring_ctx *ctx)
-{
- req->ctx = ctx;
- req->link = NULL;
- req->async_data = NULL;
- /* not necessary, but safer to zero */
- req->cqe.res = 0;
-}
-
-static void io_flush_cached_locked_reqs(struct io_ring_ctx *ctx,
- struct io_submit_state *state)
-{
- spin_lock(&ctx->completion_lock);
- wq_list_splice(&ctx->locked_free_list, &state->free_list);
- ctx->locked_free_nr = 0;
- spin_unlock(&ctx->completion_lock);
-}
-
-static inline bool io_req_cache_empty(struct io_ring_ctx *ctx)
-{
- return !ctx->submit_state.free_list.next;
-}
-
-/*
- * A request might get retired back into the request caches even before opcode
- * handlers and io_issue_sqe() are done with it, e.g. inline completion path.
- * Because of that, io_alloc_req() should be called only under ->uring_lock
- * and with extra caution to not get a request that is still worked on.
- */
-static __cold bool __io_alloc_req_refill(struct io_ring_ctx *ctx)
- __must_hold(&ctx->uring_lock)
-{
- gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
- void *reqs[IO_REQ_ALLOC_BATCH];
- int ret, i;
-
- /*
- * If we have more than a batch's worth of requests in our IRQ side
- * locked cache, grab the lock and move them over to our submission
- * side cache.
- */
- if (data_race(ctx->locked_free_nr) > IO_COMPL_BATCH) {
- io_flush_cached_locked_reqs(ctx, &ctx->submit_state);
- if (!io_req_cache_empty(ctx))
- return true;
- }
-
- ret = kmem_cache_alloc_bulk(req_cachep, gfp, ARRAY_SIZE(reqs), reqs);
-
- /*
- * Bulk alloc is all-or-nothing. If we fail to get a batch,
- * retry single alloc to be on the safe side.
- */
- if (unlikely(ret <= 0)) {
- reqs[0] = kmem_cache_alloc(req_cachep, gfp);
- if (!reqs[0])
- return false;
- ret = 1;
- }
-
- percpu_ref_get_many(&ctx->refs, ret);
- for (i = 0; i < ret; i++) {
- struct io_kiocb *req = reqs[i];
-
- io_preinit_req(req, ctx);
- io_req_add_to_cache(req, ctx);
- }
- return true;
-}
-
-static inline bool io_alloc_req_refill(struct io_ring_ctx *ctx)
-{
- if (unlikely(io_req_cache_empty(ctx)))
- return __io_alloc_req_refill(ctx);
- return true;
-}
-
-static inline struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx)
-{
- struct io_wq_work_node *node;
-
- node = wq_stack_extract(&ctx->submit_state.free_list);
- return container_of(node, struct io_kiocb, comp_list);
-}
-
-static inline void io_put_file(struct file *file)
-{
- if (file)
- fput(file);
-}
-
-static inline void io_dismantle_req(struct io_kiocb *req)
-{
- unsigned int flags = req->flags;
-
- if (unlikely(flags & IO_REQ_CLEAN_FLAGS))
- io_clean_op(req);
- if (!(flags & REQ_F_FIXED_FILE))
- io_put_file(req->file);
-}
-
-static __cold void io_free_req(struct io_kiocb *req)
-{
- struct io_ring_ctx *ctx = req->ctx;
-
- io_req_put_rsrc(req);
- io_dismantle_req(req);
- io_put_task(req->task, 1);
-
- spin_lock(&ctx->completion_lock);
- wq_list_add_head(&req->comp_list, &ctx->locked_free_list);
- ctx->locked_free_nr++;
- spin_unlock(&ctx->completion_lock);
-}
-
-static inline void io_remove_next_linked(struct io_kiocb *req)
-{
- struct io_kiocb *nxt = req->link;
-
- req->link = nxt->link;
- nxt->link = NULL;
-}
-
-static struct io_kiocb *io_disarm_linked_timeout(struct io_kiocb *req)
- __must_hold(&req->ctx->completion_lock)
- __must_hold(&req->ctx->timeout_lock)
-{
- struct io_kiocb *link = req->link;
-
- if (link && link->opcode == IORING_OP_LINK_TIMEOUT) {
- struct io_timeout_data *io = link->async_data;
-
- io_remove_next_linked(req);
- link->timeout.head = NULL;
- if (hrtimer_try_to_cancel(&io->timer) != -1) {
- list_del(&link->timeout.list);
- return link;
- }
- }
- return NULL;
-}
-
-static void io_fail_links(struct io_kiocb *req)
- __must_hold(&req->ctx->completion_lock)
-{
- struct io_kiocb *nxt, *link = req->link;
- bool ignore_cqes = req->flags & REQ_F_SKIP_LINK_CQES;
-
- req->link = NULL;
- while (link) {
- long res = -ECANCELED;
-
- if (link->flags & REQ_F_FAIL)
- res = link->cqe.res;
-
- nxt = link->link;
- link->link = NULL;
-
- trace_io_uring_fail_link(req->ctx, req, req->cqe.user_data,
- req->opcode, link);
-
- if (ignore_cqes)
- link->flags |= REQ_F_CQE_SKIP;
- else
- link->flags &= ~REQ_F_CQE_SKIP;
- __io_req_complete_post(link, res, 0);
- link = nxt;
- }
-}
-
-static bool io_disarm_next(struct io_kiocb *req)
- __must_hold(&req->ctx->completion_lock)
-{
- struct io_kiocb *link = NULL;
- bool posted = false;
-
- if (req->flags & REQ_F_ARM_LTIMEOUT) {
- link = req->link;
- req->flags &= ~REQ_F_ARM_LTIMEOUT;
- if (link && link->opcode == IORING_OP_LINK_TIMEOUT) {
- io_remove_next_linked(req);
- io_req_tw_post_queue(link, -ECANCELED, 0);
- posted = true;
- }
- } else if (req->flags & REQ_F_LINK_TIMEOUT) {
- struct io_ring_ctx *ctx = req->ctx;
-
- spin_lock_irq(&ctx->timeout_lock);
- link = io_disarm_linked_timeout(req);
- spin_unlock_irq(&ctx->timeout_lock);
- if (link) {
- posted = true;
- io_req_tw_post_queue(link, -ECANCELED, 0);
- }
- }
- if (unlikely((req->flags & REQ_F_FAIL) &&
- !(req->flags & REQ_F_HARDLINK))) {
- posted |= (req->link != NULL);
- io_fail_links(req);
- }
- return posted;
-}
-
-static void __io_req_find_next_prep(struct io_kiocb *req)
-{
- struct io_ring_ctx *ctx = req->ctx;
- bool posted;
-
- spin_lock(&ctx->completion_lock);
- posted = io_disarm_next(req);
- io_commit_cqring(ctx);
- spin_unlock(&ctx->completion_lock);
- if (posted)
- io_cqring_ev_posted(ctx);
-}
-
-static inline struct io_kiocb *io_req_find_next(struct io_kiocb *req)
-{
- struct io_kiocb *nxt;
-
- /*
- * If LINK is set, we have dependent requests in this chain. If we
- * didn't fail this request, queue the first one up, moving any other
- * dependencies to the next request. In case of failure, fail the rest
- * of the chain.
- */
- if (unlikely(req->flags & IO_DISARM_MASK))
- __io_req_find_next_prep(req);
- nxt = req->link;
- req->link = NULL;
- return nxt;
-}
-
-static void ctx_flush_and_put(struct io_ring_ctx *ctx, bool *locked)
-{
- if (!ctx)
- return;
- if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
- atomic_andnot(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
- if (*locked) {
- io_submit_flush_completions(ctx);
- mutex_unlock(&ctx->uring_lock);
- *locked = false;
- }
- percpu_ref_put(&ctx->refs);
-}
-
-static inline void ctx_commit_and_unlock(struct io_ring_ctx *ctx)
-{
- io_commit_cqring(ctx);
- spin_unlock(&ctx->completion_lock);
- io_cqring_ev_posted(ctx);
-}
-
-static void handle_prev_tw_list(struct io_wq_work_node *node,
- struct io_ring_ctx **ctx, bool *uring_locked)
-{
- if (*ctx && !*uring_locked)
- spin_lock(&(*ctx)->completion_lock);
-
- do {
- struct io_wq_work_node *next = node->next;
- struct io_kiocb *req = container_of(node, struct io_kiocb,
- io_task_work.node);
-
- prefetch(container_of(next, struct io_kiocb, io_task_work.node));
-
- if (req->ctx != *ctx) {
- if (unlikely(!*uring_locked && *ctx))
- ctx_commit_and_unlock(*ctx);
-
- ctx_flush_and_put(*ctx, uring_locked);
- *ctx = req->ctx;
- /* if not contended, grab and improve batching */
- *uring_locked = mutex_trylock(&(*ctx)->uring_lock);
- percpu_ref_get(&(*ctx)->refs);
- if (unlikely(!*uring_locked))
- spin_lock(&(*ctx)->completion_lock);
- }
- if (likely(*uring_locked))
- req->io_task_work.func(req, uring_locked);
- else
- __io_req_complete_post(req, req->cqe.res,
- io_put_kbuf_comp(req));
- node = next;
- } while (node);
-
- if (unlikely(!*uring_locked))
- ctx_commit_and_unlock(*ctx);
-}
-
-static void handle_tw_list(struct io_wq_work_node *node,
- struct io_ring_ctx **ctx, bool *locked)
-{
- do {
- struct io_wq_work_node *next = node->next;
- struct io_kiocb *req = container_of(node, struct io_kiocb,
- io_task_work.node);
-
- prefetch(container_of(next, struct io_kiocb, io_task_work.node));
-
- if (req->ctx != *ctx) {
- ctx_flush_and_put(*ctx, locked);
- *ctx = req->ctx;
- /* if not contended, grab and improve batching */
- *locked = mutex_trylock(&(*ctx)->uring_lock);
- percpu_ref_get(&(*ctx)->refs);
- }
- req->io_task_work.func(req, locked);
- node = next;
- } while (node);
-}
-
-static void tctx_task_work(struct callback_head *cb)
-{
- bool uring_locked = false;
- struct io_ring_ctx *ctx = NULL;
- struct io_uring_task *tctx = container_of(cb, struct io_uring_task,
- task_work);
-
- while (1) {
- struct io_wq_work_node *node1, *node2;
-
- spin_lock_irq(&tctx->task_lock);
- node1 = tctx->prio_task_list.first;
- node2 = tctx->task_list.first;
- INIT_WQ_LIST(&tctx->task_list);
- INIT_WQ_LIST(&tctx->prio_task_list);
- if (!node2 && !node1)
- tctx->task_running = false;
- spin_unlock_irq(&tctx->task_lock);
- if (!node2 && !node1)
- break;
-
- if (node1)
- handle_prev_tw_list(node1, &ctx, &uring_locked);
- if (node2)
- handle_tw_list(node2, &ctx, &uring_locked);
- cond_resched();
-
- if (data_race(!tctx->task_list.first) &&
- data_race(!tctx->prio_task_list.first) && uring_locked)
- io_submit_flush_completions(ctx);
- }
-
- ctx_flush_and_put(ctx, &uring_locked);
-
- /* relaxed read is enough as only the task itself sets ->in_idle */
- if (unlikely(atomic_read(&tctx->in_idle)))
- io_uring_drop_tctx_refs(current);
-}
-
-static void __io_req_task_work_add(struct io_kiocb *req,
- struct io_uring_task *tctx,
- struct io_wq_work_list *list)
-{
- struct io_ring_ctx *ctx = req->ctx;
- struct io_wq_work_node *node;
- unsigned long flags;
- bool running;
-
- spin_lock_irqsave(&tctx->task_lock, flags);
- wq_list_add_tail(&req->io_task_work.node, list);
- running = tctx->task_running;
- if (!running)
- tctx->task_running = true;
- spin_unlock_irqrestore(&tctx->task_lock, flags);
-
- /* task_work already pending, we're done */
- if (running)
- return;
-
- if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
- atomic_or(IORING_SQ_TASKRUN, &ctx->rings->sq_flags);
-
- if (likely(!task_work_add(req->task, &tctx->task_work, ctx->notify_method)))
- return;
-
- spin_lock_irqsave(&tctx->task_lock, flags);
- tctx->task_running = false;
- node = wq_list_merge(&tctx->prio_task_list, &tctx->task_list);
- spin_unlock_irqrestore(&tctx->task_lock, flags);
-
- while (node) {
- req = container_of(node, struct io_kiocb, io_task_work.node);
- node = node->next;
- if (llist_add(&req->io_task_work.fallback_node,
- &req->ctx->fallback_llist))
- schedule_delayed_work(&req->ctx->fallback_work, 1);
- }
-}
-
-static void io_req_task_work_add(struct io_kiocb *req)
-{
- struct io_uring_task *tctx = req->task->io_uring;
-
- __io_req_task_work_add(req, tctx, &tctx->task_list);
-}
-
-static void io_req_task_prio_work_add(struct io_kiocb *req)
-{
- struct io_uring_task *tctx = req->task->io_uring;
-
- if (req->ctx->flags & IORING_SETUP_SQPOLL)
- __io_req_task_work_add(req, tctx, &tctx->prio_task_list);
- else
- __io_req_task_work_add(req, tctx, &tctx->task_list);
-}
-
-static void io_req_tw_post(struct io_kiocb *req, bool *locked)
-{
- io_req_complete_post(req, req->cqe.res, req->cqe.flags);
-}
-
-static void io_req_tw_post_queue(struct io_kiocb *req, s32 res, u32 cflags)
-{
- req->cqe.res = res;
- req->cqe.flags = cflags;
- req->io_task_work.func = io_req_tw_post;
- io_req_task_work_add(req);
-}
-
-static void io_req_task_cancel(struct io_kiocb *req, bool *locked)
-{
- /* not needed for normal modes, but SQPOLL depends on it */
- io_tw_lock(req->ctx, locked);
- io_req_complete_failed(req, req->cqe.res);
-}
-
-static void io_req_task_submit(struct io_kiocb *req, bool *locked)
-{
- io_tw_lock(req->ctx, locked);
- /* req->task == current here, checking PF_EXITING is safe */
- if (likely(!(req->task->flags & PF_EXITING)))
- io_queue_sqe(req);
- else
- io_req_complete_failed(req, -EFAULT);
-}
-
-static void io_req_task_queue_fail(struct io_kiocb *req, int ret)
-{
- req->cqe.res = ret;
- req->io_task_work.func = io_req_task_cancel;
- io_req_task_work_add(req);
-}
-
-static void io_req_task_queue(struct io_kiocb *req)
-{
- req->io_task_work.func = io_req_task_submit;
- io_req_task_work_add(req);
-}
-
-static void io_req_task_queue_reissue(struct io_kiocb *req)
-{
- req->io_task_work.func = io_queue_iowq;
- io_req_task_work_add(req);
-}
-
-static void io_queue_next(struct io_kiocb *req)
-{
- struct io_kiocb *nxt = io_req_find_next(req);
-
- if (nxt)
- io_req_task_queue(nxt);
-}
-
-static void io_free_batch_list(struct io_ring_ctx *ctx,
- struct io_wq_work_node *node)
- __must_hold(&ctx->uring_lock)
-{
- struct task_struct *task = NULL;
- int task_refs = 0;
-
- do {
- struct io_kiocb *req = container_of(node, struct io_kiocb,
- comp_list);
-
- if (unlikely(req->flags & IO_REQ_CLEAN_SLOW_FLAGS)) {
- if (req->flags & REQ_F_REFCOUNT) {
- node = req->comp_list.next;
- if (!req_ref_put_and_test(req))
- continue;
- }
- if ((req->flags & REQ_F_POLLED) && req->apoll) {
- struct async_poll *apoll = req->apoll;
-
- if (apoll->double_poll)
- kfree(apoll->double_poll);
- list_add(&apoll->poll.wait.entry,
- &ctx->apoll_cache);
- req->flags &= ~REQ_F_POLLED;
- }
- if (req->flags & IO_REQ_LINK_FLAGS)
- io_queue_next(req);
- if (unlikely(req->flags & IO_REQ_CLEAN_FLAGS))
- io_clean_op(req);
- }
- if (!(req->flags & REQ_F_FIXED_FILE))
- io_put_file(req->file);
-
- io_req_put_rsrc_locked(req, ctx);
-
- if (req->task != task) {
- if (task)
- io_put_task(task, task_refs);
- task = req->task;
- task_refs = 0;
- }
- task_refs++;
- node = req->comp_list.next;
- io_req_add_to_cache(req, ctx);
- } while (node);
-
- if (task)
- io_put_task(task, task_refs);
-}
-
-static void __io_submit_flush_completions(struct io_ring_ctx *ctx)
- __must_hold(&ctx->uring_lock)
-{
- struct io_wq_work_node *node, *prev;
- struct io_submit_state *state = &ctx->submit_state;
-
- if (state->flush_cqes) {
- spin_lock(&ctx->completion_lock);
- wq_list_for_each(node, prev, &state->compl_reqs) {
- struct io_kiocb *req = container_of(node, struct io_kiocb,
- comp_list);
-
- if (!(req->flags & REQ_F_CQE_SKIP))
- __io_fill_cqe_req(ctx, req);
- }
-
- io_commit_cqring(ctx);
- spin_unlock(&ctx->completion_lock);
- io_cqring_ev_posted(ctx);
- state->flush_cqes = false;
- }
-
- io_free_batch_list(ctx, state->compl_reqs.first);
- INIT_WQ_LIST(&state->compl_reqs);
-}
-
-/*
- * Drop reference to request, return next in chain (if there is one) if this
- * was the last reference to this request.
- */
-static inline struct io_kiocb *io_put_req_find_next(struct io_kiocb *req)
-{
- struct io_kiocb *nxt = NULL;
-
- if (req_ref_put_and_test(req)) {
- if (unlikely(req->flags & IO_REQ_LINK_FLAGS))
- nxt = io_req_find_next(req);
- io_free_req(req);
- }
- return nxt;
-}
-
-static inline void io_put_req(struct io_kiocb *req)
-{
- if (req_ref_put_and_test(req)) {
- io_queue_next(req);
- io_free_req(req);
- }
-}
-
-static unsigned io_cqring_events(struct io_ring_ctx *ctx)
-{
- /* See comment at the top of this file */
- smp_rmb();
- return __io_cqring_events(ctx);
-}
-
-static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
-{
- struct io_rings *rings = ctx->rings;
-
- /* make sure SQ entry isn't read before tail */
- return smp_load_acquire(&rings->sq.tail) - ctx->cached_sq_head;
-}
-
-static inline bool io_run_task_work(void)
-{
- if (test_thread_flag(TIF_NOTIFY_SIGNAL) || task_work_pending(current)) {
- __set_current_state(TASK_RUNNING);
- clear_notify_signal();
- if (task_work_pending(current))
- task_work_run();
- return true;
- }
-
- return false;
-}
-
-static int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin)
-{
- struct io_wq_work_node *pos, *start, *prev;
- unsigned int poll_flags = BLK_POLL_NOSLEEP;
- DEFINE_IO_COMP_BATCH(iob);
- int nr_events = 0;
-
- /*
- * Only spin for completions if we don't have multiple devices hanging
- * off our complete list.
- */
- if (ctx->poll_multi_queue || force_nonspin)
- poll_flags |= BLK_POLL_ONESHOT;
-
- wq_list_for_each(pos, start, &ctx->iopoll_list) {
- struct io_kiocb *req = container_of(pos, struct io_kiocb, comp_list);
- struct kiocb *kiocb = &req->rw.kiocb;
- int ret;
-
- /*
- * Move completed and retryable entries to our local lists.
- * If we find a request that requires polling, break out
- * and complete those lists first, if we have entries there.
- */
- if (READ_ONCE(req->iopoll_completed))
- break;
-
- ret = kiocb->ki_filp->f_op->iopoll(kiocb, &iob, poll_flags);
- if (unlikely(ret < 0))
- return ret;
- else if (ret)
- poll_flags |= BLK_POLL_ONESHOT;
-
- /* iopoll may have completed current req */
- if (!rq_list_empty(iob.req_list) ||
- READ_ONCE(req->iopoll_completed))
- break;
- }
-
- if (!rq_list_empty(iob.req_list))
- iob.complete(&iob);
- else if (!pos)
- return 0;
-
- prev = start;
- wq_list_for_each_resume(pos, prev) {
- struct io_kiocb *req = container_of(pos, struct io_kiocb, comp_list);
-
- /* order with io_complete_rw_iopoll(), e.g. ->result updates */
- if (!smp_load_acquire(&req->iopoll_completed))
- break;
- nr_events++;
- if (unlikely(req->flags & REQ_F_CQE_SKIP))
- continue;
-
- req->cqe.flags = io_put_kbuf(req, 0);
- __io_fill_cqe_req(req->ctx, req);
- }
-
- if (unlikely(!nr_events))
- return 0;
-
- io_commit_cqring(ctx);
- io_cqring_ev_posted_iopoll(ctx);
- pos = start ? start->next : ctx->iopoll_list.first;
- wq_list_cut(&ctx->iopoll_list, prev, start);
- io_free_batch_list(ctx, pos);
- return nr_events;
-}
-
-/*
- * We can't just wait for polled events to come to us, we have to actively
- * find and complete them.
- */
-static __cold void io_iopoll_try_reap_events(struct io_ring_ctx *ctx)
-{
- if (!(ctx->flags & IORING_SETUP_IOPOLL))
- return;
-
- mutex_lock(&ctx->uring_lock);
- while (!wq_list_empty(&ctx->iopoll_list)) {
- /* let it sleep and repeat later if can't complete a request */
- if (io_do_iopoll(ctx, true) == 0)
- break;
- /*
- * Ensure we allow local-to-the-cpu processing to take place,
- * in this case we need to ensure that we reap all events.
- * Also let task_work, etc. to progress by releasing the mutex
- */
- if (need_resched()) {
- mutex_unlock(&ctx->uring_lock);
- cond_resched();
- mutex_lock(&ctx->uring_lock);
- }
- }
- mutex_unlock(&ctx->uring_lock);
-}
-
-static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
-{
- unsigned int nr_events = 0;
- int ret = 0;
- unsigned long check_cq;
-
- /*
- * Don't enter poll loop if we already have events pending.
- * If we do, we can potentially be spinning for commands that
- * already triggered a CQE (eg in error).
- */
- check_cq = READ_ONCE(ctx->check_cq);
- if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT))
- __io_cqring_overflow_flush(ctx, false);
- if (io_cqring_events(ctx))
- return 0;
-
- /*
- * Similarly do not spin if we have not informed the user of any
- * dropped CQE.
- */
- if (unlikely(check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT)))
- return -EBADR;
-
- do {
- /*
- * If a submit got punted to a workqueue, we can have the
- * application entering polling for a command before it gets
- * issued. That app will hold the uring_lock for the duration
- * of the poll right here, so we need to take a breather every
- * now and then to ensure that the issue has a chance to add
- * the poll to the issued list. Otherwise we can spin here
- * forever, while the workqueue is stuck trying to acquire the
- * very same mutex.
- */
- if (wq_list_empty(&ctx->iopoll_list)) {
- u32 tail = ctx->cached_cq_tail;
-
- mutex_unlock(&ctx->uring_lock);
- io_run_task_work();
- mutex_lock(&ctx->uring_lock);
-
- /* some requests don't go through iopoll_list */
- if (tail != ctx->cached_cq_tail ||
- wq_list_empty(&ctx->iopoll_list))
- break;
- }
- ret = io_do_iopoll(ctx, !min);
- if (ret < 0)
- break;
- nr_events += ret;
- ret = 0;
- } while (nr_events < min && !need_resched());
-
- return ret;
-}
-
-static void kiocb_end_write(struct io_kiocb *req)
-{
- /*
- * Tell lockdep we inherited freeze protection from submission
- * thread.
- */
- if (req->flags & REQ_F_ISREG) {
- struct super_block *sb = file_inode(req->file)->i_sb;
-
- __sb_writers_acquired(sb, SB_FREEZE_WRITE);
- sb_end_write(sb);
- }
-}
-
-#ifdef CONFIG_BLOCK
-static bool io_resubmit_prep(struct io_kiocb *req)
-{
- struct io_async_rw *rw = req->async_data;
-
- if (!req_has_async_data(req))
- return !io_req_prep_async(req);
- iov_iter_restore(&rw->s.iter, &rw->s.iter_state);
- return true;
-}
-
-static bool io_rw_should_reissue(struct io_kiocb *req)
-{
- umode_t mode = file_inode(req->file)->i_mode;
- struct io_ring_ctx *ctx = req->ctx;
-
- if (!S_ISBLK(mode) && !S_ISREG(mode))
- return false;
- if ((req->flags & REQ_F_NOWAIT) || (io_wq_current_is_worker() &&
- !(ctx->flags & IORING_SETUP_IOPOLL)))
- return false;
- /*
- * If ref is dying, we might be running poll reap from the exit work.
- * Don't attempt to reissue from that path, just let it fail with
- * -EAGAIN.
- */
- if (percpu_ref_is_dying(&ctx->refs))
- return false;
- /*
- * Play it safe and assume not safe to re-import and reissue if we're
- * not in the original thread group (or in task context).
- */
- if (!same_thread_group(req->task, current) || !in_task())
- return false;
- return true;
-}
-#else
-static bool io_resubmit_prep(struct io_kiocb *req)
-{
- return false;
-}
-static bool io_rw_should_reissue(struct io_kiocb *req)
-{
- return false;
-}
-#endif
-
-static bool __io_complete_rw_common(struct io_kiocb *req, long res)
-{
- if (req->rw.kiocb.ki_flags & IOCB_WRITE) {
- kiocb_end_write(req);
- fsnotify_modify(req->file);
- } else {
- fsnotify_access(req->file);
- }
- if (unlikely(res != req->cqe.res)) {
- if ((res == -EAGAIN || res == -EOPNOTSUPP) &&
- io_rw_should_reissue(req)) {
- req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO;
- return true;
- }
- req_set_fail(req);
- req->cqe.res = res;
- }
- return false;
-}
-
-static inline void io_req_task_complete(struct io_kiocb *req, bool *locked)
-{
- int res = req->cqe.res;
-
- if (*locked) {
- io_req_complete_state(req, res, io_put_kbuf(req, 0));
- io_req_add_compl_list(req);
- } else {
- io_req_complete_post(req, res,
- io_put_kbuf(req, IO_URING_F_UNLOCKED));
- }
-}
-
-static void __io_complete_rw(struct io_kiocb *req, long res,
- unsigned int issue_flags)
-{
- if (__io_complete_rw_common(req, res))
- return;
- __io_req_complete(req, issue_flags, req->cqe.res,
- io_put_kbuf(req, issue_flags));
-}
-
-static void io_complete_rw(struct kiocb *kiocb, long res)
-{
- struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
-
- if (__io_complete_rw_common(req, res))
- return;
- req->cqe.res = res;
- req->io_task_work.func = io_req_task_complete;
- io_req_task_prio_work_add(req);
-}
-
-static void io_complete_rw_iopoll(struct kiocb *kiocb, long res)
-{
- struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
-
- if (kiocb->ki_flags & IOCB_WRITE)
- kiocb_end_write(req);
- if (unlikely(res != req->cqe.res)) {
- if (res == -EAGAIN && io_rw_should_reissue(req)) {
- req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO;
- return;
- }
- req->cqe.res = res;
- }
-
- /* order with io_iopoll_complete() checking ->iopoll_completed */
- smp_store_release(&req->iopoll_completed, 1);
-}
-
-/*
- * After the iocb has been issued, it's safe to be found on the poll list.
- * Adding the kiocb to the list AFTER submission ensures that we don't
- * find it from a io_do_iopoll() thread before the issuer is done
- * accessing the kiocb cookie.
- */
-static void io_iopoll_req_issued(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_ring_ctx *ctx = req->ctx;
- const bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
-
- /* workqueue context doesn't hold uring_lock, grab it now */
- if (unlikely(needs_lock))
- mutex_lock(&ctx->uring_lock);
-
- /*
- * Track whether we have multiple files in our lists. This will impact
- * how we do polling eventually, not spinning if we're on potentially
- * different devices.
- */
- if (wq_list_empty(&ctx->iopoll_list)) {
- ctx->poll_multi_queue = false;
- } else if (!ctx->poll_multi_queue) {
- struct io_kiocb *list_req;
-
- list_req = container_of(ctx->iopoll_list.first, struct io_kiocb,
- comp_list);
- if (list_req->file != req->file)
- ctx->poll_multi_queue = true;
- }
-
- /*
- * For fast devices, IO may have already completed. If it has, add
- * it to the front so we find it first.
- */
- if (READ_ONCE(req->iopoll_completed))
- wq_list_add_head(&req->comp_list, &ctx->iopoll_list);
- else
- wq_list_add_tail(&req->comp_list, &ctx->iopoll_list);
-
- if (unlikely(needs_lock)) {
- /*
- * If IORING_SETUP_SQPOLL is enabled, sqes are either handle
- * in sq thread task context or in io worker task context. If
- * current task context is sq thread, we don't need to check
- * whether should wake up sq thread.
- */
- if ((ctx->flags & IORING_SETUP_SQPOLL) &&
- wq_has_sleeper(&ctx->sq_data->wait))
- wake_up(&ctx->sq_data->wait);
-
- mutex_unlock(&ctx->uring_lock);
- }
-}
-
-static bool io_bdev_nowait(struct block_device *bdev)
-{
- return !bdev || blk_queue_nowait(bdev_get_queue(bdev));
-}
-
-/*
- * If we tracked the file through the SCM inflight mechanism, we could support
- * any file. For now, just ensure that anything potentially problematic is done
- * inline.
- */
-static bool __io_file_supports_nowait(struct file *file, umode_t mode)
-{
- if (S_ISBLK(mode)) {
- if (IS_ENABLED(CONFIG_BLOCK) &&
- io_bdev_nowait(I_BDEV(file->f_mapping->host)))
- return true;
- return false;
- }
- if (S_ISSOCK(mode))
- return true;
- if (S_ISREG(mode)) {
- if (IS_ENABLED(CONFIG_BLOCK) &&
- io_bdev_nowait(file->f_inode->i_sb->s_bdev) &&
- file->f_op != &io_uring_fops)
- return true;
- return false;
- }
-
- /* any ->read/write should understand O_NONBLOCK */
- if (file->f_flags & O_NONBLOCK)
- return true;
- return file->f_mode & FMODE_NOWAIT;
-}
-
-/*
- * If we tracked the file through the SCM inflight mechanism, we could support
- * any file. For now, just ensure that anything potentially problematic is done
- * inline.
- */
-static unsigned int io_file_get_flags(struct file *file)
-{
- umode_t mode = file_inode(file)->i_mode;
- unsigned int res = 0;
-
- if (S_ISREG(mode))
- res |= FFS_ISREG;
- if (__io_file_supports_nowait(file, mode))
- res |= FFS_NOWAIT;
- if (io_file_need_scm(file))
- res |= FFS_SCM;
- return res;
-}
-
-static inline bool io_file_supports_nowait(struct io_kiocb *req)
-{
- return req->flags & REQ_F_SUPPORT_NOWAIT;
-}
-
-static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
- struct kiocb *kiocb = &req->rw.kiocb;
- unsigned ioprio;
- int ret;
-
- kiocb->ki_pos = READ_ONCE(sqe->off);
- /* used for fixed read/write too - just read unconditionally */
- req->buf_index = READ_ONCE(sqe->buf_index);
-
- if (req->opcode == IORING_OP_READ_FIXED ||
- req->opcode == IORING_OP_WRITE_FIXED) {
- struct io_ring_ctx *ctx = req->ctx;
- u16 index;
-
- if (unlikely(req->buf_index >= ctx->nr_user_bufs))
- return -EFAULT;
- index = array_index_nospec(req->buf_index, ctx->nr_user_bufs);
- req->imu = ctx->user_bufs[index];
- io_req_set_rsrc_node(req, ctx, 0);
- }
-
- ioprio = READ_ONCE(sqe->ioprio);
- if (ioprio) {
- ret = ioprio_check_cap(ioprio);
- if (ret)
- return ret;
-
- kiocb->ki_ioprio = ioprio;
- } else {
- kiocb->ki_ioprio = get_current_ioprio();
- }
-
- req->rw.addr = READ_ONCE(sqe->addr);
- req->rw.len = READ_ONCE(sqe->len);
- req->rw.flags = READ_ONCE(sqe->rw_flags);
- return 0;
-}
-
-static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
-{
- switch (ret) {
- case -EIOCBQUEUED:
- break;
- case -ERESTARTSYS:
- case -ERESTARTNOINTR:
- case -ERESTARTNOHAND:
- case -ERESTART_RESTARTBLOCK:
- /*
- * We can't just restart the syscall, since previously
- * submitted sqes may already be in progress. Just fail this
- * IO with EINTR.
- */
- ret = -EINTR;
- fallthrough;
- default:
- kiocb->ki_complete(kiocb, ret);
- }
-}
-
-static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req)
-{
- struct kiocb *kiocb = &req->rw.kiocb;
-
- if (kiocb->ki_pos != -1)
- return &kiocb->ki_pos;
-
- if (!(req->file->f_mode & FMODE_STREAM)) {
- req->flags |= REQ_F_CUR_POS;
- kiocb->ki_pos = req->file->f_pos;
- return &kiocb->ki_pos;
- }
-
- kiocb->ki_pos = 0;
- return NULL;
-}
-
-static void kiocb_done(struct io_kiocb *req, ssize_t ret,
- unsigned int issue_flags)
-{
- struct io_async_rw *io = req->async_data;
-
- /* add previously done IO, if any */
- if (req_has_async_data(req) && io->bytes_done > 0) {
- if (ret < 0)
- ret = io->bytes_done;
- else
- ret += io->bytes_done;
- }
-
- if (req->flags & REQ_F_CUR_POS)
- req->file->f_pos = req->rw.kiocb.ki_pos;
- if (ret >= 0 && (req->rw.kiocb.ki_complete == io_complete_rw))
- __io_complete_rw(req, ret, issue_flags);
- else
- io_rw_done(&req->rw.kiocb, ret);
-
- if (req->flags & REQ_F_REISSUE) {
- req->flags &= ~REQ_F_REISSUE;
- if (io_resubmit_prep(req))
- io_req_task_queue_reissue(req);
- else
- io_req_task_queue_fail(req, ret);
- }
-}
-
-static int __io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter,
- struct io_mapped_ubuf *imu)
-{
- size_t len = req->rw.len;
- u64 buf_end, buf_addr = req->rw.addr;
- size_t offset;
-
- if (unlikely(check_add_overflow(buf_addr, (u64)len, &buf_end)))
- return -EFAULT;
- /* not inside the mapped region */
- if (unlikely(buf_addr < imu->ubuf || buf_end > imu->ubuf_end))
- return -EFAULT;
-
- /*
- * May not be a start of buffer, set size appropriately
- * and advance us to the beginning.
- */
- offset = buf_addr - imu->ubuf;
- iov_iter_bvec(iter, rw, imu->bvec, imu->nr_bvecs, offset + len);
-
- if (offset) {
- /*
- * Don't use iov_iter_advance() here, as it's really slow for
- * using the latter parts of a big fixed buffer - it iterates
- * over each segment manually. We can cheat a bit here, because
- * we know that:
- *
- * 1) it's a BVEC iter, we set it up
- * 2) all bvecs are PAGE_SIZE in size, except potentially the
- * first and last bvec
- *
- * So just find our index, and adjust the iterator afterwards.
- * If the offset is within the first bvec (or the whole first
- * bvec, just use iov_iter_advance(). This makes it easier
- * since we can just skip the first segment, which may not
- * be PAGE_SIZE aligned.
- */
- const struct bio_vec *bvec = imu->bvec;
-
- if (offset <= bvec->bv_len) {
- iov_iter_advance(iter, offset);
- } else {
- unsigned long seg_skip;
-
- /* skip first vec */
- offset -= bvec->bv_len;
- seg_skip = 1 + (offset >> PAGE_SHIFT);
-
- iter->bvec = bvec + seg_skip;
- iter->nr_segs -= seg_skip;
- iter->count -= bvec->bv_len + offset;
- iter->iov_offset = offset & ~PAGE_MASK;
- }
- }
-
- return 0;
-}
-
-static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter,
- unsigned int issue_flags)
-{
- if (WARN_ON_ONCE(!req->imu))
- return -EFAULT;
- return __io_import_fixed(req, rw, iter, req->imu);
-}
-
-static int io_buffer_add_list(struct io_ring_ctx *ctx,
- struct io_buffer_list *bl, unsigned int bgid)
-{
- bl->bgid = bgid;
- if (bgid < BGID_ARRAY)
- return 0;
-
- return xa_err(xa_store(&ctx->io_bl_xa, bgid, bl, GFP_KERNEL));
-}
-
-static void __user *io_provided_buffer_select(struct io_kiocb *req, size_t *len,
- struct io_buffer_list *bl)
-{
- if (!list_empty(&bl->buf_list)) {
- struct io_buffer *kbuf;
-
- kbuf = list_first_entry(&bl->buf_list, struct io_buffer, list);
- list_del(&kbuf->list);
- if (*len > kbuf->len)
- *len = kbuf->len;
- req->flags |= REQ_F_BUFFER_SELECTED;
- req->kbuf = kbuf;
- req->buf_index = kbuf->bid;
- return u64_to_user_ptr(kbuf->addr);
- }
- return NULL;
-}
-
-static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len,
- struct io_buffer_list *bl,
- unsigned int issue_flags)
-{
- struct io_uring_buf_ring *br = bl->buf_ring;
- struct io_uring_buf *buf;
- __u16 head = bl->head;
-
- if (unlikely(smp_load_acquire(&br->tail) == head))
- return NULL;
-
- head &= bl->mask;
- if (head < IO_BUFFER_LIST_BUF_PER_PAGE) {
- buf = &br->bufs[head];
- } else {
- int off = head & (IO_BUFFER_LIST_BUF_PER_PAGE - 1);
- int index = head / IO_BUFFER_LIST_BUF_PER_PAGE;
- buf = page_address(bl->buf_pages[index]);
- buf += off;
- }
- if (*len > buf->len)
- *len = buf->len;
- req->flags |= REQ_F_BUFFER_RING;
- req->buf_list = bl;
- req->buf_index = buf->bid;
-
- if (issue_flags & IO_URING_F_UNLOCKED || !file_can_poll(req->file)) {
- /*
- * If we came in unlocked, we have no choice but to consume the
- * buffer here. This does mean it'll be pinned until the IO
- * completes. But coming in unlocked means we're in io-wq
- * context, hence there should be no further retry. For the
- * locked case, the caller must ensure to call the commit when
- * the transfer completes (or if we get -EAGAIN and must poll
- * or retry).
- */
- req->buf_list = NULL;
- bl->head++;
- }
- return u64_to_user_ptr(buf->addr);
-}
-
-static void __user *io_buffer_select(struct io_kiocb *req, size_t *len,
- unsigned int issue_flags)
-{
- struct io_ring_ctx *ctx = req->ctx;
- struct io_buffer_list *bl;
- void __user *ret = NULL;
-
- io_ring_submit_lock(req->ctx, issue_flags);
-
- bl = io_buffer_get_list(ctx, req->buf_index);
- if (likely(bl)) {
- if (bl->buf_nr_pages)
- ret = io_ring_buffer_select(req, len, bl, issue_flags);
- else
- ret = io_provided_buffer_select(req, len, bl);
- }
- io_ring_submit_unlock(req->ctx, issue_flags);
- return ret;
-}
-
-#ifdef CONFIG_COMPAT
-static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov,
- unsigned int issue_flags)
-{
- struct compat_iovec __user *uiov;
- compat_ssize_t clen;
- void __user *buf;
- size_t len;
-
- uiov = u64_to_user_ptr(req->rw.addr);
- if (!access_ok(uiov, sizeof(*uiov)))
- return -EFAULT;
- if (__get_user(clen, &uiov->iov_len))
- return -EFAULT;
- if (clen < 0)
- return -EINVAL;
-
- len = clen;
- buf = io_buffer_select(req, &len, issue_flags);
- if (!buf)
- return -ENOBUFS;
- req->rw.addr = (unsigned long) buf;
- iov[0].iov_base = buf;
- req->rw.len = iov[0].iov_len = (compat_size_t) len;
- return 0;
-}
-#endif
-
-static ssize_t __io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
- unsigned int issue_flags)
-{
- struct iovec __user *uiov = u64_to_user_ptr(req->rw.addr);
- void __user *buf;
- ssize_t len;
-
- if (copy_from_user(iov, uiov, sizeof(*uiov)))
- return -EFAULT;
-
- len = iov[0].iov_len;
- if (len < 0)
- return -EINVAL;
- buf = io_buffer_select(req, &len, issue_flags);
- if (!buf)
- return -ENOBUFS;
- req->rw.addr = (unsigned long) buf;
- iov[0].iov_base = buf;
- req->rw.len = iov[0].iov_len = len;
- return 0;
-}
-
-static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
- unsigned int issue_flags)
-{
- if (req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)) {
- iov[0].iov_base = u64_to_user_ptr(req->rw.addr);
- iov[0].iov_len = req->rw.len;
- return 0;
- }
- if (req->rw.len != 1)
- return -EINVAL;
-
-#ifdef CONFIG_COMPAT
- if (req->ctx->compat)
- return io_compat_import(req, iov, issue_flags);
-#endif
-
- return __io_iov_buffer_select(req, iov, issue_flags);
-}
-
-static inline bool io_do_buffer_select(struct io_kiocb *req)
-{
- if (!(req->flags & REQ_F_BUFFER_SELECT))
- return false;
- return !(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING));
-}
-
-static struct iovec *__io_import_iovec(int rw, struct io_kiocb *req,
- struct io_rw_state *s,
- unsigned int issue_flags)
-{
- struct iov_iter *iter = &s->iter;
- u8 opcode = req->opcode;
- struct iovec *iovec;
- void __user *buf;
- size_t sqe_len;
- ssize_t ret;
-
- if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) {
- ret = io_import_fixed(req, rw, iter, issue_flags);
- if (ret)
- return ERR_PTR(ret);
- return NULL;
- }
-
- buf = u64_to_user_ptr(req->rw.addr);
- sqe_len = req->rw.len;
-
- if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) {
- if (io_do_buffer_select(req)) {
- buf = io_buffer_select(req, &sqe_len, issue_flags);
- if (!buf)
- return ERR_PTR(-ENOBUFS);
- req->rw.addr = (unsigned long) buf;
- req->rw.len = sqe_len;
- }
-
- ret = import_single_range(rw, buf, sqe_len, s->fast_iov, iter);
- if (ret)
- return ERR_PTR(ret);
- return NULL;
- }
-
- iovec = s->fast_iov;
- if (req->flags & REQ_F_BUFFER_SELECT) {
- ret = io_iov_buffer_select(req, iovec, issue_flags);
- if (ret)
- return ERR_PTR(ret);
- iov_iter_init(iter, rw, iovec, 1, iovec->iov_len);
- return NULL;
- }
-
- ret = __import_iovec(rw, buf, sqe_len, UIO_FASTIOV, &iovec, iter,
- req->ctx->compat);
- if (unlikely(ret < 0))
- return ERR_PTR(ret);
- return iovec;
-}
-
-static inline int io_import_iovec(int rw, struct io_kiocb *req,
- struct iovec **iovec, struct io_rw_state *s,
- unsigned int issue_flags)
-{
- *iovec = __io_import_iovec(rw, req, s, issue_flags);
- if (unlikely(IS_ERR(*iovec)))
- return PTR_ERR(*iovec);
-
- iov_iter_save_state(&s->iter, &s->iter_state);
- return 0;
-}
-
-static inline loff_t *io_kiocb_ppos(struct kiocb *kiocb)
-{
- return (kiocb->ki_filp->f_mode & FMODE_STREAM) ? NULL : &kiocb->ki_pos;
-}
-
-/*
- * For files that don't have ->read_iter() and ->write_iter(), handle them
- * by looping over ->read() or ->write() manually.
- */
-static ssize_t loop_rw_iter(int rw, struct io_kiocb *req, struct iov_iter *iter)
-{
- struct kiocb *kiocb = &req->rw.kiocb;
- struct file *file = req->file;
- ssize_t ret = 0;
- loff_t *ppos;
-
- /*
- * Don't support polled IO through this interface, and we can't
- * support non-blocking either. For the latter, this just causes
- * the kiocb to be handled from an async context.
- */
- if (kiocb->ki_flags & IOCB_HIPRI)
- return -EOPNOTSUPP;
- if ((kiocb->ki_flags & IOCB_NOWAIT) &&
- !(kiocb->ki_filp->f_flags & O_NONBLOCK))
- return -EAGAIN;
-
- ppos = io_kiocb_ppos(kiocb);
-
- while (iov_iter_count(iter)) {
- struct iovec iovec;
- ssize_t nr;
-
- if (!iov_iter_is_bvec(iter)) {
- iovec = iov_iter_iovec(iter);
- } else {
- iovec.iov_base = u64_to_user_ptr(req->rw.addr);
- iovec.iov_len = req->rw.len;
- }
-
- if (rw == READ) {
- nr = file->f_op->read(file, iovec.iov_base,
- iovec.iov_len, ppos);
- } else {
- nr = file->f_op->write(file, iovec.iov_base,
- iovec.iov_len, ppos);
- }
-
- if (nr < 0) {
- if (!ret)
- ret = nr;
- break;
- }
- ret += nr;
- if (!iov_iter_is_bvec(iter)) {
- iov_iter_advance(iter, nr);
- } else {
- req->rw.addr += nr;
- req->rw.len -= nr;
- if (!req->rw.len)
- break;
- }
- if (nr != iovec.iov_len)
- break;
- }
-
- return ret;
-}
-
-static void io_req_map_rw(struct io_kiocb *req, const struct iovec *iovec,
- const struct iovec *fast_iov, struct iov_iter *iter)
-{
- struct io_async_rw *rw = req->async_data;
-
- memcpy(&rw->s.iter, iter, sizeof(*iter));
- rw->free_iovec = iovec;
- rw->bytes_done = 0;
- /* can only be fixed buffers, no need to do anything */
- if (iov_iter_is_bvec(iter))
- return;
- if (!iovec) {
- unsigned iov_off = 0;
-
- rw->s.iter.iov = rw->s.fast_iov;
- if (iter->iov != fast_iov) {
- iov_off = iter->iov - fast_iov;
- rw->s.iter.iov += iov_off;
- }
- if (rw->s.fast_iov != fast_iov)
- memcpy(rw->s.fast_iov + iov_off, fast_iov + iov_off,
- sizeof(struct iovec) * iter->nr_segs);
- } else {
- req->flags |= REQ_F_NEED_CLEANUP;
- }
-}
-
-static inline bool io_alloc_async_data(struct io_kiocb *req)
-{
- WARN_ON_ONCE(!io_op_defs[req->opcode].async_size);
- req->async_data = kmalloc(io_op_defs[req->opcode].async_size, GFP_KERNEL);
- if (req->async_data) {
- req->flags |= REQ_F_ASYNC_DATA;
- return false;
- }
- return true;
-}
-
-static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec,
- struct io_rw_state *s, bool force)
-{
- if (!force && !io_op_defs[req->opcode].needs_async_setup)
- return 0;
- if (!req_has_async_data(req)) {
- struct io_async_rw *iorw;
-
- if (io_alloc_async_data(req)) {
- kfree(iovec);
- return -ENOMEM;
- }
-
- io_req_map_rw(req, iovec, s->fast_iov, &s->iter);
- iorw = req->async_data;
- /* we've copied and mapped the iter, ensure state is saved */
- iov_iter_save_state(&iorw->s.iter, &iorw->s.iter_state);
- }
- return 0;
-}
-
-static inline int io_rw_prep_async(struct io_kiocb *req, int rw)
-{
- struct io_async_rw *iorw = req->async_data;
- struct iovec *iov;
- int ret;
-
- /* submission path, ->uring_lock should already be taken */
- ret = io_import_iovec(rw, req, &iov, &iorw->s, 0);
- if (unlikely(ret < 0))
- return ret;
-
- iorw->bytes_done = 0;
- iorw->free_iovec = iov;
- if (iov)
- req->flags |= REQ_F_NEED_CLEANUP;
- return 0;
-}
-
-static int io_readv_prep_async(struct io_kiocb *req)
-{
- return io_rw_prep_async(req, READ);
-}
-
-static int io_writev_prep_async(struct io_kiocb *req)
-{
- return io_rw_prep_async(req, WRITE);
-}
-
-/*
- * This is our waitqueue callback handler, registered through __folio_lock_async()
- * when we initially tried to do the IO with the iocb armed our waitqueue.
- * This gets called when the page is unlocked, and we generally expect that to
- * happen when the page IO is completed and the page is now uptodate. This will
- * queue a task_work based retry of the operation, attempting to copy the data
- * again. If the latter fails because the page was NOT uptodate, then we will
- * do a thread based blocking retry of the operation. That's the unexpected
- * slow path.
- */
-static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode,
- int sync, void *arg)
-{
- struct wait_page_queue *wpq;
- struct io_kiocb *req = wait->private;
- struct wait_page_key *key = arg;
-
- wpq = container_of(wait, struct wait_page_queue, wait);
-
- if (!wake_page_match(wpq, key))
- return 0;
-
- req->rw.kiocb.ki_flags &= ~IOCB_WAITQ;
- list_del_init(&wait->entry);
- io_req_task_queue(req);
- return 1;
-}
-
-/*
- * This controls whether a given IO request should be armed for async page
- * based retry. If we return false here, the request is handed to the async
- * worker threads for retry. If we're doing buffered reads on a regular file,
- * we prepare a private wait_page_queue entry and retry the operation. This
- * will either succeed because the page is now uptodate and unlocked, or it
- * will register a callback when the page is unlocked at IO completion. Through
- * that callback, io_uring uses task_work to setup a retry of the operation.
- * That retry will attempt the buffered read again. The retry will generally
- * succeed, or in rare cases where it fails, we then fall back to using the
- * async worker threads for a blocking retry.
- */
-static bool io_rw_should_retry(struct io_kiocb *req)
-{
- struct io_async_rw *rw = req->async_data;
- struct wait_page_queue *wait = &rw->wpq;
- struct kiocb *kiocb = &req->rw.kiocb;
-
- /* never retry for NOWAIT, we just complete with -EAGAIN */
- if (req->flags & REQ_F_NOWAIT)
- return false;
-
- /* Only for buffered IO */
- if (kiocb->ki_flags & (IOCB_DIRECT | IOCB_HIPRI))
- return false;
-
- /*
- * just use poll if we can, and don't attempt if the fs doesn't
- * support callback based unlocks
- */
- if (file_can_poll(req->file) || !(req->file->f_mode & FMODE_BUF_RASYNC))
- return false;
-
- wait->wait.func = io_async_buf_func;
- wait->wait.private = req;
- wait->wait.flags = 0;
- INIT_LIST_HEAD(&wait->wait.entry);
- kiocb->ki_flags |= IOCB_WAITQ;
- kiocb->ki_flags &= ~IOCB_NOWAIT;
- kiocb->ki_waitq = wait;
- return true;
-}
-
-static inline int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter)
-{
- if (likely(req->file->f_op->read_iter))
- return call_read_iter(req->file, &req->rw.kiocb, iter);
- else if (req->file->f_op->read)
- return loop_rw_iter(READ, req, iter);
- else
- return -EINVAL;
-}
-
-static bool need_read_all(struct io_kiocb *req)
-{
- return req->flags & REQ_F_ISREG ||
- S_ISBLK(file_inode(req->file)->i_mode);
-}
-
-static int io_rw_init_file(struct io_kiocb *req, fmode_t mode)
-{
- struct kiocb *kiocb = &req->rw.kiocb;
- struct io_ring_ctx *ctx = req->ctx;
- struct file *file = req->file;
- int ret;
-
- if (unlikely(!file || !(file->f_mode & mode)))
- return -EBADF;
-
- if (!io_req_ffs_set(req))
- req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT;
-
- kiocb->ki_flags = iocb_flags(file);
- ret = kiocb_set_rw_flags(kiocb, req->rw.flags);
- if (unlikely(ret))
- return ret;
-
- /*
- * If the file is marked O_NONBLOCK, still allow retry for it if it
- * supports async. Otherwise it's impossible to use O_NONBLOCK files
- * reliably. If not, or it IOCB_NOWAIT is set, don't retry.
- */
- if ((kiocb->ki_flags & IOCB_NOWAIT) ||
- ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req)))
- req->flags |= REQ_F_NOWAIT;
-
- if (ctx->flags & IORING_SETUP_IOPOLL) {
- if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll)
- return -EOPNOTSUPP;
-
- kiocb->private = NULL;
- kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE;
- kiocb->ki_complete = io_complete_rw_iopoll;
- req->iopoll_completed = 0;
- } else {
- if (kiocb->ki_flags & IOCB_HIPRI)
- return -EINVAL;
- kiocb->ki_complete = io_complete_rw;
- }
-
- return 0;
-}
-
-static int io_read(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_rw_state __s, *s = &__s;
- struct iovec *iovec;
- struct kiocb *kiocb = &req->rw.kiocb;
- bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
- struct io_async_rw *rw;
- ssize_t ret, ret2;
- loff_t *ppos;
-
- if (!req_has_async_data(req)) {
- ret = io_import_iovec(READ, req, &iovec, s, issue_flags);
- if (unlikely(ret < 0))
- return ret;
- } else {
- rw = req->async_data;
- s = &rw->s;
-
- /*
- * Safe and required to re-import if we're using provided
- * buffers, as we dropped the selected one before retry.
- */
- if (io_do_buffer_select(req)) {
- ret = io_import_iovec(READ, req, &iovec, s, issue_flags);
- if (unlikely(ret < 0))
- return ret;
- }
-
- /*
- * We come here from an earlier attempt, restore our state to
- * match in case it doesn't. It's cheap enough that we don't
- * need to make this conditional.
- */
- iov_iter_restore(&s->iter, &s->iter_state);
- iovec = NULL;
- }
- ret = io_rw_init_file(req, FMODE_READ);
- if (unlikely(ret)) {
- kfree(iovec);
- return ret;
- }
- req->cqe.res = iov_iter_count(&s->iter);
-
- if (force_nonblock) {
- /* If the file doesn't support async, just async punt */
- if (unlikely(!io_file_supports_nowait(req))) {
- ret = io_setup_async_rw(req, iovec, s, true);
- return ret ?: -EAGAIN;
- }
- kiocb->ki_flags |= IOCB_NOWAIT;
- } else {
- /* Ensure we clear previously set non-block flag */
- kiocb->ki_flags &= ~IOCB_NOWAIT;
- }
-
- ppos = io_kiocb_update_pos(req);
-
- ret = rw_verify_area(READ, req->file, ppos, req->cqe.res);
- if (unlikely(ret)) {
- kfree(iovec);
- return ret;
- }
-
- ret = io_iter_do_read(req, &s->iter);
-
- if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) {
- req->flags &= ~REQ_F_REISSUE;
- /* if we can poll, just do that */
- if (req->opcode == IORING_OP_READ && file_can_poll(req->file))
- return -EAGAIN;
- /* IOPOLL retry should happen for io-wq threads */
- if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL))
- goto done;
- /* no retry on NONBLOCK nor RWF_NOWAIT */
- if (req->flags & REQ_F_NOWAIT)
- goto done;
- ret = 0;
- } else if (ret == -EIOCBQUEUED) {
- goto out_free;
- } else if (ret == req->cqe.res || ret <= 0 || !force_nonblock ||
- (req->flags & REQ_F_NOWAIT) || !need_read_all(req)) {
- /* read all, failed, already did sync or don't want to retry */
- goto done;
- }
-
- /*
- * Don't depend on the iter state matching what was consumed, or being
- * untouched in case of error. Restore it and we'll advance it
- * manually if we need to.
- */
- iov_iter_restore(&s->iter, &s->iter_state);
-
- ret2 = io_setup_async_rw(req, iovec, s, true);
- if (ret2)
- return ret2;
-
- iovec = NULL;
- rw = req->async_data;
- s = &rw->s;
- /*
- * Now use our persistent iterator and state, if we aren't already.
- * We've restored and mapped the iter to match.
- */
-
- do {
- /*
- * We end up here because of a partial read, either from
- * above or inside this loop. Advance the iter by the bytes
- * that were consumed.
- */
- iov_iter_advance(&s->iter, ret);
- if (!iov_iter_count(&s->iter))
- break;
- rw->bytes_done += ret;
- iov_iter_save_state(&s->iter, &s->iter_state);
-
- /* if we can retry, do so with the callbacks armed */
- if (!io_rw_should_retry(req)) {
- kiocb->ki_flags &= ~IOCB_WAITQ;
- return -EAGAIN;
- }
-
- /*
- * Now retry read with the IOCB_WAITQ parts set in the iocb. If
- * we get -EIOCBQUEUED, then we'll get a notification when the
- * desired page gets unlocked. We can also get a partial read
- * here, and if we do, then just retry at the new offset.
- */
- ret = io_iter_do_read(req, &s->iter);
- if (ret == -EIOCBQUEUED)
- return 0;
- /* we got some bytes, but not all. retry. */
- kiocb->ki_flags &= ~IOCB_WAITQ;
- iov_iter_restore(&s->iter, &s->iter_state);
- } while (ret > 0);
-done:
- kiocb_done(req, ret, issue_flags);
-out_free:
- /* it's faster to check here then delegate to kfree */
- if (iovec)
- kfree(iovec);
- return 0;
-}
-
-static int io_write(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_rw_state __s, *s = &__s;
- struct iovec *iovec;
- struct kiocb *kiocb = &req->rw.kiocb;
- bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
- ssize_t ret, ret2;
- loff_t *ppos;
-
- if (!req_has_async_data(req)) {
- ret = io_import_iovec(WRITE, req, &iovec, s, issue_flags);
- if (unlikely(ret < 0))
- return ret;
- } else {
- struct io_async_rw *rw = req->async_data;
-
- s = &rw->s;
- iov_iter_restore(&s->iter, &s->iter_state);
- iovec = NULL;
- }
- ret = io_rw_init_file(req, FMODE_WRITE);
- if (unlikely(ret)) {
- kfree(iovec);
- return ret;
- }
- req->cqe.res = iov_iter_count(&s->iter);
-
- if (force_nonblock) {
- /* If the file doesn't support async, just async punt */
- if (unlikely(!io_file_supports_nowait(req)))
- goto copy_iov;
-
- /* file path doesn't support NOWAIT for non-direct_IO */
- if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT) &&
- (req->flags & REQ_F_ISREG))
- goto copy_iov;
-
- kiocb->ki_flags |= IOCB_NOWAIT;
- } else {
- /* Ensure we clear previously set non-block flag */
- kiocb->ki_flags &= ~IOCB_NOWAIT;
- }
-
- ppos = io_kiocb_update_pos(req);
-
- ret = rw_verify_area(WRITE, req->file, ppos, req->cqe.res);
- if (unlikely(ret))
- goto out_free;
-
- /*
- * Open-code file_start_write here to grab freeze protection,
- * which will be released by another thread in
- * io_complete_rw(). Fool lockdep by telling it the lock got
- * released so that it doesn't complain about the held lock when
- * we return to userspace.
- */
- if (req->flags & REQ_F_ISREG) {
- sb_start_write(file_inode(req->file)->i_sb);
- __sb_writers_release(file_inode(req->file)->i_sb,
- SB_FREEZE_WRITE);
- }
- kiocb->ki_flags |= IOCB_WRITE;
-
- if (likely(req->file->f_op->write_iter))
- ret2 = call_write_iter(req->file, kiocb, &s->iter);
- else if (req->file->f_op->write)
- ret2 = loop_rw_iter(WRITE, req, &s->iter);
- else
- ret2 = -EINVAL;
-
- if (req->flags & REQ_F_REISSUE) {
- req->flags &= ~REQ_F_REISSUE;
- ret2 = -EAGAIN;
- }
-
- /*
- * Raw bdev writes will return -EOPNOTSUPP for IOCB_NOWAIT. Just
- * retry them without IOCB_NOWAIT.
- */
- if (ret2 == -EOPNOTSUPP && (kiocb->ki_flags & IOCB_NOWAIT))
- ret2 = -EAGAIN;
- /* no retry on NONBLOCK nor RWF_NOWAIT */
- if (ret2 == -EAGAIN && (req->flags & REQ_F_NOWAIT))
- goto done;
- if (!force_nonblock || ret2 != -EAGAIN) {
- /* IOPOLL retry should happen for io-wq threads */
- if (ret2 == -EAGAIN && (req->ctx->flags & IORING_SETUP_IOPOLL))
- goto copy_iov;
-done:
- kiocb_done(req, ret2, issue_flags);
- } else {
-copy_iov:
- iov_iter_restore(&s->iter, &s->iter_state);
- ret = io_setup_async_rw(req, iovec, s, false);
- return ret ?: -EAGAIN;
- }
-out_free:
- /* it's reportedly faster than delegating the null check to kfree() */
- if (iovec)
- kfree(iovec);
- return ret;
-}
-
-static int io_renameat_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- struct io_rename *ren = &req->rename;
- const char __user *oldf, *newf;
-
- if (sqe->buf_index || sqe->splice_fd_in)
- return -EINVAL;
- if (unlikely(req->flags & REQ_F_FIXED_FILE))
- return -EBADF;
-
- ren->old_dfd = READ_ONCE(sqe->fd);
- oldf = u64_to_user_ptr(READ_ONCE(sqe->addr));
- newf = u64_to_user_ptr(READ_ONCE(sqe->addr2));
- ren->new_dfd = READ_ONCE(sqe->len);
- ren->flags = READ_ONCE(sqe->rename_flags);
-
- ren->oldpath = getname(oldf);
- if (IS_ERR(ren->oldpath))
- return PTR_ERR(ren->oldpath);
-
- ren->newpath = getname(newf);
- if (IS_ERR(ren->newpath)) {
- putname(ren->oldpath);
- return PTR_ERR(ren->newpath);
- }
-
- req->flags |= REQ_F_NEED_CLEANUP;
- return 0;
-}
-
-static int io_renameat(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_rename *ren = &req->rename;
- int ret;
-
- if (issue_flags & IO_URING_F_NONBLOCK)
- return -EAGAIN;
-
- ret = do_renameat2(ren->old_dfd, ren->oldpath, ren->new_dfd,
- ren->newpath, ren->flags);
-
- req->flags &= ~REQ_F_NEED_CLEANUP;
- io_req_complete(req, ret);
- return 0;
-}
-
-static inline void __io_xattr_finish(struct io_kiocb *req)
-{
- struct io_xattr *ix = &req->xattr;
-
- if (ix->filename)
- putname(ix->filename);
-
- kfree(ix->ctx.kname);
- kvfree(ix->ctx.kvalue);
-}
-
-static void io_xattr_finish(struct io_kiocb *req, int ret)
-{
- req->flags &= ~REQ_F_NEED_CLEANUP;
-
- __io_xattr_finish(req);
- io_req_complete(req, ret);
-}
-
-static int __io_getxattr_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- struct io_xattr *ix = &req->xattr;
- const char __user *name;
- int ret;
-
- if (unlikely(req->flags & REQ_F_FIXED_FILE))
- return -EBADF;
-
- ix->filename = NULL;
- ix->ctx.kvalue = NULL;
- name = u64_to_user_ptr(READ_ONCE(sqe->addr));
- ix->ctx.cvalue = u64_to_user_ptr(READ_ONCE(sqe->addr2));
- ix->ctx.size = READ_ONCE(sqe->len);
- ix->ctx.flags = READ_ONCE(sqe->xattr_flags);
-
- if (ix->ctx.flags)
- return -EINVAL;
-
- ix->ctx.kname = kmalloc(sizeof(*ix->ctx.kname), GFP_KERNEL);
- if (!ix->ctx.kname)
- return -ENOMEM;
-
- ret = strncpy_from_user(ix->ctx.kname->name, name,
- sizeof(ix->ctx.kname->name));
- if (!ret || ret == sizeof(ix->ctx.kname->name))
- ret = -ERANGE;
- if (ret < 0) {
- kfree(ix->ctx.kname);
- return ret;
- }
-
- req->flags |= REQ_F_NEED_CLEANUP;
- return 0;
-}
-
-static int io_fgetxattr_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- return __io_getxattr_prep(req, sqe);
-}
-
-static int io_getxattr_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- struct io_xattr *ix = &req->xattr;
- const char __user *path;
- int ret;
-
- ret = __io_getxattr_prep(req, sqe);
- if (ret)
- return ret;
-
- path = u64_to_user_ptr(READ_ONCE(sqe->addr3));
-
- ix->filename = getname_flags(path, LOOKUP_FOLLOW, NULL);
- if (IS_ERR(ix->filename)) {
- ret = PTR_ERR(ix->filename);
- ix->filename = NULL;
- }
-
- return ret;
-}
-
-static int io_fgetxattr(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_xattr *ix = &req->xattr;
- int ret;
-
- if (issue_flags & IO_URING_F_NONBLOCK)
- return -EAGAIN;
-
- ret = do_getxattr(mnt_user_ns(req->file->f_path.mnt),
- req->file->f_path.dentry,
- &ix->ctx);
-
- io_xattr_finish(req, ret);
- return 0;
-}
-
-static int io_getxattr(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_xattr *ix = &req->xattr;
- unsigned int lookup_flags = LOOKUP_FOLLOW;
- struct path path;
- int ret;
-
- if (issue_flags & IO_URING_F_NONBLOCK)
- return -EAGAIN;
-
-retry:
- ret = filename_lookup(AT_FDCWD, ix->filename, lookup_flags, &path, NULL);
- if (!ret) {
- ret = do_getxattr(mnt_user_ns(path.mnt),
- path.dentry,
- &ix->ctx);
-
- path_put(&path);
- if (retry_estale(ret, lookup_flags)) {
- lookup_flags |= LOOKUP_REVAL;
- goto retry;
- }
- }
-
- io_xattr_finish(req, ret);
- return 0;
-}
-
-static int __io_setxattr_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- struct io_xattr *ix = &req->xattr;
- const char __user *name;
- int ret;
-
- if (unlikely(req->flags & REQ_F_FIXED_FILE))
- return -EBADF;
-
- ix->filename = NULL;
- name = u64_to_user_ptr(READ_ONCE(sqe->addr));
- ix->ctx.cvalue = u64_to_user_ptr(READ_ONCE(sqe->addr2));
- ix->ctx.kvalue = NULL;
- ix->ctx.size = READ_ONCE(sqe->len);
- ix->ctx.flags = READ_ONCE(sqe->xattr_flags);
-
- ix->ctx.kname = kmalloc(sizeof(*ix->ctx.kname), GFP_KERNEL);
- if (!ix->ctx.kname)
- return -ENOMEM;
-
- ret = setxattr_copy(name, &ix->ctx);
- if (ret) {
- kfree(ix->ctx.kname);
- return ret;
- }
-
- req->flags |= REQ_F_NEED_CLEANUP;
- return 0;
-}
-
-static int io_setxattr_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- struct io_xattr *ix = &req->xattr;
- const char __user *path;
- int ret;
-
- ret = __io_setxattr_prep(req, sqe);
- if (ret)
- return ret;
-
- path = u64_to_user_ptr(READ_ONCE(sqe->addr3));
-
- ix->filename = getname_flags(path, LOOKUP_FOLLOW, NULL);
- if (IS_ERR(ix->filename)) {
- ret = PTR_ERR(ix->filename);
- ix->filename = NULL;
- }
-
- return ret;
-}
-
-static int io_fsetxattr_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- return __io_setxattr_prep(req, sqe);
-}
-
-static int __io_setxattr(struct io_kiocb *req, unsigned int issue_flags,
- struct path *path)
-{
- struct io_xattr *ix = &req->xattr;
- int ret;
-
- ret = mnt_want_write(path->mnt);
- if (!ret) {
- ret = do_setxattr(mnt_user_ns(path->mnt), path->dentry, &ix->ctx);
- mnt_drop_write(path->mnt);
- }
-
- return ret;
-}
-
-static int io_fsetxattr(struct io_kiocb *req, unsigned int issue_flags)
-{
- int ret;
-
- if (issue_flags & IO_URING_F_NONBLOCK)
- return -EAGAIN;
-
- ret = __io_setxattr(req, issue_flags, &req->file->f_path);
- io_xattr_finish(req, ret);
-
- return 0;
-}
-
-static int io_setxattr(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_xattr *ix = &req->xattr;
- unsigned int lookup_flags = LOOKUP_FOLLOW;
- struct path path;
- int ret;
-
- if (issue_flags & IO_URING_F_NONBLOCK)
- return -EAGAIN;
-
-retry:
- ret = filename_lookup(AT_FDCWD, ix->filename, lookup_flags, &path, NULL);
- if (!ret) {
- ret = __io_setxattr(req, issue_flags, &path);
- path_put(&path);
- if (retry_estale(ret, lookup_flags)) {
- lookup_flags |= LOOKUP_REVAL;
- goto retry;
- }
- }
-
- io_xattr_finish(req, ret);
- return 0;
-}
-
-static int io_unlinkat_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- struct io_unlink *un = &req->unlink;
- const char __user *fname;
-
- if (sqe->off || sqe->len || sqe->buf_index || sqe->splice_fd_in)
- return -EINVAL;
- if (unlikely(req->flags & REQ_F_FIXED_FILE))
- return -EBADF;
-
- un->dfd = READ_ONCE(sqe->fd);
-
- un->flags = READ_ONCE(sqe->unlink_flags);
- if (un->flags & ~AT_REMOVEDIR)
- return -EINVAL;
-
- fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
- un->filename = getname(fname);
- if (IS_ERR(un->filename))
- return PTR_ERR(un->filename);
-
- req->flags |= REQ_F_NEED_CLEANUP;
- return 0;
-}
-
-static int io_unlinkat(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_unlink *un = &req->unlink;
- int ret;
-
- if (issue_flags & IO_URING_F_NONBLOCK)
- return -EAGAIN;
-
- if (un->flags & AT_REMOVEDIR)
- ret = do_rmdir(un->dfd, un->filename);
- else
- ret = do_unlinkat(un->dfd, un->filename);
-
- req->flags &= ~REQ_F_NEED_CLEANUP;
- io_req_complete(req, ret);
- return 0;
-}
-
-static int io_mkdirat_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- struct io_mkdir *mkd = &req->mkdir;
- const char __user *fname;
-
- if (sqe->off || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in)
- return -EINVAL;
- if (unlikely(req->flags & REQ_F_FIXED_FILE))
- return -EBADF;
-
- mkd->dfd = READ_ONCE(sqe->fd);
- mkd->mode = READ_ONCE(sqe->len);
-
- fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
- mkd->filename = getname(fname);
- if (IS_ERR(mkd->filename))
- return PTR_ERR(mkd->filename);
-
- req->flags |= REQ_F_NEED_CLEANUP;
- return 0;
-}
-
-static int io_mkdirat(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_mkdir *mkd = &req->mkdir;
- int ret;
-
- if (issue_flags & IO_URING_F_NONBLOCK)
- return -EAGAIN;
-
- ret = do_mkdirat(mkd->dfd, mkd->filename, mkd->mode);
-
- req->flags &= ~REQ_F_NEED_CLEANUP;
- io_req_complete(req, ret);
- return 0;
-}
-
-static int io_symlinkat_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- struct io_symlink *sl = &req->symlink;
- const char __user *oldpath, *newpath;
-
- if (sqe->len || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in)
- return -EINVAL;
- if (unlikely(req->flags & REQ_F_FIXED_FILE))
- return -EBADF;
-
- sl->new_dfd = READ_ONCE(sqe->fd);
- oldpath = u64_to_user_ptr(READ_ONCE(sqe->addr));
- newpath = u64_to_user_ptr(READ_ONCE(sqe->addr2));
-
- sl->oldpath = getname(oldpath);
- if (IS_ERR(sl->oldpath))
- return PTR_ERR(sl->oldpath);
-
- sl->newpath = getname(newpath);
- if (IS_ERR(sl->newpath)) {
- putname(sl->oldpath);
- return PTR_ERR(sl->newpath);
- }
-
- req->flags |= REQ_F_NEED_CLEANUP;
- return 0;
-}
-
-static int io_symlinkat(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_symlink *sl = &req->symlink;
- int ret;
-
- if (issue_flags & IO_URING_F_NONBLOCK)
- return -EAGAIN;
-
- ret = do_symlinkat(sl->oldpath, sl->new_dfd, sl->newpath);
-
- req->flags &= ~REQ_F_NEED_CLEANUP;
- io_req_complete(req, ret);
- return 0;
-}
-
-static int io_linkat_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- struct io_hardlink *lnk = &req->hardlink;
- const char __user *oldf, *newf;
-
- if (sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in)
- return -EINVAL;
- if (unlikely(req->flags & REQ_F_FIXED_FILE))
- return -EBADF;
-
- lnk->old_dfd = READ_ONCE(sqe->fd);
- lnk->new_dfd = READ_ONCE(sqe->len);
- oldf = u64_to_user_ptr(READ_ONCE(sqe->addr));
- newf = u64_to_user_ptr(READ_ONCE(sqe->addr2));
- lnk->flags = READ_ONCE(sqe->hardlink_flags);
-
- lnk->oldpath = getname(oldf);
- if (IS_ERR(lnk->oldpath))
- return PTR_ERR(lnk->oldpath);
-
- lnk->newpath = getname(newf);
- if (IS_ERR(lnk->newpath)) {
- putname(lnk->oldpath);
- return PTR_ERR(lnk->newpath);
- }
-
- req->flags |= REQ_F_NEED_CLEANUP;
- return 0;
-}
-
-static int io_linkat(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_hardlink *lnk = &req->hardlink;
- int ret;
-
- if (issue_flags & IO_URING_F_NONBLOCK)
- return -EAGAIN;
-
- ret = do_linkat(lnk->old_dfd, lnk->oldpath, lnk->new_dfd,
- lnk->newpath, lnk->flags);
-
- req->flags &= ~REQ_F_NEED_CLEANUP;
- io_req_complete(req, ret);
- return 0;
-}
-
-static void io_uring_cmd_work(struct io_kiocb *req, bool *locked)
-{
- req->uring_cmd.task_work_cb(&req->uring_cmd);
-}
-
-void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
- void (*task_work_cb)(struct io_uring_cmd *))
-{
- struct io_kiocb *req = container_of(ioucmd, struct io_kiocb, uring_cmd);
-
- req->uring_cmd.task_work_cb = task_work_cb;
- req->io_task_work.func = io_uring_cmd_work;
- io_req_task_work_add(req);
-}
-EXPORT_SYMBOL_GPL(io_uring_cmd_complete_in_task);
-
-static inline void io_req_set_cqe32_extra(struct io_kiocb *req,
- u64 extra1, u64 extra2)
-{
- req->extra1 = extra1;
- req->extra2 = extra2;
- req->flags |= REQ_F_CQE32_INIT;
-}
-
-/*
- * Called by consumers of io_uring_cmd, if they originally returned
- * -EIOCBQUEUED upon receiving the command.
- */
-void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2)
-{
- struct io_kiocb *req = container_of(ioucmd, struct io_kiocb, uring_cmd);
-
- if (ret < 0)
- req_set_fail(req);
-
- if (req->ctx->flags & IORING_SETUP_CQE32)
- io_req_set_cqe32_extra(req, res2, 0);
- io_req_complete(req, ret);
-}
-EXPORT_SYMBOL_GPL(io_uring_cmd_done);
-
-static int io_uring_cmd_prep_async(struct io_kiocb *req)
-{
- size_t cmd_size;
-
- cmd_size = uring_cmd_pdu_size(req->ctx->flags & IORING_SETUP_SQE128);
-
- memcpy(req->async_data, req->uring_cmd.cmd, cmd_size);
- return 0;
-}
-
-static int io_uring_cmd_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- struct io_uring_cmd *ioucmd = &req->uring_cmd;
-
- if (sqe->rw_flags || sqe->__pad1)
- return -EINVAL;
- ioucmd->cmd = sqe->cmd;
- ioucmd->cmd_op = READ_ONCE(sqe->cmd_op);
- return 0;
-}
-
-static int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_uring_cmd *ioucmd = &req->uring_cmd;
- struct io_ring_ctx *ctx = req->ctx;
- struct file *file = req->file;
- int ret;
-
- if (!req->file->f_op->uring_cmd)
- return -EOPNOTSUPP;
-
- if (ctx->flags & IORING_SETUP_SQE128)
- issue_flags |= IO_URING_F_SQE128;
- if (ctx->flags & IORING_SETUP_CQE32)
- issue_flags |= IO_URING_F_CQE32;
- if (ctx->flags & IORING_SETUP_IOPOLL)
- issue_flags |= IO_URING_F_IOPOLL;
-
- if (req_has_async_data(req))
- ioucmd->cmd = req->async_data;
-
- ret = file->f_op->uring_cmd(ioucmd, issue_flags);
- if (ret == -EAGAIN) {
- if (!req_has_async_data(req)) {
- if (io_alloc_async_data(req))
- return -ENOMEM;
- io_uring_cmd_prep_async(req);
- }
- return -EAGAIN;
- }
-
- if (ret != -EIOCBQUEUED)
- io_uring_cmd_done(ioucmd, ret, 0);
- return 0;
-}
-
-static int __io_splice_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- struct io_splice *sp = &req->splice;
- unsigned int valid_flags = SPLICE_F_FD_IN_FIXED | SPLICE_F_ALL;
-
- sp->len = READ_ONCE(sqe->len);
- sp->flags = READ_ONCE(sqe->splice_flags);
- if (unlikely(sp->flags & ~valid_flags))
- return -EINVAL;
- sp->splice_fd_in = READ_ONCE(sqe->splice_fd_in);
- return 0;
-}
-
-static int io_tee_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- if (READ_ONCE(sqe->splice_off_in) || READ_ONCE(sqe->off))
- return -EINVAL;
- return __io_splice_prep(req, sqe);
-}
-
-static int io_tee(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_splice *sp = &req->splice;
- struct file *out = sp->file_out;
- unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
- struct file *in;
- long ret = 0;
-
- if (issue_flags & IO_URING_F_NONBLOCK)
- return -EAGAIN;
-
- if (sp->flags & SPLICE_F_FD_IN_FIXED)
- in = io_file_get_fixed(req, sp->splice_fd_in, issue_flags);
- else
- in = io_file_get_normal(req, sp->splice_fd_in);
- if (!in) {
- ret = -EBADF;
- goto done;
- }
-
- if (sp->len)
- ret = do_tee(in, out, sp->len, flags);
-
- if (!(sp->flags & SPLICE_F_FD_IN_FIXED))
- io_put_file(in);
-done:
- if (ret != sp->len)
- req_set_fail(req);
- __io_req_complete(req, 0, ret, 0);
- return 0;
-}
-
-static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
- struct io_splice *sp = &req->splice;
-
- sp->off_in = READ_ONCE(sqe->splice_off_in);
- sp->off_out = READ_ONCE(sqe->off);
- return __io_splice_prep(req, sqe);
-}
-
-static int io_splice(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_splice *sp = &req->splice;
- struct file *out = sp->file_out;
- unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
- loff_t *poff_in, *poff_out;
- struct file *in;
- long ret = 0;
-
- if (issue_flags & IO_URING_F_NONBLOCK)
- return -EAGAIN;
-
- if (sp->flags & SPLICE_F_FD_IN_FIXED)
- in = io_file_get_fixed(req, sp->splice_fd_in, issue_flags);
- else
- in = io_file_get_normal(req, sp->splice_fd_in);
- if (!in) {
- ret = -EBADF;
- goto done;
- }
-
- poff_in = (sp->off_in == -1) ? NULL : &sp->off_in;
- poff_out = (sp->off_out == -1) ? NULL : &sp->off_out;
-
- if (sp->len)
- ret = do_splice(in, poff_in, out, poff_out, sp->len, flags);
-
- if (!(sp->flags & SPLICE_F_FD_IN_FIXED))
- io_put_file(in);
-done:
- if (ret != sp->len)
- req_set_fail(req);
- __io_req_complete(req, 0, ret, 0);
- return 0;
-}
-
-static int io_nop_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
- return 0;
-}
-
-/*
- * IORING_OP_NOP just posts a completion event, nothing else.
- */
-static int io_nop(struct io_kiocb *req, unsigned int issue_flags)
-{
- __io_req_complete(req, issue_flags, 0, 0);
- return 0;
-}
-
-static int io_msg_ring_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- if (unlikely(sqe->addr || sqe->rw_flags || sqe->splice_fd_in ||
- sqe->buf_index || sqe->personality))
- return -EINVAL;
-
- req->msg.user_data = READ_ONCE(sqe->off);
- req->msg.len = READ_ONCE(sqe->len);
- return 0;
-}
-
-static int io_msg_ring(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_ring_ctx *target_ctx;
- struct io_msg *msg = &req->msg;
- bool filled;
- int ret;
-
- ret = -EBADFD;
- if (req->file->f_op != &io_uring_fops)
- goto done;
-
- ret = -EOVERFLOW;
- target_ctx = req->file->private_data;
-
- spin_lock(&target_ctx->completion_lock);
- filled = io_fill_cqe_aux(target_ctx, msg->user_data, msg->len, 0);
- io_commit_cqring(target_ctx);
- spin_unlock(&target_ctx->completion_lock);
-
- if (filled) {
- io_cqring_ev_posted(target_ctx);
- ret = 0;
- }
-
-done:
- if (ret < 0)
- req_set_fail(req);
- __io_req_complete(req, issue_flags, ret, 0);
- /* put file to avoid an attempt to IOPOLL the req */
- io_put_file(req->file);
- req->file = NULL;
- return 0;
-}
-
-static int io_fsync_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
- if (unlikely(sqe->addr || sqe->buf_index || sqe->splice_fd_in))
- return -EINVAL;
-
- req->sync.flags = READ_ONCE(sqe->fsync_flags);
- if (unlikely(req->sync.flags & ~IORING_FSYNC_DATASYNC))
- return -EINVAL;
-
- req->sync.off = READ_ONCE(sqe->off);
- req->sync.len = READ_ONCE(sqe->len);
- return 0;
-}
-
-static int io_fsync(struct io_kiocb *req, unsigned int issue_flags)
-{
- loff_t end = req->sync.off + req->sync.len;
- int ret;
-
- /* fsync always requires a blocking context */
- if (issue_flags & IO_URING_F_NONBLOCK)
- return -EAGAIN;
-
- ret = vfs_fsync_range(req->file, req->sync.off,
- end > 0 ? end : LLONG_MAX,
- req->sync.flags & IORING_FSYNC_DATASYNC);
- io_req_complete(req, ret);
- return 0;
-}
-
-static int io_fallocate_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- if (sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in)
- return -EINVAL;
-
- req->sync.off = READ_ONCE(sqe->off);
- req->sync.len = READ_ONCE(sqe->addr);
- req->sync.mode = READ_ONCE(sqe->len);
- return 0;
-}
-
-static int io_fallocate(struct io_kiocb *req, unsigned int issue_flags)
-{
- int ret;
-
- /* fallocate always requiring blocking context */
- if (issue_flags & IO_URING_F_NONBLOCK)
- return -EAGAIN;
- ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off,
- req->sync.len);
- if (ret >= 0)
- fsnotify_modify(req->file);
- io_req_complete(req, ret);
- return 0;
-}
-
-static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
- const char __user *fname;
- int ret;
-
- if (unlikely(sqe->buf_index))
- return -EINVAL;
- if (unlikely(req->flags & REQ_F_FIXED_FILE))
- return -EBADF;
-
- /* open.how should be already initialised */
- if (!(req->open.how.flags & O_PATH) && force_o_largefile())
- req->open.how.flags |= O_LARGEFILE;
-
- req->open.dfd = READ_ONCE(sqe->fd);
- fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
- req->open.filename = getname(fname);
- if (IS_ERR(req->open.filename)) {
- ret = PTR_ERR(req->open.filename);
- req->open.filename = NULL;
- return ret;
- }
-
- req->open.file_slot = READ_ONCE(sqe->file_index);
- if (req->open.file_slot && (req->open.how.flags & O_CLOEXEC))
- return -EINVAL;
-
- req->open.nofile = rlimit(RLIMIT_NOFILE);
- req->flags |= REQ_F_NEED_CLEANUP;
- return 0;
-}
-
-static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
- u64 mode = READ_ONCE(sqe->len);
- u64 flags = READ_ONCE(sqe->open_flags);
-
- req->open.how = build_open_how(flags, mode);
- return __io_openat_prep(req, sqe);
-}
-
-static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
- struct open_how __user *how;
- size_t len;
- int ret;
-
- how = u64_to_user_ptr(READ_ONCE(sqe->addr2));
- len = READ_ONCE(sqe->len);
- if (len < OPEN_HOW_SIZE_VER0)
- return -EINVAL;
-
- ret = copy_struct_from_user(&req->open.how, sizeof(req->open.how), how,
- len);
- if (ret)
- return ret;
-
- return __io_openat_prep(req, sqe);
-}
-
-static int io_file_bitmap_get(struct io_ring_ctx *ctx)
-{
- struct io_file_table *table = &ctx->file_table;
- unsigned long nr = ctx->nr_user_files;
- int ret;
-
- do {
- ret = find_next_zero_bit(table->bitmap, nr, table->alloc_hint);
- if (ret != nr)
- return ret;
-
- if (!table->alloc_hint)
- break;
-
- nr = table->alloc_hint;
- table->alloc_hint = 0;
- } while (1);
-
- return -ENFILE;
-}
-
-/*
- * Note when io_fixed_fd_install() returns error value, it will ensure
- * fput() is called correspondingly.
- */
-static int io_fixed_fd_install(struct io_kiocb *req, unsigned int issue_flags,
- struct file *file, unsigned int file_slot)
-{
- bool alloc_slot = file_slot == IORING_FILE_INDEX_ALLOC;
- struct io_ring_ctx *ctx = req->ctx;
- int ret;
-
- io_ring_submit_lock(ctx, issue_flags);
-
- if (alloc_slot) {
- ret = io_file_bitmap_get(ctx);
- if (unlikely(ret < 0))
- goto err;
- file_slot = ret;
- } else {
- file_slot--;
- }
-
- ret = io_install_fixed_file(req, file, issue_flags, file_slot);
- if (!ret && alloc_slot)
- ret = file_slot;
-err:
- io_ring_submit_unlock(ctx, issue_flags);
- if (unlikely(ret < 0))
- fput(file);
- return ret;
-}
-
-static int io_openat2(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct open_flags op;
- struct file *file;
- bool resolve_nonblock, nonblock_set;
- bool fixed = !!req->open.file_slot;
- int ret;
-
- ret = build_open_flags(&req->open.how, &op);
- if (ret)
- goto err;
- nonblock_set = op.open_flag & O_NONBLOCK;
- resolve_nonblock = req->open.how.resolve & RESOLVE_CACHED;
- if (issue_flags & IO_URING_F_NONBLOCK) {
- /*
- * Don't bother trying for O_TRUNC, O_CREAT, or O_TMPFILE open,
- * it'll always -EAGAIN
- */
- if (req->open.how.flags & (O_TRUNC | O_CREAT | O_TMPFILE))
- return -EAGAIN;
- op.lookup_flags |= LOOKUP_CACHED;
- op.open_flag |= O_NONBLOCK;
- }
-
- if (!fixed) {
- ret = __get_unused_fd_flags(req->open.how.flags, req->open.nofile);
- if (ret < 0)
- goto err;
- }
-
- file = do_filp_open(req->open.dfd, req->open.filename, &op);
- if (IS_ERR(file)) {
- /*
- * We could hang on to this 'fd' on retrying, but seems like
- * marginal gain for something that is now known to be a slower
- * path. So just put it, and we'll get a new one when we retry.
- */
- if (!fixed)
- put_unused_fd(ret);
-
- ret = PTR_ERR(file);
- /* only retry if RESOLVE_CACHED wasn't already set by application */
- if (ret == -EAGAIN &&
- (!resolve_nonblock && (issue_flags & IO_URING_F_NONBLOCK)))
- return -EAGAIN;
- goto err;
- }
-
- if ((issue_flags & IO_URING_F_NONBLOCK) && !nonblock_set)
- file->f_flags &= ~O_NONBLOCK;
- fsnotify_open(file);
-
- if (!fixed)
- fd_install(ret, file);
- else
- ret = io_fixed_fd_install(req, issue_flags, file,
- req->open.file_slot);
-err:
- putname(req->open.filename);
- req->flags &= ~REQ_F_NEED_CLEANUP;
- if (ret < 0)
- req_set_fail(req);
- __io_req_complete(req, issue_flags, ret, 0);
- return 0;
-}
-
-static int io_openat(struct io_kiocb *req, unsigned int issue_flags)
-{
- return io_openat2(req, issue_flags);
-}
-
-static int io_remove_buffers_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- struct io_provide_buf *p = &req->pbuf;
- u64 tmp;
-
- if (sqe->rw_flags || sqe->addr || sqe->len || sqe->off ||
- sqe->splice_fd_in)
- return -EINVAL;
-
- tmp = READ_ONCE(sqe->fd);
- if (!tmp || tmp > USHRT_MAX)
- return -EINVAL;
-
- memset(p, 0, sizeof(*p));
- p->nbufs = tmp;
- p->bgid = READ_ONCE(sqe->buf_group);
- return 0;
-}
-
-static int __io_remove_buffers(struct io_ring_ctx *ctx,
- struct io_buffer_list *bl, unsigned nbufs)
-{
- unsigned i = 0;
-
- /* shouldn't happen */
- if (!nbufs)
- return 0;
-
- if (bl->buf_nr_pages) {
- int j;
-
- i = bl->buf_ring->tail - bl->head;
- for (j = 0; j < bl->buf_nr_pages; j++)
- unpin_user_page(bl->buf_pages[j]);
- kvfree(bl->buf_pages);
- bl->buf_pages = NULL;
- bl->buf_nr_pages = 0;
- /* make sure it's seen as empty */
- INIT_LIST_HEAD(&bl->buf_list);
- return i;
- }
-
- /* the head kbuf is the list itself */
- while (!list_empty(&bl->buf_list)) {
- struct io_buffer *nxt;
-
- nxt = list_first_entry(&bl->buf_list, struct io_buffer, list);
- list_del(&nxt->list);
- if (++i == nbufs)
- return i;
- cond_resched();
- }
- i++;
-
- return i;
-}
-
-static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_provide_buf *p = &req->pbuf;
- struct io_ring_ctx *ctx = req->ctx;
- struct io_buffer_list *bl;
- int ret = 0;
-
- io_ring_submit_lock(ctx, issue_flags);
-
- ret = -ENOENT;
- bl = io_buffer_get_list(ctx, p->bgid);
- if (bl) {
- ret = -EINVAL;
- /* can't use provide/remove buffers command on mapped buffers */
- if (!bl->buf_nr_pages)
- ret = __io_remove_buffers(ctx, bl, p->nbufs);
- }
- if (ret < 0)
- req_set_fail(req);
-
- /* complete before unlock, IOPOLL may need the lock */
- __io_req_complete(req, issue_flags, ret, 0);
- io_ring_submit_unlock(ctx, issue_flags);
- return 0;
-}
-
-static int io_provide_buffers_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- unsigned long size, tmp_check;
- struct io_provide_buf *p = &req->pbuf;
- u64 tmp;
-
- if (sqe->rw_flags || sqe->splice_fd_in)
- return -EINVAL;
-
- tmp = READ_ONCE(sqe->fd);
- if (!tmp || tmp > USHRT_MAX)
- return -E2BIG;
- p->nbufs = tmp;
- p->addr = READ_ONCE(sqe->addr);
- p->len = READ_ONCE(sqe->len);
-
- if (check_mul_overflow((unsigned long)p->len, (unsigned long)p->nbufs,
- &size))
- return -EOVERFLOW;
- if (check_add_overflow((unsigned long)p->addr, size, &tmp_check))
- return -EOVERFLOW;
-
- size = (unsigned long)p->len * p->nbufs;
- if (!access_ok(u64_to_user_ptr(p->addr), size))
- return -EFAULT;
-
- p->bgid = READ_ONCE(sqe->buf_group);
- tmp = READ_ONCE(sqe->off);
- if (tmp > USHRT_MAX)
- return -E2BIG;
- p->bid = tmp;
- return 0;
-}
-
-static int io_refill_buffer_cache(struct io_ring_ctx *ctx)
-{
- struct io_buffer *buf;
- struct page *page;
- int bufs_in_page;
-
- /*
- * Completions that don't happen inline (eg not under uring_lock) will
- * add to ->io_buffers_comp. If we don't have any free buffers, check
- * the completion list and splice those entries first.
- */
- if (!list_empty_careful(&ctx->io_buffers_comp)) {
- spin_lock(&ctx->completion_lock);
- if (!list_empty(&ctx->io_buffers_comp)) {
- list_splice_init(&ctx->io_buffers_comp,
- &ctx->io_buffers_cache);
- spin_unlock(&ctx->completion_lock);
- return 0;
- }
- spin_unlock(&ctx->completion_lock);
- }
-
- /*
- * No free buffers and no completion entries either. Allocate a new
- * page worth of buffer entries and add those to our freelist.
- */
- page = alloc_page(GFP_KERNEL_ACCOUNT);
- if (!page)
- return -ENOMEM;
-
- list_add(&page->lru, &ctx->io_buffers_pages);
-
- buf = page_address(page);
- bufs_in_page = PAGE_SIZE / sizeof(*buf);
- while (bufs_in_page) {
- list_add_tail(&buf->list, &ctx->io_buffers_cache);
- buf++;
- bufs_in_page--;
- }
-
- return 0;
-}
-
-static int io_add_buffers(struct io_ring_ctx *ctx, struct io_provide_buf *pbuf,
- struct io_buffer_list *bl)
-{
- struct io_buffer *buf;
- u64 addr = pbuf->addr;
- int i, bid = pbuf->bid;
-
- for (i = 0; i < pbuf->nbufs; i++) {
- if (list_empty(&ctx->io_buffers_cache) &&
- io_refill_buffer_cache(ctx))
- break;
- buf = list_first_entry(&ctx->io_buffers_cache, struct io_buffer,
- list);
- list_move_tail(&buf->list, &bl->buf_list);
- buf->addr = addr;
- buf->len = min_t(__u32, pbuf->len, MAX_RW_COUNT);
- buf->bid = bid;
- buf->bgid = pbuf->bgid;
- addr += pbuf->len;
- bid++;
- cond_resched();
- }
-
- return i ? 0 : -ENOMEM;
-}
-
-static __cold int io_init_bl_list(struct io_ring_ctx *ctx)
-{
- int i;
-
- ctx->io_bl = kcalloc(BGID_ARRAY, sizeof(struct io_buffer_list),
- GFP_KERNEL);
- if (!ctx->io_bl)
- return -ENOMEM;
-
- for (i = 0; i < BGID_ARRAY; i++) {
- INIT_LIST_HEAD(&ctx->io_bl[i].buf_list);
- ctx->io_bl[i].bgid = i;
- }
-
- return 0;
-}
-
-static int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_provide_buf *p = &req->pbuf;
- struct io_ring_ctx *ctx = req->ctx;
- struct io_buffer_list *bl;
- int ret = 0;
-
- io_ring_submit_lock(ctx, issue_flags);
-
- if (unlikely(p->bgid < BGID_ARRAY && !ctx->io_bl)) {
- ret = io_init_bl_list(ctx);
- if (ret)
- goto err;
- }
-
- bl = io_buffer_get_list(ctx, p->bgid);
- if (unlikely(!bl)) {
- bl = kzalloc(sizeof(*bl), GFP_KERNEL);
- if (!bl) {
- ret = -ENOMEM;
- goto err;
- }
- INIT_LIST_HEAD(&bl->buf_list);
- ret = io_buffer_add_list(ctx, bl, p->bgid);
- if (ret) {
- kfree(bl);
- goto err;
- }
- }
- /* can't add buffers via this command for a mapped buffer ring */
- if (bl->buf_nr_pages) {
- ret = -EINVAL;
- goto err;
- }
-
- ret = io_add_buffers(ctx, p, bl);
-err:
- if (ret < 0)
- req_set_fail(req);
- /* complete before unlock, IOPOLL may need the lock */
- __io_req_complete(req, issue_flags, ret, 0);
- io_ring_submit_unlock(ctx, issue_flags);
- return 0;
-}
-
-static int io_epoll_ctl_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
-#if defined(CONFIG_EPOLL)
- if (sqe->buf_index || sqe->splice_fd_in)
- return -EINVAL;
-
- req->epoll.epfd = READ_ONCE(sqe->fd);
- req->epoll.op = READ_ONCE(sqe->len);
- req->epoll.fd = READ_ONCE(sqe->off);
-
- if (ep_op_has_event(req->epoll.op)) {
- struct epoll_event __user *ev;
-
- ev = u64_to_user_ptr(READ_ONCE(sqe->addr));
- if (copy_from_user(&req->epoll.event, ev, sizeof(*ev)))
- return -EFAULT;
- }
-
- return 0;
-#else
- return -EOPNOTSUPP;
-#endif
-}
-
-static int io_epoll_ctl(struct io_kiocb *req, unsigned int issue_flags)
-{
-#if defined(CONFIG_EPOLL)
- struct io_epoll *ie = &req->epoll;
- int ret;
- bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
-
- ret = do_epoll_ctl(ie->epfd, ie->op, ie->fd, &ie->event, force_nonblock);
- if (force_nonblock && ret == -EAGAIN)
- return -EAGAIN;
-
- if (ret < 0)
- req_set_fail(req);
- __io_req_complete(req, issue_flags, ret, 0);
- return 0;
-#else
- return -EOPNOTSUPP;
-#endif
-}
-
-static int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
-#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU)
- if (sqe->buf_index || sqe->off || sqe->splice_fd_in)
- return -EINVAL;
-
- req->madvise.addr = READ_ONCE(sqe->addr);
- req->madvise.len = READ_ONCE(sqe->len);
- req->madvise.advice = READ_ONCE(sqe->fadvise_advice);
- return 0;
-#else
- return -EOPNOTSUPP;
-#endif
-}
-
-static int io_madvise(struct io_kiocb *req, unsigned int issue_flags)
-{
-#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU)
- struct io_madvise *ma = &req->madvise;
- int ret;
-
- if (issue_flags & IO_URING_F_NONBLOCK)
- return -EAGAIN;
-
- ret = do_madvise(current->mm, ma->addr, ma->len, ma->advice);
- io_req_complete(req, ret);
- return 0;
-#else
- return -EOPNOTSUPP;
-#endif
-}
-
-static int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
- if (sqe->buf_index || sqe->addr || sqe->splice_fd_in)
- return -EINVAL;
-
- req->fadvise.offset = READ_ONCE(sqe->off);
- req->fadvise.len = READ_ONCE(sqe->len);
- req->fadvise.advice = READ_ONCE(sqe->fadvise_advice);
- return 0;
-}
-
-static int io_fadvise(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_fadvise *fa = &req->fadvise;
- int ret;
-
- if (issue_flags & IO_URING_F_NONBLOCK) {
- switch (fa->advice) {
- case POSIX_FADV_NORMAL:
- case POSIX_FADV_RANDOM:
- case POSIX_FADV_SEQUENTIAL:
- break;
- default:
- return -EAGAIN;
- }
- }
-
- ret = vfs_fadvise(req->file, fa->offset, fa->len, fa->advice);
- if (ret < 0)
- req_set_fail(req);
- __io_req_complete(req, issue_flags, ret, 0);
- return 0;
-}
-
-static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
- const char __user *path;
-
- if (sqe->buf_index || sqe->splice_fd_in)
- return -EINVAL;
- if (req->flags & REQ_F_FIXED_FILE)
- return -EBADF;
-
- req->statx.dfd = READ_ONCE(sqe->fd);
- req->statx.mask = READ_ONCE(sqe->len);
- path = u64_to_user_ptr(READ_ONCE(sqe->addr));
- req->statx.buffer = u64_to_user_ptr(READ_ONCE(sqe->addr2));
- req->statx.flags = READ_ONCE(sqe->statx_flags);
-
- req->statx.filename = getname_flags(path,
- getname_statx_lookup_flags(req->statx.flags),
- NULL);
-
- if (IS_ERR(req->statx.filename)) {
- int ret = PTR_ERR(req->statx.filename);
-
- req->statx.filename = NULL;
- return ret;
- }
-
- req->flags |= REQ_F_NEED_CLEANUP;
- return 0;
-}
-
-static int io_statx(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_statx *ctx = &req->statx;
- int ret;
-
- if (issue_flags & IO_URING_F_NONBLOCK)
- return -EAGAIN;
-
- ret = do_statx(ctx->dfd, ctx->filename, ctx->flags, ctx->mask,
- ctx->buffer);
- io_req_complete(req, ret);
- return 0;
-}
-
-static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
- if (sqe->off || sqe->addr || sqe->len || sqe->rw_flags || sqe->buf_index)
- return -EINVAL;
- if (req->flags & REQ_F_FIXED_FILE)
- return -EBADF;
-
- req->close.fd = READ_ONCE(sqe->fd);
- req->close.file_slot = READ_ONCE(sqe->file_index);
- if (req->close.file_slot && req->close.fd)
- return -EINVAL;
-
- return 0;
-}
-
-static int io_close(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct files_struct *files = current->files;
- struct io_close *close = &req->close;
- struct fdtable *fdt;
- struct file *file;
- int ret = -EBADF;
-
- if (req->close.file_slot) {
- ret = io_close_fixed(req, issue_flags);
- goto err;
- }
-
- spin_lock(&files->file_lock);
- fdt = files_fdtable(files);
- if (close->fd >= fdt->max_fds) {
- spin_unlock(&files->file_lock);
- goto err;
- }
- file = rcu_dereference_protected(fdt->fd[close->fd],
- lockdep_is_held(&files->file_lock));
- if (!file || file->f_op == &io_uring_fops) {
- spin_unlock(&files->file_lock);
- goto err;
- }
-
- /* if the file has a flush method, be safe and punt to async */
- if (file->f_op->flush && (issue_flags & IO_URING_F_NONBLOCK)) {
- spin_unlock(&files->file_lock);
- return -EAGAIN;
- }
-
- file = __close_fd_get_file(close->fd);
- spin_unlock(&files->file_lock);
- if (!file)
- goto err;
-
- /* No ->flush() or already async, safely close from here */
- ret = filp_close(file, current->files);
-err:
- if (ret < 0)
- req_set_fail(req);
- __io_req_complete(req, issue_flags, ret, 0);
- return 0;
-}
-
-static int io_sfr_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
- if (unlikely(sqe->addr || sqe->buf_index || sqe->splice_fd_in))
- return -EINVAL;
-
- req->sync.off = READ_ONCE(sqe->off);
- req->sync.len = READ_ONCE(sqe->len);
- req->sync.flags = READ_ONCE(sqe->sync_range_flags);
- return 0;
-}
-
-static int io_sync_file_range(struct io_kiocb *req, unsigned int issue_flags)
-{
- int ret;
-
- /* sync_file_range always requires a blocking context */
- if (issue_flags & IO_URING_F_NONBLOCK)
- return -EAGAIN;
-
- ret = sync_file_range(req->file, req->sync.off, req->sync.len,
- req->sync.flags);
- io_req_complete(req, ret);
- return 0;
-}
-
-#if defined(CONFIG_NET)
-static int io_shutdown_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- if (unlikely(sqe->off || sqe->addr || sqe->rw_flags ||
- sqe->buf_index || sqe->splice_fd_in))
- return -EINVAL;
-
- req->shutdown.how = READ_ONCE(sqe->len);
- return 0;
-}
-
-static int io_shutdown(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct socket *sock;
- int ret;
-
- if (issue_flags & IO_URING_F_NONBLOCK)
- return -EAGAIN;
-
- sock = sock_from_file(req->file);
- if (unlikely(!sock))
- return -ENOTSOCK;
-
- ret = __sys_shutdown_sock(sock, req->shutdown.how);
- io_req_complete(req, ret);
- return 0;
-}
-
-static bool io_net_retry(struct socket *sock, int flags)
-{
- if (!(flags & MSG_WAITALL))
- return false;
- return sock->type == SOCK_STREAM || sock->type == SOCK_SEQPACKET;
-}
-
-static int io_setup_async_msg(struct io_kiocb *req,
- struct io_async_msghdr *kmsg)
-{
- struct io_async_msghdr *async_msg = req->async_data;
-
- if (async_msg)
- return -EAGAIN;
- if (io_alloc_async_data(req)) {
- kfree(kmsg->free_iov);
- return -ENOMEM;
- }
- async_msg = req->async_data;
- req->flags |= REQ_F_NEED_CLEANUP;
- memcpy(async_msg, kmsg, sizeof(*kmsg));
- async_msg->msg.msg_name = &async_msg->addr;
- /* if were using fast_iov, set it to the new one */
- if (!async_msg->free_iov)
- async_msg->msg.msg_iter.iov = async_msg->fast_iov;
-
- return -EAGAIN;
-}
-
-static int io_sendmsg_copy_hdr(struct io_kiocb *req,
- struct io_async_msghdr *iomsg)
-{
- iomsg->msg.msg_name = &iomsg->addr;
- iomsg->free_iov = iomsg->fast_iov;
- return sendmsg_copy_msghdr(&iomsg->msg, req->sr_msg.umsg,
- req->sr_msg.msg_flags, &iomsg->free_iov);
-}
-
-static int io_sendmsg_prep_async(struct io_kiocb *req)
-{
- int ret;
-
- ret = io_sendmsg_copy_hdr(req, req->async_data);
- if (!ret)
- req->flags |= REQ_F_NEED_CLEANUP;
- return ret;
-}
-
-static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
- struct io_sr_msg *sr = &req->sr_msg;
-
- if (unlikely(sqe->file_index || sqe->addr2))
- return -EINVAL;
-
- sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr));
- sr->len = READ_ONCE(sqe->len);
- sr->flags = READ_ONCE(sqe->ioprio);
- if (sr->flags & ~IORING_RECVSEND_POLL_FIRST)
- return -EINVAL;
- sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL;
- if (sr->msg_flags & MSG_DONTWAIT)
- req->flags |= REQ_F_NOWAIT;
-
-#ifdef CONFIG_COMPAT
- if (req->ctx->compat)
- sr->msg_flags |= MSG_CMSG_COMPAT;
-#endif
- sr->done_io = 0;
- return 0;
-}
-
-static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_async_msghdr iomsg, *kmsg;
- struct io_sr_msg *sr = &req->sr_msg;
- struct socket *sock;
- unsigned flags;
- int min_ret = 0;
- int ret;
-
- sock = sock_from_file(req->file);
- if (unlikely(!sock))
- return -ENOTSOCK;
-
- if (req_has_async_data(req)) {
- kmsg = req->async_data;
- } else {
- ret = io_sendmsg_copy_hdr(req, &iomsg);
- if (ret)
- return ret;
- kmsg = &iomsg;
- }
-
- if (!(req->flags & REQ_F_POLLED) &&
- (sr->flags & IORING_RECVSEND_POLL_FIRST))
- return io_setup_async_msg(req, kmsg);
-
- flags = sr->msg_flags;
- if (issue_flags & IO_URING_F_NONBLOCK)
- flags |= MSG_DONTWAIT;
- if (flags & MSG_WAITALL)
- min_ret = iov_iter_count(&kmsg->msg.msg_iter);
-
- ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags);
-
- if (ret < min_ret) {
- if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK))
- return io_setup_async_msg(req, kmsg);
- if (ret == -ERESTARTSYS)
- ret = -EINTR;
- if (ret > 0 && io_net_retry(sock, flags)) {
- sr->done_io += ret;
- req->flags |= REQ_F_PARTIAL_IO;
- return io_setup_async_msg(req, kmsg);
- }
- req_set_fail(req);
- }
- /* fast path, check for non-NULL to avoid function call */
- if (kmsg->free_iov)
- kfree(kmsg->free_iov);
- req->flags &= ~REQ_F_NEED_CLEANUP;
- if (ret >= 0)
- ret += sr->done_io;
- else if (sr->done_io)
- ret = sr->done_io;
- __io_req_complete(req, issue_flags, ret, 0);
- return 0;
-}
-
-static int io_send(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_sr_msg *sr = &req->sr_msg;
- struct msghdr msg;
- struct iovec iov;
- struct socket *sock;
- unsigned flags;
- int min_ret = 0;
- int ret;
-
- if (!(req->flags & REQ_F_POLLED) &&
- (sr->flags & IORING_RECVSEND_POLL_FIRST))
- return -EAGAIN;
-
- sock = sock_from_file(req->file);
- if (unlikely(!sock))
- return -ENOTSOCK;
-
- ret = import_single_range(WRITE, sr->buf, sr->len, &iov, &msg.msg_iter);
- if (unlikely(ret))
- return ret;
-
- msg.msg_name = NULL;
- msg.msg_control = NULL;
- msg.msg_controllen = 0;
- msg.msg_namelen = 0;
-
- flags = sr->msg_flags;
- if (issue_flags & IO_URING_F_NONBLOCK)
- flags |= MSG_DONTWAIT;
- if (flags & MSG_WAITALL)
- min_ret = iov_iter_count(&msg.msg_iter);
-
- msg.msg_flags = flags;
- ret = sock_sendmsg(sock, &msg);
- if (ret < min_ret) {
- if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK))
- return -EAGAIN;
- if (ret == -ERESTARTSYS)
- ret = -EINTR;
- if (ret > 0 && io_net_retry(sock, flags)) {
- sr->len -= ret;
- sr->buf += ret;
- sr->done_io += ret;
- req->flags |= REQ_F_PARTIAL_IO;
- return -EAGAIN;
- }
- req_set_fail(req);
- }
- if (ret >= 0)
- ret += sr->done_io;
- else if (sr->done_io)
- ret = sr->done_io;
- __io_req_complete(req, issue_flags, ret, 0);
- return 0;
-}
-
-static int __io_recvmsg_copy_hdr(struct io_kiocb *req,
- struct io_async_msghdr *iomsg)
-{
- struct io_sr_msg *sr = &req->sr_msg;
- struct iovec __user *uiov;
- size_t iov_len;
- int ret;
-
- ret = __copy_msghdr_from_user(&iomsg->msg, sr->umsg,
- &iomsg->uaddr, &uiov, &iov_len);
- if (ret)
- return ret;
-
- if (req->flags & REQ_F_BUFFER_SELECT) {
- if (iov_len > 1)
- return -EINVAL;
- if (copy_from_user(iomsg->fast_iov, uiov, sizeof(*uiov)))
- return -EFAULT;
- sr->len = iomsg->fast_iov[0].iov_len;
- iomsg->free_iov = NULL;
- } else {
- iomsg->free_iov = iomsg->fast_iov;
- ret = __import_iovec(READ, uiov, iov_len, UIO_FASTIOV,
- &iomsg->free_iov, &iomsg->msg.msg_iter,
- false);
- if (ret > 0)
- ret = 0;
- }
-
- return ret;
-}
-
-#ifdef CONFIG_COMPAT
-static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req,
- struct io_async_msghdr *iomsg)
-{
- struct io_sr_msg *sr = &req->sr_msg;
- struct compat_iovec __user *uiov;
- compat_uptr_t ptr;
- compat_size_t len;
- int ret;
-
- ret = __get_compat_msghdr(&iomsg->msg, sr->umsg_compat, &iomsg->uaddr,
- &ptr, &len);
- if (ret)
- return ret;
-
- uiov = compat_ptr(ptr);
- if (req->flags & REQ_F_BUFFER_SELECT) {
- compat_ssize_t clen;
-
- if (len > 1)
- return -EINVAL;
- if (!access_ok(uiov, sizeof(*uiov)))
- return -EFAULT;
- if (__get_user(clen, &uiov->iov_len))
- return -EFAULT;
- if (clen < 0)
- return -EINVAL;
- sr->len = clen;
- iomsg->free_iov = NULL;
- } else {
- iomsg->free_iov = iomsg->fast_iov;
- ret = __import_iovec(READ, (struct iovec __user *)uiov, len,
- UIO_FASTIOV, &iomsg->free_iov,
- &iomsg->msg.msg_iter, true);
- if (ret < 0)
- return ret;
- }
-
- return 0;
-}
-#endif
-
-static int io_recvmsg_copy_hdr(struct io_kiocb *req,
- struct io_async_msghdr *iomsg)
-{
- iomsg->msg.msg_name = &iomsg->addr;
-
-#ifdef CONFIG_COMPAT
- if (req->ctx->compat)
- return __io_compat_recvmsg_copy_hdr(req, iomsg);
-#endif
-
- return __io_recvmsg_copy_hdr(req, iomsg);
-}
-
-static int io_recvmsg_prep_async(struct io_kiocb *req)
-{
- int ret;
-
- ret = io_recvmsg_copy_hdr(req, req->async_data);
- if (!ret)
- req->flags |= REQ_F_NEED_CLEANUP;
- return ret;
-}
-
-static int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
- struct io_sr_msg *sr = &req->sr_msg;
-
- if (unlikely(sqe->file_index || sqe->addr2))
- return -EINVAL;
-
- sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr));
- sr->len = READ_ONCE(sqe->len);
- sr->flags = READ_ONCE(sqe->ioprio);
- if (sr->flags & ~IORING_RECVSEND_POLL_FIRST)
- return -EINVAL;
- sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL;
- if (sr->msg_flags & MSG_DONTWAIT)
- req->flags |= REQ_F_NOWAIT;
-
-#ifdef CONFIG_COMPAT
- if (req->ctx->compat)
- sr->msg_flags |= MSG_CMSG_COMPAT;
-#endif
- sr->done_io = 0;
- return 0;
-}
-
-static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_async_msghdr iomsg, *kmsg;
- struct io_sr_msg *sr = &req->sr_msg;
- struct socket *sock;
- unsigned int cflags;
- unsigned flags;
- int ret, min_ret = 0;
- bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
-
- sock = sock_from_file(req->file);
- if (unlikely(!sock))
- return -ENOTSOCK;
-
- if (req_has_async_data(req)) {
- kmsg = req->async_data;
- } else {
- ret = io_recvmsg_copy_hdr(req, &iomsg);
- if (ret)
- return ret;
- kmsg = &iomsg;
- }
-
- if (!(req->flags & REQ_F_POLLED) &&
- (sr->flags & IORING_RECVSEND_POLL_FIRST))
- return io_setup_async_msg(req, kmsg);
-
- if (io_do_buffer_select(req)) {
- void __user *buf;
-
- buf = io_buffer_select(req, &sr->len, issue_flags);
- if (!buf)
- return -ENOBUFS;
- kmsg->fast_iov[0].iov_base = buf;
- kmsg->fast_iov[0].iov_len = sr->len;
- iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->fast_iov, 1,
- sr->len);
- }
-
- flags = sr->msg_flags;
- if (force_nonblock)
- flags |= MSG_DONTWAIT;
- if (flags & MSG_WAITALL)
- min_ret = iov_iter_count(&kmsg->msg.msg_iter);
-
- kmsg->msg.msg_get_inq = 1;
- ret = __sys_recvmsg_sock(sock, &kmsg->msg, sr->umsg, kmsg->uaddr, flags);
- if (ret < min_ret) {
- if (ret == -EAGAIN && force_nonblock)
- return io_setup_async_msg(req, kmsg);
- if (ret == -ERESTARTSYS)
- ret = -EINTR;
- if (ret > 0 && io_net_retry(sock, flags)) {
- sr->done_io += ret;
- req->flags |= REQ_F_PARTIAL_IO;
- return io_setup_async_msg(req, kmsg);
- }
- req_set_fail(req);
- } else if ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) {
- req_set_fail(req);
- }
-
- /* fast path, check for non-NULL to avoid function call */
- if (kmsg->free_iov)
- kfree(kmsg->free_iov);
- req->flags &= ~REQ_F_NEED_CLEANUP;
- if (ret >= 0)
- ret += sr->done_io;
- else if (sr->done_io)
- ret = sr->done_io;
- cflags = io_put_kbuf(req, issue_flags);
- if (kmsg->msg.msg_inq)
- cflags |= IORING_CQE_F_SOCK_NONEMPTY;
- __io_req_complete(req, issue_flags, ret, cflags);
- return 0;
-}
-
-static int io_recv(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_sr_msg *sr = &req->sr_msg;
- struct msghdr msg;
- struct socket *sock;
- struct iovec iov;
- unsigned int cflags;
- unsigned flags;
- int ret, min_ret = 0;
- bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
-
- if (!(req->flags & REQ_F_POLLED) &&
- (sr->flags & IORING_RECVSEND_POLL_FIRST))
- return -EAGAIN;
-
- sock = sock_from_file(req->file);
- if (unlikely(!sock))
- return -ENOTSOCK;
-
- if (io_do_buffer_select(req)) {
- void __user *buf;
-
- buf = io_buffer_select(req, &sr->len, issue_flags);
- if (!buf)
- return -ENOBUFS;
- sr->buf = buf;
- }
-
- ret = import_single_range(READ, sr->buf, sr->len, &iov, &msg.msg_iter);
- if (unlikely(ret))
- goto out_free;
-
- msg.msg_name = NULL;
- msg.msg_namelen = 0;
- msg.msg_control = NULL;
- msg.msg_get_inq = 1;
- msg.msg_flags = 0;
- msg.msg_controllen = 0;
- msg.msg_iocb = NULL;
-
- flags = sr->msg_flags;
- if (force_nonblock)
- flags |= MSG_DONTWAIT;
- if (flags & MSG_WAITALL)
- min_ret = iov_iter_count(&msg.msg_iter);
-
- ret = sock_recvmsg(sock, &msg, flags);
- if (ret < min_ret) {
- if (ret == -EAGAIN && force_nonblock)
- return -EAGAIN;
- if (ret == -ERESTARTSYS)
- ret = -EINTR;
- if (ret > 0 && io_net_retry(sock, flags)) {
- sr->len -= ret;
- sr->buf += ret;
- sr->done_io += ret;
- req->flags |= REQ_F_PARTIAL_IO;
- return -EAGAIN;
- }
- req_set_fail(req);
- } else if ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))) {
-out_free:
- req_set_fail(req);
- }
-
- if (ret >= 0)
- ret += sr->done_io;
- else if (sr->done_io)
- ret = sr->done_io;
- cflags = io_put_kbuf(req, issue_flags);
- if (msg.msg_inq)
- cflags |= IORING_CQE_F_SOCK_NONEMPTY;
- __io_req_complete(req, issue_flags, ret, cflags);
- return 0;
-}
-
-static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
- struct io_accept *accept = &req->accept;
- unsigned flags;
-
- if (sqe->len || sqe->buf_index)
- return -EINVAL;
-
- accept->addr = u64_to_user_ptr(READ_ONCE(sqe->addr));
- accept->addr_len = u64_to_user_ptr(READ_ONCE(sqe->addr2));
- accept->flags = READ_ONCE(sqe->accept_flags);
- accept->nofile = rlimit(RLIMIT_NOFILE);
- flags = READ_ONCE(sqe->ioprio);
- if (flags & ~IORING_ACCEPT_MULTISHOT)
- return -EINVAL;
-
- accept->file_slot = READ_ONCE(sqe->file_index);
- if (accept->file_slot) {
- if (accept->flags & SOCK_CLOEXEC)
- return -EINVAL;
- if (flags & IORING_ACCEPT_MULTISHOT &&
- accept->file_slot != IORING_FILE_INDEX_ALLOC)
- return -EINVAL;
- }
- if (accept->flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
- return -EINVAL;
- if (SOCK_NONBLOCK != O_NONBLOCK && (accept->flags & SOCK_NONBLOCK))
- accept->flags = (accept->flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
- if (flags & IORING_ACCEPT_MULTISHOT)
- req->flags |= REQ_F_APOLL_MULTISHOT;
- return 0;
-}
-
-static int io_accept(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_ring_ctx *ctx = req->ctx;
- struct io_accept *accept = &req->accept;
- bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
- unsigned int file_flags = force_nonblock ? O_NONBLOCK : 0;
- bool fixed = !!accept->file_slot;
- struct file *file;
- int ret, fd;
-
-retry:
- if (!fixed) {
- fd = __get_unused_fd_flags(accept->flags, accept->nofile);
- if (unlikely(fd < 0))
- return fd;
- }
- file = do_accept(req->file, file_flags, accept->addr, accept->addr_len,
- accept->flags);
- if (IS_ERR(file)) {
- if (!fixed)
- put_unused_fd(fd);
- ret = PTR_ERR(file);
- if (ret == -EAGAIN && force_nonblock) {
- /*
- * if it's multishot and polled, we don't need to
- * return EAGAIN to arm the poll infra since it
- * has already been done
- */
- if ((req->flags & IO_APOLL_MULTI_POLLED) ==
- IO_APOLL_MULTI_POLLED)
- ret = 0;
- return ret;
- }
- if (ret == -ERESTARTSYS)
- ret = -EINTR;
- req_set_fail(req);
- } else if (!fixed) {
- fd_install(fd, file);
- ret = fd;
- } else {
- ret = io_fixed_fd_install(req, issue_flags, file,
- accept->file_slot);
- }
-
- if (!(req->flags & REQ_F_APOLL_MULTISHOT)) {
- __io_req_complete(req, issue_flags, ret, 0);
- return 0;
- }
- if (ret >= 0) {
- bool filled;
-
- spin_lock(&ctx->completion_lock);
- filled = io_fill_cqe_aux(ctx, req->cqe.user_data, ret,
- IORING_CQE_F_MORE);
- io_commit_cqring(ctx);
- spin_unlock(&ctx->completion_lock);
- if (filled) {
- io_cqring_ev_posted(ctx);
- goto retry;
- }
- ret = -ECANCELED;
- }
-
- return ret;
-}
-
-static int io_socket_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
- struct io_socket *sock = &req->sock;
-
- if (sqe->addr || sqe->rw_flags || sqe->buf_index)
- return -EINVAL;
-
- sock->domain = READ_ONCE(sqe->fd);
- sock->type = READ_ONCE(sqe->off);
- sock->protocol = READ_ONCE(sqe->len);
- sock->file_slot = READ_ONCE(sqe->file_index);
- sock->nofile = rlimit(RLIMIT_NOFILE);
-
- sock->flags = sock->type & ~SOCK_TYPE_MASK;
- if (sock->file_slot && (sock->flags & SOCK_CLOEXEC))
- return -EINVAL;
- if (sock->flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK))
- return -EINVAL;
- return 0;
-}
-
-static int io_socket(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_socket *sock = &req->sock;
- bool fixed = !!sock->file_slot;
- struct file *file;
- int ret, fd;
-
- if (!fixed) {
- fd = __get_unused_fd_flags(sock->flags, sock->nofile);
- if (unlikely(fd < 0))
- return fd;
- }
- file = __sys_socket_file(sock->domain, sock->type, sock->protocol);
- if (IS_ERR(file)) {
- if (!fixed)
- put_unused_fd(fd);
- ret = PTR_ERR(file);
- if (ret == -EAGAIN && (issue_flags & IO_URING_F_NONBLOCK))
- return -EAGAIN;
- if (ret == -ERESTARTSYS)
- ret = -EINTR;
- req_set_fail(req);
- } else if (!fixed) {
- fd_install(fd, file);
- ret = fd;
- } else {
- ret = io_fixed_fd_install(req, issue_flags, file,
- sock->file_slot);
- }
- __io_req_complete(req, issue_flags, ret, 0);
- return 0;
-}
-
-static int io_connect_prep_async(struct io_kiocb *req)
-{
- struct io_async_connect *io = req->async_data;
- struct io_connect *conn = &req->connect;
-
- return move_addr_to_kernel(conn->addr, conn->addr_len, &io->address);
-}
-
-static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
- struct io_connect *conn = &req->connect;
-
- if (sqe->len || sqe->buf_index || sqe->rw_flags || sqe->splice_fd_in)
- return -EINVAL;
-
- conn->addr = u64_to_user_ptr(READ_ONCE(sqe->addr));
- conn->addr_len = READ_ONCE(sqe->addr2);
- return 0;
-}
-
-static int io_connect(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_async_connect __io, *io;
- unsigned file_flags;
- int ret;
- bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
-
- if (req_has_async_data(req)) {
- io = req->async_data;
- } else {
- ret = move_addr_to_kernel(req->connect.addr,
- req->connect.addr_len,
- &__io.address);
- if (ret)
- goto out;
- io = &__io;
- }
-
- file_flags = force_nonblock ? O_NONBLOCK : 0;
-
- ret = __sys_connect_file(req->file, &io->address,
- req->connect.addr_len, file_flags);
- if ((ret == -EAGAIN || ret == -EINPROGRESS) && force_nonblock) {
- if (req_has_async_data(req))
- return -EAGAIN;
- if (io_alloc_async_data(req)) {
- ret = -ENOMEM;
- goto out;
- }
- memcpy(req->async_data, &__io, sizeof(__io));
- return -EAGAIN;
- }
- if (ret == -ERESTARTSYS)
- ret = -EINTR;
-out:
- if (ret < 0)
- req_set_fail(req);
- __io_req_complete(req, issue_flags, ret, 0);
- return 0;
-}
-#else /* !CONFIG_NET */
-#define IO_NETOP_FN(op) \
-static int io_##op(struct io_kiocb *req, unsigned int issue_flags) \
-{ \
- return -EOPNOTSUPP; \
-}
-
-#define IO_NETOP_PREP(op) \
-IO_NETOP_FN(op) \
-static int io_##op##_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) \
-{ \
- return -EOPNOTSUPP; \
-} \
-
-#define IO_NETOP_PREP_ASYNC(op) \
-IO_NETOP_PREP(op) \
-static int io_##op##_prep_async(struct io_kiocb *req) \
-{ \
- return -EOPNOTSUPP; \
-}
-
-IO_NETOP_PREP_ASYNC(sendmsg);
-IO_NETOP_PREP_ASYNC(recvmsg);
-IO_NETOP_PREP_ASYNC(connect);
-IO_NETOP_PREP(accept);
-IO_NETOP_PREP(socket);
-IO_NETOP_PREP(shutdown);
-IO_NETOP_FN(send);
-IO_NETOP_FN(recv);
-#endif /* CONFIG_NET */
-
-struct io_poll_table {
- struct poll_table_struct pt;
- struct io_kiocb *req;
- int nr_entries;
- int error;
-};
-
-#define IO_POLL_CANCEL_FLAG BIT(31)
-#define IO_POLL_REF_MASK GENMASK(30, 0)
-
-/*
- * If refs part of ->poll_refs (see IO_POLL_REF_MASK) is 0, it's free. We can
- * bump it and acquire ownership. It's disallowed to modify requests while not
- * owning it, that prevents from races for enqueueing task_work's and b/w
- * arming poll and wakeups.
- */
-static inline bool io_poll_get_ownership(struct io_kiocb *req)
-{
- return !(atomic_fetch_inc(&req->poll_refs) & IO_POLL_REF_MASK);
-}
-
-static void io_poll_mark_cancelled(struct io_kiocb *req)
-{
- atomic_or(IO_POLL_CANCEL_FLAG, &req->poll_refs);
-}
-
-static struct io_poll_iocb *io_poll_get_double(struct io_kiocb *req)
-{
- /* pure poll stashes this in ->async_data, poll driven retry elsewhere */
- if (req->opcode == IORING_OP_POLL_ADD)
- return req->async_data;
- return req->apoll->double_poll;
-}
-
-static struct io_poll_iocb *io_poll_get_single(struct io_kiocb *req)
-{
- if (req->opcode == IORING_OP_POLL_ADD)
- return &req->poll;
- return &req->apoll->poll;
-}
-
-static void io_poll_req_insert(struct io_kiocb *req)
-{
- struct io_ring_ctx *ctx = req->ctx;
- struct hlist_head *list;
-
- list = &ctx->cancel_hash[hash_long(req->cqe.user_data, ctx->cancel_hash_bits)];
- hlist_add_head(&req->hash_node, list);
-}
-
-static void io_init_poll_iocb(struct io_poll_iocb *poll, __poll_t events,
- wait_queue_func_t wake_func)
-{
- poll->head = NULL;
-#define IO_POLL_UNMASK (EPOLLERR|EPOLLHUP|EPOLLNVAL|EPOLLRDHUP)
- /* mask in events that we always want/need */
- poll->events = events | IO_POLL_UNMASK;
- INIT_LIST_HEAD(&poll->wait.entry);
- init_waitqueue_func_entry(&poll->wait, wake_func);
-}
-
-static inline void io_poll_remove_entry(struct io_poll_iocb *poll)
-{
- struct wait_queue_head *head = smp_load_acquire(&poll->head);
-
- if (head) {
- spin_lock_irq(&head->lock);
- list_del_init(&poll->wait.entry);
- poll->head = NULL;
- spin_unlock_irq(&head->lock);
- }
-}
-
-static void io_poll_remove_entries(struct io_kiocb *req)
-{
- /*
- * Nothing to do if neither of those flags are set. Avoid dipping
- * into the poll/apoll/double cachelines if we can.
- */
- if (!(req->flags & (REQ_F_SINGLE_POLL | REQ_F_DOUBLE_POLL)))
- return;
-
- /*
- * While we hold the waitqueue lock and the waitqueue is nonempty,
- * wake_up_pollfree() will wait for us. However, taking the waitqueue
- * lock in the first place can race with the waitqueue being freed.
- *
- * We solve this as eventpoll does: by taking advantage of the fact that
- * all users of wake_up_pollfree() will RCU-delay the actual free. If
- * we enter rcu_read_lock() and see that the pointer to the queue is
- * non-NULL, we can then lock it without the memory being freed out from
- * under us.
- *
- * Keep holding rcu_read_lock() as long as we hold the queue lock, in
- * case the caller deletes the entry from the queue, leaving it empty.
- * In that case, only RCU prevents the queue memory from being freed.
- */
- rcu_read_lock();
- if (req->flags & REQ_F_SINGLE_POLL)
- io_poll_remove_entry(io_poll_get_single(req));
- if (req->flags & REQ_F_DOUBLE_POLL)
- io_poll_remove_entry(io_poll_get_double(req));
- rcu_read_unlock();
-}
-
-static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags);
-/*
- * All poll tw should go through this. Checks for poll events, manages
- * references, does rewait, etc.
- *
- * Returns a negative error on failure. >0 when no action require, which is
- * either spurious wakeup or multishot CQE is served. 0 when it's done with
- * the request, then the mask is stored in req->cqe.res.
- */
-static int io_poll_check_events(struct io_kiocb *req, bool *locked)
-{
- struct io_ring_ctx *ctx = req->ctx;
- int v, ret;
-
- /* req->task == current here, checking PF_EXITING is safe */
- if (unlikely(req->task->flags & PF_EXITING))
- return -ECANCELED;
-
- do {
- v = atomic_read(&req->poll_refs);
-
- /* tw handler should be the owner, and so have some references */
- if (WARN_ON_ONCE(!(v & IO_POLL_REF_MASK)))
- return 0;
- if (v & IO_POLL_CANCEL_FLAG)
- return -ECANCELED;
-
- if (!req->cqe.res) {
- struct poll_table_struct pt = { ._key = req->apoll_events };
- req->cqe.res = vfs_poll(req->file, &pt) & req->apoll_events;
- }
-
- if ((unlikely(!req->cqe.res)))
- continue;
- if (req->apoll_events & EPOLLONESHOT)
- return 0;
-
- /* multishot, just fill a CQE and proceed */
- if (!(req->flags & REQ_F_APOLL_MULTISHOT)) {
- __poll_t mask = mangle_poll(req->cqe.res &
- req->apoll_events);
- bool filled;
-
- spin_lock(&ctx->completion_lock);
- filled = io_fill_cqe_aux(ctx, req->cqe.user_data,
- mask, IORING_CQE_F_MORE);
- io_commit_cqring(ctx);
- spin_unlock(&ctx->completion_lock);
- if (filled) {
- io_cqring_ev_posted(ctx);
- continue;
- }
- return -ECANCELED;
- }
-
- io_tw_lock(req->ctx, locked);
- if (unlikely(req->task->flags & PF_EXITING))
- return -EFAULT;
- ret = io_issue_sqe(req,
- IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER);
- if (ret)
- return ret;
-
- /*
- * Release all references, retry if someone tried to restart
- * task_work while we were executing it.
- */
- } while (atomic_sub_return(v & IO_POLL_REF_MASK, &req->poll_refs));
-
- return 1;
-}
-
-static void io_poll_task_func(struct io_kiocb *req, bool *locked)
-{
- struct io_ring_ctx *ctx = req->ctx;
- int ret;
-
- ret = io_poll_check_events(req, locked);
- if (ret > 0)
- return;
-
- if (!ret) {
- req->cqe.res = mangle_poll(req->cqe.res & req->poll.events);
- } else {
- req->cqe.res = ret;
- req_set_fail(req);
- }
-
- io_poll_remove_entries(req);
- spin_lock(&ctx->completion_lock);
- hash_del(&req->hash_node);
- __io_req_complete_post(req, req->cqe.res, 0);
- io_commit_cqring(ctx);
- spin_unlock(&ctx->completion_lock);
- io_cqring_ev_posted(ctx);
-}
-
-static void io_apoll_task_func(struct io_kiocb *req, bool *locked)
-{
- struct io_ring_ctx *ctx = req->ctx;
- int ret;
-
- ret = io_poll_check_events(req, locked);
- if (ret > 0)
- return;
-
- io_poll_remove_entries(req);
- spin_lock(&ctx->completion_lock);
- hash_del(&req->hash_node);
- spin_unlock(&ctx->completion_lock);
-
- if (!ret)
- io_req_task_submit(req, locked);
- else
- io_req_complete_failed(req, ret);
-}
-
-static void __io_poll_execute(struct io_kiocb *req, int mask,
- __poll_t __maybe_unused events)
-{
- req->cqe.res = mask;
- /*
- * This is useful for poll that is armed on behalf of another
- * request, and where the wakeup path could be on a different
- * CPU. We want to avoid pulling in req->apoll->events for that
- * case.
- */
- if (req->opcode == IORING_OP_POLL_ADD)
- req->io_task_work.func = io_poll_task_func;
- else
- req->io_task_work.func = io_apoll_task_func;
-
- trace_io_uring_task_add(req->ctx, req, req->cqe.user_data, req->opcode, mask);
- io_req_task_work_add(req);
-}
-
-static inline void io_poll_execute(struct io_kiocb *req, int res,
- __poll_t events)
-{
- if (io_poll_get_ownership(req))
- __io_poll_execute(req, res, events);
-}
-
-static void io_poll_cancel_req(struct io_kiocb *req)
-{
- io_poll_mark_cancelled(req);
- /* kick tw, which should complete the request */
- io_poll_execute(req, 0, 0);
-}
-
-#define wqe_to_req(wait) ((void *)((unsigned long) (wait)->private & ~1))
-#define wqe_is_double(wait) ((unsigned long) (wait)->private & 1)
-#define IO_ASYNC_POLL_COMMON (EPOLLONESHOT | EPOLLPRI)
-
-static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
- void *key)
-{
- struct io_kiocb *req = wqe_to_req(wait);
- struct io_poll_iocb *poll = container_of(wait, struct io_poll_iocb,
- wait);
- __poll_t mask = key_to_poll(key);
-
- if (unlikely(mask & POLLFREE)) {
- io_poll_mark_cancelled(req);
- /* we have to kick tw in case it's not already */
- io_poll_execute(req, 0, poll->events);
-
- /*
- * If the waitqueue is being freed early but someone is already
- * holds ownership over it, we have to tear down the request as
- * best we can. That means immediately removing the request from
- * its waitqueue and preventing all further accesses to the
- * waitqueue via the request.
- */
- list_del_init(&poll->wait.entry);
-
- /*
- * Careful: this *must* be the last step, since as soon
- * as req->head is NULL'ed out, the request can be
- * completed and freed, since aio_poll_complete_work()
- * will no longer need to take the waitqueue lock.
- */
- smp_store_release(&poll->head, NULL);
- return 1;
- }
-
- /* for instances that support it check for an event match first */
- if (mask && !(mask & (poll->events & ~IO_ASYNC_POLL_COMMON)))
- return 0;
-
- if (io_poll_get_ownership(req)) {
- /* optional, saves extra locking for removal in tw handler */
- if (mask && poll->events & EPOLLONESHOT) {
- list_del_init(&poll->wait.entry);
- poll->head = NULL;
- if (wqe_is_double(wait))
- req->flags &= ~REQ_F_DOUBLE_POLL;
- else
- req->flags &= ~REQ_F_SINGLE_POLL;
- }
- __io_poll_execute(req, mask, poll->events);
- }
- return 1;
-}
-
-static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt,
- struct wait_queue_head *head,
- struct io_poll_iocb **poll_ptr)
-{
- struct io_kiocb *req = pt->req;
- unsigned long wqe_private = (unsigned long) req;
-
- /*
- * The file being polled uses multiple waitqueues for poll handling
- * (e.g. one for read, one for write). Setup a separate io_poll_iocb
- * if this happens.
- */
- if (unlikely(pt->nr_entries)) {
- struct io_poll_iocb *first = poll;
-
- /* double add on the same waitqueue head, ignore */
- if (first->head == head)
- return;
- /* already have a 2nd entry, fail a third attempt */
- if (*poll_ptr) {
- if ((*poll_ptr)->head == head)
- return;
- pt->error = -EINVAL;
- return;
- }
-
- poll = kmalloc(sizeof(*poll), GFP_ATOMIC);
- if (!poll) {
- pt->error = -ENOMEM;
- return;
- }
- /* mark as double wq entry */
- wqe_private |= 1;
- req->flags |= REQ_F_DOUBLE_POLL;
- io_init_poll_iocb(poll, first->events, first->wait.func);
- *poll_ptr = poll;
- if (req->opcode == IORING_OP_POLL_ADD)
- req->flags |= REQ_F_ASYNC_DATA;
- }
-
- req->flags |= REQ_F_SINGLE_POLL;
- pt->nr_entries++;
- poll->head = head;
- poll->wait.private = (void *) wqe_private;
-
- if (poll->events & EPOLLEXCLUSIVE)
- add_wait_queue_exclusive(head, &poll->wait);
- else
- add_wait_queue(head, &poll->wait);
-}
-
-static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head,
- struct poll_table_struct *p)
-{
- struct io_poll_table *pt = container_of(p, struct io_poll_table, pt);
-
- __io_queue_proc(&pt->req->poll, pt, head,
- (struct io_poll_iocb **) &pt->req->async_data);
-}
-
-static int __io_arm_poll_handler(struct io_kiocb *req,
- struct io_poll_iocb *poll,
- struct io_poll_table *ipt, __poll_t mask)
-{
- struct io_ring_ctx *ctx = req->ctx;
- int v;
-
- INIT_HLIST_NODE(&req->hash_node);
- req->work.cancel_seq = atomic_read(&ctx->cancel_seq);
- io_init_poll_iocb(poll, mask, io_poll_wake);
- poll->file = req->file;
-
- req->apoll_events = poll->events;
-
- ipt->pt._key = mask;
- ipt->req = req;
- ipt->error = 0;
- ipt->nr_entries = 0;
-
- /*
- * Take the ownership to delay any tw execution up until we're done
- * with poll arming. see io_poll_get_ownership().
- */
- atomic_set(&req->poll_refs, 1);
- mask = vfs_poll(req->file, &ipt->pt) & poll->events;
-
- if (mask && (poll->events & EPOLLONESHOT)) {
- io_poll_remove_entries(req);
- /* no one else has access to the req, forget about the ref */
- return mask;
- }
- if (!mask && unlikely(ipt->error || !ipt->nr_entries)) {
- io_poll_remove_entries(req);
- if (!ipt->error)
- ipt->error = -EINVAL;
- return 0;
- }
-
- spin_lock(&ctx->completion_lock);
- io_poll_req_insert(req);
- spin_unlock(&ctx->completion_lock);
-
- if (mask) {
- /* can't multishot if failed, just queue the event we've got */
- if (unlikely(ipt->error || !ipt->nr_entries)) {
- poll->events |= EPOLLONESHOT;
- req->apoll_events |= EPOLLONESHOT;
- ipt->error = 0;
- }
- __io_poll_execute(req, mask, poll->events);
- return 0;
- }
-
- /*
- * Release ownership. If someone tried to queue a tw while it was
- * locked, kick it off for them.
- */
- v = atomic_dec_return(&req->poll_refs);
- if (unlikely(v & IO_POLL_REF_MASK))
- __io_poll_execute(req, 0, poll->events);
- return 0;
-}
-
-static void io_async_queue_proc(struct file *file, struct wait_queue_head *head,
- struct poll_table_struct *p)
-{
- struct io_poll_table *pt = container_of(p, struct io_poll_table, pt);
- struct async_poll *apoll = pt->req->apoll;
-
- __io_queue_proc(&apoll->poll, pt, head, &apoll->double_poll);
-}
-
-enum {
- IO_APOLL_OK,
- IO_APOLL_ABORTED,
- IO_APOLL_READY
-};
-
-static int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags)
-{
- const struct io_op_def *def = &io_op_defs[req->opcode];
- struct io_ring_ctx *ctx = req->ctx;
- struct async_poll *apoll;
- struct io_poll_table ipt;
- __poll_t mask = POLLPRI | POLLERR;
- int ret;
-
- if (!def->pollin && !def->pollout)
- return IO_APOLL_ABORTED;
- if (!file_can_poll(req->file))
- return IO_APOLL_ABORTED;
- if ((req->flags & (REQ_F_POLLED|REQ_F_PARTIAL_IO)) == REQ_F_POLLED)
- return IO_APOLL_ABORTED;
- if (!(req->flags & REQ_F_APOLL_MULTISHOT))
- mask |= EPOLLONESHOT;
-
- if (def->pollin) {
- mask |= EPOLLIN | EPOLLRDNORM;
-
- /* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */
- if ((req->opcode == IORING_OP_RECVMSG) &&
- (req->sr_msg.msg_flags & MSG_ERRQUEUE))
- mask &= ~EPOLLIN;
- } else {
- mask |= EPOLLOUT | EPOLLWRNORM;
- }
- if (def->poll_exclusive)
- mask |= EPOLLEXCLUSIVE;
- if (req->flags & REQ_F_POLLED) {
- apoll = req->apoll;
- kfree(apoll->double_poll);
- } else if (!(issue_flags & IO_URING_F_UNLOCKED) &&
- !list_empty(&ctx->apoll_cache)) {
- apoll = list_first_entry(&ctx->apoll_cache, struct async_poll,
- poll.wait.entry);
- list_del_init(&apoll->poll.wait.entry);
- } else {
- apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC);
- if (unlikely(!apoll))
- return IO_APOLL_ABORTED;
- }
- apoll->double_poll = NULL;
- req->apoll = apoll;
- req->flags |= REQ_F_POLLED;
- ipt.pt._qproc = io_async_queue_proc;
-
- io_kbuf_recycle(req, issue_flags);
-
- ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask);
- if (ret || ipt.error)
- return ret ? IO_APOLL_READY : IO_APOLL_ABORTED;
-
- trace_io_uring_poll_arm(ctx, req, req->cqe.user_data, req->opcode,
- mask, apoll->poll.events);
- return IO_APOLL_OK;
-}
-
-/*
- * Returns true if we found and killed one or more poll requests
- */
-static __cold bool io_poll_remove_all(struct io_ring_ctx *ctx,
- struct task_struct *tsk, bool cancel_all)
-{
- struct hlist_node *tmp;
- struct io_kiocb *req;
- bool found = false;
- int i;
-
- spin_lock(&ctx->completion_lock);
- for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) {
- struct hlist_head *list;
-
- list = &ctx->cancel_hash[i];
- hlist_for_each_entry_safe(req, tmp, list, hash_node) {
- if (io_match_task_safe(req, tsk, cancel_all)) {
- hlist_del_init(&req->hash_node);
- io_poll_cancel_req(req);
- found = true;
- }
- }
- }
- spin_unlock(&ctx->completion_lock);
- return found;
-}
-
-static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, bool poll_only,
- struct io_cancel_data *cd)
- __must_hold(&ctx->completion_lock)
-{
- struct hlist_head *list;
- struct io_kiocb *req;
-
- list = &ctx->cancel_hash[hash_long(cd->data, ctx->cancel_hash_bits)];
- hlist_for_each_entry(req, list, hash_node) {
- if (cd->data != req->cqe.user_data)
- continue;
- if (poll_only && req->opcode != IORING_OP_POLL_ADD)
- continue;
- if (cd->flags & IORING_ASYNC_CANCEL_ALL) {
- if (cd->seq == req->work.cancel_seq)
- continue;
- req->work.cancel_seq = cd->seq;
- }
- return req;
- }
- return NULL;
-}
-
-static struct io_kiocb *io_poll_file_find(struct io_ring_ctx *ctx,
- struct io_cancel_data *cd)
- __must_hold(&ctx->completion_lock)
-{
- struct io_kiocb *req;
- int i;
-
- for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) {
- struct hlist_head *list;
-
- list = &ctx->cancel_hash[i];
- hlist_for_each_entry(req, list, hash_node) {
- if (!(cd->flags & IORING_ASYNC_CANCEL_ANY) &&
- req->file != cd->file)
- continue;
- if (cd->seq == req->work.cancel_seq)
- continue;
- req->work.cancel_seq = cd->seq;
- return req;
- }
- }
- return NULL;
-}
-
-static bool io_poll_disarm(struct io_kiocb *req)
- __must_hold(&ctx->completion_lock)
-{
- if (!io_poll_get_ownership(req))
- return false;
- io_poll_remove_entries(req);
- hash_del(&req->hash_node);
- return true;
-}
-
-static int io_poll_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd)
- __must_hold(&ctx->completion_lock)
-{
- struct io_kiocb *req;
-
- if (cd->flags & (IORING_ASYNC_CANCEL_FD|IORING_ASYNC_CANCEL_ANY))
- req = io_poll_file_find(ctx, cd);
- else
- req = io_poll_find(ctx, false, cd);
- if (!req)
- return -ENOENT;
- io_poll_cancel_req(req);
- return 0;
-}
-
-static __poll_t io_poll_parse_events(const struct io_uring_sqe *sqe,
- unsigned int flags)
-{
- u32 events;
-
- events = READ_ONCE(sqe->poll32_events);
-#ifdef __BIG_ENDIAN
- events = swahw32(events);
-#endif
- if (!(flags & IORING_POLL_ADD_MULTI))
- events |= EPOLLONESHOT;
- return demangle_poll(events) | (events & (EPOLLEXCLUSIVE|EPOLLONESHOT));
-}
-
-static int io_poll_remove_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- struct io_poll_update *upd = &req->poll_update;
- u32 flags;
-
- if (sqe->buf_index || sqe->splice_fd_in)
- return -EINVAL;
- flags = READ_ONCE(sqe->len);
- if (flags & ~(IORING_POLL_UPDATE_EVENTS | IORING_POLL_UPDATE_USER_DATA |
- IORING_POLL_ADD_MULTI))
- return -EINVAL;
- /* meaningless without update */
- if (flags == IORING_POLL_ADD_MULTI)
- return -EINVAL;
-
- upd->old_user_data = READ_ONCE(sqe->addr);
- upd->update_events = flags & IORING_POLL_UPDATE_EVENTS;
- upd->update_user_data = flags & IORING_POLL_UPDATE_USER_DATA;
-
- upd->new_user_data = READ_ONCE(sqe->off);
- if (!upd->update_user_data && upd->new_user_data)
- return -EINVAL;
- if (upd->update_events)
- upd->events = io_poll_parse_events(sqe, flags);
- else if (sqe->poll32_events)
- return -EINVAL;
-
- return 0;
-}
-
-static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
- struct io_poll_iocb *poll = &req->poll;
- u32 flags;
-
- if (sqe->buf_index || sqe->off || sqe->addr)
- return -EINVAL;
- flags = READ_ONCE(sqe->len);
- if (flags & ~IORING_POLL_ADD_MULTI)
- return -EINVAL;
- if ((flags & IORING_POLL_ADD_MULTI) && (req->flags & REQ_F_CQE_SKIP))
- return -EINVAL;
-
- io_req_set_refcount(req);
- poll->events = io_poll_parse_events(sqe, flags);
- return 0;
-}
-
-static int io_poll_add(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_poll_iocb *poll = &req->poll;
- struct io_poll_table ipt;
- int ret;
-
- ipt.pt._qproc = io_poll_queue_proc;
-
- ret = __io_arm_poll_handler(req, &req->poll, &ipt, poll->events);
- if (!ret && ipt.error)
- req_set_fail(req);
- ret = ret ?: ipt.error;
- if (ret)
- __io_req_complete(req, issue_flags, ret, 0);
- return 0;
-}
-
-static int io_poll_remove(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_cancel_data cd = { .data = req->poll_update.old_user_data, };
- struct io_ring_ctx *ctx = req->ctx;
- struct io_kiocb *preq;
- int ret2, ret = 0;
- bool locked;
-
- spin_lock(&ctx->completion_lock);
- preq = io_poll_find(ctx, true, &cd);
- if (!preq || !io_poll_disarm(preq)) {
- spin_unlock(&ctx->completion_lock);
- ret = preq ? -EALREADY : -ENOENT;
- goto out;
- }
- spin_unlock(&ctx->completion_lock);
-
- if (req->poll_update.update_events || req->poll_update.update_user_data) {
- /* only mask one event flags, keep behavior flags */
- if (req->poll_update.update_events) {
- preq->poll.events &= ~0xffff;
- preq->poll.events |= req->poll_update.events & 0xffff;
- preq->poll.events |= IO_POLL_UNMASK;
- }
- if (req->poll_update.update_user_data)
- preq->cqe.user_data = req->poll_update.new_user_data;
-
- ret2 = io_poll_add(preq, issue_flags);
- /* successfully updated, don't complete poll request */
- if (!ret2)
- goto out;
- }
-
- req_set_fail(preq);
- preq->cqe.res = -ECANCELED;
- locked = !(issue_flags & IO_URING_F_UNLOCKED);
- io_req_task_complete(preq, &locked);
-out:
- if (ret < 0)
- req_set_fail(req);
- /* complete update request, we're done with it */
- __io_req_complete(req, issue_flags, ret, 0);
- return 0;
-}
-
-static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer)
-{
- struct io_timeout_data *data = container_of(timer,
- struct io_timeout_data, timer);
- struct io_kiocb *req = data->req;
- struct io_ring_ctx *ctx = req->ctx;
- unsigned long flags;
-
- spin_lock_irqsave(&ctx->timeout_lock, flags);
- list_del_init(&req->timeout.list);
- atomic_set(&req->ctx->cq_timeouts,
- atomic_read(&req->ctx->cq_timeouts) + 1);
- spin_unlock_irqrestore(&ctx->timeout_lock, flags);
-
- if (!(data->flags & IORING_TIMEOUT_ETIME_SUCCESS))
- req_set_fail(req);
-
- req->cqe.res = -ETIME;
- req->io_task_work.func = io_req_task_complete;
- io_req_task_work_add(req);
- return HRTIMER_NORESTART;
-}
-
-static struct io_kiocb *io_timeout_extract(struct io_ring_ctx *ctx,
- struct io_cancel_data *cd)
- __must_hold(&ctx->timeout_lock)
-{
- struct io_timeout_data *io;
- struct io_kiocb *req;
- bool found = false;
-
- list_for_each_entry(req, &ctx->timeout_list, timeout.list) {
- if (!(cd->flags & IORING_ASYNC_CANCEL_ANY) &&
- cd->data != req->cqe.user_data)
- continue;
- if (cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY)) {
- if (cd->seq == req->work.cancel_seq)
- continue;
- req->work.cancel_seq = cd->seq;
- }
- found = true;
- break;
- }
- if (!found)
- return ERR_PTR(-ENOENT);
-
- io = req->async_data;
- if (hrtimer_try_to_cancel(&io->timer) == -1)
- return ERR_PTR(-EALREADY);
- list_del_init(&req->timeout.list);
- return req;
-}
-
-static int io_timeout_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd)
- __must_hold(&ctx->completion_lock)
-{
- struct io_kiocb *req;
-
- spin_lock_irq(&ctx->timeout_lock);
- req = io_timeout_extract(ctx, cd);
- spin_unlock_irq(&ctx->timeout_lock);
-
- if (IS_ERR(req))
- return PTR_ERR(req);
- io_req_task_queue_fail(req, -ECANCELED);
- return 0;
-}
-
-static clockid_t io_timeout_get_clock(struct io_timeout_data *data)
-{
- switch (data->flags & IORING_TIMEOUT_CLOCK_MASK) {
- case IORING_TIMEOUT_BOOTTIME:
- return CLOCK_BOOTTIME;
- case IORING_TIMEOUT_REALTIME:
- return CLOCK_REALTIME;
- default:
- /* can't happen, vetted at prep time */
- WARN_ON_ONCE(1);
- fallthrough;
- case 0:
- return CLOCK_MONOTONIC;
- }
-}
-
-static int io_linked_timeout_update(struct io_ring_ctx *ctx, __u64 user_data,
- struct timespec64 *ts, enum hrtimer_mode mode)
- __must_hold(&ctx->timeout_lock)
-{
- struct io_timeout_data *io;
- struct io_kiocb *req;
- bool found = false;
-
- list_for_each_entry(req, &ctx->ltimeout_list, timeout.list) {
- found = user_data == req->cqe.user_data;
- if (found)
- break;
- }
- if (!found)
- return -ENOENT;
-
- io = req->async_data;
- if (hrtimer_try_to_cancel(&io->timer) == -1)
- return -EALREADY;
- hrtimer_init(&io->timer, io_timeout_get_clock(io), mode);
- io->timer.function = io_link_timeout_fn;
- hrtimer_start(&io->timer, timespec64_to_ktime(*ts), mode);
- return 0;
-}
-
-static int io_timeout_update(struct io_ring_ctx *ctx, __u64 user_data,
- struct timespec64 *ts, enum hrtimer_mode mode)
- __must_hold(&ctx->timeout_lock)
-{
- struct io_cancel_data cd = { .data = user_data, };
- struct io_kiocb *req = io_timeout_extract(ctx, &cd);
- struct io_timeout_data *data;
-
- if (IS_ERR(req))
- return PTR_ERR(req);
-
- req->timeout.off = 0; /* noseq */
- data = req->async_data;
- list_add_tail(&req->timeout.list, &ctx->timeout_list);
- hrtimer_init(&data->timer, io_timeout_get_clock(data), mode);
- data->timer.function = io_timeout_fn;
- hrtimer_start(&data->timer, timespec64_to_ktime(*ts), mode);
- return 0;
-}
-
-static int io_timeout_remove_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- struct io_timeout_rem *tr = &req->timeout_rem;
-
- if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT)))
- return -EINVAL;
- if (sqe->buf_index || sqe->len || sqe->splice_fd_in)
- return -EINVAL;
-
- tr->ltimeout = false;
- tr->addr = READ_ONCE(sqe->addr);
- tr->flags = READ_ONCE(sqe->timeout_flags);
- if (tr->flags & IORING_TIMEOUT_UPDATE_MASK) {
- if (hweight32(tr->flags & IORING_TIMEOUT_CLOCK_MASK) > 1)
- return -EINVAL;
- if (tr->flags & IORING_LINK_TIMEOUT_UPDATE)
- tr->ltimeout = true;
- if (tr->flags & ~(IORING_TIMEOUT_UPDATE_MASK|IORING_TIMEOUT_ABS))
- return -EINVAL;
- if (get_timespec64(&tr->ts, u64_to_user_ptr(sqe->addr2)))
- return -EFAULT;
- if (tr->ts.tv_sec < 0 || tr->ts.tv_nsec < 0)
- return -EINVAL;
- } else if (tr->flags) {
- /* timeout removal doesn't support flags */
- return -EINVAL;
- }
-
- return 0;
-}
-
-static inline enum hrtimer_mode io_translate_timeout_mode(unsigned int flags)
-{
- return (flags & IORING_TIMEOUT_ABS) ? HRTIMER_MODE_ABS
- : HRTIMER_MODE_REL;
-}
-
-/*
- * Remove or update an existing timeout command
- */
-static int io_timeout_remove(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_timeout_rem *tr = &req->timeout_rem;
- struct io_ring_ctx *ctx = req->ctx;
- int ret;
-
- if (!(req->timeout_rem.flags & IORING_TIMEOUT_UPDATE)) {
- struct io_cancel_data cd = { .data = tr->addr, };
-
- spin_lock(&ctx->completion_lock);
- ret = io_timeout_cancel(ctx, &cd);
- spin_unlock(&ctx->completion_lock);
- } else {
- enum hrtimer_mode mode = io_translate_timeout_mode(tr->flags);
-
- spin_lock_irq(&ctx->timeout_lock);
- if (tr->ltimeout)
- ret = io_linked_timeout_update(ctx, tr->addr, &tr->ts, mode);
- else
- ret = io_timeout_update(ctx, tr->addr, &tr->ts, mode);
- spin_unlock_irq(&ctx->timeout_lock);
- }
-
- if (ret < 0)
- req_set_fail(req);
- io_req_complete_post(req, ret, 0);
- return 0;
-}
-
-static int __io_timeout_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe,
- bool is_timeout_link)
-{
- struct io_timeout_data *data;
- unsigned flags;
- u32 off = READ_ONCE(sqe->off);
-
- if (sqe->buf_index || sqe->len != 1 || sqe->splice_fd_in)
- return -EINVAL;
- if (off && is_timeout_link)
- return -EINVAL;
- flags = READ_ONCE(sqe->timeout_flags);
- if (flags & ~(IORING_TIMEOUT_ABS | IORING_TIMEOUT_CLOCK_MASK |
- IORING_TIMEOUT_ETIME_SUCCESS))
- return -EINVAL;
- /* more than one clock specified is invalid, obviously */
- if (hweight32(flags & IORING_TIMEOUT_CLOCK_MASK) > 1)
- return -EINVAL;
-
- INIT_LIST_HEAD(&req->timeout.list);
- req->timeout.off = off;
- if (unlikely(off && !req->ctx->off_timeout_used))
- req->ctx->off_timeout_used = true;
-
- if (WARN_ON_ONCE(req_has_async_data(req)))
- return -EFAULT;
- if (io_alloc_async_data(req))
- return -ENOMEM;
-
- data = req->async_data;
- data->req = req;
- data->flags = flags;
-
- if (get_timespec64(&data->ts, u64_to_user_ptr(sqe->addr)))
- return -EFAULT;
-
- if (data->ts.tv_sec < 0 || data->ts.tv_nsec < 0)
- return -EINVAL;
-
- INIT_LIST_HEAD(&req->timeout.list);
- data->mode = io_translate_timeout_mode(flags);
- hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode);
-
- if (is_timeout_link) {
- struct io_submit_link *link = &req->ctx->submit_state.link;
-
- if (!link->head)
- return -EINVAL;
- if (link->last->opcode == IORING_OP_LINK_TIMEOUT)
- return -EINVAL;
- req->timeout.head = link->last;
- link->last->flags |= REQ_F_ARM_LTIMEOUT;
- }
- return 0;
-}
-
-static int io_timeout_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- return __io_timeout_prep(req, sqe, false);
-}
-
-static int io_link_timeout_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- return __io_timeout_prep(req, sqe, true);
-}
-
-static int io_timeout(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_ring_ctx *ctx = req->ctx;
- struct io_timeout_data *data = req->async_data;
- struct list_head *entry;
- u32 tail, off = req->timeout.off;
-
- spin_lock_irq(&ctx->timeout_lock);
-
- /*
- * sqe->off holds how many events that need to occur for this
- * timeout event to be satisfied. If it isn't set, then this is
- * a pure timeout request, sequence isn't used.
- */
- if (io_is_timeout_noseq(req)) {
- entry = ctx->timeout_list.prev;
- goto add;
- }
-
- tail = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
- req->timeout.target_seq = tail + off;
-
- /* Update the last seq here in case io_flush_timeouts() hasn't.
- * This is safe because ->completion_lock is held, and submissions
- * and completions are never mixed in the same ->completion_lock section.
- */
- ctx->cq_last_tm_flush = tail;
-
- /*
- * Insertion sort, ensuring the first entry in the list is always
- * the one we need first.
- */
- list_for_each_prev(entry, &ctx->timeout_list) {
- struct io_kiocb *nxt = list_entry(entry, struct io_kiocb,
- timeout.list);
-
- if (io_is_timeout_noseq(nxt))
- continue;
- /* nxt.seq is behind @tail, otherwise would've been completed */
- if (off >= nxt->timeout.target_seq - tail)
- break;
- }
-add:
- list_add(&req->timeout.list, entry);
- data->timer.function = io_timeout_fn;
- hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), data->mode);
- spin_unlock_irq(&ctx->timeout_lock);
- return 0;
-}
-
-static bool io_cancel_cb(struct io_wq_work *work, void *data)
-{
- struct io_kiocb *req = container_of(work, struct io_kiocb, work);
- struct io_cancel_data *cd = data;
-
- if (req->ctx != cd->ctx)
- return false;
- if (cd->flags & IORING_ASYNC_CANCEL_ANY) {
- ;
- } else if (cd->flags & IORING_ASYNC_CANCEL_FD) {
- if (req->file != cd->file)
- return false;
- } else {
- if (req->cqe.user_data != cd->data)
- return false;
- }
- if (cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY)) {
- if (cd->seq == req->work.cancel_seq)
- return false;
- req->work.cancel_seq = cd->seq;
- }
- return true;
-}
-
-static int io_async_cancel_one(struct io_uring_task *tctx,
- struct io_cancel_data *cd)
-{
- enum io_wq_cancel cancel_ret;
- int ret = 0;
- bool all;
-
- if (!tctx || !tctx->io_wq)
- return -ENOENT;
-
- all = cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY);
- cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, cd, all);
- switch (cancel_ret) {
- case IO_WQ_CANCEL_OK:
- ret = 0;
- break;
- case IO_WQ_CANCEL_RUNNING:
- ret = -EALREADY;
- break;
- case IO_WQ_CANCEL_NOTFOUND:
- ret = -ENOENT;
- break;
- }
-
- return ret;
-}
-
-static int io_try_cancel(struct io_kiocb *req, struct io_cancel_data *cd)
-{
- struct io_ring_ctx *ctx = req->ctx;
- int ret;
-
- WARN_ON_ONCE(!io_wq_current_is_worker() && req->task != current);
-
- ret = io_async_cancel_one(req->task->io_uring, cd);
- /*
- * Fall-through even for -EALREADY, as we may have poll armed
- * that need unarming.
- */
- if (!ret)
- return 0;
-
- spin_lock(&ctx->completion_lock);
- ret = io_poll_cancel(ctx, cd);
- if (ret != -ENOENT)
- goto out;
- if (!(cd->flags & IORING_ASYNC_CANCEL_FD))
- ret = io_timeout_cancel(ctx, cd);
-out:
- spin_unlock(&ctx->completion_lock);
- return ret;
-}
-
-#define CANCEL_FLAGS (IORING_ASYNC_CANCEL_ALL | IORING_ASYNC_CANCEL_FD | \
- IORING_ASYNC_CANCEL_ANY)
-
-static int io_async_cancel_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- if (unlikely(req->flags & REQ_F_BUFFER_SELECT))
- return -EINVAL;
- if (sqe->off || sqe->len || sqe->splice_fd_in)
- return -EINVAL;
-
- req->cancel.addr = READ_ONCE(sqe->addr);
- req->cancel.flags = READ_ONCE(sqe->cancel_flags);
- if (req->cancel.flags & ~CANCEL_FLAGS)
- return -EINVAL;
- if (req->cancel.flags & IORING_ASYNC_CANCEL_FD) {
- if (req->cancel.flags & IORING_ASYNC_CANCEL_ANY)
- return -EINVAL;
- req->cancel.fd = READ_ONCE(sqe->fd);
- }
-
- return 0;
-}
-
-static int __io_async_cancel(struct io_cancel_data *cd, struct io_kiocb *req,
- unsigned int issue_flags)
-{
- bool all = cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY);
- struct io_ring_ctx *ctx = cd->ctx;
- struct io_tctx_node *node;
- int ret, nr = 0;
-
- do {
- ret = io_try_cancel(req, cd);
- if (ret == -ENOENT)
- break;
- if (!all)
- return ret;
- nr++;
- } while (1);
-
- /* slow path, try all io-wq's */
- io_ring_submit_lock(ctx, issue_flags);
- ret = -ENOENT;
- list_for_each_entry(node, &ctx->tctx_list, ctx_node) {
- struct io_uring_task *tctx = node->task->io_uring;
-
- ret = io_async_cancel_one(tctx, cd);
- if (ret != -ENOENT) {
- if (!all)
- break;
- nr++;
- }
- }
- io_ring_submit_unlock(ctx, issue_flags);
- return all ? nr : ret;
-}
-
-static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_cancel_data cd = {
- .ctx = req->ctx,
- .data = req->cancel.addr,
- .flags = req->cancel.flags,
- .seq = atomic_inc_return(&req->ctx->cancel_seq),
- };
- int ret;
-
- if (cd.flags & IORING_ASYNC_CANCEL_FD) {
- if (req->flags & REQ_F_FIXED_FILE)
- req->file = io_file_get_fixed(req, req->cancel.fd,
- issue_flags);
- else
- req->file = io_file_get_normal(req, req->cancel.fd);
- if (!req->file) {
- ret = -EBADF;
- goto done;
- }
- cd.file = req->file;
- }
-
- ret = __io_async_cancel(&cd, req, issue_flags);
-done:
- if (ret < 0)
- req_set_fail(req);
- io_req_complete_post(req, ret, 0);
- return 0;
-}
-
-static int io_files_update_prep(struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
-{
- if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT)))
- return -EINVAL;
- if (sqe->rw_flags || sqe->splice_fd_in)
- return -EINVAL;
-
- req->rsrc_update.offset = READ_ONCE(sqe->off);
- req->rsrc_update.nr_args = READ_ONCE(sqe->len);
- if (!req->rsrc_update.nr_args)
- return -EINVAL;
- req->rsrc_update.arg = READ_ONCE(sqe->addr);
- return 0;
-}
-
-static int io_files_update_with_index_alloc(struct io_kiocb *req,
- unsigned int issue_flags)
-{
- __s32 __user *fds = u64_to_user_ptr(req->rsrc_update.arg);
- unsigned int done;
- struct file *file;
- int ret, fd;
-
- if (!req->ctx->file_data)
- return -ENXIO;
-
- for (done = 0; done < req->rsrc_update.nr_args; done++) {
- if (copy_from_user(&fd, &fds[done], sizeof(fd))) {
- ret = -EFAULT;
- break;
- }
-
- file = fget(fd);
- if (!file) {
- ret = -EBADF;
- break;
- }
- ret = io_fixed_fd_install(req, issue_flags, file,
- IORING_FILE_INDEX_ALLOC);
- if (ret < 0)
- break;
- if (copy_to_user(&fds[done], &ret, sizeof(ret))) {
- __io_close_fixed(req, issue_flags, ret);
- ret = -EFAULT;
- break;
- }
- }
-
- if (done)
- return done;
- return ret;
-}
-
-static int io_files_update(struct io_kiocb *req, unsigned int issue_flags)
-{
- struct io_ring_ctx *ctx = req->ctx;
- struct io_uring_rsrc_update2 up;
- int ret;
-
- up.offset = req->rsrc_update.offset;
- up.data = req->rsrc_update.arg;
- up.nr = 0;
- up.tags = 0;
- up.resv = 0;
- up.resv2 = 0;
-
- if (req->rsrc_update.offset == IORING_FILE_INDEX_ALLOC) {
- ret = io_files_update_with_index_alloc(req, issue_flags);
- } else {
- io_ring_submit_lock(ctx, issue_flags);
- ret = __io_register_rsrc_update(ctx, IORING_RSRC_FILE,
- &up, req->rsrc_update.nr_args);
- io_ring_submit_unlock(ctx, issue_flags);
- }
-
- if (ret < 0)
- req_set_fail(req);
- __io_req_complete(req, issue_flags, ret, 0);
- return 0;
-}
-
-static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
-{
- switch (req->opcode) {
- case IORING_OP_NOP:
- return io_nop_prep(req, sqe);
- case IORING_OP_READV:
- case IORING_OP_READ_FIXED:
- case IORING_OP_READ:
- case IORING_OP_WRITEV:
- case IORING_OP_WRITE_FIXED:
- case IORING_OP_WRITE:
- return io_prep_rw(req, sqe);
- case IORING_OP_POLL_ADD:
- return io_poll_add_prep(req, sqe);
- case IORING_OP_POLL_REMOVE:
- return io_poll_remove_prep(req, sqe);
- case IORING_OP_FSYNC:
- return io_fsync_prep(req, sqe);
- case IORING_OP_SYNC_FILE_RANGE:
- return io_sfr_prep(req, sqe);
- case IORING_OP_SENDMSG:
- case IORING_OP_SEND:
- return io_sendmsg_prep(req, sqe);
- case IORING_OP_RECVMSG:
- case IORING_OP_RECV:
- return io_recvmsg_prep(req, sqe);
- case IORING_OP_CONNECT:
- return io_connect_prep(req, sqe);
- case IORING_OP_TIMEOUT:
- return io_timeout_prep(req, sqe);
- case IORING_OP_TIMEOUT_REMOVE:
- return io_timeout_remove_prep(req, sqe);
- case IORING_OP_ASYNC_CANCEL:
- return io_async_cancel_prep(req, sqe);
- case IORING_OP_LINK_TIMEOUT:
- return io_link_timeout_prep(req, sqe);
- case IORING_OP_ACCEPT:
- return io_accept_prep(req, sqe);
- case IORING_OP_FALLOCATE:
- return io_fallocate_prep(req, sqe);
- case IORING_OP_OPENAT:
- return io_openat_prep(req, sqe);
- case IORING_OP_CLOSE:
- return io_close_prep(req, sqe);
- case IORING_OP_FILES_UPDATE:
- return io_files_update_prep(req, sqe);
- case IORING_OP_STATX:
- return io_statx_prep(req, sqe);
- case IORING_OP_FADVISE:
- return io_fadvise_prep(req, sqe);
- case IORING_OP_MADVISE:
- return io_madvise_prep(req, sqe);
- case IORING_OP_OPENAT2:
- return io_openat2_prep(req, sqe);
- case IORING_OP_EPOLL_CTL:
- return io_epoll_ctl_prep(req, sqe);
- case IORING_OP_SPLICE:
- return io_splice_prep(req, sqe);
- case IORING_OP_PROVIDE_BUFFERS:
- return io_provide_buffers_prep(req, sqe);
- case IORING_OP_REMOVE_BUFFERS:
- return io_remove_buffers_prep(req, sqe);
- case IORING_OP_TEE:
- return io_tee_prep(req, sqe);
- case IORING_OP_SHUTDOWN:
- return io_shutdown_prep(req, sqe);
- case IORING_OP_RENAMEAT:
- return io_renameat_prep(req, sqe);
- case IORING_OP_UNLINKAT:
- return io_unlinkat_prep(req, sqe);
- case IORING_OP_MKDIRAT:
- return io_mkdirat_prep(req, sqe);
- case IORING_OP_SYMLINKAT:
- return io_symlinkat_prep(req, sqe);
- case IORING_OP_LINKAT:
- return io_linkat_prep(req, sqe);
- case IORING_OP_MSG_RING:
- return io_msg_ring_prep(req, sqe);
- case IORING_OP_FSETXATTR:
- return io_fsetxattr_prep(req, sqe);
- case IORING_OP_SETXATTR:
- return io_setxattr_prep(req, sqe);
- case IORING_OP_FGETXATTR:
- return io_fgetxattr_prep(req, sqe);
- case IORING_OP_GETXATTR:
- return io_getxattr_prep(req, sqe);
- case IORING_OP_SOCKET:
- return io_socket_prep(req, sqe);
- case IORING_OP_URING_CMD:
- return io_uring_cmd_prep(req, sqe);
- }
-
- printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
- req->opcode);
- return -EINVAL;
-}
-
-static int io_req_prep_async(struct io_kiocb *req)
-{
- const struct io_op_def *def = &io_op_defs[req->opcode];
-
- /* assign early for deferred execution for non-fixed file */
- if (def->needs_file && !(req->flags & REQ_F_FIXED_FILE))
- req->file = io_file_get_normal(req, req->cqe.fd);
- if (!def->needs_async_setup)
- return 0;
- if (WARN_ON_ONCE(req_has_async_data(req)))
- return -EFAULT;
- if (io_alloc_async_data(req))
- return -EAGAIN;
-
- switch (req->opcode) {
- case IORING_OP_READV:
- return io_readv_prep_async(req);
- case IORING_OP_WRITEV:
- return io_writev_prep_async(req);
- case IORING_OP_SENDMSG:
- return io_sendmsg_prep_async(req);
- case IORING_OP_RECVMSG:
- return io_recvmsg_prep_async(req);
- case IORING_OP_CONNECT:
- return io_connect_prep_async(req);
- case IORING_OP_URING_CMD:
- return io_uring_cmd_prep_async(req);
- }
- printk_once(KERN_WARNING "io_uring: prep_async() bad opcode %d\n",
- req->opcode);
- return -EFAULT;
-}
-
-static u32 io_get_sequence(struct io_kiocb *req)
-{
- u32 seq = req->ctx->cached_sq_head;
- struct io_kiocb *cur;
-
- /* need original cached_sq_head, but it was increased for each req */
- io_for_each_link(cur, req)
- seq--;
- return seq;
-}
-
-static __cold void io_drain_req(struct io_kiocb *req)
-{
- struct io_ring_ctx *ctx = req->ctx;
- struct io_defer_entry *de;
- int ret;
- u32 seq = io_get_sequence(req);
-
- /* Still need defer if there is pending req in defer list. */
- spin_lock(&ctx->completion_lock);
- if (!req_need_defer(req, seq) && list_empty_careful(&ctx->defer_list)) {
- spin_unlock(&ctx->completion_lock);
-queue:
- ctx->drain_active = false;
- io_req_task_queue(req);
- return;
- }
- spin_unlock(&ctx->completion_lock);
-
- ret = io_req_prep_async(req);
- if (ret) {
-fail:
- io_req_complete_failed(req, ret);
- return;
- }
- io_prep_async_link(req);
- de = kmalloc(sizeof(*de), GFP_KERNEL);
- if (!de) {
- ret = -ENOMEM;
- goto fail;
- }
-
- spin_lock(&ctx->completion_lock);
- if (!req_need_defer(req, seq) && list_empty(&ctx->defer_list)) {
- spin_unlock(&ctx->completion_lock);
- kfree(de);
- goto queue;
- }
-
- trace_io_uring_defer(ctx, req, req->cqe.user_data, req->opcode);
- de->req = req;
- de->seq = seq;
- list_add_tail(&de->list, &ctx->defer_list);
- spin_unlock(&ctx->completion_lock);
-}
-
-static void io_clean_op(struct io_kiocb *req)
-{
- if (req->flags & REQ_F_BUFFER_SELECTED) {
- spin_lock(&req->ctx->completion_lock);
- io_put_kbuf_comp(req);
- spin_unlock(&req->ctx->completion_lock);
- }
-
- if (req->flags & REQ_F_NEED_CLEANUP) {
- switch (req->opcode) {
- case IORING_OP_READV:
- case IORING_OP_READ_FIXED:
- case IORING_OP_READ:
- case IORING_OP_WRITEV:
- case IORING_OP_WRITE_FIXED:
- case IORING_OP_WRITE: {
- struct io_async_rw *io = req->async_data;
-
- kfree(io->free_iovec);
- break;
- }
- case IORING_OP_RECVMSG:
- case IORING_OP_SENDMSG: {
- struct io_async_msghdr *io = req->async_data;
-
- kfree(io->free_iov);
- break;
- }
- case IORING_OP_OPENAT:
- case IORING_OP_OPENAT2:
- if (req->open.filename)
- putname(req->open.filename);
- break;
- case IORING_OP_RENAMEAT:
- putname(req->rename.oldpath);
- putname(req->rename.newpath);
- break;
- case IORING_OP_UNLINKAT:
- putname(req->unlink.filename);
- break;
- case IORING_OP_MKDIRAT:
- putname(req->mkdir.filename);
- break;
- case IORING_OP_SYMLINKAT:
- putname(req->symlink.oldpath);
- putname(req->symlink.newpath);
- break;
- case IORING_OP_LINKAT:
- putname(req->hardlink.oldpath);
- putname(req->hardlink.newpath);
- break;
- case IORING_OP_STATX:
- if (req->statx.filename)
- putname(req->statx.filename);
- break;
- case IORING_OP_SETXATTR:
- case IORING_OP_FSETXATTR:
- case IORING_OP_GETXATTR:
- case IORING_OP_FGETXATTR:
- __io_xattr_finish(req);
- break;
- }
- }
- if ((req->flags & REQ_F_POLLED) && req->apoll) {
- kfree(req->apoll->double_poll);
- kfree(req->apoll);
- req->apoll = NULL;
- }
- if (req->flags & REQ_F_INFLIGHT) {
- struct io_uring_task *tctx = req->task->io_uring;
-
- atomic_dec(&tctx->inflight_tracked);
- }
- if (req->flags & REQ_F_CREDS)
- put_cred(req->creds);
- if (req->flags & REQ_F_ASYNC_DATA) {
- kfree(req->async_data);
- req->async_data = NULL;
- }
- req->flags &= ~IO_REQ_CLEAN_FLAGS;
-}
-
-static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags)
-{
- if (req->file || !io_op_defs[req->opcode].needs_file)
- return true;
-
- if (req->flags & REQ_F_FIXED_FILE)
- req->file = io_file_get_fixed(req, req->cqe.fd, issue_flags);
- else
- req->file = io_file_get_normal(req, req->cqe.fd);
-
- return !!req->file;
-}
-
-static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
-{
- const struct io_op_def *def = &io_op_defs[req->opcode];
- const struct cred *creds = NULL;
- int ret;
-
- if (unlikely(!io_assign_file(req, issue_flags)))
- return -EBADF;
-
- if (unlikely((req->flags & REQ_F_CREDS) && req->creds != current_cred()))
- creds = override_creds(req->creds);
-
- if (!def->audit_skip)
- audit_uring_entry(req->opcode);
-
- switch (req->opcode) {
- case IORING_OP_NOP:
- ret = io_nop(req, issue_flags);
- break;
- case IORING_OP_READV:
- case IORING_OP_READ_FIXED:
- case IORING_OP_READ:
- ret = io_read(req, issue_flags);
- break;
- case IORING_OP_WRITEV:
- case IORING_OP_WRITE_FIXED:
- case IORING_OP_WRITE:
- ret = io_write(req, issue_flags);
- break;
- case IORING_OP_FSYNC:
- ret = io_fsync(req, issue_flags);
- break;
- case IORING_OP_POLL_ADD:
- ret = io_poll_add(req, issue_flags);
- break;
- case IORING_OP_POLL_REMOVE:
- ret = io_poll_remove(req, issue_flags);
- break;
- case IORING_OP_SYNC_FILE_RANGE:
- ret = io_sync_file_range(req, issue_flags);
- break;
- case IORING_OP_SENDMSG:
- ret = io_sendmsg(req, issue_flags);
- break;
- case IORING_OP_SEND:
- ret = io_send(req, issue_flags);
- break;
- case IORING_OP_RECVMSG:
- ret = io_recvmsg(req, issue_flags);
- break;
- case IORING_OP_RECV:
- ret = io_recv(req, issue_flags);
- break;
- case IORING_OP_TIMEOUT:
- ret = io_timeout(req, issue_flags);
- break;
- case IORING_OP_TIMEOUT_REMOVE:
- ret = io_timeout_remove(req, issue_flags);
- break;
- case IORING_OP_ACCEPT:
- ret = io_accept(req, issue_flags);
- break;
- case IORING_OP_CONNECT:
- ret = io_connect(req, issue_flags);
- break;
- case IORING_OP_ASYNC_CANCEL:
- ret = io_async_cancel(req, issue_flags);
- break;
- case IORING_OP_FALLOCATE:
- ret = io_fallocate(req, issue_flags);
- break;
- case IORING_OP_OPENAT:
- ret = io_openat(req, issue_flags);
- break;
- case IORING_OP_CLOSE:
- ret = io_close(req, issue_flags);
- break;
- case IORING_OP_FILES_UPDATE:
- ret = io_files_update(req, issue_flags);
- break;
- case IORING_OP_STATX:
- ret = io_statx(req, issue_flags);
- break;
- case IORING_OP_FADVISE:
- ret = io_fadvise(req, issue_flags);
- break;
- case IORING_OP_MADVISE:
- ret = io_madvise(req, issue_flags);
- break;
- case IORING_OP_OPENAT2:
- ret = io_openat2(req, issue_flags);
- break;
- case IORING_OP_EPOLL_CTL:
- ret = io_epoll_ctl(req, issue_flags);
- break;
- case IORING_OP_SPLICE:
- ret = io_splice(req, issue_flags);
- break;
- case IORING_OP_PROVIDE_BUFFERS:
- ret = io_provide_buffers(req, issue_flags);
- break;
- case IORING_OP_REMOVE_BUFFERS:
- ret = io_remove_buffers(req, issue_flags);
- break;
- case IORING_OP_TEE:
- ret = io_tee(req, issue_flags);
- break;
- case IORING_OP_SHUTDOWN:
- ret = io_shutdown(req, issue_flags);
- break;
- case IORING_OP_RENAMEAT:
- ret = io_renameat(req, issue_flags);
- break;
- case IORING_OP_UNLINKAT:
- ret = io_unlinkat(req, issue_flags);
- break;
- case IORING_OP_MKDIRAT:
- ret = io_mkdirat(req, issue_flags);
- break;
- case IORING_OP_SYMLINKAT:
- ret = io_symlinkat(req, issue_flags);
- break;
- case IORING_OP_LINKAT:
- ret = io_linkat(req, issue_flags);
- break;
- case IORING_OP_MSG_RING:
- ret = io_msg_ring(req, issue_flags);
- break;
- case IORING_OP_FSETXATTR:
- ret = io_fsetxattr(req, issue_flags);
- break;
- case IORING_OP_SETXATTR:
- ret = io_setxattr(req, issue_flags);
- break;
- case IORING_OP_FGETXATTR:
- ret = io_fgetxattr(req, issue_flags);
- break;
- case IORING_OP_GETXATTR:
- ret = io_getxattr(req, issue_flags);
- break;
- case IORING_OP_SOCKET:
- ret = io_socket(req, issue_flags);
- break;
- case IORING_OP_URING_CMD:
- ret = io_uring_cmd(req, issue_flags);
- break;
- default:
- ret = -EINVAL;
- break;
- }
-
- if (!def->audit_skip)
- audit_uring_exit(!ret, ret);
-
- if (creds)
- revert_creds(creds);
- if (ret)
- return ret;
- /* If the op doesn't have a file, we're not polling for it */
- if ((req->ctx->flags & IORING_SETUP_IOPOLL) && req->file)
- io_iopoll_req_issued(req, issue_flags);
-
- return 0;
-}
-
-static struct io_wq_work *io_wq_free_work(struct io_wq_work *work)
-{
- struct io_kiocb *req = container_of(work, struct io_kiocb, work);
-
- req = io_put_req_find_next(req);
- return req ? &req->work : NULL;
-}
-
-static void io_wq_submit_work(struct io_wq_work *work)
-{
- struct io_kiocb *req = container_of(work, struct io_kiocb, work);
- const struct io_op_def *def = &io_op_defs[req->opcode];
- unsigned int issue_flags = IO_URING_F_UNLOCKED;
- bool needs_poll = false;
- int ret = 0, err = -ECANCELED;
-
- /* one will be dropped by ->io_free_work() after returning to io-wq */
- if (!(req->flags & REQ_F_REFCOUNT))
- __io_req_set_refcount(req, 2);
- else
- req_ref_get(req);
-
- io_arm_ltimeout(req);
-
- /* either cancelled or io-wq is dying, so don't touch tctx->iowq */
- if (work->flags & IO_WQ_WORK_CANCEL) {
-fail:
- io_req_task_queue_fail(req, err);
- return;
- }
- if (!io_assign_file(req, issue_flags)) {
- err = -EBADF;
- work->flags |= IO_WQ_WORK_CANCEL;
- goto fail;
- }
-
- if (req->flags & REQ_F_FORCE_ASYNC) {
- bool opcode_poll = def->pollin || def->pollout;
-
- if (opcode_poll && file_can_poll(req->file)) {
- needs_poll = true;
- issue_flags |= IO_URING_F_NONBLOCK;
- }
- }
-
- do {
- ret = io_issue_sqe(req, issue_flags);
- if (ret != -EAGAIN)
- break;
- /*
- * We can get EAGAIN for iopolled IO even though we're
- * forcing a sync submission from here, since we can't
- * wait for request slots on the block side.
- */
- if (!needs_poll) {
- if (!(req->ctx->flags & IORING_SETUP_IOPOLL))
- break;
- cond_resched();
- continue;
- }
-
- if (io_arm_poll_handler(req, issue_flags) == IO_APOLL_OK)
- return;
- /* aborted or ready, in either case retry blocking */
- needs_poll = false;
- issue_flags &= ~IO_URING_F_NONBLOCK;
- } while (1);
-
- /* avoid locking problems by failing it from a clean context */
- if (ret)
- io_req_task_queue_fail(req, ret);
-}
-
-static inline struct io_fixed_file *io_fixed_file_slot(struct io_file_table *table,
- unsigned i)
-{
- return &table->files[i];
-}
-
-static inline struct file *io_file_from_index(struct io_ring_ctx *ctx,
- int index)
-{
- struct io_fixed_file *slot = io_fixed_file_slot(&ctx->file_table, index);
-
- return (struct file *) (slot->file_ptr & FFS_MASK);
-}
-
-static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file)
-{
- unsigned long file_ptr = (unsigned long) file;
-
- file_ptr |= io_file_get_flags(file);
- file_slot->file_ptr = file_ptr;
-}
-
-static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
- unsigned int issue_flags)
-{
- struct io_ring_ctx *ctx = req->ctx;
- struct file *file = NULL;
- unsigned long file_ptr;
-
- io_ring_submit_lock(ctx, issue_flags);
-
- if (unlikely((unsigned int)fd >= ctx->nr_user_files))
- goto out;
- fd = array_index_nospec(fd, ctx->nr_user_files);
- file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr;
- file = (struct file *) (file_ptr & FFS_MASK);
- file_ptr &= ~FFS_MASK;
- /* mask in overlapping REQ_F and FFS bits */
- req->flags |= (file_ptr << REQ_F_SUPPORT_NOWAIT_BIT);
- io_req_set_rsrc_node(req, ctx, 0);
- WARN_ON_ONCE(file && !test_bit(fd, ctx->file_table.bitmap));
-out:
- io_ring_submit_unlock(ctx, issue_flags);
- return file;
-}
-
-static struct file *io_file_get_normal(struct io_kiocb *req, int fd)
-{
- struct file *file = fget(fd);
-
- trace_io_uring_file_get(req->ctx, req, req->cqe.user_data, fd);
-
- /* we don't allow fixed io_uring files */
- if (file && file->f_op == &io_uring_fops)
- io_req_track_inflight(req);
- return file;
-}
-
-static void io_req_task_link_timeout(struct io_kiocb *req, bool *locked)
-{
- struct io_kiocb *prev = req->timeout.prev;
- int ret = -ENOENT;
-
- if (prev) {
- if (!(req->task->flags & PF_EXITING)) {
- struct io_cancel_data cd = {
- .ctx = req->ctx,
- .data = prev->cqe.user_data,
- };
-
- ret = io_try_cancel(req, &cd);
- }
- io_req_complete_post(req, ret ?: -ETIME, 0);
- io_put_req(prev);
- } else {
- io_req_complete_post(req, -ETIME, 0);
- }
-}
-
-static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer)
-{
- struct io_timeout_data *data = container_of(timer,
- struct io_timeout_data, timer);
- struct io_kiocb *prev, *req = data->req;
- struct io_ring_ctx *ctx = req->ctx;
- unsigned long flags;
-
- spin_lock_irqsave(&ctx->timeout_lock, flags);
- prev = req->timeout.head;
- req->timeout.head = NULL;
-
- /*
- * We don't expect the list to be empty, that will only happen if we
- * race with the completion of the linked work.
- */
- if (prev) {
- io_remove_next_linked(prev);
- if (!req_ref_inc_not_zero(prev))
- prev = NULL;
- }
- list_del(&req->timeout.list);
- req->timeout.prev = prev;
- spin_unlock_irqrestore(&ctx->timeout_lock, flags);
-
- req->io_task_work.func = io_req_task_link_timeout;
- io_req_task_work_add(req);
- return HRTIMER_NORESTART;
-}
-
-static void io_queue_linked_timeout(struct io_kiocb *req)
-{
- struct io_ring_ctx *ctx = req->ctx;
-
- spin_lock_irq(&ctx->timeout_lock);
- /*
- * If the back reference is NULL, then our linked request finished
- * before we got a chance to setup the timer
- */
- if (req->timeout.head) {
- struct io_timeout_data *data = req->async_data;
-
- data->timer.function = io_link_timeout_fn;
- hrtimer_start(&data->timer, timespec64_to_ktime(data->ts),
- data->mode);
- list_add_tail(&req->timeout.list, &ctx->ltimeout_list);
- }
- spin_unlock_irq(&ctx->timeout_lock);
- /* drop submission reference */
- io_put_req(req);
-}
-
-static void io_queue_async(struct io_kiocb *req, int ret)
- __must_hold(&req->ctx->uring_lock)
-{
- struct io_kiocb *linked_timeout;
-
- if (ret != -EAGAIN || (req->flags & REQ_F_NOWAIT)) {
- io_req_complete_failed(req, ret);
- return;
- }
-
- linked_timeout = io_prep_linked_timeout(req);
-
- switch (io_arm_poll_handler(req, 0)) {
- case IO_APOLL_READY:
- io_req_task_queue(req);
- break;
- case IO_APOLL_ABORTED:
- /*
- * Queued up for async execution, worker will release
- * submit reference when the iocb is actually submitted.
- */
- io_kbuf_recycle(req, 0);
- io_queue_iowq(req, NULL);
- break;
- case IO_APOLL_OK:
- break;
- }
-
- if (linked_timeout)
- io_queue_linked_timeout(linked_timeout);
-}
-
-static inline void io_queue_sqe(struct io_kiocb *req)
- __must_hold(&req->ctx->uring_lock)
-{
- int ret;
-
- ret = io_issue_sqe(req, IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER);
-
- if (req->flags & REQ_F_COMPLETE_INLINE) {
- io_req_add_compl_list(req);
- return;
- }
- /*
- * We async punt it if the file wasn't marked NOWAIT, or if the file
- * doesn't support non-blocking read/write attempts
- */
- if (likely(!ret))
- io_arm_ltimeout(req);
- else
- io_queue_async(req, ret);
-}
-
-static void io_queue_sqe_fallback(struct io_kiocb *req)
- __must_hold(&req->ctx->uring_lock)
-{
- if (unlikely(req->flags & REQ_F_FAIL)) {
- /*
- * We don't submit, fail them all, for that replace hardlinks
- * with normal links. Extra REQ_F_LINK is tolerated.
- */
- req->flags &= ~REQ_F_HARDLINK;
- req->flags |= REQ_F_LINK;
- io_req_complete_failed(req, req->cqe.res);
- } else if (unlikely(req->ctx->drain_active)) {
- io_drain_req(req);
- } else {
- int ret = io_req_prep_async(req);
-
- if (unlikely(ret))
- io_req_complete_failed(req, ret);
- else
- io_queue_iowq(req, NULL);
- }
-}
-
-/*
- * Check SQE restrictions (opcode and flags).
- *
- * Returns 'true' if SQE is allowed, 'false' otherwise.
- */
-static inline bool io_check_restriction(struct io_ring_ctx *ctx,
- struct io_kiocb *req,
- unsigned int sqe_flags)
-{
- if (!test_bit(req->opcode, ctx->restrictions.sqe_op))
- return false;
-
- if ((sqe_flags & ctx->restrictions.sqe_flags_required) !=
- ctx->restrictions.sqe_flags_required)
- return false;
-
- if (sqe_flags & ~(ctx->restrictions.sqe_flags_allowed |
- ctx->restrictions.sqe_flags_required))
- return false;
-
- return true;
-}
-
-static void io_init_req_drain(struct io_kiocb *req)
-{
- struct io_ring_ctx *ctx = req->ctx;
- struct io_kiocb *head = ctx->submit_state.link.head;
-
- ctx->drain_active = true;
- if (head) {
- /*
- * If we need to drain a request in the middle of a link, drain
- * the head request and the next request/link after the current
- * link. Considering sequential execution of links,
- * REQ_F_IO_DRAIN will be maintained for every request of our
- * link.
- */
- head->flags |= REQ_F_IO_DRAIN | REQ_F_FORCE_ASYNC;
- ctx->drain_next = true;
- }
-}
-
-static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
- __must_hold(&ctx->uring_lock)
-{
- const struct io_op_def *def;
- unsigned int sqe_flags;
- int personality;
- u8 opcode;
-
- /* req is partially pre-initialised, see io_preinit_req() */
- req->opcode = opcode = READ_ONCE(sqe->opcode);
- /* same numerical values with corresponding REQ_F_*, safe to copy */
- req->flags = sqe_flags = READ_ONCE(sqe->flags);
- req->cqe.user_data = READ_ONCE(sqe->user_data);
- req->file = NULL;
- req->rsrc_node = NULL;
- req->task = current;
-
- if (unlikely(opcode >= IORING_OP_LAST)) {
- req->opcode = 0;
- return -EINVAL;
- }
- def = &io_op_defs[opcode];
- if (unlikely(sqe_flags & ~SQE_COMMON_FLAGS)) {
- /* enforce forwards compatibility on users */
- if (sqe_flags & ~SQE_VALID_FLAGS)
- return -EINVAL;
- if (sqe_flags & IOSQE_BUFFER_SELECT) {
- if (!def->buffer_select)
- return -EOPNOTSUPP;
- req->buf_index = READ_ONCE(sqe->buf_group);
- }
- if (sqe_flags & IOSQE_CQE_SKIP_SUCCESS)
- ctx->drain_disabled = true;
- if (sqe_flags & IOSQE_IO_DRAIN) {
- if (ctx->drain_disabled)
- return -EOPNOTSUPP;
- io_init_req_drain(req);
- }
- }
- if (unlikely(ctx->restricted || ctx->drain_active || ctx->drain_next)) {
- if (ctx->restricted && !io_check_restriction(ctx, req, sqe_flags))
- return -EACCES;
- /* knock it to the slow queue path, will be drained there */
- if (ctx->drain_active)
- req->flags |= REQ_F_FORCE_ASYNC;
- /* if there is no link, we're at "next" request and need to drain */
- if (unlikely(ctx->drain_next) && !ctx->submit_state.link.head) {
- ctx->drain_next = false;
- ctx->drain_active = true;
- req->flags |= REQ_F_IO_DRAIN | REQ_F_FORCE_ASYNC;
- }
- }
-
- if (!def->ioprio && sqe->ioprio)
- return -EINVAL;
- if (!def->iopoll && (ctx->flags & IORING_SETUP_IOPOLL))
- return -EINVAL;
-
- if (def->needs_file) {
- struct io_submit_state *state = &ctx->submit_state;
-
- req->cqe.fd = READ_ONCE(sqe->fd);
-
- /*
- * Plug now if we have more than 2 IO left after this, and the
- * target is potentially a read/write to block based storage.
- */
- if (state->need_plug && def->plug) {
- state->plug_started = true;
- state->need_plug = false;
- blk_start_plug_nr_ios(&state->plug, state->submit_nr);
- }
- }
-
- personality = READ_ONCE(sqe->personality);
- if (personality) {
- int ret;
-
- req->creds = xa_load(&ctx->personalities, personality);
- if (!req->creds)
- return -EINVAL;
- get_cred(req->creds);
- ret = security_uring_override_creds(req->creds);
- if (ret) {
- put_cred(req->creds);
- return ret;
- }
- req->flags |= REQ_F_CREDS;
- }
-
- return io_req_prep(req, sqe);
-}
-
-static __cold int io_submit_fail_init(const struct io_uring_sqe *sqe,
- struct io_kiocb *req, int ret)
-{
- struct io_ring_ctx *ctx = req->ctx;
- struct io_submit_link *link = &ctx->submit_state.link;
- struct io_kiocb *head = link->head;
-
- trace_io_uring_req_failed(sqe, ctx, req, ret);
-
- /*
- * Avoid breaking links in the middle as it renders links with SQPOLL
- * unusable. Instead of failing eagerly, continue assembling the link if
- * applicable and mark the head with REQ_F_FAIL. The link flushing code
- * should find the flag and handle the rest.
- */
- req_fail_link_node(req, ret);
- if (head && !(head->flags & REQ_F_FAIL))
- req_fail_link_node(head, -ECANCELED);
-
- if (!(req->flags & IO_REQ_LINK_FLAGS)) {
- if (head) {
- link->last->link = req;
- link->head = NULL;
- req = head;
- }
- io_queue_sqe_fallback(req);
- return ret;
- }
-
- if (head)
- link->last->link = req;
- else
- link->head = req;
- link->last = req;
- return 0;
-}
-
-static inline int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
- __must_hold(&ctx->uring_lock)
-{
- struct io_submit_link *link = &ctx->submit_state.link;
- int ret;
-
- ret = io_init_req(ctx, req, sqe);
- if (unlikely(ret))
- return io_submit_fail_init(sqe, req, ret);
-
- /* don't need @sqe from now on */
- trace_io_uring_submit_sqe(ctx, req, req->cqe.user_data, req->opcode,
- req->flags, true,
- ctx->flags & IORING_SETUP_SQPOLL);
-
- /*
- * If we already have a head request, queue this one for async
- * submittal once the head completes. If we don't have a head but
- * IOSQE_IO_LINK is set in the sqe, start a new head. This one will be
- * submitted sync once the chain is complete. If none of those
- * conditions are true (normal request), then just queue it.
- */
- if (unlikely(link->head)) {
- ret = io_req_prep_async(req);
- if (unlikely(ret))
- return io_submit_fail_init(sqe, req, ret);
-
- trace_io_uring_link(ctx, req, link->head);
- link->last->link = req;
- link->last = req;
-
- if (req->flags & IO_REQ_LINK_FLAGS)
- return 0;
- /* last request of the link, flush it */
- req = link->head;
- link->head = NULL;
- if (req->flags & (REQ_F_FORCE_ASYNC | REQ_F_FAIL))
- goto fallback;
-
- } else if (unlikely(req->flags & (IO_REQ_LINK_FLAGS |
- REQ_F_FORCE_ASYNC | REQ_F_FAIL))) {
- if (req->flags & IO_REQ_LINK_FLAGS) {
- link->head = req;
- link->last = req;
- } else {
-fallback:
- io_queue_sqe_fallback(req);
- }
- return 0;
- }
-
- io_queue_sqe(req);
- return 0;
-}
-
-/*
- * Batched submission is done, ensure local IO is flushed out.
- */
-static void io_submit_state_end(struct io_ring_ctx *ctx)
-{
- struct io_submit_state *state = &ctx->submit_state;
-
- if (unlikely(state->link.head))
- io_queue_sqe_fallback(state->link.head);
- /* flush only after queuing links as they can generate completions */
- io_submit_flush_completions(ctx);
- if (state->plug_started)
- blk_finish_plug(&state->plug);
-}
-
-/*
- * Start submission side cache.
- */
-static void io_submit_state_start(struct io_submit_state *state,
- unsigned int max_ios)
-{
- state->plug_started = false;
- state->need_plug = max_ios > 2;
- state->submit_nr = max_ios;
- /* set only head, no need to init link_last in advance */
- state->link.head = NULL;
-}
-
-static void io_commit_sqring(struct io_ring_ctx *ctx)
-{
- struct io_rings *rings = ctx->rings;
-
- /*
- * Ensure any loads from the SQEs are done at this point,
- * since once we write the new head, the application could
- * write new data to them.
- */
- smp_store_release(&rings->sq.head, ctx->cached_sq_head);
-}
-
-/*
- * Fetch an sqe, if one is available. Note this returns a pointer to memory
- * that is mapped by userspace. This means that care needs to be taken to
- * ensure that reads are stable, as we cannot rely on userspace always
- * being a good citizen. If members of the sqe are validated and then later
- * used, it's important that those reads are done through READ_ONCE() to
- * prevent a re-load down the line.
- */
-static const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx)
-{
- unsigned head, mask = ctx->sq_entries - 1;
- unsigned sq_idx = ctx->cached_sq_head++ & mask;
-
- /*
- * The cached sq head (or cq tail) serves two purposes:
- *
- * 1) allows us to batch the cost of updating the user visible
- * head updates.
- * 2) allows the kernel side to track the head on its own, even
- * though the application is the one updating it.
- */
- head = READ_ONCE(ctx->sq_array[sq_idx]);
- if (likely(head < ctx->sq_entries)) {
- /* double index for 128-byte SQEs, twice as long */
- if (ctx->flags & IORING_SETUP_SQE128)
- head <<= 1;
- return &ctx->sq_sqes[head];
- }
-
- /* drop invalid entries */
- ctx->cq_extra--;
- WRITE_ONCE(ctx->rings->sq_dropped,
- READ_ONCE(ctx->rings->sq_dropped) + 1);
- return NULL;
-}
-
-static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
- __must_hold(&ctx->uring_lock)
-{
- unsigned int entries = io_sqring_entries(ctx);
- unsigned int left;
- int ret;
-
- if (unlikely(!entries))
- return 0;
- /* make sure SQ entry isn't read before tail */
- ret = left = min3(nr, ctx->sq_entries, entries);
- io_get_task_refs(left);
- io_submit_state_start(&ctx->submit_state, left);
-
- do {
- const struct io_uring_sqe *sqe;
- struct io_kiocb *req;
-
- if (unlikely(!io_alloc_req_refill(ctx)))
- break;
- req = io_alloc_req(ctx);
- sqe = io_get_sqe(ctx);
- if (unlikely(!sqe)) {
- io_req_add_to_cache(req, ctx);
- break;
- }
-
- /*
- * Continue submitting even for sqe failure if the
- * ring was setup with IORING_SETUP_SUBMIT_ALL
- */
- if (unlikely(io_submit_sqe(ctx, req, sqe)) &&
- !(ctx->flags & IORING_SETUP_SUBMIT_ALL)) {
- left--;
- break;
- }
- } while (--left);
-
- if (unlikely(left)) {
- ret -= left;
- /* try again if it submitted nothing and can't allocate a req */
- if (!ret && io_req_cache_empty(ctx))
- ret = -EAGAIN;
- current->io_uring->cached_refs += left;
- }
-
- io_submit_state_end(ctx);
- /* Commit SQ ring head once we've consumed and submitted all SQEs */
- io_commit_sqring(ctx);
- return ret;
-}
-
-static inline bool io_sqd_events_pending(struct io_sq_data *sqd)
-{
- return READ_ONCE(sqd->state);
-}
-
-static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries)
-{
- unsigned int to_submit;
- int ret = 0;
-
- to_submit = io_sqring_entries(ctx);
- /* if we're handling multiple rings, cap submit size for fairness */
- if (cap_entries && to_submit > IORING_SQPOLL_CAP_ENTRIES_VALUE)
- to_submit = IORING_SQPOLL_CAP_ENTRIES_VALUE;
-
- if (!wq_list_empty(&ctx->iopoll_list) || to_submit) {
- const struct cred *creds = NULL;
-
- if (ctx->sq_creds != current_cred())
- creds = override_creds(ctx->sq_creds);
-
- mutex_lock(&ctx->uring_lock);
- if (!wq_list_empty(&ctx->iopoll_list))
- io_do_iopoll(ctx, true);
-
- /*
- * Don't submit if refs are dying, good for io_uring_register(),
- * but also it is relied upon by io_ring_exit_work()
- */
- if (to_submit && likely(!percpu_ref_is_dying(&ctx->refs)) &&
- !(ctx->flags & IORING_SETUP_R_DISABLED))
- ret = io_submit_sqes(ctx, to_submit);
- mutex_unlock(&ctx->uring_lock);
-
- if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait))
- wake_up(&ctx->sqo_sq_wait);
- if (creds)
- revert_creds(creds);
- }
-
- return ret;
-}
-
-static __cold void io_sqd_update_thread_idle(struct io_sq_data *sqd)
-{
- struct io_ring_ctx *ctx;
- unsigned sq_thread_idle = 0;
-
- list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
- sq_thread_idle = max(sq_thread_idle, ctx->sq_thread_idle);
- sqd->sq_thread_idle = sq_thread_idle;
-}
-
-static bool io_sqd_handle_event(struct io_sq_data *sqd)
-{
- bool did_sig = false;
- struct ksignal ksig;
-
- if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state) ||
- signal_pending(current)) {
- mutex_unlock(&sqd->lock);
- if (signal_pending(current))
- did_sig = get_signal(&ksig);
- cond_resched();
- mutex_lock(&sqd->lock);
- }
- return did_sig || test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
-}
-
-static int io_sq_thread(void *data)
-{
- struct io_sq_data *sqd = data;
- struct io_ring_ctx *ctx;
- unsigned long timeout = 0;
- char buf[TASK_COMM_LEN];
- DEFINE_WAIT(wait);
-
- snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid);
- set_task_comm(current, buf);
-
- if (sqd->sq_cpu != -1)
- set_cpus_allowed_ptr(current, cpumask_of(sqd->sq_cpu));
- else
- set_cpus_allowed_ptr(current, cpu_online_mask);
- current->flags |= PF_NO_SETAFFINITY;
-
- audit_alloc_kernel(current);
-
- mutex_lock(&sqd->lock);
- while (1) {
- bool cap_entries, sqt_spin = false;
-
- if (io_sqd_events_pending(sqd) || signal_pending(current)) {
- if (io_sqd_handle_event(sqd))
- break;
- timeout = jiffies + sqd->sq_thread_idle;
- }
-
- cap_entries = !list_is_singular(&sqd->ctx_list);
- list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
- int ret = __io_sq_thread(ctx, cap_entries);
-
- if (!sqt_spin && (ret > 0 || !wq_list_empty(&ctx->iopoll_list)))
- sqt_spin = true;
- }
- if (io_run_task_work())
- sqt_spin = true;
-
- if (sqt_spin || !time_after(jiffies, timeout)) {
- cond_resched();
- if (sqt_spin)
- timeout = jiffies + sqd->sq_thread_idle;
- continue;
- }
-
- prepare_to_wait(&sqd->wait, &wait, TASK_INTERRUPTIBLE);
- if (!io_sqd_events_pending(sqd) && !task_work_pending(current)) {
- bool needs_sched = true;
-
- list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
- atomic_or(IORING_SQ_NEED_WAKEUP,
- &ctx->rings->sq_flags);
- if ((ctx->flags & IORING_SETUP_IOPOLL) &&
- !wq_list_empty(&ctx->iopoll_list)) {
- needs_sched = false;
- break;
- }
-
- /*
- * Ensure the store of the wakeup flag is not
- * reordered with the load of the SQ tail
- */
- smp_mb__after_atomic();
-
- if (io_sqring_entries(ctx)) {
- needs_sched = false;
- break;
- }
- }
-
- if (needs_sched) {
- mutex_unlock(&sqd->lock);
- schedule();
- mutex_lock(&sqd->lock);
- }
- list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
- atomic_andnot(IORING_SQ_NEED_WAKEUP,
- &ctx->rings->sq_flags);
- }
-
- finish_wait(&sqd->wait, &wait);
- timeout = jiffies + sqd->sq_thread_idle;
- }
-
- io_uring_cancel_generic(true, sqd);
- sqd->thread = NULL;
- list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
- atomic_or(IORING_SQ_NEED_WAKEUP, &ctx->rings->sq_flags);
- io_run_task_work();
- mutex_unlock(&sqd->lock);
-
- audit_free(current);
-
- complete(&sqd->exited);
- do_exit(0);
-}
-
-struct io_wait_queue {
- struct wait_queue_entry wq;
- struct io_ring_ctx *ctx;
- unsigned cq_tail;
- unsigned nr_timeouts;
-};
-
-static inline bool io_should_wake(struct io_wait_queue *iowq)
-{
- struct io_ring_ctx *ctx = iowq->ctx;
- int dist = ctx->cached_cq_tail - (int) iowq->cq_tail;
-
- /*
- * Wake up if we have enough events, or if a timeout occurred since we
- * started waiting. For timeouts, we always want to return to userspace,
- * regardless of event count.
- */
- return dist >= 0 || atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts;
-}
-
-static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode,
- int wake_flags, void *key)
-{
- struct io_wait_queue *iowq = container_of(curr, struct io_wait_queue,
- wq);
-
- /*
- * Cannot safely flush overflowed CQEs from here, ensure we wake up
- * the task, and the next invocation will do it.
- */
- if (io_should_wake(iowq) ||
- test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &iowq->ctx->check_cq))
- return autoremove_wake_function(curr, mode, wake_flags, key);
- return -1;
-}
-
-static int io_run_task_work_sig(void)
-{
- if (io_run_task_work())
- return 1;
- if (test_thread_flag(TIF_NOTIFY_SIGNAL))
- return -ERESTARTSYS;
- if (task_sigpending(current))
- return -EINTR;
- return 0;
-}
-
-/* when returns >0, the caller should retry */
-static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
- struct io_wait_queue *iowq,
- ktime_t timeout)
-{
- int ret;
- unsigned long check_cq;
-
- /* make sure we run task_work before checking for signals */
- ret = io_run_task_work_sig();
- if (ret || io_should_wake(iowq))
- return ret;
- check_cq = READ_ONCE(ctx->check_cq);
- /* let the caller flush overflows, retry */
- if (check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT))
- return 1;
- if (unlikely(check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT)))
- return -EBADR;
- if (!schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS))
- return -ETIME;
- return 1;
-}
-
-/*
- * Wait until events become available, if we don't already have some. The
- * application must reap them itself, as they reside on the shared cq ring.
- */
-static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
- const sigset_t __user *sig, size_t sigsz,
- struct __kernel_timespec __user *uts)
-{
- struct io_wait_queue iowq;
- struct io_rings *rings = ctx->rings;
- ktime_t timeout = KTIME_MAX;
- int ret;
-
- do {
- io_cqring_overflow_flush(ctx);
- if (io_cqring_events(ctx) >= min_events)
- return 0;
- if (!io_run_task_work())
- break;
- } while (1);
-
- if (sig) {
-#ifdef CONFIG_COMPAT
- if (in_compat_syscall())
- ret = set_compat_user_sigmask((const compat_sigset_t __user *)sig,
- sigsz);
- else
-#endif
- ret = set_user_sigmask(sig, sigsz);
-
- if (ret)
- return ret;
- }
-
- if (uts) {
- struct timespec64 ts;
-
- if (get_timespec64(&ts, uts))
- return -EFAULT;
- timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns());
- }
-
- init_waitqueue_func_entry(&iowq.wq, io_wake_function);
- iowq.wq.private = current;
- INIT_LIST_HEAD(&iowq.wq.entry);
- iowq.ctx = ctx;
- iowq.nr_timeouts = atomic_read(&ctx->cq_timeouts);
- iowq.cq_tail = READ_ONCE(ctx->rings->cq.head) + min_events;
-
- trace_io_uring_cqring_wait(ctx, min_events);
- do {
- /* if we can't even flush overflow, don't wait for more */
- if (!io_cqring_overflow_flush(ctx)) {
- ret = -EBUSY;
- break;
- }
- prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq,
- TASK_INTERRUPTIBLE);
- ret = io_cqring_wait_schedule(ctx, &iowq, timeout);
- cond_resched();
- } while (ret > 0);
-
- finish_wait(&ctx->cq_wait, &iowq.wq);
- restore_saved_sigmask_unless(ret == -EINTR);
-
- return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0;
-}
-
-static void io_free_page_table(void **table, size_t size)
-{
- unsigned i, nr_tables = DIV_ROUND_UP(size, PAGE_SIZE);
-
- for (i = 0; i < nr_tables; i++)
- kfree(table[i]);
- kfree(table);
-}
-
-static __cold void **io_alloc_page_table(size_t size)
-{
- unsigned i, nr_tables = DIV_ROUND_UP(size, PAGE_SIZE);
- size_t init_size = size;
- void **table;
-
- table = kcalloc(nr_tables, sizeof(*table), GFP_KERNEL_ACCOUNT);
- if (!table)
- return NULL;
-
- for (i = 0; i < nr_tables; i++) {
- unsigned int this_size = min_t(size_t, size, PAGE_SIZE);
-
- table[i] = kzalloc(this_size, GFP_KERNEL_ACCOUNT);
- if (!table[i]) {
- io_free_page_table(table, init_size);
- return NULL;
- }
- size -= this_size;
- }
- return table;
-}
-
-static void io_rsrc_node_destroy(struct io_rsrc_node *ref_node)
-{
- percpu_ref_exit(&ref_node->refs);
- kfree(ref_node);
-}
-
-static __cold void io_rsrc_node_ref_zero(struct percpu_ref *ref)
-{
- struct io_rsrc_node *node = container_of(ref, struct io_rsrc_node, refs);
- struct io_ring_ctx *ctx = node->rsrc_data->ctx;
- unsigned long flags;
- bool first_add = false;
- unsigned long delay = HZ;
-
- spin_lock_irqsave(&ctx->rsrc_ref_lock, flags);
- node->done = true;
-
- /* if we are mid-quiesce then do not delay */
- if (node->rsrc_data->quiesce)
- delay = 0;
-
- while (!list_empty(&ctx->rsrc_ref_list)) {
- node = list_first_entry(&ctx->rsrc_ref_list,
- struct io_rsrc_node, node);
- /* recycle ref nodes in order */
- if (!node->done)
- break;
- list_del(&node->node);
- first_add |= llist_add(&node->llist, &ctx->rsrc_put_llist);
- }
- spin_unlock_irqrestore(&ctx->rsrc_ref_lock, flags);
-
- if (first_add)
- mod_delayed_work(system_wq, &ctx->rsrc_put_work, delay);
-}
-
-static struct io_rsrc_node *io_rsrc_node_alloc(void)
-{
- struct io_rsrc_node *ref_node;
-
- ref_node = kzalloc(sizeof(*ref_node), GFP_KERNEL);
- if (!ref_node)
- return NULL;
-
- if (percpu_ref_init(&ref_node->refs, io_rsrc_node_ref_zero,
- 0, GFP_KERNEL)) {
- kfree(ref_node);
- return NULL;
- }
- INIT_LIST_HEAD(&ref_node->node);
- INIT_LIST_HEAD(&ref_node->rsrc_list);
- ref_node->done = false;
- return ref_node;
-}
-
-static void io_rsrc_node_switch(struct io_ring_ctx *ctx,
- struct io_rsrc_data *data_to_kill)
- __must_hold(&ctx->uring_lock)
-{
- WARN_ON_ONCE(!ctx->rsrc_backup_node);
- WARN_ON_ONCE(data_to_kill && !ctx->rsrc_node);
-
- io_rsrc_refs_drop(ctx);
-
- if (data_to_kill) {
- struct io_rsrc_node *rsrc_node = ctx->rsrc_node;
-
- rsrc_node->rsrc_data = data_to_kill;
- spin_lock_irq(&ctx->rsrc_ref_lock);
- list_add_tail(&rsrc_node->node, &ctx->rsrc_ref_list);
- spin_unlock_irq(&ctx->rsrc_ref_lock);
-
- atomic_inc(&data_to_kill->refs);
- percpu_ref_kill(&rsrc_node->refs);
- ctx->rsrc_node = NULL;
- }
-
- if (!ctx->rsrc_node) {
- ctx->rsrc_node = ctx->rsrc_backup_node;
- ctx->rsrc_backup_node = NULL;
- }
-}
-
-static int io_rsrc_node_switch_start(struct io_ring_ctx *ctx)
-{
- if (ctx->rsrc_backup_node)
- return 0;
- ctx->rsrc_backup_node = io_rsrc_node_alloc();
- return ctx->rsrc_backup_node ? 0 : -ENOMEM;
-}
-
-static __cold int io_rsrc_ref_quiesce(struct io_rsrc_data *data,
- struct io_ring_ctx *ctx)
-{
- int ret;
-
- /* As we may drop ->uring_lock, other task may have started quiesce */
- if (data->quiesce)
- return -ENXIO;
-
- data->quiesce = true;
- do {
- ret = io_rsrc_node_switch_start(ctx);
- if (ret)
- break;
- io_rsrc_node_switch(ctx, data);
-
- /* kill initial ref, already quiesced if zero */
- if (atomic_dec_and_test(&data->refs))
- break;
- mutex_unlock(&ctx->uring_lock);
- flush_delayed_work(&ctx->rsrc_put_work);
- ret = wait_for_completion_interruptible(&data->done);
- if (!ret) {
- mutex_lock(&ctx->uring_lock);
- if (atomic_read(&data->refs) > 0) {
- /*
- * it has been revived by another thread while
- * we were unlocked
- */
- mutex_unlock(&ctx->uring_lock);
- } else {
- break;
- }
- }
-
- atomic_inc(&data->refs);
- /* wait for all works potentially completing data->done */
- flush_delayed_work(&ctx->rsrc_put_work);
- reinit_completion(&data->done);
-
- ret = io_run_task_work_sig();
- mutex_lock(&ctx->uring_lock);
- } while (ret >= 0);
- data->quiesce = false;
-
- return ret;
-}
-
-static u64 *io_get_tag_slot(struct io_rsrc_data *data, unsigned int idx)
-{
- unsigned int off = idx & IO_RSRC_TAG_TABLE_MASK;
- unsigned int table_idx = idx >> IO_RSRC_TAG_TABLE_SHIFT;
-
- return &data->tags[table_idx][off];
-}
-
-static void io_rsrc_data_free(struct io_rsrc_data *data)
-{
- size_t size = data->nr * sizeof(data->tags[0][0]);
-
- if (data->tags)
- io_free_page_table((void **)data->tags, size);
- kfree(data);
-}
-
-static __cold int io_rsrc_data_alloc(struct io_ring_ctx *ctx, rsrc_put_fn *do_put,
- u64 __user *utags, unsigned nr,
- struct io_rsrc_data **pdata)
-{
- struct io_rsrc_data *data;
- int ret = -ENOMEM;
- unsigned i;
-
- data = kzalloc(sizeof(*data), GFP_KERNEL);
- if (!data)
- return -ENOMEM;
- data->tags = (u64 **)io_alloc_page_table(nr * sizeof(data->tags[0][0]));
- if (!data->tags) {
- kfree(data);
- return -ENOMEM;
- }
-
- data->nr = nr;
- data->ctx = ctx;
- data->do_put = do_put;
- if (utags) {
- ret = -EFAULT;
- for (i = 0; i < nr; i++) {
- u64 *tag_slot = io_get_tag_slot(data, i);
-
- if (copy_from_user(tag_slot, &utags[i],
- sizeof(*tag_slot)))
- goto fail;
- }
- }
-
- atomic_set(&data->refs, 1);
- init_completion(&data->done);
- *pdata = data;
- return 0;
-fail:
- io_rsrc_data_free(data);
- return ret;
-}
-
-static bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files)
-{
- table->files = kvcalloc(nr_files, sizeof(table->files[0]),
- GFP_KERNEL_ACCOUNT);
- if (unlikely(!table->files))
- return false;
-
- table->bitmap = bitmap_zalloc(nr_files, GFP_KERNEL_ACCOUNT);
- if (unlikely(!table->bitmap)) {
- kvfree(table->files);
- return false;
- }
-
- return true;
-}
-
-static void io_free_file_tables(struct io_file_table *table)
-{
- kvfree(table->files);
- bitmap_free(table->bitmap);
- table->files = NULL;
- table->bitmap = NULL;
-}
-
-static inline void io_file_bitmap_set(struct io_file_table *table, int bit)
-{
- WARN_ON_ONCE(test_bit(bit, table->bitmap));
- __set_bit(bit, table->bitmap);
- table->alloc_hint = bit + 1;
-}
-
-static inline void io_file_bitmap_clear(struct io_file_table *table, int bit)
-{
- __clear_bit(bit, table->bitmap);
- table->alloc_hint = bit;
-}
-
-static void __io_sqe_files_unregister(struct io_ring_ctx *ctx)
-{
-#if !defined(IO_URING_SCM_ALL)
- int i;
-
- for (i = 0; i < ctx->nr_user_files; i++) {
- struct file *file = io_file_from_index(ctx, i);
-
- if (!file)
- continue;
- if (io_fixed_file_slot(&ctx->file_table, i)->file_ptr & FFS_SCM)
- continue;
- io_file_bitmap_clear(&ctx->file_table, i);
- fput(file);
- }
-#endif
-
-#if defined(CONFIG_UNIX)
- if (ctx->ring_sock) {
- struct sock *sock = ctx->ring_sock->sk;
- struct sk_buff *skb;
-
- while ((skb = skb_dequeue(&sock->sk_receive_queue)) != NULL)
- kfree_skb(skb);
- }
-#endif
- io_free_file_tables(&ctx->file_table);
- io_rsrc_data_free(ctx->file_data);
- ctx->file_data = NULL;
- ctx->nr_user_files = 0;
-}
-
-static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
-{
- unsigned nr = ctx->nr_user_files;
- int ret;
-
- if (!ctx->file_data)
- return -ENXIO;
-
- /*
- * Quiesce may unlock ->uring_lock, and while it's not held
- * prevent new requests using the table.
- */
- ctx->nr_user_files = 0;
- ret = io_rsrc_ref_quiesce(ctx->file_data, ctx);
- ctx->nr_user_files = nr;
- if (!ret)
- __io_sqe_files_unregister(ctx);
- return ret;
-}
-
-static void io_sq_thread_unpark(struct io_sq_data *sqd)
- __releases(&sqd->lock)
-{
- WARN_ON_ONCE(sqd->thread == current);
-
- /*
- * Do the dance but not conditional clear_bit() because it'd race with
- * other threads incrementing park_pending and setting the bit.
- */
- clear_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
- if (atomic_dec_return(&sqd->park_pending))
- set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
- mutex_unlock(&sqd->lock);
-}
-
-static void io_sq_thread_park(struct io_sq_data *sqd)
- __acquires(&sqd->lock)
-{
- WARN_ON_ONCE(sqd->thread == current);
-
- atomic_inc(&sqd->park_pending);
- set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
- mutex_lock(&sqd->lock);
- if (sqd->thread)
- wake_up_process(sqd->thread);
-}
-
-static void io_sq_thread_stop(struct io_sq_data *sqd)
-{
- WARN_ON_ONCE(sqd->thread == current);
- WARN_ON_ONCE(test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state));
-
- set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
- mutex_lock(&sqd->lock);
- if (sqd->thread)
- wake_up_process(sqd->thread);
- mutex_unlock(&sqd->lock);
- wait_for_completion(&sqd->exited);
-}
-
-static void io_put_sq_data(struct io_sq_data *sqd)
-{
- if (refcount_dec_and_test(&sqd->refs)) {
- WARN_ON_ONCE(atomic_read(&sqd->park_pending));
-
- io_sq_thread_stop(sqd);
- kfree(sqd);
- }
-}
-
-static void io_sq_thread_finish(struct io_ring_ctx *ctx)
-{
- struct io_sq_data *sqd = ctx->sq_data;
-
- if (sqd) {
- io_sq_thread_park(sqd);
- list_del_init(&ctx->sqd_list);
- io_sqd_update_thread_idle(sqd);
- io_sq_thread_unpark(sqd);
-
- io_put_sq_data(sqd);
- ctx->sq_data = NULL;
- }
-}
-
-static struct io_sq_data *io_attach_sq_data(struct io_uring_params *p)
-{
- struct io_ring_ctx *ctx_attach;
- struct io_sq_data *sqd;
- struct fd f;
-
- f = fdget(p->wq_fd);
- if (!f.file)
- return ERR_PTR(-ENXIO);
- if (f.file->f_op != &io_uring_fops) {
- fdput(f);
- return ERR_PTR(-EINVAL);
- }
-
- ctx_attach = f.file->private_data;
- sqd = ctx_attach->sq_data;
- if (!sqd) {
- fdput(f);
- return ERR_PTR(-EINVAL);
- }
- if (sqd->task_tgid != current->tgid) {
- fdput(f);
- return ERR_PTR(-EPERM);
- }
-
- refcount_inc(&sqd->refs);
- fdput(f);
- return sqd;
-}
-
-static struct io_sq_data *io_get_sq_data(struct io_uring_params *p,
- bool *attached)
-{
- struct io_sq_data *sqd;
-
- *attached = false;
- if (p->flags & IORING_SETUP_ATTACH_WQ) {
- sqd = io_attach_sq_data(p);
- if (!IS_ERR(sqd)) {
- *attached = true;
- return sqd;
- }
- /* fall through for EPERM case, setup new sqd/task */
- if (PTR_ERR(sqd) != -EPERM)
- return sqd;
- }
-
- sqd = kzalloc(sizeof(*sqd), GFP_KERNEL);
- if (!sqd)
- return ERR_PTR(-ENOMEM);
-
- atomic_set(&sqd->park_pending, 0);
- refcount_set(&sqd->refs, 1);
- INIT_LIST_HEAD(&sqd->ctx_list);
- mutex_init(&sqd->lock);
- init_waitqueue_head(&sqd->wait);
- init_completion(&sqd->exited);
- return sqd;
-}
-
-/*
- * Ensure the UNIX gc is aware of our file set, so we are certain that
- * the io_uring can be safely unregistered on process exit, even if we have
- * loops in the file referencing. We account only files that can hold other
- * files because otherwise they can't form a loop and so are not interesting
- * for GC.
- */
-static int io_scm_file_account(struct io_ring_ctx *ctx, struct file *file)
-{
-#if defined(CONFIG_UNIX)
- struct sock *sk = ctx->ring_sock->sk;
- struct sk_buff_head *head = &sk->sk_receive_queue;
- struct scm_fp_list *fpl;
- struct sk_buff *skb;
-
- if (likely(!io_file_need_scm(file)))
- return 0;
-
- /*
- * See if we can merge this file into an existing skb SCM_RIGHTS
- * file set. If there's no room, fall back to allocating a new skb
- * and filling it in.
- */
- spin_lock_irq(&head->lock);
- skb = skb_peek(head);
- if (skb && UNIXCB(skb).fp->count < SCM_MAX_FD)
- __skb_unlink(skb, head);
- else
- skb = NULL;
- spin_unlock_irq(&head->lock);
-
- if (!skb) {
- fpl = kzalloc(sizeof(*fpl), GFP_KERNEL);
- if (!fpl)
- return -ENOMEM;
-
- skb = alloc_skb(0, GFP_KERNEL);
- if (!skb) {
- kfree(fpl);
- return -ENOMEM;
- }
-
- fpl->user = get_uid(current_user());
- fpl->max = SCM_MAX_FD;
- fpl->count = 0;
-
- UNIXCB(skb).fp = fpl;
- skb->sk = sk;
- skb->destructor = unix_destruct_scm;
- refcount_add(skb->truesize, &sk->sk_wmem_alloc);
- }
-
- fpl = UNIXCB(skb).fp;
- fpl->fp[fpl->count++] = get_file(file);
- unix_inflight(fpl->user, file);
- skb_queue_head(head, skb);
- fput(file);
-#endif
- return 0;
-}
-
-static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc)
-{
- struct file *file = prsrc->file;
-#if defined(CONFIG_UNIX)
- struct sock *sock = ctx->ring_sock->sk;
- struct sk_buff_head list, *head = &sock->sk_receive_queue;
- struct sk_buff *skb;
- int i;
-
- if (!io_file_need_scm(file)) {
- fput(file);
- return;
- }
-
- __skb_queue_head_init(&list);
-
- /*
- * Find the skb that holds this file in its SCM_RIGHTS. When found,
- * remove this entry and rearrange the file array.
- */
- skb = skb_dequeue(head);
- while (skb) {
- struct scm_fp_list *fp;
-
- fp = UNIXCB(skb).fp;
- for (i = 0; i < fp->count; i++) {
- int left;
-
- if (fp->fp[i] != file)
- continue;
-
- unix_notinflight(fp->user, fp->fp[i]);
- left = fp->count - 1 - i;
- if (left) {
- memmove(&fp->fp[i], &fp->fp[i + 1],
- left * sizeof(struct file *));
- }
- fp->count--;
- if (!fp->count) {
- kfree_skb(skb);
- skb = NULL;
- } else {
- __skb_queue_tail(&list, skb);
- }
- fput(file);
- file = NULL;
- break;
- }
-
- if (!file)
- break;
-
- __skb_queue_tail(&list, skb);
-
- skb = skb_dequeue(head);
- }
-
- if (skb_peek(&list)) {
- spin_lock_irq(&head->lock);
- while ((skb = __skb_dequeue(&list)) != NULL)
- __skb_queue_tail(head, skb);
- spin_unlock_irq(&head->lock);
- }
-#else
- fput(file);
-#endif
-}
-
-static void __io_rsrc_put_work(struct io_rsrc_node *ref_node)
-{
- struct io_rsrc_data *rsrc_data = ref_node->rsrc_data;
- struct io_ring_ctx *ctx = rsrc_data->ctx;
- struct io_rsrc_put *prsrc, *tmp;
-
- list_for_each_entry_safe(prsrc, tmp, &ref_node->rsrc_list, list) {
- list_del(&prsrc->list);
-
- if (prsrc->tag) {
- if (ctx->flags & IORING_SETUP_IOPOLL)
- mutex_lock(&ctx->uring_lock);
-
- spin_lock(&ctx->completion_lock);
- io_fill_cqe_aux(ctx, prsrc->tag, 0, 0);
- io_commit_cqring(ctx);
- spin_unlock(&ctx->completion_lock);
- io_cqring_ev_posted(ctx);
-
- if (ctx->flags & IORING_SETUP_IOPOLL)
- mutex_unlock(&ctx->uring_lock);
- }
-
- rsrc_data->do_put(ctx, prsrc);
- kfree(prsrc);
- }
-
- io_rsrc_node_destroy(ref_node);
- if (atomic_dec_and_test(&rsrc_data->refs))
- complete(&rsrc_data->done);
-}
-
-static void io_rsrc_put_work(struct work_struct *work)
-{
- struct io_ring_ctx *ctx;
- struct llist_node *node;
-
- ctx = container_of(work, struct io_ring_ctx, rsrc_put_work.work);
- node = llist_del_all(&ctx->rsrc_put_llist);
-
- while (node) {
- struct io_rsrc_node *ref_node;
- struct llist_node *next = node->next;
-
- ref_node = llist_entry(node, struct io_rsrc_node, llist);
- __io_rsrc_put_work(ref_node);
- node = next;
- }
-}
-
-static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
- unsigned nr_args, u64 __user *tags)
-{
- __s32 __user *fds = (__s32 __user *) arg;
- struct file *file;
- int fd, ret;
- unsigned i;
-
- if (ctx->file_data)
- return -EBUSY;
- if (!nr_args)
- return -EINVAL;
- if (nr_args > IORING_MAX_FIXED_FILES)
- return -EMFILE;
- if (nr_args > rlimit(RLIMIT_NOFILE))
- return -EMFILE;
- ret = io_rsrc_node_switch_start(ctx);
- if (ret)
- return ret;
- ret = io_rsrc_data_alloc(ctx, io_rsrc_file_put, tags, nr_args,
- &ctx->file_data);
- if (ret)
- return ret;
-
- if (!io_alloc_file_tables(&ctx->file_table, nr_args)) {
- io_rsrc_data_free(ctx->file_data);
- ctx->file_data = NULL;
- return -ENOMEM;
- }
-
- for (i = 0; i < nr_args; i++, ctx->nr_user_files++) {
- struct io_fixed_file *file_slot;
-
- if (fds && copy_from_user(&fd, &fds[i], sizeof(fd))) {
- ret = -EFAULT;
- goto fail;
- }
- /* allow sparse sets */
- if (!fds || fd == -1) {
- ret = -EINVAL;
- if (unlikely(*io_get_tag_slot(ctx->file_data, i)))
- goto fail;
- continue;
- }
-
- file = fget(fd);
- ret = -EBADF;
- if (unlikely(!file))
- goto fail;
-
- /*
- * Don't allow io_uring instances to be registered. If UNIX
- * isn't enabled, then this causes a reference cycle and this
- * instance can never get freed. If UNIX is enabled we'll
- * handle it just fine, but there's still no point in allowing
- * a ring fd as it doesn't support regular read/write anyway.
- */
- if (file->f_op == &io_uring_fops) {
- fput(file);
- goto fail;
- }
- ret = io_scm_file_account(ctx, file);
- if (ret) {
- fput(file);
- goto fail;
- }
- file_slot = io_fixed_file_slot(&ctx->file_table, i);
- io_fixed_file_set(file_slot, file);
- io_file_bitmap_set(&ctx->file_table, i);
- }
-
- io_rsrc_node_switch(ctx, NULL);
- return 0;
-fail:
- __io_sqe_files_unregister(ctx);
- return ret;
-}
-
-static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx,
- struct io_rsrc_node *node, void *rsrc)
-{
- u64 *tag_slot = io_get_tag_slot(data, idx);
- struct io_rsrc_put *prsrc;
-
- prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL);
- if (!prsrc)
- return -ENOMEM;
-
- prsrc->tag = *tag_slot;
- *tag_slot = 0;
- prsrc->rsrc = rsrc;
- list_add(&prsrc->list, &node->rsrc_list);
- return 0;
-}
-
-static int io_install_fixed_file(struct io_kiocb *req, struct file *file,
- unsigned int issue_flags, u32 slot_index)
- __must_hold(&req->ctx->uring_lock)
-{
- struct io_ring_ctx *ctx = req->ctx;
- bool needs_switch = false;
- struct io_fixed_file *file_slot;
- int ret;
-
- if (file->f_op == &io_uring_fops)
- return -EBADF;
- if (!ctx->file_data)
- return -ENXIO;
- if (slot_index >= ctx->nr_user_files)
- return -EINVAL;
-
- slot_index = array_index_nospec(slot_index, ctx->nr_user_files);
- file_slot = io_fixed_file_slot(&ctx->file_table, slot_index);
-
- if (file_slot->file_ptr) {
- struct file *old_file;
-
- ret = io_rsrc_node_switch_start(ctx);
- if (ret)
- goto err;
-
- old_file = (struct file *)(file_slot->file_ptr & FFS_MASK);
- ret = io_queue_rsrc_removal(ctx->file_data, slot_index,
- ctx->rsrc_node, old_file);
- if (ret)
- goto err;
- file_slot->file_ptr = 0;
- io_file_bitmap_clear(&ctx->file_table, slot_index);
- needs_switch = true;
- }
-
- ret = io_scm_file_account(ctx, file);
- if (!ret) {
- *io_get_tag_slot(ctx->file_data, slot_index) = 0;
- io_fixed_file_set(file_slot, file);
- io_file_bitmap_set(&ctx->file_table, slot_index);
- }
-err:
- if (needs_switch)
- io_rsrc_node_switch(ctx, ctx->file_data);
- if (ret)
- fput(file);
- return ret;
-}
-
-static int __io_close_fixed(struct io_kiocb *req, unsigned int issue_flags,
- unsigned int offset)
-{
- struct io_ring_ctx *ctx = req->ctx;
- struct io_fixed_file *file_slot;
- struct file *file;
- int ret;
-
- io_ring_submit_lock(ctx, issue_flags);
- ret = -ENXIO;
- if (unlikely(!ctx->file_data))
- goto out;
- ret = -EINVAL;
- if (offset >= ctx->nr_user_files)
- goto out;
- ret = io_rsrc_node_switch_start(ctx);
- if (ret)
- goto out;
-
- offset = array_index_nospec(offset, ctx->nr_user_files);
- file_slot = io_fixed_file_slot(&ctx->file_table, offset);
- ret = -EBADF;
- if (!file_slot->file_ptr)
- goto out;
-
- file = (struct file *)(file_slot->file_ptr & FFS_MASK);
- ret = io_queue_rsrc_removal(ctx->file_data, offset, ctx->rsrc_node, file);
- if (ret)
- goto out;
-
- file_slot->file_ptr = 0;
- io_file_bitmap_clear(&ctx->file_table, offset);
- io_rsrc_node_switch(ctx, ctx->file_data);
- ret = 0;
-out:
- io_ring_submit_unlock(ctx, issue_flags);
- return ret;
-}
-
-static inline int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags)
-{
- return __io_close_fixed(req, issue_flags, req->close.file_slot - 1);
-}
-
-static int __io_sqe_files_update(struct io_ring_ctx *ctx,
- struct io_uring_rsrc_update2 *up,
- unsigned nr_args)
-{
- u64 __user *tags = u64_to_user_ptr(up->tags);
- __s32 __user *fds = u64_to_user_ptr(up->data);
- struct io_rsrc_data *data = ctx->file_data;
- struct io_fixed_file *file_slot;
- struct file *file;
- int fd, i, err = 0;
- unsigned int done;
- bool needs_switch = false;
-
- if (!ctx->file_data)
- return -ENXIO;
- if (up->offset + nr_args > ctx->nr_user_files)
- return -EINVAL;
-
- for (done = 0; done < nr_args; done++) {
- u64 tag = 0;
-
- if ((tags && copy_from_user(&tag, &tags[done], sizeof(tag))) ||
- copy_from_user(&fd, &fds[done], sizeof(fd))) {
- err = -EFAULT;
- break;
- }
- if ((fd == IORING_REGISTER_FILES_SKIP || fd == -1) && tag) {
- err = -EINVAL;
- break;
- }
- if (fd == IORING_REGISTER_FILES_SKIP)
- continue;
-
- i = array_index_nospec(up->offset + done, ctx->nr_user_files);
- file_slot = io_fixed_file_slot(&ctx->file_table, i);
-
- if (file_slot->file_ptr) {
- file = (struct file *)(file_slot->file_ptr & FFS_MASK);
- err = io_queue_rsrc_removal(data, i, ctx->rsrc_node, file);
- if (err)
- break;
- file_slot->file_ptr = 0;
- io_file_bitmap_clear(&ctx->file_table, i);
- needs_switch = true;
- }
- if (fd != -1) {
- file = fget(fd);
- if (!file) {
- err = -EBADF;
- break;
- }
- /*
- * Don't allow io_uring instances to be registered. If
- * UNIX isn't enabled, then this causes a reference
- * cycle and this instance can never get freed. If UNIX
- * is enabled we'll handle it just fine, but there's
- * still no point in allowing a ring fd as it doesn't
- * support regular read/write anyway.
- */
- if (file->f_op == &io_uring_fops) {
- fput(file);
- err = -EBADF;
- break;
- }
- err = io_scm_file_account(ctx, file);
- if (err) {
- fput(file);
- break;
- }
- *io_get_tag_slot(data, i) = tag;
- io_fixed_file_set(file_slot, file);
- io_file_bitmap_set(&ctx->file_table, i);
- }
- }
-
- if (needs_switch)
- io_rsrc_node_switch(ctx, data);
- return done ? done : err;
-}
-
-static struct io_wq *io_init_wq_offload(struct io_ring_ctx *ctx,
- struct task_struct *task)
-{
- struct io_wq_hash *hash;
- struct io_wq_data data;
- unsigned int concurrency;
-
- mutex_lock(&ctx->uring_lock);
- hash = ctx->hash_map;
- if (!hash) {
- hash = kzalloc(sizeof(*hash), GFP_KERNEL);
- if (!hash) {
- mutex_unlock(&ctx->uring_lock);
- return ERR_PTR(-ENOMEM);
- }
- refcount_set(&hash->refs, 1);
- init_waitqueue_head(&hash->wait);
- ctx->hash_map = hash;
- }
- mutex_unlock(&ctx->uring_lock);
-
- data.hash = hash;
- data.task = task;
- data.free_work = io_wq_free_work;
- data.do_work = io_wq_submit_work;
-
- /* Do QD, or 4 * CPUS, whatever is smallest */
- concurrency = min(ctx->sq_entries, 4 * num_online_cpus());
-
- return io_wq_create(concurrency, &data);
-}
-
-static __cold int io_uring_alloc_task_context(struct task_struct *task,
- struct io_ring_ctx *ctx)
-{
- struct io_uring_task *tctx;
- int ret;
-
- tctx = kzalloc(sizeof(*tctx), GFP_KERNEL);
- if (unlikely(!tctx))
- return -ENOMEM;
-
- tctx->registered_rings = kcalloc(IO_RINGFD_REG_MAX,
- sizeof(struct file *), GFP_KERNEL);
- if (unlikely(!tctx->registered_rings)) {
- kfree(tctx);
- return -ENOMEM;
- }
-
- ret = percpu_counter_init(&tctx->inflight, 0, GFP_KERNEL);
- if (unlikely(ret)) {
- kfree(tctx->registered_rings);
- kfree(tctx);
- return ret;
- }
-
- tctx->io_wq = io_init_wq_offload(ctx, task);
- if (IS_ERR(tctx->io_wq)) {
- ret = PTR_ERR(tctx->io_wq);
- percpu_counter_destroy(&tctx->inflight);
- kfree(tctx->registered_rings);
- kfree(tctx);
- return ret;
- }
-
- xa_init(&tctx->xa);
- init_waitqueue_head(&tctx->wait);
- atomic_set(&tctx->in_idle, 0);
- atomic_set(&tctx->inflight_tracked, 0);
- task->io_uring = tctx;
- spin_lock_init(&tctx->task_lock);
- INIT_WQ_LIST(&tctx->task_list);
- INIT_WQ_LIST(&tctx->prio_task_list);
- init_task_work(&tctx->task_work, tctx_task_work);
- return 0;
-}
-
-void __io_uring_free(struct task_struct *tsk)
-{
- struct io_uring_task *tctx = tsk->io_uring;
-
- WARN_ON_ONCE(!xa_empty(&tctx->xa));
- WARN_ON_ONCE(tctx->io_wq);
- WARN_ON_ONCE(tctx->cached_refs);
-
- kfree(tctx->registered_rings);
- percpu_counter_destroy(&tctx->inflight);
- kfree(tctx);
- tsk->io_uring = NULL;
-}
-
-static __cold int io_sq_offload_create(struct io_ring_ctx *ctx,
- struct io_uring_params *p)
-{
- int ret;
-
- /* Retain compatibility with failing for an invalid attach attempt */
- if ((ctx->flags & (IORING_SETUP_ATTACH_WQ | IORING_SETUP_SQPOLL)) ==
- IORING_SETUP_ATTACH_WQ) {
- struct fd f;
-
- f = fdget(p->wq_fd);
- if (!f.file)
- return -ENXIO;
- if (f.file->f_op != &io_uring_fops) {
- fdput(f);
- return -EINVAL;
- }
- fdput(f);
- }
- if (ctx->flags & IORING_SETUP_SQPOLL) {
- struct task_struct *tsk;
- struct io_sq_data *sqd;
- bool attached;
-
- ret = security_uring_sqpoll();
- if (ret)
- return ret;
-
- sqd = io_get_sq_data(p, &attached);
- if (IS_ERR(sqd)) {
- ret = PTR_ERR(sqd);
- goto err;
- }
-
- ctx->sq_creds = get_current_cred();
- ctx->sq_data = sqd;
- ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle);
- if (!ctx->sq_thread_idle)
- ctx->sq_thread_idle = HZ;
-
- io_sq_thread_park(sqd);
- list_add(&ctx->sqd_list, &sqd->ctx_list);
- io_sqd_update_thread_idle(sqd);
- /* don't attach to a dying SQPOLL thread, would be racy */
- ret = (attached && !sqd->thread) ? -ENXIO : 0;
- io_sq_thread_unpark(sqd);
-
- if (ret < 0)
- goto err;
- if (attached)
- return 0;
-
- if (p->flags & IORING_SETUP_SQ_AFF) {
- int cpu = p->sq_thread_cpu;
-
- ret = -EINVAL;
- if (cpu >= nr_cpu_ids || !cpu_online(cpu))
- goto err_sqpoll;
- sqd->sq_cpu = cpu;
- } else {
- sqd->sq_cpu = -1;
- }
-
- sqd->task_pid = current->pid;
- sqd->task_tgid = current->tgid;
- tsk = create_io_thread(io_sq_thread, sqd, NUMA_NO_NODE);
- if (IS_ERR(tsk)) {
- ret = PTR_ERR(tsk);
- goto err_sqpoll;
- }
-
- sqd->thread = tsk;
- ret = io_uring_alloc_task_context(tsk, ctx);
- wake_up_new_task(tsk);
- if (ret)
- goto err;
- } else if (p->flags & IORING_SETUP_SQ_AFF) {
- /* Can't have SQ_AFF without SQPOLL */
- ret = -EINVAL;
- goto err;
- }
-
- return 0;
-err_sqpoll:
- complete(&ctx->sq_data->exited);
-err:
- io_sq_thread_finish(ctx);
- return ret;
-}
-
-static inline void __io_unaccount_mem(struct user_struct *user,
- unsigned long nr_pages)
-{
- atomic_long_sub(nr_pages, &user->locked_vm);
-}
-
-static inline int __io_account_mem(struct user_struct *user,
- unsigned long nr_pages)
-{
- unsigned long page_limit, cur_pages, new_pages;
-
- /* Don't allow more pages than we can safely lock */
- page_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-
- do {
- cur_pages = atomic_long_read(&user->locked_vm);
- new_pages = cur_pages + nr_pages;
- if (new_pages > page_limit)
- return -ENOMEM;
- } while (atomic_long_cmpxchg(&user->locked_vm, cur_pages,
- new_pages) != cur_pages);
-
- return 0;
-}
-
-static void io_unaccount_mem(struct io_ring_ctx *ctx, unsigned long nr_pages)
-{
- if (ctx->user)
- __io_unaccount_mem(ctx->user, nr_pages);
-
- if (ctx->mm_account)
- atomic64_sub(nr_pages, &ctx->mm_account->pinned_vm);
-}
-
-static int io_account_mem(struct io_ring_ctx *ctx, unsigned long nr_pages)
-{
- int ret;
-
- if (ctx->user) {
- ret = __io_account_mem(ctx->user, nr_pages);
- if (ret)
- return ret;
- }
-
- if (ctx->mm_account)
- atomic64_add(nr_pages, &ctx->mm_account->pinned_vm);
-
- return 0;
-}
-
-static void io_mem_free(void *ptr)
-{
- struct page *page;
-
- if (!ptr)
- return;
-
- page = virt_to_head_page(ptr);
- if (put_page_testzero(page))
- free_compound_page(page);
-}
-
-static void *io_mem_alloc(size_t size)
-{
- gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP;
-
- return (void *) __get_free_pages(gfp, get_order(size));
-}
-
-static unsigned long rings_size(struct io_ring_ctx *ctx, unsigned int sq_entries,
- unsigned int cq_entries, size_t *sq_offset)
-{
- struct io_rings *rings;
- size_t off, sq_array_size;
-
- off = struct_size(rings, cqes, cq_entries);
- if (off == SIZE_MAX)
- return SIZE_MAX;
- if (ctx->flags & IORING_SETUP_CQE32) {
- if (check_shl_overflow(off, 1, &off))
- return SIZE_MAX;
- }
-
-#ifdef CONFIG_SMP
- off = ALIGN(off, SMP_CACHE_BYTES);
- if (off == 0)
- return SIZE_MAX;
-#endif
-
- if (sq_offset)
- *sq_offset = off;
-
- sq_array_size = array_size(sizeof(u32), sq_entries);
- if (sq_array_size == SIZE_MAX)
- return SIZE_MAX;
-
- if (check_add_overflow(off, sq_array_size, &off))
- return SIZE_MAX;
-
- return off;
-}
-
-static void io_buffer_unmap(struct io_ring_ctx *ctx, struct io_mapped_ubuf **slot)
-{
- struct io_mapped_ubuf *imu = *slot;
- unsigned int i;
-
- if (imu != ctx->dummy_ubuf) {
- for (i = 0; i < imu->nr_bvecs; i++)
- unpin_user_page(imu->bvec[i].bv_page);
- if (imu->acct_pages)
- io_unaccount_mem(ctx, imu->acct_pages);
- kvfree(imu);
- }
- *slot = NULL;
-}
-
-static void io_rsrc_buf_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc)
-{
- io_buffer_unmap(ctx, &prsrc->buf);
- prsrc->buf = NULL;
-}
-
-static void __io_sqe_buffers_unregister(struct io_ring_ctx *ctx)
-{
- unsigned int i;
-
- for (i = 0; i < ctx->nr_user_bufs; i++)
- io_buffer_unmap(ctx, &ctx->user_bufs[i]);
- kfree(ctx->user_bufs);
- io_rsrc_data_free(ctx->buf_data);
- ctx->user_bufs = NULL;
- ctx->buf_data = NULL;
- ctx->nr_user_bufs = 0;
-}
-
-static int io_sqe_buffers_unregister(struct io_ring_ctx *ctx)
-{
- unsigned nr = ctx->nr_user_bufs;
- int ret;
-
- if (!ctx->buf_data)
- return -ENXIO;
-
- /*
- * Quiesce may unlock ->uring_lock, and while it's not held
- * prevent new requests using the table.
- */
- ctx->nr_user_bufs = 0;
- ret = io_rsrc_ref_quiesce(ctx->buf_data, ctx);
- ctx->nr_user_bufs = nr;
- if (!ret)
- __io_sqe_buffers_unregister(ctx);
- return ret;
-}
-
-static int io_copy_iov(struct io_ring_ctx *ctx, struct iovec *dst,
- void __user *arg, unsigned index)
-{
- struct iovec __user *src;
-
-#ifdef CONFIG_COMPAT
- if (ctx->compat) {
- struct compat_iovec __user *ciovs;
- struct compat_iovec ciov;
-
- ciovs = (struct compat_iovec __user *) arg;
- if (copy_from_user(&ciov, &ciovs[index], sizeof(ciov)))
- return -EFAULT;
-
- dst->iov_base = u64_to_user_ptr((u64)ciov.iov_base);
- dst->iov_len = ciov.iov_len;
- return 0;
- }
-#endif
- src = (struct iovec __user *) arg;
- if (copy_from_user(dst, &src[index], sizeof(*dst)))
- return -EFAULT;
- return 0;
-}
-
-/*
- * Not super efficient, but this is just a registration time. And we do cache
- * the last compound head, so generally we'll only do a full search if we don't
- * match that one.
- *
- * We check if the given compound head page has already been accounted, to
- * avoid double accounting it. This allows us to account the full size of the
- * page, not just the constituent pages of a huge page.
- */
-static bool headpage_already_acct(struct io_ring_ctx *ctx, struct page **pages,
- int nr_pages, struct page *hpage)
-{
- int i, j;
-
- /* check current page array */
- for (i = 0; i < nr_pages; i++) {
- if (!PageCompound(pages[i]))
- continue;
- if (compound_head(pages[i]) == hpage)
- return true;
- }
-
- /* check previously registered pages */
- for (i = 0; i < ctx->nr_user_bufs; i++) {
- struct io_mapped_ubuf *imu = ctx->user_bufs[i];
-
- for (j = 0; j < imu->nr_bvecs; j++) {
- if (!PageCompound(imu->bvec[j].bv_page))
- continue;
- if (compound_head(imu->bvec[j].bv_page) == hpage)
- return true;
- }
- }
-
- return false;
-}
-
-static int io_buffer_account_pin(struct io_ring_ctx *ctx, struct page **pages,
- int nr_pages, struct io_mapped_ubuf *imu,
- struct page **last_hpage)
-{
- int i, ret;
-
- imu->acct_pages = 0;
- for (i = 0; i < nr_pages; i++) {
- if (!PageCompound(pages[i])) {
- imu->acct_pages++;
- } else {
- struct page *hpage;
-
- hpage = compound_head(pages[i]);
- if (hpage == *last_hpage)
- continue;
- *last_hpage = hpage;
- if (headpage_already_acct(ctx, pages, i, hpage))
- continue;
- imu->acct_pages += page_size(hpage) >> PAGE_SHIFT;
- }
- }
-
- if (!imu->acct_pages)
- return 0;
-
- ret = io_account_mem(ctx, imu->acct_pages);
- if (ret)
- imu->acct_pages = 0;
- return ret;
-}
-
-static struct page **io_pin_pages(unsigned long ubuf, unsigned long len,
- int *npages)
-{
- unsigned long start, end, nr_pages;
- struct vm_area_struct **vmas = NULL;
- struct page **pages = NULL;
- int i, pret, ret = -ENOMEM;
-
- end = (ubuf + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
- start = ubuf >> PAGE_SHIFT;
- nr_pages = end - start;
-
- pages = kvmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL);
- if (!pages)
- goto done;
-
- vmas = kvmalloc_array(nr_pages, sizeof(struct vm_area_struct *),
- GFP_KERNEL);
- if (!vmas)
- goto done;
-
- ret = 0;
- mmap_read_lock(current->mm);
- pret = pin_user_pages(ubuf, nr_pages, FOLL_WRITE | FOLL_LONGTERM,
- pages, vmas);
- if (pret == nr_pages) {
- /* don't support file backed memory */
- for (i = 0; i < nr_pages; i++) {
- struct vm_area_struct *vma = vmas[i];
-
- if (vma_is_shmem(vma))
- continue;
- if (vma->vm_file &&
- !is_file_hugepages(vma->vm_file)) {
- ret = -EOPNOTSUPP;
- break;
- }
- }
- *npages = nr_pages;
- } else {
- ret = pret < 0 ? pret : -EFAULT;
- }
- mmap_read_unlock(current->mm);
- if (ret) {
- /*
- * if we did partial map, or found file backed vmas,
- * release any pages we did get
- */
- if (pret > 0)
- unpin_user_pages(pages, pret);
- goto done;
- }
- ret = 0;
-done:
- kvfree(vmas);
- if (ret < 0) {
- kvfree(pages);
- pages = ERR_PTR(ret);
- }
- return pages;
-}
-
-static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov,
- struct io_mapped_ubuf **pimu,
- struct page **last_hpage)
-{
- struct io_mapped_ubuf *imu = NULL;
- struct page **pages = NULL;
- unsigned long off;
- size_t size;
- int ret, nr_pages, i;
-
- if (!iov->iov_base) {
- *pimu = ctx->dummy_ubuf;
- return 0;
- }
-
- *pimu = NULL;
- ret = -ENOMEM;
-
- pages = io_pin_pages((unsigned long) iov->iov_base, iov->iov_len,
- &nr_pages);
- if (IS_ERR(pages)) {
- ret = PTR_ERR(pages);
- pages = NULL;
- goto done;
- }
-
- imu = kvmalloc(struct_size(imu, bvec, nr_pages), GFP_KERNEL);
- if (!imu)
- goto done;
-
- ret = io_buffer_account_pin(ctx, pages, nr_pages, imu, last_hpage);
- if (ret) {
- unpin_user_pages(pages, nr_pages);
- goto done;
- }
-
- off = (unsigned long) iov->iov_base & ~PAGE_MASK;
- size = iov->iov_len;
- for (i = 0; i < nr_pages; i++) {
- size_t vec_len;
-
- vec_len = min_t(size_t, size, PAGE_SIZE - off);
- imu->bvec[i].bv_page = pages[i];
- imu->bvec[i].bv_len = vec_len;
- imu->bvec[i].bv_offset = off;
- off = 0;
- size -= vec_len;
- }
- /* store original address for later verification */
- imu->ubuf = (unsigned long) iov->iov_base;
- imu->ubuf_end = imu->ubuf + iov->iov_len;
- imu->nr_bvecs = nr_pages;
- *pimu = imu;
- ret = 0;
-done:
- if (ret)
- kvfree(imu);
- kvfree(pages);
- return ret;
-}
-
-static int io_buffers_map_alloc(struct io_ring_ctx *ctx, unsigned int nr_args)
-{
- ctx->user_bufs = kcalloc(nr_args, sizeof(*ctx->user_bufs), GFP_KERNEL);
- return ctx->user_bufs ? 0 : -ENOMEM;
-}
-
-static int io_buffer_validate(struct iovec *iov)
-{
- unsigned long tmp, acct_len = iov->iov_len + (PAGE_SIZE - 1);
-
- /*
- * Don't impose further limits on the size and buffer
- * constraints here, we'll -EINVAL later when IO is
- * submitted if they are wrong.
- */
- if (!iov->iov_base)
- return iov->iov_len ? -EFAULT : 0;
- if (!iov->iov_len)
- return -EFAULT;
-
- /* arbitrary limit, but we need something */
- if (iov->iov_len > SZ_1G)
- return -EFAULT;
-
- if (check_add_overflow((unsigned long)iov->iov_base, acct_len, &tmp))
- return -EOVERFLOW;
-
- return 0;
-}
-
-static int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
- unsigned int nr_args, u64 __user *tags)
-{
- struct page *last_hpage = NULL;
- struct io_rsrc_data *data;
- int i, ret;
- struct iovec iov;
-
- if (ctx->user_bufs)
- return -EBUSY;
- if (!nr_args || nr_args > IORING_MAX_REG_BUFFERS)
- return -EINVAL;
- ret = io_rsrc_node_switch_start(ctx);
- if (ret)
- return ret;
- ret = io_rsrc_data_alloc(ctx, io_rsrc_buf_put, tags, nr_args, &data);
- if (ret)
- return ret;
- ret = io_buffers_map_alloc(ctx, nr_args);
- if (ret) {
- io_rsrc_data_free(data);
- return ret;
- }
-
- for (i = 0; i < nr_args; i++, ctx->nr_user_bufs++) {
- if (arg) {
- ret = io_copy_iov(ctx, &iov, arg, i);
- if (ret)
- break;
- ret = io_buffer_validate(&iov);
- if (ret)
- break;
- } else {
- memset(&iov, 0, sizeof(iov));
- }
-
- if (!iov.iov_base && *io_get_tag_slot(data, i)) {
- ret = -EINVAL;
- break;
- }
-
- ret = io_sqe_buffer_register(ctx, &iov, &ctx->user_bufs[i],
- &last_hpage);
- if (ret)
- break;
- }
-
- WARN_ON_ONCE(ctx->buf_data);
-
- ctx->buf_data = data;
- if (ret)
- __io_sqe_buffers_unregister(ctx);
- else
- io_rsrc_node_switch(ctx, NULL);
- return ret;
-}
-
-static int __io_sqe_buffers_update(struct io_ring_ctx *ctx,
- struct io_uring_rsrc_update2 *up,
- unsigned int nr_args)
-{
- u64 __user *tags = u64_to_user_ptr(up->tags);
- struct iovec iov, __user *iovs = u64_to_user_ptr(up->data);
- struct page *last_hpage = NULL;
- bool needs_switch = false;
- __u32 done;
- int i, err;
-
- if (!ctx->buf_data)
- return -ENXIO;
- if (up->offset + nr_args > ctx->nr_user_bufs)
- return -EINVAL;
-
- for (done = 0; done < nr_args; done++) {
- struct io_mapped_ubuf *imu;
- int offset = up->offset + done;
- u64 tag = 0;
-
- err = io_copy_iov(ctx, &iov, iovs, done);
- if (err)
- break;
- if (tags && copy_from_user(&tag, &tags[done], sizeof(tag))) {
- err = -EFAULT;
- break;
- }
- err = io_buffer_validate(&iov);
- if (err)
- break;
- if (!iov.iov_base && tag) {
- err = -EINVAL;
- break;
- }
- err = io_sqe_buffer_register(ctx, &iov, &imu, &last_hpage);
- if (err)
- break;
-
- i = array_index_nospec(offset, ctx->nr_user_bufs);
- if (ctx->user_bufs[i] != ctx->dummy_ubuf) {
- err = io_queue_rsrc_removal(ctx->buf_data, i,
- ctx->rsrc_node, ctx->user_bufs[i]);
- if (unlikely(err)) {
- io_buffer_unmap(ctx, &imu);
- break;
- }
- ctx->user_bufs[i] = NULL;
- needs_switch = true;
- }
-
- ctx->user_bufs[i] = imu;
- *io_get_tag_slot(ctx->buf_data, offset) = tag;
- }
-
- if (needs_switch)
- io_rsrc_node_switch(ctx, ctx->buf_data);
- return done ? done : err;
-}
-
-static int io_eventfd_register(struct io_ring_ctx *ctx, void __user *arg,
- unsigned int eventfd_async)
-{
- struct io_ev_fd *ev_fd;
- __s32 __user *fds = arg;
- int fd;
-
- ev_fd = rcu_dereference_protected(ctx->io_ev_fd,
- lockdep_is_held(&ctx->uring_lock));
- if (ev_fd)
- return -EBUSY;
-
- if (copy_from_user(&fd, fds, sizeof(*fds)))
- return -EFAULT;
-
- ev_fd = kmalloc(sizeof(*ev_fd), GFP_KERNEL);
- if (!ev_fd)
- return -ENOMEM;
-
- ev_fd->cq_ev_fd = eventfd_ctx_fdget(fd);
- if (IS_ERR(ev_fd->cq_ev_fd)) {
- int ret = PTR_ERR(ev_fd->cq_ev_fd);
- kfree(ev_fd);
- return ret;
- }
- ev_fd->eventfd_async = eventfd_async;
- ctx->has_evfd = true;
- rcu_assign_pointer(ctx->io_ev_fd, ev_fd);
- return 0;
-}
-
-static void io_eventfd_put(struct rcu_head *rcu)
-{
- struct io_ev_fd *ev_fd = container_of(rcu, struct io_ev_fd, rcu);
-
- eventfd_ctx_put(ev_fd->cq_ev_fd);
- kfree(ev_fd);
-}
-
-static int io_eventfd_unregister(struct io_ring_ctx *ctx)
-{
- struct io_ev_fd *ev_fd;
-
- ev_fd = rcu_dereference_protected(ctx->io_ev_fd,
- lockdep_is_held(&ctx->uring_lock));
- if (ev_fd) {
- ctx->has_evfd = false;
- rcu_assign_pointer(ctx->io_ev_fd, NULL);
- call_rcu(&ev_fd->rcu, io_eventfd_put);
- return 0;
- }
-
- return -ENXIO;
-}
-
-static void io_destroy_buffers(struct io_ring_ctx *ctx)
-{
- struct io_buffer_list *bl;
- unsigned long index;
- int i;
-
- for (i = 0; i < BGID_ARRAY; i++) {
- if (!ctx->io_bl)
- break;
- __io_remove_buffers(ctx, &ctx->io_bl[i], -1U);
- }
-
- xa_for_each(&ctx->io_bl_xa, index, bl) {
- xa_erase(&ctx->io_bl_xa, bl->bgid);
- __io_remove_buffers(ctx, bl, -1U);
- kfree(bl);
- }
-
- while (!list_empty(&ctx->io_buffers_pages)) {
- struct page *page;
-
- page = list_first_entry(&ctx->io_buffers_pages, struct page, lru);
- list_del_init(&page->lru);
- __free_page(page);
- }
-}
-
-static void io_req_caches_free(struct io_ring_ctx *ctx)
-{
- struct io_submit_state *state = &ctx->submit_state;
- int nr = 0;
-
- mutex_lock(&ctx->uring_lock);
- io_flush_cached_locked_reqs(ctx, state);
-
- while (!io_req_cache_empty(ctx)) {
- struct io_wq_work_node *node;
- struct io_kiocb *req;
-
- node = wq_stack_extract(&state->free_list);
- req = container_of(node, struct io_kiocb, comp_list);
- kmem_cache_free(req_cachep, req);
- nr++;
- }
- if (nr)
- percpu_ref_put_many(&ctx->refs, nr);
- mutex_unlock(&ctx->uring_lock);
-}
-
-static void io_wait_rsrc_data(struct io_rsrc_data *data)
-{
- if (data && !atomic_dec_and_test(&data->refs))
- wait_for_completion(&data->done);
-}
-
-static void io_flush_apoll_cache(struct io_ring_ctx *ctx)
-{
- struct async_poll *apoll;
-
- while (!list_empty(&ctx->apoll_cache)) {
- apoll = list_first_entry(&ctx->apoll_cache, struct async_poll,
- poll.wait.entry);
- list_del(&apoll->poll.wait.entry);
- kfree(apoll);
- }
-}
-
-static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
-{
- io_sq_thread_finish(ctx);
-
- if (ctx->mm_account) {
- mmdrop(ctx->mm_account);
- ctx->mm_account = NULL;
- }
-
- io_rsrc_refs_drop(ctx);
- /* __io_rsrc_put_work() may need uring_lock to progress, wait w/o it */
- io_wait_rsrc_data(ctx->buf_data);
- io_wait_rsrc_data(ctx->file_data);
-
- mutex_lock(&ctx->uring_lock);
- if (ctx->buf_data)
- __io_sqe_buffers_unregister(ctx);
- if (ctx->file_data)
- __io_sqe_files_unregister(ctx);
- if (ctx->rings)
- __io_cqring_overflow_flush(ctx, true);
- io_eventfd_unregister(ctx);
- io_flush_apoll_cache(ctx);
- mutex_unlock(&ctx->uring_lock);
- io_destroy_buffers(ctx);
- if (ctx->sq_creds)
- put_cred(ctx->sq_creds);
-
- /* there are no registered resources left, nobody uses it */
- if (ctx->rsrc_node)
- io_rsrc_node_destroy(ctx->rsrc_node);
- if (ctx->rsrc_backup_node)
- io_rsrc_node_destroy(ctx->rsrc_backup_node);
- flush_delayed_work(&ctx->rsrc_put_work);
- flush_delayed_work(&ctx->fallback_work);
-
- WARN_ON_ONCE(!list_empty(&ctx->rsrc_ref_list));
- WARN_ON_ONCE(!llist_empty(&ctx->rsrc_put_llist));
-
-#if defined(CONFIG_UNIX)
- if (ctx->ring_sock) {
- ctx->ring_sock->file = NULL; /* so that iput() is called */
- sock_release(ctx->ring_sock);
- }
-#endif
- WARN_ON_ONCE(!list_empty(&ctx->ltimeout_list));
-
- io_mem_free(ctx->rings);
- io_mem_free(ctx->sq_sqes);
-
- percpu_ref_exit(&ctx->refs);
- free_uid(ctx->user);
- io_req_caches_free(ctx);
- if (ctx->hash_map)
- io_wq_put_hash(ctx->hash_map);
- kfree(ctx->cancel_hash);
- kfree(ctx->dummy_ubuf);
- kfree(ctx->io_bl);
- xa_destroy(&ctx->io_bl_xa);
- kfree(ctx);
-}
-
-static __poll_t io_uring_poll(struct file *file, poll_table *wait)
-{
- struct io_ring_ctx *ctx = file->private_data;
- __poll_t mask = 0;
-
- poll_wait(file, &ctx->cq_wait, wait);
- /*
- * synchronizes with barrier from wq_has_sleeper call in
- * io_commit_cqring
- */
- smp_rmb();
- if (!io_sqring_full(ctx))
- mask |= EPOLLOUT | EPOLLWRNORM;
-
- /*
- * Don't flush cqring overflow list here, just do a simple check.
- * Otherwise there could possible be ABBA deadlock:
- * CPU0 CPU1
- * ---- ----
- * lock(&ctx->uring_lock);
- * lock(&ep->mtx);
- * lock(&ctx->uring_lock);
- * lock(&ep->mtx);
- *
- * Users may get EPOLLIN meanwhile seeing nothing in cqring, this
- * pushs them to do the flush.
- */
- if (io_cqring_events(ctx) ||
- test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq))
- mask |= EPOLLIN | EPOLLRDNORM;
-
- return mask;
-}
-
-static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id)
-{
- const struct cred *creds;
-
- creds = xa_erase(&ctx->personalities, id);
- if (creds) {
- put_cred(creds);
- return 0;
- }
-
- return -EINVAL;
-}
-
-struct io_tctx_exit {
- struct callback_head task_work;
- struct completion completion;
- struct io_ring_ctx *ctx;
-};
-
-static __cold void io_tctx_exit_cb(struct callback_head *cb)
-{
- struct io_uring_task *tctx = current->io_uring;
- struct io_tctx_exit *work;
-
- work = container_of(cb, struct io_tctx_exit, task_work);
- /*
- * When @in_idle, we're in cancellation and it's racy to remove the
- * node. It'll be removed by the end of cancellation, just ignore it.
- */
- if (!atomic_read(&tctx->in_idle))
- io_uring_del_tctx_node((unsigned long)work->ctx);
- complete(&work->completion);
-}
-
-static __cold bool io_cancel_ctx_cb(struct io_wq_work *work, void *data)
-{
- struct io_kiocb *req = container_of(work, struct io_kiocb, work);
-
- return req->ctx == data;
-}
-
-static __cold void io_ring_exit_work(struct work_struct *work)
-{
- struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, exit_work);
- unsigned long timeout = jiffies + HZ * 60 * 5;
- unsigned long interval = HZ / 20;
- struct io_tctx_exit exit;
- struct io_tctx_node *node;
- int ret;
-
- /*
- * If we're doing polled IO and end up having requests being
- * submitted async (out-of-line), then completions can come in while
- * we're waiting for refs to drop. We need to reap these manually,
- * as nobody else will be looking for them.
- */
- do {
- io_uring_try_cancel_requests(ctx, NULL, true);
- if (ctx->sq_data) {
- struct io_sq_data *sqd = ctx->sq_data;
- struct task_struct *tsk;
-
- io_sq_thread_park(sqd);
- tsk = sqd->thread;
- if (tsk && tsk->io_uring && tsk->io_uring->io_wq)
- io_wq_cancel_cb(tsk->io_uring->io_wq,
- io_cancel_ctx_cb, ctx, true);
- io_sq_thread_unpark(sqd);
- }
-
- io_req_caches_free(ctx);
-
- if (WARN_ON_ONCE(time_after(jiffies, timeout))) {
- /* there is little hope left, don't run it too often */
- interval = HZ * 60;
- }
- } while (!wait_for_completion_timeout(&ctx->ref_comp, interval));
-
- init_completion(&exit.completion);
- init_task_work(&exit.task_work, io_tctx_exit_cb);
- exit.ctx = ctx;
- /*
- * Some may use context even when all refs and requests have been put,
- * and they are free to do so while still holding uring_lock or
- * completion_lock, see io_req_task_submit(). Apart from other work,
- * this lock/unlock section also waits them to finish.
- */
- mutex_lock(&ctx->uring_lock);
- while (!list_empty(&ctx->tctx_list)) {
- WARN_ON_ONCE(time_after(jiffies, timeout));
-
- node = list_first_entry(&ctx->tctx_list, struct io_tctx_node,
- ctx_node);
- /* don't spin on a single task if cancellation failed */
- list_rotate_left(&ctx->tctx_list);
- ret = task_work_add(node->task, &exit.task_work, TWA_SIGNAL);
- if (WARN_ON_ONCE(ret))
- continue;
-
- mutex_unlock(&ctx->uring_lock);
- wait_for_completion(&exit.completion);
- mutex_lock(&ctx->uring_lock);
- }
- mutex_unlock(&ctx->uring_lock);
- spin_lock(&ctx->completion_lock);
- spin_unlock(&ctx->completion_lock);
-
- io_ring_ctx_free(ctx);
-}
-
-/* Returns true if we found and killed one or more timeouts */
-static __cold bool io_kill_timeouts(struct io_ring_ctx *ctx,
- struct task_struct *tsk, bool cancel_all)
-{
- struct io_kiocb *req, *tmp;
- int canceled = 0;
-
- spin_lock(&ctx->completion_lock);
- spin_lock_irq(&ctx->timeout_lock);
- list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) {
- if (io_match_task(req, tsk, cancel_all)) {
- io_kill_timeout(req, -ECANCELED);
- canceled++;
- }
- }
- spin_unlock_irq(&ctx->timeout_lock);
- io_commit_cqring(ctx);
- spin_unlock(&ctx->completion_lock);
- if (canceled != 0)
- io_cqring_ev_posted(ctx);
- return canceled != 0;
-}
-
-static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
-{
- unsigned long index;
- struct creds *creds;
-
- mutex_lock(&ctx->uring_lock);
- percpu_ref_kill(&ctx->refs);
- if (ctx->rings)
- __io_cqring_overflow_flush(ctx, true);
- xa_for_each(&ctx->personalities, index, creds)
- io_unregister_personality(ctx, index);
- mutex_unlock(&ctx->uring_lock);
-
- /* failed during ring init, it couldn't have issued any requests */
- if (ctx->rings) {
- io_kill_timeouts(ctx, NULL, true);
- io_poll_remove_all(ctx, NULL, true);
- /* if we failed setting up the ctx, we might not have any rings */
- io_iopoll_try_reap_events(ctx);
- }
-
- INIT_WORK(&ctx->exit_work, io_ring_exit_work);
- /*
- * Use system_unbound_wq to avoid spawning tons of event kworkers
- * if we're exiting a ton of rings at the same time. It just adds
- * noise and overhead, there's no discernable change in runtime
- * over using system_wq.
- */
- queue_work(system_unbound_wq, &ctx->exit_work);
-}
-
-static int io_uring_release(struct inode *inode, struct file *file)
-{
- struct io_ring_ctx *ctx = file->private_data;
-
- file->private_data = NULL;
- io_ring_ctx_wait_and_kill(ctx);
- return 0;
-}
-
-struct io_task_cancel {
- struct task_struct *task;
- bool all;
-};
-
-static bool io_cancel_task_cb(struct io_wq_work *work, void *data)
-{
- struct io_kiocb *req = container_of(work, struct io_kiocb, work);
- struct io_task_cancel *cancel = data;
-
- return io_match_task_safe(req, cancel->task, cancel->all);
-}
-
-static __cold bool io_cancel_defer_files(struct io_ring_ctx *ctx,
- struct task_struct *task,
- bool cancel_all)
-{
- struct io_defer_entry *de;
- LIST_HEAD(list);
-
- spin_lock(&ctx->completion_lock);
- list_for_each_entry_reverse(de, &ctx->defer_list, list) {
- if (io_match_task_safe(de->req, task, cancel_all)) {
- list_cut_position(&list, &ctx->defer_list, &de->list);
- break;
- }
- }
- spin_unlock(&ctx->completion_lock);
- if (list_empty(&list))
- return false;
-
- while (!list_empty(&list)) {
- de = list_first_entry(&list, struct io_defer_entry, list);
- list_del_init(&de->list);
- io_req_complete_failed(de->req, -ECANCELED);
- kfree(de);
- }
- return true;
-}
-
-static __cold bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx)
-{
- struct io_tctx_node *node;
- enum io_wq_cancel cret;
- bool ret = false;
-
- mutex_lock(&ctx->uring_lock);
- list_for_each_entry(node, &ctx->tctx_list, ctx_node) {
- struct io_uring_task *tctx = node->task->io_uring;
-
- /*
- * io_wq will stay alive while we hold uring_lock, because it's
- * killed after ctx nodes, which requires to take the lock.
- */
- if (!tctx || !tctx->io_wq)
- continue;
- cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_ctx_cb, ctx, true);
- ret |= (cret != IO_WQ_CANCEL_NOTFOUND);
- }
- mutex_unlock(&ctx->uring_lock);
-
- return ret;
-}
-
-static __cold void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
- struct task_struct *task,
- bool cancel_all)
-{
- struct io_task_cancel cancel = { .task = task, .all = cancel_all, };
- struct io_uring_task *tctx = task ? task->io_uring : NULL;
-
- /* failed during ring init, it couldn't have issued any requests */
- if (!ctx->rings)
- return;
-
- while (1) {
- enum io_wq_cancel cret;
- bool ret = false;
-
- if (!task) {
- ret |= io_uring_try_cancel_iowq(ctx);
- } else if (tctx && tctx->io_wq) {
- /*
- * Cancels requests of all rings, not only @ctx, but
- * it's fine as the task is in exit/exec.
- */
- cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_task_cb,
- &cancel, true);
- ret |= (cret != IO_WQ_CANCEL_NOTFOUND);
- }
-
- /* SQPOLL thread does its own polling */
- if ((!(ctx->flags & IORING_SETUP_SQPOLL) && cancel_all) ||
- (ctx->sq_data && ctx->sq_data->thread == current)) {
- while (!wq_list_empty(&ctx->iopoll_list)) {
- io_iopoll_try_reap_events(ctx);
- ret = true;
- }
- }
-
- ret |= io_cancel_defer_files(ctx, task, cancel_all);
- ret |= io_poll_remove_all(ctx, task, cancel_all);
- ret |= io_kill_timeouts(ctx, task, cancel_all);
- if (task)
- ret |= io_run_task_work();
- if (!ret)
- break;
- cond_resched();
- }
-}
-
-static int __io_uring_add_tctx_node(struct io_ring_ctx *ctx)
-{
- struct io_uring_task *tctx = current->io_uring;
- struct io_tctx_node *node;
- int ret;
-
- if (unlikely(!tctx)) {
- ret = io_uring_alloc_task_context(current, ctx);
- if (unlikely(ret))
- return ret;
-
- tctx = current->io_uring;
- if (ctx->iowq_limits_set) {
- unsigned int limits[2] = { ctx->iowq_limits[0],
- ctx->iowq_limits[1], };
-
- ret = io_wq_max_workers(tctx->io_wq, limits);
- if (ret)
- return ret;
- }
- }
- if (!xa_load(&tctx->xa, (unsigned long)ctx)) {
- node = kmalloc(sizeof(*node), GFP_KERNEL);
- if (!node)
- return -ENOMEM;
- node->ctx = ctx;
- node->task = current;
-
- ret = xa_err(xa_store(&tctx->xa, (unsigned long)ctx,
- node, GFP_KERNEL));
- if (ret) {
- kfree(node);
- return ret;
- }
-
- mutex_lock(&ctx->uring_lock);
- list_add(&node->ctx_node, &ctx->tctx_list);
- mutex_unlock(&ctx->uring_lock);
- }
- tctx->last = ctx;
- return 0;
-}
-
-/*
- * Note that this task has used io_uring. We use it for cancelation purposes.
- */
-static inline int io_uring_add_tctx_node(struct io_ring_ctx *ctx)
-{
- struct io_uring_task *tctx = current->io_uring;
-
- if (likely(tctx && tctx->last == ctx))
- return 0;
- return __io_uring_add_tctx_node(ctx);
-}
-
-/*
- * Remove this io_uring_file -> task mapping.
- */
-static __cold void io_uring_del_tctx_node(unsigned long index)
-{
- struct io_uring_task *tctx = current->io_uring;
- struct io_tctx_node *node;
-
- if (!tctx)
- return;
- node = xa_erase(&tctx->xa, index);
- if (!node)
- return;
-
- WARN_ON_ONCE(current != node->task);
- WARN_ON_ONCE(list_empty(&node->ctx_node));
-
- mutex_lock(&node->ctx->uring_lock);
- list_del(&node->ctx_node);
- mutex_unlock(&node->ctx->uring_lock);
-
- if (tctx->last == node->ctx)
- tctx->last = NULL;
- kfree(node);
-}
-
-static __cold void io_uring_clean_tctx(struct io_uring_task *tctx)
-{
- struct io_wq *wq = tctx->io_wq;
- struct io_tctx_node *node;
- unsigned long index;
-
- xa_for_each(&tctx->xa, index, node) {
- io_uring_del_tctx_node(index);
- cond_resched();
- }
- if (wq) {
- /*
- * Must be after io_uring_del_tctx_node() (removes nodes under
- * uring_lock) to avoid race with io_uring_try_cancel_iowq().
- */
- io_wq_put_and_exit(wq);
- tctx->io_wq = NULL;
- }
-}
-
-static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked)
-{
- if (tracked)
- return atomic_read(&tctx->inflight_tracked);
- return percpu_counter_sum(&tctx->inflight);
-}
-
-/*
- * Find any io_uring ctx that this task has registered or done IO on, and cancel
- * requests. @sqd should be not-null IFF it's an SQPOLL thread cancellation.
- */
-static __cold void io_uring_cancel_generic(bool cancel_all,
- struct io_sq_data *sqd)
-{
- struct io_uring_task *tctx = current->io_uring;
- struct io_ring_ctx *ctx;
- s64 inflight;
- DEFINE_WAIT(wait);
-
- WARN_ON_ONCE(sqd && sqd->thread != current);
-
- if (!current->io_uring)
- return;
- if (tctx->io_wq)
- io_wq_exit_start(tctx->io_wq);
-
- atomic_inc(&tctx->in_idle);
- do {
- io_uring_drop_tctx_refs(current);
- /* read completions before cancelations */
- inflight = tctx_inflight(tctx, !cancel_all);
- if (!inflight)
- break;
-
- if (!sqd) {
- struct io_tctx_node *node;
- unsigned long index;
-
- xa_for_each(&tctx->xa, index, node) {
- /* sqpoll task will cancel all its requests */
- if (node->ctx->sq_data)
- continue;
- io_uring_try_cancel_requests(node->ctx, current,
- cancel_all);
- }
- } else {
- list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
- io_uring_try_cancel_requests(ctx, current,
- cancel_all);
- }
-
- prepare_to_wait(&tctx->wait, &wait, TASK_INTERRUPTIBLE);
- io_run_task_work();
- io_uring_drop_tctx_refs(current);
-
- /*
- * If we've seen completions, retry without waiting. This
- * avoids a race where a completion comes in before we did
- * prepare_to_wait().
- */
- if (inflight == tctx_inflight(tctx, !cancel_all))
- schedule();
- finish_wait(&tctx->wait, &wait);
- } while (1);
-
- io_uring_clean_tctx(tctx);
- if (cancel_all) {
- /*
- * We shouldn't run task_works after cancel, so just leave
- * ->in_idle set for normal exit.
- */
- atomic_dec(&tctx->in_idle);
- /* for exec all current's requests should be gone, kill tctx */
- __io_uring_free(current);
- }
-}
-
-void __io_uring_cancel(bool cancel_all)
-{
- io_uring_cancel_generic(cancel_all, NULL);
-}
-
-void io_uring_unreg_ringfd(void)
-{
- struct io_uring_task *tctx = current->io_uring;
- int i;
-
- for (i = 0; i < IO_RINGFD_REG_MAX; i++) {
- if (tctx->registered_rings[i]) {
- fput(tctx->registered_rings[i]);
- tctx->registered_rings[i] = NULL;
- }
- }
-}
-
-static int io_ring_add_registered_fd(struct io_uring_task *tctx, int fd,
- int start, int end)
-{
- struct file *file;
- int offset;
-
- for (offset = start; offset < end; offset++) {
- offset = array_index_nospec(offset, IO_RINGFD_REG_MAX);
- if (tctx->registered_rings[offset])
- continue;
-
- file = fget(fd);
- if (!file) {
- return -EBADF;
- } else if (file->f_op != &io_uring_fops) {
- fput(file);
- return -EOPNOTSUPP;
- }
- tctx->registered_rings[offset] = file;
- return offset;
- }
-
- return -EBUSY;
-}
-
-/*
- * Register a ring fd to avoid fdget/fdput for each io_uring_enter()
- * invocation. User passes in an array of struct io_uring_rsrc_update
- * with ->data set to the ring_fd, and ->offset given for the desired
- * index. If no index is desired, application may set ->offset == -1U
- * and we'll find an available index. Returns number of entries
- * successfully processed, or < 0 on error if none were processed.
- */
-static int io_ringfd_register(struct io_ring_ctx *ctx, void __user *__arg,
- unsigned nr_args)
-{
- struct io_uring_rsrc_update __user *arg = __arg;
- struct io_uring_rsrc_update reg;
- struct io_uring_task *tctx;
- int ret, i;
-
- if (!nr_args || nr_args > IO_RINGFD_REG_MAX)
- return -EINVAL;
-
- mutex_unlock(&ctx->uring_lock);
- ret = io_uring_add_tctx_node(ctx);
- mutex_lock(&ctx->uring_lock);
- if (ret)
- return ret;
-
- tctx = current->io_uring;
- for (i = 0; i < nr_args; i++) {
- int start, end;
-
- if (copy_from_user(&reg, &arg[i], sizeof(reg))) {
- ret = -EFAULT;
- break;
- }
-
- if (reg.resv) {
- ret = -EINVAL;
- break;
- }
-
- if (reg.offset == -1U) {
- start = 0;
- end = IO_RINGFD_REG_MAX;
- } else {
- if (reg.offset >= IO_RINGFD_REG_MAX) {
- ret = -EINVAL;
- break;
- }
- start = reg.offset;
- end = start + 1;
- }
-
- ret = io_ring_add_registered_fd(tctx, reg.data, start, end);
- if (ret < 0)
- break;
-
- reg.offset = ret;
- if (copy_to_user(&arg[i], &reg, sizeof(reg))) {
- fput(tctx->registered_rings[reg.offset]);
- tctx->registered_rings[reg.offset] = NULL;
- ret = -EFAULT;
- break;
- }
- }
-
- return i ? i : ret;
-}
-
-static int io_ringfd_unregister(struct io_ring_ctx *ctx, void __user *__arg,
- unsigned nr_args)
-{
- struct io_uring_rsrc_update __user *arg = __arg;
- struct io_uring_task *tctx = current->io_uring;
- struct io_uring_rsrc_update reg;
- int ret = 0, i;
-
- if (!nr_args || nr_args > IO_RINGFD_REG_MAX)
- return -EINVAL;
- if (!tctx)
- return 0;
-
- for (i = 0; i < nr_args; i++) {
- if (copy_from_user(&reg, &arg[i], sizeof(reg))) {
- ret = -EFAULT;
- break;
- }
- if (reg.resv || reg.data || reg.offset >= IO_RINGFD_REG_MAX) {
- ret = -EINVAL;
- break;
- }
-
- reg.offset = array_index_nospec(reg.offset, IO_RINGFD_REG_MAX);
- if (tctx->registered_rings[reg.offset]) {
- fput(tctx->registered_rings[reg.offset]);
- tctx->registered_rings[reg.offset] = NULL;
- }
- }
-
- return i ? i : ret;
-}
-
-static void *io_uring_validate_mmap_request(struct file *file,
- loff_t pgoff, size_t sz)
-{
- struct io_ring_ctx *ctx = file->private_data;
- loff_t offset = pgoff << PAGE_SHIFT;
- struct page *page;
- void *ptr;
-
- switch (offset) {
- case IORING_OFF_SQ_RING:
- case IORING_OFF_CQ_RING:
- ptr = ctx->rings;
- break;
- case IORING_OFF_SQES:
- ptr = ctx->sq_sqes;
- break;
- default:
- return ERR_PTR(-EINVAL);
- }
-
- page = virt_to_head_page(ptr);
- if (sz > page_size(page))
- return ERR_PTR(-EINVAL);
-
- return ptr;
-}
-
-#ifdef CONFIG_MMU
-
-static __cold int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
-{
- size_t sz = vma->vm_end - vma->vm_start;
- unsigned long pfn;
- void *ptr;
-
- ptr = io_uring_validate_mmap_request(file, vma->vm_pgoff, sz);
- if (IS_ERR(ptr))
- return PTR_ERR(ptr);
-
- pfn = virt_to_phys(ptr) >> PAGE_SHIFT;
- return remap_pfn_range(vma, vma->vm_start, pfn, sz, vma->vm_page_prot);
-}
-
-#else /* !CONFIG_MMU */
-
-static int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
-{
- return vma->vm_flags & (VM_SHARED | VM_MAYSHARE) ? 0 : -EINVAL;
-}
-
-static unsigned int io_uring_nommu_mmap_capabilities(struct file *file)
-{
- return NOMMU_MAP_DIRECT | NOMMU_MAP_READ | NOMMU_MAP_WRITE;
-}
-
-static unsigned long io_uring_nommu_get_unmapped_area(struct file *file,
- unsigned long addr, unsigned long len,
- unsigned long pgoff, unsigned long flags)
-{
- void *ptr;
-
- ptr = io_uring_validate_mmap_request(file, pgoff, len);
- if (IS_ERR(ptr))
- return PTR_ERR(ptr);
-
- return (unsigned long) ptr;
-}
-
-#endif /* !CONFIG_MMU */
-
-static int io_sqpoll_wait_sq(struct io_ring_ctx *ctx)
-{
- DEFINE_WAIT(wait);
-
- do {
- if (!io_sqring_full(ctx))
- break;
- prepare_to_wait(&ctx->sqo_sq_wait, &wait, TASK_INTERRUPTIBLE);
-
- if (!io_sqring_full(ctx))
- break;
- schedule();
- } while (!signal_pending(current));
-
- finish_wait(&ctx->sqo_sq_wait, &wait);
- return 0;
-}
-
-static int io_validate_ext_arg(unsigned flags, const void __user *argp, size_t argsz)
-{
- if (flags & IORING_ENTER_EXT_ARG) {
- struct io_uring_getevents_arg arg;
-
- if (argsz != sizeof(arg))
- return -EINVAL;
- if (copy_from_user(&arg, argp, sizeof(arg)))
- return -EFAULT;
- }
- return 0;
-}
-
-static int io_get_ext_arg(unsigned flags, const void __user *argp, size_t *argsz,
- struct __kernel_timespec __user **ts,
- const sigset_t __user **sig)
-{
- struct io_uring_getevents_arg arg;
-
- /*
- * If EXT_ARG isn't set, then we have no timespec and the argp pointer
- * is just a pointer to the sigset_t.
- */
- if (!(flags & IORING_ENTER_EXT_ARG)) {
- *sig = (const sigset_t __user *) argp;
- *ts = NULL;
- return 0;
- }
-
- /*
- * EXT_ARG is set - ensure we agree on the size of it and copy in our
- * timespec and sigset_t pointers if good.
- */
- if (*argsz != sizeof(arg))
- return -EINVAL;
- if (copy_from_user(&arg, argp, sizeof(arg)))
- return -EFAULT;
- if (arg.pad)
- return -EINVAL;
- *sig = u64_to_user_ptr(arg.sigmask);
- *argsz = arg.sigmask_sz;
- *ts = u64_to_user_ptr(arg.ts);
- return 0;
-}
-
-SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
- u32, min_complete, u32, flags, const void __user *, argp,
- size_t, argsz)
-{
- struct io_ring_ctx *ctx;
- struct fd f;
- long ret;
-
- io_run_task_work();
-
- if (unlikely(flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP |
- IORING_ENTER_SQ_WAIT | IORING_ENTER_EXT_ARG |
- IORING_ENTER_REGISTERED_RING)))
- return -EINVAL;
-
- /*
- * Ring fd has been registered via IORING_REGISTER_RING_FDS, we
- * need only dereference our task private array to find it.
- */
- if (flags & IORING_ENTER_REGISTERED_RING) {
- struct io_uring_task *tctx = current->io_uring;
-
- if (!tctx || fd >= IO_RINGFD_REG_MAX)
- return -EINVAL;
- fd = array_index_nospec(fd, IO_RINGFD_REG_MAX);
- f.file = tctx->registered_rings[fd];
- f.flags = 0;
- } else {
- f = fdget(fd);
- }
-
- if (unlikely(!f.file))
- return -EBADF;
-
- ret = -EOPNOTSUPP;
- if (unlikely(f.file->f_op != &io_uring_fops))
- goto out_fput;
-
- ret = -ENXIO;
- ctx = f.file->private_data;
- if (unlikely(!percpu_ref_tryget(&ctx->refs)))
- goto out_fput;
-
- ret = -EBADFD;
- if (unlikely(ctx->flags & IORING_SETUP_R_DISABLED))
- goto out;
-
- /*
- * For SQ polling, the thread will do all submissions and completions.
- * Just return the requested submit count, and wake the thread if
- * we were asked to.
- */
- ret = 0;
- if (ctx->flags & IORING_SETUP_SQPOLL) {
- io_cqring_overflow_flush(ctx);
-
- if (unlikely(ctx->sq_data->thread == NULL)) {
- ret = -EOWNERDEAD;
- goto out;
- }
- if (flags & IORING_ENTER_SQ_WAKEUP)
- wake_up(&ctx->sq_data->wait);
- if (flags & IORING_ENTER_SQ_WAIT) {
- ret = io_sqpoll_wait_sq(ctx);
- if (ret)
- goto out;
- }
- ret = to_submit;
- } else if (to_submit) {
- ret = io_uring_add_tctx_node(ctx);
- if (unlikely(ret))
- goto out;
-
- mutex_lock(&ctx->uring_lock);
- ret = io_submit_sqes(ctx, to_submit);
- if (ret != to_submit) {
- mutex_unlock(&ctx->uring_lock);
- goto out;
- }
- if ((flags & IORING_ENTER_GETEVENTS) && ctx->syscall_iopoll)
- goto iopoll_locked;
- mutex_unlock(&ctx->uring_lock);
- }
- if (flags & IORING_ENTER_GETEVENTS) {
- int ret2;
- if (ctx->syscall_iopoll) {
- /*
- * We disallow the app entering submit/complete with
- * polling, but we still need to lock the ring to
- * prevent racing with polled issue that got punted to
- * a workqueue.
- */
- mutex_lock(&ctx->uring_lock);
-iopoll_locked:
- ret2 = io_validate_ext_arg(flags, argp, argsz);
- if (likely(!ret2)) {
- min_complete = min(min_complete,
- ctx->cq_entries);
- ret2 = io_iopoll_check(ctx, min_complete);
- }
- mutex_unlock(&ctx->uring_lock);
- } else {
- const sigset_t __user *sig;
- struct __kernel_timespec __user *ts;
-
- ret2 = io_get_ext_arg(flags, argp, &argsz, &ts, &sig);
- if (likely(!ret2)) {
- min_complete = min(min_complete,
- ctx->cq_entries);
- ret2 = io_cqring_wait(ctx, min_complete, sig,
- argsz, ts);
- }
- }
-
- if (!ret) {
- ret = ret2;
-
- /*
- * EBADR indicates that one or more CQE were dropped.
- * Once the user has been informed we can clear the bit
- * as they are obviously ok with those drops.
- */
- if (unlikely(ret2 == -EBADR))
- clear_bit(IO_CHECK_CQ_DROPPED_BIT,
- &ctx->check_cq);
- }
- }
-
-out:
- percpu_ref_put(&ctx->refs);
-out_fput:
- fdput(f);
- return ret;
-}
-
-#ifdef CONFIG_PROC_FS
-static __cold int io_uring_show_cred(struct seq_file *m, unsigned int id,
- const struct cred *cred)
-{
- struct user_namespace *uns = seq_user_ns(m);
- struct group_info *gi;
- kernel_cap_t cap;
- unsigned __capi;
- int g;
-
- seq_printf(m, "%5d\n", id);
- seq_put_decimal_ull(m, "\tUid:\t", from_kuid_munged(uns, cred->uid));
- seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->euid));
- seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->suid));
- seq_put_decimal_ull(m, "\t\t", from_kuid_munged(uns, cred->fsuid));
- seq_put_decimal_ull(m, "\n\tGid:\t", from_kgid_munged(uns, cred->gid));
- seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->egid));
- seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->sgid));
- seq_put_decimal_ull(m, "\t\t", from_kgid_munged(uns, cred->fsgid));
- seq_puts(m, "\n\tGroups:\t");
- gi = cred->group_info;
- for (g = 0; g < gi->ngroups; g++) {
- seq_put_decimal_ull(m, g ? " " : "",
- from_kgid_munged(uns, gi->gid[g]));
- }
- seq_puts(m, "\n\tCapEff:\t");
- cap = cred->cap_effective;
- CAP_FOR_EACH_U32(__capi)
- seq_put_hex_ll(m, NULL, cap.cap[CAP_LAST_U32 - __capi], 8);
- seq_putc(m, '\n');
- return 0;
-}
-
-static __cold void __io_uring_show_fdinfo(struct io_ring_ctx *ctx,
- struct seq_file *m)
-{
- struct io_sq_data *sq = NULL;
- struct io_overflow_cqe *ocqe;
- struct io_rings *r = ctx->rings;
- unsigned int sq_mask = ctx->sq_entries - 1, cq_mask = ctx->cq_entries - 1;
- unsigned int sq_head = READ_ONCE(r->sq.head);
- unsigned int sq_tail = READ_ONCE(r->sq.tail);
- unsigned int cq_head = READ_ONCE(r->cq.head);
- unsigned int cq_tail = READ_ONCE(r->cq.tail);
- unsigned int cq_shift = 0;
- unsigned int sq_entries, cq_entries;
- bool has_lock;
- bool is_cqe32 = (ctx->flags & IORING_SETUP_CQE32);
- unsigned int i;
-
- if (is_cqe32)
- cq_shift = 1;
-
- /*
- * we may get imprecise sqe and cqe info if uring is actively running
- * since we get cached_sq_head and cached_cq_tail without uring_lock
- * and sq_tail and cq_head are changed by userspace. But it's ok since
- * we usually use these info when it is stuck.
- */
- seq_printf(m, "SqMask:\t0x%x\n", sq_mask);
- seq_printf(m, "SqHead:\t%u\n", sq_head);
- seq_printf(m, "SqTail:\t%u\n", sq_tail);
- seq_printf(m, "CachedSqHead:\t%u\n", ctx->cached_sq_head);
- seq_printf(m, "CqMask:\t0x%x\n", cq_mask);
- seq_printf(m, "CqHead:\t%u\n", cq_head);
- seq_printf(m, "CqTail:\t%u\n", cq_tail);
- seq_printf(m, "CachedCqTail:\t%u\n", ctx->cached_cq_tail);
- seq_printf(m, "SQEs:\t%u\n", sq_tail - ctx->cached_sq_head);
- sq_entries = min(sq_tail - sq_head, ctx->sq_entries);
- for (i = 0; i < sq_entries; i++) {
- unsigned int entry = i + sq_head;
- unsigned int sq_idx = READ_ONCE(ctx->sq_array[entry & sq_mask]);
- struct io_uring_sqe *sqe;
-
- if (sq_idx > sq_mask)
- continue;
- sqe = &ctx->sq_sqes[sq_idx];
- seq_printf(m, "%5u: opcode:%d, fd:%d, flags:%x, user_data:%llu\n",
- sq_idx, sqe->opcode, sqe->fd, sqe->flags,
- sqe->user_data);
- }
- seq_printf(m, "CQEs:\t%u\n", cq_tail - cq_head);
- cq_entries = min(cq_tail - cq_head, ctx->cq_entries);
- for (i = 0; i < cq_entries; i++) {
- unsigned int entry = i + cq_head;
- struct io_uring_cqe *cqe = &r->cqes[(entry & cq_mask) << cq_shift];
-
- if (!is_cqe32) {
- seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x\n",
- entry & cq_mask, cqe->user_data, cqe->res,
- cqe->flags);
- } else {
- seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x, "
- "extra1:%llu, extra2:%llu\n",
- entry & cq_mask, cqe->user_data, cqe->res,
- cqe->flags, cqe->big_cqe[0], cqe->big_cqe[1]);
- }
- }
-
- /*
- * Avoid ABBA deadlock between the seq lock and the io_uring mutex,
- * since fdinfo case grabs it in the opposite direction of normal use
- * cases. If we fail to get the lock, we just don't iterate any
- * structures that could be going away outside the io_uring mutex.
- */
- has_lock = mutex_trylock(&ctx->uring_lock);
-
- if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) {
- sq = ctx->sq_data;
- if (!sq->thread)
- sq = NULL;
- }
-
- seq_printf(m, "SqThread:\t%d\n", sq ? task_pid_nr(sq->thread) : -1);
- seq_printf(m, "SqThreadCpu:\t%d\n", sq ? task_cpu(sq->thread) : -1);
- seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files);
- for (i = 0; has_lock && i < ctx->nr_user_files; i++) {
- struct file *f = io_file_from_index(ctx, i);
-
- if (f)
- seq_printf(m, "%5u: %s\n", i, file_dentry(f)->d_iname);
- else
- seq_printf(m, "%5u: <none>\n", i);
- }
- seq_printf(m, "UserBufs:\t%u\n", ctx->nr_user_bufs);
- for (i = 0; has_lock && i < ctx->nr_user_bufs; i++) {
- struct io_mapped_ubuf *buf = ctx->user_bufs[i];
- unsigned int len = buf->ubuf_end - buf->ubuf;
-
- seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, len);
- }
- if (has_lock && !xa_empty(&ctx->personalities)) {
- unsigned long index;
- const struct cred *cred;
-
- seq_printf(m, "Personalities:\n");
- xa_for_each(&ctx->personalities, index, cred)
- io_uring_show_cred(m, index, cred);
- }
- if (has_lock)
- mutex_unlock(&ctx->uring_lock);
-
- seq_puts(m, "PollList:\n");
- spin_lock(&ctx->completion_lock);
- for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) {
- struct hlist_head *list = &ctx->cancel_hash[i];
- struct io_kiocb *req;
-
- hlist_for_each_entry(req, list, hash_node)
- seq_printf(m, " op=%d, task_works=%d\n", req->opcode,
- task_work_pending(req->task));
- }
-
- seq_puts(m, "CqOverflowList:\n");
- list_for_each_entry(ocqe, &ctx->cq_overflow_list, list) {
- struct io_uring_cqe *cqe = &ocqe->cqe;
-
- seq_printf(m, " user_data=%llu, res=%d, flags=%x\n",
- cqe->user_data, cqe->res, cqe->flags);
-
- }
-
- spin_unlock(&ctx->completion_lock);
-}
-
-static __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
-{
- struct io_ring_ctx *ctx = f->private_data;
-
- if (percpu_ref_tryget(&ctx->refs)) {
- __io_uring_show_fdinfo(ctx, m);
- percpu_ref_put(&ctx->refs);
- }
-}
-#endif
-
-static const struct file_operations io_uring_fops = {
- .release = io_uring_release,
- .mmap = io_uring_mmap,
-#ifndef CONFIG_MMU
- .get_unmapped_area = io_uring_nommu_get_unmapped_area,
- .mmap_capabilities = io_uring_nommu_mmap_capabilities,
-#endif
- .poll = io_uring_poll,
-#ifdef CONFIG_PROC_FS
- .show_fdinfo = io_uring_show_fdinfo,
-#endif
-};
-
-static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx,
- struct io_uring_params *p)
-{
- struct io_rings *rings;
- size_t size, sq_array_offset;
-
- /* make sure these are sane, as we already accounted them */
- ctx->sq_entries = p->sq_entries;
- ctx->cq_entries = p->cq_entries;
-
- size = rings_size(ctx, p->sq_entries, p->cq_entries, &sq_array_offset);
- if (size == SIZE_MAX)
- return -EOVERFLOW;
-
- rings = io_mem_alloc(size);
- if (!rings)
- return -ENOMEM;
-
- ctx->rings = rings;
- ctx->sq_array = (u32 *)((char *)rings + sq_array_offset);
- rings->sq_ring_mask = p->sq_entries - 1;
- rings->cq_ring_mask = p->cq_entries - 1;
- rings->sq_ring_entries = p->sq_entries;
- rings->cq_ring_entries = p->cq_entries;
-
- if (p->flags & IORING_SETUP_SQE128)
- size = array_size(2 * sizeof(struct io_uring_sqe), p->sq_entries);
- else
- size = array_size(sizeof(struct io_uring_sqe), p->sq_entries);
- if (size == SIZE_MAX) {
- io_mem_free(ctx->rings);
- ctx->rings = NULL;
- return -EOVERFLOW;
- }
-
- ctx->sq_sqes = io_mem_alloc(size);
- if (!ctx->sq_sqes) {
- io_mem_free(ctx->rings);
- ctx->rings = NULL;
- return -ENOMEM;
- }
-
- return 0;
-}
-
-static int io_uring_install_fd(struct io_ring_ctx *ctx, struct file *file)
-{
- int ret, fd;
-
- fd = get_unused_fd_flags(O_RDWR | O_CLOEXEC);
- if (fd < 0)
- return fd;
-
- ret = io_uring_add_tctx_node(ctx);
- if (ret) {
- put_unused_fd(fd);
- return ret;
- }
- fd_install(fd, file);
- return fd;
-}
-
-/*
- * Allocate an anonymous fd, this is what constitutes the application
- * visible backing of an io_uring instance. The application mmaps this
- * fd to gain access to the SQ/CQ ring details. If UNIX sockets are enabled,
- * we have to tie this fd to a socket for file garbage collection purposes.
- */
-static struct file *io_uring_get_file(struct io_ring_ctx *ctx)
-{
- struct file *file;
-#if defined(CONFIG_UNIX)
- int ret;
-
- ret = sock_create_kern(&init_net, PF_UNIX, SOCK_RAW, IPPROTO_IP,
- &ctx->ring_sock);
- if (ret)
- return ERR_PTR(ret);
-#endif
-
- file = anon_inode_getfile_secure("[io_uring]", &io_uring_fops, ctx,
- O_RDWR | O_CLOEXEC, NULL);
-#if defined(CONFIG_UNIX)
- if (IS_ERR(file)) {
- sock_release(ctx->ring_sock);
- ctx->ring_sock = NULL;
- } else {
- ctx->ring_sock->file = file;
- }
-#endif
- return file;
-}
-
-static __cold int io_uring_create(unsigned entries, struct io_uring_params *p,
- struct io_uring_params __user *params)
-{
- struct io_ring_ctx *ctx;
- struct file *file;
- int ret;
-
- if (!entries)
- return -EINVAL;
- if (entries > IORING_MAX_ENTRIES) {
- if (!(p->flags & IORING_SETUP_CLAMP))
- return -EINVAL;
- entries = IORING_MAX_ENTRIES;
- }
-
- /*
- * Use twice as many entries for the CQ ring. It's possible for the
- * application to drive a higher depth than the size of the SQ ring,
- * since the sqes are only used at submission time. This allows for
- * some flexibility in overcommitting a bit. If the application has
- * set IORING_SETUP_CQSIZE, it will have passed in the desired number
- * of CQ ring entries manually.
- */
- p->sq_entries = roundup_pow_of_two(entries);
- if (p->flags & IORING_SETUP_CQSIZE) {
- /*
- * If IORING_SETUP_CQSIZE is set, we do the same roundup
- * to a power-of-two, if it isn't already. We do NOT impose
- * any cq vs sq ring sizing.
- */
- if (!p->cq_entries)
- return -EINVAL;
- if (p->cq_entries > IORING_MAX_CQ_ENTRIES) {
- if (!(p->flags & IORING_SETUP_CLAMP))
- return -EINVAL;
- p->cq_entries = IORING_MAX_CQ_ENTRIES;
- }
- p->cq_entries = roundup_pow_of_two(p->cq_entries);
- if (p->cq_entries < p->sq_entries)
- return -EINVAL;
- } else {
- p->cq_entries = 2 * p->sq_entries;
- }
-
- ctx = io_ring_ctx_alloc(p);
- if (!ctx)
- return -ENOMEM;
-
- /*
- * When SETUP_IOPOLL and SETUP_SQPOLL are both enabled, user
- * space applications don't need to do io completion events
- * polling again, they can rely on io_sq_thread to do polling
- * work, which can reduce cpu usage and uring_lock contention.
- */
- if (ctx->flags & IORING_SETUP_IOPOLL &&
- !(ctx->flags & IORING_SETUP_SQPOLL))
- ctx->syscall_iopoll = 1;
-
- ctx->compat = in_compat_syscall();
- if (!capable(CAP_IPC_LOCK))
- ctx->user = get_uid(current_user());
-
- /*
- * For SQPOLL, we just need a wakeup, always. For !SQPOLL, if
- * COOP_TASKRUN is set, then IPIs are never needed by the app.
- */
- ret = -EINVAL;
- if (ctx->flags & IORING_SETUP_SQPOLL) {
- /* IPI related flags don't make sense with SQPOLL */
- if (ctx->flags & (IORING_SETUP_COOP_TASKRUN |
- IORING_SETUP_TASKRUN_FLAG))
- goto err;
- ctx->notify_method = TWA_SIGNAL_NO_IPI;
- } else if (ctx->flags & IORING_SETUP_COOP_TASKRUN) {
- ctx->notify_method = TWA_SIGNAL_NO_IPI;
- } else {
- if (ctx->flags & IORING_SETUP_TASKRUN_FLAG)
- goto err;
- ctx->notify_method = TWA_SIGNAL;
- }
-
- /*
- * This is just grabbed for accounting purposes. When a process exits,
- * the mm is exited and dropped before the files, hence we need to hang
- * on to this mm purely for the purposes of being able to unaccount
- * memory (locked/pinned vm). It's not used for anything else.
- */
- mmgrab(current->mm);
- ctx->mm_account = current->mm;
-
- ret = io_allocate_scq_urings(ctx, p);
- if (ret)
- goto err;
-
- ret = io_sq_offload_create(ctx, p);
- if (ret)
- goto err;
- /* always set a rsrc node */
- ret = io_rsrc_node_switch_start(ctx);
- if (ret)
- goto err;
- io_rsrc_node_switch(ctx, NULL);
-
- memset(&p->sq_off, 0, sizeof(p->sq_off));
- p->sq_off.head = offsetof(struct io_rings, sq.head);
- p->sq_off.tail = offsetof(struct io_rings, sq.tail);
- p->sq_off.ring_mask = offsetof(struct io_rings, sq_ring_mask);
- p->sq_off.ring_entries = offsetof(struct io_rings, sq_ring_entries);
- p->sq_off.flags = offsetof(struct io_rings, sq_flags);
- p->sq_off.dropped = offsetof(struct io_rings, sq_dropped);
- p->sq_off.array = (char *)ctx->sq_array - (char *)ctx->rings;
-
- memset(&p->cq_off, 0, sizeof(p->cq_off));
- p->cq_off.head = offsetof(struct io_rings, cq.head);
- p->cq_off.tail = offsetof(struct io_rings, cq.tail);
- p->cq_off.ring_mask = offsetof(struct io_rings, cq_ring_mask);
- p->cq_off.ring_entries = offsetof(struct io_rings, cq_ring_entries);
- p->cq_off.overflow = offsetof(struct io_rings, cq_overflow);
- p->cq_off.cqes = offsetof(struct io_rings, cqes);
- p->cq_off.flags = offsetof(struct io_rings, cq_flags);
-
- p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP |
- IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
- IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL |
- IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED |
- IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS |
- IORING_FEAT_RSRC_TAGS | IORING_FEAT_CQE_SKIP |
- IORING_FEAT_LINKED_FILE;
-
- if (copy_to_user(params, p, sizeof(*p))) {
- ret = -EFAULT;
- goto err;
- }
-
- file = io_uring_get_file(ctx);
- if (IS_ERR(file)) {
- ret = PTR_ERR(file);
- goto err;
- }
-
- /*
- * Install ring fd as the very last thing, so we don't risk someone
- * having closed it before we finish setup
- */
- ret = io_uring_install_fd(ctx, file);
- if (ret < 0) {
- /* fput will clean it up */
- fput(file);
- return ret;
- }
-
- trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags);
- return ret;
-err:
- io_ring_ctx_wait_and_kill(ctx);
- return ret;
-}
-
-/*
- * Sets up an aio uring context, and returns the fd. Applications asks for a
- * ring size, we return the actual sq/cq ring sizes (among other things) in the
- * params structure passed in.
- */
-static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
-{
- struct io_uring_params p;
- int i;
-
- if (copy_from_user(&p, params, sizeof(p)))
- return -EFAULT;
- for (i = 0; i < ARRAY_SIZE(p.resv); i++) {
- if (p.resv[i])
- return -EINVAL;
- }
-
- if (p.flags & ~(IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL |
- IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE |
- IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ |
- IORING_SETUP_R_DISABLED | IORING_SETUP_SUBMIT_ALL |
- IORING_SETUP_COOP_TASKRUN | IORING_SETUP_TASKRUN_FLAG |
- IORING_SETUP_SQE128 | IORING_SETUP_CQE32))
- return -EINVAL;
-
- return io_uring_create(entries, &p, params);
-}
-
-SYSCALL_DEFINE2(io_uring_setup, u32, entries,
- struct io_uring_params __user *, params)
-{
- return io_uring_setup(entries, params);
-}
-
-static __cold int io_probe(struct io_ring_ctx *ctx, void __user *arg,
- unsigned nr_args)
-{
- struct io_uring_probe *p;
- size_t size;
- int i, ret;
-
- size = struct_size(p, ops, nr_args);
- if (size == SIZE_MAX)
- return -EOVERFLOW;
- p = kzalloc(size, GFP_KERNEL);
- if (!p)
- return -ENOMEM;
-
- ret = -EFAULT;
- if (copy_from_user(p, arg, size))
- goto out;
- ret = -EINVAL;
- if (memchr_inv(p, 0, size))
- goto out;
-
- p->last_op = IORING_OP_LAST - 1;
- if (nr_args > IORING_OP_LAST)
- nr_args = IORING_OP_LAST;
-
- for (i = 0; i < nr_args; i++) {
- p->ops[i].op = i;
- if (!io_op_defs[i].not_supported)
- p->ops[i].flags = IO_URING_OP_SUPPORTED;
- }
- p->ops_len = i;
-
- ret = 0;
- if (copy_to_user(arg, p, size))
- ret = -EFAULT;
-out:
- kfree(p);
- return ret;
-}
-
-static int io_register_personality(struct io_ring_ctx *ctx)
-{
- const struct cred *creds;
- u32 id;
- int ret;
-
- creds = get_current_cred();
-
- ret = xa_alloc_cyclic(&ctx->personalities, &id, (void *)creds,
- XA_LIMIT(0, USHRT_MAX), &ctx->pers_next, GFP_KERNEL);
- if (ret < 0) {
- put_cred(creds);
- return ret;
- }
- return id;
-}
-
-static __cold int io_register_restrictions(struct io_ring_ctx *ctx,
- void __user *arg, unsigned int nr_args)
-{
- struct io_uring_restriction *res;
- size_t size;
- int i, ret;
-
- /* Restrictions allowed only if rings started disabled */
- if (!(ctx->flags & IORING_SETUP_R_DISABLED))
- return -EBADFD;
-
- /* We allow only a single restrictions registration */
- if (ctx->restrictions.registered)
- return -EBUSY;
-
- if (!arg || nr_args > IORING_MAX_RESTRICTIONS)
- return -EINVAL;
-
- size = array_size(nr_args, sizeof(*res));
- if (size == SIZE_MAX)
- return -EOVERFLOW;
-
- res = memdup_user(arg, size);
- if (IS_ERR(res))
- return PTR_ERR(res);
-
- ret = 0;
-
- for (i = 0; i < nr_args; i++) {
- switch (res[i].opcode) {
- case IORING_RESTRICTION_REGISTER_OP:
- if (res[i].register_op >= IORING_REGISTER_LAST) {
- ret = -EINVAL;
- goto out;
- }
-
- __set_bit(res[i].register_op,
- ctx->restrictions.register_op);
- break;
- case IORING_RESTRICTION_SQE_OP:
- if (res[i].sqe_op >= IORING_OP_LAST) {
- ret = -EINVAL;
- goto out;
- }
-
- __set_bit(res[i].sqe_op, ctx->restrictions.sqe_op);
- break;
- case IORING_RESTRICTION_SQE_FLAGS_ALLOWED:
- ctx->restrictions.sqe_flags_allowed = res[i].sqe_flags;
- break;
- case IORING_RESTRICTION_SQE_FLAGS_REQUIRED:
- ctx->restrictions.sqe_flags_required = res[i].sqe_flags;
- break;
- default:
- ret = -EINVAL;
- goto out;
- }
- }
-
-out:
- /* Reset all restrictions if an error happened */
- if (ret != 0)
- memset(&ctx->restrictions, 0, sizeof(ctx->restrictions));
- else
- ctx->restrictions.registered = true;
-
- kfree(res);
- return ret;
-}
-
-static int io_register_enable_rings(struct io_ring_ctx *ctx)
-{
- if (!(ctx->flags & IORING_SETUP_R_DISABLED))
- return -EBADFD;
-
- if (ctx->restrictions.registered)
- ctx->restricted = 1;
-
- ctx->flags &= ~IORING_SETUP_R_DISABLED;
- if (ctx->sq_data && wq_has_sleeper(&ctx->sq_data->wait))
- wake_up(&ctx->sq_data->wait);
- return 0;
-}
-
-static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type,
- struct io_uring_rsrc_update2 *up,
- unsigned nr_args)
-{
- __u32 tmp;
- int err;
-
- if (check_add_overflow(up->offset, nr_args, &tmp))
- return -EOVERFLOW;
- err = io_rsrc_node_switch_start(ctx);
- if (err)
- return err;
-
- switch (type) {
- case IORING_RSRC_FILE:
- return __io_sqe_files_update(ctx, up, nr_args);
- case IORING_RSRC_BUFFER:
- return __io_sqe_buffers_update(ctx, up, nr_args);
- }
- return -EINVAL;
-}
-
-static int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg,
- unsigned nr_args)
-{
- struct io_uring_rsrc_update2 up;
-
- if (!nr_args)
- return -EINVAL;
- memset(&up, 0, sizeof(up));
- if (copy_from_user(&up, arg, sizeof(struct io_uring_rsrc_update)))
- return -EFAULT;
- if (up.resv || up.resv2)
- return -EINVAL;
- return __io_register_rsrc_update(ctx, IORING_RSRC_FILE, &up, nr_args);
-}
-
-static int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg,
- unsigned size, unsigned type)
-{
- struct io_uring_rsrc_update2 up;
-
- if (size != sizeof(up))
- return -EINVAL;
- if (copy_from_user(&up, arg, sizeof(up)))
- return -EFAULT;
- if (!up.nr || up.resv || up.resv2)
- return -EINVAL;
- return __io_register_rsrc_update(ctx, type, &up, up.nr);
-}
-
-static __cold int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg,
- unsigned int size, unsigned int type)
-{
- struct io_uring_rsrc_register rr;
-
- /* keep it extendible */
- if (size != sizeof(rr))
- return -EINVAL;
-
- memset(&rr, 0, sizeof(rr));
- if (copy_from_user(&rr, arg, size))
- return -EFAULT;
- if (!rr.nr || rr.resv2)
- return -EINVAL;
- if (rr.flags & ~IORING_RSRC_REGISTER_SPARSE)
- return -EINVAL;
-
- switch (type) {
- case IORING_RSRC_FILE:
- if (rr.flags & IORING_RSRC_REGISTER_SPARSE && rr.data)
- break;
- return io_sqe_files_register(ctx, u64_to_user_ptr(rr.data),
- rr.nr, u64_to_user_ptr(rr.tags));
- case IORING_RSRC_BUFFER:
- if (rr.flags & IORING_RSRC_REGISTER_SPARSE && rr.data)
- break;
- return io_sqe_buffers_register(ctx, u64_to_user_ptr(rr.data),
- rr.nr, u64_to_user_ptr(rr.tags));
- }
- return -EINVAL;
-}
-
-static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx,
- void __user *arg, unsigned len)
-{
- struct io_uring_task *tctx = current->io_uring;
- cpumask_var_t new_mask;
- int ret;
-
- if (!tctx || !tctx->io_wq)
- return -EINVAL;
-
- if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
- return -ENOMEM;
-
- cpumask_clear(new_mask);
- if (len > cpumask_size())
- len = cpumask_size();
-
- if (in_compat_syscall()) {
- ret = compat_get_bitmap(cpumask_bits(new_mask),
- (const compat_ulong_t __user *)arg,
- len * 8 /* CHAR_BIT */);
- } else {
- ret = copy_from_user(new_mask, arg, len);
- }
-
- if (ret) {
- free_cpumask_var(new_mask);
- return -EFAULT;
- }
-
- ret = io_wq_cpu_affinity(tctx->io_wq, new_mask);
- free_cpumask_var(new_mask);
- return ret;
-}
-
-static __cold int io_unregister_iowq_aff(struct io_ring_ctx *ctx)
-{
- struct io_uring_task *tctx = current->io_uring;
-
- if (!tctx || !tctx->io_wq)
- return -EINVAL;
-
- return io_wq_cpu_affinity(tctx->io_wq, NULL);
-}
-
-static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
- void __user *arg)
- __must_hold(&ctx->uring_lock)
-{
- struct io_tctx_node *node;
- struct io_uring_task *tctx = NULL;
- struct io_sq_data *sqd = NULL;
- __u32 new_count[2];
- int i, ret;
-
- if (copy_from_user(new_count, arg, sizeof(new_count)))
- return -EFAULT;
- for (i = 0; i < ARRAY_SIZE(new_count); i++)
- if (new_count[i] > INT_MAX)
- return -EINVAL;
-
- if (ctx->flags & IORING_SETUP_SQPOLL) {
- sqd = ctx->sq_data;
- if (sqd) {
- /*
- * Observe the correct sqd->lock -> ctx->uring_lock
- * ordering. Fine to drop uring_lock here, we hold
- * a ref to the ctx.
- */
- refcount_inc(&sqd->refs);
- mutex_unlock(&ctx->uring_lock);
- mutex_lock(&sqd->lock);
- mutex_lock(&ctx->uring_lock);
- if (sqd->thread)
- tctx = sqd->thread->io_uring;
- }
- } else {
- tctx = current->io_uring;
- }
-
- BUILD_BUG_ON(sizeof(new_count) != sizeof(ctx->iowq_limits));
-
- for (i = 0; i < ARRAY_SIZE(new_count); i++)
- if (new_count[i])
- ctx->iowq_limits[i] = new_count[i];
- ctx->iowq_limits_set = true;
-
- if (tctx && tctx->io_wq) {
- ret = io_wq_max_workers(tctx->io_wq, new_count);
- if (ret)
- goto err;
- } else {
- memset(new_count, 0, sizeof(new_count));
- }
-
- if (sqd) {
- mutex_unlock(&sqd->lock);
- io_put_sq_data(sqd);
- }
-
- if (copy_to_user(arg, new_count, sizeof(new_count)))
- return -EFAULT;
-
- /* that's it for SQPOLL, only the SQPOLL task creates requests */
- if (sqd)
- return 0;
-
- /* now propagate the restriction to all registered users */
- list_for_each_entry(node, &ctx->tctx_list, ctx_node) {
- struct io_uring_task *tctx = node->task->io_uring;
-
- if (WARN_ON_ONCE(!tctx->io_wq))
- continue;
-
- for (i = 0; i < ARRAY_SIZE(new_count); i++)
- new_count[i] = ctx->iowq_limits[i];
- /* ignore errors, it always returns zero anyway */
- (void)io_wq_max_workers(tctx->io_wq, new_count);
- }
- return 0;
-err:
- if (sqd) {
- mutex_unlock(&sqd->lock);
- io_put_sq_data(sqd);
- }
- return ret;
-}
-
-static int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
-{
- struct io_uring_buf_ring *br;
- struct io_uring_buf_reg reg;
- struct io_buffer_list *bl;
- struct page **pages;
- int nr_pages;
-
- if (copy_from_user(&reg, arg, sizeof(reg)))
- return -EFAULT;
-
- if (reg.pad || reg.resv[0] || reg.resv[1] || reg.resv[2])
- return -EINVAL;
- if (!reg.ring_addr)
- return -EFAULT;
- if (reg.ring_addr & ~PAGE_MASK)
- return -EINVAL;
- if (!is_power_of_2(reg.ring_entries))
- return -EINVAL;
-
- /* cannot disambiguate full vs empty due to head/tail size */
- if (reg.ring_entries >= 65536)
- return -EINVAL;
-
- if (unlikely(reg.bgid < BGID_ARRAY && !ctx->io_bl)) {
- int ret = io_init_bl_list(ctx);
- if (ret)
- return ret;
- }
-
- bl = io_buffer_get_list(ctx, reg.bgid);
- if (bl) {
- /* if mapped buffer ring OR classic exists, don't allow */
- if (bl->buf_nr_pages || !list_empty(&bl->buf_list))
- return -EEXIST;
- } else {
- bl = kzalloc(sizeof(*bl), GFP_KERNEL);
- if (!bl)
- return -ENOMEM;
- }
-
- pages = io_pin_pages(reg.ring_addr,
- struct_size(br, bufs, reg.ring_entries),
- &nr_pages);
- if (IS_ERR(pages)) {
- kfree(bl);
- return PTR_ERR(pages);
- }
-
- br = page_address(pages[0]);
- bl->buf_pages = pages;
- bl->buf_nr_pages = nr_pages;
- bl->nr_entries = reg.ring_entries;
- bl->buf_ring = br;
- bl->mask = reg.ring_entries - 1;
- io_buffer_add_list(ctx, bl, reg.bgid);
- return 0;
-}
-
-static int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
-{
- struct io_uring_buf_reg reg;
- struct io_buffer_list *bl;
-
- if (copy_from_user(&reg, arg, sizeof(reg)))
- return -EFAULT;
- if (reg.pad || reg.resv[0] || reg.resv[1] || reg.resv[2])
- return -EINVAL;
-
- bl = io_buffer_get_list(ctx, reg.bgid);
- if (!bl)
- return -ENOENT;
- if (!bl->buf_nr_pages)
- return -EINVAL;
-
- __io_remove_buffers(ctx, bl, -1U);
- if (bl->bgid >= BGID_ARRAY) {
- xa_erase(&ctx->io_bl_xa, bl->bgid);
- kfree(bl);
- }
- return 0;
-}
-
-static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
- void __user *arg, unsigned nr_args)
- __releases(ctx->uring_lock)
- __acquires(ctx->uring_lock)
-{
- int ret;
-
- /*
- * We're inside the ring mutex, if the ref is already dying, then
- * someone else killed the ctx or is already going through
- * io_uring_register().
- */
- if (percpu_ref_is_dying(&ctx->refs))
- return -ENXIO;
-
- if (ctx->restricted) {
- if (opcode >= IORING_REGISTER_LAST)
- return -EINVAL;
- opcode = array_index_nospec(opcode, IORING_REGISTER_LAST);
- if (!test_bit(opcode, ctx->restrictions.register_op))
- return -EACCES;
- }
-
- switch (opcode) {
- case IORING_REGISTER_BUFFERS:
- ret = -EFAULT;
- if (!arg)
- break;
- ret = io_sqe_buffers_register(ctx, arg, nr_args, NULL);
- break;
- case IORING_UNREGISTER_BUFFERS:
- ret = -EINVAL;
- if (arg || nr_args)
- break;
- ret = io_sqe_buffers_unregister(ctx);
- break;
- case IORING_REGISTER_FILES:
- ret = -EFAULT;
- if (!arg)
- break;
- ret = io_sqe_files_register(ctx, arg, nr_args, NULL);
- break;
- case IORING_UNREGISTER_FILES:
- ret = -EINVAL;
- if (arg || nr_args)
- break;
- ret = io_sqe_files_unregister(ctx);
- break;
- case IORING_REGISTER_FILES_UPDATE:
- ret = io_register_files_update(ctx, arg, nr_args);
- break;
- case IORING_REGISTER_EVENTFD:
- ret = -EINVAL;
- if (nr_args != 1)
- break;
- ret = io_eventfd_register(ctx, arg, 0);
- break;
- case IORING_REGISTER_EVENTFD_ASYNC:
- ret = -EINVAL;
- if (nr_args != 1)
- break;
- ret = io_eventfd_register(ctx, arg, 1);
- break;
- case IORING_UNREGISTER_EVENTFD:
- ret = -EINVAL;
- if (arg || nr_args)
- break;
- ret = io_eventfd_unregister(ctx);
- break;
- case IORING_REGISTER_PROBE:
- ret = -EINVAL;
- if (!arg || nr_args > 256)
- break;
- ret = io_probe(ctx, arg, nr_args);
- break;
- case IORING_REGISTER_PERSONALITY:
- ret = -EINVAL;
- if (arg || nr_args)
- break;
- ret = io_register_personality(ctx);
- break;
- case IORING_UNREGISTER_PERSONALITY:
- ret = -EINVAL;
- if (arg)
- break;
- ret = io_unregister_personality(ctx, nr_args);
- break;
- case IORING_REGISTER_ENABLE_RINGS:
- ret = -EINVAL;
- if (arg || nr_args)
- break;
- ret = io_register_enable_rings(ctx);
- break;
- case IORING_REGISTER_RESTRICTIONS:
- ret = io_register_restrictions(ctx, arg, nr_args);
- break;
- case IORING_REGISTER_FILES2:
- ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_FILE);
- break;
- case IORING_REGISTER_FILES_UPDATE2:
- ret = io_register_rsrc_update(ctx, arg, nr_args,
- IORING_RSRC_FILE);
- break;
- case IORING_REGISTER_BUFFERS2:
- ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_BUFFER);
- break;
- case IORING_REGISTER_BUFFERS_UPDATE:
- ret = io_register_rsrc_update(ctx, arg, nr_args,
- IORING_RSRC_BUFFER);
- break;
- case IORING_REGISTER_IOWQ_AFF:
- ret = -EINVAL;
- if (!arg || !nr_args)
- break;
- ret = io_register_iowq_aff(ctx, arg, nr_args);
- break;
- case IORING_UNREGISTER_IOWQ_AFF:
- ret = -EINVAL;
- if (arg || nr_args)
- break;
- ret = io_unregister_iowq_aff(ctx);
- break;
- case IORING_REGISTER_IOWQ_MAX_WORKERS:
- ret = -EINVAL;
- if (!arg || nr_args != 2)
- break;
- ret = io_register_iowq_max_workers(ctx, arg);
- break;
- case IORING_REGISTER_RING_FDS:
- ret = io_ringfd_register(ctx, arg, nr_args);
- break;
- case IORING_UNREGISTER_RING_FDS:
- ret = io_ringfd_unregister(ctx, arg, nr_args);
- break;
- case IORING_REGISTER_PBUF_RING:
- ret = -EINVAL;
- if (!arg || nr_args != 1)
- break;
- ret = io_register_pbuf_ring(ctx, arg);
- break;
- case IORING_UNREGISTER_PBUF_RING:
- ret = -EINVAL;
- if (!arg || nr_args != 1)
- break;
- ret = io_unregister_pbuf_ring(ctx, arg);
- break;
- default:
- ret = -EINVAL;
- break;
- }
-
- return ret;
-}
-
-SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode,
- void __user *, arg, unsigned int, nr_args)
-{
- struct io_ring_ctx *ctx;
- long ret = -EBADF;
- struct fd f;
-
- f = fdget(fd);
- if (!f.file)
- return -EBADF;
-
- ret = -EOPNOTSUPP;
- if (f.file->f_op != &io_uring_fops)
- goto out_fput;
-
- ctx = f.file->private_data;
-
- io_run_task_work();
-
- mutex_lock(&ctx->uring_lock);
- ret = __io_uring_register(ctx, opcode, arg, nr_args);
- mutex_unlock(&ctx->uring_lock);
- trace_io_uring_register(ctx, opcode, ctx->nr_user_files, ctx->nr_user_bufs, ret);
-out_fput:
- fdput(f);
- return ret;
-}
-
-static int __init io_uring_init(void)
-{
-#define __BUILD_BUG_VERIFY_ELEMENT(stype, eoffset, etype, ename) do { \
- BUILD_BUG_ON(offsetof(stype, ename) != eoffset); \
- BUILD_BUG_ON(sizeof(etype) != sizeof_field(stype, ename)); \
-} while (0)
-
-#define BUILD_BUG_SQE_ELEM(eoffset, etype, ename) \
- __BUILD_BUG_VERIFY_ELEMENT(struct io_uring_sqe, eoffset, etype, ename)
- BUILD_BUG_ON(sizeof(struct io_uring_sqe) != 64);
- BUILD_BUG_SQE_ELEM(0, __u8, opcode);
- BUILD_BUG_SQE_ELEM(1, __u8, flags);
- BUILD_BUG_SQE_ELEM(2, __u16, ioprio);
- BUILD_BUG_SQE_ELEM(4, __s32, fd);
- BUILD_BUG_SQE_ELEM(8, __u64, off);
- BUILD_BUG_SQE_ELEM(8, __u64, addr2);
- BUILD_BUG_SQE_ELEM(16, __u64, addr);
- BUILD_BUG_SQE_ELEM(16, __u64, splice_off_in);
- BUILD_BUG_SQE_ELEM(24, __u32, len);
- BUILD_BUG_SQE_ELEM(28, __kernel_rwf_t, rw_flags);
- BUILD_BUG_SQE_ELEM(28, /* compat */ int, rw_flags);
- BUILD_BUG_SQE_ELEM(28, /* compat */ __u32, rw_flags);
- BUILD_BUG_SQE_ELEM(28, __u32, fsync_flags);
- BUILD_BUG_SQE_ELEM(28, /* compat */ __u16, poll_events);
- BUILD_BUG_SQE_ELEM(28, __u32, poll32_events);
- BUILD_BUG_SQE_ELEM(28, __u32, sync_range_flags);
- BUILD_BUG_SQE_ELEM(28, __u32, msg_flags);
- BUILD_BUG_SQE_ELEM(28, __u32, timeout_flags);
- BUILD_BUG_SQE_ELEM(28, __u32, accept_flags);
- BUILD_BUG_SQE_ELEM(28, __u32, cancel_flags);
- BUILD_BUG_SQE_ELEM(28, __u32, open_flags);
- BUILD_BUG_SQE_ELEM(28, __u32, statx_flags);
- BUILD_BUG_SQE_ELEM(28, __u32, fadvise_advice);
- BUILD_BUG_SQE_ELEM(28, __u32, splice_flags);
- BUILD_BUG_SQE_ELEM(32, __u64, user_data);
- BUILD_BUG_SQE_ELEM(40, __u16, buf_index);
- BUILD_BUG_SQE_ELEM(40, __u16, buf_group);
- BUILD_BUG_SQE_ELEM(42, __u16, personality);
- BUILD_BUG_SQE_ELEM(44, __s32, splice_fd_in);
- BUILD_BUG_SQE_ELEM(44, __u32, file_index);
- BUILD_BUG_SQE_ELEM(48, __u64, addr3);
-
- BUILD_BUG_ON(sizeof(struct io_uring_files_update) !=
- sizeof(struct io_uring_rsrc_update));
- BUILD_BUG_ON(sizeof(struct io_uring_rsrc_update) >
- sizeof(struct io_uring_rsrc_update2));
-
- /* ->buf_index is u16 */
- BUILD_BUG_ON(IORING_MAX_REG_BUFFERS >= (1u << 16));
- BUILD_BUG_ON(BGID_ARRAY * sizeof(struct io_buffer_list) > PAGE_SIZE);
- BUILD_BUG_ON(offsetof(struct io_uring_buf_ring, bufs) != 0);
- BUILD_BUG_ON(offsetof(struct io_uring_buf, resv) !=
- offsetof(struct io_uring_buf_ring, tail));
-
- /* should fit into one byte */
- BUILD_BUG_ON(SQE_VALID_FLAGS >= (1 << 8));
- BUILD_BUG_ON(SQE_COMMON_FLAGS >= (1 << 8));
- BUILD_BUG_ON((SQE_VALID_FLAGS | SQE_COMMON_FLAGS) != SQE_VALID_FLAGS);
-
- BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST);
- BUILD_BUG_ON(__REQ_F_LAST_BIT > 8 * sizeof(int));
-
- BUILD_BUG_ON(sizeof(atomic_t) != sizeof(u32));
-
- BUILD_BUG_ON(sizeof(struct io_uring_cmd) > 64);
-
- req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC |
- SLAB_ACCOUNT);
- return 0;
-};
-__initcall(io_uring_init);
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index d2a9f699e17e..c681eacc389b 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -44,20 +44,28 @@ static inline struct iomap_page *to_iomap_page(struct folio *folio)
static struct bio_set iomap_ioend_bioset;
static struct iomap_page *
-iomap_page_create(struct inode *inode, struct folio *folio)
+iomap_page_create(struct inode *inode, struct folio *folio, unsigned int flags)
{
struct iomap_page *iop = to_iomap_page(folio);
unsigned int nr_blocks = i_blocks_per_folio(inode, folio);
+ gfp_t gfp;
if (iop || nr_blocks <= 1)
return iop;
+ if (flags & IOMAP_NOWAIT)
+ gfp = GFP_NOWAIT;
+ else
+ gfp = GFP_NOFS | __GFP_NOFAIL;
+
iop = kzalloc(struct_size(iop, uptodate, BITS_TO_LONGS(nr_blocks)),
- GFP_NOFS | __GFP_NOFAIL);
- spin_lock_init(&iop->uptodate_lock);
- if (folio_test_uptodate(folio))
- bitmap_fill(iop->uptodate, nr_blocks);
- folio_attach_private(folio, iop);
+ gfp);
+ if (iop) {
+ spin_lock_init(&iop->uptodate_lock);
+ if (folio_test_uptodate(folio))
+ bitmap_fill(iop->uptodate, nr_blocks);
+ folio_attach_private(folio, iop);
+ }
return iop;
}
@@ -226,7 +234,7 @@ static int iomap_read_inline_data(const struct iomap_iter *iter,
if (WARN_ON_ONCE(size > iomap->length))
return -EIO;
if (offset > 0)
- iop = iomap_page_create(iter->inode, folio);
+ iop = iomap_page_create(iter->inode, folio, iter->flags);
else
iop = to_iomap_page(folio);
@@ -264,7 +272,7 @@ static loff_t iomap_readpage_iter(const struct iomap_iter *iter,
return iomap_read_inline_data(iter, folio);
/* zero post-eof blocks as the page may be mapped */
- iop = iomap_page_create(iter->inode, folio);
+ iop = iomap_page_create(iter->inode, folio, iter->flags);
iomap_adjust_read_range(iter->inode, folio, &pos, length, &poff, &plen);
if (plen == 0)
goto done;
@@ -547,10 +555,11 @@ static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
size_t len, struct folio *folio)
{
const struct iomap *srcmap = iomap_iter_srcmap(iter);
- struct iomap_page *iop = iomap_page_create(iter->inode, folio);
+ struct iomap_page *iop;
loff_t block_size = i_blocksize(iter->inode);
loff_t block_start = round_down(pos, block_size);
loff_t block_end = round_up(pos + len, block_size);
+ unsigned int nr_blocks = i_blocks_per_folio(iter->inode, folio);
size_t from = offset_in_folio(folio, pos), to = from + len;
size_t poff, plen;
@@ -558,6 +567,10 @@ static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
return 0;
folio_clear_error(folio);
+ iop = iomap_page_create(iter->inode, folio, iter->flags);
+ if ((iter->flags & IOMAP_NOWAIT) && !iop && nr_blocks > 1)
+ return -EAGAIN;
+
do {
iomap_adjust_read_range(iter->inode, folio, &block_start,
block_end - block_start, &poff, &plen);
@@ -574,7 +587,12 @@ static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
return -EIO;
folio_zero_segments(folio, poff, from, to, poff + plen);
} else {
- int status = iomap_read_folio_sync(block_start, folio,
+ int status;
+
+ if (iter->flags & IOMAP_NOWAIT)
+ return -EAGAIN;
+
+ status = iomap_read_folio_sync(block_start, folio,
poff, plen, srcmap);
if (status)
return status;
@@ -603,6 +621,9 @@ static int iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
unsigned fgp = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE | FGP_NOFS;
int status = 0;
+ if (iter->flags & IOMAP_NOWAIT)
+ fgp |= FGP_NOWAIT;
+
BUG_ON(pos + len > iter->iomap.offset + iter->iomap.length);
if (srcmap != &iter->iomap)
BUG_ON(pos + len > srcmap->offset + srcmap->length);
@@ -622,7 +643,7 @@ static int iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
folio = __filemap_get_folio(iter->inode->i_mapping, pos >> PAGE_SHIFT,
fgp, mapping_gfp_mask(iter->inode->i_mapping));
if (!folio) {
- status = -ENOMEM;
+ status = (iter->flags & IOMAP_NOWAIT) ? -EAGAIN : -ENOMEM;
goto out_no_page;
}
if (pos + len > folio_pos(folio) + folio_size(folio))
@@ -740,6 +761,8 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
loff_t pos = iter->pos;
ssize_t written = 0;
long status = 0;
+ struct address_space *mapping = iter->inode->i_mapping;
+ unsigned int bdp_flags = (iter->flags & IOMAP_NOWAIT) ? BDP_ASYNC : 0;
do {
struct folio *folio;
@@ -752,6 +775,11 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
bytes = min_t(unsigned long, PAGE_SIZE - offset,
iov_iter_count(i));
again:
+ status = balance_dirty_pages_ratelimited_flags(mapping,
+ bdp_flags);
+ if (unlikely(status))
+ break;
+
if (bytes > length)
bytes = length;
@@ -760,6 +788,10 @@ again:
* Otherwise there's a nasty deadlock on copying from the
* same page as we're writing to, without it being marked
* up-to-date.
+ *
+ * For async buffered writes the assumption is that the user
+ * page has already been faulted in. This can be optimized by
+ * faulting the user page.
*/
if (unlikely(fault_in_iov_iter_readable(i, bytes) == bytes)) {
status = -EFAULT;
@@ -771,7 +803,7 @@ again:
break;
page = folio_file_page(folio, pos >> PAGE_SHIFT);
- if (mapping_writably_mapped(iter->inode->i_mapping))
+ if (mapping_writably_mapped(mapping))
flush_dcache_page(page);
copied = copy_page_from_iter_atomic(page, offset, bytes, i);
@@ -796,10 +828,12 @@ again:
pos += status;
written += status;
length -= status;
-
- balance_dirty_pages_ratelimited(iter->inode->i_mapping);
} while (iov_iter_count(i) && length);
+ if (status == -EAGAIN) {
+ iov_iter_revert(i, written);
+ return -EAGAIN;
+ }
return written ? written : status;
}
@@ -815,6 +849,9 @@ iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i,
};
int ret;
+ if (iocb->ki_flags & IOCB_NOWAIT)
+ iter.flags |= IOMAP_NOWAIT;
+
while ((ret = iomap_iter(&iter, ops)) > 0)
iter.processed = iomap_write_iter(&iter, i);
if (iter.pos == iocb->ki_pos)
@@ -1329,7 +1366,7 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc,
struct writeback_control *wbc, struct inode *inode,
struct folio *folio, u64 end_pos)
{
- struct iomap_page *iop = iomap_page_create(inode, folio);
+ struct iomap_page *iop = iomap_page_create(inode, folio, 0);
struct iomap_ioend *ioend, *next;
unsigned len = i_blocksize(inode);
unsigned nblocks = i_blocks_per_folio(inode, folio);
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 370c3241618a..18a3d9357dce 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -52,7 +52,7 @@ struct iomap_dio {
};
static struct bio *iomap_dio_alloc_bio(const struct iomap_iter *iter,
- struct iomap_dio *dio, unsigned short nr_vecs, unsigned int opf)
+ struct iomap_dio *dio, unsigned short nr_vecs, blk_opf_t opf)
{
if (dio->dops && dio->dops->bio_set)
return bio_alloc_bioset(iter->iomap.bdev, nr_vecs, opf,
@@ -212,10 +212,10 @@ static void iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio,
* mapping, and whether or not we want FUA. Note that we can end up
* clearing the WRITE_FUA flag in the dio request.
*/
-static inline unsigned int iomap_dio_bio_opflags(struct iomap_dio *dio,
+static inline blk_opf_t iomap_dio_bio_opflags(struct iomap_dio *dio,
const struct iomap *iomap, bool use_fua)
{
- unsigned int opflags = REQ_SYNC | REQ_IDLE;
+ blk_opf_t opflags = REQ_SYNC | REQ_IDLE;
if (!(dio->flags & IOMAP_DIO_WRITE)) {
WARN_ON_ONCE(iomap->flags & IOMAP_F_ZONE_APPEND);
@@ -242,10 +242,9 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
struct inode *inode = iter->inode;
unsigned int blkbits = blksize_bits(bdev_logical_block_size(iomap->bdev));
unsigned int fs_block_size = i_blocksize(inode), pad;
- unsigned int align = iov_iter_alignment(dio->submit.iter);
loff_t length = iomap_length(iter);
loff_t pos = iter->pos;
- unsigned int bio_opf;
+ blk_opf_t bio_opf;
struct bio *bio;
bool need_zeroout = false;
bool use_fua = false;
@@ -253,7 +252,8 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
size_t copied = 0;
size_t orig_count;
- if ((pos | length | align) & ((1 << blkbits) - 1))
+ if ((pos | length) & ((1 << blkbits) - 1) ||
+ !bdev_iter_is_aligned(iomap->bdev, dio->submit.iter))
return -EINVAL;
if (iomap->type == IOMAP_UNWRITTEN) {
diff --git a/fs/isofs/compress.c b/fs/isofs/compress.c
index 95a19f25d61c..b466172eec25 100644
--- a/fs/isofs/compress.c
+++ b/fs/isofs/compress.c
@@ -82,7 +82,7 @@ static loff_t zisofs_uncompress_block(struct inode *inode, loff_t block_start,
return 0;
}
haveblocks = isofs_get_blocks(inode, blocknum, bhs, needblocks);
- ll_rw_block(REQ_OP_READ, 0, haveblocks, bhs);
+ ll_rw_block(REQ_OP_READ, haveblocks, bhs);
curbh = 0;
curpage = 0;
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index eb315e81f1a6..890b5543a1c5 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -155,10 +155,10 @@ static int journal_submit_commit_record(journal_t *journal,
if (journal->j_flags & JBD2_BARRIER &&
!jbd2_has_feature_async_commit(journal))
- ret = submit_bh(REQ_OP_WRITE,
- REQ_SYNC | REQ_PREFLUSH | REQ_FUA, bh);
+ ret = submit_bh(REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH |
+ REQ_FUA, bh);
else
- ret = submit_bh(REQ_OP_WRITE, REQ_SYNC, bh);
+ ret = submit_bh(REQ_OP_WRITE | REQ_SYNC, bh);
*cbh = bh;
return ret;
@@ -763,7 +763,7 @@ start_journal_io:
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
bh->b_end_io = journal_end_buffer_io_sync;
- submit_bh(REQ_OP_WRITE, REQ_SYNC, bh);
+ submit_bh(REQ_OP_WRITE | REQ_SYNC, bh);
}
cond_resched();
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index c0cbeeaec2d1..2a1b9da7c3e3 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1465,7 +1465,8 @@ journal_t *jbd2_journal_init_dev(struct block_device *bdev,
if (!journal)
return NULL;
- bdevname(journal->j_dev, journal->j_devname);
+ snprintf(journal->j_devname, sizeof(journal->j_devname),
+ "%pg", journal->j_dev);
strreplace(journal->j_devname, '/', '!');
jbd2_stats_proc_init(journal);
@@ -1507,7 +1508,8 @@ journal_t *jbd2_journal_init_inode(struct inode *inode)
return NULL;
journal->j_inode = inode;
- bdevname(journal->j_dev, journal->j_devname);
+ snprintf(journal->j_devname, sizeof(journal->j_devname),
+ "%pg", journal->j_dev);
p = strreplace(journal->j_devname, '/', '!');
sprintf(p, "-%lu", journal->j_inode->i_ino);
jbd2_stats_proc_init(journal);
@@ -1602,7 +1604,7 @@ static int journal_reset(journal_t *journal)
* This function expects that the caller will have locked the journal
* buffer head, and will return with it unlocked
*/
-static int jbd2_write_superblock(journal_t *journal, int write_flags)
+static int jbd2_write_superblock(journal_t *journal, blk_opf_t write_flags)
{
struct buffer_head *bh = journal->j_sb_buffer;
journal_superblock_t *sb = journal->j_superblock;
@@ -1636,7 +1638,7 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags)
sb->s_checksum = jbd2_superblock_csum(journal, sb);
get_bh(bh);
bh->b_end_io = end_buffer_write_sync;
- ret = submit_bh(REQ_OP_WRITE, write_flags, bh);
+ ret = submit_bh(REQ_OP_WRITE | write_flags, bh);
wait_on_buffer(bh);
if (buffer_write_io_error(bh)) {
clear_buffer_write_io_error(bh);
@@ -1659,13 +1661,14 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags)
* @journal: The journal to update.
* @tail_tid: TID of the new transaction at the tail of the log
* @tail_block: The first block of the transaction at the tail of the log
- * @write_op: With which operation should we write the journal sb
+ * @write_flags: Flags for the journal sb write operation
*
* Update a journal's superblock information about log tail and write it to
* disk, waiting for the IO to complete.
*/
int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid,
- unsigned long tail_block, int write_op)
+ unsigned long tail_block,
+ blk_opf_t write_flags)
{
journal_superblock_t *sb = journal->j_superblock;
int ret;
@@ -1685,7 +1688,7 @@ int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid,
sb->s_sequence = cpu_to_be32(tail_tid);
sb->s_start = cpu_to_be32(tail_block);
- ret = jbd2_write_superblock(journal, write_op);
+ ret = jbd2_write_superblock(journal, write_flags);
if (ret)
goto out;
@@ -1702,12 +1705,12 @@ out:
/**
* jbd2_mark_journal_empty() - Mark on disk journal as empty.
* @journal: The journal to update.
- * @write_op: With which operation should we write the journal sb
+ * @write_flags: Flags for the journal sb write operation
*
* Update a journal's dynamic superblock fields to show that journal is empty.
* Write updated superblock to disk waiting for IO to complete.
*/
-static void jbd2_mark_journal_empty(journal_t *journal, int write_op)
+static void jbd2_mark_journal_empty(journal_t *journal, blk_opf_t write_flags)
{
journal_superblock_t *sb = journal->j_superblock;
bool had_fast_commit = false;
@@ -1733,7 +1736,7 @@ static void jbd2_mark_journal_empty(journal_t *journal, int write_op)
had_fast_commit = true;
}
- jbd2_write_superblock(journal, write_op);
+ jbd2_write_superblock(journal, write_flags);
if (had_fast_commit)
jbd2_set_feature_fast_commit(journal);
@@ -1898,7 +1901,7 @@ static int journal_get_superblock(journal_t *journal)
J_ASSERT(bh != NULL);
if (!buffer_uptodate(bh)) {
- ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+ ll_rw_block(REQ_OP_READ, 1, &bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
printk(KERN_ERR
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 8ca3527189f8..e699d6ab2c0e 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -100,7 +100,7 @@ static int do_readahead(journal_t *journal, unsigned int start)
if (!buffer_uptodate(bh) && !buffer_locked(bh)) {
bufs[nbufs++] = bh;
if (nbufs == MAXBUF) {
- ll_rw_block(REQ_OP_READ, 0, nbufs, bufs);
+ ll_rw_block(REQ_OP_READ, nbufs, bufs);
journal_brelse_array(bufs, nbufs);
nbufs = 0;
}
@@ -109,7 +109,7 @@ static int do_readahead(journal_t *journal, unsigned int start)
}
if (nbufs)
- ll_rw_block(REQ_OP_READ, 0, nbufs, bufs);
+ ll_rw_block(REQ_OP_READ, nbufs, bufs);
err = 0;
failed:
diff --git a/fs/jfs/file.c b/fs/jfs/file.c
index 1d732fd223d4..332dc9ac47a9 100644
--- a/fs/jfs/file.c
+++ b/fs/jfs/file.c
@@ -95,14 +95,14 @@ int jfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
if (rc)
return rc;
- if (is_quota_modification(inode, iattr)) {
+ if (is_quota_modification(mnt_userns, inode, iattr)) {
rc = dquot_initialize(inode);
if (rc)
return rc;
}
if ((iattr->ia_valid & ATTR_UID && !uid_eq(iattr->ia_uid, inode->i_uid)) ||
(iattr->ia_valid & ATTR_GID && !gid_eq(iattr->ia_gid, inode->i_gid))) {
- rc = dquot_transfer(inode, iattr);
+ rc = dquot_transfer(mnt_userns, inode, iattr);
if (rc)
return rc;
}
diff --git a/fs/ksmbd/vfs.c b/fs/ksmbd/vfs.c
index 05efcdf7a4a7..7c849024999f 100644
--- a/fs/ksmbd/vfs.c
+++ b/fs/ksmbd/vfs.c
@@ -963,7 +963,7 @@ ssize_t ksmbd_vfs_getxattr(struct user_namespace *user_ns,
*/
int ksmbd_vfs_setxattr(struct user_namespace *user_ns,
struct dentry *dentry, const char *attr_name,
- const void *attr_value, size_t attr_size, int flags)
+ void *attr_value, size_t attr_size, int flags)
{
int err;
diff --git a/fs/ksmbd/vfs.h b/fs/ksmbd/vfs.h
index 8c37aaf936ab..70da4c0ba7ad 100644
--- a/fs/ksmbd/vfs.h
+++ b/fs/ksmbd/vfs.h
@@ -109,7 +109,7 @@ ssize_t ksmbd_vfs_casexattr_len(struct user_namespace *user_ns,
int attr_name_len);
int ksmbd_vfs_setxattr(struct user_namespace *user_ns,
struct dentry *dentry, const char *attr_name,
- const void *attr_value, size_t attr_size, int flags);
+ void *attr_value, size_t attr_size, int flags);
int ksmbd_vfs_xattr_stream_name(char *stream_name, char **xattr_stream_name,
size_t *xattr_stream_name_size, int s_type);
int ksmbd_vfs_remove_xattr(struct user_namespace *user_ns,
diff --git a/fs/locks.c b/fs/locks.c
index ca28e0e50e56..c266cfdc3291 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -425,21 +425,9 @@ static inline int flock_translate_cmd(int cmd) {
}
/* Fill in a file_lock structure with an appropriate FLOCK lock. */
-static struct file_lock *
-flock_make_lock(struct file *filp, unsigned int cmd, struct file_lock *fl)
+static void flock_make_lock(struct file *filp, struct file_lock *fl, int type)
{
- int type = flock_translate_cmd(cmd);
-
- if (type < 0)
- return ERR_PTR(type);
-
- if (fl == NULL) {
- fl = locks_alloc_lock();
- if (fl == NULL)
- return ERR_PTR(-ENOMEM);
- } else {
- locks_init_lock(fl);
- }
+ locks_init_lock(fl);
fl->fl_file = filp;
fl->fl_owner = filp;
@@ -447,8 +435,6 @@ flock_make_lock(struct file *filp, unsigned int cmd, struct file_lock *fl)
fl->fl_flags = FL_FLOCK;
fl->fl_type = type;
fl->fl_end = OFFSET_MAX;
-
- return fl;
}
static int assign_type(struct file_lock *fl, long type)
@@ -2097,21 +2083,9 @@ EXPORT_SYMBOL(locks_lock_inode_wait);
*/
SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd)
{
- struct fd f = fdget(fd);
- struct file_lock *lock;
- int can_sleep, unlock;
- int error;
-
- error = -EBADF;
- if (!f.file)
- goto out;
-
- can_sleep = !(cmd & LOCK_NB);
- cmd &= ~LOCK_NB;
- unlock = (cmd == LOCK_UN);
-
- if (!unlock && !(f.file->f_mode & (FMODE_READ|FMODE_WRITE)))
- goto out_putf;
+ 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
@@ -2123,36 +2097,41 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd)
*/
if (cmd & LOCK_MAND) {
pr_warn_once("Attempt to set a LOCK_MAND lock via flock(2). This support has been removed and the request ignored.\n");
- error = 0;
- goto out_putf;
+ return 0;
}
- lock = flock_make_lock(f.file, cmd, NULL);
- if (IS_ERR(lock)) {
- error = PTR_ERR(lock);
+ type = flock_translate_cmd(cmd & ~LOCK_NB);
+ if (type < 0)
+ return type;
+
+ error = -EBADF;
+ f = fdget(fd);
+ if (!f.file)
+ return error;
+
+ if (type != F_UNLCK && !(f.file->f_mode & (FMODE_READ | FMODE_WRITE)))
goto out_putf;
- }
- if (can_sleep)
- lock->fl_flags |= FL_SLEEP;
+ flock_make_lock(f.file, &fl, type);
- error = security_file_lock(f.file, lock->fl_type);
+ error = security_file_lock(f.file, fl.fl_type);
if (error)
- goto out_free;
+ goto out_putf;
+
+ can_sleep = !(cmd & LOCK_NB);
+ if (can_sleep)
+ fl.fl_flags |= FL_SLEEP;
if (f.file->f_op->flock)
error = f.file->f_op->flock(f.file,
- (can_sleep) ? F_SETLKW : F_SETLK,
- lock);
+ (can_sleep) ? F_SETLKW : F_SETLK,
+ &fl);
else
- error = locks_lock_file_wait(f.file, lock);
-
- out_free:
- locks_free_lock(lock);
+ error = locks_lock_file_wait(f.file, &fl);
out_putf:
fdput(f);
- out:
+
return error;
}
@@ -2614,7 +2593,7 @@ locks_remove_flock(struct file *filp, struct file_lock_context *flctx)
if (list_empty(&flctx->flc_flock))
return;
- flock_make_lock(filp, LOCK_UN, &fl);
+ flock_make_lock(filp, &fl, F_UNLCK);
fl.fl_flags |= FL_CLOSE;
if (filp->f_op->flock)
diff --git a/fs/mpage.c b/fs/mpage.c
index 0d25f44f5707..c6d8bf8c22a5 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -145,13 +145,13 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args)
struct block_device *bdev = NULL;
int length;
int fully_mapped = 1;
- int op = REQ_OP_READ;
+ blk_opf_t opf = REQ_OP_READ;
unsigned nblocks;
unsigned relative_block;
gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL);
if (args->is_readahead) {
- op |= REQ_RAHEAD;
+ opf |= REQ_RAHEAD;
gfp |= __GFP_NORETRY | __GFP_NOWARN;
}
@@ -269,7 +269,7 @@ alloc_new:
page))
goto out;
}
- args->bio = bio_alloc(bdev, bio_max_segs(args->nr_pages), op,
+ args->bio = bio_alloc(bdev, bio_max_segs(args->nr_pages), opf,
gfp);
if (args->bio == NULL)
goto confused;
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 79a8b451791f..943aeea1eb16 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -121,7 +121,7 @@ static bool offset_in_map(u64 offset, struct pnfs_block_dev_map *map)
}
static struct bio *
-do_add_page_to_bio(struct bio *bio, int npg, int rw, sector_t isect,
+do_add_page_to_bio(struct bio *bio, int npg, enum req_op op, sector_t isect,
struct page *page, struct pnfs_block_dev_map *map,
struct pnfs_block_extent *be, bio_end_io_t end_io,
struct parallel_io *par, unsigned int offset, int *len)
@@ -131,7 +131,7 @@ do_add_page_to_bio(struct bio *bio, int npg, int rw, sector_t isect,
u64 disk_addr, end;
dprintk("%s: npg %d rw %d isect %llu offset %u len %d\n", __func__,
- npg, rw, (unsigned long long)isect, offset, *len);
+ npg, (__force u32)op, (unsigned long long)isect, offset, *len);
/* translate to device offset */
isect += be->be_v_offset;
@@ -154,7 +154,7 @@ do_add_page_to_bio(struct bio *bio, int npg, int rw, sector_t isect,
retry:
if (!bio) {
- bio = bio_alloc(map->bdev, bio_max_segs(npg), rw, GFP_NOIO);
+ bio = bio_alloc(map->bdev, bio_max_segs(npg), op, GFP_NOIO);
bio->bi_iter.bi_sector = disk_addr >> SECTOR_SHIFT;
bio->bi_end_io = end_io;
bio->bi_private = par;
@@ -291,7 +291,7 @@ bl_read_pagelist(struct nfs_pgio_header *header)
} else {
bio = do_add_page_to_bio(bio,
header->page_array.npages - i,
- READ,
+ REQ_OP_READ,
isect, pages[i], &map, &be,
bl_end_io_read, par,
pg_offset, &pg_len);
@@ -420,9 +420,8 @@ bl_write_pagelist(struct nfs_pgio_header *header, int sync)
pg_len = PAGE_SIZE;
bio = do_add_page_to_bio(bio, header->page_array.npages - i,
- WRITE, isect, pages[i], &map, &be,
- bl_end_io_write, par,
- 0, &pg_len);
+ REQ_OP_WRITE, isect, pages[i], &map,
+ &be, bl_end_io_write, par, 0, &pg_len);
if (IS_ERR(bio)) {
header->pnfs_error = PTR_ERR(bio);
bio = NULL;
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index ca611ac09f7c..e74fda212620 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -70,7 +70,7 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr)
}
int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr,
- sector_t pblocknr, int mode, int mode_flags,
+ sector_t pblocknr, blk_opf_t opf,
struct buffer_head **pbh, sector_t *submit_ptr)
{
struct buffer_head *bh;
@@ -103,13 +103,13 @@ int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr,
}
}
- if (mode_flags & REQ_RAHEAD) {
+ if (opf & REQ_RAHEAD) {
if (pblocknr != *submit_ptr + 1 || !trylock_buffer(bh)) {
err = -EBUSY; /* internal code */
brelse(bh);
goto out_locked;
}
- } else { /* mode == READ */
+ } else { /* opf == REQ_OP_READ */
lock_buffer(bh);
}
if (buffer_uptodate(bh)) {
@@ -122,7 +122,7 @@ int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr,
bh->b_blocknr = pblocknr; /* set block address for read */
bh->b_end_io = end_buffer_read_sync;
get_bh(bh);
- submit_bh(mode, mode_flags, bh);
+ submit_bh(opf, bh);
bh->b_blocknr = blocknr; /* set back to the given block address */
*submit_ptr = pblocknr;
err = 0;
diff --git a/fs/nilfs2/btnode.h b/fs/nilfs2/btnode.h
index bd5544e63a01..4bc5612dff94 100644
--- a/fs/nilfs2/btnode.h
+++ b/fs/nilfs2/btnode.h
@@ -34,8 +34,8 @@ void nilfs_init_btnc_inode(struct inode *btnc_inode);
void nilfs_btnode_cache_clear(struct address_space *);
struct buffer_head *nilfs_btnode_create_block(struct address_space *btnc,
__u64 blocknr);
-int nilfs_btnode_submit_block(struct address_space *, __u64, sector_t, int,
- int, struct buffer_head **, sector_t *);
+int nilfs_btnode_submit_block(struct address_space *, __u64, sector_t,
+ blk_opf_t, struct buffer_head **, sector_t *);
void nilfs_btnode_delete(struct buffer_head *);
int nilfs_btnode_prepare_change_key(struct address_space *,
struct nilfs_btnode_chkey_ctxt *);
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index f544c22fff78..9f4d9432d38a 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -477,7 +477,7 @@ static int __nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr,
sector_t submit_ptr = 0;
int ret;
- ret = nilfs_btnode_submit_block(btnc, ptr, 0, REQ_OP_READ, 0, &bh,
+ ret = nilfs_btnode_submit_block(btnc, ptr, 0, REQ_OP_READ, &bh,
&submit_ptr);
if (ret) {
if (ret != -EEXIST)
@@ -495,8 +495,8 @@ static int __nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr,
ptr2 = nilfs_btree_node_get_ptr(ra->node, i, ra->ncmax);
ret = nilfs_btnode_submit_block(btnc, ptr2, 0,
- REQ_OP_READ, REQ_RAHEAD,
- &ra_bh, &submit_ptr);
+ REQ_OP_READ | REQ_RAHEAD,
+ &ra_bh, &submit_ptr);
if (likely(!ret || ret == -EEXIST))
brelse(ra_bh);
else if (ret != -EBUSY)
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index 04fdd420eae7..b0d22ff24b67 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -92,7 +92,7 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff,
bh->b_blocknr = pbn;
bh->b_end_io = end_buffer_read_sync;
get_bh(bh);
- submit_bh(REQ_OP_READ, 0, bh);
+ submit_bh(REQ_OP_READ, bh);
if (vbn)
bh->b_blocknr = vbn;
out:
@@ -129,9 +129,8 @@ int nilfs_gccache_submit_read_node(struct inode *inode, sector_t pbn,
struct inode *btnc_inode = NILFS_I(inode)->i_assoc_inode;
int ret;
- ret = nilfs_btnode_submit_block(btnc_inode->i_mapping,
- vbn ? : pbn, pbn, REQ_OP_READ, 0,
- out_bh, &pbn);
+ ret = nilfs_btnode_submit_block(btnc_inode->i_mapping, vbn ? : pbn, pbn,
+ REQ_OP_READ, out_bh, &pbn);
if (ret == -EEXIST) /* internal code (cache hit) */
ret = 0;
return ret;
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index d29a0f2b9c16..cbf4fa60eea2 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -111,8 +111,8 @@ static int nilfs_mdt_create_block(struct inode *inode, unsigned long block,
}
static int
-nilfs_mdt_submit_block(struct inode *inode, unsigned long blkoff,
- int mode, int mode_flags, struct buffer_head **out_bh)
+nilfs_mdt_submit_block(struct inode *inode, unsigned long blkoff, blk_opf_t opf,
+ struct buffer_head **out_bh)
{
struct buffer_head *bh;
__u64 blknum = 0;
@@ -126,12 +126,12 @@ nilfs_mdt_submit_block(struct inode *inode, unsigned long blkoff,
if (buffer_uptodate(bh))
goto out;
- if (mode_flags & REQ_RAHEAD) {
+ if (opf & REQ_RAHEAD) {
if (!trylock_buffer(bh)) {
ret = -EBUSY;
goto failed_bh;
}
- } else /* mode == READ */
+ } else /* opf == REQ_OP_READ */
lock_buffer(bh);
if (buffer_uptodate(bh)) {
@@ -148,10 +148,11 @@ nilfs_mdt_submit_block(struct inode *inode, unsigned long blkoff,
bh->b_end_io = end_buffer_read_sync;
get_bh(bh);
- submit_bh(mode, mode_flags, bh);
+ submit_bh(opf, bh);
ret = 0;
- trace_nilfs2_mdt_submit_block(inode, inode->i_ino, blkoff, mode);
+ trace_nilfs2_mdt_submit_block(inode, inode->i_ino, blkoff,
+ opf & REQ_OP_MASK);
out:
get_bh(bh);
*out_bh = bh;
@@ -172,7 +173,7 @@ static int nilfs_mdt_read_block(struct inode *inode, unsigned long block,
int i, nr_ra_blocks = NILFS_MDT_MAX_RA_BLOCKS;
int err;
- err = nilfs_mdt_submit_block(inode, block, REQ_OP_READ, 0, &first_bh);
+ err = nilfs_mdt_submit_block(inode, block, REQ_OP_READ, &first_bh);
if (err == -EEXIST) /* internal code */
goto out;
@@ -182,8 +183,8 @@ static int nilfs_mdt_read_block(struct inode *inode, unsigned long block,
if (readahead) {
blkoff = block + 1;
for (i = 0; i < nr_ra_blocks; i++, blkoff++) {
- err = nilfs_mdt_submit_block(inode, blkoff, REQ_OP_READ,
- REQ_RAHEAD, &bh);
+ err = nilfs_mdt_submit_block(inode, blkoff,
+ REQ_OP_READ | REQ_RAHEAD, &bh);
if (likely(!err || err == -EEXIST))
brelse(bh);
else if (err != -EBUSY)
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 4f897e109547..cd7d09a569ff 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -295,12 +295,13 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group,
const void *data, int data_type,
struct inode *dir)
{
- __u32 marks_mask = 0, marks_ignored_mask = 0;
+ __u32 marks_mask = 0, marks_ignore_mask = 0;
__u32 test_mask, user_mask = FANOTIFY_OUTGOING_EVENTS |
FANOTIFY_EVENT_FLAGS;
const struct path *path = fsnotify_data_path(data, data_type);
unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
struct fsnotify_mark *mark;
+ bool ondir = event_mask & FAN_ONDIR;
int type;
pr_debug("%s: report_mask=%x mask=%x data=%p data_type=%d\n",
@@ -315,19 +316,21 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group,
return 0;
} else if (!(fid_mode & FAN_REPORT_FID)) {
/* Do we have a directory inode to report? */
- if (!dir && !(event_mask & FS_ISDIR))
+ if (!dir && !ondir)
return 0;
}
fsnotify_foreach_iter_mark_type(iter_info, mark, type) {
- /* Apply ignore mask regardless of mark's ISDIR flag */
- marks_ignored_mask |= mark->ignored_mask;
+ /*
+ * Apply ignore mask depending on event flags in ignore mask.
+ */
+ marks_ignore_mask |=
+ fsnotify_effective_ignore_mask(mark, ondir, type);
/*
- * If the event is on dir and this mark doesn't care about
- * events on dir, don't send it!
+ * Send the event depending on event flags in mark mask.
*/
- if (event_mask & FS_ISDIR && !(mark->mask & FS_ISDIR))
+ if (!fsnotify_mask_applicable(mark->mask, ondir, type))
continue;
marks_mask |= mark->mask;
@@ -336,7 +339,7 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group,
*match_mask |= 1U << type;
}
- test_mask = event_mask & marks_mask & ~marks_ignored_mask;
+ test_mask = event_mask & marks_mask & ~marks_ignore_mask;
/*
* For dirent modification events (create/delete/move) that do not carry
diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h
index 80e0ec95b113..1d9f11255c64 100644
--- a/fs/notify/fanotify/fanotify.h
+++ b/fs/notify/fanotify/fanotify.h
@@ -499,6 +499,8 @@ static inline unsigned int fanotify_mark_user_flags(struct fsnotify_mark *mark)
mflags |= FAN_MARK_IGNORED_SURV_MODIFY;
if (mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF)
mflags |= FAN_MARK_EVICTABLE;
+ if (mark->flags & FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS)
+ mflags |= FAN_MARK_IGNORE;
return mflags;
}
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index b08ce0d821a7..f0e49a406ffa 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -1009,10 +1009,10 @@ static __u32 fanotify_mark_remove_from_mask(struct fsnotify_mark *fsn_mark,
mask &= ~umask;
spin_lock(&fsn_mark->lock);
oldmask = fsnotify_calc_mask(fsn_mark);
- if (!(flags & FAN_MARK_IGNORED_MASK)) {
+ if (!(flags & FANOTIFY_MARK_IGNORE_BITS)) {
fsn_mark->mask &= ~mask;
} else {
- fsn_mark->ignored_mask &= ~mask;
+ fsn_mark->ignore_mask &= ~mask;
}
newmask = fsnotify_calc_mask(fsn_mark);
/*
@@ -1021,7 +1021,7 @@ static __u32 fanotify_mark_remove_from_mask(struct fsnotify_mark *fsn_mark,
* changes to the mask.
* Destroy mark when only umask bits remain.
*/
- *destroy = !((fsn_mark->mask | fsn_mark->ignored_mask) & ~umask);
+ *destroy = !((fsn_mark->mask | fsn_mark->ignore_mask) & ~umask);
spin_unlock(&fsn_mark->lock);
return oldmask & ~newmask;
@@ -1085,15 +1085,24 @@ static bool fanotify_mark_update_flags(struct fsnotify_mark *fsn_mark,
unsigned int fan_flags)
{
bool want_iref = !(fan_flags & FAN_MARK_EVICTABLE);
+ unsigned int ignore = fan_flags & FANOTIFY_MARK_IGNORE_BITS;
bool recalc = false;
/*
+ * When using FAN_MARK_IGNORE for the first time, mark starts using
+ * independent event flags in ignore mask. After that, trying to
+ * update the ignore mask with the old FAN_MARK_IGNORED_MASK API
+ * will result in EEXIST error.
+ */
+ if (ignore == FAN_MARK_IGNORE)
+ fsn_mark->flags |= FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS;
+
+ /*
* Setting FAN_MARK_IGNORED_SURV_MODIFY for the first time may lead to
* the removal of the FS_MODIFY bit in calculated mask if it was set
- * because of an ignored mask that is now going to survive FS_MODIFY.
+ * because of an ignore mask that is now going to survive FS_MODIFY.
*/
- if ((fan_flags & FAN_MARK_IGNORED_MASK) &&
- (fan_flags & FAN_MARK_IGNORED_SURV_MODIFY) &&
+ if (ignore && (fan_flags & FAN_MARK_IGNORED_SURV_MODIFY) &&
!(fsn_mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)) {
fsn_mark->flags |= FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY;
if (!(fsn_mark->mask & FS_MODIFY))
@@ -1120,10 +1129,10 @@ static bool fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark,
bool recalc;
spin_lock(&fsn_mark->lock);
- if (!(fan_flags & FAN_MARK_IGNORED_MASK))
+ if (!(fan_flags & FANOTIFY_MARK_IGNORE_BITS))
fsn_mark->mask |= mask;
else
- fsn_mark->ignored_mask |= mask;
+ fsn_mark->ignore_mask |= mask;
recalc = fsnotify_calc_mask(fsn_mark) &
~fsnotify_conn_mask(fsn_mark->connector);
@@ -1187,6 +1196,37 @@ static int fanotify_group_init_error_pool(struct fsnotify_group *group)
sizeof(struct fanotify_error_event));
}
+static int fanotify_may_update_existing_mark(struct fsnotify_mark *fsn_mark,
+ unsigned int fan_flags)
+{
+ /*
+ * Non evictable mark cannot be downgraded to evictable mark.
+ */
+ if (fan_flags & FAN_MARK_EVICTABLE &&
+ !(fsn_mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF))
+ return -EEXIST;
+
+ /*
+ * New ignore mask semantics cannot be downgraded to old semantics.
+ */
+ if (fan_flags & FAN_MARK_IGNORED_MASK &&
+ fsn_mark->flags & FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS)
+ return -EEXIST;
+
+ /*
+ * An ignore mask that survives modify could never be downgraded to not
+ * survive modify. With new FAN_MARK_IGNORE semantics we make that rule
+ * explicit and return an error when trying to update the ignore mask
+ * without the original FAN_MARK_IGNORED_SURV_MODIFY value.
+ */
+ if (fan_flags & FAN_MARK_IGNORE &&
+ !(fan_flags & FAN_MARK_IGNORED_SURV_MODIFY) &&
+ fsn_mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)
+ return -EEXIST;
+
+ return 0;
+}
+
static int fanotify_add_mark(struct fsnotify_group *group,
fsnotify_connp_t *connp, unsigned int obj_type,
__u32 mask, unsigned int fan_flags,
@@ -1208,19 +1248,18 @@ static int fanotify_add_mark(struct fsnotify_group *group,
}
/*
- * Non evictable mark cannot be downgraded to evictable mark.
+ * Check if requested mark flags conflict with an existing mark flags.
*/
- if (fan_flags & FAN_MARK_EVICTABLE &&
- !(fsn_mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF)) {
- ret = -EEXIST;
+ ret = fanotify_may_update_existing_mark(fsn_mark, fan_flags);
+ if (ret)
goto out;
- }
/*
* Error events are pre-allocated per group, only if strictly
* needed (i.e. FAN_FS_ERROR was requested).
*/
- if (!(fan_flags & FAN_MARK_IGNORED_MASK) && (mask & FAN_FS_ERROR)) {
+ if (!(fan_flags & FANOTIFY_MARK_IGNORE_BITS) &&
+ (mask & FAN_FS_ERROR)) {
ret = fanotify_group_init_error_pool(group);
if (ret)
goto out;
@@ -1261,10 +1300,10 @@ static int fanotify_add_inode_mark(struct fsnotify_group *group,
/*
* If some other task has this inode open for write we should not add
- * an ignored mark, unless that ignored mark is supposed to survive
+ * an ignore mask, unless that ignore mask is supposed to survive
* modification changes anyway.
*/
- if ((flags & FAN_MARK_IGNORED_MASK) &&
+ if ((flags & FANOTIFY_MARK_IGNORE_BITS) &&
!(flags & FAN_MARK_IGNORED_SURV_MODIFY) &&
inode_is_open_for_write(inode))
return 0;
@@ -1520,7 +1559,8 @@ static int fanotify_events_supported(struct fsnotify_group *group,
unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS;
/* Strict validation of events in non-dir inode mask with v5.17+ APIs */
bool strict_dir_events = FAN_GROUP_FLAG(group, FAN_REPORT_TARGET_FID) ||
- (mask & FAN_RENAME);
+ (mask & FAN_RENAME) ||
+ (flags & FAN_MARK_IGNORE);
/*
* Some filesystems such as 'proc' acquire unusual locks when opening
@@ -1557,7 +1597,8 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
__kernel_fsid_t __fsid, *fsid = NULL;
u32 valid_mask = FANOTIFY_EVENTS | FANOTIFY_EVENT_FLAGS;
unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS;
- bool ignored = flags & FAN_MARK_IGNORED_MASK;
+ unsigned int mark_cmd = flags & FANOTIFY_MARK_CMD_BITS;
+ unsigned int ignore = flags & FANOTIFY_MARK_IGNORE_BITS;
unsigned int obj_type, fid_mode;
u32 umask = 0;
int ret;
@@ -1586,7 +1627,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
return -EINVAL;
}
- switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE | FAN_MARK_FLUSH)) {
+ switch (mark_cmd) {
case FAN_MARK_ADD:
case FAN_MARK_REMOVE:
if (!mask)
@@ -1606,9 +1647,19 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
if (mask & ~valid_mask)
return -EINVAL;
- /* Event flags (ONDIR, ON_CHILD) are meaningless in ignored mask */
- if (ignored)
+
+ /* We don't allow FAN_MARK_IGNORE & FAN_MARK_IGNORED_MASK together */
+ if (ignore == (FAN_MARK_IGNORE | FAN_MARK_IGNORED_MASK))
+ return -EINVAL;
+
+ /*
+ * Event flags (FAN_ONDIR, FAN_EVENT_ON_CHILD) have no effect with
+ * FAN_MARK_IGNORED_MASK.
+ */
+ if (ignore == FAN_MARK_IGNORED_MASK) {
mask &= ~FANOTIFY_EVENT_FLAGS;
+ umask = FANOTIFY_EVENT_FLAGS;
+ }
f = fdget(fanotify_fd);
if (unlikely(!f.file))
@@ -1672,7 +1723,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
if (mask & FAN_RENAME && !(fid_mode & FAN_REPORT_NAME))
goto fput_and_out;
- if (flags & FAN_MARK_FLUSH) {
+ if (mark_cmd == FAN_MARK_FLUSH) {
ret = 0;
if (mark_type == FAN_MARK_MOUNT)
fsnotify_clear_vfsmount_marks_by_group(group);
@@ -1688,7 +1739,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
if (ret)
goto fput_and_out;
- if (flags & FAN_MARK_ADD) {
+ if (mark_cmd == FAN_MARK_ADD) {
ret = fanotify_events_supported(group, &path, mask, flags);
if (ret)
goto path_put_and_out;
@@ -1712,6 +1763,13 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
else
mnt = path.mnt;
+ ret = mnt ? -EINVAL : -EISDIR;
+ /* FAN_MARK_IGNORE requires SURV_MODIFY for sb/mount/dir marks */
+ if (mark_cmd == FAN_MARK_ADD && ignore == FAN_MARK_IGNORE &&
+ (mnt || S_ISDIR(inode->i_mode)) &&
+ !(flags & FAN_MARK_IGNORED_SURV_MODIFY))
+ goto path_put_and_out;
+
/* Mask out FAN_EVENT_ON_CHILD flag for sb/mount/non-dir marks */
if (mnt || !S_ISDIR(inode->i_mode)) {
mask &= ~FAN_EVENT_ON_CHILD;
@@ -1721,12 +1779,12 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
* events with parent/name info for non-directory.
*/
if ((fid_mode & FAN_REPORT_DIR_FID) &&
- (flags & FAN_MARK_ADD) && !ignored)
+ (flags & FAN_MARK_ADD) && !ignore)
mask |= FAN_EVENT_ON_CHILD;
}
/* create/update an inode mark */
- switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE)) {
+ switch (mark_cmd) {
case FAN_MARK_ADD:
if (mark_type == FAN_MARK_MOUNT)
ret = fanotify_add_vfsmount_mark(group, mnt, mask,
@@ -1804,7 +1862,7 @@ static int __init fanotify_user_setup(void)
BUILD_BUG_ON(FANOTIFY_INIT_FLAGS & FANOTIFY_INTERNAL_GROUP_FLAGS);
BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 12);
- BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 10);
+ BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 11);
fanotify_mark_cache = KMEM_CACHE(fsnotify_mark,
SLAB_PANIC|SLAB_ACCOUNT);
diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c
index 59fb40abe33d..55081ae3a6ec 100644
--- a/fs/notify/fdinfo.c
+++ b/fs/notify/fdinfo.c
@@ -113,7 +113,7 @@ static void fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
return;
seq_printf(m, "fanotify ino:%lx sdev:%x mflags:%x mask:%x ignored_mask:%x ",
inode->i_ino, inode->i_sb->s_dev,
- mflags, mark->mask, mark->ignored_mask);
+ mflags, mark->mask, mark->ignore_mask);
show_mark_fhandle(m, inode);
seq_putc(m, '\n');
iput(inode);
@@ -121,12 +121,12 @@ static void fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
struct mount *mnt = fsnotify_conn_mount(mark->connector);
seq_printf(m, "fanotify mnt_id:%x mflags:%x mask:%x ignored_mask:%x\n",
- mnt->mnt_id, mflags, mark->mask, mark->ignored_mask);
+ mnt->mnt_id, mflags, mark->mask, mark->ignore_mask);
} else if (mark->connector->type == FSNOTIFY_OBJ_TYPE_SB) {
struct super_block *sb = fsnotify_conn_sb(mark->connector);
seq_printf(m, "fanotify sdev:%x mflags:%x mask:%x ignored_mask:%x\n",
- sb->s_dev, mflags, mark->mask, mark->ignored_mask);
+ sb->s_dev, mflags, mark->mask, mark->ignore_mask);
}
}
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 0b3e74935cb4..7974e91ffe13 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -100,7 +100,7 @@ void fsnotify_sb_delete(struct super_block *sb)
* Given an inode, first check if we care what happens to our children. Inotify
* and dnotify both tell their parents about events. If we care about any event
* on a child we run all of our children and set a dentry flag saying that the
- * parent cares. Thus when an event happens on a child it can quickly tell if
+ * parent cares. Thus when an event happens on a child it can quickly tell
* if there is a need to find a parent and send the event to the parent.
*/
void __fsnotify_update_child_dentry_flags(struct inode *inode)
@@ -324,7 +324,8 @@ static int send_to_group(__u32 mask, const void *data, int data_type,
struct fsnotify_group *group = NULL;
__u32 test_mask = (mask & ALL_FSNOTIFY_EVENTS);
__u32 marks_mask = 0;
- __u32 marks_ignored_mask = 0;
+ __u32 marks_ignore_mask = 0;
+ bool is_dir = mask & FS_ISDIR;
struct fsnotify_mark *mark;
int type;
@@ -336,7 +337,7 @@ static int send_to_group(__u32 mask, const void *data, int data_type,
fsnotify_foreach_iter_mark_type(iter_info, mark, type) {
if (!(mark->flags &
FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY))
- mark->ignored_mask = 0;
+ mark->ignore_mask = 0;
}
}
@@ -344,14 +345,15 @@ static int send_to_group(__u32 mask, const void *data, int data_type,
fsnotify_foreach_iter_mark_type(iter_info, mark, type) {
group = mark->group;
marks_mask |= mark->mask;
- marks_ignored_mask |= mark->ignored_mask;
+ marks_ignore_mask |=
+ fsnotify_effective_ignore_mask(mark, is_dir, type);
}
- pr_debug("%s: group=%p mask=%x marks_mask=%x marks_ignored_mask=%x data=%p data_type=%d dir=%p cookie=%d\n",
- __func__, group, mask, marks_mask, marks_ignored_mask,
+ pr_debug("%s: group=%p mask=%x marks_mask=%x marks_ignore_mask=%x data=%p data_type=%d dir=%p cookie=%d\n",
+ __func__, group, mask, marks_mask, marks_ignore_mask,
data, data_type, dir, cookie);
- if (!(test_mask & marks_mask & ~marks_ignored_mask))
+ if (!(test_mask & marks_mask & ~marks_ignore_mask))
return 0;
if (group->ops->handle_event) {
@@ -423,7 +425,8 @@ static bool fsnotify_iter_select_report_types(
* But is *this mark* watching children?
*/
if (type == FSNOTIFY_ITER_TYPE_PARENT &&
- !(mark->mask & FS_EVENT_ON_CHILD))
+ !(mark->mask & FS_EVENT_ON_CHILD) &&
+ !(fsnotify_ignore_mask(mark) & FS_EVENT_ON_CHILD))
continue;
fsnotify_iter_set_report_type(iter_info, type);
@@ -532,8 +535,8 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
/*
- * If this is a modify event we may need to clear some ignored masks.
- * In that case, the object with ignored masks will have the FS_MODIFY
+ * If this is a modify event we may need to clear some ignore masks.
+ * In that case, the object with ignore masks will have the FS_MODIFY
* event in its mask.
* Otherwise, return if none of the marks care about this type of event.
*/
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index ed42a189faa2..1c4bfdab008d 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -136,7 +136,7 @@ static inline u32 inotify_mask_to_arg(__u32 mask)
IN_Q_OVERFLOW);
}
-/* intofiy userspace file descriptor functions */
+/* inotify userspace file descriptor functions */
static __poll_t inotify_poll(struct file *file, poll_table *wait)
{
struct fsnotify_group *group = file->private_data;
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index 9e3964ea2ea0..b5765fdb3a47 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -342,7 +342,7 @@ handle_zblock:
for (i = 0; i < nr; i++) {
tbh = arr[i];
if (likely(!buffer_uptodate(tbh)))
- submit_bh(REQ_OP_READ, 0, tbh);
+ submit_bh(REQ_OP_READ, tbh);
else
ntfs_end_buffer_async_read(tbh, 1);
}
@@ -859,7 +859,7 @@ lock_retry_remap:
do {
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
- submit_bh(REQ_OP_WRITE, 0, bh);
+ submit_bh(REQ_OP_WRITE, bh);
need_end_writeback = false;
}
bh = next;
@@ -1187,7 +1187,7 @@ lock_retry_remap:
BUG_ON(!buffer_mapped(tbh));
get_bh(tbh);
tbh->b_end_io = end_buffer_write_sync;
- submit_bh(REQ_OP_WRITE, 0, tbh);
+ submit_bh(REQ_OP_WRITE, tbh);
}
/* Synchronize the mft mirror now if not @sync. */
if (is_mft && !sync)
diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c
index 4de597a83b88..52615e6090e1 100644
--- a/fs/ntfs/attrib.c
+++ b/fs/ntfs/attrib.c
@@ -592,8 +592,12 @@ static int ntfs_attr_find(const ATTR_TYPE type, const ntfschar *name,
a = (ATTR_RECORD*)((u8*)ctx->attr +
le32_to_cpu(ctx->attr->length));
for (;; a = (ATTR_RECORD*)((u8*)a + le32_to_cpu(a->length))) {
- if ((u8*)a < (u8*)ctx->mrec || (u8*)a > (u8*)ctx->mrec +
- le32_to_cpu(ctx->mrec->bytes_allocated))
+ u8 *mrec_end = (u8 *)ctx->mrec +
+ le32_to_cpu(ctx->mrec->bytes_allocated);
+ u8 *name_end = (u8 *)a + le16_to_cpu(a->name_offset) +
+ a->name_length * sizeof(ntfschar);
+ if ((u8*)a < (u8*)ctx->mrec || (u8*)a > mrec_end ||
+ name_end > mrec_end)
break;
ctx->attr = a;
if (unlikely(le32_to_cpu(a->type) > le32_to_cpu(type) ||
diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c
index a60f543e7557..587e9b187873 100644
--- a/fs/ntfs/compress.c
+++ b/fs/ntfs/compress.c
@@ -658,7 +658,7 @@ lock_retry_remap:
}
get_bh(tbh);
tbh->b_end_io = end_buffer_read_sync;
- submit_bh(REQ_OP_READ, 0, tbh);
+ submit_bh(REQ_OP_READ, tbh);
}
/* Wait for io completion on all buffer heads. */
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index a8abe2296514..46ed69b86c33 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -537,7 +537,7 @@ static inline int ntfs_submit_bh_for_read(struct buffer_head *bh)
lock_buffer(bh);
get_bh(bh);
bh->b_end_io = end_buffer_read_sync;
- return submit_bh(REQ_OP_READ, 0, bh);
+ return submit_bh(REQ_OP_READ, bh);
}
/**
diff --git a/fs/ntfs/logfile.c b/fs/ntfs/logfile.c
index bc1bf217b38e..6ce60ffc6ac0 100644
--- a/fs/ntfs/logfile.c
+++ b/fs/ntfs/logfile.c
@@ -807,7 +807,7 @@ map_vcn:
* completed ignore errors afterwards as we can assume
* that if one buffer worked all of them will work.
*/
- submit_bh(REQ_OP_WRITE, 0, bh);
+ submit_bh(REQ_OP_WRITE, bh);
if (should_wait) {
should_wait = false;
wait_on_buffer(bh);
diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c
index 0d62cd5bb7f8..f7bf5ce960cc 100644
--- a/fs/ntfs/mft.c
+++ b/fs/ntfs/mft.c
@@ -583,7 +583,7 @@ int ntfs_sync_mft_mirror(ntfs_volume *vol, const unsigned long mft_no,
clear_buffer_dirty(tbh);
get_bh(tbh);
tbh->b_end_io = end_buffer_write_sync;
- submit_bh(REQ_OP_WRITE, 0, tbh);
+ submit_bh(REQ_OP_WRITE, tbh);
}
/* Wait on i/o completion of buffers. */
for (i_bhs = 0; i_bhs < nr_bhs; i_bhs++) {
@@ -780,7 +780,7 @@ int write_mft_record_nolock(ntfs_inode *ni, MFT_RECORD *m, int sync)
clear_buffer_dirty(tbh);
get_bh(tbh);
tbh->b_end_io = end_buffer_write_sync;
- submit_bh(REQ_OP_WRITE, 0, tbh);
+ submit_bh(REQ_OP_WRITE, tbh);
}
/* Synchronize the mft mirror now if not @sync. */
if (!sync && ni->mft_no < vol->mftmirr_size)
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index 8e9d2b35175f..4a21745711fe 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -242,7 +242,7 @@ static int ntfs_zero_range(struct inode *inode, u64 vbo, u64 vbo_to)
lock_buffer(bh);
bh->b_end_io = end_buffer_read_sync;
get_bh(bh);
- submit_bh(REQ_OP_READ, 0, bh);
+ submit_bh(REQ_OP_READ, bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c
index 3de5700a9b83..1835e35199c2 100644
--- a/fs/ntfs3/fsntfs.c
+++ b/fs/ntfs3/fsntfs.c
@@ -1448,7 +1448,7 @@ int ntfs_write_bh(struct ntfs_sb_info *sbi, struct NTFS_RECORD_HEADER *rhdr,
*/
int ntfs_bio_pages(struct ntfs_sb_info *sbi, const struct runs_tree *run,
struct page **pages, u32 nr_pages, u64 vbo, u32 bytes,
- u32 op)
+ enum req_op op)
{
int err = 0;
struct bio *new, *bio = NULL;
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index be4ebdd8048b..d100a063def2 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -629,7 +629,7 @@ static noinline int ntfs_get_block_vbo(struct inode *inode, u64 vbo,
bh->b_size = block_size;
off = vbo & (PAGE_SIZE - 1);
set_bh_page(bh, page, off);
- ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+ ll_rw_block(REQ_OP_READ, 1, &bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
err = -EIO;
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index 8de129a6419b..3a8abf13143e 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -617,7 +617,7 @@ int ntfs_write_bh(struct ntfs_sb_info *sbi, struct NTFS_RECORD_HEADER *rhdr,
struct ntfs_buffers *nb, int sync);
int ntfs_bio_pages(struct ntfs_sb_info *sbi, const struct runs_tree *run,
struct page **pages, u32 nr_pages, u64 vbo, u32 bytes,
- u32 op);
+ enum req_op op);
int ntfs_bio_fill_1(struct ntfs_sb_info *sbi, const struct runs_tree *run);
int ntfs_vbo_to_lbo(struct ntfs_sb_info *sbi, const struct runs_tree *run,
u64 vbo, u64 *lbo, u64 *bytes);
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 35d40a67204c..304ed2be1b83 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -638,7 +638,7 @@ int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno,
!buffer_new(bh) &&
ocfs2_should_read_blk(inode, page, block_start) &&
(block_start < from || block_end > to)) {
- ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+ ll_rw_block(REQ_OP_READ, 1, &bh);
*wait_bh++=bh;
}
diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c
index e7758778abef..196638a22b48 100644
--- a/fs/ocfs2/buffer_head_io.c
+++ b/fs/ocfs2/buffer_head_io.c
@@ -64,7 +64,7 @@ int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh,
get_bh(bh); /* for end_buffer_write_sync() */
bh->b_end_io = end_buffer_write_sync;
- submit_bh(REQ_OP_WRITE, 0, bh);
+ submit_bh(REQ_OP_WRITE, bh);
wait_on_buffer(bh);
@@ -147,7 +147,7 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
get_bh(bh); /* for end_buffer_read_sync() */
bh->b_end_io = end_buffer_read_sync;
- submit_bh(REQ_OP_READ, 0, bh);
+ submit_bh(REQ_OP_READ, bh);
}
read_failure:
@@ -328,7 +328,7 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
if (validate)
set_buffer_needs_validate(bh);
bh->b_end_io = end_buffer_read_sync;
- submit_bh(REQ_OP_READ, 0, bh);
+ submit_bh(REQ_OP_READ, bh);
continue;
}
}
@@ -449,7 +449,7 @@ int ocfs2_write_super_or_backup(struct ocfs2_super *osb,
get_bh(bh); /* for end_buffer_write_sync() */
bh->b_end_io = end_buffer_write_sync;
ocfs2_compute_meta_ecc(osb->sb, bh->b_data, &di->i_check);
- submit_bh(REQ_OP_WRITE, 0, bh);
+ submit_bh(REQ_OP_WRITE, bh);
wait_on_buffer(bh);
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index ea0e70c0fce0..b13d344d40b6 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -235,8 +235,6 @@ struct o2hb_region {
* (hr_steady_iterations == 0) within hr_unsteady_iterations */
atomic_t hr_unsteady_iterations;
- char hr_dev_name[BDEVNAME_SIZE];
-
unsigned int hr_timeout_ms;
/* randomized as the region goes up and down so that a node
@@ -287,8 +285,8 @@ static void o2hb_write_timeout(struct work_struct *work)
container_of(work, struct o2hb_region,
hr_write_timeout_work.work);
- mlog(ML_ERROR, "Heartbeat write timeout to device %s after %u "
- "milliseconds\n", reg->hr_dev_name,
+ mlog(ML_ERROR, "Heartbeat write timeout to device %pg after %u "
+ "milliseconds\n", reg->hr_bdev,
jiffies_to_msecs(jiffies - reg->hr_last_timeout_start));
if (o2hb_global_heartbeat_active()) {
@@ -383,9 +381,9 @@ static void o2hb_nego_timeout(struct work_struct *work)
if (master_node == o2nm_this_node()) {
if (!test_bit(master_node, reg->hr_nego_node_bitmap)) {
- printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%s).\n",
+ printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%pg).\n",
o2nm_this_node(), O2HB_NEGO_TIMEOUT_MS/1000,
- config_item_name(&reg->hr_item), reg->hr_dev_name);
+ config_item_name(&reg->hr_item), reg->hr_bdev);
set_bit(master_node, reg->hr_nego_node_bitmap);
}
if (memcmp(reg->hr_nego_node_bitmap, live_node_bitmap,
@@ -399,8 +397,8 @@ static void o2hb_nego_timeout(struct work_struct *work)
return;
}
- printk(KERN_NOTICE "o2hb: all nodes hb write hung, maybe region %s (%s) is down.\n",
- config_item_name(&reg->hr_item), reg->hr_dev_name);
+ printk(KERN_NOTICE "o2hb: all nodes hb write hung, maybe region %s (%pg) is down.\n",
+ config_item_name(&reg->hr_item), reg->hr_bdev);
/* approve negotiate timeout request. */
o2hb_arm_timeout(reg);
@@ -419,9 +417,9 @@ static void o2hb_nego_timeout(struct work_struct *work)
}
} else {
/* negotiate timeout with master node. */
- printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%s), negotiate timeout with node %d.\n",
+ printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%pg), negotiate timeout with node %d.\n",
o2nm_this_node(), O2HB_NEGO_TIMEOUT_MS/1000, config_item_name(&reg->hr_item),
- reg->hr_dev_name, master_node);
+ reg->hr_bdev, master_node);
ret = o2hb_send_nego_msg(reg->hr_key, O2HB_NEGO_TIMEOUT_MSG,
master_node);
if (ret)
@@ -437,8 +435,8 @@ static int o2hb_nego_timeout_handler(struct o2net_msg *msg, u32 len, void *data,
struct o2hb_nego_msg *nego_msg;
nego_msg = (struct o2hb_nego_msg *)msg->buf;
- printk(KERN_NOTICE "o2hb: receive negotiate timeout message from node %d on region %s (%s).\n",
- nego_msg->node_num, config_item_name(&reg->hr_item), reg->hr_dev_name);
+ printk(KERN_NOTICE "o2hb: receive negotiate timeout message from node %d on region %s (%pg).\n",
+ nego_msg->node_num, config_item_name(&reg->hr_item), reg->hr_bdev);
if (nego_msg->node_num < O2NM_MAX_NODES)
set_bit(nego_msg->node_num, reg->hr_nego_node_bitmap);
else
@@ -452,8 +450,8 @@ static int o2hb_nego_approve_handler(struct o2net_msg *msg, u32 len, void *data,
{
struct o2hb_region *reg = data;
- printk(KERN_NOTICE "o2hb: negotiate timeout approved by master node on region %s (%s).\n",
- config_item_name(&reg->hr_item), reg->hr_dev_name);
+ printk(KERN_NOTICE "o2hb: negotiate timeout approved by master node on region %s (%pg).\n",
+ config_item_name(&reg->hr_item), reg->hr_bdev);
o2hb_arm_timeout(reg);
return 0;
}
@@ -503,8 +501,7 @@ static void o2hb_bio_end_io(struct bio *bio)
static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg,
struct o2hb_bio_wait_ctxt *wc,
unsigned int *current_slot,
- unsigned int max_slots, int op,
- int op_flags)
+ unsigned int max_slots, blk_opf_t opf)
{
int len, current_page;
unsigned int vec_len, vec_start;
@@ -518,7 +515,7 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg,
* GFP_KERNEL that the local node can get fenced. It would be
* nicest if we could pre-allocate these bios and avoid this
* all together. */
- bio = bio_alloc(reg->hr_bdev, 16, op | op_flags, GFP_ATOMIC);
+ bio = bio_alloc(reg->hr_bdev, 16, opf, GFP_ATOMIC);
if (!bio) {
mlog(ML_ERROR, "Could not alloc slots BIO!\n");
bio = ERR_PTR(-ENOMEM);
@@ -566,7 +563,7 @@ static int o2hb_read_slots(struct o2hb_region *reg,
while(current_slot < max_slots) {
bio = o2hb_setup_one_bio(reg, &wc, &current_slot, max_slots,
- REQ_OP_READ, 0);
+ REQ_OP_READ);
if (IS_ERR(bio)) {
status = PTR_ERR(bio);
mlog_errno(status);
@@ -598,8 +595,8 @@ static int o2hb_issue_node_write(struct o2hb_region *reg,
slot = o2nm_this_node();
- bio = o2hb_setup_one_bio(reg, write_wc, &slot, slot+1, REQ_OP_WRITE,
- REQ_SYNC);
+ bio = o2hb_setup_one_bio(reg, write_wc, &slot, slot+1,
+ REQ_OP_WRITE | REQ_SYNC);
if (IS_ERR(bio)) {
status = PTR_ERR(bio);
mlog_errno(status);
@@ -689,8 +686,8 @@ static int o2hb_check_own_slot(struct o2hb_region *reg)
else
errstr = ERRSTR3;
- mlog(ML_ERROR, "%s (%s): expected(%u:0x%llx, 0x%llx), "
- "ondisk(%u:0x%llx, 0x%llx)\n", errstr, reg->hr_dev_name,
+ mlog(ML_ERROR, "%s (%pg): expected(%u:0x%llx, 0x%llx), "
+ "ondisk(%u:0x%llx, 0x%llx)\n", errstr, reg->hr_bdev,
slot->ds_node_num, (unsigned long long)slot->ds_last_generation,
(unsigned long long)slot->ds_last_time, hb_block->hb_node,
(unsigned long long)le64_to_cpu(hb_block->hb_generation),
@@ -863,8 +860,8 @@ static void o2hb_set_quorum_device(struct o2hb_region *reg)
sizeof(o2hb_live_node_bitmap)))
goto unlock;
- printk(KERN_NOTICE "o2hb: Region %s (%s) is now a quorum device\n",
- config_item_name(&reg->hr_item), reg->hr_dev_name);
+ printk(KERN_NOTICE "o2hb: Region %s (%pg) is now a quorum device\n",
+ config_item_name(&reg->hr_item), reg->hr_bdev);
set_bit(reg->hr_region_num, o2hb_quorum_region_bitmap);
@@ -922,8 +919,8 @@ static int o2hb_check_slot(struct o2hb_region *reg,
/* The node is live but pushed out a bad crc. We
* consider it a transient miss but don't populate any
* other values as they may be junk. */
- mlog(ML_ERROR, "Node %d has written a bad crc to %s\n",
- slot->ds_node_num, reg->hr_dev_name);
+ mlog(ML_ERROR, "Node %d has written a bad crc to %pg\n",
+ slot->ds_node_num, reg->hr_bdev);
o2hb_dump_slot(hb_block);
slot->ds_equal_samples++;
@@ -1002,11 +999,11 @@ fire_callbacks:
slot_dead_ms = le32_to_cpu(hb_block->hb_dead_ms);
if (slot_dead_ms && slot_dead_ms != dead_ms) {
/* TODO: Perhaps we can fail the region here. */
- mlog(ML_ERROR, "Node %d on device %s has a dead count "
+ mlog(ML_ERROR, "Node %d on device %pg has a dead count "
"of %u ms, but our count is %u ms.\n"
"Please double check your configuration values "
"for 'O2CB_HEARTBEAT_THRESHOLD'\n",
- slot->ds_node_num, reg->hr_dev_name, slot_dead_ms,
+ slot->ds_node_num, reg->hr_bdev, slot_dead_ms,
dead_ms);
}
goto out;
@@ -1145,8 +1142,8 @@ static int o2hb_do_disk_heartbeat(struct o2hb_region *reg)
/* Do not re-arm the write timeout on I/O error - we
* can't be sure that the new block ever made it to
* disk */
- mlog(ML_ERROR, "Write error %d on device \"%s\"\n",
- write_wc.wc_error, reg->hr_dev_name);
+ mlog(ML_ERROR, "Write error %d on device \"%pg\"\n",
+ write_wc.wc_error, reg->hr_bdev);
ret = write_wc.wc_error;
goto bail;
}
@@ -1170,9 +1167,9 @@ bail:
if (atomic_read(&reg->hr_steady_iterations) != 0) {
if (atomic_dec_and_test(&reg->hr_unsteady_iterations)) {
printk(KERN_NOTICE "o2hb: Unable to stabilize "
- "heartbeat on region %s (%s)\n",
+ "heartbeat on region %s (%pg)\n",
config_item_name(&reg->hr_item),
- reg->hr_dev_name);
+ reg->hr_bdev);
atomic_set(&reg->hr_steady_iterations, 0);
reg->hr_aborted_start = 1;
wake_up(&o2hb_steady_queue);
@@ -1494,7 +1491,7 @@ static void o2hb_region_release(struct config_item *item)
struct page *page;
struct o2hb_region *reg = to_o2hb_region(item);
- mlog(ML_HEARTBEAT, "hb region release (%s)\n", reg->hr_dev_name);
+ mlog(ML_HEARTBEAT, "hb region release (%pg)\n", reg->hr_bdev);
kfree(reg->hr_tmp_block);
@@ -1641,7 +1638,7 @@ static ssize_t o2hb_region_dev_show(struct config_item *item, char *page)
unsigned int ret = 0;
if (to_o2hb_region(item)->hr_bdev)
- ret = sprintf(page, "%s\n", to_o2hb_region(item)->hr_dev_name);
+ ret = sprintf(page, "%pg\n", to_o2hb_region(item)->hr_bdev);
return ret;
}
@@ -1798,8 +1795,6 @@ static ssize_t o2hb_region_dev_store(struct config_item *item,
goto out2;
}
- bdevname(reg->hr_bdev, reg->hr_dev_name);
-
sectsize = bdev_logical_block_size(reg->hr_bdev);
if (sectsize != reg->hr_block_bytes) {
mlog(ML_ERROR,
@@ -1895,8 +1890,8 @@ static ssize_t o2hb_region_dev_store(struct config_item *item,
ret = -EIO;
if (hb_task && o2hb_global_heartbeat_active())
- printk(KERN_NOTICE "o2hb: Heartbeat started on region %s (%s)\n",
- config_item_name(&reg->hr_item), reg->hr_dev_name);
+ printk(KERN_NOTICE "o2hb: Heartbeat started on region %s (%pg)\n",
+ config_item_name(&reg->hr_item), reg->hr_bdev);
out3:
if (ret < 0) {
@@ -2088,10 +2083,10 @@ static void o2hb_heartbeat_group_drop_item(struct config_group *group,
quorum_region = 1;
clear_bit(reg->hr_region_num, o2hb_quorum_region_bitmap);
spin_unlock(&o2hb_live_lock);
- printk(KERN_NOTICE "o2hb: Heartbeat %s on region %s (%s)\n",
+ printk(KERN_NOTICE "o2hb: Heartbeat %s on region %s (%pg)\n",
((atomic_read(&reg->hr_steady_iterations) == 0) ?
"stopped" : "start aborted"), config_item_name(item),
- reg->hr_dev_name);
+ reg->hr_bdev);
}
/*
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 7497cd592258..9c67edd215d5 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1146,7 +1146,7 @@ int ocfs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
if (status)
return status;
- if (is_quota_modification(inode, attr)) {
+ if (is_quota_modification(mnt_userns, inode, attr)) {
status = dquot_initialize(inode);
if (status)
return status;
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 337527571461..740b64238312 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -277,7 +277,6 @@ enum ocfs2_mount_options
OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT = 1 << 15, /* Journal Async Commit */
OCFS2_MOUNT_ERRORS_CONT = 1 << 16, /* Return EIO to the calling process on error */
OCFS2_MOUNT_ERRORS_ROFS = 1 << 17, /* Change filesystem to read-only on error */
- OCFS2_MOUNT_NOCLUSTER = 1 << 18, /* No cluster aware filesystem mount */
};
#define OCFS2_OSB_SOFT_RO 0x0001
@@ -673,8 +672,7 @@ static inline int ocfs2_cluster_o2cb_global_heartbeat(struct ocfs2_super *osb)
static inline int ocfs2_mount_local(struct ocfs2_super *osb)
{
- return ((osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT)
- || (osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER));
+ return (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT);
}
static inline int ocfs2_uses_extended_slot_map(struct ocfs2_super *osb)
diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c
index 0b0ae3ebb0cf..da7718cef735 100644
--- a/fs/ocfs2/slot_map.c
+++ b/fs/ocfs2/slot_map.c
@@ -252,16 +252,14 @@ static int __ocfs2_find_empty_slot(struct ocfs2_slot_info *si,
int i, ret = -ENOSPC;
if ((preferred >= 0) && (preferred < si->si_num_slots)) {
- if (!si->si_slots[preferred].sl_valid ||
- !si->si_slots[preferred].sl_node_num) {
+ if (!si->si_slots[preferred].sl_valid) {
ret = preferred;
goto out;
}
}
for(i = 0; i < si->si_num_slots; i++) {
- if (!si->si_slots[i].sl_valid ||
- !si->si_slots[i].sl_node_num) {
+ if (!si->si_slots[i].sl_valid) {
ret = i;
break;
}
@@ -456,30 +454,24 @@ int ocfs2_find_slot(struct ocfs2_super *osb)
spin_lock(&osb->osb_lock);
ocfs2_update_slot_info(si);
- if (ocfs2_mount_local(osb))
- /* use slot 0 directly in local mode */
- slot = 0;
- else {
- /* search for ourselves first and take the slot if it already
- * exists. Perhaps we need to mark this in a variable for our
- * own journal recovery? Possibly not, though we certainly
- * need to warn to the user */
- slot = __ocfs2_node_num_to_slot(si, osb->node_num);
+ /* search for ourselves first and take the slot if it already
+ * exists. Perhaps we need to mark this in a variable for our
+ * own journal recovery? Possibly not, though we certainly
+ * need to warn to the user */
+ slot = __ocfs2_node_num_to_slot(si, osb->node_num);
+ if (slot < 0) {
+ /* if no slot yet, then just take 1st available
+ * one. */
+ slot = __ocfs2_find_empty_slot(si, osb->preferred_slot);
if (slot < 0) {
- /* if no slot yet, then just take 1st available
- * one. */
- slot = __ocfs2_find_empty_slot(si, osb->preferred_slot);
- if (slot < 0) {
- spin_unlock(&osb->osb_lock);
- mlog(ML_ERROR, "no free slots available!\n");
- status = -EINVAL;
- goto bail;
- }
- } else
- printk(KERN_INFO "ocfs2: Slot %d on device (%s) was "
- "already allocated to this node!\n",
- slot, osb->dev_str);
- }
+ spin_unlock(&osb->osb_lock);
+ mlog(ML_ERROR, "no free slots available!\n");
+ status = -EINVAL;
+ goto bail;
+ }
+ } else
+ printk(KERN_INFO "ocfs2: Slot %d on device (%s) was already "
+ "allocated to this node!\n", slot, osb->dev_str);
ocfs2_set_slot(si, slot, osb->node_num);
osb->slot_num = slot;
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index f7298816d8d9..013a727bd7c8 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -172,7 +172,6 @@ enum {
Opt_dir_resv_level,
Opt_journal_async_commit,
Opt_err_cont,
- Opt_nocluster,
Opt_err,
};
@@ -206,7 +205,6 @@ static const match_table_t tokens = {
{Opt_dir_resv_level, "dir_resv_level=%u"},
{Opt_journal_async_commit, "journal_async_commit"},
{Opt_err_cont, "errors=continue"},
- {Opt_nocluster, "nocluster"},
{Opt_err, NULL}
};
@@ -618,13 +616,6 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data)
goto out;
}
- tmp = OCFS2_MOUNT_NOCLUSTER;
- if ((osb->s_mount_opt & tmp) != (parsed_options.mount_opt & tmp)) {
- ret = -EINVAL;
- mlog(ML_ERROR, "Cannot change nocluster option on remount\n");
- goto out;
- }
-
tmp = OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL |
OCFS2_MOUNT_HB_NONE;
if ((osb->s_mount_opt & tmp) != (parsed_options.mount_opt & tmp)) {
@@ -865,7 +856,6 @@ static int ocfs2_verify_userspace_stack(struct ocfs2_super *osb,
}
if (ocfs2_userspace_stack(osb) &&
- !(osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER) &&
strncmp(osb->osb_cluster_stack, mopt->cluster_stack,
OCFS2_STACK_LABEL_LEN)) {
mlog(ML_ERROR,
@@ -1137,11 +1127,6 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
osb->s_mount_opt & OCFS2_MOUNT_DATA_WRITEBACK ? "writeback" :
"ordered");
- if ((osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER) &&
- !(osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT))
- printk(KERN_NOTICE "ocfs2: The shared device (%s) is mounted "
- "without cluster aware mode.\n", osb->dev_str);
-
atomic_set(&osb->vol_state, VOLUME_MOUNTED);
wake_up(&osb->osb_mount_event);
@@ -1452,9 +1437,6 @@ static int ocfs2_parse_options(struct super_block *sb,
case Opt_journal_async_commit:
mopt->mount_opt |= OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT;
break;
- case Opt_nocluster:
- mopt->mount_opt |= OCFS2_MOUNT_NOCLUSTER;
- break;
default:
mlog(ML_ERROR,
"Unrecognized mount option \"%s\" "
@@ -1566,9 +1548,6 @@ static int ocfs2_show_options(struct seq_file *s, struct dentry *root)
if (opts & OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT)
seq_printf(s, ",journal_async_commit");
- if (opts & OCFS2_MOUNT_NOCLUSTER)
- seq_printf(s, ",nocluster");
-
return 0;
}
@@ -1785,7 +1764,7 @@ static int ocfs2_get_sector(struct super_block *sb,
if (!buffer_dirty(*bh))
clear_buffer_uptodate(*bh);
unlock_buffer(*bh);
- ll_rw_block(REQ_OP_READ, 0, 1, bh);
+ ll_rw_block(REQ_OP_READ, 1, bh);
wait_on_buffer(*bh);
if (!buffer_uptodate(*bh)) {
mlog_errno(-EIO);
diff --git a/fs/open.c b/fs/open.c
index 1d57fbde2feb..2790aac66e58 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -663,6 +663,42 @@ SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode)
return do_fchmodat(AT_FDCWD, filename, mode);
}
+/**
+ * setattr_vfsuid - check and set ia_fsuid attribute
+ * @kuid: new inode owner
+ *
+ * Check whether @kuid is valid and if so generate and set vfsuid_t in
+ * ia_vfsuid.
+ *
+ * Return: true if @kuid is valid, false if not.
+ */
+static inline bool setattr_vfsuid(struct iattr *attr, kuid_t kuid)
+{
+ if (!uid_valid(kuid))
+ return false;
+ attr->ia_valid |= ATTR_UID;
+ attr->ia_vfsuid = VFSUIDT_INIT(kuid);
+ return true;
+}
+
+/**
+ * setattr_vfsgid - check and set ia_fsgid attribute
+ * @kgid: new inode owner
+ *
+ * Check whether @kgid is valid and if so generate and set vfsgid_t in
+ * ia_vfsgid.
+ *
+ * Return: true if @kgid is valid, false if not.
+ */
+static inline bool setattr_vfsgid(struct iattr *attr, kgid_t kgid)
+{
+ if (!gid_valid(kgid))
+ return false;
+ attr->ia_valid |= ATTR_GID;
+ attr->ia_vfsgid = VFSGIDT_INIT(kgid);
+ return true;
+}
+
int chown_common(const struct path *path, uid_t user, gid_t group)
{
struct user_namespace *mnt_userns, *fs_userns;
@@ -678,28 +714,22 @@ int chown_common(const struct path *path, uid_t user, gid_t group)
mnt_userns = mnt_user_ns(path->mnt);
fs_userns = i_user_ns(inode);
- uid = mapped_kuid_user(mnt_userns, fs_userns, uid);
- gid = mapped_kgid_user(mnt_userns, fs_userns, gid);
retry_deleg:
newattrs.ia_valid = ATTR_CTIME;
- if (user != (uid_t) -1) {
- if (!uid_valid(uid))
- return -EINVAL;
- newattrs.ia_valid |= ATTR_UID;
- newattrs.ia_uid = uid;
- }
- if (group != (gid_t) -1) {
- if (!gid_valid(gid))
- return -EINVAL;
- newattrs.ia_valid |= ATTR_GID;
- newattrs.ia_gid = gid;
- }
+ if ((user != (uid_t)-1) && !setattr_vfsuid(&newattrs, uid))
+ return -EINVAL;
+ if ((group != (gid_t)-1) && !setattr_vfsgid(&newattrs, gid))
+ return -EINVAL;
if (!S_ISDIR(inode->i_mode))
newattrs.ia_valid |=
ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;
inode_lock(inode);
- error = security_path_chown(path, uid, gid);
+ /* Continue to send actual fs values, not the mount values. */
+ error = security_path_chown(
+ path,
+ from_vfsuid(mnt_userns, fs_userns, newattrs.ia_vfsuid),
+ from_vfsgid(mnt_userns, fs_userns, newattrs.ia_vfsgid));
if (!error)
error = notify_change(mnt_userns, path->dentry, &newattrs,
&delegated_inode);
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 714ec569d25b..245e2cb62708 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -331,8 +331,8 @@ int ovl_set_attr(struct ovl_fs *ofs, struct dentry *upperdentry,
if (!err) {
struct iattr attr = {
.ia_valid = ATTR_UID | ATTR_GID,
- .ia_uid = stat->uid,
- .ia_gid = stat->gid,
+ .ia_vfsuid = VFSUIDT_INIT(stat->uid),
+ .ia_vfsgid = VFSGIDT_INIT(stat->gid),
};
err = ovl_do_notify_change(ofs, upperdentry, &attr);
}
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 492eddeb481f..7922b619f6c8 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -454,23 +454,94 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
return res;
}
+/*
+ * Apply the idmapping of the layer to POSIX ACLs. The caller must pass a clone
+ * of the POSIX ACLs retrieved from the lower layer to this function to not
+ * alter the POSIX ACLs for the underlying filesystem.
+ */
+static void ovl_idmap_posix_acl(struct user_namespace *mnt_userns,
+ struct posix_acl *acl)
+{
+ for (unsigned int i = 0; i < acl->a_count; i++) {
+ vfsuid_t vfsuid;
+ vfsgid_t vfsgid;
+
+ struct posix_acl_entry *e = &acl->a_entries[i];
+ switch (e->e_tag) {
+ case ACL_USER:
+ vfsuid = make_vfsuid(mnt_userns, &init_user_ns, e->e_uid);
+ e->e_uid = vfsuid_into_kuid(vfsuid);
+ break;
+ case ACL_GROUP:
+ vfsgid = make_vfsgid(mnt_userns, &init_user_ns, e->e_gid);
+ e->e_gid = vfsgid_into_kgid(vfsgid);
+ break;
+ }
+ }
+}
+
+/*
+ * When the relevant layer is an idmapped mount we need to take the idmapping
+ * of the layer into account and translate any ACL_{GROUP,USER} values
+ * according to the idmapped mount.
+ *
+ * We cannot alter the ACLs returned from the relevant layer as that would
+ * alter the cached values filesystem wide for the lower filesystem. Instead we
+ * can clone the ACLs and then apply the relevant idmapping of the layer.
+ *
+ * This is obviously only relevant when idmapped layers are used.
+ */
struct posix_acl *ovl_get_acl(struct inode *inode, int type, bool rcu)
{
struct inode *realinode = ovl_inode_real(inode);
- const struct cred *old_cred;
- struct posix_acl *acl;
+ struct posix_acl *acl, *clone;
+ struct path realpath;
if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode))
return NULL;
- if (rcu)
- return get_cached_acl_rcu(realinode, type);
+ /* Careful in RCU walk mode */
+ ovl_i_path_real(inode, &realpath);
+ if (!realpath.dentry) {
+ WARN_ON(!rcu);
+ return ERR_PTR(-ECHILD);
+ }
- old_cred = ovl_override_creds(inode->i_sb);
- acl = get_acl(realinode, type);
- revert_creds(old_cred);
+ if (rcu) {
+ acl = get_cached_acl_rcu(realinode, type);
+ } else {
+ const struct cred *old_cred;
+
+ old_cred = ovl_override_creds(inode->i_sb);
+ acl = get_acl(realinode, type);
+ revert_creds(old_cred);
+ }
+ /*
+ * If there are no POSIX ACLs, or we encountered an error,
+ * or the layer isn't idmapped we don't need to do anything.
+ */
+ if (!is_idmapped_mnt(realpath.mnt) || IS_ERR_OR_NULL(acl))
+ return acl;
- return acl;
+ /*
+ * We only get here if the layer is idmapped. So drop out of RCU path
+ * walk so we can clone the ACLs. There's no need to release the ACLs
+ * since get_cached_acl_rcu() doesn't take a reference on the ACLs.
+ */
+ if (rcu)
+ return ERR_PTR(-ECHILD);
+
+ clone = posix_acl_clone(acl, GFP_KERNEL);
+ if (!clone)
+ clone = ERR_PTR(-ENOMEM);
+ else
+ ovl_idmap_posix_acl(mnt_user_ns(realpath.mnt), clone);
+ /*
+ * Since we're not in RCU path walk we always need to release the
+ * original ACLs.
+ */
+ posix_acl_release(acl);
+ return clone;
}
int ovl_update_time(struct inode *inode, struct timespec64 *ts, int flags)
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 4f34b7e02eee..6ec815b84d48 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -139,17 +139,7 @@ static inline int ovl_do_notify_change(struct ovl_fs *ofs,
struct dentry *upperdentry,
struct iattr *attr)
{
- struct user_namespace *upper_mnt_userns = ovl_upper_mnt_userns(ofs);
- struct user_namespace *fs_userns = i_user_ns(d_inode(upperdentry));
-
- if (attr->ia_valid & ATTR_UID)
- attr->ia_uid = mapped_kuid_user(upper_mnt_userns,
- fs_userns, attr->ia_uid);
- if (attr->ia_valid & ATTR_GID)
- attr->ia_gid = mapped_kgid_user(upper_mnt_userns,
- fs_userns, attr->ia_gid);
-
- return notify_change(upper_mnt_userns, upperdentry, attr, NULL);
+ return notify_change(ovl_upper_mnt_userns(ofs), upperdentry, attr, NULL);
}
static inline int ovl_do_rmdir(struct ovl_fs *ofs,
@@ -259,7 +249,8 @@ static inline int ovl_do_setxattr(struct ovl_fs *ofs, struct dentry *dentry,
const char *name, const void *value,
size_t size, int flags)
{
- int err = vfs_setxattr(ovl_upper_mnt_userns(ofs), dentry, name, value, size, flags);
+ int err = vfs_setxattr(ovl_upper_mnt_userns(ofs), dentry, name,
+ (void *)value, size, flags);
pr_debug("setxattr(%pd2, \"%s\", \"%*pE\", %zu, %d) = %i\n",
dentry, name, min((int)size, 48), value, size, flags, err);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 1ce5c9698393..e0a2e0468ee7 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1003,9 +1003,6 @@ ovl_posix_acl_xattr_get(const struct xattr_handler *handler,
struct dentry *dentry, struct inode *inode,
const char *name, void *buffer, size_t size)
{
- if (!IS_POSIXACL(inode))
- return -EOPNOTSUPP;
-
return ovl_xattr_get(dentry, inode, handler->name, buffer, size);
}
@@ -1021,9 +1018,6 @@ ovl_posix_acl_xattr_set(const struct xattr_handler *handler,
struct posix_acl *acl = NULL;
int err;
- if (!IS_POSIXACL(inode))
- return -EOPNOTSUPP;
-
/* Check that everything is OK before copy-up */
if (value) {
acl = posix_acl_from_xattr(&init_user_ns, value, size);
@@ -1966,20 +1960,6 @@ static struct dentry *ovl_get_root(struct super_block *sb,
return root;
}
-static bool ovl_has_idmapped_layers(struct ovl_fs *ofs)
-{
-
- unsigned int i;
- const struct vfsmount *mnt;
-
- for (i = 0; i < ofs->numlayer; i++) {
- mnt = ofs->layers[i].mnt;
- if (mnt && is_idmapped_mnt(mnt))
- return true;
- }
- return false;
-}
-
static int ovl_fill_super(struct super_block *sb, void *data, int silent)
{
struct path upperpath = { };
@@ -2149,10 +2129,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
sb->s_xattr = ofs->config.userxattr ? ovl_user_xattr_handlers :
ovl_trusted_xattr_handlers;
sb->s_fs_info = ofs;
- if (ovl_has_idmapped_layers(ofs))
- pr_warn("POSIX ACLs are not yet supported with idmapped layers, mounting without ACL support.\n");
- else
- sb->s_flags |= SB_POSIXACL;
+ sb->s_flags |= SB_POSIXACL;
sb->s_iflags |= SB_I_SKIP_SYNC;
err = -ENOMEM;
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 962d32468eb4..1d17d7b13dcd 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -199,7 +199,7 @@ EXPORT_SYMBOL(posix_acl_alloc);
/*
* Clone an ACL.
*/
-static struct posix_acl *
+struct posix_acl *
posix_acl_clone(const struct posix_acl *acl, gfp_t flags)
{
struct posix_acl *clone = NULL;
@@ -213,6 +213,7 @@ posix_acl_clone(const struct posix_acl *acl, gfp_t flags)
}
return clone;
}
+EXPORT_SYMBOL_GPL(posix_acl_clone);
/*
* Check if an acl is valid. Returns 0 if it is, or -E... otherwise.
@@ -361,8 +362,8 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode,
{
const struct posix_acl_entry *pa, *pe, *mask_obj;
int found = 0;
- kuid_t uid;
- kgid_t gid;
+ vfsuid_t vfsuid;
+ vfsgid_t vfsgid;
want &= MAY_READ | MAY_WRITE | MAY_EXEC;
@@ -370,30 +371,28 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode,
switch(pa->e_tag) {
case ACL_USER_OBJ:
/* (May have been checked already) */
- uid = i_uid_into_mnt(mnt_userns, inode);
- if (uid_eq(uid, current_fsuid()))
+ vfsuid = i_uid_into_vfsuid(mnt_userns, inode);
+ if (vfsuid_eq_kuid(vfsuid, current_fsuid()))
goto check_perm;
break;
case ACL_USER:
- uid = mapped_kuid_fs(mnt_userns,
- i_user_ns(inode),
+ vfsuid = make_vfsuid(mnt_userns, &init_user_ns,
pa->e_uid);
- if (uid_eq(uid, current_fsuid()))
+ if (vfsuid_eq_kuid(vfsuid, current_fsuid()))
goto mask;
break;
case ACL_GROUP_OBJ:
- gid = i_gid_into_mnt(mnt_userns, inode);
- if (in_group_p(gid)) {
+ vfsgid = i_gid_into_vfsgid(mnt_userns, inode);
+ if (vfsgid_in_group_p(vfsgid)) {
found = 1;
if ((pa->e_perm & want) == want)
goto mask;
}
break;
case ACL_GROUP:
- gid = mapped_kgid_fs(mnt_userns,
- i_user_ns(inode),
+ vfsgid = make_vfsgid(mnt_userns, &init_user_ns,
pa->e_gid);
- if (in_group_p(gid)) {
+ if (vfsgid_in_group_p(vfsgid)) {
found = 1;
if ((pa->e_perm & want) == want)
goto mask;
@@ -699,7 +698,7 @@ int posix_acl_update_mode(struct user_namespace *mnt_userns,
return error;
if (error == 0)
*acl = NULL;
- if (!in_group_p(i_gid_into_mnt(mnt_userns, inode)) &&
+ if (!vfsgid_in_group_p(i_gid_into_vfsgid(mnt_userns, inode)) &&
!capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID))
mode &= ~S_ISGID;
*mode_p = mode;
@@ -710,46 +709,127 @@ EXPORT_SYMBOL(posix_acl_update_mode);
/*
* Fix up the uids and gids in posix acl extended attributes in place.
*/
-static void posix_acl_fix_xattr_userns(
- struct user_namespace *to, struct user_namespace *from,
- struct user_namespace *mnt_userns,
- void *value, size_t size, bool from_user)
+static int posix_acl_fix_xattr_common(void *value, size_t size)
+{
+ struct posix_acl_xattr_header *header = value;
+ int count;
+
+ if (!header)
+ return -EINVAL;
+ if (size < sizeof(struct posix_acl_xattr_header))
+ return -EINVAL;
+ if (header->a_version != cpu_to_le32(POSIX_ACL_XATTR_VERSION))
+ return -EINVAL;
+
+ count = posix_acl_xattr_count(size);
+ if (count < 0)
+ return -EINVAL;
+ if (count == 0)
+ return -EINVAL;
+
+ return count;
+}
+
+void posix_acl_getxattr_idmapped_mnt(struct user_namespace *mnt_userns,
+ const struct inode *inode,
+ void *value, size_t size)
{
struct posix_acl_xattr_header *header = value;
struct posix_acl_xattr_entry *entry = (void *)(header + 1), *end;
int count;
+ vfsuid_t vfsuid;
+ vfsgid_t vfsgid;
kuid_t uid;
kgid_t gid;
- if (!value)
+ if (no_idmapping(mnt_userns, i_user_ns(inode)))
return;
- if (size < sizeof(struct posix_acl_xattr_header))
+
+ count = posix_acl_fix_xattr_common(value, size);
+ if (count < 0)
return;
- if (header->a_version != cpu_to_le32(POSIX_ACL_XATTR_VERSION))
+
+ for (end = entry + count; entry != end; entry++) {
+ switch (le16_to_cpu(entry->e_tag)) {
+ case ACL_USER:
+ uid = make_kuid(&init_user_ns, le32_to_cpu(entry->e_id));
+ vfsuid = make_vfsuid(mnt_userns, &init_user_ns, uid);
+ entry->e_id = cpu_to_le32(from_kuid(&init_user_ns,
+ vfsuid_into_kuid(vfsuid)));
+ break;
+ case ACL_GROUP:
+ gid = make_kgid(&init_user_ns, le32_to_cpu(entry->e_id));
+ vfsgid = make_vfsgid(mnt_userns, &init_user_ns, gid);
+ entry->e_id = cpu_to_le32(from_kgid(&init_user_ns,
+ vfsgid_into_kgid(vfsgid)));
+ break;
+ default:
+ break;
+ }
+ }
+}
+
+void posix_acl_setxattr_idmapped_mnt(struct user_namespace *mnt_userns,
+ const struct inode *inode,
+ void *value, size_t size)
+{
+ struct posix_acl_xattr_header *header = value;
+ struct posix_acl_xattr_entry *entry = (void *)(header + 1), *end;
+ int count;
+ vfsuid_t vfsuid;
+ vfsgid_t vfsgid;
+ kuid_t uid;
+ kgid_t gid;
+
+ if (no_idmapping(mnt_userns, i_user_ns(inode)))
return;
- count = posix_acl_xattr_count(size);
+ count = posix_acl_fix_xattr_common(value, size);
if (count < 0)
return;
- if (count == 0)
+
+ for (end = entry + count; entry != end; entry++) {
+ switch (le16_to_cpu(entry->e_tag)) {
+ case ACL_USER:
+ uid = make_kuid(&init_user_ns, le32_to_cpu(entry->e_id));
+ vfsuid = VFSUIDT_INIT(uid);
+ uid = from_vfsuid(mnt_userns, &init_user_ns, vfsuid);
+ entry->e_id = cpu_to_le32(from_kuid(&init_user_ns, uid));
+ break;
+ case ACL_GROUP:
+ gid = make_kgid(&init_user_ns, le32_to_cpu(entry->e_id));
+ vfsgid = VFSGIDT_INIT(gid);
+ gid = from_vfsgid(mnt_userns, &init_user_ns, vfsgid);
+ entry->e_id = cpu_to_le32(from_kgid(&init_user_ns, gid));
+ break;
+ default:
+ break;
+ }
+ }
+}
+
+static void posix_acl_fix_xattr_userns(
+ struct user_namespace *to, struct user_namespace *from,
+ void *value, size_t size)
+{
+ struct posix_acl_xattr_header *header = value;
+ struct posix_acl_xattr_entry *entry = (void *)(header + 1), *end;
+ int count;
+ kuid_t uid;
+ kgid_t gid;
+
+ count = posix_acl_fix_xattr_common(value, size);
+ if (count < 0)
return;
for (end = entry + count; entry != end; entry++) {
switch(le16_to_cpu(entry->e_tag)) {
case ACL_USER:
uid = make_kuid(from, le32_to_cpu(entry->e_id));
- if (from_user)
- uid = mapped_kuid_user(mnt_userns, &init_user_ns, uid);
- else
- uid = mapped_kuid_fs(mnt_userns, &init_user_ns, uid);
entry->e_id = cpu_to_le32(from_kuid(to, uid));
break;
case ACL_GROUP:
gid = make_kgid(from, le32_to_cpu(entry->e_id));
- if (from_user)
- gid = mapped_kgid_user(mnt_userns, &init_user_ns, gid);
- else
- gid = mapped_kgid_fs(mnt_userns, &init_user_ns, gid);
entry->e_id = cpu_to_le32(from_kgid(to, gid));
break;
default:
@@ -758,34 +838,20 @@ static void posix_acl_fix_xattr_userns(
}
}
-void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns,
- struct inode *inode,
- void *value, size_t size)
+void posix_acl_fix_xattr_from_user(void *value, size_t size)
{
struct user_namespace *user_ns = current_user_ns();
-
- /* Leave ids untouched on non-idmapped mounts. */
- if (no_idmapping(mnt_userns, i_user_ns(inode)))
- mnt_userns = &init_user_ns;
- if ((user_ns == &init_user_ns) && (mnt_userns == &init_user_ns))
+ if (user_ns == &init_user_ns)
return;
- posix_acl_fix_xattr_userns(&init_user_ns, user_ns, mnt_userns, value,
- size, true);
+ posix_acl_fix_xattr_userns(&init_user_ns, user_ns, value, size);
}
-void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns,
- struct inode *inode,
- void *value, size_t size)
+void posix_acl_fix_xattr_to_user(void *value, size_t size)
{
struct user_namespace *user_ns = current_user_ns();
-
- /* Leave ids untouched on non-idmapped mounts. */
- if (no_idmapping(mnt_userns, i_user_ns(inode)))
- mnt_userns = &init_user_ns;
- if ((user_ns == &init_user_ns) && (mnt_userns == &init_user_ns))
+ if (user_ns == &init_user_ns)
return;
- posix_acl_fix_xattr_userns(user_ns, &init_user_ns, mnt_userns, value,
- size, false);
+ posix_acl_fix_xattr_userns(user_ns, &init_user_ns, value, size);
}
/*
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index e26162f102ff..4d7fc1c06a6c 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -28,11 +28,14 @@
#include <linux/crypto.h>
#include <linux/string.h>
#include <linux/timer.h>
+#include <linux/scatterlist.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/jiffies.h>
#include <linux/workqueue.h>
+#include <crypto/acompress.h>
+
#include "internal.h"
/*
@@ -90,7 +93,8 @@ module_param(compress, charp, 0444);
MODULE_PARM_DESC(compress, "compression to use");
/* Compression parameters */
-static struct crypto_comp *tfm;
+static struct crypto_acomp *tfm;
+static struct acomp_req *creq;
struct pstore_zbackend {
int (*zbufsize)(size_t size);
@@ -268,12 +272,21 @@ static const struct pstore_zbackend zbackends[] = {
static int pstore_compress(const void *in, void *out,
unsigned int inlen, unsigned int outlen)
{
+ struct scatterlist src, dst;
int ret;
if (!IS_ENABLED(CONFIG_PSTORE_COMPRESS))
return -EINVAL;
- ret = crypto_comp_compress(tfm, in, inlen, out, &outlen);
+ sg_init_table(&src, 1);
+ sg_set_buf(&src, in, inlen);
+
+ sg_init_table(&dst, 1);
+ sg_set_buf(&dst, out, outlen);
+
+ acomp_request_set_params(creq, &src, &dst, inlen, outlen);
+
+ ret = crypto_acomp_compress(creq);
if (ret) {
pr_err("crypto_comp_compress failed, ret = %d!\n", ret);
return ret;
@@ -284,7 +297,7 @@ static int pstore_compress(const void *in, void *out,
static void allocate_buf_for_compression(void)
{
- struct crypto_comp *ctx;
+ struct crypto_acomp *acomp;
int size;
char *buf;
@@ -296,7 +309,7 @@ static void allocate_buf_for_compression(void)
if (!psinfo || tfm)
return;
- if (!crypto_has_comp(zbackend->name, 0, 0)) {
+ if (!crypto_has_acomp(zbackend->name, 0, CRYPTO_ALG_ASYNC)) {
pr_err("Unknown compression: %s\n", zbackend->name);
return;
}
@@ -315,16 +328,24 @@ static void allocate_buf_for_compression(void)
return;
}
- ctx = crypto_alloc_comp(zbackend->name, 0, 0);
- if (IS_ERR_OR_NULL(ctx)) {
+ acomp = crypto_alloc_acomp(zbackend->name, 0, CRYPTO_ALG_ASYNC);
+ if (IS_ERR_OR_NULL(acomp)) {
kfree(buf);
pr_err("crypto_alloc_comp('%s') failed: %ld\n", zbackend->name,
- PTR_ERR(ctx));
+ PTR_ERR(acomp));
+ return;
+ }
+
+ creq = acomp_request_alloc(acomp);
+ if (!creq) {
+ crypto_free_acomp(acomp);
+ kfree(buf);
+ pr_err("acomp_request_alloc('%s') failed\n", zbackend->name);
return;
}
/* A non-NULL big_oops_buf indicates compression is available. */
- tfm = ctx;
+ tfm = acomp;
big_oops_buf_sz = size;
big_oops_buf = buf;
@@ -334,7 +355,8 @@ static void allocate_buf_for_compression(void)
static void free_buf_for_compression(void)
{
if (IS_ENABLED(CONFIG_PSTORE_COMPRESS) && tfm) {
- crypto_free_comp(tfm);
+ acomp_request_free(creq);
+ crypto_free_acomp(tfm);
tfm = NULL;
}
kfree(big_oops_buf);
@@ -671,6 +693,8 @@ static void decompress_record(struct pstore_record *record)
int ret;
int unzipped_len;
char *unzipped, *workspace;
+ struct acomp_req *dreq;
+ struct scatterlist src, dst;
if (!IS_ENABLED(CONFIG_PSTORE_COMPRESS) || !record->compressed)
return;
@@ -694,16 +718,30 @@ static void decompress_record(struct pstore_record *record)
if (!workspace)
return;
+ dreq = acomp_request_alloc(tfm);
+ if (!dreq) {
+ kfree(workspace);
+ return;
+ }
+
+ sg_init_table(&src, 1);
+ sg_set_buf(&src, record->buf, record->size);
+
+ sg_init_table(&dst, 1);
+ sg_set_buf(&dst, workspace, unzipped_len);
+
+ acomp_request_set_params(dreq, &src, &dst, record->size, unzipped_len);
+
/* After decompression "unzipped_len" is almost certainly smaller. */
- ret = crypto_comp_decompress(tfm, record->buf, record->size,
- workspace, &unzipped_len);
+ ret = crypto_acomp_decompress(dreq);
if (ret) {
- pr_err("crypto_comp_decompress failed, ret = %d!\n", ret);
+ pr_err("crypto_acomp_decompress failed, ret = %d!\n", ret);
kfree(workspace);
return;
}
/* Append ECC notice to decompressed buffer. */
+ unzipped_len = dreq->dlen;
memcpy(workspace + unzipped_len, record->buf + record->size,
record->ecc_notice_size);
@@ -711,6 +749,7 @@ static void decompress_record(struct pstore_record *record)
unzipped = kmemdup(workspace, unzipped_len + record->ecc_notice_size,
GFP_KERNEL);
kfree(workspace);
+ acomp_request_free(dreq);
if (!unzipped)
return;
diff --git a/fs/pstore/zone.c b/fs/pstore/zone.c
index 7c8f8feac6c3..017d0d4ad329 100644
--- a/fs/pstore/zone.c
+++ b/fs/pstore/zone.c
@@ -363,7 +363,7 @@ static int psz_kmsg_recover_data(struct psz_context *cxt)
rcnt = info->read((char *)buf, zone->buffer_size + sizeof(*buf),
zone->off);
if (rcnt != zone->buffer_size + sizeof(*buf))
- return (int)rcnt < 0 ? (int)rcnt : -EIO;
+ return rcnt < 0 ? rcnt : -EIO;
}
return 0;
}
@@ -372,7 +372,7 @@ static int psz_kmsg_recover_meta(struct psz_context *cxt)
{
struct pstore_zone_info *info = cxt->pstore_zone_info;
struct pstore_zone *zone;
- size_t rcnt, len;
+ ssize_t rcnt, len;
struct psz_buffer *buf;
struct psz_kmsg_header *hdr;
struct timespec64 time = { };
@@ -400,7 +400,7 @@ static int psz_kmsg_recover_meta(struct psz_context *cxt)
continue;
} else if (rcnt != len) {
pr_err("read %s with id %lu failed\n", zone->name, i);
- return (int)rcnt < 0 ? (int)rcnt : -EIO;
+ return rcnt < 0 ? rcnt : -EIO;
}
if (buf->sig != zone->buffer->sig) {
@@ -502,7 +502,7 @@ static int psz_recover_zone(struct psz_context *cxt, struct pstore_zone *zone)
rcnt = info->read((char *)&tmpbuf, len, zone->off);
if (rcnt != len) {
pr_debug("read zone %s failed\n", zone->name);
- return (int)rcnt < 0 ? (int)rcnt : -EIO;
+ return rcnt < 0 ? rcnt : -EIO;
}
if (tmpbuf.sig != zone->buffer->sig) {
@@ -544,7 +544,7 @@ static int psz_recover_zone(struct psz_context *cxt, struct pstore_zone *zone)
rcnt = info->read(buf, len - start, off + start);
if (rcnt != len - start) {
pr_err("read zone %s failed\n", zone->name);
- ret = (int)rcnt < 0 ? (int)rcnt : -EIO;
+ ret = rcnt < 0 ? rcnt : -EIO;
goto free_oldbuf;
}
@@ -552,7 +552,7 @@ static int psz_recover_zone(struct psz_context *cxt, struct pstore_zone *zone)
rcnt = info->read(buf + len - start, start, off);
if (rcnt != start) {
pr_err("read zone %s failed\n", zone->name);
- ret = (int)rcnt < 0 ? (int)rcnt : -EIO;
+ ret = rcnt < 0 ? rcnt : -EIO;
goto free_oldbuf;
}
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 09d1307959d0..28966da7834e 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -2085,7 +2085,8 @@ EXPORT_SYMBOL(__dquot_transfer);
/* Wrapper for transferring ownership of an inode for uid/gid only
* Called from FSXXX_setattr()
*/
-int dquot_transfer(struct inode *inode, struct iattr *iattr)
+int dquot_transfer(struct user_namespace *mnt_userns, struct inode *inode,
+ struct iattr *iattr)
{
struct dquot *transfer_to[MAXQUOTAS] = {};
struct dquot *dquot;
@@ -2095,8 +2096,11 @@ int dquot_transfer(struct inode *inode, struct iattr *iattr)
if (!dquot_active(inode))
return 0;
- if (iattr->ia_valid & ATTR_UID && !uid_eq(iattr->ia_uid, inode->i_uid)){
- dquot = dqget(sb, make_kqid_uid(iattr->ia_uid));
+ if (i_uid_needs_update(mnt_userns, iattr, inode)) {
+ kuid_t kuid = from_vfsuid(mnt_userns, i_user_ns(inode),
+ iattr->ia_vfsuid);
+
+ dquot = dqget(sb, make_kqid_uid(kuid));
if (IS_ERR(dquot)) {
if (PTR_ERR(dquot) != -ESRCH) {
ret = PTR_ERR(dquot);
@@ -2106,8 +2110,11 @@ int dquot_transfer(struct inode *inode, struct iattr *iattr)
}
transfer_to[USRQUOTA] = dquot;
}
- if (iattr->ia_valid & ATTR_GID && !gid_eq(iattr->ia_gid, inode->i_gid)){
- dquot = dqget(sb, make_kqid_gid(iattr->ia_gid));
+ if (i_gid_needs_update(mnt_userns, iattr, inode)) {
+ kgid_t kgid = from_vfsgid(mnt_userns, i_user_ns(inode),
+ iattr->ia_vfsgid);
+
+ dquot = dqget(sb, make_kqid_gid(kgid));
if (IS_ERR(dquot)) {
if (PTR_ERR(dquot) != -ESRCH) {
ret = PTR_ERR(dquot);
diff --git a/fs/read_write.c b/fs/read_write.c
index e0777eefd846..0131d0df0476 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1263,6 +1263,9 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
count, fl);
file_end_write(out.file);
} else {
+ if (out.file->f_flags & O_NONBLOCK)
+ fl |= SPLICE_F_NONBLOCK;
+
retval = splice_file_to_pipe(in.file, opipe, &pos, count, fl);
}
@@ -1660,7 +1663,9 @@ int generic_write_checks_count(struct kiocb *iocb, loff_t *count)
if (iocb->ki_flags & IOCB_APPEND)
iocb->ki_pos = i_size_read(inode);
- if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
+ if ((iocb->ki_flags & IOCB_NOWAIT) &&
+ !((iocb->ki_flags & IOCB_DIRECT) ||
+ (file->f_mode & FMODE_BUF_WASYNC)))
return -EINVAL;
return generic_write_check_limits(iocb->ki_filp, iocb->ki_pos, count);
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 0cffe054b78e..b9580a6515ee 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -290,7 +290,7 @@ static int _get_block_create_0(struct inode *inode, sector_t block,
struct buffer_head *bh;
struct item_head *ih, tmp_ih;
b_blocknr_t blocknr;
- char *p = NULL;
+ char *p;
int chars;
int ret;
int result;
@@ -305,8 +305,6 @@ static int _get_block_create_0(struct inode *inode, sector_t block,
result = search_for_position_by_key(inode->i_sb, &key, &path);
if (result != POSITION_FOUND) {
pathrelse(&path);
- if (p)
- kunmap(bh_result->b_page);
if (result == IO_ERROR)
return -EIO;
/*
@@ -352,8 +350,6 @@ static int _get_block_create_0(struct inode *inode, sector_t block,
}
pathrelse(&path);
- if (p)
- kunmap(bh_result->b_page);
return ret;
}
/* requested data are in direct item(s) */
@@ -363,8 +359,6 @@ static int _get_block_create_0(struct inode *inode, sector_t block,
* when it is stored in direct item(s)
*/
pathrelse(&path);
- if (p)
- kunmap(bh_result->b_page);
return -ENOENT;
}
@@ -396,9 +390,7 @@ static int _get_block_create_0(struct inode *inode, sector_t block,
* sure we need to. But, this means the item might move if
* kmap schedules
*/
- if (!p)
- p = (char *)kmap(bh_result->b_page);
-
+ p = (char *)kmap(bh_result->b_page);
p += offset;
memset(p, 0, inode->i_sb->s_blocksize);
do {
@@ -2664,7 +2656,7 @@ static int reiserfs_write_full_page(struct page *page,
do {
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
- submit_bh(REQ_OP_WRITE, 0, bh);
+ submit_bh(REQ_OP_WRITE, bh);
nr++;
}
put_bh(bh);
@@ -2724,7 +2716,7 @@ fail:
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
clear_buffer_dirty(bh);
- submit_bh(REQ_OP_WRITE, 0, bh);
+ submit_bh(REQ_OP_WRITE, bh);
nr++;
}
put_bh(bh);
@@ -3284,7 +3276,7 @@ int reiserfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
/* must be turned off for recursive notify_change calls */
ia_valid = attr->ia_valid &= ~(ATTR_KILL_SUID|ATTR_KILL_SGID);
- if (is_quota_modification(inode, attr)) {
+ if (is_quota_modification(mnt_userns, inode, attr)) {
error = dquot_initialize(inode);
if (error)
return error;
@@ -3367,7 +3359,7 @@ int reiserfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
reiserfs_write_unlock(inode->i_sb);
if (error)
goto out;
- error = dquot_transfer(inode, attr);
+ error = dquot_transfer(mnt_userns, inode, attr);
reiserfs_write_lock(inode->i_sb);
if (error) {
journal_end(&th);
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index d8cc9a366124..94addfcefede 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -650,7 +650,7 @@ static void submit_logged_buffer(struct buffer_head *bh)
BUG();
if (!buffer_uptodate(bh))
BUG();
- submit_bh(REQ_OP_WRITE, 0, bh);
+ submit_bh(REQ_OP_WRITE, bh);
}
static void submit_ordered_buffer(struct buffer_head *bh)
@@ -660,7 +660,7 @@ static void submit_ordered_buffer(struct buffer_head *bh)
clear_buffer_dirty(bh);
if (!buffer_uptodate(bh))
BUG();
- submit_bh(REQ_OP_WRITE, 0, bh);
+ submit_bh(REQ_OP_WRITE, bh);
}
#define CHUNK_SIZE 32
@@ -868,7 +868,7 @@ loop_next:
*/
if (buffer_dirty(bh) && unlikely(bh->b_page->mapping == NULL)) {
spin_unlock(lock);
- ll_rw_block(REQ_OP_WRITE, 0, 1, &bh);
+ ll_rw_block(REQ_OP_WRITE, 1, &bh);
spin_lock(lock);
}
put_bh(bh);
@@ -1054,7 +1054,7 @@ static int flush_commit_list(struct super_block *s,
if (tbh) {
if (buffer_dirty(tbh)) {
depth = reiserfs_write_unlock_nested(s);
- ll_rw_block(REQ_OP_WRITE, 0, 1, &tbh);
+ ll_rw_block(REQ_OP_WRITE, 1, &tbh);
reiserfs_write_lock_nested(s, depth);
}
put_bh(tbh) ;
@@ -2240,7 +2240,7 @@ abort_replay:
}
}
/* read in the log blocks, memcpy to the corresponding real block */
- ll_rw_block(REQ_OP_READ, 0, get_desc_trans_len(desc), log_blocks);
+ ll_rw_block(REQ_OP_READ, get_desc_trans_len(desc), log_blocks);
for (i = 0; i < get_desc_trans_len(desc); i++) {
wait_on_buffer(log_blocks[i]);
@@ -2342,7 +2342,7 @@ static struct buffer_head *reiserfs_breada(struct block_device *dev,
} else
bhlist[j++] = bh;
}
- ll_rw_block(REQ_OP_READ, 0, j, bhlist);
+ ll_rw_block(REQ_OP_READ, j, bhlist);
for (i = 1; i < j; i++)
brelse(bhlist[i]);
bh = bhlist[0];
diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c
index ef42729216d1..9a293609a022 100644
--- a/fs/reiserfs/stree.c
+++ b/fs/reiserfs/stree.c
@@ -579,7 +579,7 @@ static int search_by_key_reada(struct super_block *s,
if (!buffer_uptodate(bh[j])) {
if (depth == -1)
depth = reiserfs_write_unlock_nested(s);
- ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, bh + j);
+ ll_rw_block(REQ_OP_READ | REQ_RAHEAD, 1, bh + j);
}
brelse(bh[j]);
}
@@ -685,7 +685,7 @@ int search_by_key(struct super_block *sb, const struct cpu_key *key,
if (!buffer_uptodate(bh) && depth == -1)
depth = reiserfs_write_unlock_nested(sb);
- ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+ ll_rw_block(REQ_OP_READ, 1, &bh);
wait_on_buffer(bh);
if (depth != -1)
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index cfb7c44c7366..c88cd2ce0665 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -1702,7 +1702,7 @@ static int read_super_block(struct super_block *s, int offset)
/* after journal replay, reread all bitmap and super blocks */
static int reread_meta_blocks(struct super_block *s)
{
- ll_rw_block(REQ_OP_READ, 0, 1, &SB_BUFFER_WITH_SB(s));
+ ll_rw_block(REQ_OP_READ, 1, &SB_BUFFER_WITH_SB(s));
wait_on_buffer(SB_BUFFER_WITH_SB(s));
if (!buffer_uptodate(SB_BUFFER_WITH_SB(s))) {
reiserfs_warning(s, "reiserfs-2504", "error reading the super");
diff --git a/fs/udf/dir.c b/fs/udf/dir.c
index 42e3e551fa4c..cad3772f9dbe 100644
--- a/fs/udf/dir.c
+++ b/fs/udf/dir.c
@@ -130,7 +130,7 @@ static int udf_readdir(struct file *file, struct dir_context *ctx)
brelse(tmp);
}
if (num) {
- ll_rw_block(REQ_OP_READ, REQ_RAHEAD, num, bha);
+ ll_rw_block(REQ_OP_READ | REQ_RAHEAD, num, bha);
for (i = 0; i < num; i++)
brelse(bha[i]);
}
diff --git a/fs/udf/directory.c b/fs/udf/directory.c
index 73720320f0ab..a2adf6293093 100644
--- a/fs/udf/directory.c
+++ b/fs/udf/directory.c
@@ -89,7 +89,7 @@ struct fileIdentDesc *udf_fileident_read(struct inode *dir, loff_t *nf_pos,
brelse(tmp);
}
if (num) {
- ll_rw_block(REQ_OP_READ, REQ_RAHEAD, num, bha);
+ ll_rw_block(REQ_OP_READ | REQ_RAHEAD, num, bha);
for (i = 0; i < num; i++)
brelse(bha[i]);
}
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index edc88716751a..8d06daed549f 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -1214,7 +1214,7 @@ struct buffer_head *udf_bread(struct inode *inode, udf_pblk_t block,
if (buffer_uptodate(bh))
return bh;
- ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+ ll_rw_block(REQ_OP_READ, 1, &bh);
wait_on_buffer(bh);
if (buffer_uptodate(bh))
diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c
index 075d3d9114c8..bd810d8239f2 100644
--- a/fs/ufs/balloc.c
+++ b/fs/ufs/balloc.c
@@ -296,7 +296,7 @@ static void ufs_change_blocknr(struct inode *inode, sector_t beg,
if (!buffer_mapped(bh))
map_bh(bh, inode->i_sb, oldb + pos);
if (!buffer_uptodate(bh)) {
- ll_rw_block(REQ_OP_READ, 0, 1, &bh);
+ ll_rw_block(REQ_OP_READ, 1, &bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
ufs_error(inode->i_sb, __func__,
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index e943370107d0..de86f5b2859f 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -192,17 +192,19 @@ static inline void msg_init(struct uffd_msg *msg)
}
static inline struct uffd_msg userfault_msg(unsigned long address,
+ unsigned long real_address,
unsigned int flags,
unsigned long reason,
unsigned int features)
{
struct uffd_msg msg;
+
msg_init(&msg);
msg.event = UFFD_EVENT_PAGEFAULT;
- if (!(features & UFFD_FEATURE_EXACT_ADDRESS))
- address &= PAGE_MASK;
- msg.arg.pagefault.address = address;
+ msg.arg.pagefault.address = (features & UFFD_FEATURE_EXACT_ADDRESS) ?
+ real_address : address;
+
/*
* These flags indicate why the userfault occurred:
* - UFFD_PAGEFAULT_FLAG_WP indicates a write protect fault.
@@ -488,8 +490,8 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function);
uwq.wq.private = current;
- uwq.msg = userfault_msg(vmf->real_address, vmf->flags, reason,
- ctx->features);
+ uwq.msg = userfault_msg(vmf->address, vmf->real_address, vmf->flags,
+ reason, ctx->features);
uwq.ctx = ctx;
uwq.waken = false;
diff --git a/fs/verity/Kconfig b/fs/verity/Kconfig
index 54598cd80145..aad1f1d998b9 100644
--- a/fs/verity/Kconfig
+++ b/fs/verity/Kconfig
@@ -14,11 +14,11 @@ config FS_VERITY
help
This option enables fs-verity. fs-verity is the dm-verity
mechanism implemented at the file level. On supported
- filesystems (currently EXT4 and F2FS), userspace can use an
- ioctl to enable verity for a file, which causes the filesystem
- to build a Merkle tree for the file. The filesystem will then
- transparently verify any data read from the file against the
- Merkle tree. The file is also made read-only.
+ filesystems (currently ext4, f2fs, and btrfs), userspace can
+ use an ioctl to enable verity for a file, which causes the
+ filesystem to build a Merkle tree for the file. The filesystem
+ will then transparently verify any data read from the file
+ against the Merkle tree. The file is also made read-only.
This serves as an integrity check, but the availability of the
Merkle tree root hash also allows efficiently supporting
diff --git a/fs/xattr.c b/fs/xattr.c
index e8dd03e4561e..a1f4998bc6be 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -282,9 +282,15 @@ out:
}
EXPORT_SYMBOL_GPL(__vfs_setxattr_locked);
+static inline bool is_posix_acl_xattr(const char *name)
+{
+ return (strcmp(name, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
+ (strcmp(name, XATTR_NAME_POSIX_ACL_DEFAULT) == 0);
+}
+
int
vfs_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
- const char *name, const void *value, size_t size, int flags)
+ const char *name, void *value, size_t size, int flags)
{
struct inode *inode = dentry->d_inode;
struct inode *delegated_inode = NULL;
@@ -292,12 +298,16 @@ vfs_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
int error;
if (size && strcmp(name, XATTR_NAME_CAPS) == 0) {
- error = cap_convert_nscap(mnt_userns, dentry, &value, size);
+ error = cap_convert_nscap(mnt_userns, dentry,
+ (const void **)&value, size);
if (error < 0)
return error;
size = error;
}
+ if (size && is_posix_acl_xattr(name))
+ posix_acl_setxattr_idmapped_mnt(mnt_userns, inode, value, size);
+
retry_deleg:
inode_lock(inode);
error = __vfs_setxattr_locked(mnt_userns, dentry, name, value, size,
@@ -431,7 +441,10 @@ vfs_getxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
return ret;
}
nolsm:
- return __vfs_getxattr(dentry, inode, name, value, size);
+ error = __vfs_getxattr(dentry, inode, name, value, size);
+ if (error > 0 && is_posix_acl_xattr(name))
+ posix_acl_getxattr_idmapped_mnt(mnt_userns, inode, value, size);
+ return error;
}
EXPORT_SYMBOL_GPL(vfs_getxattr);
@@ -577,8 +590,7 @@ static void setxattr_convert(struct user_namespace *mnt_userns,
if (ctx->size &&
((strcmp(ctx->kname->name, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
(strcmp(ctx->kname->name, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)))
- posix_acl_fix_xattr_from_user(mnt_userns, d_inode(d),
- ctx->kvalue, ctx->size);
+ posix_acl_fix_xattr_from_user(ctx->kvalue, ctx->size);
}
int do_setxattr(struct user_namespace *mnt_userns, struct dentry *dentry,
@@ -695,8 +707,7 @@ do_getxattr(struct user_namespace *mnt_userns, struct dentry *d,
if (error > 0) {
if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
(strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0))
- posix_acl_fix_xattr_to_user(mnt_userns, d_inode(d),
- ctx->kvalue, error);
+ posix_acl_fix_xattr_to_user(ctx->kvalue, error);
if (ctx->size && copy_to_user(ctx->value, ctx->kvalue, error))
error = -EFAULT;
} else if (error == -ERANGE && ctx->size >= XATTR_SIZE_MAX) {
diff --git a/fs/xfs/xfs_bio_io.c b/fs/xfs/xfs_bio_io.c
index ae4345b37621..fe21c76f75b8 100644
--- a/fs/xfs/xfs_bio_io.c
+++ b/fs/xfs/xfs_bio_io.c
@@ -15,7 +15,7 @@ xfs_rw_bdev(
sector_t sector,
unsigned int count,
char *data,
- unsigned int op)
+ enum req_op op)
{
unsigned int is_vmalloc = is_vmalloc_addr(data);
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index bf4e60871068..5e8f40d8c052 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1416,7 +1416,7 @@ xfs_buf_ioapply_map(
int map,
int *buf_offset,
int *count,
- int op)
+ blk_opf_t op)
{
int page_index;
unsigned int total_nr_pages = bp->b_page_count;
@@ -1493,7 +1493,7 @@ _xfs_buf_ioapply(
struct xfs_buf *bp)
{
struct blk_plug plug;
- int op;
+ blk_opf_t op;
int offset;
int size;
int i;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 5a171c0b244b..8d9b14d2b912 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -410,7 +410,7 @@ restart:
spin_unlock(&ip->i_flags_lock);
out:
- return file_modified(file);
+ return kiocb_modified(iocb);
}
static int
@@ -700,12 +700,11 @@ xfs_file_buffered_write(
bool cleared_space = false;
unsigned int iolock;
- if (iocb->ki_flags & IOCB_NOWAIT)
- return -EOPNOTSUPP;
-
write_retry:
iolock = XFS_IOLOCK_EXCL;
- xfs_ilock(ip, iolock);
+ ret = xfs_ilock_iocb(iocb, iolock);
+ if (ret)
+ return ret;
ret = xfs_file_write_checks(iocb, from, &iolock);
if (ret)
@@ -1165,7 +1164,7 @@ xfs_file_open(
{
if (xfs_is_shutdown(XFS_M(inode->i_sb)))
return -EIO;
- file->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC;
+ file->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC | FMODE_BUF_WASYNC;
return generic_file_open(inode, file);
}
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 5a393259a3a3..5d50fed291b4 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -664,7 +664,7 @@ xfs_ilock_for_iomap(
unsigned flags,
unsigned *lockmode)
{
- unsigned mode = XFS_ILOCK_SHARED;
+ unsigned int mode = *lockmode;
bool is_write = flags & (IOMAP_WRITE | IOMAP_ZERO);
/*
@@ -742,7 +742,7 @@ xfs_direct_write_iomap_begin(
int nimaps = 1, error = 0;
bool shared = false;
u16 iomap_flags = 0;
- unsigned lockmode;
+ unsigned int lockmode = XFS_ILOCK_SHARED;
ASSERT(flags & (IOMAP_WRITE | IOMAP_ZERO));
@@ -886,6 +886,7 @@ xfs_buffered_write_iomap_begin(
bool eof = false, cow_eof = false, shared = false;
int allocfork = XFS_DATA_FORK;
int error = 0;
+ unsigned int lockmode = XFS_ILOCK_EXCL;
if (xfs_is_shutdown(mp))
return -EIO;
@@ -897,7 +898,9 @@ xfs_buffered_write_iomap_begin(
ASSERT(!XFS_IS_REALTIME_INODE(ip));
- xfs_ilock(ip, XFS_ILOCK_EXCL);
+ error = xfs_ilock_for_iomap(ip, flags, &lockmode);
+ if (error)
+ return error;
if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(&ip->i_df)) ||
XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
@@ -1172,7 +1175,7 @@ xfs_read_iomap_begin(
xfs_fileoff_t end_fsb = xfs_iomap_end_fsb(mp, offset, length);
int nimaps = 1, error = 0;
bool shared = false;
- unsigned lockmode;
+ unsigned int lockmode = XFS_ILOCK_SHARED;
ASSERT(!(flags & (IOMAP_WRITE | IOMAP_ZERO)));
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 29f5b8b8aca6..a7402f6ea510 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -667,13 +667,15 @@ xfs_setattr_nonsize(
uint qflags = 0;
if ((mask & ATTR_UID) && XFS_IS_UQUOTA_ON(mp)) {
- uid = iattr->ia_uid;
+ uid = from_vfsuid(mnt_userns, i_user_ns(inode),
+ iattr->ia_vfsuid);
qflags |= XFS_QMOPT_UQUOTA;
} else {
uid = inode->i_uid;
}
if ((mask & ATTR_GID) && XFS_IS_GQUOTA_ON(mp)) {
- gid = iattr->ia_gid;
+ gid = from_vfsgid(mnt_userns, i_user_ns(inode),
+ iattr->ia_vfsgid);
qflags |= XFS_QMOPT_GQUOTA;
} else {
gid = inode->i_gid;
@@ -704,13 +706,13 @@ xfs_setattr_nonsize(
* didn't have the inode locked, inode's dquot(s) would have changed
* also.
*/
- if ((mask & ATTR_UID) && XFS_IS_UQUOTA_ON(mp) &&
- !uid_eq(inode->i_uid, iattr->ia_uid)) {
+ if (XFS_IS_UQUOTA_ON(mp) &&
+ i_uid_needs_update(mnt_userns, iattr, inode)) {
ASSERT(udqp);
old_udqp = xfs_qm_vop_chown(tp, ip, &ip->i_udquot, udqp);
}
- if ((mask & ATTR_GID) && XFS_IS_GQUOTA_ON(mp) &&
- !gid_eq(inode->i_gid, iattr->ia_gid)) {
+ if (XFS_IS_GQUOTA_ON(mp) &&
+ i_gid_needs_update(mnt_userns, iattr, inode)) {
ASSERT(xfs_has_pquotino(mp) || !XFS_IS_PQUOTA_ON(mp));
ASSERT(gdqp);
old_gdqp = xfs_qm_vop_chown(tp, ip, &ip->i_gdquot, gdqp);
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index cb9105d667db..f9878021e7d0 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -196,7 +196,7 @@ static inline uint64_t howmany_64(uint64_t x, uint32_t y)
}
int xfs_rw_bdev(struct block_device *bdev, sector_t sector, unsigned int count,
- char *data, unsigned int op);
+ char *data, enum req_op op);
#define ASSERT_ALWAYS(expr) \
(likely(expr) ? (void)0 : assfail(NULL, #expr, __FILE__, __LINE__))
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 5f7e4e6e33ce..940c8107cbd4 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -122,7 +122,7 @@ xlog_do_io(
xfs_daddr_t blk_no,
unsigned int nbblks,
char *data,
- unsigned int op)
+ enum req_op op)
{
int error;
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index 053299758deb..295ed36a5d12 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -60,8 +60,7 @@ static void zonefs_account_active(struct inode *inode)
}
}
-static inline int zonefs_zone_mgmt(struct inode *inode,
- enum req_opf op)
+static inline int zonefs_zone_mgmt(struct inode *inode, enum req_op op)
{
struct zonefs_inode_info *zi = ZONEFS_I(inode);
int ret;
@@ -525,7 +524,7 @@ static int zonefs_file_truncate(struct inode *inode, loff_t isize)
{
struct zonefs_inode_info *zi = ZONEFS_I(inode);
loff_t old_isize;
- enum req_opf op;
+ enum req_op op;
int ret = 0;
/*
@@ -616,7 +615,7 @@ static int zonefs_inode_setattr(struct user_namespace *mnt_userns,
!uid_eq(iattr->ia_uid, inode->i_uid)) ||
((iattr->ia_valid & ATTR_GID) &&
!gid_eq(iattr->ia_gid, inode->i_gid))) {
- ret = dquot_transfer(inode, iattr);
+ ret = dquot_transfer(mnt_userns, inode, iattr);
if (ret)
return ret;
}
@@ -1394,7 +1393,7 @@ static void zonefs_init_dir_inode(struct inode *parent, struct inode *inode,
{
struct super_block *sb = parent->i_sb;
- inode->i_ino = blkdev_nr_zones(sb->s_bdev->bd_disk) + type + 1;
+ inode->i_ino = bdev_nr_zones(sb->s_bdev) + type + 1;
inode_init_owner(&init_user_ns, inode, parent, S_IFDIR | 0555);
inode->i_op = &zonefs_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
@@ -1540,7 +1539,7 @@ static int zonefs_create_zgroup(struct zonefs_zone_data *zd,
/*
* The first zone contains the super block: skip it.
*/
- end = zd->zones + blkdev_nr_zones(sb->s_bdev->bd_disk);
+ end = zd->zones + bdev_nr_zones(sb->s_bdev);
for (zone = &zd->zones[1]; zone < end; zone = next) {
next = zone + 1;
@@ -1635,8 +1634,8 @@ static int zonefs_get_zone_info(struct zonefs_zone_data *zd)
struct block_device *bdev = zd->sb->s_bdev;
int ret;
- zd->zones = kvcalloc(blkdev_nr_zones(bdev->bd_disk),
- sizeof(struct blk_zone), GFP_KERNEL);
+ zd->zones = kvcalloc(bdev_nr_zones(bdev), sizeof(struct blk_zone),
+ GFP_KERNEL);
if (!zd->zones)
return -ENOMEM;
@@ -1648,9 +1647,9 @@ static int zonefs_get_zone_info(struct zonefs_zone_data *zd)
return ret;
}
- if (ret != blkdev_nr_zones(bdev->bd_disk)) {
+ if (ret != bdev_nr_zones(bdev)) {
zonefs_err(zd->sb, "Invalid zone report (%d/%u zones)\n",
- ret, blkdev_nr_zones(bdev->bd_disk));
+ ret, bdev_nr_zones(bdev));
return -EIO;
}
@@ -1816,8 +1815,7 @@ static int zonefs_fill_super(struct super_block *sb, void *data, int silent)
if (ret)
goto cleanup;
- zonefs_info(sb, "Mounting %u zones",
- blkdev_nr_zones(sb->s_bdev->bd_disk));
+ zonefs_info(sb, "Mounting %u zones", bdev_nr_zones(sb->s_bdev));
if (!sbi->s_max_wro_seq_files &&
!sbi->s_max_active_seq_files &&
@@ -1833,7 +1831,7 @@ static int zonefs_fill_super(struct super_block *sb, void *data, int silent)
if (!inode)
goto cleanup;
- inode->i_ino = blkdev_nr_zones(sb->s_bdev->bd_disk);
+ inode->i_ino = bdev_nr_zones(sb->s_bdev);
inode->i_mode = S_IFDIR | 0555;
inode->i_ctime = inode->i_mtime = inode->i_atime = current_time(inode);
inode->i_op = &zonefs_dir_inode_operations;
diff --git a/fs/zonefs/trace.h b/fs/zonefs/trace.h
index f369d7d50303..42edcfd393ed 100644
--- a/fs/zonefs/trace.h
+++ b/fs/zonefs/trace.h
@@ -20,12 +20,12 @@
#define show_dev(dev) MAJOR(dev), MINOR(dev)
TRACE_EVENT(zonefs_zone_mgmt,
- TP_PROTO(struct inode *inode, enum req_opf op),
+ TP_PROTO(struct inode *inode, enum req_op op),
TP_ARGS(inode, op),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(ino_t, ino)
- __field(int, op)
+ __field(enum req_op, op)
__field(sector_t, sector)
__field(sector_t, nr_sectors)
),