summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/Makefile2
-rw-r--r--fs/adfs/adfs.h32
-rw-r--r--fs/adfs/dir.c314
-rw-r--r--fs/adfs/dir_f.c302
-rw-r--r--fs/adfs/dir_f.h52
-rw-r--r--fs/adfs/dir_fplus.c346
-rw-r--r--fs/adfs/dir_fplus.h6
-rw-r--r--fs/adfs/inode.c64
-rw-r--r--fs/adfs/map.c247
-rw-r--r--fs/adfs/super.c267
-rw-r--r--fs/binfmt_elf.c144
-rw-r--r--fs/btrfs/compression.c2
-rw-r--r--fs/btrfs/zlib.c135
-rw-r--r--fs/compat_ioctl.c261
-rw-r--r--fs/debugfs/file.c38
-rw-r--r--fs/debugfs/inode.c9
-rw-r--r--fs/dlm/lowcomms.c6
-rw-r--r--fs/ecryptfs/crypto.c2
-rw-r--r--fs/ecryptfs/keystore.c4
-rw-r--r--fs/erofs/decompressor.c22
-rw-r--r--fs/erofs/internal.h4
-rw-r--r--fs/erofs/utils.c15
-rw-r--r--fs/erofs/xattr.h17
-rw-r--r--fs/erofs/zdata.c123
-rw-r--r--fs/eventpoll.c87
-rw-r--r--fs/exec.c6
-rw-r--r--fs/ext2/super.c7
-rw-r--r--fs/ext4/Kconfig8
-rw-r--r--fs/ext4/Makefile3
-rw-r--r--fs/ext4/balloc.c5
-rw-r--r--fs/ext4/dir.c10
-rw-r--r--fs/ext4/ext4.h81
-rw-r--r--fs/ext4/ext4_extents.h5
-rw-r--r--fs/ext4/ext4_jbd2.c25
-rw-r--r--fs/ext4/ext4_jbd2.h22
-rw-r--r--fs/ext4/extents.c205
-rw-r--r--fs/ext4/extents_status.h6
-rw-r--r--fs/ext4/file.c203
-rw-r--r--fs/ext4/ialloc.c6
-rw-r--r--fs/ext4/indirect.c26
-rw-r--r--fs/ext4/inline.c4
-rw-r--r--fs/ext4/inode-test.c4
-rw-r--r--fs/ext4/inode.c53
-rw-r--r--fs/ext4/ioctl.c2
-rw-r--r--fs/ext4/mballoc.c4
-rw-r--r--fs/ext4/mmp.c6
-rw-r--r--fs/ext4/namei.c20
-rw-r--r--fs/ext4/page-io.c19
-rw-r--r--fs/ext4/readpage.c42
-rw-r--r--fs/ext4/resize.c10
-rw-r--r--fs/ext4/super.c122
-rw-r--r--fs/ext4/sysfs.c88
-rw-r--r--fs/ext4/xattr.c6
-rw-r--r--fs/f2fs/Kconfig27
-rw-r--r--fs/f2fs/Makefile1
-rw-r--r--fs/f2fs/checkpoint.c6
-rw-r--r--fs/f2fs/compress.c1176
-rw-r--r--fs/f2fs/data.c734
-rw-r--r--fs/f2fs/debug.c88
-rw-r--r--fs/f2fs/dir.c25
-rw-r--r--fs/f2fs/f2fs.h326
-rw-r--r--fs/f2fs/file.c251
-rw-r--r--fs/f2fs/gc.c18
-rw-r--r--fs/f2fs/inline.c44
-rw-r--r--fs/f2fs/inode.c41
-rw-r--r--fs/f2fs/namei.c120
-rw-r--r--fs/f2fs/recovery.c20
-rw-r--r--fs/f2fs/segment.c271
-rw-r--r--fs/f2fs/segment.h19
-rw-r--r--fs/f2fs/super.c182
-rw-r--r--fs/f2fs/sysfs.c158
-rw-r--r--fs/fat/inode.c3
-rw-r--r--fs/file.c28
-rw-r--r--fs/fs-writeback.c2
-rw-r--r--fs/gfs2/aops.c4
-rw-r--r--fs/gfs2/dir.c3
-rw-r--r--fs/gfs2/glock.c2
-rw-r--r--fs/gfs2/glops.c2
-rw-r--r--fs/gfs2/incore.h6
-rw-r--r--fs/gfs2/inode.c10
-rw-r--r--fs/gfs2/log.c21
-rw-r--r--fs/gfs2/log.h4
-rw-r--r--fs/gfs2/lops.c70
-rw-r--r--fs/gfs2/ops_fstype.c2
-rw-r--r--fs/gfs2/rgrp.c10
-rw-r--r--fs/gfs2/trans.c9
-rw-r--r--fs/hfs/hfs_fs.h28
-rw-r--r--fs/hfs/inode.c4
-rw-r--r--fs/hfsplus/hfsplus_fs.h28
-rw-r--r--fs/hfsplus/inode.c12
-rw-r--r--fs/hostfs/hostfs.h22
-rw-r--r--fs/hostfs/hostfs_kern.c15
-rw-r--r--fs/internal.h14
-rw-r--r--fs/io-wq.c103
-rw-r--r--fs/io-wq.h11
-rw-r--r--fs/io_uring.c2206
-rw-r--r--fs/ioctl.c131
-rw-r--r--fs/iomap/buffered-io.c18
-rw-r--r--fs/jbd2/checkpoint.c2
-rw-r--r--fs/jbd2/commit.c4
-rw-r--r--fs/jbd2/journal.c119
-rw-r--r--fs/jbd2/transaction.c4
-rw-r--r--fs/kernfs/dir.c2
-rw-r--r--fs/namei.c203
-rw-r--r--fs/nfs/fscache-index.c6
-rw-r--r--fs/nfs/fscache.c18
-rw-r--r--fs/nfs/fscache.h8
-rw-r--r--fs/nfs/nfs4xdr.c10
-rw-r--r--fs/nsfs.c29
-rw-r--r--fs/ocfs2/cluster/quorum.c2
-rw-r--r--fs/ocfs2/dlm/Makefile2
-rw-r--r--fs/ocfs2/dlm/dlmast.c8
-rw-r--r--fs/ocfs2/dlm/dlmcommon.h4
-rw-r--r--fs/ocfs2/dlm/dlmconvert.c8
-rw-r--r--fs/ocfs2/dlm/dlmdebug.c8
-rw-r--r--fs/ocfs2/dlm/dlmdomain.c8
-rw-r--r--fs/ocfs2/dlm/dlmlock.c8
-rw-r--r--fs/ocfs2/dlm/dlmmaster.c10
-rw-r--r--fs/ocfs2/dlm/dlmrecovery.c10
-rw-r--r--fs/ocfs2/dlm/dlmthread.c8
-rw-r--r--fs/ocfs2/dlm/dlmunlock.c8
-rw-r--r--fs/ocfs2/dlmfs/Makefile2
-rw-r--r--fs/ocfs2/dlmfs/dlmfs.c4
-rw-r--r--fs/ocfs2/dlmfs/userdlm.c6
-rw-r--r--fs/ocfs2/dlmglue.c2
-rw-r--r--fs/ocfs2/journal.h8
-rw-r--r--fs/ocfs2/namei.c3
-rw-r--r--fs/open.c146
-rw-r--r--fs/proc/base.c3
-rw-r--r--fs/proc/namespaces.c20
-rw-r--r--fs/quota/quota_v2.c2
-rw-r--r--fs/quota/quotaio_v1.h6
-rw-r--r--fs/reiserfs/journal.c2
-rw-r--r--fs/reiserfs/procfs.c1
-rw-r--r--fs/reiserfs/stree.c9
-rw-r--r--fs/reiserfs/super.c4
-rw-r--r--fs/stat.c34
-rw-r--r--fs/ubifs/file.c4
-rw-r--r--fs/ubifs/ioctl.c14
-rw-r--r--fs/ubifs/orphan.c4
-rw-r--r--fs/ubifs/sb.c2
-rw-r--r--fs/ubifs/super.c2
-rw-r--r--fs/udf/ecma_167.h46
-rw-r--r--fs/udf/inode.c6
-rw-r--r--fs/udf/osta_udf.h100
-rw-r--r--fs/udf/super.c40
-rw-r--r--fs/udf/truncate.c2
-rw-r--r--fs/xfs/libxfs/xfs_attr.c14
-rw-r--r--fs/xfs/libxfs/xfs_attr.h15
-rw-r--r--fs/xfs/libxfs/xfs_attr_leaf.c4
-rw-r--r--fs/xfs/libxfs/xfs_attr_leaf.h9
-rw-r--r--fs/xfs/libxfs/xfs_attr_remote.c89
-rw-r--r--fs/xfs/libxfs/xfs_attr_remote.h2
-rw-r--r--fs/xfs/libxfs/xfs_btree.c2
-rw-r--r--fs/xfs/libxfs/xfs_da_btree.h4
-rw-r--r--fs/xfs/libxfs/xfs_da_format.h4
-rw-r--r--fs/xfs/libxfs/xfs_format.h7
-rw-r--r--fs/xfs/libxfs/xfs_log_format.h19
-rw-r--r--fs/xfs/scrub/repair.h1
-rw-r--r--fs/xfs/xfs_acl.c11
-rw-r--r--fs/xfs/xfs_attr_inactive.c149
-rw-r--r--fs/xfs/xfs_buf_item.c45
-rw-r--r--fs/xfs/xfs_buf_item.h1
-rw-r--r--fs/xfs/xfs_dquot.c6
-rw-r--r--fs/xfs/xfs_file.c7
-rw-r--r--fs/xfs/xfs_inode.c25
-rw-r--r--fs/xfs/xfs_ioctl.c20
-rw-r--r--fs/xfs/xfs_ioctl32.c9
-rw-r--r--fs/xfs/xfs_ioctl32.h2
-rw-r--r--fs/xfs/xfs_iomap.c2
-rw-r--r--fs/xfs/xfs_iops.c6
-rw-r--r--fs/xfs/xfs_log_recover.c6
-rw-r--r--fs/xfs/xfs_ondisk.h1
-rw-r--r--fs/xfs/xfs_qm.h6
-rw-r--r--fs/xfs/xfs_quotaops.c6
-rw-r--r--fs/xfs/xfs_reflink.c9
-rw-r--r--fs/xfs/xfs_reflink.h2
-rw-r--r--fs/xfs/xfs_super.c48
-rw-r--r--fs/xfs/xfs_trans_dquot.c8
-rw-r--r--fs/xfs/xfs_xattr.c14
180 files changed, 8109 insertions, 3179 deletions
diff --git a/fs/Makefile b/fs/Makefile
index 1148c555c4d3..98be354fdb61 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -37,7 +37,7 @@ obj-$(CONFIG_FS_DAX) += dax.o
obj-$(CONFIG_FS_ENCRYPTION) += crypto/
obj-$(CONFIG_FS_VERITY) += verity/
obj-$(CONFIG_FILE_LOCKING) += locks.o
-obj-$(CONFIG_COMPAT) += compat.o compat_ioctl.o
+obj-$(CONFIG_COMPAT) += compat.o
obj-$(CONFIG_BINFMT_AOUT) += binfmt_aout.o
obj-$(CONFIG_BINFMT_EM86) += binfmt_em86.o
obj-$(CONFIG_BINFMT_MISC) += binfmt_misc.o
diff --git a/fs/adfs/adfs.h b/fs/adfs/adfs.h
index b7e844d2f321..699c4fa8b78b 100644
--- a/fs/adfs/adfs.h
+++ b/fs/adfs/adfs.h
@@ -26,14 +26,13 @@ static inline u16 adfs_filetype(u32 loadaddr)
#define ADFS_NDA_PUBLIC_READ (1 << 5)
#define ADFS_NDA_PUBLIC_WRITE (1 << 6)
-#include "dir_f.h"
-
/*
* adfs file system inode data in memory
*/
struct adfs_inode_info {
loff_t mmu_private;
__u32 parent_id; /* parent indirect disc address */
+ __u32 indaddr; /* object indirect disc address */
__u32 loadaddr; /* RISC OS load address */
__u32 execaddr; /* RISC OS exec address */
unsigned int attr; /* RISC OS permissions */
@@ -93,15 +92,19 @@ struct adfs_dir {
int nr_buffers;
struct buffer_head *bh[4];
-
- /* big directories need allocated buffers */
- struct buffer_head **bh_fplus;
+ struct buffer_head **bhs;
unsigned int pos;
__u32 parent_id;
- struct adfs_dirheader dirhead;
- union adfs_dirtail dirtail;
+ union {
+ struct adfs_dirheader *dirhead;
+ struct adfs_bigdirheader *bighead;
+ };
+ union {
+ struct adfs_newdirtail *newtail;
+ struct adfs_bigdirtail *bigtail;
+ };
};
/*
@@ -122,13 +125,13 @@ struct object_info {
struct adfs_dir_ops {
int (*read)(struct super_block *sb, unsigned int indaddr,
unsigned int size, struct adfs_dir *dir);
+ int (*iterate)(struct adfs_dir *dir, struct dir_context *ctx);
int (*setpos)(struct adfs_dir *dir, unsigned int fpos);
int (*getnext)(struct adfs_dir *dir, struct object_info *obj);
int (*update)(struct adfs_dir *dir, struct object_info *obj);
int (*create)(struct adfs_dir *dir, struct object_info *obj);
int (*remove)(struct adfs_dir *dir, struct object_info *obj);
- int (*sync)(struct adfs_dir *dir);
- void (*free)(struct adfs_dir *dir);
+ int (*commit)(struct adfs_dir *dir);
};
struct adfs_discmap {
@@ -145,7 +148,9 @@ int adfs_notify_change(struct dentry *dentry, struct iattr *attr);
/* map.c */
int adfs_map_lookup(struct super_block *sb, u32 frag_id, unsigned int offset);
-extern unsigned int adfs_map_free(struct super_block *sb);
+void adfs_map_statfs(struct super_block *sb, struct kstatfs *buf);
+struct adfs_discmap *adfs_read_map(struct super_block *sb, struct adfs_discrecord *dr);
+void adfs_free_map(struct super_block *sb);
/* Misc */
__printf(3, 4)
@@ -167,6 +172,13 @@ extern const struct dentry_operations adfs_dentry_operations;
extern const struct adfs_dir_ops adfs_f_dir_ops;
extern const struct adfs_dir_ops adfs_fplus_dir_ops;
+int adfs_dir_copyfrom(void *dst, struct adfs_dir *dir, unsigned int offset,
+ size_t len);
+int adfs_dir_copyto(struct adfs_dir *dir, unsigned int offset, const void *src,
+ size_t len);
+void adfs_dir_relse(struct adfs_dir *dir);
+int adfs_dir_read_buffers(struct super_block *sb, u32 indaddr,
+ unsigned int size, struct adfs_dir *dir);
void adfs_object_fixup(struct adfs_dir *dir, struct object_info *obj);
extern int adfs_dir_update(struct super_block *sb, struct object_info *obj,
int wait);
diff --git a/fs/adfs/dir.c b/fs/adfs/dir.c
index a54c53244992..77fbd196008f 100644
--- a/fs/adfs/dir.c
+++ b/fs/adfs/dir.c
@@ -6,12 +6,196 @@
*
* Common directory handling for ADFS
*/
+#include <linux/slab.h>
#include "adfs.h"
/*
* For future. This should probably be per-directory.
*/
-static DEFINE_RWLOCK(adfs_dir_lock);
+static DECLARE_RWSEM(adfs_dir_rwsem);
+
+int adfs_dir_copyfrom(void *dst, struct adfs_dir *dir, unsigned int offset,
+ size_t len)
+{
+ struct super_block *sb = dir->sb;
+ unsigned int index, remain;
+
+ index = offset >> sb->s_blocksize_bits;
+ offset &= sb->s_blocksize - 1;
+ remain = sb->s_blocksize - offset;
+ if (index + (remain < len) >= dir->nr_buffers)
+ return -EINVAL;
+
+ if (remain < len) {
+ memcpy(dst, dir->bhs[index]->b_data + offset, remain);
+ dst += remain;
+ len -= remain;
+ index += 1;
+ offset = 0;
+ }
+
+ memcpy(dst, dir->bhs[index]->b_data + offset, len);
+
+ return 0;
+}
+
+int adfs_dir_copyto(struct adfs_dir *dir, unsigned int offset, const void *src,
+ size_t len)
+{
+ struct super_block *sb = dir->sb;
+ unsigned int index, remain;
+
+ index = offset >> sb->s_blocksize_bits;
+ offset &= sb->s_blocksize - 1;
+ remain = sb->s_blocksize - offset;
+ if (index + (remain < len) >= dir->nr_buffers)
+ return -EINVAL;
+
+ if (remain < len) {
+ memcpy(dir->bhs[index]->b_data + offset, src, remain);
+ src += remain;
+ len -= remain;
+ index += 1;
+ offset = 0;
+ }
+
+ memcpy(dir->bhs[index]->b_data + offset, src, len);
+
+ return 0;
+}
+
+static void __adfs_dir_cleanup(struct adfs_dir *dir)
+{
+ dir->nr_buffers = 0;
+
+ if (dir->bhs != dir->bh)
+ kfree(dir->bhs);
+ dir->bhs = NULL;
+ dir->sb = NULL;
+}
+
+void adfs_dir_relse(struct adfs_dir *dir)
+{
+ unsigned int i;
+
+ for (i = 0; i < dir->nr_buffers; i++)
+ brelse(dir->bhs[i]);
+
+ __adfs_dir_cleanup(dir);
+}
+
+static void adfs_dir_forget(struct adfs_dir *dir)
+{
+ unsigned int i;
+
+ for (i = 0; i < dir->nr_buffers; i++)
+ bforget(dir->bhs[i]);
+
+ __adfs_dir_cleanup(dir);
+}
+
+int adfs_dir_read_buffers(struct super_block *sb, u32 indaddr,
+ unsigned int size, struct adfs_dir *dir)
+{
+ struct buffer_head **bhs;
+ unsigned int i, num;
+ int block;
+
+ num = ALIGN(size, sb->s_blocksize) >> sb->s_blocksize_bits;
+ if (num > ARRAY_SIZE(dir->bh)) {
+ /* We only allow one extension */
+ if (dir->bhs != dir->bh)
+ return -EINVAL;
+
+ bhs = kcalloc(num, sizeof(*bhs), GFP_KERNEL);
+ if (!bhs)
+ return -ENOMEM;
+
+ if (dir->nr_buffers)
+ memcpy(bhs, dir->bhs, dir->nr_buffers * sizeof(*bhs));
+
+ dir->bhs = bhs;
+ }
+
+ for (i = dir->nr_buffers; i < num; i++) {
+ block = __adfs_block_map(sb, indaddr, i);
+ if (!block) {
+ adfs_error(sb, "dir %06x has a hole at offset %u",
+ indaddr, i);
+ goto error;
+ }
+
+ dir->bhs[i] = sb_bread(sb, block);
+ if (!dir->bhs[i]) {
+ adfs_error(sb,
+ "dir %06x failed read at offset %u, mapped block 0x%08x",
+ indaddr, i, block);
+ goto error;
+ }
+
+ dir->nr_buffers++;
+ }
+ return 0;
+
+error:
+ adfs_dir_relse(dir);
+
+ return -EIO;
+}
+
+static int adfs_dir_read(struct super_block *sb, u32 indaddr,
+ unsigned int size, struct adfs_dir *dir)
+{
+ dir->sb = sb;
+ dir->bhs = dir->bh;
+ dir->nr_buffers = 0;
+
+ return ADFS_SB(sb)->s_dir->read(sb, indaddr, size, dir);
+}
+
+static int adfs_dir_read_inode(struct super_block *sb, struct inode *inode,
+ struct adfs_dir *dir)
+{
+ int ret;
+
+ ret = adfs_dir_read(sb, ADFS_I(inode)->indaddr, inode->i_size, dir);
+ if (ret)
+ return ret;
+
+ if (ADFS_I(inode)->parent_id != dir->parent_id) {
+ adfs_error(sb,
+ "parent directory id changed under me! (%06x but got %06x)\n",
+ ADFS_I(inode)->parent_id, dir->parent_id);
+ adfs_dir_relse(dir);
+ ret = -EIO;
+ }
+
+ return ret;
+}
+
+static void adfs_dir_mark_dirty(struct adfs_dir *dir)
+{
+ unsigned int i;
+
+ /* Mark the buffers dirty */
+ for (i = 0; i < dir->nr_buffers; i++)
+ mark_buffer_dirty(dir->bhs[i]);
+}
+
+static int adfs_dir_sync(struct adfs_dir *dir)
+{
+ int err = 0;
+ int i;
+
+ for (i = dir->nr_buffers - 1; i >= 0; i--) {
+ struct buffer_head *bh = dir->bhs[i];
+ sync_dirty_buffer(bh);
+ if (buffer_req(bh) && !buffer_uptodate(bh))
+ err = -EIO;
+ }
+
+ return err;
+}
void adfs_object_fixup(struct adfs_dir *dir, struct object_info *obj)
{
@@ -51,87 +235,90 @@ void adfs_object_fixup(struct adfs_dir *dir, struct object_info *obj)
}
}
-static int
-adfs_readdir(struct file *file, struct dir_context *ctx)
+static int adfs_iterate(struct file *file, struct dir_context *ctx)
{
struct inode *inode = file_inode(file);
struct super_block *sb = inode->i_sb;
const struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir;
- struct object_info obj;
struct adfs_dir dir;
- int ret = 0;
-
- if (ctx->pos >> 32)
- return 0;
+ int ret;
- ret = ops->read(sb, inode->i_ino, inode->i_size, &dir);
+ down_read(&adfs_dir_rwsem);
+ ret = adfs_dir_read_inode(sb, inode, &dir);
if (ret)
- return ret;
+ goto unlock;
if (ctx->pos == 0) {
if (!dir_emit_dot(file, ctx))
- goto free_out;
+ goto unlock_relse;
ctx->pos = 1;
}
if (ctx->pos == 1) {
if (!dir_emit(ctx, "..", 2, dir.parent_id, DT_DIR))
- goto free_out;
+ goto unlock_relse;
ctx->pos = 2;
}
- read_lock(&adfs_dir_lock);
+ ret = ops->iterate(&dir, ctx);
- ret = ops->setpos(&dir, ctx->pos - 2);
- if (ret)
- goto unlock_out;
- while (ops->getnext(&dir, &obj) == 0) {
- if (!dir_emit(ctx, obj.name, obj.name_len,
- obj.indaddr, DT_UNKNOWN))
- break;
- ctx->pos++;
- }
-
-unlock_out:
- read_unlock(&adfs_dir_lock);
+unlock_relse:
+ up_read(&adfs_dir_rwsem);
+ adfs_dir_relse(&dir);
+ return ret;
-free_out:
- ops->free(&dir);
+unlock:
+ up_read(&adfs_dir_rwsem);
return ret;
}
int
adfs_dir_update(struct super_block *sb, struct object_info *obj, int wait)
{
- int ret = -EINVAL;
-#ifdef CONFIG_ADFS_FS_RW
const struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir;
struct adfs_dir dir;
+ int ret;
- printk(KERN_INFO "adfs_dir_update: object %06x in dir %06x\n",
- obj->indaddr, obj->parent_id);
+ if (!IS_ENABLED(CONFIG_ADFS_FS_RW))
+ return -EINVAL;
- if (!ops->update) {
- ret = -EINVAL;
- goto out;
- }
+ if (!ops->update)
+ return -EINVAL;
- ret = ops->read(sb, obj->parent_id, 0, &dir);
+ down_write(&adfs_dir_rwsem);
+ ret = adfs_dir_read(sb, obj->parent_id, 0, &dir);
if (ret)
- goto out;
+ goto unlock;
- write_lock(&adfs_dir_lock);
ret = ops->update(&dir, obj);
- write_unlock(&adfs_dir_lock);
+ if (ret)
+ goto forget;
- if (wait) {
- int err = ops->sync(&dir);
- if (!ret)
- ret = err;
- }
+ ret = ops->commit(&dir);
+ if (ret)
+ goto forget;
+ up_write(&adfs_dir_rwsem);
+
+ adfs_dir_mark_dirty(&dir);
+
+ if (wait)
+ ret = adfs_dir_sync(&dir);
+
+ adfs_dir_relse(&dir);
+ return ret;
+
+ /*
+ * If the updated failed because the entry wasn't found, we can
+ * just release the buffers. If it was any other error, forget
+ * the dirtied buffers so they aren't written back to the media.
+ */
+forget:
+ if (ret == -ENOENT)
+ adfs_dir_relse(&dir);
+ else
+ adfs_dir_forget(&dir);
+unlock:
+ up_write(&adfs_dir_rwsem);
- ops->free(&dir);
-out:
-#endif
return ret;
}
@@ -167,25 +354,14 @@ static int adfs_dir_lookup_byname(struct inode *inode, const struct qstr *qstr,
u32 name_len;
int ret;
- ret = ops->read(sb, inode->i_ino, inode->i_size, &dir);
+ down_read(&adfs_dir_rwsem);
+ ret = adfs_dir_read_inode(sb, inode, &dir);
if (ret)
- goto out;
-
- if (ADFS_I(inode)->parent_id != dir.parent_id) {
- adfs_error(sb,
- "parent directory changed under me! (%06x but got %06x)\n",
- ADFS_I(inode)->parent_id, dir.parent_id);
- ret = -EIO;
- goto free_out;
- }
-
- obj->parent_id = inode->i_ino;
-
- read_lock(&adfs_dir_lock);
+ goto unlock;
ret = ops->setpos(&dir, 0);
if (ret)
- goto unlock_out;
+ goto unlock_relse;
ret = -ENOENT;
name = qstr->name;
@@ -196,20 +372,22 @@ static int adfs_dir_lookup_byname(struct inode *inode, const struct qstr *qstr,
break;
}
}
+ obj->parent_id = ADFS_I(inode)->indaddr;
-unlock_out:
- read_unlock(&adfs_dir_lock);
+unlock_relse:
+ up_read(&adfs_dir_rwsem);
+ adfs_dir_relse(&dir);
+ return ret;
-free_out:
- ops->free(&dir);
-out:
+unlock:
+ up_read(&adfs_dir_rwsem);
return ret;
}
const struct file_operations adfs_dir_operations = {
.read = generic_read_dir,
.llseek = generic_file_llseek,
- .iterate = adfs_readdir,
+ .iterate_shared = adfs_iterate,
.fsync = generic_file_fsync,
};
diff --git a/fs/adfs/dir_f.c b/fs/adfs/dir_f.c
index c1a950c7400a..30d526fecc3f 100644
--- a/fs/adfs/dir_f.c
+++ b/fs/adfs/dir_f.c
@@ -9,8 +9,6 @@
#include "adfs.h"
#include "dir_f.h"
-static void adfs_f_free(struct adfs_dir *dir);
-
/*
* Read an (unaligned) value of length 1..4 bytes
*/
@@ -60,7 +58,7 @@ static inline void adfs_writeval(unsigned char *p, int len, unsigned int val)
#define bufoff(_bh,_idx) \
({ int _buf = _idx >> blocksize_bits; \
int _off = _idx - (_buf << blocksize_bits);\
- (u8 *)(_bh[_buf]->b_data + _off); \
+ (void *)(_bh[_buf]->b_data + _off); \
})
/*
@@ -123,65 +121,49 @@ adfs_dir_checkbyte(const struct adfs_dir *dir)
return (dircheck ^ (dircheck >> 8) ^ (dircheck >> 16) ^ (dircheck >> 24)) & 0xff;
}
-/* Read and check that a directory is valid */
-static int adfs_dir_read(struct super_block *sb, u32 indaddr,
- unsigned int size, struct adfs_dir *dir)
+static int adfs_f_validate(struct adfs_dir *dir)
{
- const unsigned int blocksize_bits = sb->s_blocksize_bits;
- int blk = 0;
-
- /*
- * Directories which are not a multiple of 2048 bytes
- * are considered bad v2 [3.6]
- */
- if (size & 2047)
- goto bad_dir;
-
- size >>= blocksize_bits;
-
- dir->nr_buffers = 0;
- dir->sb = sb;
-
- for (blk = 0; blk < size; blk++) {
- int phys;
+ struct adfs_dirheader *head = dir->dirhead;
+ struct adfs_newdirtail *tail = dir->newtail;
+
+ if (head->startmasseq != tail->endmasseq ||
+ tail->dirlastmask || tail->reserved[0] || tail->reserved[1] ||
+ (memcmp(&head->startname, "Nick", 4) &&
+ memcmp(&head->startname, "Hugo", 4)) ||
+ memcmp(&head->startname, &tail->endname, 4) ||
+ adfs_dir_checkbyte(dir) != tail->dircheckbyte)
+ return -EIO;
- phys = __adfs_block_map(sb, indaddr, blk);
- if (!phys) {
- adfs_error(sb, "dir %06x has a hole at offset %d",
- indaddr, blk);
- goto release_buffers;
- }
+ return 0;
+}
- dir->bh[blk] = sb_bread(sb, phys);
- if (!dir->bh[blk])
- goto release_buffers;
- }
+/* Read and check that a directory is valid */
+static int adfs_f_read(struct super_block *sb, u32 indaddr, unsigned int size,
+ struct adfs_dir *dir)
+{
+ const unsigned int blocksize_bits = sb->s_blocksize_bits;
+ int ret;
- memcpy(&dir->dirhead, bufoff(dir->bh, 0), sizeof(dir->dirhead));
- memcpy(&dir->dirtail, bufoff(dir->bh, 2007), sizeof(dir->dirtail));
+ if (size && size != ADFS_NEWDIR_SIZE)
+ return -EIO;
- if (dir->dirhead.startmasseq != dir->dirtail.new.endmasseq ||
- memcmp(&dir->dirhead.startname, &dir->dirtail.new.endname, 4))
- goto bad_dir;
+ ret = adfs_dir_read_buffers(sb, indaddr, ADFS_NEWDIR_SIZE, dir);
+ if (ret)
+ return ret;
- if (memcmp(&dir->dirhead.startname, "Nick", 4) &&
- memcmp(&dir->dirhead.startname, "Hugo", 4))
- goto bad_dir;
+ dir->dirhead = bufoff(dir->bh, 0);
+ dir->newtail = bufoff(dir->bh, 2007);
- if (adfs_dir_checkbyte(dir) != dir->dirtail.new.dircheckbyte)
+ if (adfs_f_validate(dir))
goto bad_dir;
- dir->nr_buffers = blk;
+ dir->parent_id = adfs_readval(dir->newtail->dirparent, 3);
return 0;
bad_dir:
adfs_error(sb, "dir %06x is corrupted", indaddr);
-release_buffers:
- for (blk -= 1; blk >= 0; blk -= 1)
- brelse(dir->bh[blk]);
-
- dir->sb = NULL;
+ adfs_dir_relse(dir);
return -EIO;
}
@@ -232,24 +214,12 @@ adfs_obj2dir(struct adfs_direntry *de, struct object_info *obj)
static int
__adfs_dir_get(struct adfs_dir *dir, int pos, struct object_info *obj)
{
- struct super_block *sb = dir->sb;
struct adfs_direntry de;
- int thissize, buffer, offset;
-
- buffer = pos >> sb->s_blocksize_bits;
-
- if (buffer > dir->nr_buffers)
- return -EINVAL;
-
- offset = pos & (sb->s_blocksize - 1);
- thissize = sb->s_blocksize - offset;
- if (thissize > 26)
- thissize = 26;
+ int ret;
- memcpy(&de, dir->bh[buffer]->b_data + offset, thissize);
- if (thissize != 26)
- memcpy(((char *)&de) + thissize, dir->bh[buffer + 1]->b_data,
- 26 - thissize);
+ ret = adfs_dir_copyfrom(&de, dir, pos, 26);
+ if (ret)
+ return ret;
if (!de.dirobname[0])
return -ENOENT;
@@ -260,89 +230,6 @@ __adfs_dir_get(struct adfs_dir *dir, int pos, struct object_info *obj)
}
static int
-__adfs_dir_put(struct adfs_dir *dir, int pos, struct object_info *obj)
-{
- struct super_block *sb = dir->sb;
- struct adfs_direntry de;
- int thissize, buffer, offset;
-
- buffer = pos >> sb->s_blocksize_bits;
-
- if (buffer > dir->nr_buffers)
- return -EINVAL;
-
- offset = pos & (sb->s_blocksize - 1);
- thissize = sb->s_blocksize - offset;
- if (thissize > 26)
- thissize = 26;
-
- /*
- * Get the entry in total
- */
- memcpy(&de, dir->bh[buffer]->b_data + offset, thissize);
- if (thissize != 26)
- memcpy(((char *)&de) + thissize, dir->bh[buffer + 1]->b_data,
- 26 - thissize);
-
- /*
- * update it
- */
- adfs_obj2dir(&de, obj);
-
- /*
- * Put the new entry back
- */
- memcpy(dir->bh[buffer]->b_data + offset, &de, thissize);
- if (thissize != 26)
- memcpy(dir->bh[buffer + 1]->b_data, ((char *)&de) + thissize,
- 26 - thissize);
-
- return 0;
-}
-
-/*
- * the caller is responsible for holding the necessary
- * locks.
- */
-static int adfs_dir_find_entry(struct adfs_dir *dir, u32 indaddr)
-{
- int pos, ret;
-
- ret = -ENOENT;
-
- for (pos = 5; pos < ADFS_NUM_DIR_ENTRIES * 26 + 5; pos += 26) {
- struct object_info obj;
-
- if (!__adfs_dir_get(dir, pos, &obj))
- break;
-
- if (obj.indaddr == indaddr) {
- ret = pos;
- break;
- }
- }
-
- return ret;
-}
-
-static int adfs_f_read(struct super_block *sb, u32 indaddr, unsigned int size,
- struct adfs_dir *dir)
-{
- int ret;
-
- if (size != ADFS_NEWDIR_SIZE)
- return -EIO;
-
- ret = adfs_dir_read(sb, indaddr, size, dir);
- if (ret)
- adfs_error(sb, "unable to read directory");
- else
- dir->parent_id = adfs_readval(dir->dirtail.new.dirparent, 3);
-
- return ret;
-}
-
-static int
adfs_f_setpos(struct adfs_dir *dir, unsigned int fpos)
{
if (fpos >= ADFS_NUM_DIR_ENTRIES)
@@ -364,99 +251,74 @@ adfs_f_getnext(struct adfs_dir *dir, struct object_info *obj)
return ret;
}
-static int
-adfs_f_update(struct adfs_dir *dir, struct object_info *obj)
+static int adfs_f_iterate(struct adfs_dir *dir, struct dir_context *ctx)
{
- struct super_block *sb = dir->sb;
- int ret, i;
+ struct object_info obj;
+ int pos = 5 + (ctx->pos - 2) * 26;
- ret = adfs_dir_find_entry(dir, obj->indaddr);
- if (ret < 0) {
- adfs_error(dir->sb, "unable to locate entry to update");
- goto out;
+ while (ctx->pos < 2 + ADFS_NUM_DIR_ENTRIES) {
+ if (__adfs_dir_get(dir, pos, &obj))
+ break;
+ if (!dir_emit(ctx, obj.name, obj.name_len,
+ obj.indaddr, DT_UNKNOWN))
+ break;
+ pos += 26;
+ ctx->pos++;
}
+ return 0;
+}
- __adfs_dir_put(dir, ret, obj);
-
- /*
- * Increment directory sequence number
- */
- dir->bh[0]->b_data[0] += 1;
- dir->bh[dir->nr_buffers - 1]->b_data[sb->s_blocksize - 6] += 1;
-
- ret = adfs_dir_checkbyte(dir);
- /*
- * Update directory check byte
- */
- dir->bh[dir->nr_buffers - 1]->b_data[sb->s_blocksize - 1] = ret;
-
-#if 1
- {
- const unsigned int blocksize_bits = sb->s_blocksize_bits;
-
- memcpy(&dir->dirhead, bufoff(dir->bh, 0), sizeof(dir->dirhead));
- memcpy(&dir->dirtail, bufoff(dir->bh, 2007), sizeof(dir->dirtail));
+static int adfs_f_update(struct adfs_dir *dir, struct object_info *obj)
+{
+ struct adfs_direntry de;
+ int offset, ret;
- if (dir->dirhead.startmasseq != dir->dirtail.new.endmasseq ||
- memcmp(&dir->dirhead.startname, &dir->dirtail.new.endname, 4))
- goto bad_dir;
+ offset = 5 - (int)sizeof(de);
- if (memcmp(&dir->dirhead.startname, "Nick", 4) &&
- memcmp(&dir->dirhead.startname, "Hugo", 4))
- goto bad_dir;
+ do {
+ offset += sizeof(de);
+ ret = adfs_dir_copyfrom(&de, dir, offset, sizeof(de));
+ if (ret) {
+ adfs_error(dir->sb, "error reading directory entry");
+ return -ENOENT;
+ }
+ if (!de.dirobname[0]) {
+ adfs_error(dir->sb, "unable to locate entry to update");
+ return -ENOENT;
+ }
+ } while (adfs_readval(de.dirinddiscadd, 3) != obj->indaddr);
- if (adfs_dir_checkbyte(dir) != dir->dirtail.new.dircheckbyte)
- goto bad_dir;
- }
-#endif
- for (i = dir->nr_buffers - 1; i >= 0; i--)
- mark_buffer_dirty(dir->bh[i]);
+ /* Update the directory entry with the new object state */
+ adfs_obj2dir(&de, obj);
- ret = 0;
-out:
- return ret;
-#if 1
-bad_dir:
- adfs_error(dir->sb, "whoops! I broke a directory!");
- return -EIO;
-#endif
+ /* Write the directory entry back to the directory */
+ return adfs_dir_copyto(dir, offset, &de, 26);
}
-static int
-adfs_f_sync(struct adfs_dir *dir)
+static int adfs_f_commit(struct adfs_dir *dir)
{
- int err = 0;
- int i;
-
- for (i = dir->nr_buffers - 1; i >= 0; i--) {
- struct buffer_head *bh = dir->bh[i];
- sync_dirty_buffer(bh);
- if (buffer_req(bh) && !buffer_uptodate(bh))
- err = -EIO;
- }
+ int ret;
- return err;
-}
+ /* Increment directory sequence number */
+ dir->dirhead->startmasseq += 1;
+ dir->newtail->endmasseq += 1;
-static void
-adfs_f_free(struct adfs_dir *dir)
-{
- int i;
+ /* Update directory check byte */
+ dir->newtail->dircheckbyte = adfs_dir_checkbyte(dir);
- for (i = dir->nr_buffers - 1; i >= 0; i--) {
- brelse(dir->bh[i]);
- dir->bh[i] = NULL;
- }
+ /* Make sure the directory still validates correctly */
+ ret = adfs_f_validate(dir);
+ if (ret)
+ adfs_msg(dir->sb, KERN_ERR, "error: update broke directory");
- dir->nr_buffers = 0;
- dir->sb = NULL;
+ return ret;
}
const struct adfs_dir_ops adfs_f_dir_ops = {
.read = adfs_f_read,
+ .iterate = adfs_f_iterate,
.setpos = adfs_f_setpos,
.getnext = adfs_f_getnext,
.update = adfs_f_update,
- .sync = adfs_f_sync,
- .free = adfs_f_free
+ .commit = adfs_f_commit,
};
diff --git a/fs/adfs/dir_f.h b/fs/adfs/dir_f.h
index 5aec332b90f5..a5393e6cf9f4 100644
--- a/fs/adfs/dir_f.h
+++ b/fs/adfs/dir_f.h
@@ -13,9 +13,9 @@
* Directory header
*/
struct adfs_dirheader {
- unsigned char startmasseq;
- unsigned char startname[4];
-};
+ __u8 startmasseq;
+ __u8 startname[4];
+} __attribute__((packed));
#define ADFS_NEWDIR_SIZE 2048
#define ADFS_NUM_DIR_ENTRIES 77
@@ -31,32 +31,36 @@ struct adfs_direntry {
__u8 dirlen[4];
__u8 dirinddiscadd[3];
__u8 newdiratts;
-};
+} __attribute__((packed));
/*
* Directory tail
*/
+struct adfs_olddirtail {
+ __u8 dirlastmask;
+ char dirname[10];
+ __u8 dirparent[3];
+ char dirtitle[19];
+ __u8 reserved[14];
+ __u8 endmasseq;
+ __u8 endname[4];
+ __u8 dircheckbyte;
+} __attribute__((packed));
+
+struct adfs_newdirtail {
+ __u8 dirlastmask;
+ __u8 reserved[2];
+ __u8 dirparent[3];
+ char dirtitle[19];
+ char dirname[10];
+ __u8 endmasseq;
+ __u8 endname[4];
+ __u8 dircheckbyte;
+} __attribute__((packed));
+
union adfs_dirtail {
- struct {
- unsigned char dirlastmask;
- char dirname[10];
- unsigned char dirparent[3];
- char dirtitle[19];
- unsigned char reserved[14];
- unsigned char endmasseq;
- unsigned char endname[4];
- unsigned char dircheckbyte;
- } old;
- struct {
- unsigned char dirlastmask;
- unsigned char reserved[2];
- unsigned char dirparent[3];
- char dirtitle[19];
- char dirname[10];
- unsigned char endmasseq;
- unsigned char endname[4];
- unsigned char dircheckbyte;
- } new;
+ struct adfs_olddirtail old;
+ struct adfs_newdirtail new;
};
#endif
diff --git a/fs/adfs/dir_fplus.c b/fs/adfs/dir_fplus.c
index d56924c11b17..4a15924014da 100644
--- a/fs/adfs/dir_fplus.c
+++ b/fs/adfs/dir_fplus.c
@@ -4,123 +4,163 @@
*
* Copyright (C) 1997-1999 Russell King
*/
-#include <linux/slab.h>
#include "adfs.h"
#include "dir_fplus.h"
-static int
-adfs_fplus_read(struct super_block *sb, unsigned int id, unsigned int sz, struct adfs_dir *dir)
+/* Return the byte offset to directory entry pos */
+static unsigned int adfs_fplus_offset(const struct adfs_bigdirheader *h,
+ unsigned int pos)
{
- struct adfs_bigdirheader *h;
- struct adfs_bigdirtail *t;
- unsigned long block;
- unsigned int blk, size;
- int i, ret = -EIO;
+ return offsetof(struct adfs_bigdirheader, bigdirname) +
+ ALIGN(le32_to_cpu(h->bigdirnamelen), 4) +
+ pos * sizeof(struct adfs_bigdirentry);
+}
- dir->nr_buffers = 0;
+static int adfs_fplus_validate_header(const struct adfs_bigdirheader *h)
+{
+ unsigned int size = le32_to_cpu(h->bigdirsize);
+ unsigned int len;
- /* start off using fixed bh set - only alloc for big dirs */
- dir->bh_fplus = &dir->bh[0];
+ if (h->bigdirversion[0] != 0 || h->bigdirversion[1] != 0 ||
+ h->bigdirversion[2] != 0 ||
+ h->bigdirstartname != cpu_to_le32(BIGDIRSTARTNAME) ||
+ !size || size & 2047 || size > SZ_4M)
+ return -EIO;
- block = __adfs_block_map(sb, id, 0);
- if (!block) {
- adfs_error(sb, "dir object %X has a hole at offset 0", id);
- goto out;
- }
+ size -= sizeof(struct adfs_bigdirtail) +
+ offsetof(struct adfs_bigdirheader, bigdirname);
- dir->bh_fplus[0] = sb_bread(sb, block);
- if (!dir->bh_fplus[0])
- goto out;
- dir->nr_buffers += 1;
+ /* Check that bigdirnamelen fits within the directory */
+ len = ALIGN(le32_to_cpu(h->bigdirnamelen), 4);
+ if (len > size)
+ return -EIO;
- h = (struct adfs_bigdirheader *)dir->bh_fplus[0]->b_data;
- size = le32_to_cpu(h->bigdirsize);
- if (size != sz) {
- adfs_msg(sb, KERN_WARNING,
- "directory header size %X does not match directory size %X",
- size, sz);
+ size -= len;
+
+ /* Check that bigdirnamesize fits within the directory */
+ len = le32_to_cpu(h->bigdirnamesize);
+ if (len > size)
+ return -EIO;
+
+ size -= len;
+
+ /*
+ * Avoid division, we know that absolute maximum number of entries
+ * can not be so large to cause overflow of the multiplication below.
+ */
+ len = le32_to_cpu(h->bigdirentries);
+ if (len > SZ_4M / sizeof(struct adfs_bigdirentry) ||
+ len * sizeof(struct adfs_bigdirentry) > size)
+ return -EIO;
+
+ return 0;
+}
+
+static int adfs_fplus_validate_tail(const struct adfs_bigdirheader *h,
+ const struct adfs_bigdirtail *t)
+{
+ if (t->bigdirendname != cpu_to_le32(BIGDIRENDNAME) ||
+ t->bigdirendmasseq != h->startmasseq ||
+ t->reserved[0] != 0 || t->reserved[1] != 0)
+ return -EIO;
+
+ return 0;
+}
+
+static u8 adfs_fplus_checkbyte(struct adfs_dir *dir)
+{
+ struct adfs_bigdirheader *h = dir->bighead;
+ struct adfs_bigdirtail *t = dir->bigtail;
+ unsigned int end, bs, bi, i;
+ __le32 *bp;
+ u32 dircheck;
+
+ end = adfs_fplus_offset(h, le32_to_cpu(h->bigdirentries)) +
+ le32_to_cpu(h->bigdirnamesize);
+
+ /* Accumulate the contents of the header, entries and names */
+ for (dircheck = 0, bi = 0; end; bi++) {
+ bp = (void *)dir->bhs[bi]->b_data;
+ bs = dir->bhs[bi]->b_size;
+ if (bs > end)
+ bs = end;
+
+ for (i = 0; i < bs; i += sizeof(u32))
+ dircheck = ror32(dircheck, 13) ^ le32_to_cpup(bp++);
+
+ end -= bs;
}
- if (h->bigdirversion[0] != 0 || h->bigdirversion[1] != 0 ||
- h->bigdirversion[2] != 0 || size & 2047 ||
- h->bigdirstartname != cpu_to_le32(BIGDIRSTARTNAME)) {
- adfs_error(sb, "dir %06x has malformed header", id);
+ /* Accumulate the contents of the tail except for the check byte */
+ dircheck = ror32(dircheck, 13) ^ le32_to_cpu(t->bigdirendname);
+ dircheck = ror32(dircheck, 13) ^ t->bigdirendmasseq;
+ dircheck = ror32(dircheck, 13) ^ t->reserved[0];
+ dircheck = ror32(dircheck, 13) ^ t->reserved[1];
+
+ return dircheck ^ dircheck >> 8 ^ dircheck >> 16 ^ dircheck >> 24;
+}
+
+static int adfs_fplus_read(struct super_block *sb, u32 indaddr,
+ unsigned int size, struct adfs_dir *dir)
+{
+ struct adfs_bigdirheader *h;
+ struct adfs_bigdirtail *t;
+ unsigned int dirsize;
+ int ret;
+
+ /* Read first buffer */
+ ret = adfs_dir_read_buffers(sb, indaddr, sb->s_blocksize, dir);
+ if (ret)
+ return ret;
+
+ dir->bighead = h = (void *)dir->bhs[0]->b_data;
+ ret = adfs_fplus_validate_header(h);
+ if (ret) {
+ adfs_error(sb, "dir %06x has malformed header", indaddr);
goto out;
}
- size >>= sb->s_blocksize_bits;
- if (size > ARRAY_SIZE(dir->bh)) {
- /* this directory is too big for fixed bh set, must allocate */
- struct buffer_head **bh_fplus =
- kcalloc(size, sizeof(struct buffer_head *),
- GFP_KERNEL);
- if (!bh_fplus) {
- adfs_msg(sb, KERN_ERR,
- "not enough memory for dir object %X (%d blocks)",
- id, size);
- ret = -ENOMEM;
- goto out;
- }
- dir->bh_fplus = bh_fplus;
- /* copy over the pointer to the block that we've already read */
- dir->bh_fplus[0] = dir->bh[0];
+ dirsize = le32_to_cpu(h->bigdirsize);
+ if (size && dirsize != size) {
+ adfs_msg(sb, KERN_WARNING,
+ "dir %06x header size %X does not match directory size %X",
+ indaddr, dirsize, size);
}
- for (blk = 1; blk < size; blk++) {
- block = __adfs_block_map(sb, id, blk);
- if (!block) {
- adfs_error(sb, "dir object %X has a hole at offset %d", id, blk);
- goto out;
- }
+ /* Read remaining buffers */
+ ret = adfs_dir_read_buffers(sb, indaddr, dirsize, dir);
+ if (ret)
+ return ret;
- dir->bh_fplus[blk] = sb_bread(sb, block);
- if (!dir->bh_fplus[blk]) {
- adfs_error(sb, "dir object %x failed read for offset %d, mapped block %lX",
- id, blk, block);
- goto out;
- }
+ dir->bigtail = t = (struct adfs_bigdirtail *)
+ (dir->bhs[dir->nr_buffers - 1]->b_data + (sb->s_blocksize - 8));
- dir->nr_buffers += 1;
+ ret = adfs_fplus_validate_tail(h, t);
+ if (ret) {
+ adfs_error(sb, "dir %06x has malformed tail", indaddr);
+ goto out;
}
- t = (struct adfs_bigdirtail *)
- (dir->bh_fplus[size - 1]->b_data + (sb->s_blocksize - 8));
-
- if (t->bigdirendname != cpu_to_le32(BIGDIRENDNAME) ||
- t->bigdirendmasseq != h->startmasseq ||
- t->reserved[0] != 0 || t->reserved[1] != 0) {
- adfs_error(sb, "dir %06x has malformed tail", id);
+ if (adfs_fplus_checkbyte(dir) != t->bigdircheckbyte) {
+ adfs_error(sb, "dir %06x checkbyte mismatch\n", indaddr);
goto out;
}
dir->parent_id = le32_to_cpu(h->bigdirparent);
- dir->sb = sb;
return 0;
out:
- if (dir->bh_fplus) {
- for (i = 0; i < dir->nr_buffers; i++)
- brelse(dir->bh_fplus[i]);
-
- if (&dir->bh[0] != dir->bh_fplus)
- kfree(dir->bh_fplus);
+ adfs_dir_relse(dir);
- dir->bh_fplus = NULL;
- }
-
- dir->nr_buffers = 0;
- dir->sb = NULL;
return ret;
}
static int
adfs_fplus_setpos(struct adfs_dir *dir, unsigned int fpos)
{
- struct adfs_bigdirheader *h =
- (struct adfs_bigdirheader *) dir->bh_fplus[0]->b_data;
int ret = -ENOENT;
- if (fpos <= le32_to_cpu(h->bigdirentries)) {
+ if (fpos <= le32_to_cpu(dir->bighead->bigdirentries)) {
dir->pos = fpos;
ret = 0;
}
@@ -128,51 +168,23 @@ adfs_fplus_setpos(struct adfs_dir *dir, unsigned int fpos)
return ret;
}
-static void
-dir_memcpy(struct adfs_dir *dir, unsigned int offset, void *to, int len)
-{
- struct super_block *sb = dir->sb;
- unsigned int buffer, partial, remainder;
-
- buffer = offset >> sb->s_blocksize_bits;
- offset &= sb->s_blocksize - 1;
-
- partial = sb->s_blocksize - offset;
-
- if (partial >= len)
- memcpy(to, dir->bh_fplus[buffer]->b_data + offset, len);
- else {
- char *c = (char *)to;
-
- remainder = len - partial;
-
- memcpy(c,
- dir->bh_fplus[buffer]->b_data + offset,
- partial);
-
- memcpy(c + partial,
- dir->bh_fplus[buffer + 1]->b_data,
- remainder);
- }
-}
-
static int
adfs_fplus_getnext(struct adfs_dir *dir, struct object_info *obj)
{
- struct adfs_bigdirheader *h =
- (struct adfs_bigdirheader *) dir->bh_fplus[0]->b_data;
+ struct adfs_bigdirheader *h = dir->bighead;
struct adfs_bigdirentry bde;
unsigned int offset;
- int ret = -ENOENT;
+ int ret;
if (dir->pos >= le32_to_cpu(h->bigdirentries))
- goto out;
+ return -ENOENT;
- offset = offsetof(struct adfs_bigdirheader, bigdirname);
- offset += ((le32_to_cpu(h->bigdirnamelen) + 4) & ~3);
- offset += dir->pos * sizeof(struct adfs_bigdirentry);
+ offset = adfs_fplus_offset(h, dir->pos);
- dir_memcpy(dir, offset, &bde, sizeof(struct adfs_bigdirentry));
+ ret = adfs_dir_copyfrom(&bde, dir, offset,
+ sizeof(struct adfs_bigdirentry));
+ if (ret)
+ return ret;
obj->loadaddr = le32_to_cpu(bde.bigdirload);
obj->execaddr = le32_to_cpu(bde.bigdirexec);
@@ -181,59 +193,95 @@ adfs_fplus_getnext(struct adfs_dir *dir, struct object_info *obj)
obj->attr = le32_to_cpu(bde.bigdirattr);
obj->name_len = le32_to_cpu(bde.bigdirobnamelen);
- offset = offsetof(struct adfs_bigdirheader, bigdirname);
- offset += ((le32_to_cpu(h->bigdirnamelen) + 4) & ~3);
- offset += le32_to_cpu(h->bigdirentries) * sizeof(struct adfs_bigdirentry);
+ offset = adfs_fplus_offset(h, le32_to_cpu(h->bigdirentries));
offset += le32_to_cpu(bde.bigdirobnameptr);
- dir_memcpy(dir, offset, obj->name, obj->name_len);
+ ret = adfs_dir_copyfrom(obj->name, dir, offset, obj->name_len);
+ if (ret)
+ return ret;
+
adfs_object_fixup(dir, obj);
dir->pos += 1;
- ret = 0;
-out:
- return ret;
+
+ return 0;
}
-static int
-adfs_fplus_sync(struct adfs_dir *dir)
+static int adfs_fplus_iterate(struct adfs_dir *dir, struct dir_context *ctx)
{
- int err = 0;
- int i;
-
- for (i = dir->nr_buffers - 1; i >= 0; i--) {
- struct buffer_head *bh = dir->bh_fplus[i];
- sync_dirty_buffer(bh);
- if (buffer_req(bh) && !buffer_uptodate(bh))
- err = -EIO;
+ struct object_info obj;
+
+ if ((ctx->pos - 2) >> 32)
+ return 0;
+
+ if (adfs_fplus_setpos(dir, ctx->pos - 2))
+ return 0;
+
+ while (!adfs_fplus_getnext(dir, &obj)) {
+ if (!dir_emit(ctx, obj.name, obj.name_len,
+ obj.indaddr, DT_UNKNOWN))
+ break;
+ ctx->pos++;
}
- return err;
+ return 0;
}
-static void
-adfs_fplus_free(struct adfs_dir *dir)
+static int adfs_fplus_update(struct adfs_dir *dir, struct object_info *obj)
{
- int i;
+ struct adfs_bigdirheader *h = dir->bighead;
+ struct adfs_bigdirentry bde;
+ int offset, end, ret;
- if (dir->bh_fplus) {
- for (i = 0; i < dir->nr_buffers; i++)
- brelse(dir->bh_fplus[i]);
+ offset = adfs_fplus_offset(h, 0) - sizeof(bde);
+ end = adfs_fplus_offset(h, le32_to_cpu(h->bigdirentries));
- if (&dir->bh[0] != dir->bh_fplus)
- kfree(dir->bh_fplus);
+ do {
+ offset += sizeof(bde);
+ if (offset >= end) {
+ adfs_error(dir->sb, "unable to locate entry to update");
+ return -ENOENT;
+ }
+ ret = adfs_dir_copyfrom(&bde, dir, offset, sizeof(bde));
+ if (ret) {
+ adfs_error(dir->sb, "error reading directory entry");
+ return -ENOENT;
+ }
+ } while (le32_to_cpu(bde.bigdirindaddr) != obj->indaddr);
- dir->bh_fplus = NULL;
- }
+ bde.bigdirload = cpu_to_le32(obj->loadaddr);
+ bde.bigdirexec = cpu_to_le32(obj->execaddr);
+ bde.bigdirlen = cpu_to_le32(obj->size);
+ bde.bigdirindaddr = cpu_to_le32(obj->indaddr);
+ bde.bigdirattr = cpu_to_le32(obj->attr);
+
+ return adfs_dir_copyto(dir, offset, &bde, sizeof(bde));
+}
+
+static int adfs_fplus_commit(struct adfs_dir *dir)
+{
+ int ret;
- dir->nr_buffers = 0;
- dir->sb = NULL;
+ /* Increment directory sequence number */
+ dir->bighead->startmasseq += 1;
+ dir->bigtail->bigdirendmasseq += 1;
+
+ /* Update directory check byte */
+ dir->bigtail->bigdircheckbyte = adfs_fplus_checkbyte(dir);
+
+ /* Make sure the directory still validates correctly */
+ ret = adfs_fplus_validate_header(dir->bighead);
+ if (ret == 0)
+ ret = adfs_fplus_validate_tail(dir->bighead, dir->bigtail);
+
+ return ret;
}
const struct adfs_dir_ops adfs_fplus_dir_ops = {
.read = adfs_fplus_read,
+ .iterate = adfs_fplus_iterate,
.setpos = adfs_fplus_setpos,
.getnext = adfs_fplus_getnext,
- .sync = adfs_fplus_sync,
- .free = adfs_fplus_free
+ .update = adfs_fplus_update,
+ .commit = adfs_fplus_commit,
};
diff --git a/fs/adfs/dir_fplus.h b/fs/adfs/dir_fplus.h
index 4ec0931e36ad..d729b1591e5e 100644
--- a/fs/adfs/dir_fplus.h
+++ b/fs/adfs/dir_fplus.h
@@ -22,7 +22,7 @@ struct adfs_bigdirheader {
__le32 bigdirnamesize;
__le32 bigdirparent;
char bigdirname[1];
-};
+} __attribute__((packed, aligned(4)));
struct adfs_bigdirentry {
__le32 bigdirload;
@@ -32,11 +32,11 @@ struct adfs_bigdirentry {
__le32 bigdirattr;
__le32 bigdirobnamelen;
__le32 bigdirobnameptr;
-};
+} __attribute__((packed, aligned(4)));
struct adfs_bigdirtail {
__le32 bigdirendname;
__u8 bigdirendmasseq;
__u8 reserved[2];
__u8 bigdircheckbyte;
-};
+} __attribute__((packed, aligned(4)));
diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c
index 124de75413a5..32620f4a7623 100644
--- a/fs/adfs/inode.c
+++ b/fs/adfs/inode.c
@@ -20,7 +20,8 @@ adfs_get_block(struct inode *inode, sector_t block, struct buffer_head *bh,
if (block >= inode->i_blocks)
goto abort_toobig;
- block = __adfs_block_map(inode->i_sb, inode->i_ino, block);
+ block = __adfs_block_map(inode->i_sb, ADFS_I(inode)->indaddr,
+ block);
if (block)
map_bh(bh, inode->i_sb, block);
return 0;
@@ -126,29 +127,29 @@ adfs_atts2mode(struct super_block *sb, struct inode *inode)
* Convert Linux permission to ADFS attribute. We try to do the reverse
* of atts2mode, but there is not a 1:1 translation.
*/
-static int
-adfs_mode2atts(struct super_block *sb, struct inode *inode)
+static int adfs_mode2atts(struct super_block *sb, struct inode *inode,
+ umode_t ia_mode)
{
+ struct adfs_sb_info *asb = ADFS_SB(sb);
umode_t mode;
int attr;
- struct adfs_sb_info *asb = ADFS_SB(sb);
/* FIXME: should we be able to alter a link? */
if (S_ISLNK(inode->i_mode))
return ADFS_I(inode)->attr;
+ /* Directories do not have read/write permissions on the media */
if (S_ISDIR(inode->i_mode))
- attr = ADFS_NDA_DIRECTORY;
- else
- attr = 0;
+ return ADFS_NDA_DIRECTORY;
- mode = inode->i_mode & asb->s_owner_mask;
+ attr = 0;
+ mode = ia_mode & asb->s_owner_mask;
if (mode & S_IRUGO)
attr |= ADFS_NDA_OWNER_READ;
if (mode & S_IWUGO)
attr |= ADFS_NDA_OWNER_WRITE;
- mode = inode->i_mode & asb->s_other_mask;
+ mode = ia_mode & asb->s_other_mask;
mode &= ~asb->s_owner_mask;
if (mode & S_IRUGO)
attr |= ADFS_NDA_PUBLIC_READ;
@@ -158,6 +159,8 @@ adfs_mode2atts(struct super_block *sb, struct inode *inode)
return attr;
}
+static const s64 nsec_unix_epoch_diff_risc_os_epoch = 2208988800000000000LL;
+
/*
* Convert an ADFS time to Unix time. ADFS has a 40-bit centi-second time
* referenced to 1 Jan 1900 (til 2248) so we need to discard 2208988800 seconds
@@ -170,8 +173,6 @@ adfs_adfs2unix_time(struct timespec64 *tv, struct inode *inode)
/* 01 Jan 1970 00:00:00 (Unix epoch) as nanoseconds since
* 01 Jan 1900 00:00:00 (RISC OS epoch)
*/
- static const s64 nsec_unix_epoch_diff_risc_os_epoch =
- 2208988800000000000LL;
s64 nsec;
if (!adfs_inode_is_stamped(inode))
@@ -204,24 +205,23 @@ adfs_adfs2unix_time(struct timespec64 *tv, struct inode *inode)
return;
}
-/*
- * Convert an Unix time to ADFS time. We only do this if the entry has a
- * time/date stamp already.
- */
-static void
-adfs_unix2adfs_time(struct inode *inode, unsigned int secs)
+/* Convert an Unix time to ADFS time for an entry that is already stamped. */
+static void adfs_unix2adfs_time(struct inode *inode,
+ const struct timespec64 *ts)
{
- unsigned int high, low;
+ s64 cs, nsec = timespec64_to_ns(ts);
- if (adfs_inode_is_stamped(inode)) {
- /* convert 32-bit seconds to 40-bit centi-seconds */
- low = (secs & 255) * 100;
- high = (secs / 256) * 100 + (low >> 8) + 0x336e996a;
+ /* convert from Unix to RISC OS epoch */
+ nsec += nsec_unix_epoch_diff_risc_os_epoch;
- ADFS_I(inode)->loadaddr = (high >> 24) |
- (ADFS_I(inode)->loadaddr & ~0xff);
- ADFS_I(inode)->execaddr = (low & 255) | (high << 8);
- }
+ /* convert from nanoseconds to centiseconds */
+ cs = div_s64(nsec, 10000000);
+
+ cs = clamp_t(s64, cs, 0, 0xffffffffff);
+
+ ADFS_I(inode)->loadaddr &= ~0xff;
+ ADFS_I(inode)->loadaddr |= (cs >> 32) & 0xff;
+ ADFS_I(inode)->execaddr = cs;
}
/*
@@ -260,6 +260,7 @@ adfs_iget(struct super_block *sb, struct object_info *obj)
* for cross-directory renames.
*/
ADFS_I(inode)->parent_id = obj->parent_id;
+ ADFS_I(inode)->indaddr = obj->indaddr;
ADFS_I(inode)->loadaddr = obj->loadaddr;
ADFS_I(inode)->execaddr = obj->execaddr;
ADFS_I(inode)->attr = obj->attr;
@@ -315,10 +316,11 @@ adfs_notify_change(struct dentry *dentry, struct iattr *attr)
if (ia_valid & ATTR_SIZE)
truncate_setsize(inode, attr->ia_size);
- if (ia_valid & ATTR_MTIME) {
- inode->i_mtime = attr->ia_mtime;
- adfs_unix2adfs_time(inode, attr->ia_mtime.tv_sec);
+ if (ia_valid & ATTR_MTIME && adfs_inode_is_stamped(inode)) {
+ adfs_unix2adfs_time(inode, &attr->ia_mtime);
+ adfs_adfs2unix_time(&inode->i_mtime, inode);
}
+
/*
* FIXME: should we make these == to i_mtime since we don't
* have the ability to represent them in our filesystem?
@@ -328,7 +330,7 @@ adfs_notify_change(struct dentry *dentry, struct iattr *attr)
if (ia_valid & ATTR_CTIME)
inode->i_ctime = attr->ia_ctime;
if (ia_valid & ATTR_MODE) {
- ADFS_I(inode)->attr = adfs_mode2atts(sb, inode);
+ ADFS_I(inode)->attr = adfs_mode2atts(sb, inode, attr->ia_mode);
inode->i_mode = adfs_atts2mode(sb, inode);
}
@@ -353,7 +355,7 @@ int adfs_write_inode(struct inode *inode, struct writeback_control *wbc)
struct object_info obj;
int ret;
- obj.indaddr = inode->i_ino;
+ obj.indaddr = ADFS_I(inode)->indaddr;
obj.name_len = 0;
obj.parent_id = ADFS_I(inode)->parent_id;
obj.loadaddr = ADFS_I(inode)->loadaddr;
diff --git a/fs/adfs/map.c b/fs/adfs/map.c
index f44d12cef5be..a81de80c45c1 100644
--- a/fs/adfs/map.c
+++ b/fs/adfs/map.c
@@ -4,6 +4,8 @@
*
* Copyright (C) 1997-2002 Russell King
*/
+#include <linux/slab.h>
+#include <linux/statfs.h>
#include <asm/unaligned.h>
#include "adfs.h"
@@ -66,54 +68,41 @@ static DEFINE_RWLOCK(adfs_map_lock);
static int lookup_zone(const struct adfs_discmap *dm, const unsigned int idlen,
const u32 frag_id, unsigned int *offset)
{
- const unsigned int mapsize = dm->dm_endbit;
+ const unsigned int endbit = dm->dm_endbit;
const u32 idmask = (1 << idlen) - 1;
- unsigned char *map = dm->dm_bh->b_data + 4;
+ unsigned char *map = dm->dm_bh->b_data;
unsigned int start = dm->dm_startbit;
- unsigned int mapptr;
+ unsigned int freelink, fragend;
u32 frag;
+ frag = GET_FRAG_ID(map, 8, idmask & 0x7fff);
+ freelink = frag ? 8 + frag : 0;
+
do {
frag = GET_FRAG_ID(map, start, idmask);
- mapptr = start + idlen;
-
- /*
- * find end of fragment
- */
- {
- __le32 *_map = (__le32 *)map;
- u32 v = le32_to_cpu(_map[mapptr >> 5]) >> (mapptr & 31);
- while (v == 0) {
- mapptr = (mapptr & ~31) + 32;
- if (mapptr >= mapsize)
- goto error;
- v = le32_to_cpu(_map[mapptr >> 5]);
- }
-
- mapptr += 1 + ffz(~v);
+
+ fragend = find_next_bit_le(map, endbit, start + idlen);
+ if (fragend >= endbit)
+ goto error;
+
+ if (start == freelink) {
+ freelink += frag & 0x7fff;
+ } else if (frag == frag_id) {
+ unsigned int length = fragend + 1 - start;
+
+ if (*offset < length)
+ return start + *offset;
+ *offset -= length;
}
- if (frag == frag_id)
- goto found;
-again:
- start = mapptr;
- } while (mapptr < mapsize);
+ start = fragend + 1;
+ } while (start < endbit);
return -1;
error:
printk(KERN_ERR "adfs: oversized fragment 0x%x at 0x%x-0x%x\n",
- frag, start, mapptr);
+ frag, start, fragend);
return -1;
-
-found:
- {
- int length = mapptr - start;
- if (*offset >= length) {
- *offset -= length;
- goto again;
- }
- }
- return start + *offset;
}
/*
@@ -125,12 +114,12 @@ found:
static unsigned int
scan_free_map(struct adfs_sb_info *asb, struct adfs_discmap *dm)
{
- const unsigned int mapsize = dm->dm_endbit + 32;
+ const unsigned int endbit = dm->dm_endbit;
const unsigned int idlen = asb->s_idlen;
const unsigned int frag_idlen = idlen <= 15 ? idlen : 15;
const u32 idmask = (1 << frag_idlen) - 1;
unsigned char *map = dm->dm_bh->b_data;
- unsigned int start = 8, mapptr;
+ unsigned int start = 8, fragend;
u32 frag;
unsigned long total = 0;
@@ -149,29 +138,13 @@ scan_free_map(struct adfs_sb_info *asb, struct adfs_discmap *dm)
do {
start += frag;
- /*
- * get fragment id
- */
frag = GET_FRAG_ID(map, start, idmask);
- mapptr = start + idlen;
-
- /*
- * find end of fragment
- */
- {
- __le32 *_map = (__le32 *)map;
- u32 v = le32_to_cpu(_map[mapptr >> 5]) >> (mapptr & 31);
- while (v == 0) {
- mapptr = (mapptr & ~31) + 32;
- if (mapptr >= mapsize)
- goto error;
- v = le32_to_cpu(_map[mapptr >> 5]);
- }
-
- mapptr += 1 + ffz(~v);
- }
- total += mapptr - start;
+ fragend = find_next_bit_le(map, endbit, start + idlen);
+ if (fragend >= endbit)
+ goto error;
+
+ total += fragend + 1 - start;
} while (frag >= idlen + 1);
if (frag != 0)
@@ -220,10 +193,10 @@ found:
* total_free = E(free_in_zone_n)
* nzones
*/
-unsigned int
-adfs_map_free(struct super_block *sb)
+void adfs_map_statfs(struct super_block *sb, struct kstatfs *buf)
{
struct adfs_sb_info *asb = ADFS_SB(sb);
+ struct adfs_discrecord *dr = adfs_map_discrecord(asb->s_map);
struct adfs_discmap *dm;
unsigned int total = 0;
unsigned int zone;
@@ -235,7 +208,10 @@ adfs_map_free(struct super_block *sb)
total += scan_free_map(asb, dm++);
} while (--zone > 0);
- return signed_asl(total, asb->s_map2blk);
+ buf->f_blocks = adfs_disc_size(dr) >> sb->s_blocksize_bits;
+ buf->f_files = asb->s_ids_per_zone * asb->s_map_size;
+ buf->f_bavail =
+ buf->f_bfree = signed_asl(total, asb->s_map2blk);
}
int adfs_map_lookup(struct super_block *sb, u32 frag_id, unsigned int offset)
@@ -280,3 +256,152 @@ bad_fragment:
frag_id, zone, asb->s_map_size);
return 0;
}
+
+static unsigned char adfs_calczonecheck(struct super_block *sb, unsigned char *map)
+{
+ unsigned int v0, v1, v2, v3;
+ int i;
+
+ v0 = v1 = v2 = v3 = 0;
+ for (i = sb->s_blocksize - 4; i; i -= 4) {
+ v0 += map[i] + (v3 >> 8);
+ v3 &= 0xff;
+ v1 += map[i + 1] + (v0 >> 8);
+ v0 &= 0xff;
+ v2 += map[i + 2] + (v1 >> 8);
+ v1 &= 0xff;
+ v3 += map[i + 3] + (v2 >> 8);
+ v2 &= 0xff;
+ }
+ v0 += v3 >> 8;
+ v1 += map[1] + (v0 >> 8);
+ v2 += map[2] + (v1 >> 8);
+ v3 += map[3] + (v2 >> 8);
+
+ return v0 ^ v1 ^ v2 ^ v3;
+}
+
+static int adfs_checkmap(struct super_block *sb, struct adfs_discmap *dm)
+{
+ unsigned char crosscheck = 0, zonecheck = 1;
+ int i;
+
+ for (i = 0; i < ADFS_SB(sb)->s_map_size; i++) {
+ unsigned char *map;
+
+ map = dm[i].dm_bh->b_data;
+
+ if (adfs_calczonecheck(sb, map) != map[0]) {
+ adfs_error(sb, "zone %d fails zonecheck", i);
+ zonecheck = 0;
+ }
+ crosscheck ^= map[3];
+ }
+ if (crosscheck != 0xff)
+ adfs_error(sb, "crosscheck != 0xff");
+ return crosscheck == 0xff && zonecheck;
+}
+
+/*
+ * Layout the map - the first zone contains a copy of the disc record,
+ * and the last zone must be limited to the size of the filesystem.
+ */
+static void adfs_map_layout(struct adfs_discmap *dm, unsigned int nzones,
+ struct adfs_discrecord *dr)
+{
+ unsigned int zone, zone_size;
+ u64 size;
+
+ zone_size = (8 << dr->log2secsize) - le16_to_cpu(dr->zone_spare);
+
+ dm[0].dm_bh = NULL;
+ dm[0].dm_startblk = 0;
+ dm[0].dm_startbit = 32 + ADFS_DR_SIZE_BITS;
+ dm[0].dm_endbit = 32 + zone_size;
+
+ for (zone = 1; zone < nzones; zone++) {
+ dm[zone].dm_bh = NULL;
+ dm[zone].dm_startblk = zone * zone_size - ADFS_DR_SIZE_BITS;
+ dm[zone].dm_startbit = 32;
+ dm[zone].dm_endbit = 32 + zone_size;
+ }
+
+ size = adfs_disc_size(dr) >> dr->log2bpmb;
+ size -= (nzones - 1) * zone_size - ADFS_DR_SIZE_BITS;
+ dm[nzones - 1].dm_endbit = 32 + size;
+}
+
+static int adfs_map_read(struct adfs_discmap *dm, struct super_block *sb,
+ unsigned int map_addr, unsigned int nzones)
+{
+ unsigned int zone;
+
+ for (zone = 0; zone < nzones; zone++) {
+ dm[zone].dm_bh = sb_bread(sb, map_addr + zone);
+ if (!dm[zone].dm_bh)
+ return -EIO;
+ }
+
+ return 0;
+}
+
+static void adfs_map_relse(struct adfs_discmap *dm, unsigned int nzones)
+{
+ unsigned int zone;
+
+ for (zone = 0; zone < nzones; zone++)
+ brelse(dm[zone].dm_bh);
+}
+
+struct adfs_discmap *adfs_read_map(struct super_block *sb, struct adfs_discrecord *dr)
+{
+ struct adfs_sb_info *asb = ADFS_SB(sb);
+ struct adfs_discmap *dm;
+ unsigned int map_addr, zone_size, nzones;
+ int ret;
+
+ nzones = dr->nzones | dr->nzones_high << 8;
+ zone_size = (8 << dr->log2secsize) - le16_to_cpu(dr->zone_spare);
+
+ asb->s_idlen = dr->idlen;
+ asb->s_map_size = nzones;
+ asb->s_map2blk = dr->log2bpmb - dr->log2secsize;
+ asb->s_log2sharesize = dr->log2sharesize;
+ asb->s_ids_per_zone = zone_size / (asb->s_idlen + 1);
+
+ map_addr = (nzones >> 1) * zone_size -
+ ((nzones > 1) ? ADFS_DR_SIZE_BITS : 0);
+ map_addr = signed_asl(map_addr, asb->s_map2blk);
+
+ dm = kmalloc_array(nzones, sizeof(*dm), GFP_KERNEL);
+ if (dm == NULL) {
+ adfs_error(sb, "not enough memory");
+ return ERR_PTR(-ENOMEM);
+ }
+
+ adfs_map_layout(dm, nzones, dr);
+
+ ret = adfs_map_read(dm, sb, map_addr, nzones);
+ if (ret) {
+ adfs_error(sb, "unable to read map");
+ goto error_free;
+ }
+
+ if (adfs_checkmap(sb, dm))
+ return dm;
+
+ adfs_error(sb, "map corrupted");
+
+error_free:
+ adfs_map_relse(dm, nzones);
+ kfree(dm);
+ return ERR_PTR(-EIO);
+}
+
+void adfs_free_map(struct super_block *sb)
+{
+ struct adfs_sb_info *asb = ADFS_SB(sb);
+
+ adfs_map_relse(asb->s_map, asb->s_map_size);
+ kfree(asb->s_map);
+}
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index 65b04ebb51c3..a3cc8ecb50da 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -88,59 +88,11 @@ static int adfs_checkdiscrecord(struct adfs_discrecord *dr)
return 0;
}
-static unsigned char adfs_calczonecheck(struct super_block *sb, unsigned char *map)
-{
- unsigned int v0, v1, v2, v3;
- int i;
-
- v0 = v1 = v2 = v3 = 0;
- for (i = sb->s_blocksize - 4; i; i -= 4) {
- v0 += map[i] + (v3 >> 8);
- v3 &= 0xff;
- v1 += map[i + 1] + (v0 >> 8);
- v0 &= 0xff;
- v2 += map[i + 2] + (v1 >> 8);
- v1 &= 0xff;
- v3 += map[i + 3] + (v2 >> 8);
- v2 &= 0xff;
- }
- v0 += v3 >> 8;
- v1 += map[1] + (v0 >> 8);
- v2 += map[2] + (v1 >> 8);
- v3 += map[3] + (v2 >> 8);
-
- return v0 ^ v1 ^ v2 ^ v3;
-}
-
-static int adfs_checkmap(struct super_block *sb, struct adfs_discmap *dm)
-{
- unsigned char crosscheck = 0, zonecheck = 1;
- int i;
-
- for (i = 0; i < ADFS_SB(sb)->s_map_size; i++) {
- unsigned char *map;
-
- map = dm[i].dm_bh->b_data;
-
- if (adfs_calczonecheck(sb, map) != map[0]) {
- adfs_error(sb, "zone %d fails zonecheck", i);
- zonecheck = 0;
- }
- crosscheck ^= map[3];
- }
- if (crosscheck != 0xff)
- adfs_error(sb, "crosscheck != 0xff");
- return crosscheck == 0xff && zonecheck;
-}
-
static void adfs_put_super(struct super_block *sb)
{
- int i;
struct adfs_sb_info *asb = ADFS_SB(sb);
- for (i = 0; i < asb->s_map_size; i++)
- brelse(asb->s_map[i].dm_bh);
- kfree(asb->s_map);
+ adfs_free_map(sb);
kfree_rcu(asb, rcu);
}
@@ -249,16 +201,13 @@ static int adfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
struct adfs_sb_info *sbi = ADFS_SB(sb);
- struct adfs_discrecord *dr = adfs_map_discrecord(sbi->s_map);
u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
+ adfs_map_statfs(sb, buf);
+
buf->f_type = ADFS_SUPER_MAGIC;
buf->f_namelen = sbi->s_namelen;
buf->f_bsize = sb->s_blocksize;
- buf->f_blocks = adfs_disc_size(dr) >> sb->s_blocksize_bits;
- buf->f_files = sbi->s_ids_per_zone * sbi->s_map_size;
- buf->f_bavail =
- buf->f_bfree = adfs_map_free(sb);
buf->f_ffree = (long)(buf->f_bfree * buf->f_files) / (long)buf->f_blocks;
buf->f_fsid.val[0] = (u32)id;
buf->f_fsid.val[1] = (u32)(id >> 32);
@@ -282,6 +231,12 @@ static void adfs_free_inode(struct inode *inode)
kmem_cache_free(adfs_inode_cachep, ADFS_I(inode));
}
+static int adfs_drop_inode(struct inode *inode)
+{
+ /* always drop inodes if we are read-only */
+ return !IS_ENABLED(CONFIG_ADFS_FS_RW) || IS_RDONLY(inode);
+}
+
static void init_once(void *foo)
{
struct adfs_inode_info *ei = (struct adfs_inode_info *) foo;
@@ -314,7 +269,7 @@ static void destroy_inodecache(void)
static const struct super_operations adfs_sops = {
.alloc_inode = adfs_alloc_inode,
.free_inode = adfs_free_inode,
- .drop_inode = generic_delete_inode,
+ .drop_inode = adfs_drop_inode,
.write_inode = adfs_write_inode,
.put_super = adfs_put_super,
.statfs = adfs_statfs,
@@ -322,66 +277,94 @@ static const struct super_operations adfs_sops = {
.show_options = adfs_show_options,
};
-static struct adfs_discmap *adfs_read_map(struct super_block *sb, struct adfs_discrecord *dr)
+static int adfs_probe(struct super_block *sb, unsigned int offset, int silent,
+ int (*validate)(struct super_block *sb,
+ struct buffer_head *bh,
+ struct adfs_discrecord **bhp))
{
- struct adfs_discmap *dm;
- unsigned int map_addr, zone_size, nzones;
- int i, zone;
struct adfs_sb_info *asb = ADFS_SB(sb);
+ struct adfs_discrecord *dr;
+ struct buffer_head *bh;
+ unsigned int blocksize = BLOCK_SIZE;
+ int ret, try;
+
+ for (try = 0; try < 2; try++) {
+ /* try to set the requested block size */
+ if (sb->s_blocksize != blocksize &&
+ !sb_set_blocksize(sb, blocksize)) {
+ if (!silent)
+ adfs_msg(sb, KERN_ERR,
+ "error: unsupported blocksize");
+ return -EINVAL;
+ }
- nzones = asb->s_map_size;
- zone_size = (8 << dr->log2secsize) - le16_to_cpu(dr->zone_spare);
- map_addr = (nzones >> 1) * zone_size -
- ((nzones > 1) ? ADFS_DR_SIZE_BITS : 0);
- map_addr = signed_asl(map_addr, asb->s_map2blk);
+ /* read the buffer */
+ bh = sb_bread(sb, offset >> sb->s_blocksize_bits);
+ if (!bh) {
+ adfs_msg(sb, KERN_ERR,
+ "error: unable to read block %u, try %d",
+ offset >> sb->s_blocksize_bits, try);
+ return -EIO;
+ }
+
+ /* validate it */
+ ret = validate(sb, bh, &dr);
+ if (ret) {
+ brelse(bh);
+ return ret;
+ }
- asb->s_ids_per_zone = zone_size / (asb->s_idlen + 1);
+ /* does the block size match the filesystem block size? */
+ blocksize = 1 << dr->log2secsize;
+ if (sb->s_blocksize == blocksize) {
+ asb->s_map = adfs_read_map(sb, dr);
+ brelse(bh);
+ return PTR_ERR_OR_ZERO(asb->s_map);
+ }
- dm = kmalloc_array(nzones, sizeof(*dm), GFP_KERNEL);
- if (dm == NULL) {
- adfs_error(sb, "not enough memory");
- return ERR_PTR(-ENOMEM);
+ brelse(bh);
}
- for (zone = 0; zone < nzones; zone++, map_addr++) {
- dm[zone].dm_startbit = 0;
- dm[zone].dm_endbit = zone_size;
- dm[zone].dm_startblk = zone * zone_size - ADFS_DR_SIZE_BITS;
- dm[zone].dm_bh = sb_bread(sb, map_addr);
+ return -EIO;
+}
- if (!dm[zone].dm_bh) {
- adfs_error(sb, "unable to read map");
- goto error_free;
- }
- }
+static int adfs_validate_bblk(struct super_block *sb, struct buffer_head *bh,
+ struct adfs_discrecord **drp)
+{
+ struct adfs_discrecord *dr;
+ unsigned char *b_data;
- /* adjust the limits for the first and last map zones */
- i = zone - 1;
- dm[0].dm_startblk = 0;
- dm[0].dm_startbit = ADFS_DR_SIZE_BITS;
- dm[i].dm_endbit = (adfs_disc_size(dr) >> dr->log2bpmb) +
- (ADFS_DR_SIZE_BITS - i * zone_size);
+ b_data = bh->b_data + (ADFS_DISCRECORD % sb->s_blocksize);
+ if (adfs_checkbblk(b_data))
+ return -EILSEQ;
- if (adfs_checkmap(sb, dm))
- return dm;
+ /* Do some sanity checks on the ADFS disc record */
+ dr = (struct adfs_discrecord *)(b_data + ADFS_DR_OFFSET);
+ if (adfs_checkdiscrecord(dr))
+ return -EILSEQ;
+
+ *drp = dr;
+ return 0;
+}
- adfs_error(sb, "map corrupted");
+static int adfs_validate_dr0(struct super_block *sb, struct buffer_head *bh,
+ struct adfs_discrecord **drp)
+{
+ struct adfs_discrecord *dr;
-error_free:
- while (--zone >= 0)
- brelse(dm[zone].dm_bh);
+ /* Do some sanity checks on the ADFS disc record */
+ dr = (struct adfs_discrecord *)(bh->b_data + 4);
+ if (adfs_checkdiscrecord(dr) || dr->nzones_high || dr->nzones != 1)
+ return -EILSEQ;
- kfree(dm);
- return ERR_PTR(-EIO);
+ *drp = dr;
+ return 0;
}
static int adfs_fill_super(struct super_block *sb, void *data, int silent)
{
struct adfs_discrecord *dr;
- struct buffer_head *bh;
struct object_info root_obj;
- unsigned char *b_data;
- unsigned int blocksize;
struct adfs_sb_info *asb;
struct inode *root;
int ret = -EINVAL;
@@ -391,7 +374,10 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent)
asb = kzalloc(sizeof(*asb), GFP_KERNEL);
if (!asb)
return -ENOMEM;
+
sb->s_fs_info = asb;
+ sb->s_magic = ADFS_SUPER_MAGIC;
+ sb->s_time_gran = 10000000;
/* set default options */
asb->s_uid = GLOBAL_ROOT_UID;
@@ -403,78 +389,21 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent)
if (parse_options(sb, asb, data))
goto error;
- sb_set_blocksize(sb, BLOCK_SIZE);
- if (!(bh = sb_bread(sb, ADFS_DISCRECORD / BLOCK_SIZE))) {
- adfs_msg(sb, KERN_ERR, "error: unable to read superblock");
- ret = -EIO;
- goto error;
- }
-
- b_data = bh->b_data + (ADFS_DISCRECORD % BLOCK_SIZE);
-
- if (adfs_checkbblk(b_data)) {
- ret = -EINVAL;
- goto error_badfs;
- }
-
- dr = (struct adfs_discrecord *)(b_data + ADFS_DR_OFFSET);
-
- /*
- * Do some sanity checks on the ADFS disc record
- */
- if (adfs_checkdiscrecord(dr)) {
- ret = -EINVAL;
- goto error_badfs;
- }
-
- blocksize = 1 << dr->log2secsize;
- brelse(bh);
-
- if (sb_set_blocksize(sb, blocksize)) {
- bh = sb_bread(sb, ADFS_DISCRECORD / sb->s_blocksize);
- if (!bh) {
- adfs_msg(sb, KERN_ERR,
- "error: couldn't read superblock on 2nd try.");
- ret = -EIO;
- goto error;
- }
- b_data = bh->b_data + (ADFS_DISCRECORD % sb->s_blocksize);
- if (adfs_checkbblk(b_data)) {
- adfs_msg(sb, KERN_ERR,
- "error: disc record mismatch, very weird!");
- ret = -EINVAL;
- goto error_free_bh;
- }
- dr = (struct adfs_discrecord *)(b_data + ADFS_DR_OFFSET);
- } else {
+ /* Try to probe the filesystem boot block */
+ ret = adfs_probe(sb, ADFS_DISCRECORD, 1, adfs_validate_bblk);
+ if (ret == -EILSEQ)
+ ret = adfs_probe(sb, 0, silent, adfs_validate_dr0);
+ if (ret == -EILSEQ) {
if (!silent)
adfs_msg(sb, KERN_ERR,
- "error: unsupported blocksize");
+ "error: can't find an ADFS filesystem on dev %s.",
+ sb->s_id);
ret = -EINVAL;
- goto error;
}
+ if (ret)
+ goto error;
- /*
- * blocksize on this device should now be set to the ADFS log2secsize
- */
-
- sb->s_magic = ADFS_SUPER_MAGIC;
- asb->s_idlen = dr->idlen;
- asb->s_map_size = dr->nzones | (dr->nzones_high << 8);
- asb->s_map2blk = dr->log2bpmb - dr->log2secsize;
- asb->s_log2sharesize = dr->log2sharesize;
-
- asb->s_map = adfs_read_map(sb, dr);
- if (IS_ERR(asb->s_map)) {
- ret = PTR_ERR(asb->s_map);
- goto error_free_bh;
- }
-
- brelse(bh);
-
- /*
- * set up enough so that we can read an inode
- */
+ /* set up enough so that we can read an inode */
sb->s_op = &adfs_sops;
dr = adfs_map_discrecord(asb->s_map);
@@ -511,23 +440,13 @@ static int adfs_fill_super(struct super_block *sb, void *data, int silent)
root = adfs_iget(sb, &root_obj);
sb->s_root = d_make_root(root);
if (!sb->s_root) {
- int i;
- for (i = 0; i < asb->s_map_size; i++)
- brelse(asb->s_map[i].dm_bh);
- kfree(asb->s_map);
+ adfs_free_map(sb);
adfs_error(sb, "get root inode failed\n");
ret = -EIO;
goto error;
}
return 0;
-error_badfs:
- if (!silent)
- adfs_msg(sb, KERN_ERR,
- "error: can't find an ADFS filesystem on dev %s.",
- sb->s_id);
-error_free_bh:
- brelse(bh);
error:
sb->s_fs_info = NULL;
kfree(asb);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index ecd8d2698515..f4713ea76e82 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -97,7 +97,7 @@ static struct linux_binfmt elf_format = {
.min_coredump = ELF_EXEC_PAGESIZE,
};
-#define BAD_ADDR(x) ((unsigned long)(x) >= TASK_SIZE)
+#define BAD_ADDR(x) (unlikely((unsigned long)(x) >= TASK_SIZE))
static int set_brk(unsigned long start, unsigned long end, int prot)
{
@@ -161,9 +161,11 @@ static int padzero(unsigned long elf_bss)
#endif
static int
-create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
- unsigned long load_addr, unsigned long interp_load_addr)
+create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec,
+ unsigned long load_addr, unsigned long interp_load_addr,
+ unsigned long e_entry)
{
+ struct mm_struct *mm = current->mm;
unsigned long p = bprm->p;
int argc = bprm->argc;
int envc = bprm->envc;
@@ -176,7 +178,7 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
unsigned char k_rand_bytes[16];
int items;
elf_addr_t *elf_info;
- int ei_index = 0;
+ int ei_index;
const struct cred *cred = current_cred();
struct vm_area_struct *vma;
@@ -226,12 +228,12 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
return -EFAULT;
/* Create the ELF interpreter info */
- elf_info = (elf_addr_t *)current->mm->saved_auxv;
+ elf_info = (elf_addr_t *)mm->saved_auxv;
/* update AT_VECTOR_SIZE_BASE if the number of NEW_AUX_ENT() changes */
#define NEW_AUX_ENT(id, val) \
do { \
- elf_info[ei_index++] = id; \
- elf_info[ei_index++] = val; \
+ *elf_info++ = id; \
+ *elf_info++ = val; \
} while (0)
#ifdef ARCH_DLINFO
@@ -251,7 +253,7 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
NEW_AUX_ENT(AT_PHNUM, exec->e_phnum);
NEW_AUX_ENT(AT_BASE, interp_load_addr);
NEW_AUX_ENT(AT_FLAGS, 0);
- NEW_AUX_ENT(AT_ENTRY, exec->e_entry);
+ NEW_AUX_ENT(AT_ENTRY, e_entry);
NEW_AUX_ENT(AT_UID, from_kuid_munged(cred->user_ns, cred->uid));
NEW_AUX_ENT(AT_EUID, from_kuid_munged(cred->user_ns, cred->euid));
NEW_AUX_ENT(AT_GID, from_kgid_munged(cred->user_ns, cred->gid));
@@ -275,12 +277,13 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
}
#undef NEW_AUX_ENT
/* AT_NULL is zero; clear the rest too */
- memset(&elf_info[ei_index], 0,
- sizeof current->mm->saved_auxv - ei_index * sizeof elf_info[0]);
+ memset(elf_info, 0, (char *)mm->saved_auxv +
+ sizeof(mm->saved_auxv) - (char *)elf_info);
/* And advance past the AT_NULL entry. */
- ei_index += 2;
+ elf_info += 2;
+ ei_index = elf_info - (elf_addr_t *)mm->saved_auxv;
sp = STACK_ADD(p, ei_index);
items = (argc + 1) + (envc + 1) + 1;
@@ -299,7 +302,7 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
* Grow the stack manually; some architectures have a limit on how
* far ahead a user-space access may be in order to grow the stack.
*/
- vma = find_extend_vma(current->mm, bprm->p);
+ vma = find_extend_vma(mm, bprm->p);
if (!vma)
return -EFAULT;
@@ -308,7 +311,7 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
return -EFAULT;
/* Populate list of argv pointers back to argv strings. */
- p = current->mm->arg_end = current->mm->arg_start;
+ p = mm->arg_end = mm->arg_start;
while (argc-- > 0) {
size_t len;
if (__put_user((elf_addr_t)p, sp++))
@@ -320,10 +323,10 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
}
if (__put_user(0, sp++))
return -EFAULT;
- current->mm->arg_end = p;
+ mm->arg_end = p;
/* Populate list of envp pointers back to envp strings. */
- current->mm->env_end = current->mm->env_start = p;
+ mm->env_end = mm->env_start = p;
while (envc-- > 0) {
size_t len;
if (__put_user((elf_addr_t)p, sp++))
@@ -335,10 +338,10 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
}
if (__put_user(0, sp++))
return -EFAULT;
- current->mm->env_end = p;
+ mm->env_end = p;
/* Put the elf_info on the stack in the right place. */
- if (copy_to_user(sp, elf_info, ei_index * sizeof(elf_addr_t)))
+ if (copy_to_user(sp, mm->saved_auxv, ei_index * sizeof(elf_addr_t)))
return -EFAULT;
return 0;
}
@@ -689,15 +692,17 @@ static int load_elf_binary(struct linux_binprm *bprm)
int bss_prot = 0;
int retval, i;
unsigned long elf_entry;
+ unsigned long e_entry;
unsigned long interp_load_addr = 0;
unsigned long start_code, end_code, start_data, end_data;
unsigned long reloc_func_desc __maybe_unused = 0;
int executable_stack = EXSTACK_DEFAULT;
+ struct elfhdr *elf_ex = (struct elfhdr *)bprm->buf;
struct {
- struct elfhdr elf_ex;
struct elfhdr interp_elf_ex;
} *loc;
struct arch_elf_state arch_state = INIT_ARCH_ELF_STATE;
+ struct mm_struct *mm;
struct pt_regs *regs;
loc = kmalloc(sizeof(*loc), GFP_KERNEL);
@@ -705,30 +710,27 @@ static int load_elf_binary(struct linux_binprm *bprm)
retval = -ENOMEM;
goto out_ret;
}
-
- /* Get the exec-header */
- loc->elf_ex = *((struct elfhdr *)bprm->buf);
retval = -ENOEXEC;
/* First of all, some simple consistency checks */
- if (memcmp(loc->elf_ex.e_ident, ELFMAG, SELFMAG) != 0)
+ if (memcmp(elf_ex->e_ident, ELFMAG, SELFMAG) != 0)
goto out;
- if (loc->elf_ex.e_type != ET_EXEC && loc->elf_ex.e_type != ET_DYN)
+ if (elf_ex->e_type != ET_EXEC && elf_ex->e_type != ET_DYN)
goto out;
- if (!elf_check_arch(&loc->elf_ex))
+ if (!elf_check_arch(elf_ex))
goto out;
- if (elf_check_fdpic(&loc->elf_ex))
+ if (elf_check_fdpic(elf_ex))
goto out;
if (!bprm->file->f_op->mmap)
goto out;
- elf_phdata = load_elf_phdrs(&loc->elf_ex, bprm->file);
+ elf_phdata = load_elf_phdrs(elf_ex, bprm->file);
if (!elf_phdata)
goto out;
elf_ppnt = elf_phdata;
- for (i = 0; i < loc->elf_ex.e_phnum; i++, elf_ppnt++) {
+ for (i = 0; i < elf_ex->e_phnum; i++, elf_ppnt++) {
char *elf_interpreter;
if (elf_ppnt->p_type != PT_INTERP)
@@ -782,7 +784,7 @@ out_free_interp:
}
elf_ppnt = elf_phdata;
- for (i = 0; i < loc->elf_ex.e_phnum; i++, elf_ppnt++)
+ for (i = 0; i < elf_ex->e_phnum; i++, elf_ppnt++)
switch (elf_ppnt->p_type) {
case PT_GNU_STACK:
if (elf_ppnt->p_flags & PF_X)
@@ -792,7 +794,7 @@ out_free_interp:
break;
case PT_LOPROC ... PT_HIPROC:
- retval = arch_elf_pt_proc(&loc->elf_ex, elf_ppnt,
+ retval = arch_elf_pt_proc(elf_ex, elf_ppnt,
bprm->file, false,
&arch_state);
if (retval)
@@ -836,7 +838,7 @@ out_free_interp:
* still possible to return an error to the code that invoked
* the exec syscall.
*/
- retval = arch_check_elf(&loc->elf_ex,
+ retval = arch_check_elf(elf_ex,
!!interpreter, &loc->interp_elf_ex,
&arch_state);
if (retval)
@@ -849,8 +851,8 @@ out_free_interp:
/* Do this immediately, since STACK_TOP as used in setup_arg_pages
may depend on the personality. */
- SET_PERSONALITY2(loc->elf_ex, &arch_state);
- if (elf_read_implies_exec(loc->elf_ex, executable_stack))
+ SET_PERSONALITY2(*elf_ex, &arch_state);
+ if (elf_read_implies_exec(*elf_ex, executable_stack))
current->personality |= READ_IMPLIES_EXEC;
if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
@@ -877,7 +879,7 @@ out_free_interp:
/* Now we do a little grungy work by mmapping the ELF image into
the correct location in memory. */
for(i = 0, elf_ppnt = elf_phdata;
- i < loc->elf_ex.e_phnum; i++, elf_ppnt++) {
+ i < elf_ex->e_phnum; i++, elf_ppnt++) {
int elf_prot, elf_flags;
unsigned long k, vaddr;
unsigned long total_size = 0;
@@ -921,9 +923,9 @@ out_free_interp:
* If we are loading ET_EXEC or we have already performed
* the ET_DYN load_addr calculations, proceed normally.
*/
- if (loc->elf_ex.e_type == ET_EXEC || load_addr_set) {
+ if (elf_ex->e_type == ET_EXEC || load_addr_set) {
elf_flags |= MAP_FIXED;
- } else if (loc->elf_ex.e_type == ET_DYN) {
+ } else if (elf_ex->e_type == ET_DYN) {
/*
* This logic is run once for the first LOAD Program
* Header for ET_DYN binaries to calculate the
@@ -972,7 +974,7 @@ out_free_interp:
load_bias = ELF_PAGESTART(load_bias - vaddr);
total_size = total_mapping_size(elf_phdata,
- loc->elf_ex.e_phnum);
+ elf_ex->e_phnum);
if (!total_size) {
retval = -EINVAL;
goto out_free_dentry;
@@ -990,7 +992,7 @@ out_free_interp:
if (!load_addr_set) {
load_addr_set = 1;
load_addr = (elf_ppnt->p_vaddr - elf_ppnt->p_offset);
- if (loc->elf_ex.e_type == ET_DYN) {
+ if (elf_ex->e_type == ET_DYN) {
load_bias += error -
ELF_PAGESTART(load_bias + vaddr);
load_addr += load_bias;
@@ -998,7 +1000,7 @@ out_free_interp:
}
}
k = elf_ppnt->p_vaddr;
- if (k < start_code)
+ if ((elf_ppnt->p_flags & PF_X) && k < start_code)
start_code = k;
if (start_data < k)
start_data = k;
@@ -1031,7 +1033,7 @@ out_free_interp:
}
}
- loc->elf_ex.e_entry += load_bias;
+ e_entry = elf_ex->e_entry + load_bias;
elf_bss += load_bias;
elf_brk += load_bias;
start_code += load_bias;
@@ -1074,7 +1076,7 @@ out_free_interp:
allow_write_access(interpreter);
fput(interpreter);
} else {
- elf_entry = loc->elf_ex.e_entry;
+ elf_entry = e_entry;
if (BAD_ADDR(elf_entry)) {
retval = -EINVAL;
goto out_free_dentry;
@@ -1092,15 +1094,17 @@ out_free_interp:
goto out;
#endif /* ARCH_HAS_SETUP_ADDITIONAL_PAGES */
- retval = create_elf_tables(bprm, &loc->elf_ex,
- load_addr, interp_load_addr);
+ retval = create_elf_tables(bprm, elf_ex,
+ load_addr, interp_load_addr, e_entry);
if (retval < 0)
goto out;
- current->mm->end_code = end_code;
- current->mm->start_code = start_code;
- current->mm->start_data = start_data;
- current->mm->end_data = end_data;
- current->mm->start_stack = bprm->p;
+
+ mm = current->mm;
+ mm->end_code = end_code;
+ mm->start_code = start_code;
+ mm->start_data = start_data;
+ mm->end_data = end_data;
+ mm->start_stack = bprm->p;
if ((current->flags & PF_RANDOMIZE) && (randomize_va_space > 1)) {
/*
@@ -1111,12 +1115,11 @@ out_free_interp:
* growing down), and into the unused ELF_ET_DYN_BASE region.
*/
if (IS_ENABLED(CONFIG_ARCH_HAS_ELF_RANDOMIZE) &&
- loc->elf_ex.e_type == ET_DYN && !interpreter)
- current->mm->brk = current->mm->start_brk =
- ELF_ET_DYN_BASE;
+ elf_ex->e_type == ET_DYN && !interpreter) {
+ mm->brk = mm->start_brk = ELF_ET_DYN_BASE;
+ }
- current->mm->brk = current->mm->start_brk =
- arch_randomize_brk(current->mm);
+ mm->brk = mm->start_brk = arch_randomize_brk(mm);
#ifdef compat_brk_randomized
current->brk_randomized = 1;
#endif
@@ -1574,6 +1577,7 @@ static void fill_siginfo_note(struct memelfnote *note, user_siginfo_t *csigdata,
*/
static int fill_files_note(struct memelfnote *note)
{
+ struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
unsigned count, size, names_ofs, remaining, n;
user_long_t *data;
@@ -1581,7 +1585,7 @@ static int fill_files_note(struct memelfnote *note)
char *name_base, *name_curpos;
/* *Estimated* file count and total data size needed */
- count = current->mm->map_count;
+ count = mm->map_count;
if (count > UINT_MAX / 64)
return -EINVAL;
size = count * 64;
@@ -1591,6 +1595,10 @@ static int fill_files_note(struct memelfnote *note)
if (size >= MAX_FILE_NOTE_SIZE) /* paranoia check */
return -EINVAL;
size = round_up(size, PAGE_SIZE);
+ /*
+ * "size" can be 0 here legitimately.
+ * Let it ENOMEM and omit NT_FILE section which will be empty anyway.
+ */
data = kvmalloc(size, GFP_KERNEL);
if (ZERO_OR_NULL_PTR(data))
return -ENOMEM;
@@ -1599,7 +1607,7 @@ static int fill_files_note(struct memelfnote *note)
name_base = name_curpos = ((char *)data) + names_ofs;
remaining = size - names_ofs;
count = 0;
- for (vma = current->mm->mmap; vma != NULL; vma = vma->vm_next) {
+ for (vma = mm->mmap; vma != NULL; vma = vma->vm_next) {
struct file *file;
const char *filename;
@@ -1633,10 +1641,10 @@ static int fill_files_note(struct memelfnote *note)
data[0] = count;
data[1] = PAGE_SIZE;
/*
- * Count usually is less than current->mm->map_count,
+ * Count usually is less than mm->map_count,
* we need to move filenames down.
*/
- n = current->mm->map_count - count;
+ n = mm->map_count - count;
if (n != 0) {
unsigned shift_bytes = n * 3 * sizeof(data[0]);
memmove(name_base - shift_bytes, name_base,
@@ -2182,7 +2190,7 @@ static int elf_core_dump(struct coredump_params *cprm)
int segs, i;
size_t vma_data_size = 0;
struct vm_area_struct *vma, *gate_vma;
- struct elfhdr *elf = NULL;
+ struct elfhdr elf;
loff_t offset = 0, dataoff;
struct elf_note_info info = { };
struct elf_phdr *phdr4note = NULL;
@@ -2203,10 +2211,6 @@ static int elf_core_dump(struct coredump_params *cprm)
* exists while dumping the mm->vm_next areas to the core file.
*/
- /* alloc memory for large data structures: too large to be on stack */
- elf = kmalloc(sizeof(*elf), GFP_KERNEL);
- if (!elf)
- goto out;
/*
* The number of segs are recored into ELF header as 16bit value.
* Please check DEFAULT_MAX_MAP_COUNT definition when you modify here.
@@ -2230,7 +2234,7 @@ static int elf_core_dump(struct coredump_params *cprm)
* Collect all the non-memory information about the process for the
* notes. This also sets up the file header.
*/
- if (!fill_note_info(elf, e_phnum, &info, cprm->siginfo, cprm->regs))
+ if (!fill_note_info(&elf, e_phnum, &info, cprm->siginfo, cprm->regs))
goto cleanup;
has_dumped = 1;
@@ -2238,7 +2242,7 @@ static int elf_core_dump(struct coredump_params *cprm)
fs = get_fs();
set_fs(KERNEL_DS);
- offset += sizeof(*elf); /* Elf header */
+ offset += sizeof(elf); /* Elf header */
offset += segs * sizeof(struct elf_phdr); /* Program headers */
/* Write notes phdr entry */
@@ -2257,11 +2261,13 @@ static int elf_core_dump(struct coredump_params *cprm)
dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);
- if (segs - 1 > ULONG_MAX / sizeof(*vma_filesz))
- goto end_coredump;
+ /*
+ * Zero vma process will get ZERO_SIZE_PTR here.
+ * Let coredump continue for register state at least.
+ */
vma_filesz = kvmalloc(array_size(sizeof(*vma_filesz), (segs - 1)),
GFP_KERNEL);
- if (ZERO_OR_NULL_PTR(vma_filesz))
+ if (!vma_filesz)
goto end_coredump;
for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
@@ -2281,12 +2287,12 @@ static int elf_core_dump(struct coredump_params *cprm)
shdr4extnum = kmalloc(sizeof(*shdr4extnum), GFP_KERNEL);
if (!shdr4extnum)
goto end_coredump;
- fill_extnum_info(elf, shdr4extnum, e_shoff, segs);
+ fill_extnum_info(&elf, shdr4extnum, e_shoff, segs);
}
offset = dataoff;
- if (!dump_emit(cprm, elf, sizeof(*elf)))
+ if (!dump_emit(cprm, &elf, sizeof(elf)))
goto end_coredump;
if (!dump_emit(cprm, phdr4note, sizeof(*phdr4note)))
@@ -2370,8 +2376,6 @@ cleanup:
kfree(shdr4extnum);
kvfree(vma_filesz);
kfree(phdr4note);
- kfree(elf);
-out:
return has_dumped;
}
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index de95ad27722f..9ab610cc9114 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -1290,7 +1290,7 @@ int btrfs_decompress_buf2page(const char *buf, unsigned long buf_start,
/* copy bytes from the working buffer into the pages */
while (working_bytes > 0) {
bytes = min_t(unsigned long, bvec.bv_len,
- PAGE_SIZE - buf_offset);
+ PAGE_SIZE - (buf_offset % PAGE_SIZE));
bytes = min(bytes, working_bytes);
kaddr = kmap_atomic(bvec.bv_page);
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index a6c90a003c12..05615a1099db 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -20,9 +20,13 @@
#include <linux/refcount.h>
#include "compression.h"
+/* workspace buffer size for s390 zlib hardware support */
+#define ZLIB_DFLTCC_BUF_SIZE (4 * PAGE_SIZE)
+
struct workspace {
z_stream strm;
char *buf;
+ unsigned int buf_size;
struct list_head list;
int level;
};
@@ -61,7 +65,21 @@ struct list_head *zlib_alloc_workspace(unsigned int level)
zlib_inflate_workspacesize());
workspace->strm.workspace = kvmalloc(workspacesize, GFP_KERNEL);
workspace->level = level;
- workspace->buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ workspace->buf = NULL;
+ /*
+ * In case of s390 zlib hardware support, allocate lager workspace
+ * buffer. If allocator fails, fall back to a single page buffer.
+ */
+ if (zlib_deflate_dfltcc_enabled()) {
+ workspace->buf = kmalloc(ZLIB_DFLTCC_BUF_SIZE,
+ __GFP_NOMEMALLOC | __GFP_NORETRY |
+ __GFP_NOWARN | GFP_NOIO);
+ workspace->buf_size = ZLIB_DFLTCC_BUF_SIZE;
+ }
+ if (!workspace->buf) {
+ workspace->buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ workspace->buf_size = PAGE_SIZE;
+ }
if (!workspace->strm.workspace || !workspace->buf)
goto fail;
@@ -85,6 +103,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
struct page *in_page = NULL;
struct page *out_page = NULL;
unsigned long bytes_left;
+ unsigned int in_buf_pages;
unsigned long len = *total_out;
unsigned long nr_dest_pages = *out_pages;
const unsigned long max_out = nr_dest_pages * PAGE_SIZE;
@@ -102,9 +121,6 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
workspace->strm.total_in = 0;
workspace->strm.total_out = 0;
- in_page = find_get_page(mapping, start >> PAGE_SHIFT);
- data_in = kmap(in_page);
-
out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
if (out_page == NULL) {
ret = -ENOMEM;
@@ -114,12 +130,51 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
pages[0] = out_page;
nr_pages = 1;
- workspace->strm.next_in = data_in;
+ workspace->strm.next_in = workspace->buf;
+ workspace->strm.avail_in = 0;
workspace->strm.next_out = cpage_out;
workspace->strm.avail_out = PAGE_SIZE;
- workspace->strm.avail_in = min(len, PAGE_SIZE);
while (workspace->strm.total_in < len) {
+ /*
+ * Get next input pages and copy the contents to
+ * the workspace buffer if required.
+ */
+ if (workspace->strm.avail_in == 0) {
+ bytes_left = len - workspace->strm.total_in;
+ in_buf_pages = min(DIV_ROUND_UP(bytes_left, PAGE_SIZE),
+ workspace->buf_size / PAGE_SIZE);
+ if (in_buf_pages > 1) {
+ int i;
+
+ for (i = 0; i < in_buf_pages; i++) {
+ if (in_page) {
+ kunmap(in_page);
+ put_page(in_page);
+ }
+ in_page = find_get_page(mapping,
+ start >> PAGE_SHIFT);
+ data_in = kmap(in_page);
+ memcpy(workspace->buf + i * PAGE_SIZE,
+ data_in, PAGE_SIZE);
+ start += PAGE_SIZE;
+ }
+ workspace->strm.next_in = workspace->buf;
+ } else {
+ if (in_page) {
+ kunmap(in_page);
+ put_page(in_page);
+ }
+ in_page = find_get_page(mapping,
+ start >> PAGE_SHIFT);
+ data_in = kmap(in_page);
+ start += PAGE_SIZE;
+ workspace->strm.next_in = data_in;
+ }
+ workspace->strm.avail_in = min(bytes_left,
+ (unsigned long) workspace->buf_size);
+ }
+
ret = zlib_deflate(&workspace->strm, Z_SYNC_FLUSH);
if (ret != Z_OK) {
pr_debug("BTRFS: deflate in loop returned %d\n",
@@ -161,33 +216,43 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
/* we're all done */
if (workspace->strm.total_in >= len)
break;
-
- /* we've read in a full page, get a new one */
- if (workspace->strm.avail_in == 0) {
- if (workspace->strm.total_out > max_out)
- break;
-
- bytes_left = len - workspace->strm.total_in;
- kunmap(in_page);
- put_page(in_page);
-
- start += PAGE_SIZE;
- in_page = find_get_page(mapping,
- start >> PAGE_SHIFT);
- data_in = kmap(in_page);
- workspace->strm.avail_in = min(bytes_left,
- PAGE_SIZE);
- workspace->strm.next_in = data_in;
- }
+ if (workspace->strm.total_out > max_out)
+ break;
}
workspace->strm.avail_in = 0;
- ret = zlib_deflate(&workspace->strm, Z_FINISH);
- zlib_deflateEnd(&workspace->strm);
-
- if (ret != Z_STREAM_END) {
- ret = -EIO;
- goto out;
+ /*
+ * Call deflate with Z_FINISH flush parameter providing more output
+ * space but no more input data, until it returns with Z_STREAM_END.
+ */
+ while (ret != Z_STREAM_END) {
+ ret = zlib_deflate(&workspace->strm, Z_FINISH);
+ if (ret == Z_STREAM_END)
+ break;
+ if (ret != Z_OK && ret != Z_BUF_ERROR) {
+ zlib_deflateEnd(&workspace->strm);
+ ret = -EIO;
+ goto out;
+ } else if (workspace->strm.avail_out == 0) {
+ /* get another page for the stream end */
+ kunmap(out_page);
+ if (nr_pages == nr_dest_pages) {
+ out_page = NULL;
+ ret = -E2BIG;
+ goto out;
+ }
+ out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
+ if (out_page == NULL) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ cpage_out = kmap(out_page);
+ pages[nr_pages] = out_page;
+ nr_pages++;
+ workspace->strm.avail_out = PAGE_SIZE;
+ workspace->strm.next_out = cpage_out;
+ }
}
+ zlib_deflateEnd(&workspace->strm);
if (workspace->strm.total_out >= workspace->strm.total_in) {
ret = -E2BIG;
@@ -231,7 +296,7 @@ int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
workspace->strm.total_out = 0;
workspace->strm.next_out = workspace->buf;
- workspace->strm.avail_out = PAGE_SIZE;
+ workspace->strm.avail_out = workspace->buf_size;
/* If it's deflate, and it's got no preset dictionary, then
we can tell zlib to skip the adler32 check. */
@@ -270,7 +335,7 @@ int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
}
workspace->strm.next_out = workspace->buf;
- workspace->strm.avail_out = PAGE_SIZE;
+ workspace->strm.avail_out = workspace->buf_size;
if (workspace->strm.avail_in == 0) {
unsigned long tmp;
@@ -320,7 +385,7 @@ int zlib_decompress(struct list_head *ws, unsigned char *data_in,
workspace->strm.total_in = 0;
workspace->strm.next_out = workspace->buf;
- workspace->strm.avail_out = PAGE_SIZE;
+ workspace->strm.avail_out = workspace->buf_size;
workspace->strm.total_out = 0;
/* If it's deflate, and it's got no preset dictionary, then
we can tell zlib to skip the adler32 check. */
@@ -364,7 +429,7 @@ int zlib_decompress(struct list_head *ws, unsigned char *data_in,
buf_offset = 0;
bytes = min(PAGE_SIZE - pg_offset,
- PAGE_SIZE - buf_offset);
+ PAGE_SIZE - (buf_offset % PAGE_SIZE));
bytes = min(bytes, bytes_left);
kaddr = kmap_atomic(dest_page);
@@ -375,7 +440,7 @@ int zlib_decompress(struct list_head *ws, unsigned char *data_in,
bytes_left -= bytes;
next:
workspace->strm.next_out = workspace->buf;
- workspace->strm.avail_out = PAGE_SIZE;
+ workspace->strm.avail_out = workspace->buf_size;
}
if (ret != Z_STREAM_END && bytes_left != 0)
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
deleted file mode 100644
index 358ea2ecf36b..000000000000
--- a/fs/compat_ioctl.c
+++ /dev/null
@@ -1,261 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * ioctl32.c: Conversion between 32bit and 64bit native ioctls.
- *
- * Copyright (C) 1997-2000 Jakub Jelinek (jakub@redhat.com)
- * Copyright (C) 1998 Eddie C. Dost (ecd@skynet.be)
- * Copyright (C) 2001,2002 Andi Kleen, SuSE Labs
- * Copyright (C) 2003 Pavel Machek (pavel@ucw.cz)
- *
- * These routines maintain argument size conversion between 32bit and 64bit
- * ioctls.
- */
-
-#include <linux/types.h>
-#include <linux/compat.h>
-#include <linux/kernel.h>
-#include <linux/capability.h>
-#include <linux/compiler.h>
-#include <linux/sched.h>
-#include <linux/smp.h>
-#include <linux/ioctl.h>
-#include <linux/if.h>
-#include <linux/raid/md_u.h>
-#include <linux/falloc.h>
-#include <linux/file.h>
-#include <linux/ppp-ioctl.h>
-#include <linux/if_pppox.h>
-#include <linux/tty.h>
-#include <linux/vt_kern.h>
-#include <linux/blkdev.h>
-#include <linux/serial.h>
-#include <linux/ctype.h>
-#include <linux/syscalls.h>
-#include <linux/gfp.h>
-#include <linux/cec.h>
-
-#include "internal.h"
-
-#ifdef CONFIG_BLOCK
-#include <linux/cdrom.h>
-#include <linux/fd.h>
-#include <scsi/scsi.h>
-#include <scsi/scsi_ioctl.h>
-#include <scsi/sg.h>
-#endif
-
-#include <linux/uaccess.h>
-#include <linux/watchdog.h>
-
-#include <linux/hiddev.h>
-
-
-#include <linux/sort.h>
-
-/*
- * simple reversible transform to make our table more evenly
- * distributed after sorting.
- */
-#define XFORM(i) (((i) ^ ((i) << 27) ^ ((i) << 17)) & 0xffffffff)
-
-#define COMPATIBLE_IOCTL(cmd) XFORM((u32)cmd),
-static unsigned int ioctl_pointer[] = {
-#ifdef CONFIG_BLOCK
-/* Big S */
-COMPATIBLE_IOCTL(SCSI_IOCTL_GET_IDLUN)
-COMPATIBLE_IOCTL(SCSI_IOCTL_DOORLOCK)
-COMPATIBLE_IOCTL(SCSI_IOCTL_DOORUNLOCK)
-COMPATIBLE_IOCTL(SCSI_IOCTL_TEST_UNIT_READY)
-COMPATIBLE_IOCTL(SCSI_IOCTL_GET_BUS_NUMBER)
-COMPATIBLE_IOCTL(SCSI_IOCTL_SEND_COMMAND)
-COMPATIBLE_IOCTL(SCSI_IOCTL_PROBE_HOST)
-COMPATIBLE_IOCTL(SCSI_IOCTL_GET_PCI)
-#endif
-#ifdef CONFIG_BLOCK
-/* SG stuff */
-COMPATIBLE_IOCTL(SG_IO)
-COMPATIBLE_IOCTL(SG_GET_REQUEST_TABLE)
-COMPATIBLE_IOCTL(SG_SET_TIMEOUT)
-COMPATIBLE_IOCTL(SG_GET_TIMEOUT)
-COMPATIBLE_IOCTL(SG_EMULATED_HOST)
-COMPATIBLE_IOCTL(SG_GET_TRANSFORM)
-COMPATIBLE_IOCTL(SG_SET_RESERVED_SIZE)
-COMPATIBLE_IOCTL(SG_GET_RESERVED_SIZE)
-COMPATIBLE_IOCTL(SG_GET_SCSI_ID)
-COMPATIBLE_IOCTL(SG_SET_FORCE_LOW_DMA)
-COMPATIBLE_IOCTL(SG_GET_LOW_DMA)
-COMPATIBLE_IOCTL(SG_SET_FORCE_PACK_ID)
-COMPATIBLE_IOCTL(SG_GET_PACK_ID)
-COMPATIBLE_IOCTL(SG_GET_NUM_WAITING)
-COMPATIBLE_IOCTL(SG_SET_DEBUG)
-COMPATIBLE_IOCTL(SG_GET_SG_TABLESIZE)
-COMPATIBLE_IOCTL(SG_GET_COMMAND_Q)
-COMPATIBLE_IOCTL(SG_SET_COMMAND_Q)
-COMPATIBLE_IOCTL(SG_GET_VERSION_NUM)
-COMPATIBLE_IOCTL(SG_NEXT_CMD_LEN)
-COMPATIBLE_IOCTL(SG_SCSI_RESET)
-COMPATIBLE_IOCTL(SG_GET_REQUEST_TABLE)
-COMPATIBLE_IOCTL(SG_SET_KEEP_ORPHAN)
-COMPATIBLE_IOCTL(SG_GET_KEEP_ORPHAN)
-#endif
-};
-
-/*
- * Convert common ioctl arguments based on their command number
- *
- * Please do not add any code in here. Instead, implement
- * a compat_ioctl operation in the place that handleѕ the
- * ioctl for the native case.
- */
-static long do_ioctl_trans(unsigned int cmd,
- unsigned long arg, struct file *file)
-{
- return -ENOIOCTLCMD;
-}
-
-static int compat_ioctl_check_table(unsigned int xcmd)
-{
-#ifdef CONFIG_BLOCK
- int i;
- const int max = ARRAY_SIZE(ioctl_pointer) - 1;
-
- BUILD_BUG_ON(max >= (1 << 16));
-
- /* guess initial offset into table, assuming a
- normalized distribution */
- i = ((xcmd >> 16) * max) >> 16;
-
- /* do linear search up first, until greater or equal */
- while (ioctl_pointer[i] < xcmd && i < max)
- i++;
-
- /* then do linear search down */
- while (ioctl_pointer[i] > xcmd && i > 0)
- i--;
-
- return ioctl_pointer[i] == xcmd;
-#else
- return 0;
-#endif
-}
-
-COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd,
- compat_ulong_t, arg32)
-{
- unsigned long arg = arg32;
- struct fd f = fdget(fd);
- int error = -EBADF;
- if (!f.file)
- goto out;
-
- /* RED-PEN how should LSM module know it's handling 32bit? */
- error = security_file_ioctl(f.file, cmd, arg);
- if (error)
- goto out_fput;
-
- switch (cmd) {
- /* these are never seen by ->ioctl(), no argument or int argument */
- case FIOCLEX:
- case FIONCLEX:
- case FIFREEZE:
- case FITHAW:
- case FICLONE:
- goto do_ioctl;
- /* these are never seen by ->ioctl(), pointer argument */
- case FIONBIO:
- case FIOASYNC:
- case FIOQSIZE:
- case FS_IOC_FIEMAP:
- case FIGETBSZ:
- case FICLONERANGE:
- case FIDEDUPERANGE:
- goto found_handler;
- /*
- * The next group is the stuff handled inside file_ioctl().
- * For regular files these never reach ->ioctl(); for
- * devices, sockets, etc. they do and one (FIONREAD) is
- * even accepted in some cases. In all those cases
- * argument has the same type, so we can handle these
- * here, shunting them towards do_vfs_ioctl().
- * ->compat_ioctl() will never see any of those.
- */
- /* pointer argument, never actually handled by ->ioctl() */
- case FIBMAP:
- goto found_handler;
- /* handled by some ->ioctl(); always a pointer to int */
- case FIONREAD:
- goto found_handler;
- /* these get messy on amd64 due to alignment differences */
-#if defined(CONFIG_X86_64)
- case FS_IOC_RESVSP_32:
- case FS_IOC_RESVSP64_32:
- error = compat_ioctl_preallocate(f.file, 0, compat_ptr(arg));
- goto out_fput;
- case FS_IOC_UNRESVSP_32:
- case FS_IOC_UNRESVSP64_32:
- error = compat_ioctl_preallocate(f.file, FALLOC_FL_PUNCH_HOLE,
- compat_ptr(arg));
- goto out_fput;
- case FS_IOC_ZERO_RANGE_32:
- error = compat_ioctl_preallocate(f.file, FALLOC_FL_ZERO_RANGE,
- compat_ptr(arg));
- goto out_fput;
-#else
- case FS_IOC_RESVSP:
- case FS_IOC_RESVSP64:
- case FS_IOC_UNRESVSP:
- case FS_IOC_UNRESVSP64:
- case FS_IOC_ZERO_RANGE:
- goto found_handler;
-#endif
-
- default:
- if (f.file->f_op->compat_ioctl) {
- error = f.file->f_op->compat_ioctl(f.file, cmd, arg);
- if (error != -ENOIOCTLCMD)
- goto out_fput;
- }
-
- if (!f.file->f_op->unlocked_ioctl)
- goto do_ioctl;
- break;
- }
-
- if (compat_ioctl_check_table(XFORM(cmd)))
- goto found_handler;
-
- error = do_ioctl_trans(cmd, arg, f.file);
- if (error == -ENOIOCTLCMD)
- error = -ENOTTY;
-
- goto out_fput;
-
- found_handler:
- arg = (unsigned long)compat_ptr(arg);
- do_ioctl:
- error = do_vfs_ioctl(f.file, fd, cmd, arg);
- out_fput:
- fdput(f);
- out:
- return error;
-}
-
-static int __init init_sys32_ioctl_cmp(const void *p, const void *q)
-{
- unsigned int a, b;
- a = *(unsigned int *)p;
- b = *(unsigned int *)q;
- if (a > b)
- return 1;
- if (a < b)
- return -1;
- return 0;
-}
-
-static int __init init_sys32_ioctl(void)
-{
- sort(ioctl_pointer, ARRAY_SIZE(ioctl_pointer), sizeof(*ioctl_pointer),
- init_sys32_ioctl_cmp, NULL);
- return 0;
-}
-__initcall(init_sys32_ioctl);
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index dede25247b81..634b09d18b77 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -142,18 +142,21 @@ EXPORT_SYMBOL_GPL(debugfs_file_put);
* We also need to exclude any file that has ways to write or alter it as root
* can bypass the permissions check.
*/
-static bool debugfs_is_locked_down(struct inode *inode,
- struct file *filp,
- const struct file_operations *real_fops)
+static int debugfs_locked_down(struct inode *inode,
+ struct file *filp,
+ const struct file_operations *real_fops)
{
if ((inode->i_mode & 07777) == 0444 &&
!(filp->f_mode & FMODE_WRITE) &&
!real_fops->unlocked_ioctl &&
!real_fops->compat_ioctl &&
!real_fops->mmap)
- return false;
+ return 0;
- return security_locked_down(LOCKDOWN_DEBUGFS);
+ if (security_locked_down(LOCKDOWN_DEBUGFS))
+ return -EPERM;
+
+ return 0;
}
static int open_proxy_open(struct inode *inode, struct file *filp)
@@ -168,7 +171,7 @@ static int open_proxy_open(struct inode *inode, struct file *filp)
real_fops = debugfs_real_fops(filp);
- r = debugfs_is_locked_down(inode, filp, real_fops);
+ r = debugfs_locked_down(inode, filp, real_fops);
if (r)
goto out;
@@ -298,7 +301,7 @@ static int full_proxy_open(struct inode *inode, struct file *filp)
real_fops = debugfs_real_fops(filp);
- r = debugfs_is_locked_down(inode, filp, real_fops);
+ r = debugfs_locked_down(inode, filp, real_fops);
if (r)
goto out;
@@ -496,10 +499,10 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_u32_wo, NULL, debugfs_u32_set, "%llu\n");
* This function will return a pointer to a dentry if it succeeds. This
* pointer must be passed to the debugfs_remove() function when the file is
* to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be
+ * you are responsible here.) If an error occurs, ERR_PTR(-ERROR) will be
* returned.
*
- * If debugfs is not enabled in the kernel, the value %ERR_PTR(-ENODEV) will
+ * If debugfs is not enabled in the kernel, the value ERR_PTR(-ENODEV) will
* be returned.
*/
struct dentry *debugfs_create_u32(const char *name, umode_t mode,
@@ -581,10 +584,10 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_ulong_wo, NULL, debugfs_ulong_set, "%llu\n");
* This function will return a pointer to a dentry if it succeeds. This
* pointer must be passed to the debugfs_remove() function when the file is
* to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be
+ * you are responsible here.) If an error occurs, ERR_PTR(-ERROR) will be
* returned.
*
- * If debugfs is not enabled in the kernel, the value %ERR_PTR(-ENODEV) will
+ * If debugfs is not enabled in the kernel, the value ERR_PTR(-ENODEV) will
* be returned.
*/
struct dentry *debugfs_create_ulong(const char *name, umode_t mode,
@@ -846,10 +849,10 @@ static const struct file_operations fops_bool_wo = {
* This function will return a pointer to a dentry if it succeeds. This
* pointer must be passed to the debugfs_remove() function when the file is
* to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be
+ * you are responsible here.) If an error occurs, ERR_PTR(-ERROR) will be
* returned.
*
- * If debugfs is not enabled in the kernel, the value %ERR_PTR(-ENODEV) will
+ * If debugfs is not enabled in the kernel, the value ERR_PTR(-ENODEV) will
* be returned.
*/
struct dentry *debugfs_create_bool(const char *name, umode_t mode,
@@ -899,10 +902,10 @@ static const struct file_operations fops_blob = {
* This function will return a pointer to a dentry if it succeeds. This
* pointer must be passed to the debugfs_remove() function when the file is
* to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be
+ * you are responsible here.) If an error occurs, ERR_PTR(-ERROR) will be
* returned.
*
- * If debugfs is not enabled in the kernel, the value %ERR_PTR(-ENODEV) will
+ * If debugfs is not enabled in the kernel, the value ERR_PTR(-ENODEV) will
* be returned.
*/
struct dentry *debugfs_create_blob(const char *name, umode_t mode,
@@ -1091,10 +1094,10 @@ static const struct file_operations fops_regset32 = {
* This function will return a pointer to a dentry if it succeeds. This
* pointer must be passed to the debugfs_remove() function when the file is
* to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be
+ * you are responsible here.) If an error occurs, ERR_PTR(-ERROR) will be
* returned.
*
- * If debugfs is not enabled in the kernel, the value %ERR_PTR(-ENODEV) will
+ * If debugfs is not enabled in the kernel, the value ERR_PTR(-ENODEV) will
* be returned.
*/
struct dentry *debugfs_create_regset32(const char *name, umode_t mode,
@@ -1158,4 +1161,3 @@ struct dentry *debugfs_create_devm_seqfile(struct device *dev, const char *name,
&debugfs_devm_entry_ops);
}
EXPORT_SYMBOL_GPL(debugfs_create_devm_seqfile);
-
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index f4d8df5e4714..dc6cffc4feba 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -423,7 +423,7 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode,
* This function will return a pointer to a dentry if it succeeds. This
* pointer must be passed to the debugfs_remove() function when the file is
* to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be
+ * you are responsible here.) If an error occurs, ERR_PTR(-ERROR) will be
* returned.
*
* If debugfs is not enabled in the kernel, the value -%ENODEV will be
@@ -502,7 +502,7 @@ EXPORT_SYMBOL_GPL(debugfs_create_file_unsafe);
* This function will return a pointer to a dentry if it succeeds. This
* pointer must be passed to the debugfs_remove() function when the file is
* to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be
+ * you are responsible here.) If an error occurs, ERR_PTR(-ERROR) will be
* returned.
*
* If debugfs is not enabled in the kernel, the value -%ENODEV will be
@@ -534,7 +534,7 @@ EXPORT_SYMBOL_GPL(debugfs_create_file_size);
* This function will return a pointer to a dentry if it succeeds. This
* pointer must be passed to the debugfs_remove() function when the file is
* to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be
+ * you are responsible here.) If an error occurs, ERR_PTR(-ERROR) will be
* returned.
*
* If debugfs is not enabled in the kernel, the value -%ENODEV will be
@@ -627,7 +627,7 @@ EXPORT_SYMBOL(debugfs_create_automount);
* This function will return a pointer to a dentry if it succeeds. This
* pointer must be passed to the debugfs_remove() function when the symbolic
* link is to be removed (no automatic cleanup happens if your module is
- * unloaded, you are responsible here.) If an error occurs, %ERR_PTR(-ERROR)
+ * unloaded, you are responsible here.) If an error occurs, ERR_PTR(-ERROR)
* will be returned.
*
* If debugfs is not enabled in the kernel, the value -%ENODEV will be
@@ -906,4 +906,3 @@ static int __init debugfs_init(void)
return retval;
}
core_initcall(debugfs_init);
-
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 3951d39b9b75..cdfaf4f0e11a 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -1035,7 +1035,7 @@ static void sctp_connect_to_sock(struct connection *con)
int result;
int addr_len;
struct socket *sock;
- struct timeval tv = { .tv_sec = 5, .tv_usec = 0 };
+ struct __kernel_sock_timeval tv = { .tv_sec = 5, .tv_usec = 0 };
if (con->nodeid == 0) {
log_print("attempt to connect sock 0 foiled");
@@ -1087,12 +1087,12 @@ static void sctp_connect_to_sock(struct connection *con)
* since O_NONBLOCK argument in connect() function does not work here,
* then, we should restore the default value of this attribute.
*/
- kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO_OLD, (char *)&tv,
+ kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO_NEW, (char *)&tv,
sizeof(tv));
result = sock->ops->connect(sock, (struct sockaddr *)&daddr, addr_len,
0);
memset(&tv, 0, sizeof(tv));
- kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO_OLD, (char *)&tv,
+ kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO_NEW, (char *)&tv,
sizeof(tv));
if (result == -EINPROGRESS)
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index f91db24bbf3b..db1ef144c63a 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -1586,7 +1586,7 @@ ecryptfs_process_key_cipher(struct crypto_skcipher **key_tfm,
}
crypto_skcipher_set_flags(*key_tfm, CRYPTO_TFM_REQ_FORBID_WEAK_KEYS);
if (*key_size == 0)
- *key_size = crypto_skcipher_default_keysize(*key_tfm);
+ *key_size = crypto_skcipher_max_keysize(*key_tfm);
get_random_bytes(dummy_key, *key_size);
rc = crypto_skcipher_setkey(*key_tfm, dummy_key, *key_size);
if (rc) {
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index 216fbe6a4837..7d326aa0308e 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -2204,9 +2204,9 @@ write_tag_3_packet(char *dest, size_t *remaining_bytes,
if (mount_crypt_stat->global_default_cipher_key_size == 0) {
printk(KERN_WARNING "No key size specified at mount; "
"defaulting to [%d]\n",
- crypto_skcipher_default_keysize(tfm));
+ crypto_skcipher_max_keysize(tfm));
mount_crypt_stat->global_default_cipher_key_size =
- crypto_skcipher_default_keysize(tfm);
+ crypto_skcipher_max_keysize(tfm);
}
if (crypt_stat->key_size == 0)
crypt_stat->key_size =
diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c
index 2890a67a1ded..5779a15c2cd6 100644
--- a/fs/erofs/decompressor.c
+++ b/fs/erofs/decompressor.c
@@ -306,24 +306,22 @@ static int z_erofs_shifted_transform(const struct z_erofs_decompress_req *rq,
}
src = kmap_atomic(*rq->in);
- if (!rq->out[0]) {
- dst = NULL;
- } else {
+ if (rq->out[0]) {
dst = kmap_atomic(rq->out[0]);
memcpy(dst + rq->pageofs_out, src, righthalf);
+ kunmap_atomic(dst);
}
- if (rq->out[1] == *rq->in) {
- memmove(src, src + righthalf, rq->pageofs_out);
- } else if (nrpages_out == 2) {
- if (dst)
- kunmap_atomic(dst);
+ if (nrpages_out == 2) {
DBG_BUGON(!rq->out[1]);
- dst = kmap_atomic(rq->out[1]);
- memcpy(dst, src + righthalf, rq->pageofs_out);
+ if (rq->out[1] == *rq->in) {
+ memmove(src, src + righthalf, rq->pageofs_out);
+ } else {
+ dst = kmap_atomic(rq->out[1]);
+ memcpy(dst, src + righthalf, rq->pageofs_out);
+ kunmap_atomic(dst);
+ }
}
- if (dst)
- kunmap_atomic(dst);
kunmap_atomic(src);
return 0;
}
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 1ed5beff7d11..c4c6dcdc89ad 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -401,9 +401,9 @@ static inline void *erofs_get_pcpubuf(unsigned int pagenr)
#ifdef CONFIG_EROFS_FS_ZIP
int erofs_workgroup_put(struct erofs_workgroup *grp);
struct erofs_workgroup *erofs_find_workgroup(struct super_block *sb,
- pgoff_t index, bool *tag);
+ pgoff_t index);
int erofs_register_workgroup(struct super_block *sb,
- struct erofs_workgroup *grp, bool tag);
+ struct erofs_workgroup *grp);
void erofs_workgroup_free_rcu(struct erofs_workgroup *grp);
void erofs_shrinker_register(struct super_block *sb);
void erofs_shrinker_unregister(struct super_block *sb);
diff --git a/fs/erofs/utils.c b/fs/erofs/utils.c
index 1e8e1450d5b0..fddc5059c930 100644
--- a/fs/erofs/utils.c
+++ b/fs/erofs/utils.c
@@ -59,7 +59,7 @@ repeat:
}
struct erofs_workgroup *erofs_find_workgroup(struct super_block *sb,
- pgoff_t index, bool *tag)
+ pgoff_t index)
{
struct erofs_sb_info *sbi = EROFS_SB(sb);
struct erofs_workgroup *grp;
@@ -68,9 +68,6 @@ repeat:
rcu_read_lock();
grp = radix_tree_lookup(&sbi->workstn_tree, index);
if (grp) {
- *tag = xa_pointer_tag(grp);
- grp = xa_untag_pointer(grp);
-
if (erofs_workgroup_get(grp)) {
/* prefer to relax rcu read side */
rcu_read_unlock();
@@ -84,8 +81,7 @@ repeat:
}
int erofs_register_workgroup(struct super_block *sb,
- struct erofs_workgroup *grp,
- bool tag)
+ struct erofs_workgroup *grp)
{
struct erofs_sb_info *sbi;
int err;
@@ -103,8 +99,6 @@ int erofs_register_workgroup(struct super_block *sb,
sbi = EROFS_SB(sb);
xa_lock(&sbi->workstn_tree);
- grp = xa_tag_pointer(grp, tag);
-
/*
* Bump up reference count before making this workgroup
* visible to other users in order to avoid potential UAF
@@ -175,8 +169,7 @@ static bool erofs_try_to_release_workgroup(struct erofs_sb_info *sbi,
* however in order to avoid some race conditions, add a
* DBG_BUGON to observe this in advance.
*/
- DBG_BUGON(xa_untag_pointer(radix_tree_delete(&sbi->workstn_tree,
- grp->index)) != grp);
+ DBG_BUGON(radix_tree_delete(&sbi->workstn_tree, grp->index) != grp);
/*
* If managed cache is on, last refcount should indicate
@@ -201,7 +194,7 @@ repeat:
batch, first_index, PAGEVEC_SIZE);
for (i = 0; i < found; ++i) {
- struct erofs_workgroup *grp = xa_untag_pointer(batch[i]);
+ struct erofs_workgroup *grp = batch[i];
first_index = grp->index + 1;
diff --git a/fs/erofs/xattr.h b/fs/erofs/xattr.h
index 3585b84d2f20..50966f1c676e 100644
--- a/fs/erofs/xattr.h
+++ b/fs/erofs/xattr.h
@@ -46,18 +46,19 @@ extern const struct xattr_handler erofs_xattr_security_handler;
static inline const struct xattr_handler *erofs_xattr_handler(unsigned int idx)
{
-static const struct xattr_handler *xattr_handler_map[] = {
- [EROFS_XATTR_INDEX_USER] = &erofs_xattr_user_handler,
+ static const struct xattr_handler *xattr_handler_map[] = {
+ [EROFS_XATTR_INDEX_USER] = &erofs_xattr_user_handler,
#ifdef CONFIG_EROFS_FS_POSIX_ACL
- [EROFS_XATTR_INDEX_POSIX_ACL_ACCESS] = &posix_acl_access_xattr_handler,
- [EROFS_XATTR_INDEX_POSIX_ACL_DEFAULT] =
- &posix_acl_default_xattr_handler,
+ [EROFS_XATTR_INDEX_POSIX_ACL_ACCESS] =
+ &posix_acl_access_xattr_handler,
+ [EROFS_XATTR_INDEX_POSIX_ACL_DEFAULT] =
+ &posix_acl_default_xattr_handler,
#endif
- [EROFS_XATTR_INDEX_TRUSTED] = &erofs_xattr_trusted_handler,
+ [EROFS_XATTR_INDEX_TRUSTED] = &erofs_xattr_trusted_handler,
#ifdef CONFIG_EROFS_FS_SECURITY
- [EROFS_XATTR_INDEX_SECURITY] = &erofs_xattr_security_handler,
+ [EROFS_XATTR_INDEX_SECURITY] = &erofs_xattr_security_handler,
#endif
-};
+ };
return idx && idx < ARRAY_SIZE(xattr_handler_map) ?
xattr_handler_map[idx] : NULL;
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index ca99425a4536..80e47f07d946 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -345,9 +345,8 @@ static int z_erofs_lookup_collection(struct z_erofs_collector *clt,
struct z_erofs_pcluster *pcl;
struct z_erofs_collection *cl;
unsigned int length;
- bool tag;
- grp = erofs_find_workgroup(inode->i_sb, map->m_pa >> PAGE_SHIFT, &tag);
+ grp = erofs_find_workgroup(inode->i_sb, map->m_pa >> PAGE_SHIFT);
if (!grp)
return -ENOENT;
@@ -438,7 +437,7 @@ static int z_erofs_register_collection(struct z_erofs_collector *clt,
*/
mutex_trylock(&cl->lock);
- err = erofs_register_workgroup(inode->i_sb, &pcl->obj, 0);
+ err = erofs_register_workgroup(inode->i_sb, &pcl->obj);
if (err) {
mutex_unlock(&cl->lock);
kmem_cache_free(pcluster_cachep, pcl);
@@ -1149,21 +1148,7 @@ static void move_to_bypass_jobqueue(struct z_erofs_pcluster *pcl,
qtail[JQ_BYPASS] = &pcl->next;
}
-static bool postsubmit_is_all_bypassed(struct z_erofs_decompressqueue *q[],
- unsigned int nr_bios, bool force_fg)
-{
- /*
- * although background is preferred, no one is pending for submission.
- * don't issue workqueue for decompression but drop it directly instead.
- */
- if (force_fg || nr_bios)
- return false;
-
- kvfree(q[JQ_SUBMIT]);
- return true;
-}
-
-static bool z_erofs_submit_queue(struct super_block *sb,
+static void z_erofs_submit_queue(struct super_block *sb,
z_erofs_next_pcluster_t owned_head,
struct list_head *pagepool,
struct z_erofs_decompressqueue *fgq,
@@ -1172,19 +1157,12 @@ static bool z_erofs_submit_queue(struct super_block *sb,
struct erofs_sb_info *const sbi = EROFS_SB(sb);
z_erofs_next_pcluster_t qtail[NR_JOBQUEUES];
struct z_erofs_decompressqueue *q[NR_JOBQUEUES];
- struct bio *bio;
void *bi_private;
/* since bio will be NULL, no need to initialize last_index */
pgoff_t uninitialized_var(last_index);
- bool force_submit = false;
- unsigned int nr_bios;
-
- if (owned_head == Z_EROFS_PCLUSTER_TAIL)
- return false;
+ unsigned int nr_bios = 0;
+ struct bio *bio = NULL;
- force_submit = false;
- bio = NULL;
- nr_bios = 0;
bi_private = jobqueueset_init(sb, q, fgq, force_fg);
qtail[JQ_BYPASS] = &q[JQ_BYPASS]->head;
qtail[JQ_SUBMIT] = &q[JQ_SUBMIT]->head;
@@ -1194,11 +1172,9 @@ static bool z_erofs_submit_queue(struct super_block *sb,
do {
struct z_erofs_pcluster *pcl;
- unsigned int clusterpages;
- pgoff_t first_index;
- struct page *page;
- unsigned int i = 0, bypass = 0;
- int err;
+ pgoff_t cur, end;
+ unsigned int i = 0;
+ bool bypass = true;
/* no possible 'owned_head' equals the following */
DBG_BUGON(owned_head == Z_EROFS_PCLUSTER_TAIL_CLOSED);
@@ -1206,55 +1182,50 @@ static bool z_erofs_submit_queue(struct super_block *sb,
pcl = container_of(owned_head, struct z_erofs_pcluster, next);
- clusterpages = BIT(pcl->clusterbits);
+ cur = pcl->obj.index;
+ end = cur + BIT(pcl->clusterbits);
/* close the main owned chain at first */
owned_head = cmpxchg(&pcl->next, Z_EROFS_PCLUSTER_TAIL,
Z_EROFS_PCLUSTER_TAIL_CLOSED);
- first_index = pcl->obj.index;
- force_submit |= (first_index != last_index + 1);
+ do {
+ struct page *page;
+ int err;
-repeat:
- page = pickup_page_for_submission(pcl, i, pagepool,
- MNGD_MAPPING(sbi),
- GFP_NOFS);
- if (!page) {
- force_submit = true;
- ++bypass;
- goto skippage;
- }
+ page = pickup_page_for_submission(pcl, i++, pagepool,
+ MNGD_MAPPING(sbi),
+ GFP_NOFS);
+ if (!page)
+ continue;
- if (bio && force_submit) {
+ if (bio && cur != last_index + 1) {
submit_bio_retry:
- submit_bio(bio);
- bio = NULL;
- }
-
- if (!bio) {
- bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
+ submit_bio(bio);
+ bio = NULL;
+ }
- bio->bi_end_io = z_erofs_decompressqueue_endio;
- bio_set_dev(bio, sb->s_bdev);
- bio->bi_iter.bi_sector = (sector_t)(first_index + i) <<
- LOG_SECTORS_PER_BLOCK;
- bio->bi_private = bi_private;
- bio->bi_opf = REQ_OP_READ;
+ if (!bio) {
+ bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
- ++nr_bios;
- }
+ bio->bi_end_io = z_erofs_decompressqueue_endio;
+ bio_set_dev(bio, sb->s_bdev);
+ bio->bi_iter.bi_sector = (sector_t)cur <<
+ LOG_SECTORS_PER_BLOCK;
+ bio->bi_private = bi_private;
+ bio->bi_opf = REQ_OP_READ;
+ ++nr_bios;
+ }
- err = bio_add_page(bio, page, PAGE_SIZE, 0);
- if (err < PAGE_SIZE)
- goto submit_bio_retry;
+ err = bio_add_page(bio, page, PAGE_SIZE, 0);
+ if (err < PAGE_SIZE)
+ goto submit_bio_retry;
- force_submit = false;
- last_index = first_index + i;
-skippage:
- if (++i < clusterpages)
- goto repeat;
+ last_index = cur;
+ bypass = false;
+ } while (++cur < end);
- if (bypass < clusterpages)
+ if (!bypass)
qtail[JQ_SUBMIT] = &pcl->next;
else
move_to_bypass_jobqueue(pcl, qtail, owned_head);
@@ -1263,11 +1234,15 @@ skippage:
if (bio)
submit_bio(bio);
- if (postsubmit_is_all_bypassed(q, nr_bios, *force_fg))
- return true;
-
+ /*
+ * although background is preferred, no one is pending for submission.
+ * don't issue workqueue for decompression but drop it directly instead.
+ */
+ if (!*force_fg && !nr_bios) {
+ kvfree(q[JQ_SUBMIT]);
+ return;
+ }
z_erofs_decompress_kickoff(q[JQ_SUBMIT], *force_fg, nr_bios);
- return true;
}
static void z_erofs_runqueue(struct super_block *sb,
@@ -1276,9 +1251,9 @@ static void z_erofs_runqueue(struct super_block *sb,
{
struct z_erofs_decompressqueue io[NR_JOBQUEUES];
- if (!z_erofs_submit_queue(sb, clt->owned_head,
- pagepool, io, &force_fg))
+ if (clt->owned_head == Z_EROFS_PCLUSTER_TAIL)
return;
+ z_erofs_submit_queue(sb, clt->owned_head, pagepool, io, &force_fg);
/* handle bypass queue (no i/o pclusters) immediately */
z_erofs_decompress_queue(&io[JQ_BYPASS], pagepool);
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 67a395039268..b041b66002db 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -354,12 +354,6 @@ static inline struct epitem *ep_item_from_epqueue(poll_table *p)
return container_of(p, struct ep_pqueue, pt)->epi;
}
-/* Tells if the epoll_ctl(2) operation needs an event copy from userspace */
-static inline int ep_op_has_event(int op)
-{
- return op != EPOLL_CTL_DEL;
-}
-
/* Initialize the poll safe wake up structure */
static void ep_nested_calls_init(struct nested_calls *ncalls)
{
@@ -2074,27 +2068,28 @@ SYSCALL_DEFINE1(epoll_create, int, size)
return do_epoll_create(0);
}
-/*
- * The following function implements the controller interface for
- * the eventpoll file that enables the insertion/removal/change of
- * file descriptors inside the interest set.
- */
-SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
- struct epoll_event __user *, event)
+static inline int epoll_mutex_lock(struct mutex *mutex, int depth,
+ bool nonblock)
+{
+ if (!nonblock) {
+ mutex_lock_nested(mutex, depth);
+ return 0;
+ }
+ if (mutex_trylock(mutex))
+ return 0;
+ return -EAGAIN;
+}
+
+int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds,
+ bool nonblock)
{
int error;
int full_check = 0;
struct fd f, tf;
struct eventpoll *ep;
struct epitem *epi;
- struct epoll_event epds;
struct eventpoll *tep = NULL;
- error = -EFAULT;
- if (ep_op_has_event(op) &&
- copy_from_user(&epds, event, sizeof(struct epoll_event)))
- goto error_return;
-
error = -EBADF;
f = fdget(epfd);
if (!f.file)
@@ -2112,7 +2107,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
/* Check if EPOLLWAKEUP is allowed */
if (ep_op_has_event(op))
- ep_take_care_of_epollwakeup(&epds);
+ ep_take_care_of_epollwakeup(epds);
/*
* We have to check that the file structure underneath the file descriptor
@@ -2128,11 +2123,11 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
* so EPOLLEXCLUSIVE is not allowed for a EPOLL_CTL_MOD operation.
* Also, we do not currently supported nested exclusive wakeups.
*/
- if (ep_op_has_event(op) && (epds.events & EPOLLEXCLUSIVE)) {
+ if (ep_op_has_event(op) && (epds->events & EPOLLEXCLUSIVE)) {
if (op == EPOLL_CTL_MOD)
goto error_tgt_fput;
if (op == EPOLL_CTL_ADD && (is_file_epoll(tf.file) ||
- (epds.events & ~EPOLLEXCLUSIVE_OK_BITS)))
+ (epds->events & ~EPOLLEXCLUSIVE_OK_BITS)))
goto error_tgt_fput;
}
@@ -2157,13 +2152,17 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
* deep wakeup paths from forming in parallel through multiple
* EPOLL_CTL_ADD operations.
*/
- mutex_lock_nested(&ep->mtx, 0);
+ error = epoll_mutex_lock(&ep->mtx, 0, nonblock);
+ if (error)
+ goto error_tgt_fput;
if (op == EPOLL_CTL_ADD) {
if (!list_empty(&f.file->f_ep_links) ||
is_file_epoll(tf.file)) {
- full_check = 1;
mutex_unlock(&ep->mtx);
- mutex_lock(&epmutex);
+ error = epoll_mutex_lock(&epmutex, 0, nonblock);
+ if (error)
+ goto error_tgt_fput;
+ full_check = 1;
if (is_file_epoll(tf.file)) {
error = -ELOOP;
if (ep_loop_check(ep, tf.file) != 0) {
@@ -2173,10 +2172,19 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
} else
list_add(&tf.file->f_tfile_llink,
&tfile_check_list);
- mutex_lock_nested(&ep->mtx, 0);
+ error = epoll_mutex_lock(&ep->mtx, 0, nonblock);
+ if (error) {
+out_del:
+ list_del(&tf.file->f_tfile_llink);
+ goto error_tgt_fput;
+ }
if (is_file_epoll(tf.file)) {
tep = tf.file->private_data;
- mutex_lock_nested(&tep->mtx, 1);
+ error = epoll_mutex_lock(&tep->mtx, 1, nonblock);
+ if (error) {
+ mutex_unlock(&ep->mtx);
+ goto out_del;
+ }
}
}
}
@@ -2192,8 +2200,8 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
switch (op) {
case EPOLL_CTL_ADD:
if (!epi) {
- epds.events |= EPOLLERR | EPOLLHUP;
- error = ep_insert(ep, &epds, tf.file, fd, full_check);
+ epds->events |= EPOLLERR | EPOLLHUP;
+ error = ep_insert(ep, epds, tf.file, fd, full_check);
} else
error = -EEXIST;
if (full_check)
@@ -2208,8 +2216,8 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
case EPOLL_CTL_MOD:
if (epi) {
if (!(epi->event.events & EPOLLEXCLUSIVE)) {
- epds.events |= EPOLLERR | EPOLLHUP;
- error = ep_modify(ep, epi, &epds);
+ epds->events |= EPOLLERR | EPOLLHUP;
+ error = ep_modify(ep, epi, epds);
}
} else
error = -ENOENT;
@@ -2232,6 +2240,23 @@ error_return:
}
/*
+ * The following function implements the controller interface for
+ * the eventpoll file that enables the insertion/removal/change of
+ * file descriptors inside the interest set.
+ */
+SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
+ struct epoll_event __user *, event)
+{
+ struct epoll_event epds;
+
+ if (ep_op_has_event(op) &&
+ copy_from_user(&epds, event, sizeof(struct epoll_event)))
+ return -EFAULT;
+
+ return do_epoll_ctl(epfd, op, fd, &epds, false);
+}
+
+/*
* Implement the event wait interface for the eventpoll file. It is the kernel
* part of the user space epoll_wait(2).
*/
diff --git a/fs/exec.c b/fs/exec.c
index 74d88dab98dd..db17be51b112 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -272,7 +272,6 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
goto err;
mm->stack_vm = mm->total_vm = 1;
- arch_bprm_mm_init(mm, vma);
up_write(&mm->mmap_sem);
bprm->p = vma->vm_end - sizeof(void *);
return 0;
@@ -761,6 +760,11 @@ int setup_arg_pages(struct linux_binprm *bprm,
goto out_unlock;
BUG_ON(prev != vma);
+ if (unlikely(vm_flags & VM_EXEC)) {
+ pr_warn_once("process '%pD4' started with executable stack\n",
+ bprm->file);
+ }
+
/* Move stack pages down in memory. */
if (stack_shift) {
ret = shift_arg_pages(vma, stack_shift);
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index bcffe25da2f0..4a4ab683250d 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1073,9 +1073,9 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
if (EXT2_BLOCKS_PER_GROUP(sb) == 0)
goto cantfind_ext2;
- 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;
+ 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;
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,
@@ -1138,6 +1138,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
ext2_count_dirs(sb), GFP_KERNEL);
}
if (err) {
+ ret = err;
ext2_msg(sb, KERN_ERR, "error: insufficient memory");
goto failed_mount3;
}
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index db9bfa08d3e0..2a592e38cdfe 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -4,12 +4,7 @@
# kernels after the removal of ext3 driver.
config EXT3_FS
tristate "The Extended 3 (ext3) filesystem"
- # These must match EXT4_FS selects...
select EXT4_FS
- select JBD2
- select CRC16
- select CRYPTO
- select CRYPTO_CRC32C
help
This config option is here only for backward compatibility. ext3
filesystem is now handled by the ext4 driver.
@@ -33,7 +28,6 @@ config EXT3_FS_SECURITY
config EXT4_FS
tristate "The Extended 4 (ext4) filesystem"
- # Please update EXT3_FS selects when changing these
select JBD2
select CRC16
select CRYPTO
@@ -109,7 +103,7 @@ config EXT4_DEBUG
echo 1 > /sys/module/ext4/parameters/mballoc_debug
config EXT4_KUNIT_TESTS
- bool "KUnit tests for ext4"
+ tristate "KUnit tests for ext4"
select EXT4_FS
depends on KUNIT
help
diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
index 840b91d040f1..4ccb3c9189d8 100644
--- a/fs/ext4/Makefile
+++ b/fs/ext4/Makefile
@@ -13,5 +13,6 @@ ext4-y := balloc.o bitmap.o block_validity.o dir.o ext4_jbd2.o extents.o \
ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o
ext4-$(CONFIG_EXT4_FS_SECURITY) += xattr_security.o
-ext4-$(CONFIG_EXT4_KUNIT_TESTS) += inode-test.o
+ext4-inode-test-objs += inode-test.o
+obj-$(CONFIG_EXT4_KUNIT_TESTS) += ext4-inode-test.o
ext4-$(CONFIG_FS_VERITY) += verity.o
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 0b202e00d93f..5f993a411251 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -371,7 +371,8 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
if (buffer_verified(bh))
goto verified;
if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group,
- desc, bh))) {
+ desc, bh) ||
+ ext4_simulate_fail(sb, EXT4_SIM_BBITMAP_CRC))) {
ext4_unlock_group(sb, block_group);
ext4_error(sb, "bg %u: bad block bitmap checksum", block_group);
ext4_mark_group_bitmap_corrupted(sb, block_group,
@@ -505,7 +506,9 @@ int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group,
if (!desc)
return -EFSCORRUPTED;
wait_on_buffer(bh);
+ ext4_simulate_fail_bh(sb, bh, EXT4_SIM_BBITMAP_EIO);
if (!buffer_uptodate(bh)) {
+ ext4_set_errno(sb, EIO);
ext4_error(sb, "Cannot read block bitmap - "
"block_group = %u, block_bitmap = %llu",
block_group, (unsigned long long) bh->b_blocknr);
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 4e093277c8bf..1f340743c9a8 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -462,7 +462,6 @@ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
new_fn->name_len = ent_name->len;
new_fn->file_type = dirent->file_type;
memcpy(new_fn->name, ent_name->name, ent_name->len);
- new_fn->name[ent_name->len] = 0;
while (*p) {
parent = *p;
@@ -672,9 +671,11 @@ static int ext4_d_compare(const struct dentry *dentry, unsigned int len,
const char *str, const struct qstr *name)
{
struct qstr qstr = {.name = str, .len = len };
- struct inode *inode = dentry->d_parent->d_inode;
+ const struct dentry *parent = READ_ONCE(dentry->d_parent);
+ const struct inode *inode = READ_ONCE(parent->d_inode);
- if (!IS_CASEFOLDED(inode) || !EXT4_SB(inode->i_sb)->s_encoding) {
+ if (!inode || !IS_CASEFOLDED(inode) ||
+ !EXT4_SB(inode->i_sb)->s_encoding) {
if (len != name->len)
return -1;
return memcmp(str, name->name, len);
@@ -687,10 +688,11 @@ static int ext4_d_hash(const struct dentry *dentry, struct qstr *str)
{
const struct ext4_sb_info *sbi = EXT4_SB(dentry->d_sb);
const struct unicode_map *um = sbi->s_encoding;
+ const struct inode *inode = READ_ONCE(dentry->d_inode);
unsigned char *norm;
int len, ret = 0;
- if (!IS_CASEFOLDED(dentry->d_inode) || !um)
+ if (!inode || !IS_CASEFOLDED(inode) || !um)
return 0;
norm = kmalloc(PATH_MAX, GFP_ATOMIC);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index f8578caba40d..9a2ee2428ecc 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1052,8 +1052,6 @@ struct ext4_inode_info {
/* allocation reservation info for delalloc */
/* In case of bigalloc, this refer to clusters rather than blocks */
unsigned int i_reserved_data_blocks;
- ext4_lblk_t i_da_metadata_calc_last_lblock;
- int i_da_metadata_calc_len;
/* pending cluster reservations for bigalloc file systems */
struct ext4_pending_tree i_pending_tree;
@@ -1343,7 +1341,8 @@ struct ext4_super_block {
__u8 s_lastcheck_hi;
__u8 s_first_error_time_hi;
__u8 s_last_error_time_hi;
- __u8 s_pad[2];
+ __u8 s_first_error_errcode;
+ __u8 s_last_error_errcode;
__le16 s_encoding; /* Filename charset encoding */
__le16 s_encoding_flags; /* Filename charset encoding flags */
__le32 s_reserved[95]; /* Padding to the end of the block */
@@ -1556,6 +1555,9 @@ struct ext4_sb_info {
/* Barrier between changing inodes' journal flags and writepages ops. */
struct percpu_rw_semaphore s_journal_flag_rwsem;
struct dax_device *s_daxdev;
+#ifdef CONFIG_EXT4_DEBUG
+ unsigned long s_simulate_fail;
+#endif
};
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -1575,6 +1577,66 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
}
/*
+ * Simulate_fail codes
+ */
+#define EXT4_SIM_BBITMAP_EIO 1
+#define EXT4_SIM_BBITMAP_CRC 2
+#define EXT4_SIM_IBITMAP_EIO 3
+#define EXT4_SIM_IBITMAP_CRC 4
+#define EXT4_SIM_INODE_EIO 5
+#define EXT4_SIM_INODE_CRC 6
+#define EXT4_SIM_DIRBLOCK_EIO 7
+#define EXT4_SIM_DIRBLOCK_CRC 8
+
+static inline bool ext4_simulate_fail(struct super_block *sb,
+ unsigned long code)
+{
+#ifdef CONFIG_EXT4_DEBUG
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+ if (unlikely(sbi->s_simulate_fail == code)) {
+ sbi->s_simulate_fail = 0;
+ return true;
+ }
+#endif
+ return false;
+}
+
+static inline void ext4_simulate_fail_bh(struct super_block *sb,
+ struct buffer_head *bh,
+ unsigned long code)
+{
+ if (!IS_ERR(bh) && ext4_simulate_fail(sb, code))
+ clear_buffer_uptodate(bh);
+}
+
+/*
+ * Error number codes for s_{first,last}_error_errno
+ *
+ * Linux errno numbers are architecture specific, so we need to translate
+ * them into something which is architecture independent. We don't define
+ * codes for all errno's; just the ones which are most likely to be the cause
+ * of an ext4_error() call.
+ */
+#define EXT4_ERR_UNKNOWN 1
+#define EXT4_ERR_EIO 2
+#define EXT4_ERR_ENOMEM 3
+#define EXT4_ERR_EFSBADCRC 4
+#define EXT4_ERR_EFSCORRUPTED 5
+#define EXT4_ERR_ENOSPC 6
+#define EXT4_ERR_ENOKEY 7
+#define EXT4_ERR_EROFS 8
+#define EXT4_ERR_EFBIG 9
+#define EXT4_ERR_EEXIST 10
+#define EXT4_ERR_ERANGE 11
+#define EXT4_ERR_EOVERFLOW 12
+#define EXT4_ERR_EBUSY 13
+#define EXT4_ERR_ENOTDIR 14
+#define EXT4_ERR_ENOTEMPTY 15
+#define EXT4_ERR_ESHUTDOWN 16
+#define EXT4_ERR_EFAULT 17
+
+/*
* Inode dynamic state flags
*/
enum {
@@ -2628,7 +2690,6 @@ extern int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk,
/* indirect.c */
extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags);
-extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks);
extern void ext4_ind_truncate(handle_t *, struct inode *inode);
extern int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
@@ -2679,8 +2740,6 @@ extern struct buffer_head *ext4_sb_bread(struct super_block *sb,
extern int ext4_seq_options_show(struct seq_file *seq, void *offset);
extern int ext4_calculate_overhead(struct super_block *sb);
extern void ext4_superblock_csum_set(struct super_block *sb);
-extern void *ext4_kvmalloc(size_t size, gfp_t flags);
-extern void *ext4_kvzalloc(size_t size, gfp_t flags);
extern int ext4_alloc_flex_bg_array(struct super_block *sb,
ext4_group_t ngroup);
extern const char *ext4_decode_error(struct super_block *sb, int errno,
@@ -2688,6 +2747,7 @@ extern const char *ext4_decode_error(struct super_block *sb, int errno,
extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb,
ext4_group_t block_group,
unsigned int flags);
+extern void ext4_set_errno(struct super_block *sb, int err);
extern __printf(4, 5)
void __ext4_error(struct super_block *, const char *, unsigned int,
@@ -3254,7 +3314,6 @@ struct ext4_extent;
#define EXT_MAX_BLOCKS 0xffffffff
extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
-extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
extern int ext4_ext_index_trans_blocks(struct inode *inode, int extents);
extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags);
@@ -3271,14 +3330,9 @@ extern int ext4_convert_unwritten_io_end_vec(handle_t *handle,
ext4_io_end_t *io_end);
extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags);
-extern int ext4_ext_calc_metadata_amount(struct inode *inode,
- ext4_lblk_t lblocks);
extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode,
int num,
struct ext4_ext_path *path);
-extern int ext4_can_extents_be_merged(struct inode *inode,
- struct ext4_extent *ex1,
- struct ext4_extent *ex2);
extern int ext4_ext_insert_extent(handle_t *, struct inode *,
struct ext4_ext_path **,
struct ext4_extent *, int);
@@ -3294,8 +3348,6 @@ extern int ext4_get_es_cache(struct inode *inode,
struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len);
extern int ext4_ext_precache(struct inode *inode);
-extern int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len);
-extern int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len);
extern int ext4_swap_extents(handle_t *handle, struct inode *inode1,
struct inode *inode2, ext4_lblk_t lblk1,
ext4_lblk_t lblk2, ext4_lblk_t count,
@@ -3390,6 +3442,7 @@ static inline void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end)
}
extern const struct iomap_ops ext4_iomap_ops;
+extern const struct iomap_ops ext4_iomap_overwrite_ops;
extern const struct iomap_ops ext4_iomap_report_ops;
static inline int ext4_buffer_uptodate(struct buffer_head *bh)
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 98bd0e9ee7df..1c216fcc202a 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -267,10 +267,5 @@ static inline void ext4_idx_store_pblock(struct ext4_extent_idx *ix,
0xffff);
}
-#define ext4_ext_dirty(handle, inode, path) \
- __ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path))
-int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle,
- struct inode *inode, struct ext4_ext_path *path);
-
#endif /* _EXT4_EXTENTS */
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index d3b8cdea5df7..1f53d64e42a5 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -7,6 +7,28 @@
#include <trace/events/ext4.h>
+int ext4_inode_journal_mode(struct inode *inode)
+{
+ if (EXT4_JOURNAL(inode) == NULL)
+ return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */
+ /* We do not support data journalling with delayed allocation */
+ if (!S_ISREG(inode->i_mode) ||
+ ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE) ||
+ test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
+ (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
+ !test_opt(inode->i_sb, DELALLOC))) {
+ /* We do not support data journalling for encrypted data */
+ if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode))
+ return EXT4_INODE_ORDERED_DATA_MODE; /* ordered */
+ return EXT4_INODE_JOURNAL_DATA_MODE; /* journal data */
+ }
+ if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
+ return EXT4_INODE_ORDERED_DATA_MODE; /* ordered */
+ if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
+ return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */
+ BUG();
+}
+
/* Just increment the non-pointer handle value */
static handle_t *ext4_get_nojournal(void)
{
@@ -58,6 +80,7 @@ static int ext4_journal_check_start(struct super_block *sb)
* take the FS itself readonly cleanly.
*/
if (journal && is_journal_aborted(journal)) {
+ ext4_set_errno(sb, -journal->j_errno);
ext4_abort(sb, "Detected aborted journal");
return -EROFS;
}
@@ -249,6 +272,7 @@ int __ext4_forget(const char *where, unsigned int line, handle_t *handle,
if (err) {
ext4_journal_abort_handle(where, line, __func__,
bh, handle, err);
+ ext4_set_errno(inode->i_sb, -err);
__ext4_abort(inode->i_sb, where, line,
"error %d when attempting revoke", err);
}
@@ -320,6 +344,7 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
es = EXT4_SB(inode->i_sb)->s_es;
es->s_last_error_block =
cpu_to_le64(bh->b_blocknr);
+ ext4_set_errno(inode->i_sb, EIO);
ext4_error_inode(inode, where, line,
bh->b_blocknr,
"IO error syncing itable block");
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index a6b9b66dbfad..7ea4f6fa173b 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -463,27 +463,7 @@ int ext4_force_commit(struct super_block *sb);
#define EXT4_INODE_ORDERED_DATA_MODE 0x02 /* ordered data mode */
#define EXT4_INODE_WRITEBACK_DATA_MODE 0x04 /* writeback data mode */
-static inline int ext4_inode_journal_mode(struct inode *inode)
-{
- if (EXT4_JOURNAL(inode) == NULL)
- return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */
- /* We do not support data journalling with delayed allocation */
- if (!S_ISREG(inode->i_mode) ||
- ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE) ||
- test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
- (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
- !test_opt(inode->i_sb, DELALLOC))) {
- /* We do not support data journalling for encrypted data */
- if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode))
- return EXT4_INODE_ORDERED_DATA_MODE; /* ordered */
- return EXT4_INODE_JOURNAL_DATA_MODE; /* journal data */
- }
- if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
- return EXT4_INODE_ORDERED_DATA_MODE; /* ordered */
- if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
- return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */
- BUG();
-}
+int ext4_inode_journal_mode(struct inode *inode);
static inline int ext4_should_journal_data(struct inode *inode)
{
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 0e8708b77da6..954013d6076b 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -161,8 +161,9 @@ static int ext4_ext_get_access(handle_t *handle, struct inode *inode,
* - ENOMEM
* - EIO
*/
-int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle,
- struct inode *inode, struct ext4_ext_path *path)
+static int __ext4_ext_dirty(const char *where, unsigned int line,
+ handle_t *handle, struct inode *inode,
+ struct ext4_ext_path *path)
{
int err;
@@ -179,6 +180,9 @@ int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle,
return err;
}
+#define ext4_ext_dirty(handle, inode, path) \
+ __ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path))
+
static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
struct ext4_ext_path *path,
ext4_lblk_t block)
@@ -309,53 +313,6 @@ ext4_force_split_extent_at(handle_t *handle, struct inode *inode,
(nofail ? EXT4_GET_BLOCKS_METADATA_NOFAIL:0));
}
-/*
- * Calculate the number of metadata blocks needed
- * to allocate @blocks
- * Worse case is one block per extent
- */
-int ext4_ext_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock)
-{
- struct ext4_inode_info *ei = EXT4_I(inode);
- int idxs;
-
- idxs = ((inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
- / sizeof(struct ext4_extent_idx));
-
- /*
- * If the new delayed allocation block is contiguous with the
- * previous da block, it can share index blocks with the
- * previous block, so we only need to allocate a new index
- * block every idxs leaf blocks. At ldxs**2 blocks, we need
- * an additional index block, and at ldxs**3 blocks, yet
- * another index blocks.
- */
- if (ei->i_da_metadata_calc_len &&
- ei->i_da_metadata_calc_last_lblock+1 == lblock) {
- int num = 0;
-
- if ((ei->i_da_metadata_calc_len % idxs) == 0)
- num++;
- if ((ei->i_da_metadata_calc_len % (idxs*idxs)) == 0)
- num++;
- if ((ei->i_da_metadata_calc_len % (idxs*idxs*idxs)) == 0) {
- num++;
- ei->i_da_metadata_calc_len = 0;
- } else
- ei->i_da_metadata_calc_len++;
- ei->i_da_metadata_calc_last_lblock++;
- return num;
- }
-
- /*
- * In the worst case we need a new set of index blocks at
- * every level of the inode's extent tree.
- */
- ei->i_da_metadata_calc_len = 1;
- ei->i_da_metadata_calc_last_lblock = lblock;
- return ext_depth(inode) + 1;
-}
-
static int
ext4_ext_max_entries(struct inode *inode, int depth)
{
@@ -492,6 +449,7 @@ static int __ext4_ext_check(const char *function, unsigned int line,
return 0;
corrupted:
+ ext4_set_errno(inode->i_sb, -err);
ext4_error_inode(inode, function, line, 0,
"pblk %llu bad header/extent: %s - magic %x, "
"entries %u, max %u(%u), depth %u(%u)",
@@ -510,6 +468,30 @@ int ext4_ext_check_inode(struct inode *inode)
return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode), 0);
}
+static void ext4_cache_extents(struct inode *inode,
+ struct ext4_extent_header *eh)
+{
+ struct ext4_extent *ex = EXT_FIRST_EXTENT(eh);
+ ext4_lblk_t prev = 0;
+ int i;
+
+ for (i = le16_to_cpu(eh->eh_entries); i > 0; i--, ex++) {
+ unsigned int status = EXTENT_STATUS_WRITTEN;
+ ext4_lblk_t lblk = le32_to_cpu(ex->ee_block);
+ int len = ext4_ext_get_actual_len(ex);
+
+ if (prev && (prev != lblk))
+ ext4_es_cache_extent(inode, prev, lblk - prev, ~0,
+ EXTENT_STATUS_HOLE);
+
+ if (ext4_ext_is_unwritten(ex))
+ status = EXTENT_STATUS_UNWRITTEN;
+ ext4_es_cache_extent(inode, lblk, len,
+ ext4_ext_pblock(ex), status);
+ prev = lblk + len;
+ }
+}
+
static struct buffer_head *
__read_extent_tree_block(const char *function, unsigned int line,
struct inode *inode, ext4_fsblk_t pblk, int depth,
@@ -544,26 +526,7 @@ __read_extent_tree_block(const char *function, unsigned int line,
*/
if (!(flags & EXT4_EX_NOCACHE) && depth == 0) {
struct ext4_extent_header *eh = ext_block_hdr(bh);
- struct ext4_extent *ex = EXT_FIRST_EXTENT(eh);
- ext4_lblk_t prev = 0;
- int i;
-
- for (i = le16_to_cpu(eh->eh_entries); i > 0; i--, ex++) {
- unsigned int status = EXTENT_STATUS_WRITTEN;
- ext4_lblk_t lblk = le32_to_cpu(ex->ee_block);
- int len = ext4_ext_get_actual_len(ex);
-
- if (prev && (prev != lblk))
- ext4_es_cache_extent(inode, prev,
- lblk - prev, ~0,
- EXTENT_STATUS_HOLE);
-
- if (ext4_ext_is_unwritten(ex))
- status = EXTENT_STATUS_UNWRITTEN;
- ext4_es_cache_extent(inode, lblk, len,
- ext4_ext_pblock(ex), status);
- prev = lblk + len;
- }
+ ext4_cache_extents(inode, eh);
}
return bh;
errout:
@@ -649,8 +612,9 @@ static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path)
ext_debug("path:");
for (k = 0; k <= l; k++, path++) {
if (path->p_idx) {
- ext_debug(" %d->%llu", le32_to_cpu(path->p_idx->ei_block),
- ext4_idx_pblock(path->p_idx));
+ ext_debug(" %d->%llu",
+ le32_to_cpu(path->p_idx->ei_block),
+ ext4_idx_pblock(path->p_idx));
} else if (path->p_ext) {
ext_debug(" %d:[%d]%d:%llu ",
le32_to_cpu(path->p_ext->ee_block),
@@ -731,11 +695,12 @@ void ext4_ext_drop_refs(struct ext4_ext_path *path)
if (!path)
return;
depth = path->p_depth;
- for (i = 0; i <= depth; i++, path++)
+ for (i = 0; i <= depth; i++, path++) {
if (path->p_bh) {
brelse(path->p_bh);
path->p_bh = NULL;
}
+ }
}
/*
@@ -777,8 +742,8 @@ ext4_ext_binsearch_idx(struct inode *inode,
chix = ix = EXT_FIRST_INDEX(eh);
for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ix++) {
- if (k != 0 &&
- le32_to_cpu(ix->ei_block) <= le32_to_cpu(ix[-1].ei_block)) {
+ if (k != 0 && le32_to_cpu(ix->ei_block) <=
+ le32_to_cpu(ix[-1].ei_block)) {
printk(KERN_DEBUG "k=%d, ix=0x%p, "
"first=0x%p\n", k,
ix, EXT_FIRST_INDEX(eh));
@@ -911,6 +876,8 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block,
path[0].p_bh = NULL;
i = depth;
+ if (!(flags & EXT4_EX_NOCACHE) && depth == 0)
+ ext4_cache_extents(inode, eh);
/* walk through the tree */
while (i) {
ext_debug("depth %d: num %d, max %d\n",
@@ -1632,17 +1599,16 @@ ext4_ext_next_allocated_block(struct ext4_ext_path *path)
return EXT_MAX_BLOCKS;
while (depth >= 0) {
+ struct ext4_ext_path *p = &path[depth];
+
if (depth == path->p_depth) {
/* leaf */
- if (path[depth].p_ext &&
- path[depth].p_ext !=
- EXT_LAST_EXTENT(path[depth].p_hdr))
- return le32_to_cpu(path[depth].p_ext[1].ee_block);
+ if (p->p_ext && p->p_ext != EXT_LAST_EXTENT(p->p_hdr))
+ return le32_to_cpu(p->p_ext[1].ee_block);
} else {
/* index */
- if (path[depth].p_idx !=
- EXT_LAST_INDEX(path[depth].p_hdr))
- return le32_to_cpu(path[depth].p_idx[1].ei_block);
+ if (p->p_idx != EXT_LAST_INDEX(p->p_hdr))
+ return le32_to_cpu(p->p_idx[1].ei_block);
}
depth--;
}
@@ -1742,9 +1708,9 @@ static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode,
return err;
}
-int
-ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
- struct ext4_extent *ex2)
+static int ext4_can_extents_be_merged(struct inode *inode,
+ struct ext4_extent *ex1,
+ struct ext4_extent *ex2)
{
unsigned short ext1_ee_len, ext2_ee_len;
@@ -1758,11 +1724,6 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
le32_to_cpu(ex2->ee_block))
return 0;
- /*
- * To allow future support for preallocated extents to be added
- * as an RO_COMPAT feature, refuse to merge to extents if
- * this can result in the top bit of ee_len being set.
- */
if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN)
return 0;
@@ -1870,13 +1831,14 @@ static void ext4_ext_try_to_merge_up(handle_t *handle,
}
/*
- * This function tries to merge the @ex extent to neighbours in the tree.
- * return 1 if merge left else 0.
+ * This function tries to merge the @ex extent to neighbours in the tree, then
+ * tries to collapse the extent tree into the inode.
*/
static void ext4_ext_try_to_merge(handle_t *handle,
struct inode *inode,
struct ext4_ext_path *path,
- struct ext4_extent *ex) {
+ struct ext4_extent *ex)
+{
struct ext4_extent_header *eh;
unsigned int depth;
int merge_done = 0;
@@ -3718,9 +3680,6 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
max_zeroout = sbi->s_extent_max_zeroout_kb >>
(inode->i_sb->s_blocksize_bits - 10);
- if (IS_ENCRYPTED(inode))
- max_zeroout = 0;
-
/*
* five cases:
* 1. split the extent into three extents.
@@ -4706,6 +4665,10 @@ retry:
return ret > 0 ? ret2 : ret;
}
+static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len);
+
+static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len);
+
static long ext4_zero_range(struct file *file, loff_t offset,
loff_t len, int mode)
{
@@ -4723,9 +4686,6 @@ static long ext4_zero_range(struct file *file, loff_t offset,
trace_ext4_zero_range(inode, offset, len, mode);
- if (!S_ISREG(inode->i_mode))
- return -EINVAL;
-
/* Call ext4_force_commit to flush all data in case of data=journal. */
if (ext4_should_journal_data(inode)) {
ret = ext4_force_commit(inode->i_sb);
@@ -4765,7 +4725,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
}
if (!(mode & FALLOC_FL_KEEP_SIZE) &&
- (offset + len > i_size_read(inode) ||
+ (offset + len > inode->i_size ||
offset + len > EXT4_I(inode)->i_disksize)) {
new_size = offset + len;
ret = inode_newsize_ok(inode, new_size);
@@ -4849,7 +4809,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
* Mark that we allocate beyond EOF so the subsequent truncate
* can proceed even if the new size is the same as i_size.
*/
- if ((offset + len) > i_size_read(inode))
+ if (offset + len > inode->i_size)
ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
}
ext4_mark_inode_dirty(handle, inode);
@@ -4890,14 +4850,9 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
* range since we would need to re-encrypt blocks with a
* different IV or XTS tweak (which are based on the logical
* block number).
- *
- * XXX It's not clear why zero range isn't working, but we'll
- * leave it disabled for encrypted inodes for now. This is a
- * bug we should fix....
*/
if (IS_ENCRYPTED(inode) &&
- (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE |
- FALLOC_FL_ZERO_RANGE)))
+ (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE)))
return -EOPNOTSUPP;
/* Return error if mode is not supported */
@@ -4941,7 +4896,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
}
if (!(mode & FALLOC_FL_KEEP_SIZE) &&
- (offset + len > i_size_read(inode) ||
+ (offset + len > inode->i_size ||
offset + len > EXT4_I(inode)->i_disksize)) {
new_size = offset + len;
ret = inode_newsize_ok(inode, new_size);
@@ -5268,7 +5223,7 @@ ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift,
{
int depth, err = 0;
struct ext4_extent *ex_start, *ex_last;
- bool update = 0;
+ bool update = false;
depth = path->p_depth;
while (depth >= 0) {
@@ -5284,7 +5239,7 @@ ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift,
goto out;
if (ex_start == EXT_FIRST_EXTENT(path[depth].p_hdr))
- update = 1;
+ update = true;
while (ex_start <= ex_last) {
if (SHIFT == SHIFT_LEFT) {
@@ -5472,7 +5427,7 @@ out:
* This implements the fallocate's collapse range functionality for ext4
* Returns: 0 and non-zero on error.
*/
-int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
+static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
{
struct super_block *sb = inode->i_sb;
ext4_lblk_t punch_start, punch_stop;
@@ -5489,12 +5444,8 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
return -EOPNOTSUPP;
- /* Collapse range works only on fs block size aligned offsets. */
- if (offset & (EXT4_CLUSTER_SIZE(sb) - 1) ||
- len & (EXT4_CLUSTER_SIZE(sb) - 1))
- return -EINVAL;
-
- if (!S_ISREG(inode->i_mode))
+ /* Collapse range works only on fs cluster size aligned regions. */
+ if (!IS_ALIGNED(offset | len, EXT4_CLUSTER_SIZE(sb)))
return -EINVAL;
trace_ext4_collapse_range(inode, offset, len);
@@ -5514,7 +5465,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
* There is no need to overlap collapse range with EOF, in which case
* it is effectively a truncate operation
*/
- if (offset + len >= i_size_read(inode)) {
+ if (offset + len >= inode->i_size) {
ret = -EINVAL;
goto out_mutex;
}
@@ -5592,7 +5543,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
goto out_stop;
}
- new_size = i_size_read(inode) - len;
+ new_size = inode->i_size - len;
i_size_write(inode, new_size);
EXT4_I(inode)->i_disksize = new_size;
@@ -5620,7 +5571,7 @@ out_mutex:
* by len bytes.
* Returns 0 on success, error otherwise.
*/
-int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
+static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
{
struct super_block *sb = inode->i_sb;
handle_t *handle;
@@ -5639,14 +5590,10 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
return -EOPNOTSUPP;
- /* Insert range works only on fs block size aligned offsets. */
- if (offset & (EXT4_CLUSTER_SIZE(sb) - 1) ||
- len & (EXT4_CLUSTER_SIZE(sb) - 1))
+ /* Insert range works only on fs cluster size aligned regions. */
+ if (!IS_ALIGNED(offset | len, EXT4_CLUSTER_SIZE(sb)))
return -EINVAL;
- if (!S_ISREG(inode->i_mode))
- return -EOPNOTSUPP;
-
trace_ext4_insert_range(inode, offset, len);
offset_lblk = offset >> EXT4_BLOCK_SIZE_BITS(sb);
@@ -5666,14 +5613,14 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
goto out_mutex;
}
- /* Check for wrap through zero */
- if (inode->i_size + len > inode->i_sb->s_maxbytes) {
+ /* Check whether the maximum file size would be exceeded */
+ if (len > inode->i_sb->s_maxbytes - inode->i_size) {
ret = -EFBIG;
goto out_mutex;
}
- /* Offset should be less than i_size */
- if (offset >= i_size_read(inode)) {
+ /* Offset must be less than i_size */
+ if (offset >= inode->i_size) {
ret = -EINVAL;
goto out_mutex;
}
diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h
index 825313c59752..4ec30a798260 100644
--- a/fs/ext4/extents_status.h
+++ b/fs/ext4/extents_status.h
@@ -209,6 +209,12 @@ static inline ext4_fsblk_t ext4_es_pblock(struct extent_status *es)
return es->es_pblk & ~ES_MASK;
}
+static inline ext4_fsblk_t ext4_es_show_pblock(struct extent_status *es)
+{
+ ext4_fsblk_t pblock = ext4_es_pblock(es);
+ return pblock == ~ES_MASK ? 0 : pblock;
+}
+
static inline void ext4_es_store_pblock(struct extent_status *es,
ext4_fsblk_t pb)
{
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 6a7293a5cda2..5f225881176b 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -88,9 +88,10 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
struct inode *inode = file_inode(iocb->ki_filp);
ssize_t ret;
- if (!inode_trylock_shared(inode)) {
- if (iocb->ki_flags & IOCB_NOWAIT)
+ if (iocb->ki_flags & IOCB_NOWAIT) {
+ if (!inode_trylock_shared(inode))
return -EAGAIN;
+ } else {
inode_lock_shared(inode);
}
/*
@@ -165,19 +166,25 @@ static int ext4_release_file(struct inode *inode, struct file *filp)
* threads are at work on the same unwritten block, they must be synchronized
* or one thread will zero the other's data, causing corruption.
*/
-static int
-ext4_unaligned_aio(struct inode *inode, struct iov_iter *from, loff_t pos)
+static bool
+ext4_unaligned_io(struct inode *inode, struct iov_iter *from, loff_t pos)
{
struct super_block *sb = inode->i_sb;
- int blockmask = sb->s_blocksize - 1;
-
- if (pos >= ALIGN(i_size_read(inode), sb->s_blocksize))
- return 0;
+ unsigned long blockmask = sb->s_blocksize - 1;
if ((pos | iov_iter_alignment(from)) & blockmask)
- return 1;
+ return true;
- return 0;
+ return false;
+}
+
+static bool
+ext4_extending_io(struct inode *inode, loff_t offset, size_t len)
+{
+ if (offset + len > i_size_read(inode) ||
+ offset + len > EXT4_I(inode)->i_disksize)
+ return true;
+ return false;
}
/* Is IO overwriting allocated and initialized blocks? */
@@ -203,7 +210,8 @@ static bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len)
return err == blklen && (map.m_flags & EXT4_MAP_MAPPED);
}
-static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
+static ssize_t ext4_generic_write_checks(struct kiocb *iocb,
+ struct iov_iter *from)
{
struct inode *inode = file_inode(iocb->ki_filp);
ssize_t ret;
@@ -227,11 +235,21 @@ static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
iov_iter_truncate(from, sbi->s_bitmap_maxbytes - iocb->ki_pos);
}
+ return iov_iter_count(from);
+}
+
+static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
+{
+ ssize_t ret, count;
+
+ count = ext4_generic_write_checks(iocb, from);
+ if (count <= 0)
+ return count;
+
ret = file_modified(iocb->ki_filp);
if (ret)
return ret;
-
- return iov_iter_count(from);
+ return count;
}
static ssize_t ext4_buffered_write_iter(struct kiocb *iocb,
@@ -363,62 +381,137 @@ static const struct iomap_dio_ops ext4_dio_write_ops = {
.end_io = ext4_dio_write_end_io,
};
+/*
+ * The intention here is to start with shared lock acquired then see if any
+ * condition requires an exclusive inode lock. If yes, then we restart the
+ * whole operation by releasing the shared lock and acquiring exclusive lock.
+ *
+ * - For unaligned_io we never take shared lock as it may cause data corruption
+ * when two unaligned IO tries to modify the same block e.g. while zeroing.
+ *
+ * - For extending writes case we don't take the shared lock, since it requires
+ * updating inode i_disksize and/or orphan handling with exclusive lock.
+ *
+ * - shared locking will only be true mostly with overwrites. Otherwise we will
+ * switch to exclusive i_rwsem lock.
+ */
+static ssize_t ext4_dio_write_checks(struct kiocb *iocb, struct iov_iter *from,
+ bool *ilock_shared, bool *extend)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file_inode(file);
+ loff_t offset;
+ size_t count;
+ ssize_t ret;
+
+restart:
+ ret = ext4_generic_write_checks(iocb, from);
+ if (ret <= 0)
+ goto out;
+
+ offset = iocb->ki_pos;
+ count = ret;
+ if (ext4_extending_io(inode, offset, count))
+ *extend = true;
+ /*
+ * Determine whether the IO operation will overwrite allocated
+ * and initialized blocks.
+ * We need exclusive i_rwsem for changing security info
+ * in file_modified().
+ */
+ if (*ilock_shared && (!IS_NOSEC(inode) || *extend ||
+ !ext4_overwrite_io(inode, offset, count))) {
+ inode_unlock_shared(inode);
+ *ilock_shared = false;
+ inode_lock(inode);
+ goto restart;
+ }
+
+ ret = file_modified(file);
+ if (ret < 0)
+ goto out;
+
+ return count;
+out:
+ if (*ilock_shared)
+ inode_unlock_shared(inode);
+ else
+ inode_unlock(inode);
+ return ret;
+}
+
static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
ssize_t ret;
- size_t count;
- loff_t offset;
handle_t *handle;
struct inode *inode = file_inode(iocb->ki_filp);
- bool extend = false, overwrite = false, unaligned_aio = false;
+ loff_t offset = iocb->ki_pos;
+ size_t count = iov_iter_count(from);
+ const struct iomap_ops *iomap_ops = &ext4_iomap_ops;
+ bool extend = false, unaligned_io = false;
+ bool ilock_shared = true;
+
+ /*
+ * We initially start with shared inode lock unless it is
+ * unaligned IO which needs exclusive lock anyways.
+ */
+ if (ext4_unaligned_io(inode, from, offset)) {
+ unaligned_io = true;
+ ilock_shared = false;
+ }
+ /*
+ * Quick check here without any i_rwsem lock to see if it is extending
+ * IO. A more reliable check is done in ext4_dio_write_checks() with
+ * proper locking in place.
+ */
+ if (offset + count > i_size_read(inode))
+ ilock_shared = false;
if (iocb->ki_flags & IOCB_NOWAIT) {
- if (!inode_trylock(inode))
- return -EAGAIN;
+ if (ilock_shared) {
+ if (!inode_trylock_shared(inode))
+ return -EAGAIN;
+ } else {
+ if (!inode_trylock(inode))
+ return -EAGAIN;
+ }
} else {
- inode_lock(inode);
+ if (ilock_shared)
+ inode_lock_shared(inode);
+ else
+ inode_lock(inode);
}
+ /* Fallback to buffered I/O if the inode does not support direct I/O. */
if (!ext4_dio_supported(inode)) {
- inode_unlock(inode);
- /*
- * Fallback to buffered I/O if the inode does not support
- * direct I/O.
- */
+ if (ilock_shared)
+ inode_unlock_shared(inode);
+ else
+ inode_unlock(inode);
return ext4_buffered_write_iter(iocb, from);
}
- ret = ext4_write_checks(iocb, from);
- if (ret <= 0) {
- inode_unlock(inode);
+ ret = ext4_dio_write_checks(iocb, from, &ilock_shared, &extend);
+ if (ret <= 0)
return ret;
- }
- /*
- * Unaligned asynchronous direct I/O must be serialized among each
- * other as the zeroing of partial blocks of two competing unaligned
- * asynchronous direct I/O writes can result in data corruption.
- */
offset = iocb->ki_pos;
- count = iov_iter_count(from);
- if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
- !is_sync_kiocb(iocb) && ext4_unaligned_aio(inode, from, offset)) {
- unaligned_aio = true;
- inode_dio_wait(inode);
- }
+ count = ret;
/*
- * Determine whether the I/O will overwrite allocated and initialized
- * blocks. If so, check to see whether it is possible to take the
- * dioread_nolock path.
+ * Unaligned direct IO must be serialized among each other as zeroing
+ * of partial blocks of two competing unaligned IOs can result in data
+ * corruption.
+ *
+ * So we make sure we don't allow any unaligned IO in flight.
+ * For IOs where we need not wait (like unaligned non-AIO DIO),
+ * below inode_dio_wait() may anyway become a no-op, since we start
+ * with exclusive lock.
*/
- if (!unaligned_aio && ext4_overwrite_io(inode, offset, count) &&
- ext4_should_dioread_nolock(inode)) {
- overwrite = true;
- downgrade_write(&inode->i_rwsem);
- }
+ if (unaligned_io)
+ inode_dio_wait(inode);
- if (offset + count > EXT4_I(inode)->i_disksize) {
+ if (extend) {
handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
@@ -431,18 +524,19 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
goto out;
}
- extend = true;
ext4_journal_stop(handle);
}
- ret = iomap_dio_rw(iocb, from, &ext4_iomap_ops, &ext4_dio_write_ops,
- is_sync_kiocb(iocb) || unaligned_aio || extend);
+ if (ilock_shared)
+ iomap_ops = &ext4_iomap_overwrite_ops;
+ ret = iomap_dio_rw(iocb, from, iomap_ops, &ext4_dio_write_ops,
+ is_sync_kiocb(iocb) || unaligned_io || extend);
if (extend)
ret = ext4_handle_inode_extension(inode, offset, ret, count);
out:
- if (overwrite)
+ if (ilock_shared)
inode_unlock_shared(inode);
else
inode_unlock(inode);
@@ -487,9 +581,10 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
bool extend = false;
struct inode *inode = file_inode(iocb->ki_filp);
- if (!inode_trylock(inode)) {
- if (iocb->ki_flags & IOCB_NOWAIT)
+ if (iocb->ki_flags & IOCB_NOWAIT) {
+ if (!inode_trylock(inode))
return -EAGAIN;
+ } else {
inode_lock(inode);
}
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 8ca4a23129aa..c66e8f9451a2 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -94,7 +94,8 @@ static int ext4_validate_inode_bitmap(struct super_block *sb,
goto verified;
blk = ext4_inode_bitmap(sb, desc);
if (!ext4_inode_bitmap_csum_verify(sb, block_group, desc, bh,
- EXT4_INODES_PER_GROUP(sb) / 8)) {
+ EXT4_INODES_PER_GROUP(sb) / 8) ||
+ ext4_simulate_fail(sb, EXT4_SIM_IBITMAP_CRC)) {
ext4_unlock_group(sb, block_group);
ext4_error(sb, "Corrupt inode bitmap - block_group = %u, "
"inode_bitmap = %llu", block_group, blk);
@@ -192,8 +193,10 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
get_bh(bh);
submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO, bh);
wait_on_buffer(bh);
+ ext4_simulate_fail_bh(sb, bh, EXT4_SIM_IBITMAP_EIO);
if (!buffer_uptodate(bh)) {
put_bh(bh);
+ ext4_set_errno(sb, EIO);
ext4_error(sb, "Cannot read inode bitmap - "
"block_group = %u, inode_bitmap = %llu",
block_group, bitmap_blk);
@@ -1223,6 +1226,7 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
+ ext4_set_errno(sb, -err);
ext4_error(sb, "couldn't read orphan inode %lu (err %d)",
ino, err);
return inode;
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 3a4ab70fe9e0..569fc68e8975 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -660,32 +660,6 @@ out:
}
/*
- * Calculate the number of metadata blocks need to reserve
- * to allocate a new block at @lblocks for non extent file based file
- */
-int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock)
-{
- struct ext4_inode_info *ei = EXT4_I(inode);
- sector_t dind_mask = ~((sector_t)EXT4_ADDR_PER_BLOCK(inode->i_sb) - 1);
- int blk_bits;
-
- if (lblock < EXT4_NDIR_BLOCKS)
- return 0;
-
- lblock -= EXT4_NDIR_BLOCKS;
-
- if (ei->i_da_metadata_calc_len &&
- (lblock & dind_mask) == ei->i_da_metadata_calc_last_lblock) {
- ei->i_da_metadata_calc_len++;
- return 0;
- }
- ei->i_da_metadata_calc_last_lblock = lblock & dind_mask;
- ei->i_da_metadata_calc_len = 1;
- blk_bits = order_base_2(lblock);
- return (blk_bits / EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb)) + 1;
-}
-
-/*
* Calculate number of indirect blocks touched by mapping @nrblocks logically
* contiguous blocks
*/
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 2fec62d764fa..fad82d08fca5 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -98,6 +98,7 @@ int ext4_get_max_inline_size(struct inode *inode)
error = ext4_get_inode_loc(inode, &iloc);
if (error) {
+ ext4_set_errno(inode->i_sb, -error);
ext4_error_inode(inode, __func__, __LINE__, 0,
"can't get inode location %lu",
inode->i_ino);
@@ -849,7 +850,7 @@ out:
/*
* Prepare the write for the inline data.
- * If the the data can be written into the inode, we just read
+ * If the data can be written into the inode, we just read
* the page and make it uptodate, and start the journal.
* Otherwise read the page, makes it dirty so that it can be
* handle in writepages(the i_disksize update is left to the
@@ -1761,6 +1762,7 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data)
err = ext4_get_inode_loc(dir, &iloc);
if (err) {
+ ext4_set_errno(dir->i_sb, -err);
EXT4_ERROR_INODE(dir, "error %d getting inode %lu block",
err, dir->i_ino);
return true;
diff --git a/fs/ext4/inode-test.c b/fs/ext4/inode-test.c
index bbce1c328d85..d62d802c9c12 100644
--- a/fs/ext4/inode-test.c
+++ b/fs/ext4/inode-test.c
@@ -269,4 +269,6 @@ static struct kunit_suite ext4_inode_test_suite = {
.test_cases = ext4_inode_test_cases,
};
-kunit_test_suite(ext4_inode_test_suite);
+kunit_test_suites(&ext4_inode_test_suite);
+
+MODULE_LICENSE("GPL v2");
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 629a25d999f0..3313168b680f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -48,8 +48,6 @@
#include <trace/events/ext4.h>
-#define MPAGE_DA_EXTENT_TAIL 0x01
-
static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
struct ext4_inode_info *ei)
{
@@ -271,6 +269,7 @@ void ext4_evict_inode(struct inode *inode)
if (inode->i_blocks) {
err = ext4_truncate(inode);
if (err) {
+ ext4_set_errno(inode->i_sb, -err);
ext4_error(inode->i_sb,
"couldn't truncate inode %lu (err %d)",
inode->i_ino, err);
@@ -402,7 +401,7 @@ int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk,
{
int ret;
- if (IS_ENCRYPTED(inode))
+ if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode))
return fscrypt_zeroout_range(inode, lblk, pblk, len);
ret = sb_issue_zeroout(inode->i_sb, pblk, len, GFP_NOFS);
@@ -2478,10 +2477,12 @@ update_disksize:
EXT4_I(inode)->i_disksize = disksize;
up_write(&EXT4_I(inode)->i_data_sem);
err2 = ext4_mark_inode_dirty(handle, inode);
- if (err2)
+ if (err2) {
+ ext4_set_errno(inode->i_sb, -err2);
ext4_error(inode->i_sb,
"Failed to mark inode %lu dirty",
inode->i_ino);
+ }
if (!err)
err = err2;
}
@@ -3448,6 +3449,22 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
return 0;
}
+static int ext4_iomap_overwrite_begin(struct inode *inode, loff_t offset,
+ loff_t length, unsigned flags, struct iomap *iomap,
+ struct iomap *srcmap)
+{
+ int ret;
+
+ /*
+ * Even for writes we don't need to allocate blocks, so just pretend
+ * we are reading to save overhead of starting a transaction.
+ */
+ flags &= ~IOMAP_WRITE;
+ ret = ext4_iomap_begin(inode, offset, length, flags, iomap, srcmap);
+ WARN_ON_ONCE(iomap->type != IOMAP_MAPPED);
+ return ret;
+}
+
static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length,
ssize_t written, unsigned flags, struct iomap *iomap)
{
@@ -3469,6 +3486,11 @@ const struct iomap_ops ext4_iomap_ops = {
.iomap_end = ext4_iomap_end,
};
+const struct iomap_ops ext4_iomap_overwrite_ops = {
+ .iomap_begin = ext4_iomap_overwrite_begin,
+ .iomap_end = ext4_iomap_end,
+};
+
static bool ext4_iomap_is_delalloc(struct inode *inode,
struct ext4_map_blocks *map)
{
@@ -3701,8 +3723,12 @@ static int __ext4_block_zero_page_range(handle_t *handle,
if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode)) {
/* We expect the key to be set. */
BUG_ON(!fscrypt_has_encryption_key(inode));
- WARN_ON_ONCE(fscrypt_decrypt_pagecache_blocks(
- page, blocksize, bh_offset(bh)));
+ err = fscrypt_decrypt_pagecache_blocks(page, blocksize,
+ bh_offset(bh));
+ if (err) {
+ clear_buffer_uptodate(bh);
+ goto unlock;
+ }
}
}
if (ext4_should_journal_data(inode)) {
@@ -3912,9 +3938,6 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
unsigned int credits;
int ret = 0;
- if (!S_ISREG(inode->i_mode))
- return -EOPNOTSUPP;
-
trace_ext4_punch_hole(inode, offset, length, 0);
ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
@@ -4240,6 +4263,8 @@ static int __ext4_get_inode_loc(struct inode *inode,
bh = sb_getblk(sb, block);
if (unlikely(!bh))
return -ENOMEM;
+ if (ext4_simulate_fail(sb, EXT4_SIM_INODE_EIO))
+ goto simulate_eio;
if (!buffer_uptodate(bh)) {
lock_buffer(bh);
@@ -4338,6 +4363,8 @@ make_io:
blk_finish_plug(&plug);
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
+ simulate_eio:
+ ext4_set_errno(inode->i_sb, EIO);
EXT4_ERROR_INODE_BLOCK(inode, block,
"unable to read itable block");
brelse(bh);
@@ -4551,7 +4578,9 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
sizeof(gen));
}
- if (!ext4_inode_csum_verify(inode, raw_inode, ei)) {
+ if (!ext4_inode_csum_verify(inode, raw_inode, ei) ||
+ ext4_simulate_fail(sb, EXT4_SIM_INODE_CRC)) {
+ ext4_set_errno(inode->i_sb, EFSBADCRC);
ext4_error_inode(inode, function, line, 0,
"iget: checksum invalid");
ret = -EFSBADCRC;
@@ -5090,6 +5119,7 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync)
sync_dirty_buffer(iloc.bh);
if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) {
+ ext4_set_errno(inode->i_sb, EIO);
EXT4_ERROR_INODE_BLOCK(inode, iloc.bh->b_blocknr,
"IO error syncing inode");
err = -EIO;
@@ -5368,7 +5398,8 @@ int ext4_getattr(const struct path *path, struct kstat *stat,
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int flags;
- if (EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) {
+ if ((request_mask & STATX_BTIME) &&
+ EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) {
stat->result_mask |= STATX_BTIME;
stat->btime.tv_sec = ei->i_crtime.tv_sec;
stat->btime.tv_nsec = ei->i_crtime.tv_nsec;
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index e8870fff8224..a0ec750018dd 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -1377,6 +1377,8 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case EXT4_IOC_CLEAR_ES_CACHE:
case EXT4_IOC_GETSTATE:
case EXT4_IOC_GET_ES_CACHE:
+ case EXT4_IOC_FSGETXATTR:
+ case EXT4_IOC_FSSETXATTR:
break;
default:
return -ENOIOCTLCMD;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index a3e2767bdf2f..f64838187559 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3895,6 +3895,7 @@ ext4_mb_discard_group_preallocations(struct super_block *sb,
bitmap_bh = ext4_read_block_bitmap(sb, group);
if (IS_ERR(bitmap_bh)) {
err = PTR_ERR(bitmap_bh);
+ ext4_set_errno(sb, -err);
ext4_error(sb, "Error %d reading block bitmap for %u",
err, group);
return 0;
@@ -4063,6 +4064,7 @@ repeat:
err = ext4_mb_load_buddy_gfp(sb, group, &e4b,
GFP_NOFS|__GFP_NOFAIL);
if (err) {
+ ext4_set_errno(sb, -err);
ext4_error(sb, "Error %d loading buddy information for %u",
err, group);
continue;
@@ -4071,6 +4073,7 @@ repeat:
bitmap_bh = ext4_read_block_bitmap(sb, group);
if (IS_ERR(bitmap_bh)) {
err = PTR_ERR(bitmap_bh);
+ ext4_set_errno(sb, -err);
ext4_error(sb, "Error %d reading block bitmap for %u",
err, group);
ext4_mb_unload_buddy(&e4b);
@@ -4325,6 +4328,7 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb,
err = ext4_mb_load_buddy_gfp(sb, group, &e4b,
GFP_NOFS|__GFP_NOFAIL);
if (err) {
+ ext4_set_errno(sb, -err);
ext4_error(sb, "Error %d loading buddy information for %u",
err, group);
continue;
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 2305b4374fd3..1c44b1a32001 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -173,8 +173,10 @@ static int kmmpd(void *data)
* (s_mmp_update_interval * 60) seconds.
*/
if (retval) {
- if ((failed_writes % 60) == 0)
+ if ((failed_writes % 60) == 0) {
+ ext4_set_errno(sb, -retval);
ext4_error(sb, "Error writing to MMP block");
+ }
failed_writes++;
}
@@ -205,6 +207,7 @@ static int kmmpd(void *data)
retval = read_mmp_block(sb, &bh_check, mmp_block);
if (retval) {
+ ext4_set_errno(sb, -retval);
ext4_error(sb, "error reading MMP data: %d",
retval);
goto exit_thread;
@@ -218,6 +221,7 @@ static int kmmpd(void *data)
"Error while updating MMP info. "
"The filesystem seems to have been"
" multiply mounted.");
+ ext4_set_errno(sb, EBUSY);
ext4_error(sb, "abort");
put_bh(bh_check);
retval = -EBUSY;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 1cb42d940784..129d2ebae00d 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -109,7 +109,10 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode,
struct ext4_dir_entry *dirent;
int is_dx_block = 0;
- bh = ext4_bread(NULL, inode, block, 0);
+ if (ext4_simulate_fail(inode->i_sb, EXT4_SIM_DIRBLOCK_EIO))
+ bh = ERR_PTR(-EIO);
+ else
+ bh = ext4_bread(NULL, inode, block, 0);
if (IS_ERR(bh)) {
__ext4_warning(inode->i_sb, func, line,
"inode #%lu: lblock %lu: comm %s: "
@@ -153,9 +156,11 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode,
* caller is sure it should be an index block.
*/
if (is_dx_block && type == INDEX) {
- if (ext4_dx_csum_verify(inode, dirent))
+ if (ext4_dx_csum_verify(inode, dirent) &&
+ !ext4_simulate_fail(inode->i_sb, EXT4_SIM_DIRBLOCK_CRC))
set_buffer_verified(bh);
else {
+ ext4_set_errno(inode->i_sb, EFSBADCRC);
ext4_error_inode(inode, func, line, block,
"Directory index failed checksum");
brelse(bh);
@@ -163,9 +168,11 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode,
}
}
if (!is_dx_block) {
- if (ext4_dirblock_csum_verify(inode, bh))
+ if (ext4_dirblock_csum_verify(inode, bh) &&
+ !ext4_simulate_fail(inode->i_sb, EXT4_SIM_DIRBLOCK_CRC))
set_buffer_verified(bh);
else {
+ ext4_set_errno(inode->i_sb, EFSBADCRC);
ext4_error_inode(inode, func, line, block,
"Directory block failed checksum");
brelse(bh);
@@ -1002,7 +1009,6 @@ static int htree_dirblock_to_tree(struct file *dir_file,
top = (struct ext4_dir_entry_2 *) ((char *) de +
dir->i_sb->s_blocksize -
EXT4_DIR_REC_LEN(0));
-#ifdef CONFIG_FS_ENCRYPTION
/* Check if the directory is encrypted */
if (IS_ENCRYPTED(dir)) {
err = fscrypt_get_encryption_info(dir);
@@ -1017,7 +1023,7 @@ static int htree_dirblock_to_tree(struct file *dir_file,
return err;
}
}
-#endif
+
for (; de < top; de = ext4_next_entry(de, dir->i_sb->s_blocksize)) {
if (ext4_check_dir_entry(dir, NULL, de, bh,
bh->b_data, bh->b_size,
@@ -1065,9 +1071,7 @@ static int htree_dirblock_to_tree(struct file *dir_file,
}
errout:
brelse(bh);
-#ifdef CONFIG_FS_ENCRYPTION
fscrypt_fname_free_buffer(&fname_crypto_str);
-#endif
return count;
}
@@ -1527,6 +1531,7 @@ restart:
goto next;
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
+ ext4_set_errno(sb, EIO);
EXT4_ERROR_INODE(dir, "reading directory lblock %lu",
(unsigned long) block);
brelse(bh);
@@ -1537,6 +1542,7 @@ restart:
!is_dx_internal_node(dir, block,
(struct ext4_dir_entry *)bh->b_data) &&
!ext4_dirblock_csum_verify(dir, bh)) {
+ ext4_set_errno(sb, EFSBADCRC);
EXT4_ERROR_INODE(dir, "checksumming directory "
"block %lu", (unsigned long)block);
brelse(bh);
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 24aeedb8fc75..68b39e75446a 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -512,17 +512,26 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
gfp_t gfp_flags = GFP_NOFS;
unsigned int enc_bytes = round_up(len, i_blocksize(inode));
+ /*
+ * Since bounce page allocation uses a mempool, we can only use
+ * a waiting mask (i.e. request guaranteed allocation) on the
+ * first page of the bio. Otherwise it can deadlock.
+ */
+ if (io->io_bio)
+ gfp_flags = GFP_NOWAIT | __GFP_NOWARN;
retry_encrypt:
bounce_page = fscrypt_encrypt_pagecache_blocks(page, enc_bytes,
0, gfp_flags);
if (IS_ERR(bounce_page)) {
ret = PTR_ERR(bounce_page);
- if (ret == -ENOMEM && wbc->sync_mode == WB_SYNC_ALL) {
- if (io->io_bio) {
+ if (ret == -ENOMEM &&
+ (io->io_bio || wbc->sync_mode == WB_SYNC_ALL)) {
+ gfp_flags = GFP_NOFS;
+ if (io->io_bio)
ext4_io_submit(io);
- congestion_wait(BLK_RW_ASYNC, HZ/50);
- }
- gfp_flags |= __GFP_NOFAIL;
+ else
+ gfp_flags |= __GFP_NOFAIL;
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
goto retry_encrypt;
}
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index fef7755300c3..c1769afbf799 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -57,6 +57,7 @@ enum bio_post_read_step {
STEP_INITIAL = 0,
STEP_DECRYPT,
STEP_VERITY,
+ STEP_MAX,
};
struct bio_post_read_ctx {
@@ -106,10 +107,22 @@ static void verity_work(struct work_struct *work)
{
struct bio_post_read_ctx *ctx =
container_of(work, struct bio_post_read_ctx, work);
+ struct bio *bio = ctx->bio;
- fsverity_verify_bio(ctx->bio);
+ /*
+ * fsverity_verify_bio() may call readpages() again, and although verity
+ * will be disabled for that, decryption may still be needed, causing
+ * another bio_post_read_ctx to be allocated. So to guarantee that
+ * mempool_alloc() never deadlocks we must free the current ctx first.
+ * This is safe because verity is the last post-read step.
+ */
+ BUILD_BUG_ON(STEP_VERITY + 1 != STEP_MAX);
+ mempool_free(ctx, bio_post_read_ctx_pool);
+ bio->bi_private = NULL;
- bio_post_read_processing(ctx);
+ fsverity_verify_bio(bio);
+
+ __read_end_io(bio);
}
static void bio_post_read_processing(struct bio_post_read_ctx *ctx)
@@ -176,12 +189,11 @@ static inline bool ext4_need_verity(const struct inode *inode, pgoff_t idx)
idx < DIV_ROUND_UP(inode->i_size, PAGE_SIZE);
}
-static struct bio_post_read_ctx *get_bio_post_read_ctx(struct inode *inode,
- struct bio *bio,
- pgoff_t first_idx)
+static void ext4_set_bio_post_read_ctx(struct bio *bio,
+ const struct inode *inode,
+ pgoff_t first_idx)
{
unsigned int post_read_steps = 0;
- struct bio_post_read_ctx *ctx = NULL;
if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode))
post_read_steps |= 1 << STEP_DECRYPT;
@@ -190,14 +202,14 @@ static struct bio_post_read_ctx *get_bio_post_read_ctx(struct inode *inode,
post_read_steps |= 1 << STEP_VERITY;
if (post_read_steps) {
- ctx = mempool_alloc(bio_post_read_ctx_pool, GFP_NOFS);
- if (!ctx)
- return ERR_PTR(-ENOMEM);
+ /* Due to the mempool, this never fails. */
+ struct bio_post_read_ctx *ctx =
+ mempool_alloc(bio_post_read_ctx_pool, GFP_NOFS);
+
ctx->bio = bio;
ctx->enabled_steps = post_read_steps;
bio->bi_private = ctx;
}
- return ctx;
}
static inline loff_t ext4_readpage_limit(struct inode *inode)
@@ -358,24 +370,16 @@ int ext4_mpage_readpages(struct address_space *mapping,
bio = NULL;
}
if (bio == NULL) {
- struct bio_post_read_ctx *ctx;
-
/*
* bio_alloc will _always_ be able to allocate a bio if
* __GFP_DIRECT_RECLAIM is set, see bio_alloc_bioset().
*/
bio = bio_alloc(GFP_KERNEL,
min_t(int, nr_pages, BIO_MAX_PAGES));
- ctx = get_bio_post_read_ctx(inode, bio, page->index);
- if (IS_ERR(ctx)) {
- bio_put(bio);
- bio = NULL;
- goto set_error_page;
- }
+ ext4_set_bio_post_read_ctx(bio, inode, page->index);
bio_set_dev(bio, bdev);
bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9);
bio->bi_end_io = mpage_end_io;
- bio->bi_private = ctx;
bio_set_op_attrs(bio, REQ_OP_READ,
is_readahead ? REQ_RAHEAD : 0);
}
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index a8c0f2b5b6e1..86a2500ed292 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -824,9 +824,8 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
if (unlikely(err))
goto errout;
- n_group_desc = ext4_kvmalloc((gdb_num + 1) *
- sizeof(struct buffer_head *),
- GFP_NOFS);
+ n_group_desc = kvmalloc((gdb_num + 1) * sizeof(struct buffer_head *),
+ GFP_KERNEL);
if (!n_group_desc) {
err = -ENOMEM;
ext4_warning(sb, "not enough memory for %lu groups",
@@ -900,9 +899,8 @@ static int add_new_gdb_meta_bg(struct super_block *sb,
gdb_bh = ext4_sb_bread(sb, gdblock, 0);
if (IS_ERR(gdb_bh))
return PTR_ERR(gdb_bh);
- n_group_desc = ext4_kvmalloc((gdb_num + 1) *
- sizeof(struct buffer_head *),
- GFP_NOFS);
+ n_group_desc = kvmalloc((gdb_num + 1) * sizeof(struct buffer_head *),
+ GFP_KERNEL);
if (!n_group_desc) {
brelse(gdb_bh);
err = -ENOMEM;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 2937a8873fe1..88b213bd32bc 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -154,7 +154,7 @@ ext4_sb_bread(struct super_block *sb, sector_t block, int op_flags)
if (bh == NULL)
return ERR_PTR(-ENOMEM);
- if (buffer_uptodate(bh))
+ if (ext4_buffer_uptodate(bh))
return bh;
ll_rw_block(REQ_OP_READ, REQ_META | op_flags, 1, &bh);
wait_on_buffer(bh);
@@ -204,26 +204,6 @@ void ext4_superblock_csum_set(struct super_block *sb)
es->s_checksum = ext4_superblock_csum(sb, es);
}
-void *ext4_kvmalloc(size_t size, gfp_t flags)
-{
- void *ret;
-
- ret = kmalloc(size, flags | __GFP_NOWARN);
- if (!ret)
- ret = __vmalloc(size, flags, PAGE_KERNEL);
- return ret;
-}
-
-void *ext4_kvzalloc(size_t size, gfp_t flags)
-{
- void *ret;
-
- ret = kzalloc(size, flags | __GFP_NOWARN);
- if (!ret)
- ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL);
- return ret;
-}
-
ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
struct ext4_group_desc *bg)
{
@@ -367,6 +347,8 @@ static void __save_error_info(struct super_block *sb, const char *func,
ext4_update_tstamp(es, s_last_error_time);
strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func));
es->s_last_error_line = cpu_to_le32(line);
+ if (es->s_last_error_errcode == 0)
+ es->s_last_error_errcode = EXT4_ERR_EFSCORRUPTED;
if (!es->s_first_error_time) {
es->s_first_error_time = es->s_last_error_time;
es->s_first_error_time_hi = es->s_last_error_time_hi;
@@ -375,6 +357,7 @@ static void __save_error_info(struct super_block *sb, const char *func,
es->s_first_error_line = cpu_to_le32(line);
es->s_first_error_ino = es->s_last_error_ino;
es->s_first_error_block = es->s_last_error_block;
+ es->s_first_error_errcode = es->s_last_error_errcode;
}
/*
* Start the daily error reporting function if it hasn't been
@@ -631,6 +614,66 @@ const char *ext4_decode_error(struct super_block *sb, int errno,
return errstr;
}
+void ext4_set_errno(struct super_block *sb, int err)
+{
+ if (err < 0)
+ err = -err;
+
+ switch (err) {
+ case EIO:
+ err = EXT4_ERR_EIO;
+ break;
+ case ENOMEM:
+ err = EXT4_ERR_ENOMEM;
+ break;
+ case EFSBADCRC:
+ err = EXT4_ERR_EFSBADCRC;
+ break;
+ case EFSCORRUPTED:
+ err = EXT4_ERR_EFSCORRUPTED;
+ break;
+ case ENOSPC:
+ err = EXT4_ERR_ENOSPC;
+ break;
+ case ENOKEY:
+ err = EXT4_ERR_ENOKEY;
+ break;
+ case EROFS:
+ err = EXT4_ERR_EROFS;
+ break;
+ case EFBIG:
+ err = EXT4_ERR_EFBIG;
+ break;
+ case EEXIST:
+ err = EXT4_ERR_EEXIST;
+ break;
+ case ERANGE:
+ err = EXT4_ERR_ERANGE;
+ break;
+ case EOVERFLOW:
+ err = EXT4_ERR_EOVERFLOW;
+ break;
+ case EBUSY:
+ err = EXT4_ERR_EBUSY;
+ break;
+ case ENOTDIR:
+ err = EXT4_ERR_ENOTDIR;
+ break;
+ case ENOTEMPTY:
+ err = EXT4_ERR_ENOTEMPTY;
+ break;
+ case ESHUTDOWN:
+ err = EXT4_ERR_ESHUTDOWN;
+ break;
+ case EFAULT:
+ err = EXT4_ERR_EFAULT;
+ break;
+ default:
+ err = EXT4_ERR_UNKNOWN;
+ }
+ EXT4_SB(sb)->s_es->s_last_error_errcode = err;
+}
+
/* __ext4_std_error decodes expected errors from journaling functions
* automatically and invokes the appropriate error response. */
@@ -655,6 +698,7 @@ void __ext4_std_error(struct super_block *sb, const char *function,
sb->s_id, function, line, errstr);
}
+ ext4_set_errno(sb, -errno);
save_error_info(sb, function, line);
ext4_handle_error(sb);
}
@@ -982,8 +1026,10 @@ static void ext4_put_super(struct super_block *sb)
aborted = is_journal_aborted(sbi->s_journal);
err = jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
- if ((err < 0) && !aborted)
+ if ((err < 0) && !aborted) {
+ ext4_set_errno(sb, -err);
ext4_abort(sb, "Couldn't clean up the journal");
+ }
}
ext4_unregister_sysfs(sb);
@@ -1085,8 +1131,6 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
ei->i_es_shk_nr = 0;
ei->i_es_shrink_lblk = 0;
ei->i_reserved_data_blocks = 0;
- ei->i_da_metadata_calc_len = 0;
- ei->i_da_metadata_calc_last_lblock = 0;
spin_lock_init(&(ei->i_block_reservation_lock));
ext4_init_pending_tree(&ei->i_pending_tree);
#ifdef CONFIG_QUOTA
@@ -1548,6 +1592,7 @@ static const match_table_t tokens = {
{Opt_auto_da_alloc, "auto_da_alloc"},
{Opt_noauto_da_alloc, "noauto_da_alloc"},
{Opt_dioread_nolock, "dioread_nolock"},
+ {Opt_dioread_lock, "nodioread_nolock"},
{Opt_dioread_lock, "dioread_lock"},
{Opt_discard, "discard"},
{Opt_nodiscard, "nodiscard"},
@@ -3720,6 +3765,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
set_opt(sb, NO_UID32);
/* xattr user namespace & acls are now defaulted on */
set_opt(sb, XATTR_USER);
+ set_opt(sb, DIOREAD_NOLOCK);
#ifdef CONFIG_EXT4_FS_POSIX_ACL
set_opt(sb, POSIX_ACL);
#endif
@@ -3887,9 +3933,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
#endif
if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
- printk_once(KERN_WARNING "EXT4-fs: Warning: mounting "
- "with data=journal disables delayed "
- "allocation and O_DIRECT support!\n");
+ printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, and O_DIRECT support!\n");
+ clear_opt(sb, DIOREAD_NOLOCK);
if (test_opt2(sb, EXPLICIT_DELALLOC)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"both data=journal and delalloc");
@@ -5540,9 +5585,15 @@ static int ext4_statfs_project(struct super_block *sb,
return PTR_ERR(dquot);
spin_lock(&dquot->dq_dqb_lock);
- limit = (dquot->dq_dqb.dqb_bsoftlimit ?
- dquot->dq_dqb.dqb_bsoftlimit :
- dquot->dq_dqb.dqb_bhardlimit) >> sb->s_blocksize_bits;
+ limit = 0;
+ if (dquot->dq_dqb.dqb_bsoftlimit &&
+ (!limit || dquot->dq_dqb.dqb_bsoftlimit < limit))
+ limit = dquot->dq_dqb.dqb_bsoftlimit;
+ if (dquot->dq_dqb.dqb_bhardlimit &&
+ (!limit || dquot->dq_dqb.dqb_bhardlimit < limit))
+ limit = dquot->dq_dqb.dqb_bhardlimit;
+ limit >>= sb->s_blocksize_bits;
+
if (limit && buf->f_blocks > limit) {
curblock = (dquot->dq_dqb.dqb_curspace +
dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits;
@@ -5552,9 +5603,14 @@ static int ext4_statfs_project(struct super_block *sb,
(buf->f_blocks - curblock) : 0;
}
- limit = dquot->dq_dqb.dqb_isoftlimit ?
- dquot->dq_dqb.dqb_isoftlimit :
- dquot->dq_dqb.dqb_ihardlimit;
+ limit = 0;
+ if (dquot->dq_dqb.dqb_isoftlimit &&
+ (!limit || dquot->dq_dqb.dqb_isoftlimit < limit))
+ limit = dquot->dq_dqb.dqb_isoftlimit;
+ if (dquot->dq_dqb.dqb_ihardlimit &&
+ (!limit || dquot->dq_dqb.dqb_ihardlimit < limit))
+ limit = dquot->dq_dqb.dqb_ihardlimit;
+
if (limit && buf->f_files > limit) {
buf->f_files = limit;
buf->f_ffree =
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index eb1efad0e20a..d218ebdafa4a 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -29,6 +29,10 @@ typedef enum {
attr_last_error_time,
attr_feature,
attr_pointer_ui,
+ attr_pointer_ul,
+ attr_pointer_u64,
+ attr_pointer_u8,
+ attr_pointer_string,
attr_pointer_atomic,
attr_journal_task,
} attr_id_t;
@@ -46,6 +50,7 @@ struct ext4_attr {
struct attribute attr;
short attr_id;
short attr_ptr;
+ unsigned short attr_size;
union {
int offset;
void *explicit_ptr;
@@ -154,12 +159,35 @@ static struct ext4_attr ext4_attr_##_name = { \
}, \
}
+#define EXT4_ATTR_STRING(_name,_mode,_size,_struct,_elname) \
+static struct ext4_attr ext4_attr_##_name = { \
+ .attr = {.name = __stringify(_name), .mode = _mode }, \
+ .attr_id = attr_pointer_string, \
+ .attr_size = _size, \
+ .attr_ptr = ptr_##_struct##_offset, \
+ .u = { \
+ .offset = offsetof(struct _struct, _elname),\
+ }, \
+}
+
#define EXT4_RO_ATTR_ES_UI(_name,_elname) \
EXT4_ATTR_OFFSET(_name, 0444, pointer_ui, ext4_super_block, _elname)
+#define EXT4_RO_ATTR_ES_U8(_name,_elname) \
+ EXT4_ATTR_OFFSET(_name, 0444, pointer_u8, ext4_super_block, _elname)
+
+#define EXT4_RO_ATTR_ES_U64(_name,_elname) \
+ EXT4_ATTR_OFFSET(_name, 0444, pointer_u64, ext4_super_block, _elname)
+
+#define EXT4_RO_ATTR_ES_STRING(_name,_elname,_size) \
+ EXT4_ATTR_STRING(_name, 0444, _size, ext4_super_block, _elname)
+
#define EXT4_RW_ATTR_SBI_UI(_name,_elname) \
EXT4_ATTR_OFFSET(_name, 0644, pointer_ui, ext4_sb_info, _elname)
+#define EXT4_RW_ATTR_SBI_UL(_name,_elname) \
+ EXT4_ATTR_OFFSET(_name, 0644, pointer_ul, ext4_sb_info, _elname)
+
#define EXT4_ATTR_PTR(_name,_mode,_id,_ptr) \
static struct ext4_attr ext4_attr_##_name = { \
.attr = {.name = __stringify(_name), .mode = _mode }, \
@@ -194,7 +222,20 @@ EXT4_RW_ATTR_SBI_UI(warning_ratelimit_interval_ms, s_warning_ratelimit_state.int
EXT4_RW_ATTR_SBI_UI(warning_ratelimit_burst, s_warning_ratelimit_state.burst);
EXT4_RW_ATTR_SBI_UI(msg_ratelimit_interval_ms, s_msg_ratelimit_state.interval);
EXT4_RW_ATTR_SBI_UI(msg_ratelimit_burst, s_msg_ratelimit_state.burst);
+#ifdef CONFIG_EXT4_DEBUG
+EXT4_RW_ATTR_SBI_UL(simulate_fail, s_simulate_fail);
+#endif
EXT4_RO_ATTR_ES_UI(errors_count, s_error_count);
+EXT4_RO_ATTR_ES_U8(first_error_errcode, s_first_error_errcode);
+EXT4_RO_ATTR_ES_U8(last_error_errcode, s_last_error_errcode);
+EXT4_RO_ATTR_ES_UI(first_error_ino, s_first_error_ino);
+EXT4_RO_ATTR_ES_UI(last_error_ino, s_last_error_ino);
+EXT4_RO_ATTR_ES_U64(first_error_block, s_first_error_block);
+EXT4_RO_ATTR_ES_U64(last_error_block, s_last_error_block);
+EXT4_RO_ATTR_ES_UI(first_error_line, s_first_error_line);
+EXT4_RO_ATTR_ES_UI(last_error_line, s_last_error_line);
+EXT4_RO_ATTR_ES_STRING(first_error_func, s_first_error_func, 32);
+EXT4_RO_ATTR_ES_STRING(last_error_func, s_last_error_func, 32);
EXT4_ATTR(first_error_time, 0444, first_error_time);
EXT4_ATTR(last_error_time, 0444, last_error_time);
EXT4_ATTR(journal_task, 0444, journal_task);
@@ -225,9 +266,22 @@ static struct attribute *ext4_attrs[] = {
ATTR_LIST(msg_ratelimit_interval_ms),
ATTR_LIST(msg_ratelimit_burst),
ATTR_LIST(errors_count),
+ ATTR_LIST(first_error_ino),
+ ATTR_LIST(last_error_ino),
+ ATTR_LIST(first_error_block),
+ ATTR_LIST(last_error_block),
+ ATTR_LIST(first_error_line),
+ ATTR_LIST(last_error_line),
+ ATTR_LIST(first_error_func),
+ ATTR_LIST(last_error_func),
+ ATTR_LIST(first_error_errcode),
+ ATTR_LIST(last_error_errcode),
ATTR_LIST(first_error_time),
ATTR_LIST(last_error_time),
ATTR_LIST(journal_task),
+#ifdef CONFIG_EXT4_DEBUG
+ ATTR_LIST(simulate_fail),
+#endif
NULL,
};
ATTRIBUTE_GROUPS(ext4);
@@ -280,7 +334,7 @@ static void *calc_ptr(struct ext4_attr *a, struct ext4_sb_info *sbi)
static ssize_t __print_tstamp(char *buf, __le32 lo, __u8 hi)
{
- return snprintf(buf, PAGE_SIZE, "%lld",
+ return snprintf(buf, PAGE_SIZE, "%lld\n",
((time64_t)hi << 32) + le32_to_cpu(lo));
}
@@ -318,6 +372,30 @@ static ssize_t ext4_attr_show(struct kobject *kobj,
else
return snprintf(buf, PAGE_SIZE, "%u\n",
*((unsigned int *) ptr));
+ case attr_pointer_ul:
+ if (!ptr)
+ return 0;
+ return snprintf(buf, PAGE_SIZE, "%lu\n",
+ *((unsigned long *) ptr));
+ case attr_pointer_u8:
+ if (!ptr)
+ return 0;
+ return snprintf(buf, PAGE_SIZE, "%u\n",
+ *((unsigned char *) ptr));
+ case attr_pointer_u64:
+ if (!ptr)
+ return 0;
+ if (a->attr_ptr == ptr_ext4_super_block_offset)
+ return snprintf(buf, PAGE_SIZE, "%llu\n",
+ le64_to_cpup(ptr));
+ else
+ return snprintf(buf, PAGE_SIZE, "%llu\n",
+ *((unsigned long long *) ptr));
+ case attr_pointer_string:
+ if (!ptr)
+ return 0;
+ return snprintf(buf, PAGE_SIZE, "%.*s\n", a->attr_size,
+ (char *) ptr);
case attr_pointer_atomic:
if (!ptr)
return 0;
@@ -361,6 +439,14 @@ static ssize_t ext4_attr_store(struct kobject *kobj,
else
*((unsigned int *) ptr) = t;
return len;
+ case attr_pointer_ul:
+ if (!ptr)
+ return 0;
+ ret = kstrtoul(skip_spaces(buf), 0, &t);
+ if (ret)
+ return ret;
+ *((unsigned long *) ptr) = t;
+ return len;
case attr_inode_readahead:
return inode_readahead_blks_store(sbi, buf, len);
case attr_trigger_test_error:
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 8966a5439a22..8cac7d95c3ad 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -1456,7 +1456,7 @@ ext4_xattr_inode_cache_find(struct inode *inode, const void *value,
if (!ce)
return NULL;
- ea_data = ext4_kvmalloc(value_len, GFP_NOFS);
+ ea_data = kvmalloc(value_len, GFP_KERNEL);
if (!ea_data) {
mb_cache_entry_put(ea_inode_cache, ce);
return NULL;
@@ -2879,9 +2879,11 @@ int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO);
if (IS_ERR(bh)) {
error = PTR_ERR(bh);
- if (error == -EIO)
+ if (error == -EIO) {
+ ext4_set_errno(inode->i_sb, EIO);
EXT4_ERROR_INODE(inode, "block %llu read error",
EXT4_I(inode)->i_file_acl);
+ }
bh = NULL;
goto cleanup;
}
diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig
index 599fb9194c6a..f0faada30f30 100644
--- a/fs/f2fs/Kconfig
+++ b/fs/f2fs/Kconfig
@@ -22,7 +22,7 @@ config F2FS_FS
config F2FS_STAT_FS
bool "F2FS Status Information"
- depends on F2FS_FS && DEBUG_FS
+ depends on F2FS_FS
default y
help
/sys/kernel/debug/f2fs/ contains information about all the partitions
@@ -93,3 +93,28 @@ config F2FS_FAULT_INJECTION
Test F2FS to inject faults such as ENOMEM, ENOSPC, and so on.
If unsure, say N.
+
+config F2FS_FS_COMPRESSION
+ bool "F2FS compression feature"
+ depends on F2FS_FS
+ help
+ Enable filesystem-level compression on f2fs regular files,
+ multiple back-end compression algorithms are supported.
+
+config F2FS_FS_LZO
+ bool "LZO compression support"
+ depends on F2FS_FS_COMPRESSION
+ select LZO_COMPRESS
+ select LZO_DECOMPRESS
+ default y
+ help
+ Support LZO compress algorithm, if unsure, say Y.
+
+config F2FS_FS_LZ4
+ bool "LZ4 compression support"
+ depends on F2FS_FS_COMPRESSION
+ select LZ4_COMPRESS
+ select LZ4_DECOMPRESS
+ default y
+ help
+ Support LZ4 compress algorithm, if unsure, say Y.
diff --git a/fs/f2fs/Makefile b/fs/f2fs/Makefile
index 2aaecc63834f..ee7316b42f69 100644
--- a/fs/f2fs/Makefile
+++ b/fs/f2fs/Makefile
@@ -9,3 +9,4 @@ f2fs-$(CONFIG_F2FS_FS_XATTR) += xattr.o
f2fs-$(CONFIG_F2FS_FS_POSIX_ACL) += acl.o
f2fs-$(CONFIG_F2FS_IO_TRACE) += trace.o
f2fs-$(CONFIG_FS_VERITY) += verity.o
+f2fs-$(CONFIG_F2FS_FS_COMPRESSION) += compress.o
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index ffdaba0c55d2..44e84ac5c941 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -1509,10 +1509,10 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
f2fs_wait_on_all_pages_writeback(sbi);
/*
- * invalidate intermediate page cache borrowed from meta inode
- * which are used for migration of encrypted inode's blocks.
+ * invalidate intermediate page cache borrowed from meta inode which are
+ * used for migration of encrypted or verity inode's blocks.
*/
- if (f2fs_sb_has_encrypt(sbi))
+ if (f2fs_sb_has_encrypt(sbi) || f2fs_sb_has_verity(sbi))
invalidate_mapping_pages(META_MAPPING(sbi),
MAIN_BLKADDR(sbi), MAX_BLKADDR(sbi) - 1);
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
new file mode 100644
index 000000000000..d8a64be90a50
--- /dev/null
+++ b/fs/f2fs/compress.c
@@ -0,0 +1,1176 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * f2fs compress support
+ *
+ * Copyright (c) 2019 Chao Yu <chao@kernel.org>
+ */
+
+#include <linux/fs.h>
+#include <linux/f2fs_fs.h>
+#include <linux/writeback.h>
+#include <linux/backing-dev.h>
+#include <linux/lzo.h>
+#include <linux/lz4.h>
+
+#include "f2fs.h"
+#include "node.h"
+#include <trace/events/f2fs.h>
+
+struct f2fs_compress_ops {
+ int (*init_compress_ctx)(struct compress_ctx *cc);
+ void (*destroy_compress_ctx)(struct compress_ctx *cc);
+ int (*compress_pages)(struct compress_ctx *cc);
+ int (*decompress_pages)(struct decompress_io_ctx *dic);
+};
+
+static unsigned int offset_in_cluster(struct compress_ctx *cc, pgoff_t index)
+{
+ return index & (cc->cluster_size - 1);
+}
+
+static pgoff_t cluster_idx(struct compress_ctx *cc, pgoff_t index)
+{
+ return index >> cc->log_cluster_size;
+}
+
+static pgoff_t start_idx_of_cluster(struct compress_ctx *cc)
+{
+ return cc->cluster_idx << cc->log_cluster_size;
+}
+
+bool f2fs_is_compressed_page(struct page *page)
+{
+ if (!PagePrivate(page))
+ return false;
+ if (!page_private(page))
+ return false;
+ if (IS_ATOMIC_WRITTEN_PAGE(page) || IS_DUMMY_WRITTEN_PAGE(page))
+ return false;
+ f2fs_bug_on(F2FS_M_SB(page->mapping),
+ *((u32 *)page_private(page)) != F2FS_COMPRESSED_PAGE_MAGIC);
+ return true;
+}
+
+static void f2fs_set_compressed_page(struct page *page,
+ struct inode *inode, pgoff_t index, void *data, refcount_t *r)
+{
+ SetPagePrivate(page);
+ set_page_private(page, (unsigned long)data);
+
+ /* i_crypto_info and iv index */
+ page->index = index;
+ page->mapping = inode->i_mapping;
+ if (r)
+ refcount_inc(r);
+}
+
+static void f2fs_put_compressed_page(struct page *page)
+{
+ set_page_private(page, (unsigned long)NULL);
+ ClearPagePrivate(page);
+ page->mapping = NULL;
+ unlock_page(page);
+ put_page(page);
+}
+
+static void f2fs_drop_rpages(struct compress_ctx *cc, int len, bool unlock)
+{
+ int i;
+
+ for (i = 0; i < len; i++) {
+ if (!cc->rpages[i])
+ continue;
+ if (unlock)
+ unlock_page(cc->rpages[i]);
+ else
+ put_page(cc->rpages[i]);
+ }
+}
+
+static void f2fs_put_rpages(struct compress_ctx *cc)
+{
+ f2fs_drop_rpages(cc, cc->cluster_size, false);
+}
+
+static void f2fs_unlock_rpages(struct compress_ctx *cc, int len)
+{
+ f2fs_drop_rpages(cc, len, true);
+}
+
+static void f2fs_put_rpages_mapping(struct compress_ctx *cc,
+ struct address_space *mapping,
+ pgoff_t start, int len)
+{
+ int i;
+
+ for (i = 0; i < len; i++) {
+ struct page *page = find_get_page(mapping, start + i);
+
+ put_page(page);
+ put_page(page);
+ }
+}
+
+static void f2fs_put_rpages_wbc(struct compress_ctx *cc,
+ struct writeback_control *wbc, bool redirty, int unlock)
+{
+ unsigned int i;
+
+ for (i = 0; i < cc->cluster_size; i++) {
+ if (!cc->rpages[i])
+ continue;
+ if (redirty)
+ redirty_page_for_writepage(wbc, cc->rpages[i]);
+ f2fs_put_page(cc->rpages[i], unlock);
+ }
+}
+
+struct page *f2fs_compress_control_page(struct page *page)
+{
+ return ((struct compress_io_ctx *)page_private(page))->rpages[0];
+}
+
+int f2fs_init_compress_ctx(struct compress_ctx *cc)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(cc->inode);
+
+ if (cc->nr_rpages)
+ return 0;
+
+ cc->rpages = f2fs_kzalloc(sbi, sizeof(struct page *) <<
+ cc->log_cluster_size, GFP_NOFS);
+ return cc->rpages ? 0 : -ENOMEM;
+}
+
+void f2fs_destroy_compress_ctx(struct compress_ctx *cc)
+{
+ kfree(cc->rpages);
+ cc->rpages = NULL;
+ cc->nr_rpages = 0;
+ cc->nr_cpages = 0;
+ cc->cluster_idx = NULL_CLUSTER;
+}
+
+void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct page *page)
+{
+ unsigned int cluster_ofs;
+
+ if (!f2fs_cluster_can_merge_page(cc, page->index))
+ f2fs_bug_on(F2FS_I_SB(cc->inode), 1);
+
+ cluster_ofs = offset_in_cluster(cc, page->index);
+ cc->rpages[cluster_ofs] = page;
+ cc->nr_rpages++;
+ cc->cluster_idx = cluster_idx(cc, page->index);
+}
+
+#ifdef CONFIG_F2FS_FS_LZO
+static int lzo_init_compress_ctx(struct compress_ctx *cc)
+{
+ cc->private = f2fs_kvmalloc(F2FS_I_SB(cc->inode),
+ LZO1X_MEM_COMPRESS, GFP_NOFS);
+ if (!cc->private)
+ return -ENOMEM;
+
+ cc->clen = lzo1x_worst_compress(PAGE_SIZE << cc->log_cluster_size);
+ return 0;
+}
+
+static void lzo_destroy_compress_ctx(struct compress_ctx *cc)
+{
+ kvfree(cc->private);
+ cc->private = NULL;
+}
+
+static int lzo_compress_pages(struct compress_ctx *cc)
+{
+ int ret;
+
+ ret = lzo1x_1_compress(cc->rbuf, cc->rlen, cc->cbuf->cdata,
+ &cc->clen, cc->private);
+ if (ret != LZO_E_OK) {
+ printk_ratelimited("%sF2FS-fs (%s): lzo compress failed, ret:%d\n",
+ KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id, ret);
+ return -EIO;
+ }
+ return 0;
+}
+
+static int lzo_decompress_pages(struct decompress_io_ctx *dic)
+{
+ int ret;
+
+ ret = lzo1x_decompress_safe(dic->cbuf->cdata, dic->clen,
+ dic->rbuf, &dic->rlen);
+ if (ret != LZO_E_OK) {
+ printk_ratelimited("%sF2FS-fs (%s): lzo decompress failed, ret:%d\n",
+ KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id, ret);
+ return -EIO;
+ }
+
+ if (dic->rlen != PAGE_SIZE << dic->log_cluster_size) {
+ printk_ratelimited("%sF2FS-fs (%s): lzo invalid rlen:%zu, "
+ "expected:%lu\n", KERN_ERR,
+ F2FS_I_SB(dic->inode)->sb->s_id,
+ dic->rlen,
+ PAGE_SIZE << dic->log_cluster_size);
+ return -EIO;
+ }
+ return 0;
+}
+
+static const struct f2fs_compress_ops f2fs_lzo_ops = {
+ .init_compress_ctx = lzo_init_compress_ctx,
+ .destroy_compress_ctx = lzo_destroy_compress_ctx,
+ .compress_pages = lzo_compress_pages,
+ .decompress_pages = lzo_decompress_pages,
+};
+#endif
+
+#ifdef CONFIG_F2FS_FS_LZ4
+static int lz4_init_compress_ctx(struct compress_ctx *cc)
+{
+ cc->private = f2fs_kvmalloc(F2FS_I_SB(cc->inode),
+ LZ4_MEM_COMPRESS, GFP_NOFS);
+ if (!cc->private)
+ return -ENOMEM;
+
+ cc->clen = LZ4_compressBound(PAGE_SIZE << cc->log_cluster_size);
+ return 0;
+}
+
+static void lz4_destroy_compress_ctx(struct compress_ctx *cc)
+{
+ kvfree(cc->private);
+ cc->private = NULL;
+}
+
+static int lz4_compress_pages(struct compress_ctx *cc)
+{
+ int len;
+
+ len = LZ4_compress_default(cc->rbuf, cc->cbuf->cdata, cc->rlen,
+ cc->clen, cc->private);
+ if (!len) {
+ printk_ratelimited("%sF2FS-fs (%s): lz4 compress failed\n",
+ KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id);
+ return -EIO;
+ }
+ cc->clen = len;
+ return 0;
+}
+
+static int lz4_decompress_pages(struct decompress_io_ctx *dic)
+{
+ int ret;
+
+ ret = LZ4_decompress_safe(dic->cbuf->cdata, dic->rbuf,
+ dic->clen, dic->rlen);
+ if (ret < 0) {
+ printk_ratelimited("%sF2FS-fs (%s): lz4 decompress failed, ret:%d\n",
+ KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id, ret);
+ return -EIO;
+ }
+
+ if (ret != PAGE_SIZE << dic->log_cluster_size) {
+ printk_ratelimited("%sF2FS-fs (%s): lz4 invalid rlen:%zu, "
+ "expected:%lu\n", KERN_ERR,
+ F2FS_I_SB(dic->inode)->sb->s_id,
+ dic->rlen,
+ PAGE_SIZE << dic->log_cluster_size);
+ return -EIO;
+ }
+ return 0;
+}
+
+static const struct f2fs_compress_ops f2fs_lz4_ops = {
+ .init_compress_ctx = lz4_init_compress_ctx,
+ .destroy_compress_ctx = lz4_destroy_compress_ctx,
+ .compress_pages = lz4_compress_pages,
+ .decompress_pages = lz4_decompress_pages,
+};
+#endif
+
+static const struct f2fs_compress_ops *f2fs_cops[COMPRESS_MAX] = {
+#ifdef CONFIG_F2FS_FS_LZO
+ &f2fs_lzo_ops,
+#else
+ NULL,
+#endif
+#ifdef CONFIG_F2FS_FS_LZ4
+ &f2fs_lz4_ops,
+#else
+ NULL,
+#endif
+};
+
+bool f2fs_is_compress_backend_ready(struct inode *inode)
+{
+ if (!f2fs_compressed_file(inode))
+ return true;
+ return f2fs_cops[F2FS_I(inode)->i_compress_algorithm];
+}
+
+static struct page *f2fs_grab_page(void)
+{
+ struct page *page;
+
+ page = alloc_page(GFP_NOFS);
+ if (!page)
+ return NULL;
+ lock_page(page);
+ return page;
+}
+
+static int f2fs_compress_pages(struct compress_ctx *cc)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(cc->inode);
+ struct f2fs_inode_info *fi = F2FS_I(cc->inode);
+ const struct f2fs_compress_ops *cops =
+ f2fs_cops[fi->i_compress_algorithm];
+ unsigned int max_len, nr_cpages;
+ int i, ret;
+
+ trace_f2fs_compress_pages_start(cc->inode, cc->cluster_idx,
+ cc->cluster_size, fi->i_compress_algorithm);
+
+ ret = cops->init_compress_ctx(cc);
+ if (ret)
+ goto out;
+
+ max_len = COMPRESS_HEADER_SIZE + cc->clen;
+ cc->nr_cpages = DIV_ROUND_UP(max_len, PAGE_SIZE);
+
+ cc->cpages = f2fs_kzalloc(sbi, sizeof(struct page *) *
+ cc->nr_cpages, GFP_NOFS);
+ if (!cc->cpages) {
+ ret = -ENOMEM;
+ goto destroy_compress_ctx;
+ }
+
+ for (i = 0; i < cc->nr_cpages; i++) {
+ cc->cpages[i] = f2fs_grab_page();
+ if (!cc->cpages[i]) {
+ ret = -ENOMEM;
+ goto out_free_cpages;
+ }
+ }
+
+ cc->rbuf = vmap(cc->rpages, cc->cluster_size, VM_MAP, PAGE_KERNEL_RO);
+ if (!cc->rbuf) {
+ ret = -ENOMEM;
+ goto out_free_cpages;
+ }
+
+ cc->cbuf = vmap(cc->cpages, cc->nr_cpages, VM_MAP, PAGE_KERNEL);
+ if (!cc->cbuf) {
+ ret = -ENOMEM;
+ goto out_vunmap_rbuf;
+ }
+
+ ret = cops->compress_pages(cc);
+ if (ret)
+ goto out_vunmap_cbuf;
+
+ max_len = PAGE_SIZE * (cc->cluster_size - 1) - COMPRESS_HEADER_SIZE;
+
+ if (cc->clen > max_len) {
+ ret = -EAGAIN;
+ goto out_vunmap_cbuf;
+ }
+
+ cc->cbuf->clen = cpu_to_le32(cc->clen);
+ cc->cbuf->chksum = cpu_to_le32(0);
+
+ for (i = 0; i < COMPRESS_DATA_RESERVED_SIZE; i++)
+ cc->cbuf->reserved[i] = cpu_to_le32(0);
+
+ vunmap(cc->cbuf);
+ vunmap(cc->rbuf);
+
+ nr_cpages = DIV_ROUND_UP(cc->clen + COMPRESS_HEADER_SIZE, PAGE_SIZE);
+
+ for (i = nr_cpages; i < cc->nr_cpages; i++) {
+ f2fs_put_compressed_page(cc->cpages[i]);
+ cc->cpages[i] = NULL;
+ }
+
+ cc->nr_cpages = nr_cpages;
+
+ trace_f2fs_compress_pages_end(cc->inode, cc->cluster_idx,
+ cc->clen, ret);
+ return 0;
+
+out_vunmap_cbuf:
+ vunmap(cc->cbuf);
+out_vunmap_rbuf:
+ vunmap(cc->rbuf);
+out_free_cpages:
+ for (i = 0; i < cc->nr_cpages; i++) {
+ if (cc->cpages[i])
+ f2fs_put_compressed_page(cc->cpages[i]);
+ }
+ kfree(cc->cpages);
+ cc->cpages = NULL;
+destroy_compress_ctx:
+ cops->destroy_compress_ctx(cc);
+out:
+ trace_f2fs_compress_pages_end(cc->inode, cc->cluster_idx,
+ cc->clen, ret);
+ return ret;
+}
+
+void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity)
+{
+ struct decompress_io_ctx *dic =
+ (struct decompress_io_ctx *)page_private(page);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dic->inode);
+ struct f2fs_inode_info *fi= F2FS_I(dic->inode);
+ const struct f2fs_compress_ops *cops =
+ f2fs_cops[fi->i_compress_algorithm];
+ int ret;
+
+ dec_page_count(sbi, F2FS_RD_DATA);
+
+ if (bio->bi_status || PageError(page))
+ dic->failed = true;
+
+ if (refcount_dec_not_one(&dic->ref))
+ return;
+
+ trace_f2fs_decompress_pages_start(dic->inode, dic->cluster_idx,
+ dic->cluster_size, fi->i_compress_algorithm);
+
+ /* submit partial compressed pages */
+ if (dic->failed) {
+ ret = -EIO;
+ goto out_free_dic;
+ }
+
+ dic->rbuf = vmap(dic->tpages, dic->cluster_size, VM_MAP, PAGE_KERNEL);
+ if (!dic->rbuf) {
+ ret = -ENOMEM;
+ goto out_free_dic;
+ }
+
+ dic->cbuf = vmap(dic->cpages, dic->nr_cpages, VM_MAP, PAGE_KERNEL_RO);
+ if (!dic->cbuf) {
+ ret = -ENOMEM;
+ goto out_vunmap_rbuf;
+ }
+
+ dic->clen = le32_to_cpu(dic->cbuf->clen);
+ dic->rlen = PAGE_SIZE << dic->log_cluster_size;
+
+ if (dic->clen > PAGE_SIZE * dic->nr_cpages - COMPRESS_HEADER_SIZE) {
+ ret = -EFSCORRUPTED;
+ goto out_vunmap_cbuf;
+ }
+
+ ret = cops->decompress_pages(dic);
+
+out_vunmap_cbuf:
+ vunmap(dic->cbuf);
+out_vunmap_rbuf:
+ vunmap(dic->rbuf);
+out_free_dic:
+ if (!verity)
+ f2fs_decompress_end_io(dic->rpages, dic->cluster_size,
+ ret, false);
+
+ trace_f2fs_decompress_pages_end(dic->inode, dic->cluster_idx,
+ dic->clen, ret);
+ if (!verity)
+ f2fs_free_dic(dic);
+}
+
+static bool is_page_in_cluster(struct compress_ctx *cc, pgoff_t index)
+{
+ if (cc->cluster_idx == NULL_CLUSTER)
+ return true;
+ return cc->cluster_idx == cluster_idx(cc, index);
+}
+
+bool f2fs_cluster_is_empty(struct compress_ctx *cc)
+{
+ return cc->nr_rpages == 0;
+}
+
+static bool f2fs_cluster_is_full(struct compress_ctx *cc)
+{
+ return cc->cluster_size == cc->nr_rpages;
+}
+
+bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index)
+{
+ if (f2fs_cluster_is_empty(cc))
+ return true;
+ return is_page_in_cluster(cc, index);
+}
+
+static bool __cluster_may_compress(struct compress_ctx *cc)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(cc->inode);
+ loff_t i_size = i_size_read(cc->inode);
+ unsigned nr_pages = DIV_ROUND_UP(i_size, PAGE_SIZE);
+ int i;
+
+ for (i = 0; i < cc->cluster_size; i++) {
+ struct page *page = cc->rpages[i];
+
+ f2fs_bug_on(sbi, !page);
+
+ if (unlikely(f2fs_cp_error(sbi)))
+ return false;
+ if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+ return false;
+
+ /* beyond EOF */
+ if (page->index >= nr_pages)
+ return false;
+ }
+ return true;
+}
+
+/* return # of compressed block addresses */
+static int f2fs_compressed_blocks(struct compress_ctx *cc)
+{
+ struct dnode_of_data dn;
+ int ret;
+
+ set_new_dnode(&dn, cc->inode, NULL, NULL, 0);
+ ret = f2fs_get_dnode_of_data(&dn, start_idx_of_cluster(cc),
+ LOOKUP_NODE);
+ if (ret) {
+ if (ret == -ENOENT)
+ ret = 0;
+ goto fail;
+ }
+
+ if (dn.data_blkaddr == COMPRESS_ADDR) {
+ int i;
+
+ ret = 1;
+ for (i = 1; i < cc->cluster_size; i++) {
+ block_t blkaddr;
+
+ blkaddr = datablock_addr(dn.inode,
+ dn.node_page, dn.ofs_in_node + i);
+ if (blkaddr != NULL_ADDR)
+ ret++;
+ }
+ }
+fail:
+ f2fs_put_dnode(&dn);
+ return ret;
+}
+
+int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index)
+{
+ struct compress_ctx cc = {
+ .inode = inode,
+ .log_cluster_size = F2FS_I(inode)->i_log_cluster_size,
+ .cluster_size = F2FS_I(inode)->i_cluster_size,
+ .cluster_idx = index >> F2FS_I(inode)->i_log_cluster_size,
+ };
+
+ return f2fs_compressed_blocks(&cc);
+}
+
+static bool cluster_may_compress(struct compress_ctx *cc)
+{
+ if (!f2fs_compressed_file(cc->inode))
+ return false;
+ if (f2fs_is_atomic_file(cc->inode))
+ return false;
+ if (f2fs_is_mmap_file(cc->inode))
+ return false;
+ if (!f2fs_cluster_is_full(cc))
+ return false;
+ return __cluster_may_compress(cc);
+}
+
+static void set_cluster_writeback(struct compress_ctx *cc)
+{
+ int i;
+
+ for (i = 0; i < cc->cluster_size; i++) {
+ if (cc->rpages[i])
+ set_page_writeback(cc->rpages[i]);
+ }
+}
+
+static void set_cluster_dirty(struct compress_ctx *cc)
+{
+ int i;
+
+ for (i = 0; i < cc->cluster_size; i++)
+ if (cc->rpages[i])
+ set_page_dirty(cc->rpages[i]);
+}
+
+static int prepare_compress_overwrite(struct compress_ctx *cc,
+ struct page **pagep, pgoff_t index, void **fsdata)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(cc->inode);
+ struct address_space *mapping = cc->inode->i_mapping;
+ struct page *page;
+ struct dnode_of_data dn;
+ sector_t last_block_in_bio;
+ unsigned fgp_flag = FGP_LOCK | FGP_WRITE | FGP_CREAT;
+ pgoff_t start_idx = start_idx_of_cluster(cc);
+ int i, ret;
+ bool prealloc;
+
+retry:
+ ret = f2fs_compressed_blocks(cc);
+ if (ret <= 0)
+ return ret;
+
+ /* compressed case */
+ prealloc = (ret < cc->cluster_size);
+
+ ret = f2fs_init_compress_ctx(cc);
+ if (ret)
+ return ret;
+
+ /* keep page reference to avoid page reclaim */
+ for (i = 0; i < cc->cluster_size; i++) {
+ page = f2fs_pagecache_get_page(mapping, start_idx + i,
+ fgp_flag, GFP_NOFS);
+ if (!page) {
+ ret = -ENOMEM;
+ goto unlock_pages;
+ }
+
+ if (PageUptodate(page))
+ unlock_page(page);
+ else
+ f2fs_compress_ctx_add_page(cc, page);
+ }
+
+ if (!f2fs_cluster_is_empty(cc)) {
+ struct bio *bio = NULL;
+
+ ret = f2fs_read_multi_pages(cc, &bio, cc->cluster_size,
+ &last_block_in_bio, false);
+ f2fs_destroy_compress_ctx(cc);
+ if (ret)
+ goto release_pages;
+ if (bio)
+ f2fs_submit_bio(sbi, bio, DATA);
+
+ ret = f2fs_init_compress_ctx(cc);
+ if (ret)
+ goto release_pages;
+ }
+
+ for (i = 0; i < cc->cluster_size; i++) {
+ f2fs_bug_on(sbi, cc->rpages[i]);
+
+ page = find_lock_page(mapping, start_idx + i);
+ f2fs_bug_on(sbi, !page);
+
+ f2fs_wait_on_page_writeback(page, DATA, true, true);
+
+ f2fs_compress_ctx_add_page(cc, page);
+ f2fs_put_page(page, 0);
+
+ if (!PageUptodate(page)) {
+ f2fs_unlock_rpages(cc, i + 1);
+ f2fs_put_rpages_mapping(cc, mapping, start_idx,
+ cc->cluster_size);
+ f2fs_destroy_compress_ctx(cc);
+ goto retry;
+ }
+ }
+
+ if (prealloc) {
+ __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true);
+
+ set_new_dnode(&dn, cc->inode, NULL, NULL, 0);
+
+ for (i = cc->cluster_size - 1; i > 0; i--) {
+ ret = f2fs_get_block(&dn, start_idx + i);
+ if (ret) {
+ i = cc->cluster_size;
+ break;
+ }
+
+ if (dn.data_blkaddr != NEW_ADDR)
+ break;
+ }
+
+ __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false);
+ }
+
+ if (likely(!ret)) {
+ *fsdata = cc->rpages;
+ *pagep = cc->rpages[offset_in_cluster(cc, index)];
+ return cc->cluster_size;
+ }
+
+unlock_pages:
+ f2fs_unlock_rpages(cc, i);
+release_pages:
+ f2fs_put_rpages_mapping(cc, mapping, start_idx, i);
+ f2fs_destroy_compress_ctx(cc);
+ return ret;
+}
+
+int f2fs_prepare_compress_overwrite(struct inode *inode,
+ struct page **pagep, pgoff_t index, void **fsdata)
+{
+ struct compress_ctx cc = {
+ .inode = inode,
+ .log_cluster_size = F2FS_I(inode)->i_log_cluster_size,
+ .cluster_size = F2FS_I(inode)->i_cluster_size,
+ .cluster_idx = index >> F2FS_I(inode)->i_log_cluster_size,
+ .rpages = NULL,
+ .nr_rpages = 0,
+ };
+
+ return prepare_compress_overwrite(&cc, pagep, index, fsdata);
+}
+
+bool f2fs_compress_write_end(struct inode *inode, void *fsdata,
+ pgoff_t index, unsigned copied)
+
+{
+ struct compress_ctx cc = {
+ .log_cluster_size = F2FS_I(inode)->i_log_cluster_size,
+ .cluster_size = F2FS_I(inode)->i_cluster_size,
+ .rpages = fsdata,
+ };
+ bool first_index = (index == cc.rpages[0]->index);
+
+ if (copied)
+ set_cluster_dirty(&cc);
+
+ f2fs_put_rpages_wbc(&cc, NULL, false, 1);
+ f2fs_destroy_compress_ctx(&cc);
+
+ return first_index;
+}
+
+static int f2fs_write_compressed_pages(struct compress_ctx *cc,
+ int *submitted,
+ struct writeback_control *wbc,
+ enum iostat_type io_type)
+{
+ struct inode *inode = cc->inode;
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ struct f2fs_io_info fio = {
+ .sbi = sbi,
+ .ino = cc->inode->i_ino,
+ .type = DATA,
+ .op = REQ_OP_WRITE,
+ .op_flags = wbc_to_write_flags(wbc),
+ .old_blkaddr = NEW_ADDR,
+ .page = NULL,
+ .encrypted_page = NULL,
+ .compressed_page = NULL,
+ .submitted = false,
+ .need_lock = LOCK_RETRY,
+ .io_type = io_type,
+ .io_wbc = wbc,
+ .encrypted = f2fs_encrypted_file(cc->inode),
+ };
+ struct dnode_of_data dn;
+ struct node_info ni;
+ struct compress_io_ctx *cic;
+ pgoff_t start_idx = start_idx_of_cluster(cc);
+ unsigned int last_index = cc->cluster_size - 1;
+ loff_t psize;
+ int i, err;
+
+ set_new_dnode(&dn, cc->inode, NULL, NULL, 0);
+
+ f2fs_lock_op(sbi);
+
+ err = f2fs_get_dnode_of_data(&dn, start_idx, LOOKUP_NODE);
+ if (err)
+ goto out_unlock_op;
+
+ for (i = 0; i < cc->cluster_size; i++) {
+ if (datablock_addr(dn.inode, dn.node_page,
+ dn.ofs_in_node + i) == NULL_ADDR)
+ goto out_put_dnode;
+ }
+
+ psize = (loff_t)(cc->rpages[last_index]->index + 1) << PAGE_SHIFT;
+
+ err = f2fs_get_node_info(fio.sbi, dn.nid, &ni);
+ if (err)
+ goto out_put_dnode;
+
+ fio.version = ni.version;
+
+ cic = f2fs_kzalloc(sbi, sizeof(struct compress_io_ctx), GFP_NOFS);
+ if (!cic)
+ goto out_put_dnode;
+
+ cic->magic = F2FS_COMPRESSED_PAGE_MAGIC;
+ cic->inode = inode;
+ refcount_set(&cic->ref, 1);
+ cic->rpages = f2fs_kzalloc(sbi, sizeof(struct page *) <<
+ cc->log_cluster_size, GFP_NOFS);
+ if (!cic->rpages)
+ goto out_put_cic;
+
+ cic->nr_rpages = cc->cluster_size;
+
+ for (i = 0; i < cc->nr_cpages; i++) {
+ f2fs_set_compressed_page(cc->cpages[i], inode,
+ cc->rpages[i + 1]->index,
+ cic, i ? &cic->ref : NULL);
+ fio.compressed_page = cc->cpages[i];
+ if (fio.encrypted) {
+ fio.page = cc->rpages[i + 1];
+ err = f2fs_encrypt_one_page(&fio);
+ if (err)
+ goto out_destroy_crypt;
+ cc->cpages[i] = fio.encrypted_page;
+ }
+ }
+
+ set_cluster_writeback(cc);
+
+ for (i = 0; i < cc->cluster_size; i++)
+ cic->rpages[i] = cc->rpages[i];
+
+ for (i = 0; i < cc->cluster_size; i++, dn.ofs_in_node++) {
+ block_t blkaddr;
+
+ blkaddr = datablock_addr(dn.inode, dn.node_page,
+ dn.ofs_in_node);
+ fio.page = cic->rpages[i];
+ fio.old_blkaddr = blkaddr;
+
+ /* cluster header */
+ if (i == 0) {
+ if (blkaddr == COMPRESS_ADDR)
+ fio.compr_blocks++;
+ if (__is_valid_data_blkaddr(blkaddr))
+ f2fs_invalidate_blocks(sbi, blkaddr);
+ f2fs_update_data_blkaddr(&dn, COMPRESS_ADDR);
+ goto unlock_continue;
+ }
+
+ if (fio.compr_blocks && __is_valid_data_blkaddr(blkaddr))
+ fio.compr_blocks++;
+
+ if (i > cc->nr_cpages) {
+ if (__is_valid_data_blkaddr(blkaddr)) {
+ f2fs_invalidate_blocks(sbi, blkaddr);
+ f2fs_update_data_blkaddr(&dn, NEW_ADDR);
+ }
+ goto unlock_continue;
+ }
+
+ f2fs_bug_on(fio.sbi, blkaddr == NULL_ADDR);
+
+ if (fio.encrypted)
+ fio.encrypted_page = cc->cpages[i - 1];
+ else
+ fio.compressed_page = cc->cpages[i - 1];
+
+ cc->cpages[i - 1] = NULL;
+ f2fs_outplace_write_data(&dn, &fio);
+ (*submitted)++;
+unlock_continue:
+ inode_dec_dirty_pages(cc->inode);
+ unlock_page(fio.page);
+ }
+
+ if (fio.compr_blocks)
+ f2fs_i_compr_blocks_update(inode, fio.compr_blocks - 1, false);
+ f2fs_i_compr_blocks_update(inode, cc->nr_cpages, true);
+
+ set_inode_flag(cc->inode, FI_APPEND_WRITE);
+ if (cc->cluster_idx == 0)
+ set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
+
+ f2fs_put_dnode(&dn);
+ f2fs_unlock_op(sbi);
+
+ down_write(&fi->i_sem);
+ if (fi->last_disk_size < psize)
+ fi->last_disk_size = psize;
+ up_write(&fi->i_sem);
+
+ f2fs_put_rpages(cc);
+ f2fs_destroy_compress_ctx(cc);
+ return 0;
+
+out_destroy_crypt:
+ kfree(cic->rpages);
+
+ for (--i; i >= 0; i--)
+ fscrypt_finalize_bounce_page(&cc->cpages[i]);
+ for (i = 0; i < cc->nr_cpages; i++) {
+ if (!cc->cpages[i])
+ continue;
+ f2fs_put_page(cc->cpages[i], 1);
+ }
+out_put_cic:
+ kfree(cic);
+out_put_dnode:
+ f2fs_put_dnode(&dn);
+out_unlock_op:
+ f2fs_unlock_op(sbi);
+ return -EAGAIN;
+}
+
+void f2fs_compress_write_end_io(struct bio *bio, struct page *page)
+{
+ struct f2fs_sb_info *sbi = bio->bi_private;
+ struct compress_io_ctx *cic =
+ (struct compress_io_ctx *)page_private(page);
+ int i;
+
+ if (unlikely(bio->bi_status))
+ mapping_set_error(cic->inode->i_mapping, -EIO);
+
+ f2fs_put_compressed_page(page);
+
+ dec_page_count(sbi, F2FS_WB_DATA);
+
+ if (refcount_dec_not_one(&cic->ref))
+ return;
+
+ for (i = 0; i < cic->nr_rpages; i++) {
+ WARN_ON(!cic->rpages[i]);
+ clear_cold_data(cic->rpages[i]);
+ end_page_writeback(cic->rpages[i]);
+ }
+
+ kfree(cic->rpages);
+ kfree(cic);
+}
+
+static int f2fs_write_raw_pages(struct compress_ctx *cc,
+ int *submitted,
+ struct writeback_control *wbc,
+ enum iostat_type io_type)
+{
+ struct address_space *mapping = cc->inode->i_mapping;
+ int _submitted, compr_blocks, ret;
+ int i = -1, err = 0;
+
+ compr_blocks = f2fs_compressed_blocks(cc);
+ if (compr_blocks < 0) {
+ err = compr_blocks;
+ goto out_err;
+ }
+
+ for (i = 0; i < cc->cluster_size; i++) {
+ if (!cc->rpages[i])
+ continue;
+retry_write:
+ if (cc->rpages[i]->mapping != mapping) {
+ unlock_page(cc->rpages[i]);
+ continue;
+ }
+
+ BUG_ON(!PageLocked(cc->rpages[i]));
+
+ ret = f2fs_write_single_data_page(cc->rpages[i], &_submitted,
+ NULL, NULL, wbc, io_type,
+ compr_blocks);
+ if (ret) {
+ if (ret == AOP_WRITEPAGE_ACTIVATE) {
+ unlock_page(cc->rpages[i]);
+ ret = 0;
+ } else if (ret == -EAGAIN) {
+ ret = 0;
+ cond_resched();
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ lock_page(cc->rpages[i]);
+ clear_page_dirty_for_io(cc->rpages[i]);
+ goto retry_write;
+ }
+ err = ret;
+ goto out_fail;
+ }
+
+ *submitted += _submitted;
+ }
+ return 0;
+
+out_fail:
+ /* TODO: revoke partially updated block addresses */
+ BUG_ON(compr_blocks);
+out_err:
+ for (++i; i < cc->cluster_size; i++) {
+ if (!cc->rpages[i])
+ continue;
+ redirty_page_for_writepage(wbc, cc->rpages[i]);
+ unlock_page(cc->rpages[i]);
+ }
+ return err;
+}
+
+int f2fs_write_multi_pages(struct compress_ctx *cc,
+ int *submitted,
+ struct writeback_control *wbc,
+ enum iostat_type io_type)
+{
+ struct f2fs_inode_info *fi = F2FS_I(cc->inode);
+ const struct f2fs_compress_ops *cops =
+ f2fs_cops[fi->i_compress_algorithm];
+ int err;
+
+ *submitted = 0;
+ if (cluster_may_compress(cc)) {
+ err = f2fs_compress_pages(cc);
+ if (err == -EAGAIN) {
+ goto write;
+ } else if (err) {
+ f2fs_put_rpages_wbc(cc, wbc, true, 1);
+ goto destroy_out;
+ }
+
+ err = f2fs_write_compressed_pages(cc, submitted,
+ wbc, io_type);
+ cops->destroy_compress_ctx(cc);
+ if (!err)
+ return 0;
+ f2fs_bug_on(F2FS_I_SB(cc->inode), err != -EAGAIN);
+ }
+write:
+ f2fs_bug_on(F2FS_I_SB(cc->inode), *submitted);
+
+ err = f2fs_write_raw_pages(cc, submitted, wbc, io_type);
+ f2fs_put_rpages_wbc(cc, wbc, false, 0);
+destroy_out:
+ f2fs_destroy_compress_ctx(cc);
+ return err;
+}
+
+struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(cc->inode);
+ struct decompress_io_ctx *dic;
+ pgoff_t start_idx = start_idx_of_cluster(cc);
+ int i;
+
+ dic = f2fs_kzalloc(sbi, sizeof(struct decompress_io_ctx), GFP_NOFS);
+ if (!dic)
+ return ERR_PTR(-ENOMEM);
+
+ dic->rpages = f2fs_kzalloc(sbi, sizeof(struct page *) <<
+ cc->log_cluster_size, GFP_NOFS);
+ if (!dic->rpages) {
+ kfree(dic);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ dic->magic = F2FS_COMPRESSED_PAGE_MAGIC;
+ dic->inode = cc->inode;
+ refcount_set(&dic->ref, 1);
+ dic->cluster_idx = cc->cluster_idx;
+ dic->cluster_size = cc->cluster_size;
+ dic->log_cluster_size = cc->log_cluster_size;
+ dic->nr_cpages = cc->nr_cpages;
+ dic->failed = false;
+
+ for (i = 0; i < dic->cluster_size; i++)
+ dic->rpages[i] = cc->rpages[i];
+ dic->nr_rpages = cc->cluster_size;
+
+ dic->cpages = f2fs_kzalloc(sbi, sizeof(struct page *) *
+ dic->nr_cpages, GFP_NOFS);
+ if (!dic->cpages)
+ goto out_free;
+
+ for (i = 0; i < dic->nr_cpages; i++) {
+ struct page *page;
+
+ page = f2fs_grab_page();
+ if (!page)
+ goto out_free;
+
+ f2fs_set_compressed_page(page, cc->inode,
+ start_idx + i + 1,
+ dic, i ? &dic->ref : NULL);
+ dic->cpages[i] = page;
+ }
+
+ dic->tpages = f2fs_kzalloc(sbi, sizeof(struct page *) *
+ dic->cluster_size, GFP_NOFS);
+ if (!dic->tpages)
+ goto out_free;
+
+ for (i = 0; i < dic->cluster_size; i++) {
+ if (cc->rpages[i])
+ continue;
+
+ dic->tpages[i] = f2fs_grab_page();
+ if (!dic->tpages[i])
+ goto out_free;
+ }
+
+ for (i = 0; i < dic->cluster_size; i++) {
+ if (dic->tpages[i])
+ continue;
+ dic->tpages[i] = cc->rpages[i];
+ }
+
+ return dic;
+
+out_free:
+ f2fs_free_dic(dic);
+ return ERR_PTR(-ENOMEM);
+}
+
+void f2fs_free_dic(struct decompress_io_ctx *dic)
+{
+ int i;
+
+ if (dic->tpages) {
+ for (i = 0; i < dic->cluster_size; i++) {
+ if (dic->rpages[i])
+ continue;
+ f2fs_put_page(dic->tpages[i], 1);
+ }
+ kfree(dic->tpages);
+ }
+
+ if (dic->cpages) {
+ for (i = 0; i < dic->nr_cpages; i++) {
+ if (!dic->cpages[i])
+ continue;
+ f2fs_put_compressed_page(dic->cpages[i]);
+ }
+ kfree(dic->cpages);
+ }
+
+ kfree(dic->rpages);
+ kfree(dic);
+}
+
+void f2fs_decompress_end_io(struct page **rpages,
+ unsigned int cluster_size, bool err, bool verity)
+{
+ int i;
+
+ for (i = 0; i < cluster_size; i++) {
+ struct page *rpage = rpages[i];
+
+ if (!rpage)
+ continue;
+
+ if (err || PageError(rpage)) {
+ ClearPageUptodate(rpage);
+ ClearPageError(rpage);
+ } else {
+ if (!verity || fsverity_verify_page(rpage))
+ SetPageUptodate(rpage);
+ else
+ SetPageError(rpage);
+ }
+ unlock_page(rpage);
+ }
+}
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 0fa356e94ef5..8bd9afa81c54 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -31,6 +31,47 @@
static struct kmem_cache *bio_post_read_ctx_cache;
static struct kmem_cache *bio_entry_slab;
static mempool_t *bio_post_read_ctx_pool;
+static struct bio_set f2fs_bioset;
+
+#define F2FS_BIO_POOL_SIZE NR_CURSEG_TYPE
+
+int __init f2fs_init_bioset(void)
+{
+ if (bioset_init(&f2fs_bioset, F2FS_BIO_POOL_SIZE,
+ 0, BIOSET_NEED_BVECS))
+ return -ENOMEM;
+ return 0;
+}
+
+void f2fs_destroy_bioset(void)
+{
+ bioset_exit(&f2fs_bioset);
+}
+
+static inline struct bio *__f2fs_bio_alloc(gfp_t gfp_mask,
+ unsigned int nr_iovecs)
+{
+ return bio_alloc_bioset(gfp_mask, nr_iovecs, &f2fs_bioset);
+}
+
+struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages, bool no_fail)
+{
+ struct bio *bio;
+
+ if (no_fail) {
+ /* No failure on bio allocation */
+ bio = __f2fs_bio_alloc(GFP_NOIO, npages);
+ if (!bio)
+ bio = __f2fs_bio_alloc(GFP_NOIO | __GFP_NOFAIL, npages);
+ return bio;
+ }
+ if (time_to_inject(sbi, FAULT_ALLOC_BIO)) {
+ f2fs_show_injection_info(sbi, FAULT_ALLOC_BIO);
+ return NULL;
+ }
+
+ return __f2fs_bio_alloc(GFP_KERNEL, npages);
+}
static bool __is_cp_guaranteed(struct page *page)
{
@@ -41,6 +82,9 @@ static bool __is_cp_guaranteed(struct page *page)
if (!mapping)
return false;
+ if (f2fs_is_compressed_page(page))
+ return false;
+
inode = mapping->host;
sbi = F2FS_I_SB(inode);
@@ -73,19 +117,19 @@ static enum count_type __read_io_type(struct page *page)
/* postprocessing steps for read bios */
enum bio_post_read_step {
- STEP_INITIAL = 0,
STEP_DECRYPT,
+ STEP_DECOMPRESS,
STEP_VERITY,
};
struct bio_post_read_ctx {
struct bio *bio;
+ struct f2fs_sb_info *sbi;
struct work_struct work;
- unsigned int cur_step;
unsigned int enabled_steps;
};
-static void __read_end_io(struct bio *bio)
+static void __read_end_io(struct bio *bio, bool compr, bool verity)
{
struct page *page;
struct bio_vec *bv;
@@ -94,6 +138,13 @@ static void __read_end_io(struct bio *bio)
bio_for_each_segment_all(bv, bio, iter_all) {
page = bv->bv_page;
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+ if (compr && f2fs_is_compressed_page(page)) {
+ f2fs_decompress_pages(bio, page, verity);
+ continue;
+ }
+#endif
+
/* PG_error was set if any post_read step failed */
if (bio->bi_status || PageError(page)) {
ClearPageUptodate(page);
@@ -105,31 +156,107 @@ static void __read_end_io(struct bio *bio)
dec_page_count(F2FS_P_SB(page), __read_io_type(page));
unlock_page(page);
}
- if (bio->bi_private)
- mempool_free(bio->bi_private, bio_post_read_ctx_pool);
- bio_put(bio);
+}
+
+static void f2fs_release_read_bio(struct bio *bio);
+static void __f2fs_read_end_io(struct bio *bio, bool compr, bool verity)
+{
+ if (!compr)
+ __read_end_io(bio, false, verity);
+ f2fs_release_read_bio(bio);
+}
+
+static void f2fs_decompress_bio(struct bio *bio, bool verity)
+{
+ __read_end_io(bio, true, verity);
}
static void bio_post_read_processing(struct bio_post_read_ctx *ctx);
-static void decrypt_work(struct work_struct *work)
+static void f2fs_decrypt_work(struct bio_post_read_ctx *ctx)
+{
+ fscrypt_decrypt_bio(ctx->bio);
+}
+
+static void f2fs_decompress_work(struct bio_post_read_ctx *ctx)
+{
+ f2fs_decompress_bio(ctx->bio, ctx->enabled_steps & (1 << STEP_VERITY));
+}
+
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+static void f2fs_verify_pages(struct page **rpages, unsigned int cluster_size)
+{
+ f2fs_decompress_end_io(rpages, cluster_size, false, true);
+}
+
+static void f2fs_verify_bio(struct bio *bio)
+{
+ struct page *page = bio_first_page_all(bio);
+ struct decompress_io_ctx *dic =
+ (struct decompress_io_ctx *)page_private(page);
+
+ f2fs_verify_pages(dic->rpages, dic->cluster_size);
+ f2fs_free_dic(dic);
+}
+#endif
+
+static void f2fs_verity_work(struct work_struct *work)
{
struct bio_post_read_ctx *ctx =
container_of(work, struct bio_post_read_ctx, work);
+ struct bio *bio = ctx->bio;
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+ unsigned int enabled_steps = ctx->enabled_steps;
+#endif
- fscrypt_decrypt_bio(ctx->bio);
+ /*
+ * fsverity_verify_bio() may call readpages() again, and while verity
+ * will be disabled for this, decryption may still be needed, resulting
+ * in another bio_post_read_ctx being allocated. So to prevent
+ * deadlocks we need to release the current ctx to the mempool first.
+ * This assumes that verity is the last post-read step.
+ */
+ mempool_free(ctx, bio_post_read_ctx_pool);
+ bio->bi_private = NULL;
+
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+ /* previous step is decompression */
+ if (enabled_steps & (1 << STEP_DECOMPRESS)) {
+ f2fs_verify_bio(bio);
+ f2fs_release_read_bio(bio);
+ return;
+ }
+#endif
- bio_post_read_processing(ctx);
+ fsverity_verify_bio(bio);
+ __f2fs_read_end_io(bio, false, false);
}
-static void verity_work(struct work_struct *work)
+static void f2fs_post_read_work(struct work_struct *work)
{
struct bio_post_read_ctx *ctx =
container_of(work, struct bio_post_read_ctx, work);
- fsverity_verify_bio(ctx->bio);
+ if (ctx->enabled_steps & (1 << STEP_DECRYPT))
+ f2fs_decrypt_work(ctx);
- bio_post_read_processing(ctx);
+ if (ctx->enabled_steps & (1 << STEP_DECOMPRESS))
+ f2fs_decompress_work(ctx);
+
+ if (ctx->enabled_steps & (1 << STEP_VERITY)) {
+ INIT_WORK(&ctx->work, f2fs_verity_work);
+ fsverity_enqueue_verify_work(&ctx->work);
+ return;
+ }
+
+ __f2fs_read_end_io(ctx->bio,
+ ctx->enabled_steps & (1 << STEP_DECOMPRESS), false);
+}
+
+static void f2fs_enqueue_post_read_work(struct f2fs_sb_info *sbi,
+ struct work_struct *work)
+{
+ queue_work(sbi->post_read_wq, work);
}
static void bio_post_read_processing(struct bio_post_read_ctx *ctx)
@@ -139,31 +266,26 @@ static void bio_post_read_processing(struct bio_post_read_ctx *ctx)
* verity may require reading metadata pages that need decryption, and
* we shouldn't recurse to the same workqueue.
*/
- switch (++ctx->cur_step) {
- case STEP_DECRYPT:
- if (ctx->enabled_steps & (1 << STEP_DECRYPT)) {
- INIT_WORK(&ctx->work, decrypt_work);
- fscrypt_enqueue_decrypt_work(&ctx->work);
- return;
- }
- ctx->cur_step++;
- /* fall-through */
- case STEP_VERITY:
- if (ctx->enabled_steps & (1 << STEP_VERITY)) {
- INIT_WORK(&ctx->work, verity_work);
- fsverity_enqueue_verify_work(&ctx->work);
- return;
- }
- ctx->cur_step++;
- /* fall-through */
- default:
- __read_end_io(ctx->bio);
+
+ if (ctx->enabled_steps & (1 << STEP_DECRYPT) ||
+ ctx->enabled_steps & (1 << STEP_DECOMPRESS)) {
+ INIT_WORK(&ctx->work, f2fs_post_read_work);
+ f2fs_enqueue_post_read_work(ctx->sbi, &ctx->work);
+ return;
}
+
+ if (ctx->enabled_steps & (1 << STEP_VERITY)) {
+ INIT_WORK(&ctx->work, f2fs_verity_work);
+ fsverity_enqueue_verify_work(&ctx->work);
+ return;
+ }
+
+ __f2fs_read_end_io(ctx->bio, false, false);
}
static bool f2fs_bio_post_read_required(struct bio *bio)
{
- return bio->bi_private && !bio->bi_status;
+ return bio->bi_private;
}
static void f2fs_read_end_io(struct bio *bio)
@@ -178,12 +300,11 @@ static void f2fs_read_end_io(struct bio *bio)
if (f2fs_bio_post_read_required(bio)) {
struct bio_post_read_ctx *ctx = bio->bi_private;
- ctx->cur_step = STEP_INITIAL;
bio_post_read_processing(ctx);
return;
}
- __read_end_io(bio);
+ __f2fs_read_end_io(bio, false, false);
}
static void f2fs_write_end_io(struct bio *bio)
@@ -214,6 +335,13 @@ static void f2fs_write_end_io(struct bio *bio)
fscrypt_finalize_bounce_page(&page);
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+ if (f2fs_is_compressed_page(page)) {
+ f2fs_compress_write_end_io(bio, page);
+ continue;
+ }
+#endif
+
if (unlikely(bio->bi_status)) {
mapping_set_error(page->mapping, -EIO);
if (type == F2FS_WB_CP_DATA)
@@ -358,6 +486,12 @@ submit_io:
submit_bio(bio);
}
+void f2fs_submit_bio(struct f2fs_sb_info *sbi,
+ struct bio *bio, enum page_type type)
+{
+ __submit_bio(sbi, bio, type);
+}
+
static void __submit_merged_bio(struct f2fs_bio_info *io)
{
struct f2fs_io_info *fio = &io->fio;
@@ -380,7 +514,6 @@ static bool __has_merged_page(struct bio *bio, struct inode *inode,
struct page *page, nid_t ino)
{
struct bio_vec *bvec;
- struct page *target;
struct bvec_iter_all iter_all;
if (!bio)
@@ -390,10 +523,18 @@ static bool __has_merged_page(struct bio *bio, struct inode *inode,
return true;
bio_for_each_segment_all(bvec, bio, iter_all) {
+ struct page *target = bvec->bv_page;
- target = bvec->bv_page;
- if (fscrypt_is_bounce_page(target))
+ if (fscrypt_is_bounce_page(target)) {
target = fscrypt_pagecache_page(target);
+ if (IS_ERR(target))
+ continue;
+ }
+ if (f2fs_is_compressed_page(target)) {
+ target = f2fs_compress_control_page(target);
+ if (IS_ERR(target))
+ continue;
+ }
if (inode && inode == target->mapping->host)
return true;
@@ -588,7 +729,8 @@ static int add_ipu_page(struct f2fs_sb_info *sbi, struct bio **bio,
found = true;
- if (bio_add_page(*bio, page, PAGE_SIZE, 0) == PAGE_SIZE) {
+ if (bio_add_page(*bio, page, PAGE_SIZE, 0) ==
+ PAGE_SIZE) {
ret = 0;
break;
}
@@ -728,7 +870,12 @@ next:
verify_fio_blkaddr(fio);
- bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page;
+ if (fio->encrypted_page)
+ bio_page = fio->encrypted_page;
+ else if (fio->compressed_page)
+ bio_page = fio->compressed_page;
+ else
+ bio_page = fio->page;
/* set submitted = true as a return value */
fio->submitted = true;
@@ -797,17 +944,16 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
if (f2fs_encrypted_file(inode))
post_read_steps |= 1 << STEP_DECRYPT;
-
+ if (f2fs_compressed_file(inode))
+ post_read_steps |= 1 << STEP_DECOMPRESS;
if (f2fs_need_verity(inode, first_idx))
post_read_steps |= 1 << STEP_VERITY;
if (post_read_steps) {
+ /* Due to the mempool, this never fails. */
ctx = mempool_alloc(bio_post_read_ctx_pool, GFP_NOFS);
- if (!ctx) {
- bio_put(bio);
- return ERR_PTR(-ENOMEM);
- }
ctx->bio = bio;
+ ctx->sbi = sbi;
ctx->enabled_steps = post_read_steps;
bio->bi_private = ctx;
}
@@ -815,6 +961,13 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
return bio;
}
+static void f2fs_release_read_bio(struct bio *bio)
+{
+ if (bio->bi_private)
+ mempool_free(bio->bi_private, bio_post_read_ctx_pool);
+ bio_put(bio);
+}
+
/* This can handle encryption stuffs */
static int f2fs_submit_page_read(struct inode *inode, struct page *page,
block_t blkaddr)
@@ -1180,19 +1333,6 @@ int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
int err = 0;
bool direct_io = iocb->ki_flags & IOCB_DIRECT;
- /* convert inline data for Direct I/O*/
- if (direct_io) {
- err = f2fs_convert_inline_inode(inode);
- if (err)
- return err;
- }
-
- if (direct_io && allow_outplace_dio(inode, iocb, from))
- return 0;
-
- if (is_inode_flag_set(inode, FI_NO_PREALLOC))
- return 0;
-
map.m_lblk = F2FS_BLK_ALIGN(iocb->ki_pos);
map.m_len = F2FS_BYTES_TO_BLK(iocb->ki_pos + iov_iter_count(from));
if (map.m_len > map.m_lblk)
@@ -1872,6 +2012,144 @@ out:
return ret;
}
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
+ unsigned nr_pages, sector_t *last_block_in_bio,
+ bool is_readahead)
+{
+ struct dnode_of_data dn;
+ struct inode *inode = cc->inode;
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct bio *bio = *bio_ret;
+ unsigned int start_idx = cc->cluster_idx << cc->log_cluster_size;
+ sector_t last_block_in_file;
+ const unsigned blkbits = inode->i_blkbits;
+ const unsigned blocksize = 1 << blkbits;
+ struct decompress_io_ctx *dic = NULL;
+ int i;
+ int ret = 0;
+
+ f2fs_bug_on(sbi, f2fs_cluster_is_empty(cc));
+
+ last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits;
+
+ /* get rid of pages beyond EOF */
+ for (i = 0; i < cc->cluster_size; i++) {
+ struct page *page = cc->rpages[i];
+
+ if (!page)
+ continue;
+ if ((sector_t)page->index >= last_block_in_file) {
+ zero_user_segment(page, 0, PAGE_SIZE);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
+ } else if (!PageUptodate(page)) {
+ continue;
+ }
+ unlock_page(page);
+ cc->rpages[i] = NULL;
+ cc->nr_rpages--;
+ }
+
+ /* we are done since all pages are beyond EOF */
+ if (f2fs_cluster_is_empty(cc))
+ goto out;
+
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ ret = f2fs_get_dnode_of_data(&dn, start_idx, LOOKUP_NODE);
+ if (ret)
+ goto out;
+
+ /* cluster was overwritten as normal cluster */
+ if (dn.data_blkaddr != COMPRESS_ADDR)
+ goto out;
+
+ for (i = 1; i < cc->cluster_size; i++) {
+ block_t blkaddr;
+
+ blkaddr = datablock_addr(dn.inode, dn.node_page,
+ dn.ofs_in_node + i);
+
+ if (!__is_valid_data_blkaddr(blkaddr))
+ break;
+
+ if (!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC)) {
+ ret = -EFAULT;
+ goto out_put_dnode;
+ }
+ cc->nr_cpages++;
+ }
+
+ /* nothing to decompress */
+ if (cc->nr_cpages == 0) {
+ ret = 0;
+ goto out_put_dnode;
+ }
+
+ dic = f2fs_alloc_dic(cc);
+ if (IS_ERR(dic)) {
+ ret = PTR_ERR(dic);
+ goto out_put_dnode;
+ }
+
+ for (i = 0; i < dic->nr_cpages; i++) {
+ struct page *page = dic->cpages[i];
+ block_t blkaddr;
+
+ blkaddr = datablock_addr(dn.inode, dn.node_page,
+ dn.ofs_in_node + i + 1);
+
+ if (bio && !page_is_mergeable(sbi, bio,
+ *last_block_in_bio, blkaddr)) {
+submit_and_realloc:
+ __submit_bio(sbi, bio, DATA);
+ bio = NULL;
+ }
+
+ if (!bio) {
+ bio = f2fs_grab_read_bio(inode, blkaddr, nr_pages,
+ is_readahead ? REQ_RAHEAD : 0,
+ page->index);
+ if (IS_ERR(bio)) {
+ ret = PTR_ERR(bio);
+ bio = NULL;
+ dic->failed = true;
+ if (refcount_sub_and_test(dic->nr_cpages - i,
+ &dic->ref))
+ f2fs_decompress_end_io(dic->rpages,
+ cc->cluster_size, true,
+ false);
+ f2fs_free_dic(dic);
+ f2fs_put_dnode(&dn);
+ *bio_ret = bio;
+ return ret;
+ }
+ }
+
+ f2fs_wait_on_block_writeback(inode, blkaddr);
+
+ if (bio_add_page(bio, page, blocksize, 0) < blocksize)
+ goto submit_and_realloc;
+
+ inc_page_count(sbi, F2FS_RD_DATA);
+ ClearPageError(page);
+ *last_block_in_bio = blkaddr;
+ }
+
+ f2fs_put_dnode(&dn);
+
+ *bio_ret = bio;
+ return 0;
+
+out_put_dnode:
+ f2fs_put_dnode(&dn);
+out:
+ f2fs_decompress_end_io(cc->rpages, cc->cluster_size, true, false);
+ *bio_ret = bio;
+ return ret;
+}
+#endif
+
/*
* This function was originally taken from fs/mpage.c, and customized for f2fs.
* Major change was from block_size == page_size in f2fs by default.
@@ -1889,6 +2167,19 @@ int f2fs_mpage_readpages(struct address_space *mapping,
sector_t last_block_in_bio = 0;
struct inode *inode = mapping->host;
struct f2fs_map_blocks map;
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+ struct compress_ctx cc = {
+ .inode = inode,
+ .log_cluster_size = F2FS_I(inode)->i_log_cluster_size,
+ .cluster_size = F2FS_I(inode)->i_cluster_size,
+ .cluster_idx = NULL_CLUSTER,
+ .rpages = NULL,
+ .cpages = NULL,
+ .nr_rpages = 0,
+ .nr_cpages = 0,
+ };
+#endif
+ unsigned max_nr_pages = nr_pages;
int ret = 0;
map.m_pblk = 0;
@@ -1912,9 +2203,41 @@ int f2fs_mpage_readpages(struct address_space *mapping,
goto next_page;
}
- ret = f2fs_read_single_page(inode, page, nr_pages, &map, &bio,
- &last_block_in_bio, is_readahead);
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+ if (f2fs_compressed_file(inode)) {
+ /* there are remained comressed pages, submit them */
+ if (!f2fs_cluster_can_merge_page(&cc, page->index)) {
+ ret = f2fs_read_multi_pages(&cc, &bio,
+ max_nr_pages,
+ &last_block_in_bio,
+ is_readahead);
+ f2fs_destroy_compress_ctx(&cc);
+ if (ret)
+ goto set_error_page;
+ }
+ ret = f2fs_is_compressed_cluster(inode, page->index);
+ if (ret < 0)
+ goto set_error_page;
+ else if (!ret)
+ goto read_single_page;
+
+ ret = f2fs_init_compress_ctx(&cc);
+ if (ret)
+ goto set_error_page;
+
+ f2fs_compress_ctx_add_page(&cc, page);
+
+ goto next_page;
+ }
+read_single_page:
+#endif
+
+ ret = f2fs_read_single_page(inode, page, max_nr_pages, &map,
+ &bio, &last_block_in_bio, is_readahead);
if (ret) {
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+set_error_page:
+#endif
SetPageError(page);
zero_user_segment(page, 0, PAGE_SIZE);
unlock_page(page);
@@ -1922,6 +2245,19 @@ int f2fs_mpage_readpages(struct address_space *mapping,
next_page:
if (pages)
put_page(page);
+
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+ if (f2fs_compressed_file(inode)) {
+ /* last page */
+ if (nr_pages == 1 && !f2fs_cluster_is_empty(&cc)) {
+ ret = f2fs_read_multi_pages(&cc, &bio,
+ max_nr_pages,
+ &last_block_in_bio,
+ is_readahead);
+ f2fs_destroy_compress_ctx(&cc);
+ }
+ }
+#endif
}
BUG_ON(pages && !list_empty(pages));
if (bio)
@@ -1936,6 +2272,11 @@ static int f2fs_read_data_page(struct file *file, struct page *page)
trace_f2fs_readpage(page, DATA);
+ if (!f2fs_is_compress_backend_ready(inode)) {
+ unlock_page(page);
+ return -EOPNOTSUPP;
+ }
+
/* If the file has inline data, try to read it directly */
if (f2fs_has_inline_data(inode))
ret = f2fs_read_inline_data(inode, page);
@@ -1954,6 +2295,9 @@ static int f2fs_read_data_pages(struct file *file,
trace_f2fs_readpages(inode, page, nr_pages);
+ if (!f2fs_is_compress_backend_ready(inode))
+ return 0;
+
/* If the file has inline data, skip readpages */
if (f2fs_has_inline_data(inode))
return 0;
@@ -1961,22 +2305,23 @@ static int f2fs_read_data_pages(struct file *file,
return f2fs_mpage_readpages(mapping, pages, NULL, nr_pages, true);
}
-static int encrypt_one_page(struct f2fs_io_info *fio)
+int f2fs_encrypt_one_page(struct f2fs_io_info *fio)
{
struct inode *inode = fio->page->mapping->host;
- struct page *mpage;
+ struct page *mpage, *page;
gfp_t gfp_flags = GFP_NOFS;
if (!f2fs_encrypted_file(inode))
return 0;
+ page = fio->compressed_page ? fio->compressed_page : fio->page;
+
/* wait for GCed page writeback via META_MAPPING */
f2fs_wait_on_block_writeback(inode, fio->old_blkaddr);
retry_encrypt:
- fio->encrypted_page = fscrypt_encrypt_pagecache_blocks(fio->page,
- PAGE_SIZE, 0,
- gfp_flags);
+ fio->encrypted_page = fscrypt_encrypt_pagecache_blocks(page,
+ PAGE_SIZE, 0, gfp_flags);
if (IS_ERR(fio->encrypted_page)) {
/* flush pending IOs and wait for a while in the ENOMEM case */
if (PTR_ERR(fio->encrypted_page) == -ENOMEM) {
@@ -2136,7 +2481,7 @@ got_it:
if (ipu_force ||
(__is_valid_data_blkaddr(fio->old_blkaddr) &&
need_inplace_update(fio))) {
- err = encrypt_one_page(fio);
+ err = f2fs_encrypt_one_page(fio);
if (err)
goto out_writepage;
@@ -2172,13 +2517,16 @@ got_it:
fio->version = ni.version;
- err = encrypt_one_page(fio);
+ err = f2fs_encrypt_one_page(fio);
if (err)
goto out_writepage;
set_page_writeback(page);
ClearPageError(page);
+ if (fio->compr_blocks && fio->old_blkaddr == COMPRESS_ADDR)
+ f2fs_i_compr_blocks_update(inode, fio->compr_blocks - 1, false);
+
/* LFS mode write path */
f2fs_outplace_write_data(&dn, fio);
trace_f2fs_do_write_data_page(page, OPU);
@@ -2193,16 +2541,17 @@ out:
return err;
}
-static int __write_data_page(struct page *page, bool *submitted,
+int f2fs_write_single_data_page(struct page *page, int *submitted,
struct bio **bio,
sector_t *last_block,
struct writeback_control *wbc,
- enum iostat_type io_type)
+ enum iostat_type io_type,
+ int compr_blocks)
{
struct inode *inode = page->mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
loff_t i_size = i_size_read(inode);
- const pgoff_t end_index = ((unsigned long long) i_size)
+ const pgoff_t end_index = ((unsigned long long)i_size)
>> PAGE_SHIFT;
loff_t psize = (loff_t)(page->index + 1) << PAGE_SHIFT;
unsigned offset = 0;
@@ -2218,6 +2567,7 @@ static int __write_data_page(struct page *page, bool *submitted,
.page = page,
.encrypted_page = NULL,
.submitted = false,
+ .compr_blocks = compr_blocks,
.need_lock = LOCK_RETRY,
.io_type = io_type,
.io_wbc = wbc,
@@ -2242,7 +2592,9 @@ static int __write_data_page(struct page *page, bool *submitted,
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto redirty_out;
- if (page->index < end_index || f2fs_verity_in_progress(inode))
+ if (page->index < end_index ||
+ f2fs_verity_in_progress(inode) ||
+ compr_blocks)
goto write;
/*
@@ -2318,7 +2670,6 @@ out:
f2fs_remove_dirty_inode(inode);
submitted = NULL;
}
-
unlock_page(page);
if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode) &&
!F2FS_I(inode)->cp_task)
@@ -2331,7 +2682,7 @@ out:
}
if (submitted)
- *submitted = fio.submitted;
+ *submitted = fio.submitted ? 1 : 0;
return 0;
@@ -2352,7 +2703,23 @@ redirty_out:
static int f2fs_write_data_page(struct page *page,
struct writeback_control *wbc)
{
- return __write_data_page(page, NULL, NULL, NULL, wbc, FS_DATA_IO);
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+ struct inode *inode = page->mapping->host;
+
+ if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
+ goto out;
+
+ if (f2fs_compressed_file(inode)) {
+ if (f2fs_is_compressed_cluster(inode, page->index)) {
+ redirty_page_for_writepage(wbc, page);
+ return AOP_WRITEPAGE_ACTIVATE;
+ }
+ }
+out:
+#endif
+
+ return f2fs_write_single_data_page(page, NULL, NULL, NULL,
+ wbc, FS_DATA_IO, 0);
}
/*
@@ -2365,11 +2732,27 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
enum iostat_type io_type)
{
int ret = 0;
- int done = 0;
+ int done = 0, retry = 0;
struct pagevec pvec;
struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
struct bio *bio = NULL;
sector_t last_block;
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+ struct inode *inode = mapping->host;
+ struct compress_ctx cc = {
+ .inode = inode,
+ .log_cluster_size = F2FS_I(inode)->i_log_cluster_size,
+ .cluster_size = F2FS_I(inode)->i_cluster_size,
+ .cluster_idx = NULL_CLUSTER,
+ .rpages = NULL,
+ .nr_rpages = 0,
+ .cpages = NULL,
+ .rbuf = NULL,
+ .cbuf = NULL,
+ .rlen = PAGE_SIZE * F2FS_I(inode)->i_cluster_size,
+ .private = NULL,
+ };
+#endif
int nr_pages;
pgoff_t uninitialized_var(writeback_index);
pgoff_t index;
@@ -2379,6 +2762,8 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
int range_whole = 0;
xa_mark_t tag;
int nwritten = 0;
+ int submitted = 0;
+ int i;
pagevec_init(&pvec);
@@ -2408,12 +2793,11 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
else
tag = PAGECACHE_TAG_DIRTY;
retry:
+ retry = 0;
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, index, end);
done_index = index;
- while (!done && (index <= end)) {
- int i;
-
+ while (!done && !retry && (index <= end)) {
nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end,
tag);
if (nr_pages == 0)
@@ -2421,15 +2805,62 @@ retry:
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
- bool submitted = false;
+ bool need_readd;
+readd:
+ need_readd = false;
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+ if (f2fs_compressed_file(inode)) {
+ ret = f2fs_init_compress_ctx(&cc);
+ if (ret) {
+ done = 1;
+ break;
+ }
+
+ if (!f2fs_cluster_can_merge_page(&cc,
+ page->index)) {
+ ret = f2fs_write_multi_pages(&cc,
+ &submitted, wbc, io_type);
+ if (!ret)
+ need_readd = true;
+ goto result;
+ }
+ if (unlikely(f2fs_cp_error(sbi)))
+ goto lock_page;
+
+ if (f2fs_cluster_is_empty(&cc)) {
+ void *fsdata = NULL;
+ struct page *pagep;
+ int ret2;
+
+ ret2 = f2fs_prepare_compress_overwrite(
+ inode, &pagep,
+ page->index, &fsdata);
+ if (ret2 < 0) {
+ ret = ret2;
+ done = 1;
+ break;
+ } else if (ret2 &&
+ !f2fs_compress_write_end(inode,
+ fsdata, page->index,
+ 1)) {
+ retry = 1;
+ break;
+ }
+ } else {
+ goto lock_page;
+ }
+ }
+#endif
/* give a priority to WB_SYNC threads */
if (atomic_read(&sbi->wb_sync_req[DATA]) &&
wbc->sync_mode == WB_SYNC_NONE) {
done = 1;
break;
}
-
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+lock_page:
+#endif
done_index = page->index;
retry_write:
lock_page(page);
@@ -2456,45 +2887,71 @@ continue_unlock:
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
- ret = __write_data_page(page, &submitted, &bio,
- &last_block, wbc, io_type);
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+ if (f2fs_compressed_file(inode)) {
+ get_page(page);
+ f2fs_compress_ctx_add_page(&cc, page);
+ continue;
+ }
+#endif
+ ret = f2fs_write_single_data_page(page, &submitted,
+ &bio, &last_block, wbc, io_type, 0);
+ if (ret == AOP_WRITEPAGE_ACTIVATE)
+ unlock_page(page);
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+result:
+#endif
+ nwritten += submitted;
+ wbc->nr_to_write -= submitted;
+
if (unlikely(ret)) {
/*
* keep nr_to_write, since vfs uses this to
* get # of written pages.
*/
if (ret == AOP_WRITEPAGE_ACTIVATE) {
- unlock_page(page);
ret = 0;
- continue;
+ goto next;
} else if (ret == -EAGAIN) {
ret = 0;
if (wbc->sync_mode == WB_SYNC_ALL) {
cond_resched();
congestion_wait(BLK_RW_ASYNC,
- HZ/50);
+ HZ/50);
goto retry_write;
}
- continue;
+ goto next;
}
done_index = page->index + 1;
done = 1;
break;
- } else if (submitted) {
- nwritten++;
}
- if (--wbc->nr_to_write <= 0 &&
+ if (wbc->nr_to_write <= 0 &&
wbc->sync_mode == WB_SYNC_NONE) {
done = 1;
break;
}
+next:
+ if (need_readd)
+ goto readd;
}
pagevec_release(&pvec);
cond_resched();
}
-
- if (!cycled && !done) {
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+ /* flush remained pages in compress cluster */
+ if (f2fs_compressed_file(inode) && !f2fs_cluster_is_empty(&cc)) {
+ ret = f2fs_write_multi_pages(&cc, &submitted, wbc, io_type);
+ nwritten += submitted;
+ wbc->nr_to_write -= submitted;
+ if (ret) {
+ done = 1;
+ retry = 0;
+ }
+ }
+#endif
+ if ((!cycled && !done) || retry) {
cycled = 1;
index = 0;
end = writeback_index - 1;
@@ -2518,6 +2975,8 @@ static inline bool __should_serialize_io(struct inode *inode,
{
if (!S_ISREG(inode->i_mode))
return false;
+ if (f2fs_compressed_file(inode))
+ return true;
if (IS_NOQUOTA(inode))
return false;
/* to avoid deadlock in path of data flush */
@@ -2613,14 +3072,16 @@ static void f2fs_write_failed(struct address_space *mapping, loff_t to)
struct inode *inode = mapping->host;
loff_t i_size = i_size_read(inode);
+ if (IS_NOQUOTA(inode))
+ return;
+
/* In the fs-verity case, f2fs_end_enable_verity() does the truncate */
if (to > i_size && !f2fs_verity_in_progress(inode)) {
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
down_write(&F2FS_I(inode)->i_mmap_sem);
truncate_pagecache(inode, i_size);
- if (!IS_NOQUOTA(inode))
- f2fs_truncate_blocks(inode, i_size, true);
+ f2fs_truncate_blocks(inode, i_size, true);
up_write(&F2FS_I(inode)->i_mmap_sem);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
@@ -2660,6 +3121,7 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi,
__do_map_lock(sbi, flag, true);
locked = true;
}
+
restart:
/* check inline_data */
ipage = f2fs_get_node_page(sbi, inode->i_ino);
@@ -2750,6 +3212,24 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
if (err)
goto fail;
}
+
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+ if (f2fs_compressed_file(inode)) {
+ int ret;
+
+ *fsdata = NULL;
+
+ ret = f2fs_prepare_compress_overwrite(inode, pagep,
+ index, fsdata);
+ if (ret < 0) {
+ err = ret;
+ goto fail;
+ } else if (ret) {
+ return 0;
+ }
+ }
+#endif
+
repeat:
/*
* Do not use grab_cache_page_write_begin() to avoid deadlock due to
@@ -2762,6 +3242,8 @@ repeat:
goto fail;
}
+ /* TODO: cluster can be compressed due to race with .writepage */
+
*pagep = page;
err = prepare_write_begin(sbi, page, pos, len,
@@ -2845,6 +3327,16 @@ static int f2fs_write_end(struct file *file,
else
SetPageUptodate(page);
}
+
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+ /* overwrite compressed file */
+ if (f2fs_compressed_file(inode) && fsdata) {
+ f2fs_compress_write_end(inode, fsdata, page->index, copied);
+ f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
+ return copied;
+ }
+#endif
+
if (!copied)
goto unlock_out;
@@ -3145,7 +3637,8 @@ int f2fs_migrate_page(struct address_space *mapping,
#ifdef CONFIG_SWAP
/* Copied from generic_swapfile_activate() to check any holes */
-static int check_swap_activate(struct file *swap_file, unsigned int max)
+static int check_swap_activate(struct swap_info_struct *sis,
+ struct file *swap_file, sector_t *span)
{
struct address_space *mapping = swap_file->f_mapping;
struct inode *inode = mapping->host;
@@ -3156,6 +3649,8 @@ static int check_swap_activate(struct file *swap_file, unsigned int max)
sector_t last_block;
sector_t lowest_block = -1;
sector_t highest_block = 0;
+ int nr_extents = 0;
+ int ret;
blkbits = inode->i_blkbits;
blocks_per_page = PAGE_SIZE >> blkbits;
@@ -3167,7 +3662,8 @@ static int check_swap_activate(struct file *swap_file, unsigned int max)
probe_block = 0;
page_no = 0;
last_block = i_size_read(inode) >> blkbits;
- while ((probe_block + blocks_per_page) <= last_block && page_no < max) {
+ while ((probe_block + blocks_per_page) <= last_block &&
+ page_no < sis->max) {
unsigned block_in_page;
sector_t first_block;
@@ -3207,13 +3703,27 @@ static int check_swap_activate(struct file *swap_file, unsigned int max)
highest_block = first_block;
}
+ /*
+ * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks
+ */
+ ret = add_swap_extent(sis, page_no, 1, first_block);
+ if (ret < 0)
+ goto out;
+ nr_extents += ret;
page_no++;
probe_block += blocks_per_page;
reprobe:
continue;
}
- return 0;
-
+ ret = nr_extents;
+ *span = 1 + highest_block - lowest_block;
+ if (page_no == 0)
+ page_no = 1; /* force Empty message */
+ sis->max = page_no;
+ sis->pages = page_no - 1;
+ sis->highest_bit = page_no - 1;
+out:
+ return ret;
bad_bmap:
pr_err("swapon: swapfile has holes\n");
return -EINVAL;
@@ -3235,14 +3745,17 @@ static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file,
if (ret)
return ret;
- ret = check_swap_activate(file, sis->max);
- if (ret)
+ if (f2fs_disable_compressed_file(inode))
+ return -EINVAL;
+
+ ret = check_swap_activate(sis, file, span);
+ if (ret < 0)
return ret;
set_inode_flag(inode, FI_PIN_FILE);
f2fs_precache_extents(inode);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
- return 0;
+ return ret;
}
static void f2fs_swap_deactivate(struct file *file)
@@ -3319,6 +3832,27 @@ void f2fs_destroy_post_read_processing(void)
kmem_cache_destroy(bio_post_read_ctx_cache);
}
+int f2fs_init_post_read_wq(struct f2fs_sb_info *sbi)
+{
+ if (!f2fs_sb_has_encrypt(sbi) &&
+ !f2fs_sb_has_verity(sbi) &&
+ !f2fs_sb_has_compression(sbi))
+ return 0;
+
+ sbi->post_read_wq = alloc_workqueue("f2fs_post_read_wq",
+ WQ_UNBOUND | WQ_HIGHPRI,
+ num_online_cpus());
+ if (!sbi->post_read_wq)
+ return -ENOMEM;
+ return 0;
+}
+
+void f2fs_destroy_post_read_wq(struct f2fs_sb_info *sbi)
+{
+ if (sbi->post_read_wq)
+ destroy_workqueue(sbi->post_read_wq);
+}
+
int __init f2fs_init_bio_entry_cache(void)
{
bio_entry_slab = f2fs_kmem_cache_create("bio_entry_slab",
@@ -3328,7 +3862,7 @@ int __init f2fs_init_bio_entry_cache(void)
return 0;
}
-void __exit f2fs_destroy_bio_entry_cache(void)
+void f2fs_destroy_bio_entry_cache(void)
{
kmem_cache_destroy(bio_entry_slab);
}
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 9b0bedd82581..6b89eae5e4ca 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -21,9 +21,45 @@
#include "gc.h"
static LIST_HEAD(f2fs_stat_list);
-static struct dentry *f2fs_debugfs_root;
static DEFINE_MUTEX(f2fs_stat_mutex);
+#ifdef CONFIG_DEBUG_FS
+static struct dentry *f2fs_debugfs_root;
+#endif
+
+/*
+ * This function calculates BDF of every segments
+ */
+void f2fs_update_sit_info(struct f2fs_sb_info *sbi)
+{
+ struct f2fs_stat_info *si = F2FS_STAT(sbi);
+ unsigned long long blks_per_sec, hblks_per_sec, total_vblocks;
+ unsigned long long bimodal, dist;
+ unsigned int segno, vblocks;
+ int ndirty = 0;
+
+ bimodal = 0;
+ total_vblocks = 0;
+ blks_per_sec = BLKS_PER_SEC(sbi);
+ hblks_per_sec = blks_per_sec / 2;
+ for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
+ vblocks = get_valid_blocks(sbi, segno, true);
+ dist = abs(vblocks - hblks_per_sec);
+ bimodal += dist * dist;
+
+ if (vblocks > 0 && vblocks < blks_per_sec) {
+ total_vblocks += vblocks;
+ ndirty++;
+ }
+ }
+ dist = div_u64(MAIN_SECS(sbi) * hblks_per_sec * hblks_per_sec, 100);
+ si->bimodal = div64_u64(bimodal, dist);
+ if (si->dirty_count)
+ si->avg_vblocks = div_u64(total_vblocks, ndirty);
+ else
+ si->avg_vblocks = 0;
+}
+#ifdef CONFIG_DEBUG_FS
static void update_general_status(struct f2fs_sb_info *sbi)
{
struct f2fs_stat_info *si = F2FS_STAT(sbi);
@@ -56,7 +92,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
si->nquota_files = sbi->nquota_files;
si->ndirty_all = sbi->ndirty_inode[DIRTY_META];
si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES);
- si->aw_cnt = atomic_read(&sbi->aw_cnt);
+ si->aw_cnt = sbi->atomic_files;
si->vw_cnt = atomic_read(&sbi->vw_cnt);
si->max_aw_cnt = atomic_read(&sbi->max_aw_cnt);
si->max_vw_cnt = atomic_read(&sbi->max_vw_cnt);
@@ -94,6 +130,8 @@ static void update_general_status(struct f2fs_sb_info *sbi)
si->inline_xattr = atomic_read(&sbi->inline_xattr);
si->inline_inode = atomic_read(&sbi->inline_inode);
si->inline_dir = atomic_read(&sbi->inline_dir);
+ si->compr_inode = atomic_read(&sbi->compr_inode);
+ si->compr_blocks = atomic_read(&sbi->compr_blocks);
si->append = sbi->im[APPEND_INO].ino_num;
si->update = sbi->im[UPDATE_INO].ino_num;
si->orphans = sbi->im[ORPHAN_INO].ino_num;
@@ -114,7 +152,6 @@ static void update_general_status(struct f2fs_sb_info *sbi)
si->free_nids = NM_I(sbi)->nid_cnt[FREE_NID];
si->avail_nids = NM_I(sbi)->available_nids;
si->alloc_nids = NM_I(sbi)->nid_cnt[PREALLOC_NID];
- si->bg_gc = sbi->bg_gc;
si->io_skip_bggc = sbi->io_skip_bggc;
si->other_skip_bggc = sbi->other_skip_bggc;
si->skipped_atomic_files[BG_GC] = sbi->skipped_atomic_files[BG_GC];
@@ -146,39 +183,6 @@ static void update_general_status(struct f2fs_sb_info *sbi)
}
/*
- * This function calculates BDF of every segments
- */
-static void update_sit_info(struct f2fs_sb_info *sbi)
-{
- struct f2fs_stat_info *si = F2FS_STAT(sbi);
- unsigned long long blks_per_sec, hblks_per_sec, total_vblocks;
- unsigned long long bimodal, dist;
- unsigned int segno, vblocks;
- int ndirty = 0;
-
- bimodal = 0;
- total_vblocks = 0;
- blks_per_sec = BLKS_PER_SEC(sbi);
- hblks_per_sec = blks_per_sec / 2;
- for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
- vblocks = get_valid_blocks(sbi, segno, true);
- dist = abs(vblocks - hblks_per_sec);
- bimodal += dist * dist;
-
- if (vblocks > 0 && vblocks < blks_per_sec) {
- total_vblocks += vblocks;
- ndirty++;
- }
- }
- dist = div_u64(MAIN_SECS(sbi) * hblks_per_sec * hblks_per_sec, 100);
- si->bimodal = div64_u64(bimodal, dist);
- if (si->dirty_count)
- si->avg_vblocks = div_u64(total_vblocks, ndirty);
- else
- si->avg_vblocks = 0;
-}
-
-/*
* This function calculates memory footprint.
*/
static void update_mem_info(struct f2fs_sb_info *sbi)
@@ -315,6 +319,8 @@ static int stat_show(struct seq_file *s, void *v)
si->inline_inode);
seq_printf(s, " - Inline_dentry Inode: %u\n",
si->inline_dir);
+ seq_printf(s, " - Compressed Inode: %u, Blocks: %u\n",
+ si->compr_inode, si->compr_blocks);
seq_printf(s, " - Orphan/Append/Update Inode: %u, %u, %u\n",
si->orphans, si->append, si->update);
seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n",
@@ -441,7 +447,7 @@ static int stat_show(struct seq_file *s, void *v)
si->block_count[LFS], si->segment_count[LFS]);
/* segment usage info */
- update_sit_info(si->sbi);
+ f2fs_update_sit_info(si->sbi);
seq_printf(s, "\nBDF: %u, avg. vblocks: %u\n",
si->bimodal, si->avg_vblocks);
@@ -461,6 +467,7 @@ static int stat_show(struct seq_file *s, void *v)
}
DEFINE_SHOW_ATTRIBUTE(stat);
+#endif
int f2fs_build_stats(struct f2fs_sb_info *sbi)
{
@@ -491,11 +498,12 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
atomic_set(&sbi->inline_xattr, 0);
atomic_set(&sbi->inline_inode, 0);
atomic_set(&sbi->inline_dir, 0);
+ atomic_set(&sbi->compr_inode, 0);
+ atomic_set(&sbi->compr_blocks, 0);
atomic_set(&sbi->inplace_count, 0);
for (i = META_CP; i < META_MAX; i++)
atomic_set(&sbi->meta_count[i], 0);
- atomic_set(&sbi->aw_cnt, 0);
atomic_set(&sbi->vw_cnt, 0);
atomic_set(&sbi->max_aw_cnt, 0);
atomic_set(&sbi->max_vw_cnt, 0);
@@ -520,14 +528,18 @@ void f2fs_destroy_stats(struct f2fs_sb_info *sbi)
void __init f2fs_create_root_stats(void)
{
+#ifdef CONFIG_DEBUG_FS
f2fs_debugfs_root = debugfs_create_dir("f2fs", NULL);
debugfs_create_file("status", S_IRUGO, f2fs_debugfs_root, NULL,
&stat_fops);
+#endif
}
void f2fs_destroy_root_stats(void)
{
+#ifdef CONFIG_DEBUG_FS
debugfs_remove_recursive(f2fs_debugfs_root);
f2fs_debugfs_root = NULL;
+#endif
}
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index d9ad842945df..27d0dd7a16d6 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -578,6 +578,20 @@ next:
goto next;
}
+bool f2fs_has_enough_room(struct inode *dir, struct page *ipage,
+ struct fscrypt_name *fname)
+{
+ struct f2fs_dentry_ptr d;
+ unsigned int bit_pos;
+ int slots = GET_DENTRY_SLOTS(fname_len(fname));
+
+ make_dentry_ptr_inline(dir, &d, inline_data_addr(dir, ipage));
+
+ bit_pos = f2fs_room_for_filename(d.bitmap, slots, d.max);
+
+ return bit_pos < d.max;
+}
+
void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
const struct qstr *name, f2fs_hash_t name_hash,
unsigned int bit_pos)
@@ -1069,24 +1083,27 @@ static int f2fs_d_compare(const struct dentry *dentry, unsigned int len,
const char *str, const struct qstr *name)
{
struct qstr qstr = {.name = str, .len = len };
+ const struct dentry *parent = READ_ONCE(dentry->d_parent);
+ const struct inode *inode = READ_ONCE(parent->d_inode);
- if (!IS_CASEFOLDED(dentry->d_parent->d_inode)) {
+ if (!inode || !IS_CASEFOLDED(inode)) {
if (len != name->len)
return -1;
- return memcmp(str, name, len);
+ return memcmp(str, name->name, len);
}
- return f2fs_ci_compare(dentry->d_parent->d_inode, name, &qstr, false);
+ return f2fs_ci_compare(inode, name, &qstr, false);
}
static int f2fs_d_hash(const struct dentry *dentry, struct qstr *str)
{
struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
const struct unicode_map *um = sbi->s_encoding;
+ const struct inode *inode = READ_ONCE(dentry->d_inode);
unsigned char *norm;
int len, ret = 0;
- if (!IS_CASEFOLDED(dentry->d_inode))
+ if (!inode || !IS_CASEFOLDED(inode))
return 0;
norm = f2fs_kmalloc(sbi, PATH_MAX, GFP_ATOMIC);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 059ade83bfb1..5355be6b6755 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -116,6 +116,8 @@ typedef u32 block_t; /*
*/
typedef u32 nid_t;
+#define COMPRESS_EXT_NUM 16
+
struct f2fs_mount_info {
unsigned int opt;
int write_io_size_bits; /* Write IO size bits */
@@ -140,6 +142,12 @@ struct f2fs_mount_info {
block_t unusable_cap; /* Amount of space allowed to be
* unusable when disabling checkpoint
*/
+
+ /* For compression */
+ unsigned char compress_algorithm; /* algorithm type */
+ unsigned compress_log_size; /* cluster log size */
+ unsigned char compress_ext_cnt; /* extension count */
+ unsigned char extensions[COMPRESS_EXT_NUM][F2FS_EXTENSION_LEN]; /* extensions */
};
#define F2FS_FEATURE_ENCRYPT 0x0001
@@ -155,6 +163,7 @@ struct f2fs_mount_info {
#define F2FS_FEATURE_VERITY 0x0400
#define F2FS_FEATURE_SB_CHKSUM 0x0800
#define F2FS_FEATURE_CASEFOLD 0x1000
+#define F2FS_FEATURE_COMPRESSION 0x2000
#define __F2FS_HAS_FEATURE(raw_super, mask) \
((raw_super->feature & cpu_to_le32(mask)) != 0)
@@ -712,6 +721,12 @@ struct f2fs_inode_info {
int i_inline_xattr_size; /* inline xattr size */
struct timespec64 i_crtime; /* inode creation time */
struct timespec64 i_disk_time[4];/* inode disk times */
+
+ /* for file compress */
+ u64 i_compr_blocks; /* # of compressed blocks */
+ unsigned char i_compress_algorithm; /* algorithm type */
+ unsigned char i_log_cluster_size; /* log of cluster size */
+ unsigned int i_cluster_size; /* cluster size */
};
static inline void get_extent_info(struct extent_info *ext,
@@ -1018,6 +1033,7 @@ enum need_lock_type {
enum cp_reason_type {
CP_NO_NEEDED,
CP_NON_REGULAR,
+ CP_COMPRESSED,
CP_HARDLINK,
CP_SB_NEED_CP,
CP_WRONG_PINO,
@@ -1056,12 +1072,15 @@ struct f2fs_io_info {
block_t old_blkaddr; /* old block address before Cow */
struct page *page; /* page to be written */
struct page *encrypted_page; /* encrypted page */
+ struct page *compressed_page; /* compressed page */
struct list_head list; /* serialize IOs */
bool submitted; /* indicate IO submission */
int need_lock; /* indicate we need to lock cp_rwsem */
bool in_list; /* indicate fio is in io_list */
bool is_por; /* indicate IO is from recovery or not */
bool retry; /* need to reallocate block address */
+ int compr_blocks; /* # of compressed block addresses */
+ bool encrypted; /* indicate file is encrypted */
enum iostat_type io_type; /* io type */
struct writeback_control *io_wbc; /* writeback control */
struct bio **bio; /* bio for ipu */
@@ -1169,6 +1188,18 @@ enum fsync_mode {
FSYNC_MODE_NOBARRIER, /* fsync behaves nobarrier based on posix */
};
+/*
+ * this value is set in page as a private data which indicate that
+ * the page is atomically written, and it is in inmem_pages list.
+ */
+#define ATOMIC_WRITTEN_PAGE ((unsigned long)-1)
+#define DUMMY_WRITTEN_PAGE ((unsigned long)-2)
+
+#define IS_ATOMIC_WRITTEN_PAGE(page) \
+ (page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE)
+#define IS_DUMMY_WRITTEN_PAGE(page) \
+ (page_private(page) == (unsigned long)DUMMY_WRITTEN_PAGE)
+
#ifdef CONFIG_FS_ENCRYPTION
#define DUMMY_ENCRYPTION_ENABLED(sbi) \
(unlikely(F2FS_OPTION(sbi).test_dummy_encryption))
@@ -1176,6 +1207,75 @@ enum fsync_mode {
#define DUMMY_ENCRYPTION_ENABLED(sbi) (0)
#endif
+/* For compression */
+enum compress_algorithm_type {
+ COMPRESS_LZO,
+ COMPRESS_LZ4,
+ COMPRESS_MAX,
+};
+
+#define COMPRESS_DATA_RESERVED_SIZE 4
+struct compress_data {
+ __le32 clen; /* compressed data size */
+ __le32 chksum; /* checksum of compressed data */
+ __le32 reserved[COMPRESS_DATA_RESERVED_SIZE]; /* reserved */
+ u8 cdata[]; /* compressed data */
+};
+
+#define COMPRESS_HEADER_SIZE (sizeof(struct compress_data))
+
+#define F2FS_COMPRESSED_PAGE_MAGIC 0xF5F2C000
+
+/* compress context */
+struct compress_ctx {
+ struct inode *inode; /* inode the context belong to */
+ pgoff_t cluster_idx; /* cluster index number */
+ unsigned int cluster_size; /* page count in cluster */
+ unsigned int log_cluster_size; /* log of cluster size */
+ struct page **rpages; /* pages store raw data in cluster */
+ unsigned int nr_rpages; /* total page number in rpages */
+ struct page **cpages; /* pages store compressed data in cluster */
+ unsigned int nr_cpages; /* total page number in cpages */
+ void *rbuf; /* virtual mapped address on rpages */
+ struct compress_data *cbuf; /* virtual mapped address on cpages */
+ size_t rlen; /* valid data length in rbuf */
+ size_t clen; /* valid data length in cbuf */
+ void *private; /* payload buffer for specified compression algorithm */
+};
+
+/* compress context for write IO path */
+struct compress_io_ctx {
+ u32 magic; /* magic number to indicate page is compressed */
+ struct inode *inode; /* inode the context belong to */
+ struct page **rpages; /* pages store raw data in cluster */
+ unsigned int nr_rpages; /* total page number in rpages */
+ refcount_t ref; /* referrence count of raw page */
+};
+
+/* decompress io context for read IO path */
+struct decompress_io_ctx {
+ u32 magic; /* magic number to indicate page is compressed */
+ struct inode *inode; /* inode the context belong to */
+ pgoff_t cluster_idx; /* cluster index number */
+ unsigned int cluster_size; /* page count in cluster */
+ unsigned int log_cluster_size; /* log of cluster size */
+ struct page **rpages; /* pages store raw data in cluster */
+ unsigned int nr_rpages; /* total page number in rpages */
+ struct page **cpages; /* pages store compressed data in cluster */
+ unsigned int nr_cpages; /* total page number in cpages */
+ struct page **tpages; /* temp pages to pad holes in cluster */
+ void *rbuf; /* virtual mapped address on rpages */
+ struct compress_data *cbuf; /* virtual mapped address on cpages */
+ size_t rlen; /* valid data length in rbuf */
+ size_t clen; /* valid data length in cbuf */
+ refcount_t ref; /* referrence count of compressed page */
+ bool failed; /* indicate IO error during decompression */
+};
+
+#define NULL_CLUSTER ((unsigned int)(~0))
+#define MIN_COMPRESS_LOG_SIZE 2
+#define MAX_COMPRESS_LOG_SIZE 8
+
struct f2fs_sb_info {
struct super_block *sb; /* pointer to VFS super block */
struct proc_dir_entry *s_proc; /* proc entry */
@@ -1291,7 +1391,10 @@ struct f2fs_sb_info {
struct f2fs_mount_info mount_opt; /* mount options */
/* for cleaning operations */
- struct mutex gc_mutex; /* mutex for GC */
+ struct rw_semaphore gc_lock; /*
+ * semaphore for GC, avoid
+ * race between GC and GC or CP
+ */
struct f2fs_gc_kthread *gc_thread; /* GC thread */
unsigned int cur_victim_sec; /* current victim section num */
unsigned int gc_mode; /* current GC state */
@@ -1327,11 +1430,11 @@ struct f2fs_sb_info {
atomic_t inline_xattr; /* # of inline_xattr inodes */
atomic_t inline_inode; /* # of inline_data inodes */
atomic_t inline_dir; /* # of inline_dentry inodes */
- atomic_t aw_cnt; /* # of atomic writes */
+ atomic_t compr_inode; /* # of compressed inodes */
+ atomic_t compr_blocks; /* # of compressed blocks */
atomic_t vw_cnt; /* # of volatile writes */
atomic_t max_aw_cnt; /* max # of atomic writes */
atomic_t max_vw_cnt; /* max # of volatile writes */
- int bg_gc; /* background gc calls */
unsigned int io_skip_bggc; /* skip background gc for in-flight IO */
unsigned int other_skip_bggc; /* skip background gc for other reasons */
unsigned int ndirty_inode[NR_INODE_TYPE]; /* # of dirty inodes */
@@ -1365,6 +1468,8 @@ struct f2fs_sb_info {
/* Precomputed FS UUID checksum for seeding other checksums */
__u32 s_chksum_seed;
+
+ struct workqueue_struct *post_read_wq; /* post read workqueue */
};
struct f2fs_private_dio {
@@ -2222,26 +2327,6 @@ static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep,
return entry;
}
-static inline struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi,
- int npages, bool no_fail)
-{
- struct bio *bio;
-
- if (no_fail) {
- /* No failure on bio allocation */
- bio = bio_alloc(GFP_NOIO, npages);
- if (!bio)
- bio = bio_alloc(GFP_NOIO | __GFP_NOFAIL, npages);
- return bio;
- }
- if (time_to_inject(sbi, FAULT_ALLOC_BIO)) {
- f2fs_show_injection_info(sbi, FAULT_ALLOC_BIO);
- return NULL;
- }
-
- return bio_alloc(GFP_KERNEL, npages);
-}
-
static inline bool is_idle(struct f2fs_sb_info *sbi, int type)
{
if (sbi->gc_mode == GC_URGENT)
@@ -2378,11 +2463,13 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr)
/*
* On-disk inode flags (f2fs_inode::i_flags)
*/
+#define F2FS_COMPR_FL 0x00000004 /* Compress file */
#define F2FS_SYNC_FL 0x00000008 /* Synchronous updates */
#define F2FS_IMMUTABLE_FL 0x00000010 /* Immutable file */
#define F2FS_APPEND_FL 0x00000020 /* writes to file may only append */
#define F2FS_NODUMP_FL 0x00000040 /* do not dump file */
#define F2FS_NOATIME_FL 0x00000080 /* do not update atime */
+#define F2FS_NOCOMP_FL 0x00000400 /* Don't compress */
#define F2FS_INDEX_FL 0x00001000 /* hash-indexed directory */
#define F2FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */
#define F2FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */
@@ -2391,7 +2478,7 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr)
/* Flags that should be inherited by new inodes from their parent. */
#define F2FS_FL_INHERITED (F2FS_SYNC_FL | F2FS_NODUMP_FL | F2FS_NOATIME_FL | \
F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \
- F2FS_CASEFOLD_FL)
+ F2FS_CASEFOLD_FL | F2FS_COMPR_FL | F2FS_NOCOMP_FL)
/* Flags that are appropriate for regular files (all but dir-specific ones). */
#define F2FS_REG_FLMASK (~(F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \
@@ -2443,6 +2530,8 @@ enum {
FI_PIN_FILE, /* indicate file should not be gced */
FI_ATOMIC_REVOKE_REQUEST, /* request to drop atomic data */
FI_VERITY_IN_PROGRESS, /* building fs-verity Merkle tree */
+ FI_COMPRESSED_FILE, /* indicate file's data can be compressed */
+ FI_MMAP_FILE, /* indicate file was mmapped */
};
static inline void __mark_inode_dirty_flag(struct inode *inode,
@@ -2459,6 +2548,7 @@ static inline void __mark_inode_dirty_flag(struct inode *inode,
case FI_DATA_EXIST:
case FI_INLINE_DOTS:
case FI_PIN_FILE:
+ case FI_COMPRESSED_FILE:
f2fs_mark_inode_dirty_sync(inode, true);
}
}
@@ -2614,16 +2704,27 @@ static inline int f2fs_has_inline_xattr(struct inode *inode)
return is_inode_flag_set(inode, FI_INLINE_XATTR);
}
+static inline int f2fs_compressed_file(struct inode *inode)
+{
+ return S_ISREG(inode->i_mode) &&
+ is_inode_flag_set(inode, FI_COMPRESSED_FILE);
+}
+
static inline unsigned int addrs_per_inode(struct inode *inode)
{
unsigned int addrs = CUR_ADDRS_PER_INODE(inode) -
get_inline_xattr_addrs(inode);
- return ALIGN_DOWN(addrs, 1);
+
+ if (!f2fs_compressed_file(inode))
+ return addrs;
+ return ALIGN_DOWN(addrs, F2FS_I(inode)->i_cluster_size);
}
static inline unsigned int addrs_per_block(struct inode *inode)
{
- return ALIGN_DOWN(DEF_ADDRS_PER_BLOCK, 1);
+ if (!f2fs_compressed_file(inode))
+ return DEF_ADDRS_PER_BLOCK;
+ return ALIGN_DOWN(DEF_ADDRS_PER_BLOCK, F2FS_I(inode)->i_cluster_size);
}
static inline void *inline_xattr_addr(struct inode *inode, struct page *page)
@@ -2656,6 +2757,11 @@ static inline int f2fs_has_inline_dots(struct inode *inode)
return is_inode_flag_set(inode, FI_INLINE_DOTS);
}
+static inline int f2fs_is_mmap_file(struct inode *inode)
+{
+ return is_inode_flag_set(inode, FI_MMAP_FILE);
+}
+
static inline bool f2fs_is_pinned_file(struct inode *inode)
{
return is_inode_flag_set(inode, FI_PIN_FILE);
@@ -2783,7 +2889,8 @@ static inline bool f2fs_may_extent_tree(struct inode *inode)
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
if (!test_opt(sbi, EXTENT_CACHE) ||
- is_inode_flag_set(inode, FI_NO_EXTENT))
+ is_inode_flag_set(inode, FI_NO_EXTENT) ||
+ is_inode_flag_set(inode, FI_COMPRESSED_FILE))
return false;
/*
@@ -2903,7 +3010,8 @@ static inline void verify_blkaddr(struct f2fs_sb_info *sbi,
static inline bool __is_valid_data_blkaddr(block_t blkaddr)
{
- if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR)
+ if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR ||
+ blkaddr == COMPRESS_ADDR)
return false;
return true;
}
@@ -3001,6 +3109,8 @@ ino_t f2fs_inode_by_name(struct inode *dir, const struct qstr *qstr,
struct page **page);
void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
struct page *page, struct inode *inode);
+bool f2fs_has_enough_room(struct inode *dir, struct page *ipage,
+ struct fscrypt_name *fname);
void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
const struct qstr *name, f2fs_hash_t name_hash,
unsigned int bit_pos);
@@ -3155,6 +3265,8 @@ void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
unsigned int val, int alloc);
void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi);
+int f2fs_check_write_pointer(struct f2fs_sb_info *sbi);
int f2fs_build_segment_manager(struct f2fs_sb_info *sbi);
void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi);
int __init f2fs_create_segment_manager_caches(void);
@@ -3205,10 +3317,13 @@ void f2fs_destroy_checkpoint_caches(void);
/*
* data.c
*/
-int f2fs_init_post_read_processing(void);
-void f2fs_destroy_post_read_processing(void);
+int __init f2fs_init_bioset(void);
+void f2fs_destroy_bioset(void);
+struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages, bool no_fail);
int f2fs_init_bio_entry_cache(void);
void f2fs_destroy_bio_entry_cache(void);
+void f2fs_submit_bio(struct f2fs_sb_info *sbi,
+ struct bio *bio, enum page_type type);
void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type);
void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
struct inode *inode, struct page *page,
@@ -3245,8 +3360,14 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
int create, int flag);
int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len);
+int f2fs_encrypt_one_page(struct f2fs_io_info *fio);
bool f2fs_should_update_inplace(struct inode *inode, struct f2fs_io_info *fio);
bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio);
+int f2fs_write_single_data_page(struct page *page, int *submitted,
+ struct bio **bio, sector_t *last_block,
+ struct writeback_control *wbc,
+ enum iostat_type io_type,
+ int compr_blocks);
void f2fs_invalidate_page(struct page *page, unsigned int offset,
unsigned int length);
int f2fs_release_page(struct page *page, gfp_t wait);
@@ -3256,6 +3377,10 @@ int f2fs_migrate_page(struct address_space *mapping, struct page *newpage,
#endif
bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len);
void f2fs_clear_page_cache_dirty_tag(struct page *page);
+int f2fs_init_post_read_processing(void);
+void f2fs_destroy_post_read_processing(void);
+int f2fs_init_post_read_wq(struct f2fs_sb_info *sbi);
+void f2fs_destroy_post_read_wq(struct f2fs_sb_info *sbi);
/*
* gc.c
@@ -3302,6 +3427,7 @@ struct f2fs_stat_info {
int nr_discard_cmd;
unsigned int undiscard_blks;
int inline_xattr, inline_inode, inline_dir, append, update, orphans;
+ int compr_inode, compr_blocks;
int aw_cnt, max_aw_cnt, vw_cnt, max_vw_cnt;
unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks;
unsigned int bimodal, avg_vblocks;
@@ -3333,7 +3459,7 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
#define stat_inc_cp_count(si) ((si)->cp_count++)
#define stat_inc_bg_cp_count(si) ((si)->bg_cp_count++)
#define stat_inc_call_count(si) ((si)->call_count++)
-#define stat_inc_bggc_count(sbi) ((sbi)->bg_gc++)
+#define stat_inc_bggc_count(si) ((si)->bg_gc++)
#define stat_io_skip_bggc_count(sbi) ((sbi)->io_skip_bggc++)
#define stat_other_skip_bggc_count(sbi) ((sbi)->other_skip_bggc++)
#define stat_inc_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]++)
@@ -3372,6 +3498,20 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
if (f2fs_has_inline_dentry(inode)) \
(atomic_dec(&F2FS_I_SB(inode)->inline_dir)); \
} while (0)
+#define stat_inc_compr_inode(inode) \
+ do { \
+ if (f2fs_compressed_file(inode)) \
+ (atomic_inc(&F2FS_I_SB(inode)->compr_inode)); \
+ } while (0)
+#define stat_dec_compr_inode(inode) \
+ do { \
+ if (f2fs_compressed_file(inode)) \
+ (atomic_dec(&F2FS_I_SB(inode)->compr_inode)); \
+ } while (0)
+#define stat_add_compr_blocks(inode, blocks) \
+ (atomic_add(blocks, &F2FS_I_SB(inode)->compr_blocks))
+#define stat_sub_compr_blocks(inode, blocks) \
+ (atomic_sub(blocks, &F2FS_I_SB(inode)->compr_blocks))
#define stat_inc_meta_count(sbi, blkaddr) \
do { \
if (blkaddr < SIT_I(sbi)->sit_base_addr) \
@@ -3389,13 +3529,9 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
((sbi)->block_count[(curseg)->alloc_type]++)
#define stat_inc_inplace_blocks(sbi) \
(atomic_inc(&(sbi)->inplace_count))
-#define stat_inc_atomic_write(inode) \
- (atomic_inc(&F2FS_I_SB(inode)->aw_cnt))
-#define stat_dec_atomic_write(inode) \
- (atomic_dec(&F2FS_I_SB(inode)->aw_cnt))
#define stat_update_max_atomic_write(inode) \
do { \
- int cur = atomic_read(&F2FS_I_SB(inode)->aw_cnt); \
+ int cur = F2FS_I_SB(inode)->atomic_files; \
int max = atomic_read(&F2FS_I_SB(inode)->max_aw_cnt); \
if (cur > max) \
atomic_set(&F2FS_I_SB(inode)->max_aw_cnt, cur); \
@@ -3447,6 +3583,7 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi);
void f2fs_destroy_stats(struct f2fs_sb_info *sbi);
void __init f2fs_create_root_stats(void);
void f2fs_destroy_root_stats(void);
+void f2fs_update_sit_info(struct f2fs_sb_info *sbi);
#else
#define stat_inc_cp_count(si) do { } while (0)
#define stat_inc_bg_cp_count(si) do { } while (0)
@@ -3456,8 +3593,8 @@ void f2fs_destroy_root_stats(void);
#define stat_other_skip_bggc_count(sbi) do { } while (0)
#define stat_inc_dirty_inode(sbi, type) do { } while (0)
#define stat_dec_dirty_inode(sbi, type) do { } while (0)
-#define stat_inc_total_hit(sb) do { } while (0)
-#define stat_inc_rbtree_node_hit(sb) do { } while (0)
+#define stat_inc_total_hit(sbi) do { } while (0)
+#define stat_inc_rbtree_node_hit(sbi) do { } while (0)
#define stat_inc_largest_node_hit(sbi) do { } while (0)
#define stat_inc_cached_node_hit(sbi) do { } while (0)
#define stat_inc_inline_xattr(inode) do { } while (0)
@@ -3466,6 +3603,10 @@ void f2fs_destroy_root_stats(void);
#define stat_dec_inline_inode(inode) do { } while (0)
#define stat_inc_inline_dir(inode) do { } while (0)
#define stat_dec_inline_dir(inode) do { } while (0)
+#define stat_inc_compr_inode(inode) do { } while (0)
+#define stat_dec_compr_inode(inode) do { } while (0)
+#define stat_add_compr_blocks(inode, blocks) do { } while (0)
+#define stat_sub_compr_blocks(inode, blocks) do { } while (0)
#define stat_inc_atomic_write(inode) do { } while (0)
#define stat_dec_atomic_write(inode) do { } while (0)
#define stat_update_max_atomic_write(inode) do { } while (0)
@@ -3485,6 +3626,7 @@ static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; }
static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { }
static inline void __init f2fs_create_root_stats(void) { }
static inline void f2fs_destroy_root_stats(void) { }
+static inline void update_sit_info(struct f2fs_sb_info *sbi) {}
#endif
extern const struct file_operations f2fs_dir_operations;
@@ -3513,6 +3655,7 @@ void f2fs_truncate_inline_inode(struct inode *inode,
int f2fs_read_inline_data(struct inode *inode, struct page *page);
int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page);
int f2fs_convert_inline_inode(struct inode *inode);
+int f2fs_try_convert_inline_dir(struct inode *dir, struct dentry *dentry);
int f2fs_write_inline_data(struct inode *inode, struct page *page);
bool f2fs_recover_inline_data(struct inode *inode, struct page *npage);
struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
@@ -3605,7 +3748,85 @@ static inline void f2fs_set_encrypted_inode(struct inode *inode)
*/
static inline bool f2fs_post_read_required(struct inode *inode)
{
- return f2fs_encrypted_file(inode) || fsverity_active(inode);
+ return f2fs_encrypted_file(inode) || fsverity_active(inode) ||
+ f2fs_compressed_file(inode);
+}
+
+/*
+ * compress.c
+ */
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+bool f2fs_is_compressed_page(struct page *page);
+struct page *f2fs_compress_control_page(struct page *page);
+int f2fs_prepare_compress_overwrite(struct inode *inode,
+ struct page **pagep, pgoff_t index, void **fsdata);
+bool f2fs_compress_write_end(struct inode *inode, void *fsdata,
+ pgoff_t index, unsigned copied);
+void f2fs_compress_write_end_io(struct bio *bio, struct page *page);
+bool f2fs_is_compress_backend_ready(struct inode *inode);
+void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity);
+bool f2fs_cluster_is_empty(struct compress_ctx *cc);
+bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index);
+void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct page *page);
+int f2fs_write_multi_pages(struct compress_ctx *cc,
+ int *submitted,
+ struct writeback_control *wbc,
+ enum iostat_type io_type);
+int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index);
+int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
+ unsigned nr_pages, sector_t *last_block_in_bio,
+ bool is_readahead);
+struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc);
+void f2fs_free_dic(struct decompress_io_ctx *dic);
+void f2fs_decompress_end_io(struct page **rpages,
+ unsigned int cluster_size, bool err, bool verity);
+int f2fs_init_compress_ctx(struct compress_ctx *cc);
+void f2fs_destroy_compress_ctx(struct compress_ctx *cc);
+void f2fs_init_compress_info(struct f2fs_sb_info *sbi);
+#else
+static inline bool f2fs_is_compressed_page(struct page *page) { return false; }
+static inline bool f2fs_is_compress_backend_ready(struct inode *inode)
+{
+ if (!f2fs_compressed_file(inode))
+ return true;
+ /* not support compression */
+ return false;
+}
+static inline struct page *f2fs_compress_control_page(struct page *page)
+{
+ WARN_ON_ONCE(1);
+ return ERR_PTR(-EINVAL);
+}
+#endif
+
+static inline void set_compress_context(struct inode *inode)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+ F2FS_I(inode)->i_compress_algorithm =
+ F2FS_OPTION(sbi).compress_algorithm;
+ F2FS_I(inode)->i_log_cluster_size =
+ F2FS_OPTION(sbi).compress_log_size;
+ F2FS_I(inode)->i_cluster_size =
+ 1 << F2FS_I(inode)->i_log_cluster_size;
+ F2FS_I(inode)->i_flags |= F2FS_COMPR_FL;
+ set_inode_flag(inode, FI_COMPRESSED_FILE);
+ stat_inc_compr_inode(inode);
+}
+
+static inline u64 f2fs_disable_compressed_file(struct inode *inode)
+{
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+
+ if (!f2fs_compressed_file(inode))
+ return 0;
+ if (fi->i_compr_blocks)
+ return fi->i_compr_blocks;
+
+ fi->i_flags &= ~F2FS_COMPR_FL;
+ clear_inode_flag(inode, FI_COMPRESSED_FILE);
+ stat_dec_compr_inode(inode);
+ return 0;
}
#define F2FS_FEATURE_FUNCS(name, flagname) \
@@ -3626,6 +3847,7 @@ F2FS_FEATURE_FUNCS(lost_found, LOST_FOUND);
F2FS_FEATURE_FUNCS(verity, VERITY);
F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM);
F2FS_FEATURE_FUNCS(casefold, CASEFOLD);
+F2FS_FEATURE_FUNCS(compression, COMPRESSION);
#ifdef CONFIG_BLK_DEV_ZONED
static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi,
@@ -3707,6 +3929,30 @@ static inline bool f2fs_may_encrypt(struct inode *inode)
#endif
}
+static inline bool f2fs_may_compress(struct inode *inode)
+{
+ if (IS_SWAPFILE(inode) || f2fs_is_pinned_file(inode) ||
+ f2fs_is_atomic_file(inode) ||
+ f2fs_is_volatile_file(inode))
+ return false;
+ return S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode);
+}
+
+static inline void f2fs_i_compr_blocks_update(struct inode *inode,
+ u64 blocks, bool add)
+{
+ int diff = F2FS_I(inode)->i_cluster_size - blocks;
+
+ if (add) {
+ F2FS_I(inode)->i_compr_blocks += diff;
+ stat_add_compr_blocks(inode, diff);
+ } else {
+ F2FS_I(inode)->i_compr_blocks -= diff;
+ stat_sub_compr_blocks(inode, diff);
+ }
+ f2fs_mark_inode_dirty_sync(inode, true);
+}
+
static inline int block_unaligned_IO(struct inode *inode,
struct kiocb *iocb, struct iov_iter *iter)
{
@@ -3738,6 +3984,8 @@ static inline bool f2fs_force_buffered_io(struct inode *inode,
return true;
if (f2fs_is_multi_device(sbi))
return true;
+ if (f2fs_compressed_file(inode))
+ return true;
/*
* for blkzoned device, fallback direct IO to buffered IO, so
* all IOs can be serialized by log-structured write.
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 85af112e868d..86ddbb55d2b1 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -50,8 +50,9 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
struct page *page = vmf->page;
struct inode *inode = file_inode(vmf->vma->vm_file);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct dnode_of_data dn = { .node_changed = false };
- int err;
+ struct dnode_of_data dn;
+ bool need_alloc = true;
+ int err = 0;
if (unlikely(f2fs_cp_error(sbi))) {
err = -EIO;
@@ -63,6 +64,26 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
goto err;
}
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+ if (f2fs_compressed_file(inode)) {
+ int ret = f2fs_is_compressed_cluster(inode, page->index);
+
+ if (ret < 0) {
+ err = ret;
+ goto err;
+ } else if (ret) {
+ if (ret < F2FS_I(inode)->i_cluster_size) {
+ err = -EAGAIN;
+ goto err;
+ }
+ need_alloc = false;
+ }
+ }
+#endif
+ /* should do out of any locked page */
+ if (need_alloc)
+ f2fs_balance_fs(sbi, true);
+
sb_start_pagefault(inode->i_sb);
f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
@@ -78,15 +99,17 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
goto out_sem;
}
- /* block allocation */
- __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true);
- set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = f2fs_get_block(&dn, page->index);
- f2fs_put_dnode(&dn);
- __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false);
- if (err) {
- unlock_page(page);
- goto out_sem;
+ if (need_alloc) {
+ /* block allocation */
+ __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true);
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ err = f2fs_get_block(&dn, page->index);
+ f2fs_put_dnode(&dn);
+ __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false);
+ if (err) {
+ unlock_page(page);
+ goto out_sem;
+ }
}
/* fill the page */
@@ -120,8 +143,6 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
out_sem:
up_read(&F2FS_I(inode)->i_mmap_sem);
- f2fs_balance_fs(sbi, dn.node_changed);
-
sb_end_pagefault(inode->i_sb);
err:
return block_page_mkwrite_return(err);
@@ -155,6 +176,8 @@ static inline enum cp_reason_type need_do_checkpoint(struct inode *inode)
if (!S_ISREG(inode->i_mode))
cp_reason = CP_NON_REGULAR;
+ else if (f2fs_compressed_file(inode))
+ cp_reason = CP_COMPRESSED;
else if (inode->i_nlink != 1)
cp_reason = CP_HARDLINK;
else if (is_sbi_flag_set(sbi, SBI_NEED_CP))
@@ -485,6 +508,9 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
return -EIO;
+ if (!f2fs_is_compress_backend_ready(inode))
+ return -EOPNOTSUPP;
+
/* we don't need to use inline_data strictly */
err = f2fs_convert_inline_inode(inode);
if (err)
@@ -492,6 +518,7 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
file_accessed(file);
vma->vm_ops = &f2fs_file_vm_ops;
+ set_inode_flag(inode, FI_MMAP_FILE);
return 0;
}
@@ -502,6 +529,9 @@ static int f2fs_file_open(struct inode *inode, struct file *filp)
if (err)
return err;
+ if (!f2fs_is_compress_backend_ready(inode))
+ return -EOPNOTSUPP;
+
err = fsverity_file_open(inode, filp);
if (err)
return err;
@@ -518,6 +548,9 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
int nr_free = 0, ofs = dn->ofs_in_node, len = count;
__le32 *addr;
int base = 0;
+ bool compressed_cluster = false;
+ int cluster_index = 0, valid_blocks = 0;
+ int cluster_size = F2FS_I(dn->inode)->i_cluster_size;
if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode))
base = get_extra_isize(dn->inode);
@@ -525,26 +558,43 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
raw_node = F2FS_NODE(dn->node_page);
addr = blkaddr_in_node(raw_node) + base + ofs;
- for (; count > 0; count--, addr++, dn->ofs_in_node++) {
+ /* Assumption: truncateion starts with cluster */
+ for (; count > 0; count--, addr++, dn->ofs_in_node++, cluster_index++) {
block_t blkaddr = le32_to_cpu(*addr);
+ if (f2fs_compressed_file(dn->inode) &&
+ !(cluster_index & (cluster_size - 1))) {
+ if (compressed_cluster)
+ f2fs_i_compr_blocks_update(dn->inode,
+ valid_blocks, false);
+ compressed_cluster = (blkaddr == COMPRESS_ADDR);
+ valid_blocks = 0;
+ }
+
if (blkaddr == NULL_ADDR)
continue;
dn->data_blkaddr = NULL_ADDR;
f2fs_set_data_blkaddr(dn);
- if (__is_valid_data_blkaddr(blkaddr) &&
- !f2fs_is_valid_blkaddr(sbi, blkaddr,
+ if (__is_valid_data_blkaddr(blkaddr)) {
+ if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
DATA_GENERIC_ENHANCE))
- continue;
+ continue;
+ if (compressed_cluster)
+ valid_blocks++;
+ }
- f2fs_invalidate_blocks(sbi, blkaddr);
if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page))
clear_inode_flag(dn->inode, FI_FIRST_BLOCK_WRITTEN);
+
+ f2fs_invalidate_blocks(sbi, blkaddr);
nr_free++;
}
+ if (compressed_cluster)
+ f2fs_i_compr_blocks_update(dn->inode, valid_blocks, false);
+
if (nr_free) {
pgoff_t fofs;
/*
@@ -587,6 +637,9 @@ static int truncate_partial_data_page(struct inode *inode, u64 from,
return 0;
}
+ if (f2fs_compressed_file(inode))
+ return 0;
+
page = f2fs_get_lock_data_page(inode, index, true);
if (IS_ERR(page))
return PTR_ERR(page) == -ENOENT ? 0 : PTR_ERR(page);
@@ -602,7 +655,7 @@ truncate_out:
return 0;
}
-int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock)
+static int do_truncate_blocks(struct inode *inode, u64 from, bool lock)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
@@ -667,6 +720,28 @@ free_partial:
return err;
}
+int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock)
+{
+ u64 free_from = from;
+
+ /*
+ * for compressed file, only support cluster size
+ * aligned truncation.
+ */
+ if (f2fs_compressed_file(inode)) {
+ size_t cluster_shift = PAGE_SHIFT +
+ F2FS_I(inode)->i_log_cluster_size;
+ size_t cluster_mask = (1 << cluster_shift) - 1;
+
+ free_from = from >> cluster_shift;
+ if (from & cluster_mask)
+ free_from++;
+ free_from <<= cluster_shift;
+ }
+
+ return do_truncate_blocks(inode, free_from, lock);
+}
+
int f2fs_truncate(struct inode *inode)
{
int err;
@@ -786,6 +861,10 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
return -EIO;
+ if ((attr->ia_valid & ATTR_SIZE) &&
+ !f2fs_is_compress_backend_ready(inode))
+ return -EOPNOTSUPP;
+
err = setattr_prepare(dentry, attr);
if (err)
return err;
@@ -1026,8 +1105,8 @@ next_dnode:
} else if (ret == -ENOENT) {
if (dn.max_level == 0)
return -ENOENT;
- done = min((pgoff_t)ADDRS_PER_BLOCK(inode) - dn.ofs_in_node,
- len);
+ done = min((pgoff_t)ADDRS_PER_BLOCK(inode) -
+ dn.ofs_in_node, len);
blkaddr += done;
do_replace += done;
goto next;
@@ -1190,13 +1269,13 @@ static int __exchange_data_block(struct inode *src_inode,
src_blkaddr = f2fs_kvzalloc(F2FS_I_SB(src_inode),
array_size(olen, sizeof(block_t)),
- GFP_KERNEL);
+ GFP_NOFS);
if (!src_blkaddr)
return -ENOMEM;
do_replace = f2fs_kvzalloc(F2FS_I_SB(src_inode),
array_size(olen, sizeof(int)),
- GFP_KERNEL);
+ GFP_NOFS);
if (!do_replace) {
kvfree(src_blkaddr);
return -ENOMEM;
@@ -1563,7 +1642,7 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
next_alloc:
if (has_not_enough_free_secs(sbi, 0,
GET_SEC_FROM_SEG(sbi, overprovision_segments(sbi)))) {
- mutex_lock(&sbi->gc_mutex);
+ down_write(&sbi->gc_lock);
err = f2fs_gc(sbi, true, false, NULL_SEGNO);
if (err && err != -ENODATA && err != -EAGAIN)
goto out_err;
@@ -1621,6 +1700,8 @@ static long f2fs_fallocate(struct file *file, int mode,
return -EIO;
if (!f2fs_is_checkpoint_ready(F2FS_I_SB(inode)))
return -ENOSPC;
+ if (!f2fs_is_compress_backend_ready(inode))
+ return -EOPNOTSUPP;
/* f2fs only support ->fallocate for regular file */
if (!S_ISREG(inode->i_mode))
@@ -1630,6 +1711,11 @@ static long f2fs_fallocate(struct file *file, int mode,
(mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE)))
return -EOPNOTSUPP;
+ if (f2fs_compressed_file(inode) &&
+ (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE |
+ FALLOC_FL_ZERO_RANGE | FALLOC_FL_INSERT_RANGE)))
+ return -EOPNOTSUPP;
+
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |
FALLOC_FL_INSERT_RANGE))
@@ -1719,7 +1805,40 @@ static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask)
return -ENOTEMPTY;
}
+ if (iflags & (F2FS_COMPR_FL | F2FS_NOCOMP_FL)) {
+ if (!f2fs_sb_has_compression(F2FS_I_SB(inode)))
+ return -EOPNOTSUPP;
+ if ((iflags & F2FS_COMPR_FL) && (iflags & F2FS_NOCOMP_FL))
+ return -EINVAL;
+ }
+
+ if ((iflags ^ fi->i_flags) & F2FS_COMPR_FL) {
+ if (S_ISREG(inode->i_mode) &&
+ (fi->i_flags & F2FS_COMPR_FL || i_size_read(inode) ||
+ F2FS_HAS_BLOCKS(inode)))
+ return -EINVAL;
+ if (iflags & F2FS_NOCOMP_FL)
+ return -EINVAL;
+ if (iflags & F2FS_COMPR_FL) {
+ int err = f2fs_convert_inline_inode(inode);
+
+ if (err)
+ return err;
+
+ if (!f2fs_may_compress(inode))
+ return -EINVAL;
+
+ set_compress_context(inode);
+ }
+ }
+ if ((iflags ^ fi->i_flags) & F2FS_NOCOMP_FL) {
+ if (fi->i_flags & F2FS_COMPR_FL)
+ return -EINVAL;
+ }
+
fi->i_flags = iflags | (fi->i_flags & ~mask);
+ f2fs_bug_on(F2FS_I_SB(inode), (fi->i_flags & F2FS_COMPR_FL) &&
+ (fi->i_flags & F2FS_NOCOMP_FL));
if (fi->i_flags & F2FS_PROJINHERIT_FL)
set_inode_flag(inode, FI_PROJ_INHERIT);
@@ -1745,11 +1864,13 @@ static const struct {
u32 iflag;
u32 fsflag;
} f2fs_fsflags_map[] = {
+ { F2FS_COMPR_FL, FS_COMPR_FL },
{ F2FS_SYNC_FL, FS_SYNC_FL },
{ F2FS_IMMUTABLE_FL, FS_IMMUTABLE_FL },
{ F2FS_APPEND_FL, FS_APPEND_FL },
{ F2FS_NODUMP_FL, FS_NODUMP_FL },
{ F2FS_NOATIME_FL, FS_NOATIME_FL },
+ { F2FS_NOCOMP_FL, FS_NOCOMP_FL },
{ F2FS_INDEX_FL, FS_INDEX_FL },
{ F2FS_DIRSYNC_FL, FS_DIRSYNC_FL },
{ F2FS_PROJINHERIT_FL, FS_PROJINHERIT_FL },
@@ -1757,11 +1878,13 @@ static const struct {
};
#define F2FS_GETTABLE_FS_FL ( \
+ FS_COMPR_FL | \
FS_SYNC_FL | \
FS_IMMUTABLE_FL | \
FS_APPEND_FL | \
FS_NODUMP_FL | \
FS_NOATIME_FL | \
+ FS_NOCOMP_FL | \
FS_INDEX_FL | \
FS_DIRSYNC_FL | \
FS_PROJINHERIT_FL | \
@@ -1772,11 +1895,13 @@ static const struct {
FS_CASEFOLD_FL)
#define F2FS_SETTABLE_FS_FL ( \
+ FS_COMPR_FL | \
FS_SYNC_FL | \
FS_IMMUTABLE_FL | \
FS_APPEND_FL | \
FS_NODUMP_FL | \
FS_NOATIME_FL | \
+ FS_NOCOMP_FL | \
FS_DIRSYNC_FL | \
FS_PROJINHERIT_FL | \
FS_CASEFOLD_FL)
@@ -1897,6 +2022,8 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
inode_lock(inode);
+ f2fs_disable_compressed_file(inode);
+
if (f2fs_is_atomic_file(inode)) {
if (is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST))
ret = -EINVAL;
@@ -1935,7 +2062,6 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
F2FS_I(inode)->inmem_task = current;
- stat_inc_atomic_write(inode);
stat_update_max_atomic_write(inode);
out:
inode_unlock(inode);
@@ -2324,12 +2450,12 @@ static int f2fs_ioc_gc(struct file *filp, unsigned long arg)
return ret;
if (!sync) {
- if (!mutex_trylock(&sbi->gc_mutex)) {
+ if (!down_write_trylock(&sbi->gc_lock)) {
ret = -EBUSY;
goto out;
}
} else {
- mutex_lock(&sbi->gc_mutex);
+ down_write(&sbi->gc_lock);
}
ret = f2fs_gc(sbi, sync, true, NULL_SEGNO);
@@ -2367,12 +2493,12 @@ static int f2fs_ioc_gc_range(struct file *filp, unsigned long arg)
do_more:
if (!range.sync) {
- if (!mutex_trylock(&sbi->gc_mutex)) {
+ if (!down_write_trylock(&sbi->gc_lock)) {
ret = -EBUSY;
goto out;
}
} else {
- mutex_lock(&sbi->gc_mutex);
+ down_write(&sbi->gc_lock);
}
ret = f2fs_gc(sbi, range.sync, true, GET_SEGNO(sbi, range.start));
@@ -2803,7 +2929,7 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg)
end_segno = min(start_segno + range.segments, dev_end_segno);
while (start_segno < end_segno) {
- if (!mutex_trylock(&sbi->gc_mutex)) {
+ if (!down_write_trylock(&sbi->gc_lock)) {
ret = -EBUSY;
goto out;
}
@@ -3098,10 +3224,16 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg)
ret = -EAGAIN;
goto out;
}
+
ret = f2fs_convert_inline_inode(inode);
if (ret)
goto out;
+ if (f2fs_disable_compressed_file(inode)) {
+ ret = -EOPNOTSUPP;
+ goto out;
+ }
+
set_inode_flag(inode, FI_PIN_FILE);
ret = F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN];
done:
@@ -3350,6 +3482,17 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
}
}
+static ssize_t f2fs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file_inode(file);
+
+ if (!f2fs_is_compress_backend_ready(inode))
+ return -EOPNOTSUPP;
+
+ return generic_file_read_iter(iocb, iter);
+}
+
static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
@@ -3361,6 +3504,9 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
goto out;
}
+ if (!f2fs_is_compress_backend_ready(inode))
+ return -EOPNOTSUPP;
+
if (iocb->ki_flags & IOCB_NOWAIT) {
if (!inode_trylock(inode)) {
ret = -EAGAIN;
@@ -3389,18 +3535,41 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
ret = -EAGAIN;
goto out;
}
- } else {
- preallocated = true;
- target_size = iocb->ki_pos + iov_iter_count(from);
+ goto write;
+ }
- err = f2fs_preallocate_blocks(iocb, from);
- if (err) {
- clear_inode_flag(inode, FI_NO_PREALLOC);
- inode_unlock(inode);
- ret = err;
- goto out;
- }
+ if (is_inode_flag_set(inode, FI_NO_PREALLOC))
+ goto write;
+
+ if (iocb->ki_flags & IOCB_DIRECT) {
+ /*
+ * Convert inline data for Direct I/O before entering
+ * f2fs_direct_IO().
+ */
+ err = f2fs_convert_inline_inode(inode);
+ if (err)
+ goto out_err;
+ /*
+ * If force_buffere_io() is true, we have to allocate
+ * blocks all the time, since f2fs_direct_IO will fall
+ * back to buffered IO.
+ */
+ if (!f2fs_force_buffered_io(inode, iocb, from) &&
+ allow_outplace_dio(inode, iocb, from))
+ goto write;
+ }
+ preallocated = true;
+ target_size = iocb->ki_pos + iov_iter_count(from);
+
+ err = f2fs_preallocate_blocks(iocb, from);
+ if (err) {
+out_err:
+ clear_inode_flag(inode, FI_NO_PREALLOC);
+ inode_unlock(inode);
+ ret = err;
+ goto out;
}
+write:
ret = __generic_file_write_iter(iocb, from);
clear_inode_flag(inode, FI_NO_PREALLOC);
@@ -3475,7 +3644,7 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
const struct file_operations f2fs_file_operations = {
.llseek = f2fs_llseek,
- .read_iter = generic_file_read_iter,
+ .read_iter = f2fs_file_read_iter,
.write_iter = f2fs_file_write_iter,
.open = f2fs_file_open,
.release = f2fs_release_file,
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index b3d399623290..db8725d473b5 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -78,18 +78,18 @@ static int gc_thread_func(void *data)
*/
if (sbi->gc_mode == GC_URGENT) {
wait_ms = gc_th->urgent_sleep_time;
- mutex_lock(&sbi->gc_mutex);
+ down_write(&sbi->gc_lock);
goto do_gc;
}
- if (!mutex_trylock(&sbi->gc_mutex)) {
+ if (!down_write_trylock(&sbi->gc_lock)) {
stat_other_skip_bggc_count(sbi);
goto next;
}
if (!is_idle(sbi, GC_TIME)) {
increase_sleep_time(gc_th, &wait_ms);
- mutex_unlock(&sbi->gc_mutex);
+ up_write(&sbi->gc_lock);
stat_io_skip_bggc_count(sbi);
goto next;
}
@@ -99,7 +99,7 @@ static int gc_thread_func(void *data)
else
increase_sleep_time(gc_th, &wait_ms);
do_gc:
- stat_inc_bggc_count(sbi);
+ stat_inc_bggc_count(sbi->stat_info);
/* if return value is not zero, no victim was selected */
if (f2fs_gc(sbi, test_opt(sbi, FORCE_FG_GC), true, NULL_SEGNO))
@@ -1049,8 +1049,10 @@ next_step:
if (phase == 3) {
inode = f2fs_iget(sb, dni.ino);
- if (IS_ERR(inode) || is_bad_inode(inode))
+ if (IS_ERR(inode) || is_bad_inode(inode)) {
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
continue;
+ }
if (!down_write_trylock(
&F2FS_I(inode)->i_gc_rwsem[WRITE])) {
@@ -1368,7 +1370,7 @@ stop:
reserved_segments(sbi),
prefree_segments(sbi));
- mutex_unlock(&sbi->gc_mutex);
+ up_write(&sbi->gc_lock);
put_gc_inode(&gc_list);
@@ -1407,9 +1409,9 @@ static int free_segment_range(struct f2fs_sb_info *sbi, unsigned int start,
.iroot = RADIX_TREE_INIT(gc_list.iroot, GFP_NOFS),
};
- mutex_lock(&sbi->gc_mutex);
+ down_write(&sbi->gc_lock);
do_garbage_collect(sbi, segno, &gc_list, FG_GC);
- mutex_unlock(&sbi->gc_mutex);
+ up_write(&sbi->gc_lock);
put_gc_inode(&gc_list);
if (get_valid_blocks(sbi, segno, true))
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 896db0416f0e..4167e5408151 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -368,7 +368,7 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
struct f2fs_dentry_ptr src, dst;
int err;
- page = f2fs_grab_cache_page(dir->i_mapping, 0, false);
+ page = f2fs_grab_cache_page(dir->i_mapping, 0, true);
if (!page) {
f2fs_put_page(ipage, 1);
return -ENOMEM;
@@ -530,7 +530,7 @@ recover:
return err;
}
-static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
+static int do_convert_inline_dir(struct inode *dir, struct page *ipage,
void *inline_dentry)
{
if (!F2FS_I(dir)->i_dir_level)
@@ -539,6 +539,44 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
return f2fs_move_rehashed_dirents(dir, ipage, inline_dentry);
}
+int f2fs_try_convert_inline_dir(struct inode *dir, struct dentry *dentry)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
+ struct page *ipage;
+ struct fscrypt_name fname;
+ void *inline_dentry = NULL;
+ int err = 0;
+
+ if (!f2fs_has_inline_dentry(dir))
+ return 0;
+
+ f2fs_lock_op(sbi);
+
+ err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &fname);
+ if (err)
+ goto out;
+
+ ipage = f2fs_get_node_page(sbi, dir->i_ino);
+ if (IS_ERR(ipage)) {
+ err = PTR_ERR(ipage);
+ goto out;
+ }
+
+ if (f2fs_has_enough_room(dir, ipage, &fname)) {
+ f2fs_put_page(ipage, 1);
+ goto out;
+ }
+
+ inline_dentry = inline_data_addr(dir, ipage);
+
+ err = do_convert_inline_dir(dir, ipage, inline_dentry);
+ if (!err)
+ f2fs_put_page(ipage, 1);
+out:
+ f2fs_unlock_op(sbi);
+ return err;
+}
+
int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
const struct qstr *orig_name,
struct inode *inode, nid_t ino, umode_t mode)
@@ -562,7 +600,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
bit_pos = f2fs_room_for_filename(d.bitmap, slots, d.max);
if (bit_pos >= d.max) {
- err = f2fs_convert_inline_dir(dir, ipage, inline_dentry);
+ err = do_convert_inline_dir(dir, ipage, inline_dentry);
if (err)
return err;
err = -EAGAIN;
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 502bd491336a..78c3f1d70f1d 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -200,6 +200,7 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
+ struct f2fs_inode *ri = F2FS_INODE(node_page);
unsigned long long iblocks;
iblocks = le64_to_cpu(F2FS_INODE(node_page)->i_blocks);
@@ -286,6 +287,19 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
return false;
}
+ if (f2fs_has_extra_attr(inode) && f2fs_sb_has_compression(sbi) &&
+ fi->i_flags & F2FS_COMPR_FL &&
+ F2FS_FITS_IN_INODE(ri, fi->i_extra_isize,
+ i_log_cluster_size)) {
+ if (ri->i_compress_algorithm >= COMPRESS_MAX)
+ return false;
+ if (le64_to_cpu(ri->i_compr_blocks) > inode->i_blocks)
+ return false;
+ if (ri->i_log_cluster_size < MIN_COMPRESS_LOG_SIZE ||
+ ri->i_log_cluster_size > MAX_COMPRESS_LOG_SIZE)
+ return false;
+ }
+
return true;
}
@@ -407,6 +421,18 @@ static int do_read_inode(struct inode *inode)
fi->i_crtime.tv_nsec = le32_to_cpu(ri->i_crtime_nsec);
}
+ if (f2fs_has_extra_attr(inode) && f2fs_sb_has_compression(sbi) &&
+ (fi->i_flags & F2FS_COMPR_FL)) {
+ if (F2FS_FITS_IN_INODE(ri, fi->i_extra_isize,
+ i_log_cluster_size)) {
+ fi->i_compr_blocks = le64_to_cpu(ri->i_compr_blocks);
+ fi->i_compress_algorithm = ri->i_compress_algorithm;
+ fi->i_log_cluster_size = ri->i_log_cluster_size;
+ fi->i_cluster_size = 1 << fi->i_log_cluster_size;
+ set_inode_flag(inode, FI_COMPRESSED_FILE);
+ }
+ }
+
F2FS_I(inode)->i_disk_time[0] = inode->i_atime;
F2FS_I(inode)->i_disk_time[1] = inode->i_ctime;
F2FS_I(inode)->i_disk_time[2] = inode->i_mtime;
@@ -416,6 +442,8 @@ static int do_read_inode(struct inode *inode)
stat_inc_inline_xattr(inode);
stat_inc_inline_inode(inode);
stat_inc_inline_dir(inode);
+ stat_inc_compr_inode(inode);
+ stat_add_compr_blocks(inode, F2FS_I(inode)->i_compr_blocks);
return 0;
}
@@ -569,6 +597,17 @@ void f2fs_update_inode(struct inode *inode, struct page *node_page)
ri->i_crtime_nsec =
cpu_to_le32(F2FS_I(inode)->i_crtime.tv_nsec);
}
+
+ if (f2fs_sb_has_compression(F2FS_I_SB(inode)) &&
+ F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize,
+ i_log_cluster_size)) {
+ ri->i_compr_blocks =
+ cpu_to_le64(F2FS_I(inode)->i_compr_blocks);
+ ri->i_compress_algorithm =
+ F2FS_I(inode)->i_compress_algorithm;
+ ri->i_log_cluster_size =
+ F2FS_I(inode)->i_log_cluster_size;
+ }
}
__set_inode_rdev(inode, ri);
@@ -711,6 +750,8 @@ no_delete:
stat_dec_inline_xattr(inode);
stat_dec_inline_dir(inode);
stat_dec_inline_inode(inode);
+ stat_dec_compr_inode(inode);
+ stat_sub_compr_blocks(inode, F2FS_I(inode)->i_compr_blocks);
if (likely(!f2fs_cp_error(sbi) &&
!is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index a1c507b0b4ac..2aa035422c0f 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -119,6 +119,13 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
if (F2FS_I(inode)->i_flags & F2FS_PROJINHERIT_FL)
set_inode_flag(inode, FI_PROJ_INHERIT);
+ if (f2fs_sb_has_compression(sbi)) {
+ /* Inherit the compression flag in directory */
+ if ((F2FS_I(dir)->i_flags & F2FS_COMPR_FL) &&
+ f2fs_may_compress(inode))
+ set_compress_context(inode);
+ }
+
f2fs_set_inode_flags(inode);
trace_f2fs_new_inode(inode, 0);
@@ -149,6 +156,9 @@ static inline int is_extension_exist(const unsigned char *s, const char *sub)
size_t sublen = strlen(sub);
int i;
+ if (sublen == 1 && *sub == '*')
+ return 1;
+
/*
* filename format of multimedia file should be defined as:
* "filename + '.' + extension + (optional: '.' + temp extension)".
@@ -262,6 +272,45 @@ int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name,
return 0;
}
+static void set_compress_inode(struct f2fs_sb_info *sbi, struct inode *inode,
+ const unsigned char *name)
+{
+ __u8 (*extlist)[F2FS_EXTENSION_LEN] = sbi->raw_super->extension_list;
+ unsigned char (*ext)[F2FS_EXTENSION_LEN];
+ unsigned int ext_cnt = F2FS_OPTION(sbi).compress_ext_cnt;
+ int i, cold_count, hot_count;
+
+ if (!f2fs_sb_has_compression(sbi) ||
+ is_inode_flag_set(inode, FI_COMPRESSED_FILE) ||
+ F2FS_I(inode)->i_flags & F2FS_NOCOMP_FL ||
+ !f2fs_may_compress(inode))
+ return;
+
+ down_read(&sbi->sb_lock);
+
+ cold_count = le32_to_cpu(sbi->raw_super->extension_count);
+ hot_count = sbi->raw_super->hot_ext_count;
+
+ for (i = cold_count; i < cold_count + hot_count; i++) {
+ if (is_extension_exist(name, extlist[i])) {
+ up_read(&sbi->sb_lock);
+ return;
+ }
+ }
+
+ up_read(&sbi->sb_lock);
+
+ ext = F2FS_OPTION(sbi).extensions;
+
+ for (i = 0; i < ext_cnt; i++) {
+ if (!is_extension_exist(name, ext[i]))
+ continue;
+
+ set_compress_context(inode);
+ return;
+ }
+}
+
static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
bool excl)
{
@@ -286,6 +335,8 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
if (!test_opt(sbi, DISABLE_EXT_IDENTIFY))
set_file_temperature(sbi, inode, dentry->d_name.name);
+ set_compress_inode(sbi, inode, dentry->d_name.name);
+
inode->i_op = &f2fs_file_inode_operations;
inode->i_fop = &f2fs_file_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
@@ -797,6 +848,7 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
if (whiteout) {
f2fs_i_links_write(inode, false);
+ inode->i_state |= I_LINKABLE;
*whiteout = inode;
} else {
d_tmpfile(dentry, inode);
@@ -849,12 +901,11 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *old_inode = d_inode(old_dentry);
struct inode *new_inode = d_inode(new_dentry);
struct inode *whiteout = NULL;
- struct page *old_dir_page;
+ struct page *old_dir_page = NULL;
struct page *old_page, *new_page = NULL;
struct f2fs_dir_entry *old_dir_entry = NULL;
struct f2fs_dir_entry *old_entry;
struct f2fs_dir_entry *new_entry;
- bool is_old_inline = f2fs_has_inline_dentry(old_dir);
int err;
if (unlikely(f2fs_cp_error(sbi)))
@@ -867,6 +918,26 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
F2FS_I(old_dentry->d_inode)->i_projid)))
return -EXDEV;
+ /*
+ * If new_inode is null, the below renaming flow will
+ * add a link in old_dir which can conver inline_dir.
+ * After then, if we failed to get the entry due to other
+ * reasons like ENOMEM, we had to remove the new entry.
+ * Instead of adding such the error handling routine, let's
+ * simply convert first here.
+ */
+ if (old_dir == new_dir && !new_inode) {
+ err = f2fs_try_convert_inline_dir(old_dir, new_dentry);
+ if (err)
+ return err;
+ }
+
+ if (flags & RENAME_WHITEOUT) {
+ err = f2fs_create_whiteout(old_dir, &whiteout);
+ if (err)
+ return err;
+ }
+
err = dquot_initialize(old_dir);
if (err)
goto out;
@@ -898,17 +969,11 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
}
}
- if (flags & RENAME_WHITEOUT) {
- err = f2fs_create_whiteout(old_dir, &whiteout);
- if (err)
- goto out_dir;
- }
-
if (new_inode) {
err = -ENOTEMPTY;
if (old_dir_entry && !f2fs_empty_dir(new_inode))
- goto out_whiteout;
+ goto out_dir;
err = -ENOENT;
new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name,
@@ -916,7 +981,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
if (!new_entry) {
if (IS_ERR(new_page))
err = PTR_ERR(new_page);
- goto out_whiteout;
+ goto out_dir;
}
f2fs_balance_fs(sbi, true);
@@ -928,6 +993,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
goto put_out_dir;
f2fs_set_link(new_dir, new_entry, new_page, old_inode);
+ new_page = NULL;
new_inode->i_ctime = current_time(new_inode);
down_write(&F2FS_I(new_inode)->i_sem);
@@ -948,33 +1014,11 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
err = f2fs_add_link(new_dentry, old_inode);
if (err) {
f2fs_unlock_op(sbi);
- goto out_whiteout;
+ goto out_dir;
}
if (old_dir_entry)
f2fs_i_links_write(new_dir, true);
-
- /*
- * old entry and new entry can locate in the same inline
- * dentry in inode, when attaching new entry in inline dentry,
- * it could force inline dentry conversion, after that,
- * old_entry and old_page will point to wrong address, in
- * order to avoid this, let's do the check and update here.
- */
- if (is_old_inline && !f2fs_has_inline_dentry(old_dir)) {
- f2fs_put_page(old_page, 0);
- old_page = NULL;
-
- old_entry = f2fs_find_entry(old_dir,
- &old_dentry->d_name, &old_page);
- if (!old_entry) {
- err = -ENOENT;
- if (IS_ERR(old_page))
- err = PTR_ERR(old_page);
- f2fs_unlock_op(sbi);
- goto out_whiteout;
- }
- }
}
down_write(&F2FS_I(old_inode)->i_sem);
@@ -989,9 +1033,9 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
f2fs_mark_inode_dirty_sync(old_inode, false);
f2fs_delete_entry(old_entry, old_page, old_dir, NULL);
+ old_page = NULL;
if (whiteout) {
- whiteout->i_state |= I_LINKABLE;
set_inode_flag(whiteout, FI_INC_LINK);
err = f2fs_add_link(old_dentry, whiteout);
if (err)
@@ -1025,17 +1069,15 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
put_out_dir:
f2fs_unlock_op(sbi);
- if (new_page)
- f2fs_put_page(new_page, 0);
-out_whiteout:
- if (whiteout)
- iput(whiteout);
+ f2fs_put_page(new_page, 0);
out_dir:
if (old_dir_entry)
f2fs_put_page(old_dir_page, 0);
out_old:
f2fs_put_page(old_page, 0);
out:
+ if (whiteout)
+ iput(whiteout);
return err;
}
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 76477f71d4ee..763d5c0951d1 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -723,6 +723,7 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
int ret = 0;
unsigned long s_flags = sbi->sb->s_flags;
bool need_writecp = false;
+ bool fix_curseg_write_pointer = false;
#ifdef CONFIG_QUOTA
int quota_enabled;
#endif
@@ -774,6 +775,8 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
sbi->sb->s_flags = s_flags;
}
skip:
+ fix_curseg_write_pointer = !check_only || list_empty(&inode_list);
+
destroy_fsync_dnodes(&inode_list, err);
destroy_fsync_dnodes(&tmp_inode_list, err);
@@ -784,9 +787,22 @@ skip:
if (err) {
truncate_inode_pages_final(NODE_MAPPING(sbi));
truncate_inode_pages_final(META_MAPPING(sbi));
- } else {
- clear_sbi_flag(sbi, SBI_POR_DOING);
}
+
+ /*
+ * If fsync data succeeds or there is no fsync data to recover,
+ * and the f2fs is not read only, check and fix zoned block devices'
+ * write pointer consistency.
+ */
+ if (!err && fix_curseg_write_pointer && !f2fs_readonly(sbi->sb) &&
+ f2fs_sb_has_blkzoned(sbi)) {
+ err = f2fs_fix_curseg_write_pointer(sbi);
+ ret = err;
+ }
+
+ if (!err)
+ clear_sbi_flag(sbi, SBI_POR_DOING);
+
mutex_unlock(&sbi->cp_mutex);
/* let's drop all the directory inodes for clean checkpoint */
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 56e81447e2f3..cf0eb002cfd4 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -334,7 +334,6 @@ void f2fs_drop_inmem_pages(struct inode *inode)
}
fi->i_gc_failures[GC_FAILURE_ATOMIC] = 0;
- stat_dec_atomic_write(inode);
spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
if (!list_empty(&fi->inmem_ilist))
@@ -505,7 +504,7 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
* dir/node pages without enough free segments.
*/
if (has_not_enough_free_secs(sbi, 0, 0)) {
- mutex_lock(&sbi->gc_mutex);
+ down_write(&sbi->gc_lock);
f2fs_gc(sbi, false, false, NULL_SEGNO);
}
}
@@ -2225,7 +2224,7 @@ void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
struct sit_info *sit_i = SIT_I(sbi);
f2fs_bug_on(sbi, addr == NULL_ADDR);
- if (addr == NEW_ADDR)
+ if (addr == NEW_ADDR || addr == COMPRESS_ADDR)
return;
invalidate_mapping_pages(META_MAPPING(sbi), addr, addr);
@@ -2861,9 +2860,9 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
if (sbi->discard_blks == 0)
goto out;
- mutex_lock(&sbi->gc_mutex);
+ down_write(&sbi->gc_lock);
err = f2fs_write_checkpoint(sbi, &cpc);
- mutex_unlock(&sbi->gc_mutex);
+ up_write(&sbi->gc_lock);
if (err)
goto out;
@@ -3036,7 +3035,8 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
if (fio->type == DATA) {
struct inode *inode = fio->page->mapping->host;
- if (is_cold_data(fio->page) || file_is_cold(inode))
+ if (is_cold_data(fio->page) || file_is_cold(inode) ||
+ f2fs_compressed_file(inode))
return CURSEG_COLD_DATA;
if (file_is_hot(inode) ||
is_inode_flag_set(inode, FI_HOT_DATA) ||
@@ -3289,7 +3289,7 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio)
stat_inc_inplace_blocks(fio->sbi);
- if (fio->bio)
+ if (fio->bio && !(SM_I(sbi)->ipu_policy & (1 << F2FS_IPU_NOCACHE)))
err = f2fs_merge_page_bio(fio);
else
err = f2fs_submit_page_bio(fio);
@@ -4368,6 +4368,263 @@ out:
return 0;
}
+#ifdef CONFIG_BLK_DEV_ZONED
+
+static int check_zone_write_pointer(struct f2fs_sb_info *sbi,
+ struct f2fs_dev_info *fdev,
+ struct blk_zone *zone)
+{
+ unsigned int wp_segno, wp_blkoff, zone_secno, zone_segno, segno;
+ block_t zone_block, wp_block, last_valid_block;
+ unsigned int log_sectors_per_block = sbi->log_blocksize - SECTOR_SHIFT;
+ int i, s, b, ret;
+ struct seg_entry *se;
+
+ if (zone->type != BLK_ZONE_TYPE_SEQWRITE_REQ)
+ return 0;
+
+ wp_block = fdev->start_blk + (zone->wp >> log_sectors_per_block);
+ wp_segno = GET_SEGNO(sbi, wp_block);
+ wp_blkoff = wp_block - START_BLOCK(sbi, wp_segno);
+ zone_block = fdev->start_blk + (zone->start >> log_sectors_per_block);
+ zone_segno = GET_SEGNO(sbi, zone_block);
+ zone_secno = GET_SEC_FROM_SEG(sbi, zone_segno);
+
+ if (zone_segno >= MAIN_SEGS(sbi))
+ return 0;
+
+ /*
+ * Skip check of zones cursegs point to, since
+ * fix_curseg_write_pointer() checks them.
+ */
+ for (i = 0; i < NO_CHECK_TYPE; i++)
+ if (zone_secno == GET_SEC_FROM_SEG(sbi,
+ CURSEG_I(sbi, i)->segno))
+ return 0;
+
+ /*
+ * Get last valid block of the zone.
+ */
+ last_valid_block = zone_block - 1;
+ for (s = sbi->segs_per_sec - 1; s >= 0; s--) {
+ segno = zone_segno + s;
+ se = get_seg_entry(sbi, segno);
+ for (b = sbi->blocks_per_seg - 1; b >= 0; b--)
+ if (f2fs_test_bit(b, se->cur_valid_map)) {
+ last_valid_block = START_BLOCK(sbi, segno) + b;
+ break;
+ }
+ if (last_valid_block >= zone_block)
+ break;
+ }
+
+ /*
+ * If last valid block is beyond the write pointer, report the
+ * inconsistency. This inconsistency does not cause write error
+ * because the zone will not be selected for write operation until
+ * it get discarded. Just report it.
+ */
+ if (last_valid_block >= wp_block) {
+ f2fs_notice(sbi, "Valid block beyond write pointer: "
+ "valid block[0x%x,0x%x] wp[0x%x,0x%x]",
+ GET_SEGNO(sbi, last_valid_block),
+ GET_BLKOFF_FROM_SEG0(sbi, last_valid_block),
+ wp_segno, wp_blkoff);
+ return 0;
+ }
+
+ /*
+ * If there is no valid block in the zone and if write pointer is
+ * not at zone start, reset the write pointer.
+ */
+ if (last_valid_block + 1 == zone_block && zone->wp != zone->start) {
+ f2fs_notice(sbi,
+ "Zone without valid block has non-zero write "
+ "pointer. Reset the write pointer: wp[0x%x,0x%x]",
+ wp_segno, wp_blkoff);
+ ret = __f2fs_issue_discard_zone(sbi, fdev->bdev, zone_block,
+ zone->len >> log_sectors_per_block);
+ if (ret) {
+ f2fs_err(sbi, "Discard zone failed: %s (errno=%d)",
+ fdev->path, ret);
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
+static struct f2fs_dev_info *get_target_zoned_dev(struct f2fs_sb_info *sbi,
+ block_t zone_blkaddr)
+{
+ int i;
+
+ for (i = 0; i < sbi->s_ndevs; i++) {
+ if (!bdev_is_zoned(FDEV(i).bdev))
+ continue;
+ if (sbi->s_ndevs == 1 || (FDEV(i).start_blk <= zone_blkaddr &&
+ zone_blkaddr <= FDEV(i).end_blk))
+ return &FDEV(i);
+ }
+
+ return NULL;
+}
+
+static int report_one_zone_cb(struct blk_zone *zone, unsigned int idx,
+ void *data) {
+ memcpy(data, zone, sizeof(struct blk_zone));
+ return 0;
+}
+
+static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type)
+{
+ struct curseg_info *cs = CURSEG_I(sbi, type);
+ struct f2fs_dev_info *zbd;
+ struct blk_zone zone;
+ unsigned int cs_section, wp_segno, wp_blkoff, wp_sector_off;
+ block_t cs_zone_block, wp_block;
+ unsigned int log_sectors_per_block = sbi->log_blocksize - SECTOR_SHIFT;
+ sector_t zone_sector;
+ int err;
+
+ cs_section = GET_SEC_FROM_SEG(sbi, cs->segno);
+ cs_zone_block = START_BLOCK(sbi, GET_SEG_FROM_SEC(sbi, cs_section));
+
+ zbd = get_target_zoned_dev(sbi, cs_zone_block);
+ if (!zbd)
+ return 0;
+
+ /* report zone for the sector the curseg points to */
+ zone_sector = (sector_t)(cs_zone_block - zbd->start_blk)
+ << log_sectors_per_block;
+ err = blkdev_report_zones(zbd->bdev, zone_sector, 1,
+ report_one_zone_cb, &zone);
+ if (err != 1) {
+ f2fs_err(sbi, "Report zone failed: %s errno=(%d)",
+ zbd->path, err);
+ return err;
+ }
+
+ if (zone.type != BLK_ZONE_TYPE_SEQWRITE_REQ)
+ return 0;
+
+ wp_block = zbd->start_blk + (zone.wp >> log_sectors_per_block);
+ wp_segno = GET_SEGNO(sbi, wp_block);
+ wp_blkoff = wp_block - START_BLOCK(sbi, wp_segno);
+ wp_sector_off = zone.wp & GENMASK(log_sectors_per_block - 1, 0);
+
+ if (cs->segno == wp_segno && cs->next_blkoff == wp_blkoff &&
+ wp_sector_off == 0)
+ return 0;
+
+ f2fs_notice(sbi, "Unaligned curseg[%d] with write pointer: "
+ "curseg[0x%x,0x%x] wp[0x%x,0x%x]",
+ type, cs->segno, cs->next_blkoff, wp_segno, wp_blkoff);
+
+ f2fs_notice(sbi, "Assign new section to curseg[%d]: "
+ "curseg[0x%x,0x%x]", type, cs->segno, cs->next_blkoff);
+ allocate_segment_by_default(sbi, type, true);
+
+ /* check consistency of the zone curseg pointed to */
+ if (check_zone_write_pointer(sbi, zbd, &zone))
+ return -EIO;
+
+ /* check newly assigned zone */
+ cs_section = GET_SEC_FROM_SEG(sbi, cs->segno);
+ cs_zone_block = START_BLOCK(sbi, GET_SEG_FROM_SEC(sbi, cs_section));
+
+ zbd = get_target_zoned_dev(sbi, cs_zone_block);
+ if (!zbd)
+ return 0;
+
+ zone_sector = (sector_t)(cs_zone_block - zbd->start_blk)
+ << log_sectors_per_block;
+ err = blkdev_report_zones(zbd->bdev, zone_sector, 1,
+ report_one_zone_cb, &zone);
+ if (err != 1) {
+ f2fs_err(sbi, "Report zone failed: %s errno=(%d)",
+ zbd->path, err);
+ return err;
+ }
+
+ if (zone.type != BLK_ZONE_TYPE_SEQWRITE_REQ)
+ return 0;
+
+ if (zone.wp != zone.start) {
+ f2fs_notice(sbi,
+ "New zone for curseg[%d] is not yet discarded. "
+ "Reset the zone: curseg[0x%x,0x%x]",
+ type, cs->segno, cs->next_blkoff);
+ err = __f2fs_issue_discard_zone(sbi, zbd->bdev,
+ zone_sector >> log_sectors_per_block,
+ zone.len >> log_sectors_per_block);
+ if (err) {
+ f2fs_err(sbi, "Discard zone failed: %s (errno=%d)",
+ zbd->path, err);
+ return err;
+ }
+ }
+
+ return 0;
+}
+
+int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi)
+{
+ int i, ret;
+
+ for (i = 0; i < NO_CHECK_TYPE; i++) {
+ ret = fix_curseg_write_pointer(sbi, i);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+struct check_zone_write_pointer_args {
+ struct f2fs_sb_info *sbi;
+ struct f2fs_dev_info *fdev;
+};
+
+static int check_zone_write_pointer_cb(struct blk_zone *zone, unsigned int idx,
+ void *data) {
+ struct check_zone_write_pointer_args *args;
+ args = (struct check_zone_write_pointer_args *)data;
+
+ return check_zone_write_pointer(args->sbi, args->fdev, zone);
+}
+
+int f2fs_check_write_pointer(struct f2fs_sb_info *sbi)
+{
+ int i, ret;
+ struct check_zone_write_pointer_args args;
+
+ for (i = 0; i < sbi->s_ndevs; i++) {
+ if (!bdev_is_zoned(FDEV(i).bdev))
+ continue;
+
+ args.sbi = sbi;
+ args.fdev = &FDEV(i);
+ ret = blkdev_report_zones(FDEV(i).bdev, 0, BLK_ALL_ZONES,
+ check_zone_write_pointer_cb, &args);
+ if (ret < 0)
+ return ret;
+ }
+
+ return 0;
+}
+#else
+int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi)
+{
+ return 0;
+}
+
+int f2fs_check_write_pointer(struct f2fs_sb_info *sbi)
+{
+ return 0;
+}
+#endif
+
/*
* Update min, max modified time for cost-benefit GC algorithm
*/
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index a95467b202ea..459dc3901a57 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -200,18 +200,6 @@ struct segment_allocation {
void (*allocate_segment)(struct f2fs_sb_info *, int, bool);
};
-/*
- * this value is set in page as a private data which indicate that
- * the page is atomically written, and it is in inmem_pages list.
- */
-#define ATOMIC_WRITTEN_PAGE ((unsigned long)-1)
-#define DUMMY_WRITTEN_PAGE ((unsigned long)-2)
-
-#define IS_ATOMIC_WRITTEN_PAGE(page) \
- (page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE)
-#define IS_DUMMY_WRITTEN_PAGE(page) \
- (page_private(page) == (unsigned long)DUMMY_WRITTEN_PAGE)
-
#define MAX_SKIP_GC_COUNT 16
struct inmem_pages {
@@ -619,8 +607,10 @@ static inline int utilization(struct f2fs_sb_info *sbi)
* threashold,
* F2FS_IPU_FSYNC - activated in fsync path only for high performance flash
* storages. IPU will be triggered only if the # of dirty
- * pages over min_fsync_blocks.
- * F2FS_IPUT_DISABLE - disable IPU. (=default option)
+ * pages over min_fsync_blocks. (=default option)
+ * F2FS_IPU_ASYNC - do IPU given by asynchronous write requests.
+ * F2FS_IPU_NOCACHE - disable IPU bio cache.
+ * F2FS_IPUT_DISABLE - disable IPU. (=default option in LFS mode)
*/
#define DEF_MIN_IPU_UTIL 70
#define DEF_MIN_FSYNC_BLOCKS 8
@@ -635,6 +625,7 @@ enum {
F2FS_IPU_SSR_UTIL,
F2FS_IPU_FSYNC,
F2FS_IPU_ASYNC,
+ F2FS_IPU_NOCACHE,
};
static inline unsigned int curseg_segno(struct f2fs_sb_info *sbi,
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 5111e1ffe58a..65a7a432dfee 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -141,6 +141,9 @@ enum {
Opt_checkpoint_disable_cap,
Opt_checkpoint_disable_cap_perc,
Opt_checkpoint_enable,
+ Opt_compress_algorithm,
+ Opt_compress_log_size,
+ Opt_compress_extension,
Opt_err,
};
@@ -203,6 +206,9 @@ static match_table_t f2fs_tokens = {
{Opt_checkpoint_disable_cap, "checkpoint=disable:%u"},
{Opt_checkpoint_disable_cap_perc, "checkpoint=disable:%u%%"},
{Opt_checkpoint_enable, "checkpoint=enable"},
+ {Opt_compress_algorithm, "compress_algorithm=%s"},
+ {Opt_compress_log_size, "compress_log_size=%u"},
+ {Opt_compress_extension, "compress_extension=%s"},
{Opt_err, NULL},
};
@@ -391,8 +397,9 @@ static int parse_options(struct super_block *sb, char *options)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
substring_t args[MAX_OPT_ARGS];
+ unsigned char (*ext)[F2FS_EXTENSION_LEN];
char *p, *name;
- int arg = 0;
+ int arg = 0, ext_cnt;
kuid_t uid;
kgid_t gid;
#ifdef CONFIG_QUOTA
@@ -810,6 +817,66 @@ static int parse_options(struct super_block *sb, char *options)
case Opt_checkpoint_enable:
clear_opt(sbi, DISABLE_CHECKPOINT);
break;
+ case Opt_compress_algorithm:
+ if (!f2fs_sb_has_compression(sbi)) {
+ f2fs_err(sbi, "Compression feature if off");
+ return -EINVAL;
+ }
+ name = match_strdup(&args[0]);
+ if (!name)
+ return -ENOMEM;
+ if (strlen(name) == 3 && !strcmp(name, "lzo")) {
+ F2FS_OPTION(sbi).compress_algorithm =
+ COMPRESS_LZO;
+ } else if (strlen(name) == 3 &&
+ !strcmp(name, "lz4")) {
+ F2FS_OPTION(sbi).compress_algorithm =
+ COMPRESS_LZ4;
+ } else {
+ kfree(name);
+ return -EINVAL;
+ }
+ kfree(name);
+ break;
+ case Opt_compress_log_size:
+ if (!f2fs_sb_has_compression(sbi)) {
+ f2fs_err(sbi, "Compression feature is off");
+ return -EINVAL;
+ }
+ if (args->from && match_int(args, &arg))
+ return -EINVAL;
+ if (arg < MIN_COMPRESS_LOG_SIZE ||
+ arg > MAX_COMPRESS_LOG_SIZE) {
+ f2fs_err(sbi,
+ "Compress cluster log size is out of range");
+ return -EINVAL;
+ }
+ F2FS_OPTION(sbi).compress_log_size = arg;
+ break;
+ case Opt_compress_extension:
+ if (!f2fs_sb_has_compression(sbi)) {
+ f2fs_err(sbi, "Compression feature is off");
+ return -EINVAL;
+ }
+ name = match_strdup(&args[0]);
+ if (!name)
+ return -ENOMEM;
+
+ ext = F2FS_OPTION(sbi).extensions;
+ ext_cnt = F2FS_OPTION(sbi).compress_ext_cnt;
+
+ if (strlen(name) >= F2FS_EXTENSION_LEN ||
+ ext_cnt >= COMPRESS_EXT_NUM) {
+ f2fs_err(sbi,
+ "invalid extension length/number");
+ kfree(name);
+ return -EINVAL;
+ }
+
+ strcpy(ext[ext_cnt], name);
+ F2FS_OPTION(sbi).compress_ext_cnt++;
+ kfree(name);
+ break;
default:
f2fs_err(sbi, "Unrecognized mount option \"%s\" or missing value",
p);
@@ -1125,6 +1192,8 @@ static void f2fs_put_super(struct super_block *sb)
f2fs_destroy_node_manager(sbi);
f2fs_destroy_segment_manager(sbi);
+ f2fs_destroy_post_read_wq(sbi);
+
kvfree(sbi->ckpt);
f2fs_unregister_sysfs(sbi);
@@ -1169,9 +1238,9 @@ int f2fs_sync_fs(struct super_block *sb, int sync)
cpc.reason = __get_cp_reason(sbi);
- mutex_lock(&sbi->gc_mutex);
+ down_write(&sbi->gc_lock);
err = f2fs_write_checkpoint(sbi, &cpc);
- mutex_unlock(&sbi->gc_mutex);
+ up_write(&sbi->gc_lock);
}
f2fs_trace_ios(NULL, 1);
@@ -1213,12 +1282,10 @@ static int f2fs_statfs_project(struct super_block *sb,
return PTR_ERR(dquot);
spin_lock(&dquot->dq_dqb_lock);
- limit = 0;
- if (dquot->dq_dqb.dqb_bsoftlimit)
- limit = dquot->dq_dqb.dqb_bsoftlimit;
- if (dquot->dq_dqb.dqb_bhardlimit &&
- (!limit || dquot->dq_dqb.dqb_bhardlimit < limit))
- limit = dquot->dq_dqb.dqb_bhardlimit;
+ limit = min_not_zero(dquot->dq_dqb.dqb_bsoftlimit,
+ dquot->dq_dqb.dqb_bhardlimit);
+ if (limit)
+ limit >>= sb->s_blocksize_bits;
if (limit && buf->f_blocks > limit) {
curblock = dquot->dq_dqb.dqb_curspace >> sb->s_blocksize_bits;
@@ -1228,12 +1295,8 @@ static int f2fs_statfs_project(struct super_block *sb,
(buf->f_blocks - curblock) : 0;
}
- limit = 0;
- if (dquot->dq_dqb.dqb_isoftlimit)
- limit = dquot->dq_dqb.dqb_isoftlimit;
- if (dquot->dq_dqb.dqb_ihardlimit &&
- (!limit || dquot->dq_dqb.dqb_ihardlimit < limit))
- limit = dquot->dq_dqb.dqb_ihardlimit;
+ limit = min_not_zero(dquot->dq_dqb.dqb_isoftlimit,
+ dquot->dq_dqb.dqb_ihardlimit);
if (limit && buf->f_files > limit) {
buf->f_files = limit;
@@ -1340,6 +1403,35 @@ static inline void f2fs_show_quota_options(struct seq_file *seq,
#endif
}
+static inline void f2fs_show_compress_options(struct seq_file *seq,
+ struct super_block *sb)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ char *algtype = "";
+ int i;
+
+ if (!f2fs_sb_has_compression(sbi))
+ return;
+
+ switch (F2FS_OPTION(sbi).compress_algorithm) {
+ case COMPRESS_LZO:
+ algtype = "lzo";
+ break;
+ case COMPRESS_LZ4:
+ algtype = "lz4";
+ break;
+ }
+ seq_printf(seq, ",compress_algorithm=%s", algtype);
+
+ seq_printf(seq, ",compress_log_size=%u",
+ F2FS_OPTION(sbi).compress_log_size);
+
+ for (i = 0; i < F2FS_OPTION(sbi).compress_ext_cnt; i++) {
+ seq_printf(seq, ",compress_extension=%s",
+ F2FS_OPTION(sbi).extensions[i]);
+ }
+}
+
static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
{
struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb);
@@ -1462,6 +1554,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
seq_printf(seq, ",fsync_mode=%s", "strict");
else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_NOBARRIER)
seq_printf(seq, ",fsync_mode=%s", "nobarrier");
+
+ f2fs_show_compress_options(seq, sbi->sb);
return 0;
}
@@ -1476,6 +1570,9 @@ static void default_options(struct f2fs_sb_info *sbi)
F2FS_OPTION(sbi).test_dummy_encryption = false;
F2FS_OPTION(sbi).s_resuid = make_kuid(&init_user_ns, F2FS_DEF_RESUID);
F2FS_OPTION(sbi).s_resgid = make_kgid(&init_user_ns, F2FS_DEF_RESGID);
+ F2FS_OPTION(sbi).compress_algorithm = COMPRESS_LZO;
+ F2FS_OPTION(sbi).compress_log_size = MIN_COMPRESS_LOG_SIZE;
+ F2FS_OPTION(sbi).compress_ext_cnt = 0;
set_opt(sbi, BG_GC);
set_opt(sbi, INLINE_XATTR);
@@ -1524,7 +1621,7 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
f2fs_update_time(sbi, DISABLE_TIME);
while (!f2fs_time_over(sbi, DISABLE_TIME)) {
- mutex_lock(&sbi->gc_mutex);
+ down_write(&sbi->gc_lock);
err = f2fs_gc(sbi, true, false, NULL_SEGNO);
if (err == -ENODATA) {
err = 0;
@@ -1546,7 +1643,7 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
goto restore_flag;
}
- mutex_lock(&sbi->gc_mutex);
+ down_write(&sbi->gc_lock);
cpc.reason = CP_PAUSE;
set_sbi_flag(sbi, SBI_CP_DISABLED);
err = f2fs_write_checkpoint(sbi, &cpc);
@@ -1558,7 +1655,7 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
spin_unlock(&sbi->stat_lock);
out_unlock:
- mutex_unlock(&sbi->gc_mutex);
+ up_write(&sbi->gc_lock);
restore_flag:
sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */
return err;
@@ -1566,12 +1663,12 @@ restore_flag:
static void f2fs_enable_checkpoint(struct f2fs_sb_info *sbi)
{
- mutex_lock(&sbi->gc_mutex);
+ down_write(&sbi->gc_lock);
f2fs_dirty_to_prefree(sbi);
clear_sbi_flag(sbi, SBI_CP_DISABLED);
set_sbi_flag(sbi, SBI_IS_DIRTY);
- mutex_unlock(&sbi->gc_mutex);
+ up_write(&sbi->gc_lock);
f2fs_sync_fs(sbi->sb, 1);
}
@@ -2158,7 +2255,7 @@ static int f2fs_dquot_commit(struct dquot *dquot)
struct f2fs_sb_info *sbi = F2FS_SB(dquot->dq_sb);
int ret;
- down_read(&sbi->quota_sem);
+ down_read_nested(&sbi->quota_sem, SINGLE_DEPTH_NESTING);
ret = dquot_commit(dquot);
if (ret < 0)
set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR);
@@ -2182,13 +2279,10 @@ static int f2fs_dquot_acquire(struct dquot *dquot)
static int f2fs_dquot_release(struct dquot *dquot)
{
struct f2fs_sb_info *sbi = F2FS_SB(dquot->dq_sb);
- int ret;
+ int ret = dquot_release(dquot);
- down_read(&sbi->quota_sem);
- ret = dquot_release(dquot);
if (ret < 0)
set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR);
- up_read(&sbi->quota_sem);
return ret;
}
@@ -2196,29 +2290,22 @@ static int f2fs_dquot_mark_dquot_dirty(struct dquot *dquot)
{
struct super_block *sb = dquot->dq_sb;
struct f2fs_sb_info *sbi = F2FS_SB(sb);
- int ret;
-
- down_read(&sbi->quota_sem);
- ret = dquot_mark_dquot_dirty(dquot);
+ int ret = dquot_mark_dquot_dirty(dquot);
/* if we are using journalled quota */
if (is_journalled_quota(sbi))
set_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH);
- up_read(&sbi->quota_sem);
return ret;
}
static int f2fs_dquot_commit_info(struct super_block *sb, int type)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
- int ret;
+ int ret = dquot_commit_info(sb, type);
- down_read(&sbi->quota_sem);
- ret = dquot_commit_info(sb, type);
if (ret < 0)
set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR);
- up_read(&sbi->quota_sem);
return ret;
}
@@ -3311,7 +3398,7 @@ try_onemore:
/* init f2fs-specific super block info */
sbi->valid_super_block = valid_super_block;
- mutex_init(&sbi->gc_mutex);
+ init_rwsem(&sbi->gc_lock);
mutex_init(&sbi->writepages);
mutex_init(&sbi->cp_mutex);
mutex_init(&sbi->resize_mutex);
@@ -3400,6 +3487,12 @@ try_onemore:
goto free_devices;
}
+ err = f2fs_init_post_read_wq(sbi);
+ if (err) {
+ f2fs_err(sbi, "Failed to initialize post read workqueue");
+ goto free_devices;
+ }
+
sbi->total_valid_node_count =
le32_to_cpu(sbi->ckpt->valid_node_count);
percpu_counter_set(&sbi->total_valid_inode_count,
@@ -3544,6 +3637,17 @@ try_onemore:
goto free_meta;
}
}
+
+ /*
+ * If the f2fs is not readonly and fsync data recovery succeeds,
+ * check zoned block devices' write pointer consistency.
+ */
+ if (!err && !f2fs_readonly(sb) && f2fs_sb_has_blkzoned(sbi)) {
+ err = f2fs_check_write_pointer(sbi);
+ if (err)
+ goto free_meta;
+ }
+
reset_checkpoint:
/* f2fs_recover_fsync_data() cleared this already */
clear_sbi_flag(sbi, SBI_POR_DOING);
@@ -3621,6 +3725,7 @@ free_nm:
f2fs_destroy_node_manager(sbi);
free_sm:
f2fs_destroy_segment_manager(sbi);
+ f2fs_destroy_post_read_wq(sbi);
free_devices:
destroy_device_list(sbi);
kvfree(sbi->ckpt);
@@ -3762,8 +3867,12 @@ static int __init init_f2fs_fs(void)
err = f2fs_init_bio_entry_cache();
if (err)
goto free_post_read;
+ err = f2fs_init_bioset();
+ if (err)
+ goto free_bio_enrty_cache;
return 0;
-
+free_bio_enrty_cache:
+ f2fs_destroy_bio_entry_cache();
free_post_read:
f2fs_destroy_post_read_processing();
free_root_stats:
@@ -3789,6 +3898,7 @@ fail:
static void __exit exit_f2fs_fs(void)
{
+ f2fs_destroy_bioset();
f2fs_destroy_bio_entry_cache();
f2fs_destroy_post_read_processing();
f2fs_destroy_root_stats();
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index 70945ceb9c0c..91d649790b1b 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -25,6 +25,9 @@ enum {
DCC_INFO, /* struct discard_cmd_control */
NM_INFO, /* struct f2fs_nm_info */
F2FS_SBI, /* struct f2fs_sb_info */
+#ifdef CONFIG_F2FS_STAT_FS
+ STAT_INFO, /* struct f2fs_stat_info */
+#endif
#ifdef CONFIG_F2FS_FAULT_INJECTION
FAULT_INFO_RATE, /* struct f2fs_fault_info */
FAULT_INFO_TYPE, /* struct f2fs_fault_info */
@@ -42,6 +45,9 @@ struct f2fs_attr {
int id;
};
+static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi, char *buf);
+
static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
{
if (struct_type == GC_THREAD)
@@ -59,41 +65,25 @@ static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
struct_type == FAULT_INFO_TYPE)
return (unsigned char *)&F2FS_OPTION(sbi).fault_info;
#endif
+#ifdef CONFIG_F2FS_STAT_FS
+ else if (struct_type == STAT_INFO)
+ return (unsigned char *)F2FS_STAT(sbi);
+#endif
return NULL;
}
static ssize_t dirty_segments_show(struct f2fs_attr *a,
struct f2fs_sb_info *sbi, char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%llu\n",
- (unsigned long long)(dirty_segments(sbi)));
+ return sprintf(buf, "%llu\n",
+ (unsigned long long)(dirty_segments(sbi)));
}
-static ssize_t unusable_show(struct f2fs_attr *a,
+static ssize_t free_segments_show(struct f2fs_attr *a,
struct f2fs_sb_info *sbi, char *buf)
{
- block_t unusable;
-
- if (test_opt(sbi, DISABLE_CHECKPOINT))
- unusable = sbi->unusable_block_count;
- else
- unusable = f2fs_get_unusable_blocks(sbi);
- return snprintf(buf, PAGE_SIZE, "%llu\n",
- (unsigned long long)unusable);
-}
-
-static ssize_t encoding_show(struct f2fs_attr *a,
- struct f2fs_sb_info *sbi, char *buf)
-{
-#ifdef CONFIG_UNICODE
- if (f2fs_sb_has_casefold(sbi))
- return snprintf(buf, PAGE_SIZE, "%s (%d.%d.%d)\n",
- sbi->s_encoding->charset,
- (sbi->s_encoding->version >> 16) & 0xff,
- (sbi->s_encoding->version >> 8) & 0xff,
- sbi->s_encoding->version & 0xff);
-#endif
- return snprintf(buf, PAGE_SIZE, "(none)");
+ return sprintf(buf, "%llu\n",
+ (unsigned long long)(free_segments(sbi)));
}
static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
@@ -102,10 +92,10 @@ static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
struct super_block *sb = sbi->sb;
if (!sb->s_bdev->bd_part)
- return snprintf(buf, PAGE_SIZE, "0\n");
+ return sprintf(buf, "0\n");
- return snprintf(buf, PAGE_SIZE, "%llu\n",
- (unsigned long long)(sbi->kbytes_written +
+ return sprintf(buf, "%llu\n",
+ (unsigned long long)(sbi->kbytes_written +
BD_PART_WRITTEN(sbi)));
}
@@ -116,7 +106,7 @@ static ssize_t features_show(struct f2fs_attr *a,
int len = 0;
if (!sb->s_bdev->bd_part)
- return snprintf(buf, PAGE_SIZE, "0\n");
+ return sprintf(buf, "0\n");
if (f2fs_sb_has_encrypt(sbi))
len += snprintf(buf, PAGE_SIZE - len, "%s",
@@ -154,6 +144,9 @@ static ssize_t features_show(struct f2fs_attr *a,
if (f2fs_sb_has_casefold(sbi))
len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
len ? ", " : "", "casefold");
+ if (f2fs_sb_has_compression(sbi))
+ len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len ? ", " : "", "compression");
len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
len ? ", " : "", "pin_file");
len += snprintf(buf + len, PAGE_SIZE - len, "\n");
@@ -163,9 +156,66 @@ static ssize_t features_show(struct f2fs_attr *a,
static ssize_t current_reserved_blocks_show(struct f2fs_attr *a,
struct f2fs_sb_info *sbi, char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%u\n", sbi->current_reserved_blocks);
+ return sprintf(buf, "%u\n", sbi->current_reserved_blocks);
+}
+
+static ssize_t unusable_show(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi, char *buf)
+{
+ block_t unusable;
+
+ if (test_opt(sbi, DISABLE_CHECKPOINT))
+ unusable = sbi->unusable_block_count;
+ else
+ unusable = f2fs_get_unusable_blocks(sbi);
+ return sprintf(buf, "%llu\n", (unsigned long long)unusable);
+}
+
+static ssize_t encoding_show(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi, char *buf)
+{
+#ifdef CONFIG_UNICODE
+ if (f2fs_sb_has_casefold(sbi))
+ return snprintf(buf, PAGE_SIZE, "%s (%d.%d.%d)\n",
+ sbi->s_encoding->charset,
+ (sbi->s_encoding->version >> 16) & 0xff,
+ (sbi->s_encoding->version >> 8) & 0xff,
+ sbi->s_encoding->version & 0xff);
+#endif
+ return sprintf(buf, "(none)");
}
+#ifdef CONFIG_F2FS_STAT_FS
+static ssize_t moved_blocks_foreground_show(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi, char *buf)
+{
+ struct f2fs_stat_info *si = F2FS_STAT(sbi);
+
+ return sprintf(buf, "%llu\n",
+ (unsigned long long)(si->tot_blks -
+ (si->bg_data_blks + si->bg_node_blks)));
+}
+
+static ssize_t moved_blocks_background_show(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi, char *buf)
+{
+ struct f2fs_stat_info *si = F2FS_STAT(sbi);
+
+ return sprintf(buf, "%llu\n",
+ (unsigned long long)(si->bg_data_blks + si->bg_node_blks));
+}
+
+static ssize_t avg_vblocks_show(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi, char *buf)
+{
+ struct f2fs_stat_info *si = F2FS_STAT(sbi);
+
+ si->dirty_count = dirty_segments(sbi);
+ f2fs_update_sit_info(sbi);
+ return sprintf(buf, "%llu\n", (unsigned long long)(si->avg_vblocks));
+}
+#endif
+
static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
struct f2fs_sb_info *sbi, char *buf)
{
@@ -199,7 +249,7 @@ static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
ui = (unsigned int *)(ptr + a->offset);
- return snprintf(buf, PAGE_SIZE, "%u\n", *ui);
+ return sprintf(buf, "%u\n", *ui);
}
static ssize_t __sbi_store(struct f2fs_attr *a,
@@ -389,6 +439,7 @@ enum feat_id {
FEAT_VERITY,
FEAT_SB_CHECKSUM,
FEAT_CASEFOLD,
+ FEAT_COMPRESSION,
};
static ssize_t f2fs_feature_show(struct f2fs_attr *a,
@@ -408,7 +459,8 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a,
case FEAT_VERITY:
case FEAT_SB_CHECKSUM:
case FEAT_CASEFOLD:
- return snprintf(buf, PAGE_SIZE, "supported\n");
+ case FEAT_COMPRESSION:
+ return sprintf(buf, "supported\n");
}
return 0;
}
@@ -437,6 +489,14 @@ static struct f2fs_attr f2fs_attr_##_name = { \
.id = _id, \
}
+#define F2FS_STAT_ATTR(_struct_type, _struct_name, _name, _elname) \
+static struct f2fs_attr f2fs_attr_##_name = { \
+ .attr = {.name = __stringify(_name), .mode = 0444 }, \
+ .show = f2fs_sbi_show, \
+ .struct_type = _struct_type, \
+ .offset = offsetof(struct _struct_name, _elname), \
+}
+
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_urgent_sleep_time,
urgent_sleep_time);
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_min_sleep_time, min_sleep_time);
@@ -478,11 +538,21 @@ F2FS_RW_ATTR(FAULT_INFO_RATE, f2fs_fault_info, inject_rate, inject_rate);
F2FS_RW_ATTR(FAULT_INFO_TYPE, f2fs_fault_info, inject_type, inject_type);
#endif
F2FS_GENERAL_RO_ATTR(dirty_segments);
+F2FS_GENERAL_RO_ATTR(free_segments);
F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes);
F2FS_GENERAL_RO_ATTR(features);
F2FS_GENERAL_RO_ATTR(current_reserved_blocks);
F2FS_GENERAL_RO_ATTR(unusable);
F2FS_GENERAL_RO_ATTR(encoding);
+#ifdef CONFIG_F2FS_STAT_FS
+F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, cp_foreground_calls, cp_count);
+F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, cp_background_calls, bg_cp_count);
+F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, gc_foreground_calls, call_count);
+F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, gc_background_calls, bg_gc);
+F2FS_GENERAL_RO_ATTR(moved_blocks_background);
+F2FS_GENERAL_RO_ATTR(moved_blocks_foreground);
+F2FS_GENERAL_RO_ATTR(avg_vblocks);
+#endif
#ifdef CONFIG_FS_ENCRYPTION
F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO);
@@ -503,6 +573,7 @@ F2FS_FEATURE_RO_ATTR(verity, FEAT_VERITY);
#endif
F2FS_FEATURE_RO_ATTR(sb_checksum, FEAT_SB_CHECKSUM);
F2FS_FEATURE_RO_ATTR(casefold, FEAT_CASEFOLD);
+F2FS_FEATURE_RO_ATTR(compression, FEAT_COMPRESSION);
#define ATTR_LIST(name) (&f2fs_attr_##name.attr)
static struct attribute *f2fs_attrs[] = {
@@ -543,12 +614,22 @@ static struct attribute *f2fs_attrs[] = {
ATTR_LIST(inject_type),
#endif
ATTR_LIST(dirty_segments),
+ ATTR_LIST(free_segments),
ATTR_LIST(unusable),
ATTR_LIST(lifetime_write_kbytes),
ATTR_LIST(features),
ATTR_LIST(reserved_blocks),
ATTR_LIST(current_reserved_blocks),
ATTR_LIST(encoding),
+#ifdef CONFIG_F2FS_STAT_FS
+ ATTR_LIST(cp_foreground_calls),
+ ATTR_LIST(cp_background_calls),
+ ATTR_LIST(gc_foreground_calls),
+ ATTR_LIST(gc_background_calls),
+ ATTR_LIST(moved_blocks_foreground),
+ ATTR_LIST(moved_blocks_background),
+ ATTR_LIST(avg_vblocks),
+#endif
NULL,
};
ATTRIBUTE_GROUPS(f2fs);
@@ -573,6 +654,7 @@ static struct attribute *f2fs_feat_attrs[] = {
#endif
ATTR_LIST(sb_checksum),
ATTR_LIST(casefold),
+ ATTR_LIST(compression),
NULL,
};
ATTRIBUTE_GROUPS(f2fs_feat);
@@ -733,10 +815,12 @@ int __init f2fs_init_sysfs(void)
ret = kobject_init_and_add(&f2fs_feat, &f2fs_feat_ktype,
NULL, "features");
- if (ret)
+ if (ret) {
+ kobject_put(&f2fs_feat);
kset_unregister(&f2fs_kset);
- else
+ } else {
f2fs_proc_root = proc_mkdir("fs/f2fs", NULL);
+ }
return ret;
}
@@ -757,8 +841,11 @@ int f2fs_register_sysfs(struct f2fs_sb_info *sbi)
init_completion(&sbi->s_kobj_unregister);
err = kobject_init_and_add(&sbi->s_kobj, &f2fs_sb_ktype, NULL,
"%s", sb->s_id);
- if (err)
+ if (err) {
+ kobject_put(&sbi->s_kobj);
+ wait_for_completion(&sbi->s_kobj_unregister);
return err;
+ }
if (f2fs_proc_root)
sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
@@ -786,4 +873,5 @@ void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi)
remove_proc_entry(sbi->sb->s_id, f2fs_proc_root);
}
kobject_del(&sbi->s_kobj);
+ kobject_put(&sbi->s_kobj);
}
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 5f04c5c810fb..594b05ae16c9 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -21,6 +21,7 @@
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <asm/unaligned.h>
+#include <linux/random.h>
#include <linux/iversion.h>
#include "fat.h"
@@ -521,7 +522,7 @@ int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
inode->i_uid = sbi->options.fs_uid;
inode->i_gid = sbi->options.fs_gid;
inode_inc_iversion(inode);
- inode->i_generation = get_seconds();
+ inode->i_generation = prandom_u32();
if ((de->attr & ATTR_DIR) && !IS_FREE(de->name)) {
inode->i_generation &= ~1;
diff --git a/fs/file.c b/fs/file.c
index 3da91a112bab..a364e1a9b7e8 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -642,7 +642,9 @@ out_unlock:
EXPORT_SYMBOL(__close_fd); /* for ksys_close() */
/*
- * variant of __close_fd that gets a ref on the file for later fput
+ * variant of __close_fd that gets a ref on the file for later fput.
+ * The caller must ensure that filp_close() called on the file, and then
+ * an fput().
*/
int __close_fd_get_file(unsigned int fd, struct file **res)
{
@@ -662,7 +664,7 @@ int __close_fd_get_file(unsigned int fd, struct file **res)
spin_unlock(&files->file_lock);
get_file(file);
*res = file;
- return filp_close(file, files);
+ return 0;
out_unlock:
spin_unlock(&files->file_lock);
@@ -706,9 +708,9 @@ void do_close_on_exec(struct files_struct *files)
spin_unlock(&files->file_lock);
}
-static struct file *__fget(unsigned int fd, fmode_t mask, unsigned int refs)
+static struct file *__fget_files(struct files_struct *files, unsigned int fd,
+ fmode_t mask, unsigned int refs)
{
- struct files_struct *files = current->files;
struct file *file;
rcu_read_lock();
@@ -729,6 +731,12 @@ loop:
return file;
}
+static inline struct file *__fget(unsigned int fd, fmode_t mask,
+ unsigned int refs)
+{
+ return __fget_files(current->files, fd, mask, refs);
+}
+
struct file *fget_many(unsigned int fd, unsigned int refs)
{
return __fget(fd, FMODE_PATH, refs);
@@ -746,6 +754,18 @@ struct file *fget_raw(unsigned int fd)
}
EXPORT_SYMBOL(fget_raw);
+struct file *fget_task(struct task_struct *task, unsigned int fd)
+{
+ struct file *file = NULL;
+
+ task_lock(task);
+ if (task->files)
+ file = __fget_files(task->files, fd, 0, 1);
+ task_unlock(task);
+
+ return file;
+}
+
/*
* Lightweight file lookup - no refcnt increment if fd table isn't shared.
*
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 335607b8c5c0..76ac9c7d32ec 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -2063,7 +2063,7 @@ void wb_workfn(struct work_struct *work)
struct bdi_writeback, dwork);
long pages_written;
- set_worker_desc("flush-%s", dev_name(wb->bdi->dev));
+ set_worker_desc("flush-%s", bdi_dev_name(wb->bdi));
current->flags |= PF_SWAPWRITE;
if (likely(!current_is_workqueue_rescuer() ||
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 9c6df721321a..ba83b49ce18c 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -183,14 +183,12 @@ static int gfs2_jdata_writepage(struct page *page, struct writeback_control *wbc
struct inode *inode = page->mapping->host;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
- int ret;
if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(ip->i_gl)))
goto out;
if (PageChecked(page) || current->journal_info)
goto out_ignore;
- ret = __gfs2_jdata_writepage(page, wbc);
- return ret;
+ return __gfs2_jdata_writepage(page, wbc);
out_ignore:
redirty_page_for_writepage(wbc, page);
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index eb9c0578978f..c8b62577e2f2 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -73,9 +73,6 @@
#include "bmap.h"
#include "util.h"
-#define IS_LEAF 1 /* Hashed (leaf) directory */
-#define IS_DINODE 2 /* Linear (stuffed dinode block) directory */
-
#define MAX_RA_BLOCKS 32 /* max read-ahead blocks */
#define gfs2_disk_hash2offset(h) (((u64)(h)) >> 1)
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index b7123de7c180..d0eceaff3cea 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -826,7 +826,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
memset(&gl->gl_lksb, 0, sizeof(struct dlm_lksb));
if (glops->go_flags & GLOF_LVB) {
- gl->gl_lksb.sb_lvbptr = kzalloc(GFS2_MIN_LVB_SIZE, GFP_NOFS);
+ gl->gl_lksb.sb_lvbptr = kzalloc(GDLM_LVB_SIZE, GFP_NOFS);
if (!gl->gl_lksb.sb_lvbptr) {
kmem_cache_free(cachep, gl);
return -ENOMEM;
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 4ede1f18de85..061d22e1ceb6 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -95,7 +95,7 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
/* A shortened, inline version of gfs2_trans_begin()
* tr->alloced is not set since the transaction structure is
* on the stack */
- tr.tr_reserved = 1 + gfs2_struct2blk(sdp, tr.tr_revokes, sizeof(u64));
+ tr.tr_reserved = 1 + gfs2_struct2blk(sdp, tr.tr_revokes);
tr.tr_ip = _RET_IP_;
if (gfs2_log_reserve(sdp, tr.tr_reserved) < 0)
return;
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 5f89c515f5bb..9fd88ed18807 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -387,8 +387,6 @@ struct gfs2_glock {
struct rhash_head gl_node;
};
-#define GFS2_MIN_LVB_SIZE 32 /* Min size of LVB that gfs2 supports */
-
enum {
GIF_INVALID = 0,
GIF_QD_LOCKED = 1,
@@ -505,6 +503,7 @@ struct gfs2_trans {
unsigned int tr_num_buf_rm;
unsigned int tr_num_databuf_rm;
unsigned int tr_num_revoke;
+ unsigned int tr_num_revoke_rm;
struct list_head tr_list;
struct list_head tr_databuf;
@@ -703,6 +702,7 @@ struct gfs2_sbd {
u32 sd_fsb2bb_shift;
u32 sd_diptrs; /* Number of pointers in a dinode */
u32 sd_inptrs; /* Number of pointers in a indirect block */
+ u32 sd_ldptrs; /* Number of pointers in a log descriptor block */
u32 sd_jbsize; /* Size of a journaled data block */
u32 sd_hash_bsize; /* sizeof(exhash block) */
u32 sd_hash_bsize_shift;
@@ -803,7 +803,7 @@ struct gfs2_sbd {
struct gfs2_trans *sd_log_tr;
unsigned int sd_log_blks_reserved;
- int sd_log_commited_revoke;
+ int sd_log_committed_revoke;
atomic_t sd_log_pinned;
unsigned int sd_log_num_revoke;
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index dafef10b91f1..2716d56ed0a0 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -136,7 +136,6 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
if (inode->i_state & I_NEW) {
struct gfs2_sbd *sdp = GFS2_SB(inode);
- ip->i_no_formal_ino = no_formal_ino;
error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl);
if (unlikely(error))
@@ -175,21 +174,22 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
gfs2_glock_put(io_gl);
io_gl = NULL;
+ /* Lowest possible timestamp; will be overwritten in gfs2_dinode_in. */
+ inode->i_atime.tv_sec = 1LL << (8 * sizeof(inode->i_atime.tv_sec) - 1);
+ inode->i_atime.tv_nsec = 0;
+
if (type == DT_UNKNOWN) {
/* Inode glock must be locked already */
error = gfs2_inode_refresh(GFS2_I(inode));
if (error)
goto fail_refresh;
} else {
+ ip->i_no_formal_ino = no_formal_ino;
inode->i_mode = DT2IF(type);
}
gfs2_set_iop(inode);
- /* Lowest possible timestamp; will be overwritten in gfs2_dinode_in. */
- inode->i_atime.tv_sec = 1LL << (8 * sizeof(inode->i_atime.tv_sec) - 1);
- inode->i_atime.tv_nsec = 0;
-
unlock_new_inode(inode);
}
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index eb3f2e7b8085..00a2e721a374 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -37,7 +37,6 @@ static void gfs2_log_shutdown(struct gfs2_sbd *sdp);
* gfs2_struct2blk - compute stuff
* @sdp: the filesystem
* @nstruct: the number of structures
- * @ssize: the size of the structures
*
* Compute the number of log descriptor blocks needed to hold a certain number
* of structures of a certain size.
@@ -45,18 +44,16 @@ static void gfs2_log_shutdown(struct gfs2_sbd *sdp);
* Returns: the number of blocks needed (minimum is always 1)
*/
-unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
- unsigned int ssize)
+unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct)
{
unsigned int blks;
unsigned int first, second;
blks = 1;
- first = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / ssize;
+ first = sdp->sd_ldptrs;
if (nstruct > first) {
- second = (sdp->sd_sb.sb_bsize -
- sizeof(struct gfs2_meta_header)) / ssize;
+ second = sdp->sd_inptrs;
blks += DIV_ROUND_UP(nstruct - first, second);
}
@@ -472,9 +469,8 @@ static unsigned int calc_reserved(struct gfs2_sbd *sdp)
reserved += DIV_ROUND_UP(dbuf, databuf_limit(sdp));
}
- if (sdp->sd_log_commited_revoke > 0)
- reserved += gfs2_struct2blk(sdp, sdp->sd_log_commited_revoke,
- sizeof(u64));
+ if (sdp->sd_log_committed_revoke > 0)
+ reserved += gfs2_struct2blk(sdp, sdp->sd_log_committed_revoke);
/* One for the overall header */
if (reserved)
reserved++;
@@ -829,7 +825,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags)
if (unlikely(state == SFS_FROZEN))
gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
gfs2_assert_withdraw(sdp,
- sdp->sd_log_num_revoke == sdp->sd_log_commited_revoke);
+ sdp->sd_log_num_revoke == sdp->sd_log_committed_revoke);
gfs2_ordered_write(sdp);
lops_before_commit(sdp, tr);
@@ -848,7 +844,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags)
gfs2_log_lock(sdp);
sdp->sd_log_head = sdp->sd_log_flush_head;
sdp->sd_log_blks_reserved = 0;
- sdp->sd_log_commited_revoke = 0;
+ sdp->sd_log_committed_revoke = 0;
spin_lock(&sdp->sd_ail_lock);
if (tr && !list_empty(&tr->tr_ail1_list)) {
@@ -899,6 +895,7 @@ static void gfs2_merge_trans(struct gfs2_trans *old, struct gfs2_trans *new)
old->tr_num_buf_rm += new->tr_num_buf_rm;
old->tr_num_databuf_rm += new->tr_num_databuf_rm;
old->tr_num_revoke += new->tr_num_revoke;
+ old->tr_num_revoke_rm += new->tr_num_revoke_rm;
list_splice_tail_init(&new->tr_databuf, &old->tr_databuf);
list_splice_tail_init(&new->tr_buf, &old->tr_buf);
@@ -920,7 +917,7 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
set_bit(TR_ATTACHED, &tr->tr_flags);
}
- sdp->sd_log_commited_revoke += tr->tr_num_revoke;
+ sdp->sd_log_committed_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm;
reserved = calc_reserved(sdp);
maxres = sdp->sd_log_blks_reserved + tr->tr_reserved;
gfs2_assert_withdraw(sdp, maxres >= reserved);
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index 2ff163a8dce1..c0a65e5a126b 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -60,9 +60,9 @@ static inline void gfs2_ordered_add_inode(struct gfs2_inode *ip)
spin_unlock(&sdp->sd_ordered_lock);
}
}
+
extern void gfs2_ordered_del_inode(struct gfs2_inode *ip);
-extern unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
- unsigned int ssize);
+extern unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct);
extern void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks);
extern int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks);
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 55fed7daf2b1..d9431724b788 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -259,7 +259,7 @@ static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno,
struct super_block *sb = sdp->sd_vfs;
struct bio *bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
- bio->bi_iter.bi_sector = blkno * (sb->s_blocksize >> 9);
+ bio->bi_iter.bi_sector = blkno << (sb->s_blocksize_bits - 9);
bio_set_dev(bio, sb->s_bdev);
bio->bi_end_io = end_io;
bio->bi_private = sdp;
@@ -472,6 +472,20 @@ static void gfs2_jhead_process_page(struct gfs2_jdesc *jd, unsigned long index,
put_page(page); /* Once more for find_or_create_page */
}
+static struct bio *gfs2_chain_bio(struct bio *prev, unsigned int nr_iovecs)
+{
+ struct bio *new;
+
+ new = bio_alloc(GFP_NOIO, nr_iovecs);
+ bio_copy_dev(new, prev);
+ new->bi_iter.bi_sector = bio_end_sector(prev);
+ new->bi_opf = prev->bi_opf;
+ new->bi_write_hint = prev->bi_write_hint;
+ bio_chain(new, prev);
+ submit_bio(prev);
+ return new;
+}
+
/**
* gfs2_find_jhead - find the head of a log
* @jd: The journal descriptor
@@ -488,15 +502,15 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head,
struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
struct address_space *mapping = jd->jd_inode->i_mapping;
unsigned int block = 0, blocks_submitted = 0, blocks_read = 0;
- unsigned int bsize = sdp->sd_sb.sb_bsize;
+ unsigned int bsize = sdp->sd_sb.sb_bsize, off;
unsigned int bsize_shift = sdp->sd_sb.sb_bsize_shift;
unsigned int shift = PAGE_SHIFT - bsize_shift;
- unsigned int readhead_blocks = BIO_MAX_PAGES << shift;
+ unsigned int readahead_blocks = BIO_MAX_PAGES << shift;
struct gfs2_journal_extent *je;
int sz, ret = 0;
struct bio *bio = NULL;
struct page *page = NULL;
- bool done = false;
+ bool bio_chained = false, done = false;
errseq_t since;
memset(head, 0, sizeof(*head));
@@ -505,9 +519,9 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head,
since = filemap_sample_wb_err(mapping);
list_for_each_entry(je, &jd->extent_list, list) {
- for (; block < je->lblock + je->blocks; block++) {
- u64 dblock;
+ u64 dblock = je->dblock;
+ for (; block < je->lblock + je->blocks; block++, dblock++) {
if (!page) {
page = find_or_create_page(mapping,
block >> shift, GFP_NOFS);
@@ -516,35 +530,41 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head,
done = true;
goto out;
}
+ off = 0;
}
- if (bio) {
- unsigned int off;
-
- off = (block << bsize_shift) & ~PAGE_MASK;
+ if (!bio || (bio_chained && !off)) {
+ /* start new bio */
+ } else {
sz = bio_add_page(bio, page, bsize, off);
- if (sz == bsize) { /* block added */
- if (off + bsize == PAGE_SIZE) {
- page = NULL;
- goto page_added;
- }
- continue;
+ if (sz == bsize)
+ goto block_added;
+ if (off) {
+ unsigned int blocks =
+ (PAGE_SIZE - off) >> bsize_shift;
+
+ bio = gfs2_chain_bio(bio, blocks);
+ bio_chained = true;
+ goto add_block_to_new_bio;
}
+ }
+
+ if (bio) {
blocks_submitted = block + 1;
submit_bio(bio);
- bio = NULL;
}
- dblock = je->dblock + (block - je->lblock);
bio = gfs2_log_alloc_bio(sdp, dblock, gfs2_end_log_read);
bio->bi_opf = REQ_OP_READ;
- sz = bio_add_page(bio, page, bsize, 0);
- gfs2_assert_warn(sdp, sz == bsize);
- if (bsize == PAGE_SIZE)
+ bio_chained = false;
+add_block_to_new_bio:
+ sz = bio_add_page(bio, page, bsize, off);
+ BUG_ON(sz != bsize);
+block_added:
+ off += bsize;
+ if (off == PAGE_SIZE)
page = NULL;
-
-page_added:
- if (blocks_submitted < blocks_read + readhead_blocks) {
+ if (blocks_submitted < blocks_read + readahead_blocks) {
/* Keep at least one bio in flight */
continue;
}
@@ -846,7 +866,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
if (!sdp->sd_log_num_revoke)
return;
- length = gfs2_struct2blk(sdp, sdp->sd_log_num_revoke, sizeof(u64));
+ length = gfs2_struct2blk(sdp, sdp->sd_log_num_revoke);
page = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_REVOKE, length, sdp->sd_log_num_revoke);
offset = sizeof(struct gfs2_log_descriptor);
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index e8b7b0ce8404..b3e904bcc02c 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -298,6 +298,8 @@ static int gfs2_read_sb(struct gfs2_sbd *sdp, int silent)
sizeof(struct gfs2_dinode)) / sizeof(u64);
sdp->sd_inptrs = (sdp->sd_sb.sb_bsize -
sizeof(struct gfs2_meta_header)) / sizeof(u64);
+ sdp->sd_ldptrs = (sdp->sd_sb.sb_bsize -
+ sizeof(struct gfs2_log_descriptor)) / sizeof(u64);
sdp->sd_jbsize = sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header);
sdp->sd_hash_bsize = sdp->sd_sb.sb_bsize / 2;
sdp->sd_hash_bsize_shift = sdp->sd_sb.sb_bsize_shift - 1;
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 2466bb44a23c..e7bf91ec231c 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -36,16 +36,6 @@
#define BFITNOENT ((u32)~0)
#define NO_BLOCK ((u64)~0)
-#if BITS_PER_LONG == 32
-#define LBITMASK (0x55555555UL)
-#define LBITSKIP55 (0x55555555UL)
-#define LBITSKIP00 (0x00000000UL)
-#else
-#define LBITMASK (0x5555555555555555UL)
-#define LBITSKIP55 (0x5555555555555555UL)
-#define LBITSKIP00 (0x0000000000000000UL)
-#endif
-
/*
* These routines are used by the resource group routines (rgrp.c)
* to keep track of block allocation. Each block is represented by two
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index 9d4227330de4..a685637a5b55 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -49,8 +49,7 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
if (blocks)
tr->tr_reserved += 6 + blocks;
if (revokes)
- tr->tr_reserved += gfs2_struct2blk(sdp, revokes,
- sizeof(u64));
+ tr->tr_reserved += gfs2_struct2blk(sdp, revokes);
INIT_LIST_HEAD(&tr->tr_databuf);
INIT_LIST_HEAD(&tr->tr_buf);
@@ -77,10 +76,10 @@ static void gfs2_print_trans(struct gfs2_sbd *sdp, const struct gfs2_trans *tr)
fs_warn(sdp, "blocks=%u revokes=%u reserved=%u touched=%u\n",
tr->tr_blocks, tr->tr_revokes, tr->tr_reserved,
test_bit(TR_TOUCHED, &tr->tr_flags));
- fs_warn(sdp, "Buf %u/%u Databuf %u/%u Revoke %u\n",
+ fs_warn(sdp, "Buf %u/%u Databuf %u/%u Revoke %u/%u\n",
tr->tr_num_buf_new, tr->tr_num_buf_rm,
tr->tr_num_databuf_new, tr->tr_num_databuf_rm,
- tr->tr_num_revoke);
+ tr->tr_num_revoke, tr->tr_num_revoke_rm);
}
void gfs2_trans_end(struct gfs2_sbd *sdp)
@@ -265,7 +264,7 @@ void gfs2_trans_remove_revoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len)
if (bd->bd_gl)
gfs2_glock_remove_revoke(bd->bd_gl);
kmem_cache_free(gfs2_bufdata_cachep, bd);
- tr->tr_num_revoke--;
+ tr->tr_num_revoke_rm++;
if (--n == 0)
break;
}
diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h
index 6d0783e2e276..f71c384064c8 100644
--- a/fs/hfs/hfs_fs.h
+++ b/fs/hfs/hfs_fs.h
@@ -242,19 +242,35 @@ extern void hfs_mark_mdb_dirty(struct super_block *sb);
/*
* There are two time systems. Both are based on seconds since
* a particular time/date.
- * Unix: unsigned lil-endian since 00:00 GMT, Jan. 1, 1970
+ * Unix: signed little-endian since 00:00 GMT, Jan. 1, 1970
* mac: unsigned big-endian since 00:00 GMT, Jan. 1, 1904
*
+ * HFS implementations are highly inconsistent, this one matches the
+ * traditional behavior of 64-bit Linux, giving the most useful
+ * time range between 1970 and 2106, by treating any on-disk timestamp
+ * under HFS_UTC_OFFSET (Jan 1 1970) as a time between 2040 and 2106.
*/
-#define __hfs_u_to_mtime(sec) cpu_to_be32(sec + 2082844800U - sys_tz.tz_minuteswest * 60)
-#define __hfs_m_to_utime(sec) (be32_to_cpu(sec) - 2082844800U + sys_tz.tz_minuteswest * 60)
+#define HFS_UTC_OFFSET 2082844800U
+static inline time64_t __hfs_m_to_utime(__be32 mt)
+{
+ time64_t ut = (u32)(be32_to_cpu(mt) - HFS_UTC_OFFSET);
+
+ return ut + sys_tz.tz_minuteswest * 60;
+}
+
+static inline __be32 __hfs_u_to_mtime(time64_t ut)
+{
+ ut -= sys_tz.tz_minuteswest * 60;
+
+ return cpu_to_be32(lower_32_bits(ut) + HFS_UTC_OFFSET);
+}
#define HFS_I(inode) (container_of(inode, struct hfs_inode_info, vfs_inode))
#define HFS_SB(sb) ((struct hfs_sb_info *)(sb)->s_fs_info)
-#define hfs_m_to_utime(time) (struct timespec){ .tv_sec = __hfs_m_to_utime(time) }
-#define hfs_u_to_mtime(time) __hfs_u_to_mtime((time).tv_sec)
-#define hfs_mtime() __hfs_u_to_mtime(get_seconds())
+#define hfs_m_to_utime(time) (struct timespec64){ .tv_sec = __hfs_m_to_utime(time) }
+#define hfs_u_to_mtime(time) __hfs_u_to_mtime((time).tv_sec)
+#define hfs_mtime() __hfs_u_to_mtime(ktime_get_real_seconds())
static inline const char *hfs_mdb_name(struct super_block *sb)
{
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index da243c84e93b..2f224b98ee94 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -351,7 +351,7 @@ static int hfs_read_inode(struct inode *inode, void *data)
inode->i_mode &= ~hsb->s_file_umask;
inode->i_mode |= S_IFREG;
inode->i_ctime = inode->i_atime = inode->i_mtime =
- timespec_to_timespec64(hfs_m_to_utime(rec->file.MdDat));
+ hfs_m_to_utime(rec->file.MdDat);
inode->i_op = &hfs_file_inode_operations;
inode->i_fop = &hfs_file_operations;
inode->i_mapping->a_ops = &hfs_aops;
@@ -362,7 +362,7 @@ static int hfs_read_inode(struct inode *inode, void *data)
HFS_I(inode)->fs_blocks = 0;
inode->i_mode = S_IFDIR | (S_IRWXUGO & ~hsb->s_dir_umask);
inode->i_ctime = inode->i_atime = inode->i_mtime =
- timespec_to_timespec64(hfs_m_to_utime(rec->dir.MdDat));
+ hfs_m_to_utime(rec->dir.MdDat);
inode->i_op = &hfs_dir_inode_operations;
inode->i_fop = &hfs_dir_operations;
break;
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index b8471bf05def..3b03fff68543 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -533,13 +533,31 @@ int hfsplus_submit_bio(struct super_block *sb, sector_t sector, void *buf,
void **data, int op, int op_flags);
int hfsplus_read_wrapper(struct super_block *sb);
-/* time macros */
-#define __hfsp_mt2ut(t) (be32_to_cpu(t) - 2082844800U)
-#define __hfsp_ut2mt(t) (cpu_to_be32(t + 2082844800U))
+/*
+ * time helpers: convert between 1904-base and 1970-base timestamps
+ *
+ * HFS+ implementations are highly inconsistent, this one matches the
+ * traditional behavior of 64-bit Linux, giving the most useful
+ * time range between 1970 and 2106, by treating any on-disk timestamp
+ * under HFSPLUS_UTC_OFFSET (Jan 1 1970) as a time between 2040 and 2106.
+ */
+#define HFSPLUS_UTC_OFFSET 2082844800U
+
+static inline time64_t __hfsp_mt2ut(__be32 mt)
+{
+ time64_t ut = (u32)(be32_to_cpu(mt) - HFSPLUS_UTC_OFFSET);
+
+ return ut;
+}
+
+static inline __be32 __hfsp_ut2mt(time64_t ut)
+{
+ return cpu_to_be32(lower_32_bits(ut) + HFSPLUS_UTC_OFFSET);
+}
/* compatibility */
-#define hfsp_mt2ut(t) (struct timespec){ .tv_sec = __hfsp_mt2ut(t) }
+#define hfsp_mt2ut(t) (struct timespec64){ .tv_sec = __hfsp_mt2ut(t) }
#define hfsp_ut2mt(t) __hfsp_ut2mt((t).tv_sec)
-#define hfsp_now2mt() __hfsp_ut2mt(get_seconds())
+#define hfsp_now2mt() __hfsp_ut2mt(ktime_get_real_seconds())
#endif
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index d131c8ea7eb6..94bd83b36644 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -504,9 +504,9 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd)
hfsplus_get_perms(inode, &folder->permissions, 1);
set_nlink(inode, 1);
inode->i_size = 2 + be32_to_cpu(folder->valence);
- inode->i_atime = timespec_to_timespec64(hfsp_mt2ut(folder->access_date));
- inode->i_mtime = timespec_to_timespec64(hfsp_mt2ut(folder->content_mod_date));
- inode->i_ctime = timespec_to_timespec64(hfsp_mt2ut(folder->attribute_mod_date));
+ inode->i_atime = hfsp_mt2ut(folder->access_date);
+ inode->i_mtime = hfsp_mt2ut(folder->content_mod_date);
+ inode->i_ctime = hfsp_mt2ut(folder->attribute_mod_date);
HFSPLUS_I(inode)->create_date = folder->create_date;
HFSPLUS_I(inode)->fs_blocks = 0;
if (folder->flags & cpu_to_be16(HFSPLUS_HAS_FOLDER_COUNT)) {
@@ -542,9 +542,9 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd)
init_special_inode(inode, inode->i_mode,
be32_to_cpu(file->permissions.dev));
}
- inode->i_atime = timespec_to_timespec64(hfsp_mt2ut(file->access_date));
- inode->i_mtime = timespec_to_timespec64(hfsp_mt2ut(file->content_mod_date));
- inode->i_ctime = timespec_to_timespec64(hfsp_mt2ut(file->attribute_mod_date));
+ inode->i_atime = hfsp_mt2ut(file->access_date);
+ inode->i_mtime = hfsp_mt2ut(file->content_mod_date);
+ inode->i_ctime = hfsp_mt2ut(file->attribute_mod_date);
HFSPLUS_I(inode)->create_date = file->create_date;
} else {
pr_err("bad catalog entry used to create inode\n");
diff --git a/fs/hostfs/hostfs.h b/fs/hostfs/hostfs.h
index f4295aa19350..69cb796f6270 100644
--- a/fs/hostfs/hostfs.h
+++ b/fs/hostfs/hostfs.h
@@ -37,16 +37,20 @@
* is on, and remove the appropriate bits from attr->ia_mode (attr is a
* "struct iattr *"). -BlaisorBlade
*/
+struct hostfs_timespec {
+ long long tv_sec;
+ long long tv_nsec;
+};
struct hostfs_iattr {
- unsigned int ia_valid;
- unsigned short ia_mode;
- uid_t ia_uid;
- gid_t ia_gid;
- loff_t ia_size;
- struct timespec ia_atime;
- struct timespec ia_mtime;
- struct timespec ia_ctime;
+ unsigned int ia_valid;
+ unsigned short ia_mode;
+ uid_t ia_uid;
+ gid_t ia_gid;
+ loff_t ia_size;
+ struct hostfs_timespec ia_atime;
+ struct hostfs_timespec ia_mtime;
+ struct hostfs_timespec ia_ctime;
};
struct hostfs_stat {
@@ -56,7 +60,7 @@ struct hostfs_stat {
unsigned int uid;
unsigned int gid;
unsigned long long size;
- struct timespec atime, mtime, ctime;
+ struct hostfs_timespec atime, mtime, ctime;
unsigned int blksize;
unsigned long long blocks;
unsigned int maj;
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 5a7eb0c79839..e6b8c49076bb 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -549,9 +549,9 @@ static int read_name(struct inode *ino, char *name)
set_nlink(ino, st.nlink);
i_uid_write(ino, st.uid);
i_gid_write(ino, st.gid);
- ino->i_atime = timespec_to_timespec64(st.atime);
- ino->i_mtime = timespec_to_timespec64(st.mtime);
- ino->i_ctime = timespec_to_timespec64(st.ctime);
+ ino->i_atime = (struct timespec64){ st.atime.tv_sec, st.atime.tv_nsec };
+ ino->i_mtime = (struct timespec64){ st.mtime.tv_sec, st.mtime.tv_nsec };
+ ino->i_ctime = (struct timespec64){ st.ctime.tv_sec, st.ctime.tv_nsec };
ino->i_size = st.size;
ino->i_blocks = st.blocks;
return 0;
@@ -820,15 +820,18 @@ static int hostfs_setattr(struct dentry *dentry, struct iattr *attr)
}
if (attr->ia_valid & ATTR_ATIME) {
attrs.ia_valid |= HOSTFS_ATTR_ATIME;
- attrs.ia_atime = timespec64_to_timespec(attr->ia_atime);
+ attrs.ia_atime = (struct hostfs_timespec)
+ { attr->ia_atime.tv_sec, attr->ia_atime.tv_nsec };
}
if (attr->ia_valid & ATTR_MTIME) {
attrs.ia_valid |= HOSTFS_ATTR_MTIME;
- attrs.ia_mtime = timespec64_to_timespec(attr->ia_mtime);
+ attrs.ia_mtime = (struct hostfs_timespec)
+ { attr->ia_mtime.tv_sec, attr->ia_mtime.tv_nsec };
}
if (attr->ia_valid & ATTR_CTIME) {
attrs.ia_valid |= HOSTFS_ATTR_CTIME;
- attrs.ia_ctime = timespec64_to_timespec(attr->ia_ctime);
+ attrs.ia_ctime = (struct hostfs_timespec)
+ { attr->ia_ctime.tv_sec, attr->ia_ctime.tv_nsec };
}
if (attr->ia_valid & ATTR_ATIME_SET) {
attrs.ia_valid |= HOSTFS_ATTR_ATIME_SET;
diff --git a/fs/internal.h b/fs/internal.h
index e3fa69544b66..f3f280b952a3 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -124,6 +124,8 @@ extern struct file *do_filp_open(int dfd, struct filename *pathname,
const struct open_flags *op);
extern struct file *do_file_open_root(struct dentry *, struct vfsmount *,
const char *, const struct open_flags *);
+extern struct open_how build_open_how(int flags, umode_t mode);
+extern int build_open_flags(const struct open_how *how, struct open_flags *op);
long do_sys_ftruncate(unsigned int fd, loff_t length, int small);
long do_faccessat(int dfd, const char __user *filename, int mode);
@@ -180,11 +182,11 @@ extern void mnt_pin_kill(struct mount *m);
*/
extern const struct dentry_operations ns_dentry_operations;
-/*
- * fs/ioctl.c
- */
-extern int do_vfs_ioctl(struct file *file, unsigned int fd, unsigned int cmd,
- unsigned long arg);
-
/* direct-io.c: */
int sb_init_dio_done_wq(struct super_block *sb);
+
+/*
+ * fs/stat.c:
+ */
+unsigned vfs_stat_set_lookup_flags(unsigned *lookup_flags, int flags);
+int cp_statx(const struct kstat *stat, struct statx __user *buffer);
diff --git a/fs/io-wq.c b/fs/io-wq.c
index 5147d2213b01..cb60a42b9fdf 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -56,7 +56,8 @@ struct io_worker {
struct rcu_head rcu;
struct mm_struct *mm;
- const struct cred *creds;
+ const struct cred *cur_creds;
+ const struct cred *saved_creds;
struct files_struct *restore_files;
};
@@ -109,10 +110,10 @@ struct io_wq {
struct task_struct *manager;
struct user_struct *user;
- const struct cred *creds;
- struct mm_struct *mm;
refcount_t refs;
struct completion done;
+
+ refcount_t use_refs;
};
static bool io_worker_get(struct io_worker *worker)
@@ -135,9 +136,9 @@ static bool __io_worker_unuse(struct io_wqe *wqe, struct io_worker *worker)
{
bool dropped_lock = false;
- if (worker->creds) {
- revert_creds(worker->creds);
- worker->creds = NULL;
+ if (worker->saved_creds) {
+ revert_creds(worker->saved_creds);
+ worker->cur_creds = worker->saved_creds = NULL;
}
if (current->files != worker->restore_files) {
@@ -396,6 +397,43 @@ static struct io_wq_work *io_get_next_work(struct io_wqe *wqe, unsigned *hash)
return NULL;
}
+static void io_wq_switch_mm(struct io_worker *worker, struct io_wq_work *work)
+{
+ if (worker->mm) {
+ unuse_mm(worker->mm);
+ mmput(worker->mm);
+ worker->mm = NULL;
+ }
+ if (!work->mm) {
+ set_fs(KERNEL_DS);
+ return;
+ }
+ if (mmget_not_zero(work->mm)) {
+ use_mm(work->mm);
+ if (!worker->mm)
+ set_fs(USER_DS);
+ worker->mm = work->mm;
+ /* hang on to this mm */
+ work->mm = NULL;
+ return;
+ }
+
+ /* failed grabbing mm, ensure work gets cancelled */
+ work->flags |= IO_WQ_WORK_CANCEL;
+}
+
+static void io_wq_switch_creds(struct io_worker *worker,
+ struct io_wq_work *work)
+{
+ const struct cred *old_creds = override_creds(work->creds);
+
+ worker->cur_creds = work->creds;
+ if (worker->saved_creds)
+ put_cred(old_creds); /* creds set by previous switch */
+ else
+ worker->saved_creds = old_creds;
+}
+
static void io_worker_handle_work(struct io_worker *worker)
__releases(wqe->lock)
{
@@ -438,24 +476,19 @@ next:
if (work->flags & IO_WQ_WORK_CB)
work->func(&work);
- if ((work->flags & IO_WQ_WORK_NEEDS_FILES) &&
- current->files != work->files) {
+ if (work->files && current->files != work->files) {
task_lock(current);
current->files = work->files;
task_unlock(current);
}
- if ((work->flags & IO_WQ_WORK_NEEDS_USER) && !worker->mm &&
- wq->mm) {
- if (mmget_not_zero(wq->mm)) {
- use_mm(wq->mm);
- set_fs(USER_DS);
- worker->mm = wq->mm;
- } else {
- work->flags |= IO_WQ_WORK_CANCEL;
- }
- }
- if (!worker->creds)
- worker->creds = override_creds(wq->creds);
+ if (work->mm != worker->mm)
+ io_wq_switch_mm(worker, work);
+ if (worker->cur_creds != work->creds)
+ io_wq_switch_creds(worker, work);
+ /*
+ * OK to set IO_WQ_WORK_CANCEL even for uncancellable work,
+ * the worker function will do the right thing.
+ */
if (test_bit(IO_WQ_BIT_CANCEL, &wq->state))
work->flags |= IO_WQ_WORK_CANCEL;
if (worker->mm)
@@ -720,6 +753,7 @@ static bool io_wq_can_queue(struct io_wqe *wqe, struct io_wqe_acct *acct,
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);
+ int work_flags;
unsigned long flags;
/*
@@ -734,12 +768,14 @@ static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
return;
}
+ work_flags = work->flags;
spin_lock_irqsave(&wqe->lock, flags);
wq_list_add_tail(&work->list, &wqe->work_list);
wqe->flags &= ~IO_WQE_FLAG_STALLED;
spin_unlock_irqrestore(&wqe->lock, flags);
- if (!atomic_read(&acct->nr_running))
+ if ((work_flags & IO_WQ_WORK_CONCURRENT) ||
+ !atomic_read(&acct->nr_running))
io_wqe_wake_worker(wqe, acct);
}
@@ -828,6 +864,7 @@ static bool io_work_cancel(struct io_worker *worker, void *cancel_data)
*/
spin_lock_irqsave(&worker->lock, flags);
if (worker->cur_work &&
+ !(worker->cur_work->flags & IO_WQ_WORK_NO_CANCEL) &&
data->cancel(worker->cur_work, data->caller_data)) {
send_sig(SIGINT, worker->task, 1);
ret = true;
@@ -902,7 +939,8 @@ static bool io_wq_worker_cancel(struct io_worker *worker, void *data)
return false;
spin_lock_irqsave(&worker->lock, flags);
- if (worker->cur_work == work) {
+ if (worker->cur_work == work &&
+ !(worker->cur_work->flags & IO_WQ_WORK_NO_CANCEL)) {
send_sig(SIGINT, worker->task, 1);
ret = true;
}
@@ -1026,7 +1064,6 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
/* caller must already hold a reference to this */
wq->user = data->user;
- wq->creds = data->creds;
for_each_node(node) {
struct io_wqe *wqe;
@@ -1053,9 +1090,6 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
init_completion(&wq->done);
- /* caller must have already done mmgrab() on this mm */
- wq->mm = data->mm;
-
wq->manager = kthread_create(io_wq_manager, wq, "io_wq_manager");
if (!IS_ERR(wq->manager)) {
wake_up_process(wq->manager);
@@ -1064,6 +1098,7 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
ret = -ENOMEM;
goto err;
}
+ refcount_set(&wq->use_refs, 1);
reinit_completion(&wq->done);
return wq;
}
@@ -1078,13 +1113,21 @@ err:
return ERR_PTR(ret);
}
+bool io_wq_get(struct io_wq *wq, struct io_wq_data *data)
+{
+ if (data->get_work != wq->get_work || data->put_work != wq->put_work)
+ return false;
+
+ return refcount_inc_not_zero(&wq->use_refs);
+}
+
static bool io_wq_worker_wake(struct io_worker *worker, void *data)
{
wake_up_process(worker->task);
return false;
}
-void io_wq_destroy(struct io_wq *wq)
+static void __io_wq_destroy(struct io_wq *wq)
{
int node;
@@ -1104,3 +1147,9 @@ void io_wq_destroy(struct io_wq *wq)
kfree(wq->wqes);
kfree(wq);
}
+
+void io_wq_destroy(struct io_wq *wq)
+{
+ if (refcount_dec_and_test(&wq->use_refs))
+ __io_wq_destroy(wq);
+}
diff --git a/fs/io-wq.h b/fs/io-wq.h
index 3f5e356de980..50b3378febf2 100644
--- a/fs/io-wq.h
+++ b/fs/io-wq.h
@@ -7,11 +7,11 @@ enum {
IO_WQ_WORK_CANCEL = 1,
IO_WQ_WORK_HAS_MM = 2,
IO_WQ_WORK_HASHED = 4,
- IO_WQ_WORK_NEEDS_USER = 8,
- IO_WQ_WORK_NEEDS_FILES = 16,
IO_WQ_WORK_UNBOUND = 32,
IO_WQ_WORK_INTERNAL = 64,
IO_WQ_WORK_CB = 128,
+ IO_WQ_WORK_NO_CANCEL = 256,
+ IO_WQ_WORK_CONCURRENT = 512,
IO_WQ_HASH_SHIFT = 24, /* upper 8 bits are used for hash key */
};
@@ -72,6 +72,8 @@ struct io_wq_work {
};
void (*func)(struct io_wq_work **);
struct files_struct *files;
+ struct mm_struct *mm;
+ const struct cred *creds;
unsigned flags;
};
@@ -81,21 +83,22 @@ struct io_wq_work {
(work)->func = _func; \
(work)->flags = 0; \
(work)->files = NULL; \
+ (work)->mm = NULL; \
+ (work)->creds = NULL; \
} while (0) \
typedef void (get_work_fn)(struct io_wq_work *);
typedef void (put_work_fn)(struct io_wq_work *);
struct io_wq_data {
- struct mm_struct *mm;
struct user_struct *user;
- const struct cred *creds;
get_work_fn *get_work;
put_work_fn *put_work;
};
struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data);
+bool io_wq_get(struct io_wq *wq, struct io_wq_data *data);
void io_wq_destroy(struct io_wq *wq);
void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index e54556b0fcc6..1806afddfea5 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -46,6 +46,7 @@
#include <linux/compat.h>
#include <linux/refcount.h>
#include <linux/uio.h>
+#include <linux/bits.h>
#include <linux/sched/signal.h>
#include <linux/fs.h>
@@ -70,6 +71,10 @@
#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>
#define CREATE_TRACE_POINTS
#include <trace/events/io_uring.h>
@@ -177,6 +182,21 @@ struct fixed_file_table {
struct file **files;
};
+enum {
+ FFD_F_ATOMIC,
+};
+
+struct fixed_file_data {
+ struct fixed_file_table *table;
+ struct io_ring_ctx *ctx;
+
+ struct percpu_ref refs;
+ struct llist_head put_llist;
+ unsigned long state;
+ struct work_struct ref_work;
+ struct completion done;
+};
+
struct io_ring_ctx {
struct {
struct percpu_ref refs;
@@ -184,10 +204,11 @@ struct io_ring_ctx {
struct {
unsigned int flags;
- bool compat;
- bool account_mem;
- bool cq_overflow_flushed;
- bool drain_next;
+ int compat: 1;
+ int account_mem: 1;
+ int cq_overflow_flushed: 1;
+ int drain_next: 1;
+ int eventfd_async: 1;
/*
* Ring buffer of indices into array of io_uring_sqe, which is
@@ -207,13 +228,14 @@ struct io_ring_ctx {
unsigned sq_thread_idle;
unsigned cached_sq_dropped;
atomic_t cached_cq_overflow;
- struct io_uring_sqe *sq_sqes;
+ unsigned long sq_check_overflow;
struct list_head defer_list;
struct list_head timeout_list;
struct list_head cq_overflow_list;
wait_queue_head_t inflight_wait;
+ struct io_uring_sqe *sq_sqes;
} ____cacheline_aligned_in_smp;
struct io_rings *rings;
@@ -229,8 +251,10 @@ struct io_ring_ctx {
* readers must ensure that ->refs is alive as long as the file* is
* used. Only updated through io_uring_register(2).
*/
- struct fixed_file_table *file_table;
+ struct fixed_file_data *file_data;
unsigned nr_user_files;
+ int ring_fd;
+ struct file *ring_file;
/* if used, fixed mapped user buffers */
unsigned nr_user_bufs;
@@ -250,11 +274,14 @@ struct io_ring_ctx {
struct socket *ring_sock;
#endif
+ struct idr personality_idr;
+
struct {
unsigned cached_cq_tail;
unsigned cq_entries;
unsigned cq_mask;
atomic_t cq_timeouts;
+ unsigned long cq_check_overflow;
struct wait_queue_head cq_wait;
struct fasync_struct *cq_fasync;
struct eventfd_ctx *cq_ev_fd;
@@ -267,7 +294,8 @@ struct io_ring_ctx {
struct {
spinlock_t completion_lock;
- bool poll_multi_file;
+ struct llist_head poll_llist;
+
/*
* ->poll_list is protected by the ctx->uring_lock for
* io_uring instances that don't use IORING_SETUP_SQPOLL.
@@ -277,6 +305,7 @@ struct io_ring_ctx {
struct list_head poll_list;
struct hlist_head *cancel_hash;
unsigned cancel_hash_bits;
+ bool poll_multi_file;
spinlock_t inflight_lock;
struct list_head inflight_list;
@@ -299,6 +328,12 @@ struct io_poll_iocb {
struct wait_queue_entry wait;
};
+struct io_close {
+ struct file *file;
+ struct file *put_file;
+ int fd;
+};
+
struct io_timeout_data {
struct io_kiocb *req;
struct hrtimer timer;
@@ -319,6 +354,7 @@ struct io_sync {
loff_t len;
loff_t off;
int flags;
+ int mode;
};
struct io_cancel {
@@ -348,8 +384,52 @@ struct io_connect {
struct io_sr_msg {
struct file *file;
- struct user_msghdr __user *msg;
+ union {
+ struct user_msghdr __user *msg;
+ void __user *buf;
+ };
int msg_flags;
+ size_t len;
+};
+
+struct io_open {
+ struct file *file;
+ int dfd;
+ union {
+ unsigned mask;
+ };
+ struct filename *filename;
+ struct statx __user *buffer;
+ struct open_how how;
+};
+
+struct io_files_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_async_connect {
@@ -370,15 +450,79 @@ struct io_async_rw {
ssize_t size;
};
+struct io_async_open {
+ struct filename *filename;
+};
+
struct io_async_ctx {
union {
struct io_async_rw rw;
struct io_async_msghdr msg;
struct io_async_connect connect;
struct io_timeout_data timeout;
+ struct io_async_open open;
};
};
+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_LINK_NEXT_BIT,
+ REQ_F_FAIL_LINK_BIT,
+ REQ_F_INFLIGHT_BIT,
+ REQ_F_CUR_POS_BIT,
+ REQ_F_NOWAIT_BIT,
+ REQ_F_IOPOLL_COMPLETED_BIT,
+ REQ_F_LINK_TIMEOUT_BIT,
+ REQ_F_TIMEOUT_BIT,
+ REQ_F_ISREG_BIT,
+ REQ_F_MUST_PUNT_BIT,
+ REQ_F_TIMEOUT_NOSEQ_BIT,
+ REQ_F_COMP_LOCKED_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),
+
+ /* already grabbed next link */
+ REQ_F_LINK_NEXT = BIT(REQ_F_LINK_NEXT_BIT),
+ /* fail rest of links */
+ REQ_F_FAIL_LINK = BIT(REQ_F_FAIL_LINK_BIT),
+ /* on inflight list */
+ 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),
+ /* polled IO has completed */
+ REQ_F_IOPOLL_COMPLETED = BIT(REQ_F_IOPOLL_COMPLETED_BIT),
+ /* has linked timeout */
+ REQ_F_LINK_TIMEOUT = BIT(REQ_F_LINK_TIMEOUT_BIT),
+ /* timeout request */
+ REQ_F_TIMEOUT = BIT(REQ_F_TIMEOUT_BIT),
+ /* regular file */
+ REQ_F_ISREG = BIT(REQ_F_ISREG_BIT),
+ /* must be punted even for NONBLOCK */
+ REQ_F_MUST_PUNT = BIT(REQ_F_MUST_PUNT_BIT),
+ /* no timeout sequence */
+ REQ_F_TIMEOUT_NOSEQ = BIT(REQ_F_TIMEOUT_NOSEQ_BIT),
+ /* completion under lock */
+ REQ_F_COMP_LOCKED = BIT(REQ_F_COMP_LOCKED_BIT),
+};
+
/*
* NOTE! Each of the iocb union members has the file pointer
* as the first entry in their struct definition. So you can
@@ -396,11 +540,19 @@ struct io_kiocb {
struct io_timeout timeout;
struct io_connect connect;
struct io_sr_msg sr_msg;
+ struct io_open open;
+ struct io_close close;
+ struct io_files_update files_update;
+ struct io_fadvise fadvise;
+ struct io_madvise madvise;
+ struct io_epoll epoll;
};
struct io_async_ctx *io;
- struct file *ring_file;
- int ring_fd;
+ /*
+ * llist_node is only used for poll deferred completions
+ */
+ struct llist_node llist_node;
bool has_user;
bool in_async;
bool needs_fixed_file;
@@ -414,23 +566,6 @@ struct io_kiocb {
struct list_head link_list;
unsigned int flags;
refcount_t refs;
-#define REQ_F_NOWAIT 1 /* must not punt to workers */
-#define REQ_F_IOPOLL_COMPLETED 2 /* polled IO has completed */
-#define REQ_F_FIXED_FILE 4 /* ctx owns file */
-#define REQ_F_LINK_NEXT 8 /* already grabbed next link */
-#define REQ_F_IO_DRAIN 16 /* drain existing IO first */
-#define REQ_F_IO_DRAINED 32 /* drain done */
-#define REQ_F_LINK 64 /* linked sqes */
-#define REQ_F_LINK_TIMEOUT 128 /* has linked timeout */
-#define REQ_F_FAIL_LINK 256 /* fail rest of links */
-#define REQ_F_DRAIN_LINK 512 /* link should be fully drained */
-#define REQ_F_TIMEOUT 1024 /* timeout request */
-#define REQ_F_ISREG 2048 /* regular file */
-#define REQ_F_MUST_PUNT 4096 /* must be punted even for NONBLOCK */
-#define REQ_F_TIMEOUT_NOSEQ 8192 /* no timeout sequence */
-#define REQ_F_INFLIGHT 16384 /* on inflight list */
-#define REQ_F_COMP_LOCKED 32768 /* completion under lock */
-#define REQ_F_HARDLINK 65536 /* doesn't sever on completion < 0 */
u64 user_data;
u32 result;
u32 sequence;
@@ -463,14 +598,162 @@ struct io_submit_state {
unsigned int ios_left;
};
+struct io_op_def {
+ /* needs req->io allocated for deferral/async */
+ unsigned async_ctx : 1;
+ /* needs current->mm setup, does mm access */
+ unsigned needs_mm : 1;
+ /* needs req->file assigned */
+ unsigned needs_file : 1;
+ /* needs req->file assigned IFF fd is >= 0 */
+ unsigned fd_non_neg : 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;
+ /* opcode is not supported by this kernel */
+ unsigned not_supported : 1;
+ /* needs file table */
+ unsigned file_table : 1;
+};
+
+static const struct io_op_def io_op_defs[] = {
+ [IORING_OP_NOP] = {},
+ [IORING_OP_READV] = {
+ .async_ctx = 1,
+ .needs_mm = 1,
+ .needs_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+ [IORING_OP_WRITEV] = {
+ .async_ctx = 1,
+ .needs_mm = 1,
+ .needs_file = 1,
+ .hash_reg_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+ [IORING_OP_FSYNC] = {
+ .needs_file = 1,
+ },
+ [IORING_OP_READ_FIXED] = {
+ .needs_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+ [IORING_OP_WRITE_FIXED] = {
+ .needs_file = 1,
+ .hash_reg_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+ [IORING_OP_POLL_ADD] = {
+ .needs_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+ [IORING_OP_POLL_REMOVE] = {},
+ [IORING_OP_SYNC_FILE_RANGE] = {
+ .needs_file = 1,
+ },
+ [IORING_OP_SENDMSG] = {
+ .async_ctx = 1,
+ .needs_mm = 1,
+ .needs_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+ [IORING_OP_RECVMSG] = {
+ .async_ctx = 1,
+ .needs_mm = 1,
+ .needs_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+ [IORING_OP_TIMEOUT] = {
+ .async_ctx = 1,
+ .needs_mm = 1,
+ },
+ [IORING_OP_TIMEOUT_REMOVE] = {},
+ [IORING_OP_ACCEPT] = {
+ .needs_mm = 1,
+ .needs_file = 1,
+ .unbound_nonreg_file = 1,
+ .file_table = 1,
+ },
+ [IORING_OP_ASYNC_CANCEL] = {},
+ [IORING_OP_LINK_TIMEOUT] = {
+ .async_ctx = 1,
+ .needs_mm = 1,
+ },
+ [IORING_OP_CONNECT] = {
+ .async_ctx = 1,
+ .needs_mm = 1,
+ .needs_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+ [IORING_OP_FALLOCATE] = {
+ .needs_file = 1,
+ },
+ [IORING_OP_OPENAT] = {
+ .needs_file = 1,
+ .fd_non_neg = 1,
+ .file_table = 1,
+ },
+ [IORING_OP_CLOSE] = {
+ .needs_file = 1,
+ .file_table = 1,
+ },
+ [IORING_OP_FILES_UPDATE] = {
+ .needs_mm = 1,
+ .file_table = 1,
+ },
+ [IORING_OP_STATX] = {
+ .needs_mm = 1,
+ .needs_file = 1,
+ .fd_non_neg = 1,
+ },
+ [IORING_OP_READ] = {
+ .needs_mm = 1,
+ .needs_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+ [IORING_OP_WRITE] = {
+ .needs_mm = 1,
+ .needs_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+ [IORING_OP_FADVISE] = {
+ .needs_file = 1,
+ },
+ [IORING_OP_MADVISE] = {
+ .needs_mm = 1,
+ },
+ [IORING_OP_SEND] = {
+ .needs_mm = 1,
+ .needs_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+ [IORING_OP_RECV] = {
+ .needs_mm = 1,
+ .needs_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+ [IORING_OP_OPENAT2] = {
+ .needs_file = 1,
+ .fd_non_neg = 1,
+ .file_table = 1,
+ },
+ [IORING_OP_EPOLL_CTL] = {
+ .unbound_nonreg_file = 1,
+ .file_table = 1,
+ },
+};
+
static void io_wq_submit_work(struct io_wq_work **workptr);
static void io_cqring_fill_event(struct io_kiocb *req, long res);
-static void __io_free_req(struct io_kiocb *req);
static void io_put_req(struct io_kiocb *req);
-static void io_double_put_req(struct io_kiocb *req);
static void __io_double_put_req(struct io_kiocb *req);
static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req);
static void io_queue_linked_timeout(struct io_kiocb *req);
+static int __io_sqe_files_update(struct io_ring_ctx *ctx,
+ struct io_uring_files_update *ip,
+ unsigned nr_args);
+static int io_grab_files(struct io_kiocb *req);
static struct kmem_cache *req_cachep;
@@ -537,9 +820,11 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
INIT_LIST_HEAD(&ctx->cq_overflow_list);
init_completion(&ctx->completions[0]);
init_completion(&ctx->completions[1]);
+ idr_init(&ctx->personality_idr);
mutex_init(&ctx->uring_lock);
init_waitqueue_head(&ctx->wait);
spin_lock_init(&ctx->completion_lock);
+ init_llist_head(&ctx->poll_llist);
INIT_LIST_HEAD(&ctx->poll_list);
INIT_LIST_HEAD(&ctx->defer_list);
INIT_LIST_HEAD(&ctx->timeout_list);
@@ -566,7 +851,7 @@ static inline bool __req_need_defer(struct io_kiocb *req)
static inline bool req_need_defer(struct io_kiocb *req)
{
- if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) == REQ_F_IO_DRAIN)
+ if (unlikely(req->flags & REQ_F_IO_DRAIN))
return __req_need_defer(req);
return false;
@@ -606,53 +891,53 @@ static void __io_commit_cqring(struct io_ring_ctx *ctx)
{
struct io_rings *rings = ctx->rings;
- if (ctx->cached_cq_tail != READ_ONCE(rings->cq.tail)) {
- /* order cqe stores with ring update */
- smp_store_release(&rings->cq.tail, ctx->cached_cq_tail);
+ /* order cqe stores with ring update */
+ smp_store_release(&rings->cq.tail, ctx->cached_cq_tail);
- if (wq_has_sleeper(&ctx->cq_wait)) {
- wake_up_interruptible(&ctx->cq_wait);
- kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN);
- }
+ if (wq_has_sleeper(&ctx->cq_wait)) {
+ wake_up_interruptible(&ctx->cq_wait);
+ kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN);
+ }
+}
+
+static inline void io_req_work_grab_env(struct io_kiocb *req,
+ const struct io_op_def *def)
+{
+ if (!req->work.mm && def->needs_mm) {
+ mmgrab(current->mm);
+ req->work.mm = current->mm;
}
+ if (!req->work.creds)
+ req->work.creds = get_current_cred();
}
-static inline bool io_req_needs_user(struct io_kiocb *req)
+static inline void io_req_work_drop_env(struct io_kiocb *req)
{
- return !(req->opcode == IORING_OP_READ_FIXED ||
- req->opcode == IORING_OP_WRITE_FIXED);
+ if (req->work.mm) {
+ mmdrop(req->work.mm);
+ req->work.mm = NULL;
+ }
+ if (req->work.creds) {
+ put_cred(req->work.creds);
+ req->work.creds = NULL;
+ }
}
static inline bool io_prep_async_work(struct io_kiocb *req,
struct io_kiocb **link)
{
+ const struct io_op_def *def = &io_op_defs[req->opcode];
bool do_hashed = false;
- switch (req->opcode) {
- case IORING_OP_WRITEV:
- case IORING_OP_WRITE_FIXED:
- /* only regular files should be hashed for writes */
- if (req->flags & REQ_F_ISREG)
+ if (req->flags & REQ_F_ISREG) {
+ if (def->hash_reg_file)
do_hashed = true;
- /* fall-through */
- case IORING_OP_READV:
- case IORING_OP_READ_FIXED:
- case IORING_OP_SENDMSG:
- case IORING_OP_RECVMSG:
- case IORING_OP_ACCEPT:
- case IORING_OP_POLL_ADD:
- case IORING_OP_CONNECT:
- /*
- * We know REQ_F_ISREG is not set on some of these
- * opcodes, but this enables us to keep the check in
- * just one place.
- */
- if (!(req->flags & REQ_F_ISREG))
+ } else {
+ if (def->unbound_nonreg_file)
req->work.flags |= IO_WQ_WORK_UNBOUND;
- break;
}
- if (io_req_needs_user(req))
- req->work.flags |= IO_WQ_WORK_NEEDS_USER;
+
+ io_req_work_grab_env(req, def);
*link = io_prep_linked_timeout(req);
return do_hashed;
@@ -711,10 +996,8 @@ static void io_commit_cqring(struct io_ring_ctx *ctx)
__io_commit_cqring(ctx);
- while ((req = io_get_deferred_req(ctx)) != NULL) {
- req->flags |= REQ_F_IO_DRAINED;
+ while ((req = io_get_deferred_req(ctx)) != NULL)
io_queue_async_work(req);
- }
}
static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
@@ -735,13 +1018,20 @@ static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
return &rings->cqes[tail & ctx->cq_mask];
}
+static inline bool io_should_trigger_evfd(struct io_ring_ctx *ctx)
+{
+ if (!ctx->eventfd_async)
+ return true;
+ return io_wq_current_is_worker() || in_interrupt();
+}
+
static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
{
if (waitqueue_active(&ctx->wait))
wake_up(&ctx->wait);
if (waitqueue_active(&ctx->sqo_wait))
wake_up(&ctx->sqo_wait);
- if (ctx->cq_ev_fd)
+ if (ctx->cq_ev_fd && io_should_trigger_evfd(ctx))
eventfd_signal(ctx->cq_ev_fd, 1);
}
@@ -766,7 +1056,7 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
/* if force is set, the ring is going away. always drop after that */
if (force)
- ctx->cq_overflow_flushed = true;
+ ctx->cq_overflow_flushed = 1;
cqe = NULL;
while (!list_empty(&ctx->cq_overflow_list)) {
@@ -788,6 +1078,10 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
}
io_commit_cqring(ctx);
+ if (cqe) {
+ clear_bit(0, &ctx->sq_check_overflow);
+ clear_bit(0, &ctx->cq_check_overflow);
+ }
spin_unlock_irqrestore(&ctx->completion_lock, flags);
io_cqring_ev_posted(ctx);
@@ -821,6 +1115,10 @@ static void io_cqring_fill_event(struct io_kiocb *req, long res)
WRITE_ONCE(ctx->rings->cq_overflow,
atomic_inc_return(&ctx->cached_cq_overflow));
} else {
+ if (list_empty(&ctx->cq_overflow_list)) {
+ set_bit(0, &ctx->sq_check_overflow);
+ set_bit(0, &ctx->cq_check_overflow);
+ }
refcount_inc(&req->refs);
req->result = res;
list_add_tail(&req->list, &ctx->cq_overflow_list);
@@ -863,9 +1161,6 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
struct io_kiocb *req;
- if (!percpu_ref_tryget(&ctx->refs))
- return NULL;
-
if (!state) {
req = kmem_cache_alloc(req_cachep, gfp);
if (unlikely(!req))
@@ -898,7 +1193,6 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
got_it:
req->io = NULL;
- req->ring_file = NULL;
req->file = NULL;
req->ctx = ctx;
req->flags = 0;
@@ -915,24 +1209,35 @@ fallback:
return NULL;
}
-static void io_free_req_many(struct io_ring_ctx *ctx, void **reqs, int *nr)
+static void __io_req_do_free(struct io_kiocb *req)
{
- if (*nr) {
- kmem_cache_free_bulk(req_cachep, *nr, reqs);
- percpu_ref_put_many(&ctx->refs, *nr);
- *nr = 0;
+ if (likely(!io_is_fallback_req(req)))
+ kmem_cache_free(req_cachep, req);
+ else
+ clear_bit_unlock(0, (unsigned long *) req->ctx->fallback_req);
+}
+
+static void __io_req_aux_free(struct io_kiocb *req)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+
+ kfree(req->io);
+ if (req->file) {
+ if (req->flags & REQ_F_FIXED_FILE)
+ percpu_ref_put(&ctx->file_data->refs);
+ else
+ fput(req->file);
}
+
+ io_req_work_drop_env(req);
}
static void __io_free_req(struct io_kiocb *req)
{
- struct io_ring_ctx *ctx = req->ctx;
+ __io_req_aux_free(req);
- if (req->io)
- kfree(req->io);
- if (req->file && !(req->flags & REQ_F_FIXED_FILE))
- fput(req->file);
if (req->flags & REQ_F_INFLIGHT) {
+ struct io_ring_ctx *ctx = req->ctx;
unsigned long flags;
spin_lock_irqsave(&ctx->inflight_lock, flags);
@@ -941,11 +1246,63 @@ static void __io_free_req(struct io_kiocb *req)
wake_up(&ctx->inflight_wait);
spin_unlock_irqrestore(&ctx->inflight_lock, flags);
}
- percpu_ref_put(&ctx->refs);
- if (likely(!io_is_fallback_req(req)))
- kmem_cache_free(req_cachep, req);
- else
- clear_bit_unlock(0, (unsigned long *) ctx->fallback_req);
+
+ percpu_ref_put(&req->ctx->refs);
+ __io_req_do_free(req);
+}
+
+struct req_batch {
+ void *reqs[IO_IOPOLL_BATCH];
+ int to_free;
+ int need_iter;
+};
+
+static void io_free_req_many(struct io_ring_ctx *ctx, struct req_batch *rb)
+{
+ int fixed_refs = rb->to_free;
+
+ if (!rb->to_free)
+ return;
+ if (rb->need_iter) {
+ int i, inflight = 0;
+ unsigned long flags;
+
+ fixed_refs = 0;
+ for (i = 0; i < rb->to_free; i++) {
+ struct io_kiocb *req = rb->reqs[i];
+
+ if (req->flags & REQ_F_FIXED_FILE) {
+ req->file = NULL;
+ fixed_refs++;
+ }
+ if (req->flags & REQ_F_INFLIGHT)
+ inflight++;
+ __io_req_aux_free(req);
+ }
+ if (!inflight)
+ goto do_free;
+
+ spin_lock_irqsave(&ctx->inflight_lock, flags);
+ for (i = 0; i < rb->to_free; i++) {
+ struct io_kiocb *req = rb->reqs[i];
+
+ if (req->flags & REQ_F_INFLIGHT) {
+ list_del(&req->inflight_entry);
+ if (!--inflight)
+ break;
+ }
+ }
+ spin_unlock_irqrestore(&ctx->inflight_lock, flags);
+
+ if (waitqueue_active(&ctx->inflight_wait))
+ wake_up(&ctx->inflight_wait);
+ }
+do_free:
+ kmem_cache_free_bulk(req_cachep, rb->to_free, rb->reqs);
+ if (fixed_refs)
+ percpu_ref_put_many(&ctx->file_data->refs, fixed_refs);
+ percpu_ref_put_many(&ctx->refs, rb->to_free);
+ rb->to_free = rb->need_iter = 0;
}
static bool io_link_cancel_timeout(struct io_kiocb *req)
@@ -1118,19 +1475,21 @@ static unsigned io_cqring_events(struct io_ring_ctx *ctx, bool noflush)
{
struct io_rings *rings = ctx->rings;
- /*
- * noflush == true is from the waitqueue handler, just ensure we wake
- * up the task, and the next invocation will flush the entries. We
- * cannot safely to it from here.
- */
- if (noflush && !list_empty(&ctx->cq_overflow_list))
- return -1U;
+ if (test_bit(0, &ctx->cq_check_overflow)) {
+ /*
+ * noflush == true is from the waitqueue handler, just ensure
+ * we wake up the task, and the next invocation will flush the
+ * entries. We cannot safely to it from here.
+ */
+ if (noflush && !list_empty(&ctx->cq_overflow_list))
+ return -1U;
- io_cqring_overflow_flush(ctx, false);
+ io_cqring_overflow_flush(ctx, false);
+ }
/* See comment at the top of this file */
smp_rmb();
- return READ_ONCE(rings->cq.tail) - READ_ONCE(rings->cq.head);
+ return ctx->cached_cq_tail - READ_ONCE(rings->cq.head);
}
static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
@@ -1141,17 +1500,30 @@ static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
return smp_load_acquire(&rings->sq.tail) - ctx->cached_sq_head;
}
+static inline bool io_req_multi_free(struct req_batch *rb, struct io_kiocb *req)
+{
+ if ((req->flags & REQ_F_LINK) || io_is_fallback_req(req))
+ return false;
+
+ if (!(req->flags & REQ_F_FIXED_FILE) || req->io)
+ rb->need_iter++;
+
+ rb->reqs[rb->to_free++] = req;
+ if (unlikely(rb->to_free == ARRAY_SIZE(rb->reqs)))
+ io_free_req_many(req->ctx, rb);
+ return true;
+}
+
/*
* Find and free completed poll iocbs
*/
static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
struct list_head *done)
{
- void *reqs[IO_IOPOLL_BATCH];
+ struct req_batch rb;
struct io_kiocb *req;
- int to_free;
- to_free = 0;
+ rb.to_free = rb.need_iter = 0;
while (!list_empty(done)) {
req = list_first_entry(done, struct io_kiocb, list);
list_del(&req->list);
@@ -1159,26 +1531,13 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
io_cqring_fill_event(req, req->result);
(*nr_events)++;
- if (refcount_dec_and_test(&req->refs)) {
- /* If we're not using fixed files, we have to pair the
- * completion part with the file put. Use regular
- * completions for those, only batch free for fixed
- * file and non-linked commands.
- */
- if (((req->flags & (REQ_F_FIXED_FILE|REQ_F_LINK)) ==
- REQ_F_FIXED_FILE) && !io_is_fallback_req(req) &&
- !req->io) {
- reqs[to_free++] = req;
- if (to_free == ARRAY_SIZE(reqs))
- io_free_req_many(ctx, reqs, &to_free);
- } else {
- io_free_req(req);
- }
- }
+ if (refcount_dec_and_test(&req->refs) &&
+ !io_req_multi_free(&rb, req))
+ io_free_req(req);
}
io_commit_cqring(ctx);
- io_free_req_many(ctx, reqs, &to_free);
+ io_free_req_many(ctx, &rb);
}
static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
@@ -1503,6 +1862,10 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
req->flags |= REQ_F_ISREG;
kiocb->ki_pos = READ_ONCE(sqe->off);
+ if (kiocb->ki_pos == -1 && !(req->file->f_mode & FMODE_STREAM)) {
+ req->flags |= REQ_F_CUR_POS;
+ kiocb->ki_pos = req->file->f_pos;
+ }
kiocb->ki_flags = iocb_flags(kiocb->ki_filp);
kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp));
@@ -1574,6 +1937,10 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
static void kiocb_done(struct kiocb *kiocb, ssize_t ret, struct io_kiocb **nxt,
bool in_async)
{
+ struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
+
+ if (req->flags & REQ_F_CUR_POS)
+ req->file->f_pos = kiocb->ki_pos;
if (in_async && ret >= 0 && kiocb->ki_complete == io_complete_rw)
*nxt = __io_complete_rw(kiocb, ret);
else
@@ -1671,6 +2038,13 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
if (req->rw.kiocb.private)
return -EINVAL;
+ if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) {
+ ssize_t ret;
+ ret = import_single_range(rw, buf, sqe_len, *iovec, iter);
+ *iovec = NULL;
+ return ret;
+ }
+
if (req->io) {
struct io_async_rw *iorw = &req->io->rw;
@@ -1767,6 +2141,8 @@ static void io_req_map_rw(struct io_kiocb *req, ssize_t io_size,
static int io_alloc_async_ctx(struct io_kiocb *req)
{
+ if (!io_op_defs[req->opcode].async_ctx)
+ return 0;
req->io = kmalloc(sizeof(*req->io), GFP_KERNEL);
return req->io == NULL;
}
@@ -1786,8 +2162,7 @@ static int io_setup_async_rw(struct io_kiocb *req, ssize_t io_size,
struct iovec *iovec, struct iovec *fast_iov,
struct iov_iter *iter)
{
- if (req->opcode == IORING_OP_READ_FIXED ||
- req->opcode == IORING_OP_WRITE_FIXED)
+ if (!io_op_defs[req->opcode].async_ctx)
return 0;
if (!req->io && io_alloc_async_ctx(req))
return -ENOMEM;
@@ -2101,6 +2476,421 @@ static int io_fsync(struct io_kiocb *req, struct io_kiocb **nxt,
return 0;
}
+static void io_fallocate_finish(struct io_wq_work **workptr)
+{
+ struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
+ struct io_kiocb *nxt = NULL;
+ int ret;
+
+ ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off,
+ req->sync.len);
+ if (ret < 0)
+ req_set_fail_links(req);
+ io_cqring_add_event(req, ret);
+ io_put_req_find_next(req, &nxt);
+ if (nxt)
+ io_wq_assign_next(workptr, nxt);
+}
+
+static int io_fallocate_prep(struct io_kiocb *req,
+ const struct io_uring_sqe *sqe)
+{
+ if (sqe->ioprio || sqe->buf_index || sqe->rw_flags)
+ 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, struct io_kiocb **nxt,
+ bool force_nonblock)
+{
+ struct io_wq_work *work, *old_work;
+
+ /* fallocate always requiring blocking context */
+ if (force_nonblock) {
+ io_put_req(req);
+ req->work.func = io_fallocate_finish;
+ return -EAGAIN;
+ }
+
+ work = old_work = &req->work;
+ io_fallocate_finish(&work);
+ if (work && work != old_work)
+ *nxt = container_of(work, struct io_kiocb, work);
+
+ return 0;
+}
+
+static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ const char __user *fname;
+ int ret;
+
+ if (sqe->ioprio || sqe->buf_index)
+ return -EINVAL;
+
+ req->open.dfd = READ_ONCE(sqe->fd);
+ req->open.how.mode = READ_ONCE(sqe->len);
+ fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
+ req->open.how.flags = READ_ONCE(sqe->open_flags);
+
+ req->open.filename = getname(fname);
+ if (IS_ERR(req->open.filename)) {
+ ret = PTR_ERR(req->open.filename);
+ req->open.filename = NULL;
+ return ret;
+ }
+
+ return 0;
+}
+
+static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ struct open_how __user *how;
+ const char __user *fname;
+ size_t len;
+ int ret;
+
+ if (sqe->ioprio || sqe->buf_index)
+ return -EINVAL;
+
+ req->open.dfd = READ_ONCE(sqe->fd);
+ fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
+ 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;
+
+ if (!(req->open.how.flags & O_PATH) && force_o_largefile())
+ req->open.how.flags |= O_LARGEFILE;
+
+ req->open.filename = getname(fname);
+ if (IS_ERR(req->open.filename)) {
+ ret = PTR_ERR(req->open.filename);
+ req->open.filename = NULL;
+ return ret;
+ }
+
+ return 0;
+}
+
+static int io_openat2(struct io_kiocb *req, struct io_kiocb **nxt,
+ bool force_nonblock)
+{
+ struct open_flags op;
+ struct file *file;
+ int ret;
+
+ if (force_nonblock)
+ return -EAGAIN;
+
+ ret = build_open_flags(&req->open.how, &op);
+ if (ret)
+ goto err;
+
+ ret = get_unused_fd_flags(req->open.how.flags);
+ if (ret < 0)
+ goto err;
+
+ file = do_filp_open(req->open.dfd, req->open.filename, &op);
+ if (IS_ERR(file)) {
+ put_unused_fd(ret);
+ ret = PTR_ERR(file);
+ } else {
+ fsnotify_open(file);
+ fd_install(ret, file);
+ }
+err:
+ putname(req->open.filename);
+ if (ret < 0)
+ req_set_fail_links(req);
+ io_cqring_add_event(req, ret);
+ io_put_req_find_next(req, nxt);
+ return 0;
+}
+
+static int io_openat(struct io_kiocb *req, struct io_kiocb **nxt,
+ bool force_nonblock)
+{
+ req->open.how = build_open_how(req->open.how.flags, req->open.how.mode);
+ return io_openat2(req, nxt, force_nonblock);
+}
+
+static int io_epoll_ctl_prep(struct io_kiocb *req,
+ const struct io_uring_sqe *sqe)
+{
+#if defined(CONFIG_EPOLL)
+ if (sqe->ioprio || sqe->buf_index)
+ 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, struct io_kiocb **nxt,
+ bool force_nonblock)
+{
+#if defined(CONFIG_EPOLL)
+ struct io_epoll *ie = &req->epoll;
+ int ret;
+
+ 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_links(req);
+ io_cqring_add_event(req, ret);
+ io_put_req_find_next(req, nxt);
+ 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->ioprio || sqe->buf_index || sqe->off)
+ 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, struct io_kiocb **nxt,
+ bool force_nonblock)
+{
+#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU)
+ struct io_madvise *ma = &req->madvise;
+ int ret;
+
+ if (force_nonblock)
+ return -EAGAIN;
+
+ ret = do_madvise(ma->addr, ma->len, ma->advice);
+ if (ret < 0)
+ req_set_fail_links(req);
+ io_cqring_add_event(req, ret);
+ io_put_req_find_next(req, nxt);
+ return 0;
+#else
+ return -EOPNOTSUPP;
+#endif
+}
+
+static int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ if (sqe->ioprio || sqe->buf_index || sqe->addr)
+ 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, struct io_kiocb **nxt,
+ bool force_nonblock)
+{
+ struct io_fadvise *fa = &req->fadvise;
+ int ret;
+
+ /* DONTNEED may block, others _should_ not */
+ if (fa->advice == POSIX_FADV_DONTNEED && force_nonblock)
+ return -EAGAIN;
+
+ ret = vfs_fadvise(req->file, fa->offset, fa->len, fa->advice);
+ if (ret < 0)
+ req_set_fail_links(req);
+ io_cqring_add_event(req, ret);
+ io_put_req_find_next(req, nxt);
+ return 0;
+}
+
+static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ const char __user *fname;
+ unsigned lookup_flags;
+ int ret;
+
+ if (sqe->ioprio || sqe->buf_index)
+ return -EINVAL;
+
+ req->open.dfd = READ_ONCE(sqe->fd);
+ req->open.mask = READ_ONCE(sqe->len);
+ fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
+ req->open.buffer = u64_to_user_ptr(READ_ONCE(sqe->addr2));
+ req->open.how.flags = READ_ONCE(sqe->statx_flags);
+
+ if (vfs_stat_set_lookup_flags(&lookup_flags, req->open.how.flags))
+ return -EINVAL;
+
+ req->open.filename = getname_flags(fname, lookup_flags, NULL);
+ if (IS_ERR(req->open.filename)) {
+ ret = PTR_ERR(req->open.filename);
+ req->open.filename = NULL;
+ return ret;
+ }
+
+ return 0;
+}
+
+static int io_statx(struct io_kiocb *req, struct io_kiocb **nxt,
+ bool force_nonblock)
+{
+ struct io_open *ctx = &req->open;
+ unsigned lookup_flags;
+ struct path path;
+ struct kstat stat;
+ int ret;
+
+ if (force_nonblock)
+ return -EAGAIN;
+
+ if (vfs_stat_set_lookup_flags(&lookup_flags, ctx->how.flags))
+ return -EINVAL;
+
+retry:
+ /* filename_lookup() drops it, keep a reference */
+ ctx->filename->refcnt++;
+
+ ret = filename_lookup(ctx->dfd, ctx->filename, lookup_flags, &path,
+ NULL);
+ if (ret)
+ goto err;
+
+ ret = vfs_getattr(&path, &stat, ctx->mask, ctx->how.flags);
+ path_put(&path);
+ if (retry_estale(ret, lookup_flags)) {
+ lookup_flags |= LOOKUP_REVAL;
+ goto retry;
+ }
+ if (!ret)
+ ret = cp_statx(&stat, ctx->buffer);
+err:
+ putname(ctx->filename);
+ if (ret < 0)
+ req_set_fail_links(req);
+ io_cqring_add_event(req, ret);
+ io_put_req_find_next(req, nxt);
+ return 0;
+}
+
+static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ /*
+ * If we queue this for async, it must not be cancellable. That would
+ * leave the 'file' in an undeterminate state.
+ */
+ req->work.flags |= IO_WQ_WORK_NO_CANCEL;
+
+ if (sqe->ioprio || sqe->off || sqe->addr || sqe->len ||
+ sqe->rw_flags || sqe->buf_index)
+ return -EINVAL;
+ if (sqe->flags & IOSQE_FIXED_FILE)
+ return -EINVAL;
+
+ req->close.fd = READ_ONCE(sqe->fd);
+ if (req->file->f_op == &io_uring_fops ||
+ req->close.fd == req->ctx->ring_fd)
+ return -EBADF;
+
+ return 0;
+}
+
+static void io_close_finish(struct io_wq_work **workptr)
+{
+ struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
+ struct io_kiocb *nxt = NULL;
+
+ /* Invoked with files, we need to do the close */
+ if (req->work.files) {
+ int ret;
+
+ ret = filp_close(req->close.put_file, req->work.files);
+ if (ret < 0) {
+ req_set_fail_links(req);
+ }
+ io_cqring_add_event(req, ret);
+ }
+
+ fput(req->close.put_file);
+
+ /* we bypassed the re-issue, drop the submission reference */
+ io_put_req(req);
+ io_put_req_find_next(req, &nxt);
+ if (nxt)
+ io_wq_assign_next(workptr, nxt);
+}
+
+static int io_close(struct io_kiocb *req, struct io_kiocb **nxt,
+ bool force_nonblock)
+{
+ int ret;
+
+ req->close.put_file = NULL;
+ ret = __close_fd_get_file(req->close.fd, &req->close.put_file);
+ if (ret < 0)
+ return ret;
+
+ /* if the file has a flush method, be safe and punt to async */
+ if (req->close.put_file->f_op->flush && !io_wq_current_is_worker())
+ goto eagain;
+
+ /*
+ * No ->flush(), safely close from here and just punt the
+ * fput() to async context.
+ */
+ ret = filp_close(req->close.put_file, current->files);
+
+ if (ret < 0)
+ req_set_fail_links(req);
+ io_cqring_add_event(req, ret);
+
+ if (io_wq_current_is_worker()) {
+ struct io_wq_work *old_work, *work;
+
+ old_work = work = &req->work;
+ io_close_finish(&work);
+ if (work && work != old_work)
+ *nxt = container_of(work, struct io_kiocb, work);
+ return 0;
+ }
+
+eagain:
+ req->work.func = io_close_finish;
+ return -EAGAIN;
+}
+
static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_ring_ctx *ctx = req->ctx;
@@ -2178,8 +2968,9 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
sr->msg_flags = READ_ONCE(sqe->msg_flags);
sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr));
+ sr->len = READ_ONCE(sqe->len);
- if (!io)
+ if (!io || req->opcode == IORING_OP_SEND)
return 0;
io->msg.iov = io->msg.fast_iov;
@@ -2259,6 +3050,56 @@ static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt,
#endif
}
+static int io_send(struct io_kiocb *req, struct io_kiocb **nxt,
+ bool force_nonblock)
+{
+#if defined(CONFIG_NET)
+ struct socket *sock;
+ int ret;
+
+ if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+ return -EINVAL;
+
+ sock = sock_from_file(req->file, &ret);
+ if (sock) {
+ struct io_sr_msg *sr = &req->sr_msg;
+ struct msghdr msg;
+ struct iovec iov;
+ unsigned flags;
+
+ ret = import_single_range(WRITE, sr->buf, sr->len, &iov,
+ &msg.msg_iter);
+ if (ret)
+ return ret;
+
+ msg.msg_name = NULL;
+ msg.msg_control = NULL;
+ msg.msg_controllen = 0;
+ msg.msg_namelen = 0;
+
+ flags = req->sr_msg.msg_flags;
+ if (flags & MSG_DONTWAIT)
+ req->flags |= REQ_F_NOWAIT;
+ else if (force_nonblock)
+ flags |= MSG_DONTWAIT;
+
+ ret = __sys_sendmsg_sock(sock, &msg, flags);
+ if (force_nonblock && ret == -EAGAIN)
+ return -EAGAIN;
+ if (ret == -ERESTARTSYS)
+ ret = -EINTR;
+ }
+
+ io_cqring_add_event(req, ret);
+ if (ret < 0)
+ req_set_fail_links(req);
+ io_put_req_find_next(req, nxt);
+ return 0;
+#else
+ return -EOPNOTSUPP;
+#endif
+}
+
static int io_recvmsg_prep(struct io_kiocb *req,
const struct io_uring_sqe *sqe)
{
@@ -2269,7 +3110,7 @@ static int io_recvmsg_prep(struct io_kiocb *req,
sr->msg_flags = READ_ONCE(sqe->msg_flags);
sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr));
- if (!io)
+ if (!io || req->opcode == IORING_OP_RECV)
return 0;
io->msg.iov = io->msg.fast_iov;
@@ -2351,6 +3192,59 @@ static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt,
#endif
}
+static int io_recv(struct io_kiocb *req, struct io_kiocb **nxt,
+ bool force_nonblock)
+{
+#if defined(CONFIG_NET)
+ struct socket *sock;
+ int ret;
+
+ if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+ return -EINVAL;
+
+ sock = sock_from_file(req->file, &ret);
+ if (sock) {
+ struct io_sr_msg *sr = &req->sr_msg;
+ struct msghdr msg;
+ struct iovec iov;
+ unsigned flags;
+
+ ret = import_single_range(READ, sr->buf, sr->len, &iov,
+ &msg.msg_iter);
+ if (ret)
+ return ret;
+
+ msg.msg_name = NULL;
+ msg.msg_control = NULL;
+ msg.msg_controllen = 0;
+ msg.msg_namelen = 0;
+ msg.msg_iocb = NULL;
+ msg.msg_flags = 0;
+
+ flags = req->sr_msg.msg_flags;
+ if (flags & MSG_DONTWAIT)
+ req->flags |= REQ_F_NOWAIT;
+ else if (force_nonblock)
+ flags |= MSG_DONTWAIT;
+
+ ret = __sys_recvmsg_sock(sock, &msg, NULL, NULL, flags);
+ if (force_nonblock && ret == -EAGAIN)
+ return -EAGAIN;
+ if (ret == -ERESTARTSYS)
+ ret = -EINTR;
+ }
+
+ io_cqring_add_event(req, ret);
+ if (ret < 0)
+ req_set_fail_links(req);
+ io_put_req_find_next(req, nxt);
+ return 0;
+#else
+ return -EOPNOTSUPP;
+#endif
+}
+
+
static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
#if defined(CONFIG_NET)
@@ -2414,7 +3308,6 @@ static int io_accept(struct io_kiocb *req, struct io_kiocb **nxt,
ret = __io_accept(req, nxt, force_nonblock);
if (ret == -EAGAIN && force_nonblock) {
req->work.func = io_accept_finish;
- req->work.flags |= IO_WQ_WORK_NEEDS_FILES;
io_put_req(req);
return -EAGAIN;
}
@@ -2635,6 +3528,39 @@ static void io_poll_complete_work(struct io_wq_work **workptr)
io_wq_assign_next(workptr, nxt);
}
+static void __io_poll_flush(struct io_ring_ctx *ctx, struct llist_node *nodes)
+{
+ struct io_kiocb *req, *tmp;
+ struct req_batch rb;
+
+ rb.to_free = rb.need_iter = 0;
+ spin_lock_irq(&ctx->completion_lock);
+ llist_for_each_entry_safe(req, tmp, nodes, llist_node) {
+ hash_del(&req->hash_node);
+ io_poll_complete(req, req->result, 0);
+
+ if (refcount_dec_and_test(&req->refs) &&
+ !io_req_multi_free(&rb, req)) {
+ req->flags |= REQ_F_COMP_LOCKED;
+ io_free_req(req);
+ }
+ }
+ spin_unlock_irq(&ctx->completion_lock);
+
+ io_cqring_ev_posted(ctx);
+ io_free_req_many(ctx, &rb);
+}
+
+static void io_poll_flush(struct io_wq_work **workptr)
+{
+ struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
+ struct llist_node *nodes;
+
+ nodes = llist_del_all(&req->ctx->poll_llist);
+ if (nodes)
+ __io_poll_flush(req->ctx, nodes);
+}
+
static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
void *key)
{
@@ -2642,7 +3568,6 @@ static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
struct io_kiocb *req = container_of(poll, struct io_kiocb, poll);
struct io_ring_ctx *ctx = req->ctx;
__poll_t mask = key_to_poll(key);
- unsigned long flags;
/* for instances that support it check for an event match first: */
if (mask && !(mask & poll->events))
@@ -2656,17 +3581,31 @@ static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
* If we have a link timeout we're going to need the completion_lock
* for finalizing the request, mark us as having grabbed that already.
*/
- if (mask && spin_trylock_irqsave(&ctx->completion_lock, flags)) {
- hash_del(&req->hash_node);
- io_poll_complete(req, mask, 0);
- req->flags |= REQ_F_COMP_LOCKED;
- io_put_req(req);
- spin_unlock_irqrestore(&ctx->completion_lock, flags);
+ if (mask) {
+ unsigned long flags;
- io_cqring_ev_posted(ctx);
- } else {
- io_queue_async_work(req);
+ if (llist_empty(&ctx->poll_llist) &&
+ spin_trylock_irqsave(&ctx->completion_lock, flags)) {
+ hash_del(&req->hash_node);
+ io_poll_complete(req, mask, 0);
+ req->flags |= REQ_F_COMP_LOCKED;
+ io_put_req(req);
+ spin_unlock_irqrestore(&ctx->completion_lock, flags);
+
+ io_cqring_ev_posted(ctx);
+ req = NULL;
+ } else {
+ req->result = mask;
+ req->llist_node.next = NULL;
+ /* if the list wasn't empty, we're done */
+ if (!llist_add(&req->llist_node, &ctx->poll_llist))
+ req = NULL;
+ else
+ req->work.func = io_poll_flush;
+ }
}
+ if (req)
+ io_queue_async_work(req);
return 1;
}
@@ -3071,20 +4010,67 @@ static int io_async_cancel(struct io_kiocb *req, struct io_kiocb **nxt)
return 0;
}
+static int io_files_update_prep(struct io_kiocb *req,
+ const struct io_uring_sqe *sqe)
+{
+ if (sqe->flags || sqe->ioprio || sqe->rw_flags)
+ return -EINVAL;
+
+ req->files_update.offset = READ_ONCE(sqe->off);
+ req->files_update.nr_args = READ_ONCE(sqe->len);
+ if (!req->files_update.nr_args)
+ return -EINVAL;
+ req->files_update.arg = READ_ONCE(sqe->addr);
+ return 0;
+}
+
+static int io_files_update(struct io_kiocb *req, bool force_nonblock)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+ struct io_uring_files_update up;
+ int ret;
+
+ if (force_nonblock)
+ return -EAGAIN;
+
+ up.offset = req->files_update.offset;
+ up.fds = req->files_update.arg;
+
+ mutex_lock(&ctx->uring_lock);
+ ret = __io_sqe_files_update(ctx, &up, req->files_update.nr_args);
+ mutex_unlock(&ctx->uring_lock);
+
+ if (ret < 0)
+ req_set_fail_links(req);
+ io_cqring_add_event(req, ret);
+ io_put_req(req);
+ return 0;
+}
+
static int io_req_defer_prep(struct io_kiocb *req,
const struct io_uring_sqe *sqe)
{
ssize_t ret = 0;
+ if (io_op_defs[req->opcode].file_table) {
+ ret = io_grab_files(req);
+ if (unlikely(ret))
+ return ret;
+ }
+
+ io_req_work_grab_env(req, &io_op_defs[req->opcode]);
+
switch (req->opcode) {
case IORING_OP_NOP:
break;
case IORING_OP_READV:
case IORING_OP_READ_FIXED:
+ case IORING_OP_READ:
ret = io_read_prep(req, sqe, true);
break;
case IORING_OP_WRITEV:
case IORING_OP_WRITE_FIXED:
+ case IORING_OP_WRITE:
ret = io_write_prep(req, sqe, true);
break;
case IORING_OP_POLL_ADD:
@@ -3100,9 +4086,11 @@ static int io_req_defer_prep(struct io_kiocb *req,
ret = io_prep_sfr(req, sqe);
break;
case IORING_OP_SENDMSG:
+ case IORING_OP_SEND:
ret = io_sendmsg_prep(req, sqe);
break;
case IORING_OP_RECVMSG:
+ case IORING_OP_RECV:
ret = io_recvmsg_prep(req, sqe);
break;
case IORING_OP_CONNECT:
@@ -3123,6 +4111,33 @@ static int io_req_defer_prep(struct io_kiocb *req,
case IORING_OP_ACCEPT:
ret = io_accept_prep(req, sqe);
break;
+ case IORING_OP_FALLOCATE:
+ ret = io_fallocate_prep(req, sqe);
+ break;
+ case IORING_OP_OPENAT:
+ ret = io_openat_prep(req, sqe);
+ break;
+ case IORING_OP_CLOSE:
+ ret = io_close_prep(req, sqe);
+ break;
+ case IORING_OP_FILES_UPDATE:
+ ret = io_files_update_prep(req, sqe);
+ break;
+ case IORING_OP_STATX:
+ ret = io_statx_prep(req, sqe);
+ break;
+ case IORING_OP_FADVISE:
+ ret = io_fadvise_prep(req, sqe);
+ break;
+ case IORING_OP_MADVISE:
+ ret = io_madvise_prep(req, sqe);
+ break;
+ case IORING_OP_OPENAT2:
+ ret = io_openat2_prep(req, sqe);
+ break;
+ case IORING_OP_EPOLL_CTL:
+ ret = io_epoll_ctl_prep(req, sqe);
+ break;
default:
printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
req->opcode);
@@ -3173,6 +4188,7 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
break;
case IORING_OP_READV:
case IORING_OP_READ_FIXED:
+ case IORING_OP_READ:
if (sqe) {
ret = io_read_prep(req, sqe, force_nonblock);
if (ret < 0)
@@ -3182,6 +4198,7 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
break;
case IORING_OP_WRITEV:
case IORING_OP_WRITE_FIXED:
+ case IORING_OP_WRITE:
if (sqe) {
ret = io_write_prep(req, sqe, force_nonblock);
if (ret < 0)
@@ -3222,20 +4239,28 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
ret = io_sync_file_range(req, nxt, force_nonblock);
break;
case IORING_OP_SENDMSG:
+ case IORING_OP_SEND:
if (sqe) {
ret = io_sendmsg_prep(req, sqe);
if (ret < 0)
break;
}
- ret = io_sendmsg(req, nxt, force_nonblock);
+ if (req->opcode == IORING_OP_SENDMSG)
+ ret = io_sendmsg(req, nxt, force_nonblock);
+ else
+ ret = io_send(req, nxt, force_nonblock);
break;
case IORING_OP_RECVMSG:
+ case IORING_OP_RECV:
if (sqe) {
ret = io_recvmsg_prep(req, sqe);
if (ret)
break;
}
- ret = io_recvmsg(req, nxt, force_nonblock);
+ if (req->opcode == IORING_OP_RECVMSG)
+ ret = io_recvmsg(req, nxt, force_nonblock);
+ else
+ ret = io_recv(req, nxt, force_nonblock);
break;
case IORING_OP_TIMEOUT:
if (sqe) {
@@ -3277,6 +4302,78 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
}
ret = io_async_cancel(req, nxt);
break;
+ case IORING_OP_FALLOCATE:
+ if (sqe) {
+ ret = io_fallocate_prep(req, sqe);
+ if (ret)
+ break;
+ }
+ ret = io_fallocate(req, nxt, force_nonblock);
+ break;
+ case IORING_OP_OPENAT:
+ if (sqe) {
+ ret = io_openat_prep(req, sqe);
+ if (ret)
+ break;
+ }
+ ret = io_openat(req, nxt, force_nonblock);
+ break;
+ case IORING_OP_CLOSE:
+ if (sqe) {
+ ret = io_close_prep(req, sqe);
+ if (ret)
+ break;
+ }
+ ret = io_close(req, nxt, force_nonblock);
+ break;
+ case IORING_OP_FILES_UPDATE:
+ if (sqe) {
+ ret = io_files_update_prep(req, sqe);
+ if (ret)
+ break;
+ }
+ ret = io_files_update(req, force_nonblock);
+ break;
+ case IORING_OP_STATX:
+ if (sqe) {
+ ret = io_statx_prep(req, sqe);
+ if (ret)
+ break;
+ }
+ ret = io_statx(req, nxt, force_nonblock);
+ break;
+ case IORING_OP_FADVISE:
+ if (sqe) {
+ ret = io_fadvise_prep(req, sqe);
+ if (ret)
+ break;
+ }
+ ret = io_fadvise(req, nxt, force_nonblock);
+ break;
+ case IORING_OP_MADVISE:
+ if (sqe) {
+ ret = io_madvise_prep(req, sqe);
+ if (ret)
+ break;
+ }
+ ret = io_madvise(req, nxt, force_nonblock);
+ break;
+ case IORING_OP_OPENAT2:
+ if (sqe) {
+ ret = io_openat2_prep(req, sqe);
+ if (ret)
+ break;
+ }
+ ret = io_openat2(req, nxt, force_nonblock);
+ break;
+ case IORING_OP_EPOLL_CTL:
+ if (sqe) {
+ ret = io_epoll_ctl_prep(req, sqe);
+ if (ret)
+ break;
+ }
+ ret = io_epoll_ctl(req, nxt, force_nonblock);
+ break;
default:
ret = -EINVAL;
break;
@@ -3311,8 +4408,11 @@ static void io_wq_submit_work(struct io_wq_work **workptr)
struct io_kiocb *nxt = NULL;
int ret = 0;
- if (work->flags & IO_WQ_WORK_CANCEL)
+ /* if NO_CANCEL is set, we must still run the work */
+ if ((work->flags & (IO_WQ_WORK_CANCEL|IO_WQ_WORK_NO_CANCEL)) ==
+ IO_WQ_WORK_CANCEL) {
ret = -ECANCELED;
+ }
if (!ret) {
req->has_user = (work->flags & IO_WQ_WORK_HAS_MM) != 0;
@@ -3344,26 +4444,13 @@ static void io_wq_submit_work(struct io_wq_work **workptr)
io_wq_assign_next(workptr, nxt);
}
-static bool io_req_op_valid(int op)
-{
- return op >= IORING_OP_NOP && op < IORING_OP_LAST;
-}
-
-static int io_req_needs_file(struct io_kiocb *req)
+static int io_req_needs_file(struct io_kiocb *req, int fd)
{
- switch (req->opcode) {
- case IORING_OP_NOP:
- case IORING_OP_POLL_REMOVE:
- case IORING_OP_TIMEOUT:
- case IORING_OP_TIMEOUT_REMOVE:
- case IORING_OP_ASYNC_CANCEL:
- case IORING_OP_LINK_TIMEOUT:
+ if (!io_op_defs[req->opcode].needs_file)
return 0;
- default:
- if (io_req_op_valid(req->opcode))
- return 1;
- return -EINVAL;
- }
+ if (fd == -1 && io_op_defs[req->opcode].fd_non_neg)
+ return 0;
+ return 1;
}
static inline struct file *io_file_from_index(struct io_ring_ctx *ctx,
@@ -3371,8 +4458,8 @@ static inline struct file *io_file_from_index(struct io_ring_ctx *ctx,
{
struct fixed_file_table *table;
- table = &ctx->file_table[index >> IORING_FILE_TABLE_SHIFT];
- return table->files[index & IORING_FILE_TABLE_MASK];
+ table = &ctx->file_data->table[index >> IORING_FILE_TABLE_SHIFT];
+ return table->files[index & IORING_FILE_TABLE_MASK];;
}
static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req,
@@ -3380,20 +4467,16 @@ static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req,
{
struct io_ring_ctx *ctx = req->ctx;
unsigned flags;
- int fd, ret;
+ int fd;
flags = READ_ONCE(sqe->flags);
fd = READ_ONCE(sqe->fd);
- if (flags & IOSQE_IO_DRAIN)
- req->flags |= REQ_F_IO_DRAIN;
-
- ret = io_req_needs_file(req);
- if (ret <= 0)
- return ret;
+ if (!io_req_needs_file(req, fd))
+ return 0;
if (flags & IOSQE_FIXED_FILE) {
- if (unlikely(!ctx->file_table ||
+ if (unlikely(!ctx->file_data ||
(unsigned) fd >= ctx->nr_user_files))
return -EBADF;
fd = array_index_nospec(fd, ctx->nr_user_files);
@@ -3401,6 +4484,7 @@ static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req,
if (!req->file)
return -EBADF;
req->flags |= REQ_F_FIXED_FILE;
+ percpu_ref_get(&ctx->file_data->refs);
} else {
if (req->needs_fixed_file)
return -EBADF;
@@ -3418,6 +4502,11 @@ static int io_grab_files(struct io_kiocb *req)
int ret = -EBADF;
struct io_ring_ctx *ctx = req->ctx;
+ if (req->work.files)
+ return 0;
+ if (!ctx->ring_file)
+ return -EBADF;
+
rcu_read_lock();
spin_lock_irq(&ctx->inflight_lock);
/*
@@ -3426,7 +4515,7 @@ static int io_grab_files(struct io_kiocb *req)
* the fd has changed since we started down this path, and disallow
* this operation if it has.
*/
- if (fcheck(req->ring_fd) == req->ring_file) {
+ if (fcheck(ctx->ring_fd) == ctx->ring_file) {
list_add(&req->inflight_entry, &ctx->inflight_list);
req->flags |= REQ_F_INFLIGHT;
req->work.files = current->files;
@@ -3532,7 +4621,8 @@ again:
*/
if (ret == -EAGAIN && (!(req->flags & REQ_F_NOWAIT) ||
(req->flags & REQ_F_MUST_PUNT))) {
- if (req->work.flags & IO_WQ_WORK_NEEDS_FILES) {
+punt:
+ if (io_op_defs[req->opcode].file_table) {
ret = io_grab_files(req);
if (ret)
goto err;
@@ -3567,6 +4657,9 @@ done_req:
if (nxt) {
req = nxt;
nxt = NULL;
+
+ if (req->flags & REQ_F_FORCE_ASYNC)
+ goto punt;
goto again;
}
}
@@ -3575,21 +4668,27 @@ static void io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
int ret;
- if (unlikely(req->ctx->drain_next)) {
- req->flags |= REQ_F_IO_DRAIN;
- req->ctx->drain_next = false;
- }
- req->ctx->drain_next = (req->flags & REQ_F_DRAIN_LINK);
-
ret = io_req_defer(req, sqe);
if (ret) {
if (ret != -EIOCBQUEUED) {
+fail_req:
io_cqring_add_event(req, ret);
req_set_fail_links(req);
io_double_put_req(req);
}
- } else
+ } else if (req->flags & REQ_F_FORCE_ASYNC) {
+ ret = io_req_defer_prep(req, sqe);
+ if (unlikely(ret < 0))
+ goto fail_req;
+ /*
+ * Never try inline submit of IOSQE_ASYNC is set, go straight
+ * to async execution.
+ */
+ req->work.flags |= IO_WQ_WORK_CONCURRENT;
+ io_queue_async_work(req);
+ } else {
__io_queue_sqe(req, sqe);
+ }
}
static inline void io_queue_link_head(struct io_kiocb *req)
@@ -3602,25 +4701,47 @@ static inline void io_queue_link_head(struct io_kiocb *req)
}
#define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK| \
- IOSQE_IO_HARDLINK)
+ IOSQE_IO_HARDLINK | IOSQE_ASYNC)
static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
struct io_submit_state *state, struct io_kiocb **link)
{
+ const struct cred *old_creds = NULL;
struct io_ring_ctx *ctx = req->ctx;
- int ret;
+ unsigned int sqe_flags;
+ int ret, id;
+
+ sqe_flags = READ_ONCE(sqe->flags);
/* enforce forwards compatibility on users */
- if (unlikely(sqe->flags & ~SQE_VALID_FLAGS)) {
+ if (unlikely(sqe_flags & ~SQE_VALID_FLAGS)) {
ret = -EINVAL;
goto err_req;
}
+ id = READ_ONCE(sqe->personality);
+ if (id) {
+ const struct cred *personality_creds;
+
+ personality_creds = idr_find(&ctx->personality_idr, id);
+ if (unlikely(!personality_creds)) {
+ ret = -EINVAL;
+ goto err_req;
+ }
+ old_creds = override_creds(personality_creds);
+ }
+
+ /* same numerical values with corresponding REQ_F_*, safe to copy */
+ req->flags |= sqe_flags & (IOSQE_IO_DRAIN|IOSQE_IO_HARDLINK|
+ IOSQE_ASYNC);
+
ret = io_req_set_file(state, req, sqe);
if (unlikely(ret)) {
err_req:
io_cqring_add_event(req, ret);
io_double_put_req(req);
+ if (old_creds)
+ revert_creds(old_creds);
return false;
}
@@ -3632,14 +4753,19 @@ err_req:
* conditions are true (normal request), then just queue it.
*/
if (*link) {
- struct io_kiocb *prev = *link;
-
- if (sqe->flags & IOSQE_IO_DRAIN)
- (*link)->flags |= REQ_F_DRAIN_LINK | REQ_F_IO_DRAIN;
-
- if (sqe->flags & IOSQE_IO_HARDLINK)
- req->flags |= REQ_F_HARDLINK;
+ struct io_kiocb *head = *link;
+ /*
+ * Taking sequential execution of a link, draining both sides
+ * of the link also fullfils IOSQE_IO_DRAIN semantics for all
+ * requests in the link. So, it drains the head and the
+ * next after the link request. The last one is done via
+ * drain_next flag to persist the effect across calls.
+ */
+ if (sqe_flags & IOSQE_IO_DRAIN) {
+ head->flags |= REQ_F_IO_DRAIN;
+ ctx->drain_next = 1;
+ }
if (io_alloc_async_ctx(req)) {
ret = -EAGAIN;
goto err_req;
@@ -3648,25 +4774,36 @@ err_req:
ret = io_req_defer_prep(req, sqe);
if (ret) {
/* fail even hard links since we don't submit */
- prev->flags |= REQ_F_FAIL_LINK;
+ head->flags |= REQ_F_FAIL_LINK;
goto err_req;
}
- trace_io_uring_link(ctx, req, prev);
- list_add_tail(&req->link_list, &prev->link_list);
- } else if (sqe->flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK)) {
- req->flags |= REQ_F_LINK;
- if (sqe->flags & IOSQE_IO_HARDLINK)
- req->flags |= REQ_F_HARDLINK;
-
- INIT_LIST_HEAD(&req->link_list);
- ret = io_req_defer_prep(req, sqe);
- if (ret)
- req->flags |= REQ_F_FAIL_LINK;
- *link = req;
+ trace_io_uring_link(ctx, req, head);
+ list_add_tail(&req->link_list, &head->link_list);
+
+ /* last request of a link, enqueue the link */
+ if (!(sqe_flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK))) {
+ io_queue_link_head(head);
+ *link = NULL;
+ }
} else {
- io_queue_sqe(req, sqe);
+ if (unlikely(ctx->drain_next)) {
+ req->flags |= REQ_F_IO_DRAIN;
+ req->ctx->drain_next = 0;
+ }
+ if (sqe_flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK)) {
+ req->flags |= REQ_F_LINK;
+ INIT_LIST_HEAD(&req->link_list);
+ ret = io_req_defer_prep(req, sqe);
+ if (ret)
+ req->flags |= REQ_F_FAIL_LINK;
+ *link = req;
+ } else {
+ io_queue_sqe(req, sqe);
+ }
}
+ if (old_creds)
+ revert_creds(old_creds);
return true;
}
@@ -3698,14 +4835,12 @@ static void io_commit_sqring(struct io_ring_ctx *ctx)
{
struct io_rings *rings = ctx->rings;
- if (ctx->cached_sq_head != READ_ONCE(rings->sq.head)) {
- /*
- * 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);
- }
+ /*
+ * 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);
}
/*
@@ -3719,7 +4854,6 @@ static void io_commit_sqring(struct io_ring_ctx *ctx)
static bool io_get_sqring(struct io_ring_ctx *ctx, struct io_kiocb *req,
const struct io_uring_sqe **sqe_ptr)
{
- struct io_rings *rings = ctx->rings;
u32 *sq_array = ctx->sq_array;
unsigned head;
@@ -3731,12 +4865,7 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct io_kiocb *req,
* 2) allows the kernel side to track the head on its own, even
* though the application is the one updating it.
*/
- head = ctx->cached_sq_head;
- /* make sure SQ entry isn't read before tail */
- if (unlikely(head == smp_load_acquire(&rings->sq.tail)))
- return false;
-
- head = READ_ONCE(sq_array[head & ctx->sq_mask]);
+ head = READ_ONCE(sq_array[ctx->cached_sq_head & ctx->sq_mask]);
if (likely(head < ctx->sq_entries)) {
/*
* All io need record the previous position, if LINK vs DARIN,
@@ -3754,7 +4883,7 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct io_kiocb *req,
/* drop invalid entries */
ctx->cached_sq_head++;
ctx->cached_sq_dropped++;
- WRITE_ONCE(rings->sq_dropped, ctx->cached_sq_dropped);
+ WRITE_ONCE(ctx->rings->sq_dropped, ctx->cached_sq_dropped);
return false;
}
@@ -3768,19 +4897,29 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
bool mm_fault = false;
/* if we have a backlog and couldn't flush it all, return BUSY */
- if (!list_empty(&ctx->cq_overflow_list) &&
- !io_cqring_overflow_flush(ctx, false))
- return -EBUSY;
+ if (test_bit(0, &ctx->sq_check_overflow)) {
+ if (!list_empty(&ctx->cq_overflow_list) &&
+ !io_cqring_overflow_flush(ctx, false))
+ return -EBUSY;
+ }
+
+ /* make sure SQ entry isn't read before tail */
+ nr = min3(nr, ctx->sq_entries, io_sqring_entries(ctx));
+
+ if (!percpu_ref_tryget_many(&ctx->refs, nr))
+ return -EAGAIN;
if (nr > IO_PLUG_THRESHOLD) {
io_submit_state_start(&state, nr);
statep = &state;
}
+ ctx->ring_fd = ring_fd;
+ ctx->ring_file = ring_file;
+
for (i = 0; i < nr; i++) {
const struct io_uring_sqe *sqe;
struct io_kiocb *req;
- unsigned int sqe_flags;
req = io_get_req(ctx, statep);
if (unlikely(!req)) {
@@ -3789,11 +4928,20 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
break;
}
if (!io_get_sqring(ctx, req, &sqe)) {
- __io_free_req(req);
+ __io_req_do_free(req);
break;
}
- if (io_req_needs_user(req) && !*mm) {
+ /* will complete beyond this point, count as submitted */
+ submitted++;
+
+ if (unlikely(req->opcode >= IORING_OP_LAST)) {
+ io_cqring_add_event(req, -EINVAL);
+ io_double_put_req(req);
+ break;
+ }
+
+ if (io_op_defs[req->opcode].needs_mm && !*mm) {
mm_fault = mm_fault || !mmget_not_zero(ctx->sqo_mm);
if (!mm_fault) {
use_mm(ctx->sqo_mm);
@@ -3801,27 +4949,20 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
}
}
- submitted++;
- sqe_flags = sqe->flags;
-
- req->ring_file = ring_file;
- req->ring_fd = ring_fd;
req->has_user = *mm != NULL;
req->in_async = async;
req->needs_fixed_file = async;
- trace_io_uring_submit_sqe(ctx, req->user_data, true, async);
+ trace_io_uring_submit_sqe(ctx, req->opcode, req->user_data,
+ true, async);
if (!io_submit_sqe(req, sqe, statep, &link))
break;
- /*
- * If previous wasn't linked and we have a linked command,
- * that's the end of the chain. Submit the previous link.
- */
- if (!(sqe_flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK)) && link) {
- io_queue_link_head(link);
- link = NULL;
- }
}
+ if (unlikely(submitted != nr)) {
+ int ref_used = (submitted == -EAGAIN) ? 0 : submitted;
+
+ percpu_ref_put_many(&ctx->refs, nr - ref_used);
+ }
if (link)
io_queue_link_head(link);
if (statep)
@@ -3944,7 +5085,6 @@ static int io_sq_thread(void *data)
ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP;
}
- to_submit = min(to_submit, ctx->sq_entries);
mutex_lock(&ctx->uring_lock);
ret = io_submit_sqes(ctx, to_submit, NULL, -1, &cur_mm, true);
mutex_unlock(&ctx->uring_lock);
@@ -4075,19 +5215,40 @@ static void __io_sqe_files_unregister(struct io_ring_ctx *ctx)
#endif
}
+static void io_file_ref_kill(struct percpu_ref *ref)
+{
+ struct fixed_file_data *data;
+
+ data = container_of(ref, struct fixed_file_data, refs);
+ complete(&data->done);
+}
+
static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
{
+ struct fixed_file_data *data = ctx->file_data;
unsigned nr_tables, i;
- if (!ctx->file_table)
+ if (!data)
return -ENXIO;
+ /* protect against inflight atomic switch, which drops the ref */
+ percpu_ref_get(&data->refs);
+ /* wait for existing switches */
+ flush_work(&data->ref_work);
+ percpu_ref_kill_and_confirm(&data->refs, io_file_ref_kill);
+ wait_for_completion(&data->done);
+ percpu_ref_put(&data->refs);
+ /* flush potential new switch */
+ flush_work(&data->ref_work);
+ percpu_ref_exit(&data->refs);
+
__io_sqe_files_unregister(ctx);
nr_tables = DIV_ROUND_UP(ctx->nr_user_files, IORING_MAX_FILES_TABLE);
for (i = 0; i < nr_tables; i++)
- kfree(ctx->file_table[i].files);
- kfree(ctx->file_table);
- ctx->file_table = NULL;
+ kfree(data->table[i].files);
+ kfree(data->table);
+ kfree(data);
+ ctx->file_data = NULL;
ctx->nr_user_files = 0;
return 0;
}
@@ -4118,16 +5279,6 @@ static void io_finish_async(struct io_ring_ctx *ctx)
}
#if defined(CONFIG_UNIX)
-static void io_destruct_skb(struct sk_buff *skb)
-{
- struct io_ring_ctx *ctx = skb->sk->sk_user_data;
-
- if (ctx->io_wq)
- io_wq_flush(ctx->io_wq);
-
- unix_destruct_scm(skb);
-}
-
/*
* 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
@@ -4175,7 +5326,7 @@ static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset)
fpl->max = SCM_MAX_FD;
fpl->count = nr_files;
UNIXCB(skb).fp = fpl;
- skb->destructor = io_destruct_skb;
+ skb->destructor = unix_destruct_scm;
refcount_add(skb->truesize, &sk->sk_wmem_alloc);
skb_queue_head(&sk->sk_receive_queue, skb);
@@ -4237,7 +5388,7 @@ static int io_sqe_alloc_file_tables(struct io_ring_ctx *ctx, unsigned nr_tables,
int i;
for (i = 0; i < nr_tables; i++) {
- struct fixed_file_table *table = &ctx->file_table[i];
+ struct fixed_file_table *table = &ctx->file_data->table[i];
unsigned this_files;
this_files = min(nr_files, IORING_MAX_FILES_TABLE);
@@ -4252,36 +5403,159 @@ static int io_sqe_alloc_file_tables(struct io_ring_ctx *ctx, unsigned nr_tables,
return 0;
for (i = 0; i < nr_tables; i++) {
- struct fixed_file_table *table = &ctx->file_table[i];
+ struct fixed_file_table *table = &ctx->file_data->table[i];
kfree(table->files);
}
return 1;
}
+static void io_ring_file_put(struct io_ring_ctx *ctx, struct file *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;
+
+ __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
+}
+
+struct io_file_put {
+ struct llist_node llist;
+ struct file *file;
+ struct completion *done;
+};
+
+static void io_ring_file_ref_switch(struct work_struct *work)
+{
+ struct io_file_put *pfile, *tmp;
+ struct fixed_file_data *data;
+ struct llist_node *node;
+
+ data = container_of(work, struct fixed_file_data, ref_work);
+
+ while ((node = llist_del_all(&data->put_llist)) != NULL) {
+ llist_for_each_entry_safe(pfile, tmp, node, llist) {
+ io_ring_file_put(data->ctx, pfile->file);
+ if (pfile->done)
+ complete(pfile->done);
+ else
+ kfree(pfile);
+ }
+ }
+
+ percpu_ref_get(&data->refs);
+ percpu_ref_switch_to_percpu(&data->refs);
+}
+
+static void io_file_data_ref_zero(struct percpu_ref *ref)
+{
+ struct fixed_file_data *data;
+
+ data = container_of(ref, struct fixed_file_data, refs);
+
+ /* we can't safely switch from inside this context, punt to wq */
+ queue_work(system_wq, &data->ref_work);
+}
+
static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
unsigned nr_args)
{
__s32 __user *fds = (__s32 __user *) arg;
unsigned nr_tables;
+ struct file *file;
int fd, ret = 0;
unsigned i;
- if (ctx->file_table)
+ if (ctx->file_data)
return -EBUSY;
if (!nr_args)
return -EINVAL;
if (nr_args > IORING_MAX_FIXED_FILES)
return -EMFILE;
+ ctx->file_data = kzalloc(sizeof(*ctx->file_data), GFP_KERNEL);
+ if (!ctx->file_data)
+ return -ENOMEM;
+ ctx->file_data->ctx = ctx;
+ init_completion(&ctx->file_data->done);
+
nr_tables = DIV_ROUND_UP(nr_args, IORING_MAX_FILES_TABLE);
- ctx->file_table = kcalloc(nr_tables, sizeof(struct fixed_file_table),
+ ctx->file_data->table = kcalloc(nr_tables,
+ sizeof(struct fixed_file_table),
GFP_KERNEL);
- if (!ctx->file_table)
+ if (!ctx->file_data->table) {
+ kfree(ctx->file_data);
+ ctx->file_data = NULL;
return -ENOMEM;
+ }
+
+ if (percpu_ref_init(&ctx->file_data->refs, io_file_data_ref_zero,
+ PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) {
+ kfree(ctx->file_data->table);
+ kfree(ctx->file_data);
+ ctx->file_data = NULL;
+ return -ENOMEM;
+ }
+ ctx->file_data->put_llist.first = NULL;
+ INIT_WORK(&ctx->file_data->ref_work, io_ring_file_ref_switch);
if (io_sqe_alloc_file_tables(ctx, nr_tables, nr_args)) {
- kfree(ctx->file_table);
- ctx->file_table = NULL;
+ percpu_ref_exit(&ctx->file_data->refs);
+ kfree(ctx->file_data->table);
+ kfree(ctx->file_data);
+ ctx->file_data = NULL;
return -ENOMEM;
}
@@ -4298,13 +5572,14 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
continue;
}
- table = &ctx->file_table[i >> IORING_FILE_TABLE_SHIFT];
+ table = &ctx->file_data->table[i >> IORING_FILE_TABLE_SHIFT];
index = i & IORING_FILE_TABLE_MASK;
- table->files[index] = fget(fd);
+ file = fget(fd);
ret = -EBADF;
- if (!table->files[index])
+ if (!file)
break;
+
/*
* Don't allow io_uring instances to be registered. If UNIX
* isn't enabled, then this causes a reference cycle and this
@@ -4312,26 +5587,26 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
* 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 (table->files[index]->f_op == &io_uring_fops) {
- fput(table->files[index]);
+ if (file->f_op == &io_uring_fops) {
+ fput(file);
break;
}
ret = 0;
+ table->files[index] = file;
}
if (ret) {
for (i = 0; i < ctx->nr_user_files; i++) {
- struct file *file;
-
file = io_file_from_index(ctx, i);
if (file)
fput(file);
}
for (i = 0; i < nr_tables; i++)
- kfree(ctx->file_table[i].files);
+ kfree(ctx->file_data->table[i].files);
- kfree(ctx->file_table);
- ctx->file_table = NULL;
+ kfree(ctx->file_data->table);
+ kfree(ctx->file_data);
+ ctx->file_data = NULL;
ctx->nr_user_files = 0;
return ret;
}
@@ -4343,69 +5618,6 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
return ret;
}
-static void io_sqe_file_unregister(struct io_ring_ctx *ctx, int index)
-{
-#if defined(CONFIG_UNIX)
- struct file *file = io_file_from_index(ctx, index);
- struct sock *sock = ctx->ring_sock->sk;
- struct sk_buff_head list, *head = &sock->sk_receive_queue;
- struct sk_buff *skb;
- int i;
-
- __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(io_file_from_index(ctx, index));
-#endif
-}
-
static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file,
int index)
{
@@ -4449,29 +5661,65 @@ static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file,
#endif
}
-static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg,
- unsigned nr_args)
+static void io_atomic_switch(struct percpu_ref *ref)
{
- struct io_uring_files_update up;
+ struct fixed_file_data *data;
+
+ data = container_of(ref, struct fixed_file_data, refs);
+ clear_bit(FFD_F_ATOMIC, &data->state);
+}
+
+static bool io_queue_file_removal(struct fixed_file_data *data,
+ struct file *file)
+{
+ struct io_file_put *pfile, pfile_stack;
+ DECLARE_COMPLETION_ONSTACK(done);
+
+ /*
+ * If we fail allocating the struct we need for doing async reomval
+ * of this file, just punt to sync and wait for it.
+ */
+ pfile = kzalloc(sizeof(*pfile), GFP_KERNEL);
+ if (!pfile) {
+ pfile = &pfile_stack;
+ pfile->done = &done;
+ }
+
+ pfile->file = file;
+ llist_add(&pfile->llist, &data->put_llist);
+
+ if (pfile == &pfile_stack) {
+ if (!test_and_set_bit(FFD_F_ATOMIC, &data->state)) {
+ percpu_ref_put(&data->refs);
+ percpu_ref_switch_to_atomic(&data->refs,
+ io_atomic_switch);
+ }
+ wait_for_completion(&done);
+ flush_work(&data->ref_work);
+ return false;
+ }
+
+ return true;
+}
+
+static int __io_sqe_files_update(struct io_ring_ctx *ctx,
+ struct io_uring_files_update *up,
+ unsigned nr_args)
+{
+ struct fixed_file_data *data = ctx->file_data;
+ bool ref_switch = false;
+ struct file *file;
__s32 __user *fds;
int fd, i, err;
__u32 done;
- if (!ctx->file_table)
- return -ENXIO;
- if (!nr_args)
- return -EINVAL;
- if (copy_from_user(&up, arg, sizeof(up)))
- return -EFAULT;
- if (up.resv)
- return -EINVAL;
- if (check_add_overflow(up.offset, nr_args, &done))
+ if (check_add_overflow(up->offset, nr_args, &done))
return -EOVERFLOW;
if (done > ctx->nr_user_files)
return -EINVAL;
done = 0;
- fds = u64_to_user_ptr(up.fds);
+ fds = u64_to_user_ptr(up->fds);
while (nr_args) {
struct fixed_file_table *table;
unsigned index;
@@ -4481,16 +5729,16 @@ static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg,
err = -EFAULT;
break;
}
- i = array_index_nospec(up.offset, ctx->nr_user_files);
- table = &ctx->file_table[i >> IORING_FILE_TABLE_SHIFT];
+ i = array_index_nospec(up->offset, ctx->nr_user_files);
+ table = &ctx->file_data->table[i >> IORING_FILE_TABLE_SHIFT];
index = i & IORING_FILE_TABLE_MASK;
if (table->files[index]) {
- io_sqe_file_unregister(ctx, i);
+ file = io_file_from_index(ctx, index);
table->files[index] = NULL;
+ if (io_queue_file_removal(data, file))
+ ref_switch = true;
}
if (fd != -1) {
- struct file *file;
-
file = fget(fd);
if (!file) {
err = -EBADF;
@@ -4516,11 +5764,32 @@ static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg,
}
nr_args--;
done++;
- up.offset++;
+ up->offset++;
+ }
+
+ if (ref_switch && !test_and_set_bit(FFD_F_ATOMIC, &data->state)) {
+ percpu_ref_put(&data->refs);
+ percpu_ref_switch_to_atomic(&data->refs, io_atomic_switch);
}
return done ? done : err;
}
+static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg,
+ unsigned nr_args)
+{
+ struct io_uring_files_update up;
+
+ if (!ctx->file_data)
+ return -ENXIO;
+ if (!nr_args)
+ return -EINVAL;
+ if (copy_from_user(&up, arg, sizeof(up)))
+ return -EFAULT;
+ if (up.resv)
+ return -EINVAL;
+
+ return __io_sqe_files_update(ctx, &up, nr_args);
+}
static void io_put_work(struct io_wq_work *work)
{
@@ -4536,11 +5805,56 @@ static void io_get_work(struct io_wq_work *work)
refcount_inc(&req->refs);
}
+static int io_init_wq_offload(struct io_ring_ctx *ctx,
+ struct io_uring_params *p)
+{
+ struct io_wq_data data;
+ struct fd f;
+ struct io_ring_ctx *ctx_attach;
+ unsigned int concurrency;
+ int ret = 0;
+
+ data.user = ctx->user;
+ data.get_work = io_get_work;
+ data.put_work = io_put_work;
+
+ if (!(p->flags & IORING_SETUP_ATTACH_WQ)) {
+ /* Do QD, or 4 * CPUS, whatever is smallest */
+ concurrency = min(ctx->sq_entries, 4 * num_online_cpus());
+
+ ctx->io_wq = io_wq_create(concurrency, &data);
+ if (IS_ERR(ctx->io_wq)) {
+ ret = PTR_ERR(ctx->io_wq);
+ ctx->io_wq = NULL;
+ }
+ return ret;
+ }
+
+ f = fdget(p->wq_fd);
+ if (!f.file)
+ return -EBADF;
+
+ if (f.file->f_op != &io_uring_fops) {
+ ret = -EINVAL;
+ goto out_fput;
+ }
+
+ ctx_attach = f.file->private_data;
+ /* @io_wq is protected by holding the fd */
+ if (!io_wq_get(ctx_attach->io_wq, &data)) {
+ ret = -EINVAL;
+ goto out_fput;
+ }
+
+ ctx->io_wq = ctx_attach->io_wq;
+out_fput:
+ fdput(f);
+ return ret;
+}
+
static int io_sq_offload_start(struct io_ring_ctx *ctx,
struct io_uring_params *p)
{
- struct io_wq_data data;
- unsigned concurrency;
int ret;
init_waitqueue_head(&ctx->sqo_wait);
@@ -4584,20 +5898,9 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx,
goto err;
}
- data.mm = ctx->sqo_mm;
- data.user = ctx->user;
- data.creds = ctx->creds;
- data.get_work = io_get_work;
- data.put_work = io_put_work;
-
- /* Do QD, or 4 * CPUS, whatever is smallest */
- concurrency = min(ctx->sq_entries, 4 * num_online_cpus());
- ctx->io_wq = io_wq_create(concurrency, &data);
- if (IS_ERR(ctx->io_wq)) {
- ret = PTR_ERR(ctx->io_wq);
- ctx->io_wq = NULL;
+ ret = io_init_wq_offload(ctx, p);
+ if (ret)
goto err;
- }
return 0;
err:
@@ -4702,7 +6005,7 @@ static int io_sqe_buffer_unregister(struct io_ring_ctx *ctx)
struct io_mapped_ubuf *imu = &ctx->user_bufs[i];
for (j = 0; j < imu->nr_bvecs; j++)
- put_user_page(imu->bvec[j].bv_page);
+ unpin_user_page(imu->bvec[j].bv_page);
if (ctx->account_mem)
io_unaccount_mem(ctx->user, imu->nr_bvecs);
@@ -4823,7 +6126,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
ret = 0;
down_read(&current->mm->mmap_sem);
- pret = get_user_pages(ubuf, nr_pages,
+ pret = pin_user_pages(ubuf, nr_pages,
FOLL_WRITE | FOLL_LONGTERM,
pages, vmas);
if (pret == nr_pages) {
@@ -4847,7 +6150,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
* release any pages we did get
*/
if (pret > 0)
- put_user_pages(pages, pret);
+ unpin_user_pages(pages, pret);
if (ctx->account_mem)
io_unaccount_mem(ctx->user, nr_pages);
kvfree(imu->bvec);
@@ -4975,6 +6278,17 @@ static int io_uring_fasync(int fd, struct file *file, int on)
return fasync_helper(fd, file, on, &ctx->cq_fasync);
}
+static int io_remove_personalities(int id, void *p, void *data)
+{
+ struct io_ring_ctx *ctx = data;
+ const struct cred *cred;
+
+ cred = idr_remove(&ctx->personality_idr, id);
+ if (cred)
+ put_cred(cred);
+ return 0;
+}
+
static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
{
mutex_lock(&ctx->uring_lock);
@@ -4991,6 +6305,7 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
/* if we failed setting up the ctx, we might not have any rings */
if (ctx->rings)
io_cqring_overflow_flush(ctx, true);
+ idr_for_each(&ctx->personality_idr, io_remove_personalities, ctx);
wait_for_completion(&ctx->completions[0]);
io_ring_ctx_free(ctx);
}
@@ -5157,7 +6472,6 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
} else if (to_submit) {
struct mm_struct *cur_mm;
- to_submit = min(to_submit, ctx->sq_entries);
mutex_lock(&ctx->uring_lock);
/* already have mm, so io_submit_sqes() won't try to grab it */
cur_mm = ctx->sqo_mm;
@@ -5273,7 +6587,6 @@ static int io_uring_get_fd(struct io_ring_ctx *ctx)
#if defined(CONFIG_UNIX)
ctx->ring_sock->file = file;
- ctx->ring_sock->sk->sk_user_data = ctx;
#endif
fd_install(ret, file);
return ret;
@@ -5292,8 +6605,13 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
bool account_mem;
int ret;
- if (!entries || entries > IORING_MAX_ENTRIES)
+ 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
@@ -5310,8 +6628,13 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
* to a power-of-two, if it isn't already. We do NOT impose
* any cq vs sq ring sizing.
*/
- if (p->cq_entries < p->sq_entries || p->cq_entries > IORING_MAX_CQ_ENTRIES)
+ if (p->cq_entries < p->sq_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);
} else {
p->cq_entries = 2 * p->sq_entries;
@@ -5376,7 +6699,8 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
goto err;
p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP |
- IORING_FEAT_SUBMIT_STABLE;
+ IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
+ IORING_FEAT_CUR_PERSONALITY;
trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags);
return ret;
err:
@@ -5403,7 +6727,8 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
}
if (p.flags & ~(IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL |
- IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE))
+ IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE |
+ IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ))
return -EINVAL;
ret = io_uring_create(entries, &p);
@@ -5422,6 +6747,84 @@ SYSCALL_DEFINE2(io_uring_setup, u32, entries,
return io_uring_setup(entries, params);
}
+static 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 = get_current_cred();
+ int id;
+
+ id = idr_alloc_cyclic(&ctx->personality_idr, (void *) creds, 1,
+ USHRT_MAX, GFP_KERNEL);
+ if (id < 0)
+ put_cred(creds);
+ return id;
+}
+
+static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id)
+{
+ const struct cred *old_creds;
+
+ old_creds = idr_remove(&ctx->personality_idr, id);
+ if (old_creds) {
+ put_cred(old_creds);
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
+static bool io_register_op_must_quiesce(int op)
+{
+ switch (op) {
+ case IORING_UNREGISTER_FILES:
+ case IORING_REGISTER_FILES_UPDATE:
+ case IORING_REGISTER_PROBE:
+ case IORING_REGISTER_PERSONALITY:
+ case IORING_UNREGISTER_PERSONALITY:
+ return false;
+ default:
+ return true;
+ }
+}
+
static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
void __user *arg, unsigned nr_args)
__releases(ctx->uring_lock)
@@ -5437,18 +6840,26 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
if (percpu_ref_is_dying(&ctx->refs))
return -ENXIO;
- percpu_ref_kill(&ctx->refs);
+ if (io_register_op_must_quiesce(opcode)) {
+ percpu_ref_kill(&ctx->refs);
- /*
- * Drop uring mutex before waiting for references to exit. If another
- * thread is currently inside io_uring_enter() it might need to grab
- * the uring_lock to make progress. If we hold it here across the drain
- * wait, then we can deadlock. It's safe to drop the mutex here, since
- * no new references will come in after we've killed the percpu ref.
- */
- mutex_unlock(&ctx->uring_lock);
- wait_for_completion(&ctx->completions[0]);
- mutex_lock(&ctx->uring_lock);
+ /*
+ * Drop uring mutex before waiting for references to exit. If
+ * another thread is currently inside io_uring_enter() it might
+ * need to grab the uring_lock to make progress. If we hold it
+ * here across the drain wait, then we can deadlock. It's safe
+ * to drop the mutex here, since no new references will come in
+ * after we've killed the percpu ref.
+ */
+ mutex_unlock(&ctx->uring_lock);
+ ret = wait_for_completion_interruptible(&ctx->completions[0]);
+ mutex_lock(&ctx->uring_lock);
+ if (ret) {
+ percpu_ref_resurrect(&ctx->refs);
+ ret = -EINTR;
+ goto out;
+ }
+ }
switch (opcode) {
case IORING_REGISTER_BUFFERS:
@@ -5473,10 +6884,17 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
ret = io_sqe_files_update(ctx, arg, nr_args);
break;
case IORING_REGISTER_EVENTFD:
+ case IORING_REGISTER_EVENTFD_ASYNC:
ret = -EINVAL;
if (nr_args != 1)
break;
ret = io_eventfd_register(ctx, arg);
+ if (ret)
+ break;
+ if (opcode == IORING_REGISTER_EVENTFD_ASYNC)
+ ctx->eventfd_async = 1;
+ else
+ ctx->eventfd_async = 0;
break;
case IORING_UNREGISTER_EVENTFD:
ret = -EINVAL;
@@ -5484,14 +6902,35 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
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;
default:
ret = -EINVAL;
break;
}
- /* bring the ctx back to life */
- reinit_completion(&ctx->completions[0]);
- percpu_ref_reinit(&ctx->refs);
+ if (io_register_op_must_quiesce(opcode)) {
+ /* bring the ctx back to life */
+ percpu_ref_reinit(&ctx->refs);
+out:
+ reinit_completion(&ctx->completions[0]);
+ }
return ret;
}
@@ -5524,6 +6963,7 @@ out_fput:
static int __init io_uring_init(void)
{
+ BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST);
req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC);
return 0;
};
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 2f5e4e5b97e1..7c9a5df5a597 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -467,7 +467,7 @@ EXPORT_SYMBOL(generic_block_fiemap);
* Only the l_start, l_len and l_whence fields of the 'struct space_resv'
* are used here, rest are ignored.
*/
-int ioctl_preallocate(struct file *filp, int mode, void __user *argp)
+static int ioctl_preallocate(struct file *filp, int mode, void __user *argp)
{
struct inode *inode = file_inode(filp);
struct space_resv sr;
@@ -495,8 +495,8 @@ int ioctl_preallocate(struct file *filp, int mode, void __user *argp)
/* on ia32 l_start is on a 32-bit boundary */
#if defined CONFIG_COMPAT && defined(CONFIG_X86_64)
/* just account for different alignment */
-int compat_ioctl_preallocate(struct file *file, int mode,
- struct space_resv_32 __user *argp)
+static int compat_ioctl_preallocate(struct file *file, int mode,
+ struct space_resv_32 __user *argp)
{
struct inode *inode = file_inode(file);
struct space_resv_32 sr;
@@ -521,11 +521,9 @@ int compat_ioctl_preallocate(struct file *file, int mode,
}
#endif
-static int file_ioctl(struct file *filp, unsigned int cmd,
- unsigned long arg)
+static int file_ioctl(struct file *filp, unsigned int cmd, int __user *p)
{
struct inode *inode = file_inode(filp);
- int __user *p = (int __user *)arg;
switch (cmd) {
case FIBMAP:
@@ -542,7 +540,7 @@ static int file_ioctl(struct file *filp, unsigned int cmd,
return ioctl_preallocate(filp, FALLOC_FL_ZERO_RANGE, p);
}
- return vfs_ioctl(filp, cmd, arg);
+ return -ENOIOCTLCMD;
}
static int ioctl_fionbio(struct file *filp, int __user *argp)
@@ -661,53 +659,48 @@ out:
}
/*
- * When you add any new common ioctls to the switches above and below
- * please update compat_sys_ioctl() too.
- *
* do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d.
* It's just a simple helper for sys_ioctl and compat_sys_ioctl.
+ *
+ * When you add any new common ioctls to the switches above and below,
+ * please ensure they have compatible arguments in compat mode.
*/
-int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
- unsigned long arg)
+static int do_vfs_ioctl(struct file *filp, unsigned int fd,
+ unsigned int cmd, unsigned long arg)
{
- int error = 0;
void __user *argp = (void __user *)arg;
struct inode *inode = file_inode(filp);
switch (cmd) {
case FIOCLEX:
set_close_on_exec(fd, 1);
- break;
+ return 0;
case FIONCLEX:
set_close_on_exec(fd, 0);
- break;
+ return 0;
case FIONBIO:
- error = ioctl_fionbio(filp, argp);
- break;
+ return ioctl_fionbio(filp, argp);
case FIOASYNC:
- error = ioctl_fioasync(fd, filp, argp);
- break;
+ return ioctl_fioasync(fd, filp, argp);
case FIOQSIZE:
if (S_ISDIR(inode->i_mode) || S_ISREG(inode->i_mode) ||
S_ISLNK(inode->i_mode)) {
loff_t res = inode_get_bytes(inode);
- error = copy_to_user(argp, &res, sizeof(res)) ?
- -EFAULT : 0;
- } else
- error = -ENOTTY;
- break;
+ return copy_to_user(argp, &res, sizeof(res)) ?
+ -EFAULT : 0;
+ }
+
+ return -ENOTTY;
case FIFREEZE:
- error = ioctl_fsfreeze(filp);
- break;
+ return ioctl_fsfreeze(filp);
case FITHAW:
- error = ioctl_fsthaw(filp);
- break;
+ return ioctl_fsthaw(filp);
case FS_IOC_FIEMAP:
return ioctl_fiemap(filp, argp);
@@ -716,6 +709,7 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
/* anon_bdev filesystems may not have a block size */
if (!inode->i_sb->s_blocksize)
return -EINVAL;
+
return put_user(inode->i_sb->s_blocksize, (int __user *)argp);
case FICLONE:
@@ -729,24 +723,30 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
default:
if (S_ISREG(inode->i_mode))
- error = file_ioctl(filp, cmd, arg);
- else
- error = vfs_ioctl(filp, cmd, arg);
+ return file_ioctl(filp, cmd, argp);
break;
}
- return error;
+
+ return -ENOIOCTLCMD;
}
int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg)
{
- int error;
struct fd f = fdget(fd);
+ int error;
if (!f.file)
return -EBADF;
+
error = security_file_ioctl(f.file, cmd, arg);
- if (!error)
- error = do_vfs_ioctl(f.file, fd, cmd, arg);
+ if (error)
+ goto out;
+
+ error = do_vfs_ioctl(f.file, fd, cmd, arg);
+ if (error == -ENOIOCTLCMD)
+ error = vfs_ioctl(f.file, cmd, arg);
+
+out:
fdput(f);
return error;
}
@@ -788,4 +788,65 @@ long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
return file->f_op->unlocked_ioctl(file, cmd, (unsigned long)compat_ptr(arg));
}
EXPORT_SYMBOL(compat_ptr_ioctl);
+
+COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd,
+ compat_ulong_t, arg)
+{
+ struct fd f = fdget(fd);
+ int error;
+
+ if (!f.file)
+ return -EBADF;
+
+ /* RED-PEN how should LSM module know it's handling 32bit? */
+ error = security_file_ioctl(f.file, cmd, arg);
+ if (error)
+ goto out;
+
+ switch (cmd) {
+ /* FICLONE takes an int argument, so don't use compat_ptr() */
+ case FICLONE:
+ error = ioctl_file_clone(f.file, arg, 0, 0, 0);
+ break;
+
+#if defined(CONFIG_X86_64)
+ /* these get messy on amd64 due to alignment differences */
+ case FS_IOC_RESVSP_32:
+ case FS_IOC_RESVSP64_32:
+ error = compat_ioctl_preallocate(f.file, 0, compat_ptr(arg));
+ break;
+ case FS_IOC_UNRESVSP_32:
+ case FS_IOC_UNRESVSP64_32:
+ error = compat_ioctl_preallocate(f.file, FALLOC_FL_PUNCH_HOLE,
+ compat_ptr(arg));
+ break;
+ case FS_IOC_ZERO_RANGE_32:
+ error = compat_ioctl_preallocate(f.file, FALLOC_FL_ZERO_RANGE,
+ compat_ptr(arg));
+ break;
+#endif
+
+ /*
+ * everything else in do_vfs_ioctl() takes either a compatible
+ * pointer argument or no argument -- call it with a modified
+ * argument.
+ */
+ default:
+ error = do_vfs_ioctl(f.file, fd, cmd,
+ (unsigned long)compat_ptr(arg));
+ if (error != -ENOIOCTLCMD)
+ break;
+
+ if (f.file->f_op->compat_ioctl)
+ error = f.file->f_op->compat_ioctl(f.file, cmd, arg);
+ if (error == -ENOIOCTLCMD)
+ error = -ENOTTY;
+ break;
+ }
+
+ out:
+ fdput(f);
+
+ return error;
+}
#endif
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 828444e14d09..7c84c4c027c4 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1077,24 +1077,16 @@ vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops)
struct page *page = vmf->page;
struct inode *inode = file_inode(vmf->vma->vm_file);
unsigned long length;
- loff_t offset, size;
+ loff_t offset;
ssize_t ret;
lock_page(page);
- size = i_size_read(inode);
- offset = page_offset(page);
- if (page->mapping != inode->i_mapping || offset > size) {
- /* We overload EFAULT to mean page got truncated */
- ret = -EFAULT;
+ ret = page_mkwrite_check_truncate(page, inode);
+ if (ret < 0)
goto out_unlock;
- }
-
- /* page is wholly or partially inside EOF */
- if (offset > size - PAGE_SIZE)
- length = offset_in_page(size);
- else
- length = PAGE_SIZE;
+ length = ret;
+ offset = page_offset(page);
while (length > 0) {
ret = iomap_apply(inode, offset, length,
IOMAP_WRITE | IOMAP_FAULT, ops, page,
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 8fff6677a5da..96bf33986d03 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -164,7 +164,7 @@ void __jbd2_log_wait_for_space(journal_t *journal)
"journal space in %s\n", __func__,
journal->j_devname);
WARN_ON(1);
- jbd2_journal_abort(journal, 0);
+ jbd2_journal_abort(journal, -EIO);
}
write_lock(&journal->j_state_lock);
} else {
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 7f0b362b3842..2494095e0340 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -782,7 +782,7 @@ start_journal_io:
err = journal_submit_commit_record(journal, commit_transaction,
&cbh, crc32_sum);
if (err)
- __jbd2_journal_abort_hard(journal);
+ jbd2_journal_abort(journal, err);
}
blk_finish_plug(&plug);
@@ -875,7 +875,7 @@ start_journal_io:
err = journal_submit_commit_record(journal, commit_transaction,
&cbh, crc32_sum);
if (err)
- __jbd2_journal_abort_hard(journal);
+ jbd2_journal_abort(journal, err);
}
if (cbh)
err = journal_wait_on_commit_record(journal, cbh);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 5e408ee24a1a..60bf8ff78913 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -96,7 +96,6 @@ EXPORT_SYMBOL(jbd2_journal_release_jbd_inode);
EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate);
EXPORT_SYMBOL(jbd2_inode_cache);
-static void __journal_abort_soft (journal_t *journal, int errno);
static int jbd2_journal_create_slab(size_t slab_size);
#ifdef CONFIG_JBD2_DEBUG
@@ -805,7 +804,7 @@ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr,
"at offset %lu on %s\n",
__func__, blocknr, journal->j_devname);
err = -EIO;
- __journal_abort_soft(journal, err);
+ jbd2_journal_abort(journal, err);
}
} else {
*retp = blocknr; /* +journal->j_blk_offset */
@@ -982,6 +981,7 @@ static void *jbd2_seq_info_start(struct seq_file *seq, loff_t *pos)
static void *jbd2_seq_info_next(struct seq_file *seq, void *v, loff_t *pos)
{
+ (*pos)++;
return NULL;
}
@@ -1710,6 +1710,11 @@ int jbd2_journal_load(journal_t *journal)
journal->j_devname);
return -EFSCORRUPTED;
}
+ /*
+ * clear JBD2_ABORT flag initialized in journal_init_common
+ * here to update log tail information with the newest seq.
+ */
+ journal->j_flags &= ~JBD2_ABORT;
/* OK, we've finished with the dynamic journal bits:
* reinitialise the dynamic contents of the superblock in memory
@@ -1717,7 +1722,6 @@ int jbd2_journal_load(journal_t *journal)
if (journal_reset(journal))
goto recovery_error;
- journal->j_flags &= ~JBD2_ABORT;
journal->j_flags |= JBD2_LOADED;
return 0;
@@ -2098,67 +2102,6 @@ int jbd2_journal_wipe(journal_t *journal, int write)
return err;
}
-/*
- * Journal abort has very specific semantics, which we describe
- * for journal abort.
- *
- * Two internal functions, which provide abort to the jbd layer
- * itself are here.
- */
-
-/*
- * Quick version for internal journal use (doesn't lock the journal).
- * Aborts hard --- we mark the abort as occurred, but do _nothing_ else,
- * and don't attempt to make any other journal updates.
- */
-void __jbd2_journal_abort_hard(journal_t *journal)
-{
- transaction_t *transaction;
-
- if (journal->j_flags & JBD2_ABORT)
- return;
-
- printk(KERN_ERR "Aborting journal on device %s.\n",
- journal->j_devname);
-
- write_lock(&journal->j_state_lock);
- journal->j_flags |= JBD2_ABORT;
- transaction = journal->j_running_transaction;
- if (transaction)
- __jbd2_log_start_commit(journal, transaction->t_tid);
- write_unlock(&journal->j_state_lock);
-}
-
-/* Soft abort: record the abort error status in the journal superblock,
- * but don't do any other IO. */
-static void __journal_abort_soft (journal_t *journal, int errno)
-{
- int old_errno;
-
- write_lock(&journal->j_state_lock);
- old_errno = journal->j_errno;
- if (!journal->j_errno || errno == -ESHUTDOWN)
- journal->j_errno = errno;
-
- if (journal->j_flags & JBD2_ABORT) {
- write_unlock(&journal->j_state_lock);
- if (!old_errno && old_errno != -ESHUTDOWN &&
- errno == -ESHUTDOWN)
- jbd2_journal_update_sb_errno(journal);
- return;
- }
- write_unlock(&journal->j_state_lock);
-
- __jbd2_journal_abort_hard(journal);
-
- if (errno) {
- jbd2_journal_update_sb_errno(journal);
- write_lock(&journal->j_state_lock);
- journal->j_flags |= JBD2_REC_ERR;
- write_unlock(&journal->j_state_lock);
- }
-}
-
/**
* void jbd2_journal_abort () - Shutdown the journal immediately.
* @journal: the journal to shutdown.
@@ -2198,16 +2141,51 @@ static void __journal_abort_soft (journal_t *journal, int errno)
* failure to disk. ext3_error, for example, now uses this
* functionality.
*
- * Errors which originate from within the journaling layer will NOT
- * supply an errno; a null errno implies that absolutely no further
- * writes are done to the journal (unless there are any already in
- * progress).
- *
*/
void jbd2_journal_abort(journal_t *journal, int errno)
{
- __journal_abort_soft(journal, errno);
+ transaction_t *transaction;
+
+ /*
+ * ESHUTDOWN always takes precedence because a file system check
+ * caused by any other journal abort error is not required after
+ * a shutdown triggered.
+ */
+ write_lock(&journal->j_state_lock);
+ if (journal->j_flags & JBD2_ABORT) {
+ int old_errno = journal->j_errno;
+
+ write_unlock(&journal->j_state_lock);
+ if (old_errno != -ESHUTDOWN && errno == -ESHUTDOWN) {
+ journal->j_errno = errno;
+ jbd2_journal_update_sb_errno(journal);
+ }
+ return;
+ }
+
+ /*
+ * Mark the abort as occurred and start current running transaction
+ * to release all journaled buffer.
+ */
+ pr_err("Aborting journal on device %s.\n", journal->j_devname);
+
+ journal->j_flags |= JBD2_ABORT;
+ journal->j_errno = errno;
+ transaction = journal->j_running_transaction;
+ if (transaction)
+ __jbd2_log_start_commit(journal, transaction->t_tid);
+ write_unlock(&journal->j_state_lock);
+
+ /*
+ * Record errno to the journal super block, so that fsck and jbd2
+ * layer could realise that a filesystem check is needed.
+ */
+ jbd2_journal_update_sb_errno(journal);
+
+ write_lock(&journal->j_state_lock);
+ journal->j_flags |= JBD2_REC_ERR;
+ write_unlock(&journal->j_state_lock);
}
/**
@@ -2556,7 +2534,6 @@ static void __journal_remove_journal_head(struct buffer_head *bh)
{
struct journal_head *jh = bh2jh(bh);
- J_ASSERT_JH(jh, jh->b_jcount >= 0);
J_ASSERT_JH(jh, jh->b_transaction == NULL);
J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
J_ASSERT_JH(jh, jh->b_cp_transaction == NULL);
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 27b9f9dee434..e77a5a0b4e46 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -525,7 +525,7 @@ EXPORT_SYMBOL(jbd2__journal_start);
* modified buffers in the log. We block until the log can guarantee
* that much space. Additionally, if rsv_blocks > 0, we also create another
* handle with rsv_blocks reserved blocks in the journal. This handle is
- * is stored in h_rsv_handle. It is not attached to any particular transaction
+ * stored in h_rsv_handle. It is not attached to any particular transaction
* and thus doesn't block transaction commit. If the caller uses this reserved
* handle, it has to set h_rsv_handle to NULL as otherwise jbd2_journal_stop()
* on the parent handle will dispose the reserved one. Reserved handle has to
@@ -1595,7 +1595,7 @@ out:
* Allow this call even if the handle has aborted --- it may be part of
* the caller's cleanup after an abort.
*/
-int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
+int jbd2_journal_forget(handle_t *handle, struct buffer_head *bh)
{
transaction_t *transaction = handle->h_transaction;
journal_t *journal;
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 9d96e6871e1a..9aec80b9d7c6 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -1266,7 +1266,7 @@ void kernfs_activate(struct kernfs_node *kn)
pos = NULL;
while ((pos = kernfs_next_descendant_post(pos, kn))) {
- if (!pos || (pos->flags & KERNFS_ACTIVATED))
+ if (pos->flags & KERNFS_ACTIVATED)
continue;
WARN_ON_ONCE(pos->parent && RB_EMPTY_NODE(&pos->rb));
diff --git a/fs/namei.c b/fs/namei.c
index 4fb61e0754ed..db6565c99825 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -491,7 +491,7 @@ struct nameidata {
struct path root;
struct inode *inode; /* path.dentry.d_inode */
unsigned int flags;
- unsigned seq, m_seq;
+ unsigned seq, m_seq, r_seq;
int last_type;
unsigned depth;
int total_link_count;
@@ -641,6 +641,14 @@ static bool legitimize_links(struct nameidata *nd)
static bool legitimize_root(struct nameidata *nd)
{
+ /*
+ * For scoped-lookups (where nd->root has been zeroed), we need to
+ * restart the whole lookup from scratch -- because set_root() is wrong
+ * for these lookups (nd->dfd is the root, not the filesystem root).
+ */
+ if (!nd->root.mnt && (nd->flags & LOOKUP_IS_SCOPED))
+ return false;
+ /* Nothing to do if nd->root is zero or is managed by the VFS user. */
if (!nd->root.mnt || (nd->flags & LOOKUP_ROOT))
return true;
nd->flags |= LOOKUP_ROOT_GRABBED;
@@ -776,12 +784,37 @@ static int complete_walk(struct nameidata *nd)
int status;
if (nd->flags & LOOKUP_RCU) {
- if (!(nd->flags & LOOKUP_ROOT))
+ /*
+ * We don't want to zero nd->root for scoped-lookups or
+ * externally-managed nd->root.
+ */
+ if (!(nd->flags & (LOOKUP_ROOT | LOOKUP_IS_SCOPED)))
nd->root.mnt = NULL;
if (unlikely(unlazy_walk(nd)))
return -ECHILD;
}
+ if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) {
+ /*
+ * While the guarantee of LOOKUP_IS_SCOPED is (roughly) "don't
+ * ever step outside the root during lookup" and should already
+ * be guaranteed by the rest of namei, we want to avoid a namei
+ * BUG resulting in userspace being given a path that was not
+ * scoped within the root at some point during the lookup.
+ *
+ * So, do a final sanity-check to make sure that in the
+ * worst-case scenario (a complete bypass of LOOKUP_IS_SCOPED)
+ * we won't silently return an fd completely outside of the
+ * requested root to userspace.
+ *
+ * Userspace could move the path outside the root after this
+ * check, but as discussed elsewhere this is not a concern (the
+ * resolved file was inside the root at some point).
+ */
+ if (!path_is_under(&nd->path, &nd->root))
+ return -EXDEV;
+ }
+
if (likely(!(nd->flags & LOOKUP_JUMPED)))
return 0;
@@ -798,10 +831,18 @@ static int complete_walk(struct nameidata *nd)
return status;
}
-static void set_root(struct nameidata *nd)
+static int set_root(struct nameidata *nd)
{
struct fs_struct *fs = current->fs;
+ /*
+ * Jumping to the real root in a scoped-lookup is a BUG in namei, but we
+ * still have to ensure it doesn't happen because it will cause a breakout
+ * from the dirfd.
+ */
+ if (WARN_ON(nd->flags & LOOKUP_IS_SCOPED))
+ return -ENOTRECOVERABLE;
+
if (nd->flags & LOOKUP_RCU) {
unsigned seq;
@@ -814,6 +855,7 @@ static void set_root(struct nameidata *nd)
get_fs_root(fs, &nd->root);
nd->flags |= LOOKUP_ROOT_GRABBED;
}
+ return 0;
}
static void path_put_conditional(struct path *path, struct nameidata *nd)
@@ -837,6 +879,18 @@ static inline void path_to_nameidata(const struct path *path,
static int nd_jump_root(struct nameidata *nd)
{
+ if (unlikely(nd->flags & LOOKUP_BENEATH))
+ return -EXDEV;
+ if (unlikely(nd->flags & LOOKUP_NO_XDEV)) {
+ /* Absolute path arguments to path_init() are allowed. */
+ if (nd->path.mnt != NULL && nd->path.mnt != nd->root.mnt)
+ return -EXDEV;
+ }
+ if (!nd->root.mnt) {
+ int error = set_root(nd);
+ if (error)
+ return error;
+ }
if (nd->flags & LOOKUP_RCU) {
struct dentry *d;
nd->path = nd->root;
@@ -859,14 +913,32 @@ static int nd_jump_root(struct nameidata *nd)
* Helper to directly jump to a known parsed path from ->get_link,
* caller must have taken a reference to path beforehand.
*/
-void nd_jump_link(struct path *path)
+int nd_jump_link(struct path *path)
{
+ int error = -ELOOP;
struct nameidata *nd = current->nameidata;
- path_put(&nd->path);
+ if (unlikely(nd->flags & LOOKUP_NO_MAGICLINKS))
+ goto err;
+
+ error = -EXDEV;
+ if (unlikely(nd->flags & LOOKUP_NO_XDEV)) {
+ if (nd->path.mnt != path->mnt)
+ goto err;
+ }
+ /* Not currently safe for scoped-lookups. */
+ if (unlikely(nd->flags & LOOKUP_IS_SCOPED))
+ goto err;
+
+ path_put(&nd->path);
nd->path = *path;
nd->inode = nd->path.dentry->d_inode;
nd->flags |= LOOKUP_JUMPED;
+ return 0;
+
+err:
+ path_put(path);
+ return error;
}
static inline void put_link(struct nameidata *nd)
@@ -1050,6 +1122,9 @@ const char *get_link(struct nameidata *nd)
int error;
const char *res;
+ if (unlikely(nd->flags & LOOKUP_NO_SYMLINKS))
+ return ERR_PTR(-ELOOP);
+
if (!(nd->flags & LOOKUP_RCU)) {
touch_atime(&last->link);
cond_resched();
@@ -1084,10 +1159,9 @@ const char *get_link(struct nameidata *nd)
return res;
}
if (*res == '/') {
- if (!nd->root.mnt)
- set_root(nd);
- if (unlikely(nd_jump_root(nd)))
- return ERR_PTR(-ECHILD);
+ error = nd_jump_root(nd);
+ if (unlikely(error))
+ return ERR_PTR(error);
while (unlikely(*++res == '/'))
;
}
@@ -1269,10 +1343,14 @@ static int follow_managed(struct path *path, struct nameidata *nd)
break;
}
- if (need_mntput && path->mnt == mnt)
- mntput(path->mnt);
- if (need_mntput)
- nd->flags |= LOOKUP_JUMPED;
+ if (need_mntput) {
+ if (path->mnt == mnt)
+ mntput(path->mnt);
+ if (unlikely(nd->flags & LOOKUP_NO_XDEV))
+ ret = -EXDEV;
+ else
+ nd->flags |= LOOKUP_JUMPED;
+ }
if (ret == -EISDIR || !ret)
ret = 1;
if (ret > 0 && unlikely(d_flags_negative(flags)))
@@ -1333,6 +1411,8 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
mounted = __lookup_mnt(path->mnt, path->dentry);
if (!mounted)
break;
+ if (unlikely(nd->flags & LOOKUP_NO_XDEV))
+ return false;
path->mnt = &mounted->mnt;
path->dentry = mounted->mnt.mnt_root;
nd->flags |= LOOKUP_JUMPED;
@@ -1353,8 +1433,11 @@ static int follow_dotdot_rcu(struct nameidata *nd)
struct inode *inode = nd->inode;
while (1) {
- if (path_equal(&nd->path, &nd->root))
+ if (path_equal(&nd->path, &nd->root)) {
+ if (unlikely(nd->flags & LOOKUP_BENEATH))
+ return -ECHILD;
break;
+ }
if (nd->path.dentry != nd->path.mnt->mnt_root) {
struct dentry *old = nd->path.dentry;
struct dentry *parent = old->d_parent;
@@ -1367,7 +1450,7 @@ static int follow_dotdot_rcu(struct nameidata *nd)
nd->path.dentry = parent;
nd->seq = seq;
if (unlikely(!path_connected(&nd->path)))
- return -ENOENT;
+ return -ECHILD;
break;
} else {
struct mount *mnt = real_mount(nd->path.mnt);
@@ -1379,6 +1462,8 @@ static int follow_dotdot_rcu(struct nameidata *nd)
return -ECHILD;
if (&mparent->mnt == nd->path.mnt)
break;
+ if (unlikely(nd->flags & LOOKUP_NO_XDEV))
+ return -ECHILD;
/* we know that mountpoint was pinned */
nd->path.dentry = mountpoint;
nd->path.mnt = &mparent->mnt;
@@ -1393,6 +1478,8 @@ static int follow_dotdot_rcu(struct nameidata *nd)
return -ECHILD;
if (!mounted)
break;
+ if (unlikely(nd->flags & LOOKUP_NO_XDEV))
+ return -ECHILD;
nd->path.mnt = &mounted->mnt;
nd->path.dentry = mounted->mnt.mnt_root;
inode = nd->path.dentry->d_inode;
@@ -1480,9 +1567,12 @@ static int path_parent_directory(struct path *path)
static int follow_dotdot(struct nameidata *nd)
{
- while(1) {
- if (path_equal(&nd->path, &nd->root))
+ while (1) {
+ if (path_equal(&nd->path, &nd->root)) {
+ if (unlikely(nd->flags & LOOKUP_BENEATH))
+ return -EXDEV;
break;
+ }
if (nd->path.dentry != nd->path.mnt->mnt_root) {
int ret = path_parent_directory(&nd->path);
if (ret)
@@ -1491,6 +1581,8 @@ static int follow_dotdot(struct nameidata *nd)
}
if (!follow_up(&nd->path))
break;
+ if (unlikely(nd->flags & LOOKUP_NO_XDEV))
+ return -EXDEV;
}
follow_mount(&nd->path);
nd->inode = nd->path.dentry->d_inode;
@@ -1699,12 +1791,33 @@ static inline int may_lookup(struct nameidata *nd)
static inline int handle_dots(struct nameidata *nd, int type)
{
if (type == LAST_DOTDOT) {
- if (!nd->root.mnt)
- set_root(nd);
- if (nd->flags & LOOKUP_RCU) {
- return follow_dotdot_rcu(nd);
- } else
- return follow_dotdot(nd);
+ int error = 0;
+
+ if (!nd->root.mnt) {
+ error = set_root(nd);
+ if (error)
+ return error;
+ }
+ if (nd->flags & LOOKUP_RCU)
+ error = follow_dotdot_rcu(nd);
+ else
+ error = follow_dotdot(nd);
+ if (error)
+ return error;
+
+ if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) {
+ /*
+ * If there was a racing rename or mount along our
+ * path, then we can't be sure that ".." hasn't jumped
+ * above nd->root (and so userspace should retry or use
+ * some fallback).
+ */
+ smp_rmb();
+ if (unlikely(__read_seqcount_retry(&mount_lock.seqcount, nd->m_seq)))
+ return -EAGAIN;
+ if (unlikely(__read_seqcount_retry(&rename_lock.seqcount, nd->r_seq)))
+ return -EAGAIN;
+ }
}
return 0;
}
@@ -2158,6 +2271,7 @@ OK:
/* must be paired with terminate_walk() */
static const char *path_init(struct nameidata *nd, unsigned flags)
{
+ int error;
const char *s = nd->name->name;
if (!*s)
@@ -2168,6 +2282,11 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
nd->last_type = LAST_ROOT; /* if there are only slashes... */
nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT;
nd->depth = 0;
+
+ nd->m_seq = __read_seqcount_begin(&mount_lock.seqcount);
+ nd->r_seq = __read_seqcount_begin(&rename_lock.seqcount);
+ smp_rmb();
+
if (flags & LOOKUP_ROOT) {
struct dentry *root = nd->root.dentry;
struct inode *inode = root->d_inode;
@@ -2176,9 +2295,8 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
nd->path = nd->root;
nd->inode = inode;
if (flags & LOOKUP_RCU) {
- nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
+ nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
nd->root_seq = nd->seq;
- nd->m_seq = read_seqbegin(&mount_lock);
} else {
path_get(&nd->path);
}
@@ -2189,13 +2307,16 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
nd->path.mnt = NULL;
nd->path.dentry = NULL;
- nd->m_seq = read_seqbegin(&mount_lock);
- if (*s == '/') {
- set_root(nd);
- if (likely(!nd_jump_root(nd)))
- return s;
- return ERR_PTR(-ECHILD);
- } else if (nd->dfd == AT_FDCWD) {
+ /* Absolute pathname -- fetch the root (LOOKUP_IN_ROOT uses nd->dfd). */
+ if (*s == '/' && !(flags & LOOKUP_IN_ROOT)) {
+ error = nd_jump_root(nd);
+ if (unlikely(error))
+ return ERR_PTR(error);
+ return s;
+ }
+
+ /* Relative pathname -- get the starting-point it is relative to. */
+ if (nd->dfd == AT_FDCWD) {
if (flags & LOOKUP_RCU) {
struct fs_struct *fs = current->fs;
unsigned seq;
@@ -2210,7 +2331,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
get_fs_pwd(current->fs, &nd->path);
nd->inode = nd->path.dentry->d_inode;
}
- return s;
} else {
/* Caller must check execute permissions on the starting path component */
struct fd f = fdget_raw(nd->dfd);
@@ -2235,8 +2355,19 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
nd->inode = nd->path.dentry->d_inode;
}
fdput(f);
- return s;
}
+
+ /* For scoped-lookups we need to set the root to the dirfd as well. */
+ if (flags & LOOKUP_IS_SCOPED) {
+ nd->root = nd->path;
+ if (flags & LOOKUP_RCU) {
+ nd->root_seq = nd->seq;
+ } else {
+ path_get(&nd->root);
+ nd->flags |= LOOKUP_ROOT_GRABBED;
+ }
+ }
+ return s;
}
static const char *trailing_symlink(struct nameidata *nd)
@@ -3202,8 +3333,8 @@ static int do_last(struct nameidata *nd,
struct file *file, const struct open_flags *op)
{
struct dentry *dir = nd->path.dentry;
- kuid_t dir_uid = dir->d_inode->i_uid;
- umode_t dir_mode = dir->d_inode->i_mode;
+ kuid_t dir_uid = nd->inode->i_uid;
+ umode_t dir_mode = nd->inode->i_mode;
int open_flag = op->open_flag;
bool will_truncate = (open_flag & O_TRUNC) != 0;
bool got_write = false;
diff --git a/fs/nfs/fscache-index.c b/fs/nfs/fscache-index.c
index 15f271401dcc..573b1da9342c 100644
--- a/fs/nfs/fscache-index.c
+++ b/fs/nfs/fscache-index.c
@@ -84,8 +84,10 @@ enum fscache_checkaux nfs_fscache_inode_check_aux(void *cookie_netfs_data,
return FSCACHE_CHECKAUX_OBSOLETE;
memset(&auxdata, 0, sizeof(auxdata));
- auxdata.mtime = timespec64_to_timespec(nfsi->vfs_inode.i_mtime);
- auxdata.ctime = timespec64_to_timespec(nfsi->vfs_inode.i_ctime);
+ auxdata.mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec;
+ auxdata.mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec;
+ auxdata.ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec;
+ auxdata.ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec;
if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index 3800ab6f08fa..7def925d3af5 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -238,8 +238,10 @@ void nfs_fscache_init_inode(struct inode *inode)
return;
memset(&auxdata, 0, sizeof(auxdata));
- auxdata.mtime = timespec64_to_timespec(nfsi->vfs_inode.i_mtime);
- auxdata.ctime = timespec64_to_timespec(nfsi->vfs_inode.i_ctime);
+ auxdata.mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec;
+ auxdata.mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec;
+ auxdata.ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec;
+ auxdata.ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec;
if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);
@@ -263,8 +265,10 @@ void nfs_fscache_clear_inode(struct inode *inode)
dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n", nfsi, cookie);
memset(&auxdata, 0, sizeof(auxdata));
- auxdata.mtime = timespec64_to_timespec(nfsi->vfs_inode.i_mtime);
- auxdata.ctime = timespec64_to_timespec(nfsi->vfs_inode.i_ctime);
+ auxdata.mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec;
+ auxdata.mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec;
+ auxdata.ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec;
+ auxdata.ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec;
fscache_relinquish_cookie(cookie, &auxdata, false);
nfsi->fscache = NULL;
}
@@ -305,8 +309,10 @@ void nfs_fscache_open_file(struct inode *inode, struct file *filp)
return;
memset(&auxdata, 0, sizeof(auxdata));
- auxdata.mtime = timespec64_to_timespec(nfsi->vfs_inode.i_mtime);
- auxdata.ctime = timespec64_to_timespec(nfsi->vfs_inode.i_ctime);
+ auxdata.mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec;
+ auxdata.mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec;
+ auxdata.ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec;
+ auxdata.ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec;
if (inode_is_open_for_write(inode)) {
dfprintk(FSCACHE, "NFS: nfsi 0x%p disabling cache\n", nfsi);
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
index ad041cfbf9ec..6754c8607230 100644
--- a/fs/nfs/fscache.h
+++ b/fs/nfs/fscache.h
@@ -62,9 +62,11 @@ struct nfs_fscache_key {
* cache object.
*/
struct nfs_fscache_inode_auxdata {
- struct timespec mtime;
- struct timespec ctime;
- u64 change_attr;
+ s64 mtime_sec;
+ s64 mtime_nsec;
+ s64 ctime_sec;
+ s64 ctime_nsec;
+ u64 change_attr;
};
/*
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 936c57779ff4..728d88b6a698 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -4097,7 +4097,7 @@ static int decode_attr_time_access(struct xdr_stream *xdr, uint32_t *bitmap, str
status = NFS_ATTR_FATTR_ATIME;
bitmap[1] &= ~FATTR4_WORD1_TIME_ACCESS;
}
- dprintk("%s: atime=%ld\n", __func__, (long)time->tv_sec);
+ dprintk("%s: atime=%lld\n", __func__, time->tv_sec);
return status;
}
@@ -4115,7 +4115,7 @@ static int decode_attr_time_metadata(struct xdr_stream *xdr, uint32_t *bitmap, s
status = NFS_ATTR_FATTR_CTIME;
bitmap[1] &= ~FATTR4_WORD1_TIME_METADATA;
}
- dprintk("%s: ctime=%ld\n", __func__, (long)time->tv_sec);
+ dprintk("%s: ctime=%lld\n", __func__, time->tv_sec);
return status;
}
@@ -4132,8 +4132,8 @@ static int decode_attr_time_delta(struct xdr_stream *xdr, uint32_t *bitmap,
status = decode_attr_time(xdr, time);
bitmap[1] &= ~FATTR4_WORD1_TIME_DELTA;
}
- dprintk("%s: time_delta=%ld %ld\n", __func__, (long)time->tv_sec,
- (long)time->tv_nsec);
+ dprintk("%s: time_delta=%lld %ld\n", __func__, time->tv_sec,
+ time->tv_nsec);
return status;
}
@@ -4197,7 +4197,7 @@ static int decode_attr_time_modify(struct xdr_stream *xdr, uint32_t *bitmap, str
status = NFS_ATTR_FATTR_MTIME;
bitmap[1] &= ~FATTR4_WORD1_TIME_MODIFY;
}
- dprintk("%s: mtime=%ld\n", __func__, (long)time->tv_sec);
+ dprintk("%s: mtime=%lld\n", __func__, time->tv_sec);
return status;
}
diff --git a/fs/nsfs.c b/fs/nsfs.c
index f75767bd623a..b13bfd406820 100644
--- a/fs/nsfs.c
+++ b/fs/nsfs.c
@@ -55,7 +55,7 @@ static void nsfs_evict(struct inode *inode)
ns->ops->put(ns);
}
-static void *__ns_get_path(struct path *path, struct ns_common *ns)
+static int __ns_get_path(struct path *path, struct ns_common *ns)
{
struct vfsmount *mnt = nsfs_mnt;
struct dentry *dentry;
@@ -74,13 +74,13 @@ static void *__ns_get_path(struct path *path, struct ns_common *ns)
got_it:
path->mnt = mntget(mnt);
path->dentry = dentry;
- return NULL;
+ return 0;
slow:
rcu_read_unlock();
inode = new_inode_pseudo(mnt->mnt_sb);
if (!inode) {
ns->ops->put(ns);
- return ERR_PTR(-ENOMEM);
+ return -ENOMEM;
}
inode->i_ino = ns->inum;
inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
@@ -92,7 +92,7 @@ slow:
dentry = d_alloc_anon(mnt->mnt_sb);
if (!dentry) {
iput(inode);
- return ERR_PTR(-ENOMEM);
+ return -ENOMEM;
}
d_instantiate(dentry, inode);
dentry->d_fsdata = (void *)ns->ops;
@@ -101,23 +101,22 @@ slow:
d_delete(dentry); /* make sure ->d_prune() does nothing */
dput(dentry);
cpu_relax();
- return ERR_PTR(-EAGAIN);
+ return -EAGAIN;
}
goto got_it;
}
-void *ns_get_path_cb(struct path *path, ns_get_path_helper_t *ns_get_cb,
+int ns_get_path_cb(struct path *path, ns_get_path_helper_t *ns_get_cb,
void *private_data)
{
- void *ret;
+ int ret;
do {
struct ns_common *ns = ns_get_cb(private_data);
if (!ns)
- return ERR_PTR(-ENOENT);
-
+ return -ENOENT;
ret = __ns_get_path(path, ns);
- } while (ret == ERR_PTR(-EAGAIN));
+ } while (ret == -EAGAIN);
return ret;
}
@@ -134,7 +133,7 @@ static struct ns_common *ns_get_path_task(void *private_data)
return args->ns_ops->get(args->task);
}
-void *ns_get_path(struct path *path, struct task_struct *task,
+int ns_get_path(struct path *path, struct task_struct *task,
const struct proc_ns_operations *ns_ops)
{
struct ns_get_path_task_args args = {
@@ -150,7 +149,7 @@ int open_related_ns(struct ns_common *ns,
{
struct path path = {};
struct file *f;
- void *err;
+ int err;
int fd;
fd = get_unused_fd_flags(O_CLOEXEC);
@@ -167,11 +166,11 @@ int open_related_ns(struct ns_common *ns,
}
err = __ns_get_path(&path, relative);
- } while (err == ERR_PTR(-EAGAIN));
+ } while (err == -EAGAIN);
- if (IS_ERR(err)) {
+ if (err) {
put_unused_fd(fd);
- return PTR_ERR(err);
+ return err;
}
f = dentry_open(&path, O_RDONLY, current_cred());
diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c
index 5c424a099280..1ef24574f481 100644
--- a/fs/ocfs2/cluster/quorum.c
+++ b/fs/ocfs2/cluster/quorum.c
@@ -73,7 +73,7 @@ static void o2quo_fence_self(void)
"system by restarting ***\n");
emergency_restart();
break;
- };
+ }
}
/* Indicate that a timeout occurred on a heartbeat region write. The
diff --git a/fs/ocfs2/dlm/Makefile b/fs/ocfs2/dlm/Makefile
index 38b224372776..5e700b45d32d 100644
--- a/fs/ocfs2/dlm/Makefile
+++ b/fs/ocfs2/dlm/Makefile
@@ -1,6 +1,4 @@
# SPDX-License-Identifier: GPL-2.0-only
-ccflags-y := -I $(srctree)/$(src)/..
-
obj-$(CONFIG_OCFS2_FS_O2CB) += ocfs2_dlm.o
ocfs2_dlm-objs := dlmdomain.o dlmdebug.o dlmthread.o dlmrecovery.o \
diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c
index 4de89af96abf..6abaded3ff6b 100644
--- a/fs/ocfs2/dlm/dlmast.c
+++ b/fs/ocfs2/dlm/dlmast.c
@@ -23,15 +23,15 @@
#include <linux/spinlock.h>
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
#include "dlmapi.h"
#include "dlmcommon.h"
#define MLOG_MASK_PREFIX ML_DLM
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
static void dlm_update_lvb(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
struct dlm_lock *lock);
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index aaf24548b02a..0463dce65bb2 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -688,10 +688,6 @@ struct dlm_begin_reco
__be32 pad2;
};
-
-#define BITS_PER_BYTE 8
-#define BITS_TO_BYTES(bits) (((bits)+BITS_PER_BYTE-1)/BITS_PER_BYTE)
-
struct dlm_query_join_request
{
u8 node_idx;
diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c
index 965f45dbe17b..6051edc33aef 100644
--- a/fs/ocfs2/dlm/dlmconvert.c
+++ b/fs/ocfs2/dlm/dlmconvert.c
@@ -23,9 +23,9 @@
#include <linux/spinlock.h>
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
#include "dlmapi.h"
#include "dlmcommon.h"
@@ -33,7 +33,7 @@
#include "dlmconvert.h"
#define MLOG_MASK_PREFIX ML_DLM
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
/* NOTE: __dlmconvert_master is the only function in here that
* needs a spinlock held on entry (res->spinlock) and it is the
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index 4d0b452012b2..c5c6efba7b5e 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -17,9 +17,9 @@
#include <linux/debugfs.h>
#include <linux/export.h>
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
#include "dlmapi.h"
#include "dlmcommon.h"
@@ -27,7 +27,7 @@
#include "dlmdebug.h"
#define MLOG_MASK_PREFIX ML_DLM
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
static int stringify_lockname(const char *lockname, int locklen, char *buf,
int len);
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index ee6f459f9770..357cfc702ce3 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -20,9 +20,9 @@
#include <linux/debugfs.h>
#include <linux/sched/signal.h>
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
#include "dlmapi.h"
#include "dlmcommon.h"
@@ -30,7 +30,7 @@
#include "dlmdebug.h"
#define MLOG_MASK_PREFIX (ML_DLM|ML_DLM_DOMAIN)
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
/*
* ocfs2 node maps are array of long int, which limits to send them freely
diff --git a/fs/ocfs2/dlm/dlmlock.c b/fs/ocfs2/dlm/dlmlock.c
index baff087f3863..83f0760e4fba 100644
--- a/fs/ocfs2/dlm/dlmlock.c
+++ b/fs/ocfs2/dlm/dlmlock.c
@@ -25,9 +25,9 @@
#include <linux/delay.h>
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
#include "dlmapi.h"
#include "dlmcommon.h"
@@ -35,7 +35,7 @@
#include "dlmconvert.h"
#define MLOG_MASK_PREFIX ML_DLM
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
static struct kmem_cache *dlm_lock_cache;
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 74b768ca1cd8..900f7e466d11 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -25,9 +25,9 @@
#include <linux/delay.h>
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
#include "dlmapi.h"
#include "dlmcommon.h"
@@ -35,7 +35,7 @@
#include "dlmdebug.h"
#define MLOG_MASK_PREFIX (ML_DLM|ML_DLM_MASTER)
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
static void dlm_mle_node_down(struct dlm_ctxt *dlm,
struct dlm_master_list_entry *mle,
@@ -2554,8 +2554,6 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm,
if (!dlm_grab(dlm))
return -EINVAL;
- BUG_ON(target == O2NM_MAX_NODES);
-
name = res->lockname.name;
namelen = res->lockname.len;
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 064ce5bbc3f6..4b566e88582f 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -26,16 +26,16 @@
#include <linux/delay.h>
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
#include "dlmapi.h"
#include "dlmcommon.h"
#include "dlmdomain.h"
#define MLOG_MASK_PREFIX (ML_DLM|ML_DLM_RECOVERY)
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node);
@@ -1668,7 +1668,7 @@ static int dlm_lockres_master_requery(struct dlm_ctxt *dlm,
int dlm_do_master_requery(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
u8 nodenum, u8 *real_master)
{
- int ret = -EINVAL;
+ int ret;
struct dlm_master_requery req;
int status = DLM_LOCK_RES_OWNER_UNKNOWN;
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index 61c51c268460..fd40c17cd022 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -25,16 +25,16 @@
#include <linux/delay.h>
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
#include "dlmapi.h"
#include "dlmcommon.h"
#include "dlmdomain.h"
#define MLOG_MASK_PREFIX (ML_DLM|ML_DLM_THREAD)
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
static int dlm_thread(void *data);
static void dlm_flush_asts(struct dlm_ctxt *dlm);
diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c
index 3883633e82eb..dcb17ca8ae74 100644
--- a/fs/ocfs2/dlm/dlmunlock.c
+++ b/fs/ocfs2/dlm/dlmunlock.c
@@ -23,15 +23,15 @@
#include <linux/spinlock.h>
#include <linux/delay.h>
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
#include "dlmapi.h"
#include "dlmcommon.h"
#define MLOG_MASK_PREFIX ML_DLM
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
#define DLM_UNLOCK_FREE_LOCK 0x00000001
#define DLM_UNLOCK_CALL_AST 0x00000002
diff --git a/fs/ocfs2/dlmfs/Makefile b/fs/ocfs2/dlmfs/Makefile
index a9874e441bd4..c7895f65be0e 100644
--- a/fs/ocfs2/dlmfs/Makefile
+++ b/fs/ocfs2/dlmfs/Makefile
@@ -1,6 +1,4 @@
# SPDX-License-Identifier: GPL-2.0-only
-ccflags-y := -I $(srctree)/$(src)/..
-
obj-$(CONFIG_OCFS2_FS) += ocfs2_dlmfs.o
ocfs2_dlmfs-objs := userdlm.o dlmfs.o
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index 4f1668c81e1f..8e4f1ace467c 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -33,11 +33,11 @@
#include <linux/uaccess.h>
-#include "stackglue.h"
+#include "../stackglue.h"
#include "userdlm.h"
#define MLOG_MASK_PREFIX ML_DLMFS
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
static const struct super_operations dlmfs_ops;
diff --git a/fs/ocfs2/dlmfs/userdlm.c b/fs/ocfs2/dlmfs/userdlm.c
index 525b14ddfba5..3df5be25bfb1 100644
--- a/fs/ocfs2/dlmfs/userdlm.c
+++ b/fs/ocfs2/dlmfs/userdlm.c
@@ -21,12 +21,12 @@
#include <linux/types.h>
#include <linux/crc32.h>
-#include "ocfs2_lockingver.h"
-#include "stackglue.h"
+#include "../ocfs2_lockingver.h"
+#include "../stackglue.h"
#include "userdlm.h"
#define MLOG_MASK_PREFIX ML_DLMFS
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
static inline struct user_lock_res *user_lksb_to_lock_res(struct ocfs2_dlm_lksb *lksb)
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index cda1027d0819..cb9e6a73bea9 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -570,7 +570,7 @@ void ocfs2_inode_lock_res_init(struct ocfs2_lock_res *res,
mlog_bug_on_msg(1, "type: %d\n", type);
ops = NULL; /* thanks, gcc */
break;
- };
+ }
ocfs2_build_lock_name(type, OCFS2_I(inode)->ip_blkno,
generation, res->l_name);
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 3103ba7f97a2..bfe611ed1b1d 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -597,9 +597,11 @@ static inline void ocfs2_update_inode_fsync_trans(handle_t *handle,
{
struct ocfs2_inode_info *oi = OCFS2_I(inode);
- oi->i_sync_tid = handle->h_transaction->t_tid;
- if (datasync)
- oi->i_datasync_tid = handle->h_transaction->t_tid;
+ if (!is_handle_aborted(handle)) {
+ oi->i_sync_tid = handle->h_transaction->t_tid;
+ if (datasync)
+ oi->i_datasync_tid = handle->h_transaction->t_tid;
+ }
}
#endif /* OCFS2_JOURNAL_H */
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 8ea51cf27b97..da65251ef815 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -586,8 +586,7 @@ static int __ocfs2_mknod_locked(struct inode *dir,
mlog_errno(status);
}
- oi->i_sync_tid = handle->h_transaction->t_tid;
- oi->i_datasync_tid = handle->h_transaction->t_tid;
+ ocfs2_update_inode_fsync_trans(handle, inode, 1);
leave:
if (status < 0) {
diff --git a/fs/open.c b/fs/open.c
index b62f5c0923a8..0788b3715731 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -955,48 +955,83 @@ struct file *open_with_fake_path(const struct path *path, int flags,
}
EXPORT_SYMBOL(open_with_fake_path);
-static inline int build_open_flags(int flags, umode_t mode, struct open_flags *op)
+#define WILL_CREATE(flags) (flags & (O_CREAT | __O_TMPFILE))
+#define O_PATH_FLAGS (O_DIRECTORY | O_NOFOLLOW | O_PATH | O_CLOEXEC)
+
+inline struct open_how build_open_how(int flags, umode_t mode)
+{
+ struct open_how how = {
+ .flags = flags & VALID_OPEN_FLAGS,
+ .mode = mode & S_IALLUGO,
+ };
+
+ /* O_PATH beats everything else. */
+ if (how.flags & O_PATH)
+ how.flags &= O_PATH_FLAGS;
+ /* Modes should only be set for create-like flags. */
+ if (!WILL_CREATE(how.flags))
+ how.mode = 0;
+ return how;
+}
+
+inline int build_open_flags(const struct open_how *how, struct open_flags *op)
{
+ int flags = how->flags;
int lookup_flags = 0;
int acc_mode = ACC_MODE(flags);
+ /* Must never be set by userspace */
+ flags &= ~(FMODE_NONOTIFY | O_CLOEXEC);
+
/*
- * Clear out all open flags we don't know about so that we don't report
- * them in fcntl(F_GETFD) or similar interfaces.
+ * Older syscalls implicitly clear all of the invalid flags or argument
+ * values before calling build_open_flags(), but openat2(2) checks all
+ * of its arguments.
*/
- flags &= VALID_OPEN_FLAGS;
+ if (flags & ~VALID_OPEN_FLAGS)
+ return -EINVAL;
+ if (how->resolve & ~VALID_RESOLVE_FLAGS)
+ return -EINVAL;
- if (flags & (O_CREAT | __O_TMPFILE))
- op->mode = (mode & S_IALLUGO) | S_IFREG;
- else
+ /* Deal with the mode. */
+ if (WILL_CREATE(flags)) {
+ if (how->mode & ~S_IALLUGO)
+ return -EINVAL;
+ op->mode = how->mode | S_IFREG;
+ } else {
+ if (how->mode != 0)
+ return -EINVAL;
op->mode = 0;
-
- /* Must never be set by userspace */
- flags &= ~FMODE_NONOTIFY & ~O_CLOEXEC;
+ }
/*
- * O_SYNC is implemented as __O_SYNC|O_DSYNC. As many places only
- * check for O_DSYNC if the need any syncing at all we enforce it's
- * always set instead of having to deal with possibly weird behaviour
- * for malicious applications setting only __O_SYNC.
+ * In order to ensure programs get explicit errors when trying to use
+ * O_TMPFILE on old kernels, O_TMPFILE is implemented such that it
+ * looks like (O_DIRECTORY|O_RDWR & ~O_CREAT) to old kernels. But we
+ * have to require userspace to explicitly set it.
*/
- if (flags & __O_SYNC)
- flags |= O_DSYNC;
-
if (flags & __O_TMPFILE) {
if ((flags & O_TMPFILE_MASK) != O_TMPFILE)
return -EINVAL;
if (!(acc_mode & MAY_WRITE))
return -EINVAL;
- } else if (flags & O_PATH) {
- /*
- * If we have O_PATH in the open flag. Then we
- * cannot have anything other than the below set of flags
- */
- flags &= O_DIRECTORY | O_NOFOLLOW | O_PATH;
+ }
+ if (flags & O_PATH) {
+ /* O_PATH only permits certain other flags to be set. */
+ if (flags & ~O_PATH_FLAGS)
+ return -EINVAL;
acc_mode = 0;
}
+ /*
+ * O_SYNC is implemented as __O_SYNC|O_DSYNC. As many places only
+ * check for O_DSYNC if the need any syncing at all we enforce it's
+ * always set instead of having to deal with possibly weird behaviour
+ * for malicious applications setting only __O_SYNC.
+ */
+ if (flags & __O_SYNC)
+ flags |= O_DSYNC;
+
op->open_flag = flags;
/* O_TRUNC implies we need access checks for write permissions */
@@ -1022,6 +1057,18 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
lookup_flags |= LOOKUP_DIRECTORY;
if (!(flags & O_NOFOLLOW))
lookup_flags |= LOOKUP_FOLLOW;
+
+ if (how->resolve & RESOLVE_NO_XDEV)
+ lookup_flags |= LOOKUP_NO_XDEV;
+ if (how->resolve & RESOLVE_NO_MAGICLINKS)
+ lookup_flags |= LOOKUP_NO_MAGICLINKS;
+ if (how->resolve & RESOLVE_NO_SYMLINKS)
+ lookup_flags |= LOOKUP_NO_SYMLINKS;
+ if (how->resolve & RESOLVE_BENEATH)
+ lookup_flags |= LOOKUP_BENEATH;
+ if (how->resolve & RESOLVE_IN_ROOT)
+ lookup_flags |= LOOKUP_IN_ROOT;
+
op->lookup_flags = lookup_flags;
return 0;
}
@@ -1040,8 +1087,11 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
struct file *file_open_name(struct filename *name, int flags, umode_t mode)
{
struct open_flags op;
- int err = build_open_flags(flags, mode, &op);
- return err ? ERR_PTR(err) : do_filp_open(AT_FDCWD, name, &op);
+ struct open_how how = build_open_how(flags, mode);
+ int err = build_open_flags(&how, &op);
+ if (err)
+ return ERR_PTR(err);
+ return do_filp_open(AT_FDCWD, name, &op);
}
/**
@@ -1072,17 +1122,19 @@ struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt,
const char *filename, int flags, umode_t mode)
{
struct open_flags op;
- int err = build_open_flags(flags, mode, &op);
+ struct open_how how = build_open_how(flags, mode);
+ int err = build_open_flags(&how, &op);
if (err)
return ERR_PTR(err);
return do_file_open_root(dentry, mnt, filename, &op);
}
EXPORT_SYMBOL(file_open_root);
-long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
+static long do_sys_openat2(int dfd, const char __user *filename,
+ struct open_how *how)
{
struct open_flags op;
- int fd = build_open_flags(flags, mode, &op);
+ int fd = build_open_flags(how, &op);
struct filename *tmp;
if (fd)
@@ -1092,7 +1144,7 @@ long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
if (IS_ERR(tmp))
return PTR_ERR(tmp);
- fd = get_unused_fd_flags(flags);
+ fd = get_unused_fd_flags(how->flags);
if (fd >= 0) {
struct file *f = do_filp_open(dfd, tmp, &op);
if (IS_ERR(f)) {
@@ -1107,12 +1159,16 @@ long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
return fd;
}
-SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode)
+long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
{
- if (force_o_largefile())
- flags |= O_LARGEFILE;
+ struct open_how how = build_open_how(flags, mode);
+ return do_sys_openat2(dfd, filename, &how);
+}
- return do_sys_open(AT_FDCWD, filename, flags, mode);
+
+SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode)
+{
+ return ksys_open(filename, flags, mode);
}
SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags,
@@ -1120,10 +1176,32 @@ SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags,
{
if (force_o_largefile())
flags |= O_LARGEFILE;
-
return do_sys_open(dfd, filename, flags, mode);
}
+SYSCALL_DEFINE4(openat2, int, dfd, const char __user *, filename,
+ struct open_how __user *, how, size_t, usize)
+{
+ int err;
+ struct open_how tmp;
+
+ BUILD_BUG_ON(sizeof(struct open_how) < OPEN_HOW_SIZE_VER0);
+ BUILD_BUG_ON(sizeof(struct open_how) != OPEN_HOW_SIZE_LATEST);
+
+ if (unlikely(usize < OPEN_HOW_SIZE_VER0))
+ return -EINVAL;
+
+ err = copy_struct_from_user(&tmp, sizeof(tmp), how, usize);
+ if (err)
+ return err;
+
+ /* O_LARGEFILE is only allowed for non-O_PATH. */
+ if (!(tmp.flags & O_PATH) && force_o_largefile())
+ tmp.flags |= O_LARGEFILE;
+
+ return do_sys_openat2(dfd, filename, &tmp);
+}
+
#ifdef CONFIG_COMPAT
/*
* Exactly like sys_open(), except that it doesn't set the
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 915686772f0e..c7c64272b0fa 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1718,8 +1718,7 @@ static const char *proc_pid_get_link(struct dentry *dentry,
if (error)
goto out;
- nd_jump_link(&path);
- return NULL;
+ error = nd_jump_link(&path);
out:
return ERR_PTR(error);
}
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 8b5c720fe5d7..8e159fc78c0a 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -46,22 +46,26 @@ static const char *proc_ns_get_link(struct dentry *dentry,
const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops;
struct task_struct *task;
struct path ns_path;
- void *error = ERR_PTR(-EACCES);
+ int error = -EACCES;
if (!dentry)
return ERR_PTR(-ECHILD);
task = get_proc_task(inode);
if (!task)
- return error;
+ return ERR_PTR(-EACCES);
- if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
- error = ns_get_path(&ns_path, task, ns_ops);
- if (!error)
- nd_jump_link(&ns_path);
- }
+ if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
+ goto out;
+
+ error = ns_get_path(&ns_path, task, ns_ops);
+ if (error)
+ goto out;
+
+ error = nd_jump_link(&ns_path);
+out:
put_task_struct(task);
- return error;
+ return ERR_PTR(error);
}
static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int buflen)
diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c
index 53429c29c784..58fc2a7c7fd1 100644
--- a/fs/quota/quota_v2.c
+++ b/fs/quota/quota_v2.c
@@ -22,8 +22,6 @@ MODULE_AUTHOR("Jan Kara");
MODULE_DESCRIPTION("Quota format v2 support");
MODULE_LICENSE("GPL");
-#define __QUOTA_V2_PARANOIA
-
static void v2r0_mem2diskdqb(void *dp, struct dquot *dquot);
static void v2r0_disk2memdqb(struct dquot *dquot, void *dp);
static int v2r0_is_id(void *dp, struct dquot *dquot);
diff --git a/fs/quota/quotaio_v1.h b/fs/quota/quotaio_v1.h
index bd11e2c08119..31dca9a89176 100644
--- a/fs/quota/quotaio_v1.h
+++ b/fs/quota/quotaio_v1.h
@@ -25,8 +25,10 @@ struct v1_disk_dqblk {
__u32 dqb_ihardlimit; /* absolute limit on allocated inodes */
__u32 dqb_isoftlimit; /* preferred inode limit */
__u32 dqb_curinodes; /* current # allocated inodes */
- time_t dqb_btime; /* time limit for excessive disk use */
- time_t dqb_itime; /* time limit for excessive inode use */
+
+ /* below fields differ in length on 32-bit vs 64-bit architectures */
+ unsigned long dqb_btime; /* time limit for excessive disk use */
+ unsigned long dqb_itime; /* time limit for excessive inode use */
};
#define v1_dqoff(UID) ((loff_t)((UID) * sizeof (struct v1_disk_dqblk)))
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 4b3e3e73b512..072156c4f895 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -56,8 +56,6 @@
/* gets a struct reiserfs_journal_list * from a list head */
#define JOURNAL_LIST_ENTRY(h) (list_entry((h), struct reiserfs_journal_list, \
j_list))
-#define JOURNAL_WORK_ENTRY(h) (list_entry((h), struct reiserfs_journal_list, \
- j_working_list))
/* must be correct to keep the desc and commit structs at 4k */
#define JOURNAL_TRANS_HALF 1018
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index f2cf3441fdfc..ff336513c254 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -63,7 +63,6 @@ static int show_version(struct seq_file *m, void *unused)
#define MAP( i ) D4C( objectid_map( sb, rs )[ i ] )
#define DJF( x ) le32_to_cpu( rs -> x )
-#define DJV( x ) le32_to_cpu( s_v1 -> x )
#define DJP( x ) le32_to_cpu( jp -> x )
#define JF( x ) ( r -> s_journal -> x )
diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c
index da9ebe33882b..8bf88d690729 100644
--- a/fs/reiserfs/stree.c
+++ b/fs/reiserfs/stree.c
@@ -918,12 +918,6 @@ int comp_items(const struct item_head *stored_ih, const struct treepath *path)
return memcmp(stored_ih, ih, IH_SIZE);
}
-/* unformatted nodes are not logged anymore, ever. This is safe now */
-#define held_by_others(bh) (atomic_read(&(bh)->b_count) > 1)
-
-/* block can not be forgotten as it is in I/O or held by someone */
-#define block_in_use(bh) (buffer_locked(bh) || (held_by_others(bh)))
-
/* prepare for delete or cut of direct item */
static inline int prepare_for_direct_item(struct treepath *path,
struct item_head *le_ih,
@@ -2246,7 +2240,8 @@ error_out:
/* also releases the path */
unfix_nodes(&s_ins_balance);
#ifdef REISERQUOTA_DEBUG
- reiserfs_debug(th->t_super, REISERFS_DEBUG_CODE,
+ if (inode)
+ reiserfs_debug(th->t_super, REISERFS_DEBUG_CODE,
"reiserquota insert_item(): freeing %u id=%u type=%c",
quota_bytes, inode->i_uid, head2type(ih));
#endif
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 3244037b1286..a6bce5b1fb1d 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -629,6 +629,7 @@ static void reiserfs_put_super(struct super_block *s)
reiserfs_write_unlock(s);
mutex_destroy(&REISERFS_SB(s)->lock);
destroy_workqueue(REISERFS_SB(s)->commit_wq);
+ kfree(REISERFS_SB(s)->s_jdev);
kfree(s->s_fs_info);
s->s_fs_info = NULL;
}
@@ -1947,7 +1948,7 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
if (!sbi->s_jdev) {
SWARN(silent, s, "", "Cannot allocate memory for "
"journal device name");
- goto error;
+ goto error_unlocked;
}
}
#ifdef CONFIG_QUOTA
@@ -2240,6 +2241,7 @@ error_unlocked:
kfree(qf_names[j]);
}
#endif
+ kfree(sbi->s_jdev);
kfree(sbi);
s->s_fs_info = NULL;
diff --git a/fs/stat.c b/fs/stat.c
index c38e4c2e1221..030008796479 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -21,6 +21,8 @@
#include <linux/uaccess.h>
#include <asm/unistd.h>
+#include "internal.h"
+
/**
* generic_fillattr - Fill in the basic attributes from the inode struct
* @inode: Inode to use as the source
@@ -150,6 +152,23 @@ int vfs_statx_fd(unsigned int fd, struct kstat *stat,
}
EXPORT_SYMBOL(vfs_statx_fd);
+inline unsigned vfs_stat_set_lookup_flags(unsigned *lookup_flags, int flags)
+{
+ if ((flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT |
+ AT_EMPTY_PATH | KSTAT_QUERY_FLAGS)) != 0)
+ return -EINVAL;
+
+ *lookup_flags = LOOKUP_FOLLOW | LOOKUP_AUTOMOUNT;
+ if (flags & AT_SYMLINK_NOFOLLOW)
+ *lookup_flags &= ~LOOKUP_FOLLOW;
+ if (flags & AT_NO_AUTOMOUNT)
+ *lookup_flags &= ~LOOKUP_AUTOMOUNT;
+ if (flags & AT_EMPTY_PATH)
+ *lookup_flags |= LOOKUP_EMPTY;
+
+ return 0;
+}
+
/**
* vfs_statx - Get basic and extra attributes by filename
* @dfd: A file descriptor representing the base dir for a relative filename
@@ -170,19 +189,10 @@ int vfs_statx(int dfd, const char __user *filename, int flags,
{
struct path path;
int error = -EINVAL;
- unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_AUTOMOUNT;
+ unsigned lookup_flags;
- if ((flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT |
- AT_EMPTY_PATH | KSTAT_QUERY_FLAGS)) != 0)
+ if (vfs_stat_set_lookup_flags(&lookup_flags, flags))
return -EINVAL;
-
- if (flags & AT_SYMLINK_NOFOLLOW)
- lookup_flags &= ~LOOKUP_FOLLOW;
- if (flags & AT_NO_AUTOMOUNT)
- lookup_flags &= ~LOOKUP_AUTOMOUNT;
- if (flags & AT_EMPTY_PATH)
- lookup_flags |= LOOKUP_EMPTY;
-
retry:
error = user_path_at(dfd, filename, lookup_flags, &path);
if (error)
@@ -523,7 +533,7 @@ SYSCALL_DEFINE4(fstatat64, int, dfd, const char __user *, filename,
}
#endif /* __ARCH_WANT_STAT64 || __ARCH_WANT_COMPAT_STAT64 */
-static noinline_for_stack int
+noinline_for_stack int
cp_statx(const struct kstat *stat, struct statx __user *buffer)
{
struct statx tmp;
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index c8e8f50c6054..bc4dec5b1633 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -786,7 +786,9 @@ static int ubifs_do_bulk_read(struct ubifs_info *c, struct bu_info *bu,
if (page_offset > end_index)
break;
- page = find_or_create_page(mapping, page_offset, ra_gfp_mask);
+ page = pagecache_get_page(mapping, page_offset,
+ FGP_LOCK|FGP_ACCESSED|FGP_CREAT|FGP_NOWAIT,
+ ra_gfp_mask);
if (!page)
break;
if (!PageUptodate(page))
diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c
index 5dc5abca11c7..d49fc04f2d7d 100644
--- a/fs/ubifs/ioctl.c
+++ b/fs/ubifs/ioctl.c
@@ -17,10 +17,14 @@
#include "ubifs.h"
/* Need to be kept consistent with checked flags in ioctl2ubifs() */
-#define UBIFS_SUPPORTED_IOCTL_FLAGS \
+#define UBIFS_SETTABLE_IOCTL_FLAGS \
(FS_COMPR_FL | FS_SYNC_FL | FS_APPEND_FL | \
FS_IMMUTABLE_FL | FS_DIRSYNC_FL)
+/* Need to be kept consistent with checked flags in ubifs2ioctl() */
+#define UBIFS_GETTABLE_IOCTL_FLAGS \
+ (UBIFS_SETTABLE_IOCTL_FLAGS | FS_ENCRYPT_FL)
+
/**
* ubifs_set_inode_flags - set VFS inode flags.
* @inode: VFS inode to set flags for
@@ -91,6 +95,8 @@ static int ubifs2ioctl(int ubifs_flags)
ioctl_flags |= FS_IMMUTABLE_FL;
if (ubifs_flags & UBIFS_DIRSYNC_FL)
ioctl_flags |= FS_DIRSYNC_FL;
+ if (ubifs_flags & UBIFS_CRYPT_FL)
+ ioctl_flags |= FS_ENCRYPT_FL;
return ioctl_flags;
}
@@ -113,7 +119,8 @@ static int setflags(struct inode *inode, int flags)
if (err)
goto out_unlock;
- ui->flags = ioctl2ubifs(flags);
+ ui->flags &= ~ioctl2ubifs(UBIFS_SETTABLE_IOCTL_FLAGS);
+ ui->flags |= ioctl2ubifs(flags);
ubifs_set_inode_flags(inode);
inode->i_ctime = current_time(inode);
release = ui->dirty;
@@ -155,8 +162,9 @@ long ubifs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
if (get_user(flags, (int __user *) arg))
return -EFAULT;
- if (flags & ~UBIFS_SUPPORTED_IOCTL_FLAGS)
+ if (flags & ~UBIFS_GETTABLE_IOCTL_FLAGS)
return -EOPNOTSUPP;
+ flags &= UBIFS_SETTABLE_IOCTL_FLAGS;
if (!S_ISDIR(inode->i_mode))
flags &= ~FS_DIRSYNC_FL;
diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c
index 54d6db61106f..edf43ddd7dce 100644
--- a/fs/ubifs/orphan.c
+++ b/fs/ubifs/orphan.c
@@ -129,7 +129,7 @@ static void __orphan_drop(struct ubifs_info *c, struct ubifs_orphan *o)
static void orphan_delete(struct ubifs_info *c, struct ubifs_orphan *orph)
{
if (orph->del) {
- dbg_gen("deleted twice ino %lu", orph->inum);
+ dbg_gen("deleted twice ino %lu", (unsigned long)orph->inum);
return;
}
@@ -137,7 +137,7 @@ static void orphan_delete(struct ubifs_info *c, struct ubifs_orphan *orph)
orph->del = 1;
orph->dnext = c->orph_dnext;
c->orph_dnext = orph;
- dbg_gen("delete later ino %lu", orph->inum);
+ dbg_gen("delete later ino %lu", (unsigned long)orph->inum);
return;
}
diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c
index 2b7c04bf8983..17c90dff7266 100644
--- a/fs/ubifs/sb.c
+++ b/fs/ubifs/sb.c
@@ -161,7 +161,7 @@ static int create_default_filesystem(struct ubifs_info *c)
sup = kzalloc(ALIGN(UBIFS_SB_NODE_SZ, c->min_io_size), GFP_KERNEL);
mst = kzalloc(c->mst_node_alsz, GFP_KERNEL);
idx_node_size = ubifs_idx_node_sz(c, 1);
- idx = kzalloc(ALIGN(tmp, c->min_io_size), GFP_KERNEL);
+ idx = kzalloc(ALIGN(idx_node_size, c->min_io_size), GFP_KERNEL);
ino = kzalloc(ALIGN(UBIFS_INO_NODE_SZ, c->min_io_size), GFP_KERNEL);
cs = kzalloc(ALIGN(UBIFS_CS_NODE_SZ, c->min_io_size), GFP_KERNEL);
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 5e1e8ec0589e..7fc2f3f07c16 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -1599,6 +1599,7 @@ out_free:
vfree(c->ileb_buf);
vfree(c->sbuf);
kfree(c->bottom_up_buf);
+ kfree(c->sup_node);
ubifs_debugging_exit(c);
return err;
}
@@ -1641,6 +1642,7 @@ static void ubifs_umount(struct ubifs_info *c)
vfree(c->ileb_buf);
vfree(c->sbuf);
kfree(c->bottom_up_buf);
+ kfree(c->sup_node);
ubifs_debugging_exit(c);
}
diff --git a/fs/udf/ecma_167.h b/fs/udf/ecma_167.h
index fb7f2c7bec9c..3fd85464abd5 100644
--- a/fs/udf/ecma_167.h
+++ b/fs/udf/ecma_167.h
@@ -4,7 +4,8 @@
* This file is based on ECMA-167 3rd edition (June 1997)
* http://www.ecma.ch
*
- * Copyright (c) 2001-2002 Ben Fennema <bfennema@falcon.csc.calpoly.edu>
+ * Copyright (c) 2001-2002 Ben Fennema
+ * Copyright (c) 2017-2019 Pali Rohár <pali.rohar@gmail.com>
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
@@ -32,11 +33,19 @@
* SUCH DAMAGE.
*/
+/**
+ * @file
+ * ECMA-167r3 defines and structure definitions
+ */
+
#include <linux/types.h>
#ifndef _ECMA_167_H
#define _ECMA_167_H 1
+/* Character sets and coding - d-characters (ECMA 167r3 1/7.2) */
+typedef uint8_t dchars;
+
/* Character set specification (ECMA 167r3 1/7.2.1) */
struct charspec {
uint8_t charSetType;
@@ -54,6 +63,7 @@ struct charspec {
#define CHARSPEC_TYPE_CS7 0x07 /* (1/7.2.9) */
#define CHARSPEC_TYPE_CS8 0x08 /* (1/7.2.10) */
+/* Fixed-length character fields - d-string (EMCA 167r3 1/7.2.12) */
typedef uint8_t dstring;
/* Timestamp (ECMA 167r3 1/7.3) */
@@ -85,22 +95,8 @@ struct regid {
} __packed;
/* Flags (ECMA 167r3 1/7.4.1) */
-#define ENTITYID_FLAGS_DIRTY 0x00
-#define ENTITYID_FLAGS_PROTECTED 0x01
-
-/* OSTA UDF 2.1.5.2 */
-#define UDF_ID_COMPLIANT "*OSTA UDF Compliant"
-
-/* OSTA UDF 2.1.5.3 */
-struct domainEntityIDSuffix {
- uint16_t revision;
- uint8_t flags;
- uint8_t reserved[5];
-};
-
-/* OSTA UDF 2.1.5.3 */
-#define ENTITYIDSUFFIX_FLAGS_HARDWRITEPROTECT 0
-#define ENTITYIDSUFFIX_FLAGS_SOFTWRITEPROTECT 1
+#define ENTITYID_FLAGS_DIRTY 0x01
+#define ENTITYID_FLAGS_PROTECTED 0x02
/* Volume Structure Descriptor (ECMA 167r3 2/9.1) */
#define VSD_STD_ID_LEN 5
@@ -202,6 +198,13 @@ struct NSRDesc {
uint8_t structData[2040];
} __packed;
+/* Generic Descriptor */
+struct genericDesc {
+ struct tag descTag;
+ __le32 volDescSeqNum;
+ uint8_t reserved[492];
+} __packed;
+
/* Primary Volume Descriptor (ECMA 167r3 3/10.1) */
struct primaryVolDesc {
struct tag descTag;
@@ -316,7 +319,7 @@ struct genericPartitionMap {
/* Partition Map Type (ECMA 167r3 3/10.7.1.1) */
#define GP_PARTITION_MAP_TYPE_UNDEF 0x00
-#define GP_PARTIITON_MAP_TYPE_1 0x01
+#define GP_PARTITION_MAP_TYPE_1 0x01
#define GP_PARTITION_MAP_TYPE_2 0x02
/* Type 1 Partition Map (ECMA 167r3 3/10.7.2) */
@@ -723,6 +726,7 @@ struct appUseExtAttr {
#define EXTATTR_DEV_SPEC 12
#define EXTATTR_IMP_USE 2048
#define EXTATTR_APP_USE 65536
+#define EXTATTR_SUBTYPE 1
/* Unallocated Space Entry (ECMA 167r3 4/14.11) */
struct unallocSpaceEntry {
@@ -754,10 +758,12 @@ struct partitionIntegrityEntry {
/* Short Allocation Descriptor (ECMA 167r3 4/14.14.1) */
/* Extent Length (ECMA 167r3 4/14.14.1.1) */
+#define EXT_LENGTH_MASK 0x3FFFFFFF
+#define EXT_TYPE_MASK 0xC0000000
#define EXT_RECORDED_ALLOCATED 0x00000000
#define EXT_NOT_RECORDED_ALLOCATED 0x40000000
#define EXT_NOT_RECORDED_NOT_ALLOCATED 0x80000000
-#define EXT_NEXT_EXTENT_ALLOCDECS 0xC0000000
+#define EXT_NEXT_EXTENT_ALLOCDESCS 0xC0000000
/* Long Allocation Descriptor (ECMA 167r3 4/14.14.2) */
@@ -774,7 +780,7 @@ struct pathComponent {
uint8_t componentType;
uint8_t lengthComponentIdent;
__le16 componentFileVersionNum;
- dstring componentIdent[0];
+ dchars componentIdent[0];
} __packed;
/* File Entry (ECMA 167r3 4/14.17) */
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index ea80036d7897..e875bc5668ee 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -1981,10 +1981,10 @@ int udf_setup_indirect_aext(struct inode *inode, udf_pblk_t block,
__udf_add_aext(inode, &nepos, &cp_loc, cp_len, 1);
udf_write_aext(inode, epos, &nepos.block,
- sb->s_blocksize | EXT_NEXT_EXTENT_ALLOCDECS, 0);
+ sb->s_blocksize | EXT_NEXT_EXTENT_ALLOCDESCS, 0);
} else {
__udf_add_aext(inode, epos, &nepos.block,
- sb->s_blocksize | EXT_NEXT_EXTENT_ALLOCDECS, 0);
+ sb->s_blocksize | EXT_NEXT_EXTENT_ALLOCDESCS, 0);
}
brelse(epos->bh);
@@ -2143,7 +2143,7 @@ int8_t udf_next_aext(struct inode *inode, struct extent_position *epos,
unsigned int indirections = 0;
while ((etype = udf_current_aext(inode, epos, eloc, elen, inc)) ==
- (EXT_NEXT_EXTENT_ALLOCDECS >> 30)) {
+ (EXT_NEXT_EXTENT_ALLOCDESCS >> 30)) {
udf_pblk_t block;
if (++indirections > UDF_MAX_INDIR_EXTS) {
diff --git a/fs/udf/osta_udf.h b/fs/udf/osta_udf.h
index a4da59e38b7f..35e61b2cacfe 100644
--- a/fs/udf/osta_udf.h
+++ b/fs/udf/osta_udf.h
@@ -1,10 +1,11 @@
/*
* osta_udf.h
*
- * This file is based on OSTA UDF(tm) 2.50 (April 30, 2003)
+ * This file is based on OSTA UDF(tm) 2.60 (March 1, 2005)
* http://www.osta.org
*
- * Copyright (c) 2001-2004 Ben Fennema <bfennema@falcon.csc.calpoly.edu>
+ * Copyright (c) 2001-2004 Ben Fennema
+ * Copyright (c) 2017-2019 Pali Rohár <pali.rohar@gmail.com>
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
@@ -32,38 +33,57 @@
* SUCH DAMAGE.
*/
+/**
+ * @file
+ * OSTA-UDF defines and structure definitions
+ */
+
#include "ecma_167.h"
#ifndef _OSTA_UDF_H
#define _OSTA_UDF_H 1
-/* OSTA CS0 Charspec (UDF 2.50 2.1.2) */
+/* OSTA CS0 Charspec (UDF 2.60 2.1.2) */
#define UDF_CHAR_SET_TYPE 0
#define UDF_CHAR_SET_INFO "OSTA Compressed Unicode"
-/* Entity Identifier (UDF 2.50 2.1.5) */
-/* Identifiers (UDF 2.50 2.1.5.2) */
+/* Entity Identifier (UDF 2.60 2.1.5) */
+/* Identifiers (UDF 2.60 2.1.5.2) */
+/* Implementation Use Extended Attribute (UDF 2.60 3.3.4.5) */
+/* Virtual Allocation Table (UDF 1.50 2.2.10) */
+/* Logical Volume Extended Information (UDF 1.50 Errata, DCN 5003, 3.3.4.5.1.3) */
+/* OS2EA (UDF 1.50 3.3.4.5.3.1) */
+/* MacUniqueIDTable (UDF 1.50 3.3.4.5.4.3) */
+/* MacResourceFork (UDF 1.50 3.3.4.5.4.4) */
#define UDF_ID_DEVELOPER "*Linux UDFFS"
#define UDF_ID_COMPLIANT "*OSTA UDF Compliant"
#define UDF_ID_LV_INFO "*UDF LV Info"
#define UDF_ID_FREE_EA "*UDF FreeEASpace"
#define UDF_ID_FREE_APP_EA "*UDF FreeAppEASpace"
#define UDF_ID_DVD_CGMS "*UDF DVD CGMS Info"
+#define UDF_ID_VAT_LVEXTENSION "*UDF VAT LVExtension"
#define UDF_ID_OS2_EA "*UDF OS/2 EA"
#define UDF_ID_OS2_EA_LENGTH "*UDF OS/2 EALength"
#define UDF_ID_MAC_VOLUME "*UDF Mac VolumeInfo"
#define UDF_ID_MAC_FINDER "*UDF Mac FinderInfo"
#define UDF_ID_MAC_UNIQUE "*UDF Mac UniqueIDTable"
#define UDF_ID_MAC_RESOURCE "*UDF Mac ResourceFork"
+#define UDF_ID_OS400_DIRINFO "*UDF OS/400 DirInfo"
#define UDF_ID_VIRTUAL "*UDF Virtual Partition"
#define UDF_ID_SPARABLE "*UDF Sparable Partition"
#define UDF_ID_ALLOC "*UDF Virtual Alloc Tbl"
#define UDF_ID_SPARING "*UDF Sparing Table"
#define UDF_ID_METADATA "*UDF Metadata Partition"
-/* Identifier Suffix (UDF 2.50 2.1.5.3) */
-#define IS_DF_HARD_WRITE_PROTECT 0x01
-#define IS_DF_SOFT_WRITE_PROTECT 0x02
+/* Identifier Suffix (UDF 2.60 2.1.5.3) */
+#define DOMAIN_FLAGS_HARD_WRITE_PROTECT 0x01
+#define DOMAIN_FLAGS_SOFT_WRITE_PROTECT 0x02
+
+struct domainIdentSuffix {
+ __le16 UDFRevision;
+ uint8_t domainFlags;
+ uint8_t reserved[5];
+} __packed;
struct UDFIdentSuffix {
__le16 UDFRevision;
@@ -75,15 +95,15 @@ struct UDFIdentSuffix {
struct impIdentSuffix {
uint8_t OSClass;
uint8_t OSIdentifier;
- uint8_t reserved[6];
+ uint8_t impUse[6];
} __packed;
struct appIdentSuffix {
uint8_t impUse[8];
} __packed;
-/* Logical Volume Integrity Descriptor (UDF 2.50 2.2.6) */
-/* Implementation Use (UDF 2.50 2.2.6.4) */
+/* Logical Volume Integrity Descriptor (UDF 2.60 2.2.6) */
+/* Implementation Use (UDF 2.60 2.2.6.4) */
struct logicalVolIntegrityDescImpUse {
struct regid impIdent;
__le32 numFiles;
@@ -94,8 +114,8 @@ struct logicalVolIntegrityDescImpUse {
uint8_t impUse[0];
} __packed;
-/* Implementation Use Volume Descriptor (UDF 2.50 2.2.7) */
-/* Implementation Use (UDF 2.50 2.2.7.2) */
+/* Implementation Use Volume Descriptor (UDF 2.60 2.2.7) */
+/* Implementation Use (UDF 2.60 2.2.7.2) */
struct impUseVolDescImpUse {
struct charspec LVICharset;
dstring logicalVolIdent[128];
@@ -115,7 +135,7 @@ struct udfPartitionMap2 {
__le16 partitionNum;
} __packed;
-/* Virtual Partition Map (UDF 2.50 2.2.8) */
+/* Virtual Partition Map (UDF 2.60 2.2.8) */
struct virtualPartitionMap {
uint8_t partitionMapType;
uint8_t partitionMapLength;
@@ -126,7 +146,7 @@ struct virtualPartitionMap {
uint8_t reserved2[24];
} __packed;
-/* Sparable Partition Map (UDF 2.50 2.2.9) */
+/* Sparable Partition Map (UDF 2.60 2.2.9) */
struct sparablePartitionMap {
uint8_t partitionMapType;
uint8_t partitionMapLength;
@@ -141,7 +161,7 @@ struct sparablePartitionMap {
__le32 locSparingTable[4];
} __packed;
-/* Metadata Partition Map (UDF 2.4.0 2.2.10) */
+/* Metadata Partition Map (UDF 2.60 2.2.10) */
struct metadataPartitionMap {
uint8_t partitionMapType;
uint8_t partitionMapLength;
@@ -160,14 +180,14 @@ struct metadataPartitionMap {
/* Virtual Allocation Table (UDF 1.5 2.2.10) */
struct virtualAllocationTable15 {
- __le32 VirtualSector[0];
+ __le32 vatEntry[0];
struct regid vatIdent;
__le32 previousVATICBLoc;
} __packed;
#define ICBTAG_FILE_TYPE_VAT15 0x00U
-/* Virtual Allocation Table (UDF 2.50 2.2.11) */
+/* Virtual Allocation Table (UDF 2.60 2.2.11) */
struct virtualAllocationTable20 {
__le16 lengthHeader;
__le16 lengthImpUse;
@@ -175,9 +195,9 @@ struct virtualAllocationTable20 {
__le32 previousVATICBLoc;
__le32 numFiles;
__le32 numDirs;
- __le16 minReadRevision;
- __le16 minWriteRevision;
- __le16 maxWriteRevision;
+ __le16 minUDFReadRev;
+ __le16 minUDFWriteRev;
+ __le16 maxUDFWriteRev;
__le16 reserved;
uint8_t impUse[0];
__le32 vatEntry[0];
@@ -185,7 +205,7 @@ struct virtualAllocationTable20 {
#define ICBTAG_FILE_TYPE_VAT20 0xF8U
-/* Sparing Table (UDF 2.50 2.2.12) */
+/* Sparing Table (UDF 2.60 2.2.12) */
struct sparingEntry {
__le32 origLocation;
__le32 mappedLocation;
@@ -201,12 +221,12 @@ struct sparingTable {
mapEntry[0];
} __packed;
-/* Metadata File (and Metadata Mirror File) (UDF 2.50 2.2.13.1) */
+/* Metadata File (and Metadata Mirror File) (UDF 2.60 2.2.13.1) */
#define ICBTAG_FILE_TYPE_MAIN 0xFA
#define ICBTAG_FILE_TYPE_MIRROR 0xFB
#define ICBTAG_FILE_TYPE_BITMAP 0xFC
-/* struct struct long_ad ICB - ADImpUse (UDF 2.50 2.2.4.3) */
+/* struct struct long_ad ICB - ADImpUse (UDF 2.60 2.2.4.3) */
struct allocDescImpUse {
__le16 flags;
uint8_t impUse[4];
@@ -214,17 +234,17 @@ struct allocDescImpUse {
#define AD_IU_EXT_ERASED 0x0001
-/* Real-Time Files (UDF 2.50 6.11) */
+/* Real-Time Files (UDF 2.60 6.11) */
#define ICBTAG_FILE_TYPE_REALTIME 0xF9U
-/* Implementation Use Extended Attribute (UDF 2.50 3.3.4.5) */
-/* FreeEASpace (UDF 2.50 3.3.4.5.1.1) */
+/* Implementation Use Extended Attribute (UDF 2.60 3.3.4.5) */
+/* FreeEASpace (UDF 2.60 3.3.4.5.1.1) */
struct freeEaSpace {
__le16 headerChecksum;
uint8_t freeEASpace[0];
} __packed;
-/* DVD Copyright Management Information (UDF 2.50 3.3.4.5.1.2) */
+/* DVD Copyright Management Information (UDF 2.60 3.3.4.5.1.2) */
struct DVDCopyrightImpUse {
__le16 headerChecksum;
uint8_t CGMSInfo;
@@ -232,20 +252,35 @@ struct DVDCopyrightImpUse {
uint8_t protectionSystemInfo[4];
} __packed;
-/* Application Use Extended Attribute (UDF 2.50 3.3.4.6) */
-/* FreeAppEASpace (UDF 2.50 3.3.4.6.1) */
+/* Logical Volume Extended Information (UDF 1.50 Errata, DCN 5003, 3.3.4.5.1.3) */
+struct LVExtensionEA {
+ __le16 headerChecksum;
+ __le64 verificationID;
+ __le32 numFiles;
+ __le32 numDirs;
+ dstring logicalVolIdent[128];
+} __packed;
+
+/* Application Use Extended Attribute (UDF 2.60 3.3.4.6) */
+/* FreeAppEASpace (UDF 2.60 3.3.4.6.1) */
struct freeAppEASpace {
__le16 headerChecksum;
uint8_t freeEASpace[0];
} __packed;
-/* UDF Defined System Stream (UDF 2.50 3.3.7) */
+/* UDF Defined System Stream (UDF 2.60 3.3.7) */
#define UDF_ID_UNIQUE_ID "*UDF Unique ID Mapping Data"
#define UDF_ID_NON_ALLOC "*UDF Non-Allocatable Space"
#define UDF_ID_POWER_CAL "*UDF Power Cal Table"
#define UDF_ID_BACKUP "*UDF Backup"
-/* Operating System Identifiers (UDF 2.50 6.3) */
+/* UDF Defined Non-System Streams (UDF 2.60 3.3.8) */
+#define UDF_ID_MAC_RESOURCE_FORK_STREAM "*UDF Macintosh Resource Fork"
+/* #define UDF_ID_OS2_EA "*UDF OS/2 EA" */
+#define UDF_ID_NT_ACL "*UDF NT ACL"
+#define UDF_ID_UNIX_ACL "*UDF UNIX ACL"
+
+/* Operating System Identifiers (UDF 2.60 6.3) */
#define UDF_OS_CLASS_UNDEF 0x00U
#define UDF_OS_CLASS_DOS 0x01U
#define UDF_OS_CLASS_OS2 0x02U
@@ -270,6 +305,7 @@ struct freeAppEASpace {
#define UDF_OS_ID_LINUX 0x05U
#define UDF_OS_ID_MKLINUX 0x06U
#define UDF_OS_ID_FREEBSD 0x07U
+#define UDF_OS_ID_NETBSD 0x08U
#define UDF_OS_ID_WIN9X 0x00U
#define UDF_OS_ID_WINNT 0x00U
#define UDF_OS_ID_OS400 0x00U
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 8c28e93e9b73..f747bf72edbe 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -767,20 +767,20 @@ static int udf_check_vsd(struct super_block *sb)
static int udf_verify_domain_identifier(struct super_block *sb,
struct regid *ident, char *dname)
{
- struct domainEntityIDSuffix *suffix;
+ struct domainIdentSuffix *suffix;
if (memcmp(ident->ident, UDF_ID_COMPLIANT, strlen(UDF_ID_COMPLIANT))) {
udf_warn(sb, "Not OSTA UDF compliant %s descriptor.\n", dname);
goto force_ro;
}
- if (ident->flags & (1 << ENTITYID_FLAGS_DIRTY)) {
+ if (ident->flags & ENTITYID_FLAGS_DIRTY) {
udf_warn(sb, "Possibly not OSTA UDF compliant %s descriptor.\n",
dname);
goto force_ro;
}
- suffix = (struct domainEntityIDSuffix *)ident->identSuffix;
- if (suffix->flags & (1 << ENTITYIDSUFFIX_FLAGS_HARDWRITEPROTECT) ||
- suffix->flags & (1 << ENTITYIDSUFFIX_FLAGS_SOFTWRITEPROTECT)) {
+ suffix = (struct domainIdentSuffix *)ident->identSuffix;
+ if ((suffix->domainFlags & DOMAIN_FLAGS_HARD_WRITE_PROTECT) ||
+ (suffix->domainFlags & DOMAIN_FLAGS_SOFT_WRITE_PROTECT)) {
if (!sb_rdonly(sb)) {
udf_warn(sb, "Descriptor for %s marked write protected."
" Forcing read only mount.\n", dname);
@@ -1035,7 +1035,6 @@ static int check_partition_desc(struct super_block *sb,
switch (le32_to_cpu(p->accessType)) {
case PD_ACCESS_TYPE_READ_ONLY:
case PD_ACCESS_TYPE_WRITE_ONCE:
- case PD_ACCESS_TYPE_REWRITABLE:
case PD_ACCESS_TYPE_NONE:
goto force_ro;
}
@@ -1063,7 +1062,8 @@ static int check_partition_desc(struct super_block *sb,
goto force_ro;
if (map->s_partition_type == UDF_VIRTUAL_MAP15 ||
- map->s_partition_type == UDF_VIRTUAL_MAP20)
+ map->s_partition_type == UDF_VIRTUAL_MAP20 ||
+ map->s_partition_type == UDF_METADATA_MAP25)
goto force_ro;
return 0;
@@ -2402,6 +2402,10 @@ static int udf_statfs(struct dentry *dentry, struct kstatfs *buf)
buf->f_blocks = sbi->s_partmaps[sbi->s_partition].s_partition_len;
buf->f_bfree = udf_count_free(sb);
buf->f_bavail = buf->f_bfree;
+ /*
+ * Let's pretend each free block is also a free 'inode' since UDF does
+ * not have separate preallocated table of inodes.
+ */
buf->f_files = (lvidiu != NULL ? (le32_to_cpu(lvidiu->numFiles) +
le32_to_cpu(lvidiu->numDirs)) : 0)
+ buf->f_bfree;
@@ -2492,17 +2496,29 @@ static unsigned int udf_count_free_table(struct super_block *sb,
static unsigned int udf_count_free(struct super_block *sb)
{
unsigned int accum = 0;
- struct udf_sb_info *sbi;
+ struct udf_sb_info *sbi = UDF_SB(sb);
struct udf_part_map *map;
+ unsigned int part = sbi->s_partition;
+ int ptype = sbi->s_partmaps[part].s_partition_type;
+
+ if (ptype == UDF_METADATA_MAP25) {
+ part = sbi->s_partmaps[part].s_type_specific.s_metadata.
+ s_phys_partition_ref;
+ } else if (ptype == UDF_VIRTUAL_MAP15 || ptype == UDF_VIRTUAL_MAP20) {
+ /*
+ * Filesystems with VAT are append-only and we cannot write to
+ * them. Let's just report 0 here.
+ */
+ return 0;
+ }
- sbi = UDF_SB(sb);
if (sbi->s_lvid_bh) {
struct logicalVolIntegrityDesc *lvid =
(struct logicalVolIntegrityDesc *)
sbi->s_lvid_bh->b_data;
- if (le32_to_cpu(lvid->numOfPartitions) > sbi->s_partition) {
+ if (le32_to_cpu(lvid->numOfPartitions) > part) {
accum = le32_to_cpu(
- lvid->freeSpaceTable[sbi->s_partition]);
+ lvid->freeSpaceTable[part]);
if (accum == 0xFFFFFFFF)
accum = 0;
}
@@ -2511,7 +2527,7 @@ static unsigned int udf_count_free(struct super_block *sb)
if (accum)
return accum;
- map = &sbi->s_partmaps[sbi->s_partition];
+ map = &sbi->s_partmaps[part];
if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_BITMAP) {
accum += udf_count_free_bitmap(sb,
map->s_uspace.s_bitmap);
diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c
index 63a47f1e1d52..532cda99644e 100644
--- a/fs/udf/truncate.c
+++ b/fs/udf/truncate.c
@@ -241,7 +241,7 @@ int udf_truncate_extents(struct inode *inode)
while ((etype = udf_current_aext(inode, &epos, &eloc,
&elen, 0)) != -1) {
- if (etype == (EXT_NEXT_EXTENT_ALLOCDECS >> 30)) {
+ if (etype == (EXT_NEXT_EXTENT_ALLOCDESCS >> 30)) {
udf_write_aext(inode, &epos, &neloc, nelen, 0);
if (indirect_ext_len) {
/* We managed to free all extents in the
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 0d7fcc983b3d..e6149720ce02 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -62,6 +62,7 @@ xfs_attr_args_init(
struct xfs_da_args *args,
struct xfs_inode *dp,
const unsigned char *name,
+ size_t namelen,
int flags)
{
@@ -74,7 +75,7 @@ xfs_attr_args_init(
args->dp = dp;
args->flags = flags;
args->name = name;
- args->namelen = strlen((const char *)name);
+ args->namelen = namelen;
if (args->namelen >= MAXNAMELEN)
return -EFAULT; /* match IRIX behaviour */
@@ -139,6 +140,7 @@ int
xfs_attr_get(
struct xfs_inode *ip,
const unsigned char *name,
+ size_t namelen,
unsigned char **value,
int *valuelenp,
int flags)
@@ -154,7 +156,7 @@ xfs_attr_get(
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
return -EIO;
- error = xfs_attr_args_init(&args, ip, name, flags);
+ error = xfs_attr_args_init(&args, ip, name, namelen, flags);
if (error)
return error;
@@ -338,6 +340,7 @@ int
xfs_attr_set(
struct xfs_inode *dp,
const unsigned char *name,
+ size_t namelen,
unsigned char *value,
int valuelen,
int flags)
@@ -353,7 +356,7 @@ xfs_attr_set(
if (XFS_FORCED_SHUTDOWN(dp->i_mount))
return -EIO;
- error = xfs_attr_args_init(&args, dp, name, flags);
+ error = xfs_attr_args_init(&args, dp, name, namelen, flags);
if (error)
return error;
@@ -442,6 +445,7 @@ int
xfs_attr_remove(
struct xfs_inode *dp,
const unsigned char *name,
+ size_t namelen,
int flags)
{
struct xfs_mount *mp = dp->i_mount;
@@ -453,7 +457,7 @@ xfs_attr_remove(
if (XFS_FORCED_SHUTDOWN(dp->i_mount))
return -EIO;
- error = xfs_attr_args_init(&args, dp, name, flags);
+ error = xfs_attr_args_init(&args, dp, name, namelen, flags);
if (error)
return error;
@@ -1007,7 +1011,7 @@ restart:
* The INCOMPLETE flag means that we will find the "old"
* attr, not the "new" one.
*/
- args->flags |= XFS_ATTR_INCOMPLETE;
+ args->op_flags |= XFS_DA_OP_INCOMPLETE;
state = xfs_da_state_alloc();
state->args = args;
state->mp = mp;
diff --git a/fs/xfs/libxfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h
index 94badfa1743e..4243b2272642 100644
--- a/fs/xfs/libxfs/xfs_attr.h
+++ b/fs/xfs/libxfs/xfs_attr.h
@@ -26,7 +26,7 @@ struct xfs_attr_list_context;
*========================================================================*/
-#define ATTR_DONTFOLLOW 0x0001 /* -- unused, from IRIX -- */
+#define ATTR_DONTFOLLOW 0x0001 /* -- ignored, from IRIX -- */
#define ATTR_ROOT 0x0002 /* use attrs in root (trusted) namespace */
#define ATTR_TRUST 0x0004 /* -- unused, from IRIX -- */
#define ATTR_SECURE 0x0008 /* use attrs in security namespace */
@@ -37,7 +37,10 @@ struct xfs_attr_list_context;
#define ATTR_KERNOVAL 0x2000 /* [kernel] get attr size only, not value */
#define ATTR_INCOMPLETE 0x4000 /* [kernel] return INCOMPLETE attr keys */
-#define ATTR_ALLOC 0x8000 /* allocate xattr buffer on demand */
+#define ATTR_ALLOC 0x8000 /* [kernel] allocate xattr buffer on demand */
+
+#define ATTR_KERNEL_FLAGS \
+ (ATTR_KERNOTIME | ATTR_KERNOVAL | ATTR_INCOMPLETE | ATTR_ALLOC)
#define XFS_ATTR_FLAGS \
{ ATTR_DONTFOLLOW, "DONTFOLLOW" }, \
@@ -145,11 +148,13 @@ int xfs_attr_list_int(struct xfs_attr_list_context *);
int xfs_inode_hasattr(struct xfs_inode *ip);
int xfs_attr_get_ilocked(struct xfs_inode *ip, struct xfs_da_args *args);
int xfs_attr_get(struct xfs_inode *ip, const unsigned char *name,
- unsigned char **value, int *valuelenp, int flags);
+ size_t namelen, unsigned char **value, int *valuelenp,
+ int flags);
int xfs_attr_set(struct xfs_inode *dp, const unsigned char *name,
- unsigned char *value, int valuelen, int flags);
+ size_t namelen, unsigned char *value, int valuelen, int flags);
int xfs_attr_set_args(struct xfs_da_args *args);
-int xfs_attr_remove(struct xfs_inode *dp, const unsigned char *name, int flags);
+int xfs_attr_remove(struct xfs_inode *dp, const unsigned char *name,
+ size_t namelen, int flags);
int xfs_attr_remove_args(struct xfs_da_args *args);
int xfs_attr_list(struct xfs_inode *dp, char *buffer, int bufsize,
int flags, struct attrlist_cursor_kern *cursor);
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 08d4b10ae2d5..fed537a4353d 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -2403,8 +2403,8 @@ xfs_attr3_leaf_lookup_int(
* If we are looking for INCOMPLETE entries, show only those.
* If we are looking for complete entries, show only those.
*/
- if ((args->flags & XFS_ATTR_INCOMPLETE) !=
- (entry->flags & XFS_ATTR_INCOMPLETE)) {
+ if (!!(args->op_flags & XFS_DA_OP_INCOMPLETE) !=
+ !!(entry->flags & XFS_ATTR_INCOMPLETE)) {
continue;
}
if (entry->flags & XFS_ATTR_LOCAL) {
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h
index f4a188e28b7b..73615b1dd1a8 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.h
+++ b/fs/xfs/libxfs/xfs_attr_leaf.h
@@ -39,15 +39,6 @@ struct xfs_attr3_icleaf_hdr {
} freemap[XFS_ATTR_LEAF_MAPSIZE];
};
-/*
- * Used to keep a list of "remote value" extents when unlinking an inode.
- */
-typedef struct xfs_attr_inactive_list {
- xfs_dablk_t valueblk; /* block number of value bytes */
- int valuelen; /* number of bytes in value */
-} xfs_attr_inactive_list_t;
-
-
/*========================================================================
* Function prototypes for the kernel.
*========================================================================*/
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index a6ef5df42669..a266d05df146 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -26,6 +26,23 @@
#define ATTR_RMTVALUE_MAPSIZE 1 /* # of map entries at once */
/*
+ * Remote Attribute Values
+ * =======================
+ *
+ * Remote extended attribute values are conceptually simple -- they're written
+ * to data blocks mapped by an inode's attribute fork, and they have an upper
+ * size limit of 64k. Setting a value does not involve the XFS log.
+ *
+ * However, on a v5 filesystem, maximally sized remote attr values require one
+ * block more than 64k worth of space to hold both the remote attribute value
+ * header (64 bytes). On a 4k block filesystem this results in a 68k buffer;
+ * on a 64k block filesystem, this would be a 128k buffer. Note that the log
+ * format can only handle a dirty buffer of XFS_MAX_BLOCKSIZE length (64k).
+ * Therefore, we /must/ ensure that remote attribute value buffers never touch
+ * the logging system and therefore never have a log item.
+ */
+
+/*
* Each contiguous block has a header, so it is not just a simple attribute
* length to FSB conversion.
*/
@@ -401,17 +418,25 @@ xfs_attr_rmtval_get(
(map[i].br_startblock != HOLESTARTBLOCK));
dblkno = XFS_FSB_TO_DADDR(mp, map[i].br_startblock);
dblkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount);
- error = xfs_trans_read_buf(mp, args->trans,
- mp->m_ddev_targp,
- dblkno, dblkcnt, 0, &bp,
- &xfs_attr3_rmt_buf_ops);
- if (error)
+ bp = xfs_buf_read(mp->m_ddev_targp, dblkno, dblkcnt, 0,
+ &xfs_attr3_rmt_buf_ops);
+ if (!bp)
+ return -ENOMEM;
+ error = bp->b_error;
+ if (error) {
+ xfs_buf_ioerror_alert(bp, __func__);
+ xfs_buf_relse(bp);
+
+ /* bad CRC means corrupted metadata */
+ if (error == -EFSBADCRC)
+ error = -EFSCORRUPTED;
return error;
+ }
error = xfs_attr_rmtval_copyout(mp, bp, args->dp->i_ino,
&offset, &valuelen,
&dst);
- xfs_trans_brelse(args->trans, bp);
+ xfs_buf_relse(bp);
if (error)
return error;
@@ -552,6 +577,33 @@ xfs_attr_rmtval_set(
return 0;
}
+/* Mark stale any incore buffers for the remote value. */
+int
+xfs_attr_rmtval_stale(
+ struct xfs_inode *ip,
+ struct xfs_bmbt_irec *map,
+ xfs_buf_flags_t incore_flags)
+{
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_buf *bp;
+
+ ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+
+ if (XFS_IS_CORRUPT(mp, map->br_startblock == DELAYSTARTBLOCK) ||
+ XFS_IS_CORRUPT(mp, map->br_startblock == HOLESTARTBLOCK))
+ return -EFSCORRUPTED;
+
+ bp = xfs_buf_incore(mp->m_ddev_targp,
+ XFS_FSB_TO_DADDR(mp, map->br_startblock),
+ XFS_FSB_TO_BB(mp, map->br_blockcount), incore_flags);
+ if (bp) {
+ xfs_buf_stale(bp);
+ xfs_buf_relse(bp);
+ }
+
+ return 0;
+}
+
/*
* Remove the value associated with an attribute by deleting the
* out-of-line buffer that it is stored on.
@@ -560,7 +612,6 @@ int
xfs_attr_rmtval_remove(
struct xfs_da_args *args)
{
- struct xfs_mount *mp = args->dp->i_mount;
xfs_dablk_t lblkno;
int blkcnt;
int error;
@@ -575,9 +626,6 @@ xfs_attr_rmtval_remove(
blkcnt = args->rmtblkcnt;
while (blkcnt > 0) {
struct xfs_bmbt_irec map;
- struct xfs_buf *bp;
- xfs_daddr_t dblkno;
- int dblkcnt;
int nmap;
/*
@@ -588,22 +636,11 @@ xfs_attr_rmtval_remove(
blkcnt, &map, &nmap, XFS_BMAPI_ATTRFORK);
if (error)
return error;
- ASSERT(nmap == 1);
- ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
- (map.br_startblock != HOLESTARTBLOCK));
-
- dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock),
- dblkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount);
-
- /*
- * If the "remote" value is in the cache, remove it.
- */
- bp = xfs_buf_incore(mp->m_ddev_targp, dblkno, dblkcnt, XBF_TRYLOCK);
- if (bp) {
- xfs_buf_stale(bp);
- xfs_buf_relse(bp);
- bp = NULL;
- }
+ if (XFS_IS_CORRUPT(args->dp->i_mount, nmap != 1))
+ return -EFSCORRUPTED;
+ error = xfs_attr_rmtval_stale(args->dp, &map, XBF_TRYLOCK);
+ if (error)
+ return error;
lblkno += map.br_blockcount;
blkcnt -= map.br_blockcount;
diff --git a/fs/xfs/libxfs/xfs_attr_remote.h b/fs/xfs/libxfs/xfs_attr_remote.h
index 9d20b66ad379..6fb4572845ce 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.h
+++ b/fs/xfs/libxfs/xfs_attr_remote.h
@@ -11,5 +11,7 @@ int xfs_attr3_rmt_blocks(struct xfs_mount *mp, int attrlen);
int xfs_attr_rmtval_get(struct xfs_da_args *args);
int xfs_attr_rmtval_set(struct xfs_da_args *args);
int xfs_attr_rmtval_remove(struct xfs_da_args *args);
+int xfs_attr_rmtval_stale(struct xfs_inode *ip, struct xfs_bmbt_irec *map,
+ xfs_buf_flags_t incore_flags);
#endif /* __XFS_ATTR_REMOTE_H__ */
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index e2cc98931552..b22c7e928eb1 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -2389,8 +2389,6 @@ xfs_btree_lshift(
XFS_BTREE_STATS_ADD(cur, moves, rrecs - 1);
if (level > 0) {
/* It's a nonleaf. operate on keys and ptrs */
- int i; /* loop index */
-
for (i = 0; i < rrecs; i++) {
error = xfs_btree_debug_check_ptr(cur, rpp, i + 1, level);
if (error)
diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h
index e16610d1c14f..0f4fbb0889ff 100644
--- a/fs/xfs/libxfs/xfs_da_btree.h
+++ b/fs/xfs/libxfs/xfs_da_btree.h
@@ -89,6 +89,7 @@ typedef struct xfs_da_args {
#define XFS_DA_OP_OKNOENT 0x0008 /* lookup/add op, ENOENT ok, else die */
#define XFS_DA_OP_CILOOKUP 0x0010 /* lookup to return CI name if found */
#define XFS_DA_OP_ALLOCVAL 0x0020 /* lookup to alloc buffer if found */
+#define XFS_DA_OP_INCOMPLETE 0x0040 /* lookup INCOMPLETE attr keys */
#define XFS_DA_OP_FLAGS \
{ XFS_DA_OP_JUSTCHECK, "JUSTCHECK" }, \
@@ -96,7 +97,8 @@ typedef struct xfs_da_args {
{ XFS_DA_OP_ADDNAME, "ADDNAME" }, \
{ XFS_DA_OP_OKNOENT, "OKNOENT" }, \
{ XFS_DA_OP_CILOOKUP, "CILOOKUP" }, \
- { XFS_DA_OP_ALLOCVAL, "ALLOCVAL" }
+ { XFS_DA_OP_ALLOCVAL, "ALLOCVAL" }, \
+ { XFS_DA_OP_INCOMPLETE, "INCOMPLETE" }
/*
* Storage for holding state during Btree searches and split/join ops.
diff --git a/fs/xfs/libxfs/xfs_da_format.h b/fs/xfs/libxfs/xfs_da_format.h
index 3dee33043e09..734837a9b51a 100644
--- a/fs/xfs/libxfs/xfs_da_format.h
+++ b/fs/xfs/libxfs/xfs_da_format.h
@@ -217,7 +217,7 @@ typedef struct xfs_dir2_sf_entry {
* A 64-bit or 32-bit inode number follows here, at a variable offset
* after the name.
*/
-} xfs_dir2_sf_entry_t;
+} __packed xfs_dir2_sf_entry_t;
static inline int xfs_dir2_sf_hdr_size(int i8count)
{
@@ -683,8 +683,6 @@ struct xfs_attr3_leafblock {
/*
* Flags used in the leaf_entry[i].flags field.
- * NOTE: the INCOMPLETE bit must not collide with the flags bits specified
- * on the system call, they are "or"ed together for various operations.
*/
#define XFS_ATTR_LOCAL_BIT 0 /* attr is stored locally */
#define XFS_ATTR_ROOT_BIT 1 /* limit access to trusted attrs */
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 1b7dcbae051c..77e9fa385980 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -1540,6 +1540,13 @@ typedef struct xfs_bmdr_block {
#define BMBT_BLOCKCOUNT_BITLEN 21
#define BMBT_STARTOFF_MASK ((1ULL << BMBT_STARTOFF_BITLEN) - 1)
+#define BMBT_BLOCKCOUNT_MASK ((1ULL << BMBT_BLOCKCOUNT_BITLEN) - 1)
+
+/*
+ * bmbt records have a file offset (block) field that is 54 bits wide, so this
+ * is the largest xfs_fileoff_t that we ever expect to see.
+ */
+#define XFS_MAX_FILEOFF (BMBT_STARTOFF_MASK + BMBT_BLOCKCOUNT_MASK)
typedef struct xfs_bmbt_rec {
__be64 l0, l1;
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index 8ef31d71a9c7..9bac0d2e56dc 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -462,11 +462,20 @@ static inline uint xfs_log_dinode_size(int version)
#define XFS_BLF_GDQUOT_BUF (1<<4)
/*
- * This is the structure used to lay out a buf log item in the
- * log. The data map describes which 128 byte chunks of the buffer
- * have been logged.
- */
-#define XFS_BLF_DATAMAP_SIZE ((XFS_MAX_BLOCKSIZE / XFS_BLF_CHUNK) / NBWORD)
+ * This is the structure used to lay out a buf log item in the log. The data
+ * map describes which 128 byte chunks of the buffer have been logged.
+ *
+ * The placement of blf_map_size causes blf_data_map to start at an odd
+ * multiple of sizeof(unsigned int) offset within the struct. Because the data
+ * bitmap size will always be an even number, the end of the data_map (and
+ * therefore the structure) will also be at an odd multiple of sizeof(unsigned
+ * int). Some 64-bit compilers will insert padding at the end of the struct to
+ * ensure 64-bit alignment of blf_blkno, but 32-bit ones will not. Therefore,
+ * XFS_BLF_DATAMAP_SIZE must be an odd number to make the padding explicit and
+ * keep the structure size consistent between 32-bit and 64-bit platforms.
+ */
+#define __XFS_BLF_DATAMAP_SIZE ((XFS_MAX_BLOCKSIZE / XFS_BLF_CHUNK) / NBWORD)
+#define XFS_BLF_DATAMAP_SIZE (__XFS_BLF_DATAMAP_SIZE + 1)
typedef struct xfs_buf_log_format {
unsigned short blf_type; /* buf log item type indicator */
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 60c61d7052a8..c3422403b169 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -75,7 +75,6 @@ static inline xfs_extlen_t
xrep_calc_ag_resblks(
struct xfs_scrub *sc)
{
- ASSERT(!(sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR));
return 0;
}
diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c
index 91693fce34a8..cd743fad8478 100644
--- a/fs/xfs/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
@@ -145,7 +145,8 @@ xfs_get_acl(struct inode *inode, int type)
* go out to the disk.
*/
len = XFS_ACL_MAX_SIZE(ip->i_mount);
- error = xfs_attr_get(ip, ea_name, (unsigned char **)&xfs_acl, &len,
+ error = xfs_attr_get(ip, ea_name, strlen(ea_name),
+ (unsigned char **)&xfs_acl, &len,
ATTR_ALLOC | ATTR_ROOT);
if (error) {
/*
@@ -196,15 +197,17 @@ __xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
len -= sizeof(struct xfs_acl_entry) *
(XFS_ACL_MAX_ENTRIES(ip->i_mount) - acl->a_count);
- error = xfs_attr_set(ip, ea_name, (unsigned char *)xfs_acl,
- len, ATTR_ROOT);
+ error = xfs_attr_set(ip, ea_name, strlen(ea_name),
+ (unsigned char *)xfs_acl, len, ATTR_ROOT);
kmem_free(xfs_acl);
} else {
/*
* A NULL ACL argument means we want to remove the ACL.
*/
- error = xfs_attr_remove(ip, ea_name, ATTR_ROOT);
+ error = xfs_attr_remove(ip, ea_name,
+ strlen(ea_name),
+ ATTR_ROOT);
/*
* If the attribute didn't exist to start with that's fine.
diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c
index 5ff49523d8ea..8fbb841cd6fe 100644
--- a/fs/xfs/xfs_attr_inactive.c
+++ b/fs/xfs/xfs_attr_inactive.c
@@ -25,22 +25,18 @@
#include "xfs_error.h"
/*
- * Look at all the extents for this logical region,
- * invalidate any buffers that are incore/in transactions.
+ * Invalidate any incore buffers associated with this remote attribute value
+ * extent. We never log remote attribute value buffers, which means that they
+ * won't be attached to a transaction and are therefore safe to mark stale.
+ * The actual bunmapi will be taken care of later.
*/
STATIC int
-xfs_attr3_leaf_freextent(
- struct xfs_trans **trans,
+xfs_attr3_rmt_stale(
struct xfs_inode *dp,
xfs_dablk_t blkno,
int blkcnt)
{
struct xfs_bmbt_irec map;
- struct xfs_buf *bp;
- xfs_dablk_t tblkno;
- xfs_daddr_t dblkno;
- int tblkcnt;
- int dblkcnt;
int nmap;
int error;
@@ -48,47 +44,29 @@ xfs_attr3_leaf_freextent(
* Roll through the "value", invalidating the attribute value's
* blocks.
*/
- tblkno = blkno;
- tblkcnt = blkcnt;
- while (tblkcnt > 0) {
+ while (blkcnt > 0) {
/*
* Try to remember where we decided to put the value.
*/
nmap = 1;
- error = xfs_bmapi_read(dp, (xfs_fileoff_t)tblkno, tblkcnt,
+ error = xfs_bmapi_read(dp, (xfs_fileoff_t)blkno, blkcnt,
&map, &nmap, XFS_BMAPI_ATTRFORK);
- if (error) {
+ if (error)
return error;
- }
- ASSERT(nmap == 1);
- ASSERT(map.br_startblock != DELAYSTARTBLOCK);
+ if (XFS_IS_CORRUPT(dp->i_mount, nmap != 1))
+ return -EFSCORRUPTED;
/*
- * If it's a hole, these are already unmapped
- * so there's nothing to invalidate.
+ * Mark any incore buffers for the remote value as stale. We
+ * never log remote attr value buffers, so the buffer should be
+ * easy to kill.
*/
- if (map.br_startblock != HOLESTARTBLOCK) {
-
- dblkno = XFS_FSB_TO_DADDR(dp->i_mount,
- map.br_startblock);
- dblkcnt = XFS_FSB_TO_BB(dp->i_mount,
- map.br_blockcount);
- bp = xfs_trans_get_buf(*trans,
- dp->i_mount->m_ddev_targp,
- dblkno, dblkcnt, 0);
- if (!bp)
- return -ENOMEM;
- xfs_trans_binval(*trans, bp);
- /*
- * Roll to next transaction.
- */
- error = xfs_trans_roll_inode(trans, dp);
- if (error)
- return error;
- }
+ error = xfs_attr_rmtval_stale(dp, &map, 0);
+ if (error)
+ return error;
- tblkno += map.br_blockcount;
- tblkcnt -= map.br_blockcount;
+ blkno += map.br_blockcount;
+ blkcnt -= map.br_blockcount;
}
return 0;
@@ -102,86 +80,45 @@ xfs_attr3_leaf_freextent(
*/
STATIC int
xfs_attr3_leaf_inactive(
- struct xfs_trans **trans,
- struct xfs_inode *dp,
- struct xfs_buf *bp)
+ struct xfs_trans **trans,
+ struct xfs_inode *dp,
+ struct xfs_buf *bp)
{
- struct xfs_attr_leafblock *leaf;
- struct xfs_attr3_icleaf_hdr ichdr;
- struct xfs_attr_leaf_entry *entry;
+ struct xfs_attr3_icleaf_hdr ichdr;
+ struct xfs_mount *mp = bp->b_mount;
+ struct xfs_attr_leafblock *leaf = bp->b_addr;
+ struct xfs_attr_leaf_entry *entry;
struct xfs_attr_leaf_name_remote *name_rmt;
- struct xfs_attr_inactive_list *list;
- struct xfs_attr_inactive_list *lp;
- int error;
- int count;
- int size;
- int tmp;
- int i;
- struct xfs_mount *mp = bp->b_mount;
+ int error = 0;
+ int i;
- leaf = bp->b_addr;
xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf);
/*
- * Count the number of "remote" value extents.
+ * Find the remote value extents for this leaf and invalidate their
+ * incore buffers.
*/
- count = 0;
entry = xfs_attr3_leaf_entryp(leaf);
for (i = 0; i < ichdr.count; entry++, i++) {
- if (be16_to_cpu(entry->nameidx) &&
- ((entry->flags & XFS_ATTR_LOCAL) == 0)) {
- name_rmt = xfs_attr3_leaf_name_remote(leaf, i);
- if (name_rmt->valueblk)
- count++;
- }
- }
+ int blkcnt;
- /*
- * If there are no "remote" values, we're done.
- */
- if (count == 0) {
- xfs_trans_brelse(*trans, bp);
- return 0;
- }
-
- /*
- * Allocate storage for a list of all the "remote" value extents.
- */
- size = count * sizeof(xfs_attr_inactive_list_t);
- list = kmem_alloc(size, 0);
-
- /*
- * Identify each of the "remote" value extents.
- */
- lp = list;
- entry = xfs_attr3_leaf_entryp(leaf);
- for (i = 0; i < ichdr.count; entry++, i++) {
- if (be16_to_cpu(entry->nameidx) &&
- ((entry->flags & XFS_ATTR_LOCAL) == 0)) {
- name_rmt = xfs_attr3_leaf_name_remote(leaf, i);
- if (name_rmt->valueblk) {
- lp->valueblk = be32_to_cpu(name_rmt->valueblk);
- lp->valuelen = xfs_attr3_rmt_blocks(dp->i_mount,
- be32_to_cpu(name_rmt->valuelen));
- lp++;
- }
- }
- }
- xfs_trans_brelse(*trans, bp); /* unlock for trans. in freextent() */
+ if (!entry->nameidx || (entry->flags & XFS_ATTR_LOCAL))
+ continue;
- /*
- * Invalidate each of the "remote" value extents.
- */
- error = 0;
- for (lp = list, i = 0; i < count; i++, lp++) {
- tmp = xfs_attr3_leaf_freextent(trans, dp,
- lp->valueblk, lp->valuelen);
+ name_rmt = xfs_attr3_leaf_name_remote(leaf, i);
+ if (!name_rmt->valueblk)
+ continue;
- if (error == 0)
- error = tmp; /* save only the 1st errno */
+ blkcnt = xfs_attr3_rmt_blocks(dp->i_mount,
+ be32_to_cpu(name_rmt->valuelen));
+ error = xfs_attr3_rmt_stale(dp,
+ be32_to_cpu(name_rmt->valueblk), blkcnt);
+ if (error)
+ goto err;
}
- kmem_free(list);
+ xfs_trans_brelse(*trans, bp);
+err:
return error;
}
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 3984779e5911..5be8973a452c 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -27,6 +27,23 @@ static inline struct xfs_buf_log_item *BUF_ITEM(struct xfs_log_item *lip)
STATIC void xfs_buf_do_callbacks(struct xfs_buf *bp);
+/* Is this log iovec plausibly large enough to contain the buffer log format? */
+bool
+xfs_buf_log_check_iovec(
+ struct xfs_log_iovec *iovec)
+{
+ struct xfs_buf_log_format *blfp = iovec->i_addr;
+ char *bmp_end;
+ char *item_end;
+
+ if (offsetof(struct xfs_buf_log_format, blf_data_map) > iovec->i_len)
+ return false;
+
+ item_end = (char *)iovec->i_addr + iovec->i_len;
+ bmp_end = (char *)&blfp->blf_data_map[blfp->blf_map_size];
+ return bmp_end <= item_end;
+}
+
static inline int
xfs_buf_log_format_size(
struct xfs_buf_log_format *blfp)
@@ -688,7 +705,7 @@ static const struct xfs_item_ops xfs_buf_item_ops = {
.iop_push = xfs_buf_item_push,
};
-STATIC int
+STATIC void
xfs_buf_item_get_format(
struct xfs_buf_log_item *bip,
int count)
@@ -698,14 +715,11 @@ xfs_buf_item_get_format(
if (count == 1) {
bip->bli_formats = &bip->__bli_format;
- return 0;
+ return;
}
bip->bli_formats = kmem_zalloc(count * sizeof(struct xfs_buf_log_format),
0);
- if (!bip->bli_formats)
- return -ENOMEM;
- return 0;
}
STATIC void
@@ -731,7 +745,6 @@ xfs_buf_item_init(
struct xfs_buf_log_item *bip = bp->b_log_item;
int chunks;
int map_size;
- int error;
int i;
/*
@@ -760,19 +773,22 @@ xfs_buf_item_init(
* Discontiguous buffer support follows the layout of the underlying
* buffer. This makes the implementation as simple as possible.
*/
- error = xfs_buf_item_get_format(bip, bp->b_map_count);
- ASSERT(error == 0);
- if (error) { /* to stop gcc throwing set-but-unused warnings */
- kmem_cache_free(xfs_buf_item_zone, bip);
- return error;
- }
-
+ xfs_buf_item_get_format(bip, bp->b_map_count);
for (i = 0; i < bip->bli_format_count; i++) {
chunks = DIV_ROUND_UP(BBTOB(bp->b_maps[i].bm_len),
XFS_BLF_CHUNK);
map_size = DIV_ROUND_UP(chunks, NBWORD);
+ if (map_size > XFS_BLF_DATAMAP_SIZE) {
+ kmem_cache_free(xfs_buf_item_zone, bip);
+ xfs_err(mp,
+ "buffer item dirty bitmap (%u uints) too small to reflect %u bytes!",
+ map_size,
+ BBTOB(bp->b_maps[i].bm_len));
+ return -EFSCORRUPTED;
+ }
+
bip->bli_formats[i].blf_type = XFS_LI_BUF;
bip->bli_formats[i].blf_blkno = bp->b_maps[i].bm_bn;
bip->bli_formats[i].blf_len = bp->b_maps[i].bm_len;
@@ -805,6 +821,9 @@ xfs_buf_item_log_segment(
uint end_bit;
uint mask;
+ ASSERT(first < XFS_BLF_DATAMAP_SIZE * XFS_BLF_CHUNK * NBWORD);
+ ASSERT(last < XFS_BLF_DATAMAP_SIZE * XFS_BLF_CHUNK * NBWORD);
+
/*
* Convert byte offsets to bit numbers.
*/
diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h
index 4a054b11011a..30114b510332 100644
--- a/fs/xfs/xfs_buf_item.h
+++ b/fs/xfs/xfs_buf_item.h
@@ -61,6 +61,7 @@ void xfs_buf_iodone_callbacks(struct xfs_buf *);
void xfs_buf_iodone(struct xfs_buf *, struct xfs_log_item *);
bool xfs_buf_resubmit_failed_buffers(struct xfs_buf *,
struct list_head *);
+bool xfs_buf_log_check_iovec(struct xfs_log_iovec *iovec);
extern kmem_zone_t *xfs_buf_item_zone;
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 2bff21ca9d78..9cfd3209f52b 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -137,7 +137,7 @@ xfs_qm_adjust_dqtimers(
(d->d_blk_hardlimit &&
(be64_to_cpu(d->d_bcount) >
be64_to_cpu(d->d_blk_hardlimit)))) {
- d->d_btimer = cpu_to_be32(get_seconds() +
+ d->d_btimer = cpu_to_be32(ktime_get_real_seconds() +
mp->m_quotainfo->qi_btimelimit);
} else {
d->d_bwarns = 0;
@@ -160,7 +160,7 @@ xfs_qm_adjust_dqtimers(
(d->d_ino_hardlimit &&
(be64_to_cpu(d->d_icount) >
be64_to_cpu(d->d_ino_hardlimit)))) {
- d->d_itimer = cpu_to_be32(get_seconds() +
+ d->d_itimer = cpu_to_be32(ktime_get_real_seconds() +
mp->m_quotainfo->qi_itimelimit);
} else {
d->d_iwarns = 0;
@@ -183,7 +183,7 @@ xfs_qm_adjust_dqtimers(
(d->d_rtb_hardlimit &&
(be64_to_cpu(d->d_rtbcount) >
be64_to_cpu(d->d_rtb_hardlimit)))) {
- d->d_rtbtimer = cpu_to_be32(get_seconds() +
+ d->d_rtbtimer = cpu_to_be32(ktime_get_real_seconds() +
mp->m_quotainfo->qi_rtbtimelimit);
} else {
d->d_rtbwarns = 0;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index c93250108952..b8a4a3f29b36 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -187,7 +187,12 @@ xfs_file_dio_aio_read(
file_accessed(iocb->ki_filp);
- xfs_ilock(ip, XFS_IOLOCK_SHARED);
+ if (iocb->ki_flags & IOCB_NOWAIT) {
+ if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED))
+ return -EAGAIN;
+ } else {
+ xfs_ilock(ip, XFS_IOLOCK_SHARED);
+ }
ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops, NULL,
is_sync_kiocb(iocb));
xfs_iunlock(ip, XFS_IOLOCK_SHARED);
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 401da197f012..1979a0055763 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1518,10 +1518,8 @@ xfs_itruncate_extents_flags(
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp = *tpp;
xfs_fileoff_t first_unmap_block;
- xfs_fileoff_t last_block;
xfs_filblks_t unmap_len;
int error = 0;
- int done = 0;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
ASSERT(!atomic_read(&VFS_I(ip)->i_count) ||
@@ -1541,21 +1539,22 @@ xfs_itruncate_extents_flags(
* the end of the file (in a crash where the space is allocated
* but the inode size is not yet updated), simply remove any
* blocks which show up between the new EOF and the maximum
- * possible file size. If the first block to be removed is
- * beyond the maximum file size (ie it is the same as last_block),
- * then there is nothing to do.
+ * possible file size.
+ *
+ * We have to free all the blocks to the bmbt maximum offset, even if
+ * the page cache can't scale that far.
*/
first_unmap_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)new_size);
- last_block = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
- if (first_unmap_block == last_block)
+ if (first_unmap_block >= XFS_MAX_FILEOFF) {
+ WARN_ON_ONCE(first_unmap_block > XFS_MAX_FILEOFF);
return 0;
+ }
- ASSERT(first_unmap_block < last_block);
- unmap_len = last_block - first_unmap_block + 1;
- while (!done) {
+ unmap_len = XFS_MAX_FILEOFF - first_unmap_block + 1;
+ while (unmap_len > 0) {
ASSERT(tp->t_firstblock == NULLFSBLOCK);
- error = xfs_bunmapi(tp, ip, first_unmap_block, unmap_len, flags,
- XFS_ITRUNC_MAX_EXTENTS, &done);
+ error = __xfs_bunmapi(tp, ip, first_unmap_block, &unmap_len,
+ flags, XFS_ITRUNC_MAX_EXTENTS);
if (error)
goto out;
@@ -1575,7 +1574,7 @@ xfs_itruncate_extents_flags(
if (whichfork == XFS_DATA_FORK) {
/* Remove all pending CoW reservations. */
error = xfs_reflink_cancel_cow_blocks(ip, &tp,
- first_unmap_block, last_block, true);
+ first_unmap_block, XFS_MAX_FILEOFF, true);
if (error)
goto out;
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 7b35d62ede9f..d42de92cb283 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -357,6 +357,7 @@ xfs_attrmulti_attr_get(
{
unsigned char *kbuf;
int error = -EFAULT;
+ size_t namelen;
if (*len > XFS_XATTR_SIZE_MAX)
return -EINVAL;
@@ -364,7 +365,9 @@ xfs_attrmulti_attr_get(
if (!kbuf)
return -ENOMEM;
- error = xfs_attr_get(XFS_I(inode), name, &kbuf, (int *)len, flags);
+ namelen = strlen(name);
+ error = xfs_attr_get(XFS_I(inode), name, namelen, &kbuf, (int *)len,
+ flags);
if (error)
goto out_kfree;
@@ -386,6 +389,7 @@ xfs_attrmulti_attr_set(
{
unsigned char *kbuf;
int error;
+ size_t namelen;
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
return -EPERM;
@@ -396,7 +400,8 @@ xfs_attrmulti_attr_set(
if (IS_ERR(kbuf))
return PTR_ERR(kbuf);
- error = xfs_attr_set(XFS_I(inode), name, kbuf, len, flags);
+ namelen = strlen(name);
+ error = xfs_attr_set(XFS_I(inode), name, namelen, kbuf, len, flags);
if (!error)
xfs_forget_acl(inode, name, flags);
kfree(kbuf);
@@ -410,10 +415,12 @@ xfs_attrmulti_attr_remove(
uint32_t flags)
{
int error;
+ size_t namelen;
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
return -EPERM;
- error = xfs_attr_remove(XFS_I(inode), name, flags);
+ namelen = strlen(name);
+ error = xfs_attr_remove(XFS_I(inode), name, namelen, flags);
if (!error)
xfs_forget_acl(inode, name, flags);
return error;
@@ -462,6 +469,13 @@ xfs_attrmulti_by_handle(
error = 0;
for (i = 0; i < am_hreq.opcount; i++) {
+ if ((ops[i].am_flags & ATTR_ROOT) &&
+ (ops[i].am_flags & ATTR_SECURE)) {
+ ops[i].am_error = -EINVAL;
+ continue;
+ }
+ ops[i].am_flags &= ~ATTR_KERNEL_FLAGS;
+
ops[i].am_error = strncpy_from_user((char *)attr_name,
ops[i].am_attrname, MAXNAMELEN);
if (ops[i].am_error == 0 || ops[i].am_error == MAXNAMELEN)
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index c4c4f09113d3..769581a79c58 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -107,7 +107,7 @@ xfs_ioctl32_bstime_copyin(
xfs_bstime_t *bstime,
compat_xfs_bstime_t __user *bstime32)
{
- compat_time_t sec32; /* tv_sec differs on 64 vs. 32 */
+ old_time32_t sec32; /* tv_sec differs on 64 vs. 32 */
if (get_user(sec32, &bstime32->tv_sec) ||
get_user(bstime->tv_nsec, &bstime32->tv_nsec))
@@ -450,6 +450,13 @@ xfs_compat_attrmulti_by_handle(
error = 0;
for (i = 0; i < am_hreq.opcount; i++) {
+ if ((ops[i].am_flags & ATTR_ROOT) &&
+ (ops[i].am_flags & ATTR_SECURE)) {
+ ops[i].am_error = -EINVAL;
+ continue;
+ }
+ ops[i].am_flags &= ~ATTR_KERNEL_FLAGS;
+
ops[i].am_error = strncpy_from_user((char *)attr_name,
compat_ptr(ops[i].am_attrname),
MAXNAMELEN);
diff --git a/fs/xfs/xfs_ioctl32.h b/fs/xfs/xfs_ioctl32.h
index 8c7743cd490e..053de7d894cd 100644
--- a/fs/xfs/xfs_ioctl32.h
+++ b/fs/xfs/xfs_ioctl32.h
@@ -32,7 +32,7 @@
#endif
typedef struct compat_xfs_bstime {
- compat_time_t tv_sec; /* seconds */
+ old_time32_t tv_sec; /* seconds */
__s32 tv_nsec; /* and nanoseconds */
} compat_xfs_bstime_t;
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 28e2d1f37267..bb590a267a7f 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -923,7 +923,7 @@ xfs_buffered_write_iomap_begin(
xfs_trim_extent(&imap, offset_fsb, end_fsb - offset_fsb);
/* Trim the mapping to the nearest shared extent boundary. */
- error = xfs_inode_need_cow(ip, &imap, &shared);
+ error = xfs_bmap_trim_cow(ip, &imap, &shared);
if (error)
goto out_unlock;
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 8afe69ca188b..81f2f93caec0 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -50,8 +50,10 @@ xfs_initxattrs(
int error = 0;
for (xattr = xattr_array; xattr->name != NULL; xattr++) {
- error = xfs_attr_set(ip, xattr->name, xattr->value,
- xattr->value_len, ATTR_SECURE);
+ error = xfs_attr_set(ip, xattr->name,
+ strlen(xattr->name),
+ xattr->value, xattr->value_len,
+ ATTR_SECURE);
if (error < 0)
break;
}
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 99ec3fba4548..0d683fb96396 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1934,6 +1934,12 @@ xlog_recover_buffer_pass1(
struct list_head *bucket;
struct xfs_buf_cancel *bcp;
+ if (!xfs_buf_log_check_iovec(&item->ri_buf[0])) {
+ xfs_err(log->l_mp, "bad buffer log item size (%d)",
+ item->ri_buf[0].i_len);
+ return -EFSCORRUPTED;
+ }
+
/*
* If this isn't a cancel buffer item, then just return.
*/
diff --git a/fs/xfs/xfs_ondisk.h b/fs/xfs/xfs_ondisk.h
index b6701b4f59a9..5f04d8a5ab2a 100644
--- a/fs/xfs/xfs_ondisk.h
+++ b/fs/xfs/xfs_ondisk.h
@@ -111,6 +111,7 @@ xfs_check_ondisk_structs(void)
XFS_CHECK_STRUCT_SIZE(xfs_dir2_sf_hdr_t, 10);
/* log structures */
+ XFS_CHECK_STRUCT_SIZE(struct xfs_buf_log_format, 88);
XFS_CHECK_STRUCT_SIZE(struct xfs_dq_logformat, 24);
XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_32, 28);
XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_64, 32);
diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h
index 7823af39008b..4e57edca8bce 100644
--- a/fs/xfs/xfs_qm.h
+++ b/fs/xfs/xfs_qm.h
@@ -64,9 +64,9 @@ struct xfs_quotainfo {
struct xfs_inode *qi_pquotaip; /* project quota inode */
struct list_lru qi_lru;
int qi_dquots;
- time_t qi_btimelimit; /* limit for blks timer */
- time_t qi_itimelimit; /* limit for inodes timer */
- time_t qi_rtbtimelimit;/* limit for rt blks timer */
+ time64_t qi_btimelimit; /* limit for blks timer */
+ time64_t qi_itimelimit; /* limit for inodes timer */
+ time64_t qi_rtbtimelimit;/* limit for rt blks timer */
xfs_qwarncnt_t qi_bwarnlimit; /* limit for blks warnings */
xfs_qwarncnt_t qi_iwarnlimit; /* limit for inodes warnings */
xfs_qwarncnt_t qi_rtbwarnlimit;/* limit for rt blks warnings */
diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
index c7de17deeae6..38669e827206 100644
--- a/fs/xfs/xfs_quotaops.c
+++ b/fs/xfs/xfs_quotaops.c
@@ -37,9 +37,9 @@ xfs_qm_fill_state(
tstate->flags |= QCI_SYSFILE;
tstate->blocks = ip->i_d.di_nblocks;
tstate->nextents = ip->i_d.di_nextents;
- tstate->spc_timelimit = q->qi_btimelimit;
- tstate->ino_timelimit = q->qi_itimelimit;
- tstate->rt_spc_timelimit = q->qi_rtbtimelimit;
+ tstate->spc_timelimit = (u32)q->qi_btimelimit;
+ tstate->ino_timelimit = (u32)q->qi_itimelimit;
+ tstate->rt_spc_timelimit = (u32)q->qi_rtbtimelimit;
tstate->spc_warnlimit = q->qi_bwarnlimit;
tstate->ino_warnlimit = q->qi_iwarnlimit;
tstate->rt_spc_warnlimit = q->qi_rtbwarnlimit;
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index de451235c4ee..e723b267a247 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -223,8 +223,8 @@ xfs_reflink_trim_around_shared(
}
}
-bool
-xfs_inode_need_cow(
+int
+xfs_bmap_trim_cow(
struct xfs_inode *ip,
struct xfs_bmbt_irec *imap,
bool *shared)
@@ -327,7 +327,7 @@ xfs_find_trim_cow_extent(
if (cmap->br_startoff > offset_fsb) {
xfs_trim_extent(imap, imap->br_startoff,
cmap->br_startoff - imap->br_startoff);
- return xfs_inode_need_cow(ip, imap, shared);
+ return xfs_bmap_trim_cow(ip, imap, shared);
}
*shared = true;
@@ -1457,7 +1457,8 @@ xfs_reflink_clear_inode_flag(
* We didn't find any shared blocks so turn off the reflink flag.
* First, get rid of any leftover CoW mappings.
*/
- error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, NULLFILEOFF, true);
+ error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, XFS_MAX_FILEOFF,
+ true);
if (error)
return error;
diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h
index d18ad7f4fb64..3e4fd46373ab 100644
--- a/fs/xfs/xfs_reflink.h
+++ b/fs/xfs/xfs_reflink.h
@@ -22,7 +22,7 @@ extern int xfs_reflink_find_shared(struct xfs_mount *mp, struct xfs_trans *tp,
xfs_agblock_t *fbno, xfs_extlen_t *flen, bool find_maximal);
extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip,
struct xfs_bmbt_irec *irec, bool *shared);
-bool xfs_inode_need_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *imap,
+int xfs_bmap_trim_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *imap,
bool *shared);
int xfs_reflink_allocate_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *imap,
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index d9ae27ddf253..760901783944 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -193,32 +193,6 @@ xfs_fs_show_options(
return 0;
}
-static uint64_t
-xfs_max_file_offset(
- unsigned int blockshift)
-{
- unsigned int pagefactor = 1;
- unsigned int bitshift = BITS_PER_LONG - 1;
-
- /* Figure out maximum filesize, on Linux this can depend on
- * the filesystem blocksize (on 32 bit platforms).
- * __block_write_begin does this in an [unsigned] long long...
- * page->index << (PAGE_SHIFT - bbits)
- * So, for page sized blocks (4K on 32 bit platforms),
- * this wraps at around 8Tb (hence MAX_LFS_FILESIZE which is
- * (((u64)PAGE_SIZE << (BITS_PER_LONG-1))-1)
- * but for smaller blocksizes it is less (bbits = log2 bsize).
- */
-
-#if BITS_PER_LONG == 32
- ASSERT(sizeof(sector_t) == 8);
- pagefactor = PAGE_SIZE;
- bitshift = BITS_PER_LONG;
-#endif
-
- return (((uint64_t)pagefactor) << bitshift) - 1;
-}
-
/*
* Set parameters for inode allocation heuristics, taking into account
* filesystem size and inode32/inode64 mount options; i.e. specifically
@@ -1424,6 +1398,26 @@ xfs_fc_fill_super(
if (error)
goto out_free_sb;
+ /*
+ * XFS block mappings use 54 bits to store the logical block offset.
+ * This should suffice to handle the maximum file size that the VFS
+ * supports (currently 2^63 bytes on 64-bit and ULONG_MAX << PAGE_SHIFT
+ * bytes on 32-bit), but as XFS and VFS have gotten the s_maxbytes
+ * calculation wrong on 32-bit kernels in the past, we'll add a WARN_ON
+ * to check this assertion.
+ *
+ * Avoid integer overflow by comparing the maximum bmbt offset to the
+ * maximum pagecache offset in units of fs blocks.
+ */
+ if (XFS_B_TO_FSBT(mp, MAX_LFS_FILESIZE) > XFS_MAX_FILEOFF) {
+ xfs_warn(mp,
+"MAX_LFS_FILESIZE block offset (%llu) exceeds extent map maximum (%llu)!",
+ XFS_B_TO_FSBT(mp, MAX_LFS_FILESIZE),
+ XFS_MAX_FILEOFF);
+ error = -EINVAL;
+ goto out_free_sb;
+ }
+
error = xfs_filestream_mount(mp);
if (error)
goto out_free_sb;
@@ -1435,7 +1429,7 @@ xfs_fc_fill_super(
sb->s_magic = XFS_SUPER_MAGIC;
sb->s_blocksize = mp->m_sb.sb_blocksize;
sb->s_blocksize_bits = ffs(sb->s_blocksize) - 1;
- sb->s_maxbytes = xfs_max_file_offset(sb->s_blocksize_bits);
+ sb->s_maxbytes = MAX_LFS_FILESIZE;
sb->s_max_links = XFS_MAXLINK;
sb->s_time_gran = 1;
sb->s_time_min = S32_MIN;
diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c
index a6fe2d8dc40f..d1b9869bc5fa 100644
--- a/fs/xfs/xfs_trans_dquot.c
+++ b/fs/xfs/xfs_trans_dquot.c
@@ -580,7 +580,7 @@ xfs_trans_dqresv(
{
xfs_qcnt_t hardlimit;
xfs_qcnt_t softlimit;
- time_t timer;
+ time64_t timer;
xfs_qwarncnt_t warns;
xfs_qwarncnt_t warnlimit;
xfs_qcnt_t total_count;
@@ -635,7 +635,8 @@ xfs_trans_dqresv(
goto error_return;
}
if (softlimit && total_count > softlimit) {
- if ((timer != 0 && get_seconds() > timer) ||
+ if ((timer != 0 &&
+ ktime_get_real_seconds() > timer) ||
(warns != 0 && warns >= warnlimit)) {
xfs_quota_warn(mp, dqp,
QUOTA_NL_BSOFTLONGWARN);
@@ -662,7 +663,8 @@ xfs_trans_dqresv(
goto error_return;
}
if (softlimit && total_count > softlimit) {
- if ((timer != 0 && get_seconds() > timer) ||
+ if ((timer != 0 &&
+ ktime_get_real_seconds() > timer) ||
(warns != 0 && warns >= warnlimit)) {
xfs_quota_warn(mp, dqp,
QUOTA_NL_ISOFTLONGWARN);
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index 383f0203d103..b0fedb543f97 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -24,6 +24,7 @@ xfs_xattr_get(const struct xattr_handler *handler, struct dentry *unused,
int xflags = handler->flags;
struct xfs_inode *ip = XFS_I(inode);
int error, asize = size;
+ size_t namelen = strlen(name);
/* Convert Linux syscall to XFS internal ATTR flags */
if (!size) {
@@ -31,7 +32,8 @@ xfs_xattr_get(const struct xattr_handler *handler, struct dentry *unused,
value = NULL;
}
- error = xfs_attr_get(ip, name, (unsigned char **)&value, &asize, xflags);
+ error = xfs_attr_get(ip, name, namelen, (unsigned char **)&value,
+ &asize, xflags);
if (error)
return error;
return asize;
@@ -67,6 +69,7 @@ xfs_xattr_set(const struct xattr_handler *handler, struct dentry *unused,
int xflags = handler->flags;
struct xfs_inode *ip = XFS_I(inode);
int error;
+ size_t namelen = strlen(name);
/* Convert Linux syscall to XFS internal ATTR flags */
if (flags & XATTR_CREATE)
@@ -74,10 +77,11 @@ xfs_xattr_set(const struct xattr_handler *handler, struct dentry *unused,
if (flags & XATTR_REPLACE)
xflags |= ATTR_REPLACE;
- if (!value)
- return xfs_attr_remove(ip, (unsigned char *)name, xflags);
- error = xfs_attr_set(ip, (unsigned char *)name,
- (void *)value, size, xflags);
+ if (value)
+ error = xfs_attr_set(ip, name, namelen, (void *)value, size,
+ xflags);
+ else
+ error = xfs_attr_remove(ip, name, namelen, xflags);
if (!error)
xfs_forget_acl(inode, name, xflags);