diff options
Diffstat (limited to 'fs')
97 files changed, 1989 insertions, 444 deletions
diff --git a/fs/adfs/super.c b/fs/adfs/super.c index 0ff4bae2c2a2..479ef5a9c5d3 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -213,6 +213,7 @@ static int parse_options(struct super_block *sb, char *options) static int adfs_remount(struct super_block *sb, int *flags, char *data) { + sync_filesystem(sb); *flags |= MS_NODIRATIME; return parse_options(sb, data); } diff --git a/fs/affs/super.c b/fs/affs/super.c index 45161a832bbc..01c6e07acbff 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -549,6 +549,7 @@ affs_remount(struct super_block *sb, int *flags, char *data) pr_debug("AFFS: remount(flags=0x%x,opts=\"%s\")\n",*flags,data); + sync_filesystem(sb); *flags |= MS_NODIRATIME; memcpy(volume, sbi->s_volume, 32); diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index f95dddced968..7192a7e99373 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -908,6 +908,7 @@ befs_fill_super(struct super_block *sb, void *data, int silent) static int befs_remount(struct super_block *sb, int *flags, char *data) { + sync_filesystem(sb); if (!(*flags & MS_RDONLY)) return -EINVAL; return 0; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index f0857e092a3c..461731c7fa3a 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1239,6 +1239,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) unsigned int old_metadata_ratio = fs_info->metadata_ratio; int ret; + sync_filesystem(sb); btrfs_remount_prepare(fs_info); ret = btrfs_parse_options(root, data); diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 3752b9f6d9e4..0d7daf714c4b 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -521,6 +521,7 @@ static int cifs_show_stats(struct seq_file *s, struct dentry *root) static int cifs_remount(struct super_block *sb, int *flags, char *data) { + sync_filesystem(sb); *flags |= MS_NODIRATIME; return 0; } diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index bfbf4700d160..b70aa7c91394 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -447,7 +447,7 @@ wait_for_response(struct TCP_Server_Info *server, struct mid_q_entry *midQ) { int error; - error = wait_event_freezekillable(server->response_q, + error = wait_event_freezekillable_unsafe(server->response_q, midQ->mid_state != MID_REQUEST_SUBMITTED); if (error < 0) return -ERESTARTSYS; diff --git a/fs/coda/dir.c b/fs/coda/dir.c index b7d3a05c062c..fc66861b3598 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -391,8 +391,7 @@ static int coda_readdir(struct file *coda_file, void *buf, filldir_t filldir) if (!host_file->f_op) return -ENOTDIR; - if (host_file->f_op->readdir) - { + if (host_file->f_op->readdir) { /* potemkin case: we were handed a directory inode. * We can't use vfs_readdir because we have to keep the file * position in sync between the coda_file and the host_file. @@ -410,8 +409,20 @@ static int coda_readdir(struct file *coda_file, void *buf, filldir_t filldir) coda_file->f_pos = host_file->f_pos; mutex_unlock(&host_inode->i_mutex); - } - else /* Venus: we must read Venus dirents from a file */ + } else if (host_file->f_op->iterate) { + struct inode *host_inode = file_inode(host_file); + struct dir_context *ctx = buf; + + mutex_lock(&host_inode->i_mutex); + ret = -ENOENT; + if (!IS_DEADDIR(host_inode)) { + ret = host_file->f_op->iterate(host_file, ctx); + file_accessed(host_file); + } + mutex_unlock(&host_inode->i_mutex); + + coda_file->f_pos = ctx->pos; + } else /* Venus: we must read Venus dirents from a file */ ret = coda_venus_readdir(coda_file, buf, filldir); return ret; diff --git a/fs/coda/inode.c b/fs/coda/inode.c index 4dcc0d81a7aa..0aa4c4d75ec6 100644 --- a/fs/coda/inode.c +++ b/fs/coda/inode.c @@ -96,6 +96,7 @@ void coda_destroy_inodecache(void) static int coda_remount(struct super_block *sb, int *flags, char *data) { + sync_filesystem(sb); *flags |= MS_NOATIME; return 0; } diff --git a/fs/compat.c b/fs/compat.c index fc3b55dce184..6af20de2c1a3 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -832,6 +832,7 @@ struct compat_old_linux_dirent { }; struct compat_readdir_callback { + struct dir_context ctx; struct compat_old_linux_dirent __user *dirent; int result; }; @@ -873,15 +874,15 @@ asmlinkage long compat_sys_old_readdir(unsigned int fd, { int error; struct fd f = fdget(fd); - struct compat_readdir_callback buf; + struct compat_readdir_callback buf = { + .ctx.actor = compat_fillonedir, + .dirent = dirent + }; if (!f.file) return -EBADF; - buf.result = 0; - buf.dirent = dirent; - - error = vfs_readdir(f.file, compat_fillonedir, &buf); + error = iterate_dir(f.file, &buf.ctx); if (buf.result) error = buf.result; @@ -897,6 +898,7 @@ struct compat_linux_dirent { }; struct compat_getdents_callback { + struct dir_context ctx; struct compat_linux_dirent __user *current_dir; struct compat_linux_dirent __user *previous; int count; @@ -951,7 +953,11 @@ asmlinkage long compat_sys_getdents(unsigned int fd, { struct fd f; struct compat_linux_dirent __user * lastdirent; - struct compat_getdents_callback buf; + struct compat_getdents_callback buf = { + .ctx.actor = compat_filldir, + .current_dir = dirent, + .count = count + }; int error; if (!access_ok(VERIFY_WRITE, dirent, count)) @@ -961,17 +967,12 @@ asmlinkage long compat_sys_getdents(unsigned int fd, if (!f.file) return -EBADF; - buf.current_dir = dirent; - buf.previous = NULL; - buf.count = count; - buf.error = 0; - - error = vfs_readdir(f.file, compat_filldir, &buf); + error = iterate_dir(f.file, &buf.ctx); if (error >= 0) error = buf.error; lastdirent = buf.previous; if (lastdirent) { - if (put_user(f.file->f_pos, &lastdirent->d_off)) + if (put_user(buf.ctx.pos, &lastdirent->d_off)) error = -EFAULT; else error = count - buf.count; @@ -983,6 +984,7 @@ asmlinkage long compat_sys_getdents(unsigned int fd, #ifndef __ARCH_OMIT_COMPAT_SYS_GETDENTS64 struct compat_getdents_callback64 { + struct dir_context ctx; struct linux_dirent64 __user *current_dir; struct linux_dirent64 __user *previous; int count; @@ -1036,7 +1038,11 @@ asmlinkage long compat_sys_getdents64(unsigned int fd, { struct fd f; struct linux_dirent64 __user * lastdirent; - struct compat_getdents_callback64 buf; + struct compat_getdents_callback64 buf = { + .ctx.actor = compat_filldir64, + .current_dir = dirent, + .count = count + }; int error; if (!access_ok(VERIFY_WRITE, dirent, count)) @@ -1046,17 +1052,12 @@ asmlinkage long compat_sys_getdents64(unsigned int fd, if (!f.file) return -EBADF; - buf.current_dir = dirent; - buf.previous = NULL; - buf.count = count; - buf.error = 0; - - error = vfs_readdir(f.file, compat_filldir64, &buf); + error = iterate_dir(f.file, &buf.ctx); if (error >= 0) error = buf.error; lastdirent = buf.previous; if (lastdirent) { - typeof(lastdirent->d_off) d_off = f.file->f_pos; + typeof(lastdirent->d_off) d_off = buf.ctx.pos; if (__put_user_unaligned(d_off, &lastdirent->d_off)) error = -EFAULT; else diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 35b1c7bd18b7..c0148585670d 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -227,6 +227,7 @@ static void cramfs_put_super(struct super_block *sb) static int cramfs_remount(struct super_block *sb, int *flags, char *data) { + sync_filesystem(sb); *flags |= MS_RDONLY; return 0; } diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 26d7fff8d78e..84378f0ffd6d 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -218,6 +218,7 @@ static int debugfs_remount(struct super_block *sb, int *flags, char *data) int err; struct debugfs_fs_info *fsi = sb->s_fs_info; + sync_filesystem(sb); err = debugfs_parse_options(data, &fsi->mount_opts); if (err) goto fail; diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index a726b9f29cb7..c71038079b47 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -313,6 +313,7 @@ static int devpts_remount(struct super_block *sb, int *flags, char *data) struct pts_fs_info *fsi = DEVPTS_SB(sb); struct pts_mount_opts *opts = &fsi->mount_opts; + sync_filesystem(sb); err = parse_mount_options(data, PARSE_REMOUNT, opts); /* diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index 9ff3664bb3ea..4912bf47226c 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -68,6 +68,7 @@ static ssize_t ecryptfs_read_update_atime(struct kiocb *iocb, } struct ecryptfs_getdents_callback { + struct dir_context ctx; void *dirent; struct dentry *dentry; filldir_t filldir; @@ -115,18 +116,19 @@ static int ecryptfs_readdir(struct file *file, void *dirent, filldir_t filldir) int rc; struct file *lower_file; struct inode *inode; - struct ecryptfs_getdents_callback buf; + struct ecryptfs_getdents_callback buf = { + .dirent = dirent, + .dentry = file->f_path.dentry, + .filldir = filldir, + .filldir_called = 0, + .entries_written = 0, + .ctx.actor = ecryptfs_filldir + }; lower_file = ecryptfs_file_to_lower(file); lower_file->f_pos = file->f_pos; inode = file_inode(file); - memset(&buf, 0, sizeof(buf)); - buf.dirent = dirent; - buf.dentry = file->f_path.dentry; - buf.filldir = filldir; - buf.filldir_called = 0; - buf.entries_written = 0; - rc = vfs_readdir(lower_file, ecryptfs_filldir, (void *)&buf); + rc = iterate_dir(lower_file, &buf.ctx); file->f_pos = lower_file->f_pos; if (rc < 0) goto out; diff --git a/fs/efs/super.c b/fs/efs/super.c index c6f57a74a559..4709692cd7a0 100644 --- a/fs/efs/super.c +++ b/fs/efs/super.c @@ -113,6 +113,7 @@ static void efs_put_super(struct super_block *s) static int efs_remount(struct super_block *sb, int *flags, char *data) { + sync_filesystem(sb); *flags |= MS_RDONLY; return 0; } diff --git a/fs/eventpoll.c b/fs/eventpoll.c index deecc7294a67..db10e00c971a 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -34,6 +34,7 @@ #include <linux/mutex.h> #include <linux/anon_inodes.h> #include <linux/device.h> +#include <linux/freezer.h> #include <asm/uaccess.h> #include <asm/io.h> #include <asm/mman.h> @@ -1602,7 +1603,8 @@ fetch_events: } spin_unlock_irqrestore(&ep->lock, flags); - if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) + if (!freezable_schedule_hrtimeout_range(to, slack, + HRTIMER_MODE_ABS)) timed_out = 1; spin_lock_irqsave(&ep->lock, flags); @@ -1817,8 +1819,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, goto error_tgt_fput; /* Check if EPOLLWAKEUP is allowed */ - if ((epds.events & EPOLLWAKEUP) && !capable(CAP_BLOCK_SUSPEND)) - epds.events &= ~EPOLLWAKEUP; + ep_take_care_of_epollwakeup(&epds); /* * We have to check that the file structure underneath the file descriptor diff --git a/fs/exec.c b/fs/exec.c index dd6aa61c8548..cb7f31c71c6b 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1220,7 +1220,7 @@ EXPORT_SYMBOL(install_exec_creds); /* * determine how safe it is to execute the proposed program * - the caller must hold ->cred_guard_mutex to protect against - * PTRACE_ATTACH + * PTRACE_ATTACH or seccomp thread-sync */ static int check_unsafe_exec(struct linux_binprm *bprm) { @@ -1239,7 +1239,7 @@ static int check_unsafe_exec(struct linux_binprm *bprm) * This isn't strictly necessary, but it makes it harder for LSMs to * mess up. */ - if (current->no_new_privs) + if (task_no_new_privs(current)) bprm->unsafe |= LSM_UNSAFE_NO_NEW_PRIVS; n_fs = 1; @@ -1286,7 +1286,7 @@ int prepare_binprm(struct linux_binprm *bprm) bprm->cred->egid = current_egid(); if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) && - !current->no_new_privs && + !task_no_new_privs(current) && kuid_has_mapping(bprm->cred->user_ns, inode->i_uid) && kgid_has_mapping(bprm->cred->user_ns, inode->i_gid)) { /* Set-uid? */ diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index b4eec4c9a790..dc4784b52d92 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -212,6 +212,7 @@ reconnect_path(struct vfsmount *mnt, struct dentry *target_dir, char *nbuf) } struct getdents_callback { + struct dir_context ctx; char *name; /* name that was found. It already points to a buffer NAME_MAX+1 is size */ unsigned long ino; /* the inum we are looking for */ @@ -254,7 +255,11 @@ static int get_name(const struct path *path, char *name, struct dentry *child) struct inode *dir = path->dentry->d_inode; int error; struct file *file; - struct getdents_callback buffer; + struct getdents_callback buffer = { + .ctx.actor = filldir_one, + .name = name, + .ino = child->d_inode->i_ino + }; error = -ENOTDIR; if (!dir || !S_ISDIR(dir->i_mode)) @@ -271,17 +276,14 @@ static int get_name(const struct path *path, char *name, struct dentry *child) goto out; error = -EINVAL; - if (!file->f_op->readdir) + if (!file->f_op->readdir && !file->f_op->iterate) goto out_close; - buffer.name = name; - buffer.ino = child->d_inode->i_ino; - buffer.found = 0; buffer.sequence = 0; while (1) { int old_seq = buffer.sequence; - error = vfs_readdir(file, filldir_one, &buffer); + error = iterate_dir(file, &buffer.ctx); if (buffer.found) { error = 0; break; diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 20d6697bd638..d260115c0350 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -1254,6 +1254,7 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data) unsigned long old_sb_flags; int err; + sync_filesystem(sb); spin_lock(&sbi->s_lock); /* Store the old options */ diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 882d4bdfd428..b1e30be1945b 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -2588,6 +2588,8 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data) int i; #endif + sync_filesystem(sb); + /* Store the original options */ old_sb_flags = sb->s_flags; old_opts.s_mount_opt = sbi->s_mount_opt; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 2a71466b0115..e5a77bb30ba3 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2063,7 +2063,8 @@ extern int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t i, struct ext4_group_desc *desc); extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, ext4_fsblk_t block, unsigned long count); -extern int ext4_trim_fs(struct super_block *, struct fstrim_range *); +extern int ext4_trim_fs(struct super_block *, struct fstrim_range *, + unsigned long blkdev_flags); /* inode.c */ struct buffer_head *ext4_getblk(handle_t *, struct inode *, diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index d4fd81c44f55..8855db670425 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -605,11 +605,13 @@ resizefs_out: return err; } + case FIDTRIM: case FITRIM: { struct request_queue *q = bdev_get_queue(sb->s_bdev); struct fstrim_range range; int ret = 0; + int flags = cmd == FIDTRIM ? BLKDEV_DISCARD_SECURE : 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -617,13 +619,15 @@ resizefs_out: if (!blk_queue_discard(q)) return -EOPNOTSUPP; + if ((flags & BLKDEV_DISCARD_SECURE) && !blk_queue_secdiscard(q)) + return -EOPNOTSUPP; if (copy_from_user(&range, (struct fstrim_range __user *)arg, sizeof(range))) return -EFAULT; range.minlen = max((unsigned int)range.minlen, q->limits.discard_granularity); - ret = ext4_trim_fs(sb, &range); + ret = ext4_trim_fs(sb, &range, flags); if (ret < 0) return ret; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index df5050f9080b..aed1a67ab3a2 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2707,7 +2707,8 @@ int ext4_mb_release(struct super_block *sb) } static inline int ext4_issue_discard(struct super_block *sb, - ext4_group_t block_group, ext4_grpblk_t cluster, int count) + ext4_group_t block_group, ext4_grpblk_t cluster, int count, + unsigned long flags) { ext4_fsblk_t discard_block; @@ -2716,7 +2717,7 @@ static inline int ext4_issue_discard(struct super_block *sb, count = EXT4_C2B(EXT4_SB(sb), count); trace_ext4_discard_blocks(sb, (unsigned long long) discard_block, count); - return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0); + return sb_issue_discard(sb, discard_block, count, GFP_NOFS, flags); } /* @@ -2738,7 +2739,7 @@ static void ext4_free_data_callback(struct super_block *sb, if (test_opt(sb, DISCARD)) { err = ext4_issue_discard(sb, entry->efd_group, entry->efd_start_cluster, - entry->efd_count); + entry->efd_count, 0); if (err && err != -EOPNOTSUPP) ext4_msg(sb, KERN_WARNING, "discard request in" " group:%d block:%d count:%d failed" @@ -4790,7 +4791,8 @@ do_more: * them with group lock_held */ if (test_opt(sb, DISCARD)) { - err = ext4_issue_discard(sb, block_group, bit, count); + err = ext4_issue_discard(sb, block_group, bit, count, + 0); if (err && err != -EOPNOTSUPP) ext4_msg(sb, KERN_WARNING, "discard request in" " group:%d block:%d count:%lu failed" @@ -4997,13 +4999,15 @@ error_return: * @count: number of blocks to TRIM * @group: alloc. group we are working with * @e4b: ext4 buddy for the group + * @blkdev_flags: flags for the block device * * Trim "count" blocks starting at "start" in the "group". To assure that no * one will allocate those blocks, mark it as used in buddy bitmap. This must * be called with under the group lock. */ static int ext4_trim_extent(struct super_block *sb, int start, int count, - ext4_group_t group, struct ext4_buddy *e4b) + ext4_group_t group, struct ext4_buddy *e4b, + unsigned long blkdev_flags) { struct ext4_free_extent ex; int ret = 0; @@ -5022,7 +5026,7 @@ static int ext4_trim_extent(struct super_block *sb, int start, int count, */ mb_mark_used(e4b, &ex); ext4_unlock_group(sb, group); - ret = ext4_issue_discard(sb, group, start, count); + ret = ext4_issue_discard(sb, group, start, count, blkdev_flags); ext4_lock_group(sb, group); mb_free_blocks(NULL, e4b, start, ex.fe_len); return ret; @@ -5035,6 +5039,7 @@ static int ext4_trim_extent(struct super_block *sb, int start, int count, * @start: first group block to examine * @max: last group block to examine * @minblocks: minimum extent block count + * @blkdev_flags: flags for the block device * * ext4_trim_all_free walks through group's buddy bitmap searching for free * extents. When the free block is found, ext4_trim_extent is called to TRIM @@ -5049,7 +5054,7 @@ static int ext4_trim_extent(struct super_block *sb, int start, int count, static ext4_grpblk_t ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t max, - ext4_grpblk_t minblocks) + ext4_grpblk_t minblocks, unsigned long blkdev_flags) { void *bitmap; ext4_grpblk_t next, count = 0, free_count = 0; @@ -5082,7 +5087,8 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, if ((next - start) >= minblocks) { ret = ext4_trim_extent(sb, start, - next - start, group, &e4b); + next - start, group, &e4b, + blkdev_flags); if (ret && ret != -EOPNOTSUPP) break; ret = 0; @@ -5124,6 +5130,7 @@ out: * ext4_trim_fs() -- trim ioctl handle function * @sb: superblock for filesystem * @range: fstrim_range structure + * @blkdev_flags: flags for the block device * * start: First Byte to trim * len: number of Bytes to trim from start @@ -5132,7 +5139,8 @@ out: * start to start+len. For each such a group ext4_trim_all_free function * is invoked to trim all free space. */ -int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) +int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range, + unsigned long blkdev_flags) { struct ext4_group_info *grp; ext4_group_t group, first_group, last_group; @@ -5188,7 +5196,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) if (grp->bb_free >= minlen) { cnt = ext4_trim_all_free(sb, group, first_cluster, - end, minlen); + end, minlen, blkdev_flags); if (cnt < 0) { ret = cnt; break; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 21a0b43a7d31..913a6b279220 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4622,6 +4622,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) #endif char *orig_data = kstrdup(data, GFP_KERNEL); + sync_filesystem(sb); + /* Store the original options */ old_sb_flags = sb->s_flags; old_opts.s_mount_opt = sbi->s_mount_opt; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 8555f7df82c7..03ab8b830940 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -239,7 +239,6 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) if (test_opt(sbi, DISABLE_EXT_IDENTIFY)) seq_puts(seq, ",disable_ext_identify"); - seq_printf(seq, ",active_logs=%u", sbi->active_logs); return 0; } diff --git a/fs/fat/dir.c b/fs/fat/dir.c index 7a6f02caf286..4b775e606fc8 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -776,6 +776,13 @@ static int fat_ioctl_readdir(struct inode *inode, struct file *filp, return ret; } +static int fat_ioctl_volume_id(struct inode *dir) +{ + struct super_block *sb = dir->i_sb; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + return sbi->vol_id; +} + static long fat_dir_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { @@ -792,6 +799,8 @@ static long fat_dir_ioctl(struct file *filp, unsigned int cmd, short_only = 0; both = 1; break; + case VFAT_IOCTL_GET_VOLUME_ID: + return fat_ioctl_volume_id(inode); default: return fat_generic_ioctl(filp, cmd, arg); } @@ -832,6 +841,8 @@ static long fat_compat_dir_ioctl(struct file *filp, unsigned cmd, short_only = 0; both = 1; break; + case VFAT_IOCTL_GET_VOLUME_ID: + return fat_ioctl_volume_id(inode); default: return fat_generic_ioctl(filp, cmd, (unsigned long)arg); } diff --git a/fs/fat/fat.h b/fs/fat/fat.h index 21664fcf3616..8180ecef59fc 100644 --- a/fs/fat/fat.h +++ b/fs/fat/fat.h @@ -86,6 +86,7 @@ struct msdos_sb_info { const void *dir_ops; /* Opaque; default directory operations */ int dir_per_block; /* dir entries per block */ int dir_per_block_bits; /* log2(dir_per_block) */ + unsigned long vol_id; /* volume ID */ int fatent_shift; struct fatent_operations *fatent_ops; diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 5d4513cb1b3c..ebdc6656c067 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -632,6 +632,8 @@ static int fat_remount(struct super_block *sb, int *flags, char *data) struct msdos_sb_info *sbi = MSDOS_SB(sb); *flags |= MS_NODIRATIME | (sbi->options.isvfat ? 0 : MS_NOATIME); + sync_filesystem(sb); + /* make sure we update state on remount. */ new_rdonly = *flags & MS_RDONLY; if (new_rdonly != (sb->s_flags & MS_RDONLY)) { @@ -1252,6 +1254,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, struct inode *fsinfo_inode = NULL; struct buffer_head *bh; struct fat_boot_sector *b; + struct fat_boot_bsx *bsx; struct msdos_sb_info *sbi; u16 logical_sector_size; u32 total_sectors, total_clusters, fat_clusters, rootdir_sectors; @@ -1398,6 +1401,8 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, goto out_fail; } + bsx = (struct fat_boot_bsx *)(bh->b_data + FAT32_BSX_OFFSET); + fsinfo = (struct fat_boot_fsinfo *)fsinfo_bh->b_data; if (!IS_FSINFO(fsinfo)) { fat_msg(sb, KERN_WARNING, "Invalid FSINFO signature: " @@ -1413,8 +1418,14 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, } brelse(fsinfo_bh); + } else { + bsx = (struct fat_boot_bsx *)(bh->b_data + FAT16_BSX_OFFSET); } + /* interpret volume ID as a little endian 32 bit integer */ + sbi->vol_id = (((u32)bsx->vol_id[0]) | ((u32)bsx->vol_id[1] << 8) | + ((u32)bsx->vol_id[2] << 16) | ((u32)bsx->vol_id[3] << 24)); + sbi->dir_per_block = sb->s_blocksize / sizeof(struct msdos_dir_entry); sbi->dir_per_block_bits = ffs(sbi->dir_per_block) - 1; diff --git a/fs/freevxfs/vxfs_super.c b/fs/freevxfs/vxfs_super.c index e37eb274e492..7ca8c75d50d3 100644 --- a/fs/freevxfs/vxfs_super.c +++ b/fs/freevxfs/vxfs_super.c @@ -124,6 +124,7 @@ vxfs_statfs(struct dentry *dentry, struct kstatfs *bufp) static int vxfs_remount(struct super_block *sb, int *flags, char *data) { + sync_filesystem(sb); *flags |= MS_RDONLY; return 0; } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index b44306378193..62d426d1d5e3 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1170,7 +1170,7 @@ void __mark_inode_dirty(struct inode *inode, int flags) if ((inode->i_state & flags) == flags) return; - if (unlikely(block_dump)) + if (unlikely(block_dump > 1)) block_dump___mark_inode_dirty(inode); spin_lock(&inode->i_lock); diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index b535008b6c4c..f4e875a29e7a 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -20,6 +20,7 @@ #include <linux/swap.h> #include <linux/splice.h> #include <linux/aio.h> +#include <linux/freezer.h> MODULE_ALIAS_MISCDEV(FUSE_MINOR); MODULE_ALIAS("devname:fuse"); @@ -464,7 +465,10 @@ __acquires(fc->lock) * Wait it out. */ spin_unlock(&fc->lock); - wait_event(req->waitq, req->state == FUSE_REQ_FINISHED); + + while (req->state != FUSE_REQ_FINISHED) + wait_event_freezable(req->waitq, + req->state == FUSE_REQ_FINISHED); spin_lock(&fc->lock); if (!req->aborted) diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 39a986e1da9e..8aabbe2a3989 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -135,6 +135,7 @@ static void fuse_evict_inode(struct inode *inode) static int fuse_remount_fs(struct super_block *sb, int *flags, char *data) { + sync_filesystem(sb); if (*flags & MS_MANDLOCK) return -EINVAL; diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c index 9973df4ff565..7102c7a5af4d 100644 --- a/fs/gfs2/export.c +++ b/fs/gfs2/export.c @@ -88,7 +88,10 @@ static int gfs2_get_name(struct dentry *parent, char *name, struct inode *dir = parent->d_inode; struct inode *inode = child->d_inode; struct gfs2_inode *dip, *ip; - struct get_name_filldir gnfd; + struct get_name_filldir gnfd = { + .ctx.actor = get_name_filldir, + .name = name + }; struct gfs2_holder gh; u64 offset = 0; int error; @@ -106,7 +109,6 @@ static int gfs2_get_name(struct dentry *parent, char *name, *name = 0; gnfd.inum.no_addr = ip->i_no_addr; gnfd.inum.no_formal_ino = ip->i_no_formal_ino; - gnfd.name = name; error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &gh); if (error) diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index e5639dec66c4..db7fff5a29c1 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1142,6 +1142,8 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data) struct gfs2_tune *gt = &sdp->sd_tune; int error; + sync_filesystem(sb); + spin_lock(>->gt_spin); args.ar_commit = gt->gt_logd_secs; args.ar_quota_quantum = gt->gt_quota_quantum; diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 2d2039e754cd..eee7206c38d1 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -112,6 +112,7 @@ static int hfs_statfs(struct dentry *dentry, struct kstatfs *buf) static int hfs_remount(struct super_block *sb, int *flags, char *data) { + sync_filesystem(sb); *flags |= MS_NODIRATIME; if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) return 0; diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 4c4d142cf890..1b9414f701e6 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -323,6 +323,7 @@ static int hfsplus_statfs(struct dentry *dentry, struct kstatfs *buf) static int hfsplus_remount(struct super_block *sb, int *flags, char *data) { + sync_filesystem(sb); if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) return 0; if (!(*flags & MS_RDONLY)) { diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index 962e90c37aec..d37f6ff8e07f 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -395,6 +395,8 @@ static int hpfs_remount_fs(struct super_block *s, int *flags, char *data) struct hpfs_sb_info *sbi = hpfs_sb(s); char *new_opts = kstrdup(data, GFP_KERNEL); + sync_filesystem(s); + *flags |= MS_NOATIME; hpfs_lock(s); diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index 0defb1cc2a35..0918f0e2e266 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -243,6 +243,7 @@ static int jffs2_remount_fs(struct super_block *sb, int *flags, char *data) struct jffs2_sb_info *c = JFFS2_SB_INFO(sb); int err; + sync_filesystem(sb); err = jffs2_parse_options(c, data); if (err) return -EINVAL; diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 788e0a9c1fb0..b7486dafa1cd 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -413,6 +413,7 @@ static int jfs_remount(struct super_block *sb, int *flags, char *data) int flag = JFS_SBI(sb)->flag; int ret; + sync_filesystem(sb); if (!parse_options(data, sb, &newLVSize, &flag)) { return -EINVAL; } diff --git a/fs/minix/inode.c b/fs/minix/inode.c index df122496f328..a54d08865e59 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -123,6 +123,7 @@ static int minix_remount (struct super_block * sb, int * flags, char * data) struct minix_sb_info * sbi = minix_sb(sb); struct minix_super_block * ms; + sync_filesystem(sb); ms = sbi->s_ms; if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) return 0; diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index 26910c8154da..3f54348b926b 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -99,6 +99,7 @@ static void destroy_inodecache(void) static int ncp_remount(struct super_block *sb, int *flags, char* data) { + sync_filesystem(sb); *flags |= MS_NODIRATIME; return 0; } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index e9be01b2cc5a..e2bb3012d025 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -79,7 +79,7 @@ int nfs_wait_bit_killable(void *word) { if (fatal_signal_pending(current)) return -ERESTARTSYS; - freezable_schedule(); + freezable_schedule_unsafe(); return 0; } EXPORT_SYMBOL_GPL(nfs_wait_bit_killable); diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 43ea96ced28c..ce90eb4775c2 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -33,7 +33,7 @@ nfs3_rpc_wrapper(struct rpc_clnt *clnt, struct rpc_message *msg, int flags) res = rpc_call_sync(clnt, msg, flags); if (res != -EJUKEBOX) break; - freezable_schedule_timeout_killable(NFS_JUKEBOX_RETRY_TIME); + freezable_schedule_timeout_killable_unsafe(NFS_JUKEBOX_RETRY_TIME); res = -ERESTARTSYS; } while (!fatal_signal_pending(current)); return res; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 20ebcfa3c92e..86390c3a95db 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -268,7 +268,7 @@ static int nfs4_delay(struct rpc_clnt *clnt, long *timeout) *timeout = NFS4_POLL_RETRY_MIN; if (*timeout > NFS4_POLL_RETRY_MAX) *timeout = NFS4_POLL_RETRY_MAX; - freezable_schedule_timeout_killable(*timeout); + freezable_schedule_timeout_killable_unsafe(*timeout); if (fatal_signal_pending(current)) res = -ERESTARTSYS; *timeout <<= 1; @@ -4558,7 +4558,7 @@ int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4 static unsigned long nfs4_set_lock_task_retry(unsigned long timeout) { - freezable_schedule_timeout_killable(timeout); + freezable_schedule_timeout_killable_unsafe(timeout); timeout <<= 1; if (timeout > NFS4_LOCK_MAXTIMEOUT) return NFS4_LOCK_MAXTIMEOUT; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 2d7525fbcf25..d85c1b819145 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2133,6 +2133,8 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data) struct nfs4_mount_data *options4 = (struct nfs4_mount_data *)raw_data; u32 nfsvers = nfss->nfs_client->rpc_ops->version; + sync_filesystem(sb); + /* * Userspace mount programs that send binary options generally send * them populated with default values. We have no way to know which diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 4e9a21db867a..105a3b080d12 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -240,11 +240,16 @@ struct name_list { struct list_head list; }; +struct nfs4_dir_ctx { + struct dir_context ctx; + struct list_head names; +}; + static int nfsd4_build_namelist(void *arg, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type) { - struct list_head *names = arg; + struct nfs4_dir_ctx *ctx = arg; struct name_list *entry; if (namlen != HEXDIR_LEN - 1) @@ -254,7 +259,7 @@ nfsd4_build_namelist(void *arg, const char *name, int namlen, return -ENOMEM; memcpy(entry->name, name, HEXDIR_LEN - 1); entry->name[HEXDIR_LEN - 1] = '\0'; - list_add(&entry->list, names); + list_add(&entry->list, &ctx->names); return 0; } @@ -263,7 +268,10 @@ nfsd4_list_rec_dir(recdir_func *f, struct nfsd_net *nn) { const struct cred *original_cred; struct dentry *dir = nn->rec_file->f_path.dentry; - LIST_HEAD(names); + struct nfs4_dir_ctx ctx = { + .ctx.actor = nfsd4_build_namelist, + .names = LIST_HEAD_INIT(ctx.names) + }; int status; status = nfs4_save_creds(&original_cred); @@ -276,11 +284,11 @@ nfsd4_list_rec_dir(recdir_func *f, struct nfsd_net *nn) return status; } - status = vfs_readdir(nn->rec_file, nfsd4_build_namelist, &names); + status = iterate_dir(nn->rec_file, &ctx.ctx); mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT); - while (!list_empty(&names)) { + while (!list_empty(&ctx.names)) { struct name_list *entry; - entry = list_entry(names.next, struct name_list, list); + entry = list_entry(ctx.names.next, struct name_list, list); if (!status) { struct dentry *dentry; dentry = lookup_one_len(entry->name, dir, HEXDIR_LEN-1); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 81325ba8660a..11224fa5ff25 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1950,6 +1950,7 @@ struct buffered_dirent { }; struct readdir_data { + struct dir_context ctx; char *dirent; size_t used; int full; @@ -1981,13 +1982,15 @@ static int nfsd_buffered_filldir(void *__buf, const char *name, int namlen, static __be32 nfsd_buffered_readdir(struct file *file, filldir_t func, struct readdir_cd *cdp, loff_t *offsetp) { - struct readdir_data buf; struct buffered_dirent *de; int host_err; int size; loff_t offset; + struct readdir_data buf = { + .ctx.actor = nfsd_buffered_filldir, + .dirent = (void *)__get_free_page(GFP_KERNEL) + }; - buf.dirent = (void *)__get_free_page(GFP_KERNEL); if (!buf.dirent) return nfserrno(-ENOMEM); @@ -2001,7 +2004,7 @@ static __be32 nfsd_buffered_readdir(struct file *file, filldir_t func, buf.used = 0; buf.full = 0; - host_err = vfs_readdir(file, nfsd_buffered_filldir, &buf); + host_err = iterate_dir(file, &buf.ctx); if (buf.full) host_err = 0; diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index c7d1f9f18b09..4b0a8d4a8345 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1114,6 +1114,7 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data) unsigned long old_mount_opt; int err; + sync_filesystem(sb); old_sb_flags = sb->s_flags; old_mount_opt = nilfs->ns_mount_opt; diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 82650d52d916..bd5610d48242 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -468,6 +468,8 @@ static int ntfs_remount(struct super_block *sb, int *flags, char *opt) ntfs_debug("Entering with remount options string: %s", opt); + sync_filesystem(sb); + #ifndef NTFS_RW /* For read-only compiled driver, enforce read-only flag. */ *flags |= MS_RDONLY; diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 01b85165552b..616bde667d8d 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -632,6 +632,8 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data) struct ocfs2_super *osb = OCFS2_SB(sb); u32 tmp; + sync_filesystem(sb); + if (!ocfs2_parse_options(sb, data, &parsed_options, 1) || !ocfs2_check_set_options(sb, &parsed_options)) { ret = -EINVAL; diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c index 75885ffde44e..f4026aba26f3 100644 --- a/fs/openpromfs/inode.c +++ b/fs/openpromfs/inode.c @@ -375,6 +375,7 @@ static struct inode *openprom_iget(struct super_block *sb, ino_t ino) static int openprom_remount(struct super_block *sb, int *flags, char *data) { + sync_filesystem(sb); *flags |= MS_NOATIME; return 0; } diff --git a/fs/proc/base.c b/fs/proc/base.c index 8fc784aef0b8..809d92a68a50 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2749,8 +2749,8 @@ static const struct pid_entry tgid_base_stuff[] = { REG("cgroup", S_IRUGO, proc_cgroup_operations), #endif INF("oom_score", S_IRUGO, proc_oom_score), - REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), - REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), + REG("oom_adj", S_IRUSR, proc_oom_adj_operations), + REG("oom_score_adj", S_IRUSR, proc_oom_score_adj_operations), #ifdef CONFIG_AUDITSYSCALL REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), REG("sessionid", S_IRUGO, proc_sessionid_operations), @@ -3106,8 +3106,8 @@ static const struct pid_entry tid_base_stuff[] = { REG("cgroup", S_IRUGO, proc_cgroup_operations), #endif INF("oom_score", S_IRUGO, proc_oom_score), - REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), - REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), + REG("oom_adj", S_IRUSR, proc_oom_adj_operations), + REG("oom_score_adj", S_IRUSR, proc_oom_score_adj_operations), #ifdef CONFIG_AUDITSYSCALL REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), REG("sessionid", S_IRUGO, proc_sessionid_operations), diff --git a/fs/proc/root.c b/fs/proc/root.c index 9459710c55ae..8ead812d9897 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -92,6 +92,8 @@ static int proc_parse_options(char *options, struct pid_namespace *pid) int proc_remount(struct super_block *sb, int *flags, char *data) { struct pid_namespace *pid = sb->s_fs_info; + + sync_filesystem(sb); return !proc_parse_options(data, pid); } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 9f285fb9bab3..0e2899492133 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -134,6 +134,56 @@ static void release_task_mempolicy(struct proc_maps_private *priv) } #endif +static void seq_print_vma_name(struct seq_file *m, struct vm_area_struct *vma) +{ + const char __user *name = vma_get_anon_name(vma); + struct mm_struct *mm = vma->vm_mm; + + unsigned long page_start_vaddr; + unsigned long page_offset; + unsigned long num_pages; + unsigned long max_len = NAME_MAX; + int i; + + page_start_vaddr = (unsigned long)name & PAGE_MASK; + page_offset = (unsigned long)name - page_start_vaddr; + num_pages = DIV_ROUND_UP(page_offset + max_len, PAGE_SIZE); + + seq_puts(m, "[anon:"); + + for (i = 0; i < num_pages; i++) { + int len; + int write_len; + const char *kaddr; + long pages_pinned; + struct page *page; + + pages_pinned = get_user_pages(current, mm, page_start_vaddr, + 1, 0, 0, &page, NULL); + if (pages_pinned < 1) { + seq_puts(m, "<fault>]"); + return; + } + + kaddr = (const char *)kmap(page); + len = min(max_len, PAGE_SIZE - page_offset); + write_len = strnlen(kaddr + page_offset, len); + seq_write(m, kaddr + page_offset, write_len); + kunmap(page); + put_page(page); + + /* if strnlen hit a null terminator then we're done */ + if (write_len != len) + break; + + max_len -= len; + page_offset = 0; + page_start_vaddr += PAGE_SIZE; + } + + seq_putc(m, ']'); +} + static void vma_stop(struct proc_maps_private *priv, struct vm_area_struct *vma) { if (vma && vma != priv->tail_vma) { @@ -335,6 +385,12 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) pad_len_spaces(m, len); seq_printf(m, "[stack:%d]", tid); } + goto done; + } + + if (vma_get_anon_name(vma)) { + pad_len_spaces(m, len); + seq_print_vma_name(m, vma); } } @@ -634,6 +690,12 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) show_smap_vma_flags(m, vma); + if (vma_get_anon_name(vma)) { + seq_puts(m, "Name: "); + seq_print_vma_name(m, vma); + seq_putc(m, '\n'); + } + if (m->count < m->size) /* vma is copied successfully */ m->version = (vma != get_gate_vma(task->mm)) ? vma->vm_start : 0; @@ -722,6 +784,7 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, #define CLEAR_REFS_ALL 1 #define CLEAR_REFS_ANON 2 #define CLEAR_REFS_MAPPED 3 +#define CLEAR_REFS_MM_HIWATER_RSS 5 static ssize_t clear_refs_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) @@ -741,7 +804,8 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, rv = kstrtoint(strstrip(buffer), 10, &type); if (rv < 0) return rv; - if (type < CLEAR_REFS_ALL || type > CLEAR_REFS_MAPPED) + if ((type < CLEAR_REFS_ALL || type > CLEAR_REFS_MAPPED) && + type != CLEAR_REFS_MM_HIWATER_RSS) return -EINVAL; task = get_proc_task(file_inode(file)); if (!task) @@ -752,6 +816,18 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, .pmd_entry = clear_refs_pte_range, .mm = mm, }; + + if (type == CLEAR_REFS_MM_HIWATER_RSS) { + /* + * Writing 5 to /proc/pid/clear_refs resets the peak + * resident set size to this mm's current rss value. + */ + down_write(&mm->mmap_sem); + reset_mm_hiwater_rss(mm); + up_write(&mm->mmap_sem); + goto out_mm; + } + down_read(&mm->mmap_sem); for (vma = mm->mmap; vma; vma = vma->vm_next) { clear_refs_walk.private = vma; @@ -775,6 +851,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, } flush_tlb_mm(mm); up_read(&mm->mmap_sem); +out_mm: mmput(mm); } put_task_struct(task); diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig index ca71db69da07..da12fd4e3d47 100644 --- a/fs/pstore/Kconfig +++ b/fs/pstore/Kconfig @@ -19,6 +19,16 @@ config PSTORE_CONSOLE When the option is enabled, pstore will log all kernel messages, even if no oops or panic happened. +config PSTORE_PMSG + bool "Log user space messages" + depends on PSTORE + help + When the option is enabled, pstore will export a character + interface /dev/pmsg0 to log user space messages. On reboot + data can be retrieved from /sys/fs/pstore/pmsg-ramoops-[ID]. + + If unsure, say N. + config PSTORE_FTRACE bool "Persistent function tracer" depends on PSTORE diff --git a/fs/pstore/Makefile b/fs/pstore/Makefile index 4c9095c2781e..e647d8e81712 100644 --- a/fs/pstore/Makefile +++ b/fs/pstore/Makefile @@ -7,5 +7,7 @@ obj-y += pstore.o pstore-objs += inode.o platform.o obj-$(CONFIG_PSTORE_FTRACE) += ftrace.o +obj-$(CONFIG_PSTORE_PMSG) += pmsg.o + ramoops-objs += ram.o ram_core.o obj-$(CONFIG_PSTORE_RAM) += ramoops.o diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index 66c8c2fe86b7..a12e0829d8ac 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -249,6 +249,7 @@ static void parse_options(char *options) static int pstore_remount(struct super_block *sb, int *flags, char *data) { + sync_filesystem(sb); parse_options(data); return 0; @@ -315,22 +316,27 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count, switch (type) { case PSTORE_TYPE_DMESG: - sprintf(name, "dmesg-%s-%lld", psname, id); + scnprintf(name, sizeof(name), "dmesg-%s-%lld", + psname, id); break; case PSTORE_TYPE_CONSOLE: - sprintf(name, "console-%s-%lld", psname, id); + scnprintf(name, sizeof(name), "console-%s", psname); break; case PSTORE_TYPE_FTRACE: - sprintf(name, "ftrace-%s-%lld", psname, id); + scnprintf(name, sizeof(name), "ftrace-%s", psname); break; case PSTORE_TYPE_MCE: - sprintf(name, "mce-%s-%lld", psname, id); + scnprintf(name, sizeof(name), "mce-%s-%lld", psname, id); + break; + case PSTORE_TYPE_PMSG: + scnprintf(name, sizeof(name), "pmsg-%s-%lld", psname, id); break; case PSTORE_TYPE_UNKNOWN: - sprintf(name, "unknown-%s-%lld", psname, id); + scnprintf(name, sizeof(name), "unknown-%s-%lld", psname, id); break; default: - sprintf(name, "type%d-%s-%lld", type, psname, id); + scnprintf(name, sizeof(name), "type%d-%s-%lld", + type, psname, id); break; } diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h index 937d820f273c..fd8d248c285c 100644 --- a/fs/pstore/internal.h +++ b/fs/pstore/internal.h @@ -45,6 +45,12 @@ extern void pstore_register_ftrace(void); static inline void pstore_register_ftrace(void) {} #endif +#ifdef CONFIG_PSTORE_PMSG +extern void pstore_register_pmsg(void); +#else +static inline void pstore_register_pmsg(void) {} +#endif + extern struct pstore_info *psinfo; extern void pstore_set_kmsg_bytes(int); diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 86d1038b5a12..4f11f2382e24 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -267,6 +267,7 @@ int pstore_register(struct pstore_info *psi) kmsg_dump_register(&pstore_dumper); pstore_register_console(); pstore_register_ftrace(); + pstore_register_pmsg(); if (pstore_update_ms >= 0) { pstore_timer.expires = jiffies + diff --git a/fs/pstore/pmsg.c b/fs/pstore/pmsg.c new file mode 100644 index 000000000000..db47810a92d8 --- /dev/null +++ b/fs/pstore/pmsg.c @@ -0,0 +1,114 @@ +/* + * Copyright 2014 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/cdev.h> +#include <linux/device.h> +#include <linux/fs.h> +#include <linux/uaccess.h> +#include <linux/vmalloc.h> +#include "internal.h" + +static DEFINE_MUTEX(pmsg_lock); +#define PMSG_MAX_BOUNCE_BUFFER_SIZE (2*PAGE_SIZE) + +static ssize_t write_pmsg(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + size_t i, buffer_size; + char *buffer; + + if (!count) + return 0; + + if (!access_ok(VERIFY_READ, buf, count)) + return -EFAULT; + + buffer_size = count; + if (buffer_size > PMSG_MAX_BOUNCE_BUFFER_SIZE) + buffer_size = PMSG_MAX_BOUNCE_BUFFER_SIZE; + buffer = vmalloc(buffer_size); + + mutex_lock(&pmsg_lock); + for (i = 0; i < count; ) { + size_t c = min(count - i, buffer_size); + u64 id; + long ret; + + ret = __copy_from_user(buffer, buf + i, c); + if (unlikely(ret != 0)) { + mutex_unlock(&pmsg_lock); + vfree(buffer); + return -EFAULT; + } + psinfo->write_buf(PSTORE_TYPE_PMSG, 0, &id, 0, buffer, c, + psinfo); + + i += c; + } + + mutex_unlock(&pmsg_lock); + vfree(buffer); + return count; +} + +static const struct file_operations pmsg_fops = { + .owner = THIS_MODULE, + .llseek = noop_llseek, + .write = write_pmsg, +}; + +static struct class *pmsg_class; +static int pmsg_major; +#define PMSG_NAME "pmsg" +#undef pr_fmt +#define pr_fmt(fmt) PMSG_NAME ": " fmt + +static char *pmsg_devnode(struct device *dev, umode_t *mode) +{ + if (mode) + *mode = 0220; + return NULL; +} + +void pstore_register_pmsg(void) +{ + struct device *pmsg_device; + + pmsg_major = register_chrdev(0, PMSG_NAME, &pmsg_fops); + if (pmsg_major < 0) { + pr_err("register_chrdev failed\n"); + goto err; + } + + pmsg_class = class_create(THIS_MODULE, PMSG_NAME); + if (IS_ERR(pmsg_class)) { + pr_err("device class file already in use\n"); + goto err_class; + } + pmsg_class->devnode = pmsg_devnode; + + pmsg_device = device_create(pmsg_class, NULL, MKDEV(pmsg_major, 0), + NULL, "%s%d", PMSG_NAME, 0); + if (IS_ERR(pmsg_device)) { + pr_err("failed to create device\n"); + goto err_device; + } + return; + +err_device: + class_destroy(pmsg_class); +err_class: + unregister_chrdev(pmsg_major, PMSG_NAME); +err: + return; +} diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index d3d37142bd93..f721e47db8ad 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -51,6 +51,10 @@ static ulong ramoops_ftrace_size = MIN_MEM_SIZE; module_param_named(ftrace_size, ramoops_ftrace_size, ulong, 0400); MODULE_PARM_DESC(ftrace_size, "size of ftrace log"); +static ulong ramoops_pmsg_size = MIN_MEM_SIZE; +module_param_named(pmsg_size, ramoops_pmsg_size, ulong, 0400); +MODULE_PARM_DESC(pmsg_size, "size of user space message log"); + static ulong mem_address; module_param(mem_address, ulong, 0400); MODULE_PARM_DESC(mem_address, @@ -82,12 +86,14 @@ struct ramoops_context { struct persistent_ram_zone **przs; struct persistent_ram_zone *cprz; struct persistent_ram_zone *fprz; + struct persistent_ram_zone *mprz; phys_addr_t phys_addr; unsigned long size; unsigned int memtype; size_t record_size; size_t console_size; size_t ftrace_size; + size_t pmsg_size; int dump_oops; struct persistent_ram_ecc_info ecc_info; unsigned int max_dump_cnt; @@ -96,6 +102,7 @@ struct ramoops_context { unsigned int dump_read_cnt; unsigned int console_read_cnt; unsigned int ftrace_read_cnt; + unsigned int pmsg_read_cnt; struct pstore_info pstore; }; @@ -109,6 +116,7 @@ static int ramoops_pstore_open(struct pstore_info *psi) cxt->dump_read_cnt = 0; cxt->console_read_cnt = 0; cxt->ftrace_read_cnt = 0; + cxt->pmsg_read_cnt = 0; return 0; } @@ -141,6 +149,12 @@ ramoops_get_next_prz(struct persistent_ram_zone *przs[], uint *c, uint max, return prz; } +static bool prz_ok(struct persistent_ram_zone *prz) +{ + return !!prz && !!(persistent_ram_old_size(prz) + + persistent_ram_ecc_string(prz, NULL, 0)); +} + static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, int *count, struct timespec *time, char **buf, struct pstore_info *psi) @@ -153,13 +167,16 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, prz = ramoops_get_next_prz(cxt->przs, &cxt->dump_read_cnt, cxt->max_dump_cnt, id, type, PSTORE_TYPE_DMESG, 1); - if (!prz) + if (!prz_ok(prz)) prz = ramoops_get_next_prz(&cxt->cprz, &cxt->console_read_cnt, 1, id, type, PSTORE_TYPE_CONSOLE, 0); - if (!prz) + if (!prz_ok(prz)) prz = ramoops_get_next_prz(&cxt->fprz, &cxt->ftrace_read_cnt, 1, id, type, PSTORE_TYPE_FTRACE, 0); - if (!prz) + if (!prz_ok(prz)) + prz = ramoops_get_next_prz(&cxt->mprz, &cxt->pmsg_read_cnt, + 1, id, type, PSTORE_TYPE_PMSG, 0); + if (!prz_ok(prz)) return 0; /* TODO(kees): Bogus time for the moment. */ @@ -222,6 +239,11 @@ static int notrace ramoops_pstore_write_buf(enum pstore_type_id type, return -ENOMEM; persistent_ram_write(cxt->fprz, buf, size); return 0; + } else if (type == PSTORE_TYPE_PMSG) { + if (!cxt->mprz) + return -ENOMEM; + persistent_ram_write(cxt->mprz, buf, size); + return 0; } if (type != PSTORE_TYPE_DMESG) @@ -279,6 +301,9 @@ static int ramoops_pstore_erase(enum pstore_type_id type, u64 id, int count, case PSTORE_TYPE_FTRACE: prz = cxt->fprz; break; + case PSTORE_TYPE_PMSG: + prz = cxt->mprz; + break; default: return -EINVAL; } @@ -388,6 +413,12 @@ static int ramoops_init_prz(struct device *dev, struct ramoops_context *cxt, return 0; } +void notrace ramoops_console_write_buf(const char *buf, size_t size) +{ + struct ramoops_context *cxt = &oops_cxt; + persistent_ram_write(cxt->cprz, buf, size); +} + static int ramoops_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -404,7 +435,7 @@ static int ramoops_probe(struct platform_device *pdev) goto fail_out; if (!pdata->mem_size || (!pdata->record_size && !pdata->console_size && - !pdata->ftrace_size)) { + !pdata->ftrace_size && !pdata->pmsg_size)) { pr_err("The memory size and the record/console size must be " "non-zero\n"); goto fail_out; @@ -418,6 +449,8 @@ static int ramoops_probe(struct platform_device *pdev) pdata->console_size = rounddown_pow_of_two(pdata->console_size); if (!is_power_of_2(pdata->ftrace_size)) pdata->ftrace_size = rounddown_pow_of_two(pdata->ftrace_size); + if (pdata->pmsg_size && !is_power_of_2(pdata->pmsg_size)) + pdata->pmsg_size = rounddown_pow_of_two(pdata->pmsg_size); cxt->size = pdata->mem_size; cxt->phys_addr = pdata->mem_address; @@ -425,12 +458,14 @@ static int ramoops_probe(struct platform_device *pdev) cxt->record_size = pdata->record_size; cxt->console_size = pdata->console_size; cxt->ftrace_size = pdata->ftrace_size; + cxt->pmsg_size = pdata->pmsg_size; cxt->dump_oops = pdata->dump_oops; cxt->ecc_info = pdata->ecc_info; paddr = cxt->phys_addr; - dump_mem_sz = cxt->size - cxt->console_size - cxt->ftrace_size; + dump_mem_sz = cxt->size - cxt->console_size - cxt->ftrace_size + - cxt->pmsg_size; err = ramoops_init_przs(dev, cxt, &paddr, dump_mem_sz); if (err) goto fail_out; @@ -445,13 +480,9 @@ static int ramoops_probe(struct platform_device *pdev) if (err) goto fail_init_fprz; - if (!cxt->przs && !cxt->cprz && !cxt->fprz) { - pr_err("memory size too small, minimum is %zu\n", - cxt->console_size + cxt->record_size + - cxt->ftrace_size); - err = -EINVAL; - goto fail_cnt; - } + err = ramoops_init_prz(dev, cxt, &cxt->mprz, &paddr, cxt->pmsg_size, 0); + if (err) + goto fail_init_mprz; cxt->pstore.data = cxt; /* @@ -497,7 +528,8 @@ fail_buf: fail_clear: cxt->pstore.bufsize = 0; cxt->max_dump_cnt = 0; -fail_cnt: + kfree(cxt->mprz); +fail_init_mprz: kfree(cxt->fprz); fail_init_fprz: kfree(cxt->cprz); @@ -556,6 +588,7 @@ static void ramoops_register_dummy(void) dummy_data->record_size = record_size; dummy_data->console_size = ramoops_console_size; dummy_data->ftrace_size = ramoops_ftrace_size; + dummy_data->pmsg_size = ramoops_pmsg_size; dummy_data->dump_oops = dump_oops; /* * For backwards compatibility ramoops.ecc=1 means 16 bytes ECC diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index 2e8caa62da78..3410e9f657ca 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -46,6 +46,7 @@ static int qnx4_remount(struct super_block *sb, int *flags, char *data) { struct qnx4_sb_info *qs; + sync_filesystem(sb); qs = qnx4_sb(sb); qs->Version = QNX4_VERSION; *flags |= MS_RDONLY; diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c index 8d941edfefa1..65cdaab3ed49 100644 --- a/fs/qnx6/inode.c +++ b/fs/qnx6/inode.c @@ -55,6 +55,7 @@ static int qnx6_show_options(struct seq_file *seq, struct dentry *root) static int qnx6_remount(struct super_block *sb, int *flags, char *data) { + sync_filesystem(sb); *flags |= MS_RDONLY; return 0; } diff --git a/fs/readdir.c b/fs/readdir.c index fee38e04fae4..d46eca8567a4 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -20,11 +20,11 @@ #include <asm/uaccess.h> -int vfs_readdir(struct file *file, filldir_t filler, void *buf) +int iterate_dir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); int res = -ENOTDIR; - if (!file->f_op || !file->f_op->readdir) + if (!file->f_op || (!file->f_op->readdir && !file->f_op->iterate)) goto out; res = security_file_permission(file, MAY_READ); @@ -37,15 +37,21 @@ int vfs_readdir(struct file *file, filldir_t filler, void *buf) res = -ENOENT; if (!IS_DEADDIR(inode)) { - res = file->f_op->readdir(file, buf, filler); + if (file->f_op->iterate) { + ctx->pos = file->f_pos; + res = file->f_op->iterate(file, ctx); + file->f_pos = ctx->pos; + } else { + res = file->f_op->readdir(file, ctx, ctx->actor); + ctx->pos = file->f_pos; + } file_accessed(file); } mutex_unlock(&inode->i_mutex); out: return res; } - -EXPORT_SYMBOL(vfs_readdir); +EXPORT_SYMBOL(iterate_dir); /* * Traditional linux readdir() handling.. @@ -66,6 +72,7 @@ struct old_linux_dirent { }; struct readdir_callback { + struct dir_context ctx; struct old_linux_dirent __user * dirent; int result; }; @@ -73,7 +80,7 @@ struct readdir_callback { static int fillonedir(void * __buf, const char * name, int namlen, loff_t offset, u64 ino, unsigned int d_type) { - struct readdir_callback * buf = (struct readdir_callback *) __buf; + struct readdir_callback *buf = (struct readdir_callback *) __buf; struct old_linux_dirent __user * dirent; unsigned long d_ino; @@ -107,15 +114,15 @@ SYSCALL_DEFINE3(old_readdir, unsigned int, fd, { int error; struct fd f = fdget(fd); - struct readdir_callback buf; + struct readdir_callback buf = { + .ctx.actor = fillonedir, + .dirent = dirent + }; if (!f.file) return -EBADF; - buf.result = 0; - buf.dirent = dirent; - - error = vfs_readdir(f.file, fillonedir, &buf); + error = iterate_dir(f.file, &buf.ctx); if (buf.result) error = buf.result; @@ -137,6 +144,7 @@ struct linux_dirent { }; struct getdents_callback { + struct dir_context ctx; struct linux_dirent __user * current_dir; struct linux_dirent __user * previous; int count; @@ -191,7 +199,11 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd, { struct fd f; struct linux_dirent __user * lastdirent; - struct getdents_callback buf; + struct getdents_callback buf = { + .ctx.actor = filldir, + .count = count, + .current_dir = dirent + }; int error; if (!access_ok(VERIFY_WRITE, dirent, count)) @@ -201,17 +213,12 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd, if (!f.file) return -EBADF; - buf.current_dir = dirent; - buf.previous = NULL; - buf.count = count; - buf.error = 0; - - error = vfs_readdir(f.file, filldir, &buf); + error = iterate_dir(f.file, &buf.ctx); if (error >= 0) error = buf.error; lastdirent = buf.previous; if (lastdirent) { - if (put_user(f.file->f_pos, &lastdirent->d_off)) + if (put_user(buf.ctx.pos, &lastdirent->d_off)) error = -EFAULT; else error = count - buf.count; @@ -221,6 +228,7 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd, } struct getdents_callback64 { + struct dir_context ctx; struct linux_dirent64 __user * current_dir; struct linux_dirent64 __user * previous; int count; @@ -271,7 +279,11 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd, { struct fd f; struct linux_dirent64 __user * lastdirent; - struct getdents_callback64 buf; + struct getdents_callback64 buf = { + .ctx.actor = filldir64, + .count = count, + .current_dir = dirent + }; int error; if (!access_ok(VERIFY_WRITE, dirent, count)) @@ -281,17 +293,12 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd, if (!f.file) return -EBADF; - buf.current_dir = dirent; - buf.previous = NULL; - buf.count = count; - buf.error = 0; - - error = vfs_readdir(f.file, filldir64, &buf); + error = iterate_dir(f.file, &buf.ctx); if (error >= 0) error = buf.error; lastdirent = buf.previous; if (lastdirent) { - typeof(lastdirent->d_off) d_off = f.file->f_pos; + typeof(lastdirent->d_off) d_off = buf.ctx.pos; if (__put_user(d_off, &lastdirent->d_off)) error = -EFAULT; else diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index e2e202a07b31..460f762a85c0 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -1317,6 +1317,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) int i; #endif + sync_filesystem(s); reiserfs_write_lock(s); #ifdef CONFIG_QUOTA diff --git a/fs/romfs/super.c b/fs/romfs/super.c index 15cbc41ee365..ae839482c341 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -435,6 +435,7 @@ static int romfs_statfs(struct dentry *dentry, struct kstatfs *buf) */ static int romfs_remount(struct super_block *sb, int *flags, char *data) { + sync_filesystem(sb); *flags |= MS_RDONLY; return 0; } diff --git a/fs/select.c b/fs/select.c index 8c1c96c27062..6b14dc7df3a4 100644 --- a/fs/select.c +++ b/fs/select.c @@ -27,6 +27,7 @@ #include <linux/rcupdate.h> #include <linux/hrtimer.h> #include <linux/sched/rt.h> +#include <linux/freezer.h> #include <asm/uaccess.h> @@ -236,7 +237,8 @@ int poll_schedule_timeout(struct poll_wqueues *pwq, int state, set_current_state(state); if (!pwq->triggered) - rc = schedule_hrtimeout_range(expires, slack, HRTIMER_MODE_ABS); + rc = freezable_schedule_hrtimeout_range(expires, slack, + HRTIMER_MODE_ABS); __set_current_state(TASK_RUNNING); /* diff --git a/fs/seq_file.c b/fs/seq_file.c index 3dd44db1465e..d84ca5932c73 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -8,8 +8,10 @@ #include <linux/fs.h> #include <linux/export.h> #include <linux/seq_file.h> +#include <linux/vmalloc.h> #include <linux/slab.h> #include <linux/cred.h> +#include <linux/mm.h> #include <asm/uaccess.h> #include <asm/page.h> @@ -30,6 +32,16 @@ static void seq_set_overflow(struct seq_file *m) m->count = m->size; } +static void *seq_buf_alloc(unsigned long size) +{ + void *buf; + + buf = kmalloc(size, GFP_KERNEL | __GFP_NOWARN); + if (!buf && size > PAGE_SIZE) + buf = vmalloc(size); + return buf; +} + /** * seq_open - initialize sequential file * @file: file we initialize @@ -96,7 +108,7 @@ static int traverse(struct seq_file *m, loff_t offset) return 0; } if (!m->buf) { - m->buf = kmalloc(m->size = PAGE_SIZE, GFP_KERNEL); + m->buf = seq_buf_alloc(m->size = PAGE_SIZE); if (!m->buf) return -ENOMEM; } @@ -135,8 +147,8 @@ static int traverse(struct seq_file *m, loff_t offset) Eoverflow: m->op->stop(m, p); - kfree(m->buf); - m->buf = kmalloc(m->size <<= 1, GFP_KERNEL); + kvfree(m->buf); + m->buf = seq_buf_alloc(m->size <<= 1); return !m->buf ? -ENOMEM : -EAGAIN; } @@ -191,7 +203,7 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos) /* grab buffer if we didn't have one */ if (!m->buf) { - m->buf = kmalloc(m->size = PAGE_SIZE, GFP_KERNEL); + m->buf = seq_buf_alloc(m->size = PAGE_SIZE); if (!m->buf) goto Enomem; } @@ -231,8 +243,8 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos) if (m->count < m->size) goto Fill; m->op->stop(m, p); - kfree(m->buf); - m->buf = kmalloc(m->size <<= 1, GFP_KERNEL); + kvfree(m->buf); + m->buf = seq_buf_alloc(m->size <<= 1); if (!m->buf) goto Enomem; m->count = 0; @@ -349,7 +361,7 @@ EXPORT_SYMBOL(seq_lseek); int seq_release(struct inode *inode, struct file *file) { struct seq_file *m = file->private_data; - kfree(m->buf); + kvfree(m->buf); kfree(m); return 0; } @@ -604,13 +616,13 @@ EXPORT_SYMBOL(single_open); int single_open_size(struct file *file, int (*show)(struct seq_file *, void *), void *data, size_t size) { - char *buf = kmalloc(size, GFP_KERNEL); + char *buf = seq_buf_alloc(size); int ret; if (!buf) return -ENOMEM; ret = single_open(file, show, data); if (ret) { - kfree(buf); + kvfree(buf); return ret; } ((struct seq_file *)file->private_data)->buf = buf; diff --git a/fs/squashfs/Kconfig b/fs/squashfs/Kconfig index c70111ebefd4..ffb093e72b6c 100644 --- a/fs/squashfs/Kconfig +++ b/fs/squashfs/Kconfig @@ -25,6 +25,78 @@ config SQUASHFS If unsure, say N. +choice + prompt "File decompression options" + depends on SQUASHFS + help + Squashfs now supports two options for decompressing file + data. Traditionally Squashfs has decompressed into an + intermediate buffer and then memcopied it into the page cache. + Squashfs now supports the ability to decompress directly into + the page cache. + + If unsure, select "Decompress file data into an intermediate buffer" + +config SQUASHFS_FILE_CACHE + bool "Decompress file data into an intermediate buffer" + help + Decompress file data into an intermediate buffer and then + memcopy it into the page cache. + +config SQUASHFS_FILE_DIRECT + bool "Decompress files directly into the page cache" + help + Directly decompress file data into the page cache. + Doing so can significantly improve performance because + it eliminates a memcpy and it also removes the lock contention + on the single buffer. + +endchoice + +choice + prompt "Decompressor parallelisation options" + depends on SQUASHFS + help + Squashfs now supports three parallelisation options for + decompression. Each one exhibits various trade-offs between + decompression performance and CPU and memory usage. + + If in doubt, select "Single threaded compression" + +config SQUASHFS_DECOMP_SINGLE + bool "Single threaded compression" + help + Traditionally Squashfs has used single-threaded decompression. + Only one block (data or metadata) can be decompressed at any + one time. This limits CPU and memory usage to a minimum. + +config SQUASHFS_DECOMP_MULTI + bool "Use multiple decompressors for parallel I/O" + help + By default Squashfs uses a single decompressor but it gives + poor performance on parallel I/O workloads when using multiple CPU + machines due to waiting on decompressor availability. + + If you have a parallel I/O workload and your system has enough memory, + using this option may improve overall I/O performance. + + This decompressor implementation uses up to two parallel + decompressors per core. It dynamically allocates decompressors + on a demand basis. + +config SQUASHFS_DECOMP_MULTI_PERCPU + bool "Use percpu multiple decompressors for parallel I/O" + help + By default Squashfs uses a single decompressor but it gives + poor performance on parallel I/O workloads when using multiple CPU + machines due to waiting on decompressor availability. + + This decompressor implementation uses a maximum of one + decompressor per core. It uses percpu variables to ensure + decompression is load-balanced across the cores. + +endchoice + config SQUASHFS_XATTR bool "Squashfs XATTR support" depends on SQUASHFS @@ -48,6 +120,21 @@ config SQUASHFS_ZLIB If unsure, say Y. +config SQUASHFS_LZ4 + bool "Include support for LZ4 compressed file systems" + depends on SQUASHFS + select LZ4_DECOMPRESS + help + Saying Y here includes support for reading Squashfs file systems + compressed with LZ4 compression. LZ4 compression is mainly + aimed at embedded systems with slower CPUs where the overheads + of zlib are too high. + + LZ4 is not the standard compression used in Squashfs and so most + file systems will be readable without selecting this option. + + If unsure, say N. + config SQUASHFS_LZO bool "Include support for LZO compressed file systems" depends on SQUASHFS diff --git a/fs/squashfs/Makefile b/fs/squashfs/Makefile index 110b0476f3b4..246a6f329d89 100644 --- a/fs/squashfs/Makefile +++ b/fs/squashfs/Makefile @@ -5,7 +5,13 @@ obj-$(CONFIG_SQUASHFS) += squashfs.o squashfs-y += block.o cache.o dir.o export.o file.o fragment.o id.o inode.o squashfs-y += namei.o super.o symlink.o decompressor.o +squashfs-$(CONFIG_SQUASHFS_FILE_CACHE) += file_cache.o +squashfs-$(CONFIG_SQUASHFS_FILE_DIRECT) += file_direct.o page_actor.o +squashfs-$(CONFIG_SQUASHFS_DECOMP_SINGLE) += decompressor_single.o +squashfs-$(CONFIG_SQUASHFS_DECOMP_MULTI) += decompressor_multi.o +squashfs-$(CONFIG_SQUASHFS_DECOMP_MULTI_PERCPU) += decompressor_multi_percpu.o squashfs-$(CONFIG_SQUASHFS_XATTR) += xattr.o xattr_id.o +squashfs-$(CONFIG_SQUASHFS_LZ4) += lz4_wrapper.o squashfs-$(CONFIG_SQUASHFS_LZO) += lzo_wrapper.o squashfs-$(CONFIG_SQUASHFS_XZ) += xz_wrapper.o squashfs-$(CONFIG_SQUASHFS_ZLIB) += zlib_wrapper.o diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index fb50652e4e11..0cea9b9236d0 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -36,6 +36,7 @@ #include "squashfs_fs_sb.h" #include "squashfs.h" #include "decompressor.h" +#include "page_actor.h" /* * Read the metadata block length, this is stored in the first two @@ -86,16 +87,16 @@ static struct buffer_head *get_block_length(struct super_block *sb, * generated a larger block - this does occasionally happen with compression * algorithms). */ -int squashfs_read_data(struct super_block *sb, void **buffer, u64 index, - int length, u64 *next_index, int srclength, int pages) +int squashfs_read_data(struct super_block *sb, u64 index, int length, + u64 *next_index, struct squashfs_page_actor *output) { struct squashfs_sb_info *msblk = sb->s_fs_info; struct buffer_head **bh; int offset = index & ((1 << msblk->devblksize_log2) - 1); u64 cur_index = index >> msblk->devblksize_log2; - int bytes, compressed, b = 0, k = 0, page = 0, avail; + int bytes, compressed, b = 0, k = 0, avail, i; - bh = kcalloc(((srclength + msblk->devblksize - 1) + bh = kcalloc(((output->length + msblk->devblksize - 1) >> msblk->devblksize_log2) + 1, sizeof(*bh), GFP_KERNEL); if (bh == NULL) return -ENOMEM; @@ -111,9 +112,9 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index, *next_index = index + length; TRACE("Block @ 0x%llx, %scompressed size %d, src size %d\n", - index, compressed ? "" : "un", length, srclength); + index, compressed ? "" : "un", length, output->length); - if (length < 0 || length > srclength || + if (length < 0 || length > output->length || (index + length) > msblk->bytes_used) goto read_failure; @@ -145,7 +146,7 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index, TRACE("Block @ 0x%llx, %scompressed size %d\n", index, compressed ? "" : "un", length); - if (length < 0 || length > srclength || + if (length < 0 || length > output->length || (index + length) > msblk->bytes_used) goto block_release; @@ -158,35 +159,36 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index, ll_rw_block(READ, b - 1, bh + 1); } + for (i = 0; i < b; i++) { + wait_on_buffer(bh[i]); + if (!buffer_uptodate(bh[i])) + goto block_release; + } + if (compressed) { - length = squashfs_decompress(msblk, buffer, bh, b, offset, - length, srclength, pages); + length = squashfs_decompress(msblk, bh, b, offset, length, + output); if (length < 0) goto read_failure; } else { /* * Block is uncompressed. */ - int i, in, pg_offset = 0; - - for (i = 0; i < b; i++) { - wait_on_buffer(bh[i]); - if (!buffer_uptodate(bh[i])) - goto block_release; - } + int in, pg_offset = 0; + void *data = squashfs_first_page(output); for (bytes = length; k < b; k++) { in = min(bytes, msblk->devblksize - offset); bytes -= in; while (in) { if (pg_offset == PAGE_CACHE_SIZE) { - page++; + data = squashfs_next_page(output); pg_offset = 0; } avail = min_t(int, in, PAGE_CACHE_SIZE - pg_offset); - memcpy(buffer[page] + pg_offset, - bh[k]->b_data + offset, avail); + memcpy(data + pg_offset, bh[k]->b_data + offset, + avail); in -= avail; pg_offset += avail; offset += avail; @@ -194,6 +196,7 @@ int squashfs_read_data(struct super_block *sb, void **buffer, u64 index, offset = 0; put_bh(bh[k]); } + squashfs_finish_page(output); } kfree(bh); diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c index af0b73802592..1cb70a0b2168 100644 --- a/fs/squashfs/cache.c +++ b/fs/squashfs/cache.c @@ -56,6 +56,7 @@ #include "squashfs_fs.h" #include "squashfs_fs_sb.h" #include "squashfs.h" +#include "page_actor.h" /* * Look-up block in cache, and increment usage count. If not in cache, read @@ -119,9 +120,8 @@ struct squashfs_cache_entry *squashfs_cache_get(struct super_block *sb, entry->error = 0; spin_unlock(&cache->lock); - entry->length = squashfs_read_data(sb, entry->data, - block, length, &entry->next_index, - cache->block_size, cache->pages); + entry->length = squashfs_read_data(sb, block, length, + &entry->next_index, entry->actor); spin_lock(&cache->lock); @@ -220,6 +220,7 @@ void squashfs_cache_delete(struct squashfs_cache *cache) kfree(cache->entry[i].data[j]); kfree(cache->entry[i].data); } + kfree(cache->entry[i].actor); } kfree(cache->entry); @@ -280,6 +281,13 @@ struct squashfs_cache *squashfs_cache_init(char *name, int entries, goto cleanup; } } + + entry->actor = squashfs_page_actor_init(entry->data, + cache->pages, 0); + if (entry->actor == NULL) { + ERROR("Failed to allocate %s cache entry\n", name); + goto cleanup; + } } return cache; @@ -410,6 +418,7 @@ void *squashfs_read_table(struct super_block *sb, u64 block, int length) int pages = (length + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; int i, res; void *table, *buffer, **data; + struct squashfs_page_actor *actor; table = buffer = kmalloc(length, GFP_KERNEL); if (table == NULL) @@ -421,19 +430,28 @@ void *squashfs_read_table(struct super_block *sb, u64 block, int length) goto failed; } + actor = squashfs_page_actor_init(data, pages, length); + if (actor == NULL) { + res = -ENOMEM; + goto failed2; + } + for (i = 0; i < pages; i++, buffer += PAGE_CACHE_SIZE) data[i] = buffer; - res = squashfs_read_data(sb, data, block, length | - SQUASHFS_COMPRESSED_BIT_BLOCK, NULL, length, pages); + res = squashfs_read_data(sb, block, length | + SQUASHFS_COMPRESSED_BIT_BLOCK, NULL, actor); kfree(data); + kfree(actor); if (res < 0) goto failed; return table; +failed2: + kfree(data); failed: kfree(table); return ERR_PTR(res); diff --git a/fs/squashfs/decompressor.c b/fs/squashfs/decompressor.c index 3f6271d86abc..e9034bf6e5ae 100644 --- a/fs/squashfs/decompressor.c +++ b/fs/squashfs/decompressor.c @@ -30,6 +30,7 @@ #include "squashfs_fs_sb.h" #include "decompressor.h" #include "squashfs.h" +#include "page_actor.h" /* * This file (and decompressor.h) implements a decompressor framework for @@ -37,33 +38,40 @@ */ static const struct squashfs_decompressor squashfs_lzma_unsupported_comp_ops = { - NULL, NULL, NULL, LZMA_COMPRESSION, "lzma", 0 + NULL, NULL, NULL, NULL, LZMA_COMPRESSION, "lzma", 0 }; +#ifndef CONFIG_SQUASHFS_LZ4 +static const struct squashfs_decompressor squashfs_lz4_comp_ops = { + NULL, NULL, NULL, NULL, LZ4_COMPRESSION, "lz4", 0 +}; +#endif + #ifndef CONFIG_SQUASHFS_LZO static const struct squashfs_decompressor squashfs_lzo_comp_ops = { - NULL, NULL, NULL, LZO_COMPRESSION, "lzo", 0 + NULL, NULL, NULL, NULL, LZO_COMPRESSION, "lzo", 0 }; #endif #ifndef CONFIG_SQUASHFS_XZ static const struct squashfs_decompressor squashfs_xz_comp_ops = { - NULL, NULL, NULL, XZ_COMPRESSION, "xz", 0 + NULL, NULL, NULL, NULL, XZ_COMPRESSION, "xz", 0 }; #endif #ifndef CONFIG_SQUASHFS_ZLIB static const struct squashfs_decompressor squashfs_zlib_comp_ops = { - NULL, NULL, NULL, ZLIB_COMPRESSION, "zlib", 0 + NULL, NULL, NULL, NULL, ZLIB_COMPRESSION, "zlib", 0 }; #endif static const struct squashfs_decompressor squashfs_unknown_comp_ops = { - NULL, NULL, NULL, 0, "unknown", 0 + NULL, NULL, NULL, NULL, 0, "unknown", 0 }; static const struct squashfs_decompressor *decompressor[] = { &squashfs_zlib_comp_ops, + &squashfs_lz4_comp_ops, &squashfs_lzo_comp_ops, &squashfs_xz_comp_ops, &squashfs_lzma_unsupported_comp_ops, @@ -83,10 +91,11 @@ const struct squashfs_decompressor *squashfs_lookup_decompressor(int id) } -void *squashfs_decompressor_init(struct super_block *sb, unsigned short flags) +static void *get_comp_opts(struct super_block *sb, unsigned short flags) { struct squashfs_sb_info *msblk = sb->s_fs_info; - void *strm, *buffer = NULL; + void *buffer = NULL, *comp_opts; + struct squashfs_page_actor *actor = NULL; int length = 0; /* @@ -94,23 +103,46 @@ void *squashfs_decompressor_init(struct super_block *sb, unsigned short flags) */ if (SQUASHFS_COMP_OPTS(flags)) { buffer = kmalloc(PAGE_CACHE_SIZE, GFP_KERNEL); - if (buffer == NULL) - return ERR_PTR(-ENOMEM); + if (buffer == NULL) { + comp_opts = ERR_PTR(-ENOMEM); + goto out; + } - length = squashfs_read_data(sb, &buffer, - sizeof(struct squashfs_super_block), 0, NULL, - PAGE_CACHE_SIZE, 1); + actor = squashfs_page_actor_init(&buffer, 1, 0); + if (actor == NULL) { + comp_opts = ERR_PTR(-ENOMEM); + goto out; + } + + length = squashfs_read_data(sb, + sizeof(struct squashfs_super_block), 0, NULL, actor); if (length < 0) { - strm = ERR_PTR(length); - goto finished; + comp_opts = ERR_PTR(length); + goto out; } } - strm = msblk->decompressor->init(msblk, buffer, length); + comp_opts = squashfs_comp_opts(msblk, buffer, length); -finished: +out: + kfree(actor); kfree(buffer); + return comp_opts; +} + + +void *squashfs_decompressor_setup(struct super_block *sb, unsigned short flags) +{ + struct squashfs_sb_info *msblk = sb->s_fs_info; + void *stream, *comp_opts = get_comp_opts(sb, flags); + + if (IS_ERR(comp_opts)) + return comp_opts; + + stream = squashfs_decompressor_create(msblk, comp_opts); + if (IS_ERR(stream)) + kfree(comp_opts); - return strm; + return stream; } diff --git a/fs/squashfs/decompressor.h b/fs/squashfs/decompressor.h index 330073e29029..a25713c031a5 100644 --- a/fs/squashfs/decompressor.h +++ b/fs/squashfs/decompressor.h @@ -24,34 +24,32 @@ */ struct squashfs_decompressor { - void *(*init)(struct squashfs_sb_info *, void *, int); + void *(*init)(struct squashfs_sb_info *, void *); + void *(*comp_opts)(struct squashfs_sb_info *, void *, int); void (*free)(void *); - int (*decompress)(struct squashfs_sb_info *, void **, - struct buffer_head **, int, int, int, int, int); + int (*decompress)(struct squashfs_sb_info *, void *, + struct buffer_head **, int, int, int, + struct squashfs_page_actor *); int id; char *name; int supported; }; -static inline void squashfs_decompressor_free(struct squashfs_sb_info *msblk, - void *s) +static inline void *squashfs_comp_opts(struct squashfs_sb_info *msblk, + void *buff, int length) { - if (msblk->decompressor) - msblk->decompressor->free(s); -} - -static inline int squashfs_decompress(struct squashfs_sb_info *msblk, - void **buffer, struct buffer_head **bh, int b, int offset, int length, - int srclength, int pages) -{ - return msblk->decompressor->decompress(msblk, buffer, bh, b, offset, - length, srclength, pages); + return msblk->decompressor->comp_opts ? + msblk->decompressor->comp_opts(msblk, buff, length) : NULL; } #ifdef CONFIG_SQUASHFS_XZ extern const struct squashfs_decompressor squashfs_xz_comp_ops; #endif +#ifdef CONFIG_SQUASHFS_LZ4 +extern const struct squashfs_decompressor squashfs_lz4_comp_ops; +#endif + #ifdef CONFIG_SQUASHFS_LZO extern const struct squashfs_decompressor squashfs_lzo_comp_ops; #endif diff --git a/fs/squashfs/decompressor_multi.c b/fs/squashfs/decompressor_multi.c new file mode 100644 index 000000000000..d6008a636479 --- /dev/null +++ b/fs/squashfs/decompressor_multi.c @@ -0,0 +1,198 @@ +/* + * Copyright (c) 2013 + * Minchan Kim <minchan@kernel.org> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ +#include <linux/types.h> +#include <linux/mutex.h> +#include <linux/slab.h> +#include <linux/buffer_head.h> +#include <linux/sched.h> +#include <linux/wait.h> +#include <linux/cpumask.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "decompressor.h" +#include "squashfs.h" + +/* + * This file implements multi-threaded decompression in the + * decompressor framework + */ + + +/* + * The reason that multiply two is that a CPU can request new I/O + * while it is waiting previous request. + */ +#define MAX_DECOMPRESSOR (num_online_cpus() * 2) + + +int squashfs_max_decompressors(void) +{ + return MAX_DECOMPRESSOR; +} + + +struct squashfs_stream { + void *comp_opts; + struct list_head strm_list; + struct mutex mutex; + int avail_decomp; + wait_queue_head_t wait; +}; + + +struct decomp_stream { + void *stream; + struct list_head list; +}; + + +static void put_decomp_stream(struct decomp_stream *decomp_strm, + struct squashfs_stream *stream) +{ + mutex_lock(&stream->mutex); + list_add(&decomp_strm->list, &stream->strm_list); + mutex_unlock(&stream->mutex); + wake_up(&stream->wait); +} + +void *squashfs_decompressor_create(struct squashfs_sb_info *msblk, + void *comp_opts) +{ + struct squashfs_stream *stream; + struct decomp_stream *decomp_strm = NULL; + int err = -ENOMEM; + + stream = kzalloc(sizeof(*stream), GFP_KERNEL); + if (!stream) + goto out; + + stream->comp_opts = comp_opts; + mutex_init(&stream->mutex); + INIT_LIST_HEAD(&stream->strm_list); + init_waitqueue_head(&stream->wait); + + /* + * We should have a decompressor at least as default + * so if we fail to allocate new decompressor dynamically, + * we could always fall back to default decompressor and + * file system works. + */ + decomp_strm = kmalloc(sizeof(*decomp_strm), GFP_KERNEL); + if (!decomp_strm) + goto out; + + decomp_strm->stream = msblk->decompressor->init(msblk, + stream->comp_opts); + if (IS_ERR(decomp_strm->stream)) { + err = PTR_ERR(decomp_strm->stream); + goto out; + } + + list_add(&decomp_strm->list, &stream->strm_list); + stream->avail_decomp = 1; + return stream; + +out: + kfree(decomp_strm); + kfree(stream); + return ERR_PTR(err); +} + + +void squashfs_decompressor_destroy(struct squashfs_sb_info *msblk) +{ + struct squashfs_stream *stream = msblk->stream; + if (stream) { + struct decomp_stream *decomp_strm; + + while (!list_empty(&stream->strm_list)) { + decomp_strm = list_entry(stream->strm_list.prev, + struct decomp_stream, list); + list_del(&decomp_strm->list); + msblk->decompressor->free(decomp_strm->stream); + kfree(decomp_strm); + stream->avail_decomp--; + } + WARN_ON(stream->avail_decomp); + kfree(stream->comp_opts); + kfree(stream); + } +} + + +static struct decomp_stream *get_decomp_stream(struct squashfs_sb_info *msblk, + struct squashfs_stream *stream) +{ + struct decomp_stream *decomp_strm; + + while (1) { + mutex_lock(&stream->mutex); + + /* There is available decomp_stream */ + if (!list_empty(&stream->strm_list)) { + decomp_strm = list_entry(stream->strm_list.prev, + struct decomp_stream, list); + list_del(&decomp_strm->list); + mutex_unlock(&stream->mutex); + break; + } + + /* + * If there is no available decomp and already full, + * let's wait for releasing decomp from other users. + */ + if (stream->avail_decomp >= MAX_DECOMPRESSOR) + goto wait; + + /* Let's allocate new decomp */ + decomp_strm = kmalloc(sizeof(*decomp_strm), GFP_KERNEL); + if (!decomp_strm) + goto wait; + + decomp_strm->stream = msblk->decompressor->init(msblk, + stream->comp_opts); + if (IS_ERR(decomp_strm->stream)) { + kfree(decomp_strm); + goto wait; + } + + stream->avail_decomp++; + WARN_ON(stream->avail_decomp > MAX_DECOMPRESSOR); + + mutex_unlock(&stream->mutex); + break; +wait: + /* + * If system memory is tough, let's for other's + * releasing instead of hurting VM because it could + * make page cache thrashing. + */ + mutex_unlock(&stream->mutex); + wait_event(stream->wait, + !list_empty(&stream->strm_list)); + } + + return decomp_strm; +} + + +int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh, + int b, int offset, int length, struct squashfs_page_actor *output) +{ + int res; + struct squashfs_stream *stream = msblk->stream; + struct decomp_stream *decomp_stream = get_decomp_stream(msblk, stream); + res = msblk->decompressor->decompress(msblk, decomp_stream->stream, + bh, b, offset, length, output); + put_decomp_stream(decomp_stream, stream); + if (res < 0) + ERROR("%s decompression failed, data probably corrupt\n", + msblk->decompressor->name); + return res; +} diff --git a/fs/squashfs/decompressor_multi_percpu.c b/fs/squashfs/decompressor_multi_percpu.c new file mode 100644 index 000000000000..23a9c28ad8ea --- /dev/null +++ b/fs/squashfs/decompressor_multi_percpu.c @@ -0,0 +1,97 @@ +/* + * Copyright (c) 2013 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/percpu.h> +#include <linux/buffer_head.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "decompressor.h" +#include "squashfs.h" + +/* + * This file implements multi-threaded decompression using percpu + * variables, one thread per cpu core. + */ + +struct squashfs_stream { + void *stream; +}; + +void *squashfs_decompressor_create(struct squashfs_sb_info *msblk, + void *comp_opts) +{ + struct squashfs_stream *stream; + struct squashfs_stream __percpu *percpu; + int err, cpu; + + percpu = alloc_percpu(struct squashfs_stream); + if (percpu == NULL) + return ERR_PTR(-ENOMEM); + + for_each_possible_cpu(cpu) { + stream = per_cpu_ptr(percpu, cpu); + stream->stream = msblk->decompressor->init(msblk, comp_opts); + if (IS_ERR(stream->stream)) { + err = PTR_ERR(stream->stream); + goto out; + } + } + + kfree(comp_opts); + return (__force void *) percpu; + +out: + for_each_possible_cpu(cpu) { + stream = per_cpu_ptr(percpu, cpu); + if (!IS_ERR_OR_NULL(stream->stream)) + msblk->decompressor->free(stream->stream); + } + free_percpu(percpu); + return ERR_PTR(err); +} + +void squashfs_decompressor_destroy(struct squashfs_sb_info *msblk) +{ + struct squashfs_stream __percpu *percpu = + (struct squashfs_stream __percpu *) msblk->stream; + struct squashfs_stream *stream; + int cpu; + + if (msblk->stream) { + for_each_possible_cpu(cpu) { + stream = per_cpu_ptr(percpu, cpu); + msblk->decompressor->free(stream->stream); + } + free_percpu(percpu); + } +} + +int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh, + int b, int offset, int length, struct squashfs_page_actor *output) +{ + struct squashfs_stream __percpu *percpu = + (struct squashfs_stream __percpu *) msblk->stream; + struct squashfs_stream *stream = get_cpu_ptr(percpu); + int res = msblk->decompressor->decompress(msblk, stream->stream, bh, b, + offset, length, output); + put_cpu_ptr(stream); + + if (res < 0) + ERROR("%s decompression failed, data probably corrupt\n", + msblk->decompressor->name); + + return res; +} + +int squashfs_max_decompressors(void) +{ + return num_possible_cpus(); +} diff --git a/fs/squashfs/decompressor_single.c b/fs/squashfs/decompressor_single.c new file mode 100644 index 000000000000..a6c75929a00e --- /dev/null +++ b/fs/squashfs/decompressor_single.c @@ -0,0 +1,85 @@ +/* + * Copyright (c) 2013 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include <linux/types.h> +#include <linux/mutex.h> +#include <linux/slab.h> +#include <linux/buffer_head.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "decompressor.h" +#include "squashfs.h" + +/* + * This file implements single-threaded decompression in the + * decompressor framework + */ + +struct squashfs_stream { + void *stream; + struct mutex mutex; +}; + +void *squashfs_decompressor_create(struct squashfs_sb_info *msblk, + void *comp_opts) +{ + struct squashfs_stream *stream; + int err = -ENOMEM; + + stream = kmalloc(sizeof(*stream), GFP_KERNEL); + if (stream == NULL) + goto out; + + stream->stream = msblk->decompressor->init(msblk, comp_opts); + if (IS_ERR(stream->stream)) { + err = PTR_ERR(stream->stream); + goto out; + } + + kfree(comp_opts); + mutex_init(&stream->mutex); + return stream; + +out: + kfree(stream); + return ERR_PTR(err); +} + +void squashfs_decompressor_destroy(struct squashfs_sb_info *msblk) +{ + struct squashfs_stream *stream = msblk->stream; + + if (stream) { + msblk->decompressor->free(stream->stream); + kfree(stream); + } +} + +int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh, + int b, int offset, int length, struct squashfs_page_actor *output) +{ + int res; + struct squashfs_stream *stream = msblk->stream; + + mutex_lock(&stream->mutex); + res = msblk->decompressor->decompress(msblk, stream->stream, bh, b, + offset, length, output); + mutex_unlock(&stream->mutex); + + if (res < 0) + ERROR("%s decompression failed, data probably corrupt\n", + msblk->decompressor->name); + + return res; +} + +int squashfs_max_decompressors(void) +{ + return 1; +} diff --git a/fs/squashfs/dir.c b/fs/squashfs/dir.c index 57dc70ebbb19..d8c2d747be28 100644 --- a/fs/squashfs/dir.c +++ b/fs/squashfs/dir.c @@ -54,6 +54,7 @@ static int get_dir_index_using_offset(struct super_block *sb, { struct squashfs_sb_info *msblk = sb->s_fs_info; int err, i, index, length = 0; + unsigned int size; struct squashfs_dir_index dir_index; TRACE("Entered get_dir_index_using_offset, i_count %d, f_pos %lld\n", @@ -81,8 +82,14 @@ static int get_dir_index_using_offset(struct super_block *sb, */ break; + size = le32_to_cpu(dir_index.size) + 1; + + /* size should never be larger than SQUASHFS_NAME_LEN */ + if (size > SQUASHFS_NAME_LEN) + break; + err = squashfs_read_metadata(sb, NULL, &index_start, - &index_offset, le32_to_cpu(dir_index.size) + 1); + &index_offset, size); if (err < 0) break; @@ -100,14 +107,13 @@ static int get_dir_index_using_offset(struct super_block *sb, } -static int squashfs_readdir(struct file *file, void *dirent, filldir_t filldir) +static int squashfs_readdir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; u64 block = squashfs_i(inode)->start + msblk->directory_table; - int offset = squashfs_i(inode)->offset, length, dir_count, size, - type, err; - unsigned int inode_number; + int offset = squashfs_i(inode)->offset, length, err; + unsigned int inode_number, dir_count, size, type; struct squashfs_dir_header dirh; struct squashfs_dir_entry *dire; @@ -127,11 +133,11 @@ static int squashfs_readdir(struct file *file, void *dirent, filldir_t filldir) * It also means that the external f_pos is offset by 3 from the * on-disk directory f_pos. */ - while (file->f_pos < 3) { + while (ctx->pos < 3) { char *name; int i_ino; - if (file->f_pos == 0) { + if (ctx->pos == 0) { name = "."; size = 1; i_ino = inode->i_ino; @@ -141,24 +147,18 @@ static int squashfs_readdir(struct file *file, void *dirent, filldir_t filldir) i_ino = squashfs_i(inode)->parent; } - TRACE("Calling filldir(%p, %s, %d, %lld, %d, %d)\n", - dirent, name, size, file->f_pos, i_ino, - squashfs_filetype_table[1]); - - if (filldir(dirent, name, size, file->f_pos, i_ino, - squashfs_filetype_table[1]) < 0) { - TRACE("Filldir returned less than 0\n"); + if (!dir_emit(ctx, name, size, i_ino, + squashfs_filetype_table[1])) goto finish; - } - file->f_pos += size; + ctx->pos += size; } length = get_dir_index_using_offset(inode->i_sb, &block, &offset, squashfs_i(inode)->dir_idx_start, squashfs_i(inode)->dir_idx_offset, squashfs_i(inode)->dir_idx_cnt, - file->f_pos); + ctx->pos); while (length < i_size_read(inode)) { /* @@ -198,7 +198,7 @@ static int squashfs_readdir(struct file *file, void *dirent, filldir_t filldir) length += sizeof(*dire) + size; - if (file->f_pos >= length) + if (ctx->pos >= length) continue; dire->name[size] = '\0'; @@ -206,22 +206,15 @@ static int squashfs_readdir(struct file *file, void *dirent, filldir_t filldir) ((short) le16_to_cpu(dire->inode_number)); type = le16_to_cpu(dire->type); - TRACE("Calling filldir(%p, %s, %d, %lld, %x:%x, %d, %d)" - "\n", dirent, dire->name, size, - file->f_pos, - le32_to_cpu(dirh.start_block), - le16_to_cpu(dire->offset), - inode_number, - squashfs_filetype_table[type]); + if (type > SQUASHFS_MAX_DIR_TYPE) + goto failed_read; - if (filldir(dirent, dire->name, size, file->f_pos, + if (!dir_emit(ctx, dire->name, size, inode_number, - squashfs_filetype_table[type]) < 0) { - TRACE("Filldir returned less than 0\n"); + squashfs_filetype_table[type])) goto finish; - } - file->f_pos = length; + ctx->pos = length; } } @@ -238,6 +231,6 @@ failed_read: const struct file_operations squashfs_dir_ops = { .read = generic_read_dir, - .readdir = squashfs_readdir, + .iterate = squashfs_readdir, .llseek = default_llseek, }; diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c index 8ca62c28fe12..e5c9689062ba 100644 --- a/fs/squashfs/file.c +++ b/fs/squashfs/file.c @@ -370,77 +370,15 @@ static int read_blocklist(struct inode *inode, int index, u64 *block) return le32_to_cpu(size); } - -static int squashfs_readpage(struct file *file, struct page *page) +/* Copy data into page cache */ +void squashfs_copy_cache(struct page *page, struct squashfs_cache_entry *buffer, + int bytes, int offset) { struct inode *inode = page->mapping->host; struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; - int bytes, i, offset = 0, sparse = 0; - struct squashfs_cache_entry *buffer = NULL; void *pageaddr; - - int mask = (1 << (msblk->block_log - PAGE_CACHE_SHIFT)) - 1; - int index = page->index >> (msblk->block_log - PAGE_CACHE_SHIFT); - int start_index = page->index & ~mask; - int end_index = start_index | mask; - int file_end = i_size_read(inode) >> msblk->block_log; - - TRACE("Entered squashfs_readpage, page index %lx, start block %llx\n", - page->index, squashfs_i(inode)->start); - - if (page->index >= ((i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT)) - goto out; - - if (index < file_end || squashfs_i(inode)->fragment_block == - SQUASHFS_INVALID_BLK) { - /* - * Reading a datablock from disk. Need to read block list - * to get location and block size. - */ - u64 block = 0; - int bsize = read_blocklist(inode, index, &block); - if (bsize < 0) - goto error_out; - - if (bsize == 0) { /* hole */ - bytes = index == file_end ? - (i_size_read(inode) & (msblk->block_size - 1)) : - msblk->block_size; - sparse = 1; - } else { - /* - * Read and decompress datablock. - */ - buffer = squashfs_get_datablock(inode->i_sb, - block, bsize); - if (buffer->error) { - ERROR("Unable to read page, block %llx, size %x" - "\n", block, bsize); - squashfs_cache_put(buffer); - goto error_out; - } - bytes = buffer->length; - } - } else { - /* - * Datablock is stored inside a fragment (tail-end packed - * block). - */ - buffer = squashfs_get_fragment(inode->i_sb, - squashfs_i(inode)->fragment_block, - squashfs_i(inode)->fragment_size); - - if (buffer->error) { - ERROR("Unable to read page, block %llx, size %x\n", - squashfs_i(inode)->fragment_block, - squashfs_i(inode)->fragment_size); - squashfs_cache_put(buffer); - goto error_out; - } - bytes = i_size_read(inode) & (msblk->block_size - 1); - offset = squashfs_i(inode)->fragment_offset; - } + int i, mask = (1 << (msblk->block_log - PAGE_CACHE_SHIFT)) - 1; + int start_index = page->index & ~mask, end_index = start_index | mask; /* * Loop copying datablock into pages. As the datablock likely covers @@ -451,7 +389,7 @@ static int squashfs_readpage(struct file *file, struct page *page) for (i = start_index; i <= end_index && bytes > 0; i++, bytes -= PAGE_CACHE_SIZE, offset += PAGE_CACHE_SIZE) { struct page *push_page; - int avail = sparse ? 0 : min_t(int, bytes, PAGE_CACHE_SIZE); + int avail = buffer ? min_t(int, bytes, PAGE_CACHE_SIZE) : 0; TRACE("bytes %d, i %d, available_bytes %d\n", bytes, i, avail); @@ -475,11 +413,75 @@ skip_page: if (i != page->index) page_cache_release(push_page); } +} + +/* Read datablock stored packed inside a fragment (tail-end packed block) */ +static int squashfs_readpage_fragment(struct page *page) +{ + struct inode *inode = page->mapping->host; + struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; + struct squashfs_cache_entry *buffer = squashfs_get_fragment(inode->i_sb, + squashfs_i(inode)->fragment_block, + squashfs_i(inode)->fragment_size); + int res = buffer->error; + + if (res) + ERROR("Unable to read page, block %llx, size %x\n", + squashfs_i(inode)->fragment_block, + squashfs_i(inode)->fragment_size); + else + squashfs_copy_cache(page, buffer, i_size_read(inode) & + (msblk->block_size - 1), + squashfs_i(inode)->fragment_offset); + + squashfs_cache_put(buffer); + return res; +} - if (!sparse) - squashfs_cache_put(buffer); +static int squashfs_readpage_sparse(struct page *page, int index, int file_end) +{ + struct inode *inode = page->mapping->host; + struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; + int bytes = index == file_end ? + (i_size_read(inode) & (msblk->block_size - 1)) : + msblk->block_size; + squashfs_copy_cache(page, NULL, bytes, 0); return 0; +} + +static int squashfs_readpage(struct file *file, struct page *page) +{ + struct inode *inode = page->mapping->host; + struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; + int index = page->index >> (msblk->block_log - PAGE_CACHE_SHIFT); + int file_end = i_size_read(inode) >> msblk->block_log; + int res; + void *pageaddr; + + TRACE("Entered squashfs_readpage, page index %lx, start block %llx\n", + page->index, squashfs_i(inode)->start); + + if (page->index >= ((i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> + PAGE_CACHE_SHIFT)) + goto out; + + if (index < file_end || squashfs_i(inode)->fragment_block == + SQUASHFS_INVALID_BLK) { + u64 block = 0; + int bsize = read_blocklist(inode, index, &block); + if (bsize < 0) + goto error_out; + + if (bsize == 0) + res = squashfs_readpage_sparse(page, index, file_end); + else + res = squashfs_readpage_block(page, block, bsize); + } else + res = squashfs_readpage_fragment(page); + + if (!res) + return 0; error_out: SetPageError(page); diff --git a/fs/squashfs/file_cache.c b/fs/squashfs/file_cache.c new file mode 100644 index 000000000000..f2310d2a2019 --- /dev/null +++ b/fs/squashfs/file_cache.c @@ -0,0 +1,38 @@ +/* + * Copyright (c) 2013 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include <linux/fs.h> +#include <linux/vfs.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/pagemap.h> +#include <linux/mutex.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs_fs_i.h" +#include "squashfs.h" + +/* Read separately compressed datablock and memcopy into page cache */ +int squashfs_readpage_block(struct page *page, u64 block, int bsize) +{ + struct inode *i = page->mapping->host; + struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb, + block, bsize); + int res = buffer->error; + + if (res) + ERROR("Unable to read page, block %llx, size %x\n", block, + bsize); + else + squashfs_copy_cache(page, buffer, buffer->length, 0); + + squashfs_cache_put(buffer); + return res; +} diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c new file mode 100644 index 000000000000..43e7a7eddac0 --- /dev/null +++ b/fs/squashfs/file_direct.c @@ -0,0 +1,176 @@ +/* + * Copyright (c) 2013 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include <linux/fs.h> +#include <linux/vfs.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/pagemap.h> +#include <linux/mutex.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs_fs_i.h" +#include "squashfs.h" +#include "page_actor.h" + +static int squashfs_read_cache(struct page *target_page, u64 block, int bsize, + int pages, struct page **page); + +/* Read separately compressed datablock directly into page cache */ +int squashfs_readpage_block(struct page *target_page, u64 block, int bsize) + +{ + struct inode *inode = target_page->mapping->host; + struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; + + int file_end = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT; + int mask = (1 << (msblk->block_log - PAGE_CACHE_SHIFT)) - 1; + int start_index = target_page->index & ~mask; + int end_index = start_index | mask; + int i, n, pages, missing_pages, bytes, res = -ENOMEM; + struct page **page; + struct squashfs_page_actor *actor; + void *pageaddr; + + if (end_index > file_end) + end_index = file_end; + + pages = end_index - start_index + 1; + + page = kmalloc_array(pages, sizeof(void *), GFP_KERNEL); + if (page == NULL) + return res; + + /* + * Create a "page actor" which will kmap and kunmap the + * page cache pages appropriately within the decompressor + */ + actor = squashfs_page_actor_init_special(page, pages, 0); + if (actor == NULL) + goto out; + + /* Try to grab all the pages covered by the Squashfs block */ + for (missing_pages = 0, i = 0, n = start_index; i < pages; i++, n++) { + page[i] = (n == target_page->index) ? target_page : + grab_cache_page_nowait(target_page->mapping, n); + + if (page[i] == NULL) { + missing_pages++; + continue; + } + + if (PageUptodate(page[i])) { + unlock_page(page[i]); + page_cache_release(page[i]); + page[i] = NULL; + missing_pages++; + } + } + + if (missing_pages) { + /* + * Couldn't get one or more pages, this page has either + * been VM reclaimed, but others are still in the page cache + * and uptodate, or we're racing with another thread in + * squashfs_readpage also trying to grab them. Fall back to + * using an intermediate buffer. + */ + res = squashfs_read_cache(target_page, block, bsize, pages, + page); + if (res < 0) + goto mark_errored; + + goto out; + } + + /* Decompress directly into the page cache buffers */ + res = squashfs_read_data(inode->i_sb, block, bsize, NULL, actor); + if (res < 0) + goto mark_errored; + + /* Last page may have trailing bytes not filled */ + bytes = res % PAGE_CACHE_SIZE; + if (bytes) { + pageaddr = kmap_atomic(page[pages - 1]); + memset(pageaddr + bytes, 0, PAGE_CACHE_SIZE - bytes); + kunmap_atomic(pageaddr); + } + + /* Mark pages as uptodate, unlock and release */ + for (i = 0; i < pages; i++) { + flush_dcache_page(page[i]); + SetPageUptodate(page[i]); + unlock_page(page[i]); + if (page[i] != target_page) + page_cache_release(page[i]); + } + + kfree(actor); + kfree(page); + + return 0; + +mark_errored: + /* Decompression failed, mark pages as errored. Target_page is + * dealt with by the caller + */ + for (i = 0; i < pages; i++) { + if (page[i] == NULL || page[i] == target_page) + continue; + flush_dcache_page(page[i]); + SetPageError(page[i]); + unlock_page(page[i]); + page_cache_release(page[i]); + } + +out: + kfree(actor); + kfree(page); + return res; +} + + +static int squashfs_read_cache(struct page *target_page, u64 block, int bsize, + int pages, struct page **page) +{ + struct inode *i = target_page->mapping->host; + struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb, + block, bsize); + int bytes = buffer->length, res = buffer->error, n, offset = 0; + void *pageaddr; + + if (res) { + ERROR("Unable to read page, block %llx, size %x\n", block, + bsize); + goto out; + } + + for (n = 0; n < pages && bytes > 0; n++, + bytes -= PAGE_CACHE_SIZE, offset += PAGE_CACHE_SIZE) { + int avail = min_t(int, bytes, PAGE_CACHE_SIZE); + + if (page[n] == NULL) + continue; + + pageaddr = kmap_atomic(page[n]); + squashfs_copy_data(pageaddr, buffer, offset, avail); + memset(pageaddr + avail, 0, PAGE_CACHE_SIZE - avail); + kunmap_atomic(pageaddr); + flush_dcache_page(page[n]); + SetPageUptodate(page[n]); + unlock_page(page[n]); + if (page[n] != target_page) + page_cache_release(page[n]); + } + +out: + squashfs_cache_put(buffer); + return res; +} diff --git a/fs/squashfs/lz4_wrapper.c b/fs/squashfs/lz4_wrapper.c new file mode 100644 index 000000000000..c31e2bc9c081 --- /dev/null +++ b/fs/squashfs/lz4_wrapper.c @@ -0,0 +1,142 @@ +/* + * Copyright (c) 2013, 2014 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include <linux/buffer_head.h> +#include <linux/mutex.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> +#include <linux/lz4.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs.h" +#include "decompressor.h" +#include "page_actor.h" + +#define LZ4_LEGACY 1 + +struct lz4_comp_opts { + __le32 version; + __le32 flags; +}; + +struct squashfs_lz4 { + void *input; + void *output; +}; + + +static void *lz4_comp_opts(struct squashfs_sb_info *msblk, + void *buff, int len) +{ + struct lz4_comp_opts *comp_opts = buff; + + /* LZ4 compressed filesystems always have compression options */ + if (comp_opts == NULL || len < sizeof(*comp_opts)) + return ERR_PTR(-EIO); + + if (le32_to_cpu(comp_opts->version) != LZ4_LEGACY) { + /* LZ4 format currently used by the kernel is the 'legacy' + * format */ + ERROR("Unknown LZ4 version\n"); + return ERR_PTR(-EINVAL); + } + + return NULL; +} + + +static void *lz4_init(struct squashfs_sb_info *msblk, void *buff) +{ + int block_size = max_t(int, msblk->block_size, SQUASHFS_METADATA_SIZE); + struct squashfs_lz4 *stream; + + stream = kzalloc(sizeof(*stream), GFP_KERNEL); + if (stream == NULL) + goto failed; + stream->input = vmalloc(block_size); + if (stream->input == NULL) + goto failed2; + stream->output = vmalloc(block_size); + if (stream->output == NULL) + goto failed3; + + return stream; + +failed3: + vfree(stream->input); +failed2: + kfree(stream); +failed: + ERROR("Failed to initialise LZ4 decompressor\n"); + return ERR_PTR(-ENOMEM); +} + + +static void lz4_free(void *strm) +{ + struct squashfs_lz4 *stream = strm; + + if (stream) { + vfree(stream->input); + vfree(stream->output); + } + kfree(stream); +} + + +static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm, + struct buffer_head **bh, int b, int offset, int length, + struct squashfs_page_actor *output) +{ + struct squashfs_lz4 *stream = strm; + void *buff = stream->input, *data; + int avail, i, bytes = length, res; + size_t dest_len = output->length; + + for (i = 0; i < b; i++) { + avail = min(bytes, msblk->devblksize - offset); + memcpy(buff, bh[i]->b_data + offset, avail); + buff += avail; + bytes -= avail; + offset = 0; + put_bh(bh[i]); + } + + res = lz4_decompress_unknownoutputsize(stream->input, length, + stream->output, &dest_len); + if (res) + return -EIO; + + bytes = dest_len; + data = squashfs_first_page(output); + buff = stream->output; + while (data) { + if (bytes <= PAGE_CACHE_SIZE) { + memcpy(data, buff, bytes); + break; + } + memcpy(data, buff, PAGE_CACHE_SIZE); + buff += PAGE_CACHE_SIZE; + bytes -= PAGE_CACHE_SIZE; + data = squashfs_next_page(output); + } + squashfs_finish_page(output); + + return dest_len; +} + +const struct squashfs_decompressor squashfs_lz4_comp_ops = { + .init = lz4_init, + .comp_opts = lz4_comp_opts, + .free = lz4_free, + .decompress = lz4_uncompress, + .id = LZ4_COMPRESSION, + .name = "lz4", + .supported = 1 +}; diff --git a/fs/squashfs/lzo_wrapper.c b/fs/squashfs/lzo_wrapper.c index 00f4dfc5f088..244b9fbfff7b 100644 --- a/fs/squashfs/lzo_wrapper.c +++ b/fs/squashfs/lzo_wrapper.c @@ -31,13 +31,14 @@ #include "squashfs_fs_sb.h" #include "squashfs.h" #include "decompressor.h" +#include "page_actor.h" struct squashfs_lzo { void *input; void *output; }; -static void *lzo_init(struct squashfs_sb_info *msblk, void *buff, int len) +static void *lzo_init(struct squashfs_sb_info *msblk, void *buff) { int block_size = max_t(int, msblk->block_size, SQUASHFS_METADATA_SIZE); @@ -74,22 +75,16 @@ static void lzo_free(void *strm) } -static int lzo_uncompress(struct squashfs_sb_info *msblk, void **buffer, - struct buffer_head **bh, int b, int offset, int length, int srclength, - int pages) +static int lzo_uncompress(struct squashfs_sb_info *msblk, void *strm, + struct buffer_head **bh, int b, int offset, int length, + struct squashfs_page_actor *output) { - struct squashfs_lzo *stream = msblk->stream; - void *buff = stream->input; + struct squashfs_lzo *stream = strm; + void *buff = stream->input, *data; int avail, i, bytes = length, res; - size_t out_len = srclength; - - mutex_lock(&msblk->read_data_mutex); + size_t out_len = output->length; for (i = 0; i < b; i++) { - wait_on_buffer(bh[i]); - if (!buffer_uptodate(bh[i])) - goto block_release; - avail = min(bytes, msblk->devblksize - offset); memcpy(buff, bh[i]->b_data + offset, avail); buff += avail; @@ -104,24 +99,24 @@ static int lzo_uncompress(struct squashfs_sb_info *msblk, void **buffer, goto failed; res = bytes = (int)out_len; - for (i = 0, buff = stream->output; bytes && i < pages; i++) { - avail = min_t(int, bytes, PAGE_CACHE_SIZE); - memcpy(buffer[i], buff, avail); - buff += avail; - bytes -= avail; + data = squashfs_first_page(output); + buff = stream->output; + while (data) { + if (bytes <= PAGE_CACHE_SIZE) { + memcpy(data, buff, bytes); + break; + } else { + memcpy(data, buff, PAGE_CACHE_SIZE); + buff += PAGE_CACHE_SIZE; + bytes -= PAGE_CACHE_SIZE; + data = squashfs_next_page(output); + } } + squashfs_finish_page(output); - mutex_unlock(&msblk->read_data_mutex); return res; -block_release: - for (; i < b; i++) - put_bh(bh[i]); - failed: - mutex_unlock(&msblk->read_data_mutex); - - ERROR("lzo decompression failed, data probably corrupt\n"); return -EIO; } diff --git a/fs/squashfs/namei.c b/fs/squashfs/namei.c index 7834a517f7f4..67cad77fefb4 100644 --- a/fs/squashfs/namei.c +++ b/fs/squashfs/namei.c @@ -79,7 +79,8 @@ static int get_dir_index_using_name(struct super_block *sb, int len) { struct squashfs_sb_info *msblk = sb->s_fs_info; - int i, size, length = 0, err; + int i, length = 0, err; + unsigned int size; struct squashfs_dir_index *index; char *str; @@ -103,6 +104,8 @@ static int get_dir_index_using_name(struct super_block *sb, size = le32_to_cpu(index->size) + 1; + if (size > SQUASHFS_NAME_LEN) + break; err = squashfs_read_metadata(sb, index->name, &index_start, &index_offset, size); @@ -144,7 +147,8 @@ static struct dentry *squashfs_lookup(struct inode *dir, struct dentry *dentry, struct squashfs_dir_entry *dire; u64 block = squashfs_i(dir)->start + msblk->directory_table; int offset = squashfs_i(dir)->offset; - int err, length, dir_count, size; + int err, length; + unsigned int dir_count, size; TRACE("Entered squashfs_lookup [%llx:%x]\n", block, offset); diff --git a/fs/squashfs/page_actor.c b/fs/squashfs/page_actor.c new file mode 100644 index 000000000000..5a1c11f56441 --- /dev/null +++ b/fs/squashfs/page_actor.c @@ -0,0 +1,100 @@ +/* + * Copyright (c) 2013 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/pagemap.h> +#include "page_actor.h" + +/* + * This file contains implementations of page_actor for decompressing into + * an intermediate buffer, and for decompressing directly into the + * page cache. + * + * Calling code should avoid sleeping between calls to squashfs_first_page() + * and squashfs_finish_page(). + */ + +/* Implementation of page_actor for decompressing into intermediate buffer */ +static void *cache_first_page(struct squashfs_page_actor *actor) +{ + actor->next_page = 1; + return actor->buffer[0]; +} + +static void *cache_next_page(struct squashfs_page_actor *actor) +{ + if (actor->next_page == actor->pages) + return NULL; + + return actor->buffer[actor->next_page++]; +} + +static void cache_finish_page(struct squashfs_page_actor *actor) +{ + /* empty */ +} + +struct squashfs_page_actor *squashfs_page_actor_init(void **buffer, + int pages, int length) +{ + struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL); + + if (actor == NULL) + return NULL; + + actor->length = length ? : pages * PAGE_CACHE_SIZE; + actor->buffer = buffer; + actor->pages = pages; + actor->next_page = 0; + actor->squashfs_first_page = cache_first_page; + actor->squashfs_next_page = cache_next_page; + actor->squashfs_finish_page = cache_finish_page; + return actor; +} + +/* Implementation of page_actor for decompressing directly into page cache. */ +static void *direct_first_page(struct squashfs_page_actor *actor) +{ + actor->next_page = 1; + return actor->pageaddr = kmap_atomic(actor->page[0]); +} + +static void *direct_next_page(struct squashfs_page_actor *actor) +{ + if (actor->pageaddr) + kunmap_atomic(actor->pageaddr); + + return actor->pageaddr = actor->next_page == actor->pages ? NULL : + kmap_atomic(actor->page[actor->next_page++]); +} + +static void direct_finish_page(struct squashfs_page_actor *actor) +{ + if (actor->pageaddr) + kunmap_atomic(actor->pageaddr); +} + +struct squashfs_page_actor *squashfs_page_actor_init_special(struct page **page, + int pages, int length) +{ + struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL); + + if (actor == NULL) + return NULL; + + actor->length = length ? : pages * PAGE_CACHE_SIZE; + actor->page = page; + actor->pages = pages; + actor->next_page = 0; + actor->pageaddr = NULL; + actor->squashfs_first_page = direct_first_page; + actor->squashfs_next_page = direct_next_page; + actor->squashfs_finish_page = direct_finish_page; + return actor; +} diff --git a/fs/squashfs/page_actor.h b/fs/squashfs/page_actor.h new file mode 100644 index 000000000000..26dd82008b82 --- /dev/null +++ b/fs/squashfs/page_actor.h @@ -0,0 +1,81 @@ +#ifndef PAGE_ACTOR_H +#define PAGE_ACTOR_H +/* + * Copyright (c) 2013 + * Phillip Lougher <phillip@squashfs.org.uk> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#ifndef CONFIG_SQUASHFS_FILE_DIRECT +struct squashfs_page_actor { + void **page; + int pages; + int length; + int next_page; +}; + +static inline struct squashfs_page_actor *squashfs_page_actor_init(void **page, + int pages, int length) +{ + struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL); + + if (actor == NULL) + return NULL; + + actor->length = length ? : pages * PAGE_CACHE_SIZE; + actor->page = page; + actor->pages = pages; + actor->next_page = 0; + return actor; +} + +static inline void *squashfs_first_page(struct squashfs_page_actor *actor) +{ + actor->next_page = 1; + return actor->page[0]; +} + +static inline void *squashfs_next_page(struct squashfs_page_actor *actor) +{ + return actor->next_page == actor->pages ? NULL : + actor->page[actor->next_page++]; +} + +static inline void squashfs_finish_page(struct squashfs_page_actor *actor) +{ + /* empty */ +} +#else +struct squashfs_page_actor { + union { + void **buffer; + struct page **page; + }; + void *pageaddr; + void *(*squashfs_first_page)(struct squashfs_page_actor *); + void *(*squashfs_next_page)(struct squashfs_page_actor *); + void (*squashfs_finish_page)(struct squashfs_page_actor *); + int pages; + int length; + int next_page; +}; + +extern struct squashfs_page_actor *squashfs_page_actor_init(void **, int, int); +extern struct squashfs_page_actor *squashfs_page_actor_init_special(struct page + **, int, int); +static inline void *squashfs_first_page(struct squashfs_page_actor *actor) +{ + return actor->squashfs_first_page(actor); +} +static inline void *squashfs_next_page(struct squashfs_page_actor *actor) +{ + return actor->squashfs_next_page(actor); +} +static inline void squashfs_finish_page(struct squashfs_page_actor *actor) +{ + actor->squashfs_finish_page(actor); +} +#endif +#endif diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h index d1266516ed08..887d6d270080 100644 --- a/fs/squashfs/squashfs.h +++ b/fs/squashfs/squashfs.h @@ -25,11 +25,11 @@ #define ERROR(s, args...) pr_err("SQUASHFS error: "s, ## args) -#define WARNING(s, args...) pr_warning("SQUASHFS: "s, ## args) +#define WARNING(s, args...) pr_warn("SQUASHFS: "s, ## args) /* block.c */ -extern int squashfs_read_data(struct super_block *, void **, u64, int, u64 *, - int, int); +extern int squashfs_read_data(struct super_block *, u64, int, u64 *, + struct squashfs_page_actor *); /* cache.c */ extern struct squashfs_cache *squashfs_cache_init(char *, int, int); @@ -48,7 +48,14 @@ extern void *squashfs_read_table(struct super_block *, u64, int); /* decompressor.c */ extern const struct squashfs_decompressor *squashfs_lookup_decompressor(int); -extern void *squashfs_decompressor_init(struct super_block *, unsigned short); +extern void *squashfs_decompressor_setup(struct super_block *, unsigned short); + +/* decompressor_xxx.c */ +extern void *squashfs_decompressor_create(struct squashfs_sb_info *, void *); +extern void squashfs_decompressor_destroy(struct squashfs_sb_info *); +extern int squashfs_decompress(struct squashfs_sb_info *, struct buffer_head **, + int, int, int, struct squashfs_page_actor *); +extern int squashfs_max_decompressors(void); /* export.c */ extern __le64 *squashfs_read_inode_lookup_table(struct super_block *, u64, u64, @@ -59,6 +66,13 @@ extern int squashfs_frag_lookup(struct super_block *, unsigned int, u64 *); extern __le64 *squashfs_read_fragment_index_table(struct super_block *, u64, u64, unsigned int); +/* file.c */ +void squashfs_copy_cache(struct page *, struct squashfs_cache_entry *, int, + int); + +/* file_xxx.c */ +extern int squashfs_readpage_block(struct page *, u64, int); + /* id.c */ extern int squashfs_get_id(struct super_block *, unsigned int, unsigned int *); extern __le64 *squashfs_read_id_index_table(struct super_block *, u64, u64, diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h index 9e2349d07cb1..506f4ba5b983 100644 --- a/fs/squashfs/squashfs_fs.h +++ b/fs/squashfs/squashfs_fs.h @@ -87,7 +87,7 @@ #define SQUASHFS_COMP_OPTS(flags) SQUASHFS_BIT(flags, \ SQUASHFS_COMP_OPT) -/* Max number of types and file types */ +/* Inode types including extended types */ #define SQUASHFS_DIR_TYPE 1 #define SQUASHFS_REG_TYPE 2 #define SQUASHFS_SYMLINK_TYPE 3 @@ -103,6 +103,9 @@ #define SQUASHFS_LFIFO_TYPE 13 #define SQUASHFS_LSOCKET_TYPE 14 +/* Max type value stored in directory entry */ +#define SQUASHFS_MAX_DIR_TYPE 7 + /* Xattr types */ #define SQUASHFS_XATTR_USER 0 #define SQUASHFS_XATTR_TRUSTED 1 @@ -237,6 +240,7 @@ struct meta_index { #define LZMA_COMPRESSION 2 #define LZO_COMPRESSION 3 #define XZ_COMPRESSION 4 +#define LZ4_COMPRESSION 5 struct squashfs_super_block { __le32 s_magic; diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h index 52934a22f296..1da565cb50c3 100644 --- a/fs/squashfs/squashfs_fs_sb.h +++ b/fs/squashfs/squashfs_fs_sb.h @@ -50,6 +50,7 @@ struct squashfs_cache_entry { wait_queue_head_t wait_queue; struct squashfs_cache *cache; void **data; + struct squashfs_page_actor *actor; }; struct squashfs_sb_info { @@ -63,10 +64,9 @@ struct squashfs_sb_info { __le64 *id_table; __le64 *fragment_index; __le64 *xattr_id_table; - struct mutex read_data_mutex; struct mutex meta_index_mutex; struct meta_index *meta_index; - void *stream; + struct squashfs_stream *stream; __le64 *inode_lookup_table; u64 inode_table; u64 directory_table; diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 60553a9053ca..5056babe00df 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -27,6 +27,8 @@ * the filesystem. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/fs.h> #include <linux/vfs.h> #include <linux/slab.h> @@ -98,7 +100,6 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) msblk->devblksize = sb_min_blocksize(sb, SQUASHFS_DEVBLK_SIZE); msblk->devblksize_log2 = ffz(~msblk->devblksize); - mutex_init(&msblk->read_data_mutex); mutex_init(&msblk->meta_index_mutex); /* @@ -206,13 +207,14 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; /* Allocate read_page block */ - msblk->read_page = squashfs_cache_init("data", 1, msblk->block_size); + msblk->read_page = squashfs_cache_init("data", + squashfs_max_decompressors(), msblk->block_size); if (msblk->read_page == NULL) { ERROR("Failed to allocate read_page block\n"); goto failed_mount; } - msblk->stream = squashfs_decompressor_init(sb, flags); + msblk->stream = squashfs_decompressor_setup(sb, flags); if (IS_ERR(msblk->stream)) { err = PTR_ERR(msblk->stream); msblk->stream = NULL; @@ -336,7 +338,7 @@ failed_mount: squashfs_cache_delete(msblk->block_cache); squashfs_cache_delete(msblk->fragment_cache); squashfs_cache_delete(msblk->read_page); - squashfs_decompressor_free(msblk, msblk->stream); + squashfs_decompressor_destroy(msblk); kfree(msblk->inode_lookup_table); kfree(msblk->fragment_index); kfree(msblk->id_table); @@ -371,6 +373,7 @@ static int squashfs_statfs(struct dentry *dentry, struct kstatfs *buf) static int squashfs_remount(struct super_block *sb, int *flags, char *data) { + sync_filesystem(sb); *flags |= MS_RDONLY; return 0; } @@ -383,7 +386,7 @@ static void squashfs_put_super(struct super_block *sb) squashfs_cache_delete(sbi->block_cache); squashfs_cache_delete(sbi->fragment_cache); squashfs_cache_delete(sbi->read_page); - squashfs_decompressor_free(sbi, sbi->stream); + squashfs_decompressor_destroy(sbi); kfree(sbi->id_table); kfree(sbi->fragment_index); kfree(sbi->meta_index); @@ -447,8 +450,7 @@ static int __init init_squashfs_fs(void) return err; } - printk(KERN_INFO "squashfs: version 4.0 (2009/01/31) " - "Phillip Lougher\n"); + pr_info("version 4.0 (2009/01/31) Phillip Lougher\n"); return 0; } diff --git a/fs/squashfs/xz_wrapper.c b/fs/squashfs/xz_wrapper.c index 1760b7d108f6..c609624e4b8a 100644 --- a/fs/squashfs/xz_wrapper.c +++ b/fs/squashfs/xz_wrapper.c @@ -32,44 +32,70 @@ #include "squashfs_fs_sb.h" #include "squashfs.h" #include "decompressor.h" +#include "page_actor.h" struct squashfs_xz { struct xz_dec *state; struct xz_buf buf; }; -struct comp_opts { +struct disk_comp_opts { __le32 dictionary_size; __le32 flags; }; -static void *squashfs_xz_init(struct squashfs_sb_info *msblk, void *buff, - int len) +struct comp_opts { + int dict_size; +}; + +static void *squashfs_xz_comp_opts(struct squashfs_sb_info *msblk, + void *buff, int len) { - struct comp_opts *comp_opts = buff; - struct squashfs_xz *stream; - int dict_size = msblk->block_size; - int err, n; + struct disk_comp_opts *comp_opts = buff; + struct comp_opts *opts; + int err = 0, n; + + opts = kmalloc(sizeof(*opts), GFP_KERNEL); + if (opts == NULL) { + err = -ENOMEM; + goto out2; + } if (comp_opts) { /* check compressor options are the expected length */ if (len < sizeof(*comp_opts)) { err = -EIO; - goto failed; + goto out; } - dict_size = le32_to_cpu(comp_opts->dictionary_size); + opts->dict_size = le32_to_cpu(comp_opts->dictionary_size); /* the dictionary size should be 2^n or 2^n+2^(n+1) */ - n = ffs(dict_size) - 1; - if (dict_size != (1 << n) && dict_size != (1 << n) + + n = ffs(opts->dict_size) - 1; + if (opts->dict_size != (1 << n) && opts->dict_size != (1 << n) + (1 << (n + 1))) { err = -EIO; - goto failed; + goto out; } - } + } else + /* use defaults */ + opts->dict_size = max_t(int, msblk->block_size, + SQUASHFS_METADATA_SIZE); + + return opts; + +out: + kfree(opts); +out2: + return ERR_PTR(err); +} + - dict_size = max_t(int, dict_size, SQUASHFS_METADATA_SIZE); +static void *squashfs_xz_init(struct squashfs_sb_info *msblk, void *buff) +{ + struct comp_opts *comp_opts = buff; + struct squashfs_xz *stream; + int err; stream = kmalloc(sizeof(*stream), GFP_KERNEL); if (stream == NULL) { @@ -77,7 +103,7 @@ static void *squashfs_xz_init(struct squashfs_sb_info *msblk, void *buff, goto failed; } - stream->state = xz_dec_init(XZ_PREALLOC, dict_size); + stream->state = xz_dec_init(XZ_PREALLOC, comp_opts->dict_size); if (stream->state == NULL) { kfree(stream); err = -ENOMEM; @@ -103,42 +129,37 @@ static void squashfs_xz_free(void *strm) } -static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void **buffer, - struct buffer_head **bh, int b, int offset, int length, int srclength, - int pages) +static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void *strm, + struct buffer_head **bh, int b, int offset, int length, + struct squashfs_page_actor *output) { enum xz_ret xz_err; - int avail, total = 0, k = 0, page = 0; - struct squashfs_xz *stream = msblk->stream; - - mutex_lock(&msblk->read_data_mutex); + int avail, total = 0, k = 0; + struct squashfs_xz *stream = strm; xz_dec_reset(stream->state); stream->buf.in_pos = 0; stream->buf.in_size = 0; stream->buf.out_pos = 0; stream->buf.out_size = PAGE_CACHE_SIZE; - stream->buf.out = buffer[page++]; + stream->buf.out = squashfs_first_page(output); do { if (stream->buf.in_pos == stream->buf.in_size && k < b) { avail = min(length, msblk->devblksize - offset); length -= avail; - wait_on_buffer(bh[k]); - if (!buffer_uptodate(bh[k])) - goto release_mutex; - stream->buf.in = bh[k]->b_data + offset; stream->buf.in_size = avail; stream->buf.in_pos = 0; offset = 0; } - if (stream->buf.out_pos == stream->buf.out_size - && page < pages) { - stream->buf.out = buffer[page++]; - stream->buf.out_pos = 0; - total += PAGE_CACHE_SIZE; + if (stream->buf.out_pos == stream->buf.out_size) { + stream->buf.out = squashfs_next_page(output); + if (stream->buf.out != NULL) { + stream->buf.out_pos = 0; + total += PAGE_CACHE_SIZE; + } } xz_err = xz_dec_run(stream->state, &stream->buf); @@ -147,23 +168,14 @@ static int squashfs_xz_uncompress(struct squashfs_sb_info *msblk, void **buffer, put_bh(bh[k++]); } while (xz_err == XZ_OK); - if (xz_err != XZ_STREAM_END) { - ERROR("xz_dec_run error, data probably corrupt\n"); - goto release_mutex; - } - - if (k < b) { - ERROR("xz_uncompress error, input remaining\n"); - goto release_mutex; - } + squashfs_finish_page(output); - total += stream->buf.out_pos; - mutex_unlock(&msblk->read_data_mutex); - return total; + if (xz_err != XZ_STREAM_END || k < b) + goto out; -release_mutex: - mutex_unlock(&msblk->read_data_mutex); + return total + stream->buf.out_pos; +out: for (; k < b; k++) put_bh(bh[k]); @@ -172,6 +184,7 @@ release_mutex: const struct squashfs_decompressor squashfs_xz_comp_ops = { .init = squashfs_xz_init, + .comp_opts = squashfs_xz_comp_opts, .free = squashfs_xz_free, .decompress = squashfs_xz_uncompress, .id = XZ_COMPRESSION, diff --git a/fs/squashfs/zlib_wrapper.c b/fs/squashfs/zlib_wrapper.c index 55d918fd2d86..8727caba6882 100644 --- a/fs/squashfs/zlib_wrapper.c +++ b/fs/squashfs/zlib_wrapper.c @@ -32,8 +32,9 @@ #include "squashfs_fs_sb.h" #include "squashfs.h" #include "decompressor.h" +#include "page_actor.h" -static void *zlib_init(struct squashfs_sb_info *dummy, void *buff, int len) +static void *zlib_init(struct squashfs_sb_info *dummy, void *buff) { z_stream *stream = kmalloc(sizeof(z_stream), GFP_KERNEL); if (stream == NULL) @@ -61,44 +62,37 @@ static void zlib_free(void *strm) } -static int zlib_uncompress(struct squashfs_sb_info *msblk, void **buffer, - struct buffer_head **bh, int b, int offset, int length, int srclength, - int pages) +static int zlib_uncompress(struct squashfs_sb_info *msblk, void *strm, + struct buffer_head **bh, int b, int offset, int length, + struct squashfs_page_actor *output) { - int zlib_err, zlib_init = 0; - int k = 0, page = 0; - z_stream *stream = msblk->stream; - - mutex_lock(&msblk->read_data_mutex); + int zlib_err, zlib_init = 0, k = 0; + z_stream *stream = strm; - stream->avail_out = 0; + stream->avail_out = PAGE_CACHE_SIZE; + stream->next_out = squashfs_first_page(output); stream->avail_in = 0; do { if (stream->avail_in == 0 && k < b) { int avail = min(length, msblk->devblksize - offset); length -= avail; - wait_on_buffer(bh[k]); - if (!buffer_uptodate(bh[k])) - goto release_mutex; - stream->next_in = bh[k]->b_data + offset; stream->avail_in = avail; offset = 0; } - if (stream->avail_out == 0 && page < pages) { - stream->next_out = buffer[page++]; - stream->avail_out = PAGE_CACHE_SIZE; + if (stream->avail_out == 0) { + stream->next_out = squashfs_next_page(output); + if (stream->next_out != NULL) + stream->avail_out = PAGE_CACHE_SIZE; } if (!zlib_init) { zlib_err = zlib_inflateInit(stream); if (zlib_err != Z_OK) { - ERROR("zlib_inflateInit returned unexpected " - "result 0x%x, srclength %d\n", - zlib_err, srclength); - goto release_mutex; + squashfs_finish_page(output); + goto out; } zlib_init = 1; } @@ -109,29 +103,21 @@ static int zlib_uncompress(struct squashfs_sb_info *msblk, void **buffer, put_bh(bh[k++]); } while (zlib_err == Z_OK); - if (zlib_err != Z_STREAM_END) { - ERROR("zlib_inflate error, data probably corrupt\n"); - goto release_mutex; - } + squashfs_finish_page(output); - zlib_err = zlib_inflateEnd(stream); - if (zlib_err != Z_OK) { - ERROR("zlib_inflate error, data probably corrupt\n"); - goto release_mutex; - } + if (zlib_err != Z_STREAM_END) + goto out; - if (k < b) { - ERROR("zlib_uncompress error, data remaining\n"); - goto release_mutex; - } + zlib_err = zlib_inflateEnd(stream); + if (zlib_err != Z_OK) + goto out; - length = stream->total_out; - mutex_unlock(&msblk->read_data_mutex); - return length; + if (k < b) + goto out; -release_mutex: - mutex_unlock(&msblk->read_data_mutex); + return stream->total_out; +out: for (; k < b; k++) put_bh(bh[k]); diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index c327d4ee1235..4742e58f3fc5 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -60,6 +60,7 @@ static int sysv_remount(struct super_block *sb, int *flags, char *data) { struct sysv_sb_info *sbi = SYSV_SB(sb); + sync_filesystem(sb); if (sbi->s_forced_ro) *flags |= MS_RDONLY; return 0; diff --git a/fs/timerfd.c b/fs/timerfd.c index 32b644f03690..0013142c0475 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -8,6 +8,7 @@ * */ +#include <linux/alarmtimer.h> #include <linux/file.h> #include <linux/poll.h> #include <linux/init.h> @@ -26,7 +27,10 @@ #include <linux/rcupdate.h> struct timerfd_ctx { - struct hrtimer tmr; + union { + struct hrtimer tmr; + struct alarm alarm; + } t; ktime_t tintv; ktime_t moffs; wait_queue_head_t wqh; @@ -41,14 +45,19 @@ struct timerfd_ctx { static LIST_HEAD(cancel_list); static DEFINE_SPINLOCK(cancel_lock); +static inline bool isalarm(struct timerfd_ctx *ctx) +{ + return ctx->clockid == CLOCK_REALTIME_ALARM || + ctx->clockid == CLOCK_BOOTTIME_ALARM; +} + /* * This gets called when the timer event triggers. We set the "expired" * flag, but we do not re-arm the timer (in case it's necessary, * tintv.tv64 != 0) until the timer is accessed. */ -static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr) +static void timerfd_triggered(struct timerfd_ctx *ctx) { - struct timerfd_ctx *ctx = container_of(htmr, struct timerfd_ctx, tmr); unsigned long flags; spin_lock_irqsave(&ctx->wqh.lock, flags); @@ -56,10 +65,25 @@ static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr) ctx->ticks++; wake_up_locked(&ctx->wqh); spin_unlock_irqrestore(&ctx->wqh.lock, flags); +} +static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr) +{ + struct timerfd_ctx *ctx = container_of(htmr, struct timerfd_ctx, + t.tmr); + timerfd_triggered(ctx); return HRTIMER_NORESTART; } +static enum alarmtimer_restart timerfd_alarmproc(struct alarm *alarm, + ktime_t now) +{ + struct timerfd_ctx *ctx = container_of(alarm, struct timerfd_ctx, + t.alarm); + timerfd_triggered(ctx); + return ALARMTIMER_NORESTART; +} + /* * Called when the clock was set to cancel the timers in the cancel * list. This will wake up processes waiting on these timers. The @@ -107,8 +131,9 @@ static bool timerfd_canceled(struct timerfd_ctx *ctx) static void timerfd_setup_cancel(struct timerfd_ctx *ctx, int flags) { - if (ctx->clockid == CLOCK_REALTIME && (flags & TFD_TIMER_ABSTIME) && - (flags & TFD_TIMER_CANCEL_ON_SET)) { + if ((ctx->clockid == CLOCK_REALTIME || + ctx->clockid == CLOCK_REALTIME_ALARM) && + (flags & TFD_TIMER_ABSTIME) && (flags & TFD_TIMER_CANCEL_ON_SET)) { if (!ctx->might_cancel) { ctx->might_cancel = true; spin_lock(&cancel_lock); @@ -124,7 +149,11 @@ static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx) { ktime_t remaining; - remaining = hrtimer_expires_remaining(&ctx->tmr); + if (isalarm(ctx)) + remaining = alarm_expires_remaining(&ctx->t.alarm); + else + remaining = hrtimer_expires_remaining(&ctx->t.tmr); + return remaining.tv64 < 0 ? ktime_set(0, 0): remaining; } @@ -142,11 +171,28 @@ static int timerfd_setup(struct timerfd_ctx *ctx, int flags, ctx->expired = 0; ctx->ticks = 0; ctx->tintv = timespec_to_ktime(ktmr->it_interval); - hrtimer_init(&ctx->tmr, clockid, htmode); - hrtimer_set_expires(&ctx->tmr, texp); - ctx->tmr.function = timerfd_tmrproc; + + if (isalarm(ctx)) { + alarm_init(&ctx->t.alarm, + ctx->clockid == CLOCK_REALTIME_ALARM ? + ALARM_REALTIME : ALARM_BOOTTIME, + timerfd_alarmproc); + } else { + hrtimer_init(&ctx->t.tmr, clockid, htmode); + hrtimer_set_expires(&ctx->t.tmr, texp); + ctx->t.tmr.function = timerfd_tmrproc; + } + if (texp.tv64 != 0) { - hrtimer_start(&ctx->tmr, texp, htmode); + if (isalarm(ctx)) { + if (flags & TFD_TIMER_ABSTIME) + alarm_start(&ctx->t.alarm, texp); + else + alarm_start_relative(&ctx->t.alarm, texp); + } else { + hrtimer_start(&ctx->t.tmr, texp, htmode); + } + if (timerfd_canceled(ctx)) return -ECANCELED; } @@ -158,7 +204,11 @@ static int timerfd_release(struct inode *inode, struct file *file) struct timerfd_ctx *ctx = file->private_data; timerfd_remove_cancel(ctx); - hrtimer_cancel(&ctx->tmr); + + if (isalarm(ctx)) + alarm_cancel(&ctx->t.alarm); + else + hrtimer_cancel(&ctx->t.tmr); kfree_rcu(ctx, rcu); return 0; } @@ -215,9 +265,15 @@ static ssize_t timerfd_read(struct file *file, char __user *buf, size_t count, * callback to avoid DoS attacks specifying a very * short timer period. */ - ticks += hrtimer_forward_now(&ctx->tmr, - ctx->tintv) - 1; - hrtimer_restart(&ctx->tmr); + if (isalarm(ctx)) { + ticks += alarm_forward_now( + &ctx->t.alarm, ctx->tintv) - 1; + alarm_restart(&ctx->t.alarm); + } else { + ticks += hrtimer_forward_now(&ctx->t.tmr, + ctx->tintv) - 1; + hrtimer_restart(&ctx->t.tmr); + } } ctx->expired = 0; ctx->ticks = 0; @@ -259,7 +315,10 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags) if ((flags & ~TFD_CREATE_FLAGS) || (clockid != CLOCK_MONOTONIC && - clockid != CLOCK_REALTIME)) + clockid != CLOCK_REALTIME && + clockid != CLOCK_REALTIME_ALARM && + clockid != CLOCK_BOOTTIME && + clockid != CLOCK_BOOTTIME_ALARM)) return -EINVAL; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); @@ -268,7 +327,15 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags) init_waitqueue_head(&ctx->wqh); ctx->clockid = clockid; - hrtimer_init(&ctx->tmr, clockid, HRTIMER_MODE_ABS); + + if (isalarm(ctx)) + alarm_init(&ctx->t.alarm, + ctx->clockid == CLOCK_REALTIME_ALARM ? + ALARM_REALTIME : ALARM_BOOTTIME, + timerfd_alarmproc); + else + hrtimer_init(&ctx->t.tmr, clockid, HRTIMER_MODE_ABS); + ctx->moffs = ktime_get_monotonic_offset(); ufd = anon_inode_getfd("[timerfd]", &timerfd_fops, ctx, @@ -305,8 +372,14 @@ static int do_timerfd_settime(int ufd, int flags, */ for (;;) { spin_lock_irq(&ctx->wqh.lock); - if (hrtimer_try_to_cancel(&ctx->tmr) >= 0) - break; + + if (isalarm(ctx)) { + if (alarm_try_to_cancel(&ctx->t.alarm) >= 0) + break; + } else { + if (hrtimer_try_to_cancel(&ctx->t.tmr) >= 0) + break; + } spin_unlock_irq(&ctx->wqh.lock); cpu_relax(); } @@ -317,8 +390,12 @@ static int do_timerfd_settime(int ufd, int flags, * We do not update "ticks" and "expired" since the timer will be * re-programmed again in the following timerfd_setup() call. */ - if (ctx->expired && ctx->tintv.tv64) - hrtimer_forward_now(&ctx->tmr, ctx->tintv); + if (ctx->expired && ctx->tintv.tv64) { + if (isalarm(ctx)) + alarm_forward_now(&ctx->t.alarm, ctx->tintv); + else + hrtimer_forward_now(&ctx->t.tmr, ctx->tintv); + } old->it_value = ktime_to_timespec(timerfd_get_remaining(ctx)); old->it_interval = ktime_to_timespec(ctx->tintv); @@ -345,9 +422,18 @@ static int do_timerfd_gettime(int ufd, struct itimerspec *t) spin_lock_irq(&ctx->wqh.lock); if (ctx->expired && ctx->tintv.tv64) { ctx->expired = 0; - ctx->ticks += - hrtimer_forward_now(&ctx->tmr, ctx->tintv) - 1; - hrtimer_restart(&ctx->tmr); + + if (isalarm(ctx)) { + ctx->ticks += + alarm_forward_now( + &ctx->t.alarm, ctx->tintv) - 1; + alarm_restart(&ctx->t.alarm); + } else { + ctx->ticks += + hrtimer_forward_now(&ctx->t.tmr, ctx->tintv) + - 1; + hrtimer_restart(&ctx->t.tmr); + } } t->it_value = ktime_to_timespec(timerfd_get_remaining(ctx)); t->it_interval = ktime_to_timespec(ctx->tintv); diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 05115d719408..3bf098a82dac 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1840,6 +1840,7 @@ static int ubifs_remount_fs(struct super_block *sb, int *flags, char *data) int err; struct ubifs_info *c = sb->s_fs_info; + sync_filesystem(sb); dbg_gen("old flags %#lx, new flags %#x", sb->s_flags, *flags); err = ubifs_parse_options(c, data, 1); diff --git a/fs/udf/super.c b/fs/udf/super.c index 839a2bad7f45..32f5297dfbab 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -629,6 +629,7 @@ static int udf_remount_fs(struct super_block *sb, int *flags, char *options) struct udf_options uopt; struct udf_sb_info *sbi = UDF_SB(sb); int error = 0; + sync_filesystem(sb); if (sbi->s_lvid_bh) { int write_rev = le16_to_cpu(udf_sb_lvidiu(sbi)->minUDFWriteRev); diff --git a/fs/ufs/super.c b/fs/ufs/super.c index 329f2f53b7ed..b8c6791f046f 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -1280,6 +1280,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) unsigned new_mount_opt, ufstype; unsigned flags; + sync_filesystem(sb); lock_ufs(sb); mutex_lock(&UFS_SB(sb)->s_lock); uspi = UFS_SB(sb)->s_uspi; diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 3033ba5e9762..478c0ad5e36f 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1218,6 +1218,7 @@ xfs_fs_remount( char *p; int error; + sync_filesystem(sb); while ((p = strsep(&options, ",")) != NULL) { int token; |