diff options
Diffstat (limited to 'fs')
121 files changed, 2526 insertions, 2622 deletions
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 041c5269228..68bf2af6c38 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -178,7 +178,7 @@ v9fs_file_read(struct file *filp, char __user *udata, size_t count, int ret; struct p9_fid *fid; - P9_DPRINTK(P9_DEBUG_VFS, "count %d offset %lld\n", count, *offset); + P9_DPRINTK(P9_DEBUG_VFS, "count %zu offset %lld\n", count, *offset); fid = filp->private_data; if (count > (fid->clnt->msize - P9_IOHDRSZ)) diff --git a/fs/Kconfig b/fs/Kconfig index e282002b94d..522469a7eca 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -22,9 +22,10 @@ source "fs/jbd2/Kconfig" config FS_MBCACHE # Meta block cache for Extended Attributes (ext2/ext3/ext4) tristate - depends on EXT2_FS_XATTR || EXT3_FS_XATTR || EXT4_FS_XATTR - default y if EXT2_FS=y || EXT3_FS=y || EXT4_FS=y - default m if EXT2_FS=m || EXT3_FS=m || EXT4_FS=m + default y if EXT2_FS=y && EXT2_FS_XATTR + default y if EXT3_FS=y && EXT3_FS_XATTR + default y if EXT4_FS=y && EXT4_FS_XATTR + default m if EXT2_FS_XATTR || EXT3_FS_XATTR || EXT4_FS_XATTR config REISERFS_FS tristate "Reiserfs support" @@ -403,7 +404,7 @@ config AUTOFS4_FS N here. config FUSE_FS - tristate "Filesystem in Userspace support" + tristate "FUSE (Filesystem in Userspace) support" help With FUSE it is possible to implement a fully functional filesystem in a userspace program. diff --git a/fs/afs/dir.c b/fs/afs/dir.c index dfda03d4397..99cf390641f 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -45,6 +45,7 @@ const struct file_operations afs_dir_file_operations = { .release = afs_release, .readdir = afs_readdir, .lock = afs_lock, + .llseek = generic_file_llseek, }; const struct inode_operations afs_dir_inode_operations = { diff --git a/fs/attr.c b/fs/attr.c index 26c71ba1eed..7a83819f6ba 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -159,17 +159,17 @@ int notify_change(struct dentry * dentry, struct iattr * attr) if (!(attr->ia_valid & ~(ATTR_KILL_SUID | ATTR_KILL_SGID))) return 0; + error = security_inode_setattr(dentry, attr); + if (error) + return error; + if (ia_valid & ATTR_SIZE) down_write(&dentry->d_inode->i_alloc_sem); if (inode->i_op && inode->i_op->setattr) { - error = security_inode_setattr(dentry, attr); - if (!error) - error = inode->i_op->setattr(dentry, attr); + error = inode->i_op->setattr(dentry, attr); } else { error = inode_change_ok(inode, attr); - if (!error) - error = security_inode_setattr(dentry, attr); if (!error) { if ((ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) || (ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid)) diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c index ed8feb052df..daae463068e 100644 --- a/fs/bfs/dir.c +++ b/fs/bfs/dir.c @@ -80,6 +80,7 @@ const struct file_operations bfs_dir_operations = { .read = generic_read_dir, .readdir = bfs_readdir, .fsync = file_fsync, + .llseek = generic_file_llseek, }; extern void dump_imap(const char *, struct super_block *); diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index e2159063198..8fcfa398d35 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1341,20 +1341,15 @@ static void fill_prstatus(struct elf_prstatus *prstatus, prstatus->pr_pgrp = task_pgrp_vnr(p); prstatus->pr_sid = task_session_vnr(p); if (thread_group_leader(p)) { + struct task_cputime cputime; + /* - * This is the record for the group leader. Add in the - * cumulative times of previous dead threads. This total - * won't include the time of each live thread whose state - * is included in the core dump. The final total reported - * to our parent process when it calls wait4 will include - * those sums as well as the little bit more time it takes - * this and each other thread to finish dying after the - * core dump synchronization phase. + * This is the record for the group leader. It shows the + * group-wide total, not its individual thread total. */ - cputime_to_timeval(cputime_add(p->utime, p->signal->utime), - &prstatus->pr_utime); - cputime_to_timeval(cputime_add(p->stime, p->signal->stime), - &prstatus->pr_stime); + thread_group_cputime(p, &cputime); + cputime_to_timeval(cputime.utime, &prstatus->pr_utime); + cputime_to_timeval(cputime.stime, &prstatus->pr_stime); } else { cputime_to_timeval(p->utime, &prstatus->pr_utime); cputime_to_timeval(p->stime, &prstatus->pr_stime); diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 0e8367c5462..5b5424cb339 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1390,20 +1390,15 @@ static void fill_prstatus(struct elf_prstatus *prstatus, prstatus->pr_pgrp = task_pgrp_vnr(p); prstatus->pr_sid = task_session_vnr(p); if (thread_group_leader(p)) { + struct task_cputime cputime; + /* - * This is the record for the group leader. Add in the - * cumulative times of previous dead threads. This total - * won't include the time of each live thread whose state - * is included in the core dump. The final total reported - * to our parent process when it calls wait4 will include - * those sums as well as the little bit more time it takes - * this and each other thread to finish dying after the - * core dump synchronization phase. + * This is the record for the group leader. It shows the + * group-wide total, not its individual thread total. */ - cputime_to_timeval(cputime_add(p->utime, p->signal->utime), - &prstatus->pr_utime); - cputime_to_timeval(cputime_add(p->stime, p->signal->stime), - &prstatus->pr_stime); + thread_group_cputime(p, &cputime); + cputime_to_timeval(cputime.utime, &prstatus->pr_utime); + cputime_to_timeval(cputime.stime, &prstatus->pr_stime); } else { cputime_to_timeval(p->utime, &prstatus->pr_utime); cputime_to_timeval(p->stime, &prstatus->pr_stime); diff --git a/fs/block_dev.c b/fs/block_dev.c index 218408eed1b..88a776fa0ef 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -840,13 +840,12 @@ EXPORT_SYMBOL_GPL(bd_release_from_disk); * to be used for internal purposes. If you ever need it - reconsider * your API. */ -struct block_device *open_by_devnum(dev_t dev, unsigned mode) +struct block_device *open_by_devnum(dev_t dev, fmode_t mode) { struct block_device *bdev = bdget(dev); int err = -ENOMEM; - int flags = mode & FMODE_WRITE ? O_RDWR : O_RDONLY; if (bdev) - err = blkdev_get(bdev, mode, flags); + err = blkdev_get(bdev, mode); return err ? ERR_PTR(err) : bdev; } @@ -975,9 +974,7 @@ void bd_set_size(struct block_device *bdev, loff_t size) } EXPORT_SYMBOL(bd_set_size); -static int __blkdev_get(struct block_device *bdev, mode_t mode, unsigned flags, - int for_part); -static int __blkdev_put(struct block_device *bdev, int for_part); +static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part); /* * bd_mutex locking: @@ -986,7 +983,7 @@ static int __blkdev_put(struct block_device *bdev, int for_part); * mutex_lock_nested(whole->bd_mutex, 1) */ -static int do_open(struct block_device *bdev, struct file *file, int for_part) +static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) { struct gendisk *disk; struct hd_struct *part = NULL; @@ -994,9 +991,9 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part) int partno; int perm = 0; - if (file->f_mode & FMODE_READ) + if (mode & FMODE_READ) perm |= MAY_READ; - if (file->f_mode & FMODE_WRITE) + if (mode & FMODE_WRITE) perm |= MAY_WRITE; /* * hooks: /n/, see "layering violations". @@ -1008,7 +1005,6 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part) } ret = -ENXIO; - file->f_mapping = bdev->bd_inode->i_mapping; lock_kernel(); @@ -1027,7 +1023,7 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part) if (!partno) { struct backing_dev_info *bdi; if (disk->fops->open) { - ret = disk->fops->open(bdev->bd_inode, file); + ret = disk->fops->open(bdev, mode); if (ret) goto out_clear; } @@ -1047,7 +1043,7 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part) if (!whole) goto out_clear; BUG_ON(for_part); - ret = __blkdev_get(whole, file->f_mode, file->f_flags, 1); + ret = __blkdev_get(whole, mode, 1); if (ret) goto out_clear; bdev->bd_contains = whole; @@ -1068,7 +1064,7 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part) disk = NULL; if (bdev->bd_contains == bdev) { if (bdev->bd_disk->fops->open) { - ret = bdev->bd_disk->fops->open(bdev->bd_inode, file); + ret = bdev->bd_disk->fops->open(bdev, mode); if (ret) goto out_unlock_bdev; } @@ -1088,7 +1084,7 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part) bdev->bd_part = NULL; bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info; if (bdev != bdev->bd_contains) - __blkdev_put(bdev->bd_contains, 1); + __blkdev_put(bdev->bd_contains, mode, 1); bdev->bd_contains = NULL; out_unlock_bdev: mutex_unlock(&bdev->bd_mutex); @@ -1104,28 +1100,9 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part) return ret; } -static int __blkdev_get(struct block_device *bdev, mode_t mode, unsigned flags, - int for_part) +int blkdev_get(struct block_device *bdev, fmode_t mode) { - /* - * This crockload is due to bad choice of ->open() type. - * It will go away. - * For now, block device ->open() routine must _not_ - * examine anything in 'inode' argument except ->i_rdev. - */ - struct file fake_file = {}; - struct dentry fake_dentry = {}; - fake_file.f_mode = mode; - fake_file.f_flags = flags; - fake_file.f_path.dentry = &fake_dentry; - fake_dentry.d_inode = bdev->bd_inode; - - return do_open(bdev, &fake_file, for_part); -} - -int blkdev_get(struct block_device *bdev, mode_t mode, unsigned flags) -{ - return __blkdev_get(bdev, mode, flags, 0); + return __blkdev_get(bdev, mode, 0); } EXPORT_SYMBOL(blkdev_get); @@ -1142,28 +1119,36 @@ static int blkdev_open(struct inode * inode, struct file * filp) */ filp->f_flags |= O_LARGEFILE; + if (filp->f_flags & O_NDELAY) + filp->f_mode |= FMODE_NDELAY; + if (filp->f_flags & O_EXCL) + filp->f_mode |= FMODE_EXCL; + if ((filp->f_flags & O_ACCMODE) == 3) + filp->f_mode |= FMODE_WRITE_IOCTL; + bdev = bd_acquire(inode); if (bdev == NULL) return -ENOMEM; - res = do_open(bdev, filp, 0); + filp->f_mapping = bdev->bd_inode->i_mapping; + + res = blkdev_get(bdev, filp->f_mode); if (res) return res; - if (!(filp->f_flags & O_EXCL) ) + if (!(filp->f_mode & FMODE_EXCL)) return 0; if (!(res = bd_claim(bdev, filp))) return 0; - blkdev_put(bdev); + blkdev_put(bdev, filp->f_mode); return res; } -static int __blkdev_put(struct block_device *bdev, int for_part) +static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) { int ret = 0; - struct inode *bd_inode = bdev->bd_inode; struct gendisk *disk = bdev->bd_disk; struct block_device *victim = NULL; @@ -1178,7 +1163,7 @@ static int __blkdev_put(struct block_device *bdev, int for_part) } if (bdev->bd_contains == bdev) { if (disk->fops->release) - ret = disk->fops->release(bd_inode, NULL); + ret = disk->fops->release(disk, mode); } if (!bdev->bd_openers) { struct module *owner = disk->fops->owner; @@ -1197,13 +1182,13 @@ static int __blkdev_put(struct block_device *bdev, int for_part) mutex_unlock(&bdev->bd_mutex); bdput(bdev); if (victim) - __blkdev_put(victim, 1); + __blkdev_put(victim, mode, 1); return ret; } -int blkdev_put(struct block_device *bdev) +int blkdev_put(struct block_device *bdev, fmode_t mode) { - return __blkdev_put(bdev, 0); + return __blkdev_put(bdev, mode, 0); } EXPORT_SYMBOL(blkdev_put); @@ -1212,12 +1197,16 @@ static int blkdev_close(struct inode * inode, struct file * filp) struct block_device *bdev = I_BDEV(filp->f_mapping->host); if (bdev->bd_holder == filp) bd_release(bdev); - return blkdev_put(bdev); + return blkdev_put(bdev, filp->f_mode); } static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg) { - return blkdev_ioctl(file->f_mapping->host, file, cmd, arg); + struct block_device *bdev = I_BDEV(file->f_mapping->host); + fmode_t mode = file->f_mode; + if (file->f_flags & O_NDELAY) + mode |= FMODE_NDELAY_NOW; + return blkdev_ioctl(bdev, mode, cmd, arg); } static const struct address_space_operations def_blk_aops = { @@ -1253,7 +1242,7 @@ int ioctl_by_bdev(struct block_device *bdev, unsigned cmd, unsigned long arg) int res; mm_segment_t old_fs = get_fs(); set_fs(KERNEL_DS); - res = blkdev_ioctl(bdev->bd_inode, NULL, cmd, arg); + res = blkdev_ioctl(bdev, 0, cmd, arg); set_fs(old_fs); return res; } @@ -1268,33 +1257,33 @@ EXPORT_SYMBOL(ioctl_by_bdev); * namespace if possible and return it. Return ERR_PTR(error) * otherwise. */ -struct block_device *lookup_bdev(const char *path) +struct block_device *lookup_bdev(const char *pathname) { struct block_device *bdev; struct inode *inode; - struct nameidata nd; + struct path path; int error; - if (!path || !*path) + if (!pathname || !*pathname) return ERR_PTR(-EINVAL); - error = path_lookup(path, LOOKUP_FOLLOW, &nd); + error = kern_path(pathname, LOOKUP_FOLLOW, &path); if (error) return ERR_PTR(error); - inode = nd.path.dentry->d_inode; + inode = path.dentry->d_inode; error = -ENOTBLK; if (!S_ISBLK(inode->i_mode)) goto fail; error = -EACCES; - if (nd.path.mnt->mnt_flags & MNT_NODEV) + if (path.mnt->mnt_flags & MNT_NODEV) goto fail; error = -ENOMEM; bdev = bd_acquire(inode); if (!bdev) goto fail; out: - path_put(&nd.path); + path_put(&path); return bdev; fail: bdev = ERR_PTR(error); @@ -1303,32 +1292,29 @@ fail: EXPORT_SYMBOL(lookup_bdev); /** - * open_bdev_excl - open a block device by name and set it up for use + * open_bdev_exclusive - open a block device by name and set it up for use * * @path: special file representing the block device - * @flags: %MS_RDONLY for opening read-only + * @mode: FMODE_... combination to pass be used * @holder: owner for exclusion * * Open the blockdevice described by the special file at @path, claim it * for the @holder. */ -struct block_device *open_bdev_excl(const char *path, int flags, void *holder) +struct block_device *open_bdev_exclusive(const char *path, fmode_t mode, void *holder) { struct block_device *bdev; - mode_t mode = FMODE_READ; int error = 0; bdev = lookup_bdev(path); if (IS_ERR(bdev)) return bdev; - if (!(flags & MS_RDONLY)) - mode |= FMODE_WRITE; - error = blkdev_get(bdev, mode, 0); + error = blkdev_get(bdev, mode); if (error) return ERR_PTR(error); error = -EACCES; - if (!(flags & MS_RDONLY) && bdev_read_only(bdev)) + if ((mode & FMODE_WRITE) && bdev_read_only(bdev)) goto blkdev_put; error = bd_claim(bdev, holder); if (error) @@ -1337,26 +1323,27 @@ struct block_device *open_bdev_excl(const char *path, int flags, void *holder) return bdev; blkdev_put: - blkdev_put(bdev); + blkdev_put(bdev, mode); return ERR_PTR(error); } -EXPORT_SYMBOL(open_bdev_excl); +EXPORT_SYMBOL(open_bdev_exclusive); /** - * close_bdev_excl - release a blockdevice openen by open_bdev_excl() + * close_bdev_exclusive - close a blockdevice opened by open_bdev_exclusive() * * @bdev: blockdevice to close + * @mode: mode, must match that used to open. * - * This is the counterpart to open_bdev_excl(). + * This is the counterpart to open_bdev_exclusive(). */ -void close_bdev_excl(struct block_device *bdev) +void close_bdev_exclusive(struct block_device *bdev, fmode_t mode) { bd_release(bdev); - blkdev_put(bdev); + blkdev_put(bdev, mode); } -EXPORT_SYMBOL(close_bdev_excl); +EXPORT_SYMBOL(close_bdev_exclusive); int __invalidate_device(struct block_device *bdev) { diff --git a/fs/char_dev.c b/fs/char_dev.c index 262fa10e213..700697a7261 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -386,15 +386,22 @@ static int chrdev_open(struct inode *inode, struct file *filp) cdev_put(new); if (ret) return ret; + + ret = -ENXIO; filp->f_op = fops_get(p->ops); - if (!filp->f_op) { - cdev_put(p); - return -ENXIO; - } - if (filp->f_op->open) + if (!filp->f_op) + goto out_cdev_put; + + if (filp->f_op->open) { ret = filp->f_op->open(inode,filp); - if (ret) - cdev_put(p); + if (ret) + goto out_cdev_put; + } + + return 0; + + out_cdev_put: + cdev_put(p); return ret; } diff --git a/fs/cifs/CHANGES b/fs/cifs/CHANGES index 06e521a945c..8f528ea24c4 100644 --- a/fs/cifs/CHANGES +++ b/fs/cifs/CHANGES @@ -1,3 +1,11 @@ +Version 1.55 +------------ +Various fixes to make delete of open files behavior more predictable +(when delete of an open file fails we mark the file as "delete-on-close" +in a way that more servers accept, but only if we can first rename the +file to a temporary name). Add experimental support for more safely +handling fcntl(F_SETLEASE). + Version 1.54 ------------ Fix premature write failure on congested networks (we would give up @@ -13,6 +21,7 @@ on dns_upcall (resolving DFS referralls). Fix plain text password authentication (requires setting SecurityFlags to 0x30030 to enable lanman and plain text though). Fix writes to be at correct offset when file is open with O_APPEND and file is on a directio (forcediretio) mount. +Fix bug in rewinding readdir directory searches. Add nodfs mount option. Version 1.53 ------------ diff --git a/fs/cifs/README b/fs/cifs/README index bd2343d4c6a..a439dc1739b 100644 --- a/fs/cifs/README +++ b/fs/cifs/README @@ -463,6 +463,9 @@ A partial list of the supported mount options follows: with cifs style mandatory byte range locks (and most cifs servers do not yet support requesting advisory byte range locks). + nodfs Disable DFS (global name space support) even if the + server claims to support it. This can help work around + a problem with parsing of DFS paths with Samba 3.0.24 server. remount remount the share (often used to change from ro to rw mounts or vice versa) cifsacl Report mode bits (e.g. on stat) based on the Windows ACL for @@ -488,6 +491,19 @@ A partial list of the supported mount options follows: Note that this differs from the sign mount option in that it causes encryption of data sent over this mounted share but other shares mounted to the same server are unaffected. + locallease This option is rarely needed. Fcntl F_SETLEASE is + used by some applications such as Samba and NFSv4 server to + check to see whether a file is cacheable. CIFS has no way + to explicitly request a lease, but can check whether a file + is cacheable (oplocked). Unfortunately, even if a file + is not oplocked, it could still be cacheable (ie cifs client + could grant fcntl leases if no other local processes are using + the file) for cases for example such as when the server does not + support oplocks and the user is sure that the only updates to + the file will be from this client. Specifying this mount option + will allow the cifs client to check for leases (only) locally + for files which are not oplocked instead of denying leases + in that case. (EXPERIMENTAL) sec Security mode. Allowed values are: none attempt to connection as a null user (no name) krb5 Use Kerberos version 5 authentication @@ -638,6 +654,9 @@ requires enabling CONFIG_CIFS_EXPERIMENTAL cifsacl support needed to retrieve approximated mode bits based on the contents on the CIFS ACL. + lease support: cifs will check the oplock state before calling into + the vfs to see if we can grant a lease on a file. + DNOTIFY fcntl: needed for support of directory change notification and perhaps later for file leases) diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 25ecbd5b040..ac5915d61dc 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -275,9 +275,12 @@ static int cifs_permission(struct inode *inode, int mask) cifs_sb = CIFS_SB(inode->i_sb); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) - return 0; - else /* file mode might have been restricted at mount time + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) { + if ((mask & MAY_EXEC) && !execute_ok(inode)) + return -EACCES; + else + return 0; + } else /* file mode might have been restricted at mount time on the client (above and beyond ACL on servers) for servers which do not support setting and viewing mode bits, so allowing client to check permissions is useful */ @@ -309,6 +312,7 @@ cifs_alloc_inode(struct super_block *sb) file data or metadata */ cifs_inode->clientCanCacheRead = false; cifs_inode->clientCanCacheAll = false; + cifs_inode->delete_pending = false; cifs_inode->vfs_inode.i_blkbits = 14; /* 2**14 = CIFS_MAX_MSGSIZE */ /* Can not set i_flags here - they get immediately overwritten @@ -617,6 +621,37 @@ static loff_t cifs_llseek(struct file *file, loff_t offset, int origin) return generic_file_llseek_unlocked(file, offset, origin); } +#ifdef CONFIG_CIFS_EXPERIMENTAL +static int cifs_setlease(struct file *file, long arg, struct file_lock **lease) +{ + /* note that this is called by vfs setlease with the BKL held + although I doubt that BKL is needed here in cifs */ + struct inode *inode = file->f_path.dentry->d_inode; + + if (!(S_ISREG(inode->i_mode))) + return -EINVAL; + + /* check if file is oplocked */ + if (((arg == F_RDLCK) && + (CIFS_I(inode)->clientCanCacheRead)) || + ((arg == F_WRLCK) && + (CIFS_I(inode)->clientCanCacheAll))) + return generic_setlease(file, arg, lease); + else if (CIFS_SB(inode->i_sb)->tcon->local_lease && + !CIFS_I(inode)->clientCanCacheRead) + /* If the server claims to support oplock on this + file, then we still need to check oplock even + if the local_lease mount option is set, but there + are servers which do not support oplock for which + this mount option may be useful if the user + knows that the file won't be changed on the server + by anyone else */ + return generic_setlease(file, arg, lease); + else + return -EAGAIN; +} +#endif + struct file_system_type cifs_fs_type = { .owner = THIS_MODULE, .name = "cifs", @@ -695,6 +730,7 @@ const struct file_operations cifs_file_ops = { #ifdef CONFIG_CIFS_EXPERIMENTAL .dir_notify = cifs_dir_notify, + .setlease = cifs_setlease, #endif /* CONFIG_CIFS_EXPERIMENTAL */ }; @@ -715,6 +751,7 @@ const struct file_operations cifs_file_direct_ops = { .llseek = cifs_llseek, #ifdef CONFIG_CIFS_EXPERIMENTAL .dir_notify = cifs_dir_notify, + .setlease = cifs_setlease, #endif /* CONFIG_CIFS_EXPERIMENTAL */ }; const struct file_operations cifs_file_nobrl_ops = { @@ -735,6 +772,7 @@ const struct file_operations cifs_file_nobrl_ops = { #ifdef CONFIG_CIFS_EXPERIMENTAL .dir_notify = cifs_dir_notify, + .setlease = cifs_setlease, #endif /* CONFIG_CIFS_EXPERIMENTAL */ }; @@ -754,6 +792,7 @@ const struct file_operations cifs_file_direct_nobrl_ops = { .llseek = cifs_llseek, #ifdef CONFIG_CIFS_EXPERIMENTAL .dir_notify = cifs_dir_notify, + .setlease = cifs_setlease, #endif /* CONFIG_CIFS_EXPERIMENTAL */ }; @@ -765,6 +804,7 @@ const struct file_operations cifs_dir_ops = { .dir_notify = cifs_dir_notify, #endif /* CONFIG_CIFS_EXPERIMENTAL */ .unlocked_ioctl = cifs_ioctl, + .llseek = generic_file_llseek, }; static void @@ -945,6 +985,12 @@ static int cifs_oplock_thread(void *dummyarg) the call */ /* mutex_lock(&inode->i_mutex);*/ if (S_ISREG(inode->i_mode)) { +#ifdef CONFIG_CIFS_EXPERIMENTAL + if (CIFS_I(inode)->clientCanCacheAll == 0) + break_lease(inode, FMODE_READ); + else if (CIFS_I(inode)->clientCanCacheRead == 0) + break_lease(inode, FMODE_WRITE); +#endif rc = filemap_fdatawrite(inode->i_mapping); if (CIFS_I(inode)->clientCanCacheRead == 0) { waitrc = filemap_fdatawait( diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index f7b4a5cd837..074de0b5064 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -101,5 +101,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* EXPERIMENTAL */ -#define CIFS_VERSION "1.54" +#define CIFS_VERSION "1.55" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 0d22479d99b..c791e5b5a91 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -285,6 +285,7 @@ struct cifsTconInfo { bool seal:1; /* transport encryption for this mounted share */ bool unix_ext:1; /* if false disable Linux extensions to CIFS protocol for this mount even if server would support */ + bool local_lease:1; /* check leases (only) on local system not remote */ /* BB add field for back pointer to sb struct(s)? */ }; @@ -353,6 +354,7 @@ struct cifsInodeInfo { bool clientCanCacheRead:1; /* read oplock */ bool clientCanCacheAll:1; /* read and writebehind oplock */ bool oplockPending:1; + bool delete_pending:1; /* DELETE_ON_CLOSE is set */ struct inode vfs_inode; }; diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 6f4ffe15d68..843a85fb8b9 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -1309,6 +1309,7 @@ OldOpenRetry: cpu_to_le64(le32_to_cpu(pSMBr->EndOfFile)); pfile_info->EndOfFile = pfile_info->AllocationSize; pfile_info->NumberOfLinks = cpu_to_le32(1); + pfile_info->DeletePending = 0; } } @@ -1410,6 +1411,7 @@ openRetry: pfile_info->AllocationSize = pSMBr->AllocationSize; pfile_info->EndOfFile = pSMBr->EndOfFile; pfile_info->NumberOfLinks = cpu_to_le32(1); + pfile_info->DeletePending = 0; } } diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 4c13bcdb92a..71b7661e226 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -90,6 +90,8 @@ struct smb_vol { bool nocase:1; /* request case insensitive filenames */ bool nobrl:1; /* disable sending byte range locks to srv */ bool seal:1; /* request transport encryption on share */ + bool nodfs:1; /* Do not request DFS, even if available */ + bool local_lease:1; /* check leases only on local system, not remote */ unsigned int rsize; unsigned int wsize; unsigned int sockopt; @@ -124,7 +126,7 @@ cifs_reconnect(struct TCP_Server_Info *server) struct mid_q_entry *mid_entry; spin_lock(&GlobalMid_Lock); - if (kthread_should_stop()) { + if (server->tcpStatus == CifsExiting) { /* the demux thread will exit normally next time through the loop */ spin_unlock(&GlobalMid_Lock); @@ -184,7 +186,8 @@ cifs_reconnect(struct TCP_Server_Info *server) spin_unlock(&GlobalMid_Lock); up(&server->tcpSem); - while ((!kthread_should_stop()) && (server->tcpStatus != CifsGood)) { + while ((server->tcpStatus != CifsExiting) && + (server->tcpStatus != CifsGood)) { try_to_freeze(); if (server->protocolType == IPV6) { rc = ipv6_connect(&server->addr.sockAddr6, @@ -201,7 +204,7 @@ cifs_reconnect(struct TCP_Server_Info *server) } else { atomic_inc(&tcpSesReconnectCount); spin_lock(&GlobalMid_Lock); - if (!kthread_should_stop()) + if (server->tcpStatus != CifsExiting) server->tcpStatus = CifsGood; server->sequence_number = 0; spin_unlock(&GlobalMid_Lock); @@ -356,7 +359,7 @@ cifs_demultiplex_thread(struct TCP_Server_Info *server) GFP_KERNEL); set_freezable(); - while (!kthread_should_stop()) { + while (server->tcpStatus != CifsExiting) { if (try_to_freeze()) continue; if (bigbuf == NULL) { @@ -397,7 +400,7 @@ incomplete_rcv: kernel_recvmsg(csocket, &smb_msg, &iov, 1, pdu_length, 0 /* BB other flags? */); - if (kthread_should_stop()) { + if (server->tcpStatus == CifsExiting) { break; } else if (server->tcpStatus == CifsNeedReconnect) { cFYI(1, ("Reconnect after server stopped responding")); @@ -522,7 +525,7 @@ incomplete_rcv: total_read += length) { length = kernel_recvmsg(csocket, &smb_msg, &iov, 1, pdu_length - total_read, 0); - if (kthread_should_stop() || + if ((server->tcpStatus == CifsExiting) || (length == -EINTR)) { /* then will exit */ reconnect = 2; @@ -651,14 +654,6 @@ multi_t2_fnd: spin_unlock(&GlobalMid_Lock); wake_up_all(&server->response_q); - /* don't exit until kthread_stop is called */ - set_current_state(TASK_UNINTERRUPTIBLE); - while (!kthread_should_stop()) { - schedule(); - set_current_state(TASK_UNINTERRUPTIBLE); - } - set_current_state(TASK_RUNNING); - /* check if we have blocked requests that need to free */ /* Note that cifs_max_pending is normally 50, but can be set at module install time to as little as two */ @@ -755,6 +750,7 @@ multi_t2_fnd: write_unlock(&GlobalSMBSeslock); kfree(server->hostname); + task_to_wake = xchg(&server->tsk, NULL); kfree(server); length = atomic_dec_return(&tcpSesAllocCount); @@ -762,6 +758,16 @@ multi_t2_fnd: mempool_resize(cifs_req_poolp, length + cifs_min_rcv, GFP_KERNEL); + /* if server->tsk was NULL then wait for a signal before exiting */ + if (!task_to_wake) { + set_current_state(TASK_INTERRUPTIBLE); + while (!signal_pending(current)) { + schedule(); + set_current_state(TASK_INTERRUPTIBLE); + } + set_current_state(TASK_RUNNING); + } + return 0; } @@ -1218,6 +1224,8 @@ cifs_parse_mount_options(char *options, const char *devname, vol->sfu_emul = 1; } else if (strnicmp(data, "nosfu", 5) == 0) { vol->sfu_emul = 0; + } else if (strnicmp(data, "nodfs", 5) == 0) { + vol->nodfs = 1; } else if (strnicmp(data, "posixpaths", 10) == 0) { vol->posix_paths = 1; } else if (strnicmp(data, "noposixpaths", 12) == 0) { @@ -1268,6 +1276,10 @@ cifs_parse_mount_options(char *options, const char *devname, vol->no_psx_acl = 0; } else if (strnicmp(data, "noacl", 5) == 0) { vol->no_psx_acl = 1; +#ifdef CONFIG_CIFS_EXPERIMENTAL + } else if (strnicmp(data, "locallease", 6) == 0) { + vol->local_lease = 1; +#endif } else if (strnicmp(data, "sign", 4) == 0) { vol->secFlg |= CIFSSEC_MUST_SIGN; } else if (strnicmp(data, "seal", 4) == 0) { @@ -1845,6 +1857,16 @@ convert_delimiter(char *path, char delim) } } +static void +kill_cifsd(struct TCP_Server_Info *server) +{ + struct task_struct *task; + + task = xchg(&server->tsk, NULL); + if (task) + force_sig(SIGKILL, task); +} + int cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, char *mount_data, const char *devname) @@ -2166,6 +2188,7 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, for the retry flag is used */ tcon->retry = volume_info.retry; tcon->nocase = volume_info.nocase; + tcon->local_lease = volume_info.local_lease; if (tcon->seal != volume_info.seal) cERROR(1, ("transport encryption setting " "conflicts with existing tid")); @@ -2197,6 +2220,12 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, volume_info.UNC, tcon, cifs_sb->local_nls); cFYI(1, ("CIFS Tcon rc = %d", rc)); + if (volume_info.nodfs) { + tcon->Flags &= + ~SMB_SHARE_IS_IN_DFS; + cFYI(1, ("DFS disabled (%d)", + tcon->Flags)); + } } if (!rc) { atomic_inc(&pSesInfo->inUse); @@ -2225,14 +2254,7 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, spin_lock(&GlobalMid_Lock); srvTcp->tcpStatus = CifsExiting; spin_unlock(&GlobalMid_Lock); - if (srvTcp->tsk) { - /* If we could verify that kthread_stop would - always wake up processes blocked in - tcp in recv_mesg then we could remove the - send_sig call */ - force_sig(SIGKILL, srvTcp->tsk); - kthread_stop(srvTcp->tsk); - } + kill_cifsd(srvTcp); } /* If find_unc succeeded then rc == 0 so we can not end */ if (tcon) /* up accidently freeing someone elses tcon struct */ @@ -2245,19 +2267,15 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, temp_rc = CIFSSMBLogoff(xid, pSesInfo); /* if the socketUseCount is now zero */ if ((temp_rc == -ESHUTDOWN) && - (pSesInfo->server) && - (pSesInfo->server->tsk)) { - force_sig(SIGKILL, - pSesInfo->server->tsk); - kthread_stop(pSesInfo->server->tsk); - } + (pSesInfo->server)) + kill_cifsd(pSesInfo->server); } else { cFYI(1, ("No session or bad tcon")); - if ((pSesInfo->server) && - (pSesInfo->server->tsk)) { - force_sig(SIGKILL, - pSesInfo->server->tsk); - kthread_stop(pSesInfo->server->tsk); + if (pSesInfo->server) { + spin_lock(&GlobalMid_Lock); + srvTcp->tcpStatus = CifsExiting; + spin_unlock(&GlobalMid_Lock); + kill_cifsd(pSesInfo->server); } } sesInfoFree(pSesInfo); @@ -3544,7 +3562,6 @@ cifs_umount(struct super_block *sb, struct cifs_sb_info *cifs_sb) int rc = 0; int xid; struct cifsSesInfo *ses = NULL; - struct task_struct *cifsd_task; char *tmp; xid = GetXid(); @@ -3560,7 +3577,6 @@ cifs_umount(struct super_block *sb, struct cifs_sb_info *cifs_sb) tconInfoFree(cifs_sb->tcon); if ((ses) && (ses->server)) { /* save off task so we do not refer to ses later */ - cifsd_task = ses->server->tsk; cFYI(1, ("About to do SMBLogoff ")); rc = CIFSSMBLogoff(xid, ses); if (rc == -EBUSY) { @@ -3568,10 +3584,8 @@ cifs_umount(struct super_block *sb, struct cifs_sb_info *cifs_sb) return 0; } else if (rc == -ESHUTDOWN) { cFYI(1, ("Waking up socket by sending signal")); - if (cifsd_task) { - force_sig(SIGKILL, cifsd_task); - kthread_stop(cifsd_task); - } + if (ses->server) + kill_cifsd(ses->server); rc = 0; } /* else - we have an smb session left on this socket do not kill cifsd */ @@ -3701,7 +3715,9 @@ int cifs_setup_session(unsigned int xid, struct cifsSesInfo *pSesInfo, cERROR(1, ("Send error in SessSetup = %d", rc)); } else { cFYI(1, ("CIFS Session Established successfully")); + spin_lock(&GlobalMid_Lock); pSesInfo->status = CifsGood; + spin_unlock(&GlobalMid_Lock); } ss_err_exit: diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index a8c833345fc..d54fa8aeaea 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -506,6 +506,7 @@ int cifs_get_inode_info(struct inode **pinode, inode = *pinode; cifsInfo = CIFS_I(inode); cifsInfo->cifsAttrs = attr; + cifsInfo->delete_pending = pfindData->DeletePending ? true : false; cFYI(1, ("Old time %ld", cifsInfo->time)); cifsInfo->time = jiffies; cFYI(1, ("New time %ld", cifsInfo->time)); @@ -772,63 +773,106 @@ out: * anything else. */ static int -cifs_rename_pending_delete(char *full_path, struct inode *inode, int xid) +cifs_rename_pending_delete(char *full_path, struct dentry *dentry, int xid) { int oplock = 0; int rc; __u16 netfid; + struct inode *inode = dentry->d_inode; struct cifsInodeInfo *cifsInode = CIFS_I(inode); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifsTconInfo *tcon = cifs_sb->tcon; - __u32 dosattr; - FILE_BASIC_INFO *info_buf; + __u32 dosattr, origattr; + FILE_BASIC_INFO *info_buf = NULL; rc = CIFSSMBOpen(xid, tcon, full_path, FILE_OPEN, - DELETE|FILE_WRITE_ATTRIBUTES, - CREATE_NOT_DIR|CREATE_DELETE_ON_CLOSE, + DELETE|FILE_WRITE_ATTRIBUTES, CREATE_NOT_DIR, &netfid, &oplock, NULL, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); if (rc != 0) goto out; - /* set ATTR_HIDDEN and clear ATTR_READONLY */ - cifsInode = CIFS_I(inode); - dosattr = cifsInode->cifsAttrs & ~ATTR_READONLY; + origattr = cifsInode->cifsAttrs; + if (origattr == 0) + origattr |= ATTR_NORMAL; + + dosattr = origattr & ~ATTR_READONLY; if (dosattr == 0) dosattr |= ATTR_NORMAL; dosattr |= ATTR_HIDDEN; - info_buf = kzalloc(sizeof(*info_buf), GFP_KERNEL); - if (info_buf == NULL) { - rc = -ENOMEM; - goto out_close; + /* set ATTR_HIDDEN and clear ATTR_READONLY, but only if needed */ + if (dosattr != origattr) { + info_buf = kzalloc(sizeof(*info_buf), GFP_KERNEL); + if (info_buf == NULL) { + rc = -ENOMEM; + goto out_close; + } + info_buf->Attributes = cpu_to_le32(dosattr); + rc = CIFSSMBSetFileInfo(xid, tcon, info_buf, netfid, + current->tgid); + /* although we would like to mark the file hidden + if that fails we will still try to rename it */ + if (rc != 0) + cifsInode->cifsAttrs = dosattr; + else + dosattr = origattr; /* since not able to change them */ } - info_buf->Attributes = cpu_to_le32(dosattr); - rc = CIFSSMBSetFileInfo(xid, tcon, info_buf, netfid, current->tgid); - kfree(info_buf); - if (rc != 0) - goto out_close; - cifsInode->cifsAttrs = dosattr; - /* silly-rename the file */ - CIFSSMBRenameOpenFile(xid, tcon, netfid, NULL, cifs_sb->local_nls, + /* rename the file */ + rc = CIFSSMBRenameOpenFile(xid, tcon, netfid, NULL, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); + if (rc != 0) { + rc = -ETXTBSY; + goto undo_setattr; + } - /* set DELETE_ON_CLOSE */ - rc = CIFSSMBSetFileDisposition(xid, tcon, true, netfid, current->tgid); - - /* - * some samba versions return -ENOENT when we try to set the file - * disposition here. Likely a samba bug, but work around it for now - */ - if (rc == -ENOENT) - rc = 0; + /* try to set DELETE_ON_CLOSE */ + if (!cifsInode->delete_pending) { + rc = CIFSSMBSetFileDisposition(xid, tcon, true, netfid, + current->tgid); + /* + * some samba versions return -ENOENT when we try to set the + * file disposition here. Likely a samba bug, but work around + * it for now. This means that some cifsXXX files may hang + * around after they shouldn't. + * + * BB: remove this hack after more servers have the fix + */ + if (rc == -ENOENT) + rc = 0; + else if (rc != 0) { + rc = -ETXTBSY; + goto undo_rename; + } + cifsInode->delete_pending = true; + } out_close: CIFSSMBClose(xid, tcon, netfid); out: + kfree(info_buf); return rc; + + /* + * reset everything back to the original state. Don't bother + * dealing with errors here since we can't do anything about + * them anyway. + */ +undo_rename: + CIFSSMBRenameOpenFile(xid, tcon, netfid, dentry->d_name.name, + cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & + CIFS_MOUNT_MAP_SPECIAL_CHR); +undo_setattr: + if (dosattr != origattr) { + info_buf->Attributes = cpu_to_le32(origattr); + if (!CIFSSMBSetFileInfo(xid, tcon, info_buf, netfid, + current->tgid)) + cifsInode->cifsAttrs = origattr; + } + + goto out_close; } int cifs_unlink(struct inode *dir, struct dentry *dentry) @@ -878,7 +922,7 @@ psx_del_no_retry: } else if (rc == -ENOENT) { d_drop(dentry); } else if (rc == -ETXTBSY) { - rc = cifs_rename_pending_delete(full_path, inode, xid); + rc = cifs_rename_pending_delete(full_path, dentry, xid); if (rc == 0) drop_nlink(inode); } else if (rc == -EACCES && dosattr == 0) { @@ -1241,22 +1285,21 @@ cifs_do_rename(int xid, struct dentry *from_dentry, const char *fromPath, return rc; } -int cifs_rename(struct inode *source_inode, struct dentry *source_direntry, - struct inode *target_inode, struct dentry *target_direntry) +int cifs_rename(struct inode *source_dir, struct dentry *source_dentry, + struct inode *target_dir, struct dentry *target_dentry) { char *fromName = NULL; char *toName = NULL; struct cifs_sb_info *cifs_sb_source; struct cifs_sb_info *cifs_sb_target; - struct cifsTconInfo *pTcon; + struct cifsTconInfo *tcon; FILE_UNIX_BASIC_INFO *info_buf_source = NULL; FILE_UNIX_BASIC_INFO *info_buf_target; - int xid; - int rc; + int xid, rc, tmprc; - cifs_sb_target = CIFS_SB(target_inode->i_sb); - cifs_sb_source = CIFS_SB(source_inode->i_sb); - pTcon = cifs_sb_source->tcon; + cifs_sb_target = CIFS_SB(target_dir->i_sb); + cifs_sb_source = CIFS_SB(source_dir->i_sb); + tcon = cifs_sb_source->tcon; xid = GetXid(); @@ -1264,7 +1307,7 @@ int cifs_rename(struct inode *source_inode, struct dentry *source_direntry, * BB: this might be allowed if same server, but different share. * Consider adding support for this */ - if (pTcon != cifs_sb_target->tcon) { + if (tcon != cifs_sb_target->tcon) { rc = -EXDEV; goto cifs_rename_exit; } @@ -1273,65 +1316,65 @@ int cifs_rename(struct inode *source_inode, struct dentry *source_direntry, * we already have the rename sem so we do not need to * grab it again here to protect the path integrity */ - fromName = build_path_from_dentry(source_direntry); + fromName = build_path_from_dentry(source_dentry); if (fromName == NULL) { rc = -ENOMEM; goto cifs_rename_exit; } - toName = build_path_from_dentry(target_direntry); + toName = build_path_from_dentry(target_dentry); if (toName == NULL) { rc = -ENOMEM; goto cifs_rename_exit; } - rc = cifs_do_rename(xid, source_direntry, fromName, - target_direntry, toName); + rc = cifs_do_rename(xid, source_dentry, fromName, + target_dentry, toName); - if (rc == -EEXIST) { - if (pTcon->unix_ext) { - /* - * Are src and dst hardlinks of same inode? We can - * only tell with unix extensions enabled - */ - info_buf_source = - kmalloc(2 * sizeof(FILE_UNIX_BASIC_INFO), - GFP_KERNEL); - if (info_buf_source == NULL) - goto unlink_target; - - info_buf_target = info_buf_source + 1; - rc = CIFSSMBUnixQPathInfo(xid, pTcon, fromName, - info_buf_source, - cifs_sb_source->local_nls, - cifs_sb_source->mnt_cifs_flags & - CIFS_MOUNT_MAP_SPECIAL_CHR); - if (rc != 0) - goto unlink_target; - - rc = CIFSSMBUnixQPathInfo(xid, pTcon, - toName, info_buf_target, - cifs_sb_target->local_nls, - /* remap based on source sb */ - cifs_sb_source->mnt_cifs_flags & - CIFS_MOUNT_MAP_SPECIAL_CHR); + if (rc == -EEXIST && tcon->unix_ext) { + /* + * Are src and dst hardlinks of same inode? We can + * only tell with unix extensions enabled + */ + info_buf_source = + kmalloc(2 * sizeof(FILE_UNIX_BASIC_INFO), + GFP_KERNEL); + if (info_buf_source == NULL) { + rc = -ENOMEM; + goto cifs_rename_exit; + } - if (rc == 0 && (info_buf_source->UniqueId == - info_buf_target->UniqueId)) - /* same file, POSIX says that this is a noop */ - goto cifs_rename_exit; - } /* else ... BB we could add the same check for Windows by + info_buf_target = info_buf_source + 1; + tmprc = CIFSSMBUnixQPathInfo(xid, tcon, fromName, + info_buf_source, + cifs_sb_source->local_nls, + cifs_sb_source->mnt_cifs_flags & + CIFS_MOUNT_MAP_SPECIAL_CHR); + if (tmprc != 0) + goto unlink_target; + + tmprc = CIFSSMBUnixQPathInfo(xid, tcon, + toName, info_buf_target, + cifs_sb_target->local_nls, + /* remap based on source sb */ + cifs_sb_source->mnt_cifs_flags & + CIFS_MOUNT_MAP_SPECIAL_CHR); + + if (tmprc == 0 && (info_buf_source->UniqueId == + info_buf_target->UniqueId)) + /* same file, POSIX says that this is a noop */ + goto cifs_rename_exit; + } /* else ... BB we could add the same check for Windows by checking the UniqueId via FILE_INTERNAL_INFO */ + unlink_target: - /* - * we either can not tell the files are hardlinked (as with - * Windows servers) or files are not hardlinked. Delete the - * target manually before renaming to follow POSIX rather than - * Windows semantics - */ - cifs_unlink(target_inode, target_direntry); - rc = cifs_do_rename(xid, source_direntry, fromName, - target_direntry, toName); + if ((rc == -EACCES) || (rc == -EEXIST)) { + tmprc = cifs_unlink(target_dir, target_dentry); + if (tmprc) + goto cifs_rename_exit; + + rc = cifs_do_rename(xid, source_dentry, fromName, + target_dentry, toName); } cifs_rename_exit: diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 765adf12d54..58d57299f2a 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -762,14 +762,15 @@ static int find_cifs_entry(const int xid, struct cifsTconInfo *pTcon, rc)); return rc; } + cifs_save_resume_key(cifsFile->srch_inf.last_entry, cifsFile); } while ((index_to_find >= cifsFile->srch_inf.index_of_last_entry) && (rc == 0) && !cifsFile->srch_inf.endOfSearch) { cFYI(1, ("calling findnext2")); - cifs_save_resume_key(cifsFile->srch_inf.last_entry, cifsFile); rc = CIFSFindNext(xid, pTcon, cifsFile->netfid, &cifsFile->srch_inf); + cifs_save_resume_key(cifsFile->srch_inf.last_entry, cifsFile); if (rc) return -ENOENT; } diff --git a/fs/coda/dir.c b/fs/coda/dir.c index c5916228243..75b1fa90b2c 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -146,6 +146,9 @@ int coda_permission(struct inode *inode, int mask) if (!mask) return 0; + if ((mask & MAY_EXEC) && !execute_ok(inode)) + return -EACCES; + lock_kernel(); if (coda_cache_check(inode, mask)) diff --git a/fs/coda/pioctl.c b/fs/coda/pioctl.c index c51365422aa..773f2ce9aa0 100644 --- a/fs/coda/pioctl.c +++ b/fs/coda/pioctl.c @@ -43,7 +43,7 @@ const struct file_operations coda_ioctl_operations = { /* the coda pioctl inode ops */ static int coda_ioctl_permission(struct inode *inode, int mask) { - return 0; + return (mask & MAY_EXEC) ? -EACCES : 0; } static int coda_pioctl(struct inode * inode, struct file * filp, diff --git a/fs/compat.c b/fs/compat.c index 5f9ec449c79..fe3c9bf8760 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -869,7 +869,7 @@ asmlinkage long compat_sys_old_readdir(unsigned int fd, buf.dirent = dirent; error = vfs_readdir(file, compat_fillonedir, &buf); - if (error >= 0) + if (buf.result) error = buf.result; fput(file); @@ -956,9 +956,8 @@ asmlinkage long compat_sys_getdents(unsigned int fd, buf.error = 0; error = vfs_readdir(file, compat_filldir, &buf); - if (error < 0) - goto out_putf; - error = buf.error; + if (error >= 0) + error = buf.error; lastdirent = buf.previous; if (lastdirent) { if (put_user(file->f_pos, &lastdirent->d_off)) @@ -966,8 +965,6 @@ asmlinkage long compat_sys_getdents(unsigned int fd, else error = count - buf.count; } - -out_putf: fput(file); out: return error; @@ -1047,19 +1044,16 @@ asmlinkage long compat_sys_getdents64(unsigned int fd, buf.error = 0; error = vfs_readdir(file, compat_filldir64, &buf); - if (error < 0) - goto out_putf; - error = buf.error; + if (error >= 0) + error = buf.error; lastdirent = buf.previous; if (lastdirent) { typeof(lastdirent->d_off) d_off = file->f_pos; - error = -EFAULT; if (__put_user_unaligned(d_off, &lastdirent->d_off)) - goto out_putf; - error = count - buf.count; + error = -EFAULT; + else + error = count - buf.count; } - -out_putf: fput(file); out: return error; @@ -1475,6 +1469,57 @@ out_ret: #define __COMPAT_NFDBITS (8 * sizeof(compat_ulong_t)) +static int poll_select_copy_remaining(struct timespec *end_time, void __user *p, + int timeval, int ret) +{ + struct timespec ts; + + if (!p) + return ret; + + if (current->personality & STICKY_TIMEOUTS) + goto sticky; + + /* No update for zero timeout */ + if (!end_time->tv_sec && !end_time->tv_nsec) + return ret; + + ktime_get_ts(&ts); + ts = timespec_sub(*end_time, ts); + if (ts.tv_sec < 0) + ts.tv_sec = ts.tv_nsec = 0; + + if (timeval) { + struct compat_timeval rtv; + + rtv.tv_sec = ts.tv_sec; + rtv.tv_usec = ts.tv_nsec / NSEC_PER_USEC; + + if (!copy_to_user(p, &rtv, sizeof(rtv))) + return ret; + } else { + struct compat_timespec rts; + + rts.tv_sec = ts.tv_sec; + rts.tv_nsec = ts.tv_nsec; + + if (!copy_to_user(p, &rts, sizeof(rts))) + return ret; + } + /* + * If an application puts its timeval in read-only memory, we + * don't want the Linux-specific update to the timeval to + * cause a fault after the select has completed + * successfully. However, because we're not updating the + * timeval, we can't restart the system call. + */ + +sticky: + if (ret == -ERESTARTNOHAND) + ret = -EINTR; + return ret; +} + /* * Ooo, nasty. We need here to frob 32-bit unsigned longs to * 64-bit unsigned longs. @@ -1556,7 +1601,8 @@ int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, ((unsigned long) (MAX_SCHEDULE_TIMEOUT / HZ)-1) int compat_core_sys_select(int n, compat_ulong_t __user *inp, - compat_ulong_t __user *outp, compat_ulong_t __user *exp, s64 *timeout) + compat_ulong_t __user *outp, compat_ulong_t __user *exp, + struct timespec *end_time) { fd_set_bits fds; void *bits; @@ -1603,7 +1649,7 @@ int compat_core_sys_select(int n, compat_ulong_t __user *inp, zero_fd_set(n, fds.res_out); zero_fd_set(n, fds.res_ex); - ret = do_select(n, &fds, timeout); + ret = do_select(n, &fds, end_time); if (ret < 0) goto out; @@ -1629,7 +1675,7 @@ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct compat_timeval __user *tvp) { - s64 timeout = -1; + struct timespec end_time, *to = NULL; struct compat_timeval tv; int ret; @@ -1637,43 +1683,14 @@ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, if (copy_from_user(&tv, tvp, sizeof(tv))) return -EFAULT; - if (tv.tv_sec < 0 || tv.tv_usec < 0) + to = &end_time; + if (poll_select_set_timeout(to, tv.tv_sec, + tv.tv_usec * NSEC_PER_USEC)) return -EINVAL; - - /* Cast to u64 to make GCC stop complaining */ - if ((u64)tv.tv_sec >= (u64)MAX_INT64_SECONDS) - timeout = -1; /* infinite */ - else { - timeout = DIV_ROUND_UP(tv.tv_usec, 1000000/HZ); - timeout += tv.tv_sec * HZ; - } } - ret = compat_core_sys_select(n, inp, outp, exp, &timeout); - - if (tvp) { - struct compat_timeval rtv; - - if (current->personality & STICKY_TIMEOUTS) - goto sticky; - rtv.tv_usec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)); - rtv.tv_sec = timeout; - if (compat_timeval_compare(&rtv, &tv) >= 0) - rtv = tv; - if (copy_to_user(tvp, &rtv, sizeof(rtv))) { -sticky: - /* - * If an application puts its timeval in read-only - * memory, we don't want the Linux-specific update to - * the timeval to cause a fault after the select has - * completed successfully. However, because we're not - * updating the timeval, we can't restart the system - * call. - */ - if (ret == -ERESTARTNOHAND) - ret = -EINTR; - } - } + ret = compat_core_sys_select(n, inp, outp, exp, to); + ret = poll_select_copy_remaining(&end_time, tvp, 1, ret); return ret; } @@ -1686,15 +1703,16 @@ asmlinkage long compat_sys_pselect7(int n, compat_ulong_t __user *inp, { compat_sigset_t ss32; sigset_t ksigmask, sigsaved; - s64 timeout = MAX_SCHEDULE_TIMEOUT; struct compat_timespec ts; + struct timespec end_time, *to = NULL; int ret; if (tsp) { if (copy_from_user(&ts, tsp, sizeof(ts))) return -EFAULT; - if (ts.tv_sec < 0 || ts.tv_nsec < 0) + to = &end_time; + if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } @@ -1709,51 +1727,8 @@ asmlinkage long compat_sys_pselect7(int n, compat_ulong_t __user *inp, sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); } - do { - if (tsp) { - if ((unsigned long)ts.tv_sec < MAX_SELECT_SECONDS) { - timeout = DIV_ROUND_UP(ts.tv_nsec, 1000000000/HZ); - timeout += ts.tv_sec * (unsigned long)HZ; - ts.tv_sec = 0; - ts.tv_nsec = 0; - } else { - ts.tv_sec -= MAX_SELECT_SECONDS; - timeout = MAX_SELECT_SECONDS * HZ; - } - } - - ret = compat_core_sys_select(n, inp, outp, exp, &timeout); - - } while (!ret && !timeout && tsp && (ts.tv_sec || ts.tv_nsec)); - - if (tsp) { - struct compat_timespec rts; - - if (current->personality & STICKY_TIMEOUTS) - goto sticky; - - rts.tv_sec = timeout / HZ; - rts.tv_nsec = (timeout % HZ) * (NSEC_PER_SEC/HZ); - if (rts.tv_nsec >= NSEC_PER_SEC) { - rts.tv_sec++; - rts.tv_nsec -= NSEC_PER_SEC; - } - if (compat_timespec_compare(&rts, &ts) >= 0) - rts = ts; - if (copy_to_user(tsp, &rts, sizeof(rts))) { -sticky: - /* - * If an application puts its timeval in read-only - * memory, we don't want the Linux-specific update to - * the timeval to cause a fault after the select has - * completed successfully. However, because we're not - * updating the timeval, we can't restart the system - * call. - */ - if (ret == -ERESTARTNOHAND) - ret = -EINTR; - } - } + ret = compat_core_sys_select(n, inp, outp, exp, to); + ret = poll_select_copy_remaining(&end_time, tsp, 0, ret); if (ret == -ERESTARTNOHAND) { /* @@ -1798,18 +1773,16 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, compat_sigset_t ss32; sigset_t ksigmask, sigsaved; struct compat_timespec ts; - s64 timeout = -1; + struct timespec end_time, *to = NULL; int ret; if (tsp) { if (copy_from_user(&ts, tsp, sizeof(ts))) return -EFAULT; - /* We assume that ts.tv_sec is always lower than - the number of seconds that can be expressed in - an s64. Otherwise the compiler bitches at us */ - timeout = DIV_ROUND_UP(ts.tv_nsec, 1000000000/HZ); - timeout += ts.tv_sec * HZ; + to = &end_time; + if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) + return -EINVAL; } if (sigmask) { @@ -1823,7 +1796,7 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); } - ret = do_sys_poll(ufds, nfds, &timeout); + ret = do_sys_poll(ufds, nfds, to); /* We can restart this syscall, usually */ if (ret == -EINTR) { @@ -1841,31 +1814,7 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, } else if (sigmask) sigprocmask(SIG_SETMASK, &sigsaved, NULL); - if (tsp && timeout >= 0) { - struct compat_timespec rts; - - if (current->personality & STICKY_TIMEOUTS) - goto sticky; - /* Yes, we know it's actually an s64, but it's also positive. */ - rts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) * - 1000; - rts.tv_sec = timeout; - if (compat_timespec_compare(&rts, &ts) >= 0) - rts = ts; - if (copy_to_user(tsp, &rts, sizeof(rts))) { -sticky: - /* - * If an application puts its timeval in read-only - * memory, we don't want the Linux-specific update to - * the timeval to cause a fault after the select has - * completed successfully. However, because we're not - * updating the timeval, we can't restart the system - * call. - */ - if (ret == -ERESTARTNOHAND && timeout >= 0) - ret = -EINTR; - } - } + ret = poll_select_copy_remaining(&end_time, tsp, 0, ret); return ret; } diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c index bf74973b049..932a92b3148 100644 --- a/fs/configfs/symlink.c +++ b/fs/configfs/symlink.c @@ -108,18 +108,18 @@ out: } -static int get_target(const char *symname, struct nameidata *nd, +static int get_target(const char *symname, struct path *path, struct config_item **target) { int ret; - ret = path_lookup(symname, LOOKUP_FOLLOW|LOOKUP_DIRECTORY, nd); + ret = kern_path(symname, LOOKUP_FOLLOW|LOOKUP_DIRECTORY, path); if (!ret) { - if (nd->path.dentry->d_sb == configfs_sb) { - *target = configfs_get_config_item(nd->path.dentry); + if (path->dentry->d_sb == configfs_sb) { + *target = configfs_get_config_item(path->dentry); if (!*target) { ret = -ENOENT; - path_put(&nd->path); + path_put(path); } } else ret = -EPERM; @@ -132,7 +132,7 @@ static int get_target(const char *symname, struct nameidata *nd, int configfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) { int ret; - struct nameidata nd; + struct path path; struct configfs_dirent *sd; struct config_item *parent_item; struct config_item *target_item; @@ -159,7 +159,7 @@ int configfs_symlink(struct inode *dir, struct dentry *dentry, const char *symna !type->ct_item_ops->allow_link) goto out_put; - ret = get_target(symname, &nd, &target_item); + ret = get_target(symname, &path, &target_item); if (ret) goto out_put; @@ -174,7 +174,7 @@ int configfs_symlink(struct inode *dir, struct dentry *dentry, const char *symna } config_item_put(target_item); - path_put(&nd.path); + path_put(&path); out_put: config_item_put(parent_item); diff --git a/fs/dcache.c b/fs/dcache.c index e7a1a99b746..a1d86c7f3e6 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -69,6 +69,7 @@ struct dentry_stat_t dentry_stat = { static void __d_free(struct dentry *dentry) { + WARN_ON(!list_empty(&dentry->d_alias)); if (dname_external(dentry)) kfree(dentry->d_name.name); kmem_cache_free(dentry_cache, dentry); @@ -174,9 +175,12 @@ static struct dentry *d_kill(struct dentry *dentry) dentry_stat.nr_dentry--; /* For d_free, below */ /*drops the locks, at that point nobody can reach this dentry */ dentry_iput(dentry); - parent = dentry->d_parent; + if (IS_ROOT(dentry)) + parent = NULL; + else + parent = dentry->d_parent; d_free(dentry); - return dentry == parent ? NULL : parent; + return parent; } /* @@ -666,11 +670,12 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) BUG(); } - parent = dentry->d_parent; - if (parent == dentry) + if (IS_ROOT(dentry)) parent = NULL; - else + else { + parent = dentry->d_parent; atomic_dec(&parent->d_count); + } list_del(&dentry->d_u.d_child); detached++; @@ -977,6 +982,15 @@ struct dentry *d_alloc_name(struct dentry *parent, const char *name) return d_alloc(parent, &q); } +/* the caller must hold dcache_lock */ +static void __d_instantiate(struct dentry *dentry, struct inode *inode) +{ + if (inode) + list_add(&dentry->d_alias, &inode->i_dentry); + dentry->d_inode = inode; + fsnotify_d_instantiate(dentry, inode); +} + /** * d_instantiate - fill in inode information for a dentry * @entry: dentry to complete @@ -996,10 +1010,7 @@ void d_instantiate(struct dentry *entry, struct inode * inode) { BUG_ON(!list_empty(&entry->d_alias)); spin_lock(&dcache_lock); - if (inode) - list_add(&entry->d_alias, &inode->i_dentry); - entry->d_inode = inode; - fsnotify_d_instantiate(entry, inode); + __d_instantiate(entry, inode); spin_unlock(&dcache_lock); security_d_instantiate(entry, inode); } @@ -1029,7 +1040,7 @@ static struct dentry *__d_instantiate_unique(struct dentry *entry, unsigned int hash = entry->d_name.hash; if (!inode) { - entry->d_inode = NULL; + __d_instantiate(entry, NULL); return NULL; } @@ -1048,9 +1059,7 @@ static struct dentry *__d_instantiate_unique(struct dentry *entry, return alias; } - list_add(&entry->d_alias, &inode->i_dentry); - entry->d_inode = inode; - fsnotify_d_instantiate(entry, inode); + __d_instantiate(entry, inode); return NULL; } @@ -1111,69 +1120,71 @@ static inline struct hlist_head *d_hash(struct dentry *parent, } /** - * d_alloc_anon - allocate an anonymous dentry + * d_obtain_alias - find or allocate a dentry for a given inode * @inode: inode to allocate the dentry for * - * This is similar to d_alloc_root. It is used by filesystems when - * creating a dentry for a given inode, often in the process of - * mapping a filehandle to a dentry. The returned dentry may be - * anonymous, or may have a full name (if the inode was already - * in the cache). The file system may need to make further - * efforts to connect this dentry into the dcache properly. + * Obtain a dentry for an inode resulting from NFS filehandle conversion or + * similar open by handle operations. The returned dentry may be anonymous, + * or may have a full name (if the inode was already in the cache). * - * When called on a directory inode, we must ensure that - * the inode only ever has one dentry. If a dentry is - * found, that is returned instead of allocating a new one. + * When called on a directory inode, we must ensure that the inode only ever + * has one dentry. If a dentry is found, that is returned instead of + * allocating a new one. * * On successful return, the reference to the inode has been transferred - * to the dentry. If %NULL is returned (indicating kmalloc failure), - * the reference on the inode has not been released. + * to the dentry. In case of an error the reference on the inode is released. + * To make it easier to use in export operations a %NULL or IS_ERR inode may + * be passed in and will be the error will be propagate to the return value, + * with a %NULL @inode replaced by ERR_PTR(-ESTALE). */ - -struct dentry * d_alloc_anon(struct inode *inode) +struct dentry *d_obtain_alias(struct inode *inode) { static const struct qstr anonstring = { .name = "" }; struct dentry *tmp; struct dentry *res; - if ((res = d_find_alias(inode))) { - iput(inode); - return res; - } + if (!inode) + return ERR_PTR(-ESTALE); + if (IS_ERR(inode)) + return ERR_CAST(inode); - tmp = d_alloc(NULL, &anonstring); - if (!tmp) - return NULL; + res = d_find_alias(inode); + if (res) + goto out_iput; + tmp = d_alloc(NULL, &anonstring); + if (!tmp) { + res = ERR_PTR(-ENOMEM); + goto out_iput; + } tmp->d_parent = tmp; /* make sure dput doesn't croak */ - + spin_lock(&dcache_lock); res = __d_find_alias(inode, 0); - if (!res) { - /* attach a disconnected dentry */ - res = tmp; - tmp = NULL; - spin_lock(&res->d_lock); - res->d_sb = inode->i_sb; - res->d_parent = res; - res->d_inode = inode; - res->d_flags |= DCACHE_DISCONNECTED; - res->d_flags &= ~DCACHE_UNHASHED; - list_add(&res->d_alias, &inode->i_dentry); - hlist_add_head(&res->d_hash, &inode->i_sb->s_anon); - spin_unlock(&res->d_lock); - - inode = NULL; /* don't drop reference */ + if (res) { + spin_unlock(&dcache_lock); + dput(tmp); + goto out_iput; } + + /* attach a disconnected dentry */ + spin_lock(&tmp->d_lock); + tmp->d_sb = inode->i_sb; + tmp->d_inode = inode; + tmp->d_flags |= DCACHE_DISCONNECTED; + tmp->d_flags &= ~DCACHE_UNHASHED; + list_add(&tmp->d_alias, &inode->i_dentry); + hlist_add_head(&tmp->d_hash, &inode->i_sb->s_anon); + spin_unlock(&tmp->d_lock); + spin_unlock(&dcache_lock); + return tmp; - if (inode) - iput(inode); - if (tmp) - dput(tmp); + out_iput: + iput(inode); return res; } - +EXPORT_SYMBOL_GPL(d_obtain_alias); /** * d_splice_alias - splice a disconnected dentry into the tree if one exists @@ -1200,17 +1211,14 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry) new = __d_find_alias(inode, 1); if (new) { BUG_ON(!(new->d_flags & DCACHE_DISCONNECTED)); - fsnotify_d_instantiate(new, inode); spin_unlock(&dcache_lock); security_d_instantiate(new, inode); d_rehash(dentry); d_move(new, dentry); iput(inode); } else { - /* d_instantiate takes dcache_lock, so we do it by hand */ - list_add(&dentry->d_alias, &inode->i_dentry); - dentry->d_inode = inode; - fsnotify_d_instantiate(dentry, inode); + /* already taking dcache_lock, so d_add() by hand */ + __d_instantiate(dentry, inode); spin_unlock(&dcache_lock); security_d_instantiate(dentry, inode); d_rehash(dentry); @@ -1293,8 +1301,7 @@ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode, * d_instantiate() by hand because it takes dcache_lock which * we already hold. */ - list_add(&found->d_alias, &inode->i_dentry); - found->d_inode = inode; + __d_instantiate(found, inode); spin_unlock(&dcache_lock); security_d_instantiate(found, inode); return found; @@ -1456,8 +1463,6 @@ out: * d_validate - verify dentry provided from insecure source * @dentry: The dentry alleged to be valid child of @dparent * @dparent: The parent dentry (known to be valid) - * @hash: Hash of the dentry - * @len: Length of the name * * An insecure source has sent us a dentry, here we verify it and dget() it. * This is used by ncpfs in its readdir implementation. @@ -1714,18 +1719,23 @@ void d_move(struct dentry * dentry, struct dentry * target) spin_unlock(&dcache_lock); } -/* - * Helper that returns 1 if p1 is a parent of p2, else 0 +/** + * d_ancestor - search for an ancestor + * @p1: ancestor dentry + * @p2: child dentry + * + * Returns the ancestor dentry of p2 which is a child of p1, if p1 is + * an ancestor of p2, else NULL. */ -static int d_isparent(struct dentry *p1, struct dentry *p2) +struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2) { struct dentry *p; - for (p = p2; p->d_parent != p; p = p->d_parent) { + for (p = p2; !IS_ROOT(p); p = p->d_parent) { if (p->d_parent == p1) - return 1; + return p; } - return 0; + return NULL; } /* @@ -1749,7 +1759,7 @@ static struct dentry *__d_unalias(struct dentry *dentry, struct dentry *alias) /* Check for loops */ ret = ERR_PTR(-ELOOP); - if (d_isparent(alias, dentry)) + if (d_ancestor(alias, dentry)) goto out_err; /* See lock_rename() */ @@ -1822,7 +1832,7 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode) if (!inode) { actual = dentry; - dentry->d_inode = NULL; + __d_instantiate(dentry, NULL); goto found_lock; } @@ -2149,32 +2159,27 @@ out: * Caller must ensure that "new_dentry" is pinned before calling is_subdir() */ -int is_subdir(struct dentry * new_dentry, struct dentry * old_dentry) +int is_subdir(struct dentry *new_dentry, struct dentry *old_dentry) { int result; - struct dentry * saved = new_dentry; unsigned long seq; - /* need rcu_readlock to protect against the d_parent trashing due to - * d_move + /* FIXME: This is old behavior, needed? Please check callers. */ + if (new_dentry == old_dentry) + return 1; + + /* + * Need rcu_readlock to protect against the d_parent trashing + * due to d_move */ rcu_read_lock(); - do { + do { /* for restarting inner loop in case of seq retry */ - new_dentry = saved; - result = 0; seq = read_seqbegin(&rename_lock); - for (;;) { - if (new_dentry != old_dentry) { - struct dentry * parent = new_dentry->d_parent; - if (parent == new_dentry) - break; - new_dentry = parent; - continue; - } + if (d_ancestor(old_dentry, new_dentry)) result = 1; - break; - } + else + result = 0; } while (read_seqretry(&rename_lock, seq)); rcu_read_unlock(); @@ -2344,7 +2349,6 @@ void __init vfs_caches_init(unsigned long mempages) } EXPORT_SYMBOL(d_alloc); -EXPORT_SYMBOL(d_alloc_anon); EXPORT_SYMBOL(d_alloc_root); EXPORT_SYMBOL(d_delete); EXPORT_SYMBOL(d_find_alias); diff --git a/fs/dquot.c b/fs/dquot.c index da30a27f224..5e95261005b 100644 --- a/fs/dquot.c +++ b/fs/dquot.c @@ -1805,19 +1805,19 @@ int vfs_quota_on_path(struct super_block *sb, int type, int format_id, } /* Actual function called from quotactl() */ -int vfs_quota_on(struct super_block *sb, int type, int format_id, char *path, +int vfs_quota_on(struct super_block *sb, int type, int format_id, char *name, int remount) { - struct nameidata nd; + struct path path; int error; if (remount) return vfs_quota_on_remount(sb, type); - error = path_lookup(path, LOOKUP_FOLLOW, &nd); + error = kern_path(name, LOOKUP_FOLLOW, &path); if (!error) { - error = vfs_quota_on_path(sb, type, format_id, &nd.path); - path_put(&nd.path); + error = vfs_quota_on_path(sb, type, format_id, &path); + path_put(&path); } return error; } diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 046e027a4cb..64d2ba980df 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -471,31 +471,26 @@ out: */ static int ecryptfs_read_super(struct super_block *sb, const char *dev_name) { + struct path path; int rc; - struct nameidata nd; - struct dentry *lower_root; - struct vfsmount *lower_mnt; - memset(&nd, 0, sizeof(struct nameidata)); - rc = path_lookup(dev_name, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &nd); + rc = kern_path(dev_name, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path); if (rc) { ecryptfs_printk(KERN_WARNING, "path_lookup() failed\n"); goto out; } - lower_root = nd.path.dentry; - lower_mnt = nd.path.mnt; - ecryptfs_set_superblock_lower(sb, lower_root->d_sb); - sb->s_maxbytes = lower_root->d_sb->s_maxbytes; - sb->s_blocksize = lower_root->d_sb->s_blocksize; - ecryptfs_set_dentry_lower(sb->s_root, lower_root); - ecryptfs_set_dentry_lower_mnt(sb->s_root, lower_mnt); - rc = ecryptfs_interpose(lower_root, sb->s_root, sb, 0); + ecryptfs_set_superblock_lower(sb, path.dentry->d_sb); + sb->s_maxbytes = path.dentry->d_sb->s_maxbytes; + sb->s_blocksize = path.dentry->d_sb->s_blocksize; + ecryptfs_set_dentry_lower(sb->s_root, path.dentry); + ecryptfs_set_dentry_lower_mnt(sb->s_root, path.mnt); + rc = ecryptfs_interpose(path.dentry, sb->s_root, sb, 0); if (rc) goto out_free; rc = 0; goto out; out_free: - path_put(&nd.path); + path_put(&path); out: return rc; } diff --git a/fs/efs/namei.c b/fs/efs/namei.c index 291abb11e20..c3fb5f9c4a4 100644 --- a/fs/efs/namei.c +++ b/fs/efs/namei.c @@ -112,35 +112,14 @@ struct dentry *efs_fh_to_parent(struct super_block *sb, struct fid *fid, struct dentry *efs_get_parent(struct dentry *child) { - struct dentry *parent; - struct inode *inode; + struct dentry *parent = ERR_PTR(-ENOENT); efs_ino_t ino; - long error; lock_kernel(); - - error = -ENOENT; ino = efs_find_entry(child->d_inode, "..", 2); - if (!ino) - goto fail; - - inode = efs_iget(child->d_inode->i_sb, ino); - if (IS_ERR(inode)) { - error = PTR_ERR(inode); - goto fail; - } - - error = -ENOMEM; - parent = d_alloc_anon(inode); - if (!parent) - goto fail_iput; - + if (ino) + parent = d_obtain_alias(efs_iget(child->d_inode->i_sb, ino)); unlock_kernel(); - return parent; - fail_iput: - iput(inode); - fail: - unlock_kernel(); - return ERR_PTR(error); + return parent; } diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index cc91227d3bb..80246bad1b7 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -94,9 +94,8 @@ find_disconnected_root(struct dentry *dentry) * It may already be, as the flag isn't always updated when connection happens. */ static int -reconnect_path(struct vfsmount *mnt, struct dentry *target_dir) +reconnect_path(struct vfsmount *mnt, struct dentry *target_dir, char *nbuf) { - char nbuf[NAME_MAX+1]; int noprogress = 0; int err = -ESTALE; @@ -281,13 +280,14 @@ static int get_name(struct vfsmount *mnt, struct dentry *dentry, int old_seq = buffer.sequence; error = vfs_readdir(file, filldir_one, &buffer); + if (buffer.found) { + error = 0; + break; + } if (error < 0) break; - error = 0; - if (buffer.found) - break; error = -ENOENT; if (old_seq == buffer.sequence) break; @@ -360,14 +360,13 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid, { const struct export_operations *nop = mnt->mnt_sb->s_export_op; struct dentry *result, *alias; + char nbuf[NAME_MAX+1]; int err; /* * Try to get any dentry for the given file handle from the filesystem. */ result = nop->fh_to_dentry(mnt->mnt_sb, fid, fh_len, fileid_type); - if (!result) - result = ERR_PTR(-ESTALE); if (IS_ERR(result)) return result; @@ -381,7 +380,7 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid, * filesystem root. */ if (result->d_flags & DCACHE_DISCONNECTED) { - err = reconnect_path(mnt, result); + err = reconnect_path(mnt, result, nbuf); if (err) goto err_result; } @@ -397,7 +396,6 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid, * It's not a directory. Life is a little more complicated. */ struct dentry *target_dir, *nresult; - char nbuf[NAME_MAX+1]; /* * See if either the dentry we just got from the filesystem @@ -422,8 +420,6 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid, target_dir = nop->fh_to_parent(mnt->mnt_sb, fid, fh_len, fileid_type); - if (!target_dir) - goto err_result; err = PTR_ERR(target_dir); if (IS_ERR(target_dir)) goto err_result; @@ -433,7 +429,7 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid, * connected to the filesystem root. The VFS really doesn't * like disconnected directories.. */ - err = reconnect_path(mnt, target_dir); + err = reconnect_path(mnt, target_dir, nbuf); if (err) { dput(target_dir); goto err_result; diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index 11a49ce8439..9a0fc400f91 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -354,11 +354,11 @@ ext2_readdir (struct file * filp, void * dirent, filldir_t filldir) * (as a parameter - res_dir). Page is returned mapped and unlocked. * Entry is guaranteed to be valid. */ -struct ext2_dir_entry_2 * ext2_find_entry (struct inode * dir, - struct dentry *dentry, struct page ** res_page) +struct ext2_dir_entry_2 *ext2_find_entry (struct inode * dir, + struct qstr *child, struct page ** res_page) { - const char *name = dentry->d_name.name; - int namelen = dentry->d_name.len; + const char *name = child->name; + int namelen = child->len; unsigned reclen = EXT2_DIR_REC_LEN(namelen); unsigned long start, n; unsigned long npages = dir_pages(dir); @@ -431,13 +431,13 @@ struct ext2_dir_entry_2 * ext2_dotdot (struct inode *dir, struct page **p) return de; } -ino_t ext2_inode_by_name(struct inode * dir, struct dentry *dentry) +ino_t ext2_inode_by_name(struct inode *dir, struct qstr *child) { ino_t res = 0; - struct ext2_dir_entry_2 * de; + struct ext2_dir_entry_2 *de; struct page *page; - de = ext2_find_entry (dir, dentry, &page); + de = ext2_find_entry (dir, child, &page); if (de) { res = le32_to_cpu(de->inode); ext2_put_page(page); diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index bae998c1e44..3203042b36e 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -105,9 +105,9 @@ extern void ext2_rsv_window_add(struct super_block *sb, struct ext2_reserve_wind /* dir.c */ extern int ext2_add_link (struct dentry *, struct inode *); -extern ino_t ext2_inode_by_name(struct inode *, struct dentry *); +extern ino_t ext2_inode_by_name(struct inode *, struct qstr *); extern int ext2_make_empty(struct inode *, struct inode *); -extern struct ext2_dir_entry_2 * ext2_find_entry (struct inode *,struct dentry *, struct page **); +extern struct ext2_dir_entry_2 * ext2_find_entry (struct inode *,struct qstr *, struct page **); extern int ext2_delete_entry (struct ext2_dir_entry_2 *, struct page *); extern int ext2_empty_dir (struct inode *); extern struct ext2_dir_entry_2 * ext2_dotdot (struct inode *, struct page **); diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index 80c97fd8c57..2a747252ec1 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -60,7 +60,7 @@ static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, str if (dentry->d_name.len > EXT2_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); - ino = ext2_inode_by_name(dir, dentry); + ino = ext2_inode_by_name(dir, &dentry->d_name); inode = NULL; if (ino) { inode = ext2_iget(dir->i_sb, ino); @@ -72,27 +72,11 @@ static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, str struct dentry *ext2_get_parent(struct dentry *child) { - unsigned long ino; - struct dentry *parent; - struct inode *inode; - struct dentry dotdot; - - dotdot.d_name.name = ".."; - dotdot.d_name.len = 2; - - ino = ext2_inode_by_name(child->d_inode, &dotdot); + struct qstr dotdot = {.name = "..", .len = 2}; + unsigned long ino = ext2_inode_by_name(child->d_inode, &dotdot); if (!ino) return ERR_PTR(-ENOENT); - inode = ext2_iget(child->d_inode->i_sb, ino); - - if (IS_ERR(inode)) - return ERR_CAST(inode); - parent = d_alloc_anon(inode); - if (!parent) { - iput(inode); - parent = ERR_PTR(-ENOMEM); - } - return parent; + return d_obtain_alias(ext2_iget(child->d_inode->i_sb, ino)); } /* @@ -257,7 +241,7 @@ static int ext2_unlink(struct inode * dir, struct dentry *dentry) struct page * page; int err = -ENOENT; - de = ext2_find_entry (dir, dentry, &page); + de = ext2_find_entry (dir, &dentry->d_name, &page); if (!de) goto out; @@ -299,7 +283,7 @@ static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry, struct ext2_dir_entry_2 * old_de; int err = -ENOENT; - old_de = ext2_find_entry (old_dir, old_dentry, &old_page); + old_de = ext2_find_entry (old_dir, &old_dentry->d_name, &old_page); if (!old_de) goto out; @@ -319,7 +303,7 @@ static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry, goto out_dir; err = -ENOENT; - new_de = ext2_find_entry (new_dir, new_dentry, &new_page); + new_de = ext2_find_entry (new_dir, &new_dentry->d_name, &new_page); if (!new_de) goto out_dir; inode_inc_link_count(old_inode); diff --git a/fs/ext2/xip.c b/fs/ext2/xip.c index 4fb94c20041..b72b8588422 100644 --- a/fs/ext2/xip.c +++ b/fs/ext2/xip.c @@ -11,6 +11,7 @@ #include <linux/buffer_head.h> #include <linux/ext2_fs_sb.h> #include <linux/ext2_fs.h> +#include <linux/blkdev.h> #include "ext2.h" #include "xip.h" diff --git a/fs/ext3/ioctl.c b/fs/ext3/ioctl.c index 0d0c7015164..b7394d05ee8 100644 --- a/fs/ext3/ioctl.c +++ b/fs/ext3/ioctl.c @@ -239,7 +239,7 @@ setrsvsz_out: case EXT3_IOC_GROUP_EXTEND: { ext3_fsblk_t n_blocks_count; struct super_block *sb = inode->i_sb; - int err; + int err, err2; if (!capable(CAP_SYS_RESOURCE)) return -EPERM; @@ -254,8 +254,10 @@ setrsvsz_out: } err = ext3_group_extend(sb, EXT3_SB(sb)->s_es, n_blocks_count); journal_lock_updates(EXT3_SB(sb)->s_journal); - journal_flush(EXT3_SB(sb)->s_journal); + err2 = journal_flush(EXT3_SB(sb)->s_journal); journal_unlock_updates(EXT3_SB(sb)->s_journal); + if (err == 0) + err = err2; group_extend_out: mnt_drop_write(filp->f_path.mnt); return err; @@ -263,7 +265,7 @@ group_extend_out: case EXT3_IOC_GROUP_ADD: { struct ext3_new_group_data input; struct super_block *sb = inode->i_sb; - int err; + int err, err2; if (!capable(CAP_SYS_RESOURCE)) return -EPERM; @@ -280,8 +282,10 @@ group_extend_out: err = ext3_group_add(sb, &input); journal_lock_updates(EXT3_SB(sb)->s_journal); - journal_flush(EXT3_SB(sb)->s_journal); + err2 = journal_flush(EXT3_SB(sb)->s_journal); journal_unlock_updates(EXT3_SB(sb)->s_journal); + if (err == 0) + err = err2; group_add_out: mnt_drop_write(filp->f_path.mnt); return err; diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index de13e919cd8..3e5edc92aa0 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -159,7 +159,7 @@ static void dx_set_count (struct dx_entry *entries, unsigned value); static void dx_set_limit (struct dx_entry *entries, unsigned value); static unsigned dx_root_limit (struct inode *dir, unsigned infosize); static unsigned dx_node_limit (struct inode *dir); -static struct dx_frame *dx_probe(struct dentry *dentry, +static struct dx_frame *dx_probe(struct qstr *entry, struct inode *dir, struct dx_hash_info *hinfo, struct dx_frame *frame, @@ -176,8 +176,9 @@ static int ext3_htree_next_block(struct inode *dir, __u32 hash, struct dx_frame *frame, struct dx_frame *frames, __u32 *start_hash); -static struct buffer_head * ext3_dx_find_entry(struct dentry *dentry, - struct ext3_dir_entry_2 **res_dir, int *err); +static struct buffer_head * ext3_dx_find_entry(struct inode *dir, + struct qstr *entry, struct ext3_dir_entry_2 **res_dir, + int *err); static int ext3_dx_add_entry(handle_t *handle, struct dentry *dentry, struct inode *inode); @@ -342,7 +343,7 @@ struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir, * back to userspace. */ static struct dx_frame * -dx_probe(struct dentry *dentry, struct inode *dir, +dx_probe(struct qstr *entry, struct inode *dir, struct dx_hash_info *hinfo, struct dx_frame *frame_in, int *err) { unsigned count, indirect; @@ -353,8 +354,6 @@ dx_probe(struct dentry *dentry, struct inode *dir, u32 hash; frame->bh = NULL; - if (dentry) - dir = dentry->d_parent->d_inode; if (!(bh = ext3_bread (NULL,dir, 0, 0, err))) goto fail; root = (struct dx_root *) bh->b_data; @@ -370,8 +369,8 @@ dx_probe(struct dentry *dentry, struct inode *dir, } hinfo->hash_version = root->info.hash_version; hinfo->seed = EXT3_SB(dir->i_sb)->s_hash_seed; - if (dentry) - ext3fs_dirhash(dentry->d_name.name, dentry->d_name.len, hinfo); + if (entry) + ext3fs_dirhash(entry->name, entry->len, hinfo); hash = hinfo->hash; if (root->info.unused_flags & 1) { @@ -803,15 +802,15 @@ static inline int ext3_match (int len, const char * const name, */ static inline int search_dirblock(struct buffer_head * bh, struct inode *dir, - struct dentry *dentry, + struct qstr *child, unsigned long offset, struct ext3_dir_entry_2 ** res_dir) { struct ext3_dir_entry_2 * de; char * dlimit; int de_len; - const char *name = dentry->d_name.name; - int namelen = dentry->d_name.len; + const char *name = child->name; + int namelen = child->len; de = (struct ext3_dir_entry_2 *) bh->b_data; dlimit = bh->b_data + dir->i_sb->s_blocksize; @@ -850,8 +849,9 @@ static inline int search_dirblock(struct buffer_head * bh, * The returned buffer_head has ->b_count elevated. The caller is expected * to brelse() it when appropriate. */ -static struct buffer_head * ext3_find_entry (struct dentry *dentry, - struct ext3_dir_entry_2 ** res_dir) +static struct buffer_head *ext3_find_entry(struct inode *dir, + struct qstr *entry, + struct ext3_dir_entry_2 **res_dir) { struct super_block * sb; struct buffer_head * bh_use[NAMEI_RA_SIZE]; @@ -863,16 +863,15 @@ static struct buffer_head * ext3_find_entry (struct dentry *dentry, buffer */ int num = 0; int nblocks, i, err; - struct inode *dir = dentry->d_parent->d_inode; int namelen; *res_dir = NULL; sb = dir->i_sb; - namelen = dentry->d_name.len; + namelen = entry->len; if (namelen > EXT3_NAME_LEN) return NULL; if (is_dx(dir)) { - bh = ext3_dx_find_entry(dentry, res_dir, &err); + bh = ext3_dx_find_entry(dir, entry, res_dir, &err); /* * On success, or if the error was file not found, * return. Otherwise, fall back to doing a search the @@ -923,7 +922,7 @@ restart: brelse(bh); goto next; } - i = search_dirblock(bh, dir, dentry, + i = search_dirblock(bh, dir, entry, block << EXT3_BLOCK_SIZE_BITS(sb), res_dir); if (i == 1) { EXT3_I(dir)->i_dir_start_lookup = block; @@ -957,8 +956,9 @@ cleanup_and_exit: return ret; } -static struct buffer_head * ext3_dx_find_entry(struct dentry *dentry, - struct ext3_dir_entry_2 **res_dir, int *err) +static struct buffer_head * ext3_dx_find_entry(struct inode *dir, + struct qstr *entry, struct ext3_dir_entry_2 **res_dir, + int *err) { struct super_block * sb; struct dx_hash_info hinfo; @@ -968,14 +968,13 @@ static struct buffer_head * ext3_dx_find_entry(struct dentry *dentry, struct buffer_head *bh; unsigned long block; int retval; - int namelen = dentry->d_name.len; - const u8 *name = dentry->d_name.name; - struct inode *dir = dentry->d_parent->d_inode; + int namelen = entry->len; + const u8 *name = entry->name; sb = dir->i_sb; /* NFS may look up ".." - look at dx_root directory block */ - if (namelen > 2 || name[0] != '.'||(name[1] != '.' && name[1] != '\0')){ - if (!(frame = dx_probe(dentry, NULL, &hinfo, frames, err))) + if (namelen > 2 || name[0] != '.'|| (namelen == 2 && name[1] != '.')) { + if (!(frame = dx_probe(entry, dir, &hinfo, frames, err))) return NULL; } else { frame = frames; @@ -1036,7 +1035,7 @@ static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, str if (dentry->d_name.len > EXT3_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); - bh = ext3_find_entry(dentry, &de); + bh = ext3_find_entry(dir, &dentry->d_name, &de); inode = NULL; if (bh) { unsigned long ino = le32_to_cpu(de->inode); @@ -1057,18 +1056,11 @@ static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, str struct dentry *ext3_get_parent(struct dentry *child) { unsigned long ino; - struct dentry *parent; - struct inode *inode; - struct dentry dotdot; + struct qstr dotdot = {.name = "..", .len = 2}; struct ext3_dir_entry_2 * de; struct buffer_head *bh; - dotdot.d_name.name = ".."; - dotdot.d_name.len = 2; - dotdot.d_parent = child; /* confusing, isn't it! */ - - bh = ext3_find_entry(&dotdot, &de); - inode = NULL; + bh = ext3_find_entry(child->d_inode, &dotdot, &de); if (!bh) return ERR_PTR(-ENOENT); ino = le32_to_cpu(de->inode); @@ -1080,16 +1072,7 @@ struct dentry *ext3_get_parent(struct dentry *child) return ERR_PTR(-EIO); } - inode = ext3_iget(child->d_inode->i_sb, ino); - if (IS_ERR(inode)) - return ERR_CAST(inode); - - parent = d_alloc_anon(inode); - if (!parent) { - iput(inode); - parent = ERR_PTR(-ENOMEM); - } - return parent; + return d_obtain_alias(ext3_iget(child->d_inode->i_sb, ino)); } #define S_SHIFT 12 @@ -1503,7 +1486,7 @@ static int ext3_dx_add_entry(handle_t *handle, struct dentry *dentry, struct ext3_dir_entry_2 *de; int err; - frame = dx_probe(dentry, NULL, &hinfo, frames, &err); + frame = dx_probe(&dentry->d_name, dir, &hinfo, frames, &err); if (!frame) return err; entries = frame->entries; @@ -2056,7 +2039,7 @@ static int ext3_rmdir (struct inode * dir, struct dentry *dentry) return PTR_ERR(handle); retval = -ENOENT; - bh = ext3_find_entry (dentry, &de); + bh = ext3_find_entry(dir, &dentry->d_name, &de); if (!bh) goto end_rmdir; @@ -2118,7 +2101,7 @@ static int ext3_unlink(struct inode * dir, struct dentry *dentry) handle->h_sync = 1; retval = -ENOENT; - bh = ext3_find_entry (dentry, &de); + bh = ext3_find_entry(dir, &dentry->d_name, &de); if (!bh) goto end_unlink; @@ -2276,7 +2259,7 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry, if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) handle->h_sync = 1; - old_bh = ext3_find_entry (old_dentry, &old_de); + old_bh = ext3_find_entry(old_dir, &old_dentry->d_name, &old_de); /* * Check for inode number is _not_ due to possible IO errors. * We might rmdir the source, keep it as pwd of some process @@ -2289,7 +2272,7 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry, goto end_rename; new_inode = new_dentry->d_inode; - new_bh = ext3_find_entry (new_dentry, &new_de); + new_bh = ext3_find_entry(new_dir, &new_dentry->d_name, &new_de); if (new_bh) { if (!new_inode) { brelse (new_bh); @@ -2355,7 +2338,8 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry, struct buffer_head *old_bh2; struct ext3_dir_entry_2 *old_de2; - old_bh2 = ext3_find_entry(old_dentry, &old_de2); + old_bh2 = ext3_find_entry(old_dir, &old_dentry->d_name, + &old_de2); if (old_bh2) { retval = ext3_delete_entry(handle, old_dir, old_de2, old_bh2); diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 3a260af5544..18eaa78ecb4 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -347,7 +347,7 @@ fail: static int ext3_blkdev_put(struct block_device *bdev) { bd_release(bdev); - return blkdev_put(bdev); + return blkdev_put(bdev, FMODE_READ|FMODE_WRITE); } static int ext3_blkdev_remove(struct ext3_sb_info *sbi) @@ -393,7 +393,8 @@ static void ext3_put_super (struct super_block * sb) int i; ext3_xattr_put_super(sb); - journal_destroy(sbi->s_journal); + if (journal_destroy(sbi->s_journal) < 0) + ext3_abort(sb, __func__, "Couldn't clean up the journal"); if (!(sb->s_flags & MS_RDONLY)) { EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER); es->s_state = cpu_to_le16(sbi->s_mount_state); @@ -2066,7 +2067,7 @@ static journal_t *ext3_get_dev_journal(struct super_block *sb, if (bd_claim(bdev, sb)) { printk(KERN_ERR "EXT3: failed to claim external journal device.\n"); - blkdev_put(bdev); + blkdev_put(bdev, FMODE_READ|FMODE_WRITE); return NULL; } @@ -2296,7 +2297,9 @@ static void ext3_mark_recovery_complete(struct super_block * sb, journal_t *journal = EXT3_SB(sb)->s_journal; journal_lock_updates(journal); - journal_flush(journal); + if (journal_flush(journal) < 0) + goto out; + lock_super(sb); if (EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER) && sb->s_flags & MS_RDONLY) { @@ -2305,6 +2308,8 @@ static void ext3_mark_recovery_complete(struct super_block * sb, ext3_commit_super(sb, es, 1); } unlock_super(sb); + +out: journal_unlock_updates(journal); } @@ -2404,7 +2409,13 @@ static void ext3_write_super_lockfs(struct super_block *sb) /* Now we set up the journal barrier. */ journal_lock_updates(journal); - journal_flush(journal); + + /* + * We don't want to clear needs_recovery flag when we failed + * to flush the journal. + */ + if (journal_flush(journal) < 0) + return; /* Journal blocked and flushed, clear needs_recovery flag. */ EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER); @@ -2783,30 +2794,30 @@ static int ext3_quota_on_mount(struct super_block *sb, int type) * Standard function to be called on quota_on */ static int ext3_quota_on(struct super_block *sb, int type, int format_id, - char *path, int remount) + char *name, int remount) { int err; - struct nameidata nd; + struct path path; if (!test_opt(sb, QUOTA)) return -EINVAL; - /* When remounting, no checks are needed and in fact, path is NULL */ + /* When remounting, no checks are needed and in fact, name is NULL */ if (remount) - return vfs_quota_on(sb, type, format_id, path, remount); + return vfs_quota_on(sb, type, format_id, name, remount); - err = path_lookup(path, LOOKUP_FOLLOW, &nd); + err = kern_path(name, LOOKUP_FOLLOW, &path); if (err) return err; /* Quotafile not on the same filesystem? */ - if (nd.path.mnt->mnt_sb != sb) { - path_put(&nd.path); + if (path.mnt->mnt_sb != sb) { + path_put(&path); return -EXDEV; } /* Journaling quota? */ if (EXT3_SB(sb)->s_qf_names[type]) { /* Quotafile not of fs root? */ - if (nd.path.dentry->d_parent->d_inode != sb->s_root->d_inode) + if (path.dentry->d_parent != sb->s_root) printk(KERN_WARNING "EXT3-fs: Quota file not on filesystem root. " "Journaled quota will not work.\n"); @@ -2816,18 +2827,22 @@ static int ext3_quota_on(struct super_block *sb, int type, int format_id, * When we journal data on quota file, we have to flush journal to see * all updates to the file when we bypass pagecache... */ - if (ext3_should_journal_data(nd.path.dentry->d_inode)) { + if (ext3_should_journal_data(path.dentry->d_inode)) { /* * We don't need to lock updates but journal_flush() could * otherwise be livelocked... */ journal_lock_updates(EXT3_SB(sb)->s_journal); - journal_flush(EXT3_SB(sb)->s_journal); + err = journal_flush(EXT3_SB(sb)->s_journal); journal_unlock_updates(EXT3_SB(sb)->s_journal); + if (err) { + path_put(&path); + return err; + } } - err = vfs_quota_on_path(sb, type, format_id, &nd.path); - path_put(&nd.path); + err = vfs_quota_on_path(sb, type, format_id, &path); + path_put(&path); return err; } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 92db9e94514..63adcb79298 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1061,7 +1061,6 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, stru struct dentry *ext4_get_parent(struct dentry *child) { unsigned long ino; - struct dentry *parent; struct inode *inode; static const struct qstr dotdot = { .name = "..", @@ -1083,16 +1082,7 @@ struct dentry *ext4_get_parent(struct dentry *child) return ERR_PTR(-EIO); } - inode = ext4_iget(child->d_inode->i_sb, ino); - if (IS_ERR(inode)) - return ERR_CAST(inode); - - parent = d_alloc_anon(inode); - if (!parent) { - iput(inode); - parent = ERR_PTR(-ENOMEM); - } - return parent; + return d_obtain_alias(ext4_iget(child->d_inode->i_sb, ino)); } #define S_SHIFT 12 diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 9b2b2bc4ec1..bdddea14e78 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -399,7 +399,7 @@ fail: static int ext4_blkdev_put(struct block_device *bdev) { bd_release(bdev); - return blkdev_put(bdev); + return blkdev_put(bdev, FMODE_READ|FMODE_WRITE); } static int ext4_blkdev_remove(struct ext4_sb_info *sbi) @@ -2553,7 +2553,7 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, if (bd_claim(bdev, sb)) { printk(KERN_ERR "EXT4: failed to claim external journal device.\n"); - blkdev_put(bdev); + blkdev_put(bdev, FMODE_READ|FMODE_WRITE); return NULL; } @@ -3328,30 +3328,30 @@ static int ext4_quota_on_mount(struct super_block *sb, int type) * Standard function to be called on quota_on */ static int ext4_quota_on(struct super_block *sb, int type, int format_id, - char *path, int remount) + char *name, int remount) { int err; - struct nameidata nd; + struct path path; if (!test_opt(sb, QUOTA)) return -EINVAL; - /* When remounting, no checks are needed and in fact, path is NULL */ + /* When remounting, no checks are needed and in fact, name is NULL */ if (remount) - return vfs_quota_on(sb, type, format_id, path, remount); + return vfs_quota_on(sb, type, format_id, name, remount); - err = path_lookup(path, LOOKUP_FOLLOW, &nd); + err = kern_path(name, LOOKUP_FOLLOW, &path); if (err) return err; /* Quotafile not on the same filesystem? */ - if (nd.path.mnt->mnt_sb != sb) { - path_put(&nd.path); + if (path.mnt->mnt_sb != sb) { + path_put(&path); return -EXDEV; } /* Journaling quota? */ if (EXT4_SB(sb)->s_qf_names[type]) { /* Quotafile not in fs root? */ - if (nd.path.dentry->d_parent->d_inode != sb->s_root->d_inode) + if (path.dentry->d_parent != sb->s_root) printk(KERN_WARNING "EXT4-fs: Quota file not on filesystem root. " "Journaled quota will not work.\n"); @@ -3361,7 +3361,7 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, * When we journal data on quota file, we have to flush journal to see * all updates to the file when we bypass pagecache... */ - if (ext4_should_journal_data(nd.path.dentry->d_inode)) { + if (ext4_should_journal_data(path.dentry->d_inode)) { /* * We don't need to lock updates but journal_flush() could * otherwise be livelocked... @@ -3370,13 +3370,13 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, err = jbd2_journal_flush(EXT4_SB(sb)->s_journal); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); if (err) { - path_put(&nd.path); + path_put(&path); return err; } } - err = vfs_quota_on_path(sb, type, format_id, &nd.path); - path_put(&nd.path); + err = vfs_quota_on_path(sb, type, format_id, &path); + path_put(&path); return err; } diff --git a/fs/fat/dir.c b/fs/fat/dir.c index cd4a0162e10..bae1c329252 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -839,6 +839,7 @@ const struct file_operations fat_dir_operations = { .compat_ioctl = fat_compat_dir_ioctl, #endif .fsync = file_fsync, + .llseek = generic_file_llseek, }; static int fat_get_short_entry(struct inode *dir, loff_t *pos, diff --git a/fs/fat/inode.c b/fs/fat/inode.c index d12cdf2a040..19eafbe3c37 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -681,33 +681,24 @@ static struct dentry *fat_fh_to_dentry(struct super_block *sb, inode = NULL; } } - if (!inode) { - /* For now, do nothing - * What we could do is: - * follow the file starting at fh[4], and record - * the ".." entry, and the name of the fh[2] entry. - * The follow the ".." file finding the next step up. - * This way we build a path to the root of - * the tree. If this works, we lookup the path and so - * get this inode into the cache. - * Finally try the fat_iget lookup again - * If that fails, then weare totally out of luck - * But all that is for another day - */ - } - if (!inode) - return ERR_PTR(-ESTALE); - - /* now to find a dentry. - * If possible, get a well-connected one + /* + * For now, do nothing if the inode is not found. + * + * What we could do is: + * + * - follow the file starting at fh[4], and record the ".." entry, + * and the name of the fh[2] entry. + * - then follow the ".." file finding the next step up. + * + * This way we build a path to the root of the tree. If this works, we + * lookup the path and so get this inode into the cache. Finally try + * the fat_iget lookup again. If that fails, then we are totally out + * of luck. But all that is for another day */ - result = d_alloc_anon(inode); - if (result == NULL) { - iput(inode); - return ERR_PTR(-ENOMEM); - } - result->d_op = sb->s_root->d_op; + result = d_obtain_alias(inode); + if (!IS_ERR(result)) + result->d_op = sb->s_root->d_op; return result; } @@ -754,15 +745,8 @@ static struct dentry *fat_get_parent(struct dentry *child) } inode = fat_build_inode(sb, de, i_pos); brelse(bh); - if (IS_ERR(inode)) { - parent = ERR_CAST(inode); - goto out; - } - parent = d_alloc_anon(inode); - if (!parent) { - iput(inode); - parent = ERR_PTR(-ENOMEM); - } + + parent = d_obtain_alias(inode); out: unlock_super(sb); diff --git a/fs/fifo.c b/fs/fifo.c index 987bf941149..f8f97b8b6d4 100644 --- a/fs/fifo.c +++ b/fs/fifo.c @@ -51,7 +51,7 @@ static int fifo_open(struct inode *inode, struct file *filp) filp->f_mode &= (FMODE_READ | FMODE_WRITE); switch (filp->f_mode) { - case 1: + case FMODE_READ: /* * O_RDONLY * POSIX.1 says that O_NONBLOCK means return with the FIFO @@ -76,7 +76,7 @@ static int fifo_open(struct inode *inode, struct file *filp) } break; - case 2: + case FMODE_WRITE: /* * O_WRONLY * POSIX.1 says that O_NONBLOCK means return -1 with @@ -98,7 +98,7 @@ static int fifo_open(struct inode *inode, struct file *filp) } break; - case 3: + case FMODE_READ | FMODE_WRITE: /* * O_RDWR * POSIX.1 leaves this case "undefined" when O_NONBLOCK is set. diff --git a/fs/file_table.c b/fs/file_table.c index f45a4493f9e..efc06faede6 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -161,7 +161,7 @@ EXPORT_SYMBOL(get_empty_filp); * code should be moved into this function. */ struct file *alloc_file(struct vfsmount *mnt, struct dentry *dentry, - mode_t mode, const struct file_operations *fop) + fmode_t mode, const struct file_operations *fop) { struct file *file; struct path; @@ -193,7 +193,7 @@ EXPORT_SYMBOL(alloc_file); * of this should be moving to alloc_file(). */ int init_file(struct file *file, struct vfsmount *mnt, struct dentry *dentry, - mode_t mode, const struct file_operations *fop) + fmode_t mode, const struct file_operations *fop) { int error = 0; file->f_path.dentry = dentry; diff --git a/fs/filesystems.c b/fs/filesystems.c index f37f8726283..d0e20ced62d 100644 --- a/fs/filesystems.c +++ b/fs/filesystems.c @@ -8,6 +8,8 @@ #include <linux/syscalls.h> #include <linux/fs.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> #include <linux/slab.h> #include <linux/kmod.h> #include <linux/init.h> @@ -214,6 +216,43 @@ int get_filesystem_list(char * buf) return len; } +#ifdef CONFIG_PROC_FS +static int filesystems_proc_show(struct seq_file *m, void *v) +{ + struct file_system_type * tmp; + + read_lock(&file_systems_lock); + tmp = file_systems; + while (tmp) { + seq_printf(m, "%s\t%s\n", + (tmp->fs_flags & FS_REQUIRES_DEV) ? "" : "nodev", + tmp->name); + tmp = tmp->next; + } + read_unlock(&file_systems_lock); + return 0; +} + +static int filesystems_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, filesystems_proc_show, NULL); +} + +static const struct file_operations filesystems_proc_fops = { + .open = filesystems_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init proc_filesystems_init(void) +{ + proc_create("filesystems", 0, NULL, &filesystems_proc_fops); + return 0; +} +module_init(proc_filesystems_init); +#endif + struct file_system_type *get_fs_type(const char *name) { struct file_system_type *fs; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 2bada6bbc31..34930a964b8 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -101,6 +101,8 @@ void fuse_finish_open(struct inode *inode, struct file *file, file->f_op = &fuse_direct_io_file_operations; if (!(outarg->open_flags & FOPEN_KEEP_CACHE)) invalidate_inode_pages2(inode->i_mapping); + if (outarg->open_flags & FOPEN_NONSEEKABLE) + nonseekable_open(inode, file); ff->fh = outarg->fh; file->private_data = fuse_file_get(ff); } @@ -1448,6 +1450,9 @@ static loff_t fuse_file_llseek(struct file *file, loff_t offset, int origin) mutex_lock(&inode->i_mutex); switch (origin) { case SEEK_END: + retval = fuse_update_attributes(inode, NULL, file, NULL); + if (retval) + return retval; offset += i_size_read(inode); break; case SEEK_CUR: diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 3a876076bdd..35accfdd747 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -6,6 +6,9 @@ See the file COPYING. */ +#ifndef _FS_FUSE_I_H +#define _FS_FUSE_I_H + #include <linux/fuse.h> #include <linux/fs.h> #include <linux/mount.h> @@ -655,3 +658,5 @@ void fuse_set_nowrite(struct inode *inode); void fuse_release_nowrite(struct inode *inode); u64 fuse_get_attr_version(struct fuse_conn *fc); + +#endif /* _FS_FUSE_I_H */ diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 6a84388cacf..2e99f34b443 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -596,12 +596,8 @@ static struct dentry *fuse_get_dentry(struct super_block *sb, if (inode->i_generation != handle->generation) goto out_iput; - entry = d_alloc_anon(inode); - err = -ENOMEM; - if (!entry) - goto out_iput; - - if (get_node_id(inode) != FUSE_ROOT_ID) { + entry = d_obtain_alias(inode); + if (!IS_ERR(entry) && get_node_id(inode) != FUSE_ROOT_ID) { entry->d_op = &fuse_dentry_operations; fuse_invalidate_entry_cache(entry); } @@ -696,17 +692,14 @@ static struct dentry *fuse_get_parent(struct dentry *child) name.name = ".."; err = fuse_lookup_name(child_inode->i_sb, get_node_id(child_inode), &name, &outarg, &inode); - if (err && err != -ENOENT) + if (err) { + if (err == -ENOENT) + return ERR_PTR(-ESTALE); return ERR_PTR(err); - if (err || !inode) - return ERR_PTR(-ESTALE); - - parent = d_alloc_anon(inode); - if (!parent) { - iput(inode); - return ERR_PTR(-ENOMEM); } - if (get_node_id(inode) != FUSE_ROOT_ID) { + + parent = d_obtain_alias(inode); + if (!IS_ERR(parent) && get_node_id(inode) != FUSE_ROOT_ID) { parent->d_op = &fuse_dentry_operations; fuse_invalidate_entry_cache(parent); } @@ -865,7 +858,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) if (is_bdev) { fc->destroy_req = fuse_request_alloc(); if (!fc->destroy_req) - goto err_put_root; + goto err_free_init_req; } mutex_lock(&fuse_mutex); @@ -895,6 +888,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) err_unlock: mutex_unlock(&fuse_mutex); + err_free_init_req: fuse_request_free(init_req); err_put_root: dput(root_dentry); diff --git a/fs/gfs2/ops_export.c b/fs/gfs2/ops_export.c index 9cda8536530..bbb8c36403a 100644 --- a/fs/gfs2/ops_export.c +++ b/fs/gfs2/ops_export.c @@ -130,28 +130,17 @@ static int gfs2_get_name(struct dentry *parent, char *name, static struct dentry *gfs2_get_parent(struct dentry *child) { struct qstr dotdot; - struct inode *inode; struct dentry *dentry; - gfs2_str2qstr(&dotdot, ".."); - inode = gfs2_lookupi(child->d_inode, &dotdot, 1); - - if (!inode) - return ERR_PTR(-ENOENT); /* - * In case of an error, @inode carries the error value, and we - * have to return that as a(n invalid) pointer to dentry. + * XXX(hch): it would be a good idea to keep this around as a + * static variable. */ - if (IS_ERR(inode)) - return ERR_CAST(inode); - - dentry = d_alloc_anon(inode); - if (!dentry) { - iput(inode); - return ERR_PTR(-ENOMEM); - } + gfs2_str2qstr(&dotdot, ".."); - dentry->d_op = &gfs2_dops; + dentry = d_obtain_alias(gfs2_lookupi(child->d_inode, &dotdot, 1)); + if (!IS_ERR(dentry)) + dentry->d_op = &gfs2_dops; return dentry; } @@ -233,13 +222,9 @@ static struct dentry *gfs2_get_dentry(struct super_block *sb, gfs2_glock_dq_uninit(&i_gh); out_inode: - dentry = d_alloc_anon(inode); - if (!dentry) { - iput(inode); - return ERR_PTR(-ENOMEM); - } - - dentry->d_op = &gfs2_dops; + dentry = d_obtain_alias(inode); + if (!IS_ERR(dentry)) + dentry->d_op = &gfs2_dops; return dentry; fail_rgd: diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c index 534e1e2c65c..d232991b904 100644 --- a/fs/gfs2/ops_inode.c +++ b/fs/gfs2/ops_inode.c @@ -69,7 +69,7 @@ static int gfs2_create(struct inode *dir, struct dentry *dentry, mark_inode_dirty(inode); break; } else if (PTR_ERR(inode) != -EEXIST || - (nd && (nd->intent.open.flags & O_EXCL))) { + (nd && nd->flags & LOOKUP_EXCL)) { gfs2_holder_uninit(ghs); return PTR_ERR(inode); } diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 7e19835efa2..c69b7ac75bf 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -511,13 +511,6 @@ void hfs_clear_inode(struct inode *inode) } } -static int hfs_permission(struct inode *inode, int mask) -{ - if (S_ISREG(inode->i_mode) && mask & MAY_EXEC) - return 0; - return generic_permission(inode, mask, NULL); -} - static int hfs_file_open(struct inode *inode, struct file *file) { if (HFS_IS_RSRC(inode)) @@ -616,7 +609,6 @@ static const struct inode_operations hfs_file_inode_operations = { .lookup = hfs_file_lookup, .truncate = hfs_file_truncate, .setattr = hfs_inode_setattr, - .permission = hfs_permission, .setxattr = hfs_setxattr, .getxattr = hfs_getxattr, .listxattr = hfs_listxattr, diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 963be644297..b207f0e6fc2 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -238,18 +238,6 @@ static void hfsplus_set_perms(struct inode *inode, struct hfsplus_perm *perms) perms->dev = cpu_to_be32(HFSPLUS_I(inode).dev); } -static int hfsplus_permission(struct inode *inode, int mask) -{ - /* MAY_EXEC is also used for lookup, if no x bit is set allow lookup, - * open_exec has the same test, so it's still not executable, if a x bit - * is set fall back to standard permission check. - */ - if (S_ISREG(inode->i_mode) && mask & MAY_EXEC && !(inode->i_mode & 0111)) - return 0; - return generic_permission(inode, mask, NULL); -} - - static int hfsplus_file_open(struct inode *inode, struct file *file) { if (HFSPLUS_IS_RSRC(inode)) @@ -281,7 +269,6 @@ static int hfsplus_file_release(struct inode *inode, struct file *file) static const struct inode_operations hfsplus_file_inode_operations = { .lookup = hfsplus_file_lookup, .truncate = hfsplus_file_truncate, - .permission = hfsplus_permission, .setxattr = hfsplus_setxattr, .getxattr = hfsplus_getxattr, .listxattr = hfsplus_listxattr, diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index d6ecabf4d23..7f34f4385de 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -20,7 +20,7 @@ struct hostfs_inode_info { char *host_filename; int fd; - int mode; + fmode_t mode; struct inode vfs_inode; }; @@ -373,7 +373,8 @@ int hostfs_readdir(struct file *file, void *ent, filldir_t filldir) int hostfs_file_open(struct inode *ino, struct file *file) { char *name; - int mode = 0, r = 0, w = 0, fd; + fmode_t mode = 0; + int r = 0, w = 0, fd; mode = file->f_mode & (FMODE_READ | FMODE_WRITE); if ((mode & HOSTFS_I(ino)->mode) == mode) diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index be8be5040e0..64ab5225920 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -143,5 +143,5 @@ const struct file_operations hpfs_file_ops = const struct inode_operations hpfs_file_iops = { .truncate = hpfs_truncate, - .setattr = hpfs_notify_change, + .setattr = hpfs_setattr, }; diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h index 42ff60ccf2a..c2ea31bae31 100644 --- a/fs/hpfs/hpfs_fn.h +++ b/fs/hpfs/hpfs_fn.h @@ -275,7 +275,7 @@ void hpfs_init_inode(struct inode *); void hpfs_read_inode(struct inode *); void hpfs_write_inode(struct inode *); void hpfs_write_inode_nolock(struct inode *); -int hpfs_notify_change(struct dentry *, struct iattr *); +int hpfs_setattr(struct dentry *, struct iattr *); void hpfs_write_if_changed(struct inode *); void hpfs_delete_inode(struct inode *); diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c index 85d3e1d9ac0..39a1bfbea31 100644 --- a/fs/hpfs/inode.c +++ b/fs/hpfs/inode.c @@ -260,19 +260,28 @@ void hpfs_write_inode_nolock(struct inode *i) brelse(bh); } -int hpfs_notify_change(struct dentry *dentry, struct iattr *attr) +int hpfs_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = dentry->d_inode; - int error=0; + int error = -EINVAL; + lock_kernel(); - if ( ((attr->ia_valid & ATTR_SIZE) && attr->ia_size > inode->i_size) || - (hpfs_sb(inode->i_sb)->sb_root == inode->i_ino) ) { - error = -EINVAL; - } else if ((error = inode_change_ok(inode, attr))) { - } else if ((error = inode_setattr(inode, attr))) { - } else { - hpfs_write_inode(inode); - } + if (inode->i_ino == hpfs_sb(inode->i_sb)->sb_root) + goto out_unlock; + if ((attr->ia_valid & ATTR_SIZE) && attr->ia_size > inode->i_size) + goto out_unlock; + + error = inode_change_ok(inode, attr); + if (error) + goto out_unlock; + + error = inode_setattr(inode, attr); + if (error) + goto out_unlock; + + hpfs_write_inode(inode); + + out_unlock: unlock_kernel(); return error; } diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index d9c59a77544..10783f3d265 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -669,5 +669,5 @@ const struct inode_operations hpfs_dir_iops = .rmdir = hpfs_rmdir, .mknod = hpfs_mknod, .rename = hpfs_rename, - .setattr = hpfs_notify_change, + .setattr = hpfs_setattr, }; diff --git a/fs/isofs/export.c b/fs/isofs/export.c index bb219138331..e81a30593ba 100644 --- a/fs/isofs/export.c +++ b/fs/isofs/export.c @@ -22,7 +22,7 @@ isofs_export_iget(struct super_block *sb, __u32 generation) { struct inode *inode; - struct dentry *result; + if (block == 0) return ERR_PTR(-ESTALE); inode = isofs_iget(sb, block, offset); @@ -32,12 +32,7 @@ isofs_export_iget(struct super_block *sb, iput(inode); return ERR_PTR(-ESTALE); } - result = d_alloc_anon(inode); - if (!result) { - iput(inode); - return ERR_PTR(-ENOMEM); - } - return result; + return d_obtain_alias(inode); } /* This function is surprisingly simple. The trick is understanding @@ -51,7 +46,6 @@ static struct dentry *isofs_export_get_parent(struct dentry *child) unsigned long parent_offset = 0; struct inode *child_inode = child->d_inode; struct iso_inode_info *e_child_inode = ISOFS_I(child_inode); - struct inode *parent_inode = NULL; struct iso_directory_record *de = NULL; struct buffer_head * bh = NULL; struct dentry *rv = NULL; @@ -104,28 +98,11 @@ static struct dentry *isofs_export_get_parent(struct dentry *child) /* Normalize */ isofs_normalize_block_and_offset(de, &parent_block, &parent_offset); - /* Get the inode. */ - parent_inode = isofs_iget(child_inode->i_sb, - parent_block, - parent_offset); - if (IS_ERR(parent_inode)) { - rv = ERR_CAST(parent_inode); - if (rv != ERR_PTR(-ENOMEM)) - rv = ERR_PTR(-EACCES); - goto out; - } - - /* Allocate the dentry. */ - rv = d_alloc_anon(parent_inode); - if (rv == NULL) { - rv = ERR_PTR(-ENOMEM); - goto out; - } - + rv = d_obtain_alias(isofs_iget(child_inode->i_sb, parent_block, + parent_offset)); out: - if (bh) { + if (bh) brelse(bh); - } return rv; } diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c index a5432bbbfb8..1bd8d4acc6f 100644 --- a/fs/jbd/checkpoint.c +++ b/fs/jbd/checkpoint.c @@ -93,7 +93,8 @@ static int __try_to_free_cp_buf(struct journal_head *jh) int ret = 0; struct buffer_head *bh = jh2bh(jh); - if (jh->b_jlist == BJ_None && !buffer_locked(bh) && !buffer_dirty(bh)) { + if (jh->b_jlist == BJ_None && !buffer_locked(bh) && + !buffer_dirty(bh) && !buffer_write_io_error(bh)) { JBUFFER_TRACE(jh, "remove from checkpoint list"); ret = __journal_remove_checkpoint(jh) + 1; jbd_unlock_bh_state(bh); @@ -126,14 +127,29 @@ void __log_wait_for_space(journal_t *journal) /* * Test again, another process may have checkpointed while we - * were waiting for the checkpoint lock + * were waiting for the checkpoint lock. If there are no + * outstanding transactions there is nothing to checkpoint and + * we can't make progress. Abort the journal in this case. */ spin_lock(&journal->j_state_lock); + spin_lock(&journal->j_list_lock); nblocks = jbd_space_needed(journal); if (__log_space_left(journal) < nblocks) { + int chkpt = journal->j_checkpoint_transactions != NULL; + + spin_unlock(&journal->j_list_lock); spin_unlock(&journal->j_state_lock); - log_do_checkpoint(journal); + if (chkpt) { + log_do_checkpoint(journal); + } else { + printk(KERN_ERR "%s: no transactions\n", + __func__); + journal_abort(journal, 0); + } + spin_lock(&journal->j_state_lock); + } else { + spin_unlock(&journal->j_list_lock); } mutex_unlock(&journal->j_checkpoint_mutex); } @@ -160,21 +176,25 @@ static void jbd_sync_bh(journal_t *journal, struct buffer_head *bh) * buffers. Note that we take the buffers in the opposite ordering * from the one in which they were submitted for IO. * + * Return 0 on success, and return <0 if some buffers have failed + * to be written out. + * * Called with j_list_lock held. */ -static void __wait_cp_io(journal_t *journal, transaction_t *transaction) +static int __wait_cp_io(journal_t *journal, transaction_t *transaction) { struct journal_head *jh; struct buffer_head *bh; tid_t this_tid; int released = 0; + int ret = 0; this_tid = transaction->t_tid; restart: /* Did somebody clean up the transaction in the meanwhile? */ if (journal->j_checkpoint_transactions != transaction || transaction->t_tid != this_tid) - return; + return ret; while (!released && transaction->t_checkpoint_io_list) { jh = transaction->t_checkpoint_io_list; bh = jh2bh(jh); @@ -194,6 +214,9 @@ restart: spin_lock(&journal->j_list_lock); goto restart; } + if (unlikely(buffer_write_io_error(bh))) + ret = -EIO; + /* * Now in whatever state the buffer currently is, we know that * it has been written out and so we can drop it from the list @@ -203,6 +226,8 @@ restart: journal_remove_journal_head(bh); __brelse(bh); } + + return ret; } #define NR_BATCH 64 @@ -226,7 +251,8 @@ __flush_batch(journal_t *journal, struct buffer_head **bhs, int *batch_count) * Try to flush one buffer from the checkpoint list to disk. * * Return 1 if something happened which requires us to abort the current - * scan of the checkpoint list. + * scan of the checkpoint list. Return <0 if the buffer has failed to + * be written out. * * Called with j_list_lock held and drops it if 1 is returned * Called under jbd_lock_bh_state(jh2bh(jh)), and drops it @@ -256,6 +282,9 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh, log_wait_commit(journal, tid); ret = 1; } else if (!buffer_dirty(bh)) { + ret = 1; + if (unlikely(buffer_write_io_error(bh))) + ret = -EIO; J_ASSERT_JH(jh, !buffer_jbddirty(bh)); BUFFER_TRACE(bh, "remove from checkpoint"); __journal_remove_checkpoint(jh); @@ -263,7 +292,6 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh, jbd_unlock_bh_state(bh); journal_remove_journal_head(bh); __brelse(bh); - ret = 1; } else { /* * Important: we are about to write the buffer, and @@ -295,6 +323,7 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh, * to disk. We submit larger chunks of data at once. * * The journal should be locked before calling this function. + * Called with j_checkpoint_mutex held. */ int log_do_checkpoint(journal_t *journal) { @@ -318,6 +347,7 @@ int log_do_checkpoint(journal_t *journal) * OK, we need to start writing disk blocks. Take one transaction * and write it. */ + result = 0; spin_lock(&journal->j_list_lock); if (!journal->j_checkpoint_transactions) goto out; @@ -334,7 +364,7 @@ restart: int batch_count = 0; struct buffer_head *bhs[NR_BATCH]; struct journal_head *jh; - int retry = 0; + int retry = 0, err; while (!retry && transaction->t_checkpoint_list) { struct buffer_head *bh; @@ -347,6 +377,8 @@ restart: break; } retry = __process_buffer(journal, jh, bhs,&batch_count); + if (retry < 0 && !result) + result = retry; if (!retry && (need_resched() || spin_needbreak(&journal->j_list_lock))) { spin_unlock(&journal->j_list_lock); @@ -371,14 +403,18 @@ restart: * Now we have cleaned up the first transaction's checkpoint * list. Let's clean up the second one */ - __wait_cp_io(journal, transaction); + err = __wait_cp_io(journal, transaction); + if (!result) + result = err; } out: spin_unlock(&journal->j_list_lock); - result = cleanup_journal_tail(journal); if (result < 0) - return result; - return 0; + journal_abort(journal, result); + else + result = cleanup_journal_tail(journal); + + return (result < 0) ? result : 0; } /* @@ -394,8 +430,9 @@ out: * This is the only part of the journaling code which really needs to be * aware of transaction aborts. Checkpointing involves writing to the * main filesystem area rather than to the journal, so it can proceed - * even in abort state, but we must not update the journal superblock if - * we have an abort error outstanding. + * even in abort state, but we must not update the super block if + * checkpointing may have failed. Otherwise, we would lose some metadata + * buffers which should be written-back to the filesystem. */ int cleanup_journal_tail(journal_t *journal) @@ -404,6 +441,9 @@ int cleanup_journal_tail(journal_t *journal) tid_t first_tid; unsigned long blocknr, freed; + if (is_journal_aborted(journal)) + return 1; + /* OK, work out the oldest transaction remaining in the log, and * the log block it starts at. * diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index aa7143a8349..9e4fa52d7dc 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -1121,9 +1121,12 @@ recovery_error: * * Release a journal_t structure once it is no longer in use by the * journaled object. + * Return <0 if we couldn't clean up the journal. */ -void journal_destroy(journal_t *journal) +int journal_destroy(journal_t *journal) { + int err = 0; + /* Wait for the commit thread to wake up and die. */ journal_kill_thread(journal); @@ -1146,11 +1149,16 @@ void journal_destroy(journal_t *journal) J_ASSERT(journal->j_checkpoint_transactions == NULL); spin_unlock(&journal->j_list_lock); - /* We can now mark the journal as empty. */ - journal->j_tail = 0; - journal->j_tail_sequence = ++journal->j_transaction_sequence; if (journal->j_sb_buffer) { - journal_update_superblock(journal, 1); + if (!is_journal_aborted(journal)) { + /* We can now mark the journal as empty. */ + journal->j_tail = 0; + journal->j_tail_sequence = + ++journal->j_transaction_sequence; + journal_update_superblock(journal, 1); + } else { + err = -EIO; + } brelse(journal->j_sb_buffer); } @@ -1160,6 +1168,8 @@ void journal_destroy(journal_t *journal) journal_destroy_revoke(journal); kfree(journal->j_wbuf); kfree(journal); + + return err; } @@ -1359,10 +1369,16 @@ int journal_flush(journal_t *journal) spin_lock(&journal->j_list_lock); while (!err && journal->j_checkpoint_transactions != NULL) { spin_unlock(&journal->j_list_lock); + mutex_lock(&journal->j_checkpoint_mutex); err = log_do_checkpoint(journal); + mutex_unlock(&journal->j_checkpoint_mutex); spin_lock(&journal->j_list_lock); } spin_unlock(&journal->j_list_lock); + + if (is_journal_aborted(journal)) + return -EIO; + cleanup_journal_tail(journal); /* Finally, mark the journal as really needing no recovery. @@ -1384,7 +1400,7 @@ int journal_flush(journal_t *journal) J_ASSERT(journal->j_head == journal->j_tail); J_ASSERT(journal->j_tail_sequence == journal->j_transaction_sequence); spin_unlock(&journal->j_state_lock); - return err; + return 0; } /** diff --git a/fs/jbd/recovery.c b/fs/jbd/recovery.c index 43bc5e5ed06..db5e982c5dd 100644 --- a/fs/jbd/recovery.c +++ b/fs/jbd/recovery.c @@ -223,7 +223,7 @@ do { \ */ int journal_recover(journal_t *journal) { - int err; + int err, err2; journal_superblock_t * sb; struct recovery_info info; @@ -261,7 +261,10 @@ int journal_recover(journal_t *journal) journal->j_transaction_sequence = ++info.end_transaction; journal_clear_revoke(journal); - sync_blockdev(journal->j_fs_dev); + err2 = sync_blockdev(journal->j_fs_dev); + if (!err) + err = err2; + return err; } diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index b1aaae823a5..6f60cc910f4 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -39,7 +39,8 @@ const struct file_operations jffs2_dir_operations = .read = generic_read_dir, .readdir = jffs2_readdir, .unlocked_ioctl=jffs2_ioctl, - .fsync = jffs2_fsync + .fsync = jffs2_fsync, + .llseek = generic_file_llseek, }; @@ -108,9 +109,7 @@ static struct dentry *jffs2_lookup(struct inode *dir_i, struct dentry *target, } } - d_add(target, inode); - - return NULL; + return d_splice_alias(inode, target); } /***********************************************************************/ diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index efd401257ed..4c4e18c54a5 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -22,6 +22,7 @@ #include <linux/mtd/super.h> #include <linux/ctype.h> #include <linux/namei.h> +#include <linux/exportfs.h> #include "compr.h" #include "nodelist.h" @@ -62,6 +63,52 @@ static int jffs2_sync_fs(struct super_block *sb, int wait) return 0; } +static struct inode *jffs2_nfs_get_inode(struct super_block *sb, uint64_t ino, + uint32_t generation) +{ + /* We don't care about i_generation. We'll destroy the flash + before we start re-using inode numbers anyway. And even + if that wasn't true, we'd have other problems...*/ + return jffs2_iget(sb, ino); +} + +static struct dentry *jffs2_fh_to_dentry(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type) +{ + return generic_fh_to_dentry(sb, fid, fh_len, fh_type, + jffs2_nfs_get_inode); +} + +static struct dentry *jffs2_fh_to_parent(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type) +{ + return generic_fh_to_parent(sb, fid, fh_len, fh_type, + jffs2_nfs_get_inode); +} + +static struct dentry *jffs2_get_parent(struct dentry *child) +{ + struct jffs2_inode_info *f; + uint32_t pino; + + BUG_ON(!S_ISDIR(child->d_inode->i_mode)); + + f = JFFS2_INODE_INFO(child->d_inode); + + pino = f->inocache->pino_nlink; + + JFFS2_DEBUG("Parent of directory ino #%u is #%u\n", + f->inocache->ino, pino); + + return d_obtain_alias(jffs2_iget(child->d_inode->i_sb, pino)); +} + +static struct export_operations jffs2_export_ops = { + .get_parent = jffs2_get_parent, + .fh_to_dentry = jffs2_fh_to_dentry, + .fh_to_parent = jffs2_fh_to_parent, +}; + static const struct super_operations jffs2_super_operations = { .alloc_inode = jffs2_alloc_inode, @@ -104,6 +151,7 @@ static int jffs2_fill_super(struct super_block *sb, void *data, int silent) spin_lock_init(&c->inocache_lock); sb->s_op = &jffs2_super_operations; + sb->s_export_op = &jffs2_export_ops; sb->s_flags = sb->s_flags | MS_NOATIME; sb->s_xattr = jffs2_xattr_handlers; #ifdef CONFIG_JFFS2_FS_POSIX_ACL diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c index cd2ec2988b5..335c4de6552 100644 --- a/fs/jfs/jfs_logmgr.c +++ b/fs/jfs/jfs_logmgr.c @@ -1168,7 +1168,7 @@ journal_found: bd_release(bdev); close: /* close external log device */ - blkdev_put(bdev); + blkdev_put(bdev, FMODE_READ|FMODE_WRITE); free: /* free log descriptor */ mutex_unlock(&jfs_log_mutex); @@ -1514,7 +1514,7 @@ int lmLogClose(struct super_block *sb) rc = lmLogShutdown(log); bd_release(bdev); - blkdev_put(bdev); + blkdev_put(bdev, FMODE_READ|FMODE_WRITE); kfree(log); diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 2aba8238681..cc3cedffbfa 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -1511,25 +1511,12 @@ struct dentry *jfs_fh_to_parent(struct super_block *sb, struct fid *fid, struct dentry *jfs_get_parent(struct dentry *dentry) { - struct super_block *sb = dentry->d_inode->i_sb; - struct dentry *parent = ERR_PTR(-ENOENT); - struct inode *inode; unsigned long parent_ino; parent_ino = le32_to_cpu(JFS_IP(dentry->d_inode)->i_dtroot.header.idotdot); - inode = jfs_iget(sb, parent_ino); - if (IS_ERR(inode)) { - parent = ERR_CAST(inode); - } else { - parent = d_alloc_anon(inode); - if (!parent) { - parent = ERR_PTR(-ENOMEM); - iput(inode); - } - } - return parent; + return d_obtain_alias(jfs_iget(dentry->d_inode->i_sb, parent_ino)); } const struct inode_operations jfs_dir_inode_operations = { @@ -1560,6 +1547,7 @@ const struct file_operations jfs_dir_operations = { #ifdef CONFIG_COMPAT .compat_ioctl = jfs_compat_ioctl, #endif + .llseek = generic_file_llseek, }; static int jfs_ci_hash(struct dentry *dir, struct qstr *this) diff --git a/fs/libfs.c b/fs/libfs.c index 1add676a19d..74688598bcf 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -732,28 +732,6 @@ out: return ret; } -/* - * This is what d_alloc_anon should have been. Once the exportfs - * argument transition has been finished I will update d_alloc_anon - * to this prototype and this wrapper will go away. --hch - */ -static struct dentry *exportfs_d_alloc(struct inode *inode) -{ - struct dentry *dentry; - - if (!inode) - return NULL; - if (IS_ERR(inode)) - return ERR_PTR(PTR_ERR(inode)); - - dentry = d_alloc_anon(inode); - if (!dentry) { - iput(inode); - dentry = ERR_PTR(-ENOMEM); - } - return dentry; -} - /** * generic_fh_to_dentry - generic helper for the fh_to_dentry export operation * @sb: filesystem to do the file handle conversion on @@ -782,7 +760,7 @@ struct dentry *generic_fh_to_dentry(struct super_block *sb, struct fid *fid, break; } - return exportfs_d_alloc(inode); + return d_obtain_alias(inode); } EXPORT_SYMBOL_GPL(generic_fh_to_dentry); @@ -815,7 +793,7 @@ struct dentry *generic_fh_to_parent(struct super_block *sb, struct fid *fid, break; } - return exportfs_d_alloc(inode); + return d_obtain_alias(inode); } EXPORT_SYMBOL_GPL(generic_fh_to_parent); diff --git a/fs/locks.c b/fs/locks.c index 5eb259e3cd3..09062e3ff10 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1580,7 +1580,8 @@ asmlinkage long sys_flock(unsigned int fd, unsigned int cmd) cmd &= ~LOCK_NB; unlock = (cmd == LOCK_UN); - if (!unlock && !(cmd & LOCK_MAND) && !(filp->f_mode & 3)) + if (!unlock && !(cmd & LOCK_MAND) && + !(filp->f_mode & (FMODE_READ|FMODE_WRITE))) goto out_putf; error = flock_make_lock(filp, &lock, cmd); @@ -2078,6 +2079,7 @@ int vfs_cancel_lock(struct file *filp, struct file_lock *fl) EXPORT_SYMBOL_GPL(vfs_cancel_lock); #ifdef CONFIG_PROC_FS +#include <linux/proc_fs.h> #include <linux/seq_file.h> static void lock_get_status(struct seq_file *f, struct file_lock *fl, @@ -2183,12 +2185,31 @@ static void locks_stop(struct seq_file *f, void *v) unlock_kernel(); } -struct seq_operations locks_seq_operations = { +static const struct seq_operations locks_seq_operations = { .start = locks_start, .next = locks_next, .stop = locks_stop, .show = locks_show, }; + +static int locks_open(struct inode *inode, struct file *filp) +{ + return seq_open(filp, &locks_seq_operations); +} + +static const struct file_operations proc_locks_operations = { + .open = locks_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init proc_locks_init(void) +{ + proc_create("locks", 0, NULL, &proc_locks_operations); + return 0; +} +module_init(proc_locks_init); #endif /** diff --git a/fs/namei.c b/fs/namei.c index 4ea63ed5e79..09ce58e49e7 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -212,8 +212,7 @@ int generic_permission(struct inode *inode, int mask, * Read/write DACs are always overridable. * Executable DACs are overridable if at least one exec bit is set. */ - if (!(mask & MAY_EXEC) || - (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode)) + if (!(mask & MAY_EXEC) || execute_ok(inode)) if (capable(CAP_DAC_OVERRIDE)) return 0; @@ -249,23 +248,11 @@ int inode_permission(struct inode *inode, int mask) } /* Ordinary permission routines do not understand MAY_APPEND. */ - if (inode->i_op && inode->i_op->permission) { + if (inode->i_op && inode->i_op->permission) retval = inode->i_op->permission(inode, mask); - if (!retval) { - /* - * Exec permission on a regular file is denied if none - * of the execute bits are set. - * - * This check should be done by the ->permission() - * method. - */ - if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode) && - !(inode->i_mode & S_IXUGO)) - return -EACCES; - } - } else { + else retval = generic_permission(inode, mask, NULL); - } + if (retval) return retval; @@ -1106,6 +1093,15 @@ int path_lookup(const char *name, unsigned int flags, return do_path_lookup(AT_FDCWD, name, flags, nd); } +int kern_path(const char *name, unsigned int flags, struct path *path) +{ + struct nameidata nd; + int res = do_path_lookup(AT_FDCWD, name, flags, &nd); + if (!res) + *path = nd.path; + return res; +} + /** * vfs_path_lookup - lookup a file path relative to a dentry-vfsmount pair * @dentry: pointer to dentry of the base directory @@ -1138,9 +1134,16 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, } -static int __path_lookup_intent_open(int dfd, const char *name, - unsigned int lookup_flags, struct nameidata *nd, - int open_flags, int create_mode) +/** + * path_lookup_open - lookup a file path with open intent + * @dfd: the directory to use as base, or AT_FDCWD + * @name: pointer to file name + * @lookup_flags: lookup intent flags + * @nd: pointer to nameidata + * @open_flags: open intent flags + */ +int path_lookup_open(int dfd, const char *name, unsigned int lookup_flags, + struct nameidata *nd, int open_flags) { struct file *filp = get_empty_filp(); int err; @@ -1149,7 +1152,7 @@ static int __path_lookup_intent_open(int dfd, const char *name, return -ENFILE; nd->intent.open.file = filp; nd->intent.open.flags = open_flags; - nd->intent.open.create_mode = create_mode; + nd->intent.open.create_mode = 0; err = do_path_lookup(dfd, name, lookup_flags|LOOKUP_OPEN, nd); if (IS_ERR(nd->intent.open.file)) { if (err == 0) { @@ -1161,38 +1164,6 @@ static int __path_lookup_intent_open(int dfd, const char *name, return err; } -/** - * path_lookup_open - lookup a file path with open intent - * @dfd: the directory to use as base, or AT_FDCWD - * @name: pointer to file name - * @lookup_flags: lookup intent flags - * @nd: pointer to nameidata - * @open_flags: open intent flags - */ -int path_lookup_open(int dfd, const char *name, unsigned int lookup_flags, - struct nameidata *nd, int open_flags) -{ - return __path_lookup_intent_open(dfd, name, lookup_flags, nd, - open_flags, 0); -} - -/** - * path_lookup_create - lookup a file path with open + create intent - * @dfd: the directory to use as base, or AT_FDCWD - * @name: pointer to file name - * @lookup_flags: lookup intent flags - * @nd: pointer to nameidata - * @open_flags: open intent flags - * @create_mode: create intent flags - */ -static int path_lookup_create(int dfd, const char *name, - unsigned int lookup_flags, struct nameidata *nd, - int open_flags, int create_mode) -{ - return __path_lookup_intent_open(dfd, name, lookup_flags|LOOKUP_CREATE, - nd, open_flags, create_mode); -} - static struct dentry *__lookup_hash(struct qstr *name, struct dentry *base, struct nameidata *nd) { @@ -1470,20 +1441,18 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) mutex_lock(&p1->d_inode->i_sb->s_vfs_rename_mutex); - for (p = p1; p->d_parent != p; p = p->d_parent) { - if (p->d_parent == p2) { - mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_PARENT); - mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_CHILD); - return p; - } + p = d_ancestor(p2, p1); + if (p) { + mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_CHILD); + return p; } - for (p = p2; p->d_parent != p; p = p->d_parent) { - if (p->d_parent == p1) { - mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT); - mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD); - return p; - } + p = d_ancestor(p1, p2); + if (p) { + mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD); + return p; } mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT); @@ -1702,8 +1671,7 @@ struct file *do_filp_open(int dfd, const char *pathname, /* * Create - we need to know the parent. */ - error = path_lookup_create(dfd, pathname, LOOKUP_PARENT, - &nd, flag, mode); + error = do_path_lookup(dfd, pathname, LOOKUP_PARENT, &nd); if (error) return ERR_PTR(error); @@ -1714,10 +1682,20 @@ struct file *do_filp_open(int dfd, const char *pathname, */ error = -EISDIR; if (nd.last_type != LAST_NORM || nd.last.name[nd.last.len]) - goto exit; + goto exit_parent; + error = -ENFILE; + filp = get_empty_filp(); + if (filp == NULL) + goto exit_parent; + nd.intent.open.file = filp; + nd.intent.open.flags = flag; + nd.intent.open.create_mode = mode; dir = nd.path.dentry; nd.flags &= ~LOOKUP_PARENT; + nd.flags |= LOOKUP_CREATE | LOOKUP_OPEN; + if (flag & O_EXCL) + nd.flags |= LOOKUP_EXCL; mutex_lock(&dir->d_inode->i_mutex); path.dentry = lookup_hash(&nd); path.mnt = nd.path.mnt; @@ -1822,6 +1800,7 @@ exit_dput: exit: if (!IS_ERR(nd.intent.open.file)) release_open_intent(&nd); +exit_parent: path_put(&nd.path); return ERR_PTR(error); @@ -1914,7 +1893,7 @@ struct dentry *lookup_create(struct nameidata *nd, int is_dir) if (nd->last_type != LAST_NORM) goto fail; nd->flags &= ~LOOKUP_PARENT; - nd->flags |= LOOKUP_CREATE; + nd->flags |= LOOKUP_CREATE | LOOKUP_EXCL; nd->intent.open.flags = O_EXCL; /* @@ -2178,16 +2157,19 @@ static long do_rmdir(int dfd, const char __user *pathname) return error; switch(nd.last_type) { - case LAST_DOTDOT: - error = -ENOTEMPTY; - goto exit1; - case LAST_DOT: - error = -EINVAL; - goto exit1; - case LAST_ROOT: - error = -EBUSY; - goto exit1; + case LAST_DOTDOT: + error = -ENOTEMPTY; + goto exit1; + case LAST_DOT: + error = -EINVAL; + goto exit1; + case LAST_ROOT: + error = -EBUSY; + goto exit1; } + + nd.flags &= ~LOOKUP_PARENT; + mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT); dentry = lookup_hash(&nd); error = PTR_ERR(dentry); @@ -2265,6 +2247,9 @@ static long do_unlinkat(int dfd, const char __user *pathname) error = -EISDIR; if (nd.last_type != LAST_NORM) goto exit1; + + nd.flags &= ~LOOKUP_PARENT; + mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT); dentry = lookup_hash(&nd); error = PTR_ERR(dentry); @@ -2654,6 +2639,10 @@ asmlinkage long sys_renameat(int olddfd, const char __user *oldname, if (newnd.last_type != LAST_NORM) goto exit2; + oldnd.flags &= ~LOOKUP_PARENT; + newnd.flags &= ~LOOKUP_PARENT; + newnd.flags |= LOOKUP_RENAME_TARGET; + trap = lock_rename(new_dir, old_dir); old_dentry = lookup_hash(&oldnd); @@ -2855,6 +2844,7 @@ EXPORT_SYMBOL(__page_symlink); EXPORT_SYMBOL(page_symlink); EXPORT_SYMBOL(page_symlink_inode_operations); EXPORT_SYMBOL(path_lookup); +EXPORT_SYMBOL(kern_path); EXPORT_SYMBOL(vfs_path_lookup); EXPORT_SYMBOL(inode_permission); EXPORT_SYMBOL(vfs_permission); diff --git a/fs/namespace.c b/fs/namespace.c index 6e283c93b50..cce46702d33 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1167,19 +1167,19 @@ asmlinkage long sys_oldumount(char __user * name) #endif -static int mount_is_safe(struct nameidata *nd) +static int mount_is_safe(struct path *path) { if (capable(CAP_SYS_ADMIN)) return 0; return -EPERM; #ifdef notyet - if (S_ISLNK(nd->path.dentry->d_inode->i_mode)) + if (S_ISLNK(path->dentry->d_inode->i_mode)) return -EPERM; - if (nd->path.dentry->d_inode->i_mode & S_ISVTX) { - if (current->uid != nd->path.dentry->d_inode->i_uid) + if (path->dentry->d_inode->i_mode & S_ISVTX) { + if (current->uid != path->dentry->d_inode->i_uid) return -EPERM; } - if (vfs_permission(nd, MAY_WRITE)) + if (inode_permission(path->dentry->d_inode, MAY_WRITE)) return -EPERM; return 0; #endif @@ -1425,11 +1425,10 @@ out_unlock: /* * recursively change the type of the mountpoint. - * noinline this do_mount helper to save do_mount stack space. */ -static noinline int do_change_type(struct nameidata *nd, int flag) +static int do_change_type(struct path *path, int flag) { - struct vfsmount *m, *mnt = nd->path.mnt; + struct vfsmount *m, *mnt = path->mnt; int recurse = flag & MS_REC; int type = flag & ~MS_REC; int err = 0; @@ -1437,7 +1436,7 @@ static noinline int do_change_type(struct nameidata *nd, int flag) if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (nd->path.dentry != nd->path.mnt->mnt_root) + if (path->dentry != path->mnt->mnt_root) return -EINVAL; down_write(&namespace_sem); @@ -1459,40 +1458,39 @@ static noinline int do_change_type(struct nameidata *nd, int flag) /* * do loopback mount. - * noinline this do_mount helper to save do_mount stack space. */ -static noinline int do_loopback(struct nameidata *nd, char *old_name, +static int do_loopback(struct path *path, char *old_name, int recurse) { - struct nameidata old_nd; + struct path old_path; struct vfsmount *mnt = NULL; - int err = mount_is_safe(nd); + int err = mount_is_safe(path); if (err) return err; if (!old_name || !*old_name) return -EINVAL; - err = path_lookup(old_name, LOOKUP_FOLLOW, &old_nd); + err = kern_path(old_name, LOOKUP_FOLLOW, &old_path); if (err) return err; down_write(&namespace_sem); err = -EINVAL; - if (IS_MNT_UNBINDABLE(old_nd.path.mnt)) + if (IS_MNT_UNBINDABLE(old_path.mnt)) goto out; - if (!check_mnt(nd->path.mnt) || !check_mnt(old_nd.path.mnt)) + if (!check_mnt(path->mnt) || !check_mnt(old_path.mnt)) goto out; err = -ENOMEM; if (recurse) - mnt = copy_tree(old_nd.path.mnt, old_nd.path.dentry, 0); + mnt = copy_tree(old_path.mnt, old_path.dentry, 0); else - mnt = clone_mnt(old_nd.path.mnt, old_nd.path.dentry, 0); + mnt = clone_mnt(old_path.mnt, old_path.dentry, 0); if (!mnt) goto out; - err = graft_tree(mnt, &nd->path); + err = graft_tree(mnt, path); if (err) { LIST_HEAD(umount_list); spin_lock(&vfsmount_lock); @@ -1503,7 +1501,7 @@ static noinline int do_loopback(struct nameidata *nd, char *old_name, out: up_write(&namespace_sem); - path_put(&old_nd.path); + path_put(&old_path); return err; } @@ -1528,33 +1526,37 @@ static int change_mount_flags(struct vfsmount *mnt, int ms_flags) * change filesystem flags. dir should be a physical root of filesystem. * If you've mounted a non-root directory somewhere and want to do remount * on it - tough luck. - * noinline this do_mount helper to save do_mount stack space. */ -static noinline int do_remount(struct nameidata *nd, int flags, int mnt_flags, +static int do_remount(struct path *path, int flags, int mnt_flags, void *data) { int err; - struct super_block *sb = nd->path.mnt->mnt_sb; + struct super_block *sb = path->mnt->mnt_sb; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!check_mnt(nd->path.mnt)) + if (!check_mnt(path->mnt)) return -EINVAL; - if (nd->path.dentry != nd->path.mnt->mnt_root) + if (path->dentry != path->mnt->mnt_root) return -EINVAL; down_write(&sb->s_umount); if (flags & MS_BIND) - err = change_mount_flags(nd->path.mnt, flags); + err = change_mount_flags(path->mnt, flags); else err = do_remount_sb(sb, flags, data, 0); if (!err) - nd->path.mnt->mnt_flags = mnt_flags; + path->mnt->mnt_flags = mnt_flags; up_write(&sb->s_umount); - if (!err) - security_sb_post_remount(nd->path.mnt, flags, data); + if (!err) { + security_sb_post_remount(path->mnt, flags, data); + + spin_lock(&vfsmount_lock); + touch_mnt_namespace(path->mnt->mnt_ns); + spin_unlock(&vfsmount_lock); + } return err; } @@ -1568,90 +1570,85 @@ static inline int tree_contains_unbindable(struct vfsmount *mnt) return 0; } -/* - * noinline this do_mount helper to save do_mount stack space. - */ -static noinline int do_move_mount(struct nameidata *nd, char *old_name) +static int do_move_mount(struct path *path, char *old_name) { - struct nameidata old_nd; - struct path parent_path; + struct path old_path, parent_path; struct vfsmount *p; int err = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!old_name || !*old_name) return -EINVAL; - err = path_lookup(old_name, LOOKUP_FOLLOW, &old_nd); + err = kern_path(old_name, LOOKUP_FOLLOW, &old_path); if (err) return err; down_write(&namespace_sem); - while (d_mountpoint(nd->path.dentry) && - follow_down(&nd->path.mnt, &nd->path.dentry)) + while (d_mountpoint(path->dentry) && + follow_down(&path->mnt, &path->dentry)) ; err = -EINVAL; - if (!check_mnt(nd->path.mnt) || !check_mnt(old_nd.path.mnt)) + if (!check_mnt(path->mnt) || !check_mnt(old_path.mnt)) goto out; err = -ENOENT; - mutex_lock(&nd->path.dentry->d_inode->i_mutex); - if (IS_DEADDIR(nd->path.dentry->d_inode)) + mutex_lock(&path->dentry->d_inode->i_mutex); + if (IS_DEADDIR(path->dentry->d_inode)) goto out1; - if (!IS_ROOT(nd->path.dentry) && d_unhashed(nd->path.dentry)) + if (!IS_ROOT(path->dentry) && d_unhashed(path->dentry)) goto out1; err = -EINVAL; - if (old_nd.path.dentry != old_nd.path.mnt->mnt_root) + if (old_path.dentry != old_path.mnt->mnt_root) goto out1; - if (old_nd.path.mnt == old_nd.path.mnt->mnt_parent) + if (old_path.mnt == old_path.mnt->mnt_parent) goto out1; - if (S_ISDIR(nd->path.dentry->d_inode->i_mode) != - S_ISDIR(old_nd.path.dentry->d_inode->i_mode)) + if (S_ISDIR(path->dentry->d_inode->i_mode) != + S_ISDIR(old_path.dentry->d_inode->i_mode)) goto out1; /* * Don't move a mount residing in a shared parent. */ - if (old_nd.path.mnt->mnt_parent && - IS_MNT_SHARED(old_nd.path.mnt->mnt_parent)) + if (old_path.mnt->mnt_parent && + IS_MNT_SHARED(old_path.mnt->mnt_parent)) goto out1; /* * Don't move a mount tree containing unbindable mounts to a destination * mount which is shared. */ - if (IS_MNT_SHARED(nd->path.mnt) && - tree_contains_unbindable(old_nd.path.mnt)) + if (IS_MNT_SHARED(path->mnt) && + tree_contains_unbindable(old_path.mnt)) goto out1; err = -ELOOP; - for (p = nd->path.mnt; p->mnt_parent != p; p = p->mnt_parent) - if (p == old_nd.path.mnt) + for (p = path->mnt; p->mnt_parent != p; p = p->mnt_parent) + if (p == old_path.mnt) goto out1; - err = attach_recursive_mnt(old_nd.path.mnt, &nd->path, &parent_path); + err = attach_recursive_mnt(old_path.mnt, path, &parent_path); if (err) goto out1; /* if the mount is moved, it should no longer be expire * automatically */ - list_del_init(&old_nd.path.mnt->mnt_expire); + list_del_init(&old_path.mnt->mnt_expire); out1: - mutex_unlock(&nd->path.dentry->d_inode->i_mutex); + mutex_unlock(&path->dentry->d_inode->i_mutex); out: up_write(&namespace_sem); if (!err) path_put(&parent_path); - path_put(&old_nd.path); + path_put(&old_path); return err; } /* * create a new mount for userspace and request it to be added into the * namespace's tree - * noinline this do_mount helper to save do_mount stack space. */ -static noinline int do_new_mount(struct nameidata *nd, char *type, int flags, +static int do_new_mount(struct path *path, char *type, int flags, int mnt_flags, char *name, void *data) { struct vfsmount *mnt; @@ -1667,7 +1664,7 @@ static noinline int do_new_mount(struct nameidata *nd, char *type, int flags, if (IS_ERR(mnt)) return PTR_ERR(mnt); - return do_add_mount(mnt, &nd->path, mnt_flags, NULL); + return do_add_mount(mnt, path, mnt_flags, NULL); } /* @@ -1902,7 +1899,7 @@ int copy_mount_options(const void __user * data, unsigned long *where) long do_mount(char *dev_name, char *dir_name, char *type_page, unsigned long flags, void *data_page) { - struct nameidata nd; + struct path path; int retval = 0; int mnt_flags = 0; @@ -1940,29 +1937,29 @@ long do_mount(char *dev_name, char *dir_name, char *type_page, MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT); /* ... and get the mountpoint */ - retval = path_lookup(dir_name, LOOKUP_FOLLOW, &nd); + retval = kern_path(dir_name, LOOKUP_FOLLOW, &path); if (retval) return retval; - retval = security_sb_mount(dev_name, &nd.path, + retval = security_sb_mount(dev_name, &path, type_page, flags, data_page); if (retval) goto dput_out; if (flags & MS_REMOUNT) - retval = do_remount(&nd, flags & ~MS_REMOUNT, mnt_flags, + retval = do_remount(&path, flags & ~MS_REMOUNT, mnt_flags, data_page); else if (flags & MS_BIND) - retval = do_loopback(&nd, dev_name, flags & MS_REC); + retval = do_loopback(&path, dev_name, flags & MS_REC); else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) - retval = do_change_type(&nd, flags); + retval = do_change_type(&path, flags); else if (flags & MS_MOVE) - retval = do_move_mount(&nd, dev_name); + retval = do_move_mount(&path, dev_name); else - retval = do_new_mount(&nd, type_page, flags, mnt_flags, + retval = do_new_mount(&path, type_page, flags, mnt_flags, dev_name, data_page); dput_out: - path_put(&nd.path); + path_put(&path); return retval; } diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index efdba2e802d..3e64b98f3a9 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -707,9 +707,7 @@ static int nfs_is_exclusive_create(struct inode *dir, struct nameidata *nd) { if (NFS_PROTO(dir)->version == 2) return 0; - if (nd == NULL || nfs_lookup_check_intent(nd, LOOKUP_CREATE) == 0) - return 0; - return (nd->intent.open.flags & O_EXCL) != 0; + return nd && nfs_lookup_check_intent(nd, LOOKUP_EXCL); } /* @@ -1009,7 +1007,7 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry /* Let vfs_create() deal with O_EXCL. Instantiate, but don't hash * the dentry. */ - if (nd->intent.open.flags & O_EXCL) { + if (nd->flags & LOOKUP_EXCL) { d_instantiate(dentry, NULL); goto out; } @@ -1959,6 +1957,9 @@ force_lookup: } else res = PTR_ERR(cred); out: + if (!res && (mask & MAY_EXEC) && !execute_ok(inode)) + res = -EACCES; + dfprintk(VFS, "NFS: permission(%s/%ld), mask=0x%x, res=%d\n", inode->i_sb->s_id, inode->i_ino, mask, res); return res; diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index fae97196daa..b7c9b2df1f2 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -107,11 +107,10 @@ struct dentry *nfs_get_root(struct super_block *sb, struct nfs_fh *mntfh) * if the dentry tree reaches them; however if the dentry already * exists, we'll pick it up at this point and use it as the root */ - mntroot = d_alloc_anon(inode); - if (!mntroot) { - iput(inode); + mntroot = d_obtain_alias(inode); + if (IS_ERR(mntroot)) { dprintk("nfs_get_root: get root dentry failed\n"); - return ERR_PTR(-ENOMEM); + return mntroot; } security_d_instantiate(mntroot, inode); @@ -277,11 +276,10 @@ struct dentry *nfs4_get_root(struct super_block *sb, struct nfs_fh *mntfh) * if the dentry tree reaches them; however if the dentry already * exists, we'll pick it up at this point and use it as the root */ - mntroot = d_alloc_anon(inode); - if (!mntroot) { - iput(inode); + mntroot = d_obtain_alias(inode); + if (IS_ERR(mntroot)) { dprintk("nfs_get_root: get root dentry failed\n"); - return ERR_PTR(-ENOMEM); + return mntroot; } security_d_instantiate(mntroot, inode); diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 9dc036f1835..5839b229cd0 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -99,7 +99,7 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen) int fsidtype; char *ep; struct svc_expkey key; - struct svc_expkey *ek; + struct svc_expkey *ek = NULL; if (mesg[mlen-1] != '\n') return -EINVAL; @@ -107,7 +107,8 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen) buf = kmalloc(PAGE_SIZE, GFP_KERNEL); err = -ENOMEM; - if (!buf) goto out; + if (!buf) + goto out; err = -EINVAL; if ((len=qword_get(&mesg, buf, PAGE_SIZE)) <= 0) @@ -151,34 +152,32 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen) /* now we want a pathname, or empty meaning NEGATIVE */ err = -EINVAL; - if ((len=qword_get(&mesg, buf, PAGE_SIZE)) < 0) + len = qword_get(&mesg, buf, PAGE_SIZE); + if (len < 0) goto out; dprintk("Path seems to be <%s>\n", buf); err = 0; if (len == 0) { set_bit(CACHE_NEGATIVE, &key.h.flags); ek = svc_expkey_update(&key, ek); - if (ek) - cache_put(&ek->h, &svc_expkey_cache); - else err = -ENOMEM; + if (!ek) + err = -ENOMEM; } else { - struct nameidata nd; - err = path_lookup(buf, 0, &nd); + err = kern_path(buf, 0, &key.ek_path); if (err) goto out; dprintk("Found the path %s\n", buf); - key.ek_path = nd.path; ek = svc_expkey_update(&key, ek); - if (ek) - cache_put(&ek->h, &svc_expkey_cache); - else + if (!ek) err = -ENOMEM; - path_put(&nd.path); + path_put(&key.ek_path); } cache_flush(); out: + if (ek) + cache_put(&ek->h, &svc_expkey_cache); if (dom) auth_domain_put(dom); kfree(buf); @@ -500,35 +499,22 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) int len; int err; struct auth_domain *dom = NULL; - struct nameidata nd; - struct svc_export exp, *expp; + struct svc_export exp = {}, *expp; int an_int; - nd.path.dentry = NULL; - exp.ex_pathname = NULL; - - /* fs locations */ - exp.ex_fslocs.locations = NULL; - exp.ex_fslocs.locations_count = 0; - exp.ex_fslocs.migrated = 0; - - exp.ex_uuid = NULL; - - /* secinfo */ - exp.ex_nflavors = 0; - if (mesg[mlen-1] != '\n') return -EINVAL; mesg[mlen-1] = 0; buf = kmalloc(PAGE_SIZE, GFP_KERNEL); - err = -ENOMEM; - if (!buf) goto out; + if (!buf) + return -ENOMEM; /* client */ - len = qword_get(&mesg, buf, PAGE_SIZE); err = -EINVAL; - if (len <= 0) goto out; + len = qword_get(&mesg, buf, PAGE_SIZE); + if (len <= 0) + goto out; err = -ENOENT; dom = auth_domain_find(buf); @@ -537,25 +523,25 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) /* path */ err = -EINVAL; - if ((len=qword_get(&mesg, buf, PAGE_SIZE)) <= 0) - goto out; - err = path_lookup(buf, 0, &nd); - if (err) goto out_no_path; + if ((len = qword_get(&mesg, buf, PAGE_SIZE)) <= 0) + goto out1; + + err = kern_path(buf, 0, &exp.ex_path); + if (err) + goto out1; - exp.h.flags = 0; exp.ex_client = dom; - exp.ex_path.mnt = nd.path.mnt; - exp.ex_path.dentry = nd.path.dentry; - exp.ex_pathname = kstrdup(buf, GFP_KERNEL); + err = -ENOMEM; + exp.ex_pathname = kstrdup(buf, GFP_KERNEL); if (!exp.ex_pathname) - goto out; + goto out2; /* expiry */ err = -EINVAL; exp.h.expiry_time = get_expiry(&mesg); if (exp.h.expiry_time == 0) - goto out; + goto out3; /* flags */ err = get_int(&mesg, &an_int); @@ -563,22 +549,26 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) err = 0; set_bit(CACHE_NEGATIVE, &exp.h.flags); } else { - if (err || an_int < 0) goto out; + if (err || an_int < 0) + goto out3; exp.ex_flags= an_int; /* anon uid */ err = get_int(&mesg, &an_int); - if (err) goto out; + if (err) + goto out3; exp.ex_anon_uid= an_int; /* anon gid */ err = get_int(&mesg, &an_int); - if (err) goto out; + if (err) + goto out3; exp.ex_anon_gid= an_int; /* fsid */ err = get_int(&mesg, &an_int); - if (err) goto out; + if (err) + goto out3; exp.ex_fsid = an_int; while ((len = qword_get(&mesg, buf, PAGE_SIZE)) > 0) { @@ -604,12 +594,13 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) */ break; if (err) - goto out; + goto out4; } - err = check_export(nd.path.dentry->d_inode, exp.ex_flags, + err = check_export(exp.ex_path.dentry->d_inode, exp.ex_flags, exp.ex_uuid); - if (err) goto out; + if (err) + goto out4; } expp = svc_export_lookup(&exp); @@ -622,15 +613,16 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) err = -ENOMEM; else exp_put(expp); - out: +out4: nfsd4_fslocs_free(&exp.ex_fslocs); kfree(exp.ex_uuid); +out3: kfree(exp.ex_pathname); - if (nd.path.dentry) - path_put(&nd.path); - out_no_path: - if (dom) - auth_domain_put(dom); +out2: + path_put(&exp.ex_path); +out1: + auth_domain_put(dom); +out: kfree(buf); return err; } @@ -998,7 +990,7 @@ exp_export(struct nfsctl_export *nxp) struct svc_export *exp = NULL; struct svc_export new; struct svc_expkey *fsid_key = NULL; - struct nameidata nd; + struct path path; int err; /* Consistency check */ @@ -1021,12 +1013,12 @@ exp_export(struct nfsctl_export *nxp) /* Look up the dentry */ - err = path_lookup(nxp->ex_path, 0, &nd); + err = kern_path(nxp->ex_path, 0, &path); if (err) goto out_put_clp; err = -EINVAL; - exp = exp_get_by_name(clp, nd.path.mnt, nd.path.dentry, NULL); + exp = exp_get_by_name(clp, path.mnt, path.dentry, NULL); memset(&new, 0, sizeof(new)); @@ -1034,8 +1026,8 @@ exp_export(struct nfsctl_export *nxp) if ((nxp->ex_flags & NFSEXP_FSID) && (!IS_ERR(fsid_key = exp_get_fsid_key(clp, nxp->ex_dev))) && fsid_key->ek_path.mnt && - (fsid_key->ek_path.mnt != nd.path.mnt || - fsid_key->ek_path.dentry != nd.path.dentry)) + (fsid_key->ek_path.mnt != path.mnt || + fsid_key->ek_path.dentry != path.dentry)) goto finish; if (!IS_ERR(exp)) { @@ -1051,7 +1043,7 @@ exp_export(struct nfsctl_export *nxp) goto finish; } - err = check_export(nd.path.dentry->d_inode, nxp->ex_flags, NULL); + err = check_export(path.dentry->d_inode, nxp->ex_flags, NULL); if (err) goto finish; err = -ENOMEM; @@ -1064,7 +1056,7 @@ exp_export(struct nfsctl_export *nxp) if (!new.ex_pathname) goto finish; new.ex_client = clp; - new.ex_path = nd.path; + new.ex_path = path; new.ex_flags = nxp->ex_flags; new.ex_anon_uid = nxp->ex_anon_uid; new.ex_anon_gid = nxp->ex_anon_gid; @@ -1090,7 +1082,7 @@ finish: exp_put(exp); if (fsid_key && !IS_ERR(fsid_key)) cache_put(&fsid_key->h, &svc_expkey_cache); - path_put(&nd.path); + path_put(&path); out_put_clp: auth_domain_put(clp); out_unlock: @@ -1121,7 +1113,7 @@ exp_unexport(struct nfsctl_export *nxp) { struct auth_domain *dom; svc_export *exp; - struct nameidata nd; + struct path path; int err; /* Consistency check */ @@ -1138,13 +1130,13 @@ exp_unexport(struct nfsctl_export *nxp) goto out_unlock; } - err = path_lookup(nxp->ex_path, 0, &nd); + err = kern_path(nxp->ex_path, 0, &path); if (err) goto out_domain; err = -EINVAL; - exp = exp_get_by_name(dom, nd.path.mnt, nd.path.dentry, NULL); - path_put(&nd.path); + exp = exp_get_by_name(dom, path.mnt, path.dentry, NULL); + path_put(&path); if (IS_ERR(exp)) goto out_domain; @@ -1166,26 +1158,26 @@ out_unlock: * since its harder to fool a kernel module than a user space program. */ int -exp_rootfh(svc_client *clp, char *path, struct knfsd_fh *f, int maxsize) +exp_rootfh(svc_client *clp, char *name, struct knfsd_fh *f, int maxsize) { struct svc_export *exp; - struct nameidata nd; + struct path path; struct inode *inode; struct svc_fh fh; int err; err = -EPERM; /* NB: we probably ought to check that it's NUL-terminated */ - if (path_lookup(path, 0, &nd)) { - printk("nfsd: exp_rootfh path not found %s", path); + if (kern_path(name, 0, &path)) { + printk("nfsd: exp_rootfh path not found %s", name); return err; } - inode = nd.path.dentry->d_inode; + inode = path.dentry->d_inode; dprintk("nfsd: exp_rootfh(%s [%p] %s:%s/%ld)\n", - path, nd.path.dentry, clp->name, + name, path.dentry, clp->name, inode->i_sb->s_id, inode->i_ino); - exp = exp_parent(clp, nd.path.mnt, nd.path.dentry, NULL); + exp = exp_parent(clp, path.mnt, path.dentry, NULL); if (IS_ERR(exp)) { err = PTR_ERR(exp); goto out; @@ -1195,7 +1187,7 @@ exp_rootfh(svc_client *clp, char *path, struct knfsd_fh *f, int maxsize) * fh must be initialized before calling fh_compose */ fh_init(&fh, maxsize); - if (fh_compose(&fh, exp, nd.path.dentry, NULL)) + if (fh_compose(&fh, exp, path.dentry, NULL)) err = -EINVAL; else err = 0; @@ -1203,7 +1195,7 @@ exp_rootfh(svc_client *clp, char *path, struct knfsd_fh *f, int maxsize) fh_put(&fh); exp_put(exp); out: - path_put(&nd.path); + path_put(&path); return err; } diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 145b3c877a2..bb93946ace2 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -51,7 +51,7 @@ #define NFSDDBG_FACILITY NFSDDBG_PROC /* Globals */ -static struct nameidata rec_dir; +static struct path rec_dir; static int rec_dir_init = 0; static void @@ -121,9 +121,9 @@ out_no_tfm: static void nfsd4_sync_rec_dir(void) { - mutex_lock(&rec_dir.path.dentry->d_inode->i_mutex); - nfsd_sync_dir(rec_dir.path.dentry); - mutex_unlock(&rec_dir.path.dentry->d_inode->i_mutex); + mutex_lock(&rec_dir.dentry->d_inode->i_mutex); + nfsd_sync_dir(rec_dir.dentry); + mutex_unlock(&rec_dir.dentry->d_inode->i_mutex); } int @@ -143,9 +143,9 @@ nfsd4_create_clid_dir(struct nfs4_client *clp) nfs4_save_user(&uid, &gid); /* lock the parent */ - mutex_lock(&rec_dir.path.dentry->d_inode->i_mutex); + mutex_lock(&rec_dir.dentry->d_inode->i_mutex); - dentry = lookup_one_len(dname, rec_dir.path.dentry, HEXDIR_LEN-1); + dentry = lookup_one_len(dname, rec_dir.dentry, HEXDIR_LEN-1); if (IS_ERR(dentry)) { status = PTR_ERR(dentry); goto out_unlock; @@ -155,15 +155,15 @@ nfsd4_create_clid_dir(struct nfs4_client *clp) dprintk("NFSD: nfsd4_create_clid_dir: DIRECTORY EXISTS\n"); goto out_put; } - status = mnt_want_write(rec_dir.path.mnt); + status = mnt_want_write(rec_dir.mnt); if (status) goto out_put; - status = vfs_mkdir(rec_dir.path.dentry->d_inode, dentry, S_IRWXU); - mnt_drop_write(rec_dir.path.mnt); + status = vfs_mkdir(rec_dir.dentry->d_inode, dentry, S_IRWXU); + mnt_drop_write(rec_dir.mnt); out_put: dput(dentry); out_unlock: - mutex_unlock(&rec_dir.path.dentry->d_inode->i_mutex); + mutex_unlock(&rec_dir.dentry->d_inode->i_mutex); if (status == 0) { clp->cl_firststate = 1; nfsd4_sync_rec_dir(); @@ -226,7 +226,7 @@ nfsd4_list_rec_dir(struct dentry *dir, recdir_func *f) nfs4_save_user(&uid, &gid); - filp = dentry_open(dget(dir), mntget(rec_dir.path.mnt), O_RDONLY); + filp = dentry_open(dget(dir), mntget(rec_dir.mnt), O_RDONLY); status = PTR_ERR(filp); if (IS_ERR(filp)) goto out; @@ -291,9 +291,9 @@ nfsd4_unlink_clid_dir(char *name, int namlen) dprintk("NFSD: nfsd4_unlink_clid_dir. name %.*s\n", namlen, name); - mutex_lock(&rec_dir.path.dentry->d_inode->i_mutex); - dentry = lookup_one_len(name, rec_dir.path.dentry, namlen); - mutex_unlock(&rec_dir.path.dentry->d_inode->i_mutex); + mutex_lock(&rec_dir.dentry->d_inode->i_mutex); + dentry = lookup_one_len(name, rec_dir.dentry, namlen); + mutex_unlock(&rec_dir.dentry->d_inode->i_mutex); if (IS_ERR(dentry)) { status = PTR_ERR(dentry); return status; @@ -302,7 +302,7 @@ nfsd4_unlink_clid_dir(char *name, int namlen) if (!dentry->d_inode) goto out; - status = nfsd4_clear_clid_dir(rec_dir.path.dentry, dentry); + status = nfsd4_clear_clid_dir(rec_dir.dentry, dentry); out: dput(dentry); return status; @@ -318,7 +318,7 @@ nfsd4_remove_clid_dir(struct nfs4_client *clp) if (!rec_dir_init || !clp->cl_firststate) return; - status = mnt_want_write(rec_dir.path.mnt); + status = mnt_want_write(rec_dir.mnt); if (status) goto out; clp->cl_firststate = 0; @@ -327,7 +327,7 @@ nfsd4_remove_clid_dir(struct nfs4_client *clp) nfs4_reset_user(uid, gid); if (status == 0) nfsd4_sync_rec_dir(); - mnt_drop_write(rec_dir.path.mnt); + mnt_drop_write(rec_dir.mnt); out: if (status) printk("NFSD: Failed to remove expired client state directory" @@ -357,17 +357,17 @@ nfsd4_recdir_purge_old(void) { if (!rec_dir_init) return; - status = mnt_want_write(rec_dir.path.mnt); + status = mnt_want_write(rec_dir.mnt); if (status) goto out; - status = nfsd4_list_rec_dir(rec_dir.path.dentry, purge_old); + status = nfsd4_list_rec_dir(rec_dir.dentry, purge_old); if (status == 0) nfsd4_sync_rec_dir(); - mnt_drop_write(rec_dir.path.mnt); + mnt_drop_write(rec_dir.mnt); out: if (status) printk("nfsd4: failed to purge old clients from recovery" - " directory %s\n", rec_dir.path.dentry->d_name.name); + " directory %s\n", rec_dir.dentry->d_name.name); } static int @@ -387,10 +387,10 @@ int nfsd4_recdir_load(void) { int status; - status = nfsd4_list_rec_dir(rec_dir.path.dentry, load_recdir); + status = nfsd4_list_rec_dir(rec_dir.dentry, load_recdir); if (status) printk("nfsd4: failed loading clients from recovery" - " directory %s\n", rec_dir.path.dentry->d_name.name); + " directory %s\n", rec_dir.dentry->d_name.name); return status; } @@ -412,7 +412,7 @@ nfsd4_init_recdir(char *rec_dirname) nfs4_save_user(&uid, &gid); - status = path_lookup(rec_dirname, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, + status = kern_path(rec_dirname, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &rec_dir); if (status) printk("NFSD: unable to find recovery directory %s\n", @@ -429,5 +429,5 @@ nfsd4_shutdown_recdir(void) if (!rec_dir_init) return; rec_dir_init = 0; - path_put(&rec_dir.path); + path_put(&rec_dir); } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 0cc7ff5d5ab..b0bebc552a1 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -3284,17 +3284,17 @@ int nfs4_reset_recoverydir(char *recdir) { int status; - struct nameidata nd; + struct path path; - status = path_lookup(recdir, LOOKUP_FOLLOW, &nd); + status = kern_path(recdir, LOOKUP_FOLLOW, &path); if (status) return status; status = -ENOTDIR; - if (S_ISDIR(nd.path.dentry->d_inode->i_mode)) { + if (S_ISDIR(path.dentry->d_inode->i_mode)) { nfs4_set_recdir(recdir); status = 0; } - path_put(&nd.path); + path_put(&path); return status; } diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 97543df5824..e3f9783fdcf 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -341,7 +341,7 @@ static ssize_t failover_unlock_ip(struct file *file, char *buf, size_t size) static ssize_t failover_unlock_fs(struct file *file, char *buf, size_t size) { - struct nameidata nd; + struct path path; char *fo_path; int error; @@ -356,13 +356,13 @@ static ssize_t failover_unlock_fs(struct file *file, char *buf, size_t size) if (qword_get(&buf, fo_path, size) < 0) return -EINVAL; - error = path_lookup(fo_path, 0, &nd); + error = kern_path(fo_path, 0, &path); if (error) return error; - error = nlmsvc_unlock_all_by_sb(nd.path.mnt->mnt_sb); + error = nlmsvc_unlock_all_by_sb(path.mnt->mnt_sb); - path_put(&nd.path); + path_put(&path); return error; } diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 59eeb46f82c..07e4f5d7baa 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -249,6 +249,10 @@ static int nfsd_init_socks(int port) if (error < 0) return error; + error = lockd_up(); + if (error < 0) + return error; + error = svc_create_xprt(nfsd_serv, "tcp", port, SVC_SOCK_DEFAULTS); if (error < 0) diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index aa1d0d6489a..0bc56f6d927 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -410,6 +410,7 @@ out_nfserr: static ssize_t nfsd_getxattr(struct dentry *dentry, char *key, void **buf) { ssize_t buflen; + ssize_t ret; buflen = vfs_getxattr(dentry, key, NULL, 0); if (buflen <= 0) @@ -419,7 +420,10 @@ static ssize_t nfsd_getxattr(struct dentry *dentry, char *key, void **buf) if (!*buf) return -ENOMEM; - return vfs_getxattr(dentry, key, *buf, buflen); + ret = vfs_getxattr(dentry, key, *buf, buflen); + if (ret < 0) + kfree(*buf); + return ret; } #endif @@ -1814,6 +1818,115 @@ out: } /* + * We do this buffering because we must not call back into the file + * system's ->lookup() method from the filldir callback. That may well + * deadlock a number of file systems. + * + * This is based heavily on the implementation of same in XFS. + */ +struct buffered_dirent { + u64 ino; + loff_t offset; + int namlen; + unsigned int d_type; + char name[]; +}; + +struct readdir_data { + char *dirent; + size_t used; + int full; +}; + +static int nfsd_buffered_filldir(void *__buf, const char *name, int namlen, + loff_t offset, u64 ino, unsigned int d_type) +{ + struct readdir_data *buf = __buf; + struct buffered_dirent *de = (void *)(buf->dirent + buf->used); + unsigned int reclen; + + reclen = ALIGN(sizeof(struct buffered_dirent) + namlen, sizeof(u64)); + if (buf->used + reclen > PAGE_SIZE) { + buf->full = 1; + return -EINVAL; + } + + de->namlen = namlen; + de->offset = offset; + de->ino = ino; + de->d_type = d_type; + memcpy(de->name, name, namlen); + buf->used += reclen; + + return 0; +} + +static int 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; + + buf.dirent = (void *)__get_free_page(GFP_KERNEL); + if (!buf.dirent) + return -ENOMEM; + + offset = *offsetp; + cdp->err = nfserr_eof; /* will be cleared on successful read */ + + while (1) { + unsigned int reclen; + + buf.used = 0; + buf.full = 0; + + host_err = vfs_readdir(file, nfsd_buffered_filldir, &buf); + if (buf.full) + host_err = 0; + + if (host_err < 0) + break; + + size = buf.used; + + if (!size) + break; + + de = (struct buffered_dirent *)buf.dirent; + while (size > 0) { + offset = de->offset; + + if (func(cdp, de->name, de->namlen, de->offset, + de->ino, de->d_type)) + goto done; + + if (cdp->err != nfs_ok) + goto done; + + reclen = ALIGN(sizeof(*de) + de->namlen, + sizeof(u64)); + size -= reclen; + de = (struct buffered_dirent *)((char *)de + reclen); + } + offset = vfs_llseek(file, 0, SEEK_CUR); + if (!buf.full) + break; + } + + done: + free_page((unsigned long)(buf.dirent)); + + if (host_err) + return nfserrno(host_err); + + *offsetp = offset; + return cdp->err; +} + +/* * Read entries from a directory. * The NFSv3/4 verifier we ignore for now. */ @@ -1822,7 +1935,6 @@ nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp, struct readdir_cd *cdp, filldir_t func) { __be32 err; - int host_err; struct file *file; loff_t offset = *offsetp; @@ -1836,21 +1948,7 @@ nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp, goto out_close; } - /* - * Read the directory entries. This silly loop is necessary because - * readdir() is not guaranteed to fill up the entire buffer, but - * may choose to do less. - */ - - do { - cdp->err = nfserr_eof; /* will be cleared on successful read */ - host_err = vfs_readdir(file, func, cdp); - } while (host_err >=0 && cdp->err == nfs_ok); - if (host_err) - err = nfserrno(host_err); - else - err = cdp->err; - *offsetp = vfs_llseek(file, 0, 1); + err = nfsd_buffered_readdir(file, func, cdp, offsetp); if (err == nfserr_eof || err == nfserr_toosmall) err = nfs_ok; /* can still be found in ->err */ diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c index 9e8a95be7a1..2ca00153b6e 100644 --- a/fs/ntfs/namei.c +++ b/fs/ntfs/namei.c @@ -304,8 +304,6 @@ static struct dentry *ntfs_get_parent(struct dentry *child_dent) ntfs_attr_search_ctx *ctx; ATTR_RECORD *attr; FILE_NAME_ATTR *fn; - struct inode *parent_vi; - struct dentry *parent_dent; unsigned long parent_ino; int err; @@ -345,24 +343,8 @@ try_next: /* Release the search context and the mft record of the child. */ ntfs_attr_put_search_ctx(ctx); unmap_mft_record(ni); - /* Get the inode of the parent directory. */ - parent_vi = ntfs_iget(vi->i_sb, parent_ino); - if (IS_ERR(parent_vi) || unlikely(is_bad_inode(parent_vi))) { - if (!IS_ERR(parent_vi)) - iput(parent_vi); - ntfs_error(vi->i_sb, "Failed to get parent directory inode " - "0x%lx of child inode 0x%lx.", parent_ino, - vi->i_ino); - return ERR_PTR(-EACCES); - } - /* Finally get a dentry for the parent directory and return it. */ - parent_dent = d_alloc_anon(parent_vi); - if (unlikely(!parent_dent)) { - iput(parent_vi); - return ERR_PTR(-ENOMEM); - } - ntfs_debug("Done for inode 0x%lx.", vi->i_ino); - return parent_dent; + + return d_obtain_alias(ntfs_iget(vi->i_sb, parent_ino)); } static struct inode *ntfs_nfs_get_inode(struct super_block *sb, diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 7dce1612553..6ebaa58e2c0 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -976,7 +976,7 @@ static void o2hb_region_release(struct config_item *item) } if (reg->hr_bdev) - blkdev_put(reg->hr_bdev); + blkdev_put(reg->hr_bdev, FMODE_READ|FMODE_WRITE); if (reg->hr_slots) kfree(reg->hr_slots); @@ -1268,7 +1268,7 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg, goto out; reg->hr_bdev = I_BDEV(filp->f_mapping->host); - ret = blkdev_get(reg->hr_bdev, FMODE_WRITE | FMODE_READ, 0); + ret = blkdev_get(reg->hr_bdev, FMODE_WRITE | FMODE_READ); if (ret) { reg->hr_bdev = NULL; goto out; @@ -1358,7 +1358,7 @@ out: iput(inode); if (ret < 0) { if (reg->hr_bdev) { - blkdev_put(reg->hr_bdev); + blkdev_put(reg->hr_bdev, FMODE_READ|FMODE_WRITE); reg->hr_bdev = NULL; } } diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c index 67527cebf21..2f27b332d8b 100644 --- a/fs/ocfs2/export.c +++ b/fs/ocfs2/export.c @@ -68,14 +68,9 @@ static struct dentry *ocfs2_get_dentry(struct super_block *sb, return ERR_PTR(-ESTALE); } - result = d_alloc_anon(inode); - - if (!result) { - iput(inode); - mlog_errno(-ENOMEM); - return ERR_PTR(-ENOMEM); - } - result->d_op = &ocfs2_dentry_ops; + result = d_obtain_alias(inode); + if (!IS_ERR(result)) + result->d_op = &ocfs2_dentry_ops; mlog_exit_ptr(result); return result; @@ -86,7 +81,6 @@ static struct dentry *ocfs2_get_parent(struct dentry *child) int status; u64 blkno; struct dentry *parent; - struct inode *inode; struct inode *dir = child->d_inode; mlog_entry("(0x%p, '%.*s')\n", child, @@ -109,21 +103,9 @@ static struct dentry *ocfs2_get_parent(struct dentry *child) goto bail_unlock; } - inode = ocfs2_iget(OCFS2_SB(dir->i_sb), blkno, 0, 0); - if (IS_ERR(inode)) { - mlog(ML_ERROR, "Unable to create inode %llu\n", - (unsigned long long)blkno); - parent = ERR_PTR(-EACCES); - goto bail_unlock; - } - - parent = d_alloc_anon(inode); - if (!parent) { - iput(inode); - parent = ERR_PTR(-ENOMEM); - } - - parent->d_op = &ocfs2_dentry_ops; + parent = d_obtain_alias(ocfs2_iget(OCFS2_SB(dir->i_sb), blkno, 0, 0)); + if (!IS_ERR(parent)) + parent->d_op = &ocfs2_dentry_ops; bail_unlock: ocfs2_inode_unlock(dir, 0); diff --git a/fs/omfs/dir.c b/fs/omfs/dir.c index c0757e99887..c7275cfbdcf 100644 --- a/fs/omfs/dir.c +++ b/fs/omfs/dir.c @@ -501,4 +501,5 @@ struct inode_operations omfs_dir_inops = { struct file_operations omfs_dir_operations = { .read = generic_read_dir, .readdir = omfs_readdir, + .llseek = generic_file_llseek, }; diff --git a/fs/open.c b/fs/open.c index 5596049863b..83cdb9dee0c 100644 --- a/fs/open.c +++ b/fs/open.c @@ -798,7 +798,7 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt, int error; f->f_flags = flags; - f->f_mode = ((flags+1) & O_ACCMODE) | FMODE_LSEEK | + f->f_mode = (__force fmode_t)((flags+1) & O_ACCMODE) | FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; inode = dentry->d_inode; if (f->f_mode & FMODE_WRITE) { diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c index 9f5b054f06b..d41bdc784de 100644 --- a/fs/openpromfs/inode.c +++ b/fs/openpromfs/inode.c @@ -167,6 +167,7 @@ static int openpromfs_readdir(struct file *, void *, filldir_t); static const struct file_operations openprom_operations = { .read = generic_read_dir, .readdir = openpromfs_readdir, + .llseek = generic_file_llseek, }; static struct dentry *openpromfs_lookup(struct inode *, struct dentry *, struct nameidata *); diff --git a/fs/partitions/check.c b/fs/partitions/check.c index cfb0c80690a..633f7a0ebb2 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -485,10 +485,10 @@ void register_disk(struct gendisk *disk) goto exit; bdev->bd_invalidated = 1; - err = blkdev_get(bdev, FMODE_READ, 0); + err = blkdev_get(bdev, FMODE_READ); if (err < 0) goto exit; - blkdev_put(bdev); + blkdev_put(bdev, FMODE_READ); exit: /* announce disk after possible partitions are created */ diff --git a/fs/proc/Makefile b/fs/proc/Makefile index ebaba021354..63d965193b2 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -8,11 +8,20 @@ proc-y := nommu.o task_nommu.o proc-$(CONFIG_MMU) := mmu.o task_mmu.o proc-y += inode.o root.o base.o generic.o array.o \ - proc_tty.o proc_misc.o - + proc_tty.o +proc-y += cmdline.o +proc-y += cpuinfo.o +proc-y += devices.o +proc-y += interrupts.o +proc-y += loadavg.o +proc-y += meminfo.o +proc-y += stat.o +proc-y += uptime.o +proc-y += version.o proc-$(CONFIG_PROC_SYSCTL) += proc_sysctl.o proc-$(CONFIG_NET) += proc_net.o proc-$(CONFIG_PROC_KCORE) += kcore.o proc-$(CONFIG_PROC_VMCORE) += vmcore.o proc-$(CONFIG_PROC_DEVICETREE) += proc_devtree.o proc-$(CONFIG_PRINTK) += kmsg.o +proc-$(CONFIG_PROC_PAGE_MONITOR) += page.o diff --git a/fs/proc/array.c b/fs/proc/array.c index f4bc0e78953..bb9f4b05703 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -388,20 +388,20 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, /* add up live thread stats at the group level */ if (whole) { + struct task_cputime cputime; struct task_struct *t = task; do { min_flt += t->min_flt; maj_flt += t->maj_flt; - utime = cputime_add(utime, task_utime(t)); - stime = cputime_add(stime, task_stime(t)); gtime = cputime_add(gtime, task_gtime(t)); t = next_thread(t); } while (t != task); min_flt += sig->min_flt; maj_flt += sig->maj_flt; - utime = cputime_add(utime, sig->utime); - stime = cputime_add(stime, sig->stime); + thread_group_cputime(task, &cputime); + utime = cputime.utime; + stime = cputime.stime; gtime = cputime_add(gtime, sig->gtime); } diff --git a/fs/proc/base.c b/fs/proc/base.c index b5918ae8ca7..486cf3fe713 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1712,9 +1712,9 @@ static struct dentry *proc_fd_instantiate(struct inode *dir, file = fcheck_files(files, fd); if (!file) goto out_unlock; - if (file->f_mode & 1) + if (file->f_mode & FMODE_READ) inode->i_mode |= S_IRUSR | S_IXUSR; - if (file->f_mode & 2) + if (file->f_mode & FMODE_WRITE) inode->i_mode |= S_IWUSR | S_IXUSR; spin_unlock(&files->file_lock); put_files_struct(files); diff --git a/fs/proc/cmdline.c b/fs/proc/cmdline.c new file mode 100644 index 00000000000..82676e3fcd1 --- /dev/null +++ b/fs/proc/cmdline.c @@ -0,0 +1,29 @@ +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> + +static int cmdline_proc_show(struct seq_file *m, void *v) +{ + seq_printf(m, "%s\n", saved_command_line); + return 0; +} + +static int cmdline_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, cmdline_proc_show, NULL); +} + +static const struct file_operations cmdline_proc_fops = { + .open = cmdline_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init proc_cmdline_init(void) +{ + proc_create("cmdline", 0, NULL, &cmdline_proc_fops); + return 0; +} +module_init(proc_cmdline_init); diff --git a/fs/proc/cpuinfo.c b/fs/proc/cpuinfo.c new file mode 100644 index 00000000000..5a1e539a234 --- /dev/null +++ b/fs/proc/cpuinfo.c @@ -0,0 +1,24 @@ +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> + +extern const struct seq_operations cpuinfo_op; +static int cpuinfo_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &cpuinfo_op); +} + +static const struct file_operations proc_cpuinfo_operations = { + .open = cpuinfo_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init proc_cpuinfo_init(void) +{ + proc_create("cpuinfo", 0, NULL, &proc_cpuinfo_operations); + return 0; +} +module_init(proc_cpuinfo_init); diff --git a/fs/proc/devices.c b/fs/proc/devices.c new file mode 100644 index 00000000000..59ee7da959c --- /dev/null +++ b/fs/proc/devices.c @@ -0,0 +1,70 @@ +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> + +static int devinfo_show(struct seq_file *f, void *v) +{ + int i = *(loff_t *) v; + + if (i < CHRDEV_MAJOR_HASH_SIZE) { + if (i == 0) + seq_printf(f, "Character devices:\n"); + chrdev_show(f, i); + } +#ifdef CONFIG_BLOCK + else { + i -= CHRDEV_MAJOR_HASH_SIZE; + if (i == 0) + seq_printf(f, "\nBlock devices:\n"); + blkdev_show(f, i); + } +#endif + return 0; +} + +static void *devinfo_start(struct seq_file *f, loff_t *pos) +{ + if (*pos < (BLKDEV_MAJOR_HASH_SIZE + CHRDEV_MAJOR_HASH_SIZE)) + return pos; + return NULL; +} + +static void *devinfo_next(struct seq_file *f, void *v, loff_t *pos) +{ + (*pos)++; + if (*pos >= (BLKDEV_MAJOR_HASH_SIZE + CHRDEV_MAJOR_HASH_SIZE)) + return NULL; + return pos; +} + +static void devinfo_stop(struct seq_file *f, void *v) +{ + /* Nothing to do */ +} + +static const struct seq_operations devinfo_ops = { + .start = devinfo_start, + .next = devinfo_next, + .stop = devinfo_stop, + .show = devinfo_show +}; + +static int devinfo_open(struct inode *inode, struct file *filp) +{ + return seq_open(filp, &devinfo_ops); +} + +static const struct file_operations proc_devinfo_operations = { + .open = devinfo_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init proc_devices_init(void) +{ + proc_create("devices", 0, NULL, &proc_devinfo_operations); + return 0; +} +module_init(proc_devices_init); diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 7821589a17d..60a359b3558 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -547,9 +547,8 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp for (tmp = dir->subdir; tmp; tmp = tmp->next) if (strcmp(tmp->name, dp->name) == 0) { - printk(KERN_WARNING "proc_dir_entry '%s/%s' already registered\n", + WARN(1, KERN_WARNING "proc_dir_entry '%s/%s' already registered\n", dir->name, dp->name); - dump_stack(); break; } diff --git a/fs/proc/inode.c b/fs/proc/inode.c index c6b4fa7e3b4..2543fd00c65 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -106,14 +106,13 @@ static void init_once(void *foo) inode_init_once(&ei->vfs_inode); } -int __init proc_init_inodecache(void) +void __init proc_init_inodecache(void) { proc_inode_cachep = kmem_cache_create("proc_inode_cache", sizeof(struct proc_inode), 0, (SLAB_RECLAIM_ACCOUNT| SLAB_MEM_SPREAD|SLAB_PANIC), init_once); - return 0; } static const struct super_operations proc_sops = { diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 3bfb7b8747b..3e8aeb8b61c 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -61,12 +61,11 @@ extern const struct file_operations proc_smaps_operations; extern const struct file_operations proc_clear_refs_operations; extern const struct file_operations proc_pagemap_operations; extern const struct file_operations proc_net_operations; -extern const struct file_operations proc_kmsg_operations; extern const struct inode_operations proc_net_inode_operations; void free_proc_entry(struct proc_dir_entry *de); -int proc_init_inodecache(void); +void proc_init_inodecache(void); static inline struct pid *proc_pid(struct inode *inode) { diff --git a/fs/proc/interrupts.c b/fs/proc/interrupts.c new file mode 100644 index 00000000000..05029c0e2f2 --- /dev/null +++ b/fs/proc/interrupts.c @@ -0,0 +1,53 @@ +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/irqnr.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> + +/* + * /proc/interrupts + */ +static void *int_seq_start(struct seq_file *f, loff_t *pos) +{ + return (*pos <= nr_irqs) ? pos : NULL; +} + +static void *int_seq_next(struct seq_file *f, void *v, loff_t *pos) +{ + (*pos)++; + if (*pos > nr_irqs) + return NULL; + return pos; +} + +static void int_seq_stop(struct seq_file *f, void *v) +{ + /* Nothing to do */ +} + +static const struct seq_operations int_seq_ops = { + .start = int_seq_start, + .next = int_seq_next, + .stop = int_seq_stop, + .show = show_interrupts +}; + +static int interrupts_open(struct inode *inode, struct file *filp) +{ + return seq_open(filp, &int_seq_ops); +} + +static const struct file_operations proc_interrupts_operations = { + .open = interrupts_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init proc_interrupts_init(void) +{ + proc_create("interrupts", 0, NULL, &proc_interrupts_operations); + return 0; +} +module_init(proc_interrupts_init); diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index c2370c76fb7..59b43a06887 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -27,6 +27,8 @@ #define ELF_CORE_EFLAGS 0 #endif +static struct proc_dir_entry *proc_root_kcore; + static int open_kcore(struct inode * inode, struct file * filp) { return capable(CAP_SYS_RAWIO) ? 0 : -EPERM; @@ -34,7 +36,7 @@ static int open_kcore(struct inode * inode, struct file * filp) static ssize_t read_kcore(struct file *, char __user *, size_t, loff_t *); -const struct file_operations proc_kcore_operations = { +static const struct file_operations proc_kcore_operations = { .read = read_kcore, .open = open_kcore, }; @@ -399,3 +401,13 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) return acc; } + +static int __init proc_kcore_init(void) +{ + proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, &proc_kcore_operations); + if (proc_root_kcore) + proc_root_kcore->size = + (size_t)high_memory - PAGE_OFFSET + PAGE_SIZE; + return 0; +} +module_init(proc_kcore_init); diff --git a/fs/proc/kmsg.c b/fs/proc/kmsg.c index 9fd5df3f40c..7ca78346d3f 100644 --- a/fs/proc/kmsg.c +++ b/fs/proc/kmsg.c @@ -10,13 +10,12 @@ #include <linux/time.h> #include <linux/kernel.h> #include <linux/poll.h> +#include <linux/proc_fs.h> #include <linux/fs.h> #include <asm/uaccess.h> #include <asm/io.h> -#include "internal.h" - extern wait_queue_head_t log_wait; extern int do_syslog(int type, char __user *bug, int count); @@ -49,9 +48,16 @@ static unsigned int kmsg_poll(struct file *file, poll_table *wait) } -const struct file_operations proc_kmsg_operations = { +static const struct file_operations proc_kmsg_operations = { .read = kmsg_read, .poll = kmsg_poll, .open = kmsg_open, .release = kmsg_release, }; + +static int __init proc_kmsg_init(void) +{ + proc_create("kmsg", S_IRUSR, NULL, &proc_kmsg_operations); + return 0; +} +module_init(proc_kmsg_init); diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c new file mode 100644 index 00000000000..9bca39cf99e --- /dev/null +++ b/fs/proc/loadavg.c @@ -0,0 +1,51 @@ +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/pid_namespace.h> +#include <linux/proc_fs.h> +#include <linux/sched.h> +#include <linux/seq_file.h> +#include <linux/seqlock.h> +#include <linux/time.h> + +#define LOAD_INT(x) ((x) >> FSHIFT) +#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) + +static int loadavg_proc_show(struct seq_file *m, void *v) +{ + int a, b, c; + unsigned long seq; + + do { + seq = read_seqbegin(&xtime_lock); + a = avenrun[0] + (FIXED_1/200); + b = avenrun[1] + (FIXED_1/200); + c = avenrun[2] + (FIXED_1/200); + } while (read_seqretry(&xtime_lock, seq)); + + seq_printf(m, "%d.%02d %d.%02d %d.%02d %ld/%d %d\n", + LOAD_INT(a), LOAD_FRAC(a), + LOAD_INT(b), LOAD_FRAC(b), + LOAD_INT(c), LOAD_FRAC(c), + nr_running(), nr_threads, + task_active_pid_ns(current)->last_pid); + return 0; +} + +static int loadavg_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, loadavg_proc_show, NULL); +} + +static const struct file_operations loadavg_proc_fops = { + .open = loadavg_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init proc_loadavg_init(void) +{ + proc_create("loadavg", 0, NULL, &loadavg_proc_fops); + return 0; +} +module_init(proc_loadavg_init); diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c new file mode 100644 index 00000000000..b1675c4e66d --- /dev/null +++ b/fs/proc/meminfo.c @@ -0,0 +1,168 @@ +#include <linux/fs.h> +#include <linux/hugetlb.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/mman.h> +#include <linux/mmzone.h> +#include <linux/proc_fs.h> +#include <linux/quicklist.h> +#include <linux/seq_file.h> +#include <linux/swap.h> +#include <linux/vmstat.h> +#include <asm/atomic.h> +#include <asm/page.h> +#include <asm/pgtable.h> +#include "internal.h" + +void __attribute__((weak)) arch_report_meminfo(struct seq_file *m) +{ +} + +static int meminfo_proc_show(struct seq_file *m, void *v) +{ + struct sysinfo i; + unsigned long committed; + unsigned long allowed; + struct vmalloc_info vmi; + long cached; + unsigned long pages[NR_LRU_LISTS]; + int lru; + +/* + * display in kilobytes. + */ +#define K(x) ((x) << (PAGE_SHIFT - 10)) + si_meminfo(&i); + si_swapinfo(&i); + committed = atomic_long_read(&vm_committed_space); + allowed = ((totalram_pages - hugetlb_total_pages()) + * sysctl_overcommit_ratio / 100) + total_swap_pages; + + cached = global_page_state(NR_FILE_PAGES) - + total_swapcache_pages - i.bufferram; + if (cached < 0) + cached = 0; + + get_vmalloc_info(&vmi); + + for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++) + pages[lru] = global_page_state(NR_LRU_BASE + lru); + + /* + * Tagged format, for easy grepping and expansion. + */ + seq_printf(m, + "MemTotal: %8lu kB\n" + "MemFree: %8lu kB\n" + "Buffers: %8lu kB\n" + "Cached: %8lu kB\n" + "SwapCached: %8lu kB\n" + "Active: %8lu kB\n" + "Inactive: %8lu kB\n" + "Active(anon): %8lu kB\n" + "Inactive(anon): %8lu kB\n" + "Active(file): %8lu kB\n" + "Inactive(file): %8lu kB\n" +#ifdef CONFIG_UNEVICTABLE_LRU + "Unevictable: %8lu kB\n" + "Mlocked: %8lu kB\n" +#endif +#ifdef CONFIG_HIGHMEM + "HighTotal: %8lu kB\n" + "HighFree: %8lu kB\n" + "LowTotal: %8lu kB\n" + "LowFree: %8lu kB\n" +#endif + "SwapTotal: %8lu kB\n" + "SwapFree: %8lu kB\n" + "Dirty: %8lu kB\n" + "Writeback: %8lu kB\n" + "AnonPages: %8lu kB\n" + "Mapped: %8lu kB\n" + "Slab: %8lu kB\n" + "SReclaimable: %8lu kB\n" + "SUnreclaim: %8lu kB\n" + "PageTables: %8lu kB\n" +#ifdef CONFIG_QUICKLIST + "Quicklists: %8lu kB\n" +#endif + "NFS_Unstable: %8lu kB\n" + "Bounce: %8lu kB\n" + "WritebackTmp: %8lu kB\n" + "CommitLimit: %8lu kB\n" + "Committed_AS: %8lu kB\n" + "VmallocTotal: %8lu kB\n" + "VmallocUsed: %8lu kB\n" + "VmallocChunk: %8lu kB\n", + K(i.totalram), + K(i.freeram), + K(i.bufferram), + K(cached), + K(total_swapcache_pages), + K(pages[LRU_ACTIVE_ANON] + pages[LRU_ACTIVE_FILE]), + K(pages[LRU_INACTIVE_ANON] + pages[LRU_INACTIVE_FILE]), + K(pages[LRU_ACTIVE_ANON]), + K(pages[LRU_INACTIVE_ANON]), + K(pages[LRU_ACTIVE_FILE]), + K(pages[LRU_INACTIVE_FILE]), +#ifdef CONFIG_UNEVICTABLE_LRU + K(pages[LRU_UNEVICTABLE]), + K(global_page_state(NR_MLOCK)), +#endif +#ifdef CONFIG_HIGHMEM + K(i.totalhigh), + K(i.freehigh), + K(i.totalram-i.totalhigh), + K(i.freeram-i.freehigh), +#endif + K(i.totalswap), + K(i.freeswap), + K(global_page_state(NR_FILE_DIRTY)), + K(global_page_state(NR_WRITEBACK)), + K(global_page_state(NR_ANON_PAGES)), + K(global_page_state(NR_FILE_MAPPED)), + K(global_page_state(NR_SLAB_RECLAIMABLE) + + global_page_state(NR_SLAB_UNRECLAIMABLE)), + K(global_page_state(NR_SLAB_RECLAIMABLE)), + K(global_page_state(NR_SLAB_UNRECLAIMABLE)), + K(global_page_state(NR_PAGETABLE)), +#ifdef CONFIG_QUICKLIST + K(quicklist_total_size()), +#endif + K(global_page_state(NR_UNSTABLE_NFS)), + K(global_page_state(NR_BOUNCE)), + K(global_page_state(NR_WRITEBACK_TEMP)), + K(allowed), + K(committed), + (unsigned long)VMALLOC_TOTAL >> 10, + vmi.used >> 10, + vmi.largest_chunk >> 10 + ); + + hugetlb_report_meminfo(m); + + arch_report_meminfo(m); + + return 0; +#undef K +} + +static int meminfo_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, meminfo_proc_show, NULL); +} + +static const struct file_operations meminfo_proc_fops = { + .open = meminfo_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init proc_meminfo_init(void) +{ + proc_create("meminfo", 0, NULL, &meminfo_proc_fops); + return 0; +} +module_init(proc_meminfo_init); diff --git a/fs/proc/page.c b/fs/proc/page.c new file mode 100644 index 00000000000..767d95a6d1b --- /dev/null +++ b/fs/proc/page.c @@ -0,0 +1,147 @@ +#include <linux/bootmem.h> +#include <linux/compiler.h> +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/mmzone.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <asm/uaccess.h> +#include "internal.h" + +#define KPMSIZE sizeof(u64) +#define KPMMASK (KPMSIZE - 1) +/* /proc/kpagecount - an array exposing page counts + * + * Each entry is a u64 representing the corresponding + * physical page count. + */ +static ssize_t kpagecount_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + u64 __user *out = (u64 __user *)buf; + struct page *ppage; + unsigned long src = *ppos; + unsigned long pfn; + ssize_t ret = 0; + u64 pcount; + + pfn = src / KPMSIZE; + count = min_t(size_t, count, (max_pfn * KPMSIZE) - src); + if (src & KPMMASK || count & KPMMASK) + return -EINVAL; + + while (count > 0) { + ppage = NULL; + if (pfn_valid(pfn)) + ppage = pfn_to_page(pfn); + pfn++; + if (!ppage) + pcount = 0; + else + pcount = page_mapcount(ppage); + + if (put_user(pcount, out++)) { + ret = -EFAULT; + break; + } + + count -= KPMSIZE; + } + + *ppos += (char __user *)out - buf; + if (!ret) + ret = (char __user *)out - buf; + return ret; +} + +static const struct file_operations proc_kpagecount_operations = { + .llseek = mem_lseek, + .read = kpagecount_read, +}; + +/* /proc/kpageflags - an array exposing page flags + * + * Each entry is a u64 representing the corresponding + * physical page flags. + */ + +/* These macros are used to decouple internal flags from exported ones */ + +#define KPF_LOCKED 0 +#define KPF_ERROR 1 +#define KPF_REFERENCED 2 +#define KPF_UPTODATE 3 +#define KPF_DIRTY 4 +#define KPF_LRU 5 +#define KPF_ACTIVE 6 +#define KPF_SLAB 7 +#define KPF_WRITEBACK 8 +#define KPF_RECLAIM 9 +#define KPF_BUDDY 10 + +#define kpf_copy_bit(flags, srcpos, dstpos) (((flags >> srcpos) & 1) << dstpos) + +static ssize_t kpageflags_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + u64 __user *out = (u64 __user *)buf; + struct page *ppage; + unsigned long src = *ppos; + unsigned long pfn; + ssize_t ret = 0; + u64 kflags, uflags; + + pfn = src / KPMSIZE; + count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src); + if (src & KPMMASK || count & KPMMASK) + return -EINVAL; + + while (count > 0) { + ppage = NULL; + if (pfn_valid(pfn)) + ppage = pfn_to_page(pfn); + pfn++; + if (!ppage) + kflags = 0; + else + kflags = ppage->flags; + + uflags = kpf_copy_bit(KPF_LOCKED, PG_locked, kflags) | + kpf_copy_bit(kflags, KPF_ERROR, PG_error) | + kpf_copy_bit(kflags, KPF_REFERENCED, PG_referenced) | + kpf_copy_bit(kflags, KPF_UPTODATE, PG_uptodate) | + kpf_copy_bit(kflags, KPF_DIRTY, PG_dirty) | + kpf_copy_bit(kflags, KPF_LRU, PG_lru) | + kpf_copy_bit(kflags, KPF_ACTIVE, PG_active) | + kpf_copy_bit(kflags, KPF_SLAB, PG_slab) | + kpf_copy_bit(kflags, KPF_WRITEBACK, PG_writeback) | + kpf_copy_bit(kflags, KPF_RECLAIM, PG_reclaim) | + kpf_copy_bit(kflags, KPF_BUDDY, PG_buddy); + + if (put_user(uflags, out++)) { + ret = -EFAULT; + break; + } + + count -= KPMSIZE; + } + + *ppos += (char __user *)out - buf; + if (!ret) + ret = (char __user *)out - buf; + return ret; +} + +static const struct file_operations proc_kpageflags_operations = { + .llseek = mem_lseek, + .read = kpageflags_read, +}; + +static int __init proc_page_init(void) +{ + proc_create("kpagecount", S_IRUSR, NULL, &proc_kpagecount_operations); + proc_create("kpageflags", S_IRUSR, NULL, &proc_kpageflags_operations); + return 0; +} +module_init(proc_page_init); diff --git a/fs/proc/proc_devtree.c b/fs/proc/proc_devtree.c index eca471bc851..d777789b7a8 100644 --- a/fs/proc/proc_devtree.c +++ b/fs/proc/proc_devtree.c @@ -4,6 +4,7 @@ * Copyright 1997 Paul Mackerras */ #include <linux/errno.h> +#include <linux/init.h> #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/stat.h> @@ -214,7 +215,7 @@ void proc_device_tree_add_node(struct device_node *np, /* * Called on initialization to set up the /proc/device-tree subtree */ -void proc_device_tree_init(void) +void __init proc_device_tree_init(void) { struct device_node *root; if ( !have_of ) diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c deleted file mode 100644 index 61b25f4eabe..00000000000 --- a/fs/proc/proc_misc.c +++ /dev/null @@ -1,935 +0,0 @@ -/* - * linux/fs/proc/proc_misc.c - * - * linux/fs/proc/array.c - * Copyright (C) 1992 by Linus Torvalds - * based on ideas by Darren Senn - * - * This used to be the part of array.c. See the rest of history and credits - * there. I took this into a separate file and switched the thing to generic - * proc_file_inode_operations, leaving in array.c only per-process stuff. - * Inumbers allocation made dynamic (via create_proc_entry()). AV, May 1999. - * - * Changes: - * Fulton Green : Encapsulated position metric calculations. - * <kernel@FultonGreen.com> - */ - -#include <linux/types.h> -#include <linux/errno.h> -#include <linux/time.h> -#include <linux/kernel.h> -#include <linux/kernel_stat.h> -#include <linux/fs.h> -#include <linux/tty.h> -#include <linux/string.h> -#include <linux/mman.h> -#include <linux/quicklist.h> -#include <linux/proc_fs.h> -#include <linux/ioport.h> -#include <linux/mm.h> -#include <linux/mmzone.h> -#include <linux/pagemap.h> -#include <linux/interrupt.h> -#include <linux/swap.h> -#include <linux/slab.h> -#include <linux/genhd.h> -#include <linux/smp.h> -#include <linux/signal.h> -#include <linux/module.h> -#include <linux/init.h> -#include <linux/seq_file.h> -#include <linux/times.h> -#include <linux/profile.h> -#include <linux/utsname.h> -#include <linux/blkdev.h> -#include <linux/hugetlb.h> -#include <linux/jiffies.h> -#include <linux/vmalloc.h> -#include <linux/crash_dump.h> -#include <linux/pid_namespace.h> -#include <linux/bootmem.h> -#include <asm/uaccess.h> -#include <asm/pgtable.h> -#include <asm/io.h> -#include <asm/tlb.h> -#include <asm/div64.h> -#include "internal.h" - -#define LOAD_INT(x) ((x) >> FSHIFT) -#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) -/* - * Warning: stuff below (imported functions) assumes that its output will fit - * into one page. For some of those functions it may be wrong. Moreover, we - * have a way to deal with that gracefully. Right now I used straightforward - * wrappers, but this needs further analysis wrt potential overflows. - */ -extern int get_hardware_list(char *); -extern int get_stram_list(char *); -extern int get_exec_domain_list(char *); - -static int proc_calc_metrics(char *page, char **start, off_t off, - int count, int *eof, int len) -{ - if (len <= off+count) *eof = 1; - *start = page + off; - len -= off; - if (len>count) len = count; - if (len<0) len = 0; - return len; -} - -static int loadavg_read_proc(char *page, char **start, off_t off, - int count, int *eof, void *data) -{ - int a, b, c; - int len; - unsigned long seq; - - do { - seq = read_seqbegin(&xtime_lock); - a = avenrun[0] + (FIXED_1/200); - b = avenrun[1] + (FIXED_1/200); - c = avenrun[2] + (FIXED_1/200); - } while (read_seqretry(&xtime_lock, seq)); - - len = sprintf(page,"%d.%02d %d.%02d %d.%02d %ld/%d %d\n", - LOAD_INT(a), LOAD_FRAC(a), - LOAD_INT(b), LOAD_FRAC(b), - LOAD_INT(c), LOAD_FRAC(c), - nr_running(), nr_threads, - task_active_pid_ns(current)->last_pid); - return proc_calc_metrics(page, start, off, count, eof, len); -} - -static int uptime_read_proc(char *page, char **start, off_t off, - int count, int *eof, void *data) -{ - struct timespec uptime; - struct timespec idle; - int len; - cputime_t idletime = cputime_add(init_task.utime, init_task.stime); - - do_posix_clock_monotonic_gettime(&uptime); - monotonic_to_bootbased(&uptime); - cputime_to_timespec(idletime, &idle); - len = sprintf(page,"%lu.%02lu %lu.%02lu\n", - (unsigned long) uptime.tv_sec, - (uptime.tv_nsec / (NSEC_PER_SEC / 100)), - (unsigned long) idle.tv_sec, - (idle.tv_nsec / (NSEC_PER_SEC / 100))); - - return proc_calc_metrics(page, start, off, count, eof, len); -} - -int __attribute__((weak)) arch_report_meminfo(char *page) -{ - return 0; -} - -static int meminfo_read_proc(char *page, char **start, off_t off, - int count, int *eof, void *data) -{ - struct sysinfo i; - int len; - unsigned long committed; - unsigned long allowed; - struct vmalloc_info vmi; - long cached; - unsigned long pages[NR_LRU_LISTS]; - int lru; - -/* - * display in kilobytes. - */ -#define K(x) ((x) << (PAGE_SHIFT - 10)) - si_meminfo(&i); - si_swapinfo(&i); - committed = atomic_long_read(&vm_committed_space); - allowed = ((totalram_pages - hugetlb_total_pages()) - * sysctl_overcommit_ratio / 100) + total_swap_pages; - - cached = global_page_state(NR_FILE_PAGES) - - total_swapcache_pages - i.bufferram; - if (cached < 0) - cached = 0; - - get_vmalloc_info(&vmi); - - for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++) - pages[lru] = global_page_state(NR_LRU_BASE + lru); - - /* - * Tagged format, for easy grepping and expansion. - */ - len = sprintf(page, - "MemTotal: %8lu kB\n" - "MemFree: %8lu kB\n" - "Buffers: %8lu kB\n" - "Cached: %8lu kB\n" - "SwapCached: %8lu kB\n" - "Active: %8lu kB\n" - "Inactive: %8lu kB\n" - "Active(anon): %8lu kB\n" - "Inactive(anon): %8lu kB\n" - "Active(file): %8lu kB\n" - "Inactive(file): %8lu kB\n" -#ifdef CONFIG_UNEVICTABLE_LRU - "Unevictable: %8lu kB\n" - "Mlocked: %8lu kB\n" -#endif -#ifdef CONFIG_HIGHMEM - "HighTotal: %8lu kB\n" - "HighFree: %8lu kB\n" - "LowTotal: %8lu kB\n" - "LowFree: %8lu kB\n" -#endif - "SwapTotal: %8lu kB\n" - "SwapFree: %8lu kB\n" - "Dirty: %8lu kB\n" - "Writeback: %8lu kB\n" - "AnonPages: %8lu kB\n" - "Mapped: %8lu kB\n" - "Slab: %8lu kB\n" - "SReclaimable: %8lu kB\n" - "SUnreclaim: %8lu kB\n" - "PageTables: %8lu kB\n" -#ifdef CONFIG_QUICKLIST - "Quicklists: %8lu kB\n" -#endif - "NFS_Unstable: %8lu kB\n" - "Bounce: %8lu kB\n" - "WritebackTmp: %8lu kB\n" - "CommitLimit: %8lu kB\n" - "Committed_AS: %8lu kB\n" - "VmallocTotal: %8lu kB\n" - "VmallocUsed: %8lu kB\n" - "VmallocChunk: %8lu kB\n", - K(i.totalram), - K(i.freeram), - K(i.bufferram), - K(cached), - K(total_swapcache_pages), - K(pages[LRU_ACTIVE_ANON] + pages[LRU_ACTIVE_FILE]), - K(pages[LRU_INACTIVE_ANON] + pages[LRU_INACTIVE_FILE]), - K(pages[LRU_ACTIVE_ANON]), - K(pages[LRU_INACTIVE_ANON]), - K(pages[LRU_ACTIVE_FILE]), - K(pages[LRU_INACTIVE_FILE]), -#ifdef CONFIG_UNEVICTABLE_LRU - K(pages[LRU_UNEVICTABLE]), - K(global_page_state(NR_MLOCK)), -#endif -#ifdef CONFIG_HIGHMEM - K(i.totalhigh), - K(i.freehigh), - K(i.totalram-i.totalhigh), - K(i.freeram-i.freehigh), -#endif - K(i.totalswap), - K(i.freeswap), - K(global_page_state(NR_FILE_DIRTY)), - K(global_page_state(NR_WRITEBACK)), - K(global_page_state(NR_ANON_PAGES)), - K(global_page_state(NR_FILE_MAPPED)), - K(global_page_state(NR_SLAB_RECLAIMABLE) + - global_page_state(NR_SLAB_UNRECLAIMABLE)), - K(global_page_state(NR_SLAB_RECLAIMABLE)), - K(global_page_state(NR_SLAB_UNRECLAIMABLE)), - K(global_page_state(NR_PAGETABLE)), -#ifdef CONFIG_QUICKLIST - K(quicklist_total_size()), -#endif - K(global_page_state(NR_UNSTABLE_NFS)), - K(global_page_state(NR_BOUNCE)), - K(global_page_state(NR_WRITEBACK_TEMP)), - K(allowed), - K(committed), - (unsigned long)VMALLOC_TOTAL >> 10, - vmi.used >> 10, - vmi.largest_chunk >> 10 - ); - - len += hugetlb_report_meminfo(page + len); - - len += arch_report_meminfo(page + len); - - return proc_calc_metrics(page, start, off, count, eof, len); -#undef K -} - -static int fragmentation_open(struct inode *inode, struct file *file) -{ - (void)inode; - return seq_open(file, &fragmentation_op); -} - -static const struct file_operations fragmentation_file_operations = { - .open = fragmentation_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -static int pagetypeinfo_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &pagetypeinfo_op); -} - -static const struct file_operations pagetypeinfo_file_ops = { - .open = pagetypeinfo_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -static int zoneinfo_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &zoneinfo_op); -} - -static const struct file_operations proc_zoneinfo_file_operations = { - .open = zoneinfo_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -static int version_read_proc(char *page, char **start, off_t off, - int count, int *eof, void *data) -{ - int len; - - len = snprintf(page, PAGE_SIZE, linux_proc_banner, - utsname()->sysname, - utsname()->release, - utsname()->version); - return proc_calc_metrics(page, start, off, count, eof, len); -} - -extern const struct seq_operations cpuinfo_op; -static int cpuinfo_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &cpuinfo_op); -} - -static const struct file_operations proc_cpuinfo_operations = { - .open = cpuinfo_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -static int devinfo_show(struct seq_file *f, void *v) -{ - int i = *(loff_t *) v; - - if (i < CHRDEV_MAJOR_HASH_SIZE) { - if (i == 0) - seq_printf(f, "Character devices:\n"); - chrdev_show(f, i); - } -#ifdef CONFIG_BLOCK - else { - i -= CHRDEV_MAJOR_HASH_SIZE; - if (i == 0) - seq_printf(f, "\nBlock devices:\n"); - blkdev_show(f, i); - } -#endif - return 0; -} - -static void *devinfo_start(struct seq_file *f, loff_t *pos) -{ - if (*pos < (BLKDEV_MAJOR_HASH_SIZE + CHRDEV_MAJOR_HASH_SIZE)) - return pos; - return NULL; -} - -static void *devinfo_next(struct seq_file *f, void *v, loff_t *pos) -{ - (*pos)++; - if (*pos >= (BLKDEV_MAJOR_HASH_SIZE + CHRDEV_MAJOR_HASH_SIZE)) - return NULL; - return pos; -} - -static void devinfo_stop(struct seq_file *f, void *v) -{ - /* Nothing to do */ -} - -static const struct seq_operations devinfo_ops = { - .start = devinfo_start, - .next = devinfo_next, - .stop = devinfo_stop, - .show = devinfo_show -}; - -static int devinfo_open(struct inode *inode, struct file *filp) -{ - return seq_open(filp, &devinfo_ops); -} - -static const struct file_operations proc_devinfo_operations = { - .open = devinfo_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -static int vmstat_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &vmstat_op); -} -static const struct file_operations proc_vmstat_file_operations = { - .open = vmstat_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -#ifdef CONFIG_PROC_HARDWARE -static int hardware_read_proc(char *page, char **start, off_t off, - int count, int *eof, void *data) -{ - int len = get_hardware_list(page); - return proc_calc_metrics(page, start, off, count, eof, len); -} -#endif - -#ifdef CONFIG_STRAM_PROC -static int stram_read_proc(char *page, char **start, off_t off, - int count, int *eof, void *data) -{ - int len = get_stram_list(page); - return proc_calc_metrics(page, start, off, count, eof, len); -} -#endif - -#ifdef CONFIG_BLOCK -static int partitions_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &partitions_op); -} -static const struct file_operations proc_partitions_operations = { - .open = partitions_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -static int diskstats_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &diskstats_op); -} -static const struct file_operations proc_diskstats_operations = { - .open = diskstats_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; -#endif - -#ifdef CONFIG_MODULES -extern const struct seq_operations modules_op; -static int modules_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &modules_op); -} -static const struct file_operations proc_modules_operations = { - .open = modules_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; -#endif - -#ifdef CONFIG_SLABINFO -static int slabinfo_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &slabinfo_op); -} -static const struct file_operations proc_slabinfo_operations = { - .open = slabinfo_open, - .read = seq_read, - .write = slabinfo_write, - .llseek = seq_lseek, - .release = seq_release, -}; - -#ifdef CONFIG_DEBUG_SLAB_LEAK -extern const struct seq_operations slabstats_op; -static int slabstats_open(struct inode *inode, struct file *file) -{ - unsigned long *n = kzalloc(PAGE_SIZE, GFP_KERNEL); - int ret = -ENOMEM; - if (n) { - ret = seq_open(file, &slabstats_op); - if (!ret) { - struct seq_file *m = file->private_data; - *n = PAGE_SIZE / (2 * sizeof(unsigned long)); - m->private = n; - n = NULL; - } - kfree(n); - } - return ret; -} - -static const struct file_operations proc_slabstats_operations = { - .open = slabstats_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_private, -}; -#endif -#endif - -#ifdef CONFIG_MMU -static int vmalloc_open(struct inode *inode, struct file *file) -{ - unsigned int *ptr = NULL; - int ret; - - if (NUMA_BUILD) - ptr = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL); - ret = seq_open(file, &vmalloc_op); - if (!ret) { - struct seq_file *m = file->private_data; - m->private = ptr; - } else - kfree(ptr); - return ret; -} - -static const struct file_operations proc_vmalloc_operations = { - .open = vmalloc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_private, -}; -#endif - -#ifndef arch_irq_stat_cpu -#define arch_irq_stat_cpu(cpu) 0 -#endif -#ifndef arch_irq_stat -#define arch_irq_stat() 0 -#endif - -static int show_stat(struct seq_file *p, void *v) -{ - int i; - unsigned long jif; - cputime64_t user, nice, system, idle, iowait, irq, softirq, steal; - cputime64_t guest; - u64 sum = 0; - struct timespec boottime; - unsigned int *per_irq_sum; - - per_irq_sum = kzalloc(sizeof(unsigned int)*NR_IRQS, GFP_KERNEL); - if (!per_irq_sum) - return -ENOMEM; - - user = nice = system = idle = iowait = - irq = softirq = steal = cputime64_zero; - guest = cputime64_zero; - getboottime(&boottime); - jif = boottime.tv_sec; - - for_each_possible_cpu(i) { - int j; - - user = cputime64_add(user, kstat_cpu(i).cpustat.user); - nice = cputime64_add(nice, kstat_cpu(i).cpustat.nice); - system = cputime64_add(system, kstat_cpu(i).cpustat.system); - idle = cputime64_add(idle, kstat_cpu(i).cpustat.idle); - iowait = cputime64_add(iowait, kstat_cpu(i).cpustat.iowait); - irq = cputime64_add(irq, kstat_cpu(i).cpustat.irq); - softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq); - steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal); - guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest); - for (j = 0; j < NR_IRQS; j++) { - unsigned int temp = kstat_cpu(i).irqs[j]; - sum += temp; - per_irq_sum[j] += temp; - } - sum += arch_irq_stat_cpu(i); - } - sum += arch_irq_stat(); - - seq_printf(p, "cpu %llu %llu %llu %llu %llu %llu %llu %llu %llu\n", - (unsigned long long)cputime64_to_clock_t(user), - (unsigned long long)cputime64_to_clock_t(nice), - (unsigned long long)cputime64_to_clock_t(system), - (unsigned long long)cputime64_to_clock_t(idle), - (unsigned long long)cputime64_to_clock_t(iowait), - (unsigned long long)cputime64_to_clock_t(irq), - (unsigned long long)cputime64_to_clock_t(softirq), - (unsigned long long)cputime64_to_clock_t(steal), - (unsigned long long)cputime64_to_clock_t(guest)); - for_each_online_cpu(i) { - - /* Copy values here to work around gcc-2.95.3, gcc-2.96 */ - user = kstat_cpu(i).cpustat.user; - nice = kstat_cpu(i).cpustat.nice; - system = kstat_cpu(i).cpustat.system; - idle = kstat_cpu(i).cpustat.idle; - iowait = kstat_cpu(i).cpustat.iowait; - irq = kstat_cpu(i).cpustat.irq; - softirq = kstat_cpu(i).cpustat.softirq; - steal = kstat_cpu(i).cpustat.steal; - guest = kstat_cpu(i).cpustat.guest; - seq_printf(p, - "cpu%d %llu %llu %llu %llu %llu %llu %llu %llu %llu\n", - i, - (unsigned long long)cputime64_to_clock_t(user), - (unsigned long long)cputime64_to_clock_t(nice), - (unsigned long long)cputime64_to_clock_t(system), - (unsigned long long)cputime64_to_clock_t(idle), - (unsigned long long)cputime64_to_clock_t(iowait), - (unsigned long long)cputime64_to_clock_t(irq), - (unsigned long long)cputime64_to_clock_t(softirq), - (unsigned long long)cputime64_to_clock_t(steal), - (unsigned long long)cputime64_to_clock_t(guest)); - } - seq_printf(p, "intr %llu", (unsigned long long)sum); - - for (i = 0; i < NR_IRQS; i++) - seq_printf(p, " %u", per_irq_sum[i]); - - seq_printf(p, - "\nctxt %llu\n" - "btime %lu\n" - "processes %lu\n" - "procs_running %lu\n" - "procs_blocked %lu\n", - nr_context_switches(), - (unsigned long)jif, - total_forks, - nr_running(), - nr_iowait()); - - kfree(per_irq_sum); - return 0; -} - -static int stat_open(struct inode *inode, struct file *file) -{ - unsigned size = 4096 * (1 + num_possible_cpus() / 32); - char *buf; - struct seq_file *m; - int res; - - /* don't ask for more than the kmalloc() max size, currently 128 KB */ - if (size > 128 * 1024) - size = 128 * 1024; - buf = kmalloc(size, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - res = single_open(file, show_stat, NULL); - if (!res) { - m = file->private_data; - m->buf = buf; - m->size = size; - } else - kfree(buf); - return res; -} -static const struct file_operations proc_stat_operations = { - .open = stat_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -/* - * /proc/interrupts - */ -static void *int_seq_start(struct seq_file *f, loff_t *pos) -{ - return (*pos <= NR_IRQS) ? pos : NULL; -} - -static void *int_seq_next(struct seq_file *f, void *v, loff_t *pos) -{ - (*pos)++; - if (*pos > NR_IRQS) - return NULL; - return pos; -} - -static void int_seq_stop(struct seq_file *f, void *v) -{ - /* Nothing to do */ -} - - -static const struct seq_operations int_seq_ops = { - .start = int_seq_start, - .next = int_seq_next, - .stop = int_seq_stop, - .show = show_interrupts -}; - -static int interrupts_open(struct inode *inode, struct file *filp) -{ - return seq_open(filp, &int_seq_ops); -} - -static const struct file_operations proc_interrupts_operations = { - .open = interrupts_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -static int filesystems_read_proc(char *page, char **start, off_t off, - int count, int *eof, void *data) -{ - int len = get_filesystem_list(page); - return proc_calc_metrics(page, start, off, count, eof, len); -} - -static int cmdline_read_proc(char *page, char **start, off_t off, - int count, int *eof, void *data) -{ - int len; - - len = sprintf(page, "%s\n", saved_command_line); - return proc_calc_metrics(page, start, off, count, eof, len); -} - -#ifdef CONFIG_FILE_LOCKING -static int locks_open(struct inode *inode, struct file *filp) -{ - return seq_open(filp, &locks_seq_operations); -} - -static const struct file_operations proc_locks_operations = { - .open = locks_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; -#endif /* CONFIG_FILE_LOCKING */ - -static int execdomains_read_proc(char *page, char **start, off_t off, - int count, int *eof, void *data) -{ - int len = get_exec_domain_list(page); - return proc_calc_metrics(page, start, off, count, eof, len); -} - -#ifdef CONFIG_PROC_PAGE_MONITOR -#define KPMSIZE sizeof(u64) -#define KPMMASK (KPMSIZE - 1) -/* /proc/kpagecount - an array exposing page counts - * - * Each entry is a u64 representing the corresponding - * physical page count. - */ -static ssize_t kpagecount_read(struct file *file, char __user *buf, - size_t count, loff_t *ppos) -{ - u64 __user *out = (u64 __user *)buf; - struct page *ppage; - unsigned long src = *ppos; - unsigned long pfn; - ssize_t ret = 0; - u64 pcount; - - pfn = src / KPMSIZE; - count = min_t(size_t, count, (max_pfn * KPMSIZE) - src); - if (src & KPMMASK || count & KPMMASK) - return -EINVAL; - - while (count > 0) { - ppage = NULL; - if (pfn_valid(pfn)) - ppage = pfn_to_page(pfn); - pfn++; - if (!ppage) - pcount = 0; - else - pcount = page_mapcount(ppage); - - if (put_user(pcount, out++)) { - ret = -EFAULT; - break; - } - - count -= KPMSIZE; - } - - *ppos += (char __user *)out - buf; - if (!ret) - ret = (char __user *)out - buf; - return ret; -} - -static struct file_operations proc_kpagecount_operations = { - .llseek = mem_lseek, - .read = kpagecount_read, -}; - -/* /proc/kpageflags - an array exposing page flags - * - * Each entry is a u64 representing the corresponding - * physical page flags. - */ - -/* These macros are used to decouple internal flags from exported ones */ - -#define KPF_LOCKED 0 -#define KPF_ERROR 1 -#define KPF_REFERENCED 2 -#define KPF_UPTODATE 3 -#define KPF_DIRTY 4 -#define KPF_LRU 5 -#define KPF_ACTIVE 6 -#define KPF_SLAB 7 -#define KPF_WRITEBACK 8 -#define KPF_RECLAIM 9 -#define KPF_BUDDY 10 - -#define kpf_copy_bit(flags, srcpos, dstpos) (((flags >> srcpos) & 1) << dstpos) - -static ssize_t kpageflags_read(struct file *file, char __user *buf, - size_t count, loff_t *ppos) -{ - u64 __user *out = (u64 __user *)buf; - struct page *ppage; - unsigned long src = *ppos; - unsigned long pfn; - ssize_t ret = 0; - u64 kflags, uflags; - - pfn = src / KPMSIZE; - count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src); - if (src & KPMMASK || count & KPMMASK) - return -EINVAL; - - while (count > 0) { - ppage = NULL; - if (pfn_valid(pfn)) - ppage = pfn_to_page(pfn); - pfn++; - if (!ppage) - kflags = 0; - else - kflags = ppage->flags; - - uflags = kpf_copy_bit(KPF_LOCKED, PG_locked, kflags) | - kpf_copy_bit(kflags, KPF_ERROR, PG_error) | - kpf_copy_bit(kflags, KPF_REFERENCED, PG_referenced) | - kpf_copy_bit(kflags, KPF_UPTODATE, PG_uptodate) | - kpf_copy_bit(kflags, KPF_DIRTY, PG_dirty) | - kpf_copy_bit(kflags, KPF_LRU, PG_lru) | - kpf_copy_bit(kflags, KPF_ACTIVE, PG_active) | - kpf_copy_bit(kflags, KPF_SLAB, PG_slab) | - kpf_copy_bit(kflags, KPF_WRITEBACK, PG_writeback) | - kpf_copy_bit(kflags, KPF_RECLAIM, PG_reclaim) | - kpf_copy_bit(kflags, KPF_BUDDY, PG_buddy); - - if (put_user(uflags, out++)) { - ret = -EFAULT; - break; - } - - count -= KPMSIZE; - } - - *ppos += (char __user *)out - buf; - if (!ret) - ret = (char __user *)out - buf; - return ret; -} - -static struct file_operations proc_kpageflags_operations = { - .llseek = mem_lseek, - .read = kpageflags_read, -}; -#endif /* CONFIG_PROC_PAGE_MONITOR */ - -struct proc_dir_entry *proc_root_kcore; - -void __init proc_misc_init(void) -{ - static struct { - char *name; - int (*read_proc)(char*,char**,off_t,int,int*,void*); - } *p, simple_ones[] = { - {"loadavg", loadavg_read_proc}, - {"uptime", uptime_read_proc}, - {"meminfo", meminfo_read_proc}, - {"version", version_read_proc}, -#ifdef CONFIG_PROC_HARDWARE - {"hardware", hardware_read_proc}, -#endif -#ifdef CONFIG_STRAM_PROC - {"stram", stram_read_proc}, -#endif - {"filesystems", filesystems_read_proc}, - {"cmdline", cmdline_read_proc}, - {"execdomains", execdomains_read_proc}, - {NULL,} - }; - for (p = simple_ones; p->name; p++) - create_proc_read_entry(p->name, 0, NULL, p->read_proc, NULL); - - proc_symlink("mounts", NULL, "self/mounts"); - - /* And now for trickier ones */ -#ifdef CONFIG_PRINTK - proc_create("kmsg", S_IRUSR, NULL, &proc_kmsg_operations); -#endif -#ifdef CONFIG_FILE_LOCKING - proc_create("locks", 0, NULL, &proc_locks_operations); -#endif - proc_create("devices", 0, NULL, &proc_devinfo_operations); - proc_create("cpuinfo", 0, NULL, &proc_cpuinfo_operations); -#ifdef CONFIG_BLOCK - proc_create("partitions", 0, NULL, &proc_partitions_operations); -#endif - proc_create("stat", 0, NULL, &proc_stat_operations); - proc_create("interrupts", 0, NULL, &proc_interrupts_operations); -#ifdef CONFIG_SLABINFO - proc_create("slabinfo",S_IWUSR|S_IRUGO,NULL,&proc_slabinfo_operations); -#ifdef CONFIG_DEBUG_SLAB_LEAK - proc_create("slab_allocators", 0, NULL, &proc_slabstats_operations); -#endif -#endif -#ifdef CONFIG_MMU - proc_create("vmallocinfo", S_IRUSR, NULL, &proc_vmalloc_operations); -#endif - proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations); - proc_create("pagetypeinfo", S_IRUGO, NULL, &pagetypeinfo_file_ops); - proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations); - proc_create("zoneinfo", S_IRUGO, NULL, &proc_zoneinfo_file_operations); -#ifdef CONFIG_BLOCK - proc_create("diskstats", 0, NULL, &proc_diskstats_operations); -#endif -#ifdef CONFIG_MODULES - proc_create("modules", 0, NULL, &proc_modules_operations); -#endif -#ifdef CONFIG_SCHEDSTATS - proc_create("schedstat", 0, NULL, &proc_schedstat_operations); -#endif -#ifdef CONFIG_PROC_KCORE - proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, &proc_kcore_operations); - if (proc_root_kcore) - proc_root_kcore->size = - (size_t)high_memory - PAGE_OFFSET + PAGE_SIZE; -#endif -#ifdef CONFIG_PROC_PAGE_MONITOR - proc_create("kpagecount", S_IRUSR, NULL, &proc_kpagecount_operations); - proc_create("kpageflags", S_IRUSR, NULL, &proc_kpageflags_operations); -#endif -#ifdef CONFIG_PROC_VMCORE - proc_vmcore = proc_create("vmcore", S_IRUSR, NULL, &proc_vmcore_operations); -#endif -} diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 945a81043ba..94fcfff6863 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1,7 +1,7 @@ /* * /proc/sys support */ - +#include <linux/init.h> #include <linux/sysctl.h> #include <linux/proc_fs.h> #include <linux/security.h> @@ -298,13 +298,19 @@ static int proc_sys_permission(struct inode *inode, int mask) * sysctl entries that are not writeable, * are _NOT_ writeable, capabilities or not. */ - struct ctl_table_header *head = grab_header(inode); - struct ctl_table *table = PROC_I(inode)->sysctl_entry; + struct ctl_table_header *head; + struct ctl_table *table; int error; + /* Executable files are not allowed under /proc/sys/ */ + if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode)) + return -EACCES; + + head = grab_header(inode); if (IS_ERR(head)) return PTR_ERR(head); + table = PROC_I(inode)->sysctl_entry; if (!table) /* global root - r-xr-xr-x */ error = mask & MAY_WRITE ? -EACCES : 0; else /* Use the permissions on the sysctl table entry */ @@ -353,6 +359,7 @@ static const struct file_operations proc_sys_file_operations = { static const struct file_operations proc_sys_dir_file_operations = { .readdir = proc_sys_readdir, + .llseek = generic_file_llseek, }; static const struct inode_operations proc_sys_inode_operations = { @@ -395,7 +402,7 @@ static struct dentry_operations proc_sys_dentry_operations = { .d_compare = proc_sys_compare, }; -int proc_sys_init(void) +int __init proc_sys_init(void) { struct proc_dir_entry *proc_sys_root; diff --git a/fs/proc/root.c b/fs/proc/root.c index 95117538a4f..7761602af9d 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -104,9 +104,9 @@ static struct file_system_type proc_fs_type = { void __init proc_root_init(void) { - int err = proc_init_inodecache(); - if (err) - return; + int err; + + proc_init_inodecache(); err = register_filesystem(&proc_fs_type); if (err) return; @@ -117,7 +117,7 @@ void __init proc_root_init(void) return; } - proc_misc_init(); + proc_symlink("mounts", NULL, "self/mounts"); proc_net_init(); diff --git a/fs/proc/stat.c b/fs/proc/stat.c new file mode 100644 index 00000000000..81904f07679 --- /dev/null +++ b/fs/proc/stat.c @@ -0,0 +1,153 @@ +#include <linux/cpumask.h> +#include <linux/fs.h> +#include <linux/gfp.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kernel_stat.h> +#include <linux/proc_fs.h> +#include <linux/sched.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/time.h> +#include <asm/cputime.h> + +#ifndef arch_irq_stat_cpu +#define arch_irq_stat_cpu(cpu) 0 +#endif +#ifndef arch_irq_stat +#define arch_irq_stat() 0 +#endif + +static int show_stat(struct seq_file *p, void *v) +{ + int i, j; + unsigned long jif; + cputime64_t user, nice, system, idle, iowait, irq, softirq, steal; + cputime64_t guest; + u64 sum = 0; + struct timespec boottime; + unsigned int per_irq_sum; + + user = nice = system = idle = iowait = + irq = softirq = steal = cputime64_zero; + guest = cputime64_zero; + getboottime(&boottime); + jif = boottime.tv_sec; + + for_each_possible_cpu(i) { + user = cputime64_add(user, kstat_cpu(i).cpustat.user); + nice = cputime64_add(nice, kstat_cpu(i).cpustat.nice); + system = cputime64_add(system, kstat_cpu(i).cpustat.system); + idle = cputime64_add(idle, kstat_cpu(i).cpustat.idle); + iowait = cputime64_add(iowait, kstat_cpu(i).cpustat.iowait); + irq = cputime64_add(irq, kstat_cpu(i).cpustat.irq); + softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq); + steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal); + guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest); + + for_each_irq_nr(j) + sum += kstat_irqs_cpu(j, i); + + sum += arch_irq_stat_cpu(i); + } + sum += arch_irq_stat(); + + seq_printf(p, "cpu %llu %llu %llu %llu %llu %llu %llu %llu %llu\n", + (unsigned long long)cputime64_to_clock_t(user), + (unsigned long long)cputime64_to_clock_t(nice), + (unsigned long long)cputime64_to_clock_t(system), + (unsigned long long)cputime64_to_clock_t(idle), + (unsigned long long)cputime64_to_clock_t(iowait), + (unsigned long long)cputime64_to_clock_t(irq), + (unsigned long long)cputime64_to_clock_t(softirq), + (unsigned long long)cputime64_to_clock_t(steal), + (unsigned long long)cputime64_to_clock_t(guest)); + for_each_online_cpu(i) { + + /* Copy values here to work around gcc-2.95.3, gcc-2.96 */ + user = kstat_cpu(i).cpustat.user; + nice = kstat_cpu(i).cpustat.nice; + system = kstat_cpu(i).cpustat.system; + idle = kstat_cpu(i).cpustat.idle; + iowait = kstat_cpu(i).cpustat.iowait; + irq = kstat_cpu(i).cpustat.irq; + softirq = kstat_cpu(i).cpustat.softirq; + steal = kstat_cpu(i).cpustat.steal; + guest = kstat_cpu(i).cpustat.guest; + seq_printf(p, + "cpu%d %llu %llu %llu %llu %llu %llu %llu %llu %llu\n", + i, + (unsigned long long)cputime64_to_clock_t(user), + (unsigned long long)cputime64_to_clock_t(nice), + (unsigned long long)cputime64_to_clock_t(system), + (unsigned long long)cputime64_to_clock_t(idle), + (unsigned long long)cputime64_to_clock_t(iowait), + (unsigned long long)cputime64_to_clock_t(irq), + (unsigned long long)cputime64_to_clock_t(softirq), + (unsigned long long)cputime64_to_clock_t(steal), + (unsigned long long)cputime64_to_clock_t(guest)); + } + seq_printf(p, "intr %llu", (unsigned long long)sum); + + /* sum again ? it could be updated? */ + for_each_irq_nr(j) { + per_irq_sum = 0; + + for_each_possible_cpu(i) + per_irq_sum += kstat_irqs_cpu(j, i); + + seq_printf(p, " %u", per_irq_sum); + } + + seq_printf(p, + "\nctxt %llu\n" + "btime %lu\n" + "processes %lu\n" + "procs_running %lu\n" + "procs_blocked %lu\n", + nr_context_switches(), + (unsigned long)jif, + total_forks, + nr_running(), + nr_iowait()); + + return 0; +} + +static int stat_open(struct inode *inode, struct file *file) +{ + unsigned size = 4096 * (1 + num_possible_cpus() / 32); + char *buf; + struct seq_file *m; + int res; + + /* don't ask for more than the kmalloc() max size, currently 128 KB */ + if (size > 128 * 1024) + size = 128 * 1024; + buf = kmalloc(size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + res = single_open(file, show_stat, NULL); + if (!res) { + m = file->private_data; + m->buf = buf; + m->size = size; + } else + kfree(buf); + return res; +} + +static const struct file_operations proc_stat_operations = { + .open = stat_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init proc_stat_init(void) +{ + proc_create("stat", 0, NULL, &proc_stat_operations); + return 0; +} +module_init(proc_stat_init); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 4806830ea2a..b770c095e45 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -198,11 +198,8 @@ static int do_maps_open(struct inode *inode, struct file *file, return ret; } -static int show_map(struct seq_file *m, void *v) +static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma) { - struct proc_maps_private *priv = m->private; - struct task_struct *task = priv->task; - struct vm_area_struct *vma = v; struct mm_struct *mm = vma->vm_mm; struct file *file = vma->vm_file; int flags = vma->vm_flags; @@ -254,6 +251,15 @@ static int show_map(struct seq_file *m, void *v) } } seq_putc(m, '\n'); +} + +static int show_map(struct seq_file *m, void *v) +{ + struct vm_area_struct *vma = v; + struct proc_maps_private *priv = m->private; + struct task_struct *task = priv->task; + + show_map_vma(m, vma); if (m->count < m->size) /* vma is copied successfully */ m->version = (vma != get_gate_vma(task))? vma->vm_start: 0; @@ -364,9 +370,10 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, static int show_smap(struct seq_file *m, void *v) { + struct proc_maps_private *priv = m->private; + struct task_struct *task = priv->task; struct vm_area_struct *vma = v; struct mem_size_stats mss; - int ret; struct mm_walk smaps_walk = { .pmd_entry = smaps_pte_range, .mm = vma->vm_mm, @@ -378,9 +385,7 @@ static int show_smap(struct seq_file *m, void *v) if (vma->vm_mm && !is_vm_hugetlb_page(vma)) walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk); - ret = show_map(m, v); - if (ret) - return ret; + show_map_vma(m, vma); seq_printf(m, "Size: %8lu kB\n" @@ -402,7 +407,9 @@ static int show_smap(struct seq_file *m, void *v) mss.referenced >> 10, mss.swap >> 10); - return ret; + if (m->count < m->size) /* vma is copied successfully */ + m->version = (vma != get_gate_vma(task)) ? vma->vm_start : 0; + return 0; } static const struct seq_operations proc_pid_smaps_op = { diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c new file mode 100644 index 00000000000..0c10a0b3f14 --- /dev/null +++ b/fs/proc/uptime.c @@ -0,0 +1,43 @@ +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/proc_fs.h> +#include <linux/sched.h> +#include <linux/seq_file.h> +#include <linux/time.h> +#include <asm/cputime.h> + +static int uptime_proc_show(struct seq_file *m, void *v) +{ + struct timespec uptime; + struct timespec idle; + cputime_t idletime = cputime_add(init_task.utime, init_task.stime); + + do_posix_clock_monotonic_gettime(&uptime); + monotonic_to_bootbased(&uptime); + cputime_to_timespec(idletime, &idle); + seq_printf(m, "%lu.%02lu %lu.%02lu\n", + (unsigned long) uptime.tv_sec, + (uptime.tv_nsec / (NSEC_PER_SEC / 100)), + (unsigned long) idle.tv_sec, + (idle.tv_nsec / (NSEC_PER_SEC / 100))); + return 0; +} + +static int uptime_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, uptime_proc_show, NULL); +} + +static const struct file_operations uptime_proc_fops = { + .open = uptime_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init proc_uptime_init(void) +{ + proc_create("uptime", 0, NULL, &uptime_proc_fops); + return 0; +} +module_init(proc_uptime_init); diff --git a/fs/proc/version.c b/fs/proc/version.c new file mode 100644 index 00000000000..76817a60678 --- /dev/null +++ b/fs/proc/version.c @@ -0,0 +1,34 @@ +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/utsname.h> + +static int version_proc_show(struct seq_file *m, void *v) +{ + seq_printf(m, linux_proc_banner, + utsname()->sysname, + utsname()->release, + utsname()->version); + return 0; +} + +static int version_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, version_proc_show, NULL); +} + +static const struct file_operations version_proc_fops = { + .open = version_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init proc_version_init(void) +{ + proc_create("version", 0, NULL, &version_proc_fops); + return 0; +} +module_init(proc_version_init); diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index cd9ca67f841..03ec5950490 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -32,7 +32,7 @@ static size_t elfcorebuf_sz; /* Total size of vmcore file. */ static u64 vmcore_size; -struct proc_dir_entry *proc_vmcore = NULL; +static struct proc_dir_entry *proc_vmcore = NULL; /* Reads a page from the oldmem device from given offset. */ static ssize_t read_from_oldmem(char *buf, size_t count, @@ -162,7 +162,7 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer, return acc; } -const struct file_operations proc_vmcore_operations = { +static const struct file_operations proc_vmcore_operations = { .read = read_vmcore, }; @@ -652,7 +652,7 @@ static int __init vmcore_init(void) return rc; } - /* Initialize /proc/vmcore size if proc is already up. */ + proc_vmcore = proc_create("vmcore", S_IRUSR, NULL, &proc_vmcore_operations); if (proc_vmcore) proc_vmcore->size = vmcore_size; return 0; diff --git a/fs/read_write.c b/fs/read_write.c index 9ba495d5a29..969a6d9c020 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -31,39 +31,61 @@ const struct file_operations generic_ro_fops = { EXPORT_SYMBOL(generic_ro_fops); +/** + * generic_file_llseek_unlocked - lockless generic llseek implementation + * @file: file structure to seek on + * @offset: file offset to seek to + * @origin: type of seek + * + * Updates the file offset to the value specified by @offset and @origin. + * Locking must be provided by the caller. + */ loff_t generic_file_llseek_unlocked(struct file *file, loff_t offset, int origin) { - loff_t retval; struct inode *inode = file->f_mapping->host; switch (origin) { - case SEEK_END: - offset += inode->i_size; - break; - case SEEK_CUR: - offset += file->f_pos; + case SEEK_END: + offset += inode->i_size; + break; + case SEEK_CUR: + offset += file->f_pos; + break; } - retval = -EINVAL; - if (offset>=0 && offset<=inode->i_sb->s_maxbytes) { - /* Special lock needed here? */ - if (offset != file->f_pos) { - file->f_pos = offset; - file->f_version = 0; - } - retval = offset; + + if (offset < 0 || offset > inode->i_sb->s_maxbytes) + return -EINVAL; + + /* Special lock needed here? */ + if (offset != file->f_pos) { + file->f_pos = offset; + file->f_version = 0; } - return retval; + + return offset; } EXPORT_SYMBOL(generic_file_llseek_unlocked); +/** + * generic_file_llseek - generic llseek implementation for regular files + * @file: file structure to seek on + * @offset: file offset to seek to + * @origin: type of seek + * + * This is a generic implemenation of ->llseek useable for all normal local + * filesystems. It just updates the file offset to the value specified by + * @offset and @origin under i_mutex. + */ loff_t generic_file_llseek(struct file *file, loff_t offset, int origin) { - loff_t n; + loff_t rval; + mutex_lock(&file->f_dentry->d_inode->i_mutex); - n = generic_file_llseek_unlocked(file, offset, origin); + rval = generic_file_llseek_unlocked(file, offset, origin); mutex_unlock(&file->f_dentry->d_inode->i_mutex); - return n; + + return rval; } EXPORT_SYMBOL(generic_file_llseek); diff --git a/fs/readdir.c b/fs/readdir.c index 93a7559bbfd..b318d9b5af2 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -117,7 +117,7 @@ asmlinkage long old_readdir(unsigned int fd, struct old_linux_dirent __user * di buf.dirent = dirent; error = vfs_readdir(file, fillonedir, &buf); - if (error >= 0) + if (buf.result) error = buf.result; fput(file); @@ -209,9 +209,8 @@ asmlinkage long sys_getdents(unsigned int fd, struct linux_dirent __user * diren buf.error = 0; error = vfs_readdir(file, filldir, &buf); - if (error < 0) - goto out_putf; - error = buf.error; + if (error >= 0) + error = buf.error; lastdirent = buf.previous; if (lastdirent) { if (put_user(file->f_pos, &lastdirent->d_off)) @@ -219,8 +218,6 @@ asmlinkage long sys_getdents(unsigned int fd, struct linux_dirent __user * diren else error = count - buf.count; } - -out_putf: fput(file); out: return error; @@ -293,19 +290,16 @@ asmlinkage long sys_getdents64(unsigned int fd, struct linux_dirent64 __user * d buf.error = 0; error = vfs_readdir(file, filldir64, &buf); - if (error < 0) - goto out_putf; - error = buf.error; + if (error >= 0) + error = buf.error; lastdirent = buf.previous; if (lastdirent) { typeof(lastdirent->d_off) d_off = file->f_pos; - error = -EFAULT; if (__put_user(d_off, &lastdirent->d_off)) - goto out_putf; - error = count - buf.count; + error = -EFAULT; + else + error = count - buf.count; } - -out_putf: fput(file); out: return error; diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index a804903d31d..33408417038 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -296,6 +296,7 @@ const struct file_operations reiserfs_file_operations = { .aio_write = generic_file_aio_write, .splice_read = generic_file_splice_read, .splice_write = generic_file_splice_write, + .llseek = generic_file_llseek, }; const struct inode_operations reiserfs_file_inode_operations = { diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 5699171212a..6c4c2c69449 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -1522,7 +1522,6 @@ static struct dentry *reiserfs_get_dentry(struct super_block *sb, { struct cpu_key key; - struct dentry *result; struct inode *inode; key.on_disk_key.k_objectid = objectid; @@ -1535,16 +1534,8 @@ static struct dentry *reiserfs_get_dentry(struct super_block *sb, inode = NULL; } reiserfs_write_unlock(sb); - if (!inode) - inode = ERR_PTR(-ESTALE); - if (IS_ERR(inode)) - return ERR_CAST(inode); - result = d_alloc_anon(inode); - if (!result) { - iput(inode); - return ERR_PTR(-ENOMEM); - } - return result; + + return d_obtain_alias(inode); } struct dentry *reiserfs_fh_to_dentry(struct super_block *sb, struct fid *fid, diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index c21df71943a..9643c3bbeb3 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -2575,7 +2575,7 @@ static int release_journal_dev(struct super_block *super, if (journal->j_dev_bd != NULL) { if (journal->j_dev_bd->bd_dev != super->s_dev) bd_release(journal->j_dev_bd); - result = blkdev_put(journal->j_dev_bd); + result = blkdev_put(journal->j_dev_bd, journal->j_dev_mode); journal->j_dev_bd = NULL; } @@ -2593,7 +2593,7 @@ static int journal_init_dev(struct super_block *super, { int result; dev_t jdev; - int blkdev_mode = FMODE_READ | FMODE_WRITE; + fmode_t blkdev_mode = FMODE_READ | FMODE_WRITE; char b[BDEVNAME_SIZE]; result = 0; @@ -2608,6 +2608,7 @@ static int journal_init_dev(struct super_block *super, /* there is no "jdev" option and journal is on separate device */ if ((!jdev_name || !jdev_name[0])) { journal->j_dev_bd = open_by_devnum(jdev, blkdev_mode); + journal->j_dev_mode = blkdev_mode; if (IS_ERR(journal->j_dev_bd)) { result = PTR_ERR(journal->j_dev_bd); journal->j_dev_bd = NULL; @@ -2618,7 +2619,7 @@ static int journal_init_dev(struct super_block *super, } else if (jdev != super->s_dev) { result = bd_claim(journal->j_dev_bd, journal); if (result) { - blkdev_put(journal->j_dev_bd); + blkdev_put(journal->j_dev_bd, blkdev_mode); return result; } @@ -2628,7 +2629,9 @@ static int journal_init_dev(struct super_block *super, return 0; } - journal->j_dev_bd = open_bdev_excl(jdev_name, 0, journal); + journal->j_dev_mode = blkdev_mode; + journal->j_dev_bd = open_bdev_exclusive(jdev_name, + blkdev_mode, journal); if (IS_ERR(journal->j_dev_bd)) { result = PTR_ERR(journal->j_dev_bd); journal->j_dev_bd = NULL; diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index c1add28dd45..f89ebb943f3 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -383,7 +383,6 @@ struct dentry *reiserfs_get_parent(struct dentry *child) struct inode *inode = NULL; struct reiserfs_dir_entry de; INITIALIZE_PATH(path_to_entry); - struct dentry *parent; struct inode *dir = child->d_inode; if (dir->i_nlink == 0) { @@ -401,15 +400,7 @@ struct dentry *reiserfs_get_parent(struct dentry *child) inode = reiserfs_iget(dir->i_sb, (struct cpu_key *)&(de.de_dir_id)); reiserfs_write_unlock(dir->i_sb); - if (!inode || IS_ERR(inode)) { - return ERR_PTR(-EACCES); - } - parent = d_alloc_anon(inode); - if (!parent) { - iput(inode); - parent = ERR_PTR(-ENOMEM); - } - return parent; + return d_obtain_alias(inode); } /* add entry to the directory (entry can be hidden). diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index d318c7e663f..663a91f5dce 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -2058,10 +2058,10 @@ static int reiserfs_quota_on_mount(struct super_block *sb, int type) * Standard function to be called on quota_on */ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id, - char *path, int remount) + char *name, int remount) { int err; - struct nameidata nd; + struct path path; struct inode *inode; struct reiserfs_transaction_handle th; @@ -2069,16 +2069,16 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id, return -EINVAL; /* No more checks needed? Path and format_id are bogus anyway... */ if (remount) - return vfs_quota_on(sb, type, format_id, path, 1); - err = path_lookup(path, LOOKUP_FOLLOW, &nd); + return vfs_quota_on(sb, type, format_id, name, 1); + err = kern_path(name, LOOKUP_FOLLOW, &path); if (err) return err; /* Quotafile not on the same filesystem? */ - if (nd.path.mnt->mnt_sb != sb) { + if (path.mnt->mnt_sb != sb) { err = -EXDEV; goto out; } - inode = nd.path.dentry->d_inode; + inode = path.dentry->d_inode; /* We must not pack tails for quota files on reiserfs for quota IO to work */ if (!(REISERFS_I(inode)->i_flags & i_nopack_mask)) { err = reiserfs_unpack(inode, NULL); @@ -2094,7 +2094,7 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id, /* Journaling quota? */ if (REISERFS_SB(sb)->s_qf_names[type]) { /* Quotafile not of fs root? */ - if (nd.path.dentry->d_parent->d_inode != sb->s_root->d_inode) + if (path.dentry->d_parent != sb->s_root) reiserfs_warning(sb, "reiserfs: Quota file not on filesystem root. " "Journalled quota will not work."); @@ -2113,9 +2113,9 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id, if (err) goto out; } - err = vfs_quota_on_path(sb, type, format_id, &nd.path); + err = vfs_quota_on_path(sb, type, format_id, &path); out: - path_put(&nd.path); + path_put(&path); return err; } diff --git a/fs/select.c b/fs/select.c index da0e88201c3..448e4400128 100644 --- a/fs/select.c +++ b/fs/select.c @@ -24,9 +24,64 @@ #include <linux/fdtable.h> #include <linux/fs.h> #include <linux/rcupdate.h> +#include <linux/hrtimer.h> #include <asm/uaccess.h> + +/* + * Estimate expected accuracy in ns from a timeval. + * + * After quite a bit of churning around, we've settled on + * a simple thing of taking 0.1% of the timeout as the + * slack, with a cap of 100 msec. + * "nice" tasks get a 0.5% slack instead. + * + * Consider this comment an open invitation to come up with even + * better solutions.. + */ + +static long __estimate_accuracy(struct timespec *tv) +{ + long slack; + int divfactor = 1000; + + if (task_nice(current) > 0) + divfactor = divfactor / 5; + + slack = tv->tv_nsec / divfactor; + slack += tv->tv_sec * (NSEC_PER_SEC/divfactor); + + if (slack > 100 * NSEC_PER_MSEC) + slack = 100 * NSEC_PER_MSEC; + + if (slack < 0) + slack = 0; + return slack; +} + +static long estimate_accuracy(struct timespec *tv) +{ + unsigned long ret; + struct timespec now; + + /* + * Realtime tasks get a slack of 0 for obvious reasons. + */ + + if (rt_task(current)) + return 0; + + ktime_get_ts(&now); + now = timespec_sub(*tv, now); + ret = __estimate_accuracy(&now); + if (ret < current->timer_slack_ns) + return current->timer_slack_ns; + return ret; +} + + + struct poll_table_page { struct poll_table_page * next; struct poll_table_entry * entry; @@ -130,6 +185,79 @@ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address, add_wait_queue(wait_address, &entry->wait); } +/** + * poll_select_set_timeout - helper function to setup the timeout value + * @to: pointer to timespec variable for the final timeout + * @sec: seconds (from user space) + * @nsec: nanoseconds (from user space) + * + * Note, we do not use a timespec for the user space value here, That + * way we can use the function for timeval and compat interfaces as well. + * + * Returns -EINVAL if sec/nsec are not normalized. Otherwise 0. + */ +int poll_select_set_timeout(struct timespec *to, long sec, long nsec) +{ + struct timespec ts = {.tv_sec = sec, .tv_nsec = nsec}; + + if (!timespec_valid(&ts)) + return -EINVAL; + + /* Optimize for the zero timeout value here */ + if (!sec && !nsec) { + to->tv_sec = to->tv_nsec = 0; + } else { + ktime_get_ts(to); + *to = timespec_add_safe(*to, ts); + } + return 0; +} + +static int poll_select_copy_remaining(struct timespec *end_time, void __user *p, + int timeval, int ret) +{ + struct timespec rts; + struct timeval rtv; + + if (!p) + return ret; + + if (current->personality & STICKY_TIMEOUTS) + goto sticky; + + /* No update for zero timeout */ + if (!end_time->tv_sec && !end_time->tv_nsec) + return ret; + + ktime_get_ts(&rts); + rts = timespec_sub(*end_time, rts); + if (rts.tv_sec < 0) + rts.tv_sec = rts.tv_nsec = 0; + + if (timeval) { + rtv.tv_sec = rts.tv_sec; + rtv.tv_usec = rts.tv_nsec / NSEC_PER_USEC; + + if (!copy_to_user(p, &rtv, sizeof(rtv))) + return ret; + + } else if (!copy_to_user(p, &rts, sizeof(rts))) + return ret; + + /* + * If an application puts its timeval in read-only memory, we + * don't want the Linux-specific update to the timeval to + * cause a fault after the select has completed + * successfully. However, because we're not updating the + * timeval, we can't restart the system call. + */ + +sticky: + if (ret == -ERESTARTNOHAND) + ret = -EINTR; + return ret; +} + #define FDS_IN(fds, n) (fds->in + n) #define FDS_OUT(fds, n) (fds->out + n) #define FDS_EX(fds, n) (fds->ex + n) @@ -182,11 +310,13 @@ get_max: #define POLLOUT_SET (POLLWRBAND | POLLWRNORM | POLLOUT | POLLERR) #define POLLEX_SET (POLLPRI) -int do_select(int n, fd_set_bits *fds, s64 *timeout) +int do_select(int n, fd_set_bits *fds, struct timespec *end_time) { + ktime_t expire, *to = NULL; struct poll_wqueues table; poll_table *wait; - int retval, i; + int retval, i, timed_out = 0; + unsigned long slack = 0; rcu_read_lock(); retval = max_select_fd(n, fds); @@ -198,12 +328,17 @@ int do_select(int n, fd_set_bits *fds, s64 *timeout) poll_initwait(&table); wait = &table.pt; - if (!*timeout) + if (end_time && !end_time->tv_sec && !end_time->tv_nsec) { wait = NULL; + timed_out = 1; + } + + if (end_time && !timed_out) + slack = estimate_accuracy(end_time); + retval = 0; for (;;) { unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp; - long __timeout; set_current_state(TASK_INTERRUPTIBLE); @@ -259,27 +394,25 @@ int do_select(int n, fd_set_bits *fds, s64 *timeout) cond_resched(); } wait = NULL; - if (retval || !*timeout || signal_pending(current)) + if (retval || timed_out || signal_pending(current)) break; if (table.error) { retval = table.error; break; } - if (*timeout < 0) { - /* Wait indefinitely */ - __timeout = MAX_SCHEDULE_TIMEOUT; - } else if (unlikely(*timeout >= (s64)MAX_SCHEDULE_TIMEOUT - 1)) { - /* Wait for longer than MAX_SCHEDULE_TIMEOUT. Do it in a loop */ - __timeout = MAX_SCHEDULE_TIMEOUT - 1; - *timeout -= __timeout; - } else { - __timeout = *timeout; - *timeout = 0; + /* + * If this is the first loop and we have a timeout + * given, then we convert to ktime_t and set the to + * pointer to the expiry value. + */ + if (end_time && !to) { + expire = timespec_to_ktime(*end_time); + to = &expire; } - __timeout = schedule_timeout(__timeout); - if (*timeout >= 0) - *timeout += __timeout; + + if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) + timed_out = 1; } __set_current_state(TASK_RUNNING); @@ -300,7 +433,7 @@ int do_select(int n, fd_set_bits *fds, s64 *timeout) ((unsigned long) (MAX_SCHEDULE_TIMEOUT / HZ)-1) int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp, - fd_set __user *exp, s64 *timeout) + fd_set __user *exp, struct timespec *end_time) { fd_set_bits fds; void *bits; @@ -351,7 +484,7 @@ int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp, zero_fd_set(n, fds.res_out); zero_fd_set(n, fds.res_ex); - ret = do_select(n, &fds, timeout); + ret = do_select(n, &fds, end_time); if (ret < 0) goto out; @@ -377,7 +510,7 @@ out_nofds: asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp) { - s64 timeout = -1; + struct timespec end_time, *to = NULL; struct timeval tv; int ret; @@ -385,43 +518,14 @@ asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp, if (copy_from_user(&tv, tvp, sizeof(tv))) return -EFAULT; - if (tv.tv_sec < 0 || tv.tv_usec < 0) + to = &end_time; + if (poll_select_set_timeout(to, tv.tv_sec, + tv.tv_usec * NSEC_PER_USEC)) return -EINVAL; - - /* Cast to u64 to make GCC stop complaining */ - if ((u64)tv.tv_sec >= (u64)MAX_INT64_SECONDS) - timeout = -1; /* infinite */ - else { - timeout = DIV_ROUND_UP(tv.tv_usec, USEC_PER_SEC/HZ); - timeout += tv.tv_sec * HZ; - } } - ret = core_sys_select(n, inp, outp, exp, &timeout); - - if (tvp) { - struct timeval rtv; - - if (current->personality & STICKY_TIMEOUTS) - goto sticky; - rtv.tv_usec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)); - rtv.tv_sec = timeout; - if (timeval_compare(&rtv, &tv) >= 0) - rtv = tv; - if (copy_to_user(tvp, &rtv, sizeof(rtv))) { -sticky: - /* - * If an application puts its timeval in read-only - * memory, we don't want the Linux-specific update to - * the timeval to cause a fault after the select has - * completed successfully. However, because we're not - * updating the timeval, we can't restart the system - * call. - */ - if (ret == -ERESTARTNOHAND) - ret = -EINTR; - } - } + ret = core_sys_select(n, inp, outp, exp, to); + ret = poll_select_copy_remaining(&end_time, tvp, 1, ret); return ret; } @@ -431,25 +535,17 @@ asmlinkage long sys_pselect7(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timespec __user *tsp, const sigset_t __user *sigmask, size_t sigsetsize) { - s64 timeout = MAX_SCHEDULE_TIMEOUT; sigset_t ksigmask, sigsaved; - struct timespec ts; + struct timespec ts, end_time, *to = NULL; int ret; if (tsp) { if (copy_from_user(&ts, tsp, sizeof(ts))) return -EFAULT; - if (ts.tv_sec < 0 || ts.tv_nsec < 0) + to = &end_time; + if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; - - /* Cast to u64 to make GCC stop complaining */ - if ((u64)ts.tv_sec >= (u64)MAX_INT64_SECONDS) - timeout = -1; /* infinite */ - else { - timeout = DIV_ROUND_UP(ts.tv_nsec, NSEC_PER_SEC/HZ); - timeout += ts.tv_sec * HZ; - } } if (sigmask) { @@ -463,32 +559,8 @@ asmlinkage long sys_pselect7(int n, fd_set __user *inp, fd_set __user *outp, sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); } - ret = core_sys_select(n, inp, outp, exp, &timeout); - - if (tsp) { - struct timespec rts; - - if (current->personality & STICKY_TIMEOUTS) - goto sticky; - rts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) * - 1000; - rts.tv_sec = timeout; - if (timespec_compare(&rts, &ts) >= 0) - rts = ts; - if (copy_to_user(tsp, &rts, sizeof(rts))) { -sticky: - /* - * If an application puts its timeval in read-only - * memory, we don't want the Linux-specific update to - * the timeval to cause a fault after the select has - * completed successfully. However, because we're not - * updating the timeval, we can't restart the system - * call. - */ - if (ret == -ERESTARTNOHAND) - ret = -EINTR; - } - } + ret = core_sys_select(n, inp, outp, exp, &end_time); + ret = poll_select_copy_remaining(&end_time, tsp, 0, ret); if (ret == -ERESTARTNOHAND) { /* @@ -574,18 +646,24 @@ static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait) } static int do_poll(unsigned int nfds, struct poll_list *list, - struct poll_wqueues *wait, s64 *timeout) + struct poll_wqueues *wait, struct timespec *end_time) { - int count = 0; poll_table* pt = &wait->pt; + ktime_t expire, *to = NULL; + int timed_out = 0, count = 0; + unsigned long slack = 0; /* Optimise the no-wait case */ - if (!(*timeout)) + if (end_time && !end_time->tv_sec && !end_time->tv_nsec) { pt = NULL; + timed_out = 1; + } + + if (end_time && !timed_out) + slack = estimate_accuracy(end_time); for (;;) { struct poll_list *walk; - long __timeout; set_current_state(TASK_INTERRUPTIBLE); for (walk = list; walk != NULL; walk = walk->next) { @@ -617,27 +695,21 @@ static int do_poll(unsigned int nfds, struct poll_list *list, if (signal_pending(current)) count = -EINTR; } - if (count || !*timeout) + if (count || timed_out) break; - if (*timeout < 0) { - /* Wait indefinitely */ - __timeout = MAX_SCHEDULE_TIMEOUT; - } else if (unlikely(*timeout >= (s64)MAX_SCHEDULE_TIMEOUT-1)) { - /* - * Wait for longer than MAX_SCHEDULE_TIMEOUT. Do it in - * a loop - */ - __timeout = MAX_SCHEDULE_TIMEOUT - 1; - *timeout -= __timeout; - } else { - __timeout = *timeout; - *timeout = 0; + /* + * If this is the first loop and we have a timeout + * given, then we convert to ktime_t and set the to + * pointer to the expiry value. + */ + if (end_time && !to) { + expire = timespec_to_ktime(*end_time); + to = &expire; } - __timeout = schedule_timeout(__timeout); - if (*timeout >= 0) - *timeout += __timeout; + if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) + timed_out = 1; } __set_current_state(TASK_RUNNING); return count; @@ -646,7 +718,8 @@ static int do_poll(unsigned int nfds, struct poll_list *list, #define N_STACK_PPS ((sizeof(stack_pps) - sizeof(struct poll_list)) / \ sizeof(struct pollfd)) -int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, s64 *timeout) +int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, + struct timespec *end_time) { struct poll_wqueues table; int err = -EFAULT, fdcount, len, size; @@ -686,7 +759,7 @@ int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, s64 *timeout) } poll_initwait(&table); - fdcount = do_poll(nfds, head, &table, timeout); + fdcount = do_poll(nfds, head, &table, end_time); poll_freewait(&table); for (walk = head; walk; walk = walk->next) { @@ -712,16 +785,21 @@ out_fds: static long do_restart_poll(struct restart_block *restart_block) { - struct pollfd __user *ufds = (struct pollfd __user*)restart_block->arg0; - int nfds = restart_block->arg1; - s64 timeout = ((s64)restart_block->arg3<<32) | (s64)restart_block->arg2; + struct pollfd __user *ufds = restart_block->poll.ufds; + int nfds = restart_block->poll.nfds; + struct timespec *to = NULL, end_time; int ret; - ret = do_sys_poll(ufds, nfds, &timeout); + if (restart_block->poll.has_timeout) { + end_time.tv_sec = restart_block->poll.tv_sec; + end_time.tv_nsec = restart_block->poll.tv_nsec; + to = &end_time; + } + + ret = do_sys_poll(ufds, nfds, to); + if (ret == -EINTR) { restart_block->fn = do_restart_poll; - restart_block->arg2 = timeout & 0xFFFFFFFF; - restart_block->arg3 = (u64)timeout >> 32; ret = -ERESTART_RESTARTBLOCK; } return ret; @@ -730,31 +808,32 @@ static long do_restart_poll(struct restart_block *restart_block) asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds, long timeout_msecs) { - s64 timeout_jiffies; + struct timespec end_time, *to = NULL; int ret; - if (timeout_msecs > 0) { -#if HZ > 1000 - /* We can only overflow if HZ > 1000 */ - if (timeout_msecs / 1000 > (s64)0x7fffffffffffffffULL / (s64)HZ) - timeout_jiffies = -1; - else -#endif - timeout_jiffies = msecs_to_jiffies(timeout_msecs) + 1; - } else { - /* Infinite (< 0) or no (0) timeout */ - timeout_jiffies = timeout_msecs; + if (timeout_msecs >= 0) { + to = &end_time; + poll_select_set_timeout(to, timeout_msecs / MSEC_PER_SEC, + NSEC_PER_MSEC * (timeout_msecs % MSEC_PER_SEC)); } - ret = do_sys_poll(ufds, nfds, &timeout_jiffies); + ret = do_sys_poll(ufds, nfds, to); + if (ret == -EINTR) { struct restart_block *restart_block; + restart_block = ¤t_thread_info()->restart_block; restart_block->fn = do_restart_poll; - restart_block->arg0 = (unsigned long)ufds; - restart_block->arg1 = nfds; - restart_block->arg2 = timeout_jiffies & 0xFFFFFFFF; - restart_block->arg3 = (u64)timeout_jiffies >> 32; + restart_block->poll.ufds = ufds; + restart_block->poll.nfds = nfds; + + if (timeout_msecs >= 0) { + restart_block->poll.tv_sec = end_time.tv_sec; + restart_block->poll.tv_nsec = end_time.tv_nsec; + restart_block->poll.has_timeout = 1; + } else + restart_block->poll.has_timeout = 0; + ret = -ERESTART_RESTARTBLOCK; } return ret; @@ -766,21 +845,16 @@ asmlinkage long sys_ppoll(struct pollfd __user *ufds, unsigned int nfds, size_t sigsetsize) { sigset_t ksigmask, sigsaved; - struct timespec ts; - s64 timeout = -1; + struct timespec ts, end_time, *to = NULL; int ret; if (tsp) { if (copy_from_user(&ts, tsp, sizeof(ts))) return -EFAULT; - /* Cast to u64 to make GCC stop complaining */ - if ((u64)ts.tv_sec >= (u64)MAX_INT64_SECONDS) - timeout = -1; /* infinite */ - else { - timeout = DIV_ROUND_UP(ts.tv_nsec, NSEC_PER_SEC/HZ); - timeout += ts.tv_sec * HZ; - } + to = &end_time; + if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) + return -EINVAL; } if (sigmask) { @@ -794,7 +868,7 @@ asmlinkage long sys_ppoll(struct pollfd __user *ufds, unsigned int nfds, sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); } - ret = do_sys_poll(ufds, nfds, &timeout); + ret = do_sys_poll(ufds, nfds, to); /* We can restart this syscall, usually */ if (ret == -EINTR) { @@ -812,31 +886,7 @@ asmlinkage long sys_ppoll(struct pollfd __user *ufds, unsigned int nfds, } else if (sigmask) sigprocmask(SIG_SETMASK, &sigsaved, NULL); - if (tsp && timeout >= 0) { - struct timespec rts; - - if (current->personality & STICKY_TIMEOUTS) - goto sticky; - /* Yes, we know it's actually an s64, but it's also positive. */ - rts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) * - 1000; - rts.tv_sec = timeout; - if (timespec_compare(&rts, &ts) >= 0) - rts = ts; - if (copy_to_user(tsp, &rts, sizeof(rts))) { - sticky: - /* - * If an application puts its timeval in read-only - * memory, we don't want the Linux-specific update to - * the timeval to cause a fault after the select has - * completed successfully. However, because we're not - * updating the timeval, we can't restart the system - * call. - */ - if (ret == -ERESTARTNOHAND && timeout >= 0) - ret = -EINTR; - } - } + ret = poll_select_copy_remaining(&end_time, tsp, 0, ret); return ret; } diff --git a/fs/super.c b/fs/super.c index e931ae9511f..400a7608f15 100644 --- a/fs/super.c +++ b/fs/super.c @@ -682,7 +682,7 @@ void emergency_remount(void) * filesystems which don't use real block-devices. -- jrs */ -static struct idr unnamed_dev_idr; +static DEFINE_IDA(unnamed_dev_ida); static DEFINE_SPINLOCK(unnamed_dev_lock);/* protects the above */ int set_anon_super(struct super_block *s, void *data) @@ -691,10 +691,10 @@ int set_anon_super(struct super_block *s, void *data) int error; retry: - if (idr_pre_get(&unnamed_dev_idr, GFP_ATOMIC) == 0) + if (ida_pre_get(&unnamed_dev_ida, GFP_ATOMIC) == 0) return -ENOMEM; spin_lock(&unnamed_dev_lock); - error = idr_get_new(&unnamed_dev_idr, NULL, &dev); + error = ida_get_new(&unnamed_dev_ida, &dev); spin_unlock(&unnamed_dev_lock); if (error == -EAGAIN) /* We raced and lost with another CPU. */ @@ -704,7 +704,7 @@ int set_anon_super(struct super_block *s, void *data) if ((dev & MAX_ID_MASK) == (1 << MINORBITS)) { spin_lock(&unnamed_dev_lock); - idr_remove(&unnamed_dev_idr, dev); + ida_remove(&unnamed_dev_ida, dev); spin_unlock(&unnamed_dev_lock); return -EMFILE; } @@ -720,17 +720,12 @@ void kill_anon_super(struct super_block *sb) generic_shutdown_super(sb); spin_lock(&unnamed_dev_lock); - idr_remove(&unnamed_dev_idr, slot); + ida_remove(&unnamed_dev_ida, slot); spin_unlock(&unnamed_dev_lock); } EXPORT_SYMBOL(kill_anon_super); -void __init unnamed_dev_init(void) -{ - idr_init(&unnamed_dev_idr); -} - void kill_litter_super(struct super_block *sb) { if (sb->s_root) @@ -760,9 +755,13 @@ int get_sb_bdev(struct file_system_type *fs_type, { struct block_device *bdev; struct super_block *s; + fmode_t mode = FMODE_READ; int error = 0; - bdev = open_bdev_excl(dev_name, flags, fs_type); + if (!(flags & MS_RDONLY)) + mode |= FMODE_WRITE; + + bdev = open_bdev_exclusive(dev_name, mode, fs_type); if (IS_ERR(bdev)) return PTR_ERR(bdev); @@ -785,11 +784,12 @@ int get_sb_bdev(struct file_system_type *fs_type, goto error_bdev; } - close_bdev_excl(bdev); + close_bdev_exclusive(bdev, mode); } else { char b[BDEVNAME_SIZE]; s->s_flags = flags; + s->s_mode = mode; strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id)); sb_set_blocksize(s, block_size(bdev)); error = fill_super(s, data, flags & MS_SILENT ? 1 : 0); @@ -807,7 +807,7 @@ int get_sb_bdev(struct file_system_type *fs_type, error_s: error = PTR_ERR(s); error_bdev: - close_bdev_excl(bdev); + close_bdev_exclusive(bdev, mode); error: return error; } @@ -817,10 +817,11 @@ EXPORT_SYMBOL(get_sb_bdev); void kill_block_super(struct super_block *sb) { struct block_device *bdev = sb->s_bdev; + fmode_t mode = sb->s_mode; generic_shutdown_super(sb); sync_blockdev(bdev); - close_bdev_excl(bdev); + close_bdev_exclusive(bdev, mode); } EXPORT_SYMBOL(kill_block_super); diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index 3a05a596e3b..82d3b79d0e0 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -983,4 +983,5 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir) const struct file_operations sysfs_dir_operations = { .read = generic_read_dir, .readdir = sysfs_readdir, + .llseek = generic_file_llseek, }; diff --git a/fs/timerfd.c b/fs/timerfd.c index c502c60e4f5..0862f0e49d0 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -52,11 +52,9 @@ static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr) static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx) { - ktime_t now, remaining; - - now = ctx->tmr.base->get_time(); - remaining = ktime_sub(ctx->tmr.expires, now); + ktime_t remaining; + remaining = hrtimer_expires_remaining(&ctx->tmr); return remaining.tv64 < 0 ? ktime_set(0, 0): remaining; } @@ -74,7 +72,7 @@ static void timerfd_setup(struct timerfd_ctx *ctx, int flags, ctx->ticks = 0; ctx->tintv = timespec_to_ktime(ktmr->it_interval); hrtimer_init(&ctx->tmr, ctx->clockid, htmode); - ctx->tmr.expires = texp; + hrtimer_set_expires(&ctx->tmr, texp); ctx->tmr.function = timerfd_tmrproc; if (texp.tv64 != 0) hrtimer_start(&ctx->tmr, texp, htmode); diff --git a/fs/udf/namei.c b/fs/udf/namei.c index d3231947db1..082409cd4b8 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -142,7 +142,7 @@ int udf_write_fi(struct inode *inode, struct fileIdentDesc *cfi, } static struct fileIdentDesc *udf_find_entry(struct inode *dir, - struct dentry *dentry, + struct qstr *child, struct udf_fileident_bh *fibh, struct fileIdentDesc *cfi) { @@ -159,8 +159,8 @@ static struct fileIdentDesc *udf_find_entry(struct inode *dir, sector_t offset; struct extent_position epos = {}; struct udf_inode_info *dinfo = UDF_I(dir); - int isdotdot = dentry->d_name.len == 2 && - dentry->d_name.name[0] == '.' && dentry->d_name.name[1] == '.'; + int isdotdot = child->len == 2 && + child->name[0] == '.' && child->name[1] == '.'; size = udf_ext0_offset(dir) + dir->i_size; f_pos = udf_ext0_offset(dir); @@ -238,8 +238,7 @@ static struct fileIdentDesc *udf_find_entry(struct inode *dir, continue; flen = udf_get_filename(dir->i_sb, nameptr, fname, lfi); - if (flen && udf_match(flen, fname, dentry->d_name.len, - dentry->d_name.name)) + if (flen && udf_match(flen, fname, child->len, child->name)) goto out_ok; } @@ -283,7 +282,7 @@ static struct dentry *udf_lookup(struct inode *dir, struct dentry *dentry, } else #endif /* UDF_RECOVERY */ - if (udf_find_entry(dir, dentry, &fibh, &cfi)) { + if (udf_find_entry(dir, &dentry->d_name, &fibh, &cfi)) { if (fibh.sbh != fibh.ebh) brelse(fibh.ebh); brelse(fibh.sbh); @@ -783,7 +782,7 @@ static int udf_rmdir(struct inode *dir, struct dentry *dentry) retval = -ENOENT; lock_kernel(); - fi = udf_find_entry(dir, dentry, &fibh, &cfi); + fi = udf_find_entry(dir, &dentry->d_name, &fibh, &cfi); if (!fi) goto out; @@ -829,7 +828,7 @@ static int udf_unlink(struct inode *dir, struct dentry *dentry) retval = -ENOENT; lock_kernel(); - fi = udf_find_entry(dir, dentry, &fibh, &cfi); + fi = udf_find_entry(dir, &dentry->d_name, &fibh, &cfi); if (!fi) goto out; @@ -1113,7 +1112,7 @@ static int udf_rename(struct inode *old_dir, struct dentry *old_dentry, struct udf_inode_info *old_iinfo = UDF_I(old_inode); lock_kernel(); - ofi = udf_find_entry(old_dir, old_dentry, &ofibh, &ocfi); + ofi = udf_find_entry(old_dir, &old_dentry->d_name, &ofibh, &ocfi); if (ofi) { if (ofibh.sbh != ofibh.ebh) brelse(ofibh.ebh); @@ -1124,7 +1123,7 @@ static int udf_rename(struct inode *old_dir, struct dentry *old_dentry, != old_inode->i_ino) goto end_rename; - nfi = udf_find_entry(new_dir, new_dentry, &nfibh, &ncfi); + nfi = udf_find_entry(new_dir, &new_dentry->d_name, &nfibh, &ncfi); if (nfi) { if (!new_inode) { if (nfibh.sbh != nfibh.ebh) @@ -1192,7 +1191,7 @@ static int udf_rename(struct inode *old_dir, struct dentry *old_dentry, udf_write_fi(new_dir, &ncfi, nfi, &nfibh, NULL, NULL); /* The old fid may have moved - find it again */ - ofi = udf_find_entry(old_dir, old_dentry, &ofibh, &ocfi); + ofi = udf_find_entry(old_dir, &old_dentry->d_name, &ofibh, &ocfi); udf_delete_entry(old_dir, ofi, &ofibh, &ocfi); if (new_inode) { @@ -1243,15 +1242,11 @@ end_rename: static struct dentry *udf_get_parent(struct dentry *child) { - struct dentry *parent; struct inode *inode = NULL; - struct dentry dotdot; + struct qstr dotdot = {.name = "..", .len = 2}; struct fileIdentDesc cfi; struct udf_fileident_bh fibh; - dotdot.d_name.name = ".."; - dotdot.d_name.len = 2; - lock_kernel(); if (!udf_find_entry(child->d_inode, &dotdot, &fibh, &cfi)) goto out_unlock; @@ -1266,13 +1261,7 @@ static struct dentry *udf_get_parent(struct dentry *child) goto out_unlock; unlock_kernel(); - parent = d_alloc_anon(inode); - if (!parent) { - iput(inode); - parent = ERR_PTR(-ENOMEM); - } - - return parent; + return d_obtain_alias(inode); out_unlock: unlock_kernel(); return ERR_PTR(-EACCES); @@ -1283,7 +1272,6 @@ static struct dentry *udf_nfs_get_inode(struct super_block *sb, u32 block, u16 partref, __u32 generation) { struct inode *inode; - struct dentry *result; kernel_lb_addr loc; if (block == 0) @@ -1300,12 +1288,7 @@ static struct dentry *udf_nfs_get_inode(struct super_block *sb, u32 block, iput(inode); return ERR_PTR(-ESTALE); } - result = d_alloc_anon(inode); - if (!result) { - iput(inode); - return ERR_PTR(-ENOMEM); - } - return result; + return d_obtain_alias(inode); } static struct dentry *udf_fh_to_dentry(struct super_block *sb, diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c index df0bef18742..dbbbc466876 100644 --- a/fs/ufs/dir.c +++ b/fs/ufs/dir.c @@ -667,4 +667,5 @@ const struct file_operations ufs_dir_operations = { .read = generic_read_dir, .readdir = ufs_readdir, .fsync = file_fsync, + .llseek = generic_file_llseek, }; diff --git a/fs/xfs/linux-2.6/xfs_export.c b/fs/xfs/linux-2.6/xfs_export.c index 24fd598af84..7f7abec25e1 100644 --- a/fs/xfs/linux-2.6/xfs_export.c +++ b/fs/xfs/linux-2.6/xfs_export.c @@ -148,7 +148,6 @@ xfs_fs_fh_to_dentry(struct super_block *sb, struct fid *fid, { struct xfs_fid64 *fid64 = (struct xfs_fid64 *)fid; struct inode *inode = NULL; - struct dentry *result; if (fh_len < xfs_fileid_length(fileid_type)) return NULL; @@ -164,16 +163,7 @@ xfs_fs_fh_to_dentry(struct super_block *sb, struct fid *fid, break; } - if (!inode) - return NULL; - if (IS_ERR(inode)) - return ERR_CAST(inode); - result = d_alloc_anon(inode); - if (!result) { - iput(inode); - return ERR_PTR(-ENOMEM); - } - return result; + return d_obtain_alias(inode); } STATIC struct dentry * @@ -182,7 +172,6 @@ xfs_fs_fh_to_parent(struct super_block *sb, struct fid *fid, { struct xfs_fid64 *fid64 = (struct xfs_fid64 *)fid; struct inode *inode = NULL; - struct dentry *result; switch (fileid_type) { case FILEID_INO32_GEN_PARENT: @@ -195,16 +184,7 @@ xfs_fs_fh_to_parent(struct super_block *sb, struct fid *fid, break; } - if (!inode) - return NULL; - if (IS_ERR(inode)) - return ERR_CAST(inode); - result = d_alloc_anon(inode); - if (!result) { - iput(inode); - return ERR_PTR(-ENOMEM); - } - return result; + return d_obtain_alias(inode); } STATIC struct dentry * @@ -213,18 +193,12 @@ xfs_fs_get_parent( { int error; struct xfs_inode *cip; - struct dentry *parent; error = xfs_lookup(XFS_I(child->d_inode), &xfs_name_dotdot, &cip, NULL); if (unlikely(error)) return ERR_PTR(-error); - parent = d_alloc_anon(VFS_I(cip)); - if (unlikely(!parent)) { - iput(VFS_I(cip)); - return ERR_PTR(-ENOMEM); - } - return parent; + return d_obtain_alias(VFS_I(cip)); } const struct export_operations xfs_export_operations = { diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c index 5311c1acdd4..3fee790f138 100644 --- a/fs/xfs/linux-2.6/xfs_file.c +++ b/fs/xfs/linux-2.6/xfs_file.c @@ -204,15 +204,6 @@ xfs_file_fsync( return -xfs_fsync(XFS_I(dentry->d_inode)); } -/* - * Unfortunately we can't just use the clean and simple readdir implementation - * below, because nfs might call back into ->lookup from the filldir callback - * and that will deadlock the low-level btree code. - * - * Hopefully we'll find a better workaround that allows to use the optimal - * version at least for local readdirs for 2.6.25. - */ -#if 0 STATIC int xfs_file_readdir( struct file *filp, @@ -244,125 +235,6 @@ xfs_file_readdir( return -error; return 0; } -#else - -struct hack_dirent { - u64 ino; - loff_t offset; - int namlen; - unsigned int d_type; - char name[]; -}; - -struct hack_callback { - char *dirent; - size_t len; - size_t used; -}; - -STATIC int -xfs_hack_filldir( - void *__buf, - const char *name, - int namlen, - loff_t offset, - u64 ino, - unsigned int d_type) -{ - struct hack_callback *buf = __buf; - struct hack_dirent *de = (struct hack_dirent *)(buf->dirent + buf->used); - unsigned int reclen; - - reclen = ALIGN(sizeof(struct hack_dirent) + namlen, sizeof(u64)); - if (buf->used + reclen > buf->len) - return -EINVAL; - - de->namlen = namlen; - de->offset = offset; - de->ino = ino; - de->d_type = d_type; - memcpy(de->name, name, namlen); - buf->used += reclen; - return 0; -} - -STATIC int -xfs_file_readdir( - struct file *filp, - void *dirent, - filldir_t filldir) -{ - struct inode *inode = filp->f_path.dentry->d_inode; - xfs_inode_t *ip = XFS_I(inode); - struct hack_callback buf; - struct hack_dirent *de; - int error; - loff_t size; - int eof = 0; - xfs_off_t start_offset, curr_offset, offset; - - /* - * Try fairly hard to get memory - */ - buf.len = PAGE_CACHE_SIZE; - do { - buf.dirent = kmalloc(buf.len, GFP_KERNEL); - if (buf.dirent) - break; - buf.len >>= 1; - } while (buf.len >= 1024); - - if (!buf.dirent) - return -ENOMEM; - - curr_offset = filp->f_pos; - if (curr_offset == 0x7fffffff) - offset = 0xffffffff; - else - offset = filp->f_pos; - - while (!eof) { - unsigned int reclen; - - start_offset = offset; - - buf.used = 0; - error = -xfs_readdir(ip, &buf, buf.len, &offset, - xfs_hack_filldir); - if (error || offset == start_offset) { - size = 0; - break; - } - - size = buf.used; - de = (struct hack_dirent *)buf.dirent; - while (size > 0) { - curr_offset = de->offset /* & 0x7fffffff */; - if (filldir(dirent, de->name, de->namlen, - curr_offset & 0x7fffffff, - de->ino, de->d_type)) { - goto done; - } - - reclen = ALIGN(sizeof(struct hack_dirent) + de->namlen, - sizeof(u64)); - size -= reclen; - de = (struct hack_dirent *)((char *)de + reclen); - } - } - - done: - if (!error) { - if (size == 0) - filp->f_pos = offset & 0x7fffffff; - else if (de) - filp->f_pos = curr_offset; - } - - kfree(buf.dirent); - return error; -} -#endif STATIC int xfs_file_mmap( diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c index 48799ba7e3e..d3438c72dca 100644 --- a/fs/xfs/linux-2.6/xfs_ioctl.c +++ b/fs/xfs/linux-2.6/xfs_ioctl.c @@ -311,11 +311,10 @@ xfs_open_by_handle( return new_fd; } - dentry = d_alloc_anon(inode); - if (dentry == NULL) { - iput(inode); + dentry = d_obtain_alias(inode); + if (IS_ERR(dentry)) { put_unused_fd(new_fd); - return -XFS_ERROR(ENOMEM); + return PTR_ERR(dentry); } /* Ensure umount returns EBUSY on umounts while this file is open. */ diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index e39013619b2..37ebe36056e 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -589,7 +589,7 @@ xfs_blkdev_get( { int error = 0; - *bdevp = open_bdev_excl(name, 0, mp); + *bdevp = open_bdev_exclusive(name, FMODE_READ|FMODE_WRITE, mp); if (IS_ERR(*bdevp)) { error = PTR_ERR(*bdevp); printk("XFS: Invalid device [%s], error=%d\n", name, error); @@ -603,7 +603,7 @@ xfs_blkdev_put( struct block_device *bdev) { if (bdev) - close_bdev_excl(bdev); + close_bdev_exclusive(bdev, FMODE_READ|FMODE_WRITE); } /* |