diff options
Diffstat (limited to '')
402 files changed, 13064 insertions, 5226 deletions
diff --git a/fs/autofs/Kconfig b/drivers/staging/autofs/Kconfig index 480e210c83ab..480e210c83ab 100644 --- a/fs/autofs/Kconfig +++ b/drivers/staging/autofs/Kconfig diff --git a/fs/autofs/Makefile b/drivers/staging/autofs/Makefile index 453a60f46d05..f48781c34df1 100644 --- a/fs/autofs/Makefile +++ b/drivers/staging/autofs/Makefile @@ -4,4 +4,4 @@ obj-$(CONFIG_AUTOFS_FS) += autofs.o -autofs-objs := dirhash.o init.o inode.o root.o symlink.o waitq.o +autofs-y := dirhash.o init.o inode.o root.o symlink.o waitq.o diff --git a/fs/autofs/autofs_i.h b/drivers/staging/autofs/autofs_i.h index 901a3e67ec45..647a14356e39 100644 --- a/fs/autofs/autofs_i.h +++ b/drivers/staging/autofs/autofs_i.h @@ -1,6 +1,6 @@ /* -*- linux-c -*- ------------------------------------------------------- * * - * linux/fs/autofs/autofs_i.h + * drivers/staging/autofs/autofs_i.h * * Copyright 1997-1998 Transmeta Corporation - All Rights Reserved * diff --git a/fs/autofs/dirhash.c b/drivers/staging/autofs/dirhash.c index e947915109e5..8f3e2b816129 100644 --- a/fs/autofs/dirhash.c +++ b/drivers/staging/autofs/dirhash.c @@ -1,6 +1,6 @@ /* -*- linux-c -*- --------------------------------------------------------- * * - * linux/fs/autofs/dirhash.c + * drivers/staging/autofs/dirhash.c * * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved * diff --git a/fs/autofs/init.c b/drivers/staging/autofs/init.c index cea5219b4f37..5e4b372ea663 100644 --- a/fs/autofs/init.c +++ b/drivers/staging/autofs/init.c @@ -1,6 +1,6 @@ /* -*- linux-c -*- --------------------------------------------------------- * * - * linux/fs/autofs/init.c + * drivers/staging/autofs/init.c * * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved * @@ -14,16 +14,16 @@ #include <linux/init.h> #include "autofs_i.h" -static int autofs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *autofs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_nodev(fs_type, flags, data, autofs_fill_super, mnt); + return mount_nodev(fs_type, flags, data, autofs_fill_super); } static struct file_system_type autofs_fs_type = { .owner = THIS_MODULE, .name = "autofs", - .get_sb = autofs_get_sb, + .mount = autofs_mount, .kill_sb = autofs_kill_sb, }; diff --git a/fs/autofs/inode.c b/drivers/staging/autofs/inode.c index e1734f2d6e26..74db190ae845 100644 --- a/fs/autofs/inode.c +++ b/drivers/staging/autofs/inode.c @@ -1,6 +1,6 @@ /* -*- linux-c -*- --------------------------------------------------------- * * - * linux/fs/autofs/inode.c + * drivers/staging/autofs/inode.c * * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved * diff --git a/fs/autofs/root.c b/drivers/staging/autofs/root.c index 0c4ca81aeaeb..0fdec4befd84 100644 --- a/fs/autofs/root.c +++ b/drivers/staging/autofs/root.c @@ -1,6 +1,6 @@ /* -*- linux-c -*- --------------------------------------------------------- * * - * linux/fs/autofs/root.c + * drivers/staging/autofs/root.c * * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved * diff --git a/fs/autofs/symlink.c b/drivers/staging/autofs/symlink.c index 7ce9cb2c9ce2..ff2c65cde753 100644 --- a/fs/autofs/symlink.c +++ b/drivers/staging/autofs/symlink.c @@ -1,6 +1,6 @@ /* -*- linux-c -*- --------------------------------------------------------- * * - * linux/fs/autofs/symlink.c + * drivers/staging/autofs/symlink.c * * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved * diff --git a/fs/autofs/waitq.c b/drivers/staging/autofs/waitq.c index be46805972f0..d3c8cc9eb4d1 100644 --- a/fs/autofs/waitq.c +++ b/drivers/staging/autofs/waitq.c @@ -1,6 +1,6 @@ /* -*- linux-c -*- --------------------------------------------------------- * * - * linux/fs/autofs/waitq.c + * drivers/staging/autofs/waitq.c * * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved * diff --git a/fs/smbfs/Kconfig b/drivers/staging/smbfs/Kconfig index 2bc24a8c4039..2bc24a8c4039 100644 --- a/fs/smbfs/Kconfig +++ b/drivers/staging/smbfs/Kconfig diff --git a/fs/smbfs/Makefile b/drivers/staging/smbfs/Makefile index 4faf8c4722c3..d2a92c5cb119 100644 --- a/fs/smbfs/Makefile +++ b/drivers/staging/smbfs/Makefile @@ -4,15 +4,15 @@ obj-$(CONFIG_SMB_FS) += smbfs.o -smbfs-objs := proc.o dir.o cache.o sock.o inode.o file.o ioctl.o getopt.o \ +smbfs-y := proc.o dir.o cache.o sock.o inode.o file.o ioctl.o getopt.o \ symlink.o smbiod.o request.o # If you want debugging output, you may add these flags to the EXTRA_CFLAGS # SMBFS_PARANOIA should normally be enabled. -EXTRA_CFLAGS += -DSMBFS_PARANOIA -#EXTRA_CFLAGS += -DSMBFS_DEBUG -#EXTRA_CFLAGS += -DSMBFS_DEBUG_VERBOSE -#EXTRA_CFLAGS += -DDEBUG_SMB_TIMESTAMP -#EXTRA_CFLAGS += -Werror +ccflags-y := -DSMBFS_PARANOIA +#ccflags-y += -DSMBFS_DEBUG +#ccflags-y += -DSMBFS_DEBUG_VERBOSE +#ccflags-y += -DDEBUG_SMB_TIMESTAMP +#ccflags-y += -Werror diff --git a/fs/smbfs/cache.c b/drivers/staging/smbfs/cache.c index 8c177eb7e344..dbb98658148b 100644 --- a/fs/smbfs/cache.c +++ b/drivers/staging/smbfs/cache.c @@ -13,12 +13,12 @@ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/mm.h> -#include <linux/smb_fs.h> #include <linux/pagemap.h> #include <linux/net.h> #include <asm/page.h> +#include "smb_fs.h" #include "smb_debug.h" #include "proto.h" diff --git a/fs/smbfs/dir.c b/drivers/staging/smbfs/dir.c index 00a70cab1f36..f088ea2f6ac9 100644 --- a/fs/smbfs/dir.c +++ b/drivers/staging/smbfs/dir.c @@ -15,9 +15,9 @@ #include <linux/net.h> #include <linux/sched.h> -#include <linux/smb_fs.h> -#include <linux/smb_mount.h> -#include <linux/smbno.h> +#include "smb_fs.h" +#include "smb_mount.h" +#include "smbno.h" #include "smb_debug.h" #include "proto.h" @@ -406,21 +406,15 @@ void smb_renew_times(struct dentry * dentry) { dget(dentry); - spin_lock(&dentry->d_lock); - for (;;) { - struct dentry *parent; + dentry->d_time = jiffies; - dentry->d_time = jiffies; - if (IS_ROOT(dentry)) - break; - parent = dentry->d_parent; - dget(parent); - spin_unlock(&dentry->d_lock); + while (!IS_ROOT(dentry)) { + struct dentry *parent = dget_parent(dentry); dput(dentry); dentry = parent; - spin_lock(&dentry->d_lock); + + dentry->d_time = jiffies; } - spin_unlock(&dentry->d_lock); dput(dentry); } diff --git a/fs/smbfs/file.c b/drivers/staging/smbfs/file.c index 8e187a0f94bb..5dcd19c60eb9 100644 --- a/fs/smbfs/file.c +++ b/drivers/staging/smbfs/file.c @@ -21,9 +21,8 @@ #include <asm/uaccess.h> #include <asm/system.h> -#include <linux/smbno.h> -#include <linux/smb_fs.h> - +#include "smbno.h" +#include "smb_fs.h" #include "smb_debug.h" #include "proto.h" diff --git a/fs/smbfs/getopt.c b/drivers/staging/smbfs/getopt.c index 7ae0f5273ab1..7ae0f5273ab1 100644 --- a/fs/smbfs/getopt.c +++ b/drivers/staging/smbfs/getopt.c diff --git a/fs/smbfs/getopt.h b/drivers/staging/smbfs/getopt.h index 146219ac7c46..146219ac7c46 100644 --- a/fs/smbfs/getopt.h +++ b/drivers/staging/smbfs/getopt.h diff --git a/fs/smbfs/inode.c b/drivers/staging/smbfs/inode.c index 8fc5e50e142f..540a984bb516 100644 --- a/fs/smbfs/inode.c +++ b/drivers/staging/smbfs/inode.c @@ -26,13 +26,13 @@ #include <linux/vfs.h> #include <linux/highuid.h> #include <linux/sched.h> -#include <linux/smb_fs.h> -#include <linux/smbno.h> -#include <linux/smb_mount.h> #include <asm/system.h> #include <asm/uaccess.h> +#include "smb_fs.h" +#include "smbno.h" +#include "smb_mount.h" #include "smb_debug.h" #include "getopt.h" #include "proto.h" @@ -229,7 +229,6 @@ smb_invalidate_inodes(struct smb_sb_info *server) { VERBOSE("\n"); shrink_dcache_sb(SB_of(server)); - invalidate_inodes(SB_of(server)); } /* @@ -506,7 +505,7 @@ static int smb_fill_super(struct super_block *sb, void *raw_data, int silent) if (warn_count < 5) { warn_count++; printk(KERN_EMERG "smbfs is deprecated and will be removed" - " from the 2.6.27 kernel. Please migrate to cifs\n"); + " from the 2.6.37 kernel. Please migrate to cifs\n"); } if (!raw_data) @@ -538,7 +537,7 @@ static int smb_fill_super(struct super_block *sb, void *raw_data, int silent) server->mnt = NULL; server->sock_file = NULL; init_waitqueue_head(&server->conn_wq); - init_MUTEX(&server->sem); + sema_init(&server->sem, 1); INIT_LIST_HEAD(&server->entry); INIT_LIST_HEAD(&server->xmitq); INIT_LIST_HEAD(&server->recvq); @@ -794,16 +793,16 @@ out: return error; } -static int smb_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *smb_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_nodev(fs_type, flags, data, smb_fill_super, mnt); + return mount_nodev(fs_type, flags, data, smb_fill_super); } static struct file_system_type smb_fs_type = { .owner = THIS_MODULE, .name = "smbfs", - .get_sb = smb_get_sb, + .mount = smb_mount, .kill_sb = kill_anon_super, .fs_flags = FS_BINARY_MOUNTDATA, }; diff --git a/fs/smbfs/ioctl.c b/drivers/staging/smbfs/ioctl.c index 07215312ad39..2da169267470 100644 --- a/fs/smbfs/ioctl.c +++ b/drivers/staging/smbfs/ioctl.c @@ -16,11 +16,10 @@ #include <linux/smp_lock.h> #include <linux/net.h> -#include <linux/smb_fs.h> -#include <linux/smb_mount.h> - #include <asm/uaccess.h> +#include "smb_fs.h" +#include "smb_mount.h" #include "proto.h" long diff --git a/fs/smbfs/proc.c b/drivers/staging/smbfs/proc.c index 71c29b6670b4..ba37b1fae182 100644 --- a/fs/smbfs/proc.c +++ b/drivers/staging/smbfs/proc.c @@ -20,15 +20,14 @@ #include <linux/smp_lock.h> #include <linux/net.h> #include <linux/vfs.h> -#include <linux/smb_fs.h> -#include <linux/smbno.h> -#include <linux/smb_mount.h> - #include <net/sock.h> #include <asm/string.h> #include <asm/div64.h> +#include "smb_fs.h" +#include "smbno.h" +#include "smb_mount.h" #include "smb_debug.h" #include "proto.h" #include "request.h" @@ -332,16 +331,15 @@ static int smb_build_path(struct smb_sb_info *server, unsigned char *buf, * and store it in reversed order [see reverse_string()] */ dget(entry); - spin_lock(&entry->d_lock); while (!IS_ROOT(entry)) { struct dentry *parent; if (maxlen < (3<<unicode)) { - spin_unlock(&entry->d_lock); dput(entry); return -ENAMETOOLONG; } + spin_lock(&entry->d_lock); len = server->ops->convert(path, maxlen-2, entry->d_name.name, entry->d_name.len, server->local_nls, server->remote_nls); @@ -359,15 +357,12 @@ static int smb_build_path(struct smb_sb_info *server, unsigned char *buf, } *path++ = '\\'; maxlen -= len+1; - - parent = entry->d_parent; - dget(parent); spin_unlock(&entry->d_lock); + + parent = dget_parent(entry); dput(entry); entry = parent; - spin_lock(&entry->d_lock); } - spin_unlock(&entry->d_lock); dput(entry); reverse_string(buf, path-buf); diff --git a/fs/smbfs/proto.h b/drivers/staging/smbfs/proto.h index 05939a6f43e6..05939a6f43e6 100644 --- a/fs/smbfs/proto.h +++ b/drivers/staging/smbfs/proto.h diff --git a/fs/smbfs/request.c b/drivers/staging/smbfs/request.c index 45f45933e862..3e7716864306 100644 --- a/fs/smbfs/request.c +++ b/drivers/staging/smbfs/request.c @@ -13,10 +13,9 @@ #include <linux/net.h> #include <linux/sched.h> -#include <linux/smb_fs.h> -#include <linux/smbno.h> -#include <linux/smb_mount.h> - +#include "smb_fs.h" +#include "smbno.h" +#include "smb_mount.h" #include "smb_debug.h" #include "request.h" #include "proto.h" diff --git a/fs/smbfs/request.h b/drivers/staging/smbfs/request.h index efb21451e7c9..efb21451e7c9 100644 --- a/fs/smbfs/request.h +++ b/drivers/staging/smbfs/request.h diff --git a/fs/smbfs/smb_debug.h b/drivers/staging/smbfs/smb_debug.h index fc4b1a5dd755..fc4b1a5dd755 100644 --- a/fs/smbfs/smb_debug.h +++ b/drivers/staging/smbfs/smb_debug.h diff --git a/fs/smbfs/smbiod.c b/drivers/staging/smbfs/smbiod.c index 0e39a924f10a..ec998920f8d9 100644 --- a/fs/smbfs/smbiod.c +++ b/drivers/staging/smbfs/smbiod.c @@ -20,13 +20,12 @@ #include <linux/kthread.h> #include <net/ip.h> -#include <linux/smb_fs.h> -#include <linux/smbno.h> -#include <linux/smb_mount.h> - #include <asm/system.h> #include <asm/uaccess.h> +#include "smb_fs.h" +#include "smbno.h" +#include "smb_mount.h" #include "smb_debug.h" #include "request.h" #include "proto.h" diff --git a/fs/smbfs/sock.c b/drivers/staging/smbfs/sock.c index e37fe4deebd0..9e264090e611 100644 --- a/fs/smbfs/sock.c +++ b/drivers/staging/smbfs/sock.c @@ -22,13 +22,12 @@ #include <net/tcp_states.h> #include <net/ip.h> -#include <linux/smb_fs.h> -#include <linux/smb.h> -#include <linux/smbno.h> - #include <asm/uaccess.h> #include <asm/ioctls.h> +#include "smb_fs.h" +#include "smb.h" +#include "smbno.h" #include "smb_debug.h" #include "proto.h" #include "request.h" diff --git a/fs/smbfs/symlink.c b/drivers/staging/smbfs/symlink.c index 00b2909bd469..632c4acd062d 100644 --- a/fs/smbfs/symlink.c +++ b/drivers/staging/smbfs/symlink.c @@ -19,9 +19,8 @@ #include <asm/uaccess.h> #include <asm/system.h> -#include <linux/smbno.h> -#include <linux/smb_fs.h> - +#include "smbno.h" +#include "smb_fs.h" #include "smb_debug.h" #include "proto.h" diff --git a/fs/9p/Kconfig b/fs/9p/Kconfig index 795233702a4e..7e0511476797 100644 --- a/fs/9p/Kconfig +++ b/fs/9p/Kconfig @@ -17,3 +17,16 @@ config 9P_FSCACHE Choose Y here to enable persistent, read-only local caching support for 9p clients using FS-Cache + +config 9P_FS_POSIX_ACL + bool "9P POSIX Access Control Lists" + depends on 9P_FS + select FS_POSIX_ACL + help + POSIX Access Control Lists (ACLs) support permissions for users and + groups beyond the owner/group/world scheme. + + To learn more about Access Control Lists, visit the POSIX ACLs for + Linux website <http://acl.bestbits.at/>. + + If you don't know what Access Control Lists are, say N diff --git a/fs/9p/Makefile b/fs/9p/Makefile index 91fba025fcbe..f8ba37effd1b 100644 --- a/fs/9p/Makefile +++ b/fs/9p/Makefile @@ -13,3 +13,4 @@ obj-$(CONFIG_9P_FS) := 9p.o xattr_user.o 9p-$(CONFIG_9P_FSCACHE) += cache.o +9p-$(CONFIG_9P_FS_POSIX_ACL) += acl.o diff --git a/fs/9p/acl.c b/fs/9p/acl.c new file mode 100644 index 000000000000..12d602351dbe --- /dev/null +++ b/fs/9p/acl.c @@ -0,0 +1,392 @@ +/* + * Copyright IBM Corporation, 2010 + * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2.1 of the GNU Lesser General Public License + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it would be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * + */ + +#include <linux/module.h> +#include <linux/fs.h> +#include <net/9p/9p.h> +#include <net/9p/client.h> +#include <linux/slab.h> +#include <linux/sched.h> +#include <linux/posix_acl_xattr.h> +#include "xattr.h" +#include "acl.h" +#include "v9fs_vfs.h" +#include "v9fs.h" + +static struct posix_acl *__v9fs_get_acl(struct p9_fid *fid, char *name) +{ + ssize_t size; + void *value = NULL; + struct posix_acl *acl = NULL;; + + size = v9fs_fid_xattr_get(fid, name, NULL, 0); + if (size > 0) { + value = kzalloc(size, GFP_NOFS); + if (!value) + return ERR_PTR(-ENOMEM); + size = v9fs_fid_xattr_get(fid, name, value, size); + if (size > 0) { + acl = posix_acl_from_xattr(value, size); + if (IS_ERR(acl)) + goto err_out; + } + } else if (size == -ENODATA || size == 0 || + size == -ENOSYS || size == -EOPNOTSUPP) { + acl = NULL; + } else + acl = ERR_PTR(-EIO); + +err_out: + kfree(value); + return acl; +} + +int v9fs_get_acl(struct inode *inode, struct p9_fid *fid) +{ + int retval = 0; + struct posix_acl *pacl, *dacl; + struct v9fs_session_info *v9ses; + + v9ses = v9fs_inode2v9ses(inode); + if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT) { + set_cached_acl(inode, ACL_TYPE_DEFAULT, NULL); + set_cached_acl(inode, ACL_TYPE_ACCESS, NULL); + return 0; + } + /* get the default/access acl values and cache them */ + dacl = __v9fs_get_acl(fid, POSIX_ACL_XATTR_DEFAULT); + pacl = __v9fs_get_acl(fid, POSIX_ACL_XATTR_ACCESS); + + if (!IS_ERR(dacl) && !IS_ERR(pacl)) { + set_cached_acl(inode, ACL_TYPE_DEFAULT, dacl); + set_cached_acl(inode, ACL_TYPE_ACCESS, pacl); + posix_acl_release(dacl); + posix_acl_release(pacl); + } else + retval = -EIO; + + return retval; +} + +static struct posix_acl *v9fs_get_cached_acl(struct inode *inode, int type) +{ + struct posix_acl *acl; + /* + * 9p Always cache the acl value when + * instantiating the inode (v9fs_inode_from_fid) + */ + acl = get_cached_acl(inode, type); + BUG_ON(acl == ACL_NOT_CACHED); + return acl; +} + +int v9fs_check_acl(struct inode *inode, int mask) +{ + struct posix_acl *acl; + struct v9fs_session_info *v9ses; + + v9ses = v9fs_inode2v9ses(inode); + if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT) { + /* + * On access = client mode get the acl + * values from the server + */ + return 0; + } + acl = v9fs_get_cached_acl(inode, ACL_TYPE_ACCESS); + + if (IS_ERR(acl)) + return PTR_ERR(acl); + if (acl) { + int error = posix_acl_permission(inode, acl, mask); + posix_acl_release(acl); + return error; + } + return -EAGAIN; +} + +static int v9fs_set_acl(struct dentry *dentry, int type, struct posix_acl *acl) +{ + int retval; + char *name; + size_t size; + void *buffer; + struct inode *inode = dentry->d_inode; + + set_cached_acl(inode, type, acl); + /* Set a setxattr request to server */ + size = posix_acl_xattr_size(acl->a_count); + buffer = kmalloc(size, GFP_KERNEL); + if (!buffer) + return -ENOMEM; + retval = posix_acl_to_xattr(acl, buffer, size); + if (retval < 0) + goto err_free_out; + switch (type) { + case ACL_TYPE_ACCESS: + name = POSIX_ACL_XATTR_ACCESS; + break; + case ACL_TYPE_DEFAULT: + name = POSIX_ACL_XATTR_DEFAULT; + break; + default: + BUG(); + } + retval = v9fs_xattr_set(dentry, name, buffer, size, 0); +err_free_out: + kfree(buffer); + return retval; +} + +int v9fs_acl_chmod(struct dentry *dentry) +{ + int retval = 0; + struct posix_acl *acl, *clone; + struct inode *inode = dentry->d_inode; + + if (S_ISLNK(inode->i_mode)) + return -EOPNOTSUPP; + acl = v9fs_get_cached_acl(inode, ACL_TYPE_ACCESS); + if (acl) { + clone = posix_acl_clone(acl, GFP_KERNEL); + posix_acl_release(acl); + if (!clone) + return -ENOMEM; + retval = posix_acl_chmod_masq(clone, inode->i_mode); + if (!retval) + retval = v9fs_set_acl(dentry, ACL_TYPE_ACCESS, clone); + posix_acl_release(clone); + } + return retval; +} + +int v9fs_set_create_acl(struct dentry *dentry, + struct posix_acl *dpacl, struct posix_acl *pacl) +{ + if (dpacl) + v9fs_set_acl(dentry, ACL_TYPE_DEFAULT, dpacl); + if (pacl) + v9fs_set_acl(dentry, ACL_TYPE_ACCESS, pacl); + posix_acl_release(dpacl); + posix_acl_release(pacl); + return 0; +} + +int v9fs_acl_mode(struct inode *dir, mode_t *modep, + struct posix_acl **dpacl, struct posix_acl **pacl) +{ + int retval = 0; + mode_t mode = *modep; + struct posix_acl *acl = NULL; + + if (!S_ISLNK(mode)) { + acl = v9fs_get_cached_acl(dir, ACL_TYPE_DEFAULT); + if (IS_ERR(acl)) + return PTR_ERR(acl); + if (!acl) + mode &= ~current_umask(); + } + if (acl) { + struct posix_acl *clone; + + if (S_ISDIR(mode)) + *dpacl = acl; + clone = posix_acl_clone(acl, GFP_NOFS); + retval = -ENOMEM; + if (!clone) + goto cleanup; + + retval = posix_acl_create_masq(clone, &mode); + if (retval < 0) { + posix_acl_release(clone); + goto cleanup; + } + if (retval > 0) + *pacl = clone; + } + *modep = mode; + return 0; +cleanup: + posix_acl_release(acl); + return retval; + +} + +static int v9fs_remote_get_acl(struct dentry *dentry, const char *name, + void *buffer, size_t size, int type) +{ + char *full_name; + + switch (type) { + case ACL_TYPE_ACCESS: + full_name = POSIX_ACL_XATTR_ACCESS; + break; + case ACL_TYPE_DEFAULT: + full_name = POSIX_ACL_XATTR_DEFAULT; + break; + default: + BUG(); + } + return v9fs_xattr_get(dentry, full_name, buffer, size); +} + +static int v9fs_xattr_get_acl(struct dentry *dentry, const char *name, + void *buffer, size_t size, int type) +{ + struct v9fs_session_info *v9ses; + struct posix_acl *acl; + int error; + + if (strcmp(name, "") != 0) + return -EINVAL; + + v9ses = v9fs_inode2v9ses(dentry->d_inode); + /* + * We allow set/get/list of acl when access=client is not specified + */ + if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT) + return v9fs_remote_get_acl(dentry, name, buffer, size, type); + + acl = v9fs_get_cached_acl(dentry->d_inode, type); + if (IS_ERR(acl)) + return PTR_ERR(acl); + if (acl == NULL) + return -ENODATA; + error = posix_acl_to_xattr(acl, buffer, size); + posix_acl_release(acl); + + return error; +} + +static int v9fs_remote_set_acl(struct dentry *dentry, const char *name, + const void *value, size_t size, + int flags, int type) +{ + char *full_name; + + switch (type) { + case ACL_TYPE_ACCESS: + full_name = POSIX_ACL_XATTR_ACCESS; + break; + case ACL_TYPE_DEFAULT: + full_name = POSIX_ACL_XATTR_DEFAULT; + break; + default: + BUG(); + } + return v9fs_xattr_set(dentry, full_name, value, size, flags); +} + + +static int v9fs_xattr_set_acl(struct dentry *dentry, const char *name, + const void *value, size_t size, + int flags, int type) +{ + int retval; + struct posix_acl *acl; + struct v9fs_session_info *v9ses; + struct inode *inode = dentry->d_inode; + + if (strcmp(name, "") != 0) + return -EINVAL; + + v9ses = v9fs_inode2v9ses(dentry->d_inode); + /* + * set the attribute on the remote. Without even looking at the + * xattr value. We leave it to the server to validate + */ + if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT) + return v9fs_remote_set_acl(dentry, name, + value, size, flags, type); + + if (S_ISLNK(inode->i_mode)) + return -EOPNOTSUPP; + if (!is_owner_or_cap(inode)) + return -EPERM; + if (value) { + /* update the cached acl value */ + acl = posix_acl_from_xattr(value, size); + if (IS_ERR(acl)) + return PTR_ERR(acl); + else if (acl) { + retval = posix_acl_valid(acl); + if (retval) + goto err_out; + } + } else + acl = NULL; + + switch (type) { + case ACL_TYPE_ACCESS: + name = POSIX_ACL_XATTR_ACCESS; + if (acl) { + mode_t mode = inode->i_mode; + retval = posix_acl_equiv_mode(acl, &mode); + if (retval < 0) + goto err_out; + else { + struct iattr iattr; + if (retval == 0) { + /* + * ACL can be represented + * by the mode bits. So don't + * update ACL. + */ + acl = NULL; + value = NULL; + size = 0; + } + /* Updte the mode bits */ + iattr.ia_mode = ((mode & S_IALLUGO) | + (inode->i_mode & ~S_IALLUGO)); + iattr.ia_valid = ATTR_MODE; + /* FIXME should we update ctime ? + * What is the following setxattr update the + * mode ? + */ + v9fs_vfs_setattr_dotl(dentry, &iattr); + } + } + break; + case ACL_TYPE_DEFAULT: + name = POSIX_ACL_XATTR_DEFAULT; + if (!S_ISDIR(inode->i_mode)) { + retval = -EINVAL; + goto err_out; + } + break; + default: + BUG(); + } + retval = v9fs_xattr_set(dentry, name, value, size, flags); + if (!retval) + set_cached_acl(inode, type, acl); +err_out: + posix_acl_release(acl); + return retval; +} + +const struct xattr_handler v9fs_xattr_acl_access_handler = { + .prefix = POSIX_ACL_XATTR_ACCESS, + .flags = ACL_TYPE_ACCESS, + .get = v9fs_xattr_get_acl, + .set = v9fs_xattr_set_acl, +}; + +const struct xattr_handler v9fs_xattr_acl_default_handler = { + .prefix = POSIX_ACL_XATTR_DEFAULT, + .flags = ACL_TYPE_DEFAULT, + .get = v9fs_xattr_get_acl, + .set = v9fs_xattr_set_acl, +}; diff --git a/fs/9p/acl.h b/fs/9p/acl.h new file mode 100644 index 000000000000..59e18c2e8c7e --- /dev/null +++ b/fs/9p/acl.h @@ -0,0 +1,49 @@ +/* + * Copyright IBM Corporation, 2010 + * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2.1 of the GNU Lesser General Public License + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it would be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * + */ +#ifndef FS_9P_ACL_H +#define FS_9P_ACL_H + +#ifdef CONFIG_9P_FS_POSIX_ACL +extern int v9fs_get_acl(struct inode *, struct p9_fid *); +extern int v9fs_check_acl(struct inode *inode, int mask); +extern int v9fs_acl_chmod(struct dentry *); +extern int v9fs_set_create_acl(struct dentry *, + struct posix_acl *, struct posix_acl *); +extern int v9fs_acl_mode(struct inode *dir, mode_t *modep, + struct posix_acl **dpacl, struct posix_acl **pacl); +#else +#define v9fs_check_acl NULL +static inline int v9fs_get_acl(struct inode *inode, struct p9_fid *fid) +{ + return 0; +} +static inline int v9fs_acl_chmod(struct dentry *dentry) +{ + return 0; +} +static inline int v9fs_set_create_acl(struct dentry *dentry, + struct posix_acl *dpacl, + struct posix_acl *pacl) +{ + return 0; +} +static inline int v9fs_acl_mode(struct inode *dir, mode_t *modep, + struct posix_acl **dpacl, + struct posix_acl **pacl) +{ + return 0; +} + +#endif +#endif /* FS_9P_XATTR_H */ diff --git a/fs/9p/fid.c b/fs/9p/fid.c index 6406f896bf95..b00223c99d70 100644 --- a/fs/9p/fid.c +++ b/fs/9p/fid.c @@ -149,6 +149,7 @@ struct p9_fid *v9fs_fid_lookup(struct dentry *dentry) switch (access) { case V9FS_ACCESS_SINGLE: case V9FS_ACCESS_USER: + case V9FS_ACCESS_CLIENT: uid = current_fsuid(); any = 0; break; diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 38dc0e067599..2f77cd33ba83 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -193,7 +193,17 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) v9ses->flags |= V9FS_ACCESS_USER; else if (strcmp(s, "any") == 0) v9ses->flags |= V9FS_ACCESS_ANY; - else { + else if (strcmp(s, "client") == 0) { +#ifdef CONFIG_9P_FS_POSIX_ACL + v9ses->flags |= V9FS_ACCESS_CLIENT; +#else + P9_DPRINTK(P9_DEBUG_ERROR, + "access=client option not supported\n"); + kfree(s); + ret = -EINVAL; + goto free_and_return; +#endif + } else { v9ses->flags |= V9FS_ACCESS_SINGLE; v9ses->uid = simple_strtoul(s, &e, 10); if (*e != '\0') @@ -278,6 +288,16 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses, v9ses->maxdata = v9ses->clnt->msize - P9_IOHDRSZ; + if (!v9fs_proto_dotl(v9ses) && + ((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_CLIENT)) { + /* + * We support ACCESS_CLIENT only for dotl. + * Fall back to ACCESS_USER + */ + v9ses->flags &= ~V9FS_ACCESS_MASK; + v9ses->flags |= V9FS_ACCESS_USER; + } + /*FIXME !! */ /* for legacy mode, fall back to V9FS_ACCESS_ANY */ if (!(v9fs_proto_dotu(v9ses) || v9fs_proto_dotl(v9ses)) && ((v9ses->flags&V9FS_ACCESS_MASK) == V9FS_ACCESS_USER)) { diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 4c963c9fc41f..cb6396855e2d 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -33,13 +33,17 @@ * * Session flags reflect options selected by users at mount time */ +#define V9FS_ACCESS_ANY (V9FS_ACCESS_SINGLE | \ + V9FS_ACCESS_USER | \ + V9FS_ACCESS_CLIENT) +#define V9FS_ACCESS_MASK V9FS_ACCESS_ANY + enum p9_session_flags { V9FS_PROTO_2000U = 0x01, V9FS_PROTO_2000L = 0x02, V9FS_ACCESS_SINGLE = 0x04, V9FS_ACCESS_USER = 0x08, - V9FS_ACCESS_ANY = 0x0C, - V9FS_ACCESS_MASK = 0x0C, + V9FS_ACCESS_CLIENT = 0x10 }; /* possible values of ->cache */ @@ -113,8 +117,6 @@ void v9fs_session_close(struct v9fs_session_info *v9ses); void v9fs_session_cancel(struct v9fs_session_info *v9ses); void v9fs_session_begin_cancel(struct v9fs_session_info *v9ses); -#define V9FS_MAGIC 0x01021997 - /* other default globals */ #define V9FS_PORT 564 #define V9FS_DEFUSER "nobody" diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h index 88418c419ea7..bab0eac873f4 100644 --- a/fs/9p/v9fs_vfs.h +++ b/fs/9p/v9fs_vfs.h @@ -64,3 +64,7 @@ int v9fs_uflags2omode(int uflags, int extended); ssize_t v9fs_file_readn(struct file *, char *, char __user *, u32, u64); void v9fs_blank_wstat(struct p9_wstat *wstat); +int v9fs_vfs_setattr_dotl(struct dentry *, struct iattr *); +int v9fs_file_fsync_dotl(struct file *filp, int datasync); + +#define P9_LOCK_TIMEOUT (30*HZ) diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 90e38449f4b3..b7f2a8e3863e 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -154,10 +154,40 @@ static int v9fs_launder_page(struct page *page) return 0; } +/** + * v9fs_direct_IO - 9P address space operation for direct I/O + * @rw: direction (read or write) + * @iocb: target I/O control block + * @iov: array of vectors that define I/O buffer + * @pos: offset in file to begin the operation + * @nr_segs: size of iovec array + * + * The presence of v9fs_direct_IO() in the address space ops vector + * allowes open() O_DIRECT flags which would have failed otherwise. + * + * In the non-cached mode, we shunt off direct read and write requests before + * the VFS gets them, so this method should never be called. + * + * Direct IO is not 'yet' supported in the cached mode. Hence when + * this routine is called through generic_file_aio_read(), the read/write fails + * with an error. + * + */ +ssize_t v9fs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, + loff_t pos, unsigned long nr_segs) +{ + P9_DPRINTK(P9_DEBUG_VFS, "v9fs_direct_IO: v9fs_direct_IO (%s) " + "off/no(%lld/%lu) EINVAL\n", + iocb->ki_filp->f_path.dentry->d_name.name, + (long long) pos, nr_segs); + + return -EINVAL; +} const struct address_space_operations v9fs_addr_operations = { .readpage = v9fs_vfs_readpage, .readpages = v9fs_vfs_readpages, .releasepage = v9fs_release_page, .invalidatepage = v9fs_invalidate_page, .launder_page = v9fs_launder_page, + .direct_IO = v9fs_direct_IO, }; diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c index 899f168fd19c..b84ebe8cefed 100644 --- a/fs/9p/vfs_dir.c +++ b/fs/9p/vfs_dir.c @@ -242,7 +242,8 @@ static int v9fs_dir_readdir_dotl(struct file *filp, void *dirent, while (rdir->head < rdir->tail) { err = p9dirent_read(rdir->buf + rdir->head, - buflen - rdir->head, &curdirent, + rdir->tail - rdir->head, + &curdirent, fid->clnt->proto_version); if (err < 0) { P9_DPRINTK(P9_DEBUG_VFS, "returned %d\n", err); @@ -314,4 +315,5 @@ const struct file_operations v9fs_dir_operations_dotl = { .readdir = v9fs_dir_readdir_dotl, .open = v9fs_file_open, .release = v9fs_dir_release, + .fsync = v9fs_file_fsync_dotl, }; diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index e97c92bd6f16..240c30674396 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -33,6 +33,7 @@ #include <linux/inet.h> #include <linux/list.h> #include <linux/pagemap.h> +#include <linux/utsname.h> #include <asm/uaccess.h> #include <linux/idr.h> #include <net/9p/9p.h> @@ -44,6 +45,7 @@ #include "cache.h" static const struct file_operations v9fs_cached_file_operations; +static const struct file_operations v9fs_cached_file_operations_dotl; /** * v9fs_file_open - open a file (or directory) @@ -92,6 +94,8 @@ int v9fs_file_open(struct inode *inode, struct file *file) /* enable cached file options */ if(file->f_op == &v9fs_file_operations) file->f_op = &v9fs_cached_file_operations; + else if (file->f_op == &v9fs_file_operations_dotl) + file->f_op = &v9fs_cached_file_operations_dotl; #ifdef CONFIG_9P_FSCACHE v9fs_cache_inode_set_cookie(inode, file); @@ -130,6 +134,206 @@ static int v9fs_file_lock(struct file *filp, int cmd, struct file_lock *fl) return res; } +static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl) +{ + struct p9_flock flock; + struct p9_fid *fid; + uint8_t status; + int res = 0; + unsigned char fl_type; + + fid = filp->private_data; + BUG_ON(fid == NULL); + + if ((fl->fl_flags & FL_POSIX) != FL_POSIX) + BUG(); + + res = posix_lock_file_wait(filp, fl); + if (res < 0) + goto out; + + /* convert posix lock to p9 tlock args */ + memset(&flock, 0, sizeof(flock)); + flock.type = fl->fl_type; + flock.start = fl->fl_start; + if (fl->fl_end == OFFSET_MAX) + flock.length = 0; + else + flock.length = fl->fl_end - fl->fl_start + 1; + flock.proc_id = fl->fl_pid; + flock.client_id = utsname()->nodename; + if (IS_SETLKW(cmd)) + flock.flags = P9_LOCK_FLAGS_BLOCK; + + /* + * if its a blocked request and we get P9_LOCK_BLOCKED as the status + * for lock request, keep on trying + */ + for (;;) { + res = p9_client_lock_dotl(fid, &flock, &status); + if (res < 0) + break; + + if (status != P9_LOCK_BLOCKED) + break; + if (status == P9_LOCK_BLOCKED && !IS_SETLKW(cmd)) + break; + schedule_timeout_interruptible(P9_LOCK_TIMEOUT); + } + + /* map 9p status to VFS status */ + switch (status) { + case P9_LOCK_SUCCESS: + res = 0; + break; + case P9_LOCK_BLOCKED: + res = -EAGAIN; + break; + case P9_LOCK_ERROR: + case P9_LOCK_GRACE: + res = -ENOLCK; + break; + default: + BUG(); + } + + /* + * incase server returned error for lock request, revert + * it locally + */ + if (res < 0 && fl->fl_type != F_UNLCK) { + fl_type = fl->fl_type; + fl->fl_type = F_UNLCK; + res = posix_lock_file_wait(filp, fl); + fl->fl_type = fl_type; + } +out: + return res; +} + +static int v9fs_file_getlock(struct file *filp, struct file_lock *fl) +{ + struct p9_getlock glock; + struct p9_fid *fid; + int res = 0; + + fid = filp->private_data; + BUG_ON(fid == NULL); + + posix_test_lock(filp, fl); + /* + * if we have a conflicting lock locally, no need to validate + * with server + */ + if (fl->fl_type != F_UNLCK) + return res; + + /* convert posix lock to p9 tgetlock args */ + memset(&glock, 0, sizeof(glock)); + glock.type = fl->fl_type; + glock.start = fl->fl_start; + if (fl->fl_end == OFFSET_MAX) + glock.length = 0; + else + glock.length = fl->fl_end - fl->fl_start + 1; + glock.proc_id = fl->fl_pid; + glock.client_id = utsname()->nodename; + + res = p9_client_getlock_dotl(fid, &glock); + if (res < 0) + return res; + if (glock.type != F_UNLCK) { + fl->fl_type = glock.type; + fl->fl_start = glock.start; + if (glock.length == 0) + fl->fl_end = OFFSET_MAX; + else + fl->fl_end = glock.start + glock.length - 1; + fl->fl_pid = glock.proc_id; + } else + fl->fl_type = F_UNLCK; + + return res; +} + +/** + * v9fs_file_lock_dotl - lock a file (or directory) + * @filp: file to be locked + * @cmd: lock command + * @fl: file lock structure + * + */ + +static int v9fs_file_lock_dotl(struct file *filp, int cmd, struct file_lock *fl) +{ + struct inode *inode = filp->f_path.dentry->d_inode; + int ret = -ENOLCK; + + P9_DPRINTK(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %s\n", filp, + cmd, fl, filp->f_path.dentry->d_name.name); + + /* No mandatory locks */ + if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK) + goto out_err; + + if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) { + filemap_write_and_wait(inode->i_mapping); + invalidate_mapping_pages(&inode->i_data, 0, -1); + } + + if (IS_SETLK(cmd) || IS_SETLKW(cmd)) + ret = v9fs_file_do_lock(filp, cmd, fl); + else if (IS_GETLK(cmd)) + ret = v9fs_file_getlock(filp, fl); + else + ret = -EINVAL; +out_err: + return ret; +} + +/** + * v9fs_file_flock_dotl - lock a file + * @filp: file to be locked + * @cmd: lock command + * @fl: file lock structure + * + */ + +static int v9fs_file_flock_dotl(struct file *filp, int cmd, + struct file_lock *fl) +{ + struct inode *inode = filp->f_path.dentry->d_inode; + int ret = -ENOLCK; + + P9_DPRINTK(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %s\n", filp, + cmd, fl, filp->f_path.dentry->d_name.name); + + /* No mandatory locks */ + if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK) + goto out_err; + + if (!(fl->fl_flags & FL_FLOCK)) + goto out_err; + + if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) { + filemap_write_and_wait(inode->i_mapping); + invalidate_mapping_pages(&inode->i_data, 0, -1); + } + /* Convert flock to posix lock */ + fl->fl_owner = (fl_owner_t)filp; + fl->fl_start = 0; + fl->fl_end = OFFSET_MAX; + fl->fl_flags |= FL_POSIX; + fl->fl_flags ^= FL_FLOCK; + + if (IS_SETLK(cmd) | IS_SETLKW(cmd)) + ret = v9fs_file_do_lock(filp, cmd, fl); + else + ret = -EINVAL; +out_err: + return ret; +} + /** * v9fs_file_readn - read from a file * @filp: file pointer to read @@ -219,7 +423,9 @@ static ssize_t v9fs_file_write(struct file *filp, const char __user * data, size_t count, loff_t * offset) { - int n, rsize, total = 0; + ssize_t retval; + size_t total = 0; + int n; struct p9_fid *fid; struct p9_client *clnt; struct inode *inode = filp->f_path.dentry->d_inode; @@ -232,14 +438,19 @@ v9fs_file_write(struct file *filp, const char __user * data, fid = filp->private_data; clnt = fid->clnt; - rsize = fid->iounit ? fid->iounit : clnt->msize - P9_IOHDRSZ; + retval = generic_write_checks(filp, &origin, &count, 0); + if (retval) + goto out; - do { - if (count < rsize) - rsize = count; + retval = -EINVAL; + if ((ssize_t) count < 0) + goto out; + retval = 0; + if (!count) + goto out; - n = p9_client_write(fid, NULL, data+total, origin+total, - rsize); + do { + n = p9_client_write(fid, NULL, data+total, origin+total, count); if (n <= 0) break; count -= n; @@ -258,9 +469,11 @@ v9fs_file_write(struct file *filp, const char __user * data, } if (n < 0) - return n; - - return total; + retval = n; + else + retval = total; +out: + return retval; } static int v9fs_file_fsync(struct file *filp, int datasync) @@ -278,6 +491,20 @@ static int v9fs_file_fsync(struct file *filp, int datasync) return retval; } +int v9fs_file_fsync_dotl(struct file *filp, int datasync) +{ + struct p9_fid *fid; + int retval; + + P9_DPRINTK(P9_DEBUG_VFS, "v9fs_file_fsync_dotl: filp %p datasync %x\n", + filp, datasync); + + fid = filp->private_data; + + retval = p9_client_fsync(fid, datasync); + return retval; +} + static const struct file_operations v9fs_cached_file_operations = { .llseek = generic_file_llseek, .read = do_sync_read, @@ -290,6 +517,19 @@ static const struct file_operations v9fs_cached_file_operations = { .fsync = v9fs_file_fsync, }; +static const struct file_operations v9fs_cached_file_operations_dotl = { + .llseek = generic_file_llseek, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = v9fs_file_write, + .open = v9fs_file_open, + .release = v9fs_dir_release, + .lock = v9fs_file_lock_dotl, + .flock = v9fs_file_flock_dotl, + .mmap = generic_file_readonly_mmap, + .fsync = v9fs_file_fsync_dotl, +}; + const struct file_operations v9fs_file_operations = { .llseek = generic_file_llseek, .read = v9fs_file_read, @@ -307,7 +547,8 @@ const struct file_operations v9fs_file_operations_dotl = { .write = v9fs_file_write, .open = v9fs_file_open, .release = v9fs_dir_release, - .lock = v9fs_file_lock, + .lock = v9fs_file_lock_dotl, + .flock = v9fs_file_flock_dotl, .mmap = generic_file_readonly_mmap, - .fsync = v9fs_file_fsync, + .fsync = v9fs_file_fsync_dotl, }; diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 9e670d527646..34bf71b56542 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -36,6 +36,7 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/xattr.h> +#include <linux/posix_acl.h> #include <net/9p/9p.h> #include <net/9p/client.h> @@ -44,6 +45,7 @@ #include "fid.h" #include "cache.h" #include "xattr.h" +#include "acl.h" static const struct inode_operations v9fs_dir_inode_operations; static const struct inode_operations v9fs_dir_inode_operations_dotu; @@ -53,6 +55,10 @@ static const struct inode_operations v9fs_file_inode_operations_dotl; static const struct inode_operations v9fs_symlink_inode_operations; static const struct inode_operations v9fs_symlink_inode_operations_dotl; +static int +v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, int omode, + dev_t rdev); + /** * unixmode2p9mode - convert unix mode bits to plan 9 * @v9ses: v9fs session information @@ -500,6 +506,11 @@ v9fs_inode_dotl(struct v9fs_session_info *v9ses, struct p9_fid *fid, v9fs_vcookie_set_qid(ret, &st->qid); v9fs_cache_inode_get_cookie(ret); #endif + err = v9fs_get_acl(ret, fid); + if (err) { + iput(ret); + goto error; + } kfree(st); return ret; error: @@ -553,13 +564,6 @@ static int v9fs_remove(struct inode *dir, struct dentry *file, int rmdir) return retval; } -static int -v9fs_open_created(struct inode *inode, struct file *file) -{ - return 0; -} - - /** * v9fs_create - Create a file * @v9ses: session information @@ -655,29 +659,37 @@ error: */ static int -v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, int mode, +v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, int omode, struct nameidata *nd) { int err = 0; char *name = NULL; gid_t gid; int flags; + mode_t mode; struct v9fs_session_info *v9ses; struct p9_fid *fid = NULL; struct p9_fid *dfid, *ofid; struct file *filp; struct p9_qid qid; struct inode *inode; + struct posix_acl *pacl = NULL, *dacl = NULL; v9ses = v9fs_inode2v9ses(dir); if (nd && nd->flags & LOOKUP_OPEN) flags = nd->intent.open.flags - 1; - else - flags = O_RDWR; + else { + /* + * create call without LOOKUP_OPEN is due + * to mknod of regular files. So use mknod + * operation. + */ + return v9fs_vfs_mknod_dotl(dir, dentry, omode, 0); + } name = (char *) dentry->d_name.name; P9_DPRINTK(P9_DEBUG_VFS, "v9fs_vfs_create_dotl: name:%s flags:0x%x " - "mode:0x%x\n", name, flags, mode); + "mode:0x%x\n", name, flags, omode); dfid = v9fs_fid_lookup(dentry->d_parent); if (IS_ERR(dfid)) { @@ -695,6 +707,15 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, int mode, } gid = v9fs_get_fsgid_for_create(dir); + + mode = omode; + /* Update mode based on ACL value */ + err = v9fs_acl_mode(dir, &mode, &dacl, &pacl); + if (err) { + P9_DPRINTK(P9_DEBUG_VFS, + "Failed to get acl values in creat %d\n", err); + goto error; + } err = p9_client_create_dotl(ofid, name, flags, mode, gid, &qid); if (err < 0) { P9_DPRINTK(P9_DEBUG_VFS, @@ -702,46 +723,52 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, int mode, err); goto error; } + /* instantiate inode and assign the unopened fid to the dentry */ + if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE || + (nd && nd->flags & LOOKUP_OPEN)) { + fid = p9_client_walk(dfid, 1, &name, 1); + if (IS_ERR(fid)) { + err = PTR_ERR(fid); + P9_DPRINTK(P9_DEBUG_VFS, "p9_client_walk failed %d\n", + err); + fid = NULL; + goto error; + } - /* No need to populate the inode if we are not opening the file AND - * not in cached mode. - */ - if (!v9ses->cache && !(nd && nd->flags & LOOKUP_OPEN)) { - /* Not in cached mode. No need to populate inode with stat */ - dentry->d_op = &v9fs_dentry_operations; - p9_client_clunk(ofid); - d_instantiate(dentry, NULL); - return 0; - } - - /* Now walk from the parent so we can get an unopened fid. */ - fid = p9_client_walk(dfid, 1, &name, 1); - if (IS_ERR(fid)) { - err = PTR_ERR(fid); - P9_DPRINTK(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err); - fid = NULL; - goto error; - } - - /* instantiate inode and assign the unopened fid to dentry */ - inode = v9fs_inode_from_fid(v9ses, fid, dir->i_sb); - if (IS_ERR(inode)) { - err = PTR_ERR(inode); - P9_DPRINTK(P9_DEBUG_VFS, "inode creation failed %d\n", err); - goto error; - } - if (v9ses->cache) + inode = v9fs_inode_from_fid(v9ses, fid, dir->i_sb); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + P9_DPRINTK(P9_DEBUG_VFS, "inode creation failed %d\n", + err); + goto error; + } dentry->d_op = &v9fs_cached_dentry_operations; - else + d_instantiate(dentry, inode); + err = v9fs_fid_add(dentry, fid); + if (err < 0) + goto error; + /* The fid would get clunked via a dput */ + fid = NULL; + } else { + /* + * Not in cached mode. No need to populate + * inode with stat. We need to get an inode + * so that we can set the acl with dentry + */ + inode = v9fs_get_inode(dir->i_sb, mode); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto error; + } dentry->d_op = &v9fs_dentry_operations; - d_instantiate(dentry, inode); - err = v9fs_fid_add(dentry, fid); - if (err < 0) - goto error; + d_instantiate(dentry, inode); + } + /* Now set the ACL based on the default value */ + v9fs_set_create_acl(dentry, dacl, pacl); /* if we are opening a file, assign the open fid to the file */ if (nd && nd->flags & LOOKUP_OPEN) { - filp = lookup_instantiate_filp(nd, dentry, v9fs_open_created); + filp = lookup_instantiate_filp(nd, dentry, generic_file_open); if (IS_ERR(filp)) { p9_client_clunk(ofid); return PTR_ERR(filp); @@ -800,7 +827,7 @@ v9fs_vfs_create(struct inode *dir, struct dentry *dentry, int mode, /* if we are opening a file, assign the open fid to the file */ if (nd && nd->flags & LOOKUP_OPEN) { - filp = lookup_instantiate_filp(nd, dentry, v9fs_open_created); + filp = lookup_instantiate_filp(nd, dentry, generic_file_open); if (IS_ERR(filp)) { err = PTR_ERR(filp); goto error; @@ -859,23 +886,28 @@ static int v9fs_vfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) * */ -static int v9fs_vfs_mkdir_dotl(struct inode *dir, struct dentry *dentry, - int mode) +static int v9fs_vfs_mkdir_dotl(struct inode *dir, + struct dentry *dentry, int omode) { int err; struct v9fs_session_info *v9ses; struct p9_fid *fid = NULL, *dfid = NULL; gid_t gid; char *name; + mode_t mode; struct inode *inode; struct p9_qid qid; struct dentry *dir_dentry; + struct posix_acl *dacl = NULL, *pacl = NULL; P9_DPRINTK(P9_DEBUG_VFS, "name %s\n", dentry->d_name.name); err = 0; v9ses = v9fs_inode2v9ses(dir); - mode |= S_IFDIR; + omode |= S_IFDIR; + if (dir->i_mode & S_ISGID) + omode |= S_ISGID; + dir_dentry = v9fs_dentry_from_dir_inode(dir); dfid = v9fs_fid_lookup(dir_dentry); if (IS_ERR(dfid)) { @@ -886,11 +918,14 @@ static int v9fs_vfs_mkdir_dotl(struct inode *dir, struct dentry *dentry, } gid = v9fs_get_fsgid_for_create(dir); - if (gid < 0) { - P9_DPRINTK(P9_DEBUG_VFS, "v9fs_get_fsgid_for_create failed\n"); + mode = omode; + /* Update mode based on ACL value */ + err = v9fs_acl_mode(dir, &mode, &dacl, &pacl); + if (err) { + P9_DPRINTK(P9_DEBUG_VFS, + "Failed to get acl values in mkdir %d\n", err); goto error; } - name = (char *) dentry->d_name.name; err = p9_client_mkdir_dotl(dfid, name, mode, gid, &qid); if (err < 0) @@ -920,7 +955,23 @@ static int v9fs_vfs_mkdir_dotl(struct inode *dir, struct dentry *dentry, if (err < 0) goto error; fid = NULL; + } else { + /* + * Not in cached mode. No need to populate + * inode with stat. We need to get an inode + * so that we can set the acl with dentry + */ + inode = v9fs_get_inode(dir->i_sb, mode); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto error; + } + dentry->d_op = &v9fs_dentry_operations; + d_instantiate(dentry, inode); } + /* Now set the ACL based on the default value */ + v9fs_set_create_acl(dentry, dacl, pacl); + error: if (fid) p9_client_clunk(fid); @@ -979,7 +1030,7 @@ static struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry, result = v9fs_fid_add(dentry, fid); if (result < 0) - goto error; + goto error_iput; inst_out: if (v9ses->cache) @@ -990,6 +1041,8 @@ inst_out: d_add(dentry, inode); return NULL; +error_iput: + iput(inode); error: p9_client_clunk(fid); @@ -1237,7 +1290,7 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr) * */ -static int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr) +int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr) { int retval; struct v9fs_session_info *v9ses; @@ -1279,6 +1332,12 @@ static int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr) setattr_copy(dentry->d_inode, iattr); mark_inode_dirty(dentry->d_inode); + if (iattr->ia_valid & ATTR_MODE) { + /* We also want to update ACL when we update mode bits */ + retval = v9fs_acl_chmod(dentry); + if (retval < 0) + return retval; + } return 0; } @@ -1473,7 +1532,7 @@ static int v9fs_readlink(struct dentry *dentry, char *buffer, int buflen) if (IS_ERR(fid)) return PTR_ERR(fid); - if (!v9fs_proto_dotu(v9ses) && !v9fs_proto_dotl(v9ses)) + if (!v9fs_proto_dotu(v9ses)) return -EBADF; st = p9_client_stat(fid); @@ -1616,11 +1675,6 @@ v9fs_vfs_symlink_dotl(struct inode *dir, struct dentry *dentry, gid = v9fs_get_fsgid_for_create(dir); - if (gid < 0) { - P9_DPRINTK(P9_DEBUG_VFS, "v9fs_get_egid failed %d\n", gid); - goto error; - } - /* Server doesn't alter fid on TSYMLINK. Hence no need to clone it. */ err = p9_client_symlink(dfid, name, (char *)symname, gid, &qid); @@ -1789,9 +1843,10 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir, kfree(st); } else { /* Caching disabled. No need to get upto date stat info. - * This dentry will be released immediately. So, just i_count++ + * This dentry will be released immediately. So, just hold the + * inode */ - atomic_inc(&old_dentry->d_inode->i_count); + ihold(old_dentry->d_inode); } dentry->d_op = old_dentry->d_op; @@ -1854,21 +1909,23 @@ v9fs_vfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t rdev) * */ static int -v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, int mode, +v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, int omode, dev_t rdev) { int err; char *name; + mode_t mode; struct v9fs_session_info *v9ses; struct p9_fid *fid = NULL, *dfid = NULL; struct inode *inode; gid_t gid; struct p9_qid qid; struct dentry *dir_dentry; + struct posix_acl *dacl = NULL, *pacl = NULL; P9_DPRINTK(P9_DEBUG_VFS, " %lu,%s mode: %x MAJOR: %u MINOR: %u\n", dir->i_ino, - dentry->d_name.name, mode, MAJOR(rdev), MINOR(rdev)); + dentry->d_name.name, omode, MAJOR(rdev), MINOR(rdev)); if (!new_valid_dev(rdev)) return -EINVAL; @@ -1884,11 +1941,14 @@ v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, int mode, } gid = v9fs_get_fsgid_for_create(dir); - if (gid < 0) { - P9_DPRINTK(P9_DEBUG_VFS, "v9fs_get_fsgid_for_create failed\n"); + mode = omode; + /* Update mode based on ACL value */ + err = v9fs_acl_mode(dir, &mode, &dacl, &pacl); + if (err) { + P9_DPRINTK(P9_DEBUG_VFS, + "Failed to get acl values in mknod %d\n", err); goto error; } - name = (char *) dentry->d_name.name; err = p9_client_mknod_dotl(dfid, name, mode, rdev, gid, &qid); @@ -1932,13 +1992,68 @@ v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, int mode, dentry->d_op = &v9fs_dentry_operations; d_instantiate(dentry, inode); } - + /* Now set the ACL based on the default value */ + v9fs_set_create_acl(dentry, dacl, pacl); error: if (fid) p9_client_clunk(fid); return err; } +static int +v9fs_vfs_readlink_dotl(struct dentry *dentry, char *buffer, int buflen) +{ + int retval; + struct p9_fid *fid; + char *target = NULL; + + P9_DPRINTK(P9_DEBUG_VFS, " %s\n", dentry->d_name.name); + retval = -EPERM; + fid = v9fs_fid_lookup(dentry); + if (IS_ERR(fid)) + return PTR_ERR(fid); + + retval = p9_client_readlink(fid, &target); + if (retval < 0) + return retval; + + strncpy(buffer, target, buflen); + P9_DPRINTK(P9_DEBUG_VFS, "%s -> %s\n", dentry->d_name.name, buffer); + + retval = strnlen(buffer, buflen); + return retval; +} + +/** + * v9fs_vfs_follow_link_dotl - follow a symlink path + * @dentry: dentry for symlink + * @nd: nameidata + * + */ + +static void * +v9fs_vfs_follow_link_dotl(struct dentry *dentry, struct nameidata *nd) +{ + int len = 0; + char *link = __getname(); + + P9_DPRINTK(P9_DEBUG_VFS, "%s n", dentry->d_name.name); + + if (!link) + link = ERR_PTR(-ENOMEM); + else { + len = v9fs_vfs_readlink_dotl(dentry, link, PATH_MAX); + if (len < 0) { + __putname(link); + link = ERR_PTR(len); + } else + link[min(len, PATH_MAX-1)] = 0; + } + nd_set_link(nd, link); + + return NULL; +} + static const struct inode_operations v9fs_dir_inode_operations_dotu = { .create = v9fs_vfs_create, .lookup = v9fs_vfs_lookup, @@ -1969,7 +2084,7 @@ static const struct inode_operations v9fs_dir_inode_operations_dotl = { .getxattr = generic_getxattr, .removexattr = generic_removexattr, .listxattr = v9fs_listxattr, - + .check_acl = v9fs_check_acl, }; static const struct inode_operations v9fs_dir_inode_operations = { @@ -1996,6 +2111,7 @@ static const struct inode_operations v9fs_file_inode_operations_dotl = { .getxattr = generic_getxattr, .removexattr = generic_removexattr, .listxattr = v9fs_listxattr, + .check_acl = v9fs_check_acl, }; static const struct inode_operations v9fs_symlink_inode_operations = { @@ -2007,8 +2123,8 @@ static const struct inode_operations v9fs_symlink_inode_operations = { }; static const struct inode_operations v9fs_symlink_inode_operations_dotl = { - .readlink = generic_readlink, - .follow_link = v9fs_vfs_follow_link, + .readlink = v9fs_vfs_readlink_dotl, + .follow_link = v9fs_vfs_follow_link_dotl, .put_link = v9fs_vfs_put_link, .getattr = v9fs_vfs_getattr_dotl, .setattr = v9fs_vfs_setattr_dotl, diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index 1d12ba0ed3db..c55c614500ad 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -39,6 +39,7 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/statfs.h> +#include <linux/magic.h> #include <net/9p/9p.h> #include <net/9p/client.h> @@ -46,6 +47,7 @@ #include "v9fs_vfs.h" #include "fid.h" #include "xattr.h" +#include "acl.h" static const struct super_operations v9fs_super_ops, v9fs_super_ops_dotl; @@ -66,7 +68,7 @@ static int v9fs_set_super(struct super_block *s, void *data) * v9fs_fill_super - populate superblock with info * @sb: superblock * @v9ses: session information - * @flags: flags propagated from v9fs_get_sb() + * @flags: flags propagated from v9fs_mount() * */ @@ -88,22 +90,25 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses, sb->s_flags = flags | MS_ACTIVE | MS_SYNCHRONOUS | MS_DIRSYNC | MS_NOATIME; +#ifdef CONFIG_9P_FS_POSIX_ACL + if ((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_CLIENT) + sb->s_flags |= MS_POSIXACL; +#endif + save_mount_options(sb, data); } /** - * v9fs_get_sb - mount a superblock + * v9fs_mount - mount a superblock * @fs_type: file system type * @flags: mount flags * @dev_name: device name that was mounted * @data: mount options - * @mnt: mountpoint record to be instantiated * */ -static int v9fs_get_sb(struct file_system_type *fs_type, int flags, - const char *dev_name, void *data, - struct vfsmount *mnt) +static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *data) { struct super_block *sb = NULL; struct inode *inode = NULL; @@ -117,7 +122,7 @@ static int v9fs_get_sb(struct file_system_type *fs_type, int flags, v9ses = kzalloc(sizeof(struct v9fs_session_info), GFP_KERNEL); if (!v9ses) - return -ENOMEM; + return ERR_PTR(-ENOMEM); fid = v9fs_session_init(v9ses, dev_name, data); if (IS_ERR(fid)) { @@ -149,7 +154,6 @@ static int v9fs_get_sb(struct file_system_type *fs_type, int flags, goto release_sb; } sb->s_root = root; - if (v9fs_proto_dotl(v9ses)) { struct p9_stat_dotl *st = NULL; st = p9_client_getattr_dotl(fid, P9_STATS_BASIC); @@ -174,19 +178,21 @@ static int v9fs_get_sb(struct file_system_type *fs_type, int flags, p9stat_free(st); kfree(st); } - + retval = v9fs_get_acl(inode, fid); + if (retval) + goto release_sb; v9fs_fid_add(root, fid); P9_DPRINTK(P9_DEBUG_VFS, " simple set mount, return 0\n"); - simple_set_mnt(mnt, sb); - return 0; + return dget(sb->s_root); clunk_fid: p9_client_clunk(fid); close_session: v9fs_session_close(v9ses); kfree(v9ses); - return retval; + return ERR_PTR(retval); + release_sb: /* * we will do the session_close and root dentry release @@ -196,7 +202,7 @@ release_sb: */ p9_client_clunk(fid); deactivate_locked_super(sb); - return retval; + return ERR_PTR(retval); } /** @@ -249,7 +255,7 @@ static int v9fs_statfs(struct dentry *dentry, struct kstatfs *buf) if (v9fs_proto_dotl(v9ses)) { res = p9_client_statfs(fid, &rs); if (res == 0) { - buf->f_type = rs.type; + buf->f_type = V9FS_MAGIC; buf->f_bsize = rs.bsize; buf->f_blocks = rs.blocks; buf->f_bfree = rs.bfree; @@ -292,7 +298,7 @@ static const struct super_operations v9fs_super_ops_dotl = { struct file_system_type v9fs_fs_type = { .name = "9p", - .get_sb = v9fs_get_sb, + .mount = v9fs_mount, .kill_sb = v9fs_kill_super, .owner = THIS_MODULE, .fs_flags = FS_RENAME_DOES_D_MOVE, diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c index f88e5c2dc873..43ec7df84336 100644 --- a/fs/9p/xattr.c +++ b/fs/9p/xattr.c @@ -21,30 +21,13 @@ #include "fid.h" #include "xattr.h" -/* - * v9fs_xattr_get() - * - * Copy an extended attribute into the buffer - * provided, or compute the buffer size required. - * Buffer is NULL to compute the size of the buffer required. - * - * Returns a negative error number on failure, or the number of bytes - * used / required on success. - */ -ssize_t v9fs_xattr_get(struct dentry *dentry, const char *name, - void *buffer, size_t buffer_size) +ssize_t v9fs_fid_xattr_get(struct p9_fid *fid, const char *name, + void *buffer, size_t buffer_size) { ssize_t retval; int msize, read_count; u64 offset = 0, attr_size; - struct p9_fid *fid, *attr_fid; - - P9_DPRINTK(P9_DEBUG_VFS, "%s: name = %s value_len = %zu\n", - __func__, name, buffer_size); - - fid = v9fs_fid_lookup(dentry); - if (IS_ERR(fid)) - return PTR_ERR(fid); + struct p9_fid *attr_fid; attr_fid = p9_client_xattrwalk(fid, name, &attr_size); if (IS_ERR(attr_fid)) { @@ -88,6 +71,31 @@ error: } + +/* + * v9fs_xattr_get() + * + * Copy an extended attribute into the buffer + * provided, or compute the buffer size required. + * Buffer is NULL to compute the size of the buffer required. + * + * Returns a negative error number on failure, or the number of bytes + * used / required on success. + */ +ssize_t v9fs_xattr_get(struct dentry *dentry, const char *name, + void *buffer, size_t buffer_size) +{ + struct p9_fid *fid; + + P9_DPRINTK(P9_DEBUG_VFS, "%s: name = %s value_len = %zu\n", + __func__, name, buffer_size); + fid = v9fs_fid_lookup(dentry); + if (IS_ERR(fid)) + return PTR_ERR(fid); + + return v9fs_fid_xattr_get(fid, name, buffer, buffer_size); +} + /* * v9fs_xattr_set() * @@ -156,5 +164,9 @@ ssize_t v9fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) const struct xattr_handler *v9fs_xattr_handlers[] = { &v9fs_xattr_user_handler, +#ifdef CONFIG_9P_FS_POSIX_ACL + &v9fs_xattr_acl_access_handler, + &v9fs_xattr_acl_default_handler, +#endif NULL }; diff --git a/fs/9p/xattr.h b/fs/9p/xattr.h index 9ddf672ae5c4..eaa837c53bd5 100644 --- a/fs/9p/xattr.h +++ b/fs/9p/xattr.h @@ -15,10 +15,16 @@ #define FS_9P_XATTR_H #include <linux/xattr.h> +#include <net/9p/9p.h> +#include <net/9p/client.h> extern const struct xattr_handler *v9fs_xattr_handlers[]; extern struct xattr_handler v9fs_xattr_user_handler; +extern const struct xattr_handler v9fs_xattr_acl_access_handler; +extern const struct xattr_handler v9fs_xattr_acl_default_handler; +extern ssize_t v9fs_fid_xattr_get(struct p9_fid *, const char *, + void *, size_t); extern ssize_t v9fs_xattr_get(struct dentry *, const char *, void *, size_t); extern int v9fs_xattr_set(struct dentry *, const char *, diff --git a/fs/Kconfig b/fs/Kconfig index 65781de44fc0..771f457402d4 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -47,10 +47,12 @@ source "fs/nilfs2/Kconfig" endif # BLOCK +config EXPORTFS + tristate + config FILE_LOCKING bool "Enable POSIX file locking API" if EMBEDDED default y - select BKL # while lockd still uses it. help This option enables standard file locking support, required for filesystems like NFS and for the flock() system @@ -60,7 +62,6 @@ source "fs/notify/Kconfig" source "fs/quota/Kconfig" -source "fs/autofs/Kconfig" source "fs/autofs4/Kconfig" source "fs/fuse/Kconfig" @@ -222,9 +223,6 @@ config LOCKD_V4 depends on FILE_LOCKING default y -config EXPORTFS - tristate - config NFS_ACL_SUPPORT tristate select FS_POSIX_ACL @@ -235,7 +233,6 @@ config NFS_COMMON default y source "net/sunrpc/Kconfig" -source "fs/smbfs/Kconfig" source "fs/ceph/Kconfig" source "fs/cifs/Kconfig" source "fs/ncpfs/Kconfig" diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index bb4cc5b8abc8..79e2ca7973b7 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -42,7 +42,7 @@ config BINFMT_ELF_FDPIC config CORE_DUMP_DEFAULT_ELF_HEADERS bool "Write ELF core dumps with partial segments" - default n + default y depends on BINFMT_ELF && ELF_CORE help ELF core dump files describe each memory mapping of the crashed @@ -60,7 +60,7 @@ config CORE_DUMP_DEFAULT_ELF_HEADERS inherited. See Documentation/filesystems/proc.txt for details. This config option changes the default setting of coredump_filter - seen at boot time. If unsure, say N. + seen at boot time. If unsure, say Y. config BINFMT_FLAT bool "Kernel support for flat binaries" diff --git a/fs/Makefile b/fs/Makefile index e6ec1d309b1d..a7f7cef0c0c8 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -29,10 +29,7 @@ obj-$(CONFIG_EVENTFD) += eventfd.o obj-$(CONFIG_AIO) += aio.o obj-$(CONFIG_FILE_LOCKING) += locks.o obj-$(CONFIG_COMPAT) += compat.o compat_ioctl.o - -nfsd-$(CONFIG_NFSD) := nfsctl.o -obj-y += $(nfsd-y) $(nfsd-m) - +obj-$(CONFIG_NFSD_DEPRECATED) += nfsctl.o obj-$(CONFIG_BINFMT_AOUT) += binfmt_aout.o obj-$(CONFIG_BINFMT_EM86) += binfmt_em86.o obj-$(CONFIG_BINFMT_MISC) += binfmt_misc.o @@ -91,7 +88,6 @@ obj-$(CONFIG_NFSD) += nfsd/ obj-$(CONFIG_LOCKD) += lockd/ obj-$(CONFIG_NLS) += nls/ obj-$(CONFIG_SYSV_FS) += sysv/ -obj-$(CONFIG_SMB_FS) += smbfs/ obj-$(CONFIG_CIFS) += cifs/ obj-$(CONFIG_NCP_FS) += ncpfs/ obj-$(CONFIG_HPFS_FS) += hpfs/ @@ -104,7 +100,6 @@ obj-$(CONFIG_UBIFS_FS) += ubifs/ obj-$(CONFIG_AFFS_FS) += affs/ obj-$(CONFIG_ROMFS_FS) += romfs/ obj-$(CONFIG_QNX4FS_FS) += qnx4/ -obj-$(CONFIG_AUTOFS_FS) += autofs/ obj-$(CONFIG_AUTOFS4_FS) += autofs4/ obj-$(CONFIG_ADFS_FS) += adfs/ obj-$(CONFIG_FUSE_FS) += fuse/ diff --git a/fs/adfs/super.c b/fs/adfs/super.c index d9803f73236f..959dbff2d42d 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -490,17 +490,16 @@ error: return -EINVAL; } -static int adfs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *adfs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, adfs_fill_super, - mnt); + return mount_bdev(fs_type, flags, dev_name, data, adfs_fill_super); } static struct file_system_type adfs_fs_type = { .owner = THIS_MODULE, .name = "adfs", - .get_sb = adfs_get_sb, + .mount = adfs_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/affs/file.c b/fs/affs/file.c index c4a9875bd1a6..0a90dcd46de2 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -894,9 +894,9 @@ affs_truncate(struct inode *inode) if (AFFS_SB(sb)->s_flags & SF_OFS) { struct buffer_head *bh = affs_bread_ino(inode, last_blk, 0); u32 tmp; - if (IS_ERR(ext_bh)) { + if (IS_ERR(bh)) { affs_warning(sb, "truncate", "unexpected read error for last block %u (%d)", - ext, PTR_ERR(ext_bh)); + ext, PTR_ERR(bh)); return; } tmp = be32_to_cpu(AFFS_DATA_HEAD(bh)->next); diff --git a/fs/affs/inode.c b/fs/affs/inode.c index 3a0fdec175ba..5d828903ac69 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -388,7 +388,7 @@ affs_add_entry(struct inode *dir, struct inode *inode, struct dentry *dentry, s3 affs_adjust_checksum(inode_bh, block - be32_to_cpu(chain)); mark_buffer_dirty_inode(inode_bh, inode); inode->i_nlink = 2; - atomic_inc(&inode->i_count); + ihold(inode); } affs_fix_checksum(sb, bh); mark_buffer_dirty_inode(bh, inode); diff --git a/fs/affs/super.c b/fs/affs/super.c index fa4fbe1e238a..0cf7f4384cbd 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -573,17 +573,16 @@ affs_statfs(struct dentry *dentry, struct kstatfs *buf) return 0; } -static int affs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *affs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, affs_fill_super, - mnt); + return mount_bdev(fs_type, flags, dev_name, data, affs_fill_super); } static struct file_system_type affs_fs_type = { .owner = THIS_MODULE, .name = "affs", - .get_sb = affs_get_sb, + .mount = affs_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 0d38c09bd55e..5439e1bc9a86 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -1045,7 +1045,7 @@ static int afs_link(struct dentry *from, struct inode *dir, if (ret < 0) goto link_error; - atomic_inc(&vnode->vfs_inode.i_count); + ihold(&vnode->vfs_inode); d_instantiate(dentry, &vnode->vfs_inode); key_put(key); _leave(" = 0"); diff --git a/fs/afs/super.c b/fs/afs/super.c index eacf76d98ae0..27201cffece4 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -29,9 +29,8 @@ #define AFS_FS_MAGIC 0x6B414653 /* 'kAFS' */ static void afs_i_init_once(void *foo); -static int afs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, - void *data, struct vfsmount *mnt); +static struct dentry *afs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data); static struct inode *afs_alloc_inode(struct super_block *sb); static void afs_put_super(struct super_block *sb); static void afs_destroy_inode(struct inode *inode); @@ -40,7 +39,7 @@ static int afs_statfs(struct dentry *dentry, struct kstatfs *buf); struct file_system_type afs_fs_type = { .owner = THIS_MODULE, .name = "afs", - .get_sb = afs_get_sb, + .mount = afs_mount, .kill_sb = kill_anon_super, .fs_flags = 0, }; @@ -359,11 +358,8 @@ error: /* * get an AFS superblock */ -static int afs_get_sb(struct file_system_type *fs_type, - int flags, - const char *dev_name, - void *options, - struct vfsmount *mnt) +static struct dentry *afs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *options) { struct afs_mount_params params; struct super_block *sb; @@ -427,12 +423,11 @@ static int afs_get_sb(struct file_system_type *fs_type, ASSERTCMP(sb->s_flags, &, MS_ACTIVE); } - simple_set_mnt(mnt, sb); afs_put_volume(params.volume); afs_put_cell(params.cell); kfree(new_opts); _leave(" = 0 [%p]", sb); - return 0; + return dget(sb->s_root); error: afs_put_volume(params.volume); @@ -440,7 +435,7 @@ error: key_put(params.key); kfree(new_opts); _leave(" = %d", ret); - return ret; + return ERR_PTR(ret); } /* diff --git a/fs/afs/write.c b/fs/afs/write.c index 722743b152d8..15690bb1d3b5 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -438,7 +438,6 @@ no_more: */ int afs_writepage(struct page *page, struct writeback_control *wbc) { - struct backing_dev_info *bdi = page->mapping->backing_dev_info; struct afs_writeback *wb; int ret; @@ -455,8 +454,6 @@ int afs_writepage(struct page *page, struct writeback_control *wbc) } wbc->nr_to_write -= ret; - if (wbc->nonblocking && bdi_write_congested(bdi)) - wbc->encountered_congestion = 1; _leave(" = 0"); return 0; @@ -469,7 +466,6 @@ static int afs_writepages_region(struct address_space *mapping, struct writeback_control *wbc, pgoff_t index, pgoff_t end, pgoff_t *_next) { - struct backing_dev_info *bdi = mapping->backing_dev_info; struct afs_writeback *wb; struct page *page; int ret, n; @@ -529,11 +525,6 @@ static int afs_writepages_region(struct address_space *mapping, wbc->nr_to_write -= ret; - if (wbc->nonblocking && bdi_write_congested(bdi)) { - wbc->encountered_congestion = 1; - break; - } - cond_resched(); } while (index < end && wbc->nr_to_write > 0); @@ -548,24 +539,16 @@ static int afs_writepages_region(struct address_space *mapping, int afs_writepages(struct address_space *mapping, struct writeback_control *wbc) { - struct backing_dev_info *bdi = mapping->backing_dev_info; pgoff_t start, end, next; int ret; _enter(""); - if (wbc->nonblocking && bdi_write_congested(bdi)) { - wbc->encountered_congestion = 1; - _leave(" = 0 [congest]"); - return 0; - } - if (wbc->range_cyclic) { start = mapping->writeback_index; end = -1; ret = afs_writepages_region(mapping, wbc, start, end, &next); - if (start > 0 && wbc->nr_to_write > 0 && ret == 0 && - !(wbc->nonblocking && wbc->encountered_congestion)) + if (start > 0 && wbc->nr_to_write > 0 && ret == 0) ret = afs_writepages_region(mapping, wbc, 0, start, &next); mapping->writeback_index = next; @@ -1543,7 +1543,19 @@ static void aio_batch_add(struct address_space *mapping, } abe = mempool_alloc(abe_pool, GFP_KERNEL); - BUG_ON(!igrab(mapping->host)); + + /* + * we should be using igrab here, but + * we don't want to hammer on the global + * inode spinlock just to take an extra + * reference on a file that we must already + * have a reference to. + * + * When we're called, we always have a reference + * on the file, so we must always have a reference + * on the inode, so ihold() is safe here. + */ + ihold(mapping->host); abe->mapping = mapping; hlist_add_head(&abe->list, &batch_hash[bucket]); return; diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index e4b75d6eda83..57ce55b2564c 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -26,12 +26,10 @@ static struct vfsmount *anon_inode_mnt __read_mostly; static struct inode *anon_inode_inode; static const struct file_operations anon_inode_fops; -static int anon_inodefs_get_sb(struct file_system_type *fs_type, int flags, - const char *dev_name, void *data, - struct vfsmount *mnt) +static struct dentry *anon_inodefs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_pseudo(fs_type, "anon_inode:", NULL, ANON_INODE_FS_MAGIC, - mnt); + return mount_pseudo(fs_type, "anon_inode:", NULL, ANON_INODE_FS_MAGIC); } /* @@ -45,7 +43,7 @@ static char *anon_inodefs_dname(struct dentry *dentry, char *buffer, int buflen) static struct file_system_type anon_inode_fs_type = { .name = "anon_inodefs", - .get_sb = anon_inodefs_get_sb, + .mount = anon_inodefs_mount, .kill_sb = kill_anon_super, }; static const struct dentry_operations anon_inodefs_dentry_operations = { @@ -111,10 +109,9 @@ struct file *anon_inode_getfile(const char *name, path.mnt = mntget(anon_inode_mnt); /* * We know the anon_inode inode count is always greater than zero, - * so we can avoid doing an igrab() and we can use an open-coded - * atomic_inc(). + * so ihold() is safe. */ - atomic_inc(&anon_inode_inode->i_count); + ihold(anon_inode_inode); path.dentry->d_op = &anon_inodefs_dentry_operations; d_instantiate(path.dentry, anon_inode_inode); @@ -194,6 +191,7 @@ static struct inode *anon_inode_mkinode(void) if (!inode) return ERR_PTR(-ENOMEM); + inode->i_ino = get_next_ino(); inode->i_fop = &anon_inode_fops; inode->i_mapping->a_ops = &anon_aops; diff --git a/fs/autofs4/init.c b/fs/autofs4/init.c index 9722e4bd8957..c038727b4050 100644 --- a/fs/autofs4/init.c +++ b/fs/autofs4/init.c @@ -14,16 +14,16 @@ #include <linux/init.h> #include "autofs_i.h" -static int autofs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *autofs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_nodev(fs_type, flags, data, autofs4_fill_super, mnt); + return mount_nodev(fs_type, flags, data, autofs4_fill_super); } static struct file_system_type autofs_fs_type = { .owner = THIS_MODULE, .name = "autofs", - .get_sb = autofs_get_sb, + .mount = autofs_mount, .kill_sb = autofs4_kill_sb, }; diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c index 821b2b955dac..ac87e49fa706 100644 --- a/fs/autofs4/inode.c +++ b/fs/autofs4/inode.c @@ -398,6 +398,7 @@ struct inode *autofs4_get_inode(struct super_block *sb, inode->i_gid = sb->s_root->d_inode->i_gid; } inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; + inode->i_ino = get_next_ino(); if (S_ISDIR(inf->mode)) { inode->i_nlink = 2; diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index d5c1401f0031..d34896cfb19f 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -980,19 +980,11 @@ static int autofs4_root_ioctl_unlocked(struct inode *inode, struct file *filp, } } -static DEFINE_MUTEX(autofs4_ioctl_mutex); - static long autofs4_root_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { - long ret; struct inode *inode = filp->f_dentry->d_inode; - - mutex_lock(&autofs4_ioctl_mutex); - ret = autofs4_root_ioctl_unlocked(inode, filp, cmd, arg); - mutex_unlock(&autofs4_ioctl_mutex); - - return ret; + return autofs4_root_ioctl_unlocked(inode, filp, cmd, arg); } #ifdef CONFIG_COMPAT @@ -1002,13 +994,11 @@ static long autofs4_root_compat_ioctl(struct file *filp, struct inode *inode = filp->f_path.dentry->d_inode; int ret; - mutex_lock(&autofs4_ioctl_mutex); if (cmd == AUTOFS_IOC_READY || cmd == AUTOFS_IOC_FAIL) ret = autofs4_root_ioctl_unlocked(inode, filp, cmd, arg); else ret = autofs4_root_ioctl_unlocked(inode, filp, cmd, (unsigned long)compat_ptr(arg)); - mutex_unlock(&autofs4_ioctl_mutex); return ret; } diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index dc39d2824885..aa4e7c7ae3c6 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -913,18 +913,17 @@ befs_statfs(struct dentry *dentry, struct kstatfs *buf) return 0; } -static int -befs_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, - void *data, struct vfsmount *mnt) +static struct dentry * +befs_mount(struct file_system_type *fs_type, int flags, const char *dev_name, + void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, befs_fill_super, - mnt); + return mount_bdev(fs_type, flags, dev_name, data, befs_fill_super); } static struct file_system_type befs_fs_type = { .owner = THIS_MODULE, .name = "befs", - .get_sb = befs_get_sb, + .mount = befs_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c index d967e052b779..685ecff3ab31 100644 --- a/fs/bfs/dir.c +++ b/fs/bfs/dir.c @@ -176,7 +176,7 @@ static int bfs_link(struct dentry *old, struct inode *dir, inc_nlink(inode); inode->i_ctime = CURRENT_TIME_SEC; mark_inode_dirty(inode); - atomic_inc(&inode->i_count); + ihold(inode); d_instantiate(new, inode); mutex_unlock(&info->bfs_lock); return 0; diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index 883e77acd5a8..76db6d7d49bb 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -450,16 +450,16 @@ out: return ret; } -static int bfs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *bfs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, bfs_fill_super, mnt); + return mount_bdev(fs_type, flags, dev_name, data, bfs_fill_super); } static struct file_system_type bfs_fs_type = { .owner = THIS_MODULE, .name = "bfs", - .get_sb = bfs_get_sb, + .mount = bfs_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 139fc8083f53..1befe2ec8186 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -495,6 +495,7 @@ static struct inode *bm_get_inode(struct super_block *sb, int mode) struct inode * inode = new_inode(sb); if (inode) { + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_atime = inode->i_mtime = inode->i_ctime = current_fs_time(inode->i_sb); @@ -705,10 +706,10 @@ static int bm_fill_super(struct super_block * sb, void * data, int silent) return err; } -static int bm_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *bm_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_single(fs_type, flags, data, bm_fill_super, mnt); + return mount_single(fs_type, flags, data, bm_fill_super); } static struct linux_binfmt misc_format = { @@ -719,7 +720,7 @@ static struct linux_binfmt misc_format = { static struct file_system_type bm_fs_type = { .owner = THIS_MODULE, .name = "binfmt_misc", - .get_sb = bm_get_sb, + .mount = bm_mount, .kill_sb = kill_litter_super, }; @@ -370,6 +370,9 @@ struct bio *bio_kmalloc(gfp_t gfp_mask, int nr_iovecs) { struct bio *bio; + if (nr_iovecs > UIO_MAXIOV) + return NULL; + bio = kmalloc(sizeof(struct bio) + nr_iovecs * sizeof(struct bio_vec), gfp_mask); if (unlikely(!bio)) @@ -697,8 +700,12 @@ static void bio_free_map_data(struct bio_map_data *bmd) static struct bio_map_data *bio_alloc_map_data(int nr_segs, int iov_count, gfp_t gfp_mask) { - struct bio_map_data *bmd = kmalloc(sizeof(*bmd), gfp_mask); + struct bio_map_data *bmd; + if (iov_count > UIO_MAXIOV) + return NULL; + + bmd = kmalloc(sizeof(*bmd), gfp_mask); if (!bmd) return NULL; @@ -827,6 +834,12 @@ struct bio *bio_copy_user_iov(struct request_queue *q, end = (uaddr + iov[i].iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT; start = uaddr >> PAGE_SHIFT; + /* + * Overflow, abort + */ + if (end < start) + return ERR_PTR(-EINVAL); + nr_pages += end - start; len += iov[i].iov_len; } @@ -955,6 +968,12 @@ static struct bio *__bio_map_user_iov(struct request_queue *q, unsigned long end = (uaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT; unsigned long start = uaddr >> PAGE_SHIFT; + /* + * Overflow, abort + */ + if (end < start) + return ERR_PTR(-EINVAL); + nr_pages += end - start; /* * buffer must be aligned to at least hardsector size for now @@ -982,7 +1001,7 @@ static struct bio *__bio_map_user_iov(struct request_queue *q, unsigned long start = uaddr >> PAGE_SHIFT; const int local_nr_pages = end - start; const int page_limit = cur_page + local_nr_pages; - + ret = get_user_pages_fast(uaddr, local_nr_pages, write_to_vm, &pages[cur_page]); if (ret < local_nr_pages) { diff --git a/fs/block_dev.c b/fs/block_dev.c index b737451e2e9d..4230252fd689 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -11,7 +11,6 @@ #include <linux/slab.h> #include <linux/kmod.h> #include <linux/major.h> -#include <linux/smp_lock.h> #include <linux/device_cgroup.h> #include <linux/highmem.h> #include <linux/blkdev.h> @@ -48,6 +47,21 @@ inline struct block_device *I_BDEV(struct inode *inode) EXPORT_SYMBOL(I_BDEV); +/* + * move the inode from it's current bdi to the a new bdi. if the inode is dirty + * we need to move it onto the dirty list of @dst so that the inode is always + * on the right list. + */ +static void bdev_inode_switch_bdi(struct inode *inode, + struct backing_dev_info *dst) +{ + spin_lock(&inode_lock); + inode->i_data.backing_dev_info = dst; + if (inode->i_state & I_DIRTY) + list_move(&inode->i_wb_list, &dst->wb.b_dirty); + spin_unlock(&inode_lock); +} + static sector_t max_block(struct block_device *bdev) { sector_t retval = ~((sector_t)0); @@ -449,15 +463,15 @@ static const struct super_operations bdev_sops = { .evict_inode = bdev_evict_inode, }; -static int bd_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *bd_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_pseudo(fs_type, "bdev:", &bdev_sops, 0x62646576, mnt); + return mount_pseudo(fs_type, "bdev:", &bdev_sops, 0x62646576); } static struct file_system_type bd_type = { .name = "bdev", - .get_sb = bd_get_sb, + .mount = bd_mount, .kill_sb = kill_anon_super, }; @@ -550,7 +564,7 @@ EXPORT_SYMBOL(bdget); */ struct block_device *bdgrab(struct block_device *bdev) { - atomic_inc(&bdev->bd_inode->i_count); + ihold(bdev->bd_inode); return bdev; } @@ -580,7 +594,7 @@ static struct block_device *bd_acquire(struct inode *inode) spin_lock(&bdev_lock); bdev = inode->i_bdev; if (bdev) { - atomic_inc(&bdev->bd_inode->i_count); + ihold(bdev->bd_inode); spin_unlock(&bdev_lock); return bdev; } @@ -591,12 +605,12 @@ static struct block_device *bd_acquire(struct inode *inode) spin_lock(&bdev_lock); if (!inode->i_bdev) { /* - * We take an additional bd_inode->i_count for inode, + * We take an additional reference to bd_inode, * and it's released in clear_inode() of inode. * So, we can access it via ->i_mapping always * without igrab(). */ - atomic_inc(&bdev->bd_inode->i_count); + ihold(bdev->bd_inode); inode->i_bdev = bdev; inode->i_mapping = bdev->bd_inode->i_mapping; list_add(&inode->i_devices, &bdev->bd_inodes); @@ -1390,7 +1404,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) bdi = blk_get_backing_dev_info(bdev); if (bdi == NULL) bdi = &default_backing_dev_info; - bdev->bd_inode->i_data.backing_dev_info = bdi; + bdev_inode_switch_bdi(bdev->bd_inode, bdi); } if (bdev->bd_invalidated) rescan_partitions(disk, bdev); @@ -1405,8 +1419,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) if (ret) goto out_clear; bdev->bd_contains = whole; - bdev->bd_inode->i_data.backing_dev_info = - whole->bd_inode->i_data.backing_dev_info; + bdev_inode_switch_bdi(bdev->bd_inode, + whole->bd_inode->i_data.backing_dev_info); bdev->bd_part = disk_get_part(disk, partno); if (!(disk->flags & GENHD_FL_UP) || !bdev->bd_part || !bdev->bd_part->nr_sects) { @@ -1439,7 +1453,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) disk_put_part(bdev->bd_part); bdev->bd_disk = NULL; bdev->bd_part = NULL; - bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info; + bdev_inode_switch_bdi(bdev->bd_inode, &default_backing_dev_info); if (bdev != bdev->bd_contains) __blkdev_put(bdev->bd_contains, mode, 1); bdev->bd_contains = NULL; @@ -1533,7 +1547,8 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) disk_put_part(bdev->bd_part); bdev->bd_part = NULL; bdev->bd_disk = NULL; - bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info; + bdev_inode_switch_bdi(bdev->bd_inode, + &default_backing_dev_info); if (bdev != bdev->bd_contains) victim = bdev->bd_contains; bdev->bd_contains = NULL; diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 396039b3a8a2..b50bc4bd5c56 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -91,23 +91,10 @@ static inline int compressed_bio_size(struct btrfs_root *root, static struct bio *compressed_bio_alloc(struct block_device *bdev, u64 first_byte, gfp_t gfp_flags) { - struct bio *bio; int nr_vecs; nr_vecs = bio_get_nr_vecs(bdev); - bio = bio_alloc(gfp_flags, nr_vecs); - - if (bio == NULL && (current->flags & PF_MEMALLOC)) { - while (!bio && (nr_vecs /= 2)) - bio = bio_alloc(gfp_flags, nr_vecs); - } - - if (bio) { - bio->bi_size = 0; - bio->bi_bdev = bdev; - bio->bi_sector = first_byte >> 9; - } - return bio; + return btrfs_bio_alloc(bdev, first_byte >> 9, nr_vecs, gfp_flags); } static int check_compressed_csum(struct inode *inode, @@ -163,7 +150,6 @@ fail: */ static void end_compressed_bio_read(struct bio *bio, int err) { - struct extent_io_tree *tree; struct compressed_bio *cb = bio->bi_private; struct inode *inode; struct page *page; @@ -187,7 +173,6 @@ static void end_compressed_bio_read(struct bio *bio, int err) /* ok, we're the last bio for this extent, lets start * the decompression. */ - tree = &BTRFS_I(inode)->io_tree; ret = btrfs_zlib_decompress_biovec(cb->compressed_pages, cb->start, cb->orig_bio->bi_io_vec, diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index c3df14ce2cc2..9ac171599258 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -200,7 +200,6 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, struct extent_buffer **cow_ret, u64 new_root_objectid) { struct extent_buffer *cow; - u32 nritems; int ret = 0; int level; struct btrfs_disk_key disk_key; @@ -210,7 +209,6 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, WARN_ON(root->ref_cows && trans->transid != root->last_trans); level = btrfs_header_level(buf); - nritems = btrfs_header_nritems(buf); if (level == 0) btrfs_item_key(buf, &disk_key, 0); else @@ -1008,7 +1006,6 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, int wret; int pslot; int orig_slot = path->slots[level]; - int err_on_enospc = 0; u64 orig_ptr; if (level == 0) @@ -1071,8 +1068,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, BTRFS_NODEPTRS_PER_BLOCK(root) / 4) return 0; - if (btrfs_header_nritems(mid) < 2) - err_on_enospc = 1; + btrfs_header_nritems(mid); left = read_node_slot(root, parent, pslot - 1); if (left) { @@ -1103,8 +1099,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, wret = push_node_left(trans, root, left, mid, 1); if (wret < 0) ret = wret; - if (btrfs_header_nritems(mid) < 2) - err_on_enospc = 1; + btrfs_header_nritems(mid); } /* @@ -1224,14 +1219,12 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans, int wret; int pslot; int orig_slot = path->slots[level]; - u64 orig_ptr; if (level == 0) return 1; mid = path->nodes[level]; WARN_ON(btrfs_header_generation(mid) != trans->transid); - orig_ptr = btrfs_node_blockptr(mid, orig_slot); if (level < BTRFS_MAX_LEVEL - 1) parent = path->nodes[level + 1]; @@ -1577,13 +1570,33 @@ read_block_for_search(struct btrfs_trans_handle *trans, blocksize = btrfs_level_size(root, level - 1); tmp = btrfs_find_tree_block(root, blocknr, blocksize); - if (tmp && btrfs_buffer_uptodate(tmp, gen)) { - /* - * we found an up to date block without sleeping, return - * right away - */ - *eb_ret = tmp; - return 0; + if (tmp) { + if (btrfs_buffer_uptodate(tmp, 0)) { + if (btrfs_buffer_uptodate(tmp, gen)) { + /* + * we found an up to date block without + * sleeping, return + * right away + */ + *eb_ret = tmp; + return 0; + } + /* the pages were up to date, but we failed + * the generation number check. Do a full + * read for the generation number that is correct. + * We must do this without dropping locks so + * we can trust our generation number + */ + free_extent_buffer(tmp); + tmp = read_tree_block(root, blocknr, blocksize, gen); + if (tmp && btrfs_buffer_uptodate(tmp, gen)) { + *eb_ret = tmp; + return 0; + } + free_extent_buffer(tmp); + btrfs_release_path(NULL, p); + return -EIO; + } } /* @@ -1596,8 +1609,7 @@ read_block_for_search(struct btrfs_trans_handle *trans, btrfs_unlock_up_safe(p, level + 1); btrfs_set_path_blocking(p); - if (tmp) - free_extent_buffer(tmp); + free_extent_buffer(tmp); if (p->reada) reada_for_search(root, p, level, slot, key->objectid); @@ -2548,7 +2560,6 @@ static noinline int __push_leaf_left(struct btrfs_trans_handle *trans, { struct btrfs_disk_key disk_key; struct extent_buffer *right = path->nodes[0]; - int slot; int i; int push_space = 0; int push_items = 0; @@ -2560,8 +2571,6 @@ static noinline int __push_leaf_left(struct btrfs_trans_handle *trans, u32 this_item_size; u32 old_left_item_size; - slot = path->slots[1]; - if (empty) nr = min(right_nritems, max_slot); else @@ -3330,7 +3339,6 @@ int btrfs_truncate_item(struct btrfs_trans_handle *trans, { int ret = 0; int slot; - int slot_orig; struct extent_buffer *leaf; struct btrfs_item *item; u32 nritems; @@ -3340,7 +3348,6 @@ int btrfs_truncate_item(struct btrfs_trans_handle *trans, unsigned int size_diff; int i; - slot_orig = path->slots[0]; leaf = path->nodes[0]; slot = path->slots[0]; @@ -3445,7 +3452,6 @@ int btrfs_extend_item(struct btrfs_trans_handle *trans, { int ret = 0; int slot; - int slot_orig; struct extent_buffer *leaf; struct btrfs_item *item; u32 nritems; @@ -3454,7 +3460,6 @@ int btrfs_extend_item(struct btrfs_trans_handle *trans, unsigned int old_size; int i; - slot_orig = path->slots[0]; leaf = path->nodes[0]; nritems = btrfs_header_nritems(leaf); @@ -3787,7 +3792,6 @@ int btrfs_insert_empty_items(struct btrfs_trans_handle *trans, struct btrfs_key *cpu_key, u32 *data_size, int nr) { - struct extent_buffer *leaf; int ret = 0; int slot; int i; @@ -3804,7 +3808,6 @@ int btrfs_insert_empty_items(struct btrfs_trans_handle *trans, if (ret < 0) goto out; - leaf = path->nodes[0]; slot = path->slots[0]; BUG_ON(slot < 0); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index eaf286abad17..af52f6d7a4d8 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -99,6 +99,9 @@ struct btrfs_ordered_sum; */ #define BTRFS_EXTENT_CSUM_OBJECTID -10ULL +/* For storing free space cache */ +#define BTRFS_FREE_SPACE_OBJECTID -11ULL + /* dummy objectid represents multiple objectids */ #define BTRFS_MULTIPLE_OBJECTIDS -255ULL @@ -265,6 +268,22 @@ struct btrfs_chunk { /* additional stripes go here */ } __attribute__ ((__packed__)); +#define BTRFS_FREE_SPACE_EXTENT 1 +#define BTRFS_FREE_SPACE_BITMAP 2 + +struct btrfs_free_space_entry { + __le64 offset; + __le64 bytes; + u8 type; +} __attribute__ ((__packed__)); + +struct btrfs_free_space_header { + struct btrfs_disk_key location; + __le64 generation; + __le64 num_entries; + __le64 num_bitmaps; +} __attribute__ ((__packed__)); + static inline unsigned long btrfs_chunk_item_size(int num_stripes) { BUG_ON(num_stripes == 0); @@ -365,8 +384,10 @@ struct btrfs_super_block { char label[BTRFS_LABEL_SIZE]; + __le64 cache_generation; + /* future expansion */ - __le64 reserved[32]; + __le64 reserved[31]; u8 sys_chunk_array[BTRFS_SYSTEM_CHUNK_ARRAY_SIZE]; } __attribute__ ((__packed__)); @@ -375,13 +396,15 @@ struct btrfs_super_block { * ones specified below then we will fail to mount */ #define BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF (1ULL << 0) -#define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL (2ULL << 0) +#define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL (1ULL << 1) +#define BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS (1ULL << 2) #define BTRFS_FEATURE_COMPAT_SUPP 0ULL #define BTRFS_FEATURE_COMPAT_RO_SUPP 0ULL -#define BTRFS_FEATURE_INCOMPAT_SUPP \ - (BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF | \ - BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL) +#define BTRFS_FEATURE_INCOMPAT_SUPP \ + (BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF | \ + BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL | \ + BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) /* * A leaf is full of items. offset and size tell us where to find @@ -675,7 +698,8 @@ struct btrfs_block_group_item { struct btrfs_space_info { u64 flags; - u64 total_bytes; /* total bytes in the space */ + u64 total_bytes; /* total bytes in the space, + this doesn't take mirrors into account */ u64 bytes_used; /* total bytes used, this does't take mirrors into account */ u64 bytes_pinned; /* total bytes pinned, will be freed when the @@ -687,6 +711,8 @@ struct btrfs_space_info { u64 bytes_may_use; /* number of bytes that may be used for delalloc/allocations */ u64 disk_used; /* total bytes used on disk */ + u64 disk_total; /* total bytes on disk, takes mirrors into + account */ int full; /* indicates that we cannot allocate any more chunks for this space */ @@ -750,6 +776,14 @@ enum btrfs_caching_type { BTRFS_CACHE_FINISHED = 2, }; +enum btrfs_disk_cache_state { + BTRFS_DC_WRITTEN = 0, + BTRFS_DC_ERROR = 1, + BTRFS_DC_CLEAR = 2, + BTRFS_DC_SETUP = 3, + BTRFS_DC_NEED_WRITE = 4, +}; + struct btrfs_caching_control { struct list_head list; struct mutex mutex; @@ -763,6 +797,7 @@ struct btrfs_block_group_cache { struct btrfs_key key; struct btrfs_block_group_item item; struct btrfs_fs_info *fs_info; + struct inode *inode; spinlock_t lock; u64 pinned; u64 reserved; @@ -773,8 +808,11 @@ struct btrfs_block_group_cache { int extents_thresh; int free_extents; int total_bitmaps; - int ro; - int dirty; + unsigned int ro:1; + unsigned int dirty:1; + unsigned int iref:1; + + int disk_cache_state; /* cache tracking stuff */ int cached; @@ -863,6 +901,7 @@ struct btrfs_fs_info { struct btrfs_transaction *running_transaction; wait_queue_head_t transaction_throttle; wait_queue_head_t transaction_wait; + wait_queue_head_t transaction_blocked_wait; wait_queue_head_t async_submit_wait; struct btrfs_super_block super_copy; @@ -949,6 +988,7 @@ struct btrfs_fs_info { struct btrfs_workers endio_meta_workers; struct btrfs_workers endio_meta_write_workers; struct btrfs_workers endio_write_workers; + struct btrfs_workers endio_freespace_worker; struct btrfs_workers submit_workers; /* * fixup workers take dirty pages that didn't properly go through @@ -1192,6 +1232,9 @@ struct btrfs_root { #define BTRFS_MOUNT_NOSSD (1 << 9) #define BTRFS_MOUNT_DISCARD (1 << 10) #define BTRFS_MOUNT_FORCE_COMPRESS (1 << 11) +#define BTRFS_MOUNT_SPACE_CACHE (1 << 12) +#define BTRFS_MOUNT_CLEAR_CACHE (1 << 13) +#define BTRFS_MOUNT_USER_SUBVOL_RM_ALLOWED (1 << 14) #define btrfs_clear_opt(o, opt) ((o) &= ~BTRFS_MOUNT_##opt) #define btrfs_set_opt(o, opt) ((o) |= BTRFS_MOUNT_##opt) @@ -1665,6 +1708,27 @@ static inline void btrfs_set_dir_item_key(struct extent_buffer *eb, write_eb_member(eb, item, struct btrfs_dir_item, location, key); } +BTRFS_SETGET_FUNCS(free_space_entries, struct btrfs_free_space_header, + num_entries, 64); +BTRFS_SETGET_FUNCS(free_space_bitmaps, struct btrfs_free_space_header, + num_bitmaps, 64); +BTRFS_SETGET_FUNCS(free_space_generation, struct btrfs_free_space_header, + generation, 64); + +static inline void btrfs_free_space_key(struct extent_buffer *eb, + struct btrfs_free_space_header *h, + struct btrfs_disk_key *key) +{ + read_eb_member(eb, h, struct btrfs_free_space_header, location, key); +} + +static inline void btrfs_set_free_space_key(struct extent_buffer *eb, + struct btrfs_free_space_header *h, + struct btrfs_disk_key *key) +{ + write_eb_member(eb, h, struct btrfs_free_space_header, location, key); +} + /* struct btrfs_disk_key */ BTRFS_SETGET_STACK_FUNCS(disk_key_objectid, struct btrfs_disk_key, objectid, 64); @@ -1876,6 +1940,8 @@ BTRFS_SETGET_STACK_FUNCS(super_incompat_flags, struct btrfs_super_block, incompat_flags, 64); BTRFS_SETGET_STACK_FUNCS(super_csum_type, struct btrfs_super_block, csum_type, 16); +BTRFS_SETGET_STACK_FUNCS(super_cache_generation, struct btrfs_super_block, + cache_generation, 64); static inline int btrfs_super_csum_size(struct btrfs_super_block *s) { @@ -1988,6 +2054,12 @@ static inline struct dentry *fdentry(struct file *file) return file->f_path.dentry; } +static inline bool btrfs_mixed_space_info(struct btrfs_space_info *space_info) +{ + return ((space_info->flags & BTRFS_BLOCK_GROUP_METADATA) && + (space_info->flags & BTRFS_BLOCK_GROUP_DATA)); +} + /* extent-tree.c */ void btrfs_put_block_group(struct btrfs_block_group_cache *cache); int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, @@ -2079,7 +2151,7 @@ int btrfs_check_data_free_space(struct inode *inode, u64 bytes); void btrfs_free_reserved_data_space(struct inode *inode, u64 bytes); int btrfs_trans_reserve_metadata(struct btrfs_trans_handle *trans, struct btrfs_root *root, - int num_items, int *retries); + int num_items); void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans, struct btrfs_root *root); int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans, @@ -2100,7 +2172,7 @@ void btrfs_add_durable_block_rsv(struct btrfs_fs_info *fs_info, int btrfs_block_rsv_add(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_block_rsv *block_rsv, - u64 num_bytes, int *retries); + u64 num_bytes); int btrfs_block_rsv_check(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_block_rsv *block_rsv, @@ -2115,6 +2187,7 @@ int btrfs_set_block_group_ro(struct btrfs_root *root, struct btrfs_block_group_cache *cache); int btrfs_set_block_group_rw(struct btrfs_root *root, struct btrfs_block_group_cache *cache); +void btrfs_put_block_group_cache(struct btrfs_fs_info *info); /* ctree.c */ int btrfs_bin_search(struct extent_buffer *eb, struct btrfs_key *key, int level, int *slot); @@ -2373,7 +2446,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, u32 min_type); int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput); -int btrfs_start_one_delalloc_inode(struct btrfs_root *root, int delay_iput); +int btrfs_start_one_delalloc_inode(struct btrfs_root *root, int delay_iput, + int sync); int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end, struct extent_state **cached_state); int btrfs_writepages(struct address_space *mapping, @@ -2426,6 +2500,10 @@ void btrfs_run_delayed_iputs(struct btrfs_root *root); int btrfs_prealloc_file_range(struct inode *inode, int mode, u64 start, u64 num_bytes, u64 min_size, loff_t actual_len, u64 *alloc_hint); +int btrfs_prealloc_file_range_trans(struct inode *inode, + struct btrfs_trans_handle *trans, int mode, + u64 start, u64 num_bytes, u64 min_size, + loff_t actual_len, u64 *alloc_hint); extern const struct dentry_operations btrfs_dentry_operations; /* ioctl.c */ diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index e9103b3baa49..f0cad5ae5be7 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -427,5 +427,5 @@ int btrfs_delete_one_dir_name(struct btrfs_trans_handle *trans, ret = btrfs_truncate_item(trans, root, path, item_len - sub_item_len, 1); } - return 0; + return ret; } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 5e789f4a3ed0..c547cca26a26 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -28,6 +28,7 @@ #include <linux/freezer.h> #include <linux/crc32c.h> #include <linux/slab.h> +#include <linux/migrate.h> #include "compat.h" #include "ctree.h" #include "disk-io.h" @@ -338,7 +339,6 @@ static int csum_dirty_buffer(struct btrfs_root *root, struct page *page) struct extent_io_tree *tree; u64 start = (u64)page->index << PAGE_CACHE_SHIFT; u64 found_start; - int found_level; unsigned long len; struct extent_buffer *eb; int ret; @@ -356,6 +356,8 @@ static int csum_dirty_buffer(struct btrfs_root *root, struct page *page) ret = btree_read_extent_buffer_pages(root, eb, start + PAGE_CACHE_SIZE, btrfs_header_generation(eb)); BUG_ON(ret); + WARN_ON(!btrfs_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN)); + found_start = btrfs_header_bytenr(eb); if (found_start != start) { WARN_ON(1); @@ -369,8 +371,6 @@ static int csum_dirty_buffer(struct btrfs_root *root, struct page *page) WARN_ON(1); goto err; } - found_level = btrfs_header_level(eb); - csum_tree_block(root, eb, 0); err: free_extent_buffer(eb); @@ -481,9 +481,12 @@ static void end_workqueue_bio(struct bio *bio, int err) end_io_wq->work.flags = 0; if (bio->bi_rw & REQ_WRITE) { - if (end_io_wq->metadata) + if (end_io_wq->metadata == 1) btrfs_queue_worker(&fs_info->endio_meta_write_workers, &end_io_wq->work); + else if (end_io_wq->metadata == 2) + btrfs_queue_worker(&fs_info->endio_freespace_worker, + &end_io_wq->work); else btrfs_queue_worker(&fs_info->endio_write_workers, &end_io_wq->work); @@ -497,6 +500,13 @@ static void end_workqueue_bio(struct bio *bio, int err) } } +/* + * For the metadata arg you want + * + * 0 - if data + * 1 - if normal metadta + * 2 - if writing to the free space cache area + */ int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio, int metadata) { @@ -533,11 +543,9 @@ int btrfs_congested_async(struct btrfs_fs_info *info, int iodone) static void run_one_async_start(struct btrfs_work *work) { - struct btrfs_fs_info *fs_info; struct async_submit_bio *async; async = container_of(work, struct async_submit_bio, work); - fs_info = BTRFS_I(async->inode)->root->fs_info; async->submit_bio_start(async->inode, async->rw, async->bio, async->mirror_num, async->bio_flags, async->bio_offset); @@ -688,6 +696,29 @@ static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio, __btree_submit_bio_done); } +static int btree_migratepage(struct address_space *mapping, + struct page *newpage, struct page *page) +{ + /* + * we can't safely write a btree page from here, + * we haven't done the locking hook + */ + if (PageDirty(page)) + return -EAGAIN; + /* + * Buffers may be managed in a filesystem specific way. + * We must have no buffers or drop them. + */ + if (page_has_private(page) && + !try_to_release_page(page, GFP_KERNEL)) + return -EAGAIN; +#ifdef CONFIG_MIGRATION + return migrate_page(mapping, newpage, page); +#else + return -ENOSYS; +#endif +} + static int btree_writepage(struct page *page, struct writeback_control *wbc) { struct extent_io_tree *tree; @@ -702,8 +733,7 @@ static int btree_writepage(struct page *page, struct writeback_control *wbc) } redirty_page_for_writepage(wbc, page); - eb = btrfs_find_tree_block(root, page_offset(page), - PAGE_CACHE_SIZE); + eb = btrfs_find_tree_block(root, page_offset(page), PAGE_CACHE_SIZE); WARN_ON(!eb); was_dirty = test_and_set_bit(EXTENT_BUFFER_DIRTY, &eb->bflags); @@ -794,6 +824,9 @@ static const struct address_space_operations btree_aops = { .releasepage = btree_releasepage, .invalidatepage = btree_invalidatepage, .sync_page = block_sync_page, +#ifdef CONFIG_MIGRATION + .migratepage = btree_migratepage, +#endif }; int readahead_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize, @@ -850,12 +883,8 @@ struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize, u64 parent_transid) { struct extent_buffer *buf = NULL; - struct inode *btree_inode = root->fs_info->btree_inode; - struct extent_io_tree *io_tree; int ret; - io_tree = &BTRFS_I(btree_inode)->io_tree; - buf = btrfs_find_create_tree_block(root, bytenr, blocksize); if (!buf) return NULL; @@ -1377,7 +1406,6 @@ static int bio_ready_for_csum(struct bio *bio) u64 start = 0; struct page *page; struct extent_io_tree *io_tree = NULL; - struct btrfs_fs_info *info = NULL; struct bio_vec *bvec; int i; int ret; @@ -1396,7 +1424,6 @@ static int bio_ready_for_csum(struct bio *bio) buf_len = page->private >> 2; start = page_offset(page) + bvec->bv_offset; io_tree = &BTRFS_I(page->mapping->host)->io_tree; - info = BTRFS_I(page->mapping->host)->root->fs_info; } /* are we fully contained in this bio? */ if (buf_len <= length) @@ -1539,10 +1566,8 @@ struct btrfs_root *open_ctree(struct super_block *sb, GFP_NOFS); struct btrfs_root *csum_root = kzalloc(sizeof(struct btrfs_root), GFP_NOFS); - struct btrfs_root *tree_root = kzalloc(sizeof(struct btrfs_root), - GFP_NOFS); - struct btrfs_fs_info *fs_info = kzalloc(sizeof(*fs_info), - GFP_NOFS); + struct btrfs_root *tree_root = btrfs_sb(sb); + struct btrfs_fs_info *fs_info = tree_root->fs_info; struct btrfs_root *chunk_root = kzalloc(sizeof(struct btrfs_root), GFP_NOFS); struct btrfs_root *dev_root = kzalloc(sizeof(struct btrfs_root), @@ -1680,12 +1705,12 @@ struct btrfs_root *open_ctree(struct super_block *sb, init_waitqueue_head(&fs_info->transaction_throttle); init_waitqueue_head(&fs_info->transaction_wait); + init_waitqueue_head(&fs_info->transaction_blocked_wait); init_waitqueue_head(&fs_info->async_submit_wait); __setup_root(4096, 4096, 4096, 4096, tree_root, fs_info, BTRFS_ROOT_TREE_OBJECTID); - bh = btrfs_read_dev_super(fs_devices->latest_bdev); if (!bh) goto fail_iput; @@ -1775,6 +1800,8 @@ struct btrfs_root *open_ctree(struct super_block *sb, btrfs_init_workers(&fs_info->endio_write_workers, "endio-write", fs_info->thread_pool_size, &fs_info->generic_worker); + btrfs_init_workers(&fs_info->endio_freespace_worker, "freespace-write", + 1, &fs_info->generic_worker); /* * endios are largely parallel and should have a very @@ -1795,6 +1822,7 @@ struct btrfs_root *open_ctree(struct super_block *sb, btrfs_start_workers(&fs_info->endio_meta_workers, 1); btrfs_start_workers(&fs_info->endio_meta_write_workers, 1); btrfs_start_workers(&fs_info->endio_write_workers, 1); + btrfs_start_workers(&fs_info->endio_freespace_worker, 1); fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super); fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages, @@ -1993,6 +2021,7 @@ struct btrfs_root *open_ctree(struct super_block *sb, if (!(sb->s_flags & MS_RDONLY)) { down_read(&fs_info->cleanup_work_sem); btrfs_orphan_cleanup(fs_info->fs_root); + btrfs_orphan_cleanup(fs_info->tree_root); up_read(&fs_info->cleanup_work_sem); } @@ -2035,6 +2064,7 @@ fail_sb_buffer: btrfs_stop_workers(&fs_info->endio_meta_workers); btrfs_stop_workers(&fs_info->endio_meta_write_workers); btrfs_stop_workers(&fs_info->endio_write_workers); + btrfs_stop_workers(&fs_info->endio_freespace_worker); btrfs_stop_workers(&fs_info->submit_workers); fail_iput: invalidate_inode_pages2(fs_info->btree_inode->i_mapping); @@ -2410,6 +2440,7 @@ int close_ctree(struct btrfs_root *root) fs_info->closing = 1; smp_mb(); + btrfs_put_block_group_cache(fs_info); if (!(fs_info->sb->s_flags & MS_RDONLY)) { ret = btrfs_commit_super(root); if (ret) @@ -2456,6 +2487,7 @@ int close_ctree(struct btrfs_root *root) btrfs_stop_workers(&fs_info->endio_meta_workers); btrfs_stop_workers(&fs_info->endio_meta_write_workers); btrfs_stop_workers(&fs_info->endio_write_workers); + btrfs_stop_workers(&fs_info->endio_freespace_worker); btrfs_stop_workers(&fs_info->submit_workers); btrfs_close_devices(fs_info->fs_devices); diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index 951ef09b82f4..6f0444473594 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -232,9 +232,85 @@ fail: return ERR_PTR(ret); } +static int btrfs_get_name(struct dentry *parent, char *name, + struct dentry *child) +{ + struct inode *inode = child->d_inode; + struct inode *dir = parent->d_inode; + struct btrfs_path *path; + struct btrfs_root *root = BTRFS_I(dir)->root; + struct btrfs_inode_ref *iref; + struct btrfs_root_ref *rref; + struct extent_buffer *leaf; + unsigned long name_ptr; + struct btrfs_key key; + int name_len; + int ret; + + if (!dir || !inode) + return -EINVAL; + + if (!S_ISDIR(dir->i_mode)) + return -EINVAL; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + path->leave_spinning = 1; + + if (inode->i_ino == BTRFS_FIRST_FREE_OBJECTID) { + key.objectid = BTRFS_I(inode)->root->root_key.objectid; + key.type = BTRFS_ROOT_BACKREF_KEY; + key.offset = (u64)-1; + root = root->fs_info->tree_root; + } else { + key.objectid = inode->i_ino; + key.offset = dir->i_ino; + key.type = BTRFS_INODE_REF_KEY; + } + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) { + btrfs_free_path(path); + return ret; + } else if (ret > 0) { + if (inode->i_ino == BTRFS_FIRST_FREE_OBJECTID) { + path->slots[0]--; + } else { + btrfs_free_path(path); + return -ENOENT; + } + } + leaf = path->nodes[0]; + + if (inode->i_ino == BTRFS_FIRST_FREE_OBJECTID) { + rref = btrfs_item_ptr(leaf, path->slots[0], + struct btrfs_root_ref); + name_ptr = (unsigned long)(rref + 1); + name_len = btrfs_root_ref_name_len(leaf, rref); + } else { + iref = btrfs_item_ptr(leaf, path->slots[0], + struct btrfs_inode_ref); + name_ptr = (unsigned long)(iref + 1); + name_len = btrfs_inode_ref_name_len(leaf, iref); + } + + read_extent_buffer(leaf, name, name_ptr, name_len); + btrfs_free_path(path); + + /* + * have to add the null termination to make sure that reconnect_path + * gets the right len for strlen + */ + name[name_len] = '\0'; + + return 0; +} + const struct export_operations btrfs_export_ops = { .encode_fh = btrfs_encode_fh, .fh_to_dentry = btrfs_fh_to_dentry, .fh_to_parent = btrfs_fh_to_parent, .get_parent = btrfs_get_parent, + .get_name = btrfs_get_name, }; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 0b81ecdb101c..bcd59c7dfb57 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -242,6 +242,12 @@ get_caching_control(struct btrfs_block_group_cache *cache) return NULL; } + /* We're loading it the fast way, so we don't have a caching_ctl. */ + if (!cache->caching_ctl) { + spin_unlock(&cache->lock); + return NULL; + } + ctl = cache->caching_ctl; atomic_inc(&ctl->count); spin_unlock(&cache->lock); @@ -421,7 +427,9 @@ err: return 0; } -static int cache_block_group(struct btrfs_block_group_cache *cache) +static int cache_block_group(struct btrfs_block_group_cache *cache, + struct btrfs_trans_handle *trans, + int load_cache_only) { struct btrfs_fs_info *fs_info = cache->fs_info; struct btrfs_caching_control *caching_ctl; @@ -432,6 +440,36 @@ static int cache_block_group(struct btrfs_block_group_cache *cache) if (cache->cached != BTRFS_CACHE_NO) return 0; + /* + * We can't do the read from on-disk cache during a commit since we need + * to have the normal tree locking. + */ + if (!trans->transaction->in_commit) { + spin_lock(&cache->lock); + if (cache->cached != BTRFS_CACHE_NO) { + spin_unlock(&cache->lock); + return 0; + } + cache->cached = BTRFS_CACHE_STARTED; + spin_unlock(&cache->lock); + + ret = load_free_space_cache(fs_info, cache); + + spin_lock(&cache->lock); + if (ret == 1) { + cache->cached = BTRFS_CACHE_FINISHED; + cache->last_byte_to_unpin = (u64)-1; + } else { + cache->cached = BTRFS_CACHE_NO; + } + spin_unlock(&cache->lock); + if (ret == 1) + return 0; + } + + if (load_cache_only) + return 0; + caching_ctl = kzalloc(sizeof(*caching_ctl), GFP_KERNEL); BUG_ON(!caching_ctl); @@ -509,7 +547,7 @@ static struct btrfs_space_info *__find_space_info(struct btrfs_fs_info *info, rcu_read_lock(); list_for_each_entry_rcu(found, head, list) { - if (found->flags == flags) { + if (found->flags & flags) { rcu_read_unlock(); return found; } @@ -542,6 +580,15 @@ static u64 div_factor(u64 num, int factor) return num; } +static u64 div_factor_fine(u64 num, int factor) +{ + if (factor == 100) + return num; + num *= factor; + do_div(num, 100); + return num; +} + u64 btrfs_find_block_group(struct btrfs_root *root, u64 search_start, u64 search_hint, int owner) { @@ -2687,6 +2734,109 @@ next_block_group(struct btrfs_root *root, return cache; } +static int cache_save_setup(struct btrfs_block_group_cache *block_group, + struct btrfs_trans_handle *trans, + struct btrfs_path *path) +{ + struct btrfs_root *root = block_group->fs_info->tree_root; + struct inode *inode = NULL; + u64 alloc_hint = 0; + int num_pages = 0; + int retries = 0; + int ret = 0; + + /* + * If this block group is smaller than 100 megs don't bother caching the + * block group. + */ + if (block_group->key.offset < (100 * 1024 * 1024)) { + spin_lock(&block_group->lock); + block_group->disk_cache_state = BTRFS_DC_WRITTEN; + spin_unlock(&block_group->lock); + return 0; + } + +again: + inode = lookup_free_space_inode(root, block_group, path); + if (IS_ERR(inode) && PTR_ERR(inode) != -ENOENT) { + ret = PTR_ERR(inode); + btrfs_release_path(root, path); + goto out; + } + + if (IS_ERR(inode)) { + BUG_ON(retries); + retries++; + + if (block_group->ro) + goto out_free; + + ret = create_free_space_inode(root, trans, block_group, path); + if (ret) + goto out_free; + goto again; + } + + /* + * We want to set the generation to 0, that way if anything goes wrong + * from here on out we know not to trust this cache when we load up next + * time. + */ + BTRFS_I(inode)->generation = 0; + ret = btrfs_update_inode(trans, root, inode); + WARN_ON(ret); + + if (i_size_read(inode) > 0) { + ret = btrfs_truncate_free_space_cache(root, trans, path, + inode); + if (ret) + goto out_put; + } + + spin_lock(&block_group->lock); + if (block_group->cached != BTRFS_CACHE_FINISHED) { + spin_unlock(&block_group->lock); + goto out_put; + } + spin_unlock(&block_group->lock); + + num_pages = (int)div64_u64(block_group->key.offset, 1024 * 1024 * 1024); + if (!num_pages) + num_pages = 1; + + /* + * Just to make absolutely sure we have enough space, we're going to + * preallocate 12 pages worth of space for each block group. In + * practice we ought to use at most 8, but we need extra space so we can + * add our header and have a terminator between the extents and the + * bitmaps. + */ + num_pages *= 16; + num_pages *= PAGE_CACHE_SIZE; + + ret = btrfs_check_data_free_space(inode, num_pages); + if (ret) + goto out_put; + + ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, num_pages, + num_pages, num_pages, + &alloc_hint); + btrfs_free_reserved_data_space(inode, num_pages); +out_put: + iput(inode); +out_free: + btrfs_release_path(root, path); +out: + spin_lock(&block_group->lock); + if (ret) + block_group->disk_cache_state = BTRFS_DC_ERROR; + else + block_group->disk_cache_state = BTRFS_DC_SETUP; + spin_unlock(&block_group->lock); + + return ret; +} + int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans, struct btrfs_root *root) { @@ -2699,6 +2849,25 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans, if (!path) return -ENOMEM; +again: + while (1) { + cache = btrfs_lookup_first_block_group(root->fs_info, last); + while (cache) { + if (cache->disk_cache_state == BTRFS_DC_CLEAR) + break; + cache = next_block_group(root, cache); + } + if (!cache) { + if (last == 0) + break; + last = 0; + continue; + } + err = cache_save_setup(cache, trans, path); + last = cache->key.objectid + cache->key.offset; + btrfs_put_block_group(cache); + } + while (1) { if (last == 0) { err = btrfs_run_delayed_refs(trans, root, @@ -2708,6 +2877,11 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans, cache = btrfs_lookup_first_block_group(root->fs_info, last); while (cache) { + if (cache->disk_cache_state == BTRFS_DC_CLEAR) { + btrfs_put_block_group(cache); + goto again; + } + if (cache->dirty) break; cache = next_block_group(root, cache); @@ -2719,6 +2893,8 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans, continue; } + if (cache->disk_cache_state == BTRFS_DC_SETUP) + cache->disk_cache_state = BTRFS_DC_NEED_WRITE; cache->dirty = 0; last = cache->key.objectid + cache->key.offset; @@ -2727,6 +2903,52 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans, btrfs_put_block_group(cache); } + while (1) { + /* + * I don't think this is needed since we're just marking our + * preallocated extent as written, but just in case it can't + * hurt. + */ + if (last == 0) { + err = btrfs_run_delayed_refs(trans, root, + (unsigned long)-1); + BUG_ON(err); + } + + cache = btrfs_lookup_first_block_group(root->fs_info, last); + while (cache) { + /* + * Really this shouldn't happen, but it could if we + * couldn't write the entire preallocated extent and + * splitting the extent resulted in a new block. + */ + if (cache->dirty) { + btrfs_put_block_group(cache); + goto again; + } + if (cache->disk_cache_state == BTRFS_DC_NEED_WRITE) + break; + cache = next_block_group(root, cache); + } + if (!cache) { + if (last == 0) + break; + last = 0; + continue; + } + + btrfs_write_out_cache(root, trans, cache, path); + + /* + * If we didn't have an error then the cache state is still + * NEED_WRITE, so we can set it to WRITTEN. + */ + if (cache->disk_cache_state == BTRFS_DC_NEED_WRITE) + cache->disk_cache_state = BTRFS_DC_WRITTEN; + last = cache->key.objectid + cache->key.offset; + btrfs_put_block_group(cache); + } + btrfs_free_path(path); return 0; } @@ -2762,6 +2984,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags, if (found) { spin_lock(&found->lock); found->total_bytes += total_bytes; + found->disk_total += total_bytes * factor; found->bytes_used += bytes_used; found->disk_used += bytes_used * factor; found->full = 0; @@ -2781,6 +3004,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags, BTRFS_BLOCK_GROUP_SYSTEM | BTRFS_BLOCK_GROUP_METADATA); found->total_bytes = total_bytes; + found->disk_total = total_bytes * factor; found->bytes_used = bytes_used; found->disk_used = bytes_used * factor; found->bytes_pinned = 0; @@ -2882,11 +3106,16 @@ int btrfs_check_data_free_space(struct inode *inode, u64 bytes) struct btrfs_space_info *data_sinfo; struct btrfs_root *root = BTRFS_I(inode)->root; u64 used; - int ret = 0, committed = 0; + int ret = 0, committed = 0, alloc_chunk = 1; /* make sure bytes are sectorsize aligned */ bytes = (bytes + root->sectorsize - 1) & ~((u64)root->sectorsize - 1); + if (root == root->fs_info->tree_root) { + alloc_chunk = 0; + committed = 1; + } + data_sinfo = BTRFS_I(inode)->space_info; if (!data_sinfo) goto alloc; @@ -2905,7 +3134,7 @@ again: * if we don't have enough free bytes in this space then we need * to alloc a new chunk. */ - if (!data_sinfo->full) { + if (!data_sinfo->full && alloc_chunk) { u64 alloc_target; data_sinfo->force_alloc = 1; @@ -2997,10 +3226,11 @@ static void force_metadata_allocation(struct btrfs_fs_info *info) rcu_read_unlock(); } -static int should_alloc_chunk(struct btrfs_space_info *sinfo, - u64 alloc_bytes) +static int should_alloc_chunk(struct btrfs_root *root, + struct btrfs_space_info *sinfo, u64 alloc_bytes) { u64 num_bytes = sinfo->total_bytes - sinfo->bytes_readonly; + u64 thresh; if (sinfo->bytes_used + sinfo->bytes_reserved + alloc_bytes + 256 * 1024 * 1024 < num_bytes) @@ -3010,6 +3240,12 @@ static int should_alloc_chunk(struct btrfs_space_info *sinfo, alloc_bytes < div_factor(num_bytes, 8)) return 0; + thresh = btrfs_super_total_bytes(&root->fs_info->super_copy); + thresh = max_t(u64, 256 * 1024 * 1024, div_factor_fine(thresh, 5)); + + if (num_bytes > thresh && sinfo->bytes_used < div_factor(num_bytes, 3)) + return 0; + return 1; } @@ -3041,13 +3277,21 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans, goto out; } - if (!force && !should_alloc_chunk(space_info, alloc_bytes)) { + if (!force && !should_alloc_chunk(extent_root, space_info, + alloc_bytes)) { spin_unlock(&space_info->lock); goto out; } spin_unlock(&space_info->lock); /* + * If we have mixed data/metadata chunks we want to make sure we keep + * allocating mixed chunks instead of individual chunks. + */ + if (btrfs_mixed_space_info(space_info)) + flags |= (BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_METADATA); + + /* * if we're doing a data chunk, go ahead and make sure that * we keep a reasonable number of metadata chunks allocated in the * FS as well. @@ -3072,55 +3316,25 @@ out: return ret; } -static int maybe_allocate_chunk(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - struct btrfs_space_info *sinfo, u64 num_bytes) -{ - int ret; - int end_trans = 0; - - if (sinfo->full) - return 0; - - spin_lock(&sinfo->lock); - ret = should_alloc_chunk(sinfo, num_bytes + 2 * 1024 * 1024); - spin_unlock(&sinfo->lock); - if (!ret) - return 0; - - if (!trans) { - trans = btrfs_join_transaction(root, 1); - BUG_ON(IS_ERR(trans)); - end_trans = 1; - } - - ret = do_chunk_alloc(trans, root->fs_info->extent_root, - num_bytes + 2 * 1024 * 1024, - get_alloc_profile(root, sinfo->flags), 0); - - if (end_trans) - btrfs_end_transaction(trans, root); - - return ret == 1 ? 1 : 0; -} - /* * shrink metadata reservation for delalloc */ static int shrink_delalloc(struct btrfs_trans_handle *trans, - struct btrfs_root *root, u64 to_reclaim) + struct btrfs_root *root, u64 to_reclaim, int sync) { struct btrfs_block_rsv *block_rsv; + struct btrfs_space_info *space_info; u64 reserved; u64 max_reclaim; u64 reclaimed = 0; int pause = 1; - int ret; + int nr_pages = (2 * 1024 * 1024) >> PAGE_CACHE_SHIFT; block_rsv = &root->fs_info->delalloc_block_rsv; - spin_lock(&block_rsv->lock); - reserved = block_rsv->reserved; - spin_unlock(&block_rsv->lock); + space_info = block_rsv->space_info; + + smp_mb(); + reserved = space_info->bytes_reserved; if (reserved == 0) return 0; @@ -3128,104 +3342,169 @@ static int shrink_delalloc(struct btrfs_trans_handle *trans, max_reclaim = min(reserved, to_reclaim); while (1) { - ret = btrfs_start_one_delalloc_inode(root, trans ? 1 : 0); - if (!ret) { - __set_current_state(TASK_INTERRUPTIBLE); - schedule_timeout(pause); - pause <<= 1; - if (pause > HZ / 10) - pause = HZ / 10; - } else { - pause = 1; - } + /* have the flusher threads jump in and do some IO */ + smp_mb(); + nr_pages = min_t(unsigned long, nr_pages, + root->fs_info->delalloc_bytes >> PAGE_CACHE_SHIFT); + writeback_inodes_sb_nr_if_idle(root->fs_info->sb, nr_pages); - spin_lock(&block_rsv->lock); - if (reserved > block_rsv->reserved) - reclaimed = reserved - block_rsv->reserved; - reserved = block_rsv->reserved; - spin_unlock(&block_rsv->lock); + spin_lock(&space_info->lock); + if (reserved > space_info->bytes_reserved) + reclaimed += reserved - space_info->bytes_reserved; + reserved = space_info->bytes_reserved; + spin_unlock(&space_info->lock); if (reserved == 0 || reclaimed >= max_reclaim) break; if (trans && trans->transaction->blocked) return -EAGAIN; + + __set_current_state(TASK_INTERRUPTIBLE); + schedule_timeout(pause); + pause <<= 1; + if (pause > HZ / 10) + pause = HZ / 10; + } return reclaimed >= to_reclaim; } -static int should_retry_reserve(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - struct btrfs_block_rsv *block_rsv, - u64 num_bytes, int *retries) +/* + * Retries tells us how many times we've called reserve_metadata_bytes. The + * idea is if this is the first call (retries == 0) then we will add to our + * reserved count if we can't make the allocation in order to hold our place + * while we go and try and free up space. That way for retries > 1 we don't try + * and add space, we just check to see if the amount of unused space is >= the + * total space, meaning that our reservation is valid. + * + * However if we don't intend to retry this reservation, pass -1 as retries so + * that it short circuits this logic. + */ +static int reserve_metadata_bytes(struct btrfs_trans_handle *trans, + struct btrfs_root *root, + struct btrfs_block_rsv *block_rsv, + u64 orig_bytes, int flush) { struct btrfs_space_info *space_info = block_rsv->space_info; - int ret; + u64 unused; + u64 num_bytes = orig_bytes; + int retries = 0; + int ret = 0; + bool reserved = false; + bool committed = false; - if ((*retries) > 2) - return -ENOSPC; +again: + ret = -ENOSPC; + if (reserved) + num_bytes = 0; - ret = maybe_allocate_chunk(trans, root, space_info, num_bytes); - if (ret) - return 1; + spin_lock(&space_info->lock); + unused = space_info->bytes_used + space_info->bytes_reserved + + space_info->bytes_pinned + space_info->bytes_readonly + + space_info->bytes_may_use; - if (trans && trans->transaction->in_commit) - return -ENOSPC; + /* + * The idea here is that we've not already over-reserved the block group + * then we can go ahead and save our reservation first and then start + * flushing if we need to. Otherwise if we've already overcommitted + * lets start flushing stuff first and then come back and try to make + * our reservation. + */ + if (unused <= space_info->total_bytes) { + unused = space_info->total_bytes - unused; + if (unused >= num_bytes) { + if (!reserved) + space_info->bytes_reserved += orig_bytes; + ret = 0; + } else { + /* + * Ok set num_bytes to orig_bytes since we aren't + * overocmmitted, this way we only try and reclaim what + * we need. + */ + num_bytes = orig_bytes; + } + } else { + /* + * Ok we're over committed, set num_bytes to the overcommitted + * amount plus the amount of bytes that we need for this + * reservation. + */ + num_bytes = unused - space_info->total_bytes + + (orig_bytes * (retries + 1)); + } - ret = shrink_delalloc(trans, root, num_bytes); - if (ret) - return ret; + /* + * Couldn't make our reservation, save our place so while we're trying + * to reclaim space we can actually use it instead of somebody else + * stealing it from us. + */ + if (ret && !reserved) { + space_info->bytes_reserved += orig_bytes; + reserved = true; + } - spin_lock(&space_info->lock); - if (space_info->bytes_pinned < num_bytes) - ret = 1; spin_unlock(&space_info->lock); - if (ret) - return -ENOSPC; - (*retries)++; - - if (trans) - return -EAGAIN; + if (!ret) + return 0; - trans = btrfs_join_transaction(root, 1); - BUG_ON(IS_ERR(trans)); - ret = btrfs_commit_transaction(trans, root); - BUG_ON(ret); + if (!flush) + goto out; - return 1; -} + /* + * We do synchronous shrinking since we don't actually unreserve + * metadata until after the IO is completed. + */ + ret = shrink_delalloc(trans, root, num_bytes, 1); + if (ret > 0) + return 0; + else if (ret < 0) + goto out; -static int reserve_metadata_bytes(struct btrfs_block_rsv *block_rsv, - u64 num_bytes) -{ - struct btrfs_space_info *space_info = block_rsv->space_info; - u64 unused; - int ret = -ENOSPC; + /* + * So if we were overcommitted it's possible that somebody else flushed + * out enough space and we simply didn't have enough space to reclaim, + * so go back around and try again. + */ + if (retries < 2) { + retries++; + goto again; + } spin_lock(&space_info->lock); - unused = space_info->bytes_used + space_info->bytes_reserved + - space_info->bytes_pinned + space_info->bytes_readonly; + /* + * Not enough space to be reclaimed, don't bother committing the + * transaction. + */ + if (space_info->bytes_pinned < orig_bytes) + ret = -ENOSPC; + spin_unlock(&space_info->lock); + if (ret) + goto out; - if (unused < space_info->total_bytes) - unused = space_info->total_bytes - unused; - else - unused = 0; + ret = -EAGAIN; + if (trans || committed) + goto out; - if (unused >= num_bytes) { - if (block_rsv->priority >= 10) { - space_info->bytes_reserved += num_bytes; - ret = 0; - } else { - if ((unused + block_rsv->reserved) * - block_rsv->priority >= - (num_bytes + block_rsv->reserved) * 10) { - space_info->bytes_reserved += num_bytes; - ret = 0; - } - } + ret = -ENOSPC; + trans = btrfs_join_transaction(root, 1); + if (IS_ERR(trans)) + goto out; + ret = btrfs_commit_transaction(trans, root); + if (!ret) { + trans = NULL; + committed = true; + goto again; + } + +out: + if (reserved) { + spin_lock(&space_info->lock); + space_info->bytes_reserved -= orig_bytes; + spin_unlock(&space_info->lock); } - spin_unlock(&space_info->lock); return ret; } @@ -3327,18 +3606,14 @@ struct btrfs_block_rsv *btrfs_alloc_block_rsv(struct btrfs_root *root) { struct btrfs_block_rsv *block_rsv; struct btrfs_fs_info *fs_info = root->fs_info; - u64 alloc_target; block_rsv = kmalloc(sizeof(*block_rsv), GFP_NOFS); if (!block_rsv) return NULL; btrfs_init_block_rsv(block_rsv); - - alloc_target = btrfs_get_alloc_profile(root, 0); block_rsv->space_info = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA); - return block_rsv; } @@ -3369,23 +3644,19 @@ void btrfs_add_durable_block_rsv(struct btrfs_fs_info *fs_info, int btrfs_block_rsv_add(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_block_rsv *block_rsv, - u64 num_bytes, int *retries) + u64 num_bytes) { int ret; if (num_bytes == 0) return 0; -again: - ret = reserve_metadata_bytes(block_rsv, num_bytes); + + ret = reserve_metadata_bytes(trans, root, block_rsv, num_bytes, 1); if (!ret) { block_rsv_add_bytes(block_rsv, num_bytes, 1); return 0; } - ret = should_retry_reserve(trans, root, block_rsv, num_bytes, retries); - if (ret > 0) - goto again; - return ret; } @@ -3420,7 +3691,8 @@ int btrfs_block_rsv_check(struct btrfs_trans_handle *trans, return 0; if (block_rsv->refill_used) { - ret = reserve_metadata_bytes(block_rsv, num_bytes); + ret = reserve_metadata_bytes(trans, root, block_rsv, + num_bytes, 0); if (!ret) { block_rsv_add_bytes(block_rsv, num_bytes, 0); return 0; @@ -3499,6 +3771,8 @@ static u64 calc_global_metadata_size(struct btrfs_fs_info *fs_info) sinfo = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA); spin_lock(&sinfo->lock); + if (sinfo->flags & BTRFS_BLOCK_GROUP_DATA) + data_used = 0; meta_used = sinfo->bytes_used; spin_unlock(&sinfo->lock); @@ -3526,7 +3800,8 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info) block_rsv->size = num_bytes; num_bytes = sinfo->bytes_used + sinfo->bytes_pinned + - sinfo->bytes_reserved + sinfo->bytes_readonly; + sinfo->bytes_reserved + sinfo->bytes_readonly + + sinfo->bytes_may_use; if (sinfo->total_bytes > num_bytes) { num_bytes = sinfo->total_bytes - num_bytes; @@ -3597,7 +3872,7 @@ static u64 calc_trans_metadata_size(struct btrfs_root *root, int num_items) int btrfs_trans_reserve_metadata(struct btrfs_trans_handle *trans, struct btrfs_root *root, - int num_items, int *retries) + int num_items) { u64 num_bytes; int ret; @@ -3607,7 +3882,7 @@ int btrfs_trans_reserve_metadata(struct btrfs_trans_handle *trans, num_bytes = calc_trans_metadata_size(root, num_items); ret = btrfs_block_rsv_add(trans, root, &root->fs_info->trans_block_rsv, - num_bytes, retries); + num_bytes); if (!ret) { trans->bytes_reserved += num_bytes; trans->block_rsv = &root->fs_info->trans_block_rsv; @@ -3681,14 +3956,13 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) struct btrfs_block_rsv *block_rsv = &root->fs_info->delalloc_block_rsv; u64 to_reserve; int nr_extents; - int retries = 0; int ret; if (btrfs_transaction_in_commit(root->fs_info)) schedule_timeout(1); num_bytes = ALIGN(num_bytes, root->sectorsize); -again: + spin_lock(&BTRFS_I(inode)->accounting_lock); nr_extents = atomic_read(&BTRFS_I(inode)->outstanding_extents) + 1; if (nr_extents > BTRFS_I(inode)->reserved_extents) { @@ -3698,18 +3972,14 @@ again: nr_extents = 0; to_reserve = 0; } + spin_unlock(&BTRFS_I(inode)->accounting_lock); to_reserve += calc_csum_metadata_size(inode, num_bytes); - ret = reserve_metadata_bytes(block_rsv, to_reserve); - if (ret) { - spin_unlock(&BTRFS_I(inode)->accounting_lock); - ret = should_retry_reserve(NULL, root, block_rsv, to_reserve, - &retries); - if (ret > 0) - goto again; + ret = reserve_metadata_bytes(NULL, root, block_rsv, to_reserve, 1); + if (ret) return ret; - } + spin_lock(&BTRFS_I(inode)->accounting_lock); BTRFS_I(inode)->reserved_extents += nr_extents; atomic_inc(&BTRFS_I(inode)->outstanding_extents); spin_unlock(&BTRFS_I(inode)->accounting_lock); @@ -3717,7 +3987,7 @@ again: block_rsv_add_bytes(block_rsv, to_reserve, 1); if (block_rsv->size > 512 * 1024 * 1024) - shrink_delalloc(NULL, root, to_reserve); + shrink_delalloc(NULL, root, to_reserve, 0); return 0; } @@ -3776,12 +4046,12 @@ static int update_block_group(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, int alloc) { - struct btrfs_block_group_cache *cache; + struct btrfs_block_group_cache *cache = NULL; struct btrfs_fs_info *info = root->fs_info; - int factor; u64 total = num_bytes; u64 old_val; u64 byte_in_group; + int factor; /* block accounting for super block */ spin_lock(&info->delalloc_lock); @@ -3803,11 +4073,25 @@ static int update_block_group(struct btrfs_trans_handle *trans, factor = 2; else factor = 1; + /* + * If this block group has free space cache written out, we + * need to make sure to load it if we are removing space. This + * is because we need the unpinning stage to actually add the + * space back to the block group, otherwise we will leak space. + */ + if (!alloc && cache->cached == BTRFS_CACHE_NO) + cache_block_group(cache, trans, 1); + byte_in_group = bytenr - cache->key.objectid; WARN_ON(byte_in_group > cache->key.offset); spin_lock(&cache->space_info->lock); spin_lock(&cache->lock); + + if (btrfs_super_cache_generation(&info->super_copy) != 0 && + cache->disk_cache_state < BTRFS_DC_CLEAR) + cache->disk_cache_state = BTRFS_DC_CLEAR; + cache->dirty = 1; old_val = btrfs_block_group_used(&cache->item); num_bytes = min(total, cache->key.offset - byte_in_group); @@ -4554,6 +4838,7 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans, bool found_uncached_bg = false; bool failed_cluster_refill = false; bool failed_alloc = false; + bool use_cluster = true; u64 ideal_cache_percent = 0; u64 ideal_cache_offset = 0; @@ -4568,16 +4853,24 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans, return -ENOSPC; } + /* + * If the space info is for both data and metadata it means we have a + * small filesystem and we can't use the clustering stuff. + */ + if (btrfs_mixed_space_info(space_info)) + use_cluster = false; + if (orig_root->ref_cows || empty_size) allowed_chunk_alloc = 1; - if (data & BTRFS_BLOCK_GROUP_METADATA) { + if (data & BTRFS_BLOCK_GROUP_METADATA && use_cluster) { last_ptr = &root->fs_info->meta_alloc_cluster; if (!btrfs_test_opt(root, SSD)) empty_cluster = 64 * 1024; } - if ((data & BTRFS_BLOCK_GROUP_DATA) && btrfs_test_opt(root, SSD)) { + if ((data & BTRFS_BLOCK_GROUP_DATA) && use_cluster && + btrfs_test_opt(root, SSD)) { last_ptr = &root->fs_info->data_alloc_cluster; } @@ -4641,6 +4934,10 @@ have_block_group: if (unlikely(block_group->cached == BTRFS_CACHE_NO)) { u64 free_percent; + ret = cache_block_group(block_group, trans, 1); + if (block_group->cached == BTRFS_CACHE_FINISHED) + goto have_block_group; + free_percent = btrfs_block_group_used(&block_group->item); free_percent *= 100; free_percent = div64_u64(free_percent, @@ -4661,7 +4958,7 @@ have_block_group: if (loop > LOOP_CACHING_NOWAIT || (loop > LOOP_FIND_IDEAL && atomic_read(&space_info->caching_threads) < 2)) { - ret = cache_block_group(block_group); + ret = cache_block_group(block_group, trans, 0); BUG_ON(ret); } found_uncached_bg = true; @@ -5218,7 +5515,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans, u64 num_bytes = ins->offset; block_group = btrfs_lookup_block_group(root->fs_info, ins->objectid); - cache_block_group(block_group); + cache_block_group(block_group, trans, 0); caching_ctl = get_caching_control(block_group); if (!caching_ctl) { @@ -5308,7 +5605,8 @@ use_block_rsv(struct btrfs_trans_handle *trans, block_rsv = get_block_rsv(trans, root); if (block_rsv->size == 0) { - ret = reserve_metadata_bytes(block_rsv, blocksize); + ret = reserve_metadata_bytes(trans, root, block_rsv, + blocksize, 0); if (ret) return ERR_PTR(ret); return block_rsv; @@ -5318,11 +5616,6 @@ use_block_rsv(struct btrfs_trans_handle *trans, if (!ret) return block_rsv; - WARN_ON(1); - printk(KERN_INFO"block_rsv size %llu reserved %llu freed %llu %llu\n", - block_rsv->size, block_rsv->reserved, - block_rsv->freed[0], block_rsv->freed[1]); - return ERR_PTR(-ENOSPC); } @@ -5421,7 +5714,6 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans, u64 generation; u64 refs; u64 flags; - u64 last = 0; u32 nritems; u32 blocksize; struct btrfs_key key; @@ -5489,7 +5781,6 @@ reada: generation); if (ret) break; - last = bytenr + blocksize; nread++; } wc->reada_slot = slot; @@ -7813,6 +8104,40 @@ out: return ret; } +void btrfs_put_block_group_cache(struct btrfs_fs_info *info) +{ + struct btrfs_block_group_cache *block_group; + u64 last = 0; + + while (1) { + struct inode *inode; + + block_group = btrfs_lookup_first_block_group(info, last); + while (block_group) { + spin_lock(&block_group->lock); + if (block_group->iref) + break; + spin_unlock(&block_group->lock); + block_group = next_block_group(info->tree_root, + block_group); + } + if (!block_group) { + if (last == 0) + break; + last = 0; + continue; + } + + inode = block_group->inode; + block_group->iref = 0; + block_group->inode = NULL; + spin_unlock(&block_group->lock); + iput(inode); + last = block_group->key.objectid + block_group->key.offset; + btrfs_put_block_group(block_group); + } +} + int btrfs_free_block_groups(struct btrfs_fs_info *info) { struct btrfs_block_group_cache *block_group; @@ -7896,6 +8221,8 @@ int btrfs_read_block_groups(struct btrfs_root *root) struct btrfs_key key; struct btrfs_key found_key; struct extent_buffer *leaf; + int need_clear = 0; + u64 cache_gen; root = info->extent_root; key.objectid = 0; @@ -7905,6 +8232,15 @@ int btrfs_read_block_groups(struct btrfs_root *root) if (!path) return -ENOMEM; + cache_gen = btrfs_super_cache_generation(&root->fs_info->super_copy); + if (cache_gen != 0 && + btrfs_super_generation(&root->fs_info->super_copy) != cache_gen) + need_clear = 1; + if (btrfs_test_opt(root, CLEAR_CACHE)) + need_clear = 1; + if (!btrfs_test_opt(root, SPACE_CACHE) && cache_gen) + printk(KERN_INFO "btrfs: disk space caching is enabled\n"); + while (1) { ret = find_first_block_group(root, path, &key); if (ret > 0) @@ -7927,6 +8263,9 @@ int btrfs_read_block_groups(struct btrfs_root *root) INIT_LIST_HEAD(&cache->list); INIT_LIST_HEAD(&cache->cluster_list); + if (need_clear) + cache->disk_cache_state = BTRFS_DC_CLEAR; + /* * we only want to have 32k of ram per block group for keeping * track of free space, and if we pass 1/2 of that we want to @@ -8031,6 +8370,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, cache->key.offset = size; cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY; cache->sectorsize = root->sectorsize; + cache->fs_info = root->fs_info; /* * we only want to have 32k of ram per block group for keeping track @@ -8087,8 +8427,11 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, struct btrfs_path *path; struct btrfs_block_group_cache *block_group; struct btrfs_free_cluster *cluster; + struct btrfs_root *tree_root = root->fs_info->tree_root; struct btrfs_key key; + struct inode *inode; int ret; + int factor; root = root->fs_info->extent_root; @@ -8097,6 +8440,12 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, BUG_ON(!block_group->ro); memcpy(&key, &block_group->key, sizeof(key)); + if (block_group->flags & (BTRFS_BLOCK_GROUP_DUP | + BTRFS_BLOCK_GROUP_RAID1 | + BTRFS_BLOCK_GROUP_RAID10)) + factor = 2; + else + factor = 1; /* make sure this block group isn't part of an allocation cluster */ cluster = &root->fs_info->data_alloc_cluster; @@ -8116,6 +8465,40 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, path = btrfs_alloc_path(); BUG_ON(!path); + inode = lookup_free_space_inode(root, block_group, path); + if (!IS_ERR(inode)) { + btrfs_orphan_add(trans, inode); + clear_nlink(inode); + /* One for the block groups ref */ + spin_lock(&block_group->lock); + if (block_group->iref) { + block_group->iref = 0; + block_group->inode = NULL; + spin_unlock(&block_group->lock); + iput(inode); + } else { + spin_unlock(&block_group->lock); + } + /* One for our lookup ref */ + iput(inode); + } + + key.objectid = BTRFS_FREE_SPACE_OBJECTID; + key.offset = block_group->key.objectid; + key.type = 0; + + ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1); + if (ret < 0) + goto out; + if (ret > 0) + btrfs_release_path(tree_root, path); + if (ret == 0) { + ret = btrfs_del_item(trans, tree_root, path); + if (ret) + goto out; + btrfs_release_path(tree_root, path); + } + spin_lock(&root->fs_info->block_group_cache_lock); rb_erase(&block_group->cache_node, &root->fs_info->block_group_cache_tree); @@ -8137,8 +8520,11 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, spin_lock(&block_group->space_info->lock); block_group->space_info->total_bytes -= block_group->key.offset; block_group->space_info->bytes_readonly -= block_group->key.offset; + block_group->space_info->disk_total -= block_group->key.offset * factor; spin_unlock(&block_group->space_info->lock); + memcpy(&key, &block_group->key, sizeof(key)); + btrfs_clear_space_info_full(root->fs_info); btrfs_put_block_group(block_group); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index d74e6af9b53a..3e86b9f36507 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -104,7 +104,7 @@ void extent_io_tree_init(struct extent_io_tree *tree, struct address_space *mapping, gfp_t mask) { tree->state = RB_ROOT; - tree->buffer = RB_ROOT; + INIT_RADIX_TREE(&tree->buffer, GFP_ATOMIC); tree->ops = NULL; tree->dirty_bytes = 0; spin_lock_init(&tree->lock); @@ -235,50 +235,6 @@ static inline struct rb_node *tree_search(struct extent_io_tree *tree, return ret; } -static struct extent_buffer *buffer_tree_insert(struct extent_io_tree *tree, - u64 offset, struct rb_node *node) -{ - struct rb_root *root = &tree->buffer; - struct rb_node **p = &root->rb_node; - struct rb_node *parent = NULL; - struct extent_buffer *eb; - - while (*p) { - parent = *p; - eb = rb_entry(parent, struct extent_buffer, rb_node); - - if (offset < eb->start) - p = &(*p)->rb_left; - else if (offset > eb->start) - p = &(*p)->rb_right; - else - return eb; - } - - rb_link_node(node, parent, p); - rb_insert_color(node, root); - return NULL; -} - -static struct extent_buffer *buffer_search(struct extent_io_tree *tree, - u64 offset) -{ - struct rb_root *root = &tree->buffer; - struct rb_node *n = root->rb_node; - struct extent_buffer *eb; - - while (n) { - eb = rb_entry(n, struct extent_buffer, rb_node); - if (offset < eb->start) - n = n->rb_left; - else if (offset > eb->start) - n = n->rb_right; - else - return eb; - } - return NULL; -} - static void merge_cb(struct extent_io_tree *tree, struct extent_state *new, struct extent_state *other) { @@ -1872,9 +1828,9 @@ static void end_bio_extent_preparewrite(struct bio *bio, int err) bio_put(bio); } -static struct bio * -extent_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs, - gfp_t gfp_flags) +struct bio * +btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs, + gfp_t gfp_flags) { struct bio *bio; @@ -1901,10 +1857,8 @@ static int submit_one_bio(int rw, struct bio *bio, int mirror_num, struct page *page = bvec->bv_page; struct extent_io_tree *tree = bio->bi_private; u64 start; - u64 end; start = ((u64)page->index << PAGE_CACHE_SHIFT) + bvec->bv_offset; - end = start + bvec->bv_len - 1; bio->bi_private = NULL; @@ -1965,7 +1919,7 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree, else nr = bio_get_nr_vecs(bdev); - bio = extent_bio_alloc(bdev, sector, nr, GFP_NOFS | __GFP_HIGH); + bio = btrfs_bio_alloc(bdev, sector, nr, GFP_NOFS | __GFP_HIGH); bio_add_page(bio, page, page_size, offset); bio->bi_end_io = end_io_func; @@ -2204,7 +2158,6 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc, u64 last_byte = i_size_read(inode); u64 block_start; u64 iosize; - u64 unlock_start; sector_t sector; struct extent_state *cached_state = NULL; struct extent_map *em; @@ -2329,7 +2282,6 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc, if (tree->ops && tree->ops->writepage_end_io_hook) tree->ops->writepage_end_io_hook(page, start, page_end, NULL, 1); - unlock_start = page_end + 1; goto done; } @@ -2340,7 +2292,6 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc, if (tree->ops && tree->ops->writepage_end_io_hook) tree->ops->writepage_end_io_hook(page, cur, page_end, NULL, 1); - unlock_start = page_end + 1; break; } em = epd->get_extent(inode, page, pg_offset, cur, @@ -2387,7 +2338,6 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc, cur += iosize; pg_offset += iosize; - unlock_start = cur; continue; } /* leave this out until we have a page_mkwrite call */ @@ -2473,7 +2423,6 @@ static int extent_write_cache_pages(struct extent_io_tree *tree, pgoff_t index; pgoff_t end; /* Inclusive */ int scanned = 0; - int range_whole = 0; pagevec_init(&pvec, 0); if (wbc->range_cyclic) { @@ -2482,8 +2431,6 @@ static int extent_write_cache_pages(struct extent_io_tree *tree, } else { index = wbc->range_start >> PAGE_CACHE_SHIFT; end = wbc->range_end >> PAGE_CACHE_SHIFT; - if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) - range_whole = 1; scanned = 1; } retry: @@ -2823,6 +2770,8 @@ int extent_prepare_write(struct extent_io_tree *tree, NULL, 1, end_bio_extent_preparewrite, 0, 0, 0); + if (ret && !err) + err = ret; iocount++; block_start = block_start + iosize; } else { @@ -2952,21 +2901,53 @@ out: int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len, get_extent_t *get_extent) { - int ret; + int ret = 0; u64 off = start; u64 max = start + len; u32 flags = 0; + u32 found_type; + u64 last; u64 disko = 0; + struct btrfs_key found_key; struct extent_map *em = NULL; struct extent_state *cached_state = NULL; + struct btrfs_path *path; + struct btrfs_file_extent_item *item; int end = 0; u64 em_start = 0, em_len = 0; unsigned long emflags; - ret = 0; + int hole = 0; if (len == 0) return -EINVAL; + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + path->leave_spinning = 1; + + ret = btrfs_lookup_file_extent(NULL, BTRFS_I(inode)->root, + path, inode->i_ino, -1, 0); + if (ret < 0) { + btrfs_free_path(path); + return ret; + } + WARN_ON(!ret); + path->slots[0]--; + item = btrfs_item_ptr(path->nodes[0], path->slots[0], + struct btrfs_file_extent_item); + btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); + found_type = btrfs_key_type(&found_key); + + /* No extents, just return */ + if (found_key.objectid != inode->i_ino || + found_type != BTRFS_EXTENT_DATA_KEY) { + btrfs_free_path(path); + return 0; + } + last = found_key.offset; + btrfs_free_path(path); + lock_extent_bits(&BTRFS_I(inode)->io_tree, start, start + len, 0, &cached_state, GFP_NOFS); em = get_extent(inode, NULL, 0, off, max - off, 0); @@ -2976,11 +2957,18 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, ret = PTR_ERR(em); goto out; } + while (!end) { + hole = 0; off = em->start + em->len; if (off >= max) end = 1; + if (em->block_start == EXTENT_MAP_HOLE) { + hole = 1; + goto next; + } + em_start = em->start; em_len = em->len; @@ -2990,8 +2978,6 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, if (em->block_start == EXTENT_MAP_LAST_BYTE) { end = 1; flags |= FIEMAP_EXTENT_LAST; - } else if (em->block_start == EXTENT_MAP_HOLE) { - flags |= FIEMAP_EXTENT_UNWRITTEN; } else if (em->block_start == EXTENT_MAP_INLINE) { flags |= (FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_NOT_ALIGNED); @@ -3004,10 +2990,10 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) flags |= FIEMAP_EXTENT_ENCODED; +next: emflags = em->flags; free_extent_map(em); em = NULL; - if (!end) { em = get_extent(inode, NULL, 0, off, max - off, 0); if (!em) @@ -3018,15 +3004,23 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, } emflags = em->flags; } + if (test_bit(EXTENT_FLAG_VACANCY, &emflags)) { flags |= FIEMAP_EXTENT_LAST; end = 1; } - ret = fiemap_fill_next_extent(fieinfo, em_start, disko, - em_len, flags); - if (ret) - goto out_free; + if (em_start == last) { + flags |= FIEMAP_EXTENT_LAST; + end = 1; + } + + if (!hole) { + ret = fiemap_fill_next_extent(fieinfo, em_start, disko, + em_len, flags); + if (ret) + goto out_free; + } } out_free: free_extent_map(em); @@ -3104,6 +3098,39 @@ static void __free_extent_buffer(struct extent_buffer *eb) kmem_cache_free(extent_buffer_cache, eb); } +/* + * Helper for releasing extent buffer page. + */ +static void btrfs_release_extent_buffer_page(struct extent_buffer *eb, + unsigned long start_idx) +{ + unsigned long index; + struct page *page; + + if (!eb->first_page) + return; + + index = num_extent_pages(eb->start, eb->len); + if (start_idx >= index) + return; + + do { + index--; + page = extent_buffer_page(eb, index); + if (page) + page_cache_release(page); + } while (index != start_idx); +} + +/* + * Helper for releasing the extent buffer. + */ +static inline void btrfs_release_extent_buffer(struct extent_buffer *eb) +{ + btrfs_release_extent_buffer_page(eb, 0); + __free_extent_buffer(eb); +} + struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree, u64 start, unsigned long len, struct page *page0, @@ -3117,16 +3144,16 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree, struct page *p; struct address_space *mapping = tree->mapping; int uptodate = 1; + int ret; - spin_lock(&tree->buffer_lock); - eb = buffer_search(tree, start); - if (eb) { - atomic_inc(&eb->refs); - spin_unlock(&tree->buffer_lock); + rcu_read_lock(); + eb = radix_tree_lookup(&tree->buffer, start >> PAGE_CACHE_SHIFT); + if (eb && atomic_inc_not_zero(&eb->refs)) { + rcu_read_unlock(); mark_page_accessed(eb->first_page); return eb; } - spin_unlock(&tree->buffer_lock); + rcu_read_unlock(); eb = __alloc_extent_buffer(tree, start, len, mask); if (!eb) @@ -3165,26 +3192,31 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree, if (uptodate) set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); + ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM); + if (ret) + goto free_eb; + spin_lock(&tree->buffer_lock); - exists = buffer_tree_insert(tree, start, &eb->rb_node); - if (exists) { + ret = radix_tree_insert(&tree->buffer, start >> PAGE_CACHE_SHIFT, eb); + if (ret == -EEXIST) { + exists = radix_tree_lookup(&tree->buffer, + start >> PAGE_CACHE_SHIFT); /* add one reference for the caller */ atomic_inc(&exists->refs); spin_unlock(&tree->buffer_lock); + radix_tree_preload_end(); goto free_eb; } /* add one reference for the tree */ atomic_inc(&eb->refs); spin_unlock(&tree->buffer_lock); + radix_tree_preload_end(); return eb; free_eb: if (!atomic_dec_and_test(&eb->refs)) return exists; - for (index = 1; index < i; index++) - page_cache_release(extent_buffer_page(eb, index)); - page_cache_release(extent_buffer_page(eb, 0)); - __free_extent_buffer(eb); + btrfs_release_extent_buffer(eb); return exists; } @@ -3194,16 +3226,16 @@ struct extent_buffer *find_extent_buffer(struct extent_io_tree *tree, { struct extent_buffer *eb; - spin_lock(&tree->buffer_lock); - eb = buffer_search(tree, start); - if (eb) - atomic_inc(&eb->refs); - spin_unlock(&tree->buffer_lock); - - if (eb) + rcu_read_lock(); + eb = radix_tree_lookup(&tree->buffer, start >> PAGE_CACHE_SHIFT); + if (eb && atomic_inc_not_zero(&eb->refs)) { + rcu_read_unlock(); mark_page_accessed(eb->first_page); + return eb; + } + rcu_read_unlock(); - return eb; + return NULL; } void free_extent_buffer(struct extent_buffer *eb) @@ -3833,34 +3865,47 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset, } } +static inline void btrfs_release_extent_buffer_rcu(struct rcu_head *head) +{ + struct extent_buffer *eb = + container_of(head, struct extent_buffer, rcu_head); + + btrfs_release_extent_buffer(eb); +} + int try_release_extent_buffer(struct extent_io_tree *tree, struct page *page) { u64 start = page_offset(page); struct extent_buffer *eb; int ret = 1; - unsigned long i; - unsigned long num_pages; spin_lock(&tree->buffer_lock); - eb = buffer_search(tree, start); - if (!eb) - goto out; + eb = radix_tree_lookup(&tree->buffer, start >> PAGE_CACHE_SHIFT); + if (!eb) { + spin_unlock(&tree->buffer_lock); + return ret; + } - if (atomic_read(&eb->refs) > 1) { + if (test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)) { ret = 0; goto out; } - if (test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)) { + + /* + * set @eb->refs to 0 if it is already 1, and then release the @eb. + * Or go back. + */ + if (atomic_cmpxchg(&eb->refs, 1, 0) != 1) { ret = 0; goto out; } - /* at this point we can safely release the extent buffer */ - num_pages = num_extent_pages(eb->start, eb->len); - for (i = 0; i < num_pages; i++) - page_cache_release(extent_buffer_page(eb, i)); - rb_erase(&eb->rb_node, &tree->buffer); - __free_extent_buffer(eb); + + radix_tree_delete(&tree->buffer, start >> PAGE_CACHE_SHIFT); out: spin_unlock(&tree->buffer_lock); + + /* at this point we can safely release the extent buffer */ + if (atomic_read(&eb->refs) == 0) + call_rcu(&eb->rcu_head, btrfs_release_extent_buffer_rcu); return ret; } diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 5691c7b590da..4183c8178f01 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -85,7 +85,7 @@ struct extent_io_ops { struct extent_io_tree { struct rb_root state; - struct rb_root buffer; + struct radix_tree_root buffer; struct address_space *mapping; u64 dirty_bytes; spinlock_t lock; @@ -123,7 +123,7 @@ struct extent_buffer { unsigned long bflags; atomic_t refs; struct list_head leak_list; - struct rb_node rb_node; + struct rcu_head rcu_head; /* the spinlock is used to protect most operations */ spinlock_t lock; @@ -310,4 +310,7 @@ int extent_clear_unlock_delalloc(struct inode *inode, struct extent_io_tree *tree, u64 start, u64 end, struct page *locked_page, unsigned long op); +struct bio * +btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs, + gfp_t gfp_flags); #endif diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 454ca52d6451..23cb8da3ff66 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -335,7 +335,7 @@ struct extent_map *lookup_extent_mapping(struct extent_map_tree *tree, goto out; } if (IS_ERR(rb_node)) { - em = ERR_PTR(PTR_ERR(rb_node)); + em = ERR_CAST(rb_node); goto out; } em = rb_entry(rb_node, struct extent_map, rb_node); @@ -384,7 +384,7 @@ struct extent_map *search_extent_mapping(struct extent_map_tree *tree, goto out; } if (IS_ERR(rb_node)) { - em = ERR_PTR(PTR_ERR(rb_node)); + em = ERR_CAST(rb_node); goto out; } em = rb_entry(rb_node, struct extent_map, rb_node); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index e354c33df082..c1faded5fca0 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1047,8 +1047,14 @@ out: if ((file->f_flags & O_DSYNC) || IS_SYNC(inode)) { trans = btrfs_start_transaction(root, 0); + if (IS_ERR(trans)) { + num_written = PTR_ERR(trans); + goto done; + } + mutex_lock(&inode->i_mutex); ret = btrfs_log_dentry_safe(trans, root, file->f_dentry); + mutex_unlock(&inode->i_mutex); if (ret == 0) { ret = btrfs_sync_log(trans, root); if (ret == 0) @@ -1067,6 +1073,7 @@ out: (start_pos + num_written - 1) >> PAGE_CACHE_SHIFT); } } +done: current->backing_dev_info = NULL; return num_written ? num_written : err; } diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index f488fac04d99..22ee0dc2e6b8 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -23,10 +23,761 @@ #include "ctree.h" #include "free-space-cache.h" #include "transaction.h" +#include "disk-io.h" #define BITS_PER_BITMAP (PAGE_CACHE_SIZE * 8) #define MAX_CACHE_BYTES_PER_GIG (32 * 1024) +static void recalculate_thresholds(struct btrfs_block_group_cache + *block_group); +static int link_free_space(struct btrfs_block_group_cache *block_group, + struct btrfs_free_space *info); + +struct inode *lookup_free_space_inode(struct btrfs_root *root, + struct btrfs_block_group_cache + *block_group, struct btrfs_path *path) +{ + struct btrfs_key key; + struct btrfs_key location; + struct btrfs_disk_key disk_key; + struct btrfs_free_space_header *header; + struct extent_buffer *leaf; + struct inode *inode = NULL; + int ret; + + spin_lock(&block_group->lock); + if (block_group->inode) + inode = igrab(block_group->inode); + spin_unlock(&block_group->lock); + if (inode) + return inode; + + key.objectid = BTRFS_FREE_SPACE_OBJECTID; + key.offset = block_group->key.objectid; + key.type = 0; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) + return ERR_PTR(ret); + if (ret > 0) { + btrfs_release_path(root, path); + return ERR_PTR(-ENOENT); + } + + leaf = path->nodes[0]; + header = btrfs_item_ptr(leaf, path->slots[0], + struct btrfs_free_space_header); + btrfs_free_space_key(leaf, header, &disk_key); + btrfs_disk_key_to_cpu(&location, &disk_key); + btrfs_release_path(root, path); + + inode = btrfs_iget(root->fs_info->sb, &location, root, NULL); + if (!inode) + return ERR_PTR(-ENOENT); + if (IS_ERR(inode)) + return inode; + if (is_bad_inode(inode)) { + iput(inode); + return ERR_PTR(-ENOENT); + } + + spin_lock(&block_group->lock); + if (!root->fs_info->closing) { + block_group->inode = igrab(inode); + block_group->iref = 1; + } + spin_unlock(&block_group->lock); + + return inode; +} + +int create_free_space_inode(struct btrfs_root *root, + struct btrfs_trans_handle *trans, + struct btrfs_block_group_cache *block_group, + struct btrfs_path *path) +{ + struct btrfs_key key; + struct btrfs_disk_key disk_key; + struct btrfs_free_space_header *header; + struct btrfs_inode_item *inode_item; + struct extent_buffer *leaf; + u64 objectid; + int ret; + + ret = btrfs_find_free_objectid(trans, root, 0, &objectid); + if (ret < 0) + return ret; + + ret = btrfs_insert_empty_inode(trans, root, path, objectid); + if (ret) + return ret; + + leaf = path->nodes[0]; + inode_item = btrfs_item_ptr(leaf, path->slots[0], + struct btrfs_inode_item); + btrfs_item_key(leaf, &disk_key, path->slots[0]); + memset_extent_buffer(leaf, 0, (unsigned long)inode_item, + sizeof(*inode_item)); + btrfs_set_inode_generation(leaf, inode_item, trans->transid); + btrfs_set_inode_size(leaf, inode_item, 0); + btrfs_set_inode_nbytes(leaf, inode_item, 0); + btrfs_set_inode_uid(leaf, inode_item, 0); + btrfs_set_inode_gid(leaf, inode_item, 0); + btrfs_set_inode_mode(leaf, inode_item, S_IFREG | 0600); + btrfs_set_inode_flags(leaf, inode_item, BTRFS_INODE_NOCOMPRESS | + BTRFS_INODE_PREALLOC | BTRFS_INODE_NODATASUM); + btrfs_set_inode_nlink(leaf, inode_item, 1); + btrfs_set_inode_transid(leaf, inode_item, trans->transid); + btrfs_set_inode_block_group(leaf, inode_item, + block_group->key.objectid); + btrfs_mark_buffer_dirty(leaf); + btrfs_release_path(root, path); + + key.objectid = BTRFS_FREE_SPACE_OBJECTID; + key.offset = block_group->key.objectid; + key.type = 0; + + ret = btrfs_insert_empty_item(trans, root, path, &key, + sizeof(struct btrfs_free_space_header)); + if (ret < 0) { + btrfs_release_path(root, path); + return ret; + } + leaf = path->nodes[0]; + header = btrfs_item_ptr(leaf, path->slots[0], + struct btrfs_free_space_header); + memset_extent_buffer(leaf, 0, (unsigned long)header, sizeof(*header)); + btrfs_set_free_space_key(leaf, header, &disk_key); + btrfs_mark_buffer_dirty(leaf); + btrfs_release_path(root, path); + + return 0; +} + +int btrfs_truncate_free_space_cache(struct btrfs_root *root, + struct btrfs_trans_handle *trans, + struct btrfs_path *path, + struct inode *inode) +{ + loff_t oldsize; + int ret = 0; + + trans->block_rsv = root->orphan_block_rsv; + ret = btrfs_block_rsv_check(trans, root, + root->orphan_block_rsv, + 0, 5); + if (ret) + return ret; + + oldsize = i_size_read(inode); + btrfs_i_size_write(inode, 0); + truncate_pagecache(inode, oldsize, 0); + + /* + * We don't need an orphan item because truncating the free space cache + * will never be split across transactions. + */ + ret = btrfs_truncate_inode_items(trans, root, inode, + 0, BTRFS_EXTENT_DATA_KEY); + if (ret) { + WARN_ON(1); + return ret; + } + + return btrfs_update_inode(trans, root, inode); +} + +static int readahead_cache(struct inode *inode) +{ + struct file_ra_state *ra; + unsigned long last_index; + + ra = kzalloc(sizeof(*ra), GFP_NOFS); + if (!ra) + return -ENOMEM; + + file_ra_state_init(ra, inode->i_mapping); + last_index = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT; + + page_cache_sync_readahead(inode->i_mapping, ra, NULL, 0, last_index); + + kfree(ra); + + return 0; +} + +int load_free_space_cache(struct btrfs_fs_info *fs_info, + struct btrfs_block_group_cache *block_group) +{ + struct btrfs_root *root = fs_info->tree_root; + struct inode *inode; + struct btrfs_free_space_header *header; + struct extent_buffer *leaf; + struct page *page; + struct btrfs_path *path; + u32 *checksums = NULL, *crc; + char *disk_crcs = NULL; + struct btrfs_key key; + struct list_head bitmaps; + u64 num_entries; + u64 num_bitmaps; + u64 generation; + u32 cur_crc = ~(u32)0; + pgoff_t index = 0; + unsigned long first_page_offset; + int num_checksums; + int ret = 0; + + /* + * If we're unmounting then just return, since this does a search on the + * normal root and not the commit root and we could deadlock. + */ + smp_mb(); + if (fs_info->closing) + return 0; + + /* + * If this block group has been marked to be cleared for one reason or + * another then we can't trust the on disk cache, so just return. + */ + spin_lock(&block_group->lock); + if (block_group->disk_cache_state != BTRFS_DC_WRITTEN) { + spin_unlock(&block_group->lock); + return 0; + } + spin_unlock(&block_group->lock); + + INIT_LIST_HEAD(&bitmaps); + + path = btrfs_alloc_path(); + if (!path) + return 0; + + inode = lookup_free_space_inode(root, block_group, path); + if (IS_ERR(inode)) { + btrfs_free_path(path); + return 0; + } + + /* Nothing in the space cache, goodbye */ + if (!i_size_read(inode)) { + btrfs_free_path(path); + goto out; + } + + key.objectid = BTRFS_FREE_SPACE_OBJECTID; + key.offset = block_group->key.objectid; + key.type = 0; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret) { + btrfs_free_path(path); + goto out; + } + + leaf = path->nodes[0]; + header = btrfs_item_ptr(leaf, path->slots[0], + struct btrfs_free_space_header); + num_entries = btrfs_free_space_entries(leaf, header); + num_bitmaps = btrfs_free_space_bitmaps(leaf, header); + generation = btrfs_free_space_generation(leaf, header); + btrfs_free_path(path); + + if (BTRFS_I(inode)->generation != generation) { + printk(KERN_ERR "btrfs: free space inode generation (%llu) did" + " not match free space cache generation (%llu) for " + "block group %llu\n", + (unsigned long long)BTRFS_I(inode)->generation, + (unsigned long long)generation, + (unsigned long long)block_group->key.objectid); + goto out; + } + + if (!num_entries) + goto out; + + /* Setup everything for doing checksumming */ + num_checksums = i_size_read(inode) / PAGE_CACHE_SIZE; + checksums = crc = kzalloc(sizeof(u32) * num_checksums, GFP_NOFS); + if (!checksums) + goto out; + first_page_offset = (sizeof(u32) * num_checksums) + sizeof(u64); + disk_crcs = kzalloc(first_page_offset, GFP_NOFS); + if (!disk_crcs) + goto out; + + ret = readahead_cache(inode); + if (ret) { + ret = 0; + goto out; + } + + while (1) { + struct btrfs_free_space_entry *entry; + struct btrfs_free_space *e; + void *addr; + unsigned long offset = 0; + unsigned long start_offset = 0; + int need_loop = 0; + + if (!num_entries && !num_bitmaps) + break; + + if (index == 0) { + start_offset = first_page_offset; + offset = start_offset; + } + + page = grab_cache_page(inode->i_mapping, index); + if (!page) { + ret = 0; + goto free_cache; + } + + if (!PageUptodate(page)) { + btrfs_readpage(NULL, page); + lock_page(page); + if (!PageUptodate(page)) { + unlock_page(page); + page_cache_release(page); + printk(KERN_ERR "btrfs: error reading free " + "space cache: %llu\n", + (unsigned long long) + block_group->key.objectid); + goto free_cache; + } + } + addr = kmap(page); + + if (index == 0) { + u64 *gen; + + memcpy(disk_crcs, addr, first_page_offset); + gen = addr + (sizeof(u32) * num_checksums); + if (*gen != BTRFS_I(inode)->generation) { + printk(KERN_ERR "btrfs: space cache generation" + " (%llu) does not match inode (%llu) " + "for block group %llu\n", + (unsigned long long)*gen, + (unsigned long long) + BTRFS_I(inode)->generation, + (unsigned long long) + block_group->key.objectid); + kunmap(page); + unlock_page(page); + page_cache_release(page); + goto free_cache; + } + crc = (u32 *)disk_crcs; + } + entry = addr + start_offset; + + /* First lets check our crc before we do anything fun */ + cur_crc = ~(u32)0; + cur_crc = btrfs_csum_data(root, addr + start_offset, cur_crc, + PAGE_CACHE_SIZE - start_offset); + btrfs_csum_final(cur_crc, (char *)&cur_crc); + if (cur_crc != *crc) { + printk(KERN_ERR "btrfs: crc mismatch for page %lu in " + "block group %llu\n", index, + (unsigned long long)block_group->key.objectid); + kunmap(page); + unlock_page(page); + page_cache_release(page); + goto free_cache; + } + crc++; + + while (1) { + if (!num_entries) + break; + + need_loop = 1; + e = kzalloc(sizeof(struct btrfs_free_space), GFP_NOFS); + if (!e) { + kunmap(page); + unlock_page(page); + page_cache_release(page); + goto free_cache; + } + + e->offset = le64_to_cpu(entry->offset); + e->bytes = le64_to_cpu(entry->bytes); + if (!e->bytes) { + kunmap(page); + kfree(e); + unlock_page(page); + page_cache_release(page); + goto free_cache; + } + + if (entry->type == BTRFS_FREE_SPACE_EXTENT) { + spin_lock(&block_group->tree_lock); + ret = link_free_space(block_group, e); + spin_unlock(&block_group->tree_lock); + BUG_ON(ret); + } else { + e->bitmap = kzalloc(PAGE_CACHE_SIZE, GFP_NOFS); + if (!e->bitmap) { + kunmap(page); + kfree(e); + unlock_page(page); + page_cache_release(page); + goto free_cache; + } + spin_lock(&block_group->tree_lock); + ret = link_free_space(block_group, e); + block_group->total_bitmaps++; + recalculate_thresholds(block_group); + spin_unlock(&block_group->tree_lock); + list_add_tail(&e->list, &bitmaps); + } + + num_entries--; + offset += sizeof(struct btrfs_free_space_entry); + if (offset + sizeof(struct btrfs_free_space_entry) >= + PAGE_CACHE_SIZE) + break; + entry++; + } + + /* + * We read an entry out of this page, we need to move on to the + * next page. + */ + if (need_loop) { + kunmap(page); + goto next; + } + + /* + * We add the bitmaps at the end of the entries in order that + * the bitmap entries are added to the cache. + */ + e = list_entry(bitmaps.next, struct btrfs_free_space, list); + list_del_init(&e->list); + memcpy(e->bitmap, addr, PAGE_CACHE_SIZE); + kunmap(page); + num_bitmaps--; +next: + unlock_page(page); + page_cache_release(page); + index++; + } + + ret = 1; +out: + kfree(checksums); + kfree(disk_crcs); + iput(inode); + return ret; + +free_cache: + /* This cache is bogus, make sure it gets cleared */ + spin_lock(&block_group->lock); + block_group->disk_cache_state = BTRFS_DC_CLEAR; + spin_unlock(&block_group->lock); + btrfs_remove_free_space_cache(block_group); + goto out; +} + +int btrfs_write_out_cache(struct btrfs_root *root, + struct btrfs_trans_handle *trans, + struct btrfs_block_group_cache *block_group, + struct btrfs_path *path) +{ + struct btrfs_free_space_header *header; + struct extent_buffer *leaf; + struct inode *inode; + struct rb_node *node; + struct list_head *pos, *n; + struct page *page; + struct extent_state *cached_state = NULL; + struct list_head bitmap_list; + struct btrfs_key key; + u64 bytes = 0; + u32 *crc, *checksums; + pgoff_t index = 0, last_index = 0; + unsigned long first_page_offset; + int num_checksums; + int entries = 0; + int bitmaps = 0; + int ret = 0; + + root = root->fs_info->tree_root; + + INIT_LIST_HEAD(&bitmap_list); + + spin_lock(&block_group->lock); + if (block_group->disk_cache_state < BTRFS_DC_SETUP) { + spin_unlock(&block_group->lock); + return 0; + } + spin_unlock(&block_group->lock); + + inode = lookup_free_space_inode(root, block_group, path); + if (IS_ERR(inode)) + return 0; + + if (!i_size_read(inode)) { + iput(inode); + return 0; + } + + last_index = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT; + filemap_write_and_wait(inode->i_mapping); + btrfs_wait_ordered_range(inode, inode->i_size & + ~(root->sectorsize - 1), (u64)-1); + + /* We need a checksum per page. */ + num_checksums = i_size_read(inode) / PAGE_CACHE_SIZE; + crc = checksums = kzalloc(sizeof(u32) * num_checksums, GFP_NOFS); + if (!crc) { + iput(inode); + return 0; + } + + /* Since the first page has all of our checksums and our generation we + * need to calculate the offset into the page that we can start writing + * our entries. + */ + first_page_offset = (sizeof(u32) * num_checksums) + sizeof(u64); + + node = rb_first(&block_group->free_space_offset); + if (!node) + goto out_free; + + /* + * Lock all pages first so we can lock the extent safely. + * + * NOTE: Because we hold the ref the entire time we're going to write to + * the page find_get_page should never fail, so we don't do a check + * after find_get_page at this point. Just putting this here so people + * know and don't freak out. + */ + while (index <= last_index) { + page = grab_cache_page(inode->i_mapping, index); + if (!page) { + pgoff_t i = 0; + + while (i < index) { + page = find_get_page(inode->i_mapping, i); + unlock_page(page); + page_cache_release(page); + page_cache_release(page); + i++; + } + goto out_free; + } + index++; + } + + index = 0; + lock_extent_bits(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1, + 0, &cached_state, GFP_NOFS); + + /* Write out the extent entries */ + do { + struct btrfs_free_space_entry *entry; + void *addr; + unsigned long offset = 0; + unsigned long start_offset = 0; + + if (index == 0) { + start_offset = first_page_offset; + offset = start_offset; + } + + page = find_get_page(inode->i_mapping, index); + + addr = kmap(page); + entry = addr + start_offset; + + memset(addr, 0, PAGE_CACHE_SIZE); + while (1) { + struct btrfs_free_space *e; + + e = rb_entry(node, struct btrfs_free_space, offset_index); + entries++; + + entry->offset = cpu_to_le64(e->offset); + entry->bytes = cpu_to_le64(e->bytes); + if (e->bitmap) { + entry->type = BTRFS_FREE_SPACE_BITMAP; + list_add_tail(&e->list, &bitmap_list); + bitmaps++; + } else { + entry->type = BTRFS_FREE_SPACE_EXTENT; + } + node = rb_next(node); + if (!node) + break; + offset += sizeof(struct btrfs_free_space_entry); + if (offset + sizeof(struct btrfs_free_space_entry) >= + PAGE_CACHE_SIZE) + break; + entry++; + } + *crc = ~(u32)0; + *crc = btrfs_csum_data(root, addr + start_offset, *crc, + PAGE_CACHE_SIZE - start_offset); + kunmap(page); + + btrfs_csum_final(*crc, (char *)crc); + crc++; + + bytes += PAGE_CACHE_SIZE; + + ClearPageChecked(page); + set_page_extent_mapped(page); + SetPageUptodate(page); + set_page_dirty(page); + + /* + * We need to release our reference we got for grab_cache_page, + * except for the first page which will hold our checksums, we + * do that below. + */ + if (index != 0) { + unlock_page(page); + page_cache_release(page); + } + + page_cache_release(page); + + index++; + } while (node); + + /* Write out the bitmaps */ + list_for_each_safe(pos, n, &bitmap_list) { + void *addr; + struct btrfs_free_space *entry = + list_entry(pos, struct btrfs_free_space, list); + + page = find_get_page(inode->i_mapping, index); + + addr = kmap(page); + memcpy(addr, entry->bitmap, PAGE_CACHE_SIZE); + *crc = ~(u32)0; + *crc = btrfs_csum_data(root, addr, *crc, PAGE_CACHE_SIZE); + kunmap(page); + btrfs_csum_final(*crc, (char *)crc); + crc++; + bytes += PAGE_CACHE_SIZE; + + ClearPageChecked(page); + set_page_extent_mapped(page); + SetPageUptodate(page); + set_page_dirty(page); + unlock_page(page); + page_cache_release(page); + page_cache_release(page); + list_del_init(&entry->list); + index++; + } + + /* Zero out the rest of the pages just to make sure */ + while (index <= last_index) { + void *addr; + + page = find_get_page(inode->i_mapping, index); + + addr = kmap(page); + memset(addr, 0, PAGE_CACHE_SIZE); + kunmap(page); + ClearPageChecked(page); + set_page_extent_mapped(page); + SetPageUptodate(page); + set_page_dirty(page); + unlock_page(page); + page_cache_release(page); + page_cache_release(page); + bytes += PAGE_CACHE_SIZE; + index++; + } + + btrfs_set_extent_delalloc(inode, 0, bytes - 1, &cached_state); + + /* Write the checksums and trans id to the first page */ + { + void *addr; + u64 *gen; + + page = find_get_page(inode->i_mapping, 0); + + addr = kmap(page); + memcpy(addr, checksums, sizeof(u32) * num_checksums); + gen = addr + (sizeof(u32) * num_checksums); + *gen = trans->transid; + kunmap(page); + ClearPageChecked(page); + set_page_extent_mapped(page); + SetPageUptodate(page); + set_page_dirty(page); + unlock_page(page); + page_cache_release(page); + page_cache_release(page); + } + BTRFS_I(inode)->generation = trans->transid; + + unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0, + i_size_read(inode) - 1, &cached_state, GFP_NOFS); + + filemap_write_and_wait(inode->i_mapping); + + key.objectid = BTRFS_FREE_SPACE_OBJECTID; + key.offset = block_group->key.objectid; + key.type = 0; + + ret = btrfs_search_slot(trans, root, &key, path, 1, 1); + if (ret < 0) { + ret = 0; + clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, bytes - 1, + EXTENT_DIRTY | EXTENT_DELALLOC | + EXTENT_DO_ACCOUNTING, 0, 0, NULL, GFP_NOFS); + goto out_free; + } + leaf = path->nodes[0]; + if (ret > 0) { + struct btrfs_key found_key; + BUG_ON(!path->slots[0]); + path->slots[0]--; + btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); + if (found_key.objectid != BTRFS_FREE_SPACE_OBJECTID || + found_key.offset != block_group->key.objectid) { + ret = 0; + clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, bytes - 1, + EXTENT_DIRTY | EXTENT_DELALLOC | + EXTENT_DO_ACCOUNTING, 0, 0, NULL, + GFP_NOFS); + btrfs_release_path(root, path); + goto out_free; + } + } + header = btrfs_item_ptr(leaf, path->slots[0], + struct btrfs_free_space_header); + btrfs_set_free_space_entries(leaf, header, entries); + btrfs_set_free_space_bitmaps(leaf, header, bitmaps); + btrfs_set_free_space_generation(leaf, header, trans->transid); + btrfs_mark_buffer_dirty(leaf); + btrfs_release_path(root, path); + + ret = 1; + +out_free: + if (ret == 0) { + invalidate_inode_pages2_range(inode->i_mapping, 0, index); + spin_lock(&block_group->lock); + block_group->disk_cache_state = BTRFS_DC_ERROR; + spin_unlock(&block_group->lock); + BTRFS_I(inode)->generation = 0; + } + kfree(checksums); + btrfs_update_inode(trans, root, inode); + iput(inode); + return ret; +} + static inline unsigned long offset_to_bit(u64 bitmap_start, u64 sectorsize, u64 offset) { diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h index 890a8e79011b..e49ca5c321b5 100644 --- a/fs/btrfs/free-space-cache.h +++ b/fs/btrfs/free-space-cache.h @@ -27,6 +27,24 @@ struct btrfs_free_space { struct list_head list; }; +struct inode *lookup_free_space_inode(struct btrfs_root *root, + struct btrfs_block_group_cache + *block_group, struct btrfs_path *path); +int create_free_space_inode(struct btrfs_root *root, + struct btrfs_trans_handle *trans, + struct btrfs_block_group_cache *block_group, + struct btrfs_path *path); + +int btrfs_truncate_free_space_cache(struct btrfs_root *root, + struct btrfs_trans_handle *trans, + struct btrfs_path *path, + struct inode *inode); +int load_free_space_cache(struct btrfs_fs_info *fs_info, + struct btrfs_block_group_cache *block_group); +int btrfs_write_out_cache(struct btrfs_root *root, + struct btrfs_trans_handle *trans, + struct btrfs_block_group_cache *block_group, + struct btrfs_path *path); int btrfs_add_free_space(struct btrfs_block_group_cache *block_group, u64 bytenr, u64 size); int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c03864406af3..8039390bd6a6 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -319,8 +319,6 @@ static noinline int compress_file_range(struct inode *inode, struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_trans_handle *trans; u64 num_bytes; - u64 orig_start; - u64 disk_num_bytes; u64 blocksize = root->sectorsize; u64 actual_end; u64 isize = i_size_read(inode); @@ -335,8 +333,6 @@ static noinline int compress_file_range(struct inode *inode, int i; int will_compress; - orig_start = start; - actual_end = min_t(u64, isize, end + 1); again: will_compress = 0; @@ -371,7 +367,6 @@ again: total_compressed = min(total_compressed, max_uncompressed); num_bytes = (end - start + blocksize) & ~(blocksize - 1); num_bytes = max(blocksize, num_bytes); - disk_num_bytes = num_bytes; total_in = 0; ret = 0; @@ -467,7 +462,6 @@ again: if (total_compressed >= total_in) { will_compress = 0; } else { - disk_num_bytes = total_compressed; num_bytes = total_in; } } @@ -757,20 +751,17 @@ static noinline int cow_file_range(struct inode *inode, u64 disk_num_bytes; u64 cur_alloc_size; u64 blocksize = root->sectorsize; - u64 actual_end; - u64 isize = i_size_read(inode); struct btrfs_key ins; struct extent_map *em; struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; int ret = 0; + BUG_ON(root == root->fs_info->tree_root); trans = btrfs_join_transaction(root, 1); BUG_ON(!trans); btrfs_set_trans_block_group(trans, inode); trans->block_rsv = &root->fs_info->delalloc_block_rsv; - actual_end = min_t(u64, isize, end + 1); - num_bytes = (end - start + blocksize) & ~(blocksize - 1); num_bytes = max(blocksize, num_bytes); disk_num_bytes = num_bytes; @@ -1035,10 +1026,16 @@ static noinline int run_delalloc_nocow(struct inode *inode, int type; int nocow; int check_prev = 1; + bool nolock = false; path = btrfs_alloc_path(); BUG_ON(!path); - trans = btrfs_join_transaction(root, 1); + if (root == root->fs_info->tree_root) { + nolock = true; + trans = btrfs_join_transaction_nolock(root, 1); + } else { + trans = btrfs_join_transaction(root, 1); + } BUG_ON(!trans); cow_start = (u64)-1; @@ -1211,8 +1208,13 @@ out_check: BUG_ON(ret); } - ret = btrfs_end_transaction(trans, root); - BUG_ON(ret); + if (nolock) { + ret = btrfs_end_transaction_nolock(trans, root); + BUG_ON(ret); + } else { + ret = btrfs_end_transaction(trans, root); + BUG_ON(ret); + } btrfs_free_path(path); return 0; } @@ -1289,6 +1291,8 @@ static int btrfs_set_bit_hook(struct inode *inode, if (!(state->state & EXTENT_DELALLOC) && (*bits & EXTENT_DELALLOC)) { struct btrfs_root *root = BTRFS_I(inode)->root; u64 len = state->end + 1 - state->start; + int do_list = (root->root_key.objectid != + BTRFS_ROOT_TREE_OBJECTID); if (*bits & EXTENT_FIRST_DELALLOC) *bits &= ~EXTENT_FIRST_DELALLOC; @@ -1298,7 +1302,7 @@ static int btrfs_set_bit_hook(struct inode *inode, spin_lock(&root->fs_info->delalloc_lock); BTRFS_I(inode)->delalloc_bytes += len; root->fs_info->delalloc_bytes += len; - if (list_empty(&BTRFS_I(inode)->delalloc_inodes)) { + if (do_list && list_empty(&BTRFS_I(inode)->delalloc_inodes)) { list_add_tail(&BTRFS_I(inode)->delalloc_inodes, &root->fs_info->delalloc_inodes); } @@ -1321,6 +1325,8 @@ static int btrfs_clear_bit_hook(struct inode *inode, if ((state->state & EXTENT_DELALLOC) && (*bits & EXTENT_DELALLOC)) { struct btrfs_root *root = BTRFS_I(inode)->root; u64 len = state->end + 1 - state->start; + int do_list = (root->root_key.objectid != + BTRFS_ROOT_TREE_OBJECTID); if (*bits & EXTENT_FIRST_DELALLOC) *bits &= ~EXTENT_FIRST_DELALLOC; @@ -1330,14 +1336,15 @@ static int btrfs_clear_bit_hook(struct inode *inode, if (*bits & EXTENT_DO_ACCOUNTING) btrfs_delalloc_release_metadata(inode, len); - if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) + if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID + && do_list) btrfs_free_reserved_data_space(inode, len); spin_lock(&root->fs_info->delalloc_lock); root->fs_info->delalloc_bytes -= len; BTRFS_I(inode)->delalloc_bytes -= len; - if (BTRFS_I(inode)->delalloc_bytes == 0 && + if (do_list && BTRFS_I(inode)->delalloc_bytes == 0 && !list_empty(&BTRFS_I(inode)->delalloc_inodes)) { list_del_init(&BTRFS_I(inode)->delalloc_inodes); } @@ -1372,7 +1379,7 @@ int btrfs_merge_bio_hook(struct page *page, unsigned long offset, if (map_length < length + size) return 1; - return 0; + return ret; } /* @@ -1426,7 +1433,10 @@ static int btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio, skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM; - ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0); + if (root == root->fs_info->tree_root) + ret = btrfs_bio_wq_end_io(root->fs_info, bio, 2); + else + ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0); BUG_ON(ret); if (!(rw & REQ_WRITE)) { @@ -1662,6 +1672,7 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end) struct extent_state *cached_state = NULL; int compressed = 0; int ret; + bool nolock = false; ret = btrfs_dec_test_ordered_pending(inode, &ordered_extent, start, end - start + 1); @@ -1669,11 +1680,17 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end) return 0; BUG_ON(!ordered_extent); + nolock = (root == root->fs_info->tree_root); + if (test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags)) { BUG_ON(!list_empty(&ordered_extent->list)); ret = btrfs_ordered_update_i_size(inode, 0, ordered_extent); if (!ret) { - trans = btrfs_join_transaction(root, 1); + if (nolock) + trans = btrfs_join_transaction_nolock(root, 1); + else + trans = btrfs_join_transaction(root, 1); + BUG_ON(!trans); btrfs_set_trans_block_group(trans, inode); trans->block_rsv = &root->fs_info->delalloc_block_rsv; ret = btrfs_update_inode(trans, root, inode); @@ -1686,7 +1703,10 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end) ordered_extent->file_offset + ordered_extent->len - 1, 0, &cached_state, GFP_NOFS); - trans = btrfs_join_transaction(root, 1); + if (nolock) + trans = btrfs_join_transaction_nolock(root, 1); + else + trans = btrfs_join_transaction(root, 1); btrfs_set_trans_block_group(trans, inode); trans->block_rsv = &root->fs_info->delalloc_block_rsv; @@ -1700,6 +1720,7 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end) ordered_extent->len); BUG_ON(ret); } else { + BUG_ON(root == root->fs_info->tree_root); ret = insert_reserved_file_extent(trans, inode, ordered_extent->file_offset, ordered_extent->start, @@ -1724,9 +1745,15 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end) ret = btrfs_update_inode(trans, root, inode); BUG_ON(ret); out: - btrfs_delalloc_release_metadata(inode, ordered_extent->len); - if (trans) - btrfs_end_transaction(trans, root); + if (nolock) { + if (trans) + btrfs_end_transaction_nolock(trans, root); + } else { + btrfs_delalloc_release_metadata(inode, ordered_extent->len); + if (trans) + btrfs_end_transaction(trans, root); + } + /* once for us */ btrfs_put_ordered_extent(ordered_extent); /* once for the tree */ @@ -2237,7 +2264,6 @@ void btrfs_orphan_cleanup(struct btrfs_root *root) { struct btrfs_path *path; struct extent_buffer *leaf; - struct btrfs_item *item; struct btrfs_key key, found_key; struct btrfs_trans_handle *trans; struct inode *inode; @@ -2275,7 +2301,6 @@ void btrfs_orphan_cleanup(struct btrfs_root *root) /* pull out the item */ leaf = path->nodes[0]; - item = btrfs_item_nr(leaf, path->slots[0]); btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); /* make sure the item matches what we want */ @@ -2651,7 +2676,8 @@ int btrfs_unlink_inode(struct btrfs_trans_handle *trans, ret = btrfs_del_dir_entries_in_log(trans, root, name, name_len, dir, index); - BUG_ON(ret); + if (ret == -ENOENT) + ret = 0; err: btrfs_free_path(path); if (ret) @@ -2672,8 +2698,8 @@ static int check_path_shared(struct btrfs_root *root, { struct extent_buffer *eb; int level; - int ret; u64 refs = 1; + int uninitialized_var(ret); for (level = 0; level < BTRFS_MAX_LEVEL; level++) { if (!path->nodes[level]) @@ -2686,7 +2712,7 @@ static int check_path_shared(struct btrfs_root *root, if (refs > 1) return 1; } - return 0; + return ret; /* XXX callers? */ } /* @@ -3196,7 +3222,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, BUG_ON(new_size > 0 && min_type != BTRFS_EXTENT_DATA_KEY); - if (root->ref_cows) + if (root->ref_cows || root == root->fs_info->tree_root) btrfs_drop_extent_cache(inode, new_size & (~mask), (u64)-1, 0); path = btrfs_alloc_path(); @@ -3344,7 +3370,8 @@ delete: } else { break; } - if (found_extent && root->ref_cows) { + if (found_extent && (root->ref_cows || + root == root->fs_info->tree_root)) { btrfs_set_path_blocking(path); ret = btrfs_free_extent(trans, root, extent_start, extent_num_bytes, 0, @@ -3675,7 +3702,8 @@ void btrfs_evict_inode(struct inode *inode) int ret; truncate_inode_pages(&inode->i_data, 0); - if (inode->i_nlink && btrfs_root_refs(&root->root_item) != 0) + if (inode->i_nlink && (btrfs_root_refs(&root->root_item) != 0 || + root == root->fs_info->tree_root)) goto no_delete; if (is_bad_inode(inode)) { @@ -3849,7 +3877,7 @@ again: p = &root->inode_tree.rb_node; parent = NULL; - if (hlist_unhashed(&inode->i_hash)) + if (inode_unhashed(inode)) return; spin_lock(&root->inode_lock); @@ -3888,7 +3916,14 @@ static void inode_tree_del(struct inode *inode) } spin_unlock(&root->inode_lock); - if (empty && btrfs_root_refs(&root->root_item) == 0) { + /* + * Free space cache has inodes in the tree root, but the tree root has a + * root_refs of 0, so this could end up dropping the tree root as a + * snapshot, so we need the extra !root->fs_info->tree_root check to + * make sure we don't drop it. + */ + if (empty && btrfs_root_refs(&root->root_item) == 0 && + root != root->fs_info->tree_root) { synchronize_srcu(&root->fs_info->subvol_srcu); spin_lock(&root->inode_lock); empty = RB_EMPTY_ROOT(&root->inode_tree); @@ -4282,14 +4317,24 @@ int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc) struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_trans_handle *trans; int ret = 0; + bool nolock = false; if (BTRFS_I(inode)->dummy_inode) return 0; + smp_mb(); + nolock = (root->fs_info->closing && root == root->fs_info->tree_root); + if (wbc->sync_mode == WB_SYNC_ALL) { - trans = btrfs_join_transaction(root, 1); + if (nolock) + trans = btrfs_join_transaction_nolock(root, 1); + else + trans = btrfs_join_transaction(root, 1); btrfs_set_trans_block_group(trans, inode); - ret = btrfs_commit_transaction(trans, root); + if (nolock) + ret = btrfs_end_transaction_nolock(trans, root); + else + ret = btrfs_commit_transaction(trans, root); } return ret; } @@ -4456,6 +4501,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans, BTRFS_I(inode)->index_cnt = 2; BTRFS_I(inode)->root = root; BTRFS_I(inode)->generation = trans->transid; + inode->i_generation = BTRFS_I(inode)->generation; btrfs_set_inode_space_info(root, inode); if (mode & S_IFDIR) @@ -4577,12 +4623,12 @@ int btrfs_add_link(struct btrfs_trans_handle *trans, } static int btrfs_add_nondir(struct btrfs_trans_handle *trans, - struct dentry *dentry, struct inode *inode, - int backref, u64 index) + struct inode *dir, struct dentry *dentry, + struct inode *inode, int backref, u64 index) { - int err = btrfs_add_link(trans, dentry->d_parent->d_inode, - inode, dentry->d_name.name, - dentry->d_name.len, backref, index); + int err = btrfs_add_link(trans, dir, inode, + dentry->d_name.name, dentry->d_name.len, + backref, index); if (!err) { d_instantiate(dentry, inode); return 0; @@ -4623,8 +4669,7 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry, btrfs_set_trans_block_group(trans, dir); inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name, - dentry->d_name.len, - dentry->d_parent->d_inode->i_ino, objectid, + dentry->d_name.len, dir->i_ino, objectid, BTRFS_I(dir)->block_group, mode, &index); err = PTR_ERR(inode); if (IS_ERR(inode)) @@ -4637,7 +4682,7 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry, } btrfs_set_trans_block_group(trans, inode); - err = btrfs_add_nondir(trans, dentry, inode, 0, index); + err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index); if (err) drop_inode = 1; else { @@ -4685,10 +4730,8 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry, btrfs_set_trans_block_group(trans, dir); inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name, - dentry->d_name.len, - dentry->d_parent->d_inode->i_ino, - objectid, BTRFS_I(dir)->block_group, mode, - &index); + dentry->d_name.len, dir->i_ino, objectid, + BTRFS_I(dir)->block_group, mode, &index); err = PTR_ERR(inode); if (IS_ERR(inode)) goto out_unlock; @@ -4700,7 +4743,7 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry, } btrfs_set_trans_block_group(trans, inode); - err = btrfs_add_nondir(trans, dentry, inode, 0, index); + err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index); if (err) drop_inode = 1; else { @@ -4742,6 +4785,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, return -EPERM; btrfs_inc_nlink(inode); + inode->i_ctime = CURRENT_TIME; err = btrfs_set_inode_index(dir, &index); if (err) @@ -4758,17 +4802,19 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, } btrfs_set_trans_block_group(trans, dir); - atomic_inc(&inode->i_count); + ihold(inode); - err = btrfs_add_nondir(trans, dentry, inode, 1, index); + err = btrfs_add_nondir(trans, dir, dentry, inode, 1, index); if (err) { drop_inode = 1; } else { + struct dentry *parent = dget_parent(dentry); btrfs_update_inode_block_group(trans, dir); err = btrfs_update_inode(trans, root, inode); BUG_ON(err); - btrfs_log_new_name(trans, inode, NULL, dentry->d_parent); + btrfs_log_new_name(trans, inode, NULL, parent); + dput(parent); } nr = trans->blocks_used; @@ -4808,8 +4854,7 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) btrfs_set_trans_block_group(trans, dir); inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name, - dentry->d_name.len, - dentry->d_parent->d_inode->i_ino, objectid, + dentry->d_name.len, dir->i_ino, objectid, BTRFS_I(dir)->block_group, S_IFDIR | mode, &index); if (IS_ERR(inode)) { @@ -4832,9 +4877,8 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) if (err) goto out_fail; - err = btrfs_add_link(trans, dentry->d_parent->d_inode, - inode, dentry->d_name.name, - dentry->d_name.len, 0, index); + err = btrfs_add_link(trans, dir, inode, dentry->d_name.name, + dentry->d_name.len, 0, index); if (err) goto out_fail; @@ -5490,13 +5534,21 @@ struct btrfs_dio_private { u64 bytes; u32 *csums; void *private; + + /* number of bios pending for this dio */ + atomic_t pending_bios; + + /* IO errors */ + int errors; + + struct bio *orig_bio; }; static void btrfs_endio_direct_read(struct bio *bio, int err) { + struct btrfs_dio_private *dip = bio->bi_private; struct bio_vec *bvec_end = bio->bi_io_vec + bio->bi_vcnt - 1; struct bio_vec *bvec = bio->bi_io_vec; - struct btrfs_dio_private *dip = bio->bi_private; struct inode *inode = dip->inode; struct btrfs_root *root = BTRFS_I(inode)->root; u64 start; @@ -5550,15 +5602,18 @@ static void btrfs_endio_direct_write(struct bio *bio, int err) struct btrfs_trans_handle *trans; struct btrfs_ordered_extent *ordered = NULL; struct extent_state *cached_state = NULL; + u64 ordered_offset = dip->logical_offset; + u64 ordered_bytes = dip->bytes; int ret; if (err) goto out_done; - - ret = btrfs_dec_test_ordered_pending(inode, &ordered, - dip->logical_offset, dip->bytes); +again: + ret = btrfs_dec_test_first_ordered_pending(inode, &ordered, + &ordered_offset, + ordered_bytes); if (!ret) - goto out_done; + goto out_test; BUG_ON(!ordered); @@ -5618,8 +5673,20 @@ out_unlock: out: btrfs_delalloc_release_metadata(inode, ordered->len); btrfs_end_transaction(trans, root); + ordered_offset = ordered->file_offset + ordered->len; btrfs_put_ordered_extent(ordered); btrfs_put_ordered_extent(ordered); + +out_test: + /* + * our bio might span multiple ordered extents. If we haven't + * completed the accounting for the whole dio, go back and try again + */ + if (ordered_offset < dip->logical_offset + dip->bytes) { + ordered_bytes = dip->logical_offset + dip->bytes - + ordered_offset; + goto again; + } out_done: bio->bi_private = dip->private; @@ -5639,13 +5706,182 @@ static int __btrfs_submit_bio_start_direct_io(struct inode *inode, int rw, return 0; } +static void btrfs_end_dio_bio(struct bio *bio, int err) +{ + struct btrfs_dio_private *dip = bio->bi_private; + + if (err) { + printk(KERN_ERR "btrfs direct IO failed ino %lu rw %lu " + "disk_bytenr %lu len %u err no %d\n", + dip->inode->i_ino, bio->bi_rw, bio->bi_sector, + bio->bi_size, err); + dip->errors = 1; + + /* + * before atomic variable goto zero, we must make sure + * dip->errors is perceived to be set. + */ + smp_mb__before_atomic_dec(); + } + + /* if there are more bios still pending for this dio, just exit */ + if (!atomic_dec_and_test(&dip->pending_bios)) + goto out; + + if (dip->errors) + bio_io_error(dip->orig_bio); + else { + set_bit(BIO_UPTODATE, &dip->orig_bio->bi_flags); + bio_endio(dip->orig_bio, 0); + } +out: + bio_put(bio); +} + +static struct bio *btrfs_dio_bio_alloc(struct block_device *bdev, + u64 first_sector, gfp_t gfp_flags) +{ + int nr_vecs = bio_get_nr_vecs(bdev); + return btrfs_bio_alloc(bdev, first_sector, nr_vecs, gfp_flags); +} + +static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode, + int rw, u64 file_offset, int skip_sum, + u32 *csums) +{ + int write = rw & REQ_WRITE; + struct btrfs_root *root = BTRFS_I(inode)->root; + int ret; + + bio_get(bio); + ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0); + if (ret) + goto err; + + if (write && !skip_sum) { + ret = btrfs_wq_submit_bio(root->fs_info, + inode, rw, bio, 0, 0, + file_offset, + __btrfs_submit_bio_start_direct_io, + __btrfs_submit_bio_done); + goto err; + } else if (!skip_sum) + btrfs_lookup_bio_sums_dio(root, inode, bio, + file_offset, csums); + + ret = btrfs_map_bio(root, rw, bio, 0, 1); +err: + bio_put(bio); + return ret; +} + +static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip, + int skip_sum) +{ + struct inode *inode = dip->inode; + struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_mapping_tree *map_tree = &root->fs_info->mapping_tree; + struct bio *bio; + struct bio *orig_bio = dip->orig_bio; + struct bio_vec *bvec = orig_bio->bi_io_vec; + u64 start_sector = orig_bio->bi_sector; + u64 file_offset = dip->logical_offset; + u64 submit_len = 0; + u64 map_length; + int nr_pages = 0; + u32 *csums = dip->csums; + int ret = 0; + + bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, start_sector, GFP_NOFS); + if (!bio) + return -ENOMEM; + bio->bi_private = dip; + bio->bi_end_io = btrfs_end_dio_bio; + atomic_inc(&dip->pending_bios); + + map_length = orig_bio->bi_size; + ret = btrfs_map_block(map_tree, READ, start_sector << 9, + &map_length, NULL, 0); + if (ret) { + bio_put(bio); + return -EIO; + } + + while (bvec <= (orig_bio->bi_io_vec + orig_bio->bi_vcnt - 1)) { + if (unlikely(map_length < submit_len + bvec->bv_len || + bio_add_page(bio, bvec->bv_page, bvec->bv_len, + bvec->bv_offset) < bvec->bv_len)) { + /* + * inc the count before we submit the bio so + * we know the end IO handler won't happen before + * we inc the count. Otherwise, the dip might get freed + * before we're done setting it up + */ + atomic_inc(&dip->pending_bios); + ret = __btrfs_submit_dio_bio(bio, inode, rw, + file_offset, skip_sum, + csums); + if (ret) { + bio_put(bio); + atomic_dec(&dip->pending_bios); + goto out_err; + } + + if (!skip_sum) + csums = csums + nr_pages; + start_sector += submit_len >> 9; + file_offset += submit_len; + + submit_len = 0; + nr_pages = 0; + + bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, + start_sector, GFP_NOFS); + if (!bio) + goto out_err; + bio->bi_private = dip; + bio->bi_end_io = btrfs_end_dio_bio; + + map_length = orig_bio->bi_size; + ret = btrfs_map_block(map_tree, READ, start_sector << 9, + &map_length, NULL, 0); + if (ret) { + bio_put(bio); + goto out_err; + } + } else { + submit_len += bvec->bv_len; + nr_pages ++; + bvec++; + } + } + + ret = __btrfs_submit_dio_bio(bio, inode, rw, file_offset, skip_sum, + csums); + if (!ret) + return 0; + + bio_put(bio); +out_err: + dip->errors = 1; + /* + * before atomic variable goto zero, we must + * make sure dip->errors is perceived to be set. + */ + smp_mb__before_atomic_dec(); + if (atomic_dec_and_test(&dip->pending_bios)) + bio_io_error(dip->orig_bio); + + /* bio_end_io() will handle error, so we needn't return it */ + return 0; +} + static void btrfs_submit_direct(int rw, struct bio *bio, struct inode *inode, loff_t file_offset) { struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_dio_private *dip; struct bio_vec *bvec = bio->bi_io_vec; - u64 start; int skip_sum; int write = rw & REQ_WRITE; int ret = 0; @@ -5671,7 +5907,6 @@ static void btrfs_submit_direct(int rw, struct bio *bio, struct inode *inode, dip->inode = inode; dip->logical_offset = file_offset; - start = dip->logical_offset; dip->bytes = 0; do { dip->bytes += bvec->bv_len; @@ -5680,36 +5915,18 @@ static void btrfs_submit_direct(int rw, struct bio *bio, struct inode *inode, dip->disk_bytenr = (u64)bio->bi_sector << 9; bio->bi_private = dip; + dip->errors = 0; + dip->orig_bio = bio; + atomic_set(&dip->pending_bios, 0); if (write) bio->bi_end_io = btrfs_endio_direct_write; else bio->bi_end_io = btrfs_endio_direct_read; - ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0); - if (ret) - goto out_err; - - if (write && !skip_sum) { - ret = btrfs_wq_submit_bio(BTRFS_I(inode)->root->fs_info, - inode, rw, bio, 0, 0, - dip->logical_offset, - __btrfs_submit_bio_start_direct_io, - __btrfs_submit_bio_done); - if (ret) - goto out_err; + ret = btrfs_submit_direct_hook(rw, dip, skip_sum); + if (!ret) return; - } else if (!skip_sum) - btrfs_lookup_bio_sums_dio(root, inode, bio, - dip->logical_offset, dip->csums); - - ret = btrfs_map_bio(root, rw, bio, 0, 1); - if (ret) - goto out_err; - return; -out_err: - kfree(dip->csums); - kfree(dip); free_ordered: /* * If this is a write, we need to clean up the reserved space and kill @@ -6308,6 +6525,21 @@ void btrfs_destroy_inode(struct inode *inode) spin_unlock(&root->fs_info->ordered_extent_lock); } + if (root == root->fs_info->tree_root) { + struct btrfs_block_group_cache *block_group; + + block_group = btrfs_lookup_block_group(root->fs_info, + BTRFS_I(inode)->block_group); + if (block_group && block_group->inode == inode) { + spin_lock(&block_group->lock); + block_group->inode = NULL; + spin_unlock(&block_group->lock); + btrfs_put_block_group(block_group); + } else if (block_group) { + btrfs_put_block_group(block_group); + } + } + spin_lock(&root->orphan_lock); if (!list_empty(&BTRFS_I(inode)->i_orphan)) { printk(KERN_INFO "BTRFS: inode %lu still on the orphan list\n", @@ -6340,7 +6572,8 @@ int btrfs_drop_inode(struct inode *inode) { struct btrfs_root *root = BTRFS_I(inode)->root; - if (btrfs_root_refs(&root->root_item) == 0) + if (btrfs_root_refs(&root->root_item) == 0 && + root != root->fs_info->tree_root) return 1; else return generic_drop_inode(inode); @@ -6548,8 +6781,9 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, BUG_ON(ret); if (old_inode->i_ino != BTRFS_FIRST_FREE_OBJECTID) { - btrfs_log_new_name(trans, old_inode, old_dir, - new_dentry->d_parent); + struct dentry *parent = dget_parent(new_dentry); + btrfs_log_new_name(trans, old_inode, old_dir, parent); + dput(parent); btrfs_end_log_trans(root); } out_fail: @@ -6609,7 +6843,8 @@ int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput) return 0; } -int btrfs_start_one_delalloc_inode(struct btrfs_root *root, int delay_iput) +int btrfs_start_one_delalloc_inode(struct btrfs_root *root, int delay_iput, + int sync) { struct btrfs_inode *binode; struct inode *inode = NULL; @@ -6631,7 +6866,26 @@ int btrfs_start_one_delalloc_inode(struct btrfs_root *root, int delay_iput) spin_unlock(&root->fs_info->delalloc_lock); if (inode) { - write_inode_now(inode, 0); + if (sync) { + filemap_write_and_wait(inode->i_mapping); + /* + * We have to do this because compression doesn't + * actually set PG_writeback until it submits the pages + * for IO, which happens in an async thread, so we could + * race and not actually wait for any writeback pages + * because they've not been submitted yet. Technically + * this could still be the case for the ordered stuff + * since the async thread may not have started to do its + * work yet. If this becomes the case then we need to + * figure out a way to make sure that in writepage we + * wait for any async pages to be submitted before + * returning so that fdatawait does what its supposed to + * do. + */ + btrfs_wait_ordered_range(inode, 0, (u64)-1); + } else { + filemap_flush(inode->i_mapping); + } if (delay_iput) btrfs_add_delayed_iput(inode); else @@ -6679,8 +6933,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, btrfs_set_trans_block_group(trans, dir); inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name, - dentry->d_name.len, - dentry->d_parent->d_inode->i_ino, objectid, + dentry->d_name.len, dir->i_ino, objectid, BTRFS_I(dir)->block_group, S_IFLNK|S_IRWXUGO, &index); err = PTR_ERR(inode); @@ -6694,7 +6947,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, } btrfs_set_trans_block_group(trans, inode); - err = btrfs_add_nondir(trans, dentry, inode, 0, index); + err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index); if (err) drop_inode = 1; else { @@ -6757,27 +7010,34 @@ out_unlock: return err; } -int btrfs_prealloc_file_range(struct inode *inode, int mode, - u64 start, u64 num_bytes, u64 min_size, - loff_t actual_len, u64 *alloc_hint) +static int __btrfs_prealloc_file_range(struct inode *inode, int mode, + u64 start, u64 num_bytes, u64 min_size, + loff_t actual_len, u64 *alloc_hint, + struct btrfs_trans_handle *trans) { - struct btrfs_trans_handle *trans; struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_key ins; u64 cur_offset = start; + u64 i_size; int ret = 0; + bool own_trans = true; + if (trans) + own_trans = false; while (num_bytes > 0) { - trans = btrfs_start_transaction(root, 3); - if (IS_ERR(trans)) { - ret = PTR_ERR(trans); - break; + if (own_trans) { + trans = btrfs_start_transaction(root, 3); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + break; + } } ret = btrfs_reserve_extent(trans, root, num_bytes, min_size, 0, *alloc_hint, (u64)-1, &ins, 1); if (ret) { - btrfs_end_transaction(trans, root); + if (own_trans) + btrfs_end_transaction(trans, root); break; } @@ -6800,21 +7060,40 @@ int btrfs_prealloc_file_range(struct inode *inode, int mode, (actual_len > inode->i_size) && (cur_offset > inode->i_size)) { if (cur_offset > actual_len) - i_size_write(inode, actual_len); + i_size = actual_len; else - i_size_write(inode, cur_offset); - i_size_write(inode, cur_offset); - btrfs_ordered_update_i_size(inode, cur_offset, NULL); + i_size = cur_offset; + i_size_write(inode, i_size); + btrfs_ordered_update_i_size(inode, i_size, NULL); } ret = btrfs_update_inode(trans, root, inode); BUG_ON(ret); - btrfs_end_transaction(trans, root); + if (own_trans) + btrfs_end_transaction(trans, root); } return ret; } +int btrfs_prealloc_file_range(struct inode *inode, int mode, + u64 start, u64 num_bytes, u64 min_size, + loff_t actual_len, u64 *alloc_hint) +{ + return __btrfs_prealloc_file_range(inode, mode, start, num_bytes, + min_size, actual_len, alloc_hint, + NULL); +} + +int btrfs_prealloc_file_range_trans(struct inode *inode, + struct btrfs_trans_handle *trans, int mode, + u64 start, u64 num_bytes, u64 min_size, + loff_t actual_len, u64 *alloc_hint) +{ + return __btrfs_prealloc_file_range(inode, mode, start, num_bytes, + min_size, actual_len, alloc_hint, trans); +} + static long btrfs_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len) { @@ -6839,6 +7118,10 @@ static long btrfs_fallocate(struct inode *inode, int mode, btrfs_wait_ordered_range(inode, alloc_start, alloc_end - alloc_start); mutex_lock(&inode->i_mutex); + ret = inode_newsize_ok(inode, alloc_end); + if (ret) + goto out; + if (alloc_start > inode->i_size) { ret = btrfs_cont_expand(inode, alloc_start); if (ret) @@ -7035,6 +7318,7 @@ static const struct inode_operations btrfs_symlink_inode_operations = { .readlink = generic_readlink, .follow_link = page_follow_link_light, .put_link = page_put_link, + .getattr = btrfs_getattr, .permission = btrfs_permission, .setxattr = btrfs_setxattr, .getxattr = btrfs_getxattr, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 9254b3d58dbe..f1c9bb4079ed 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -224,7 +224,8 @@ static int btrfs_ioctl_getversion(struct file *file, int __user *arg) static noinline int create_subvol(struct btrfs_root *root, struct dentry *dentry, - char *name, int namelen) + char *name, int namelen, + u64 *async_transid) { struct btrfs_trans_handle *trans; struct btrfs_key key; @@ -232,7 +233,8 @@ static noinline int create_subvol(struct btrfs_root *root, struct btrfs_inode_item *inode_item; struct extent_buffer *leaf; struct btrfs_root *new_root; - struct inode *dir = dentry->d_parent->d_inode; + struct dentry *parent = dget_parent(dentry); + struct inode *dir; int ret; int err; u64 objectid; @@ -241,8 +243,13 @@ static noinline int create_subvol(struct btrfs_root *root, ret = btrfs_find_free_objectid(NULL, root->fs_info->tree_root, 0, &objectid); - if (ret) + if (ret) { + dput(parent); return ret; + } + + dir = parent->d_inode; + /* * 1 - inode item * 2 - refs @@ -250,8 +257,10 @@ static noinline int create_subvol(struct btrfs_root *root, * 2 - dir items */ trans = btrfs_start_transaction(root, 6); - if (IS_ERR(trans)) + if (IS_ERR(trans)) { + dput(parent); return PTR_ERR(trans); + } leaf = btrfs_alloc_free_block(trans, root, root->leafsize, 0, objectid, NULL, 0, 0, 0); @@ -338,15 +347,23 @@ static noinline int create_subvol(struct btrfs_root *root, d_instantiate(dentry, btrfs_lookup_dentry(dir, dentry)); fail: - err = btrfs_commit_transaction(trans, root); + dput(parent); + if (async_transid) { + *async_transid = trans->transid; + err = btrfs_commit_transaction_async(trans, root, 1); + } else { + err = btrfs_commit_transaction(trans, root); + } if (err && !ret) ret = err; return ret; } -static int create_snapshot(struct btrfs_root *root, struct dentry *dentry) +static int create_snapshot(struct btrfs_root *root, struct dentry *dentry, + char *name, int namelen, u64 *async_transid) { struct inode *inode; + struct dentry *parent; struct btrfs_pending_snapshot *pending_snapshot; struct btrfs_trans_handle *trans; int ret; @@ -373,7 +390,14 @@ static int create_snapshot(struct btrfs_root *root, struct dentry *dentry) list_add(&pending_snapshot->list, &trans->transaction->pending_snapshots); - ret = btrfs_commit_transaction(trans, root->fs_info->extent_root); + if (async_transid) { + *async_transid = trans->transid; + ret = btrfs_commit_transaction_async(trans, + root->fs_info->extent_root, 1); + } else { + ret = btrfs_commit_transaction(trans, + root->fs_info->extent_root); + } BUG_ON(ret); ret = pending_snapshot->error; @@ -382,7 +406,9 @@ static int create_snapshot(struct btrfs_root *root, struct dentry *dentry) btrfs_orphan_cleanup(pending_snapshot->snap); - inode = btrfs_lookup_dentry(dentry->d_parent->d_inode, dentry); + parent = dget_parent(dentry); + inode = btrfs_lookup_dentry(parent->d_inode, dentry); + dput(parent); if (IS_ERR(inode)) { ret = PTR_ERR(inode); goto fail; @@ -395,6 +421,76 @@ fail: return ret; } +/* copy of check_sticky in fs/namei.c() +* It's inline, so penalty for filesystems that don't use sticky bit is +* minimal. +*/ +static inline int btrfs_check_sticky(struct inode *dir, struct inode *inode) +{ + uid_t fsuid = current_fsuid(); + + if (!(dir->i_mode & S_ISVTX)) + return 0; + if (inode->i_uid == fsuid) + return 0; + if (dir->i_uid == fsuid) + return 0; + return !capable(CAP_FOWNER); +} + +/* copy of may_delete in fs/namei.c() + * Check whether we can remove a link victim from directory dir, check + * whether the type of victim is right. + * 1. We can't do it if dir is read-only (done in permission()) + * 2. We should have write and exec permissions on dir + * 3. We can't remove anything from append-only dir + * 4. We can't do anything with immutable dir (done in permission()) + * 5. If the sticky bit on dir is set we should either + * a. be owner of dir, or + * b. be owner of victim, or + * c. have CAP_FOWNER capability + * 6. If the victim is append-only or immutable we can't do antyhing with + * links pointing to it. + * 7. If we were asked to remove a directory and victim isn't one - ENOTDIR. + * 8. If we were asked to remove a non-directory and victim isn't one - EISDIR. + * 9. We can't remove a root or mountpoint. + * 10. We don't allow removal of NFS sillyrenamed files; it's handled by + * nfs_async_unlink(). + */ + +static int btrfs_may_delete(struct inode *dir,struct dentry *victim,int isdir) +{ + int error; + + if (!victim->d_inode) + return -ENOENT; + + BUG_ON(victim->d_parent->d_inode != dir); + audit_inode_child(victim, dir); + + error = inode_permission(dir, MAY_WRITE | MAY_EXEC); + if (error) + return error; + if (IS_APPEND(dir)) + return -EPERM; + if (btrfs_check_sticky(dir, victim->d_inode)|| + IS_APPEND(victim->d_inode)|| + IS_IMMUTABLE(victim->d_inode) || IS_SWAPFILE(victim->d_inode)) + return -EPERM; + if (isdir) { + if (!S_ISDIR(victim->d_inode->i_mode)) + return -ENOTDIR; + if (IS_ROOT(victim)) + return -EBUSY; + } else if (S_ISDIR(victim->d_inode->i_mode)) + return -EISDIR; + if (IS_DEADDIR(dir)) + return -ENOENT; + if (victim->d_flags & DCACHE_NFSFS_RENAMED) + return -EBUSY; + return 0; +} + /* copy of may_create in fs/namei.c() */ static inline int btrfs_may_create(struct inode *dir, struct dentry *child) { @@ -412,7 +508,8 @@ static inline int btrfs_may_create(struct inode *dir, struct dentry *child) */ static noinline int btrfs_mksubvol(struct path *parent, char *name, int namelen, - struct btrfs_root *snap_src) + struct btrfs_root *snap_src, + u64 *async_transid) { struct inode *dir = parent->dentry->d_inode; struct dentry *dentry; @@ -443,10 +540,11 @@ static noinline int btrfs_mksubvol(struct path *parent, goto out_up_read; if (snap_src) { - error = create_snapshot(snap_src, dentry); + error = create_snapshot(snap_src, dentry, + name, namelen, async_transid); } else { error = create_subvol(BTRFS_I(dir)->root, dentry, - name, namelen); + name, namelen, async_transid); } if (!error) fsnotify_mkdir(dir, dentry); @@ -708,7 +806,6 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, char *sizestr; char *devstr = NULL; int ret = 0; - int namelen; int mod = 0; if (root->fs_info->sb->s_flags & MS_RDONLY) @@ -722,7 +819,6 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, return PTR_ERR(vol_args); vol_args->name[BTRFS_PATH_NAME_MAX] = '\0'; - namelen = strlen(vol_args->name); mutex_lock(&root->fs_info->volume_mutex); sizestr = vol_args->name; @@ -801,11 +897,13 @@ out_unlock: return ret; } -static noinline int btrfs_ioctl_snap_create(struct file *file, - void __user *arg, int subvol) +static noinline int btrfs_ioctl_snap_create_transid(struct file *file, + char *name, + unsigned long fd, + int subvol, + u64 *transid) { struct btrfs_root *root = BTRFS_I(fdentry(file)->d_inode)->root; - struct btrfs_ioctl_vol_args *vol_args; struct file *src_file; int namelen; int ret = 0; @@ -813,23 +911,18 @@ static noinline int btrfs_ioctl_snap_create(struct file *file, if (root->fs_info->sb->s_flags & MS_RDONLY) return -EROFS; - vol_args = memdup_user(arg, sizeof(*vol_args)); - if (IS_ERR(vol_args)) - return PTR_ERR(vol_args); - - vol_args->name[BTRFS_PATH_NAME_MAX] = '\0'; - namelen = strlen(vol_args->name); - if (strchr(vol_args->name, '/')) { + namelen = strlen(name); + if (strchr(name, '/')) { ret = -EINVAL; goto out; } if (subvol) { - ret = btrfs_mksubvol(&file->f_path, vol_args->name, namelen, - NULL); + ret = btrfs_mksubvol(&file->f_path, name, namelen, + NULL, transid); } else { struct inode *src_inode; - src_file = fget(vol_args->fd); + src_file = fget(fd); if (!src_file) { ret = -EINVAL; goto out; @@ -843,12 +936,56 @@ static noinline int btrfs_ioctl_snap_create(struct file *file, fput(src_file); goto out; } - ret = btrfs_mksubvol(&file->f_path, vol_args->name, namelen, - BTRFS_I(src_inode)->root); + ret = btrfs_mksubvol(&file->f_path, name, namelen, + BTRFS_I(src_inode)->root, + transid); fput(src_file); } out: + return ret; +} + +static noinline int btrfs_ioctl_snap_create(struct file *file, + void __user *arg, int subvol, + int async) +{ + struct btrfs_ioctl_vol_args *vol_args = NULL; + struct btrfs_ioctl_async_vol_args *async_vol_args = NULL; + char *name; + u64 fd; + u64 transid = 0; + int ret; + + if (async) { + async_vol_args = memdup_user(arg, sizeof(*async_vol_args)); + if (IS_ERR(async_vol_args)) + return PTR_ERR(async_vol_args); + + name = async_vol_args->name; + fd = async_vol_args->fd; + async_vol_args->name[BTRFS_SNAPSHOT_NAME_MAX] = '\0'; + } else { + vol_args = memdup_user(arg, sizeof(*vol_args)); + if (IS_ERR(vol_args)) + return PTR_ERR(vol_args); + name = vol_args->name; + fd = vol_args->fd; + vol_args->name[BTRFS_PATH_NAME_MAX] = '\0'; + } + + ret = btrfs_ioctl_snap_create_transid(file, name, fd, + subvol, &transid); + + if (!ret && async) { + if (copy_to_user(arg + + offsetof(struct btrfs_ioctl_async_vol_args, + transid), &transid, sizeof(transid))) + return -EFAULT; + } + kfree(vol_args); + kfree(async_vol_args); + return ret; } @@ -1073,14 +1210,10 @@ static noinline int btrfs_ioctl_tree_search(struct file *file, if (!capable(CAP_SYS_ADMIN)) return -EPERM; - args = kmalloc(sizeof(*args), GFP_KERNEL); - if (!args) - return -ENOMEM; + args = memdup_user(argp, sizeof(*args)); + if (IS_ERR(args)) + return PTR_ERR(args); - if (copy_from_user(args, argp, sizeof(*args))) { - kfree(args); - return -EFAULT; - } inode = fdentry(file)->d_inode; ret = search_ioctl(inode, args); if (ret == 0 && copy_to_user(argp, args, sizeof(*args))) @@ -1188,14 +1321,10 @@ static noinline int btrfs_ioctl_ino_lookup(struct file *file, if (!capable(CAP_SYS_ADMIN)) return -EPERM; - args = kmalloc(sizeof(*args), GFP_KERNEL); - if (!args) - return -ENOMEM; + args = memdup_user(argp, sizeof(*args)); + if (IS_ERR(args)) + return PTR_ERR(args); - if (copy_from_user(args, argp, sizeof(*args))) { - kfree(args); - return -EFAULT; - } inode = fdentry(file)->d_inode; if (args->treeid == 0) @@ -1227,9 +1356,6 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, int ret; int err = 0; - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - vol_args = memdup_user(arg, sizeof(*vol_args)); if (IS_ERR(vol_args)) return PTR_ERR(vol_args); @@ -1259,13 +1385,51 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, } inode = dentry->d_inode; + dest = BTRFS_I(inode)->root; + if (!capable(CAP_SYS_ADMIN)){ + /* + * Regular user. Only allow this with a special mount + * option, when the user has write+exec access to the + * subvol root, and when rmdir(2) would have been + * allowed. + * + * Note that this is _not_ check that the subvol is + * empty or doesn't contain data that we wouldn't + * otherwise be able to delete. + * + * Users who want to delete empty subvols should try + * rmdir(2). + */ + err = -EPERM; + if (!btrfs_test_opt(root, USER_SUBVOL_RM_ALLOWED)) + goto out_dput; + + /* + * Do not allow deletion if the parent dir is the same + * as the dir to be deleted. That means the ioctl + * must be called on the dentry referencing the root + * of the subvol, not a random directory contained + * within it. + */ + err = -EINVAL; + if (root == dest) + goto out_dput; + + err = inode_permission(inode, MAY_WRITE | MAY_EXEC); + if (err) + goto out_dput; + + /* check if subvolume may be deleted by a non-root user */ + err = btrfs_may_delete(dir, dentry, 1); + if (err) + goto out_dput; + } + if (inode->i_ino != BTRFS_FIRST_FREE_OBJECTID) { err = -EINVAL; goto out_dput; } - dest = BTRFS_I(inode)->root; - mutex_lock(&inode->i_mutex); err = d_invalidate(dentry); if (err) @@ -1304,7 +1468,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, BUG_ON(ret); } - ret = btrfs_commit_transaction(trans, root); + ret = btrfs_end_transaction(trans, root); BUG_ON(ret); inode->i_flags |= S_DEAD; out_up_write: @@ -1502,11 +1666,11 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, path->reada = 2; if (inode < src) { - mutex_lock(&inode->i_mutex); - mutex_lock(&src->i_mutex); + mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&src->i_mutex, I_MUTEX_CHILD); } else { - mutex_lock(&src->i_mutex); - mutex_lock(&inode->i_mutex); + mutex_lock_nested(&src->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD); } /* determine range to clone */ @@ -1517,12 +1681,11 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, olen = len = src->i_size - off; /* if we extend to eof, continue to block boundary */ if (off + len == src->i_size) - len = ((src->i_size + bs-1) & ~(bs-1)) - - off; + len = ALIGN(src->i_size, bs) - off; /* verify the end result is block aligned */ - if ((off & (bs-1)) || - ((off + len) & (bs-1))) + if (!IS_ALIGNED(off, bs) || !IS_ALIGNED(off + len, bs) || + !IS_ALIGNED(destoff, bs)) goto out_unlock; /* do any pending delalloc/csum calc on src, one way or @@ -1530,13 +1693,15 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, while (1) { struct btrfs_ordered_extent *ordered; lock_extent(&BTRFS_I(src)->io_tree, off, off+len, GFP_NOFS); - ordered = btrfs_lookup_first_ordered_extent(inode, off+len); - if (BTRFS_I(src)->delalloc_bytes == 0 && !ordered) + ordered = btrfs_lookup_first_ordered_extent(src, off+len); + if (!ordered && + !test_range_bit(&BTRFS_I(src)->io_tree, off, off+len, + EXTENT_DELALLOC, 0, NULL)) break; unlock_extent(&BTRFS_I(src)->io_tree, off, off+len, GFP_NOFS); if (ordered) btrfs_put_ordered_extent(ordered); - btrfs_wait_ordered_range(src, off, off+len); + btrfs_wait_ordered_range(src, off, len); } /* clone data */ @@ -1605,7 +1770,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, } btrfs_release_path(root, path); - if (key.offset + datal < off || + if (key.offset + datal <= off || key.offset >= off+len) goto next; @@ -1720,8 +1885,8 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, * but shouldn't round up the file size */ endoff = new_key.offset + datal; - if (endoff > off+olen) - endoff = off+olen; + if (endoff > destoff+olen) + endoff = destoff+olen; if (endoff > inode->i_size) btrfs_i_size_write(inode, endoff); @@ -1879,6 +2044,22 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) return 0; } +static void get_block_group_info(struct list_head *groups_list, + struct btrfs_ioctl_space_info *space) +{ + struct btrfs_block_group_cache *block_group; + + space->total_bytes = 0; + space->used_bytes = 0; + space->flags = 0; + list_for_each_entry(block_group, groups_list, list) { + space->flags = block_group->flags; + space->total_bytes += block_group->key.offset; + space->used_bytes += + btrfs_block_group_used(&block_group->item); + } +} + long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg) { struct btrfs_ioctl_space_args space_args; @@ -1887,27 +2068,56 @@ long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg) struct btrfs_ioctl_space_info *dest_orig; struct btrfs_ioctl_space_info *user_dest; struct btrfs_space_info *info; + u64 types[] = {BTRFS_BLOCK_GROUP_DATA, + BTRFS_BLOCK_GROUP_SYSTEM, + BTRFS_BLOCK_GROUP_METADATA, + BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_METADATA}; + int num_types = 4; int alloc_size; int ret = 0; int slot_count = 0; + int i, c; if (copy_from_user(&space_args, (struct btrfs_ioctl_space_args __user *)arg, sizeof(space_args))) return -EFAULT; - /* first we count slots */ - rcu_read_lock(); - list_for_each_entry_rcu(info, &root->fs_info->space_info, list) - slot_count++; - rcu_read_unlock(); + for (i = 0; i < num_types; i++) { + struct btrfs_space_info *tmp; + + info = NULL; + rcu_read_lock(); + list_for_each_entry_rcu(tmp, &root->fs_info->space_info, + list) { + if (tmp->flags == types[i]) { + info = tmp; + break; + } + } + rcu_read_unlock(); + + if (!info) + continue; + + down_read(&info->groups_sem); + for (c = 0; c < BTRFS_NR_RAID_TYPES; c++) { + if (!list_empty(&info->block_groups[c])) + slot_count++; + } + up_read(&info->groups_sem); + } /* space_slots == 0 means they are asking for a count */ if (space_args.space_slots == 0) { space_args.total_spaces = slot_count; goto out; } + + slot_count = min_t(int, space_args.space_slots, slot_count); + alloc_size = sizeof(*dest) * slot_count; + /* we generally have at most 6 or so space infos, one for each raid * level. So, a whole page should be more than enough for everyone */ @@ -1921,27 +2131,34 @@ long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg) dest_orig = dest; /* now we have a buffer to copy into */ - rcu_read_lock(); - list_for_each_entry_rcu(info, &root->fs_info->space_info, list) { - /* make sure we don't copy more than we allocated - * in our buffer - */ - if (slot_count == 0) - break; - slot_count--; - - /* make sure userland has enough room in their buffer */ - if (space_args.total_spaces >= space_args.space_slots) - break; + for (i = 0; i < num_types; i++) { + struct btrfs_space_info *tmp; + + info = NULL; + rcu_read_lock(); + list_for_each_entry_rcu(tmp, &root->fs_info->space_info, + list) { + if (tmp->flags == types[i]) { + info = tmp; + break; + } + } + rcu_read_unlock(); - space.flags = info->flags; - space.total_bytes = info->total_bytes; - space.used_bytes = info->bytes_used; - memcpy(dest, &space, sizeof(space)); - dest++; - space_args.total_spaces++; + if (!info) + continue; + down_read(&info->groups_sem); + for (c = 0; c < BTRFS_NR_RAID_TYPES; c++) { + if (!list_empty(&info->block_groups[c])) { + get_block_group_info(&info->block_groups[c], + &space); + memcpy(dest, &space, sizeof(space)); + dest++; + space_args.total_spaces++; + } + } + up_read(&info->groups_sem); } - rcu_read_unlock(); user_dest = (struct btrfs_ioctl_space_info *) (arg + sizeof(struct btrfs_ioctl_space_args)); @@ -1984,6 +2201,36 @@ long btrfs_ioctl_trans_end(struct file *file) return 0; } +static noinline long btrfs_ioctl_start_sync(struct file *file, void __user *argp) +{ + struct btrfs_root *root = BTRFS_I(file->f_dentry->d_inode)->root; + struct btrfs_trans_handle *trans; + u64 transid; + + trans = btrfs_start_transaction(root, 0); + transid = trans->transid; + btrfs_commit_transaction_async(trans, root, 0); + + if (argp) + if (copy_to_user(argp, &transid, sizeof(transid))) + return -EFAULT; + return 0; +} + +static noinline long btrfs_ioctl_wait_sync(struct file *file, void __user *argp) +{ + struct btrfs_root *root = BTRFS_I(file->f_dentry->d_inode)->root; + u64 transid; + + if (argp) { + if (copy_from_user(&transid, argp, sizeof(transid))) + return -EFAULT; + } else { + transid = 0; /* current trans */ + } + return btrfs_wait_for_commit(root, transid); +} + long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -1998,9 +2245,11 @@ long btrfs_ioctl(struct file *file, unsigned int case FS_IOC_GETVERSION: return btrfs_ioctl_getversion(file, argp); case BTRFS_IOC_SNAP_CREATE: - return btrfs_ioctl_snap_create(file, argp, 0); + return btrfs_ioctl_snap_create(file, argp, 0, 0); + case BTRFS_IOC_SNAP_CREATE_ASYNC: + return btrfs_ioctl_snap_create(file, argp, 0, 1); case BTRFS_IOC_SUBVOL_CREATE: - return btrfs_ioctl_snap_create(file, argp, 1); + return btrfs_ioctl_snap_create(file, argp, 1, 0); case BTRFS_IOC_SNAP_DESTROY: return btrfs_ioctl_snap_destroy(file, argp); case BTRFS_IOC_DEFAULT_SUBVOL: @@ -2034,6 +2283,10 @@ long btrfs_ioctl(struct file *file, unsigned int case BTRFS_IOC_SYNC: btrfs_sync_fs(file->f_dentry->d_sb, 1); return 0; + case BTRFS_IOC_START_SYNC: + return btrfs_ioctl_start_sync(file, argp); + case BTRFS_IOC_WAIT_SYNC: + return btrfs_ioctl_wait_sync(file, argp); } return -ENOTTY; diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h index 424694aa517f..17c99ebdf960 100644 --- a/fs/btrfs/ioctl.h +++ b/fs/btrfs/ioctl.h @@ -22,14 +22,21 @@ #define BTRFS_IOCTL_MAGIC 0x94 #define BTRFS_VOL_NAME_MAX 255 -#define BTRFS_PATH_NAME_MAX 4087 /* this should be 4k */ +#define BTRFS_PATH_NAME_MAX 4087 struct btrfs_ioctl_vol_args { __s64 fd; char name[BTRFS_PATH_NAME_MAX + 1]; }; +#define BTRFS_SNAPSHOT_NAME_MAX 4079 +struct btrfs_ioctl_async_vol_args { + __s64 fd; + __u64 transid; + char name[BTRFS_SNAPSHOT_NAME_MAX + 1]; +}; + #define BTRFS_INO_LOOKUP_PATH_MAX 4080 struct btrfs_ioctl_ino_lookup_args { __u64 treeid; @@ -178,4 +185,8 @@ struct btrfs_ioctl_space_args { #define BTRFS_IOC_DEFAULT_SUBVOL _IOW(BTRFS_IOCTL_MAGIC, 19, u64) #define BTRFS_IOC_SPACE_INFO _IOWR(BTRFS_IOCTL_MAGIC, 20, \ struct btrfs_ioctl_space_args) +#define BTRFS_IOC_START_SYNC _IOR(BTRFS_IOCTL_MAGIC, 24, __u64) +#define BTRFS_IOC_WAIT_SYNC _IOW(BTRFS_IOCTL_MAGIC, 22, __u64) +#define BTRFS_IOC_SNAP_CREATE_ASYNC _IOW(BTRFS_IOCTL_MAGIC, 23, \ + struct btrfs_ioctl_async_vol_args) #endif diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index e56c72bc5add..ae7737e352c9 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -250,6 +250,73 @@ int btrfs_add_ordered_sum(struct inode *inode, /* * this is used to account for finished IO across a given range + * of the file. The IO may span ordered extents. If + * a given ordered_extent is completely done, 1 is returned, otherwise + * 0. + * + * test_and_set_bit on a flag in the struct btrfs_ordered_extent is used + * to make sure this function only returns 1 once for a given ordered extent. + * + * file_offset is updated to one byte past the range that is recorded as + * complete. This allows you to walk forward in the file. + */ +int btrfs_dec_test_first_ordered_pending(struct inode *inode, + struct btrfs_ordered_extent **cached, + u64 *file_offset, u64 io_size) +{ + struct btrfs_ordered_inode_tree *tree; + struct rb_node *node; + struct btrfs_ordered_extent *entry = NULL; + int ret; + u64 dec_end; + u64 dec_start; + u64 to_dec; + + tree = &BTRFS_I(inode)->ordered_tree; + spin_lock(&tree->lock); + node = tree_search(tree, *file_offset); + if (!node) { + ret = 1; + goto out; + } + + entry = rb_entry(node, struct btrfs_ordered_extent, rb_node); + if (!offset_in_entry(entry, *file_offset)) { + ret = 1; + goto out; + } + + dec_start = max(*file_offset, entry->file_offset); + dec_end = min(*file_offset + io_size, entry->file_offset + + entry->len); + *file_offset = dec_end; + if (dec_start > dec_end) { + printk(KERN_CRIT "bad ordering dec_start %llu end %llu\n", + (unsigned long long)dec_start, + (unsigned long long)dec_end); + } + to_dec = dec_end - dec_start; + if (to_dec > entry->bytes_left) { + printk(KERN_CRIT "bad ordered accounting left %llu size %llu\n", + (unsigned long long)entry->bytes_left, + (unsigned long long)to_dec); + } + entry->bytes_left -= to_dec; + if (entry->bytes_left == 0) + ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags); + else + ret = 1; +out: + if (!ret && cached && entry) { + *cached = entry; + atomic_inc(&entry->refs); + } + spin_unlock(&tree->lock); + return ret == 0; +} + +/* + * this is used to account for finished IO across a given range * of the file. The IO should not span ordered extents. If * a given ordered_extent is completely done, 1 is returned, otherwise * 0. @@ -526,7 +593,6 @@ int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len) { u64 end; u64 orig_end; - u64 wait_end; struct btrfs_ordered_extent *ordered; int found; @@ -537,7 +603,6 @@ int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len) if (orig_end > INT_LIMIT(loff_t)) orig_end = INT_LIMIT(loff_t); } - wait_end = orig_end; again: /* start IO across the range first to instantiate any delalloc * extents diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index 8ac365492a3f..61dca83119dd 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -141,6 +141,9 @@ int btrfs_remove_ordered_extent(struct inode *inode, int btrfs_dec_test_ordered_pending(struct inode *inode, struct btrfs_ordered_extent **cached, u64 file_offset, u64 io_size); +int btrfs_dec_test_first_ordered_pending(struct inode *inode, + struct btrfs_ordered_extent **cached, + u64 *file_offset, u64 io_size); int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset, u64 start, u64 len, u64 disk_len, int type); int btrfs_add_ordered_extent_dio(struct inode *inode, u64 file_offset, diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index b37d723b9d4a..045c9c2b2d7e 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -29,6 +29,7 @@ #include "locking.h" #include "btrfs_inode.h" #include "async-thread.h" +#include "free-space-cache.h" /* * backref_node, mapping_node and tree_block start with this @@ -178,8 +179,6 @@ struct reloc_control { u64 search_start; u64 extents_found; - int block_rsv_retries; - unsigned int stage:8; unsigned int create_reloc_tree:1; unsigned int merge_reloc_tree:1; @@ -2133,7 +2132,6 @@ int prepare_to_merge(struct reloc_control *rc, int err) LIST_HEAD(reloc_roots); u64 num_bytes = 0; int ret; - int retries = 0; mutex_lock(&root->fs_info->trans_mutex); rc->merging_rsv_size += root->nodesize * (BTRFS_MAX_LEVEL - 1) * 2; @@ -2143,7 +2141,7 @@ again: if (!err) { num_bytes = rc->merging_rsv_size; ret = btrfs_block_rsv_add(NULL, root, rc->block_rsv, - num_bytes, &retries); + num_bytes); if (ret) err = ret; } @@ -2155,7 +2153,6 @@ again: btrfs_end_transaction(trans, rc->extent_root); btrfs_block_rsv_release(rc->extent_root, rc->block_rsv, num_bytes); - retries = 0; goto again; } } @@ -2405,15 +2402,13 @@ static int reserve_metadata_space(struct btrfs_trans_handle *trans, num_bytes = calcu_metadata_size(rc, node, 1) * 2; trans->block_rsv = rc->block_rsv; - ret = btrfs_block_rsv_add(trans, root, rc->block_rsv, num_bytes, - &rc->block_rsv_retries); + ret = btrfs_block_rsv_add(trans, root, rc->block_rsv, num_bytes); if (ret) { if (ret == -EAGAIN) rc->commit_transaction = 1; return ret; } - rc->block_rsv_retries = 0; return 0; } @@ -3099,6 +3094,8 @@ static int add_tree_block(struct reloc_control *rc, BUG_ON(item_size != sizeof(struct btrfs_extent_item_v0)); ret = get_ref_objectid_v0(rc, path, extent_key, &ref_owner, NULL); + if (ret < 0) + return ret; BUG_ON(ref_owner >= BTRFS_MAX_LEVEL); level = (int)ref_owner; /* FIXME: get real generation */ @@ -3191,6 +3188,54 @@ static int block_use_full_backref(struct reloc_control *rc, return ret; } +static int delete_block_group_cache(struct btrfs_fs_info *fs_info, + struct inode *inode, u64 ino) +{ + struct btrfs_key key; + struct btrfs_path *path; + struct btrfs_root *root = fs_info->tree_root; + struct btrfs_trans_handle *trans; + unsigned long nr; + int ret = 0; + + if (inode) + goto truncate; + + key.objectid = ino; + key.type = BTRFS_INODE_ITEM_KEY; + key.offset = 0; + + inode = btrfs_iget(fs_info->sb, &key, root, NULL); + if (!inode || IS_ERR(inode) || is_bad_inode(inode)) { + if (inode && !IS_ERR(inode)) + iput(inode); + return -ENOENT; + } + +truncate: + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; + goto out; + } + + trans = btrfs_join_transaction(root, 0); + if (IS_ERR(trans)) { + btrfs_free_path(path); + goto out; + } + + ret = btrfs_truncate_free_space_cache(root, trans, path, inode); + + btrfs_free_path(path); + nr = trans->blocks_used; + btrfs_end_transaction(trans, root); + btrfs_btree_balance_dirty(root, nr); +out: + iput(inode); + return ret; +} + /* * helper to add tree blocks for backref of type BTRFS_EXTENT_DATA_REF_KEY * this function scans fs tree to find blocks reference the data extent @@ -3217,15 +3262,27 @@ static int find_data_references(struct reloc_control *rc, int counted; int ret; - path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; - ref_root = btrfs_extent_data_ref_root(leaf, ref); ref_objectid = btrfs_extent_data_ref_objectid(leaf, ref); ref_offset = btrfs_extent_data_ref_offset(leaf, ref); ref_count = btrfs_extent_data_ref_count(leaf, ref); + /* + * This is an extent belonging to the free space cache, lets just delete + * it and redo the search. + */ + if (ref_root == BTRFS_ROOT_TREE_OBJECTID) { + ret = delete_block_group_cache(rc->extent_root->fs_info, + NULL, ref_objectid); + if (ret != -ENOENT) + return ret; + ret = 0; + } + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + root = read_fs_root(rc->extent_root->fs_info, ref_root); if (IS_ERR(root)) { err = PTR_ERR(root); @@ -3554,8 +3611,7 @@ int prepare_to_relocate(struct reloc_control *rc) * is no reservation in transaction handle. */ ret = btrfs_block_rsv_add(NULL, rc->extent_root, rc->block_rsv, - rc->extent_root->nodesize * 256, - &rc->block_rsv_retries); + rc->extent_root->nodesize * 256); if (ret) return ret; @@ -3567,7 +3623,6 @@ int prepare_to_relocate(struct reloc_control *rc) rc->extents_found = 0; rc->nodes_relocated = 0; rc->merging_rsv_size = 0; - rc->block_rsv_retries = 0; rc->create_reloc_tree = 1; set_reloc_control(rc); @@ -3860,6 +3915,8 @@ int btrfs_relocate_block_group(struct btrfs_root *extent_root, u64 group_start) { struct btrfs_fs_info *fs_info = extent_root->fs_info; struct reloc_control *rc; + struct inode *inode; + struct btrfs_path *path; int ret; int rw = 0; int err = 0; @@ -3882,6 +3939,26 @@ int btrfs_relocate_block_group(struct btrfs_root *extent_root, u64 group_start) rw = 1; } + path = btrfs_alloc_path(); + if (!path) { + err = -ENOMEM; + goto out; + } + + inode = lookup_free_space_inode(fs_info->tree_root, rc->block_group, + path); + btrfs_free_path(path); + + if (!IS_ERR(inode)) + ret = delete_block_group_cache(fs_info, inode, 0); + else + ret = PTR_ERR(inode); + + if (ret && ret != -ENOENT) { + err = ret; + goto out; + } + rc->data_inode = create_reloc_inode(fs_info, rc->block_group); if (IS_ERR(rc->data_inode)) { err = PTR_ERR(rc->data_inode); @@ -4143,7 +4220,7 @@ int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len) btrfs_add_ordered_sum(inode, ordered, sums); } btrfs_put_ordered_extent(ordered); - return 0; + return ret; } void btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 2d958be761c8..6a1086e83ffc 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -181,7 +181,6 @@ int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root int btrfs_find_dead_roots(struct btrfs_root *root, u64 objectid) { struct btrfs_root *dead_root; - struct btrfs_item *item; struct btrfs_root_item *ri; struct btrfs_key key; struct btrfs_key found_key; @@ -214,7 +213,6 @@ again: nritems = btrfs_header_nritems(leaf); slot = path->slots[0]; } - item = btrfs_item_nr(leaf, slot); btrfs_item_key_to_cpu(leaf, &key, slot); if (btrfs_key_type(&key) != BTRFS_ROOT_ITEM_KEY) goto next; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 144f8a5730f5..dbb51ea7a13c 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -61,6 +61,8 @@ static void btrfs_put_super(struct super_block *sb) ret = close_ctree(root); sb->s_fs_info = NULL; + + (void)ret; /* FIXME: need to fix VFS to return error? */ } enum { @@ -68,7 +70,8 @@ enum { Opt_nodatacow, Opt_max_inline, Opt_alloc_start, Opt_nobarrier, Opt_ssd, Opt_nossd, Opt_ssd_spread, Opt_thread_pool, Opt_noacl, Opt_compress, Opt_compress_force, Opt_notreelog, Opt_ratio, Opt_flushoncommit, - Opt_discard, Opt_err, + Opt_discard, Opt_space_cache, Opt_clear_cache, Opt_err, + Opt_user_subvol_rm_allowed, }; static match_table_t tokens = { @@ -92,6 +95,9 @@ static match_table_t tokens = { {Opt_flushoncommit, "flushoncommit"}, {Opt_ratio, "metadata_ratio=%d"}, {Opt_discard, "discard"}, + {Opt_space_cache, "space_cache"}, + {Opt_clear_cache, "clear_cache"}, + {Opt_user_subvol_rm_allowed, "user_subvol_rm_allowed"}, {Opt_err, NULL}, }; @@ -235,6 +241,17 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) case Opt_discard: btrfs_set_opt(info->mount_opt, DISCARD); break; + case Opt_space_cache: + printk(KERN_INFO "btrfs: enabling disk space caching\n"); + btrfs_set_opt(info->mount_opt, SPACE_CACHE); + break; + case Opt_clear_cache: + printk(KERN_INFO "btrfs: force clearing of disk cache\n"); + btrfs_set_opt(info->mount_opt, CLEAR_CACHE); + break; + case Opt_user_subvol_rm_allowed: + btrfs_set_opt(info->mount_opt, USER_SUBVOL_RM_ALLOWED); + break; case Opt_err: printk(KERN_INFO "btrfs: unrecognized mount option " "'%s'\n", p); @@ -380,7 +397,7 @@ static struct dentry *get_default_root(struct super_block *sb, find_root: new_root = btrfs_read_fs_root_no_name(root->fs_info, &location); if (IS_ERR(new_root)) - return ERR_PTR(PTR_ERR(new_root)); + return ERR_CAST(new_root); if (btrfs_root_refs(&new_root->root_item) == 0) return ERR_PTR(-ENOENT); @@ -436,7 +453,6 @@ static int btrfs_fill_super(struct super_block *sb, { struct inode *inode; struct dentry *root_dentry; - struct btrfs_super_block *disk_super; struct btrfs_root *tree_root; struct btrfs_key key; int err; @@ -458,7 +474,6 @@ static int btrfs_fill_super(struct super_block *sb, return PTR_ERR(tree_root); } sb->s_fs_info = tree_root; - disk_super = &tree_root->fs_info->super_copy; key.objectid = BTRFS_FIRST_FREE_OBJECTID; key.type = BTRFS_INODE_ITEM_KEY; @@ -548,30 +563,45 @@ static int btrfs_show_options(struct seq_file *seq, struct vfsmount *vfs) static int btrfs_test_super(struct super_block *s, void *data) { - struct btrfs_fs_devices *test_fs_devices = data; + struct btrfs_root *test_root = data; struct btrfs_root *root = btrfs_sb(s); - return root->fs_info->fs_devices == test_fs_devices; + /* + * If this super block is going away, return false as it + * can't match as an existing super block. + */ + if (!atomic_read(&s->s_active)) + return 0; + return root->fs_info->fs_devices == test_root->fs_info->fs_devices; } +static int btrfs_set_super(struct super_block *s, void *data) +{ + s->s_fs_info = data; + + return set_anon_super(s, data); +} + + /* * Find a superblock for the given device / mount point. * * Note: This is based on get_sb_bdev from fs/super.c with a few additions * for multiple device setup. Make sure to keep it in sync. */ -static int btrfs_get_sb(struct file_system_type *fs_type, int flags, - const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *data) { struct block_device *bdev = NULL; struct super_block *s; struct dentry *root; struct btrfs_fs_devices *fs_devices = NULL; + struct btrfs_root *tree_root = NULL; + struct btrfs_fs_info *fs_info = NULL; fmode_t mode = FMODE_READ; char *subvol_name = NULL; u64 subvol_objectid = 0; int error = 0; - int found = 0; if (!(flags & MS_RDONLY)) mode |= FMODE_WRITE; @@ -580,7 +610,7 @@ static int btrfs_get_sb(struct file_system_type *fs_type, int flags, &subvol_name, &subvol_objectid, &fs_devices); if (error) - return error; + return ERR_PTR(error); error = btrfs_scan_one_device(dev_name, mode, fs_type, &fs_devices); if (error) @@ -595,8 +625,24 @@ static int btrfs_get_sb(struct file_system_type *fs_type, int flags, goto error_close_devices; } + /* + * Setup a dummy root and fs_info for test/set super. This is because + * we don't actually fill this stuff out until open_ctree, but we need + * it for searching for existing supers, so this lets us do that and + * then open_ctree will properly initialize everything later. + */ + fs_info = kzalloc(sizeof(struct btrfs_fs_info), GFP_NOFS); + tree_root = kzalloc(sizeof(struct btrfs_root), GFP_NOFS); + if (!fs_info || !tree_root) { + error = -ENOMEM; + goto error_close_devices; + } + fs_info->tree_root = tree_root; + fs_info->fs_devices = fs_devices; + tree_root->fs_info = fs_info; + bdev = fs_devices->latest_bdev; - s = sget(fs_type, btrfs_test_super, set_anon_super, fs_devices); + s = sget(fs_type, btrfs_test_super, btrfs_set_super, tree_root); if (IS_ERR(s)) goto error_s; @@ -607,7 +653,6 @@ static int btrfs_get_sb(struct file_system_type *fs_type, int flags, goto error_close_devices; } - found = 1; btrfs_close_devices(fs_devices); } else { char b[BDEVNAME_SIZE]; @@ -629,7 +674,7 @@ static int btrfs_get_sb(struct file_system_type *fs_type, int flags, if (IS_ERR(root)) { error = PTR_ERR(root); deactivate_locked_super(s); - goto error; + goto error_free_subvol_name; } /* if they gave us a subvolume name bind mount into that */ if (strcmp(subvol_name, ".")) { @@ -643,33 +688,31 @@ static int btrfs_get_sb(struct file_system_type *fs_type, int flags, deactivate_locked_super(s); error = PTR_ERR(new_root); dput(root); - goto error_close_devices; + goto error_free_subvol_name; } if (!new_root->d_inode) { dput(root); dput(new_root); deactivate_locked_super(s); error = -ENXIO; - goto error_close_devices; + goto error_free_subvol_name; } dput(root); root = new_root; } - mnt->mnt_sb = s; - mnt->mnt_root = root; - kfree(subvol_name); - return 0; + return root; error_s: error = PTR_ERR(s); error_close_devices: btrfs_close_devices(fs_devices); + kfree(fs_info); + kfree(tree_root); error_free_subvol_name: kfree(subvol_name); -error: - return error; + return ERR_PTR(error); } static int btrfs_remount(struct super_block *sb, int *flags, char *data) @@ -716,18 +759,25 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) struct list_head *head = &root->fs_info->space_info; struct btrfs_space_info *found; u64 total_used = 0; + u64 total_used_data = 0; int bits = dentry->d_sb->s_blocksize_bits; __be32 *fsid = (__be32 *)root->fs_info->fsid; rcu_read_lock(); - list_for_each_entry_rcu(found, head, list) + list_for_each_entry_rcu(found, head, list) { + if (found->flags & (BTRFS_BLOCK_GROUP_METADATA | + BTRFS_BLOCK_GROUP_SYSTEM)) + total_used_data += found->disk_total; + else + total_used_data += found->disk_used; total_used += found->disk_used; + } rcu_read_unlock(); buf->f_namelen = BTRFS_NAME_LEN; buf->f_blocks = btrfs_super_total_bytes(disk_super) >> bits; buf->f_bfree = buf->f_blocks - (total_used >> bits); - buf->f_bavail = buf->f_bfree; + buf->f_bavail = buf->f_blocks - (total_used_data >> bits); buf->f_bsize = dentry->d_sb->s_blocksize; buf->f_type = BTRFS_SUPER_MAGIC; @@ -746,7 +796,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) static struct file_system_type btrfs_fs_type = { .owner = THIS_MODULE, .name = "btrfs", - .get_sb = btrfs_get_sb, + .mount = btrfs_mount, .kill_sb = kill_anon_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 66e4c66cc63b..f50e931fc217 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -163,6 +163,7 @@ enum btrfs_trans_type { TRANS_START, TRANS_JOIN, TRANS_USERSPACE, + TRANS_JOIN_NOLOCK, }; static int may_wait_transaction(struct btrfs_root *root, int type) @@ -179,14 +180,14 @@ static struct btrfs_trans_handle *start_transaction(struct btrfs_root *root, { struct btrfs_trans_handle *h; struct btrfs_transaction *cur_trans; - int retries = 0; int ret; again: h = kmem_cache_alloc(btrfs_trans_handle_cachep, GFP_NOFS); if (!h) return ERR_PTR(-ENOMEM); - mutex_lock(&root->fs_info->trans_mutex); + if (type != TRANS_JOIN_NOLOCK) + mutex_lock(&root->fs_info->trans_mutex); if (may_wait_transaction(root, type)) wait_current_trans(root); @@ -195,7 +196,8 @@ again: cur_trans = root->fs_info->running_transaction; cur_trans->use_count++; - mutex_unlock(&root->fs_info->trans_mutex); + if (type != TRANS_JOIN_NOLOCK) + mutex_unlock(&root->fs_info->trans_mutex); h->transid = cur_trans->transid; h->transaction = cur_trans; @@ -212,8 +214,7 @@ again: } if (num_items > 0) { - ret = btrfs_trans_reserve_metadata(h, root, num_items, - &retries); + ret = btrfs_trans_reserve_metadata(h, root, num_items); if (ret == -EAGAIN) { btrfs_commit_transaction(h, root); goto again; @@ -224,9 +225,11 @@ again: } } - mutex_lock(&root->fs_info->trans_mutex); + if (type != TRANS_JOIN_NOLOCK) + mutex_lock(&root->fs_info->trans_mutex); record_root_in_trans(h, root); - mutex_unlock(&root->fs_info->trans_mutex); + if (type != TRANS_JOIN_NOLOCK) + mutex_unlock(&root->fs_info->trans_mutex); if (!current->journal_info && type != TRANS_USERSPACE) current->journal_info = h; @@ -244,6 +247,12 @@ struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root, return start_transaction(root, 0, TRANS_JOIN); } +struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root, + int num_blocks) +{ + return start_transaction(root, 0, TRANS_JOIN_NOLOCK); +} + struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *r, int num_blocks) { @@ -270,6 +279,58 @@ static noinline int wait_for_commit(struct btrfs_root *root, return 0; } +int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid) +{ + struct btrfs_transaction *cur_trans = NULL, *t; + int ret; + + mutex_lock(&root->fs_info->trans_mutex); + + ret = 0; + if (transid) { + if (transid <= root->fs_info->last_trans_committed) + goto out_unlock; + + /* find specified transaction */ + list_for_each_entry(t, &root->fs_info->trans_list, list) { + if (t->transid == transid) { + cur_trans = t; + break; + } + if (t->transid > transid) + break; + } + ret = -EINVAL; + if (!cur_trans) + goto out_unlock; /* bad transid */ + } else { + /* find newest transaction that is committing | committed */ + list_for_each_entry_reverse(t, &root->fs_info->trans_list, + list) { + if (t->in_commit) { + if (t->commit_done) + goto out_unlock; + cur_trans = t; + break; + } + } + if (!cur_trans) + goto out_unlock; /* nothing committing|committed */ + } + + cur_trans->use_count++; + mutex_unlock(&root->fs_info->trans_mutex); + + wait_for_commit(root, cur_trans); + + mutex_lock(&root->fs_info->trans_mutex); + put_transaction(cur_trans); + ret = 0; +out_unlock: + mutex_unlock(&root->fs_info->trans_mutex); + return ret; +} + #if 0 /* * rate limit against the drop_snapshot code. This helps to slow down new @@ -348,7 +409,7 @@ int btrfs_should_end_transaction(struct btrfs_trans_handle *trans, } static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, - struct btrfs_root *root, int throttle) + struct btrfs_root *root, int throttle, int lock) { struct btrfs_transaction *cur_trans = trans->transaction; struct btrfs_fs_info *info = root->fs_info; @@ -376,26 +437,29 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, btrfs_trans_release_metadata(trans, root); - if (!root->fs_info->open_ioctl_trans && + if (lock && !root->fs_info->open_ioctl_trans && should_end_transaction(trans, root)) trans->transaction->blocked = 1; - if (cur_trans->blocked && !cur_trans->in_commit) { + if (lock && cur_trans->blocked && !cur_trans->in_commit) { if (throttle) return btrfs_commit_transaction(trans, root); else wake_up_process(info->transaction_kthread); } - mutex_lock(&info->trans_mutex); + if (lock) + mutex_lock(&info->trans_mutex); WARN_ON(cur_trans != info->running_transaction); WARN_ON(cur_trans->num_writers < 1); cur_trans->num_writers--; + smp_mb(); if (waitqueue_active(&cur_trans->writer_wait)) wake_up(&cur_trans->writer_wait); put_transaction(cur_trans); - mutex_unlock(&info->trans_mutex); + if (lock) + mutex_unlock(&info->trans_mutex); if (current->journal_info == trans) current->journal_info = NULL; @@ -411,13 +475,19 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, int btrfs_end_transaction(struct btrfs_trans_handle *trans, struct btrfs_root *root) { - return __btrfs_end_transaction(trans, root, 0); + return __btrfs_end_transaction(trans, root, 0, 1); } int btrfs_end_transaction_throttle(struct btrfs_trans_handle *trans, struct btrfs_root *root) { - return __btrfs_end_transaction(trans, root, 1); + return __btrfs_end_transaction(trans, root, 1, 1); +} + +int btrfs_end_transaction_nolock(struct btrfs_trans_handle *trans, + struct btrfs_root *root) +{ + return __btrfs_end_transaction(trans, root, 0, 0); } /* @@ -832,11 +902,11 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, struct btrfs_root *root = pending->root; struct btrfs_root *parent_root; struct inode *parent_inode; + struct dentry *parent; struct dentry *dentry; struct extent_buffer *tmp; struct extent_buffer *old; int ret; - int retries = 0; u64 to_reserve = 0; u64 index = 0; u64 objectid; @@ -858,7 +928,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, if (to_reserve > 0) { ret = btrfs_block_rsv_add(trans, root, &pending->block_rsv, - to_reserve, &retries); + to_reserve); if (ret) { pending->error = ret; goto fail; @@ -872,7 +942,8 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, trans->block_rsv = &pending->block_rsv; dentry = pending->dentry; - parent_inode = dentry->d_parent->d_inode; + parent = dget_parent(dentry); + parent_inode = parent->d_inode; parent_root = BTRFS_I(parent_inode)->root; record_root_in_trans(trans, parent_root); @@ -920,6 +991,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, parent_inode->i_ino, index, dentry->d_name.name, dentry->d_name.len); BUG_ON(ret); + dput(parent); key.offset = (u64)-1; pending->snap = btrfs_read_fs_root_no_name(root->fs_info, &key); @@ -966,6 +1038,8 @@ static void update_super_roots(struct btrfs_root *root) super->root = root_item->bytenr; super->generation = root_item->generation; super->root_level = root_item->level; + if (super->cache_generation != 0 || btrfs_test_opt(root, SPACE_CACHE)) + super->cache_generation = root_item->generation; } int btrfs_transaction_in_commit(struct btrfs_fs_info *info) @@ -988,11 +1062,127 @@ int btrfs_transaction_blocked(struct btrfs_fs_info *info) return ret; } +/* + * wait for the current transaction commit to start and block subsequent + * transaction joins + */ +static void wait_current_trans_commit_start(struct btrfs_root *root, + struct btrfs_transaction *trans) +{ + DEFINE_WAIT(wait); + + if (trans->in_commit) + return; + + while (1) { + prepare_to_wait(&root->fs_info->transaction_blocked_wait, &wait, + TASK_UNINTERRUPTIBLE); + if (trans->in_commit) { + finish_wait(&root->fs_info->transaction_blocked_wait, + &wait); + break; + } + mutex_unlock(&root->fs_info->trans_mutex); + schedule(); + mutex_lock(&root->fs_info->trans_mutex); + finish_wait(&root->fs_info->transaction_blocked_wait, &wait); + } +} + +/* + * wait for the current transaction to start and then become unblocked. + * caller holds ref. + */ +static void wait_current_trans_commit_start_and_unblock(struct btrfs_root *root, + struct btrfs_transaction *trans) +{ + DEFINE_WAIT(wait); + + if (trans->commit_done || (trans->in_commit && !trans->blocked)) + return; + + while (1) { + prepare_to_wait(&root->fs_info->transaction_wait, &wait, + TASK_UNINTERRUPTIBLE); + if (trans->commit_done || + (trans->in_commit && !trans->blocked)) { + finish_wait(&root->fs_info->transaction_wait, + &wait); + break; + } + mutex_unlock(&root->fs_info->trans_mutex); + schedule(); + mutex_lock(&root->fs_info->trans_mutex); + finish_wait(&root->fs_info->transaction_wait, + &wait); + } +} + +/* + * commit transactions asynchronously. once btrfs_commit_transaction_async + * returns, any subsequent transaction will not be allowed to join. + */ +struct btrfs_async_commit { + struct btrfs_trans_handle *newtrans; + struct btrfs_root *root; + struct delayed_work work; +}; + +static void do_async_commit(struct work_struct *work) +{ + struct btrfs_async_commit *ac = + container_of(work, struct btrfs_async_commit, work.work); + + btrfs_commit_transaction(ac->newtrans, ac->root); + kfree(ac); +} + +int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans, + struct btrfs_root *root, + int wait_for_unblock) +{ + struct btrfs_async_commit *ac; + struct btrfs_transaction *cur_trans; + + ac = kmalloc(sizeof(*ac), GFP_NOFS); + BUG_ON(!ac); + + INIT_DELAYED_WORK(&ac->work, do_async_commit); + ac->root = root; + ac->newtrans = btrfs_join_transaction(root, 0); + + /* take transaction reference */ + mutex_lock(&root->fs_info->trans_mutex); + cur_trans = trans->transaction; + cur_trans->use_count++; + mutex_unlock(&root->fs_info->trans_mutex); + + btrfs_end_transaction(trans, root); + schedule_delayed_work(&ac->work, 0); + + /* wait for transaction to start and unblock */ + mutex_lock(&root->fs_info->trans_mutex); + if (wait_for_unblock) + wait_current_trans_commit_start_and_unblock(root, cur_trans); + else + wait_current_trans_commit_start(root, cur_trans); + put_transaction(cur_trans); + mutex_unlock(&root->fs_info->trans_mutex); + + return 0; +} + +/* + * btrfs_transaction state sequence: + * in_commit = 0, blocked = 0 (initial) + * in_commit = 1, blocked = 1 + * blocked = 0 + * commit_done = 1 + */ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, struct btrfs_root *root) { unsigned long joined = 0; - unsigned long timeout = 1; struct btrfs_transaction *cur_trans; struct btrfs_transaction *prev_trans = NULL; DEFINE_WAIT(wait); @@ -1039,6 +1229,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, trans->transaction->in_commit = 1; trans->transaction->blocked = 1; + wake_up(&root->fs_info->transaction_blocked_wait); + if (cur_trans->list.prev != &root->fs_info->trans_list) { prev_trans = list_entry(cur_trans->list.prev, struct btrfs_transaction, list); @@ -1063,11 +1255,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, snap_pending = 1; WARN_ON(cur_trans != trans->transaction); - if (cur_trans->num_writers > 1) - timeout = MAX_SCHEDULE_TIMEOUT; - else if (should_grow) - timeout = 1; - mutex_unlock(&root->fs_info->trans_mutex); if (flush_on_commit || snap_pending) { @@ -1089,8 +1276,10 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, TASK_UNINTERRUPTIBLE); smp_mb(); - if (cur_trans->num_writers > 1 || should_grow) - schedule_timeout(timeout); + if (cur_trans->num_writers > 1) + schedule_timeout(MAX_SCHEDULE_TIMEOUT); + else if (should_grow) + schedule_timeout(1); mutex_lock(&root->fs_info->trans_mutex); finish_wait(&cur_trans->writer_wait, &wait); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index e104986d0bfd..f104b57ad4ef 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -87,12 +87,17 @@ static inline void btrfs_set_inode_last_trans(struct btrfs_trans_handle *trans, int btrfs_end_transaction(struct btrfs_trans_handle *trans, struct btrfs_root *root); +int btrfs_end_transaction_nolock(struct btrfs_trans_handle *trans, + struct btrfs_root *root); struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root, int num_items); struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root, int num_blocks); +struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root, + int num_blocks); struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *r, int num_blocks); +int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid); int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans, struct btrfs_root *root); int btrfs_commit_tree_roots(struct btrfs_trans_handle *trans, @@ -104,6 +109,9 @@ int btrfs_defrag_root(struct btrfs_root *root, int cacheonly); int btrfs_clean_old_snapshots(struct btrfs_root *root); int btrfs_commit_transaction(struct btrfs_trans_handle *trans, struct btrfs_root *root); +int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans, + struct btrfs_root *root, + int wait_for_unblock); int btrfs_end_transaction_throttle(struct btrfs_trans_handle *trans, struct btrfs_root *root); int btrfs_should_end_transaction(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/tree-defrag.c b/fs/btrfs/tree-defrag.c index f7ac8e013ed7..992ab425599d 100644 --- a/fs/btrfs/tree-defrag.c +++ b/fs/btrfs/tree-defrag.c @@ -36,7 +36,6 @@ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans, int ret = 0; int wret; int level; - int orig_level; int is_extent = 0; int next_key_ret = 0; u64 last_ret = 0; @@ -64,7 +63,6 @@ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans, return -ENOMEM; level = btrfs_header_level(root->node); - orig_level = level; if (level == 0) goto out; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index fb102a9aee9c..054744ac5719 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -786,7 +786,6 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, { struct inode *dir; int ret; - struct btrfs_key location; struct btrfs_inode_ref *ref; struct btrfs_dir_item *di; struct inode *inode; @@ -795,10 +794,6 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, unsigned long ref_ptr; unsigned long ref_end; - location.objectid = key->objectid; - location.type = BTRFS_INODE_ITEM_KEY; - location.offset = 0; - /* * it is possible that we didn't log all the parent directories * for a given inode. If we don't find the dir, just don't @@ -1583,7 +1578,6 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, struct btrfs_path *path; struct btrfs_root *root = wc->replay_dest; struct btrfs_key key; - u32 item_size; int level; int i; int ret; @@ -1601,7 +1595,6 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, nritems = btrfs_header_nritems(eb); for (i = 0; i < nritems; i++) { btrfs_item_key_to_cpu(eb, &key, i); - item_size = btrfs_item_size_nr(eb, i); /* inode keys are done during the first stage */ if (key.type == BTRFS_INODE_ITEM_KEY && @@ -1668,7 +1661,6 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, struct walk_control *wc) { u64 root_owner; - u64 root_gen; u64 bytenr; u64 ptr_gen; struct extent_buffer *next; @@ -1698,7 +1690,6 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, parent = path->nodes[*level]; root_owner = btrfs_header_owner(parent); - root_gen = btrfs_header_generation(parent); next = btrfs_find_create_tree_block(root, bytenr, blocksize); @@ -1749,7 +1740,6 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans, struct walk_control *wc) { u64 root_owner; - u64 root_gen; int i; int slot; int ret; @@ -1757,8 +1747,6 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans, for (i = *level; i < BTRFS_MAX_LEVEL - 1 && path->nodes[i]; i++) { slot = path->slots[i]; if (slot + 1 < btrfs_header_nritems(path->nodes[i])) { - struct extent_buffer *node; - node = path->nodes[i]; path->slots[i]++; *level = i; WARN_ON(*level == 0); @@ -1771,7 +1759,6 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans, parent = path->nodes[*level + 1]; root_owner = btrfs_header_owner(parent); - root_gen = btrfs_header_generation(parent); wc->process_func(root, path->nodes[*level], wc, btrfs_header_generation(path->nodes[*level])); if (wc->free) { @@ -2273,7 +2260,7 @@ fail: } btrfs_end_log_trans(root); - return 0; + return err; } /* see comments for btrfs_del_dir_entries_in_log */ @@ -2729,7 +2716,6 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, struct btrfs_key max_key; struct btrfs_root *log = root->log_root; struct extent_buffer *src = NULL; - u32 size; int err = 0; int ret; int nritems; @@ -2793,7 +2779,6 @@ again: break; src = path->nodes[0]; - size = btrfs_item_size_nr(src, path->slots[0]); if (ins_nr && ins_start_slot + ins_nr == path->slots[0]) { ins_nr++; goto next_slot; @@ -2884,6 +2869,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, { int ret = 0; struct btrfs_root *root; + struct dentry *old_parent = NULL; /* * for regular files, if its inode is already on disk, we don't @@ -2925,10 +2911,13 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, if (IS_ROOT(parent)) break; - parent = parent->d_parent; + parent = dget_parent(parent); + dput(old_parent); + old_parent = parent; inode = parent->d_inode; } + dput(old_parent); out: return ret; } @@ -2960,6 +2949,7 @@ int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, { int inode_only = exists_only ? LOG_INODE_EXISTS : LOG_INODE_ALL; struct super_block *sb; + struct dentry *old_parent = NULL; int ret = 0; u64 last_committed = root->fs_info->last_trans_committed; @@ -3031,10 +3021,13 @@ int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, if (IS_ROOT(parent)) break; - parent = parent->d_parent; + parent = dget_parent(parent); + dput(old_parent); + old_parent = parent; } ret = 0; end_trans: + dput(old_parent); if (ret < 0) { BUG_ON(ret != -ENOSPC); root->fs_info->last_trans_log_full_commit = trans->transid; @@ -3054,8 +3047,13 @@ end_no_trans: int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct dentry *dentry) { - return btrfs_log_inode_parent(trans, root, dentry->d_inode, - dentry->d_parent, 0); + struct dentry *parent = dget_parent(dentry); + int ret; + + ret = btrfs_log_inode_parent(trans, root, dentry->d_inode, parent, 0); + dput(parent); + + return ret; } /* diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index e25e46a8b4e2..cc04dc1445d6 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1898,7 +1898,6 @@ int btrfs_balance(struct btrfs_root *dev_root) u64 size_to_free; struct btrfs_path *path; struct btrfs_key key; - struct btrfs_chunk *chunk; struct btrfs_root *chunk_root = dev_root->fs_info->chunk_root; struct btrfs_trans_handle *trans; struct btrfs_key found_key; @@ -1962,9 +1961,6 @@ int btrfs_balance(struct btrfs_root *dev_root) if (found_key.objectid != key.objectid) break; - chunk = btrfs_item_ptr(path->nodes[0], - path->slots[0], - struct btrfs_chunk); /* chunk zero is special */ if (found_key.offset == 0) break; @@ -3031,8 +3027,7 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio, } bio->bi_sector = multi->stripes[dev_nr].physical >> 9; dev = multi->stripes[dev_nr].dev; - BUG_ON(rw == WRITE && !dev->writeable); - if (dev && dev->bdev) { + if (dev && dev->bdev && (rw != WRITE || dev->writeable)) { bio->bi_bdev = dev->bdev; if (async_submit) schedule_bio(root, dev, rw, bio); diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 88ecbb215878..698fdd2c739c 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -178,7 +178,6 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size) struct inode *inode = dentry->d_inode; struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_path *path; - struct btrfs_item *item; struct extent_buffer *leaf; struct btrfs_dir_item *di; int ret = 0, slot, advance; @@ -234,7 +233,6 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size) } advance = 1; - item = btrfs_item_nr(leaf, slot); btrfs_item_key_to_cpu(leaf, &found_key, slot); /* check to make sure this item is what we want */ diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index 3e2b90eaa239..b9cd5445f71c 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -199,8 +199,6 @@ int btrfs_zlib_compress_pages(struct address_space *mapping, int nr_pages = 0; struct page *in_page = NULL; struct page *out_page = NULL; - int out_written = 0; - int in_read = 0; unsigned long bytes_left; *out_pages = 0; @@ -233,9 +231,6 @@ int btrfs_zlib_compress_pages(struct address_space *mapping, workspace->def_strm.avail_out = PAGE_CACHE_SIZE; workspace->def_strm.avail_in = min(len, PAGE_CACHE_SIZE); - out_written = 0; - in_read = 0; - while (workspace->def_strm.total_in < len) { ret = zlib_deflate(&workspace->def_strm, Z_SYNC_FLUSH); if (ret != Z_OK) { diff --git a/fs/buffer.c b/fs/buffer.c index 7f0b9b083f77..5930e382959b 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -905,7 +905,6 @@ try_again: bh->b_state = 0; atomic_set(&bh->b_count, 0); - bh->b_private = NULL; bh->b_size = size; /* Link the buffer to its page */ @@ -1706,7 +1705,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page, * and kswapd activity, but those code paths have their own * higher-level throttling. */ - if (wbc->sync_mode != WB_SYNC_NONE || !wbc->nonblocking) { + if (wbc->sync_mode != WB_SYNC_NONE) { lock_buffer(bh); } else if (!trylock_buffer(bh)) { redirty_page_for_writepage(wbc, page); @@ -1834,9 +1833,11 @@ void page_zero_new_buffers(struct page *page, unsigned from, unsigned to) } EXPORT_SYMBOL(page_zero_new_buffers); -int block_prepare_write(struct page *page, unsigned from, unsigned to, +int __block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block) { + unsigned from = pos & (PAGE_CACHE_SIZE - 1); + unsigned to = from + len; struct inode *inode = page->mapping->host; unsigned block_start, block_end; sector_t block; @@ -1916,7 +1917,7 @@ int block_prepare_write(struct page *page, unsigned from, unsigned to, } return err; } -EXPORT_SYMBOL(block_prepare_write); +EXPORT_SYMBOL(__block_write_begin); static int __block_commit_write(struct inode *inode, struct page *page, unsigned from, unsigned to) @@ -1953,15 +1954,6 @@ static int __block_commit_write(struct inode *inode, struct page *page, return 0; } -int __block_write_begin(struct page *page, loff_t pos, unsigned len, - get_block_t *get_block) -{ - unsigned start = pos & (PAGE_CACHE_SIZE - 1); - - return block_prepare_write(page, start, start + len, get_block); -} -EXPORT_SYMBOL(__block_write_begin); - /* * block_write_begin takes care of the basic task of block allocation and * bringing partial write blocks uptodate first. @@ -2379,7 +2371,7 @@ block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, else end = PAGE_CACHE_SIZE; - ret = block_prepare_write(page, 0, end, get_block); + ret = __block_write_begin(page, 0, end, get_block); if (!ret) ret = block_commit_write(page, 0, end); @@ -2466,11 +2458,10 @@ int nobh_write_begin(struct address_space *mapping, *fsdata = NULL; if (page_has_buffers(page)) { - unlock_page(page); - page_cache_release(page); - *pagep = NULL; - return block_write_begin(mapping, pos, len, flags, pagep, - get_block); + ret = __block_write_begin(page, pos, len, get_block); + if (unlikely(ret)) + goto out_release; + return ret; } if (PageMappedToDisk(page)) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 51bcc5ce3230..561438b6a50c 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -204,7 +204,7 @@ static int readpage_nounlock(struct file *filp, struct page *page) err = ceph_osdc_readpages(osdc, ceph_vino(inode), &ci->i_layout, page->index << PAGE_CACHE_SHIFT, &len, ci->i_truncate_seq, ci->i_truncate_size, - &page, 1); + &page, 1, 0); if (err == -ENOENT) err = 0; if (err < 0) { @@ -287,7 +287,7 @@ static int ceph_readpages(struct file *file, struct address_space *mapping, rc = ceph_osdc_readpages(osdc, ceph_vino(inode), &ci->i_layout, offset, &len, ci->i_truncate_seq, ci->i_truncate_size, - pages, nr_pages); + pages, nr_pages, 0); if (rc == -ENOENT) rc = 0; if (rc < 0) @@ -591,7 +591,6 @@ static int ceph_writepages_start(struct address_space *mapping, struct writeback_control *wbc) { struct inode *inode = mapping->host; - struct backing_dev_info *bdi = mapping->backing_dev_info; struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_fs_client *fsc; pgoff_t index, start, end; @@ -633,13 +632,6 @@ static int ceph_writepages_start(struct address_space *mapping, pagevec_init(&pvec, 0); - /* ?? */ - if (wbc->nonblocking && bdi_write_congested(bdi)) { - dout(" writepages congested\n"); - wbc->encountered_congestion = 1; - goto out_final; - } - /* where to start/end? */ if (wbc->range_cyclic) { start = mapping->writeback_index; /* Start from prev offset */ @@ -782,7 +774,7 @@ get_more_pages: snapc, do_sync, ci->i_truncate_seq, ci->i_truncate_size, - &inode->i_mtime, true, 1); + &inode->i_mtime, true, 1, 0); max_pages = req->r_num_pages; alloc_page_vec(fsc, req); @@ -885,7 +877,6 @@ out: rc = 0; /* vfs expects us to return 0 */ ceph_put_snap_context(snapc); dout("writepages done, rc = %d\n", rc); -out_final: return rc; } diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 98ab13e2b71d..60d27bc9eb83 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1430,8 +1430,8 @@ static int try_nonblocking_invalidate(struct inode *inode) invalidating_gen == ci->i_rdcache_gen) { /* success. */ dout("try_nonblocking_invalidate %p success\n", inode); - ci->i_rdcache_gen = 0; - ci->i_rdcache_revoking = 0; + /* save any racing async invalidate some trouble */ + ci->i_rdcache_revoking = ci->i_rdcache_gen - 1; return 0; } dout("try_nonblocking_invalidate %p failed\n", inode); @@ -2273,8 +2273,7 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant, { struct ceph_inode_info *ci = ceph_inode(inode); int mds = session->s_mds; - unsigned seq = le32_to_cpu(grant->seq); - unsigned issue_seq = le32_to_cpu(grant->issue_seq); + int seq = le32_to_cpu(grant->seq); int newcaps = le32_to_cpu(grant->caps); int issued, implemented, used, wanted, dirty; u64 size = le64_to_cpu(grant->size); @@ -2286,8 +2285,8 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant, int revoked_rdcache = 0; int queue_invalidate = 0; - dout("handle_cap_grant inode %p cap %p mds%d seq %u/%u %s\n", - inode, cap, mds, seq, issue_seq, ceph_cap_string(newcaps)); + dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n", + inode, cap, mds, seq, ceph_cap_string(newcaps)); dout(" size %llu max_size %llu, i_size %llu\n", size, max_size, inode->i_size); @@ -2383,7 +2382,6 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant, } cap->seq = seq; - cap->issue_seq = issue_seq; /* file layout may have changed */ ci->i_layout = grant->layout; @@ -2691,6 +2689,11 @@ static void handle_cap_import(struct ceph_mds_client *mdsc, NULL /* no caps context */); try_flush_caps(inode, session, NULL); up_read(&mdsc->snap_rwsem); + + /* make sure we re-request max_size, if necessary */ + spin_lock(&inode->i_lock); + ci->i_requested_max_size = 0; + spin_unlock(&inode->i_lock); } /* diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index e0a2dc6fcafc..7d447af84ec4 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -336,7 +336,10 @@ more: if (req->r_reply_info.dir_end) { kfree(fi->last_name); fi->last_name = NULL; - fi->next_offset = 2; + if (ceph_frag_is_rightmost(frag)) + fi->next_offset = 2; + else + fi->next_offset = 0; } else { rinfo = &req->r_reply_info; err = note_last_dentry(fi, @@ -355,18 +358,22 @@ more: u64 pos = ceph_make_fpos(frag, off); struct ceph_mds_reply_inode *in = rinfo->dir_in[off - fi->offset].in; + struct ceph_vino vino; + ino_t ino; + dout("readdir off %d (%d/%d) -> %lld '%.*s' %p\n", off, off - fi->offset, rinfo->dir_nr, pos, rinfo->dir_dname_len[off - fi->offset], rinfo->dir_dname[off - fi->offset], in); BUG_ON(!in); ftype = le32_to_cpu(in->mode) >> 12; + vino.ino = le64_to_cpu(in->ino); + vino.snap = le64_to_cpu(in->snapid); + ino = ceph_vino_to_ino(vino); if (filldir(dirent, rinfo->dir_dname[off - fi->offset], rinfo->dir_dname_len[off - fi->offset], - pos, - le64_to_cpu(in->ino), - ftype) < 0) { + pos, ino, ftype) < 0) { dout("filldir stopping us...\n"); return 0; } @@ -414,6 +421,7 @@ static void reset_readdir(struct ceph_file_info *fi) fi->last_readdir = NULL; } kfree(fi->last_name); + fi->last_name = NULL; fi->next_offset = 2; /* compensate for . and .. */ if (fi->dentry) { dput(fi->dentry); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index e77c28cf3690..8d79b8912e31 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -154,11 +154,13 @@ int ceph_open(struct inode *inode, struct file *file) } /* - * No need to block if we have any caps. Update wanted set + * No need to block if we have caps on the auth MDS (for + * write) or any MDS (for read). Update wanted set * asynchronously. */ spin_lock(&inode->i_lock); - if (__ceph_is_any_real_caps(ci)) { + if (__ceph_is_any_real_caps(ci) && + (((fmode & CEPH_FILE_MODE_WR) == 0) || ci->i_auth_cap)) { int mds_wanted = __ceph_caps_mds_wanted(ci); int issued = __ceph_caps_issued(ci, NULL); @@ -280,11 +282,12 @@ int ceph_release(struct inode *inode, struct file *file) static int striped_read(struct inode *inode, u64 off, u64 len, struct page **pages, int num_pages, - int *checkeof) + int *checkeof, bool align_to_pages) { struct ceph_fs_client *fsc = ceph_inode_to_client(inode); struct ceph_inode_info *ci = ceph_inode(inode); u64 pos, this_len; + int io_align, page_align; int page_off = off & ~PAGE_CACHE_MASK; /* first byte's offset in page */ int left, pages_left; int read; @@ -300,14 +303,19 @@ static int striped_read(struct inode *inode, page_pos = pages; pages_left = num_pages; read = 0; + io_align = off & ~PAGE_MASK; more: + if (align_to_pages) + page_align = (pos - io_align) & ~PAGE_MASK; + else + page_align = pos & ~PAGE_MASK; this_len = left; ret = ceph_osdc_readpages(&fsc->client->osdc, ceph_vino(inode), &ci->i_layout, pos, &this_len, ci->i_truncate_seq, ci->i_truncate_size, - page_pos, pages_left); + page_pos, pages_left, page_align); hit_stripe = this_len < left; was_short = ret >= 0 && ret < this_len; if (ret == -ENOENT) @@ -374,26 +382,25 @@ static ssize_t ceph_sync_read(struct file *file, char __user *data, dout("sync_read on file %p %llu~%u %s\n", file, off, len, (file->f_flags & O_DIRECT) ? "O_DIRECT" : ""); - if (file->f_flags & O_DIRECT) { - pages = ceph_get_direct_page_vector(data, num_pages, off, len); - - /* - * flush any page cache pages in this range. this - * will make concurrent normal and O_DIRECT io slow, - * but it will at least behave sensibly when they are - * in sequence. - */ - } else { + if (file->f_flags & O_DIRECT) + pages = ceph_get_direct_page_vector(data, num_pages); + else pages = ceph_alloc_page_vector(num_pages, GFP_NOFS); - } if (IS_ERR(pages)) return PTR_ERR(pages); + /* + * flush any page cache pages in this range. this + * will make concurrent normal and sync io slow, + * but it will at least behave sensibly when they are + * in sequence. + */ ret = filemap_write_and_wait(inode->i_mapping); if (ret < 0) goto done; - ret = striped_read(inode, off, len, pages, num_pages, checkeof); + ret = striped_read(inode, off, len, pages, num_pages, checkeof, + file->f_flags & O_DIRECT); if (ret >= 0 && (file->f_flags & O_DIRECT) == 0) ret = ceph_copy_page_vector_to_user(pages, data, off, ret); @@ -448,6 +455,7 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data, int flags; int do_sync = 0; int check_caps = 0; + int page_align, io_align; int ret; struct timespec mtime = CURRENT_TIME; @@ -462,6 +470,8 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data, else pos = *offset; + io_align = pos & ~PAGE_MASK; + ret = filemap_write_and_wait_range(inode->i_mapping, pos, pos + left); if (ret < 0) return ret; @@ -486,20 +496,26 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data, */ more: len = left; + if (file->f_flags & O_DIRECT) + /* write from beginning of first page, regardless of + io alignment */ + page_align = (pos - io_align) & ~PAGE_MASK; + else + page_align = pos & ~PAGE_MASK; req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, ceph_vino(inode), pos, &len, CEPH_OSD_OP_WRITE, flags, ci->i_snap_realm->cached_context, do_sync, ci->i_truncate_seq, ci->i_truncate_size, - &mtime, false, 2); + &mtime, false, 2, page_align); if (!req) return -ENOMEM; num_pages = calc_pages_for(pos, len); if (file->f_flags & O_DIRECT) { - pages = ceph_get_direct_page_vector(data, num_pages, pos, len); + pages = ceph_get_direct_page_vector(data, num_pages); if (IS_ERR(pages)) { ret = PTR_ERR(pages); goto out; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 1d6a45b5a04c..bf1286588f26 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -2,7 +2,6 @@ #include <linux/module.h> #include <linux/fs.h> -#include <linux/smp_lock.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/uaccess.h> @@ -471,7 +470,9 @@ void ceph_fill_file_time(struct inode *inode, int issued, if (issued & (CEPH_CAP_FILE_EXCL| CEPH_CAP_FILE_WR| - CEPH_CAP_FILE_BUFFER)) { + CEPH_CAP_FILE_BUFFER| + CEPH_CAP_AUTH_EXCL| + CEPH_CAP_XATTR_EXCL)) { if (timespec_compare(ctime, &inode->i_ctime) > 0) { dout("ctime %ld.%09ld -> %ld.%09ld inc w/ cap\n", inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec, @@ -511,7 +512,7 @@ void ceph_fill_file_time(struct inode *inode, int issued, warn = 1; } } else { - /* we have no write caps; whatever the MDS says is true */ + /* we have no write|excl caps; whatever the MDS says is true */ if (ceph_seq_cmp(time_warp_seq, ci->i_time_warp_seq) >= 0) { inode->i_ctime = *ctime; inode->i_mtime = *mtime; @@ -567,12 +568,17 @@ static int fill_inode(struct inode *inode, /* * provided version will be odd if inode value is projected, - * even if stable. skip the update if we have a newer info - * (e.g., due to inode info racing form multiple MDSs), or if - * we are getting projected (unstable) inode info. + * even if stable. skip the update if we have newer stable + * info (ours>=theirs, e.g. due to racing mds replies), unless + * we are getting projected (unstable) info (in which case the + * version is odd, and we want ours>theirs). + * us them + * 2 2 skip + * 3 2 skip + * 3 3 update */ if (le64_to_cpu(info->version) > 0 && - (ci->i_version & ~1) > le64_to_cpu(info->version)) + (ci->i_version & ~1) >= le64_to_cpu(info->version)) goto no_change; issued = __ceph_caps_issued(ci, &implemented); @@ -606,7 +612,14 @@ static int fill_inode(struct inode *inode, le32_to_cpu(info->time_warp_seq), &ctime, &mtime, &atime); - ci->i_max_size = le64_to_cpu(info->max_size); + /* only update max_size on auth cap */ + if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) && + ci->i_max_size != le64_to_cpu(info->max_size)) { + dout("max_size %lld -> %llu\n", ci->i_max_size, + le64_to_cpu(info->max_size)); + ci->i_max_size = le64_to_cpu(info->max_size); + } + ci->i_layout = info->layout; inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1; @@ -1055,7 +1068,8 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, ininfo = rinfo->targeti.in; vino.ino = le64_to_cpu(ininfo->ino); vino.snap = le64_to_cpu(ininfo->snapid); - if (!dn->d_inode) { + in = dn->d_inode; + if (!in) { in = ceph_get_inode(sb, vino); if (IS_ERR(in)) { pr_err("fill_trace bad get_inode " @@ -1386,11 +1400,8 @@ static void ceph_invalidate_work(struct work_struct *work) spin_lock(&inode->i_lock); dout("invalidate_pages %p gen %d revoking %d\n", inode, ci->i_rdcache_gen, ci->i_rdcache_revoking); - if (ci->i_rdcache_gen == 0 || - ci->i_rdcache_revoking != ci->i_rdcache_gen) { - BUG_ON(ci->i_rdcache_revoking > ci->i_rdcache_gen); + if (ci->i_rdcache_revoking != ci->i_rdcache_gen) { /* nevermind! */ - ci->i_rdcache_revoking = 0; spin_unlock(&inode->i_lock); goto out; } @@ -1400,15 +1411,16 @@ static void ceph_invalidate_work(struct work_struct *work) ceph_invalidate_nondirty_pages(inode->i_mapping); spin_lock(&inode->i_lock); - if (orig_gen == ci->i_rdcache_gen) { + if (orig_gen == ci->i_rdcache_gen && + orig_gen == ci->i_rdcache_revoking) { dout("invalidate_pages %p gen %d successful\n", inode, ci->i_rdcache_gen); - ci->i_rdcache_gen = 0; - ci->i_rdcache_revoking = 0; + ci->i_rdcache_revoking--; check = 1; } else { - dout("invalidate_pages %p gen %d raced, gen now %d\n", - inode, orig_gen, ci->i_rdcache_gen); + dout("invalidate_pages %p gen %d raced, now %d revoking %d\n", + inode, orig_gen, ci->i_rdcache_gen, + ci->i_rdcache_revoking); } spin_unlock(&inode->i_lock); @@ -1739,7 +1751,7 @@ int ceph_do_getattr(struct inode *inode, int mask) return 0; } - dout("do_getattr inode %p mask %s\n", inode, ceph_cap_string(mask)); + dout("do_getattr inode %p mask %s mode 0%o\n", inode, ceph_cap_string(mask), inode->i_mode); if (ceph_caps_issued_mask(ceph_inode(inode), mask, 1)) return 0; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 3142b15940c2..098b18508479 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -6,7 +6,6 @@ #include <linux/sched.h> #include <linux/debugfs.h> #include <linux/seq_file.h> -#include <linux/smp_lock.h> #include "super.h" #include "mds_client.h" @@ -529,6 +528,9 @@ static void __register_request(struct ceph_mds_client *mdsc, ceph_mdsc_get_request(req); __insert_request(mdsc, req); + req->r_uid = current_fsuid(); + req->r_gid = current_fsgid(); + if (dir) { struct ceph_inode_info *ci = ceph_inode(dir); @@ -1588,8 +1590,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, head->mdsmap_epoch = cpu_to_le32(mdsc->mdsmap->m_epoch); head->op = cpu_to_le32(req->r_op); - head->caller_uid = cpu_to_le32(current_fsuid()); - head->caller_gid = cpu_to_le32(current_fsgid()); + head->caller_uid = cpu_to_le32(req->r_uid); + head->caller_gid = cpu_to_le32(req->r_gid); head->args = req->r_args; ceph_encode_filepath(&p, end, ino1, path1); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index d66d63c72355..9341fd4f1432 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -170,6 +170,8 @@ struct ceph_mds_request { union ceph_mds_request_args r_args; int r_fmode; /* file mode, if expecting cap */ + uid_t r_uid; + gid_t r_gid; /* for choosing which mds to send this request to */ int r_direct_mode; diff --git a/fs/ceph/super.c b/fs/ceph/super.c index d6e0e0421891..08b460ae0539 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -635,7 +635,7 @@ static struct dentry *open_root_dentry(struct ceph_fs_client *fsc, /* * mount: join the ceph cluster, and open root directory. */ -static int ceph_mount(struct ceph_fs_client *fsc, struct vfsmount *mnt, +static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc, const char *path) { int err; @@ -678,16 +678,14 @@ static int ceph_mount(struct ceph_fs_client *fsc, struct vfsmount *mnt, } } - mnt->mnt_root = root; - mnt->mnt_sb = fsc->sb; - fsc->mount_state = CEPH_MOUNT_MOUNTED; dout("mount success\n"); - err = 0; + mutex_unlock(&fsc->client->mount_mutex); + return root; out: mutex_unlock(&fsc->client->mount_mutex); - return err; + return ERR_PTR(err); fail: if (first) { @@ -777,41 +775,45 @@ static int ceph_register_bdi(struct super_block *sb, return err; } -static int ceph_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, - struct vfsmount *mnt) +static struct dentry *ceph_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { struct super_block *sb; struct ceph_fs_client *fsc; + struct dentry *res; int err; int (*compare_super)(struct super_block *, void *) = ceph_compare_super; const char *path = NULL; struct ceph_mount_options *fsopt = NULL; struct ceph_options *opt = NULL; - dout("ceph_get_sb\n"); + dout("ceph_mount\n"); err = parse_mount_options(&fsopt, &opt, flags, data, dev_name, &path); - if (err < 0) + if (err < 0) { + res = ERR_PTR(err); goto out_final; + } /* create client (which we may/may not use) */ fsc = create_fs_client(fsopt, opt); if (IS_ERR(fsc)) { - err = PTR_ERR(fsc); + res = ERR_CAST(fsc); kfree(fsopt); kfree(opt); goto out_final; } err = ceph_mdsc_init(fsc); - if (err < 0) + if (err < 0) { + res = ERR_PTR(err); goto out; + } if (ceph_test_opt(fsc->client, NOSHARE)) compare_super = NULL; sb = sget(fs_type, compare_super, ceph_set_super, fsc); if (IS_ERR(sb)) { - err = PTR_ERR(sb); + res = ERR_CAST(sb); goto out; } @@ -823,16 +825,18 @@ static int ceph_get_sb(struct file_system_type *fs_type, } else { dout("get_sb using new client %p\n", fsc); err = ceph_register_bdi(sb, fsc); - if (err < 0) + if (err < 0) { + res = ERR_PTR(err); goto out_splat; + } } - err = ceph_mount(fsc, mnt, path); - if (err < 0) + res = ceph_real_mount(fsc, path); + if (IS_ERR(res)) goto out_splat; - dout("root %p inode %p ino %llx.%llx\n", mnt->mnt_root, - mnt->mnt_root->d_inode, ceph_vinop(mnt->mnt_root->d_inode)); - return 0; + dout("root %p inode %p ino %llx.%llx\n", res, + res->d_inode, ceph_vinop(res->d_inode)); + return res; out_splat: ceph_mdsc_close_sessions(fsc->mdsc); @@ -843,8 +847,8 @@ out: ceph_mdsc_destroy(fsc); destroy_fs_client(fsc); out_final: - dout("ceph_get_sb fail %d\n", err); - return err; + dout("ceph_mount fail %ld\n", PTR_ERR(res)); + return res; } static void ceph_kill_sb(struct super_block *s) @@ -860,7 +864,7 @@ static void ceph_kill_sb(struct super_block *s) static struct file_system_type ceph_fs_type = { .owner = THIS_MODULE, .name = "ceph", - .get_sb = ceph_get_sb, + .mount = ceph_mount, .kill_sb = ceph_kill_sb, .fs_flags = FS_RENAME_DOES_D_MOVE, }; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 1886294e12f7..7f01728a4657 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -293,9 +293,7 @@ struct ceph_inode_info { int i_rd_ref, i_rdcache_ref, i_wr_ref; int i_wrbuffer_ref, i_wrbuffer_ref_head; u32 i_shared_gen; /* increment each time we get FILE_SHARED */ - u32 i_rdcache_gen; /* we increment this each time we get - FILE_CACHE. If it's non-zero, we - _may_ have cached pages. */ + u32 i_rdcache_gen; /* incremented each time we get FILE_CACHE. */ u32 i_rdcache_revoking; /* RDCACHE gen to async invalidate, if any */ struct list_head i_unsafe_writes; /* uncommitted sync writes */ diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig index 917b7d449bb2..ee45648b0d1a 100644 --- a/fs/cifs/Kconfig +++ b/fs/cifs/Kconfig @@ -2,6 +2,10 @@ config CIFS tristate "CIFS support (advanced network filesystem, SMBFS successor)" depends on INET select NLS + select CRYPTO + select CRYPTO_MD5 + select CRYPTO_HMAC + select CRYPTO_ARC4 help This is the client VFS module for the Common Internet File System (CIFS) protocol which is the successor to the Server Message Block @@ -140,6 +144,13 @@ config CIFS_FSCACHE to be cached locally on disk through the general filesystem cache manager. If unsure, say N. +config CIFS_ACL + bool "Provide CIFS ACL support (EXPERIMENTAL)" + depends on EXPERIMENTAL && CIFS_XATTR + help + Allows to fetch CIFS/NTFS ACL from the server. The DACL blob + is handed over to the application/caller. + config CIFS_EXPERIMENTAL bool "CIFS Experimental Features (EXPERIMENTAL)" depends on CIFS && EXPERIMENTAL diff --git a/fs/cifs/TODO b/fs/cifs/TODO index 5aff46c61e52..355abcdcda98 100644 --- a/fs/cifs/TODO +++ b/fs/cifs/TODO @@ -81,7 +81,7 @@ u) DOS attrs - returned as pseudo-xattr in Samba format (check VFAT and NTFS for v) mount check for unmatched uids -w) Add support for new vfs entry points for setlease and fallocate +w) Add support for new vfs entry point for fallocate x) Fix Samba 3 server to handle Linux kernel aio so dbench with lots of processes can proceed better in parallel (on the server) diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h index 525ba59a4105..e9a393c9c2ca 100644 --- a/fs/cifs/cifs_fs_sb.h +++ b/fs/cifs/cifs_fs_sb.h @@ -15,7 +15,7 @@ * the GNU Lesser General Public License for more details. * */ -#include <linux/radix-tree.h> +#include <linux/rbtree.h> #ifndef _CIFS_FS_SB_H #define _CIFS_FS_SB_H @@ -42,9 +42,9 @@ #define CIFS_MOUNT_MULTIUSER 0x20000 /* multiuser mount */ struct cifs_sb_info { - struct radix_tree_root tlink_tree; -#define CIFS_TLINK_MASTER_TAG 0 /* is "master" (mount) tcon */ + struct rb_root tlink_tree; spinlock_t tlink_tree_lock; + struct tcon_link *master_tlink; struct nls_table *local_nls; unsigned int rsize; unsigned int wsize; diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index c9b4792ae825..c6ebea088ac7 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -560,7 +560,7 @@ static struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) - return NULL; + return ERR_CAST(tlink); xid = GetXid(); rc = CIFSSMBGetCIFSACL(xid, tlink_tcon(tlink), fid, &pntsd, pacllen); @@ -568,7 +568,9 @@ static struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, cifs_put_tlink(tlink); - cFYI(1, "GetCIFSACL rc = %d ACL len %d", rc, *pacllen); + cFYI(1, "%s: rc = %d ACL len %d", __func__, rc, *pacllen); + if (rc) + return ERR_PTR(rc); return pntsd; } @@ -583,7 +585,7 @@ static struct cifs_ntsd *get_cifs_acl_by_path(struct cifs_sb_info *cifs_sb, struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) - return NULL; + return ERR_CAST(tlink); tcon = tlink_tcon(tlink); xid = GetXid(); @@ -591,23 +593,22 @@ static struct cifs_ntsd *get_cifs_acl_by_path(struct cifs_sb_info *cifs_sb, rc = CIFSSMBOpen(xid, tcon, path, FILE_OPEN, READ_CONTROL, 0, &fid, &oplock, NULL, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); - if (rc) { - cERROR(1, "Unable to open file to get ACL"); - goto out; + if (!rc) { + rc = CIFSSMBGetCIFSACL(xid, tcon, fid, &pntsd, pacllen); + CIFSSMBClose(xid, tcon, fid); } - rc = CIFSSMBGetCIFSACL(xid, tcon, fid, &pntsd, pacllen); - cFYI(1, "GetCIFSACL rc = %d ACL len %d", rc, *pacllen); - - CIFSSMBClose(xid, tcon, fid); - out: cifs_put_tlink(tlink); FreeXid(xid); + + cFYI(1, "%s: rc = %d ACL len %d", __func__, rc, *pacllen); + if (rc) + return ERR_PTR(rc); return pntsd; } /* Retrieve an ACL from the server */ -static struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *cifs_sb, +struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *cifs_sb, struct inode *inode, const char *path, u32 *pacllen) { @@ -695,7 +696,7 @@ static int set_cifs_acl(struct cifs_ntsd *pnntsd, __u32 acllen, } /* Translate the CIFS ACL (simlar to NTFS ACL) for a file into mode bits */ -void +int cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, struct inode *inode, const char *path, const __u16 *pfid) { @@ -711,17 +712,21 @@ cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, pntsd = get_cifs_acl(cifs_sb, inode, path, &acllen); /* if we can retrieve the ACL, now parse Access Control Entries, ACEs */ - if (pntsd) + if (IS_ERR(pntsd)) { + rc = PTR_ERR(pntsd); + cERROR(1, "%s: error %d getting sec desc", __func__, rc); + } else { rc = parse_sec_desc(pntsd, acllen, fattr); - if (rc) - cFYI(1, "parse sec desc failed rc = %d", rc); + kfree(pntsd); + if (rc) + cERROR(1, "parse sec desc failed rc = %d", rc); + } - kfree(pntsd); - return; + return rc; } /* Convert mode bits to an ACL so we can update the ACL on the server */ -int mode_to_acl(struct inode *inode, const char *path, __u64 nmode) +int mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode) { int rc = 0; __u32 secdesclen = 0; @@ -736,7 +741,10 @@ int mode_to_acl(struct inode *inode, const char *path, __u64 nmode) /* Add three ACEs for owner, group, everyone getting rid of other ACEs as chmod disables ACEs and set the security descriptor */ - if (pntsd) { + if (IS_ERR(pntsd)) { + rc = PTR_ERR(pntsd); + cERROR(1, "%s: error %d getting sec desc", __func__, rc); + } else { /* allocate memory for the smb header, set security descriptor request security descriptor parameters, and secuirty descriptor itself */ diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index 7ac0056294cf..f856732161ab 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -43,18 +43,32 @@ extern void SMBencrypt(unsigned char *passwd, const unsigned char *c8, unsigned char *p24); static int cifs_calculate_signature(const struct smb_hdr *cifs_pdu, - const struct session_key *key, char *signature) + struct TCP_Server_Info *server, char *signature) { - struct MD5Context context; + int rc; - if ((cifs_pdu == NULL) || (signature == NULL) || (key == NULL)) + if (cifs_pdu == NULL || signature == NULL || server == NULL) return -EINVAL; - cifs_MD5_init(&context); - cifs_MD5_update(&context, (char *)&key->data, key->len); - cifs_MD5_update(&context, cifs_pdu->Protocol, cifs_pdu->smb_buf_length); + if (!server->secmech.sdescmd5) { + cERROR(1, "%s: Can't generate signature\n", __func__); + return -1; + } + + rc = crypto_shash_init(&server->secmech.sdescmd5->shash); + if (rc) { + cERROR(1, "%s: Oould not init md5\n", __func__); + return rc; + } + + crypto_shash_update(&server->secmech.sdescmd5->shash, + server->session_key.response, server->session_key.len); + + crypto_shash_update(&server->secmech.sdescmd5->shash, + cifs_pdu->Protocol, cifs_pdu->smb_buf_length); + + rc = crypto_shash_final(&server->secmech.sdescmd5->shash, signature); - cifs_MD5_final(signature, &context); return 0; } @@ -79,8 +93,7 @@ int cifs_sign_smb(struct smb_hdr *cifs_pdu, struct TCP_Server_Info *server, server->sequence_number++; spin_unlock(&GlobalMid_Lock); - rc = cifs_calculate_signature(cifs_pdu, &server->session_key, - smb_signature); + rc = cifs_calculate_signature(cifs_pdu, server, smb_signature); if (rc) memset(cifs_pdu->Signature.SecuritySignature, 0, 8); else @@ -90,16 +103,28 @@ int cifs_sign_smb(struct smb_hdr *cifs_pdu, struct TCP_Server_Info *server, } static int cifs_calc_signature2(const struct kvec *iov, int n_vec, - const struct session_key *key, char *signature) + struct TCP_Server_Info *server, char *signature) { - struct MD5Context context; int i; + int rc; - if ((iov == NULL) || (signature == NULL) || (key == NULL)) + if (iov == NULL || signature == NULL || server == NULL) return -EINVAL; - cifs_MD5_init(&context); - cifs_MD5_update(&context, (char *)&key->data, key->len); + if (!server->secmech.sdescmd5) { + cERROR(1, "%s: Can't generate signature\n", __func__); + return -1; + } + + rc = crypto_shash_init(&server->secmech.sdescmd5->shash); + if (rc) { + cERROR(1, "%s: Oould not init md5\n", __func__); + return rc; + } + + crypto_shash_update(&server->secmech.sdescmd5->shash, + server->session_key.response, server->session_key.len); + for (i = 0; i < n_vec; i++) { if (iov[i].iov_len == 0) continue; @@ -112,18 +137,18 @@ static int cifs_calc_signature2(const struct kvec *iov, int n_vec, if (i == 0) { if (iov[0].iov_len <= 8) /* cmd field at offset 9 */ break; /* nothing to sign or corrupt header */ - cifs_MD5_update(&context, iov[0].iov_base+4, - iov[0].iov_len-4); + crypto_shash_update(&server->secmech.sdescmd5->shash, + iov[i].iov_base + 4, iov[i].iov_len - 4); } else - cifs_MD5_update(&context, iov[i].iov_base, iov[i].iov_len); + crypto_shash_update(&server->secmech.sdescmd5->shash, + iov[i].iov_base, iov[i].iov_len); } - cifs_MD5_final(signature, &context); + rc = crypto_shash_final(&server->secmech.sdescmd5->shash, signature); - return 0; + return rc; } - int cifs_sign_smb2(struct kvec *iov, int n_vec, struct TCP_Server_Info *server, __u32 *pexpected_response_sequence_number) { @@ -146,8 +171,7 @@ int cifs_sign_smb2(struct kvec *iov, int n_vec, struct TCP_Server_Info *server, server->sequence_number++; spin_unlock(&GlobalMid_Lock); - rc = cifs_calc_signature2(iov, n_vec, &server->session_key, - smb_signature); + rc = cifs_calc_signature2(iov, n_vec, server, smb_signature); if (rc) memset(cifs_pdu->Signature.SecuritySignature, 0, 8); else @@ -157,14 +181,14 @@ int cifs_sign_smb2(struct kvec *iov, int n_vec, struct TCP_Server_Info *server, } int cifs_verify_signature(struct smb_hdr *cifs_pdu, - const struct session_key *session_key, + struct TCP_Server_Info *server, __u32 expected_sequence_number) { unsigned int rc; char server_response_sig[8]; char what_we_think_sig_should_be[20]; - if (cifs_pdu == NULL || session_key == NULL) + if (cifs_pdu == NULL || server == NULL) return -EINVAL; if (cifs_pdu->Command == SMB_COM_NEGOTIATE) @@ -193,7 +217,7 @@ int cifs_verify_signature(struct smb_hdr *cifs_pdu, cpu_to_le32(expected_sequence_number); cifs_pdu->Signature.Sequence.Reserved = 0; - rc = cifs_calculate_signature(cifs_pdu, session_key, + rc = cifs_calculate_signature(cifs_pdu, server, what_we_think_sig_should_be); if (rc) @@ -209,18 +233,28 @@ int cifs_verify_signature(struct smb_hdr *cifs_pdu, } -/* We fill in key by putting in 40 byte array which was allocated by caller */ -int cifs_calculate_session_key(struct session_key *key, const char *rn, - const char *password) +/* first calculate 24 bytes ntlm response and then 16 byte session key */ +int setup_ntlm_response(struct cifsSesInfo *ses) { - char temp_key[16]; - if ((key == NULL) || (rn == NULL)) + unsigned int temp_len = CIFS_SESS_KEY_SIZE + CIFS_AUTH_RESP_SIZE; + char temp_key[CIFS_SESS_KEY_SIZE]; + + if (!ses) return -EINVAL; - E_md4hash(password, temp_key); - mdfour(key->data.ntlm, temp_key, 16); - memcpy(key->data.ntlm+16, rn, CIFS_SESS_KEY_SIZE); - key->len = 40; + ses->auth_key.response = kmalloc(temp_len, GFP_KERNEL); + if (!ses->auth_key.response) { + cERROR(1, "NTLM can't allocate (%u bytes) memory", temp_len); + return -ENOMEM; + } + ses->auth_key.len = temp_len; + + SMBNTencrypt(ses->password, ses->server->cryptkey, + ses->auth_key.response + CIFS_SESS_KEY_SIZE); + + E_md4hash(ses->password, temp_key); + mdfour(ses->auth_key.response, temp_key, CIFS_SESS_KEY_SIZE); + return 0; } @@ -294,15 +328,15 @@ build_avpair_blob(struct cifsSesInfo *ses, const struct nls_table *nls_cp) * two times the unicode length of a server name + * size of a timestamp (which is 8 bytes). */ - ses->tilen = size + 2 * (2 * dlen) + 2 * (2 * wlen) + 8; - ses->tiblob = kzalloc(ses->tilen, GFP_KERNEL); - if (!ses->tiblob) { - ses->tilen = 0; + ses->auth_key.len = size + 2 * (2 * dlen) + 2 * (2 * wlen) + 8; + ses->auth_key.response = kzalloc(ses->auth_key.len, GFP_KERNEL); + if (!ses->auth_key.response) { + ses->auth_key.len = 0; cERROR(1, "Challenge target info allocation failure"); return -ENOMEM; } - blobptr = ses->tiblob; + blobptr = ses->auth_key.response; attrptr = (struct ntlmssp2_name *) blobptr; attrptr->type = cpu_to_le16(NTLMSSP_AV_NB_DOMAIN_NAME); @@ -357,7 +391,7 @@ build_avpair_blob(struct cifsSesInfo *ses, const struct nls_table *nls_cp) * about target string i.e. for some, just user name might suffice. */ static int -find_domain_name(struct cifsSesInfo *ses) +find_domain_name(struct cifsSesInfo *ses, const struct nls_table *nls_cp) { unsigned int attrsize; unsigned int type; @@ -366,11 +400,11 @@ find_domain_name(struct cifsSesInfo *ses) unsigned char *blobend; struct ntlmssp2_name *attrptr; - if (!ses->tilen || !ses->tiblob) + if (!ses->auth_key.len || !ses->auth_key.response) return 0; - blobptr = ses->tiblob; - blobend = ses->tiblob + ses->tilen; + blobptr = ses->auth_key.response; + blobend = blobptr + ses->auth_key.len; while (blobptr + onesize < blobend) { attrptr = (struct ntlmssp2_name *) blobptr; @@ -386,16 +420,13 @@ find_domain_name(struct cifsSesInfo *ses) if (!attrsize) break; if (!ses->domainName) { - struct nls_table *default_nls; ses->domainName = kmalloc(attrsize + 1, GFP_KERNEL); if (!ses->domainName) return -ENOMEM; - default_nls = load_nls_default(); cifs_from_ucs2(ses->domainName, (__le16 *)blobptr, attrsize, attrsize, - default_nls, false); - unload_nls(default_nls); + nls_cp, false); break; } } @@ -405,82 +436,136 @@ find_domain_name(struct cifsSesInfo *ses) return 0; } -static int calc_ntlmv2_hash(struct cifsSesInfo *ses, +static int calc_ntlmv2_hash(struct cifsSesInfo *ses, char *ntlmv2_hash, const struct nls_table *nls_cp) { int rc = 0; int len; - char nt_hash[16]; - struct HMACMD5Context *pctxt; + char nt_hash[CIFS_NTHASH_SIZE]; wchar_t *user; wchar_t *domain; + wchar_t *server; - pctxt = kmalloc(sizeof(struct HMACMD5Context), GFP_KERNEL); - - if (pctxt == NULL) - return -ENOMEM; + if (!ses->server->secmech.sdeschmacmd5) { + cERROR(1, "calc_ntlmv2_hash: can't generate ntlmv2 hash\n"); + return -1; + } /* calculate md4 hash of password */ E_md4hash(ses->password, nt_hash); - /* convert Domainname to unicode and uppercase */ - hmac_md5_init_limK_to_64(nt_hash, 16, pctxt); + crypto_shash_setkey(ses->server->secmech.hmacmd5, nt_hash, + CIFS_NTHASH_SIZE); + + rc = crypto_shash_init(&ses->server->secmech.sdeschmacmd5->shash); + if (rc) { + cERROR(1, "calc_ntlmv2_hash: could not init hmacmd5\n"); + return rc; + } /* convert ses->userName to unicode and uppercase */ len = strlen(ses->userName); user = kmalloc(2 + (len * 2), GFP_KERNEL); - if (user == NULL) + if (user == NULL) { + cERROR(1, "calc_ntlmv2_hash: user mem alloc failure\n"); + rc = -ENOMEM; goto calc_exit_2; + } len = cifs_strtoUCS((__le16 *)user, ses->userName, len, nls_cp); UniStrupr(user); - hmac_md5_update((char *)user, 2*len, pctxt); + + crypto_shash_update(&ses->server->secmech.sdeschmacmd5->shash, + (char *)user, 2 * len); /* convert ses->domainName to unicode and uppercase */ if (ses->domainName) { len = strlen(ses->domainName); domain = kmalloc(2 + (len * 2), GFP_KERNEL); - if (domain == NULL) + if (domain == NULL) { + cERROR(1, "calc_ntlmv2_hash: domain mem alloc failure"); + rc = -ENOMEM; goto calc_exit_1; + } len = cifs_strtoUCS((__le16 *)domain, ses->domainName, len, nls_cp); - /* the following line was removed since it didn't work well - with lower cased domain name that passed as an option. - Maybe converting the domain name earlier makes sense */ - /* UniStrupr(domain); */ - - hmac_md5_update((char *)domain, 2*len, pctxt); - + crypto_shash_update(&ses->server->secmech.sdeschmacmd5->shash, + (char *)domain, 2 * len); kfree(domain); + } else if (ses->serverName) { + len = strlen(ses->serverName); + + server = kmalloc(2 + (len * 2), GFP_KERNEL); + if (server == NULL) { + cERROR(1, "calc_ntlmv2_hash: server mem alloc failure"); + rc = -ENOMEM; + goto calc_exit_1; + } + len = cifs_strtoUCS((__le16 *)server, ses->serverName, len, + nls_cp); + crypto_shash_update(&ses->server->secmech.sdeschmacmd5->shash, + (char *)server, 2 * len); + kfree(server); } + + rc = crypto_shash_final(&ses->server->secmech.sdeschmacmd5->shash, + ntlmv2_hash); + calc_exit_1: kfree(user); calc_exit_2: - /* BB FIXME what about bytes 24 through 40 of the signing key? - compare with the NTLM example */ - hmac_md5_final(ses->ntlmv2_hash, pctxt); + return rc; +} + +static int +CalcNTLMv2_response(const struct cifsSesInfo *ses, char *ntlmv2_hash) +{ + int rc; + unsigned int offset = CIFS_SESS_KEY_SIZE + 8; + + if (!ses->server->secmech.sdeschmacmd5) { + cERROR(1, "calc_ntlmv2_hash: can't generate ntlmv2 hash\n"); + return -1; + } + + crypto_shash_setkey(ses->server->secmech.hmacmd5, + ntlmv2_hash, CIFS_HMAC_MD5_HASH_SIZE); + + rc = crypto_shash_init(&ses->server->secmech.sdeschmacmd5->shash); + if (rc) { + cERROR(1, "CalcNTLMv2_response: could not init hmacmd5"); + return rc; + } + + if (ses->server->secType == RawNTLMSSP) + memcpy(ses->auth_key.response + offset, + ses->ntlmssp->cryptkey, CIFS_SERVER_CHALLENGE_SIZE); + else + memcpy(ses->auth_key.response + offset, + ses->server->cryptkey, CIFS_SERVER_CHALLENGE_SIZE); + crypto_shash_update(&ses->server->secmech.sdeschmacmd5->shash, + ses->auth_key.response + offset, ses->auth_key.len - offset); + + rc = crypto_shash_final(&ses->server->secmech.sdeschmacmd5->shash, + ses->auth_key.response + CIFS_SESS_KEY_SIZE); - kfree(pctxt); return rc; } + int -setup_ntlmv2_rsp(struct cifsSesInfo *ses, char *resp_buf, - const struct nls_table *nls_cp) +setup_ntlmv2_rsp(struct cifsSesInfo *ses, const struct nls_table *nls_cp) { int rc; - struct ntlmv2_resp *buf = (struct ntlmv2_resp *)resp_buf; - struct HMACMD5Context context; - - buf->blob_signature = cpu_to_le32(0x00000101); - buf->reserved = 0; - buf->time = cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME)); - get_random_bytes(&buf->client_chal, sizeof(buf->client_chal)); - buf->reserved2 = 0; + int baselen; + unsigned int tilen; + struct ntlmv2_resp *buf; + char ntlmv2_hash[16]; + unsigned char *tiblob = NULL; /* target info blob */ if (ses->server->secType == RawNTLMSSP) { if (!ses->domainName) { - rc = find_domain_name(ses); + rc = find_domain_name(ses, nls_cp); if (rc) { cERROR(1, "error %d finding domain name", rc); goto setup_ntlmv2_rsp_ret; @@ -490,51 +575,179 @@ setup_ntlmv2_rsp(struct cifsSesInfo *ses, char *resp_buf, rc = build_avpair_blob(ses, nls_cp); if (rc) { cERROR(1, "error %d building av pair blob", rc); - return rc; + goto setup_ntlmv2_rsp_ret; } } - /* calculate buf->ntlmv2_hash */ - rc = calc_ntlmv2_hash(ses, nls_cp); + baselen = CIFS_SESS_KEY_SIZE + sizeof(struct ntlmv2_resp); + tilen = ses->auth_key.len; + tiblob = ses->auth_key.response; + + ses->auth_key.response = kmalloc(baselen + tilen, GFP_KERNEL); + if (!ses->auth_key.response) { + rc = ENOMEM; + ses->auth_key.len = 0; + cERROR(1, "%s: Can't allocate auth blob", __func__); + goto setup_ntlmv2_rsp_ret; + } + ses->auth_key.len += baselen; + + buf = (struct ntlmv2_resp *) + (ses->auth_key.response + CIFS_SESS_KEY_SIZE); + buf->blob_signature = cpu_to_le32(0x00000101); + buf->reserved = 0; + buf->time = cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME)); + get_random_bytes(&buf->client_chal, sizeof(buf->client_chal)); + buf->reserved2 = 0; + + memcpy(ses->auth_key.response + baselen, tiblob, tilen); + + /* calculate ntlmv2_hash */ + rc = calc_ntlmv2_hash(ses, ntlmv2_hash, nls_cp); if (rc) { cERROR(1, "could not get v2 hash rc %d", rc); goto setup_ntlmv2_rsp_ret; } - CalcNTLMv2_response(ses, resp_buf); + + /* calculate first part of the client response (CR1) */ + rc = CalcNTLMv2_response(ses, ntlmv2_hash); + if (rc) { + cERROR(1, "Could not calculate CR1 rc: %d", rc); + goto setup_ntlmv2_rsp_ret; + } /* now calculate the session key for NTLMv2 */ - hmac_md5_init_limK_to_64(ses->ntlmv2_hash, 16, &context); - hmac_md5_update(resp_buf, 16, &context); - hmac_md5_final(ses->auth_key.data.ntlmv2.key, &context); + crypto_shash_setkey(ses->server->secmech.hmacmd5, + ntlmv2_hash, CIFS_HMAC_MD5_HASH_SIZE); + + rc = crypto_shash_init(&ses->server->secmech.sdeschmacmd5->shash); + if (rc) { + cERROR(1, "%s: Could not init hmacmd5\n", __func__); + goto setup_ntlmv2_rsp_ret; + } - memcpy(&ses->auth_key.data.ntlmv2.resp, resp_buf, - sizeof(struct ntlmv2_resp)); - ses->auth_key.len = 16 + sizeof(struct ntlmv2_resp); + crypto_shash_update(&ses->server->secmech.sdeschmacmd5->shash, + ses->auth_key.response + CIFS_SESS_KEY_SIZE, + CIFS_HMAC_MD5_HASH_SIZE); - return 0; + rc = crypto_shash_final(&ses->server->secmech.sdeschmacmd5->shash, + ses->auth_key.response); setup_ntlmv2_rsp_ret: - kfree(ses->tiblob); - ses->tiblob = NULL; - ses->tilen = 0; + kfree(tiblob); return rc; } -void CalcNTLMv2_response(const struct cifsSesInfo *ses, - char *v2_session_response) +int +calc_seckey(struct cifsSesInfo *ses) { - struct HMACMD5Context context; - /* rest of v2 struct already generated */ - memcpy(v2_session_response + 8, ses->cryptKey, 8); - hmac_md5_init_limK_to_64(ses->ntlmv2_hash, 16, &context); + int rc; + struct crypto_blkcipher *tfm_arc4; + struct scatterlist sgin, sgout; + struct blkcipher_desc desc; + unsigned char sec_key[CIFS_SESS_KEY_SIZE]; /* a nonce */ + + get_random_bytes(sec_key, CIFS_SESS_KEY_SIZE); + + tfm_arc4 = crypto_alloc_blkcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC); + if (!tfm_arc4 || IS_ERR(tfm_arc4)) { + cERROR(1, "could not allocate crypto API arc4\n"); + return PTR_ERR(tfm_arc4); + } - hmac_md5_update(v2_session_response+8, - sizeof(struct ntlmv2_resp) - 8, &context); + desc.tfm = tfm_arc4; - if (ses->tilen) - hmac_md5_update(ses->tiblob, ses->tilen, &context); + crypto_blkcipher_setkey(tfm_arc4, ses->auth_key.response, + CIFS_SESS_KEY_SIZE); - hmac_md5_final(v2_session_response, &context); -/* cifs_dump_mem("v2_sess_rsp: ", v2_session_response, 32); */ + sg_init_one(&sgin, sec_key, CIFS_SESS_KEY_SIZE); + sg_init_one(&sgout, ses->ntlmssp->ciphertext, CIFS_CPHTXT_SIZE); + + rc = crypto_blkcipher_encrypt(&desc, &sgout, &sgin, CIFS_CPHTXT_SIZE); + if (rc) { + cERROR(1, "could not encrypt session key rc: %d\n", rc); + crypto_free_blkcipher(tfm_arc4); + return rc; + } + + /* make secondary_key/nonce as session key */ + memcpy(ses->auth_key.response, sec_key, CIFS_SESS_KEY_SIZE); + /* and make len as that of session key only */ + ses->auth_key.len = CIFS_SESS_KEY_SIZE; + + crypto_free_blkcipher(tfm_arc4); + + return 0; +} + +void +cifs_crypto_shash_release(struct TCP_Server_Info *server) +{ + if (server->secmech.md5) + crypto_free_shash(server->secmech.md5); + + if (server->secmech.hmacmd5) + crypto_free_shash(server->secmech.hmacmd5); + + kfree(server->secmech.sdeschmacmd5); + + kfree(server->secmech.sdescmd5); +} + +int +cifs_crypto_shash_allocate(struct TCP_Server_Info *server) +{ + int rc; + unsigned int size; + + server->secmech.hmacmd5 = crypto_alloc_shash("hmac(md5)", 0, 0); + if (!server->secmech.hmacmd5 || + IS_ERR(server->secmech.hmacmd5)) { + cERROR(1, "could not allocate crypto hmacmd5\n"); + return PTR_ERR(server->secmech.hmacmd5); + } + + server->secmech.md5 = crypto_alloc_shash("md5", 0, 0); + if (!server->secmech.md5 || IS_ERR(server->secmech.md5)) { + cERROR(1, "could not allocate crypto md5\n"); + rc = PTR_ERR(server->secmech.md5); + goto crypto_allocate_md5_fail; + } + + size = sizeof(struct shash_desc) + + crypto_shash_descsize(server->secmech.hmacmd5); + server->secmech.sdeschmacmd5 = kmalloc(size, GFP_KERNEL); + if (!server->secmech.sdeschmacmd5) { + cERROR(1, "cifs_crypto_shash_allocate: can't alloc hmacmd5\n"); + rc = -ENOMEM; + goto crypto_allocate_hmacmd5_sdesc_fail; + } + server->secmech.sdeschmacmd5->shash.tfm = server->secmech.hmacmd5; + server->secmech.sdeschmacmd5->shash.flags = 0x0; + + + size = sizeof(struct shash_desc) + + crypto_shash_descsize(server->secmech.md5); + server->secmech.sdescmd5 = kmalloc(size, GFP_KERNEL); + if (!server->secmech.sdescmd5) { + cERROR(1, "cifs_crypto_shash_allocate: can't alloc md5\n"); + rc = -ENOMEM; + goto crypto_allocate_md5_sdesc_fail; + } + server->secmech.sdescmd5->shash.tfm = server->secmech.md5; + server->secmech.sdescmd5->shash.flags = 0x0; + + return 0; + +crypto_allocate_md5_sdesc_fail: + kfree(server->secmech.sdeschmacmd5); + +crypto_allocate_hmacmd5_sdesc_fail: + crypto_free_shash(server->secmech.md5); + +crypto_allocate_md5_fail: + crypto_free_shash(server->secmech.hmacmd5); + + return rc; } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 34371637f210..76c8a906a63e 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -116,7 +116,7 @@ cifs_read_super(struct super_block *sb, void *data, return -ENOMEM; spin_lock_init(&cifs_sb->tlink_tree_lock); - INIT_RADIX_TREE(&cifs_sb->tlink_tree, GFP_KERNEL); + cifs_sb->tlink_tree = RB_ROOT; rc = bdi_setup_and_register(&cifs_sb->bdi, "cifs", BDI_CAP_MAP_COPY); if (rc) { @@ -318,12 +318,10 @@ cifs_alloc_inode(struct super_block *sb) return NULL; cifs_inode->cifsAttrs = 0x20; /* default */ cifs_inode->time = 0; - cifs_inode->write_behind_rc = 0; /* Until the file is open and we have gotten oplock info back from the server, can not assume caching of file data or metadata */ - cifs_inode->clientCanCacheRead = false; - cifs_inode->clientCanCacheAll = false; + cifs_set_oplock_level(cifs_inode, 0); cifs_inode->delete_pending = false; cifs_inode->invalid_mapping = false; cifs_inode->vfs_inode.i_blkbits = 14; /* 2**14 = CIFS_MAX_MSGSIZE */ @@ -460,6 +458,8 @@ cifs_show_options(struct seq_file *s, struct vfsmount *m) seq_printf(s, ",acl"); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) seq_printf(s, ",mfsymlinks"); + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_FSCACHE) + seq_printf(s, ",fsc"); seq_printf(s, ",rsize=%d", cifs_sb->rsize); seq_printf(s, ",wsize=%d", cifs_sb->wsize); @@ -545,9 +545,9 @@ static const struct super_operations cifs_super_ops = { #endif }; -static int -cifs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry * +cifs_do_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { int rc; struct super_block *sb; @@ -557,18 +557,17 @@ cifs_get_sb(struct file_system_type *fs_type, cFYI(1, "Devname: %s flags: %d ", dev_name, flags); if (IS_ERR(sb)) - return PTR_ERR(sb); + return ERR_CAST(sb); sb->s_flags = flags; rc = cifs_read_super(sb, data, dev_name, flags & MS_SILENT ? 1 : 0); if (rc) { deactivate_locked_super(sb); - return rc; + return ERR_PTR(rc); } sb->s_flags |= MS_ACTIVE; - simple_set_mnt(mnt, sb); - return 0; + return dget(sb->s_root); } static ssize_t cifs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, @@ -634,7 +633,7 @@ static int cifs_setlease(struct file *file, long arg, struct file_lock **lease) struct file_system_type cifs_fs_type = { .owner = THIS_MODULE, .name = "cifs", - .get_sb = cifs_get_sb, + .mount = cifs_do_mount, .kill_sb = kill_anon_super, /* .fs_flags */ }; diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index f35795a16b42..897b2b2b28b5 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -112,5 +112,5 @@ 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 "1.67" +#define CIFS_VERSION "1.68" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 3365e77f6f24..b577bf0a1bb3 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -25,6 +25,9 @@ #include <linux/workqueue.h> #include "cifs_fs_sb.h" #include "cifsacl.h" +#include <crypto/internal/hash.h> +#include <linux/scatterlist.h> + /* * The sizes of various internal tables and strings */ @@ -74,7 +77,7 @@ * CIFS vfs client Status information (based on what we know.) */ - /* associated with each tcp and smb session */ +/* associated with each tcp and smb session */ enum statusEnum { CifsNew = 0, CifsGood, @@ -99,14 +102,29 @@ enum protocolEnum { struct session_key { unsigned int len; - union { - char ntlm[CIFS_SESS_KEY_SIZE + 16]; - char krb5[CIFS_SESS_KEY_SIZE + 16]; /* BB: length correct? */ - struct { - char key[16]; - struct ntlmv2_resp resp; - } ntlmv2; - } data; + char *response; +}; + +/* crypto security descriptor definition */ +struct sdesc { + struct shash_desc shash; + char ctx[]; +}; + +/* crypto hashing related structure/fields, not specific to a sec mech */ +struct cifs_secmech { + struct crypto_shash *hmacmd5; /* hmac-md5 hash function */ + struct crypto_shash *md5; /* md5 hash function */ + struct sdesc *sdeschmacmd5; /* ctxt to generate ntlmv2 hash, CR1 */ + struct sdesc *sdescmd5; /* ctxt to generate cifs/smb signature */ +}; + +/* per smb session structure/fields */ +struct ntlmssp_auth { + __u32 client_flags; /* sent by client in type 1 ntlmsssp exchange */ + __u32 server_flags; /* sent by server in type 2 ntlmssp exchange */ + unsigned char ciphertext[CIFS_CPHTXT_SIZE]; /* sent to server */ + char cryptkey[CIFS_CRYPTO_KEY_SIZE]; /* used by ntlmssp */ }; struct cifs_cred { @@ -179,12 +197,14 @@ struct TCP_Server_Info { int capabilities; /* allow selective disabling of caps by smb sess */ int timeAdj; /* Adjust for difference in server time zone in sec */ __u16 CurrentMid; /* multiplex id - rotating counter */ + char cryptkey[CIFS_CRYPTO_KEY_SIZE]; /* used by ntlm, ntlmv2 etc */ /* 16th byte of RFC1001 workstation name is always null */ char workstation_RFC1001_name[RFC1001_NAME_LEN_WITH_NULL]; __u32 sequence_number; /* needed for CIFS PDU signature */ struct session_key session_key; unsigned long lstrp; /* when we got last response from this server */ u16 dialect; /* dialect index that server chose */ + struct cifs_secmech secmech; /* crypto sec mech functs, descriptors */ /* extended security flavors that server supports */ bool sec_kerberos; /* supports plain Kerberos */ bool sec_mskerberos; /* supports legacy MS Kerberos */ @@ -222,11 +242,8 @@ struct cifsSesInfo { char userName[MAX_USERNAME_SIZE + 1]; char *domainName; char *password; - char cryptKey[CIFS_CRYPTO_KEY_SIZE]; struct session_key auth_key; - char ntlmv2_hash[16]; - unsigned int tilen; /* length of the target info blob */ - unsigned char *tiblob; /* target info blob in challenge response */ + struct ntlmssp_auth *ntlmssp; /* ciphertext, flags, server challenge */ bool need_reconnect:1; /* connection reset, uid now invalid */ }; /* no more than one of the following three session flags may be set */ @@ -319,7 +336,8 @@ struct cifsTconInfo { * "get" on the container. */ struct tcon_link { - unsigned long tl_index; + struct rb_node tl_rbnode; + uid_t tl_uid; unsigned long tl_flags; #define TCON_LINK_MASTER 0 #define TCON_LINK_PENDING 1 @@ -395,16 +413,19 @@ struct cifsFileInfo { struct list_head llist; /* list of byte range locks we have. */ bool invalidHandle:1; /* file closed via session abend */ bool oplock_break_cancelled:1; - atomic_t count; /* reference count */ + int count; /* refcount protected by cifs_file_list_lock */ struct mutex fh_mutex; /* prevents reopen race after dead ses*/ struct cifs_search_info srch_inf; struct work_struct oplock_break; /* work for oplock breaks */ }; -/* Take a reference on the file private data */ +/* + * Take a reference on the file private data. Must be called with + * cifs_file_list_lock held. + */ static inline void cifsFileInfo_get(struct cifsFileInfo *cifs_file) { - atomic_inc(&cifs_file->count); + ++cifs_file->count; } void cifsFileInfo_put(struct cifsFileInfo *cifs_file); @@ -417,7 +438,6 @@ struct cifsInodeInfo { struct list_head lockList; /* BB add in lists for dirty pages i.e. write caching info for oplock */ struct list_head openFileList; - int write_behind_rc; __u32 cifsAttrs; /* e.g. DOS archive bit, sparse, compressed, system */ unsigned long time; /* jiffies of last update/check of inode */ bool clientCanCacheRead:1; /* read oplock */ @@ -668,7 +688,7 @@ require use of the stronger protocol */ * GlobalMid_Lock protects: * list operations on pending_mid_q and oplockQ * updates to XID counters, multiplex id and SMB sequence numbers - * GlobalSMBSesLock protects: + * cifs_file_list_lock protects: * list operations on tcp and SMB session lists and tCon lists * f_owner.lock protects certain per file struct operations * mapping->page_lock protects certain per page operations diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h index b0f4b5656d4c..de36b09763a8 100644 --- a/fs/cifs/cifspdu.h +++ b/fs/cifs/cifspdu.h @@ -131,9 +131,20 @@ #define CIFS_CRYPTO_KEY_SIZE (8) /* + * Size of the ntlm client response + */ +#define CIFS_AUTH_RESP_SIZE (24) + +/* * Size of the session key (crypto key encrypted with the password */ -#define CIFS_SESS_KEY_SIZE (24) +#define CIFS_SESS_KEY_SIZE (16) + +#define CIFS_CLIENT_CHALLENGE_SIZE (8) +#define CIFS_SERVER_CHALLENGE_SIZE (8) +#define CIFS_HMAC_MD5_HASH_SIZE (16) +#define CIFS_CPHTXT_SIZE (16) +#define CIFS_NTHASH_SIZE (16) /* * Maximum user name length diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index e593c40ba7ba..db961dc4fd3d 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -104,6 +104,7 @@ extern struct timespec cifs_NTtimeToUnix(__le64 utc_nanoseconds_since_1601); extern u64 cifs_UnixTimeToNT(struct timespec); extern struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time, int offset); +extern void cifs_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock); extern struct cifsFileInfo *cifs_new_fileinfo(__u16 fileHandle, struct file *file, struct tcon_link *tlink, @@ -129,10 +130,12 @@ extern int cifs_get_file_info_unix(struct file *filp); extern int cifs_get_inode_info_unix(struct inode **pinode, const unsigned char *search_path, struct super_block *sb, int xid); -extern void cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, +extern int cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, struct inode *inode, const char *path, const __u16 *pfid); -extern int mode_to_acl(struct inode *inode, const char *path, __u64); +extern int mode_to_cifs_acl(struct inode *inode, const char *path, __u64); +extern struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *, struct inode *, + const char *, u32 *); extern int cifs_mount(struct super_block *, struct cifs_sb_info *, char *, const char *); @@ -362,13 +365,15 @@ extern int cifs_sign_smb(struct smb_hdr *, struct TCP_Server_Info *, __u32 *); extern int cifs_sign_smb2(struct kvec *iov, int n_vec, struct TCP_Server_Info *, __u32 *); extern int cifs_verify_signature(struct smb_hdr *, - const struct session_key *session_key, + struct TCP_Server_Info *server, __u32 expected_sequence_number); -extern int cifs_calculate_session_key(struct session_key *key, const char *rn, - const char *pass); -extern void CalcNTLMv2_response(const struct cifsSesInfo *, char *); -extern int setup_ntlmv2_rsp(struct cifsSesInfo *, char *, - const struct nls_table *); +extern void SMBNTencrypt(unsigned char *, unsigned char *, unsigned char *); +extern int setup_ntlm_response(struct cifsSesInfo *); +extern int setup_ntlmv2_rsp(struct cifsSesInfo *, const struct nls_table *); +extern int cifs_crypto_shash_allocate(struct TCP_Server_Info *); +extern void cifs_crypto_shash_release(struct TCP_Server_Info *); +extern int calc_seckey(struct cifsSesInfo *); + #ifdef CONFIG_CIFS_WEAK_PW_HASH extern void calc_lanman_hash(const char *password, const char *cryptkey, bool encrypt, char *lnm_session_key); diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index e98f1f317b15..2f2632b6df5a 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -503,7 +503,7 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses) if (rsp->EncryptionKeyLength == cpu_to_le16(CIFS_CRYPTO_KEY_SIZE)) { - memcpy(ses->cryptKey, rsp->EncryptionKey, + memcpy(ses->server->cryptkey, rsp->EncryptionKey, CIFS_CRYPTO_KEY_SIZE); } else if (server->secMode & SECMODE_PW_ENCRYPT) { rc = -EIO; /* need cryptkey unless plain text */ @@ -574,7 +574,7 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses) server->timeAdj = (int)(__s16)le16_to_cpu(pSMBr->ServerTimeZone); server->timeAdj *= 60; if (pSMBr->EncryptionKeyLength == CIFS_CRYPTO_KEY_SIZE) { - memcpy(ses->cryptKey, pSMBr->u.EncryptionKey, + memcpy(ses->server->cryptkey, pSMBr->u.EncryptionKey, CIFS_CRYPTO_KEY_SIZE); } else if ((pSMBr->hdr.Flags2 & SMBFLG2_EXT_SEC) && (pSMBr->EncryptionKeyLength == 0)) { diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 7e73176acb58..32fa4d9b5dbc 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -116,6 +116,7 @@ struct smb_vol { static int ipv4_connect(struct TCP_Server_Info *server); static int ipv6_connect(struct TCP_Server_Info *server); +static void tlink_rb_insert(struct rb_root *root, struct tcon_link *new_tlink); static void cifs_prune_tlinks(struct work_struct *work); /* @@ -175,6 +176,9 @@ cifs_reconnect(struct TCP_Server_Info *server) } server->sequence_number = 0; server->session_estab = false; + kfree(server->session_key.response); + server->session_key.response = NULL; + server->session_key.len = 0; spin_lock(&GlobalMid_Lock); list_for_each(tmp, &server->pending_mid_q) { @@ -1064,7 +1068,7 @@ cifs_parse_mount_options(char *options, const char *devname, } i = cifs_convert_address((struct sockaddr *)&vol->srcaddr, value, strlen(value)); - if (i < 0) { + if (i == 0) { printk(KERN_WARNING "CIFS: Could not parse" " srcaddr: %s\n", value); @@ -1348,6 +1352,11 @@ cifs_parse_mount_options(char *options, const char *devname, "supported. Instead set " "/proc/fs/cifs/LookupCacheEnabled to 0\n"); } else if (strnicmp(data, "fsc", 3) == 0) { +#ifndef CONFIG_CIFS_FSCACHE + cERROR(1, "FS-Cache support needs CONFIG_CIFS_FSCACHE" + "kernel config option set"); + return 1; +#endif vol->fsc = true; } else if (strnicmp(data, "mfsymlinks", 10) == 0) { vol->mfsymlinks = true; @@ -1560,8 +1569,13 @@ cifs_put_tcp_session(struct TCP_Server_Info *server) server->tcpStatus = CifsExiting; spin_unlock(&GlobalMid_Lock); + cifs_crypto_shash_release(server); cifs_fscache_release_client_cookie(server); + kfree(server->session_key.response); + server->session_key.response = NULL; + server->session_key.len = 0; + task = xchg(&server->tsk, NULL); if (task) force_sig(SIGKILL, task); @@ -1614,10 +1628,16 @@ cifs_get_tcp_session(struct smb_vol *volume_info) goto out_err; } + rc = cifs_crypto_shash_allocate(tcp_ses); + if (rc) { + cERROR(1, "could not setup hash structures rc %d", rc); + goto out_err; + } + tcp_ses->hostname = extract_hostname(volume_info->UNC); if (IS_ERR(tcp_ses->hostname)) { rc = PTR_ERR(tcp_ses->hostname); - goto out_err; + goto out_err_crypto_release; } tcp_ses->noblocksnd = volume_info->noblocksnd; @@ -1661,7 +1681,7 @@ cifs_get_tcp_session(struct smb_vol *volume_info) } if (rc < 0) { cERROR(1, "Error connecting to socket. Aborting operation"); - goto out_err; + goto out_err_crypto_release; } /* @@ -1675,7 +1695,7 @@ cifs_get_tcp_session(struct smb_vol *volume_info) rc = PTR_ERR(tcp_ses->tsk); cERROR(1, "error %d create cifsd thread", rc); module_put(THIS_MODULE); - goto out_err; + goto out_err_crypto_release; } /* thread spawned, put it on the list */ @@ -1687,6 +1707,9 @@ cifs_get_tcp_session(struct smb_vol *volume_info) return tcp_ses; +out_err_crypto_release: + cifs_crypto_shash_release(tcp_ses); + out_err: if (tcp_ses) { if (!IS_ERR(tcp_ses->hostname)) @@ -1801,8 +1824,6 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info) if (ses == NULL) goto get_ses_fail; - ses->tilen = 0; - ses->tiblob = NULL; /* new SMB session uses our server ref */ ses->server = server; if (server->addr.sockAddr6.sin6_family == AF_INET6) @@ -1823,10 +1844,9 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info) goto get_ses_fail; } if (volume_info->domainname) { - int len = strlen(volume_info->domainname); - ses->domainName = kmalloc(len + 1, GFP_KERNEL); - if (ses->domainName) - strcpy(ses->domainName, volume_info->domainname); + ses->domainName = kstrdup(volume_info->domainname, GFP_KERNEL); + if (!ses->domainName) + goto get_ses_fail; } ses->cred_uid = volume_info->cred_uid; ses->linux_uid = volume_info->linux_uid; @@ -2886,24 +2906,16 @@ remote_path_check: goto mount_fail_check; } - tlink->tl_index = pSesInfo->linux_uid; + tlink->tl_uid = pSesInfo->linux_uid; tlink->tl_tcon = tcon; tlink->tl_time = jiffies; set_bit(TCON_LINK_MASTER, &tlink->tl_flags); set_bit(TCON_LINK_IN_TREE, &tlink->tl_flags); - rc = radix_tree_preload(GFP_KERNEL); - if (rc == -ENOMEM) { - kfree(tlink); - goto mount_fail_check; - } - + cifs_sb->master_tlink = tlink; spin_lock(&cifs_sb->tlink_tree_lock); - radix_tree_insert(&cifs_sb->tlink_tree, pSesInfo->linux_uid, tlink); - radix_tree_tag_set(&cifs_sb->tlink_tree, pSesInfo->linux_uid, - CIFS_TLINK_MASTER_TAG); + tlink_rb_insert(&cifs_sb->tlink_tree, tlink); spin_unlock(&cifs_sb->tlink_tree_lock); - radix_tree_preload_end(); queue_delayed_work(system_nrt_wq, &cifs_sb->prune_tlinks, TLINK_IDLE_EXPIRE); @@ -2985,13 +2997,13 @@ CIFSTCon(unsigned int xid, struct cifsSesInfo *ses, #ifdef CONFIG_CIFS_WEAK_PW_HASH if ((global_secflags & CIFSSEC_MAY_LANMAN) && (ses->server->secType == LANMAN)) - calc_lanman_hash(tcon->password, ses->cryptKey, + calc_lanman_hash(tcon->password, ses->server->cryptkey, ses->server->secMode & SECMODE_PW_ENCRYPT ? true : false, bcc_ptr); else #endif /* CIFS_WEAK_PW_HASH */ - SMBNTencrypt(tcon->password, ses->cryptKey, bcc_ptr); + SMBNTencrypt(tcon->password, ses->server->cryptkey, bcc_ptr); bcc_ptr += CIFS_SESS_KEY_SIZE; if (ses->capabilities & CAP_UNICODE) { @@ -3093,32 +3105,25 @@ CIFSTCon(unsigned int xid, struct cifsSesInfo *ses, int cifs_umount(struct super_block *sb, struct cifs_sb_info *cifs_sb) { - int i, ret; + struct rb_root *root = &cifs_sb->tlink_tree; + struct rb_node *node; + struct tcon_link *tlink; char *tmp; - struct tcon_link *tlink[8]; - unsigned long index = 0; cancel_delayed_work_sync(&cifs_sb->prune_tlinks); - do { - spin_lock(&cifs_sb->tlink_tree_lock); - ret = radix_tree_gang_lookup(&cifs_sb->tlink_tree, - (void **)tlink, index, - ARRAY_SIZE(tlink)); - /* increment index for next pass */ - if (ret > 0) - index = tlink[ret - 1]->tl_index + 1; - for (i = 0; i < ret; i++) { - cifs_get_tlink(tlink[i]); - clear_bit(TCON_LINK_IN_TREE, &tlink[i]->tl_flags); - radix_tree_delete(&cifs_sb->tlink_tree, - tlink[i]->tl_index); - } - spin_unlock(&cifs_sb->tlink_tree_lock); + spin_lock(&cifs_sb->tlink_tree_lock); + while ((node = rb_first(root))) { + tlink = rb_entry(node, struct tcon_link, tl_rbnode); + cifs_get_tlink(tlink); + clear_bit(TCON_LINK_IN_TREE, &tlink->tl_flags); + rb_erase(node, root); - for (i = 0; i < ret; i++) - cifs_put_tlink(tlink[i]); - } while (ret != 0); + spin_unlock(&cifs_sb->tlink_tree_lock); + cifs_put_tlink(tlink); + spin_lock(&cifs_sb->tlink_tree_lock); + } + spin_unlock(&cifs_sb->tlink_tree_lock); tmp = cifs_sb->prepath; cifs_sb->prepathlen = 0; @@ -3178,10 +3183,11 @@ int cifs_setup_session(unsigned int xid, struct cifsSesInfo *ses, } else { mutex_lock(&ses->server->srv_mutex); if (!server->session_estab) { - memcpy(&server->session_key.data, - &ses->auth_key.data, ses->auth_key.len); + server->session_key.response = ses->auth_key.response; server->session_key.len = ses->auth_key.len; - ses->server->session_estab = true; + server->sequence_number = 0x2; + server->session_estab = true; + ses->auth_key.response = NULL; } mutex_unlock(&server->srv_mutex); @@ -3192,6 +3198,12 @@ int cifs_setup_session(unsigned int xid, struct cifsSesInfo *ses, spin_unlock(&GlobalMid_Lock); } + kfree(ses->auth_key.response); + ses->auth_key.response = NULL; + ses->auth_key.len = 0; + kfree(ses->ntlmssp); + ses->ntlmssp = NULL; + return rc; } @@ -3250,22 +3262,10 @@ out: return tcon; } -static struct tcon_link * +static inline struct tcon_link * cifs_sb_master_tlink(struct cifs_sb_info *cifs_sb) { - struct tcon_link *tlink; - unsigned int ret; - - spin_lock(&cifs_sb->tlink_tree_lock); - ret = radix_tree_gang_lookup_tag(&cifs_sb->tlink_tree, (void **)&tlink, - 0, 1, CIFS_TLINK_MASTER_TAG); - spin_unlock(&cifs_sb->tlink_tree_lock); - - /* the master tcon should always be present */ - if (ret == 0) - BUG(); - - return tlink; + return cifs_sb->master_tlink; } struct cifsTconInfo * @@ -3281,6 +3281,47 @@ cifs_sb_tcon_pending_wait(void *unused) return signal_pending(current) ? -ERESTARTSYS : 0; } +/* find and return a tlink with given uid */ +static struct tcon_link * +tlink_rb_search(struct rb_root *root, uid_t uid) +{ + struct rb_node *node = root->rb_node; + struct tcon_link *tlink; + + while (node) { + tlink = rb_entry(node, struct tcon_link, tl_rbnode); + + if (tlink->tl_uid > uid) + node = node->rb_left; + else if (tlink->tl_uid < uid) + node = node->rb_right; + else + return tlink; + } + return NULL; +} + +/* insert a tcon_link into the tree */ +static void +tlink_rb_insert(struct rb_root *root, struct tcon_link *new_tlink) +{ + struct rb_node **new = &(root->rb_node), *parent = NULL; + struct tcon_link *tlink; + + while (*new) { + tlink = rb_entry(*new, struct tcon_link, tl_rbnode); + parent = *new; + + if (tlink->tl_uid > new_tlink->tl_uid) + new = &((*new)->rb_left); + else + new = &((*new)->rb_right); + } + + rb_link_node(&new_tlink->tl_rbnode, parent, new); + rb_insert_color(&new_tlink->tl_rbnode, root); +} + /* * Find or construct an appropriate tcon given a cifs_sb and the fsuid of the * current task. @@ -3288,7 +3329,7 @@ cifs_sb_tcon_pending_wait(void *unused) * If the superblock doesn't refer to a multiuser mount, then just return * the master tcon for the mount. * - * First, search the radix tree for an existing tcon for this fsuid. If one + * First, search the rbtree for an existing tcon for this fsuid. If one * exists, then check to see if it's pending construction. If it is then wait * for construction to complete. Once it's no longer pending, check to see if * it failed and either return an error or retry construction, depending on @@ -3301,14 +3342,14 @@ struct tcon_link * cifs_sb_tlink(struct cifs_sb_info *cifs_sb) { int ret; - unsigned long fsuid = (unsigned long) current_fsuid(); + uid_t fsuid = current_fsuid(); struct tcon_link *tlink, *newtlink; if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER)) return cifs_get_tlink(cifs_sb_master_tlink(cifs_sb)); spin_lock(&cifs_sb->tlink_tree_lock); - tlink = radix_tree_lookup(&cifs_sb->tlink_tree, fsuid); + tlink = tlink_rb_search(&cifs_sb->tlink_tree, fsuid); if (tlink) cifs_get_tlink(tlink); spin_unlock(&cifs_sb->tlink_tree_lock); @@ -3317,36 +3358,24 @@ cifs_sb_tlink(struct cifs_sb_info *cifs_sb) newtlink = kzalloc(sizeof(*tlink), GFP_KERNEL); if (newtlink == NULL) return ERR_PTR(-ENOMEM); - newtlink->tl_index = fsuid; + newtlink->tl_uid = fsuid; newtlink->tl_tcon = ERR_PTR(-EACCES); set_bit(TCON_LINK_PENDING, &newtlink->tl_flags); set_bit(TCON_LINK_IN_TREE, &newtlink->tl_flags); cifs_get_tlink(newtlink); - ret = radix_tree_preload(GFP_KERNEL); - if (ret != 0) { - kfree(newtlink); - return ERR_PTR(ret); - } - spin_lock(&cifs_sb->tlink_tree_lock); /* was one inserted after previous search? */ - tlink = radix_tree_lookup(&cifs_sb->tlink_tree, fsuid); + tlink = tlink_rb_search(&cifs_sb->tlink_tree, fsuid); if (tlink) { cifs_get_tlink(tlink); spin_unlock(&cifs_sb->tlink_tree_lock); - radix_tree_preload_end(); kfree(newtlink); goto wait_for_construction; } - ret = radix_tree_insert(&cifs_sb->tlink_tree, fsuid, newtlink); - spin_unlock(&cifs_sb->tlink_tree_lock); - radix_tree_preload_end(); - if (ret) { - kfree(newtlink); - return ERR_PTR(ret); - } tlink = newtlink; + tlink_rb_insert(&cifs_sb->tlink_tree, tlink); + spin_unlock(&cifs_sb->tlink_tree_lock); } else { wait_for_construction: ret = wait_on_bit(&tlink->tl_flags, TCON_LINK_PENDING, @@ -3392,39 +3421,39 @@ cifs_prune_tlinks(struct work_struct *work) { struct cifs_sb_info *cifs_sb = container_of(work, struct cifs_sb_info, prune_tlinks.work); - struct tcon_link *tlink[8]; - unsigned long now = jiffies; - unsigned long index = 0; - int i, ret; + struct rb_root *root = &cifs_sb->tlink_tree; + struct rb_node *node = rb_first(root); + struct rb_node *tmp; + struct tcon_link *tlink; - do { - spin_lock(&cifs_sb->tlink_tree_lock); - ret = radix_tree_gang_lookup(&cifs_sb->tlink_tree, - (void **)tlink, index, - ARRAY_SIZE(tlink)); - /* increment index for next pass */ - if (ret > 0) - index = tlink[ret - 1]->tl_index + 1; - for (i = 0; i < ret; i++) { - if (test_bit(TCON_LINK_MASTER, &tlink[i]->tl_flags) || - atomic_read(&tlink[i]->tl_count) != 0 || - time_after(tlink[i]->tl_time + TLINK_IDLE_EXPIRE, - now)) { - tlink[i] = NULL; - continue; - } - cifs_get_tlink(tlink[i]); - clear_bit(TCON_LINK_IN_TREE, &tlink[i]->tl_flags); - radix_tree_delete(&cifs_sb->tlink_tree, - tlink[i]->tl_index); - } - spin_unlock(&cifs_sb->tlink_tree_lock); + /* + * Because we drop the spinlock in the loop in order to put the tlink + * it's not guarded against removal of links from the tree. The only + * places that remove entries from the tree are this function and + * umounts. Because this function is non-reentrant and is canceled + * before umount can proceed, this is safe. + */ + spin_lock(&cifs_sb->tlink_tree_lock); + node = rb_first(root); + while (node != NULL) { + tmp = node; + node = rb_next(tmp); + tlink = rb_entry(tmp, struct tcon_link, tl_rbnode); + + if (test_bit(TCON_LINK_MASTER, &tlink->tl_flags) || + atomic_read(&tlink->tl_count) != 0 || + time_after(tlink->tl_time + TLINK_IDLE_EXPIRE, jiffies)) + continue; - for (i = 0; i < ret; i++) { - if (tlink[i] != NULL) - cifs_put_tlink(tlink[i]); - } - } while (ret != 0); + cifs_get_tlink(tlink); + clear_bit(TCON_LINK_IN_TREE, &tlink->tl_flags); + rb_erase(tmp, root); + + spin_unlock(&cifs_sb->tlink_tree_lock); + cifs_put_tlink(tlink); + spin_lock(&cifs_sb->tlink_tree_lock); + } + spin_unlock(&cifs_sb->tlink_tree_lock); queue_delayed_work(system_nrt_wq, &cifs_sb->prune_tlinks, TLINK_IDLE_EXPIRE); diff --git a/fs/cifs/dns_resolve.c b/fs/cifs/dns_resolve.c index 0eb87026cad3..548f06230a6d 100644 --- a/fs/cifs/dns_resolve.c +++ b/fs/cifs/dns_resolve.c @@ -66,7 +66,7 @@ dns_resolve_server_name_to_ip(const char *unc, char **ip_addr) /* Search for server name delimiter */ sep = memchr(hostname, '\\', len); if (sep) - len = sep - unc; + len = sep - hostname; else cFYI(1, "%s: probably server name is whole unc: %s", __func__, unc); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 8c81e7b14d53..b857ce5db775 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -131,8 +131,7 @@ static inline int cifs_open_inode_helper(struct inode *inode, /* BB no need to lock inode until after invalidate since namei code should already have it locked? */ rc = filemap_write_and_wait(inode->i_mapping); - if (rc != 0) - pCifsInode->write_behind_rc = rc; + mapping_set_error(inode->i_mapping, rc); } cFYI(1, "invalidating remote inode since open detected it " "changed"); @@ -147,12 +146,7 @@ client_can_cache: rc = cifs_get_inode_info(&inode, full_path, buf, inode->i_sb, xid, NULL); - if ((oplock & 0xF) == OPLOCK_EXCLUSIVE) { - pCifsInode->clientCanCacheAll = true; - pCifsInode->clientCanCacheRead = true; - cFYI(1, "Exclusive Oplock granted on inode %p", inode); - } else if ((oplock & 0xF) == OPLOCK_READ) - pCifsInode->clientCanCacheRead = true; + cifs_set_oplock_level(pCifsInode, oplock); return rc; } @@ -232,6 +226,7 @@ cifs_new_fileinfo(__u16 fileHandle, struct file *file, if (pCifsFile == NULL) return pCifsFile; + pCifsFile->count = 1; pCifsFile->netfid = fileHandle; pCifsFile->pid = current->tgid; pCifsFile->uid = current_fsuid(); @@ -242,7 +237,6 @@ cifs_new_fileinfo(__u16 fileHandle, struct file *file, mutex_init(&pCifsFile->fh_mutex); mutex_init(&pCifsFile->lock_mutex); INIT_LIST_HEAD(&pCifsFile->llist); - atomic_set(&pCifsFile->count, 1); INIT_WORK(&pCifsFile->oplock_break, cifs_oplock_break); spin_lock(&cifs_file_list_lock); @@ -254,12 +248,7 @@ cifs_new_fileinfo(__u16 fileHandle, struct file *file, list_add_tail(&pCifsFile->flist, &pCifsInode->openFileList); spin_unlock(&cifs_file_list_lock); - if ((oplock & 0xF) == OPLOCK_EXCLUSIVE) { - pCifsInode->clientCanCacheAll = true; - pCifsInode->clientCanCacheRead = true; - cFYI(1, "Exclusive Oplock inode %p", inode); - } else if ((oplock & 0xF) == OPLOCK_READ) - pCifsInode->clientCanCacheRead = true; + cifs_set_oplock_level(pCifsInode, oplock); file->private_data = pCifsFile; return pCifsFile; @@ -267,16 +256,18 @@ cifs_new_fileinfo(__u16 fileHandle, struct file *file, /* * Release a reference on the file private data. This may involve closing - * the filehandle out on the server. + * the filehandle out on the server. Must be called without holding + * cifs_file_list_lock. */ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) { + struct inode *inode = cifs_file->dentry->d_inode; struct cifsTconInfo *tcon = tlink_tcon(cifs_file->tlink); - struct cifsInodeInfo *cifsi = CIFS_I(cifs_file->dentry->d_inode); + struct cifsInodeInfo *cifsi = CIFS_I(inode); struct cifsLockInfo *li, *tmp; spin_lock(&cifs_file_list_lock); - if (!atomic_dec_and_test(&cifs_file->count)) { + if (--cifs_file->count > 0) { spin_unlock(&cifs_file_list_lock); return; } @@ -288,8 +279,7 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) if (list_empty(&cifsi->openFileList)) { cFYI(1, "closing last open instance for inode %p", cifs_file->dentry->d_inode); - cifsi->clientCanCacheRead = false; - cifsi->clientCanCacheAll = false; + cifs_set_oplock_level(cifsi, 0); } spin_unlock(&cifs_file_list_lock); @@ -605,11 +595,8 @@ reopen_success: if (can_flush) { rc = filemap_write_and_wait(inode->i_mapping); - if (rc != 0) - CIFS_I(inode)->write_behind_rc = rc; + mapping_set_error(inode->i_mapping, rc); - pCifsInode->clientCanCacheAll = false; - pCifsInode->clientCanCacheRead = false; if (tcon->unix_ext) rc = cifs_get_inode_info_unix(&inode, full_path, inode->i_sb, xid); @@ -623,18 +610,9 @@ reopen_success: invalidate the current end of file on the server we can not go to the server to get the new inod info */ - if ((oplock & 0xF) == OPLOCK_EXCLUSIVE) { - pCifsInode->clientCanCacheAll = true; - pCifsInode->clientCanCacheRead = true; - cFYI(1, "Exclusive Oplock granted on inode %p", - pCifsFile->dentry->d_inode); - } else if ((oplock & 0xF) == OPLOCK_READ) { - pCifsInode->clientCanCacheRead = true; - pCifsInode->clientCanCacheAll = false; - } else { - pCifsInode->clientCanCacheRead = false; - pCifsInode->clientCanCacheAll = false; - } + + cifs_set_oplock_level(pCifsInode, oplock); + cifs_relock_file(pCifsFile); reopen_error_exit: @@ -776,12 +754,6 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *pfLock) cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); tcon = tlink_tcon(((struct cifsFileInfo *)file->private_data)->tlink); - - if (file->private_data == NULL) { - rc = -EBADF; - FreeXid(xid); - return rc; - } netfid = ((struct cifsFileInfo *)file->private_data)->netfid; if ((tcon->ses->capabilities & CAP_UNIX) && @@ -957,6 +929,7 @@ cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset, ssize_t cifs_user_write(struct file *file, const char __user *write_data, size_t write_size, loff_t *poffset) { + struct inode *inode = file->f_path.dentry->d_inode; int rc = 0; unsigned int bytes_written = 0; unsigned int total_written; @@ -964,7 +937,7 @@ ssize_t cifs_user_write(struct file *file, const char __user *write_data, struct cifsTconInfo *pTcon; int xid, long_op; struct cifsFileInfo *open_file; - struct cifsInodeInfo *cifsi = CIFS_I(file->f_path.dentry->d_inode); + struct cifsInodeInfo *cifsi = CIFS_I(inode); cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); @@ -1030,21 +1003,17 @@ ssize_t cifs_user_write(struct file *file, const char __user *write_data, cifs_stats_bytes_written(pTcon, total_written); - /* since the write may have blocked check these pointers again */ - if ((file->f_path.dentry) && (file->f_path.dentry->d_inode)) { - struct inode *inode = file->f_path.dentry->d_inode; /* Do not update local mtime - server will set its actual value on write - * inode->i_ctime = inode->i_mtime = - * current_fs_time(inode->i_sb);*/ - if (total_written > 0) { - spin_lock(&inode->i_lock); - if (*poffset > file->f_path.dentry->d_inode->i_size) - i_size_write(file->f_path.dentry->d_inode, - *poffset); - spin_unlock(&inode->i_lock); - } - mark_inode_dirty_sync(file->f_path.dentry->d_inode); + * inode->i_ctime = inode->i_mtime = + * current_fs_time(inode->i_sb);*/ + if (total_written > 0) { + spin_lock(&inode->i_lock); + if (*poffset > inode->i_size) + i_size_write(inode, *poffset); + spin_unlock(&inode->i_lock); } + mark_inode_dirty_sync(inode); + FreeXid(xid); return total_written; } @@ -1179,7 +1148,7 @@ struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode, bool fsuid_only) { struct cifsFileInfo *open_file; - struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode->vfs_inode.i_sb); + struct cifs_sb_info *cifs_sb; bool any_available = false; int rc; @@ -1193,6 +1162,8 @@ struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode, return NULL; } + cifs_sb = CIFS_SB(cifs_inode->vfs_inode.i_sb); + /* only filter by fsuid on multiuser mounts */ if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER)) fsuid_only = false; @@ -1303,7 +1274,6 @@ static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to) static int cifs_writepages(struct address_space *mapping, struct writeback_control *wbc) { - struct backing_dev_info *bdi = mapping->backing_dev_info; unsigned int bytes_to_write; unsigned int bytes_written; struct cifs_sb_info *cifs_sb; @@ -1326,15 +1296,6 @@ static int cifs_writepages(struct address_space *mapping, int scanned = 0; int xid, long_op; - /* - * BB: Is this meaningful for a non-block-device file system? - * If it is, we should test it again after we do I/O - */ - if (wbc->nonblocking && bdi_write_congested(bdi)) { - wbc->encountered_congestion = 1; - return 0; - } - cifs_sb = CIFS_SB(mapping->host->i_sb); /* @@ -1363,6 +1324,7 @@ static int cifs_writepages(struct address_space *mapping, if (!experimEnabled && tcon->ses->server->secMode & (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED)) { cifsFileInfo_put(open_file); + kfree(iov); return generic_writepages(mapping, wbc); } cifsFileInfo_put(open_file); @@ -1488,12 +1450,7 @@ retry: if (rc || bytes_written < bytes_to_write) { cERROR(1, "Write2 ret %d, wrote %d", rc, bytes_written); - /* BB what if continued retry is - requested via mount flags? */ - if (rc == -ENOSPC) - set_bit(AS_ENOSPC, &mapping->flags); - else - set_bit(AS_EIO, &mapping->flags); + mapping_set_error(mapping, rc); } else { cifs_stats_bytes_written(tcon, bytes_written); } @@ -1638,11 +1595,10 @@ int cifs_fsync(struct file *file, int datasync) rc = filemap_write_and_wait(inode->i_mapping); if (rc == 0) { - rc = CIFS_I(inode)->write_behind_rc; - CIFS_I(inode)->write_behind_rc = 0; + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + tcon = tlink_tcon(smbfile->tlink); - if (!rc && tcon && smbfile && - !(CIFS_SB(inode->i_sb)->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) rc = CIFSSMBFlush(xid, tcon, smbfile->netfid); } @@ -1687,21 +1643,8 @@ int cifs_flush(struct file *file, fl_owner_t id) struct inode *inode = file->f_path.dentry->d_inode; int rc = 0; - /* Rather than do the steps manually: - lock the inode for writing - loop through pages looking for write behind data (dirty pages) - coalesce into contiguous 16K (or smaller) chunks to write to server - send to server (prefer in parallel) - deal with writebehind errors - unlock inode for writing - filemapfdatawrite appears easier for the time being */ - - rc = filemap_fdatawrite(inode->i_mapping); - /* reset wb rc if we were able to write out dirty pages */ - if (!rc) { - rc = CIFS_I(inode)->write_behind_rc; - CIFS_I(inode)->write_behind_rc = 0; - } + if (file->f_mode & FMODE_WRITE) + rc = filemap_write_and_wait(inode->i_mapping); cFYI(1, "Flush inode %p file %p rc %d", inode, file, rc); @@ -2280,7 +2223,7 @@ void cifs_oplock_break(struct work_struct *work) oplock_break); struct inode *inode = cfile->dentry->d_inode; struct cifsInodeInfo *cinode = CIFS_I(inode); - int rc, waitrc = 0; + int rc = 0; if (inode && S_ISREG(inode->i_mode)) { if (cinode->clientCanCacheRead) @@ -2289,13 +2232,10 @@ void cifs_oplock_break(struct work_struct *work) break_lease(inode, O_WRONLY); rc = filemap_fdatawrite(inode->i_mapping); if (cinode->clientCanCacheRead == 0) { - waitrc = filemap_fdatawait(inode->i_mapping); + rc = filemap_fdatawait(inode->i_mapping); + mapping_set_error(inode->i_mapping, rc); invalidate_remote_inode(inode); } - if (!rc) - rc = waitrc; - if (rc) - cinode->write_behind_rc = rc; cFYI(1, "Oplock flush inode %p rc %d", inode, rc); } @@ -2314,7 +2254,7 @@ void cifs_oplock_break(struct work_struct *work) /* * We might have kicked in before is_valid_oplock_break() * finished grabbing reference for us. Make sure it's done by - * waiting for GlobalSMSSeslock. + * waiting for cifs_file_list_lock. */ spin_lock(&cifs_file_list_lock); spin_unlock(&cifs_file_list_lock); @@ -2322,6 +2262,7 @@ void cifs_oplock_break(struct work_struct *work) cifs_oplock_break_put(cfile); } +/* must be called while holding cifs_file_list_lock */ void cifs_oplock_break_get(struct cifsFileInfo *cfile) { cifs_sb_active(cfile->dentry->d_sb); @@ -2330,8 +2271,10 @@ void cifs_oplock_break_get(struct cifsFileInfo *cfile) void cifs_oplock_break_put(struct cifsFileInfo *cfile) { + struct super_block *sb = cfile->dentry->d_sb; + cifsFileInfo_put(cfile); - cifs_sb_deactive(cfile->dentry->d_sb); + cifs_sb_deactive(sb); } const struct address_space_operations cifs_addr_ops = { diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c index a2ad94efcfe6..297a43d0ff7f 100644 --- a/fs/cifs/fscache.c +++ b/fs/cifs/fscache.c @@ -2,7 +2,7 @@ * fs/cifs/fscache.c - CIFS filesystem cache interface * * Copyright (c) 2010 Novell, Inc. - * Author(s): Suresh Jayaraman (sjayaraman@suse.de> + * Author(s): Suresh Jayaraman <sjayaraman@suse.de> * * This library is free software; you can redistribute it and/or modify * it under the terms of the GNU Lesser General Public License as published @@ -67,10 +67,12 @@ static void cifs_fscache_enable_inode_cookie(struct inode *inode) if (cifsi->fscache) return; - cifsi->fscache = fscache_acquire_cookie(tcon->fscache, + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_FSCACHE) { + cifsi->fscache = fscache_acquire_cookie(tcon->fscache, &cifs_fscache_inode_object_def, cifsi); - cFYI(1, "CIFS: got FH cookie (0x%p/0x%p)", tcon->fscache, + cFYI(1, "CIFS: got FH cookie (0x%p/0x%p)", tcon->fscache, cifsi->fscache); + } } void cifs_fscache_release_inode_cookie(struct inode *inode) @@ -101,10 +103,8 @@ void cifs_fscache_set_inode_cookie(struct inode *inode, struct file *filp) { if ((filp->f_flags & O_ACCMODE) != O_RDONLY) cifs_fscache_disable_inode_cookie(inode); - else { + else cifs_fscache_enable_inode_cookie(inode); - cFYI(1, "CIFS: fscache inode cookie set"); - } } void cifs_fscache_reset_inode_cookie(struct inode *inode) diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 94979309698a..28cb6e735943 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -689,8 +689,13 @@ int cifs_get_inode_info(struct inode **pinode, #ifdef CONFIG_CIFS_EXPERIMENTAL /* fill in 0777 bits from ACL */ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) { - cFYI(1, "Getting mode bits from ACL"); - cifs_acl_to_fattr(cifs_sb, &fattr, *pinode, full_path, pfid); + rc = cifs_acl_to_fattr(cifs_sb, &fattr, *pinode, full_path, + pfid); + if (rc) { + cFYI(1, "%s: Getting ACL failed with error: %d", + __func__, rc); + goto cgii_exit; + } } #endif @@ -881,8 +886,10 @@ struct inode *cifs_root_iget(struct super_block *sb, unsigned long ino) rc = cifs_get_inode_info(&inode, full_path, NULL, sb, xid, NULL); - if (!inode) - return ERR_PTR(rc); + if (!inode) { + inode = ERR_PTR(rc); + goto out; + } #ifdef CONFIG_CIFS_FSCACHE /* populate tcon->resource_id */ @@ -898,13 +905,11 @@ struct inode *cifs_root_iget(struct super_block *sb, unsigned long ino) inode->i_uid = cifs_sb->mnt_uid; inode->i_gid = cifs_sb->mnt_gid; } else if (rc) { - kfree(full_path); - _FreeXid(xid); iget_failed(inode); - return ERR_PTR(rc); + inode = ERR_PTR(rc); } - +out: kfree(full_path); /* can not call macro FreeXid here since in a void func * TODO: This is no longer true @@ -1670,7 +1675,9 @@ cifs_inode_needs_reval(struct inode *inode) return false; } -/* check invalid_mapping flag and zap the cache if it's set */ +/* + * Zap the cache. Called when invalid_mapping flag is set. + */ static void cifs_invalidate_mapping(struct inode *inode) { @@ -1682,8 +1689,7 @@ cifs_invalidate_mapping(struct inode *inode) /* write back any cached data */ if (inode->i_mapping && inode->i_mapping->nrpages != 0) { rc = filemap_write_and_wait(inode->i_mapping); - if (rc) - cifs_i->write_behind_rc = rc; + mapping_set_error(inode->i_mapping, rc); } invalidate_remote_inode(inode); cifs_fscache_reset_inode_cookie(inode); @@ -1943,10 +1949,8 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) * the flush returns error? */ rc = filemap_write_and_wait(inode->i_mapping); - if (rc != 0) { - cifsInode->write_behind_rc = rc; - rc = 0; - } + mapping_set_error(inode->i_mapping, rc); + rc = 0; if (attrs->ia_valid & ATTR_SIZE) { rc = cifs_set_file_size(inode, attrs, xid, full_path); @@ -2087,10 +2091,8 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) * the flush returns error? */ rc = filemap_write_and_wait(inode->i_mapping); - if (rc != 0) { - cifsInode->write_behind_rc = rc; - rc = 0; - } + mapping_set_error(inode->i_mapping, rc); + rc = 0; if (attrs->ia_valid & ATTR_SIZE) { rc = cifs_set_file_size(inode, attrs, xid, full_path); @@ -2120,9 +2122,14 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) if (attrs->ia_valid & ATTR_MODE) { rc = 0; #ifdef CONFIG_CIFS_EXPERIMENTAL - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) - rc = mode_to_acl(inode, full_path, mode); - else + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) { + rc = mode_to_cifs_acl(inode, full_path, mode); + if (rc) { + cFYI(1, "%s: Setting ACL failed with error: %d", + __func__, rc); + goto cifs_setattr_exit; + } + } else #endif if (((mode & S_IWUGO) == 0) && (cifsInode->cifsAttrs & ATTR_READONLY) == 0) { @@ -2182,7 +2189,6 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) setattr_copy(inode, attrs); mark_inode_dirty(inode); - return 0; cifs_setattr_exit: kfree(full_path); diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 077bf756f342..0c98672d0122 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -38,10 +38,10 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) struct cifs_sb_info *cifs_sb; #ifdef CONFIG_CIFS_POSIX struct cifsFileInfo *pSMBFile = filep->private_data; - struct cifsTconInfo *tcon = tlink_tcon(pSMBFile->tlink); + struct cifsTconInfo *tcon; __u64 ExtAttrBits = 0; __u64 ExtAttrMask = 0; - __u64 caps = le64_to_cpu(tcon->fsUnixInfo.Capability); + __u64 caps; #endif /* CONFIG_CIFS_POSIX */ xid = GetXid(); @@ -62,9 +62,11 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) break; #ifdef CONFIG_CIFS_POSIX case FS_IOC_GETFLAGS: + if (pSMBFile == NULL) + break; + tcon = tlink_tcon(pSMBFile->tlink); + caps = le64_to_cpu(tcon->fsUnixInfo.Capability); if (CIFS_UNIX_EXTATTR_CAP & caps) { - if (pSMBFile == NULL) - break; rc = CIFSGetExtAttr(xid, tcon, pSMBFile->netfid, &ExtAttrBits, &ExtAttrMask); if (rc == 0) @@ -75,13 +77,15 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) break; case FS_IOC_SETFLAGS: + if (pSMBFile == NULL) + break; + tcon = tlink_tcon(pSMBFile->tlink); + caps = le64_to_cpu(tcon->fsUnixInfo.Capability); if (CIFS_UNIX_EXTATTR_CAP & caps) { if (get_user(ExtAttrBits, (int __user *)arg)) { rc = -EFAULT; break; } - if (pSMBFile == NULL) - break; /* rc= CIFSGetExtAttr(xid,tcon,pSMBFile->netfid, extAttrBits, &ExtAttrMask);*/ } diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 1c681f6a6803..43f10281bc19 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -569,15 +569,14 @@ is_valid_oplock_break(struct smb_hdr *buf, struct TCP_Server_Info *srv) cFYI(1, "file id match, oplock break"); pCifsInode = CIFS_I(netfile->dentry->d_inode); - pCifsInode->clientCanCacheAll = false; - if (pSMB->OplockLevel == 0) - pCifsInode->clientCanCacheRead = false; + cifs_set_oplock_level(pCifsInode, + pSMB->OplockLevel); /* * cifs_oplock_break_put() can't be called * from here. Get reference after queueing * succeeded. cifs_oplock_break() will - * synchronize using GlobalSMSSeslock. + * synchronize using cifs_file_list_lock. */ if (queue_work(system_nrt_wq, &netfile->oplock_break)) @@ -722,3 +721,23 @@ cifs_autodisable_serverino(struct cifs_sb_info *cifs_sb) cifs_sb_master_tcon(cifs_sb)->treeName); } } + +void cifs_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock) +{ + oplock &= 0xF; + + if (oplock == OPLOCK_EXCLUSIVE) { + cinode->clientCanCacheAll = true; + cinode->clientCanCacheRead = true; + cFYI(1, "Exclusive Oplock granted on inode %p", + &cinode->vfs_inode); + } else if (oplock == OPLOCK_READ) { + cinode->clientCanCacheAll = false; + cinode->clientCanCacheRead = true; + cFYI(1, "Level II Oplock granted on inode %p", + &cinode->vfs_inode); + } else { + cinode->clientCanCacheAll = false; + cinode->clientCanCacheRead = false; + } +} diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index ef7bb7b50f58..32d300e8f20e 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -226,26 +226,29 @@ static int initiate_cifs_search(const int xid, struct file *file) char *full_path = NULL; struct cifsFileInfo *cifsFile; struct cifs_sb_info *cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); - struct tcon_link *tlink; + struct tcon_link *tlink = NULL; struct cifsTconInfo *pTcon; - tlink = cifs_sb_tlink(cifs_sb); - if (IS_ERR(tlink)) - return PTR_ERR(tlink); - pTcon = tlink_tcon(tlink); - - if (file->private_data == NULL) - file->private_data = - kzalloc(sizeof(struct cifsFileInfo), GFP_KERNEL); if (file->private_data == NULL) { - rc = -ENOMEM; - goto error_exit; + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + + cifsFile = kzalloc(sizeof(struct cifsFileInfo), GFP_KERNEL); + if (cifsFile == NULL) { + rc = -ENOMEM; + goto error_exit; + } + file->private_data = cifsFile; + cifsFile->tlink = cifs_get_tlink(tlink); + pTcon = tlink_tcon(tlink); + } else { + cifsFile = file->private_data; + pTcon = tlink_tcon(cifsFile->tlink); } - cifsFile = file->private_data; cifsFile->invalidHandle = true; cifsFile->srch_inf.endOfSearch = false; - cifsFile->tlink = cifs_get_tlink(tlink); full_path = build_path_from_dentry(file->f_path.dentry); if (full_path == NULL) { diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 2a11efd96592..7b01d3f6eed6 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -32,9 +32,6 @@ #include <linux/slab.h> #include "cifs_spnego.h" -extern void SMBNTencrypt(unsigned char *passwd, unsigned char *c8, - unsigned char *p24); - /* * Checks if this is the first smb session to be reconnected after * the socket has been reestablished (so we know whether to use vc 0). @@ -402,23 +399,22 @@ static int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, return -EINVAL; } - memcpy(ses->cryptKey, pblob->Challenge, CIFS_CRYPTO_KEY_SIZE); + memcpy(ses->ntlmssp->cryptkey, pblob->Challenge, CIFS_CRYPTO_KEY_SIZE); /* BB we could decode pblob->NegotiateFlags; some may be useful */ /* In particular we can examine sign flags */ /* BB spec says that if AvId field of MsvAvTimestamp is populated then we must set the MIC field of the AUTHENTICATE_MESSAGE */ - + ses->ntlmssp->server_flags = le32_to_cpu(pblob->NegotiateFlags); tioffset = cpu_to_le16(pblob->TargetInfoArray.BufferOffset); tilen = cpu_to_le16(pblob->TargetInfoArray.Length); - ses->tilen = tilen; - if (ses->tilen) { - ses->tiblob = kmalloc(tilen, GFP_KERNEL); - if (!ses->tiblob) { + if (tilen) { + ses->auth_key.response = kmalloc(tilen, GFP_KERNEL); + if (!ses->auth_key.response) { cERROR(1, "Challenge target info allocation failure"); - ses->tilen = 0; return -ENOMEM; } - memcpy(ses->tiblob, bcc_ptr + tioffset, ses->tilen); + memcpy(ses->auth_key.response, bcc_ptr + tioffset, tilen); + ses->auth_key.len = tilen; } return 0; @@ -443,10 +439,12 @@ static void build_ntlmssp_negotiate_blob(unsigned char *pbuffer, NTLMSSP_NEGOTIATE_128 | NTLMSSP_NEGOTIATE_UNICODE | NTLMSSP_NEGOTIATE_NTLM; if (ses->server->secMode & - (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED)) + (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED)) { flags |= NTLMSSP_NEGOTIATE_SIGN; - if (ses->server->secMode & SECMODE_SIGN_REQUIRED) - flags |= NTLMSSP_NEGOTIATE_ALWAYS_SIGN; + if (!ses->server->session_estab) + flags |= NTLMSSP_NEGOTIATE_KEY_XCH | + NTLMSSP_NEGOTIATE_EXTENDED_SEC; + } sec_blob->NegotiateFlags |= cpu_to_le32(flags); @@ -469,11 +467,9 @@ static int build_ntlmssp_auth_blob(unsigned char *pbuffer, const struct nls_table *nls_cp) { int rc; - unsigned int size; AUTHENTICATE_MESSAGE *sec_blob = (AUTHENTICATE_MESSAGE *)pbuffer; __u32 flags; unsigned char *tmp; - struct ntlmv2_resp ntlmv2_response = {}; memcpy(sec_blob->Signature, NTLMSSP_SIGNATURE, 8); sec_blob->MessageType = NtLmAuthenticate; @@ -497,25 +493,19 @@ static int build_ntlmssp_auth_blob(unsigned char *pbuffer, sec_blob->LmChallengeResponse.MaximumLength = 0; sec_blob->NtChallengeResponse.BufferOffset = cpu_to_le32(tmp - pbuffer); - rc = setup_ntlmv2_rsp(ses, (char *)&ntlmv2_response, nls_cp); + rc = setup_ntlmv2_rsp(ses, nls_cp); if (rc) { cERROR(1, "Error %d during NTLMSSP authentication", rc); goto setup_ntlmv2_ret; } - size = sizeof(struct ntlmv2_resp); - memcpy(tmp, (char *)&ntlmv2_response, size); - tmp += size; - if (ses->tilen > 0) { - memcpy(tmp, ses->tiblob, ses->tilen); - tmp += ses->tilen; - } + memcpy(tmp, ses->auth_key.response + CIFS_SESS_KEY_SIZE, + ses->auth_key.len - CIFS_SESS_KEY_SIZE); + tmp += ses->auth_key.len - CIFS_SESS_KEY_SIZE; - sec_blob->NtChallengeResponse.Length = cpu_to_le16(size + ses->tilen); + sec_blob->NtChallengeResponse.Length = + cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE); sec_blob->NtChallengeResponse.MaximumLength = - cpu_to_le16(size + ses->tilen); - kfree(ses->tiblob); - ses->tiblob = NULL; - ses->tilen = 0; + cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE); if (ses->domainName == NULL) { sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - pbuffer); @@ -554,9 +544,19 @@ static int build_ntlmssp_auth_blob(unsigned char *pbuffer, sec_blob->WorkstationName.MaximumLength = 0; tmp += 2; - sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - pbuffer); - sec_blob->SessionKey.Length = 0; - sec_blob->SessionKey.MaximumLength = 0; + if ((ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_KEY_XCH) && + !calc_seckey(ses)) { + memcpy(tmp, ses->ntlmssp->ciphertext, CIFS_CPHTXT_SIZE); + sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - pbuffer); + sec_blob->SessionKey.Length = cpu_to_le16(CIFS_CPHTXT_SIZE); + sec_blob->SessionKey.MaximumLength = + cpu_to_le16(CIFS_CPHTXT_SIZE); + tmp += CIFS_CPHTXT_SIZE; + } else { + sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - pbuffer); + sec_blob->SessionKey.Length = 0; + sec_blob->SessionKey.MaximumLength = 0; + } setup_ntlmv2_ret: *buflen = tmp - pbuffer; @@ -600,8 +600,16 @@ CIFS_SessSetup(unsigned int xid, struct cifsSesInfo *ses, return -EINVAL; type = ses->server->secType; - cFYI(1, "sess setup type %d", type); + if (type == RawNTLMSSP) { + /* if memory allocation is successful, caller of this function + * frees it. + */ + ses->ntlmssp = kmalloc(sizeof(struct ntlmssp_auth), GFP_KERNEL); + if (!ses->ntlmssp) + return -ENOMEM; + } + ssetup_ntlmssp_authenticate: if (phase == NtLmChallenge) phase = NtLmAuthenticate; /* if ntlmssp, now final phase */ @@ -666,10 +674,14 @@ ssetup_ntlmssp_authenticate: /* no capabilities flags in old lanman negotiation */ pSMB->old_req.PasswordLength = cpu_to_le16(CIFS_SESS_KEY_SIZE); - /* BB calculate hash with password */ - /* and copy into bcc */ - calc_lanman_hash(ses->password, ses->cryptKey, + /* Calculate hash with password and copy into bcc_ptr. + * Encryption Key (stored as in cryptkey) gets used if the + * security mode bit in Negottiate Protocol response states + * to use challenge/response method (i.e. Password bit is 1). + */ + + calc_lanman_hash(ses->password, ses->server->cryptkey, ses->server->secMode & SECMODE_PW_ENCRYPT ? true : false, lnm_session_key); @@ -687,24 +699,27 @@ ssetup_ntlmssp_authenticate: ascii_ssetup_strings(&bcc_ptr, ses, nls_cp); #endif } else if (type == NTLM) { - char ntlm_session_key[CIFS_SESS_KEY_SIZE]; - pSMB->req_no_secext.Capabilities = cpu_to_le32(capabilities); pSMB->req_no_secext.CaseInsensitivePasswordLength = - cpu_to_le16(CIFS_SESS_KEY_SIZE); + cpu_to_le16(CIFS_AUTH_RESP_SIZE); pSMB->req_no_secext.CaseSensitivePasswordLength = - cpu_to_le16(CIFS_SESS_KEY_SIZE); + cpu_to_le16(CIFS_AUTH_RESP_SIZE); + + /* calculate ntlm response and session key */ + rc = setup_ntlm_response(ses); + if (rc) { + cERROR(1, "Error %d during NTLM authentication", rc); + goto ssetup_exit; + } - /* calculate session key */ - SMBNTencrypt(ses->password, ses->cryptKey, ntlm_session_key); + /* copy ntlm response */ + memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE, + CIFS_AUTH_RESP_SIZE); + bcc_ptr += CIFS_AUTH_RESP_SIZE; + memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE, + CIFS_AUTH_RESP_SIZE); + bcc_ptr += CIFS_AUTH_RESP_SIZE; - cifs_calculate_session_key(&ses->auth_key, - ntlm_session_key, ses->password); - /* copy session key */ - memcpy(bcc_ptr, (char *)ntlm_session_key, CIFS_SESS_KEY_SIZE); - bcc_ptr += CIFS_SESS_KEY_SIZE; - memcpy(bcc_ptr, (char *)ntlm_session_key, CIFS_SESS_KEY_SIZE); - bcc_ptr += CIFS_SESS_KEY_SIZE; if (ses->capabilities & CAP_UNICODE) { /* unicode strings must be word aligned */ if (iov[0].iov_len % 2) { @@ -715,47 +730,26 @@ ssetup_ntlmssp_authenticate: } else ascii_ssetup_strings(&bcc_ptr, ses, nls_cp); } else if (type == NTLMv2) { - char *v2_sess_key = - kmalloc(sizeof(struct ntlmv2_resp), GFP_KERNEL); - - /* BB FIXME change all users of v2_sess_key to - struct ntlmv2_resp */ - - if (v2_sess_key == NULL) { - rc = -ENOMEM; - goto ssetup_exit; - } - pSMB->req_no_secext.Capabilities = cpu_to_le32(capabilities); /* LM2 password would be here if we supported it */ pSMB->req_no_secext.CaseInsensitivePasswordLength = 0; - /* cpu_to_le16(LM2_SESS_KEY_SIZE); */ - /* calculate session key */ - rc = setup_ntlmv2_rsp(ses, v2_sess_key, nls_cp); + /* calculate nlmv2 response and session key */ + rc = setup_ntlmv2_rsp(ses, nls_cp); if (rc) { cERROR(1, "Error %d during NTLMv2 authentication", rc); - kfree(v2_sess_key); goto ssetup_exit; } - memcpy(bcc_ptr, (char *)v2_sess_key, - sizeof(struct ntlmv2_resp)); - bcc_ptr += sizeof(struct ntlmv2_resp); - kfree(v2_sess_key); + memcpy(bcc_ptr, ses->auth_key.response + CIFS_SESS_KEY_SIZE, + ses->auth_key.len - CIFS_SESS_KEY_SIZE); + bcc_ptr += ses->auth_key.len - CIFS_SESS_KEY_SIZE; + /* set case sensitive password length after tilen may get * assigned, tilen is 0 otherwise. */ pSMB->req_no_secext.CaseSensitivePasswordLength = - cpu_to_le16(sizeof(struct ntlmv2_resp) + ses->tilen); - if (ses->tilen > 0) { - memcpy(bcc_ptr, ses->tiblob, ses->tilen); - bcc_ptr += ses->tilen; - /* we never did allocate ses->domainName to free */ - kfree(ses->tiblob); - ses->tiblob = NULL; - ses->tilen = 0; - } + cpu_to_le16(ses->auth_key.len - CIFS_SESS_KEY_SIZE); if (ses->capabilities & CAP_UNICODE) { if (iov[0].iov_len % 2) { @@ -768,6 +762,7 @@ ssetup_ntlmssp_authenticate: } else if (type == Kerberos) { #ifdef CONFIG_CIFS_UPCALL struct cifs_spnego_msg *msg; + spnego_key = cifs_get_spnego_key(ses); if (IS_ERR(spnego_key)) { rc = PTR_ERR(spnego_key); @@ -785,16 +780,17 @@ ssetup_ntlmssp_authenticate: rc = -EKEYREJECTED; goto ssetup_exit; } - /* bail out if key is too long */ - if (msg->sesskey_len > - sizeof(ses->auth_key.data.krb5)) { - cERROR(1, "Kerberos signing key too long (%u bytes)", - msg->sesskey_len); - rc = -EOVERFLOW; + + ses->auth_key.response = kmalloc(msg->sesskey_len, GFP_KERNEL); + if (!ses->auth_key.response) { + cERROR(1, "Kerberos can't allocate (%u bytes) memory", + msg->sesskey_len); + rc = -ENOMEM; goto ssetup_exit; } + memcpy(ses->auth_key.response, msg->data, msg->sesskey_len); ses->auth_key.len = msg->sesskey_len; - memcpy(ses->auth_key.data.krb5, msg->data, msg->sesskey_len); + pSMB->req.hdr.Flags2 |= SMBFLG2_EXT_SEC; capabilities |= CAP_EXTENDED_SECURITY; pSMB->req.Capabilities = cpu_to_le32(capabilities); @@ -897,8 +893,6 @@ ssetup_ntlmssp_authenticate: CIFS_STD_OP /* not long */ | CIFS_LOG_ERROR); /* SMB request buf freed in SendReceive2 */ - cFYI(1, "ssetup rc from sendrecv2 is %d", rc); - pSMB = (SESSION_SETUP_ANDX *)iov[0].iov_base; smb_buf = (struct smb_hdr *)iov[0].iov_base; diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index a66c91eb6eb4..e0588cdf4cc5 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -543,7 +543,7 @@ SendReceive2(const unsigned int xid, struct cifsSesInfo *ses, (ses->server->secMode & (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))) { rc = cifs_verify_signature(midQ->resp_buf, - &ses->server->session_key, + ses->server, midQ->sequence_number+1); if (rc) { cERROR(1, "Unexpected SMB signature"); @@ -731,7 +731,7 @@ SendReceive(const unsigned int xid, struct cifsSesInfo *ses, (ses->server->secMode & (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))) { rc = cifs_verify_signature(out_buf, - &ses->server->session_key, + ses->server, midQ->sequence_number+1); if (rc) { cERROR(1, "Unexpected SMB signature"); @@ -981,7 +981,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifsTconInfo *tcon, (ses->server->secMode & (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))) { rc = cifs_verify_signature(out_buf, - &ses->server->session_key, + ses->server, midQ->sequence_number+1); if (rc) { cERROR(1, "Unexpected SMB signature"); diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index a264b744bb41..eae2a1491608 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -30,10 +30,11 @@ #define MAX_EA_VALUE_SIZE 65535 #define CIFS_XATTR_DOS_ATTRIB "user.DosAttrib" +#define CIFS_XATTR_CIFS_ACL "system.cifs_acl" #define CIFS_XATTR_USER_PREFIX "user." #define CIFS_XATTR_SYSTEM_PREFIX "system." #define CIFS_XATTR_OS2_PREFIX "os2." -#define CIFS_XATTR_SECURITY_PREFIX ".security" +#define CIFS_XATTR_SECURITY_PREFIX "security." #define CIFS_XATTR_TRUSTED_PREFIX "trusted." #define XATTR_TRUSTED_PREFIX_LEN 8 #define XATTR_SECURITY_PREFIX_LEN 9 @@ -277,29 +278,8 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name, cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); -#ifdef CONFIG_CIFS_EXPERIMENTAL - else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) { - __u16 fid; - int oplock = 0; - struct cifs_ntsd *pacl = NULL; - __u32 buflen = 0; - if (experimEnabled) - rc = CIFSSMBOpen(xid, pTcon, full_path, - FILE_OPEN, GENERIC_READ, 0, &fid, - &oplock, NULL, cifs_sb->local_nls, - cifs_sb->mnt_cifs_flags & - CIFS_MOUNT_MAP_SPECIAL_CHR); - /* else rc is EOPNOTSUPP from above */ - - if (rc == 0) { - rc = CIFSSMBGetCIFSACL(xid, pTcon, fid, &pacl, - &buflen); - CIFSSMBClose(xid, pTcon, fid); - } - } -#endif /* EXPERIMENTAL */ #else - cFYI(1, "query POSIX ACL not supported yet"); + cFYI(1, "Query POSIX ACL not supported yet"); #endif /* CONFIG_CIFS_POSIX */ } else if (strncmp(ea_name, POSIX_ACL_XATTR_DEFAULT, strlen(POSIX_ACL_XATTR_DEFAULT)) == 0) { @@ -311,8 +291,33 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); #else - cFYI(1, "query POSIX default ACL not supported yet"); -#endif + cFYI(1, "Query POSIX default ACL not supported yet"); +#endif /* CONFIG_CIFS_POSIX */ + } else if (strncmp(ea_name, CIFS_XATTR_CIFS_ACL, + strlen(CIFS_XATTR_CIFS_ACL)) == 0) { +#ifdef CONFIG_CIFS_ACL + u32 acllen; + struct cifs_ntsd *pacl; + + pacl = get_cifs_acl(cifs_sb, direntry->d_inode, + full_path, &acllen); + if (IS_ERR(pacl)) { + rc = PTR_ERR(pacl); + cERROR(1, "%s: error %zd getting sec desc", + __func__, rc); + } else { + if (ea_value) { + if (acllen > buf_size) + acllen = -ERANGE; + else + memcpy(ea_value, pacl, acllen); + } + rc = acllen; + kfree(pacl); + } +#else + cFYI(1, "Query CIFS ACL not supported yet"); +#endif /* CONFIG_CIFS_ACL */ } else if (strncmp(ea_name, CIFS_XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) == 0) { cFYI(1, "Trusted xattr namespace not supported yet"); diff --git a/fs/coda/dir.c b/fs/coda/dir.c index 96fbeab77f2f..5d8b35539601 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -276,7 +276,7 @@ static int coda_link(struct dentry *source_de, struct inode *dir_inode, } coda_dir_update_mtime(dir_inode); - atomic_inc(&inode->i_count); + ihold(inode); d_instantiate(de, inode); inc_nlink(inode); return 0; diff --git a/fs/coda/inode.c b/fs/coda/inode.c index 7993b96ca348..5ea57c8c7f97 100644 --- a/fs/coda/inode.c +++ b/fs/coda/inode.c @@ -306,16 +306,16 @@ static int coda_statfs(struct dentry *dentry, struct kstatfs *buf) /* init_coda: used by filesystems.c to register coda */ -static int coda_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *coda_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_nodev(fs_type, flags, data, coda_fill_super, mnt); + return mount_nodev(fs_type, flags, data, coda_fill_super); } struct file_system_type coda_fs_type = { .owner = THIS_MODULE, .name = "coda", - .get_sb = coda_get_sb, + .mount = coda_mount, .kill_sb = kill_anon_super, .fs_flags = FS_BINARY_MOUNTDATA, }; diff --git a/fs/compat.c b/fs/compat.c index 0644a154672b..eb1740ac8c0a 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -29,8 +29,6 @@ #include <linux/vfs.h> #include <linux/ioctl.h> #include <linux/init.h> -#include <linux/smb.h> -#include <linux/smb_mount.h> #include <linux/ncp_mount.h> #include <linux/nfs4_mount.h> #include <linux/syscalls.h> @@ -51,6 +49,7 @@ #include <linux/eventpoll.h> #include <linux/fs_struct.h> #include <linux/slab.h> +#include <linux/pagemap.h> #include <asm/uaccess.h> #include <asm/mmu_context.h> @@ -608,14 +607,14 @@ ssize_t compat_rw_copy_check_uvector(int type, /* * Single unix specification: * We should -EINVAL if an element length is not >= 0 and fitting an - * ssize_t. The total length is fitting an ssize_t + * ssize_t. * - * Be careful here because iov_len is a size_t not an ssize_t + * In Linux, the total length is limited to MAX_RW_COUNT, there is + * no overflow possibility. */ tot_len = 0; ret = -EINVAL; for (seg = 0; seg < nr_segs; seg++) { - compat_ssize_t tmp = tot_len; compat_uptr_t buf; compat_ssize_t len; @@ -626,13 +625,13 @@ ssize_t compat_rw_copy_check_uvector(int type, } if (len < 0) /* size_t not fitting in compat_ssize_t .. */ goto out; - tot_len += len; - if (tot_len < tmp) /* maths overflow on the compat_ssize_t */ - goto out; if (!access_ok(vrfy_dir(type), compat_ptr(buf), len)) { ret = -EFAULT; goto out; } + if (len > MAX_RW_COUNT - tot_len) + len = MAX_RW_COUNT - tot_len; + tot_len += len; iov->iov_base = compat_ptr(buf); iov->iov_len = (compat_size_t) len; uvector++; @@ -745,30 +744,6 @@ static void *do_ncp_super_data_conv(void *raw_data) return raw_data; } -struct compat_smb_mount_data { - compat_int_t version; - __compat_uid_t mounted_uid; - __compat_uid_t uid; - __compat_gid_t gid; - compat_mode_t file_mode; - compat_mode_t dir_mode; -}; - -static void *do_smb_super_data_conv(void *raw_data) -{ - struct smb_mount_data *s = raw_data; - struct compat_smb_mount_data *c_s = raw_data; - - if (c_s->version != SMB_MOUNT_OLDVERSION) - goto out; - s->dir_mode = c_s->dir_mode; - s->file_mode = c_s->file_mode; - s->gid = c_s->gid; - s->uid = c_s->uid; - s->mounted_uid = c_s->mounted_uid; - out: - return raw_data; -} struct compat_nfs_string { compat_uint_t len; @@ -835,7 +810,6 @@ static int do_nfs4_super_data_conv(void *raw_data) return 0; } -#define SMBFS_NAME "smbfs" #define NCPFS_NAME "ncpfs" #define NFS4_NAME "nfs4" @@ -870,9 +844,7 @@ asmlinkage long compat_sys_mount(const char __user * dev_name, retval = -EINVAL; if (kernel_type && data_page) { - if (!strcmp(kernel_type, SMBFS_NAME)) { - do_smb_super_data_conv((void *)data_page); - } else if (!strcmp(kernel_type, NCPFS_NAME)) { + if (!strcmp(kernel_type, NCPFS_NAME)) { do_ncp_super_data_conv((void *)data_page); } else if (!strcmp(kernel_type, NFS4_NAME)) { if (do_nfs4_super_data_conv((void *) data_page)) @@ -1378,6 +1350,10 @@ static int compat_count(compat_uptr_t __user *argv, int max) argv++; if (i++ >= max) return -E2BIG; + + if (fatal_signal_pending(current)) + return -ERESTARTNOHAND; + cond_resched(); } } return i; @@ -1419,6 +1395,12 @@ static int compat_copy_strings(int argc, compat_uptr_t __user *argv, while (len > 0) { int offset, bytes_to_copy; + if (fatal_signal_pending(current)) { + ret = -ERESTARTNOHAND; + goto out; + } + cond_resched(); + offset = pos % PAGE_SIZE; if (offset == 0) offset = PAGE_SIZE; @@ -1435,18 +1417,8 @@ static int compat_copy_strings(int argc, compat_uptr_t __user *argv, if (!kmapped_page || kpos != (pos & PAGE_MASK)) { struct page *page; -#ifdef CONFIG_STACK_GROWSUP - ret = expand_stack_downwards(bprm->vma, pos); - if (ret < 0) { - /* We've exceed the stack rlimit. */ - ret = -E2BIG; - goto out; - } -#endif - ret = get_user_pages(current, bprm->mm, pos, - 1, 1, 1, &page, NULL); - if (ret <= 0) { - /* We've exceed the stack rlimit. */ + page = get_arg_page(bprm, pos, 1); + if (!page) { ret = -E2BIG; goto out; } @@ -1567,8 +1539,10 @@ int compat_do_execve(char * filename, return retval; out: - if (bprm->mm) + if (bprm->mm) { + acct_arg_size(bprm, 0); mmput(bprm->mm); + } out_file: if (bprm->file) { @@ -1963,7 +1937,7 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, } #endif /* HAVE_SET_RESTORE_SIGMASK */ -#if defined(CONFIG_NFSD) || defined(CONFIG_NFSD_MODULE) +#if (defined(CONFIG_NFSD) || defined(CONFIG_NFSD_MODULE)) && !defined(CONFIG_NFSD_DEPRECATED) /* Stuff for NFS server syscalls... */ struct compat_nfsctl_svc { u16 svc32_port; diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index d0ad09d57789..a60579b007b0 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -19,7 +19,6 @@ #include <linux/compiler.h> #include <linux/sched.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/ioctl.h> #include <linux/if.h> #include <linux/if_bridge.h> @@ -46,7 +45,6 @@ #include <linux/videodev.h> #include <linux/netdevice.h> #include <linux/raw.h> -#include <linux/smb_fs.h> #include <linux/blkdev.h> #include <linux/elevator.h> #include <linux/rtc.h> @@ -558,25 +556,6 @@ static int mt_ioctl_trans(unsigned int fd, unsigned int cmd, void __user *argp) #endif /* CONFIG_BLOCK */ -static int do_smb_getmountuid(unsigned int fd, unsigned int cmd, - compat_uid_t __user *argp) -{ - mm_segment_t old_fs = get_fs(); - __kernel_uid_t kuid; - int err; - - cmd = SMB_IOC_GETMOUNTUID; - - set_fs(KERNEL_DS); - err = sys_ioctl(fd, cmd, (unsigned long)&kuid); - set_fs(old_fs); - - if (err >= 0) - err = put_user(kuid, argp); - - return err; -} - /* Bluetooth ioctls */ #define HCIUARTSETPROTO _IOW('U', 200, int) #define HCIUARTGETPROTO _IOR('U', 201, int) @@ -1199,8 +1178,9 @@ COMPATIBLE_IOCTL(SOUND_MIXER_PRIVATE5) COMPATIBLE_IOCTL(SOUND_MIXER_GETLEVELS) COMPATIBLE_IOCTL(SOUND_MIXER_SETLEVELS) COMPATIBLE_IOCTL(OSS_GETVERSION) -/* SMB ioctls which do not need any translations */ -COMPATIBLE_IOCTL(SMB_IOC_NEWCONN) +/* Raw devices */ +COMPATIBLE_IOCTL(RAW_SETBIND) +COMPATIBLE_IOCTL(RAW_GETBIND) /* Watchdog */ COMPATIBLE_IOCTL(WDIOC_GETSUPPORT) COMPATIBLE_IOCTL(WDIOC_GETSTATUS) @@ -1458,10 +1438,6 @@ static long do_ioctl_trans(int fd, unsigned int cmd, case MTIOCPOS32: return mt_ioctl_trans(fd, cmd, argp); #endif - /* One SMB ioctl needs translations. */ -#define SMB_IOC_GETMOUNTUID_32 _IOR('u', 1, compat_uid_t) - case SMB_IOC_GETMOUNTUID_32: - return do_smb_getmountuid(fd, cmd, argp); /* Serial */ case TIOCGSERIAL: case TIOCSSERIAL: diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index cf78d44a8d6a..253476d78ed8 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -135,6 +135,7 @@ struct inode * configfs_new_inode(mode_t mode, struct configfs_dirent * sd) { struct inode * inode = new_inode(configfs_sb); if (inode) { + inode->i_ino = get_next_ino(); inode->i_mapping->a_ops = &configfs_aops; inode->i_mapping->backing_dev_info = &configfs_backing_dev_info; inode->i_op = &configfs_inode_operations; diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c index 8c8d64230c2d..7d3607febe1c 100644 --- a/fs/configfs/mount.c +++ b/fs/configfs/mount.c @@ -104,16 +104,16 @@ static int configfs_fill_super(struct super_block *sb, void *data, int silent) return 0; } -static int configfs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *configfs_do_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_single(fs_type, flags, data, configfs_fill_super, mnt); + return mount_single(fs_type, flags, data, configfs_fill_super); } static struct file_system_type configfs_fs_type = { .owner = THIS_MODULE, .name = "configfs", - .get_sb = configfs_get_sb, + .mount = configfs_do_mount, .kill_sb = kill_litter_super, }; diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 1e7a33028d33..32fd5fe9ca0e 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -533,17 +533,16 @@ static const struct super_operations cramfs_ops = { .statfs = cramfs_statfs, }; -static int cramfs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *cramfs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, cramfs_fill_super, - mnt); + return mount_bdev(fs_type, flags, dev_name, data, cramfs_fill_super); } static struct file_system_type cramfs_fs_type = { .owner = THIS_MODULE, .name = "cramfs", - .get_sb = cramfs_get_sb, + .mount = cramfs_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/dcache.c b/fs/dcache.c index 83293be48149..23702a9d4e6d 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -67,33 +67,43 @@ struct dentry_stat_t dentry_stat = { .age_limit = 45, }; -static void __d_free(struct dentry *dentry) +static struct percpu_counter nr_dentry __cacheline_aligned_in_smp; +static struct percpu_counter nr_dentry_unused __cacheline_aligned_in_smp; + +#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) +int proc_nr_dentry(ctl_table *table, int write, void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + dentry_stat.nr_dentry = percpu_counter_sum_positive(&nr_dentry); + dentry_stat.nr_unused = percpu_counter_sum_positive(&nr_dentry_unused); + return proc_dointvec(table, write, buffer, lenp, ppos); +} +#endif + +static void __d_free(struct rcu_head *head) { + struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); + WARN_ON(!list_empty(&dentry->d_alias)); if (dname_external(dentry)) kfree(dentry->d_name.name); kmem_cache_free(dentry_cache, dentry); } -static void d_callback(struct rcu_head *head) -{ - struct dentry * dentry = container_of(head, struct dentry, d_u.d_rcu); - __d_free(dentry); -} - /* - * no dcache_lock, please. The caller must decrement dentry_stat.nr_dentry - * inside dcache_lock. + * no dcache_lock, please. */ static void d_free(struct dentry *dentry) { + percpu_counter_dec(&nr_dentry); if (dentry->d_op && dentry->d_op->d_release) dentry->d_op->d_release(dentry); + /* if dentry was never inserted into hash, immediate free is OK */ if (hlist_unhashed(&dentry->d_hash)) - __d_free(dentry); + __d_free(&dentry->d_u.d_rcu); else - call_rcu(&dentry->d_u.d_rcu, d_callback); + call_rcu(&dentry->d_u.d_rcu, __d_free); } /* @@ -123,37 +133,34 @@ static void dentry_iput(struct dentry * dentry) } /* - * dentry_lru_(add|add_tail|del|del_init) must be called with dcache_lock held. + * dentry_lru_(add|del|move_tail) must be called with dcache_lock held. */ static void dentry_lru_add(struct dentry *dentry) { - list_add(&dentry->d_lru, &dentry->d_sb->s_dentry_lru); - dentry->d_sb->s_nr_dentry_unused++; - dentry_stat.nr_unused++; -} - -static void dentry_lru_add_tail(struct dentry *dentry) -{ - list_add_tail(&dentry->d_lru, &dentry->d_sb->s_dentry_lru); - dentry->d_sb->s_nr_dentry_unused++; - dentry_stat.nr_unused++; + if (list_empty(&dentry->d_lru)) { + list_add(&dentry->d_lru, &dentry->d_sb->s_dentry_lru); + dentry->d_sb->s_nr_dentry_unused++; + percpu_counter_inc(&nr_dentry_unused); + } } static void dentry_lru_del(struct dentry *dentry) { if (!list_empty(&dentry->d_lru)) { - list_del(&dentry->d_lru); + list_del_init(&dentry->d_lru); dentry->d_sb->s_nr_dentry_unused--; - dentry_stat.nr_unused--; + percpu_counter_dec(&nr_dentry_unused); } } -static void dentry_lru_del_init(struct dentry *dentry) +static void dentry_lru_move_tail(struct dentry *dentry) { - if (likely(!list_empty(&dentry->d_lru))) { - list_del_init(&dentry->d_lru); - dentry->d_sb->s_nr_dentry_unused--; - dentry_stat.nr_unused--; + if (list_empty(&dentry->d_lru)) { + list_add_tail(&dentry->d_lru, &dentry->d_sb->s_dentry_lru); + dentry->d_sb->s_nr_dentry_unused++; + percpu_counter_inc(&nr_dentry_unused); + } else { + list_move_tail(&dentry->d_lru, &dentry->d_sb->s_dentry_lru); } } @@ -172,7 +179,6 @@ static struct dentry *d_kill(struct dentry *dentry) struct dentry *parent; list_del(&dentry->d_u.d_child); - dentry_stat.nr_dentry--; /* For d_free, below */ /*drops the locks, at that point nobody can reach this dentry */ dentry_iput(dentry); if (IS_ROOT(dentry)) @@ -237,13 +243,15 @@ repeat: if (dentry->d_op->d_delete(dentry)) goto unhash_it; } + /* Unreachable? Get rid of it */ if (d_unhashed(dentry)) goto kill_it; - if (list_empty(&dentry->d_lru)) { - dentry->d_flags |= DCACHE_REFERENCED; - dentry_lru_add(dentry); - } + + /* Otherwise leave it cached and ensure it's on the LRU */ + dentry->d_flags |= DCACHE_REFERENCED; + dentry_lru_add(dentry); + spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); return; @@ -318,11 +326,10 @@ int d_invalidate(struct dentry * dentry) EXPORT_SYMBOL(d_invalidate); /* This should be called _only_ with dcache_lock held */ - static inline struct dentry * __dget_locked(struct dentry *dentry) { atomic_inc(&dentry->d_count); - dentry_lru_del_init(dentry); + dentry_lru_del(dentry); return dentry; } @@ -441,73 +448,27 @@ static void prune_one_dentry(struct dentry * dentry) if (dentry->d_op && dentry->d_op->d_delete) dentry->d_op->d_delete(dentry); - dentry_lru_del_init(dentry); + dentry_lru_del(dentry); __d_drop(dentry); dentry = d_kill(dentry); spin_lock(&dcache_lock); } } -/* - * Shrink the dentry LRU on a given superblock. - * @sb : superblock to shrink dentry LRU. - * @count: If count is NULL, we prune all dentries on superblock. - * @flags: If flags is non-zero, we need to do special processing based on - * which flags are set. This means we don't need to maintain multiple - * similar copies of this loop. - */ -static void __shrink_dcache_sb(struct super_block *sb, int *count, int flags) +static void shrink_dentry_list(struct list_head *list) { - LIST_HEAD(referenced); - LIST_HEAD(tmp); struct dentry *dentry; - int cnt = 0; - BUG_ON(!sb); - BUG_ON((flags & DCACHE_REFERENCED) && count == NULL); - spin_lock(&dcache_lock); - if (count != NULL) - /* called from prune_dcache() and shrink_dcache_parent() */ - cnt = *count; -restart: - if (count == NULL) - list_splice_init(&sb->s_dentry_lru, &tmp); - else { - while (!list_empty(&sb->s_dentry_lru)) { - dentry = list_entry(sb->s_dentry_lru.prev, - struct dentry, d_lru); - BUG_ON(dentry->d_sb != sb); + while (!list_empty(list)) { + dentry = list_entry(list->prev, struct dentry, d_lru); + dentry_lru_del(dentry); - spin_lock(&dentry->d_lock); - /* - * If we are honouring the DCACHE_REFERENCED flag and - * the dentry has this flag set, don't free it. Clear - * the flag and put it back on the LRU. - */ - if ((flags & DCACHE_REFERENCED) - && (dentry->d_flags & DCACHE_REFERENCED)) { - dentry->d_flags &= ~DCACHE_REFERENCED; - list_move(&dentry->d_lru, &referenced); - spin_unlock(&dentry->d_lock); - } else { - list_move_tail(&dentry->d_lru, &tmp); - spin_unlock(&dentry->d_lock); - cnt--; - if (!cnt) - break; - } - cond_resched_lock(&dcache_lock); - } - } - while (!list_empty(&tmp)) { - dentry = list_entry(tmp.prev, struct dentry, d_lru); - dentry_lru_del_init(dentry); - spin_lock(&dentry->d_lock); /* * We found an inuse dentry which was not removed from * the LRU because of laziness during lookup. Do not free * it - just keep it off the LRU list. */ + spin_lock(&dentry->d_lock); if (atomic_read(&dentry->d_count)) { spin_unlock(&dentry->d_lock); continue; @@ -516,13 +477,60 @@ restart: /* dentry->d_lock was dropped in prune_one_dentry() */ cond_resched_lock(&dcache_lock); } - if (count == NULL && !list_empty(&sb->s_dentry_lru)) - goto restart; - if (count != NULL) - *count = cnt; +} + +/** + * __shrink_dcache_sb - shrink the dentry LRU on a given superblock + * @sb: superblock to shrink dentry LRU. + * @count: number of entries to prune + * @flags: flags to control the dentry processing + * + * If flags contains DCACHE_REFERENCED reference dentries will not be pruned. + */ +static void __shrink_dcache_sb(struct super_block *sb, int *count, int flags) +{ + /* called from prune_dcache() and shrink_dcache_parent() */ + struct dentry *dentry; + LIST_HEAD(referenced); + LIST_HEAD(tmp); + int cnt = *count; + + spin_lock(&dcache_lock); + while (!list_empty(&sb->s_dentry_lru)) { + dentry = list_entry(sb->s_dentry_lru.prev, + struct dentry, d_lru); + BUG_ON(dentry->d_sb != sb); + + /* + * If we are honouring the DCACHE_REFERENCED flag and the + * dentry has this flag set, don't free it. Clear the flag + * and put it back on the LRU. + */ + if (flags & DCACHE_REFERENCED) { + spin_lock(&dentry->d_lock); + if (dentry->d_flags & DCACHE_REFERENCED) { + dentry->d_flags &= ~DCACHE_REFERENCED; + list_move(&dentry->d_lru, &referenced); + spin_unlock(&dentry->d_lock); + cond_resched_lock(&dcache_lock); + continue; + } + spin_unlock(&dentry->d_lock); + } + + list_move_tail(&dentry->d_lru, &tmp); + if (!--cnt) + break; + cond_resched_lock(&dcache_lock); + } + + *count = cnt; + shrink_dentry_list(&tmp); + if (!list_empty(&referenced)) list_splice(&referenced, &sb->s_dentry_lru); spin_unlock(&dcache_lock); + } /** @@ -538,7 +546,7 @@ static void prune_dcache(int count) { struct super_block *sb, *p = NULL; int w_count; - int unused = dentry_stat.nr_unused; + int unused = percpu_counter_sum_positive(&nr_dentry_unused); int prune_ratio; int pruned; @@ -608,13 +616,19 @@ static void prune_dcache(int count) * shrink_dcache_sb - shrink dcache for a superblock * @sb: superblock * - * Shrink the dcache for the specified super block. This - * is used to free the dcache before unmounting a file - * system + * Shrink the dcache for the specified super block. This is used to free + * the dcache before unmounting a file system. */ -void shrink_dcache_sb(struct super_block * sb) +void shrink_dcache_sb(struct super_block *sb) { - __shrink_dcache_sb(sb, NULL, 0); + LIST_HEAD(tmp); + + spin_lock(&dcache_lock); + while (!list_empty(&sb->s_dentry_lru)) { + list_splice_init(&sb->s_dentry_lru, &tmp); + shrink_dentry_list(&tmp); + } + spin_unlock(&dcache_lock); } EXPORT_SYMBOL(shrink_dcache_sb); @@ -632,7 +646,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) /* detach this root from the system */ spin_lock(&dcache_lock); - dentry_lru_del_init(dentry); + dentry_lru_del(dentry); __d_drop(dentry); spin_unlock(&dcache_lock); @@ -646,7 +660,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) spin_lock(&dcache_lock); list_for_each_entry(loop, &dentry->d_subdirs, d_u.d_child) { - dentry_lru_del_init(loop); + dentry_lru_del(loop); __d_drop(loop); cond_resched_lock(&dcache_lock); } @@ -703,20 +717,13 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry) * otherwise we ascend to the parent and move to the * next sibling if there is one */ if (!parent) - goto out; - + return; dentry = parent; - } while (list_empty(&dentry->d_subdirs)); dentry = list_entry(dentry->d_subdirs.next, struct dentry, d_u.d_child); } -out: - /* several dentries were freed, need to correct nr_dentry */ - spin_lock(&dcache_lock); - dentry_stat.nr_dentry -= detached; - spin_unlock(&dcache_lock); } /* @@ -830,14 +837,15 @@ resume: struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child); next = tmp->next; - dentry_lru_del_init(dentry); /* * move only zero ref count dentries to the end * of the unused list for prune_dcache */ if (!atomic_read(&dentry->d_count)) { - dentry_lru_add_tail(dentry); + dentry_lru_move_tail(dentry); found++; + } else { + dentry_lru_del(dentry); } /* @@ -900,12 +908,16 @@ EXPORT_SYMBOL(shrink_dcache_parent); */ static int shrink_dcache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask) { + int nr_unused; + if (nr) { if (!(gfp_mask & __GFP_FS)) return -1; prune_dcache(nr); } - return (dentry_stat.nr_unused / 100) * sysctl_vfs_cache_pressure; + + nr_unused = percpu_counter_sum_positive(&nr_dentry_unused); + return (nr_unused / 100) * sysctl_vfs_cache_pressure; } static struct shrinker dcache_shrinker = { @@ -972,9 +984,10 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) spin_lock(&dcache_lock); if (parent) list_add(&dentry->d_u.d_child, &parent->d_subdirs); - dentry_stat.nr_dentry++; spin_unlock(&dcache_lock); + percpu_counter_inc(&nr_dentry); + return dentry; } EXPORT_SYMBOL(d_alloc); @@ -1478,33 +1491,26 @@ out: * This is used by ncpfs in its readdir implementation. * Zero is returned in the dentry is invalid. */ - -int d_validate(struct dentry *dentry, struct dentry *dparent) +int d_validate(struct dentry *dentry, struct dentry *parent) { - struct hlist_head *base; - struct hlist_node *lhp; + struct hlist_head *head = d_hash(parent, dentry->d_name.hash); + struct hlist_node *node; + struct dentry *d; /* Check whether the ptr might be valid at all.. */ if (!kmem_ptr_validate(dentry_cache, dentry)) - goto out; - - if (dentry->d_parent != dparent) - goto out; + return 0; + if (dentry->d_parent != parent) + return 0; - spin_lock(&dcache_lock); - base = d_hash(dparent, dentry->d_name.hash); - hlist_for_each(lhp,base) { - /* hlist_for_each_entry_rcu() not required for d_hash list - * as it is parsed under dcache_lock - */ - if (dentry == hlist_entry(lhp, struct dentry, d_hash)) { - __dget_locked(dentry); - spin_unlock(&dcache_lock); + rcu_read_lock(); + hlist_for_each_entry_rcu(d, node, head, d_hash) { + if (d == dentry) { + dget(dentry); return 1; } } - spin_unlock(&dcache_lock); -out: + rcu_read_unlock(); return 0; } EXPORT_SYMBOL(d_validate); @@ -1994,7 +2000,7 @@ global_root: * Returns a pointer into the buffer or an error code if the * path was too long. * - * "buflen" should be positive. Caller holds the dcache_lock. + * "buflen" should be positive. * * If path is not reachable from the supplied root, then the value of * root is changed (without modifying refcounts). @@ -2006,10 +2012,12 @@ char *__d_path(const struct path *path, struct path *root, int error; prepend(&res, &buflen, "\0", 1); + spin_lock(&dcache_lock); error = prepend_path(path, root, &res, &buflen); + spin_unlock(&dcache_lock); + if (error) return ERR_PTR(error); - return res; } @@ -2419,6 +2427,9 @@ static void __init dcache_init(void) { int loop; + percpu_counter_init(&nr_dentry, 0); + percpu_counter_init(&nr_dentry_unused, 0); + /* * A constructor could be added for stable state like the lists, * but it is probably not worth it because of the cache nature diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 30a87b3dbcac..37a8ca7c1222 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -40,6 +40,7 @@ static struct inode *debugfs_get_inode(struct super_block *sb, int mode, dev_t d struct inode *inode = new_inode(sb); if (inode) { + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; switch (mode & S_IFMT) { @@ -134,17 +135,17 @@ static int debug_fill_super(struct super_block *sb, void *data, int silent) return simple_fill_super(sb, DEBUGFS_MAGIC, debug_files); } -static int debug_get_sb(struct file_system_type *fs_type, +static struct dentry *debug_mount(struct file_system_type *fs_type, int flags, const char *dev_name, - void *data, struct vfsmount *mnt) + void *data) { - return get_sb_single(fs_type, flags, data, debug_fill_super, mnt); + return mount_single(fs_type, flags, data, debug_fill_super); } static struct file_system_type debug_fs_type = { .owner = THIS_MODULE, .name = "debugfs", - .get_sb = debug_get_sb, + .mount = debug_mount, .kill_sb = kill_litter_super, }; diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 8b3ffd5b5235..1bb547c9cad6 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -331,7 +331,7 @@ static int compare_init_pts_sb(struct super_block *s, void *p) } /* - * devpts_get_sb() + * devpts_mount() * * If the '-o newinstance' mount option was specified, mount a new * (private) instance of devpts. PTYs created in this instance are @@ -345,20 +345,20 @@ static int compare_init_pts_sb(struct super_block *s, void *p) * semantics in devpts while preserving backward compatibility of the * current 'single-namespace' semantics. i.e all mounts of devpts * without the 'newinstance' mount option should bind to the initial - * kernel mount, like get_sb_single(). + * kernel mount, like mount_single(). * * Mounts with 'newinstance' option create a new, private namespace. * * NOTE: * - * For single-mount semantics, devpts cannot use get_sb_single(), - * because get_sb_single()/sget() find and use the super-block from + * For single-mount semantics, devpts cannot use mount_single(), + * because mount_single()/sget() find and use the super-block from * the most recent mount of devpts. But that recent mount may be a - * 'newinstance' mount and get_sb_single() would pick the newinstance + * 'newinstance' mount and mount_single() would pick the newinstance * super-block instead of the initial super-block. */ -static int devpts_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *devpts_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { int error; struct pts_mount_opts opts; @@ -366,7 +366,7 @@ static int devpts_get_sb(struct file_system_type *fs_type, error = parse_mount_options(data, PARSE_MOUNT, &opts); if (error) - return error; + return ERR_PTR(error); if (opts.newinstance) s = sget(fs_type, NULL, set_anon_super, NULL); @@ -374,7 +374,7 @@ static int devpts_get_sb(struct file_system_type *fs_type, s = sget(fs_type, compare_init_pts_sb, set_anon_super, NULL); if (IS_ERR(s)) - return PTR_ERR(s); + return ERR_CAST(s); if (!s->s_root) { s->s_flags = flags; @@ -390,13 +390,11 @@ static int devpts_get_sb(struct file_system_type *fs_type, if (error) goto out_undo_sget; - simple_set_mnt(mnt, s); - - return 0; + return dget(s->s_root); out_undo_sget: deactivate_locked_super(s); - return error; + return ERR_PTR(error); } #else @@ -404,10 +402,10 @@ out_undo_sget: * This supports only the legacy single-instance semantics (no * multiple-instance semantics) */ -static int devpts_get_sb(struct file_system_type *fs_type, int flags, - const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *devpts_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *data) { - return get_sb_single(fs_type, flags, data, devpts_fill_super, mnt); + return mount_single(fs_type, flags, data, devpts_fill_super); } #endif @@ -421,7 +419,7 @@ static void devpts_kill_sb(struct super_block *sb) static struct file_system_type devpts_fs_type = { .name = "devpts", - .get_sb = devpts_get_sb, + .mount = devpts_mount, .kill_sb = devpts_kill_sb, }; diff --git a/fs/direct-io.c b/fs/direct-io.c index 48d74c7391d1..85882f6ba5f7 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -218,7 +218,7 @@ static struct page *dio_get_page(struct dio *dio) * filesystems can use it to hold additional state between get_block calls and * dio_complete. */ -static int dio_complete(struct dio *dio, loff_t offset, int ret, bool is_async) +static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, bool is_async) { ssize_t transferred = 0; diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index 40186b959429..413a3c48f0bb 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -377,6 +377,7 @@ struct ecryptfs_mount_crypt_stat { #define ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES 0x00000010 #define ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK 0x00000020 #define ECRYPTFS_GLOBAL_ENCFN_USE_FEK 0x00000040 +#define ECRYPTFS_GLOBAL_MOUNT_AUTH_TOK_ONLY 0x00000080 u32 flags; struct list_head global_auth_tok_list; struct mutex global_auth_tok_list_mutex; diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 3fbc94203380..9d1a22d62765 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -32,6 +32,7 @@ #include <linux/crypto.h> #include <linux/fs_stack.h> #include <linux/slab.h> +#include <linux/xattr.h> #include <asm/unaligned.h> #include "ecryptfs_kernel.h" @@ -70,15 +71,19 @@ ecryptfs_create_underlying_file(struct inode *lower_dir_inode, struct vfsmount *lower_mnt = ecryptfs_dentry_to_lower_mnt(dentry); struct dentry *dentry_save; struct vfsmount *vfsmount_save; + unsigned int flags_save; int rc; dentry_save = nd->path.dentry; vfsmount_save = nd->path.mnt; + flags_save = nd->flags; nd->path.dentry = lower_dentry; nd->path.mnt = lower_mnt; + nd->flags &= ~LOOKUP_OPEN; rc = vfs_create(lower_dir_inode, lower_dentry, mode, nd); nd->path.dentry = dentry_save; nd->path.mnt = vfsmount_save; + nd->flags = flags_save; return rc; } @@ -1108,10 +1113,8 @@ ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value, rc = -EOPNOTSUPP; goto out; } - mutex_lock(&lower_dentry->d_inode->i_mutex); - rc = lower_dentry->d_inode->i_op->setxattr(lower_dentry, name, value, - size, flags); - mutex_unlock(&lower_dentry->d_inode->i_mutex); + + rc = vfs_setxattr(lower_dentry, name, value, size, flags); out: return rc; } diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c index 73811cfa2ea4..b1f6858a5223 100644 --- a/fs/ecryptfs/keystore.c +++ b/fs/ecryptfs/keystore.c @@ -446,6 +446,7 @@ out: */ static int ecryptfs_find_auth_tok_for_sig( + struct key **auth_tok_key, struct ecryptfs_auth_tok **auth_tok, struct ecryptfs_mount_crypt_stat *mount_crypt_stat, char *sig) @@ -453,12 +454,21 @@ ecryptfs_find_auth_tok_for_sig( struct ecryptfs_global_auth_tok *global_auth_tok; int rc = 0; + (*auth_tok_key) = NULL; (*auth_tok) = NULL; if (ecryptfs_find_global_auth_tok_for_sig(&global_auth_tok, mount_crypt_stat, sig)) { - struct key *auth_tok_key; - rc = ecryptfs_keyring_auth_tok_for_sig(&auth_tok_key, auth_tok, + /* if the flag ECRYPTFS_GLOBAL_MOUNT_AUTH_TOK_ONLY is set in the + * mount_crypt_stat structure, we prevent to use auth toks that + * are not inserted through the ecryptfs_add_global_auth_tok + * function. + */ + if (mount_crypt_stat->flags + & ECRYPTFS_GLOBAL_MOUNT_AUTH_TOK_ONLY) + return -EINVAL; + + rc = ecryptfs_keyring_auth_tok_for_sig(auth_tok_key, auth_tok, sig); } else (*auth_tok) = global_auth_tok->global_auth_tok; @@ -509,6 +519,7 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes, char *filename, size_t filename_size) { struct ecryptfs_write_tag_70_packet_silly_stack *s; + struct key *auth_tok_key = NULL; int rc = 0; s = kmalloc(sizeof(*s), GFP_KERNEL); @@ -606,6 +617,7 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes, } dest[s->i++] = s->cipher_code; rc = ecryptfs_find_auth_tok_for_sig( + &auth_tok_key, &s->auth_tok, mount_crypt_stat, mount_crypt_stat->global_default_fnek_sig); if (rc) { @@ -753,6 +765,8 @@ out_free_unlock: out_unlock: mutex_unlock(s->tfm_mutex); out: + if (auth_tok_key) + key_put(auth_tok_key); kfree(s); return rc; } @@ -798,6 +812,7 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size, char *data, size_t max_packet_size) { struct ecryptfs_parse_tag_70_packet_silly_stack *s; + struct key *auth_tok_key = NULL; int rc = 0; (*packet_size) = 0; @@ -910,7 +925,8 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size, * >= ECRYPTFS_MAX_IV_BYTES. */ memset(s->iv, 0, ECRYPTFS_MAX_IV_BYTES); s->desc.info = s->iv; - rc = ecryptfs_find_auth_tok_for_sig(&s->auth_tok, mount_crypt_stat, + rc = ecryptfs_find_auth_tok_for_sig(&auth_tok_key, + &s->auth_tok, mount_crypt_stat, s->fnek_sig_hex); if (rc) { printk(KERN_ERR "%s: Error attempting to find auth tok for " @@ -986,6 +1002,8 @@ out: (*filename_size) = 0; (*filename) = NULL; } + if (auth_tok_key) + key_put(auth_tok_key); kfree(s); return rc; } @@ -1557,14 +1575,19 @@ int ecryptfs_keyring_auth_tok_for_sig(struct key **auth_tok_key, ECRYPTFS_VERSION_MAJOR, ECRYPTFS_VERSION_MINOR); rc = -EINVAL; - goto out; + goto out_release_key; } if ((*auth_tok)->token_type != ECRYPTFS_PASSWORD && (*auth_tok)->token_type != ECRYPTFS_PRIVATE_KEY) { printk(KERN_ERR "Invalid auth_tok structure " "returned from key query\n"); rc = -EINVAL; - goto out; + goto out_release_key; + } +out_release_key: + if (rc) { + key_put(*auth_tok_key); + (*auth_tok_key) = NULL; } out: return rc; @@ -1688,6 +1711,7 @@ int ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat, struct ecryptfs_auth_tok_list_item *auth_tok_list_item; size_t tag_11_contents_size; size_t tag_11_packet_size; + struct key *auth_tok_key = NULL; int rc = 0; INIT_LIST_HEAD(&auth_tok_list); @@ -1784,6 +1808,10 @@ int ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat, * just one will be sufficient to decrypt to get the FEK. */ find_next_matching_auth_tok: found_auth_tok = 0; + if (auth_tok_key) { + key_put(auth_tok_key); + auth_tok_key = NULL; + } list_for_each_entry(auth_tok_list_item, &auth_tok_list, list) { candidate_auth_tok = &auth_tok_list_item->auth_tok; if (unlikely(ecryptfs_verbosity > 0)) { @@ -1800,10 +1828,11 @@ find_next_matching_auth_tok: rc = -EINVAL; goto out_wipe_list; } - ecryptfs_find_auth_tok_for_sig(&matching_auth_tok, + rc = ecryptfs_find_auth_tok_for_sig(&auth_tok_key, + &matching_auth_tok, crypt_stat->mount_crypt_stat, candidate_auth_tok_sig); - if (matching_auth_tok) { + if (!rc) { found_auth_tok = 1; goto found_matching_auth_tok; } @@ -1866,6 +1895,8 @@ found_matching_auth_tok: out_wipe_list: wipe_auth_tok_list(&auth_tok_list); out: + if (auth_tok_key) + key_put(auth_tok_key); return rc; } diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index cbd4e18adb20..a9dbd62518e6 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -208,7 +208,8 @@ enum { ecryptfs_opt_sig, ecryptfs_opt_ecryptfs_sig, ecryptfs_opt_passthrough, ecryptfs_opt_xattr_metadata, ecryptfs_opt_encrypted_view, ecryptfs_opt_fnek_sig, ecryptfs_opt_fn_cipher, ecryptfs_opt_fn_cipher_key_bytes, - ecryptfs_opt_unlink_sigs, ecryptfs_opt_err }; + ecryptfs_opt_unlink_sigs, ecryptfs_opt_mount_auth_tok_only, + ecryptfs_opt_err }; static const match_table_t tokens = { {ecryptfs_opt_sig, "sig=%s"}, @@ -223,6 +224,7 @@ static const match_table_t tokens = { {ecryptfs_opt_fn_cipher, "ecryptfs_fn_cipher=%s"}, {ecryptfs_opt_fn_cipher_key_bytes, "ecryptfs_fn_key_bytes=%u"}, {ecryptfs_opt_unlink_sigs, "ecryptfs_unlink_sigs"}, + {ecryptfs_opt_mount_auth_tok_only, "ecryptfs_mount_auth_tok_only"}, {ecryptfs_opt_err, NULL} }; @@ -406,6 +408,10 @@ static int ecryptfs_parse_options(struct ecryptfs_sb_info *sbi, char *options) case ecryptfs_opt_unlink_sigs: mount_crypt_stat->flags |= ECRYPTFS_UNLINK_SIGS; break; + case ecryptfs_opt_mount_auth_tok_only: + mount_crypt_stat->flags |= + ECRYPTFS_GLOBAL_MOUNT_AUTH_TOK_ONLY; + break; case ecryptfs_opt_err: default: printk(KERN_WARNING @@ -540,9 +546,8 @@ out: * ecryptfs_interpose to perform most of the linking * ecryptfs_interpose(): links the lower filesystem into ecryptfs (inode.c) */ -static int ecryptfs_get_sb(struct file_system_type *fs_type, int flags, - const char *dev_name, void *raw_data, - struct vfsmount *mnt) +static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *raw_data) { struct super_block *s; struct ecryptfs_sb_info *sbi; @@ -607,8 +612,7 @@ static int ecryptfs_get_sb(struct file_system_type *fs_type, int flags, err = "Reading sb failed"; goto out; } - simple_set_mnt(mnt, s); - return 0; + return dget(s->s_root); out: if (sbi) { @@ -616,7 +620,7 @@ out: kmem_cache_free(ecryptfs_sb_info_cache, sbi); } printk(KERN_ERR "%s; rc = [%d]\n", err, rc); - return rc; + return ERR_PTR(rc); } /** @@ -639,7 +643,7 @@ static void ecryptfs_kill_block_super(struct super_block *sb) static struct file_system_type ecryptfs_fs_type = { .owner = THIS_MODULE, .name = "ecryptfs", - .get_sb = ecryptfs_get_sb, + .mount = ecryptfs_mount, .kill_sb = ecryptfs_kill_block_super, .fs_flags = 0 }; diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c index f7fc286a3aa9..2720178b7718 100644 --- a/fs/ecryptfs/super.c +++ b/fs/ecryptfs/super.c @@ -28,7 +28,6 @@ #include <linux/key.h> #include <linux/slab.h> #include <linux/seq_file.h> -#include <linux/smp_lock.h> #include <linux/file.h> #include <linux/crypto.h> #include "ecryptfs_kernel.h" @@ -180,6 +179,8 @@ static int ecryptfs_show_options(struct seq_file *m, struct vfsmount *mnt) seq_printf(m, ",ecryptfs_encrypted_view"); if (mount_crypt_stat->flags & ECRYPTFS_UNLINK_SIGS) seq_printf(m, ",ecryptfs_unlink_sigs"); + if (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_MOUNT_AUTH_TOK_ONLY) + seq_printf(m, ",ecryptfs_mount_auth_tok_only"); return 0; } diff --git a/fs/efs/super.c b/fs/efs/super.c index f04942810818..5073a07652cc 100644 --- a/fs/efs/super.c +++ b/fs/efs/super.c @@ -20,16 +20,16 @@ static int efs_statfs(struct dentry *dentry, struct kstatfs *buf); static int efs_fill_super(struct super_block *s, void *d, int silent); -static int efs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *efs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, efs_fill_super, mnt); + return mount_bdev(fs_type, flags, dev_name, data, efs_fill_super); } static struct file_system_type efs_fs_type = { .owner = THIS_MODULE, .name = "efs", - .get_sb = efs_get_sb, + .mount = efs_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 256bb7bb102a..8cf07242067d 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -77,9 +77,6 @@ /* Maximum number of nesting allowed inside epoll sets */ #define EP_MAX_NESTS 4 -/* Maximum msec timeout value storeable in a long int */ -#define EP_MAX_MSTIMEO min(1000ULL * MAX_SCHEDULE_TIMEOUT / HZ, (LONG_MAX - 999ULL) / HZ) - #define EP_MAX_EVENTS (INT_MAX / sizeof(struct epoll_event)) #define EP_UNACTIVE_PTR ((void *) -1L) @@ -1117,18 +1114,22 @@ static int ep_send_events(struct eventpoll *ep, static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, int maxevents, long timeout) { - int res, eavail; + int res, eavail, timed_out = 0; unsigned long flags; - long jtimeout; + long slack; wait_queue_t wait; - - /* - * Calculate the timeout by checking for the "infinite" value (-1) - * and the overflow condition. The passed timeout is in milliseconds, - * that why (t * HZ) / 1000. - */ - jtimeout = (timeout < 0 || timeout >= EP_MAX_MSTIMEO) ? - MAX_SCHEDULE_TIMEOUT : (timeout * HZ + 999) / 1000; + struct timespec end_time; + ktime_t expires, *to = NULL; + + if (timeout > 0) { + ktime_get_ts(&end_time); + timespec_add_ns(&end_time, (u64)timeout * NSEC_PER_MSEC); + slack = select_estimate_accuracy(&end_time); + to = &expires; + *to = timespec_to_ktime(end_time); + } else if (timeout == 0) { + timed_out = 1; + } retry: spin_lock_irqsave(&ep->lock, flags); @@ -1150,7 +1151,7 @@ retry: * to TASK_INTERRUPTIBLE before doing the checks. */ set_current_state(TASK_INTERRUPTIBLE); - if (!list_empty(&ep->rdllist) || !jtimeout) + if (!list_empty(&ep->rdllist) || timed_out) break; if (signal_pending(current)) { res = -EINTR; @@ -1158,7 +1159,9 @@ retry: } spin_unlock_irqrestore(&ep->lock, flags); - jtimeout = schedule_timeout(jtimeout); + if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) + timed_out = 1; + spin_lock_irqsave(&ep->lock, flags); } __remove_wait_queue(&ep->wq, &wait); @@ -1176,7 +1179,7 @@ retry: * more luck. */ if (!res && eavail && - !(res = ep_send_events(ep, events, maxevents)) && jtimeout) + !(res = ep_send_events(ep, events, maxevents)) && !timed_out) goto retry; return res; diff --git a/fs/exec.c b/fs/exec.c index 6d2b6f936858..d68c378a3137 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -54,6 +54,7 @@ #include <linux/fsnotify.h> #include <linux/fs_struct.h> #include <linux/pipe_fs_i.h> +#include <linux/oom.h> #include <asm/uaccess.h> #include <asm/mmu_context.h> @@ -65,6 +66,12 @@ char core_pattern[CORENAME_MAX_SIZE] = "core"; unsigned int core_pipe_limit; int suid_dumpable = 0; +struct core_name { + char *corename; + int used, size; +}; +static atomic_t call_count = ATOMIC_INIT(1); + /* The maximal length of core_pattern is also specified in sysctl.c */ static LIST_HEAD(formats); @@ -157,7 +164,26 @@ out: #ifdef CONFIG_MMU -static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, +void acct_arg_size(struct linux_binprm *bprm, unsigned long pages) +{ + struct mm_struct *mm = current->mm; + long diff = (long)(pages - bprm->vma_pages); + + if (!mm || !diff) + return; + + bprm->vma_pages = pages; + +#ifdef SPLIT_RSS_COUNTING + add_mm_counter(mm, MM_ANONPAGES, diff); +#else + spin_lock(&mm->page_table_lock); + add_mm_counter(mm, MM_ANONPAGES, diff); + spin_unlock(&mm->page_table_lock); +#endif +} + +struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, int write) { struct page *page; @@ -179,6 +205,8 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start; struct rlimit *rlim; + acct_arg_size(bprm, size / PAGE_SIZE); + /* * We've historically supported up to 32 pages (ARG_MAX) * of argument strings even with small stacks @@ -269,7 +297,11 @@ static bool valid_arg_len(struct linux_binprm *bprm, long len) #else -static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, +void acct_arg_size(struct linux_binprm *bprm, unsigned long pages) +{ +} + +struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, int write) { struct page *page; @@ -759,6 +791,10 @@ static int exec_mmap(struct mm_struct *mm) tsk->mm = mm; tsk->active_mm = mm; activate_mm(active_mm, mm); + if (old_mm && tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) { + atomic_dec(&old_mm->oom_disable_count); + atomic_inc(&tsk->mm->oom_disable_count); + } task_unlock(tsk); arch_pick_mmap_layout(mm); if (old_mm) { @@ -992,13 +1028,14 @@ int flush_old_exec(struct linux_binprm * bprm) /* * Release all of the old mmap stuff */ + acct_arg_size(bprm, 0); retval = exec_mmap(bprm->mm); if (retval) goto out; bprm->mm = NULL; /* We're using it now */ - current->flags &= ~PF_RANDOMIZE; + current->flags &= ~(PF_RANDOMIZE | PF_KTHREAD); flush_thread(); current->personality &= ~bprm->per_clear; @@ -1078,14 +1115,14 @@ EXPORT_SYMBOL(setup_new_exec); */ int prepare_bprm_creds(struct linux_binprm *bprm) { - if (mutex_lock_interruptible(¤t->cred_guard_mutex)) + if (mutex_lock_interruptible(¤t->signal->cred_guard_mutex)) return -ERESTARTNOINTR; bprm->cred = prepare_exec_creds(); if (likely(bprm->cred)) return 0; - mutex_unlock(¤t->cred_guard_mutex); + mutex_unlock(¤t->signal->cred_guard_mutex); return -ENOMEM; } @@ -1093,7 +1130,7 @@ void free_bprm(struct linux_binprm *bprm) { free_arg_pages(bprm); if (bprm->cred) { - mutex_unlock(¤t->cred_guard_mutex); + mutex_unlock(¤t->signal->cred_guard_mutex); abort_creds(bprm->cred); } kfree(bprm); @@ -1114,13 +1151,13 @@ void install_exec_creds(struct linux_binprm *bprm) * credentials; any time after this it may be unlocked. */ security_bprm_committed_creds(bprm); - mutex_unlock(¤t->cred_guard_mutex); + mutex_unlock(¤t->signal->cred_guard_mutex); } EXPORT_SYMBOL(install_exec_creds); /* * determine how safe it is to execute the proposed program - * - the caller must hold current->cred_guard_mutex to protect against + * - the caller must hold ->cred_guard_mutex to protect against * PTRACE_ATTACH */ int check_unsafe_exec(struct linux_binprm *bprm) @@ -1401,7 +1438,6 @@ int do_execve(const char * filename, if (retval < 0) goto out; - current->flags &= ~PF_KTHREAD; retval = search_binary_handler(bprm,regs); if (retval < 0) goto out; @@ -1416,8 +1452,10 @@ int do_execve(const char * filename, return retval; out: - if (bprm->mm) - mmput (bprm->mm); + if (bprm->mm) { + acct_arg_size(bprm, 0); + mmput(bprm->mm); + } out_file: if (bprm->file) { @@ -1454,127 +1492,148 @@ void set_binfmt(struct linux_binfmt *new) EXPORT_SYMBOL(set_binfmt); +static int expand_corename(struct core_name *cn) +{ + char *old_corename = cn->corename; + + cn->size = CORENAME_MAX_SIZE * atomic_inc_return(&call_count); + cn->corename = krealloc(old_corename, cn->size, GFP_KERNEL); + + if (!cn->corename) { + kfree(old_corename); + return -ENOMEM; + } + + return 0; +} + +static int cn_printf(struct core_name *cn, const char *fmt, ...) +{ + char *cur; + int need; + int ret; + va_list arg; + + va_start(arg, fmt); + need = vsnprintf(NULL, 0, fmt, arg); + va_end(arg); + + if (likely(need < cn->size - cn->used - 1)) + goto out_printf; + + ret = expand_corename(cn); + if (ret) + goto expand_fail; + +out_printf: + cur = cn->corename + cn->used; + va_start(arg, fmt); + vsnprintf(cur, need + 1, fmt, arg); + va_end(arg); + cn->used += need; + return 0; + +expand_fail: + return ret; +} + /* format_corename will inspect the pattern parameter, and output a * name into corename, which must have space for at least * CORENAME_MAX_SIZE bytes plus one byte for the zero terminator. */ -static int format_corename(char *corename, long signr) +static int format_corename(struct core_name *cn, long signr) { const struct cred *cred = current_cred(); const char *pat_ptr = core_pattern; int ispipe = (*pat_ptr == '|'); - char *out_ptr = corename; - char *const out_end = corename + CORENAME_MAX_SIZE; - int rc; int pid_in_pattern = 0; + int err = 0; + + cn->size = CORENAME_MAX_SIZE * atomic_read(&call_count); + cn->corename = kmalloc(cn->size, GFP_KERNEL); + cn->used = 0; + + if (!cn->corename) + return -ENOMEM; /* Repeat as long as we have more pattern to process and more output space */ while (*pat_ptr) { if (*pat_ptr != '%') { - if (out_ptr == out_end) + if (*pat_ptr == 0) goto out; - *out_ptr++ = *pat_ptr++; + err = cn_printf(cn, "%c", *pat_ptr++); } else { switch (*++pat_ptr) { + /* single % at the end, drop that */ case 0: goto out; /* Double percent, output one percent */ case '%': - if (out_ptr == out_end) - goto out; - *out_ptr++ = '%'; + err = cn_printf(cn, "%c", '%'); break; /* pid */ case 'p': pid_in_pattern = 1; - rc = snprintf(out_ptr, out_end - out_ptr, - "%d", task_tgid_vnr(current)); - if (rc > out_end - out_ptr) - goto out; - out_ptr += rc; + err = cn_printf(cn, "%d", + task_tgid_vnr(current)); break; /* uid */ case 'u': - rc = snprintf(out_ptr, out_end - out_ptr, - "%d", cred->uid); - if (rc > out_end - out_ptr) - goto out; - out_ptr += rc; + err = cn_printf(cn, "%d", cred->uid); break; /* gid */ case 'g': - rc = snprintf(out_ptr, out_end - out_ptr, - "%d", cred->gid); - if (rc > out_end - out_ptr) - goto out; - out_ptr += rc; + err = cn_printf(cn, "%d", cred->gid); break; /* signal that caused the coredump */ case 's': - rc = snprintf(out_ptr, out_end - out_ptr, - "%ld", signr); - if (rc > out_end - out_ptr) - goto out; - out_ptr += rc; + err = cn_printf(cn, "%ld", signr); break; /* UNIX time of coredump */ case 't': { struct timeval tv; do_gettimeofday(&tv); - rc = snprintf(out_ptr, out_end - out_ptr, - "%lu", tv.tv_sec); - if (rc > out_end - out_ptr) - goto out; - out_ptr += rc; + err = cn_printf(cn, "%lu", tv.tv_sec); break; } /* hostname */ case 'h': down_read(&uts_sem); - rc = snprintf(out_ptr, out_end - out_ptr, - "%s", utsname()->nodename); + err = cn_printf(cn, "%s", + utsname()->nodename); up_read(&uts_sem); - if (rc > out_end - out_ptr) - goto out; - out_ptr += rc; break; /* executable */ case 'e': - rc = snprintf(out_ptr, out_end - out_ptr, - "%s", current->comm); - if (rc > out_end - out_ptr) - goto out; - out_ptr += rc; + err = cn_printf(cn, "%s", current->comm); break; /* core limit size */ case 'c': - rc = snprintf(out_ptr, out_end - out_ptr, - "%lu", rlimit(RLIMIT_CORE)); - if (rc > out_end - out_ptr) - goto out; - out_ptr += rc; + err = cn_printf(cn, "%lu", + rlimit(RLIMIT_CORE)); break; default: break; } ++pat_ptr; } + + if (err) + return err; } + /* Backward compatibility with core_uses_pid: * * If core_pattern does not include a %p (as is the default) * and core_uses_pid is set, then .%pid will be appended to * the filename. Do not do this for piped commands. */ if (!ispipe && !pid_in_pattern && core_uses_pid) { - rc = snprintf(out_ptr, out_end - out_ptr, - ".%d", task_tgid_vnr(current)); - if (rc > out_end - out_ptr) - goto out; - out_ptr += rc; + err = cn_printf(cn, ".%d", task_tgid_vnr(current)); + if (err) + return err; } out: - *out_ptr = 0; return ispipe; } @@ -1851,7 +1910,7 @@ static int umh_pipe_setup(struct subprocess_info *info) void do_coredump(long signr, int exit_code, struct pt_regs *regs) { struct core_state core_state; - char corename[CORENAME_MAX_SIZE + 1]; + struct core_name cn; struct mm_struct *mm = current->mm; struct linux_binfmt * binfmt; const struct cred *old_cred; @@ -1906,7 +1965,13 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs) */ clear_thread_flag(TIF_SIGPENDING); - ispipe = format_corename(corename, signr); + ispipe = format_corename(&cn, signr); + + if (ispipe == -ENOMEM) { + printk(KERN_WARNING "format_corename failed\n"); + printk(KERN_WARNING "Aborting core\n"); + goto fail_corename; + } if (ispipe) { int dump_count; @@ -1943,7 +2008,7 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs) goto fail_dropcount; } - helper_argv = argv_split(GFP_KERNEL, corename+1, NULL); + helper_argv = argv_split(GFP_KERNEL, cn.corename+1, NULL); if (!helper_argv) { printk(KERN_WARNING "%s failed to allocate memory\n", __func__); @@ -1956,7 +2021,7 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs) argv_free(helper_argv); if (retval) { printk(KERN_INFO "Core dump to %s pipe failed\n", - corename); + cn.corename); goto close_fail; } } else { @@ -1965,7 +2030,7 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs) if (cprm.limit < binfmt->min_coredump) goto fail_unlock; - cprm.file = filp_open(corename, + cprm.file = filp_open(cn.corename, O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag, 0600); if (IS_ERR(cprm.file)) @@ -2007,6 +2072,8 @@ fail_dropcount: if (ispipe) atomic_dec(&core_dump_count); fail_unlock: + kfree(cn.corename); +fail_corename: coredump_finish(mm); revert_creds(old_cred); fail_creds: diff --git a/fs/exofs/file.c b/fs/exofs/file.c index 68cb23e3bb98..b905c79b4f0a 100644 --- a/fs/exofs/file.c +++ b/fs/exofs/file.c @@ -46,10 +46,6 @@ static int exofs_file_fsync(struct file *filp, int datasync) { int ret; struct inode *inode = filp->f_mapping->host; - struct writeback_control wbc = { - .sync_mode = WB_SYNC_ALL, - .nr_to_write = 0, /* metadata-only; caller takes care of data */ - }; struct super_block *sb; if (!(inode->i_state & I_DIRTY)) @@ -57,7 +53,7 @@ static int exofs_file_fsync(struct file *filp, int datasync) if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) return 0; - ret = sync_inode(inode, &wbc); + ret = sync_inode_metadata(inode, 1); /* This is a good place to write the sb */ /* TODO: Sechedule an sb-sync on create */ diff --git a/fs/exofs/namei.c b/fs/exofs/namei.c index b7dd0c236863..264e95d02830 100644 --- a/fs/exofs/namei.c +++ b/fs/exofs/namei.c @@ -153,7 +153,7 @@ static int exofs_link(struct dentry *old_dentry, struct inode *dir, inode->i_ctime = CURRENT_TIME; inode_inc_link_count(inode); - atomic_inc(&inode->i_count); + ihold(inode); return exofs_add_nondir(dentry, inode); } diff --git a/fs/exofs/super.c b/fs/exofs/super.c index 047e92fa3af8..79c3ae6e0456 100644 --- a/fs/exofs/super.c +++ b/fs/exofs/super.c @@ -659,19 +659,19 @@ free_bdi: /* * Set up the superblock (calls exofs_fill_super eventually) */ -static int exofs_get_sb(struct file_system_type *type, +static struct dentry *exofs_mount(struct file_system_type *type, int flags, const char *dev_name, - void *data, struct vfsmount *mnt) + void *data) { struct exofs_mountopt opts; int ret; ret = parse_options(data, &opts); if (ret) - return ret; + return ERR_PTR(ret); opts.dev_name = dev_name; - return get_sb_nodev(type, flags, &opts, exofs_fill_super, mnt); + return mount_nodev(type, flags, &opts, exofs_fill_super); } /* @@ -809,7 +809,7 @@ static const struct export_operations exofs_export_ops = { static struct file_system_type exofs_type = { .owner = THIS_MODULE, .name = "exofs", - .get_sb = exofs_get_sb, + .mount = exofs_mount, .kill_sb = generic_shutdown_super, }; diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index e9e175949a63..51b304056f10 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -74,21 +74,20 @@ static struct dentry * find_disconnected_root(struct dentry *dentry) { dget(dentry); - spin_lock(&dentry->d_lock); - while (!IS_ROOT(dentry) && - (dentry->d_parent->d_flags & DCACHE_DISCONNECTED)) { - struct dentry *parent = dentry->d_parent; - dget(parent); - spin_unlock(&dentry->d_lock); + while (!IS_ROOT(dentry)) { + struct dentry *parent = dget_parent(dentry); + + if (!(parent->d_flags & DCACHE_DISCONNECTED)) { + dput(parent); + break; + } + dput(dentry); dentry = parent; - spin_lock(&dentry->d_lock); } - spin_unlock(&dentry->d_lock); return dentry; } - /* * Make sure target_dir is fully connected to the dentry tree. * diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c index c6c684b44ea1..0d06f4e75699 100644 --- a/fs/ext2/balloc.c +++ b/fs/ext2/balloc.c @@ -646,10 +646,9 @@ find_next_usable_block(int start, struct buffer_head *bh, int maxblocks) return here; } -/* +/** * ext2_try_to_allocate() * @sb: superblock - * @handle: handle to this transaction * @group: given allocation block group * @bitmap_bh: bufferhead holds the block bitmap * @grp_goal: given target block within the group diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index 764109886ec0..2709b34206ab 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -98,7 +98,7 @@ static int ext2_commit_chunk(struct page *page, loff_t pos, unsigned len) if (IS_DIRSYNC(dir)) { err = write_one_page(page, 1); if (!err) - err = ext2_sync_inode(dir); + err = sync_inode_metadata(dir, 1); } else { unlock_page(page); } diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 416daa62242c..6346a2acf326 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -120,7 +120,6 @@ extern unsigned long ext2_count_free (struct buffer_head *, unsigned); extern struct inode *ext2_iget (struct super_block *, unsigned long); extern int ext2_write_inode (struct inode *, struct writeback_control *); extern void ext2_evict_inode(struct inode *); -extern int ext2_sync_inode (struct inode *); extern int ext2_get_block(struct inode *, sector_t, struct buffer_head *, int); extern int ext2_setattr (struct dentry *, struct iattr *); extern void ext2_set_inode_flags(struct inode *inode); diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 533699c16040..40ad210a5049 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1203,7 +1203,7 @@ static int ext2_setsize(struct inode *inode, loff_t newsize) inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC; if (inode_needs_sync(inode)) { sync_mapping_buffers(inode->i_mapping); - ext2_sync_inode (inode); + sync_inode_metadata(inode, 1); } else { mark_inode_dirty(inode); } @@ -1523,15 +1523,6 @@ int ext2_write_inode(struct inode *inode, struct writeback_control *wbc) return __ext2_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL); } -int ext2_sync_inode(struct inode *inode) -{ - struct writeback_control wbc = { - .sync_mode = WB_SYNC_ALL, - .nr_to_write = 0, /* sys_fsync did this */ - }; - return sync_inode(inode, &wbc); -} - int ext2_setattr(struct dentry *dentry, struct iattr *iattr) { struct inode *inode = dentry->d_inode; diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index 71efb0e9a3f2..f8aecd2e3297 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -206,7 +206,7 @@ static int ext2_link (struct dentry * old_dentry, struct inode * dir, inode->i_ctime = CURRENT_TIME_SEC; inode_inc_link_count(inode); - atomic_inc(&inode->i_count); + ihold(inode); err = ext2_add_link(dentry, inode); if (!err) { diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 85df87d0f7b7..d89e0b6a2d78 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -1221,9 +1221,7 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data) } es = sbi->s_es; - if (((sbi->s_mount_opt & EXT2_MOUNT_XIP) != - (old_mount_opt & EXT2_MOUNT_XIP)) && - invalidate_inodes(sb)) { + if ((sbi->s_mount_opt ^ old_mount_opt) & EXT2_MOUNT_XIP) { ext2_msg(sb, KERN_WARNING, "warning: refusing change of " "xip flag with busy inodes while remounting"); sbi->s_mount_opt &= ~EXT2_MOUNT_XIP; @@ -1358,10 +1356,10 @@ static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf) return 0; } -static int ext2_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *ext2_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, ext2_fill_super, mnt); + return mount_bdev(fs_type, flags, dev_name, data, ext2_fill_super); } #ifdef CONFIG_QUOTA @@ -1475,7 +1473,7 @@ out: static struct file_system_type ext2_fs_type = { .owner = THIS_MODULE, .name = "ext2", - .get_sb = ext2_get_sb, + .mount = ext2_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index 8c29ae15129e..f84700be3274 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -699,7 +699,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh, EXT2_I(inode)->i_file_acl = new_bh ? new_bh->b_blocknr : 0; inode->i_ctime = CURRENT_TIME_SEC; if (IS_SYNC(inode)) { - error = ext2_sync_inode (inode); + error = sync_inode_metadata(inode, 1); /* In case sync failed due to ENOSPC the inode was actually * written (only some dirty data were not) so we just proceed * as if nothing happened and cleanup the unused block */ diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c index 4a32511f4ded..b3db22649426 100644 --- a/fs/ext3/balloc.c +++ b/fs/ext3/balloc.c @@ -792,9 +792,9 @@ find_next_usable_block(ext3_grpblk_t start, struct buffer_head *bh, if (here < 0) here = 0; - p = ((char *)bh->b_data) + (here >> 3); + p = bh->b_data + (here >> 3); r = memscan(p, 0, ((maxblocks + 7) >> 3) - (here >> 3)); - next = (r - ((char *)bh->b_data)) << 3; + next = (r - bh->b_data) << 3; if (next < maxblocks && next >= start && ext3_test_allocatable(next, bh)) return next; @@ -810,8 +810,9 @@ find_next_usable_block(ext3_grpblk_t start, struct buffer_head *bh, /** * claim_block() + * @lock: the spin lock for this block group * @block: the free block (group relative) to allocate - * @bh: the bufferhead containts the block group bitmap + * @bh: the buffer_head contains the block group bitmap * * We think we can allocate this block in this bitmap. Try to set the bit. * If that succeeds then check that nobody has allocated and then freed the @@ -956,9 +957,11 @@ fail_access: * but we will shift to the place where start_block is, * then start from there, when looking for a reservable space. * - * @size: the target new reservation window size + * @my_rsv: the reservation window * - * @group_first_block: the first block we consider to start + * @sb: the super block + * + * @start_block: the first block we consider to start * the real search from * * @last_block: @@ -1084,7 +1087,7 @@ static int find_next_reservable_window( * * failed: we failed to find a reservation window in this group * - * @rsv: the reservation + * @my_rsv: the reservation window * * @grp_goal: The goal (group-relative). It is where the search for a * free reservable space should start from. @@ -1273,8 +1276,8 @@ static void try_to_extend_reservation(struct ext3_reserve_window_node *my_rsv, * @group: given allocation block group * @bitmap_bh: bufferhead holds the block bitmap * @grp_goal: given target block within the group - * @count: target number of blocks to allocate * @my_rsv: reservation window + * @count: target number of blocks to allocate * @errp: pointer to store the error code * * This is the main function used to allocate a new block and its reservation diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c index 4ab72db3559e..9724aef22460 100644 --- a/fs/ext3/ialloc.c +++ b/fs/ext3/ialloc.c @@ -570,9 +570,14 @@ got: ei->i_state_flags = 0; ext3_set_inode_state(inode, EXT3_STATE_NEW); - ei->i_extra_isize = - (EXT3_INODE_SIZE(inode->i_sb) > EXT3_GOOD_OLD_INODE_SIZE) ? - sizeof(struct ext3_inode) - EXT3_GOOD_OLD_INODE_SIZE : 0; + /* See comment in ext3_iget for explanation */ + if (ino >= EXT3_FIRST_INO(sb) + 1 && + EXT3_INODE_SIZE(sb) > EXT3_GOOD_OLD_INODE_SIZE) { + ei->i_extra_isize = + sizeof(struct ext3_inode) - EXT3_GOOD_OLD_INODE_SIZE; + } else { + ei->i_extra_isize = 0; + } ret = inode; dquot_initialize(inode); diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 5e0faf4cda79..a9580617edd2 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -498,7 +498,7 @@ static ext3_fsblk_t ext3_find_goal(struct inode *inode, long block, } /** - * ext3_blks_to_allocate: Look up the block map and count the number + * ext3_blks_to_allocate - Look up the block map and count the number * of direct blocks need to be allocated for the given branch. * * @branch: chain of indirect blocks @@ -536,14 +536,18 @@ static int ext3_blks_to_allocate(Indirect *branch, int k, unsigned long blks, } /** - * ext3_alloc_blocks: multiple allocate blocks needed for a branch + * ext3_alloc_blocks - multiple allocate blocks needed for a branch + * @handle: handle for this transaction + * @inode: owner + * @goal: preferred place for allocation * @indirect_blks: the number of blocks need to allocate for indirect * blocks - * + * @blks: number of blocks need to allocated for direct blocks * @new_blocks: on return it will store the new block numbers for * the indirect blocks(if needed) and the first direct block, - * @blks: on return it will store the total number of allocated - * direct blocks + * @err: here we store the error value + * + * return the number of direct blocks allocated */ static int ext3_alloc_blocks(handle_t *handle, struct inode *inode, ext3_fsblk_t goal, int indirect_blks, int blks, @@ -598,9 +602,11 @@ failed_out: /** * ext3_alloc_branch - allocate and set up a chain of blocks. + * @handle: handle for this transaction * @inode: owner * @indirect_blks: number of allocated indirect blocks * @blks: number of allocated direct blocks + * @goal: preferred place for allocation * @offsets: offsets (in the blocks) to store the pointers to next. * @branch: place to store the chain in. * @@ -700,10 +706,9 @@ failed: /** * ext3_splice_branch - splice the allocated branch onto inode. + * @handle: handle for this transaction * @inode: owner * @block: (logical) number of block we are adding - * @chain: chain of indirect blocks (with a missing link - see - * ext3_alloc_branch) * @where: location of missing link * @num: number of indirect blocks we are adding * @blks: number of direct blocks we are adding @@ -1696,8 +1701,8 @@ static int ext3_journalled_writepage(struct page *page, * doesn't seem much point in redirtying the page here. */ ClearPageChecked(page); - ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE, - ext3_get_block); + ret = __block_write_begin(page, 0, PAGE_CACHE_SIZE, + ext3_get_block); if (ret != 0) { ext3_journal_stop(handle); goto out_unlock; @@ -2530,7 +2535,6 @@ void ext3_truncate(struct inode *inode) */ } else { /* Shared branch grows from an indirect block */ - BUFFER_TRACE(partial->bh, "get_write_access"); ext3_free_branches(handle, inode, partial->bh, partial->p, partial->p+1, (chain+n-1) - partial); diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index 2b35ddb70d65..bce9dce639b8 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -2260,7 +2260,7 @@ retry: inode->i_ctime = CURRENT_TIME_SEC; inc_nlink(inode); - atomic_inc(&inode->i_count); + ihold(inode); err = ext3_add_entry(handle, dentry, inode); if (!err) { diff --git a/fs/ext3/resize.c b/fs/ext3/resize.c index 0ccd7b12b73c..e746d30b1232 100644 --- a/fs/ext3/resize.c +++ b/fs/ext3/resize.c @@ -977,7 +977,8 @@ int ext3_group_extend(struct super_block *sb, struct ext3_super_block *es, o_blocks_count = le32_to_cpu(es->s_blocks_count); if (test_opt(sb, DEBUG)) - printk(KERN_DEBUG "EXT3-fs: extending last group from "E3FSBLK" uto "E3FSBLK" blocks\n", + printk(KERN_DEBUG "EXT3-fs: extending last group from "E3FSBLK + " upto "E3FSBLK" blocks\n", o_blocks_count, n_blocks_count); if (n_blocks_count == 0 || n_blocks_count == o_blocks_count) @@ -985,7 +986,7 @@ int ext3_group_extend(struct super_block *sb, struct ext3_super_block *es, if (n_blocks_count > (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) { printk(KERN_ERR "EXT3-fs: filesystem on %s:" - " too large to resize to %lu blocks safely\n", + " too large to resize to "E3FSBLK" blocks safely\n", sb->s_id, n_blocks_count); if (sizeof(sector_t) < 8) ext3_warning(sb, __func__, @@ -1065,11 +1066,11 @@ int ext3_group_extend(struct super_block *sb, struct ext3_super_block *es, es->s_blocks_count = cpu_to_le32(o_blocks_count + add); ext3_journal_dirty_metadata(handle, EXT3_SB(sb)->s_sbh); mutex_unlock(&EXT3_SB(sb)->s_resize_lock); - ext3_debug("freeing blocks %lu through "E3FSBLK"\n", o_blocks_count, - o_blocks_count + add); + ext3_debug("freeing blocks "E3FSBLK" through "E3FSBLK"\n", + o_blocks_count, o_blocks_count + add); ext3_free_blocks_sb(handle, sb, o_blocks_count, add, &freed_blocks); - ext3_debug("freed blocks "E3FSBLK" through "E3FSBLK"\n", o_blocks_count, - o_blocks_count + add); + ext3_debug("freed blocks "E3FSBLK" through "E3FSBLK"\n", + o_blocks_count, o_blocks_count + add); if ((err = ext3_journal_stop(handle))) goto exit_put; if (test_opt(sb, DEBUG)) diff --git a/fs/ext3/super.c b/fs/ext3/super.c index 377768009106..acf8695fa8f0 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -27,7 +27,6 @@ #include <linux/init.h> #include <linux/blkdev.h> #include <linux/parser.h> -#include <linux/smp_lock.h> #include <linux/buffer_head.h> #include <linux/exportfs.h> #include <linux/vfs.h> @@ -1301,9 +1300,9 @@ static int ext3_setup_super(struct super_block *sb, struct ext3_super_block *es, ext3_msg(sb, KERN_WARNING, "warning: mounting fs with errors, " "running e2fsck is recommended"); - else if ((__s16) le16_to_cpu(es->s_max_mnt_count) >= 0 && + else if ((__s16) le16_to_cpu(es->s_max_mnt_count) > 0 && le16_to_cpu(es->s_mnt_count) >= - (unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count)) + le16_to_cpu(es->s_max_mnt_count)) ext3_msg(sb, KERN_WARNING, "warning: maximal mount count reached, " "running e2fsck is recommended"); @@ -1320,7 +1319,7 @@ static int ext3_setup_super(struct super_block *sb, struct ext3_super_block *es, valid forever! :) */ es->s_state &= cpu_to_le16(~EXT3_VALID_FS); #endif - if (!(__s16) le16_to_cpu(es->s_max_mnt_count)) + if (!le16_to_cpu(es->s_max_mnt_count)) es->s_max_mnt_count = cpu_to_le16(EXT3_DFL_MAX_MNT_COUNT); le16_add_cpu(&es->s_mnt_count, 1); es->s_mtime = cpu_to_le32(get_seconds()); @@ -1647,7 +1646,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) * Note: s_es must be initialized as soon as possible because * some ext3 macro-instructions depend on its value */ - es = (struct ext3_super_block *) (((char *)bh->b_data) + offset); + es = (struct ext3_super_block *) (bh->b_data + offset); sbi->s_es = es; sb->s_magic = le16_to_cpu(es->s_magic); if (sb->s_magic != EXT3_SUPER_MAGIC) @@ -1758,7 +1757,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) "error: can't read superblock on 2nd try"); goto failed_mount; } - es = (struct ext3_super_block *)(((char *)bh->b_data) + offset); + es = (struct ext3_super_block *)(bh->b_data + offset); sbi->s_es = es; if (es->s_magic != cpu_to_le16(EXT3_SUPER_MAGIC)) { ext3_msg(sb, KERN_ERR, @@ -1857,13 +1856,13 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) - le32_to_cpu(es->s_first_data_block) - 1) / EXT3_BLOCKS_PER_GROUP(sb)) + 1; - db_count = (sbi->s_groups_count + EXT3_DESC_PER_BLOCK(sb) - 1) / - EXT3_DESC_PER_BLOCK(sb); + db_count = DIV_ROUND_UP(sbi->s_groups_count, EXT3_DESC_PER_BLOCK(sb)); sbi->s_group_desc = kmalloc(db_count * sizeof (struct buffer_head *), GFP_KERNEL); if (sbi->s_group_desc == NULL) { ext3_msg(sb, KERN_ERR, "error: not enough memory"); + ret = -ENOMEM; goto failed_mount; } @@ -1951,6 +1950,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) } if (err) { ext3_msg(sb, KERN_ERR, "error: insufficient memory"); + ret = err; goto failed_mount3; } @@ -2159,7 +2159,7 @@ static journal_t *ext3_get_dev_journal(struct super_block *sb, goto out_bdev; } - es = (struct ext3_super_block *) (((char *)bh->b_data) + offset); + es = (struct ext3_super_block *) (bh->b_data + offset); if ((le16_to_cpu(es->s_magic) != EXT3_SUPER_MAGIC) || !(le32_to_cpu(es->s_feature_incompat) & EXT3_FEATURE_INCOMPAT_JOURNAL_DEV)) { @@ -2352,6 +2352,21 @@ static int ext3_commit_super(struct super_block *sb, if (!sbh) return error; + + if (buffer_write_io_error(sbh)) { + /* + * Oh, dear. A previous attempt to write the + * superblock failed. This could happen because the + * USB device was yanked out. Or it could happen to + * be a transient write error and maybe the block will + * be remapped. Nothing we can do but to retry the + * write and hope for the best. + */ + ext3_msg(sb, KERN_ERR, "previous I/O error to " + "superblock detected"); + clear_buffer_write_io_error(sbh); + set_buffer_uptodate(sbh); + } /* * If the file system is mounted read-only, don't update the * superblock write time. This avoids updating the superblock @@ -2368,8 +2383,15 @@ static int ext3_commit_super(struct super_block *sb, es->s_free_inodes_count = cpu_to_le32(ext3_count_free_inodes(sb)); BUFFER_TRACE(sbh, "marking dirty"); mark_buffer_dirty(sbh); - if (sync) + if (sync) { error = sync_dirty_buffer(sbh); + if (buffer_write_io_error(sbh)) { + ext3_msg(sb, KERN_ERR, "I/O error while writing " + "superblock"); + clear_buffer_write_io_error(sbh); + set_buffer_uptodate(sbh); + } + } return error; } @@ -2997,16 +3019,16 @@ out: #endif -static int ext3_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *ext3_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, ext3_fill_super, mnt); + return mount_bdev(fs_type, flags, dev_name, data, ext3_fill_super); } static struct file_system_type ext3_fs_type = { .owner = THIS_MODULE, .name = "ext3", - .get_sb = ext3_get_sb, + .mount = ext3_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile index 8867b2a1e5fe..c947e36eda6c 100644 --- a/fs/ext4/Makefile +++ b/fs/ext4/Makefile @@ -4,7 +4,7 @@ obj-$(CONFIG_EXT4_FS) += ext4.o -ext4-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o \ +ext4-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o page-io.o \ ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \ ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index bd30799a43ed..14c3af26c671 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -171,7 +171,8 @@ unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, * less than the blocksize * 8 ( which is the size * of bitmap ), set rest of the block bitmap to 1 */ - mark_bitmap_end(group_blocks, sb->s_blocksize * 8, bh->b_data); + ext4_mark_bitmap_end(group_blocks, sb->s_blocksize * 8, + bh->b_data); } return free_blocks - ext4_group_used_meta_blocks(sb, block_group, gdp); } @@ -489,7 +490,7 @@ error_return: * Check if filesystem has nblocks free & available for allocation. * On success return 1, return 0 on failure. */ -int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks) +static int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks) { s64 free_blocks, dirty_blocks, root_blocks; struct percpu_counter *fbc = &sbi->s_freeblocks_counter; diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index 3db5084db9bd..fac90f3fba80 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -29,16 +29,15 @@ struct ext4_system_zone { static struct kmem_cache *ext4_system_zone_cachep; -int __init init_ext4_system_zone(void) +int __init ext4_init_system_zone(void) { - ext4_system_zone_cachep = KMEM_CACHE(ext4_system_zone, - SLAB_RECLAIM_ACCOUNT); + ext4_system_zone_cachep = KMEM_CACHE(ext4_system_zone, 0); if (ext4_system_zone_cachep == NULL) return -ENOMEM; return 0; } -void exit_ext4_system_zone(void) +void ext4_exit_system_zone(void) { kmem_cache_destroy(ext4_system_zone_cachep); } diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 374510f72baa..ece76fb6a40c 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -39,7 +39,7 @@ static int ext4_release_dir(struct inode *inode, struct file *filp); const struct file_operations ext4_dir_operations = { - .llseek = generic_file_llseek, + .llseek = ext4_llseek, .read = generic_read_dir, .readdir = ext4_readdir, /* we take BKL. needed?*/ .unlocked_ioctl = ext4_ioctl, diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 889ec9d5e6ad..6a5edea2d70b 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -168,7 +168,20 @@ struct mpage_da_data { int pages_written; int retval; }; -#define EXT4_IO_UNWRITTEN 0x1 + +/* + * Flags for ext4_io_end->flags + */ +#define EXT4_IO_END_UNWRITTEN 0x0001 +#define EXT4_IO_END_ERROR 0x0002 + +struct ext4_io_page { + struct page *p_page; + atomic_t p_count; +}; + +#define MAX_IO_PAGES 128 + typedef struct ext4_io_end { struct list_head list; /* per-file finished IO list */ struct inode *inode; /* file being written to */ @@ -179,8 +192,18 @@ typedef struct ext4_io_end { struct work_struct work; /* data work queue */ struct kiocb *iocb; /* iocb struct for AIO */ int result; /* error value for AIO */ + int num_io_pages; + struct ext4_io_page *pages[MAX_IO_PAGES]; } ext4_io_end_t; +struct ext4_io_submit { + int io_op; + struct bio *io_bio; + ext4_io_end_t *io_end; + struct ext4_io_page *io_page; + sector_t io_next_block; +}; + /* * Special inodes numbers */ @@ -205,6 +228,7 @@ typedef struct ext4_io_end { #define EXT4_MIN_BLOCK_SIZE 1024 #define EXT4_MAX_BLOCK_SIZE 65536 #define EXT4_MIN_BLOCK_LOG_SIZE 10 +#define EXT4_MAX_BLOCK_LOG_SIZE 16 #ifdef __KERNEL__ # define EXT4_BLOCK_SIZE(s) ((s)->s_blocksize) #else @@ -834,6 +858,7 @@ struct ext4_inode_info { spinlock_t i_completed_io_lock; /* current io_end structure for async DIO write*/ ext4_io_end_t *cur_aio_dio; + atomic_t i_ioend_count; /* Number of outstanding io_end structs */ /* * Transactions that contain inode's metadata needed to complete @@ -889,6 +914,7 @@ struct ext4_inode_info { #define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */ #define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */ #define EXT4_MOUNT_DISCARD 0x40000000 /* Issue DISCARD requests */ +#define EXT4_MOUNT_INIT_INODE_TABLE 0x80000000 /* Initialize uninitialized itables */ #define clear_opt(o, opt) o &= ~EXT4_MOUNT_##opt #define set_opt(o, opt) o |= EXT4_MOUNT_##opt @@ -1087,7 +1113,6 @@ struct ext4_sb_info { struct completion s_kobj_unregister; /* Journaling */ - struct inode *s_journal_inode; struct journal_s *s_journal; struct list_head s_orphan; struct mutex s_orphan_lock; @@ -1120,10 +1145,7 @@ struct ext4_sb_info { /* for buddy allocator */ struct ext4_group_info ***s_group_info; struct inode *s_buddy_cache; - long s_blocks_reserved; - spinlock_t s_reserve_lock; spinlock_t s_md_lock; - tid_t s_last_transaction; unsigned short *s_mb_offsets; unsigned int *s_mb_maxs; @@ -1141,7 +1163,6 @@ struct ext4_sb_info { unsigned long s_mb_last_start; /* stats for buddy allocator */ - spinlock_t s_mb_pa_lock; atomic_t s_bal_reqs; /* number of reqs with len > 1 */ atomic_t s_bal_success; /* we found long enough chunks */ atomic_t s_bal_allocated; /* in blocks */ @@ -1172,6 +1193,11 @@ struct ext4_sb_info { /* timer for periodic error stats printing */ struct timer_list s_err_report; + + /* Lazy inode table initialization info */ + struct ext4_li_request *s_li_request; + /* Wait multiplier for lazy initialization thread */ + unsigned int s_li_wait_mult; }; static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb) @@ -1533,7 +1559,42 @@ ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no) void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr, ext4_group_t *blockgrpp, ext4_grpblk_t *offsetp); -extern struct proc_dir_entry *ext4_proc_root; +/* + * Timeout and state flag for lazy initialization inode thread. + */ +#define EXT4_DEF_LI_WAIT_MULT 10 +#define EXT4_DEF_LI_MAX_START_DELAY 5 +#define EXT4_LAZYINIT_QUIT 0x0001 +#define EXT4_LAZYINIT_RUNNING 0x0002 + +/* + * Lazy inode table initialization info + */ +struct ext4_lazy_init { + unsigned long li_state; + + wait_queue_head_t li_wait_daemon; + wait_queue_head_t li_wait_task; + struct timer_list li_timer; + struct task_struct *li_task; + + struct list_head li_request_list; + struct mutex li_list_mtx; +}; + +struct ext4_li_request { + struct super_block *lr_super; + struct ext4_sb_info *lr_sbi; + ext4_group_t lr_next_group; + struct list_head lr_request; + unsigned long lr_next_sched; + unsigned long lr_timeout; +}; + +struct ext4_features { + struct kobject f_kobj; + struct completion f_kobj_unregister; +}; /* * Function prototypes @@ -1561,7 +1622,6 @@ extern unsigned long ext4_bg_num_gdb(struct super_block *sb, extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode, ext4_fsblk_t goal, unsigned long *count, int *errp); extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi, s64 nblocks); -extern int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks); extern void ext4_add_groupblocks(handle_t *handle, struct super_block *sb, ext4_fsblk_t block, unsigned long count); extern ext4_fsblk_t ext4_count_free_blocks(struct super_block *); @@ -1605,11 +1665,9 @@ extern struct inode * ext4_orphan_get(struct super_block *, unsigned long); extern unsigned long ext4_count_free_inodes(struct super_block *); extern unsigned long ext4_count_dirs(struct super_block *); extern void ext4_check_inodes_bitmap(struct super_block *); -extern unsigned ext4_init_inode_bitmap(struct super_block *sb, - struct buffer_head *bh, - ext4_group_t group, - struct ext4_group_desc *desc); -extern void mark_bitmap_end(int start_bit, int end_bit, char *bitmap); +extern void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap); +extern int ext4_init_inode_table(struct super_block *sb, + ext4_group_t group, int barrier); /* mballoc.c */ extern long ext4_mb_stats; @@ -1620,16 +1678,15 @@ extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *, struct ext4_allocation_request *, int *); extern int ext4_mb_reserve_blocks(struct super_block *, int); extern void ext4_discard_preallocations(struct inode *); -extern int __init init_ext4_mballoc(void); -extern void exit_ext4_mballoc(void); +extern int __init ext4_init_mballoc(void); +extern void ext4_exit_mballoc(void); extern void ext4_free_blocks(handle_t *handle, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t block, unsigned long count, int flags); extern int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t i, struct ext4_group_desc *desc); -extern int ext4_mb_get_buddy_cache_lock(struct super_block *, ext4_group_t); -extern void ext4_mb_put_buddy_cache_lock(struct super_block *, - ext4_group_t, int); +extern int ext4_trim_fs(struct super_block *, struct fstrim_range *); + /* inode.c */ struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int, int *); @@ -1657,13 +1714,11 @@ extern void ext4_get_inode_flags(struct ext4_inode_info *); extern int ext4_alloc_da_blocks(struct inode *inode); extern void ext4_set_aops(struct inode *inode); extern int ext4_writepage_trans_blocks(struct inode *); -extern int ext4_meta_trans_blocks(struct inode *, int nrblocks, int idxblocks); extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks); extern int ext4_block_truncate_page(handle_t *handle, struct address_space *mapping, loff_t from); extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); extern qsize_t *ext4_get_reserved_space(struct inode *inode); -extern int flush_completed_IO(struct inode *inode); extern void ext4_da_update_reserve_space(struct inode *inode, int used, int quota_claim); /* ioctl.c */ @@ -1960,6 +2015,7 @@ extern const struct file_operations ext4_dir_operations; /* file.c */ extern const struct inode_operations ext4_file_inode_operations; extern const struct file_operations ext4_file_operations; +extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin); /* namei.c */ extern const struct inode_operations ext4_dir_inode_operations; @@ -1973,8 +2029,8 @@ extern const struct inode_operations ext4_fast_symlink_inode_operations; /* block_validity */ extern void ext4_release_system_zone(struct super_block *sb); extern int ext4_setup_system_zone(struct super_block *sb); -extern int __init init_ext4_system_zone(void); -extern void exit_ext4_system_zone(void); +extern int __init ext4_init_system_zone(void); +extern void ext4_exit_system_zone(void); extern int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk, unsigned int count); @@ -2002,6 +2058,18 @@ extern int ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 start_orig, __u64 start_donor, __u64 len, __u64 *moved_len); +/* page-io.c */ +extern int __init ext4_init_pageio(void); +extern void ext4_exit_pageio(void); +extern void ext4_ioend_wait(struct inode *); +extern void ext4_free_io_end(ext4_io_end_t *io); +extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags); +extern int ext4_end_io_nolock(ext4_io_end_t *io); +extern void ext4_io_submit(struct ext4_io_submit *io); +extern int ext4_bio_write_page(struct ext4_io_submit *io, + struct page *page, + int len, + struct writeback_control *wbc); /* BH_Uninit flag: blocks are allocated but uninitialized on disk */ enum ext4_state_bits { diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index bdb6ce7e2eb4..28ce70fd9cd0 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -225,11 +225,60 @@ static inline void ext4_ext_mark_initialized(struct ext4_extent *ext) ext->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ext)); } +/* + * ext4_ext_pblock: + * combine low and high parts of physical block number into ext4_fsblk_t + */ +static inline ext4_fsblk_t ext4_ext_pblock(struct ext4_extent *ex) +{ + ext4_fsblk_t block; + + block = le32_to_cpu(ex->ee_start_lo); + block |= ((ext4_fsblk_t) le16_to_cpu(ex->ee_start_hi) << 31) << 1; + return block; +} + +/* + * ext4_idx_pblock: + * combine low and high parts of a leaf physical block number into ext4_fsblk_t + */ +static inline ext4_fsblk_t ext4_idx_pblock(struct ext4_extent_idx *ix) +{ + ext4_fsblk_t block; + + block = le32_to_cpu(ix->ei_leaf_lo); + block |= ((ext4_fsblk_t) le16_to_cpu(ix->ei_leaf_hi) << 31) << 1; + return block; +} + +/* + * ext4_ext_store_pblock: + * stores a large physical block number into an extent struct, + * breaking it into parts + */ +static inline void ext4_ext_store_pblock(struct ext4_extent *ex, + ext4_fsblk_t pb) +{ + ex->ee_start_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff)); + ex->ee_start_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & + 0xffff); +} + +/* + * ext4_idx_store_pblock: + * stores a large physical block number into an index struct, + * breaking it into parts + */ +static inline void ext4_idx_store_pblock(struct ext4_extent_idx *ix, + ext4_fsblk_t pb) +{ + ix->ei_leaf_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff)); + ix->ei_leaf_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & + 0xffff); +} + extern int ext4_ext_calc_metadata_amount(struct inode *inode, sector_t lblocks); -extern ext4_fsblk_t ext_pblock(struct ext4_extent *ex); -extern ext4_fsblk_t idx_pblock(struct ext4_extent_idx *); -extern void ext4_ext_store_pblock(struct ext4_extent *, ext4_fsblk_t); extern int ext4_extent_tree_init(handle_t *, struct inode *); extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int num, @@ -237,19 +286,9 @@ extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode, extern int ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1, struct ext4_extent *ex2); -extern int ext4_ext_try_to_merge(struct inode *inode, - struct ext4_ext_path *path, - struct ext4_extent *); -extern unsigned int ext4_ext_check_overlap(struct inode *, struct ext4_extent *, struct ext4_ext_path *); extern int ext4_ext_insert_extent(handle_t *, struct inode *, struct ext4_ext_path *, struct ext4_extent *, int); -extern int ext4_ext_walk_space(struct inode *, ext4_lblk_t, ext4_lblk_t, - ext_prepare_callback, void *); extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t, struct ext4_ext_path *); -extern int ext4_ext_search_left(struct inode *, struct ext4_ext_path *, - ext4_lblk_t *, ext4_fsblk_t *); -extern int ext4_ext_search_right(struct inode *, struct ext4_ext_path *, - ext4_lblk_t *, ext4_fsblk_t *); extern void ext4_ext_drop_refs(struct ext4_ext_path *); extern int ext4_ext_check_inode(struct inode *inode); #endif /* _EXT4_EXTENTS */ diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 06328d3e5717..0554c48cb1fd 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -44,55 +44,6 @@ #include "ext4_jbd2.h" #include "ext4_extents.h" - -/* - * ext_pblock: - * combine low and high parts of physical block number into ext4_fsblk_t - */ -ext4_fsblk_t ext_pblock(struct ext4_extent *ex) -{ - ext4_fsblk_t block; - - block = le32_to_cpu(ex->ee_start_lo); - block |= ((ext4_fsblk_t) le16_to_cpu(ex->ee_start_hi) << 31) << 1; - return block; -} - -/* - * idx_pblock: - * combine low and high parts of a leaf physical block number into ext4_fsblk_t - */ -ext4_fsblk_t idx_pblock(struct ext4_extent_idx *ix) -{ - ext4_fsblk_t block; - - block = le32_to_cpu(ix->ei_leaf_lo); - block |= ((ext4_fsblk_t) le16_to_cpu(ix->ei_leaf_hi) << 31) << 1; - return block; -} - -/* - * ext4_ext_store_pblock: - * stores a large physical block number into an extent struct, - * breaking it into parts - */ -void ext4_ext_store_pblock(struct ext4_extent *ex, ext4_fsblk_t pb) -{ - ex->ee_start_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff)); - ex->ee_start_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff); -} - -/* - * ext4_idx_store_pblock: - * stores a large physical block number into an index struct, - * breaking it into parts - */ -static void ext4_idx_store_pblock(struct ext4_extent_idx *ix, ext4_fsblk_t pb) -{ - ix->ei_leaf_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff)); - ix->ei_leaf_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) & 0xffff); -} - static int ext4_ext_truncate_extend_restart(handle_t *handle, struct inode *inode, int needed) @@ -169,7 +120,8 @@ static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode, /* try to predict block placement */ ex = path[depth].p_ext; if (ex) - return ext_pblock(ex)+(block-le32_to_cpu(ex->ee_block)); + return (ext4_ext_pblock(ex) + + (block - le32_to_cpu(ex->ee_block))); /* it looks like index is empty; * try to find starting block from index itself */ @@ -354,7 +306,7 @@ ext4_ext_max_entries(struct inode *inode, int depth) static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext) { - ext4_fsblk_t block = ext_pblock(ext); + ext4_fsblk_t block = ext4_ext_pblock(ext); int len = ext4_ext_get_actual_len(ext); return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len); @@ -363,7 +315,7 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext) static int ext4_valid_extent_idx(struct inode *inode, struct ext4_extent_idx *ext_idx) { - ext4_fsblk_t block = idx_pblock(ext_idx); + ext4_fsblk_t block = ext4_idx_pblock(ext_idx); return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, 1); } @@ -463,13 +415,13 @@ static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path) for (k = 0; k <= l; k++, path++) { if (path->p_idx) { ext_debug(" %d->%llu", le32_to_cpu(path->p_idx->ei_block), - idx_pblock(path->p_idx)); + ext4_idx_pblock(path->p_idx)); } else if (path->p_ext) { ext_debug(" %d:[%d]%d:%llu ", le32_to_cpu(path->p_ext->ee_block), ext4_ext_is_uninitialized(path->p_ext), ext4_ext_get_actual_len(path->p_ext), - ext_pblock(path->p_ext)); + ext4_ext_pblock(path->p_ext)); } else ext_debug(" []"); } @@ -494,7 +446,7 @@ static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path) for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) { ext_debug("%d:[%d]%d:%llu ", le32_to_cpu(ex->ee_block), ext4_ext_is_uninitialized(ex), - ext4_ext_get_actual_len(ex), ext_pblock(ex)); + ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex)); } ext_debug("\n"); } @@ -545,7 +497,7 @@ ext4_ext_binsearch_idx(struct inode *inode, path->p_idx = l - 1; ext_debug(" -> %d->%lld ", le32_to_cpu(path->p_idx->ei_block), - idx_pblock(path->p_idx)); + ext4_idx_pblock(path->p_idx)); #ifdef CHECK_BINSEARCH { @@ -614,7 +566,7 @@ ext4_ext_binsearch(struct inode *inode, path->p_ext = l - 1; ext_debug(" -> %d:%llu:[%d]%d ", le32_to_cpu(path->p_ext->ee_block), - ext_pblock(path->p_ext), + ext4_ext_pblock(path->p_ext), ext4_ext_is_uninitialized(path->p_ext), ext4_ext_get_actual_len(path->p_ext)); @@ -682,7 +634,7 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block, ppos, le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max)); ext4_ext_binsearch_idx(inode, path + ppos, block); - path[ppos].p_block = idx_pblock(path[ppos].p_idx); + path[ppos].p_block = ext4_idx_pblock(path[ppos].p_idx); path[ppos].p_depth = i; path[ppos].p_ext = NULL; @@ -721,7 +673,7 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block, ext4_ext_binsearch(inode, path + ppos, block); /* if not an empty leaf */ if (path[ppos].p_ext) - path[ppos].p_block = ext_pblock(path[ppos].p_ext); + path[ppos].p_block = ext4_ext_pblock(path[ppos].p_ext); ext4_ext_show_path(inode, path); @@ -739,9 +691,9 @@ err: * insert new index [@logical;@ptr] into the block at @curp; * check where to insert: before @curp or after @curp */ -int ext4_ext_insert_index(handle_t *handle, struct inode *inode, - struct ext4_ext_path *curp, - int logical, ext4_fsblk_t ptr) +static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, + struct ext4_ext_path *curp, + int logical, ext4_fsblk_t ptr) { struct ext4_extent_idx *ix; int len, err; @@ -917,7 +869,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, EXT_MAX_EXTENT(path[depth].p_hdr)) { ext_debug("move %d:%llu:[%d]%d in new leaf %llu\n", le32_to_cpu(path[depth].p_ext->ee_block), - ext_pblock(path[depth].p_ext), + ext4_ext_pblock(path[depth].p_ext), ext4_ext_is_uninitialized(path[depth].p_ext), ext4_ext_get_actual_len(path[depth].p_ext), newblock); @@ -1007,7 +959,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, while (path[i].p_idx <= EXT_MAX_INDEX(path[i].p_hdr)) { ext_debug("%d: move %d:%llu in new index %llu\n", i, le32_to_cpu(path[i].p_idx->ei_block), - idx_pblock(path[i].p_idx), + ext4_idx_pblock(path[i].p_idx), newblock); /*memmove(++fidx, path[i].p_idx++, sizeof(struct ext4_extent_idx)); @@ -1146,7 +1098,7 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, ext_debug("new root: num %d(%d), lblock %d, ptr %llu\n", le16_to_cpu(neh->eh_entries), le16_to_cpu(neh->eh_max), le32_to_cpu(EXT_FIRST_INDEX(neh)->ei_block), - idx_pblock(EXT_FIRST_INDEX(neh))); + ext4_idx_pblock(EXT_FIRST_INDEX(neh))); neh->eh_depth = cpu_to_le16(path->p_depth + 1); err = ext4_ext_dirty(handle, inode, curp); @@ -1232,9 +1184,9 @@ out: * returns 0 at @phys * return value contains 0 (success) or error code */ -int -ext4_ext_search_left(struct inode *inode, struct ext4_ext_path *path, - ext4_lblk_t *logical, ext4_fsblk_t *phys) +static int ext4_ext_search_left(struct inode *inode, + struct ext4_ext_path *path, + ext4_lblk_t *logical, ext4_fsblk_t *phys) { struct ext4_extent_idx *ix; struct ext4_extent *ex; @@ -1286,7 +1238,7 @@ ext4_ext_search_left(struct inode *inode, struct ext4_ext_path *path, } *logical = le32_to_cpu(ex->ee_block) + ee_len - 1; - *phys = ext_pblock(ex) + ee_len - 1; + *phys = ext4_ext_pblock(ex) + ee_len - 1; return 0; } @@ -1297,9 +1249,9 @@ ext4_ext_search_left(struct inode *inode, struct ext4_ext_path *path, * returns 0 at @phys * return value contains 0 (success) or error code */ -int -ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path, - ext4_lblk_t *logical, ext4_fsblk_t *phys) +static int ext4_ext_search_right(struct inode *inode, + struct ext4_ext_path *path, + ext4_lblk_t *logical, ext4_fsblk_t *phys) { struct buffer_head *bh = NULL; struct ext4_extent_header *eh; @@ -1342,7 +1294,7 @@ ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path, } } *logical = le32_to_cpu(ex->ee_block); - *phys = ext_pblock(ex); + *phys = ext4_ext_pblock(ex); return 0; } @@ -1357,7 +1309,7 @@ ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path, /* next allocated block in this leaf */ ex++; *logical = le32_to_cpu(ex->ee_block); - *phys = ext_pblock(ex); + *phys = ext4_ext_pblock(ex); return 0; } @@ -1376,7 +1328,7 @@ got_index: * follow it and find the closest allocated * block to the right */ ix++; - block = idx_pblock(ix); + block = ext4_idx_pblock(ix); while (++depth < path->p_depth) { bh = sb_bread(inode->i_sb, block); if (bh == NULL) @@ -1388,7 +1340,7 @@ got_index: return -EIO; } ix = EXT_FIRST_INDEX(eh); - block = idx_pblock(ix); + block = ext4_idx_pblock(ix); put_bh(bh); } @@ -1402,7 +1354,7 @@ got_index: } ex = EXT_FIRST_EXTENT(eh); *logical = le32_to_cpu(ex->ee_block); - *phys = ext_pblock(ex); + *phys = ext4_ext_pblock(ex); put_bh(bh); return 0; } @@ -1573,7 +1525,7 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1, return 0; #endif - if (ext_pblock(ex1) + ext1_ee_len == ext_pblock(ex2)) + if (ext4_ext_pblock(ex1) + ext1_ee_len == ext4_ext_pblock(ex2)) return 1; return 0; } @@ -1585,9 +1537,9 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1, * Returns 0 if the extents (ex and ex+1) were _not_ merged and returns * 1 if they got merged. */ -int ext4_ext_try_to_merge(struct inode *inode, - struct ext4_ext_path *path, - struct ext4_extent *ex) +static int ext4_ext_try_to_merge(struct inode *inode, + struct ext4_ext_path *path, + struct ext4_extent *ex) { struct ext4_extent_header *eh; unsigned int depth, len; @@ -1632,9 +1584,9 @@ int ext4_ext_try_to_merge(struct inode *inode, * such that there will be no overlap, and then returns 1. * If there is no overlap found, it returns 0. */ -unsigned int ext4_ext_check_overlap(struct inode *inode, - struct ext4_extent *newext, - struct ext4_ext_path *path) +static unsigned int ext4_ext_check_overlap(struct inode *inode, + struct ext4_extent *newext, + struct ext4_ext_path *path) { ext4_lblk_t b1, b2; unsigned int depth, len1; @@ -1706,11 +1658,12 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, if (ex && !(flag & EXT4_GET_BLOCKS_PRE_IO) && ext4_can_extents_be_merged(inode, ex, newext)) { ext_debug("append [%d]%d block to %d:[%d]%d (from %llu)\n", - ext4_ext_is_uninitialized(newext), - ext4_ext_get_actual_len(newext), - le32_to_cpu(ex->ee_block), - ext4_ext_is_uninitialized(ex), - ext4_ext_get_actual_len(ex), ext_pblock(ex)); + ext4_ext_is_uninitialized(newext), + ext4_ext_get_actual_len(newext), + le32_to_cpu(ex->ee_block), + ext4_ext_is_uninitialized(ex), + ext4_ext_get_actual_len(ex), + ext4_ext_pblock(ex)); err = ext4_ext_get_access(handle, inode, path + depth); if (err) return err; @@ -1780,7 +1733,7 @@ has_space: /* there is no extent in this leaf, create first one */ ext_debug("first extent in the leaf: %d:%llu:[%d]%d\n", le32_to_cpu(newext->ee_block), - ext_pblock(newext), + ext4_ext_pblock(newext), ext4_ext_is_uninitialized(newext), ext4_ext_get_actual_len(newext)); path[depth].p_ext = EXT_FIRST_EXTENT(eh); @@ -1794,7 +1747,7 @@ has_space: ext_debug("insert %d:%llu:[%d]%d after: nearest 0x%p, " "move %d from 0x%p to 0x%p\n", le32_to_cpu(newext->ee_block), - ext_pblock(newext), + ext4_ext_pblock(newext), ext4_ext_is_uninitialized(newext), ext4_ext_get_actual_len(newext), nearex, len, nearex + 1, nearex + 2); @@ -1808,7 +1761,7 @@ has_space: ext_debug("insert %d:%llu:[%d]%d before: nearest 0x%p, " "move %d from 0x%p to 0x%p\n", le32_to_cpu(newext->ee_block), - ext_pblock(newext), + ext4_ext_pblock(newext), ext4_ext_is_uninitialized(newext), ext4_ext_get_actual_len(newext), nearex, len, nearex + 1, nearex + 2); @@ -1819,7 +1772,7 @@ has_space: le16_add_cpu(&eh->eh_entries, 1); nearex = path[depth].p_ext; nearex->ee_block = newext->ee_block; - ext4_ext_store_pblock(nearex, ext_pblock(newext)); + ext4_ext_store_pblock(nearex, ext4_ext_pblock(newext)); nearex->ee_len = newext->ee_len; merge: @@ -1845,9 +1798,9 @@ cleanup: return err; } -int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block, - ext4_lblk_t num, ext_prepare_callback func, - void *cbdata) +static int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block, + ext4_lblk_t num, ext_prepare_callback func, + void *cbdata) { struct ext4_ext_path *path = NULL; struct ext4_ext_cache cbex; @@ -1923,7 +1876,7 @@ int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block, } else { cbex.ec_block = le32_to_cpu(ex->ee_block); cbex.ec_len = ext4_ext_get_actual_len(ex); - cbex.ec_start = ext_pblock(ex); + cbex.ec_start = ext4_ext_pblock(ex); cbex.ec_type = EXT4_EXT_CACHE_EXTENT; } @@ -2073,7 +2026,7 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode, /* free index block */ path--; - leaf = idx_pblock(path->p_idx); + leaf = ext4_idx_pblock(path->p_idx); if (unlikely(path->p_hdr->eh_entries == 0)) { EXT4_ERROR_INODE(inode, "path->p_hdr->eh_entries == 0"); return -EIO; @@ -2181,7 +2134,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode, ext4_fsblk_t start; num = le32_to_cpu(ex->ee_block) + ee_len - from; - start = ext_pblock(ex) + ee_len - num; + start = ext4_ext_pblock(ex) + ee_len - num; ext_debug("free last %u blocks starting %llu\n", num, start); ext4_free_blocks(handle, inode, 0, start, num, flags); } else if (from == le32_to_cpu(ex->ee_block) @@ -2310,7 +2263,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, goto out; ext_debug("new extent: %u:%u:%llu\n", block, num, - ext_pblock(ex)); + ext4_ext_pblock(ex)); ex--; ex_ee_block = le32_to_cpu(ex->ee_block); ex_ee_len = ext4_ext_get_actual_len(ex); @@ -2421,9 +2374,9 @@ again: struct buffer_head *bh; /* go to the next level */ ext_debug("move to level %d (block %llu)\n", - i + 1, idx_pblock(path[i].p_idx)); + i + 1, ext4_idx_pblock(path[i].p_idx)); memset(path + i + 1, 0, sizeof(*path)); - bh = sb_bread(sb, idx_pblock(path[i].p_idx)); + bh = sb_bread(sb, ext4_idx_pblock(path[i].p_idx)); if (!bh) { /* should we reset i_size? */ err = -EIO; @@ -2535,77 +2488,21 @@ void ext4_ext_release(struct super_block *sb) #endif } -static void bi_complete(struct bio *bio, int error) -{ - complete((struct completion *)bio->bi_private); -} - /* FIXME!! we need to try to merge to left or right after zero-out */ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex) { + ext4_fsblk_t ee_pblock; + unsigned int ee_len; int ret; - struct bio *bio; - int blkbits, blocksize; - sector_t ee_pblock; - struct completion event; - unsigned int ee_len, len, done, offset; - - blkbits = inode->i_blkbits; - blocksize = inode->i_sb->s_blocksize; ee_len = ext4_ext_get_actual_len(ex); - ee_pblock = ext_pblock(ex); - - /* convert ee_pblock to 512 byte sectors */ - ee_pblock = ee_pblock << (blkbits - 9); - - while (ee_len > 0) { - - if (ee_len > BIO_MAX_PAGES) - len = BIO_MAX_PAGES; - else - len = ee_len; - - bio = bio_alloc(GFP_NOIO, len); - if (!bio) - return -ENOMEM; - - bio->bi_sector = ee_pblock; - bio->bi_bdev = inode->i_sb->s_bdev; - - done = 0; - offset = 0; - while (done < len) { - ret = bio_add_page(bio, ZERO_PAGE(0), - blocksize, offset); - if (ret != blocksize) { - /* - * We can't add any more pages because of - * hardware limitations. Start a new bio. - */ - break; - } - done++; - offset += blocksize; - if (offset >= PAGE_CACHE_SIZE) - offset = 0; - } + ee_pblock = ext4_ext_pblock(ex); - init_completion(&event); - bio->bi_private = &event; - bio->bi_end_io = bi_complete; - submit_bio(WRITE, bio); - wait_for_completion(&event); + ret = sb_issue_zeroout(inode->i_sb, ee_pblock, ee_len, GFP_NOFS); + if (ret > 0) + ret = 0; - if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) { - bio_put(bio); - return -EIO; - } - bio_put(bio); - ee_len -= done; - ee_pblock += done << (blkbits - 9); - } - return 0; + return ret; } #define EXT4_EXT_ZERO_LEN 7 @@ -2651,12 +2548,12 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); allocated = ee_len - (map->m_lblk - ee_block); - newblock = map->m_lblk - ee_block + ext_pblock(ex); + newblock = map->m_lblk - ee_block + ext4_ext_pblock(ex); ex2 = ex; orig_ex.ee_block = ex->ee_block; orig_ex.ee_len = cpu_to_le16(ee_len); - ext4_ext_store_pblock(&orig_ex, ext_pblock(ex)); + ext4_ext_store_pblock(&orig_ex, ext4_ext_pblock(ex)); /* * It is safe to convert extent to initialized via explicit @@ -2675,7 +2572,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, /* update the extent length and mark as initialized */ ex->ee_block = orig_ex.ee_block; ex->ee_len = orig_ex.ee_len; - ext4_ext_store_pblock(ex, ext_pblock(&orig_ex)); + ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex)); ext4_ext_dirty(handle, inode, path + depth); /* zeroed the full extent */ return allocated; @@ -2710,7 +2607,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, ex->ee_block = orig_ex.ee_block; ex->ee_len = cpu_to_le16(ee_len - allocated); ext4_ext_mark_uninitialized(ex); - ext4_ext_store_pblock(ex, ext_pblock(&orig_ex)); + ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex)); ext4_ext_dirty(handle, inode, path + depth); ex3 = &newex; @@ -2725,7 +2622,8 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, goto fix_extent_len; ex->ee_block = orig_ex.ee_block; ex->ee_len = orig_ex.ee_len; - ext4_ext_store_pblock(ex, ext_pblock(&orig_ex)); + ext4_ext_store_pblock(ex, + ext4_ext_pblock(&orig_ex)); ext4_ext_dirty(handle, inode, path + depth); /* blocks available from map->m_lblk */ return allocated; @@ -2782,7 +2680,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, /* update the extent length and mark as initialized */ ex->ee_block = orig_ex.ee_block; ex->ee_len = orig_ex.ee_len; - ext4_ext_store_pblock(ex, ext_pblock(&orig_ex)); + ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex)); ext4_ext_dirty(handle, inode, path + depth); /* zeroed the full extent */ /* blocks available from map->m_lblk */ @@ -2833,7 +2731,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, /* update the extent length and mark as initialized */ ex->ee_block = orig_ex.ee_block; ex->ee_len = orig_ex.ee_len; - ext4_ext_store_pblock(ex, ext_pblock(&orig_ex)); + ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex)); ext4_ext_dirty(handle, inode, path + depth); /* zero out the first half */ /* blocks available from map->m_lblk */ @@ -2902,7 +2800,7 @@ insert: /* update the extent length and mark as initialized */ ex->ee_block = orig_ex.ee_block; ex->ee_len = orig_ex.ee_len; - ext4_ext_store_pblock(ex, ext_pblock(&orig_ex)); + ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex)); ext4_ext_dirty(handle, inode, path + depth); /* zero out the first half */ return allocated; @@ -2915,7 +2813,7 @@ out: fix_extent_len: ex->ee_block = orig_ex.ee_block; ex->ee_len = orig_ex.ee_len; - ext4_ext_store_pblock(ex, ext_pblock(&orig_ex)); + ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex)); ext4_ext_mark_uninitialized(ex); ext4_ext_dirty(handle, inode, path + depth); return err; @@ -2973,12 +2871,12 @@ static int ext4_split_unwritten_extents(handle_t *handle, ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); allocated = ee_len - (map->m_lblk - ee_block); - newblock = map->m_lblk - ee_block + ext_pblock(ex); + newblock = map->m_lblk - ee_block + ext4_ext_pblock(ex); ex2 = ex; orig_ex.ee_block = ex->ee_block; orig_ex.ee_len = cpu_to_le16(ee_len); - ext4_ext_store_pblock(&orig_ex, ext_pblock(ex)); + ext4_ext_store_pblock(&orig_ex, ext4_ext_pblock(ex)); /* * It is safe to convert extent to initialized via explicit @@ -3027,7 +2925,7 @@ static int ext4_split_unwritten_extents(handle_t *handle, /* update the extent length and mark as initialized */ ex->ee_block = orig_ex.ee_block; ex->ee_len = orig_ex.ee_len; - ext4_ext_store_pblock(ex, ext_pblock(&orig_ex)); + ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex)); ext4_ext_dirty(handle, inode, path + depth); /* zeroed the full extent */ /* blocks available from map->m_lblk */ @@ -3099,7 +2997,7 @@ insert: /* update the extent length and mark as initialized */ ex->ee_block = orig_ex.ee_block; ex->ee_len = orig_ex.ee_len; - ext4_ext_store_pblock(ex, ext_pblock(&orig_ex)); + ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex)); ext4_ext_dirty(handle, inode, path + depth); /* zero out the first half */ return allocated; @@ -3112,7 +3010,7 @@ out: fix_extent_len: ex->ee_block = orig_ex.ee_block; ex->ee_len = orig_ex.ee_len; - ext4_ext_store_pblock(ex, ext_pblock(&orig_ex)); + ext4_ext_store_pblock(ex, ext4_ext_pblock(&orig_ex)); ext4_ext_mark_uninitialized(ex); ext4_ext_dirty(handle, inode, path + depth); return err; @@ -3180,6 +3078,57 @@ static void unmap_underlying_metadata_blocks(struct block_device *bdev, unmap_underlying_metadata(bdev, block + i); } +/* + * Handle EOFBLOCKS_FL flag, clearing it if necessary + */ +static int check_eofblocks_fl(handle_t *handle, struct inode *inode, + struct ext4_map_blocks *map, + struct ext4_ext_path *path, + unsigned int len) +{ + int i, depth; + struct ext4_extent_header *eh; + struct ext4_extent *ex, *last_ex; + + if (!ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS)) + return 0; + + depth = ext_depth(inode); + eh = path[depth].p_hdr; + ex = path[depth].p_ext; + + if (unlikely(!eh->eh_entries)) { + EXT4_ERROR_INODE(inode, "eh->eh_entries == 0 and " + "EOFBLOCKS_FL set"); + return -EIO; + } + last_ex = EXT_LAST_EXTENT(eh); + /* + * We should clear the EOFBLOCKS_FL flag if we are writing the + * last block in the last extent in the file. We test this by + * first checking to see if the caller to + * ext4_ext_get_blocks() was interested in the last block (or + * a block beyond the last block) in the current extent. If + * this turns out to be false, we can bail out from this + * function immediately. + */ + if (map->m_lblk + len < le32_to_cpu(last_ex->ee_block) + + ext4_ext_get_actual_len(last_ex)) + return 0; + /* + * If the caller does appear to be planning to write at or + * beyond the end of the current extent, we then test to see + * if the current extent is the last extent in the file, by + * checking to make sure it was reached via the rightmost node + * at each level of the tree. + */ + for (i = depth-1; i >= 0; i--) + if (path[i].p_idx != EXT_LAST_INDEX(path[i].p_hdr)) + return 0; + ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS); + return ext4_mark_inode_dirty(handle, inode); +} + static int ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, @@ -3206,7 +3155,7 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, * completed */ if (io) - io->flag = EXT4_IO_UNWRITTEN; + io->flag = EXT4_IO_END_UNWRITTEN; else ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN); if (ext4_should_dioread_nolock(inode)) @@ -3217,8 +3166,12 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, if ((flags & EXT4_GET_BLOCKS_CONVERT)) { ret = ext4_convert_unwritten_extents_endio(handle, inode, path); - if (ret >= 0) + if (ret >= 0) { ext4_update_inode_fsync_trans(handle, inode, 1); + err = check_eofblocks_fl(handle, inode, map, path, + map->m_len); + } else + err = ret; goto out2; } /* buffered IO case */ @@ -3244,8 +3197,13 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, /* buffered write, writepage time, convert*/ ret = ext4_ext_convert_to_initialized(handle, inode, map, path); - if (ret >= 0) + if (ret >= 0) { ext4_update_inode_fsync_trans(handle, inode, 1); + err = check_eofblocks_fl(handle, inode, map, path, map->m_len); + if (err < 0) + goto out2; + } + out: if (ret <= 0) { err = ret; @@ -3292,6 +3250,7 @@ out2: } return err ? err : allocated; } + /* * Block allocation/map/preallocation routine for extents based files * @@ -3315,9 +3274,9 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, { struct ext4_ext_path *path = NULL; struct ext4_extent_header *eh; - struct ext4_extent newex, *ex, *last_ex; + struct ext4_extent newex, *ex; ext4_fsblk_t newblock; - int i, err = 0, depth, ret, cache_type; + int err = 0, depth, ret, cache_type; unsigned int allocated = 0; struct ext4_allocation_request ar; ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio; @@ -3341,7 +3300,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, /* block is already allocated */ newblock = map->m_lblk - le32_to_cpu(newex.ee_block) - + ext_pblock(&newex); + + ext4_ext_pblock(&newex); /* number of remaining blocks in the extent */ allocated = ext4_ext_get_actual_len(&newex) - (map->m_lblk - le32_to_cpu(newex.ee_block)); @@ -3379,7 +3338,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, ex = path[depth].p_ext; if (ex) { ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block); - ext4_fsblk_t ee_start = ext_pblock(ex); + ext4_fsblk_t ee_start = ext4_ext_pblock(ex); unsigned short ee_len; /* @@ -3488,7 +3447,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, */ if ((flags & EXT4_GET_BLOCKS_PRE_IO)) { if (io) - io->flag = EXT4_IO_UNWRITTEN; + io->flag = EXT4_IO_END_UNWRITTEN; else ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN); @@ -3497,44 +3456,23 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, map->m_flags |= EXT4_MAP_UNINIT; } - if (unlikely(ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS))) { - if (unlikely(!eh->eh_entries)) { - EXT4_ERROR_INODE(inode, - "eh->eh_entries == 0 and " - "EOFBLOCKS_FL set"); - err = -EIO; - goto out2; - } - last_ex = EXT_LAST_EXTENT(eh); - /* - * If the current leaf block was reached by looking at - * the last index block all the way down the tree, and - * we are extending the inode beyond the last extent - * in the current leaf block, then clear the - * EOFBLOCKS_FL flag. - */ - for (i = depth-1; i >= 0; i--) { - if (path[i].p_idx != EXT_LAST_INDEX(path[i].p_hdr)) - break; - } - if ((i < 0) && - (map->m_lblk + ar.len > le32_to_cpu(last_ex->ee_block) + - ext4_ext_get_actual_len(last_ex))) - ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS); - } + err = check_eofblocks_fl(handle, inode, map, path, ar.len); + if (err) + goto out2; + err = ext4_ext_insert_extent(handle, inode, path, &newex, flags); if (err) { /* free data blocks we just allocated */ /* not a good idea to call discard here directly, * but otherwise we'd need to call it every free() */ ext4_discard_preallocations(inode); - ext4_free_blocks(handle, inode, 0, ext_pblock(&newex), + ext4_free_blocks(handle, inode, 0, ext4_ext_pblock(&newex), ext4_ext_get_actual_len(&newex), 0); goto out2; } /* previous routine could use block we allocated */ - newblock = ext_pblock(&newex); + newblock = ext4_ext_pblock(&newex); allocated = ext4_ext_get_actual_len(&newex); if (allocated > map->m_len) allocated = map->m_len; @@ -3729,7 +3667,7 @@ retry: printk(KERN_ERR "%s: ext4_ext_map_blocks " "returned error inode#%lu, block=%u, " "max_blocks=%u", __func__, - inode->i_ino, block, max_blocks); + inode->i_ino, map.m_lblk, max_blocks); #endif ext4_mark_inode_dirty(handle, inode); ret2 = ext4_journal_stop(handle); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index ee92b66d4558..5a5c55ddceef 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -130,8 +130,50 @@ static int ext4_file_open(struct inode * inode, struct file * filp) return dquot_file_open(inode, filp); } +/* + * ext4_llseek() copied from generic_file_llseek() to handle both + * block-mapped and extent-mapped maxbytes values. This should + * otherwise be identical with generic_file_llseek(). + */ +loff_t ext4_llseek(struct file *file, loff_t offset, int origin) +{ + struct inode *inode = file->f_mapping->host; + loff_t maxbytes; + + if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) + maxbytes = EXT4_SB(inode->i_sb)->s_bitmap_maxbytes; + else + maxbytes = inode->i_sb->s_maxbytes; + mutex_lock(&inode->i_mutex); + switch (origin) { + case SEEK_END: + offset += inode->i_size; + break; + case SEEK_CUR: + if (offset == 0) { + mutex_unlock(&inode->i_mutex); + return file->f_pos; + } + offset += file->f_pos; + break; + } + + if (offset < 0 || offset > maxbytes) { + mutex_unlock(&inode->i_mutex); + return -EINVAL; + } + + if (offset != file->f_pos) { + file->f_pos = offset; + file->f_version = 0; + } + mutex_unlock(&inode->i_mutex); + + return offset; +} + const struct file_operations ext4_file_operations = { - .llseek = generic_file_llseek, + .llseek = ext4_llseek, .read = do_sync_read, .write = do_sync_write, .aio_read = generic_file_aio_read, diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 3f3ff5ee8f9d..c1a7bc923cf6 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -34,6 +34,89 @@ #include <trace/events/ext4.h> +static void dump_completed_IO(struct inode * inode) +{ +#ifdef EXT4_DEBUG + struct list_head *cur, *before, *after; + ext4_io_end_t *io, *io0, *io1; + unsigned long flags; + + if (list_empty(&EXT4_I(inode)->i_completed_io_list)){ + ext4_debug("inode %lu completed_io list is empty\n", inode->i_ino); + return; + } + + ext4_debug("Dump inode %lu completed_io list \n", inode->i_ino); + spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags); + list_for_each_entry(io, &EXT4_I(inode)->i_completed_io_list, list){ + cur = &io->list; + before = cur->prev; + io0 = container_of(before, ext4_io_end_t, list); + after = cur->next; + io1 = container_of(after, ext4_io_end_t, list); + + ext4_debug("io 0x%p from inode %lu,prev 0x%p,next 0x%p\n", + io, inode->i_ino, io0, io1); + } + spin_unlock_irqrestore(&EXT4_I(inode)->i_completed_io_lock, flags); +#endif +} + +/* + * This function is called from ext4_sync_file(). + * + * When IO is completed, the work to convert unwritten extents to + * written is queued on workqueue but may not get immediately + * scheduled. When fsync is called, we need to ensure the + * conversion is complete before fsync returns. + * The inode keeps track of a list of pending/completed IO that + * might needs to do the conversion. This function walks through + * the list and convert the related unwritten extents for completed IO + * to written. + * The function return the number of pending IOs on success. + */ +static int flush_completed_IO(struct inode *inode) +{ + ext4_io_end_t *io; + struct ext4_inode_info *ei = EXT4_I(inode); + unsigned long flags; + int ret = 0; + int ret2 = 0; + + if (list_empty(&ei->i_completed_io_list)) + return ret; + + dump_completed_IO(inode); + spin_lock_irqsave(&ei->i_completed_io_lock, flags); + while (!list_empty(&ei->i_completed_io_list)){ + io = list_entry(ei->i_completed_io_list.next, + ext4_io_end_t, list); + /* + * Calling ext4_end_io_nolock() to convert completed + * IO to written. + * + * When ext4_sync_file() is called, run_queue() may already + * about to flush the work corresponding to this io structure. + * It will be upset if it founds the io structure related + * to the work-to-be schedule is freed. + * + * Thus we need to keep the io structure still valid here after + * convertion finished. The io structure has a flag to + * avoid double converting from both fsync and background work + * queue work. + */ + spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); + ret = ext4_end_io_nolock(io); + spin_lock_irqsave(&ei->i_completed_io_lock, flags); + if (ret < 0) + ret2 = ret; + else + list_del_init(&io->list); + } + spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); + return (ret2 < 0) ? ret2 : 0; +} + /* * If we're not journaling and this is a just-created file, we have to * sync our parent directory (if it was freshly created) since diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 45853e0d1f21..1ce240a23ebb 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -50,7 +50,7 @@ * need to use it within a single byte (to ensure we get endianness right). * We can use memset for the rest of the bitmap as there are no other users. */ -void mark_bitmap_end(int start_bit, int end_bit, char *bitmap) +void ext4_mark_bitmap_end(int start_bit, int end_bit, char *bitmap) { int i; @@ -65,9 +65,10 @@ void mark_bitmap_end(int start_bit, int end_bit, char *bitmap) } /* Initializes an uninitialized inode bitmap */ -unsigned ext4_init_inode_bitmap(struct super_block *sb, struct buffer_head *bh, - ext4_group_t block_group, - struct ext4_group_desc *gdp) +static unsigned ext4_init_inode_bitmap(struct super_block *sb, + struct buffer_head *bh, + ext4_group_t block_group, + struct ext4_group_desc *gdp) { struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -85,7 +86,7 @@ unsigned ext4_init_inode_bitmap(struct super_block *sb, struct buffer_head *bh, } memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8); - mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8, + ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8, bh->b_data); return EXT4_INODES_PER_GROUP(sb); @@ -107,6 +108,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) desc = ext4_get_group_desc(sb, block_group, NULL); if (!desc) return NULL; + bitmap_blk = ext4_inode_bitmap(sb, desc); bh = sb_getblk(sb, bitmap_blk); if (unlikely(!bh)) { @@ -123,6 +125,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) unlock_buffer(bh); return bh; } + ext4_lock_group(sb, block_group); if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) { ext4_init_inode_bitmap(sb, bh, block_group, desc); @@ -133,6 +136,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) return bh; } ext4_unlock_group(sb, block_group); + if (buffer_uptodate(bh)) { /* * if not uninit if bh is uptodate, @@ -411,8 +415,8 @@ struct orlov_stats { * for a particular block group or flex_bg. If flex_size is 1, then g * is a block group number; otherwise it is flex_bg number. */ -void get_orlov_stats(struct super_block *sb, ext4_group_t g, - int flex_size, struct orlov_stats *stats) +static void get_orlov_stats(struct super_block *sb, ext4_group_t g, + int flex_size, struct orlov_stats *stats) { struct ext4_group_desc *desc; struct flex_groups *flex_group = EXT4_SB(sb)->s_flex_groups; @@ -712,8 +716,17 @@ static int ext4_claim_inode(struct super_block *sb, { int free = 0, retval = 0, count; struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); + /* + * We have to be sure that new inode allocation does not race with + * inode table initialization, because otherwise we may end up + * allocating and writing new inode right before sb_issue_zeroout + * takes place and overwriting our new inode with zeroes. So we + * take alloc_sem to prevent it. + */ + down_read(&grp->alloc_sem); ext4_lock_group(sb, group); if (ext4_set_bit(ino, inode_bitmap_bh->b_data)) { /* not a free inode */ @@ -724,6 +737,7 @@ static int ext4_claim_inode(struct super_block *sb, if ((group == 0 && ino < EXT4_FIRST_INO(sb)) || ino > EXT4_INODES_PER_GROUP(sb)) { ext4_unlock_group(sb, group); + up_read(&grp->alloc_sem); ext4_error(sb, "reserved inode or inode > inodes count - " "block_group = %u, inode=%lu", group, ino + group * EXT4_INODES_PER_GROUP(sb)); @@ -772,6 +786,7 @@ static int ext4_claim_inode(struct super_block *sb, gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp); err_ret: ext4_unlock_group(sb, group); + up_read(&grp->alloc_sem); return retval; } @@ -1205,3 +1220,109 @@ unsigned long ext4_count_dirs(struct super_block * sb) } return count; } + +/* + * Zeroes not yet zeroed inode table - just write zeroes through the whole + * inode table. Must be called without any spinlock held. The only place + * where it is called from on active part of filesystem is ext4lazyinit + * thread, so we do not need any special locks, however we have to prevent + * inode allocation from the current group, so we take alloc_sem lock, to + * block ext4_claim_inode until we are finished. + */ +extern int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, + int barrier) +{ + struct ext4_group_info *grp = ext4_get_group_info(sb, group); + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_group_desc *gdp = NULL; + struct buffer_head *group_desc_bh; + handle_t *handle; + ext4_fsblk_t blk; + int num, ret = 0, used_blks = 0; + + /* This should not happen, but just to be sure check this */ + if (sb->s_flags & MS_RDONLY) { + ret = 1; + goto out; + } + + gdp = ext4_get_group_desc(sb, group, &group_desc_bh); + if (!gdp) + goto out; + + /* + * We do not need to lock this, because we are the only one + * handling this flag. + */ + if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)) + goto out; + + handle = ext4_journal_start_sb(sb, 1); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out; + } + + down_write(&grp->alloc_sem); + /* + * If inode bitmap was already initialized there may be some + * used inodes so we need to skip blocks with used inodes in + * inode table. + */ + if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT))) + used_blks = DIV_ROUND_UP((EXT4_INODES_PER_GROUP(sb) - + ext4_itable_unused_count(sb, gdp)), + sbi->s_inodes_per_block); + + if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group)) { + ext4_error(sb, "Something is wrong with group %u\n" + "Used itable blocks: %d" + "itable unused count: %u\n", + group, used_blks, + ext4_itable_unused_count(sb, gdp)); + ret = 1; + goto out; + } + + blk = ext4_inode_table(sb, gdp) + used_blks; + num = sbi->s_itb_per_group - used_blks; + + BUFFER_TRACE(group_desc_bh, "get_write_access"); + ret = ext4_journal_get_write_access(handle, + group_desc_bh); + if (ret) + goto err_out; + + /* + * Skip zeroout if the inode table is full. But we set the ZEROED + * flag anyway, because obviously, when it is full it does not need + * further zeroing. + */ + if (unlikely(num == 0)) + goto skip_zeroout; + + ext4_debug("going to zero out inode table in group %d\n", + group); + ret = sb_issue_zeroout(sb, blk, num, GFP_NOFS); + if (ret < 0) + goto err_out; + if (barrier) + blkdev_issue_flush(sb->s_bdev, GFP_NOFS, NULL); + +skip_zeroout: + ext4_lock_group(sb, group); + gdp->bg_flags |= cpu_to_le16(EXT4_BG_INODE_ZEROED); + gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp); + ext4_unlock_group(sb, group); + + BUFFER_TRACE(group_desc_bh, + "call ext4_handle_dirty_metadata"); + ret = ext4_handle_dirty_metadata(handle, NULL, + group_desc_bh); + +err_out: + up_write(&grp->alloc_sem); + ext4_journal_stop(handle); +out: + return ret; +} diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 4b8debeb3965..bdbe69902207 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -53,6 +53,7 @@ static inline int ext4_begin_ordered_truncate(struct inode *inode, loff_t new_size) { + trace_ext4_begin_ordered_truncate(inode, new_size); return jbd2_journal_begin_ordered_truncate( EXT4_SB(inode->i_sb)->s_journal, &EXT4_I(inode)->jinode, @@ -60,6 +61,12 @@ static inline int ext4_begin_ordered_truncate(struct inode *inode, } static void ext4_invalidatepage(struct page *page, unsigned long offset); +static int noalloc_get_block_write(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create); +static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode); +static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate); +static int __ext4_journalled_writepage(struct page *page, unsigned int len); +static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh); /* * Test whether an inode is a fast symlink. @@ -172,6 +179,7 @@ void ext4_evict_inode(struct inode *inode) handle_t *handle; int err; + trace_ext4_evict_inode(inode); if (inode->i_nlink) { truncate_inode_pages(&inode->i_data, 0); goto no_delete; @@ -755,6 +763,11 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode, * parent to disk. */ bh = sb_getblk(inode->i_sb, new_blocks[n-1]); + if (unlikely(!bh)) { + err = -EIO; + goto failed; + } + branch[n].bh = bh; lock_buffer(bh); BUFFER_TRACE(bh, "call get_create_access"); @@ -1207,8 +1220,10 @@ static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx, break; idx++; num++; - if (num >= max_pages) + if (num >= max_pages) { + done = 1; break; + } } pagevec_release(&pvec); } @@ -1538,10 +1553,10 @@ static int do_journal_get_write_access(handle_t *handle, if (!buffer_mapped(bh) || buffer_freed(bh)) return 0; /* - * __block_prepare_write() could have dirtied some buffers. Clean + * __block_write_begin() could have dirtied some buffers. Clean * the dirty bit as jbd2_journal_get_write_access() could complain * otherwise about fs integrity issues. Setting of the dirty bit - * by __block_prepare_write() isn't a real problem here as we clear + * by __block_write_begin() isn't a real problem here as we clear * the bit before releasing a page lock and thus writeback cannot * ever write the buffer. */ @@ -1995,16 +2010,23 @@ static void ext4_da_page_release_reservation(struct page *page, * * As pages are already locked by write_cache_pages(), we can't use it */ -static int mpage_da_submit_io(struct mpage_da_data *mpd) +static int mpage_da_submit_io(struct mpage_da_data *mpd, + struct ext4_map_blocks *map) { - long pages_skipped; struct pagevec pvec; unsigned long index, end; int ret = 0, err, nr_pages, i; struct inode *inode = mpd->inode; struct address_space *mapping = inode->i_mapping; + loff_t size = i_size_read(inode); + unsigned int len, block_start; + struct buffer_head *bh, *page_bufs = NULL; + int journal_data = ext4_should_journal_data(inode); + sector_t pblock = 0, cur_logical = 0; + struct ext4_io_submit io_submit; BUG_ON(mpd->next_page <= mpd->first_page); + memset(&io_submit, 0, sizeof(io_submit)); /* * We need to start from the first_page to the next_page - 1 * to make sure we also write the mapped dirty buffer_heads. @@ -2020,122 +2042,108 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd) if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { + int commit_write = 0, redirty_page = 0; struct page *page = pvec.pages[i]; index = page->index; if (index > end) break; + + if (index == size >> PAGE_CACHE_SHIFT) + len = size & ~PAGE_CACHE_MASK; + else + len = PAGE_CACHE_SIZE; + if (map) { + cur_logical = index << (PAGE_CACHE_SHIFT - + inode->i_blkbits); + pblock = map->m_pblk + (cur_logical - + map->m_lblk); + } index++; BUG_ON(!PageLocked(page)); BUG_ON(PageWriteback(page)); - pages_skipped = mpd->wbc->pages_skipped; - err = mapping->a_ops->writepage(page, mpd->wbc); - if (!err && (pages_skipped == mpd->wbc->pages_skipped)) - /* - * have successfully written the page - * without skipping the same - */ - mpd->pages_written++; /* - * In error case, we have to continue because - * remaining pages are still locked - * XXX: unlock and re-dirty them? + * If the page does not have buffers (for + * whatever reason), try to create them using + * __block_write_begin. If this fails, + * redirty the page and move on. */ - if (ret == 0) - ret = err; - } - pagevec_release(&pvec); - } - return ret; -} - -/* - * mpage_put_bnr_to_bhs - walk blocks and assign them actual numbers - * - * the function goes through all passed space and put actual disk - * block numbers into buffer heads, dropping BH_Delay and BH_Unwritten - */ -static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, - struct ext4_map_blocks *map) -{ - struct inode *inode = mpd->inode; - struct address_space *mapping = inode->i_mapping; - int blocks = map->m_len; - sector_t pblock = map->m_pblk, cur_logical; - struct buffer_head *head, *bh; - pgoff_t index, end; - struct pagevec pvec; - int nr_pages, i; - - index = map->m_lblk >> (PAGE_CACHE_SHIFT - inode->i_blkbits); - end = (map->m_lblk + blocks - 1) >> (PAGE_CACHE_SHIFT - inode->i_blkbits); - cur_logical = index << (PAGE_CACHE_SHIFT - inode->i_blkbits); - - pagevec_init(&pvec, 0); - - while (index <= end) { - /* XXX: optimize tail */ - nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE); - if (nr_pages == 0) - break; - for (i = 0; i < nr_pages; i++) { - struct page *page = pvec.pages[i]; - - index = page->index; - if (index > end) - break; - index++; - - BUG_ON(!PageLocked(page)); - BUG_ON(PageWriteback(page)); - BUG_ON(!page_has_buffers(page)); - - bh = page_buffers(page); - head = bh; - - /* skip blocks out of the range */ - do { - if (cur_logical >= map->m_lblk) - break; - cur_logical++; - } while ((bh = bh->b_this_page) != head); + if (!page_has_buffers(page)) { + if (__block_write_begin(page, 0, len, + noalloc_get_block_write)) { + redirty_page: + redirty_page_for_writepage(mpd->wbc, + page); + unlock_page(page); + continue; + } + commit_write = 1; + } + bh = page_bufs = page_buffers(page); + block_start = 0; do { - if (cur_logical >= map->m_lblk + blocks) - break; - - if (buffer_delay(bh) || buffer_unwritten(bh)) { - - BUG_ON(bh->b_bdev != inode->i_sb->s_bdev); - + if (!bh) + goto redirty_page; + if (map && (cur_logical >= map->m_lblk) && + (cur_logical <= (map->m_lblk + + (map->m_len - 1)))) { if (buffer_delay(bh)) { clear_buffer_delay(bh); bh->b_blocknr = pblock; - } else { - /* - * unwritten already should have - * blocknr assigned. Verify that - */ - clear_buffer_unwritten(bh); - BUG_ON(bh->b_blocknr != pblock); } + if (buffer_unwritten(bh) || + buffer_mapped(bh)) + BUG_ON(bh->b_blocknr != pblock); + if (map->m_flags & EXT4_MAP_UNINIT) + set_buffer_uninit(bh); + clear_buffer_unwritten(bh); + } - } else if (buffer_mapped(bh)) - BUG_ON(bh->b_blocknr != pblock); - - if (map->m_flags & EXT4_MAP_UNINIT) - set_buffer_uninit(bh); + /* redirty page if block allocation undone */ + if (buffer_delay(bh) || buffer_unwritten(bh)) + redirty_page = 1; + bh = bh->b_this_page; + block_start += bh->b_size; cur_logical++; pblock++; - } while ((bh = bh->b_this_page) != head); + } while (bh != page_bufs); + + if (redirty_page) + goto redirty_page; + + if (commit_write) + /* mark the buffer_heads as dirty & uptodate */ + block_commit_write(page, 0, len); + + /* + * Delalloc doesn't support data journalling, + * but eventually maybe we'll lift this + * restriction. + */ + if (unlikely(journal_data && PageChecked(page))) + err = __ext4_journalled_writepage(page, len); + else + err = ext4_bio_write_page(&io_submit, page, + len, mpd->wbc); + + if (!err) + mpd->pages_written++; + /* + * In error case, we have to continue because + * remaining pages are still locked + */ + if (ret == 0) + ret = err; } pagevec_release(&pvec); } + ext4_io_submit(&io_submit); + return ret; } - static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd, sector_t logical, long blk_cnt) { @@ -2187,35 +2195,32 @@ static void ext4_print_free_blocks(struct inode *inode) } /* - * mpage_da_map_blocks - go through given space + * mpage_da_map_and_submit - go through given space, map them + * if necessary, and then submit them for I/O * * @mpd - bh describing space * * The function skips space we know is already mapped to disk blocks. * */ -static int mpage_da_map_blocks(struct mpage_da_data *mpd) +static void mpage_da_map_and_submit(struct mpage_da_data *mpd) { int err, blks, get_blocks_flags; - struct ext4_map_blocks map; + struct ext4_map_blocks map, *mapp = NULL; sector_t next = mpd->b_blocknr; unsigned max_blocks = mpd->b_size >> mpd->inode->i_blkbits; loff_t disksize = EXT4_I(mpd->inode)->i_disksize; handle_t *handle = NULL; /* - * We consider only non-mapped and non-allocated blocks + * If the blocks are mapped already, or we couldn't accumulate + * any blocks, then proceed immediately to the submission stage. */ - if ((mpd->b_state & (1 << BH_Mapped)) && - !(mpd->b_state & (1 << BH_Delay)) && - !(mpd->b_state & (1 << BH_Unwritten))) - return 0; - - /* - * If we didn't accumulate anything to write simply return - */ - if (!mpd->b_size) - return 0; + if ((mpd->b_size == 0) || + ((mpd->b_state & (1 << BH_Mapped)) && + !(mpd->b_state & (1 << BH_Delay)) && + !(mpd->b_state & (1 << BH_Unwritten)))) + goto submit_io; handle = ext4_journal_current_handle(); BUG_ON(!handle); @@ -2252,17 +2257,18 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd) err = blks; /* - * If get block returns with error we simply - * return. Later writepage will redirty the page and - * writepages will find the dirty page again + * If get block returns EAGAIN or ENOSPC and there + * appears to be free blocks we will call + * ext4_writepage() for all of the pages which will + * just redirty the pages. */ if (err == -EAGAIN) - return 0; + goto submit_io; if (err == -ENOSPC && ext4_count_free_blocks(sb)) { mpd->retval = err; - return 0; + goto submit_io; } /* @@ -2287,10 +2293,11 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd) /* invalidate all the pages */ ext4_da_block_invalidatepages(mpd, next, mpd->b_size >> mpd->inode->i_blkbits); - return err; + return; } BUG_ON(blks == 0); + mapp = ↦ if (map.m_flags & EXT4_MAP_NEW) { struct block_device *bdev = mpd->inode->i_sb->s_bdev; int i; @@ -2299,18 +2306,11 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd) unmap_underlying_metadata(bdev, map.m_pblk + i); } - /* - * If blocks are delayed marked, we need to - * put actual blocknr and drop delayed bit - */ - if ((mpd->b_state & (1 << BH_Delay)) || - (mpd->b_state & (1 << BH_Unwritten))) - mpage_put_bnr_to_bhs(mpd, &map); - if (ext4_should_order_data(mpd->inode)) { err = ext4_jbd2_file_inode(handle, mpd->inode); if (err) - return err; + /* This only happens if the journal is aborted */ + return; } /* @@ -2321,10 +2321,16 @@ static int mpage_da_map_blocks(struct mpage_da_data *mpd) disksize = i_size_read(mpd->inode); if (disksize > EXT4_I(mpd->inode)->i_disksize) { ext4_update_i_disksize(mpd->inode, disksize); - return ext4_mark_inode_dirty(handle, mpd->inode); + err = ext4_mark_inode_dirty(handle, mpd->inode); + if (err) + ext4_error(mpd->inode->i_sb, + "Failed to mark inode %lu dirty", + mpd->inode->i_ino); } - return 0; +submit_io: + mpage_da_submit_io(mpd, mapp); + mpd->io_done = 1; } #define BH_FLAGS ((1 << BH_Uptodate) | (1 << BH_Mapped) | \ @@ -2401,9 +2407,7 @@ flush_it: * We couldn't merge the block to our extent, so we * need to flush current extent and start new one */ - if (mpage_da_map_blocks(mpd) == 0) - mpage_da_submit_io(mpd); - mpd->io_done = 1; + mpage_da_map_and_submit(mpd); return; } @@ -2422,9 +2426,9 @@ static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh) * The function finds extents of pages and scan them for all blocks. */ static int __mpage_da_writepage(struct page *page, - struct writeback_control *wbc, void *data) + struct writeback_control *wbc, + struct mpage_da_data *mpd) { - struct mpage_da_data *mpd = data; struct inode *inode = mpd->inode; struct buffer_head *bh, *head; sector_t logical; @@ -2435,15 +2439,13 @@ static int __mpage_da_writepage(struct page *page, if (mpd->next_page != page->index) { /* * Nope, we can't. So, we map non-allocated blocks - * and start IO on them using writepage() + * and start IO on them */ if (mpd->next_page != mpd->first_page) { - if (mpage_da_map_blocks(mpd) == 0) - mpage_da_submit_io(mpd); + mpage_da_map_and_submit(mpd); /* * skip rest of the page in the page_vec */ - mpd->io_done = 1; redirty_page_for_writepage(wbc, page); unlock_page(page); return MPAGE_DA_EXTENT_TAIL; @@ -2550,8 +2552,7 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, if (buffer_delay(bh)) return 0; /* Not sure this could or should happen */ /* - * XXX: __block_prepare_write() unmaps passed block, - * is it OK? + * XXX: __block_write_begin() unmaps passed block, is it OK? */ ret = ext4_da_reserve_space(inode, iblock); if (ret) @@ -2583,7 +2584,7 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, /* * This function is used as a standard get_block_t calback function * when there is no desire to allocate any blocks. It is used as a - * callback function for block_prepare_write() and block_write_full_page(). + * callback function for block_write_begin() and block_write_full_page(). * These functions should only try to map a single block at a time. * * Since this function doesn't do block allocations even if the caller @@ -2623,6 +2624,7 @@ static int __ext4_journalled_writepage(struct page *page, int ret = 0; int err; + ClearPageChecked(page); page_bufs = page_buffers(page); BUG_ON(!page_bufs); walk_page_buffers(handle, page_bufs, 0, len, NULL, bget_one); @@ -2700,7 +2702,7 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate); static int ext4_writepage(struct page *page, struct writeback_control *wbc) { - int ret = 0; + int ret = 0, commit_write = 0; loff_t size; unsigned int len; struct buffer_head *page_bufs = NULL; @@ -2713,71 +2715,44 @@ static int ext4_writepage(struct page *page, else len = PAGE_CACHE_SIZE; - if (page_has_buffers(page)) { - page_bufs = page_buffers(page); - if (walk_page_buffers(NULL, page_bufs, 0, len, NULL, - ext4_bh_delay_or_unwritten)) { - /* - * We don't want to do block allocation - * So redirty the page and return - * We may reach here when we do a journal commit - * via journal_submit_inode_data_buffers. - * If we don't have mapping block we just ignore - * them. We can also reach here via shrink_page_list - */ + /* + * If the page does not have buffers (for whatever reason), + * try to create them using __block_write_begin. If this + * fails, redirty the page and move on. + */ + if (!page_has_buffers(page)) { + if (__block_write_begin(page, 0, len, + noalloc_get_block_write)) { + redirty_page: redirty_page_for_writepage(wbc, page); unlock_page(page); return 0; } - } else { + commit_write = 1; + } + page_bufs = page_buffers(page); + if (walk_page_buffers(NULL, page_bufs, 0, len, NULL, + ext4_bh_delay_or_unwritten)) { /* - * The test for page_has_buffers() is subtle: - * We know the page is dirty but it lost buffers. That means - * that at some moment in time after write_begin()/write_end() - * has been called all buffers have been clean and thus they - * must have been written at least once. So they are all - * mapped and we can happily proceed with mapping them - * and writing the page. - * - * Try to initialize the buffer_heads and check whether - * all are mapped and non delay. We don't want to - * do block allocation here. + * We don't want to do block allocation, so redirty + * the page and return. We may reach here when we do + * a journal commit via journal_submit_inode_data_buffers. + * We can also reach here via shrink_page_list */ - ret = block_prepare_write(page, 0, len, - noalloc_get_block_write); - if (!ret) { - page_bufs = page_buffers(page); - /* check whether all are mapped and non delay */ - if (walk_page_buffers(NULL, page_bufs, 0, len, NULL, - ext4_bh_delay_or_unwritten)) { - redirty_page_for_writepage(wbc, page); - unlock_page(page); - return 0; - } - } else { - /* - * We can't do block allocation here - * so just redity the page and unlock - * and return - */ - redirty_page_for_writepage(wbc, page); - unlock_page(page); - return 0; - } + goto redirty_page; + } + if (commit_write) /* now mark the buffer_heads as dirty and uptodate */ block_commit_write(page, 0, len); - } - if (PageChecked(page) && ext4_should_journal_data(inode)) { + if (PageChecked(page) && ext4_should_journal_data(inode)) /* * It's mmapped pagecache. Add buffers and journal it. There * doesn't seem much point in redirtying the page here. */ - ClearPageChecked(page); return __ext4_journalled_writepage(page, len); - } - if (page_bufs && buffer_uninit(page_bufs)) { + if (buffer_uninit(page_bufs)) { ext4_set_bh_endio(page_bufs, inode); ret = block_write_full_page_endio(page, noalloc_get_block_write, wbc, ext4_end_io_buffer_write); @@ -2824,25 +2799,32 @@ static int ext4_da_writepages_trans_blocks(struct inode *inode) */ static int write_cache_pages_da(struct address_space *mapping, struct writeback_control *wbc, - struct mpage_da_data *mpd) + struct mpage_da_data *mpd, + pgoff_t *done_index) { int ret = 0; int done = 0; struct pagevec pvec; - int nr_pages; + unsigned nr_pages; pgoff_t index; pgoff_t end; /* Inclusive */ long nr_to_write = wbc->nr_to_write; + int tag; pagevec_init(&pvec, 0); index = wbc->range_start >> PAGE_CACHE_SHIFT; end = wbc->range_end >> PAGE_CACHE_SHIFT; + if (wbc->sync_mode == WB_SYNC_ALL) + tag = PAGECACHE_TAG_TOWRITE; + else + tag = PAGECACHE_TAG_DIRTY; + + *done_index = index; while (!done && (index <= end)) { int i; - nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, - PAGECACHE_TAG_DIRTY, + nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag, min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); if (nr_pages == 0) break; @@ -2862,6 +2844,8 @@ static int write_cache_pages_da(struct address_space *mapping, break; } + *done_index = page->index + 1; + lock_page(page); /* @@ -2947,6 +2931,8 @@ static int ext4_da_writepages(struct address_space *mapping, long desired_nr_to_write, nr_to_writebump = 0; loff_t range_start = wbc->range_start; struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb); + pgoff_t done_index = 0; + pgoff_t end; trace_ext4_da_writepages(inode, wbc); @@ -2982,8 +2968,11 @@ static int ext4_da_writepages(struct address_space *mapping, wbc->range_start = index << PAGE_CACHE_SHIFT; wbc->range_end = LLONG_MAX; wbc->range_cyclic = 0; - } else + end = -1; + } else { index = wbc->range_start >> PAGE_CACHE_SHIFT; + end = wbc->range_end >> PAGE_CACHE_SHIFT; + } /* * This works around two forms of stupidity. The first is in @@ -3002,9 +2991,12 @@ static int ext4_da_writepages(struct address_space *mapping, * sbi->max_writeback_mb_bump whichever is smaller. */ max_pages = sbi->s_max_writeback_mb_bump << (20 - PAGE_CACHE_SHIFT); - if (!range_cyclic && range_whole) - desired_nr_to_write = wbc->nr_to_write * 8; - else + if (!range_cyclic && range_whole) { + if (wbc->nr_to_write == LONG_MAX) + desired_nr_to_write = wbc->nr_to_write; + else + desired_nr_to_write = wbc->nr_to_write * 8; + } else desired_nr_to_write = ext4_num_dirty_pages(inode, index, max_pages); if (desired_nr_to_write > max_pages) @@ -3021,6 +3013,9 @@ static int ext4_da_writepages(struct address_space *mapping, pages_skipped = wbc->pages_skipped; retry: + if (wbc->sync_mode == WB_SYNC_ALL) + tag_pages_for_writeback(mapping, index, end); + while (!ret && wbc->nr_to_write > 0) { /* @@ -3059,16 +3054,14 @@ retry: mpd.io_done = 0; mpd.pages_written = 0; mpd.retval = 0; - ret = write_cache_pages_da(mapping, wbc, &mpd); + ret = write_cache_pages_da(mapping, wbc, &mpd, &done_index); /* * If we have a contiguous extent of pages and we * haven't done the I/O yet, map the blocks and submit * them for I/O. */ if (!mpd.io_done && mpd.next_page != mpd.first_page) { - if (mpage_da_map_blocks(&mpd) == 0) - mpage_da_submit_io(&mpd); - mpd.io_done = 1; + mpage_da_map_and_submit(&mpd); ret = MPAGE_DA_EXTENT_TAIL; } trace_ext4_da_write_pages(inode, &mpd); @@ -3115,14 +3108,13 @@ retry: __func__, wbc->nr_to_write, ret); /* Update index */ - index += pages_written; wbc->range_cyclic = range_cyclic; if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) /* * set the writeback_index so that range_cyclic * mode will write it back later */ - mapping->writeback_index = index; + mapping->writeback_index = done_index; out_writepages: wbc->nr_to_write -= nr_to_writebump; @@ -3457,15 +3449,6 @@ ext4_readpages(struct file *file, struct address_space *mapping, return mpage_readpages(mapping, pages, nr_pages, ext4_get_block); } -static void ext4_free_io_end(ext4_io_end_t *io) -{ - BUG_ON(!io); - if (io->page) - put_page(io->page); - iput(io->inode); - kfree(io); -} - static void ext4_invalidatepage_free_endio(struct page *page, unsigned long offset) { struct buffer_head *head, *bh; @@ -3642,173 +3625,6 @@ static int ext4_get_block_write(struct inode *inode, sector_t iblock, EXT4_GET_BLOCKS_IO_CREATE_EXT); } -static void dump_completed_IO(struct inode * inode) -{ -#ifdef EXT4_DEBUG - struct list_head *cur, *before, *after; - ext4_io_end_t *io, *io0, *io1; - unsigned long flags; - - if (list_empty(&EXT4_I(inode)->i_completed_io_list)){ - ext4_debug("inode %lu completed_io list is empty\n", inode->i_ino); - return; - } - - ext4_debug("Dump inode %lu completed_io list \n", inode->i_ino); - spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags); - list_for_each_entry(io, &EXT4_I(inode)->i_completed_io_list, list){ - cur = &io->list; - before = cur->prev; - io0 = container_of(before, ext4_io_end_t, list); - after = cur->next; - io1 = container_of(after, ext4_io_end_t, list); - - ext4_debug("io 0x%p from inode %lu,prev 0x%p,next 0x%p\n", - io, inode->i_ino, io0, io1); - } - spin_unlock_irqrestore(&EXT4_I(inode)->i_completed_io_lock, flags); -#endif -} - -/* - * check a range of space and convert unwritten extents to written. - */ -static int ext4_end_io_nolock(ext4_io_end_t *io) -{ - struct inode *inode = io->inode; - loff_t offset = io->offset; - ssize_t size = io->size; - int ret = 0; - - ext4_debug("ext4_end_io_nolock: io 0x%p from inode %lu,list->next 0x%p," - "list->prev 0x%p\n", - io, inode->i_ino, io->list.next, io->list.prev); - - if (list_empty(&io->list)) - return ret; - - if (io->flag != EXT4_IO_UNWRITTEN) - return ret; - - ret = ext4_convert_unwritten_extents(inode, offset, size); - if (ret < 0) { - printk(KERN_EMERG "%s: failed to convert unwritten" - "extents to written extents, error is %d" - " io is still on inode %lu aio dio list\n", - __func__, ret, inode->i_ino); - return ret; - } - - if (io->iocb) - aio_complete(io->iocb, io->result, 0); - /* clear the DIO AIO unwritten flag */ - io->flag = 0; - return ret; -} - -/* - * work on completed aio dio IO, to convert unwritten extents to extents - */ -static void ext4_end_io_work(struct work_struct *work) -{ - ext4_io_end_t *io = container_of(work, ext4_io_end_t, work); - struct inode *inode = io->inode; - struct ext4_inode_info *ei = EXT4_I(inode); - unsigned long flags; - int ret; - - mutex_lock(&inode->i_mutex); - ret = ext4_end_io_nolock(io); - if (ret < 0) { - mutex_unlock(&inode->i_mutex); - return; - } - - spin_lock_irqsave(&ei->i_completed_io_lock, flags); - if (!list_empty(&io->list)) - list_del_init(&io->list); - spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); - mutex_unlock(&inode->i_mutex); - ext4_free_io_end(io); -} - -/* - * This function is called from ext4_sync_file(). - * - * When IO is completed, the work to convert unwritten extents to - * written is queued on workqueue but may not get immediately - * scheduled. When fsync is called, we need to ensure the - * conversion is complete before fsync returns. - * The inode keeps track of a list of pending/completed IO that - * might needs to do the conversion. This function walks through - * the list and convert the related unwritten extents for completed IO - * to written. - * The function return the number of pending IOs on success. - */ -int flush_completed_IO(struct inode *inode) -{ - ext4_io_end_t *io; - struct ext4_inode_info *ei = EXT4_I(inode); - unsigned long flags; - int ret = 0; - int ret2 = 0; - - if (list_empty(&ei->i_completed_io_list)) - return ret; - - dump_completed_IO(inode); - spin_lock_irqsave(&ei->i_completed_io_lock, flags); - while (!list_empty(&ei->i_completed_io_list)){ - io = list_entry(ei->i_completed_io_list.next, - ext4_io_end_t, list); - /* - * Calling ext4_end_io_nolock() to convert completed - * IO to written. - * - * When ext4_sync_file() is called, run_queue() may already - * about to flush the work corresponding to this io structure. - * It will be upset if it founds the io structure related - * to the work-to-be schedule is freed. - * - * Thus we need to keep the io structure still valid here after - * convertion finished. The io structure has a flag to - * avoid double converting from both fsync and background work - * queue work. - */ - spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); - ret = ext4_end_io_nolock(io); - spin_lock_irqsave(&ei->i_completed_io_lock, flags); - if (ret < 0) - ret2 = ret; - else - list_del_init(&io->list); - } - spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); - return (ret2 < 0) ? ret2 : 0; -} - -static ext4_io_end_t *ext4_init_io_end (struct inode *inode, gfp_t flags) -{ - ext4_io_end_t *io = NULL; - - io = kmalloc(sizeof(*io), flags); - - if (io) { - igrab(inode); - io->inode = inode; - io->flag = 0; - io->offset = 0; - io->size = 0; - io->page = NULL; - io->iocb = NULL; - io->result = 0; - INIT_WORK(&io->work, ext4_end_io_work); - INIT_LIST_HEAD(&io->list); - } - - return io; -} - static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, ssize_t size, void *private, int ret, bool is_async) @@ -3828,7 +3644,7 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, size); /* if not aio dio with unwritten extents, just free io and return */ - if (io_end->flag != EXT4_IO_UNWRITTEN){ + if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) { ext4_free_io_end(io_end); iocb->private = NULL; out: @@ -3845,14 +3661,14 @@ out: } wq = EXT4_SB(io_end->inode->i_sb)->dio_unwritten_wq; - /* queue the work to convert unwritten extents to written */ - queue_work(wq, &io_end->work); - /* Add the io_end to per-inode completed aio dio list*/ ei = EXT4_I(io_end->inode); spin_lock_irqsave(&ei->i_completed_io_lock, flags); list_add_tail(&io_end->list, &ei->i_completed_io_list); spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); + + /* queue the work to convert unwritten extents to written */ + queue_work(wq, &io_end->work); iocb->private = NULL; } @@ -3873,7 +3689,7 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate) goto out; } - io_end->flag = EXT4_IO_UNWRITTEN; + io_end->flag = EXT4_IO_END_UNWRITTEN; inode = io_end->inode; /* Add the io_end to per-inode completed io list*/ @@ -5464,6 +5280,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = dentry->d_inode; int error, rc = 0; + int orphan = 0; const unsigned int ia_valid = attr->ia_valid; error = inode_change_ok(inode, attr); @@ -5519,8 +5336,10 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) error = PTR_ERR(handle); goto err_out; } - - error = ext4_orphan_add(handle, inode); + if (ext4_handle_valid(handle)) { + error = ext4_orphan_add(handle, inode); + orphan = 1; + } EXT4_I(inode)->i_disksize = attr->ia_size; rc = ext4_mark_inode_dirty(handle, inode); if (!error) @@ -5538,6 +5357,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) goto err_out; } ext4_orphan_del(handle, inode); + orphan = 0; ext4_journal_stop(handle); goto err_out; } @@ -5560,7 +5380,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) * If the call to ext4_truncate failed to get a transaction handle at * all, we need to clean up the in-core orphan list manually. */ - if (inode->i_nlink) + if (orphan && inode->i_nlink) ext4_orphan_del(NULL, inode); if (!rc && (ia_valid & ATTR_MODE)) @@ -5592,9 +5412,7 @@ int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry, * will return the blocks that include the delayed allocation * blocks for this file. */ - spin_lock(&EXT4_I(inode)->i_block_reservation_lock); delalloc_blocks = EXT4_I(inode)->i_reserved_data_blocks; - spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); stat->blocks += (delalloc_blocks << inode->i_sb->s_blocksize_bits)>>9; return 0; @@ -5643,7 +5461,7 @@ static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk) * * Also account for superblock, inode, quota and xattr blocks */ -int ext4_meta_trans_blocks(struct inode *inode, int nrblocks, int chunk) +static int ext4_meta_trans_blocks(struct inode *inode, int nrblocks, int chunk) { ext4_group_t groups, ngroups = ext4_get_groups_count(inode->i_sb); int gdpblocks; @@ -5831,6 +5649,7 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) int err, ret; might_sleep(); + trace_ext4_mark_inode_dirty(inode, _RET_IP_); err = ext4_reserve_inode_write(handle, inode, &iloc); if (ext4_handle_valid(handle) && EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize && diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index bf5ae883b1bd..eb3bc2fe647e 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -331,6 +331,30 @@ mext_out: return err; } + case FITRIM: + { + struct super_block *sb = inode->i_sb; + struct fstrim_range range; + int ret = 0; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (copy_from_user(&range, (struct fstrim_range *)arg, + sizeof(range))) + return -EFAULT; + + ret = ext4_trim_fs(sb, &range); + if (ret < 0) + return ret; + + if (copy_to_user((struct fstrim_range *)arg, &range, + sizeof(range))) + return -EFAULT; + + return 0; + } + default: return -ENOTTY; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 19aa0d44d822..5b4d4e3a4d58 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -338,6 +338,14 @@ static struct kmem_cache *ext4_pspace_cachep; static struct kmem_cache *ext4_ac_cachep; static struct kmem_cache *ext4_free_ext_cachep; + +/* We create slab caches for groupinfo data structures based on the + * superblock block size. There will be one per mounted filesystem for + * each unique s_blocksize_bits */ +#define NR_GRPINFO_CACHES \ + (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE + 1) +static struct kmem_cache *ext4_groupinfo_caches[NR_GRPINFO_CACHES]; + static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_group_t group); static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, @@ -939,6 +947,85 @@ out: } /* + * lock the group_info alloc_sem of all the groups + * belonging to the same buddy cache page. This + * make sure other parallel operation on the buddy + * cache doesn't happen whild holding the buddy cache + * lock + */ +static int ext4_mb_get_buddy_cache_lock(struct super_block *sb, + ext4_group_t group) +{ + int i; + int block, pnum; + int blocks_per_page; + int groups_per_page; + ext4_group_t ngroups = ext4_get_groups_count(sb); + ext4_group_t first_group; + struct ext4_group_info *grp; + + blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize; + /* + * the buddy cache inode stores the block bitmap + * and buddy information in consecutive blocks. + * So for each group we need two blocks. + */ + block = group * 2; + pnum = block / blocks_per_page; + first_group = pnum * blocks_per_page / 2; + + groups_per_page = blocks_per_page >> 1; + if (groups_per_page == 0) + groups_per_page = 1; + /* read all groups the page covers into the cache */ + for (i = 0; i < groups_per_page; i++) { + + if ((first_group + i) >= ngroups) + break; + grp = ext4_get_group_info(sb, first_group + i); + /* take all groups write allocation + * semaphore. This make sure there is + * no block allocation going on in any + * of that groups + */ + down_write_nested(&grp->alloc_sem, i); + } + return i; +} + +static void ext4_mb_put_buddy_cache_lock(struct super_block *sb, + ext4_group_t group, int locked_group) +{ + int i; + int block, pnum; + int blocks_per_page; + ext4_group_t first_group; + struct ext4_group_info *grp; + + blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize; + /* + * the buddy cache inode stores the block bitmap + * and buddy information in consecutive blocks. + * So for each group we need two blocks. + */ + block = group * 2; + pnum = block / blocks_per_page; + first_group = pnum * blocks_per_page / 2; + /* release locks on all the groups */ + for (i = 0; i < locked_group; i++) { + + grp = ext4_get_group_info(sb, first_group + i); + /* take all groups write allocation + * semaphore. This make sure there is + * no block allocation going on in any + * of that groups + */ + up_write(&grp->alloc_sem); + } + +} + +/* * Locking note: This routine calls ext4_mb_init_cache(), which takes the * block group lock of all groups for this page; do not hold the BG lock when * calling this routine! @@ -1915,84 +2002,6 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac, return 0; } -/* - * lock the group_info alloc_sem of all the groups - * belonging to the same buddy cache page. This - * make sure other parallel operation on the buddy - * cache doesn't happen whild holding the buddy cache - * lock - */ -int ext4_mb_get_buddy_cache_lock(struct super_block *sb, ext4_group_t group) -{ - int i; - int block, pnum; - int blocks_per_page; - int groups_per_page; - ext4_group_t ngroups = ext4_get_groups_count(sb); - ext4_group_t first_group; - struct ext4_group_info *grp; - - blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize; - /* - * the buddy cache inode stores the block bitmap - * and buddy information in consecutive blocks. - * So for each group we need two blocks. - */ - block = group * 2; - pnum = block / blocks_per_page; - first_group = pnum * blocks_per_page / 2; - - groups_per_page = blocks_per_page >> 1; - if (groups_per_page == 0) - groups_per_page = 1; - /* read all groups the page covers into the cache */ - for (i = 0; i < groups_per_page; i++) { - - if ((first_group + i) >= ngroups) - break; - grp = ext4_get_group_info(sb, first_group + i); - /* take all groups write allocation - * semaphore. This make sure there is - * no block allocation going on in any - * of that groups - */ - down_write_nested(&grp->alloc_sem, i); - } - return i; -} - -void ext4_mb_put_buddy_cache_lock(struct super_block *sb, - ext4_group_t group, int locked_group) -{ - int i; - int block, pnum; - int blocks_per_page; - ext4_group_t first_group; - struct ext4_group_info *grp; - - blocks_per_page = PAGE_CACHE_SIZE / sb->s_blocksize; - /* - * the buddy cache inode stores the block bitmap - * and buddy information in consecutive blocks. - * So for each group we need two blocks. - */ - block = group * 2; - pnum = block / blocks_per_page; - first_group = pnum * blocks_per_page / 2; - /* release locks on all the groups */ - for (i = 0; i < locked_group; i++) { - - grp = ext4_get_group_info(sb, first_group + i); - /* take all groups write allocation - * semaphore. This make sure there is - * no block allocation going on in any - * of that groups - */ - up_write(&grp->alloc_sem); - } - -} - static noinline_for_stack int ext4_mb_regular_allocator(struct ext4_allocation_context *ac) { @@ -2233,15 +2242,24 @@ static const struct file_operations ext4_mb_seq_groups_fops = { .release = seq_release, }; +static struct kmem_cache *get_groupinfo_cache(int blocksize_bits) +{ + int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE; + struct kmem_cache *cachep = ext4_groupinfo_caches[cache_index]; + + BUG_ON(!cachep); + return cachep; +} /* Create and initialize ext4_group_info data for the given group. */ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *desc) { - int i, len; + int i; int metalen = 0; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_info **meta_group_info; + struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); /* * First check if this group is the first of a reserved block. @@ -2261,22 +2279,16 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, meta_group_info; } - /* - * calculate needed size. if change bb_counters size, - * don't forget about ext4_mb_generate_buddy() - */ - len = offsetof(typeof(**meta_group_info), - bb_counters[sb->s_blocksize_bits + 2]); - meta_group_info = sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)]; i = group & (EXT4_DESC_PER_BLOCK(sb) - 1); - meta_group_info[i] = kzalloc(len, GFP_KERNEL); + meta_group_info[i] = kmem_cache_alloc(cachep, GFP_KERNEL); if (meta_group_info[i] == NULL) { printk(KERN_ERR "EXT4-fs: can't allocate buddy mem\n"); goto exit_group_info; } + memset(meta_group_info[i], 0, kmem_cache_size(cachep)); set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(meta_group_info[i]->bb_state)); @@ -2331,6 +2343,7 @@ static int ext4_mb_init_backend(struct super_block *sb) int num_meta_group_infos_max; int array_size; struct ext4_group_desc *desc; + struct kmem_cache *cachep; /* This is the number of blocks used by GDT */ num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) - @@ -2373,6 +2386,7 @@ static int ext4_mb_init_backend(struct super_block *sb) printk(KERN_ERR "EXT4-fs: can't get new inode\n"); goto err_freesgi; } + sbi->s_buddy_cache->i_ino = get_next_ino(); EXT4_I(sbi->s_buddy_cache)->i_disksize = 0; for (i = 0; i < ngroups; i++) { desc = ext4_get_group_desc(sb, i, NULL); @@ -2388,8 +2402,9 @@ static int ext4_mb_init_backend(struct super_block *sb) return 0; err_freebuddy: + cachep = get_groupinfo_cache(sb->s_blocksize_bits); while (i-- > 0) - kfree(ext4_get_group_info(sb, i)); + kmem_cache_free(cachep, ext4_get_group_info(sb, i)); i = num_meta_group_infos; while (i-- > 0) kfree(sbi->s_group_info[i]); @@ -2406,19 +2421,48 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery) unsigned offset; unsigned max; int ret; + int cache_index; + struct kmem_cache *cachep; + char *namep = NULL; i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_offsets); sbi->s_mb_offsets = kmalloc(i, GFP_KERNEL); if (sbi->s_mb_offsets == NULL) { - return -ENOMEM; + ret = -ENOMEM; + goto out; } i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_maxs); sbi->s_mb_maxs = kmalloc(i, GFP_KERNEL); if (sbi->s_mb_maxs == NULL) { - kfree(sbi->s_mb_offsets); - return -ENOMEM; + ret = -ENOMEM; + goto out; + } + + cache_index = sb->s_blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE; + cachep = ext4_groupinfo_caches[cache_index]; + if (!cachep) { + char name[32]; + int len = offsetof(struct ext4_group_info, + bb_counters[sb->s_blocksize_bits + 2]); + + sprintf(name, "ext4_groupinfo_%d", sb->s_blocksize_bits); + namep = kstrdup(name, GFP_KERNEL); + if (!namep) { + ret = -ENOMEM; + goto out; + } + + /* Need to free the kmem_cache_name() when we + * destroy the slab */ + cachep = kmem_cache_create(namep, len, 0, + SLAB_RECLAIM_ACCOUNT, NULL); + if (!cachep) { + ret = -ENOMEM; + goto out; + } + ext4_groupinfo_caches[cache_index] = cachep; } /* order 0 is regular bitmap */ @@ -2439,9 +2483,7 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery) /* init file for buddy data */ ret = ext4_mb_init_backend(sb); if (ret != 0) { - kfree(sbi->s_mb_offsets); - kfree(sbi->s_mb_maxs); - return ret; + goto out; } spin_lock_init(&sbi->s_md_lock); @@ -2456,9 +2498,8 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery) sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group); if (sbi->s_locality_groups == NULL) { - kfree(sbi->s_mb_offsets); - kfree(sbi->s_mb_maxs); - return -ENOMEM; + ret = -ENOMEM; + goto out; } for_each_possible_cpu(i) { struct ext4_locality_group *lg; @@ -2475,7 +2516,13 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery) if (sbi->s_journal) sbi->s_journal->j_commit_callback = release_blocks_on_commit; - return 0; +out: + if (ret) { + kfree(sbi->s_mb_offsets); + kfree(sbi->s_mb_maxs); + kfree(namep); + } + return ret; } /* need to called with the ext4 group lock held */ @@ -2503,6 +2550,7 @@ int ext4_mb_release(struct super_block *sb) int num_meta_group_infos; struct ext4_group_info *grinfo; struct ext4_sb_info *sbi = EXT4_SB(sb); + struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); if (sbi->s_group_info) { for (i = 0; i < ngroups; i++) { @@ -2513,7 +2561,7 @@ int ext4_mb_release(struct super_block *sb) ext4_lock_group(sb, i); ext4_mb_cleanup_pa(grinfo); ext4_unlock_group(sb, i); - kfree(grinfo); + kmem_cache_free(cachep, grinfo); } num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> @@ -2557,7 +2605,7 @@ int ext4_mb_release(struct super_block *sb) return 0; } -static inline void ext4_issue_discard(struct super_block *sb, +static inline int ext4_issue_discard(struct super_block *sb, ext4_group_t block_group, ext4_grpblk_t block, int count) { int ret; @@ -2567,10 +2615,11 @@ static inline void ext4_issue_discard(struct super_block *sb, trace_ext4_discard_blocks(sb, (unsigned long long) discard_block, count); ret = sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0); - if (ret == EOPNOTSUPP) { + if (ret == -EOPNOTSUPP) { ext4_warning(sb, "discard not supported, disabling"); clear_opt(EXT4_SB(sb)->s_mount_opt, DISCARD); } + return ret; } /* @@ -2658,28 +2707,22 @@ static void ext4_remove_debugfs_entry(void) #endif -int __init init_ext4_mballoc(void) +int __init ext4_init_mballoc(void) { - ext4_pspace_cachep = - kmem_cache_create("ext4_prealloc_space", - sizeof(struct ext4_prealloc_space), - 0, SLAB_RECLAIM_ACCOUNT, NULL); + ext4_pspace_cachep = KMEM_CACHE(ext4_prealloc_space, + SLAB_RECLAIM_ACCOUNT); if (ext4_pspace_cachep == NULL) return -ENOMEM; - ext4_ac_cachep = - kmem_cache_create("ext4_alloc_context", - sizeof(struct ext4_allocation_context), - 0, SLAB_RECLAIM_ACCOUNT, NULL); + ext4_ac_cachep = KMEM_CACHE(ext4_allocation_context, + SLAB_RECLAIM_ACCOUNT); if (ext4_ac_cachep == NULL) { kmem_cache_destroy(ext4_pspace_cachep); return -ENOMEM; } - ext4_free_ext_cachep = - kmem_cache_create("ext4_free_block_extents", - sizeof(struct ext4_free_data), - 0, SLAB_RECLAIM_ACCOUNT, NULL); + ext4_free_ext_cachep = KMEM_CACHE(ext4_free_data, + SLAB_RECLAIM_ACCOUNT); if (ext4_free_ext_cachep == NULL) { kmem_cache_destroy(ext4_pspace_cachep); kmem_cache_destroy(ext4_ac_cachep); @@ -2689,8 +2732,9 @@ int __init init_ext4_mballoc(void) return 0; } -void exit_ext4_mballoc(void) +void ext4_exit_mballoc(void) { + int i; /* * Wait for completion of call_rcu()'s on ext4_pspace_cachep * before destroying the slab cache. @@ -2699,6 +2743,15 @@ void exit_ext4_mballoc(void) kmem_cache_destroy(ext4_pspace_cachep); kmem_cache_destroy(ext4_ac_cachep); kmem_cache_destroy(ext4_free_ext_cachep); + + for (i = 0; i < NR_GRPINFO_CACHES; i++) { + struct kmem_cache *cachep = ext4_groupinfo_caches[i]; + if (cachep) { + char *name = (char *)kmem_cache_name(cachep); + kmem_cache_destroy(cachep); + kfree(name); + } + } ext4_remove_debugfs_entry(); } @@ -3535,8 +3588,7 @@ static int ext4_mb_new_preallocation(struct ext4_allocation_context *ac) */ static noinline_for_stack int ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, - struct ext4_prealloc_space *pa, - struct ext4_allocation_context *ac) + struct ext4_prealloc_space *pa) { struct super_block *sb = e4b->bd_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -3554,11 +3606,6 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, BUG_ON(group != e4b->bd_group && pa->pa_len != 0); end = bit + pa->pa_len; - if (ac) { - ac->ac_sb = sb; - ac->ac_inode = pa->pa_inode; - } - while (bit < end) { bit = mb_find_next_zero_bit(bitmap_bh->b_data, end, bit); if (bit >= end) @@ -3569,16 +3616,9 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, (unsigned) next - bit, (unsigned) group); free += next - bit; - if (ac) { - ac->ac_b_ex.fe_group = group; - ac->ac_b_ex.fe_start = bit; - ac->ac_b_ex.fe_len = next - bit; - ac->ac_b_ex.fe_logical = 0; - trace_ext4_mballoc_discard(ac); - } - - trace_ext4_mb_release_inode_pa(sb, ac, pa, grp_blk_start + bit, - next - bit); + trace_ext4_mballoc_discard(sb, NULL, group, bit, next - bit); + trace_ext4_mb_release_inode_pa(sb, pa->pa_inode, pa, + grp_blk_start + bit, next - bit); mb_free_blocks(pa->pa_inode, e4b, bit, next - bit); bit = next + 1; } @@ -3601,29 +3641,19 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, static noinline_for_stack int ext4_mb_release_group_pa(struct ext4_buddy *e4b, - struct ext4_prealloc_space *pa, - struct ext4_allocation_context *ac) + struct ext4_prealloc_space *pa) { struct super_block *sb = e4b->bd_sb; ext4_group_t group; ext4_grpblk_t bit; - trace_ext4_mb_release_group_pa(sb, ac, pa); + trace_ext4_mb_release_group_pa(sb, pa); BUG_ON(pa->pa_deleted == 0); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit); BUG_ON(group != e4b->bd_group && pa->pa_len != 0); mb_free_blocks(pa->pa_inode, e4b, bit, pa->pa_len); atomic_add(pa->pa_len, &EXT4_SB(sb)->s_mb_discarded); - - if (ac) { - ac->ac_sb = sb; - ac->ac_inode = NULL; - ac->ac_b_ex.fe_group = group; - ac->ac_b_ex.fe_start = bit; - ac->ac_b_ex.fe_len = pa->pa_len; - ac->ac_b_ex.fe_logical = 0; - trace_ext4_mballoc_discard(ac); - } + trace_ext4_mballoc_discard(sb, NULL, group, bit, pa->pa_len); return 0; } @@ -3644,7 +3674,6 @@ ext4_mb_discard_group_preallocations(struct super_block *sb, struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct buffer_head *bitmap_bh = NULL; struct ext4_prealloc_space *pa, *tmp; - struct ext4_allocation_context *ac; struct list_head list; struct ext4_buddy e4b; int err; @@ -3673,9 +3702,6 @@ ext4_mb_discard_group_preallocations(struct super_block *sb, needed = EXT4_BLOCKS_PER_GROUP(sb) + 1; INIT_LIST_HEAD(&list); - ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS); - if (ac) - ac->ac_sb = sb; repeat: ext4_lock_group(sb, group); list_for_each_entry_safe(pa, tmp, @@ -3730,9 +3756,9 @@ repeat: spin_unlock(pa->pa_obj_lock); if (pa->pa_type == MB_GROUP_PA) - ext4_mb_release_group_pa(&e4b, pa, ac); + ext4_mb_release_group_pa(&e4b, pa); else - ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa, ac); + ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa); list_del(&pa->u.pa_tmp_list); call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback); @@ -3740,8 +3766,6 @@ repeat: out: ext4_unlock_group(sb, group); - if (ac) - kmem_cache_free(ext4_ac_cachep, ac); ext4_mb_unload_buddy(&e4b); put_bh(bitmap_bh); return free; @@ -3762,7 +3786,6 @@ void ext4_discard_preallocations(struct inode *inode) struct super_block *sb = inode->i_sb; struct buffer_head *bitmap_bh = NULL; struct ext4_prealloc_space *pa, *tmp; - struct ext4_allocation_context *ac; ext4_group_t group = 0; struct list_head list; struct ext4_buddy e4b; @@ -3778,11 +3801,6 @@ void ext4_discard_preallocations(struct inode *inode) INIT_LIST_HEAD(&list); - ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS); - if (ac) { - ac->ac_sb = sb; - ac->ac_inode = inode; - } repeat: /* first, collect all pa's in the inode */ spin_lock(&ei->i_prealloc_lock); @@ -3852,7 +3870,7 @@ repeat: ext4_lock_group(sb, group); list_del(&pa->pa_group_list); - ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa, ac); + ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa); ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); @@ -3861,8 +3879,6 @@ repeat: list_del(&pa->u.pa_tmp_list); call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback); } - if (ac) - kmem_cache_free(ext4_ac_cachep, ac); } /* @@ -4060,14 +4076,10 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb, struct ext4_buddy e4b; struct list_head discard_list; struct ext4_prealloc_space *pa, *tmp; - struct ext4_allocation_context *ac; mb_debug(1, "discard locality group preallocation\n"); INIT_LIST_HEAD(&discard_list); - ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS); - if (ac) - ac->ac_sb = sb; spin_lock(&lg->lg_prealloc_lock); list_for_each_entry_rcu(pa, &lg->lg_prealloc_list[order], @@ -4119,15 +4131,13 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb, } ext4_lock_group(sb, group); list_del(&pa->pa_group_list); - ext4_mb_release_group_pa(&e4b, pa, ac); + ext4_mb_release_group_pa(&e4b, pa); ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); list_del(&pa->u.pa_tmp_list); call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback); } - if (ac) - kmem_cache_free(ext4_ac_cachep, ac); } /* @@ -4491,7 +4501,6 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, { struct buffer_head *bitmap_bh = NULL; struct super_block *sb = inode->i_sb; - struct ext4_allocation_context *ac = NULL; struct ext4_group_desc *gdp; unsigned long freed = 0; unsigned int overflow; @@ -4531,6 +4540,8 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, if (!bh) tbh = sb_find_get_block(inode->i_sb, block + i); + if (unlikely(!tbh)) + continue; ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA, inode, tbh, block + i); } @@ -4546,12 +4557,6 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, if (!ext4_should_writeback_data(inode)) flags |= EXT4_FREE_BLOCKS_METADATA; - ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS); - if (ac) { - ac->ac_inode = inode; - ac->ac_sb = sb; - } - do_more: overflow = 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); @@ -4609,12 +4614,7 @@ do_more: BUG_ON(!mb_test_bit(bit + i, bitmap_bh->b_data)); } #endif - if (ac) { - ac->ac_b_ex.fe_group = block_group; - ac->ac_b_ex.fe_start = bit; - ac->ac_b_ex.fe_len = count; - trace_ext4_mballoc_free(ac); - } + trace_ext4_mballoc_free(sb, inode, block_group, bit, count); err = ext4_mb_load_buddy(sb, block_group, &e4b); if (err) @@ -4644,8 +4644,6 @@ do_more: mb_clear_bits(bitmap_bh->b_data, bit, count); mb_free_blocks(inode, &e4b, bit, count); ext4_mb_return_to_preallocation(inode, &e4b, block, count); - if (test_opt(sb, DISCARD)) - ext4_issue_discard(sb, block_group, bit, count); } ret = ext4_free_blks_count(sb, gdp) + count; @@ -4685,7 +4683,190 @@ error_return: dquot_free_block(inode, freed); brelse(bitmap_bh); ext4_std_error(sb, err); - if (ac) - kmem_cache_free(ext4_ac_cachep, ac); return; } + +/** + * ext4_trim_extent -- function to TRIM one single free extent in the group + * @sb: super block for the file system + * @start: starting block of the free extent in the alloc. group + * @count: number of blocks to TRIM + * @group: alloc. group we are working with + * @e4b: ext4 buddy for the group + * + * Trim "count" blocks starting at "start" in the "group". To assure that no + * one will allocate those blocks, mark it as used in buddy bitmap. This must + * be called with under the group lock. + */ +static int ext4_trim_extent(struct super_block *sb, int start, int count, + ext4_group_t group, struct ext4_buddy *e4b) +{ + struct ext4_free_extent ex; + int ret = 0; + + assert_spin_locked(ext4_group_lock_ptr(sb, group)); + + ex.fe_start = start; + ex.fe_group = group; + ex.fe_len = count; + + /* + * Mark blocks used, so no one can reuse them while + * being trimmed. + */ + mb_mark_used(e4b, &ex); + ext4_unlock_group(sb, group); + + ret = ext4_issue_discard(sb, group, start, count); + if (ret) + ext4_std_error(sb, ret); + + ext4_lock_group(sb, group); + mb_free_blocks(NULL, e4b, start, ex.fe_len); + return ret; +} + +/** + * ext4_trim_all_free -- function to trim all free space in alloc. group + * @sb: super block for file system + * @e4b: ext4 buddy + * @start: first group block to examine + * @max: last group block to examine + * @minblocks: minimum extent block count + * + * ext4_trim_all_free walks through group's buddy bitmap searching for free + * extents. When the free block is found, ext4_trim_extent is called to TRIM + * the extent. + * + * + * ext4_trim_all_free walks through group's block bitmap searching for free + * extents. When the free extent is found, mark it as used in group buddy + * bitmap. Then issue a TRIM command on this extent and free the extent in + * the group buddy bitmap. This is done until whole group is scanned. + */ +ext4_grpblk_t ext4_trim_all_free(struct super_block *sb, struct ext4_buddy *e4b, + ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks) +{ + void *bitmap; + ext4_grpblk_t next, count = 0; + ext4_group_t group; + int ret = 0; + + BUG_ON(e4b == NULL); + + bitmap = e4b->bd_bitmap; + group = e4b->bd_group; + start = (e4b->bd_info->bb_first_free > start) ? + e4b->bd_info->bb_first_free : start; + ext4_lock_group(sb, group); + + while (start < max) { + start = mb_find_next_zero_bit(bitmap, max, start); + if (start >= max) + break; + next = mb_find_next_bit(bitmap, max, start); + + if ((next - start) >= minblocks) { + ret = ext4_trim_extent(sb, start, + next - start, group, e4b); + if (ret < 0) + break; + count += next - start; + } + start = next + 1; + + if (fatal_signal_pending(current)) { + count = -ERESTARTSYS; + break; + } + + if (need_resched()) { + ext4_unlock_group(sb, group); + cond_resched(); + ext4_lock_group(sb, group); + } + + if ((e4b->bd_info->bb_free - count) < minblocks) + break; + } + ext4_unlock_group(sb, group); + + ext4_debug("trimmed %d blocks in the group %d\n", + count, group); + + if (ret < 0) + count = ret; + + return count; +} + +/** + * ext4_trim_fs() -- trim ioctl handle function + * @sb: superblock for filesystem + * @range: fstrim_range structure + * + * start: First Byte to trim + * len: number of Bytes to trim from start + * minlen: minimum extent length in Bytes + * ext4_trim_fs goes through all allocation groups containing Bytes from + * start to start+len. For each such a group ext4_trim_all_free function + * is invoked to trim all free space. + */ +int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) +{ + struct ext4_buddy e4b; + ext4_group_t first_group, last_group; + ext4_group_t group, ngroups = ext4_get_groups_count(sb); + ext4_grpblk_t cnt = 0, first_block, last_block; + uint64_t start, len, minlen, trimmed; + int ret = 0; + + start = range->start >> sb->s_blocksize_bits; + len = range->len >> sb->s_blocksize_bits; + minlen = range->minlen >> sb->s_blocksize_bits; + trimmed = 0; + + if (unlikely(minlen > EXT4_BLOCKS_PER_GROUP(sb))) + return -EINVAL; + + /* Determine first and last group to examine based on start and len */ + ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) start, + &first_group, &first_block); + ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) (start + len), + &last_group, &last_block); + last_group = (last_group > ngroups - 1) ? ngroups - 1 : last_group; + last_block = EXT4_BLOCKS_PER_GROUP(sb); + + if (first_group > last_group) + return -EINVAL; + + for (group = first_group; group <= last_group; group++) { + ret = ext4_mb_load_buddy(sb, group, &e4b); + if (ret) { + ext4_error(sb, "Error in loading buddy " + "information for %u", group); + break; + } + + if (len >= EXT4_BLOCKS_PER_GROUP(sb)) + len -= (EXT4_BLOCKS_PER_GROUP(sb) - first_block); + else + last_block = len; + + if (e4b.bd_info->bb_free >= minlen) { + cnt = ext4_trim_all_free(sb, &e4b, first_block, + last_block, minlen); + if (cnt < 0) { + ret = cnt; + ext4_mb_unload_buddy(&e4b); + break; + } + } + ext4_mb_unload_buddy(&e4b); + trimmed += cnt; + first_block = 0; + } + range->len = trimmed * sb->s_blocksize; + + return ret; +} diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 1765c2c50a9b..25f3a974b725 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -412,7 +412,7 @@ static int free_ext_idx(handle_t *handle, struct inode *inode, struct buffer_head *bh; struct ext4_extent_header *eh; - block = idx_pblock(ix); + block = ext4_idx_pblock(ix); bh = sb_bread(inode->i_sb, block); if (!bh) return -EIO; diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 5f1ed9fc913c..b9f3e7862f13 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -85,7 +85,7 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path, if (EXT_LAST_EXTENT(path[ppos].p_hdr) > path[ppos].p_ext) { /* leaf block */ *extent = ++path[ppos].p_ext; - path[ppos].p_block = ext_pblock(path[ppos].p_ext); + path[ppos].p_block = ext4_ext_pblock(path[ppos].p_ext); return 0; } @@ -96,7 +96,7 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path, /* index block */ path[ppos].p_idx++; - path[ppos].p_block = idx_pblock(path[ppos].p_idx); + path[ppos].p_block = ext4_idx_pblock(path[ppos].p_idx); if (path[ppos+1].p_bh) brelse(path[ppos+1].p_bh); path[ppos+1].p_bh = @@ -111,7 +111,7 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path, path[cur_ppos].p_idx = EXT_FIRST_INDEX(path[cur_ppos].p_hdr); path[cur_ppos].p_block = - idx_pblock(path[cur_ppos].p_idx); + ext4_idx_pblock(path[cur_ppos].p_idx); if (path[cur_ppos+1].p_bh) brelse(path[cur_ppos+1].p_bh); path[cur_ppos+1].p_bh = sb_bread(inode->i_sb, @@ -133,7 +133,7 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path, path[leaf_ppos].p_ext = *extent = EXT_FIRST_EXTENT(path[leaf_ppos].p_hdr); path[leaf_ppos].p_block = - ext_pblock(path[leaf_ppos].p_ext); + ext4_ext_pblock(path[leaf_ppos].p_ext); return 0; } } @@ -249,7 +249,7 @@ mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode, */ o_end->ee_block = end_ext->ee_block; o_end->ee_len = end_ext->ee_len; - ext4_ext_store_pblock(o_end, ext_pblock(end_ext)); + ext4_ext_store_pblock(o_end, ext4_ext_pblock(end_ext)); } o_start->ee_len = start_ext->ee_len; @@ -276,7 +276,7 @@ mext_insert_across_blocks(handle_t *handle, struct inode *orig_inode, */ o_end->ee_block = end_ext->ee_block; o_end->ee_len = end_ext->ee_len; - ext4_ext_store_pblock(o_end, ext_pblock(end_ext)); + ext4_ext_store_pblock(o_end, ext4_ext_pblock(end_ext)); /* * Set 0 to the extent block if new_ext was @@ -361,7 +361,7 @@ mext_insert_inside_block(struct ext4_extent *o_start, /* Insert new entry */ if (new_ext->ee_len) { o_start[i] = *new_ext; - ext4_ext_store_pblock(&o_start[i++], ext_pblock(new_ext)); + ext4_ext_store_pblock(&o_start[i++], ext4_ext_pblock(new_ext)); } /* Insert end entry */ @@ -488,7 +488,7 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode, start_ext.ee_len = end_ext.ee_len = 0; new_ext.ee_block = cpu_to_le32(*from); - ext4_ext_store_pblock(&new_ext, ext_pblock(dext)); + ext4_ext_store_pblock(&new_ext, ext4_ext_pblock(dext)); new_ext.ee_len = dext->ee_len; new_ext_alen = ext4_ext_get_actual_len(&new_ext); new_ext_end = le32_to_cpu(new_ext.ee_block) + new_ext_alen - 1; @@ -553,7 +553,7 @@ mext_leaf_block(handle_t *handle, struct inode *orig_inode, copy_extent_status(oext, &end_ext); end_ext_alen = ext4_ext_get_actual_len(&end_ext); ext4_ext_store_pblock(&end_ext, - (ext_pblock(o_end) + oext_alen - end_ext_alen)); + (ext4_ext_pblock(o_end) + oext_alen - end_ext_alen)); end_ext.ee_block = cpu_to_le32(le32_to_cpu(o_end->ee_block) + oext_alen - end_ext_alen); @@ -604,7 +604,7 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext, /* When tmp_dext is too large, pick up the target range. */ diff = donor_off - le32_to_cpu(tmp_dext->ee_block); - ext4_ext_store_pblock(tmp_dext, ext_pblock(tmp_dext) + diff); + ext4_ext_store_pblock(tmp_dext, ext4_ext_pblock(tmp_dext) + diff); tmp_dext->ee_block = cpu_to_le32(le32_to_cpu(tmp_dext->ee_block) + diff); tmp_dext->ee_len = cpu_to_le16(le16_to_cpu(tmp_dext->ee_len) - diff); @@ -613,7 +613,7 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext, tmp_dext->ee_len = cpu_to_le16(max_count); orig_diff = orig_off - le32_to_cpu(tmp_oext->ee_block); - ext4_ext_store_pblock(tmp_oext, ext_pblock(tmp_oext) + orig_diff); + ext4_ext_store_pblock(tmp_oext, ext4_ext_pblock(tmp_oext) + orig_diff); /* Adjust extent length if donor extent is larger than orig */ if (ext4_ext_get_actual_len(tmp_dext) > diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 314c0d3b3fa9..92203b8a099f 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -856,6 +856,7 @@ static struct buffer_head * ext4_find_entry (struct inode *dir, struct buffer_head *bh_use[NAMEI_RA_SIZE]; struct buffer_head *bh, *ret = NULL; ext4_lblk_t start, block, b; + const u8 *name = d_name->name; int ra_max = 0; /* Number of bh's in the readahead buffer, bh_use[] */ int ra_ptr = 0; /* Current index into readahead @@ -870,6 +871,16 @@ static struct buffer_head * ext4_find_entry (struct inode *dir, namelen = d_name->len; if (namelen > EXT4_NAME_LEN) return NULL; + if ((namelen <= 2) && (name[0] == '.') && + (name[1] == '.' || name[1] == '0')) { + /* + * "." or ".." will only be in the first block + * NFS may look up ".."; "." should be handled by the VFS + */ + block = start = 0; + nblocks = 1; + goto restart; + } if (is_dx(dir)) { bh = ext4_dx_find_entry(dir, d_name, res_dir, &err); /* @@ -960,55 +971,35 @@ cleanup_and_exit: static struct buffer_head * ext4_dx_find_entry(struct inode *dir, const struct qstr *d_name, struct ext4_dir_entry_2 **res_dir, int *err) { - struct super_block * sb; + struct super_block * sb = dir->i_sb; struct dx_hash_info hinfo; - u32 hash; struct dx_frame frames[2], *frame; - struct ext4_dir_entry_2 *de, *top; struct buffer_head *bh; ext4_lblk_t block; int retval; - int namelen = d_name->len; - const u8 *name = d_name->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(d_name, dir, &hinfo, frames, err))) - return NULL; - } else { - frame = frames; - frame->bh = NULL; /* for dx_release() */ - frame->at = (struct dx_entry *)frames; /* hack for zero entry*/ - dx_set_block(frame->at, 0); /* dx_root block is 0 */ - } - hash = hinfo.hash; + if (!(frame = dx_probe(d_name, dir, &hinfo, frames, err))) + return NULL; do { block = dx_get_block(frame->at); - if (!(bh = ext4_bread (NULL,dir, block, 0, err))) + if (!(bh = ext4_bread(NULL, dir, block, 0, err))) goto errout; - de = (struct ext4_dir_entry_2 *) bh->b_data; - top = (struct ext4_dir_entry_2 *) ((char *) de + sb->s_blocksize - - EXT4_DIR_REC_LEN(0)); - for (; de < top; de = ext4_next_entry(de, sb->s_blocksize)) { - int off = (block << EXT4_BLOCK_SIZE_BITS(sb)) - + ((char *) de - bh->b_data); - - if (!ext4_check_dir_entry(dir, de, bh, off)) { - brelse(bh); - *err = ERR_BAD_DX_DIR; - goto errout; - } - if (ext4_match(namelen, name, de)) { - *res_dir = de; - dx_release(frames); - return bh; - } + retval = search_dirblock(bh, dir, d_name, + block << EXT4_BLOCK_SIZE_BITS(sb), + res_dir); + if (retval == 1) { /* Success! */ + dx_release(frames); + return bh; } brelse(bh); + if (retval == -1) { + *err = ERR_BAD_DX_DIR; + goto errout; + } + /* Check to see if we should continue to search */ - retval = ext4_htree_next_block(dir, hash, frame, + retval = ext4_htree_next_block(dir, hinfo.hash, frame, frames, NULL); if (retval < 0) { ext4_warning(sb, @@ -2312,7 +2303,7 @@ retry: inode->i_ctime = ext4_current_time(inode); ext4_inc_count(handle, inode); - atomic_inc(&inode->i_count); + ihold(inode); err = ext4_add_entry(handle, dentry, inode); if (!err) { diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c new file mode 100644 index 000000000000..beacce11ac50 --- /dev/null +++ b/fs/ext4/page-io.c @@ -0,0 +1,431 @@ +/* + * linux/fs/ext4/page-io.c + * + * This contains the new page_io functions for ext4 + * + * Written by Theodore Ts'o, 2010. + */ + +#include <linux/module.h> +#include <linux/fs.h> +#include <linux/time.h> +#include <linux/jbd2.h> +#include <linux/highuid.h> +#include <linux/pagemap.h> +#include <linux/quotaops.h> +#include <linux/string.h> +#include <linux/buffer_head.h> +#include <linux/writeback.h> +#include <linux/pagevec.h> +#include <linux/mpage.h> +#include <linux/namei.h> +#include <linux/uio.h> +#include <linux/bio.h> +#include <linux/workqueue.h> +#include <linux/kernel.h> +#include <linux/slab.h> + +#include "ext4_jbd2.h" +#include "xattr.h" +#include "acl.h" +#include "ext4_extents.h" + +static struct kmem_cache *io_page_cachep, *io_end_cachep; + +#define WQ_HASH_SZ 37 +#define to_ioend_wq(v) (&ioend_wq[((unsigned long)v) % WQ_HASH_SZ]) +static wait_queue_head_t ioend_wq[WQ_HASH_SZ]; + +int __init ext4_init_pageio(void) +{ + int i; + + io_page_cachep = KMEM_CACHE(ext4_io_page, SLAB_RECLAIM_ACCOUNT); + if (io_page_cachep == NULL) + return -ENOMEM; + io_end_cachep = KMEM_CACHE(ext4_io_end, SLAB_RECLAIM_ACCOUNT); + if (io_page_cachep == NULL) { + kmem_cache_destroy(io_page_cachep); + return -ENOMEM; + } + for (i = 0; i < WQ_HASH_SZ; i++) + init_waitqueue_head(&ioend_wq[i]); + + return 0; +} + +void ext4_exit_pageio(void) +{ + kmem_cache_destroy(io_end_cachep); + kmem_cache_destroy(io_page_cachep); +} + +void ext4_ioend_wait(struct inode *inode) +{ + wait_queue_head_t *wq = to_ioend_wq(inode); + + wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_ioend_count) == 0)); +} + +static void put_io_page(struct ext4_io_page *io_page) +{ + if (atomic_dec_and_test(&io_page->p_count)) { + end_page_writeback(io_page->p_page); + put_page(io_page->p_page); + kmem_cache_free(io_page_cachep, io_page); + } +} + +void ext4_free_io_end(ext4_io_end_t *io) +{ + int i; + wait_queue_head_t *wq; + + BUG_ON(!io); + if (io->page) + put_page(io->page); + for (i = 0; i < io->num_io_pages; i++) + put_io_page(io->pages[i]); + io->num_io_pages = 0; + wq = to_ioend_wq(io->inode); + if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count) && + waitqueue_active(wq)) + wake_up_all(wq); + kmem_cache_free(io_end_cachep, io); +} + +/* + * check a range of space and convert unwritten extents to written. + */ +int ext4_end_io_nolock(ext4_io_end_t *io) +{ + struct inode *inode = io->inode; + loff_t offset = io->offset; + ssize_t size = io->size; + int ret = 0; + + ext4_debug("ext4_end_io_nolock: io 0x%p from inode %lu,list->next 0x%p," + "list->prev 0x%p\n", + io, inode->i_ino, io->list.next, io->list.prev); + + if (list_empty(&io->list)) + return ret; + + if (!(io->flag & EXT4_IO_END_UNWRITTEN)) + return ret; + + ret = ext4_convert_unwritten_extents(inode, offset, size); + if (ret < 0) { + printk(KERN_EMERG "%s: failed to convert unwritten " + "extents to written extents, error is %d " + "io is still on inode %lu aio dio list\n", + __func__, ret, inode->i_ino); + return ret; + } + + if (io->iocb) + aio_complete(io->iocb, io->result, 0); + /* clear the DIO AIO unwritten flag */ + io->flag &= ~EXT4_IO_END_UNWRITTEN; + return ret; +} + +/* + * work on completed aio dio IO, to convert unwritten extents to extents + */ +static void ext4_end_io_work(struct work_struct *work) +{ + ext4_io_end_t *io = container_of(work, ext4_io_end_t, work); + struct inode *inode = io->inode; + struct ext4_inode_info *ei = EXT4_I(inode); + unsigned long flags; + int ret; + + mutex_lock(&inode->i_mutex); + ret = ext4_end_io_nolock(io); + if (ret < 0) { + mutex_unlock(&inode->i_mutex); + return; + } + + spin_lock_irqsave(&ei->i_completed_io_lock, flags); + if (!list_empty(&io->list)) + list_del_init(&io->list); + spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); + mutex_unlock(&inode->i_mutex); + ext4_free_io_end(io); +} + +ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags) +{ + ext4_io_end_t *io = NULL; + + io = kmem_cache_alloc(io_end_cachep, flags); + if (io) { + memset(io, 0, sizeof(*io)); + atomic_inc(&EXT4_I(inode)->i_ioend_count); + io->inode = inode; + INIT_WORK(&io->work, ext4_end_io_work); + INIT_LIST_HEAD(&io->list); + } + return io; +} + +/* + * Print an buffer I/O error compatible with the fs/buffer.c. This + * provides compatibility with dmesg scrapers that look for a specific + * buffer I/O error message. We really need a unified error reporting + * structure to userspace ala Digital Unix's uerf system, but it's + * probably not going to happen in my lifetime, due to LKML politics... + */ +static void buffer_io_error(struct buffer_head *bh) +{ + char b[BDEVNAME_SIZE]; + printk(KERN_ERR "Buffer I/O error on device %s, logical block %llu\n", + bdevname(bh->b_bdev, b), + (unsigned long long)bh->b_blocknr); +} + +static void ext4_end_bio(struct bio *bio, int error) +{ + ext4_io_end_t *io_end = bio->bi_private; + struct workqueue_struct *wq; + struct inode *inode; + unsigned long flags; + int i; + + BUG_ON(!io_end); + bio->bi_private = NULL; + bio->bi_end_io = NULL; + if (test_bit(BIO_UPTODATE, &bio->bi_flags)) + error = 0; + bio_put(bio); + + for (i = 0; i < io_end->num_io_pages; i++) { + struct page *page = io_end->pages[i]->p_page; + struct buffer_head *bh, *head; + int partial_write = 0; + + head = page_buffers(page); + if (error) + SetPageError(page); + BUG_ON(!head); + if (head->b_size == PAGE_CACHE_SIZE) + clear_buffer_dirty(head); + else { + loff_t offset; + loff_t io_end_offset = io_end->offset + io_end->size; + + offset = (sector_t) page->index << PAGE_CACHE_SHIFT; + bh = head; + do { + if ((offset >= io_end->offset) && + (offset+bh->b_size <= io_end_offset)) { + if (error) + buffer_io_error(bh); + + clear_buffer_dirty(bh); + } + if (buffer_delay(bh)) + partial_write = 1; + else if (!buffer_mapped(bh)) + clear_buffer_dirty(bh); + else if (buffer_dirty(bh)) + partial_write = 1; + offset += bh->b_size; + bh = bh->b_this_page; + } while (bh != head); + } + + /* + * If this is a partial write which happened to make + * all buffers uptodate then we can optimize away a + * bogus readpage() for the next read(). Here we + * 'discover' whether the page went uptodate as a + * result of this (potentially partial) write. + */ + if (!partial_write) + SetPageUptodate(page); + + put_io_page(io_end->pages[i]); + } + io_end->num_io_pages = 0; + inode = io_end->inode; + + if (error) { + io_end->flag |= EXT4_IO_END_ERROR; + ext4_warning(inode->i_sb, "I/O error writing to inode %lu " + "(offset %llu size %ld starting block %llu)", + inode->i_ino, + (unsigned long long) io_end->offset, + (long) io_end->size, + (unsigned long long) + bio->bi_sector >> (inode->i_blkbits - 9)); + } + + /* Add the io_end to per-inode completed io list*/ + spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags); + list_add_tail(&io_end->list, &EXT4_I(inode)->i_completed_io_list); + spin_unlock_irqrestore(&EXT4_I(inode)->i_completed_io_lock, flags); + + wq = EXT4_SB(inode->i_sb)->dio_unwritten_wq; + /* queue the work to convert unwritten extents to written */ + queue_work(wq, &io_end->work); +} + +void ext4_io_submit(struct ext4_io_submit *io) +{ + struct bio *bio = io->io_bio; + + if (bio) { + bio_get(io->io_bio); + submit_bio(io->io_op, io->io_bio); + BUG_ON(bio_flagged(io->io_bio, BIO_EOPNOTSUPP)); + bio_put(io->io_bio); + } + io->io_bio = 0; + io->io_op = 0; + io->io_end = 0; +} + +static int io_submit_init(struct ext4_io_submit *io, + struct inode *inode, + struct writeback_control *wbc, + struct buffer_head *bh) +{ + ext4_io_end_t *io_end; + struct page *page = bh->b_page; + int nvecs = bio_get_nr_vecs(bh->b_bdev); + struct bio *bio; + + io_end = ext4_init_io_end(inode, GFP_NOFS); + if (!io_end) + return -ENOMEM; + do { + bio = bio_alloc(GFP_NOIO, nvecs); + nvecs >>= 1; + } while (bio == NULL); + + bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9); + bio->bi_bdev = bh->b_bdev; + bio->bi_private = io->io_end = io_end; + bio->bi_end_io = ext4_end_bio; + + io_end->offset = (page->index << PAGE_CACHE_SHIFT) + bh_offset(bh); + + io->io_bio = bio; + io->io_op = (wbc->sync_mode == WB_SYNC_ALL ? + WRITE_SYNC_PLUG : WRITE); + io->io_next_block = bh->b_blocknr; + return 0; +} + +static int io_submit_add_bh(struct ext4_io_submit *io, + struct ext4_io_page *io_page, + struct inode *inode, + struct writeback_control *wbc, + struct buffer_head *bh) +{ + ext4_io_end_t *io_end; + int ret; + + if (buffer_new(bh)) { + clear_buffer_new(bh); + unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr); + } + + if (!buffer_mapped(bh) || buffer_delay(bh)) { + if (!buffer_mapped(bh)) + clear_buffer_dirty(bh); + if (io->io_bio) + ext4_io_submit(io); + return 0; + } + + if (io->io_bio && bh->b_blocknr != io->io_next_block) { +submit_and_retry: + ext4_io_submit(io); + } + if (io->io_bio == NULL) { + ret = io_submit_init(io, inode, wbc, bh); + if (ret) + return ret; + } + io_end = io->io_end; + if ((io_end->num_io_pages >= MAX_IO_PAGES) && + (io_end->pages[io_end->num_io_pages-1] != io_page)) + goto submit_and_retry; + if (buffer_uninit(bh)) + io->io_end->flag |= EXT4_IO_END_UNWRITTEN; + io->io_end->size += bh->b_size; + io->io_next_block++; + ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh)); + if (ret != bh->b_size) + goto submit_and_retry; + if ((io_end->num_io_pages == 0) || + (io_end->pages[io_end->num_io_pages-1] != io_page)) { + io_end->pages[io_end->num_io_pages++] = io_page; + atomic_inc(&io_page->p_count); + } + return 0; +} + +int ext4_bio_write_page(struct ext4_io_submit *io, + struct page *page, + int len, + struct writeback_control *wbc) +{ + struct inode *inode = page->mapping->host; + unsigned block_start, block_end, blocksize; + struct ext4_io_page *io_page; + struct buffer_head *bh, *head; + int ret = 0; + + blocksize = 1 << inode->i_blkbits; + + BUG_ON(PageWriteback(page)); + set_page_writeback(page); + ClearPageError(page); + + io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS); + if (!io_page) { + set_page_dirty(page); + unlock_page(page); + return -ENOMEM; + } + io_page->p_page = page; + atomic_set(&io_page->p_count, 1); + get_page(page); + + for (bh = head = page_buffers(page), block_start = 0; + bh != head || !block_start; + block_start = block_end, bh = bh->b_this_page) { + block_end = block_start + blocksize; + if (block_start >= len) { + clear_buffer_dirty(bh); + set_buffer_uptodate(bh); + continue; + } + ret = io_submit_add_bh(io, io_page, inode, wbc, bh); + if (ret) { + /* + * We only get here on ENOMEM. Not much else + * we can do but mark the page as dirty, and + * better luck next time. + */ + set_page_dirty(page); + break; + } + } + unlock_page(page); + /* + * If the page was truncated before we could do the writeback, + * or we had a memory allocation error while trying to write + * the first buffer head, we won't have submitted any pages for + * I/O. In that case we need to make sure we've cleared the + * PageWriteback bit from the page to prevent the system from + * wedging later on. + */ + put_io_page(io_page); + return ret; +} diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index ca5c8aa00a2f..dc963929de65 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -226,23 +226,13 @@ static int setup_new_group_blocks(struct super_block *sb, } /* Zero out all of the reserved backup group descriptor table blocks */ - for (i = 0, bit = gdblocks + 1, block = start + bit; - i < reserved_gdb; i++, block++, bit++) { - struct buffer_head *gdb; - - ext4_debug("clear reserved block %#04llx (+%d)\n", block, bit); - - if ((err = extend_or_restart_transaction(handle, 1, bh))) - goto exit_bh; + ext4_debug("clear inode table blocks %#04llx -> %#04llx\n", + block, sbi->s_itb_per_group); + err = sb_issue_zeroout(sb, gdblocks + start + 1, reserved_gdb, + GFP_NOFS); + if (err) + goto exit_bh; - if (IS_ERR(gdb = bclean(handle, sb, block))) { - err = PTR_ERR(gdb); - goto exit_bh; - } - ext4_handle_dirty_metadata(handle, NULL, gdb); - ext4_set_bit(bit, bh->b_data); - brelse(gdb); - } ext4_debug("mark block bitmap %#04llx (+%llu)\n", input->block_bitmap, input->block_bitmap - start); ext4_set_bit(input->block_bitmap - start, bh->b_data); @@ -251,28 +241,18 @@ static int setup_new_group_blocks(struct super_block *sb, ext4_set_bit(input->inode_bitmap - start, bh->b_data); /* Zero out all of the inode table blocks */ - for (i = 0, block = input->inode_table, bit = block - start; - i < sbi->s_itb_per_group; i++, bit++, block++) { - struct buffer_head *it; - - ext4_debug("clear inode block %#04llx (+%d)\n", block, bit); - - if ((err = extend_or_restart_transaction(handle, 1, bh))) - goto exit_bh; - - if (IS_ERR(it = bclean(handle, sb, block))) { - err = PTR_ERR(it); - goto exit_bh; - } - ext4_handle_dirty_metadata(handle, NULL, it); - brelse(it); - ext4_set_bit(bit, bh->b_data); - } + block = input->inode_table; + ext4_debug("clear inode table blocks %#04llx -> %#04llx\n", + block, sbi->s_itb_per_group); + err = sb_issue_zeroout(sb, block, sbi->s_itb_per_group, GFP_NOFS); + if (err) + goto exit_bh; if ((err = extend_or_restart_transaction(handle, 2, bh))) goto exit_bh; - mark_bitmap_end(input->blocks_count, sb->s_blocksize * 8, bh->b_data); + ext4_mark_bitmap_end(input->blocks_count, sb->s_blocksize * 8, + bh->b_data); ext4_handle_dirty_metadata(handle, NULL, bh); brelse(bh); /* Mark unused entries in inode bitmap used */ @@ -283,8 +263,8 @@ static int setup_new_group_blocks(struct super_block *sb, goto exit_journal; } - mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8, - bh->b_data); + ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8, + bh->b_data); ext4_handle_dirty_metadata(handle, NULL, bh); exit_bh: brelse(bh); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 8ecc1e590303..e32195d6aac3 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -40,6 +40,9 @@ #include <linux/crc16.h> #include <asm/uaccess.h> +#include <linux/kthread.h> +#include <linux/freezer.h> + #include "ext4.h" #include "ext4_jbd2.h" #include "xattr.h" @@ -49,8 +52,11 @@ #define CREATE_TRACE_POINTS #include <trace/events/ext4.h> -struct proc_dir_entry *ext4_proc_root; +static struct proc_dir_entry *ext4_proc_root; static struct kset *ext4_kset; +struct ext4_lazy_init *ext4_li_info; +struct mutex ext4_li_mtx; +struct ext4_features *ext4_feat; static int ext4_load_journal(struct super_block *, struct ext4_super_block *, unsigned long journal_devnum); @@ -67,14 +73,16 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf); static int ext4_unfreeze(struct super_block *sb); static void ext4_write_super(struct super_block *sb); static int ext4_freeze(struct super_block *sb); -static int ext4_get_sb(struct file_system_type *fs_type, int flags, - const char *dev_name, void *data, struct vfsmount *mnt); +static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *data); +static void ext4_destroy_lazyinit_thread(void); +static void ext4_unregister_li_request(struct super_block *sb); #if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23) static struct file_system_type ext3_fs_type = { .owner = THIS_MODULE, .name = "ext3", - .get_sb = ext4_get_sb, + .mount = ext4_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; @@ -701,6 +709,7 @@ static void ext4_put_super(struct super_block *sb) struct ext4_super_block *es = sbi->s_es; int i, err; + ext4_unregister_li_request(sb); dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); flush_workqueue(sbi->dio_unwritten_wq); @@ -717,6 +726,7 @@ static void ext4_put_super(struct super_block *sb) ext4_abort(sb, "Couldn't clean up the journal"); } + del_timer(&sbi->s_err_report); ext4_release_system_zone(sb); ext4_mb_release(sb); ext4_ext_release(sb); @@ -818,12 +828,22 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) ei->cur_aio_dio = NULL; ei->i_sync_tid = 0; ei->i_datasync_tid = 0; + atomic_set(&ei->i_ioend_count, 0); return &ei->vfs_inode; } +static int ext4_drop_inode(struct inode *inode) +{ + int drop = generic_drop_inode(inode); + + trace_ext4_drop_inode(inode, drop); + return drop; +} + static void ext4_destroy_inode(struct inode *inode) { + ext4_ioend_wait(inode); if (!list_empty(&(EXT4_I(inode)->i_orphan))) { ext4_msg(inode->i_sb, KERN_ERR, "Inode %lu (%p): orphan list check failed!", @@ -1042,6 +1062,12 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs) !(def_mount_opts & EXT4_DEFM_BLOCK_VALIDITY)) seq_puts(seq, ",block_validity"); + if (!test_opt(sb, INIT_INODE_TABLE)) + seq_puts(seq, ",noinit_inode_table"); + else if (sbi->s_li_wait_mult) + seq_printf(seq, ",init_inode_table=%u", + (unsigned) sbi->s_li_wait_mult); + ext4_show_quota_options(seq, sb); return 0; @@ -1157,6 +1183,7 @@ static const struct super_operations ext4_sops = { .destroy_inode = ext4_destroy_inode, .write_inode = ext4_write_inode, .dirty_inode = ext4_dirty_inode, + .drop_inode = ext4_drop_inode, .evict_inode = ext4_evict_inode, .put_super = ext4_put_super, .sync_fs = ext4_sync_fs, @@ -1177,6 +1204,7 @@ static const struct super_operations ext4_nojournal_sops = { .destroy_inode = ext4_destroy_inode, .write_inode = ext4_write_inode, .dirty_inode = ext4_dirty_inode, + .drop_inode = ext4_drop_inode, .evict_inode = ext4_evict_inode, .write_super = ext4_write_super, .put_super = ext4_put_super, @@ -1216,6 +1244,7 @@ enum { Opt_inode_readahead_blks, Opt_journal_ioprio, Opt_dioread_nolock, Opt_dioread_lock, Opt_discard, Opt_nodiscard, + Opt_init_inode_table, Opt_noinit_inode_table, }; static const match_table_t tokens = { @@ -1286,6 +1315,9 @@ static const match_table_t tokens = { {Opt_dioread_lock, "dioread_lock"}, {Opt_discard, "discard"}, {Opt_nodiscard, "nodiscard"}, + {Opt_init_inode_table, "init_itable=%u"}, + {Opt_init_inode_table, "init_itable"}, + {Opt_noinit_inode_table, "noinit_itable"}, {Opt_err, NULL}, }; @@ -1756,6 +1788,20 @@ set_qf_format: case Opt_dioread_lock: clear_opt(sbi->s_mount_opt, DIOREAD_NOLOCK); break; + case Opt_init_inode_table: + set_opt(sbi->s_mount_opt, INIT_INODE_TABLE); + if (args[0].from) { + if (match_int(&args[0], &option)) + return 0; + } else + option = EXT4_DEF_LI_WAIT_MULT; + if (option < 0) + return 0; + sbi->s_li_wait_mult = option; + break; + case Opt_noinit_inode_table: + clear_opt(sbi->s_mount_opt, INIT_INODE_TABLE); + break; default: ext4_msg(sb, KERN_ERR, "Unrecognized mount option \"%s\" " @@ -1939,7 +1985,8 @@ int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 block_group, } /* Called at mount-time, super-block is locked */ -static int ext4_check_descriptors(struct super_block *sb) +static int ext4_check_descriptors(struct super_block *sb, + ext4_group_t *first_not_zeroed) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block); @@ -1948,7 +1995,7 @@ static int ext4_check_descriptors(struct super_block *sb) ext4_fsblk_t inode_bitmap; ext4_fsblk_t inode_table; int flexbg_flag = 0; - ext4_group_t i; + ext4_group_t i, grp = sbi->s_groups_count; if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) flexbg_flag = 1; @@ -1964,6 +2011,10 @@ static int ext4_check_descriptors(struct super_block *sb) last_block = first_block + (EXT4_BLOCKS_PER_GROUP(sb) - 1); + if ((grp == sbi->s_groups_count) && + !(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))) + grp = i; + block_bitmap = ext4_block_bitmap(sb, gdp); if (block_bitmap < first_block || block_bitmap > last_block) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " @@ -2001,6 +2052,8 @@ static int ext4_check_descriptors(struct super_block *sb) if (!flexbg_flag) first_block += EXT4_BLOCKS_PER_GROUP(sb); } + if (NULL != first_not_zeroed) + *first_not_zeroed = grp; ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb)); sbi->s_es->s_free_inodes_count =cpu_to_le32(ext4_count_free_inodes(sb)); @@ -2373,6 +2426,7 @@ static struct ext4_attr ext4_attr_##_name = { \ #define EXT4_ATTR(name, mode, show, store) \ static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store) +#define EXT4_INFO_ATTR(name) EXT4_ATTR(name, 0444, NULL, NULL) #define EXT4_RO_ATTR(name) EXT4_ATTR(name, 0444, name##_show, NULL) #define EXT4_RW_ATTR(name) EXT4_ATTR(name, 0644, name##_show, name##_store) #define EXT4_RW_ATTR_SBI_UI(name, elname) \ @@ -2409,6 +2463,16 @@ static struct attribute *ext4_attrs[] = { NULL, }; +/* Features this copy of ext4 supports */ +EXT4_INFO_ATTR(lazy_itable_init); +EXT4_INFO_ATTR(batched_discard); + +static struct attribute *ext4_feat_attrs[] = { + ATTR_LIST(lazy_itable_init), + ATTR_LIST(batched_discard), + NULL, +}; + static ssize_t ext4_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { @@ -2437,7 +2501,6 @@ static void ext4_sb_release(struct kobject *kobj) complete(&sbi->s_kobj_unregister); } - static const struct sysfs_ops ext4_attr_ops = { .show = ext4_attr_show, .store = ext4_attr_store, @@ -2449,6 +2512,17 @@ static struct kobj_type ext4_ktype = { .release = ext4_sb_release, }; +static void ext4_feat_release(struct kobject *kobj) +{ + complete(&ext4_feat->f_kobj_unregister); +} + +static struct kobj_type ext4_feat_ktype = { + .default_attrs = ext4_feat_attrs, + .sysfs_ops = &ext4_attr_ops, + .release = ext4_feat_release, +}; + /* * Check whether this filesystem can be mounted based on * the features present and the RDONLY/RDWR mount requested. @@ -2539,6 +2613,368 @@ static void print_daily_error_info(unsigned long arg) mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ); /* Once a day */ } +static void ext4_lazyinode_timeout(unsigned long data) +{ + struct task_struct *p = (struct task_struct *)data; + wake_up_process(p); +} + +/* Find next suitable group and run ext4_init_inode_table */ +static int ext4_run_li_request(struct ext4_li_request *elr) +{ + struct ext4_group_desc *gdp = NULL; + ext4_group_t group, ngroups; + struct super_block *sb; + unsigned long timeout = 0; + int ret = 0; + + sb = elr->lr_super; + ngroups = EXT4_SB(sb)->s_groups_count; + + for (group = elr->lr_next_group; group < ngroups; group++) { + gdp = ext4_get_group_desc(sb, group, NULL); + if (!gdp) { + ret = 1; + break; + } + + if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))) + break; + } + + if (group == ngroups) + ret = 1; + + if (!ret) { + timeout = jiffies; + ret = ext4_init_inode_table(sb, group, + elr->lr_timeout ? 0 : 1); + if (elr->lr_timeout == 0) { + timeout = jiffies - timeout; + if (elr->lr_sbi->s_li_wait_mult) + timeout *= elr->lr_sbi->s_li_wait_mult; + else + timeout *= 20; + elr->lr_timeout = timeout; + } + elr->lr_next_sched = jiffies + elr->lr_timeout; + elr->lr_next_group = group + 1; + } + + return ret; +} + +/* + * Remove lr_request from the list_request and free the + * request tructure. Should be called with li_list_mtx held + */ +static void ext4_remove_li_request(struct ext4_li_request *elr) +{ + struct ext4_sb_info *sbi; + + if (!elr) + return; + + sbi = elr->lr_sbi; + + list_del(&elr->lr_request); + sbi->s_li_request = NULL; + kfree(elr); +} + +static void ext4_unregister_li_request(struct super_block *sb) +{ + struct ext4_li_request *elr = EXT4_SB(sb)->s_li_request; + + if (!ext4_li_info) + return; + + mutex_lock(&ext4_li_info->li_list_mtx); + ext4_remove_li_request(elr); + mutex_unlock(&ext4_li_info->li_list_mtx); +} + +/* + * This is the function where ext4lazyinit thread lives. It walks + * through the request list searching for next scheduled filesystem. + * When such a fs is found, run the lazy initialization request + * (ext4_rn_li_request) and keep track of the time spend in this + * function. Based on that time we compute next schedule time of + * the request. When walking through the list is complete, compute + * next waking time and put itself into sleep. + */ +static int ext4_lazyinit_thread(void *arg) +{ + struct ext4_lazy_init *eli = (struct ext4_lazy_init *)arg; + struct list_head *pos, *n; + struct ext4_li_request *elr; + unsigned long next_wakeup; + DEFINE_WAIT(wait); + + BUG_ON(NULL == eli); + + eli->li_timer.data = (unsigned long)current; + eli->li_timer.function = ext4_lazyinode_timeout; + + eli->li_task = current; + wake_up(&eli->li_wait_task); + +cont_thread: + while (true) { + next_wakeup = MAX_JIFFY_OFFSET; + + mutex_lock(&eli->li_list_mtx); + if (list_empty(&eli->li_request_list)) { + mutex_unlock(&eli->li_list_mtx); + goto exit_thread; + } + + list_for_each_safe(pos, n, &eli->li_request_list) { + elr = list_entry(pos, struct ext4_li_request, + lr_request); + + if (time_after_eq(jiffies, elr->lr_next_sched)) { + if (ext4_run_li_request(elr) != 0) { + /* error, remove the lazy_init job */ + ext4_remove_li_request(elr); + continue; + } + } + + if (time_before(elr->lr_next_sched, next_wakeup)) + next_wakeup = elr->lr_next_sched; + } + mutex_unlock(&eli->li_list_mtx); + + if (freezing(current)) + refrigerator(); + + if ((time_after_eq(jiffies, next_wakeup)) || + (MAX_JIFFY_OFFSET == next_wakeup)) { + cond_resched(); + continue; + } + + eli->li_timer.expires = next_wakeup; + add_timer(&eli->li_timer); + prepare_to_wait(&eli->li_wait_daemon, &wait, + TASK_INTERRUPTIBLE); + if (time_before(jiffies, next_wakeup)) + schedule(); + finish_wait(&eli->li_wait_daemon, &wait); + } + +exit_thread: + /* + * It looks like the request list is empty, but we need + * to check it under the li_list_mtx lock, to prevent any + * additions into it, and of course we should lock ext4_li_mtx + * to atomically free the list and ext4_li_info, because at + * this point another ext4 filesystem could be registering + * new one. + */ + mutex_lock(&ext4_li_mtx); + mutex_lock(&eli->li_list_mtx); + if (!list_empty(&eli->li_request_list)) { + mutex_unlock(&eli->li_list_mtx); + mutex_unlock(&ext4_li_mtx); + goto cont_thread; + } + mutex_unlock(&eli->li_list_mtx); + del_timer_sync(&ext4_li_info->li_timer); + eli->li_task = NULL; + wake_up(&eli->li_wait_task); + + kfree(ext4_li_info); + ext4_li_info = NULL; + mutex_unlock(&ext4_li_mtx); + + return 0; +} + +static void ext4_clear_request_list(void) +{ + struct list_head *pos, *n; + struct ext4_li_request *elr; + + mutex_lock(&ext4_li_info->li_list_mtx); + list_for_each_safe(pos, n, &ext4_li_info->li_request_list) { + elr = list_entry(pos, struct ext4_li_request, + lr_request); + ext4_remove_li_request(elr); + } + mutex_unlock(&ext4_li_info->li_list_mtx); +} + +static int ext4_run_lazyinit_thread(void) +{ + struct task_struct *t; + + t = kthread_run(ext4_lazyinit_thread, ext4_li_info, "ext4lazyinit"); + if (IS_ERR(t)) { + int err = PTR_ERR(t); + ext4_clear_request_list(); + del_timer_sync(&ext4_li_info->li_timer); + kfree(ext4_li_info); + ext4_li_info = NULL; + printk(KERN_CRIT "EXT4: error %d creating inode table " + "initialization thread\n", + err); + return err; + } + ext4_li_info->li_state |= EXT4_LAZYINIT_RUNNING; + + wait_event(ext4_li_info->li_wait_task, ext4_li_info->li_task != NULL); + return 0; +} + +/* + * Check whether it make sense to run itable init. thread or not. + * If there is at least one uninitialized inode table, return + * corresponding group number, else the loop goes through all + * groups and return total number of groups. + */ +static ext4_group_t ext4_has_uninit_itable(struct super_block *sb) +{ + ext4_group_t group, ngroups = EXT4_SB(sb)->s_groups_count; + struct ext4_group_desc *gdp = NULL; + + for (group = 0; group < ngroups; group++) { + gdp = ext4_get_group_desc(sb, group, NULL); + if (!gdp) + continue; + + if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))) + break; + } + + return group; +} + +static int ext4_li_info_new(void) +{ + struct ext4_lazy_init *eli = NULL; + + eli = kzalloc(sizeof(*eli), GFP_KERNEL); + if (!eli) + return -ENOMEM; + + eli->li_task = NULL; + INIT_LIST_HEAD(&eli->li_request_list); + mutex_init(&eli->li_list_mtx); + + init_waitqueue_head(&eli->li_wait_daemon); + init_waitqueue_head(&eli->li_wait_task); + init_timer(&eli->li_timer); + eli->li_state |= EXT4_LAZYINIT_QUIT; + + ext4_li_info = eli; + + return 0; +} + +static struct ext4_li_request *ext4_li_request_new(struct super_block *sb, + ext4_group_t start) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_li_request *elr; + unsigned long rnd; + + elr = kzalloc(sizeof(*elr), GFP_KERNEL); + if (!elr) + return NULL; + + elr->lr_super = sb; + elr->lr_sbi = sbi; + elr->lr_next_group = start; + + /* + * Randomize first schedule time of the request to + * spread the inode table initialization requests + * better. + */ + get_random_bytes(&rnd, sizeof(rnd)); + elr->lr_next_sched = jiffies + (unsigned long)rnd % + (EXT4_DEF_LI_MAX_START_DELAY * HZ); + + return elr; +} + +static int ext4_register_li_request(struct super_block *sb, + ext4_group_t first_not_zeroed) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_li_request *elr; + ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count; + int ret; + + if (sbi->s_li_request != NULL) + return 0; + + if (first_not_zeroed == ngroups || + (sb->s_flags & MS_RDONLY) || + !test_opt(sb, INIT_INODE_TABLE)) { + sbi->s_li_request = NULL; + return 0; + } + + if (first_not_zeroed == ngroups) { + sbi->s_li_request = NULL; + return 0; + } + + elr = ext4_li_request_new(sb, first_not_zeroed); + if (!elr) + return -ENOMEM; + + mutex_lock(&ext4_li_mtx); + + if (NULL == ext4_li_info) { + ret = ext4_li_info_new(); + if (ret) + goto out; + } + + mutex_lock(&ext4_li_info->li_list_mtx); + list_add(&elr->lr_request, &ext4_li_info->li_request_list); + mutex_unlock(&ext4_li_info->li_list_mtx); + + sbi->s_li_request = elr; + + if (!(ext4_li_info->li_state & EXT4_LAZYINIT_RUNNING)) { + ret = ext4_run_lazyinit_thread(); + if (ret) + goto out; + } +out: + mutex_unlock(&ext4_li_mtx); + if (ret) + kfree(elr); + return ret; +} + +/* + * We do not need to lock anything since this is called on + * module unload. + */ +static void ext4_destroy_lazyinit_thread(void) +{ + /* + * If thread exited earlier + * there's nothing to be done. + */ + if (!ext4_li_info) + return; + + ext4_clear_request_list(); + + while (ext4_li_info->li_task) { + wake_up(&ext4_li_info->li_wait_daemon); + wait_event(ext4_li_info->li_wait_task, + ext4_li_info->li_task == NULL); + } +} + static int ext4_fill_super(struct super_block *sb, void *data, int silent) __releases(kernel_lock) __acquires(kernel_lock) @@ -2564,6 +3000,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) __u64 blocks_count; int err; unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO; + ext4_group_t first_not_zeroed; sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) @@ -2624,6 +3061,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) /* Set defaults before we parse the mount options */ def_mount_opts = le32_to_cpu(es->s_default_mount_opts); + set_opt(sbi->s_mount_opt, INIT_INODE_TABLE); if (def_mount_opts & EXT4_DEFM_DEBUG) set_opt(sbi->s_mount_opt, DEBUG); if (def_mount_opts & EXT4_DEFM_BSDGROUPS) { @@ -2826,13 +3264,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) * Test whether we have more sectors than will fit in sector_t, * and whether the max offset is addressable by the page cache. */ - ret = generic_check_addressable(sb->s_blocksize_bits, + err = generic_check_addressable(sb->s_blocksize_bits, ext4_blocks_count(es)); - if (ret) { + if (err) { ext4_msg(sb, KERN_ERR, "filesystem" " too large to mount safely on this system"); if (sizeof(sector_t) < 8) ext4_msg(sb, KERN_WARNING, "CONFIG_LBDAF not enabled"); + ret = err; goto failed_mount; } @@ -2901,7 +3340,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount2; } } - if (!ext4_check_descriptors(sb)) { + if (!ext4_check_descriptors(sb, &first_not_zeroed)) { ext4_msg(sb, KERN_ERR, "group descriptors corrupted!"); goto failed_mount2; } @@ -2917,6 +3356,24 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) get_random_bytes(&sbi->s_next_generation, sizeof(u32)); spin_lock_init(&sbi->s_next_gen_lock); + err = percpu_counter_init(&sbi->s_freeblocks_counter, + ext4_count_free_blocks(sb)); + if (!err) { + err = percpu_counter_init(&sbi->s_freeinodes_counter, + ext4_count_free_inodes(sb)); + } + if (!err) { + err = percpu_counter_init(&sbi->s_dirs_counter, + ext4_count_dirs(sb)); + } + if (!err) { + err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0); + } + if (err) { + ext4_msg(sb, KERN_ERR, "insufficient memory"); + goto failed_mount3; + } + sbi->s_stripe = ext4_get_stripe_size(sbi); sbi->s_max_writeback_mb_bump = 128; @@ -3015,22 +3472,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } set_task_ioprio(sbi->s_journal->j_task, journal_ioprio); -no_journal: - err = percpu_counter_init(&sbi->s_freeblocks_counter, - ext4_count_free_blocks(sb)); - if (!err) - err = percpu_counter_init(&sbi->s_freeinodes_counter, - ext4_count_free_inodes(sb)); - if (!err) - err = percpu_counter_init(&sbi->s_dirs_counter, - ext4_count_dirs(sb)); - if (!err) - err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0); - if (err) { - ext4_msg(sb, KERN_ERR, "insufficient memory"); - goto failed_mount_wq; - } + /* + * The journal may have updated the bg summary counts, so we + * need to update the global counters. + */ + percpu_counter_set(&sbi->s_freeblocks_counter, + ext4_count_free_blocks(sb)); + percpu_counter_set(&sbi->s_freeinodes_counter, + ext4_count_free_inodes(sb)); + percpu_counter_set(&sbi->s_dirs_counter, + ext4_count_dirs(sb)); + percpu_counter_set(&sbi->s_dirtyblocks_counter, 0); +no_journal: EXT4_SB(sb)->dio_unwritten_wq = create_workqueue("ext4-dio-unwritten"); if (!EXT4_SB(sb)->dio_unwritten_wq) { printk(KERN_ERR "EXT4-fs: failed to create DIO workqueue\n"); @@ -3122,6 +3576,10 @@ no_journal: goto failed_mount4; } + err = ext4_register_li_request(sb, first_not_zeroed); + if (err) + goto failed_mount4; + sbi->s_kobj.kset = ext4_kset; init_completion(&sbi->s_kobj_unregister); err = kobject_init_and_add(&sbi->s_kobj, &ext4_ktype, NULL, @@ -3176,10 +3634,6 @@ failed_mount_wq: jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; } - percpu_counter_destroy(&sbi->s_freeblocks_counter); - percpu_counter_destroy(&sbi->s_freeinodes_counter); - percpu_counter_destroy(&sbi->s_dirs_counter); - percpu_counter_destroy(&sbi->s_dirtyblocks_counter); failed_mount3: if (sbi->s_flex_groups) { if (is_vmalloc_addr(sbi->s_flex_groups)) @@ -3187,6 +3641,10 @@ failed_mount3: else kfree(sbi->s_flex_groups); } + percpu_counter_destroy(&sbi->s_freeblocks_counter); + percpu_counter_destroy(&sbi->s_freeinodes_counter); + percpu_counter_destroy(&sbi->s_dirs_counter); + percpu_counter_destroy(&sbi->s_dirtyblocks_counter); failed_mount2: for (i = 0; i < db_count; i++) brelse(sbi->s_group_desc[i]); @@ -3461,7 +3919,7 @@ static int ext4_load_journal(struct super_block *sb, EXT4_SB(sb)->s_journal = journal; ext4_clear_journal_err(sb, es); - if (journal_devnum && + if (!really_read_only && journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { es->s_journal_dev = cpu_to_le32(journal_devnum); @@ -3515,9 +3973,10 @@ static int ext4_commit_super(struct super_block *sb, int sync) es->s_kbytes_written = cpu_to_le64(EXT4_SB(sb)->s_kbytes_written); ext4_free_blocks_count_set(es, percpu_counter_sum_positive( - &EXT4_SB(sb)->s_freeblocks_counter)); - es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive( - &EXT4_SB(sb)->s_freeinodes_counter)); + &EXT4_SB(sb)->s_freeblocks_counter)); + es->s_free_inodes_count = + cpu_to_le32(percpu_counter_sum_positive( + &EXT4_SB(sb)->s_freeinodes_counter)); sb->s_dirt = 0; BUFFER_TRACE(sbh, "marking dirty"); mark_buffer_dirty(sbh); @@ -3835,6 +4294,19 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) enable_quota = 1; } } + + /* + * Reinitialize lazy itable initialization thread based on + * current settings + */ + if ((sb->s_flags & MS_RDONLY) || !test_opt(sb, INIT_INODE_TABLE)) + ext4_unregister_li_request(sb); + else { + ext4_group_t first_not_zeroed; + first_not_zeroed = ext4_has_uninit_itable(sb); + ext4_register_li_request(sb, first_not_zeroed); + } + ext4_setup_system_zone(sb); if (sbi->s_journal == NULL) ext4_commit_super(sb, 1); @@ -4105,12 +4577,10 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, static int ext4_quota_off(struct super_block *sb, int type) { - /* Force all delayed allocation blocks to be allocated */ - if (test_opt(sb, DELALLOC)) { - down_read(&sb->s_umount); + /* Force all delayed allocation blocks to be allocated. + * Caller already holds s_umount sem */ + if (test_opt(sb, DELALLOC)) sync_filesystem(sb); - up_read(&sb->s_umount); - } return dquot_quota_off(sb, type); } @@ -4216,17 +4686,17 @@ out: #endif -static int ext4_get_sb(struct file_system_type *fs_type, int flags, - const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, ext4_fill_super,mnt); + return mount_bdev(fs_type, flags, dev_name, data, ext4_fill_super); } #if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23) static struct file_system_type ext2_fs_type = { .owner = THIS_MODULE, .name = "ext2", - .get_sb = ext4_get_sb, + .mount = ext4_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; @@ -4271,28 +4741,58 @@ static inline void unregister_as_ext3(void) { } static struct file_system_type ext4_fs_type = { .owner = THIS_MODULE, .name = "ext4", - .get_sb = ext4_get_sb, + .mount = ext4_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; -static int __init init_ext4_fs(void) +int __init ext4_init_feat_adverts(void) +{ + struct ext4_features *ef; + int ret = -ENOMEM; + + ef = kzalloc(sizeof(struct ext4_features), GFP_KERNEL); + if (!ef) + goto out; + + ef->f_kobj.kset = ext4_kset; + init_completion(&ef->f_kobj_unregister); + ret = kobject_init_and_add(&ef->f_kobj, &ext4_feat_ktype, NULL, + "features"); + if (ret) { + kfree(ef); + goto out; + } + + ext4_feat = ef; + ret = 0; +out: + return ret; +} + +static int __init ext4_init_fs(void) { int err; ext4_check_flag_values(); - err = init_ext4_system_zone(); + err = ext4_init_pageio(); if (err) return err; + err = ext4_init_system_zone(); + if (err) + goto out5; ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj); if (!ext4_kset) goto out4; ext4_proc_root = proc_mkdir("fs/ext4", NULL); - err = init_ext4_mballoc(); + + err = ext4_init_feat_adverts(); + + err = ext4_init_mballoc(); if (err) goto out3; - err = init_ext4_xattr(); + err = ext4_init_xattr(); if (err) goto out2; err = init_inodecache(); @@ -4303,38 +4803,46 @@ static int __init init_ext4_fs(void) err = register_filesystem(&ext4_fs_type); if (err) goto out; + + ext4_li_info = NULL; + mutex_init(&ext4_li_mtx); return 0; out: unregister_as_ext2(); unregister_as_ext3(); destroy_inodecache(); out1: - exit_ext4_xattr(); + ext4_exit_xattr(); out2: - exit_ext4_mballoc(); + ext4_exit_mballoc(); out3: + kfree(ext4_feat); remove_proc_entry("fs/ext4", NULL); kset_unregister(ext4_kset); out4: - exit_ext4_system_zone(); + ext4_exit_system_zone(); +out5: + ext4_exit_pageio(); return err; } -static void __exit exit_ext4_fs(void) +static void __exit ext4_exit_fs(void) { + ext4_destroy_lazyinit_thread(); unregister_as_ext2(); unregister_as_ext3(); unregister_filesystem(&ext4_fs_type); destroy_inodecache(); - exit_ext4_xattr(); - exit_ext4_mballoc(); + ext4_exit_xattr(); + ext4_exit_mballoc(); remove_proc_entry("fs/ext4", NULL); kset_unregister(ext4_kset); - exit_ext4_system_zone(); + ext4_exit_system_zone(); + ext4_exit_pageio(); } MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others"); MODULE_DESCRIPTION("Fourth Extended Filesystem"); MODULE_LICENSE("GPL"); -module_init(init_ext4_fs) -module_exit(exit_ext4_fs) +module_init(ext4_init_fs) +module_exit(ext4_exit_fs) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 3a8cd8dff1ad..fa4b899da4b3 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1588,7 +1588,7 @@ static void ext4_xattr_rehash(struct ext4_xattr_header *header, #undef BLOCK_HASH_SHIFT int __init -init_ext4_xattr(void) +ext4_init_xattr(void) { ext4_xattr_cache = mb_cache_create("ext4_xattr", 6); if (!ext4_xattr_cache) @@ -1597,7 +1597,7 @@ init_ext4_xattr(void) } void -exit_ext4_xattr(void) +ext4_exit_xattr(void) { if (ext4_xattr_cache) mb_cache_destroy(ext4_xattr_cache); diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index 518e96e43905..1ef16520b950 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -83,8 +83,8 @@ extern void ext4_xattr_put_super(struct super_block *); extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, struct ext4_inode *raw_inode, handle_t *handle); -extern int init_ext4_xattr(void); -extern void exit_ext4_xattr(void); +extern int __init ext4_init_xattr(void); +extern void ext4_exit_xattr(void); extern const struct xattr_handler *ext4_xattr_handlers[]; @@ -121,14 +121,14 @@ ext4_xattr_put_super(struct super_block *sb) { } -static inline int -init_ext4_xattr(void) +static __init inline int +ext4_init_xattr(void) { return 0; } static inline void -exit_ext4_xattr(void) +ext4_exit_xattr(void) { } diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c index bbca5c186ae7..3345aabd1dd7 100644 --- a/fs/fat/namei_msdos.c +++ b/fs/fat/namei_msdos.c @@ -675,18 +675,17 @@ static int msdos_fill_super(struct super_block *sb, void *data, int silent) return 0; } -static int msdos_get_sb(struct file_system_type *fs_type, +static struct dentry *msdos_mount(struct file_system_type *fs_type, int flags, const char *dev_name, - void *data, struct vfsmount *mnt) + void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, msdos_fill_super, - mnt); + return mount_bdev(fs_type, flags, dev_name, data, msdos_fill_super); } static struct file_system_type msdos_fs_type = { .owner = THIS_MODULE, .name = "msdos", - .get_sb = msdos_get_sb, + .mount = msdos_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index 6f0f6c9a0152..b936703b8924 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -1071,18 +1071,17 @@ static int vfat_fill_super(struct super_block *sb, void *data, int silent) return 0; } -static int vfat_get_sb(struct file_system_type *fs_type, +static struct dentry *vfat_mount(struct file_system_type *fs_type, int flags, const char *dev_name, - void *data, struct vfsmount *mnt) + void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, vfat_fill_super, - mnt); + return mount_bdev(fs_type, flags, dev_name, data, vfat_fill_super); } static struct file_system_type vfat_fs_type = { .owner = THIS_MODULE, .name = "vfat", - .get_sb = vfat_get_sb, + .mount = vfat_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/fcntl.c b/fs/fcntl.c index f8cc34f542c3..ecc8b3954ed6 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -640,7 +640,7 @@ static void fasync_free_rcu(struct rcu_head *head) * match the state "is the filp on a fasync list". * */ -static int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp) +int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *fa, **fp; int result = 0; @@ -666,21 +666,31 @@ static int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp) return result; } +struct fasync_struct *fasync_alloc(void) +{ + return kmem_cache_alloc(fasync_cache, GFP_KERNEL); +} + /* - * Add a fasync entry. Return negative on error, positive if - * added, and zero if did nothing but change an existing one. + * NOTE! This can be used only for unused fasync entries: + * entries that actually got inserted on the fasync list + * need to be released by rcu - see fasync_remove_entry. + */ +void fasync_free(struct fasync_struct *new) +{ + kmem_cache_free(fasync_cache, new); +} + +/* + * Insert a new entry into the fasync list. Return the pointer to the + * old one if we didn't use the new one. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". */ -static int fasync_add_entry(int fd, struct file *filp, struct fasync_struct **fapp) +struct fasync_struct *fasync_insert_entry(int fd, struct file *filp, struct fasync_struct **fapp, struct fasync_struct *new) { - struct fasync_struct *new, *fa, **fp; - int result = 0; - - new = kmem_cache_alloc(fasync_cache, GFP_KERNEL); - if (!new) - return -ENOMEM; + struct fasync_struct *fa, **fp; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); @@ -691,8 +701,6 @@ static int fasync_add_entry(int fd, struct file *filp, struct fasync_struct **fa spin_lock_irq(&fa->fa_lock); fa->fa_fd = fd; spin_unlock_irq(&fa->fa_lock); - - kmem_cache_free(fasync_cache, new); goto out; } @@ -702,13 +710,39 @@ static int fasync_add_entry(int fd, struct file *filp, struct fasync_struct **fa new->fa_fd = fd; new->fa_next = *fapp; rcu_assign_pointer(*fapp, new); - result = 1; filp->f_flags |= FASYNC; out: spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); - return result; + return fa; +} + +/* + * Add a fasync entry. Return negative on error, positive if + * added, and zero if did nothing but change an existing one. + */ +static int fasync_add_entry(int fd, struct file *filp, struct fasync_struct **fapp) +{ + struct fasync_struct *new; + + new = fasync_alloc(); + if (!new) + return -ENOMEM; + + /* + * fasync_insert_entry() returns the old (update) entry if + * it existed. + * + * So free the (unused) new entry and return 0 to let the + * caller know that we didn't add any new fasync entries. + */ + if (fasync_insert_entry(fd, filp, fapp, new)) { + fasync_free(new); + return 0; + } + + return 1; } /* diff --git a/fs/file_table.c b/fs/file_table.c index a04bdd81c11c..c3dee381f1b4 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -60,7 +60,7 @@ static inline void file_free(struct file *f) /* * Return the total number of open files in the system */ -static int get_nr_files(void) +static long get_nr_files(void) { return percpu_counter_read_positive(&nr_files); } @@ -68,7 +68,7 @@ static int get_nr_files(void) /* * Return the maximum number of open files in the system */ -int get_max_files(void) +unsigned long get_max_files(void) { return files_stat.max_files; } @@ -82,7 +82,7 @@ int proc_nr_files(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { files_stat.nr_files = get_nr_files(); - return proc_dointvec(table, write, buffer, lenp, ppos); + return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #else int proc_nr_files(ctl_table *table, int write, @@ -105,7 +105,7 @@ int proc_nr_files(ctl_table *table, int write, struct file *get_empty_filp(void) { const struct cred *cred = current_cred(); - static int old_max; + static long old_max; struct file * f; /* @@ -140,8 +140,7 @@ struct file *get_empty_filp(void) over: /* Ran out of filps - report that */ if (get_nr_files() > old_max) { - printk(KERN_INFO "VFS: file-max limit %d reached\n", - get_max_files()); + pr_info("VFS: file-max limit %lu reached\n", get_max_files()); old_max = get_nr_files(); } goto fail; @@ -487,7 +486,7 @@ retry: void __init files_init(unsigned long mempages) { - int n; + unsigned long n; filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); @@ -498,9 +497,7 @@ void __init files_init(unsigned long mempages) */ n = (mempages * (PAGE_SIZE / 1024)) / 10; - files_stat.max_files = n; - if (files_stat.max_files < NR_FILE) - files_stat.max_files = NR_FILE; + files_stat.max_files = max_t(unsigned long, n, NR_FILE); files_defer_init(); lg_lock_init(files_lglock); percpu_counter_init(&nr_files, 0); diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c index 79d1b4ea13e7..8c04eac5079d 100644 --- a/fs/freevxfs/vxfs_inode.c +++ b/fs/freevxfs/vxfs_inode.c @@ -260,6 +260,7 @@ vxfs_get_fake_inode(struct super_block *sbp, struct vxfs_inode_info *vip) struct inode *ip = NULL; if ((ip = new_inode(sbp))) { + ip->i_ino = get_next_ino(); vxfs_iinit(ip, vip); ip->i_mapping->a_ops = &vxfs_aops; } diff --git a/fs/freevxfs/vxfs_super.c b/fs/freevxfs/vxfs_super.c index 71b0148b8784..9d1c99558389 100644 --- a/fs/freevxfs/vxfs_super.c +++ b/fs/freevxfs/vxfs_super.c @@ -246,17 +246,16 @@ out: /* * The usual module blurb. */ -static int vxfs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *vxfs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, vxfs_fill_super, - mnt); + return mount_bdev(fs_type, flags, dev_name, data, vxfs_fill_super); } static struct file_system_type vxfs_fs_type = { .owner = THIS_MODULE, .name = "vxfs", - .get_sb = vxfs_get_sb, + .mount = vxfs_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index ab38fef1c9a1..3d06ccc953aa 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -79,6 +79,11 @@ static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) return sb->s_bdi; } +static inline struct inode *wb_inode(struct list_head *head) +{ + return list_entry(head, struct inode, i_wb_list); +} + static void bdi_queue_work(struct backing_dev_info *bdi, struct wb_writeback_work *work) { @@ -172,11 +177,11 @@ static void redirty_tail(struct inode *inode) if (!list_empty(&wb->b_dirty)) { struct inode *tail; - tail = list_entry(wb->b_dirty.next, struct inode, i_list); + tail = wb_inode(wb->b_dirty.next); if (time_before(inode->dirtied_when, tail->dirtied_when)) inode->dirtied_when = jiffies; } - list_move(&inode->i_list, &wb->b_dirty); + list_move(&inode->i_wb_list, &wb->b_dirty); } /* @@ -186,7 +191,7 @@ static void requeue_io(struct inode *inode) { struct bdi_writeback *wb = &inode_to_bdi(inode)->wb; - list_move(&inode->i_list, &wb->b_more_io); + list_move(&inode->i_wb_list, &wb->b_more_io); } static void inode_sync_complete(struct inode *inode) @@ -227,14 +232,14 @@ static void move_expired_inodes(struct list_head *delaying_queue, int do_sb_sort = 0; while (!list_empty(delaying_queue)) { - inode = list_entry(delaying_queue->prev, struct inode, i_list); + inode = wb_inode(delaying_queue->prev); if (older_than_this && inode_dirtied_after(inode, *older_than_this)) break; if (sb && sb != inode->i_sb) do_sb_sort = 1; sb = inode->i_sb; - list_move(&inode->i_list, &tmp); + list_move(&inode->i_wb_list, &tmp); } /* just one sb in list, splice to dispatch_queue and we're done */ @@ -245,12 +250,11 @@ static void move_expired_inodes(struct list_head *delaying_queue, /* Move inodes from one superblock together */ while (!list_empty(&tmp)) { - inode = list_entry(tmp.prev, struct inode, i_list); - sb = inode->i_sb; + sb = wb_inode(tmp.prev)->i_sb; list_for_each_prev_safe(pos, node, &tmp) { - inode = list_entry(pos, struct inode, i_list); + inode = wb_inode(pos); if (inode->i_sb == sb) - list_move(&inode->i_list, dispatch_queue); + list_move(&inode->i_wb_list, dispatch_queue); } } } @@ -408,16 +412,13 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc) * completion. */ redirty_tail(inode); - } else if (atomic_read(&inode->i_count)) { - /* - * The inode is clean, inuse - */ - list_move(&inode->i_list, &inode_in_use); } else { /* - * The inode is clean, unused + * The inode is clean. At this point we either have + * a reference to the inode or it's on it's way out. + * No need to add it back to the LRU. */ - list_move(&inode->i_list, &inode_unused); + list_del_init(&inode->i_wb_list); } } inode_sync_complete(inode); @@ -465,8 +466,7 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb, { while (!list_empty(&wb->b_io)) { long pages_skipped; - struct inode *inode = list_entry(wb->b_io.prev, - struct inode, i_list); + struct inode *inode = wb_inode(wb->b_io.prev); if (inode->i_sb != sb) { if (only_this_sb) { @@ -487,10 +487,16 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb, return 0; } - if (inode->i_state & (I_NEW | I_WILL_FREE)) { + /* + * Don't bother with new inodes or inodes beeing freed, first + * kind does not need peridic writeout yet, and for the latter + * kind writeout is handled by the freer. + */ + if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { requeue_io(inode); continue; } + /* * Was this inode dirtied after sync_sb_inodes was called? * This keeps sync from extra jobs and livelock. @@ -498,7 +504,6 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb, if (inode_dirtied_after(inode, wbc->wb_start)) return 1; - BUG_ON(inode->i_state & I_FREEING); __iget(inode); pages_skipped = wbc->pages_skipped; writeback_single_inode(inode, wbc); @@ -536,8 +541,7 @@ void writeback_inodes_wb(struct bdi_writeback *wb, queue_io(wb, wbc->older_than_this); while (!list_empty(&wb->b_io)) { - struct inode *inode = list_entry(wb->b_io.prev, - struct inode, i_list); + struct inode *inode = wb_inode(wb->b_io.prev); struct super_block *sb = inode->i_sb; if (!pin_sb_for_writeback(sb)) { @@ -582,7 +586,7 @@ static inline bool over_bground_thresh(void) global_dirty_limits(&background_thresh, &dirty_thresh); return (global_page_state(NR_FILE_DIRTY) + - global_page_state(NR_UNSTABLE_NFS) >= background_thresh); + global_page_state(NR_UNSTABLE_NFS) > background_thresh); } /* @@ -675,8 +679,7 @@ static long wb_writeback(struct bdi_writeback *wb, */ spin_lock(&inode_lock); if (!list_empty(&wb->b_more_io)) { - inode = list_entry(wb->b_more_io.prev, - struct inode, i_list); + inode = wb_inode(wb->b_more_io.prev); trace_wbc_writeback_wait(&wbc, wb->bdi); inode_wait_for_writeback(inode); } @@ -704,6 +707,17 @@ get_next_work_item(struct backing_dev_info *bdi) return work; } +/* + * Add in the number of potentially dirty inodes, because each inode + * write can dirty pagecache in the underlying blockdev. + */ +static unsigned long get_nr_dirty_pages(void) +{ + return global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS) + + get_nr_dirty_inodes(); +} + static long wb_check_old_data_flush(struct bdi_writeback *wb) { unsigned long expired; @@ -721,9 +735,7 @@ static long wb_check_old_data_flush(struct bdi_writeback *wb) return 0; wb->last_old_flush = jiffies; - nr_pages = global_page_state(NR_FILE_DIRTY) + - global_page_state(NR_UNSTABLE_NFS) + - (inodes_stat.nr_inodes - inodes_stat.nr_unused); + nr_pages = get_nr_dirty_pages(); if (nr_pages) { struct wb_writeback_work work = { @@ -790,7 +802,7 @@ int bdi_writeback_thread(void *data) struct backing_dev_info *bdi = wb->bdi; long pages_written; - current->flags |= PF_FLUSHER | PF_SWAPWRITE; + current->flags |= PF_SWAPWRITE; set_freezable(); wb->last_active = jiffies; @@ -962,7 +974,7 @@ void __mark_inode_dirty(struct inode *inode, int flags) * dirty list. Add blockdev inodes as well. */ if (!S_ISBLK(inode->i_mode)) { - if (hlist_unhashed(&inode->i_hash)) + if (inode_unhashed(inode)) goto out; } if (inode->i_state & I_FREEING) @@ -990,7 +1002,7 @@ void __mark_inode_dirty(struct inode *inode, int flags) } inode->dirtied_when = jiffies; - list_move(&inode->i_list, &bdi->wb.b_dirty); + list_move(&inode->i_wb_list, &bdi->wb.b_dirty); } } out: @@ -1069,33 +1081,42 @@ static void wait_sb_inodes(struct super_block *sb) } /** - * writeback_inodes_sb - writeback dirty inodes from given super_block + * writeback_inodes_sb_nr - writeback dirty inodes from given super_block * @sb: the superblock + * @nr: the number of pages to write * * Start writeback on some inodes on this super_block. No guarantees are made * on how many (if any) will be written, and this function does not wait - * for IO completion of submitted IO. The number of pages submitted is - * returned. + * for IO completion of submitted IO. */ -void writeback_inodes_sb(struct super_block *sb) +void writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr) { - unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY); - unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS); DECLARE_COMPLETION_ONSTACK(done); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_NONE, .done = &done, + .nr_pages = nr, }; WARN_ON(!rwsem_is_locked(&sb->s_umount)); - - work.nr_pages = nr_dirty + nr_unstable + - (inodes_stat.nr_inodes - inodes_stat.nr_unused); - bdi_queue_work(sb->s_bdi, &work); wait_for_completion(&done); } +EXPORT_SYMBOL(writeback_inodes_sb_nr); + +/** + * writeback_inodes_sb - writeback dirty inodes from given super_block + * @sb: the superblock + * + * Start writeback on some inodes on this super_block. No guarantees are made + * on how many (if any) will be written, and this function does not wait + * for IO completion of submitted IO. + */ +void writeback_inodes_sb(struct super_block *sb) +{ + return writeback_inodes_sb_nr(sb, get_nr_dirty_pages()); +} EXPORT_SYMBOL(writeback_inodes_sb); /** @@ -1118,6 +1139,27 @@ int writeback_inodes_sb_if_idle(struct super_block *sb) EXPORT_SYMBOL(writeback_inodes_sb_if_idle); /** + * writeback_inodes_sb_if_idle - start writeback if none underway + * @sb: the superblock + * @nr: the number of pages to write + * + * Invoke writeback_inodes_sb if no writeback is currently underway. + * Returns 1 if writeback was started, 0 if not. + */ +int writeback_inodes_sb_nr_if_idle(struct super_block *sb, + unsigned long nr) +{ + if (!writeback_in_progress(sb->s_bdi)) { + down_read(&sb->s_umount); + writeback_inodes_sb_nr(sb, nr); + up_read(&sb->s_umount); + return 1; + } else + return 0; +} +EXPORT_SYMBOL(writeback_inodes_sb_nr_if_idle); + +/** * sync_inodes_sb - sync sb inode pages * @sb: the superblock * @@ -1198,3 +1240,23 @@ int sync_inode(struct inode *inode, struct writeback_control *wbc) return ret; } EXPORT_SYMBOL(sync_inode); + +/** + * sync_inode - write an inode to disk + * @inode: the inode to sync + * @wait: wait for I/O to complete. + * + * Write an inode to disk and adjust it's dirty state after completion. + * + * Note: only writes the actual inode, no associated data or other metadata. + */ +int sync_inode_metadata(struct inode *inode, int wait) +{ + struct writeback_control wbc = { + .sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE, + .nr_to_write = 0, /* metadata-only */ + }; + + return sync_inode(inode, &wbc); +} +EXPORT_SYMBOL(sync_inode_metadata); diff --git a/fs/fuse/control.c b/fs/fuse/control.c index 7367e177186f..85542a7daf40 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -222,6 +222,7 @@ static struct dentry *fuse_ctl_add_dentry(struct dentry *parent, if (!inode) return NULL; + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = fc->user_id; inode->i_gid = fc->group_id; @@ -321,12 +322,10 @@ static int fuse_ctl_fill_super(struct super_block *sb, void *data, int silent) return 0; } -static int fuse_ctl_get_sb(struct file_system_type *fs_type, int flags, - const char *dev_name, void *raw_data, - struct vfsmount *mnt) +static struct dentry *fuse_ctl_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data) { - return get_sb_single(fs_type, flags, raw_data, - fuse_ctl_fill_super, mnt); + return mount_single(fs_type, flags, raw_data, fuse_ctl_fill_super); } static void fuse_ctl_kill_sb(struct super_block *sb) @@ -345,7 +344,7 @@ static void fuse_ctl_kill_sb(struct super_block *sb) static struct file_system_type fuse_ctl_fs_type = { .owner = THIS_MODULE, .name = "fusectl", - .get_sb = fuse_ctl_get_sb, + .mount = fuse_ctl_mount, .kill_sb = fuse_ctl_kill_sb, }; diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index cde755cca564..6e07696308dc 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -809,11 +809,9 @@ static int fuse_copy_page(struct fuse_copy_state *cs, struct page **pagep, int err; struct page *page = *pagep; - if (page && zeroing && count < PAGE_SIZE) { - void *mapaddr = kmap_atomic(page, KM_USER1); - memset(mapaddr, 0, PAGE_SIZE); - kunmap_atomic(mapaddr, KM_USER1); - } + if (page && zeroing && count < PAGE_SIZE) + clear_highpage(page); + while (count) { if (cs->write && cs->pipebufs && page) { return fuse_ref_page(cs, page, offset, count); @@ -830,10 +828,10 @@ static int fuse_copy_page(struct fuse_copy_state *cs, struct page **pagep, } } if (page) { - void *mapaddr = kmap_atomic(page, KM_USER1); + void *mapaddr = kmap_atomic(page, KM_USER0); void *buf = mapaddr + offset; offset += fuse_copy_do(cs, &buf, &count); - kunmap_atomic(mapaddr, KM_USER1); + kunmap_atomic(mapaddr, KM_USER0); } else offset += fuse_copy_do(cs, NULL, &count); } @@ -1336,12 +1334,7 @@ out_finish: static void fuse_retrieve_end(struct fuse_conn *fc, struct fuse_req *req) { - int i; - - for (i = 0; i < req->num_pages; i++) { - struct page *page = req->pages[i]; - page_cache_release(page); - } + release_pages(req->pages, req->num_pages, 0); } static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, diff --git a/fs/fuse/file.c b/fs/fuse/file.c index c8224587123f..9242d294fe90 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -134,6 +134,7 @@ EXPORT_SYMBOL_GPL(fuse_do_open); void fuse_finish_open(struct inode *inode, struct file *file) { struct fuse_file *ff = file->private_data; + struct fuse_conn *fc = get_fuse_conn(inode); if (ff->open_flags & FOPEN_DIRECT_IO) file->f_op = &fuse_direct_io_file_operations; @@ -141,6 +142,15 @@ void fuse_finish_open(struct inode *inode, struct file *file) invalidate_inode_pages2(inode->i_mapping); if (ff->open_flags & FOPEN_NONSEEKABLE) nonseekable_open(inode, file); + if (fc->atomic_o_trunc && (file->f_flags & O_TRUNC)) { + struct fuse_inode *fi = get_fuse_inode(inode); + + spin_lock(&fc->lock); + fi->attr_version = ++fc->attr_version; + i_size_write(inode, 0); + spin_unlock(&fc->lock); + fuse_invalidate_attr(inode); + } } int fuse_open_common(struct inode *inode, struct file *file, bool isdir) diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index da9e6e11374c..cfce3ad86a92 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1041,11 +1041,11 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) return err; } -static int fuse_get_sb(struct file_system_type *fs_type, +static struct dentry *fuse_mount(struct file_system_type *fs_type, int flags, const char *dev_name, - void *raw_data, struct vfsmount *mnt) + void *raw_data) { - return get_sb_nodev(fs_type, flags, raw_data, fuse_fill_super, mnt); + return mount_nodev(fs_type, flags, raw_data, fuse_fill_super); } static void fuse_kill_sb_anon(struct super_block *sb) @@ -1065,17 +1065,16 @@ static struct file_system_type fuse_fs_type = { .owner = THIS_MODULE, .name = "fuse", .fs_flags = FS_HAS_SUBTYPE, - .get_sb = fuse_get_sb, + .mount = fuse_mount, .kill_sb = fuse_kill_sb_anon, }; #ifdef CONFIG_BLOCK -static int fuse_get_sb_blk(struct file_system_type *fs_type, +static struct dentry *fuse_mount_blk(struct file_system_type *fs_type, int flags, const char *dev_name, - void *raw_data, struct vfsmount *mnt) + void *raw_data) { - return get_sb_bdev(fs_type, flags, dev_name, raw_data, fuse_fill_super, - mnt); + return mount_bdev(fs_type, flags, dev_name, raw_data, fuse_fill_super); } static void fuse_kill_sb_blk(struct super_block *sb) @@ -1094,7 +1093,7 @@ static void fuse_kill_sb_blk(struct super_block *sb) static struct file_system_type fuseblk_fs_type = { .owner = THIS_MODULE, .name = "fuseblk", - .get_sb = fuse_get_sb_blk, + .mount = fuse_mount_blk, .kill_sb = fuse_kill_sb_blk, .fs_flags = FS_REQUIRES_DEV | FS_HAS_SUBTYPE, }; diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 6b24afb96aae..4f36f8832b9b 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -618,7 +618,6 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping, struct gfs2_alloc *al = NULL; pgoff_t index = pos >> PAGE_CACHE_SHIFT; unsigned from = pos & (PAGE_CACHE_SIZE - 1); - unsigned to = from + len; struct page *page; gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh); @@ -691,7 +690,7 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping, } prepare_write: - error = block_prepare_write(page, from, to, gfs2_block_map); + error = __block_write_begin(page, from, len, gfs2_block_map); out: if (error == 0) return 0; diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c index 06d582732d34..5ab3839dfcb9 100644 --- a/fs/gfs2/export.c +++ b/fs/gfs2/export.c @@ -138,10 +138,8 @@ static struct dentry *gfs2_get_dentry(struct super_block *sb, struct gfs2_inum_host *inum) { struct gfs2_sbd *sdp = sb->s_fs_info; - struct gfs2_holder i_gh; struct inode *inode; struct dentry *dentry; - int error; inode = gfs2_ilookup(sb, inum->no_addr); if (inode) { @@ -152,52 +150,16 @@ static struct dentry *gfs2_get_dentry(struct super_block *sb, goto out_inode; } - error = gfs2_glock_nq_num(sdp, inum->no_addr, &gfs2_inode_glops, - LM_ST_SHARED, LM_FLAG_ANY, &i_gh); - if (error) - return ERR_PTR(error); - - error = gfs2_check_blk_type(sdp, inum->no_addr, GFS2_BLKST_DINODE); - if (error) - goto fail; - - inode = gfs2_inode_lookup(sb, DT_UNKNOWN, inum->no_addr, 0); - if (IS_ERR(inode)) { - error = PTR_ERR(inode); - goto fail; - } - - error = gfs2_inode_refresh(GFS2_I(inode)); - if (error) { - iput(inode); - goto fail; - } - - /* Pick up the works we bypass in gfs2_inode_lookup */ - if (inode->i_state & I_NEW) - gfs2_set_iop(inode); - - if (GFS2_I(inode)->i_no_formal_ino != inum->no_formal_ino) { - iput(inode); - goto fail; - } - - error = -EIO; - if (GFS2_I(inode)->i_diskflags & GFS2_DIF_SYSTEM) { - iput(inode); - goto fail; - } - - gfs2_glock_dq_uninit(&i_gh); + inode = gfs2_lookup_by_inum(sdp, inum->no_addr, &inum->no_formal_ino, + GFS2_BLKST_DINODE); + if (IS_ERR(inode)) + return ERR_CAST(inode); out_inode: dentry = d_obtain_alias(inode); if (!IS_ERR(dentry)) dentry->d_op = &gfs2_dops; return dentry; -fail: - gfs2_glock_dq_uninit(&i_gh); - return ERR_PTR(error); } static struct dentry *gfs2_fh_to_dentry(struct super_block *sb, struct fid *fid, diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 87778857f099..f92c17704169 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -686,21 +686,20 @@ static void delete_work_func(struct work_struct *work) { struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_delete); struct gfs2_sbd *sdp = gl->gl_sbd; - struct gfs2_inode *ip = NULL; + struct gfs2_inode *ip; struct inode *inode; - u64 no_addr = 0; + u64 no_addr = gl->gl_name.ln_number; + + ip = gl->gl_object; + /* Note: Unsafe to dereference ip as we don't hold right refs/locks */ - spin_lock(&gl->gl_spin); - ip = (struct gfs2_inode *)gl->gl_object; if (ip) - no_addr = ip->i_no_addr; - spin_unlock(&gl->gl_spin); - if (ip) { inode = gfs2_ilookup(sdp->sd_vfs, no_addr); - if (inode) { - d_prune_aliases(inode); - iput(inode); - } + else + inode = gfs2_lookup_by_inum(sdp, no_addr, NULL, GFS2_BLKST_UNLINKED); + if (inode && !IS_ERR(inode)) { + d_prune_aliases(inode); + iput(inode); } gfs2_glock_put(gl); } diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 06370f8bd8cf..e1213f7f9217 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -73,49 +73,6 @@ static struct inode *gfs2_iget(struct super_block *sb, u64 no_addr) return iget5_locked(sb, hash, iget_test, iget_set, &no_addr); } -struct gfs2_skip_data { - u64 no_addr; - int skipped; -}; - -static int iget_skip_test(struct inode *inode, void *opaque) -{ - struct gfs2_inode *ip = GFS2_I(inode); - struct gfs2_skip_data *data = opaque; - - if (ip->i_no_addr == data->no_addr) { - if (inode->i_state & (I_FREEING|I_WILL_FREE)){ - data->skipped = 1; - return 0; - } - return 1; - } - return 0; -} - -static int iget_skip_set(struct inode *inode, void *opaque) -{ - struct gfs2_inode *ip = GFS2_I(inode); - struct gfs2_skip_data *data = opaque; - - if (data->skipped) - return 1; - inode->i_ino = (unsigned long)(data->no_addr); - ip->i_no_addr = data->no_addr; - return 0; -} - -static struct inode *gfs2_iget_skip(struct super_block *sb, - u64 no_addr) -{ - struct gfs2_skip_data data; - unsigned long hash = (unsigned long)no_addr; - - data.no_addr = no_addr; - data.skipped = 0; - return iget5_locked(sb, hash, iget_skip_test, iget_skip_set, &data); -} - /** * GFS2 lookup code fills in vfs inode contents based on info obtained * from directory entry inside gfs2_inode_lookup(). This has caused issues @@ -243,93 +200,54 @@ fail: return ERR_PTR(error); } -/** - * gfs2_process_unlinked_inode - Lookup an unlinked inode for reclamation - * and try to reclaim it by doing iput. - * - * This function assumes no rgrp locks are currently held. - * - * @sb: The super block - * no_addr: The inode number - * - */ - -void gfs2_process_unlinked_inode(struct super_block *sb, u64 no_addr) +struct inode *gfs2_lookup_by_inum(struct gfs2_sbd *sdp, u64 no_addr, + u64 *no_formal_ino, unsigned int blktype) { - struct gfs2_sbd *sdp; - struct gfs2_inode *ip; - struct gfs2_glock *io_gl = NULL; - int error; - struct gfs2_holder gh; + struct super_block *sb = sdp->sd_vfs; + struct gfs2_holder i_gh; struct inode *inode; + int error; - inode = gfs2_iget_skip(sb, no_addr); - - if (!inode) - return; - - /* If it's not a new inode, someone's using it, so leave it alone. */ - if (!(inode->i_state & I_NEW)) { - iput(inode); - return; - } - - ip = GFS2_I(inode); - sdp = GFS2_SB(inode); - ip->i_no_formal_ino = -1; + error = gfs2_glock_nq_num(sdp, no_addr, &gfs2_inode_glops, + LM_ST_SHARED, LM_FLAG_ANY, &i_gh); + if (error) + return ERR_PTR(error); - error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl); - if (unlikely(error)) + error = gfs2_check_blk_type(sdp, no_addr, blktype); + if (error) goto fail; - ip->i_gl->gl_object = ip; - error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl); - if (unlikely(error)) - goto fail_put; - - set_bit(GIF_INVALID, &ip->i_flags); - error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, LM_FLAG_TRY | GL_EXACT, - &ip->i_iopen_gh); - if (unlikely(error)) - goto fail_iopen; + inode = gfs2_inode_lookup(sb, DT_UNKNOWN, no_addr, 0); + if (IS_ERR(inode)) + goto fail; - ip->i_iopen_gh.gh_gl->gl_object = ip; - gfs2_glock_put(io_gl); - io_gl = NULL; + error = gfs2_inode_refresh(GFS2_I(inode)); + if (error) + goto fail_iput; - inode->i_mode = DT2IF(DT_UNKNOWN); + /* Pick up the works we bypass in gfs2_inode_lookup */ + if (inode->i_state & I_NEW) + gfs2_set_iop(inode); - /* - * We must read the inode in order to work out its type in - * this case. Note that this doesn't happen often as we normally - * know the type beforehand. This code path only occurs during - * unlinked inode recovery (where it is safe to do this glock, - * which is not true in the general case). - */ - error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, LM_FLAG_TRY, - &gh); - if (unlikely(error)) - goto fail_glock; + /* Two extra checks for NFS only */ + if (no_formal_ino) { + error = -ESTALE; + if (GFS2_I(inode)->i_no_formal_ino != *no_formal_ino) + goto fail_iput; - /* Inode is now uptodate */ - gfs2_glock_dq_uninit(&gh); - gfs2_set_iop(inode); + error = -EIO; + if (GFS2_I(inode)->i_diskflags & GFS2_DIF_SYSTEM) + goto fail_iput; - /* The iput will cause it to be deleted. */ - iput(inode); - return; + error = 0; + } -fail_glock: - gfs2_glock_dq(&ip->i_iopen_gh); -fail_iopen: - if (io_gl) - gfs2_glock_put(io_gl); -fail_put: - ip->i_gl->gl_object = NULL; - gfs2_glock_put(ip->i_gl); fail: - iget_failed(inode); - return; + gfs2_glock_dq_uninit(&i_gh); + return error ? ERR_PTR(error) : inode; +fail_iput: + iput(inode); + goto fail; } static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h index 6720d7d5fbc6..d8499fadcc53 100644 --- a/fs/gfs2/inode.h +++ b/fs/gfs2/inode.h @@ -99,7 +99,9 @@ err: extern void gfs2_set_iop(struct inode *inode); extern struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, u64 no_addr, u64 no_formal_ino); -extern void gfs2_process_unlinked_inode(struct super_block *sb, u64 no_addr); +extern struct inode *gfs2_lookup_by_inum(struct gfs2_sbd *sdp, u64 no_addr, + u64 *no_formal_ino, + unsigned int blktype); extern struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr); extern int gfs2_inode_refresh(struct gfs2_inode *ip); diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index f3b071f921aa..939739c7b3f9 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -55,7 +55,7 @@ static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wb * activity, but those code paths have their own higher-level * throttling. */ - if (wbc->sync_mode != WB_SYNC_NONE || !wbc->nonblocking) { + if (wbc->sync_mode != WB_SYNC_NONE) { lock_buffer(bh); } else if (!trylock_buffer(bh)) { redirty_page_for_writepage(wbc, page); diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index aeafc233dc89..3eb1393f7b81 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -1219,7 +1219,6 @@ fail_sb: fail_locking: init_locking(sdp, &mount_gh, UNDO); fail_lm: - invalidate_inodes(sb); gfs2_gl_hash_clear(sdp); gfs2_lm_unmount(sdp); fail_sys: @@ -1251,12 +1250,11 @@ static int test_gfs2_super(struct super_block *s, void *ptr) } /** - * gfs2_get_sb - Get the GFS2 superblock + * gfs2_mount - Get the GFS2 superblock * @fs_type: The GFS2 filesystem type * @flags: Mount flags * @dev_name: The name of the device * @data: The mount arguments - * @mnt: The vfsmnt for this mount * * Q. Why not use get_sb_bdev() ? * A. We need to select one of two root directories to mount, independent @@ -1265,8 +1263,8 @@ static int test_gfs2_super(struct super_block *s, void *ptr) * Returns: 0 or -ve on error */ -static int gfs2_get_sb(struct file_system_type *fs_type, int flags, - const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *data) { struct block_device *bdev; struct super_block *s; @@ -1280,7 +1278,7 @@ static int gfs2_get_sb(struct file_system_type *fs_type, int flags, bdev = open_bdev_exclusive(dev_name, mode, fs_type); if (IS_ERR(bdev)) - return PTR_ERR(bdev); + return ERR_CAST(bdev); /* * once the super is inserted into the list by sget, s_umount @@ -1299,6 +1297,9 @@ static int gfs2_get_sb(struct file_system_type *fs_type, int flags, if (IS_ERR(s)) goto error_bdev; + if (s->s_root) + close_bdev_exclusive(bdev, mode); + memset(&args, 0, sizeof(args)); args.ar_quota = GFS2_QUOTA_DEFAULT; args.ar_data = GFS2_DATA_DEFAULT; @@ -1310,17 +1311,13 @@ static int gfs2_get_sb(struct file_system_type *fs_type, int flags, error = gfs2_mount_args(&args, data); if (error) { printk(KERN_WARNING "GFS2: can't parse mount arguments\n"); - if (s->s_root) - goto error_super; - deactivate_locked_super(s); - return error; + goto error_super; } if (s->s_root) { error = -EBUSY; if ((flags ^ s->s_flags) & MS_RDONLY) goto error_super; - close_bdev_exclusive(bdev, mode); } else { char b[BDEVNAME_SIZE]; @@ -1329,27 +1326,24 @@ static int gfs2_get_sb(struct file_system_type *fs_type, int flags, strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id)); sb_set_blocksize(s, block_size(bdev)); error = fill_super(s, &args, flags & MS_SILENT ? 1 : 0); - if (error) { - deactivate_locked_super(s); - return error; - } + if (error) + goto error_super; s->s_flags |= MS_ACTIVE; bdev->bd_super = s; } sdp = s->s_fs_info; - mnt->mnt_sb = s; if (args.ar_meta) - mnt->mnt_root = dget(sdp->sd_master_dir); + return dget(sdp->sd_master_dir); else - mnt->mnt_root = dget(sdp->sd_root_dir); - return 0; + return dget(sdp->sd_root_dir); error_super: deactivate_locked_super(s); + return ERR_PTR(error); error_bdev: close_bdev_exclusive(bdev, mode); - return error; + return ERR_PTR(error); } static int set_meta_super(struct super_block *s, void *ptr) @@ -1357,8 +1351,8 @@ static int set_meta_super(struct super_block *s, void *ptr) return -EINVAL; } -static int gfs2_get_sb_meta(struct file_system_type *fs_type, int flags, - const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *gfs2_mount_meta(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { struct super_block *s; struct gfs2_sbd *sdp; @@ -1369,23 +1363,21 @@ static int gfs2_get_sb_meta(struct file_system_type *fs_type, int flags, if (error) { printk(KERN_WARNING "GFS2: path_lookup on %s returned error %d\n", dev_name, error); - return error; + return ERR_PTR(error); } s = sget(&gfs2_fs_type, test_gfs2_super, set_meta_super, path.dentry->d_inode->i_sb->s_bdev); path_put(&path); if (IS_ERR(s)) { printk(KERN_WARNING "GFS2: gfs2 mount does not exist\n"); - return PTR_ERR(s); + return ERR_CAST(s); } if ((flags ^ s->s_flags) & MS_RDONLY) { deactivate_locked_super(s); - return -EBUSY; + return ERR_PTR(-EBUSY); } sdp = s->s_fs_info; - mnt->mnt_sb = s; - mnt->mnt_root = dget(sdp->sd_master_dir); - return 0; + return dget(sdp->sd_master_dir); } static void gfs2_kill_sb(struct super_block *sb) @@ -1411,7 +1403,7 @@ static void gfs2_kill_sb(struct super_block *sb) struct file_system_type gfs2_fs_type = { .name = "gfs2", .fs_flags = FS_REQUIRES_DEV, - .get_sb = gfs2_get_sb, + .mount = gfs2_mount, .kill_sb = gfs2_kill_sb, .owner = THIS_MODULE, }; @@ -1419,7 +1411,7 @@ struct file_system_type gfs2_fs_type = { struct file_system_type gfs2meta_fs_type = { .name = "gfs2meta", .fs_flags = FS_REQUIRES_DEV, - .get_sb = gfs2_get_sb_meta, + .mount = gfs2_mount_meta, .owner = THIS_MODULE, }; diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c index 0534510200d5..12cbea7502c2 100644 --- a/fs/gfs2/ops_inode.c +++ b/fs/gfs2/ops_inode.c @@ -255,7 +255,7 @@ out_parent: gfs2_holder_uninit(ghs); gfs2_holder_uninit(ghs + 1); if (!error) { - atomic_inc(&inode->i_count); + ihold(inode); d_instantiate(dentry, inode); mark_inode_dirty(inode); } @@ -1294,7 +1294,7 @@ static int write_empty_blocks(struct page *page, unsigned from, unsigned to) int error; if (!page_has_buffers(page)) { - error = block_prepare_write(page, from, to, gfs2_block_map); + error = __block_write_begin(page, from, to - from, gfs2_block_map); if (unlikely(error)) return error; @@ -1313,7 +1313,7 @@ static int write_empty_blocks(struct page *page, unsigned from, unsigned to) next += bh->b_size; if (buffer_mapped(bh)) { if (end) { - error = block_prepare_write(page, start, end, + error = __block_write_begin(page, start, end - start, gfs2_block_map); if (unlikely(error)) return error; @@ -1328,7 +1328,7 @@ static int write_empty_blocks(struct page *page, unsigned from, unsigned to) } while (next < to); if (end) { - error = block_prepare_write(page, start, end, gfs2_block_map); + error = __block_write_begin(page, start, end - start, gfs2_block_map); if (unlikely(error)) return error; empty_write_end(page, start, end); diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 58a9b9998b42..f606baf9ba72 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -631,6 +631,7 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc, struct fs_disk_quota *fdq) { struct inode *inode = &ip->i_inode; + struct gfs2_sbd *sdp = GFS2_SB(inode); struct address_space *mapping = inode->i_mapping; unsigned long index = loc >> PAGE_CACHE_SHIFT; unsigned offset = loc & (PAGE_CACHE_SIZE - 1); @@ -658,11 +659,11 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc, qd->qd_qb.qb_value = qp->qu_value; if (fdq) { if (fdq->d_fieldmask & FS_DQ_BSOFT) { - qp->qu_warn = cpu_to_be64(fdq->d_blk_softlimit); + qp->qu_warn = cpu_to_be64(fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift); qd->qd_qb.qb_warn = qp->qu_warn; } if (fdq->d_fieldmask & FS_DQ_BHARD) { - qp->qu_limit = cpu_to_be64(fdq->d_blk_hardlimit); + qp->qu_limit = cpu_to_be64(fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift); qd->qd_qb.qb_limit = qp->qu_limit; } } @@ -1497,9 +1498,9 @@ static int gfs2_get_dqblk(struct super_block *sb, int type, qid_t id, fdq->d_version = FS_DQUOT_VERSION; fdq->d_flags = (type == QUOTA_USER) ? FS_USER_QUOTA : FS_GROUP_QUOTA; fdq->d_id = id; - fdq->d_blk_hardlimit = be64_to_cpu(qlvb->qb_limit); - fdq->d_blk_softlimit = be64_to_cpu(qlvb->qb_warn); - fdq->d_bcount = be64_to_cpu(qlvb->qb_value); + fdq->d_blk_hardlimit = be64_to_cpu(qlvb->qb_limit) << sdp->sd_fsb2bb_shift; + fdq->d_blk_softlimit = be64_to_cpu(qlvb->qb_warn) << sdp->sd_fsb2bb_shift; + fdq->d_bcount = be64_to_cpu(qlvb->qb_value) << sdp->sd_fsb2bb_shift; gfs2_glock_dq_uninit(&q_gh); out: @@ -1566,10 +1567,10 @@ static int gfs2_set_dqblk(struct super_block *sb, int type, qid_t id, /* If nothing has changed, this is a no-op */ if ((fdq->d_fieldmask & FS_DQ_BSOFT) && - (fdq->d_blk_softlimit == be64_to_cpu(qd->qd_qb.qb_warn))) + ((fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_warn))) fdq->d_fieldmask ^= FS_DQ_BSOFT; if ((fdq->d_fieldmask & FS_DQ_BHARD) && - (fdq->d_blk_hardlimit == be64_to_cpu(qd->qd_qb.qb_limit))) + ((fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_limit))) fdq->d_fieldmask ^= FS_DQ_BHARD; if (fdq->d_fieldmask == 0) goto out_i; diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index bef3ab6cf5c1..33c8407b876f 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -963,17 +963,18 @@ static int try_rgrp_fit(struct gfs2_rgrpd *rgd, struct gfs2_alloc *al) * The inode, if one has been found, in inode. */ -static u64 try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked, - u64 skip) +static void try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked, u64 skip) { u32 goal = 0, block; u64 no_addr; struct gfs2_sbd *sdp = rgd->rd_sbd; unsigned int n; + struct gfs2_glock *gl; + struct gfs2_inode *ip; + int error; + int found = 0; - for(;;) { - if (goal >= rgd->rd_data) - break; + while (goal < rgd->rd_data) { down_write(&sdp->sd_log_flush_lock); n = 1; block = rgblk_search(rgd, goal, GFS2_BLKST_UNLINKED, @@ -990,11 +991,32 @@ static u64 try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked, if (no_addr == skip) continue; *last_unlinked = no_addr; - return no_addr; + + error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &gl); + if (error) + continue; + + /* If the inode is already in cache, we can ignore it here + * because the existing inode disposal code will deal with + * it when all refs have gone away. Accessing gl_object like + * this is not safe in general. Here it is ok because we do + * not dereference the pointer, and we only need an approx + * answer to whether it is NULL or not. + */ + ip = gl->gl_object; + + if (ip || queue_work(gfs2_delete_workqueue, &gl->gl_delete) == 0) + gfs2_glock_put(gl); + else + found++; + + /* Limit reclaim to sensible number of tasks */ + if (found > 2*NR_CPUS) + return; } rgd->rd_flags &= ~GFS2_RDF_CHECK; - return 0; + return; } /** @@ -1075,11 +1097,9 @@ static void forward_rgrp_set(struct gfs2_sbd *sdp, struct gfs2_rgrpd *rgd) * Try to acquire rgrp in way which avoids contending with others. * * Returns: errno - * unlinked: the block address of an unlinked block to be reclaimed */ -static int get_local_rgrp(struct gfs2_inode *ip, u64 *unlinked, - u64 *last_unlinked) +static int get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_rgrpd *rgd, *begin = NULL; @@ -1089,7 +1109,6 @@ static int get_local_rgrp(struct gfs2_inode *ip, u64 *unlinked, int loops = 0; int error, rg_locked; - *unlinked = 0; rgd = gfs2_blk2rgrpd(sdp, ip->i_goal); while (rgd) { @@ -1106,17 +1125,10 @@ static int get_local_rgrp(struct gfs2_inode *ip, u64 *unlinked, case 0: if (try_rgrp_fit(rgd, al)) goto out; - /* If the rg came in already locked, there's no - way we can recover from a failed try_rgrp_unlink - because that would require an iput which can only - happen after the rgrp is unlocked. */ - if (!rg_locked && rgd->rd_flags & GFS2_RDF_CHECK) - *unlinked = try_rgrp_unlink(rgd, last_unlinked, - ip->i_no_addr); + if (rgd->rd_flags & GFS2_RDF_CHECK) + try_rgrp_unlink(rgd, last_unlinked, ip->i_no_addr); if (!rg_locked) gfs2_glock_dq_uninit(&al->al_rgd_gh); - if (*unlinked) - return -EAGAIN; /* fall through */ case GLR_TRYFAILED: rgd = recent_rgrp_next(rgd); @@ -1145,13 +1157,10 @@ static int get_local_rgrp(struct gfs2_inode *ip, u64 *unlinked, case 0: if (try_rgrp_fit(rgd, al)) goto out; - if (!rg_locked && rgd->rd_flags & GFS2_RDF_CHECK) - *unlinked = try_rgrp_unlink(rgd, last_unlinked, - ip->i_no_addr); + if (rgd->rd_flags & GFS2_RDF_CHECK) + try_rgrp_unlink(rgd, last_unlinked, ip->i_no_addr); if (!rg_locked) gfs2_glock_dq_uninit(&al->al_rgd_gh); - if (*unlinked) - return -EAGAIN; break; case GLR_TRYFAILED: @@ -1204,12 +1213,12 @@ int gfs2_inplace_reserve_i(struct gfs2_inode *ip, int hold_rindex, struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_alloc *al = ip->i_alloc; int error = 0; - u64 last_unlinked = NO_BLOCK, unlinked; + u64 last_unlinked = NO_BLOCK; + int tries = 0; if (gfs2_assert_warn(sdp, al->al_requested)) return -EINVAL; -try_again: if (hold_rindex) { /* We need to hold the rindex unless the inode we're using is the rindex itself, in which case it's already held. */ @@ -1218,31 +1227,23 @@ try_again: else if (!sdp->sd_rgrps) /* We may not have the rindex read in, so: */ error = gfs2_ri_update_special(ip); + if (error) + return error; } - if (error) - return error; + do { + error = get_local_rgrp(ip, &last_unlinked); + /* If there is no space, flushing the log may release some */ + if (error) + gfs2_log_flush(sdp, NULL); + } while (error && tries++ < 3); - /* Find an rgrp suitable for allocation. If it encounters any unlinked - dinodes along the way, error will equal -EAGAIN and unlinked will - contains it block address. We then need to look up that inode and - try to free it, and try the allocation again. */ - error = get_local_rgrp(ip, &unlinked, &last_unlinked); if (error) { if (hold_rindex && ip != GFS2_I(sdp->sd_rindex)) gfs2_glock_dq_uninit(&al->al_ri_gh); - if (error != -EAGAIN) - return error; - - gfs2_process_unlinked_inode(ip->i_inode.i_sb, unlinked); - /* regardless of whether or not gfs2_process_unlinked_inode - was successful, we don't want to repeat it again. */ - last_unlinked = unlinked; - gfs2_log_flush(sdp, NULL); - error = 0; - - goto try_again; + return error; } + /* no error, so we have the rgrp set in the inode's allocation. */ al->al_file = file; al->al_line = line; diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 047d1176096c..2b2c4997430b 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -857,7 +857,6 @@ restart: gfs2_clear_rgrpd(sdp); gfs2_jindex_free(sdp); /* Take apart glock structures and buffer lists */ - invalidate_inodes(sdp->sd_vfs); gfs2_gl_hash_clear(sdp); /* Unmount the locking protocol */ gfs2_lm_unmount(sdp); diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h index 4f55651aaa51..c8cffb81e849 100644 --- a/fs/hfs/hfs_fs.h +++ b/fs/hfs/hfs_fs.h @@ -147,8 +147,6 @@ struct hfs_sb_info { u16 blockoffset; int fs_div; - - struct hlist_head rsrc_inodes; }; #define HFS_FLG_BITMAP_DIRTY 0 @@ -254,17 +252,6 @@ static inline void hfs_bitmap_dirty(struct super_block *sb) sb->s_dirt = 1; } -static inline void hfs_buffer_sync(struct buffer_head *bh) -{ - while (buffer_locked(bh)) { - wait_on_buffer(bh); - } - if (buffer_dirty(bh)) { - ll_rw_block(WRITE, 1, &bh); - wait_on_buffer(bh); - } -} - #define sb_bread512(sb, sec, data) ({ \ struct buffer_head *__bh; \ sector_t __block; \ diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 397b7adc7ce6..dffb4e996643 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -524,7 +524,7 @@ static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry, HFS_I(inode)->rsrc_inode = dir; HFS_I(dir)->rsrc_inode = inode; igrab(dir); - hlist_add_head(&inode->i_hash, &HFS_SB(dir->i_sb)->rsrc_inodes); + hlist_add_fake(&inode->i_hash); mark_inode_dirty(inode); out: d_add(dentry, inode); diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c index 86428f5ac991..1563d5ce5764 100644 --- a/fs/hfs/mdb.c +++ b/fs/hfs/mdb.c @@ -220,7 +220,7 @@ int hfs_mdb_get(struct super_block *sb) mdb->drLsMod = hfs_mtime(); mark_buffer_dirty(HFS_SB(sb)->mdb_bh); - hfs_buffer_sync(HFS_SB(sb)->mdb_bh); + sync_dirty_buffer(HFS_SB(sb)->mdb_bh); } return 0; @@ -287,7 +287,7 @@ void hfs_mdb_commit(struct super_block *sb) HFS_SB(sb)->alt_mdb->drAtrb |= cpu_to_be16(HFS_SB_ATTRIB_UNMNT); HFS_SB(sb)->alt_mdb->drAtrb &= cpu_to_be16(~HFS_SB_ATTRIB_INCNSTNT); mark_buffer_dirty(HFS_SB(sb)->alt_mdb_bh); - hfs_buffer_sync(HFS_SB(sb)->alt_mdb_bh); + sync_dirty_buffer(HFS_SB(sb)->alt_mdb_bh); } if (test_and_clear_bit(HFS_FLG_BITMAP_DIRTY, &HFS_SB(sb)->flags)) { diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 33254160f650..4824c27cebb8 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -382,7 +382,6 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent) return -ENOMEM; sb->s_fs_info = sbi; - INIT_HLIST_HEAD(&sbi->rsrc_inodes); res = -EINVAL; if (!parse_options((char *)data, sbi)) { @@ -442,17 +441,16 @@ bail: return res; } -static int hfs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, - struct vfsmount *mnt) +static struct dentry *hfs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, hfs_fill_super, mnt); + return mount_bdev(fs_type, flags, dev_name, data, hfs_fill_super); } static struct file_system_type hfs_fs_type = { .owner = THIS_MODULE, .name = "hfs", - .get_sb = hfs_get_sb, + .mount = hfs_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index d236d85ec9d7..9d59c0571f59 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -286,7 +286,7 @@ static int hfsplus_link(struct dentry *src_dentry, struct inode *dst_dir, inc_nlink(inode); hfsplus_instantiate(dst_dentry, inode, cnid); - atomic_inc(&inode->i_count); + ihold(inode); inode->i_ctime = CURRENT_TIME_SEC; mark_inode_dirty(inode); sbi->file_count++; @@ -317,8 +317,10 @@ static int hfsplus_unlink(struct inode *dir, struct dentry *dentry) res = hfsplus_rename_cat(inode->i_ino, dir, &dentry->d_name, sbi->hidden_dir, &str); - if (!res) + if (!res) { inode->i_flags |= S_DEAD; + drop_nlink(inode); + } goto out; } res = hfsplus_delete_cat(cnid, dir, &dentry->d_name); diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 78449280dae0..8afd7e84f98d 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -211,7 +211,7 @@ static struct dentry *hfsplus_file_lookup(struct inode *dir, struct dentry *dent * appear hashed, but do not put on any lists. hlist_del() * will work fine and require no locking. */ - inode->i_hash.pprev = &inode->i_hash.next; + hlist_add_fake(&inode->i_hash); mark_inode_dirty(inode); out: diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c index 5b4667e08ef7..40a85a3ded6e 100644 --- a/fs/hfsplus/ioctl.c +++ b/fs/hfsplus/ioctl.c @@ -92,7 +92,7 @@ static int hfsplus_ioctl_setflags(struct file *file, int __user *user_flags) mark_inode_dirty(inode); out_unlock_inode: - mutex_lock(&inode->i_mutex); + mutex_unlock(&inode->i_mutex); out_drop_write: mnt_drop_write(file->f_path.mnt); out: diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 9a88d7536103..52cc746d3ba3 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -495,18 +495,16 @@ static void hfsplus_destroy_inode(struct inode *inode) #define HFSPLUS_INODE_SIZE sizeof(struct hfsplus_inode_info) -static int hfsplus_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, - struct vfsmount *mnt) +static struct dentry *hfsplus_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, hfsplus_fill_super, - mnt); + return mount_bdev(fs_type, flags, dev_name, data, hfsplus_fill_super); } static struct file_system_type hfsplus_fs_type = { .owner = THIS_MODULE, .name = "hfsplus", - .get_sb = hfsplus_get_sb, + .mount = hfsplus_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/hostfs/hostfs.h b/fs/hostfs/hostfs.h index 7c232c1487ee..bf15a43016b9 100644 --- a/fs/hostfs/hostfs.h +++ b/fs/hostfs/hostfs.h @@ -91,7 +91,6 @@ extern int rename_file(char *from, char *to); extern int do_statfs(char *root, long *bsize_out, long long *blocks_out, long long *bfree_out, long long *bavail_out, long long *files_out, long long *ffree_out, - void *fsid_out, int fsid_size, long *namelen_out, - long *spare_out); + void *fsid_out, int fsid_size, long *namelen_out); #endif diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index f7dc9b5f9ef8..2c0f148a49e6 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -217,7 +217,7 @@ int hostfs_statfs(struct dentry *dentry, struct kstatfs *sf) err = do_statfs(dentry->d_sb->s_fs_info, &sf->f_bsize, &f_blocks, &f_bfree, &f_bavail, &f_files, &f_ffree, &sf->f_fsid, sizeof(sf->f_fsid), - &sf->f_namelen, sf->f_spare); + &sf->f_namelen); if (err) return err; sf->f_blocks = f_blocks; @@ -962,11 +962,11 @@ out: return err; } -static int hostfs_read_sb(struct file_system_type *type, +static struct dentry *hostfs_read_sb(struct file_system_type *type, int flags, const char *dev_name, - void *data, struct vfsmount *mnt) + void *data) { - return get_sb_nodev(type, flags, data, hostfs_fill_sb_common, mnt); + return mount_nodev(type, flags, data, hostfs_fill_sb_common); } static void hostfs_kill_sb(struct super_block *s) @@ -978,7 +978,7 @@ static void hostfs_kill_sb(struct super_block *s) static struct file_system_type hostfs_type = { .owner = THIS_MODULE, .name = "hostfs", - .get_sb = hostfs_read_sb, + .mount = hostfs_read_sb, .kill_sb = hostfs_kill_sb, .fs_flags = 0, }; diff --git a/fs/hostfs/hostfs_user.c b/fs/hostfs/hostfs_user.c index 6777aa06ce2c..d51a98384bc0 100644 --- a/fs/hostfs/hostfs_user.c +++ b/fs/hostfs/hostfs_user.c @@ -94,8 +94,7 @@ void *open_dir(char *path, int *err_out) dir = opendir(path); *err_out = errno; - if (dir == NULL) - return NULL; + return dir; } @@ -205,7 +204,7 @@ int set_attr(const char *file, struct hostfs_iattr *attrs, int fd) if (attrs->ia_valid & HOSTFS_ATTR_MODE) { if (fd >= 0) { if (fchmod(fd, attrs->ia_mode) != 0) - return (-errno); + return -errno; } else if (chmod(file, attrs->ia_mode) != 0) { return -errno; } @@ -364,8 +363,7 @@ int rename_file(char *from, char *to) int do_statfs(char *root, long *bsize_out, long long *blocks_out, long long *bfree_out, long long *bavail_out, long long *files_out, long long *ffree_out, - void *fsid_out, int fsid_size, long *namelen_out, - long *spare_out) + void *fsid_out, int fsid_size, long *namelen_out) { struct statfs64 buf; int err; @@ -384,10 +382,6 @@ int do_statfs(char *root, long *bsize_out, long long *blocks_out, sizeof(buf.f_fsid) > fsid_size ? fsid_size : sizeof(buf.f_fsid)); *namelen_out = buf.f_namelen; - spare_out[0] = buf.f_spare[0]; - spare_out[1] = buf.f_spare[1]; - spare_out[2] = buf.f_spare[2]; - spare_out[3] = buf.f_spare[3]; - spare_out[4] = buf.f_spare[4]; + return 0; } diff --git a/fs/hpfs/buffer.c b/fs/hpfs/buffer.c index eac5f96323e3..793cb9d943d2 100644 --- a/fs/hpfs/buffer.c +++ b/fs/hpfs/buffer.c @@ -14,7 +14,7 @@ void hpfs_lock_creation(struct super_block *s) #ifdef DEBUG_LOCKS printk("lock creation\n"); #endif - down(&hpfs_sb(s)->hpfs_creation_de); + mutex_lock(&hpfs_sb(s)->hpfs_creation_de); } void hpfs_unlock_creation(struct super_block *s) @@ -22,7 +22,7 @@ void hpfs_unlock_creation(struct super_block *s) #ifdef DEBUG_LOCKS printk("unlock creation\n"); #endif - up(&hpfs_sb(s)->hpfs_creation_de); + mutex_unlock(&hpfs_sb(s)->hpfs_creation_de); } /* Map a sector into a buffer and return pointers to it and to the buffer. */ diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h index b59eac0232a0..2fee17d0d9ab 100644 --- a/fs/hpfs/hpfs_fn.h +++ b/fs/hpfs/hpfs_fn.h @@ -87,7 +87,7 @@ struct hpfs_sb_info { unsigned *sb_bmp_dir; /* main bitmap directory */ unsigned sb_c_bitmap; /* current bitmap */ unsigned sb_max_fwd_alloc; /* max forwad allocation */ - struct semaphore hpfs_creation_de; /* when creating dirents, nobody else + struct mutex hpfs_creation_de; /* when creating dirents, nobody else can alloc blocks */ /*unsigned sb_mounting : 1;*/ int sb_timeshift; diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index c969a1aa163a..6c5f01597c3a 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -491,7 +491,7 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent) sbi->sb_bmp_dir = NULL; sbi->sb_cp_table = NULL; - init_MUTEX(&sbi->hpfs_creation_de); + mutex_init(&sbi->hpfs_creation_de); uid = current_uid(); gid = current_gid(); @@ -686,17 +686,16 @@ bail0: return -EINVAL; } -static int hpfs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *hpfs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, hpfs_fill_super, - mnt); + return mount_bdev(fs_type, flags, dev_name, data, hpfs_fill_super); } static struct file_system_type hpfs_fs_type = { .owner = THIS_MODULE, .name = "hpfs", - .get_sb = hpfs_get_sb, + .mount = hpfs_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c index 4e2a45ea6140..f702b5f713fc 100644 --- a/fs/hppfs/hppfs.c +++ b/fs/hppfs/hppfs.c @@ -748,17 +748,17 @@ static int hppfs_fill_super(struct super_block *sb, void *d, int silent) return(err); } -static int hppfs_read_super(struct file_system_type *type, +static struct dentry *hppfs_read_super(struct file_system_type *type, int flags, const char *dev_name, - void *data, struct vfsmount *mnt) + void *data) { - return get_sb_nodev(type, flags, data, hppfs_fill_super, mnt); + return mount_nodev(type, flags, data, hppfs_fill_super); } static struct file_system_type hppfs_type = { .owner = THIS_MODULE, .name = "hppfs", - .get_sb = hppfs_read_super, + .mount = hppfs_read_super, .kill_sb = kill_anon_super, .fs_flags = 0, }; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 113eba3d3c38..a5fe68189eed 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -31,6 +31,7 @@ #include <linux/statfs.h> #include <linux/security.h> #include <linux/magic.h> +#include <linux/migrate.h> #include <asm/uaccess.h> @@ -455,6 +456,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid, inode = new_inode(sb); if (inode) { struct hugetlbfs_inode_info *info; + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = uid; inode->i_gid = gid; @@ -573,6 +575,19 @@ static int hugetlbfs_set_page_dirty(struct page *page) return 0; } +static int hugetlbfs_migrate_page(struct address_space *mapping, + struct page *newpage, struct page *page) +{ + int rc; + + rc = migrate_huge_page_move_mapping(mapping, newpage, page); + if (rc) + return rc; + migrate_page_copy(newpage, page); + + return 0; +} + static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb); @@ -659,6 +674,7 @@ static const struct address_space_operations hugetlbfs_aops = { .write_begin = hugetlbfs_write_begin, .write_end = hugetlbfs_write_end, .set_page_dirty = hugetlbfs_set_page_dirty, + .migratepage = hugetlbfs_migrate_page, }; @@ -880,15 +896,15 @@ void hugetlb_put_quota(struct address_space *mapping, long delta) } } -static int hugetlbfs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *hugetlbfs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_nodev(fs_type, flags, data, hugetlbfs_fill_super, mnt); + return mount_nodev(fs_type, flags, data, hugetlbfs_fill_super); } static struct file_system_type hugetlbfs_fs_type = { .name = "hugetlbfs", - .get_sb = hugetlbfs_get_sb, + .mount = hugetlbfs_mount, .kill_sb = kill_litter_super, }; @@ -916,8 +932,7 @@ struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag, if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) { *user = current_user(); if (user_shm_lock(size, *user)) { - WARN_ONCE(1, - "Using mlock ulimits for SHM_HUGETLB deprecated\n"); + printk_once(KERN_WARNING "Using mlock ulimits for SHM_HUGETLB is deprecated\n"); } else { *user = NULL; return ERR_PTR(-EPERM); diff --git a/fs/inode.c b/fs/inode.c index 86464332e590..ae2727ab0c3a 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -24,11 +24,11 @@ #include <linux/mount.h> #include <linux/async.h> #include <linux/posix_acl.h> +#include <linux/ima.h> /* * This is needed for the following functions: * - inode_has_buffers - * - invalidate_inode_buffers * - invalidate_bdev * * FIXME: remove all knowledge of the buffer layer from this file @@ -72,8 +72,7 @@ static unsigned int i_hash_shift __read_mostly; * allowing for low-overhead inode sync() operations. */ -LIST_HEAD(inode_in_use); -LIST_HEAD(inode_unused); +static LIST_HEAD(inode_lru); static struct hlist_head *inode_hashtable __read_mostly; /* @@ -103,8 +102,41 @@ static DECLARE_RWSEM(iprune_sem); */ struct inodes_stat_t inodes_stat; +static struct percpu_counter nr_inodes __cacheline_aligned_in_smp; +static struct percpu_counter nr_inodes_unused __cacheline_aligned_in_smp; + static struct kmem_cache *inode_cachep __read_mostly; +static inline int get_nr_inodes(void) +{ + return percpu_counter_sum_positive(&nr_inodes); +} + +static inline int get_nr_inodes_unused(void) +{ + return percpu_counter_sum_positive(&nr_inodes_unused); +} + +int get_nr_dirty_inodes(void) +{ + int nr_dirty = get_nr_inodes() - get_nr_inodes_unused(); + return nr_dirty > 0 ? nr_dirty : 0; + +} + +/* + * Handle nr_inode sysctl + */ +#ifdef CONFIG_SYSCTL +int proc_nr_inodes(ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + inodes_stat.nr_inodes = get_nr_inodes(); + inodes_stat.nr_unused = get_nr_inodes_unused(); + return proc_dointvec(table, write, buffer, lenp, ppos); +} +#endif + static void wake_up_inode(struct inode *inode) { /* @@ -192,6 +224,8 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_fsnotify_mask = 0; #endif + percpu_counter_inc(&nr_inodes); + return 0; out: return -ENOMEM; @@ -232,11 +266,13 @@ void __destroy_inode(struct inode *inode) if (inode->i_default_acl && inode->i_default_acl != ACL_NOT_CACHED) posix_acl_release(inode->i_default_acl); #endif + percpu_counter_dec(&nr_inodes); } EXPORT_SYMBOL(__destroy_inode); -void destroy_inode(struct inode *inode) +static void destroy_inode(struct inode *inode) { + BUG_ON(!list_empty(&inode->i_lru)); __destroy_inode(inode); if (inode->i_sb->s_op->destroy_inode) inode->i_sb->s_op->destroy_inode(inode); @@ -255,6 +291,8 @@ void inode_init_once(struct inode *inode) INIT_HLIST_NODE(&inode->i_hash); INIT_LIST_HEAD(&inode->i_dentry); INIT_LIST_HEAD(&inode->i_devices); + INIT_LIST_HEAD(&inode->i_wb_list); + INIT_LIST_HEAD(&inode->i_lru); INIT_RADIX_TREE(&inode->i_data.page_tree, GFP_ATOMIC); spin_lock_init(&inode->i_data.tree_lock); spin_lock_init(&inode->i_data.i_mmap_lock); @@ -281,14 +319,109 @@ static void init_once(void *foo) */ void __iget(struct inode *inode) { - if (atomic_inc_return(&inode->i_count) != 1) - return; + atomic_inc(&inode->i_count); +} + +/* + * get additional reference to inode; caller must already hold one. + */ +void ihold(struct inode *inode) +{ + WARN_ON(atomic_inc_return(&inode->i_count) < 2); +} +EXPORT_SYMBOL(ihold); + +static void inode_lru_list_add(struct inode *inode) +{ + if (list_empty(&inode->i_lru)) { + list_add(&inode->i_lru, &inode_lru); + percpu_counter_inc(&nr_inodes_unused); + } +} - if (!(inode->i_state & (I_DIRTY|I_SYNC))) - list_move(&inode->i_list, &inode_in_use); - inodes_stat.nr_unused--; +static void inode_lru_list_del(struct inode *inode) +{ + if (!list_empty(&inode->i_lru)) { + list_del_init(&inode->i_lru); + percpu_counter_dec(&nr_inodes_unused); + } +} + +static inline void __inode_sb_list_add(struct inode *inode) +{ + list_add(&inode->i_sb_list, &inode->i_sb->s_inodes); } +/** + * inode_sb_list_add - add inode to the superblock list of inodes + * @inode: inode to add + */ +void inode_sb_list_add(struct inode *inode) +{ + spin_lock(&inode_lock); + __inode_sb_list_add(inode); + spin_unlock(&inode_lock); +} +EXPORT_SYMBOL_GPL(inode_sb_list_add); + +static inline void __inode_sb_list_del(struct inode *inode) +{ + list_del_init(&inode->i_sb_list); +} + +static unsigned long hash(struct super_block *sb, unsigned long hashval) +{ + unsigned long tmp; + + tmp = (hashval * (unsigned long)sb) ^ (GOLDEN_RATIO_PRIME + hashval) / + L1_CACHE_BYTES; + tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> I_HASHBITS); + return tmp & I_HASHMASK; +} + +/** + * __insert_inode_hash - hash an inode + * @inode: unhashed inode + * @hashval: unsigned long value used to locate this object in the + * inode_hashtable. + * + * Add an inode to the inode hash for this superblock. + */ +void __insert_inode_hash(struct inode *inode, unsigned long hashval) +{ + struct hlist_head *b = inode_hashtable + hash(inode->i_sb, hashval); + + spin_lock(&inode_lock); + hlist_add_head(&inode->i_hash, b); + spin_unlock(&inode_lock); +} +EXPORT_SYMBOL(__insert_inode_hash); + +/** + * __remove_inode_hash - remove an inode from the hash + * @inode: inode to unhash + * + * Remove an inode from the superblock. + */ +static void __remove_inode_hash(struct inode *inode) +{ + hlist_del_init(&inode->i_hash); +} + +/** + * remove_inode_hash - remove an inode from the hash + * @inode: inode to unhash + * + * Remove an inode from the superblock. + */ +void remove_inode_hash(struct inode *inode) +{ + spin_lock(&inode_lock); + hlist_del_init(&inode->i_hash); + spin_unlock(&inode_lock); +} +EXPORT_SYMBOL(remove_inode_hash); + void end_writeback(struct inode *inode) { might_sleep(); @@ -327,101 +460,113 @@ static void evict(struct inode *inode) */ static void dispose_list(struct list_head *head) { - int nr_disposed = 0; - while (!list_empty(head)) { struct inode *inode; - inode = list_first_entry(head, struct inode, i_list); - list_del(&inode->i_list); + inode = list_first_entry(head, struct inode, i_lru); + list_del_init(&inode->i_lru); evict(inode); spin_lock(&inode_lock); - hlist_del_init(&inode->i_hash); - list_del_init(&inode->i_sb_list); + __remove_inode_hash(inode); + __inode_sb_list_del(inode); spin_unlock(&inode_lock); wake_up_inode(inode); destroy_inode(inode); - nr_disposed++; } - spin_lock(&inode_lock); - inodes_stat.nr_inodes -= nr_disposed; - spin_unlock(&inode_lock); } -/* - * Invalidate all inodes for a device. +/** + * evict_inodes - evict all evictable inodes for a superblock + * @sb: superblock to operate on + * + * Make sure that no inodes with zero refcount are retained. This is + * called by superblock shutdown after having MS_ACTIVE flag removed, + * so any inode reaching zero refcount during or after that call will + * be immediately evicted. */ -static int invalidate_list(struct list_head *head, struct list_head *dispose) +void evict_inodes(struct super_block *sb) { - struct list_head *next; - int busy = 0, count = 0; - - next = head->next; - for (;;) { - struct list_head *tmp = next; - struct inode *inode; + struct inode *inode, *next; + LIST_HEAD(dispose); - /* - * We can reschedule here without worrying about the list's - * consistency because the per-sb list of inodes must not - * change during umount anymore, and because iprune_sem keeps - * shrink_icache_memory() away. - */ - cond_resched_lock(&inode_lock); + down_write(&iprune_sem); - next = next->next; - if (tmp == head) - break; - inode = list_entry(tmp, struct inode, i_sb_list); - if (inode->i_state & I_NEW) + spin_lock(&inode_lock); + list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) { + if (atomic_read(&inode->i_count)) continue; - invalidate_inode_buffers(inode); - if (!atomic_read(&inode->i_count)) { - list_move(&inode->i_list, dispose); - WARN_ON(inode->i_state & I_NEW); - inode->i_state |= I_FREEING; - count++; + + if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { + WARN_ON(1); continue; } - busy = 1; + + inode->i_state |= I_FREEING; + + /* + * Move the inode off the IO lists and LRU once I_FREEING is + * set so that it won't get moved back on there if it is dirty. + */ + list_move(&inode->i_lru, &dispose); + list_del_init(&inode->i_wb_list); + if (!(inode->i_state & (I_DIRTY | I_SYNC))) + percpu_counter_dec(&nr_inodes_unused); } - /* only unused inodes may be cached with i_count zero */ - inodes_stat.nr_unused -= count; - return busy; + spin_unlock(&inode_lock); + + dispose_list(&dispose); + up_write(&iprune_sem); } /** - * invalidate_inodes - discard the inodes on a device - * @sb: superblock + * invalidate_inodes - attempt to free all inodes on a superblock + * @sb: superblock to operate on * - * Discard all of the inodes for a given superblock. If the discard - * fails because there are busy inodes then a non zero value is returned. - * If the discard is successful all the inodes have been discarded. + * Attempts to free all inodes for a given superblock. If there were any + * busy inodes return a non-zero value, else zero. */ int invalidate_inodes(struct super_block *sb) { - int busy; - LIST_HEAD(throw_away); + int busy = 0; + struct inode *inode, *next; + LIST_HEAD(dispose); down_write(&iprune_sem); + spin_lock(&inode_lock); - fsnotify_unmount_inodes(&sb->s_inodes); - busy = invalidate_list(&sb->s_inodes, &throw_away); + list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) { + if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) + continue; + if (atomic_read(&inode->i_count)) { + busy = 1; + continue; + } + + inode->i_state |= I_FREEING; + + /* + * Move the inode off the IO lists and LRU once I_FREEING is + * set so that it won't get moved back on there if it is dirty. + */ + list_move(&inode->i_lru, &dispose); + list_del_init(&inode->i_wb_list); + if (!(inode->i_state & (I_DIRTY | I_SYNC))) + percpu_counter_dec(&nr_inodes_unused); + } spin_unlock(&inode_lock); - dispose_list(&throw_away); + dispose_list(&dispose); up_write(&iprune_sem); return busy; } -EXPORT_SYMBOL(invalidate_inodes); static int can_unuse(struct inode *inode) { - if (inode->i_state) + if (inode->i_state & ~I_REFERENCED) return 0; if (inode_has_buffers(inode)) return 0; @@ -433,22 +578,24 @@ static int can_unuse(struct inode *inode) } /* - * Scan `goal' inodes on the unused list for freeable ones. They are moved to - * a temporary list and then are freed outside inode_lock by dispose_list(). + * Scan `goal' inodes on the unused list for freeable ones. They are moved to a + * temporary list and then are freed outside inode_lock by dispose_list(). * * Any inodes which are pinned purely because of attached pagecache have their - * pagecache removed. We expect the final iput() on that inode to add it to - * the front of the inode_unused list. So look for it there and if the - * inode is still freeable, proceed. The right inode is found 99.9% of the - * time in testing on a 4-way. + * pagecache removed. If the inode has metadata buffers attached to + * mapping->private_list then try to remove them. * - * If the inode has metadata buffers attached to mapping->private_list then - * try to remove them. + * If the inode has the I_REFERENCED flag set, then it means that it has been + * used recently - the flag is set in iput_final(). When we encounter such an + * inode, clear the flag and move it to the back of the LRU so it gets another + * pass through the LRU before it gets reclaimed. This is necessary because of + * the fact we are doing lazy LRU updates to minimise lock contention so the + * LRU does not have strict ordering. Hence we don't want to reclaim inodes + * with this flag set because they are the inodes that are out of order. */ static void prune_icache(int nr_to_scan) { LIST_HEAD(freeable); - int nr_pruned = 0; int nr_scanned; unsigned long reap = 0; @@ -457,13 +604,26 @@ static void prune_icache(int nr_to_scan) for (nr_scanned = 0; nr_scanned < nr_to_scan; nr_scanned++) { struct inode *inode; - if (list_empty(&inode_unused)) + if (list_empty(&inode_lru)) break; - inode = list_entry(inode_unused.prev, struct inode, i_list); + inode = list_entry(inode_lru.prev, struct inode, i_lru); - if (inode->i_state || atomic_read(&inode->i_count)) { - list_move(&inode->i_list, &inode_unused); + /* + * Referenced or dirty inodes are still in use. Give them + * another pass through the LRU as we canot reclaim them now. + */ + if (atomic_read(&inode->i_count) || + (inode->i_state & ~I_REFERENCED)) { + list_del_init(&inode->i_lru); + percpu_counter_dec(&nr_inodes_unused); + continue; + } + + /* recently referenced inodes get one more pass */ + if (inode->i_state & I_REFERENCED) { + list_move(&inode->i_lru, &inode_lru); + inode->i_state &= ~I_REFERENCED; continue; } if (inode_has_buffers(inode) || inode->i_data.nrpages) { @@ -475,18 +635,23 @@ static void prune_icache(int nr_to_scan) iput(inode); spin_lock(&inode_lock); - if (inode != list_entry(inode_unused.next, - struct inode, i_list)) + if (inode != list_entry(inode_lru.next, + struct inode, i_lru)) continue; /* wrong inode or list_empty */ if (!can_unuse(inode)) continue; } - list_move(&inode->i_list, &freeable); WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_FREEING; - nr_pruned++; + + /* + * Move the inode off the IO lists and LRU once I_FREEING is + * set so that it won't get moved back on there if it is dirty. + */ + list_move(&inode->i_lru, &freeable); + list_del_init(&inode->i_wb_list); + percpu_counter_dec(&nr_inodes_unused); } - inodes_stat.nr_unused -= nr_pruned; if (current_is_kswapd()) __count_vm_events(KSWAPD_INODESTEAL, reap); else @@ -518,7 +683,7 @@ static int shrink_icache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask) return -1; prune_icache(nr); } - return (inodes_stat.nr_unused / 100) * sysctl_vfs_cache_pressure; + return (get_nr_inodes_unused() / 100) * sysctl_vfs_cache_pressure; } static struct shrinker icache_shrinker = { @@ -529,9 +694,6 @@ static struct shrinker icache_shrinker = { static void __wait_on_freeing_inode(struct inode *inode); /* * Called with the inode lock held. - * NOTE: we are not increasing the inode-refcount, you must call __iget() - * by hand after calling find_inode now! This simplifies iunique and won't - * add any additional branch in the common code. */ static struct inode *find_inode(struct super_block *sb, struct hlist_head *head, @@ -551,9 +713,10 @@ repeat: __wait_on_freeing_inode(inode); goto repeat; } - break; + __iget(inode); + return inode; } - return node ? inode : NULL; + return NULL; } /* @@ -576,53 +739,49 @@ repeat: __wait_on_freeing_inode(inode); goto repeat; } - break; + __iget(inode); + return inode; } - return node ? inode : NULL; -} - -static unsigned long hash(struct super_block *sb, unsigned long hashval) -{ - unsigned long tmp; - - tmp = (hashval * (unsigned long)sb) ^ (GOLDEN_RATIO_PRIME + hashval) / - L1_CACHE_BYTES; - tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> I_HASHBITS); - return tmp & I_HASHMASK; -} - -static inline void -__inode_add_to_lists(struct super_block *sb, struct hlist_head *head, - struct inode *inode) -{ - inodes_stat.nr_inodes++; - list_add(&inode->i_list, &inode_in_use); - list_add(&inode->i_sb_list, &sb->s_inodes); - if (head) - hlist_add_head(&inode->i_hash, head); + return NULL; } -/** - * inode_add_to_lists - add a new inode to relevant lists - * @sb: superblock inode belongs to - * @inode: inode to mark in use +/* + * Each cpu owns a range of LAST_INO_BATCH numbers. + * 'shared_last_ino' is dirtied only once out of LAST_INO_BATCH allocations, + * to renew the exhausted range. * - * When an inode is allocated it needs to be accounted for, added to the in use - * list, the owning superblock and the inode hash. This needs to be done under - * the inode_lock, so export a function to do this rather than the inode lock - * itself. We calculate the hash list to add to here so it is all internal - * which requires the caller to have already set up the inode number in the - * inode to add. + * This does not significantly increase overflow rate because every CPU can + * consume at most LAST_INO_BATCH-1 unused inode numbers. So there is + * NR_CPUS*(LAST_INO_BATCH-1) wastage. At 4096 and 1024, this is ~0.1% of the + * 2^32 range, and is a worst-case. Even a 50% wastage would only increase + * overflow rate by 2x, which does not seem too significant. + * + * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW + * error if st_ino won't fit in target struct field. Use 32bit counter + * here to attempt to avoid that. */ -void inode_add_to_lists(struct super_block *sb, struct inode *inode) +#define LAST_INO_BATCH 1024 +static DEFINE_PER_CPU(unsigned int, last_ino); + +unsigned int get_next_ino(void) { - struct hlist_head *head = inode_hashtable + hash(sb, inode->i_ino); + unsigned int *p = &get_cpu_var(last_ino); + unsigned int res = *p; - spin_lock(&inode_lock); - __inode_add_to_lists(sb, head, inode); - spin_unlock(&inode_lock); +#ifdef CONFIG_SMP + if (unlikely((res & (LAST_INO_BATCH-1)) == 0)) { + static atomic_t shared_last_ino; + int next = atomic_add_return(LAST_INO_BATCH, &shared_last_ino); + + res = next - LAST_INO_BATCH; + } +#endif + + *p = ++res; + put_cpu_var(last_ino); + return res; } -EXPORT_SYMBOL_GPL(inode_add_to_lists); +EXPORT_SYMBOL(get_next_ino); /** * new_inode - obtain an inode @@ -638,12 +797,6 @@ EXPORT_SYMBOL_GPL(inode_add_to_lists); */ struct inode *new_inode(struct super_block *sb) { - /* - * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW - * error if st_ino won't fit in target struct field. Use 32bit counter - * here to attempt to avoid that. - */ - static unsigned int last_ino; struct inode *inode; spin_lock_prefetch(&inode_lock); @@ -651,8 +804,7 @@ struct inode *new_inode(struct super_block *sb) inode = alloc_inode(sb); if (inode) { spin_lock(&inode_lock); - __inode_add_to_lists(sb, NULL, inode); - inode->i_ino = ++last_ino; + __inode_sb_list_add(inode); inode->i_state = 0; spin_unlock(&inode_lock); } @@ -663,7 +815,7 @@ EXPORT_SYMBOL(new_inode); void unlock_new_inode(struct inode *inode) { #ifdef CONFIG_DEBUG_LOCK_ALLOC - if (inode->i_mode & S_IFDIR) { + if (S_ISDIR(inode->i_mode)) { struct file_system_type *type = inode->i_sb->s_type; /* Set new key only if filesystem hasn't already changed it */ @@ -720,7 +872,8 @@ static struct inode *get_new_inode(struct super_block *sb, if (set(inode, data)) goto set_failed; - __inode_add_to_lists(sb, head, inode); + hlist_add_head(&inode->i_hash, head); + __inode_sb_list_add(inode); inode->i_state = I_NEW; spin_unlock(&inode_lock); @@ -735,7 +888,6 @@ static struct inode *get_new_inode(struct super_block *sb, * us. Use the old inode instead of the one we just * allocated. */ - __iget(old); spin_unlock(&inode_lock); destroy_inode(inode); inode = old; @@ -767,7 +919,8 @@ static struct inode *get_new_inode_fast(struct super_block *sb, old = find_inode_fast(sb, head, ino); if (!old) { inode->i_ino = ino; - __inode_add_to_lists(sb, head, inode); + hlist_add_head(&inode->i_hash, head); + __inode_sb_list_add(inode); inode->i_state = I_NEW; spin_unlock(&inode_lock); @@ -782,7 +935,6 @@ static struct inode *get_new_inode_fast(struct super_block *sb, * us. Use the old inode instead of the one we just * allocated. */ - __iget(old); spin_unlock(&inode_lock); destroy_inode(inode); inode = old; @@ -791,6 +943,27 @@ static struct inode *get_new_inode_fast(struct super_block *sb, return inode; } +/* + * search the inode cache for a matching inode number. + * If we find one, then the inode number we are trying to + * allocate is not unique and so we should not use it. + * + * Returns 1 if the inode number is unique, 0 if it is not. + */ +static int test_inode_iunique(struct super_block *sb, unsigned long ino) +{ + struct hlist_head *b = inode_hashtable + hash(sb, ino); + struct hlist_node *node; + struct inode *inode; + + hlist_for_each_entry(inode, node, b, i_hash) { + if (inode->i_ino == ino && inode->i_sb == sb) + return 0; + } + + return 1; +} + /** * iunique - get a unique inode number * @sb: superblock @@ -812,19 +985,18 @@ ino_t iunique(struct super_block *sb, ino_t max_reserved) * error if st_ino won't fit in target struct field. Use 32bit counter * here to attempt to avoid that. */ + static DEFINE_SPINLOCK(iunique_lock); static unsigned int counter; - struct inode *inode; - struct hlist_head *head; ino_t res; spin_lock(&inode_lock); + spin_lock(&iunique_lock); do { if (counter <= max_reserved) counter = max_reserved + 1; res = counter++; - head = inode_hashtable + hash(sb, res); - inode = find_inode_fast(sb, head, res); - } while (inode != NULL); + } while (!test_inode_iunique(sb, res)); + spin_unlock(&iunique_lock); spin_unlock(&inode_lock); return res; @@ -876,7 +1048,6 @@ static struct inode *ifind(struct super_block *sb, spin_lock(&inode_lock); inode = find_inode(sb, head, test, data); if (inode) { - __iget(inode); spin_unlock(&inode_lock); if (likely(wait)) wait_on_inode(inode); @@ -909,7 +1080,6 @@ static struct inode *ifind_fast(struct super_block *sb, spin_lock(&inode_lock); inode = find_inode_fast(sb, head, ino); if (inode) { - __iget(inode); spin_unlock(&inode_lock); wait_on_inode(inode); return inode; @@ -1095,7 +1265,7 @@ int insert_inode_locked(struct inode *inode) __iget(old); spin_unlock(&inode_lock); wait_on_inode(old); - if (unlikely(!hlist_unhashed(&old->i_hash))) { + if (unlikely(!inode_unhashed(old))) { iput(old); return -EBUSY; } @@ -1134,7 +1304,7 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval, __iget(old); spin_unlock(&inode_lock); wait_on_inode(old); - if (unlikely(!hlist_unhashed(&old->i_hash))) { + if (unlikely(!inode_unhashed(old))) { iput(old); return -EBUSY; } @@ -1143,36 +1313,6 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval, } EXPORT_SYMBOL(insert_inode_locked4); -/** - * __insert_inode_hash - hash an inode - * @inode: unhashed inode - * @hashval: unsigned long value used to locate this object in the - * inode_hashtable. - * - * Add an inode to the inode hash for this superblock. - */ -void __insert_inode_hash(struct inode *inode, unsigned long hashval) -{ - struct hlist_head *head = inode_hashtable + hash(inode->i_sb, hashval); - spin_lock(&inode_lock); - hlist_add_head(&inode->i_hash, head); - spin_unlock(&inode_lock); -} -EXPORT_SYMBOL(__insert_inode_hash); - -/** - * remove_inode_hash - remove an inode from the hash - * @inode: inode to unhash - * - * Remove an inode from the superblock. - */ -void remove_inode_hash(struct inode *inode) -{ - spin_lock(&inode_lock); - hlist_del_init(&inode->i_hash); - spin_unlock(&inode_lock); -} -EXPORT_SYMBOL(remove_inode_hash); int generic_delete_inode(struct inode *inode) { @@ -1187,7 +1327,7 @@ EXPORT_SYMBOL(generic_delete_inode); */ int generic_drop_inode(struct inode *inode) { - return !inode->i_nlink || hlist_unhashed(&inode->i_hash); + return !inode->i_nlink || inode_unhashed(inode); } EXPORT_SYMBOL_GPL(generic_drop_inode); @@ -1213,10 +1353,11 @@ static void iput_final(struct inode *inode) drop = generic_drop_inode(inode); if (!drop) { - if (!(inode->i_state & (I_DIRTY|I_SYNC))) - list_move(&inode->i_list, &inode_unused); - inodes_stat.nr_unused++; if (sb->s_flags & MS_ACTIVE) { + inode->i_state |= I_REFERENCED; + if (!(inode->i_state & (I_DIRTY|I_SYNC))) { + inode_lru_list_add(inode); + } spin_unlock(&inode_lock); return; } @@ -1227,19 +1368,23 @@ static void iput_final(struct inode *inode) spin_lock(&inode_lock); WARN_ON(inode->i_state & I_NEW); inode->i_state &= ~I_WILL_FREE; - inodes_stat.nr_unused--; - hlist_del_init(&inode->i_hash); + __remove_inode_hash(inode); } - list_del_init(&inode->i_list); - list_del_init(&inode->i_sb_list); + WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_FREEING; - inodes_stat.nr_inodes--; + + /* + * Move the inode off the IO lists and LRU once I_FREEING is + * set so that it won't get moved back on there if it is dirty. + */ + inode_lru_list_del(inode); + list_del_init(&inode->i_wb_list); + + __inode_sb_list_del(inode); spin_unlock(&inode_lock); evict(inode); - spin_lock(&inode_lock); - hlist_del_init(&inode->i_hash); - spin_unlock(&inode_lock); + remove_inode_hash(inode); wake_up_inode(inode); BUG_ON(inode->i_state != (I_FREEING | I_CLEAR)); destroy_inode(inode); @@ -1503,6 +1648,8 @@ void __init inode_init(void) SLAB_MEM_SPREAD), init_once); register_shrinker(&icache_shrinker); + percpu_counter_init(&nr_inodes, 0); + percpu_counter_init(&nr_inodes_unused, 0); /* Hash may have been set up in inode_init_early */ if (!hashdist) diff --git a/fs/internal.h b/fs/internal.h index a6910e91cee8..e43b9a4dbf4e 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -101,3 +101,10 @@ extern void put_super(struct super_block *sb); struct nameidata; extern struct file *nameidata_to_filp(struct nameidata *); extern void release_open_intent(struct nameidata *); + +/* + * inode.c + */ +extern int get_nr_dirty_inodes(void); +extern void evict_inodes(struct super_block *); +extern int invalidate_inodes(struct super_block *); diff --git a/fs/ioctl.c b/fs/ioctl.c index f855ea4fc888..d6cc16476620 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -6,7 +6,6 @@ #include <linux/syscalls.h> #include <linux/mm.h> -#include <linux/smp_lock.h> #include <linux/capability.h> #include <linux/file.h> #include <linux/fs.h> diff --git a/fs/ioprio.c b/fs/ioprio.c index 748cfb92dcc6..7da2a06508e5 100644 --- a/fs/ioprio.c +++ b/fs/ioprio.c @@ -103,12 +103,7 @@ SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio) } ret = -ESRCH; - /* - * We want IOPRIO_WHO_PGRP/IOPRIO_WHO_USER to be "atomic", - * so we can't use rcu_read_lock(). See re-copy of ->ioprio - * in copy_process(). - */ - read_lock(&tasklist_lock); + rcu_read_lock(); switch (which) { case IOPRIO_WHO_PROCESS: if (!who) @@ -153,7 +148,7 @@ free_uid: ret = -EINVAL; } - read_unlock(&tasklist_lock); + rcu_read_unlock(); return ret; } @@ -197,7 +192,7 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who) int ret = -ESRCH; int tmpio; - read_lock(&tasklist_lock); + rcu_read_lock(); switch (which) { case IOPRIO_WHO_PROCESS: if (!who) @@ -250,6 +245,6 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who) ret = -EINVAL; } - read_unlock(&tasklist_lock); + rcu_read_unlock(); return ret; } diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 09ff41a752a0..bfdeb82a53be 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -544,6 +544,34 @@ static unsigned int isofs_get_last_session(struct super_block *sb, s32 session) } /* + * Check if root directory is empty (has less than 3 files). + * + * Used to detect broken CDs where ISO root directory is empty but Joliet root + * directory is OK. If such CD has Rock Ridge extensions, they will be disabled + * (and Joliet used instead) or else no files would be visible. + */ +static bool rootdir_empty(struct super_block *sb, unsigned long block) +{ + int offset = 0, files = 0, de_len; + struct iso_directory_record *de; + struct buffer_head *bh; + + bh = sb_bread(sb, block); + if (!bh) + return true; + while (files < 3) { + de = (struct iso_directory_record *) (bh->b_data + offset); + de_len = *(unsigned char *) de; + if (de_len == 0) + break; + files++; + offset += de_len; + } + brelse(bh); + return files < 3; +} + +/* * Initialize the superblock and read the root inode. * * Note: a check_disk_change() has been done immediately prior @@ -843,6 +871,18 @@ root_found: goto out_no_root; /* + * Fix for broken CDs with Rock Ridge and empty ISO root directory but + * correct Joliet root directory. + */ + if (sbi->s_rock == 1 && joliet_level && + rootdir_empty(s, sbi->s_firstdatazone)) { + printk(KERN_NOTICE + "ISOFS: primary root directory is empty. " + "Disabling Rock Ridge and switching to Joliet."); + sbi->s_rock = 0; + } + + /* * If this disk has both Rock Ridge and Joliet on it, then we * want to use Rock Ridge by default. This can be overridden * by using the norock mount option. There is still one other @@ -962,25 +1002,23 @@ static int isofs_statfs (struct dentry *dentry, struct kstatfs *buf) * or getblk() if they are not. Returns the number of blocks inserted * (-ve == error.) */ -int isofs_get_blocks(struct inode *inode, sector_t iblock_s, +int isofs_get_blocks(struct inode *inode, sector_t iblock, struct buffer_head **bh, unsigned long nblocks) { - unsigned long b_off; + unsigned long b_off = iblock; unsigned offset, sect_size; unsigned int firstext; unsigned long nextblk, nextoff; - long iblock = (long)iblock_s; int section, rv, error; struct iso_inode_info *ei = ISOFS_I(inode); error = -EIO; rv = 0; - if (iblock < 0 || iblock != iblock_s) { + if (iblock != b_off) { printk(KERN_DEBUG "%s: block number too large\n", __func__); goto abort; } - b_off = iblock; offset = 0; firstext = ei->i_first_extent; @@ -998,8 +1036,9 @@ int isofs_get_blocks(struct inode *inode, sector_t iblock_s, * I/O errors. */ if (b_off > ((inode->i_size + PAGE_CACHE_SIZE - 1) >> ISOFS_BUFFER_BITS(inode))) { - printk(KERN_DEBUG "%s: block >= EOF (%ld, %ld)\n", - __func__, iblock, (unsigned long) inode->i_size); + printk(KERN_DEBUG "%s: block >= EOF (%lu, %llu)\n", + __func__, b_off, + (unsigned long long)inode->i_size); goto abort; } @@ -1025,9 +1064,9 @@ int isofs_get_blocks(struct inode *inode, sector_t iblock_s, if (++section > 100) { printk(KERN_DEBUG "%s: More than 100 file sections ?!?" " aborting...\n", __func__); - printk(KERN_DEBUG "%s: block=%ld firstext=%u sect_size=%u " + printk(KERN_DEBUG "%s: block=%lu firstext=%u sect_size=%u " "nextblk=%lu nextoff=%lu\n", __func__, - iblock, firstext, (unsigned) sect_size, + b_off, firstext, (unsigned) sect_size, nextblk, nextoff); goto abort; } @@ -1468,17 +1507,16 @@ struct inode *isofs_iget(struct super_block *sb, return inode; } -static int isofs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *isofs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, isofs_fill_super, - mnt); + return mount_bdev(fs_type, flags, dev_name, data, isofs_fill_super); } static struct file_system_type iso9660_fs_type = { .owner = THIS_MODULE, .name = "iso9660", - .get_sb = isofs_get_sb, + .mount = isofs_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c index 05a38b9c4c0e..e4b87bc1fa56 100644 --- a/fs/jbd/checkpoint.c +++ b/fs/jbd/checkpoint.c @@ -221,7 +221,7 @@ restart: goto restart; } if (buffer_locked(bh)) { - atomic_inc(&bh->b_count); + get_bh(bh); spin_unlock(&journal->j_list_lock); jbd_unlock_bh_state(bh); wait_on_buffer(bh); @@ -283,7 +283,7 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh, int ret = 0; if (buffer_locked(bh)) { - atomic_inc(&bh->b_count); + get_bh(bh); spin_unlock(&journal->j_list_lock); jbd_unlock_bh_state(bh); wait_on_buffer(bh); diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c index 85a6883c0aca..34a4861c14b8 100644 --- a/fs/jbd/commit.c +++ b/fs/jbd/commit.c @@ -587,13 +587,13 @@ void journal_commit_transaction(journal_t *journal) /* Bump b_count to prevent truncate from stumbling over the shadowed buffer! @@@ This can go if we ever get rid of the BJ_IO/BJ_Shadow pairing of buffers. */ - atomic_inc(&jh2bh(jh)->b_count); + get_bh(jh2bh(jh)); /* Make a temporary IO buffer with which to write it out (this will requeue both the metadata buffer and the temporary IO buffer). new_bh goes on BJ_IO*/ - set_bit(BH_JWrite, &jh2bh(jh)->b_state); + set_buffer_jwrite(jh2bh(jh)); /* * akpm: journal_write_metadata_buffer() sets * new_bh->b_transaction to commit_transaction. @@ -603,7 +603,7 @@ void journal_commit_transaction(journal_t *journal) JBUFFER_TRACE(jh, "ph3: write metadata"); flags = journal_write_metadata_buffer(commit_transaction, jh, &new_jh, blocknr); - set_bit(BH_JWrite, &jh2bh(new_jh)->b_state); + set_buffer_jwrite(jh2bh(new_jh)); wbuf[bufs++] = jh2bh(new_jh); /* Record the new block's tag in the current descriptor @@ -713,7 +713,7 @@ wait_for_iobuf: shadowed buffer */ jh = commit_transaction->t_shadow_list->b_tprev; bh = jh2bh(jh); - clear_bit(BH_JWrite, &bh->b_state); + clear_buffer_jwrite(bh); J_ASSERT_BH(bh, buffer_jbddirty(bh)); /* The metadata is now released for reuse, but we need diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index 2c4b1f109da9..da1b5e4ffce1 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -36,6 +36,7 @@ #include <linux/poison.h> #include <linux/proc_fs.h> #include <linux/debugfs.h> +#include <linux/ratelimit.h> #include <asm/uaccess.h> #include <asm/page.h> @@ -84,6 +85,7 @@ EXPORT_SYMBOL(journal_force_commit); static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *); static void __journal_abort_soft (journal_t *journal, int errno); +static const char *journal_dev_name(journal_t *journal, char *buffer); /* * Helper function used to manage commit timeouts @@ -439,7 +441,7 @@ int __log_start_commit(journal_t *journal, tid_t target) */ if (!tid_geq(journal->j_commit_request, target)) { /* - * We want a new commit: OK, mark the request and wakup the + * We want a new commit: OK, mark the request and wakeup the * commit thread. We do _not_ do the commit ourselves. */ @@ -950,6 +952,8 @@ int journal_create(journal_t *journal) if (err) return err; bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize); + if (unlikely(!bh)) + return -ENOMEM; lock_buffer(bh); memset (bh->b_data, 0, journal->j_blocksize); BUFFER_TRACE(bh, "marking dirty"); @@ -1010,6 +1014,23 @@ void journal_update_superblock(journal_t *journal, int wait) goto out; } + if (buffer_write_io_error(bh)) { + char b[BDEVNAME_SIZE]; + /* + * Oh, dear. A previous attempt to write the journal + * superblock failed. This could happen because the + * USB device was yanked out. Or it could happen to + * be a transient write error and maybe the block will + * be remapped. Nothing we can do but to retry the + * write and hope for the best. + */ + printk(KERN_ERR "JBD: previous I/O error detected " + "for journal superblock update for %s.\n", + journal_dev_name(journal, b)); + clear_buffer_write_io_error(bh); + set_buffer_uptodate(bh); + } + spin_lock(&journal->j_state_lock); jbd_debug(1,"JBD: updating superblock (start %u, seq %d, errno %d)\n", journal->j_tail, journal->j_tail_sequence, journal->j_errno); @@ -1021,9 +1042,17 @@ void journal_update_superblock(journal_t *journal, int wait) BUFFER_TRACE(bh, "marking dirty"); mark_buffer_dirty(bh); - if (wait) + if (wait) { sync_dirty_buffer(bh); - else + if (buffer_write_io_error(bh)) { + char b[BDEVNAME_SIZE]; + printk(KERN_ERR "JBD: I/O error detected " + "when updating journal superblock for %s.\n", + journal_dev_name(journal, b)); + clear_buffer_write_io_error(bh); + set_buffer_uptodate(bh); + } + } else write_dirty_buffer(bh, WRITE); out: @@ -1719,7 +1748,6 @@ static void journal_destroy_journal_head_cache(void) static struct journal_head *journal_alloc_journal_head(void) { struct journal_head *ret; - static unsigned long last_warning; #ifdef CONFIG_JBD_DEBUG atomic_inc(&nr_journal_heads); @@ -1727,11 +1755,9 @@ static struct journal_head *journal_alloc_journal_head(void) ret = kmem_cache_alloc(journal_head_cache, GFP_NOFS); if (ret == NULL) { jbd_debug(1, "out of memory for journal_head\n"); - if (time_after(jiffies, last_warning + 5*HZ)) { - printk(KERN_NOTICE "ENOMEM in %s, retrying.\n", - __func__); - last_warning = jiffies; - } + printk_ratelimited(KERN_NOTICE "ENOMEM in %s, retrying.\n", + __func__); + while (ret == NULL) { yield(); ret = kmem_cache_alloc(journal_head_cache, GFP_NOFS); diff --git a/fs/jbd/recovery.c b/fs/jbd/recovery.c index 81051dafebf5..5b43e96788e6 100644 --- a/fs/jbd/recovery.c +++ b/fs/jbd/recovery.c @@ -296,10 +296,10 @@ int journal_skip_recovery(journal_t *journal) #ifdef CONFIG_JBD_DEBUG int dropped = info.end_transaction - be32_to_cpu(journal->j_superblock->s_sequence); -#endif jbd_debug(1, "JBD: ignoring %d transaction%s from the journal.\n", dropped, (dropped == 1) ? "" : "s"); +#endif journal->j_transaction_sequence = ++info.end_transaction; } diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c index 5ae71e75a491..846a3f314111 100644 --- a/fs/jbd/transaction.c +++ b/fs/jbd/transaction.c @@ -293,9 +293,7 @@ handle_t *journal_start(journal_t *journal, int nblocks) jbd_free_handle(handle); current->journal_info = NULL; handle = ERR_PTR(err); - goto out; } -out: return handle; } @@ -528,7 +526,7 @@ do_get_write_access(handle_t *handle, struct journal_head *jh, transaction = handle->h_transaction; journal = transaction->t_journal; - jbd_debug(5, "buffer_head %p, force_copy %d\n", jh, force_copy); + jbd_debug(5, "journal_head %p, force_copy %d\n", jh, force_copy); JBUFFER_TRACE(jh, "entry"); repeat: @@ -713,7 +711,7 @@ done: J_EXPECT_JH(jh, buffer_uptodate(jh2bh(jh)), "Possible IO failure.\n"); page = jh2bh(jh)->b_page; - offset = ((unsigned long) jh2bh(jh)->b_data) & ~PAGE_MASK; + offset = offset_in_page(jh2bh(jh)->b_data); source = kmap_atomic(page, KM_USER0); memcpy(jh->b_frozen_data, source+offset, jh2bh(jh)->b_size); kunmap_atomic(source, KM_USER0); diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 6571a056e55d..6a79fd0a1a32 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -299,6 +299,16 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh, transaction->t_chp_stats.cs_forced_to_close++; spin_unlock(&journal->j_list_lock); jbd_unlock_bh_state(bh); + if (unlikely(journal->j_flags & JBD2_UNMOUNT)) + /* + * The journal thread is dead; so starting and + * waiting for a commit to finish will cause + * us to wait for a _very_ long time. + */ + printk(KERN_ERR "JBD2: %s: " + "Waiting for Godot: block %llu\n", + journal->j_devname, + (unsigned long long) bh->b_blocknr); jbd2_log_start_commit(journal, tid); jbd2_log_wait_commit(journal, tid); ret = 1; diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index bc6be8bda1cc..f3ad1598b201 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -26,7 +26,9 @@ #include <linux/backing-dev.h> #include <linux/bio.h> #include <linux/blkdev.h> +#include <linux/bitops.h> #include <trace/events/jbd2.h> +#include <asm/system.h> /* * Default IO end handler for temporary BJ_IO buffer_heads. @@ -201,7 +203,7 @@ static int journal_submit_data_buffers(journal_t *journal, spin_lock(&journal->j_list_lock); list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) { mapping = jinode->i_vfs_inode->i_mapping; - jinode->i_flags |= JI_COMMIT_RUNNING; + set_bit(__JI_COMMIT_RUNNING, &jinode->i_flags); spin_unlock(&journal->j_list_lock); /* * submit the inode data buffers. We use writepage @@ -216,7 +218,8 @@ static int journal_submit_data_buffers(journal_t *journal, spin_lock(&journal->j_list_lock); J_ASSERT(jinode->i_transaction == commit_transaction); commit_transaction->t_flushed_data_blocks = 1; - jinode->i_flags &= ~JI_COMMIT_RUNNING; + clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags); + smp_mb__after_clear_bit(); wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING); } spin_unlock(&journal->j_list_lock); @@ -237,7 +240,7 @@ static int journal_finish_inode_data_buffers(journal_t *journal, /* For locking, see the comment in journal_submit_data_buffers() */ spin_lock(&journal->j_list_lock); list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) { - jinode->i_flags |= JI_COMMIT_RUNNING; + set_bit(__JI_COMMIT_RUNNING, &jinode->i_flags); spin_unlock(&journal->j_list_lock); err = filemap_fdatawait(jinode->i_vfs_inode->i_mapping); if (err) { @@ -253,7 +256,8 @@ static int journal_finish_inode_data_buffers(journal_t *journal, ret = err; } spin_lock(&journal->j_list_lock); - jinode->i_flags &= ~JI_COMMIT_RUNNING; + clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags); + smp_mb__after_clear_bit(); wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING); } diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 262419f83d80..f837ba953529 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -42,12 +42,14 @@ #include <linux/log2.h> #include <linux/vmalloc.h> #include <linux/backing-dev.h> +#include <linux/bitops.h> #define CREATE_TRACE_POINTS #include <trace/events/jbd2.h> #include <asm/uaccess.h> #include <asm/page.h> +#include <asm/system.h> EXPORT_SYMBOL(jbd2_journal_extend); EXPORT_SYMBOL(jbd2_journal_stop); @@ -478,7 +480,7 @@ int __jbd2_log_start_commit(journal_t *journal, tid_t target) */ if (!tid_geq(journal->j_commit_request, target)) { /* - * We want a new commit: OK, mark the request and wakup the + * We want a new commit: OK, mark the request and wakeup the * commit thread. We do _not_ do the commit ourselves. */ @@ -897,6 +899,14 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev, /* journal descriptor can store up to n blocks -bzzz */ journal->j_blocksize = blocksize; + journal->j_dev = bdev; + journal->j_fs_dev = fs_dev; + journal->j_blk_offset = start; + journal->j_maxlen = len; + bdevname(journal->j_dev, journal->j_devname); + p = journal->j_devname; + while ((p = strchr(p, '/'))) + *p = '!'; jbd2_stats_proc_init(journal); n = journal->j_blocksize / sizeof(journal_block_tag_t); journal->j_wbufsize = n; @@ -906,14 +916,6 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev, __func__); goto out_err; } - journal->j_dev = bdev; - journal->j_fs_dev = fs_dev; - journal->j_blk_offset = start; - journal->j_maxlen = len; - bdevname(journal->j_dev, journal->j_devname); - p = journal->j_devname; - while ((p = strchr(p, '/'))) - *p = '!'; bh = __getblk(journal->j_dev, start, journal->j_blocksize); if (!bh) { @@ -1836,7 +1838,6 @@ size_t journal_tag_bytes(journal_t *journal) */ #define JBD2_MAX_SLABS 8 static struct kmem_cache *jbd2_slab[JBD2_MAX_SLABS]; -static DECLARE_MUTEX(jbd2_slab_create_sem); static const char *jbd2_slab_names[JBD2_MAX_SLABS] = { "jbd2_1k", "jbd2_2k", "jbd2_4k", "jbd2_8k", @@ -1857,6 +1858,7 @@ static void jbd2_journal_destroy_slabs(void) static int jbd2_journal_create_slab(size_t size) { + static DEFINE_MUTEX(jbd2_slab_create_mutex); int i = order_base_2(size) - 10; size_t slab_size; @@ -1868,16 +1870,16 @@ static int jbd2_journal_create_slab(size_t size) if (unlikely(i < 0)) i = 0; - down(&jbd2_slab_create_sem); + mutex_lock(&jbd2_slab_create_mutex); if (jbd2_slab[i]) { - up(&jbd2_slab_create_sem); + mutex_unlock(&jbd2_slab_create_mutex); return 0; /* Already created */ } slab_size = 1 << (i+10); jbd2_slab[i] = kmem_cache_create(jbd2_slab_names[i], slab_size, slab_size, 0, NULL); - up(&jbd2_slab_create_sem); + mutex_unlock(&jbd2_slab_create_mutex); if (!jbd2_slab[i]) { printk(KERN_EMERG "JBD2: no memory for jbd2_slab cache\n"); return -ENOMEM; @@ -2210,7 +2212,7 @@ void jbd2_journal_release_jbd_inode(journal_t *journal, restart: spin_lock(&journal->j_list_lock); /* Is commit writing out inode - we have to wait */ - if (jinode->i_flags & JI_COMMIT_RUNNING) { + if (test_bit(__JI_COMMIT_RUNNING, &jinode->i_flags)) { wait_queue_head_t *wq; DEFINE_WAIT_BIT(wait, &jinode->i_flags, __JI_COMMIT_RUNNING); wq = bit_waitqueue(&jinode->i_flags, __JI_COMMIT_RUNNING); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index f3479d6e0a83..6bf0a242613e 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -156,6 +156,7 @@ alloc_transaction: */ repeat: read_lock(&journal->j_state_lock); + BUG_ON(journal->j_flags & JBD2_UNMOUNT); if (is_journal_aborted(journal) || (journal->j_errno != 0 && !(journal->j_flags & JBD2_ACK_ERR))) { read_unlock(&journal->j_state_lock); diff --git a/fs/jffs2/build.c b/fs/jffs2/build.c index a906f538d11c..85c6be2db02f 100644 --- a/fs/jffs2/build.c +++ b/fs/jffs2/build.c @@ -23,7 +23,7 @@ static void jffs2_build_remove_unlinked_inode(struct jffs2_sb_info *, static inline struct jffs2_inode_cache * first_inode_chain(int *i, struct jffs2_sb_info *c) { - for (; *i < INOCACHE_HASHSIZE; (*i)++) { + for (; *i < c->inocache_hashsize; (*i)++) { if (c->inocache_list[*i]) return c->inocache_list[*i]; } diff --git a/fs/jffs2/compr.c b/fs/jffs2/compr.c index 617a1e5694c1..de4247021d25 100644 --- a/fs/jffs2/compr.c +++ b/fs/jffs2/compr.c @@ -103,7 +103,7 @@ uint16_t jffs2_compress(struct jffs2_sb_info *c, struct jffs2_inode_info *f, spin_unlock(&jffs2_compressor_list_lock); *datalen = orig_slen; *cdatalen = orig_dlen; - compr_ret = this->compress(data_in, output_buf, datalen, cdatalen, NULL); + compr_ret = this->compress(data_in, output_buf, datalen, cdatalen); spin_lock(&jffs2_compressor_list_lock); this->usecount--; if (!compr_ret) { @@ -152,7 +152,7 @@ uint16_t jffs2_compress(struct jffs2_sb_info *c, struct jffs2_inode_info *f, spin_unlock(&jffs2_compressor_list_lock); *datalen = orig_slen; *cdatalen = orig_dlen; - compr_ret = this->compress(data_in, this->compr_buf, datalen, cdatalen, NULL); + compr_ret = this->compress(data_in, this->compr_buf, datalen, cdatalen); spin_lock(&jffs2_compressor_list_lock); this->usecount--; if (!compr_ret) { @@ -220,7 +220,7 @@ int jffs2_decompress(struct jffs2_sb_info *c, struct jffs2_inode_info *f, if (comprtype == this->compr) { this->usecount++; spin_unlock(&jffs2_compressor_list_lock); - ret = this->decompress(cdata_in, data_out, cdatalen, datalen, NULL); + ret = this->decompress(cdata_in, data_out, cdatalen, datalen); spin_lock(&jffs2_compressor_list_lock); if (ret) { printk(KERN_WARNING "Decompressor \"%s\" returned %d\n", this->name, ret); diff --git a/fs/jffs2/compr.h b/fs/jffs2/compr.h index e471a9106fd9..13bb7597ab39 100644 --- a/fs/jffs2/compr.h +++ b/fs/jffs2/compr.h @@ -49,9 +49,9 @@ struct jffs2_compressor { char *name; char compr; /* JFFS2_COMPR_XXX */ int (*compress)(unsigned char *data_in, unsigned char *cpage_out, - uint32_t *srclen, uint32_t *destlen, void *model); + uint32_t *srclen, uint32_t *destlen); int (*decompress)(unsigned char *cdata_in, unsigned char *data_out, - uint32_t cdatalen, uint32_t datalen, void *model); + uint32_t cdatalen, uint32_t datalen); int usecount; int disabled; /* if set the compressor won't compress */ unsigned char *compr_buf; /* used by size compr. mode */ diff --git a/fs/jffs2/compr_lzo.c b/fs/jffs2/compr_lzo.c index ed25ae7c98eb..af186ee674d8 100644 --- a/fs/jffs2/compr_lzo.c +++ b/fs/jffs2/compr_lzo.c @@ -42,7 +42,7 @@ static int __init alloc_workspace(void) } static int jffs2_lzo_compress(unsigned char *data_in, unsigned char *cpage_out, - uint32_t *sourcelen, uint32_t *dstlen, void *model) + uint32_t *sourcelen, uint32_t *dstlen) { size_t compress_size; int ret; @@ -67,7 +67,7 @@ static int jffs2_lzo_compress(unsigned char *data_in, unsigned char *cpage_out, } static int jffs2_lzo_decompress(unsigned char *data_in, unsigned char *cpage_out, - uint32_t srclen, uint32_t destlen, void *model) + uint32_t srclen, uint32_t destlen) { size_t dl = destlen; int ret; diff --git a/fs/jffs2/compr_rtime.c b/fs/jffs2/compr_rtime.c index 9696ad9ef5f7..16a5047903a6 100644 --- a/fs/jffs2/compr_rtime.c +++ b/fs/jffs2/compr_rtime.c @@ -31,8 +31,7 @@ /* _compress returns the compressed size, -1 if bigger */ static int jffs2_rtime_compress(unsigned char *data_in, unsigned char *cpage_out, - uint32_t *sourcelen, uint32_t *dstlen, - void *model) + uint32_t *sourcelen, uint32_t *dstlen) { short positions[256]; int outpos = 0; @@ -73,8 +72,7 @@ static int jffs2_rtime_compress(unsigned char *data_in, static int jffs2_rtime_decompress(unsigned char *data_in, unsigned char *cpage_out, - uint32_t srclen, uint32_t destlen, - void *model) + uint32_t srclen, uint32_t destlen) { short positions[256]; int outpos = 0; diff --git a/fs/jffs2/compr_rubin.c b/fs/jffs2/compr_rubin.c index a12b4f763373..9e7cec808c4c 100644 --- a/fs/jffs2/compr_rubin.c +++ b/fs/jffs2/compr_rubin.c @@ -298,7 +298,7 @@ static int rubin_do_compress(int bit_divider, int *bits, unsigned char *data_in, #if 0 /* _compress returns the compressed size, -1 if bigger */ int jffs2_rubinmips_compress(unsigned char *data_in, unsigned char *cpage_out, - uint32_t *sourcelen, uint32_t *dstlen, void *model) + uint32_t *sourcelen, uint32_t *dstlen) { return rubin_do_compress(BIT_DIVIDER_MIPS, bits_mips, data_in, cpage_out, sourcelen, dstlen); @@ -306,8 +306,7 @@ int jffs2_rubinmips_compress(unsigned char *data_in, unsigned char *cpage_out, #endif static int jffs2_dynrubin_compress(unsigned char *data_in, unsigned char *cpage_out, - uint32_t *sourcelen, uint32_t *dstlen, - void *model) + uint32_t *sourcelen, uint32_t *dstlen) { int bits[8]; unsigned char histo[256]; @@ -387,8 +386,7 @@ static void rubin_do_decompress(int bit_divider, int *bits, static int jffs2_rubinmips_decompress(unsigned char *data_in, unsigned char *cpage_out, - uint32_t sourcelen, uint32_t dstlen, - void *model) + uint32_t sourcelen, uint32_t dstlen) { rubin_do_decompress(BIT_DIVIDER_MIPS, bits_mips, data_in, cpage_out, sourcelen, dstlen); @@ -397,8 +395,7 @@ static int jffs2_rubinmips_decompress(unsigned char *data_in, static int jffs2_dynrubin_decompress(unsigned char *data_in, unsigned char *cpage_out, - uint32_t sourcelen, uint32_t dstlen, - void *model) + uint32_t sourcelen, uint32_t dstlen) { int bits[8]; int c; diff --git a/fs/jffs2/compr_zlib.c b/fs/jffs2/compr_zlib.c index 97fc45de6f81..fd05a0b9431d 100644 --- a/fs/jffs2/compr_zlib.c +++ b/fs/jffs2/compr_zlib.c @@ -68,8 +68,7 @@ static void free_workspaces(void) static int jffs2_zlib_compress(unsigned char *data_in, unsigned char *cpage_out, - uint32_t *sourcelen, uint32_t *dstlen, - void *model) + uint32_t *sourcelen, uint32_t *dstlen) { int ret; @@ -136,8 +135,7 @@ static int jffs2_zlib_compress(unsigned char *data_in, static int jffs2_zlib_decompress(unsigned char *data_in, unsigned char *cpage_out, - uint32_t srclen, uint32_t destlen, - void *model) + uint32_t srclen, uint32_t destlen) { int ret; int wbits = MAX_WBITS; diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index ed78a3cf3cb0..92978658ed18 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -289,7 +289,7 @@ static int jffs2_link (struct dentry *old_dentry, struct inode *dir_i, struct de mutex_unlock(&f->sem); d_instantiate(dentry, old_dentry->d_inode); dir_i->i_mtime = dir_i->i_ctime = ITIME(now); - atomic_inc(&old_dentry->d_inode->i_count); + ihold(old_dentry->d_inode); } return ret; } @@ -367,7 +367,7 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char } /* We use f->target field to store the target path. */ - f->target = kmalloc(targetlen + 1, GFP_KERNEL); + f->target = kmemdup(target, targetlen + 1, GFP_KERNEL); if (!f->target) { printk(KERN_WARNING "Can't allocate %d bytes of memory\n", targetlen + 1); mutex_unlock(&f->sem); @@ -376,7 +376,6 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char goto fail; } - memcpy(f->target, target, targetlen + 1); D1(printk(KERN_DEBUG "jffs2_symlink: symlink's target '%s' cached\n", (char *)f->target)); /* No data here. Only a metadata node, which will be @@ -864,7 +863,7 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry, printk(KERN_NOTICE "jffs2_rename(): Link succeeded, unlink failed (err %d). You now have a hard link\n", ret); /* Might as well let the VFS know */ d_instantiate(new_dentry, old_dentry->d_inode); - atomic_inc(&old_dentry->d_inode->i_count); + ihold(old_dentry->d_inode); new_dir_i->i_mtime = new_dir_i->i_ctime = ITIME(now); return ret; } diff --git a/fs/jffs2/erase.c b/fs/jffs2/erase.c index abac961f617b..e513f1913c15 100644 --- a/fs/jffs2/erase.c +++ b/fs/jffs2/erase.c @@ -151,7 +151,7 @@ int jffs2_erase_pending_blocks(struct jffs2_sb_info *c, int count) } /* Be nice */ - yield(); + cond_resched(); mutex_lock(&c->erase_free_sem); spin_lock(&c->erase_completion_lock); } diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index d9beb06e6fca..e896e67767eb 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -474,6 +474,25 @@ struct inode *jffs2_new_inode (struct inode *dir_i, int mode, struct jffs2_raw_i return inode; } +static int calculate_inocache_hashsize(uint32_t flash_size) +{ + /* + * Pick a inocache hash size based on the size of the medium. + * Count how many megabytes we're dealing with, apply a hashsize twice + * that size, but rounding down to the usual big powers of 2. And keep + * to sensible bounds. + */ + + int size_mb = flash_size / 1024 / 1024; + int hashsize = (size_mb * 2) & ~0x3f; + + if (hashsize < INOCACHE_HASHSIZE_MIN) + return INOCACHE_HASHSIZE_MIN; + if (hashsize > INOCACHE_HASHSIZE_MAX) + return INOCACHE_HASHSIZE_MAX; + + return hashsize; +} int jffs2_do_fill_super(struct super_block *sb, void *data, int silent) { @@ -520,7 +539,8 @@ int jffs2_do_fill_super(struct super_block *sb, void *data, int silent) if (ret) return ret; - c->inocache_list = kcalloc(INOCACHE_HASHSIZE, sizeof(struct jffs2_inode_cache *), GFP_KERNEL); + c->inocache_hashsize = calculate_inocache_hashsize(c->flash_size); + c->inocache_list = kcalloc(c->inocache_hashsize, sizeof(struct jffs2_inode_cache *), GFP_KERNEL); if (!c->inocache_list) { ret = -ENOMEM; goto out_wbuf; diff --git a/fs/jffs2/gc.c b/fs/jffs2/gc.c index 846a79452497..31dce611337c 100644 --- a/fs/jffs2/gc.c +++ b/fs/jffs2/gc.c @@ -219,13 +219,14 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c) if (!list_empty(&c->erase_complete_list) || !list_empty(&c->erase_pending_list)) { spin_unlock(&c->erase_completion_lock); + mutex_unlock(&c->alloc_sem); D1(printk(KERN_DEBUG "jffs2_garbage_collect_pass() erasing pending blocks\n")); - if (jffs2_erase_pending_blocks(c, 1)) { - mutex_unlock(&c->alloc_sem); + if (jffs2_erase_pending_blocks(c, 1)) return 0; - } + D1(printk(KERN_DEBUG "No progress from erasing blocks; doing GC anyway\n")); spin_lock(&c->erase_completion_lock); + mutex_lock(&c->alloc_sem); } /* First, work out which block we're garbage-collecting */ diff --git a/fs/jffs2/jffs2_fs_sb.h b/fs/jffs2/jffs2_fs_sb.h index 6784bc89add1..f864005de64c 100644 --- a/fs/jffs2/jffs2_fs_sb.h +++ b/fs/jffs2/jffs2_fs_sb.h @@ -100,6 +100,7 @@ struct jffs2_sb_info { wait_queue_head_t erase_wait; /* For waiting for erases to complete */ wait_queue_head_t inocache_wq; + int inocache_hashsize; struct jffs2_inode_cache **inocache_list; spinlock_t inocache_lock; diff --git a/fs/jffs2/nodelist.c b/fs/jffs2/nodelist.c index af02bd138469..5e03233c2363 100644 --- a/fs/jffs2/nodelist.c +++ b/fs/jffs2/nodelist.c @@ -420,7 +420,7 @@ struct jffs2_inode_cache *jffs2_get_ino_cache(struct jffs2_sb_info *c, uint32_t { struct jffs2_inode_cache *ret; - ret = c->inocache_list[ino % INOCACHE_HASHSIZE]; + ret = c->inocache_list[ino % c->inocache_hashsize]; while (ret && ret->ino < ino) { ret = ret->next; } @@ -441,7 +441,7 @@ void jffs2_add_ino_cache (struct jffs2_sb_info *c, struct jffs2_inode_cache *new dbg_inocache("add %p (ino #%u)\n", new, new->ino); - prev = &c->inocache_list[new->ino % INOCACHE_HASHSIZE]; + prev = &c->inocache_list[new->ino % c->inocache_hashsize]; while ((*prev) && (*prev)->ino < new->ino) { prev = &(*prev)->next; @@ -462,7 +462,7 @@ void jffs2_del_ino_cache(struct jffs2_sb_info *c, struct jffs2_inode_cache *old) dbg_inocache("del %p (ino #%u)\n", old, old->ino); spin_lock(&c->inocache_lock); - prev = &c->inocache_list[old->ino % INOCACHE_HASHSIZE]; + prev = &c->inocache_list[old->ino % c->inocache_hashsize]; while ((*prev) && (*prev)->ino < old->ino) { prev = &(*prev)->next; @@ -487,7 +487,7 @@ void jffs2_free_ino_caches(struct jffs2_sb_info *c) int i; struct jffs2_inode_cache *this, *next; - for (i=0; i<INOCACHE_HASHSIZE; i++) { + for (i=0; i < c->inocache_hashsize; i++) { this = c->inocache_list[i]; while (this) { next = this->next; diff --git a/fs/jffs2/nodelist.h b/fs/jffs2/nodelist.h index 523a91691052..5a53d9bdb2b5 100644 --- a/fs/jffs2/nodelist.h +++ b/fs/jffs2/nodelist.h @@ -199,7 +199,8 @@ struct jffs2_inode_cache { #define RAWNODE_CLASS_XATTR_DATUM 1 #define RAWNODE_CLASS_XATTR_REF 2 -#define INOCACHE_HASHSIZE 128 +#define INOCACHE_HASHSIZE_MIN 128 +#define INOCACHE_HASHSIZE_MAX 1024 #define write_ofs(c) ((c)->nextblock->offset + (c)->sector_size - (c)->nextblock->free_size) diff --git a/fs/jffs2/scan.c b/fs/jffs2/scan.c index 46f870d1cc36..b632dddcb482 100644 --- a/fs/jffs2/scan.c +++ b/fs/jffs2/scan.c @@ -20,7 +20,7 @@ #include "summary.h" #include "debug.h" -#define DEFAULT_EMPTY_SCAN_SIZE 1024 +#define DEFAULT_EMPTY_SCAN_SIZE 256 #define noisy_printk(noise, args...) do { \ if (*(noise)) { \ @@ -435,7 +435,7 @@ static int jffs2_scan_eraseblock (struct jffs2_sb_info *c, struct jffs2_eraseblo unsigned char *buf, uint32_t buf_size, struct jffs2_summary *s) { struct jffs2_unknown_node *node; struct jffs2_unknown_node crcnode; - uint32_t ofs, prevofs; + uint32_t ofs, prevofs, max_ofs; uint32_t hdr_crc, buf_ofs, buf_len; int err; int noise = 0; @@ -550,12 +550,12 @@ static int jffs2_scan_eraseblock (struct jffs2_sb_info *c, struct jffs2_eraseblo /* We temporarily use 'ofs' as a pointer into the buffer/jeb */ ofs = 0; - - /* Scan only 4KiB of 0xFF before declaring it's empty */ - while(ofs < EMPTY_SCAN_SIZE(c->sector_size) && *(uint32_t *)(&buf[ofs]) == 0xFFFFFFFF) + max_ofs = EMPTY_SCAN_SIZE(c->sector_size); + /* Scan only EMPTY_SCAN_SIZE of 0xFF before declaring it's empty */ + while(ofs < max_ofs && *(uint32_t *)(&buf[ofs]) == 0xFFFFFFFF) ofs += 4; - if (ofs == EMPTY_SCAN_SIZE(c->sector_size)) { + if (ofs == max_ofs) { #ifdef CONFIG_JFFS2_FS_WRITEBUFFER if (jffs2_cleanmarker_oob(c)) { /* scan oob, take care of cleanmarker */ diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index d1ae5dfc22b9..c86041b866a4 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -179,12 +179,11 @@ static int jffs2_fill_super(struct super_block *sb, void *data, int silent) return ret; } -static int jffs2_get_sb(struct file_system_type *fs_type, +static struct dentry *jffs2_mount(struct file_system_type *fs_type, int flags, const char *dev_name, - void *data, struct vfsmount *mnt) + void *data) { - return get_sb_mtd(fs_type, flags, dev_name, data, jffs2_fill_super, - mnt); + return mount_mtd(fs_type, flags, dev_name, data, jffs2_fill_super); } static void jffs2_put_super (struct super_block *sb) @@ -229,7 +228,7 @@ static void jffs2_kill_sb(struct super_block *sb) static struct file_system_type jffs2_fs_type = { .owner = THIS_MODULE, .name = "jffs2", - .get_sb = jffs2_get_sb, + .mount = jffs2_mount, .kill_sb = jffs2_kill_sb, }; diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index f8332dc8eeb2..3a09423b6c22 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -497,7 +497,7 @@ struct inode *diReadSpecial(struct super_block *sb, ino_t inum, int secondary) * appear hashed, but do not put on any lists. hlist_del() * will work fine and require no locking. */ - ip->i_hash.pprev = &ip->i_hash.next; + hlist_add_fake(&ip->i_hash); return (ip); } diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c index d945ea76b445..9466957ec841 100644 --- a/fs/jfs/jfs_txnmgr.c +++ b/fs/jfs/jfs_txnmgr.c @@ -1279,7 +1279,7 @@ int txCommit(tid_t tid, /* transaction identifier */ * lazy commit thread finishes processing */ if (tblk->xflag & COMMIT_DELETE) { - atomic_inc(&tblk->u.ip->i_count); + ihold(tblk->u.ip); /* * Avoid a rare deadlock * diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index a9cf8e8675be..231ca4af9bce 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -839,7 +839,7 @@ static int jfs_link(struct dentry *old_dentry, ip->i_ctime = CURRENT_TIME; dir->i_ctime = dir->i_mtime = CURRENT_TIME; mark_inode_dirty(dir); - atomic_inc(&ip->i_count); + ihold(ip); iplist[0] = ip; iplist[1] = dir; diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 68eee2bf629e..0669fc1cc3bf 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -583,11 +583,10 @@ static int jfs_unfreeze(struct super_block *sb) return 0; } -static int jfs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *jfs_do_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, jfs_fill_super, - mnt); + return mount_bdev(fs_type, flags, dev_name, data, jfs_fill_super); } static int jfs_sync_fs(struct super_block *sb, int wait) @@ -770,7 +769,7 @@ static const struct export_operations jfs_export_operations = { static struct file_system_type jfs_fs_type = { .owner = THIS_MODULE, .name = "jfs", - .get_sb = jfs_get_sb, + .mount = jfs_do_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/libfs.c b/fs/libfs.c index 62baa0387d6e..a3accdf528ad 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -201,9 +201,8 @@ static const struct super_operations simple_super_operations = { * Common helper for pseudo-filesystems (sockfs, pipefs, bdev - stuff that * will never be mountable) */ -int get_sb_pseudo(struct file_system_type *fs_type, char *name, - const struct super_operations *ops, unsigned long magic, - struct vfsmount *mnt) +struct dentry *mount_pseudo(struct file_system_type *fs_type, char *name, + const struct super_operations *ops, unsigned long magic) { struct super_block *s = sget(fs_type, NULL, set_anon_super, NULL); struct dentry *dentry; @@ -211,7 +210,7 @@ int get_sb_pseudo(struct file_system_type *fs_type, char *name, struct qstr d_name = {.name = name, .len = strlen(name)}; if (IS_ERR(s)) - return PTR_ERR(s); + return ERR_CAST(s); s->s_flags = MS_NOUSER; s->s_maxbytes = MAX_LFS_FILESIZE; @@ -241,12 +240,11 @@ int get_sb_pseudo(struct file_system_type *fs_type, char *name, d_instantiate(dentry, root); s->s_root = dentry; s->s_flags |= MS_ACTIVE; - simple_set_mnt(mnt, s); - return 0; + return dget(s->s_root); Enomem: deactivate_locked_super(s); - return -ENOMEM; + return ERR_PTR(-ENOMEM); } int simple_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) @@ -255,7 +253,7 @@ int simple_link(struct dentry *old_dentry, struct inode *dir, struct dentry *den inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; inc_nlink(inode); - atomic_inc(&inode->i_count); + ihold(inode); dget(dentry); d_instantiate(dentry, inode); return 0; @@ -892,10 +890,6 @@ EXPORT_SYMBOL_GPL(generic_fh_to_parent); */ int generic_file_fsync(struct file *file, int datasync) { - struct writeback_control wbc = { - .sync_mode = WB_SYNC_ALL, - .nr_to_write = 0, /* metadata-only; caller takes care of data */ - }; struct inode *inode = file->f_mapping->host; int err; int ret; @@ -906,7 +900,7 @@ int generic_file_fsync(struct file *file, int datasync) if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) return ret; - err = sync_inode(inode, &wbc); + err = sync_inode_metadata(inode, 1); if (ret == 0) ret = err; return ret; @@ -955,7 +949,7 @@ EXPORT_SYMBOL(dcache_dir_lseek); EXPORT_SYMBOL(dcache_dir_open); EXPORT_SYMBOL(dcache_readdir); EXPORT_SYMBOL(generic_read_dir); -EXPORT_SYMBOL(get_sb_pseudo); +EXPORT_SYMBOL(mount_pseudo); EXPORT_SYMBOL(simple_write_begin); EXPORT_SYMBOL(simple_write_end); EXPORT_SYMBOL(simple_dir_inode_operations); diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c index d5bb86866e6c..25509eb28fd7 100644 --- a/fs/lockd/clntlock.c +++ b/fs/lockd/clntlock.c @@ -14,7 +14,6 @@ #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/svc.h> #include <linux/lockd/lockd.h> -#include <linux/smp_lock.h> #include <linux/kthread.h> #define NLMDBG_FACILITY NLMDBG_CLIENT diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c index 47ea1e1925b8..332c54cf75e0 100644 --- a/fs/lockd/clntproc.c +++ b/fs/lockd/clntproc.c @@ -7,7 +7,6 @@ */ #include <linux/module.h> -#include <linux/smp_lock.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/errno.h> diff --git a/fs/lockd/host.c b/fs/lockd/host.c index bb464d12104c..ed0c59fe23ce 100644 --- a/fs/lockd/host.c +++ b/fs/lockd/host.c @@ -124,7 +124,7 @@ static struct nlm_host *nlm_lookup_host(struct nlm_lookup_host_info *ni) continue; if (host->h_server != ni->server) continue; - if (ni->server && + if (ni->server && ni->src_len != 0 && !rpc_cmp_addr(nlm_srcaddr(host), ni->src_sap)) continue; @@ -167,6 +167,7 @@ static struct nlm_host *nlm_lookup_host(struct nlm_lookup_host_info *ni) host->h_addrlen = ni->salen; rpc_set_port(nlm_addr(host), 0); memcpy(nlm_srcaddr(host), ni->src_sap, ni->src_len); + host->h_srcaddrlen = ni->src_len; host->h_version = ni->version; host->h_proto = ni->protocol; host->h_rpcclnt = NULL; @@ -238,9 +239,6 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap, const char *hostname, int noresvport) { - const struct sockaddr source = { - .sa_family = AF_UNSPEC, - }; struct nlm_lookup_host_info ni = { .server = 0, .sap = sap, @@ -249,8 +247,6 @@ struct nlm_host *nlmclnt_lookup_host(const struct sockaddr *sap, .version = version, .hostname = hostname, .hostname_len = strlen(hostname), - .src_sap = &source, - .src_len = sizeof(source), .noresvport = noresvport, }; @@ -353,10 +349,10 @@ nlm_bind_host(struct nlm_host *host) .to_retries = 5U, }; struct rpc_create_args args = { + .net = &init_net, .protocol = host->h_proto, .address = nlm_addr(host), .addrsize = host->h_addrlen, - .saddress = nlm_srcaddr(host), .timeout = &timeparms, .servername = host->h_name, .program = &nlm_program, @@ -375,6 +371,8 @@ nlm_bind_host(struct nlm_host *host) args.flags |= RPC_CLNT_CREATE_HARDRTRY; if (host->h_noresvport) args.flags |= RPC_CLNT_CREATE_NONPRIVPORT; + if (host->h_srcaddrlen) + args.saddress = nlm_srcaddr(host); clnt = rpc_create(&args); if (!IS_ERR(clnt)) diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index e3015464fbab..e0c918949644 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -69,6 +69,7 @@ static struct rpc_clnt *nsm_create(void) .sin_addr.s_addr = htonl(INADDR_LOOPBACK), }; struct rpc_create_args args = { + .net = &init_net, .protocol = XPRT_TRANSPORT_UDP, .address = (struct sockaddr *)&sin, .addrsize = sizeof(sin), diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index f1bacf1a0391..abfff9d7979d 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -22,7 +22,6 @@ #include <linux/in.h> #include <linux/uio.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/mutex.h> #include <linux/kthread.h> #include <linux/freezer.h> @@ -130,15 +129,6 @@ lockd(void *vrqstp) dprintk("NFS locking service started (ver " LOCKD_VERSION ").\n"); - /* - * FIXME: it would be nice if lockd didn't spend its entire life - * running under the BKL. At the very least, it would be good to - * have someone clarify what it's intended to protect here. I've - * seen some handwavy posts about posix locking needing to be - * done under the BKL, but it's far from clear. - */ - lock_kernel(); - if (!nlm_timeout) nlm_timeout = LOCKD_DFLT_TIMEO; nlmsvc_timeout = nlm_timeout * HZ; @@ -195,7 +185,6 @@ lockd(void *vrqstp) if (nlmsvc_ops) nlmsvc_invalidate_all(); nlm_shutdown_hosts(); - unlock_kernel(); return 0; } @@ -206,7 +195,7 @@ static int create_lockd_listener(struct svc_serv *serv, const char *name, xprt = svc_find_xprt(serv, name, family, 0); if (xprt == NULL) - return svc_create_xprt(serv, name, family, port, + return svc_create_xprt(serv, name, &init_net, family, port, SVC_SOCK_DEFAULTS); svc_xprt_put(xprt); return 0; diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 031c6569a134..38d261192453 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -9,7 +9,6 @@ #include <linux/types.h> #include <linux/time.h> -#include <linux/smp_lock.h> #include <linux/lockd/lockd.h> #include <linux/lockd/share.h> @@ -230,9 +229,7 @@ static void nlm4svc_callback_exit(struct rpc_task *task, void *data) static void nlm4svc_callback_release(void *data) { - lock_kernel(); nlm_release_call(data); - unlock_kernel(); } static const struct rpc_call_ops nlm4svc_callback_ops = { diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index 84055d31bfc5..ef5659b211e9 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -25,7 +25,6 @@ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/sched.h> -#include <linux/smp_lock.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/svc.h> #include <linux/lockd/nlm.h> @@ -52,12 +51,13 @@ static const struct rpc_call_ops nlmsvc_grant_ops; * The list of blocked locks to retry */ static LIST_HEAD(nlm_blocked); +static DEFINE_SPINLOCK(nlm_blocked_lock); /* * Insert a blocked lock into the global list */ static void -nlmsvc_insert_block(struct nlm_block *block, unsigned long when) +nlmsvc_insert_block_locked(struct nlm_block *block, unsigned long when) { struct nlm_block *b; struct list_head *pos; @@ -87,6 +87,13 @@ nlmsvc_insert_block(struct nlm_block *block, unsigned long when) block->b_when = when; } +static void nlmsvc_insert_block(struct nlm_block *block, unsigned long when) +{ + spin_lock(&nlm_blocked_lock); + nlmsvc_insert_block_locked(block, when); + spin_unlock(&nlm_blocked_lock); +} + /* * Remove a block from the global list */ @@ -94,7 +101,9 @@ static inline void nlmsvc_remove_block(struct nlm_block *block) { if (!list_empty(&block->b_list)) { + spin_lock(&nlm_blocked_lock); list_del_init(&block->b_list); + spin_unlock(&nlm_blocked_lock); nlmsvc_release_block(block); } } @@ -651,7 +660,7 @@ static int nlmsvc_grant_deferred(struct file_lock *fl, struct file_lock *conf, struct nlm_block *block; int rc = -ENOENT; - lock_kernel(); + spin_lock(&nlm_blocked_lock); list_for_each_entry(block, &nlm_blocked, b_list) { if (nlm_compare_locks(&block->b_call->a_args.lock.fl, fl)) { dprintk("lockd: nlmsvc_notify_blocked block %p flags %d\n", @@ -665,13 +674,13 @@ static int nlmsvc_grant_deferred(struct file_lock *fl, struct file_lock *conf, } else if (result == 0) block->b_granted = 1; - nlmsvc_insert_block(block, 0); + nlmsvc_insert_block_locked(block, 0); svc_wake_up(block->b_daemon); rc = 0; break; } } - unlock_kernel(); + spin_unlock(&nlm_blocked_lock); if (rc == -ENOENT) printk(KERN_WARNING "lockd: grant for unknown block\n"); return rc; @@ -690,14 +699,16 @@ nlmsvc_notify_blocked(struct file_lock *fl) struct nlm_block *block; dprintk("lockd: VFS unblock notification for block %p\n", fl); + spin_lock(&nlm_blocked_lock); list_for_each_entry(block, &nlm_blocked, b_list) { if (nlm_compare_locks(&block->b_call->a_args.lock.fl, fl)) { - nlmsvc_insert_block(block, 0); + nlmsvc_insert_block_locked(block, 0); + spin_unlock(&nlm_blocked_lock); svc_wake_up(block->b_daemon); return; } } - + spin_unlock(&nlm_blocked_lock); printk(KERN_WARNING "lockd: notification for unknown block!\n"); } @@ -803,7 +814,7 @@ static void nlmsvc_grant_callback(struct rpc_task *task, void *data) dprintk("lockd: GRANT_MSG RPC callback\n"); - lock_kernel(); + spin_lock(&nlm_blocked_lock); /* if the block is not on a list at this point then it has * been invalidated. Don't try to requeue it. * @@ -825,19 +836,20 @@ static void nlmsvc_grant_callback(struct rpc_task *task, void *data) /* Call was successful, now wait for client callback */ timeout = 60 * HZ; } - nlmsvc_insert_block(block, timeout); + nlmsvc_insert_block_locked(block, timeout); svc_wake_up(block->b_daemon); out: - unlock_kernel(); + spin_unlock(&nlm_blocked_lock); } +/* + * FIXME: nlmsvc_release_block() grabs a mutex. This is not allowed for an + * .rpc_release rpc_call_op + */ static void nlmsvc_grant_release(void *data) { struct nlm_rqst *call = data; - - lock_kernel(); nlmsvc_release_block(call->a_block); - unlock_kernel(); } static const struct rpc_call_ops nlmsvc_grant_ops = { diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index 0f2ab741ae7c..0caea5310ac3 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -9,7 +9,6 @@ #include <linux/types.h> #include <linux/time.h> -#include <linux/smp_lock.h> #include <linux/lockd/lockd.h> #include <linux/lockd/share.h> @@ -260,9 +259,7 @@ static void nlmsvc_callback_exit(struct rpc_task *task, void *data) static void nlmsvc_callback_release(void *data) { - lock_kernel(); nlm_release_call(data); - unlock_kernel(); } static const struct rpc_call_ops nlmsvc_callback_ops = { diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index d0ef94cfb3da..1ca0679c80bf 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -170,6 +170,7 @@ nlm_traverse_locks(struct nlm_host *host, struct nlm_file *file, again: file->f_locks = 0; + lock_flocks(); /* protects i_flock list */ for (fl = inode->i_flock; fl; fl = fl->fl_next) { if (fl->fl_lmops != &nlmsvc_lock_operations) continue; @@ -181,6 +182,7 @@ again: if (match(lockhost, host)) { struct file_lock lock = *fl; + unlock_flocks(); lock.fl_type = F_UNLCK; lock.fl_start = 0; lock.fl_end = OFFSET_MAX; @@ -192,6 +194,7 @@ again: goto again; } } + unlock_flocks(); return 0; } @@ -226,10 +229,14 @@ nlm_file_inuse(struct nlm_file *file) if (file->f_count || !list_empty(&file->f_blocks) || file->f_shares) return 1; + lock_flocks(); for (fl = inode->i_flock; fl; fl = fl->fl_next) { - if (fl->fl_lmops == &nlmsvc_lock_operations) + if (fl->fl_lmops == &nlmsvc_lock_operations) { + unlock_flocks(); return 1; + } } + unlock_flocks(); file->f_locks = 0; return 0; } diff --git a/fs/locks.c b/fs/locks.c index 8b2b6ad56a09..8729347bcd1a 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -122,7 +122,6 @@ #include <linux/module.h> #include <linux/security.h> #include <linux/slab.h> -#include <linux/smp_lock.h> #include <linux/syscalls.h> #include <linux/time.h> #include <linux/rcupdate.h> @@ -142,6 +141,7 @@ int lease_break_time = 45; static LIST_HEAD(file_lock_list); static LIST_HEAD(blocked_list); +static DEFINE_SPINLOCK(file_lock_lock); /* * Protects the two list heads above, plus the inode->i_flock list @@ -149,23 +149,24 @@ static LIST_HEAD(blocked_list); */ void lock_flocks(void) { - lock_kernel(); + spin_lock(&file_lock_lock); } EXPORT_SYMBOL_GPL(lock_flocks); void unlock_flocks(void) { - unlock_kernel(); + spin_unlock(&file_lock_lock); } EXPORT_SYMBOL_GPL(unlock_flocks); static struct kmem_cache *filelock_cache __read_mostly; /* Allocate an empty lock structure. */ -static struct file_lock *locks_alloc_lock(void) +struct file_lock *locks_alloc_lock(void) { return kmem_cache_alloc(filelock_cache, GFP_KERNEL); } +EXPORT_SYMBOL_GPL(locks_alloc_lock); void locks_release_private(struct file_lock *fl) { @@ -184,7 +185,7 @@ void locks_release_private(struct file_lock *fl) EXPORT_SYMBOL_GPL(locks_release_private); /* Free a lock which is not in use. */ -static void locks_free_lock(struct file_lock *fl) +void locks_free_lock(struct file_lock *fl) { BUG_ON(waitqueue_active(&fl->fl_wait)); BUG_ON(!list_empty(&fl->fl_block)); @@ -193,6 +194,7 @@ static void locks_free_lock(struct file_lock *fl) locks_release_private(fl); kmem_cache_free(filelock_cache, fl); } +EXPORT_SYMBOL(locks_free_lock); void locks_init_lock(struct file_lock *fl) { @@ -232,11 +234,8 @@ static void locks_copy_private(struct file_lock *new, struct file_lock *fl) fl->fl_ops->fl_copy_lock(new, fl); new->fl_ops = fl->fl_ops; } - if (fl->fl_lmops) { - if (fl->fl_lmops->fl_copy_lock) - fl->fl_lmops->fl_copy_lock(new, fl); + if (fl->fl_lmops) new->fl_lmops = fl->fl_lmops; - } } /* @@ -1365,31 +1364,27 @@ int fcntl_getlease(struct file *filp) int generic_setlease(struct file *filp, long arg, struct file_lock **flp) { struct file_lock *fl, **before, **my_before = NULL, *lease; - struct file_lock *new_fl = NULL; struct dentry *dentry = filp->f_path.dentry; struct inode *inode = dentry->d_inode; int error, rdlease_count = 0, wrlease_count = 0; + lease = *flp; + + error = -EACCES; if ((current_fsuid() != inode->i_uid) && !capable(CAP_LEASE)) - return -EACCES; + goto out; + error = -EINVAL; if (!S_ISREG(inode->i_mode)) - return -EINVAL; + goto out; error = security_file_lock(filp, arg); if (error) - return error; + goto out; time_out_leases(inode); BUG_ON(!(*flp)->fl_lmops->fl_break); - lease = *flp; - if (arg != F_UNLCK) { - error = -ENOMEM; - new_fl = locks_alloc_lock(); - if (new_fl == NULL) - goto out; - error = -EAGAIN; if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0)) goto out; @@ -1429,12 +1424,12 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp) goto out; if (my_before != NULL) { - *flp = *my_before; error = lease->fl_lmops->fl_change(my_before, arg); + if (!error) + *flp = *my_before; goto out; } - error = 0; if (arg == F_UNLCK) goto out; @@ -1442,15 +1437,10 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp) if (!leases_enable) goto out; - locks_copy_lock(new_fl, lease); - locks_insert_lock(before, new_fl); - - *flp = new_fl; + locks_insert_lock(before, lease); return 0; out: - if (new_fl != NULL) - locks_free_lock(new_fl); return error; } EXPORT_SYMBOL(generic_setlease); @@ -1502,6 +1492,59 @@ int vfs_setlease(struct file *filp, long arg, struct file_lock **lease) } EXPORT_SYMBOL_GPL(vfs_setlease); +static int do_fcntl_delete_lease(struct file *filp) +{ + struct file_lock fl, *flp = &fl; + + lease_init(filp, F_UNLCK, flp); + + return vfs_setlease(filp, F_UNLCK, &flp); +} + +static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg) +{ + struct file_lock *fl, *ret; + struct fasync_struct *new; + int error; + + fl = lease_alloc(filp, arg); + if (IS_ERR(fl)) + return PTR_ERR(fl); + + new = fasync_alloc(); + if (!new) { + locks_free_lock(fl); + return -ENOMEM; + } + ret = fl; + lock_flocks(); + error = __vfs_setlease(filp, arg, &ret); + if (error) { + unlock_flocks(); + locks_free_lock(fl); + goto out_free_fasync; + } + if (ret != fl) + locks_free_lock(fl); + + /* + * fasync_insert_entry() returns the old entry if any. + * If there was no old entry, then it used 'new' and + * inserted it into the fasync list. Clear new so that + * we don't release it here. + */ + if (!fasync_insert_entry(fd, filp, &ret->fl_fasync, new)) + new = NULL; + + error = __f_setown(filp, task_pid(current), PIDTYPE_PID, 0); + unlock_flocks(); + +out_free_fasync: + if (new) + fasync_free(new); + return error; +} + /** * fcntl_setlease - sets a lease on an open file * @fd: open file descriptor @@ -1514,34 +1557,9 @@ EXPORT_SYMBOL_GPL(vfs_setlease); */ int fcntl_setlease(unsigned int fd, struct file *filp, long arg) { - struct file_lock fl, *flp = &fl; - struct inode *inode = filp->f_path.dentry->d_inode; - int error; - - locks_init_lock(&fl); - error = lease_init(filp, arg, &fl); - if (error) - return error; - - lock_flocks(); - - error = __vfs_setlease(filp, arg, &flp); - if (error || arg == F_UNLCK) - goto out_unlock; - - error = fasync_helper(fd, filp, 1, &flp->fl_fasync); - if (error < 0) { - /* remove lease just inserted by setlease */ - flp->fl_type = F_UNLCK | F_INPROGRESS; - flp->fl_break_time = jiffies - 10; - time_out_leases(inode); - goto out_unlock; - } - - error = __f_setown(filp, task_pid(current), PIDTYPE_PID, 0); -out_unlock: - unlock_flocks(); - return error; + if (arg == F_UNLCK) + return do_fcntl_delete_lease(filp); + return do_fcntl_add_lease(fd, filp, arg); } /** @@ -2109,7 +2127,7 @@ EXPORT_SYMBOL_GPL(vfs_cancel_lock); #include <linux/seq_file.h> static void lock_get_status(struct seq_file *f, struct file_lock *fl, - int id, char *pfx) + loff_t id, char *pfx) { struct inode *inode = NULL; unsigned int fl_pid; @@ -2122,7 +2140,7 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl, if (fl->fl_file != NULL) inode = fl->fl_file->f_path.dentry->d_inode; - seq_printf(f, "%d:%s ", id, pfx); + seq_printf(f, "%lld:%s ", id, pfx); if (IS_POSIX(fl)) { seq_printf(f, "%6s %s ", (fl->fl_flags & FL_ACCESS) ? "ACCESS" : "POSIX ", @@ -2185,24 +2203,27 @@ static int locks_show(struct seq_file *f, void *v) fl = list_entry(v, struct file_lock, fl_link); - lock_get_status(f, fl, (long)f->private, ""); + lock_get_status(f, fl, *((loff_t *)f->private), ""); list_for_each_entry(bfl, &fl->fl_block, fl_block) - lock_get_status(f, bfl, (long)f->private, " ->"); + lock_get_status(f, bfl, *((loff_t *)f->private), " ->"); - f->private++; return 0; } static void *locks_start(struct seq_file *f, loff_t *pos) { + loff_t *p = f->private; + lock_flocks(); - f->private = (void *)1; + *p = (*pos + 1); return seq_list_start(&file_lock_list, *pos); } static void *locks_next(struct seq_file *f, void *v, loff_t *pos) { + loff_t *p = f->private; + ++*p; return seq_list_next(v, &file_lock_list, pos); } @@ -2220,14 +2241,14 @@ static const struct seq_operations locks_seq_operations = { static int locks_open(struct inode *inode, struct file *filp) { - return seq_open(filp, &locks_seq_operations); + return seq_open_private(filp, &locks_seq_operations, sizeof(loff_t)); } static const struct file_operations proc_locks_operations = { .open = locks_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = seq_release_private, }; static int __init proc_locks_init(void) diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c index 9bd2ce2a3040..92ca6fbe09bd 100644 --- a/fs/logfs/dev_bdev.c +++ b/fs/logfs/dev_bdev.c @@ -298,9 +298,9 @@ static int bdev_write_sb(struct super_block *sb, struct page *page) return sync_request(page, bdev, WRITE); } -static void bdev_put_device(struct super_block *sb) +static void bdev_put_device(struct logfs_super *s) { - close_bdev_exclusive(logfs_super(sb)->s_bdev, FMODE_READ|FMODE_WRITE); + close_bdev_exclusive(s->s_bdev, FMODE_READ|FMODE_WRITE); } static int bdev_can_write_buf(struct super_block *sb, u64 ofs) @@ -320,8 +320,8 @@ static const struct logfs_device_ops bd_devops = { .put_device = bdev_put_device, }; -int logfs_get_sb_bdev(struct file_system_type *type, int flags, - const char *devname, struct vfsmount *mnt) +int logfs_get_sb_bdev(struct logfs_super *p, struct file_system_type *type, + const char *devname) { struct block_device *bdev; @@ -332,8 +332,11 @@ int logfs_get_sb_bdev(struct file_system_type *type, int flags, if (MAJOR(bdev->bd_dev) == MTD_BLOCK_MAJOR) { int mtdnr = MINOR(bdev->bd_dev); close_bdev_exclusive(bdev, FMODE_READ|FMODE_WRITE); - return logfs_get_sb_mtd(type, flags, mtdnr, mnt); + return logfs_get_sb_mtd(p, mtdnr); } - return logfs_get_sb_device(type, flags, NULL, bdev, &bd_devops, mnt); + p->s_bdev = bdev; + p->s_mtd = NULL; + p->s_devops = &bd_devops; + return 0; } diff --git a/fs/logfs/dev_mtd.c b/fs/logfs/dev_mtd.c index a85d47d13e4b..7466e9dcc8c5 100644 --- a/fs/logfs/dev_mtd.c +++ b/fs/logfs/dev_mtd.c @@ -230,9 +230,9 @@ static void mtd_writeseg(struct super_block *sb, u64 ofs, size_t len) __mtd_writeseg(sb, ofs, ofs >> PAGE_SHIFT, len >> PAGE_SHIFT); } -static void mtd_put_device(struct super_block *sb) +static void mtd_put_device(struct logfs_super *s) { - put_mtd_device(logfs_super(sb)->s_mtd); + put_mtd_device(s->s_mtd); } static int mtd_can_write_buf(struct super_block *sb, u64 ofs) @@ -265,14 +265,14 @@ static const struct logfs_device_ops mtd_devops = { .put_device = mtd_put_device, }; -int logfs_get_sb_mtd(struct file_system_type *type, int flags, - int mtdnr, struct vfsmount *mnt) +int logfs_get_sb_mtd(struct logfs_super *s, int mtdnr) { - struct mtd_info *mtd; - const struct logfs_device_ops *devops = &mtd_devops; - - mtd = get_mtd_device(NULL, mtdnr); + struct mtd_info *mtd = get_mtd_device(NULL, mtdnr); if (IS_ERR(mtd)) return PTR_ERR(mtd); - return logfs_get_sb_device(type, flags, mtd, NULL, devops, mnt); + + s->s_bdev = NULL; + s->s_mtd = mtd; + s->s_devops = &mtd_devops; + return 0; } diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c index 1eb4e89e045b..409dfd65e9a1 100644 --- a/fs/logfs/dir.c +++ b/fs/logfs/dir.c @@ -569,7 +569,7 @@ static int logfs_link(struct dentry *old_dentry, struct inode *dir, return -EMLINK; inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; - atomic_inc(&inode->i_count); + ihold(inode); inode->i_nlink++; mark_inode_dirty_sync(inode); diff --git a/fs/logfs/logfs.h b/fs/logfs/logfs.h index b8786264d243..57afd4a6fabb 100644 --- a/fs/logfs/logfs.h +++ b/fs/logfs/logfs.h @@ -136,6 +136,7 @@ struct logfs_area_ops { int (*erase_segment)(struct logfs_area *area); }; +struct logfs_super; /* forward */ /** * struct logfs_device_ops - device access operations * @@ -156,7 +157,7 @@ struct logfs_device_ops { int ensure_write); int (*can_write_buf)(struct super_block *sb, u64 ofs); void (*sync)(struct super_block *sb); - void (*put_device)(struct super_block *sb); + void (*put_device)(struct logfs_super *s); }; /** @@ -471,11 +472,13 @@ void logfs_compr_exit(void); /* dev_bdev.c */ #ifdef CONFIG_BLOCK -int logfs_get_sb_bdev(struct file_system_type *type, int flags, - const char *devname, struct vfsmount *mnt); +int logfs_get_sb_bdev(struct logfs_super *s, + struct file_system_type *type, + const char *devname); #else -static inline int logfs_get_sb_bdev(struct file_system_type *type, int flags, - const char *devname, struct vfsmount *mnt) +static inline int logfs_get_sb_bdev(struct logfs_super *s, + struct file_system_type *type, + const char *devname) { return -ENODEV; } @@ -483,11 +486,9 @@ static inline int logfs_get_sb_bdev(struct file_system_type *type, int flags, /* dev_mtd.c */ #ifdef CONFIG_MTD -int logfs_get_sb_mtd(struct file_system_type *type, int flags, - int mtdnr, struct vfsmount *mnt); +int logfs_get_sb_mtd(struct logfs_super *s, int mtdnr); #else -static inline int logfs_get_sb_mtd(struct file_system_type *type, int flags, - int mtdnr, struct vfsmount *mnt) +static inline int logfs_get_sb_mtd(struct logfs_super *s, int mtdnr) { return -ENODEV; } @@ -619,9 +620,6 @@ void emergency_read_end(struct page *page); void logfs_crash_dump(struct super_block *sb); void *memchr_inv(const void *s, int c, size_t n); int logfs_statfs(struct dentry *dentry, struct kstatfs *stats); -int logfs_get_sb_device(struct file_system_type *type, int flags, - struct mtd_info *mtd, struct block_device *bdev, - const struct logfs_device_ops *devops, struct vfsmount *mnt); int logfs_check_ds(struct logfs_disk_super *ds); int logfs_write_sb(struct super_block *sb); diff --git a/fs/logfs/super.c b/fs/logfs/super.c index 5336155c5d81..33435e4b14d2 100644 --- a/fs/logfs/super.c +++ b/fs/logfs/super.c @@ -325,7 +325,7 @@ static int logfs_make_writeable(struct super_block *sb) return 0; } -static int logfs_get_sb_final(struct super_block *sb, struct vfsmount *mnt) +static int logfs_get_sb_final(struct super_block *sb) { struct logfs_super *super = logfs_super(sb); struct inode *rootdir; @@ -356,7 +356,6 @@ static int logfs_get_sb_final(struct super_block *sb, struct vfsmount *mnt) } log_super("LogFS: Finished mounting\n"); - simple_set_mnt(mnt, sb); return 0; fail: @@ -529,43 +528,37 @@ static void logfs_kill_sb(struct super_block *sb) logfs_cleanup_rw(sb); if (super->s_erase_page) __free_page(super->s_erase_page); - super->s_devops->put_device(sb); + super->s_devops->put_device(super); logfs_mempool_destroy(super->s_btree_pool); logfs_mempool_destroy(super->s_alias_pool); kfree(super); log_super("LogFS: Finished unmounting\n"); } -int logfs_get_sb_device(struct file_system_type *type, int flags, - struct mtd_info *mtd, struct block_device *bdev, - const struct logfs_device_ops *devops, struct vfsmount *mnt) +static struct dentry *logfs_get_sb_device(struct logfs_super *super, + struct file_system_type *type, int flags) { - struct logfs_super *super; struct super_block *sb; int err = -ENOMEM; static int mount_count; log_super("LogFS: Start mount %x\n", mount_count++); - super = kzalloc(sizeof(*super), GFP_KERNEL); - if (!super) - goto err0; - super->s_mtd = mtd; - super->s_bdev = bdev; err = -EINVAL; sb = sget(type, logfs_sb_test, logfs_sb_set, super); - if (IS_ERR(sb)) - goto err0; + if (IS_ERR(sb)) { + super->s_devops->put_device(super); + kfree(super); + return ERR_CAST(sb); + } if (sb->s_root) { /* Device is already in use */ - err = 0; - simple_set_mnt(mnt, sb); - goto err0; + super->s_devops->put_device(super); + kfree(super); + return dget(sb->s_root); } - super->s_devops = devops; - /* * sb->s_maxbytes is limited to 8TB. On 32bit systems, the page cache * only covers 16TB and the upper 8TB are used for indirect blocks. @@ -581,10 +574,12 @@ int logfs_get_sb_device(struct file_system_type *type, int flags, goto err1; sb->s_flags |= MS_ACTIVE; - err = logfs_get_sb_final(sb, mnt); - if (err) + err = logfs_get_sb_final(sb); + if (err) { deactivate_locked_super(sb); - return err; + return ERR_PTR(err); + } + return dget(sb->s_root); err1: /* no ->s_root, no ->put_super() */ @@ -592,37 +587,45 @@ err1: iput(super->s_segfile_inode); iput(super->s_mapping_inode); deactivate_locked_super(sb); - return err; -err0: - kfree(super); - //devops->put_device(sb); - return err; + return ERR_PTR(err); } -static int logfs_get_sb(struct file_system_type *type, int flags, - const char *devname, void *data, struct vfsmount *mnt) +static struct dentry *logfs_mount(struct file_system_type *type, int flags, + const char *devname, void *data) { ulong mtdnr; + struct logfs_super *super; + int err; - if (!devname) - return logfs_get_sb_bdev(type, flags, devname, mnt); - if (strncmp(devname, "mtd", 3)) - return logfs_get_sb_bdev(type, flags, devname, mnt); + super = kzalloc(sizeof(*super), GFP_KERNEL); + if (!super) + return ERR_PTR(-ENOMEM); - { + if (!devname) + err = logfs_get_sb_bdev(super, type, devname); + else if (strncmp(devname, "mtd", 3)) + err = logfs_get_sb_bdev(super, type, devname); + else { char *garbage; mtdnr = simple_strtoul(devname+3, &garbage, 0); if (*garbage) - return -EINVAL; + err = -EINVAL; + else + err = logfs_get_sb_mtd(super, mtdnr); + } + + if (err) { + kfree(super); + return ERR_PTR(err); } - return logfs_get_sb_mtd(type, flags, mtdnr, mnt); + return logfs_get_sb_device(super, type, flags); } static struct file_system_type logfs_fs_type = { .owner = THIS_MODULE, .name = "logfs", - .get_sb = logfs_get_sb, + .mount = logfs_mount, .kill_sb = logfs_kill_sb, .fs_flags = FS_REQUIRES_DEV, diff --git a/fs/minix/inode.c b/fs/minix/inode.c index e39d6bf2e8fb..fb2020858a34 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -614,17 +614,16 @@ void minix_truncate(struct inode * inode) V2_minix_truncate(inode); } -static int minix_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *minix_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, minix_fill_super, - mnt); + return mount_bdev(fs_type, flags, dev_name, data, minix_fill_super); } static struct file_system_type minix_fs_type = { .owner = THIS_MODULE, .name = "minix", - .get_sb = minix_get_sb, + .mount = minix_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/minix/namei.c b/fs/minix/namei.c index f3f3578393a4..c0d35a3accef 100644 --- a/fs/minix/namei.c +++ b/fs/minix/namei.c @@ -101,7 +101,7 @@ static int minix_link(struct dentry * old_dentry, struct inode * dir, inode->i_ctime = CURRENT_TIME_SEC; inode_inc_link_count(inode); - atomic_inc(&inode->i_count); + ihold(inode); return add_nondir(dentry, inode); } diff --git a/fs/namei.c b/fs/namei.c index 24896e833565..5362af9b7372 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1121,11 +1121,13 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, static struct dentry *__lookup_hash(struct qstr *name, struct dentry *base, struct nameidata *nd) { + struct inode *inode = base->d_inode; struct dentry *dentry; - struct inode *inode; int err; - inode = base->d_inode; + err = exec_permission(inode); + if (err) + return ERR_PTR(err); /* * See if the low-level filesystem might want @@ -1161,11 +1163,6 @@ out: */ static struct dentry *lookup_hash(struct nameidata *nd) { - int err; - - err = exec_permission(nd->path.dentry->d_inode); - if (err) - return ERR_PTR(err); return __lookup_hash(&nd->last, nd->path.dentry, nd); } @@ -1213,9 +1210,6 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) if (err) return ERR_PTR(err); - err = exec_permission(base->d_inode); - if (err) - return ERR_PTR(err); return __lookup_hash(&this, base, NULL); } @@ -1580,6 +1574,7 @@ static struct file *finish_open(struct nameidata *nd, */ if (will_truncate) mnt_drop_write(nd->path.mnt); + path_put(&nd->path); return filp; exit: @@ -1681,6 +1676,7 @@ static struct file *do_last(struct nameidata *nd, struct path *path, } filp = nameidata_to_filp(nd); mnt_drop_write(nd->path.mnt); + path_put(&nd->path); if (!IS_ERR(filp)) { error = ima_file_check(filp, acc_mode); if (error) { @@ -2291,7 +2287,7 @@ static long do_unlinkat(int dfd, const char __user *pathname) goto slashes; inode = dentry->d_inode; if (inode) - atomic_inc(&inode->i_count); + ihold(inode); error = mnt_want_write(nd.path.mnt); if (error) goto exit2; diff --git a/fs/namespace.c b/fs/namespace.c index 7ca5182c0bed..3dbfc072ec70 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -13,7 +13,6 @@ #include <linux/sched.h> #include <linux/spinlock.h> #include <linux/percpu.h> -#include <linux/smp_lock.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/acct.h> @@ -595,7 +594,7 @@ static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root, goto out_free; } - mnt->mnt_flags = old->mnt_flags; + mnt->mnt_flags = old->mnt_flags & ~MNT_WRITE_HOLD; atomic_inc(&sb->s_active); mnt->mnt_sb = sb; mnt->mnt_root = dget(root); diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c index aac8832e919e..f22b12e7d337 100644 --- a/fs/ncpfs/dir.c +++ b/fs/ncpfs/dir.c @@ -19,7 +19,6 @@ #include <linux/mm.h> #include <asm/uaccess.h> #include <asm/byteorder.h> -#include <linux/smp_lock.h> #include <linux/ncp_fs.h> diff --git a/fs/ncpfs/file.c b/fs/ncpfs/file.c index 6c754f70c529..cb50aaf981df 100644 --- a/fs/ncpfs/file.c +++ b/fs/ncpfs/file.c @@ -17,7 +17,6 @@ #include <linux/mm.h> #include <linux/vmalloc.h> #include <linux/sched.h> -#include <linux/smp_lock.h> #include <linux/ncp_fs.h> #include "ncplib_kernel.h" diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index 985fabb26aca..8fb93b604e73 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -26,7 +26,6 @@ #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/init.h> -#include <linux/smp_lock.h> #include <linux/vfs.h> #include <linux/mount.h> #include <linux/seq_file.h> @@ -1020,16 +1019,16 @@ out: return result; } -static int ncp_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *ncp_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_nodev(fs_type, flags, data, ncp_fill_super, mnt); + return mount_nodev(fs_type, flags, data, ncp_fill_super); } static struct file_system_type ncp_fs_type = { .owner = THIS_MODULE, .name = "ncpfs", - .get_sb = ncp_get_sb, + .mount = ncp_mount, .kill_sb = kill_anon_super, .fs_flags = FS_BINARY_MOUNTDATA, }; diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c index c2a1f9a155c3..d40a547e3377 100644 --- a/fs/ncpfs/ioctl.c +++ b/fs/ncpfs/ioctl.c @@ -17,7 +17,6 @@ #include <linux/mount.h> #include <linux/slab.h> #include <linux/highuid.h> -#include <linux/smp_lock.h> #include <linux/vmalloc.h> #include <linux/sched.h> diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 5c55c26af165..ba306658a6db 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -1,7 +1,6 @@ config NFS_FS tristate "NFS client support" depends on INET && FILE_LOCKING - depends on BKL # fix as soon as lockd is done select LOCKD select SUNRPC select NFS_ACL_SUPPORT if NFS_V3_ACL @@ -77,13 +76,17 @@ config NFS_V4 config NFS_V4_1 bool "NFS client support for NFSv4.1 (EXPERIMENTAL)" - depends on NFS_V4 && EXPERIMENTAL + depends on NFS_FS && NFS_V4 && EXPERIMENTAL + select PNFS_FILE_LAYOUT help This option enables support for minor version 1 of the NFSv4 protocol - (draft-ietf-nfsv4-minorversion1) in the kernel's NFS client. + (RFC 5661) in the kernel's NFS client. If unsure, say N. +config PNFS_FILE_LAYOUT + tristate + config ROOT_NFS bool "Root file system on NFS" depends on NFS_FS=y && IP_PNP diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index da7fda639eac..4776ff9e3814 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -15,5 +15,9 @@ nfs-$(CONFIG_NFS_V4) += nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o \ delegation.o idmap.o \ callback.o callback_xdr.o callback_proc.o \ nfs4namespace.o +nfs-$(CONFIG_NFS_V4_1) += pnfs.o nfs-$(CONFIG_SYSCTL) += sysctl.o nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o + +obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o +nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index e17b49e2eabd..93a8b3bd69e3 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -9,7 +9,6 @@ #include <linux/completion.h> #include <linux/ip.h> #include <linux/module.h> -#include <linux/smp_lock.h> #include <linux/sunrpc/svc.h> #include <linux/sunrpc/svcsock.h> #include <linux/nfs_fs.h> @@ -109,7 +108,7 @@ nfs4_callback_up(struct svc_serv *serv) { int ret; - ret = svc_create_xprt(serv, "tcp", PF_INET, + ret = svc_create_xprt(serv, "tcp", &init_net, PF_INET, nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS); if (ret <= 0) goto out_err; @@ -117,7 +116,7 @@ nfs4_callback_up(struct svc_serv *serv) dprintk("NFS: Callback listener port = %u (af %u)\n", nfs_callback_tcpport, PF_INET); - ret = svc_create_xprt(serv, "tcp", PF_INET6, + ret = svc_create_xprt(serv, "tcp", &init_net, PF_INET6, nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS); if (ret > 0) { nfs_callback_tcpport6 = ret; diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index 930d10fecdaf..2950fca0c61b 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -118,11 +118,11 @@ int nfs41_validate_delegation_stateid(struct nfs_delegation *delegation, const n if (delegation == NULL) return 0; - /* seqid is 4-bytes long */ - if (((u32 *) &stateid->data)[0] != 0) + if (stateid->stateid.seqid != 0) return 0; - if (memcmp(&delegation->stateid.data[4], &stateid->data[4], - sizeof(stateid->data)-4)) + if (memcmp(&delegation->stateid.stateid.other, + &stateid->stateid.other, + NFS4_STATEID_OTHER_SIZE)) return 0; return 1; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index a882785eba41..0870d0d4efc0 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -48,6 +48,7 @@ #include "iostat.h" #include "internal.h" #include "fscache.h" +#include "pnfs.h" #define NFSDBG_FACILITY NFSDBG_CLIENT @@ -155,7 +156,9 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_ cred = rpc_lookup_machine_cred(); if (!IS_ERR(cred)) clp->cl_machine_cred = cred; - +#if defined(CONFIG_NFS_V4_1) + INIT_LIST_HEAD(&clp->cl_layouts); +#endif nfs_fscache_get_client_cookie(clp); return clp; @@ -252,6 +255,7 @@ void nfs_put_client(struct nfs_client *clp) nfs_free_client(clp); } } +EXPORT_SYMBOL_GPL(nfs_put_client); #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) /* @@ -601,6 +605,7 @@ static int nfs_create_rpc_client(struct nfs_client *clp, { struct rpc_clnt *clnt = NULL; struct rpc_create_args args = { + .net = &init_net, .protocol = clp->cl_proto, .address = (struct sockaddr *)&clp->cl_addr, .addrsize = clp->cl_addrlen, @@ -900,6 +905,8 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo * if (server->wsize > NFS_MAX_FILE_IO_SIZE) server->wsize = NFS_MAX_FILE_IO_SIZE; server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + set_pnfs_layoutdriver(server, fsinfo->layouttype); + server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL); server->dtsize = nfs_block_size(fsinfo->dtpref, NULL); @@ -939,6 +946,7 @@ static int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, str } fsinfo.fattr = fattr; + fsinfo.layouttype = 0; error = clp->rpc_ops->fsinfo(server, mntfh, &fsinfo); if (error < 0) goto out_error; @@ -1021,6 +1029,7 @@ void nfs_free_server(struct nfs_server *server) { dprintk("--> nfs_free_server()\n"); + unset_pnfs_layoutdriver(server); spin_lock(&nfs_client_lock); list_del(&server->client_link); list_del(&server->master_link); diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 232a7eead33a..1fd62fc49be3 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -11,7 +11,6 @@ #include <linux/module.h> #include <linux/sched.h> #include <linux/slab.h> -#include <linux/smp_lock.h> #include <linux/spinlock.h> #include <linux/nfs4.h> diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 257e4052492e..f0a384e2ae63 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -34,6 +34,7 @@ #include <linux/mount.h> #include <linux/sched.h> #include <linux/vmalloc.h> +#include <linux/kmemleak.h> #include "delegation.h" #include "iostat.h" @@ -161,6 +162,7 @@ struct nfs_cache_array_entry { u64 cookie; u64 ino; struct qstr string; + unsigned char d_type; }; struct nfs_cache_array { @@ -170,8 +172,6 @@ struct nfs_cache_array { struct nfs_cache_array_entry array[0]; }; -#define MAX_READDIR_ARRAY ((PAGE_SIZE - sizeof(struct nfs_cache_array)) / sizeof(struct nfs_cache_array_entry)) - typedef __be32 * (*decode_dirent_t)(struct xdr_stream *, struct nfs_entry *, struct nfs_server *, int); typedef struct { struct file *file; @@ -194,9 +194,13 @@ typedef struct { static struct nfs_cache_array *nfs_readdir_get_array(struct page *page) { + void *ptr; if (page == NULL) return ERR_PTR(-EIO); - return (struct nfs_cache_array *)kmap(page); + ptr = kmap(page); + if (ptr == NULL) + return ERR_PTR(-ENOMEM); + return ptr; } static @@ -213,6 +217,9 @@ int nfs_readdir_clear_array(struct page *page, gfp_t mask) { struct nfs_cache_array *array = nfs_readdir_get_array(page); int i; + + if (IS_ERR(array)) + return PTR_ERR(array); for (i = 0; i < array->size; i++) kfree(array->array[i].string.name); nfs_readdir_release_array(page); @@ -231,6 +238,11 @@ int nfs_readdir_make_qstr(struct qstr *string, const char *name, unsigned int le string->name = kmemdup(name, len, GFP_KERNEL); if (string->name == NULL) return -ENOMEM; + /* + * Avoid a kmemleak false positive. The pointer to the name is stored + * in a page cache page which kmemleak does not scan. + */ + kmemleak_not_leak(string->name); string->hash = full_name_hash(name, len); return 0; } @@ -244,20 +256,24 @@ int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page) if (IS_ERR(array)) return PTR_ERR(array); - ret = -EIO; - if (array->size >= MAX_READDIR_ARRAY) - goto out; cache_entry = &array->array[array->size]; + + /* Check that this entry lies within the page bounds */ + ret = -ENOSPC; + if ((char *)&cache_entry[1] - (char *)page_address(page) > PAGE_SIZE) + goto out; + cache_entry->cookie = entry->prev_cookie; cache_entry->ino = entry->ino; + cache_entry->d_type = entry->d_type; ret = nfs_readdir_make_qstr(&cache_entry->string, entry->name, entry->len); if (ret) goto out; array->last_cookie = entry->cookie; + array->size++; if (entry->eof == 1) array->eof_index = array->size; - array->size++; out: nfs_readdir_release_array(page); return ret; @@ -272,7 +288,7 @@ int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descri if (diff < 0) goto out_eof; if (diff >= array->size) { - if (array->eof_index > 0) + if (array->eof_index >= 0) goto out_eof; desc->current_index += array->size; return -EAGAIN; @@ -281,8 +297,6 @@ int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descri index = (unsigned int)diff; *desc->dir_cookie = array->array[index].cookie; desc->cache_entry_index = index; - if (index == array->eof_index) - desc->eof = 1; return 0; out_eof: desc->eof = 1; @@ -296,17 +310,17 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des int status = -EAGAIN; for (i = 0; i < array->size; i++) { - if (i == array->eof_index) { - desc->eof = 1; - status = -EBADCOOKIE; - } if (array->array[i].cookie == *desc->dir_cookie) { desc->cache_entry_index = i; status = 0; - break; + goto out; } } - + if (i == array->eof_index) { + desc->eof = 1; + status = -EBADCOOKIE; + } +out: return status; } @@ -381,13 +395,9 @@ int xdr_decode(nfs_readdir_descriptor_t *desc, struct nfs_entry *entry, struct x static int nfs_same_file(struct dentry *dentry, struct nfs_entry *entry) { - struct nfs_inode *node; if (dentry->d_inode == NULL) goto different; - node = NFS_I(dentry->d_inode); - if (node->fh.size != entry->fh->size) - goto different; - if (strncmp(node->fh.data, entry->fh->data, node->fh.size) != 0) + if (nfs_compare_fh(entry->fh, NFS_FH(dentry->d_inode)) != 0) goto different; return 1; different: @@ -449,14 +459,15 @@ out: /* Perform conversion from xdr to cache array */ static -void nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *entry, +int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *entry, void *xdr_page, struct page *page, unsigned int buflen) { struct xdr_stream stream; struct xdr_buf buf; __be32 *ptr = xdr_page; - int status; struct nfs_cache_array *array; + unsigned int count = 0; + int status; buf.head->iov_base = xdr_page; buf.head->iov_len = buflen; @@ -471,21 +482,32 @@ void nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *e do { status = xdr_decode(desc, entry, &stream); - if (status != 0) + if (status != 0) { + if (status == -EAGAIN) + status = 0; break; + } + + count++; - if (nfs_readdir_add_to_array(entry, page) == -1) - break; if (desc->plus == 1) nfs_prime_dcache(desc->file->f_path.dentry, entry); + + status = nfs_readdir_add_to_array(entry, page); + if (status != 0) + break; } while (!entry->eof); - if (status == -EBADCOOKIE && entry->eof) { + if (count == 0 || (status == -EBADCOOKIE && entry->eof == 1)) { array = nfs_readdir_get_array(page); - array->eof_index = array->size - 1; - status = 0; - nfs_readdir_release_array(page); + if (!IS_ERR(array)) { + array->eof_index = array->size; + status = 0; + nfs_readdir_release_array(page); + } else + status = PTR_ERR(array); } + return status; } static @@ -537,7 +559,7 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page, struct nfs_entry entry; struct file *file = desc->file; struct nfs_cache_array *array; - int status = 0; + int status = -ENOMEM; unsigned int array_size = ARRAY_SIZE(pages); entry.prev_cookie = 0; @@ -549,6 +571,10 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page, goto out; array = nfs_readdir_get_array(page); + if (IS_ERR(array)) { + status = PTR_ERR(array); + goto out; + } memset(array, 0, sizeof(struct nfs_cache_array)); array->eof_index = -1; @@ -556,12 +582,19 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page, if (!pages_ptr) goto out_release_array; do { + unsigned int pglen; status = nfs_readdir_xdr_filler(pages, desc, &entry, file, inode); if (status < 0) break; - nfs_readdir_page_filler(desc, &entry, pages_ptr, page, array_size * PAGE_SIZE); - } while (array->eof_index < 0 && array->size < MAX_READDIR_ARRAY); + pglen = status; + status = nfs_readdir_page_filler(desc, &entry, pages_ptr, page, pglen); + if (status < 0) { + if (status == -ENOSPC) + status = 0; + break; + } + } while (array->eof_index < 0); nfs_readdir_free_large_page(pages_ptr, pages, array_size); out_release_array: @@ -582,8 +615,10 @@ static int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page) { struct inode *inode = desc->file->f_path.dentry->d_inode; + int ret; - if (nfs_readdir_xdr_to_array(desc, page, inode) < 0) + ret = nfs_readdir_xdr_to_array(desc, page, inode); + if (ret < 0) goto error; SetPageUptodate(page); @@ -595,7 +630,7 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page) return 0; error: unlock_page(page); - return -EIO; + return ret; } static @@ -608,12 +643,8 @@ void cache_page_release(nfs_readdir_descriptor_t *desc) static struct page *get_cache_page(nfs_readdir_descriptor_t *desc) { - struct page *page; - page = read_cache_page(desc->file->f_path.dentry->d_inode->i_mapping, + return read_cache_page(desc->file->f_path.dentry->d_inode->i_mapping, desc->page_index, (filler_t *)nfs_readdir_filler, desc); - if (IS_ERR(page)) - desc->eof = 1; - return page; } /* @@ -639,8 +670,10 @@ int find_cache_page(nfs_readdir_descriptor_t *desc) static inline int readdir_search_pagecache(nfs_readdir_descriptor_t *desc) { - int res = -EAGAIN; + int res; + if (desc->page_index == 0) + desc->current_index = 0; while (1) { res = find_cache_page(desc); if (res != -EAGAIN) @@ -666,35 +699,36 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc, void *dirent, int i = 0; int res = 0; struct nfs_cache_array *array = NULL; - unsigned int d_type = DT_UNKNOWN; - struct dentry *dentry = NULL; array = nfs_readdir_get_array(desc->page); + if (IS_ERR(array)) { + res = PTR_ERR(array); + goto out; + } for (i = desc->cache_entry_index; i < array->size; i++) { - d_type = DT_UNKNOWN; + struct nfs_cache_array_entry *ent; - res = filldir(dirent, array->array[i].string.name, - array->array[i].string.len, file->f_pos, - nfs_compat_user_ino64(array->array[i].ino), d_type); - if (res < 0) + ent = &array->array[i]; + if (filldir(dirent, ent->string.name, ent->string.len, + file->f_pos, nfs_compat_user_ino64(ent->ino), + ent->d_type) < 0) { + desc->eof = 1; break; + } file->f_pos++; desc->cache_entry_index = i; if (i < (array->size-1)) *desc->dir_cookie = array->array[i+1].cookie; else *desc->dir_cookie = array->last_cookie; - if (i == array->eof_index) { - desc->eof = 1; - break; - } } + if (i == array->eof_index) + desc->eof = 1; nfs_readdir_release_array(desc->page); +out: cache_page_release(desc); - if (dentry != NULL) - dput(dentry); dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %Lu; returning = %d\n", (unsigned long long)*desc->dir_cookie, res); return res; @@ -729,13 +763,13 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent, goto out; } - if (nfs_readdir_xdr_to_array(desc, page, inode) == -1) { - status = -EIO; - goto out_release; - } - desc->page_index = 0; desc->page = page; + + status = nfs_readdir_xdr_to_array(desc, page, inode); + if (status < 0) + goto out_release; + status = nfs_do_filldir(desc, dirent, filldir); out: @@ -786,14 +820,14 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir) res = readdir_search_pagecache(desc); if (res == -EBADCOOKIE) { + res = 0; /* This means either end of directory */ if (*desc->dir_cookie && desc->eof == 0) { /* Or that the server has 'lost' a cookie */ res = uncached_readdir(desc, dirent, filldir); - if (res >= 0) + if (res == 0) continue; } - res = 0; break; } if (res == -ETOOSMALL && desc->plus) { @@ -808,10 +842,8 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir) break; res = nfs_do_filldir(desc, dirent, filldir); - if (res < 0) { - res = 0; + if (res < 0) break; - } } out: nfs_unblock_sillyrename(dentry); @@ -1345,12 +1377,12 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry res = NULL; goto out; /* This turned out not to be a regular file */ - case -EISDIR: case -ENOTDIR: goto no_open; case -ELOOP: if (!(nd->intent.open.flags & O_NOFOLLOW)) goto no_open; + /* case -EISDIR: */ /* case -EINVAL: */ default: res = ERR_CAST(inode); @@ -1801,7 +1833,7 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) d_drop(dentry); error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name); if (error == 0) { - atomic_inc(&inode->i_count); + ihold(inode); d_add(dentry, inode); } return error; diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 064a80961677..e6ace0d93c71 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -867,13 +867,13 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov, goto out; nfs_alloc_commit_data(dreq); - if (dreq->commit_data == NULL || count < wsize) + if (dreq->commit_data == NULL || count <= wsize) sync = NFS_FILE_SYNC; dreq->inode = inode; dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp)); dreq->l_ctx = nfs_get_lock_context(dreq->ctx); - if (dreq->l_ctx != NULL) + if (dreq->l_ctx == NULL) goto out_release; if (!is_sync_kiocb(iocb)) dreq->iocb = iocb; diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c index dba50a5625db..a6e711ad130f 100644 --- a/fs/nfs/dns_resolve.c +++ b/fs/nfs/dns_resolve.c @@ -167,7 +167,7 @@ static int nfs_dns_show(struct seq_file *m, struct cache_detail *cd, return 0; } item = container_of(h, struct nfs_dns_ent, h); - ttl = (long)item->h.expiry_time - (long)get_seconds(); + ttl = item->h.expiry_time - seconds_since_boot(); if (ttl < 0) ttl = 0; @@ -239,7 +239,7 @@ static int nfs_dns_parse(struct cache_detail *cd, char *buf, int buflen) ttl = get_expiry(&buf); if (ttl == 0) goto out; - key.h.expiry_time = ttl + get_seconds(); + key.h.expiry_time = ttl + seconds_since_boot(); ret = -ENOMEM; item = nfs_dns_lookup(cd, &key); @@ -301,7 +301,7 @@ static int do_cache_lookup_nowait(struct cache_detail *cd, goto out_err; ret = -ETIMEDOUT; if (!test_bit(CACHE_VALID, &(*item)->h.flags) - || (*item)->h.expiry_time < get_seconds() + || (*item)->h.expiry_time < seconds_since_boot() || cd->flush_time > (*item)->h.last_refresh) goto out_put; ret = -ENOENT; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index e18c31e08a28..60677f9f1311 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -36,6 +36,7 @@ #include "internal.h" #include "iostat.h" #include "fscache.h" +#include "pnfs.h" #define NFSDBG_FACILITY NFSDBG_FILE @@ -386,6 +387,10 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping, file->f_path.dentry->d_name.name, mapping->host->i_ino, len, (long long) pos); + pnfs_update_layout(mapping->host, + nfs_file_open_context(file), + IOMODE_RW); + start: /* * Prevent starvation issues if someone is doing a consistency @@ -879,6 +884,5 @@ static int nfs_setlease(struct file *file, long arg, struct file_lock **fl) dprintk("NFS: setlease(%s/%s, arg=%ld)\n", file->f_path.dentry->d_parent->d_name.name, file->f_path.dentry->d_name.name, arg); - return -EINVAL; } diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index a70e446e1605..ac7b814ce162 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -54,8 +54,7 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i iput(inode); return -ENOMEM; } - /* Circumvent igrab(): we know the inode is not being freed */ - atomic_inc(&inode->i_count); + ihold(inode); /* * Ensure that this dentry is invisible to d_find_alias(). * Otherwise, it may be spliced into the tree by diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index dec47ed8b6b9..4e2d9b6b1380 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -123,7 +123,7 @@ static ssize_t nfs_idmap_get_desc(const char *name, size_t namelen, size_t desclen = typelen + namelen + 2; *desc = kmalloc(desclen, GFP_KERNEL); - if (!desc) + if (!*desc) return -ENOMEM; cp = *desc; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 6eec28656415..314f57164602 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -48,6 +48,7 @@ #include "internal.h" #include "fscache.h" #include "dns_resolve.h" +#include "pnfs.h" #define NFSDBG_FACILITY NFSDBG_VFS @@ -1410,6 +1411,7 @@ void nfs4_evict_inode(struct inode *inode) { truncate_inode_pages(&inode->i_data, 0); end_writeback(inode); + pnfs_destroy_layout(NFS_I(inode)); /* If we are holding a delegation, return it! */ nfs_inode_return_delegation_noreclaim(inode); /* First call standard NFS clear_inode() code */ @@ -1447,6 +1449,7 @@ static inline void nfs4_init_once(struct nfs_inode *nfsi) nfsi->delegation = NULL; nfsi->delegation_state = 0; init_rwsem(&nfsi->rwsem); + nfsi->layout = NULL; #endif } diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index db08ff3ff454..e6356b750b77 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -362,6 +362,15 @@ unsigned int nfs_page_length(struct page *page) } /* + * Convert a umode to a dirent->d_type + */ +static inline +unsigned char nfs_umode_to_dtype(umode_t mode) +{ + return (mode >> 12) & 15; +} + +/* * Determine the number of pages in an array of length 'len' and * with a base offset of 'base' */ diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index d610203d95c6..eceafe74f473 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -153,6 +153,7 @@ int nfs_mount(struct nfs_mount_request *info) .rpc_resp = &result, }; struct rpc_create_args args = { + .net = &init_net, .protocol = info->protocol, .address = info->sap, .addrsize = info->salen, @@ -224,6 +225,7 @@ void nfs_umount(const struct nfs_mount_request *info) .to_retries = 2, }; struct rpc_create_args args = { + .net = &init_net, .protocol = IPPROTO_UDP, .address = info->sap, .addrsize = info->salen, diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index e6bf45710cc7..5914a1911c95 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -423,7 +423,7 @@ nfs_xdr_readdirres(struct rpc_rqst *req, __be32 *p, void *dummy) struct page **page; size_t hdrlen; unsigned int pglen, recvd; - int status, nr = 0; + int status; if ((status = ntohl(*p++))) return nfs_stat_to_errno(status); @@ -443,7 +443,7 @@ nfs_xdr_readdirres(struct rpc_rqst *req, __be32 *p, void *dummy) if (pglen > recvd) pglen = recvd; page = rcvbuf->pages; - return nr; + return pglen; } static void print_overflow_msg(const char *func, const struct xdr_stream *xdr) @@ -485,6 +485,8 @@ nfs_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, struct nfs_se entry->prev_cookie = entry->cookie; entry->cookie = ntohl(*p++); + entry->d_type = DT_UNKNOWN; + p = xdr_inline_peek(xdr, 8); if (p != NULL) entry->eof = !p[0] && p[1]; @@ -495,7 +497,7 @@ nfs_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, struct nfs_se out_overflow: print_overflow_msg(__func__, xdr); - return ERR_PTR(-EIO); + return ERR_PTR(-EAGAIN); } /* diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index d9a5e832c257..f6cc60f06dac 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -555,7 +555,7 @@ nfs3_xdr_readdirres(struct rpc_rqst *req, __be32 *p, struct nfs3_readdirres *res struct page **page; size_t hdrlen; u32 recvd, pglen; - int status, nr = 0; + int status; status = ntohl(*p++); /* Decode post_op_attrs */ @@ -586,7 +586,7 @@ nfs3_xdr_readdirres(struct rpc_rqst *req, __be32 *p, struct nfs3_readdirres *res pglen = recvd; page = rcvbuf->pages; - return nr; + return pglen; } __be32 * @@ -622,11 +622,13 @@ nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, struct nfs_s entry->prev_cookie = entry->cookie; p = xdr_decode_hyper(p, &entry->cookie); + entry->d_type = DT_UNKNOWN; if (plus) { entry->fattr->valid = 0; p = xdr_decode_post_op_attr_stream(xdr, entry->fattr); if (IS_ERR(p)) goto out_overflow_exit; + entry->d_type = nfs_umode_to_dtype(entry->fattr->mode); /* In fact, a post_op_fh3: */ p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) @@ -656,7 +658,7 @@ nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, struct nfs_s out_overflow: print_overflow_msg(__func__, xdr); out_overflow_exit: - return ERR_PTR(-EIO); + return ERR_PTR(-EAGAIN); } /* diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c new file mode 100644 index 000000000000..2e92f0d8d654 --- /dev/null +++ b/fs/nfs/nfs4filelayout.c @@ -0,0 +1,280 @@ +/* + * Module for the pnfs nfs4 file layout driver. + * Defines all I/O and Policy interface operations, plus code + * to register itself with the pNFS client. + * + * Copyright (c) 2002 + * The Regents of the University of Michigan + * All Rights Reserved + * + * Dean Hildebrand <dhildebz@umich.edu> + * + * Permission is granted to use, copy, create derivative works, and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the University of Michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. If + * the above copyright notice or any other identification of the + * University of Michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * This software is provided as is, without representation or warranty + * of any kind either express or implied, including without limitation + * the implied warranties of merchantability, fitness for a particular + * purpose, or noninfringement. The Regents of the University of + * Michigan shall not be liable for any damages, including special, + * indirect, incidental, or consequential damages, with respect to any + * claim arising out of or in connection with the use of the software, + * even if it has been or is hereafter advised of the possibility of + * such damages. + */ + +#include <linux/nfs_fs.h> + +#include "internal.h" +#include "nfs4filelayout.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Dean Hildebrand <dhildebz@umich.edu>"); +MODULE_DESCRIPTION("The NFSv4 file layout driver"); + +static int +filelayout_set_layoutdriver(struct nfs_server *nfss) +{ + int status = pnfs_alloc_init_deviceid_cache(nfss->nfs_client, + nfs4_fl_free_deviceid_callback); + if (status) { + printk(KERN_WARNING "%s: deviceid cache could not be " + "initialized\n", __func__); + return status; + } + dprintk("%s: deviceid cache has been initialized successfully\n", + __func__); + return 0; +} + +/* Clear out the layout by destroying its device list */ +static int +filelayout_clear_layoutdriver(struct nfs_server *nfss) +{ + dprintk("--> %s\n", __func__); + + if (nfss->nfs_client->cl_devid_cache) + pnfs_put_deviceid_cache(nfss->nfs_client); + return 0; +} + +/* + * filelayout_check_layout() + * + * Make sure layout segment parameters are sane WRT the device. + * At this point no generic layer initialization of the lseg has occurred, + * and nothing has been added to the layout_hdr cache. + * + */ +static int +filelayout_check_layout(struct pnfs_layout_hdr *lo, + struct nfs4_filelayout_segment *fl, + struct nfs4_layoutget_res *lgr, + struct nfs4_deviceid *id) +{ + struct nfs4_file_layout_dsaddr *dsaddr; + int status = -EINVAL; + struct nfs_server *nfss = NFS_SERVER(lo->inode); + + dprintk("--> %s\n", __func__); + + if (fl->pattern_offset > lgr->range.offset) { + dprintk("%s pattern_offset %lld to large\n", + __func__, fl->pattern_offset); + goto out; + } + + if (fl->stripe_unit % PAGE_SIZE) { + dprintk("%s Stripe unit (%u) not page aligned\n", + __func__, fl->stripe_unit); + goto out; + } + + /* find and reference the deviceid */ + dsaddr = nfs4_fl_find_get_deviceid(nfss->nfs_client, id); + if (dsaddr == NULL) { + dsaddr = get_device_info(lo->inode, id); + if (dsaddr == NULL) + goto out; + } + fl->dsaddr = dsaddr; + + if (fl->first_stripe_index < 0 || + fl->first_stripe_index >= dsaddr->stripe_count) { + dprintk("%s Bad first_stripe_index %d\n", + __func__, fl->first_stripe_index); + goto out_put; + } + + if ((fl->stripe_type == STRIPE_SPARSE && + fl->num_fh > 1 && fl->num_fh != dsaddr->ds_num) || + (fl->stripe_type == STRIPE_DENSE && + fl->num_fh != dsaddr->stripe_count)) { + dprintk("%s num_fh %u not valid for given packing\n", + __func__, fl->num_fh); + goto out_put; + } + + if (fl->stripe_unit % nfss->rsize || fl->stripe_unit % nfss->wsize) { + dprintk("%s Stripe unit (%u) not aligned with rsize %u " + "wsize %u\n", __func__, fl->stripe_unit, nfss->rsize, + nfss->wsize); + } + + status = 0; +out: + dprintk("--> %s returns %d\n", __func__, status); + return status; +out_put: + pnfs_put_deviceid(nfss->nfs_client->cl_devid_cache, &dsaddr->deviceid); + goto out; +} + +static void filelayout_free_fh_array(struct nfs4_filelayout_segment *fl) +{ + int i; + + for (i = 0; i < fl->num_fh; i++) { + if (!fl->fh_array[i]) + break; + kfree(fl->fh_array[i]); + } + kfree(fl->fh_array); + fl->fh_array = NULL; +} + +static void +_filelayout_free_lseg(struct nfs4_filelayout_segment *fl) +{ + filelayout_free_fh_array(fl); + kfree(fl); +} + +static int +filelayout_decode_layout(struct pnfs_layout_hdr *flo, + struct nfs4_filelayout_segment *fl, + struct nfs4_layoutget_res *lgr, + struct nfs4_deviceid *id) +{ + uint32_t *p = (uint32_t *)lgr->layout.buf; + uint32_t nfl_util; + int i; + + dprintk("%s: set_layout_map Begin\n", __func__); + + memcpy(id, p, sizeof(*id)); + p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE); + print_deviceid(id); + + nfl_util = be32_to_cpup(p++); + if (nfl_util & NFL4_UFLG_COMMIT_THRU_MDS) + fl->commit_through_mds = 1; + if (nfl_util & NFL4_UFLG_DENSE) + fl->stripe_type = STRIPE_DENSE; + else + fl->stripe_type = STRIPE_SPARSE; + fl->stripe_unit = nfl_util & ~NFL4_UFLG_MASK; + + fl->first_stripe_index = be32_to_cpup(p++); + p = xdr_decode_hyper(p, &fl->pattern_offset); + fl->num_fh = be32_to_cpup(p++); + + dprintk("%s: nfl_util 0x%X num_fh %u fsi %u po %llu\n", + __func__, nfl_util, fl->num_fh, fl->first_stripe_index, + fl->pattern_offset); + + fl->fh_array = kzalloc(fl->num_fh * sizeof(struct nfs_fh *), + GFP_KERNEL); + if (!fl->fh_array) + return -ENOMEM; + + for (i = 0; i < fl->num_fh; i++) { + /* Do we want to use a mempool here? */ + fl->fh_array[i] = kmalloc(sizeof(struct nfs_fh), GFP_KERNEL); + if (!fl->fh_array[i]) { + filelayout_free_fh_array(fl); + return -ENOMEM; + } + fl->fh_array[i]->size = be32_to_cpup(p++); + if (sizeof(struct nfs_fh) < fl->fh_array[i]->size) { + printk(KERN_ERR "Too big fh %d received %d\n", + i, fl->fh_array[i]->size); + filelayout_free_fh_array(fl); + return -EIO; + } + memcpy(fl->fh_array[i]->data, p, fl->fh_array[i]->size); + p += XDR_QUADLEN(fl->fh_array[i]->size); + dprintk("DEBUG: %s: fh len %d\n", __func__, + fl->fh_array[i]->size); + } + + return 0; +} + +static struct pnfs_layout_segment * +filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid, + struct nfs4_layoutget_res *lgr) +{ + struct nfs4_filelayout_segment *fl; + int rc; + struct nfs4_deviceid id; + + dprintk("--> %s\n", __func__); + fl = kzalloc(sizeof(*fl), GFP_KERNEL); + if (!fl) + return NULL; + + rc = filelayout_decode_layout(layoutid, fl, lgr, &id); + if (rc != 0 || filelayout_check_layout(layoutid, fl, lgr, &id)) { + _filelayout_free_lseg(fl); + return NULL; + } + return &fl->generic_hdr; +} + +static void +filelayout_free_lseg(struct pnfs_layout_segment *lseg) +{ + struct nfs_server *nfss = NFS_SERVER(lseg->layout->inode); + struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg); + + dprintk("--> %s\n", __func__); + pnfs_put_deviceid(nfss->nfs_client->cl_devid_cache, + &fl->dsaddr->deviceid); + _filelayout_free_lseg(fl); +} + +static struct pnfs_layoutdriver_type filelayout_type = { + .id = LAYOUT_NFSV4_1_FILES, + .name = "LAYOUT_NFSV4_1_FILES", + .owner = THIS_MODULE, + .set_layoutdriver = filelayout_set_layoutdriver, + .clear_layoutdriver = filelayout_clear_layoutdriver, + .alloc_lseg = filelayout_alloc_lseg, + .free_lseg = filelayout_free_lseg, +}; + +static int __init nfs4filelayout_init(void) +{ + printk(KERN_INFO "%s: NFSv4 File Layout Driver Registering...\n", + __func__); + return pnfs_register_layoutdriver(&filelayout_type); +} + +static void __exit nfs4filelayout_exit(void) +{ + printk(KERN_INFO "%s: NFSv4 File Layout Driver Unregistering...\n", + __func__); + pnfs_unregister_layoutdriver(&filelayout_type); +} + +module_init(nfs4filelayout_init); +module_exit(nfs4filelayout_exit); diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h new file mode 100644 index 000000000000..bbf60dd2ab9d --- /dev/null +++ b/fs/nfs/nfs4filelayout.h @@ -0,0 +1,94 @@ +/* + * NFSv4 file layout driver data structures. + * + * Copyright (c) 2002 + * The Regents of the University of Michigan + * All Rights Reserved + * + * Dean Hildebrand <dhildebz@umich.edu> + * + * Permission is granted to use, copy, create derivative works, and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the University of Michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. If + * the above copyright notice or any other identification of the + * University of Michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * This software is provided as is, without representation or warranty + * of any kind either express or implied, including without limitation + * the implied warranties of merchantability, fitness for a particular + * purpose, or noninfringement. The Regents of the University of + * Michigan shall not be liable for any damages, including special, + * indirect, incidental, or consequential damages, with respect to any + * claim arising out of or in connection with the use of the software, + * even if it has been or is hereafter advised of the possibility of + * such damages. + */ + +#ifndef FS_NFS_NFS4FILELAYOUT_H +#define FS_NFS_NFS4FILELAYOUT_H + +#include "pnfs.h" + +/* + * Field testing shows we need to support upto 4096 stripe indices. + * We store each index as a u8 (u32 on the wire) to keep the memory footprint + * reasonable. This in turn means we support a maximum of 256 + * RFC 5661 multipath_list4 structures. + */ +#define NFS4_PNFS_MAX_STRIPE_CNT 4096 +#define NFS4_PNFS_MAX_MULTI_CNT 256 /* 256 fit into a u8 stripe_index */ + +enum stripetype4 { + STRIPE_SPARSE = 1, + STRIPE_DENSE = 2 +}; + +/* Individual ip address */ +struct nfs4_pnfs_ds { + struct list_head ds_node; /* nfs4_pnfs_dev_hlist dev_dslist */ + u32 ds_ip_addr; + u32 ds_port; + struct nfs_client *ds_clp; + atomic_t ds_count; +}; + +struct nfs4_file_layout_dsaddr { + struct pnfs_deviceid_node deviceid; + u32 stripe_count; + u8 *stripe_indices; + u32 ds_num; + struct nfs4_pnfs_ds *ds_list[1]; +}; + +struct nfs4_filelayout_segment { + struct pnfs_layout_segment generic_hdr; + u32 stripe_type; + u32 commit_through_mds; + u32 stripe_unit; + u32 first_stripe_index; + u64 pattern_offset; + struct nfs4_file_layout_dsaddr *dsaddr; /* Point to GETDEVINFO data */ + unsigned int num_fh; + struct nfs_fh **fh_array; +}; + +static inline struct nfs4_filelayout_segment * +FILELAYOUT_LSEG(struct pnfs_layout_segment *lseg) +{ + return container_of(lseg, + struct nfs4_filelayout_segment, + generic_hdr); +} + +extern void nfs4_fl_free_deviceid_callback(struct pnfs_deviceid_node *); +extern void print_ds(struct nfs4_pnfs_ds *ds); +extern void print_deviceid(struct nfs4_deviceid *dev_id); +extern struct nfs4_file_layout_dsaddr * +nfs4_fl_find_get_deviceid(struct nfs_client *, struct nfs4_deviceid *dev_id); +struct nfs4_file_layout_dsaddr * +get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id); + +#endif /* FS_NFS_NFS4FILELAYOUT_H */ diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c new file mode 100644 index 000000000000..51fe64ace55a --- /dev/null +++ b/fs/nfs/nfs4filelayoutdev.c @@ -0,0 +1,448 @@ +/* + * Device operations for the pnfs nfs4 file layout driver. + * + * Copyright (c) 2002 + * The Regents of the University of Michigan + * All Rights Reserved + * + * Dean Hildebrand <dhildebz@umich.edu> + * Garth Goodson <Garth.Goodson@netapp.com> + * + * Permission is granted to use, copy, create derivative works, and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the University of Michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. If + * the above copyright notice or any other identification of the + * University of Michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * This software is provided as is, without representation or warranty + * of any kind either express or implied, including without limitation + * the implied warranties of merchantability, fitness for a particular + * purpose, or noninfringement. The Regents of the University of + * Michigan shall not be liable for any damages, including special, + * indirect, incidental, or consequential damages, with respect to any + * claim arising out of or in connection with the use of the software, + * even if it has been or is hereafter advised of the possibility of + * such damages. + */ + +#include <linux/nfs_fs.h> +#include <linux/vmalloc.h> + +#include "internal.h" +#include "nfs4filelayout.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +/* + * Data server cache + * + * Data servers can be mapped to different device ids. + * nfs4_pnfs_ds reference counting + * - set to 1 on allocation + * - incremented when a device id maps a data server already in the cache. + * - decremented when deviceid is removed from the cache. + */ +DEFINE_SPINLOCK(nfs4_ds_cache_lock); +static LIST_HEAD(nfs4_data_server_cache); + +/* Debug routines */ +void +print_ds(struct nfs4_pnfs_ds *ds) +{ + if (ds == NULL) { + printk("%s NULL device\n", __func__); + return; + } + printk(" ip_addr %x port %hu\n" + " ref count %d\n" + " client %p\n" + " cl_exchange_flags %x\n", + ntohl(ds->ds_ip_addr), ntohs(ds->ds_port), + atomic_read(&ds->ds_count), ds->ds_clp, + ds->ds_clp ? ds->ds_clp->cl_exchange_flags : 0); +} + +void +print_ds_list(struct nfs4_file_layout_dsaddr *dsaddr) +{ + int i; + + ifdebug(FACILITY) { + printk("%s dsaddr->ds_num %d\n", __func__, + dsaddr->ds_num); + for (i = 0; i < dsaddr->ds_num; i++) + print_ds(dsaddr->ds_list[i]); + } +} + +void print_deviceid(struct nfs4_deviceid *id) +{ + u32 *p = (u32 *)id; + + dprintk("%s: device id= [%x%x%x%x]\n", __func__, + p[0], p[1], p[2], p[3]); +} + +/* nfs4_ds_cache_lock is held */ +static struct nfs4_pnfs_ds * +_data_server_lookup_locked(u32 ip_addr, u32 port) +{ + struct nfs4_pnfs_ds *ds; + + dprintk("_data_server_lookup: ip_addr=%x port=%hu\n", + ntohl(ip_addr), ntohs(port)); + + list_for_each_entry(ds, &nfs4_data_server_cache, ds_node) { + if (ds->ds_ip_addr == ip_addr && + ds->ds_port == port) { + return ds; + } + } + return NULL; +} + +static void +destroy_ds(struct nfs4_pnfs_ds *ds) +{ + dprintk("--> %s\n", __func__); + ifdebug(FACILITY) + print_ds(ds); + + if (ds->ds_clp) + nfs_put_client(ds->ds_clp); + kfree(ds); +} + +static void +nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr) +{ + struct nfs4_pnfs_ds *ds; + int i; + + print_deviceid(&dsaddr->deviceid.de_id); + + for (i = 0; i < dsaddr->ds_num; i++) { + ds = dsaddr->ds_list[i]; + if (ds != NULL) { + if (atomic_dec_and_lock(&ds->ds_count, + &nfs4_ds_cache_lock)) { + list_del_init(&ds->ds_node); + spin_unlock(&nfs4_ds_cache_lock); + destroy_ds(ds); + } + } + } + kfree(dsaddr->stripe_indices); + kfree(dsaddr); +} + +void +nfs4_fl_free_deviceid_callback(struct pnfs_deviceid_node *device) +{ + struct nfs4_file_layout_dsaddr *dsaddr = + container_of(device, struct nfs4_file_layout_dsaddr, deviceid); + + nfs4_fl_free_deviceid(dsaddr); +} + +static struct nfs4_pnfs_ds * +nfs4_pnfs_ds_add(struct inode *inode, u32 ip_addr, u32 port) +{ + struct nfs4_pnfs_ds *tmp_ds, *ds; + + ds = kzalloc(sizeof(*tmp_ds), GFP_KERNEL); + if (!ds) + goto out; + + spin_lock(&nfs4_ds_cache_lock); + tmp_ds = _data_server_lookup_locked(ip_addr, port); + if (tmp_ds == NULL) { + ds->ds_ip_addr = ip_addr; + ds->ds_port = port; + atomic_set(&ds->ds_count, 1); + INIT_LIST_HEAD(&ds->ds_node); + ds->ds_clp = NULL; + list_add(&ds->ds_node, &nfs4_data_server_cache); + dprintk("%s add new data server ip 0x%x\n", __func__, + ds->ds_ip_addr); + } else { + kfree(ds); + atomic_inc(&tmp_ds->ds_count); + dprintk("%s data server found ip 0x%x, inc'ed ds_count to %d\n", + __func__, tmp_ds->ds_ip_addr, + atomic_read(&tmp_ds->ds_count)); + ds = tmp_ds; + } + spin_unlock(&nfs4_ds_cache_lock); +out: + return ds; +} + +/* + * Currently only support ipv4, and one multi-path address. + */ +static struct nfs4_pnfs_ds * +decode_and_add_ds(__be32 **pp, struct inode *inode) +{ + struct nfs4_pnfs_ds *ds = NULL; + char *buf; + const char *ipend, *pstr; + u32 ip_addr, port; + int nlen, rlen, i; + int tmp[2]; + __be32 *r_netid, *r_addr, *p = *pp; + + /* r_netid */ + nlen = be32_to_cpup(p++); + r_netid = p; + p += XDR_QUADLEN(nlen); + + /* r_addr */ + rlen = be32_to_cpup(p++); + r_addr = p; + p += XDR_QUADLEN(rlen); + *pp = p; + + /* Check that netid is "tcp" */ + if (nlen != 3 || memcmp((char *)r_netid, "tcp", 3)) { + dprintk("%s: ERROR: non ipv4 TCP r_netid\n", __func__); + goto out_err; + } + + /* ipv6 length plus port is legal */ + if (rlen > INET6_ADDRSTRLEN + 8) { + dprintk("%s Invalid address, length %d\n", __func__, + rlen); + goto out_err; + } + buf = kmalloc(rlen + 1, GFP_KERNEL); + buf[rlen] = '\0'; + memcpy(buf, r_addr, rlen); + + /* replace the port dots with dashes for the in4_pton() delimiter*/ + for (i = 0; i < 2; i++) { + char *res = strrchr(buf, '.'); + *res = '-'; + } + + /* Currently only support ipv4 address */ + if (in4_pton(buf, rlen, (u8 *)&ip_addr, '-', &ipend) == 0) { + dprintk("%s: Only ipv4 addresses supported\n", __func__); + goto out_free; + } + + /* port */ + pstr = ipend; + sscanf(pstr, "-%d-%d", &tmp[0], &tmp[1]); + port = htons((tmp[0] << 8) | (tmp[1])); + + ds = nfs4_pnfs_ds_add(inode, ip_addr, port); + dprintk("%s Decoded address and port %s\n", __func__, buf); +out_free: + kfree(buf); +out_err: + return ds; +} + +/* Decode opaque device data and return the result */ +static struct nfs4_file_layout_dsaddr* +decode_device(struct inode *ino, struct pnfs_device *pdev) +{ + int i, dummy; + u32 cnt, num; + u8 *indexp; + __be32 *p = (__be32 *)pdev->area, *indicesp; + struct nfs4_file_layout_dsaddr *dsaddr; + + /* Get the stripe count (number of stripe index) */ + cnt = be32_to_cpup(p++); + dprintk("%s stripe count %d\n", __func__, cnt); + if (cnt > NFS4_PNFS_MAX_STRIPE_CNT) { + printk(KERN_WARNING "%s: stripe count %d greater than " + "supported maximum %d\n", __func__, + cnt, NFS4_PNFS_MAX_STRIPE_CNT); + goto out_err; + } + + /* Check the multipath list count */ + indicesp = p; + p += XDR_QUADLEN(cnt << 2); + num = be32_to_cpup(p++); + dprintk("%s ds_num %u\n", __func__, num); + if (num > NFS4_PNFS_MAX_MULTI_CNT) { + printk(KERN_WARNING "%s: multipath count %d greater than " + "supported maximum %d\n", __func__, + num, NFS4_PNFS_MAX_MULTI_CNT); + goto out_err; + } + dsaddr = kzalloc(sizeof(*dsaddr) + + (sizeof(struct nfs4_pnfs_ds *) * (num - 1)), + GFP_KERNEL); + if (!dsaddr) + goto out_err; + + dsaddr->stripe_indices = kzalloc(sizeof(u8) * cnt, GFP_KERNEL); + if (!dsaddr->stripe_indices) + goto out_err_free; + + dsaddr->stripe_count = cnt; + dsaddr->ds_num = num; + + memcpy(&dsaddr->deviceid.de_id, &pdev->dev_id, sizeof(pdev->dev_id)); + + /* Go back an read stripe indices */ + p = indicesp; + indexp = &dsaddr->stripe_indices[0]; + for (i = 0; i < dsaddr->stripe_count; i++) { + *indexp = be32_to_cpup(p++); + if (*indexp >= num) + goto out_err_free; + indexp++; + } + /* Skip already read multipath list count */ + p++; + + for (i = 0; i < dsaddr->ds_num; i++) { + int j; + + dummy = be32_to_cpup(p++); /* multipath count */ + if (dummy > 1) { + printk(KERN_WARNING + "%s: Multipath count %d not supported, " + "skipping all greater than 1\n", __func__, + dummy); + } + for (j = 0; j < dummy; j++) { + if (j == 0) { + dsaddr->ds_list[i] = decode_and_add_ds(&p, ino); + if (dsaddr->ds_list[i] == NULL) + goto out_err_free; + } else { + u32 len; + /* skip extra multipath */ + len = be32_to_cpup(p++); + p += XDR_QUADLEN(len); + len = be32_to_cpup(p++); + p += XDR_QUADLEN(len); + continue; + } + } + } + return dsaddr; + +out_err_free: + nfs4_fl_free_deviceid(dsaddr); +out_err: + dprintk("%s ERROR: returning NULL\n", __func__); + return NULL; +} + +/* + * Decode the opaque device specified in 'dev' + * and add it to the list of available devices. + * If the deviceid is already cached, nfs4_add_deviceid will return + * a pointer to the cached struct and throw away the new. + */ +static struct nfs4_file_layout_dsaddr* +decode_and_add_device(struct inode *inode, struct pnfs_device *dev) +{ + struct nfs4_file_layout_dsaddr *dsaddr; + struct pnfs_deviceid_node *d; + + dsaddr = decode_device(inode, dev); + if (!dsaddr) { + printk(KERN_WARNING "%s: Could not decode or add device\n", + __func__); + return NULL; + } + + d = pnfs_add_deviceid(NFS_SERVER(inode)->nfs_client->cl_devid_cache, + &dsaddr->deviceid); + + return container_of(d, struct nfs4_file_layout_dsaddr, deviceid); +} + +/* + * Retrieve the information for dev_id, add it to the list + * of available devices, and return it. + */ +struct nfs4_file_layout_dsaddr * +get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id) +{ + struct pnfs_device *pdev = NULL; + u32 max_resp_sz; + int max_pages; + struct page **pages = NULL; + struct nfs4_file_layout_dsaddr *dsaddr = NULL; + int rc, i; + struct nfs_server *server = NFS_SERVER(inode); + + /* + * Use the session max response size as the basis for setting + * GETDEVICEINFO's maxcount + */ + max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; + max_pages = max_resp_sz >> PAGE_SHIFT; + dprintk("%s inode %p max_resp_sz %u max_pages %d\n", + __func__, inode, max_resp_sz, max_pages); + + pdev = kzalloc(sizeof(struct pnfs_device), GFP_KERNEL); + if (pdev == NULL) + return NULL; + + pages = kzalloc(max_pages * sizeof(struct page *), GFP_KERNEL); + if (pages == NULL) { + kfree(pdev); + return NULL; + } + for (i = 0; i < max_pages; i++) { + pages[i] = alloc_page(GFP_KERNEL); + if (!pages[i]) + goto out_free; + } + + /* set pdev->area */ + pdev->area = vmap(pages, max_pages, VM_MAP, PAGE_KERNEL); + if (!pdev->area) + goto out_free; + + memcpy(&pdev->dev_id, dev_id, sizeof(*dev_id)); + pdev->layout_type = LAYOUT_NFSV4_1_FILES; + pdev->pages = pages; + pdev->pgbase = 0; + pdev->pglen = PAGE_SIZE * max_pages; + pdev->mincount = 0; + + rc = nfs4_proc_getdeviceinfo(server, pdev); + dprintk("%s getdevice info returns %d\n", __func__, rc); + if (rc) + goto out_free; + + /* + * Found new device, need to decode it and then add it to the + * list of known devices for this mountpoint. + */ + dsaddr = decode_and_add_device(inode, pdev); +out_free: + if (pdev->area != NULL) + vunmap(pdev->area); + for (i = 0; i < max_pages; i++) + __free_page(pages[i]); + kfree(pages); + kfree(pdev); + dprintk("<-- %s dsaddr %p\n", __func__, dsaddr); + return dsaddr; +} + +struct nfs4_file_layout_dsaddr * +nfs4_fl_find_get_deviceid(struct nfs_client *clp, struct nfs4_deviceid *id) +{ + struct pnfs_deviceid_node *d; + + d = pnfs_find_get_deviceid(clp->cl_devid_cache, id); + return (d == NULL) ? NULL : + container_of(d, struct nfs4_file_layout_dsaddr, deviceid); +} diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index e87fe612ca18..6a653ffd8e4e 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -55,6 +55,7 @@ #include "internal.h" #include "iostat.h" #include "callback.h" +#include "pnfs.h" #define NFSDBG_FACILITY NFSDBG_PROC @@ -130,6 +131,7 @@ const u32 nfs4_fsinfo_bitmap[2] = { FATTR4_WORD0_MAXFILESIZE | FATTR4_WORD0_MAXWRITE | FATTR4_WORD0_LEASE_TIME, FATTR4_WORD1_TIME_DELTA + | FATTR4_WORD1_FS_LAYOUT_TYPES }; const u32 nfs4_fs_locations_bitmap[2] = { @@ -427,7 +429,7 @@ static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res * * returned NFS4ERR_DELAY as per Section 2.10.6.2 * of RFC5661. */ - dprintk("%s: slot=%ld seq=%d: Operation in progress\n", + dprintk("%s: slot=%td seq=%d: Operation in progress\n", __func__, res->sr_slot - res->sr_session->fc_slot_table.slots, res->sr_slot->seq_nr); @@ -571,7 +573,7 @@ int nfs4_setup_sequence(const struct nfs_server *server, goto out; } - dprintk("--> %s clp %p session %p sr_slot %ld\n", + dprintk("--> %s clp %p session %p sr_slot %td\n", __func__, session->clp, session, res->sr_slot ? res->sr_slot - session->fc_slot_table.slots : -1); @@ -2850,8 +2852,10 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, nfs4_setup_readdir(cookie, NFS_COOKIEVERF(dir), dentry, &args); res.pgbase = args.pgbase; status = nfs4_call_sync(NFS_SERVER(dir), &msg, &args, &res, 0); - if (status == 0) + if (status >= 0) { memcpy(NFS_COOKIEVERF(dir), res.verifier.data, NFS4_VERIFIER_SIZE); + status += args.pgbase; + } nfs_invalidate_atime(dir); @@ -4840,49 +4844,56 @@ static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args) args->bc_attrs.max_reqs); } -static int _verify_channel_attr(char *chan, char *attr_name, u32 sent, u32 rcvd) +static int nfs4_verify_fore_channel_attrs(struct nfs41_create_session_args *args, struct nfs4_session *session) { - if (rcvd <= sent) - return 0; - printk(KERN_WARNING "%s: Session INVALID: %s channel %s increased. " - "sent=%u rcvd=%u\n", __func__, chan, attr_name, sent, rcvd); - return -EINVAL; + struct nfs4_channel_attrs *sent = &args->fc_attrs; + struct nfs4_channel_attrs *rcvd = &session->fc_attrs; + + if (rcvd->headerpadsz > sent->headerpadsz) + return -EINVAL; + if (rcvd->max_resp_sz > sent->max_resp_sz) + return -EINVAL; + /* + * Our requested max_ops is the minimum we need; we're not + * prepared to break up compounds into smaller pieces than that. + * So, no point even trying to continue if the server won't + * cooperate: + */ + if (rcvd->max_ops < sent->max_ops) + return -EINVAL; + if (rcvd->max_reqs == 0) + return -EINVAL; + return 0; } -#define _verify_fore_channel_attr(_name_) \ - _verify_channel_attr("fore", #_name_, \ - args->fc_attrs._name_, \ - session->fc_attrs._name_) +static int nfs4_verify_back_channel_attrs(struct nfs41_create_session_args *args, struct nfs4_session *session) +{ + struct nfs4_channel_attrs *sent = &args->bc_attrs; + struct nfs4_channel_attrs *rcvd = &session->bc_attrs; -#define _verify_back_channel_attr(_name_) \ - _verify_channel_attr("back", #_name_, \ - args->bc_attrs._name_, \ - session->bc_attrs._name_) + if (rcvd->max_rqst_sz > sent->max_rqst_sz) + return -EINVAL; + if (rcvd->max_resp_sz < sent->max_resp_sz) + return -EINVAL; + if (rcvd->max_resp_sz_cached > sent->max_resp_sz_cached) + return -EINVAL; + /* These would render the backchannel useless: */ + if (rcvd->max_ops == 0) + return -EINVAL; + if (rcvd->max_reqs == 0) + return -EINVAL; + return 0; +} -/* - * The server is not allowed to increase the fore channel header pad size, - * maximum response size, or maximum number of operations. - * - * The back channel attributes are only negotiatied down: We send what the - * (back channel) server insists upon. - */ static int nfs4_verify_channel_attrs(struct nfs41_create_session_args *args, struct nfs4_session *session) { - int ret = 0; - - ret |= _verify_fore_channel_attr(headerpadsz); - ret |= _verify_fore_channel_attr(max_resp_sz); - ret |= _verify_fore_channel_attr(max_ops); - - ret |= _verify_back_channel_attr(headerpadsz); - ret |= _verify_back_channel_attr(max_rqst_sz); - ret |= _verify_back_channel_attr(max_resp_sz); - ret |= _verify_back_channel_attr(max_resp_sz_cached); - ret |= _verify_back_channel_attr(max_ops); - ret |= _verify_back_channel_attr(max_reqs); + int ret; - return ret; + ret = nfs4_verify_fore_channel_attrs(args, session); + if (ret) + return ret; + return nfs4_verify_back_channel_attrs(args, session); } static int _nfs4_proc_create_session(struct nfs_client *clp) @@ -5255,6 +5266,147 @@ out: dprintk("<-- %s status=%d\n", __func__, status); return status; } + +static void +nfs4_layoutget_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs4_layoutget *lgp = calldata; + struct inode *ino = lgp->args.inode; + struct nfs_server *server = NFS_SERVER(ino); + + dprintk("--> %s\n", __func__); + if (nfs4_setup_sequence(server, &lgp->args.seq_args, + &lgp->res.seq_res, 0, task)) + return; + rpc_call_start(task); +} + +static void nfs4_layoutget_done(struct rpc_task *task, void *calldata) +{ + struct nfs4_layoutget *lgp = calldata; + struct nfs_server *server = NFS_SERVER(lgp->args.inode); + + dprintk("--> %s\n", __func__); + + if (!nfs4_sequence_done(task, &lgp->res.seq_res)) + return; + + switch (task->tk_status) { + case 0: + break; + case -NFS4ERR_LAYOUTTRYLATER: + case -NFS4ERR_RECALLCONFLICT: + task->tk_status = -NFS4ERR_DELAY; + /* Fall through */ + default: + if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) { + rpc_restart_call_prepare(task); + return; + } + } + lgp->status = task->tk_status; + dprintk("<-- %s\n", __func__); +} + +static void nfs4_layoutget_release(void *calldata) +{ + struct nfs4_layoutget *lgp = calldata; + + dprintk("--> %s\n", __func__); + put_layout_hdr(lgp->args.inode); + if (lgp->res.layout.buf != NULL) + free_page((unsigned long) lgp->res.layout.buf); + put_nfs_open_context(lgp->args.ctx); + kfree(calldata); + dprintk("<-- %s\n", __func__); +} + +static const struct rpc_call_ops nfs4_layoutget_call_ops = { + .rpc_call_prepare = nfs4_layoutget_prepare, + .rpc_call_done = nfs4_layoutget_done, + .rpc_release = nfs4_layoutget_release, +}; + +int nfs4_proc_layoutget(struct nfs4_layoutget *lgp) +{ + struct nfs_server *server = NFS_SERVER(lgp->args.inode); + struct rpc_task *task; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LAYOUTGET], + .rpc_argp = &lgp->args, + .rpc_resp = &lgp->res, + }; + struct rpc_task_setup task_setup_data = { + .rpc_client = server->client, + .rpc_message = &msg, + .callback_ops = &nfs4_layoutget_call_ops, + .callback_data = lgp, + .flags = RPC_TASK_ASYNC, + }; + int status = 0; + + dprintk("--> %s\n", __func__); + + lgp->res.layout.buf = (void *)__get_free_page(GFP_NOFS); + if (lgp->res.layout.buf == NULL) { + nfs4_layoutget_release(lgp); + return -ENOMEM; + } + + lgp->res.seq_res.sr_slot = NULL; + task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) + return PTR_ERR(task); + status = nfs4_wait_for_completion_rpc_task(task); + if (status != 0) + goto out; + status = lgp->status; + if (status != 0) + goto out; + status = pnfs_layout_process(lgp); +out: + rpc_put_task(task); + dprintk("<-- %s status=%d\n", __func__, status); + return status; +} + +static int +_nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *pdev) +{ + struct nfs4_getdeviceinfo_args args = { + .pdev = pdev, + }; + struct nfs4_getdeviceinfo_res res = { + .pdev = pdev, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GETDEVICEINFO], + .rpc_argp = &args, + .rpc_resp = &res, + }; + int status; + + dprintk("--> %s\n", __func__); + status = nfs4_call_sync(server, &msg, &args, &res, 0); + dprintk("<-- %s status=%d\n", __func__, status); + + return status; +} + +int nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *pdev) +{ + struct nfs4_exception exception = { }; + int err; + + do { + err = nfs4_handle_exception(server, + _nfs4_proc_getdeviceinfo(server, pdev), + &exception); + } while (exception.retry); + return err; +} +EXPORT_SYMBOL_GPL(nfs4_proc_getdeviceinfo); + #endif /* CONFIG_NFS_V4_1 */ struct nfs4_state_recovery_ops nfs40_reboot_recovery_ops = { diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index aa0b02a610c4..f575a3126737 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -54,6 +54,7 @@ #include "callback.h" #include "delegation.h" #include "internal.h" +#include "pnfs.h" #define OPENOWNER_POOL_SIZE 8 @@ -1475,6 +1476,7 @@ static void nfs4_state_manager(struct nfs_client *clp) } clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state); set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state); + pnfs_destroy_all_layouts(clp); } if (test_and_clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state)) { diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index bd2101d918c8..9f1826b012e6 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -52,6 +52,7 @@ #include <linux/nfs_idmap.h> #include "nfs4_fs.h" #include "internal.h" +#include "pnfs.h" #define NFSDBG_FACILITY NFSDBG_XDR @@ -310,6 +311,19 @@ static int nfs4_stat_to_errno(int); XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 5) #define encode_reclaim_complete_maxsz (op_encode_hdr_maxsz + 4) #define decode_reclaim_complete_maxsz (op_decode_hdr_maxsz + 4) +#define encode_getdeviceinfo_maxsz (op_encode_hdr_maxsz + 4 + \ + XDR_QUADLEN(NFS4_DEVICEID4_SIZE)) +#define decode_getdeviceinfo_maxsz (op_decode_hdr_maxsz + \ + 1 /* layout type */ + \ + 1 /* opaque devaddr4 length */ + \ + /* devaddr4 payload is read into page */ \ + 1 /* notification bitmap length */ + \ + 1 /* notification bitmap */) +#define encode_layoutget_maxsz (op_encode_hdr_maxsz + 10 + \ + encode_stateid_maxsz) +#define decode_layoutget_maxsz (op_decode_hdr_maxsz + 8 + \ + decode_stateid_maxsz + \ + XDR_QUADLEN(PNFS_LAYOUT_MAXSIZE)) #else /* CONFIG_NFS_V4_1 */ #define encode_sequence_maxsz 0 #define decode_sequence_maxsz 0 @@ -699,6 +713,20 @@ static int nfs4_stat_to_errno(int); #define NFS4_dec_reclaim_complete_sz (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_reclaim_complete_maxsz) +#define NFS4_enc_getdeviceinfo_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz +\ + encode_getdeviceinfo_maxsz) +#define NFS4_dec_getdeviceinfo_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_getdeviceinfo_maxsz) +#define NFS4_enc_layoutget_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_layoutget_maxsz) +#define NFS4_dec_layoutget_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_layoutget_maxsz) const u32 nfs41_maxwrite_overhead = ((RPC_MAX_HEADER_WITH_AUTH + compound_encode_hdr_maxsz + @@ -1737,6 +1765,58 @@ static void encode_sequence(struct xdr_stream *xdr, #endif /* CONFIG_NFS_V4_1 */ } +#ifdef CONFIG_NFS_V4_1 +static void +encode_getdeviceinfo(struct xdr_stream *xdr, + const struct nfs4_getdeviceinfo_args *args, + struct compound_hdr *hdr) +{ + __be32 *p; + + p = reserve_space(xdr, 16 + NFS4_DEVICEID4_SIZE); + *p++ = cpu_to_be32(OP_GETDEVICEINFO); + p = xdr_encode_opaque_fixed(p, args->pdev->dev_id.data, + NFS4_DEVICEID4_SIZE); + *p++ = cpu_to_be32(args->pdev->layout_type); + *p++ = cpu_to_be32(args->pdev->pglen); /* gdia_maxcount */ + *p++ = cpu_to_be32(0); /* bitmap length 0 */ + hdr->nops++; + hdr->replen += decode_getdeviceinfo_maxsz; +} + +static void +encode_layoutget(struct xdr_stream *xdr, + const struct nfs4_layoutget_args *args, + struct compound_hdr *hdr) +{ + nfs4_stateid stateid; + __be32 *p; + + p = reserve_space(xdr, 44 + NFS4_STATEID_SIZE); + *p++ = cpu_to_be32(OP_LAYOUTGET); + *p++ = cpu_to_be32(0); /* Signal layout available */ + *p++ = cpu_to_be32(args->type); + *p++ = cpu_to_be32(args->range.iomode); + p = xdr_encode_hyper(p, args->range.offset); + p = xdr_encode_hyper(p, args->range.length); + p = xdr_encode_hyper(p, args->minlength); + pnfs_get_layout_stateid(&stateid, NFS_I(args->inode)->layout, + args->ctx->state); + p = xdr_encode_opaque_fixed(p, &stateid.data, NFS4_STATEID_SIZE); + *p = cpu_to_be32(args->maxcount); + + dprintk("%s: 1st type:0x%x iomode:%d off:%lu len:%lu mc:%d\n", + __func__, + args->type, + args->range.iomode, + (unsigned long)args->range.offset, + (unsigned long)args->range.length, + args->maxcount); + hdr->nops++; + hdr->replen += decode_layoutget_maxsz; +} +#endif /* CONFIG_NFS_V4_1 */ + /* * END OF "GENERIC" ENCODE ROUTINES. */ @@ -2554,6 +2634,51 @@ static int nfs4_xdr_enc_reclaim_complete(struct rpc_rqst *req, uint32_t *p, return 0; } +/* + * Encode GETDEVICEINFO request + */ +static int nfs4_xdr_enc_getdeviceinfo(struct rpc_rqst *req, uint32_t *p, + struct nfs4_getdeviceinfo_args *args) +{ + struct xdr_stream xdr; + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + xdr_init_encode(&xdr, &req->rq_snd_buf, p); + encode_compound_hdr(&xdr, req, &hdr); + encode_sequence(&xdr, &args->seq_args, &hdr); + encode_getdeviceinfo(&xdr, args, &hdr); + + /* set up reply kvec. Subtract notification bitmap max size (2) + * so that notification bitmap is put in xdr_buf tail */ + xdr_inline_pages(&req->rq_rcv_buf, (hdr.replen - 2) << 2, + args->pdev->pages, args->pdev->pgbase, + args->pdev->pglen); + + encode_nops(&hdr); + return 0; +} + +/* + * Encode LAYOUTGET request + */ +static int nfs4_xdr_enc_layoutget(struct rpc_rqst *req, uint32_t *p, + struct nfs4_layoutget_args *args) +{ + struct xdr_stream xdr; + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + xdr_init_encode(&xdr, &req->rq_snd_buf, p); + encode_compound_hdr(&xdr, req, &hdr); + encode_sequence(&xdr, &args->seq_args, &hdr); + encode_putfh(&xdr, NFS_FH(args->inode), &hdr); + encode_layoutget(&xdr, args, &hdr); + encode_nops(&hdr); + return 0; +} #endif /* CONFIG_NFS_V4_1 */ static void print_overflow_msg(const char *func, const struct xdr_stream *xdr) @@ -3978,6 +4103,61 @@ static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, return decode_getfattr_generic(xdr, fattr, NULL, server, may_sleep); } +/* + * Decode potentially multiple layout types. Currently we only support + * one layout driver per file system. + */ +static int decode_first_pnfs_layout_type(struct xdr_stream *xdr, + uint32_t *layouttype) +{ + uint32_t *p; + int num; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + num = be32_to_cpup(p); + + /* pNFS is not supported by the underlying file system */ + if (num == 0) { + *layouttype = 0; + return 0; + } + if (num > 1) + printk(KERN_INFO "%s: Warning: Multiple pNFS layout drivers " + "per filesystem not supported\n", __func__); + + /* Decode and set first layout type, move xdr->p past unused types */ + p = xdr_inline_decode(xdr, num * 4); + if (unlikely(!p)) + goto out_overflow; + *layouttype = be32_to_cpup(p); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +/* + * The type of file system exported. + * Note we must ensure that layouttype is set in any non-error case. + */ +static int decode_attr_pnfstype(struct xdr_stream *xdr, uint32_t *bitmap, + uint32_t *layouttype) +{ + int status = 0; + + dprintk("%s: bitmap is %x\n", __func__, bitmap[1]); + if (unlikely(bitmap[1] & (FATTR4_WORD1_FS_LAYOUT_TYPES - 1U))) + return -EIO; + if (bitmap[1] & FATTR4_WORD1_FS_LAYOUT_TYPES) { + status = decode_first_pnfs_layout_type(xdr, layouttype); + bitmap[1] &= ~FATTR4_WORD1_FS_LAYOUT_TYPES; + } else + *layouttype = 0; + return status; +} + static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo) { __be32 *savep; @@ -4006,6 +4186,9 @@ static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo) status = decode_attr_time_delta(xdr, bitmap, &fsinfo->time_delta); if (status != 0) goto xdr_error; + status = decode_attr_pnfstype(xdr, bitmap, &fsinfo->layouttype); + if (status != 0) + goto xdr_error; status = verify_attr_len(xdr, savep, attrlen); xdr_error: @@ -4335,7 +4518,7 @@ static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct n xdr_read_pages(xdr, pglen); - return 0; + return pglen; } static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req) @@ -4772,6 +4955,134 @@ out_overflow: #endif /* CONFIG_NFS_V4_1 */ } +#if defined(CONFIG_NFS_V4_1) + +static int decode_getdeviceinfo(struct xdr_stream *xdr, + struct pnfs_device *pdev) +{ + __be32 *p; + uint32_t len, type; + int status; + + status = decode_op_hdr(xdr, OP_GETDEVICEINFO); + if (status) { + if (status == -ETOOSMALL) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + pdev->mincount = be32_to_cpup(p); + dprintk("%s: Min count too small. mincnt = %u\n", + __func__, pdev->mincount); + } + return status; + } + + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + type = be32_to_cpup(p++); + if (type != pdev->layout_type) { + dprintk("%s: layout mismatch req: %u pdev: %u\n", + __func__, pdev->layout_type, type); + return -EINVAL; + } + /* + * Get the length of the opaque device_addr4. xdr_read_pages places + * the opaque device_addr4 in the xdr_buf->pages (pnfs_device->pages) + * and places the remaining xdr data in xdr_buf->tail + */ + pdev->mincount = be32_to_cpup(p); + xdr_read_pages(xdr, pdev->mincount); /* include space for the length */ + + /* Parse notification bitmap, verifying that it is zero. */ + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + len = be32_to_cpup(p); + if (len) { + int i; + + p = xdr_inline_decode(xdr, 4 * len); + if (unlikely(!p)) + goto out_overflow; + for (i = 0; i < len; i++, p++) { + if (be32_to_cpup(p)) { + dprintk("%s: notifications not supported\n", + __func__); + return -EIO; + } + } + } + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req, + struct nfs4_layoutget_res *res) +{ + __be32 *p; + int status; + u32 layout_count; + + status = decode_op_hdr(xdr, OP_LAYOUTGET); + if (status) + return status; + p = xdr_inline_decode(xdr, 8 + NFS4_STATEID_SIZE); + if (unlikely(!p)) + goto out_overflow; + res->return_on_close = be32_to_cpup(p++); + p = xdr_decode_opaque_fixed(p, res->stateid.data, NFS4_STATEID_SIZE); + layout_count = be32_to_cpup(p); + if (!layout_count) { + dprintk("%s: server responded with empty layout array\n", + __func__); + return -EINVAL; + } + + p = xdr_inline_decode(xdr, 24); + if (unlikely(!p)) + goto out_overflow; + p = xdr_decode_hyper(p, &res->range.offset); + p = xdr_decode_hyper(p, &res->range.length); + res->range.iomode = be32_to_cpup(p++); + res->type = be32_to_cpup(p++); + + status = decode_opaque_inline(xdr, &res->layout.len, (char **)&p); + if (unlikely(status)) + return status; + + dprintk("%s roff:%lu rlen:%lu riomode:%d, lo_type:0x%x, lo.len:%d\n", + __func__, + (unsigned long)res->range.offset, + (unsigned long)res->range.length, + res->range.iomode, + res->type, + res->layout.len); + + /* nfs4_proc_layoutget allocated a single page */ + if (res->layout.len > PAGE_SIZE) + return -ENOMEM; + memcpy(res->layout.buf, p, res->layout.len); + + if (layout_count > 1) { + /* We only handle a length one array at the moment. Any + * further entries are just ignored. Note that this means + * the client may see a response that is less than the + * minimum it requested. + */ + dprintk("%s: server responded with %d layouts, dropping tail\n", + __func__, layout_count); + } + + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} +#endif /* CONFIG_NFS_V4_1 */ + /* * END OF "GENERIC" DECODE ROUTINES. */ @@ -5799,6 +6110,53 @@ static int nfs4_xdr_dec_reclaim_complete(struct rpc_rqst *rqstp, uint32_t *p, status = decode_reclaim_complete(&xdr, (void *)NULL); return status; } + +/* + * Decode GETDEVINFO response + */ +static int nfs4_xdr_dec_getdeviceinfo(struct rpc_rqst *rqstp, uint32_t *p, + struct nfs4_getdeviceinfo_res *res) +{ + struct xdr_stream xdr; + struct compound_hdr hdr; + int status; + + xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p); + status = decode_compound_hdr(&xdr, &hdr); + if (status != 0) + goto out; + status = decode_sequence(&xdr, &res->seq_res, rqstp); + if (status != 0) + goto out; + status = decode_getdeviceinfo(&xdr, res->pdev); +out: + return status; +} + +/* + * Decode LAYOUTGET response + */ +static int nfs4_xdr_dec_layoutget(struct rpc_rqst *rqstp, uint32_t *p, + struct nfs4_layoutget_res *res) +{ + struct xdr_stream xdr; + struct compound_hdr hdr; + int status; + + xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p); + status = decode_compound_hdr(&xdr, &hdr); + if (status) + goto out; + status = decode_sequence(&xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(&xdr); + if (status) + goto out; + status = decode_layoutget(&xdr, rqstp, res); +out: + return status; +} #endif /* CONFIG_NFS_V4_1 */ __be32 *nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, @@ -5850,6 +6208,10 @@ __be32 *nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, if (entry->fattr->valid & NFS_ATTR_FATTR_FILEID) entry->ino = entry->fattr->fileid; + entry->d_type = DT_UNKNOWN; + if (entry->fattr->valid & NFS_ATTR_FATTR_TYPE) + entry->d_type = nfs_umode_to_dtype(entry->fattr->mode); + if (verify_attr_len(xdr, p, len) < 0) goto out_overflow; @@ -5863,7 +6225,7 @@ __be32 *nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, out_overflow: print_overflow_msg(__func__, xdr); - return ERR_PTR(-EIO); + return ERR_PTR(-EAGAIN); } /* @@ -5990,6 +6352,8 @@ struct rpc_procinfo nfs4_procedures[] = { PROC(SEQUENCE, enc_sequence, dec_sequence), PROC(GET_LEASE_TIME, enc_get_lease_time, dec_get_lease_time), PROC(RECLAIM_COMPLETE, enc_reclaim_complete, dec_reclaim_complete), + PROC(GETDEVICEINFO, enc_getdeviceinfo, dec_getdeviceinfo), + PROC(LAYOUTGET, enc_layoutget, dec_layoutget), #endif /* CONFIG_NFS_V4_1 */ }; diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c index 460df3652889..903908a20023 100644 --- a/fs/nfs/nfsroot.c +++ b/fs/nfs/nfsroot.c @@ -101,6 +101,7 @@ static char nfs_export_path[NFS_MAXPATHLEN + 1] __initdata = ""; /* server:export path string passed to super.c */ static char nfs_root_device[NFS_MAXPATHLEN + 1] __initdata = ""; +#ifdef RPC_DEBUG /* * When the "nfsrootdebug" kernel command line option is specified, * enable debugging messages for NFSROOT. @@ -112,6 +113,7 @@ static int __init nfs_root_debug(char *__unused) } __setup("nfsrootdebug", nfs_root_debug); +#endif /* * Parse NFS server and directory information passed on the kernel diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 919490232e17..137b549e63db 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -65,6 +65,13 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode, if (req == NULL) return ERR_PTR(-ENOMEM); + /* get lock context early so we can deal with alloc failures */ + req->wb_lock_context = nfs_get_lock_context(ctx); + if (req->wb_lock_context == NULL) { + nfs_page_free(req); + return ERR_PTR(-ENOMEM); + } + /* Initialize the request struct. Initially, we assume a * long write-back delay. This will be adjusted in * update_nfs_request below if the region is not locked. */ @@ -79,7 +86,6 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode, req->wb_pgbase = offset; req->wb_bytes = count; req->wb_context = get_nfs_open_context(ctx); - req->wb_lock_context = nfs_get_lock_context(ctx); kref_init(&req->wb_kref); return req; } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c new file mode 100644 index 000000000000..db773428f95f --- /dev/null +++ b/fs/nfs/pnfs.c @@ -0,0 +1,783 @@ +/* + * pNFS functions to call and manage layout drivers. + * + * Copyright (c) 2002 [year of first publication] + * The Regents of the University of Michigan + * All Rights Reserved + * + * Dean Hildebrand <dhildebz@umich.edu> + * + * Permission is granted to use, copy, create derivative works, and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the University of Michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. If + * the above copyright notice or any other identification of the + * University of Michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * This software is provided as is, without representation or warranty + * of any kind either express or implied, including without limitation + * the implied warranties of merchantability, fitness for a particular + * purpose, or noninfringement. The Regents of the University of + * Michigan shall not be liable for any damages, including special, + * indirect, incidental, or consequential damages, with respect to any + * claim arising out of or in connection with the use of the software, + * even if it has been or is hereafter advised of the possibility of + * such damages. + */ + +#include <linux/nfs_fs.h> +#include "internal.h" +#include "pnfs.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS + +/* Locking: + * + * pnfs_spinlock: + * protects pnfs_modules_tbl. + */ +static DEFINE_SPINLOCK(pnfs_spinlock); + +/* + * pnfs_modules_tbl holds all pnfs modules + */ +static LIST_HEAD(pnfs_modules_tbl); + +/* Return the registered pnfs layout driver module matching given id */ +static struct pnfs_layoutdriver_type * +find_pnfs_driver_locked(u32 id) +{ + struct pnfs_layoutdriver_type *local; + + list_for_each_entry(local, &pnfs_modules_tbl, pnfs_tblid) + if (local->id == id) + goto out; + local = NULL; +out: + dprintk("%s: Searching for id %u, found %p\n", __func__, id, local); + return local; +} + +static struct pnfs_layoutdriver_type * +find_pnfs_driver(u32 id) +{ + struct pnfs_layoutdriver_type *local; + + spin_lock(&pnfs_spinlock); + local = find_pnfs_driver_locked(id); + spin_unlock(&pnfs_spinlock); + return local; +} + +void +unset_pnfs_layoutdriver(struct nfs_server *nfss) +{ + if (nfss->pnfs_curr_ld) { + nfss->pnfs_curr_ld->clear_layoutdriver(nfss); + module_put(nfss->pnfs_curr_ld->owner); + } + nfss->pnfs_curr_ld = NULL; +} + +/* + * Try to set the server's pnfs module to the pnfs layout type specified by id. + * Currently only one pNFS layout driver per filesystem is supported. + * + * @id layout type. Zero (illegal layout type) indicates pNFS not in use. + */ +void +set_pnfs_layoutdriver(struct nfs_server *server, u32 id) +{ + struct pnfs_layoutdriver_type *ld_type = NULL; + + if (id == 0) + goto out_no_driver; + if (!(server->nfs_client->cl_exchange_flags & + (EXCHGID4_FLAG_USE_NON_PNFS | EXCHGID4_FLAG_USE_PNFS_MDS))) { + printk(KERN_ERR "%s: id %u cl_exchange_flags 0x%x\n", __func__, + id, server->nfs_client->cl_exchange_flags); + goto out_no_driver; + } + ld_type = find_pnfs_driver(id); + if (!ld_type) { + request_module("%s-%u", LAYOUT_NFSV4_1_MODULE_PREFIX, id); + ld_type = find_pnfs_driver(id); + if (!ld_type) { + dprintk("%s: No pNFS module found for %u.\n", + __func__, id); + goto out_no_driver; + } + } + if (!try_module_get(ld_type->owner)) { + dprintk("%s: Could not grab reference on module\n", __func__); + goto out_no_driver; + } + server->pnfs_curr_ld = ld_type; + if (ld_type->set_layoutdriver(server)) { + printk(KERN_ERR + "%s: Error initializing mount point for layout driver %u.\n", + __func__, id); + module_put(ld_type->owner); + goto out_no_driver; + } + dprintk("%s: pNFS module for %u set\n", __func__, id); + return; + +out_no_driver: + dprintk("%s: Using NFSv4 I/O\n", __func__); + server->pnfs_curr_ld = NULL; +} + +int +pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *ld_type) +{ + int status = -EINVAL; + struct pnfs_layoutdriver_type *tmp; + + if (ld_type->id == 0) { + printk(KERN_ERR "%s id 0 is reserved\n", __func__); + return status; + } + if (!ld_type->alloc_lseg || !ld_type->free_lseg) { + printk(KERN_ERR "%s Layout driver must provide " + "alloc_lseg and free_lseg.\n", __func__); + return status; + } + + spin_lock(&pnfs_spinlock); + tmp = find_pnfs_driver_locked(ld_type->id); + if (!tmp) { + list_add(&ld_type->pnfs_tblid, &pnfs_modules_tbl); + status = 0; + dprintk("%s Registering id:%u name:%s\n", __func__, ld_type->id, + ld_type->name); + } else { + printk(KERN_ERR "%s Module with id %d already loaded!\n", + __func__, ld_type->id); + } + spin_unlock(&pnfs_spinlock); + + return status; +} +EXPORT_SYMBOL_GPL(pnfs_register_layoutdriver); + +void +pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *ld_type) +{ + dprintk("%s Deregistering id:%u\n", __func__, ld_type->id); + spin_lock(&pnfs_spinlock); + list_del(&ld_type->pnfs_tblid); + spin_unlock(&pnfs_spinlock); +} +EXPORT_SYMBOL_GPL(pnfs_unregister_layoutdriver); + +/* + * pNFS client layout cache + */ + +static void +get_layout_hdr_locked(struct pnfs_layout_hdr *lo) +{ + assert_spin_locked(&lo->inode->i_lock); + lo->refcount++; +} + +static void +put_layout_hdr_locked(struct pnfs_layout_hdr *lo) +{ + assert_spin_locked(&lo->inode->i_lock); + BUG_ON(lo->refcount == 0); + + lo->refcount--; + if (!lo->refcount) { + dprintk("%s: freeing layout cache %p\n", __func__, lo); + BUG_ON(!list_empty(&lo->layouts)); + NFS_I(lo->inode)->layout = NULL; + kfree(lo); + } +} + +void +put_layout_hdr(struct inode *inode) +{ + spin_lock(&inode->i_lock); + put_layout_hdr_locked(NFS_I(inode)->layout); + spin_unlock(&inode->i_lock); +} + +static void +init_lseg(struct pnfs_layout_hdr *lo, struct pnfs_layout_segment *lseg) +{ + INIT_LIST_HEAD(&lseg->fi_list); + kref_init(&lseg->kref); + lseg->layout = lo; +} + +/* Called without i_lock held, as the free_lseg call may sleep */ +static void +destroy_lseg(struct kref *kref) +{ + struct pnfs_layout_segment *lseg = + container_of(kref, struct pnfs_layout_segment, kref); + struct inode *ino = lseg->layout->inode; + + dprintk("--> %s\n", __func__); + NFS_SERVER(ino)->pnfs_curr_ld->free_lseg(lseg); + /* Matched by get_layout_hdr_locked in pnfs_insert_layout */ + put_layout_hdr(ino); +} + +static void +put_lseg(struct pnfs_layout_segment *lseg) +{ + if (!lseg) + return; + + dprintk("%s: lseg %p ref %d\n", __func__, lseg, + atomic_read(&lseg->kref.refcount)); + kref_put(&lseg->kref, destroy_lseg); +} + +static void +pnfs_clear_lseg_list(struct pnfs_layout_hdr *lo, struct list_head *tmp_list) +{ + struct pnfs_layout_segment *lseg, *next; + struct nfs_client *clp; + + dprintk("%s:Begin lo %p\n", __func__, lo); + + assert_spin_locked(&lo->inode->i_lock); + list_for_each_entry_safe(lseg, next, &lo->segs, fi_list) { + dprintk("%s: freeing lseg %p\n", __func__, lseg); + list_move(&lseg->fi_list, tmp_list); + } + clp = NFS_SERVER(lo->inode)->nfs_client; + spin_lock(&clp->cl_lock); + /* List does not take a reference, so no need for put here */ + list_del_init(&lo->layouts); + spin_unlock(&clp->cl_lock); + write_seqlock(&lo->seqlock); + clear_bit(NFS_LAYOUT_STATEID_SET, &lo->state); + write_sequnlock(&lo->seqlock); + + dprintk("%s:Return\n", __func__); +} + +static void +pnfs_free_lseg_list(struct list_head *tmp_list) +{ + struct pnfs_layout_segment *lseg; + + while (!list_empty(tmp_list)) { + lseg = list_entry(tmp_list->next, struct pnfs_layout_segment, + fi_list); + dprintk("%s calling put_lseg on %p\n", __func__, lseg); + list_del(&lseg->fi_list); + put_lseg(lseg); + } +} + +void +pnfs_destroy_layout(struct nfs_inode *nfsi) +{ + struct pnfs_layout_hdr *lo; + LIST_HEAD(tmp_list); + + spin_lock(&nfsi->vfs_inode.i_lock); + lo = nfsi->layout; + if (lo) { + pnfs_clear_lseg_list(lo, &tmp_list); + /* Matched by refcount set to 1 in alloc_init_layout_hdr */ + put_layout_hdr_locked(lo); + } + spin_unlock(&nfsi->vfs_inode.i_lock); + pnfs_free_lseg_list(&tmp_list); +} + +/* + * Called by the state manger to remove all layouts established under an + * expired lease. + */ +void +pnfs_destroy_all_layouts(struct nfs_client *clp) +{ + struct pnfs_layout_hdr *lo; + LIST_HEAD(tmp_list); + + spin_lock(&clp->cl_lock); + list_splice_init(&clp->cl_layouts, &tmp_list); + spin_unlock(&clp->cl_lock); + + while (!list_empty(&tmp_list)) { + lo = list_entry(tmp_list.next, struct pnfs_layout_hdr, + layouts); + dprintk("%s freeing layout for inode %lu\n", __func__, + lo->inode->i_ino); + pnfs_destroy_layout(NFS_I(lo->inode)); + } +} + +/* update lo->stateid with new if is more recent + * + * lo->stateid could be the open stateid, in which case we just use what given. + */ +static void +pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, + const nfs4_stateid *new) +{ + nfs4_stateid *old = &lo->stateid; + bool overwrite = false; + + write_seqlock(&lo->seqlock); + if (!test_bit(NFS_LAYOUT_STATEID_SET, &lo->state) || + memcmp(old->stateid.other, new->stateid.other, sizeof(new->stateid.other))) + overwrite = true; + else { + u32 oldseq, newseq; + + oldseq = be32_to_cpu(old->stateid.seqid); + newseq = be32_to_cpu(new->stateid.seqid); + if ((int)(newseq - oldseq) > 0) + overwrite = true; + } + if (overwrite) + memcpy(&old->stateid, &new->stateid, sizeof(new->stateid)); + write_sequnlock(&lo->seqlock); +} + +static void +pnfs_layout_from_open_stateid(struct pnfs_layout_hdr *lo, + struct nfs4_state *state) +{ + int seq; + + dprintk("--> %s\n", __func__); + write_seqlock(&lo->seqlock); + do { + seq = read_seqbegin(&state->seqlock); + memcpy(lo->stateid.data, state->stateid.data, + sizeof(state->stateid.data)); + } while (read_seqretry(&state->seqlock, seq)); + set_bit(NFS_LAYOUT_STATEID_SET, &lo->state); + write_sequnlock(&lo->seqlock); + dprintk("<-- %s\n", __func__); +} + +void +pnfs_get_layout_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo, + struct nfs4_state *open_state) +{ + int seq; + + dprintk("--> %s\n", __func__); + do { + seq = read_seqbegin(&lo->seqlock); + if (!test_bit(NFS_LAYOUT_STATEID_SET, &lo->state)) { + /* This will trigger retry of the read */ + pnfs_layout_from_open_stateid(lo, open_state); + } else + memcpy(dst->data, lo->stateid.data, + sizeof(lo->stateid.data)); + } while (read_seqretry(&lo->seqlock, seq)); + dprintk("<-- %s\n", __func__); +} + +/* +* Get layout from server. +* for now, assume that whole file layouts are requested. +* arg->offset: 0 +* arg->length: all ones +*/ +static struct pnfs_layout_segment * +send_layoutget(struct pnfs_layout_hdr *lo, + struct nfs_open_context *ctx, + u32 iomode) +{ + struct inode *ino = lo->inode; + struct nfs_server *server = NFS_SERVER(ino); + struct nfs4_layoutget *lgp; + struct pnfs_layout_segment *lseg = NULL; + + dprintk("--> %s\n", __func__); + + BUG_ON(ctx == NULL); + lgp = kzalloc(sizeof(*lgp), GFP_KERNEL); + if (lgp == NULL) { + put_layout_hdr(lo->inode); + return NULL; + } + lgp->args.minlength = NFS4_MAX_UINT64; + lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE; + lgp->args.range.iomode = iomode; + lgp->args.range.offset = 0; + lgp->args.range.length = NFS4_MAX_UINT64; + lgp->args.type = server->pnfs_curr_ld->id; + lgp->args.inode = ino; + lgp->args.ctx = get_nfs_open_context(ctx); + lgp->lsegpp = &lseg; + + /* Synchronously retrieve layout information from server and + * store in lseg. + */ + nfs4_proc_layoutget(lgp); + if (!lseg) { + /* remember that LAYOUTGET failed and suspend trying */ + set_bit(lo_fail_bit(iomode), &lo->state); + } + return lseg; +} + +/* + * Compare two layout segments for sorting into layout cache. + * We want to preferentially return RW over RO layouts, so ensure those + * are seen first. + */ +static s64 +cmp_layout(u32 iomode1, u32 iomode2) +{ + /* read > read/write */ + return (int)(iomode2 == IOMODE_READ) - (int)(iomode1 == IOMODE_READ); +} + +static void +pnfs_insert_layout(struct pnfs_layout_hdr *lo, + struct pnfs_layout_segment *lseg) +{ + struct pnfs_layout_segment *lp; + int found = 0; + + dprintk("%s:Begin\n", __func__); + + assert_spin_locked(&lo->inode->i_lock); + if (list_empty(&lo->segs)) { + struct nfs_client *clp = NFS_SERVER(lo->inode)->nfs_client; + + spin_lock(&clp->cl_lock); + BUG_ON(!list_empty(&lo->layouts)); + list_add_tail(&lo->layouts, &clp->cl_layouts); + spin_unlock(&clp->cl_lock); + } + list_for_each_entry(lp, &lo->segs, fi_list) { + if (cmp_layout(lp->range.iomode, lseg->range.iomode) > 0) + continue; + list_add_tail(&lseg->fi_list, &lp->fi_list); + dprintk("%s: inserted lseg %p " + "iomode %d offset %llu length %llu before " + "lp %p iomode %d offset %llu length %llu\n", + __func__, lseg, lseg->range.iomode, + lseg->range.offset, lseg->range.length, + lp, lp->range.iomode, lp->range.offset, + lp->range.length); + found = 1; + break; + } + if (!found) { + list_add_tail(&lseg->fi_list, &lo->segs); + dprintk("%s: inserted lseg %p " + "iomode %d offset %llu length %llu at tail\n", + __func__, lseg, lseg->range.iomode, + lseg->range.offset, lseg->range.length); + } + get_layout_hdr_locked(lo); + + dprintk("%s:Return\n", __func__); +} + +static struct pnfs_layout_hdr * +alloc_init_layout_hdr(struct inode *ino) +{ + struct pnfs_layout_hdr *lo; + + lo = kzalloc(sizeof(struct pnfs_layout_hdr), GFP_KERNEL); + if (!lo) + return NULL; + lo->refcount = 1; + INIT_LIST_HEAD(&lo->layouts); + INIT_LIST_HEAD(&lo->segs); + seqlock_init(&lo->seqlock); + lo->inode = ino; + return lo; +} + +static struct pnfs_layout_hdr * +pnfs_find_alloc_layout(struct inode *ino) +{ + struct nfs_inode *nfsi = NFS_I(ino); + struct pnfs_layout_hdr *new = NULL; + + dprintk("%s Begin ino=%p layout=%p\n", __func__, ino, nfsi->layout); + + assert_spin_locked(&ino->i_lock); + if (nfsi->layout) + return nfsi->layout; + + spin_unlock(&ino->i_lock); + new = alloc_init_layout_hdr(ino); + spin_lock(&ino->i_lock); + + if (likely(nfsi->layout == NULL)) /* Won the race? */ + nfsi->layout = new; + else + kfree(new); + return nfsi->layout; +} + +/* + * iomode matching rules: + * iomode lseg match + * ----- ----- ----- + * ANY READ true + * ANY RW true + * RW READ false + * RW RW true + * READ READ true + * READ RW true + */ +static int +is_matching_lseg(struct pnfs_layout_segment *lseg, u32 iomode) +{ + return (iomode != IOMODE_RW || lseg->range.iomode == IOMODE_RW); +} + +/* + * lookup range in layout + */ +static struct pnfs_layout_segment * +pnfs_has_layout(struct pnfs_layout_hdr *lo, u32 iomode) +{ + struct pnfs_layout_segment *lseg, *ret = NULL; + + dprintk("%s:Begin\n", __func__); + + assert_spin_locked(&lo->inode->i_lock); + list_for_each_entry(lseg, &lo->segs, fi_list) { + if (is_matching_lseg(lseg, iomode)) { + ret = lseg; + break; + } + if (cmp_layout(iomode, lseg->range.iomode) > 0) + break; + } + + dprintk("%s:Return lseg %p ref %d\n", + __func__, ret, ret ? atomic_read(&ret->kref.refcount) : 0); + return ret; +} + +/* + * Layout segment is retreived from the server if not cached. + * The appropriate layout segment is referenced and returned to the caller. + */ +struct pnfs_layout_segment * +pnfs_update_layout(struct inode *ino, + struct nfs_open_context *ctx, + enum pnfs_iomode iomode) +{ + struct nfs_inode *nfsi = NFS_I(ino); + struct pnfs_layout_hdr *lo; + struct pnfs_layout_segment *lseg = NULL; + + if (!pnfs_enabled_sb(NFS_SERVER(ino))) + return NULL; + spin_lock(&ino->i_lock); + lo = pnfs_find_alloc_layout(ino); + if (lo == NULL) { + dprintk("%s ERROR: can't get pnfs_layout_hdr\n", __func__); + goto out_unlock; + } + + /* Check to see if the layout for the given range already exists */ + lseg = pnfs_has_layout(lo, iomode); + if (lseg) { + dprintk("%s: Using cached lseg %p for iomode %d)\n", + __func__, lseg, iomode); + goto out_unlock; + } + + /* if LAYOUTGET already failed once we don't try again */ + if (test_bit(lo_fail_bit(iomode), &nfsi->layout->state)) + goto out_unlock; + + get_layout_hdr_locked(lo); /* Matched in nfs4_layoutget_release */ + spin_unlock(&ino->i_lock); + + lseg = send_layoutget(lo, ctx, iomode); +out: + dprintk("%s end, state 0x%lx lseg %p\n", __func__, + nfsi->layout->state, lseg); + return lseg; +out_unlock: + spin_unlock(&ino->i_lock); + goto out; +} + +int +pnfs_layout_process(struct nfs4_layoutget *lgp) +{ + struct pnfs_layout_hdr *lo = NFS_I(lgp->args.inode)->layout; + struct nfs4_layoutget_res *res = &lgp->res; + struct pnfs_layout_segment *lseg; + struct inode *ino = lo->inode; + int status = 0; + + /* Inject layout blob into I/O device driver */ + lseg = NFS_SERVER(ino)->pnfs_curr_ld->alloc_lseg(lo, res); + if (!lseg || IS_ERR(lseg)) { + if (!lseg) + status = -ENOMEM; + else + status = PTR_ERR(lseg); + dprintk("%s: Could not allocate layout: error %d\n", + __func__, status); + goto out; + } + + spin_lock(&ino->i_lock); + init_lseg(lo, lseg); + lseg->range = res->range; + *lgp->lsegpp = lseg; + pnfs_insert_layout(lo, lseg); + + /* Done processing layoutget. Set the layout stateid */ + pnfs_set_layout_stateid(lo, &res->stateid); + spin_unlock(&ino->i_lock); +out: + return status; +} + +/* + * Device ID cache. Currently supports one layout type per struct nfs_client. + * Add layout type to the lookup key to expand to support multiple types. + */ +int +pnfs_alloc_init_deviceid_cache(struct nfs_client *clp, + void (*free_callback)(struct pnfs_deviceid_node *)) +{ + struct pnfs_deviceid_cache *c; + + c = kzalloc(sizeof(struct pnfs_deviceid_cache), GFP_KERNEL); + if (!c) + return -ENOMEM; + spin_lock(&clp->cl_lock); + if (clp->cl_devid_cache != NULL) { + atomic_inc(&clp->cl_devid_cache->dc_ref); + dprintk("%s [kref [%d]]\n", __func__, + atomic_read(&clp->cl_devid_cache->dc_ref)); + kfree(c); + } else { + /* kzalloc initializes hlists */ + spin_lock_init(&c->dc_lock); + atomic_set(&c->dc_ref, 1); + c->dc_free_callback = free_callback; + clp->cl_devid_cache = c; + dprintk("%s [new]\n", __func__); + } + spin_unlock(&clp->cl_lock); + return 0; +} +EXPORT_SYMBOL_GPL(pnfs_alloc_init_deviceid_cache); + +/* + * Called from pnfs_layoutdriver_type->free_lseg + * last layout segment reference frees deviceid + */ +void +pnfs_put_deviceid(struct pnfs_deviceid_cache *c, + struct pnfs_deviceid_node *devid) +{ + struct nfs4_deviceid *id = &devid->de_id; + struct pnfs_deviceid_node *d; + struct hlist_node *n; + long h = nfs4_deviceid_hash(id); + + dprintk("%s [%d]\n", __func__, atomic_read(&devid->de_ref)); + if (!atomic_dec_and_lock(&devid->de_ref, &c->dc_lock)) + return; + + hlist_for_each_entry_rcu(d, n, &c->dc_deviceids[h], de_node) + if (!memcmp(&d->de_id, id, sizeof(*id))) { + hlist_del_rcu(&d->de_node); + spin_unlock(&c->dc_lock); + synchronize_rcu(); + c->dc_free_callback(devid); + return; + } + spin_unlock(&c->dc_lock); + /* Why wasn't it found in the list? */ + BUG(); +} +EXPORT_SYMBOL_GPL(pnfs_put_deviceid); + +/* Find and reference a deviceid */ +struct pnfs_deviceid_node * +pnfs_find_get_deviceid(struct pnfs_deviceid_cache *c, struct nfs4_deviceid *id) +{ + struct pnfs_deviceid_node *d; + struct hlist_node *n; + long hash = nfs4_deviceid_hash(id); + + dprintk("--> %s hash %ld\n", __func__, hash); + rcu_read_lock(); + hlist_for_each_entry_rcu(d, n, &c->dc_deviceids[hash], de_node) { + if (!memcmp(&d->de_id, id, sizeof(*id))) { + if (!atomic_inc_not_zero(&d->de_ref)) { + goto fail; + } else { + rcu_read_unlock(); + return d; + } + } + } +fail: + rcu_read_unlock(); + return NULL; +} +EXPORT_SYMBOL_GPL(pnfs_find_get_deviceid); + +/* + * Add a deviceid to the cache. + * GETDEVICEINFOs for same deviceid can race. If deviceid is found, discard new + */ +struct pnfs_deviceid_node * +pnfs_add_deviceid(struct pnfs_deviceid_cache *c, struct pnfs_deviceid_node *new) +{ + struct pnfs_deviceid_node *d; + long hash = nfs4_deviceid_hash(&new->de_id); + + dprintk("--> %s hash %ld\n", __func__, hash); + spin_lock(&c->dc_lock); + d = pnfs_find_get_deviceid(c, &new->de_id); + if (d) { + spin_unlock(&c->dc_lock); + dprintk("%s [discard]\n", __func__); + c->dc_free_callback(new); + return d; + } + INIT_HLIST_NODE(&new->de_node); + atomic_set(&new->de_ref, 1); + hlist_add_head_rcu(&new->de_node, &c->dc_deviceids[hash]); + spin_unlock(&c->dc_lock); + dprintk("%s [new]\n", __func__); + return new; +} +EXPORT_SYMBOL_GPL(pnfs_add_deviceid); + +void +pnfs_put_deviceid_cache(struct nfs_client *clp) +{ + struct pnfs_deviceid_cache *local = clp->cl_devid_cache; + + dprintk("--> %s cl_devid_cache %p\n", __func__, clp->cl_devid_cache); + if (atomic_dec_and_lock(&local->dc_ref, &clp->cl_lock)) { + int i; + /* Verify cache is empty */ + for (i = 0; i < NFS4_DEVICE_ID_HASH_SIZE; i++) + BUG_ON(!hlist_empty(&local->dc_deviceids[i])); + clp->cl_devid_cache = NULL; + spin_unlock(&clp->cl_lock); + kfree(local); + } +} +EXPORT_SYMBOL_GPL(pnfs_put_deviceid_cache); diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h new file mode 100644 index 000000000000..e12367d50489 --- /dev/null +++ b/fs/nfs/pnfs.h @@ -0,0 +1,189 @@ +/* + * pNFS client data structures. + * + * Copyright (c) 2002 + * The Regents of the University of Michigan + * All Rights Reserved + * + * Dean Hildebrand <dhildebz@umich.edu> + * + * Permission is granted to use, copy, create derivative works, and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the University of Michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. If + * the above copyright notice or any other identification of the + * University of Michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * This software is provided as is, without representation or warranty + * of any kind either express or implied, including without limitation + * the implied warranties of merchantability, fitness for a particular + * purpose, or noninfringement. The Regents of the University of + * Michigan shall not be liable for any damages, including special, + * indirect, incidental, or consequential damages, with respect to any + * claim arising out of or in connection with the use of the software, + * even if it has been or is hereafter advised of the possibility of + * such damages. + */ + +#ifndef FS_NFS_PNFS_H +#define FS_NFS_PNFS_H + +struct pnfs_layout_segment { + struct list_head fi_list; + struct pnfs_layout_range range; + struct kref kref; + struct pnfs_layout_hdr *layout; +}; + +#ifdef CONFIG_NFS_V4_1 + +#define LAYOUT_NFSV4_1_MODULE_PREFIX "nfs-layouttype4" + +enum { + NFS_LAYOUT_RO_FAILED = 0, /* get ro layout failed stop trying */ + NFS_LAYOUT_RW_FAILED, /* get rw layout failed stop trying */ + NFS_LAYOUT_STATEID_SET, /* have a valid layout stateid */ +}; + +/* Per-layout driver specific registration structure */ +struct pnfs_layoutdriver_type { + struct list_head pnfs_tblid; + const u32 id; + const char *name; + struct module *owner; + int (*set_layoutdriver) (struct nfs_server *); + int (*clear_layoutdriver) (struct nfs_server *); + struct pnfs_layout_segment * (*alloc_lseg) (struct pnfs_layout_hdr *layoutid, struct nfs4_layoutget_res *lgr); + void (*free_lseg) (struct pnfs_layout_segment *lseg); +}; + +struct pnfs_layout_hdr { + unsigned long refcount; + struct list_head layouts; /* other client layouts */ + struct list_head segs; /* layout segments list */ + seqlock_t seqlock; /* Protects the stateid */ + nfs4_stateid stateid; + unsigned long state; + struct inode *inode; +}; + +struct pnfs_device { + struct nfs4_deviceid dev_id; + unsigned int layout_type; + unsigned int mincount; + struct page **pages; + void *area; + unsigned int pgbase; + unsigned int pglen; +}; + +/* + * Device ID RCU cache. A device ID is unique per client ID and layout type. + */ +#define NFS4_DEVICE_ID_HASH_BITS 5 +#define NFS4_DEVICE_ID_HASH_SIZE (1 << NFS4_DEVICE_ID_HASH_BITS) +#define NFS4_DEVICE_ID_HASH_MASK (NFS4_DEVICE_ID_HASH_SIZE - 1) + +static inline u32 +nfs4_deviceid_hash(struct nfs4_deviceid *id) +{ + unsigned char *cptr = (unsigned char *)id->data; + unsigned int nbytes = NFS4_DEVICEID4_SIZE; + u32 x = 0; + + while (nbytes--) { + x *= 37; + x += *cptr++; + } + return x & NFS4_DEVICE_ID_HASH_MASK; +} + +struct pnfs_deviceid_node { + struct hlist_node de_node; + struct nfs4_deviceid de_id; + atomic_t de_ref; +}; + +struct pnfs_deviceid_cache { + spinlock_t dc_lock; + atomic_t dc_ref; + void (*dc_free_callback)(struct pnfs_deviceid_node *); + struct hlist_head dc_deviceids[NFS4_DEVICE_ID_HASH_SIZE]; +}; + +extern int pnfs_alloc_init_deviceid_cache(struct nfs_client *, + void (*free_callback)(struct pnfs_deviceid_node *)); +extern void pnfs_put_deviceid_cache(struct nfs_client *); +extern struct pnfs_deviceid_node *pnfs_find_get_deviceid( + struct pnfs_deviceid_cache *, + struct nfs4_deviceid *); +extern struct pnfs_deviceid_node *pnfs_add_deviceid( + struct pnfs_deviceid_cache *, + struct pnfs_deviceid_node *); +extern void pnfs_put_deviceid(struct pnfs_deviceid_cache *c, + struct pnfs_deviceid_node *devid); + +extern int pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *); +extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *); + +/* nfs4proc.c */ +extern int nfs4_proc_getdeviceinfo(struct nfs_server *server, + struct pnfs_device *dev); +extern int nfs4_proc_layoutget(struct nfs4_layoutget *lgp); + +/* pnfs.c */ +struct pnfs_layout_segment * +pnfs_update_layout(struct inode *ino, struct nfs_open_context *ctx, + enum pnfs_iomode access_type); +void set_pnfs_layoutdriver(struct nfs_server *, u32 id); +void unset_pnfs_layoutdriver(struct nfs_server *); +int pnfs_layout_process(struct nfs4_layoutget *lgp); +void pnfs_destroy_layout(struct nfs_inode *); +void pnfs_destroy_all_layouts(struct nfs_client *); +void put_layout_hdr(struct inode *inode); +void pnfs_get_layout_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo, + struct nfs4_state *open_state); + + +static inline int lo_fail_bit(u32 iomode) +{ + return iomode == IOMODE_RW ? + NFS_LAYOUT_RW_FAILED : NFS_LAYOUT_RO_FAILED; +} + +/* Return true if a layout driver is being used for this mountpoint */ +static inline int pnfs_enabled_sb(struct nfs_server *nfss) +{ + return nfss->pnfs_curr_ld != NULL; +} + +#else /* CONFIG_NFS_V4_1 */ + +static inline void pnfs_destroy_all_layouts(struct nfs_client *clp) +{ +} + +static inline void pnfs_destroy_layout(struct nfs_inode *nfsi) +{ +} + +static inline struct pnfs_layout_segment * +pnfs_update_layout(struct inode *ino, struct nfs_open_context *ctx, + enum pnfs_iomode access_type) +{ + return NULL; +} + +static inline void set_pnfs_layoutdriver(struct nfs_server *s, u32 id) +{ +} + +static inline void unset_pnfs_layoutdriver(struct nfs_server *s) +{ +} + +#endif /* CONFIG_NFS_V4_1 */ + +#endif /* FS_NFS_PNFS_H */ diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 79859c81a943..e4b62c6f5a6e 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -25,6 +25,7 @@ #include "internal.h" #include "iostat.h" #include "fscache.h" +#include "pnfs.h" #define NFSDBG_FACILITY NFSDBG_PAGECACHE @@ -120,6 +121,7 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, len = nfs_page_length(page); if (len == 0) return nfs_return_empty_page(page); + pnfs_update_layout(inode, ctx, IOMODE_READ); new = nfs_create_request(ctx, inode, page, 0, len); if (IS_ERR(new)) { unlock_page(page); @@ -624,6 +626,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping, if (ret == 0) goto read_complete; /* all pages were read */ + pnfs_update_layout(inode, desc.ctx, IOMODE_READ); if (rsize < PAGE_CACHE_SIZE) nfs_pageio_init(&pgio, inode, nfs_pagein_multi, rsize, 0); else diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 3600ec700d58..3c045044fca2 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -39,7 +39,6 @@ #include <linux/nfs_mount.h> #include <linux/nfs4_mount.h> #include <linux/lockd/bind.h> -#include <linux/smp_lock.h> #include <linux/seq_file.h> #include <linux/mount.h> #include <linux/mnt_namespace.h> @@ -67,6 +66,12 @@ #define NFSDBG_FACILITY NFSDBG_VFS +#ifdef CONFIG_NFS_V3 +#define NFS_DEFAULT_VERSION 3 +#else +#define NFS_DEFAULT_VERSION 2 +#endif + enum { /* Mount options that take no arguments */ Opt_soft, Opt_hard, @@ -260,8 +265,8 @@ static int nfs_statfs(struct dentry *, struct kstatfs *); static int nfs_show_options(struct seq_file *, struct vfsmount *); static int nfs_show_stats(struct seq_file *, struct vfsmount *); static int nfs_get_sb(struct file_system_type *, int, const char *, void *, struct vfsmount *); -static int nfs_xdev_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt); +static struct dentry *nfs_xdev_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data); static void nfs_put_super(struct super_block *); static void nfs_kill_super(struct super_block *); static int nfs_remount(struct super_block *sb, int *flags, char *raw_data); @@ -277,7 +282,7 @@ static struct file_system_type nfs_fs_type = { struct file_system_type nfs_xdev_fs_type = { .owner = THIS_MODULE, .name = "nfs", - .get_sb = nfs_xdev_get_sb, + .mount = nfs_xdev_mount, .kill_sb = nfs_kill_super, .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, }; @@ -302,14 +307,14 @@ static int nfs4_try_mount(int flags, const char *dev_name, struct nfs_parsed_mount_data *data, struct vfsmount *mnt); static int nfs4_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt); -static int nfs4_remote_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt); -static int nfs4_xdev_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt); +static struct dentry *nfs4_remote_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data); +static struct dentry *nfs4_xdev_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data); static int nfs4_referral_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt); -static int nfs4_remote_referral_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt); +static struct dentry *nfs4_remote_referral_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data); static void nfs4_kill_super(struct super_block *sb); static struct file_system_type nfs4_fs_type = { @@ -323,7 +328,7 @@ static struct file_system_type nfs4_fs_type = { static struct file_system_type nfs4_remote_fs_type = { .owner = THIS_MODULE, .name = "nfs4", - .get_sb = nfs4_remote_get_sb, + .mount = nfs4_remote_mount, .kill_sb = nfs4_kill_super, .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, }; @@ -331,7 +336,7 @@ static struct file_system_type nfs4_remote_fs_type = { struct file_system_type nfs4_xdev_fs_type = { .owner = THIS_MODULE, .name = "nfs4", - .get_sb = nfs4_xdev_get_sb, + .mount = nfs4_xdev_mount, .kill_sb = nfs4_kill_super, .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, }; @@ -339,7 +344,7 @@ struct file_system_type nfs4_xdev_fs_type = { static struct file_system_type nfs4_remote_referral_fs_type = { .owner = THIS_MODULE, .name = "nfs4", - .get_sb = nfs4_remote_referral_get_sb, + .mount = nfs4_remote_referral_mount, .kill_sb = nfs4_kill_super, .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, }; @@ -2277,7 +2282,7 @@ static int nfs_get_sb(struct file_system_type *fs_type, }; int error = -ENOMEM; - data = nfs_alloc_parsed_mount_data(3); + data = nfs_alloc_parsed_mount_data(NFS_DEFAULT_VERSION); mntfh = nfs_alloc_fhandle(); if (data == NULL || mntfh == NULL) goto out_free_fh; @@ -2397,9 +2402,9 @@ static void nfs_kill_super(struct super_block *s) /* * Clone an NFS2/3 server record on xdev traversal (FSID-change) */ -static int nfs_xdev_get_sb(struct file_system_type *fs_type, int flags, - const char *dev_name, void *raw_data, - struct vfsmount *mnt) +static struct dentry * +nfs_xdev_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *raw_data) { struct nfs_clone_mount *data = raw_data; struct super_block *s; @@ -2411,7 +2416,7 @@ static int nfs_xdev_get_sb(struct file_system_type *fs_type, int flags, }; int error; - dprintk("--> nfs_xdev_get_sb()\n"); + dprintk("--> nfs_xdev_mount()\n"); /* create a new volume representation */ server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr); @@ -2458,28 +2463,26 @@ static int nfs_xdev_get_sb(struct file_system_type *fs_type, int flags, } s->s_flags |= MS_ACTIVE; - mnt->mnt_sb = s; - mnt->mnt_root = mntroot; /* clone any lsm security options from the parent to the new sb */ security_sb_clone_mnt_opts(data->sb, s); - dprintk("<-- nfs_xdev_get_sb() = 0\n"); - return 0; + dprintk("<-- nfs_xdev_mount() = 0\n"); + return mntroot; out_err_nosb: nfs_free_server(server); out_err_noserver: - dprintk("<-- nfs_xdev_get_sb() = %d [error]\n", error); - return error; + dprintk("<-- nfs_xdev_mount() = %d [error]\n", error); + return ERR_PTR(error); error_splat_super: if (server && !s->s_root) bdi_unregister(&server->backing_dev_info); error_splat_bdi: deactivate_locked_super(s); - dprintk("<-- nfs_xdev_get_sb() = %d [splat]\n", error); - return error; + dprintk("<-- nfs_xdev_mount() = %d [splat]\n", error); + return ERR_PTR(error); } #ifdef CONFIG_NFS_V4 @@ -2649,8 +2652,9 @@ out_no_address: /* * Get the superblock for the NFS4 root partition */ -static int nfs4_remote_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt) +static struct dentry * +nfs4_remote_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *raw_data) { struct nfs_parsed_mount_data *data = raw_data; struct super_block *s; @@ -2714,15 +2718,16 @@ static int nfs4_remote_get_sb(struct file_system_type *fs_type, goto error_splat_root; s->s_flags |= MS_ACTIVE; - mnt->mnt_sb = s; - mnt->mnt_root = mntroot; - error = 0; + + security_free_mnt_opts(&data->lsm_opts); + nfs_free_fhandle(mntfh); + return mntroot; out: security_free_mnt_opts(&data->lsm_opts); out_free_fh: nfs_free_fhandle(mntfh); - return error; + return ERR_PTR(error); out_free: nfs_free_server(server); @@ -2968,9 +2973,9 @@ static void nfs4_kill_super(struct super_block *sb) /* * Clone an NFS4 server record on xdev traversal (FSID-change) */ -static int nfs4_xdev_get_sb(struct file_system_type *fs_type, int flags, - const char *dev_name, void *raw_data, - struct vfsmount *mnt) +static struct dentry * +nfs4_xdev_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *raw_data) { struct nfs_clone_mount *data = raw_data; struct super_block *s; @@ -2982,7 +2987,7 @@ static int nfs4_xdev_get_sb(struct file_system_type *fs_type, int flags, }; int error; - dprintk("--> nfs4_xdev_get_sb()\n"); + dprintk("--> nfs4_xdev_mount()\n"); /* create a new volume representation */ server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr); @@ -3029,32 +3034,30 @@ static int nfs4_xdev_get_sb(struct file_system_type *fs_type, int flags, } s->s_flags |= MS_ACTIVE; - mnt->mnt_sb = s; - mnt->mnt_root = mntroot; security_sb_clone_mnt_opts(data->sb, s); - dprintk("<-- nfs4_xdev_get_sb() = 0\n"); - return 0; + dprintk("<-- nfs4_xdev_mount() = 0\n"); + return mntroot; out_err_nosb: nfs_free_server(server); out_err_noserver: - dprintk("<-- nfs4_xdev_get_sb() = %d [error]\n", error); - return error; + dprintk("<-- nfs4_xdev_mount() = %d [error]\n", error); + return ERR_PTR(error); error_splat_super: if (server && !s->s_root) bdi_unregister(&server->backing_dev_info); error_splat_bdi: deactivate_locked_super(s); - dprintk("<-- nfs4_xdev_get_sb() = %d [splat]\n", error); - return error; + dprintk("<-- nfs4_xdev_mount() = %d [splat]\n", error); + return ERR_PTR(error); } -static int nfs4_remote_referral_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data, - struct vfsmount *mnt) +static struct dentry * +nfs4_remote_referral_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *raw_data) { struct nfs_clone_mount *data = raw_data; struct super_block *s; @@ -3118,14 +3121,12 @@ static int nfs4_remote_referral_get_sb(struct file_system_type *fs_type, } s->s_flags |= MS_ACTIVE; - mnt->mnt_sb = s; - mnt->mnt_root = mntroot; security_sb_clone_mnt_opts(data->sb, s); nfs_free_fhandle(mntfh); dprintk("<-- nfs4_referral_get_sb() = 0\n"); - return 0; + return mntroot; out_err_nosb: nfs_free_server(server); @@ -3133,7 +3134,7 @@ out_err_noserver: nfs_free_fhandle(mntfh); out_err_nofh: dprintk("<-- nfs4_referral_get_sb() = %d [error]\n", error); - return error; + return ERR_PTR(error); error_splat_super: if (server && !s->s_root) @@ -3142,7 +3143,7 @@ error_splat_bdi: deactivate_locked_super(s); nfs_free_fhandle(mntfh); dprintk("<-- nfs4_referral_get_sb() = %d [splat]\n", error); - return error; + return ERR_PTR(error); } /* diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index 9a16bad5d2ea..7bdec8531400 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -444,9 +444,9 @@ nfs_async_rename(struct inode *old_dir, struct inode *new_dir, /* set up nfs_renamedata */ data->old_dir = old_dir; - atomic_inc(&old_dir->i_count); + ihold(old_dir); data->new_dir = new_dir; - atomic_inc(&new_dir->i_count); + ihold(new_dir); data->old_dentry = dget(old_dentry); data->new_dentry = dget(new_dentry); nfs_fattr_init(&data->old_fattr); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 605e292501f4..4c14c17a5276 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -290,9 +290,7 @@ static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, st nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1); nfs_pageio_cond_complete(pgio, page->index); - ret = nfs_page_async_flush(pgio, page, - wbc->sync_mode == WB_SYNC_NONE || - wbc->nonblocking != 0); + ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE); if (ret == -EAGAIN) { redirty_page_for_writepage(wbc, page); ret = 0; diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index 7cf4ddafb4ab..18b3e8975fe0 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -2,7 +2,6 @@ config NFSD tristate "NFS server support" depends on INET depends on FILE_LOCKING - depends on BKL # fix as soon as lockd is done select LOCKD select SUNRPC select EXPORTFS @@ -29,6 +28,18 @@ config NFSD If unsure, say N. +config NFSD_DEPRECATED + bool "Include support for deprecated syscall interface to NFSD" + depends on NFSD + default y + help + The syscall interface to nfsd was obsoleted in 2.6.0 by a new + filesystem based interface. The old interface is due for removal + in 2.6.40. If you wish to remove the interface before then + say N. + + In unsure, say Y. + config NFSD_V2_ACL bool depends on NFSD diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index c2a4f71d87dd..c0fcb7ab7f6d 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -28,9 +28,6 @@ typedef struct auth_domain svc_client; typedef struct svc_export svc_export; -static void exp_do_unexport(svc_export *unexp); -static int exp_verify_string(char *cp, int max); - /* * We have two caches. * One maps client+vfsmnt+dentry to export options - the export map @@ -802,6 +799,7 @@ exp_find_key(svc_client *clp, int fsid_type, u32 *fsidv, struct cache_req *reqp) return ek; } +#ifdef CONFIG_NFSD_DEPRECATED static int exp_set_key(svc_client *clp, int fsid_type, u32 *fsidv, struct svc_export *exp) { @@ -852,6 +850,7 @@ exp_get_fsid_key(svc_client *clp, int fsid) return exp_find_key(clp, FSID_NUM, fsidv, NULL); } +#endif static svc_export *exp_get_by_name(svc_client *clp, const struct path *path, struct cache_req *reqp) @@ -893,6 +892,7 @@ static struct svc_export *exp_parent(svc_client *clp, struct path *path) return exp; } +#ifdef CONFIG_NFSD_DEPRECATED /* * Hashtable locking. Write locks are placed only by user processes * wanting to modify export information. @@ -925,6 +925,19 @@ exp_writeunlock(void) { up_write(&hash_sem); } +#else + +/* hash_sem not needed once deprecated interface is removed */ +void exp_readlock(void) {} +static inline void exp_writelock(void){} +void exp_readunlock(void) {} +static inline void exp_writeunlock(void){} + +#endif + +#ifdef CONFIG_NFSD_DEPRECATED +static void exp_do_unexport(svc_export *unexp); +static int exp_verify_string(char *cp, int max); static void exp_fsid_unhash(struct svc_export *exp) { @@ -935,10 +948,9 @@ static void exp_fsid_unhash(struct svc_export *exp) ek = exp_get_fsid_key(exp->ex_client, exp->ex_fsid); if (!IS_ERR(ek)) { - ek->h.expiry_time = get_seconds()-1; + sunrpc_invalidate(&ek->h, &svc_expkey_cache); cache_put(&ek->h, &svc_expkey_cache); } - svc_expkey_cache.nextcheck = get_seconds(); } static int exp_fsid_hash(svc_client *clp, struct svc_export *exp) @@ -973,10 +985,9 @@ static void exp_unhash(struct svc_export *exp) ek = exp_get_key(exp->ex_client, inode->i_sb->s_dev, inode->i_ino); if (!IS_ERR(ek)) { - ek->h.expiry_time = get_seconds()-1; + sunrpc_invalidate(&ek->h, &svc_expkey_cache); cache_put(&ek->h, &svc_expkey_cache); } - svc_expkey_cache.nextcheck = get_seconds(); } /* @@ -1097,8 +1108,7 @@ out: static void exp_do_unexport(svc_export *unexp) { - unexp->h.expiry_time = get_seconds()-1; - svc_export_cache.nextcheck = get_seconds(); + sunrpc_invalidate(&unexp->h, &svc_export_cache); exp_unhash(unexp); exp_fsid_unhash(unexp); } @@ -1150,6 +1160,7 @@ out_unlock: exp_writeunlock(); return err; } +#endif /* CONFIG_NFSD_DEPRECATED */ /* * Obtain the root fh on behalf of a client. @@ -1459,25 +1470,43 @@ static void show_secinfo_flags(struct seq_file *m, int flags) show_expflags(m, flags, NFSEXP_SECINFO_FLAGS); } +static bool secinfo_flags_equal(int f, int g) +{ + f &= NFSEXP_SECINFO_FLAGS; + g &= NFSEXP_SECINFO_FLAGS; + return f == g; +} + +static int show_secinfo_run(struct seq_file *m, struct exp_flavor_info **fp, struct exp_flavor_info *end) +{ + int flags; + + flags = (*fp)->flags; + seq_printf(m, ",sec=%d", (*fp)->pseudoflavor); + (*fp)++; + while (*fp != end && secinfo_flags_equal(flags, (*fp)->flags)) { + seq_printf(m, ":%d", (*fp)->pseudoflavor); + (*fp)++; + } + return flags; +} + static void show_secinfo(struct seq_file *m, struct svc_export *exp) { struct exp_flavor_info *f; struct exp_flavor_info *end = exp->ex_flavors + exp->ex_nflavors; - int lastflags = 0, first = 0; + int flags; if (exp->ex_nflavors == 0) return; - for (f = exp->ex_flavors; f < end; f++) { - if (first || f->flags != lastflags) { - if (!first) - show_secinfo_flags(m, lastflags); - seq_printf(m, ",sec=%d", f->pseudoflavor); - lastflags = f->flags; - } else { - seq_printf(m, ":%d", f->pseudoflavor); - } + f = exp->ex_flavors; + flags = show_secinfo_run(m, &f, end); + if (!secinfo_flags_equal(flags, exp->ex_flags)) + show_secinfo_flags(m, flags); + while (f != end) { + flags = show_secinfo_run(m, &f, end); + show_secinfo_flags(m, flags); } - show_secinfo_flags(m, lastflags); } static void exp_flags(struct seq_file *m, int flag, int fsid, @@ -1532,6 +1561,7 @@ const struct seq_operations nfs_exports_op = { .show = e_show, }; +#ifdef CONFIG_NFSD_DEPRECATED /* * Add or modify a client. * Change requests may involve the list of host addresses. The list of @@ -1563,7 +1593,7 @@ exp_addclient(struct nfsctl_client *ncp) /* Insert client into hashtable. */ for (i = 0; i < ncp->cl_naddr; i++) { ipv6_addr_set_v4mapped(ncp->cl_addrlist[i].s_addr, &addr6); - auth_unix_add_addr(&addr6, dom); + auth_unix_add_addr(&init_net, &addr6, dom); } auth_unix_forget_old(dom); auth_domain_put(dom); @@ -1621,6 +1651,7 @@ exp_verify_string(char *cp, int max) printk(KERN_NOTICE "nfsd: couldn't validate string %s\n", cp); return 0; } +#endif /* CONFIG_NFSD_DEPRECATED */ /* * Initialize the exports module. diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 988cbb3a19b6..143da2eecd7b 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -41,7 +41,6 @@ #define NFSPROC4_CB_NULL 0 #define NFSPROC4_CB_COMPOUND 1 -#define NFS4_STATEID_SIZE 16 /* Index of predefined Linux callback client operations */ @@ -248,10 +247,11 @@ encode_cb_recall(struct xdr_stream *xdr, struct nfs4_delegation *dp, } static void -encode_cb_sequence(struct xdr_stream *xdr, struct nfsd4_cb_sequence *args, +encode_cb_sequence(struct xdr_stream *xdr, struct nfsd4_callback *cb, struct nfs4_cb_compound_hdr *hdr) { __be32 *p; + struct nfsd4_session *ses = cb->cb_clp->cl_cb_session; if (hdr->minorversion == 0) return; @@ -259,8 +259,8 @@ encode_cb_sequence(struct xdr_stream *xdr, struct nfsd4_cb_sequence *args, RESERVE_SPACE(1 + NFS4_MAX_SESSIONID_LEN + 20); WRITE32(OP_CB_SEQUENCE); - WRITEMEM(args->cbs_clp->cl_sessionid.data, NFS4_MAX_SESSIONID_LEN); - WRITE32(args->cbs_clp->cl_cb_seq_nr); + WRITEMEM(ses->se_sessionid.data, NFS4_MAX_SESSIONID_LEN); + WRITE32(ses->se_cb_seq_nr); WRITE32(0); /* slotid, always 0 */ WRITE32(0); /* highest slotid always 0 */ WRITE32(0); /* cachethis always 0 */ @@ -280,18 +280,18 @@ nfs4_xdr_enc_cb_null(struct rpc_rqst *req, __be32 *p) static int nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, __be32 *p, - struct nfs4_rpc_args *rpc_args) + struct nfsd4_callback *cb) { struct xdr_stream xdr; - struct nfs4_delegation *args = rpc_args->args_op; + struct nfs4_delegation *args = cb->cb_op; struct nfs4_cb_compound_hdr hdr = { - .ident = args->dl_ident, - .minorversion = rpc_args->args_seq.cbs_minorversion, + .ident = cb->cb_clp->cl_cb_ident, + .minorversion = cb->cb_minorversion, }; xdr_init_encode(&xdr, &req->rq_snd_buf, p); encode_cb_compound_hdr(&xdr, &hdr); - encode_cb_sequence(&xdr, &rpc_args->args_seq, &hdr); + encode_cb_sequence(&xdr, cb, &hdr); encode_cb_recall(&xdr, args, &hdr); encode_cb_nops(&hdr); return 0; @@ -339,15 +339,16 @@ decode_cb_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected) * with a single slot. */ static int -decode_cb_sequence(struct xdr_stream *xdr, struct nfsd4_cb_sequence *res, +decode_cb_sequence(struct xdr_stream *xdr, struct nfsd4_callback *cb, struct rpc_rqst *rqstp) { + struct nfsd4_session *ses = cb->cb_clp->cl_cb_session; struct nfs4_sessionid id; int status; u32 dummy; __be32 *p; - if (res->cbs_minorversion == 0) + if (cb->cb_minorversion == 0) return 0; status = decode_cb_op_hdr(xdr, OP_CB_SEQUENCE); @@ -363,13 +364,12 @@ decode_cb_sequence(struct xdr_stream *xdr, struct nfsd4_cb_sequence *res, READ_BUF(NFS4_MAX_SESSIONID_LEN + 16); memcpy(id.data, p, NFS4_MAX_SESSIONID_LEN); p += XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN); - if (memcmp(id.data, res->cbs_clp->cl_sessionid.data, - NFS4_MAX_SESSIONID_LEN)) { + if (memcmp(id.data, ses->se_sessionid.data, NFS4_MAX_SESSIONID_LEN)) { dprintk("%s Invalid session id\n", __func__); goto out; } READ32(dummy); - if (dummy != res->cbs_clp->cl_cb_seq_nr) { + if (dummy != ses->se_cb_seq_nr) { dprintk("%s Invalid sequence number\n", __func__); goto out; } @@ -393,7 +393,7 @@ nfs4_xdr_dec_cb_null(struct rpc_rqst *req, __be32 *p) static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp, __be32 *p, - struct nfsd4_cb_sequence *seq) + struct nfsd4_callback *cb) { struct xdr_stream xdr; struct nfs4_cb_compound_hdr hdr; @@ -403,8 +403,8 @@ nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp, __be32 *p, status = decode_cb_compound_hdr(&xdr, &hdr); if (status) goto out; - if (seq) { - status = decode_cb_sequence(&xdr, seq, rqstp); + if (cb) { + status = decode_cb_sequence(&xdr, cb, rqstp); if (status) goto out; } @@ -473,30 +473,34 @@ static int max_cb_time(void) /* Reference counting, callback cleanup, etc., all look racy as heck. * And why is cl_cb_set an atomic? */ -int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *cb) +int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn) { struct rpc_timeout timeparms = { .to_initval = max_cb_time(), .to_retries = 0, }; struct rpc_create_args args = { - .protocol = XPRT_TRANSPORT_TCP, - .address = (struct sockaddr *) &cb->cb_addr, - .addrsize = cb->cb_addrlen, + .net = &init_net, + .address = (struct sockaddr *) &conn->cb_addr, + .addrsize = conn->cb_addrlen, .timeout = &timeparms, .program = &cb_program, - .prognumber = cb->cb_prog, .version = 0, .authflavor = clp->cl_flavor, .flags = (RPC_CLNT_CREATE_NOPING | RPC_CLNT_CREATE_QUIET), - .client_name = clp->cl_principal, }; struct rpc_clnt *client; - if (!clp->cl_principal && (clp->cl_flavor >= RPC_AUTH_GSS_KRB5)) - return -EINVAL; - if (cb->cb_minorversion) { - args.bc_xprt = cb->cb_xprt; + if (clp->cl_minorversion == 0) { + if (!clp->cl_principal && (clp->cl_flavor >= RPC_AUTH_GSS_KRB5)) + return -EINVAL; + args.client_name = clp->cl_principal; + args.prognumber = conn->cb_prog, + args.protocol = XPRT_TRANSPORT_TCP; + clp->cl_cb_ident = conn->cb_ident; + } else { + args.bc_xprt = conn->cb_xprt; + args.prognumber = clp->cl_cb_session->se_cb_prog; args.protocol = XPRT_TRANSPORT_BC_TCP; } /* Create RPC client */ @@ -506,7 +510,7 @@ int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *cb) PTR_ERR(client)); return PTR_ERR(client); } - nfsd4_set_callback_client(clp, client); + clp->cl_cb_client = client; return 0; } @@ -519,7 +523,7 @@ static void warn_no_callback_path(struct nfs4_client *clp, int reason) static void nfsd4_cb_probe_done(struct rpc_task *task, void *calldata) { - struct nfs4_client *clp = calldata; + struct nfs4_client *clp = container_of(calldata, struct nfs4_client, cl_cb_null); if (task->tk_status) warn_no_callback_path(clp, task->tk_status); @@ -528,6 +532,8 @@ static void nfsd4_cb_probe_done(struct rpc_task *task, void *calldata) } static const struct rpc_call_ops nfsd4_cb_probe_ops = { + /* XXX: release method to ensure we set the cb channel down if + * necessary on early failure? */ .rpc_call_done = nfsd4_cb_probe_done, }; @@ -543,38 +549,42 @@ int set_callback_cred(void) return 0; } +static struct workqueue_struct *callback_wq; -void do_probe_callback(struct nfs4_client *clp) +static void do_probe_callback(struct nfs4_client *clp) { - struct rpc_message msg = { - .rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL], - .rpc_argp = clp, - .rpc_cred = callback_cred - }; - int status; + struct nfsd4_callback *cb = &clp->cl_cb_null; - status = rpc_call_async(clp->cl_cb_client, &msg, - RPC_TASK_SOFT | RPC_TASK_SOFTCONN, - &nfsd4_cb_probe_ops, (void *)clp); - if (status) - warn_no_callback_path(clp, status); + cb->cb_op = NULL; + cb->cb_clp = clp; + + cb->cb_msg.rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL]; + cb->cb_msg.rpc_argp = NULL; + cb->cb_msg.rpc_resp = NULL; + cb->cb_msg.rpc_cred = callback_cred; + + cb->cb_ops = &nfsd4_cb_probe_ops; + + queue_work(callback_wq, &cb->cb_work); } /* - * Set up the callback client and put a NFSPROC4_CB_NULL on the wire... + * Poke the callback thread to process any updates to the callback + * parameters, and send a null probe. */ -void nfsd4_probe_callback(struct nfs4_client *clp, struct nfs4_cb_conn *cb) +void nfsd4_probe_callback(struct nfs4_client *clp) { - int status; + set_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_cb_flags); + do_probe_callback(clp); +} +void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *conn) +{ BUG_ON(atomic_read(&clp->cl_cb_set)); - status = setup_callback_client(clp, cb); - if (status) { - warn_no_callback_path(clp, status); - return; - } - do_probe_callback(clp); + spin_lock(&clp->cl_lock); + memcpy(&clp->cl_cb_conn, conn, sizeof(struct nfs4_cb_conn)); + spin_unlock(&clp->cl_lock); } /* @@ -585,8 +595,7 @@ void nfsd4_probe_callback(struct nfs4_client *clp, struct nfs4_cb_conn *cb) static int nfsd41_cb_setup_sequence(struct nfs4_client *clp, struct rpc_task *task) { - struct nfs4_rpc_args *args = task->tk_msg.rpc_argp; - u32 *ptr = (u32 *)clp->cl_sessionid.data; + u32 *ptr = (u32 *)clp->cl_cb_session->se_sessionid.data; int status = 0; dprintk("%s: %u:%u:%u:%u\n", __func__, @@ -598,14 +607,6 @@ static int nfsd41_cb_setup_sequence(struct nfs4_client *clp, status = -EAGAIN; goto out; } - - /* - * We'll need the clp during XDR encoding and decoding, - * and the sequence during decoding to verify the reply - */ - args->args_seq.cbs_clp = clp; - task->tk_msg.rpc_resp = &args->args_seq; - out: dprintk("%s status=%d\n", __func__, status); return status; @@ -617,13 +618,13 @@ out: */ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata) { - struct nfs4_delegation *dp = calldata; + struct nfsd4_callback *cb = calldata; + struct nfs4_delegation *dp = container_of(cb, struct nfs4_delegation, dl_recall); struct nfs4_client *clp = dp->dl_client; - struct nfs4_rpc_args *args = task->tk_msg.rpc_argp; - u32 minorversion = clp->cl_cb_conn.cb_minorversion; + u32 minorversion = clp->cl_minorversion; int status = 0; - args->args_seq.cbs_minorversion = minorversion; + cb->cb_minorversion = minorversion; if (minorversion) { status = nfsd41_cb_setup_sequence(clp, task); if (status) { @@ -640,19 +641,20 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata) static void nfsd4_cb_done(struct rpc_task *task, void *calldata) { - struct nfs4_delegation *dp = calldata; + struct nfsd4_callback *cb = calldata; + struct nfs4_delegation *dp = container_of(cb, struct nfs4_delegation, dl_recall); struct nfs4_client *clp = dp->dl_client; dprintk("%s: minorversion=%d\n", __func__, - clp->cl_cb_conn.cb_minorversion); + clp->cl_minorversion); - if (clp->cl_cb_conn.cb_minorversion) { + if (clp->cl_minorversion) { /* No need for lock, access serialized in nfsd4_cb_prepare */ - ++clp->cl_cb_seq_nr; + ++clp->cl_cb_session->se_cb_seq_nr; clear_bit(0, &clp->cl_cb_slot_busy); rpc_wake_up_next(&clp->cl_cb_waitq); dprintk("%s: freed slot, new seqid=%d\n", __func__, - clp->cl_cb_seq_nr); + clp->cl_cb_session->se_cb_seq_nr); /* We're done looking into the sequence information */ task->tk_msg.rpc_resp = NULL; @@ -662,7 +664,8 @@ static void nfsd4_cb_done(struct rpc_task *task, void *calldata) static void nfsd4_cb_recall_done(struct rpc_task *task, void *calldata) { - struct nfs4_delegation *dp = calldata; + struct nfsd4_callback *cb = calldata; + struct nfs4_delegation *dp = container_of(cb, struct nfs4_delegation, dl_recall); struct nfs4_client *clp = dp->dl_client; struct rpc_clnt *current_rpc_client = clp->cl_cb_client; @@ -707,7 +710,8 @@ static void nfsd4_cb_recall_done(struct rpc_task *task, void *calldata) static void nfsd4_cb_recall_release(void *calldata) { - struct nfs4_delegation *dp = calldata; + struct nfsd4_callback *cb = calldata; + struct nfs4_delegation *dp = container_of(cb, struct nfs4_delegation, dl_recall); nfs4_put_delegation(dp); } @@ -718,8 +722,6 @@ static const struct rpc_call_ops nfsd4_cb_recall_ops = { .rpc_release = nfsd4_cb_recall_release, }; -static struct workqueue_struct *callback_wq; - int nfsd4_create_callback_queue(void) { callback_wq = create_singlethread_workqueue("nfsd4_callbacks"); @@ -734,57 +736,88 @@ void nfsd4_destroy_callback_queue(void) } /* must be called under the state lock */ -void nfsd4_set_callback_client(struct nfs4_client *clp, struct rpc_clnt *new) +void nfsd4_shutdown_callback(struct nfs4_client *clp) { - struct rpc_clnt *old = clp->cl_cb_client; - - clp->cl_cb_client = new; + set_bit(NFSD4_CLIENT_KILL, &clp->cl_cb_flags); /* - * After this, any work that saw the old value of cl_cb_client will - * be gone: + * Note this won't actually result in a null callback; + * instead, nfsd4_do_callback_rpc() will detect the killed + * client, destroy the rpc client, and stop: */ + do_probe_callback(clp); flush_workqueue(callback_wq); - /* So we can safely shut it down: */ - if (old) - rpc_shutdown_client(old); } -/* - * called with dp->dl_count inc'ed. - */ -static void _nfsd4_cb_recall(struct nfs4_delegation *dp) +void nfsd4_release_cb(struct nfsd4_callback *cb) { - struct nfs4_client *clp = dp->dl_client; - struct rpc_clnt *clnt = clp->cl_cb_client; - struct nfs4_rpc_args *args = &dp->dl_recall.cb_args; - struct rpc_message msg = { - .rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_RECALL], - .rpc_cred = callback_cred - }; + if (cb->cb_ops->rpc_release) + cb->cb_ops->rpc_release(cb); +} - if (clnt == NULL) { - nfs4_put_delegation(dp); - return; /* Client is shutting down; give up. */ +void nfsd4_process_cb_update(struct nfsd4_callback *cb) +{ + struct nfs4_cb_conn conn; + struct nfs4_client *clp = cb->cb_clp; + int err; + + /* + * This is either an update, or the client dying; in either case, + * kill the old client: + */ + if (clp->cl_cb_client) { + rpc_shutdown_client(clp->cl_cb_client); + clp->cl_cb_client = NULL; } + if (test_bit(NFSD4_CLIENT_KILL, &clp->cl_cb_flags)) + return; + spin_lock(&clp->cl_lock); + /* + * Only serialized callback code is allowed to clear these + * flags; main nfsd code can only set them: + */ + BUG_ON(!clp->cl_cb_flags); + clear_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_cb_flags); + memcpy(&conn, &cb->cb_clp->cl_cb_conn, sizeof(struct nfs4_cb_conn)); + spin_unlock(&clp->cl_lock); - args->args_op = dp; - msg.rpc_argp = args; - dp->dl_retries = 1; - rpc_call_async(clnt, &msg, RPC_TASK_SOFT, &nfsd4_cb_recall_ops, dp); + err = setup_callback_client(clp, &conn); + if (err) + warn_no_callback_path(clp, err); } void nfsd4_do_callback_rpc(struct work_struct *w) { - /* XXX: for now, just send off delegation recall. */ - /* In future, generalize to handle any sort of callback. */ - struct nfsd4_callback *c = container_of(w, struct nfsd4_callback, cb_work); - struct nfs4_delegation *dp = container_of(c, struct nfs4_delegation, dl_recall); + struct nfsd4_callback *cb = container_of(w, struct nfsd4_callback, cb_work); + struct nfs4_client *clp = cb->cb_clp; + struct rpc_clnt *clnt; - _nfsd4_cb_recall(dp); -} + if (clp->cl_cb_flags) + nfsd4_process_cb_update(cb); + clnt = clp->cl_cb_client; + if (!clnt) { + /* Callback channel broken, or client killed; give up: */ + nfsd4_release_cb(cb); + return; + } + rpc_call_async(clnt, &cb->cb_msg, RPC_TASK_SOFT | RPC_TASK_SOFTCONN, + cb->cb_ops, cb); +} void nfsd4_cb_recall(struct nfs4_delegation *dp) { + struct nfsd4_callback *cb = &dp->dl_recall; + + dp->dl_retries = 1; + cb->cb_op = dp; + cb->cb_clp = dp->dl_client; + cb->cb_msg.rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_RECALL]; + cb->cb_msg.rpc_argp = cb; + cb->cb_msg.rpc_resp = cb; + cb->cb_msg.rpc_cred = callback_cred; + + cb->cb_ops = &nfsd4_cb_recall_ops; + dp->dl_retries = 1; + queue_work(callback_wq, &dp->dl_recall.cb_work); } diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index c78dbf493424..f0695e815f0e 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -482,109 +482,26 @@ nfsd_idmap_shutdown(void) cache_unregister(&nametoid_cache); } -/* - * Deferred request handling - */ - -struct idmap_defer_req { - struct cache_req req; - struct cache_deferred_req deferred_req; - wait_queue_head_t waitq; - atomic_t count; -}; - -static inline void -put_mdr(struct idmap_defer_req *mdr) -{ - if (atomic_dec_and_test(&mdr->count)) - kfree(mdr); -} - -static inline void -get_mdr(struct idmap_defer_req *mdr) -{ - atomic_inc(&mdr->count); -} - -static void -idmap_revisit(struct cache_deferred_req *dreq, int toomany) -{ - struct idmap_defer_req *mdr = - container_of(dreq, struct idmap_defer_req, deferred_req); - - wake_up(&mdr->waitq); - put_mdr(mdr); -} - -static struct cache_deferred_req * -idmap_defer(struct cache_req *req) -{ - struct idmap_defer_req *mdr = - container_of(req, struct idmap_defer_req, req); - - mdr->deferred_req.revisit = idmap_revisit; - get_mdr(mdr); - return (&mdr->deferred_req); -} - -static inline int -do_idmap_lookup(struct ent *(*lookup_fn)(struct ent *), struct ent *key, - struct cache_detail *detail, struct ent **item, - struct idmap_defer_req *mdr) -{ - *item = lookup_fn(key); - if (!*item) - return -ENOMEM; - return cache_check(detail, &(*item)->h, &mdr->req); -} - -static inline int -do_idmap_lookup_nowait(struct ent *(*lookup_fn)(struct ent *), - struct ent *key, struct cache_detail *detail, - struct ent **item) -{ - int ret = -ENOMEM; - - *item = lookup_fn(key); - if (!*item) - goto out_err; - ret = -ETIMEDOUT; - if (!test_bit(CACHE_VALID, &(*item)->h.flags) - || (*item)->h.expiry_time < get_seconds() - || detail->flush_time > (*item)->h.last_refresh) - goto out_put; - ret = -ENOENT; - if (test_bit(CACHE_NEGATIVE, &(*item)->h.flags)) - goto out_put; - return 0; -out_put: - cache_put(&(*item)->h, detail); -out_err: - *item = NULL; - return ret; -} - static int idmap_lookup(struct svc_rqst *rqstp, struct ent *(*lookup_fn)(struct ent *), struct ent *key, struct cache_detail *detail, struct ent **item) { - struct idmap_defer_req *mdr; int ret; - mdr = kzalloc(sizeof(*mdr), GFP_KERNEL); - if (!mdr) + *item = lookup_fn(key); + if (!*item) return -ENOMEM; - atomic_set(&mdr->count, 1); - init_waitqueue_head(&mdr->waitq); - mdr->req.defer = idmap_defer; - ret = do_idmap_lookup(lookup_fn, key, detail, item, mdr); - if (ret == -EAGAIN) { - wait_event_interruptible_timeout(mdr->waitq, - test_bit(CACHE_VALID, &(*item)->h.flags), 1 * HZ); - ret = do_idmap_lookup_nowait(lookup_fn, key, detail, item); + retry: + ret = cache_check(detail, &(*item)->h, &rqstp->rq_chandle); + + if (ret == -ETIMEDOUT) { + struct ent *prev_item = *item; + *item = lookup_fn(key); + if (*item != prev_item) + goto retry; + cache_put(&(*item)->h, detail); } - put_mdr(mdr); return ret; } diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 59ec449b0c7f..0cdfd022bb7b 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1031,8 +1031,11 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, resp->cstate.session = NULL; fh_init(&resp->cstate.current_fh, NFS4_FHSIZE); fh_init(&resp->cstate.save_fh, NFS4_FHSIZE); - /* Use the deferral mechanism only for NFSv4.0 compounds */ - rqstp->rq_usedeferral = (args->minorversion == 0); + /* + * Don't use the deferral mechanism for NFSv4; compounds make it + * too hard to avoid non-idempotency problems. + */ + rqstp->rq_usedeferral = 0; /* * According to RFC3010, this takes precedence over all other errors. diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index a7292fcf7718..116cab970e0f 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -207,7 +207,6 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_stateid *stp, struct svc_f { struct nfs4_delegation *dp; struct nfs4_file *fp = stp->st_file; - struct nfs4_cb_conn *cb = &stp->st_stateowner->so_client->cl_cb_conn; dprintk("NFSD alloc_init_deleg\n"); /* @@ -234,7 +233,6 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_stateid *stp, struct svc_f nfs4_file_get_access(fp, O_RDONLY); dp->dl_flock = NULL; dp->dl_type = type; - dp->dl_ident = cb->cb_ident; dp->dl_stateid.si_boot = boot_time; dp->dl_stateid.si_stateownerid = current_delegid++; dp->dl_stateid.si_fileid = 0; @@ -535,171 +533,262 @@ gen_sessionid(struct nfsd4_session *ses) */ #define NFSD_MIN_HDR_SEQ_SZ (24 + 12 + 44) +static void +free_session_slots(struct nfsd4_session *ses) +{ + int i; + + for (i = 0; i < ses->se_fchannel.maxreqs; i++) + kfree(ses->se_slots[i]); +} + /* - * Give the client the number of ca_maxresponsesize_cached slots it - * requests, of size bounded by NFSD_SLOT_CACHE_SIZE, - * NFSD_MAX_MEM_PER_SESSION, and nfsd_drc_max_mem. Do not allow more - * than NFSD_MAX_SLOTS_PER_SESSION. - * - * If we run out of reserved DRC memory we should (up to a point) + * We don't actually need to cache the rpc and session headers, so we + * can allocate a little less for each slot: + */ +static inline int slot_bytes(struct nfsd4_channel_attrs *ca) +{ + return ca->maxresp_cached - NFSD_MIN_HDR_SEQ_SZ; +} + +static int nfsd4_sanitize_slot_size(u32 size) +{ + size -= NFSD_MIN_HDR_SEQ_SZ; /* We don't cache the rpc header */ + size = min_t(u32, size, NFSD_SLOT_CACHE_SIZE); + + return size; +} + +/* + * XXX: If we run out of reserved DRC memory we could (up to a point) * re-negotiate active sessions and reduce their slot usage to make * rooom for new connections. For now we just fail the create session. */ -static int set_forechannel_drc_size(struct nfsd4_channel_attrs *fchan) +static int nfsd4_get_drc_mem(int slotsize, u32 num) { - int mem, size = fchan->maxresp_cached; + int avail; - if (fchan->maxreqs < 1) - return nfserr_inval; + num = min_t(u32, num, NFSD_MAX_SLOTS_PER_SESSION); - if (size < NFSD_MIN_HDR_SEQ_SZ) - size = NFSD_MIN_HDR_SEQ_SZ; - size -= NFSD_MIN_HDR_SEQ_SZ; - if (size > NFSD_SLOT_CACHE_SIZE) - size = NFSD_SLOT_CACHE_SIZE; - - /* bound the maxreqs by NFSD_MAX_MEM_PER_SESSION */ - mem = fchan->maxreqs * size; - if (mem > NFSD_MAX_MEM_PER_SESSION) { - fchan->maxreqs = NFSD_MAX_MEM_PER_SESSION / size; - if (fchan->maxreqs > NFSD_MAX_SLOTS_PER_SESSION) - fchan->maxreqs = NFSD_MAX_SLOTS_PER_SESSION; - mem = fchan->maxreqs * size; - } + spin_lock(&nfsd_drc_lock); + avail = min_t(int, NFSD_MAX_MEM_PER_SESSION, + nfsd_drc_max_mem - nfsd_drc_mem_used); + num = min_t(int, num, avail / slotsize); + nfsd_drc_mem_used += num * slotsize; + spin_unlock(&nfsd_drc_lock); + + return num; +} +static void nfsd4_put_drc_mem(int slotsize, int num) +{ spin_lock(&nfsd_drc_lock); - /* bound the total session drc memory ussage */ - if (mem + nfsd_drc_mem_used > nfsd_drc_max_mem) { - fchan->maxreqs = (nfsd_drc_max_mem - nfsd_drc_mem_used) / size; - mem = fchan->maxreqs * size; - } - nfsd_drc_mem_used += mem; + nfsd_drc_mem_used -= slotsize * num; spin_unlock(&nfsd_drc_lock); +} - if (fchan->maxreqs == 0) - return nfserr_jukebox; +static struct nfsd4_session *alloc_session(int slotsize, int numslots) +{ + struct nfsd4_session *new; + int mem, i; - fchan->maxresp_cached = size + NFSD_MIN_HDR_SEQ_SZ; - return 0; + BUILD_BUG_ON(NFSD_MAX_SLOTS_PER_SESSION * sizeof(struct nfsd4_slot *) + + sizeof(struct nfsd4_session) > PAGE_SIZE); + mem = numslots * sizeof(struct nfsd4_slot *); + + new = kzalloc(sizeof(*new) + mem, GFP_KERNEL); + if (!new) + return NULL; + /* allocate each struct nfsd4_slot and data cache in one piece */ + for (i = 0; i < numslots; i++) { + mem = sizeof(struct nfsd4_slot) + slotsize; + new->se_slots[i] = kzalloc(mem, GFP_KERNEL); + if (!new->se_slots[i]) + goto out_free; + } + return new; +out_free: + while (i--) + kfree(new->se_slots[i]); + kfree(new); + return NULL; } -/* - * fchan holds the client values on input, and the server values on output - * sv_max_mesg is the maximum payload plus one page for overhead. - */ -static int init_forechannel_attrs(struct svc_rqst *rqstp, - struct nfsd4_channel_attrs *session_fchan, - struct nfsd4_channel_attrs *fchan) +static void init_forechannel_attrs(struct nfsd4_channel_attrs *new, struct nfsd4_channel_attrs *req, int numslots, int slotsize) { - int status = 0; - __u32 maxcount = nfsd_serv->sv_max_mesg; + u32 maxrpc = nfsd_serv->sv_max_mesg; - /* headerpadsz set to zero in encode routine */ + new->maxreqs = numslots; + new->maxresp_cached = slotsize + NFSD_MIN_HDR_SEQ_SZ; + new->maxreq_sz = min_t(u32, req->maxreq_sz, maxrpc); + new->maxresp_sz = min_t(u32, req->maxresp_sz, maxrpc); + new->maxops = min_t(u32, req->maxops, NFSD_MAX_OPS_PER_COMPOUND); +} - /* Use the client's max request and max response size if possible */ - if (fchan->maxreq_sz > maxcount) - fchan->maxreq_sz = maxcount; - session_fchan->maxreq_sz = fchan->maxreq_sz; +static void free_conn(struct nfsd4_conn *c) +{ + svc_xprt_put(c->cn_xprt); + kfree(c); +} - if (fchan->maxresp_sz > maxcount) - fchan->maxresp_sz = maxcount; - session_fchan->maxresp_sz = fchan->maxresp_sz; +static void nfsd4_conn_lost(struct svc_xpt_user *u) +{ + struct nfsd4_conn *c = container_of(u, struct nfsd4_conn, cn_xpt_user); + struct nfs4_client *clp = c->cn_session->se_client; - /* Use the client's maxops if possible */ - if (fchan->maxops > NFSD_MAX_OPS_PER_COMPOUND) - fchan->maxops = NFSD_MAX_OPS_PER_COMPOUND; - session_fchan->maxops = fchan->maxops; + spin_lock(&clp->cl_lock); + if (!list_empty(&c->cn_persession)) { + list_del(&c->cn_persession); + free_conn(c); + } + spin_unlock(&clp->cl_lock); +} - /* FIXME: Error means no more DRC pages so the server should - * recover pages from existing sessions. For now fail session - * creation. - */ - status = set_forechannel_drc_size(fchan); +static struct nfsd4_conn *alloc_conn(struct svc_rqst *rqstp, u32 flags) +{ + struct nfsd4_conn *conn; - session_fchan->maxresp_cached = fchan->maxresp_cached; - session_fchan->maxreqs = fchan->maxreqs; + conn = kmalloc(sizeof(struct nfsd4_conn), GFP_KERNEL); + if (!conn) + return NULL; + svc_xprt_get(rqstp->rq_xprt); + conn->cn_xprt = rqstp->rq_xprt; + conn->cn_flags = flags; + INIT_LIST_HEAD(&conn->cn_xpt_user.list); + return conn; +} - dprintk("%s status %d\n", __func__, status); - return status; +static void __nfsd4_hash_conn(struct nfsd4_conn *conn, struct nfsd4_session *ses) +{ + conn->cn_session = ses; + list_add(&conn->cn_persession, &ses->se_conns); } -static void -free_session_slots(struct nfsd4_session *ses) +static void nfsd4_hash_conn(struct nfsd4_conn *conn, struct nfsd4_session *ses) { - int i; + struct nfs4_client *clp = ses->se_client; - for (i = 0; i < ses->se_fchannel.maxreqs; i++) - kfree(ses->se_slots[i]); + spin_lock(&clp->cl_lock); + __nfsd4_hash_conn(conn, ses); + spin_unlock(&clp->cl_lock); } -/* - * We don't actually need to cache the rpc and session headers, so we - * can allocate a little less for each slot: - */ -static inline int slot_bytes(struct nfsd4_channel_attrs *ca) +static int nfsd4_register_conn(struct nfsd4_conn *conn) { - return ca->maxresp_cached - NFSD_MIN_HDR_SEQ_SZ; + conn->cn_xpt_user.callback = nfsd4_conn_lost; + return register_xpt_user(conn->cn_xprt, &conn->cn_xpt_user); } -static int -alloc_init_session(struct svc_rqst *rqstp, struct nfs4_client *clp, - struct nfsd4_create_session *cses) +static __be32 nfsd4_new_conn(struct svc_rqst *rqstp, struct nfsd4_session *ses) { - struct nfsd4_session *new, tmp; - struct nfsd4_slot *sp; - int idx, slotsize, cachesize, i; - int status; + struct nfsd4_conn *conn; + u32 flags = NFS4_CDFC4_FORE; + int ret; - memset(&tmp, 0, sizeof(tmp)); + if (ses->se_flags & SESSION4_BACK_CHAN) + flags |= NFS4_CDFC4_BACK; + conn = alloc_conn(rqstp, flags); + if (!conn) + return nfserr_jukebox; + nfsd4_hash_conn(conn, ses); + ret = nfsd4_register_conn(conn); + if (ret) + /* oops; xprt is already down: */ + nfsd4_conn_lost(&conn->cn_xpt_user); + return nfs_ok; +} - /* FIXME: For now, we just accept the client back channel attributes. */ - tmp.se_bchannel = cses->back_channel; - status = init_forechannel_attrs(rqstp, &tmp.se_fchannel, - &cses->fore_channel); - if (status) - goto out; +static void nfsd4_del_conns(struct nfsd4_session *s) +{ + struct nfs4_client *clp = s->se_client; + struct nfsd4_conn *c; - BUILD_BUG_ON(NFSD_MAX_SLOTS_PER_SESSION * sizeof(struct nfsd4_slot) - + sizeof(struct nfsd4_session) > PAGE_SIZE); + spin_lock(&clp->cl_lock); + while (!list_empty(&s->se_conns)) { + c = list_first_entry(&s->se_conns, struct nfsd4_conn, cn_persession); + list_del_init(&c->cn_persession); + spin_unlock(&clp->cl_lock); - status = nfserr_jukebox; - /* allocate struct nfsd4_session and slot table pointers in one piece */ - slotsize = tmp.se_fchannel.maxreqs * sizeof(struct nfsd4_slot *); - new = kzalloc(sizeof(*new) + slotsize, GFP_KERNEL); - if (!new) - goto out; + unregister_xpt_user(c->cn_xprt, &c->cn_xpt_user); + free_conn(c); - memcpy(new, &tmp, sizeof(*new)); + spin_lock(&clp->cl_lock); + } + spin_unlock(&clp->cl_lock); +} - /* allocate each struct nfsd4_slot and data cache in one piece */ - cachesize = slot_bytes(&new->se_fchannel); - for (i = 0; i < new->se_fchannel.maxreqs; i++) { - sp = kzalloc(sizeof(*sp) + cachesize, GFP_KERNEL); - if (!sp) - goto out_free; - new->se_slots[i] = sp; +void free_session(struct kref *kref) +{ + struct nfsd4_session *ses; + int mem; + + ses = container_of(kref, struct nfsd4_session, se_ref); + nfsd4_del_conns(ses); + spin_lock(&nfsd_drc_lock); + mem = ses->se_fchannel.maxreqs * slot_bytes(&ses->se_fchannel); + nfsd_drc_mem_used -= mem; + spin_unlock(&nfsd_drc_lock); + free_session_slots(ses); + kfree(ses); +} + +static struct nfsd4_session *alloc_init_session(struct svc_rqst *rqstp, struct nfs4_client *clp, struct nfsd4_create_session *cses) +{ + struct nfsd4_session *new; + struct nfsd4_channel_attrs *fchan = &cses->fore_channel; + int numslots, slotsize; + int status; + int idx; + + /* + * Note decreasing slot size below client's request may + * make it difficult for client to function correctly, whereas + * decreasing the number of slots will (just?) affect + * performance. When short on memory we therefore prefer to + * decrease number of slots instead of their size. + */ + slotsize = nfsd4_sanitize_slot_size(fchan->maxresp_cached); + numslots = nfsd4_get_drc_mem(slotsize, fchan->maxreqs); + + new = alloc_session(slotsize, numslots); + if (!new) { + nfsd4_put_drc_mem(slotsize, fchan->maxreqs); + return NULL; } + init_forechannel_attrs(&new->se_fchannel, fchan, numslots, slotsize); new->se_client = clp; gen_sessionid(new); - idx = hash_sessionid(&new->se_sessionid); - memcpy(clp->cl_sessionid.data, new->se_sessionid.data, - NFS4_MAX_SESSIONID_LEN); + INIT_LIST_HEAD(&new->se_conns); + + new->se_cb_seq_nr = 1; new->se_flags = cses->flags; + new->se_cb_prog = cses->callback_prog; kref_init(&new->se_ref); + idx = hash_sessionid(&new->se_sessionid); spin_lock(&client_lock); list_add(&new->se_hash, &sessionid_hashtbl[idx]); list_add(&new->se_perclnt, &clp->cl_sessions); spin_unlock(&client_lock); - status = nfs_ok; -out: - return status; -out_free: - free_session_slots(new); - kfree(new); - goto out; + status = nfsd4_new_conn(rqstp, new); + /* whoops: benny points out, status is ignored! (err, or bogus) */ + if (status) { + free_session(&new->se_ref); + return NULL; + } + if (!clp->cl_cb_session && (cses->flags & SESSION4_BACK_CHAN)) { + struct sockaddr *sa = svc_addr(rqstp); + + clp->cl_cb_session = new; + clp->cl_cb_conn.cb_xprt = rqstp->rq_xprt; + svc_xprt_get(rqstp->rq_xprt); + rpc_copy_addr((struct sockaddr *)&clp->cl_cb_conn.cb_addr, sa); + clp->cl_cb_conn.cb_addrlen = svc_addr_len(sa); + nfsd4_probe_callback(clp); + } + return new; } /* caller must hold client_lock */ @@ -731,21 +820,6 @@ unhash_session(struct nfsd4_session *ses) list_del(&ses->se_perclnt); } -void -free_session(struct kref *kref) -{ - struct nfsd4_session *ses; - int mem; - - ses = container_of(kref, struct nfsd4_session, se_ref); - spin_lock(&nfsd_drc_lock); - mem = ses->se_fchannel.maxreqs * slot_bytes(&ses->se_fchannel); - nfsd_drc_mem_used -= mem; - spin_unlock(&nfsd_drc_lock); - free_session_slots(ses); - kfree(ses); -} - /* must be called under the client_lock */ static inline void renew_client_locked(struct nfs4_client *clp) @@ -812,6 +886,13 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name) static inline void free_client(struct nfs4_client *clp) { + while (!list_empty(&clp->cl_sessions)) { + struct nfsd4_session *ses; + ses = list_entry(clp->cl_sessions.next, struct nfsd4_session, + se_perclnt); + list_del(&ses->se_perclnt); + nfsd4_put_session(ses); + } if (clp->cl_cred.cr_group_info) put_group_info(clp->cl_cred.cr_group_info); kfree(clp->cl_principal); @@ -838,15 +919,12 @@ release_session_client(struct nfsd4_session *session) static inline void unhash_client_locked(struct nfs4_client *clp) { + struct nfsd4_session *ses; + mark_client_expired(clp); list_del(&clp->cl_lru); - while (!list_empty(&clp->cl_sessions)) { - struct nfsd4_session *ses; - ses = list_entry(clp->cl_sessions.next, struct nfsd4_session, - se_perclnt); - unhash_session(ses); - nfsd4_put_session(ses); - } + list_for_each_entry(ses, &clp->cl_sessions, se_perclnt) + list_del_init(&ses->se_hash); } static void @@ -875,7 +953,7 @@ expire_client(struct nfs4_client *clp) sop = list_entry(clp->cl_openowners.next, struct nfs4_stateowner, so_perclient); release_openowner(sop); } - nfsd4_set_callback_client(clp, NULL); + nfsd4_shutdown_callback(clp); if (clp->cl_cb_conn.cb_xprt) svc_xprt_put(clp->cl_cb_conn.cb_xprt); list_del(&clp->cl_idhash); @@ -960,6 +1038,8 @@ static struct nfs4_client *create_client(struct xdr_netobj name, char *recdir, if (clp == NULL) return NULL; + INIT_LIST_HEAD(&clp->cl_sessions); + princ = svc_gss_principal(rqstp); if (princ) { clp->cl_principal = kstrdup(princ, GFP_KERNEL); @@ -976,8 +1056,9 @@ static struct nfs4_client *create_client(struct xdr_netobj name, char *recdir, INIT_LIST_HEAD(&clp->cl_strhash); INIT_LIST_HEAD(&clp->cl_openowners); INIT_LIST_HEAD(&clp->cl_delegations); - INIT_LIST_HEAD(&clp->cl_sessions); INIT_LIST_HEAD(&clp->cl_lru); + spin_lock_init(&clp->cl_lock); + INIT_WORK(&clp->cl_cb_null.cb_work, nfsd4_do_callback_rpc); clp->cl_time = get_seconds(); clear_bit(0, &clp->cl_cb_slot_busy); rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table"); @@ -986,7 +1067,7 @@ static struct nfs4_client *create_client(struct xdr_netobj name, char *recdir, clp->cl_flavor = rqstp->rq_flavor; copy_cred(&clp->cl_cred, &rqstp->rq_cred); gen_confirm(clp); - + clp->cl_cb_session = NULL; return clp; } @@ -1098,7 +1179,7 @@ find_unconfirmed_client_by_str(const char *dname, unsigned int hashval, static void gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, u32 scopeid) { - struct nfs4_cb_conn *cb = &clp->cl_cb_conn; + struct nfs4_cb_conn *conn = &clp->cl_cb_conn; unsigned short expected_family; /* Currently, we only support tcp and tcp6 for the callback channel */ @@ -1111,24 +1192,23 @@ gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, u32 scopeid) else goto out_err; - cb->cb_addrlen = rpc_uaddr2sockaddr(se->se_callback_addr_val, + conn->cb_addrlen = rpc_uaddr2sockaddr(se->se_callback_addr_val, se->se_callback_addr_len, - (struct sockaddr *) &cb->cb_addr, - sizeof(cb->cb_addr)); + (struct sockaddr *)&conn->cb_addr, + sizeof(conn->cb_addr)); - if (!cb->cb_addrlen || cb->cb_addr.ss_family != expected_family) + if (!conn->cb_addrlen || conn->cb_addr.ss_family != expected_family) goto out_err; - if (cb->cb_addr.ss_family == AF_INET6) - ((struct sockaddr_in6 *) &cb->cb_addr)->sin6_scope_id = scopeid; + if (conn->cb_addr.ss_family == AF_INET6) + ((struct sockaddr_in6 *)&conn->cb_addr)->sin6_scope_id = scopeid; - cb->cb_minorversion = 0; - cb->cb_prog = se->se_callback_prog; - cb->cb_ident = se->se_callback_ident; + conn->cb_prog = se->se_callback_prog; + conn->cb_ident = se->se_callback_ident; return; out_err: - cb->cb_addr.ss_family = AF_UNSPEC; - cb->cb_addrlen = 0; + conn->cb_addr.ss_family = AF_UNSPEC; + conn->cb_addrlen = 0; dprintk(KERN_INFO "NFSD: this client (clientid %08x/%08x) " "will not receive delegations\n", clp->cl_clientid.cl_boot, clp->cl_clientid.cl_id); @@ -1415,7 +1495,9 @@ nfsd4_create_session(struct svc_rqst *rqstp, { struct sockaddr *sa = svc_addr(rqstp); struct nfs4_client *conf, *unconf; + struct nfsd4_session *new; struct nfsd4_clid_slot *cs_slot = NULL; + bool confirm_me = false; int status = 0; nfs4_lock_state(); @@ -1438,7 +1520,6 @@ nfsd4_create_session(struct svc_rqst *rqstp, cs_slot->sl_seqid, cr_ses->seqid); goto out; } - cs_slot->sl_seqid++; } else if (unconf) { if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred) || !rpc_cmp_addr(sa, (struct sockaddr *) &unconf->cl_addr)) { @@ -1451,25 +1532,10 @@ nfsd4_create_session(struct svc_rqst *rqstp, if (status) { /* an unconfirmed replay returns misordered */ status = nfserr_seq_misordered; - goto out_cache; + goto out; } - cs_slot->sl_seqid++; /* from 0 to 1 */ - move_to_confirmed(unconf); - - if (cr_ses->flags & SESSION4_BACK_CHAN) { - unconf->cl_cb_conn.cb_xprt = rqstp->rq_xprt; - svc_xprt_get(rqstp->rq_xprt); - rpc_copy_addr( - (struct sockaddr *)&unconf->cl_cb_conn.cb_addr, - sa); - unconf->cl_cb_conn.cb_addrlen = svc_addr_len(sa); - unconf->cl_cb_conn.cb_minorversion = - cstate->minorversion; - unconf->cl_cb_conn.cb_prog = cr_ses->callback_prog; - unconf->cl_cb_seq_nr = 1; - nfsd4_probe_callback(unconf, &unconf->cl_cb_conn); - } + confirm_me = true; conf = unconf; } else { status = nfserr_stale_clientid; @@ -1477,22 +1543,30 @@ nfsd4_create_session(struct svc_rqst *rqstp, } /* + * XXX: we should probably set this at creation time, and check + * for consistent minorversion use throughout: + */ + conf->cl_minorversion = 1; + /* * We do not support RDMA or persistent sessions */ cr_ses->flags &= ~SESSION4_PERSIST; cr_ses->flags &= ~SESSION4_RDMA; - status = alloc_init_session(rqstp, conf, cr_ses); - if (status) + status = nfserr_jukebox; + new = alloc_init_session(rqstp, conf, cr_ses); + if (!new) goto out; - - memcpy(cr_ses->sessionid.data, conf->cl_sessionid.data, + status = nfs_ok; + memcpy(cr_ses->sessionid.data, new->se_sessionid.data, NFS4_MAX_SESSIONID_LEN); + cs_slot->sl_seqid++; cr_ses->seqid = cs_slot->sl_seqid; -out_cache: /* cache solo and embedded create sessions under the state lock */ nfsd4_cache_create_session(cr_ses, cs_slot, status); + if (confirm_me) + move_to_confirmed(conf); out: nfs4_unlock_state(); dprintk("%s returns %d\n", __func__, ntohl(status)); @@ -1546,8 +1620,11 @@ nfsd4_destroy_session(struct svc_rqst *r, nfs4_lock_state(); /* wait for callbacks */ - nfsd4_set_callback_client(ses->se_client, NULL); + nfsd4_shutdown_callback(ses->se_client); nfs4_unlock_state(); + + nfsd4_del_conns(ses); + nfsd4_put_session(ses); status = nfs_ok; out: @@ -1555,6 +1632,40 @@ out: return status; } +static struct nfsd4_conn *__nfsd4_find_conn(struct svc_xprt *xpt, struct nfsd4_session *s) +{ + struct nfsd4_conn *c; + + list_for_each_entry(c, &s->se_conns, cn_persession) { + if (c->cn_xprt == xpt) { + return c; + } + } + return NULL; +} + +static void nfsd4_sequence_check_conn(struct nfsd4_conn *new, struct nfsd4_session *ses) +{ + struct nfs4_client *clp = ses->se_client; + struct nfsd4_conn *c; + int ret; + + spin_lock(&clp->cl_lock); + c = __nfsd4_find_conn(new->cn_xprt, ses); + if (c) { + spin_unlock(&clp->cl_lock); + free_conn(new); + return; + } + __nfsd4_hash_conn(new, ses); + spin_unlock(&clp->cl_lock); + ret = nfsd4_register_conn(new); + if (ret) + /* oops; xprt is already down: */ + nfsd4_conn_lost(&new->cn_xpt_user); + return; +} + __be32 nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, @@ -1563,11 +1674,20 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compoundres *resp = rqstp->rq_resp; struct nfsd4_session *session; struct nfsd4_slot *slot; + struct nfsd4_conn *conn; int status; if (resp->opcnt != 1) return nfserr_sequence_pos; + /* + * Will be either used or freed by nfsd4_sequence_check_conn + * below. + */ + conn = alloc_conn(rqstp, NFS4_CDFC4_FORE); + if (!conn) + return nfserr_jukebox; + spin_lock(&client_lock); status = nfserr_badsession; session = find_in_sessionid_hashtbl(&seq->sessionid); @@ -1599,6 +1719,9 @@ nfsd4_sequence(struct svc_rqst *rqstp, if (status) goto out; + nfsd4_sequence_check_conn(conn, session); + conn = NULL; + /* Success! bump slot seqid */ slot->sl_inuse = true; slot->sl_seqid = seq->seqid; @@ -1613,6 +1736,7 @@ out: nfsd4_get_session(cstate->session); atomic_inc(&session->se_client->cl_refcount); } + kfree(conn); spin_unlock(&client_lock); dprintk("%s: return %d\n", __func__, ntohl(status)); return status; @@ -1747,6 +1871,11 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; gen_clid(new); } + /* + * XXX: we should probably set this at creation time, and check + * for consistent minorversion use throughout: + */ + new->cl_minorversion = 0; gen_callback(new, setclid, rpc_get_scope_id(sa)); add_to_unconfirmed(new, strhashval); setclid->se_clientid.cl_boot = new->cl_clientid.cl_boot; @@ -1807,7 +1936,8 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, status = nfserr_clid_inuse; else { atomic_set(&conf->cl_cb_set, 0); - nfsd4_probe_callback(conf, &unconf->cl_cb_conn); + nfsd4_change_callback(conf, &unconf->cl_cb_conn); + nfsd4_probe_callback(conf); expire_client(unconf); status = nfs_ok; @@ -1841,7 +1971,7 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, } move_to_confirmed(unconf); conf = unconf; - nfsd4_probe_callback(conf, &conf->cl_cb_conn); + nfsd4_probe_callback(conf); status = nfs_ok; } } else if ((!conf || (conf && !same_verf(&conf->cl_confirm, &confirm))) @@ -2132,7 +2262,7 @@ nfs4_file_downgrade(struct nfs4_file *fp, unsigned int share_access) * Spawn a thread to perform a recall on the delegation represented * by the lease (file_lock) * - * Called from break_lease() with lock_kernel() held. + * Called from break_lease() with lock_flocks() held. * Note: we assume break_lease will only call this *once* for any given * lease. */ @@ -2156,7 +2286,7 @@ void nfsd_break_deleg_cb(struct file_lock *fl) list_add_tail(&dp->dl_recall_lru, &del_recall_lru); spin_unlock(&recall_lock); - /* only place dl_time is set. protected by lock_kernel*/ + /* only place dl_time is set. protected by lock_flocks*/ dp->dl_time = get_seconds(); /* @@ -2173,7 +2303,7 @@ void nfsd_break_deleg_cb(struct file_lock *fl) /* * The file_lock is being reapd. * - * Called by locks_free_lock() with lock_kernel() held. + * Called by locks_free_lock() with lock_flocks() held. */ static void nfsd_release_deleg_cb(struct file_lock *fl) @@ -2188,23 +2318,7 @@ void nfsd_release_deleg_cb(struct file_lock *fl) } /* - * Set the delegation file_lock back pointer. - * - * Called from setlease() with lock_kernel() held. - */ -static -void nfsd_copy_lock_deleg_cb(struct file_lock *new, struct file_lock *fl) -{ - struct nfs4_delegation *dp = (struct nfs4_delegation *)new->fl_owner; - - dprintk("NFSD: nfsd_copy_lock_deleg_cb: new fl %p dp %p\n", new, dp); - if (!dp) - return; - dp->dl_flock = new; -} - -/* - * Called from setlease() with lock_kernel() held + * Called from setlease() with lock_flocks() held */ static int nfsd_same_client_deleg_cb(struct file_lock *onlist, struct file_lock *try) @@ -2233,7 +2347,6 @@ int nfsd_change_deleg_cb(struct file_lock **onlist, int arg) static const struct lock_manager_operations nfsd_lease_mng_ops = { .fl_break = nfsd_break_deleg_cb, .fl_release_private = nfsd_release_deleg_cb, - .fl_copy_lock = nfsd_copy_lock_deleg_cb, .fl_mylease = nfsd_same_client_deleg_cb, .fl_change = nfsd_change_deleg_cb, }; @@ -2492,7 +2605,7 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, struct nfs4_sta struct nfs4_delegation *dp; struct nfs4_stateowner *sop = stp->st_stateowner; int cb_up = atomic_read(&sop->so_client->cl_cb_set); - struct file_lock fl, *flp = &fl; + struct file_lock *fl; int status, flag = 0; flag = NFS4_OPEN_DELEGATE_NONE; @@ -2526,21 +2639,28 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, struct nfs4_sta flag = NFS4_OPEN_DELEGATE_NONE; goto out; } - locks_init_lock(&fl); - fl.fl_lmops = &nfsd_lease_mng_ops; - fl.fl_flags = FL_LEASE; - fl.fl_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK; - fl.fl_end = OFFSET_MAX; - fl.fl_owner = (fl_owner_t)dp; - fl.fl_file = find_readable_file(stp->st_file); - BUG_ON(!fl.fl_file); - fl.fl_pid = current->tgid; + status = -ENOMEM; + fl = locks_alloc_lock(); + if (!fl) + goto out; + locks_init_lock(fl); + fl->fl_lmops = &nfsd_lease_mng_ops; + fl->fl_flags = FL_LEASE; + fl->fl_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK; + fl->fl_end = OFFSET_MAX; + fl->fl_owner = (fl_owner_t)dp; + fl->fl_file = find_readable_file(stp->st_file); + BUG_ON(!fl->fl_file); + fl->fl_pid = current->tgid; + dp->dl_flock = fl; /* vfs_setlease checks to see if delegation should be handed out. * the lock_manager callbacks fl_mylease and fl_change are used */ - if ((status = vfs_setlease(fl.fl_file, fl.fl_type, &flp))) { + if ((status = vfs_setlease(fl->fl_file, fl->fl_type, &fl))) { dprintk("NFSD: setlease failed [%d], no delegation\n", status); + dp->dl_flock = NULL; + locks_free_lock(fl); unhash_delegation(dp); flag = NFS4_OPEN_DELEGATE_NONE; goto out; @@ -2944,7 +3064,11 @@ nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate, if (STALE_STATEID(stateid)) goto out; - status = nfserr_bad_stateid; + /* + * We assume that any stateid that has the current boot time, + * but that we can't find, is expired: + */ + status = nfserr_expired; if (is_delegation_stateid(stateid)) { dp = find_delegation_stateid(ino, stateid); if (!dp) @@ -2964,6 +3088,7 @@ nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate, stp = find_stateid(stateid, flags); if (!stp) goto out; + status = nfserr_bad_stateid; if (nfs4_check_fh(current_fh, stp)) goto out; if (!stp->st_stateowner->so_confirmed) @@ -3038,8 +3163,9 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, * a replayed close: */ sop = search_close_lru(stateid->si_stateownerid, flags); + /* It's not stale; let's assume it's expired: */ if (sop == NULL) - return nfserr_bad_stateid; + return nfserr_expired; *sopp = sop; goto check_replay; } @@ -3304,6 +3430,7 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfserr_bad_stateid; if (!is_delegation_stateid(stateid)) goto out; + status = nfserr_expired; dp = find_delegation_stateid(inode, stateid); if (!dp) goto out; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 1a468bbd330f..f35a94a04026 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1805,19 +1805,23 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, goto out_nfserr; } } - if ((buflen -= 16) < 0) - goto out_resource; - if (unlikely(bmval2)) { + if (bmval2) { + if ((buflen -= 16) < 0) + goto out_resource; WRITE32(3); WRITE32(bmval0); WRITE32(bmval1); WRITE32(bmval2); - } else if (likely(bmval1)) { + } else if (bmval1) { + if ((buflen -= 12) < 0) + goto out_resource; WRITE32(2); WRITE32(bmval0); WRITE32(bmval1); } else { + if ((buflen -= 8) < 0) + goto out_resource; WRITE32(1); WRITE32(bmval0); } @@ -1828,15 +1832,17 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, u32 word1 = nfsd_suppattrs1(minorversion); u32 word2 = nfsd_suppattrs2(minorversion); - if ((buflen -= 12) < 0) - goto out_resource; if (!aclsupport) word0 &= ~FATTR4_WORD0_ACL; if (!word2) { + if ((buflen -= 12) < 0) + goto out_resource; WRITE32(2); WRITE32(word0); WRITE32(word1); } else { + if ((buflen -= 16) < 0) + goto out_resource; WRITE32(3); WRITE32(word0); WRITE32(word1); diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 06fa87e52e82..4514ebbee4d6 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -22,6 +22,7 @@ */ enum { NFSD_Root = 1, +#ifdef CONFIG_NFSD_DEPRECATED NFSD_Svc, NFSD_Add, NFSD_Del, @@ -29,6 +30,7 @@ enum { NFSD_Unexport, NFSD_Getfd, NFSD_Getfs, +#endif NFSD_List, NFSD_Export_features, NFSD_Fh, @@ -54,6 +56,7 @@ enum { /* * write() for these nodes. */ +#ifdef CONFIG_NFSD_DEPRECATED static ssize_t write_svc(struct file *file, char *buf, size_t size); static ssize_t write_add(struct file *file, char *buf, size_t size); static ssize_t write_del(struct file *file, char *buf, size_t size); @@ -61,6 +64,7 @@ static ssize_t write_export(struct file *file, char *buf, size_t size); static ssize_t write_unexport(struct file *file, char *buf, size_t size); static ssize_t write_getfd(struct file *file, char *buf, size_t size); static ssize_t write_getfs(struct file *file, char *buf, size_t size); +#endif static ssize_t write_filehandle(struct file *file, char *buf, size_t size); static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size); static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size); @@ -76,6 +80,7 @@ static ssize_t write_recoverydir(struct file *file, char *buf, size_t size); #endif static ssize_t (*write_op[])(struct file *, char *, size_t) = { +#ifdef CONFIG_NFSD_DEPRECATED [NFSD_Svc] = write_svc, [NFSD_Add] = write_add, [NFSD_Del] = write_del, @@ -83,6 +88,7 @@ static ssize_t (*write_op[])(struct file *, char *, size_t) = { [NFSD_Unexport] = write_unexport, [NFSD_Getfd] = write_getfd, [NFSD_Getfs] = write_getfs, +#endif [NFSD_Fh] = write_filehandle, [NFSD_FO_UnlockIP] = write_unlock_ip, [NFSD_FO_UnlockFS] = write_unlock_fs, @@ -121,6 +127,14 @@ static ssize_t nfsctl_transaction_write(struct file *file, const char __user *bu static ssize_t nfsctl_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos) { + static int warned; + if (file->f_dentry->d_name.name[0] == '.' && !warned) { + printk(KERN_INFO + "Warning: \"%s\" uses deprecated NFSD interface: %s." + " This will be removed in 2.6.40\n", + current->comm, file->f_dentry->d_name.name); + warned = 1; + } if (! file->private_data) { /* An attempt to read a transaction file without writing * causes a 0-byte write so that the file can return @@ -187,6 +201,7 @@ static const struct file_operations pool_stats_operations = { * payload - write methods */ +#ifdef CONFIG_NFSD_DEPRECATED /** * write_svc - Start kernel's NFSD server * @@ -402,7 +417,7 @@ static ssize_t write_getfs(struct file *file, char *buf, size_t size) ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &in6); - clp = auth_unix_lookup(&in6); + clp = auth_unix_lookup(&init_net, &in6); if (!clp) err = -EPERM; else { @@ -465,7 +480,7 @@ static ssize_t write_getfd(struct file *file, char *buf, size_t size) ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &in6); - clp = auth_unix_lookup(&in6); + clp = auth_unix_lookup(&init_net, &in6); if (!clp) err = -EPERM; else { @@ -482,6 +497,7 @@ static ssize_t write_getfd(struct file *file, char *buf, size_t size) out: return err; } +#endif /* CONFIG_NFSD_DEPRECATED */ /** * write_unlock_ip - Release all locks used by a client @@ -1000,12 +1016,12 @@ static ssize_t __write_ports_addxprt(char *buf) if (err != 0) return err; - err = svc_create_xprt(nfsd_serv, transport, + err = svc_create_xprt(nfsd_serv, transport, &init_net, PF_INET, port, SVC_SOCK_ANONYMOUS); if (err < 0) goto out_err; - err = svc_create_xprt(nfsd_serv, transport, + err = svc_create_xprt(nfsd_serv, transport, &init_net, PF_INET6, port, SVC_SOCK_ANONYMOUS); if (err < 0 && err != -EAFNOSUPPORT) goto out_close; @@ -1356,6 +1372,7 @@ static ssize_t write_recoverydir(struct file *file, char *buf, size_t size) static int nfsd_fill_super(struct super_block * sb, void * data, int silent) { static struct tree_descr nfsd_files[] = { +#ifdef CONFIG_NFSD_DEPRECATED [NFSD_Svc] = {".svc", &transaction_ops, S_IWUSR}, [NFSD_Add] = {".add", &transaction_ops, S_IWUSR}, [NFSD_Del] = {".del", &transaction_ops, S_IWUSR}, @@ -1363,6 +1380,7 @@ static int nfsd_fill_super(struct super_block * sb, void * data, int silent) [NFSD_Unexport] = {".unexport", &transaction_ops, S_IWUSR}, [NFSD_Getfd] = {".getfd", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Getfs] = {".getfs", &transaction_ops, S_IWUSR|S_IRUSR}, +#endif [NFSD_List] = {"exports", &exports_operations, S_IRUGO}, [NFSD_Export_features] = {"export_features", &export_features_operations, S_IRUGO}, @@ -1387,16 +1405,16 @@ static int nfsd_fill_super(struct super_block * sb, void * data, int silent) return simple_fill_super(sb, 0x6e667364, nfsd_files); } -static int nfsd_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *nfsd_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_single(fs_type, flags, data, nfsd_fill_super, mnt); + return mount_single(fs_type, flags, data, nfsd_fill_super); } static struct file_system_type nfsd_fs_type = { .owner = THIS_MODULE, .name = "nfsd", - .get_sb = nfsd_get_sb, + .mount = nfsd_mount, .kill_sb = kill_litter_super, }; diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index b76ac3a82e39..6b641cf2c19a 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -249,7 +249,7 @@ extern time_t nfsd4_grace; #define COMPOUND_SLACK_SPACE 140 /* OP_GETFH */ #define COMPOUND_ERR_SLACK_SPACE 12 /* OP_SETATTR */ -#define NFSD_LAUNDROMAT_MINTIMEOUT 10 /* seconds */ +#define NFSD_LAUNDROMAT_MINTIMEOUT 1 /* seconds */ /* * The following attributes are currently not supported by the NFSv4 server: diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index e2c43464f237..2bae1d86f5f2 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -16,6 +16,7 @@ #include <linux/lockd/bind.h> #include <linux/nfsacl.h> #include <linux/seq_file.h> +#include <net/net_namespace.h> #include "nfsd.h" #include "cache.h" #include "vfs.h" @@ -186,12 +187,12 @@ static int nfsd_init_socks(int port) if (!list_empty(&nfsd_serv->sv_permsocks)) return 0; - error = svc_create_xprt(nfsd_serv, "udp", PF_INET, port, + error = svc_create_xprt(nfsd_serv, "udp", &init_net, PF_INET, port, SVC_SOCK_DEFAULTS); if (error < 0) return error; - error = svc_create_xprt(nfsd_serv, "tcp", PF_INET, port, + error = svc_create_xprt(nfsd_serv, "tcp", &init_net, PF_INET, port, SVC_SOCK_DEFAULTS); if (error < 0) return error; diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 322518c88e4b..39adc27b0685 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -35,6 +35,7 @@ #ifndef _NFSD4_STATE_H #define _NFSD4_STATE_H +#include <linux/sunrpc/svc_xprt.h> #include <linux/nfsd/nfsfh.h> #include "nfsfh.h" @@ -64,19 +65,12 @@ typedef struct { (s)->si_fileid, \ (s)->si_generation -struct nfsd4_cb_sequence { - /* args/res */ - u32 cbs_minorversion; - struct nfs4_client *cbs_clp; -}; - -struct nfs4_rpc_args { - void *args_op; - struct nfsd4_cb_sequence args_seq; -}; - struct nfsd4_callback { - struct nfs4_rpc_args cb_args; + void *cb_op; + struct nfs4_client *cb_clp; + u32 cb_minorversion; + struct rpc_message cb_msg; + const struct rpc_call_ops *cb_ops; struct work_struct cb_work; }; @@ -91,7 +85,6 @@ struct nfs4_delegation { u32 dl_type; time_t dl_time; /* For recall: */ - u32 dl_ident; stateid_t dl_stateid; struct knfsd_fh dl_fh; int dl_retries; @@ -103,8 +96,8 @@ struct nfs4_cb_conn { /* SETCLIENTID info */ struct sockaddr_storage cb_addr; size_t cb_addrlen; - u32 cb_prog; - u32 cb_minorversion; + u32 cb_prog; /* used only in 4.0 case; + per-session otherwise */ u32 cb_ident; /* minorversion 0 only */ struct svc_xprt *cb_xprt; /* minorversion 1 only */ }; @@ -160,6 +153,15 @@ struct nfsd4_clid_slot { struct nfsd4_create_session sl_cr_ses; }; +struct nfsd4_conn { + struct list_head cn_persession; + struct svc_xprt *cn_xprt; + struct svc_xpt_user cn_xpt_user; + struct nfsd4_session *cn_session; +/* CDFC4_FORE, CDFC4_BACK: */ + unsigned char cn_flags; +}; + struct nfsd4_session { struct kref se_ref; struct list_head se_hash; /* hash by sessionid */ @@ -169,6 +171,9 @@ struct nfsd4_session { struct nfs4_sessionid se_sessionid; struct nfsd4_channel_attrs se_fchannel; struct nfsd4_channel_attrs se_bchannel; + struct list_head se_conns; + u32 se_cb_prog; + u32 se_cb_seq_nr; struct nfsd4_slot *se_slots[]; /* forward channel slots */ }; @@ -221,24 +226,32 @@ struct nfs4_client { clientid_t cl_clientid; /* generated by server */ nfs4_verifier cl_confirm; /* generated by server */ u32 cl_firststate; /* recovery dir creation */ + u32 cl_minorversion; /* for v4.0 and v4.1 callbacks: */ struct nfs4_cb_conn cl_cb_conn; +#define NFSD4_CLIENT_CB_UPDATE 1 +#define NFSD4_CLIENT_KILL 2 + unsigned long cl_cb_flags; struct rpc_clnt *cl_cb_client; + u32 cl_cb_ident; atomic_t cl_cb_set; + struct nfsd4_callback cl_cb_null; + struct nfsd4_session *cl_cb_session; + + /* for all client information that callback code might need: */ + spinlock_t cl_lock; /* for nfs41 */ struct list_head cl_sessions; struct nfsd4_clid_slot cl_cs_slot; /* create_session slot */ u32 cl_exchange_flags; - struct nfs4_sessionid cl_sessionid; /* number of rpc's in progress over an associated session: */ atomic_t cl_refcount; /* for nfs41 callbacks */ /* We currently support a single back channel with a single slot */ unsigned long cl_cb_slot_busy; - u32 cl_cb_seq_nr; struct rpc_wait_queue cl_cb_waitq; /* backchannel callers may */ /* wait here for slots */ }; @@ -440,12 +453,13 @@ extern int nfs4_in_grace(void); extern __be32 nfs4_check_open_reclaim(clientid_t *clid); extern void nfs4_free_stateowner(struct kref *kref); extern int set_callback_cred(void); -extern void nfsd4_probe_callback(struct nfs4_client *clp, struct nfs4_cb_conn *); +extern void nfsd4_probe_callback(struct nfs4_client *clp); +extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *); extern void nfsd4_do_callback_rpc(struct work_struct *); extern void nfsd4_cb_recall(struct nfs4_delegation *dp); extern int nfsd4_create_callback_queue(void); extern void nfsd4_destroy_callback_queue(void); -extern void nfsd4_set_callback_client(struct nfs4_client *, struct rpc_clnt *); +extern void nfsd4_shutdown_callback(struct nfs4_client *); extern void nfs4_put_delegation(struct nfs4_delegation *dp); extern __be32 nfs4_make_rec_clidname(char *clidname, struct xdr_netobj *clname); extern void nfsd4_init_recdir(char *recdir_name); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 661a6cf8e826..184938fcff04 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -281,23 +281,13 @@ commit_metadata(struct svc_fh *fhp) { struct inode *inode = fhp->fh_dentry->d_inode; const struct export_operations *export_ops = inode->i_sb->s_export_op; - int error = 0; if (!EX_ISSYNC(fhp->fh_export)) return 0; - if (export_ops->commit_metadata) { - error = export_ops->commit_metadata(inode); - } else { - struct writeback_control wbc = { - .sync_mode = WB_SYNC_ALL, - .nr_to_write = 0, /* metadata only */ - }; - - error = sync_inode(inode, &wbc); - } - - return error; + if (export_ops->commit_metadata) + return export_ops->commit_metadata(inode); + return sync_inode_metadata(inode, 1); } /* diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c index 49c844dab33a..59e5fe742f7b 100644 --- a/fs/nilfs2/dat.c +++ b/fs/nilfs2/dat.c @@ -335,7 +335,7 @@ int nilfs_dat_move(struct inode *dat, __u64 vblocknr, sector_t blocknr) * the device at this point. * * To prevent nilfs_dat_translate() from returning the - * uncommited block number, this makes a copy of the entry + * uncommitted block number, this makes a copy of the entry * buffer and redirects nilfs_dat_translate() to the copy. */ if (!buffer_nilfs_redirected(entry_bh)) { diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index 3e90f86d5bfe..e00d9457c256 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -349,8 +349,8 @@ static int nilfs_ioctl_move_blocks(struct super_block *sb, ino = vdesc->vd_ino; cno = vdesc->vd_cno; inode = nilfs_iget_for_gc(sb, ino, cno); - if (unlikely(inode == NULL)) { - ret = -ENOMEM; + if (IS_ERR(inode)) { + ret = PTR_ERR(inode); goto failed; } do { diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index 185d1607cb00..6e9557ecf161 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -207,7 +207,7 @@ static int nilfs_link(struct dentry *old_dentry, struct inode *dir, inode->i_ctime = CURRENT_TIME; inode_inc_link_count(inode); - atomic_inc(&inode->i_count); + ihold(inode); err = nilfs_add_nondir(dentry, inode); if (!err) diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index d926af626177..687d090cea34 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -1609,7 +1609,7 @@ nilfs_copy_replace_page_buffers(struct page *page, struct list_head *out) kunmap_atomic(kaddr, KM_USER0); if (!TestSetPageWriteback(clone_page)) - inc_zone_page_state(clone_page, NR_WRITEBACK); + account_page_writeback(clone_page); unlock_page(clone_page); return 0; diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 35ae03c0db86..f804d41ec9d3 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1141,9 +1141,9 @@ static int nilfs_test_bdev_super(struct super_block *s, void *data) return (void *)s->s_bdev == data; } -static int -nilfs_get_sb(struct file_system_type *fs_type, int flags, - const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry * +nilfs_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *data) { struct nilfs_super_data sd; struct super_block *s; @@ -1156,7 +1156,7 @@ nilfs_get_sb(struct file_system_type *fs_type, int flags, sd.bdev = open_bdev_exclusive(dev_name, mode, fs_type); if (IS_ERR(sd.bdev)) - return PTR_ERR(sd.bdev); + return ERR_CAST(sd.bdev); sd.cno = 0; sd.flags = flags; @@ -1235,9 +1235,7 @@ nilfs_get_sb(struct file_system_type *fs_type, int flags, if (!s_new) close_bdev_exclusive(sd.bdev, mode); - mnt->mnt_sb = s; - mnt->mnt_root = root_dentry; - return 0; + return root_dentry; failed_super: deactivate_locked_super(s); @@ -1245,13 +1243,13 @@ nilfs_get_sb(struct file_system_type *fs_type, int flags, failed: if (!s_new) close_bdev_exclusive(sd.bdev, mode); - return err; + return ERR_PTR(err); } struct file_system_type nilfs_fs_type = { .owner = THIS_MODULE, .name = "nilfs2", - .get_sb = nilfs_get_sb, + .mount = nilfs_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/notify/Kconfig b/fs/notify/Kconfig index b388443c3a09..22c629eedd82 100644 --- a/fs/notify/Kconfig +++ b/fs/notify/Kconfig @@ -3,4 +3,4 @@ config FSNOTIFY source "fs/notify/dnotify/Kconfig" source "fs/notify/inotify/Kconfig" -#source "fs/notify/fanotify/Kconfig" +source "fs/notify/fanotify/Kconfig" diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 85366c78cc37..b04f88eed09e 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -131,6 +131,7 @@ static int fanotify_handle_event(struct fsnotify_group *group, BUILD_BUG_ON(FAN_Q_OVERFLOW != FS_Q_OVERFLOW); BUILD_BUG_ON(FAN_OPEN_PERM != FS_OPEN_PERM); BUILD_BUG_ON(FAN_ACCESS_PERM != FS_ACCESS_PERM); + BUILD_BUG_ON(FAN_ONDIR != FS_ISDIR); pr_debug("%s: group=%p event=%p\n", __func__, group, event); @@ -160,20 +161,21 @@ static bool fanotify_should_send_event(struct fsnotify_group *group, __u32 event_mask, void *data, int data_type) { __u32 marks_mask, marks_ignored_mask; + struct path *path = data; pr_debug("%s: group=%p to_tell=%p inode_mark=%p vfsmnt_mark=%p " "mask=%x data=%p data_type=%d\n", __func__, group, to_tell, inode_mark, vfsmnt_mark, event_mask, data, data_type); - /* sorry, fanotify only gives a damn about files and dirs */ - if (!S_ISREG(to_tell->i_mode) && - !S_ISDIR(to_tell->i_mode)) - return false; - /* if we don't have enough info to send an event to userspace say no */ if (data_type != FSNOTIFY_EVENT_PATH) return false; + /* sorry, fanotify only gives a damn about files and dirs */ + if (!S_ISREG(path->dentry->d_inode->i_mode) && + !S_ISDIR(path->dentry->d_inode->i_mode)) + return false; + if (inode_mark && vfsmnt_mark) { marks_mask = (vfsmnt_mark->mask | inode_mark->mask); marks_ignored_mask = (vfsmnt_mark->ignored_mask | inode_mark->ignored_mask); @@ -194,16 +196,29 @@ static bool fanotify_should_send_event(struct fsnotify_group *group, BUG(); } + if (S_ISDIR(path->dentry->d_inode->i_mode) && + (marks_ignored_mask & FS_ISDIR)) + return false; + if (event_mask & marks_mask & ~marks_ignored_mask) return true; return false; } +static void fanotify_free_group_priv(struct fsnotify_group *group) +{ + struct user_struct *user; + + user = group->fanotify_data.user; + atomic_dec(&user->fanotify_listeners); + free_uid(user); +} + const struct fsnotify_ops fanotify_fsnotify_ops = { .handle_event = fanotify_handle_event, .should_send_event = fanotify_should_send_event, - .free_group_priv = NULL, + .free_group_priv = fanotify_free_group_priv, .free_event_priv = NULL, .freeing_mark = NULL, }; diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index bbcb98e7fcc6..063224812b7e 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -16,6 +16,10 @@ #include <asm/ioctls.h> +#define FANOTIFY_DEFAULT_MAX_EVENTS 16384 +#define FANOTIFY_DEFAULT_MAX_MARKS 8192 +#define FANOTIFY_DEFAULT_MAX_LISTENERS 128 + extern const struct fsnotify_ops fanotify_fsnotify_ops; static struct kmem_cache *fanotify_mark_cache __read_mostly; @@ -326,7 +330,7 @@ static ssize_t fanotify_read(struct file *file, char __user *buf, ret = -EAGAIN; if (file->f_flags & O_NONBLOCK) break; - ret = -EINTR; + ret = -ERESTARTSYS; if (signal_pending(current)) break; @@ -372,11 +376,10 @@ static ssize_t fanotify_write(struct file *file, const char __user *buf, size_t static int fanotify_release(struct inode *ignored, struct file *file) { struct fsnotify_group *group = file->private_data; - struct fanotify_response_event *re, *lre; - - pr_debug("%s: file=%p group=%p\n", __func__, file, group); #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS + struct fanotify_response_event *re, *lre; + mutex_lock(&group->fanotify_data.access_mutex); group->fanotify_data.bypass_perm = true; @@ -554,18 +557,24 @@ static __u32 fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark, __u32 mask, unsigned int flags) { - __u32 oldmask; + __u32 oldmask = -1; spin_lock(&fsn_mark->lock); if (!(flags & FAN_MARK_IGNORED_MASK)) { oldmask = fsn_mark->mask; fsnotify_set_mark_mask_locked(fsn_mark, (oldmask | mask)); } else { - oldmask = fsn_mark->ignored_mask; - fsnotify_set_mark_ignored_mask_locked(fsn_mark, (oldmask | mask)); + __u32 tmask = fsn_mark->ignored_mask | mask; + fsnotify_set_mark_ignored_mask_locked(fsn_mark, tmask); if (flags & FAN_MARK_IGNORED_SURV_MODIFY) fsn_mark->flags |= FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY; } + + if (!(flags & FAN_MARK_ONDIR)) { + __u32 tmask = fsn_mark->ignored_mask | FAN_ONDIR; + fsnotify_set_mark_ignored_mask_locked(fsn_mark, tmask); + } + spin_unlock(&fsn_mark->lock); return mask & ~oldmask; @@ -582,6 +591,9 @@ static int fanotify_add_vfsmount_mark(struct fsnotify_group *group, if (!fsn_mark) { int ret; + if (atomic_read(&group->num_marks) > group->fanotify_data.max_marks) + return -ENOSPC; + fsn_mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL); if (!fsn_mark) return -ENOMEM; @@ -610,10 +622,23 @@ static int fanotify_add_inode_mark(struct fsnotify_group *group, pr_debug("%s: group=%p inode=%p\n", __func__, group, inode); + /* + * If some other task has this inode open for write we should not add + * an ignored mark, unless that ignored mark is supposed to survive + * modification changes anyway. + */ + if ((flags & FAN_MARK_IGNORED_MASK) && + !(flags & FAN_MARK_IGNORED_SURV_MODIFY) && + (atomic_read(&inode->i_writecount) > 0)) + return 0; + fsn_mark = fsnotify_find_inode_mark(group, inode); if (!fsn_mark) { int ret; + if (atomic_read(&group->num_marks) > group->fanotify_data.max_marks) + return -ENOSPC; + fsn_mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL); if (!fsn_mark) return -ENOMEM; @@ -637,6 +662,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) { struct fsnotify_group *group; int f_flags, fd; + struct user_struct *user; pr_debug("%s: flags=%d event_f_flags=%d\n", __func__, flags, event_f_flags); @@ -647,6 +673,12 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) if (flags & ~FAN_ALL_INIT_FLAGS) return -EINVAL; + user = get_current_user(); + if (atomic_read(&user->fanotify_listeners) > FANOTIFY_DEFAULT_MAX_LISTENERS) { + free_uid(user); + return -EMFILE; + } + f_flags = O_RDWR | FMODE_NONOTIFY; if (flags & FAN_CLOEXEC) f_flags |= O_CLOEXEC; @@ -658,12 +690,47 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) if (IS_ERR(group)) return PTR_ERR(group); + group->fanotify_data.user = user; + atomic_inc(&user->fanotify_listeners); + group->fanotify_data.f_flags = event_f_flags; #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS mutex_init(&group->fanotify_data.access_mutex); init_waitqueue_head(&group->fanotify_data.access_waitq); INIT_LIST_HEAD(&group->fanotify_data.access_list); #endif + switch (flags & FAN_ALL_CLASS_BITS) { + case FAN_CLASS_NOTIF: + group->priority = FS_PRIO_0; + break; + case FAN_CLASS_CONTENT: + group->priority = FS_PRIO_1; + break; + case FAN_CLASS_PRE_CONTENT: + group->priority = FS_PRIO_2; + break; + default: + fd = -EINVAL; + goto out_put_group; + } + + if (flags & FAN_UNLIMITED_QUEUE) { + fd = -EPERM; + if (!capable(CAP_SYS_ADMIN)) + goto out_put_group; + group->max_events = UINT_MAX; + } else { + group->max_events = FANOTIFY_DEFAULT_MAX_EVENTS; + } + + if (flags & FAN_UNLIMITED_MARKS) { + fd = -EPERM; + if (!capable(CAP_SYS_ADMIN)) + goto out_put_group; + group->fanotify_data.max_marks = UINT_MAX; + } else { + group->fanotify_data.max_marks = FANOTIFY_DEFAULT_MAX_MARKS; + } fd = anon_inode_getfd("[fanotify]", &fanotify_fops, group, f_flags); if (fd < 0) @@ -704,6 +771,12 @@ SYSCALL_DEFINE(fanotify_mark)(int fanotify_fd, unsigned int flags, default: return -EINVAL; } + + if (mask & FAN_ONDIR) { + flags |= FAN_MARK_ONDIR; + mask &= ~FAN_ONDIR; + } + #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS if (mask & ~(FAN_ALL_EVENTS | FAN_ALL_PERM_EVENTS | FAN_EVENT_ON_CHILD)) #else @@ -719,6 +792,16 @@ SYSCALL_DEFINE(fanotify_mark)(int fanotify_fd, unsigned int flags, ret = -EINVAL; if (unlikely(filp->f_op != &fanotify_fops)) goto fput_and_out; + group = filp->private_data; + + /* + * group->priority == FS_PRIO_0 == FAN_CLASS_NOTIF. These are not + * allowed to set permissions events. + */ + ret = -EINVAL; + if (mask & FAN_ALL_PERM_EVENTS && + group->priority == FS_PRIO_0) + goto fput_and_out; ret = fanotify_find_path(dfd, pathname, &path, flags); if (ret) @@ -729,7 +812,6 @@ SYSCALL_DEFINE(fanotify_mark)(int fanotify_fd, unsigned int flags, inode = path.dentry->d_inode; else mnt = path.mnt; - group = filp->private_data; /* create/update an inode mark */ switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE | FAN_MARK_FLUSH)) { diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 36802420d69a..20dc218707ca 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -84,59 +84,39 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode) } /* Notify this dentry's parent about a child's events. */ -void __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask) +int __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask) { struct dentry *parent; struct inode *p_inode; - bool send = false; - bool should_update_children = false; + int ret = 0; if (!dentry) dentry = path->dentry; if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED)) - return; + return 0; - spin_lock(&dentry->d_lock); - parent = dentry->d_parent; + parent = dget_parent(dentry); p_inode = parent->d_inode; - if (fsnotify_inode_watches_children(p_inode)) { - if (p_inode->i_fsnotify_mask & mask) { - dget(parent); - send = true; - } - } else { - /* - * The parent doesn't care about events on it's children but - * at least one child thought it did. We need to run all the - * children and update their d_flags to let them know p_inode - * doesn't care about them any more. - */ - dget(parent); - should_update_children = true; - } - - spin_unlock(&dentry->d_lock); - - if (send) { + if (unlikely(!fsnotify_inode_watches_children(p_inode))) + __fsnotify_update_child_dentry_flags(p_inode); + else if (p_inode->i_fsnotify_mask & mask) { /* we are notifying a parent so come up with the new mask which * specifies these are events which came from a child. */ mask |= FS_EVENT_ON_CHILD; if (path) - fsnotify(p_inode, mask, path, FSNOTIFY_EVENT_PATH, - dentry->d_name.name, 0); + ret = fsnotify(p_inode, mask, path, FSNOTIFY_EVENT_PATH, + dentry->d_name.name, 0); else - fsnotify(p_inode, mask, dentry->d_inode, FSNOTIFY_EVENT_INODE, - dentry->d_name.name, 0); - dput(parent); + ret = fsnotify(p_inode, mask, dentry->d_inode, FSNOTIFY_EVENT_INODE, + dentry->d_name.name, 0); } - if (unlikely(should_update_children)) { - __fsnotify_update_child_dentry_flags(p_inode); - dput(parent); - } + dput(parent); + + return ret; } EXPORT_SYMBOL_GPL(__fsnotify_parent); @@ -275,20 +255,23 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is, if (inode_group > vfsmount_group) { /* handle inode */ - send_to_group(to_tell, NULL, inode_mark, NULL, mask, data, - data_is, cookie, file_name, &event); + ret = send_to_group(to_tell, NULL, inode_mark, NULL, mask, data, + data_is, cookie, file_name, &event); /* we didn't use the vfsmount_mark */ vfsmount_group = NULL; } else if (vfsmount_group > inode_group) { - send_to_group(to_tell, mnt, NULL, vfsmount_mark, mask, data, - data_is, cookie, file_name, &event); + ret = send_to_group(to_tell, mnt, NULL, vfsmount_mark, mask, data, + data_is, cookie, file_name, &event); inode_group = NULL; } else { - send_to_group(to_tell, mnt, inode_mark, vfsmount_mark, - mask, data, data_is, cookie, file_name, - &event); + ret = send_to_group(to_tell, mnt, inode_mark, vfsmount_mark, + mask, data, data_is, cookie, file_name, + &event); } + if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS)) + goto out; + if (inode_group) inode_node = srcu_dereference(inode_node->next, &fsnotify_mark_srcu); @@ -296,7 +279,8 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is, vfsmount_node = srcu_dereference(vfsmount_node->next, &fsnotify_mark_srcu); } - + ret = 0; +out: srcu_read_unlock(&fsnotify_mark_srcu, idx); /* * fsnotify_create_event() took a reference so the event can't be cleaned diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c index 33297c005060..4c29fcf557d1 100644 --- a/fs/notify/inode_mark.c +++ b/fs/notify/inode_mark.c @@ -177,7 +177,8 @@ void fsnotify_set_inode_mark_mask_locked(struct fsnotify_mark *mark, * Attach an initialized mark to a given inode. * These marks may be used for the fsnotify backend to determine which * event types should be delivered to which group and for which inodes. These - * marks are ordered according to the group's location in memory. + * marks are ordered according to priority, highest number first, and then by + * the group's location in memory. */ int fsnotify_add_inode_mark(struct fsnotify_mark *mark, struct fsnotify_group *group, struct inode *inode, @@ -211,7 +212,11 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark, goto out; } - if (mark->group < lmark->group) + if (mark->group->priority < lmark->group->priority) + continue; + + if ((mark->group->priority == lmark->group->priority) && + (mark->group < lmark->group)) continue; hlist_add_before_rcu(&mark->i.i_list, &lmark->i.i_list); @@ -240,6 +245,7 @@ void fsnotify_unmount_inodes(struct list_head *list) { struct inode *inode, *next_i, *need_iput = NULL; + spin_lock(&inode_lock); list_for_each_entry_safe(inode, next_i, list, i_sb_list) { struct inode *need_iput_tmp; @@ -297,4 +303,5 @@ void fsnotify_unmount_inodes(struct list_head *list) spin_lock(&inode_lock); } + spin_unlock(&inode_lock); } diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 24edc1185d53..444c305a468c 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -862,7 +862,7 @@ static int __init inotify_user_setup(void) BUILD_BUG_ON(IN_Q_OVERFLOW != FS_Q_OVERFLOW); BUILD_BUG_ON(IN_IGNORED != FS_IN_IGNORED); BUILD_BUG_ON(IN_EXCL_UNLINK != FS_EXCL_UNLINK); - BUILD_BUG_ON(IN_ISDIR != FS_IN_ISDIR); + BUILD_BUG_ON(IN_ISDIR != FS_ISDIR); BUILD_BUG_ON(IN_ONESHOT != FS_IN_ONESHOT); BUG_ON(hweight32(ALL_INOTIFY_BITS) != 21); diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c index 56772b578fbd..85eebff6d0d7 100644 --- a/fs/notify/vfsmount_mark.c +++ b/fs/notify/vfsmount_mark.c @@ -169,7 +169,11 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark, goto out; } - if (mark->group < lmark->group) + if (mark->group->priority < lmark->group->priority) + continue; + + if ((mark->group->priority == lmark->group->priority) && + (mark->group < lmark->group)) continue; hlist_add_before_rcu(&mark->m.m_list, &lmark->m.m_list); diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 19c5180f8a28..a30ecacc01f2 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -2911,8 +2911,8 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent) goto unl_upcase_iput_tmp_ino_err_out_now; } if ((sb->s_root = d_alloc_root(vol->root_ino))) { - /* We increment i_count simulating an ntfs_iget(). */ - atomic_inc(&vol->root_ino->i_count); + /* We grab a reference, simulating an ntfs_iget(). */ + ihold(vol->root_ino); ntfs_debug("Exiting, status successful."); /* Release the default upcase if it has no users. */ mutex_lock(&ntfs_lock); @@ -3021,21 +3021,6 @@ iput_tmp_ino_err_out_now: if (vol->mft_ino && vol->mft_ino != tmp_ino) iput(vol->mft_ino); vol->mft_ino = NULL; - /* - * This is needed to get ntfs_clear_extent_inode() called for each - * inode we have ever called ntfs_iget()/iput() on, otherwise we A) - * leak resources and B) a subsequent mount fails automatically due to - * ntfs_iget() never calling down into our ntfs_read_locked_inode() - * method again... FIXME: Do we need to do this twice now because of - * attribute inodes? I think not, so leave as is for now... (AIA) - */ - if (invalidate_inodes(sb)) { - ntfs_error(sb, "Busy inodes left. This is most likely a NTFS " - "driver bug."); - /* Copied from fs/super.c. I just love this message. (-; */ - printk("NTFS: Busy inodes after umount. Self-destruct in 5 " - "seconds. Have a nice day...\n"); - } /* Errors at this stage are irrelevant. */ err_out_now: sb->s_fs_info = NULL; @@ -3074,17 +3059,16 @@ struct kmem_cache *ntfs_index_ctx_cache; /* Driver wide mutex. */ DEFINE_MUTEX(ntfs_lock); -static int ntfs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *ntfs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, ntfs_fill_super, - mnt); + return mount_bdev(fs_type, flags, dev_name, data, ntfs_fill_super); } static struct file_system_type ntfs_fs_type = { .owner = THIS_MODULE, .name = "ntfs", - .get_sb = ntfs_get_sb, + .mount = ntfs_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 5cfeee118158..f1e962cb3b73 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -165,7 +165,7 @@ int ocfs2_get_block(struct inode *inode, sector_t iblock, * ocfs2 never allocates in this function - the only time we * need to use BH_New is when we're extending i_size on a file * system which doesn't support holes, in which case BH_New - * allows block_prepare_write() to zero. + * allows __block_write_begin() to zero. * * If we see this on a sparse file system, then a truncate has * raced us and removed the cluster. In this case, we clear @@ -407,21 +407,6 @@ static int ocfs2_writepage(struct page *page, struct writeback_control *wbc) return ret; } -/* - * This is called from ocfs2_write_zero_page() which has handled it's - * own cluster locking and has ensured allocation exists for those - * blocks to be written. - */ -int ocfs2_prepare_write_nolock(struct inode *inode, struct page *page, - unsigned from, unsigned to) -{ - int ret; - - ret = block_prepare_write(page, from, to, ocfs2_get_block); - - return ret; -} - /* Taken from ext3. We don't necessarily need the full blown * functionality yet, but IMHO it's better to cut and paste the whole * thing so we can avoid introducing our own bugs (and easily pick up @@ -732,7 +717,7 @@ static int ocfs2_should_read_blk(struct inode *inode, struct page *page, } /* - * Some of this taken from block_prepare_write(). We already have our + * Some of this taken from __block_write_begin(). We already have our * mapping by now though, and the entire write will be allocating or * it won't, so not much need to use BH_New. * diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h index 7606f663da6d..76bfdfda691a 100644 --- a/fs/ocfs2/aops.h +++ b/fs/ocfs2/aops.h @@ -22,9 +22,6 @@ #ifndef OCFS2_AOPS_H #define OCFS2_AOPS_H -int ocfs2_prepare_write_nolock(struct inode *inode, struct page *page, - unsigned from, unsigned to); - handle_t *ocfs2_start_walk_page_trans(struct inode *inode, struct page *page, unsigned from, diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 52c7557f3e25..9f26ac9be2a4 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -1964,8 +1964,10 @@ static struct config_item *o2hb_heartbeat_group_make_item(struct config_group *g if (reg == NULL) return ERR_PTR(-ENOMEM); - if (strlen(name) > O2HB_MAX_REGION_NAME_LEN) - return ERR_PTR(-ENAMETOOLONG); + if (strlen(name) > O2HB_MAX_REGION_NAME_LEN) { + ret = -ENAMETOOLONG; + goto free; + } spin_lock(&o2hb_live_lock); reg->hr_region_num = 0; @@ -1974,7 +1976,8 @@ static struct config_item *o2hb_heartbeat_group_make_item(struct config_group *g O2NM_MAX_REGIONS); if (reg->hr_region_num >= O2NM_MAX_REGIONS) { spin_unlock(&o2hb_live_lock); - return ERR_PTR(-EFBIG); + ret = -EFBIG; + goto free; } set_bit(reg->hr_region_num, o2hb_region_bitmap); } @@ -1986,10 +1989,13 @@ static struct config_item *o2hb_heartbeat_group_make_item(struct config_group *g ret = o2hb_debug_region_init(reg, o2hb_debug_dir); if (ret) { config_item_put(®->hr_item); - return ERR_PTR(ret); + goto free; } return ®->hr_item; +free: + kfree(reg); + return ERR_PTR(ret); } static void o2hb_heartbeat_group_drop_item(struct config_group *group, diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c index edaded48e7e9..895532ac4d98 100644 --- a/fs/ocfs2/dcache.c +++ b/fs/ocfs2/dcache.c @@ -476,7 +476,6 @@ static void ocfs2_dentry_iput(struct dentry *dentry, struct inode *inode) out: iput(inode); - ocfs2_dentry_attach_gen(dentry); } /* diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index 58a93b953735..cc2aaa96cfe5 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -959,7 +959,7 @@ static int dlm_match_regions(struct dlm_ctxt *dlm, r += O2HB_MAX_REGION_NAME_LEN; } - local = kmalloc(sizeof(qr->qr_regions), GFP_KERNEL); + local = kmalloc(sizeof(qr->qr_regions), GFP_ATOMIC); if (!local) { status = -ENOMEM; goto bail; diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index a7ebd9d42dc8..b2df490a19ed 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -400,6 +400,7 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb) if (inode) { ip = DLMFS_I(inode); + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); @@ -425,6 +426,7 @@ static struct inode *dlmfs_get_inode(struct inode *parent, if (!inode) return NULL; + inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); @@ -641,16 +643,16 @@ static const struct inode_operations dlmfs_file_inode_operations = { .setattr = dlmfs_file_setattr, }; -static int dlmfs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *dlmfs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_nodev(fs_type, flags, data, dlmfs_fill_super, mnt); + return mount_nodev(fs_type, flags, data, dlmfs_fill_super); } static struct file_system_type dlmfs_fs_type = { .owner = THIS_MODULE, .name = "ocfs2_dlmfs", - .get_sb = dlmfs_get_sb, + .mount = dlmfs_mount, .kill_sb = kill_litter_super, }; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 1ca6867935bb..77b4c04a2809 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -796,13 +796,12 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, block_end = block_start + (1 << inode->i_blkbits); /* - * block_start is block-aligned. Bump it by one to - * force ocfs2_{prepare,commit}_write() to zero the + * block_start is block-aligned. Bump it by one to force + * __block_write_begin and block_commit_write to zero the * whole block. */ - ret = ocfs2_prepare_write_nolock(inode, page, - block_start + 1, - block_start + 1); + ret = __block_write_begin(page, block_start + 1, 0, + ocfs2_get_block); if (ret < 0) { mlog_errno(ret); goto out_unlock; diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index e7bde21149ae..ff5744e1e36f 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -742,7 +742,7 @@ static int ocfs2_link(struct dentry *old_dentry, goto out_commit; } - atomic_inc(&inode->i_count); + ihold(inode); dentry->d_op = &ocfs2_dentry_ops; d_instantiate(dentry, inode); diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index d8408217e3bd..70dd3b1798f1 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -159,7 +159,9 @@ struct ocfs2_lock_res { char l_name[OCFS2_LOCK_ID_MAX_LEN]; unsigned int l_ro_holders; unsigned int l_ex_holders; - unsigned char l_level; + signed char l_level; + signed char l_requested; + signed char l_blocking; /* Data packed - type enum ocfs2_lock_type */ unsigned char l_type; @@ -169,8 +171,6 @@ struct ocfs2_lock_res { unsigned char l_action; /* Data packed - enum type ocfs2_unlock_action */ unsigned char l_unlock_action; - unsigned char l_requested; - unsigned char l_blocking; unsigned int l_pending_gen; spinlock_t l_lock; diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c index 252e7c82f929..a5ebe421195f 100644 --- a/fs/ocfs2/stack_user.c +++ b/fs/ocfs2/stack_user.c @@ -190,7 +190,7 @@ static struct ocfs2_live_connection *ocfs2_connection_find(const char *name) return c; } - return c; + return NULL; } /* diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 56f0cb395820..cfeab7ce3697 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -41,7 +41,6 @@ #include <linux/mount.h> #include <linux/seq_file.h> #include <linux/quotaops.h> -#include <linux/smp_lock.h> #define MLOG_MASK_PREFIX ML_SUPER #include <cluster/masklog.h> @@ -1236,14 +1235,12 @@ read_super_error: return status; } -static int ocfs2_get_sb(struct file_system_type *fs_type, +static struct dentry *ocfs2_mount(struct file_system_type *fs_type, int flags, const char *dev_name, - void *data, - struct vfsmount *mnt) + void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, ocfs2_fill_super, - mnt); + return mount_bdev(fs_type, flags, dev_name, data, ocfs2_fill_super); } static void ocfs2_kill_sb(struct super_block *sb) @@ -1267,8 +1264,7 @@ out: static struct file_system_type ocfs2_fs_type = { .owner = THIS_MODULE, .name = "ocfs2", - .get_sb = ocfs2_get_sb, /* is this called when we mount - * the fs? */ + .mount = ocfs2_mount, .kill_sb = ocfs2_kill_sb, .fs_flags = FS_REQUIRES_DEV|FS_RENAME_DOES_D_MOVE, diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c index 14a22863291a..e043c4cb9a97 100644 --- a/fs/omfs/inode.c +++ b/fs/omfs/inode.c @@ -557,17 +557,16 @@ end: return ret; } -static int omfs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, - void *data, struct vfsmount *m) +static struct dentry *omfs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, omfs_fill_super, m); + return mount_bdev(fs_type, flags, dev_name, data, omfs_fill_super); } static struct file_system_type omfs_fs_type = { .owner = THIS_MODULE, .name = "omfs", - .get_sb = omfs_get_sb, + .mount = omfs_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/open.c b/fs/open.c index d74e1983e8dc..4197b9ed023d 100644 --- a/fs/open.c +++ b/fs/open.c @@ -786,11 +786,11 @@ struct file *nameidata_to_filp(struct nameidata *nd) /* Pick up the filp from the open intent */ filp = nd->intent.open.file; /* Has the filesystem initialised the file for us? */ - if (filp->f_path.dentry == NULL) + if (filp->f_path.dentry == NULL) { + path_get(&nd->path); filp = __dentry_open(nd->path.dentry, nd->path.mnt, filp, NULL, cred); - else - path_put(&nd->path); + } return filp; } diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c index ffcd04f0012c..911e61f348fc 100644 --- a/fs/openpromfs/inode.c +++ b/fs/openpromfs/inode.c @@ -415,16 +415,16 @@ out_no_root: return ret; } -static int openprom_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *openprom_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_single(fs_type, flags, data, openprom_fill_super, mnt); + return mount_single(fs_type, flags, data, openprom_fill_super); } static struct file_system_type openprom_fs_type = { .owner = THIS_MODULE, .name = "openpromfs", - .get_sb = openprom_get_sb, + .mount = openprom_mount, .kill_sb = kill_anon_super, }; diff --git a/fs/pipe.c b/fs/pipe.c index 37eb1ebeaa90..04629f36e397 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -954,6 +954,8 @@ static struct inode * get_pipe_inode(void) if (!inode) goto fail_inode; + inode->i_ino = get_next_ino(); + pipe = alloc_pipe_info(inode); if (!pipe) goto fail_iput; @@ -1197,12 +1199,24 @@ int pipe_proc_fn(struct ctl_table *table, int write, void __user *buf, return ret; } +/* + * After the inode slimming patch, i_pipe/i_bdev/i_cdev share the same + * location, so checking ->i_pipe is not enough to verify that this is a + * pipe. + */ +struct pipe_inode_info *get_pipe_info(struct file *file) +{ + struct inode *i = file->f_path.dentry->d_inode; + + return S_ISFIFO(i->i_mode) ? i->i_pipe : NULL; +} + long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg) { struct pipe_inode_info *pipe; long ret; - pipe = file->f_path.dentry->d_inode->i_pipe; + pipe = get_pipe_info(file); if (!pipe) return -EBADF; @@ -1245,16 +1259,15 @@ out: * any operations on the root directory. However, we need a non-trivial * d_name - pipe: will go nicely and kill the special-casing in procfs. */ -static int pipefs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, - struct vfsmount *mnt) +static struct dentry *pipefs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_pseudo(fs_type, "pipe:", NULL, PIPEFS_MAGIC, mnt); + return mount_pseudo(fs_type, "pipe:", NULL, PIPEFS_MAGIC); } static struct file_system_type pipe_fs_type = { .name = "pipefs", - .get_sb = pipefs_get_sb, + .mount = pipefs_mount, .kill_sb = kill_anon_super, }; diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index 50f8f0600f06..6a0068841d96 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -33,8 +33,8 @@ config PROC_KCORE depends on PROC_FS && MMU config PROC_VMCORE - bool "/proc/vmcore support (EXPERIMENTAL)" - depends on PROC_FS && CRASH_DUMP + bool "/proc/vmcore support" + depends on PROC_FS && CRASH_DUMP default y help Exports the dump image of crashed kernel in ELF format. diff --git a/fs/proc/base.c b/fs/proc/base.c index dc5d5f51f3fe..182845147fe4 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -226,7 +226,7 @@ struct mm_struct *mm_for_maps(struct task_struct *task) { struct mm_struct *mm; - if (mutex_lock_killable(&task->cred_guard_mutex)) + if (mutex_lock_killable(&task->signal->cred_guard_mutex)) return NULL; mm = get_task_mm(task); @@ -235,7 +235,7 @@ struct mm_struct *mm_for_maps(struct task_struct *task) mmput(mm); mm = NULL; } - mutex_unlock(&task->cred_guard_mutex); + mutex_unlock(&task->signal->cred_guard_mutex); return mm; } @@ -771,6 +771,8 @@ static const struct file_operations proc_single_file_operations = { static int mem_open(struct inode* inode, struct file* file) { file->private_data = (void*)((long)current->self_exec_id); + /* OK to pass negative loff_t, we can catch out-of-range */ + file->f_mode |= FMODE_UNSIGNED_OFFSET; return 0; } @@ -1023,28 +1025,47 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf, memset(buffer, 0, sizeof(buffer)); if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; - if (copy_from_user(buffer, buf, count)) - return -EFAULT; + if (copy_from_user(buffer, buf, count)) { + err = -EFAULT; + goto out; + } err = strict_strtol(strstrip(buffer), 0, &oom_adjust); if (err) - return -EINVAL; + goto out; if ((oom_adjust < OOM_ADJUST_MIN || oom_adjust > OOM_ADJUST_MAX) && - oom_adjust != OOM_DISABLE) - return -EINVAL; + oom_adjust != OOM_DISABLE) { + err = -EINVAL; + goto out; + } task = get_proc_task(file->f_path.dentry->d_inode); - if (!task) - return -ESRCH; + if (!task) { + err = -ESRCH; + goto out; + } + + task_lock(task); + if (!task->mm) { + err = -EINVAL; + goto err_task_lock; + } + if (!lock_task_sighand(task, &flags)) { - put_task_struct(task); - return -ESRCH; + err = -ESRCH; + goto err_task_lock; } if (oom_adjust < task->signal->oom_adj && !capable(CAP_SYS_RESOURCE)) { - unlock_task_sighand(task, &flags); - put_task_struct(task); - return -EACCES; + err = -EACCES; + goto err_sighand; + } + + if (oom_adjust != task->signal->oom_adj) { + if (oom_adjust == OOM_DISABLE) + atomic_inc(&task->mm->oom_disable_count); + if (task->signal->oom_adj == OOM_DISABLE) + atomic_dec(&task->mm->oom_disable_count); } /* @@ -1065,10 +1086,13 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf, else task->signal->oom_score_adj = (oom_adjust * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE; +err_sighand: unlock_task_sighand(task, &flags); +err_task_lock: + task_unlock(task); put_task_struct(task); - - return count; +out: + return err < 0 ? err : count; } static const struct file_operations proc_oom_adjust_operations = { @@ -1109,30 +1133,49 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf, memset(buffer, 0, sizeof(buffer)); if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; - if (copy_from_user(buffer, buf, count)) - return -EFAULT; + if (copy_from_user(buffer, buf, count)) { + err = -EFAULT; + goto out; + } err = strict_strtol(strstrip(buffer), 0, &oom_score_adj); if (err) - return -EINVAL; + goto out; if (oom_score_adj < OOM_SCORE_ADJ_MIN || - oom_score_adj > OOM_SCORE_ADJ_MAX) - return -EINVAL; + oom_score_adj > OOM_SCORE_ADJ_MAX) { + err = -EINVAL; + goto out; + } task = get_proc_task(file->f_path.dentry->d_inode); - if (!task) - return -ESRCH; + if (!task) { + err = -ESRCH; + goto out; + } + + task_lock(task); + if (!task->mm) { + err = -EINVAL; + goto err_task_lock; + } + if (!lock_task_sighand(task, &flags)) { - put_task_struct(task); - return -ESRCH; + err = -ESRCH; + goto err_task_lock; } + if (oom_score_adj < task->signal->oom_score_adj && !capable(CAP_SYS_RESOURCE)) { - unlock_task_sighand(task, &flags); - put_task_struct(task); - return -EACCES; + err = -EACCES; + goto err_sighand; } + if (oom_score_adj != task->signal->oom_score_adj) { + if (oom_score_adj == OOM_SCORE_ADJ_MIN) + atomic_inc(&task->mm->oom_disable_count); + if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) + atomic_dec(&task->mm->oom_disable_count); + } task->signal->oom_score_adj = oom_score_adj; /* * Scale /proc/pid/oom_adj appropriately ensuring that OOM_DISABLE is @@ -1143,9 +1186,13 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf, else task->signal->oom_adj = (oom_score_adj * OOM_ADJUST_MAX) / OOM_SCORE_ADJ_MAX; +err_sighand: unlock_task_sighand(task, &flags); +err_task_lock: + task_unlock(task); put_task_struct(task); - return count; +out: + return err < 0 ? err : count; } static const struct file_operations proc_oom_score_adj_operations = { @@ -1527,7 +1574,7 @@ static int do_proc_readlink(struct path *path, char __user *buffer, int buflen) if (!tmp) return -ENOMEM; - pathname = d_path_with_unreachable(path, tmp, PAGE_SIZE); + pathname = d_path(path, tmp, PAGE_SIZE); len = PTR_ERR(pathname); if (IS_ERR(pathname)) goto out; @@ -1601,6 +1648,7 @@ static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_st /* Common stuff */ ei = PROC_I(inode); + inode->i_ino = get_next_ino(); inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; inode->i_op = &proc_def_inode_operations; @@ -2306,14 +2354,14 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, goto out_free; /* Guard against adverse ptrace interaction */ - length = mutex_lock_interruptible(&task->cred_guard_mutex); + length = mutex_lock_interruptible(&task->signal->cred_guard_mutex); if (length < 0) goto out_free; length = security_setprocattr(task, (char*)file->f_path.dentry->d_name.name, (void*)page, count); - mutex_unlock(&task->cred_guard_mutex); + mutex_unlock(&task->signal->cred_guard_mutex); out_free: free_page((unsigned long) page); out: @@ -2547,6 +2595,7 @@ static struct dentry *proc_base_instantiate(struct inode *dir, /* Initialize the inode */ ei = PROC_I(inode); + inode->i_ino = get_next_ino(); inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; /* diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 9c2b5f484879..3ddb6068177c 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -16,7 +16,6 @@ #include <linux/limits.h> #include <linux/init.h> #include <linux/module.h> -#include <linux/smp_lock.h> #include <linux/sysctl.h> #include <linux/slab.h> diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 2fc52552271d..b652cb00906b 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -23,6 +23,8 @@ static struct inode *proc_sys_make_inode(struct super_block *sb, if (!inode) goto out; + inode->i_ino = get_next_ino(); + sysctl_head_get(head); ei = PROC_I(inode); ei->sysctl = head; diff --git a/fs/proc/root.c b/fs/proc/root.c index 93d99b316325..ef9fa8e24ad6 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -35,8 +35,8 @@ static int proc_set_super(struct super_block *sb, void *data) return set_anon_super(sb, NULL); } -static int proc_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *proc_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { int err; struct super_block *sb; @@ -61,14 +61,14 @@ static int proc_get_sb(struct file_system_type *fs_type, sb = sget(fs_type, proc_test_super, proc_set_super, ns); if (IS_ERR(sb)) - return PTR_ERR(sb); + return ERR_CAST(sb); if (!sb->s_root) { sb->s_flags = flags; err = proc_fill_super(sb); if (err) { deactivate_locked_super(sb); - return err; + return ERR_PTR(err); } ei = PROC_I(sb->s_root->d_inode); @@ -79,11 +79,9 @@ static int proc_get_sb(struct file_system_type *fs_type, } sb->s_flags |= MS_ACTIVE; - ns->proc_mnt = mnt; } - simple_set_mnt(mnt, sb); - return 0; + return dget(sb->s_root); } static void proc_kill_sb(struct super_block *sb) @@ -97,7 +95,7 @@ static void proc_kill_sb(struct super_block *sb) static struct file_system_type proc_fs_type = { .name = "proc", - .get_sb = proc_get_sb, + .mount = proc_mount, .kill_sb = proc_kill_sb, }; @@ -115,6 +113,7 @@ void __init proc_root_init(void) return; } + init_pid_ns.proc_mnt = proc_mnt; proc_symlink("mounts", NULL, "self/mounts"); proc_net_init(); @@ -213,6 +212,7 @@ int pid_ns_prepare_proc(struct pid_namespace *ns) if (IS_ERR(mnt)) return PTR_ERR(mnt); + ns->proc_mnt = mnt; return 0; } diff --git a/fs/proc/softirqs.c b/fs/proc/softirqs.c index 1807c2419f17..37994737c983 100644 --- a/fs/proc/softirqs.c +++ b/fs/proc/softirqs.c @@ -10,13 +10,13 @@ static int show_softirqs(struct seq_file *p, void *v) { int i, j; - seq_printf(p, " "); + seq_printf(p, " "); for_each_possible_cpu(i) seq_printf(p, "CPU%-8d", i); seq_printf(p, "\n"); for (i = 0; i < NR_SOFTIRQS; i++) { - seq_printf(p, "%8s:", softirq_to_name[i]); + seq_printf(p, "%12s:", softirq_to_name[i]); for_each_possible_cpu(j) seq_printf(p, " %10u", kstat_softirqs_cpu(i, j)); seq_printf(p, "\n"); diff --git a/fs/proc/stat.c b/fs/proc/stat.c index bf31b03fc275..e15a19c93bae 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -31,7 +31,6 @@ static int show_stat(struct seq_file *p, void *v) u64 sum_softirq = 0; unsigned int per_softirq_sums[NR_SOFTIRQS] = {0}; struct timespec boottime; - unsigned int per_irq_sum; user = nice = system = idle = iowait = irq = softirq = steal = cputime64_zero; @@ -52,9 +51,7 @@ static int show_stat(struct seq_file *p, void *v) guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest); guest_nice = cputime64_add(guest_nice, kstat_cpu(i).cpustat.guest_nice); - for_each_irq_nr(j) { - sum += kstat_irqs_cpu(j, i); - } + sum += kstat_cpu_irqs_sum(i); sum += arch_irq_stat_cpu(i); for (j = 0; j < NR_SOFTIRQS; j++) { @@ -110,13 +107,8 @@ static int show_stat(struct seq_file *p, void *v) 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); - } + for_each_irq_nr(j) + seq_printf(p, " %u", kstat_irqs(j)); seq_printf(p, "\nctxt %llu\n" diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 871e25ed0069..c126c83b9a45 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -327,6 +327,7 @@ struct mem_size_stats { unsigned long private_clean; unsigned long private_dirty; unsigned long referenced; + unsigned long anonymous; unsigned long swap; u64 pss; }; @@ -357,6 +358,9 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, if (!page) continue; + if (PageAnon(page)) + mss->anonymous += PAGE_SIZE; + mss->resident += PAGE_SIZE; /* Accumulate the size in pages that have been accessed. */ if (pte_young(ptent) || PageReferenced(page)) @@ -410,6 +414,7 @@ static int show_smap(struct seq_file *m, void *v) "Private_Clean: %8lu kB\n" "Private_Dirty: %8lu kB\n" "Referenced: %8lu kB\n" + "Anonymous: %8lu kB\n" "Swap: %8lu kB\n" "KernelPageSize: %8lu kB\n" "MMUPageSize: %8lu kB\n", @@ -421,6 +426,7 @@ static int show_smap(struct seq_file *m, void *v) mss.private_clean >> 10, mss.private_dirty >> 10, mss.referenced >> 10, + mss.anonymous >> 10, mss.swap >> 10, vma_kernel_pagesize(vma) >> 10, vma_mmu_pagesize(vma) >> 10); @@ -700,6 +706,7 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask, * skip over unmapped regions. */ #define PAGEMAP_WALK_SIZE (PMD_SIZE) +#define PAGEMAP_WALK_MASK (PMD_MASK) static ssize_t pagemap_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -770,7 +777,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, unsigned long end; pm.pos = 0; - end = start_vaddr + PAGEMAP_WALK_SIZE; + end = (start_vaddr + PAGEMAP_WALK_SIZE) & PAGEMAP_WALK_MASK; /* overflow ? */ if (end < start_vaddr || end > end_vaddr) end = end_vaddr; diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index 01bad30026fc..fcada42f1aa3 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -454,17 +454,16 @@ static void destroy_inodecache(void) kmem_cache_destroy(qnx4_inode_cachep); } -static int qnx4_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *qnx4_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, qnx4_fill_super, - mnt); + return mount_bdev(fs_type, flags, dev_name, data, qnx4_fill_super); } static struct file_system_type qnx4_fs_type = { .owner = THIS_MODULE, .name = "qnx4", - .get_sb = qnx4_get_sb, + .mount = qnx4_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/quota/Kconfig b/fs/quota/Kconfig index 3e21b1e2ad3a..880fd9884366 100644 --- a/fs/quota/Kconfig +++ b/fs/quota/Kconfig @@ -4,6 +4,7 @@ config QUOTA bool "Quota support" + select QUOTACTL help If you say Y here, you will be able to set per user limits for disk usage (also called disk quotas). Currently, it works for the @@ -65,8 +66,7 @@ config QFMT_V2 config QUOTACTL bool - depends on XFS_QUOTA || QUOTA - default y + default n config QUOTACTL_COMPAT bool diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index aad1316a977f..0fed41e6efcd 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -1386,6 +1386,9 @@ static void __dquot_initialize(struct inode *inode, int type) /* Avoid races with quotaoff() */ if (!sb_has_quota_active(sb, cnt)) continue; + /* We could race with quotaon or dqget() could have failed */ + if (!got[cnt]) + continue; if (!inode->i_dquot[cnt]) { inode->i_dquot[cnt] = got[cnt]; got[cnt] = NULL; @@ -1736,6 +1739,7 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) qsize_t rsv_space = 0; struct dquot *transfer_from[MAXQUOTAS] = {}; int cnt, ret = 0; + char is_valid[MAXQUOTAS] = {}; char warntype_to[MAXQUOTAS]; char warntype_from_inodes[MAXQUOTAS], warntype_from_space[MAXQUOTAS]; @@ -1757,8 +1761,15 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) space = cur_space + rsv_space; /* Build the transfer_from list and check the limits */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { + /* + * Skip changes for same uid or gid or for turned off quota-type. + */ if (!transfer_to[cnt]) continue; + /* Avoid races with quotaoff() */ + if (!sb_has_quota_active(inode->i_sb, cnt)) + continue; + is_valid[cnt] = 1; transfer_from[cnt] = inode->i_dquot[cnt]; ret = check_idq(transfer_to[cnt], 1, warntype_to + cnt); if (ret) @@ -1772,12 +1783,8 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) * Finally perform the needed transfer from transfer_from to transfer_to */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - /* - * Skip changes for same uid or gid or for turned off quota-type. - */ - if (!transfer_to[cnt]) + if (!is_valid[cnt]) continue; - /* Due to IO error we might not have transfer_from[] structure */ if (transfer_from[cnt]) { warntype_from_inodes[cnt] = @@ -1801,18 +1808,19 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) mark_all_dquot_dirty(transfer_from); mark_all_dquot_dirty(transfer_to); - /* Pass back references to put */ - for (cnt = 0; cnt < MAXQUOTAS; cnt++) - transfer_to[cnt] = transfer_from[cnt]; -warn: flush_warnings(transfer_to, warntype_to); flush_warnings(transfer_from, warntype_from_inodes); flush_warnings(transfer_from, warntype_from_space); - return ret; + /* Pass back references to put */ + for (cnt = 0; cnt < MAXQUOTAS; cnt++) + if (is_valid[cnt]) + transfer_to[cnt] = transfer_from[cnt]; + return 0; over_quota: spin_unlock(&dq_data_lock); up_write(&sb_dqopt(inode->i_sb)->dqptr_sem); - goto warn; + flush_warnings(transfer_to, warntype_to); + return ret; } EXPORT_SYMBOL(__dquot_transfer); diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index a5ebae70dc6d..eacb166fb259 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -58,6 +58,7 @@ struct inode *ramfs_get_inode(struct super_block *sb, struct inode * inode = new_inode(sb); if (inode) { + inode->i_ino = get_next_ino(); inode_init_owner(inode, dir, mode); inode->i_mapping->a_ops = &ramfs_aops; inode->i_mapping->backing_dev_info = &ramfs_backing_dev_info; @@ -254,17 +255,16 @@ fail: return err; } -int ramfs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +struct dentry *ramfs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_nodev(fs_type, flags, data, ramfs_fill_super, mnt); + return mount_nodev(fs_type, flags, data, ramfs_fill_super); } -static int rootfs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *rootfs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_nodev(fs_type, flags|MS_NOUSER, data, ramfs_fill_super, - mnt); + return mount_nodev(fs_type, flags|MS_NOUSER, data, ramfs_fill_super); } static void ramfs_kill_sb(struct super_block *sb) @@ -275,12 +275,12 @@ static void ramfs_kill_sb(struct super_block *sb) static struct file_system_type ramfs_fs_type = { .name = "ramfs", - .get_sb = ramfs_get_sb, + .mount = ramfs_mount, .kill_sb = ramfs_kill_sb, }; static struct file_system_type rootfs_fs_type = { .name = "rootfs", - .get_sb = rootfs_get_sb, + .mount = rootfs_mount, .kill_sb = kill_litter_super, }; diff --git a/fs/read_write.c b/fs/read_write.c index e757ef26e4ce..5d431bacbea9 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -9,7 +9,6 @@ #include <linux/fcntl.h> #include <linux/file.h> #include <linux/uio.h> -#include <linux/smp_lock.h> #include <linux/fsnotify.h> #include <linux/security.h> #include <linux/module.h> @@ -31,6 +30,20 @@ const struct file_operations generic_ro_fops = { EXPORT_SYMBOL(generic_ro_fops); +static int +__negative_fpos_check(struct file *file, loff_t pos, size_t count) +{ + /* + * pos or pos+count is negative here, check overflow. + * too big "count" will be caught in rw_verify_area(). + */ + if ((pos < 0) && (pos + count < pos)) + return -EOVERFLOW; + if (file->f_mode & FMODE_UNSIGNED_OFFSET) + return 0; + return -EINVAL; +} + /** * generic_file_llseek_unlocked - lockless generic llseek implementation * @file: file structure to seek on @@ -62,7 +75,9 @@ generic_file_llseek_unlocked(struct file *file, loff_t offset, int origin) break; } - if (offset < 0 || offset > inode->i_sb->s_maxbytes) + if (offset < 0 && __negative_fpos_check(file, offset, 0)) + return -EINVAL; + if (offset > inode->i_sb->s_maxbytes) return -EINVAL; /* Special lock needed here? */ @@ -137,7 +152,7 @@ loff_t default_llseek(struct file *file, loff_t offset, int origin) offset += file->f_pos; } retval = -EINVAL; - if (offset >= 0) { + if (offset >= 0 || !__negative_fpos_check(file, offset, 0)) { if (offset != file->f_pos) { file->f_pos = offset; file->f_version = 0; @@ -221,13 +236,12 @@ bad: } #endif + /* * rw_verify_area doesn't like huge counts. We limit * them to something that fits in "int" so that others * won't have to do range checks all the time. */ -#define MAX_RW_COUNT (INT_MAX & PAGE_CACHE_MASK) - int rw_verify_area(int read_write, struct file *file, loff_t *ppos, size_t count) { struct inode *inode; @@ -238,8 +252,11 @@ int rw_verify_area(int read_write, struct file *file, loff_t *ppos, size_t count if (unlikely((ssize_t) count < 0)) return retval; pos = *ppos; - if (unlikely((pos < 0) || (loff_t) (pos + count) < 0)) - return retval; + if (unlikely((pos < 0) || (loff_t) (pos + count) < 0)) { + retval = __negative_fpos_check(file, pos, count); + if (retval) + return retval; + } if (unlikely(inode->i_flock && mandatory_lock(inode))) { retval = locks_mandatory_area( @@ -564,65 +581,71 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_pointer, struct iovec **ret_pointer) - { +{ unsigned long seg; - ssize_t ret; + ssize_t ret; struct iovec *iov = fast_pointer; - /* - * SuS says "The readv() function *may* fail if the iovcnt argument - * was less than or equal to 0, or greater than {IOV_MAX}. Linux has - * traditionally returned zero for zero segments, so... - */ + /* + * SuS says "The readv() function *may* fail if the iovcnt argument + * was less than or equal to 0, or greater than {IOV_MAX}. Linux has + * traditionally returned zero for zero segments, so... + */ if (nr_segs == 0) { ret = 0; - goto out; + goto out; } - /* - * First get the "struct iovec" from user memory and - * verify all the pointers - */ + /* + * First get the "struct iovec" from user memory and + * verify all the pointers + */ if (nr_segs > UIO_MAXIOV) { ret = -EINVAL; - goto out; + goto out; } if (nr_segs > fast_segs) { - iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL); + iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL); if (iov == NULL) { ret = -ENOMEM; - goto out; + goto out; } - } + } if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector))) { ret = -EFAULT; - goto out; + goto out; } - /* + /* * According to the Single Unix Specification we should return EINVAL * if an element length is < 0 when cast to ssize_t or if the * total length would overflow the ssize_t return value of the * system call. - */ + * + * Linux caps all read/write calls to MAX_RW_COUNT, and avoids the + * overflow case. + */ ret = 0; - for (seg = 0; seg < nr_segs; seg++) { - void __user *buf = iov[seg].iov_base; - ssize_t len = (ssize_t)iov[seg].iov_len; + for (seg = 0; seg < nr_segs; seg++) { + void __user *buf = iov[seg].iov_base; + ssize_t len = (ssize_t)iov[seg].iov_len; /* see if we we're about to use an invalid len or if * it's about to overflow ssize_t */ - if (len < 0 || (ret + len < ret)) { + if (len < 0) { ret = -EINVAL; - goto out; + goto out; } if (unlikely(!access_ok(vrfy_dir(type), buf, len))) { ret = -EFAULT; - goto out; + goto out; + } + if (len > MAX_RW_COUNT - ret) { + len = MAX_RW_COUNT - ret; + iov[seg].iov_len = len; } - ret += len; - } + } out: *ret_pointer = iov; return ret; diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index caa758377d66..0bae036831e2 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -8,7 +8,6 @@ #include <linux/reiserfs_acl.h> #include <linux/reiserfs_xattr.h> #include <linux/exportfs.h> -#include <linux/smp_lock.h> #include <linux/pagemap.h> #include <linux/highmem.h> #include <linux/slab.h> @@ -22,8 +21,6 @@ int reiserfs_commit_write(struct file *f, struct page *page, unsigned from, unsigned to); -int reiserfs_prepare_write(struct file *f, struct page *page, - unsigned from, unsigned to); void reiserfs_evict_inode(struct inode *inode) { @@ -165,7 +162,7 @@ inline void make_le_item_head(struct item_head *ih, const struct cpu_key *key, ** but tail is still sitting in a direct item, and we can't write to ** it. So, look through this page, and check all the mapped buffers ** to make sure they have valid block numbers. Any that don't need -** to be unmapped, so that block_prepare_write will correctly call +** to be unmapped, so that __block_write_begin will correctly call ** reiserfs_get_block to convert the tail into an unformatted node */ static inline void fix_tail_page_for_writing(struct page *page) @@ -439,13 +436,13 @@ static int reiserfs_bmap(struct inode *inode, sector_t block, } /* special version of get_block that is only used by grab_tail_page right -** now. It is sent to block_prepare_write, and when you try to get a +** now. It is sent to __block_write_begin, and when you try to get a ** block past the end of the file (or a block from a hole) it returns -** -ENOENT instead of a valid buffer. block_prepare_write expects to +** -ENOENT instead of a valid buffer. __block_write_begin expects to ** be able to do i/o on the buffers returned, unless an error value ** is also returned. ** -** So, this allows block_prepare_write to be used for reading a single block +** So, this allows __block_write_begin to be used for reading a single block ** in a page. Where it does not produce a valid page for holes, or past the ** end of the file. This turns out to be exactly what we need for reading ** tails for conversion. @@ -558,11 +555,12 @@ static int convert_tail_for_hole(struct inode *inode, ** ** We must fix the tail page for writing because it might have buffers ** that are mapped, but have a block number of 0. This indicates tail - ** data that has been read directly into the page, and block_prepare_write - ** won't trigger a get_block in this case. + ** data that has been read directly into the page, and + ** __block_write_begin won't trigger a get_block in this case. */ fix_tail_page_for_writing(tail_page); - retval = reiserfs_prepare_write(NULL, tail_page, tail_start, tail_end); + retval = __reiserfs_write_begin(tail_page, tail_start, + tail_end - tail_start); if (retval) goto unlock; @@ -2033,7 +2031,7 @@ static int grab_tail_page(struct inode *inode, /* start within the page of the last block in the file */ start = (offset / blocksize) * blocksize; - error = block_prepare_write(page, start, offset, + error = __block_write_begin(page, start, offset - start, reiserfs_get_block_create_0); if (error) goto unlock; @@ -2438,7 +2436,7 @@ static int reiserfs_write_full_page(struct page *page, /* from this point on, we know the buffer is mapped to a * real block and not a direct item */ - if (wbc->sync_mode != WB_SYNC_NONE || !wbc->nonblocking) { + if (wbc->sync_mode != WB_SYNC_NONE) { lock_buffer(bh); } else { if (!trylock_buffer(bh)) { @@ -2628,8 +2626,7 @@ static int reiserfs_write_begin(struct file *file, return ret; } -int reiserfs_prepare_write(struct file *f, struct page *page, - unsigned from, unsigned to) +int __reiserfs_write_begin(struct page *page, unsigned from, unsigned len) { struct inode *inode = page->mapping->host; int ret; @@ -2650,7 +2647,7 @@ int reiserfs_prepare_write(struct file *f, struct page *page, th->t_refcount++; } - ret = block_prepare_write(page, from, to, reiserfs_get_block); + ret = __block_write_begin(page, from, len, reiserfs_get_block); if (ret && reiserfs_transaction_running(inode->i_sb)) { struct reiserfs_transaction_handle *th = current->journal_info; /* this gets a little ugly. If reiserfs_get_block returned an diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c index 5cbb81e134ac..79265fdc317a 100644 --- a/fs/reiserfs/ioctl.c +++ b/fs/reiserfs/ioctl.c @@ -9,7 +9,6 @@ #include <linux/time.h> #include <asm/uaccess.h> #include <linux/pagemap.h> -#include <linux/smp_lock.h> #include <linux/compat.h> /* @@ -160,8 +159,6 @@ long reiserfs_compat_ioctl(struct file *file, unsigned int cmd, int reiserfs_commit_write(struct file *f, struct page *page, unsigned from, unsigned to); -int reiserfs_prepare_write(struct file *f, struct page *page, - unsigned from, unsigned to); /* ** reiserfs_unpack ** Function try to convert tail from direct item into indirect. @@ -186,12 +183,11 @@ int reiserfs_unpack(struct inode *inode, struct file *filp) return 0; } - /* we need to make sure nobody is changing the file size beneath - ** us - */ - reiserfs_mutex_lock_safe(&inode->i_mutex, inode->i_sb); depth = reiserfs_write_lock_once(inode->i_sb); + /* we need to make sure nobody is changing the file size beneath us */ + reiserfs_mutex_lock_safe(&inode->i_mutex, inode->i_sb); + write_from = inode->i_size & (blocksize - 1); /* if we are on a block boundary, we are already unpacked. */ if (write_from == 0) { @@ -200,7 +196,7 @@ int reiserfs_unpack(struct inode *inode, struct file *filp) } /* we unpack by finding the page with the tail, and calling - ** reiserfs_prepare_write on that page. This will force a + ** __reiserfs_write_begin on that page. This will force a ** reiserfs_get_block to unpack the tail for us. */ index = inode->i_size >> PAGE_CACHE_SHIFT; @@ -210,7 +206,7 @@ int reiserfs_unpack(struct inode *inode, struct file *filp) if (!page) { goto out; } - retval = reiserfs_prepare_write(NULL, page, write_from, write_from); + retval = __reiserfs_write_begin(page, write_from, 0); if (retval) goto out_unlock; diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 076c8b194682..d31bce1a9f90 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -43,7 +43,6 @@ #include <linux/fcntl.h> #include <linux/stat.h> #include <linux/string.h> -#include <linux/smp_lock.h> #include <linux/buffer_head.h> #include <linux/workqueue.h> #include <linux/writeback.h> diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index ee78d4a0086a..ba5f51ec3458 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -1156,7 +1156,7 @@ static int reiserfs_link(struct dentry *old_dentry, struct inode *dir, inode->i_ctime = CURRENT_TIME_SEC; reiserfs_update_sd(&th, inode); - atomic_inc(&inode->i_count); + ihold(inode); d_instantiate(dentry, inode); retval = journal_end(&th, dir->i_sb, jbegin_count); reiserfs_write_unlock(dir->i_sb); diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index e15ff612002d..b243117b8752 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -28,7 +28,6 @@ #include <linux/mount.h> #include <linux/namei.h> #include <linux/crc32.h> -#include <linux/smp_lock.h> struct file_system_type reiserfs_fs_type; @@ -2213,12 +2212,11 @@ out: #endif -static int get_super_block(struct file_system_type *fs_type, +static struct dentry *get_super_block(struct file_system_type *fs_type, int flags, const char *dev_name, - void *data, struct vfsmount *mnt) + void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, reiserfs_fill_super, - mnt); + return mount_bdev(fs_type, flags, dev_name, data, reiserfs_fill_super); } static int __init init_reiserfs_fs(void) @@ -2253,7 +2251,7 @@ static void __exit exit_reiserfs_fs(void) struct file_system_type reiserfs_fs_type = { .owner = THIS_MODULE, .name = "reiserfs", - .get_sb = get_super_block, + .mount = get_super_block, .kill_sb = reiserfs_kill_sb, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 8c4cf273c672..5d04a7828e7a 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -418,13 +418,11 @@ static inline __u32 xattr_hash(const char *msg, int len) int reiserfs_commit_write(struct file *f, struct page *page, unsigned from, unsigned to); -int reiserfs_prepare_write(struct file *f, struct page *page, - unsigned from, unsigned to); static void update_ctime(struct inode *inode) { struct timespec now = current_fs_time(inode->i_sb); - if (hlist_unhashed(&inode->i_hash) || !inode->i_nlink || + if (inode_unhashed(inode) || !inode->i_nlink || timespec_equal(&inode->i_ctime, &now)) return; @@ -532,8 +530,7 @@ reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th, rxh->h_hash = cpu_to_le32(xahash); } - err = reiserfs_prepare_write(NULL, page, page_offset, - page_offset + chunk + skip); + err = __reiserfs_write_begin(page, page_offset, chunk + skip); if (!err) { if (buffer) memcpy(data + skip, buffer + buffer_pos, chunk); diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index 536d697a8a28..90d2fcb67a31 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -472,7 +472,9 @@ int reiserfs_acl_chmod(struct inode *inode) struct reiserfs_transaction_handle th; size_t size = reiserfs_xattr_nblocks(inode, reiserfs_acl_size(clone->a_count)); - reiserfs_write_lock(inode->i_sb); + int depth; + + depth = reiserfs_write_lock_once(inode->i_sb); error = journal_begin(&th, inode->i_sb, size * 2); if (!error) { int error2; @@ -482,7 +484,7 @@ int reiserfs_acl_chmod(struct inode *inode) if (error2) error = error2; } - reiserfs_write_unlock(inode->i_sb); + reiserfs_write_unlock_once(inode->i_sb, depth); } posix_acl_release(clone); return error; diff --git a/fs/romfs/super.c b/fs/romfs/super.c index 268580535c92..6647f90e55cd 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -552,20 +552,19 @@ error_rsb: /* * get a superblock for mounting */ -static int romfs_get_sb(struct file_system_type *fs_type, +static struct dentry *romfs_mount(struct file_system_type *fs_type, int flags, const char *dev_name, - void *data, struct vfsmount *mnt) + void *data) { - int ret = -EINVAL; + struct dentry *ret = ERR_PTR(-EINVAL); #ifdef CONFIG_ROMFS_ON_MTD - ret = get_sb_mtd(fs_type, flags, dev_name, data, romfs_fill_super, - mnt); + ret = mount_mtd(fs_type, flags, dev_name, data, romfs_fill_super); #endif #ifdef CONFIG_ROMFS_ON_BLOCK - if (ret == -EINVAL) - ret = get_sb_bdev(fs_type, flags, dev_name, data, - romfs_fill_super, mnt); + if (ret == ERR_PTR(-EINVAL)) + ret = mount_bdev(fs_type, flags, dev_name, data, + romfs_fill_super); #endif return ret; } @@ -592,7 +591,7 @@ static void romfs_kill_sb(struct super_block *sb) static struct file_system_type romfs_fs_type = { .owner = THIS_MODULE, .name = "romfs", - .get_sb = romfs_get_sb, + .mount = romfs_mount, .kill_sb = romfs_kill_sb, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/select.c b/fs/select.c index 500a669f7790..b7b10aa30861 100644 --- a/fs/select.c +++ b/fs/select.c @@ -67,7 +67,7 @@ static long __estimate_accuracy(struct timespec *tv) return slack; } -static long estimate_accuracy(struct timespec *tv) +long select_estimate_accuracy(struct timespec *tv) { unsigned long ret; struct timespec now; @@ -417,7 +417,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time) } if (end_time && !timed_out) - slack = estimate_accuracy(end_time); + slack = select_estimate_accuracy(end_time); retval = 0; for (;;) { @@ -769,7 +769,7 @@ static int do_poll(unsigned int nfds, struct poll_list *list, } if (end_time && !timed_out) - slack = estimate_accuracy(end_time); + slack = select_estimate_accuracy(end_time); for (;;) { struct poll_list *walk; diff --git a/fs/seq_file.c b/fs/seq_file.c index 0e7cb1395a94..05d6b0e78c95 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -462,9 +462,7 @@ int seq_path_root(struct seq_file *m, struct path *path, struct path *root, if (size) { char *p; - spin_lock(&dcache_lock); p = __d_path(path, root, buf, size); - spin_unlock(&dcache_lock); res = PTR_ERR(p); if (!IS_ERR(p)) { char *end = mangle_path(buf, p, esc); diff --git a/fs/signalfd.c b/fs/signalfd.c index 74047304b01a..492465b451dd 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -99,6 +99,16 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, #ifdef __ARCH_SI_TRAPNO err |= __put_user(kinfo->si_trapno, &uinfo->ssi_trapno); #endif +#ifdef BUS_MCEERR_AO + /* + * Other callers might not initialize the si_lsb field, + * so check explicitly for the right codes here. + */ + if (kinfo->si_code == BUS_MCEERR_AR || + kinfo->si_code == BUS_MCEERR_AO) + err |= __put_user((short) kinfo->si_addr_lsb, + &uinfo->ssi_addr_lsb); +#endif break; case __SI_CHLD: err |= __put_user(kinfo->si_pid, &uinfo->ssi_pid); diff --git a/fs/splice.c b/fs/splice.c index 8f1dfaecc8f0..ce2f02579e35 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1311,18 +1311,6 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe, struct pipe_inode_info *opipe, size_t len, unsigned int flags); -/* - * After the inode slimming patch, i_pipe/i_bdev/i_cdev share the same - * location, so checking ->i_pipe is not enough to verify that this is a - * pipe. - */ -static inline struct pipe_inode_info *pipe_info(struct inode *inode) -{ - if (S_ISFIFO(inode->i_mode)) - return inode->i_pipe; - - return NULL; -} /* * Determine where to splice to/from. @@ -1336,8 +1324,8 @@ static long do_splice(struct file *in, loff_t __user *off_in, loff_t offset, *off; long ret; - ipipe = pipe_info(in->f_path.dentry->d_inode); - opipe = pipe_info(out->f_path.dentry->d_inode); + ipipe = get_pipe_info(in); + opipe = get_pipe_info(out); if (ipipe && opipe) { if (off_in || off_out) @@ -1555,7 +1543,7 @@ static long vmsplice_to_user(struct file *file, const struct iovec __user *iov, int error; long ret; - pipe = pipe_info(file->f_path.dentry->d_inode); + pipe = get_pipe_info(file); if (!pipe) return -EBADF; @@ -1642,7 +1630,7 @@ static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov, }; long ret; - pipe = pipe_info(file->f_path.dentry->d_inode); + pipe = get_pipe_info(file); if (!pipe) return -EBADF; @@ -2022,8 +2010,8 @@ static int link_pipe(struct pipe_inode_info *ipipe, static long do_tee(struct file *in, struct file *out, size_t len, unsigned int flags) { - struct pipe_inode_info *ipipe = pipe_info(in->f_path.dentry->d_inode); - struct pipe_inode_info *opipe = pipe_info(out->f_path.dentry->d_inode); + struct pipe_inode_info *ipipe = get_pipe_info(in); + struct pipe_inode_info *opipe = get_pipe_info(out); int ret = -EINVAL; /* diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 07a4f1156048..24de30ba34c1 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -370,12 +370,10 @@ static void squashfs_put_super(struct super_block *sb) } -static int squashfs_get_sb(struct file_system_type *fs_type, int flags, - const char *dev_name, void *data, - struct vfsmount *mnt) +static struct dentry *squashfs_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, squashfs_fill_super, - mnt); + return mount_bdev(fs_type, flags, dev_name, data, squashfs_fill_super); } @@ -451,7 +449,7 @@ static void squashfs_destroy_inode(struct inode *inode) static struct file_system_type squashfs_fs_type = { .owner = THIS_MODULE, .name = "squashfs", - .get_sb = squashfs_get_sb, + .mount = squashfs_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV }; diff --git a/fs/squashfs/xattr.c b/fs/squashfs/xattr.c index 652b8541f9c6..3876c36699a1 100644 --- a/fs/squashfs/xattr.c +++ b/fs/squashfs/xattr.c @@ -158,17 +158,18 @@ static int squashfs_xattr_get(struct inode *inode, int name_index, strncmp(target, name, name_size) == 0) { /* found xattr */ if (type & SQUASHFS_XATTR_VALUE_OOL) { - __le64 xattr; + __le64 xattr_val; + u64 xattr; /* val is a reference to the real location */ err = squashfs_read_metadata(sb, &val, &start, &offset, sizeof(val)); if (err < 0) goto failed; - err = squashfs_read_metadata(sb, &xattr, &start, - &offset, sizeof(xattr)); + err = squashfs_read_metadata(sb, &xattr_val, + &start, &offset, sizeof(xattr_val)); if (err < 0) goto failed; - xattr = le64_to_cpu(xattr); + xattr = le64_to_cpu(xattr_val); start = SQUASHFS_XATTR_BLK(xattr) + msblk->xattr_table; offset = SQUASHFS_XATTR_OFFSET(xattr); diff --git a/fs/squashfs/xattr.h b/fs/squashfs/xattr.h index 49fe0d719fbf..b634efce4bde 100644 --- a/fs/squashfs/xattr.h +++ b/fs/squashfs/xattr.h @@ -25,7 +25,7 @@ extern __le64 *squashfs_read_xattr_id_table(struct super_block *, u64, u64 *, int *); extern int squashfs_xattr_lookup(struct super_block *, unsigned int, int *, - int *, unsigned long long *); + unsigned int *, unsigned long long *); #else static inline __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 start, u64 *xattr_table_start, int *xattr_ids) @@ -35,7 +35,7 @@ static inline __le64 *squashfs_read_xattr_id_table(struct super_block *sb, } static inline int squashfs_xattr_lookup(struct super_block *sb, - unsigned int index, int *count, int *size, + unsigned int index, int *count, unsigned int *size, unsigned long long *xattr) { return 0; diff --git a/fs/squashfs/xattr_id.c b/fs/squashfs/xattr_id.c index cfb41106098f..d33be5dd6c32 100644 --- a/fs/squashfs/xattr_id.c +++ b/fs/squashfs/xattr_id.c @@ -34,6 +34,7 @@ #include "squashfs_fs_sb.h" #include "squashfs_fs_i.h" #include "squashfs.h" +#include "xattr.h" /* * Map xattr id using the xattr id look up table diff --git a/fs/super.c b/fs/super.c index 8819e3a7ff20..ca696155cd9a 100644 --- a/fs/super.c +++ b/fs/super.c @@ -273,14 +273,14 @@ void generic_shutdown_super(struct super_block *sb) get_fs_excl(); sb->s_flags &= ~MS_ACTIVE; - /* bad name - it should be evict_inodes() */ - invalidate_inodes(sb); + fsnotify_unmount_inodes(&sb->s_inodes); + + evict_inodes(sb); if (sop->put_super) sop->put_super(sb); - /* Forget any remaining inodes */ - if (invalidate_inodes(sb)) { + if (!list_empty(&sb->s_inodes)) { printk("VFS: Busy inodes after unmount of %s. " "Self-destruct in 5 seconds. Have a nice day...\n", sb->s_id); @@ -715,15 +715,14 @@ static int ns_set_super(struct super_block *sb, void *data) return set_anon_super(sb, NULL); } -int get_sb_ns(struct file_system_type *fs_type, int flags, void *data, - int (*fill_super)(struct super_block *, void *, int), - struct vfsmount *mnt) +struct dentry *mount_ns(struct file_system_type *fs_type, int flags, + void *data, int (*fill_super)(struct super_block *, void *, int)) { struct super_block *sb; sb = sget(fs_type, ns_test_super, ns_set_super, data); if (IS_ERR(sb)) - return PTR_ERR(sb); + return ERR_CAST(sb); if (!sb->s_root) { int err; @@ -731,17 +730,16 @@ int get_sb_ns(struct file_system_type *fs_type, int flags, void *data, err = fill_super(sb, data, flags & MS_SILENT ? 1 : 0); if (err) { deactivate_locked_super(sb); - return err; + return ERR_PTR(err); } sb->s_flags |= MS_ACTIVE; } - simple_set_mnt(mnt, sb); - return 0; + return dget(sb->s_root); } -EXPORT_SYMBOL(get_sb_ns); +EXPORT_SYMBOL(mount_ns); #ifdef CONFIG_BLOCK static int set_bdev_super(struct super_block *s, void *data) @@ -762,10 +760,9 @@ static int test_bdev_super(struct super_block *s, void *data) return (void *)s->s_bdev == data; } -int get_sb_bdev(struct file_system_type *fs_type, +struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, - int (*fill_super)(struct super_block *, void *, int), - struct vfsmount *mnt) + int (*fill_super)(struct super_block *, void *, int)) { struct block_device *bdev; struct super_block *s; @@ -777,7 +774,7 @@ int get_sb_bdev(struct file_system_type *fs_type, bdev = open_bdev_exclusive(dev_name, mode, fs_type); if (IS_ERR(bdev)) - return PTR_ERR(bdev); + return ERR_CAST(bdev); /* * once the super is inserted into the list by sget, s_umount @@ -829,15 +826,30 @@ int get_sb_bdev(struct file_system_type *fs_type, bdev->bd_super = s; } - simple_set_mnt(mnt, s); - return 0; + return dget(s->s_root); error_s: error = PTR_ERR(s); error_bdev: close_bdev_exclusive(bdev, mode); error: - return error; + return ERR_PTR(error); +} +EXPORT_SYMBOL(mount_bdev); + +int get_sb_bdev(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data, + int (*fill_super)(struct super_block *, void *, int), + struct vfsmount *mnt) +{ + struct dentry *root; + + root = mount_bdev(fs_type, flags, dev_name, data, fill_super); + if (IS_ERR(root)) + return PTR_ERR(root); + mnt->mnt_root = root; + mnt->mnt_sb = root->d_sb; + return 0; } EXPORT_SYMBOL(get_sb_bdev); @@ -856,29 +868,42 @@ void kill_block_super(struct super_block *sb) EXPORT_SYMBOL(kill_block_super); #endif -int get_sb_nodev(struct file_system_type *fs_type, +struct dentry *mount_nodev(struct file_system_type *fs_type, int flags, void *data, - int (*fill_super)(struct super_block *, void *, int), - struct vfsmount *mnt) + int (*fill_super)(struct super_block *, void *, int)) { int error; struct super_block *s = sget(fs_type, NULL, set_anon_super, NULL); if (IS_ERR(s)) - return PTR_ERR(s); + return ERR_CAST(s); s->s_flags = flags; error = fill_super(s, data, flags & MS_SILENT ? 1 : 0); if (error) { deactivate_locked_super(s); - return error; + return ERR_PTR(error); } s->s_flags |= MS_ACTIVE; - simple_set_mnt(mnt, s); - return 0; + return dget(s->s_root); } +EXPORT_SYMBOL(mount_nodev); + +int get_sb_nodev(struct file_system_type *fs_type, + int flags, void *data, + int (*fill_super)(struct super_block *, void *, int), + struct vfsmount *mnt) +{ + struct dentry *root; + root = mount_nodev(fs_type, flags, data, fill_super); + if (IS_ERR(root)) + return PTR_ERR(root); + mnt->mnt_root = root; + mnt->mnt_sb = root->d_sb; + return 0; +} EXPORT_SYMBOL(get_sb_nodev); static int compare_single(struct super_block *s, void *p) @@ -886,29 +911,42 @@ static int compare_single(struct super_block *s, void *p) return 1; } -int get_sb_single(struct file_system_type *fs_type, +struct dentry *mount_single(struct file_system_type *fs_type, int flags, void *data, - int (*fill_super)(struct super_block *, void *, int), - struct vfsmount *mnt) + int (*fill_super)(struct super_block *, void *, int)) { struct super_block *s; int error; s = sget(fs_type, compare_single, set_anon_super, NULL); if (IS_ERR(s)) - return PTR_ERR(s); + return ERR_CAST(s); if (!s->s_root) { s->s_flags = flags; error = fill_super(s, data, flags & MS_SILENT ? 1 : 0); if (error) { deactivate_locked_super(s); - return error; + return ERR_PTR(error); } s->s_flags |= MS_ACTIVE; } else { do_remount_sb(s, flags, data, 0); } - simple_set_mnt(mnt, s); + return dget(s->s_root); +} +EXPORT_SYMBOL(mount_single); + +int get_sb_single(struct file_system_type *fs_type, + int flags, void *data, + int (*fill_super)(struct super_block *, void *, int), + struct vfsmount *mnt) +{ + struct dentry *root; + root = mount_single(fs_type, flags, data, fill_super); + if (IS_ERR(root)) + return PTR_ERR(root); + mnt->mnt_root = root; + mnt->mnt_sb = root->d_sb; return 0; } @@ -918,6 +956,7 @@ struct vfsmount * vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data) { struct vfsmount *mnt; + struct dentry *root; char *secdata = NULL; int error; @@ -942,9 +981,19 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void goto out_free_secdata; } - error = type->get_sb(type, flags, name, data, mnt); - if (error < 0) - goto out_free_secdata; + if (type->mount) { + root = type->mount(type, flags, name, data); + if (IS_ERR(root)) { + error = PTR_ERR(root); + goto out_free_secdata; + } + mnt->mnt_root = root; + mnt->mnt_sb = root->d_sb; + } else { + error = type->get_sb(type, flags, name, data, mnt); + if (error < 0) + goto out_free_secdata; + } BUG_ON(!mnt->mnt_sb); WARN_ON(!mnt->mnt_sb->s_bdi); mnt->mnt_sb->s_flags |= MS_BORN; diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index f2af22574c50..266895783b47 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -23,7 +23,7 @@ #include "sysfs.h" -static struct vfsmount *sysfs_mount; +static struct vfsmount *sysfs_mnt; struct kmem_cache *sysfs_dir_cachep; static const struct super_operations sysfs_ops = { @@ -95,18 +95,17 @@ static int sysfs_set_super(struct super_block *sb, void *data) return error; } -static int sysfs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *sysfs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { struct sysfs_super_info *info; enum kobj_ns_type type; struct super_block *sb; int error; - error = -ENOMEM; info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) - goto out; + return ERR_PTR(-ENOMEM); for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++) info->ns[type] = kobj_ns_current(type); @@ -114,24 +113,19 @@ static int sysfs_get_sb(struct file_system_type *fs_type, sb = sget(fs_type, sysfs_test_super, sysfs_set_super, info); if (IS_ERR(sb) || sb->s_fs_info != info) kfree(info); - if (IS_ERR(sb)) { - error = PTR_ERR(sb); - goto out; - } + if (IS_ERR(sb)) + return ERR_CAST(sb); if (!sb->s_root) { sb->s_flags = flags; error = sysfs_fill_super(sb, data, flags & MS_SILENT ? 1 : 0); if (error) { deactivate_locked_super(sb); - goto out; + return ERR_PTR(error); } sb->s_flags |= MS_ACTIVE; } - simple_set_mnt(mnt, sb); - error = 0; -out: - return error; + return dget(sb->s_root); } static void sysfs_kill_sb(struct super_block *sb) @@ -147,7 +141,7 @@ static void sysfs_kill_sb(struct super_block *sb) static struct file_system_type sysfs_fs_type = { .name = "sysfs", - .get_sb = sysfs_get_sb, + .mount = sysfs_mount, .kill_sb = sysfs_kill_sb, }; @@ -189,11 +183,11 @@ int __init sysfs_init(void) err = register_filesystem(&sysfs_fs_type); if (!err) { - sysfs_mount = kern_mount(&sysfs_fs_type); - if (IS_ERR(sysfs_mount)) { + sysfs_mnt = kern_mount(&sysfs_fs_type); + if (IS_ERR(sysfs_mnt)) { printk(KERN_ERR "sysfs: could not mount!\n"); - err = PTR_ERR(sysfs_mount); - sysfs_mount = NULL; + err = PTR_ERR(sysfs_mnt); + sysfs_mnt = NULL; unregister_filesystem(&sysfs_fs_type); goto out_err; } diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c index 33e047b59b8d..11e7f7d11cd0 100644 --- a/fs/sysv/namei.c +++ b/fs/sysv/namei.c @@ -126,7 +126,7 @@ static int sysv_link(struct dentry * old_dentry, struct inode * dir, inode->i_ctime = CURRENT_TIME_SEC; inode_inc_link_count(inode); - atomic_inc(&inode->i_count); + ihold(inode); return add_nondir(dentry, inode); } diff --git a/fs/sysv/super.c b/fs/sysv/super.c index a0b0cda6927e..3d9c62be0c10 100644 --- a/fs/sysv/super.c +++ b/fs/sysv/super.c @@ -526,23 +526,22 @@ failed: /* Every kernel module contains stuff like this. */ -static int sysv_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *sysv_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, sysv_fill_super, - mnt); + return mount_bdev(fs_type, flags, dev_name, data, sysv_fill_super); } -static int v7_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *v7_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, v7_fill_super, mnt); + return mount_bdev(fs_type, flags, dev_name, data, v7_fill_super); } static struct file_system_type sysv_fs_type = { .owner = THIS_MODULE, .name = "sysv", - .get_sb = sysv_get_sb, + .mount = sysv_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; @@ -550,7 +549,7 @@ static struct file_system_type sysv_fs_type = { static struct file_system_type v7_fs_type = { .owner = THIS_MODULE, .name = "v7", - .get_sb = v7_get_sb, + .mount = v7_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 87ebcce72213..14f64b689d7f 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -550,7 +550,7 @@ static int ubifs_link(struct dentry *old_dentry, struct inode *dir, lock_2_inodes(dir, inode); inc_nlink(inode); - atomic_inc(&inode->i_count); + ihold(inode); inode->i_ctime = ubifs_current_time(inode); dir->i_size += sz_change; dir_ui->ui_size = dir->i_size; diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 9a47c9f0ad07..91fac54c70e3 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -2038,8 +2038,8 @@ static int sb_test(struct super_block *sb, void *data) return c->vi.cdev == *dev; } -static int ubifs_get_sb(struct file_system_type *fs_type, int flags, - const char *name, void *data, struct vfsmount *mnt) +static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags, + const char *name, void *data) { struct ubi_volume_desc *ubi; struct ubi_volume_info vi; @@ -2057,7 +2057,7 @@ static int ubifs_get_sb(struct file_system_type *fs_type, int flags, if (IS_ERR(ubi)) { dbg_err("cannot open \"%s\", error %d", name, (int)PTR_ERR(ubi)); - return PTR_ERR(ubi); + return ERR_CAST(ubi); } ubi_get_volume_info(ubi, &vi); @@ -2095,20 +2095,19 @@ static int ubifs_get_sb(struct file_system_type *fs_type, int flags, /* 'fill_super()' opens ubi again so we must close it here */ ubi_close_volume(ubi); - simple_set_mnt(mnt, sb); - return 0; + return dget(sb->s_root); out_deact: deactivate_locked_super(sb); out_close: ubi_close_volume(ubi); - return err; + return ERR_PTR(err); } static struct file_system_type ubifs_fs_type = { .name = "ubifs", .owner = THIS_MODULE, - .get_sb = ubifs_get_sb, + .mount = ubifs_mount, .kill_sb = kill_anon_super, }; diff --git a/fs/udf/namei.c b/fs/udf/namei.c index bf5fc674193c..6d8dc02baebb 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -1101,7 +1101,7 @@ static int udf_link(struct dentry *old_dentry, struct inode *dir, inc_nlink(inode); inode->i_ctime = current_fs_time(inode->i_sb); mark_inode_dirty(inode); - atomic_inc(&inode->i_count); + ihold(inode); d_instantiate(dentry, inode); unlock_kernel(); diff --git a/fs/udf/super.c b/fs/udf/super.c index 76f3d6d97b40..4a5c7c61836a 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -107,17 +107,16 @@ struct logicalVolIntegrityDescImpUse *udf_sb_lvidiu(struct udf_sb_info *sbi) } /* UDF filesystem type */ -static int udf_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, - struct vfsmount *mnt) +static struct dentry *udf_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, udf_fill_super, mnt); + return mount_bdev(fs_type, flags, dev_name, data, udf_fill_super); } static struct file_system_type udf_fstype = { .owner = THIS_MODULE, .name = "udf", - .get_sb = udf_get_sb, + .mount = udf_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c index b056f02b1fb3..12f39b9e4437 100644 --- a/fs/ufs/namei.c +++ b/fs/ufs/namei.c @@ -180,7 +180,7 @@ static int ufs_link (struct dentry * old_dentry, struct inode * dir, inode->i_ctime = CURRENT_TIME_SEC; inode_inc_link_count(inode); - atomic_inc(&inode->i_count); + ihold(inode); error = ufs_add_nondir(dentry, inode); unlock_kernel(); diff --git a/fs/ufs/super.c b/fs/ufs/super.c index 6b9be90dae7d..2c47daed56da 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -1454,16 +1454,16 @@ static const struct super_operations ufs_super_ops = { .show_options = ufs_show_options, }; -static int ufs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *ufs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, ufs_fill_super, mnt); + return mount_bdev(fs_type, flags, dev_name, data, ufs_fill_super); } static struct file_system_type ufs_fs_type = { .owner = THIS_MODULE, .name = "ufs", - .get_sb = ufs_get_sb, + .mount = ufs_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig index 480f28127f09..6100ec0fa1d4 100644 --- a/fs/xfs/Kconfig +++ b/fs/xfs/Kconfig @@ -22,6 +22,7 @@ config XFS_FS config XFS_QUOTA bool "XFS Quota support" depends on XFS_FS + select QUOTACTL help If you say Y here, you will be able to set limits for disk usage on a per user and/or a per group basis under XFS. XFS considers quota diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c index b552f816de15..691f61223ed6 100644 --- a/fs/xfs/linux-2.6/xfs_aops.c +++ b/fs/xfs/linux-2.6/xfs_aops.c @@ -934,7 +934,6 @@ xfs_aops_discard_page( struct xfs_inode *ip = XFS_I(inode); struct buffer_head *bh, *head; loff_t offset = page_offset(page); - ssize_t len = 1 << inode->i_blkbits; if (!xfs_is_delayed_page(page, IO_DELAY)) goto out_invalidate; @@ -949,58 +948,14 @@ xfs_aops_discard_page( xfs_ilock(ip, XFS_ILOCK_EXCL); bh = head = page_buffers(page); do { - int done; - xfs_fileoff_t offset_fsb; - xfs_bmbt_irec_t imap; - int nimaps = 1; int error; - xfs_fsblock_t firstblock; - xfs_bmap_free_t flist; + xfs_fileoff_t start_fsb; if (!buffer_delay(bh)) goto next_buffer; - offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset); - - /* - * Map the range first and check that it is a delalloc extent - * before trying to unmap the range. Otherwise we will be - * trying to remove a real extent (which requires a - * transaction) or a hole, which is probably a bad idea... - */ - error = xfs_bmapi(NULL, ip, offset_fsb, 1, - XFS_BMAPI_ENTIRE, NULL, 0, &imap, - &nimaps, NULL); - - if (error) { - /* something screwed, just bail */ - if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) { - xfs_fs_cmn_err(CE_ALERT, ip->i_mount, - "page discard failed delalloc mapping lookup."); - } - break; - } - if (!nimaps) { - /* nothing there */ - goto next_buffer; - } - if (imap.br_startblock != DELAYSTARTBLOCK) { - /* been converted, ignore */ - goto next_buffer; - } - WARN_ON(imap.br_blockcount == 0); - - /* - * Note: while we initialise the firstblock/flist pair, they - * should never be used because blocks should never be - * allocated or freed for a delalloc extent and hence we need - * don't cancel or finish them after the xfs_bunmapi() call. - */ - xfs_bmap_init(&flist, &firstblock); - error = xfs_bunmapi(NULL, ip, offset_fsb, 1, 0, 1, &firstblock, - &flist, &done); - - ASSERT(!flist.xbf_count && !flist.xbf_first); + start_fsb = XFS_B_TO_FSBT(ip->i_mount, offset); + error = xfs_bmap_punch_delalloc_range(ip, start_fsb, 1); if (error) { /* something screwed, just bail */ if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) { @@ -1010,7 +965,7 @@ xfs_aops_discard_page( break; } next_buffer: - offset += len; + offset += 1 << inode->i_blkbits; } while ((bh = bh->b_this_page) != head); @@ -1111,11 +1066,12 @@ xfs_vm_writepage( uptodate = 0; /* - * A hole may still be marked uptodate because discard_buffer - * leaves the flag set. + * set_page_dirty dirties all buffers in a page, independent + * of their state. The dirty state however is entirely + * meaningless for holes (!mapped && uptodate), so skip + * buffers covering holes here. */ if (!buffer_mapped(bh) && buffer_uptodate(bh)) { - ASSERT(!buffer_dirty(bh)); imap_valid = 0; continue; } @@ -1139,8 +1095,7 @@ xfs_vm_writepage( type = IO_DELAY; flags = BMAPI_ALLOCATE; - if (wbc->sync_mode == WB_SYNC_NONE && - wbc->nonblocking) + if (wbc->sync_mode == WB_SYNC_NONE) flags |= BMAPI_TRYLOCK; } @@ -1505,11 +1460,42 @@ xfs_vm_write_failed( struct inode *inode = mapping->host; if (to > inode->i_size) { - struct iattr ia = { - .ia_valid = ATTR_SIZE | ATTR_FORCE, - .ia_size = inode->i_size, - }; - xfs_setattr(XFS_I(inode), &ia, XFS_ATTR_NOLOCK); + /* + * punch out the delalloc blocks we have already allocated. We + * don't call xfs_setattr() to do this as we may be in the + * middle of a multi-iovec write and so the vfs inode->i_size + * will not match the xfs ip->i_size and so it will zero too + * much. Hence we jus truncate the page cache to zero what is + * necessary and punch the delalloc blocks directly. + */ + struct xfs_inode *ip = XFS_I(inode); + xfs_fileoff_t start_fsb; + xfs_fileoff_t end_fsb; + int error; + + truncate_pagecache(inode, to, inode->i_size); + + /* + * Check if there are any blocks that are outside of i_size + * that need to be trimmed back. + */ + start_fsb = XFS_B_TO_FSB(ip->i_mount, inode->i_size) + 1; + end_fsb = XFS_B_TO_FSB(ip->i_mount, to); + if (end_fsb <= start_fsb) + return; + + xfs_ilock(ip, XFS_ILOCK_EXCL); + error = xfs_bmap_punch_delalloc_range(ip, start_fsb, + end_fsb - start_fsb); + if (error) { + /* something screwed, just bail */ + if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) { + xfs_fs_cmn_err(CE_ALERT, ip->i_mount, + "xfs_vm_write_failed: unable to clean up ino %lld", + ip->i_ino); + } + } + xfs_iunlock(ip, XFS_ILOCK_EXCL); } } diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index ba5312802aa9..4c5deb6e9e31 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -488,29 +488,16 @@ found: spin_unlock(&pag->pag_buf_lock); xfs_perag_put(pag); - /* Attempt to get the semaphore without sleeping, - * if this does not work then we need to drop the - * spinlock and do a hard attempt on the semaphore. - */ - if (down_trylock(&bp->b_sema)) { + if (xfs_buf_cond_lock(bp)) { + /* failed, so wait for the lock if requested. */ if (!(flags & XBF_TRYLOCK)) { - /* wait for buffer ownership */ xfs_buf_lock(bp); XFS_STATS_INC(xb_get_locked_waited); } else { - /* We asked for a trylock and failed, no need - * to look at file offset and length here, we - * know that this buffer at least overlaps our - * buffer and is locked, therefore our buffer - * either does not exist, or is this buffer. - */ xfs_buf_rele(bp); XFS_STATS_INC(xb_busy_locked); return NULL; } - } else { - /* trylock worked */ - XB_SET_OWNER(bp); } if (bp->b_flags & XBF_STALE) { @@ -876,10 +863,18 @@ xfs_buf_rele( */ /* - * Locks a buffer object, if it is not already locked. - * Note that this in no way locks the underlying pages, so it is only - * useful for synchronizing concurrent use of buffer objects, not for - * synchronizing independent access to the underlying pages. + * Locks a buffer object, if it is not already locked. Note that this in + * no way locks the underlying pages, so it is only useful for + * synchronizing concurrent use of buffer objects, not for synchronizing + * independent access to the underlying pages. + * + * If we come across a stale, pinned, locked buffer, we know that we are + * being asked to lock a buffer that has been reallocated. Because it is + * pinned, we know that the log has not been pushed to disk and hence it + * will still be locked. Rather than continuing to have trylock attempts + * fail until someone else pushes the log, push it ourselves before + * returning. This means that the xfsaild will not get stuck trying + * to push on stale inode buffers. */ int xfs_buf_cond_lock( @@ -890,6 +885,8 @@ xfs_buf_cond_lock( locked = down_trylock(&bp->b_sema) == 0; if (locked) XB_SET_OWNER(bp); + else if (atomic_read(&bp->b_pin_count) && (bp->b_flags & XBF_STALE)) + xfs_log_force(bp->b_target->bt_mount, 0); trace_xfs_buf_cond_lock(bp, _RET_IP_); return locked ? 0 : -EBUSY; @@ -1580,6 +1577,7 @@ xfs_mapping_buftarg( XFS_BUFTARG_NAME(btp)); return ENOMEM; } + inode->i_ino = get_next_ino(); inode->i_mode = S_IFBLK; inode->i_bdev = bdev; inode->i_rdev = bdev->bd_dev; @@ -1780,7 +1778,6 @@ xfs_buf_delwri_split( INIT_LIST_HEAD(list); spin_lock(dwlk); list_for_each_entry_safe(bp, n, dwq, b_list) { - trace_xfs_buf_delwri_split(bp, _RET_IP_); ASSERT(bp->b_flags & XBF_DELWRI); if (!XFS_BUF_ISPINNED(bp) && !xfs_buf_cond_lock(bp)) { @@ -1794,6 +1791,7 @@ xfs_buf_delwri_split( _XBF_RUN_QUEUES); bp->b_flags |= XBF_WRITE; list_move_tail(&bp->b_list, list); + trace_xfs_buf_delwri_split(bp, _RET_IP_); } else skipped++; } diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c index 2ea238f6d38e..ad442d9e392e 100644 --- a/fs/xfs/linux-2.6/xfs_ioctl.c +++ b/fs/xfs/linux-2.6/xfs_ioctl.c @@ -416,7 +416,7 @@ xfs_attrlist_by_handle( if (IS_ERR(dentry)) return PTR_ERR(dentry); - kbuf = kmalloc(al_hreq.buflen, GFP_KERNEL); + kbuf = kzalloc(al_hreq.buflen, GFP_KERNEL); if (!kbuf) goto out_dput; diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c index ec858e09d546..94d5fd6a2973 100644 --- a/fs/xfs/linux-2.6/xfs_iops.c +++ b/fs/xfs/linux-2.6/xfs_iops.c @@ -317,7 +317,7 @@ xfs_vn_link( if (unlikely(error)) return -error; - atomic_inc(&inode->i_count); + ihold(inode); d_instantiate(dentry, inode); return 0; } @@ -760,7 +760,10 @@ xfs_setup_inode( inode->i_ino = ip->i_ino; inode->i_state = I_NEW; - inode_add_to_lists(ip->i_mount->m_super, inode); + + inode_sb_list_add(inode); + /* make the inode look hashed for the writeback code */ + hlist_add_fake(&inode->i_hash); inode->i_mode = ip->i_d.di_mode; inode->i_nlink = ip->i_d.di_nlink; diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index ab31ce5aeaf9..064f964d4f3c 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -353,9 +353,6 @@ xfs_parseargs( mp->m_qflags &= ~XFS_OQUOTA_ENFD; } else if (!strcmp(this_char, MNTOPT_DELAYLOG)) { mp->m_flags |= XFS_MOUNT_DELAYLOG; - cmn_err(CE_WARN, - "Enabling EXPERIMENTAL delayed logging feature " - "- use at your own risk.\n"); } else if (!strcmp(this_char, MNTOPT_NODELAYLOG)) { mp->m_flags &= ~XFS_MOUNT_DELAYLOG; } else if (!strcmp(this_char, "ihashsize")) { @@ -576,7 +573,7 @@ xfs_max_file_offset( /* Figure out maximum filesize, on Linux this can depend on * the filesystem blocksize (on 32 bit platforms). - * __block_prepare_write does this in an [unsigned] long... + * __block_write_begin does this in an [unsigned] long... * page->index << (PAGE_CACHE_SHIFT - bbits) * So, for page sized blocks (4K on 32 bit platforms), * this wraps at around 8Tb (hence MAX_LFS_FILESIZE which is @@ -1609,16 +1606,14 @@ xfs_fs_fill_super( goto out_free_sb; } -STATIC int -xfs_fs_get_sb( +STATIC struct dentry * +xfs_fs_mount( struct file_system_type *fs_type, int flags, const char *dev_name, - void *data, - struct vfsmount *mnt) + void *data) { - return get_sb_bdev(fs_type, flags, dev_name, data, xfs_fs_fill_super, - mnt); + return mount_bdev(fs_type, flags, dev_name, data, xfs_fs_fill_super); } static const struct super_operations xfs_super_operations = { @@ -1639,7 +1634,7 @@ static const struct super_operations xfs_super_operations = { static struct file_system_type xfs_fs_type = { .owner = THIS_MODULE, .name = "xfs", - .get_sb = xfs_fs_get_sb, + .mount = xfs_fs_mount, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, }; diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c index 37d33254981d..afb0d7cfad1c 100644 --- a/fs/xfs/linux-2.6/xfs_sync.c +++ b/fs/xfs/linux-2.6/xfs_sync.c @@ -853,6 +853,7 @@ restart: if (trylock) { if (!mutex_trylock(&pag->pag_ici_reclaim_lock)) { skipped++; + xfs_perag_put(pag); continue; } first_index = pag->pag_ici_reclaim_cursor; diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index 8abd12e32e13..4111cd3966c7 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -5471,8 +5471,13 @@ xfs_getbmap( if (error) goto out_unlock_iolock; } - - ASSERT(ip->i_delayed_blks == 0); + /* + * even after flushing the inode, there can still be delalloc + * blocks on the inode beyond EOF due to speculative + * preallocation. These are not removed until the release + * function is called or the inode is inactivated. Hence we + * cannot assert here that ip->i_delayed_blks == 0. + */ } lock = xfs_ilock_map_shared(ip); @@ -6070,3 +6075,79 @@ xfs_bmap_disk_count_leaves( *count += xfs_bmbt_disk_get_blockcount(frp); } } + +/* + * dead simple method of punching delalyed allocation blocks from a range in + * the inode. Walks a block at a time so will be slow, but is only executed in + * rare error cases so the overhead is not critical. This will alays punch out + * both the start and end blocks, even if the ranges only partially overlap + * them, so it is up to the caller to ensure that partial blocks are not + * passed in. + */ +int +xfs_bmap_punch_delalloc_range( + struct xfs_inode *ip, + xfs_fileoff_t start_fsb, + xfs_fileoff_t length) +{ + xfs_fileoff_t remaining = length; + int error = 0; + + ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); + + do { + int done; + xfs_bmbt_irec_t imap; + int nimaps = 1; + xfs_fsblock_t firstblock; + xfs_bmap_free_t flist; + + /* + * Map the range first and check that it is a delalloc extent + * before trying to unmap the range. Otherwise we will be + * trying to remove a real extent (which requires a + * transaction) or a hole, which is probably a bad idea... + */ + error = xfs_bmapi(NULL, ip, start_fsb, 1, + XFS_BMAPI_ENTIRE, NULL, 0, &imap, + &nimaps, NULL); + + if (error) { + /* something screwed, just bail */ + if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) { + xfs_fs_cmn_err(CE_ALERT, ip->i_mount, + "Failed delalloc mapping lookup ino %lld fsb %lld.", + ip->i_ino, start_fsb); + } + break; + } + if (!nimaps) { + /* nothing there */ + goto next_block; + } + if (imap.br_startblock != DELAYSTARTBLOCK) { + /* been converted, ignore */ + goto next_block; + } + WARN_ON(imap.br_blockcount == 0); + + /* + * Note: while we initialise the firstblock/flist pair, they + * should never be used because blocks should never be + * allocated or freed for a delalloc extent and hence we need + * don't cancel or finish them after the xfs_bunmapi() call. + */ + xfs_bmap_init(&flist, &firstblock); + error = xfs_bunmapi(NULL, ip, start_fsb, 1, 0, 1, &firstblock, + &flist, &done); + if (error) + break; + + ASSERT(!flist.xbf_count && !flist.xbf_first); +next_block: + start_fsb++; + remaining--; + } while(remaining > 0); + + return error; +} diff --git a/fs/xfs/xfs_bmap.h b/fs/xfs/xfs_bmap.h index 71ec9b6ecdfc..3651191daea1 100644 --- a/fs/xfs/xfs_bmap.h +++ b/fs/xfs/xfs_bmap.h @@ -394,6 +394,11 @@ xfs_bmap_count_blocks( int whichfork, int *count); +int +xfs_bmap_punch_delalloc_range( + struct xfs_inode *ip, + xfs_fileoff_t start_fsb, + xfs_fileoff_t length); #endif /* __KERNEL__ */ #endif /* __XFS_BMAP_H__ */ diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c index 3b9582c60a22..e60490bc00a6 100644 --- a/fs/xfs/xfs_dfrag.c +++ b/fs/xfs/xfs_dfrag.c @@ -377,6 +377,19 @@ xfs_swap_extents( ip->i_d.di_format = tip->i_d.di_format; tip->i_d.di_format = tmp; + /* + * The extents in the source inode could still contain speculative + * preallocation beyond EOF (e.g. the file is open but not modified + * while defrag is in progress). In that case, we need to copy over the + * number of delalloc blocks the data fork in the source inode is + * tracking beyond EOF so that when the fork is truncated away when the + * temporary inode is unlinked we don't underrun the i_delayed_blks + * counter on that inode. + */ + ASSERT(tip->i_delayed_blks == 0); + tip->i_delayed_blks = ip->i_delayed_blks; + ip->i_delayed_blks = 0; + ilf_fields = XFS_ILOG_CORE; switch(ip->i_d.di_format) { diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index ed9990267661..c78cc6a3d87c 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -58,6 +58,7 @@ xfs_error_trap(int e) int xfs_etest[XFS_NUM_INJECT_ERROR]; int64_t xfs_etest_fsid[XFS_NUM_INJECT_ERROR]; char * xfs_etest_fsname[XFS_NUM_INJECT_ERROR]; +int xfs_error_test_active; int xfs_error_test(int error_tag, int *fsidp, char *expression, @@ -108,6 +109,7 @@ xfs_errortag_add(int error_tag, xfs_mount_t *mp) len = strlen(mp->m_fsname); xfs_etest_fsname[i] = kmem_alloc(len + 1, KM_SLEEP); strcpy(xfs_etest_fsname[i], mp->m_fsname); + xfs_error_test_active++; return 0; } } @@ -137,6 +139,7 @@ xfs_errortag_clearall(xfs_mount_t *mp, int loud) xfs_etest_fsid[i] = 0LL; kmem_free(xfs_etest_fsname[i]); xfs_etest_fsname[i] = NULL; + xfs_error_test_active--; } } diff --git a/fs/xfs/xfs_error.h b/fs/xfs/xfs_error.h index c2c1a072bb82..f338847f80b8 100644 --- a/fs/xfs/xfs_error.h +++ b/fs/xfs/xfs_error.h @@ -127,13 +127,14 @@ extern void xfs_corruption_error(const char *tag, int level, #define XFS_RANDOM_BMAPIFORMAT XFS_RANDOM_DEFAULT #ifdef DEBUG +extern int xfs_error_test_active; extern int xfs_error_test(int, int *, char *, int, char *, unsigned long); #define XFS_NUM_INJECT_ERROR 10 #define XFS_TEST_ERROR(expr, mp, tag, rf) \ - ((expr) || \ + ((expr) || (xfs_error_test_active && \ xfs_error_test((tag), (mp)->m_fixedfsid, "expr", __LINE__, __FILE__, \ - (rf))) + (rf)))) extern int xfs_errortag_add(int error_tag, xfs_mount_t *mp); extern int xfs_errortag_clearall(xfs_mount_t *mp, int loud); diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c index 9b715dce5699..9124425b7f2f 100644 --- a/fs/xfs/xfs_filestream.c +++ b/fs/xfs/xfs_filestream.c @@ -744,9 +744,15 @@ xfs_filestream_new_ag( * If the file's parent directory is known, take its iolock in exclusive * mode to prevent two sibling files from racing each other to migrate * themselves and their parent to different AGs. + * + * Note that we lock the parent directory iolock inside the child + * iolock here. That's fine as we never hold both parent and child + * iolock in any other place. This is different from the ilock, + * which requires locking of the child after the parent for namespace + * operations. */ if (pip) - xfs_ilock(pip, XFS_IOLOCK_EXCL); + xfs_ilock(pip, XFS_IOLOCK_EXCL | XFS_IOLOCK_PARENT); /* * A new AG needs to be found for the file. If the file's parent diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index fac52290de90..fb2ca2e4cdc9 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -500,7 +500,7 @@ void xfs_mark_inode_dirty_sync(xfs_inode_t *); #define IHOLD(ip) \ do { \ ASSERT(atomic_read(&VFS_I(ip)->i_count) > 0) ; \ - atomic_inc(&(VFS_I(ip)->i_count)); \ + ihold(VFS_I(ip)); \ trace_xfs_ihold(ip, _THIS_IP_); \ } while (0) diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index c7ac020705df..7c8d30c453c3 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -657,18 +657,37 @@ xfs_inode_item_unlock( } /* - * This is called to find out where the oldest active copy of the - * inode log item in the on disk log resides now that the last log - * write of it completed at the given lsn. Since we always re-log - * all dirty data in an inode, the latest copy in the on disk log - * is the only one that matters. Therefore, simply return the - * given lsn. + * This is called to find out where the oldest active copy of the inode log + * item in the on disk log resides now that the last log write of it completed + * at the given lsn. Since we always re-log all dirty data in an inode, the + * latest copy in the on disk log is the only one that matters. Therefore, + * simply return the given lsn. + * + * If the inode has been marked stale because the cluster is being freed, we + * don't want to (re-)insert this inode into the AIL. There is a race condition + * where the cluster buffer may be unpinned before the inode is inserted into + * the AIL during transaction committed processing. If the buffer is unpinned + * before the inode item has been committed and inserted, then it is possible + * for the buffer to be written and IO completions before the inode is inserted + * into the AIL. In that case, we'd be inserting a clean, stale inode into the + * AIL which will never get removed. It will, however, get reclaimed which + * triggers an assert in xfs_inode_free() complaining about freein an inode + * still in the AIL. + * + * To avoid this, return a lower LSN than the one passed in so that the + * transaction committed code will not move the inode forward in the AIL but + * will still unpin it properly. */ STATIC xfs_lsn_t xfs_inode_item_committed( struct xfs_log_item *lip, xfs_lsn_t lsn) { + struct xfs_inode_log_item *iip = INODE_ITEM(lip); + struct xfs_inode *ip = iip->ili_inode; + + if (xfs_iflags_test(ip, XFS_ISTALE)) + return lsn - 1; return lsn; } diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index b1498ab5a399..19e9dfa1c254 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -275,6 +275,7 @@ xfs_free_perag( pag = radix_tree_delete(&mp->m_perag_tree, agno); spin_unlock(&mp->m_perag_lock); ASSERT(pag); + ASSERT(atomic_read(&pag->pag_ref) == 0); call_rcu(&pag->rcu_head, __xfs_free_perag); } } diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h index e0e64b113bd6..9bb6eda4cd21 100644 --- a/fs/xfs/xfs_quota.h +++ b/fs/xfs/xfs_quota.h @@ -346,8 +346,17 @@ xfs_qm_vop_dqalloc(struct xfs_inode *ip, uid_t uid, gid_t gid, prid_t prid, #define xfs_trans_mod_dquot_byino(tp, ip, fields, delta) #define xfs_trans_apply_dquot_deltas(tp) #define xfs_trans_unreserve_and_mod_dquots(tp) -#define xfs_trans_reserve_quota_nblks(tp, ip, nblks, ninos, flags) (0) -#define xfs_trans_reserve_quota_bydquots(tp, mp, u, g, nb, ni, fl) (0) +static inline int xfs_trans_reserve_quota_nblks(struct xfs_trans *tp, + struct xfs_inode *ip, long nblks, long ninos, uint flags) +{ + return 0; +} +static inline int xfs_trans_reserve_quota_bydquots(struct xfs_trans *tp, + struct xfs_mount *mp, struct xfs_dquot *udqp, + struct xfs_dquot *gdqp, long nblks, long nions, uint flags) +{ + return 0; +} #define xfs_qm_vop_create_dqattach(tp, ip, u, g) #define xfs_qm_vop_rename_dqattach(it) (0) #define xfs_qm_vop_chown(tp, ip, old, new) (NULL) @@ -357,11 +366,14 @@ xfs_qm_vop_dqalloc(struct xfs_inode *ip, uid_t uid, gid_t gid, prid_t prid, #define xfs_qm_dqdetach(ip) #define xfs_qm_dqrele(d) #define xfs_qm_statvfs(ip, s) -#define xfs_qm_sync(mp, fl) (0) +static inline int xfs_qm_sync(struct xfs_mount *mp, int flags) +{ + return 0; +} #define xfs_qm_newmount(mp, a, b) (0) #define xfs_qm_mount_quotas(mp) #define xfs_qm_unmount(mp) -#define xfs_qm_unmount_quotas(mp) (0) +#define xfs_qm_unmount_quotas(mp) #endif /* CONFIG_XFS_QUOTA */ #define xfs_trans_unreserve_quota_nblks(tp, ip, nblks, ninos, flags) \ |