diff options
Diffstat (limited to 'fs')
82 files changed, 1560 insertions, 1837 deletions
diff --git a/fs/Kconfig b/fs/Kconfig index 487236c6583..781b47d2f9f 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -1112,8 +1112,8 @@ config HFS_FS help If you say Y here, you will be able to mount Macintosh-formatted floppy disks and hard drive partitions with full read-write access. - Please read <file:fs/hfs/HFS.txt> to learn about the available mount - options. + Please read <file:Documentation/filesystems/hfs.txt> to learn about + the available mount options. To compile this file system support as a module, choose M here: the module will be called hfs. diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index ba8de7ca260..f0b3171842f 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1384,7 +1384,7 @@ static void fill_prstatus(struct elf_prstatus *prstatus, prstatus->pr_sigpend = p->pending.signal.sig[0]; prstatus->pr_sighold = p->blocked.sig[0]; prstatus->pr_pid = task_pid_vnr(p); - prstatus->pr_ppid = task_pid_vnr(p->parent); + prstatus->pr_ppid = task_pid_vnr(p->real_parent); prstatus->pr_pgrp = task_pgrp_vnr(p); prstatus->pr_sid = task_session_vnr(p); if (thread_group_leader(p)) { @@ -1430,7 +1430,7 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p, psinfo->pr_psargs[len] = 0; psinfo->pr_pid = task_pid_vnr(p); - psinfo->pr_ppid = task_pid_vnr(p->parent); + psinfo->pr_ppid = task_pid_vnr(p->real_parent); psinfo->pr_pgrp = task_pgrp_vnr(p); psinfo->pr_sid = task_session_vnr(p); diff --git a/fs/block_dev.c b/fs/block_dev.c index 993f78c5522..e48a630ae26 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -738,9 +738,9 @@ EXPORT_SYMBOL(bd_release); static struct kobject *bdev_get_kobj(struct block_device *bdev) { if (bdev->bd_contains != bdev) - return kobject_get(&bdev->bd_part->kobj); + return kobject_get(&bdev->bd_part->dev.kobj); else - return kobject_get(&bdev->bd_disk->kobj); + return kobject_get(&bdev->bd_disk->dev.kobj); } static struct kobject *bdev_get_holder(struct block_device *bdev) @@ -1176,7 +1176,7 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part) ret = -ENXIO; goto out_first; } - kobject_get(&p->kobj); + kobject_get(&p->dev.kobj); bdev->bd_part = p; bd_set_size(bdev, (loff_t) p->nr_sects << 9); } @@ -1299,7 +1299,7 @@ static int __blkdev_put(struct block_device *bdev, int for_part) module_put(owner); if (bdev->bd_contains != bdev) { - kobject_put(&bdev->bd_part->kobj); + kobject_put(&bdev->bd_part->dev.kobj); bdev->bd_part = NULL; } bdev->bd_disk = NULL; diff --git a/fs/char_dev.c b/fs/char_dev.c index c3bfa76765c..2c7a8b5b459 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -510,9 +510,8 @@ struct cdev *cdev_alloc(void) { struct cdev *p = kzalloc(sizeof(struct cdev), GFP_KERNEL); if (p) { - p->kobj.ktype = &ktype_cdev_dynamic; INIT_LIST_HEAD(&p->list); - kobject_init(&p->kobj); + kobject_init(&p->kobj, &ktype_cdev_dynamic); } return p; } @@ -529,8 +528,7 @@ void cdev_init(struct cdev *cdev, const struct file_operations *fops) { memset(cdev, 0, sizeof *cdev); INIT_LIST_HEAD(&cdev->list); - cdev->kobj.ktype = &ktype_cdev_default; - kobject_init(&cdev->kobj); + kobject_init(&cdev->kobj, &ktype_cdev_default); cdev->ops = fops; } diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c index dcc6aead70f..e3eb3556622 100644 --- a/fs/coda/psdev.c +++ b/fs/coda/psdev.c @@ -362,8 +362,8 @@ static int init_coda_psdev(void) goto out_chrdev; } for (i = 0; i < MAX_CODADEVS; i++) - class_device_create(coda_psdev_class, NULL, - MKDEV(CODA_PSDEV_MAJOR,i), NULL, "cfs%d", i); + device_create(coda_psdev_class, NULL, + MKDEV(CODA_PSDEV_MAJOR,i), "cfs%d", i); coda_sysctl_init(); goto out; @@ -405,7 +405,7 @@ static int __init init_coda(void) return 0; out: for (i = 0; i < MAX_CODADEVS; i++) - class_device_destroy(coda_psdev_class, MKDEV(CODA_PSDEV_MAJOR, i)); + device_destroy(coda_psdev_class, MKDEV(CODA_PSDEV_MAJOR, i)); class_destroy(coda_psdev_class); unregister_chrdev(CODA_PSDEV_MAJOR, "coda"); coda_sysctl_clean(); @@ -424,7 +424,7 @@ static void __exit exit_coda(void) printk("coda: failed to unregister filesystem\n"); } for (i = 0; i < MAX_CODADEVS; i++) - class_device_destroy(coda_psdev_class, MKDEV(CODA_PSDEV_MAJOR, i)); + device_destroy(coda_psdev_class, MKDEV(CODA_PSDEV_MAJOR, i)); class_destroy(coda_psdev_class); unregister_chrdev(CODA_PSDEV_MAJOR, "coda"); coda_sysctl_clean(); diff --git a/fs/compat.c b/fs/compat.c index 15078ce4c04..5216c3fd751 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1104,10 +1104,6 @@ static ssize_t compat_do_readv_writev(int type, struct file *file, if (ret < 0) goto out; - ret = security_file_permission(file, type == READ ? MAY_READ:MAY_WRITE); - if (ret) - goto out; - fnv = NULL; if (type == READ) { fn = file->f_op->read; diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index e8b7c3a98a5..da8cb3b3592 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -10,6 +10,8 @@ * ioctls. */ +#include <linux/joystick.h> + #include <linux/types.h> #include <linux/compat.h> #include <linux/kernel.h> @@ -2642,6 +2644,12 @@ COMPATIBLE_IOCTL(VIDEO_SET_ATTRIBUTES) COMPATIBLE_IOCTL(VIDEO_GET_SIZE) COMPATIBLE_IOCTL(VIDEO_GET_FRAME_RATE) +/* joystick */ +COMPATIBLE_IOCTL(JSIOCGVERSION) +COMPATIBLE_IOCTL(JSIOCGAXES) +COMPATIBLE_IOCTL(JSIOCGBUTTONS) +COMPATIBLE_IOCTL(JSIOCGNAME(0)) + /* now things that need handlers */ HANDLE_IOCTL(MEMREADOOB32, mtd_rw_oob) HANDLE_IOCTL(MEMWRITEOOB32, mtd_rw_oob) diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c index 3bf0278ea84..de3b31d0a37 100644 --- a/fs/configfs/mount.c +++ b/fs/configfs/mount.c @@ -128,7 +128,7 @@ void configfs_release_fs(void) } -static decl_subsys(config, NULL, NULL); +static struct kobject *config_kobj; static int __init configfs_init(void) { @@ -140,9 +140,8 @@ static int __init configfs_init(void) if (!configfs_dir_cachep) goto out; - kobj_set_kset_s(&config_subsys, kernel_subsys); - err = subsystem_register(&config_subsys); - if (err) { + config_kobj = kobject_create_and_add("config", kernel_kobj); + if (!config_kobj) { kmem_cache_destroy(configfs_dir_cachep); configfs_dir_cachep = NULL; goto out; @@ -151,7 +150,7 @@ static int __init configfs_init(void) err = register_filesystem(&configfs_fs_type); if (err) { printk(KERN_ERR "configfs: Unable to register filesystem!\n"); - subsystem_unregister(&config_subsys); + kobject_put(config_kobj); kmem_cache_destroy(configfs_dir_cachep); configfs_dir_cachep = NULL; goto out; @@ -160,7 +159,7 @@ static int __init configfs_init(void) err = configfs_inode_init(); if (err) { unregister_filesystem(&configfs_fs_type); - subsystem_unregister(&config_subsys); + kobject_put(config_kobj); kmem_cache_destroy(configfs_dir_cachep); configfs_dir_cachep = NULL; } @@ -171,7 +170,7 @@ out: static void __exit configfs_exit(void) { unregister_filesystem(&configfs_fs_type); - subsystem_unregister(&config_subsys); + kobject_put(config_kobj); kmem_cache_destroy(configfs_dir_cachep); configfs_dir_cachep = NULL; configfs_inode_exit(); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 6a713b33992..d26e2826ba5 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -426,20 +426,19 @@ exit: } EXPORT_SYMBOL_GPL(debugfs_rename); -static decl_subsys(debug, NULL, NULL); +static struct kobject *debug_kobj; static int __init debugfs_init(void) { int retval; - kobj_set_kset_s(&debug_subsys, kernel_subsys); - retval = subsystem_register(&debug_subsys); - if (retval) - return retval; + debug_kobj = kobject_create_and_add("debug", kernel_kobj); + if (!debug_kobj) + return -EINVAL; retval = register_filesystem(&debug_fs_type); if (retval) - subsystem_unregister(&debug_subsys); + kobject_put(debug_kobj); return retval; } @@ -447,7 +446,7 @@ static void __exit debugfs_exit(void) { simple_release_fs(&debugfs_mount, &debugfs_mount_count); unregister_filesystem(&debug_fs_type); - subsystem_unregister(&debug_subsys); + kobject_put(debug_kobj); } core_initcall(debugfs_init); diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index 6353a838452..5c108c49cb8 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -166,26 +166,7 @@ static struct kobj_type dlm_ktype = { .release = lockspace_kobj_release, }; -static struct kset dlm_kset = { - .ktype = &dlm_ktype, -}; - -static int kobject_setup(struct dlm_ls *ls) -{ - char lsname[DLM_LOCKSPACE_LEN]; - int error; - - memset(lsname, 0, DLM_LOCKSPACE_LEN); - snprintf(lsname, DLM_LOCKSPACE_LEN, "%s", ls->ls_name); - - error = kobject_set_name(&ls->ls_kobj, "%s", lsname); - if (error) - return error; - - ls->ls_kobj.kset = &dlm_kset; - ls->ls_kobj.ktype = &dlm_ktype; - return 0; -} +static struct kset *dlm_kset; static int do_uevent(struct dlm_ls *ls, int in) { @@ -220,24 +201,22 @@ static int do_uevent(struct dlm_ls *ls, int in) int dlm_lockspace_init(void) { - int error; - ls_count = 0; mutex_init(&ls_lock); INIT_LIST_HEAD(&lslist); spin_lock_init(&lslist_lock); - kobject_set_name(&dlm_kset.kobj, "dlm"); - kobj_set_kset_s(&dlm_kset, kernel_subsys); - error = kset_register(&dlm_kset); - if (error) - printk("dlm_lockspace_init: cannot register kset %d\n", error); - return error; + dlm_kset = kset_create_and_add("dlm", NULL, kernel_kobj); + if (!dlm_kset) { + printk(KERN_WARNING "%s: can not create kset\n", __FUNCTION__); + return -ENOMEM; + } + return 0; } void dlm_lockspace_exit(void) { - kset_unregister(&dlm_kset); + kset_unregister(dlm_kset); } static int dlm_scand(void *data) @@ -549,13 +528,12 @@ static int new_lockspace(char *name, int namelen, void **lockspace, goto out_delist; } - error = kobject_setup(ls); - if (error) - goto out_stop; - - error = kobject_register(&ls->ls_kobj); + ls->ls_kobj.kset = dlm_kset; + error = kobject_init_and_add(&ls->ls_kobj, &dlm_ktype, NULL, + "%s", ls->ls_name); if (error) goto out_stop; + kobject_uevent(&ls->ls_kobj, KOBJ_ADD); /* let kobject handle freeing of ls if there's an error */ do_unreg = 1; @@ -601,7 +579,7 @@ static int new_lockspace(char *name, int namelen, void **lockspace, kfree(ls->ls_rsbtbl); out_lsfree: if (do_unreg) - kobject_unregister(&ls->ls_kobj); + kobject_put(&ls->ls_kobj); else kfree(ls); out: @@ -750,7 +728,7 @@ static int release_lockspace(struct dlm_ls *ls, int force) dlm_clear_members(ls); dlm_clear_members_gone(ls); kfree(ls->ls_node_array); - kobject_unregister(&ls->ls_kobj); + kobject_put(&ls->ls_kobj); /* The ls structure will be freed when the kobject is done with */ mutex_lock(&ls_lock); diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 0b1ab016fa2..5a719180983 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -120,22 +120,9 @@ ecryptfs_do_create(struct inode *directory_inode, rc = ecryptfs_create_underlying_file(lower_dir_dentry->d_inode, ecryptfs_dentry, mode, nd); if (rc) { - struct inode *ecryptfs_inode = ecryptfs_dentry->d_inode; - struct ecryptfs_inode_info *inode_info = - ecryptfs_inode_to_private(ecryptfs_inode); - - printk(KERN_WARNING "%s: Error creating underlying file; " - "rc = [%d]; checking for existing\n", __FUNCTION__, rc); - if (inode_info) { - mutex_lock(&inode_info->lower_file_mutex); - if (!inode_info->lower_file) { - mutex_unlock(&inode_info->lower_file_mutex); - printk(KERN_ERR "%s: Failure to set underlying " - "file; rc = [%d]\n", __FUNCTION__, rc); - goto out_lock; - } - mutex_unlock(&inode_info->lower_file_mutex); - } + printk(KERN_ERR "%s: Failure to create dentry in lower fs; " + "rc = [%d]\n", __FUNCTION__, rc); + goto out_lock; } rc = ecryptfs_interpose(lower_dentry, ecryptfs_dentry, directory_inode->i_sb, 0); @@ -451,6 +438,7 @@ static int ecryptfs_unlink(struct inode *dir, struct dentry *dentry) dentry->d_inode->i_nlink = ecryptfs_inode_to_lower(dentry->d_inode)->i_nlink; dentry->d_inode->i_ctime = dir->i_ctime; + d_drop(dentry); out_unlock: unlock_parent(lower_dentry); return rc; diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index e5580bcb923..0249aa4ae18 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -734,127 +734,40 @@ static int ecryptfs_init_kmem_caches(void) return 0; } -struct ecryptfs_obj { - char *name; - struct list_head slot_list; - struct kobject kobj; -}; - -struct ecryptfs_attribute { - struct attribute attr; - ssize_t(*show) (struct ecryptfs_obj *, char *); - ssize_t(*store) (struct ecryptfs_obj *, const char *, size_t); -}; +static struct kobject *ecryptfs_kobj; -static ssize_t -ecryptfs_attr_store(struct kobject *kobj, - struct attribute *attr, const char *buf, size_t len) +static ssize_t version_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buff) { - struct ecryptfs_obj *obj = container_of(kobj, struct ecryptfs_obj, - kobj); - struct ecryptfs_attribute *attribute = - container_of(attr, struct ecryptfs_attribute, attr); - - return (attribute->store ? attribute->store(obj, buf, len) : 0); + return snprintf(buff, PAGE_SIZE, "%d\n", ECRYPTFS_VERSIONING_MASK); } -static ssize_t -ecryptfs_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) -{ - struct ecryptfs_obj *obj = container_of(kobj, struct ecryptfs_obj, - kobj); - struct ecryptfs_attribute *attribute = - container_of(attr, struct ecryptfs_attribute, attr); - - return (attribute->show ? attribute->show(obj, buf) : 0); -} +static struct kobj_attribute version_attr = __ATTR_RO(version); -static struct sysfs_ops ecryptfs_sysfs_ops = { - .show = ecryptfs_attr_show, - .store = ecryptfs_attr_store +static struct attribute *attributes[] = { + &version_attr.attr, + NULL, }; -static struct kobj_type ecryptfs_ktype = { - .sysfs_ops = &ecryptfs_sysfs_ops +static struct attribute_group attr_group = { + .attrs = attributes, }; -static decl_subsys(ecryptfs, &ecryptfs_ktype, NULL); - -static ssize_t version_show(struct ecryptfs_obj *obj, char *buff) -{ - return snprintf(buff, PAGE_SIZE, "%d\n", ECRYPTFS_VERSIONING_MASK); -} - -static struct ecryptfs_attribute sysfs_attr_version = __ATTR_RO(version); - -static struct ecryptfs_version_str_map_elem { - u32 flag; - char *str; -} ecryptfs_version_str_map[] = { - {ECRYPTFS_VERSIONING_PASSPHRASE, "passphrase"}, - {ECRYPTFS_VERSIONING_PUBKEY, "pubkey"}, - {ECRYPTFS_VERSIONING_PLAINTEXT_PASSTHROUGH, "plaintext passthrough"}, - {ECRYPTFS_VERSIONING_POLICY, "policy"}, - {ECRYPTFS_VERSIONING_XATTR, "metadata in extended attribute"}, - {ECRYPTFS_VERSIONING_MULTKEY, "multiple keys per file"} -}; - -static ssize_t version_str_show(struct ecryptfs_obj *obj, char *buff) -{ - int i; - int remaining = PAGE_SIZE; - int total_written = 0; - - buff[0] = '\0'; - for (i = 0; i < ARRAY_SIZE(ecryptfs_version_str_map); i++) { - int entry_size; - - if (!(ECRYPTFS_VERSIONING_MASK - & ecryptfs_version_str_map[i].flag)) - continue; - entry_size = strlen(ecryptfs_version_str_map[i].str); - if ((entry_size + 2) > remaining) - goto out; - memcpy(buff, ecryptfs_version_str_map[i].str, entry_size); - buff[entry_size++] = '\n'; - buff[entry_size] = '\0'; - buff += entry_size; - total_written += entry_size; - remaining -= entry_size; - } -out: - return total_written; -} - -static struct ecryptfs_attribute sysfs_attr_version_str = __ATTR_RO(version_str); - static int do_sysfs_registration(void) { int rc; - rc = subsystem_register(&ecryptfs_subsys); - if (rc) { - printk(KERN_ERR - "Unable to register ecryptfs sysfs subsystem\n"); - goto out; - } - rc = sysfs_create_file(&ecryptfs_subsys.kobj, - &sysfs_attr_version.attr); - if (rc) { - printk(KERN_ERR - "Unable to create ecryptfs version attribute\n"); - subsystem_unregister(&ecryptfs_subsys); + ecryptfs_kobj = kobject_create_and_add("ecryptfs", fs_kobj); + if (!ecryptfs_kobj) { + printk(KERN_ERR "Unable to create ecryptfs kset\n"); + rc = -ENOMEM; goto out; } - rc = sysfs_create_file(&ecryptfs_subsys.kobj, - &sysfs_attr_version_str.attr); + rc = sysfs_create_group(ecryptfs_kobj, &attr_group); if (rc) { printk(KERN_ERR - "Unable to create ecryptfs version_str attribute\n"); - sysfs_remove_file(&ecryptfs_subsys.kobj, - &sysfs_attr_version.attr); - subsystem_unregister(&ecryptfs_subsys); - goto out; + "Unable to create ecryptfs version attributes\n"); + kobject_put(ecryptfs_kobj); } out: return rc; @@ -862,11 +775,8 @@ out: static void do_sysfs_unregistration(void) { - sysfs_remove_file(&ecryptfs_subsys.kobj, - &sysfs_attr_version.attr); - sysfs_remove_file(&ecryptfs_subsys.kobj, - &sysfs_attr_version_str.attr); - subsystem_unregister(&ecryptfs_subsys); + sysfs_remove_group(ecryptfs_kobj, &attr_group); + kobject_put(ecryptfs_kobj); } static int __init ecryptfs_init(void) @@ -894,7 +804,6 @@ static int __init ecryptfs_init(void) printk(KERN_ERR "Failed to register filesystem\n"); goto out_free_kmem_caches; } - kobj_set_kset_s(&ecryptfs_subsys, fs_subsys); rc = do_sysfs_registration(); if (rc) { printk(KERN_ERR "sysfs registration failed\n"); diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c index f8cdab2bee3..4859c4eecd6 100644 --- a/fs/ecryptfs/super.c +++ b/fs/ecryptfs/super.c @@ -86,7 +86,6 @@ static void ecryptfs_destroy_inode(struct inode *inode) fput(inode_info->lower_file); inode_info->lower_file = NULL; d_drop(lower_dentry); - d_delete(lower_dentry); } } mutex_unlock(&inode_info->lower_file_mutex); diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index 2c1b73fb82a..5fb366992b7 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -590,21 +590,49 @@ error: EXPORT_SYMBOL_GPL(fat_free_clusters); +/* 128kb is the whole sectors for FAT12 and FAT16 */ +#define FAT_READA_SIZE (128 * 1024) + +static void fat_ent_reada(struct super_block *sb, struct fat_entry *fatent, + unsigned long reada_blocks) +{ + struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops; + sector_t blocknr; + int i, offset; + + ops->ent_blocknr(sb, fatent->entry, &offset, &blocknr); + + for (i = 0; i < reada_blocks; i++) + sb_breadahead(sb, blocknr + i); +} + int fat_count_free_clusters(struct super_block *sb) { struct msdos_sb_info *sbi = MSDOS_SB(sb); struct fatent_operations *ops = sbi->fatent_ops; struct fat_entry fatent; + unsigned long reada_blocks, reada_mask, cur_block; int err = 0, free; lock_fat(sbi); if (sbi->free_clusters != -1) goto out; + reada_blocks = FAT_READA_SIZE >> sb->s_blocksize_bits; + reada_mask = reada_blocks - 1; + cur_block = 0; + free = 0; fatent_init(&fatent); fatent_set_entry(&fatent, FAT_START_ENT); while (fatent.entry < sbi->max_cluster) { + /* readahead of fat blocks */ + if ((cur_block & reada_mask) == 0) { + unsigned long rest = sbi->fat_length - cur_block; + fat_ent_reada(sb, &fatent, min(reada_blocks, rest)); + } + cur_block++; + err = fat_ent_read_block(sb, &fatent); if (err) goto out; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 0fca82021d7..300324bd563 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -482,8 +482,6 @@ sync_sb_inodes(struct super_block *sb, struct writeback_control *wbc) if (wbc->nr_to_write <= 0) break; } - if (!list_empty(&sb->s_more_io)) - wbc->more_io = 1; return; /* Leave any unwritten inodes on s_io */ } diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 84f9f7dfdf5..e5e80d1a468 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -744,9 +744,6 @@ static inline void unregister_fuseblk(void) } #endif -static decl_subsys(fuse, NULL, NULL); -static decl_subsys(connections, NULL, NULL); - static void fuse_inode_init_once(struct kmem_cache *cachep, void *foo) { struct inode * inode = foo; @@ -791,32 +788,37 @@ static void fuse_fs_cleanup(void) kmem_cache_destroy(fuse_inode_cachep); } +static struct kobject *fuse_kobj; +static struct kobject *connections_kobj; + static int fuse_sysfs_init(void) { int err; - kobj_set_kset_s(&fuse_subsys, fs_subsys); - err = subsystem_register(&fuse_subsys); - if (err) + fuse_kobj = kobject_create_and_add("fuse", fs_kobj); + if (!fuse_kobj) { + err = -ENOMEM; goto out_err; + } - kobj_set_kset_s(&connections_subsys, fuse_subsys); - err = subsystem_register(&connections_subsys); - if (err) + connections_kobj = kobject_create_and_add("connections", fuse_kobj); + if (!connections_kobj) { + err = -ENOMEM; goto out_fuse_unregister; + } return 0; out_fuse_unregister: - subsystem_unregister(&fuse_subsys); + kobject_put(fuse_kobj); out_err: return err; } static void fuse_sysfs_cleanup(void) { - subsystem_unregister(&connections_subsys); - subsystem_unregister(&fuse_subsys); + kobject_put(connections_kobj); + kobject_put(fuse_kobj); } static int __init fuse_init(void) diff --git a/fs/gfs2/Makefile b/fs/gfs2/Makefile index 04ad0caebed..8fff11058ce 100644 --- a/fs/gfs2/Makefile +++ b/fs/gfs2/Makefile @@ -2,7 +2,7 @@ obj-$(CONFIG_GFS2_FS) += gfs2.o gfs2-y := acl.o bmap.o daemon.o dir.o eaops.o eattr.o glock.o \ glops.o inode.o lm.o log.o lops.o locking.o main.o meta_io.o \ mount.o ops_address.o ops_dentry.o ops_export.o ops_file.o \ - ops_fstype.o ops_inode.o ops_super.o ops_vm.o quota.o \ + ops_fstype.o ops_inode.o ops_super.o quota.o \ recovery.o rgrp.o super.o sys.o trans.o util.o obj-$(CONFIG_GFS2_FS_LOCKING_NOLOCK) += locking/nolock/ diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 93fa427bb5f..e4effc47abf 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -59,7 +59,6 @@ struct strip_mine { static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh, u64 block, struct page *page) { - struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct inode *inode = &ip->i_inode; struct buffer_head *bh; int release = 0; @@ -95,7 +94,7 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh, set_buffer_uptodate(bh); if (!gfs2_is_jdata(ip)) mark_buffer_dirty(bh); - if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip)) + if (!gfs2_is_writeback(ip)) gfs2_trans_add_bh(ip->i_gl, bh, 0); if (release) { @@ -453,8 +452,8 @@ static inline void bmap_unlock(struct inode *inode, int create) * Returns: errno */ -int gfs2_block_map(struct inode *inode, u64 lblock, int create, - struct buffer_head *bh_map) +int gfs2_block_map(struct inode *inode, sector_t lblock, + struct buffer_head *bh_map, int create) { struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); @@ -470,6 +469,7 @@ int gfs2_block_map(struct inode *inode, u64 lblock, int create, unsigned int maxlen = bh_map->b_size >> inode->i_blkbits; struct metapath mp; u64 size; + struct buffer_head *dibh = NULL; BUG_ON(maxlen == 0); @@ -500,6 +500,8 @@ int gfs2_block_map(struct inode *inode, u64 lblock, int create, error = gfs2_meta_inode_buffer(ip, &bh); if (error) goto out_fail; + dibh = bh; + get_bh(dibh); for (x = 0; x < end_of_metadata; x++) { lookup_block(ip, bh, x, &mp, create, &new, &dblock); @@ -518,13 +520,8 @@ int gfs2_block_map(struct inode *inode, u64 lblock, int create, if (boundary) set_buffer_boundary(bh_map); if (new) { - struct buffer_head *dibh; - error = gfs2_meta_inode_buffer(ip, &dibh); - if (!error) { - gfs2_trans_add_bh(ip->i_gl, dibh, 1); - gfs2_dinode_out(ip, dibh->b_data); - brelse(dibh); - } + gfs2_trans_add_bh(ip->i_gl, dibh, 1); + gfs2_dinode_out(ip, dibh->b_data); set_buffer_new(bh_map); goto out_brelse; } @@ -545,6 +542,8 @@ out_brelse: out_ok: error = 0; out_fail: + if (dibh) + brelse(dibh); bmap_unlock(inode, create); return error; } @@ -560,7 +559,7 @@ int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsi BUG_ON(!new); bh.b_size = 1 << (inode->i_blkbits + 5); - ret = gfs2_block_map(inode, lblock, create, &bh); + ret = gfs2_block_map(inode, lblock, &bh, create); *extlen = bh.b_size >> inode->i_blkbits; *dblock = bh.b_blocknr; if (buffer_new(&bh)) @@ -684,7 +683,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh, if (metadata) revokes = (height) ? sdp->sd_inptrs : sdp->sd_diptrs; - error = gfs2_rindex_hold(sdp, &ip->i_alloc.al_ri_gh); + error = gfs2_rindex_hold(sdp, &ip->i_alloc->al_ri_gh); if (error) return error; @@ -786,7 +785,7 @@ out_rg_gunlock: out_rlist: gfs2_rlist_free(&rlist); out: - gfs2_glock_dq_uninit(&ip->i_alloc.al_ri_gh); + gfs2_glock_dq_uninit(&ip->i_alloc->al_ri_gh); return error; } @@ -879,7 +878,6 @@ static int gfs2_block_truncate_page(struct address_space *mapping) { struct inode *inode = mapping->host; struct gfs2_inode *ip = GFS2_I(inode); - struct gfs2_sbd *sdp = GFS2_SB(inode); loff_t from = inode->i_size; unsigned long index = from >> PAGE_CACHE_SHIFT; unsigned offset = from & (PAGE_CACHE_SIZE-1); @@ -911,7 +909,7 @@ static int gfs2_block_truncate_page(struct address_space *mapping) err = 0; if (!buffer_mapped(bh)) { - gfs2_get_block(inode, iblock, bh, 0); + gfs2_block_map(inode, iblock, bh, 0); /* unmapped? It's a hole - nothing to do */ if (!buffer_mapped(bh)) goto unlock; @@ -931,7 +929,7 @@ static int gfs2_block_truncate_page(struct address_space *mapping) err = 0; } - if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip)) + if (!gfs2_is_writeback(ip)) gfs2_trans_add_bh(ip->i_gl, bh, 0); zero_user_page(page, offset, length, KM_USER0); @@ -1224,8 +1222,13 @@ int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset, do_div(lblock_stop, bsize); } else { unsigned int shift = sdp->sd_sb.sb_bsize_shift; + u64 end_of_file = (ip->i_di.di_size + sdp->sd_sb.sb_bsize - 1) >> shift; lblock = offset >> shift; lblock_stop = (offset + len + sdp->sd_sb.sb_bsize - 1) >> shift; + if (lblock_stop > end_of_file) { + *alloc_required = 1; + return 0; + } } for (; lblock < lblock_stop; lblock += extlen) { diff --git a/fs/gfs2/bmap.h b/fs/gfs2/bmap.h index ac2fd04370d..4e6cde2943b 100644 --- a/fs/gfs2/bmap.h +++ b/fs/gfs2/bmap.h @@ -15,7 +15,7 @@ struct gfs2_inode; struct page; int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page); -int gfs2_block_map(struct inode *inode, u64 lblock, int create, struct buffer_head *bh); +int gfs2_block_map(struct inode *inode, sector_t lblock, struct buffer_head *bh, int create); int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsigned *extlen); int gfs2_truncatei(struct gfs2_inode *ip, u64 size); diff --git a/fs/gfs2/daemon.c b/fs/gfs2/daemon.c index 3731ab0771d..e51991947d2 100644 --- a/fs/gfs2/daemon.c +++ b/fs/gfs2/daemon.c @@ -83,56 +83,6 @@ int gfs2_recoverd(void *data) } /** - * gfs2_logd - Update log tail as Active Items get flushed to in-place blocks - * @sdp: Pointer to GFS2 superblock - * - * Also, periodically check to make sure that we're using the most recent - * journal index. - */ - -int gfs2_logd(void *data) -{ - struct gfs2_sbd *sdp = data; - struct gfs2_holder ji_gh; - unsigned long t; - int need_flush; - - while (!kthread_should_stop()) { - /* Advance the log tail */ - - t = sdp->sd_log_flush_time + - gfs2_tune_get(sdp, gt_log_flush_secs) * HZ; - - gfs2_ail1_empty(sdp, DIO_ALL); - gfs2_log_lock(sdp); - need_flush = sdp->sd_log_num_buf > gfs2_tune_get(sdp, gt_incore_log_blocks); - gfs2_log_unlock(sdp); - if (need_flush || time_after_eq(jiffies, t)) { - gfs2_log_flush(sdp, NULL); - sdp->sd_log_flush_time = jiffies; - } - - /* Check for latest journal index */ - - t = sdp->sd_jindex_refresh_time + - gfs2_tune_get(sdp, gt_jindex_refresh_secs) * HZ; - - if (time_after_eq(jiffies, t)) { - if (!gfs2_jindex_hold(sdp, &ji_gh)) - gfs2_glock_dq_uninit(&ji_gh); - sdp->sd_jindex_refresh_time = jiffies; - } - - t = gfs2_tune_get(sdp, gt_logd_secs) * HZ; - if (freezing(current)) - refrigerator(); - schedule_timeout_interruptible(t); - } - - return 0; -} - -/** * gfs2_quotad - Write cached quota changes into the quota file * @sdp: Pointer to GFS2 superblock * diff --git a/fs/gfs2/daemon.h b/fs/gfs2/daemon.h index 0de9b355795..4be084fb6a6 100644 --- a/fs/gfs2/daemon.h +++ b/fs/gfs2/daemon.h @@ -12,7 +12,6 @@ int gfs2_glockd(void *data); int gfs2_recoverd(void *data); -int gfs2_logd(void *data); int gfs2_quotad(void *data); #endif /* __DAEMON_DOT_H__ */ diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index 9949bb746a5..57e2ed932ad 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -1876,7 +1876,7 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len, if (error) goto out; - error = gfs2_rindex_hold(sdp, &dip->i_alloc.al_ri_gh); + error = gfs2_rindex_hold(sdp, &dip->i_alloc->al_ri_gh); if (error) goto out_qs; @@ -1949,7 +1949,7 @@ out_rg_gunlock: gfs2_glock_dq_m(rlist.rl_rgrps, rlist.rl_ghs); out_rlist: gfs2_rlist_free(&rlist); - gfs2_glock_dq_uninit(&dip->i_alloc.al_ri_gh); + gfs2_glock_dq_uninit(&dip->i_alloc->al_ri_gh); out_qs: gfs2_quota_unhold(dip); out: diff --git a/fs/gfs2/eaops.c b/fs/gfs2/eaops.c index aa8dbf303f6..f114ba2b355 100644 --- a/fs/gfs2/eaops.c +++ b/fs/gfs2/eaops.c @@ -56,46 +56,6 @@ unsigned int gfs2_ea_name2type(const char *name, const char **truncated_name) return type; } -static int user_eo_get(struct gfs2_inode *ip, struct gfs2_ea_request *er) -{ - struct inode *inode = &ip->i_inode; - int error = permission(inode, MAY_READ, NULL); - if (error) - return error; - - return gfs2_ea_get_i(ip, er); -} - -static int user_eo_set(struct gfs2_inode *ip, struct gfs2_ea_request *er) -{ - struct inode *inode = &ip->i_inode; - - if (S_ISREG(inode->i_mode) || - (S_ISDIR(inode->i_mode) && !(inode->i_mode & S_ISVTX))) { - int error = permission(inode, MAY_WRITE, NULL); - if (error) - return error; - } else - return -EPERM; - - return gfs2_ea_set_i(ip, er); -} - -static int user_eo_remove(struct gfs2_inode *ip, struct gfs2_ea_request *er) -{ - struct inode *inode = &ip->i_inode; - - if (S_ISREG(inode->i_mode) || - (S_ISDIR(inode->i_mode) && !(inode->i_mode & S_ISVTX))) { - int error = permission(inode, MAY_WRITE, NULL); - if (error) - return error; - } else - return -EPERM; - - return gfs2_ea_remove_i(ip, er); -} - static int system_eo_get(struct gfs2_inode *ip, struct gfs2_ea_request *er) { if (!GFS2_ACL_IS_ACCESS(er->er_name, er->er_name_len) && @@ -108,8 +68,6 @@ static int system_eo_get(struct gfs2_inode *ip, struct gfs2_ea_request *er) GFS2_ACL_IS_DEFAULT(er->er_name, er->er_name_len))) return -EOPNOTSUPP; - - return gfs2_ea_get_i(ip, er); } @@ -170,40 +128,10 @@ static int system_eo_remove(struct gfs2_inode *ip, struct gfs2_ea_request *er) return gfs2_ea_remove_i(ip, er); } -static int security_eo_get(struct gfs2_inode *ip, struct gfs2_ea_request *er) -{ - struct inode *inode = &ip->i_inode; - int error = permission(inode, MAY_READ, NULL); - if (error) - return error; - - return gfs2_ea_get_i(ip, er); -} - -static int security_eo_set(struct gfs2_inode *ip, struct gfs2_ea_request *er) -{ - struct inode *inode = &ip->i_inode; - int error = permission(inode, MAY_WRITE, NULL); - if (error) - return error; - - return gfs2_ea_set_i(ip, er); -} - -static int security_eo_remove(struct gfs2_inode *ip, struct gfs2_ea_request *er) -{ - struct inode *inode = &ip->i_inode; - int error = permission(inode, MAY_WRITE, NULL); - if (error) - return error; - - return gfs2_ea_remove_i(ip, er); -} - static const struct gfs2_eattr_operations gfs2_user_eaops = { - .eo_get = user_eo_get, - .eo_set = user_eo_set, - .eo_remove = user_eo_remove, + .eo_get = gfs2_ea_get_i, + .eo_set = gfs2_ea_set_i, + .eo_remove = gfs2_ea_remove_i, .eo_name = "user", }; @@ -215,9 +143,9 @@ const struct gfs2_eattr_operations gfs2_system_eaops = { }; static const struct gfs2_eattr_operations gfs2_security_eaops = { - .eo_get = security_eo_get, - .eo_set = security_eo_set, - .eo_remove = security_eo_remove, + .eo_get = gfs2_ea_get_i, + .eo_set = gfs2_ea_set_i, + .eo_remove = gfs2_ea_remove_i, .eo_name = "security", }; diff --git a/fs/gfs2/eattr.c b/fs/gfs2/eattr.c index 2a7435b5c4d..bee99704ea1 100644 --- a/fs/gfs2/eattr.c +++ b/fs/gfs2/eattr.c @@ -1418,7 +1418,7 @@ out: static int ea_dealloc_block(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - struct gfs2_alloc *al = &ip->i_alloc; + struct gfs2_alloc *al = ip->i_alloc; struct gfs2_rgrpd *rgd; struct buffer_head *dibh; int error; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index a37efe4aae6..80e09c50590 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -217,7 +217,6 @@ int gfs2_glock_put(struct gfs2_glock *gl) if (atomic_dec_and_test(&gl->gl_ref)) { hlist_del(&gl->gl_list); write_unlock(gl_lock_addr(gl->gl_hash)); - BUG_ON(spin_is_locked(&gl->gl_spin)); gfs2_assert(sdp, gl->gl_state == LM_ST_UNLOCKED); gfs2_assert(sdp, list_empty(&gl->gl_reclaim)); gfs2_assert(sdp, list_empty(&gl->gl_holders)); @@ -346,7 +345,6 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, gl->gl_object = NULL; gl->gl_sbd = sdp; gl->gl_aspace = NULL; - lops_init_le(&gl->gl_le, &gfs2_glock_lops); INIT_DELAYED_WORK(&gl->gl_work, glock_work_func); /* If this glock protects actual on-disk data or metadata blocks, @@ -461,7 +459,6 @@ static void wait_on_holder(struct gfs2_holder *gh) static void gfs2_demote_wake(struct gfs2_glock *gl) { - BUG_ON(!spin_is_locked(&gl->gl_spin)); gl->gl_demote_state = LM_ST_EXCLUSIVE; clear_bit(GLF_DEMOTE, &gl->gl_flags); smp_mb__after_clear_bit(); @@ -507,21 +504,12 @@ static int rq_mutex(struct gfs2_holder *gh) static int rq_promote(struct gfs2_holder *gh) { struct gfs2_glock *gl = gh->gh_gl; - struct gfs2_sbd *sdp = gl->gl_sbd; if (!relaxed_state_ok(gl->gl_state, gh->gh_state, gh->gh_flags)) { if (list_empty(&gl->gl_holders)) { gl->gl_req_gh = gh; set_bit(GLF_LOCK, &gl->gl_flags); spin_unlock(&gl->gl_spin); - - if (atomic_read(&sdp->sd_reclaim_count) > - gfs2_tune_get(sdp, gt_reclaim_limit) && - !(gh->gh_flags & LM_FLAG_PRIORITY)) { - gfs2_reclaim_glock(sdp); - gfs2_reclaim_glock(sdp); - } - gfs2_glock_xmote_th(gh->gh_gl, gh); spin_lock(&gl->gl_spin); } @@ -567,7 +555,10 @@ static int rq_demote(struct gfs2_glock *gl) gfs2_demote_wake(gl); return 0; } + set_bit(GLF_LOCK, &gl->gl_flags); + set_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags); + if (gl->gl_demote_state == LM_ST_UNLOCKED || gl->gl_state != LM_ST_EXCLUSIVE) { spin_unlock(&gl->gl_spin); @@ -576,7 +567,9 @@ static int rq_demote(struct gfs2_glock *gl) spin_unlock(&gl->gl_spin); gfs2_glock_xmote_th(gl, NULL); } + spin_lock(&gl->gl_spin); + clear_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags); return 0; } @@ -598,23 +591,18 @@ static void run_queue(struct gfs2_glock *gl) if (!list_empty(&gl->gl_waiters1)) { gh = list_entry(gl->gl_waiters1.next, struct gfs2_holder, gh_list); - - if (test_bit(HIF_MUTEX, &gh->gh_iflags)) - blocked = rq_mutex(gh); - else - gfs2_assert_warn(gl->gl_sbd, 0); - + blocked = rq_mutex(gh); } else if (test_bit(GLF_DEMOTE, &gl->gl_flags)) { blocked = rq_demote(gl); + if (gl->gl_waiters2 && !blocked) { + set_bit(GLF_DEMOTE, &gl->gl_flags); + gl->gl_demote_state = LM_ST_UNLOCKED; + } + gl->gl_waiters2 = 0; } else if (!list_empty(&gl->gl_waiters3)) { gh = list_entry(gl->gl_waiters3.next, struct gfs2_holder, gh_list); - - if (test_bit(HIF_PROMOTE, &gh->gh_iflags)) - blocked = rq_promote(gh); - else - gfs2_assert_warn(gl->gl_sbd, 0); - + blocked = rq_promote(gh); } else break; @@ -632,27 +620,21 @@ static void run_queue(struct gfs2_glock *gl) static void gfs2_glmutex_lock(struct gfs2_glock *gl) { - struct gfs2_holder gh; - - gfs2_holder_init(gl, 0, 0, &gh); - set_bit(HIF_MUTEX, &gh.gh_iflags); - if (test_and_set_bit(HIF_WAIT, &gh.gh_iflags)) - BUG(); - spin_lock(&gl->gl_spin); if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) { + struct gfs2_holder gh; + + gfs2_holder_init(gl, 0, 0, &gh); + set_bit(HIF_WAIT, &gh.gh_iflags); list_add_tail(&gh.gh_list, &gl->gl_waiters1); + spin_unlock(&gl->gl_spin); + wait_on_holder(&gh); + gfs2_holder_uninit(&gh); } else { gl->gl_owner_pid = current->pid; gl->gl_ip = (unsigned long)__builtin_return_address(0); - clear_bit(HIF_WAIT, &gh.gh_iflags); - smp_mb(); - wake_up_bit(&gh.gh_iflags, HIF_WAIT); + spin_unlock(&gl->gl_spin); } - spin_unlock(&gl->gl_spin); - - wait_on_holder(&gh); - gfs2_holder_uninit(&gh); } /** @@ -691,7 +673,6 @@ static void gfs2_glmutex_unlock(struct gfs2_glock *gl) gl->gl_owner_pid = 0; gl->gl_ip = 0; run_queue(gl); - BUG_ON(!spin_is_locked(&gl->gl_spin)); spin_unlock(&gl->gl_spin); } @@ -722,7 +703,10 @@ static void handle_callback(struct gfs2_glock *gl, unsigned int state, } } else if (gl->gl_demote_state != LM_ST_UNLOCKED && gl->gl_demote_state != state) { - gl->gl_demote_state = LM_ST_UNLOCKED; + if (test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags)) + gl->gl_waiters2 = 1; + else + gl->gl_demote_state = LM_ST_UNLOCKED; } spin_unlock(&gl->gl_spin); } @@ -943,8 +927,8 @@ static void gfs2_glock_drop_th(struct gfs2_glock *gl) const struct gfs2_glock_operations *glops = gl->gl_ops; unsigned int ret; - if (glops->go_drop_th) - glops->go_drop_th(gl); + if (glops->go_xmote_th) + glops->go_xmote_th(gl); gfs2_assert_warn(sdp, test_bit(GLF_LOCK, &gl->gl_flags)); gfs2_assert_warn(sdp, list_empty(&gl->gl_holders)); @@ -1156,8 +1140,6 @@ restart: return -EIO; } - set_bit(HIF_PROMOTE, &gh->gh_iflags); - spin_lock(&gl->gl_spin); add_to_queue(gh); run_queue(gl); @@ -1248,12 +1230,11 @@ void gfs2_glock_dq(struct gfs2_holder *gh) list_del_init(&gh->gh_list); if (list_empty(&gl->gl_holders)) { - spin_unlock(&gl->gl_spin); - - if (glops->go_unlock) + if (glops->go_unlock) { + spin_unlock(&gl->gl_spin); glops->go_unlock(gh); - - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_spin); + } gl->gl_stamp = jiffies; } @@ -1910,8 +1891,6 @@ static int dump_glock(struct glock_iter *gi, struct gfs2_glock *gl) print_dbg(gi, " req_bh = %s\n", (gl->gl_req_bh) ? "yes" : "no"); print_dbg(gi, " lvb_count = %d\n", atomic_read(&gl->gl_lvb_count)); print_dbg(gi, " object = %s\n", (gl->gl_object) ? "yes" : "no"); - print_dbg(gi, " le = %s\n", - (list_empty(&gl->gl_le.le_list)) ? "no" : "yes"); print_dbg(gi, " reclaim = %s\n", (list_empty(&gl->gl_reclaim)) ? "no" : "yes"); if (gl->gl_aspace) diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 4670dcb2a87..c663b7a0f41 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -56,7 +56,7 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl) bd = list_entry(head->next, struct gfs2_bufdata, bd_ail_gl_list); bh = bd->bd_bh; - gfs2_remove_from_ail(NULL, bd); + gfs2_remove_from_ail(bd); bd->bd_bh = NULL; bh->b_private = NULL; bd->bd_blkno = bh->b_blocknr; @@ -86,15 +86,10 @@ static void gfs2_pte_inval(struct gfs2_glock *gl) if (!ip || !S_ISREG(inode->i_mode)) return; - if (!test_bit(GIF_PAGED, &ip->i_flags)) - return; - unmap_shared_mapping_range(inode->i_mapping, 0, 0); - if (test_bit(GIF_SW_PAGED, &ip->i_flags)) set_bit(GLF_DIRTY, &gl->gl_flags); - clear_bit(GIF_SW_PAGED, &ip->i_flags); } /** @@ -143,44 +138,34 @@ static void meta_go_inval(struct gfs2_glock *gl, int flags) static void inode_go_sync(struct gfs2_glock *gl) { struct gfs2_inode *ip = gl->gl_object; + struct address_space *metamapping = gl->gl_aspace->i_mapping; + int error; + + if (gl->gl_state != LM_ST_UNLOCKED) + gfs2_pte_inval(gl); + if (gl->gl_state != LM_ST_EXCLUSIVE) + return; if (ip && !S_ISREG(ip->i_inode.i_mode)) ip = NULL; if (test_bit(GLF_DIRTY, &gl->gl_flags)) { - if (ip && !gfs2_is_jdata(ip)) - filemap_fdatawrite(ip->i_inode.i_mapping); gfs2_log_flush(gl->gl_sbd, gl); - if (ip && gfs2_is_jdata(ip)) - filemap_fdatawrite(ip->i_inode.i_mapping); - gfs2_meta_sync(gl); + filemap_fdatawrite(metamapping); if (ip) { struct address_space *mapping = ip->i_inode.i_mapping; - int error = filemap_fdatawait(mapping); + filemap_fdatawrite(mapping); + error = filemap_fdatawait(mapping); mapping_set_error(mapping, error); } + error = filemap_fdatawait(metamapping); + mapping_set_error(metamapping, error); clear_bit(GLF_DIRTY, &gl->gl_flags); gfs2_ail_empty_gl(gl); } } /** - * inode_go_xmote_th - promote/demote a glock - * @gl: the glock - * @state: the requested state - * @flags: - * - */ - -static void inode_go_xmote_th(struct gfs2_glock *gl) -{ - if (gl->gl_state != LM_ST_UNLOCKED) - gfs2_pte_inval(gl); - if (gl->gl_state == LM_ST_EXCLUSIVE) - inode_go_sync(gl); -} - -/** * inode_go_xmote_bh - After promoting/demoting a glock * @gl: the glock * @@ -201,22 +186,6 @@ static void inode_go_xmote_bh(struct gfs2_glock *gl) } /** - * inode_go_drop_th - unlock a glock - * @gl: the glock - * - * Invoked from rq_demote(). - * Another node needs the lock in EXCLUSIVE mode, or lock (unused for too long) - * is being purged from our node's glock cache; we're dropping lock. - */ - -static void inode_go_drop_th(struct gfs2_glock *gl) -{ - gfs2_pte_inval(gl); - if (gl->gl_state == LM_ST_EXCLUSIVE) - inode_go_sync(gl); -} - -/** * inode_go_inval - prepare a inode glock to be released * @gl: the glock * @flags: @@ -234,10 +203,8 @@ static void inode_go_inval(struct gfs2_glock *gl, int flags) set_bit(GIF_INVALID, &ip->i_flags); } - if (ip && S_ISREG(ip->i_inode.i_mode)) { + if (ip && S_ISREG(ip->i_inode.i_mode)) truncate_inode_pages(ip->i_inode.i_mapping, 0); - clear_bit(GIF_PAGED, &ip->i_flags); - } } /** @@ -294,23 +261,6 @@ static int inode_go_lock(struct gfs2_holder *gh) } /** - * inode_go_unlock - operation done before an inode lock is unlocked by a - * process - * @gl: the glock - * @flags: - * - */ - -static void inode_go_unlock(struct gfs2_holder *gh) -{ - struct gfs2_glock *gl = gh->gh_gl; - struct gfs2_inode *ip = gl->gl_object; - - if (ip) - gfs2_meta_cache_flush(ip); -} - -/** * rgrp_go_demote_ok - Check to see if it's ok to unlock a RG's glock * @gl: the glock * @@ -350,14 +300,14 @@ static void rgrp_go_unlock(struct gfs2_holder *gh) } /** - * trans_go_xmote_th - promote/demote the transaction glock + * trans_go_sync - promote/demote the transaction glock * @gl: the glock * @state: the requested state * @flags: * */ -static void trans_go_xmote_th(struct gfs2_glock *gl) +static void trans_go_sync(struct gfs2_glock *gl) { struct gfs2_sbd *sdp = gl->gl_sbd; @@ -384,7 +334,6 @@ static void trans_go_xmote_bh(struct gfs2_glock *gl) if (gl->gl_state != LM_ST_UNLOCKED && test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) { - gfs2_meta_cache_flush(GFS2_I(sdp->sd_jdesc->jd_inode)); j_gl->gl_ops->go_inval(j_gl, DIO_METADATA); error = gfs2_find_jhead(sdp->sd_jdesc, &head); @@ -402,24 +351,6 @@ static void trans_go_xmote_bh(struct gfs2_glock *gl) } /** - * trans_go_drop_th - unlock the transaction glock - * @gl: the glock - * - * We want to sync the device even with localcaching. Remember - * that localcaching journal replay only marks buffers dirty. - */ - -static void trans_go_drop_th(struct gfs2_glock *gl) -{ - struct gfs2_sbd *sdp = gl->gl_sbd; - - if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) { - gfs2_meta_syncfs(sdp); - gfs2_log_shutdown(sdp); - } -} - -/** * quota_go_demote_ok - Check to see if it's ok to unlock a quota glock * @gl: the glock * @@ -433,25 +364,21 @@ static int quota_go_demote_ok(struct gfs2_glock *gl) const struct gfs2_glock_operations gfs2_meta_glops = { .go_xmote_th = meta_go_sync, - .go_drop_th = meta_go_sync, .go_type = LM_TYPE_META, }; const struct gfs2_glock_operations gfs2_inode_glops = { - .go_xmote_th = inode_go_xmote_th, + .go_xmote_th = inode_go_sync, .go_xmote_bh = inode_go_xmote_bh, - .go_drop_th = inode_go_drop_th, .go_inval = inode_go_inval, .go_demote_ok = inode_go_demote_ok, .go_lock = inode_go_lock, - .go_unlock = inode_go_unlock, .go_type = LM_TYPE_INODE, .go_min_hold_time = HZ / 10, }; const struct gfs2_glock_operations gfs2_rgrp_glops = { .go_xmote_th = meta_go_sync, - .go_drop_th = meta_go_sync, .go_inval = meta_go_inval, .go_demote_ok = rgrp_go_demote_ok, .go_lock = rgrp_go_lock, @@ -461,9 +388,8 @@ const struct gfs2_glock_operations gfs2_rgrp_glops = { }; const struct gfs2_glock_operations gfs2_trans_glops = { - .go_xmote_th = trans_go_xmote_th, + .go_xmote_th = trans_go_sync, .go_xmote_bh = trans_go_xmote_bh, - .go_drop_th = trans_go_drop_th, .go_type = LM_TYPE_NONDISK, }; diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index eaddfb5a8e6..513aaf0dc0a 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -131,7 +131,6 @@ struct gfs2_bufdata { struct gfs2_glock_operations { void (*go_xmote_th) (struct gfs2_glock *gl); void (*go_xmote_bh) (struct gfs2_glock *gl); - void (*go_drop_th) (struct gfs2_glock *gl); void (*go_inval) (struct gfs2_glock *gl, int flags); int (*go_demote_ok) (struct gfs2_glock *gl); int (*go_lock) (struct gfs2_holder *gh); @@ -141,10 +140,6 @@ struct gfs2_glock_operations { }; enum { - /* Actions */ - HIF_MUTEX = 0, - HIF_PROMOTE = 1, - /* States */ HIF_HOLDER = 6, HIF_FIRST = 7, @@ -171,6 +166,8 @@ enum { GLF_DEMOTE = 3, GLF_PENDING_DEMOTE = 4, GLF_DIRTY = 5, + GLF_DEMOTE_IN_PROGRESS = 6, + GLF_LFLUSH = 7, }; struct gfs2_glock { @@ -190,6 +187,7 @@ struct gfs2_glock { struct list_head gl_holders; struct list_head gl_waiters1; /* HIF_MUTEX */ struct list_head gl_waiters3; /* HIF_PROMOTE */ + int gl_waiters2; /* GIF_DEMOTE */ const struct gfs2_glock_operations *gl_ops; @@ -210,7 +208,6 @@ struct gfs2_glock { struct gfs2_sbd *gl_sbd; struct inode *gl_aspace; - struct gfs2_log_element gl_le; struct list_head gl_ail_list; atomic_t gl_ail_count; struct delayed_work gl_work; @@ -239,7 +236,6 @@ struct gfs2_alloc { enum { GIF_INVALID = 0, GIF_QD_LOCKED = 1, - GIF_PAGED = 2, GIF_SW_PAGED = 3, }; @@ -268,14 +264,10 @@ struct gfs2_inode { struct gfs2_glock *i_gl; /* Move into i_gh? */ struct gfs2_holder i_iopen_gh; struct gfs2_holder i_gh; /* for prepare/commit_write only */ - struct gfs2_alloc i_alloc; + struct gfs2_alloc *i_alloc; u64 i_last_rg_alloc; - spinlock_t i_spin; struct rw_semaphore i_rw_mutex; - unsigned long i_last_pfault; - - struct buffer_head *i_cache[GFS2_MAX_META_HEIGHT]; }; /* @@ -287,19 +279,12 @@ static inline struct gfs2_inode *GFS2_I(struct inode *inode) return container_of(inode, struct gfs2_inode, i_inode); } -/* To be removed? */ -static inline struct gfs2_sbd *GFS2_SB(struct inode *inode) +static inline struct gfs2_sbd *GFS2_SB(const struct inode *inode) { return inode->i_sb->s_fs_info; } -enum { - GFF_DID_DIRECT_ALLOC = 0, - GFF_EXLOCK = 1, -}; - struct gfs2_file { - unsigned long f_flags; /* GFF_... */ struct mutex f_fl_mutex; struct gfs2_holder f_fl_gh; }; @@ -373,8 +358,17 @@ struct gfs2_ail { u64 ai_sync_gen; }; +struct gfs2_journal_extent { + struct list_head extent_list; + + unsigned int lblock; /* First logical block */ + u64 dblock; /* First disk block */ + u64 blocks; +}; + struct gfs2_jdesc { struct list_head jd_list; + struct list_head extent_list; struct inode *jd_inode; unsigned int jd_jid; @@ -421,13 +415,9 @@ struct gfs2_args { struct gfs2_tune { spinlock_t gt_spin; - unsigned int gt_ilimit; - unsigned int gt_ilimit_tries; - unsigned int gt_ilimit_min; unsigned int gt_demote_secs; /* Cache retention for unheld glock */ unsigned int gt_incore_log_blocks; unsigned int gt_log_flush_secs; - unsigned int gt_jindex_refresh_secs; /* Check for new journal index */ unsigned int gt_recoverd_secs; unsigned int gt_logd_secs; @@ -443,10 +433,8 @@ struct gfs2_tune { unsigned int gt_new_files_jdata; unsigned int gt_new_files_directio; unsigned int gt_max_readahead; /* Max bytes to read-ahead from disk */ - unsigned int gt_lockdump_size; unsigned int gt_stall_secs; /* Detects trouble! */ unsigned int gt_complain_secs; - unsigned int gt_reclaim_limit; /* Max num of glocks in reclaim list */ unsigned int gt_statfs_quantum; unsigned int gt_statfs_slow; }; @@ -539,7 +527,6 @@ struct gfs2_sbd { /* StatFS stuff */ spinlock_t sd_statfs_spin; - struct mutex sd_statfs_mutex; struct gfs2_statfs_change_host sd_statfs_master; struct gfs2_statfs_change_host sd_statfs_local; unsigned long sd_statfs_sync_time; @@ -602,20 +589,18 @@ struct gfs2_sbd { unsigned int sd_log_commited_databuf; unsigned int sd_log_commited_revoke; - unsigned int sd_log_num_gl; unsigned int sd_log_num_buf; unsigned int sd_log_num_revoke; unsigned int sd_log_num_rg; unsigned int sd_log_num_databuf; - struct list_head sd_log_le_gl; struct list_head sd_log_le_buf; struct list_head sd_log_le_revoke; struct list_head sd_log_le_rg; struct list_head sd_log_le_databuf; struct list_head sd_log_le_ordered; - unsigned int sd_log_blks_free; + atomic_t sd_log_blks_free; struct mutex sd_log_reserve_mutex; u64 sd_log_sequence; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 5f6dc32946c..728d3169e7b 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -31,7 +31,6 @@ #include "log.h" #include "meta_io.h" #include "ops_address.h" -#include "ops_file.h" #include "ops_inode.h" #include "quota.h" #include "rgrp.h" @@ -132,15 +131,21 @@ static struct inode *gfs2_iget_skip(struct super_block *sb, void gfs2_set_iop(struct inode *inode) { + struct gfs2_sbd *sdp = GFS2_SB(inode); umode_t mode = inode->i_mode; if (S_ISREG(mode)) { inode->i_op = &gfs2_file_iops; - inode->i_fop = &gfs2_file_fops; - inode->i_mapping->a_ops = &gfs2_file_aops; + if (sdp->sd_args.ar_localflocks) + inode->i_fop = &gfs2_file_fops_nolock; + else + inode->i_fop = &gfs2_file_fops; } else if (S_ISDIR(mode)) { inode->i_op = &gfs2_dir_iops; - inode->i_fop = &gfs2_dir_fops; + if (sdp->sd_args.ar_localflocks) + inode->i_fop = &gfs2_dir_fops_nolock; + else + inode->i_fop = &gfs2_dir_fops; } else if (S_ISLNK(mode)) { inode->i_op = &gfs2_symlink_iops; } else { @@ -291,12 +296,10 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) di->di_entries = be32_to_cpu(str->di_entries); di->di_eattr = be64_to_cpu(str->di_eattr); - return 0; -} + if (S_ISREG(ip->i_inode.i_mode)) + gfs2_set_aops(&ip->i_inode); -static void gfs2_inode_bh(struct gfs2_inode *ip, struct buffer_head *bh) -{ - ip->i_cache[0] = bh; + return 0; } /** @@ -366,7 +369,8 @@ int gfs2_dinode_dealloc(struct gfs2_inode *ip) if (error) goto out_rg_gunlock; - gfs2_trans_add_gl(ip->i_gl); + set_bit(GLF_DIRTY, &ip->i_gl->gl_flags); + set_bit(GLF_LFLUSH, &ip->i_gl->gl_flags); gfs2_free_di(rgd, ip); @@ -707,9 +711,10 @@ static int alloc_dinode(struct gfs2_inode *dip, u64 *no_addr, u64 *generation) struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode); int error; - gfs2_alloc_get(dip); + if (gfs2_alloc_get(dip) == NULL) + return -ENOMEM; - dip->i_alloc.al_requested = RES_DINODE; + dip->i_alloc->al_requested = RES_DINODE; error = gfs2_inplace_reserve(dip); if (error) goto out; @@ -855,7 +860,7 @@ static int link_dinode(struct gfs2_inode *dip, const struct qstr *name, error = alloc_required = gfs2_diradd_alloc_required(&dip->i_inode, name); if (alloc_required < 0) - goto fail; + goto fail_quota_locks; if (alloc_required) { error = gfs2_quota_check(dip, dip->i_inode.i_uid, dip->i_inode.i_gid); if (error) @@ -896,7 +901,7 @@ fail_end_trans: gfs2_trans_end(sdp); fail_ipreserv: - if (dip->i_alloc.al_rgd) + if (dip->i_alloc->al_rgd) gfs2_inplace_release(dip); fail_quota_locks: @@ -966,7 +971,7 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name, struct gfs2_inum_host inum = { .no_addr = 0, .no_formal_ino = 0 }; int error; u64 generation; - struct buffer_head *bh=NULL; + struct buffer_head *bh = NULL; if (!name->len || name->len > GFS2_FNAMESIZE) return ERR_PTR(-ENAMETOOLONG); @@ -1003,8 +1008,6 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name, if (IS_ERR(inode)) goto fail_gunlock2; - gfs2_inode_bh(GFS2_I(inode), bh); - error = gfs2_inode_refresh(GFS2_I(inode)); if (error) goto fail_gunlock2; @@ -1021,6 +1024,8 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name, if (error) goto fail_gunlock2; + if (bh) + brelse(bh); if (!inode) return ERR_PTR(-ENOMEM); return inode; @@ -1032,6 +1037,8 @@ fail_gunlock2: fail_gunlock: gfs2_glock_dq(ghs); fail: + if (bh) + brelse(bh); return ERR_PTR(error); } diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h index 351ac87ab38..d4465066261 100644 --- a/fs/gfs2/inode.h +++ b/fs/gfs2/inode.h @@ -20,6 +20,18 @@ static inline int gfs2_is_jdata(const struct gfs2_inode *ip) return ip->i_di.di_flags & GFS2_DIF_JDATA; } +static inline int gfs2_is_writeback(const struct gfs2_inode *ip) +{ + const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); + return (sdp->sd_args.ar_data == GFS2_DATA_WRITEBACK) && !gfs2_is_jdata(ip); +} + +static inline int gfs2_is_ordered(const struct gfs2_inode *ip) +{ + const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); + return (sdp->sd_args.ar_data == GFS2_DATA_ORDERED) && !gfs2_is_jdata(ip); +} + static inline int gfs2_is_dir(const struct gfs2_inode *ip) { return S_ISDIR(ip->i_inode.i_mode); diff --git a/fs/gfs2/locking/dlm/mount.c b/fs/gfs2/locking/dlm/mount.c index 41c5b04caab..f2efff42422 100644 --- a/fs/gfs2/locking/dlm/mount.c +++ b/fs/gfs2/locking/dlm/mount.c @@ -67,6 +67,11 @@ static int make_args(struct gdlm_ls *ls, char *data_arg, int *nodir) memset(data, 0, 256); strncpy(data, data_arg, 255); + if (!strlen(data)) { + log_error("no mount options, (u)mount helpers not installed"); + return -EINVAL; + } + for (options = data; (x = strsep(&options, ":")); ) { if (!*x) continue; diff --git a/fs/gfs2/locking/dlm/plock.c b/fs/gfs2/locking/dlm/plock.c index 1f7b038530b..2ebd374b314 100644 --- a/fs/gfs2/locking/dlm/plock.c +++ b/fs/gfs2/locking/dlm/plock.c @@ -89,15 +89,19 @@ int gdlm_plock(void *lockspace, struct lm_lockname *name, op->info.number = name->ln_number; op->info.start = fl->fl_start; op->info.end = fl->fl_end; - op->info.owner = (__u64)(long) fl->fl_owner; if (fl->fl_lmops && fl->fl_lmops->fl_grant) { + /* fl_owner is lockd which doesn't distinguish + processes on the nfs client */ + op->info.owner = (__u64) fl->fl_pid; xop->callback = fl->fl_lmops->fl_grant; locks_init_lock(&xop->flc); locks_copy_lock(&xop->flc, fl); xop->fl = fl; xop->file = file; - } else + } else { + op->info.owner = (__u64)(long) fl->fl_owner; xop->callback = NULL; + } send_op(op); @@ -203,7 +207,10 @@ int gdlm_punlock(void *lockspace, struct lm_lockname *name, op->info.number = name->ln_number; op->info.start = fl->fl_start; op->info.end = fl->fl_end; - op->info.owner = (__u64)(long) fl->fl_owner; + if (fl->fl_lmops && fl->fl_lmops->fl_grant) + op->info.owner = (__u64) fl->fl_pid; + else + op->info.owner = (__u64)(long) fl->fl_owner; send_op(op); wait_event(recv_wq, (op->done != 0)); @@ -242,7 +249,10 @@ int gdlm_plock_get(void *lockspace, struct lm_lockname *name, op->info.number = name->ln_number; op->info.start = fl->fl_start; op->info.end = fl->fl_end; - op->info.owner = (__u64)(long) fl->fl_owner; + if (fl->fl_lmops && fl->fl_lmops->fl_grant) + op->info.owner = (__u64) fl->fl_pid; + else + op->info.owner = (__u64)(long) fl->fl_owner; send_op(op); wait_event(recv_wq, (op->done != 0)); diff --git a/fs/gfs2/locking/dlm/sysfs.c b/fs/gfs2/locking/dlm/sysfs.c index ae9e6a25fe2..a87b0983976 100644 --- a/fs/gfs2/locking/dlm/sysfs.c +++ b/fs/gfs2/locking/dlm/sysfs.c @@ -189,51 +189,39 @@ static struct kobj_type gdlm_ktype = { .sysfs_ops = &gdlm_attr_ops, }; -static struct kset gdlm_kset = { - .ktype = &gdlm_ktype, -}; +static struct kset *gdlm_kset; int gdlm_kobject_setup(struct gdlm_ls *ls, struct kobject *fskobj) { int error; - error = kobject_set_name(&ls->kobj, "%s", "lock_module"); - if (error) { - log_error("can't set kobj name %d", error); - return error; - } - - ls->kobj.kset = &gdlm_kset; - ls->kobj.ktype = &gdlm_ktype; - ls->kobj.parent = fskobj; - - error = kobject_register(&ls->kobj); + ls->kobj.kset = gdlm_kset; + error = kobject_init_and_add(&ls->kobj, &gdlm_ktype, fskobj, + "lock_module"); if (error) log_error("can't register kobj %d", error); + kobject_uevent(&ls->kobj, KOBJ_ADD); return error; } void gdlm_kobject_release(struct gdlm_ls *ls) { - kobject_unregister(&ls->kobj); + kobject_put(&ls->kobj); } int gdlm_sysfs_init(void) { - int error; - - kobject_set_name(&gdlm_kset.kobj, "lock_dlm"); - kobj_set_kset_s(&gdlm_kset, kernel_subsys); - error = kset_register(&gdlm_kset); - if (error) - printk("lock_dlm: cannot register kset %d\n", error); - - return error; + gdlm_kset = kset_create_and_add("lock_dlm", NULL, kernel_kobj); + if (!gdlm_kset) { + printk(KERN_WARNING "%s: can not create kset\n", __FUNCTION__); + return -ENOMEM; + } + return 0; } void gdlm_sysfs_exit(void) { - kset_unregister(&gdlm_kset); + kset_unregister(gdlm_kset); } diff --git a/fs/gfs2/locking/dlm/thread.c b/fs/gfs2/locking/dlm/thread.c index bd938f06481..521694fc19d 100644 --- a/fs/gfs2/locking/dlm/thread.c +++ b/fs/gfs2/locking/dlm/thread.c @@ -273,18 +273,13 @@ static int gdlm_thread(void *data, int blist) struct gdlm_ls *ls = (struct gdlm_ls *) data; struct gdlm_lock *lp = NULL; uint8_t complete, blocking, submit, drop; - DECLARE_WAITQUEUE(wait, current); /* Only thread1 is allowed to do blocking callbacks since gfs may wait for a completion callback within a blocking cb. */ while (!kthread_should_stop()) { - set_current_state(TASK_INTERRUPTIBLE); - add_wait_queue(&ls->thread_wait, &wait); - if (no_work(ls, blist)) - schedule(); - remove_wait_queue(&ls->thread_wait, &wait); - set_current_state(TASK_RUNNING); + wait_event_interruptible(ls->thread_wait, + !no_work(ls, blist) || kthread_should_stop()); complete = blocking = submit = drop = 0; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 7df70247325..161ab6f2058 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -16,6 +16,8 @@ #include <linux/crc32.h> #include <linux/lm_interface.h> #include <linux/delay.h> +#include <linux/kthread.h> +#include <linux/freezer.h> #include "gfs2.h" #include "incore.h" @@ -68,14 +70,12 @@ unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct, * */ -void gfs2_remove_from_ail(struct address_space *mapping, struct gfs2_bufdata *bd) +void gfs2_remove_from_ail(struct gfs2_bufdata *bd) { bd->bd_ail = NULL; list_del_init(&bd->bd_ail_st_list); list_del_init(&bd->bd_ail_gl_list); atomic_dec(&bd->bd_gl->gl_ail_count); - if (mapping) - gfs2_meta_cache_flush(GFS2_I(mapping->host)); brelse(bd->bd_bh); } @@ -92,8 +92,6 @@ static void gfs2_ail1_start_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai) struct buffer_head *bh; int retry; - BUG_ON(!spin_is_locked(&sdp->sd_log_lock)); - do { retry = 0; @@ -210,7 +208,7 @@ static void gfs2_ail1_start(struct gfs2_sbd *sdp, int flags) gfs2_log_unlock(sdp); } -int gfs2_ail1_empty(struct gfs2_sbd *sdp, int flags) +static int gfs2_ail1_empty(struct gfs2_sbd *sdp, int flags) { struct gfs2_ail *ai, *s; int ret; @@ -248,7 +246,7 @@ static void gfs2_ail2_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai) bd = list_entry(head->prev, struct gfs2_bufdata, bd_ail_st_list); gfs2_assert(sdp, bd->bd_ail == ai); - gfs2_remove_from_ail(bd->bd_bh->b_page->mapping, bd); + gfs2_remove_from_ail(bd); } } @@ -303,7 +301,7 @@ int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks) mutex_lock(&sdp->sd_log_reserve_mutex); gfs2_log_lock(sdp); - while(sdp->sd_log_blks_free <= (blks + reserved_blks)) { + while(atomic_read(&sdp->sd_log_blks_free) <= (blks + reserved_blks)) { gfs2_log_unlock(sdp); gfs2_ail1_empty(sdp, 0); gfs2_log_flush(sdp, NULL); @@ -312,7 +310,7 @@ int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks) gfs2_ail1_start(sdp, 0); gfs2_log_lock(sdp); } - sdp->sd_log_blks_free -= blks; + atomic_sub(blks, &sdp->sd_log_blks_free); gfs2_log_unlock(sdp); mutex_unlock(&sdp->sd_log_reserve_mutex); @@ -332,27 +330,23 @@ void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks) { gfs2_log_lock(sdp); - sdp->sd_log_blks_free += blks; + atomic_add(blks, &sdp->sd_log_blks_free); gfs2_assert_withdraw(sdp, - sdp->sd_log_blks_free <= sdp->sd_jdesc->jd_blocks); + atomic_read(&sdp->sd_log_blks_free) <= sdp->sd_jdesc->jd_blocks); gfs2_log_unlock(sdp); up_read(&sdp->sd_log_flush_lock); } static u64 log_bmap(struct gfs2_sbd *sdp, unsigned int lbn) { - struct inode *inode = sdp->sd_jdesc->jd_inode; - int error; - struct buffer_head bh_map = { .b_state = 0, .b_blocknr = 0 }; - - bh_map.b_size = 1 << inode->i_blkbits; - error = gfs2_block_map(inode, lbn, 0, &bh_map); - if (error || !bh_map.b_blocknr) - printk(KERN_INFO "error=%d, dbn=%llu lbn=%u", error, - (unsigned long long)bh_map.b_blocknr, lbn); - gfs2_assert_withdraw(sdp, !error && bh_map.b_blocknr); - - return bh_map.b_blocknr; + struct gfs2_journal_extent *je; + + list_for_each_entry(je, &sdp->sd_jdesc->extent_list, extent_list) { + if (lbn >= je->lblock && lbn < je->lblock + je->blocks) + return je->dblock + lbn - je->lblock; + } + + return -1; } /** @@ -561,8 +555,8 @@ static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail) ail2_empty(sdp, new_tail); gfs2_log_lock(sdp); - sdp->sd_log_blks_free += dist; - gfs2_assert_withdraw(sdp, sdp->sd_log_blks_free <= sdp->sd_jdesc->jd_blocks); + atomic_add(dist, &sdp->sd_log_blks_free); + gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <= sdp->sd_jdesc->jd_blocks); gfs2_log_unlock(sdp); sdp->sd_log_tail = new_tail; @@ -652,7 +646,7 @@ static void gfs2_ordered_write(struct gfs2_sbd *sdp) get_bh(bh); gfs2_log_unlock(sdp); lock_buffer(bh); - if (test_clear_buffer_dirty(bh)) { + if (buffer_mapped(bh) && test_clear_buffer_dirty(bh)) { bh->b_end_io = end_buffer_write_sync; submit_bh(WRITE, bh); } else { @@ -694,20 +688,16 @@ static void gfs2_ordered_wait(struct gfs2_sbd *sdp) * */ -void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl) +void __gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl) { struct gfs2_ail *ai; down_write(&sdp->sd_log_flush_lock); - if (gl) { - gfs2_log_lock(sdp); - if (list_empty(&gl->gl_le.le_list)) { - gfs2_log_unlock(sdp); - up_write(&sdp->sd_log_flush_lock); - return; - } - gfs2_log_unlock(sdp); + /* Log might have been flushed while we waited for the flush lock */ + if (gl && !test_bit(GLF_LFLUSH, &gl->gl_flags)) { + up_write(&sdp->sd_log_flush_lock); + return; } ai = kzalloc(sizeof(struct gfs2_ail), GFP_NOFS | __GFP_NOFAIL); @@ -739,7 +729,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl) log_flush_commit(sdp); else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle){ gfs2_log_lock(sdp); - sdp->sd_log_blks_free--; /* Adjust for unreserved buffer */ + atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */ gfs2_log_unlock(sdp); log_write_header(sdp, 0, PULL); } @@ -767,7 +757,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl) static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr) { unsigned int reserved; - unsigned int old; + unsigned int unused; gfs2_log_lock(sdp); @@ -779,14 +769,11 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr) sdp->sd_log_commited_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm; gfs2_assert_withdraw(sdp, ((int)sdp->sd_log_commited_revoke) >= 0); reserved = calc_reserved(sdp); - old = sdp->sd_log_blks_free; - sdp->sd_log_blks_free += tr->tr_reserved - - (reserved - sdp->sd_log_blks_reserved); - - gfs2_assert_withdraw(sdp, sdp->sd_log_blks_free >= old); - gfs2_assert_withdraw(sdp, sdp->sd_log_blks_free <= + unused = sdp->sd_log_blks_reserved - reserved + tr->tr_reserved; + gfs2_assert_withdraw(sdp, unused >= 0); + atomic_add(unused, &sdp->sd_log_blks_free); + gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <= sdp->sd_jdesc->jd_blocks); - sdp->sd_log_blks_reserved = reserved; gfs2_log_unlock(sdp); @@ -825,7 +812,6 @@ void gfs2_log_shutdown(struct gfs2_sbd *sdp) down_write(&sdp->sd_log_flush_lock); gfs2_assert_withdraw(sdp, !sdp->sd_log_blks_reserved); - gfs2_assert_withdraw(sdp, !sdp->sd_log_num_gl); gfs2_assert_withdraw(sdp, !sdp->sd_log_num_buf); gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke); gfs2_assert_withdraw(sdp, !sdp->sd_log_num_rg); @@ -838,7 +824,7 @@ void gfs2_log_shutdown(struct gfs2_sbd *sdp) log_write_header(sdp, GFS2_LOG_HEAD_UNMOUNT, (sdp->sd_log_tail == current_tail(sdp)) ? 0 : PULL); - gfs2_assert_warn(sdp, sdp->sd_log_blks_free == sdp->sd_jdesc->jd_blocks); + gfs2_assert_warn(sdp, atomic_read(&sdp->sd_log_blks_free) == sdp->sd_jdesc->jd_blocks); gfs2_assert_warn(sdp, sdp->sd_log_head == sdp->sd_log_tail); gfs2_assert_warn(sdp, list_empty(&sdp->sd_ail2_list)); @@ -866,3 +852,42 @@ void gfs2_meta_syncfs(struct gfs2_sbd *sdp) } } + +/** + * gfs2_logd - Update log tail as Active Items get flushed to in-place blocks + * @sdp: Pointer to GFS2 superblock + * + * Also, periodically check to make sure that we're using the most recent + * journal index. + */ + +int gfs2_logd(void *data) +{ + struct gfs2_sbd *sdp = data; + unsigned long t; + int need_flush; + + while (!kthread_should_stop()) { + /* Advance the log tail */ + + t = sdp->sd_log_flush_time + + gfs2_tune_get(sdp, gt_log_flush_secs) * HZ; + + gfs2_ail1_empty(sdp, DIO_ALL); + gfs2_log_lock(sdp); + need_flush = sdp->sd_log_num_buf > gfs2_tune_get(sdp, gt_incore_log_blocks); + gfs2_log_unlock(sdp); + if (need_flush || time_after_eq(jiffies, t)) { + gfs2_log_flush(sdp, NULL); + sdp->sd_log_flush_time = jiffies; + } + + t = gfs2_tune_get(sdp, gt_logd_secs) * HZ; + if (freezing(current)) + refrigerator(); + schedule_timeout_interruptible(t); + } + + return 0; +} + diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h index dae28240062..77115281650 100644 --- a/fs/gfs2/log.h +++ b/fs/gfs2/log.h @@ -48,8 +48,6 @@ static inline void gfs2_log_pointers_init(struct gfs2_sbd *sdp, unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct, unsigned int ssize); -int gfs2_ail1_empty(struct gfs2_sbd *sdp, int flags); - int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks); void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks); void gfs2_log_incr_head(struct gfs2_sbd *sdp); @@ -57,11 +55,19 @@ void gfs2_log_incr_head(struct gfs2_sbd *sdp); struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp); struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp, struct buffer_head *real); -void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl); +void __gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl); + +static inline void gfs2_log_flush(struct gfs2_sbd *sbd, struct gfs2_glock *gl) +{ + if (!gl || test_bit(GLF_LFLUSH, &gl->gl_flags)) + __gfs2_log_flush(sbd, gl); +} + void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *trans); -void gfs2_remove_from_ail(struct address_space *mapping, struct gfs2_bufdata *bd); +void gfs2_remove_from_ail(struct gfs2_bufdata *bd); void gfs2_log_shutdown(struct gfs2_sbd *sdp); void gfs2_meta_syncfs(struct gfs2_sbd *sdp); +int gfs2_logd(void *data); #endif /* __LOG_DOT_H__ */ diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 6c27cea761c..fae59d69d01 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -87,6 +87,7 @@ static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh, } bd->bd_ail = ai; list_add(&bd->bd_ail_st_list, &ai->ai_ail1_list); + clear_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags); gfs2_log_unlock(sdp); unlock_buffer(bh); } @@ -124,49 +125,6 @@ static struct buffer_head *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type) return bh; } -static void __glock_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) -{ - struct gfs2_glock *gl; - struct gfs2_trans *tr = current->journal_info; - - tr->tr_touched = 1; - - gl = container_of(le, struct gfs2_glock, gl_le); - if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(gl))) - return; - - if (!list_empty(&le->le_list)) - return; - - gfs2_glock_hold(gl); - set_bit(GLF_DIRTY, &gl->gl_flags); - sdp->sd_log_num_gl++; - list_add(&le->le_list, &sdp->sd_log_le_gl); -} - -static void glock_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) -{ - gfs2_log_lock(sdp); - __glock_lo_add(sdp, le); - gfs2_log_unlock(sdp); -} - -static void glock_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai) -{ - struct list_head *head = &sdp->sd_log_le_gl; - struct gfs2_glock *gl; - - while (!list_empty(head)) { - gl = list_entry(head->next, struct gfs2_glock, gl_le.le_list); - list_del_init(&gl->gl_le.le_list); - sdp->sd_log_num_gl--; - - gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(gl)); - gfs2_glock_put(gl); - } - gfs2_assert_warn(sdp, !sdp->sd_log_num_gl); -} - static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) { struct gfs2_bufdata *bd = container_of(le, struct gfs2_bufdata, bd_le); @@ -182,7 +140,8 @@ static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) list_add(&bd->bd_list_tr, &tr->tr_list_buf); if (!list_empty(&le->le_list)) goto out; - __glock_lo_add(sdp, &bd->bd_gl->gl_le); + set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags); + set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags); gfs2_meta_check(sdp, bd->bd_bh); gfs2_pin(sdp, bd->bd_bh); sdp->sd_log_num_buf++; @@ -556,17 +515,20 @@ static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) lock_buffer(bd->bd_bh); gfs2_log_lock(sdp); - if (!list_empty(&bd->bd_list_tr)) - goto out; - tr->tr_touched = 1; - if (gfs2_is_jdata(ip)) { - tr->tr_num_buf++; - list_add(&bd->bd_list_tr, &tr->tr_list_buf); + if (tr) { + if (!list_empty(&bd->bd_list_tr)) + goto out; + tr->tr_touched = 1; + if (gfs2_is_jdata(ip)) { + tr->tr_num_buf++; + list_add(&bd->bd_list_tr, &tr->tr_list_buf); + } } if (!list_empty(&le->le_list)) goto out; - __glock_lo_add(sdp, &bd->bd_gl->gl_le); + set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags); + set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags); if (gfs2_is_jdata(ip)) { gfs2_pin(sdp, bd->bd_bh); tr->tr_num_databuf_new++; @@ -773,12 +735,6 @@ static void databuf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai) } -const struct gfs2_log_operations gfs2_glock_lops = { - .lo_add = glock_lo_add, - .lo_after_commit = glock_lo_after_commit, - .lo_name = "glock", -}; - const struct gfs2_log_operations gfs2_buf_lops = { .lo_add = buf_lo_add, .lo_incore_commit = buf_lo_incore_commit, @@ -816,7 +772,6 @@ const struct gfs2_log_operations gfs2_databuf_lops = { }; const struct gfs2_log_operations *gfs2_log_ops[] = { - &gfs2_glock_lops, &gfs2_databuf_lops, &gfs2_buf_lops, &gfs2_rg_lops, diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index 7ecfe0d3a49..9c7765c12d6 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -29,9 +29,8 @@ static void gfs2_init_inode_once(struct kmem_cache *cachep, void *foo) struct gfs2_inode *ip = foo; inode_init_once(&ip->i_inode); - spin_lock_init(&ip->i_spin); init_rwsem(&ip->i_rw_mutex); - memset(ip->i_cache, 0, sizeof(ip->i_cache)); + ip->i_alloc = NULL; } static void gfs2_init_glock_once(struct kmem_cache *cachep, void *foo) diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 4da423985e4..85aea27b4a8 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -50,6 +50,7 @@ static int gfs2_aspace_writepage(struct page *page, static const struct address_space_operations aspace_aops = { .writepage = gfs2_aspace_writepage, .releasepage = gfs2_releasepage, + .sync_page = block_sync_page, }; /** @@ -221,13 +222,14 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags, struct buffer_head **bhp) { *bhp = getbuf(gl, blkno, CREATE); - if (!buffer_uptodate(*bhp)) + if (!buffer_uptodate(*bhp)) { ll_rw_block(READ_META, 1, bhp); - if (flags & DIO_WAIT) { - int error = gfs2_meta_wait(gl->gl_sbd, *bhp); - if (error) { - brelse(*bhp); - return error; + if (flags & DIO_WAIT) { + int error = gfs2_meta_wait(gl->gl_sbd, *bhp); + if (error) { + brelse(*bhp); + return error; + } } } @@ -282,7 +284,7 @@ void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh, return; } - bd = kmem_cache_zalloc(gfs2_bufdata_cachep, GFP_NOFS | __GFP_NOFAIL), + bd = kmem_cache_zalloc(gfs2_bufdata_cachep, GFP_NOFS | __GFP_NOFAIL); bd->bd_bh = bh; bd->bd_gl = gl; @@ -317,7 +319,7 @@ void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int } if (bd) { if (bd->bd_ail) { - gfs2_remove_from_ail(NULL, bd); + gfs2_remove_from_ail(bd); bh->b_private = NULL; bd->bd_bh = NULL; bd->bd_blkno = bh->b_blocknr; @@ -358,32 +360,6 @@ void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen) } /** - * gfs2_meta_cache_flush - get rid of any references on buffers for this inode - * @ip: The GFS2 inode - * - * This releases buffers that are in the most-recently-used array of - * blocks used for indirect block addressing for this inode. - */ - -void gfs2_meta_cache_flush(struct gfs2_inode *ip) -{ - struct buffer_head **bh_slot; - unsigned int x; - - spin_lock(&ip->i_spin); - - for (x = 0; x < GFS2_MAX_META_HEIGHT; x++) { - bh_slot = &ip->i_cache[x]; - if (*bh_slot) { - brelse(*bh_slot); - *bh_slot = NULL; - } - } - - spin_unlock(&ip->i_spin); -} - -/** * gfs2_meta_indirect_buffer - Get a metadata buffer * @ip: The GFS2 inode * @height: The level of this buf in the metadata (indir addr) tree (if any) @@ -391,8 +367,6 @@ void gfs2_meta_cache_flush(struct gfs2_inode *ip) * @new: Non-zero if we may create a new buffer * @bhp: the buffer is returned here * - * Try to use the gfs2_inode's MRU metadata tree cache. - * * Returns: errno */ @@ -401,58 +375,25 @@ int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num, { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_glock *gl = ip->i_gl; - struct buffer_head *bh = NULL, **bh_slot = ip->i_cache + height; - int in_cache = 0; - - BUG_ON(!gl); - BUG_ON(!sdp); - - spin_lock(&ip->i_spin); - if (*bh_slot && (*bh_slot)->b_blocknr == num) { - bh = *bh_slot; - get_bh(bh); - in_cache = 1; - } - spin_unlock(&ip->i_spin); - - if (!bh) - bh = getbuf(gl, num, CREATE); - - if (!bh) - return -ENOBUFS; + struct buffer_head *bh; + int ret = 0; if (new) { - if (gfs2_assert_warn(sdp, height)) - goto err; - meta_prep_new(bh); + BUG_ON(height == 0); + bh = gfs2_meta_new(gl, num); gfs2_trans_add_bh(ip->i_gl, bh, 1); gfs2_metatype_set(bh, GFS2_METATYPE_IN, GFS2_FORMAT_IN); gfs2_buffer_clear_tail(bh, sizeof(struct gfs2_meta_header)); } else { u32 mtype = height ? GFS2_METATYPE_IN : GFS2_METATYPE_DI; - if (!buffer_uptodate(bh)) { - ll_rw_block(READ_META, 1, &bh); - if (gfs2_meta_wait(sdp, bh)) - goto err; + ret = gfs2_meta_read(gl, num, DIO_WAIT, &bh); + if (ret == 0 && gfs2_metatype_check(sdp, bh, mtype)) { + brelse(bh); + ret = -EIO; } - if (gfs2_metatype_check(sdp, bh, mtype)) - goto err; - } - - if (!in_cache) { - spin_lock(&ip->i_spin); - if (*bh_slot) - brelse(*bh_slot); - *bh_slot = bh; - get_bh(bh); - spin_unlock(&ip->i_spin); } - *bhp = bh; - return 0; -err: - brelse(bh); - return -EIO; + return ret; } /** diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h index b7048222ebb..73e3b1c76fe 100644 --- a/fs/gfs2/meta_io.h +++ b/fs/gfs2/meta_io.h @@ -56,7 +56,6 @@ void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen); -void gfs2_meta_cache_flush(struct gfs2_inode *ip); int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num, int new, struct buffer_head **bhp); diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/ops_address.c index 9679f8b9870..38dbe99a30e 100644 --- a/fs/gfs2/ops_address.c +++ b/fs/gfs2/ops_address.c @@ -20,6 +20,8 @@ #include <linux/swap.h> #include <linux/gfs2_ondisk.h> #include <linux/lm_interface.h> +#include <linux/backing-dev.h> +#include <linux/pagevec.h> #include "gfs2.h" #include "incore.h" @@ -32,7 +34,6 @@ #include "quota.h" #include "trans.h" #include "rgrp.h" -#include "ops_file.h" #include "super.h" #include "util.h" #include "glops.h" @@ -58,22 +59,6 @@ static void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page, } /** - * gfs2_get_block - Fills in a buffer head with details about a block - * @inode: The inode - * @lblock: The block number to look up - * @bh_result: The buffer head to return the result in - * @create: Non-zero if we may add block to the file - * - * Returns: errno - */ - -int gfs2_get_block(struct inode *inode, sector_t lblock, - struct buffer_head *bh_result, int create) -{ - return gfs2_block_map(inode, lblock, create, bh_result); -} - -/** * gfs2_get_block_noalloc - Fills in a buffer head with details about a block * @inode: The inode * @lblock: The block number to look up @@ -88,7 +73,7 @@ static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock, { int error; - error = gfs2_block_map(inode, lblock, 0, bh_result); + error = gfs2_block_map(inode, lblock, bh_result, 0); if (error) return error; if (!buffer_mapped(bh_result)) @@ -99,20 +84,19 @@ static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock, static int gfs2_get_block_direct(struct inode *inode, sector_t lblock, struct buffer_head *bh_result, int create) { - return gfs2_block_map(inode, lblock, 0, bh_result); + return gfs2_block_map(inode, lblock, bh_result, 0); } /** - * gfs2_writepage - Write complete page - * @page: Page to write + * gfs2_writepage_common - Common bits of writepage + * @page: The page to be written + * @wbc: The writeback control * - * Returns: errno - * - * Some of this is copied from block_write_full_page() although we still - * call it to do most of the work. + * Returns: 1 if writepage is ok, otherwise an error code or zero if no error. */ -static int gfs2_writepage(struct page *page, struct writeback_control *wbc) +static int gfs2_writepage_common(struct page *page, + struct writeback_control *wbc) { struct inode *inode = page->mapping->host; struct gfs2_inode *ip = GFS2_I(inode); @@ -120,41 +104,133 @@ static int gfs2_writepage(struct page *page, struct writeback_control *wbc) loff_t i_size = i_size_read(inode); pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT; unsigned offset; - int error; - int done_trans = 0; + int ret = -EIO; - if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(ip->i_gl))) { - unlock_page(page); - return -EIO; - } + if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(ip->i_gl))) + goto out; + ret = 0; if (current->journal_info) - goto out_ignore; - + goto redirty; /* Is the page fully outside i_size? (truncate in progress) */ - offset = i_size & (PAGE_CACHE_SIZE-1); + offset = i_size & (PAGE_CACHE_SIZE-1); if (page->index > end_index || (page->index == end_index && !offset)) { page->mapping->a_ops->invalidatepage(page, 0); - unlock_page(page); - return 0; /* don't care */ + goto out; + } + return 1; +redirty: + redirty_page_for_writepage(wbc, page); +out: + unlock_page(page); + return 0; +} + +/** + * gfs2_writeback_writepage - Write page for writeback mappings + * @page: The page + * @wbc: The writeback control + * + */ + +static int gfs2_writeback_writepage(struct page *page, + struct writeback_control *wbc) +{ + int ret; + + ret = gfs2_writepage_common(page, wbc); + if (ret <= 0) + return ret; + + ret = mpage_writepage(page, gfs2_get_block_noalloc, wbc); + if (ret == -EAGAIN) + ret = block_write_full_page(page, gfs2_get_block_noalloc, wbc); + return ret; +} + +/** + * gfs2_ordered_writepage - Write page for ordered data files + * @page: The page to write + * @wbc: The writeback control + * + */ + +static int gfs2_ordered_writepage(struct page *page, + struct writeback_control *wbc) +{ + struct inode *inode = page->mapping->host; + struct gfs2_inode *ip = GFS2_I(inode); + int ret; + + ret = gfs2_writepage_common(page, wbc); + if (ret <= 0) + return ret; + + if (!page_has_buffers(page)) { + create_empty_buffers(page, inode->i_sb->s_blocksize, + (1 << BH_Dirty)|(1 << BH_Uptodate)); } + gfs2_page_add_databufs(ip, page, 0, inode->i_sb->s_blocksize-1); + return block_write_full_page(page, gfs2_get_block_noalloc, wbc); +} - if ((sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip)) && - PageChecked(page)) { +/** + * __gfs2_jdata_writepage - The core of jdata writepage + * @page: The page to write + * @wbc: The writeback control + * + * This is shared between writepage and writepages and implements the + * core of the writepage operation. If a transaction is required then + * PageChecked will have been set and the transaction will have + * already been started before this is called. + */ + +static int __gfs2_jdata_writepage(struct page *page, struct writeback_control *wbc) +{ + struct inode *inode = page->mapping->host; + struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_sbd *sdp = GFS2_SB(inode); + + if (PageChecked(page)) { ClearPageChecked(page); - error = gfs2_trans_begin(sdp, RES_DINODE + 1, 0); - if (error) - goto out_ignore; if (!page_has_buffers(page)) { create_empty_buffers(page, inode->i_sb->s_blocksize, (1 << BH_Dirty)|(1 << BH_Uptodate)); } gfs2_page_add_databufs(ip, page, 0, sdp->sd_vfs->s_blocksize-1); + } + return block_write_full_page(page, gfs2_get_block_noalloc, wbc); +} + +/** + * gfs2_jdata_writepage - Write complete page + * @page: Page to write + * + * Returns: errno + * + */ + +static int gfs2_jdata_writepage(struct page *page, struct writeback_control *wbc) +{ + struct inode *inode = page->mapping->host; + struct gfs2_sbd *sdp = GFS2_SB(inode); + int error; + int done_trans = 0; + + error = gfs2_writepage_common(page, wbc); + if (error <= 0) + return error; + + if (PageChecked(page)) { + if (wbc->sync_mode != WB_SYNC_ALL) + goto out_ignore; + error = gfs2_trans_begin(sdp, RES_DINODE + 1, 0); + if (error) + goto out_ignore; done_trans = 1; } - error = block_write_full_page(page, gfs2_get_block_noalloc, wbc); + error = __gfs2_jdata_writepage(page, wbc); if (done_trans) gfs2_trans_end(sdp); - gfs2_meta_cache_flush(ip); return error; out_ignore: @@ -164,29 +240,190 @@ out_ignore: } /** - * gfs2_writepages - Write a bunch of dirty pages back to disk + * gfs2_writeback_writepages - Write a bunch of dirty pages back to disk * @mapping: The mapping to write * @wbc: Write-back control * - * For journaled files and/or ordered writes this just falls back to the - * kernel's default writepages path for now. We will probably want to change - * that eventually (i.e. when we look at allocate on flush). - * - * For the data=writeback case though we can already ignore buffer heads + * For the data=writeback case we can already ignore buffer heads * and write whole extents at once. This is a big reduction in the * number of I/O requests we send and the bmap calls we make in this case. */ -static int gfs2_writepages(struct address_space *mapping, - struct writeback_control *wbc) +static int gfs2_writeback_writepages(struct address_space *mapping, + struct writeback_control *wbc) +{ + return mpage_writepages(mapping, wbc, gfs2_get_block_noalloc); +} + +/** + * gfs2_write_jdata_pagevec - Write back a pagevec's worth of pages + * @mapping: The mapping + * @wbc: The writeback control + * @writepage: The writepage function to call for each page + * @pvec: The vector of pages + * @nr_pages: The number of pages to write + * + * Returns: non-zero if loop should terminate, zero otherwise + */ + +static int gfs2_write_jdata_pagevec(struct address_space *mapping, + struct writeback_control *wbc, + struct pagevec *pvec, + int nr_pages, pgoff_t end) { struct inode *inode = mapping->host; - struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); + loff_t i_size = i_size_read(inode); + pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT; + unsigned offset = i_size & (PAGE_CACHE_SIZE-1); + unsigned nrblocks = nr_pages * (PAGE_CACHE_SIZE/inode->i_sb->s_blocksize); + struct backing_dev_info *bdi = mapping->backing_dev_info; + int i; + int ret; + + ret = gfs2_trans_begin(sdp, nrblocks, 0); + if (ret < 0) + return ret; + + for(i = 0; i < nr_pages; i++) { + struct page *page = pvec->pages[i]; + + lock_page(page); + + if (unlikely(page->mapping != mapping)) { + unlock_page(page); + continue; + } + + if (!wbc->range_cyclic && page->index > end) { + ret = 1; + unlock_page(page); + continue; + } + + if (wbc->sync_mode != WB_SYNC_NONE) + wait_on_page_writeback(page); + + if (PageWriteback(page) || + !clear_page_dirty_for_io(page)) { + unlock_page(page); + continue; + } + + /* Is the page fully outside i_size? (truncate in progress) */ + if (page->index > end_index || (page->index == end_index && !offset)) { + page->mapping->a_ops->invalidatepage(page, 0); + unlock_page(page); + continue; + } + + ret = __gfs2_jdata_writepage(page, wbc); + + if (ret || (--(wbc->nr_to_write) <= 0)) + ret = 1; + if (wbc->nonblocking && bdi_write_congested(bdi)) { + wbc->encountered_congestion = 1; + ret = 1; + } + + } + gfs2_trans_end(sdp); + return ret; +} + +/** + * gfs2_write_cache_jdata - Like write_cache_pages but different + * @mapping: The mapping to write + * @wbc: The writeback control + * @writepage: The writepage function to call + * @data: The data to pass to writepage + * + * The reason that we use our own function here is that we need to + * start transactions before we grab page locks. This allows us + * to get the ordering right. + */ + +static int gfs2_write_cache_jdata(struct address_space *mapping, + struct writeback_control *wbc) +{ + struct backing_dev_info *bdi = mapping->backing_dev_info; + int ret = 0; + int done = 0; + struct pagevec pvec; + int nr_pages; + pgoff_t index; + pgoff_t end; + int scanned = 0; + int range_whole = 0; + + if (wbc->nonblocking && bdi_write_congested(bdi)) { + wbc->encountered_congestion = 1; + return 0; + } + + pagevec_init(&pvec, 0); + if (wbc->range_cyclic) { + index = mapping->writeback_index; /* Start from prev offset */ + end = -1; + } 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; + } - if (sdp->sd_args.ar_data == GFS2_DATA_WRITEBACK && !gfs2_is_jdata(ip)) - return mpage_writepages(mapping, wbc, gfs2_get_block_noalloc); +retry: + while (!done && (index <= end) && + (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, + PAGECACHE_TAG_DIRTY, + min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) { + scanned = 1; + ret = gfs2_write_jdata_pagevec(mapping, wbc, &pvec, nr_pages, end); + if (ret) + done = 1; + if (ret > 0) + ret = 0; + + pagevec_release(&pvec); + cond_resched(); + } + + if (!scanned && !done) { + /* + * We hit the last page and there is more work to be done: wrap + * back to the start of the file + */ + scanned = 1; + index = 0; + goto retry; + } + + if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) + mapping->writeback_index = index; + return ret; +} + + +/** + * gfs2_jdata_writepages - Write a bunch of dirty pages back to disk + * @mapping: The mapping to write + * @wbc: The writeback control + * + */ - return generic_writepages(mapping, wbc); +static int gfs2_jdata_writepages(struct address_space *mapping, + struct writeback_control *wbc) +{ + struct gfs2_inode *ip = GFS2_I(mapping->host); + struct gfs2_sbd *sdp = GFS2_SB(mapping->host); + int ret; + + ret = gfs2_write_cache_jdata(mapping, wbc); + if (ret == 0 && wbc->sync_mode == WB_SYNC_ALL) { + gfs2_log_flush(sdp, ip->i_gl); + ret = gfs2_write_cache_jdata(mapping, wbc); + } + return ret; } /** @@ -231,62 +468,107 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page) /** - * gfs2_readpage - readpage with locking - * @file: The file to read a page for. N.B. This may be NULL if we are - * reading an internal file. + * __gfs2_readpage - readpage + * @file: The file to read a page for * @page: The page to read * - * Returns: errno + * This is the core of gfs2's readpage. Its used by the internal file + * reading code as in that case we already hold the glock. Also its + * called by gfs2_readpage() once the required lock has been granted. + * */ -static int gfs2_readpage(struct file *file, struct page *page) +static int __gfs2_readpage(void *file, struct page *page) { struct gfs2_inode *ip = GFS2_I(page->mapping->host); struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host); - struct gfs2_file *gf = NULL; - struct gfs2_holder gh; int error; - int do_unlock = 0; - - if (likely(file != &gfs2_internal_file_sentinel)) { - if (file) { - gf = file->private_data; - if (test_bit(GFF_EXLOCK, &gf->f_flags)) - /* gfs2_sharewrite_fault has grabbed the ip->i_gl already */ - goto skip_lock; - } - gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME|LM_FLAG_TRY_1CB, &gh); - do_unlock = 1; - error = gfs2_glock_nq_atime(&gh); - if (unlikely(error)) - goto out_unlock; - } -skip_lock: if (gfs2_is_stuffed(ip)) { error = stuffed_readpage(ip, page); unlock_page(page); - } else - error = mpage_readpage(page, gfs2_get_block); + } else { + error = mpage_readpage(page, gfs2_block_map); + } if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) - error = -EIO; + return -EIO; + + return error; +} + +/** + * gfs2_readpage - read a page of a file + * @file: The file to read + * @page: The page of the file + * + * This deals with the locking required. We use a trylock in order to + * avoid the page lock / glock ordering problems returning AOP_TRUNCATED_PAGE + * in the event that we are unable to get the lock. + */ + +static int gfs2_readpage(struct file *file, struct page *page) +{ + struct gfs2_inode *ip = GFS2_I(page->mapping->host); + struct gfs2_holder gh; + int error; - if (do_unlock) { - gfs2_glock_dq_m(1, &gh); - gfs2_holder_uninit(&gh); + gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME|LM_FLAG_TRY_1CB, &gh); + error = gfs2_glock_nq_atime(&gh); + if (unlikely(error)) { + unlock_page(page); + goto out; } + error = __gfs2_readpage(file, page); + gfs2_glock_dq(&gh); out: - return error; -out_unlock: - unlock_page(page); + gfs2_holder_uninit(&gh); if (error == GLR_TRYFAILED) { - error = AOP_TRUNCATED_PAGE; yield(); + return AOP_TRUNCATED_PAGE; } - if (do_unlock) - gfs2_holder_uninit(&gh); - goto out; + return error; +} + +/** + * gfs2_internal_read - read an internal file + * @ip: The gfs2 inode + * @ra_state: The readahead state (or NULL for no readahead) + * @buf: The buffer to fill + * @pos: The file position + * @size: The amount to read + * + */ + +int gfs2_internal_read(struct gfs2_inode *ip, struct file_ra_state *ra_state, + char *buf, loff_t *pos, unsigned size) +{ + struct address_space *mapping = ip->i_inode.i_mapping; + unsigned long index = *pos / PAGE_CACHE_SIZE; + unsigned offset = *pos & (PAGE_CACHE_SIZE - 1); + unsigned copied = 0; + unsigned amt; + struct page *page; + void *p; + + do { + amt = size - copied; + if (offset + size > PAGE_CACHE_SIZE) + amt = PAGE_CACHE_SIZE - offset; + page = read_cache_page(mapping, index, __gfs2_readpage, NULL); + if (IS_ERR(page)) + return PTR_ERR(page); + p = kmap_atomic(page, KM_USER0); + memcpy(buf + copied, p + offset, amt); + kunmap_atomic(p, KM_USER0); + mark_page_accessed(page); + page_cache_release(page); + copied += amt; + index++; + offset = 0; + } while(copied < size); + (*pos) += size; + return size; } /** @@ -300,10 +582,9 @@ out_unlock: * Any I/O we ignore at this time will be done via readpage later. * 2. We don't handle stuffed files here we let readpage do the honours. * 3. mpage_readpages() does most of the heavy lifting in the common case. - * 4. gfs2_get_block() is relied upon to set BH_Boundary in the right places. - * 5. We use LM_FLAG_TRY_1CB here, effectively we then have lock-ahead as - * well as read-ahead. + * 4. gfs2_block_map() is relied upon to set BH_Boundary in the right places. */ + static int gfs2_readpages(struct file *file, struct address_space *mapping, struct list_head *pages, unsigned nr_pages) { @@ -311,42 +592,20 @@ static int gfs2_readpages(struct file *file, struct address_space *mapping, struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); struct gfs2_holder gh; - int ret = 0; - int do_unlock = 0; + int ret; - if (likely(file != &gfs2_internal_file_sentinel)) { - if (file) { - struct gfs2_file *gf = file->private_data; - if (test_bit(GFF_EXLOCK, &gf->f_flags)) - goto skip_lock; - } - gfs2_holder_init(ip->i_gl, LM_ST_SHARED, - LM_FLAG_TRY_1CB|GL_ATIME, &gh); - do_unlock = 1; - ret = gfs2_glock_nq_atime(&gh); - if (ret == GLR_TRYFAILED) - goto out_noerror; - if (unlikely(ret)) - goto out_unlock; - } -skip_lock: + gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &gh); + ret = gfs2_glock_nq_atime(&gh); + if (unlikely(ret)) + goto out_uninit; if (!gfs2_is_stuffed(ip)) - ret = mpage_readpages(mapping, pages, nr_pages, gfs2_get_block); - - if (do_unlock) { - gfs2_glock_dq_m(1, &gh); - gfs2_holder_uninit(&gh); - } -out: + ret = mpage_readpages(mapping, pages, nr_pages, gfs2_block_map); + gfs2_glock_dq(&gh); +out_uninit: + gfs2_holder_uninit(&gh); if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) ret = -EIO; return ret; -out_noerror: - ret = 0; -out_unlock: - if (do_unlock) - gfs2_holder_uninit(&gh); - goto out; } /** @@ -382,20 +641,11 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping, if (unlikely(error)) goto out_uninit; - error = -ENOMEM; - page = __grab_cache_page(mapping, index); - *pagep = page; - if (!page) - goto out_unlock; - gfs2_write_calc_reserv(ip, len, &data_blocks, &ind_blocks); - error = gfs2_write_alloc_required(ip, pos, len, &alloc_required); if (error) - goto out_putpage; - + goto out_unlock; - ip->i_alloc.al_requested = 0; if (alloc_required) { al = gfs2_alloc_get(ip); @@ -424,40 +674,47 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping, if (error) goto out_trans_fail; + error = -ENOMEM; + page = __grab_cache_page(mapping, index); + *pagep = page; + if (unlikely(!page)) + goto out_endtrans; + if (gfs2_is_stuffed(ip)) { + error = 0; if (pos + len > sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)) { error = gfs2_unstuff_dinode(ip, page); if (error == 0) goto prepare_write; - } else if (!PageUptodate(page)) + } else if (!PageUptodate(page)) { error = stuffed_readpage(ip, page); + } goto out; } prepare_write: - error = block_prepare_write(page, from, to, gfs2_get_block); - + error = block_prepare_write(page, from, to, gfs2_block_map); out: - if (error) { - gfs2_trans_end(sdp); + if (error == 0) + return 0; + + page_cache_release(page); + if (pos + len > ip->i_inode.i_size) + vmtruncate(&ip->i_inode, ip->i_inode.i_size); +out_endtrans: + gfs2_trans_end(sdp); out_trans_fail: - if (alloc_required) { - gfs2_inplace_release(ip); + if (alloc_required) { + gfs2_inplace_release(ip); out_qunlock: - gfs2_quota_unlock(ip); + gfs2_quota_unlock(ip); out_alloc_put: - gfs2_alloc_put(ip); - } -out_putpage: - page_cache_release(page); - if (pos + len > ip->i_inode.i_size) - vmtruncate(&ip->i_inode, ip->i_inode.i_size); + gfs2_alloc_put(ip); + } out_unlock: - gfs2_glock_dq_m(1, &ip->i_gh); + gfs2_glock_dq(&ip->i_gh); out_uninit: - gfs2_holder_uninit(&ip->i_gh); - } - + gfs2_holder_uninit(&ip->i_gh); return error; } @@ -565,7 +822,7 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping, struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); struct buffer_head *dibh; - struct gfs2_alloc *al = &ip->i_alloc; + struct gfs2_alloc *al = ip->i_alloc; struct gfs2_dinode *di; unsigned int from = pos & (PAGE_CACHE_SIZE - 1); unsigned int to = from + len; @@ -585,19 +842,16 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping, if (gfs2_is_stuffed(ip)) return gfs2_stuffed_write_end(inode, dibh, pos, len, copied, page); - if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip)) + if (!gfs2_is_writeback(ip)) gfs2_page_add_databufs(ip, page, from, to); ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata); - if (likely(ret >= 0)) { - copied = ret; - if ((pos + copied) > inode->i_size) { - di = (struct gfs2_dinode *)dibh->b_data; - ip->i_di.di_size = inode->i_size; - di->di_size = cpu_to_be64(inode->i_size); - mark_inode_dirty(inode); - } + if (likely(ret >= 0) && (inode->i_size > ip->i_di.di_size)) { + di = (struct gfs2_dinode *)dibh->b_data; + ip->i_di.di_size = inode->i_size; + di->di_size = cpu_to_be64(inode->i_size); + mark_inode_dirty(inode); } if (inode == sdp->sd_rindex) @@ -606,7 +860,7 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping, brelse(dibh); gfs2_trans_end(sdp); failed: - if (al->al_requested) { + if (al) { gfs2_inplace_release(ip); gfs2_quota_unlock(ip); gfs2_alloc_put(ip); @@ -625,11 +879,7 @@ failed: static int gfs2_set_page_dirty(struct page *page) { - struct gfs2_inode *ip = GFS2_I(page->mapping->host); - struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host); - - if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip)) - SetPageChecked(page); + SetPageChecked(page); return __set_page_dirty_buffers(page); } @@ -653,7 +903,7 @@ static sector_t gfs2_bmap(struct address_space *mapping, sector_t lblock) return 0; if (!gfs2_is_stuffed(ip)) - dblock = generic_block_bmap(mapping, lblock, gfs2_get_block); + dblock = generic_block_bmap(mapping, lblock, gfs2_block_map); gfs2_glock_dq_uninit(&i_gh); @@ -719,13 +969,9 @@ static int gfs2_ok_for_dio(struct gfs2_inode *ip, int rw, loff_t offset) { /* * Should we return an error here? I can't see that O_DIRECT for - * a journaled file makes any sense. For now we'll silently fall - * back to buffered I/O, likewise we do the same for stuffed - * files since they are (a) small and (b) unaligned. + * a stuffed file makes any sense. For now we'll silently fall + * back to buffered I/O */ - if (gfs2_is_jdata(ip)) - return 0; - if (gfs2_is_stuffed(ip)) return 0; @@ -836,9 +1082,23 @@ cannot_release: return 0; } -const struct address_space_operations gfs2_file_aops = { - .writepage = gfs2_writepage, - .writepages = gfs2_writepages, +static const struct address_space_operations gfs2_writeback_aops = { + .writepage = gfs2_writeback_writepage, + .writepages = gfs2_writeback_writepages, + .readpage = gfs2_readpage, + .readpages = gfs2_readpages, + .sync_page = block_sync_page, + .write_begin = gfs2_write_begin, + .write_end = gfs2_write_end, + .bmap = gfs2_bmap, + .invalidatepage = gfs2_invalidatepage, + .releasepage = gfs2_releasepage, + .direct_IO = gfs2_direct_IO, + .migratepage = buffer_migrate_page, +}; + +static const struct address_space_operations gfs2_ordered_aops = { + .writepage = gfs2_ordered_writepage, .readpage = gfs2_readpage, .readpages = gfs2_readpages, .sync_page = block_sync_page, @@ -849,5 +1109,34 @@ const struct address_space_operations gfs2_file_aops = { .invalidatepage = gfs2_invalidatepage, .releasepage = gfs2_releasepage, .direct_IO = gfs2_direct_IO, + .migratepage = buffer_migrate_page, }; +static const struct address_space_operations gfs2_jdata_aops = { + .writepage = gfs2_jdata_writepage, + .writepages = gfs2_jdata_writepages, + .readpage = gfs2_readpage, + .readpages = gfs2_readpages, + .sync_page = block_sync_page, + .write_begin = gfs2_write_begin, + .write_end = gfs2_write_end, + .set_page_dirty = gfs2_set_page_dirty, + .bmap = gfs2_bmap, + .invalidatepage = gfs2_invalidatepage, + .releasepage = gfs2_releasepage, +}; + +void gfs2_set_aops(struct inode *inode) +{ + struct gfs2_inode *ip = GFS2_I(inode); + + if (gfs2_is_writeback(ip)) + inode->i_mapping->a_ops = &gfs2_writeback_aops; + else if (gfs2_is_ordered(ip)) + inode->i_mapping->a_ops = &gfs2_ordered_aops; + else if (gfs2_is_jdata(ip)) + inode->i_mapping->a_ops = &gfs2_jdata_aops; + else + BUG(); +} + diff --git a/fs/gfs2/ops_address.h b/fs/gfs2/ops_address.h index fa1b5b3d28b..5da21285bba 100644 --- a/fs/gfs2/ops_address.h +++ b/fs/gfs2/ops_address.h @@ -14,9 +14,10 @@ #include <linux/buffer_head.h> #include <linux/mm.h> -extern const struct address_space_operations gfs2_file_aops; -extern int gfs2_get_block(struct inode *inode, sector_t lblock, - struct buffer_head *bh_result, int create); extern int gfs2_releasepage(struct page *page, gfp_t gfp_mask); +extern int gfs2_internal_read(struct gfs2_inode *ip, + struct file_ra_state *ra_state, + char *buf, loff_t *pos, unsigned size); +extern void gfs2_set_aops(struct inode *inode); #endif /* __OPS_ADDRESS_DOT_H__ */ diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/ops_file.c index bb11fd6752d..f4842f2548c 100644 --- a/fs/gfs2/ops_file.c +++ b/fs/gfs2/ops_file.c @@ -33,57 +33,12 @@ #include "lm.h" #include "log.h" #include "meta_io.h" -#include "ops_file.h" -#include "ops_vm.h" #include "quota.h" #include "rgrp.h" #include "trans.h" #include "util.h" #include "eaops.h" - -/* - * Most fields left uninitialised to catch anybody who tries to - * use them. f_flags set to prevent file_accessed() from touching - * any other part of this. Its use is purely as a flag so that we - * know (in readpage()) whether or not do to locking. - */ -struct file gfs2_internal_file_sentinel = { - .f_flags = O_NOATIME|O_RDONLY, -}; - -static int gfs2_read_actor(read_descriptor_t *desc, struct page *page, - unsigned long offset, unsigned long size) -{ - char *kaddr; - unsigned long count = desc->count; - - if (size > count) - size = count; - - kaddr = kmap(page); - memcpy(desc->arg.data, kaddr + offset, size); - kunmap(page); - - desc->count = count - size; - desc->written += size; - desc->arg.buf += size; - return size; -} - -int gfs2_internal_read(struct gfs2_inode *ip, struct file_ra_state *ra_state, - char *buf, loff_t *pos, unsigned size) -{ - struct inode *inode = &ip->i_inode; - read_descriptor_t desc; - desc.written = 0; - desc.arg.data = buf; - desc.count = size; - desc.error = 0; - do_generic_mapping_read(inode->i_mapping, ra_state, - &gfs2_internal_file_sentinel, pos, &desc, - gfs2_read_actor); - return desc.written ? desc.written : desc.error; -} +#include "ops_address.h" /** * gfs2_llseek - seek to a location in a file @@ -214,7 +169,7 @@ static int gfs2_get_flags(struct file *filp, u32 __user *ptr) if (put_user(fsflags, ptr)) error = -EFAULT; - gfs2_glock_dq_m(1, &gh); + gfs2_glock_dq(&gh); gfs2_holder_uninit(&gh); return error; } @@ -291,7 +246,16 @@ static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask) if (error) goto out; } - + if ((flags ^ new_flags) & GFS2_DIF_JDATA) { + if (flags & GFS2_DIF_JDATA) + gfs2_log_flush(sdp, ip->i_gl); + error = filemap_fdatawrite(inode->i_mapping); + if (error) + goto out; + error = filemap_fdatawait(inode->i_mapping); + if (error) + goto out; + } error = gfs2_trans_begin(sdp, RES_DINODE, 0); if (error) goto out; @@ -303,6 +267,7 @@ static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask) gfs2_dinode_out(ip, bh->b_data); brelse(bh); gfs2_set_inode_flags(inode); + gfs2_set_aops(inode); out_trans_end: gfs2_trans_end(sdp); out: @@ -338,6 +303,128 @@ static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return -ENOTTY; } +/** + * gfs2_allocate_page_backing - Use bmap to allocate blocks + * @page: The (locked) page to allocate backing for + * + * We try to allocate all the blocks required for the page in + * one go. This might fail for various reasons, so we keep + * trying until all the blocks to back this page are allocated. + * If some of the blocks are already allocated, thats ok too. + */ + +static int gfs2_allocate_page_backing(struct page *page) +{ + struct inode *inode = page->mapping->host; + struct buffer_head bh; + unsigned long size = PAGE_CACHE_SIZE; + u64 lblock = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits); + + do { + bh.b_state = 0; + bh.b_size = size; + gfs2_block_map(inode, lblock, &bh, 1); + if (!buffer_mapped(&bh)) + return -EIO; + size -= bh.b_size; + lblock += (bh.b_size >> inode->i_blkbits); + } while(size > 0); + return 0; +} + +/** + * gfs2_page_mkwrite - Make a shared, mmap()ed, page writable + * @vma: The virtual memory area + * @page: The page which is about to become writable + * + * When the page becomes writable, we need to ensure that we have + * blocks allocated on disk to back that page. + */ + +static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct page *page) +{ + struct inode *inode = vma->vm_file->f_path.dentry->d_inode; + struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_sbd *sdp = GFS2_SB(inode); + unsigned long last_index; + u64 pos = page->index << (PAGE_CACHE_SIZE - inode->i_blkbits); + unsigned int data_blocks, ind_blocks, rblocks; + int alloc_required = 0; + struct gfs2_holder gh; + struct gfs2_alloc *al; + int ret; + + gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_ATIME, &gh); + ret = gfs2_glock_nq_atime(&gh); + if (ret) + goto out; + + set_bit(GIF_SW_PAGED, &ip->i_flags); + gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks); + ret = gfs2_write_alloc_required(ip, pos, PAGE_CACHE_SIZE, &alloc_required); + if (ret || !alloc_required) + goto out_unlock; + ret = -ENOMEM; + al = gfs2_alloc_get(ip); + if (al == NULL) + goto out_unlock; + + ret = gfs2_quota_lock(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE); + if (ret) + goto out_alloc_put; + ret = gfs2_quota_check(ip, ip->i_inode.i_uid, ip->i_inode.i_gid); + if (ret) + goto out_quota_unlock; + al->al_requested = data_blocks + ind_blocks; + ret = gfs2_inplace_reserve(ip); + if (ret) + goto out_quota_unlock; + + rblocks = RES_DINODE + ind_blocks; + if (gfs2_is_jdata(ip)) + rblocks += data_blocks ? data_blocks : 1; + if (ind_blocks || data_blocks) + rblocks += RES_STATFS + RES_QUOTA; + ret = gfs2_trans_begin(sdp, rblocks, 0); + if (ret) + goto out_trans_fail; + + lock_page(page); + ret = -EINVAL; + last_index = ip->i_inode.i_size >> PAGE_CACHE_SHIFT; + if (page->index > last_index) + goto out_unlock_page; + ret = 0; + if (!PageUptodate(page) || page->mapping != ip->i_inode.i_mapping) + goto out_unlock_page; + if (gfs2_is_stuffed(ip)) { + ret = gfs2_unstuff_dinode(ip, page); + if (ret) + goto out_unlock_page; + } + ret = gfs2_allocate_page_backing(page); + +out_unlock_page: + unlock_page(page); + gfs2_trans_end(sdp); +out_trans_fail: + gfs2_inplace_release(ip); +out_quota_unlock: + gfs2_quota_unlock(ip); +out_alloc_put: + gfs2_alloc_put(ip); +out_unlock: + gfs2_glock_dq(&gh); +out: + gfs2_holder_uninit(&gh); + return ret; +} + +static struct vm_operations_struct gfs2_vm_ops = { + .fault = filemap_fault, + .page_mkwrite = gfs2_page_mkwrite, +}; + /** * gfs2_mmap - @@ -360,14 +447,7 @@ static int gfs2_mmap(struct file *file, struct vm_area_struct *vma) return error; } - /* This is VM_MAYWRITE instead of VM_WRITE because a call - to mprotect() can turn on VM_WRITE later. */ - - if ((vma->vm_flags & (VM_MAYSHARE | VM_MAYWRITE)) == - (VM_MAYSHARE | VM_MAYWRITE)) - vma->vm_ops = &gfs2_vm_ops_sharewrite; - else - vma->vm_ops = &gfs2_vm_ops_private; + vma->vm_ops = &gfs2_vm_ops; gfs2_glock_dq_uninit(&i_gh); @@ -538,15 +618,6 @@ static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl) if (__mandatory_lock(&ip->i_inode)) return -ENOLCK; - if (sdp->sd_args.ar_localflocks) { - if (IS_GETLK(cmd)) { - posix_test_lock(file, fl); - return 0; - } else { - return posix_lock_file_wait(file, fl); - } - } - if (cmd == F_CANCELLK) { /* Hack: */ cmd = F_SETLK; @@ -632,16 +703,12 @@ static void do_unflock(struct file *file, struct file_lock *fl) static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl) { struct gfs2_inode *ip = GFS2_I(file->f_mapping->host); - struct gfs2_sbd *sdp = GFS2_SB(file->f_mapping->host); if (!(fl->fl_flags & FL_FLOCK)) return -ENOLCK; if (__mandatory_lock(&ip->i_inode)) return -ENOLCK; - if (sdp->sd_args.ar_localflocks) - return flock_lock_file_wait(file, fl); - if (fl->fl_type == F_UNLCK) { do_unflock(file, fl); return 0; @@ -678,3 +745,27 @@ const struct file_operations gfs2_dir_fops = { .flock = gfs2_flock, }; +const struct file_operations gfs2_file_fops_nolock = { + .llseek = gfs2_llseek, + .read = do_sync_read, + .aio_read = generic_file_aio_read, + .write = do_sync_write, + .aio_write = generic_file_aio_write, + .unlocked_ioctl = gfs2_ioctl, + .mmap = gfs2_mmap, + .open = gfs2_open, + .release = gfs2_close, + .fsync = gfs2_fsync, + .splice_read = generic_file_splice_read, + .splice_write = generic_file_splice_write, + .setlease = gfs2_setlease, +}; + +const struct file_operations gfs2_dir_fops_nolock = { + .readdir = gfs2_readdir, + .unlocked_ioctl = gfs2_ioctl, + .open = gfs2_open, + .release = gfs2_close, + .fsync = gfs2_fsync, +}; + diff --git a/fs/gfs2/ops_file.h b/fs/gfs2/ops_file.h deleted file mode 100644 index 7e5d8ec9c84..00000000000 --- a/fs/gfs2/ops_file.h +++ /dev/null @@ -1,24 +0,0 @@ -/* - * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. - */ - -#ifndef __OPS_FILE_DOT_H__ -#define __OPS_FILE_DOT_H__ - -#include <linux/fs.h> -struct gfs2_inode; - -extern struct file gfs2_internal_file_sentinel; -extern int gfs2_internal_read(struct gfs2_inode *ip, - struct file_ra_state *ra_state, - char *buf, loff_t *pos, unsigned size); -extern void gfs2_set_inode_flags(struct inode *inode); -extern const struct file_operations gfs2_file_fops; -extern const struct file_operations gfs2_dir_fops; - -#endif /* __OPS_FILE_DOT_H__ */ diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 17de58e83d9..43d511bba52 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -21,6 +21,7 @@ #include "gfs2.h" #include "incore.h" +#include "bmap.h" #include "daemon.h" #include "glock.h" #include "glops.h" @@ -59,7 +60,6 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) mutex_init(&sdp->sd_inum_mutex); spin_lock_init(&sdp->sd_statfs_spin); - mutex_init(&sdp->sd_statfs_mutex); spin_lock_init(&sdp->sd_rindex_spin); mutex_init(&sdp->sd_rindex_mutex); @@ -77,7 +77,6 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) spin_lock_init(&sdp->sd_log_lock); - INIT_LIST_HEAD(&sdp->sd_log_le_gl); INIT_LIST_HEAD(&sdp->sd_log_le_buf); INIT_LIST_HEAD(&sdp->sd_log_le_revoke); INIT_LIST_HEAD(&sdp->sd_log_le_rg); @@ -303,6 +302,67 @@ out: return error; } +/** + * map_journal_extents - create a reusable "extent" mapping from all logical + * blocks to all physical blocks for the given journal. This will save + * us time when writing journal blocks. Most journals will have only one + * extent that maps all their logical blocks. That's because gfs2.mkfs + * arranges the journal blocks sequentially to maximize performance. + * So the extent would map the first block for the entire file length. + * However, gfs2_jadd can happen while file activity is happening, so + * those journals may not be sequential. Less likely is the case where + * the users created their own journals by mounting the metafs and + * laying it out. But it's still possible. These journals might have + * several extents. + * + * TODO: This should be done in bigger chunks rather than one block at a time, + * but since it's only done at mount time, I'm not worried about the + * time it takes. + */ +static int map_journal_extents(struct gfs2_sbd *sdp) +{ + struct gfs2_jdesc *jd = sdp->sd_jdesc; + unsigned int lb; + u64 db, prev_db; /* logical block, disk block, prev disk block */ + struct gfs2_inode *ip = GFS2_I(jd->jd_inode); + struct gfs2_journal_extent *jext = NULL; + struct buffer_head bh; + int rc = 0; + + prev_db = 0; + + for (lb = 0; lb < ip->i_di.di_size >> sdp->sd_sb.sb_bsize_shift; lb++) { + bh.b_state = 0; + bh.b_blocknr = 0; + bh.b_size = 1 << ip->i_inode.i_blkbits; + rc = gfs2_block_map(jd->jd_inode, lb, &bh, 0); + db = bh.b_blocknr; + if (rc || !db) { + printk(KERN_INFO "GFS2 journal mapping error %d: lb=" + "%u db=%llu\n", rc, lb, (unsigned long long)db); + break; + } + if (!prev_db || db != prev_db + 1) { + jext = kzalloc(sizeof(struct gfs2_journal_extent), + GFP_KERNEL); + if (!jext) { + printk(KERN_INFO "GFS2 error: out of memory " + "mapping journal extents.\n"); + rc = -ENOMEM; + break; + } + jext->dblock = db; + jext->lblock = lb; + jext->blocks = 1; + list_add_tail(&jext->extent_list, &jd->extent_list); + } else { + jext->blocks++; + } + prev_db = db; + } + return rc; +} + static int init_journal(struct gfs2_sbd *sdp, int undo) { struct gfs2_holder ji_gh; @@ -340,7 +400,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo) if (sdp->sd_args.ar_spectator) { sdp->sd_jdesc = gfs2_jdesc_find(sdp, 0); - sdp->sd_log_blks_free = sdp->sd_jdesc->jd_blocks; + atomic_set(&sdp->sd_log_blks_free, sdp->sd_jdesc->jd_blocks); } else { if (sdp->sd_lockstruct.ls_jid >= gfs2_jindex_size(sdp)) { fs_err(sdp, "can't mount journal #%u\n", @@ -377,7 +437,10 @@ static int init_journal(struct gfs2_sbd *sdp, int undo) sdp->sd_jdesc->jd_jid, error); goto fail_jinode_gh; } - sdp->sd_log_blks_free = sdp->sd_jdesc->jd_blocks; + atomic_set(&sdp->sd_log_blks_free, sdp->sd_jdesc->jd_blocks); + + /* Map the extents for this journal's blocks */ + map_journal_extents(sdp); } if (sdp->sd_lockstruct.ls_first) { diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c index 291f0c7eaa3..9f71372c175 100644 --- a/fs/gfs2/ops_inode.c +++ b/fs/gfs2/ops_inode.c @@ -61,7 +61,7 @@ static int gfs2_create(struct inode *dir, struct dentry *dentry, inode = gfs2_createi(ghs, &dentry->d_name, S_IFREG | mode, 0); if (!IS_ERR(inode)) { gfs2_trans_end(sdp); - if (dip->i_alloc.al_rgd) + if (dip->i_alloc->al_rgd) gfs2_inplace_release(dip); gfs2_quota_unlock(dip); gfs2_alloc_put(dip); @@ -113,8 +113,18 @@ static struct dentry *gfs2_lookup(struct inode *dir, struct dentry *dentry, if (inode && IS_ERR(inode)) return ERR_PTR(PTR_ERR(inode)); - if (inode) + if (inode) { + struct gfs2_glock *gl = GFS2_I(inode)->i_gl; + struct gfs2_holder gh; + int error; + error = gfs2_glock_nq_init(gl, LM_ST_SHARED, LM_FLAG_ANY, &gh); + if (error) { + iput(inode); + return ERR_PTR(error); + } + gfs2_glock_dq_uninit(&gh); return d_splice_alias(inode, dentry); + } d_add(dentry, inode); return NULL; @@ -366,7 +376,7 @@ static int gfs2_symlink(struct inode *dir, struct dentry *dentry, } gfs2_trans_end(sdp); - if (dip->i_alloc.al_rgd) + if (dip->i_alloc->al_rgd) gfs2_inplace_release(dip); gfs2_quota_unlock(dip); gfs2_alloc_put(dip); @@ -442,7 +452,7 @@ static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, int mode) gfs2_assert_withdraw(sdp, !error); /* dip already pinned */ gfs2_trans_end(sdp); - if (dip->i_alloc.al_rgd) + if (dip->i_alloc->al_rgd) gfs2_inplace_release(dip); gfs2_quota_unlock(dip); gfs2_alloc_put(dip); @@ -548,7 +558,7 @@ static int gfs2_mknod(struct inode *dir, struct dentry *dentry, int mode, } gfs2_trans_end(sdp); - if (dip->i_alloc.al_rgd) + if (dip->i_alloc->al_rgd) gfs2_inplace_release(dip); gfs2_quota_unlock(dip); gfs2_alloc_put(dip); diff --git a/fs/gfs2/ops_inode.h b/fs/gfs2/ops_inode.h index 34f0caac1a0..fd8cee231e1 100644 --- a/fs/gfs2/ops_inode.h +++ b/fs/gfs2/ops_inode.h @@ -16,5 +16,11 @@ extern const struct inode_operations gfs2_file_iops; extern const struct inode_operations gfs2_dir_iops; extern const struct inode_operations gfs2_symlink_iops; extern const struct inode_operations gfs2_dev_iops; +extern const struct file_operations gfs2_file_fops; +extern const struct file_operations gfs2_dir_fops; +extern const struct file_operations gfs2_file_fops_nolock; +extern const struct file_operations gfs2_dir_fops_nolock; + +extern void gfs2_set_inode_flags(struct inode *inode); #endif /* __OPS_INODE_DOT_H__ */ diff --git a/fs/gfs2/ops_super.c b/fs/gfs2/ops_super.c index 950f31460e8..5e524217944 100644 --- a/fs/gfs2/ops_super.c +++ b/fs/gfs2/ops_super.c @@ -487,7 +487,6 @@ static struct inode *gfs2_alloc_inode(struct super_block *sb) if (ip) { ip->i_flags = 0; ip->i_gl = NULL; - ip->i_last_pfault = jiffies; } return &ip->i_inode; } diff --git a/fs/gfs2/ops_vm.c b/fs/gfs2/ops_vm.c deleted file mode 100644 index 927d739d468..00000000000 --- a/fs/gfs2/ops_vm.c +++ /dev/null @@ -1,169 +0,0 @@ -/* - * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. - */ - -#include <linux/slab.h> -#include <linux/spinlock.h> -#include <linux/completion.h> -#include <linux/buffer_head.h> -#include <linux/mm.h> -#include <linux/pagemap.h> -#include <linux/gfs2_ondisk.h> -#include <linux/lm_interface.h> - -#include "gfs2.h" -#include "incore.h" -#include "bmap.h" -#include "glock.h" -#include "inode.h" -#include "ops_vm.h" -#include "quota.h" -#include "rgrp.h" -#include "trans.h" -#include "util.h" - -static int gfs2_private_fault(struct vm_area_struct *vma, struct vm_fault *vmf) -{ - struct gfs2_inode *ip = GFS2_I(vma->vm_file->f_mapping->host); - - set_bit(GIF_PAGED, &ip->i_flags); - return filemap_fault(vma, vmf); -} - -static int alloc_page_backing(struct gfs2_inode *ip, struct page *page) -{ - struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - unsigned long index = page->index; - u64 lblock = index << (PAGE_CACHE_SHIFT - - sdp->sd_sb.sb_bsize_shift); - unsigned int blocks = PAGE_CACHE_SIZE >> sdp->sd_sb.sb_bsize_shift; - struct gfs2_alloc *al; - unsigned int data_blocks, ind_blocks; - unsigned int x; - int error; - - al = gfs2_alloc_get(ip); - - error = gfs2_quota_lock(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE); - if (error) - goto out; - - error = gfs2_quota_check(ip, ip->i_inode.i_uid, ip->i_inode.i_gid); - if (error) - goto out_gunlock_q; - - gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks); - - al->al_requested = data_blocks + ind_blocks; - - error = gfs2_inplace_reserve(ip); - if (error) - goto out_gunlock_q; - - error = gfs2_trans_begin(sdp, al->al_rgd->rd_length + - ind_blocks + RES_DINODE + - RES_STATFS + RES_QUOTA, 0); - if (error) - goto out_ipres; - - if (gfs2_is_stuffed(ip)) { - error = gfs2_unstuff_dinode(ip, NULL); - if (error) - goto out_trans; - } - - for (x = 0; x < blocks; ) { - u64 dblock; - unsigned int extlen; - int new = 1; - - error = gfs2_extent_map(&ip->i_inode, lblock, &new, &dblock, &extlen); - if (error) - goto out_trans; - - lblock += extlen; - x += extlen; - } - - gfs2_assert_warn(sdp, al->al_alloced); - -out_trans: - gfs2_trans_end(sdp); -out_ipres: - gfs2_inplace_release(ip); -out_gunlock_q: - gfs2_quota_unlock(ip); -out: - gfs2_alloc_put(ip); - return error; -} - -static int gfs2_sharewrite_fault(struct vm_area_struct *vma, - struct vm_fault *vmf) -{ - struct file *file = vma->vm_file; - struct gfs2_file *gf = file->private_data; - struct gfs2_inode *ip = GFS2_I(file->f_mapping->host); - struct gfs2_holder i_gh; - int alloc_required; - int error; - int ret = 0; - - error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh); - if (error) - goto out; - - set_bit(GIF_PAGED, &ip->i_flags); - set_bit(GIF_SW_PAGED, &ip->i_flags); - - error = gfs2_write_alloc_required(ip, - (u64)vmf->pgoff << PAGE_CACHE_SHIFT, - PAGE_CACHE_SIZE, &alloc_required); - if (error) { - ret = VM_FAULT_OOM; /* XXX: are these right? */ - goto out_unlock; - } - - set_bit(GFF_EXLOCK, &gf->f_flags); - ret = filemap_fault(vma, vmf); - clear_bit(GFF_EXLOCK, &gf->f_flags); - if (ret & VM_FAULT_ERROR) - goto out_unlock; - - if (alloc_required) { - /* XXX: do we need to drop page lock around alloc_page_backing?*/ - error = alloc_page_backing(ip, vmf->page); - if (error) { - /* - * VM_FAULT_LOCKED should always be the case for - * filemap_fault, but it may not be in a future - * implementation. - */ - if (ret & VM_FAULT_LOCKED) - unlock_page(vmf->page); - page_cache_release(vmf->page); - ret = VM_FAULT_OOM; - goto out_unlock; - } - set_page_dirty(vmf->page); - } - -out_unlock: - gfs2_glock_dq_uninit(&i_gh); -out: - return ret; -} - -struct vm_operations_struct gfs2_vm_ops_private = { - .fault = gfs2_private_fault, -}; - -struct vm_operations_struct gfs2_vm_ops_sharewrite = { - .fault = gfs2_sharewrite_fault, -}; - diff --git a/fs/gfs2/ops_vm.h b/fs/gfs2/ops_vm.h deleted file mode 100644 index 4ae8f43ed5e..00000000000 --- a/fs/gfs2/ops_vm.h +++ /dev/null @@ -1,18 +0,0 @@ -/* - * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. - */ - -#ifndef __OPS_VM_DOT_H__ -#define __OPS_VM_DOT_H__ - -#include <linux/mm.h> - -extern struct vm_operations_struct gfs2_vm_ops_private; -extern struct vm_operations_struct gfs2_vm_ops_sharewrite; - -#endif /* __OPS_VM_DOT_H__ */ diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index addb51e0f13..a08dabd6ce9 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -59,7 +59,6 @@ #include "super.h" #include "trans.h" #include "inode.h" -#include "ops_file.h" #include "ops_address.h" #include "util.h" @@ -274,10 +273,10 @@ static int bh_get(struct gfs2_quota_data *qd) } block = qd->qd_slot / sdp->sd_qc_per_block; - offset = qd->qd_slot % sdp->sd_qc_per_block;; + offset = qd->qd_slot % sdp->sd_qc_per_block; bh_map.b_size = 1 << ip->i_inode.i_blkbits; - error = gfs2_block_map(&ip->i_inode, block, 0, &bh_map); + error = gfs2_block_map(&ip->i_inode, block, &bh_map, 0); if (error) goto fail; error = gfs2_meta_read(ip->i_gl, bh_map.b_blocknr, DIO_WAIT, &bh); @@ -454,7 +453,7 @@ static void qdsb_put(struct gfs2_quota_data *qd) int gfs2_quota_hold(struct gfs2_inode *ip, u32 uid, u32 gid) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - struct gfs2_alloc *al = &ip->i_alloc; + struct gfs2_alloc *al = ip->i_alloc; struct gfs2_quota_data **qd = al->al_qd; int error; @@ -502,7 +501,7 @@ out: void gfs2_quota_unhold(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - struct gfs2_alloc *al = &ip->i_alloc; + struct gfs2_alloc *al = ip->i_alloc; unsigned int x; gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags)); @@ -646,7 +645,7 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc, } if (!buffer_mapped(bh)) { - gfs2_get_block(inode, iblock, bh, 1); + gfs2_block_map(inode, iblock, bh, 1); if (!buffer_mapped(bh)) goto unlock; } @@ -793,11 +792,9 @@ static int do_glock(struct gfs2_quota_data *qd, int force_refresh, struct gfs2_holder i_gh; struct gfs2_quota_host q; char buf[sizeof(struct gfs2_quota)]; - struct file_ra_state ra_state; int error; struct gfs2_quota_lvb *qlvb; - file_ra_state_init(&ra_state, sdp->sd_quota_inode->i_mapping); restart: error = gfs2_glock_nq_init(qd->qd_gl, LM_ST_SHARED, 0, q_gh); if (error) @@ -820,8 +817,8 @@ restart: memset(buf, 0, sizeof(struct gfs2_quota)); pos = qd2offset(qd); - error = gfs2_internal_read(ip, &ra_state, buf, - &pos, sizeof(struct gfs2_quota)); + error = gfs2_internal_read(ip, NULL, buf, &pos, + sizeof(struct gfs2_quota)); if (error < 0) goto fail_gunlock; @@ -856,7 +853,7 @@ fail: int gfs2_quota_lock(struct gfs2_inode *ip, u32 uid, u32 gid) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - struct gfs2_alloc *al = &ip->i_alloc; + struct gfs2_alloc *al = ip->i_alloc; unsigned int x; int error = 0; @@ -924,7 +921,7 @@ static int need_sync(struct gfs2_quota_data *qd) void gfs2_quota_unlock(struct gfs2_inode *ip) { - struct gfs2_alloc *al = &ip->i_alloc; + struct gfs2_alloc *al = ip->i_alloc; struct gfs2_quota_data *qda[4]; unsigned int count = 0; unsigned int x; @@ -972,7 +969,7 @@ static int print_message(struct gfs2_quota_data *qd, char *type) int gfs2_quota_check(struct gfs2_inode *ip, u32 uid, u32 gid) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - struct gfs2_alloc *al = &ip->i_alloc; + struct gfs2_alloc *al = ip->i_alloc; struct gfs2_quota_data *qd; s64 value; unsigned int x; @@ -1016,10 +1013,9 @@ int gfs2_quota_check(struct gfs2_inode *ip, u32 uid, u32 gid) void gfs2_quota_change(struct gfs2_inode *ip, s64 change, u32 uid, u32 gid) { - struct gfs2_alloc *al = &ip->i_alloc; + struct gfs2_alloc *al = ip->i_alloc; struct gfs2_quota_data *qd; unsigned int x; - unsigned int found = 0; if (gfs2_assert_warn(GFS2_SB(&ip->i_inode), change)) return; @@ -1032,7 +1028,6 @@ void gfs2_quota_change(struct gfs2_inode *ip, s64 change, if ((qd->qd_id == uid && test_bit(QDF_USER, &qd->qd_flags)) || (qd->qd_id == gid && !test_bit(QDF_USER, &qd->qd_flags))) { do_qc(qd, change); - found++; } } } diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index beb6c7ac008..b249e294a95 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -391,7 +391,7 @@ static int clean_journal(struct gfs2_jdesc *jd, struct gfs2_log_header_host *hea lblock = head->lh_blkno; gfs2_replay_incr_blk(sdp, &lblock); bh_map.b_size = 1 << ip->i_inode.i_blkbits; - error = gfs2_block_map(&ip->i_inode, lblock, 0, &bh_map); + error = gfs2_block_map(&ip->i_inode, lblock, &bh_map, 0); if (error) return error; if (!bh_map.b_blocknr) { @@ -504,13 +504,21 @@ int gfs2_recover_journal(struct gfs2_jdesc *jd) if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) ro = 1; } else { - if (sdp->sd_vfs->s_flags & MS_RDONLY) - ro = 1; + if (sdp->sd_vfs->s_flags & MS_RDONLY) { + /* check if device itself is read-only */ + ro = bdev_read_only(sdp->sd_vfs->s_bdev); + if (!ro) { + fs_info(sdp, "recovery required on " + "read-only filesystem.\n"); + fs_info(sdp, "write access will be " + "enabled during recovery.\n"); + } + } } if (ro) { - fs_warn(sdp, "jid=%u: Can't replay: read-only FS\n", - jd->jd_jid); + fs_warn(sdp, "jid=%u: Can't replay: read-only block " + "device\n", jd->jd_jid); error = -EROFS; goto fail_gunlock_tr; } diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 708c287e1d0..3552110b2e5 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -25,10 +25,10 @@ #include "rgrp.h" #include "super.h" #include "trans.h" -#include "ops_file.h" #include "util.h" #include "log.h" #include "inode.h" +#include "ops_address.h" #define BFITNOENT ((u32)~0) #define NO_BLOCK ((u64)~0) @@ -126,41 +126,43 @@ static unsigned char gfs2_testbit(struct gfs2_rgrpd *rgd, unsigned char *buffer, * Return: the block number (bitmap buffer scope) that was found */ -static u32 gfs2_bitfit(struct gfs2_rgrpd *rgd, unsigned char *buffer, - unsigned int buflen, u32 goal, - unsigned char old_state) +static u32 gfs2_bitfit(unsigned char *buffer, unsigned int buflen, u32 goal, + unsigned char old_state) { - unsigned char *byte, *end, alloc; + unsigned char *byte; u32 blk = goal; - unsigned int bit; + unsigned int bit, bitlong; + unsigned long *plong, plong55; byte = buffer + (goal / GFS2_NBBY); + plong = (unsigned long *)(buffer + (goal / GFS2_NBBY)); bit = (goal % GFS2_NBBY) * GFS2_BIT_SIZE; - end = buffer + buflen; - alloc = (old_state == GFS2_BLKST_FREE) ? 0x55 : 0; - - while (byte < end) { - /* If we're looking for a free block we can eliminate all - bitmap settings with 0x55, which represents four data - blocks in a row. If we're looking for a data block, we can - eliminate 0x00 which corresponds to four free blocks. */ - if ((*byte & 0x55) == alloc) { - blk += (8 - bit) >> 1; - - bit = 0; - byte++; - + bitlong = bit; +#if BITS_PER_LONG == 32 + plong55 = 0x55555555; +#else + plong55 = 0x5555555555555555; +#endif + while (byte < buffer + buflen) { + + if (bitlong == 0 && old_state == 0 && *plong == plong55) { + plong++; + byte += sizeof(unsigned long); + blk += sizeof(unsigned long) * GFS2_NBBY; continue; } - if (((*byte >> bit) & GFS2_BIT_MASK) == old_state) return blk; - bit += GFS2_BIT_SIZE; if (bit >= 8) { bit = 0; byte++; } + bitlong += GFS2_BIT_SIZE; + if (bitlong >= sizeof(unsigned long) * 8) { + bitlong = 0; + plong++; + } blk++; } @@ -817,11 +819,9 @@ void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd) struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip) { - struct gfs2_alloc *al = &ip->i_alloc; - - /* FIXME: Should assert that the correct locks are held here... */ - memset(al, 0, sizeof(*al)); - return al; + BUG_ON(ip->i_alloc != NULL); + ip->i_alloc = kzalloc(sizeof(struct gfs2_alloc), GFP_KERNEL); + return ip->i_alloc; } /** @@ -1059,26 +1059,34 @@ static struct inode *get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked) struct inode *inode = NULL; struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_rgrpd *rgd, *begin = NULL; - struct gfs2_alloc *al = &ip->i_alloc; + struct gfs2_alloc *al = ip->i_alloc; int flags = LM_FLAG_TRY; int skipped = 0; int loops = 0; - int error; + int error, rg_locked; /* Try recently successful rgrps */ rgd = recent_rgrp_first(sdp, ip->i_last_rg_alloc); while (rgd) { - error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, - LM_FLAG_TRY, &al->al_rgd_gh); + rg_locked = 0; + + if (gfs2_glock_is_locked_by_me(rgd->rd_gl)) { + rg_locked = 1; + error = 0; + } else { + error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, + LM_FLAG_TRY, &al->al_rgd_gh); + } switch (error) { case 0: if (try_rgrp_fit(rgd, al)) goto out; if (rgd->rd_flags & GFS2_RDF_CHECK) inode = try_rgrp_unlink(rgd, last_unlinked); - gfs2_glock_dq_uninit(&al->al_rgd_gh); + if (!rg_locked) + gfs2_glock_dq_uninit(&al->al_rgd_gh); if (inode) return inode; rgd = recent_rgrp_next(rgd, 1); @@ -1098,15 +1106,23 @@ static struct inode *get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked) begin = rgd = forward_rgrp_get(sdp); for (;;) { - error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, flags, - &al->al_rgd_gh); + rg_locked = 0; + + if (gfs2_glock_is_locked_by_me(rgd->rd_gl)) { + rg_locked = 1; + error = 0; + } else { + error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, flags, + &al->al_rgd_gh); + } switch (error) { case 0: if (try_rgrp_fit(rgd, al)) goto out; if (rgd->rd_flags & GFS2_RDF_CHECK) inode = try_rgrp_unlink(rgd, last_unlinked); - gfs2_glock_dq_uninit(&al->al_rgd_gh); + if (!rg_locked) + gfs2_glock_dq_uninit(&al->al_rgd_gh); if (inode) return inode; break; @@ -1158,7 +1174,7 @@ out: int gfs2_inplace_reserve_i(struct gfs2_inode *ip, char *file, unsigned int line) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - struct gfs2_alloc *al = &ip->i_alloc; + struct gfs2_alloc *al = ip->i_alloc; struct inode *inode; int error = 0; u64 last_unlinked = NO_BLOCK; @@ -1204,7 +1220,7 @@ try_again: void gfs2_inplace_release(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - struct gfs2_alloc *al = &ip->i_alloc; + struct gfs2_alloc *al = ip->i_alloc; if (gfs2_assert_warn(sdp, al->al_alloced <= al->al_requested) == -1) fs_warn(sdp, "al_alloced = %u, al_requested = %u " @@ -1213,7 +1229,8 @@ void gfs2_inplace_release(struct gfs2_inode *ip) al->al_line); al->al_rgd = NULL; - gfs2_glock_dq_uninit(&al->al_rgd_gh); + if (al->al_rgd_gh.gh_gl) + gfs2_glock_dq_uninit(&al->al_rgd_gh); if (ip != GFS2_I(sdp->sd_rindex)) gfs2_glock_dq_uninit(&al->al_ri_gh); } @@ -1301,11 +1318,10 @@ static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal, /* The GFS2_BLKST_UNLINKED state doesn't apply to the clone bitmaps, so we must search the originals for that. */ if (old_state != GFS2_BLKST_UNLINKED && bi->bi_clone) - blk = gfs2_bitfit(rgd, bi->bi_clone + bi->bi_offset, + blk = gfs2_bitfit(bi->bi_clone + bi->bi_offset, bi->bi_len, goal, old_state); else - blk = gfs2_bitfit(rgd, - bi->bi_bh->b_data + bi->bi_offset, + blk = gfs2_bitfit(bi->bi_bh->b_data + bi->bi_offset, bi->bi_len, goal, old_state); if (blk != BFITNOENT) break; @@ -1394,7 +1410,7 @@ static struct gfs2_rgrpd *rgblk_free(struct gfs2_sbd *sdp, u64 bstart, u64 gfs2_alloc_data(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - struct gfs2_alloc *al = &ip->i_alloc; + struct gfs2_alloc *al = ip->i_alloc; struct gfs2_rgrpd *rgd = al->al_rgd; u32 goal, blk; u64 block; @@ -1439,7 +1455,7 @@ u64 gfs2_alloc_data(struct gfs2_inode *ip) u64 gfs2_alloc_meta(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - struct gfs2_alloc *al = &ip->i_alloc; + struct gfs2_alloc *al = ip->i_alloc; struct gfs2_rgrpd *rgd = al->al_rgd; u32 goal, blk; u64 block; @@ -1485,7 +1501,7 @@ u64 gfs2_alloc_meta(struct gfs2_inode *ip) u64 gfs2_alloc_di(struct gfs2_inode *dip, u64 *generation) { struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode); - struct gfs2_alloc *al = &dip->i_alloc; + struct gfs2_alloc *al = dip->i_alloc; struct gfs2_rgrpd *rgd = al->al_rgd; u32 blk; u64 block; diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h index b4c6adfc6f2..149bb161f4b 100644 --- a/fs/gfs2/rgrp.h +++ b/fs/gfs2/rgrp.h @@ -32,7 +32,9 @@ void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd); struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip); static inline void gfs2_alloc_put(struct gfs2_inode *ip) { - return; /* So we can see where ip->i_alloc is used */ + BUG_ON(ip->i_alloc == NULL); + kfree(ip->i_alloc); + ip->i_alloc = NULL; } int gfs2_inplace_reserve_i(struct gfs2_inode *ip, diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index dd3e737f528..ef0562c3bc7 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -51,13 +51,9 @@ void gfs2_tune_init(struct gfs2_tune *gt) { spin_lock_init(>->gt_spin); - gt->gt_ilimit = 100; - gt->gt_ilimit_tries = 3; - gt->gt_ilimit_min = 1; gt->gt_demote_secs = 300; gt->gt_incore_log_blocks = 1024; gt->gt_log_flush_secs = 60; - gt->gt_jindex_refresh_secs = 60; gt->gt_recoverd_secs = 60; gt->gt_logd_secs = 1; gt->gt_quotad_secs = 5; @@ -71,10 +67,8 @@ void gfs2_tune_init(struct gfs2_tune *gt) gt->gt_new_files_jdata = 0; gt->gt_new_files_directio = 0; gt->gt_max_readahead = 1 << 18; - gt->gt_lockdump_size = 131072; gt->gt_stall_secs = 600; gt->gt_complain_secs = 10; - gt->gt_reclaim_limit = 5000; gt->gt_statfs_quantum = 30; gt->gt_statfs_slow = 0; } @@ -393,6 +387,7 @@ int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh) if (!jd) break; + INIT_LIST_HEAD(&jd->extent_list); jd->jd_inode = gfs2_lookupi(sdp->sd_jindex, &name, 1, NULL); if (!jd->jd_inode || IS_ERR(jd->jd_inode)) { if (!jd->jd_inode) @@ -422,8 +417,9 @@ int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh) void gfs2_jindex_free(struct gfs2_sbd *sdp) { - struct list_head list; + struct list_head list, *head; struct gfs2_jdesc *jd; + struct gfs2_journal_extent *jext; spin_lock(&sdp->sd_jindex_spin); list_add(&list, &sdp->sd_jindex_list); @@ -433,6 +429,14 @@ void gfs2_jindex_free(struct gfs2_sbd *sdp) while (!list_empty(&list)) { jd = list_entry(list.next, struct gfs2_jdesc, jd_list); + head = &jd->extent_list; + while (!list_empty(head)) { + jext = list_entry(head->next, + struct gfs2_journal_extent, + extent_list); + list_del(&jext->extent_list); + kfree(jext); + } list_del(&jd->jd_list); iput(jd->jd_inode); kfree(jd); @@ -543,7 +547,6 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp) if (error) return error; - gfs2_meta_cache_flush(ip); j_gl->gl_ops->go_inval(j_gl, DIO_METADATA); error = gfs2_find_jhead(sdp->sd_jdesc, &head); @@ -686,9 +689,7 @@ void gfs2_statfs_change(struct gfs2_sbd *sdp, s64 total, s64 free, if (error) return; - mutex_lock(&sdp->sd_statfs_mutex); gfs2_trans_add_bh(l_ip->i_gl, l_bh, 1); - mutex_unlock(&sdp->sd_statfs_mutex); spin_lock(&sdp->sd_statfs_spin); l_sc->sc_total += total; @@ -736,9 +737,7 @@ int gfs2_statfs_sync(struct gfs2_sbd *sdp) if (error) goto out_bh2; - mutex_lock(&sdp->sd_statfs_mutex); gfs2_trans_add_bh(l_ip->i_gl, l_bh, 1); - mutex_unlock(&sdp->sd_statfs_mutex); spin_lock(&sdp->sd_statfs_spin); m_sc->sc_total += l_sc->sc_total; diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index 06e0b7768d9..eaa3b7b2f99 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -32,7 +32,8 @@ spinlock_t gfs2_sys_margs_lock; static ssize_t id_show(struct gfs2_sbd *sdp, char *buf) { - return snprintf(buf, PAGE_SIZE, "%s\n", sdp->sd_vfs->s_id); + return snprintf(buf, PAGE_SIZE, "%u:%u\n", + MAJOR(sdp->sd_vfs->s_dev), MINOR(sdp->sd_vfs->s_dev)); } static ssize_t fsname_show(struct gfs2_sbd *sdp, char *buf) @@ -221,9 +222,7 @@ static struct kobj_type gfs2_ktype = { .sysfs_ops = &gfs2_attr_ops, }; -static struct kset gfs2_kset = { - .ktype = &gfs2_ktype, -}; +static struct kset *gfs2_kset; /* * display struct lm_lockstruct fields @@ -427,13 +426,11 @@ TUNE_ATTR_2(name, name##_store) TUNE_ATTR(demote_secs, 0); TUNE_ATTR(incore_log_blocks, 0); TUNE_ATTR(log_flush_secs, 0); -TUNE_ATTR(jindex_refresh_secs, 0); TUNE_ATTR(quota_warn_period, 0); TUNE_ATTR(quota_quantum, 0); TUNE_ATTR(atime_quantum, 0); TUNE_ATTR(max_readahead, 0); TUNE_ATTR(complain_secs, 0); -TUNE_ATTR(reclaim_limit, 0); TUNE_ATTR(statfs_slow, 0); TUNE_ATTR(new_files_jdata, 0); TUNE_ATTR(new_files_directio, 0); @@ -450,13 +447,11 @@ static struct attribute *tune_attrs[] = { &tune_attr_demote_secs.attr, &tune_attr_incore_log_blocks.attr, &tune_attr_log_flush_secs.attr, - &tune_attr_jindex_refresh_secs.attr, &tune_attr_quota_warn_period.attr, &tune_attr_quota_quantum.attr, &tune_attr_atime_quantum.attr, &tune_attr_max_readahead.attr, &tune_attr_complain_secs.attr, - &tune_attr_reclaim_limit.attr, &tune_attr_statfs_slow.attr, &tune_attr_quota_simul_sync.attr, &tune_attr_quota_cache_secs.attr, @@ -495,14 +490,9 @@ int gfs2_sys_fs_add(struct gfs2_sbd *sdp) { int error; - sdp->sd_kobj.kset = &gfs2_kset; - sdp->sd_kobj.ktype = &gfs2_ktype; - - error = kobject_set_name(&sdp->sd_kobj, "%s", sdp->sd_table_name); - if (error) - goto fail; - - error = kobject_register(&sdp->sd_kobj); + sdp->sd_kobj.kset = gfs2_kset; + error = kobject_init_and_add(&sdp->sd_kobj, &gfs2_ktype, NULL, + "%s", sdp->sd_table_name); if (error) goto fail; @@ -522,6 +512,7 @@ int gfs2_sys_fs_add(struct gfs2_sbd *sdp) if (error) goto fail_args; + kobject_uevent(&sdp->sd_kobj, KOBJ_ADD); return 0; fail_args: @@ -531,7 +522,7 @@ fail_counters: fail_lockstruct: sysfs_remove_group(&sdp->sd_kobj, &lockstruct_group); fail_reg: - kobject_unregister(&sdp->sd_kobj); + kobject_put(&sdp->sd_kobj); fail: fs_err(sdp, "error %d adding sysfs files", error); return error; @@ -543,21 +534,22 @@ void gfs2_sys_fs_del(struct gfs2_sbd *sdp) sysfs_remove_group(&sdp->sd_kobj, &args_group); sysfs_remove_group(&sdp->sd_kobj, &counters_group); sysfs_remove_group(&sdp->sd_kobj, &lockstruct_group); - kobject_unregister(&sdp->sd_kobj); + kobject_put(&sdp->sd_kobj); } int gfs2_sys_init(void) { gfs2_sys_margs = NULL; spin_lock_init(&gfs2_sys_margs_lock); - kobject_set_name(&gfs2_kset.kobj, "gfs2"); - kobj_set_kset_s(&gfs2_kset, fs_subsys); - return kset_register(&gfs2_kset); + gfs2_kset = kset_create_and_add("gfs2", NULL, fs_kobj); + if (!gfs2_kset) + return -ENOMEM; + return 0; } void gfs2_sys_uninit(void) { kfree(gfs2_sys_margs); - kset_unregister(&gfs2_kset); + kset_unregister(gfs2_kset); } diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index 717983e2c2a..73e5d92a657 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -114,11 +114,6 @@ void gfs2_trans_end(struct gfs2_sbd *sdp) gfs2_log_flush(sdp, NULL); } -void gfs2_trans_add_gl(struct gfs2_glock *gl) -{ - lops_add(gl->gl_sbd, &gl->gl_le); -} - /** * gfs2_trans_add_bh - Add a to-be-modified buffer to the current transaction * @gl: the glock the buffer belongs to diff --git a/fs/gfs2/trans.h b/fs/gfs2/trans.h index 043d5f4b9c4..e826f0dab80 100644 --- a/fs/gfs2/trans.h +++ b/fs/gfs2/trans.h @@ -30,7 +30,6 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks, void gfs2_trans_end(struct gfs2_sbd *sdp); -void gfs2_trans_add_gl(struct gfs2_glock *gl); void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta); void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd); void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno); diff --git a/fs/hfs/bfind.c b/fs/hfs/bfind.c index f13f1494d4f..f8452a0eab5 100644 --- a/fs/hfs/bfind.c +++ b/fs/hfs/bfind.c @@ -52,6 +52,10 @@ int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd) rec = (e + b) / 2; len = hfs_brec_lenoff(bnode, rec, &off); keylen = hfs_brec_keylen(bnode, rec); + if (keylen == HFS_BAD_KEYLEN) { + res = -EINVAL; + goto done; + } hfs_bnode_read(bnode, fd->key, off, keylen); cmpval = bnode->tree->keycmp(fd->key, fd->search_key); if (!cmpval) { @@ -67,6 +71,10 @@ int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd) if (rec != e && e >= 0) { len = hfs_brec_lenoff(bnode, e, &off); keylen = hfs_brec_keylen(bnode, e); + if (keylen == HFS_BAD_KEYLEN) { + res = -EINVAL; + goto done; + } hfs_bnode_read(bnode, fd->key, off, keylen); } done: @@ -198,6 +206,10 @@ int hfs_brec_goto(struct hfs_find_data *fd, int cnt) len = hfs_brec_lenoff(bnode, fd->record, &off); keylen = hfs_brec_keylen(bnode, fd->record); + if (keylen == HFS_BAD_KEYLEN) { + res = -EINVAL; + goto out; + } fd->keyoffset = off; fd->keylength = keylen; fd->entryoffset = off + keylen; diff --git a/fs/hfs/brec.c b/fs/hfs/brec.c index 5c87cf4801f..8626ee375ea 100644 --- a/fs/hfs/brec.c +++ b/fs/hfs/brec.c @@ -44,10 +44,21 @@ u16 hfs_brec_keylen(struct hfs_bnode *node, u16 rec) recoff = hfs_bnode_read_u16(node, node->tree->node_size - (rec + 1) * 2); if (!recoff) return 0; - if (node->tree->attributes & HFS_TREE_BIGKEYS) + if (node->tree->attributes & HFS_TREE_BIGKEYS) { retval = hfs_bnode_read_u16(node, recoff) + 2; - else + if (retval > node->tree->max_key_len + 2) { + printk(KERN_ERR "hfs: keylen %d too large\n", + retval); + retval = HFS_BAD_KEYLEN; + } + } else { retval = (hfs_bnode_read_u8(node, recoff) | 1) + 1; + if (retval > node->tree->max_key_len + 1) { + printk(KERN_ERR "hfs: keylen %d too large\n", + retval); + retval = HFS_BAD_KEYLEN; + } + } } return retval; } diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c index 8a3a650abc8..110dd3515dc 100644 --- a/fs/hfs/btree.c +++ b/fs/hfs/btree.c @@ -61,7 +61,7 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp ke mapping = tree->inode->i_mapping; page = read_mapping_page(mapping, 0, NULL); if (IS_ERR(page)) - goto free_tree; + goto free_inode; /* Load the header */ head = (struct hfs_btree_header_rec *)(kmap(page) + sizeof(struct hfs_bnode_desc)); @@ -81,6 +81,17 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp ke goto fail_page; if (!tree->node_count) goto fail_page; + if ((id == HFS_EXT_CNID) && (tree->max_key_len != HFS_MAX_EXT_KEYLEN)) { + printk(KERN_ERR "hfs: invalid extent max_key_len %d\n", + tree->max_key_len); + goto fail_page; + } + if ((id == HFS_CAT_CNID) && (tree->max_key_len != HFS_MAX_CAT_KEYLEN)) { + printk(KERN_ERR "hfs: invalid catalog max_key_len %d\n", + tree->max_key_len); + goto fail_page; + } + tree->node_size_shift = ffs(size) - 1; tree->pages_per_bnode = (tree->node_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; @@ -88,11 +99,12 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp ke page_cache_release(page); return tree; - fail_page: - tree->inode->i_mapping->a_ops = &hfs_aops; +fail_page: page_cache_release(page); - free_tree: +free_inode: + tree->inode->i_mapping->a_ops = &hfs_aops; iput(tree->inode); +free_tree: kfree(tree); return NULL; } diff --git a/fs/hfs/hfs.h b/fs/hfs/hfs.h index 1445e3a56ed..c6aae61adfe 100644 --- a/fs/hfs/hfs.h +++ b/fs/hfs/hfs.h @@ -28,6 +28,8 @@ #define HFS_MAX_NAMELEN 128 #define HFS_MAX_VALENCE 32767U +#define HFS_BAD_KEYLEN 0xFF + /* Meanings of the drAtrb field of the MDB, * Reference: _Inside Macintosh: Files_ p. 2-61 */ @@ -167,6 +169,9 @@ typedef union hfs_btree_key { struct hfs_ext_key ext; } hfs_btree_key; +#define HFS_MAX_CAT_KEYLEN (sizeof(struct hfs_cat_key) - sizeof(u8)) +#define HFS_MAX_EXT_KEYLEN (sizeof(struct hfs_ext_key) - sizeof(u8)) + typedef union hfs_btree_key btree_key; struct hfs_extent { diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c index 08ff6c7028c..038ed743619 100644 --- a/fs/jbd/transaction.c +++ b/fs/jbd/transaction.c @@ -288,10 +288,12 @@ handle_t *journal_start(journal_t *journal, int nblocks) jbd_free_handle(handle); current->journal_info = NULL; handle = ERR_PTR(err); + goto out; } lock_acquire(&handle->h_lockdep_map, 0, 0, 0, 2, _THIS_IP_); +out: return handle; } diff --git a/fs/namei.c b/fs/namei.c index 3b993db26ce..73e2e665817 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1605,7 +1605,7 @@ int may_open(struct nameidata *nd, int acc_mode, int flag) if (S_ISLNK(inode->i_mode)) return -ELOOP; - if (S_ISDIR(inode->i_mode) && (flag & FMODE_WRITE)) + if (S_ISDIR(inode->i_mode) && (acc_mode & MAY_WRITE)) return -EISDIR; /* @@ -1620,7 +1620,7 @@ int may_open(struct nameidata *nd, int acc_mode, int flag) return -EACCES; flag &= ~O_TRUNC; - } else if (IS_RDONLY(inode) && (flag & FMODE_WRITE)) + } else if (IS_RDONLY(inode) && (acc_mode & MAY_WRITE)) return -EROFS; error = vfs_permission(nd, acc_mode); diff --git a/fs/namespace.c b/fs/namespace.c index 06083885b21..61bf376e29e 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -41,8 +41,8 @@ static struct kmem_cache *mnt_cache __read_mostly; static struct rw_semaphore namespace_sem; /* /sys/fs */ -decl_subsys(fs, NULL, NULL); -EXPORT_SYMBOL_GPL(fs_subsys); +struct kobject *fs_kobj; +EXPORT_SYMBOL_GPL(fs_kobj); static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry) { @@ -1861,10 +1861,9 @@ void __init mnt_init(void) if (err) printk(KERN_WARNING "%s: sysfs_init error: %d\n", __FUNCTION__, err); - err = subsystem_register(&fs_subsys); - if (err) - printk(KERN_WARNING "%s: subsystem_register error: %d\n", - __FUNCTION__, err); + fs_kobj = kobject_create_and_add("fs", NULL); + if (!fs_kobj) + printk(KERN_WARNING "%s: kobj create error\n", __FUNCTION__); init_rootfs(); init_mount_tree(); } diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index b35069a2aa9..bd1b9d663fb 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -115,6 +115,7 @@ struct nfs4_lock_state { #define NFS_LOCK_INITIALIZED 1 int ls_flags; struct nfs_seqid_counter ls_seqid; + struct rpc_sequence ls_sequence; struct nfs_unique_id ls_id; nfs4_stateid ls_stateid; atomic_t ls_count; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index f03d9d5f5ba..9e2e1c7291d 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -741,10 +741,10 @@ static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata) if (data->rpc_status == 0) { memcpy(data->o_res.stateid.data, data->c_res.stateid.data, sizeof(data->o_res.stateid.data)); + nfs_confirm_seqid(&data->owner->so_seqid, 0); renew_lease(data->o_res.server, data->timestamp); data->rpc_done = 1; } - nfs_confirm_seqid(&data->owner->so_seqid, data->rpc_status); nfs_increment_open_seqid(data->rpc_status, data->c_arg.seqid); } @@ -759,7 +759,6 @@ static void nfs4_open_confirm_release(void *calldata) /* In case of error, no cleanup! */ if (!data->rpc_done) goto out_free; - nfs_confirm_seqid(&data->owner->so_seqid, 0); state = nfs4_opendata_to_nfs4_state(data); if (!IS_ERR(state)) nfs4_close_state(&data->path, state, data->o_arg.open_flags); @@ -886,7 +885,6 @@ static void nfs4_open_release(void *calldata) /* In case we need an open_confirm, no cleanup! */ if (data->o_res.rflags & NFS4_OPEN_RESULT_CONFIRM) goto out_free; - nfs_confirm_seqid(&data->owner->so_seqid, 0); state = nfs4_opendata_to_nfs4_state(data); if (!IS_ERR(state)) nfs4_close_state(&data->path, state, data->o_arg.open_flags); @@ -3333,6 +3331,12 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl, p->arg.fh = NFS_FH(inode); p->arg.fl = &p->fl; + if (!(lsp->ls_seqid.flags & NFS_SEQID_CONFIRMED)) { + p->arg.open_seqid = nfs_alloc_seqid(&lsp->ls_state->owner->so_seqid); + if (p->arg.open_seqid == NULL) + goto out_free; + + } p->arg.lock_seqid = nfs_alloc_seqid(&lsp->ls_seqid); if (p->arg.lock_seqid == NULL) goto out_free; @@ -3345,6 +3349,8 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl, memcpy(&p->fl, fl, sizeof(p->fl)); return p; out_free: + if (p->arg.open_seqid != NULL) + nfs_free_seqid(p->arg.open_seqid); kfree(p); return NULL; } @@ -3361,23 +3367,23 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata) .rpc_cred = sp->so_cred, }; - if (nfs_wait_on_sequence(data->arg.lock_seqid, task) != 0) - return; dprintk("%s: begin!\n", __FUNCTION__); /* Do we need to do an open_to_lock_owner? */ if (!(data->arg.lock_seqid->sequence->flags & NFS_SEQID_CONFIRMED)) { - data->arg.open_seqid = nfs_alloc_seqid(&sp->so_seqid); - if (data->arg.open_seqid == NULL) { - data->rpc_status = -ENOMEM; - task->tk_action = NULL; - goto out; - } + if (nfs_wait_on_sequence(data->arg.open_seqid, task) != 0) + return; data->arg.open_stateid = &state->stateid; data->arg.new_lock_owner = 1; + /* Retest in case we raced... */ + if (!(data->arg.lock_seqid->sequence->flags & NFS_SEQID_CONFIRMED)) + goto do_rpc; } + if (nfs_wait_on_sequence(data->arg.lock_seqid, task) != 0) + return; + data->arg.new_lock_owner = 0; +do_rpc: data->timestamp = jiffies; rpc_call_setup(task, &msg, 0); -out: dprintk("%s: done!, ret = %d\n", __FUNCTION__, data->rpc_status); } @@ -3413,8 +3419,6 @@ static void nfs4_lock_release(void *calldata) struct nfs4_lockdata *data = calldata; dprintk("%s: begin!\n", __FUNCTION__); - if (data->arg.open_seqid != NULL) - nfs_free_seqid(data->arg.open_seqid); if (data->cancelled != 0) { struct rpc_task *task; task = nfs4_do_unlck(&data->fl, data->ctx, data->lsp, @@ -3424,6 +3428,8 @@ static void nfs4_lock_release(void *calldata) dprintk("%s: cancelling lock!\n", __FUNCTION__); } else nfs_free_seqid(data->arg.lock_seqid); + if (data->arg.open_seqid != NULL) + nfs_free_seqid(data->arg.open_seqid); nfs4_put_lock_state(data->lsp); put_nfs_open_context(data->ctx); kfree(data); diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c index 3ea352d82eb..5e2e4af1a0e 100644 --- a/fs/nfs/nfs4renewd.c +++ b/fs/nfs/nfs4renewd.c @@ -133,9 +133,7 @@ nfs4_renewd_prepare_shutdown(struct nfs_server *server) void nfs4_kill_renewd(struct nfs_client *clp) { - down_read(&clp->cl_sem); cancel_delayed_work_sync(&clp->cl_renewd); - up_read(&clp->cl_sem); } /* diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 23a9a36556b..5a39c6f78ac 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -509,7 +509,10 @@ static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, f lsp = kzalloc(sizeof(*lsp), GFP_KERNEL); if (lsp == NULL) return NULL; - lsp->ls_seqid.sequence = &state->owner->so_sequence; + rpc_init_wait_queue(&lsp->ls_sequence.wait, "lock_seqid_waitqueue"); + spin_lock_init(&lsp->ls_sequence.lock); + INIT_LIST_HEAD(&lsp->ls_sequence.list); + lsp->ls_seqid.sequence = &lsp->ls_sequence; atomic_set(&lsp->ls_count, 1); lsp->ls_owner = fl_owner; spin_lock(&clp->cl_lock); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index ea929207f27..0b0c72a072f 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1475,7 +1475,7 @@ static int nfs_xdev_get_sb(struct file_system_type *fs_type, int flags, error = PTR_ERR(mntroot); goto error_splat_super; } - if (mntroot->d_inode->i_op != server->nfs_client->rpc_ops->dir_inode_ops) { + if (mntroot->d_inode->i_op != NFS_SB(s)->nfs_client->rpc_ops->dir_inode_ops) { dput(mntroot); error = -ESTALE; goto error_splat_super; @@ -1826,6 +1826,11 @@ static int nfs4_xdev_get_sb(struct file_system_type *fs_type, int flags, error = PTR_ERR(mntroot); goto error_splat_super; } + if (mntroot->d_inode->i_op != NFS_SB(s)->nfs_client->rpc_ops->dir_inode_ops) { + dput(mntroot); + error = -ESTALE; + goto error_splat_super; + } s->s_flags |= MS_ACTIVE; mnt->mnt_sb = s; @@ -1900,6 +1905,11 @@ static int nfs4_referral_get_sb(struct file_system_type *fs_type, int flags, error = PTR_ERR(mntroot); goto error_splat_super; } + if (mntroot->d_inode->i_op != NFS_SB(s)->nfs_client->rpc_ops->dir_inode_ops) { + dput(mntroot); + error = -ESTALE; + goto error_splat_super; + } s->s_flags |= MS_ACTIVE; mnt->mnt_sb = s; diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 2d116d2298f..f917fd25858 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -388,8 +388,11 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, * Round the length of the data which was specified up to * the next multiple of XDR units and then compare that * against the length which was actually received. + * Note that when RPCSEC/GSS (for example) is used, the + * data buffer can be padded so dlen might be larger + * than required. It must never be smaller. */ - if (dlen != XDR_QUADLEN(len)*4) + if (dlen < XDR_QUADLEN(len)*4) return 0; if (args->count > max_blocksize) { diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index 986f9b32083..b86e3658a0a 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -313,8 +313,11 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, * Round the length of the data which was specified up to * the next multiple of XDR units and then compare that * against the length which was actually received. + * Note that when RPCSEC/GSS (for example) is used, the + * data buffer can be padded so dlen might be larger + * than required. It must never be smaller. */ - if (dlen != XDR_QUADLEN(len)*4) + if (dlen < XDR_QUADLEN(len)*4) return 0; rqstp->rq_vec[0].iov_base = (void*)p; diff --git a/fs/ocfs2/cluster/masklog.c b/fs/ocfs2/cluster/masklog.c index a4882c8df94..23c732f2752 100644 --- a/fs/ocfs2/cluster/masklog.c +++ b/fs/ocfs2/cluster/masklog.c @@ -146,7 +146,7 @@ static struct kset mlog_kset = { .kobj = {.ktype = &mlog_ktype}, }; -int mlog_sys_init(struct kset *o2cb_subsys) +int mlog_sys_init(struct kset *o2cb_kset) { int i = 0; @@ -157,7 +157,7 @@ int mlog_sys_init(struct kset *o2cb_subsys) mlog_attr_ptrs[i] = NULL; kobject_set_name(&mlog_kset.kobj, "logmask"); - kobj_set_kset_s(&mlog_kset, *o2cb_subsys); + mlog_kset.kobj.kset = o2cb_kset; return kset_register(&mlog_kset); } diff --git a/fs/ocfs2/cluster/sys.c b/fs/ocfs2/cluster/sys.c index 64f6f378fd0..a4b07730b2e 100644 --- a/fs/ocfs2/cluster/sys.c +++ b/fs/ocfs2/cluster/sys.c @@ -28,96 +28,55 @@ #include <linux/module.h> #include <linux/kobject.h> #include <linux/sysfs.h> +#include <linux/fs.h> #include "ocfs2_nodemanager.h" #include "masklog.h" #include "sys.h" -struct o2cb_attribute { - struct attribute attr; - ssize_t (*show)(char *buf); - ssize_t (*store)(const char *buf, size_t count); -}; - -#define O2CB_ATTR(_name, _mode, _show, _store) \ -struct o2cb_attribute o2cb_attr_##_name = __ATTR(_name, _mode, _show, _store) - -#define to_o2cb_attr(_attr) container_of(_attr, struct o2cb_attribute, attr) -static ssize_t o2cb_interface_revision_show(char *buf) +static ssize_t version_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) { return snprintf(buf, PAGE_SIZE, "%u\n", O2NM_API_VERSION); } - -static O2CB_ATTR(interface_revision, S_IFREG | S_IRUGO, o2cb_interface_revision_show, NULL); +static struct kobj_attribute attr_version = + __ATTR(interface_revision, S_IFREG | S_IRUGO, version_show, NULL); static struct attribute *o2cb_attrs[] = { - &o2cb_attr_interface_revision.attr, + &attr_version.attr, NULL, }; -static ssize_t -o2cb_show(struct kobject * kobj, struct attribute * attr, char * buffer); -static ssize_t -o2cb_store(struct kobject * kobj, struct attribute * attr, - const char * buffer, size_t count); -static struct sysfs_ops o2cb_sysfs_ops = { - .show = o2cb_show, - .store = o2cb_store, +static struct attribute_group o2cb_attr_group = { + .attrs = o2cb_attrs, }; -static struct kobj_type o2cb_subsys_type = { - .default_attrs = o2cb_attrs, - .sysfs_ops = &o2cb_sysfs_ops, -}; - -/* gives us o2cb_subsys */ -static decl_subsys(o2cb, NULL, NULL); - -static ssize_t -o2cb_show(struct kobject * kobj, struct attribute * attr, char * buffer) -{ - struct o2cb_attribute *o2cb_attr = to_o2cb_attr(attr); - struct kset *sbs = to_kset(kobj); - - BUG_ON(sbs != &o2cb_subsys); - - if (o2cb_attr->show) - return o2cb_attr->show(buffer); - return -EIO; -} - -static ssize_t -o2cb_store(struct kobject * kobj, struct attribute * attr, - const char * buffer, size_t count) -{ - struct o2cb_attribute *o2cb_attr = to_o2cb_attr(attr); - struct kset *sbs = to_kset(kobj); - - BUG_ON(sbs != &o2cb_subsys); - - if (o2cb_attr->store) - return o2cb_attr->store(buffer, count); - return -EIO; -} +static struct kset *o2cb_kset; void o2cb_sys_shutdown(void) { mlog_sys_shutdown(); - subsystem_unregister(&o2cb_subsys); + kset_unregister(o2cb_kset); } int o2cb_sys_init(void) { int ret; - o2cb_subsys.kobj.ktype = &o2cb_subsys_type; - ret = subsystem_register(&o2cb_subsys); + o2cb_kset = kset_create_and_add("o2cb", NULL, fs_kobj); + if (!o2cb_kset) + return -ENOMEM; + + ret = sysfs_create_group(&o2cb_kset->kobj, &o2cb_attr_group); if (ret) - return ret; + goto error; - ret = mlog_sys_init(&o2cb_subsys); + ret = mlog_sys_init(o2cb_kset); if (ret) - subsystem_unregister(&o2cb_subsys); + goto error; + return 0; +error: + kset_unregister(o2cb_kset); return ret; } diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c index d8817384008..6b7ff161894 100644 --- a/fs/openpromfs/inode.c +++ b/fs/openpromfs/inode.c @@ -131,7 +131,7 @@ static void property_stop(struct seq_file *f, void *v) /* Nothing to do */ } -static struct seq_operations property_op = { +static const struct seq_operations property_op = { .start = property_start, .next = property_next, .stop = property_stop, diff --git a/fs/partitions/check.c b/fs/partitions/check.c index 722e12e5acc..739da701ae7 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -195,96 +195,45 @@ check_partition(struct gendisk *hd, struct block_device *bdev) return ERR_PTR(res); } -/* - * sysfs bindings for partitions - */ - -struct part_attribute { - struct attribute attr; - ssize_t (*show)(struct hd_struct *,char *); - ssize_t (*store)(struct hd_struct *,const char *, size_t); -}; - -static ssize_t -part_attr_show(struct kobject * kobj, struct attribute * attr, char * page) +static ssize_t part_start_show(struct device *dev, + struct device_attribute *attr, char *buf) { - struct hd_struct * p = container_of(kobj,struct hd_struct,kobj); - struct part_attribute * part_attr = container_of(attr,struct part_attribute,attr); - ssize_t ret = 0; - if (part_attr->show) - ret = part_attr->show(p, page); - return ret; -} -static ssize_t -part_attr_store(struct kobject * kobj, struct attribute * attr, - const char *page, size_t count) -{ - struct hd_struct * p = container_of(kobj,struct hd_struct,kobj); - struct part_attribute * part_attr = container_of(attr,struct part_attribute,attr); - ssize_t ret = 0; + struct hd_struct *p = dev_to_part(dev); - if (part_attr->store) - ret = part_attr->store(p, page, count); - return ret; + return sprintf(buf, "%llu\n",(unsigned long long)p->start_sect); } -static struct sysfs_ops part_sysfs_ops = { - .show = part_attr_show, - .store = part_attr_store, -}; - -static ssize_t part_uevent_store(struct hd_struct * p, - const char *page, size_t count) +static ssize_t part_size_show(struct device *dev, + struct device_attribute *attr, char *buf) { - kobject_uevent(&p->kobj, KOBJ_ADD); - return count; + struct hd_struct *p = dev_to_part(dev); + return sprintf(buf, "%llu\n",(unsigned long long)p->nr_sects); } -static ssize_t part_dev_read(struct hd_struct * p, char *page) -{ - struct gendisk *disk = container_of(p->kobj.parent,struct gendisk,kobj); - dev_t dev = MKDEV(disk->major, disk->first_minor + p->partno); - return print_dev_t(page, dev); -} -static ssize_t part_start_read(struct hd_struct * p, char *page) -{ - return sprintf(page, "%llu\n",(unsigned long long)p->start_sect); -} -static ssize_t part_size_read(struct hd_struct * p, char *page) -{ - return sprintf(page, "%llu\n",(unsigned long long)p->nr_sects); -} -static ssize_t part_stat_read(struct hd_struct * p, char *page) + +static ssize_t part_stat_show(struct device *dev, + struct device_attribute *attr, char *buf) { - return sprintf(page, "%8u %8llu %8u %8llu\n", + struct hd_struct *p = dev_to_part(dev); + + return sprintf(buf, "%8u %8llu %8u %8llu\n", p->ios[0], (unsigned long long)p->sectors[0], p->ios[1], (unsigned long long)p->sectors[1]); } -static struct part_attribute part_attr_uevent = { - .attr = {.name = "uevent", .mode = S_IWUSR }, - .store = part_uevent_store -}; -static struct part_attribute part_attr_dev = { - .attr = {.name = "dev", .mode = S_IRUGO }, - .show = part_dev_read -}; -static struct part_attribute part_attr_start = { - .attr = {.name = "start", .mode = S_IRUGO }, - .show = part_start_read -}; -static struct part_attribute part_attr_size = { - .attr = {.name = "size", .mode = S_IRUGO }, - .show = part_size_read -}; -static struct part_attribute part_attr_stat = { - .attr = {.name = "stat", .mode = S_IRUGO }, - .show = part_stat_read -}; #ifdef CONFIG_FAIL_MAKE_REQUEST +static ssize_t part_fail_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct hd_struct *p = dev_to_part(dev); -static ssize_t part_fail_store(struct hd_struct * p, + return sprintf(buf, "%d\n", p->make_it_fail); +} + +static ssize_t part_fail_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) { + struct hd_struct *p = dev_to_part(dev); int i; if (count > 0 && sscanf(buf, "%d", &i) > 0) @@ -292,50 +241,53 @@ static ssize_t part_fail_store(struct hd_struct * p, return count; } -static ssize_t part_fail_read(struct hd_struct * p, char *page) -{ - return sprintf(page, "%d\n", p->make_it_fail); -} -static struct part_attribute part_attr_fail = { - .attr = {.name = "make-it-fail", .mode = S_IRUGO | S_IWUSR }, - .store = part_fail_store, - .show = part_fail_read -}; +#endif +static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL); +static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL); +static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL); +#ifdef CONFIG_FAIL_MAKE_REQUEST +static struct device_attribute dev_attr_fail = + __ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store); #endif -static struct attribute * default_attrs[] = { - &part_attr_uevent.attr, - &part_attr_dev.attr, - &part_attr_start.attr, - &part_attr_size.attr, - &part_attr_stat.attr, +static struct attribute *part_attrs[] = { + &dev_attr_start.attr, + &dev_attr_size.attr, + &dev_attr_stat.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST - &part_attr_fail.attr, + &dev_attr_fail.attr, #endif - NULL, + NULL }; -extern struct kset block_subsys; +static struct attribute_group part_attr_group = { + .attrs = part_attrs, +}; -static void part_release(struct kobject *kobj) +static struct attribute_group *part_attr_groups[] = { + &part_attr_group, + NULL +}; + +static void part_release(struct device *dev) { - struct hd_struct * p = container_of(kobj,struct hd_struct,kobj); + struct hd_struct *p = dev_to_part(dev); kfree(p); } -struct kobj_type ktype_part = { +struct device_type part_type = { + .name = "partition", + .groups = part_attr_groups, .release = part_release, - .default_attrs = default_attrs, - .sysfs_ops = &part_sysfs_ops, }; static inline void partition_sysfs_add_subdir(struct hd_struct *p) { struct kobject *k; - k = kobject_get(&p->kobj); - p->holder_dir = kobject_add_dir(k, "holders"); + k = kobject_get(&p->dev.kobj); + p->holder_dir = kobject_create_and_add("holders", k); kobject_put(k); } @@ -343,15 +295,16 @@ static inline void disk_sysfs_add_subdirs(struct gendisk *disk) { struct kobject *k; - k = kobject_get(&disk->kobj); - disk->holder_dir = kobject_add_dir(k, "holders"); - disk->slave_dir = kobject_add_dir(k, "slaves"); + k = kobject_get(&disk->dev.kobj); + disk->holder_dir = kobject_create_and_add("holders", k); + disk->slave_dir = kobject_create_and_add("slaves", k); kobject_put(k); } void delete_partition(struct gendisk *disk, int part) { struct hd_struct *p = disk->part[part-1]; + if (!p) return; if (!p->nr_sects) @@ -361,113 +314,55 @@ void delete_partition(struct gendisk *disk, int part) p->nr_sects = 0; p->ios[0] = p->ios[1] = 0; p->sectors[0] = p->sectors[1] = 0; - sysfs_remove_link(&p->kobj, "subsystem"); - kobject_unregister(p->holder_dir); - kobject_uevent(&p->kobj, KOBJ_REMOVE); - kobject_del(&p->kobj); - kobject_put(&p->kobj); + kobject_put(p->holder_dir); + device_del(&p->dev); + put_device(&p->dev); } void add_partition(struct gendisk *disk, int part, sector_t start, sector_t len, int flags) { struct hd_struct *p; + int err; p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) return; - + p->start_sect = start; p->nr_sects = len; p->partno = part; p->policy = disk->policy; - if (isdigit(disk->kobj.k_name[strlen(disk->kobj.k_name)-1])) - kobject_set_name(&p->kobj, "%sp%d", - kobject_name(&disk->kobj), part); + if (isdigit(disk->dev.bus_id[strlen(disk->dev.bus_id)-1])) + snprintf(p->dev.bus_id, BUS_ID_SIZE, + "%sp%d", disk->dev.bus_id, part); else - kobject_set_name(&p->kobj, "%s%d", - kobject_name(&disk->kobj),part); - p->kobj.parent = &disk->kobj; - p->kobj.ktype = &ktype_part; - kobject_init(&p->kobj); - kobject_add(&p->kobj); - if (!disk->part_uevent_suppress) - kobject_uevent(&p->kobj, KOBJ_ADD); - sysfs_create_link(&p->kobj, &block_subsys.kobj, "subsystem"); + snprintf(p->dev.bus_id, BUS_ID_SIZE, + "%s%d", disk->dev.bus_id, part); + + device_initialize(&p->dev); + p->dev.devt = MKDEV(disk->major, disk->first_minor + part); + p->dev.class = &block_class; + p->dev.type = &part_type; + p->dev.parent = &disk->dev; + disk->part[part-1] = p; + + /* delay uevent until 'holders' subdir is created */ + p->dev.uevent_suppress = 1; + device_add(&p->dev); + partition_sysfs_add_subdir(p); + p->dev.uevent_suppress = 0; if (flags & ADDPART_FLAG_WHOLEDISK) { static struct attribute addpartattr = { .name = "whole_disk", .mode = S_IRUSR | S_IRGRP | S_IROTH, }; - - sysfs_create_file(&p->kobj, &addpartattr); + err = sysfs_create_file(&p->dev.kobj, &addpartattr); } - partition_sysfs_add_subdir(p); - disk->part[part-1] = p; -} -static char *make_block_name(struct gendisk *disk) -{ - char *name; - static char *block_str = "block:"; - int size; - char *s; - - size = strlen(block_str) + strlen(disk->disk_name) + 1; - name = kmalloc(size, GFP_KERNEL); - if (!name) - return NULL; - strcpy(name, block_str); - strcat(name, disk->disk_name); - /* ewww... some of these buggers have / in name... */ - s = strchr(name, '/'); - if (s) - *s = '!'; - return name; -} - -static int disk_sysfs_symlinks(struct gendisk *disk) -{ - struct device *target = get_device(disk->driverfs_dev); - int err; - char *disk_name = NULL; - - if (target) { - disk_name = make_block_name(disk); - if (!disk_name) { - err = -ENOMEM; - goto err_out; - } - - err = sysfs_create_link(&disk->kobj, &target->kobj, "device"); - if (err) - goto err_out_disk_name; - - err = sysfs_create_link(&target->kobj, &disk->kobj, disk_name); - if (err) - goto err_out_dev_link; - } - - err = sysfs_create_link(&disk->kobj, &block_subsys.kobj, - "subsystem"); - if (err) - goto err_out_disk_name_lnk; - - kfree(disk_name); - - return 0; - -err_out_disk_name_lnk: - if (target) { - sysfs_remove_link(&target->kobj, disk_name); -err_out_dev_link: - sysfs_remove_link(&disk->kobj, "device"); -err_out_disk_name: - kfree(disk_name); -err_out: - put_device(target); - } - return err; + /* suppress uevent if the disk supresses it */ + if (!disk->dev.uevent_suppress) + kobject_uevent(&p->dev.kobj, KOBJ_ADD); } /* Not exported, helper to add_disk(). */ @@ -479,19 +374,29 @@ void register_disk(struct gendisk *disk) struct hd_struct *p; int err; - kobject_set_name(&disk->kobj, "%s", disk->disk_name); - /* ewww... some of these buggers have / in name... */ - s = strchr(disk->kobj.k_name, '/'); + disk->dev.parent = disk->driverfs_dev; + disk->dev.devt = MKDEV(disk->major, disk->first_minor); + + strlcpy(disk->dev.bus_id, disk->disk_name, KOBJ_NAME_LEN); + /* ewww... some of these buggers have / in the name... */ + s = strchr(disk->dev.bus_id, '/'); if (s) *s = '!'; - if ((err = kobject_add(&disk->kobj))) + + /* delay uevents, until we scanned partition table */ + disk->dev.uevent_suppress = 1; + + if (device_add(&disk->dev)) return; - err = disk_sysfs_symlinks(disk); +#ifndef CONFIG_SYSFS_DEPRECATED + err = sysfs_create_link(block_depr, &disk->dev.kobj, + kobject_name(&disk->dev.kobj)); if (err) { - kobject_del(&disk->kobj); + device_del(&disk->dev); return; } - disk_sysfs_add_subdirs(disk); +#endif + disk_sysfs_add_subdirs(disk); /* No minors to use for partitions */ if (disk->minors == 1) @@ -505,25 +410,23 @@ void register_disk(struct gendisk *disk) if (!bdev) goto exit; - /* scan partition table, but suppress uevents */ bdev->bd_invalidated = 1; - disk->part_uevent_suppress = 1; err = blkdev_get(bdev, FMODE_READ, 0); - disk->part_uevent_suppress = 0; if (err < 0) goto exit; blkdev_put(bdev); exit: - /* announce disk after possible partitions are already created */ - kobject_uevent(&disk->kobj, KOBJ_ADD); + /* announce disk after possible partitions are created */ + disk->dev.uevent_suppress = 0; + kobject_uevent(&disk->dev.kobj, KOBJ_ADD); /* announce possible partitions */ for (i = 1; i < disk->minors; i++) { p = disk->part[i-1]; if (!p || !p->nr_sects) continue; - kobject_uevent(&p->kobj, KOBJ_ADD); + kobject_uevent(&p->dev.kobj, KOBJ_ADD); } } @@ -602,19 +505,11 @@ void del_gendisk(struct gendisk *disk) disk_stat_set_all(disk, 0); disk->stamp = 0; - kobject_uevent(&disk->kobj, KOBJ_REMOVE); - kobject_unregister(disk->holder_dir); - kobject_unregister(disk->slave_dir); - if (disk->driverfs_dev) { - char *disk_name = make_block_name(disk); - sysfs_remove_link(&disk->kobj, "device"); - if (disk_name) { - sysfs_remove_link(&disk->driverfs_dev->kobj, disk_name); - kfree(disk_name); - } - put_device(disk->driverfs_dev); - disk->driverfs_dev = NULL; - } - sysfs_remove_link(&disk->kobj, "subsystem"); - kobject_del(&disk->kobj); + kobject_put(disk->holder_dir); + kobject_put(disk->slave_dir); + disk->driverfs_dev = NULL; +#ifndef CONFIG_SYSFS_DEPRECATED + sysfs_remove_link(block_depr, disk->dev.bus_id); +#endif + device_del(&disk->dev); } diff --git a/fs/proc/array.c b/fs/proc/array.c index 65c62e1bfd6..eb97f2897e2 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -169,7 +169,7 @@ static inline char *task_state(struct task_struct *p, char *buffer) ppid = pid_alive(p) ? task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0; tpid = pid_alive(p) && p->ptrace ? - task_ppid_nr_ns(rcu_dereference(p->parent), ns) : 0; + task_pid_nr_ns(rcu_dereference(p->parent), ns) : 0; buffer += sprintf(buffer, "State:\t%s\n" "Tgid:\t%d\n" @@ -464,8 +464,8 @@ static int do_task_stat(struct task_struct *task, char *buffer, int whole) } sid = task_session_nr_ns(task, ns); + ppid = task_tgid_nr_ns(task->real_parent, ns); pgid = task_pgrp_nr_ns(task, ns); - ppid = task_ppid_nr_ns(task, ns); unlock_task_sighand(task, &flags); } diff --git a/fs/read_write.c b/fs/read_write.c index ea1f94cc722..c4d3d17923f 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -197,25 +197,27 @@ int rw_verify_area(int read_write, struct file *file, loff_t *ppos, size_t count { struct inode *inode; loff_t pos; + int retval = -EINVAL; inode = file->f_path.dentry->d_inode; if (unlikely((ssize_t) count < 0)) - goto Einval; + return retval; pos = *ppos; if (unlikely((pos < 0) || (loff_t) (pos + count) < 0)) - goto Einval; + return retval; if (unlikely(inode->i_flock && mandatory_lock(inode))) { - int retval = locks_mandatory_area( + retval = locks_mandatory_area( read_write == READ ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE, inode, file, pos, count); if (retval < 0) return retval; } + retval = security_file_permission(file, + read_write == READ ? MAY_READ : MAY_WRITE); + if (retval) + return retval; return count > MAX_RW_COUNT ? MAX_RW_COUNT : count; - -Einval: - return -EINVAL; } static void wait_on_retry_sync_kiocb(struct kiocb *iocb) @@ -267,18 +269,15 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) ret = rw_verify_area(READ, file, pos, count); if (ret >= 0) { count = ret; - ret = security_file_permission (file, MAY_READ); - if (!ret) { - if (file->f_op->read) - ret = file->f_op->read(file, buf, count, pos); - else - ret = do_sync_read(file, buf, count, pos); - if (ret > 0) { - fsnotify_access(file->f_path.dentry); - add_rchar(current, ret); - } - inc_syscr(current); + if (file->f_op->read) + ret = file->f_op->read(file, buf, count, pos); + else + ret = do_sync_read(file, buf, count, pos); + if (ret > 0) { + fsnotify_access(file->f_path.dentry); + add_rchar(current, ret); } + inc_syscr(current); } return ret; @@ -325,18 +324,15 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_ ret = rw_verify_area(WRITE, file, pos, count); if (ret >= 0) { count = ret; - ret = security_file_permission (file, MAY_WRITE); - if (!ret) { - if (file->f_op->write) - ret = file->f_op->write(file, buf, count, pos); - else - ret = do_sync_write(file, buf, count, pos); - if (ret > 0) { - fsnotify_modify(file->f_path.dentry); - add_wchar(current, ret); - } - inc_syscw(current); + if (file->f_op->write) + ret = file->f_op->write(file, buf, count, pos); + else + ret = do_sync_write(file, buf, count, pos); + if (ret > 0) { + fsnotify_modify(file->f_path.dentry); + add_wchar(current, ret); } + inc_syscw(current); } return ret; @@ -603,9 +599,6 @@ static ssize_t do_readv_writev(int type, struct file *file, ret = rw_verify_area(type, file, pos, tot_len); if (ret < 0) goto out; - ret = security_file_permission(file, type == READ ? MAY_READ : MAY_WRITE); - if (ret) - goto out; fnv = NULL; if (type == READ) { @@ -737,10 +730,6 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, goto fput_in; count = retval; - retval = security_file_permission (in_file, MAY_READ); - if (retval) - goto fput_in; - /* * Get output file, and verify that it is ok.. */ @@ -759,10 +748,6 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, goto fput_out; count = retval; - retval = security_file_permission (out_file, MAY_WRITE); - if (retval) - goto fput_out; - if (!max) max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes); diff --git a/fs/splice.c b/fs/splice.c index 6bdcb6107bc..56b802bfbfa 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -908,10 +908,6 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, if (unlikely(ret < 0)) return ret; - ret = security_file_permission(out, MAY_WRITE); - if (unlikely(ret < 0)) - return ret; - return out->f_op->splice_write(pipe, out, ppos, len, flags); } @@ -934,10 +930,6 @@ static long do_splice_to(struct file *in, loff_t *ppos, if (unlikely(ret < 0)) return ret; - ret = security_file_permission(in, MAY_READ); - if (unlikely(ret < 0)) - return ret; - return in->f_op->splice_read(in, ppos, pipe, len, flags); } diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index 337162935d2..4948d9bc405 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -440,7 +440,7 @@ int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd) /** * sysfs_remove_one - remove sysfs_dirent from parent * @acxt: addrm context to use - * @sd: sysfs_dirent to be added + * @sd: sysfs_dirent to be removed * * Mark @sd removed and drop nlink of parent inode if @sd is a * directory. @sd is unlinked from the children list. @@ -678,8 +678,10 @@ static struct dentry * sysfs_lookup(struct inode *dir, struct dentry *dentry, sd = sysfs_find_dirent(parent_sd, dentry->d_name.name); /* no such entry */ - if (!sd) + if (!sd) { + ret = ERR_PTR(-ENOENT); goto out_unlock; + } /* attach dentry and inode */ inode = sysfs_get_inode(sd); @@ -781,6 +783,7 @@ int sysfs_rename_dir(struct kobject * kobj, const char *new_name) old_dentry = sysfs_get_dentry(sd); if (IS_ERR(old_dentry)) { error = PTR_ERR(old_dentry); + old_dentry = NULL; goto out; } @@ -848,6 +851,7 @@ int sysfs_move_dir(struct kobject *kobj, struct kobject *new_parent_kobj) old_dentry = sysfs_get_dentry(sd); if (IS_ERR(old_dentry)) { error = PTR_ERR(old_dentry); + old_dentry = NULL; goto out; } old_parent = old_dentry->d_parent; @@ -855,6 +859,7 @@ int sysfs_move_dir(struct kobject *kobj, struct kobject *new_parent_kobj) new_parent = sysfs_get_dentry(new_parent_sd); if (IS_ERR(new_parent)) { error = PTR_ERR(new_parent); + new_parent = NULL; goto out; } @@ -878,7 +883,6 @@ again: error = 0; d_add(new_dentry, NULL); d_move(old_dentry, new_dentry); - dput(new_dentry); /* Remove from old parent's list and insert into new parent's list. */ sysfs_unlink_sibling(sd); diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 4045bdcc4b3..8acf82bba44 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -20,43 +20,6 @@ #include "sysfs.h" -#define to_sattr(a) container_of(a,struct subsys_attribute, attr) - -/* - * Subsystem file operations. - * These operations allow subsystems to have files that can be - * read/written. - */ -static ssize_t -subsys_attr_show(struct kobject * kobj, struct attribute * attr, char * page) -{ - struct kset *kset = to_kset(kobj); - struct subsys_attribute * sattr = to_sattr(attr); - ssize_t ret = -EIO; - - if (sattr->show) - ret = sattr->show(kset, page); - return ret; -} - -static ssize_t -subsys_attr_store(struct kobject * kobj, struct attribute * attr, - const char * page, size_t count) -{ - struct kset *kset = to_kset(kobj); - struct subsys_attribute * sattr = to_sattr(attr); - ssize_t ret = -EIO; - - if (sattr->store) - ret = sattr->store(kset, page, count); - return ret; -} - -static struct sysfs_ops subsys_sysfs_ops = { - .show = subsys_attr_show, - .store = subsys_attr_store, -}; - /* * There's one sysfs_buffer for each open file and one * sysfs_open_dirent for each sysfs_dirent with one or more open @@ -66,7 +29,7 @@ static struct sysfs_ops subsys_sysfs_ops = { * sysfs_dirent->s_attr.open points to sysfs_open_dirent. s_attr.open * is protected by sysfs_open_dirent_lock. */ -static spinlock_t sysfs_open_dirent_lock = SPIN_LOCK_UNLOCKED; +static DEFINE_SPINLOCK(sysfs_open_dirent_lock); struct sysfs_open_dirent { atomic_t refcnt; @@ -354,31 +317,23 @@ static int sysfs_open_file(struct inode *inode, struct file *file) { struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; struct kobject *kobj = attr_sd->s_parent->s_dir.kobj; - struct sysfs_buffer * buffer; - struct sysfs_ops * ops = NULL; - int error; + struct sysfs_buffer *buffer; + struct sysfs_ops *ops; + int error = -EACCES; /* need attr_sd for attr and ops, its parent for kobj */ if (!sysfs_get_active_two(attr_sd)) return -ENODEV; - /* if the kobject has no ktype, then we assume that it is a subsystem - * itself, and use ops for it. - */ - if (kobj->kset && kobj->kset->ktype) - ops = kobj->kset->ktype->sysfs_ops; - else if (kobj->ktype) + /* every kobject with an attribute needs a ktype assigned */ + if (kobj->ktype && kobj->ktype->sysfs_ops) ops = kobj->ktype->sysfs_ops; - else - ops = &subsys_sysfs_ops; - - error = -EACCES; - - /* No sysfs operations, either from having no subsystem, - * or the subsystem have no operations. - */ - if (!ops) + else { + printk(KERN_ERR "missing sysfs attribute operations for " + "kobject: %s\n", kobject_name(kobj)); + WARN_ON(1); goto err_out; + } /* File needs write support. * The inode's perms must say it's ok, diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c index 3eac20c63c4..5f66c446615 100644 --- a/fs/sysfs/symlink.c +++ b/fs/sysfs/symlink.c @@ -19,39 +19,6 @@ #include "sysfs.h" -static int object_depth(struct sysfs_dirent *sd) -{ - int depth = 0; - - for (; sd->s_parent; sd = sd->s_parent) - depth++; - - return depth; -} - -static int object_path_length(struct sysfs_dirent * sd) -{ - int length = 1; - - for (; sd->s_parent; sd = sd->s_parent) - length += strlen(sd->s_name) + 1; - - return length; -} - -static void fill_object_path(struct sysfs_dirent *sd, char *buffer, int length) -{ - --length; - for (; sd->s_parent; sd = sd->s_parent) { - int cur = strlen(sd->s_name); - - /* back up enough to print this bus id with '/' */ - length -= cur; - strncpy(buffer + length, sd->s_name, cur); - *(buffer + --length) = '/'; - } -} - /** * sysfs_create_link - create symlink between two objects. * @kobj: object whose directory we're creating the link in. @@ -112,7 +79,6 @@ int sysfs_create_link(struct kobject * kobj, struct kobject * target, const char return error; } - /** * sysfs_remove_link - remove symlink in object's directory. * @kobj: object we're acting for. @@ -124,24 +90,54 @@ void sysfs_remove_link(struct kobject * kobj, const char * name) sysfs_hash_and_remove(kobj->sd, name); } -static int sysfs_get_target_path(struct sysfs_dirent * parent_sd, - struct sysfs_dirent * target_sd, char *path) +static int sysfs_get_target_path(struct sysfs_dirent *parent_sd, + struct sysfs_dirent *target_sd, char *path) { - char * s; - int depth, size; + struct sysfs_dirent *base, *sd; + char *s = path; + int len = 0; + + /* go up to the root, stop at the base */ + base = parent_sd; + while (base->s_parent) { + sd = target_sd->s_parent; + while (sd->s_parent && base != sd) + sd = sd->s_parent; + + if (base == sd) + break; + + strcpy(s, "../"); + s += 3; + base = base->s_parent; + } + + /* determine end of target string for reverse fillup */ + sd = target_sd; + while (sd->s_parent && sd != base) { + len += strlen(sd->s_name) + 1; + sd = sd->s_parent; + } - depth = object_depth(parent_sd); - size = object_path_length(target_sd) + depth * 3 - 1; - if (size > PATH_MAX) + /* check limits */ + if (len < 2) + return -EINVAL; + len--; + if ((s - path) + len > PATH_MAX) return -ENAMETOOLONG; - pr_debug("%s: depth = %d, size = %d\n", __FUNCTION__, depth, size); + /* reverse fillup of target string from target to base */ + sd = target_sd; + while (sd->s_parent && sd != base) { + int slen = strlen(sd->s_name); - for (s = path; depth--; s += 3) - strcpy(s,"../"); + len -= slen; + strncpy(s + len, sd->s_name, slen); + if (len) + s[--len] = '/'; - fill_object_path(target_sd, path, size); - pr_debug("%s: path = '%s'\n", __FUNCTION__, path); + sd = sd->s_parent; + } return 0; } diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c index 4847eb83fc1..21a1c2b1c5f 100644 --- a/fs/xfs/linux-2.6/xfs_file.c +++ b/fs/xfs/linux-2.6/xfs_file.c @@ -261,9 +261,9 @@ xfs_file_readdir( #else struct hack_dirent { - int namlen; - loff_t offset; u64 ino; + loff_t offset; + int namlen; unsigned int d_type; char name[]; }; @@ -285,8 +285,10 @@ xfs_hack_filldir( { struct hack_callback *buf = __buf; struct hack_dirent *de = (struct hack_dirent *)(buf->dirent + buf->used); + unsigned int reclen; - if (buf->used + sizeof(struct hack_dirent) + namlen > buf->len) + reclen = ALIGN(sizeof(struct hack_dirent) + namlen, sizeof(u64)); + if (buf->used + reclen > buf->len) return -EINVAL; de->namlen = namlen; @@ -294,7 +296,7 @@ xfs_hack_filldir( de->ino = ino; de->d_type = d_type; memcpy(de->name, name, namlen); - buf->used += sizeof(struct hack_dirent) + namlen; + buf->used += reclen; return 0; } @@ -334,7 +336,8 @@ xfs_file_readdir( offset = filp->f_pos; while (!eof) { - int reclen; + unsigned int reclen; + start_offset = offset; buf.used = 0; @@ -355,7 +358,8 @@ xfs_file_readdir( goto done; } - reclen = sizeof(struct hack_dirent) + de->namlen; + reclen = ALIGN(sizeof(struct hack_dirent) + de->namlen, + sizeof(u64)); size -= reclen; de = (struct hack_dirent *)((char *)de + reclen); curr_offset = de->offset /* & 0x7fffffff */; |