diff options
Diffstat (limited to 'fs')
-rw-r--r-- | fs/Kconfig | 2 | ||||
-rw-r--r-- | fs/configfs/configfs_internal.h | 11 | ||||
-rw-r--r-- | fs/configfs/dir.c | 36 | ||||
-rw-r--r-- | fs/configfs/file.c | 19 | ||||
-rw-r--r-- | fs/configfs/inode.c | 120 | ||||
-rw-r--r-- | fs/configfs/mount.c | 28 | ||||
-rw-r--r-- | fs/configfs/symlink.c | 4 | ||||
-rw-r--r-- | fs/ocfs2/buffer_head_io.c | 10 | ||||
-rw-r--r-- | fs/ocfs2/cluster/heartbeat.c | 5 | ||||
-rw-r--r-- | fs/ocfs2/cluster/tcp.c | 16 | ||||
-rw-r--r-- | fs/ocfs2/dlm/dlmcommon.h | 1 | ||||
-rw-r--r-- | fs/ocfs2/dlm/dlmdomain.c | 18 | ||||
-rw-r--r-- | fs/ocfs2/dlm/dlmmaster.c | 24 | ||||
-rw-r--r-- | fs/ocfs2/dlm/dlmrecovery.c | 250 | ||||
-rw-r--r-- | fs/ocfs2/dlm/dlmunlock.c | 13 | ||||
-rw-r--r-- | fs/ocfs2/dlm/userdlm.c | 2 | ||||
-rw-r--r-- | fs/ocfs2/extent_map.c | 12 | ||||
-rw-r--r-- | fs/ocfs2/file.c | 10 | ||||
-rw-r--r-- | fs/ocfs2/inode.c | 6 | ||||
-rw-r--r-- | fs/ocfs2/inode.h | 4 | ||||
-rw-r--r-- | fs/ocfs2/journal.c | 32 | ||||
-rw-r--r-- | fs/ocfs2/ocfs2.h | 3 | ||||
-rw-r--r-- | fs/ocfs2/super.c | 11 | ||||
-rw-r--r-- | fs/ocfs2/sysfile.c | 6 | ||||
-rw-r--r-- | fs/ocfs2/uptodate.c | 12 | ||||
-rw-r--r-- | fs/ocfs2/uptodate.h | 2 |
26 files changed, 501 insertions, 156 deletions
diff --git a/fs/Kconfig b/fs/Kconfig index 93b5dc4082f..e9749b0eecd 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -883,8 +883,6 @@ config CONFIGFS_FS Both sysfs and configfs can and should exist together on the same system. One is not a replacement for the other. - If unsure, say N. - endmenu menu "Miscellaneous filesystems" diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h index 8899d9c5f6b..f70e46951b3 100644 --- a/fs/configfs/configfs_internal.h +++ b/fs/configfs/configfs_internal.h @@ -36,6 +36,7 @@ struct configfs_dirent { int s_type; umode_t s_mode; struct dentry * s_dentry; + struct iattr * s_iattr; }; #define CONFIGFS_ROOT 0x0001 @@ -48,10 +49,11 @@ struct configfs_dirent { #define CONFIGFS_NOT_PINNED (CONFIGFS_ITEM_ATTR) extern struct vfsmount * configfs_mount; +extern kmem_cache_t *configfs_dir_cachep; extern int configfs_is_root(struct config_item *item); -extern struct inode * configfs_new_inode(mode_t mode); +extern struct inode * configfs_new_inode(mode_t mode, struct configfs_dirent *); extern int configfs_create(struct dentry *, int mode, int (*init)(struct inode *)); extern int configfs_create_file(struct config_item *, const struct configfs_attribute *); @@ -63,6 +65,7 @@ extern void configfs_hash_and_remove(struct dentry * dir, const char * name); extern const unsigned char * configfs_get_name(struct configfs_dirent *sd); extern void configfs_drop_dentry(struct configfs_dirent *sd, struct dentry *parent); +extern int configfs_setattr(struct dentry *dentry, struct iattr *iattr); extern int configfs_pin_fs(void); extern void configfs_release_fs(void); @@ -120,8 +123,10 @@ static inline struct config_item *configfs_get_config_item(struct dentry *dentry static inline void release_configfs_dirent(struct configfs_dirent * sd) { - if (!(sd->s_type & CONFIGFS_ROOT)) - kfree(sd); + if (!(sd->s_type & CONFIGFS_ROOT)) { + kfree(sd->s_iattr); + kmem_cache_free(configfs_dir_cachep, sd); + } } static inline struct configfs_dirent * configfs_get(struct configfs_dirent * sd) diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index b668ec61527..ca60e3abef4 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -72,7 +72,7 @@ static struct configfs_dirent *configfs_new_dirent(struct configfs_dirent * pare { struct configfs_dirent * sd; - sd = kmalloc(sizeof(*sd), GFP_KERNEL); + sd = kmem_cache_alloc(configfs_dir_cachep, GFP_KERNEL); if (!sd) return NULL; @@ -136,13 +136,19 @@ static int create_dir(struct config_item * k, struct dentry * p, int error; umode_t mode = S_IFDIR| S_IRWXU | S_IRUGO | S_IXUGO; - error = configfs_create(d, mode, init_dir); + error = configfs_make_dirent(p->d_fsdata, d, k, mode, + CONFIGFS_DIR); if (!error) { - error = configfs_make_dirent(p->d_fsdata, d, k, mode, - CONFIGFS_DIR); + error = configfs_create(d, mode, init_dir); if (!error) { p->d_inode->i_nlink++; (d)->d_op = &configfs_dentry_ops; + } else { + struct configfs_dirent *sd = d->d_fsdata; + if (sd) { + list_del_init(&sd->s_sibling); + configfs_put(sd); + } } } return error; @@ -182,12 +188,19 @@ int configfs_create_link(struct configfs_symlink *sl, int err = 0; umode_t mode = S_IFLNK | S_IRWXUGO; - err = configfs_create(dentry, mode, init_symlink); + err = configfs_make_dirent(parent->d_fsdata, dentry, sl, mode, + CONFIGFS_ITEM_LINK); if (!err) { - err = configfs_make_dirent(parent->d_fsdata, dentry, sl, - mode, CONFIGFS_ITEM_LINK); + err = configfs_create(dentry, mode, init_symlink); if (!err) dentry->d_op = &configfs_dentry_ops; + else { + struct configfs_dirent *sd = dentry->d_fsdata; + if (sd) { + list_del_init(&sd->s_sibling); + configfs_put(sd); + } + } } return err; } @@ -241,13 +254,15 @@ static int configfs_attach_attr(struct configfs_dirent * sd, struct dentry * den struct configfs_attribute * attr = sd->s_element; int error; + dentry->d_fsdata = configfs_get(sd); + sd->s_dentry = dentry; error = configfs_create(dentry, (attr->ca_mode & S_IALLUGO) | S_IFREG, init_file); - if (error) + if (error) { + configfs_put(sd); return error; + } dentry->d_op = &configfs_dentry_ops; - dentry->d_fsdata = configfs_get(sd); - sd->s_dentry = dentry; d_rehash(dentry); return 0; @@ -839,6 +854,7 @@ struct inode_operations configfs_dir_inode_operations = { .symlink = configfs_symlink, .unlink = configfs_unlink, .lookup = configfs_lookup, + .setattr = configfs_setattr, }; #if 0 diff --git a/fs/configfs/file.c b/fs/configfs/file.c index c26cd61f13a..3921920d871 100644 --- a/fs/configfs/file.c +++ b/fs/configfs/file.c @@ -26,7 +26,6 @@ #include <linux/fs.h> #include <linux/module.h> -#include <linux/dnotify.h> #include <linux/slab.h> #include <asm/uaccess.h> #include <asm/semaphore.h> @@ -150,7 +149,7 @@ out: /** * fill_write_buffer - copy buffer from userspace. * @buffer: data buffer for file. - * @userbuf: data from user. + * @buf: data from user. * @count: number of bytes in @userbuf. * * Allocate @buffer->page if it hasn't been already, then @@ -177,8 +176,9 @@ fill_write_buffer(struct configfs_buffer * buffer, const char __user * buf, size /** * flush_write_buffer - push buffer to config_item. - * @file: file pointer. + * @dentry: dentry to the attribute * @buffer: data buffer for file. + * @count: number of bytes * * Get the correct pointers for the config_item and the attribute we're * dealing with, then call the store() method for the attribute, @@ -217,15 +217,16 @@ static ssize_t configfs_write_file(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct configfs_buffer * buffer = file->private_data; + ssize_t len; down(&buffer->sem); - count = fill_write_buffer(buffer,buf,count); - if (count > 0) - count = flush_write_buffer(file->f_dentry,buffer,count); - if (count > 0) - *ppos += count; + len = fill_write_buffer(buffer, buf, count); + if (len > 0) + len = flush_write_buffer(file->f_dentry, buffer, count); + if (len > 0) + *ppos += len; up(&buffer->sem); - return count; + return len; } static int check_perm(struct inode * inode, struct file * file) diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index 6577c588de9..c153bd9534c 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -31,6 +31,7 @@ #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/backing-dev.h> +#include <linux/capability.h> #include <linux/configfs.h> #include "configfs_internal.h" @@ -48,18 +49,107 @@ static struct backing_dev_info configfs_backing_dev_info = { .capabilities = BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK, }; -struct inode * configfs_new_inode(mode_t mode) +static struct inode_operations configfs_inode_operations ={ + .setattr = configfs_setattr, +}; + +int configfs_setattr(struct dentry * dentry, struct iattr * iattr) +{ + struct inode * inode = dentry->d_inode; + struct configfs_dirent * sd = dentry->d_fsdata; + struct iattr * sd_iattr; + unsigned int ia_valid = iattr->ia_valid; + int error; + + if (!sd) + return -EINVAL; + + sd_iattr = sd->s_iattr; + + error = inode_change_ok(inode, iattr); + if (error) + return error; + + error = inode_setattr(inode, iattr); + if (error) + return error; + + if (!sd_iattr) { + /* setting attributes for the first time, allocate now */ + sd_iattr = kmalloc(sizeof(struct iattr), GFP_KERNEL); + if (!sd_iattr) + return -ENOMEM; + /* assign default attributes */ + memset(sd_iattr, 0, sizeof(struct iattr)); + sd_iattr->ia_mode = sd->s_mode; + sd_iattr->ia_uid = 0; + sd_iattr->ia_gid = 0; + sd_iattr->ia_atime = sd_iattr->ia_mtime = sd_iattr->ia_ctime = CURRENT_TIME; + sd->s_iattr = sd_iattr; + } + + /* attributes were changed atleast once in past */ + + if (ia_valid & ATTR_UID) + sd_iattr->ia_uid = iattr->ia_uid; + if (ia_valid & ATTR_GID) + sd_iattr->ia_gid = iattr->ia_gid; + if (ia_valid & ATTR_ATIME) + sd_iattr->ia_atime = timespec_trunc(iattr->ia_atime, + inode->i_sb->s_time_gran); + if (ia_valid & ATTR_MTIME) + sd_iattr->ia_mtime = timespec_trunc(iattr->ia_mtime, + inode->i_sb->s_time_gran); + if (ia_valid & ATTR_CTIME) + sd_iattr->ia_ctime = timespec_trunc(iattr->ia_ctime, + inode->i_sb->s_time_gran); + if (ia_valid & ATTR_MODE) { + umode_t mode = iattr->ia_mode; + + if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID)) + mode &= ~S_ISGID; + sd_iattr->ia_mode = sd->s_mode = mode; + } + + return error; +} + +static inline void set_default_inode_attr(struct inode * inode, mode_t mode) +{ + inode->i_mode = mode; + inode->i_uid = 0; + inode->i_gid = 0; + inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; +} + +static inline void set_inode_attr(struct inode * inode, struct iattr * iattr) +{ + inode->i_mode = iattr->ia_mode; + inode->i_uid = iattr->ia_uid; + inode->i_gid = iattr->ia_gid; + inode->i_atime = iattr->ia_atime; + inode->i_mtime = iattr->ia_mtime; + inode->i_ctime = iattr->ia_ctime; +} + +struct inode * configfs_new_inode(mode_t mode, struct configfs_dirent * sd) { struct inode * inode = new_inode(configfs_sb); if (inode) { - inode->i_mode = mode; - inode->i_uid = 0; - inode->i_gid = 0; inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; - inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_mapping->a_ops = &configfs_aops; inode->i_mapping->backing_dev_info = &configfs_backing_dev_info; + inode->i_op = &configfs_inode_operations; + + if (sd->s_iattr) { + /* sysfs_dirent has non-default attributes + * get them for the new inode from persistent copy + * in sysfs_dirent + */ + set_inode_attr(inode, sd->s_iattr); + } else + set_default_inode_attr(inode, mode); } return inode; } @@ -70,7 +160,8 @@ int configfs_create(struct dentry * dentry, int mode, int (*init)(struct inode * struct inode * inode = NULL; if (dentry) { if (!dentry->d_inode) { - if ((inode = configfs_new_inode(mode))) { + struct configfs_dirent *sd = dentry->d_fsdata; + if ((inode = configfs_new_inode(mode, sd))) { if (dentry->d_parent && dentry->d_parent->d_inode) { struct inode *p_inode = dentry->d_parent->d_inode; p_inode->i_mtime = p_inode->i_ctime = CURRENT_TIME; @@ -103,10 +194,9 @@ int configfs_create(struct dentry * dentry, int mode, int (*init)(struct inode * */ const unsigned char * configfs_get_name(struct configfs_dirent *sd) { - struct attribute * attr; + struct configfs_attribute *attr; - if (!sd || !sd->s_element) - BUG(); + BUG_ON(!sd || !sd->s_element); /* These always have a dentry, so use that */ if (sd->s_type & (CONFIGFS_DIR | CONFIGFS_ITEM_LINK)) @@ -114,7 +204,7 @@ const unsigned char * configfs_get_name(struct configfs_dirent *sd) if (sd->s_type & CONFIGFS_ITEM_ATTR) { attr = sd->s_element; - return attr->name; + return attr->ca_name; } return NULL; } @@ -130,13 +220,17 @@ void configfs_drop_dentry(struct configfs_dirent * sd, struct dentry * parent) if (dentry) { spin_lock(&dcache_lock); + spin_lock(&dentry->d_lock); if (!(d_unhashed(dentry) && dentry->d_inode)) { dget_locked(dentry); __d_drop(dentry); + spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); simple_unlink(parent->d_inode, dentry); - } else + } else { + spin_unlock(&dentry->d_lock); spin_unlock(&dcache_lock); + } } } @@ -145,6 +239,10 @@ void configfs_hash_and_remove(struct dentry * dir, const char * name) struct configfs_dirent * sd; struct configfs_dirent * parent_sd = dir->d_fsdata; + if (dir->d_inode == NULL) + /* no inode means this hasn't been made visible yet */ + return; + mutex_lock(&dir->d_inode->i_mutex); list_for_each_entry(sd, &parent_sd->s_children, s_sibling) { if (!sd->s_element) diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c index 1a2f6f6a4d9..f920d30478e 100644 --- a/fs/configfs/mount.c +++ b/fs/configfs/mount.c @@ -38,6 +38,7 @@ struct vfsmount * configfs_mount = NULL; struct super_block * configfs_sb = NULL; +kmem_cache_t *configfs_dir_cachep; static int configfs_mnt_count = 0; static struct super_operations configfs_ops = { @@ -62,6 +63,7 @@ static struct configfs_dirent configfs_root = { .s_children = LIST_HEAD_INIT(configfs_root.s_children), .s_element = &configfs_root_group.cg_item, .s_type = CONFIGFS_ROOT, + .s_iattr = NULL, }; static int configfs_fill_super(struct super_block *sb, void *data, int silent) @@ -73,9 +75,11 @@ static int configfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_blocksize_bits = PAGE_CACHE_SHIFT; sb->s_magic = CONFIGFS_MAGIC; sb->s_op = &configfs_ops; + sb->s_time_gran = 1; configfs_sb = sb; - inode = configfs_new_inode(S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO); + inode = configfs_new_inode(S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO, + &configfs_root); if (inode) { inode->i_op = &configfs_dir_inode_operations; inode->i_fop = &configfs_dir_operations; @@ -128,19 +132,31 @@ static decl_subsys(config, NULL, NULL); static int __init configfs_init(void) { - int err; + int err = -ENOMEM; + + configfs_dir_cachep = kmem_cache_create("configfs_dir_cache", + sizeof(struct configfs_dirent), + 0, 0, NULL, NULL); + if (!configfs_dir_cachep) + goto out; kset_set_kset_s(&config_subsys, kernel_subsys); err = subsystem_register(&config_subsys); - if (err) - return err; + if (err) { + kmem_cache_destroy(configfs_dir_cachep); + configfs_dir_cachep = NULL; + goto out; + } err = register_filesystem(&configfs_fs_type); if (err) { printk(KERN_ERR "configfs: Unable to register filesystem!\n"); subsystem_unregister(&config_subsys); + kmem_cache_destroy(configfs_dir_cachep); + configfs_dir_cachep = NULL; } +out: return err; } @@ -148,11 +164,13 @@ static void __exit configfs_exit(void) { unregister_filesystem(&configfs_fs_type); subsystem_unregister(&config_subsys); + kmem_cache_destroy(configfs_dir_cachep); + configfs_dir_cachep = NULL; } MODULE_AUTHOR("Oracle"); MODULE_LICENSE("GPL"); -MODULE_VERSION("0.0.1"); +MODULE_VERSION("0.0.2"); MODULE_DESCRIPTION("Simple RAM filesystem for user driven kernel subsystem configuration."); module_init(configfs_init); diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c index 50f5840521a..e5512e295cf 100644 --- a/fs/configfs/symlink.c +++ b/fs/configfs/symlink.c @@ -162,8 +162,7 @@ int configfs_unlink(struct inode *dir, struct dentry *dentry) if (!(sd->s_type & CONFIGFS_ITEM_LINK)) goto out; - if (dentry->d_parent == configfs_sb->s_root) - BUG(); + BUG_ON(dentry->d_parent == configfs_sb->s_root); sl = sd->s_element; @@ -277,5 +276,6 @@ struct inode_operations configfs_symlink_inode_operations = { .follow_link = configfs_follow_link, .readlink = generic_readlink, .put_link = configfs_put_link, + .setattr = configfs_setattr, }; diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c index d424041b38e..bae3d7548be 100644 --- a/fs/ocfs2/buffer_head_io.c +++ b/fs/ocfs2/buffer_head_io.c @@ -58,7 +58,7 @@ int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh, goto out; } - down(&OCFS2_I(inode)->ip_io_sem); + mutex_lock(&OCFS2_I(inode)->ip_io_mutex); lock_buffer(bh); set_buffer_uptodate(bh); @@ -82,7 +82,7 @@ int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh, brelse(bh); } - up(&OCFS2_I(inode)->ip_io_sem); + mutex_unlock(&OCFS2_I(inode)->ip_io_mutex); out: mlog_exit(ret); return ret; @@ -125,13 +125,13 @@ int ocfs2_read_blocks(struct ocfs2_super *osb, u64 block, int nr, flags &= ~OCFS2_BH_CACHED; if (inode) - down(&OCFS2_I(inode)->ip_io_sem); + mutex_lock(&OCFS2_I(inode)->ip_io_mutex); for (i = 0 ; i < nr ; i++) { if (bhs[i] == NULL) { bhs[i] = sb_getblk(sb, block++); if (bhs[i] == NULL) { if (inode) - up(&OCFS2_I(inode)->ip_io_sem); + mutex_unlock(&OCFS2_I(inode)->ip_io_mutex); status = -EIO; mlog_errno(status); goto bail; @@ -220,7 +220,7 @@ int ocfs2_read_blocks(struct ocfs2_super *osb, u64 block, int nr, ocfs2_set_buffer_uptodate(inode, bh); } if (inode) - up(&OCFS2_I(inode)->ip_io_sem); + mutex_unlock(&OCFS2_I(inode)->ip_io_mutex); mlog(ML_BH_IO, "block=(%"MLFu64"), nr=(%d), cached=%s\n", block, nr, (!(flags & OCFS2_BH_CACHED) || ignore_cache) ? "no" : "yes"); diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 7307ba52891..d08971d29b6 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -917,8 +917,9 @@ static int o2hb_thread(void *data) elapsed_msec = o2hb_elapsed_msecs(&before_hb, &after_hb); mlog(0, "start = %lu.%lu, end = %lu.%lu, msec = %u\n", - before_hb.tv_sec, before_hb.tv_usec, - after_hb.tv_sec, after_hb.tv_usec, elapsed_msec); + before_hb.tv_sec, (unsigned long) before_hb.tv_usec, + after_hb.tv_sec, (unsigned long) after_hb.tv_usec, + elapsed_msec); if (elapsed_msec < reg->hr_timeout_ms) { /* the kthread api has blocked signals for us so no diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 35d92c01a97..d22d4cf08db 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -1285,14 +1285,16 @@ static void o2net_idle_timer(unsigned long data) mlog(ML_NOTICE, "here are some times that might help debug the " "situation: (tmr %ld.%ld now %ld.%ld dr %ld.%ld adv " "%ld.%ld:%ld.%ld func (%08x:%u) %ld.%ld:%ld.%ld)\n", - sc->sc_tv_timer.tv_sec, sc->sc_tv_timer.tv_usec, - now.tv_sec, now.tv_usec, - sc->sc_tv_data_ready.tv_sec, sc->sc_tv_data_ready.tv_usec, - sc->sc_tv_advance_start.tv_sec, sc->sc_tv_advance_start.tv_usec, - sc->sc_tv_advance_stop.tv_sec, sc->sc_tv_advance_stop.tv_usec, + sc->sc_tv_timer.tv_sec, (long) sc->sc_tv_timer.tv_usec, + now.tv_sec, (long) now.tv_usec, + sc->sc_tv_data_ready.tv_sec, (long) sc->sc_tv_data_ready.tv_usec, + sc->sc_tv_advance_start.tv_sec, + (long) sc->sc_tv_advance_start.tv_usec, + sc->sc_tv_advance_stop.tv_sec, + (long) sc->sc_tv_advance_stop.tv_usec, sc->sc_msg_key, sc->sc_msg_type, - sc->sc_tv_func_start.tv_sec, sc->sc_tv_func_start.tv_usec, - sc->sc_tv_func_stop.tv_sec, sc->sc_tv_func_stop.tv_usec); + sc->sc_tv_func_start.tv_sec, (long) sc->sc_tv_func_start.tv_usec, + sc->sc_tv_func_stop.tv_sec, (long) sc->sc_tv_func_stop.tv_usec); o2net_sc_queue_work(sc, &sc->sc_shutdown_work); } diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h index 3fecba0a602..42eb53b5293 100644 --- a/fs/ocfs2/dlm/dlmcommon.h +++ b/fs/ocfs2/dlm/dlmcommon.h @@ -657,6 +657,7 @@ void dlm_complete_thread(struct dlm_ctxt *dlm); int dlm_launch_recovery_thread(struct dlm_ctxt *dlm); void dlm_complete_recovery_thread(struct dlm_ctxt *dlm); void dlm_wait_for_recovery(struct dlm_ctxt *dlm); +int dlm_is_node_dead(struct dlm_ctxt *dlm, u8 node); void dlm_put(struct dlm_ctxt *dlm); struct dlm_ctxt *dlm_grab(struct dlm_ctxt *dlm); diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index da3c22045f8..6ee30837389 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -573,8 +573,11 @@ static int dlm_query_join_handler(struct o2net_msg *msg, u32 len, void *data) spin_lock(&dlm_domain_lock); dlm = __dlm_lookup_domain_full(query->domain, query->name_len); /* Once the dlm ctxt is marked as leaving then we don't want - * to be put in someone's domain map. */ + * to be put in someone's domain map. + * Also, explicitly disallow joining at certain troublesome + * times (ie. during recovery). */ if (dlm && dlm->dlm_state != DLM_CTXT_LEAVING) { + int bit = query->node_idx; spin_lock(&dlm->spinlock); if (dlm->dlm_state == DLM_CTXT_NEW && @@ -586,6 +589,19 @@ static int dlm_query_join_handler(struct o2net_msg *msg, u32 len, void *data) } else if (dlm->joining_node != DLM_LOCK_RES_OWNER_UNKNOWN) { /* Disallow parallel joins. */ response = JOIN_DISALLOW; + } else if (dlm->reco.state & DLM_RECO_STATE_ACTIVE) { + mlog(ML_NOTICE, "node %u trying to join, but recovery " + "is ongoing.\n", bit); + response = JOIN_DISALLOW; + } else if (test_bit(bit, dlm->recovery_map)) { + mlog(ML_NOTICE, "node %u trying to join, but it " + "still needs recovery.\n", bit); + response = JOIN_DISALLOW; + } else if (test_bit(bit, dlm->domain_map)) { + mlog(ML_NOTICE, "node %u trying to join, but it " + "is still in the domain! needs recovery?\n", + bit); + response = JOIN_DISALLOW; } else { /* Alright we're fully a part of this domain * so we keep some state as to who's joining diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 27e984f7e4c..a3194fe173d 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -1050,17 +1050,10 @@ static int dlm_restart_lock_mastery(struct dlm_ctxt *dlm, node = dlm_bitmap_diff_iter_next(&bdi, &sc); while (node >= 0) { if (sc == NODE_UP) { - /* a node came up. easy. might not even need - * to talk to it if its node number is higher - * or if we are already blocked. */ - mlog(0, "node up! %d\n", node); - if (blocked) - goto next; - - if (node > dlm->node_num) { - mlog(0, "node > this node. skipping.\n"); - goto next; - } + /* a node came up. clear any old vote from + * the response map and set it in the vote map + * then restart the mastery. */ + mlog(ML_NOTICE, "node %d up while restarting\n", node); /* redo the master request, but only for the new node */ mlog(0, "sending request to new node\n"); @@ -2005,6 +1998,15 @@ fail: break; mlog(0, "timed out during migration\n"); + /* avoid hang during shutdown when migrating lockres + * to a node which also goes down */ + if (dlm_is_node_dead(dlm, target)) { + mlog(0, "%s:%.*s: expected migration target %u " + "is no longer up. restarting.\n", + dlm->name, res->lockname.len, + res->lockname.name, target); + ret = -ERESTARTSYS; + } } if (ret == -ERESTARTSYS) { /* migration failed, detach and clean up mle */ diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 0c8eb1093f0..186e9a76aa5 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -39,6 +39,7 @@ #include <linux/inet.h> #include <linux/timer.h> #include <linux/kthread.h> +#include <linux/delay.h> #include "cluster/heartbeat.h" @@ -256,6 +257,27 @@ static int dlm_recovery_thread(void *data) return 0; } +/* returns true when the recovery master has contacted us */ +static int dlm_reco_master_ready(struct dlm_ctxt *dlm) +{ + int ready; + spin_lock(&dlm->spinlock); + ready = (dlm->reco.new_master != O2NM_INVALID_NODE_NUM); + spin_unlock(&dlm->spinlock); + return ready; +} + +/* returns true if node is no longer in the domain + * could be dead or just not joined */ +int dlm_is_node_dead(struct dlm_ctxt *dlm, u8 node) +{ + int dead; + spin_lock(&dlm->spinlock); + dead = test_bit(node, dlm->domain_map); + spin_unlock(&dlm->spinlock); + return dead; +} + /* callers of the top-level api calls (dlmlock/dlmunlock) should * block on the dlm->reco.event when recovery is in progress. * the dlm recovery thread will set this state when it begins @@ -297,6 +319,7 @@ static void dlm_end_recovery(struct dlm_ctxt *dlm) static int dlm_do_recovery(struct dlm_ctxt *dlm) { int status = 0; + int ret; spin_lock(&dlm->spinlock); @@ -343,10 +366,13 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm) goto master_here; if (dlm->reco.new_master == O2NM_INVALID_NODE_NUM) { - /* choose a new master */ - if (!dlm_pick_recovery_master(dlm)) { + /* choose a new master, returns 0 if this node + * is the master, -EEXIST if it's another node. + * this does not return until a new master is chosen + * or recovery completes entirely. */ + ret = dlm_pick_recovery_master(dlm); + if (!ret) { /* already notified everyone. go. */ - dlm->reco.new_master = dlm->node_num; goto master_here; } mlog(0, "another node will master this recovery session.\n"); @@ -371,8 +397,13 @@ master_here: if (status < 0) { mlog(ML_ERROR, "error %d remastering locks for node %u, " "retrying.\n", status, dlm->reco.dead_node); + /* yield a bit to allow any final network messages + * to get handled on remaining nodes */ + msleep(100); } else { /* success! see if any other nodes need recovery */ + mlog(0, "DONE mastering recovery of %s:%u here(this=%u)!\n", + dlm->name, dlm->reco.dead_node, dlm->node_num); dlm_reset_recovery(dlm); } dlm_end_recovery(dlm); @@ -477,7 +508,7 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node) BUG(); break; case DLM_RECO_NODE_DATA_DEAD: - mlog(0, "node %u died after " + mlog(ML_NOTICE, "node %u died after " "requesting recovery info for " "node %u\n", ndata->node_num, dead_node); @@ -485,6 +516,19 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node) // start all over destroy = 1; status = -EAGAIN; + /* instead of spinning like crazy here, + * wait for the domain map to catch up + * with the network state. otherwise this + * can be hit hundreds of times before + * the node is really seen as dead. */ + wait_event_timeout(dlm->dlm_reco_thread_wq, + dlm_is_node_dead(dlm, + ndata->node_num), + msecs_to_jiffies(1000)); + mlog(0, "waited 1 sec for %u, " + "dead? %s\n", ndata->node_num, + dlm_is_node_dead(dlm, ndata->node_num) ? + "yes" : "no"); goto leave; case DLM_RECO_NODE_DATA_RECEIVING: case DLM_RECO_NODE_DATA_REQUESTED: @@ -678,11 +722,27 @@ static void dlm_request_all_locks_worker(struct dlm_work_item *item, void *data) dlm = item->dlm; dead_node = item->u.ral.dead_node; reco_master = item->u.ral.reco_master; + mres = (struct dlm_migratable_lockres *)data; + + if (dead_node != dlm->reco.dead_node || + reco_master != dlm->reco.new_master) { + /* show extra debug info if the recovery state is messed */ + mlog(ML_ERROR, "%s: bad reco state: reco(dead=%u, master=%u), " + "request(dead=%u, master=%u)\n", + dlm->name, dlm->reco.dead_node, dlm->reco.new_master, + dead_node, reco_master); + mlog(ML_ERROR, "%s: name=%.*s master=%u locks=%u/%u flags=%u " + "entry[0]={c=%"MLFu64",l=%u,f=%u,t=%d,ct=%d,hb=%d,n=%u}\n", + dlm->name, mres->lockname_len, mres->lockname, mres->master, + mres->num_locks, mres->total_locks, mres->flags, + mres->ml[0].cookie, mres->ml[0].list, mres->ml[0].flags, + mres->ml[0].type, mres->ml[0].convert_type, + mres->ml[0].highest_blocked, mres->ml[0].node); + BUG(); + } BUG_ON(dead_node != dlm->reco.dead_node); BUG_ON(reco_master != dlm->reco.new_master); - mres = (struct dlm_migratable_lockres *)data; - /* lock resources should have already been moved to the * dlm->reco.resources list. now move items from that list * to a temp list if the dead owner matches. note that the @@ -757,15 +817,18 @@ int dlm_reco_data_done_handler(struct o2net_msg |