diff options
Diffstat (limited to 'fs')
142 files changed, 5568 insertions, 3497 deletions
diff --git a/fs/adfs/file.c b/fs/adfs/file.c index f544a285592..36e381c6a99 100644 --- a/fs/adfs/file.c +++ b/fs/adfs/file.c @@ -33,7 +33,7 @@ const struct file_operations adfs_file_operations = { .fsync = file_fsync, .write = do_sync_write, .aio_write = generic_file_aio_write, - .sendfile = generic_file_sendfile, + .splice_read = generic_file_splice_read, }; const struct inode_operations adfs_file_inode_operations = { diff --git a/fs/affs/file.c b/fs/affs/file.c index c8796906f58..c314a35f091 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -35,7 +35,7 @@ const struct file_operations affs_file_operations = { .open = affs_file_open, .release = affs_file_release, .fsync = file_fsync, - .sendfile = generic_file_sendfile, + .splice_read = generic_file_splice_read, }; const struct inode_operations affs_file_inode_operations = { diff --git a/fs/afs/file.c b/fs/afs/file.c index 9c0e721d9fc..aede7eb66dd 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -32,7 +32,7 @@ const struct file_operations afs_file_operations = { .aio_read = generic_file_aio_read, .aio_write = afs_file_write, .mmap = generic_file_readonly_mmap, - .sendfile = generic_file_sendfile, + .splice_read = generic_file_splice_read, .fsync = afs_fsync, }; diff --git a/fs/bad_inode.c b/fs/bad_inode.c index 329ee473eed..521ff7caadb 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -114,12 +114,6 @@ static int bad_file_lock(struct file *file, int cmd, struct file_lock *fl) return -EIO; } -static ssize_t bad_file_sendfile(struct file *in_file, loff_t *ppos, - size_t count, read_actor_t actor, void *target) -{ - return -EIO; -} - static ssize_t bad_file_sendpage(struct file *file, struct page *page, int off, size_t len, loff_t *pos, int more) { @@ -182,7 +176,6 @@ static const struct file_operations bad_file_ops = .aio_fsync = bad_file_aio_fsync, .fasync = bad_file_fasync, .lock = bad_file_lock, - .sendfile = bad_file_sendfile, .sendpage = bad_file_sendpage, .get_unmapped_area = bad_file_get_unmapped_area, .check_flags = bad_file_check_flags, diff --git a/fs/bfs/file.c b/fs/bfs/file.c index ef4d1fa04e6..24310e9ee05 100644 --- a/fs/bfs/file.c +++ b/fs/bfs/file.c @@ -24,7 +24,7 @@ const struct file_operations bfs_file_operations = { .write = do_sync_write, .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, - .sendfile = generic_file_sendfile, + .splice_read = generic_file_splice_read, }; static int bfs_move_block(unsigned long from, unsigned long to, struct super_block *sb) @@ -1223,8 +1223,6 @@ EXPORT_SYMBOL(bio_hw_segments); EXPORT_SYMBOL(bio_add_page); EXPORT_SYMBOL(bio_add_pc_page); EXPORT_SYMBOL(bio_get_nr_vecs); -EXPORT_SYMBOL(bio_map_user); -EXPORT_SYMBOL(bio_unmap_user); EXPORT_SYMBOL(bio_map_kern); EXPORT_SYMBOL(bio_pair_release); EXPORT_SYMBOL(bio_split); diff --git a/fs/block_dev.c b/fs/block_dev.c index ea1480a16f5..b3e9bfa748c 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1346,7 +1346,6 @@ const struct file_operations def_blk_fops = { #ifdef CONFIG_COMPAT .compat_ioctl = compat_blkdev_ioctl, #endif - .sendfile = generic_file_sendfile, .splice_read = generic_file_splice_read, .splice_write = generic_file_splice_write, }; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 7c04752b76c..8b0cbf4a4ad 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -616,7 +616,7 @@ const struct file_operations cifs_file_ops = { .fsync = cifs_fsync, .flush = cifs_flush, .mmap = cifs_file_mmap, - .sendfile = generic_file_sendfile, + .splice_read = generic_file_splice_read, .llseek = cifs_llseek, #ifdef CONFIG_CIFS_POSIX .ioctl = cifs_ioctl, @@ -637,7 +637,7 @@ const struct file_operations cifs_file_direct_ops = { .lock = cifs_lock, .fsync = cifs_fsync, .flush = cifs_flush, - .sendfile = generic_file_sendfile, /* BB removeme BB */ + .splice_read = generic_file_splice_read, #ifdef CONFIG_CIFS_POSIX .ioctl = cifs_ioctl, #endif /* CONFIG_CIFS_POSIX */ @@ -656,7 +656,7 @@ const struct file_operations cifs_file_nobrl_ops = { .fsync = cifs_fsync, .flush = cifs_flush, .mmap = cifs_file_mmap, - .sendfile = generic_file_sendfile, + .splice_read = generic_file_splice_read, .llseek = cifs_llseek, #ifdef CONFIG_CIFS_POSIX .ioctl = cifs_ioctl, @@ -676,7 +676,7 @@ const struct file_operations cifs_file_direct_nobrl_ops = { .release = cifs_close, .fsync = cifs_fsync, .flush = cifs_flush, - .sendfile = generic_file_sendfile, /* BB removeme BB */ + .splice_read = generic_file_splice_read, #ifdef CONFIG_CIFS_POSIX .ioctl = cifs_ioctl, #endif /* CONFIG_CIFS_POSIX */ diff --git a/fs/coda/file.c b/fs/coda/file.c index 5ef2b609ec7..99dbe866816 100644 --- a/fs/coda/file.c +++ b/fs/coda/file.c @@ -47,8 +47,9 @@ coda_file_read(struct file *coda_file, char __user *buf, size_t count, loff_t *p } static ssize_t -coda_file_sendfile(struct file *coda_file, loff_t *ppos, size_t count, - read_actor_t actor, void *target) +coda_file_splice_read(struct file *coda_file, loff_t *ppos, + struct pipe_inode_info *pipe, size_t count, + unsigned int flags) { struct coda_file_info *cfi; struct file *host_file; @@ -57,10 +58,10 @@ coda_file_sendfile(struct file *coda_file, loff_t *ppos, size_t count, BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC); host_file = cfi->cfi_container; - if (!host_file->f_op || !host_file->f_op->sendfile) + if (!host_file->f_op || !host_file->f_op->splice_read) return -EINVAL; - return host_file->f_op->sendfile(host_file, ppos, count, actor, target); + return host_file->f_op->splice_read(host_file, ppos, pipe, count,flags); } static ssize_t @@ -295,6 +296,6 @@ const struct file_operations coda_file_operations = { .flush = coda_flush, .release = coda_release, .fsync = coda_fsync, - .sendfile = coda_file_sendfile, + .splice_read = coda_file_splice_read, }; diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index ec8896b264d..1d533a2ec3a 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -368,6 +368,69 @@ void debugfs_remove(struct dentry *dentry) } EXPORT_SYMBOL_GPL(debugfs_remove); +/** + * debugfs_rename - rename a file/directory in the debugfs filesystem + * @old_dir: a pointer to the parent dentry for the renamed object. This + * should be a directory dentry. + * @old_dentry: dentry of an object to be renamed. + * @new_dir: a pointer to the parent dentry where the object should be + * moved. This should be a directory dentry. + * @new_name: a pointer to a string containing the target name. + * + * This function renames a file/directory in debugfs. The target must not + * exist for rename to succeed. + * + * This function will return a pointer to old_dentry (which is updated to + * reflect renaming) if it succeeds. If an error occurs, %NULL will be + * returned. + * + * If debugfs is not enabled in the kernel, the value -%ENODEV will be + * returned. + */ +struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, + struct dentry *new_dir, const char *new_name) +{ + int error; + struct dentry *dentry = NULL, *trap; + const char *old_name; + + trap = lock_rename(new_dir, old_dir); + /* Source or destination directories don't exist? */ + if (!old_dir->d_inode || !new_dir->d_inode) + goto exit; + /* Source does not exist, cyclic rename, or mountpoint? */ + if (!old_dentry->d_inode || old_dentry == trap || + d_mountpoint(old_dentry)) + goto exit; + dentry = lookup_one_len(new_name, new_dir, strlen(new_name)); + /* Lookup failed, cyclic rename or target exists? */ + if (IS_ERR(dentry) || dentry == trap || dentry->d_inode) + goto exit; + + old_name = fsnotify_oldname_init(old_dentry->d_name.name); + + error = simple_rename(old_dir->d_inode, old_dentry, new_dir->d_inode, + dentry); + if (error) { + fsnotify_oldname_free(old_name); + goto exit; + } + d_move(old_dentry, dentry); + fsnotify_move(old_dir->d_inode, new_dir->d_inode, old_name, + old_dentry->d_name.name, S_ISDIR(old_dentry->d_inode->i_mode), + NULL, old_dentry->d_inode); + fsnotify_oldname_free(old_name); + unlock_rename(new_dir, old_dir); + dput(dentry); + return old_dentry; +exit: + if (dentry && !IS_ERR(dentry)) + dput(dentry); + unlock_rename(new_dir, old_dir); + return NULL; +} +EXPORT_SYMBOL_GPL(debugfs_rename); + static decl_subsys(debug, NULL, NULL); static int __init debugfs_init(void) diff --git a/fs/dlm/Makefile b/fs/dlm/Makefile index 604cf7dc5f3..d248e60951b 100644 --- a/fs/dlm/Makefile +++ b/fs/dlm/Makefile @@ -8,6 +8,7 @@ dlm-y := ast.o \ member.o \ memory.o \ midcomms.o \ + netlink.o \ lowcomms.o \ rcom.o \ recover.o \ diff --git a/fs/dlm/config.c b/fs/dlm/config.c index 822abdcd143..5069b2cb5a1 100644 --- a/fs/dlm/config.c +++ b/fs/dlm/config.c @@ -90,6 +90,7 @@ struct cluster { unsigned int cl_scan_secs; unsigned int cl_log_debug; unsigned int cl_protocol; + unsigned int cl_timewarn_cs; }; enum { @@ -103,6 +104,7 @@ enum { CLUSTER_ATTR_SCAN_SECS, CLUSTER_ATTR_LOG_DEBUG, CLUSTER_ATTR_PROTOCOL, + CLUSTER_ATTR_TIMEWARN_CS, }; struct cluster_attribute { @@ -162,6 +164,7 @@ CLUSTER_ATTR(toss_secs, 1); CLUSTER_ATTR(scan_secs, 1); CLUSTER_ATTR(log_debug, 0); CLUSTER_ATTR(protocol, 0); +CLUSTER_ATTR(timewarn_cs, 1); static struct configfs_attribute *cluster_attrs[] = { [CLUSTER_ATTR_TCP_PORT] = &cluster_attr_tcp_port.attr, @@ -174,6 +177,7 @@ static struct configfs_attribute *cluster_attrs[] = { [CLUSTER_ATTR_SCAN_SECS] = &cluster_attr_scan_secs.attr, [CLUSTER_ATTR_LOG_DEBUG] = &cluster_attr_log_debug.attr, [CLUSTER_ATTR_PROTOCOL] = &cluster_attr_protocol.attr, + [CLUSTER_ATTR_TIMEWARN_CS] = &cluster_attr_timewarn_cs.attr, NULL, }; @@ -429,6 +433,8 @@ static struct config_group *make_cluster(struct config_group *g, cl->cl_toss_secs = dlm_config.ci_toss_secs; cl->cl_scan_secs = dlm_config.ci_scan_secs; cl->cl_log_debug = dlm_config.ci_log_debug; + cl->cl_protocol = dlm_config.ci_protocol; + cl->cl_timewarn_cs = dlm_config.ci_timewarn_cs; space_list = &sps->ss_group; comm_list = &cms->cs_group; @@ -748,9 +754,16 @@ static ssize_t node_weight_write(struct node *nd, const char *buf, size_t len) static struct space *get_space(char *name) { + struct config_item *i; + if (!space_list) return NULL; - return to_space(config_group_find_obj(space_list, name)); + + down(&space_list->cg_subsys->su_sem); + i = config_group_find_obj(space_list, name); + up(&space_list->cg_subsys->su_sem); + + return to_space(i); } static void put_space(struct space *sp) @@ -776,20 +789,20 @@ static struct comm *get_comm(int nodeid, struct sockaddr_storage *addr) if (cm->nodeid != nodeid) continue; found = 1; + config_item_get(i); break; } else { if (!cm->addr_count || memcmp(cm->addr[0], addr, sizeof(*addr))) continue; found = 1; + config_item_get(i); break; } } up(&clusters_root.subsys.su_sem); - if (found) - config_item_get(i); - else + if (!found) cm = NULL; return cm; } @@ -909,6 +922,7 @@ int dlm_our_addr(struct sockaddr_storage *addr, int num) #define DEFAULT_SCAN_SECS 5 #define DEFAULT_LOG_DEBUG 0 #define DEFAULT_PROTOCOL 0 +#define DEFAULT_TIMEWARN_CS 500 /* 5 sec = 500 centiseconds */ struct dlm_config_info dlm_config = { .ci_tcp_port = DEFAULT_TCP_PORT, @@ -920,6 +934,7 @@ struct dlm_config_info dlm_config = { .ci_toss_secs = DEFAULT_TOSS_SECS, .ci_scan_secs = DEFAULT_SCAN_SECS, .ci_log_debug = DEFAULT_LOG_DEBUG, - .ci_protocol = DEFAULT_PROTOCOL + .ci_protocol = DEFAULT_PROTOCOL, + .ci_timewarn_cs = DEFAULT_TIMEWARN_CS }; diff --git a/fs/dlm/config.h b/fs/dlm/config.h index 967cc3d72e5..a3170fe2209 100644 --- a/fs/dlm/config.h +++ b/fs/dlm/config.h @@ -27,6 +27,7 @@ struct dlm_config_info { int ci_scan_secs; int ci_log_debug; int ci_protocol; + int ci_timewarn_cs; }; extern struct dlm_config_info dlm_config; diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c index 61ba670b9e0..12c3bfd5e66 100644 --- a/fs/dlm/debug_fs.c +++ b/fs/dlm/debug_fs.c @@ -17,6 +17,7 @@ #include <linux/debugfs.h> #include "dlm_internal.h" +#include "lock.h" #define DLM_DEBUG_BUF_LEN 4096 static char debug_buf[DLM_DEBUG_BUF_LEN]; @@ -26,6 +27,8 @@ static struct dentry *dlm_root; struct rsb_iter { int entry; + int locks; + int header; struct dlm_ls *ls; struct list_head *next; struct dlm_rsb *rsb; @@ -57,8 +60,8 @@ static char *print_lockmode(int mode) } } -static void print_lock(struct seq_file *s, struct dlm_lkb *lkb, - struct dlm_rsb *res) +static void print_resource_lock(struct seq_file *s, struct dlm_lkb *lkb, + struct dlm_rsb *res) { seq_printf(s, "%08x %s", lkb->lkb_id, print_lockmode(lkb->lkb_grmode)); @@ -85,6 +88,8 @@ static int print_resource(struct dlm_rsb *res, struct seq_file *s) struct dlm_lkb *lkb; int i, lvblen = res->res_ls->ls_lvblen, recover_list, root_list; + lock_rsb(res); + seq_printf(s, "\nResource %p Name (len=%d) \"", res, res->res_length); for (i = 0; i < res->res_length; i++) { if (isprint(res->res_name[i])) @@ -129,15 +134,15 @@ static int print_resource(struct dlm_rsb *res, struct seq_file *s) /* Print the locks attached to this resource */ seq_printf(s, "Granted Queue\n"); list_for_each_entry(lkb, &res->res_grantqueue, lkb_statequeue) - print_lock(s, lkb, res); + print_resource_lock(s, lkb, res); seq_printf(s, "Conversion Queue\n"); list_for_each_entry(lkb, &res->res_convertqueue, lkb_statequeue) - print_lock(s, lkb, res); + print_resource_lock(s, lkb, res); seq_printf(s, "Waiting Queue\n"); list_for_each_entry(lkb, &res->res_waitqueue, lkb_statequeue) - print_lock(s, lkb, res); + print_resource_lock(s, lkb, res); if (list_empty(&res->res_lookup)) goto out; @@ -151,6 +156,61 @@ static int print_resource(struct dlm_rsb *res, struct seq_file *s) seq_printf(s, "\n"); } out: + unlock_rsb(res); + return 0; +} + +static void print_lock(struct seq_file *s, struct dlm_lkb *lkb, struct dlm_rsb *r) +{ + struct dlm_user_args *ua; + unsigned int waiting = 0; + uint64_t xid = 0; + + if (lkb->lkb_flags & DLM_IFL_USER) { + ua = (struct dlm_user_args *) lkb->lkb_astparam; + if (ua) + xid = ua->xid; + } + + if (lkb->lkb_timestamp) + waiting = jiffies_to_msecs(jiffies - lkb->lkb_timestamp); + + /* id nodeid remid pid xid exflags flags sts grmode rqmode time_ms + r_nodeid r_len r_name */ + + seq_printf(s, "%x %d %x %u %llu %x %x %d %d %d %u %u %d \"%s\"\n", + lkb->lkb_id, + lkb->lkb_nodeid, + lkb->lkb_remid, + lkb->lkb_ownpid, + (unsigned long long)xid, + lkb->lkb_exflags, + lkb->lkb_flags, + lkb->lkb_status, + lkb->lkb_grmode, + lkb->lkb_rqmode, + waiting, + r->res_nodeid, + r->res_length, + r->res_name); +} + +static int print_locks(struct dlm_rsb *r, struct seq_file *s) +{ + struct dlm_lkb *lkb; + + lock_rsb(r); + + list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue) + print_lock(s, lkb, r); + + list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue) + print_lock(s, lkb, r); + + list_for_each_entry(lkb, &r->res_waitqueue, lkb_statequeue) + print_lock(s, lkb, r); + + unlock_rsb(r); return 0; } @@ -166,6 +226,9 @@ static int rsb_iter_next(struct rsb_iter *ri) read_lock(&ls->ls_rsbtbl[i].lock); if (!list_empty(&ls->ls_rsbtbl[i].list)) { ri->next = ls->ls_rsbtbl[i].list.next; + ri->rsb = list_entry(ri->next, struct dlm_rsb, + res_hashchain); + dlm_hold_rsb(ri->rsb); read_unlock(&ls->ls_rsbtbl[i].lock); break; } @@ -176,6 +239,7 @@ static int rsb_iter_next(struct rsb_iter *ri) if (ri->entry >= ls->ls_rsbtbl_size) return 1; } else { + struct dlm_rsb *old = ri->rsb; i = ri->entry; read_lock(&ls->ls_rsbtbl[i].lock); ri->next = ri->next->next; @@ -184,11 +248,14 @@ static int rsb_iter_next(struct rsb_iter *ri) ri->next = NULL; ri->entry++; read_unlock(&ls->ls_rsbtbl[i].lock); + dlm_put_rsb(old); goto top; } + ri->rsb = list_entry(ri->next, struct dlm_rsb, res_hashchain); + dlm_hold_rsb(ri->rsb); read_unlock(&ls->ls_rsbtbl[i].lock); + dlm_put_rsb(old); } - ri->rsb = list_entry(ri->next, struct dlm_rsb, res_hashchain); return 0; } @@ -202,7 +269,7 @@ static struct rsb_iter *rsb_iter_init(struct dlm_ls *ls) { struct rsb_iter *ri; - ri = kmalloc(sizeof *ri, GFP_KERNEL); + ri = kzalloc(sizeof *ri, GFP_KERNEL); if (!ri) return NULL; @@ -260,7 +327,17 @@ static int rsb_seq_show(struct seq_file *file, void *iter_ptr) { struct rsb_iter *ri = iter_ptr; - print_resource(ri->rsb, file); + if (ri->locks) { + if (ri->header) { + seq_printf(file, "id nodeid remid pid xid exflags flags " + "sts grmode rqmode time_ms r_nodeid " + "r_len r_name\n"); + ri->header = 0; + } + print_locks(ri->rsb, file); + } else { + print_resource(ri->rsb, file); + } return 0; } @@ -296,6 +373,83 @@ static const struct file_operations rsb_fops = { }; /* + * Dump state in compact per-lock listing + */ + +static struct rsb_iter *locks_iter_init(struct dlm_ls *ls, loff_t *pos) +{ + struct rsb_iter *ri; + + ri = kzalloc(sizeof *ri, GFP_KERNEL); + if (!ri) + return NULL; + + ri->ls = ls; + ri->entry = 0; + ri->next = NULL; + ri->locks = 1; + + if (*pos == 0) + ri->header = 1; + + if (rsb_iter_next(ri)) { + rsb_iter_free(ri); + return NULL; + } + + return ri; +} + +static void *locks_seq_start(struct seq_file *file, loff_t *pos) +{ + struct rsb_iter *ri; + loff_t n = *pos; + + ri = locks_iter_init(file->private, pos); + if (!ri) + return NULL; + + while (n--) { + if (rsb_iter_next(ri)) { + rsb_iter_free(ri); + return NULL; + } + } + + return ri; +} + +static struct seq_operations locks_seq_ops = { + .start = locks_seq_start, + .next = rsb_seq_next, + .stop = rsb_seq_stop, + .show = rsb_seq_show, +}; + +static int locks_open(struct inode *inode, struct file *file) +{ + struct seq_file *seq; + int ret; + + ret = seq_open(file, &locks_seq_ops); + if (ret) + return ret; + + seq = file->private_data; + seq->private = inode->i_private; + + return 0; +} + +static const struct file_operations locks_fops = { + .owner = THIS_MODULE, + .open = locks_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release +}; + +/* * dump lkb's on the ls_waiters list */ @@ -362,6 +516,20 @@ int dlm_create_debug_file(struct dlm_ls *ls) return -ENOMEM; } + memset(name, 0, sizeof(name)); + snprintf(name, DLM_LOCKSPACE_LEN+8, "%s_locks", ls->ls_name); + + ls->ls_debug_locks_dentry = debugfs_create_file(name, + S_IFREG | S_IRUGO, + dlm_root, + ls, + &locks_fops); + if (!ls->ls_debug_locks_dentry) { + debugfs_remove(ls->ls_debug_waiters_dentry); + debugfs_remove(ls->ls_debug_rsb_dentry); + return -ENOMEM; + } + return 0; } @@ -371,6 +539,8 @@ void dlm_delete_debug_file(struct dlm_ls *ls) debugfs_remove(ls->ls_debug_rsb_dentry); if (ls->ls_debug_waiters_dentry) debugfs_remove(ls->ls_debug_waiters_dentry); + if (ls->ls_debug_locks_dentry) + debugfs_remove(ls->ls_debug_locks_dentry); } int dlm_register_debugfs(void) diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h index 30994d68f6a..74901e981e1 100644 --- a/fs/dlm/dlm_internal.h +++ b/fs/dlm/dlm_internal.h @@ -151,6 +151,7 @@ struct dlm_args { void *bastaddr; int mode; struct dlm_lksb *lksb; + unsigned long timeout; }; @@ -213,6 +214,9 @@ struct dlm_args { #define DLM_IFL_OVERLAP_UNLOCK 0x00080000 #define DLM_IFL_OVERLAP_CANCEL 0x00100000 #define DLM_IFL_ENDOFLIFE 0x00200000 +#define DLM_IFL_WATCH_TIMEWARN 0x00400000 +#define DLM_IFL_TIMEOUT_CANCEL 0x00800000 +#define DLM_IFL_DEADLOCK_CANCEL 0x01000000 #define DLM_IFL_USER 0x00000001 #define DLM_IFL_ORPHAN 0x00000002 @@ -243,6 +247,9 @@ struct dlm_lkb { struct list_head lkb_wait_reply; /* waiting for remote reply */ struct list_head lkb_astqueue; /* need ast to be sent */ struct list_head lkb_ownqueue; /* list of locks for a process */ + struct list_head lkb_time_list; + unsigned long lkb_timestamp; + unsigned long lkb_timeout_cs; char *lkb_lvbptr; struct dlm_lksb *lkb_lksb; /* caller's status block */ @@ -447,12 +454,16 @@ struct dlm_ls { struct mutex ls_orphans_mutex; struct list_head ls_orphans; + struct mutex ls_timeout_mutex; + struct list_head ls_timeout; + struct list_head ls_nodes; /* current nodes in ls */ struct list_head ls_nodes_gone; /* dead node list, recovery */ int ls_num_nodes; /* number of nodes in ls */ int ls_low_nodeid; int ls_total_weight; int *ls_node_array; + gfp_t ls_allocation; struct dlm_rsb ls_stub_rsb; /* for returning errors */ struct dlm_lkb ls_stub_lkb; /* for returning errors */ @@ -460,9 +471,12 @@ struct dlm_ls { struct dentry *ls_debug_rsb_dentry; /* debugfs */ struct dentry *ls_debug_waiters_dentry; /* debugfs */ + struct dentry *ls_debug_locks_dentry; /* debugfs */ wait_queue_head_t ls_uevent_wait; /* user part of join/leave */ int ls_uevent_result; + struct completion ls_members_done; + int ls_members_result; struct miscdevice ls_device; @@ -472,6 +486,7 @@ struct dlm_ls { struct task_struct *ls_recoverd_task; struct mutex ls_recoverd_active; spinlock_t ls_recover_lock; + unsigned long ls_recover_begin; /* jiffies timestamp */ uint32_t ls_recover_status; /* DLM_RS_ */ uint64_t ls_recover_seq; struct dlm_recover *ls_recover_args; @@ -501,6 +516,7 @@ struct dlm_ls { #define LSFL_RCOM_READY 3 #define LSFL_RCOM_WAIT 4 #define LSFL_UEVENT_WAIT 5 +#define LSFL_TIMEWARN 6 /* much of this is just saving user space pointers associated with the lock that we pass back to the user lib with an ast */ @@ -518,6 +534,7 @@ struct dlm_user_args { void __user *castaddr; void __user *bastparam; void __user *bastaddr; + uint64_t xid; }; #define DLM_PROC_FLAGS_CLOSING 1 diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index d8d6e729f96..b455919c199 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -82,10 +82,13 @@ static int send_bast(struct dlm_rsb *r, struct dlm_lkb *lkb, int mode); static int send_lookup(struct dlm_rsb *r, struct dlm_lkb *lkb); static int send_remove(struct dlm_rsb *r); static int _request_lock(struct dlm_rsb *r, struct dlm_lkb *lkb); +static int _cancel_lock(struct dlm_rsb *r, struct dlm_lkb *lkb); static void __receive_convert_reply(struct dlm_rsb *r, struct dlm_lkb *lkb, struct dlm_message *ms); static int receive_extralen(struct dlm_message *ms); static void do_purge(struct dlm_ls *ls, int nodeid, int pid); +static void del_timeout(struct dlm_lkb *lkb); +void dlm_timeout_warn(struct dlm_lkb *lkb); /* * Lock compatibilty matrix - thanks Steve @@ -194,17 +197,17 @@ void dlm_dump_rsb(struct dlm_rsb *r) /* Threads cannot use the lockspace while it's being recovered */ -static inline void lock_recovery(struct dlm_ls *ls) +static inline void dlm_lock_recovery(struct dlm_ls *ls) { down_read(&ls->ls_in_recovery); } -static inline void unlock_recovery(struct dlm_ls *ls) +void dlm_unlock_recovery(struct dlm_ls *ls) { up_read(&ls->ls_in_recovery); } -static inline int lock_recovery_try(struct dlm_ls *ls) +int dlm_lock_recovery_try(struct dlm_ls *ls) { return down_read_trylock(&ls->ls_in_recovery); } @@ -286,8 +289,22 @@ static void queue_cast(struct dlm_rsb *r, struct dlm_lkb *lkb, int rv) if (is_master_copy(lkb)) return; + del_timeout(lkb); + DLM_ASSERT(lkb->lkb_lksb, dlm_print_lkb(lkb);); + /* if the operation was a cancel, then return -DLM_ECANCEL, if a + timeout caused the cancel then return -ETIMEDOUT */ + if (rv == -DLM_ECANCEL && (lkb->lkb_flags & DLM_IFL_TIMEOUT_CANCEL)) { + lkb->lkb_flags &= ~DLM_IFL_TIMEOUT_CANCEL; + rv = -ETIMEDOUT; + } + + if (rv == -DLM_ECANCEL && (lkb->lkb_flags & DLM_IFL_DEADLOCK_CANCEL)) { + lkb->lkb_flags &= ~DLM_IFL_DEADLOCK_CANCEL; + rv = -EDEADLK; + } + lkb->lkb_lksb->sb_status = rv; lkb->lkb_lksb->sb_flags = lkb->lkb_sbflags; @@ -581,6 +598,7 @@ static int create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret) kref_init(&lkb->lkb_ref); INIT_LIST_HEAD(&lkb->lkb_ownqueue); INIT_LIST_HEAD(&lkb->lkb_rsb_lookup); + INIT_LIST_HEAD(&lkb->lkb_time_list); get_random_bytes(&bucket, sizeof(bucket)); bucket &= (ls->ls_lkbtbl_size - 1); @@ -985,15 +1003,136 @@ void dlm_scan_rsbs(struct dlm_ls *ls) { int i; - if (dlm_locking_stopped(ls)) - return; - for (i = 0; i < ls->ls_rsbtbl_size; i++) { shrink_bucket(ls, i); + if (dlm_locking_stopped(ls)) + break; cond_resched(); } } +static void add_timeout(struct dlm_lkb *lkb) +{ + struct dlm_ls *ls = lkb->lkb_resource->res_ls; + + if (is_master_copy(lkb)) { + lkb->lkb_timestamp = jiffies; + return; + } + + if (test_bit(LSFL_TIMEWARN, &ls->ls_flags) && + !(lkb->lkb_exflags & DLM_LKF_NODLCKWT)) { + lkb->lkb_flags |= DLM_IFL_WATCH_TIMEWARN; + goto add_it; + } + if (lkb->lkb_exflags & DLM_LKF_TIMEOUT) + goto add_it; + return; + + add_it: + DLM_ASSERT(list_empty(&lkb->lkb_time_list), dlm_print_lkb(lkb);); + mutex_lock(&ls->ls_timeout_mutex); + hold_lkb(lkb); + lkb->lkb_timestamp = jiffies; + list_add_tail(&lkb->lkb_time_list, &ls->ls_timeout); + mutex_unlock(&ls->ls_timeout_mutex); +} + +static void del_timeout(struct dlm_lkb *lkb) +{ + struct dlm_ls *ls = lkb->lkb_resource->res_ls; + + mutex_lock(&ls->ls_timeout_mutex); + if (!list_empty(&lkb->lkb_time_list)) { + list_del_init(&lkb->lkb_time_list); + unhold_lkb(lkb); + } + mutex_unlock(&ls->ls_timeout_mutex); +} + +/* FIXME: is it safe to look at lkb_exflags, lkb_flags, lkb_timestamp, and + lkb_lksb_timeout without lock_rsb? Note: we can't lock timeout_mutex + and then lock rsb because of lock ordering in add_timeout. We may need + to specify some special timeout-related bits in the lkb that are just to + be accessed under the timeout_mutex. */ + +void dlm_scan_timeout(struct dlm_ls *ls) +{ + struct dlm_rsb *r; + struct dlm_lkb *lkb; + int do_cancel, do_warn; + + for (;;) { + if (dlm_locking_stopped(ls)) + break; + + do_cancel = 0; + do_warn = 0; + mutex_lock(&ls->ls_timeout_mutex); + list_for_each_entry(lkb, &ls->ls_timeout, lkb_time_list) { + + if ((lkb->lkb_exflags & DLM_LKF_TIMEOUT) && + time_after_eq(jiffies, lkb->lkb_timestamp + + lkb->lkb_timeout_cs * HZ/100)) + do_cancel = 1; + + if ((lkb->lkb_flags & DLM_IFL_WATCH_TIMEWARN) && + time_after_eq(jiffies, lkb->lkb_timestamp + + dlm_config.ci_timewarn_cs * HZ/100)) + do_warn = 1; + + if (!do_cancel && !do_warn) + continue; + hold_lkb(lkb); + break; + } + mutex_unlock(&ls->ls_timeout_mutex); + + if (!do_cancel && !do_warn) + break; + + r = lkb->lkb_resource; + hold_rsb(r); + lock_rsb(r); + + if (do_warn) { + /* clear flag so we only warn once */ + lkb->lkb_flags &= ~DLM_IFL_WATCH_TIMEWARN; + if (!(lkb->lkb_exflags & DLM_LKF_TIMEOUT)) + del_timeout(lkb); + dlm_timeout_warn(lkb); + } + + if (do_cancel) { + log_debug(ls, "timeout cancel %x node %d %s", + lkb->lkb_id, lkb->lkb_nodeid, r->res_name); + lkb->lkb_flags &= ~DLM_IFL_WATCH_TIMEWARN; + lkb->lkb_flags |= DLM_IFL_TIMEOUT_CANCEL; + del_timeout(lkb); + _cancel_lock(r, lkb); + } + + unlock_rsb(r); + unhold_rsb(r); + dlm_put_lkb(lkb); + } +} + +/* This is only called by dlm_recoverd, and we rely on dlm_ls_stop() stopping + dlm_recoverd before checking/setting ls_recover_begin. */ + +void dlm_adjust_timeouts(struct dlm_ls *ls) +{ + struct dlm_lkb *lkb; + long adj = jiffies - ls->ls_recover_begin; + + ls->ls_recover_begin = 0; + mutex_lock(&ls->ls_timeout_mutex); + list_for_each_entry(lkb, &ls->ls_timeout, lkb_time_list) + lkb->lkb_timestamp += adj; + mutex_unlock(&ls->ls_timeout_mutex); +} + /* lkb is master or local copy */ static void set_lvb_lock(struct dlm_rsb *r, struct dlm_lkb *lkb) @@ -1275,10 +1414,8 @@ static int queue_conflict(struct list_head *head, struct dlm_lkb *lkb) * queue for one resource. The granted mode of each lock blocks the requested * mode of the other lock." * - * Part 2: if the granted mode of lkb is preventing the first lkb in the - * convert queue from being granted, then demote lkb (set grmode to NL). - * This second form requires that we check for conv-deadlk even when - * now == 0 in _can_be_granted(). + * Part 2: if the granted mode of lkb is preventing an earlier lkb in the + * convert queue from being granted, then deadlk/demote lkb. * * Example: * Granted Queue: empty @@ -1287,41 +1424,52 @@ static int queue_conflict(struct list_head *head, struct dlm_lkb *lkb) * * The first lock can't be granted because of the granted mode of the second * lock and the second lock can't be granted because it's not first in the - * list. We demote the granted mode of the second lock (the lkb passed to this - * function). + * list. We either cancel lkb's conversion (PR->EX) and return EDEADLK, or we + * demote the granted mode of lkb (from PR to NL) if it has the CONVDEADLK + * flag set and return DEMOTED in the lksb flags. + * + * Originally, this function detected conv-deadlk in a more limited scope: + * - if !modes_compat(lkb1, lkb2) && !modes_compat(lkb2, lkb1), or + * - if lkb1 was the first entry in the queue (not just earlier), and was + * blocked by the granted mode of lkb2, and there was nothing on the + * granted queue preventing lkb1 from being granted immediately, i.e. + * lkb2 was the only thing preventing lkb1 from being granted. + * + * That second condition meant we'd only say there was conv-deadlk if + * resolving it (by demotion) would lead to the first lock on the convert + * queue being granted right away. It allowed conversion deadlocks to exist + * between locks on the convert queue while they couldn't be granted anyway. * - * After the resolution, the "grant pending" function needs to go back and try - * to grant locks on the convert queue again since the first lock can now be - * granted. + * Now, we detect and take action on conversion deadlocks immediately when + * they're created, even if they may not be immediately consequential. If + * lkb1 exists anywhere in the convert queue and lkb2 comes in with a granted + * mode that would prevent lkb1's conversion from being granted, we do a + * deadlk/demote on lkb2 right away and don't let it onto the convert queue. + * I think this means that the lkb_is_ahead condition below should always + * be zero, i.e. there will never be conv-deadlk between two locks that are + * both already on the convert queue. */ -static int conversion_deadlock_detect(struct dlm_rsb *rsb, struct dlm_lkb *lkb) +static int conversion_deadlock_detect(struct dlm_rsb *r, struct dlm_lkb *lkb2) { - struct dlm_lkb *this, *first = NULL, *self = NULL; + struct dlm_lkb *lkb1; + int lkb_is_ahead = 0; - list_for_each_entry(this, &rsb->res_convertqueue, lkb_statequeue) { - if (!first) - first = this; - if (this == lkb) { - self = lkb; + list_for_each_entry(lkb1, &r->res_convertqueue, lkb_statequeue) { + if (lkb1 == lkb2) { + lkb_is_ahead = 1; continue; } - if (!modes_compat(this, lkb) && !modes_compat(lkb, this)) - return 1; - } - - /* if lkb is on the convert queue and is preventing the first - from being granted, then there's deadlock and we demote lkb. - multiple converting locks may need to do this before the first - converting lock can be granted. */ - - if (self && self != first) { - if (!modes_compat(lkb, first) && - !queue_conflict(&rsb->res_grantqueue, first)) - return 1; + if (!lkb_is_ahead) { + if (!modes_compat(lkb2, lkb1)) + return 1; + } else { + if (!modes_compat(lkb2, lkb1) && + !modes_compat(lkb1, lkb2)) + return 1; + } } - return 0; } @@ -1450,42 +1598,57 @@ static int _can_be_granted(struct dlm_rsb *r, struct dlm_lkb *lkb, int now) if (!now && !conv && list_empty(&r->res_convertqueue) && first_in_list(lkb, &r->res_waitqueue)) return 1; - out: - /* - * The following, enabled by CONVDEADLK, departs from VMS. - */ - - if (conv && (lkb->lkb_exflags & DLM_LKF_CONVDEADLK) && - conversion_deadlock_detect(r, lkb)) { - lkb->lkb_grmode = DLM_LOCK_NL; - lkb->lkb_sbflags |= DLM_SBF_DEMOTED; - } - return 0; } -/* - * The ALTPR and ALTCW flags aren't traditional lock manager flags, but are a - * simple way to provide a big optimization to applications that can use them. - */ - -static int can_be_granted(struct dlm_rsb *r, struct dlm_lkb *lkb, int now) +static int can_be_granted(struct dlm_rsb *r, struct dlm_lkb *lkb, int now, + int *err) { - uint32_t flags = lkb->lkb_exflags; int rv; int8_t alt = 0, rqmode = lkb->lkb_rqmode; + int8_t is_convert = (lkb->lkb_grmode != DLM_LOCK_IV); + + if (err) + *err = 0; rv = _can_be_granted(r, lkb, now); if (rv) goto out; - if (lkb->lkb_sbflags & DLM_SBF_DEMOTED) + /* + * The CONVDEADLK flag is non-standard and tells the dlm to resolve + * conversion deadlocks by demoting grmode to NL, otherwise the dlm + * cancels one of the locks. + */ + + if (is_convert && can_be_queued(lkb) && + conversion_deadlock_detect(r, lkb)) { + if (lkb->lkb_exflags & DLM_LKF_CONVDEADLK) { + lkb->lkb_grmode = DLM_LOCK_NL; + lkb->lkb_sbflags |= DLM_SBF_DEMOTED; + } else if (!(lkb->lkb_exflags & DLM_LKF_NODLCKWT)) { + if (err) + *err = -EDEADLK; + else { + log_print("can_be_granted deadlock %x now %d", + lkb->lkb_id, now); + dlm_dump_rsb(r); + } + } goto out; + } - if (rqmode != DLM_LOCK_PR && flags & DLM_LKF_ALTPR) + /* + * The ALTPR and ALTCW flags are non-standard and tell the dlm to try + * to grant a request in a mode other than the normal rqmode. It's a + * simple way to provide a big optimization to applications that can + * use them. + */ + + if (rqmode != DLM_LOCK_PR && (lkb->lkb_exflags & DLM_LKF_ALTPR)) alt = DLM_LOCK_PR; - else if (rqmode != DLM_LOCK_CW && flags & DLM_LKF_ALTCW) + else if (rqmode != DLM_LOCK_CW && (lkb->lkb_exflags & DLM_LKF_ALTCW)) alt = DLM_LOCK_CW; if (alt) { @@ -1500,10 +1663,20 @@ static int can_be_granted(struct dlm_rsb *r, struct dlm_lkb *lkb, int now) return rv; } +/* FIXME: I don't think that can_be_granted() can/will demote or find deadlock + for locks pending on the convert list. Once verified (watch for these + log_prints), we should be able to just call _can_be_granted() and not + bother with the demote/deadlk cases here (and there's no easy way to deal + with a deadlk here, we'd have to generate something like grant_lock with + the deadlk error.) */ + +/* returns the highest requested mode of all blocked conversions */ + static int grant_pending_convert(struct dlm_rsb *r, int high) { struct dlm_lkb *lkb, *s; int hi, demoted, quit, grant_restart, demote_restart; + int deadlk; quit = 0; restart: @@ -1513,14 +1686,29 @@ static int grant_pending_convert(struct dlm_rsb *r, int high) list_for_each_entry_safe(lkb, s, &r->res_convertqueue, lkb_statequeue) { demoted = is_demoted(lkb); - if (can_be_granted(r, lkb, 0)) { + deadlk = 0; + + if (can_be_granted(r, lkb, 0, &deadlk)) { grant_lock_pending(r, lkb); grant_restart = 1; - } else { - hi = max_t(int, lkb->lkb_rqmode, hi); - if (!demoted && is_demoted(lkb)) - demote_restart = 1; + continue; } + + if (!demoted && is_demoted(lkb)) { + log_print("WARN: pending demoted %x node %d %s", + lkb->lkb_id, lkb->lkb_nodeid, r->res_name); + demote_restart = 1; + continue; + } + + if (deadlk) { + log_print("WARN: pending deadlock %x node %d %s", + lkb->lkb_id, lkb->lkb_nodeid, r->res_name); + dlm_dump_rsb(r); + continue; + } + + hi = max_t(int, lkb->lkb_rqmode, hi); } if (grant_restart) @@ -1538,7 +1726,7 @@ static int grant_pending_wait(struct dlm_rsb *r, int high) struct dlm_lkb *lkb, *s; list_for_each_entry_safe(lkb, s, &r->res_waitqueue, lkb_statequeue) { - if (can_be_granted(r, lkb, 0)) + if (can_be_granted(r, lkb, 0, NULL)) grant_lock_pending(r, lkb); else high = max_t(int, lkb->lkb_rqmode, high); @@ -1733,7 +1921,7 @@ static void confirm_master(struct dlm_rsb *r, int error) } static int set_lock_args(int mode, struct dlm_lksb *lksb, uint32_t flags, - int namelen, uint32_t parent_lkid, void *ast, + int namelen, unsigned long timeout_cs, void *ast, void *astarg, void *bast, struct dlm_args *args) { int rv = -EINVAL; @@ -1776,10 +1964,6 @@ static int set_lock_args(int mode, struct dlm_lksb *lksb, uint32_t flags, if (flags & DLM_LKF_VALBLK && !lksb->sb_lvbptr) goto out; - /* parent/child locks not yet supported */ - if (parent_lkid) - goto out; - if (flags & DLM_LKF_CONVERT && !lksb->sb_lkid) goto out; @@ -1791,6 +1975,7 @@ static int set_lock_args(int mode, struct dlm_lksb *lksb, uint32_t flags, args->astaddr = ast; args->astparam = (long) astarg; args->bastaddr = bast; + args->timeout = timeout_cs; args->mode = mode; args->lksb = lksb; rv = 0; @@ -1845,6 +2030,7 @@ static int validate_lock_args(struct dlm_ls *ls, struct dlm_lkb *lkb, lkb->lkb_lksb = args->lksb; lkb->lkb_lvbptr = args->lksb->sb_lvbptr; lkb->lkb_ownpid = (int) current->pid; + lkb->lkb_timeout_cs = args->timeout; rv = 0; out: return rv; @@ -1903,6 +2089,9 @@ static int validate_unlock_args(struct dlm_lkb *lkb, struct dlm_args *args) if (is_overlap(lkb)) goto out; + /* don't let scand try to do a cancel */ + del_timeout(lkb); + if (lkb->lkb_flags & DLM_IFL_RESEND) { lkb->lkb_flags |= DLM_IFL_OVERLAP_CANCEL; rv = -EBUSY; @@ -1934,6 +2123,9 @@ static int validate_unlock_args(struct dlm_lkb *lkb, struct dlm_args *args) if (is_overlap_unlock(lkb)) goto out; + /* don't let scand try to do a cancel */ + del_timeout(lkb); + if (lkb->lkb_flags & DLM_IFL_RESEND) { lkb->lkb_flags |= DLM_IFL_OVERLAP_UNLOCK; rv = -EBUSY; @@ -1984,7 +2176,7 @@ static int do_request(struct dlm_rsb *r, struct dlm_lkb *lkb) { int error = 0; - if (can_be_granted(r, lkb, 1)) { + if (can_be_granted(r, lkb, 1, NULL)) { grant_lock(r, lkb); queue_cast(r, lkb, 0); goto out; @@ -1994,6 +2186,7 @@ static int do_request(struct dlm_rsb *r, struct dlm_lkb *lkb) error = -EINPROGRESS; add_lkb(r, lkb, DLM_LKSTS_WAITING); send_blocking_asts(r, lkb); + add_timeout(lkb); goto out; } @@ -2009,16 +2202,32 @@ static int do_request(struct dlm_rsb *r, struct dlm_lkb *lkb) static int do_convert(struct dlm_rsb *r, struct dlm_lkb *lkb) { int error = 0; + int deadlk = 0; /* changing an existing lock may allow others to be granted */ - if (can_be_granted(r, lkb, 1)) { + if (can_be_granted(r, lkb, 1, &deadlk)) { grant_lock(r, lkb); queue_cast(r, lkb, 0); grant_pending_locks(r); goto out; } + /* can_be_granted() detected that this lock would block in a conversion + deadlock, so we leave it on the granted queue and return EDEADLK in + the ast for the convert. */ + + if (deadlk) { + /* it's left on the granted queue */ + log_debug(r->res_ls, "deadlock %x node %d sts%d g%d r%d %s", + lkb->lkb_id, lkb->lkb_nodeid, lkb->lkb_status, + lkb->lkb_grmode, lkb->lkb_rqmode, r->res_name); + revert_lock(r, lkb); + queue_cast(r, lkb, -EDEADLK); + error = -EDEADLK; + goto out; + } + /* is_demoted() means the can_be_granted() above set the grmode to NL, and left us on the granted queue. This auto-demotion (due to CONVDEADLK) might mean other locks, and/or this lock, are @@ -2041,6 +2250,7 @@ static int do_convert(struct dlm_rsb *r, struct dlm_lkb *lkb) del_lkb(r, lkb); add_lkb(r, lkb, DLM_LKSTS_CONVERT); send_blocking_asts(r, lkb); + add_timeout(lkb); goto out; } @@ -2274,7 +2484,7 @@ int dlm_lock(dlm_lockspace_t *lockspace, if (!ls) return -EINVAL; - lock_recovery(ls); + dlm_lock_recovery(ls); if (convert) error = find_lkb(ls, lksb->sb_lkid, &lkb); @@ -2284,7 +2494,7 @@ int dlm_lock(dlm_lockspace_t *lockspace, if (error) goto out; - error = set_lock_args(mode, lksb, flags, namelen, parent_lkid, ast, + error = set_lock_args(mode, lksb, flags, namelen, 0, ast, astarg, bast, &args); if (error) goto out_put; @@ -2299,10 +2509,10 @@ int dlm_lock(dlm_lockspace_t *lockspace, out_put: if (convert || error) __put_lkb(ls, lkb); - if (error == -EAGAIN) + if (error == -EAGAIN || error == -EDEADLK) error = 0; out: - unlock_recovery(ls); + dlm_unlock_recovery(ls); dlm_put_lockspace(ls); return error; } @@ -2322,7 +2532,7 @@ int dlm_unlock(dlm_lockspace_t *lockspace, if (!ls) return -EINVAL; - lock_recovery(ls); + dlm_lock_recovery(ls); error = find_lkb(ls, lkid, &lkb); if (error) @@ -2344,7 +2554,7 @@ int dlm_unlock(dlm_lockspace_t *lockspace, out_put: dlm_put_lkb(lkb); out: - unlock_recovery(ls); + dlm_unlock_recovery(ls); dlm_put_lockspace(ls); return error; } @@ -2384,7 +2594,7 @@ static int _create_message(struct dlm_ls *ls, int mb_len, pass into lowcomms_commit and a message buffer (mb) that we write our data into */ - mh = dlm_lowcomms_get_buffer(to_nodeid, mb_len, GFP_KERNEL, &mb); + mh = dlm_lowcomms_get_buffer(to_nodeid, mb_len, ls->ls_allocation, &mb); if (!mh) return -ENOBUFS; @@ -3111,9 +3321,10 @@ static void receive_request_reply(struct dlm_ls *ls, struct dlm_message *ms) lkb->lkb_remid = ms->m_lkid; if (is_altmode(lkb)) munge_altmode(lkb, ms); - if (result) + if (result) { add_lkb(r, lkb, DLM_LKSTS_WAITING); - else { + add_timeout(lkb); + } else { grant_lock_pc(r, lkb, ms); queue_cast(r, lkb, 0); } @@ -3172,6 +3383,12 @@ static void __receive_convert_reply(struct dlm_rsb *r, struct dlm_lkb *lkb, queue_cast(r, lkb, -EAGAIN); break; + case -EDEADLK: + receive_flags_reply(lkb, ms); + revert_lock_pc(r, lkb); + queue_cast(r, lkb, -EDEADLK); + break; + case -EINPROGRESS: /* convert was queued on remote master */ receive_flags_reply(lkb, ms); @@ -3179,6 +3396,7 @@ static void __receive_convert_reply(struct dlm_rsb *r, struct dlm_lkb *lkb, munge_demoted(lkb, ms); del_lkb(r, lkb); add_lkb(r, lkb, DLM_LKSTS_CONVERT); + add_timeout(lkb); break; case 0: @@ -3298,8 +3516,7 @@ static void _receive_cancel_reply(struct dlm_lkb *lkb, struct dlm_message *ms) case -DLM_ECANCEL: receive_flags_reply(lkb, ms); revert_lock_pc(r, lkb); - if (ms->m_result) - queue_cast(r, lkb, -DLM_ECANCEL); + queue_cast(r, lkb, -DLM_ECANCEL); break; case 0: break; @@ -3424,7 +3641,7 @@ int dlm_receive_message(struct dlm_header *hd, int nodeid, int recovery) } } - if (lock_recovery_try(ls)) + if (dlm_lock_recovery_try(ls)) break; schedule(); } @@ -3503,7 +3720,7 @@ int dlm_receive_message(struct dlm_header *hd, int nodeid, int recovery) log_error(ls, "unknown message type %d", ms->m_type); } - unlock_recovery(ls); + dlm_unlock_recovery(ls); out: dlm_put_lockspace(ls); dlm_astd_wake(); @@ -4034,13 +4251,13 @@ int dlm_recover_process_copy(struct dlm_ls *ls, struct dlm_rcom *rc) int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua, int mode, uint32_t flags, void *name, unsigned int namelen, - uint32_t parent_lkid) + unsigned long timeout_cs) { struct dlm_lkb *lkb; struct dlm_args args; int error; - lock_recovery(ls); + dlm_lock_recovery(ls); error = create_lkb(ls, &lkb); if (error) { @@ -4062,7 +4279,7 @@ int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua, When DLM_IFL_USER is set, the dlm knows that this is a userspace lock and that lkb_astparam is the dlm_user_args structure. */ - error = set_lock_args(mode, &ua->lksb, flags, namelen, parent_lkid, + error = set_lock_args(mode, &ua->lksb, flags, namelen, timeout_cs, DLM_FAKE_USER_AST, ua, DLM_FAKE_USER_AST, &args); lkb->lkb_flags |= DLM_IFL_USER; ua->old_mode = DLM_LOCK_IV; @@ -4094,19 +4311,20 @@ int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua, list_add_tail(&lkb->lkb_ownqueue, &ua->proc->locks); spin_unlock(&ua->proc->locks_spin); out: - unlock_recovery(ls); + dlm_unlock_recovery(ls); return error; } int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp, - int mode, uint32_t flags, uint32_t lkid, char *lvb_in) + int mode, uint32_t flags, uint32_t lkid, char *lvb_in, + unsigned long timeout_cs) { struct dlm_lkb *lkb; struct dlm_args args; struct dlm_user_args *ua; int error; - lock_recovery(ls); + dlm_lock_recovery(ls); error = find_lkb(ls, lkid, &lkb); if (error) @@ -4127,6 +4345,7 @@ int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp, if (lvb_in && ua->lksb.sb_lvbptr) memcpy(ua->lksb.sb_lvbptr, lvb_in, DLM_USER_LVB_LEN); + ua->xid = ua_tmp->xid; ua->castparam = ua_tmp->castparam; ua->castaddr = ua_tmp->castaddr; ua->bastparam = ua_tmp->bastparam; @@ -4134,19 +4353,19 @@ int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp, ua->user_lksb = ua_tmp->user_lksb; ua->old_mode = lkb->lkb_grmode; - error = set_lock_args(mode, &ua->lksb, flags, 0, 0, DLM_FAKE_USER_AST, - ua, DLM_FAKE_USER_AST, &args); + error = set_lock_args(mode, &ua->lksb, flags, 0, timeout_cs, + DLM_FAKE_USER_AST, ua, DLM_FAKE_USER_AST, &args); if (error) goto out_put; error = convert_lock(ls, lkb, &args); - if (error == -EINPROGRESS || error == -EAGAIN) + if (error == -EINPROGRESS || error == -EAGAIN || error == -EDEADLK) error = 0; out_put: dlm_put_lkb(lkb); out: - unlock_recovery(ls); + dlm_unlock_recovery(ls); kfree(ua_tmp); return error; } @@ -4159,7 +4378,7 @@ int dlm_user_unlock(struct dlm_ls *ls, struct dlm_user_args *ua_tmp, struct dlm_user_args *ua; int error; - lock_recovery(ls); + dlm_lock_recovery(ls); error = find_lkb(ls, lkid, &lkb); if (error) @@ -4194,7 +4413,7 @@ int dlm_user_unlock(struct dlm_ls *ls, struct dlm_user_args *ua_tmp, out_put: dlm_put_lkb(lkb); out: - unlock_recovery(ls); + dlm_unlock_recovery(ls); kfree(ua_tmp); return error; } @@ -4207,7 +4426,7 @@ int dlm_user_cancel(struct dlm_ls *ls, struct dlm_user_args *ua_tmp, struct dlm_user_args *ua; int error; - lock_recovery(ls); + dlm_lock_recovery(ls); error = find_lkb(ls, lkid, &lkb); if (error) @@ -4231,11 +4450,59 @@ int dlm_user_cancel(struct dlm_ls *ls, struct dlm_user_args *ua_tmp, out_put: dlm_put_lkb(lkb); out: - unlock_recovery(ls); + dlm_unlock_recovery(ls); kfree(ua_tmp); return error; } +int dlm_user_deadlock(struct dlm_ls *ls, uint32_t flags, uint32_t lkid) +{ + struct dlm_lkb *lkb; + struct dlm_args args; + struct dlm_user_args *ua; + struct dlm_rsb *r; + int error; + + dlm_lock_recovery(ls); + + error = find_lkb(ls, lkid, &lkb); + if (error) + goto out; + + ua = (struct dlm_user_args *)lkb->lkb_astparam; + + error = set_unlock_args(flags, ua, &args); + if (error) + goto out_put; + + /* same as cancel_lock(), but set DEADLOCK_CANCEL after lock_rsb */ + + r = lkb->lkb_resource; + hold_rsb(r); + lock_rsb(r); + + error = validate_unlock_args(lkb, &args); + if (error) + goto out_r; + lkb->lkb_flags |= DLM_IFL_DEADLOCK_CANCEL; + + error = _cancel_lock(r, lkb); + out_r: + unlock_rsb(r); + put_rsb(r); + + if (error == -DLM_ECANCEL) + error = 0; + /* from validate_unlock_args() */ + if (error == -EBUSY) + error = 0; + out_put: + dlm_put_lkb(lkb); + out: + dlm_unlock_recovery(ls); + return error; +} + /* lkb's that are removed from the waiters list by revert are just left on the orphans list with the granted orphan locks, to be freed by purge */ @@ -4314,12 +4581,13 @@ void dlm_clear_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc) { struct dlm_lkb *lkb, *safe; - lock_recovery(ls); + dlm_lock_recovery(ls); while (1) { lkb = del_proc_lock(ls, proc); if (!lkb) break; + del_timeout(lkb); if (lkb->lkb_exflags & DLM_LKF_PERSISTENT) orphan_proc_lock(ls, lkb); else @@ -4347,7 +4615,7 @@ void dlm_clear_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc) } mutex_unlock(&ls->ls_clear_proc_locks); - unlock_recovery(ls); + dlm_unlock_recovery(ls); } static void purge_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc) @@ -4429,12 +4697,12 @@ int dlm_user_purge(struct dlm_ls *ls, struct dlm_user_proc *proc, if (nodeid != dlm_our_nodeid()) { error = send_purge(ls, nodeid, pid); } else { - lock_recovery(ls); + dlm_lock_recovery(ls); if (pid == current->pid) purge_proc_locks(ls, proc); else do_purge(ls, nodeid, pid); - unlock_recovery(ls); + dlm_unlock_recovery(ls); } return error; } diff --git a/fs/dlm/lock.h b/fs/dlm/lock.h index 64fc4ec4066..1720313c22d 100644 --- a/fs/dlm/lock.h +++ b/fs/dlm/lock.h @@ -1,7 +1,7 @@ /****************************************************************************** ******************************************************************************* ** -** Copyright (C) 2005 Red Hat, Inc. All rights reserved. +** Copyright (C) 2005-2007 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 @@ -24,6 +24,10 @@ void dlm_put_rsb(struct dlm_rsb *r); void dlm_hold_rsb(struct dlm_rsb *r); int dlm_put_lkb(struct dlm_lkb *lkb); void dlm_scan_rsbs(struct dlm_ls *ls); +int dlm_lock_recovery_try(struct dlm_ls *ls); +void dlm_unlock_recovery(struct dlm_ls *ls); +void dlm_scan_timeout(struct dlm_ls *ls); +void dlm_adjust_timeouts(struct dlm_ls *ls); int dlm_purge_locks(struct dlm_ls *ls); void dlm_purge_mstcpy_locks(struct dlm_rsb *r); @@ -34,15 +38,18 @@ int dlm_recover_master_copy(struct dlm_ls *ls, struct dlm_rcom *rc); int dlm_recover_process_copy(struct dlm_ls *ls, struct dlm_rcom *rc); int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua, int mode, - uint32_t flags, void *name, unsigned int namelen, uint32_t parent_lkid); + uint32_t flags, void *name, unsigned int namelen, + unsigned long timeout_cs); int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp, - int mode, uint32_t flags, uint32_t lkid, char *lvb_in); + int mode, uint32_t flags, uint32_t lkid, char *lvb_in, + unsigned long timeout_cs); int dlm_user_unlock(struct dlm_ls *ls, struct dlm_user_args *ua_tmp, uint32_t flags, uint32_t lkid, char *lvb_in); int dlm_user_cancel(struct dlm_ls *ls, struct dlm_user_args *ua_tmp, uint32_t flags, uint32_t lkid); int dlm_user_purge(struct dlm_ls *ls, struct dlm_user_proc *proc, int nodeid, int pid); +int dlm_user_deadlock(struct dlm_ls *ls, uint32_t flags, uint32_t lkid); void dlm_clear_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc); static inline int is_master(struct dlm_rsb *r) diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index a677b2a5eed..1dc72105ab1 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -197,13 +197,24 @@ static int do_uevent(struct dlm_ls *ls, int in) else kobject_uevent(&ls->ls_kobj, KOBJ_OFFLINE); + log_debug(ls, "%s the lockspace group...", in ? "joining" : "leaving"); + + /* dlm_controld will see the uevent, do the necessary group management + and then write to sysfs to wake us */ + error = wait_event_interruptible(ls->ls_uevent_wait, test_and_clear_bit(LSFL_UEVENT_WAIT, &ls->ls_flags)); + + log_debug(ls, "group event done %d %d", error, ls->ls_uevent_result); + if (error) goto out; error = ls->ls_uevent_result; out: + if (error) + log_error(ls, "group %s failed %d %d", in ? "join" : "leave", + error, ls->ls_uevent_result); return error; } @@ -234,8 +245,13 @@ static int dlm_scand(void *data) struct dlm_ls *ls; while (!kthread_should_stop()) { - list_for_each_entry(ls, &lslist, ls_list) - dlm_scan_rsbs(ls); + list_for_each_entry(ls, &lslist, ls_list) { + if (dlm_lock_recovery_try(ls)) { + dlm_scan_rsbs(ls); + dlm_scan_timeout(ls); + dlm_unlock_recovery(ls); + } + } schedule_timeout_interruptible(dlm_config.ci_scan_secs * HZ); } return 0; @@ -395,6 +411,7 @@ static int new_lockspace(char *name, int namelen, void **lockspace, { struct dlm_ls *ls; int i, size, error = -ENOMEM; + int do_unreg = 0; if (namelen > DLM_LOCKSPACE_LEN) return -EINVAL; @@ -417,11 +434,22 @@ static int new_lockspace(char *name, int namelen, void **lockspace, goto out; memcpy(ls->ls_name, name, namelen); ls->ls_namelen = namelen; - ls->ls_exflags = flags; ls->ls_lvblen = lvblen; ls->ls_count = 0; ls->ls_flags = 0; + if (flags & DLM_LSFL_TIMEWARN) + set_bit(LSFL_TIMEWARN, &ls->ls_flags); + + if (flags & DLM_LSFL_FS) + ls->ls_allocation = GFP_NOFS; + else + ls->ls_allocation = GFP_KERNEL; + + /* ls_exflags are forced to match among nodes, and we don't + need to require all nodes to have TIMEWARN or FS set */ + ls->ls_exflags = (flags & ~(DLM_LSFL_TIMEWARN | DLM_LSFL_FS)); + size = dlm_config.ci_rsbtbl_size; ls->ls_rsbtbl_size = size; @@ -461,6 +489,8 @@ static int new_lockspace(char *name, int namelen, void **lockspace, mutex_init(&ls->ls_waiters_mutex); INIT_LIST_HEAD(&ls->ls_orphans); mutex_init(&ls->ls_orphans_mutex); + INIT_LIST_HEAD(&ls->ls_timeout); + mutex_init(&ls->ls_timeout_mutex); INIT_LIST_HEAD(&ls->ls_nodes); INIT_LIST_HEAD(&ls->ls_nodes_gone); @@ -477,6 +507,8 @@ static int new_lockspace(char *name, int namelen, void **lockspace, init_waitqueue_head(&ls->ls_uevent_wait); ls->ls_uevent_result = 0; + init_completion(&ls->ls_members_done); + ls->ls_members_result = -1; ls->ls_recoverd_task = NULL; mutex_init(&ls->ls_recoverd_active); @@ -513,32 +545,49 @@ static int new_lockspace(char *name, int namelen, void **lockspace, error = dlm_recoverd_start(ls); if (error) { log_error(ls, "can't start dlm_recoverd %d", error); - goto out_rcomfree; + goto out_delist; } - dlm_create_debug_file(ls); - error = kobject_setup(ls); if (error) - goto out_del; + goto out_stop; error = kobject_register(&ls->ls_kobj); if (error) - goto out_del; + goto out_stop; + + /* let kobject handle freeing of ls if there's an error */ + do_unreg = 1; + + /* This uevent triggers dlm_controld in userspace to add us to the + group of nodes that are members of this lockspace (managed by the + cluster infrastructure.) Once it's done that, it tells us who the + current lockspace members are (via configfs) and then tells the + lockspace to start running (via sysfs) in dlm_ls_start(). */ error = do_uevent(ls, 1); if (error) - goto out_unreg; + goto out_stop; + + wait_for_completion(&ls->ls_members_done); + error = ls->ls_members_result; + if (error) + goto out_members; + + dlm_create_debug_file(ls); + + log_debug(ls, "join complete"); *lockspace = ls; return 0; - out_unreg: - kobject_unregister(&ls->ls_kobj); - out_del: - dlm_delete_debug_file(ls); + out_members: + do_uevent(ls, 0); + dlm_clear_members(ls); + kfree(ls->ls_node_array); + out_stop: dlm_recoverd_stop(ls); - out_rcomfree: + out_delist: spin_lock(&lslist_lock); list_del(&ls->ls_list); spin_unlock(&lslist_lock); @@ -550,7 +599,10 @@ static int new_lockspace(char *name, int namelen, void **lockspace, out_rsbfree: kfree(ls->ls_rsbtbl); out_lsfree: - kfree(ls); + if (do_unreg) + kobject_unregister(&ls->ls_kobj); + else + kfree(ls); out: module_put(THIS_MODULE); return error; @@ -570,6 +622,8 @@ int dlm_new_lockspace(char *name, int namelen, void **lockspace, error = new_lockspace(name, namelen, lockspace, flags, lvblen); if (!error) ls_count++; + else if (!ls_count) + threads_stop(); out: mutex_unlock(&ls_lock); return error; @@ -696,7 +750,7 @@ static int release_lockspace(struct dlm_ls *ls, int force) dlm_clear_members_gone(ls); kfree(ls->ls_node_array); kobject_unregister(&ls->ls_kobj); - /* The ls structure will be freed when the kobject is done with */ + /* The ls structure will be freed when the kobject is done with */ mutex_lock(&ls_lock); ls_count--; diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 27970a58d29..0553a6158dc 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -260,7 +260,7 @@ static int nodeid_to_addr(int nodeid, struct sockaddr *retaddr) static void lowcomms_data_ready(struct sock *sk, int count_unused) { struct connection *con = sock2con(sk); - if (!test_and_set_bit(CF_READ_PENDING, &con->flags)) + if (con && !test_and_set_bit(CF_READ_PENDING, &con->flags)) queue_work(recv_workqueue, &con->rwork); } @@ -268,7 +268,7 @@ static void lowcomms_write_space(struct sock *sk) { struct connection *con = sock2con(sk); - if (!test_and_set_bit(CF_WRITE_PENDING, &con->flags)) + if (con && !test_and_set_bit(CF_WRITE_PENDING, &con->flags)) queue_work(send_workqueue, &con->swork); } @@ -720,11 +720,17 @@ static int tcp_accept_from_sock(struct connection *con) INIT_WORK(&othercon->rwork, process_recv_sockets); set_bit(CF_IS_OTHERCON, &othercon->flags); newcon->othercon = othercon; + othercon->sock = newsock; + newsock->sk->sk_user_data = othercon; + add_sock(newsock, othercon); + addcon = othercon; + } + else { + printk("Extra connection from node %d attempted\n", nodeid); + result = -EAGAIN; + mutex_unlock(&newcon->sock_mutex); + goto accept_err; } - othercon->sock = newsock; - newsock->sk->sk_user_data = othercon; - add_sock(newsock, othercon); - addcon = othercon; } else { newsock->sk->sk_user_data = newcon; @@ -1400,8 +1406,11 @@ void dlm_lowcomms_stop(void) down(&connections_lock); for (i = 0; i <= max_nodeid; i++) { con = __nodeid2con(i, 0); - if (con) + if (con) { con->flags |= 0xFF; + if (con->sock) + con->sock->sk->sk_user_data = NULL; + } } up(&connections_lock); diff --git a/fs/dlm/main.c b/fs/dlm/main.c index 162fbae58fe..eca2907f238 100644 --- a/fs/dlm/main.c +++ b/fs/dlm/main.c @@ -2,7 +2,7 @@ ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. -** Copyright (C) 2004-2005 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 @@ -25,6 +25,8 @@ void dlm_unregister_debugfs(void); static inline int dlm_register_debugfs(void) { return 0; } static inline void dlm_unregister_debugfs(void) { } #endif +int dlm_netlink_init(void); +void dlm_netlink_exit(void); static int __init init_dlm(void) { @@ -50,10 +52,16 @@ static int __init init_dlm(void) if (error) goto out_debug; + error = dlm_netlink_init(); + if (error) + goto out_user; + printk("DLM (built %s %s) installed\n", __DATE__, __TIME__); return 0; + out_user: + dlm_user_exit(); out_debug: dlm_unregister_debugfs(); out_config: @@ -68,6 +76,7 @@ static int __init init_dlm(void) static void __exit exit_dlm(void) { + dlm_netlink_exit(); dlm_user_exit(); dlm_config_exit(); dlm_memory_exit(); diff --git a/fs/dlm/member.c b/fs/dlm/member.c index 85e2897bd74..073599dced2 100644 --- a/fs/dlm/member.c +++ b/fs/dlm/member.c @@ -1,7 +1,7 @@ /****************************************************************************** ******************************************************************************* ** -** Copyright (C) 2005 Red Hat, Inc. All rights reserved. +** Copyright (C) 2005-2007 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 @@ -233,6 +233,12 @@ int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv, int *neg_out) *neg_out = neg; error = ping_members(ls); + if (!error || error == -EPROTO) { + /* new_lockspace() may be waiting to know if the config + is good or bad */ + ls->ls_members_result = error; + complete(&ls->ls_members_done); + } if (error) goto out; @@ -284,6 +290,9 @@ int dlm_ls_stop(struct dlm_ls *ls) dlm_recoverd_suspend(ls); ls->ls_recover_status = 0; dlm_recoverd_resume(ls); + + if (!ls->ls_recover_begin) + ls->ls_recover_begin = jiffies; return 0; } diff --git a/fs/dlm/netlink.c b/fs/dlm/netlink.c new file mode 100644 index 00000000000..863b87d0dc7 --- /dev/null +++ b/fs/dlm/netlink.c @@ -0,0 +1,153 @@ +/* + * Copyright (C) 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 + * of the GNU General Public License v.2. + */ + +#include <net/genetlink.h> +#include <linux/dlm.h> +#include <linux/dlm_netlink.h> + +#include "dlm_internal.h" + +static uint32_t dlm_nl_seqnum; +static uint32_t listener_nlpid; + +static struct genl_family family = { + .id = GENL_ID_GENERATE, + .name = DLM_GENL_NAME, + .version = DLM_GENL_VERSION, +}; + +static int prepare_data(u8 cmd, struct sk_buff **skbp, size_t size) +{ + struct sk_buff *skb; + void *data; + + skb = genlmsg_new(size, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + /* add the message headers */ + data = genlmsg_put(skb, 0, dlm_nl_seqnum++, &family, 0, cmd); + if (!data) { + nlmsg_free(skb); + return -EINVAL; + } + + *skbp = skb; + return 0; +} + +static struct dlm_lock_data *mk_data(struct sk_buff *skb) +{ + struct nlattr *ret; + + ret = nla_reserve(skb, DLM_TYPE_LOCK, sizeof(struct dlm_lock_data)); + if (!ret) + return NULL; + return nla_data(ret); +} + +static int send_data(struct sk_buff *skb) +{ + struct genlmsghdr *genlhdr = nlmsg_data((struct nlmsghdr *)skb->data); + void *data = genlmsg_data(genlhdr); + int rv; + + rv = genlmsg_end(skb, data); + if (rv < 0) { + nlmsg_free(skb); + return rv; + } + + return genlmsg_unicast(skb, listener_nlpid); +} + +static int user_cmd(struct sk_buff *skb, struct genl_info *info) +{ + listener_nlpid = info->snd_pid; + printk("user_cmd nlpid %u\n", listener_nlpid); + return 0; +} + +static struct genl_ops dlm_nl_ops = { + .cmd = DLM_CMD_HELLO, + .doit = user_cmd, +}; + +int dlm_netlink_init(void) +{ + int rv; + + rv = genl_register_family(&family); + if (rv) + return rv; + + rv = genl_register_ops(&family, &dlm_nl_ops); + if (rv < 0) + goto err; + return 0; + err: + genl_unregister_family(&family); + return rv; +} + +void dlm_netlink_exit(void) +{ + genl_unregister_ops(&family, &dlm_nl_ops); + genl_unregister_family(&family); +} + +static void fill_data(struct dlm_lock_data *data, struct dlm_lkb *lkb) +{ + struct dlm_rsb *r = lkb->lkb_resource; + struct dlm_user_args *ua = (struct dlm_user_args *) lkb->lkb_astparam; + + memset(data, 0, sizeof(struct dlm_lock_data)); + + data->version = DLM_LOCK_DATA_VERSION; + data->nodeid = lkb->lkb_nodeid; + data->ownpid = lkb->lkb_ownpid; + data->id = lkb->lkb_id; + data->remid = lkb->lkb_remid; + data->status = lkb->lkb_status; + data->grmode = lkb->lkb_grmode; + data->rqmode = lkb->lkb_rqmode; + data->timestamp = lkb->lkb_timestamp; + if (ua) + data->xid = ua->xid; + if (r) { + data->lockspace_id = r->res_ls->ls_global_id; + data->resource_namelen = r->res_length; + memcpy(data->resource_name, r->res_name, r->res_length); + } +} + +void dlm_timeout_warn(struct dlm_lkb *lkb) +{ + struct dlm_lock_data *data; + struct sk_buff *send_skb; + size_t size; + int rv; + + size = nla_total_size(sizeof(struct dlm_lock_data)) + + nla_total_size(0); /* why this? */ + + rv = prepare_data(DLM_CMD_TIMEOUT, &send_skb, size); + if (rv < 0) + return; + + data = mk_data(send_skb); + if (!data) { + nlmsg_free(send_skb); + return; + } + + fill_data(data, lkb); + + send_data(send_skb); +} + diff --git a/fs/dlm/rcom.c b/fs/dlm/rcom.c index 6bfbd615380..e3a1527cbdb 100644 --- a/fs/dlm/rcom.c +++ b/fs/dlm/rcom.c @@ -38,7 +38,7 @@ static int create_rcom(struct dlm_ls *ls, int to_nodeid, int type, int len, char *mb; int mb_len = sizeof(struct dlm_rcom) + len; - mh = dlm_lowcomms_get_buffer(to_nodeid, mb_len, GFP_KERNEL, &mb); + mh = dlm_lowcomms_get_buffer(to_nodeid, mb_len, ls->ls_allocation, &mb); if (!mh) { log_print("create_rcom to %d type %d len %d ENOBUFS", to_nodeid, type, len); @@ -90,7 +90,7 @@ static int check_config(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid) log_error(ls, "version mismatch: %x nodeid %d: %x", DLM_HEADER_MAJOR | DLM_HEADER_MINOR, nodeid, rc->rc_header.h_version); - return -EINVAL; + return -EPROTO; } if (rf->rf_lvblen != ls->ls_lvblen || @@ -98,7 +98,7 @@ static int check_config(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid) log_error(ls, "config mismatch: %d,%x nodeid %d: %d,%x", ls->ls_lvblen, ls->ls_exflags, nodeid, rf->rf_lvblen, rf->rf_lsflags); - return -EINVAL; + return -EPROTO; } return 0; } @@ -386,7 +386,8 @@ static void receive_rcom_lock_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in) dlm_recover_process_copy(ls, rc_in); } -static int send_ls_not_ready(int nodeid, struct dlm_rcom *rc_in) +static int send_ls_not_ready(struct dlm_ls *ls, int nodeid, + struct dlm_rcom *rc_in) { struct dlm_rcom *rc; struct rcom_config *rf; @@ -394,7 +395,7 @@ static int send_ls_not_ready(int nodeid, struct dlm_rcom *rc_in) char *mb; int mb_len = sizeof(struct dlm_rcom) + sizeof(struct rcom_config); - mh = dlm_lowcomms_get_buffer(nodeid, mb_len, GFP_KERNEL, &mb); + mh = dlm_lowcomms_get_buffer(nodeid, mb_len, ls->ls_allocation, &mb); if (!mh) return -ENOBUFS; memset(mb, 0, mb_len); @@ -464,7 +465,7 @@ void dlm_receive_rcom(struct dlm_header *hd, int nodeid) log_print("lockspace %x from %d type %x not found", hd->h_lockspace, nodeid, rc->rc_type); if (rc->rc_type == DLM_RCOM_STATUS) - send_ls_not_ready(nodeid, rc); + send_ls_not_ready(ls, nodeid, rc); return; } diff --git a/fs/dlm/recoverd.c b/fs/dlm/recoverd.c index 3cb636d6024..66575997861 100644 --- a/fs/dlm/recoverd.c +++ b/fs/dlm/recoverd.c @@ -2,7 +2,7 @@ ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. -** Copyright (C) 2004-2005 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 @@ -190,6 +190,8 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv) dlm_clear_members_gone(ls); + dlm_adjust_timeouts(ls); + error = enable_locking(ls, rv->seq); if (error) { log_debug(ls, "enable_locking failed %d", error); diff --git a/fs/dlm/user.c b/fs/dlm/user.c index b0201ec325a..6438941ab1f 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -33,16 +33,17 @@ static const struct file_operations device_fops; struct dlm_lock_params32 { __u8 mode; __u8 namelen; - __u16 flags; + __u16 unused; + __u32 flags; __u32 lkid; __u32 parent; - + __u64 xid; + __u64 timeout; __u32 castparam; __u32 castaddr; __u32 bastparam; __u32 bastaddr; __u32 lksb; - char lvb[DLM_USER_LVB_LEN]; char name[0]; }; @@ -68,6 +69,7 @@ struct dlm_lksb32 { }; struct dlm_lock_result32 { + __u32 version[3]; __u32 length; __u32 user_astaddr; __u32 user_astparam; @@ -102,6 +104,8 @@ static void compat_input(struct dlm_write_request *kb, kb->i.lock.flags = kb32->i.lock.flags; kb->i.lock.lkid = kb32->i.lock.lkid; kb->i.lock.parent = kb32->i.lock.parent; + kb->i.lock.xid = kb32->i.lock.xid; + kb->i.lock.timeout = kb32->i.lock.timeout; kb->i.lock.castparam = (void *)(long)kb32->i.lock.castparam; kb->i.lock.castaddr = (void *)(long)kb32->i.lock.castaddr; kb->i.lock.bastparam = (void *)(long)kb32->i.lock.bastparam; @@ -115,6 +119,10 @@ static void compat_input(struct dlm_write_request *kb, static void compat_output(struct dlm_lock_result *res, struct dlm_lock_result32 *res32) { + res32->version[0] = res->version[0]; + res32->version[1] = res->version[1]; + res32->version[2] = res->version[2]; + res32->user_astaddr = (__u32)(long)res->user_astaddr; res32->user_astparam = (__u32)(long)res->user_astparam; res32->user_lksb = (__u32)(long)res->user_lksb; @@ -130,6 +138,36 @@ static void compat_output(struct dlm_lock_result *res, } #endif +/* Figure out if this lock is at the end of its life and no longer + available for the application to use. The lkb still exists until + the final ast is read. A lock becomes EOL in three situations: + 1. a noqueue request fails with EAGAIN + 2. an unlock completes with EUNLOCK + 3. a cancel of a waiting request completes with ECANCEL/EDEADLK + An EOL lock needs to be removed from the process's list of locks. + And we can't allow any new operation on an EOL lock. This is + not related to the lifetime of the lkb struct which is managed + entirely by refcount. */ + +static int lkb_is_endoflife(struct dlm_lkb *lkb, int sb_status, int type) +{ + switch (sb_status) { + case -DLM_EUNLOCK: + return 1; + case -DLM_ECANCEL: + case -ETIMEDOUT: + case -EDEADLK: + if (lkb->lkb_grmode == DLM_LOCK_IV) + return 1; + break; + case -EAGAIN: + if (type == AST_COMP && lkb->lkb_grmode == DLM_LOCK_IV) + return 1; + break; + } + return 0; +} + /* we could possibly check if the cancel of an orphan has resulted in the lkb being removed and then remove that lkb from the orphans list and free it */ @@ -176,25 +214,7 @@ void dlm_user_add_ast(struct dlm_lkb *lkb, int type) log_debug(ls, "ast overlap %x status %x %x", lkb->lkb_id, ua->lksb.sb_status, lkb->lkb_flags); - /* Figure out if this lock is at the end of its life and no longer - available for the application to use. The lkb still exists until - the final ast is read. A lock becomes EOL in three situations: - 1. a noqueue request fails with EAGAIN - 2. an unlock completes with EUNLOCK - 3. a cancel of a waiting request completes with ECANCEL - An EOL lock needs to be removed from the process's list of locks. - And we can't allow any new operation on an EOL lock. This is - not related to the lifetime of the lkb struct which is managed - entirely by refcount. */ - - if (type == AST_COMP && - lkb->lkb_grmode == DLM_LOCK_IV && - ua->lksb.sb_status == -EAGAIN) - eol = 1; - else if (ua->lksb.sb_status == -DLM_EUNLOCK || - (ua->lksb.sb_status == -DLM_ECANCEL && - lkb->lkb_grmode == DLM_LOCK_IV)) - eol = 1; + eol = lkb_is_endoflife(lkb, ua->lksb.sb_status, type); if (eol) { lkb->lkb_ast_type &= ~AST_BAST; lkb->lkb_flags |= DLM_IFL_ENDOFLIFE; @@ -252,16 +272,18 @@ static int device_user_lock(struct dlm_user_proc *proc, ua->castaddr = params->castaddr; ua->bastparam = params->bastparam; ua->bastaddr = params->bastaddr; + ua->xid = params->xid; if (params->flags & DLM_LKF_CONVERT) error = dlm_user_convert(ls, ua, params->mode, params->flags, - params->lkid, params->lvb); + params->lkid, params->lvb, + (unsigned long) params->timeout); else { error = dlm_user_request(ls, ua, params->mode, params->flags, params->name, params->namelen, - params->parent); + (unsigned long) params->timeout); if (!error) error = ua->lksb.sb_lkid; } @@ -299,6 +321,22 @@ static int device_user_unlock(struct dlm_user_proc *proc, return error; } +static int device_user_deadlock(struct dlm_user_proc *proc, + struct dlm_lock_params *params) +{ + struct dlm_ls *ls; + int error; + + ls = dlm_find_lockspace_local(proc->lockspace); + if (!ls) + return -ENOENT; + + error = dlm_user_deadlock(ls, params->flags, params->lkid); + + dlm_put_lockspace(ls); + return error; +} + static int create_misc_device(struct dlm_ls *ls, char *name) { int error, len; @@ -348,7 +386,7 @@ static int device_create_lockspace(struct dlm_lspace_params *params) return -EPERM; error = dlm_new_lockspace(params->name, strlen(params->name), - &lockspace, 0, DLM_USER_LVB_LEN); + &lockspace, params->flags, DLM_USER_LVB_LEN); if (error) return error; @@ -524,6 +562,14 @@ static ssize_t device_write(struct file *file, const char __user *buf, error = device_user_unlock(proc, &kbuf->i.lock); break; + case DLM_USER_DEADLOCK: + if (!proc) { + log_print("no locking on control device"); + goto out_sig; + } + error = device_user_deadlock(proc, &kbuf->i.lock); + break; + case DLM_USER_CREATE_LOCKSPACE: if (proc) { log_print("create/remove only on control device"); @@ -641,6 +687,9 @@ static int copy_result_to_user(struct dlm_user_args *ua, int compat, int type, int struct_len; memset(&result, 0, sizeof(struct dlm_lock_result)); + result.version[0] = DLM_DEVICE_VERSION_MAJOR; + result.version[1] = DLM_DEVICE_VERSION_MINOR; + result.version[2] = DLM_DEVICE_VERSION_PATCH; memcpy(&result.lksb, &ua->lksb, sizeof(struct dlm_lksb)); result.user_lksb = ua->user_lksb; @@ -699,6 +748,20 @@ static int copy_result_to_user(struct dlm_user_args *ua, int compat, int type, return error; } +static int copy_version_to_user(char __user *buf, size_t count) +{ + struct dlm_device_version ver; + + memset(&ver, 0, sizeof(struct dlm_device_version)); + ver.version[0] = DLM_DEVICE_VERSION_MAJOR; + ver.version[1] = DLM_DEVICE_VERSION_MINOR; + ver.version[2] = DLM_DEVICE_VERSION_PATCH; + + if (copy_to_user(buf, &ver, sizeof(struct dlm_device_version))) + return -EFAULT; + return sizeof(struct dlm_device_version); +} + /* a read returns a single ast described in a struct dlm_lock_result */ static ssize_t device_read(struct file *file, char __user *buf, size_t count, @@ -710,6 +773,16 @@ static ssize_t device_read(struct file *file, char __user *buf, size_t count, DECLARE_WAITQUEUE(wait, current); int error, type=0, bmode=0, removed = 0; + if (count == sizeof(struct dlm_device_version)) { + error = copy_version_to_user(buf, count); + return error; + } + + if (!proc) { + log_print("non-version read from control device %zu", count); + return -EINVAL; + } + #ifdef CONFIG_COMPAT if (count < sizeof(struct dlm_lock_result32)) #else @@ -747,11 +820,6 @@ static ssize_t device_read(struct file *file, char __user *buf, size_t count, } } - if (list_empty(&proc->asts)) { - spin_unlock(&proc->asts_spin); - return -EAGAIN; - } - /* there may be both completion and blocking asts to return for the lkb, don't remove lkb from asts list unless no asts remain */ @@ -823,6 +891,7 @@ static const struct file_operations device_fops = { static const struct file_operations ctl_device_fops = { .open = ctl_device_open, .release = ctl_device_close, + .read = device_read, .write = device_write, .owner = THIS_MODULE, }; diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index 59288d81707..94f456fe4d9 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -338,16 +338,17 @@ static int ecryptfs_fasync(int fd, struct file *file, int flag) return rc; } -static ssize_t ecryptfs_sendfile(struct file *file, loff_t * ppos, - size_t count, read_actor_t actor, void *target) +static ssize_t ecryptfs_splice_read(struct file *file, loff_t * ppos, + struct pipe_inode_info *pipe, size_t count, + unsigned int flags) { struct file *lower_file = NULL; int rc = -EINVAL; lower_file = ecryptfs_file_to_lower(file); - if (lower_file->f_op && lower_file->f_op->sendfile) - rc = lower_file->f_op->sendfile(lower_file, ppos, count, - actor, target); + if (lower_file->f_op && lower_file->f_op->splice_read) + rc = lower_file->f_op->splice_read(lower_file, ppos, pipe, + count, flags); return rc; } @@ -364,7 +365,7 @@ const struct file_operations ecryptfs_dir_fops = { .release = ecryptfs_release, .fsync = ecryptfs_fsync, .fasync = ecryptfs_fasync, - .sendfile = ecryptfs_sendfile, + .splice_read = ecryptfs_splice_read, }; const struct file_operations ecryptfs_main_fops = { @@ -381,7 +382,7 @@ const struct file_operations ecryptfs_main_fops = { .release = ecryptfs_release, .fsync = ecryptfs_fsync, .fasync = ecryptfs_fasync, - .sendfile = ecryptfs_sendfile, + .splice_read = ecryptfs_splice_read, }; static int diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 606128f5c92..02ca6f1e55d 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -840,8 +840,6 @@ static int __init ecryptfs_init(void) goto out; } kobj_set_kset_s(&ecryptfs_subsys, fs_subsys); - sysfs_attr_version.attr.owner = THIS_MODULE; - sysfs_attr_version_str.attr.owner = THIS_MODULE; rc = do_sysfs_registration(); if (rc) { printk(KERN_ERR "sysfs registration failed\n"); diff --git a/fs/ext2/file.c b/fs/ext2/file.c index 566d4e2d385..04afeecaaef 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -53,7 +53,6 @@ const struct file_operations ext2_file_operations = { .open = generic_file_open, .release = ext2_release_file, .fsync = ext2_sync_file, - .sendfile = generic_file_sendfile, .splice_read = generic_file_splice_read, .splice_write = generic_file_splice_write, }; @@ -71,7 +70,6 @@ const struct file_operations ext2_xip_file_operations = { .open = generic_file_open, .release = ext2_release_file, .fsync = ext2_sync_file, - .sendfile = xip_file_sendfile, }; #endif diff --git a/fs/ext3/file.c b/fs/ext3/file.c index 1e6f1386453..acc4913d301 100644 --- a/fs/ext3/file.c +++ b/fs/ext3/file.c @@ -120,7 +120,6 @@ const struct file_operations ext3_file_operations = { .open = generic_file_open, .release = ext3_release_file, .fsync = ext3_sync_file, - .sendfile = generic_file_sendfile, .splice_read = generic_file_splice_read, .splice_write = generic_file_splice_write, }; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 3c6c1fd2be9..d4c8186aed6 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -120,7 +120,6 @@ const struct file_operations ext4_file_operations = { .open = generic_file_open, .release = ext4_release_file, .fsync = ext4_sync_file, - .sendfile = generic_file_sendfile, .splice_read = generic_file_splice_read, .splice_write = generic_file_splice_write, }; diff --git a/fs/fat/file.c b/fs/fat/file.c index 55d3c7461c5..69a83b59dce 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -134,7 +134,7 @@ const struct file_operations fat_file_operations = { .release = fat_file_release, .ioctl = fat_generic_ioctl, .fsync = file_fsync, - .sendfile = generic_file_sendfile, + .splice_read = generic_file_splice_read, }; static int fat_cont_expand(struct inode *inode, loff_t size) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index adf7995232b..f79de7c8cdf 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -802,7 +802,7 @@ static const struct file_operations fuse_file_operations = { .release = fuse_release, .fsync = fuse_fsync, .lock = fuse_file_lock, - .sendfile = generic_file_sendfile, + .splice_read = generic_file_splice_read, }; static const struct file_operations fuse_direct_io_file_operations = { @@ -814,7 +814,7 @@ static const struct file_operations fuse_direct_io_file_operations = { .release = fuse_release, .fsync = fuse_fsync, .lock = fuse_file_lock, - /* no mmap and sendfile */ + /* no mmap and splice_read */ }; static const struct address_space_operations fuse_file_aops = { diff --git a/fs/gfs2/Makefile b/fs/gfs2/Makefile index e3f1ada643a..04ad0caebed 100644 --- a/fs/gfs2/Makefile +++ b/fs/gfs2/Makefile @@ -1,7 +1,7 @@ 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 ondisk.o ops_address.o ops_dentry.o ops_export.o ops_file.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 \ recovery.o rgrp.o super.o sys.o trans.o util.o diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index c53a5d2d059..cd805a66880 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -718,7 +718,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh, for (x = 0; x < rlist.rl_rgrps; x++) { struct gfs2_rgrpd *rgd; rgd = rlist.rl_ghs[x].gh_gl->gl_object; - rg_blocks += rgd->rd_ri.ri_length; + rg_blocks += rgd->rd_length; } error = gfs2_glock_nq_m(rlist.rl_rgrps, rlist.rl_ghs); @@ -772,7 +772,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh, gfs2_free_data(ip, bstart, blen); } - ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME_SEC; + ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME; gfs2_dinode_out(ip, dibh->b_data); @@ -824,7 +824,7 @@ static int do_grow(struct gfs2_inode *ip, u64 size) goto out_gunlock_q; error = gfs2_trans_begin(sdp, - sdp->sd_max_height + al->al_rgd->rd_ri.ri_length + + sdp->sd_max_height + al->al_rgd->rd_length + RES_JDATA + RES_DINODE + RES_STATFS + RES_QUOTA, 0); if (error) goto out_ipres; @@ -847,7 +847,7 @@ static int do_grow(struct gfs2_inode *ip, u64 size) } ip->i_di.di_size = size; - ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME_SEC; + ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME; error = gfs2_meta_inode_buffer(ip, &dibh); if (error) @@ -885,7 +885,6 @@ static int gfs2_block_truncate_page(struct address_space *mapping) unsigned blocksize, iblock, length, pos; struct buffer_head *bh; struct page *page; - void *kaddr; int err; page = grab_cache_page(mapping, index); @@ -928,15 +927,13 @@ static int gfs2_block_truncate_page(struct address_space *mapping) /* Uhhuh. Read error. Complain and punt. */ if (!buffer_uptodate(bh)) goto unlock; + err = 0; } if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip)) gfs2_trans_add_bh(ip->i_gl, bh, 0); - kaddr = kmap_atomic(page, KM_USER0); - memset(kaddr + offset, 0, length); - flush_dcache_page(page); - kunmap_atomic(kaddr, KM_USER0); + zero_user_page(page, offset, length, KM_USER0); unlock: unlock_page(page); @@ -962,7 +959,7 @@ static int trunc_start(struct gfs2_inode *ip, u64 size) if (gfs2_is_stuffed(ip)) { ip->i_di.di_size = size; - ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME_SEC; + ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME; gfs2_trans_add_bh(ip->i_gl, dibh, 1); gfs2_dinode_out(ip, dibh->b_data); gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode) + size); @@ -974,7 +971,7 @@ static int trunc_start(struct gfs2_inode *ip, u64 size) if (!error) { ip->i_di.di_size = size; - ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME_SEC; + ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME; ip->i_di.di_flags |= GFS2_DIF_TRUNC_IN_PROG; gfs2_trans_add_bh(ip->i_gl, dibh, 1); gfs2_dinode_out(ip, dibh->b_data); @@ -1044,10 +1041,10 @@ static int trunc_end(struct gfs2_inode *ip) ip->i_di.di_height = 0; ip->i_di.di_goal_meta = ip->i_di.di_goal_data = - ip->i_num.no_addr; + ip->i_no_addr; gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode)); } - ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME_SEC; + ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME; ip->i_di.di_flags &= ~GFS2_DIF_TRUNC_IN_PROG; gfs2_trans_add_bh(ip->i_gl, dibh, 1); diff --git a/fs/gfs2/daemon.c b/fs/gfs2/daemon.c index 683cb5bda87..3548d9f31e0 100644 --- a/fs/gfs2/daemon.c +++ b/fs/gfs2/daemon.c @@ -16,6 +16,7 @@ #include <linux/delay.h> #include <linux/gfs2_ondisk.h> #include <linux/lm_interface.h> +#include <linux/freezer.h> #include "gfs2.h" #include "incore.h" @@ -49,6 +50,8 @@ int gfs2_scand(void *data) while (!kthread_should_stop()) { gfs2_scand_internal(sdp); t = gfs2_tune_get(sdp, gt_scand_secs) * HZ; + if (freezing(current)) + refrigerator(); schedule_timeout_interruptible(t); } @@ -74,6 +77,8 @@ int gfs2_glockd(void *data) wait_event_interruptible(sdp->sd_reclaim_wq, (atomic_read(&sdp->sd_reclaim_count) || kthread_should_stop())); + if (freezing(current)) + refrigerator(); } return 0; @@ -93,6 +98,8 @@ int gfs2_recoverd(void *data) while (!kthread_should_stop()) { gfs2_check_journals(sdp); t = gfs2_tune_get(sdp, gt_recoverd_secs) * HZ; + if (freezing(current)) + refrigerator(); schedule_timeout_interruptible(t); } @@ -141,6 +148,8 @@ int gfs2_logd(void *data) } t = gfs2_tune_get(sdp, gt_logd_secs) * HZ; + if (freezing(current)) + refrigerator(); schedule_timeout_interruptible(t); } @@ -191,6 +200,8 @@ int gfs2_quotad(void *data) gfs2_quota_scan(sdp); t = gfs2_tune_get(sdp, gt_quotad_secs) * HZ; + if (freezing(current)) + refrigerator(); schedule_timeout_interruptible(t); } diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index a96fa07b3f3..2beb2f401aa 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -130,7 +130,7 @@ static int gfs2_dir_write_stuffed(struct gfs2_inode *ip, const char *buf, memcpy(dibh->b_data + offset + sizeof(struct gfs2_dinode), buf, size); if (ip->i_di.di_size < offset + size) ip->i_di.di_size = offset + size; - ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME_SEC; + ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME; gfs2_dinode_out(ip, dibh->b_data); brelse(dibh); @@ -228,7 +228,7 @@ out: if (ip->i_di.di_size < offset + copied) ip->i_di.di_size = offset + copied; - ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME_SEC; + ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME; gfs2_trans_add_bh(ip->i_gl, dibh, 1); gfs2_dinode_out(ip, dibh->b_data); @@ -1456,7 +1456,7 @@ int gfs2_dir_read(struct inode *inode, u64 *offset, void *opaque, if (dip->i_di.di_entries != g.offset) { fs_warn(sdp, "Number of entries corrupt in dir %llu, " "ip->i_di.di_entries (%u) != g.offset (%u)\n", - (unsigned long long)dip->i_num.no_addr, + (unsigned long long)dip->i_no_addr, dip->i_di.di_entries, g.offset); error = -EIO; @@ -1488,24 +1488,55 @@ out: * Returns: errno */ -int gfs2_dir_search(struct inode *dir, const struct qstr *name, - struct gfs2_inum_host *inum, unsigned int *type) +struct inode *gfs2_dir_search(struct inode *dir, const struct qstr *name) { struct buffer_head *bh; struct gfs2_dirent *dent; + struct inode *inode; + + dent = gfs2_dirent_search(dir, name, gfs2_dirent_find, &bh); + if (dent) { + if (IS_ERR(dent)) + return ERR_PTR(PTR_ERR(dent)); + inode = gfs2_inode_lookup(dir->i_sb, + be16_to_cpu(dent->de_type), + be64_to_cpu(dent->de_inum.no_addr), + be64_to_cpu(dent->de_inum.no_formal_ino)); + brelse(bh); + return inode; + } + return ERR_PTR(-ENOENT); +} + +int gfs2_dir_check(struct inode *dir, const struct qstr *name, + const struct gfs2_inode *ip) +{ + struct buffer_head *bh; + struct gfs2_dirent *dent; + int ret = -ENOENT; dent = gfs2_dirent_search(dir, name, gfs2_dirent_find, &bh); if (dent) { if (IS_ERR(dent)) return PTR_ERR(dent); - if (inum) - gfs2_inum_in(inum, (char *)&dent->de_inum); - if (type) - *type = be16_to_cpu(dent->de_type); + if (ip) { + if (be64_to_cpu(dent->de_inum.no_addr) != ip->i_no_addr) + goto out; + if (be64_to_cpu(dent->de_inum.no_formal_ino) != + ip->i_no_formal_ino) + goto out; + if (unlikely(IF2DT(ip->i_inode.i_mode) != + be16_to_cpu(dent->de_type))) { + gfs2_consist_inode(GFS2_I(dir)); + ret = -EIO; + goto out; + } + } + ret = 0; +out: brelse(bh); - return 0; } - return -ENOENT; + return ret; } static int dir_new_leaf(struct inode *inode, const struct qstr *name) @@ -1565,7 +1596,7 @@ static int dir_new_leaf(struct inode *inode, const struct qstr *name) */ int gfs2_dir_add(struct inode *inode, const struct qstr *name, - const struct gfs2_inum_host *inum, unsigned type) + const struct gfs2_inode *nip, unsigned type) { struct gfs2_inode *ip = GFS2_I(inode); struct buffer_head *bh; @@ -1580,7 +1611,7 @@ int gfs2_dir_add(struct inode *inode, const struct qstr *name, if (IS_ERR(dent)) return PTR_ERR(dent); dent = gfs2_init_dirent(inode, dent, name, bh); - gfs2_inum_out(inum, (char *)&dent->de_inum); + gfs2_inum_out(nip, dent); dent->de_type = cpu_to_be16(type); if (ip->i_di.di_flags & GFS2_DIF_EXHASH) { leaf = (struct gfs2_leaf *)bh->b_data; @@ -1592,7 +1623,7 @@ int gfs2_dir_add(struct inode *inode, const struct qstr *name, break; gfs2_trans_add_bh(ip->i_gl, bh, 1); ip->i_di.di_entries++; - ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME_SEC; + ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME; gfs2_dinode_out(ip, bh->b_data); brelse(bh); error = 0; @@ -1678,7 +1709,7 @@ int gfs2_dir_del(struct gfs2_inode *dip, const struct qstr *name) gfs2_consist_inode(dip); gfs2_trans_add_bh(dip->i_gl, bh, 1); dip->i_di.di_entries--; - dip->i_inode.i_mtime = dip->i_inode.i_ctime = CURRENT_TIME_SEC; + dip->i_inode.i_mtime = dip->i_inode.i_ctime = CURRENT_TIME; gfs2_dinode_out(dip, bh->b_data); brelse(bh); mark_inode_dirty(&dip->i_inode); @@ -1700,7 +1731,7 @@ int gfs2_dir_del(struct gfs2_inode *dip, const struct qstr *name) */ int gfs2_dir_mvino(struct gfs2_inode *dip, const struct qstr *filename, - struct gfs2_inum_host *inum, unsigned int new_type) + const struct gfs2_inode *nip, unsigned int new_type) { struct buffer_head *bh; struct gfs2_dirent *dent; @@ -1715,7 +1746,7 @@ int gfs2_dir_mvino(struct gfs2_inode *dip, const struct qstr *filename, return PTR_ERR(dent); gfs2_trans_add_bh(dip->i_gl, bh, 1); - gfs2_inum_out(inum, (char *)&dent->de_inum); + gfs2_inum_out(nip, dent); dent->de_type = cpu_to_be16(new_type); if (dip->i_di.di_flags & GFS2_DIF_EXHASH) { @@ -1726,7 +1757,7 @@ int gfs2_dir_mvino(struct gfs2_inode *dip, const struct qstr *filename, gfs2_trans_add_bh(dip->i_gl, bh, 1); } - dip->i_inode.i_mtime = dip->i_inode.i_ctime = CURRENT_TIME_SEC; + dip->i_inode.i_mtime = dip->i_inode.i_ctime = CURRENT_TIME; gfs2_dinode_out(dip, bh->b_data); brelse(bh); return 0; @@ -1867,7 +1898,7 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len, for (x = 0; x < rlist.rl_rgrps; x++) { struct gfs2_rgrpd *rgd; rgd = rlist.rl_ghs[x].gh_gl->gl_object; - rg_blocks += rgd->rd_ri.ri_length; + rg_blocks += rgd->rd_length; } error = gfs2_glock_nq_m(rlist.rl_rgrps, rlist.rl_ghs); diff --git a/fs/gfs2/dir.h b/fs/gfs2/dir.h index 48fe89046bb..8a468cac932 100644 --- a/fs/gfs2/dir.h +++ b/fs/gfs2/dir.h @@ -16,15 +16,16 @@ struct inode; struct gfs2_inode; struct gfs2_inum; -int gfs2_dir_search(struct inode *dir, const struct qstr *filename, - struct gfs2_inum_host *inum, unsigned int *type); +struct inode *gfs2_dir_search(struct inode *dir, const struct qstr *filename); +int gfs2_dir_check(struct inode *dir, const struct qstr *filename, + const struct gfs2_inode *ip); int gfs2_dir_add(struct inode *inode, const struct qstr *filename, - const struct gfs2_inum_host *inum, unsigned int type); + const struct gfs2_inode *ip, unsigned int type); int gfs2_dir_del(struct gfs2_inode *dip, const struct qstr *filename); int gfs2_dir_read(struct inode *inode, u64 *offset, void *opaque, filldir_t filldir); int gfs2_dir_mvino(struct gfs2_inode *dip, const struct qstr *filename, - struct gfs2_inum_host *new_inum, unsigned int new_type); + const struct gfs2_inode *nip, unsigned int new_type); int gfs2_dir_exhash_dealloc(struct gfs2_inode *dip); diff --git a/fs/gfs2/eattr.c b/fs/gfs2/eattr.c index 5b83ca6acab..2a7435b5c4d 100644 --- a/fs/gfs2/eattr.c +++ b/fs/gfs2/eattr.c @@ -254,7 +254,7 @@ static int ea_dealloc_unstuffed(struct gfs2_inode *ip, struct buffer_head *bh, if (error) return error; - error = gfs2_trans_begin(sdp, rgd->rd_ri.ri_length + RES_DINODE + + error = gfs2_trans_begin(sdp, rgd->rd_length + RES_DINODE + RES_EATTR + RES_STATFS + RES_QUOTA, blks); if (error) goto out_gunlock; @@ -300,7 +300,7 @@ static int ea_dealloc_unstuffed(struct gfs2_inode *ip, struct buffer_head *bh, error = gfs2_meta_inode_buffer(ip, &dibh); if (!error) { - ip->i_inode.i_ctime = CURRENT_TIME_SEC; + ip->i_inode.i_ctime = CURRENT_TIME; gfs2_trans_add_bh(ip->i_gl, dibh, 1); gfs2_dinode_out(ip, dibh->b_data); brelse(dibh); @@ -700,7 +700,7 @@ static int ea_alloc_skeleton(struct gfs2_inode *ip, struct gfs2_ea_request *er, goto out_gunlock_q; error = gfs2_trans_begin(GFS2_SB(&ip->i_inode), - blks + al->al_rgd->rd_ri.ri_length + + blks + al->al_rgd->rd_length + RES_DINODE + RES_STATFS + RES_QUOTA, 0); if (error) goto out_ipres; @@ -717,7 +717,7 @@ static int ea_alloc_skeleton(struct gfs2_inode *ip, struct gfs2_ea_request *er, (er->er_mode & S_IFMT)); ip->i_inode.i_mode = er->er_mode; } - ip->i_inode.i_ctime = CURRENT_TIME_SEC; + ip->i_inode.i_ctime = CURRENT_TIME; gfs2_trans_add_bh(ip->i_gl, dibh, 1); gfs2_dinode_out(ip, dibh->b_data); brelse(dibh); @@ -852,7 +852,7 @@ static int ea_set_simple_noalloc(struct gfs2_inode *ip, struct buffer_head *bh, (ip->i_inode.i_mode & S_IFMT) == (er->er_mode & S_IFMT)); ip->i_inode.i_mode = er->er_mode; } - ip->i_inode.i_ctime = CURRENT_TIME_SEC; + ip->i_inode.i_ctime = CURRENT_TIME; gfs2_trans_add_bh(ip->i_gl, dibh, 1); gfs2_dinode_out(ip, dibh->b_data); brelse(dibh); @@ -1133,7 +1133,7 @@ static int ea_remove_stuffed(struct gfs2_inode *ip, struct gfs2_ea_location *el) error = gfs2_meta_inode_buffer(ip, &dibh); if (!error) { - ip->i_inode.i_ctime = CURRENT_TIME_SEC; + ip->i_inode.i_ctime = CURRENT_TIME; gfs2_trans_add_bh(ip->i_gl, dibh, 1); gfs2_dinode_out(ip, dibh->b_data); brelse(dibh); @@ -1352,7 +1352,7 @@ static int ea_dealloc_indirect(struct gfs2_inode *ip) for (x = 0; x < rlist.rl_rgrps; x++) { struct gfs2_rgrpd *rgd; rgd = rlist.rl_ghs[x].gh_gl->gl_object; - rg_blocks += rgd->rd_ri.ri_length; + rg_blocks += rgd->rd_length; } error = gfs2_glock_nq_m(rlist.rl_rgrps, rlist.rl_ghs); diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 1815429a297..3f0974e1afe 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -422,11 +422,11 @@ void gfs2_holder_uninit(struct gfs2_holder *gh) static void gfs2_holder_wake(struct gfs2_holder *gh) { clear_bit(HIF_WAIT, &gh->gh_iflags); - smp_mb(); + smp_mb__after_clear_bit(); wake_up_bit(&gh->gh_iflags, HIF_WAIT); } -static int holder_wait(void *word) +static int just_schedule(void *word) { schedule(); return 0; @@ -435,7 +435,20 @@ static int holder_wait(void *word) static void wait_on_holder(struct gfs2_holder *gh) { might_sleep(); - wait_on_bit(&gh->gh_iflags, HIF_WAIT, holder_wait, TASK_UNINTERRUPTIBLE); + wait_on_bit(&gh->gh_iflags, HIF_WAIT, just_schedule, TASK_UNINTERRUPTIBLE); +} + +static void gfs2_demote_wake(struct gfs2_glock *gl) +{ + clear_bit(GLF_DEMOTE, &gl->gl_flags); + smp_mb__after_clear_bit(); + wake_up_bit(&gl->gl_flags, GLF_DEMOTE); +} + +static void wait_on_demote(struct gfs2_glock *gl) +{ + might_sleep(); + wait_on_bit(&gl->gl_flags, GLF_DEMOTE, just_schedule, TASK_UNINTERRUPTIBLE); } /** @@ -528,7 +541,7 @@ static int rq_demote(struct gfs2_glock *gl) if (gl->gl_state == gl->gl_demote_state || gl->gl_state == LM_ST_UNLOCKED) { - clear_bit(GLF_DEMOTE, &gl->gl_flags); + gfs2_demote_wake(gl); return 0; } set_bit(GLF_LOCK, &gl->gl_flags); @@ -666,12 +679,22 @@ static void gfs2_glmutex_unlock(struct gfs2_glock *gl) * practise: LM_ST_SHARED and LM_ST_UNLOCKED */ -static void handle_callback(struct gfs2_glock *gl, unsigned int state) +static void handle_callback(struct gfs2_glock *gl, unsigned int state, int remote) { spin_lock(&gl->gl_spin); if (test_and_set_bit(GLF_DEMOTE, &gl->gl_flags) == 0) { gl->gl_demote_state = state; gl->gl_demote_time = jiffies; + if (remote && gl->gl_ops->go_type == LM_TYPE_IOPEN && + gl->gl_object) { + struct inode *inode = igrab(gl->gl_object); + spin_unlock(&gl->gl_spin); + if (inode) { + d_prune_aliases(inode); + iput(inode); + } + return; + } } else if (gl->gl_demote_state != LM_ST_UNLOCKED) { gl->gl_demote_state = state; } @@ -740,7 +763,7 @@ static void xmote_bh(struct gfs2_glock *gl, unsigned int ret) if (ret & LM_OUT_CANCELED) op_done = 0; else - clear_bit(GLF_DEMOTE, &gl->gl_flags); + gfs2_demote_wake(gl); } else { spin_lock(&gl->gl_spin); list_del_init(&gh->gh_list); @@ -848,7 +871,7 @@ static void drop_bh(struct gfs2_glock *gl, unsigned int ret) gfs2_assert_warn(sdp, !ret); state_change(gl, LM_ST_UNLOCKED); - clear_bit(GLF_DEMOTE, &gl->gl_flags); + gfs2_demote_wake(gl); if (glops->go_inval) glops->go_inval(gl, DIO_METADATA); @@ -1174,7 +1197,7 @@ void gfs2_glock_dq(struct gfs2_holder *gh) const struct gfs2_glock_operations *glops = gl->gl_ops; if (gh->gh_flags & GL_NOCACHE) - handle_callback(gl, LM_ST_UNLOCKED); + handle_callback(gl, LM_ST_UNLOCKED, 0); gfs2_glmutex_lock(gl); @@ -1196,6 +1219,13 @@ void gfs2_glock_dq(struct gfs2_holder *gh) spin_unlock(&gl->gl_spin); } +void gfs2_glock_dq_wait(struct gfs2_holder *gh) +{ + struct gfs2_glock *gl = gh->gh_gl; + gfs2_glock_dq(gh); + wait_on_demote(gl); +} + /** * gfs2_glock_dq_uninit - dequeue a holder from a glock and initialize it * @gh: the holder structure @@ -1297,10 +1327,6 @@ static int nq_m_sync(unsigned int num_gh, struct gfs2_holder *ghs, * @num_gh: the number of structures * @ghs: an array of struct gfs2_holder structures * - * Figure out how big an impact this function has. Either: - * 1) Replace this code with code that calls gfs2_glock_prefetch() - * 2) Forget async stuff and just call nq_m_sync() - * 3) Leave it like it is * * Returns: 0 on success (all glocks acquired), * errno on failure (no glocks acquired) @@ -1308,62 +1334,28 @@ static int nq_m_sync(unsigned int num_gh, struct gfs2_holder *ghs, int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs) { - int *e; - unsigned int x; - int borked = 0, serious = 0; + struct gfs2_holder *tmp[4]; + struct gfs2_holder **pph = tmp; int error = 0; - if (!num_gh) + switch(num_gh) { + case 0: return 0; - - if (num_gh == 1) { + case 1: ghs->gh_flags &= ~(LM_FLAG_TRY | GL_ASYNC); return gfs2_glock_nq(ghs); - } - - e = kcalloc(num_gh, sizeof(struct gfs2_holder *), GFP_KERNEL); - if (!e) - return -ENOMEM; - - for (x = 0; x < num_gh; x++) { - ghs[x].gh_flags |= LM_FLAG_TRY | GL_ASYNC; - error = gfs2_glock_nq(&ghs[x]); - if (error) { - borked = 1; - serious = error; - num_gh = x; + default: + if (num_gh <= 4) break; - } - } - - for (x = 0; x < num_gh; x++) { - error = e[x] = glock_wait_internal(&ghs[x]); - if (error) { - borked = 1; - if (error != GLR_TRYFAILED && error != GLR_CANCELED) - serious = error; - } + pph = kmalloc(num_gh * sizeof(struct gfs2_holder *), GFP_NOFS); + if (!pph) + return -ENOMEM; } - if (!borked) { - kfree(e); - return 0; - } - - for (x = 0; x < num_gh; x++) - if (!e[x]) - gfs2_glock_dq(&ghs[x]); - - if (serious) - error = serious; - else { - for (x = 0; x < num_gh; x++) - gfs2_holder_reinit(ghs[x].gh_state, ghs[x].gh_flags, - &ghs[x]); - error = nq_m_sync(num_gh, ghs, (struct gfs2_holder **)e); - } + error = nq_m_sync(num_gh, ghs, pph); - kfree(e); + if (pph != tmp) + kfree(pph); return error; } @@ -1456,7 +1448,7 @@ static void blocking_cb(struct gfs2_sbd *sdp, struct lm_lockname *name, if (!gl) return; - handle_callback(gl, state); + handle_callback(gl, state, 1); spin_lock(&gl->gl_spin); run_queue(gl); @@ -1596,7 +1588,7 @@ void gfs2_reclaim_glock(struct gfs2_sbd *sdp) if (gfs2_glmutex_trylock(gl)) { if (list_empty(&gl->gl_holders) && gl->gl_state != LM_ST_UNLOCKED && demote_ok(gl)) - handle_callback(gl, LM_ST_UNLOCKED); + handle_callback(gl, LM_ST_UNLOCKED, 0); gfs2_glmutex_unlock(gl); } @@ -1709,7 +1701,7 @@ static void clear_glock(struct gfs2_glock *gl) if (gfs2_glmutex_trylock(gl)) { if (list_empty(&gl->gl_holders) && gl->gl_state != LM_ST_UNLOCKED) - handle_callback(gl, LM_ST_UNLOCKED); + handle_callback(gl, LM_ST_UNLOCKED, 0); gfs2_glmutex_unlock(gl); } } @@ -1823,7 +1815,8 @@ static int dump_inode(struct glock_iter *gi, struct gfs2_inode *ip) print_dbg(gi, " Inode:\n"); print_dbg(gi, " num = %llu/%llu\n", - ip->i_num.no_formal_ino, ip->i_num.no_addr); + (unsigned long long)ip->i_no_formal_ino, + (unsigned long long)ip->i_no_addr); print_dbg(gi, " type = %u\n", IF2DT(ip->i_inode.i_mode)); print_dbg(gi, " i_flags ="); for (x = 0; x < 32; x++) @@ -1909,8 +1902,8 @@ static int dump_glock(struct glock_iter *gi, struct gfs2_glock *gl) } if (test_bit(GLF_DEMOTE, &gl->gl_flags)) { print_dbg(gi, " Demotion req to state %u (%llu uS ago)\n", - gl->gl_demote_state, - (u64)(jiffies - gl->gl_demote_time)*(1000000/HZ)); + gl->gl_demote_state, (unsigned long long) + (jiffies - gl->gl_demote_time)*(1000000/HZ)); } if (gl->gl_ops == &gfs2_inode_glops && gl->gl_object) { if (!test_bit(GLF_LOCK, &gl->gl_flags) && diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h index b3e152db70c..7721ca3fff9 100644 --- a/fs/gfs2/glock.h +++ b/fs/gfs2/glock.h @@ -87,6 +87,7 @@ int gfs2_glock_nq(struct gfs2_holder *gh); int gfs2_glock_poll(struct gfs2_holder *gh); int gfs2_glock_wait(struct gfs2_holder *gh); void gfs2_glock_dq(struct gfs2_holder *gh); +void gfs2_glock_dq_wait(struct gfs2_holder *gh); void gfs2_glock_dq_uninit(struct gfs2_holder *gh); int gfs2_glock_nq_num(struct gfs2_sbd *sdp, diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 7b82657a991..777ca46010e 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -156,9 +156,9 @@ static void inode_go_sync(struct gfs2_glock *gl) ip = NULL; if (test_bit(GLF_DIRTY, &gl->gl_flags)) { - gfs2_log_flush(gl->gl_sbd, gl); if (ip) filemap_fdatawrite(ip->i_inode.i_mapping); + gfs2_log_flush(gl->gl_sbd, gl); gfs2_meta_sync(gl); if (ip) { struct address_space *mapping = ip->i_inode.i_mapping; diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index d995441373a..170ba93829c 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -28,6 +28,14 @@ struct gfs2_sbd; typedef void (*gfs2_glop_bh_t) (struct gfs2_glock *gl, unsigned int ret); +struct gfs2_log_header_host { + u64 lh_sequence; /* Sequence number of this transaction */ + u32 lh_flags; /* GFS2_LOG_HEAD_... */ + u32 lh_tail; /* Block number of log tail */ + u32 lh_blkno; + u32 lh_hash; +}; + /* * Structure of operations that are associated with each * type of element in the log. @@ -60,12 +68,23 @@ struct gfs2_bitmap { u32 bi_len; }; +struct gfs2_rgrp_host { + u32 rg_flags; + u32 rg_free; + u32 rg_dinodes; + u64 rg_igeneration; +}; + struct gfs2_rgrpd { struct list_head rd_list; /* Link with superblock */ struct list_head rd_list_mru; struct list_head rd_recent; /* Recently used rgrps */ struct gfs2_glock *rd_gl; /* Glock for this rgrp */ - struct gfs2_rindex_host rd_ri; + u64 rd_addr; /* grp block disk address */ + u64 rd_data0; /* first data location */ + u32 rd_length; /* length of rgrp header in fs blocks */ + u32 rd_data; /* num of data blocks in rgrp */ + u32 rd_bitbytes; /* number of bytes in data bitmaps */ struct gfs2_rgrp_host rd_rg; u64 rd_rg_vn; struct gfs2_bitmap *rd_bits; @@ -76,6 +95,8 @@ struct gfs2_rgrpd { u32 rd_last_alloc_data; u32 rd_last_alloc_meta; struct gfs2_sbd *rd_sbd; + unsigned long rd_flags; +#define GFS2_RDF_CHECK 0x0001 /* Need to check for unlinked inodes */ }; enum gfs2_state_bits { @@ -211,10 +232,24 @@ enum { GIF_SW_PAGED = 3, }; +struct gfs2_dinode_host { + u64 di_size; /* number of bytes in file */ + u64 di_blocks; /* number of blocks in file */ + u64 di_goal_meta; /* rgrp to alloc from next */ + u64 di_goal_data; /* data block goal */ + u64 di_generation; /* generation number for NFS */ + u32 di_flags; /* GFS2_DIF_... */ + u16 di_height; /* height of metadata */ + /* These only apply to directories */ + u16 di_depth; /* Number of bits in the table */ + u32 di_entries; /* The number of entries in the directory */ + u64 di_eattr; /* extended attribute block number */ +}; + struct gfs2_inode { struct inode i_inode; - struct gfs2_inum_host i_num; - + u64 i_no_addr; + u64 i_no_formal_ino; unsigned long i_flags; /* GIF_... */ struct gfs2_dinode_host i_di; /* To be replaced by ref to block */ @@ -275,14 +310,6 @@ enum { QDF_LOCKED = 2, }; -struct gfs2_quota_lvb { - __be32 qb_magic; - u32 __pad; - __be64 qb_limit; /* Hard limit of # blocks to alloc */ - __be64 qb_warn; /* Warn user when alloc is above this # */ - __be64 qb_value; /* Current # blocks allocated */ -}; - struct gfs2_quota_data { struct list_head qd_list; unsigned int qd_count; @@ -327,7 +354,9 @@ struct gfs2_trans { unsigned int tr_num_buf; unsigned int tr_num_buf_new; + unsigned int tr_num_databuf_new; unsigned int tr_num_buf_rm; + unsigned int tr_num_databuf_rm; struct list_head tr_list_buf; unsigned int tr_num_revoke; @@ -354,6 +383,12 @@ struct gfs2_jdesc { unsigned int jd_blocks; }; +struct gfs2_statfs_change_host { + s64 sc_total; + s64 sc_free; + s64 sc_dinodes; +}; + #define GFS2_GLOCKD_DEFAULT 1 #define GFS2_GLOCKD_MAX 16 @@ -426,6 +461,28 @@ enum { #define GFS2_FSNAME_LEN 256 +struct gfs2_inum_host { + u64 no_formal_ino; + u64 no_addr; +}; + +struct gfs2_sb_host { + u32 sb_magic; + u32 sb_type; + u32 sb_format; + + u32 sb_fs_format; + u32 sb_multihost_format; + u32 sb_bsize; + u32 sb_bsize_shift; + + struct gfs2_inum_host sb_master_dir; + struct gfs2_inum_host sb_root_dir; + + char sb_lockproto[GFS2_LOCKNAME_LEN]; + char sb_locktable[GFS2_LOCKNAME_LEN]; +}; + struct gfs2_sbd { struct super_block *sd_vfs; struct super_block *sd_vfs_meta; @@ -544,6 +601,7 @@ struct gfs2_sbd { unsigned int sd_log_blks_reserved; unsigned int sd_log_commited_buf; + unsigned int sd_log_commited_databuf; unsigned int sd_log_commited_revoke; unsigned int sd_log_num_gl; @@ -552,7 +610,6 @@ struct gfs2_sbd { unsigned int sd_log_num_rg; unsigned int sd_log_num_databuf; unsigned int sd_log_num_jdata; - unsigned int sd_log_num_hdrs; struct list_head sd_log_le_gl; struct list_head sd_log_le_buf; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index df0b8b3018b..34f7bcdea1e 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -38,12 +38,17 @@ #include "trans.h" #include "util.h" +struct gfs2_inum_range_host { + u64 ir_start; + u64 ir_length; +}; + static int iget_test(struct inode *inode, void *opaque) { struct gfs2_inode *ip = GFS2_I(inode); - struct gfs2_inum_host *inum = opaque; + u64 *no_addr = opaque; - if (ip->i_num.no_addr == inum->no_addr && + if (ip->i_no_addr == *no_addr && inode->i_private != NULL) return 1; @@ -53,37 +58,70 @@ static int iget_test(struct inode *inode, void *opaque) static int iget_set(struct inode *inode, void *opaque) { struct gfs2_inode *ip = GFS2_I(inode); - struct gfs2_inum_host *inum = opaque; + u64 *no_addr = opaque; - ip->i_num = *inum; - inode->i_ino = inum->no_addr; + inode->i_ino = (unsigned long)*no_addr; + ip->i_no_addr = *no_addr; return 0; } -struct inode *gfs2_ilookup(struct super_block *sb, struct gfs2_inum_host *inum) +struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr) +{ + unsigned long hash = (unsigned long)no_addr; + return ilookup5(sb, hash, iget_test, &no_addr); +} + +static struct inode *gfs2_iget(struct super_block *sb, u64 no_addr) { - return ilookup5(sb, (unsigned long)inum->no_addr, - iget_test, inum); + unsigned long hash = (unsigned long)no_addr; + return iget5_locked(sb, hash, iget_test, iget_set, &no_addr); } -static struct inode *gfs2_iget(struct super_block *sb, struct gfs2_inum_host *inum) +/** + * GFS2 lookup code fills in vfs inode contents based on info obtained + * from directory entry inside gfs2_inode_lookup(). This has caused issues + * with NFS code path since its get_dentry routine doesn't have the relevant + * directory entry when gfs2_inode_lookup() is invoked. Part of the code + * segment inside gfs2_inode_lookup code needs to get moved around. + * + * Clean up I_LOCK and I_NEW as well. + **/ + +void gfs2_set_iop(struct inode *inode) { - return iget5_locked(sb, (unsigned long)inum->no_addr, - iget_test, iget_set, inum); + 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; + } else if (S_ISDIR(mode)) { + inode->i_op = &gfs2_dir_iops; + inode->i_fop = &gfs2_dir_fops; + } else if (S_ISLNK(mode)) { + inode->i_op = &gfs2_symlink_iops; + } else { + inode->i_op = &gfs2_dev_iops; + } + + unlock_new_inode(inode); } /** * gfs2_inode_lookup - Lookup an inode * @sb: The super block - * @inum: The inode number + * @no_addr: The inode number * @type: The type of the inode * * Returns: A VFS inode, or an error */ -struct inode *gfs2_inode_lookup(struct super_block *sb, struct gfs2_inum_host *inum, unsigned int type) +struct inode *gfs2_inode_lookup(struct super_block *sb, + unsigned int type, + u64 no_addr, + u64 no_formal_ino) { - struct inode *inode = gfs2_iget(sb, inum); + struct inode *inode = gfs2_iget(sb, no_addr); struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_glock *io_gl; int error; @@ -93,29 +131,15 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, struct gfs2_inum_host *i if (inode->i_state & I_NEW) { struct gfs2_sbd *sdp = GFS2_SB(inode); - umode_t mode = DT2IF(type); inode->i_private = ip; - inode->i_mode = 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; - } else if (S_ISDIR(mode)) { - inode->i_op = &gfs2_dir_iops; - inode->i_fop = &gfs2_dir_fops; - } else if (S_ISLNK(mode)) { - inode->i_op = &gfs2_symlink_iops; - } else { - inode->i_op = &gfs2_dev_iops; - } + ip->i_no_formal_ino = no_formal_ino; - error = gfs2_glock_get(sdp, inum->no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl); + error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl); if (unlikely(error)) goto fail; ip->i_gl->gl_object = ip; - error = gfs2_glock_get(sdp, inum->no_addr, &gfs2_iopen_glops, CREATE, &io_gl); + error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl); if (unlikely(error)) goto fail_put; @@ -123,12 +147,38 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, struct gfs2_inum_host *i error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh); if (unlikely(error)) goto fail_iopen; + ip->i_iopen_gh.gh_gl->gl_object = ip; gfs2_glock_put(io_gl); - unlock_new_inode(inode); + + if ((type == DT_UNKNOWN) && (no_formal_ino == 0)) + goto gfs2_nfsbypass; + + inode->i_mode = DT2IF(type); + + /* + * We must read the inode in order to work out its type in + * this case. Note that this doesn't happen often as we normally + * know the type beforehand. This code path only occurs during + * unlinked inode recovery (where it is safe to do this glock, + * which is not true in the general case). + */ + if (type == DT_UNKNOWN) { + struct gfs2_holder gh; + error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); + if (unlikely(error)) + goto fail_glock; + /* Inode is now uptodate */ + gfs2_glock_dq_uninit(&gh); + } + + gfs2_set_iop(inode); } +gfs2_nfsbypass: return inode; +fail_glock: + gfs2_glock_dq(&ip->i_iopen_gh); fail_iopen: gfs2_glock_put(io_gl); fail_put: @@ -144,14 +194,12 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) struct gfs2_dinode_host *di = &ip->i_di; const struct gfs2_dinode *str = buf; - if (ip->i_num.no_addr != be64_to_cpu(str->di_num.no_addr)) { + if (ip->i_no_addr != be64_to_cpu(str->di_num.no_addr)) { if (gfs2_consist_inode(ip)) gfs2_dinode_print(ip); return -EIO; } - if (ip->i_num.no_formal_ino != be64_to_cpu(str->di_num.no_formal_ino)) - return -ESTALE; - + ip->i_no_formal_ino = be64_to_cpu(str->di_num.no_formal_ino); ip->i_inode.i_mode = be32_to_cpu(str->di_mode); ip->i_inode.i_rdev = 0; switch (ip->i_inode.i_mode & S_IFMT) { @@ -175,11 +223,11 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) di->di_blocks = be64_to_cpu(str->di_blocks); gfs2_set_inode_blocks(&ip->i_inode); ip->i_inode.i_atime.tv_sec = be64_to_cpu(str->di_atime); - ip->i_inode.i_atime.tv_nsec = 0; + ip->i_inode.i_atime.tv_nsec = be32_to_cpu(str->di_atime_nsec); ip->i_inode.i_mtime.tv_sec = be64_to_cpu(str->di_mtime); - ip->i_inode.i_mtime.tv_nsec = 0; + ip->i_inode.i_mtime.tv_nsec = be32_to_cpu(str->di_mtime_nsec); ip->i_inode.i_ctime.tv_sec = be64_to_cpu(str->di_ctime); - ip->i_inode.i_ctime.tv_nsec = 0; + ip->i_inode.i_ctime.tv_nsec = be32_to_cpu(str->di_ctime_nsec); di->di_goal_meta = be64_to_cpu(str->di_goal_meta); di->di_goal_data = be64_to_cpu(str->di_goal_data); @@ -247,7 +295,7 @@ int gfs2_dinode_dealloc(struct gfs2_inode *ip) if (error) goto out_qs; - rgd = gfs2_blk2rgrpd(sdp, ip->i_num.no_addr); + rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr); if (!rgd) { gfs2_consist_inode(ip); error = -EIO; @@ -314,7 +362,7 @@ int gfs2_change_nlink(struct gfs2_inode *ip, int diff) else drop_nlink(&ip->i_inode); - ip->i_inode.i_ctime = CURRENT_TIME_SEC; + ip->i_inode.i_ctime = CURRENT_TIME; gfs2_trans_add_bh(ip->i_gl, dibh, 1); gfs2_dinode_out(ip, dibh->b_data); @@ -366,9 +414,7 @@ struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name, struct super_block *sb = dir->i_sb; struct gfs2_inode *dip = GFS2_I(dir); struct gfs2_holder d_gh; - struct gfs2_inum_host inum; - unsigned int type; - int error; + int error = 0; struct inode *inode = NULL; int unlock = 0; @@ -395,12 +441,9 @@ struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name, goto out; } - error = gfs2_dir_search(dir, name, &inum, &type); - if (error) - goto out; - - inode = gfs2_inode_lookup(sb, &inum, type); - + inode = gfs2_dir_search(dir, name); + if (IS_ERR(inode)) + error = PTR_ERR(inode); out: if (unlock) gfs2_glock_dq_uninit(&d_gh); @@ -409,6 +452,22 @@ out: return inode ? inode : ERR_PTR(error); } +static void gfs2_inum_range_in(struct gfs2_inum_range_host *ir, const void *buf) +{ + const struct gfs2_inum_range *str = buf; + + ir->ir_start = be64_to_cpu(str->ir_start); + ir->ir_length = be64_to_cpu(str->ir_length); +} + +static void gfs2_inum_range_out(const struct gfs2_inum_range_host *ir, void *buf) +{ + struct gfs2_inum_range *str = buf; + + str->ir_start = cpu_to_be64(ir->ir_start); + str->ir_length = cpu_to_be64(ir->ir_length); +} + static int pick_formal_ino_1(struct gfs2_sbd *sdp, u64 *formal_ino) { struct gfs2_inode *ip = GFS2_I(sdp->sd_ir_inode); @@ -548,7 +607,7 @@ static int create_ok(struct gfs2_inode *dip, const struct qstr *name, if (!dip->i_inode.i_nlink) return -EPERM; - error = gfs2_dir_search(&dip->i_inode, name, NULL, NULL); + error = gfs2_dir_check(&dip->i_inode, name, NULL); switch (error) { case -ENOENT: error = 0; @@ -588,8 +647,7 @@ static void munge_mode_uid_gid(struct gfs2_inode *dip, unsigned int *mode, *gid = current->fsgid; } -static int alloc_dinode(struct gfs2_inode *dip, struct gfs2_inum_host *inum, - u64 *generation) +static int alloc_dinode(struct gfs2_inode *dip, u64 *no_addr, u64 *generation) { struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode); int error; @@ -605,7 +663,7 @@ static int alloc_dinode(struct gfs2_inode *dip, struct gfs2_inum_host *inum, if (error) goto out_ipreserv; - inum->no_addr = gfs2_alloc_di(dip, generation); + *no_addr = gfs2_alloc_di(dip, generation); gfs2_trans_end(sdp); @@ -635,6 +693,7 @@ static void init_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl, struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode); struct gfs2_dinode *di; struct buffer_head *dibh; + struct timespec tv = CURRENT_TIME; dibh = gfs2_meta_new(gl, inum->no_addr); gfs2_trans_add_bh(gl, dibh, 1); @@ -650,7 +709,7 @@ static void init_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl, di->di_nlink = 0; di->di_size = 0; di->di_blocks = cpu_to_be64(1); - di->di_atime = di->di_mtime = di->di_ctime = cpu_to_be64(get_seconds()); + di->di_atime = di->di_mtime = di->di_ctime = cpu_to_be64(tv.tv_sec); di->di_major = cpu_to_be32(MAJOR(dev)); di->di_minor = cpu_to_be32(MINOR(dev)); di->di_goal_meta = di->di_goal_data = cpu_to_be64(inum->no_addr); @@ -680,6 +739,9 @@ static void init_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl, di->di_entries = 0; memset(&di->__pad4, 0, sizeof(di->__pad4)); di->di_eattr = 0; + di->di_atime_nsec = cpu_to_be32(tv.tv_nsec); + di->di_mtime_nsec = cpu_to_be32(tv.tv_nsec); + di->di_ctime_nsec = cpu_to_be32(tv.tv_nsec); memset(&di->di_reserved, 0, sizeof(di->di_reserved)); brelse(dibh); @@ -749,7 +811,7 @@ static int link_dinode(struct gfs2_inode *dip, const struct qstr *name, goto fail_quota_locks; error = gfs2_trans_begin(sdp, sdp->sd_max_dirres + - al->al_rgd->rd_ri.ri_length + + al->al_rgd->rd_length + 2 * RES_DINODE + RES_STATFS + RES_QUOTA, 0); if (error) @@ -760,7 +822,7 @@ static int link_dinode(struct gfs2_inode *dip, const struct qstr *name, goto fail_quota_locks; } - error = gfs2_dir_add(&dip->i_inode, name, &ip->i_num, IF2DT(ip->i_inode.i_mode)); + error = gfs2_dir_add(&dip->i_inode, name, ip, IF2DT(ip->i_inode.i_mode)); if (error) goto fail_end_trans; @@ -840,11 +902,11 @@ static int gfs2_security_init(struct gfs2_inode *dip, struct gfs2_inode *ip) struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name, unsigned int mode, dev_t dev) { - struct inode *inode; + struct inode *inode = NULL; struct gfs2_inode *dip = ghs->gh_gl->gl_object; struct inode *dir = &dip->i_inode; struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode); - struct gfs2_inum_host inum; + struct gfs2_inum_host inum = { .no_addr = 0, .no_formal_ino = 0 }; int error; u64 generation; @@ -864,7 +926,7 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name, if (error) goto fail_gunlock; - error = alloc_dinode(dip, &inum, &generation); + error = alloc_dinode(dip, &inum.no_addr, &generation); if (error) goto fail_gunlock; @@ -877,34 +939,36 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name, if (error) goto fail_gunlock2; - inode = gfs2_inode_lookup(dir->i_sb, &inum, IF2DT(mode)); + inode = gfs2_inode_lookup(dir->i_sb, IF2DT(mode), + inum.no_addr, + inum.no_formal_ino); if (IS_ERR(inode)) goto fail_gunlock2; error = gfs2_inode_refresh(GFS2_I(inode)); if (error) - goto fail_iput; + goto fail_gunlock2; error = gfs2_acl_create(dip, GFS2_I(inode)); if (error) - goto fail_iput; + goto fail_gunlock2; error = gfs2_security_init(dip, GFS2_I(inode)); if (error) - goto fail_iput; + goto fail_gunlock2; error = link_dinode(dip, name, GFS2_I(inode)); if (error) - goto fail_iput; + goto fail_gunlock2; if (!inode) return ERR_PTR(-ENOMEM); return inode; -fail_iput: - iput(inode); fail_gunlock2: gfs2_glock_dq_uninit(ghs + 1); + if (inode) + iput(inode); fail_gunlock: gfs2_glock_dq(ghs); fail: @@ -976,10 +1040,8 @@ int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name, */ int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name, - struct gfs2_inode *ip) + const struct gfs2_inode *ip) { - struct gfs2_inum_host inum; - unsigned int type; int error; if (IS_IMMUTABLE(&ip->i_inode) || IS_APPEND(&ip->i_inode)) @@ -997,18 +1059,10 @@ int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name, if (error) return error; - error = gfs2_dir_search(&dip->i_inode, name, &inum, &type); + error = gfs2_dir_check(&dip->i_inode, name, ip); if (error) return error; - if (!gfs2_inum_equal(&inum, &ip->i_num)) - return -ENOENT; - - if (IF2DT(ip->i_inode.i_mode) != type) { - gfs2_consist_inode(dip); - return -EIO; - } - return 0; } @@ -1132,10 +1186,11 @@ int gfs2_glock_nq_atime(struct gfs2_holder *gh) struct gfs2_glock *gl = gh->gh_gl; struct gfs2_sbd *sdp = gl->gl_sbd; struct gfs2_inode *ip = gl->gl_object; - s64 curtime, quantum = gfs2_tune_get(sdp, gt_atime_quantum); + s64 quantum = gfs2_tune_get(sdp, gt_atime_quantum); unsigned int state; int flags; int error; + struct timespec tv = CURRENT_TIME; if (gfs2_assert_warn(sdp, gh->gh_flags & GL_ATIME) || gfs2_assert_warn(sdp, !(gh->gh_flags & GL_ASYNC)) || @@ -1153,8 +1208,7 @@ int gfs2_glock_nq_atime(struct gfs2_holder *gh) (sdp->sd_vfs->s_flags & MS_RDONLY)) return 0; - curtime = get_seconds(); - if (curtime - ip->i_inode.i_atime.tv_sec >= quantum) { + if (tv.tv_sec - ip->i_inode.i_atime.tv_sec >= quantum) { gfs2_glock_dq(gh); gfs2_holder_reinit(LM_ST_EXCLUSIVE, gh->gh_flags & ~LM_FLAG_ANY, gh); @@ -1165,8 +1219,8 @@ int gfs2_glock_nq_atime(struct gfs2_holder *gh) /* Verify that atime hasn't been updated while we were trying to get exclusive lock. */ - curtime = get_seconds(); - if (curtime - ip->i_inode.i_atime.tv_sec >= quantum) { + tv = CURRENT_TIME; + if (tv.tv_sec - ip->i_inode.i_atime.tv_sec >= quantum) { struct buffer_head *dibh; struct gfs2_dinode *di; @@ -1180,11 +1234,12 @@ int gfs2_glock_nq_atime(struct gfs2_holder *gh) if (error) goto fail_end_trans; - ip->i_inode.i_atime.tv_sec = curtime; + ip->i_inode.i_atime = tv; gfs2_trans_add_bh(ip->i_gl, dibh, 1); di = (struct gfs2_dinode *)dibh->b_data; di->di_atime = cpu_to_be64(ip->i_inode.i_atime.tv_sec); + di->di_atime_nsec = cpu_to_be32(ip->i_inode.i_atime.tv_nsec); brelse(dibh); gfs2_trans_end(sdp); @@ -1252,3 +1307,66 @@ int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr) return error; } +void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf) +{ + const struct gfs2_dinode_host *di = &ip->i_di; + struct gfs2_dinode *str = buf; + + str->di_header.mh_magic = cpu_to_be32(GFS2_MAGIC); + str->di_header.mh_type = cpu_to_be32(GFS2_METATYPE_DI); + str->di_header.__pad0 = 0; + str->di_header.mh_format = cpu_to_be32(GFS2_FORMAT_DI); + str->di_header.__pad1 = 0; + str->di_num.no_addr = cpu_to_be64(ip->i_no_addr); + str->di_num.no_formal_ino = cpu_to_be64(ip->i_no_formal_ino); + str->di_mode = cpu_to_be32(ip->i_inode.i_mode); + str->di_uid = cpu_to_be32(ip->i_inode.i_uid); + str->di_gid = cpu_to_be32(ip->i_inode.i_gid); + str->di_nlink = cpu_to_be32(ip->i_inode.i_nlink); + str->di_size = cpu_to_be64(di->di_size); + str->di_blocks = cpu_to_be64(di->di_blocks); + str->di_atime = cpu_to_be64(ip->i_inode.i_atime.tv_sec); + str->di_mtime = cpu_to_be64(ip->i_inode.i_mtime.tv_sec); + str->di_ctime = cpu_to_be64(ip->i_inode.i_ctime.tv_sec); + + str->di_goal_meta = cpu_to_be64(di->di_goal_meta); + str->di_goal_data = cpu_to_be64(di->di_goal_data); + str->di_generation = cpu_to_be64(di->di_generation); + + str->di_flags = cpu_to_be32(di->di_flags); + str->di_height = cpu_to_be16(di->di_height); + str->di_payload_format = cpu_to_be32(S_ISDIR(ip->i_inode.i_mode) && + !(ip->i_di.di_flags & GFS2_DIF_EXHASH) ? + GFS2_FORMAT_DE : 0); + str->di_depth = cpu_to_be16(di->di_depth); + str->di_entries = cpu_to_be32(di->di_entries); + + str->di_eattr = cpu_to_be64(di->di_eattr); + str->di_atime_nsec = cpu_to_be32(ip->i_inode.i_atime.tv_nsec); + str->di_mtime_nsec = cpu_to_be32(ip->i_inode.i_mtime.tv_nsec); + str->di_ctime_nsec = cpu_to_be32(ip->i_inode.i_ctime.tv_nsec); +} + +void gfs2_dinode_print(const struct gfs2_inode *ip) +{ + const struct gfs2_dinode_host *di = &ip->i_di; + + printk(KERN_INFO " no_formal_ino = %llu\n", + (unsigned long long)ip->i_no_formal_ino); + printk(KERN_INFO " no_addr = %llu\n", + (unsigned long long)ip->i_no_addr); + printk(KERN_INFO " di_size = %llu\n", (unsigned long long)di->di_size); + printk(KERN_INFO " di_blocks = %llu\n", + (unsigned long long)di->di_blocks); + printk(KERN_INFO " di_goal_meta = %llu\n", + (unsigned long long)di->di_goal_meta); + printk(KERN_INFO " di_goal_data = %llu\n", + (unsigned long long)di->di_goal_data); + printk(KERN_INFO " di_flags = 0x%.8X\n", di->di_flags); + printk(KERN_INFO " di_height = %u\n", di->di_height); + printk(KERN_INFO " di_depth = %u\n", di->di_depth); + printk(KERN_INFO " di_entries = %u\n", di->di_entries); + printk(KERN_INFO " di_eattr = %llu\n", + (unsigned long long)di->di_eattr); +} + diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h index b57f448b15b..4517ac82c01 100644 --- a/fs/gfs2/inode.h +++ b/fs/gfs2/inode.h @@ -10,17 +10,17 @@ #ifndef __INODE_DOT_H__ #define __INODE_DOT_H__ -static inline int gfs2_is_stuffed(struct gfs2_inode *ip) +static inline int gfs2_is_stuffed(const struct gfs2_inode *ip) { return !ip->i_di.di_height; } -static inline int gfs2_is_jdata(struct gfs2_inode *ip) +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_dir(struct gfs2_inode *ip) +static inline int gfs2_is_dir(const struct gfs2_inode *ip) { return S_ISDIR(ip->i_inode.i_mode); } @@ -32,9 +32,25 @@ static inline void gfs2_set_inode_blocks(struct inode *inode) (GFS2_SB(inode)->sd_sb.sb_bsize_shift - GFS2_BASIC_BLOCK_SHIFT); } +static inline int gfs2_check_inum(const struct gfs2_inode *ip, u64 no_addr, + u64 no_formal_ino) +{ + return ip->i_no_addr == no_addr && ip->i_no_formal_ino == no_formal_ino; +} + +static inline void gfs2_inum_out(const struct gfs2_inode *ip, + struct gfs2_dirent *dent) +{ + dent->de_inum.no_formal_ino = cpu_to_be64(ip->i_no_formal_ino); + dent->de_inum.no_addr = cpu_to_be64(ip->i_no_addr); +} + + void gfs2_inode_attr_in(struct gfs2_inode *ip); -struct inode *gfs2_inode_lookup(struct super_block *sb, struct gfs2_inum_host *inum, unsigned type); -struct inode *gfs2_ilookup(struct super_block *sb, struct gfs2_inum_host *inum); +void gfs2_set_iop(struct inode *inode); +struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, + u64 no_addr, u64 no_formal_ino); +struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr); int gfs2_inode_refresh(struct gfs2_inode *ip); @@ -47,12 +63,14 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name, int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name, struct gfs2_inode *ip); int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name, - struct gfs2_inode *ip); + const struct gfs2_inode *ip); int gfs2_ok_to_move(struct gfs2_inode *this, struct gfs2_inode *to); int gfs2_readlinki(struct gfs2_inode *ip, char **buf, unsigned int *len); int gfs2_glock_nq_atime(struct gfs2_holder *gh); int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr); struct inode *gfs2_lookup_simple(struct inode *dip, const char *name); +void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf); +void gfs2_dinode_print(const struct gfs2_inode *ip); #endif /* __INODE_DOT_H__ */ diff --git a/fs/gfs2/locking/dlm/lock.c b/fs/gfs2/locking/dlm/lock.c index c305255bfe8..542a797ac89 100644 --- a/fs/gfs2/locking/dlm/lock.c +++ b/fs/gfs2/locking/dlm/lock.c @@ -174,7 +174,6 @@ static int gdlm_create_lp(struct gdlm_ls *ls, struct lm_lockname *name, lp->cur = DLM_LOCK_IV; lp->lvb = NULL; lp->hold_null = NULL; - init_completion(&lp->ast_wait); INIT_LIST_HEAD(&lp->clist); INIT_LIST_HEAD(&lp->blist); INIT_LIST_HEAD(&lp->delay_list); @@ -399,6 +398,12 @@ static void gdlm_del_lvb(struct gdlm_lock *lp) lp->lksb.sb_lvbptr = NULL; } +static int gdlm_ast_wait(void *word) +{ + schedule(); + return 0; +} + /* This can do a synchronous dlm request (requiring a lock_dlm thread to get the completion) because gfs won't call hold_lvb() during a callback (from the context of a lock_dlm thread). */ @@ -424,10 +429,10 @@ static int hold_null_lock(struct gdlm_lock *lp) lpn->lkf = DLM_LKF_VALBLK | DLM_LKF_EXPEDITE; set_bit(LFL_NOBAST, &lpn->flags); set_bit(LFL_INLOCK, &lpn->flags); + set_bit(LFL_AST_WAIT, &lpn->flags); - init_completion(&lpn->ast_wait); gdlm_do_lock(lpn); - wait_for_completion(&lpn->ast_wait); + wait_on_bit(&lpn->flags, LFL_AST_WAIT, gdlm_ast_wait, TASK_UNINTERRUPTIBLE); error = lpn->lksb.sb_status; if (error) { printk(KERN_INFO "lock_dlm: hold_null_lock dlm error %d\n", diff --git a/fs/gfs2/locking/dlm/lock_dlm.h b/fs/gfs2/locking/dlm/lock_dlm.h index d074c6e6f9b..24d70f73b65 100644 --- a/fs/gfs2/locking/dlm/lock_dlm.h +++ b/fs/gfs2/locking/dlm/lock_dlm.h @@ -101,6 +101,7 @@ enum { LFL_NOBAST = 10, LFL_HEADQUE = 11, LFL_UNLOCK_DELETE = 12, + LFL_AST_WAIT = 13, }; struct gdlm_lock { @@ -117,7 +118,6 @@ struct gdlm_lock { unsigned long flags; /* lock_dlm flags LFL_ */ int bast_mode; /* protected by async_lock */ - struct completion ast_wait; struct list_head clist; /* complete */ struct list_head blist; /* blocking */ diff --git a/fs/gfs2/locking/dlm/mount.c b/fs/gfs2/locking/dlm/mount.c index 1d8faa3da8a..41c5b04caab 100644 --- a/fs/gfs2/locking/dlm/mount.c +++ b/fs/gfs2/locking/dlm/mount.c @@ -147,7 +147,7 @@ static int gdlm_mount(char *table_name, char *host_data, error = dlm_new_lockspace(ls->fsname, strlen(ls->fsname), &ls->dlm_lockspace, - nodir ? DLM_LSFL_NODIR : 0, + DLM_LSFL_FS | (nodir ? DLM_LSFL_NODIR : 0), GDLM_LVB_SIZE); if (error) { log_error("dlm_new_lockspace error %d", error); diff --git a/fs/gfs2/locking/dlm/plock.c b/fs/gfs2/locking/dlm/plock.c index f82495e18c2..fba1f1d87e4 100644 --- a/fs/gfs2/locking/dlm/plock.c +++ b/fs/gfs2/locking/dlm/plock.c @@ -242,7 +242,7 @@ 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; send_op(op); wait_event(recv_wq, (op->done != 0)); @@ -254,16 +254,20 @@ int gdlm_plock_get(void *lockspace, struct lm_lockname *name, } spin_unlock(&ops_lock); + /* info.rv from userspace is 1 for conflict, 0 for no-conflict, + -ENOENT if there are no locks on the file */ + rv = op->info.rv; fl->fl_type = F_UNLCK; if (rv == -ENOENT) rv = 0; - else if (rv == 0 && op->info.pid != fl->fl_pid) { + else if (rv > 0) { fl->fl_type = (op->info.ex) ? F_WRLCK : F_RDLCK; fl->fl_pid = op->info.pid; fl->fl_start = op->info.start; fl->fl_end = op->info.end; + rv = 0; } kfree(op); diff --git a/fs/gfs2/locking/dlm/thread.c b/fs/gfs2/locking/dlm/thread.c index 9cf1f168eaf..1aca51e4509 100644 --- a/fs/gfs2/locking/dlm/thread.c +++ b/fs/gfs2/locking/dlm/thread.c @@ -44,6 +44,13 @@ static void process_blocking(struct gdlm_lock *lp, int bast_mode) ls->fscb(ls->sdp, cb, &lp->lockname); } +static void wake_up_ast(struct gdlm_lock *lp) +{ + clear_bit(LFL_AST_WAIT, &lp->flags); + smp_mb__after_clear_bit(); + wake_up_bit(&lp->flags, LFL_AST_WAIT); +} + static void process_complete(struct gdlm_lock *lp) { struct gdlm_ls *ls = lp->ls; @@ -136,7 +143,7 @@ static void process_complete(struct gdlm_lock *lp) */ if (test_and_clear_bit(LFL_SYNC_LVB, &lp->flags)) { - complete(&lp->ast_wait); + wake_up_ast(lp); return; } @@ -214,7 +221,7 @@ out: if (test_bit(LFL_INLOCK, &lp->flags)) { clear_bit(LFL_NOBLOCK, &lp->flags); lp->cur = lp->req; - complete(&lp->ast_wait); + wake_up_ast(lp); return; } diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 291415ddfe5..f49a12e2408 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -83,6 +83,11 @@ static void gfs2_ail1_start_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai) gfs2_assert(sdp, bd->bd_ail == ai); + if (!bh){ + list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list); + continue; + } + if (!buffer_busy(bh)) { if (!buffer_uptodate(bh)) { gfs2_log_unlock(sdp); @@ -125,6 +130,11 @@ static int gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai, int fl bd_ail_st_list) { bh = bd->bd_bh; + if (!bh){ + list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list); + continue; + } + gfs2_assert(sdp, bd->bd_ail == ai); if (buffer_busy(bh)) { @@ -262,8 +272,8 @@ static void ail2_empty(struct gfs2_sbd *sdp, unsigned int new_tail) * @sdp: The GFS2 superblock * @blks: The number of blocks to reserve * - * Note that we never give out the last 6 blocks of the journal. Thats - * due to the fact that there is are a small number of header blocks + * Note that we never give out the last few blocks of the journal. Thats + * due to the fact that there is a small number of header blocks * associated with each log flush. The exact number can't be known until * flush time, so we ensure that we have just enough free blocks at all * times to avoid running out during a log flush. @@ -274,6 +284,7 @@ static void ail2_empty(struct gfs2_sbd *sdp, unsigned int new_tail) int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks) { unsigned int try = 0; + unsigned reserved_blks = 6 * (4096 / sdp->sd_vfs->s_blocksize); if (gfs2_assert_warn(sdp, blks) || gfs2_assert_warn(sdp, blks <= sdp->sd_jdesc->jd_blocks)) @@ -281,7 +292,7 @@ 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 + 6)) { + while(sdp->sd_log_blks_free <= (blks + reserved_blks)) { gfs2_log_unlock(sdp); gfs2_ail1_empty(sdp, 0); gfs2_log_flush(sdp, NULL); @@ -357,6 +368,58 @@ static inline unsigned int log_distance(struct gfs2_sbd *sdp, unsigned int newer return dist; } +/** + * calc_reserved - Calculate the number of blocks to reserve when + * refunding a transaction's unused buffers. + * @sdp: The GFS2 superblock + * + * This is complex. We need to reserve room for all our currently used + * metadata buffers (e.g. normal file I/O rewriting file time stamps) and + * all our journaled data buffers for journaled files (e.g. files in the + * meta_fs like rindex, or files for which chattr +j was done.) + * If we don't reserve enough space, gfs2_log_refund and gfs2_log_flush + * will count it as free space (sd_log_blks_free) and corruption will follow. + * + * We can have metadata bufs and jdata bufs in the same journal. So each + * type gets its own log header, for which we need to reserve a block. + * In fact, each type has the potential for needing more than one header + * in cases where we have more buffers than will fit on a journal page. + * Metadata journal entries take up half the space of journaled buffer entries. + * Thus, metadata entries have buf_limit (502) and journaled buffers have + * databuf_limit (251) before they cause a wrap around. + * + * Also, we need to reserve blocks for revoke journal entries and one for an + * overall header for the lot. + * + * Returns: the number of blocks reserved + */ +static unsigned int calc_reserved(struct gfs2_sbd *sdp) +{ + unsigned int reserved = 0; + unsigned int mbuf_limit, metabufhdrs_needed; + unsigned int dbuf_limit, databufhdrs_needed; + unsigned int revokes = 0; + + mbuf_limit = buf_limit(sdp); + metabufhdrs_needed = (sdp->sd_log_commited_buf + + (mbuf_limit - 1)) / mbuf_limit; + dbuf_limit = databuf_limit(sdp); + databufhdrs_needed = (sdp->sd_log_commited_databuf + + (dbuf_limit - 1)) / dbuf_limit; + + if (sdp->sd_log_commited_revoke) + revokes = gfs2_struct2blk(sdp, sdp->sd_log_commited_revoke, + sizeof(u64)); + + reserved = sdp->sd_log_commited_buf + metabufhdrs_needed + + sdp->sd_log_commited_databuf + databufhdrs_needed + + revokes; + /* One for the overall header */ + if (reserved) + reserved++; + return reserved; +} + static unsigned int current_tail(struct gfs2_sbd *sdp) { struct gfs2_ail *ai; @@ -447,14 +510,14 @@ struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp, return bh; } -static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail, int pull) +static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail) { unsigned int dist = log_distance(sdp, new_tail, sdp->sd_log_tail); ail2_empty(sdp, new_tail); gfs2_log_lock(sdp); - sdp->sd_log_blks_free += dist - (pull ? 1 : 0); + sdp->sd_log_blks_free += dist; gfs2_assert_withdraw(sdp, sdp->sd_log_blks_free <= sdp->sd_jdesc->jd_blocks); gfs2_log_unlock(sdp); @@ -504,7 +567,7 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull) brelse(bh); if (sdp->sd_log_tail != tail) - log_pull_tail(sdp, tail, pull); + log_pull_tail(sdp, tail); else gfs2_assert_withdraw(sdp, !pull); @@ -517,6 +580,7 @@ static void log_flush_commit(struct gfs2_sbd *sdp) struct list_head *head = &sdp->sd_log_flush_list; struct gfs2_log_buf *lb; struct buffer_head *bh; + int flushcount = 0; while (!list_empty(head)) { lb = list_entry(head->next, struct gfs2_log_buf, lb_list); @@ -533,9 +597,20 @@ static void log_flush_commit(struct gfs2_sbd *sdp) } else brelse(bh); kfree(lb); + flushcount++; } - log_write_header(sdp, 0, 0); + /* If nothing was journaled, the header is unplanned and unwanted. */ + if (flushcount) { + log_write_header(sdp, 0, 0); + } else { + unsigned int tail; + tail = current_tail(sdp); + + gfs2_ail1_empty(sdp, 0); + if (sdp->sd_log_tail != tail) + log_pull_tail(sdp, tail); + } } /** @@ -565,7 +640,10 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl) INIT_LIST_HEAD(&ai->ai_ail1_list); INIT_LIST_HEAD(&ai->ai_ail2_list); - gfs2_assert_withdraw(sdp, sdp->sd_log_num_buf == sdp->sd_log_commited_buf); + gfs2_assert_withdraw(sdp, + sdp->sd_log_num_buf + sdp->sd_log_num_jdata == + sdp->sd_log_commited_buf + + sdp->sd_log_commited_databuf); gfs2_assert_withdraw(sdp, sdp->sd_log_num_revoke == sdp->sd_log_commited_revoke); @@ -576,16 +654,19 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl) lops_before_commit(sdp); if (!list_empty(&sdp->sd_log_flush_list)) log_flush_commit(sdp); - else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle) + 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 */ + gfs2_log_unlock(sdp); log_write_header(sdp, 0, PULL); + } lops_after_commit(sdp, ai); gfs2_log_lock(sdp); sdp->sd_log_head = sdp->sd_log_flush_head; - sdp->sd_log_blks_free -= sdp->sd_log_num_hdrs; sdp->sd_log_blks_reserved = 0; sdp->sd_log_commited_buf = 0; - sdp->sd_log_num_hdrs = 0; + sdp->sd_log_commited_databuf = 0; sdp->sd_log_commited_revoke = 0; if (!list_empty(&ai->ai_ail1_list)) { @@ -602,32 +683,26 @@ 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 = 0; + unsigned int reserved; unsigned int old; gfs2_log_lock(sdp); sdp->sd_log_commited_buf += tr->tr_num_buf_new - tr->tr_num_buf_rm; - gfs2_assert_withdraw(sdp, ((int)sdp->sd_log_commited_buf) >= 0); + sdp->sd_log_commited_databuf += tr->tr_num_databuf_new - + tr->tr_num_databuf_rm; + gfs2_assert_withdraw(sdp, (((int)sdp->sd_log_commited_buf) >= 0) || + (((int)sdp->sd_log_commited_databuf) >= 0)); 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); - - if (sdp->sd_log_commited_buf) - reserved += sdp->sd_log_commited_buf; - if (sdp->sd_log_commited_revoke) - reserved += gfs2_struct2blk(sdp, sdp->sd_log_commited_revoke, - sizeof(u64)); - if (reserved) - reserved++; - + 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 <= sdp->sd_jdesc->jd_blocks + - sdp->sd_log_num_hdrs); + gfs2_assert_withdraw(sdp, sdp->sd_log_blks_free <= + sdp->sd_jdesc->jd_blocks); sdp->sd_log_blks_reserved = reserved; @@ -673,13 +748,13 @@ void gfs2_log_shutdown(struct gfs2_sbd *sdp) gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke); gfs2_assert_withdraw(sdp, !sdp->sd_log_num_rg); gfs2_assert_withdraw(sdp, !sdp->sd_log_num_databuf); - gfs2_assert_withdraw(sdp, !sdp->sd_log_num_hdrs); gfs2_assert_withdraw(sdp, list_empty(&sdp->sd_ail1_list)); sdp->sd_log_flush_head = sdp->sd_log_head; sdp->sd_log_flush_wrapped = 0; - log_write_header(sdp, GFS2_LOG_HEAD_UNMOUNT, 0); + 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, sdp->sd_log_head == sdp->sd_log_tail); diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index f82d84d05d2..aff70f0698f 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -17,6 +17,7 @@ #include "gfs2.h" #include "incore.h" +#include "inode.h" #include "glock.h" #include "log.h" #include "lops.h" @@ -117,15 +118,13 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp) struct gfs2_log_descriptor *ld; struct gfs2_bufdata *bd1 = NULL, *bd2; unsigned int total = sdp->sd_log_num_buf; - unsigned int offset = sizeof(struct gfs2_log_descriptor); + unsigned int offset = BUF_OFFSET; unsigned int limit; unsigned int num; unsigned n; __be64 *ptr; - offset += sizeof(__be64) - 1; - offset &= ~(sizeof(__be64) - 1); - limit = (sdp->sd_sb.sb_bsize - offset)/sizeof(__be64); + limit = buf_limit(sdp); /* for 4k blocks, limit = 503 */ bd1 = bd2 = list_prepare_entry(bd1, &sdp->sd_log_le_buf, bd_le.le_list); @@ -134,7 +133,6 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp) if (total > limit) num = limit; bh = gfs2_log_get_buf(sdp); - sdp->sd_log_num_hdrs++; ld = (struct gfs2_log_descriptor *)bh->b_data; ptr = (__be64 *)(bh->b_data + offset); ld->ld_header.mh_magic = cpu_to_be32(GFS2_MAGIC); @@ -469,25 +467,28 @@ static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) struct gfs2_inode *ip = GFS2_I(mapping->host); gfs2_log_lock(sdp); + if (!list_empty(&bd->bd_list_tr)) { + gfs2_log_unlock(sdp); + return; + } tr->tr_touched = 1; - if (list_empty(&bd->bd_list_tr) && - (ip->i_di.di_flags & GFS2_DIF_JDATA)) { + if (gfs2_is_jdata(ip)) { tr->tr_num_buf++; list_add(&bd->bd_list_tr, &tr->tr_list_buf); - gfs2_log_unlock(sdp); - gfs2_pin(sdp, bd->bd_bh); - tr->tr_num_buf_new++; - } else { - gfs2_log_unlock(sdp); } + gfs2_log_unlock(sdp); + if (!list_empty(&le->le_list)) + return; + gfs2_trans_add_gl(bd->bd_gl); - gfs2_log_lock(sdp); - if (list_empty(&le->le_list)) { - if (ip->i_di.di_flags & GFS2_DIF_JDATA) - sdp->sd_log_num_jdata++; - sdp->sd_log_num_databuf++; - list_add(&le->le_list, &sdp->sd_log_le_databuf); + if (gfs2_is_jdata(ip)) { + sdp->sd_log_num_jdata++; + gfs2_pin(sdp, bd->bd_bh); + tr->tr_num_databuf_new++; } + sdp->sd_log_num_databuf++; + gfs2_log_lock(sdp); + list_add(&le->le_list, &sdp->sd_log_le_databuf); gfs2_log_unlock(sdp); } @@ -520,7 +521,6 @@ static void databuf_lo_before_commit(struct gfs2_sbd *sdp) LIST_HEAD(started); struct gfs2_bufdata *bd1 = NULL, *bd2, *bdt; struct buffer_head *bh = NULL,*bh1 = NULL; - unsigned int offset = sizeof(struct gfs2_log_descriptor); struct gfs2_log_descriptor *ld; unsigned int limit; unsigned int total_dbuf = sdp->sd_log_num_databuf; @@ -528,9 +528,7 @@ static void databuf_lo_before_commit(struct gfs2_sbd *sdp) unsigned int num, n; __be64 *ptr = NULL; - offset += 2*sizeof(__be64) - 1; - offset &= ~(2*sizeof(__be64) - 1); - limit = (sdp->sd_sb.sb_bsize - offset)/sizeof(__be64); + limit = databuf_limit(sdp); /* * Start writing ordered buffers, write journaled buffers @@ -581,10 +579,10 @@ static void databuf_lo_before_commit(struct gfs2_sbd *sdp) gfs2_log_unlock(sdp); if (!bh) { bh = gfs2_log_get_buf(sdp); - sdp->sd_log_num_hdrs++; ld = (struct gfs2_log_descriptor *) bh->b_data; - ptr = (__be64 *)(bh->b_data + offset); + ptr = (__be64 *)(bh->b_data + + DATABUF_OFFSET); ld->ld_header.mh_magic = cpu_to_be32(GFS2_MAGIC); ld->ld_header.mh_type = @@ -605,7 +603,7 @@ static void databuf_lo_before_commit(struct gfs2_sbd *sdp) if (unlikely(magic != 0)) set_buffer_escaped(bh1); gfs2_log_lock(sdp); - if (n++ > num) + if (++n >= num) break; } else if (!bh1) { total_dbuf--; @@ -622,6 +620,7 @@ static void databuf_lo_before_commit(struct gfs2_sbd *sdp) } gfs2_log_unlock(sdp); if (bh) { + set_buffer_mapped(bh); set_buffer_dirty(bh); ll_rw_block(WRITE, 1, &bh); bh = NULL; diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h index 965bc65c7c6..41a00df7558 100644 --- a/fs/gfs2/lops.h +++ b/fs/gfs2/lops.h @@ -13,6 +13,13 @@ #include <linux/list.h> #include "incore.h" +#define BUF_OFFSET \ + ((sizeof(struct gfs2_log_descriptor) + sizeof(__be64) - 1) & \ + ~(sizeof(__be64) - 1)) +#define DATABUF_OFFSET \ + ((sizeof(struct gfs2_log_descriptor) + (2 * sizeof(__be64) - 1)) & \ + ~(2 * sizeof(__be64) - 1)) + extern const struct gfs2_log_operations gfs2_glock_lops; extern const struct gfs2_log_operations gfs2_buf_lops; extern const struct gfs2_log_operations gfs2_revoke_lops; @@ -21,6 +28,22 @@ extern const struct gfs2_log_operations gfs2_databuf_lops; extern const struct gfs2_log_operations *gfs2_log_ops[]; +static inline unsigned int buf_limit(struct gfs2_sbd *sdp) +{ + unsigned int limit; + + limit = (sdp->sd_sb.sb_bsize - BUF_OFFSET) / sizeof(__be64); + return limit; +} + +static inline unsigned int databuf_limit(struct gfs2_sbd *sdp) +{ + unsigned int limit; + + limit = (sdp->sd_sb.sb_bsize - DATABUF_OFFSET) / (2 * sizeof(__be64)); + return limit; +} + static inline void lops_init_le(struct gfs2_log_element *le, const struct gfs2_log_operations *lops) { diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index e62d4f620c5..8da343b34ae 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -387,12 +387,18 @@ void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen) if (test_clear_buffer_pinned(bh)) { struct gfs2_trans *tr = current->journal_info; + struct gfs2_inode *bh_ip = + GFS2_I(bh->b_page->mapping->host); + gfs2_log_lock(sdp); list_del_init(&bd->bd_le.le_list); gfs2_assert_warn(sdp, sdp->sd_log_num_buf); sdp->sd_log_num_buf--; gfs2_log_unlock(sdp); - tr->tr_num_buf_rm++; + if (bh_ip->i_inode.i_private != NULL) + tr->tr_num_databuf_rm++; + else + tr->tr_num_buf_rm++; brelse(bh); } if (bd) { diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h index e037425bc04..527bf19d969 100644 --- a/fs/gfs2/meta_io.h +++ b/fs/gfs2/meta_io.h @@ -63,7 +63,7 @@ int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num, static inline int gfs2_meta_inode_buffer(struct gfs2_inode *ip, struct buffer_head **bhp) { - return gfs2_meta_indirect_buffer(ip, 0, ip->i_num.no_addr, 0, bhp); + return gfs2_meta_indirect_buffer(ip, 0, ip->i_no_addr, 0, bhp); } struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen); diff --git a/fs/gfs2/mount.c b/fs/gfs2/mount.c index 4864659555d..6f006a804db 100644 --- a/fs/gfs2/mount.c +++ b/fs/gfs2/mount.c @@ -82,20 +82,19 @@ int gfs2_mount_args(struct gfs2_sbd *sdp, char *data_arg, int remount) char *options, *o, *v; int error = 0; - if (!remount) { - /* If someone preloaded options, use those instead */ - spin_lock(&gfs2_sys_margs_lock); - if (gfs2_sys_margs) { - data = gfs2_sys_margs; - gfs2_sys_margs = NULL; - } - spin_unlock(&gfs2_sys_margs_lock); - - /* Set some defaults */ - args->ar_num_glockd = GFS2_GLOCKD_DEFAULT; - args->ar_quota = GFS2_QUOTA_DEFAULT; - args->ar_data = GFS2_DATA_DEFAULT; + /* If someone preloaded options, use those instead */ + spin_lock(&gfs2_sys_margs_lock); + if (!remount && gfs2_sys_margs) { + data = gfs2_sys_margs; + gfs2_sys_margs = NULL; } + spin_unlock(&gfs2_sys_margs_lock); + + /* Set some defaults */ + memset(args, 0, sizeof(struct gfs2_args)); + args->ar_num_glockd = GFS2_GLOCKD_DEFAULT; + args->ar_quota = GFS2_QUOTA_DEFAULT; + args->ar_data = GFS2_DATA_DEFAULT; /* Split the options into tokens with the "," character and process them */ diff --git a/fs/gfs2/ondisk.c b/fs/gfs2/ondisk.c deleted file mode 100644 index d9ecfd23a49..00000000000 --- a/fs/gfs2/ondisk.c +++ /dev/null @@ -1,251 +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 "gfs2.h" -#include <linux/gfs2_ondisk.h> -#include <linux/lm_interface.h> -#include "incore.h" - -#define pv(struct, member, fmt) printk(KERN_INFO " "#member" = "fmt"\n", \ - struct->member); - -/* - * gfs2_xxx_in - read in an xxx struct - * first arg: the cpu-order structure - * buf: the disk-order buffer - * - * gfs2_xxx_out - write out an xxx struct - * first arg: the cpu-order structure - * buf: the disk-order buffer - * - * gfs2_xxx_print - print out an xxx struct - * first arg: the cpu-order structure - */ - -void gfs2_inum_in(struct gfs2_inum_host *no, const void *buf) -{ - const struct gfs2_inum *str = buf; - - no->no_formal_ino = be64_to_cpu(str->no_formal_ino); - no->no_addr = be64_to_cpu(str->no_addr); -} - -void gfs2_inum_out(const struct gfs2_inum_host *no, void *buf) -{ - struct gfs2_inum *str = buf; - - str->no_formal_ino = cpu_to_be64(no->no_formal_ino); - str->no_addr = cpu_to_be64(no->no_addr); -} - -static void gfs2_inum_print(const struct gfs2_inum_host *no) -{ - printk(KERN_INFO " no_formal_ino = %llu\n", (unsigned long long)no->no_formal_ino); - printk(KERN_INFO " no_addr = %llu\n", (unsigned long long)no->no_addr); -} - -static void gfs2_meta_header_in(struct gfs2_meta_header_host *mh, const void *buf) -{ - const struct gfs2_meta_header *str = buf; - - mh->mh_magic = be32_to_cpu(str->mh_magic); - mh->mh_type = be32_to_cpu(str->mh_type); - mh->mh_format = be32_to_cpu(str->mh_format); -} - -void gfs2_sb_in(struct gfs2_sb_host *sb, const void *buf) -{ - const struct gfs2_sb *str = buf; - - gfs2_meta_header_in(&sb->sb_header, buf); - - sb->sb_fs_format = be32_to_cpu(str->sb_fs_format); - sb->sb_multihost_format = be32_to_cpu(str->sb_multihost_format); - sb->sb_bsize = be32_to_cpu(str->sb_bsize); - sb->sb_bsize_shift = be32_to_cpu(str->sb_bsize_shift); - - gfs2_inum_in(&sb->sb_master_dir, (char *)&str->sb_master_dir); - gfs2_inum_in(&sb->sb_root_dir, (char *)&str->sb_root_dir); - - memcpy(sb->sb_lockproto, str->sb_lockproto, GFS2_LOCKNAME_LEN); - memcpy(sb->sb_locktable, str->sb_locktable, GFS2_LOCKNAME_LEN); -} - -void gfs2_rindex_in(struct gfs2_rindex_host *ri, const void *buf) -{ - const struct gfs2_rindex *str = buf; - - ri->ri_addr = be64_to_cpu(str->ri_addr); - ri->ri_length = be32_to_cpu(str->ri_length); - ri->ri_data0 = be64_to_cpu(str->ri_data0); - ri->ri_data = be32_to_cpu(str->ri_data); - ri->ri_bitbytes = be32_to_cpu(str->ri_bitbytes); - -} - -void gfs2_rindex_print(const struct gfs2_rindex_host *ri) -{ - printk(KERN_INFO " ri_addr = %llu\n", (unsigned long long)ri->ri_addr); - pv(ri, ri_length, "%u"); - - printk(KERN_INFO " ri_data0 = %llu\n", (unsigned long long)ri->ri_data0); - pv(ri, ri_data, "%u"); - - pv(ri, ri_bitbytes, "%u"); -} - -void gfs2_rgrp_in(struct gfs2_rgrp_host *rg, const void *buf) -{ - const struct gfs2_rgrp *str = buf; - - rg->rg_flags = be32_to_cpu(str->rg_flags); - rg->rg_free = be32_to_cpu(str->rg_free); - rg->rg_dinodes = be32_to_cpu(str->rg_dinodes); - rg->rg_igeneration = be64_to_cpu(str->rg_igeneration); -} - -void gfs2_rgrp_out(const struct gfs2_rgrp_host *rg, void *buf) -{ - struct gfs2_rgrp *str = buf; - - str->rg_flags = cpu_to_be32(rg->rg_flags); - str->rg_free = cpu_to_be32(rg->rg_free); - str->rg_dinodes = cpu_to_be32(rg->rg_dinodes); - str->__pad = cpu_to_be32(0); - str->rg_igeneration = cpu_to_be64(rg->rg_igeneration); - memset(&str->rg_reserved, 0, sizeof(str->rg_reserved)); -} - -void gfs2_quota_in(struct gfs2_quota_host *qu, const void *buf) -{ - const struct gfs2_quota *str = buf; - - qu->qu_limit = be64_to_cpu(str->qu_limit); - qu->qu_warn = be64_to_cpu(str->qu_warn); - qu->qu_value = be64_to_cpu(str->qu_value); -} - -void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf) -{ - const struct gfs2_dinode_host *di = &ip->i_di; - struct gfs2_dinode *str = buf; - - str->di_header.mh_magic = cpu_to_be32(GFS2_MAGIC); - str->di_header.mh_type = cpu_to_be32(GFS2_METATYPE_DI); - str->di_header.__pad0 = 0; - str->di_header.mh_format = cpu_to_be32(GFS2_FORMAT_DI); - str->di_header.__pad1 = 0; - - gfs2_inum_out(&ip->i_num, &str->di_num); - - str->di_mode = cpu_to_be32(ip->i_inode.i_mode); - str->di_uid = cpu_to_be32(ip->i_inode.i_uid); - str->di_gid = cpu_to_be32(ip->i_inode.i_gid); - str->di_nlink = cpu_to_be32(ip->i_inode.i_nlink); - str->di_size = cpu_to_be64(di->di_size); - str->di_blocks = cpu_to_be64(di->di_blocks); - str->di_atime = cpu_to_be64(ip->i_inode.i_atime.tv_sec); - str->di_mtime = cpu_to_be64(ip->i_inode.i_mtime.tv_sec); - str->di_ctime = cpu_to_be64(ip->i_inode.i_ctime.tv_sec); - - str->di_goal_meta = cpu_to_be64(di->di_goal_meta); - str->di_goal_data = cpu_to_be64(di->di_goal_data); - str->di_generation = cpu_to_be64(di->di_generation); - - str->di_flags = cpu_to_be32(di->di_flags); - str->di_height = cpu_to_be16(di->di_height); - str->di_payload_format = cpu_to_be32(S_ISDIR(ip->i_inode.i_mode) && - !(ip->i_di.di_flags & GFS2_DIF_EXHASH) ? - GFS2_FORMAT_DE : 0); - str->di_depth = cpu_to_be16(di->di_depth); - str->di_entries = cpu_to_be32(di->di_entries); - - str->di_eattr = cpu_to_be64(di->di_eattr); -} - -void gfs2_dinode_print(const struct gfs2_inode *ip) -{ - const struct gfs2_dinode_host *di = &ip->i_di; - - gfs2_inum_print(&ip->i_num); - - printk(KERN_INFO " di_size = %llu\n", (unsigned long long)di->di_size); - printk(KERN_INFO " di_blocks = %llu\n", (unsigned long long)di->di_blocks); - printk(KERN_INFO " di_goal_meta = %llu\n", (unsigned long long)di->di_goal_meta); - printk(KERN_INFO " di_goal_data = %llu\n", (unsigned long long)di->di_goal_data); - - pv(di, di_flags, "0x%.8X"); - pv(di, di_height, "%u"); - - pv(di, di_depth, "%u"); - pv(di, di_entries, "%u"); - - printk(KERN_INFO " di_eattr = %llu\n", (unsigned long long)di->di_eattr); -} - -void gfs2_log_header_in(struct gfs2_log_header_host *lh, const void *buf) -{ - const struct gfs2_log_header *str = buf; - - gfs2_meta_header_in(&lh->lh_header, buf); - lh->lh_sequence = be64_to_cpu(str->lh_sequence); - lh->lh_flags = be32_to_cpu(str->lh_flags); - lh->lh_tail = be32_to_cpu(str->lh_tail); - lh->lh_blkno = be32_to_cpu(str->lh_blkno); - lh->lh_hash = be32_to_cpu(str->lh_hash); -} - -void gfs2_inum_range_in(struct gfs2_inum_range_host *ir, const void *buf) -{ - const struct gfs2_inum_range *str = buf; - - ir->ir_start = be64_to_cpu(str->ir_start); - ir->ir_length = be64_to_cpu(str->ir_length); -} - -void gfs2_inum_range_out(const struct gfs2_inum_range_host *ir, void *buf) -{ - struct gfs2_inum_range *str = buf; - - str->ir_start = cpu_to_be64(ir->ir_start); - str->ir_length = cpu_to_be64(ir->ir_length); -} - -void gfs2_statfs_change_in(struct gfs2_statfs_change_host *sc, const void *buf) -{ - const struct gfs2_statfs_change *str = buf; - - sc->sc_total = be64_to_cpu(str->sc_total); - sc->sc_free = be64_to_cpu(str->sc_free); - sc->sc_dinodes = be64_to_cpu(str->sc_dinodes); -} - -void gfs2_statfs_change_out(const struct gfs2_statfs_change_host *sc, void *buf) -{ - struct gfs2_statfs_change *str = buf; - - str->sc_total = cpu_to_be64(sc->sc_total); - str->sc_free = cpu_to_be64(sc->sc_free); - str->sc_dinodes = cpu_to_be64(sc->sc_dinodes); -} - -void gfs2_quota_change_in(struct gfs2_quota_change_host *qc, const void *buf) -{ - const struct gfs2_quota_change *str = buf; - - qc->qc_change = be64_to_cpu(str->qc_change); - qc->qc_flags = be32_to_cpu(str->qc_flags); - qc->qc_id = be32_to_cpu(str->qc_id); -} - diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/ops_address.c index 30c15622174..26c888890c2 100644 --- a/fs/gfs2/ops_address.c +++ b/fs/gfs2/ops_address.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 @@ -32,6 +32,7 @@ #include "trans.h" #include "rgrp.h" #include "ops_file.h" +#include "super.h" #include "util.h" #include "glops.h" @@ -49,6 +50,8 @@ static void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page, end = start + bsize; if (end <= from || start >= to) continue; + if (gfs2_is_jdata(ip)) + set_buffer_uptodate(bh); gfs2_trans_add_bh(ip->i_gl, bh, 0); } } @@ -134,7 +137,9 @@ static int gfs2_writepage(struct page *page, struct writeback_control *wbc) return 0; /* don't care */ } - if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip)) { + if ((sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip)) && + PageChecked(page)) { + ClearPageChecked(page); error = gfs2_trans_begin(sdp, RES_DINODE + 1, 0); if (error) goto out_ignore; @@ -203,11 +208,7 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page) * so we need to supply one here. It doesn't happen often. */ if (unlikely(page->index)) { - kaddr = kmap_atomic(page, KM_USER0); - memset(kaddr, 0, PAGE_CACHE_SIZE); - kunmap_atomic(kaddr, KM_USER0); - flush_dcache_page(page); - SetPageUptodate(page); + zero_user_page(page, 0, PAGE_CACHE_SIZE, KM_USER0); return 0; } @@ -450,6 +451,31 @@ out_uninit: } /** + * adjust_fs_space - Adjusts the free space available due to gfs2_grow + * @inode: the rindex inode + */ +static void adjust_fs_space(struct inode *inode) +{ + struct gfs2_sbd *sdp = inode->i_sb->s_fs_info; + struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master; + struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local; + u64 fs_total, new_free; + + /* Total up the file system space, according to the latest rindex. */ + fs_total = gfs2_ri_total(sdp); + + spin_lock(&sdp->sd_statfs_spin); + if (fs_total > (m_sc->sc_total + l_sc->sc_total)) + new_free = fs_total - (m_sc->sc_total + l_sc->sc_total); + else + new_free = 0; + spin_unlock(&sdp->sd_statfs_spin); + fs_warn(sdp, "File system extended by %llu blocks.\n", + (unsigned long long)new_free); + gfs2_statfs_change(sdp, new_free, new_free, 0); +} + +/** * gfs2_commit_write - Commit write to a file * @file: The file to write to * @page: The page containing the data @@ -511,6 +537,9 @@ static int gfs2_commit_write(struct file *file, struct page *page, di->di_size = cpu_to_be64(inode->i_size); } + if (inode == sdp->sd_rindex) + adjust_fs_space(inode); + brelse(dibh); gfs2_trans_end(sdp); if (al->al_requested) { @@ -543,6 +572,23 @@ fail_nounlock: } /** + * gfs2_set_page_dirty - Page dirtying function + * @page: The page to dirty + * + * Returns: 1 if it dirtyed the page, or 0 otherwise + */ + +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); + return __set_page_dirty_buffers(page); +} + +/** * gfs2_bmap - Block map function * @mapping: Address space info * @lblock: The block to map @@ -578,6 +624,8 @@ static void discard_buffer(struct gfs2_sbd *sdp, struct buffer_head *bh) if (bd) { bd->bd_bh = NULL; bh->b_private = NULL; + if (!bd->bd_ail && list_empty(&bd->bd_le.le_list)) + kmem_cache_free(gfs2_bufdata_cachep, bd); } gfs2_log_unlock(sdp); @@ -598,6 +646,8 @@ static void gfs2_invalidatepage(struct page *page, unsigned long offset) unsigned int curr_off = 0; BUG_ON(!PageLocked(page)); + if (offset == 0) + ClearPageChecked(page); if (!page_has_buffers(page)) return; @@ -728,8 +778,8 @@ static unsigned limit = 0; return; fs_warn(sdp, "ip = %llu %llu\n", - (unsigned long long)ip->i_num.no_formal_ino, - (unsigned long long)ip->i_num.no_addr); + (unsigned long long)ip->i_no_formal_ino, + (unsigned long long)ip->i_no_addr); for (x = 0; x < GFS2_MAX_META_HEIGHT; x++) fs_warn(sdp, "ip->i_cache[%u] = %s\n", @@ -810,6 +860,7 @@ const struct address_space_operations gfs2_file_aops = { .sync_page = block_sync_page, .prepare_write = gfs2_prepare_write, .commit_write = gfs2_commit_write, + .set_page_dirty = gfs2_set_page_dirty, .bmap = gfs2_bmap, .invalidatepage = gfs2_invalidatepage, .releasepage = gfs2_releasepage, diff --git a/fs/gfs2/ops_address.h b/fs/gfs2/ops_address.h index 35aaee4aa7e..fa1b5b3d28b 100644 --- a/fs/gfs2/ops_address.h +++ b/fs/gfs2/ops_address.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 diff --git a/fs/gfs2/ops_dentry.c b/fs/gfs2/ops_dentry.c index a6fdc52f554..793e334d098 100644 --- a/fs/gfs2/ops_dentry.c +++ b/fs/gfs2/ops_dentry.c @@ -21,6 +21,7 @@ #include "glock.h" #include "ops_dentry.h" #include "util.h" +#include "inode.h" /** * gfs2_drevalidate - Check directory lookup consistency @@ -40,14 +41,15 @@ static int gfs2_drevalidate(struct dentry *dentry, struct nameidata *nd) struct gfs2_inode *dip = GFS2_I(parent->d_inode); struct inode *inode = dentry->d_inode; struct gfs2_holder d_gh; - struct gfs2_inode *ip; - struct gfs2_inum_host inum; - unsigned int type; + struct gfs2_inode *ip = NULL; int error; int had_lock=0; - if (inode && is_bad_inode(inode)) - goto invalid; + if (inode) { + if (is_bad_inode(inode)) + goto invalid; + ip = GFS2_I(inode); + } if (sdp->sd_args.ar_localcaching) goto valid; @@ -59,7 +61,7 @@ static int gfs2_drevalidate(struct dentry *dentry, struct nameidata *nd) goto fail; } - error = gfs2_dir_search(parent->d_inode, &dentry->d_name, &inum, &type); + error = gfs2_dir_check(parent->d_inode, &dentry->d_name, ip); switch (error) { case 0: if (!inode) @@ -73,16 +75,6 @@ static int gfs2_drevalidate(struct dentry *dentry, struct nameidata *nd) goto fail_gunlock; } - ip = GFS2_I(inode); - - if (!gfs2_inum_equal(&ip->i_num, &inum)) - goto invalid_gunlock; - - if (IF2DT(ip->i_inode.i_mode) != type) { - gfs2_consist_inode(dip); - goto fail_gunlock; - } - valid_gunlock: if (!had_lock) gfs2_glock_dq_uninit(&d_gh); diff --git a/fs/gfs2/ops_export.c b/fs/gfs2/ops_export.c index aad918337a4..99ea5659bc2 100644 --- a/fs/gfs2/ops_export.c +++ b/fs/gfs2/ops_export.c @@ -22,10 +22,14 @@ #include "glops.h" #include "inode.h" #include "ops_dentry.h" -#include "ops_export.h" +#include "ops_fstype.h" #include "rgrp.h" #include "util.h" +#define GFS2_SMALL_FH_SIZE 4 +#define GFS2_LARGE_FH_SIZE 8 +#define GFS2_OLD_FH_SIZE 10 + static struct dentry *gfs2_decode_fh(struct super_block *sb, __u32 *p, int fh_len, @@ -35,31 +39,28 @@ static struct dentry *gfs2_decode_fh(struct super_block *sb, void *context) { __be32 *fh = (__force __be32 *)p; - struct gfs2_fh_obj fh_obj; - struct gfs2_inum_host *this, parent; + struct gfs2_inum_host inum, parent; - this = &fh_obj.this; - fh_obj.imode = DT_UNKNOWN; memset(&parent, 0, sizeof(struct gfs2_inum)); switch (fh_len) { case GFS2_LARGE_FH_SIZE: + case GFS2_OLD_FH_SIZE: parent.no_formal_ino = ((u64)be32_to_cpu(fh[4])) << 32; parent.no_formal_ino |= be32_to_cpu(fh[5]); parent.no_addr = ((u64)be32_to_cpu(fh[6])) << 32; parent.no_addr |= be32_to_cpu(fh[7]); - fh_obj.imode = be32_to_cpu(fh[8]); case GFS2_SMALL_FH_SIZE: - this->no_formal_ino = ((u64)be32_to_cpu(fh[0])) << 32; - this->no_formal_ino |= be32_to_cpu(fh[1]); - this->no_addr = ((u64)be32_to_cpu(fh[2])) << 32; - this->no_addr |= be32_to_cpu(fh[3]); + inum.no_formal_ino = ((u64)be32_to_cpu(fh[0])) << 32; + inum.no_formal_ino |= be32_to_cpu(fh[1]); + inum.no_addr = ((u64)be32_to_cpu(fh[2])) << 32; + inum.no_addr |= be32_to_cpu(fh[3]); break; default: return NULL; } - return gfs2_export_ops.find_exported_dentry(sb, &fh_obj, &parent, + return gfs2_export_ops.find_exported_dentry(sb, &inum, &parent, acceptable, context); } @@ -75,10 +76,10 @@ static int gfs2_encode_fh(struct dentry *dentry, __u32 *p, int *len, (connectable && *len < GFS2_LARGE_FH_SIZE)) return 255; - fh[0] = cpu_to_be32(ip->i_num.no_formal_ino >> 32); - fh[1] = cpu_to_be32(ip->i_num.no_formal_ino & 0xFFFFFFFF); - fh[2] = cpu_to_be32(ip->i_num.no_addr >> 32); - fh[3] = cpu_to_be32(ip->i_num.no_addr & 0xFFFFFFFF); + fh[0] = cpu_to_be32(ip->i_no_formal_ino >> 32); + fh[1] = cpu_to_be32(ip->i_no_formal_ino & 0xFFFFFFFF); + fh[2] = cpu_to_be32(ip->i_no_addr >> 32); + fh[3] = cpu_to_be32(ip->i_no_addr & 0xFFFFFFFF); *len = GFS2_SMALL_FH_SIZE; if (!connectable || inode == sb->s_root->d_inode) @@ -90,13 +91,10 @@ static int gfs2_encode_fh(struct dentry *dentry, __u32 *p, int *len, igrab(inode); spin_unlock(&dentry->d_lock); - fh[4] = cpu_to_be32(ip->i_num.no_formal_ino >> 32); - fh[5] = cpu_to_be32(ip->i_num.no_formal_ino & 0xFFFFFFFF); - fh[6] = cpu_to_be32(ip->i_num.no_addr >> 32); - fh[7] = cpu_to_be32(ip->i_num.no_addr & 0xFFFFFFFF); - - fh[8] = cpu_to_be32(inode->i_mode); - fh[9] = 0; /* pad to double word */ + fh[4] = cpu_to_be32(ip->i_no_formal_ino >> 32); + fh[5] = cpu_to_be32(ip->i_no_formal_ino & 0xFFFFFFFF); + fh[6] = cpu_to_be32(ip->i_no_addr >> 32); + fh[7] = cpu_to_be32(ip->i_no_addr & 0xFFFFFFFF); *len = GFS2_LARGE_FH_SIZE; iput(inode); @@ -144,7 +142,8 @@ static int gfs2_get_name(struct dentry *parent, char *name, ip = GFS2_I(inode); *name = 0; - gnfd.inum = ip->i_num; + gnfd.inum.no_addr = ip->i_no_addr; + gnfd.inum.no_formal_ino = ip->i_no_formal_ino; gnfd.name = name; error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &gh); @@ -192,8 +191,7 @@ static struct dentry *gfs2_get_parent(struct dentry *child) static struct dentry *gfs2_get_dentry(struct super_block *sb, void *inum_obj) { struct gfs2_sbd *sdp = sb->s_fs_info; - struct gfs2_fh_obj *fh_obj = (struct gfs2_fh_obj *)inum_obj; - struct gfs2_inum_host *inum = &fh_obj->this; + struct gfs2_inum_host *inum = inum_obj; struct gfs2_holder i_gh, ri_gh, rgd_gh; struct gfs2_rgrpd *rgd; struct inode *inode; @@ -202,9 +200,9 @@ static struct dentry *gfs2_get_dentry(struct super_block *sb, void *inum_obj) /* System files? */ - inode = gfs2_ilookup(sb, inum); + inode = gfs2_ilookup(sb, inum->no_addr); if (inode) { - if (GFS2_I(inode)->i_num.no_formal_ino != inum->no_formal_ino) { + if (GFS2_I(inode)->i_no_formal_ino != inum->no_formal_ino) { iput(inode); return ERR_PTR(-ESTALE); } @@ -236,7 +234,9 @@ static struct dentry *gfs2_get_dentry(struct super_block *sb, void *inum_obj) gfs2_glock_dq_uninit(&rgd_gh); gfs2_glock_dq_uninit(&ri_gh); - inode = gfs2_inode_lookup(sb, inum, fh_obj->imode); + inode = gfs2_inode_lookup(sb, DT_UNKNOWN, + inum->no_addr, + 0); if (!inode) goto fail; if (IS_ERR(inode)) { @@ -250,6 +250,15 @@ static struct dentry *gfs2_get_dentry(struct super_block *sb, void *inum_obj) goto fail; } + /* Pick up the works we bypass in gfs2_inode_lookup */ + if (inode->i_state & I_NEW) + gfs2_set_iop(inode); + + if (GFS2_I(inode)->i_no_formal_ino != inum->no_formal_ino) { + iput(inode); + goto fail; + } + error = -EIO; if (GFS2_I(inode)->i_di.di_flags & GFS2_DIF_SYSTEM) { iput(inode); diff --git a/fs/gfs2/ops_export.h b/fs/gfs2/ops_export.h deleted file mode 100644 index f925a955b3b..00000000000 --- a/fs/gfs2/ops_export.h +++ /dev/null @@ -1,22 +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_EXPORT_DOT_H__ -#define __OPS_EXPORT_DOT_H__ - -#define GFS2_SMALL_FH_SIZE 4 -#define GFS2_LARGE_FH_SIZE 10 - -extern struct export_operations gfs2_export_ops; -struct gfs2_fh_obj { - struct gfs2_inum_host this; - __u32 imode; -}; - -#endif /* __OPS_EXPORT_DOT_H__ */ diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/ops_file.c index 064df880458..196d83266e3 100644 --- a/fs/gfs2/ops_file.c +++ b/fs/gfs2/ops_file.c @@ -502,7 +502,7 @@ static int gfs2_lock(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); struct lm_lockname name = - { .ln_number = ip->i_num.no_addr, + { .ln_number = ip->i_no_addr, .ln_type = LM_TYPE_PLOCK }; if (!(fl->fl_flags & FL_POSIX)) @@ -557,7 +557,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl) gfs2_glock_dq_uninit(fl_gh); } else { error = gfs2_glock_get(GFS2_SB(&ip->i_inode), - ip->i_num.no_addr, &gfs2_flock_glops, + ip->i_no_addr, &gfs2_flock_glops, CREATE, &gl); if (error) goto out; @@ -635,7 +635,6 @@ const struct file_operations gfs2_file_fops = { .release = gfs2_close, .fsync = gfs2_fsync, .lock = gfs2_lock, - .sendfile = generic_file_sendfile, .flock = gfs2_flock, .splice_read = generic_file_splice_read, .splice_write = generic_file_splice_write, diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 2c5f8e7def0..cf5aa505054 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -27,7 +27,6 @@ #include "inode.h" #include "lm.h" #include "mount.h" -#include "ops_export.h" #include "ops_fstype.h" #include "ops_super.h" #include "recovery.h" @@ -105,6 +104,7 @@ static void init_vfs(struct super_block *sb, unsigned noatime) sb->s_magic = GFS2_MAGIC; sb->s_op = &gfs2_super_ops; sb->s_export_op = &gfs2_export_ops; + sb->s_time_gran = 1; sb->s_maxbytes = MAX_LFS_FILESIZE; if (sb->s_flags & (MS_NOATIME | MS_NODIRATIME)) @@ -116,7 +116,6 @@ static void init_vfs(struct super_block *sb, unsigned noatime) static int init_names(struct gfs2_sbd *sdp, int silent) { - struct page *page; char *proto, *table; int error = 0; @@ -126,14 +125,9 @@ static int init_names(struct gfs2_sbd *sdp, int silent) /* Try to autodetect */ if (!proto[0] || !table[0]) { - struct gfs2_sb *sb; - page = gfs2_read_super(sdp->sd_vfs, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift); - if (!page) - return -ENOBUFS; - sb = kmap(page); - gfs2_sb_in(&sdp->sd_sb, sb); - kunmap(page); - __free_page(page); + error = gfs2_read_super(sdp, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift); + if (error) + return error; error = gfs2_check_sb(sdp, &sdp->sd_sb, silent); if (error) @@ -151,6 +145,9 @@ static int init_names(struct gfs2_sbd *sdp, int silent) snprintf(sdp->sd_proto_name, GFS2_FSNAME_LEN, "%s", proto); snprintf(sdp->sd_table_name, GFS2_FSNAME_LEN, "%s", table); + while ((table = strchr(sdp->sd_table_name, '/'))) + *table = '_'; + out: return error; } @@ -236,17 +233,17 @@ fail: return error; } -static struct inode *gfs2_lookup_root(struct super_block *sb, - struct gfs2_inum_host *inum) +static inline struct inode *gfs2_lookup_root(struct super_block *sb, + u64 no_addr) { - return gfs2_inode_lookup(sb, inum, DT_DIR); + return gfs2_inode_lookup(sb, DT_DIR, no_addr, 0); } static int init_sb(struct gfs2_sbd *sdp, int silent, int undo) { struct super_block *sb = sdp->sd_vfs; struct gfs2_holder sb_gh; - struct gfs2_inum_host *inum; + u64 no_addr; struct inode *inode; int error = 0; @@ -289,10 +286,10 @@ static int init_sb(struct gfs2_sbd *sdp, int silent, int undo) sb_set_blocksize(sb, sdp->sd_sb.sb_bsize); /* Get the root inode */ - inum = &sdp->sd_sb.sb_root_dir; + no_addr = sdp->sd_sb.sb_root_dir.no_addr; if (sb->s_type == &gfs2meta_fs_type) - inum = &sdp->sd_sb.sb_master_dir; - inode = gfs2_lookup_root(sb, inum); + no_addr = sdp->sd_sb.sb_master_dir.no_addr; + inode = gfs2_lookup_root(sb, no_addr); if (IS_ERR(inode)) { error = PTR_ERR(inode); fs_err(sdp, "can't read in root inode: %d\n", error); @@ -449,7 +446,7 @@ static int init_inodes(struct gfs2_sbd *sdp, int undo) if (undo) goto fail_qinode; - inode = gfs2_lookup_root(sdp->sd_vfs, &sdp->sd_sb.sb_master_dir); + inode = gfs2_lookup_root(sdp->sd_vfs, sdp->sd_sb.sb_master_dir.no_addr); if (IS_ERR(inode)) { error = PTR_ERR(inode); fs_err(sdp, "can't read in master directory: %d\n", error); diff --git a/fs/gfs2/ops_fstype.h b/fs/gfs2/ops_fstype.h index 7cc2c296271..407029b3b2b 100644 --- a/fs/gfs2/ops_fstype.h +++ b/fs/gfs2/ops_fstype.h @@ -14,5 +14,6 @@ extern struct file_system_type gfs2_fs_type; extern struct file_system_type gfs2meta_fs_type; +extern struct export_operations gfs2_export_ops; #endif /* __OPS_FSTYPE_DOT_H__ */ diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c index d85f6e05cb9..911c115b5c6 100644 --- a/fs/gfs2/ops_inode.c +++ b/fs/gfs2/ops_inode.c @@ -157,7 +157,7 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir, if (error) goto out_gunlock; - error = gfs2_dir_search(dir, &dentry->d_name, NULL, NULL); + error = gfs2_dir_check(dir, &dentry->d_name, NULL); switch (error) { case -ENOENT: break; @@ -206,7 +206,7 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir, goto out_gunlock_q; error = gfs2_trans_begin(sdp, sdp->sd_max_dirres + - al->al_rgd->rd_ri.ri_length + + al->al_rgd->rd_length + 2 * RES_DINODE + RES_STATFS + RES_QUOTA, 0); if (error) @@ -217,8 +217,7 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir, goto out_ipres; } - error = gfs2_dir_add(dir, &dentry->d_name, &ip->i_num, - IF2DT(inode->i_mode)); + error = gfs2_dir_add(dir, &dentry->d_name, ip, IF2DT(inode->i_mode)); if (error) goto out_end_trans; @@ -275,7 +274,7 @@ static int gfs2_unlink(struct inode *dir, struct dentry *dentry) gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs); gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + 1); - rgd = gfs2_blk2rgrpd(sdp, ip->i_num.no_addr); + rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr); gfs2_holder_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + 2); @@ -420,7 +419,7 @@ static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, int mode) dent = (struct gfs2_dirent *)((char*)dent + GFS2_DIRENT_SIZE(1)); gfs2_qstr2dirent(&str, dibh->b_size - GFS2_DIRENT_SIZE(1) - sizeof(struct gfs2_dinode), dent); - gfs2_inum_out(&dip->i_num, &dent->de_inum); + gfs2_inum_out(dip, dent); dent->de_type = cpu_to_be16(DT_DIR); gfs2_dinode_out(ip, di); @@ -472,7 +471,7 @@ static int gfs2_rmdir(struct inode *dir, struct dentry *dentry) gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs); gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + 1); - rgd = gfs2_blk2rgrpd(sdp, ip->i_num.no_addr); + rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr); gfs2_holder_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + 2); error = gfs2_glock_nq_m(3, ghs); @@ -614,7 +613,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry, * this is the case of the target file already existing * so we unlink before doing the rename */ - nrgd = gfs2_blk2rgrpd(sdp, nip->i_num.no_addr); + nrgd = gfs2_blk2rgrpd(sdp, nip->i_no_addr); if (nrgd) gfs2_holder_init(nrgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh++); } @@ -653,7 +652,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry, if (error) goto out_gunlock; - error = gfs2_dir_search(ndir, &ndentry->d_name, NULL, NULL); + error = gfs2_dir_check(ndir, &ndentry->d_name, NULL); switch (error) { case -ENOENT: error = 0; @@ -712,7 +711,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry, goto out_gunlock_q; error = gfs2_trans_begin(sdp, sdp->sd_max_dirres + - al->al_rgd->rd_ri.ri_length + + al->al_rgd->rd_length + 4 * RES_DINODE + 4 * RES_LEAF + RES_STATFS + RES_QUOTA + 4, 0); if (error) @@ -750,7 +749,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry, if (error) goto out_end_trans; - error = gfs2_dir_mvino(ip, &name, &ndip->i_num, DT_DIR); + error = gfs2_dir_mvino(ip, &name, ndip, DT_DIR); if (error) goto out_end_trans; } else { @@ -758,7 +757,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry, error = gfs2_meta_inode_buffer(ip, &dibh); if (error) goto out_end_trans; - ip->i_inode.i_ctime = CURRENT_TIME_SEC; + ip->i_inode.i_ctime = CURRENT_TIME; gfs2_trans_add_bh(ip->i_gl, dibh, 1); gfs2_dinode_out(ip, dibh->b_data); brelse(dibh); @@ -768,8 +767,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry, if (error) goto out_end_trans; - error = gfs2_dir_add(ndir, &ndentry->d_name, &ip->i_num, - IF2DT(ip->i_inode.i_mode)); + error = gfs2_dir_add(ndir, &ndentry->d_name, ip, IF2DT(ip->i_inode.i_mode)); if (error) goto out_end_trans; @@ -905,8 +903,8 @@ static int setattr_size(struct inode *inode, struct iattr *attr) } error = gfs2_truncatei(ip, attr->ia_size); - if (error) - return error; + if (error && (inode->i_size != ip->i_di.di_size)) + i_size_write(inode, ip->i_di.di_size); return error; } diff --git a/fs/gfs2/ops_super.c b/fs/gfs2/ops_super.c index 485ce3d4992..603d940f115 100644 --- a/fs/gfs2/ops_super.c +++ b/fs/gfs2/ops_super.c @@ -326,8 +326,10 @@ static void gfs2_clear_inode(struct inode *inode) gfs2_glock_schedule_for_reclaim(ip->i_gl); gfs2_glock_put(ip->i_gl); ip->i_gl = NULL; - if (ip->i_iopen_gh.gh_gl) + if (ip->i_iopen_gh.gh_gl) { + ip->i_iopen_gh.gh_gl->gl_object = NULL; gfs2_glock_dq_uninit(&ip->i_iopen_gh); + } } } @@ -422,13 +424,13 @@ static void gfs2_delete_inode(struct inode *inode) if (!inode->i_private) goto out; - error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB, &gh); + error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); if (unlikely(error)) { gfs2_glock_dq_uninit(&ip->i_iopen_gh); goto out; } - gfs2_glock_dq(&ip->i_iopen_gh); + gfs2_glock_dq_wait(&ip->i_iopen_gh); gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, &ip->i_iopen_gh); error = gfs2_glock_nq(&ip->i_iopen_gh); if (error) diff --git a/fs/gfs2/ops_vm.c b/fs/gfs2/ops_vm.c index aa0dbd2aac1..404b7cc9f8c 100644 --- a/fs/gfs2/ops_vm.c +++ b/fs/gfs2/ops_vm.c @@ -66,7 +66,7 @@ static int alloc_page_backing(struct gfs2_inode *ip, struct page *page) if (error) goto out_gunlock_q; - error = gfs2_trans_begin(sdp, al->al_rgd->rd_ri.ri_length + + error = gfs2_trans_begin(sdp, al->al_rgd->rd_length + ind_blocks + RES_DINODE + RES_STATFS + RES_QUOTA, 0); if (error) diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index c186857e48a..6e546ee8f3d 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -66,6 +66,18 @@ #define QUOTA_USER 1 #define QUOTA_GROUP 0 +struct gfs2_quota_host { + u64 qu_limit; + u64 qu_warn; + s64 qu_value; +}; + +struct gfs2_quota_change_host { + u64 qc_change; + u32 qc_flags; /* GFS2_QCF_... */ + u32 qc_id; +}; + static u64 qd2offset(struct gfs2_quota_data *qd) { u64 offset; @@ -561,6 +573,25 @@ static void do_qc(struct gfs2_quota_data *qd, s64 change) mutex_unlock(&sdp->sd_quota_mutex); } +static void gfs2_quota_in(struct gfs2_quota_host *qu, const void *buf) +{ + const struct gfs2_quota *str = buf; + + qu->qu_limit = be64_to_cpu(str->qu_limit); + qu->qu_warn = be64_to_cpu(str->qu_warn); + qu->qu_value = be64_to_cpu(str->qu_value); +} + +static void gfs2_quota_out(const struct gfs2_quota_host *qu, void *buf) +{ + struct gfs2_quota *str = buf; + + str->qu_limit = cpu_to_be64(qu->qu_limit); + str->qu_warn = cpu_to_be64(qu->qu_warn); + str->qu_value = cpu_to_be64(qu->qu_value); + memset(&str->qu_reserved, 0, sizeof(str->qu_reserved)); +} + /** * gfs2_adjust_quota * @@ -573,12 +604,13 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc, struct inode *inode = &ip->i_inode; struct address_space *mapping = inode->i_mapping; unsigned long index = loc >> PAGE_CACHE_SHIFT; - unsigned offset = loc & (PAGE_CACHE_SHIFT - 1); + unsigned offset = loc & (PAGE_CACHE_SIZE - 1); unsigned blocksize, iblock, pos; struct buffer_head *bh; struct page *page; void *kaddr; - __be64 *ptr; + char *ptr; + struct gfs2_quota_host qp; s64 value; int err = -EIO; @@ -620,13 +652,17 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc, kaddr = kmap_atomic(page, KM_USER0); ptr = kaddr + offset; - value = (s64)be64_to_cpu(*ptr) + change; - *ptr = cpu_to_be64(value); + gfs2_quota_in(&qp, ptr); + qp.qu_value += change; + value = qp.qu_value; + gfs2_quota_out(&qp, ptr); flush_dcache_page(page); kunmap_atomic(kaddr, KM_USER0); err = 0; qd->qd_qb.qb_magic = cpu_to_be32(GFS2_MAGIC); qd->qd_qb.qb_value = cpu_to_be64(value); + ((struct gfs2_quota_lvb*)(qd->qd_gl->gl_lvb))->qb_magic = cpu_to_be32(GFS2_MAGIC); + ((struct gfs2_quota_lvb*)(qd->qd_gl->gl_lvb))->qb_value = cpu_to_be64(value); unlock: unlock_page(page); page_cache_release(page); @@ -689,7 +725,7 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda) goto out_alloc; error = gfs2_trans_begin(sdp, - al->al_rgd->rd_ri.ri_length + + al->al_rgd->rd_length + num_qd * data_blocks + nalloc * ind_blocks + RES_DINODE + num_qd + @@ -709,7 +745,7 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda) offset = qd2offset(qd); error = gfs2_adjust_quota(ip, offset, qd->qd_change_sync, (struct gfs2_quota_data *) - qd->qd_gl->gl_lvb); + qd); if (error) goto out_end_trans; @@ -1050,6 +1086,15 @@ int gfs2_quota_refresh(struct gfs2_sbd *sdp, int user, u32 id) return error; } +static void gfs2_quota_change_in(struct gfs2_quota_change_host *qc, const void *buf) +{ + const struct gfs2_quota_change *str = buf; + + qc->qc_change = be64_to_cpu(str->qc_change); + qc->qc_flags = be32_to_cpu(str->qc_flags); + qc->qc_id = be32_to_cpu(str->qc_id); +} + int gfs2_quota_init(struct gfs2_sbd *sdp) { struct gfs2_inode *ip = GFS2_I(sdp->sd_qc_inode); diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index 8bc182c7e2e..5ada38c99a2 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -116,6 +116,22 @@ void gfs2_revoke_clean(struct gfs2_sbd *sdp) } } +static int gfs2_log_header_in(struct gfs2_log_header_host *lh, const void *buf) +{ + const struct gfs2_log_header *str = buf; + + if (str->lh_header.mh_magic != cpu_to_be32(GFS2_MAGIC) || + str->lh_header.mh_type != cpu_to_be32(GFS2_METATYPE_LH)) + return 1; + + lh->lh_sequence = be64_to_cpu(str->lh_sequence); + lh->lh_flags = be32_to_cpu(str->lh_flags); + lh->lh_tail = be32_to_cpu(str->lh_tail); + lh->lh_blkno = be32_to_cpu(str->lh_blkno); + lh->lh_hash = be32_to_cpu(str->lh_hash); + return 0; +} + /** * get_log_header - read the log header for a given segment * @jd: the journal @@ -147,12 +163,10 @@ static int get_log_header(struct gfs2_jdesc *jd, unsigned int blk, sizeof(u32)); hash = crc32_le(hash, (unsigned char const *)¬hing, sizeof(nothing)); hash ^= (u32)~0; - gfs2_log_header_in(&lh, bh->b_data); + error = gfs2_log_header_in(&lh, bh->b_data); brelse(bh); - if (lh.lh_header.mh_magic != GFS2_MAGIC || - lh.lh_header.mh_type != GFS2_METATYPE_LH || - lh.lh_blkno != blk || lh.lh_hash != hash) + if (error || lh.lh_blkno != blk || lh.lh_hash != hash) return 1; *head = lh; diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 1727f5012ef..e4e04062515 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.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 @@ -28,6 +28,7 @@ #include "ops_file.h" #include "util.h" #include "log.h" +#include "inode.h" #define BFITNOENT ((u32)~0) @@ -50,6 +51,9 @@ static const char valid_change[16] = { 1, 0, 0, 0 }; +static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal, + unsigned char old_state, unsigned char new_state); + /** * gfs2_setbit - Set a bit in the bitmaps * @buffer: the buffer that holds the bitmaps @@ -204,7 +208,7 @@ void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd) { struct gfs2_sbd *sdp = rgd->rd_sbd; struct gfs2_bitmap *bi = NULL; - u32 length = rgd->rd_ri.ri_length; + u32 length = rgd->rd_length; u32 count[4], tmp; int buf, x; @@ -227,7 +231,7 @@ void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd) return; } - tmp = rgd->rd_ri.ri_data - + tmp = rgd->rd_data - rgd->rd_rg.rg_free - rgd->rd_rg.rg_dinodes; if (count[1] + count[2] != tmp) { @@ -253,10 +257,10 @@ void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd) } -static inline int rgrp_contains_block(struct gfs2_rindex_host *ri, u64 block) +static inline int rgrp_contains_block(struct gfs2_rgrpd *rgd, u64 block) { - u64 first = ri->ri_data0; - u64 last = first + ri->ri_data; + u64 first = rgd->rd_data0; + u64 last = first + rgd->rd_data; return first <= block && block < last; } @@ -275,7 +279,7 @@ struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk) spin_lock(&sdp->sd_rindex_spin); list_for_each_entry(rgd, &sdp->sd_rindex_mru_list, rd_list_mru) { - if (rgrp_contains_block(&rgd->rd_ri, blk)) { + if (rgrp_contains_block(rgd, blk)) { list_move(&rgd->rd_list_mru, &sdp->sd_rindex_mru_list); spin_unlock(&sdp->sd_rindex_spin); return rgd; @@ -354,6 +358,15 @@ void gfs2_clear_rgrpd(struct gfs2_sbd *sdp) mutex_unlock(&sdp->sd_rindex_mutex); } +static void gfs2_rindex_print(const struct gfs2_rgrpd *rgd) +{ + printk(KERN_INFO " ri_addr = %llu\n", (unsigned long long)rgd->rd_addr); + printk(KERN_INFO " ri_length = %u\n", rgd->rd_length); + printk(KERN_INFO " ri_data0 = %llu\n", (unsigned long long)rgd->rd_data0); + printk(KERN_INFO " ri_data = %u\n", rgd->rd_data); + printk(KERN_INFO " ri_bitbytes = %u\n", rgd->rd_bitbytes); +} + /** * gfs2_compute_bitstructs - Compute the bitmap sizes * @rgd: The resource group descriptor @@ -367,7 +380,7 @@ static int compute_bitstructs(struct gfs2_rgrpd *rgd) { struct gfs2_sbd *sdp = rgd->rd_sbd; struct gfs2_bitmap *bi; - u32 length = rgd->rd_ri.ri_length; /* # blocks in hdr & bitmap */ + u32 length = rgd->rd_length; /* # blocks in hdr & bitmap */ u32 bytes_left, bytes; int x; @@ -378,7 +391,7 @@ static int compute_bitstructs(struct gfs2_rgrpd *rgd) if (!rgd->rd_bits) return -ENOMEM; - bytes_left = rgd->rd_ri.ri_bitbytes; + bytes_left = rgd->rd_bitbytes; for (x = 0; x < length; x++) { bi = rgd->rd_bits + x; @@ -399,14 +412,14 @@ static int compute_bitstructs(struct gfs2_rgrpd *rgd) } else if (x + 1 == length) { bytes = bytes_left; bi->bi_offset = sizeof(struct gfs2_meta_header); - bi->bi_start = rgd->rd_ri.ri_bitbytes - bytes_left; + bi->bi_start = rgd->rd_bitbytes - bytes_left; bi->bi_len = bytes; /* other blocks */ } else { bytes = sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header); bi->bi_offset = sizeof(struct gfs2_meta_header); - bi->bi_start = rgd->rd_ri.ri_bitbytes - bytes_left; + bi->bi_start = rgd->rd_bitbytes - bytes_left; bi->bi_len = bytes; } @@ -418,9 +431,9 @@ static int compute_bitstructs(struct gfs2_rgrpd *rgd) return -EIO; } bi = rgd->rd_bits + (length - 1); - if ((bi->bi_start + bi->bi_len) * GFS2_NBBY != rgd->rd_ri.ri_data) { + if ((bi->bi_start + bi->bi_len) * GFS2_NBBY != rgd->rd_data) { if (gfs2_consist_rgrpd(rgd)) { - gfs2_rindex_print(&rgd->rd_ri); + gfs2_rindex_print(rgd); fs_err(sdp, "start=%u len=%u offset=%u\n", bi->bi_start, bi->bi_len, bi->bi_offset); } @@ -431,9 +444,104 @@ static int compute_bitstructs(struct gfs2_rgrpd *rgd) } /** - * gfs2_ri_update - Pull in a new resource index from the disk + * gfs2_ri_total - Total up the file system space, according to the rindex. + * + */ +u64 gfs2_ri_total(struct gfs2_sbd *sdp) +{ + u64 total_data = 0; + struct inode *inode = sdp->sd_rindex; + struct gfs2_inode *ip = GFS2_I(inode); + char buf[sizeof(struct gfs2_rindex)]; + struct file_ra_state ra_state; + int error, rgrps; + + mutex_lock(&sdp->sd_rindex_mutex); + file_ra_state_init(&ra_state, inode->i_mapping); + for (rgrps = 0;; rgrps++) { + loff_t pos = rgrps * sizeof(struct gfs2_rindex); + + if (pos + sizeof(struct gfs2_rindex) >= ip->i_di.di_size) + break; + error = gfs2_internal_read(ip, &ra_state, buf, &pos, + sizeof(struct gfs2_rindex)); + if (error != sizeof(struct gfs2_rindex)) + break; + total_data += be32_to_cpu(((struct gfs2_rindex *)buf)->ri_data); + } + mutex_unlock(&sdp->sd_rindex_mutex); + return total_data; +} + +static void gfs2_rindex_in(struct gfs2_rgrpd *rgd, const void *buf) +{ + const struct gfs2_rindex *str = buf; + + rgd->rd_addr = be64_to_cpu(str->ri_addr); + rgd->rd_length = be32_to_cpu(str->ri_length); + rgd->rd_data0 = be64_to_cpu(str->ri_data0); + rgd->rd_data = be32_to_cpu(str->ri_data); + rgd->rd_bitbytes = be32_to_cpu(str->ri_bitbytes); +} + +/** + * read_rindex_entry - Pull in a new resource index entry from the disk * @gl: The glock covering the rindex inode * + * Returns: 0 on success, error code otherwise + */ + +static int read_rindex_entry(struct gfs2_inode *ip, + struct file_ra_state *ra_state) +{ + struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); + loff_t pos = sdp->sd_rgrps * sizeof(struct gfs2_rindex); + char buf[sizeof(struct gfs2_rindex)]; + int error; + struct gfs2_rgrpd *rgd; + + error = gfs2_internal_read(ip, ra_state, buf, &pos, + sizeof(struct gfs2_rindex)); + if (!error) + return 0; + if (error != sizeof(struct gfs2_rindex)) { + if (error > 0) + error = -EIO; + return error; + } + + rgd = kzalloc(sizeof(struct gfs2_rgrpd), GFP_NOFS); + error = -ENOMEM; + if (!rgd) + return error; + + mutex_init(&rgd->rd_mutex); + lops_init_le(&rgd->rd_le, &gfs2_rg_lops); + rgd->rd_sbd = sdp; + + list_add_tail(&rgd->rd_list, &sdp->sd_rindex_list); + list_add_tail(&rgd->rd_list_mru, &sdp->sd_rindex_mru_list); + + gfs2_rindex_in(rgd, buf); + error = compute_bitstructs(rgd); + if (error) + return error; + + error = gfs2_glock_get(sdp, rgd->rd_addr, + &gfs2_rgrp_glops, CREATE, &rgd->rd_gl); + if (error) + return error; + + rgd->rd_gl->gl_object = rgd; + rgd->rd_rg_vn = rgd->rd_gl->gl_vn - 1; + rgd->rd_flags |= GFS2_RDF_CHECK; + return error; +} + +/** + * gfs2_ri_update - Pull in a new resource index from the disk + * @ip: pointer to the rindex inode + * * Returns: 0 on successful update, error code otherwise */ @@ -441,13 +549,11 @@ static int gfs2_ri_update(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct inode *inode = &ip->i_inode; - struct gfs2_rgrpd *rgd; - char buf[sizeof(struct gfs2_rindex)]; struct file_ra_state ra_state; - u64 junk = ip->i_di.di_size; + u64 rgrp_count = ip->i_di.di_size; int error; - if (do_div(junk, sizeof(struct gfs2_rindex))) { + if (do_div(rgrp_count, sizeof(struct gfs2_rindex))) { gfs2_consist_inode(ip); return -EIO; } @@ -455,50 +561,50 @@ static int gfs2_ri_update(struct gfs2_inode *ip) clear_rgrpdi(sdp); file_ra_state_init(&ra_state, inode->i_mapping); - for (sdp->sd_rgrps = 0;; sdp->sd_rgrps++) { - loff_t pos = sdp->sd_rgrps * sizeof(struct gfs2_rindex); - error = gfs2_internal_read(ip, &ra_state, buf, &pos, - sizeof(struct gfs2_rindex)); - if (!error) - break; - if (error != sizeof(struct gfs2_rindex)) { - if (error > 0) - error = -EIO; - goto fail; + for (sdp->sd_rgrps = 0; sdp->sd_rgrps < rgrp_count; sdp->sd_rgrps++) { + error = read_rindex_entry(ip, &ra_state); + if (error) { + clear_rgrpdi(sdp); + return error; } + } - rgd = kzalloc(sizeof(struct gfs2_rgrpd), GFP_NOFS); - error = -ENOMEM; - if (!rgd) - goto fail; - - mutex_init(&rgd->rd_mutex); - lops_init_le(&rgd->rd_le, &gfs2_rg_lops); - rgd->rd_sbd = sdp; - - list_add_tail(&rgd->rd_list, &sdp->sd_rindex_list); - list_add_tail(&rgd->rd_list_mru, &sdp->sd_rindex_mru_list); - - gfs2_rindex_in(&rgd->rd_ri, buf); - error = compute_bitstructs(rgd); - if (error) - goto fail; + sdp->sd_rindex_vn = ip->i_gl->gl_vn; + return 0; +} - error = gfs2_glock_get(sdp, rgd->rd_ri.ri_addr, - &gfs2_rgrp_glops, CREATE, &rgd->rd_gl); - if (error) - goto fail; +/** + * gfs2_ri_update_special - Pull in a new resource index from the disk + * + * This is a special version that's safe to call from gfs2_inplace_reserve_i. + * In this case we know that we don't have any resource groups in memory yet. + * + * @ip: pointer to the rindex inode + * + * Returns: 0 on successful update, error code otherwise + */ +static int gfs2_ri_update_special(struct gfs2_inode *ip) +{ + struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); + struct inode *inode = &ip->i_inode; + struct file_ra_state ra_state; + int error; - rgd->rd_gl->gl_object = rgd; - rgd->rd_rg_vn = rgd->rd_gl->gl_vn - 1; + file_ra_state_init(&ra_state, inode->i_mapping); + for (sdp->sd_rgrps = 0;; sdp->sd_rgrps++) { + /* Ignore partials */ + if ((sdp->sd_rgrps + 1) * sizeof(struct gfs2_rindex) > + ip->i_di.di_size) + break; + error = read_rindex_entry(ip, &ra_state); + if (error) { + clear_rgrpdi(sdp); + return error; + } } sdp->sd_rindex_vn = ip->i_gl->gl_vn; return 0; - -fail: - clear_rgrpdi(sdp); - return error; } /** @@ -543,6 +649,28 @@ int gfs2_rindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ri_gh) return error; } +static void gfs2_rgrp_in(struct gfs2_rgrp_host *rg, const void *buf) +{ + const struct gfs2_rgrp *str = buf; + + rg->rg_flags = be32_to_cpu(str->rg_flags); + rg->rg_free = be32_to_cpu(str->rg_free); + rg->rg_dinodes = be32_to_cpu(str->rg_dinodes); + rg->rg_igeneration = be64_to_cpu(str->rg_igeneration); +} + +static void gfs2_rgrp_out(const struct gfs2_rgrp_host *rg, void *buf) +{ + struct gfs2_rgrp *str = buf; + + str->rg_flags = cpu_to_be32(rg->rg_flags); + str->rg_free = cpu_to_be32(rg->rg_free); + str->rg_dinodes = cpu_to_be32(rg->rg_dinodes); + str->__pad = cpu_to_be32(0); + str->rg_igeneration = cpu_to_be64(rg->rg_igeneration); + memset(&str->rg_reserved, 0, sizeof(str->rg_reserved)); +} + /** * gfs2_rgrp_bh_get - Read in a RG's header and bitmaps * @rgd: the struct gfs2_rgrpd describing the RG to read in @@ -557,7 +685,7 @@ int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd) { struct gfs2_sbd *sdp = rgd->rd_sbd; struct gfs2_glock *gl = rgd->rd_gl; - unsigned int length = rgd->rd_ri.ri_length; + unsigned int length = rgd->rd_length; struct gfs2_bitmap *bi; unsigned int x, y; int error; @@ -575,7 +703,7 @@ int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd) for (x = 0; x < length; x++) { bi = rgd->rd_bits + x; - error = gfs2_meta_read(gl, rgd->rd_ri.ri_addr + x, 0, &bi->bi_bh); + error = gfs2_meta_read(gl, rgd->rd_addr + x, 0, &bi->bi_bh); if (error) goto fail; } @@ -637,7 +765,7 @@ void gfs2_rgrp_bh_hold(struct gfs2_rgrpd *rgd) void gfs2_rgrp_bh_put(struct gfs2_rgrpd *rgd) { struct gfs2_sbd *sdp = rgd->rd_sbd; - int x, length = rgd->rd_ri.ri_length; + int x, length = rgd->rd_length; spin_lock(&sdp->sd_rindex_spin); gfs2_assert_warn(rgd->rd_sbd, rgd->rd_bh_count); @@ -660,7 +788,7 @@ void gfs2_rgrp_bh_put(struct gfs2_rgrpd *rgd) void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd) { struct gfs2_sbd *sdp = rgd->rd_sbd; - unsigned int length = rgd->rd_ri.ri_length; + unsigned int length = rgd->rd_length; unsigned int x; for (x = 0; x < length; x++) { @@ -722,6 +850,38 @@ static int try_rgrp_fit(struct gfs2_rgrpd *rgd, struct gfs2_alloc *al) } /** + * try_rgrp_unlink - Look for any unlinked, allocated, but unused inodes + * @rgd: The rgrp + * + * Returns: The inode, if one has been found + */ + +static struct inode *try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked) +{ + struct inode *inode; + u32 goal = 0; + u64 no_addr; + + for(;;) { + goal = rgblk_search(rgd, goal, GFS2_BLKST_UNLINKED, + GFS2_BLKST_UNLINKED); + if (goal == 0) + return 0; + no_addr = goal + rgd->rd_data0; + if (no_addr <= *last_unlinked) + continue; + *last_unlinked = no_addr; + inode = gfs2_inode_lookup(rgd->rd_sbd->sd_vfs, DT_UNKNOWN, + no_addr, -1); + if (!IS_ERR(inode)) + return inode; + } + + rgd->rd_flags &= ~GFS2_RDF_CHECK; + return NULL; +} + +/** * recent_rgrp_first - get first RG from "recent" list * @sdp: The GFS2 superblock * @rglast: address of the rgrp used last @@ -743,7 +903,7 @@ static struct gfs2_rgrpd *recent_rgrp_first(struct gfs2_sbd *sdp, goto first; list_for_each_entry(rgd, &sdp->sd_rindex_recent_list, rd_recent) { - if (rgd->rd_ri.ri_addr == rglast) + if (rgd->rd_addr == rglast) goto out; } @@ -882,8 +1042,9 @@ static void forward_rgrp_set(struct gfs2_sbd *sdp, struct gfs2_rgrpd *rgd) * Returns: errno */ -static int get_local_rgrp(struct gfs2_inode *ip) +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; @@ -903,7 +1064,11 @@ static int get_local_rgrp(struct gfs2_inode *ip) 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 (inode) + return inode; rgd = recent_rgrp_next(rgd, 1); break; @@ -912,7 +1077,7 @@ static int get_local_rgrp(struct gfs2_inode *ip) break; default: - return error; + return ERR_PTR(error); } } @@ -927,7 +1092,11 @@ static int get_local_rgrp(struct gfs2_inode *ip) 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 (inode) + return inode; break; case GLR_TRYFAILED: @@ -935,7 +1104,7 @@ static int get_local_rgrp(struct gfs2_inode *ip) break; default: - return error; + return ERR_PTR(error); } rgd = gfs2_rgrpd_get_next(rgd); @@ -944,7 +1113,7 @@ static int get_local_rgrp(struct gfs2_inode *ip) if (rgd == begin) { if (++loops >= 3) - return -ENOSPC; + return ERR_PTR(-ENOSPC); if (!skipped) loops++; flags = 0; @@ -954,7 +1123,7 @@ static int get_local_rgrp(struct gfs2_inode *ip) } out: - ip->i_last_rg_alloc = rgd->rd_ri.ri_addr; + ip->i_last_rg_alloc = rgd->rd_addr; if (begin) { recent_rgrp_add(rgd); @@ -964,7 +1133,7 @@ out: forward_rgrp_set(sdp, rgd); } - return 0; + return NULL; } /** @@ -978,19 +1147,33 @@ 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; - int error; + struct inode *inode; + int error = 0; + u64 last_unlinked = 0; if (gfs2_assert_warn(sdp, al->al_requested)) return -EINVAL; - error = gfs2_rindex_hold(sdp, &al->al_ri_gh); +try_again: + /* We need to hold the rindex unless the inode we're using is + the rindex itself, in which case it's already held. */ + if (ip != GFS2_I(sdp->sd_rindex)) + error = gfs2_rindex_hold(sdp, &al->al_ri_gh); + else if (!sdp->sd_rgrps) /* We may not have the rindex read in, so: */ + error = gfs2_ri_update_special(ip); + if (error) return error; - error = get_local_rgrp(ip); - if (error) { - gfs2_glock_dq_uninit(&al->al_ri_gh); - return error; + inode = get_local_rgrp(ip, &last_unlinked); + if (inode) { + if (ip != GFS2_I(sdp->sd_rindex)) + gfs2_glock_dq_uninit(&al->al_ri_gh); + if (IS_ERR(inode)) + return PTR_ERR(inode); + iput(inode); + gfs2_log_flush(sdp, NULL); + goto try_again; } al->al_file = file; @@ -1019,7 +1202,8 @@ void gfs2_inplace_release(struct gfs2_inode *ip) al->al_rgd = NULL; gfs2_glock_dq_uninit(&al->al_rgd_gh); - gfs2_glock_dq_uninit(&al->al_ri_gh); + if (ip != GFS2_I(sdp->sd_rindex)) + gfs2_glock_dq_uninit(&al->al_ri_gh); } /** @@ -1037,8 +1221,8 @@ unsigned char gfs2_get_block_type(struct gfs2_rgrpd *rgd, u64 block) unsigned int buf; unsigned char type; - length = rgd->rd_ri.ri_length; - rgrp_block = block - rgd->rd_ri.ri_data0; + length = rgd->rd_length; + rgrp_block = block - rgd->rd_data0; for (buf = 0; buf < length; buf++) { bi = rgd->rd_bits + buf; @@ -1077,10 +1261,10 @@ unsigned char gfs2_get_block_type(struct gfs2_rgrpd *rgd, u64 block) */ static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal, - unsigned char old_state, unsigned char new_state) + unsigned char old_state, unsigned char new_state) { struct gfs2_bitmap *bi = NULL; - u32 length = rgd->rd_ri.ri_length; + u32 length = rgd->rd_length; u32 blk = 0; unsigned int buf, x; @@ -1118,17 +1302,18 @@ static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal, goal = 0; } - if (gfs2_assert_withdraw(rgd->rd_sbd, x <= length)) - blk = 0; + if (old_state != new_state) { + gfs2_assert_withdraw(rgd->rd_sbd, blk != BFITNOENT); - gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1); - gfs2_setbit(rgd, bi->bi_bh->b_data + bi->bi_offset, - bi->bi_len, blk, new_state); - if (bi->bi_clone) - gfs2_setbit(rgd, bi->bi_clone + bi->bi_offset, + gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1); + gfs2_setbit(rgd, bi->bi_bh->b_data + bi->bi_offset, bi->bi_len, blk, new_state); + if (bi->bi_clone) + gfs2_setbit(rgd, bi->bi_clone + bi->bi_offset, + bi->bi_len, blk, new_state); + } - return bi->bi_start * GFS2_NBBY + blk; + return (blk == BFITNOENT) ? 0 : (bi->bi_start * GFS2_NBBY) + blk; } /** @@ -1156,9 +1341,9 @@ static struct gfs2_rgrpd *rgblk_free(struct gfs2_sbd *sdp, u64 bstart, return NULL; } - length = rgd->rd_ri.ri_length; + length = rgd->rd_length; - rgrp_blk = bstart - rgd->rd_ri.ri_data0; + rgrp_blk = bstart - rgd->rd_data0; while (blen--) { for (buf = 0; buf < length; buf++) { @@ -1202,15 +1387,15 @@ u64 gfs2_alloc_data(struct gfs2_inode *ip) u32 goal, blk; u64 block; - if (rgrp_contains_block(&rgd->rd_ri, ip->i_di.di_goal_data)) - goal = ip->i_di.di_goal_data - rgd->rd_ri.ri_data0; + if (rgrp_contains_block(rgd, ip->i_di.di_goal_data)) + goal = ip->i_di.di_goal_data - rgd->rd_data0; else goal = rgd->rd_last_alloc_data; blk = rgblk_search(rgd, goal, GFS2_BLKST_FREE, GFS2_BLKST_USED); rgd->rd_last_alloc_data = blk; - block = rgd->rd_ri.ri_data0 + blk; + block = rgd->rd_data0 + blk; ip->i_di.di_goal_data = block; gfs2_assert_withdraw(sdp, rgd->rd_rg.rg_free); @@ -1246,15 +1431,15 @@ u64 gfs2_alloc_meta(struct gfs2_inode *ip) u32 goal, blk; u64 block; - if (rgrp_contains_block(&rgd->rd_ri, ip->i_di.di_goal_meta)) - goal = ip->i_di.di_goal_meta - rgd->rd_ri.ri_data0; + if (rgrp_contains_block(rgd, ip->i_di.di_goal_meta)) + goal = ip->i_di.di_goal_meta - rgd->rd_data0; else goal = rgd->rd_last_alloc_meta; blk = rgblk_search(rgd, goal, GFS2_BLKST_FREE, GFS2_BLKST_USED); rgd->rd_last_alloc_meta = blk; - block = rgd->rd_ri.ri_data0 + blk; + block = rgd->rd_data0 + blk; ip->i_di.di_goal_meta = block; gfs2_assert_withdraw(sdp, rgd->rd_rg.rg_free); @@ -1296,7 +1481,7 @@ u64 gfs2_alloc_di(struct gfs2_inode *dip, u64 *generation) rgd->rd_last_alloc_meta = blk; - block = rgd->rd_ri.ri_data0 + blk; + block = rgd->rd_data0 + blk; gfs2_assert_withdraw(sdp, rgd->rd_rg.rg_free); rgd->rd_rg.rg_free--; @@ -1379,7 +1564,7 @@ void gfs2_unlink_di(struct inode *inode) struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); struct gfs2_rgrpd *rgd; - u64 blkno = ip->i_num.no_addr; + u64 blkno = ip->i_no_addr; rgd = rgblk_free(sdp, blkno, 1, GFS2_BLKST_UNLINKED); if (!rgd) @@ -1414,9 +1599,9 @@ static void gfs2_free_uninit_di(struct gfs2_rgrpd *rgd, u64 blkno) void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip) { - gfs2_free_uninit_di(rgd, ip->i_num.no_addr); + gfs2_free_uninit_di(rgd, ip->i_no_addr); gfs2_quota_change(ip, -1, ip->i_inode.i_uid, ip->i_inode.i_gid); - gfs2_meta_wipe(ip, ip->i_num.no_addr, 1); + gfs2_meta_wipe(ip, ip->i_no_addr, 1); } /** diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h index b01e0cfc99b..b4c6adfc6f2 100644 --- a/fs/gfs2/rgrp.h +++ b/fs/gfs2/rgrp.h @@ -65,5 +65,6 @@ void gfs2_rlist_add(struct gfs2_sbd *sdp, struct gfs2_rgrp_list *rlist, void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state, int flags); void gfs2_rlist_free(struct gfs2_rgrp_list *rlist); +u64 gfs2_ri_total(struct gfs2_sbd *sdp); #endif /* __RGRP_DOT_H__ */ diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 4fdda974dc8..f916b9740c7 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -95,8 +95,8 @@ int gfs2_check_sb(struct gfs2_sbd *sdp, struct gfs2_sb_host *sb, int silent) { unsigned int x; - if (sb->sb_header.mh_magic != GFS2_MAGIC || - sb->sb_header.mh_type != GFS2_METATYPE_SB) { + if (sb->sb_magic != GFS2_MAGIC || + sb->sb_type != GFS2_METATYPE_SB) { if (!silent) printk(KERN_WARNING "GFS2: not a GFS2 filesystem\n"); return -EINVAL; @@ -174,10 +174,31 @@ static int end_bio_io_page(struct bio *bio, unsigned int bytes_done, int error) return 0; } +static void gfs2_sb_in(struct gfs2_sb_host *sb, const void *buf) +{ + const struct gfs2_sb *str = buf; + + sb->sb_magic = be32_to_cpu(str->sb_header.mh_magic); + sb->sb_type = be32_to_cpu(str->sb_header.mh_type); + sb->sb_format = be32_to_cpu(str->sb_header.mh_format); + sb->sb_fs_format = be32_to_cpu(str->sb_fs_format); + sb->sb_multihost_format = be32_to_cpu(str->sb_multihost_format); + sb->sb_bsize = be32_to_cpu(str->sb_bsize); + sb->sb_bsize_shift = be32_to_cpu(str->sb_bsize_shift); + sb->sb_master_dir.no_addr = be64_to_cpu(str->sb_master_dir.no_addr); + sb->sb_master_dir.no_formal_ino = be64_to_cpu(str->sb_master_dir.no_formal_ino); + sb->sb_root_dir.no_addr = be64_to_cpu(str->sb_root_dir.no_addr); + sb->sb_root_dir.no_formal_ino = be64_to_cpu(str->sb_root_dir.no_formal_ino); + + memcpy(sb->sb_lockproto, str->sb_lockproto, GFS2_LOCKNAME_LEN); + memcpy(sb->sb_locktable, str->sb_locktable, GFS2_LOCKNAME_LEN); +} + /** * gfs2_read_super - Read the gfs2 super block from disk - * @sb: The VFS super block + * @sdp: The GFS2 super block * @sector: The location of the super block + * @error: The error code to return * * This uses the bio functions to read the super block from disk * because we want to be 100% sure that we never read cached data. @@ -189,17 +210,19 @@ static int end_bio_io_page(struct bio *bio, unsigned int bytes_done, int error) * the master directory (contains pointers to journals etc) and the * root directory. * - * Returns: A page containing the sb or NULL + * Returns: 0 on success or error */ -struct page *gfs2_read_super(struct super_block *sb, sector_t sector) +int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector) { + struct super_block *sb = sdp->sd_vfs; + struct gfs2_sb *p; struct page *page; struct bio *bio; page = alloc_page(GFP_KERNEL); if (unlikely(!page)) - return NULL; + return -ENOBUFS; ClearPageUptodate(page); ClearPageDirty(page); @@ -208,7 +231,7 @@ struct page *gfs2_read_super(struct super_block *sb, sector_t sector) bio = bio_alloc(GFP_KERNEL, 1); if (unlikely(!bio)) { __free_page(page); - return NULL; + return -ENOBUFS; } bio->bi_sector = sector * (sb->s_blocksize >> 9); @@ -222,9 +245,13 @@ struct page *gfs2_read_super(struct super_block *sb, sector_t sector) bio_put(bio); if (!PageUptodate(page)) { __free_page(page); - return NULL; + return -EIO; } - return page; + p = kmap(page); + gfs2_sb_in(&sdp->sd_sb, p); + kunmap(page); + __free_page(page); + return 0; } /** @@ -241,19 +268,13 @@ int gfs2_read_sb(struct gfs2_sbd *sdp, struct gfs2_glock *gl, int silent) u32 tmp_blocks; unsigned int x; int error; - struct page *page; - char *sb; - page = gfs2_read_super(sdp->sd_vfs, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift); - if (!page) { + error = gfs2_read_super(sdp, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift); + if (error) { if (!silent) fs_err(sdp, "can't read superblock\n"); - return -EIO; + return error; } - sb = kmap(page); - gfs2_sb_in(&sdp->sd_sb, sb); - kunmap(page); - __free_page(page); error = gfs2_check_sb(sdp, &sdp->sd_sb, silent); if (error) @@ -360,7 +381,7 @@ int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh) name.len = sprintf(buf, "journal%u", sdp->sd_journals); name.hash = gfs2_disk_hash(name.name, name.len); - error = gfs2_dir_search(sdp->sd_jindex, &name, NULL, NULL); + error = gfs2_dir_check(sdp->sd_jindex, &name, NULL); if (error == -ENOENT) { error = 0; break; @@ -593,6 +614,24 @@ int gfs2_make_fs_ro(struct gfs2_sbd *sdp) return error; } +static void gfs2_statfs_change_in(struct gfs2_statfs_change_host *sc, const void *buf) +{ + const struct gfs2_statfs_change *str = buf; + + sc->sc_total = be64_to_cpu(str->sc_total); + sc->sc_free = be64_to_cpu(str->sc_free); + sc->sc_dinodes = be64_to_cpu(str->sc_dinodes); +} + +static void gfs2_statfs_change_out(const struct gfs2_statfs_change_host *sc, void *buf) +{ + struct gfs2_statfs_change *str = buf; + + str->sc_total = cpu_to_be64(sc->sc_total); + str->sc_free = cpu_to_be64(sc->sc_free); + str->sc_dinodes = cpu_to_be64(sc->sc_dinodes); +} + int gfs2_statfs_init(struct gfs2_sbd *sdp) { struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode); @@ -772,7 +811,7 @@ static int statfs_slow_fill(struct gfs2_rgrpd *rgd, struct gfs2_statfs_change_host *sc) { gfs2_rgrp_verify(rgd); - sc->sc_total += rgd->rd_ri.ri_data; + sc->sc_total += rgd->rd_data; sc->sc_free += rgd->rd_rg.rg_free; sc->sc_dinodes += rgd->rd_rg.rg_dinodes; return 0; diff --git a/fs/gfs2/super.h b/fs/gfs2/super.h index e590b2df11d..60a870e430b 100644 --- a/fs/gfs2/super.h +++ b/fs/gfs2/super.h @@ -16,7 +16,7 @@ void gfs2_tune_init(struct gfs2_tune *gt); int gfs2_check_sb(struct gfs2_sbd *sdp, struct gfs2_sb_host *sb, int silent); int gfs2_read_sb(struct gfs2_sbd *sdp, struct gfs2_glock *gl, int silent); -struct page *gfs2_read_super(struct super_block *sb, sector_t sector); +int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector); static inline unsigned int gfs2_jindex_size(struct gfs2_sbd *sdp) { diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c index 601eaa1b9ed..424a0774eda 100644 --- a/fs/gfs2/util.c +++ b/fs/gfs2/util.c @@ -115,8 +115,8 @@ int gfs2_consist_inode_i(struct gfs2_inode *ip, int cluster_wide, "GFS2: fsid=%s: inode = %llu %llu\n" "GFS2: fsid=%s: function = %s, file = %s, line = %u\n", sdp->sd_fsname, - sdp->sd_fsname, (unsigned long long)ip->i_num.no_formal_ino, - (unsigned long long)ip->i_num.no_addr, + sdp->sd_fsname, (unsigned long long)ip->i_no_formal_ino, + (unsigned long long)ip->i_no_addr, sdp->sd_fsname, function, file, line); return rv; } @@ -137,7 +137,7 @@ int gfs2_consist_rgrpd_i(struct gfs2_rgrpd *rgd, int cluster_wide, "GFS2: fsid=%s: RG = %llu\n" "GFS2: fsid=%s: function = %s, file = %s, line = %u\n", sdp->sd_fsname, - sdp->sd_fsname, (unsigned long long)rgd->rd_ri.ri_addr, + sdp->sd_fsname, (unsigned long long)rgd->rd_addr, sdp->sd_fsname, function, file, line); return rv; } diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 9a934db0bd8..bc835f272a6 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -607,7 +607,7 @@ static const struct file_operations hfs_file_operations = { .write = do_sync_write, .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, - .sendfile = generic_file_sendfile, + .splice_read = generic_file_splice_read, .fsync = file_fsync, .open = hfs_file_open, .release = hfs_file_release, diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 45dab5d6cc1..409ce5429c9 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -288,7 +288,7 @@ static const struct file_operations hfsplus_file_operations = { .write = do_sync_write, .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, - .sendfile = generic_file_sendfile, + .splice_read = generic_file_splice_read, .fsync = file_fsync, .open = hfsplus_file_open, .release = hfsplus_file_release, diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 8286491dbf3..c77862032e8 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -390,7 +390,7 @@ int hostfs_fsync(struct file *file, struct dentry *dentry, int datasync) static const struct file_operations hostfs_file_fops = { .llseek = generic_file_llseek, .read = do_sync_read, - .sendfile = generic_file_sendfile, + .splice_read = generic_file_splice_read, .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write, .write = do_sync_write, diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index b4eafc0f1e5..5b53e5c5d8d 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -129,7 +129,7 @@ const struct file_operations hpfs_file_ops = .mmap = generic_file_mmap, .release = hpfs_file_release, .fsync = hpfs_file_fsync, - .sendfile = generic_file_sendfile, + .splice_read = generic_file_splice_read, }; const struct inode_operations hpfs_file_iops = diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index 99871279a1e..c2530197be0 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -47,7 +47,7 @@ const struct file_operations jffs2_file_operations = .ioctl = jffs2_ioctl, .mmap = generic_file_readonly_mmap, .fsync = jffs2_fsync, - .sendfile = generic_file_sendfile + .splice_read = generic_file_splice_read, }; /* jffs2_file_inode_operations */ diff --git a/fs/jfs/endian24.h b/fs/jfs/endian24.h index 79494c4f2b1..fa92f7f1d0d 100644 --- a/fs/jfs/endian24.h +++ b/fs/jfs/endian24.h @@ -29,7 +29,7 @@ __u32 __x = (x); \ ((__u32)( \ ((__x & (__u32)0x000000ffUL) << 16) | \ - (__x & (__u32)0x0000ff00UL) | \ + (__x & (__u32)0x0000ff00UL) | \ ((__x & (__u32)0x00ff0000UL) >> 16) )); \ }) diff --git a/fs/jfs/file.c b/fs/jfs/file.c index f7f8eff19b7..87eb93694af 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -108,7 +108,6 @@ const struct file_operations jfs_file_operations = { .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, - .sendfile = generic_file_sendfile, .splice_read = generic_file_splice_read, .splice_write = generic_file_splice_write, .fsync = jfs_fsync, diff --git a/fs/jfs/jfs_debug.c b/fs/jfs/jfs_debug.c index 9c5d59632aa..887f5759e53 100644 --- a/fs/jfs/jfs_debug.c +++ b/fs/jfs/jfs_debug.c @@ -26,34 +26,6 @@ #include "jfs_filsys.h" #include "jfs_debug.h" -#ifdef CONFIG_JFS_DEBUG -void dump_mem(char *label, void *data, int length) -{ - int i, j; - int *intptr = data; - char *charptr = data; - char buf[10], line[80]; - - printk("%s: dump of %d bytes of data at 0x%p\n\n", label, length, - data); - for (i = 0; i < length; i += 16) { - line[0] = 0; - for (j = 0; (j < 4) && (i + j * 4 < length); j++) { - sprintf(buf, " %08x", intptr[i / 4 + j]); - strcat(line, buf); - } - buf[0] = ' '; - buf[2] = 0; - for (j = 0; (j < 16) && (i + j < length); j++) { - buf[1] = - isprint(charptr[i + j]) ? charptr[i + j] : '.'; - strcat(line, buf); - } - printk("%s\n", line); - } -} -#endif - #ifdef PROC_FS_JFS /* see jfs_debug.h */ static struct proc_dir_entry *base; diff --git a/fs/jfs/jfs_debug.h b/fs/jfs/jfs_debug.h index 7378798f0b2..044c1e654cc 100644 --- a/fs/jfs/jfs_debug.h +++ b/fs/jfs/jfs_debug.h @@ -62,7 +62,6 @@ extern void jfs_proc_clean(void); extern int jfsloglevel; -extern void dump_mem(char *label, void *data, int length); extern int jfs_txanchor_read(char *, char **, off_t, int, int *, void *); /* information message: e.g., configuration, major event */ @@ -94,7 +93,6 @@ extern int jfs_txanchor_read(char *, char **, off_t, int, int *, void *); * --------- */ #else /* CONFIG_JFS_DEBUG */ -#define dump_mem(label,data,length) do {} while (0) #define ASSERT(p) do {} while (0) #define jfs_info(fmt, arg...) do {} while (0) #define jfs_debug(fmt, arg...) do {} while (0) diff --git a/fs/jfs/jfs_dinode.h b/fs/jfs/jfs_dinode.h index 40b20111383..c387540d342 100644 --- a/fs/jfs/jfs_dinode.h +++ b/fs/jfs/jfs_dinode.h @@ -19,23 +19,23 @@ #define _H_JFS_DINODE /* - * jfs_dinode.h: on-disk inode manager + * jfs_dinode.h: on-disk inode manager */ -#define INODESLOTSIZE 128 -#define L2INODESLOTSIZE 7 -#define log2INODESIZE 9 /* log2(bytes per dinode) */ +#define INODESLOTSIZE 128 +#define L2INODESLOTSIZE 7 +#define log2INODESIZE 9 /* log2(bytes per dinode) */ /* - * on-disk inode : 512 bytes + * on-disk inode : 512 bytes * * note: align 64-bit fields on 8-byte boundary. */ struct dinode { /* - * I. base area (128 bytes) - * ------------------------ + * I. base area (128 bytes) + * ------------------------ * * define generic/POSIX attributes */ @@ -70,16 +70,16 @@ struct dinode { __le32 di_acltype; /* 4: Type of ACL */ /* - * Extension Areas. + * Extension Areas. * - * Historically, the inode was partitioned into 4 128-byte areas, - * the last 3 being defined as unions which could have multiple - * uses. The first 96 bytes had been completely unused until - * an index table was added to the directory. It is now more - * useful to describe the last 3/4 of the inode as a single - * union. We would probably be better off redesigning the - * entire structure from scratch, but we don't want to break - * commonality with OS/2's JFS at this time. + * Historically, the inode was partitioned into 4 128-byte areas, + * the last 3 being defined as unions which could have multiple + * uses. The first 96 bytes had been completely unused until + * an index table was added to the directory. It is now more + * useful to describe the last 3/4 of the inode as a single + * union. We would probably be better off redesigning the + * entire structure from scratch, but we don't want to break + * commonality with OS/2's JFS at this time. */ union { struct { @@ -95,7 +95,7 @@ struct dinode { } _dir; /* (384) */ #define di_dirtable u._dir._table #define di_dtroot u._dir._dtroot -#define di_parent di_dtroot.header.idotdot +#define di_parent di_dtroot.header.idotdot #define di_DASD di_dtroot.header.DASD struct { @@ -127,14 +127,14 @@ struct dinode { #define di_inlinedata u._file._u2._special._u #define di_rdev u._file._u2._special._u._rdev #define di_fastsymlink u._file._u2._special._u._fastsymlink -#define di_inlineea u._file._u2._special._inlineea +#define di_inlineea u._file._u2._special._inlineea } u; }; /* extended mode bits (on-disk inode di_mode) */ -#define IFJOURNAL 0x00010000 /* journalled file */ -#define ISPARSE 0x00020000 /* sparse file enabled */ -#define INLINEEA 0x00040000 /* inline EA area free */ +#define IFJOURNAL 0x00010000 /* journalled file */ +#define ISPARSE 0x00020000 /* sparse file enabled */ +#define INLINEEA 0x00040000 /* inline EA area free */ #define ISWAPFILE 0x00800000 /* file open for pager swap space */ /* more extended mode bits: attributes for OS/2 */ diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index f3b1ebb2228..e1985066b1c 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -154,12 +154,12 @@ static const s8 budtab[256] = { * the in-core descriptor is initialized from disk. * * PARAMETERS: - * ipbmap - pointer to in-core inode for the block map. + * ipbmap - pointer to in-core inode for the block map. * * RETURN VALUES: - * 0 - success - * -ENOMEM - insufficient memory - * -EIO - i/o error + * 0 - success + * -ENOMEM - insufficient memory + * -EIO - i/o error */ int dbMount(struct inode *ipbmap) { @@ -232,11 +232,11 @@ int dbMount(struct inode *ipbmap) * the memory for this descriptor is freed. * * PARAMETERS: - * ipbmap - pointer to in-core inode for the block map. + * ipbmap - pointer to in-core inode for the block map. * * RETURN VALUES: - * 0 - success - * -EIO - i/o error + * 0 - success + * -EIO - i/o error */ int dbUnmount(struct inode *ipbmap, int mounterror) { @@ -320,13 +320,13 @@ int dbSync(struct inode *ipbmap) * at a time. * * PARAMETERS: - * ip - pointer to in-core inode; - * blkno - starting block number to be freed. - * nblocks - number of blocks to be freed. + * ip - pointer to in-core inode; + * blkno - starting block number to be freed. + * nblocks - number of blocks to be freed. * * RETURN VALUES: - * 0 - success - * -EIO - i/o error + * 0 - success + * -EIO - i/o error */ int dbFree(struct inode *ip, s64 blkno, s64 nblocks) { @@ -395,23 +395,23 @@ int dbFree(struct inode *ip, s64 blkno, s64 nblocks) /* * NAME: dbUpdatePMap() * - * FUNCTION: update the allocation state (free or allocate) of the + * FUNCTION: update the allocation state (free or allocate) of the * specified block range in the persistent block allocation map. * * the blocks will be updated in the persistent map one * dmap at a time. * * PARAMETERS: - * ipbmap - pointer to in-core inode for the block map. - * free - 'true' if block range is to be freed from the persistent - * map; 'false' if it is to be allocated. - * blkno - starting block number of the range. - * nblocks - number of contiguous blocks in the range. - * tblk - transaction block; + * ipbmap - pointer to in-core inode for the block map. + * free - 'true' if block range is to be freed from the persistent + * map; 'false' if it is to be allocated. + * blkno - starting block number of the range. + * nblocks - number of contiguous blocks in the range. + * tblk - transaction block; * * RETURN VALUES: - * 0 - success - * -EIO - i/o error + * 0 - success + * -EIO - i/o error */ int dbUpdatePMap(struct inode *ipbmap, @@ -573,7 +573,7 @@ dbUpdatePMap(struct inode *ipbmap, /* * NAME: dbNextAG() * - * FUNCTION: find the preferred allocation group for new allocations. + * FUNCTION: find the preferred allocation group for new allocations. * * Within the allocation groups, we maintain a preferred * allocation group which consists of a group with at least @@ -589,10 +589,10 @@ dbUpdatePMap(struct inode *ipbmap, * empty ags around for large allocations. * * PARAMETERS: - * ipbmap - pointer to in-core inode for the block map. + * ipbmap - pointer to in-core inode for the block map. * * RETURN VALUES: - * the preferred allocation group number. + * the preferred allocation group number. */ int dbNextAG(struct inode *ipbmap) { @@ -656,7 +656,7 @@ unlock: /* * NAME: dbAlloc() * - * FUNCTION: attempt to allocate a specified number of contiguous free + * FUNCTION: attempt to allocate a specified number of contiguous free * blocks from the working allocation block map. * * the block allocation policy uses hints and a multi-step @@ -680,16 +680,16 @@ unlock: * size or requests that specify no hint value. * * PARAMETERS: - * ip - pointer to in-core inode; - * hint - allocation hint. - * nblocks - number of contiguous blocks in the range. - * results - on successful return, set to the starting block number + * ip - pointer to in-core inode; + * hint - allocation hint. + * nblocks - number of contiguous blocks in the range. + * results - on successful return, set to the starting block number * of the newly allocated contiguous range. * * RETURN VALUES: - * 0 - success - * -ENOSPC - insufficient disk resources - * -EIO - i/o error + * 0 - success + * -ENOSPC - insufficient disk resources + * -EIO - i/o error */ int dbAlloc(struct inode *ip, s64 hint, s64 nblocks, s64 * results) { @@ -706,12 +706,6 @@ int dbAlloc(struct inode *ip, s64 hint, s64 nblocks, s64 * results) /* assert that nblocks is valid */ assert(nblocks > 0); -#ifdef _STILL_TO_PORT - /* DASD limit check F226941 */ - if (OVER_LIMIT(ip, nblocks)) - return -ENOSPC; -#endif /* _STILL_TO_PORT */ - /* get the log2 number of blocks to be allocated. * if the number of blocks is not a log2 multiple, * it will be rounded up to the next log2 multiple. @@ -720,7 +714,6 @@ int dbAlloc(struct inode *ip, s64 hint, s64 nblocks, s64 * results) bmp = JFS_SBI(ip->i_sb)->bmap; -//retry: /* serialize w.r.t.extendfs() */ mapSize = bmp->db_mapsize; /* the hint should be within the map */ @@ -879,17 +872,17 @@ int dbAlloc(struct inode *ip, s64 hint, s64 nblocks, s64 * results) /* * NAME: dbAllocExact() * - * FUNCTION: try to allocate the requested extent; + * FUNCTION: try to allocate the requested extent; * * PARAMETERS: - * ip - pointer to in-core inode; - * blkno - extent address; - * nblocks - extent length; + * ip - pointer to in-core inode; + * blkno - extent address; + * nblocks - extent length; * * RETURN VALUES: - * 0 - success - * -ENOSPC - insufficient disk resources - * -EIO - i/o error + * 0 - success + * -ENOSPC - insufficient disk resources + * -EIO - i/o error */ int dbAllocExact(struct inode *ip, s64 blkno, int nblocks) { @@ -946,7 +939,7 @@ int dbAllocExact(struct inode *ip, s64 blkno, int nblocks) /* * NAME: dbReAlloc() * - * FUNCTION: attempt to extend a current allocation by a specified + * FUNCTION: attempt to extend a current allocation by a specified * number of blocks. * * this routine attempts to satisfy the allocation request @@ -959,21 +952,21 @@ int dbAllocExact(struct inode *ip, s64 blkno, int nblocks) * number of blocks required. * * PARAMETERS: - * ip - pointer to in-core inode requiring allocation. - * blkno - starting block of the current allocation. - * nblocks - number of contiguous blocks within the current + * ip - pointer to in-core inode requiring allocation. + * blkno - starting block of the current allocation. + * nblocks - number of contiguous blocks within the current * allocation. - * addnblocks - number of blocks to add to the allocation. - * results - on successful return, set to the starting block number + * addnblocks - number of blocks to add to the allocation. + * results - on successful return, set to the starting block number * of the existing allocation if the existing allocation * was extended in place or to a newly allocated contiguous * range if the existing allocation could not be extended * in place. * * RETURN VALUES: - * 0 - success - * -ENOSPC - insufficient disk resources - * -EIO - i/o error + * 0 - success + * -ENOSPC - insufficient disk resources + * -EIO - i/o error */ int dbReAlloc(struct inode *ip, @@ -1004,7 +997,7 @@ dbReAlloc(struct inode *ip, /* * NAME: dbExtend() * - * FUNCTION: attempt to extend a current allocation by a specified + * FUNCTION: attempt to extend a current allocation by a specified * number of blocks. * * this routine attempts to satisfy the allocation request @@ -1013,16 +1006,16 @@ dbReAlloc(struct inode *ip, * immediately following the current allocation. * * PARAMETERS: - * ip - pointer to in-core inode requiring allocation. - * blkno - starting block of the current allocation. - * nblocks - number of contiguous blocks within the current + * ip - pointer to in-core inode requiring allocation. + * blkno - starting block of the current allocation. + * nblocks - number of contiguous blocks within the current * allocation. - * addnblocks - number of blocks to add to the allocation. + * addnblocks - number of blocks to add to the allocation. * * RETURN VALUES: - * 0 - success - * -ENOSPC - insufficient disk resources - * -EIO - i/o error + * 0 - success + * -ENOSPC - insufficient disk resources + * -EIO - i/o error */ static int dbExtend(struct inode *ip, s64 blkno, s64 nblocks, s64 addnblocks) { @@ -1109,19 +1102,19 @@ static int dbExtend(struct inode *ip, s64 blkno, s64 nblocks, s64 addnblocks) /* * NAME: dbAllocNext() * - * FUNCTION: attempt to allocate the blocks of the specified block + * FUNCTION: attempt to allocate the blocks of the specified block * range within a dmap. * * PARAMETERS: - * bmp - pointer to bmap descriptor - * dp - pointer to dmap. - * blkno - starting block number of the range. - * nblocks - number of contiguous free blocks of the range. + * bmp - pointer to bmap descriptor + * dp - pointer to dmap. + * blkno - starting block number of the range. + * nblocks - number of contiguous free blocks of the range. * * RETURN VALUES: - * 0 - success - * -ENOSPC - insufficient disk resources - * -EIO - i/o error + * 0 - success + * -ENOSPC - insufficient disk resources + * -EIO - i/o error * * serialization: IREAD_LOCK(ipbmap) held on entry/exit; */ @@ -1233,7 +1226,7 @@ static int dbAllocNext(struct bmap * bmp, struct dmap * dp, s64 blkno, /* * NAME: dbAllocNear() * - * FUNCTION: attempt to allocate a number of contiguous free blocks near + * FUNCTION: attempt to allocate a number of contiguous free blocks near * a specified block (hint) within a dmap. * * starting with the dmap leaf that covers the hint, we'll @@ -1242,18 +1235,18 @@ static int dbAllocNext(struct bmap * bmp, struct dmap * dp, s64 blkno, * the desired free space. * * PARAMETERS: - * bmp - pointer to bmap descriptor - * dp - pointer to dmap. - * blkno - block number to allocate near. - * nblocks - actual number of contiguous free blocks desired. - * l2nb - log2 number of contiguous free blocks desired. - * results - on successful return, set to the starting block number + * bmp - pointer to bmap descriptor + * dp - pointer to dmap. + * blkno - block number to allocate near. + * nblocks - actual number of contiguous free blocks desired. + * l2nb - log2 number of contiguous free blocks desired. + * results - on successful return, set to the starting block number * of the newly allocated range. * * RETURN VALUES: - * 0 - success - * -ENOSPC - insufficient disk resources - * -EIO - i/o error + * 0 - success + * -ENOSPC - insufficient disk resources + * -EIO - i/o error * * serialization: IREAD_LOCK(ipbmap) held on entry/exit; */ @@ -1316,7 +1309,7 @@ dbAllocNear(struct bmap * bmp, /* * NAME: dbAllocAG() * - * FUNCTION: attempt to allocate the specified number of contiguous + * FUNCTION: attempt to allocate the specified number of contiguous * free blocks within the specified allocation group. * * unless the allocation group size is equal to the number @@ -1353,17 +1346,17 @@ dbAllocNear(struct bmap * bmp, * the allocation group. * * PARAMETERS: - * bmp - pointer to bmap descriptor + * bmp - pointer to bmap descriptor * agno - allocation group number. - * nblocks - actual number of contiguous free blocks desired. - * l2nb - log2 number of contiguous free blocks desired. - * results - on successful return, set to the starting block number + * nblocks - actual number of contiguous free blocks desired. + * l2nb - log2 number of contiguous free blocks desired. + * results - on successful return, set to the starting block number * of the newly allocated range. * * RETURN VALUES: - * 0 - success - * -ENOSPC - insufficient disk resources - * -EIO - i/o error + * 0 - success + * -ENOSPC - insufficient disk resources + * -EIO - i/o error * * note: IWRITE_LOCK(ipmap) held on entry/exit; */ @@ -1546,7 +1539,7 @@ dbAllocAG(struct bmap * bmp, int agno, s64 nblocks, int l2nb, s64 * results) /* * NAME: dbAllocAny() * - * FUNCTION: attempt to allocate the specified number of contiguous + * FUNCTION: attempt to allocate the specified number of contiguous * free blocks anywhere in the file system. * * dbAllocAny() attempts to find the sufficient free space by @@ -1556,16 +1549,16 @@ dbAllocAG(struct bmap * bmp, int agno, s64 nblocks, int l2nb, s64 * results) * desired free space is allocated. * * PARAMETERS: - * bmp - pointer to bmap descriptor - * nblocks - actual number of contiguous free blocks desired. - * l2nb - log2 number of contiguous free blocks desired. - * results - on successful return, set to the starting block number + * bmp - pointer to bmap descriptor + * nblocks - actual number of contiguous free blocks desired. + * l2nb - log2 number of contiguous free blocks desired. + * results - on successful return, set to the starting block number * of the newly allocated range. * * RETURN VALUES: - * 0 - success - * -ENOSPC - insufficient disk resources - * -EIO - i/o error + * 0 - success + * -ENOSPC - insufficient disk resources + * -EIO - i/o error * * serialization: IWRITE_LOCK(ipbmap) held on entry/exit; */ @@ -1598,9 +1591,9 @@ static int dbAllocAny(struct bmap * bmp, s64 nblocks, int l2nb, s64 * results) /* * NAME: dbFindCtl() * - * FUNCTION: starting at a specified dmap control page level and block + * FUNCTION: starting at a specified dmap control page level and block * number, search down the dmap control levels for a range of - * contiguous free blocks large enough to satisfy an allocation + * contiguous free blocks large enough to satisfy an allocation * request for the specified number of free blocks. * * if sufficient contiguous free blocks are found, this routine @@ -1609,17 +1602,17 @@ static int dbAllocAny(struct bmap * bmp, s64 nblocks, int l2nb, s64 * results) * is sufficient in size. * * PARAMETERS: - * bmp - pointer to bmap descriptor - * level - starting dmap control page level. - * l2nb - log2 number of contiguous free blocks desired. - * *blkno - on entry, starting block number for conducting the search. + * bmp - pointer to bmap descriptor + * level - starting dmap control page level. + * l2nb - log2 number of contiguous free blocks desired. + * *blkno - on entry, starting block number for conducting the search. * on successful return, the first block within a dmap page * that contains or starts a range of contiguous free blocks. * * RETURN VALUES: - * 0 - success - * -ENOSPC - insufficient disk resources - * -EIO - i/o error + * 0 - success + * -ENOSPC - insufficient disk resources + * -EIO - i/o error * * serialization: IWRITE_LOCK(ipbmap) held on entry/exit; */ @@ -1699,7 +1692,7 @@ static int dbFindCtl(struct bmap * bmp, int l2nb, int level, s64 * blkno) /* * NAME: dbAllocCtl() * - * FUNCTION: attempt to allocate a specified number of contiguous + * FUNCTION: attempt to allocate a specified number of contiguous * blocks starting within a specific dmap. * * this routine is called by higher level routines that search @@ -1726,18 +1719,18 @@ static int dbFindCtl(struct bmap * bmp, int l2nb, int level, s64 * blkno) * first dmap (i.e. blkno). * * PARAMETERS: - * bmp - pointer to bmap descriptor - * nblocks - actual number of contiguous free blocks to allocate. - * l2nb - log2 number of contiguous free blocks to allocate. - * blkno - starting block number of the dmap to start the allocation + * bmp - pointer to bmap descriptor + * nblocks - actual number of contiguous free blocks to allocate. + * l2nb - log2 number of contiguous free blocks to allocate. + * blkno - starting block number of the dmap to start the allocation * from. - * results - on successful return, set to the starting block number + * results - on successful return, set to the starting block number * of the newly allocated range. * * RETURN VALUES: - * 0 - success - * -ENOSPC - insufficient disk resources - * -EIO - i/o error + * 0 - success + * -ENOSPC - insufficient disk resources + * -EIO - i/o error * * serialization: IWRITE_LOCK(ipbmap) held on entry/exit; */ @@ -1870,7 +1863,7 @@ dbAllocCtl(struct bmap * bmp, s64 nblocks, int l2nb, s64 blkno, s64 * results) /* * NAME: dbAllocDmapLev() * - * FUNCTION: attempt to allocate a specified number of contiguous blocks + * FUNCTION: attempt to allocate a specified number of contiguous blocks * from a specified dmap. * * this routine checks if the contiguous blocks are available. @@ -1878,17 +1871,17 @@ dbAllocCtl(struct bmap * bmp, s64 nblocks, int l2nb, s64 blkno, s64 * results) * returned. * * PARAMETERS: - * mp - pointer to bmap descriptor - * dp - pointer to dmap to attempt to allocate blocks from. - * l2nb - log2 number of contiguous block desired. - * nblocks - actual number of contiguous block desired. - * results - on successful return, set to the starting block number + * mp - pointer to bmap descriptor + * dp - pointer to dmap to attempt to allocate blocks from. + * l2nb - log2 number of contiguous block desired. + * nblocks - actual number of contiguous block desired. + * results - on successful return, set to the starting block number * of the newly allocated range. * * RETURN VALUES: - * 0 - success - * -ENOSPC - insufficient disk resources - * -EIO - i/o error + * 0 - success + * -ENOSPC - insufficient disk resources + * -EIO - i/o error * * serialization: IREAD_LOCK(ipbmap), e.g., from dbAlloc(), or * IWRITE_LOCK(ipbmap), e.g., dbAllocCtl(), held on entry/exit; @@ -1933,7 +1926,7 @@ dbAllocDmapLev(struct bmap * bmp, /* * NAME: dbAllocDmap() * - * FUNCTION: adjust the disk allocation map to reflect the allocation + * FUNCTION: adjust the disk allocation map to reflect the allocation * of a specified block range within a dmap. * * this routine allocates the specified blocks from the dmap @@ -1946,14 +1939,14 @@ dbAllocDmapLev(struct bmap * bmp, * covers this dmap. * * PARAMETERS: - * bmp - pointer to bmap descriptor - * dp - pointer to dmap to allocate the block range from. - * blkno - starting block number of the block to be allocated. - * nblocks - number of blocks to be allocated. + * bmp - pointer to bmap descriptor + * dp - pointer to dmap to allocate the block range from. + * blkno - starting block number of the block to be allocated. + * nblocks - number of blocks to be allocated. * * RETURN VALUES: - * 0 - success - * -EIO - i/o error + * 0 - success + * -EIO - i/o error * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ @@ -1989,7 +1982,7 @@ static int dbAllocDmap(struct bmap * bmp, struct dmap * dp, s64 blkno, /* * NAME: dbFreeDmap() * - * FUNCTION: adjust the disk allocation map to reflect the allocation + * FUNCTION: adjust the disk allocation map to reflect the allocation * of a specified block range within a dmap. * * this routine frees the specified blocks from the dmap through @@ -1997,18 +1990,18 @@ static int dbAllocDmap(struct bmap * bmp, struct dmap * dp, s64 blkno, * causes the maximum string of free blocks within the dmap to * change (i.e. the value of the root of the dmap's dmtree), this * routine will cause this change to be reflected up through the - * appropriate levels of the dmap control pages by a call to + * appropriate levels of the dmap control pages by a call to * dbAdjCtl() for the L0 dmap control page that covers this dmap. * * PARAMETERS: - * bmp - pointer to bmap descriptor - * dp - pointer to dmap to free the block range from. - * blkno - starting block number of the block to be freed. - * nblocks - number of blocks to be freed. + * bmp - pointer to bmap descriptor + * dp - pointer to dmap to free the block range from. + * blkno - starting block number of the block to be freed. + * nblocks - number of blocks to be freed. * * RETURN VALUES: - * 0 - success - * -EIO - i/o error + * 0 - success + * -EIO - i/o error * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ @@ -2055,7 +2048,7 @@ static int dbFreeDmap(struct bmap * bmp, struct dmap * dp, s64 blkno, /* * NAME: dbAllocBits() * - * FUNCTION: allocate a specified block range from a dmap. + * FUNCTION: allocate a specified block range from a dmap. * * this routine updates the dmap to reflect the working * state allocation of the specified block range. it directly @@ -2065,10 +2058,10 @@ static int dbFreeDmap(struct bmap * bmp, struct dmap * dp, s64 blkno, * dmap's dmtree, as a whole, to reflect the allocated range. * * PARAMETERS: - * bmp - pointer to bmap descriptor - * dp - pointer to dmap to allocate bits from. - * blkno - starting block number of the bits to be allocated. - * nblocks - number of bits to be allocated. + * bmp - pointer to bmap descriptor + * dp - pointer to dmap to allocate bits from. + * blkno - starting block number of the bits to be allocated. + * nblocks - number of bits to be allocated. * * RETURN VALUES: none * @@ -2149,7 +2142,7 @@ static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno, * the allocated words. */ for (; nwords > 0; nwords -= nw) { - if (leaf[word] < BUDMIN) { + if (leaf[word] < BUDMIN) { jfs_error(bmp->db_ipbmap->i_sb, "dbAllocBits: leaf page " "corrupt"); @@ -2202,7 +2195,7 @@ static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno, /* * NAME: dbFreeBits() * - * FUNCTION: free a specified block range from a dmap. + * FUNCTION: free a specified block range from a dmap. * * this routine updates the dmap to reflect the working * state allocation of the specified block range. it directly @@ -2212,10 +2205,10 @@ static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno, * dmtree, as a whole, to reflect the deallocated range. * * PARAMETERS: - * bmp - pointer to bmap descriptor - * dp - pointer to dmap to free bits from. - * blkno - starting block number of the bits to be freed. - * nblocks - number of bits to be freed. + * bmp - pointer to bmap descriptor + * dp - pointer to dmap to free bits from. + * blkno - starting block number of the bits to be freed. + * nblocks - number of bits to be freed. * * RETURN VALUES: 0 for success * @@ -2388,19 +2381,19 @@ static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno, * the new root value and the next dmap control page level to * be adjusted. * PARAMETERS: - * bmp - pointer to bmap descriptor - * blkno - the first block of a block range within a dmap. it is + * bmp - pointer to bmap descriptor + * blkno - the first block of a block range within a dmap. it is * the allocation or deallocation of this block range that * requires the dmap control page to be adjusted. - * newval - the new value of the lower level dmap or dmap control + * newval - the new value of the lower level dmap or dmap control * page root. - * alloc - 'true' if adjustment is due to an allocation. - * level - current level of dmap control page (i.e. L0, L1, L2) to + * alloc - 'true' if adjustment is due to an allocation. + * level - current level of dmap control page (i.e. L0, L1, L2) to * be adjusted. * * RETURN VALUES: - * 0 - success - * -EIO - i/o error + * 0 - success + * -EIO - i/o error * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ @@ -2544,16 +2537,16 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level) /* * NAME: dbSplit() * - * FUNCTION: update the leaf of a dmtree with a new value, splitting + * FUNCTION: update the leaf of a dmtree with a new value, splitting * the leaf from the binary buddy system of the dmtree's * leaves, as required. * * PARAMETERS: - * tp - pointer to the tree containing the leaf. - * leafno - the number of the leaf to be updated. - * splitsz - the size the binary buddy system starting at the leaf + * tp - pointer to the tree containing the leaf. + * leafno - the number of the leaf to be updated. + * splitsz - the size the binary buddy system starting at the leaf * must be split to, specified as the log2 number of blocks. - * newval - the new value for the leaf. + * newval - the new value for the leaf. * * RETURN VALUES: none * @@ -2600,7 +2593,7 @@ static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval) /* * NAME: dbBackSplit() * - * FUNCTION: back split the binary buddy system of dmtree leaves + * FUNCTION: back split the binary buddy system of dmtree leaves * that hold a specified leaf until the specified leaf * starts its own binary buddy system. * @@ -2617,8 +2610,8 @@ static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval) * in which a previous join operation must be backed out. * * PARAMETERS: - * tp - pointer to the tree containing the leaf. - * leafno - the number of the leaf to be updated. + * tp - pointer to the tree containing the leaf. + * leafno - the number of the leaf to be updated. * * RETURN VALUES: none * @@ -2692,14 +2685,14 @@ static int dbBackSplit(dmtree_t * tp, int leafno) /* * NAME: dbJoin() * - * FUNCTION: update the leaf of a dmtree with a new value, joining + * FUNCTION: update the leaf of a dmtree with a new value, joining * the leaf with other leaves of the dmtree into a multi-leaf * binary buddy system, as required. * * PARAMETERS: - * tp - pointer to the tree containing the leaf. - * leafno - the number of the leaf to be updated. - * newval - the new value for the leaf. + * tp - pointer to the tree containing the leaf. + * leafno - the number of the leaf to be updated. + * newval - the new value for the leaf. * * RETURN VALUES: none */ @@ -2785,15 +2778,15 @@ static int dbJoin(dmtree_t * tp, int leafno, int newval) /* * NAME: dbAdjTree() * - * FUNCTION: update a leaf of a dmtree with a new value, adjusting + * FUNCTION: update a leaf of a dmtree with a new value, adjusting * the dmtree, as required, to reflect the new leaf value. * the combination of any buddies must already be done before * this is called. * * PARAMETERS: - * tp - pointer to the tree to be adjusted. - * leafno - the number of the leaf to be updated. - * newval - the new value for the leaf. + * tp - pointer to the tree to be adjusted. + * leafno - the number of the leaf to be updated. + * newval - the new value for the leaf. * * RETURN VALUES: none */ @@ -2852,7 +2845,7 @@ static void dbAdjTree(dmtree_t * tp, int leafno, int newval) /* * NAME: dbFindLeaf() * - * FUNCTION: search a dmtree_t for sufficient free blocks, returning + * FUNCTION: search a dmtree_t for sufficient free blocks, returning * the index of a leaf describing the free blocks if * sufficient free blocks are found. * @@ -2861,15 +2854,15 @@ static void dbAdjTree(dmtree_t * tp, int leafno, int newval) * free space. * * PARAMETERS: - * tp - pointer to the tree to be searched. - * l2nb - log2 number of free blocks to search for. + * tp - pointer to the tree to be searched. + * l2nb - log2 number of free blocks to search for. * leafidx - return pointer to be set to the index of the leaf * describing at least l2nb free blocks if sufficient * free blocks are found. * * RETURN VALUES: - * 0 - success - * -ENOSPC - insufficient free blocks. + * 0 - success + * -ENOSPC - insufficient free blocks. */ static int dbFindLeaf(dmtree_t * tp, int l2nb, int *leafidx) { @@ -2916,18 +2909,18 @@ static int dbFindLeaf(dmtree_t * tp, int l2nb, int *leafidx) /* * NAME: dbFindBits() * - * FUNCTION: find a specified number of binary buddy free bits within a + * FUNCTION: find a specified number of binary buddy free bits within a * dmap bitmap word value. * * this routine searches the bitmap value for (1 << l2nb) free * bits at (1 << l2nb) alignments within the value. * * PARAMETERS: - * word - dmap bitmap word value. - * l2nb - number of free bits specified as a log2 number. + * word - dmap bitmap word value. + * l2nb - number of free bits specified as a log2 number. * * RETURN VALUES: - * starting bit number of free bits. + * starting bit number of free bits. */ static int dbFindBits(u32 word, int l2nb) { @@ -2963,14 +2956,14 @@ static int dbFindBits(u32 word, int l2nb) /* * NAME: dbMaxBud(u8 *cp) * - * FUNCTION: determine the largest binary buddy string of free + * FUNCTION: determine the largest binary buddy string of free * bits within 32-bits of the map. * * PARAMETERS: - * cp - pointer to the 32-bit value. + * cp - pointer to the 32-bit value. * * RETURN VALUES: - * largest binary buddy of free bits within a dmap word. + * largest binary buddy of free bits within a dmap word. */ static int dbMaxBud(u8 * cp) { @@ -3000,14 +2993,14 @@ static int dbMaxBud(u8 * cp) /* * NAME: cnttz(uint word) * - * FUNCTION: determine the number of trailing zeros within a 32-bit + * FUNCTION: determine the number of trailing zeros within a 32-bit * value. * * PARAMETERS: - * value - 32-bit value to be examined. + * value - 32-bit value to be examined. * * RETURN VALUES: - * count of trailing zeros + * count of trailing zeros */ static int cnttz(u32 word) { @@ -3025,14 +3018,14 @@ static int cnttz(u32 word) /* * NAME: cntlz(u32 value) * - * FUNCTION: determine the number of leading zeros within a 32-bit + * FUNCTION: determine the number of leading zeros within a 32-bit * value. * * PARAMETERS: - * value - 32-bit value to be examined. + * value - 32-bit value to be examined. * * RETURN VALUES: - * count of leading zeros + * count of leading zeros */ static int cntlz(u32 value) { @@ -3050,14 +3043,14 @@ static int cntlz(u32 value) * NAME: blkstol2(s64 nb) * * FUNCTION: convert a block count to its log2 value. if the block - * count is not a l2 multiple, it is rounded up to the next + * count is not a l2 multiple, it is rounded up to the next * larger l2 multiple. * * PARAMETERS: - * nb - number of blocks + * nb - number of blocks * * RETURN VALUES: - * log2 number of blocks + * log2 number of blocks */ static int blkstol2(s64 nb) { @@ -3099,13 +3092,13 @@ static int blkstol2(s64 nb) * at a time. * * PARAMETERS: - * ip - pointer to in-core inode; - * blkno - starting block number to be freed. - * nblocks - number of blocks to be freed. + * ip - pointer to in-core inode; + * blkno - starting block number to be freed. + * nblocks - number of blocks to be freed. * * RETURN VALUES: - * 0 - success - * -EIO - i/o error + * 0 - success + * -EIO - i/o error */ int dbAllocBottomUp(struct inode *ip, s64 blkno, s64 nblocks) { @@ -3278,10 +3271,10 @@ static int dbAllocDmapBU(struct bmap * bmp, struct dmap * dp, s64 blkno, * L2 * | * L1---------------------------------L1 - * | | - * L0---------L0---------L0 L0---------L0---------L0 - * | | | | | | - * d0,...,dn d0,...,dn d0,...,dn d0,...,dn d0,...,dn d0,.,dm; + * | | + * L0---------L0---------L0 L0---------L0---------L0 + * | | | | | | + * d0,...,dn d0,...,dn d0,...,dn d0,...,dn d0,...,dn d0,.,dm; * L2L1L0d0,...,dnL0d0,...,dnL0d0,...,dnL1L0d0,...,dnL0d0,...,dnL0d0,..dm * * <---old---><----------------------------extend-----------------------> @@ -3307,7 +3300,7 @@ int dbExtendFS(struct inode *ipbmap, s64 blkno, s64 nblocks) (long long) blkno, (long long) nblocks, (long long) newsize); /* - * initialize bmap control page. + * initialize bmap control page. * * all the data in bmap control page should exclude * the mkfs hidden dmap page. @@ -3330,7 +3323,7 @@ int dbExtendFS(struct inode *ipbmap, s64 blkno, s64 nblocks) bmp->db_numag += ((u32) newsize % (u32) bmp->db_agsize) ? 1 : 0; /* - * reconfigure db_agfree[] + * reconfigure db_agfree[] * from old AG configuration to new AG configuration; * * coalesce contiguous k (newAGSize/oldAGSize) AGs; @@ -3362,7 +3355,7 @@ int dbExtendFS(struct inode *ipbmap, s64 blkno, s64 nblocks) bmp->db_maxag = bmp->db_maxag / k; /* - * extend bmap + * extend bmap * * update bit maps and corresponding level control pages; * global control page db_nfree, db_agfree[agno], db_maxfreebud; @@ -3410,7 +3403,7 @@ int dbExtendFS(struct inode *ipbmap, s64 blkno, s64 nblocks) /* compute start L0 */ j = 0; l1leaf = l1dcp->stree + CTLLEAFIND; - p += nbperpage; /* 1st L0 of L1.k */ + p += nbperpage; /* 1st L0 of L1.k */ } /* @@ -3548,7 +3541,7 @@ errout: return -EIO; /* - * finalize bmap control page + * finalize bmap control page */ finalize: @@ -3567,7 +3560,7 @@ void dbFinalizeBmap(struct inode *ipbmap) int i, n; /* - * finalize bmap control page + * finalize bmap control page */ //finalize: /* @@ -3953,8 +3946,8 @@ static int dbGetL2AGSize(s64 nblocks) * convert number of map pages to the zero origin top dmapctl level */ #define BMAPPGTOLEV(npages) \ - (((npages) <= 3 + MAXL0PAGES) ? 0 \ - : ((npages) <= 2 + MAXL1PAGES) ? 1 : 2) + (((npages) <= 3 + MAXL0PAGES) ? 0 : \ + ((npages) <= 2 + MAXL1PAGES) ? 1 : 2) s64 dbMapFileSizeToMapSize(struct inode * ipbmap) { @@ -3981,8 +3974,8 @@ s64 dbMapFileSizeToMapSize(struct inode * ipbmap) factor = (i == 2) ? MAXL1PAGES : ((i == 1) ? MAXL0PAGES : 1); complete = (u32) npages / factor; - ndmaps += complete * ((i == 2) ? LPERCTL * LPERCTL - : ((i == 1) ? LPERCTL : 1)); + ndmaps += complete * ((i == 2) ? LPERCTL * LPERCTL : + ((i == 1) ? LPERCTL : 1)); /* pages in last/incomplete child */ npages = (u32) npages % factor; diff --git a/fs/jfs/jfs_dmap.h b/fs/jfs/jfs_dmap.h index 45ea454c74b..11e6d471b36 100644 --- a/fs/jfs/jfs_dmap.h +++ b/fs/jfs/jfs_dmap.h @@ -83,7 +83,7 @@ static __inline signed char TREEMAX(signed char *cp) * - 1 is added to account for the control page of the map. */ #define BLKTODMAP(b,s) \ - ((((b) >> 13) + ((b) >> 23) + ((b) >> 33) + 3 + 1) << (s)) + ((((b) >> 13) + ((b) >> 23) + ((b) >> 33) + 3 + 1) << (s)) /* * convert disk block number to the logical block number of the LEVEL 0 @@ -98,7 +98,7 @@ static __inline signed char TREEMAX(signed char *cp) * - 1 is added to account for the control page of the map. */ #define BLKTOL0(b,s) \ - (((((b) >> 23) << 10) + ((b) >> 23) + ((b) >> 33) + 2 + 1) << (s)) + (((((b) >> 23) << 10) + ((b) >> 23) + ((b) >> 33) + 2 + 1) << (s)) /* * convert disk block number to the logical block number of the LEVEL 1 @@ -120,7 +120,7 @@ static __inline signed char TREEMAX(signed char *cp) * at the specified level which describes the disk block. */ #define BLKTOCTL(b,s,l) \ - (((l) == 2) ? 1 : ((l) == 1) ? BLKTOL1((b),(s)) : BLKTOL0((b),(s))) + (((l) == 2) ? 1 : ((l) == 1) ? BLKTOL1((b),(s)) : BLKTOL0((b),(s))) /* * convert aggregate map size to the zero origin dmapctl level of the @@ -145,27 +145,27 @@ static __inline signed char TREEMAX(signed char *cp) * dmaptree must be consistent with dmapctl. */ struct dmaptree { - __le32 nleafs; /* 4: number of tree leafs */ - __le32 l2nleafs; /* 4: l2 number of tree leafs */ - __le32 leafidx; /* 4: index of first tree leaf */ - __le32 height; /* 4: height of the tree */ + __le32 nleafs; /* 4: number of tree leafs */ + __le32 l2nleafs; /* 4: l2 number of tree leafs */ + __le32 leafidx; /* 4: index of first tree leaf */ + __le32 height; /* 4: height of the tree */ s8 budmin; /* 1: min l2 tree leaf value to combine */ - s8 stree[TREESIZE]; /* TREESIZE: tree */ - u8 pad[2]; /* 2: pad to word boundary */ -}; /* - 360 - */ + s8 stree[TREESIZE]; /* TREESIZE: tree */ + u8 pad[2]; /* 2: pad to word boundary */ +}; /* - 360 - */ /* * dmap page per 8K blocks bitmap */ struct dmap { - __le32 nblocks; /* 4: num blks covered by this dmap */ - __le32 nfree; /* 4: num of free blks in this dmap */ - __le64 start; /* 8: starting blkno for this dmap */ - struct dmaptree tree; /* 360: dmap tree */ - u8 pad[1672]; /* 1672: pad to 2048 bytes */ - __le32 wmap[LPERDMAP]; /* 1024: bits of the working map */ - __le32 pmap[LPERDMAP]; /* 1024: bits of the persistent map */ -}; /* - 4096 - */ + __le32 nblocks; /* 4: num blks covered by this dmap */ + __le32 nfree; /* 4: num of free blks in this dmap */ + __le64 start; /* 8: starting blkno for this dmap */ + struct dmaptree tree; /* 360: dmap tree */ + u8 pad[1672]; /* 1672: pad to 2048 bytes */ + __le32 wmap[LPERDMAP]; /* 1024: bits of the working map */ + __le32 pmap[LPERDMAP]; /* 1024: bits of the persistent map */ +}; /* - 4096 - */ /* * disk map control page per level. @@ -173,14 +173,14 @@ struct dmap { * dmapctl must be consistent with dmaptree. */ struct dmapctl { - __le32 nleafs; /* 4: number of tree leafs */ - __le32 l2nleafs; /* 4: l2 number of tree leafs */ - __le32 leafidx; /* 4: index of the first tree leaf */ - __le32 height; /* 4: height of tree */ - s8 budmin; /* 1: minimum l2 tree leaf value */ - s8 stree[CTLTREESIZE]; /* CTLTREESIZE: dmapctl tree */ - u8 pad[2714]; /* 2714: pad to 4096 */ -}; /* - 4096 - */ + __le32 nleafs; /* 4: number of tree leafs */ + __le32 l2nleafs; /* 4: l2 number of tree leafs */ + __le32 leafidx; /* 4: index of the first tree leaf */ + __le32 height; /* 4: height of tree */ + s8 budmin; /* 1: minimum l2 tree leaf value */ + s8 stree[CTLTREESIZE]; /* CTLTREESIZE: dmapctl tree */ + u8 pad[2714]; /* 2714: pad to 4096 */ +}; /* - 4096 - */ /* * common definition for dmaptree within dmap and dmapctl @@ -202,41 +202,41 @@ typedef union dmtree { * on-disk aggregate disk allocation map descriptor. */ struct dbmap_disk { - __le64 dn_mapsize; /* 8: number of blocks in aggregate */ - __le64 dn_nfree; /* 8: num free blks in aggregate map */ - __le32 dn_l2nbperpage; /* 4: number of blks per page */ - __le32 dn_numag; /* 4: total number of ags */ - __le32 dn_maxlevel; /* 4: number of active ags */ - __le32 dn_maxag; /* 4: max active alloc group number */ - __le32 dn_agpref; /* 4: preferred alloc group (hint) */ - __le32 dn_aglevel; /* 4: dmapctl level holding the AG */ - __le32 dn_agheigth; /* 4: height in dmapctl of the AG */ - __le32 dn_agwidth; /* 4: width in dmapctl of the AG */ - __le32 dn_agstart; /* 4: start tree index at AG height */ - __le32 dn_agl2size; /* 4: l2 num of blks per alloc group */ - __le64 dn_agfree[MAXAG];/* 8*MAXAG: per AG free count */ - __le64 dn_agsize; /* 8: num of blks per alloc group */ - s8 dn_maxfreebud; /* 1: max free buddy system */ - u8 pad[3007]; /* 3007: pad to 4096 */ -}; /* - 4096 - */ + __le64 dn_mapsize; /* 8: number of blocks in aggregate */ + __le64 dn_nfree; /* 8: num free blks in aggregate map */ + __le32 dn_l2nbperpage; /* 4: number of blks per page */ + __le32 dn_numag; /* 4: total number of ags */ + __le32 dn_maxlevel; /* 4: number of active ags */ + __le32 dn_maxag; /* 4: max active alloc group number */ + __le32 dn_agpref; /* 4: preferred alloc group (hint) */ + __le32 dn_aglevel; /* 4: dmapctl level holding the AG */ + __le32 dn_agheigth; /* 4: height in dmapctl of the AG */ + __le32 dn_agwidth; /* 4: width in dmapctl of the AG */ + __le32 dn_agstart; /* 4: start tree index at AG height */ + __le32 dn_agl2size; /* 4: l2 num of blks per alloc group */ + __le64 dn_agfree[MAXAG];/* 8*MAXAG: per AG free count */ + __le64 dn_agsize; /* 8: num of blks per alloc group */ + s8 dn_maxfreebud; /* 1: max free buddy system */ + u8 pad[3007]; /* 3007: pad to 4096 */ +}; /* - 4096 - */ struct dbmap { - s64 dn_mapsize; /* number of blocks in aggregate */ - s64 dn_nfree; /* num free blks in aggregate map */ - int dn_l2nbperpage; /* number of blks per page */ - int dn_numag; /* total number of ags */ - int dn_maxlevel; /* number of active ags */ - int dn_maxag; /* max active alloc group number */ - int dn_agpref; /* preferred alloc group (hint) */ - int dn_aglevel; /* dmapctl level holding the AG */ - int dn_agheigth; /* height in dmapctl of the AG */ - int dn_agwidth; /* width in dmapctl of the AG */ - int dn_agstart; /* start tree index at AG height */ - int dn_agl2size; /* l2 num of blks per alloc group */ - s64 dn_agfree[MAXAG]; /* per AG free count */ - s64 dn_agsize; /* num of blks per alloc group */ - signed char dn_maxfreebud; /* max free buddy system */ -}; /* - 4096 - */ + s64 dn_mapsize; /* number of blocks in aggregate */ + s64 dn_nfree; /* num free blks in aggregate map */ + int dn_l2nbperpage; /* number of blks per page */ + int dn_numag; /* total number of ags */ + int dn_maxlevel; /* number of active ags */ + int dn_maxag; /* max active alloc group number */ + int dn_agpref; /* preferred alloc group (hint) */ + int dn_aglevel; /* dmapctl level holding the AG */ + int dn_agheigth; /* height in dmapctl of the AG */ + int dn_agwidth; /* width in dmapctl of the AG */ + int dn_agstart; /* start tree index at AG height */ + int dn_agl2size; /* l2 num of blks per alloc group */ + s64 dn_agfree[MAXAG]; /* per AG free count */ + s64 dn_agsize; /* num of blks per alloc group */ + signed char dn_maxfreebud; /* max free buddy system */ +}; /* - 4096 - */ /* * in-memory aggregate disk allocation map descriptor. */ diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c index 6d62f322289..c14ba3cfa81 100644 --- a/fs/jfs/jfs_dtree.c +++ b/fs/jfs/jfs_dtree.c @@ -315,8 +315,8 @@ static inline void lock_index(tid_t tid, struct inode *ip, struct metapage * mp, lv = &llck->lv[llck->index]; /* - * Linelock slot size is twice the size of directory table - * slot size. 512 entries per page. + * Linelock slot size is twice the size of directory table + * slot size. 512 entries per page. */ lv->offset = ((index - 2) & 511) >> 1; lv->length = 1; @@ -615,7 +615,7 @@ int dtSearch(struct inode *ip, struct component_name * key, ino_t * data, btstack->nsplit = 1; /* - * search down tree from root: + * search down tree from root: * * between two consecutive entries of <Ki, Pi> and <Kj, Pj> of * internal page, child page Pi contains entry with k, Ki <= K < Kj. @@ -659,7 +659,7 @@ int dtSearch(struct inode *ip, struct component_name * key, ino_t * data, } if (cmp == 0) { /* - * search hit + * search hit */ /* search hit - leaf page: * return the entry found @@ -723,7 +723,7 @@ int dtSearch(struct inode *ip, struct component_name * key, ino_t * data, } /* - * search miss + * search miss * * base is the smallest index with key (Kj) greater than * search key (K) and may be zero or (maxindex + 1) index. @@ -834,7 +834,7 @@ int dtInsert(tid_t tid, struct inode *ip, struct lv *lv; /* - * retrieve search result + * retrieve search result * * dtSearch() returns (leaf page pinned, index at which to insert). * n.b. dtSearch() may return index of (maxindex + 1) of @@ -843,7 +843,7 @@ int dtInsert(tid_t tid, struct inode *ip, DT_GETSEARCH(ip, btstack->top, bn, mp, p, index); /* - * insert entry for new key + * insert entry for new key */ if (DO_INDEX(ip)) { if (JFS_IP(ip)->next_index == DIREND) { @@ -860,9 +860,9 @@ int dtInsert(tid_t tid, struct inode *ip, data.leaf.ino = *fsn; /* - * leaf page does not have enough room for new entry: + * leaf page does not have enough room for new entry: * - * extend/split the leaf page; + * extend/split the leaf page; * * dtSplitUp() will insert the entry and unpin the leaf page. */ @@ -877,9 +877,9 @@ int dtInsert(tid_t tid, struct inode *ip, } /* - * leaf page does have enough room for new entry: + * leaf page does have enough room for new entry: * - * insert the new data entry into the leaf page; + * insert the new data entry into the leaf page; */ BT_MARK_DIRTY(mp, ip); /* @@ -967,13 +967,13 @@ static int dtSplitUp(tid_t tid, } /* - * split leaf page + * split leaf page * * The split routines insert the new entry, and * acquire txLock as appropriate. */ /* - * split root leaf page: + * split root leaf page: */ if (sp->header.flag & BT_ROOT) { /* @@ -1012,7 +1012,7 @@ static int dtSplitUp(tid_t tid, } /* - * extend first leaf page + * extend first leaf page * * extend the 1st extent if less than buffer page size * (dtExtendPage() reurns leaf page unpinned) @@ -1068,7 +1068,7 @@ static int dtSplitUp(tid_t tid, } /* - * split leaf page <sp> into <sp> and a new right page <rp>. + * split leaf page <sp> into <sp> and a new right page <rp>. * * return <rp> pinned and its extent descriptor <rpxd> */ @@ -1433,7 +1433,7 @@ static int dtSplitPage(tid_t tid, struct inode *ip, struct dtsplit * split, rp->header.freecnt = rp->header.maxslot - fsi; /* - * sequential append at tail: append without split + * sequential append at tail: append without split * * If splitting the last page on a level because of appending * a entry to it (skip is maxentry), it's likely that the access is @@ -1467,7 +1467,7 @@ static int dtSplitPage(tid_t tid, struct inode *ip, struct dtsplit * split, } /* - * non-sequential insert (at possibly middle page) + * non-sequential insert (at possibly middle page) */ /* @@ -1508,7 +1508,7 @@ static int dtSplitPage(tid_t tid, struct inode *ip, struct dtsplit * split, left = 0; /* - * compute fill factor for split pages + * compute fill factor for split pages * * <nxt> traces the next entry to move to rp * <off> traces the next entry to stay in sp @@ -1551,7 +1551,7 @@ static int dtSplitPage(tid_t tid, struct inode *ip, struct dtsplit * split, /* <nxt> poins to the 1st entry to move */ /* - * move entries to right page + * move entries to right page * * dtMoveEntry() initializes rp and reserves entry for insertion * @@ -1677,7 +1677,7 @@ static int dtExtendPage(tid_t tid, return (rc); /* - * extend the extent + * extend the extent */ pxdlist = split->pxdlist; pxd = &pxdlist->pxd[pxdlist->npxd]; @@ -1722,7 +1722,7 @@ static int dtExtendPage(tid_t tid, } /* - * extend the page + * extend the page */ sp->header.self = *pxd; @@ -1739,9 +1739,6 @@ static int dtExtendPage(tid_t tid, /* update buffer extent descriptor of extended page */ xlen = lengthPXD(pxd); xsize = xlen << JFS_SBI(sb)->l2bsize; -#ifdef _STILL_TO_PORT - bmSetXD(smp, xaddr, xsize); -#endif /* _STILL_TO_PORT */ /* * copy old stbl to new stbl at start of extended area @@ -1836,7 +1833,7 @@ static int dtExtendPage(tid_t tid, } /* - * update parent entry on the parent/root page + * update parent entry on the parent/root page */ /* * acquire a transaction lock on the parent/root page @@ -1904,7 +1901,7 @@ static int dtSplitRoot(tid_t tid, sp = &JFS_IP(ip)->i_dtroot; /* - * allocate/initialize a single (right) child page + * allocate/initialize a single (right) child page * * N.B. at first split, a one (or two) block to fit new entry * is allocated; at subsequent split, a full page is allocated; @@ -1943,7 +1940,7 @@ static int dtSplitRoot(tid_t tid, rp->header.prev = 0; /* - * move in-line root page into new right page extent + * move in-line root page into new right page extent */ /* linelock header + copied entries + new stbl (1st slot) in new page */ ASSERT(dtlck->index == 0); @@ -2016,7 +2013,7 @@ static int dtSplitRoot(tid_t tid, dtInsertEntry(rp, split->index, split->key, split->data, &dtlck); /* - * reset parent/root page + * reset parent/root page * * set the 1st entry offset to 0, which force the left-most key * at any level of the tree to be less than any search key. @@ -2102,7 +2099,7 @@ int dtDelete(tid_t tid, dtpage_t *np; /* - * search for the entry to delete: + * search for the entry to delete: * * dtSearch() returns (leaf page pinned, index at which to delete). */ @@ -2253,7 +2250,7 @@ static int dtDeleteUp(tid_t tid, struct inode *ip, int i; /* - * keep the root leaf page which has become empty + * keep the root leaf page which has become empty */ if (BT_IS_ROOT(fmp)) { /* @@ -2269,7 +2266,7 @@ static int dtDeleteUp(tid_t tid, struct inode *ip, } /* - * free the non-root leaf page + * free the non-root leaf page */ /* * acquire a transaction lock on the page @@ -2299,7 +2296,7 @@ static int dtDeleteUp(tid_t tid, struct inode *ip, discard_metapage(fmp); /* - * propagate page deletion up the directory tree + * propagate page deletion up the directory tree * * If the delete from the parent page makes it empty, * continue all the way up the tree. @@ -2440,10 +2437,10 @@ static int dtDeleteUp(tid_t tid, struct inode *ip, #ifdef _NOTYET /* - * NAME: dtRelocate() + * NAME: dtRelocate() * - * FUNCTION: relocate dtpage (internal or leaf) of directory; - * This function is mainly used by defragfs utility. + * FUNCTION: relocate dtpage (internal or leaf) of directory; + * This function is mainly used by defragfs utility. */ int dtRelocate(tid_t tid, struct inode *ip, s64 lmxaddr, pxd_t * opxd, s64 nxaddr) @@ -2471,8 +2468,8 @@ int dtRelocate(tid_t tid, struct inode *ip, s64 lmxaddr, pxd_t * opxd, xlen); /* - * 1. get the internal parent dtpage covering - * router entry for the tartget page to be relocated; + * 1. get the internal parent dtpage covering + * router entry for the tartget page to be relocated; */ rc = dtSearchNode(ip, lmxaddr, opxd, &btstack); if (rc) @@ -2483,7 +2480,7 @@ int dtRelocate(tid_t tid, struct inode *ip, s64 lmxaddr, pxd_t * opxd, jfs_info("dtRelocate: parent router entry validated."); /* - * 2. relocate the target dtpage + * 2. relocate the target dtpage */ /* read in the target page from src extent */ DT_GETPAGE(ip, oxaddr, mp, PSIZE, p, rc); @@ -2581,9 +2578,7 @@ int dtRelocate(tid_t tid, struct inode *ip, s64 lmxaddr, pxd_t * opxd, /* update the buffer extent descriptor of the dtpage */ xsize = xlen << JFS_SBI(ip->i_sb)->l2bsize; -#ifdef _STILL_TO_PORT - bmSetXD(mp, nxaddr, xsize); -#endif /* _STILL_TO_PORT */ + /* unpin the relocated page */ DT_PUTPAGE(mp); jfs_info("dtRelocate: target dtpage relocated."); @@ -2594,7 +2589,7 @@ int dtRelocate(tid_t tid, struct inode *ip, s64 lmxaddr, pxd_t * opxd, */ /* - * 3. acquire maplock for the source extent to be freed; + * 3. acquire maplock for the source extent to be freed; */ /* for dtpage relocation, write a LOG_NOREDOPAGE record * for the source dtpage (logredo() will init NoRedoPage @@ -2609,7 +2604,7 @@ int dtRelocate(tid_t tid, struct inode *ip, s64 lmxaddr, pxd_t * opxd, pxdlock->index = 1; /* - * 4. update the parent router entry for relocation; + * 4. update the parent router entry for relocation; * * acquire tlck for the parent entry covering the target dtpage; * write LOG_REDOPAGE to apply after image only; @@ -2637,7 +2632,7 @@ int dtRelocate(tid_t tid, struct inode *ip, s64 lmxaddr, pxd_t * opxd, * NAME: dtSearchNode() * * FUNCTION: Search for an dtpage containing a specified address - * This function is mainly used by defragfs utility. + * This function is mainly used by defragfs utility. * * NOTE: Search result on stack, the found page is pinned at exit. * The result page must be an internal dtpage. @@ -2660,7 +2655,7 @@ static int dtSearchNode(struct inode *ip, s64 lmxaddr, pxd_t * kpxd, BT_CLR(btstack); /* reset stack */ /* - * descend tree to the level with specified leftmost page + * descend tree to the level with specified leftmost page * * by convention, root bn = 0. */ @@ -2699,7 +2694,7 @@ static int dtSearchNode(struct inode *ip, s64 lmxaddr, pxd_t * kpxd, } /* - * search each page at the current levevl + * search each page at the current levevl */ loop: stbl = DT_GETSTBL(p); @@ -3044,9 +3039,9 @@ int jfs_readdir(struct file *filp, void *dirent, filldir_t filldir) if (DO_INDEX(ip)) { /* * persistent index is stored in directory entries. - * Special cases: 0 = . - * 1 = .. - * -1 = End of directory + * Special cases: 0 = . + * 1 = .. + * -1 = End of directory */ do_index = 1; @@ -3128,10 +3123,10 @@ int jfs_readdir(struct file *filp, void *dirent, filldir_t filldir) /* * Legacy filesystem - OS/2 & Linux JFS < 0.3.6 * - * pn = index = 0: First entry "." - * pn = 0; index = 1: Second entry ".." - * pn > 0: Real entries, pn=1 -> leftmost page - * pn = index = -1: No more entries + * pn = index = 0: First entry "." + * pn = 0; index = 1: Second entry ".." + * pn > 0: Real entries, pn=1 -> leftmost page + * pn = index = -1: No more entries */ dtpos = filp->f_pos; if (dtpos == 0) { @@ -3351,7 +3346,7 @@ static int dtReadFirst(struct inode *ip, struct btstack * btstack) BT_CLR(btstack); /* reset stack */ /* - * descend leftmost path of the tree + * descend leftmost path of the tree * * by convention, root bn = 0. */ @@ -4531,7 +4526,7 @@ int dtModify(tid_t tid, struct inode *ip, struct ldtentry *entry; /* - * search for the entry to modify: + * search for the entry to modify: * * dtSearch() returns (leaf page pinned, index at which to modify). */ diff --git a/fs/jfs/jfs_dtree.h b/fs/jfs/jfs_dtree.h index af8513f7864..8561c6ecece 100644 --- a/fs/jfs/jfs_dtree.h +++ b/fs/jfs/jfs_dtree.h @@ -35,7 +35,7 @@ typedef union { /* - * entry segment/slot + * entry segment/slot * * an entry consists of type dependent head/only segment/slot and * additional segments/slots linked vi next field; diff --git a/fs/jfs/jfs_extent.c b/fs/jfs/jfs_extent.c index a35bdca6a80..7ae1e3281de 100644 --- a/fs/jfs/jfs_extent.c +++ b/fs/jfs/jfs_extent.c @@ -34,8 +34,8 @@ static int extBrealloc(struct inode *, s64, s64, s64 *, s64 *); #endif static s64 extRoundDown(s64 nb); -#define DPD(a) (printk("(a): %d\n",(a))) -#define DPC(a) (printk("(a): %c\n",(a))) +#define DPD(a) (printk("(a): %d\n",(a))) +#define DPC(a) (printk("(a): %c\n",(a))) #define DPL1(a) \ { \ if ((a) >> 32) \ @@ -51,19 +51,19 @@ static s64 extRoundDown(s64 nb); printk("(a): %x\n",(a) << 32); \ } -#define DPD1(a) (printk("(a): %d ",(a))) -#define DPX(a) (printk("(a): %08x\n",(a))) -#define DPX1(a) (printk("(a): %08x ",(a))) -#define DPS(a) (printk("%s\n",(a))) -#define DPE(a) (printk("\nENTERING: %s\n",(a))) -#define DPE1(a) (printk("\nENTERING: %s",(a))) -#define DPS1(a) (printk(" %s ",(a))) +#define DPD1(a) (printk("(a): %d ",(a))) +#define DPX(a) (printk("(a): %08x\n",(a))) +#define DPX1(a) (printk("(a): %08x ",(a))) +#define DPS(a) (printk("%s\n",(a))) +#define DPE(a) (printk("\nENTERING: %s\n",(a))) +#define DPE1(a) (printk("\nENTERING: %s",(a))) +#define DPS1(a) (printk(" %s ",(a))) /* * NAME: extAlloc() * - * FUNCTION: allocate an extent for a specified page range within a + * FUNCTION: allocate an extent for a specified page range within a * file. * * PARAMETERS: @@ -78,9 +78,9 @@ static s64 extRoundDown(s64 nb); * should be marked as allocated but not recorded. * * RETURN VALUES: - * 0 - success - * -EIO - i/o error. - * -ENOSPC - insufficient disk resources. + * 0 - success + * -EIO - i/o error. + * -ENOSPC - insufficient disk resources. */ int extAlloc(struct inode *ip, s64 xlen, s64 pno, xad_t * xp, bool abnr) @@ -192,9 +192,9 @@ extAlloc(struct inode *ip, s64 xlen, s64 pno, xad_t * xp, bool abnr) #ifdef _NOTYET /* - * NAME: extRealloc() + * NAME: extRealloc() * - * FUNCTION: extend the allocation of a file extent containing a + * FUNCTION: extend the allocation of a file extent containing a * partial back last page. * * PARAMETERS: @@ -207,9 +207,9 @@ extAlloc(struct inode *ip, s64 xlen, s64 pno, xad_t * xp, bool abnr) * should be marked as allocated but not recorded. * * RETURN VALUES: - * 0 - success - * -EIO - i/o error. - * -ENOSPC - insufficient disk resources. + * 0 - success + * -EIO - i/o error. + * -ENOSPC - insufficient disk resources. */ int extRealloc(struct inode *ip, s64 nxlen, xad_t * xp, bool abnr) { @@ -345,9 +345,9 @@ exit: /* - * NAME: extHint() + * NAME: extHint() * - * FUNCTION: produce an extent allocation hint for a file offset. + * FUNCTION: produce an extent allocation hint for a file offset. * * PARAMETERS: * ip - the inode of the file. @@ -356,8 +356,8 @@ exit: * the hint. * * RETURN VALUES: - * 0 - success - * -EIO - i/o error. + * 0 - success + * -EIO - i/o error. */ int extHint(struct inode *ip, s64 offset, xad_t * xp) { @@ -387,7 +387,7 @@ int extHint(struct inode *ip, s64 offset, xad_t * xp) lxdl.nlxd = 1; lxdl.lxd = &lxd; LXDoffset(&lxd, prev) - LXDlength(&lxd, nbperpage); + LXDlength(&lxd, nbperpage); xadl.maxnxad = 1; xadl.nxad = 0; @@ -397,11 +397,11 @@ int extHint(struct inode *ip, s64 offset, xad_t * xp) if ((rc = xtLookupList(ip, &lxdl, &xadl, 0))) return (rc); - /* check if not extent exists for the previous page. + /* check if no extent exists for the previous page. * this is possible for sparse files. */ if (xadl.nxad == 0) { -// assert(ISSPARSE(ip)); +// assert(ISSPARSE(ip)); return (0); } @@ -410,28 +410,28 @@ int extHint(struct inode *ip, s64 offset, xad_t * xp) */ xp->flag &= XAD_NOTRECORDED; - if(xadl.nxad != 1 || lengthXAD(xp) != nbperpage) { + if(xadl.nxad != 1 || lengthXAD(xp) != nbperpage) { jfs_error(ip->i_sb, "extHint: corrupt xtree"); return -EIO; - } + } return (0); } /* - * NAME: extRecord() + * NAME: extRecord() * - * FUNCTION: change a page with a file from not recorded to recorded. + * FUNCTION: change a page with a file from not recorded to recorded. * * PARAMETERS: * ip - inode of the file. * cp - cbuf of the file page. * * RETURN VALUES: - * 0 - success - * -EIO - i/o error. - * -ENOSPC - insufficient disk resources. + * 0 - success + * -EIO - i/o error. + * -ENOSPC - insufficient disk resources. */ int extRecord(struct inode *ip, xad_t * xp) { @@ -451,9 +451,9 @@ int extRecord(struct inode *ip, xad_t * xp) #ifdef _NOTYET /* - * NAME: extFill() + * NAME: extFill() * - * FUNCTION: allocate disk space for a file page that represents + * FUNCTION: allocate disk space for a file page that represents * a file hole. * * PARAMETERS: @@ -461,16 +461,16 @@ int extRecord(struct inode *ip, xad_t * xp) * cp - cbuf of the file page represent the hole. * * RETURN VALUES: - * 0 - success - * -EIO - i/o error. - * -ENOSPC - insufficient disk resources. + * 0 - success + * -EIO - i/o error. + * -ENOSPC - insufficient disk resources. */ int extFill(struct inode *ip, xad_t * xp) { int rc, nbperpage = JFS_SBI(ip->i_sb)->nbperpage; s64 blkno = offsetXAD(xp) >> ip->i_blkbits; -// assert(ISSPARSE(ip)); +// assert(ISSPARSE(ip)); /* initialize the extent allocation hint */ XADaddress(xp, 0); @@ -489,7 +489,7 @@ int extFill(struct inode *ip, xad_t * xp) /* * NAME: extBalloc() * - * FUNCTION: allocate disk blocks to form an extent. + * FUNCTION: allocate disk blocks to form an extent. * * initially, we will try to allocate disk blocks for the * requested size (nblocks). if this fails (nblocks @@ -513,9 +513,9 @@ int extFill(struct inode *ip, xad_t * xp) * allocated block range. * * RETURN VALUES: - * 0 - success - * -EIO - i/o error. - * -ENOSPC - insufficient disk resources. + * 0 - success + * -EIO - i/o error. + * -ENOSPC - insufficient disk resources. */ static int extBalloc(struct inode *ip, s64 hint, s64 * nblocks, s64 * blkno) @@ -580,7 +580,7 @@ extBalloc(struct inode *ip, s64 hint, s64 * nblocks, s64 * blkno) /* * NAME: extBrealloc() * - * FUNCTION: attempt to extend an extent's allocation. + * FUNCTION: attempt to extend an extent's allocation. * * Initially, we will try to extend the extent's allocation * in place. If this fails, we'll try to move the extent @@ -597,8 +597,8 @@ extBalloc(struct inode *ip, s64 hint, s64 * nblocks, s64 * blkno) * * PARAMETERS: * ip - the inode of the file. - * blkno - starting block number of the extents current allocation. - * nblks - number of blocks within the extents current allocation. + * blkno - starting block number of the extents current allocation. + * nblks - number of blocks within the extents current allocation. * newnblks - pointer to a s64 value. on entry, this value is the * the new desired extent size (number of blocks). on * successful exit, this value is set to the extent's actual @@ -606,9 +606,9 @@ extBalloc(struct inode *ip, s64 hint, s64 * nblocks, s64 * blkno) * newblkno - the starting block number of the extents new allocation. * * RETURN VALUES: - * 0 - success - * -EIO - i/o error. - * -ENOSPC - insufficient disk resources. + * 0 - success + * -EIO - i/o error. + * -ENOSPC - insufficient disk resources. */ static int extBrealloc(struct inode *ip, @@ -634,16 +634,16 @@ extBrealloc(struct inode *ip, /* - * NAME: extRoundDown() + * NAME: extRoundDown() * - * FUNCTION: round down a specified number of blocks to the next + * FUNCTION: round down a specified number of blocks to the next * smallest power of 2 number. * * PARAMETERS: * nb - the inode of the file. * * RETURN VALUES: - * next smallest power of 2 number. + * next smallest power of 2 number. */ static s64 extRoundDown(s64 nb) { diff --git a/fs/jfs/jfs_filsys.h b/fs/jfs/jfs_filsys.h index 38f70ac03be..b3f5463fbe5 100644 --- a/fs/jfs/jfs_filsys.h +++ b/fs/jfs/jfs_filsys.h @@ -34,9 +34,9 @@ #define JFS_UNICODE 0x00000001 /* unicode name */ /* mount time flags for error handling */ -#define JFS_ERR_REMOUNT_RO 0x00000002 /* remount read-only */ -#define JFS_ERR_CONTINUE 0x00000004 /* continue */ -#define JFS_ERR_PANIC 0x00000008 /* panic */ +#define JFS_ERR_REMOUNT_RO 0x00000002 /* remount read-only */ +#define JFS_ERR_CONTINUE 0x00000004 /* continue */ +#define JFS_ERR_PANIC 0x00000008 /* panic */ /* Quota support */ #define JFS_USRQUOTA 0x00000010 @@ -83,7 +83,6 @@ /* case-insensitive name/directory support */ #define JFS_AIX 0x80000000 /* AIX support */ -/* POSIX name/directory support - Never implemented*/ /* * buffer cache configuration @@ -113,10 +112,10 @@ #define IDATASIZE 256 /* inode inline data size */ #define IXATTRSIZE 128 /* inode inline extended attribute size */ -#define XTPAGE_SIZE 4096 -#define log2_PAGESIZE 12 +#define XTPAGE_SIZE 4096 +#define log2_PAGESIZE 12 -#define IAG_SIZE 4096 +#define IAG_SIZE 4096 #define IAG_EXTENT_SIZE 4096 #define INOSPERIAG 4096 /* number of disk inodes per iag */ #define L2INOSPERIAG 12 /* l2 number of disk inodes per iag */ diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index c6530227cda..3870ba8b908 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -93,21 +93,21 @@ static int copy_from_dinode(struct dinode *, struct inode *); static void copy_to_dinode(struct dinode *, struct inode *); /* - * NAME: diMount() + * NAME: diMount() * - * FUNCTION: initialize the incore inode map control structures for + * FUNCTION: initialize the incore inode map control structures for * a fileset or aggregate init time. * - * the inode map's control structure (dinomap) is - * brought in from disk and placed in virtual memory. + * the inode map's control structure (dinomap) is + * brought in from disk and placed in virtual memory. * * PARAMETERS: - * ipimap - pointer to inode map inode for the aggregate or fileset. + * ipimap - pointer to inode map inode for the aggregate or fileset. * * RETURN VALUES: - * 0 - success - * -ENOMEM - insufficient free virtual memory. - * -EIO - i/o error. + * 0 - success + * -ENOMEM - insufficient free virtual memory. + * -EIO - i/o error. */ int diMount(struct inode *ipimap) { @@ -180,18 +180,18 @@ int diMount(struct inode *ipimap) /* - * NAME: diUnmount() + * NAME: diUnmount() * - * FUNCTION: write to disk the incore inode map control structures for + * FUNCTION: write to disk the incore inode map control structures for * a fileset or aggregate at unmount time. * * PARAMETERS: - * ipimap - pointer to inode map inode for the aggregate or fileset. + * ipimap - pointer to inode map inode for the aggregate or fileset. * * RETURN VALUES: - * 0 - success - * -ENOMEM - insufficient free virtual memory. - * -EIO - i/o error. + * 0 - success + * -ENOMEM - insufficient free virtual memory. + * -EIO - i/o error. */ int diUnmount(struct inode *ipimap, int mounterror) { @@ -274,9 +274,9 @@ int diSync(struct inode *ipimap) /* - * NAME: diRead() + * NAME: diRead() * - * FUNCTION: initialize an incore inode from disk. + * FUNCTION: initialize an incore inode from disk. * * on entry, the specifed incore inode should itself * specify the disk inode number corresponding to the @@ -285,7 +285,7 @@ int diSync(struct inode *ipimap) * this routine handles incore inode initialization for * both "special" and "regular" inodes. special inodes * are those required early in the mount process and - * require special handling since much of the file system + * require special handling since much of the file system * is not yet initialized. these "special" inodes are * identified by a NULL inode map inode pointer and are * actually initialized by a call to diReadSpecial(). @@ -298,12 +298,12 @@ int diSync(struct inode *ipimap) * incore inode. * * PARAMETERS: - * ip - pointer to incore inode to be initialized from disk. + * ip - pointer to incore inode to be initialized from disk. * * RETURN VALUES: - * 0 - success - * -EIO - i/o error. - * -ENOMEM - insufficient memory + * 0 - success + * -EIO - i/o error. + * -ENOMEM - insufficient memory * */ int diRead(struct inode *ip) @@ -410,26 +410,26 @@ int diRead(struct inode *ip) /* - * NAME: diReadSpecial() + * NAME: diReadSpecial() * - * FUNCTION: initialize a 'special' inode from disk. + * FUNCTION: initialize a 'special' inode from disk. * * this routines handles aggregate level inodes. The * inode cache cannot differentiate between the * aggregate inodes and the filesystem inodes, so we * handle these here. We don't actually use the aggregate - * inode map, since these inodes are at a fixed location + * inode map, since these inodes are at a fixed location * and in some cases the aggregate inode map isn't initialized * yet. * * PARAMETERS: - * sb - filesystem superblock + * sb - filesystem superblock * inum - aggregate inode number * secondary - 1 if secondary aggregate inode table * * RETURN VALUES: - * new inode - success - * NULL - i/o error. + * new inode - success + * NULL - i/o error. */ struct inode *diReadSpecial(struct super_block *sb, ino_t inum, int secondary) { @@ -502,12 +502,12 @@ struct inode *diReadSpecial(struct super_block *sb, ino_t inum, int secondary) } /* - * NAME: diWriteSpecial() + * NAME: diWriteSpecial() * - * FUNCTION: Write the special inode to disk + * FUNCTION: Write the special inode to disk * * PARAMETERS: - * ip - special inode + * ip - special inode * secondary - 1 if secondary aggregate inode table * * RETURN VALUES: none @@ -554,9 +554,9 @@ void diWriteSpecial(struct inode *ip, int secondary) } /* - * NAME: diFreeSpecial() + * NAME: diFreeSpecial() * - * FUNCTION: Free allocated space for special inode + * FUNCTION: Free allocated space for special inode */ void diFreeSpecial(struct inode *ip) { @@ -572,9 +572,9 @@ void diFreeSpecial(struct inode *ip) /* - * NAME: diWrite() + * NAME: diWrite() * - * FUNCTION: write the on-disk inode portion of the in-memory inode + * FUNCTION: write the on-disk inode portion of the in-memory inode * to its corresponding on-disk inode. * * on entry, the specifed incore inode should itself @@ -589,11 +589,11 @@ void diFreeSpecial(struct inode *ip) * * PARAMETERS: * tid - transacation id - * ip - pointer to incore inode to be written to the inode extent. + * ip - pointer to incore inode to be written to the inode extent. * * RETURN VALUES: - * 0 - success - * -EIO - i/o error. + * 0 - success + * -EIO - i/o error. */ int diWrite(tid_t tid, struct inode *ip) { @@ -730,7 +730,7 @@ int diWrite(tid_t tid, struct inode *ip) ilinelock = (struct linelock *) & tlck->lock; /* - * regular file: 16 byte (XAD slot) granularity + * regular file: 16 byte (XAD slot) granularity */ if (type & tlckXTREE) { xtpage_t *p, *xp; @@ -755,7 +755,7 @@ int diWrite(tid_t tid, struct inode *ip) xad->flag &= ~(XAD_NEW | XAD_EXTENDED); } /* - * directory: 32 byte (directory entry slot) granularity + * directory: 32 byte (directory entry slot) granularity */ else if (type & tlckDTREE) { dtpage_t *p, *xp; @@ -800,9 +800,8 @@ int diWrite(tid_t tid, struct inode *ip) } /* - * lock/copy inode base: 128 byte slot granularity + * lock/copy inode base: 128 byte slot granularity */ -// baseDinode: lv = & dilinelock->lv[dilinelock->index]; lv->offset = dioffset >> L2INODESLOTSIZE; copy_to_dinode(dp, ip); @@ -813,17 +812,6 @@ int diWrite(tid_t tid, struct inode *ip) lv->length = 1; dilinelock->index++; -#ifdef _JFS_FASTDASD - /* - * We aren't logging changes to the DASD used in directory inodes, - * but we need to write them to disk. If we don't unmount cleanly, - * mount will recalculate the DASD used. - */ - if (S_ISDIR(ip->i_mode) - && (ip->i_ipmnt->i_mntflag & JFS_DASD_ENABLED)) - memcpy(&dp->di_DASD, &ip->i_DASD, sizeof(struct dasd)); -#endif /* _JFS_FASTDASD */ - /* release the buffer holding the updated on-disk inode. * the buffer will be later written by commit processing. */ @@ -834,9 +822,9 @@ int diWrite(tid_t tid, struct inode *ip) /* - * NAME: diFree(ip) + * NAME: diFree(ip) * - * FUNCTION: free a specified inode from the inode working map + * FUNCTION: free a specified inode from the inode working map * for a fileset or aggregate. * * if the inode to be freed represents the first (only) @@ -865,11 +853,11 @@ int diWrite(tid_t tid, struct inode *ip) * any updates and are held until all updates are complete. * * PARAMETERS: - * ip - inode to be freed. + * ip - inode to be freed. * * RETURN VALUES: - * 0 - success - * -EIO - i/o error. + * 0 - success + * -EIO - i/o error. */ int diFree(struct inode *ip) { @@ -902,7 +890,8 @@ int diFree(struct inode *ip) * the map. */ if (iagno >= imap->im_nextiag) { - dump_mem("imap", imap, 32); + print_hex_dump(KERN_ERR, "imap: ", DUMP_PREFIX_ADDRESS, 16, 4, + imap, 32, 0); jfs_error(ip->i_sb, "diFree: inum = %d, iagno = %d, nextiag = %d", (uint) inum, iagno, imap->im_nextiag); @@ -964,8 +953,8 @@ int diFree(struct inode *ip) return -EIO; } /* - * inode extent still has some inodes or below low water mark: - * keep the inode extent; + * inode extent still has some inodes or below low water mark: + * keep the inode extent; */ if (bitmap || imap->im_agctl[agno].numfree < 96 || @@ -1047,12 +1036,12 @@ int diFree(struct inode *ip) /* - * inode extent has become free and above low water mark: - * free the inode extent; + * inode extent has become free and above low water mark: + * free the inode extent; */ /* - * prepare to update iag list(s) (careful update step 1) + * prepare to update iag list(s) (careful update step 1) */ amp = bmp = cmp = dmp = NULL; fwd = back = -1; @@ -1152,7 +1141,7 @@ int diFree(struct inode *ip) invalidate_pxd_metapages(ip, freepxd); /* - * update iag list(s) (careful update step 2) + * update iag list(s) (careful update step 2) */ /* add the iag to the ag extent free list if this is the * first free extent for the iag. @@ -1338,20 +1327,20 @@ diInitInode(struct inode *ip, int iagno, int ino, int extno, struct iag * iagp) /* - * NAME: diAlloc(pip,dir,ip) + * NAME: diAlloc(pip,dir,ip) * - * FUNCTION: allocate a disk inode from the inode working map + * FUNCTION: allocate a disk inode from the inode working map * for a fileset or aggregate. * * PARAMETERS: - * pip - pointer to incore inode for the parent inode. - * dir - 'true' if the new disk inode is for a directory. - * ip - pointer to a new inode + * pip - pointer to incore inode for the parent inode. + * dir - 'true' if the new disk inode is for a directory. + * ip - pointer to a new inode * * RETURN VALUES: - * 0 - success. - * -ENOSPC - insufficient disk resources. - * -EIO - i/o error. + * 0 - success. + * -ENOSPC - insufficient disk resources. + * -EIO - i/o error. */ int diAlloc(struct inode *pip, bool dir, struct inode *ip) { @@ -1433,7 +1422,7 @@ int diAlloc(struct inode *pip, bool dir, struct inode *ip) addext = (imap->im_agctl[agno].numfree < 32 && iagp->nfreeexts); /* - * try to allocate from the IAG + * try to allocate from the IAG */ /* check if the inode may be allocated from the iag * (i.e. the inode has free inodes or new extent can be added). @@ -1633,9 +1622,9 @@ int diAlloc(struct inode *pip, bool dir, struct inode *ip) /* - * NAME: diAllocAG(imap,agno,dir,ip) + * NAME: diAllocAG(imap,agno,dir,ip) * - * FUNCTION: allocate a disk inode from the allocation group. + * FUNCTION: allocate a disk inode from the allocation group. * * this routine first determines if a new extent of free * inodes should be added for the allocation group, with @@ -1649,17 +1638,17 @@ int diAlloc(struct inode *pip, bool dir, struct inode *ip) * PRE CONDITION: Already have the AG lock for this AG. * * PARAMETERS: - * imap - pointer to inode map control structure. - * agno - allocation group to allocate from. - * dir - 'true' if the new disk inode is for a directory. - * ip - pointer to the new inode to be filled in on successful return + * imap - pointer to inode map control structure. + * agno - allocation group to allocate from. + * dir - 'true' if the new disk inode is for a directory. + * ip - pointer to the new inode to be filled in on successful return * with the disk inode number allocated, its extent address * and the start of the ag. * * RETURN VALUES: - * 0 - success. - * -ENOSPC - insufficient disk resources. - * -EIO - i/o error. + * 0 - success. + * -ENOSPC - insufficient disk resources. + * -EIO - i/o error. */ static int diAllocAG(struct inomap * imap, int agno, bool dir, struct inode *ip) @@ -1709,9 +1698,9 @@ diAllocAG(struct inomap * imap, int agno, bool dir, struct inode *ip) /* - * NAME: diAllocAny(imap,agno,dir,iap) + * NAME: diAllocAny(imap,agno,dir,iap) * - * FUNCTION: allocate a disk inode from any other allocation group. + * FUNCTION: allocate a disk inode from any other allocation group. * * this routine is called when an allocation attempt within * the primary allocation group has failed. if attempts to @@ -1719,17 +1708,17 @@ diAllocAG(struct inomap * imap, int agno, bool dir, struct inode *ip) * specified primary group. * * PARAMETERS: - * imap - pointer to inode map control structure. - * agno - primary allocation group (to avoid). - * dir - 'true' if the new disk inode is for a directory. - * ip - pointer to a new inode to be filled in on successful return + * imap - pointer to inode map control structure. + * agno - primary allocation group (to avoid). + * dir - 'true' if the new disk inode is for a directory. + * ip - pointer to a new inode to be filled in on successful return * with the disk inode number allocated, its extent address * and the start of the ag. * * RETURN VALUES: - * 0 - success. - * -ENOSPC - insufficient disk resources. - * -EIO - i/o error. + * 0 - success. + * -ENOSPC - insufficient disk resources. + * -EIO - i/o error. */ static int diAllocAny(struct inomap * imap, int agno, bool dir, struct inode *ip) @@ -1772,9 +1761,9 @@ diAllocAny(struct inomap * imap, int agno, bool dir, struct inode *ip) /* - * NAME: diAllocIno(imap,agno,ip) + * NAME: diAllocIno(imap,agno,ip) * - * FUNCTION: allocate a disk inode from the allocation group's free + * FUNCTION: allocate a disk inode from the allocation group's free * inode list, returning an error if this free list is * empty (i.e. no iags on the list). * @@ -1785,16 +1774,16 @@ diAllocAny(struct inomap * imap, int agno, bool dir, struct inode *ip) * PRE CONDITION: Already have AG lock for this AG. * * PARAMETERS: - * imap - pointer to inode map control structure. - * agno - allocation group. - * ip - pointer to new inode to be filled in on successful return + * imap - pointer to inode map control structure. + * agno - allocation group. + * ip - pointer to new inode to be filled in on successful return * with the disk inode number allocated, its extent address * and the start of the ag. * * RETURN VALUES: - * 0 - success. - * -ENOSPC - insufficient disk resources. - * -EIO - i/o error. + * 0 - success. + * -ENOSPC - insufficient disk resources. + * -EIO - i/o error. */ static int diAllocIno(struct inomap * imap, int agno, struct inode *ip) { @@ -1890,7 +1879,7 @@ static int diAllocIno(struct inomap * imap, int agno, struct inode *ip) /* - * NAME: diAllocExt(imap,agno,ip) + * NAME: diAllocExt(imap,agno,ip) * * FUNCTION: add a new extent of free inodes to an iag, allocating * an inode from this extent to satisfy the current allocation @@ -1910,16 +1899,16 @@ static int diAllocIno(struct inomap * imap, int agno, struct inode *ip) * for the purpose of satisfying this request. * * PARAMETERS: - * imap - pointer to inode map control structure. - * agno - allocation group number. - * ip - pointer to new inode to be filled in on successful return + * imap - pointer to inode map control structure. + * agno - allocation group number. + * ip - pointer to new inode to be filled in on successful return * with the disk inode number allocated, its extent address * and the start of the ag. * * RETURN VALUES: - * 0 - success. - * -ENOSPC - insufficient disk resources. - * -EIO - i/o error. + * 0 - success. + * -ENOSPC - insufficient disk resources. + * -EIO - i/o error. */ static int diAllocExt(struct inomap * imap, int agno, struct inode *ip) { @@ -2010,7 +1999,7 @@ static int diAllocExt(struct inomap * imap, int agno, struct inode *ip) /* - * NAME: diAllocBit(imap,iagp,ino) + * NAME: diAllocBit(imap,iagp,ino) * * FUNCTION: allocate a backed inode from an iag. * @@ -2030,14 +2019,14 @@ static int diAllocExt(struct inomap * imap, int agno, struct inode *ip) * this AG. Must have read lock on imap inode. * * PARAMETERS: - * imap - pointer to inode map control structure. - * iagp - pointer to iag. - * ino - inode number to be allocated within the iag. + * imap - pointer to inode map control structure. + * iagp - pointer to iag. + * ino - inode number to be allocated within the iag. * * RETURN VALUES: - * 0 - success. - * -ENOSPC - insufficient disk resources. - * -EIO - i/o error. + * 0 - success. + * -ENOSPC - insufficient disk resources. + * -EIO - i/o error. */ static int diAllocBit(struct inomap * imap, struct iag * iagp, int ino) { @@ -2144,11 +2133,11 @@ static int diAllocBit(struct inomap * imap, struct iag * iagp, int ino) /* - * NAME: diNewExt(imap,iagp,extno) + * NAME: diNewExt(imap,iagp,extno) * - * FUNCTION: initialize a new extent of inodes for an iag, allocating - * the first inode of the extent for use for the current - * allocation request. + * FUNCTION: initialize a new extent of inodes for an iag, allocating + * the first inode of the extent for use for the current + * allocation request. * * disk resources are allocated for the new extent of inodes * and the inodes themselves are initialized to reflect their @@ -2177,14 +2166,14 @@ static int diAllocBit(struct inomap * imap, struct iag * iagp, int ino) * this AG. Must have read lock on imap inode. * * PARAMETERS: - * imap - pointer to inode map control structure. - * iagp - pointer to iag. - * extno - extent number. + * imap - pointer to inode map control structure. + * iagp - pointer to iag. + * extno - extent number. * * RETURN VALUES: - * 0 - success. - * -ENOSPC - insufficient disk resources. - * -EIO - i/o error. + * 0 - success. + * -ENOSPC - insufficient disk resources. + * -EIO - i/o error. */ static int diNewExt(struct inomap * imap, struct iag * iagp, int extno) { @@ -2430,7 +2419,7 @@ static int diNewExt(struct inomap * imap, struct iag * iagp, int extno) /* - * NAME: diNewIAG(imap,iagnop,agno) + * NAME: diNewIAG(imap,iagnop,agno) * * FUNCTION: allocate a new iag for an allocation group. * @@ -2443,16 +2432,16 @@ static int diNewExt(struct inomap * imap, struct iag * iagp, int extno) * and returned to satisfy the request. * * PARAMETERS: - * imap - pointer to inode map control structure. - * iagnop - pointer to an iag number set with the number of the + * imap - pointer to inode map control structure. + * iagnop - pointer to an iag number set with the number of the * newly allocated iag upon successful return. - * agno - allocation group number. + * agno - allocation group number. * bpp - Buffer pointer to be filled in with new IAG's buffer * * RETURN VALUES: - * 0 - success. - * -ENOSPC - insufficient disk resources. - * -EIO - i/o error. + * 0 - success. + * -ENOSPC - insufficient disk resources. + * -EIO - i/o error. * * serialization: * AG lock held on entry/exit; @@ -2461,7 +2450,7 @@ static int diNewExt(struct inomap * imap, struct iag * iagp, int extno) * * note: new iag transaction: * . synchronously write iag; - * . write log of xtree and inode of imap; + * . write log of xtree and inode of imap; * . commit; * . synchronous write of xtree (right to left, bottom to top); * . at start of logredo(): init in-memory imap with one additional iag page; @@ -2481,9 +2470,6 @@ diNewIAG(struct inomap * imap, int *iagnop, int agno, struct metapage ** mpp) s64 xaddr = 0; s64 blkno; tid_t tid; -#ifdef _STILL_TO_PORT - xad_t xad; -#endif /* _STILL_TO_PORT */ struct inode *iplist[1]; /* pick up pointers to the inode map and mount inodes */ @@ -2674,15 +2660,15 @@ diNewIAG(struct inomap * imap, int *iagnop, int agno, struct metapage ** mpp) } /* - * NAME: diIAGRead() + * NAME: diIAGRead() * - * FUNCTION: get the buffer for the specified iag within a fileset + * FUNCTION: get the buffer for the specified iag within a fileset * or aggregate inode map. * * PARAMETERS: - * imap - pointer to inode map control structure. - * iagno - iag number. - * bpp - point to buffer pointer to be filled in on successful + * imap - pointer to inode map control structure. + * iagno - iag number. + * bpp - point to buffer pointer to be filled in on successful * exit. * * SERIALIZATION: @@ -2691,8 +2677,8 @@ diNewIAG(struct inomap * imap, int *iagnop, int agno, struct metapage ** mpp) * the read lock is unnecessary.) * * RETURN VALUES: - * 0 - success. - * -EIO - i/o error. + * 0 - success. + * -EIO - i/o error. */ static int diIAGRead(struct inomap * imap, int iagno, struct metapage ** mpp) { @@ -2712,17 +2698,17 @@ static int diIAGRead(struct inomap * imap, int iagno, struct metapage ** mpp) } /* - * NAME: diFindFree() + * NAME: diFindFree() * - * FUNCTION: find the first free bit in a word starting at + * FUNCTION: find the first free bit in a word starting at * the specified bit position. * * PARAMETERS: - * word - word to be examined. - * start - starting bit position. + * word - word to be examined. + * start - starting bit position. * * RETURN VALUES: - * bit position of first free bit in the word or 32 if + * bit position of first free bit in the word or 32 if * no free bits were found. */ static int diFindFree(u32 word, int start) @@ -2897,7 +2883,7 @@ int diExtendFS(struct inode *ipimap, struct inode *ipbmap) atomic_read(&imap->im_numfree)); /* - * reconstruct imap + * reconstruct imap * * coalesce contiguous k (newAGSize/oldAGSize) AGs; * i.e., (AGi, ..., AGj) where i = k*n and j = k*(n+1) - 1 to AGn; @@ -2913,7 +2899,7 @@ int diExtendFS(struct inode *ipimap, struct inode *ipbmap) } /* - * process each iag page of the map. + * process each iag page of the map. * * rebuild AG Free Inode List, AG Free Inode Extent List; */ @@ -2932,7 +2918,7 @@ int diExtendFS(struct inode *ipimap, struct inode *ipbmap) /* leave free iag in the free iag list */ if (iagp->nfreeexts == cpu_to_le32(EXTSPERIAG)) { - release_metapage(bp); + release_metapage(bp); continue; } @@ -3063,13 +3049,13 @@ static void duplicateIXtree(struct super_block *sb, s64 blkno, } /* - * NAME: copy_from_dinode() + * NAME: copy_from_dinode() * - * FUNCTION: Copies inode info from disk inode to in-memory inode + * FUNCTION: Copies inode info from disk inode to in-memory inode * * RETURN VALUES: - * 0 - success - * -ENOMEM - insufficient memory + * 0 - success + * -ENOMEM - insufficient memory */ static int copy_from_dinode(struct dinode * dip, struct inode *ip) { @@ -3151,9 +3137,9 @@ static int copy_from_dinode(struct dinode * dip, struct inode *ip) } /* - * NAME: copy_to_dinode() + * NAME: copy_to_dinode() * - * FUNCTION: Copies inode info from in-memory inode to disk inode + * FUNCTION: Copies inode info from in-memory inode to disk inode */ static void copy_to_dinode(struct dinode * dip, struct inode *ip) { diff --git a/fs/jfs/jfs_imap.h b/fs/jfs/jfs_imap.h index 4f9c346ed49..610a0e9d894 100644 --- a/fs/jfs/jfs_imap.h +++ b/fs/jfs/jfs_imap.h @@ -24,17 +24,17 @@ * jfs_imap.h: disk inode manager */ -#define EXTSPERIAG 128 /* number of disk inode extent per iag */ -#define IMAPBLKNO 0 /* lblkno of dinomap within inode map */ -#define SMAPSZ 4 /* number of words per summary map */ +#define EXTSPERIAG 128 /* number of disk inode extent per iag */ +#define IMAPBLKNO 0 /* lblkno of dinomap within inode map */ +#define SMAPSZ 4 /* number of words per summary map */ #define EXTSPERSUM 32 /* number of extents per summary map entry */ #define L2EXTSPERSUM 5 /* l2 number of extents per summary map */ #define PGSPERIEXT 4 /* number of 4K pages per dinode extent */ -#define MAXIAGS ((1<<20)-1) /* maximum number of iags */ -#define MAXAG 128 /* maximum number of allocation groups */ +#define MAXIAGS ((1<<20)-1) /* maximum number of iags */ +#define MAXAG 128 /* maximum number of allocation groups */ -#define AMAPSIZE 512 /* bytes in the IAG allocation maps */ -#define SMAPSIZE 16 /* bytes in the IAG summary maps */ +#define AMAPSIZE 512 /* bytes in the IAG allocation maps */ +#define SMAPSIZE 16 /* bytes in the IAG summary maps */ /* convert inode number to iag number */ #define INOTOIAG(ino) ((ino) >> L2INOSPERIAG) @@ -60,31 +60,31 @@ * inode allocation group page (per 4096 inodes of an AG) */ struct iag { - __le64 agstart; /* 8: starting block of ag */ - __le32 iagnum; /* 4: inode allocation group number */ - __le32 inofreefwd; /* 4: ag inode free list forward */ - __le32 inofreeback; /* 4: ag inode free list back */ - __le32 extfreefwd; /* 4: ag inode extent free list forward */ - __le32 extfreeback; /* 4: ag inode extent free list back */ - __le32 iagfree; /* 4: iag free list */ + __le64 agstart; /* 8: starting block of ag */ + __le32 iagnum; /* 4: inode allocation group number */ + __le32 inofreefwd; /* 4: ag inode free list forward */ + __le32 inofreeback; /* 4: ag inode free list back */ + __le32 extfreefwd; /* 4: ag inode extent free list forward */ + __le32 extfreeback; /* 4: ag inode extent free list back */ + __le32 iagfree; /* 4: iag free list */ /* summary map: 1 bit per inode extent */ __le32 inosmap[SMAPSZ]; /* 16: sum map of mapwords w/ free inodes; - * note: this indicates free and backed - * inodes, if the extent is not backed the - * value will be 1. if the extent is - * backed but all inodes are being used the - * value will be 1. if the extent is - * backed but at least one of the inodes is - * free the value will be 0. + * note: this indicates free and backed + * inodes, if the extent is not backed the + * value will be 1. if the extent is + * backed but all inodes are being used the + * value will be 1. if the extent is + * backed but at least one of the inodes is + * free the value will be 0. */ __le32 extsmap[SMAPSZ]; /* 16: sum map of mapwords w/ free extents */ - __le32 nfreeinos; /* 4: number of free inodes */ - __le32 nfreeexts; /* 4: number of free extents */ + __le32 nfreeinos; /* 4: number of free inodes */ + __le32 nfreeexts; /* 4: number of free extents */ /* (72) */ u8 pad[1976]; /* 1976: pad to 2048 bytes */ /* allocation bit map: 1 bit per inode (0 - free, 1 - allocated) */ - __le32 wmap[EXTSPERIAG]; /* 512: working allocation map */ + __le32 wmap[EXTSPERIAG]; /* 512: working allocation map */ __le32 pmap[EXTSPERIAG]; /* 512: persistent allocation map */ pxd_t inoext[EXTSPERIAG]; /* 1024: inode extent addresses */ }; /* (4096) */ @@ -93,44 +93,44 @@ struct iag { * per AG control information (in inode map control page) */ struct iagctl_disk { - __le32 inofree; /* 4: free inode list anchor */ - __le32 extfree; /* 4: free extent list anchor */ - __le32 numinos; /* 4: number of backed inodes */ - __le32 numfree; /* 4: number of free inodes */ + __le32 inofree; /* 4: free inode list anchor */ + __le32 extfree; /* 4: free extent list anchor */ + __le32 numinos; /* 4: number of backed inodes */ + __le32 numfree; /* 4: number of free inodes */ }; /* (16) */ struct iagctl { - int inofree; /* free inode list anchor */ - int extfree; /* free extent list anchor */ - int numinos; /* number of backed inodes */ - int numfree; /* number of free inodes */ + int inofree; /* free inode list anchor */ + int extfree; /* free extent list anchor */ + int numinos; /* number of backed inodes */ + int numfree; /* number of free inodes */ }; /* * per fileset/aggregate inode map control page */ struct dinomap_disk { - __le32 in_freeiag; /* 4: free iag list anchor */ - __le32 in_nextiag; /* 4: next free iag number */ - __le32 in_numinos; /* 4: num of backed inodes */ + __le32 in_freeiag; /* 4: free iag list anchor */ + __le32 in_nextiag; /* 4: next free iag number */ + __le32 in_numinos; /* 4: num of backed inodes */ __le32 in_numfree; /* 4: num of free backed inodes */ __le32 in_nbperiext; /* 4: num of blocks per inode extent */ - __le32 in_l2nbperiext; /* 4: l2 of in_nbperiext */ - __le32 in_diskblock; /* 4: for standalone test driver */ - __le32 in_maxag; /* 4: for standalone test driver */ - u8 pad[2016]; /* 2016: pad to 2048 */ + __le32 in_l2nbperiext; /* 4: l2 of in_nbperiext */ + __le32 in_diskblock; /* 4: for standalone test driver */ + __le32 in_maxag; /* 4: for standalone test driver */ + u8 pad[2016]; /* 2016: pad to 2048 */ struct iagctl_disk in_agctl[MAXAG]; /* 2048: AG control information */ }; /* (4096) */ struct dinomap { - int in_freeiag; /* free iag list anchor */ - int in_nextiag; /* next free iag number */ - int in_numinos; /* num of backed inodes */ - int in_numfree; /* num of free backed inodes */ + int in_freeiag; /* free iag list anchor */ + int in_nextiag; /* next free iag number */ + int in_numinos; /* num of backed inodes */ + int in_numfree; /* num of free backed inodes */ int in_nbperiext; /* num of blocks per inode extent */ - int in_l2nbperiext; /* l2 of in_nbperiext */ - int in_diskblock; /* for standalone test driver */ - int in_maxag; /* for standalone test driver */ + int in_l2nbperiext; /* l2 of in_nbperiext */ + int in_diskblock; /* for standalone test driver */ + int in_maxag; /* for standalone test driver */ struct iagctl in_agctl[MAXAG]; /* AG control information */ }; @@ -139,9 +139,9 @@ struct dinomap { */ struct inomap { struct dinomap im_imap; /* 4096: inode allocation control */ - struct inode *im_ipimap; /* 4: ptr to inode for imap */ - struct mutex im_freelock; /* 4: iag free list lock */ - struct mutex im_aglock[MAXAG]; /* 512: per AG locks */ + struct inode *im_ipimap; /* 4: ptr to inode for imap */ + struct mutex im_freelock; /* 4: iag free list lock */ + struct mutex im_aglock[MAXAG]; /* 512: per AG locks */ u32 *im_DBGdimap; atomic_t im_numinos; /* num of backed inodes */ atomic_t im_numfree; /* num of free backed inodes */ diff --git a/fs/jfs/jfs_incore.h b/fs/jfs/jfs_incore.h index 8f453eff3c8..cb8f30985ad 100644 --- a/fs/jfs/jfs_incore.h +++ b/fs/jfs/jfs_incore.h @@ -40,7 +40,7 @@ struct jfs_inode_info { uint mode2; /* jfs-specific mode */ uint saved_uid; /* saved for uid mount option */ uint saved_gid; /* saved for gid mount option */ - pxd_t ixpxd; /* inode extent descriptor */ + pxd_t ixpxd; /* inode extent descriptor */ dxd_t acl; /* dxd describing acl */ dxd_t ea; /* dxd describing ea */ time_t otime; /* time created */ @@ -190,7 +190,7 @@ struct jfs_sb_info { uint gengen; /* inode generation generator*/ uint inostamp; /* shows inode belongs to fileset*/ - /* Formerly in ipbmap */ + /* Formerly in ipbmap */ struct bmap *bmap; /* incore bmap descriptor */ struct nls_table *nls_tab; /* current codepage */ struct inode *direct_inode; /* metadata inode */ diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c index 44a2f33cb98..de3e4a506db 100644 --- a/fs/jfs/jfs_logmgr.c +++ b/fs/jfs/jfs_logmgr.c @@ -244,7 +244,7 @@ int lmLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, goto writeRecord; /* - * initialize/update page/transaction recovery lsn + * initialize/update page/transaction recovery lsn */ lsn = log->lsn; @@ -263,7 +263,7 @@ int lmLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, } /* - * initialize/update lsn of tblock of the page + * initialize/update lsn of tblock of the page * * transaction inherits oldest lsn of pages associated * with allocation/deallocation of resources (their @@ -307,7 +307,7 @@ int lmLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, LOGSYNC_UNLOCK(log, flags); /* - * write the log record + * write the log record */ writeRecord: lsn = lmWriteRecord(log, tblk, lrd, tlck); @@ -372,7 +372,7 @@ lmWriteRecord(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, goto moveLrd; /* - * move log record data + * move log record data */ /* retrieve source meta-data page to log */ if (tlck->flag & tlckPAGELOCK) { @@ -465,7 +465,7 @@ lmWriteRecord(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, } /* - * move log record descriptor + * move log record descriptor */ moveLrd: lrd->length = cpu_to_le16(len); @@ -574,7 +574,7 @@ static int lmNextPage(struct jfs_log * log) LOGGC_LOCK(log); /* - * write or queue the full page at the tail of write queue + * write or queue the full page at the tail of write queue */ /* get the tail tblk on commit queue */ if (list_empty(&log->cqueue)) @@ -625,7 +625,7 @@ static int lmNextPage(struct jfs_log * log) LOGGC_UNLOCK(log); /* - * allocate/initialize next page + * allocate/initialize next page */ /* if log wraps, the first data page of log is 2 * (0 never used, 1 is superblock). @@ -953,7 +953,7 @@ static int lmLogSync(struct jfs_log * log, int hard_sync) } /* - * forward syncpt + * forward syncpt */ /* if last sync is same as last syncpt, * invoke sync point forward processing to update sync. @@ -989,7 +989,7 @@ static int lmLogSync(struct jfs_log * log, int hard_sync) lsn = log->lsn; /* - * setup next syncpt trigger (SWAG) + * setup next syncpt trigger (SWAG) */ logsize = log->logsize; @@ -1000,11 +1000,11 @@ static int lmLogSync(struct jfs_log * log, int hard_sync) if (more < 2 * LOGPSIZE) { jfs_warn("\n ... Log Wrap ... Log Wrap ... Log Wrap ...\n"); /* - * log wrapping + * log wrapping * * option 1 - panic ? No.! * option 2 - shutdown file systems - * associated with log ? + * associated with log ? * option 3 - extend log ? */ /* @@ -1062,7 +1062,7 @@ void jfs_syncpt(struct jfs_log *log, int hard_sync) /* * NAME: lmLogOpen() * - * FUNCTION: open the log on first open; + * FUNCTION: open the log on first open; * insert filesystem in the active list of the log. * * PARAMETER: ipmnt - file system mount inode @@ -1113,7 +1113,7 @@ int lmLogOpen(struct super_block *sb) init_waitqueue_head(&log->syncwait); /* - * external log as separate logical volume + * external log as separate logical volume * * file systems to log may have n-to-1 relationship; */ @@ -1155,7 +1155,7 @@ journal_found: return 0; /* - * unwind on error + * unwind on error */ shutdown: /* unwind lbmLogInit() */ list_del(&log->journal_list); @@ -1427,7 +1427,7 @@ int lmLogInit(struct jfs_log * log) return 0; /* - * unwind on error + * unwind on error */ errout30: /* release log page */ log->wqueue = NULL; @@ -1480,7 +1480,7 @@ int lmLogClose(struct super_block *sb) if (test_bit(log_INLINELOG, &log->flag)) { /* - * in-line log in host file system + * in-line log in host file system */ rc = lmLogShutdown(log); kfree(log); @@ -1504,7 +1504,7 @@ int lmLogClose(struct super_block *sb) goto out; /* - * external log as separate logical volume + * external log as separate logical volume */ list_del(&log->journal_list); bdev = log->bdev; @@ -1622,20 +1622,26 @@ void jfs_flush_journal(struct jfs_log *log, int wait) if (!list_empty(&log->synclist)) { struct logsyncblk *lp; + printk(KERN_ERR "jfs_flush_journal: synclist not empty\n"); list_for_each_entry(lp, &log->synclist, synclist) { if (lp->xflag & COMMIT_PAGE) { struct metapage *mp = (struct metapage *)lp; - dump_mem("orphan metapage", lp, - sizeof(struct metapage)); - dump_mem("page", mp->page, sizeof(struct page)); - } - else - dump_mem("orphan tblock", lp, - sizeof(struct tblock)); + print_hex_dump(KERN_ERR, "metapage: ", + DUMP_PREFIX_ADDRESS, 16, 4, + mp, sizeof(struct metapage), 0); + print_hex_dump(KERN_ERR, "page: ", + DUMP_PREFIX_ADDRESS, 16, + sizeof(long), mp->page, + sizeof(struct page), 0); + } else + print_hex_dump(KERN_ERR, "tblock:", + DUMP_PREFIX_ADDRESS, 16, 4, + lp, sizeof(struct tblock), 0); } } +#else + WARN_ON(!list_empty(&log->synclist)); #endif - //assert(list_empty(&log->synclist)); clear_bit(log_FLUSH, &log->flag); } @@ -1723,7 +1729,7 @@ int lmLogShutdown(struct jfs_log * log) * * PARAMETE: log - pointer to logs inode. * fsdev - kdev_t of filesystem. - * serial - pointer to returned log serial number + * serial - pointer to returned log serial number * activate - insert/remove device from active list. * * RETURN: 0 - success @@ -1963,7 +1969,7 @@ static void lbmfree(struct lbuf * bp) * FUNCTION: add a log buffer to the log redrive list * * PARAMETER: - * bp - log buffer + * bp - log buffer * * NOTES: * Takes log_redrive_lock. @@ -2054,7 +2060,7 @@ static void lbmWrite(struct jfs_log * log, struct lbuf * bp, int flag, bp->l_flag = flag; /* - * insert bp at tail of write queue associated with log + * insert bp at tail of write queue associated with log * * (request is either for bp already/currently at head of queue * or new bp to be inserted at tail) @@ -2117,7 +2123,7 @@ static void lbmDirectWrite(struct jfs_log * log, struct lbuf * bp, int flag) log->base + (bp->l_pn << (L2LOGPSIZE - log->l2bsize)); /* - * initiate pageout of the page + * initiate pageout of the page */ lbmStartIO(bp); } @@ -2128,7 +2134,7 @@ static void lbmDirectWrite(struct jfs_log * log, struct lbuf * bp, int flag) * * FUNCTION: Interface to DD strategy routine * - * RETURN: none + * RETURN: none * * serialization: LCACHE_LOCK() is NOT held during log i/o; */ @@ -2222,7 +2228,7 @@ static int lbmIODone(struct bio *bio, unsigned int bytes_done, int error) bio_put(bio); /* - * pagein completion + * pagein completion */ if (bp->l_flag & lbmREAD) { bp->l_flag &= ~lbmREAD; @@ -2236,7 +2242,7 @@ static int lbmIODone(struct bio *bio, unsigned int bytes_done, int error) } /* - * pageout completion + * pageout completion * * the bp at the head of write queue has completed pageout. * @@ -2302,7 +2308,7 @@ static int lbmIODone(struct bio *bio, unsigned int bytes_done, int error) } /* - * synchronous pageout: + * synchronous pageout: * * buffer has not necessarily been removed from write queue * (e.g., synchronous write of partial-page with COMMIT): @@ -2316,7 +2322,7 @@ static int lbmIODone(struct bio *bio, unsigned int bytes_done, int error) } /* - * Group Commit pageout: + * Group Commit pageout: */ else if (bp->l_flag & lbmGC) { LCACHE_UNLOCK(flags); @@ -2324,7 +2330,7 @@ static int lbmIODone(struct bio *bio, unsigned int bytes_done, int error) } /* - * asynchronous pageout: + * asynchronous pageout: * * buffer must have been removed from write queue: * insert buffer at head of freelist where it can be recycled @@ -2375,7 +2381,7 @@ int jfsIOWait(void *arg) * FUNCTION: format file system log * * PARAMETERS: - * log - volume log + * log - volume log * logAddress - start address of log space in FS block * logSize - length of log space in FS block; * @@ -2407,16 +2413,16 @@ int lmLogFormat(struct jfs_log *log, s64 logAddress, int logSize) npages = logSize >> sbi->l2nbperpage; /* - * log space: + * log space: * * page 0 - reserved; * page 1 - log superblock; * page 2 - log data page: A SYNC log record is written - * into this page at logform time; + * into this page at logform time; * pages 3-N - log data page: set to empty log data pages; */ /* - * init log superblock: log page 1 + * init log superblock: log page 1 */ logsuper = (struct logsuper *) bp->l_ldata; @@ -2436,7 +2442,7 @@ int lmLogFormat(struct jfs_log *log, s64 logAddress, int logSize) goto exit; /* - * init pages 2 to npages-1 as log data pages: + * init pages 2 to npages-1 as log data pages: * * log page sequence number (lpsn) initialization: * @@ -2479,7 +2485,7 @@ int lmLogFormat(struct jfs_log *log, s64 logAddress, int logSize) goto exit; /* - * initialize succeeding log pages: lpsn = 0, 1, ..., (N-2) + * initialize succeeding log pages: lpsn = 0, 1, ..., (N-2) */ for (lspn = 0; lspn < npages - 3; lspn++) { lp->h.page = lp->t.page = cpu_to_le32(lspn); @@ -2495,7 +2501,7 @@ int lmLogFormat(struct jfs_log *log, s64 logAddress, int logSize) rc = 0; exit: /* - * finalize log + * finalize log */ /* release the buffer */ lbmFree(bp); diff --git a/fs/jfs/jfs_logmgr.h b/fs/jfs/jfs_logmgr.h index a53fb17ea21..1f85ef0ec04 100644 --- a/fs/jfs/jfs_logmgr.h +++ b/fs/jfs/jfs_logmgr.h @@ -144,7 +144,7 @@ struct logpage { * * (this comment should be rewritten !) * jfs uses only "after" log records (only a single writer is allowed - * in a page, pages are written to temporary paging space if + * in a page, pages are written to temporary paging space if * if they must be written to disk before commit, and i/o is * scheduled for modified pages to their home location after * the log records containing the after values and the commit @@ -153,7 +153,7 @@ struct logpage { * * a log record consists of a data area of variable length followed by * a descriptor of fixed size LOGRDSIZE bytes. - * the data area is rounded up to an integral number of 4-bytes and + * the data area is rounded up to an integral number of 4-bytes and * must be no longer than LOGPSIZE. * the descriptor is of size of multiple of 4-bytes and aligned on a * 4-byte boundary. @@ -215,13 +215,13 @@ struct lrd { union { /* - * COMMIT: commit + * COMMIT: commit * * transaction commit: no type-dependent information; */ /* - * REDOPAGE: after-image + * REDOPAGE: after-image * * apply after-image; * @@ -236,7 +236,7 @@ struct lrd { } redopage; /* (20) */ /* - * NOREDOPAGE: the page is freed + * NOREDOPAGE: the page is freed * * do not apply after-image records which precede this record * in the log with the same page block number to this page. @@ -252,7 +252,7 @@ struct lrd { } noredopage; /* (20) */ /* - * UPDATEMAP: update block allocation map + * UPDATEMAP: update block allocation map * * either in-line PXD, * or out-of-line XADLIST; @@ -268,7 +268,7 @@ struct lrd { } updatemap; /* (20) */ /* - * NOREDOINOEXT: the inode extent is freed + * NOREDOINOEXT: the inode extent is freed * * do not apply after-image records which precede this * record in the log with the any of the 4 page block @@ -286,7 +286,7 @@ struct lrd { } noredoinoext; /* (20) */ /* - * SYNCPT: log sync point + * SYNCPT: log sync point * * replay log upto syncpt address specified; */ @@ -295,13 +295,13 @@ struct lrd { } syncpt; /* - * MOUNT: file system mount + * MOUNT: file system mount * * file system mount: no type-dependent information; */ /* - * ? FREEXTENT: free specified extent(s) + * ? FREEXTENT: free specified extent(s) * * free specified extent(s) from block allocation map * N.B.: nextents should be length of data/sizeof(xad_t) @@ -314,7 +314,7 @@ struct lrd { } freextent; /* - * ? NOREDOFILE: this file is freed + * ? NOREDOFILE: this file is freed * * do not apply records which precede this record in the log * with the same inode number. @@ -330,7 +330,7 @@ struct lrd { } noredofile; /* - * ? NEWPAGE: + * ? NEWPAGE: * * metadata type dependent */ @@ -342,7 +342,7 @@ struct lrd { } newpage; /* - * ? DUMMY: filler + * ? DUMMY: filler * * no type-dependent information */ diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c index 43d4f69afbe..77c7f1129dd 100644 --- a/fs/jfs/jfs_metapage.c +++ b/fs/jfs/jfs_metapage.c @@ -472,7 +472,8 @@ add_failed: printk(KERN_ERR "JFS: bio_add_page failed unexpectedly\n"); goto skip; dump_bio: - dump_mem("bio", bio, sizeof(*bio)); + print_hex_dump(KERN_ERR, "JFS: dump of bio: ", DUMP_PREFIX_ADDRESS, 16, + 4, bio, sizeof(*bio), 0); skip: bio_put(bio); unlock_page(page); diff --git a/fs/jfs/jfs_mount.c b/fs/jfs/jfs_mount.c index 4dd47983489..644429acb8c 100644 --- a/fs/jfs/jfs_mount.c +++ b/fs/jfs/jfs_mount.c @@ -80,7 +80,7 @@ static int logMOUNT(struct super_block *sb); */ int jfs_mount(struct super_block *sb) { - int rc = 0; /* Return code */ + int rc = 0; /* Return code */ struct jfs_sb_info *sbi = JFS_SBI(sb); struct inode *ipaimap = NULL; struct inode *ipaimap2 = NULL; @@ -169,7 +169,7 @@ int jfs_mount(struct super_block *sb) sbi->ipaimap2 = NULL; /* - * mount (the only/single) fileset + * mount (the only/single) fileset */ /* * open fileset inode allocation map (aka fileset inode) @@ -195,7 +195,7 @@ int jfs_mount(struct super_block *sb) goto out; /* - * unwind on error + * unwind on error */ errout41: /* close fileset inode allocation map inode */ diFreeSpecial(ipimap); diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c index 25430d0b0d5..7aa1f7004ea 100644 --- a/fs/jfs/jfs_txnmgr.c +++ b/fs/jfs/jfs_txnmgr.c @@ -18,7 +18,7 @@ */ /* - * jfs_txnmgr.c: transaction manager + * jfs_txnmgr.c: transaction manager * * notes: * transaction starts with txBegin() and ends with txCommit() @@ -60,7 +60,7 @@ #include "jfs_debug.h" /* - * transaction management structures + * transaction management structures */ static struct { int freetid; /* index of a free tid structure */ @@ -103,19 +103,19 @@ module_param(nTxLock, int, 0); MODULE_PARM_DESC(nTxLock, "Number of transaction locks (max:65536)"); -struct tblock *TxBlock; /* transaction block table */ -static int TxLockLWM; /* Low water mark for number of txLocks used */ -static int TxLockHWM; /* High water mark for number of txLocks used */ -static int TxLockVHWM; /* Very High water mark */ -struct tlock *TxLock; /* transaction lock table */ +struct tblock *TxBlock; /* transaction block table */ +static int TxLockLWM; /* Low water mark for number of txLocks used */ +static int TxLockHWM; /* High water mark for number of txLocks used */ +static int TxLockVHWM; /* Very High water mark */ +struct tlock *TxLock; /* transaction lock table */ /* - * transaction management lock + * transaction management lock */ static DEFINE_SPINLOCK(jfsTxnLock); -#define TXN_LOCK() spin_lock(&jfsTxnLock) -#define TXN_UNLOCK() spin_unlock(&jfsTxnLock) +#define TXN_LOCK() spin_lock(&jfsTxnLock) +#define TXN_UNLOCK() spin_unlock(&jfsTxnLock) #define LAZY_LOCK_INIT() spin_lock_init(&TxAnchor.LazyLock); #define LAZY_LOCK(flags) spin_lock_irqsave(&TxAnchor.LazyLock, flags) @@ -148,7 +148,7 @@ static inline void TXN_SLEEP_DROP_LOCK(wait_queue_head_t * event) #define TXN_WAKEUP(event) wake_up_all(event) /* - * statistics + * statistics */ static struct { tid_t maxtid; /* 4: biggest tid ever used */ @@ -181,8 +181,8 @@ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, static void LogSyncRelease(struct metapage * mp); /* - * transaction block/lock management - * --------------------------------- + * transaction block/lock management + * --------------------------------- */ /* @@ -227,9 +227,9 @@ static void txLockFree(lid_t lid) } /* - * NAME: txInit() + * NAME: txInit() * - * FUNCTION: initialize transaction management structures + * FUNCTION: initialize transaction management structures * * RETURN: * @@ -333,9 +333,9 @@ int txInit(void) } /* - * NAME: txExit() + * NAME: txExit() * - * FUNCTION: clean up when module is unloaded + * FUNCTION: clean up when module is unloaded */ void txExit(void) { @@ -346,12 +346,12 @@ void txExit(void) } /* - * NAME: txBegin() + * NAME: txBegin() * - * FUNCTION: start a transaction. + * FUNCTION: start a transaction. * - * PARAMETER: sb - superblock - * flag - force for nested tx; + * PARAMETER: sb - superblock + * flag - force for nested tx; * * RETURN: tid - transaction id * @@ -447,13 +447,13 @@ tid_t txBegin(struct super_block *sb, int flag) } /* - * NAME: txBeginAnon() + * NAME: txBeginAnon() * - * FUNCTION: start an anonymous transaction. + * FUNCTION: start an anonymous transaction. * Blocks if logsync or available tlocks are low to prevent * anonymous tlocks from depleting supply. * - * PARAMETER: sb - superblock + * PARAMETER: sb - superblock * * RETURN: none */ @@ -489,11 +489,11 @@ void txBeginAnon(struct super_block *sb) } /* - * txEnd() + * txEnd() * * function: free specified transaction block. * - * logsync barrier processing: + * logsync barrier processing: * * serialization: */ @@ -577,13 +577,13 @@ wakeup: } /* - * txLock() + * txLock() * * function: acquire a transaction lock on the specified <mp> * * parameter: * - * return: transaction lock id + * return: transaction lock id * * serialization: */ @@ -829,12 +829,16 @@ struct tlock *txLock(tid_t tid, struct inode *ip, struct metapage * mp, /* Only locks on ipimap or ipaimap should reach here */ /* assert(jfs_ip->fileset == AGGREGATE_I); */ if (jfs_ip->fileset != AGGREGATE_I) { - jfs_err("txLock: trying to lock locked page!"); - dump_mem("ip", ip, sizeof(struct inode)); - dump_mem("mp", mp, sizeof(struct metapage)); - dump_mem("Locker's tblk", tid_to_tblock(tid), - sizeof(struct tblock)); - dump_mem("Tlock", tlck, sizeof(struct tlock)); + printk(KERN_ERR "txLock: trying to lock locked page!"); + print_hex_dump(KERN_ERR, "ip: ", DUMP_PREFIX_ADDRESS, 16, 4, + ip, sizeof(*ip), 0); + print_hex_dump(KERN_ERR, "mp: ", DUMP_PREFIX_ADDRESS, 16, 4, + mp, sizeof(*mp), 0); + print_hex_dump(KERN_ERR, "Locker's tblock: ", + DUMP_PREFIX_ADDRESS, 16, 4, tid_to_tblock(tid), + sizeof(struct tblock), 0); + print_hex_dump(KERN_ERR, "Tlock: ", DUMP_PREFIX_ADDRESS, 16, 4, + tlck, sizeof(*tlck), 0); BUG(); } INCREMENT(stattx.waitlock); /* statistics */ @@ -857,17 +861,17 @@ struct tlock *txLock(tid_t tid, struct inode *ip, struct metapage * mp, } /* - * NAME: txRelease() + * NAME: txRelease() * - * FUNCTION: Release buffers associated with transaction locks, but don't + * FUNCTION: Release buffers associated with transaction locks, but don't * mark homeok yet. The allows other transactions to modify * buffers, but won't let them go to disk until commit record * actually gets written. * * PARAMETER: - * tblk - + * tblk - * - * RETURN: Errors from subroutines. + * RETURN: Errors from subroutines. */ static void txRelease(struct tblock * tblk) { @@ -896,10 +900,10 @@ static void txRelease(struct tblock * tblk) } /* - * NAME: txUnlock() + * NAME: txUnlock() * - * FUNCTION: Initiates pageout of pages modified by tid in journalled - * objects and frees their lockwords. + * FUNCTION: Initiates pageout of pages modified by tid in journalled + * objects and frees their lockwords. */ static void txUnlock(struct tblock * tblk) { @@ -983,10 +987,10 @@ static void txUnlock(struct tblock * tblk) } /* - * txMaplock() + * txMaplock() * * function: allocate a transaction lock for freed page/entry; - * for freed page, maplock is used as xtlock/dtlock type; + * for freed page, maplock is used as xtlock/dtlock type; */ struct tlock *txMaplock(tid_t tid, struct inode *ip, int type) { @@ -1057,7 +1061,7 @@ struct tlock *txMaplock(tid_t tid, struct inode *ip, int type) } /* - * txLinelock() + * txLinelock() * * function: allocate a transaction lock for log vector list */ @@ -1092,39 +1096,39 @@ struct linelock *txLinelock(struct linelock * tlock) } /* - * transaction commit management - * ----------------------------- + * transaction commit management + * ----------------------------- */ /* - * NAME: txCommit() - * - * FUNCTION: commit the changes to the objects specified in - * clist. For journalled segments only the - * changes of the caller are committed, ie by tid. - * for non-journalled segments the data are flushed to - * disk and then the change to the disk inode and indirect - * blocks committed (so blocks newly allocated to the - * segment will be made a part of the segment atomically). - * - * all of the segments specified in clist must be in - * one file system. no more than 6 segments are needed - * to handle all unix svcs. - * - * if the i_nlink field (i.e. disk inode link count) - * is zero, and the type of inode is a regular file or - * directory, or symbolic link , the inode is truncated - * to zero length. the truncation is committed but the - * VM resources are unaffected until it is closed (see - * iput and iclose). + * NAME: txCommit() + * + * FUNCTION: commit the changes to the objects specified in + * clist. For journalled segments only the + * changes of the caller are committed, ie by tid. + * for non-journalled segments the data are flushed to + * disk and then the change to the disk inode and indirect + * blocks committed (so blocks newly allocated to the + * segment will be made a part of the segment atomically). + * + * all of the segments specified in clist must be in + * one file system. no more than 6 segments are needed + * to handle all unix svcs. + * + * if the i_nlink field (i.e. disk inode link count) + * is zero, and the type of inode is a regular file or + * directory, or symbolic link , the inode is truncated + * to zero length. the truncation is committed but the + * VM resources are unaffected until it is closed (see + * iput and iclose). * * PARAMETER: * * RETURN: * * serialization: - * on entry the inode lock on each segment is assumed - * to be held. + * on entry the inode lock on each segment is assumed + * to be held. * * i/o error: */ @@ -1175,7 +1179,7 @@ int txCommit(tid_t tid, /* transaction identifier */ if ((flag & (COMMIT_FORCE | COMMIT_SYNC)) == 0) tblk->xflag |= COMMIT_LAZY; /* - * prepare non-journaled objects for commit + * prepare non-journaled objects for commit * * flush data pages of non-journaled file * to prevent the file getting non-initialized disk blocks @@ -1186,7 +1190,7 @@ int txCommit(tid_t tid, /* transaction identifier */ cd.nip = nip; /* - * acquire transaction lock on (on-disk) inodes + * acquire transaction lock on (on-disk) inodes * * update on-disk inode from in-memory inode * acquiring transaction locks for AFTER records @@ -1262,7 +1266,7 @@ int txCommit(tid_t tid, /* transaction identifier */ } /* - * write log records from transaction locks + * write log records from transaction locks * * txUpdateMap() resets XAD_NEW in XAD. */ @@ -1294,7 +1298,7 @@ int txCommit(tid_t tid, /* transaction identifier */ !test_cflag(COMMIT_Nolink, tblk->u.ip))); /* - * write COMMIT log record + * write COMMIT log record */ lrd->type = cpu_to_le16(LOG_COMMIT); lrd->length = 0; @@ -1303,7 +1307,7 @@ int txCommit(tid_t tid, /* transaction identifier */ lmGroupCommit(log, tblk); /* - * - transaction is now committed - + * - transaction is now committed - */ /* @@ -1314,11 +1318,11 @@ int txCommit(tid_t tid, /* transaction identifier */ txForce(tblk); /* - * update allocation map. + * update allocation map. * * update inode allocation map and inode: * free pager lock on memory object of inode if any. - * update block allocation map. + * update block allocation map. * * txUpdateMap() resets XAD_NEW in XAD. */ @@ -1326,7 +1330,7 @@ int txCommit(tid_t tid, /* transaction identifier */ txUpdateMap(tblk); /* - * free transaction locks and pageout/free pages + * free transaction locks and pageout/free pages */ txRelease(tblk); @@ -1335,7 +1339,7 @@ int txCommit(tid_t tid, /* transaction identifier */ /* - * reset in-memory object state + * reset in-memory object state */ for (k = 0; k < cd.nip; k++) { ip = cd.iplist[k]; @@ -1358,11 +1362,11 @@ int txCommit(tid_t tid, /* transaction identifier */ } /* - * NAME: txLog() + * NAME: txLog() * - * FUNCTION: Writes AFTER log records for all lines modified - * by tid for segments specified by inodes in comdata. - * Code assumes only WRITELOCKS are recorded in lockwords. + * FUNCTION: Writes AFTER log records for all lines modified + * by tid for segments specified by inodes in comdata. + * Code assumes only WRITELOCKS are recorded in lockwords. * * PARAMETERS: * @@ -1421,12 +1425,12 @@ static int txLog(struct jfs_log * log, struct tblock * tblk, struct commit * cd) } /* - * diLog() + * diLog() * - * function: log inode tlock and format maplock to update bmap; + * function: log inode tlock and format maplock to update bmap; */ static int diLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, - struct tlock * tlck, struct commit * cd) + struct tlock * tlck, struct commit * cd) { int rc = 0; struct metapage *mp; @@ -1442,7 +1446,7 @@ static int diLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, pxd = &lrd->log.redopage.pxd; /* - * inode after image + * inode after image */ if (tlck->type & tlckENTRY) { /* log after-image for logredo(): */ @@ -1456,7 +1460,7 @@ static int diLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, tlck->flag |= tlckWRITEPAGE; } else if (tlck->type & tlckFREE) { /* - * free inode extent + * free inode extent * * (pages of the freed inode extent have been invalidated and * a maplock for free of the extent has been formatted at @@ -1498,7 +1502,7 @@ static int diLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, jfs_err("diLog: UFO type tlck:0x%p", tlck); #ifdef _JFS_WIP /* - * alloc/free external EA extent + * alloc/free external EA extent * * a maplock for txUpdateMap() to update bPWMAP for alloc/free * of the extent has been formatted at txLock() time; @@ -1534,9 +1538,9 @@ static int diLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, } /* - * dataLog() + * dataLog() * - * function: log data tlock + * function: log data tlock */ static int dataLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, struct tlock * tlck) @@ -1580,9 +1584,9 @@ static int dataLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, } /* - * dtLog() + * dtLog() * - * function: log dtree tlock and format maplock to update bmap; + * function: log dtree tlock and format maplock to update bmap; */ static void dtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, struct tlock * tlck) @@ -1603,10 +1607,10 @@ static void dtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, lrd->log.redopage.type |= cpu_to_le16(LOG_BTROOT); /* - * page extension via relocation: entry insertion; - * page extension in-place: entry insertion; - * new right page from page split, reinitialized in-line - * root from root page split: entry insertion; + * page extension via relocation: entry insertion; + * page extension in-place: entry insertion; + * new right page from page split, reinitialized in-line + * root from root page split: entry insertion; */ if (tlck->type & (tlckNEW | tlckEXTEND)) { /* log after-image of the new page for logredo(): @@ -1641,8 +1645,8 @@ static void dtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, } /* - * entry insertion/deletion, - * sibling page link update (old right page before split); + * entry insertion/deletion, + * sibling page link update (old right page before split); */ if (tlck->type & (tlckENTRY | tlckRELINK)) { /* log after-image for logredo(): */ @@ -1658,11 +1662,11 @@ static void dtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, } /* - * page deletion: page has been invalidated - * page relocation: source extent + * page deletion: page has been invalidated + * page relocation: source extent * - * a maplock for free of the page has been formatted - * at txLock() time); + * a maplock for free of the page has been formatted + * at txLock() time); */ if (tlck->type & (tlckFREE | tlckRELOCATE)) { /* log LOG_NOREDOPAGE of the deleted page for logredo() @@ -1683,9 +1687,9 @@ static void dtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, } /* - * xtLog() + * xtLog() * - * function: log xtree tlock and format maplock to update bmap; + * function: log xtree tlock and format maplock to update bmap; */ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, struct tlock * tlck) @@ -1725,8 +1729,8 @@ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, xadlock = (struct xdlistlock *) maplock; /* - * entry insertion/extension; - * sibling page link update (old right page before split); + * entry insertion/extension; + * sibling page link update (old right page before split); */ if (tlck->type & (tlckNEW | tlckGROW | tlckRELINK)) { /* log after-image for logredo(): @@ -1801,7 +1805,7 @@ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, } /* - * page deletion: file deletion/truncation (ref. xtTruncate()) + * page deletion: file deletion/truncation (ref. xtTruncate()) * * (page will be invalidated after log is written and bmap * is updated from the page); @@ -1908,13 +1912,13 @@ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, } /* - * page/entry truncation: file truncation (ref. xtTruncate()) + * page/entry truncation: file truncation (ref. xtTruncate()) * - * |----------+------+------+---------------| - * | | | - * | | hwm - hwm before truncation - * | next - truncation point - * lwm - lwm before truncation + * |----------+------+------+---------------| + * | | | + * | | hwm - hwm before truncation + * | next - truncation point + * lwm - lwm before truncation * header ? */ if (tlck->type & tlckTRUNCATE) { @@ -1937,7 +1941,7 @@ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, twm = xtlck->twm.offset; /* - * write log records + * write log records */ /* log after-image for logredo(): * @@ -1997,7 +2001,7 @@ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, } /* - * format maplock(s) for txUpdateMap() to update bmap + * format maplock(s) for txUpdateMap() to update bmap */ maplock->index = 0; @@ -2069,9 +2073,9 @@ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, } /* - * mapLog() + * mapLog() * - * function: log from maplock of freed data extents; + * function: log from maplock of freed data extents; */ static void mapLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, struct tlock * tlck) @@ -2081,7 +2085,7 @@ static void mapLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, pxd_t *pxd; /* - * page relocation: free the source page extent + * page relocation: free the source page extent * * a maplock for txUpdateMap() for free of the page * has been formatted at txLock() time saving the src @@ -2155,10 +2159,10 @@ static void mapLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd, } /* - * txEA() + * txEA() * - * function: acquire maplock for EA/ACL extents or - * set COMMIT_INLINE flag; + * function: acquire maplock for EA/ACL extents or + * set COMMIT_INLINE flag; */ void txEA(tid_t tid, struct inode *ip, dxd_t * oldea, dxd_t * newea) { @@ -2207,10 +2211,10 @@ void txEA(tid_t tid, struct inode *ip, dxd_t * oldea, dxd_t * newea) } /* - * txForce() + * txForce() * * function: synchronously write pages locked by transaction - * after txLog() but before txUpdateMap(); + * after txLog() but before txUpdateMap(); */ static void txForce(struct tblock * tblk) { @@ -2273,10 +2277,10 @@ static void txForce(struct tblock * tblk) } /* - * txUpdateMap() + * txUpdateMap() * - * function: update persistent allocation map (and working map - * if appropriate); + * function: update persistent allocation map (and working map + * if appropriate); * * parameter: */ @@ -2298,7 +2302,7 @@ static void txUpdateMap(struct tblock * tblk) /* - * update block allocation map + * update block allocation map * * update allocation state in pmap (and wmap) and * update lsn of the pmap page; @@ -2382,7 +2386,7 @@ static void txUpdateMap(struct tblock * tblk) } } /* - * update inode allocation map + * update inode allocation map * * update allocation state in pmap and * update lsn of the pmap page; @@ -2407,24 +2411,24 @@ static void txUpdateMap(struct tblock * tblk) } /* - * txAllocPMap() + * txAllocPMap() * * function: allocate from persistent map; * * parameter: - * ipbmap - - * malock - - * xad list: - * pxd: - * - * maptype - - * allocate from persistent map; - * free from persistent map; - * (e.g., tmp file - free from working map at releae - * of last reference); - * free from persistent and working map; - * - * lsn - log sequence number; + * ipbmap - + * malock - + * xad list: + * pxd: + * + * maptype - + * allocate from persistent map; + * free from persistent map; + * (e.g., tmp file - free from working map at releae + * of last reference); + * free from persistent and working map; + * + * lsn - log sequence number; */ static void txAllocPMap(struct inode *ip, struct maplock * maplock, struct tblock * tblk) @@ -2478,9 +2482,9 @@ static void txAllocPMap(struct inode *ip, struct maplock * maplock, } /* - * txFreeMap() + * txFreeMap() * - * function: free from persistent and/or working map; + * function: free from persistent and/or working map; * * todo: optimization */ @@ -2579,9 +2583,9 @@ void txFreeMap(struct inode *ip, } /* - * txFreelock() + * txFreelock() * - * function: remove tlock from inode anonymous locklist + * function: remove tlock from inode anonymous locklist */ void txFreelock(struct inode *ip) { @@ -2619,7 +2623,7 @@ void txFreelock(struct inode *ip) } /* - * txAbort() + * txAbort() * * function: abort tx before commit; * @@ -2679,7 +2683,7 @@ void txAbort(tid_t tid, int dirty) } /* - * txLazyCommit(void) + * txLazyCommit(void) * * All transactions except those changing ipimap (COMMIT_FORCE) are * processed by this routine. This insures that the inode and block @@ -2728,7 +2732,7 @@ static void txLazyCommit(struct tblock * tblk) } /* - * jfs_lazycommit(void) + * jfs_lazycommit(void) * * To be run as a kernel daemon. If lbmIODone is called in an interrupt * context, or where blocking is not wanted, this routine will process @@ -2913,7 +2917,7 @@ void txResume(struct super_block *sb) } /* - * jfs_sync(void) + * jfs_sync(void) * * To be run as a kernel daemon. This is awakened when tlocks run low. * We write any inodes that have anonymous tlocks so they will become diff --git a/fs/jfs/jfs_txnmgr.h b/fs/jfs/jfs_txnmgr.h index 7863cf21afc..ab728893701 100644 --- a/fs/jfs/jfs_txnmgr.h +++ b/fs/jfs/jfs_txnmgr.h @@ -94,7 +94,7 @@ extern struct tblock *TxBlock; /* transaction block table */ */ struct tlock { lid_t next; /* 2: index next lockword on tid locklist - * next lockword on freelist + * next lockword on freelist */ tid_t tid; /* 2: transaction id holding lock */ diff --git a/fs/jfs/jfs_types.h b/fs/jfs/jfs_types.h index 09b25295868..649f9817acc 100644 --- a/fs/jfs/jfs_types.h +++ b/fs/jfs/jfs_types.h @@ -21,7 +21,7 @@ /* * jfs_types.h: * - * basic type/utility definitions + * basic type/utility definitions * * note: this header file must be the 1st include file * of JFS include list in all JFS .c file. @@ -54,8 +54,8 @@ struct timestruc_t { */ #define LEFTMOSTONE 0x80000000 -#define HIGHORDER 0x80000000u /* high order bit on */ -#define ONES 0xffffffffu /* all bit on */ +#define HIGHORDER 0x80000000u /* high order bit on */ +#define ONES 0xffffffffu /* all bit on */ /* * logical xd (lxd) @@ -148,7 +148,7 @@ typedef struct { #define sizeDXD(dxd) le32_to_cpu((dxd)->size) /* - * directory entry argument + * directory entry argument */ struct component_name { int namlen; @@ -160,14 +160,14 @@ struct component_name { * DASD limit information - stored in directory inode */ struct dasd { - u8 thresh; /* Alert Threshold (in percent) */ - u8 delta; /* Alert Threshold delta (in percent) */ + u8 thresh; /* Alert Threshold (in percent) */ + u8 delta; /* Alert Threshold delta (in percent) */ u8 rsrvd1; - u8 limit_hi; /* DASD limit (in logical blocks) */ - __le32 limit_lo; /* DASD limit (in logical blocks) */ + u8 limit_hi; /* DASD limit (in logical blocks) */ + __le32 limit_lo; /* DASD limit (in logical blocks) */ u8 rsrvd2[3]; - u8 used_hi; /* DASD usage (in logical blocks) */ - __le32 used_lo; /* DASD usage (in logical blocks) */ + u8 used_hi; /* DASD usage (in logical blocks) */ + __le32 used_lo; /* DASD usage (in logical blocks) */ }; #define DASDLIMIT(dasdp) \ diff --git a/fs/jfs/jfs_umount.c b/fs/jfs/jfs_umount.c index a386f48c73f..7971f37534a 100644 --- a/fs/jfs/jfs_umount.c +++ b/fs/jfs/jfs_umount.c @@ -60,7 +60,7 @@ int jfs_umount(struct super_block *sb) jfs_info("UnMount JFS: sb:0x%p", sb); /* - * update superblock and close log + * update superblock and close log * * if mounted read-write and log based recovery was enabled */ diff --git a/fs/jfs/jfs_xtree.c b/fs/jfs/jfs_xtree.c index acc97c46d8a..1543906a2e0 100644 --- a/fs/jfs/jfs_xtree.c +++ b/fs/jfs/jfs_xtree.c @@ -16,7 +16,7 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ /* - * jfs_xtree.c: extent allocation descriptor B+-tree manager + * jfs_xtree.c: extent allocation descriptor B+-tree manager */ #include <linux/fs.h> @@ -32,30 +32,30 @@ /* * xtree local flag */ -#define XT_INSERT 0x00000001 +#define XT_INSERT 0x00000001 /* - * xtree key/entry comparison: extent offset + * xtree key/entry comparison: extent offset * * return: - * -1: k < start of extent - * 0: start_of_extent <= k <= end_of_extent - * 1: k > end_of_extent + * -1: k < start of extent + * 0: start_of_extent <= k <= end_of_extent + * 1: k > end_of_extent */ #define XT_CMP(CMP, K, X, OFFSET64)\ {\ - OFFSET64 = offsetXAD(X);\ - (CMP) = ((K) >= OFFSET64 + lengthXAD(X)) ? 1 :\ - ((K) < OFFSET64) ? -1 : 0;\ + OFFSET64 = offsetXAD(X);\ + (CMP) = ((K) >= OFFSET64 + lengthXAD(X)) ? 1 :\ + ((K) < OFFSET64) ? -1 : 0;\ } /* write a xad entry */ #define XT_PUTENTRY(XAD, FLAG, OFF, LEN, ADDR)\ {\ - (XAD)->flag = (FLAG);\ - XADoffset((XAD), (OFF));\ - XADlength((XAD), (LEN));\ - XADaddress((XAD), (ADDR));\ + (XAD)->flag = (FLAG);\ + XADoffset((XAD), (OFF));\ + XADlength((XAD), (LEN));\ + XADaddress((XAD), (ADDR));\ } #define XT_PAGE(IP, MP) BT_PAGE(IP, MP, xtpage_t, i_xtroot) @@ -76,13 +76,13 @@ MP = NULL;\ RC = -EIO;\ }\ - }\ + }\ } /* for consistency */ #define XT_PUTPAGE(MP) BT_PUTPAGE(MP) -#define XT_GETSEARCH(IP, LEAF, BN, MP, P, INDEX) \ +#define XT_GETSEARCH(IP, LEAF, BN, MP, P, INDEX) \ BT_GETSEARCH(IP, LEAF, BN, MP, xtpage_t, P, INDEX, i_xtroot) /* xtree entry parameter descriptor */ struct xtsplit { @@ -97,7 +97,7 @@ struct xtsplit { /* - * statistics + * statistics */ #ifdef CONFIG_JFS_STATISTICS static struct { @@ -136,7 +136,7 @@ static int xtRelink(tid_t tid, struct inode *ip, xtpage_t * fp); #endif /* _STILL_TO_PORT */ /* - * xtLookup() + * xtLookup() * * function: map a single page into a physical extent; */ @@ -179,7 +179,7 @@ int xtLookup(struct inode *ip, s64 lstart, } /* - * compute the physical extent covering logical extent + * compute the physical extent covering logical extent * * N.B. search may have failed (e.g., hole in sparse file), * and returned the index of the next entry. @@ -220,27 +220,27 @@ int xtLookup(struct inode *ip, s64 lstart, /* - * xtLookupList() + * xtLookupList() * * function: map a single logical extent into a list of physical extent; * * parameter: - * struct inode *ip, - * struct lxdlist *lxdlist, lxd list (in) - * struct xadlist *xadlist, xad list (in/out) - * int flag) + * struct inode *ip, + * struct lxdlist *lxdlist, lxd list (in) + * struct xadlist *xadlist, xad list (in/out) + * int flag) * * coverage of lxd by xad under assumption of * . lxd's are ordered and disjoint. * . xad's are ordered and disjoint. * * return: - * 0: success + * 0: success * * note: a page being written (even a single byte) is backed fully, - * except the last page which is only backed with blocks - * required to cover the last byte; - * the extent backing a page is fully contained within an xad; + * except the last page which is only backed with blocks + * required to cover the last byte; + * the extent backing a page is fully contained within an xad; */ int xtLookupList(struct inode *ip, struct lxdlist * lxdlist, struct xadlist * xadlist, int flag) @@ -284,7 +284,7 @@ int xtLookupList(struct inode *ip, struct lxdlist * lxdlist, return rc; /* - * compute the physical extent covering logical extent + * compute the physical extent covering logical extent * * N.B. search may have failed (e.g., hole in sparse file), * and returned the index of the next entry. @@ -343,7 +343,7 @@ int xtLookupList(struct inode *ip, struct lxdlist * lxdlist, if (lstart >= size) goto mapend; - /* compare with the current xad */ + /* compare with the current xad */ goto compare1; } /* lxd is covered by xad */ @@ -430,7 +430,7 @@ int xtLookupList(struct inode *ip, struct lxdlist * lxdlist, /* * lxd is partially covered by xad */ - else { /* (xend < lend) */ + else { /* (xend < lend) */ /* * get next xad @@ -477,22 +477,22 @@ int xtLookupList(struct inode *ip, struct lxdlist * lxdlist, /* - * xtSearch() + * xtSearch() * - * function: search for the xad entry covering specified offset. + * function: search for the xad entry covering specified offset. * * parameters: - * ip - file object; - * xoff - extent offset; - * nextp - address of next extent (if any) for search miss - * cmpp - comparison result: - * btstack - traverse stack; - * flag - search process flag (XT_INSERT); + * ip - file object; + * xoff - extent offset; + * nextp - address of next extent (if any) for search miss + * cmpp - comparison result: + * btstack - traverse stack; + * flag - search process flag (XT_INSERT); * * returns: - * btstack contains (bn, index) of search path traversed to the entry. - * *cmpp is set to result of comparison with the entry returned. - * the page containing the entry is pinned at exit. + * btstack contains (bn, index) of search path traversed to the entry. + * *cmpp is set to result of comparison with the entry returned. + * the page containing the entry is pinned at exit. */ static int xtSearch(struct inode *ip, s64 xoff, s64 *nextp, int *cmpp, struct btstack * btstack, int flag) @@ -517,7 +517,7 @@ static int xtSearch(struct inode *ip, s64 xoff, s64 *nextp, btstack->nsplit = 0; /* - * search down tree from root: + * search down tree from root: * * between two consecutive entries of <Ki, Pi> and <Kj, Pj> of * internal page, child page Pi contains entry with k, Ki <= K < Kj. @@ -642,7 +642,7 @@ static int xtSearch(struct inode *ip, s64 xoff, s64 *nextp, XT_CMP(cmp, xoff, &p->xad[index], t64); if (cmp == 0) { /* - * search hit + * search hit */ /* search hit - leaf page: * return the entry found @@ -692,7 +692,7 @@ static int xtSearch(struct inode *ip, s64 xoff, s64 *nextp, } /* - * search miss + * search miss * * base is the smallest index with key (Kj) greater than * search key (K) and may be zero or maxentry index. @@ -773,22 +773,22 @@ static int xtSearch(struct inode *ip, s64 xoff, s64 *nextp, } /* - * xtInsert() + * xtInsert() * * function: * * parameter: - * tid - transaction id; - * ip - file object; - * xflag - extent flag (XAD_NOTRECORDED): - * xoff - extent offset; - * xlen - extent length; - * xaddrp - extent address pointer (in/out): - * if (*xaddrp) - * caller allocated data extent at *xaddrp; - * else - * allocate data extent and return its xaddr; - * flag - + * tid - transaction id; + * ip - file object; + * xflag - extent flag (XAD_NOTRECORDED): + * xoff - extent offset; + * xlen - extent length; + * xaddrp - extent address pointer (in/out): + * if (*xaddrp) + * caller allocated data extent at *xaddrp; + * else + * allocate data extent and return its xaddr; + * flag - * * return: */ @@ -813,7 +813,7 @@ int xtInsert(tid_t tid, /* transaction id */ jfs_info("xtInsert: nxoff:0x%lx nxlen:0x%x", (ulong) xoff, xlen); /* - * search for the entry location at which to insert: + * search for the entry location at which to insert: * * xtFastSearch() and xtSearch() both returns (leaf page * pinned, index at which to insert). @@ -853,13 +853,13 @@ int xtInsert(tid_t tid, /* transaction id */ } /* - * insert entry for new extent + * insert entry for new extent */ xflag |= XAD_NEW; /* - * if the leaf page is full, split the page and - * propagate up the router entry for the new page from split + * if the leaf page is full, split the page and + * propagate up the router entry for the new page from split * * The xtSplitUp() will insert the entry and unpin the leaf page. */ @@ -886,7 +886,7 @@ int xtInsert(tid_t tid, /* transaction id */ } /* - * insert the new entry into the leaf page + * insert the new entry into the leaf page */ /* * acquire a transaction lock on the leaf page; @@ -930,16 +930,16 @@ int xtInsert(tid_t tid, /* transaction id */ /* - * xtSplitUp() + * xtSplitUp() * * function: - * split full pages as propagating insertion up the tree + * split full pages as propagating insertion up the tree * * parameter: - * tid - transaction id; - * ip - file object; - * split - entry parameter descriptor; - * btstack - traverse stack from xtSearch() + * tid - transaction id; + * ip - file object; + * split - entry parameter descriptor; + * btstack - traverse stack from xtSearch() * * return: */ @@ -1199,22 +1199,22 @@ xtSplitUp(tid_t tid, /* - * xtSplitPage() + * xtSplitPage() * * function: - * split a full non-root page into - * original/split/left page and new right page - * i.e., the original/split page remains as left page. + * split a full non-root page into + * original/split/left page and new right page + * i.e., the original/split page remains as left page. * * parameter: - * int tid, - * struct inode *ip, - * struct xtsplit *split, - * struct metapage **rmpp, - * u64 *rbnp, + * int tid, + * struct inode *ip, + * struct xtsplit *split, + * struct metapage **rmpp, + * u64 *rbnp, * * return: - * Pointer to page in which to insert or NULL on error. + * Pointer to page in which to insert or NULL on error. */ static int xtSplitPage(tid_t tid, struct inode *ip, @@ -1248,9 +1248,9 @@ xtSplitPage(tid_t tid, struct inode *ip, rbn = addressPXD(pxd); /* Allocate blocks to quota. */ - if (DQUOT_ALLOC_BLOCK(ip, lengthPXD(pxd))) { - rc = -EDQUOT; - goto clean_up; + if (DQUOT_ALLOC_BLOCK(ip, lengthPXD(pxd))) { + rc = -EDQUOT; + goto clean_up; } quota_allocation += lengthPXD(pxd); @@ -1304,7 +1304,7 @@ xtSplitPage(tid_t tid, struct inode *ip, skip = split->index; /* - * sequential append at tail (after last entry of last page) + * sequential append at tail (after last entry of last page) * * if splitting the last page on a level because of appending * a entry to it (skip is maxentry), it's likely that the access is @@ -1342,7 +1342,7 @@ xtSplitPage(tid_t tid, struct inode *ip, } /* - * non-sequential insert (at possibly middle page) + * non-sequential insert (at possibly middle page) */ /* @@ -1465,25 +1465,24 @@ xtSplitPage(tid_t tid, struct inode *ip, /* - * xtSplitRoot() + * xtSplitRoot() * * function: - * split the full root page into - * original/root/split page and new right page - * i.e., root remains fixed in tree anchor (inode) and - * the root is copied to a single new right child page - * since root page << non-root page, and - * the split root page contains a single entry for the - * new right child page. + * split the full root page into original/root/split page and new + * right page + * i.e., root remains fixed in tree anchor (inode) and the root is + * copied to a single new right child page since root page << + * non-root page, and the split root page contains a single entry + * for the new right child page. * * parameter: - * int tid, - * struct inode *ip, - * struct xtsplit *split, - * struct metapage **rmpp) + * int tid, + * struct inode *ip, + * struct xtsplit *split, + * struct metapage **rmpp) * * return: - * Pointer to page in which to insert or NULL on error. + * Pointer to page in which to insert or NULL on error. */ static int xtSplitRoot(tid_t tid, @@ -1505,7 +1504,7 @@ xtSplitRoot(tid_t tid, INCREMENT(xtStat.split); /* - * allocate a single (right) child page + * allocate a single (right) child page */ pxdlist = split->pxdlist; pxd = &pxdlist->pxd[pxdlist->npxd]; @@ -1573,7 +1572,7 @@ xtSplitRoot(tid_t tid, } /* - * reset the root + * reset the root * * init root with the single entry for the new right page * set the 1st entry offset to 0, which force the left-most key @@ -1610,7 +1609,7 @@ xtSplitRoot(tid_t tid, /* - * xtExtend() + * xtExtend() * * function: extend in-place; * @@ -1677,7 +1676,7 @@ int xtExtend(tid_t tid, /* transaction id */ goto extendOld; /* - * extent overflow: insert entry for new extent + * extent overflow: insert entry for new extent */ //insertNew: xoff = offsetXAD(xad) + MAXXLEN; @@ -1685,8 +1684,8 @@ int xtExtend(tid_t tid, /* transaction id */ nextindex = le16_to_cpu(p->header.nextindex); /* - * if the leaf page is full, insert the new entry and - * propagate up the router entry for the new page from split + * if the leaf page is full, insert the new entry and + * propagate up the router entry for the new page from split * * The xtSplitUp() will insert the entry and unpin the leaf page. */ @@ -1731,7 +1730,7 @@ int xtExtend(tid_t tid, /* transaction id */ } } /* - * insert the new entry into the leaf page + * insert the new entry into the leaf page */ else { /* insert the new entry: mark the entry NEW */ @@ -1771,11 +1770,11 @@ int xtExtend(tid_t tid, /* transaction id */ #ifdef _NOTYET /* - * xtTailgate() + * xtTailgate() * * function: split existing 'tail' extent - * (split offset >= start offset of tail extent), and - * relocate and extend the split tail half; + * (split offset >= start offset of tail extent), and + * relocate and extend the split tail half; * * note: existing extent may or may not have been committed. * caller is responsible for pager buffer cache update, and @@ -1804,7 +1803,7 @@ int xtTailgate(tid_t tid, /* transaction id */ /* printf("xtTailgate: nxoff:0x%lx nxlen:0x%x nxaddr:0x%lx\n", - (ulong)xoff, xlen, (ulong)xaddr); + (ulong)xoff, xlen, (ulong)xaddr); */ /* there must exist extent to be tailgated */ @@ -1842,18 +1841,18 @@ printf("xtTailgate: nxoff:0x%lx nxlen:0x%x nxaddr:0x%lx\n", xad = &p->xad[index]; /* printf("xtTailgate: xoff:0x%lx xlen:0x%x xaddr:0x%lx\n", - (ulong)offsetXAD(xad), lengthXAD(xad), (ulong)addressXAD(xad)); + (ulong)offsetXAD(xad), lengthXAD(xad), (ulong)addressXAD(xad)); */ if ((llen = xoff - offsetXAD(xad)) == 0) goto updateOld; /* - * partially replace extent: insert entry for new extent + * partially replace extent: insert entry for new extent */ //insertNew: /* - * if the leaf page is full, insert the new entry and - * propagate up the router entry for the new page from split + * if the leaf page is full, insert the new entry and + * propagate up the router entry for the new page from split * * The xtSplitUp() will insert the entry and unpin the leaf page. */ @@ -1898,7 +1897,7 @@ printf("xtTailgate: xoff:0x%lx xlen:0x%x xaddr:0x%lx\n", } } /* - * insert the new entry into the leaf page + * insert the new entry into the leaf page */ else { /* insert the new entry: mark the entry NEW */ @@ -1955,17 +1954,17 @@ printf("xtTailgate: xoff:0x%lx xlen:0x%x xaddr:0x%lx\n", #endif /* _NOTYET */ /* - * xtUpdate() + * xtUpdate() * * function: update XAD; * - * update extent for allocated_but_not_recorded or - * compressed extent; + * update extent for allocated_but_not_recorded or + * compressed extent; * * parameter: - * nxad - new XAD; - * logical extent of the specified XAD must be completely - * contained by an existing XAD; + * nxad - new XAD; + * logical extent of the specified XAD must be completely + * contained by an existing XAD; */ int xtUpdate(tid_t tid, struct inode *ip, xad_t * nxad) { /* new XAD */ @@ -2416,19 +2415,19 @@ printf("xtUpdate.updateLeft.split p:0x%p\n", p); /* - * xtAppend() + * xtAppend() * * function: grow in append mode from contiguous region specified ; * * parameter: - * tid - transaction id; - * ip - file object; - * xflag - extent flag: - * xoff - extent offset; - * maxblocks - max extent length; - * xlen - extent length (in/out); - * xaddrp - extent address pointer (in/out): - * flag - + * tid - transaction id; + * ip - file object; + * xflag - extent flag: + * xoff - extent offset; + * maxblocks - max extent length; + * xlen - extent length (in/out); + * xaddrp - extent address pointer (in/out): + * flag - * * return: */ @@ -2460,7 +2459,7 @@ int xtAppend(tid_t tid, /* transaction id */ (ulong) xoff, maxblocks, xlen, (ulong) xaddr); /* - * search for the entry location at which to insert: + * search for the entry location at which to insert: * * xtFastSearch() and xtSearch() both returns (leaf page * pinned, index at which to insert). @@ -2482,13 +2481,13 @@ int xtAppend(tid_t tid, /* transaction id */ xlen = min(xlen, (int)(next - xoff)); //insert: /* - * insert entry for new extent + * insert entry for new extent */ xflag |= XAD_NEW; /* - * if the leaf page is full, split the page and - * propagate up the router entry for the new page from split + * if the leaf page is full, split the page and + * propagate up the router entry for the new page from split * * The xtSplitUp() will insert the entry and unpin the leaf page. */ @@ -2545,7 +2544,7 @@ int xtAppend(tid_t tid, /* transaction id */ return 0; /* - * insert the new entry into the leaf page + * insert the new entry into the leaf page */ insertLeaf: /* @@ -2589,17 +2588,17 @@ int xtAppend(tid_t tid, /* transaction id */ /* - TBD for defragmentaion/reorganization - * - * xtDelete() + * xtDelete() * * function: - * delete the entry with the specified key. + * delete the entry with the specified key. * - * N.B.: whole extent of the entry is assumed to be deleted. + * N.B.: whole extent of the entry is assumed to be deleted. * * parameter: * * return: - * ENOENT: if the entry is not found. + * ENOENT: if the entry is not found. * * exception: */ @@ -2665,10 +2664,10 @@ int xtDelete(tid_t tid, struct inode *ip, s64 xoff, s32 xlen, int flag) /* - TBD for defragmentaion/reorganization - * - * xtDeleteUp() + * xtDeleteUp() * * function: - * free empty pages as propagating deletion up the tree + * free empty pages as propagating deletion up the tree * * parameter: * @@ -2815,15 +2814,15 @@ xtDeleteUp(tid_t tid, struct inode *ip, /* - * NAME: xtRelocate() + * NAME: xtRelocate() * - * FUNCTION: relocate xtpage or data extent of regular file; - * This function is mainly used by defragfs utility. + * FUNCTION: relocate xtpage or data extent of regular file; + * This function is mainly used by defragfs utility. * - * NOTE: This routine does not have the logic to handle - * uncommitted allocated extent. The caller should call - * txCommit() to commit all the allocation before call - * this routine. + * NOTE: This routine does not have the logic to handle + * uncommitted allocated extent. The caller should call + * txCommit() to commit all the allocation before call + * this routine. */ int xtRelocate(tid_t tid, struct inode * ip, xad_t * oxad, /* old XAD */ @@ -2865,8 +2864,8 @@ xtRelocate(tid_t tid, struct inode * ip, xad_t * oxad, /* old XAD */ xtype, (ulong) xoff, xlen, (ulong) oxaddr, (ulong) nxaddr); /* - * 1. get and validate the parent xtpage/xad entry - * covering the source extent to be relocated; + * 1. get and validate the parent xtpage/xad entry + * covering the source extent to be relocated; */ if (xtype == DATAEXT) { /* search in leaf entry */ @@ -2910,7 +2909,7 @@ xtRelocate(tid_t tid, struct inode * ip, xad_t * oxad, /* old XAD */ jfs_info("xtRelocate: parent xad entry validated."); /* - * 2. relocate the extent + * 2. relocate the extent */ if (xtype == DATAEXT) { /* if the extent is allocated-but-not-recorded @@ -2923,7 +2922,7 @@ xtRelocate(tid_t tid, struct inode * ip, xad_t * oxad, /* old XAD */ XT_PUTPAGE(pmp); /* - * cmRelocate() + * cmRelocate() * * copy target data pages to be relocated; * @@ -2945,8 +2944,8 @@ xtRelocate(tid_t tid, struct inode * ip, xad_t * oxad, /* old XAD */ pno = offset >> CM_L2BSIZE; npages = (nbytes + (CM_BSIZE - 1)) >> CM_L2BSIZE; /* - npages = ((offset + nbytes - 1) >> CM_L2BSIZE) - - (offset >> CM_L2BSIZE) + 1; + npages = ((offset + nbytes - 1) >> CM_L2BSIZE) - + (offset >> CM_L2BSIZE) + 1; */ sxaddr = oxaddr; dxaddr = nxaddr; @@ -2981,7 +2980,7 @@ xtRelocate(tid_t tid, struct inode * ip, xad_t * oxad, /* old XAD */ XT_GETSEARCH(ip, btstack.top, bn, pmp, pp, index); jfs_info("xtRelocate: target data extent relocated."); - } else { /* (xtype == XTPAGE) */ + } else { /* (xtype == XTPAGE) */ /* * read in the target xtpage from the source extent; @@ -3026,16 +3025,14 @@ xtRelocate(tid_t tid, struct inode * ip, xad_t * oxad, /* old XAD */ */ if (lmp) { BT_MARK_DIRTY(lmp, ip); - tlck = - txLock(tid, ip, lmp, tlckXTREE | tlckRELINK); + tlck = txLock(tid, ip, lmp, tlckXTREE | tlckRELINK); lp->header.next = cpu_to_le64(nxaddr); XT_PUTPAGE(lmp); } if (rmp) { BT_MARK_DIRTY(rmp, ip); - tlck = - txLock(tid, ip, rmp, tlckXTREE | tlckRELINK); + tlck = txLock(tid, ip, rmp, tlckXTREE | tlckRELINK); rp->header.prev = cpu_to_le64(nxaddr); XT_PUTPAGE(rmp); } @@ -3062,7 +3059,7 @@ xtRelocate(tid_t tid, struct inode * ip, xad_t * oxad, /* old XAD */ * scan may be skipped by commit() and logredo(); */ BT_MARK_DIRTY(mp, ip); - /* tlckNEW init xtlck->lwm.offset = XTENTRYSTART; */ + /* tlckNEW init xtlck->lwm.offset = XTENTRYSTART; */ tlck = txLock(tid, ip, mp, tlckXTREE | tlckNEW); xtlck = (struct xtlock *) & tlck->lock; @@ -3084,7 +3081,7 @@ xtRelocate(tid_t tid, struct inode * ip, xad_t * oxad, /* old XAD */ } /* - * 3. acquire maplock for the source extent to be freed; + * 3. acquire maplock for the source extent to be freed; * * acquire a maplock saving the src relocated extent address; * to free of the extent at commit time; @@ -3105,7 +3102,7 @@ xtRelocate(tid_t tid, struct inode * ip, xad_t * oxad, /* old XAD */ * is no buffer associated with this lock since the buffer * has been redirected to the target location. */ - else /* (xtype == XTPAGE) */ + else /* (xtype == XTPAGE) */ tlck = txMaplock(tid, ip, tlckMAP | tlckRELOCATE); pxdlock = (struct pxd_lock *) & tlck->lock; @@ -3115,7 +3112,7 @@ xtRelocate(tid_t tid, struct inode * ip, xad_t * oxad, /* old XAD */ pxdlock->index = 1; /* - * 4. update the parent xad entry for relocation; + * 4. update the parent xad entry for relocation; * * acquire tlck for the parent entry with XAD_NEW as entry * update which will write LOG_REDOPAGE and update bmap for @@ -3143,22 +3140,22 @@ xtRelocate(tid_t tid, struct inode * ip, xad_t * oxad, /* old XAD */ /* - * xtSearchNode() + * xtSearchNode() * - * function: search for the internal xad entry covering specified extent. - * This function is mainly used by defragfs utility. + * function: search for the internal xad entry covering specified extent. + * This function is mainly used by defragfs utility. * * parameters: - * ip - file object; - * xad - extent to find; - * cmpp - comparison result: - * btstack - traverse stack; - * flag - search process flag; + * ip - file object; + * xad - extent to find; + * cmpp - comparison result: + * btstack - traverse stack; + * flag - search process flag; * * returns: - * btstack contains (bn, index) of search path traversed to the entry. - * *cmpp is set to result of comparison with the entry returned. - * the page containing the entry is pinned at exit. + * btstack contains (bn, index) of search path traversed to the entry. + * *cmpp is set to result of comparison with the entry returned. + * the page containing the entry is pinned at exit. */ static int xtSearchNode(struct inode *ip, xad_t * xad, /* required XAD entry */ int *cmpp, struct btstack * btstack, int flag) @@ -3181,7 +3178,7 @@ static int xtSearchNode(struct inode *ip, xad_t * xad, /* required XAD entry */ xaddr = addressXAD(xad); /* - * search down tree from root: + * search down tree from root: * * between two consecutive entries of <Ki, Pi> and <Kj, Pj> of * internal page, child page Pi contains entry with k, Ki <= K < Kj. @@ -3217,7 +3214,7 @@ static int xtSearchNode(struct inode *ip, xad_t * xad, /* required XAD entry */ XT_CMP(cmp, xoff, &p->xad[index], t64); if (cmp == 0) { /* - * search hit + * search hit * * verify for exact match; */ @@ -3245,7 +3242,7 @@ static int xtSearchNode(struct inode *ip, xad_t * xad, /* required XAD entry */ } /* - * search miss - non-leaf page: + * search miss - non-leaf page: * * base is the smallest index with key (Kj) greater than * search key (K) and may be zero or maxentry index. @@ -3268,15 +3265,15 @@ static int xtSearchNode(struct inode *ip, xad_t * xad, /* required XAD entry */ /* - * xtRelink() + * xtRelink() * * function: - * link around a freed page. + * link around a freed page. * * Parameter: - * int tid, - * struct inode *ip, - * xtpage_t *p) + * int tid, + * struct inode *ip, + * xtpage_t *p) * * returns: */ @@ -3338,7 +3335,7 @@ static int xtRelink(tid_t tid, struct inode *ip, xtpage_t * p) /* - * xtInitRoot() + * xtInitRoot() * * initialize file root (inline in inode) */ @@ -3385,42 +3382,42 @@ void xtInitRoot(tid_t tid, struct inode *ip) #define MAX_TRUNCATE_LEAVES 50 /* - * xtTruncate() + * xtTruncate() * * function: - * traverse for truncation logging backward bottom up; - * terminate at the last extent entry at the current subtree - * root page covering new down size. - * truncation may occur within the last extent entry. + * traverse for truncation logging backward bottom up; + * terminate at the last extent entry at the current subtree + * root page covering new down size. + * truncation may occur within the last extent entry. * * parameter: - * int tid, - * struct inode *ip, - * s64 newsize, - * int type) {PWMAP, PMAP, WMAP; DELETE, TRUNCATE} + * int tid, + * struct inode *ip, + * s64 newsize, + * int type) {PWMAP, PMAP, WMAP; DELETE, TRUNCATE} * * return: * * note: - * PWMAP: - * 1. truncate (non-COMMIT_NOLINK file) - * by jfs_truncate() or jfs_open(O_TRUNC): - * xtree is updated; + * PWMAP: + * 1. truncate (non-COMMIT_NOLINK file) + * by jfs_truncate() or jfs_open(O_TRUNC): + * xtree is updated; * 2. truncate index table of directory when last entry removed - * map update via tlock at commit time; - * PMAP: + * map update via tlock at commit time; + * PMAP: * Call xtTruncate_pmap instead - * WMAP: - * 1. remove (free zero link count) on last reference release - * (pmap has been freed at commit zero link count); - * 2. truncate (COMMIT_NOLINK file, i.e., tmp file): - * xtree is updated; - * map update directly at truncation time; + * WMAP: + * 1. remove (free zero link count) on last reference release + * (pmap has been freed at commit zero link count); + * 2. truncate (COMMIT_NOLINK file, i.e., tmp file): + * xtree is updated; + * map update directly at truncation time; * - * if (DELETE) - * no LOG_NOREDOPAGE is required (NOREDOFILE is sufficient); - * else if (TRUNCATE) - * must write LOG_NOREDOPAGE for deleted index page; + * if (DELETE) + * no LOG_NOREDOPAGE is required (NOREDOFILE is sufficient); + * else if (TRUNCATE) + * must write LOG_NOREDOPAGE for deleted index page; * * pages may already have been tlocked by anonymous transactions * during file growth (i.e., write) before truncation; @@ -3493,7 +3490,7 @@ s64 xtTruncate(tid_t tid, struct inode *ip, s64 newsize, int flag) * retained in the new sized file. * if type is PMAP, the data and index pages are NOT * freed, and the data and index blocks are NOT freed - * from working map. + * from working map. * (this will allow continued access of data/index of * temporary file (zerolink count file truncated to zero-length)). */ @@ -3542,7 +3539,7 @@ s64 xtTruncate(tid_t tid, struct inode *ip, s64 newsize, int flag) goto getChild; /* - * leaf page + * leaf page */ freed = 0; @@ -3916,7 +3913,7 @@ s64 xtTruncate(tid_t tid, struct inode *ip, s64 newsize, int flag) } /* - * internal page: go down to child page of current entry + * internal page: go down to child page of current entry */ getChild: /* save current parent entry for the child page */ @@ -3965,7 +3962,7 @@ s64 xtTruncate(tid_t tid, struct inode *ip, s64 newsize, int flag) /* - * xtTruncate_pmap() + * xtTruncate_pmap() * * function: * Perform truncate to zero lenghth for deleted file, leaving the @@ -3974,9 +3971,9 @@ s64 xtTruncate(tid_t tid, struct inode *ip, s64 newsize, int flag) * is committed to disk. * * parameter: - * tid_t tid, - * struct inode *ip, - * s64 committed_size) + * tid_t tid, + * struct inode *ip, + * s64 committed_size) * * return: new committed size * @@ -4050,7 +4047,7 @@ s64 xtTruncate_pmap(tid_t tid, struct inode *ip, s64 committed_size) } /* - * leaf page + * leaf page */ if (++locked_leaves > MAX_TRUNCATE_LEAVES) { @@ -4062,7 +4059,7 @@ s64 xtTruncate_pmap(tid_t tid, struct inode *ip, s64 committed_size) xoff = offsetXAD(xad); xlen = lengthXAD(xad); XT_PUTPAGE(mp); - return (xoff + xlen) << JFS_SBI(ip->i_sb)->l2bsize; + return (xoff + xlen) << JFS_SBI(ip->i_sb)->l2bsize; } tlck = txLock(tid, ip, mp, tlckXTREE); tlck->type = tlckXTREE | tlckFREE; @@ -4099,8 +4096,7 @@ s64 xtTruncate_pmap(tid_t tid, struct inode *ip, s64 committed_size) */ tlck = txLock(tid, ip, mp, tlckXTREE); xtlck = (struct xtlock *) & tlck->lock; - xtlck->hwm.offset = - le16_to_cpu(p->header.nextindex) - 1; + xtlck->hwm.offset = le16_to_cpu(p->header.nextindex) - 1; tlck->type = tlckXTREE | tlckFREE; XT_PUTPAGE(mp); @@ -4118,7 +4114,7 @@ s64 xtTruncate_pmap(tid_t tid, struct inode *ip, s64 committed_size) else index--; /* - * internal page: go down to child page of current entry + * internal page: go down to child page of current entry */ getChild: /* save current parent entry for the child page */ diff --git a/fs/jfs/jfs_xtree.h b/fs/jfs/jfs_xtree.h index 164f6f2b101..70815c8a3d6 100644 --- a/fs/jfs/jfs_xtree.h +++ b/fs/jfs/jfs_xtree.h @@ -19,14 +19,14 @@ #define _H_JFS_XTREE /* - * jfs_xtree.h: extent allocation descriptor B+-tree manager + * jfs_xtree.h: extent allocation descriptor B+-tree manager */ #include "jfs_btree.h" /* - * extent allocation descriptor (xad) + * extent allocation descriptor (xad) */ typedef struct xad { unsigned flag:8; /* 1: flag */ @@ -38,30 +38,30 @@ typedef struct xad { __le32 addr2; /* 4: address in unit of fsblksize */ } xad_t; /* (16) */ -#define MAXXLEN ((1 << 24) - 1) +#define MAXXLEN ((1 << 24) - 1) -#define XTSLOTSIZE 16 -#define L2XTSLOTSIZE 4 +#define XTSLOTSIZE 16 +#define L2XTSLOTSIZE 4 /* xad_t field construction */ #define XADoffset(xad, offset64)\ {\ - (xad)->off1 = ((u64)offset64) >> 32;\ - (xad)->off2 = __cpu_to_le32((offset64) & 0xffffffff);\ + (xad)->off1 = ((u64)offset64) >> 32;\ + (xad)->off2 = __cpu_to_le32((offset64) & 0xffffffff);\ } #define XADaddress(xad, address64)\ {\ - (xad)->addr1 = ((u64)address64) >> 32;\ - (xad)->addr2 = __cpu_to_le32((address64) & 0xffffffff);\ + (xad)->addr1 = ((u64)address64) >> 32;\ + (xad)->addr2 = __cpu_to_le32((address64) & 0xffffffff);\ } -#define XADlength(xad, length32) (xad)->len = __cpu_to_le24(length32) +#define XADlength(xad, length32) (xad)->len = __cpu_to_le24(length32) /* xad_t field extraction */ #define offsetXAD(xad)\ - ( ((s64)((xad)->off1)) << 32 | __le32_to_cpu((xad)->off2)) + ( ((s64)((xad)->off1)) << 32 | __le32_to_cpu((xad)->off2)) #define addressXAD(xad)\ - ( ((s64)((xad)->addr1)) << 32 | __le32_to_cpu((xad)->addr2)) -#define lengthXAD(xad) __le24_to_cpu((xad)->len) + ( ((s64)((xad)->addr1)) << 32 | __le32_to_cpu((xad)->addr2)) +#define lengthXAD(xad) __le24_to_cpu((xad)->len) /* xad list */ struct xadlist { @@ -71,22 +71,22 @@ struct xadlist { }; /* xad_t flags */ -#define XAD_NEW 0x01 /* new */ -#define XAD_EXTENDED 0x02 /* extended */ -#define XAD_COMPRESSED 0x04 /* compressed with recorded length */ +#define XAD_NEW 0x01 /* new */ +#define XAD_EXTENDED 0x02 /* extended */ +#define XAD_COMPRESSED 0x04 /* compressed with recorded length */ #define XAD_NOTRECORDED 0x08 /* allocated but not recorded */ -#define XAD_COW 0x10 /* copy-on-write */ +#define XAD_COW 0x10 /* copy-on-write */ /* possible values for maxentry */ -#define XTROOTINITSLOT_DIR 6 -#define XTROOTINITSLOT 10 -#define XTROOTMAXSLOT 18 -#define XTPAGEMAXSLOT 256 -#define XTENTRYSTART 2 +#define XTROOTINITSLOT_DIR 6 +#define XTROOTINITSLOT 10 +#define XTROOTMAXSLOT 18 +#define XTPAGEMAXSLOT 256 +#define XTENTRYSTART 2 /* - * xtree page: + * xtree page: */ typedef union { struct xtheader { @@ -106,7 +106,7 @@ typedef union { } xtpage_t; /* - * external declaration + * external declaration */ extern int xtLookup(struct inode *ip, s64 lstart, s64 llen, int *pflag, s64 * paddr, int *plen, int flag); diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 41c20477126..25161c4121e 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -328,7 +328,7 @@ static int jfs_mkdir(struct inode *dip, struct dentry *dentry, int mode) * dentry - child directory dentry * * RETURN: -EINVAL - if name is . or .. - * -EINVAL - if . or .. exist but are invalid. + * -EINVAL - if . or .. exist but are invalid. * errors from subroutines * * note: @@ -517,7 +517,7 @@ static int jfs_unlink(struct inode *dip, struct dentry *dentry) inode_dec_link_count(ip); /* - * commit zero link count object + * commit zero link count object */ if (ip->i_nlink == 0) { assert(!test_cflag(COMMIT_Nolink, ip)); @@ -596,7 +596,7 @@ static int jfs_unlink(struct inode *dip, struct dentry *dentry) /* * NAME: commitZeroLink() * - * FUNCTION: for non-directory, called by jfs_remove(), + * FUNCTION: for non-directory, called by jfs_remove(), * truncate a regular file, directory or symbolic * link to zero length. return 0 if type is not * one of these. @@ -676,7 +676,7 @@ static s64 commitZeroLink(tid_t tid, struct inode *ip) /* * NAME: jfs_free_zero_link() * - * FUNCTION: for non-directory, called by iClose(), + * FUNCTION: for non-directory, called by iClose(), * free resources of a file from cache and WORKING map * for a file previously committed with zero link count * while associated with a pager object, @@ -855,12 +855,12 @@ static int jfs_link(struct dentry *old_dentry, * NAME: jfs_symlink(dip, dentry, name) * * FUNCTION: creates a symbolic link to <symlink> by name <name> - * in directory <dip> + * in directory <dip> * - * PARAMETER: dip - parent directory vnode - * dentry - dentry of symbolic link - * name - the path name of the existing object - * that will be the source of the link + * PARAMETER: dip - parent directory vnode + * dentry - dentry of symbolic link + * name - the path name of the existing object + * that will be the source of the link * * RETURN: errors from subroutines * @@ -1052,9 +1052,9 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry, /* - * NAME: jfs_rename + * NAME: jfs_rename * - * FUNCTION: rename a file or directory + * FUNCTION: rename a file or directory */ static int jfs_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) @@ -1331,9 +1331,9 @@ static int jfs_rename(struct inode *old_dir, struct dentry *old_dentry, /* - * NAME: jfs_mknod + * NAME: jfs_mknod * - * FUNCTION: Create a special file (device) + * FUNCTION: Create a special file (device) */ static int jfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t rdev) diff --git a/fs/jfs/resize.c b/fs/jfs/resize.c index 79d625f3f73..71984ee9534 100644 --- a/fs/jfs/resize.c +++ b/fs/jfs/resize.c @@ -29,17 +29,17 @@ #include "jfs_txnmgr.h" #include "jfs_debug.h" -#define BITSPERPAGE (PSIZE << 3) -#define L2MEGABYTE 20 -#define MEGABYTE (1 << L2MEGABYTE) -#define MEGABYTE32 (MEGABYTE << 5) +#define BITSPERPAGE (PSIZE << 3) +#define L2MEGABYTE 20 +#define MEGABYTE (1 << L2MEGABYTE) +#define MEGABYTE32 (MEGABYTE << 5) /* convert block number to bmap file page number */ #define BLKTODMAPN(b)\ - (((b) >> 13) + ((b) >> 23) + ((b) >> 33) + 3 + 1) + (((b) >> 13) + ((b) >> 23) + ((b) >> 33) + 3 + 1) /* - * jfs_extendfs() + * jfs_extendfs() * * function: extend file system; * @@ -48,9 +48,9 @@ * workspace space * * input: - * new LVSize: in LV blocks (required) - * new LogSize: in LV blocks (optional) - * new FSSize: in LV blocks (optional) + * new LVSize: in LV blocks (required) + * new LogSize: in LV blocks (optional) + * new FSSize: in LV blocks (optional) * * new configuration: * 1. set new LogSize as specified or default from new LVSize; @@ -125,8 +125,8 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize) } /* - * reconfigure LV spaces - * --------------------- + * reconfigure LV spaces + * --------------------- * * validate new size, or, if not specified, determine new size */ @@ -198,7 +198,7 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize) log_formatted = 1; } /* - * quiesce file system + * quiesce file system * * (prepare to move the inline log and to prevent map update) * @@ -270,8 +270,8 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize) } /* - * extend block allocation map - * --------------------------- + * extend block allocation map + * --------------------------- * * extendfs() for new extension, retry after crash recovery; * @@ -283,7 +283,7 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize) * s_size: aggregate size in physical blocks; */ /* - * compute the new block allocation map configuration + * compute the new block allocation map configuration * * map dinode: * di_size: map file size in byte; @@ -301,7 +301,7 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize) newNpages = BLKTODMAPN(t64) + 1; /* - * extend map from current map (WITHOUT growing mapfile) + * extend map from current map (WITHOUT growing mapfile) * * map new extension with unmapped part of the last partial * dmap page, if applicable, and extra page(s) allocated @@ -341,8 +341,8 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize) XSize -= nblocks; /* - * grow map file to cover remaining extension - * and/or one extra dmap page for next extendfs(); + * grow map file to cover remaining extension + * and/or one extra dmap page for next extendfs(); * * allocate new map pages and its backing blocks, and * update map file xtree @@ -422,8 +422,8 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize) dbFinalizeBmap(ipbmap); /* - * update inode allocation map - * --------------------------- + * update inode allocation map + * --------------------------- * * move iag lists from old to new iag; * agstart field is not updated for logredo() to reconstruct @@ -442,8 +442,8 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize) } /* - * finalize - * -------- + * finalize + * -------- * * extension is committed when on-disk super block is * updated with new descriptors: logredo will recover @@ -480,7 +480,7 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize) diFreeSpecial(ipbmap2); /* - * update superblock + * update superblock */ if ((rc = readSuper(sb, &bh))) goto error_out; @@ -530,7 +530,7 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize) resume: /* - * resume file system transactions + * resume file system transactions */ txResume(sb); diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index b753ba21645..b2375f0774b 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -63,9 +63,9 @@ * * On-disk: * - * FEALISTs are stored on disk using blocks allocated by dbAlloc() and - * written directly. An EA list may be in-lined in the inode if there is - * sufficient room available. + * FEALISTs are stored on disk using blocks allocated by dbAlloc() and + * written directly. An EA list may be in-lined in the inode if there is + * sufficient room available. */ struct ea_buffer { @@ -590,7 +590,8 @@ static int ea_get(struct inode *inode, struct ea_buffer *ea_buf, int min_size) size_check: if (EALIST_SIZE(ea_buf->xattr) != ea_size) { printk(KERN_ERR "ea_get: invalid extended attribute\n"); - dump_mem("xattr", ea_buf->xattr, ea_size); + print_hex_dump(KERN_ERR, "", DUMP_PREFIX_ADDRESS, 16, 1, + ea_buf->xattr, ea_size, 1); ea_release(inode, ea_buf); rc = -EIO; goto clean_up; diff --git a/fs/minix/file.c b/fs/minix/file.c index f92baa1d757..17765f697e5 100644 --- a/fs/minix/file.c +++ b/fs/minix/file.c @@ -23,7 +23,7 @@ const struct file_operations minix_file_operations = { .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .fsync = minix_sync_file, - .sendfile = generic_file_sendfile, + .splice_read = generic_file_splice_read, }; const struct inode_operations minix_file_inode_operations = { diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 9eb8eb4e4a0..8689b736fdd 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -41,7 +41,9 @@ static int nfs_file_open(struct inode *, struct file *); static int nfs_file_release(struct inode *, struct file *); static loff_t nfs_file_llseek(struct file *file, loff_t offset, int origin); static int nfs_file_mmap(struct file *, struct vm_area_struct *); -static ssize_t nfs_file_sendfile(struct file *, loff_t *, size_t, read_actor_t, void *); +static ssize_t nfs_file_splice_read(struct file *filp, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t count, unsigned int flags); static ssize_t nfs_file_read(struct kiocb *, const struct iovec *iov, unsigned long nr_segs, loff_t pos); static ssize_t nfs_file_write(struct kiocb *, const struct iovec *iov, @@ -65,7 +67,7 @@ const struct file_operations nfs_file_operations = { .fsync = nfs_fsync, .lock = nfs_lock, .flock = nfs_flock, - .sendfile = nfs_file_sendfile, + .splice_read = nfs_file_splice_read, .check_flags = nfs_check_flags, }; @@ -224,20 +226,21 @@ nfs_file_read(struct kiocb *iocb, const struct iovec *iov, } static ssize_t -nfs_file_sendfile(struct file *filp, loff_t *ppos, size_t count, - read_actor_t actor, void *target) +nfs_file_splice_read(struct file *filp, loff_t *ppos, + struct pipe_inode_info *pipe, size_t count, + unsigned int flags) { struct dentry *dentry = filp->f_path.dentry; struct inode *inode = dentry->d_inode; ssize_t res; - dfprintk(VFS, "nfs: sendfile(%s/%s, %lu@%Lu)\n", + dfprintk(VFS, "nfs: splice_read(%s/%s, %lu@%Lu)\n", dentry->d_parent->d_name.name, dentry->d_name.name, (unsigned long) count, (unsigned long long) *ppos); res = nfs_revalidate_mapping(inode, filp->f_mapping); if (!res) - res = generic_file_sendfile(filp, ppos, count, actor, target); + res = generic_file_splice_read(filp, ppos, pipe, count, flags); return res; } diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 7e6aa245b5d..8604e35bd48 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -23,7 +23,7 @@ #include <linux/file.h> #include <linux/mount.h> #include <linux/major.h> -#include <linux/ext2_fs.h> +#include <linux/splice.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/fcntl.h> @@ -801,26 +801,32 @@ found: } /* - * Grab and keep cached pages assosiated with a file in the svc_rqst - * so that they can be passed to the netowork sendmsg/sendpage routines - * directrly. They will be released after the sending has completed. + * Grab and keep cached pages associated with a file in the svc_rqst + * so that they can be passed to the network sendmsg/sendpage routines + * directly. They will be released after the sending has completed. */ static int -nfsd_read_actor(read_descriptor_t *desc, struct page *page, unsigned long offset , unsigned long size) +nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf, + struct splice_desc *sd) { - unsigned long count = desc->count; - struct svc_rqst *rqstp = desc->arg.data; + struct svc_rqst *rqstp = sd->u.data; struct page **pp = rqstp->rq_respages + rqstp->rq_resused; + struct page *page = buf->page; + size_t size; + int ret; + + ret = buf->ops->confirm(pipe, buf); + if (unlikely(ret)) + return ret; - if (size > count) - size = count; + size = sd->len; if (rqstp->rq_res.page_len == 0) { get_page(page); put_page(*pp); *pp = page; rqstp->rq_resused++; - rqstp->rq_res.page_base = offset; + rqstp->rq_res.page_base = buf->offset; rqstp->rq_res.page_len = size; } else if (page != pp[-1]) { get_page(page); @@ -832,11 +838,15 @@ nfsd_read_actor(read_descriptor_t *desc, struct page *page, unsigned long offset } else rqstp->rq_res.page_len += size; - desc->count = count - size; - desc->written += size; return size; } +static int nfsd_direct_splice_actor(struct pipe_inode_info *pipe, + struct splice_desc *sd) +{ + return __splice_from_pipe(pipe, sd, nfsd_splice_actor); +} + static __be32 nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, loff_t offset, struct kvec *vec, int vlen, unsigned long *count) @@ -861,10 +871,15 @@ nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, if (ra && ra->p_set) file->f_ra = ra->p_ra; - if (file->f_op->sendfile && rqstp->rq_sendfile_ok) { - rqstp->rq_resused = 1; - host_err = file->f_op->sendfile(file, &offset, *count, - nfsd_read_actor, rqstp); + if (file->f_op->splice_read && rqstp->rq_splice_ok) { + struct splice_desc sd = { + .len = 0, + .total_len = *count, + .pos = offset, + .u.data = rqstp, + }; + + host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor); } else { oldfs = get_fs(); set_fs(KERNEL_DS); diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 7ed56390b58..ffcc504a166 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2276,7 +2276,7 @@ const struct file_operations ntfs_file_ops = { mounted filesystem. */ .mmap = generic_file_mmap, /* Mmap file. */ .open = ntfs_file_open, /* Open file. */ - .sendfile = generic_file_sendfile, /* Zero-copy data send with + .splice_read = generic_file_splice_read /* Zero-copy data send with the data source being on the ntfs partition. We do not need to care about the diff --git a/fs/ocfs2/cluster/masklog.c b/fs/ocfs2/cluster/masklog.c index 2b205f5d579..e9e042b93db 100644 --- a/fs/ocfs2/cluster/masklog.c +++ b/fs/ocfs2/cluster/masklog.c @@ -74,7 +74,6 @@ struct mlog_attribute { #define define_mask(_name) { \ .attr = { \ .name = #_name, \ - .owner = THIS_MODULE, \ .mode = S_IRUGO | S_IWUSR, \ }, \ .mask = ML_##_name, \ diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index ac6c96431bb..4979b667571 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -31,7 +31,7 @@ #include <linux/pagemap.h> #include <linux/uio.h> #include <linux/sched.h> -#include <linux/pipe_fs_i.h> +#include <linux/splice.h> #include <linux/mount.h> #include <linux/writeback.h> @@ -1583,7 +1583,7 @@ static int ocfs2_splice_write_actor(struct pipe_inode_info *pipe, ssize_t copied = 0; struct ocfs2_splice_write_priv sp; - ret = buf->ops->pin(pipe, buf); + ret = buf->ops->confirm(pipe, buf); if (ret) goto out; @@ -1604,7 +1604,7 @@ static int ocfs2_splice_write_actor(struct pipe_inode_info *pipe, * might enter ocfs2_buffered_write_cluster() more * than once, so keep track of our progress here. */ - copied = ocfs2_buffered_write_cluster(sd->file, + copied = ocfs2_buffered_write_cluster(sd->u.file, (loff_t)sd->pos + total, count, ocfs2_map_and_write_splice_data, @@ -1636,9 +1636,14 @@ static ssize_t __ocfs2_file_splice_write(struct pipe_inode_info *pipe, int ret, err; struct address_space *mapping = out->f_mapping; struct inode *inode = mapping->host; - - ret = __splice_from_pipe(pipe, out, ppos, len, flags, - ocfs2_splice_write_actor); + struct splice_desc sd = { + .total_len = len, + .flags = flags, + .pos = *ppos, + .u.file = out, + }; + + ret = __splice_from_pipe(pipe, &sd, ocfs2_splice_write_actor); if (ret > 0) { *ppos += ret; @@ -1817,7 +1822,6 @@ const struct inode_operations ocfs2_special_file_iops = { const struct file_operations ocfs2_fops = { .read = do_sync_read, .write = do_sync_write, - .sendfile = generic_file_sendfile, .mmap = ocfs2_mmap, .fsync = ocfs2_sync_file, .release = ocfs2_file_release, diff --git a/fs/partitions/check.c b/fs/partitions/check.c index 9a3a058f355..98e0b85a9bb 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -397,7 +397,6 @@ void add_partition(struct gendisk *disk, int part, sector_t start, sector_t len, static struct attribute addpartattr = { .name = "whole_disk", .mode = S_IRUSR | S_IRGRP | S_IROTH, - .owner = THIS_MODULE, }; sysfs_create_file(&p->kobj, &addpartattr); diff --git a/fs/partitions/ibm.c b/fs/partitions/ibm.c index 9f7ad4244f6..1e064c4a4f8 100644 --- a/fs/partitions/ibm.c +++ b/fs/partitions/ibm.c @@ -45,7 +45,7 @@ ibm_partition(struct parsed_partitions *state, struct block_device *bdev) { int blocksize, offset, size,res; loff_t i_size; - dasd_information_t *info; + dasd_information2_t *info; struct hd_geometry *geo; char type[5] = {0,}; char name[7] = {0,}; @@ -64,14 +64,17 @@ ibm_partition(struct parsed_partitions *state, struct block_device *bdev) if (i_size == 0) goto out_exit; - if ((info = kmalloc(sizeof(dasd_information_t), GFP_KERNEL)) == NULL) + info = kmalloc(sizeof(dasd_information2_t), GFP_KERNEL); + if (info == NULL) goto out_exit; - if ((geo = kmalloc(sizeof(struct hd_geometry), GFP_KERNEL)) == NULL) + geo = kmalloc(sizeof(struct hd_geometry), GFP_KERNEL); + if (geo == NULL) goto out_nogeo; - if ((label = kmalloc(sizeof(union label_t), GFP_KERNEL)) == NULL) + label = kmalloc(sizeof(union label_t), GFP_KERNEL); + if (label == NULL) goto out_nolab; - if (ioctl_by_bdev(bdev, BIODASDINFO, (unsigned long)info) != 0 || + if (ioctl_by_bdev(bdev, BIODASDINFO2, (unsigned long)info) != 0 || ioctl_by_bdev(bdev, HDIO_GETGEO, (unsigned long)geo) != 0) goto out_freeall; @@ -96,84 +99,108 @@ ibm_partition(struct parsed_partitions *state, struct block_device *bdev) res = 1; /* - * Three different types: CMS1, VOL1 and LNX1/unlabeled + * Three different formats: LDL, CDL and unformated disk + * + * identified by info->format + * + * unformated disks we do not have to care about */ - if (strncmp(type, "CMS1", 4) == 0) { - /* - * VM style CMS1 labeled disk - */ - if (label->cms.disk_offset != 0) { - printk("CMS1/%8s(MDSK):", name); - /* disk is reserved minidisk */ - blocksize = label->cms.block_size; - offset = label->cms.disk_offset; - size = (label->cms.block_count - 1) * (blocksize >> 9); + if (info->format == DASD_FORMAT_LDL) { + if (strncmp(type, "CMS1", 4) == 0) { + /* + * VM style CMS1 labeled disk + */ + if (label->cms.disk_offset != 0) { + printk("CMS1/%8s(MDSK):", name); + /* disk is reserved minidisk */ + blocksize = label->cms.block_size; + offset = label->cms.disk_offset; + size = (label->cms.block_count - 1) + * (blocksize >> 9); + } else { + printk("CMS1/%8s:", name); + offset = (info->label_block + 1); + size = i_size >> 9; + } } else { - printk("CMS1/%8s:", name); + /* + * Old style LNX1 or unlabeled disk + */ + if (strncmp(type, "LNX1", 4) == 0) + printk ("LNX1/%8s:", name); + else + printk("(nonl)"); offset = (info->label_block + 1); size = i_size >> 9; } put_partition(state, 1, offset*(blocksize >> 9), - size-offset*(blocksize >> 9)); - } else if ((strncmp(type, "VOL1", 4) == 0) && - (!info->FBA_layout) && (!strcmp(info->type, "ECKD"))) { + size-offset*(blocksize >> 9)); + } else if (info->format == DASD_FORMAT_CDL) { /* - * New style VOL1 labeled disk + * New style CDL formatted disk */ unsigned int blk; int counter; - printk("VOL1/%8s:", name); - - /* get block number and read then go through format1 labels */ - blk = cchhb2blk(&label->vol.vtoc, geo) + 1; - counter = 0; - while ((data = read_dev_sector(bdev, blk*(blocksize/512), - §)) != NULL) { - struct vtoc_format1_label f1; - - memcpy(&f1, data, sizeof(struct vtoc_format1_label)); - put_dev_sector(sect); - - /* skip FMT4 / FMT5 / FMT7 labels */ - if (f1.DS1FMTID == _ascebc['4'] - || f1.DS1FMTID == _ascebc['5'] - || f1.DS1FMTID == _ascebc['7']) { - blk++; - continue; - } - - /* only FMT1 valid at this point */ - if (f1.DS1FMTID != _ascebc['1']) - break; - - /* OK, we got valid partition data */ - offset = cchh2blk(&f1.DS1EXT1.llimit, geo); - size = cchh2blk(&f1.DS1EXT1.ulimit, geo) - - offset + geo->sectors; - if (counter >= state->limit) - break; - put_partition(state, counter + 1, - offset * (blocksize >> 9), - size * (blocksize >> 9)); - counter++; - blk++; - } - if (!data) - /* Are we not supposed to report this ? */ - goto out_readerr; - } else { /* - * Old style LNX1 or unlabeled disk + * check if VOL1 label is available + * if not, something is wrong, skipping partition detection */ - if (strncmp(type, "LNX1", 4) == 0) - printk ("LNX1/%8s:", name); - else - printk("(nonl)/%8s:", name); - offset = (info->label_block + 1); - size = i_size >> 9; - put_partition(state, 1, offset*(blocksize >> 9), - size-offset*(blocksize >> 9)); + if (strncmp(type, "VOL1", 4) == 0) { + printk("VOL1/%8s:", name); + /* + * get block number and read then go through format1 + * labels + */ + blk = cchhb2blk(&label->vol.vtoc, geo) + 1; + counter = 0; + data = read_dev_sector(bdev, blk * (blocksize/512), + §); + while (data != NULL) { + struct vtoc_format1_label f1; + + memcpy(&f1, data, + sizeof(struct vtoc_format1_label)); + put_dev_sector(sect); + + /* skip FMT4 / FMT5 / FMT7 labels */ + if (f1.DS1FMTID == _ascebc['4'] + || f1.DS1FMTID == _ascebc['5'] + || f1.DS1FMTID == _ascebc['7']) { + blk++; + data = read_dev_sector(bdev, blk * + (blocksize/512), + §); + continue; + } + + /* only FMT1 valid at this point */ + if (f1.DS1FMTID != _ascebc['1']) + break; + + /* OK, we got valid partition data */ + offset = cchh2blk(&f1.DS1EXT1.llimit, geo); + size = cchh2blk(&f1.DS1EXT1.ulimit, geo) - + offset + geo->sectors; + if (counter >= state->limit) + break; + put_partition(state, counter + 1, + offset * (blocksize >> 9), + size * (blocksize >> 9)); + counter++; + blk++; + data = read_dev_sector(bdev, + blk * (blocksize/512), + §); + } + + if (!data) + /* Are we not supposed to report this ? */ + goto out_readerr; + } else + printk(KERN_WARNING "Warning, expected Label VOL1 not " + "found, treating as CDL formated Disk"); + } printk("\n"); diff --git a/fs/pipe.c b/fs/pipe.c index 3a89592bdf5..d007830d9c8 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -164,6 +164,20 @@ static void anon_pipe_buf_release(struct pipe_inode_info *pipe, page_cache_release(page); } +/** + * generic_pipe_buf_map - virtually map a pipe buffer + * @pipe: the pipe that the buffer belongs to + * @buf: the buffer that should be mapped + * @atomic: whether to use an atomic map + * + * Description: + * This function returns a kernel virtual address mapping for the + * passed in @pipe_buffer. If @atomic is set, an atomic map is provided + * and the caller has to be careful not to fault before calling + * the unmap function. + * + * Note that this function occupies KM_USER0 if @atomic != 0. + */ void *generic_pipe_buf_map(struct pipe_inode_info *pipe, struct pipe_buffer *buf, int atomic) { @@ -175,6 +189,15 @@ void *generic_pipe_buf_map(struct pipe_inode_info *pipe, return kmap(buf->page); } +/** + * generic_pipe_buf_unmap - unmap a previously mapped pipe buffer + * @pipe: the pipe that the buffer belongs to + * @buf: the buffer that should be unmapped + * @map_data: the data that the mapping function returned + * + * Description: + * This function undoes the mapping that ->map() provided. + */ void generic_pipe_buf_unmap(struct pipe_inode_info *pipe, struct pipe_buffer *buf, void *map_data) { @@ -185,11 +208,28 @@ void generic_pipe_buf_unmap(struct pipe_inode_info *pipe, kunmap(buf->page); } +/** + * generic_pipe_buf_steal - attempt to take ownership of a @pipe_buffer + * @pipe: the pipe that the buffer belongs to + * @buf: the buffer to attempt to steal + * + * Description: + * This function attempts to steal the @struct page attached to + * @buf. If successful, this function returns 0 and returns with + * the page locked. The caller may then reuse the page for whatever + * he wishes, the typical use is insertion into a different file + * page cache. + */ int generic_pipe_buf_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; + /* + * A reference of one is golden, that means that the owner of this + * page is the only one holding a reference to it. lock the page + * and return OK. + */ if (page_count(page) == 1) { lock_page(page); return 0; @@ -198,12 +238,32 @@ int generic_pipe_buf_steal(struct pipe_inode_info *pipe, return 1; } -void generic_pipe_buf_get(struct pipe_inode_info *info, struct pipe_buffer *buf) +/** + * generic_pipe_buf_get - get a reference to a @struct pipe_buffer + * @pipe: the pipe that the buffer belongs to + * @buf: the buffer to get a reference to + * + * Description: + * This function grabs an extra reference to @buf. It's used in + * in the tee() system call, when we duplicate the buffers in one + * pipe into another. + */ +void generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { page_cache_get(buf->page); } -int generic_pipe_buf_pin(struct pipe_inode_info *info, struct pipe_buffer *buf) +/** + * generic_pipe_buf_confirm - verify contents of the pipe buffer + * @pipe: the pipe that the buffer belongs to + * @buf: the buffer to confirm + * + * Description: + * This function does nothing, because the generic pipe code uses + * pages that are always good when inserted into the pipe. + */ +int generic_pipe_buf_confirm(struct pipe_inode_info *info, + struct pipe_buffer *buf) { return 0; } @@ -212,7 +272,7 @@ static const struct pipe_buf_operations anon_pipe_buf_ops = { .can_merge = 1, .map = generic_pipe_buf_map, .unmap = generic_pipe_buf_unmap, - .pin = generic_pipe_buf_pin, + .confirm = generic_pipe_buf_confirm, .release = anon_pipe_buf_release, .steal = generic_pipe_buf_steal, .get = generic_pipe_buf_get, @@ -252,7 +312,7 @@ pipe_read(struct kiocb *iocb, const struct iovec *_iov, if (chars > total_len) chars = total_len; - error = ops->pin(pipe, buf); + error = ops->confirm(pipe, buf); if (error) { if (!ret) error = ret; @@ -373,7 +433,7 @@ pipe_write(struct kiocb *iocb, const struct iovec *_iov, int error, atomic = 1; void *addr; - error = ops->pin(pipe, buf); + error = ops->confirm(pipe, buf); if (error) goto out; diff --git a/fs/proc/array.c b/fs/proc/array.c index 74f30e0c038..98e78e2f18d 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -165,7 +165,6 @@ static inline char * task_state(struct task_struct *p, char *buffer) rcu_read_lock(); buffer += sprintf(buffer, "State:\t%s\n" - "SleepAVG:\t%lu%%\n" "Tgid:\t%d\n" "Pid:\t%d\n" "PPid:\t%d\n" @@ -173,7 +172,6 @@ static inline char * task_state(struct task_struct *p, char *buffer) "Uid:\t%d\t%d\t%d\t%d\n" "Gid:\t%d\t%d\t%d\t%d\n", get_task_state(p), - (p->sleep_avg/1024)*100/(1020000000/1024), p->tgid, p->pid, pid_alive(p) ? rcu_dereference(p->real_parent)->tgid : 0, pid_alive(p) && p->ptrace ? rcu_dereference(p->parent)->pid : 0, @@ -312,6 +310,41 @@ int proc_pid_status(struct task_struct *task, char * buffer) return buffer - orig; } +static clock_t task_utime(struct task_struct *p) +{ + clock_t utime = cputime_to_clock_t(p->utime), + total = utime + cputime_to_clock_t(p->stime); + u64 temp; + + /* + * Use CFS's precise accounting: + */ + temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime); + + if (total) { + temp *= utime; + do_div(temp, total); + } + utime = (clock_t)temp; + + return utime; +} + +static clock_t task_stime(struct task_struct *p) +{ + clock_t stime = cputime_to_clock_t(p->stime); + + /* + * Use CFS's precise accounting. (we subtract utime from + * the total, to make sure the total observed by userspace + * grows monotonically - apps rely on that): + */ + stime = nsec_to_clock_t(p->se.sum_exec_runtime) - task_utime(p); + + return stime; +} + + static int do_task_stat(struct task_struct *task, char * buffer, int whole) { unsigned long vsize, eip, esp, wchan = ~0UL; @@ -326,7 +359,8 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole) unsigned long long start_time; unsigned long cmin_flt = 0, cmaj_flt = 0; unsigned long min_flt = 0, maj_flt = 0; - cputime_t cutime, cstime, utime, stime; + cputime_t cutime, cstime; + clock_t utime, stime; unsigned long rsslim = 0; char tcomm[sizeof(task->comm)]; unsigned long flags; @@ -344,7 +378,8 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole) sigemptyset(&sigign); sigemptyset(&sigcatch); - cutime = cstime = utime = stime = cputime_zero; + cutime = cstime = cputime_zero; + utime = stime = 0; rcu_read_lock(); if (lock_task_sighand(task, &flags)) { @@ -370,15 +405,15 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole) do { min_flt += t->min_flt; maj_flt += t->maj_flt; - utime = cputime_add(utime, t->utime); - stime = cputime_add(stime, t->stime); + utime += task_utime(t); + stime += task_stime(t); t = next_thread(t); } while (t != task); min_flt += sig->min_flt; maj_flt += sig->maj_flt; - utime = cputime_add(utime, sig->utime); - stime = cputime_add(stime, sig->stime); + utime += cputime_to_clock_t(sig->utime); + stime += cputime_to_clock_t(sig->stime); } sid = signal_session(sig); @@ -394,8 +429,8 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole) if (!whole) { min_flt = task->min_flt; maj_flt = task->maj_flt; - utime = task->utime; - stime = task->stime; + utime = task_utime(task); + stime = task_stime(task); } /* scale priority and nice values from timeslices to -20..20 */ @@ -426,8 +461,8 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole) cmin_flt, maj_flt, cmaj_flt, - cputime_to_clock_t(utime), - cputime_to_clock_t(stime), + utime, + stime, cputime_to_clock_t(cutime), cputime_to_clock_t(cstime), priority, diff --git a/fs/proc/base.c b/fs/proc/base.c index a5fa1fdafc4..46ea5d56e1b 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -296,7 +296,7 @@ static int proc_pid_wchan(struct task_struct *task, char *buffer) */ static int proc_pid_schedstat(struct task_struct *task, char *buffer) { - return sprintf(buffer, "%lu %lu %lu\n", + return sprintf(buffer, "%llu %llu %lu\n", task->sched_info.cpu_time, task->sched_info.run_delay, task->sched_info.pcnt); @@ -929,6 +929,69 @@ static const struct file_operations proc_fault_inject_operations = { }; #endif +#ifdef CONFIG_SCHED_DEBUG +/* + * Print out various scheduling related per-task fields: + */ +static int sched_show(struct seq_file *m, void *v) +{ + struct inode *inode = m->private; + struct task_struct *p; + + WARN_ON(!inode); + + p = get_proc_task(inode); + if (!p) + return -ESRCH; + proc_sched_show_task(p, m); + + put_task_struct(p); + + return 0; +} + +static ssize_t +sched_write(struct file *file, const char __user *buf, + size_t count, loff_t *offset) +{ + struct inode *inode = file->f_path.dentry->d_inode; + struct task_struct *p; + + WARN_ON(!inode); + + p = get_proc_task(inode); + if (!p) + return -ESRCH; + proc_sched_set_task(p); + + put_task_struct(p); + + return count; +} + +static int sched_open(struct inode *inode, struct file *filp) +{ + int ret; + + ret = single_open(filp, sched_show, NULL); + if (!ret) { + struct seq_file *m = filp->private_data; + + m->private = inode; + } + return ret; +} + +static const struct file_operations proc_pid_sched_operations = { + .open = sched_open, + .read = seq_read, + .write = sched_write, + .llseek = seq_lseek, + .release = seq_release, +}; + +#endif + static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd) { struct inode *inode = dentry->d_inode; @@ -1963,6 +2026,9 @@ static const struct pid_entry tgid_base_stuff[] = { INF("environ", S_IRUSR, pid_environ), INF("auxv", S_IRUSR, pid_auxv), INF("status", S_IRUGO, pid_status), +#ifdef CONFIG_SCHED_DEBUG + REG("sched", S_IRUGO|S_IWUSR, pid_sched), +#endif INF("cmdline", S_IRUGO, pid_cmdline), INF("stat", S_IRUGO, tgid_stat), INF("statm", S_IRUGO, pid_statm), @@ -2247,6 +2313,9 @@ static const struct pid_entry tid_base_stuff[] = { INF("environ", S_IRUSR, pid_environ), INF("auxv", S_IRUSR, pid_auxv), INF("status", S_IRUGO, pid_status), +#ifdef CONFIG_SCHED_DEBUG + REG("sched", S_IRUGO|S_IWUSR, pid_sched), +#endif INF("cmdline", S_IRUGO, pid_cmdline), INF("stat", S_IRUGO, tid_stat), INF("statm", S_IRUGO, pid_statm), diff --git a/fs/qnx4/file.c b/fs/qnx4/file.c index 44649981bbc..867f42b0203 100644 --- a/fs/qnx4/file.c +++ b/fs/qnx4/file.c @@ -25,7 +25,7 @@ const struct file_operations qnx4_file_operations = .read = do_sync_read, .aio_read = generic_file_aio_read, .mmap = generic_file_mmap, - .sendfile = generic_file_sendfile, + .splice_read = generic_file_splice_read, #ifdef CONFIG_QNX4FS_RW .write = do_sync_write, .aio_write = generic_file_aio_write, diff --git a/fs/ramfs/file-mmu.c b/fs/ramfs/file-mmu.c index 2f14774a124..97bdc0b2f9d 100644 --- a/fs/ramfs/file-mmu.c +++ b/fs/ramfs/file-mmu.c @@ -41,7 +41,7 @@ const struct file_operations ramfs_file_operations = { .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .fsync = simple_sync_file, - .sendfile = generic_file_sendfile, + .splice_read = generic_file_splice_read, .llseek = generic_file_llseek, }; diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index 5d258c40a2f..cad2b7ace63 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -42,7 +42,7 @@ const struct file_operations ramfs_file_operations = { .write = do_sync_write, .aio_write = generic_file_aio_write, .fsync = simple_sync_file, - .sendfile = generic_file_sendfile, + .splice_read = generic_file_splice_read, .llseek = generic_file_llseek, }; diff --git a/fs/read_write.c b/fs/read_write.c index 4d03008f015..507ddff48a9 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -15,6 +15,7 @@ #include <linux/module.h> #include <linux/syscalls.h> #include <linux/pagemap.h> +#include <linux/splice.h> #include "read_write.h" #include <asm/uaccess.h> @@ -25,7 +26,7 @@ const struct file_operations generic_ro_fops = { .read = do_sync_read, .aio_read = generic_file_aio_read, .mmap = generic_file_readonly_mmap, - .sendfile = generic_file_sendfile, + .splice_read = generic_file_splice_read, }; EXPORT_SYMBOL(generic_ro_fops); @@ -708,7 +709,7 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, struct inode * in_inode, * out_inode; loff_t pos; ssize_t retval; - int fput_needed_in, fput_needed_out; + int fput_needed_in, fput_needed_out, fl; /* * Get input file, and verify that it is ok.. @@ -723,7 +724,7 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, in_inode = in_file->f_path.dentry->d_inode; if (!in_inode) goto fput_in; - if (!in_file->f_op || !in_file->f_op->sendfile) + if (!in_file->f_op || !in_file->f_op->splice_read) goto fput_in; retval = -ESPIPE; if (!ppos) @@ -776,7 +777,18 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, count = max - pos; } - retval = in_file->f_op->sendfile(in_file, ppos, count, file_send_actor, out_file); + fl = 0; +#if 0 + /* + * We need to debate whether we can enable this or not. The + * man page documents EAGAIN return for the output at least, + * and the application is arguably buggy if it doesn't expect + * EAGAIN on a non-blocking file descriptor. + */ + if (in_file->f_flags & O_NONBLOCK) + fl = SPLICE_F_NONBLOCK; +#endif + retval = do_splice_direct(in_file, ppos, out_file, count, fl); if (retval > 0) { add_rchar(current, retval); diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index 9e451a68580..30eebfb1b2d 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -1531,7 +1531,6 @@ const struct file_operations reiserfs_file_operations = { .open = generic_file_open, .release = reiserfs_file_release, .fsync = reiserfs_sync_file, - .sendfile = generic_file_sendfile, .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write, .splice_read = generic_file_splice_read, diff --git a/fs/seq_file.c b/fs/seq_file.c index 0ac22af7afe..49194a4e6b9 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -447,3 +447,37 @@ int seq_puts(struct seq_file *m, const char *s) return -1; } EXPORT_SYMBOL(seq_puts); + +struct list_head *seq_list_start(struct list_head *head, loff_t pos) +{ + struct list_head *lh; + + list_for_each(lh, head) + if (pos-- == 0) + return lh; + + return NULL; +} + +EXPORT_SYMBOL(seq_list_start); + +struct list_head *seq_list_start_head(struct list_head *head, loff_t pos) +{ + if (!pos) + return head; + + return seq_list_start(head, pos - 1); +} + +EXPORT_SYMBOL(seq_list_start_head); + +struct list_head *seq_list_next(void *v, struct list_head *head, loff_t *ppos) +{ + struct list_head *lh; + + lh = ((struct list_head *)v)->next; + ++*ppos; + return lh == head ? NULL : lh; +} + +EXPORT_SYMBOL(seq_list_next); diff --git a/fs/smbfs/file.c b/fs/smbfs/file.c index aea3f8aa54c..c5d78a7e492 100644 --- a/fs/smbfs/file.c +++ b/fs/smbfs/file.c @@ -262,8 +262,9 @@ out: } static ssize_t -smb_file_sendfile(struct file *file, loff_t *ppos, - size_t count, read_actor_t actor, void *target) +smb_file_splice_read(struct file *file, loff_t *ppos, + struct pipe_inode_info *pipe, size_t count, + unsigned int flags) { struct dentry *dentry = file->f_path.dentry; ssize_t status; @@ -277,7 +278,7 @@ smb_file_sendfile(struct file *file, loff_t *ppos, DENTRY_PATH(dentry), status); goto out; } - status = generic_file_sendfile(file, ppos, count, actor, target); + status = generic_file_splice_read(file, ppos, pipe, count, flags); out: return status; } @@ -416,7 +417,7 @@ const struct file_operations smb_file_operations = .open = smb_file_open, .release = smb_file_release, .fsync = smb_fsync, - .sendfile = smb_file_sendfile, + .splice_read = smb_file_splice_read, }; const struct inode_operations smb_file_inode_operations = diff --git a/fs/splice.c b/fs/splice.c index e7d7080de2f..6c9828651e6 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -20,7 +20,7 @@ #include <linux/fs.h> #include <linux/file.h> #include <linux/pagemap.h> -#include <linux/pipe_fs_i.h> +#include <linux/splice.h> #include <linux/mm_inline.h> #include <linux/swap.h> #include <linux/writeback.h> @@ -28,22 +28,7 @@ #include <linux/module.h> #include <linux/syscalls.h> #include <linux/uio.h> - -struct partial_page { - unsigned int offset; - unsigned int len; -}; - -/* - * Passed to splice_to_pipe - */ -struct splice_pipe_desc { - struct page **pages; /* page map */ - struct partial_page *partial; /* pages[] may not be contig */ - int nr_pages; /* number of pages in map */ - unsigned int flags; /* splice flags */ - const struct pipe_buf_operations *ops;/* ops associated with output pipe */ -}; +#include <linux/security.h> /* * Attempt to steal a page from a pipe buffer. This should perhaps go into @@ -101,8 +86,12 @@ static void page_cache_pipe_buf_release(struct pipe_inode_info *pipe, buf->flags &= ~PIPE_BUF_FLAG_LRU; } -static int page_cache_pipe_buf_pin(struct pipe_inode_info *pipe, - struct pipe_buffer *buf) +/* + * Check whether the contents of buf is OK to access. Since the content + * is a page cache page, IO may be in flight. + */ +static int page_cache_pipe_buf_confirm(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) { struct page *page = buf->page; int err; @@ -143,7 +132,7 @@ static const struct pipe_buf_operations page_cache_pipe_buf_ops = { .can_merge = 0, .map = generic_pipe_buf_map, .unmap = generic_pipe_buf_unmap, - .pin = page_cache_pipe_buf_pin, + .confirm = page_cache_pipe_buf_confirm, .release = page_cache_pipe_buf_release, .steal = page_cache_pipe_buf_steal, .get = generic_pipe_buf_get, @@ -163,18 +152,25 @@ static const struct pipe_buf_operations user_page_pipe_buf_ops = { .can_merge = 0, .map = generic_pipe_buf_map, .unmap = generic_pipe_buf_unmap, - .pin = generic_pipe_buf_pin, + .confirm = generic_pipe_buf_confirm, .release = page_cache_pipe_buf_release, .steal = user_page_pipe_buf_steal, .get = generic_pipe_buf_get, }; -/* - * Pipe output worker. This sets up our pipe format with the page cache - * pipe buffer operations. Otherwise very similar to the regular pipe_writev(). +/** + * splice_to_pipe - fill passed data into a pipe + * @pipe: pipe to fill + * @spd: data to fill + * + * Description: + * @spd contains a map of pages and len/offset tupples, a long with + * the struct pipe_buf_operations associated with these pages. This + * function will link that data to the pipe. + * */ -static ssize_t splice_to_pipe(struct pipe_inode_info *pipe, - struct splice_pipe_desc *spd) +ssize_t splice_to_pipe(struct pipe_inode_info *pipe, + struct splice_pipe_desc *spd) { unsigned int spd_pages = spd->nr_pages; int ret, do_wakeup, page_nr; @@ -201,6 +197,7 @@ static ssize_t splice_to_pipe(struct pipe_inode_info *pipe, buf->page = spd->pages[page_nr]; buf->offset = spd->partial[page_nr].offset; buf->len = spd->partial[page_nr].len; + buf->private = spd->partial[page_nr].private; buf->ops = spd->ops; if (spd->flags & SPLICE_F_GIFT) buf->flags |= PIPE_BUF_FLAG_GIFT; @@ -296,19 +293,15 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, page_cache_readahead(mapping, &in->f_ra, in, index, nr_pages); /* - * Now fill in the holes: - */ - error = 0; - - /* * Lookup the (hopefully) full range of pages we need. */ spd.nr_pages = find_get_pages_contig(mapping, index, nr_pages, pages); /* * If find_get_pages_contig() returned fewer pages than we needed, - * allocate the rest. + * allocate the rest and fill in the holes. */ + error = 0; index += spd.nr_pages; while (spd.nr_pages < nr_pages) { /* @@ -470,11 +463,16 @@ fill_it: /** * generic_file_splice_read - splice data from file to a pipe * @in: file to splice from + * @ppos: position in @in * @pipe: pipe to splice to * @len: number of bytes to splice * @flags: splice modifier flags * - * Will read pages from given file and fill them into a pipe. + * Description: + * Will read pages from given file and fill them into a pipe. Can be + * used as long as the address_space operations for the source implements + * a readpage() hook. + * */ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, @@ -494,7 +492,7 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos, ret = 0; spliced = 0; - while (len) { + while (len && !spliced) { ret = __generic_file_splice_read(in, ppos, pipe, len, flags); if (ret < 0) @@ -528,11 +526,11 @@ EXPORT_SYMBOL(generic_file_splice_read); static int pipe_to_sendpage(struct pipe_inode_info *pipe, struct pipe_buffer *buf, struct splice_desc *sd) { - struct file *file = sd->file; + struct file *file = sd->u.file; loff_t pos = sd->pos; int ret, more; - ret = buf->ops->pin(pipe, buf); + ret = buf->ops->confirm(pipe, buf); if (!ret) { more = (sd->flags & SPLICE_F_MORE) || sd->len < sd->total_len; @@ -566,7 +564,7 @@ static int pipe_to_sendpage(struct pipe_inode_info *pipe, static int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf, struct splice_desc *sd) { - struct file *file = sd->file; + struct file *file = sd->u.file; struct address_space *mapping = file->f_mapping; unsigned int offset, this_len; struct page *page; @@ -576,7 +574,7 @@ static int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf, /* * make sure the data in this buffer is uptodate */ - ret = buf->ops->pin(pipe, buf); + ret = buf->ops->confirm(pipe, buf); if (unlikely(ret)) return ret; @@ -663,36 +661,37 @@ out_ret: return ret; } -/* - * Pipe input worker. Most of this logic works like a regular pipe, the - * key here is the 'actor' worker passed in that actually moves the data - * to the wanted destination. See pipe_to_file/pipe_to_sendpage above. +/** + * __splice_from_pipe - splice data from a pipe to given actor + * @pipe: pipe to splice from + * @sd: information to @actor + * @actor: handler that splices the data + * + * Description: + * This function does little more than loop over the pipe and call + * @actor to do the actual moving of a single struct pipe_buffer to + * the desired destination. See pipe_to_file, pipe_to_sendpage, or + * pipe_to_user. + * */ -ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, - struct file *out, loff_t *ppos, size_t len, - unsigned int flags, splice_actor *actor) +ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, struct splice_desc *sd, + splice_actor *actor) { int ret, do_wakeup, err; - struct splice_desc sd; ret = 0; do_wakeup = 0; - sd.total_len = len; - sd.flags = flags; - sd.file = out; - sd.pos = *ppos; - for (;;) { if (pipe->nrbufs) { struct pipe_buffer *buf = pipe->bufs + pipe->curbuf; const struct pipe_buf_operations *ops = buf->ops; - sd.len = buf->len; - if (sd.len > sd.total_len) - sd.len = sd.total_len; + sd->len = buf->len; + if (sd->len > sd->total_len) + sd->len = sd->total_len; - err = actor(pipe, buf, &sd); + err = actor(pipe, buf, sd); if (err <= 0) { if (!ret && err != -ENODATA) ret = err; @@ -704,10 +703,10 @@ ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, buf->offset += err; buf->len -= err; - sd.len -= err; - sd.pos += err; - sd.total_len -= err; - if (sd.len) + sd->len -= err; + sd->pos += err; + sd->total_len -= err; + if (sd->len) continue; if (!buf->len) { @@ -719,7 +718,7 @@ ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, do_wakeup = 1; } - if (!sd.total_len) + if (!sd->total_len) break; } @@ -732,7 +731,7 @@ ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, break; } - if (flags & SPLICE_F_NONBLOCK) { + if (sd->flags & SPLICE_F_NONBLOCK) { if (!ret) ret = -EAGAIN; break; @@ -766,12 +765,32 @@ ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, } EXPORT_SYMBOL(__splice_from_pipe); +/** + * splice_from_pipe - splice data from a pipe to a file + * @pipe: pipe to splice from + * @out: file to splice to + * @ppos: position in @out + * @len: how many bytes to splice + * @flags: splice modifier flags + * @actor: handler that splices the data + * + * Description: + * See __splice_from_pipe. This function locks the input and output inodes, + * otherwise it's identical to __splice_from_pipe(). + * + */ ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags, splice_actor *actor) { ssize_t ret; struct inode *inode = out->f_mapping->host; + struct splice_desc sd = { + .total_len = len, + .flags = flags, + .pos = *ppos, + .u.file = out, + }; /* * The actor worker might be calling ->prepare_write and @@ -780,7 +799,7 @@ ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out, * pipe->inode, we have to order lock acquiry here. */ inode_double_lock(inode, pipe->inode); - ret = __splice_from_pipe(pipe, out, ppos, len, flags, actor); + ret = __splice_from_pipe(pipe, &sd, actor); inode_double_unlock(inode, pipe->inode); return ret; @@ -790,12 +809,14 @@ ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out, * generic_file_splice_write_nolock - generic_file_splice_write without mutexes * @pipe: pipe info * @out: file to write to + * @ppos: position in @out * @len: number of bytes to splice * @flags: splice modifier flags * - * Will either move or copy pages (determined by @flags options) from - * the given pipe inode to the given file. The caller is responsible - * for acquiring i_mutex on both inodes. + * Description: + * Will either move or copy pages (determined by @flags options) from + * the given pipe inode to the given file. The caller is responsible + * for acquiring i_mutex on both inodes. * */ ssize_t @@ -804,6 +825,12 @@ generic_file_splice_write_nolock(struct pipe_inode_info *pipe, struct file *out, { struct address_space *mapping = out->f_mapping; struct inode *inode = mapping->host; + struct splice_desc sd = { + .total_len = len, + .flags = flags, + .pos = *ppos, + .u.file = out, + }; ssize_t ret; int err; @@ -811,7 +838,7 @@ generic_file_splice_write_nolock(struct pipe_inode_info *pipe, struct file *out, if (unlikely(err)) return err; - ret = __splice_from_pipe(pipe, out, ppos, len, flags, pipe_to_file); + ret = __splice_from_pipe(pipe, &sd, pipe_to_file); if (ret > 0) { unsigned long nr_pages; @@ -841,11 +868,13 @@ EXPORT_SYMBOL(generic_file_splice_write_nolock); * generic_file_splice_write - splice data from a pipe to a file * @pipe: pipe info * @out: file to write to + * @ppos: position in @out * @len: number of bytes to splice * @flags: splice modifier flags * - * Will either move or copy pages (determined by @flags options) from - * the given pipe inode to the given file. + * Description: + * Will either move or copy pages (determined by @flags options) from + * the given pipe inode to the given file. * */ ssize_t @@ -896,13 +925,15 @@ EXPORT_SYMBOL(generic_file_splice_write); /** * generic_splice_sendpage - splice data from a pipe to a socket - * @inode: pipe inode + * @pipe: pipe to splice from * @out: socket to write to + * @ppos: position in @out * @len: number of bytes to splice * @flags: splice modifier flags * - * Will send @len bytes from the pipe to a network socket. No data copying - * is involved. + * Description: + * Will send @len bytes from the pipe to a network socket. No data copying + * is involved. * */ ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out, @@ -931,6 +962,10 @@ 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); } @@ -953,17 +988,34 @@ 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); } -long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, - size_t len, unsigned int flags) +/** + * splice_direct_to_actor - splices data directly between two non-pipes + * @in: file to splice from + * @sd: actor information on where to splice to + * @actor: handles the data splicing + * + * Description: + * This is a special case helper to splice directly between two + * points, without requiring an explicit pipe. Internally an allocated + * pipe is cached in the process, and reused during the life time of + * that process. + * + */ +ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, + splice_direct_actor *actor) { struct pipe_inode_info *pipe; long ret, bytes; - loff_t out_off; umode_t i_mode; - int i; + size_t len; + int i, flags; /* * We require the input being a regular file, as we don't want to @@ -999,49 +1051,41 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, */ ret = 0; bytes = 0; - out_off = 0; + len = sd->total_len; + flags = sd->flags; - while (len) { - size_t read_len, max_read_len; + /* + * Don't block on output, we have to drain the direct pipe. + */ + sd->flags &= ~SPLICE_F_NONBLOCK; - /* - * Do at most PIPE_BUFFERS pages worth of transfer: - */ - max_read_len = min(len, (size_t)(PIPE_BUFFERS*PAGE_SIZE)); + while (len) { + size_t read_len; - ret = do_splice_to(in, ppos, pipe, max_read_len, flags); - if (unlikely(ret < 0)) + ret = do_splice_to(in, &sd->pos, pipe, len, flags); + if (unlikely(ret <= 0)) goto out_release; read_len = ret; + sd->total_len = read_len; /* * NOTE: nonblocking mode only applies to the input. We * must not do the output in nonblocking mode as then we * could get stuck data in the internal pipe: */ - ret = do_splice_from(pipe, out, &out_off, read_len, - flags & ~SPLICE_F_NONBLOCK); - if (unlikely(ret < 0)) + ret = actor(pipe, sd); + if (unlikely(ret <= 0)) goto out_release; bytes += ret; len -= ret; - /* - * In nonblocking mode, if we got back a short read then - * that was due to either an IO error or due to the - * pagecache entry not being there. In the IO error case - * the _next_ splice attempt will produce a clean IO error - * return value (not a short read), so in both cases it's - * correct to break out of the loop here: - */ - if ((flags & SPLICE_F_NONBLOCK) && (read_len < max_read_len)) - break; + if (ret < read_len) + goto out_release; } pipe->nrbufs = pipe->curbuf = 0; - return bytes; out_release: @@ -1066,6 +1110,50 @@ out_release: return bytes; return ret; + +} +EXPORT_SYMBOL(splice_direct_to_actor); + +static int direct_splice_actor(struct pipe_inode_info *pipe, + struct splice_desc *sd) +{ + struct file *file = sd->u.file; + + return do_splice_from(pipe, file, &sd->pos, sd->total_len, sd->flags); +} + +/** + * do_splice_direct - splices data directly between two files + * @in: file to splice from + * @ppos: input file offset + * @out: file to splice to + * @len: number of bytes to splice + * @flags: splice modifier flags + * + * Description: + * For use by do_sendfile(). splice can easily emulate sendfile, but + * doing it in the application would incur an extra system call + * (splice in + splice out, as compared to just sendfile()). So this helper + * can splice directly through a process-private pipe. + * + */ +long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, + size_t len, unsigned int flags) +{ + struct splice_desc sd = { + .len = len, + .total_len = len, + .flags = flags, + .pos = *ppos, + .u.file = out, + }; + long ret; + + ret = splice_direct_to_actor(in, &sd, direct_splice_actor); + if (ret > 0) + *ppos += ret; + + return ret; } /* @@ -1248,28 +1336,131 @@ static int get_iovec_page_array(const struct iovec __user *iov, return error; } +static int pipe_to_user(struct pipe_inode_info *pipe, struct pipe_buffer *buf, + struct splice_desc *sd) +{ + char *src; + int ret; + + ret = buf->ops->confirm(pipe, buf); + if (unlikely(ret)) + return ret; + + /* + * See if we can use the atomic maps, by prefaulting in the + * pages and doing an atomic copy + */ + if (!fault_in_pages_writeable(sd->u.userptr, sd->len)) { + src = buf->ops->map(pipe, buf, 1); + ret = __copy_to_user_inatomic(sd->u.userptr, src + buf->offset, + sd->len); + buf->ops->unmap(pipe, buf, src); + if (!ret) { + ret = sd->len; + goto out; + } + } + + /* + * No dice, use slow non-atomic map and copy + */ + src = buf->ops->map(pipe, buf, 0); + + ret = sd->len; + if (copy_to_user(sd->u.userptr, src + buf->offset, sd->len)) + ret = -EFAULT; + +out: + if (ret > 0) + sd->u.userptr += ret; + buf->ops->unmap(pipe, buf, src); + return ret; +} + +/* + * For lack of a better implementation, implement vmsplice() to userspace + * as a simple copy of the pipes pages to the user iov. + */ +static long vmsplice_to_user(struct file *file, const struct iovec __user *iov, + unsigned long nr_segs, unsigned int flags) +{ + struct pipe_inode_info *pipe; + struct splice_desc sd; + ssize_t size; + int error; + long ret; + + pipe = pipe_info(file->f_path.dentry->d_inode); + if (!pipe) + return -EBADF; + + if (pipe->inode) + mutex_lock(&pipe->inode->i_mutex); + + error = ret = 0; + while (nr_segs) { + void __user *base; + size_t len; + + /* + * Get user address base and length for this iovec. + */ + error = get_user(base, &iov->iov_base); + if (unlikely(error)) + break; + error = get_user(len, &iov->iov_len); + if (unlikely(error)) + break; + + /* + * Sanity check this iovec. 0 read succeeds. + */ + if (unlikely(!len)) + break; + if (unlikely(!base)) { + error = -EFAULT; + break; + } + + sd.len = 0; + sd.total_len = len; + sd.flags = flags; + sd.u.userptr = base; + sd.pos = 0; + + size = __splice_from_pipe(pipe, &sd, pipe_to_user); + if (size < 0) { + if (!ret) + ret = size; + + break; + } + + ret += size; + + if (size < len) + break; + + nr_segs--; + iov++; + } + + if (pipe->inode) + mutex_unlock(&pipe->inode->i_mutex); + + if (!ret) + ret = error; + + return ret; +} + /* * vmsplice splices a user address range into a pipe. It can be thought of * as splice-from-memory, where the regular splice is splice-from-file (or * to file). In both cases the output is a pipe, naturally. - * - * Note that vmsplice only supports splicing _from_ user memory to a pipe, - * not the other way around. Splicing from user memory is a simple operation - * that can be supported without any funky alignment restrictions or nasty - * vm tricks. We simply map in the user memory and fill them into a pipe. - * The reverse isn't quite as easy, though. There are two possible solutions - * for that: - * - * - memcpy() the data internally, at which point we might as well just - * do a regular read() on the buffer anyway. - * - Lots of nasty vm tricks, that are neither fast nor flexible (it - * has restriction limitations on both ends of the pipe). - * - * Alas, it isn't here. - * */ -static long do_vmsplice(struct file *file, const struct iovec __user *iov, - unsigned long nr_segs, unsigned int flags) +static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov, + unsigned long nr_segs, unsigned int flags) { struct pipe_inode_info *pipe; struct page *pages[PIPE_BUFFERS]; @@ -1284,10 +1475,6 @@ static long do_vmsplice(struct file *file, const struct iovec __user *iov, pipe = pipe_info(file->f_path.dentry->d_inode); if (!pipe) return -EBADF; - if (unlikely(nr_segs > UIO_MAXIOV)) - return -EINVAL; - else if (unlikely(!nr_segs)) - return 0; spd.nr_pages = get_iovec_page_array(iov, nr_segs, pages, partial, flags & SPLICE_F_GIFT); @@ -1297,6 +1484,22 @@ static long do_vmsplice(struct file *file, const struct iovec __user *iov, return splice_to_pipe(pipe, &spd); } +/* + * Note that vmsplice only really supports true splicing _from_ user memory + * to a pipe, not the other way around. Splicing from user memory is a simple + * operation that can be supported without any funky alignment restrictions + * or nasty vm tricks. We simply map in the user memory and fill them into + * a pipe. The reverse isn't quite as easy, though. There are two possible + * solutions for that: + * + * - memcpy() the data internally, at which point we might as well just + * do a regular read() on the buffer anyway. + * - Lots of nasty vm tricks, that are neither fast nor flexible (it + * has restriction limitations on both ends of the pipe). + * + * Currently we punt and implement it as a normal copy, see pipe_to_user(). + * + */ asmlinkage long sys_vmsplice(int fd, const struct iovec __user *iov, unsigned long nr_segs, unsigned int flags) { @@ -1304,11 +1507,18 @@ asmlinkage long sys_vmsplice(int fd, const struct iovec __user *iov, long error; int fput; + if (unlikely(nr_segs > UIO_MAXIOV)) + return -EINVAL; + else if (unlikely(!nr_segs)) + return 0; + error = -EBADF; file = fget_light(fd, &fput); if (file) { if (file->f_mode & FMODE_WRITE) - error = do_vmsplice(file, iov, nr_segs, flags); + error = vmsplice_to_pipe(file, iov, nr_segs, flags); + else if (file->f_mode & FMODE_READ) + error = vmsplice_to_user(file, iov, nr_segs, flags); fput_light(file, fput); } diff --git a/fs/sysfs/bin.c b/fs/sysfs/bin.c index d3b9f5f07db..135353f8a29 100644 --- a/fs/sysfs/bin.c +++ b/fs/sysfs/bin.c @@ -20,29 +20,41 @@ #include "sysfs.h" +struct bin_buffer { + struct mutex mutex; + void *buffer; + int mmapped; +}; + static int fill_read(struct dentry *dentry, char *buffer, loff_t off, size_t count) { - struct bin_attribute * attr = to_bin_attr(dentry); - struct kobject * kobj = to_kobj(dentry->d_parent); + struct sysfs_dirent *attr_sd = dentry->d_fsdata; + struct bin_attribute *attr = attr_sd->s_elem.bin_attr.bin_attr; + struct kobject *kobj = attr_sd->s_parent->s_elem.dir.kobj; + int rc; + + /* need attr_sd for attr, its parent for kobj */ + if (!sysfs_get_active_two(attr_sd)) + return -ENODEV; - if (!attr->read) - return -EIO; + rc = -EIO; + if (attr->read) + rc = attr->read(kobj, attr, buffer, off, count); - return attr->read(kobj, buffer, off, count); + sysfs_put_active_two(attr_sd); + + return rc; } static ssize_t -read(struct file * file, char __user * userbuf, size_t count, loff_t * off) +read(struct file *file, char __user *userbuf, size_t bytes, loff_t *off) { - char *buffer = file->private_data; + struct bin_buffer *bb = file->private_data; struct dentry *dentry = file->f_path.dentry; int size = dentry->d_inode->i_size; loff_t offs = *off; - int ret; - - if (count > PAGE_SIZE) - count = PAGE_SIZE; + int count = min_t(size_t, bytes, PAGE_SIZE); if (size) { if (offs > size) @@ -51,43 +63,56 @@ read(struct file * file, char __user * userbuf, size_t count, loff_t * off) count = size - offs; } - ret = fill_read(dentry, buffer, offs, count); - if (ret < 0) - return ret; - count = ret; + mutex_lock(&bb->mutex); + + count = fill_read(dentry, bb->buffer, offs, count); + if (count < 0) + goto out_unlock; - if (copy_to_user(userbuf, buffer, count)) - return -EFAULT; + if (copy_to_user(userbuf, bb->buffer, count)) { + count = -EFAULT; + goto out_unlock; + } - pr_debug("offs = %lld, *off = %lld, count = %zd\n", offs, *off, count); + pr_debug("offs = %lld, *off = %lld, count = %d\n", offs, *off, count); *off = offs + count; + out_unlock: + mutex_unlock(&bb->mutex); return count; } static int flush_write(struct dentry *dentry, char *buffer, loff_t offset, size_t count) { - struct bin_attribute *attr = to_bin_attr(dentry); - struct kobject *kobj = to_kobj(dentry->d_parent); + struct sysfs_dirent *attr_sd = dentry->d_fsdata; + struct bin_attribute *attr = attr_sd->s_elem.bin_attr.bin_attr; + struct kobject *kobj = attr_sd->s_parent->s_elem.dir.kobj; + int rc; + + /* need attr_sd for attr, its parent for kobj */ + if (!sysfs_get_active_two(attr_sd)) + return -ENODEV; + + rc = -EIO; + if (attr->write) + rc = attr->write(kobj, attr, buffer, offset, count); - if (!attr->write) - return -EIO; + sysfs_put_active_two(attr_sd); - return attr->write(kobj, buffer, offset, count); + return rc; } -static ssize_t write(struct file * file, const char __user * userbuf, - size_t count, loff_t * off) +static ssize_t write(struct file *file, const char __user *userbuf, + size_t bytes, loff_t *off) { - char *buffer = file->private_data; + struct bin_buffer *bb = file->private_data; struct dentry *dentry = file->f_path.dentry; int size = dentry->d_inode->i_size; loff_t offs = *off; + int count = min_t(size_t, bytes, PAGE_SIZE); - if (count > PAGE_SIZE) - count = PAGE_SIZE; if (size) { if (offs > size) return 0; @@ -95,72 +120,100 @@ static ssize_t write(struct file * file, const char __user * userbuf, count = size - offs; } - if (copy_from_user(buffer, userbuf, count)) - return -EFAULT; + mutex_lock(&bb->mutex); - count = flush_write(dentry, buffer, offs, count); + if (copy_from_user(bb->buffer, userbuf, count)) { + count = -EFAULT; + goto out_unlock; + } + + count = flush_write(dentry, bb->buffer, offs, count); if (count > 0) *off = offs + count; + + out_unlock: + mutex_unlock(&bb->mutex); return count; } static int mmap(struct file *file, struct vm_area_struct *vma) { - struct dentry *dentry = file->f_path.dentry; - struct bin_attribute *attr = to_bin_attr(dentry); - struct kobject *kobj = to_kobj(dentry->d_parent); + struct bin_buffer *bb = file->private_data; + struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; + struct bin_attribute *attr = attr_sd->s_elem.bin_attr.bin_attr; + struct kobject *kobj = attr_sd->s_parent->s_elem.dir.kobj; + int rc; + + mutex_lock(&bb->mutex); + + /* need attr_sd for attr, its parent for kobj */ + if (!sysfs_get_active_two(attr_sd)) + return -ENODEV; - if (!attr->mmap) - return -EINVAL; + rc = -EINVAL; + if (attr->mmap) + rc = attr->mmap(kobj, attr, vma); - return attr->mmap(kobj, attr, vma); + if (rc == 0 && !bb->mmapped) + bb->mmapped = 1; + else + sysfs_put_active_two(attr_sd); + + mutex_unlock(&bb->mutex); + + return rc; } static int open(struct inode * inode, struct file * file) { - struct kobject *kobj = sysfs_get_kobject(file->f_path.dentry->d_parent); - struct bin_attribute * attr = to_bin_attr(file->f_path.dentry); - int error = -EINVAL; - - if (!kobj || !attr) - goto Done; + struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; + struct bin_attribute *attr = attr_sd->s_elem.bin_attr.bin_attr; + struct bin_buffer *bb = NULL; + int error; - /* Grab the module reference for this attribute if we have one */ - error = -ENODEV; - if (!try_module_get(attr->attr.owner)) - goto Done; + /* need attr_sd for attr */ + if (!sysfs_get_active(attr_sd)) + return -ENODEV; error = -EACCES; if ((file->f_mode & FMODE_WRITE) && !(attr->write || attr->mmap)) - goto Error; + goto err_out; if ((file->f_mode & FMODE_READ) && !(attr->read || attr->mmap)) - goto Error; + goto err_out; error = -ENOMEM; - file->private_data = kmalloc(PAGE_SIZE, GFP_KERNEL); - if (!file->private_data) - goto Error; - - error = 0; - goto Done; - - Error: - module_put(attr->attr.owner); - Done: - if (error) - kobject_put(kobj); + bb = kzalloc(sizeof(*bb), GFP_KERNEL); + if (!bb) + goto err_out; + + bb->buffer = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!bb->buffer) + goto err_out; + + mutex_init(&bb->mutex); + file->private_data = bb; + + /* open succeeded, put active reference and pin attr_sd */ + sysfs_put_active(attr_sd); + sysfs_get(attr_sd); + return 0; + + err_out: + sysfs_put_active(attr_sd); + kfree(bb); return error; } static int release(struct inode * inode, struct file * file) { - struct kobject * kobj = to_kobj(file->f_path.dentry->d_parent); - struct bin_attribute * attr = to_bin_attr(file->f_path.dentry); - u8 * buffer = file->private_data; - - kobject_put(kobj); - module_put(attr->attr.owner); - kfree(buffer); + struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; + struct bin_buffer *bb = file->private_data; + + if (bb->mmapped) + sysfs_put_active_two(attr_sd); + sysfs_put(attr_sd); + kfree(bb->buffer); + kfree(bb); return 0; } @@ -181,9 +234,9 @@ const struct file_operations bin_fops = { int sysfs_create_bin_file(struct kobject * kobj, struct bin_attribute * attr) { - BUG_ON(!kobj || !kobj->dentry || !attr); + BUG_ON(!kobj || !kobj->sd || !attr); - return sysfs_add_file(kobj->dentry, &attr->attr, SYSFS_KOBJ_BIN_ATTR); + return sysfs_add_file(kobj->sd, &attr->attr, SYSFS_KOBJ_BIN_ATTR); } @@ -195,7 +248,7 @@ int sysfs_create_bin_file(struct kobject * kobj, struct bin_attribute * attr) void sysfs_remove_bin_file(struct kobject * kobj, struct bin_attribute * attr) { - if (sysfs_hash_and_remove(kobj->dentry, attr->attr.name) < 0) { + if (sysfs_hash_and_remove(kobj->sd, attr->attr.name) < 0) { printk(KERN_ERR "%s: " "bad dentry or inode or no such file: \"%s\"\n", __FUNCTION__, attr->attr.name); diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index c4342a01997..aee966c44aa 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -9,21 +9,337 @@ #include <linux/module.h> #include <linux/kobject.h> #include <linux/namei.h> +#include <linux/idr.h> +#include <linux/completion.h> #include <asm/semaphore.h> #include "sysfs.h" -DECLARE_RWSEM(sysfs_rename_sem); -spinlock_t sysfs_lock = SPIN_LOCK_UNLOCKED; +DEFINE_MUTEX(sysfs_mutex); +spinlock_t sysfs_assoc_lock = SPIN_LOCK_UNLOCKED; + +static spinlock_t sysfs_ino_lock = SPIN_LOCK_UNLOCKED; +static DEFINE_IDA(sysfs_ino_ida); + +/** + * sysfs_link_sibling - link sysfs_dirent into sibling list + * @sd: sysfs_dirent of interest + * + * Link @sd into its sibling list which starts from + * sd->s_parent->s_children. + * + * Locking: + * mutex_lock(sysfs_mutex) + */ +void sysfs_link_sibling(struct sysfs_dirent *sd) +{ + struct sysfs_dirent *parent_sd = sd->s_parent; + + BUG_ON(sd->s_sibling); + sd->s_sibling = parent_sd->s_children; + parent_sd->s_children = sd; +} + +/** + * sysfs_unlink_sibling - unlink sysfs_dirent from sibling list + * @sd: sysfs_dirent of interest + * + * Unlink @sd from its sibling list which starts from + * sd->s_parent->s_children. + * + * Locking: + * mutex_lock(sysfs_mutex) + */ +void sysfs_unlink_sibling(struct sysfs_dirent *sd) +{ + struct sysfs_dirent **pos; + + for (pos = &sd->s_parent->s_children; *pos; pos = &(*pos)->s_sibling) { + if (*pos == sd) { + *pos = sd->s_sibling; + sd->s_sibling = NULL; + break; + } + } +} + +/** + * sysfs_get_dentry - get dentry for the given sysfs_dirent + * @sd: sysfs_dirent of interest + * + * Get dentry for @sd. Dentry is looked up if currently not + * present. This function climbs sysfs_dirent tree till it + * reaches a sysfs_dirent with valid dentry attached and descends + * down from there looking up dentry for each step. + * + * LOCKING: + * Kernel thread context (may sleep) + * + * RETURNS: + * Pointer to found dentry on success, ERR_PTR() value on error. + */ +struct dentry *sysfs_get_dentry(struct sysfs_dirent *sd) +{ + struct sysfs_dirent *cur; + struct dentry *parent_dentry, *dentry; + int i, depth; + + /* Find the first parent which has valid s_dentry and get the + * dentry. + */ + mutex_lock(&sysfs_mutex); + restart0: + spin_lock(&sysfs_assoc_lock); + restart1: + spin_lock(&dcache_lock); + + dentry = NULL; + depth = 0; + cur = sd; + while (!cur->s_dentry || !cur->s_dentry->d_inode) { + if (cur->s_flags & SYSFS_FLAG_REMOVED) { + dentry = ERR_PTR(-ENOENT); + depth = 0; + break; + } + cur = cur->s_parent; + depth++; + } + if (!IS_ERR(dentry)) + dentry = dget_locked(cur->s_dentry); + + spin_unlock(&dcache_lock); + spin_unlock(&sysfs_assoc_lock); + + /* from the found dentry, look up depth times */ + while (depth--) { + /* find and get depth'th ancestor */ + for (cur = sd, i = 0; cur && i < depth; i++) + cur = cur->s_parent; + + /* This can happen if tree structure was modified due + * to move/rename. Restart. + */ + if (i != depth) { + dput(dentry); + goto restart0; + } + + sysfs_get(cur); + + mutex_unlock(&sysfs_mutex); + + /* look it up */ + parent_dentry = dentry; + dentry = lookup_one_len_kern(cur->s_name, parent_dentry, + strlen(cur->s_name)); + dput(parent_dentry); + + if (IS_ERR(dentry)) { + sysfs_put(cur); + return dentry; + } + + mutex_lock(&sysfs_mutex); + spin_lock(&sysfs_assoc_lock); + + /* This, again, can happen if tree structure has + * changed and we looked up the wrong thing. Restart. + */ + if (cur->s_dentry != dentry) { + dput(dentry); + sysfs_put(cur); + goto restart1; + } + + spin_unlock(&sysfs_assoc_lock); + + sysfs_put(cur); + } + + mutex_unlock(&sysfs_mutex); + return dentry; +} + +/** + * sysfs_get_active - get an active reference to sysfs_dirent + * @sd: sysfs_dirent to get an active reference to + * + * Get an active reference of @sd. This function is noop if @sd + * is NULL. + * + * RETURNS: + * Pointer to @sd on success, NULL on failure. + */ +struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd) +{ + if (unlikely(!sd)) + return NULL; + + while (1) { + int v, t; + + v = atomic_read(&sd->s_active); + if (unlikely(v < 0)) + return NULL; + + t = atomic_cmpxchg(&sd->s_active, v, v + 1); + if (likely(t == v)) + return sd; + if (t < 0) + return NULL; + + cpu_relax(); + } +} + +/** + * sysfs_put_active - put an active reference to sysfs_dirent + * @sd: sysfs_dirent to put an active reference to + * + * Put an active reference to @sd. This function is noop if @sd + * is NULL. + */ +void sysfs_put_active(struct sysfs_dirent *sd) +{ + struct completion *cmpl; + int v; + + if (unlikely(!sd)) + return; + + v = atomic_dec_return(&sd->s_active); + if (likely(v != SD_DEACTIVATED_BIAS)) + return; + + /* atomic_dec_return() is a mb(), we'll always see the updated + * sd->s_sibling. + */ + cmpl = (void *)sd->s_sibling; + complete(cmpl); +} + +/** + * sysfs_get_active_two - get active references to sysfs_dirent and parent + * @sd: sysfs_dirent of interest + * + * Get active reference to @sd and its parent. Parent's active + * reference is grabbed first. This function is noop if @sd is + * NULL. + * + * RETURNS: + * Pointer to @sd on success, NULL on failure. + */ +struct sysfs_dirent *sysfs_get_active_two(struct sysfs_dirent *sd) +{ + if (sd) { + if (sd->s_parent && unlikely(!sysfs_get_active(sd->s_parent))) + return NULL; + if (unlikely(!sysfs_get_active(sd))) { + sysfs_put_active(sd->s_parent); + return NULL; + } + } + return sd; +} + +/** + * sysfs_put_active_two - put active references to sysfs_dirent and parent + * @sd: sysfs_dirent of interest + * + * Put active references to @sd and its parent. This function is + * noop if @sd is NULL. + */ +void sysfs_put_active_two(struct sysfs_dirent *sd) +{ + if (sd) { + sysfs_put_active(sd); + sysfs_put_active(sd->s_parent); + } +} + +/** + * sysfs_deactivate - deactivate sysfs_dirent + * @sd: sysfs_dirent to deactivate + * + * Deny new active references and drain existing ones. + */ +static void sysfs_deactivate(struct sysfs_dirent *sd) +{ + DECLARE_COMPLETION_ONSTACK(wait); + int v; + + BUG_ON(sd->s_sibling || !(sd->s_flags & SYSFS_FLAG_REMOVED)); + sd->s_sibling = (void *)&wait; + + /* atomic_add_return() is a mb(), put_active() will always see + * the updated sd->s_sibling. + */ + v = atomic_add_return(SD_DEACTIVATED_BIAS, &sd->s_active); + + if (v != SD_DEACTIVATED_BIAS) + wait_for_completion(&wait); + + sd->s_sibling = NULL; +} + +static int sysfs_alloc_ino(ino_t *pino) +{ + int ino, rc; + + retry: + spin_lock(&sysfs_ino_lock); + rc = ida_get_new_above(&sysfs_ino_ida, 2, &ino); + spin_unlock(&sysfs_ino_lock); + + if (rc == -EAGAIN) { + if (ida_pre_get(&sysfs_ino_ida, GFP_KERNEL)) + goto retry; + rc = -ENOMEM; + } + + *pino = ino; + return rc; +} + +static void sysfs_free_ino(ino_t ino) +{ + spin_lock(&sysfs_ino_lock); + ida_remove(&sysfs_ino_ida, ino); + spin_unlock(&sysfs_ino_lock); +} + +void release_sysfs_dirent(struct sysfs_dirent * sd) +{ + struct sysfs_dirent *parent_sd; + + repeat: + /* Moving/renaming is always done while holding reference. + * sd->s_parent won't change beneath us. + */ + parent_sd = sd->s_parent; + + if (sysfs_type(sd) == SYSFS_KOBJ_LINK) + sysfs_put(sd->s_elem.symlink.target_sd); + if (sysfs_type(sd) & SYSFS_COPY_NAME) + kfree(sd->s_name); + kfree(sd->s_iattr); + sysfs_free_ino(sd->s_ino); + kmem_cache_free(sysfs_dir_cachep, sd); + + sd = parent_sd; + if (sd && atomic_dec_and_test(&sd->s_count)) + goto repeat; +} static void sysfs_d_iput(struct dentry * dentry, struct inode * inode) { struct sysfs_dirent * sd = dentry->d_fsdata; if (sd) { - /* sd->s_dentry is protected with sysfs_lock. This - * allows sysfs_drop_dentry() to dereference it. + /* sd->s_dentry is protected with sysfs_assoc_lock. + * This allows sysfs_drop_dentry() to dereference it. */ - spin_lock(&sysfs_lock); + spin_lock(&sysfs_assoc_lock); /* The dentry might have been deleted or another * lookup could have happened updating sd->s_dentry to @@ -32,7 +348,7 @@ static void sysfs_d_iput(struct dentry * dentry, struct inode * inode) */ if (sd->s_dentry == dentry) sd->s_dentry = NULL; - spin_unlock(&sysfs_lock); + spin_unlock(&sysfs_assoc_lock); sysfs_put(sd); } iput(inode); @@ -42,260 +358,402 @@ static struct dentry_operations sysfs_dentry_ops = { .d_iput = sysfs_d_iput, }; -static unsigned int sysfs_inode_counter; -ino_t sysfs_get_inum(void) +struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type) { - if (unlikely(sysfs_inode_counter < 3)) - sysfs_inode_counter = 3; - return sysfs_inode_counter++; -} + char *dup_name = NULL; + struct sysfs_dirent *sd = NULL; -/* - * Allocates a new sysfs_dirent and links it to the parent sysfs_dirent - */ -static struct sysfs_dirent * __sysfs_new_dirent(void * element) -{ - struct sysfs_dirent * sd; + if (type & SYSFS_COPY_NAME) { + name = dup_name = kstrdup(name, GFP_KERNEL); + if (!name) + goto err_out; + } sd = kmem_cache_zalloc(sysfs_dir_cachep, GFP_KERNEL); if (!sd) - return NULL; + goto err_out; + + if (sysfs_alloc_ino(&sd->s_ino)) + goto err_out; - sd->s_ino = sysfs_get_inum(); atomic_set(&sd->s_count, 1); + atomic_set(&sd->s_active, 0); atomic_set(&sd->s_event, 1); - INIT_LIST_HEAD(&sd->s_children); - INIT_LIST_HEAD(&sd->s_sibling); - sd->s_element = element; + + sd->s_name = name; + sd->s_mode = mode; + sd->s_flags = type; return sd; + + err_out: + kfree(dup_name); + kmem_cache_free(sysfs_dir_cachep, sd); + return NULL; } -static void __sysfs_list_dirent(struct sysfs_dirent *parent_sd, - struct sysfs_dirent *sd) +/** + * sysfs_attach_dentry - associate sysfs_dirent with dentry + * @sd: target sysfs_dirent + * @dentry: dentry to associate + * + * Associate @sd with @dentry. This is protected by + * sysfs_assoc_lock to avoid race with sysfs_d_iput(). + * + * LOCKING: + * mutex_lock(sysfs_mutex) + */ +static void sysfs_attach_dentry(struct sysfs_dirent *sd, struct dentry *dentry) { - if (sd) - list_add(&sd->s_sibling, &parent_sd->s_children); + dentry->d_op = &sysfs_dentry_ops; + dentry->d_fsdata = sysfs_get(sd); + + /* protect sd->s_dentry against sysfs_d_iput */ + spin_lock(&sysfs_assoc_lock); + sd->s_dentry = dentry; + spin_unlock(&sysfs_assoc_lock); + + d_rehash(dentry); } -static struct sysfs_dirent * sysfs_new_dirent(struct sysfs_dirent *parent_sd, - void * element) +static int sysfs_ilookup_test(struct inode *inode, void *arg) { - struct sysfs_dirent *sd; - sd = __sysfs_new_dirent(element); - __sysfs_list_dirent(parent_sd, sd); - return sd; + struct sysfs_dirent *sd = arg; + return inode->i_ino == sd->s_ino; } -/* +/** + * sysfs_addrm_start - prepare for sysfs_dirent add/remove + * @acxt: pointer to sysfs_addrm_cxt to be used + * @parent_sd: parent sysfs_dirent * - * Return -EEXIST if there is already a sysfs element with the same name for - * the same parent. + * This function is called when the caller is about to add or + * remove sysfs_dirent under @parent_sd. This function acquires + * sysfs_mutex, grabs inode for @parent_sd if available and lock + * i_mutex of it. @acxt is used to keep and pass context to + * other addrm functions. * - * called with parent inode's i_mutex held + * LOCKING: + * Kernel thread context (may sleep). sysfs_mutex is locked on + * return. i_mutex of parent inode is locked on return if + * available. */ -int sysfs_dirent_exist(struct sysfs_dirent *parent_sd, - const unsigned char *new) +void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt, + struct sysfs_dirent *parent_sd) { - struct sysfs_dirent * sd; + struct inode *inode; - list_for_each_entry(sd, &parent_sd->s_children, s_sibling) { - if (sd->s_element) { - const unsigned char *existing = sysfs_get_name(sd); - if (strcmp(existing, new)) - continue; - else - return -EEXIST; - } - } + memset(acxt, 0, sizeof(*acxt)); + acxt->parent_sd = parent_sd; - return 0; + /* Lookup parent inode. inode initialization and I_NEW + * clearing are protected by sysfs_mutex. By grabbing it and + * looking up with _nowait variant, inode state can be + * determined reliably. + */ + mutex_lock(&sysfs_mutex); + + inode = ilookup5_nowait(sysfs_sb, parent_sd->s_ino, sysfs_ilookup_test, + parent_sd); + + if (inode && !(inode->i_state & I_NEW)) { + /* parent inode available */ + acxt->parent_inode = inode; + + /* sysfs_mutex is below i_mutex in lock hierarchy. + * First, trylock i_mutex. If fails, unlock + * sysfs_mutex and lock them in order. + */ + if (!mutex_trylock(&inode->i_mutex)) { + mutex_unlock(&sysfs_mutex); + mutex_lock(&inode->i_mutex); + mutex_lock(&sysfs_mutex); + } + } else + iput(inode); } +/** + * sysfs_add_one - add sysfs_dirent to parent + * @acxt: addrm context to use + * @sd: sysfs_dirent to be added + * + * Get @acxt->parent_sd and set sd->s_parent to it and increment + * nlink of parent inode if @sd is a directory. @sd is NOT + * linked into the children list of the parent. The caller + * should invoke sysfs_link_sibling() after this function + * completes if @sd needs to be on the children list. + * + * This function should be called between calls to + * sysfs_addrm_start() and sysfs_addrm_finish() and should be + * passed the same @acxt as passed to sysfs_addrm_start(). + * + * LOCKING: + * Determined by sysfs_addrm_start(). + */ +void sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd) +{ + sd->s_parent = sysfs_get(acxt->parent_sd); + + if (sysfs_type(sd) == SYSFS_DIR && acxt->parent_inode) + inc_nlink(acxt->parent_inode); + + acxt->cnt++; +} -static struct sysfs_dirent * -__sysfs_make_dirent(struct dentry *dentry, void *element, mode_t mode, int type) +/** + * sysfs_remove_one - remove sysfs_dirent from parent + * @acxt: addrm context to use + * @sd: sysfs_dirent to be added + * + * Mark @sd removed and drop nlink of parent inode if @sd is a + * directory. @sd is NOT unlinked from the children list of the + * parent. The caller is repsonsible for removing @sd from the + * children list before calling this function. + * + * This function should be called between calls to + * sysfs_addrm_start() and sysfs_addrm_finish() and should be + * passed the same @acxt as passed to sysfs_addrm_start(). + * + * LOCKING: + * Determined by sysfs_addrm_start(). + */ +void sysfs_remove_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd) { - struct sysfs_dirent * sd; + BUG_ON(sd->s_sibling || (sd->s_flags & SYSFS_FLAG_REMOVED)); - sd = __sysfs_new_dirent(element); - if (!sd) - goto out; + sd->s_flags |= SYSFS_FLAG_REMOVED; + sd->s_sibling = acxt->removed; + acxt->removed = sd; - sd->s_mode = mode; - sd->s_type = type; - sd->s_dentry = dentry; - if (dentry) { - dentry->d_fsdata = sysfs_get(sd); - dentry->d_op = &sysfs_dentry_ops; - } + if (sysfs_type(sd) == SYSFS_DIR && acxt->parent_inode) + drop_nlink(acxt->parent_inode); -out: - return sd; + acxt->cnt++; } -int sysfs_make_dirent(struct sysfs_dirent * parent_sd, struct dentry * dentry, - void * element, umode_t mode, int type) +/** + * sysfs_drop_dentry - drop dentry for the specified sysfs_dirent + * @sd: target sysfs_dirent + * + * Drop dentry for @sd. @sd must have been unlinked from its + * parent on entry to this function such that it can't be looked + * up anymore. + * + * @sd->s_dentry which is protected with sysfs_assoc_lock points + * to the currently associated dentry but we're not holding a + * reference to it and racing with dput(). Grab dcache_lock and + * verify dentry before dropping it. If @sd->s_dentry is NULL or + * dput() beats us, no need to bother. + */ +static void sysfs_drop_dentry(struct sysfs_dirent *sd) { - struct sysfs_dirent *sd; + struct dentry *dentry = NULL; + struct inode *inode; + + /* We're not holding a reference to ->s_dentry dentry but the + * field will stay valid as long as sysfs_assoc_lock is held. + */ + spin_lock(&sysfs_assoc_lock); + spin_lock(&dcache_lock); + + /* drop dentry if it's there and dput() didn't kill it yet */ + if (sd->s_dentry && sd->s_dentry->d_inode) { + dentry = dget_locked(sd->s_dentry); + spin_lock(&dentry->d_lock); + __d_drop(dentry); + spin_unlock(&dentry->d_lock); + } - sd = __sysfs_make_dirent(dentry, element, mode, type); - __sysfs_list_dirent(parent_sd, sd); + spin_unlock(&dcache_lock); + spin_unlock(&sysfs_assoc_lock); - return sd ? 0 : -ENOMEM; + /* dentries for shadowed inodes are pinned, unpin */ + if (dentry && sysfs_is_shadowed_inode(dentry->d_inode)) + dput(dentry); + dput(dentry); + + /* adjust nlink and update timestamp */ + inode = ilookup(sysfs_sb, sd->s_ino); + if (inode) { + mutex_lock(&inode->i_mutex); + + inode->i_ctime = CURRENT_TIME; + drop_nlink(inode); + if (sysfs_type(sd) == SYSFS_DIR) + drop_nlink(inode); + + mutex_unlock(&inode->i_mutex); + iput(inode); + } } -static int init_dir(struct inode * inode) +/** + * sysfs_addrm_finish - finish up sysfs_dirent add/remove + * @acxt: addrm context to finish up + * + * Finish up sysfs_dirent add/remove. Resources acquired by + * sysfs_addrm_start() are released and removed sysfs_dirents are + * cleaned up. Timestamps on the parent inode are updated. + * + * LOCKING: + * All mutexes acquired by sysfs_addrm_start() are released. + * + * RETURNS: + * Number of added/removed sysfs_dirents since sysfs_addrm_start(). + */ +int sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt) { - inode->i_op = &sysfs_dir_inode_operations; - inode->i_fop = &sysfs_dir_operations; + /* release resources acquired by sysfs_addrm_start() */ + mutex_unlock(&sysfs_mutex); + if (acxt->parent_inode) { + struct inode *inode = acxt->parent_inode; - /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inc_nlink(inode); - return 0; + /* if added/removed, update timestamps on the parent */ + if (acxt->cnt) + inode->i_ctime = inode->i_mtime = CURRENT_TIME; + + mutex_unlock(&inode->i_mutex); + iput(inode); + } + + /* kill removed sysfs_dirents */ + while (acxt->removed) { + struct sysfs_dirent *sd = acxt->removed; + + acxt->removed = sd->s_sibling; + sd->s_sibling = NULL; + + sysfs_drop_dentry(sd); + sysfs_deactivate(sd); + sysfs_put(sd); + } + + return acxt->cnt; } -static int init_file(struct inode * inode) +/** + * sysfs_find_dirent - find sysfs_dirent with the given name + * @parent_sd: sysfs_dirent to search under + * @name: name to look for + * + * Look for sysfs_dirent with name @name under @parent_sd. + * + * LOCKING: + * mutex_lock(sysfs_mutex) + * + * RETURNS: + * Pointer to sysfs_dirent if found, NULL if not. + */ +struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd, + const unsigned char *name) { - inode->i_size = PAGE_SIZE; - inode->i_fop = &sysfs_file_operations; - return 0; + struct sysfs_dirent *sd; + + for (sd = parent_sd->s_children; sd; sd = sd->s_sibling) + if (sysfs_type(sd) && !strcmp(sd->s_name, name)) + return sd; + return NULL; } -static int init_symlink(struct inode * inode) +/** + * sysfs_get_dirent - find and get sysfs_dirent with the given name + * @parent_sd: sysfs_dirent to search under + * @name: name to look for + * + * Look for sysfs_dirent with name @name under @parent_sd and get + * it if found. + * + * LOCKING: + * Kernel thread context (may sleep). Grabs sysfs_mutex. + * + * RETURNS: + * Pointer to sysfs_dirent if found, NULL if not. + */ +struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd, + const unsigned char *name) { - inode->i_op = &sysfs_symlink_inode_operations; - return 0; + struct sysfs_dirent *sd; + + mutex_lock(&sysfs_mutex); + sd = sysfs_find_dirent(parent_sd, name); + sysfs_get(sd); + mutex_unlock(&sysfs_mutex); + + return sd; } -static int create_dir(struct kobject * k, struct dentry * p, - const char * n, struct dentry ** d) +static int create_dir(struct kobject *kobj, struct sysfs_dirent *parent_sd, + const char *name, struct sysfs_dirent **p_sd) { - int error; umode_t mode = S_IFDIR| S_IRWXU | S_IRUGO | S_IXUGO; + struct sysfs_addrm_cxt acxt; + struct sysfs_dirent *sd; - mutex_lock(&p->d_inode->i_mutex); - *d = lookup_one_len(n, p, strlen(n)); - if (!IS_ERR(*d)) { - if (sysfs_dirent_exist(p->d_fsdata, n)) - error = -EEXIST; - else - error = sysfs_make_dirent(p->d_fsdata, *d, k, mode, - SYSFS_DIR); - if (!error) { - error = sysfs_create(*d, mode, init_dir); - if (!error) { - inc_nlink(p->d_inode); - (*d)->d_op = &sysfs_dentry_ops; - d_rehash(*d); - } - } - if (error && (error != -EEXIST)) { - struct sysfs_dirent *sd = (*d)->d_fsdata; - if (sd) { - list_del_init(&sd->s_sibling); - sysfs_put(sd); - } - d_drop(*d); - } - dput(*d); - } else - error = PTR_ERR(*d); - mutex_unlock(&p->d_inode->i_mutex); - return error; -} + /* allocate */ + sd = sysfs_new_dirent(name, mode, SYSFS_DIR); + if (!sd) + return -ENOMEM; + sd->s_elem.dir.kobj = kobj; + /* link in */ + sysfs_addrm_start(&acxt, parent_sd); + if (!sysfs_find_dirent(parent_sd, name)) { + sysfs_add_one(&acxt, sd); + sysfs_link_sibling(sd); + } + if (sysfs_addrm_finish(&acxt)) { + *p_sd = sd; + return 0; + } -int sysfs_create_subdir(struct kobject * k, const char * n, struct dentry ** d) + sysfs_put(sd); + return -EEXIST; +} + +int sysfs_create_subdir(struct kobject *kobj, const char *name, + struct sysfs_dirent **p_sd) { - return create_dir(k,k->dentry,n,d); + return create_dir(kobj, kobj->sd, name, p_sd); } /** * sysfs_create_dir - create a directory for an object. * @kobj: object we're creating directory for. - * @shadow_parent: parent parent object. + * @shadow_parent: parent object. */ - -int sysfs_create_dir(struct kobject * kobj, struct dentry *shadow_parent) +int sysfs_create_dir(struct kobject *kobj, + struct sysfs_dirent *shadow_parent_sd) { - struct dentry * dentry = NULL; - struct dentry * parent; + struct sysfs_dirent *parent_sd, *sd; int error = 0; BUG_ON(!kobj); - if (shadow_parent) - parent = shadow_parent; + if (shadow_parent_sd) + parent_sd = shadow_parent_sd; else if (kobj->parent) - parent = kobj->parent->dentry; + parent_sd = kobj->parent->sd; else if (sysfs_mount && sysfs_mount->mnt_sb) - parent = sysfs_mount->mnt_sb->s_root; + parent_sd = sysfs_mount->mnt_sb->s_root->d_fsdata; else return -EFAULT; - error = create_dir(kobj,parent,kobject_name(kobj),&dentry); + error = create_dir(kobj, parent_sd, kobject_name(kobj), &sd); if (!error) - kobj->dentry = dentry; + kobj->sd = sd; return error; } -/* attaches attribute's sysfs_dirent to the dentry corresponding to the - * attribute file - */ -static int sysfs_attach_attr(struct sysfs_dirent * sd, struct dentry * dentry) +static int sysfs_count_nlink(struct sysfs_dirent *sd) { - struct attribute * attr = NULL; - struct bin_attribute * bin_attr = NULL; - int (* init) (struct inode *) = NULL; - int error = 0; - - if (sd->s_type & SYSFS_KOBJ_BIN_ATTR) { - bin_attr = sd->s_element; - attr = &bin_attr->attr; - } else { - attr = sd->s_element; - init = init_file; - } + struct sysfs_dirent *child; + int nr = 0; - dentry->d_fsdata = sysfs_get(sd); - /* protect sd->s_dentry against sysfs_d_iput */ - spin_lock(&sysfs_lock); - sd->s_dentry = dentry; - spin_unlock(&sysfs_lock); - error = sysfs_create(dentry, (attr->mode & S_IALLUGO) | S_IFREG, init); - if (error) { - sysfs_put(sd); - return error; - } - - if (bin_attr) { - dentry->d_inode->i_size = bin_attr->size; - dentry->d_inode->i_fop = &bin_fops; - } - dentry->d_op = &sysfs_dentry_ops; - d_rehash(dentry); - - return 0; -} - -static int sysfs_attach_link(struct sysfs_dirent * sd, struct dentry * dentry) -{ - int err = 0; - - dentry->d_fsdata = sysfs_get(sd); - /* protect sd->s_dentry against sysfs_d_iput */ - spin_lock(&sysfs_lock); - sd->s_dentry = dentry; - spin_unlock(&sysfs_lock); - err = sysfs_create(dentry, S_IFLNK|S_IRWXUGO, init_symlink); - if (!err) { - dentry->d_op = &sysfs_dentry_ops; - d_rehash(dentry); - } else - sysfs_put(sd); - - return err; + for (child = sd->s_children; child; child = child->s_sibling) + if (sysfs_type(child) == SYSFS_DIR) + nr++; + return nr + 2; } static struct dentry * sysfs_lookup(struct inode *dir, struct dentry *dentry, @@ -303,24 +761,60 @@ static struct dentry * sysfs_lookup(struct inode *dir, struct dentry *dentry, { struct sysfs_dirent * parent_sd = dentry->d_parent->d_fsdata; struct sysfs_dirent * sd; - int err = 0; + struct bin_attribute *bin_attr; + struct inode *inode; + int found = 0; - list_for_each_entry(sd, &parent_sd->s_children, s_sibling) { - if (sd->s_type & SYSFS_NOT_PINNED) { - const unsigned char * name = sysfs_get_name(sd); + for (sd = parent_sd->s_children; sd; sd = sd->s_sibling) { + if (sysfs_type(sd) && + !strcmp(sd->s_name, dentry->d_name.name)) { + found = 1; + break; + } + } - if (strcmp(name, dentry->d_name.name)) - continue; + /* no such entry */ + if (!found) + return NULL; - if (sd->s_type & SYSFS_KOBJ_LINK) - err = sysfs_attach_link(sd, dentry); - else - err = sysfs_attach_attr(sd, dentry); + /* attach dentry and inode */ + inode = sysfs_get_inode(sd); + if (!inode) + return ERR_PTR(-ENOMEM); + + mutex_lock(&sysfs_mutex); + + if (inode->i_state & I_NEW) { + /* initialize inode according to type */ + switch (sysfs_type(sd)) { + case SYSFS_DIR: + inode->i_op = &sysfs_dir_inode_operations; + inode->i_fop = &sysfs_dir_operations; + inode->i_nlink = sysfs_count_nlink(sd); + break; + case SYSFS_KOBJ_ATTR: + inode->i_size = PAGE_SIZE; + inode->i_fop = &sysfs_file_operations; + break; + case SYSFS_KOBJ_BIN_ATTR: + bin_attr = sd->s_elem.bin_attr.bin_attr; + inode->i_size = bin_attr->size; + inode->i_fop = &bin_fops; break; + case SYSFS_KOBJ_LINK: + inode->i_op = &sysfs_symlink_inode_operations; + break; + default: + BUG(); } } - return ERR_PTR(err); + sysfs_instantiate(dentry, inode); + sysfs_attach_dentry(sd, dentry); + + mutex_unlock(&sysfs_mutex); + + return NULL; } const struct inode_operations sysfs_dir_inode_operations = { @@ -328,58 +822,46 @@ const struct inode_operations sysfs_dir_inode_operations = { .setattr = sysfs_setattr, }; -static void remove_dir(struct dentry * d) +static void remove_dir(struct sysfs_dirent *sd) { - struct dentry * parent = dget(d->d_parent); - struct sysfs_dirent * sd; - - mutex_lock(&parent->d_inode->i_mutex); - d_delete(d); - sd = d->d_fsdata; - list_del_init(&sd->s_sibling); - sysfs_put(sd); - if (d->d_inode) - simple_rmdir(parent->d_inode,d); - - pr_debug(" o %s removing done (%d)\n",d->d_name.name, - atomic_read(&d->d_count)); + struct sysfs_addrm_cxt acxt; - mutex_unlock(&parent->d_inode->i_mutex); - dput(parent); + sysfs_addrm_start(&acxt, sd->s_parent); + sysfs_unlink_sibling(sd); + sysfs_remove_one(&acxt, sd); + sysfs_addrm_finish(&acxt); } -void sysfs_remove_subdir(struct dentry * d) +void sysfs_remove_subdir(struct sysfs_dirent *sd) { - remove_dir(d); + remove_dir(sd); } -static void __sysfs_remove_dir(struct dentry *dentry) +static void __sysfs_remove_dir(struct sysfs_dirent *dir_sd) { - struct sysfs_dirent * parent_sd; - struct sysfs_dirent * sd, * tmp; + struct sysfs_addrm_cxt acxt; + struct sysfs_dirent **pos; - dget(dentry); - if (!dentry) + if (!dir_sd) return; - pr_debug("sysfs %s: removing dir\n",dentry->d_name.name); - mutex_lock(&dentry->d_inode->i_mutex); - parent_sd = dentry->d_fsdata; - list_for_each_entry_safe(sd, tmp, &parent_sd->s_children, s_sibling) { - if (!sd->s_element || !(sd->s_type & SYSFS_NOT_PINNED)) - continue; - list_del_init(&sd->s_sibling); - sysfs_drop_dentry(sd, dentry); - sysfs_put(sd); + pr_debug("sysfs %s: removing dir\n", dir_sd->s_name); + sysfs_addrm_start(&acxt, dir_sd); + pos = &dir_sd->s_children; + while (*pos) { + struct sysfs_dirent *sd = *pos; + + if (sysfs_type(sd) && sysfs_type(sd) != SYSFS_DIR) { + *pos = sd->s_sibling; + sd->s_sibling = NULL; + sysfs_remove_one(&acxt, sd); + } else + pos = &(*pos)->s_sibling; } - mutex_unlock(&dentry->d_inode->i_mutex); + sysfs_addrm_finish(&acxt); - remove_dir(dentry); - /** - * Drop reference from dget() on entrance. - */ - dput(dentry); + remove_dir(dir_sd); } /** @@ -393,102 +875,166 @@ static void __sysfs_remove_dir(struct dentry *dentry) void sysfs_remove_dir(struct kobject * kobj) { - __sysfs_remove_dir(kobj->dentry); - kobj->dentry = NULL; + struct sysfs_dirent *sd = kobj->sd; + + spin_lock(&sysfs_assoc_lock); + kobj->sd = NULL; + spin_unlock(&sysfs_assoc_lock); + + __sysfs_remove_dir(sd); } -int sysfs_rename_dir(struct kobject * kobj, struct dentry *new_parent, +int sysfs_rename_dir(struct kobject *kobj, struct sysfs_dirent *new_parent_sd, const char *new_name) { - int error = 0; - struct dentry * new_dentry; + struct sysfs_dirent *sd = kobj->sd; + struct dentry *new_parent = NULL; + struct dentry *old_dentry = NULL, *new_dentry = NULL; + const char *dup_name = NULL; + int error; - if (!new_parent) - return -EFAULT; + /* get dentries */ + old_dentry = sysfs_get_dentry(sd); + if (IS_ERR(old_dentry)) { + error = PTR_ERR(old_dentry); + goto out_dput; + } - down_write(&sysfs_rename_sem); + new_parent = sysfs_get_dentry(new_parent_sd); + if (IS_ERR(new_parent)) { + error = PTR_ERR(new_parent); + goto out_dput; + } + + /* lock new_parent and get dentry for new name */ mutex_lock(&new_parent->d_inode->i_mutex); new_dentry = lookup_one_len(new_name, new_parent, strlen(new_name)); - if (!IS_ERR(new_dentry)) { - /* By allowing two different directories with the - * same d_parent we allow this routine to move - * between different shadows of the same directory - */ - if (kobj->dentry->d_parent->d_inode != new_parent->d_inode) - return -EINVAL; - else if (new_dentry->d_parent->d_inode != new_parent->d_inode) - error = -EINVAL; - else if (new_dentry == kobj->dentry) - error = -EINVAL; - else if (!new_dentry->d_inode) { - error = kobject_set_name(kobj, "%s", new_name); - if (!error) { - struct sysfs_dirent *sd, *parent_sd; - - d_add(new_dentry, NULL); - d_move(kobj->dentry, new_dentry); - - sd = kobj->dentry->d_fsdata; - parent_sd = new_parent->d_fsdata; - - list_del_init(&sd->s_sibling); - list_add(&sd->s_sibling, &parent_sd->s_children); - } - else - d_drop(new_dentry); - } else - error = -EEXIST; - dput(new_dentry); + if (IS_ERR(new_dentry)) { + error = PTR_ERR(new_dentry); + goto out_unlock; } - mutex_unlock(&new_parent->d_inode->i_mutex); - up_write(&sysfs_rename_sem); + /* By allowing two different directories with the same + * d_parent we allow this routine to move between different + * shadows of the same directory + */ + error = -EINVAL; + if (old_dentry->d_parent->d_inode != new_parent->d_inode || + new_dentry->d_parent->d_inode != new_parent->d_inode || + old_dentry == new_dentry) + goto out_unlock; + + error = -EEXIST; + if (new_dentry->d_inode) + goto out_unlock; + + /* rename kobject and sysfs_dirent */ + error = -ENOMEM; + new_name = dup_name = kstrdup(new_name, GFP_KERNEL); + if (!new_name) + goto out_drop; + + error = kobject_set_name(kobj, "%s", new_name); + if (error) + goto out_drop; + + dup_name = sd->s_name; + sd->s_name = new_name; + + /* move under the new parent */ + d_add(new_dentry, NULL); + d_move(sd->s_dentry, new_dentry); + + mutex_lock(&sysfs_mutex); + + sysfs_unlink_sibling(sd); + sysfs_get(new_parent_sd); + sysfs_put(sd->s_parent); + sd->s_parent = new_parent_sd; + sysfs_link_sibling(sd); + + mutex_unlock(&sysfs_mutex); + + error = 0; + goto out_unlock; + + out_drop: + d_drop(new_dentry); + out_unlock: + mutex_unlock(&new_parent->d_inode->i_mutex); + out_dput: + kfree(dup_name); + dput(new_parent); + dput(old_dentry); + dput(new_dentry); return error; } -int sysfs_move_dir(struct kobject *kobj, struct kobject *new_parent) +int sysfs_move_dir(struct kobject *kobj, struct kobject *new_parent_kobj) { - struct dentry *old_parent_dentry, *new_parent_dentry, *new_dentry; - struct sysfs_dirent *new_parent_sd, *sd; + struct sysfs_dirent *sd = kobj->sd; + struct sysfs_dirent *new_parent_sd; + struct dentry *old_parent, *new_parent = NULL; + struct dentry *old_dentry = NULL, *new_dentry = NULL; int error; - old_parent_dentry = kobj->parent ? - kobj->parent->dentry : sysfs_mount->mnt_sb->s_root; - new_parent_dentry = new_parent ? - new_parent->dentry : sysfs_mount->mnt_sb->s_root; + BUG_ON(!sd->s_parent); + new_parent_sd = new_parent_kobj->sd ? new_parent_kobj->sd : &sysfs_root; + + /* get dentries */ + old_dentry = sysfs_get_dentry(sd); + if (IS_ERR(old_dentry)) { + error = PTR_ERR(old_dentry); + goto out_dput; + } + old_parent = sd->s_parent->s_dentry; + + new_parent = sysfs_get_dentry(new_parent_sd); + if (IS_ERR(new_parent)) { + error = PTR_ERR(new_parent); + goto out_dput; + } - if (old_parent_dentry->d_inode == new_parent_dentry->d_inode) - return 0; /* nothing to move */ + if (old_parent->d_inode == new_parent->d_inode) { + error = 0; + goto out_dput; /* nothing to move */ + } again: - mutex_lock(&old_parent_dentry->d_inode->i_mutex); - if (!mutex_trylock(&new_parent_dentry->d_inode->i_mutex)) { - mutex_unlock(&old_parent_dentry->d_inode->i_mutex); + mutex_lock(&old_parent->d_inode->i_mutex); + if (!mutex_trylock(&new_parent->d_inode->i_mutex)) { + mutex_unlock(&old_parent->d_inode->i_mutex); goto again; } - new_parent_sd = new_parent_dentry->d_fsdata; - sd = kobj->dentry->d_fsdata; - - new_dentry = lookup_one_len(kobj->name, new_parent_dentry, - strlen(kobj->name)); + new_dentry = lookup_one_len(kobj->name, new_parent, strlen(kobj->name)); if (IS_ERR(new_dentry)) { error = PTR_ERR(new_dentry); - goto out; + goto out_unlock; } else error = 0; d_add(new_dentry, NULL); - d_move(kobj->dentry, new_dentry); + d_move(sd->s_dentry, new_dentry); dput(new_dentry); /* Remove from old parent's list and insert into new parent's list. */ - list_del_init(&sd->s_sibling); - list_add(&sd->s_sibling, &new_parent_sd->s_children); + mutex_lock(&sysfs_mutex); + + sysfs_unlink_sibling(sd); + sysfs_get(new_parent_sd); + sysfs_put(sd->s_parent); + sd->s_parent = new_parent_sd; + sysfs_link_sibling(sd); -out: - mutex_unlock(&new_parent_dentry->d_inode->i_mutex); - mutex_unlock(&old_parent_dentry->d_inode->i_mutex); + mutex_unlock(&sysfs_mutex); + out_unlock: + mutex_unlock(&new_parent->d_inode->i_mutex); + mutex_unlock(&old_parent->d_inode->i_mutex); + out_dput: + dput(new_parent); + dput(old_dentry); + dput(new_dentry); return error; } @@ -496,23 +1042,27 @@ static int sysfs_dir_open(struct inode *inode, struct file *file) { struct dentry * dentry = file->f_path.dentry; struct sysfs_dirent * parent_sd = dentry->d_fsdata; + struct sysfs_dirent * sd; - mutex_lock(&dentry->d_inode->i_mutex); - file->private_data = sysfs_new_dirent(parent_sd, NULL); - mutex_unlock(&dentry->d_inode->i_mutex); - - return file->private_data ? 0 : -ENOMEM; + sd = sysfs_new_dirent("_DIR_", 0, 0); + if (sd) { + mutex_lock(&sysfs_mutex); + sd->s_parent = sysfs_get(parent_sd); + sysfs_link_sibling(sd); + mutex_unlock(&sysfs_mutex); + } + file->private_data = sd; + return sd ? 0 : -ENOMEM; } static int sysfs_dir_close(struct inode *inode, struct file *file) { - struct dentry * dentry = file->f_path.dentry; struct sysfs_dirent * cursor = file->private_data; - mutex_lock(&dentry->d_inode->i_mutex); - list_del_init(&cursor->s_sibling); - mutex_unlock(&dentry->d_inode->i_mutex); + mutex_lock(&sysfs_mutex); + sysfs_unlink_sibling(cursor); + mutex_unlock(&sysfs_mutex); release_sysfs_dirent(cursor); @@ -530,7 +1080,7 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir) struct dentry *dentry = filp->f_path.dentry; struct sysfs_dirent * parent_sd = dentry->d_fsdata; struct sysfs_dirent *cursor = filp->private_data; - struct list_head *p, *q = &cursor->s_sibling; + struct sysfs_dirent **pos; ino_t ino; int i = filp->f_pos; @@ -543,38 +1093,52 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir) i++; /* fallthrough */ case 1: - ino = parent_ino(dentry); + if (parent_sd->s_parent) + ino = parent_sd->s_parent->s_ino; + else + ino = parent_sd->s_ino; if (filldir(dirent, "..", 2, i, ino, DT_DIR) < 0) break; filp->f_pos++; i++; /* fallthrough */ default: + mutex_lock(&sysfs_mutex); + + pos = &parent_sd->s_children; + while (*pos != cursor) + pos = &(*pos)->s_sibling; + + /* unlink cursor */ + *pos = cursor->s_sibling; + if (filp->f_pos == 2) - list_move(q, &parent_sd->s_children); + pos = &parent_sd->s_children; - for (p=q->next; p!= &parent_sd->s_children; p=p->next) { - struct sysfs_dirent *next; + for ( ; *pos; pos = &(*pos)->s_sibling) { + struct sysfs_dirent *next = *pos; const char * name; int len; - next = list_entry(p, struct sysfs_dirent, - s_sibling); - if (!next->s_element) + if (!sysfs_type(next)) continue; - name = sysfs_get_name(next); + name = next->s_name; len = strlen(name); ino = next->s_ino; if (filldir(dirent, name, len, filp->f_pos, ino, dt_type(next)) < 0) - return 0; + break; - list_move(q, p); - p = q; filp->f_pos++; } + + /* put cursor back in */ + cursor->s_sibling = *pos; + *pos = cursor; + + mutex_unlock(&sysfs_mutex); } return 0; } @@ -583,7 +1147,6 @@ static loff_t sysfs_dir_lseek(struct file * file, loff_t offset, int origin) { struct dentry * dentry = file->f_path.dentry; - mutex_lock(&dentry->d_inode->i_mutex); switch (origin) { case 1: offset += file->f_pos; @@ -591,31 +1154,35 @@ static loff_t sysfs_dir_lseek(struct file * file, loff_t offset, int origin) if (offset >= 0) break; default: - mutex_unlock(&file->f_path.dentry->d_inode->i_mutex); return -EINVAL; } if (offset != file->f_pos) { + mutex_lock(&sysfs_mutex); + file->f_pos = offset; if (file->f_pos >= 2) { struct sysfs_dirent *sd = dentry->d_fsdata; struct sysfs_dirent *cursor = file->private_data; - struct list_head *p; + struct sysfs_dirent **pos; loff_t n = file->f_pos - 2; - list_del(&cursor->s_sibling); - p = sd->s_children.next; - while (n && p != &sd->s_children) { - struct sysfs_dirent *next; - next = list_entry(p, struct sysfs_dirent, - s_sibling); - if (next->s_element) + sysfs_unlink_sibling(cursor); + + pos = &sd->s_children; + while (n && *pos) { + struct sysfs_dirent *next = *pos; + if (sysfs_type(next)) n--; - p = p->next; + pos = &(*pos)->s_sibling; } - list_add_tail(&cursor->s_sibling, p); + + cursor->s_sibling = *pos; + *pos = cursor; } + + mutex_unlock(&sysfs_mutex); } - mutex_unlock(&dentry->d_inode->i_mutex); + return offset; } @@ -628,12 +1195,20 @@ static loff_t sysfs_dir_lseek(struct file * file, loff_t offset, int origin) int sysfs_make_shadowed_dir(struct kobject *kobj, void * (*follow_link)(struct dentry *, struct nameidata *)) { + struct dentry *dentry; struct inode *inode; struct inode_operations *i_op; - inode = kobj->dentry->d_inode; - if (inode->i_op != &sysfs_dir_inode_operations) + /* get dentry for @kobj->sd, dentry of a shadowed dir is pinned */ + dentry = sysfs_get_dentry(kobj->sd); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + + inode = dentry->d_inode; + if (inode->i_op != &sysfs_dir_inode_operations) { + dput(dentry); return -EINVAL; + } i_op = kmalloc(sizeof(*i_op), GFP_KERNEL); if (!i_op) @@ -658,54 +1233,72 @@ int sysfs_make_shadowed_dir(struct kobject *kobj, * directory. */ -struct dentry *sysfs_create_shadow_dir(struct kobject *kobj) +struct sysfs_dirent *sysfs_create_shadow_dir(struct kobject *kobj) { - struct sysfs_dirent *sd; - struct dentry *parent, *dir, *shadow; + struct sysfs_dirent *parent_sd = kobj->sd->s_parent; + struct dentry *dir, *parent, *shadow; struct inode *inode; + struct sysfs_dirent *sd; + struct sysfs_addrm_cxt acxt; - dir = kobj->dentry; - inode = dir->d_inode; + dir = sysfs_get_dentry(kobj->sd); + if (IS_ERR(dir)) { + sd = (void *)dir; + goto out; + } parent = dir->d_parent; - shadow = ERR_PTR(-EINVAL); + + inode = dir->d_inode; + sd = ERR_PTR(-EINVAL); if (!sysfs_is_shadowed_inode(inode)) - goto out; + goto out_dput; shadow = d_alloc(parent, &dir->d_name); if (!shadow) goto nomem; - sd = __sysfs_make_dirent(shadow, kobj, inode->i_mode, SYSFS_DIR); + sd = sysfs_new_dirent("_SHADOW_", inode->i_mode, SYSFS_DIR); if (!sd) goto nomem; + sd->s_elem.dir.kobj = kobj; + sysfs_addrm_start(&acxt, parent_sd); + + /* add but don't link into children list */ + sysfs_add_one(&acxt, sd); + + /* attach and instantiate dentry */ + sysfs_attach_dentry(sd, shadow); d_instantiate(shadow, igrab(inode)); - inc_nlink(inode); - inc_nlink(parent->d_inode); - shadow->d_op = &sysfs_dentry_ops; + inc_nlink(inode); /* tj: synchronization? */ + + sysfs_addrm_finish(&acxt); dget(shadow); /* Extra count - pin the dentry in core */ -out: - return shadow; -nomem: + goto out_dput; + + nomem: dput(shadow); - shadow = ERR_PTR(-ENOMEM); - goto out; + sd = ERR_PTR(-ENOMEM); + out_dput: + dput(dir); + out: + return sd; } /** * sysfs_remove_shadow_dir - remove an object's directory. - * @shadow: dentry of shadow directory + * @shadow_sd: sysfs_dirent of shadow directory * * The only thing special about this is that we remove any files in * the directory before we remove the directory, and we've inlined * what used to be sysfs_rmdir() below, instead of calling separately. */ -void sysfs_remove_shadow_dir(struct dentry *shadow) +void sysfs_remove_shadow_dir(struct sysfs_dirent *shadow_sd) { - __sysfs_remove_dir(shadow); + __sysfs_remove_dir(shadow_sd); } const struct file_operations sysfs_dir_operations = { diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index b502c7197ec..cc497994b2a 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -50,29 +50,15 @@ static struct sysfs_ops subsys_sysfs_ops = { .store = subsys_attr_store, }; -/** - * add_to_collection - add buffer to a collection - * @buffer: buffer to be added - * @node: inode of set to add to - */ - -static inline void -add_to_collection(struct sysfs_buffer *buffer, struct inode *node) -{ - struct sysfs_buffer_collection *set = node->i_private; - - mutex_lock(&node->i_mutex); - list_add(&buffer->associates, &set->associates); - mutex_unlock(&node->i_mutex); -} - -static inline void -remove_from_collection(struct sysfs_buffer *buffer, struct inode *node) -{ - mutex_lock(&node->i_mutex); - list_del(&buffer->associates); - mutex_unlock(&node->i_mutex); -} +struct sysfs_buffer { + size_t count; + loff_t pos; + char * page; + struct sysfs_ops * ops; + struct semaphore sem; + int needs_read_fill; + int event; +}; /** * fill_read_buffer - allocate and fill buffer from object. @@ -87,9 +73,8 @@ remove_from_collection(struct sysfs_buffer *buffer, struct inode *node) */ static int fill_read_buffer(struct dentry * dentry, struct sysfs_buffer * buffer) { - struct sysfs_dirent * sd = dentry->d_fsdata; - struct attribute * attr = to_attr(dentry); - struct kobject * kobj = to_kobj(dentry->d_parent); + struct sysfs_dirent *attr_sd = dentry->d_fsdata; + struct kobject *kobj = attr_sd->s_parent->s_elem.dir.kobj; struct sysfs_ops * ops = buffer->ops; int ret = 0; ssize_t count; @@ -99,8 +84,15 @@ static int fill_read_buffer(struct dentry * dentry, struct sysfs_buffer * buffer if (!buffer->page) return -ENOMEM; - buffer->event = atomic_read(&sd->s_event); - count = ops->show(kobj,attr,buffer->page); + /* need attr_sd for attr and ops, its parent for kobj */ + if (!sysfs_get_active_two(attr_sd)) + return -ENODEV; + + buffer->event = atomic_read(&attr_sd->s_event); + count = ops->show(kobj, attr_sd->s_elem.attr.attr, buffer->page); + + sysfs_put_active_two(attr_sd); + BUG_ON(count > (ssize_t)PAGE_SIZE); if (count >= 0) { buffer->needs_read_fill = 0; @@ -138,10 +130,7 @@ sysfs_read_file(struct file *file, char __user *buf, size_t count, loff_t *ppos) down(&buffer->sem); if (buffer->needs_read_fill) { - if (buffer->orphaned) - retval = -ENODEV; - else - retval = fill_read_buffer(file->f_path.dentry,buffer); + retval = fill_read_buffer(file->f_path.dentry,buffer); if (retval) goto out; } @@ -196,14 +185,23 @@ fill_write_buffer(struct sysfs_buffer * buffer, const char __user * buf, size_t * passing the buffer that we acquired in fill_write_buffer(). */ -static int +static int flush_write_buffer(struct dentry * dentry, struct sysfs_buffer * buffer, size_t count) { - struct attribute * attr = to_attr(dentry); - struct kobject * kobj = to_kobj(dentry->d_parent); + struct sysfs_dirent *attr_sd = dentry->d_fsdata; + struct kobject *kobj = attr_sd->s_parent->s_elem.dir.kobj; struct sysfs_ops * ops = buffer->ops; + int rc; + + /* need attr_sd for attr and ops, its parent for kobj */ + if (!sysfs_get_active_two(attr_sd)) + return -ENODEV; + + rc = ops->store(kobj, attr_sd->s_elem.attr.attr, buffer->page, count); - return ops->store(kobj,attr,buffer->page,count); + sysfs_put_active_two(attr_sd); + + return rc; } @@ -231,37 +229,26 @@ sysfs_write_file(struct file *file, const char __user *buf, size_t count, loff_t ssize_t len; down(&buffer->sem); - if (buffer->orphaned) { - len = -ENODEV; - goto out; - } len = fill_write_buffer(buffer, buf, count); if (len > 0) len = flush_write_buffer(file->f_path.dentry, buffer, len); if (len > 0) *ppos += len; -out: up(&buffer->sem); return len; } static int sysfs_open_file(struct inode *inode, struct file *file) { - struct kobject *kobj = sysfs_get_kobject(file->f_path.dentry->d_parent); - struct attribute * attr = to_attr(file->f_path.dentry); - struct sysfs_buffer_collection *set; + struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata; + struct kobject *kobj = attr_sd->s_parent->s_elem.dir.kobj; struct sysfs_buffer * buffer; struct sysfs_ops * ops = NULL; - int error = 0; - - if (!kobj || !attr) - goto Einval; + int error; - /* Grab the module reference for this attribute if we have one */ - if (!try_module_get(attr->owner)) { - error = -ENODEV; - goto Done; - } + /* 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. @@ -273,33 +260,21 @@ static int sysfs_open_file(struct inode *inode, struct file *file) else ops = &subsys_sysfs_ops; + error = -EACCES; + /* No sysfs operations, either from having no subsystem, * or the subsystem have no operations. */ if (!ops) - goto Eaccess; - - /* make sure we have a collection to add our buffers to */ - mutex_lock(&inode->i_mutex); - if (!(set = inode->i_private)) { - if (!(set = inode->i_private = kmalloc(sizeof(struct sysfs_buffer_collection), GFP_KERNEL))) { - error = -ENOMEM; - goto Done; - } else { - INIT_LIST_HEAD(&set->associates); - } - } - mutex_unlock(&inode->i_mutex); + goto err_out; /* File needs write support. * The inode's perms must say it's ok, * and we must have a store method. */ if (file->f_mode & FMODE_WRITE) { - if (!(inode->i_mode & S_IWUGO) || !ops->store) - goto Eaccess; - + goto err_out; } /* File needs read support. @@ -308,48 +283,38 @@ static int sysfs_open_file(struct inode *inode, struct file *file) */ if (file->f_mode & FMODE_READ) { if (!(inode->i_mode & S_IRUGO) || !ops->show) - goto Eaccess; + goto err_out; } /* No error? Great, allocate a buffer for the file, and store it * it in file->private_data for easy access. */ + error = -ENOMEM; buffer = kzalloc(sizeof(struct sysfs_buffer), GFP_KERNEL); - if (buffer) { - INIT_LIST_HEAD(&buffer->associates); - init_MUTEX(&buffer->sem); - buffer->needs_read_fill = 1; - buffer->ops = ops; - add_to_collection(buffer, inode); - file->private_data = buffer; - } else - error = -ENOMEM; - goto Done; - - Einval: - error = -EINVAL; - goto Done; - Eaccess: - error = -EACCES; - module_put(attr->owner); - Done: - if (error) - kobject_put(kobj); + if (!buffer) + goto err_out; + + init_MUTEX(&buffer->sem); + buffer->needs_read_fill = 1; + buffer->ops = ops; + file->private_data = buffer; + + /* open succeeded, put active references and pin attr_sd */ + sysfs_put_active_two(attr_sd); + sysfs_get(attr_sd); + return 0; + + err_out: + sysfs_put_active_two(attr_sd); return error; } static int sysfs_release(struct inode * inode, struct file * filp) { - struct kobject * kobj = to_kobj(filp->f_path.dentry->d_parent); - struct attribute * attr = to_attr(filp->f_path.dentry); - struct module * owner = attr->owner; - struct sysfs_buffer * buffer = filp->private_data; + struct sysfs_dirent *attr_sd = filp->f_path.dentry->d_fsdata; + struct sysfs_buffer *buffer = filp->private_data; - if (buffer) - remove_from_collection(buffer, inode); - kobject_put(kobj); - /* After this point, attr should not be accessed. */ - module_put(owner); + sysfs_put(attr_sd); if (buffer) { if (buffer->page) @@ -376,57 +341,43 @@ static int sysfs_release(struct inode * inode, struct file * filp) static unsigned int sysfs_poll(struct file *filp, poll_table *wait) { struct sysfs_buffer * buffer = filp->private_data; - struct kobject * kobj = to_kobj(filp->f_path.dentry->d_parent); - struct sysfs_dirent * sd = filp->f_path.dentry->d_fsdata; - int res = 0; + struct sysfs_dirent *attr_sd = filp->f_path.dentry->d_fsdata; + struct kobject *kobj = attr_sd->s_parent->s_elem.dir.kobj; + + /* need parent for the kobj, grab both */ + if (!sysfs_get_active_two(attr_sd)) + goto trigger; poll_wait(filp, &kobj->poll, wait); - if (buffer->event != atomic_read(&sd->s_event)) { - res = POLLERR|POLLPRI; - buffer->needs_read_fill = 1; - } + sysfs_put_active_two(attr_sd); - return res; -} + if (buffer->event != atomic_read(&attr_sd->s_event)) + goto trigger; + return 0; -static struct dentry *step_down(struct dentry *dir, const char * name) -{ - struct dentry * de; - - if (dir == NULL || dir->d_inode == NULL) - return NULL; - - mutex_lock(&dir->d_inode->i_mutex); - de = lookup_one_len(name, dir, strlen(name)); - mutex_unlock(&dir->d_inode->i_mutex); - dput(dir); - if (IS_ERR(de)) - return NULL; - if (de->d_inode == NULL) { - dput(de); - return NULL; - } - return de; + trigger: + buffer->needs_read_fill = 1; + return POLLERR|POLLPRI; } -void sysfs_notify(struct kobject * k, char *dir, char *attr) +void sysfs_notify(struct kobject *k, char *dir, char *attr) { - struct dentry *de = k->dentry; - if (de) - dget(de); - if (de && dir) - de = step_down(de, dir); - if (de && attr) - de = step_down(de, attr); - if (de) { - struct sysfs_dirent * sd = de->d_fsdata; - if (sd) - atomic_inc(&sd->s_event); + struct sysfs_dirent *sd = k->sd; + + mutex_lock(&sysfs_mutex); + + if (sd && dir) + sd = sysfs_find_dirent(sd, dir); + if (sd && attr) + sd = sysfs_find_dirent(sd, attr); + if (sd) { + atomic_inc(&sd->s_event); wake_up_interruptible(&k->poll); - dput(de); } + + mutex_unlock(&sysfs_mutex); } EXPORT_SYMBOL_GPL(sysfs_notify); @@ -440,19 +391,30 @@ const struct file_operations sysfs_file_operations = { }; -int sysfs_add_file(struct dentry * dir, const struct attribute * attr, int type) +int sysfs_add_file(struct sysfs_dirent *dir_sd, const struct attribute *attr, + int type) { - struct sysfs_dirent * parent_sd = dir->d_fsdata; umode_t mode = (attr->mode & S_IALLUGO) | S_IFREG; - int error = -EEXIST; + struct sysfs_addrm_cxt acxt; + struct sysfs_dirent *sd; - mutex_lock(&dir->d_inode->i_mutex); - if (!sysfs_dirent_exist(parent_sd, attr->name)) - error = sysfs_make_dirent(parent_sd, NULL, (void *)attr, - mode, type); - mutex_unlock(&dir->d_inode->i_mutex); + sd = sysfs_new_dirent(attr->name, mode, type); + if (!sd) + return -ENOMEM; + sd->s_elem.attr.attr = (void *)attr; - return error; + sysfs_addrm_start(&acxt, dir_sd); + + if (!sysfs_find_dirent(dir_sd, attr->name)) { + sysfs_add_one(&acxt, sd); + sysfs_link_sibling(sd); + } + + if (sysfs_addrm_finish(&acxt)) + return 0; + + sysfs_put(sd); + return -EEXIST; } @@ -464,9 +426,9 @@ int sysfs_add_file(struct dentry * dir, const struct attribute * attr, int type) int sysfs_create_file(struct kobject * kobj, const struct attribute * attr) { - BUG_ON(!kobj || !kobj->dentry || !attr); + BUG_ON(!kobj || !kobj->sd || !attr); - return sysfs_add_file(kobj->dentry, attr, SYSFS_KOBJ_ATTR); + return sysfs_add_file(kobj->sd, attr, SYSFS_KOBJ_ATTR); } @@ -480,16 +442,16 @@ int sysfs_create_file(struct kobject * kobj, const struct attribute * attr) int sysfs_add_file_to_group(struct kobject *kobj, const struct attribute *attr, const char *group) { - struct dentry *dir; + struct sysfs_dirent *dir_sd; int error; - dir = lookup_one_len(group, kobj->dentry, strlen(group)); - if (IS_ERR(dir)) - error = PTR_ERR(dir); - else { - error = sysfs_add_file(dir, attr, SYSFS_KOBJ_ATTR); - dput(dir); - } + dir_sd = sysfs_get_dirent(kobj->sd, group); + if (!dir_sd) + return -ENOENT; + + error = sysfs_add_file(dir_sd, attr, SYSFS_KOBJ_ATTR); + sysfs_put(dir_sd); + return error; } EXPORT_SYMBOL_GPL(sysfs_add_file_to_group); @@ -502,30 +464,31 @@ EXPORT_SYMBOL_GPL(sysfs_add_file_to_group); */ int sysfs_update_file(struct kobject * kobj, const struct attribute * attr) { - struct dentry * dir = kobj->dentry; - struct dentry * victim; - int res = -ENOENT; - - mutex_lock(&dir->d_inode->i_mutex); - victim = lookup_one_len(attr->name, dir, strlen(attr->name)); - if (!IS_ERR(victim)) { - /* make sure dentry is really there */ - if (victim->d_inode && - (victim->d_parent->d_inode == dir->d_inode)) { - victim->d_inode->i_mtime = CURRENT_TIME; - fsnotify_modify(victim); - res = 0; - } else - d_drop(victim); - - /** - * Drop the reference acquired from lookup_one_len() above. - */ - dput(victim); + struct sysfs_dirent *victim_sd = NULL; + struct dentry *victim = NULL; + int rc; + + rc = -ENOENT; + victim_sd = sysfs_get_dirent(kobj->sd, attr->name); + if (!victim_sd) + goto out; + + victim = sysfs_get_dentry(victim_sd); + if (IS_ERR(victim)) { + rc = PTR_ERR(victim); + victim = NULL; + goto out; } - mutex_unlock(&dir->d_inode->i_mutex); - return res; + mutex_lock(&victim->d_inode->i_mutex); + victim->d_inode->i_mtime = CURRENT_TIME; + fsnotify_modify(victim); + mutex_unlock(&victim->d_inode->i_mutex); + rc = 0; + out: + dput(victim); + sysfs_put(victim_sd); + return rc; } @@ -538,30 +501,34 @@ int sysfs_update_file(struct kobject * kobj, const struct attribute * attr) */ int sysfs_chmod_file(struct kobject *kobj, struct attribute *attr, mode_t mode) { - struct dentry *dir = kobj->dentry; - struct dentry *victim; + struct sysfs_dirent *victim_sd = NULL; + struct dentry *victim = NULL; struct inode * inode; struct iattr newattrs; - int res = -ENOENT; - - mutex_lock(&dir->d_inode->i_mutex); - victim = lookup_one_len(attr->name, dir, strlen(attr->name)); - if (!IS_ERR(victim)) { - if (victim->d_inode && - (victim->d_parent->d_inode == dir->d_inode)) { - inode = victim->d_inode; - mutex_lock(&inode->i_mutex); - newattrs.ia_mode = (mode & S_IALLUGO) | - (inode->i_mode & ~S_IALLUGO); - newattrs.ia_valid = ATTR_MODE | ATTR_CTIME; - res = notify_change(victim, &newattrs); - mutex_unlock(&inode->i_mutex); - } - dput(victim); + int rc; + + rc = -ENOENT; + victim_sd = sysfs_get_dirent(kobj->sd, attr->name); + if (!victim_sd) + goto out; + + victim = sysfs_get_dentry(victim_sd); + if (IS_ERR(victim)) { + rc = PTR_ERR(victim); + victim = NULL; + goto out; } - mutex_unlock(&dir->d_inode->i_mutex); - return res; + inode = victim->d_inode; + mutex_lock(&inode->i_mutex); + newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO); + newattrs.ia_valid = ATTR_MODE | ATTR_CTIME; + rc = notify_change(victim, &newattrs); + mutex_unlock(&inode->i_mutex); + out: + dput(victim); + sysfs_put(victim_sd); + return rc; } EXPORT_SYMBOL_GPL(sysfs_chmod_file); @@ -576,7 +543,7 @@ EXPORT_SYMBOL_GPL(sysfs_chmod_file); void sysfs_remove_file(struct kobject * kobj, const struct attribute * attr) { - sysfs_hash_and_remove(kobj->dentry, attr->name); + sysfs_hash_and_remove(kobj->sd, attr->name); } @@ -589,12 +556,12 @@ void sysfs_remove_file(struct kobject * kobj, const struct attribute * attr) void sysfs_remove_file_from_group(struct kobject *kobj, const struct attribute *attr, const char *group) { - struct dentry *dir; + struct sysfs_dirent *dir_sd; - dir = lookup_one_len(group, kobj->dentry, strlen(group)); - if (!IS_ERR(dir)) { - sysfs_hash_and_remove(dir, attr->name); - dput(dir); + dir_sd = sysfs_get_dirent(kobj->sd, group); + if (dir_sd) { + sysfs_hash_and_remove(dir_sd, attr->name); + sysfs_put(dir_sd); } } EXPORT_SYMBOL_GPL(sysfs_remove_file_from_group); diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index 52eed2a7a5e..f318b73c790 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -18,26 +18,25 @@ #include "sysfs.h" -static void remove_files(struct dentry * dir, - const struct attribute_group * grp) +static void remove_files(struct sysfs_dirent *dir_sd, + const struct attribute_group *grp) { struct attribute *const* attr; for (attr = grp->attrs; *attr; attr++) - sysfs_hash_and_remove(dir,(*attr)->name); + sysfs_hash_and_remove(dir_sd, (*attr)->name); } -static int create_files(struct dentry * dir, - const struct attribute_group * grp) +static int create_files(struct sysfs_dirent *dir_sd, + const struct attribute_group *grp) { struct attribute *const* attr; int error = 0; - for (attr = grp->attrs; *attr && !error; attr++) { - error = sysfs_add_file(dir, *attr, SYSFS_KOBJ_ATTR); - } + for (attr = grp->attrs; *attr && !error; attr++) + error = sysfs_add_file(dir_sd, *attr, SYSFS_KOBJ_ATTR); if (error) - remove_files(dir,grp); + remove_files(dir_sd, grp); return error; } @@ -45,44 +44,44 @@ static int create_files(struct dentry * dir, int sysfs_create_group(struct kobject * kobj, const struct attribute_group * grp) { - struct dentry * dir; + struct sysfs_dirent *sd; int error; - BUG_ON(!kobj || !kobj->dentry); + BUG_ON(!kobj || !kobj->sd); if (grp->name) { - error = sysfs_create_subdir(kobj,grp->name,&dir); + error = sysfs_create_subdir(kobj, grp->name, &sd); if (error) return error; } else - dir = kobj->dentry; - dir = dget(dir); - if ((error = create_files(dir,grp))) { + sd = kobj->sd; + sysfs_get(sd); + error = create_files(sd, grp); + if (error) { if (grp->name) - sysfs_remove_subdir(dir); + sysfs_remove_subdir(sd); } - dput(dir); + sysfs_put(sd); return error; } void sysfs_remove_group(struct kobject * kobj, const struct attribute_group * grp) { - struct dentry * dir; + struct sysfs_dirent *dir_sd = kobj->sd; + struct sysfs_dirent *sd; if (grp->name) { - dir = lookup_one_len_kern(grp->name, kobj->dentry, - strlen(grp->name)); - BUG_ON(IS_ERR(dir)); - } - else - dir = dget(kobj->dentry); + sd = sysfs_get_dirent(dir_sd, grp->name); + BUG_ON(!sd); + } else + sd = sysfs_get(dir_sd); - remove_files(dir,grp); + remove_files(sd, grp); if (grp->name) - sysfs_remove_subdir(dir); - /* release the ref. taken in this routine */ - dput(dir); + sysfs_remove_subdir(sd); + + sysfs_put(sd); } diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c index 5266eec15f6..3756e152285 100644 --- a/fs/sysfs/inode.c +++ b/fs/sysfs/inode.c @@ -133,187 +133,94 @@ static inline void set_inode_attr(struct inode * inode, struct iattr * iattr) */ static struct lock_class_key sysfs_inode_imutex_key; -struct inode * sysfs_new_inode(mode_t mode, struct sysfs_dirent * sd) +void sysfs_init_inode(struct sysfs_dirent *sd, struct inode *inode) { - struct inode * inode = new_inode(sysfs_sb); - if (inode) { - inode->i_blocks = 0; - inode->i_mapping->a_ops = &sysfs_aops; - inode->i_mapping->backing_dev_info = &sysfs_backing_dev_info; - inode->i_op = &sysfs_inode_operations; - inode->i_ino = sd->s_ino; - lockdep_set_class(&inode->i_mutex, &sysfs_inode_imutex_key); - - 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; -} - -int sysfs_create(struct dentry * dentry, int mode, int (*init)(struct inode *)) -{ - int error = 0; - struct inode * inode = NULL; - if (dentry) { - if (!dentry->d_inode) { - struct sysfs_dirent * sd = dentry->d_fsdata; - if ((inode = sysfs_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; - } - goto Proceed; - } - else - error = -ENOMEM; - } else - error = -EEXIST; - } else - error = -ENOENT; - goto Done; - - Proceed: - if (init) - error = init(inode); - if (!error) { - d_instantiate(dentry, inode); - if (S_ISDIR(mode)) - dget(dentry); /* pin only directory dentry in core */ + inode->i_blocks = 0; + inode->i_mapping->a_ops = &sysfs_aops; + inode->i_mapping->backing_dev_info = &sysfs_backing_dev_info; + inode->i_op = &sysfs_inode_operations; + inode->i_ino = sd->s_ino; + lockdep_set_class(&inode->i_mutex, &sysfs_inode_imutex_key); + + 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 - iput(inode); - Done: - return error; + set_default_inode_attr(inode, sd->s_mode); } -/* - * Get the name for corresponding element represented by the given sysfs_dirent +/** + * sysfs_get_inode - get inode for sysfs_dirent + * @sd: sysfs_dirent to allocate inode for + * + * Get inode for @sd. If such inode doesn't exist, a new inode + * is allocated and basics are initialized. New inode is + * returned locked. + * + * LOCKING: + * Kernel thread context (may sleep). + * + * RETURNS: + * Pointer to allocated inode on success, NULL on failure. */ -const unsigned char * sysfs_get_name(struct sysfs_dirent *sd) +struct inode * sysfs_get_inode(struct sysfs_dirent *sd) { - struct attribute * attr; - struct bin_attribute * bin_attr; - struct sysfs_symlink * sl; - - BUG_ON(!sd || !sd->s_element); - - switch (sd->s_type) { - case SYSFS_DIR: - /* Always have a dentry so use that */ - return sd->s_dentry->d_name.name; - - case SYSFS_KOBJ_ATTR: - attr = sd->s_element; - return attr->name; - - case SYSFS_KOBJ_BIN_ATTR: - bin_attr = sd->s_element; - return bin_attr->attr.name; + struct inode *inode; - case SYSFS_KOBJ_LINK: - sl = sd->s_element; - return sl->link_name; - } - return NULL; -} + inode = iget_locked(sysfs_sb, sd->s_ino); + if (inode && (inode->i_state & I_NEW)) + sysfs_init_inode(sd, inode); -static inline void orphan_all_buffers(struct inode *node) -{ - struct sysfs_buffer_collection *set; - struct sysfs_buffer *buf; - - mutex_lock_nested(&node->i_mutex, I_MUTEX_CHILD); - set = node->i_private; - if (set) { - list_for_each_entry(buf, &set->associates, associates) { - down(&buf->sem); - buf->orphaned = 1; - up(&buf->sem); - } - } - mutex_unlock(&node->i_mutex); + return inode; } - -/* - * Unhashes the dentry corresponding to given sysfs_dirent - * Called with parent inode's i_mutex held. +/** + * sysfs_instantiate - instantiate dentry + * @dentry: dentry to be instantiated + * @inode: inode associated with @sd + * + * Unlock @inode if locked and instantiate @dentry with @inode. + * + * LOCKING: + * None. */ -void sysfs_drop_dentry(struct sysfs_dirent * sd, struct dentry * parent) +void sysfs_instantiate(struct dentry *dentry, struct inode *inode) { - struct dentry *dentry = NULL; - struct inode *inode; + BUG_ON(!dentry || dentry->d_inode); - /* We're not holding a reference to ->s_dentry dentry but the - * field will stay valid as long as sysfs_lock is held. - */ - spin_lock(&sysfs_lock); - spin_lock(&dcache_lock); - - /* dget dentry if it's still alive */ - if (sd->s_dentry && sd->s_dentry->d_inode) - dentry = dget_locked(sd->s_dentry); - - spin_unlock(&dcache_lock); - spin_unlock(&sysfs_lock); - - /* drop dentry */ - if (dentry) { - spin_lock(&dcache_lock); - spin_lock(&dentry->d_lock); - if (!d_unhashed(dentry) && dentry->d_inode) { - inode = dentry->d_inode; - spin_lock(&inode->i_lock); - __iget(inode); - spin_unlock(&inode->i_lock); - dget_locked(dentry); - __d_drop(dentry); - spin_unlock(&dentry->d_lock); - spin_unlock(&dcache_lock); - simple_unlink(parent->d_inode, dentry); - orphan_all_buffers(inode); - iput(inode); - } else { - spin_unlock(&dentry->d_lock); - spin_unlock(&dcache_lock); - } + if (inode->i_state & I_NEW) + unlock_new_inode(inode); - dput(dentry); - } + d_instantiate(dentry, inode); } -int sysfs_hash_and_remove(struct dentry * dir, const char * name) +int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const char *name) { - struct sysfs_dirent * sd; - struct sysfs_dirent * parent_sd; - int found = 0; + struct sysfs_addrm_cxt acxt; + struct sysfs_dirent **pos, *sd; - if (!dir) + if (!dir_sd) return -ENOENT; - if (dir->d_inode == NULL) - /* no inode means this hasn't been made visible yet */ - return -ENOENT; + sysfs_addrm_start(&acxt, dir_sd); + + for (pos = &dir_sd->s_children; *pos; pos = &(*pos)->s_sibling) { + sd = *pos; - parent_sd = dir->d_fsdata; - mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT); - list_for_each_entry(sd, &parent_sd->s_children, s_sibling) { - if (!sd->s_element) + if (!sysfs_type(sd)) continue; - if (!strcmp(sysfs_get_name(sd), name)) { - list_del_init(&sd->s_sibling); - sysfs_drop_dentry(sd, dir); - sysfs_put(sd); - found = 1; + if (!strcmp(sd->s_name, name)) { + *pos = sd->s_sibling; + sd->s_sibling = NULL; + sysfs_remove_one(&acxt, sd); break; } } - mutex_unlock(&dir->d_inode->i_mutex); - return found ? 0 : -ENOENT; + if (sysfs_addrm_finish(&acxt)) + return 0; + return -ENOENT; } diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index 00ab9125d39..402cc356203 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -19,28 +19,18 @@ struct vfsmount *sysfs_mount; struct super_block * sysfs_sb = NULL; struct kmem_cache *sysfs_dir_cachep; -static void sysfs_clear_inode(struct inode *inode); - static const struct super_operations sysfs_ops = { .statfs = simple_statfs, .drop_inode = sysfs_delete_inode, - .clear_inode = sysfs_clear_inode, }; -static struct sysfs_dirent sysfs_root = { - .s_sibling = LIST_HEAD_INIT(sysfs_root.s_sibling), - .s_children = LIST_HEAD_INIT(sysfs_root.s_children), - .s_element = NULL, - .s_type = SYSFS_ROOT, - .s_iattr = NULL, +struct sysfs_dirent sysfs_root = { + .s_count = ATOMIC_INIT(1), + .s_flags = SYSFS_ROOT, + .s_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO, .s_ino = 1, }; -static void sysfs_clear_inode(struct inode *inode) -{ - kfree(inode->i_private); -} - static int sysfs_fill_super(struct super_block *sb, void *data, int silent) { struct inode *inode; @@ -53,24 +43,26 @@ static int sysfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_time_gran = 1; sysfs_sb = sb; - inode = sysfs_new_inode(S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO, - &sysfs_root); - if (inode) { - inode->i_op = &sysfs_dir_inode_operations; - inode->i_fop = &sysfs_dir_operations; - /* directory inodes start off with i_nlink == 2 (for "." entry) */ - inc_nlink(inode); - } else { + inode = new_inode(sysfs_sb); + if (!inode) { pr_debug("sysfs: could not get root inode\n"); return -ENOMEM; } + sysfs_init_inode(&sysfs_root, inode); + + inode->i_op = &sysfs_dir_inode_operations; + inode->i_fop = &sysfs_dir_operations; + /* directory inodes start off with i_nlink == 2 (for "." entry) */ + inc_nlink(inode); + root = d_alloc_root(inode); if (!root) { pr_debug("%s: could not get root dentry!\n",__FUNCTION__); iput(inode); return -ENOMEM; } + sysfs_root.s_dentry = root; root->d_fsdata = &sysfs_root; sb->s_root = root; return 0; diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c index 7b9c5bfde92..2f86e042229 100644 --- a/fs/sysfs/symlink.c +++ b/fs/sysfs/symlink.c @@ -11,71 +11,39 @@ #include "sysfs.h" -static int object_depth(struct kobject * kobj) +static int object_depth(struct sysfs_dirent *sd) { - struct kobject * p = kobj; int depth = 0; - do { depth++; } while ((p = p->parent)); + + for (; sd->s_parent; sd = sd->s_parent) + depth++; + return depth; } -static int object_path_length(struct kobject * kobj) +static int object_path_length(struct sysfs_dirent * sd) { - struct kobject * p = kobj; int length = 1; - do { - length += strlen(kobject_name(p)) + 1; - p = p->parent; - } while (p); + + for (; sd->s_parent; sd = sd->s_parent) + length += strlen(sd->s_name) + 1; + return length; } -static void fill_object_path(struct kobject * kobj, char * buffer, int length) +static void fill_object_path(struct sysfs_dirent *sd, char *buffer, int length) { - struct kobject * p; - --length; - for (p = kobj; p; p = p->parent) { - int cur = strlen(kobject_name(p)); + 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,kobject_name(p),cur); + strncpy(buffer + length, sd->s_name, cur); *(buffer + --length) = '/'; } } -static int sysfs_add_link(struct dentry * parent, const char * name, struct kobject * target) -{ - struct sysfs_dirent * parent_sd = parent->d_fsdata; - struct sysfs_symlink * sl; - int error = 0; - - error = -ENOMEM; - sl = kmalloc(sizeof(*sl), GFP_KERNEL); - if (!sl) - goto exit1; - - sl->link_name = kmalloc(strlen(name) + 1, GFP_KERNEL); - if (!sl->link_name) - goto exit2; - - strcpy(sl->link_name, name); - sl->target_kobj = kobject_get(target); - - error = sysfs_make_dirent(parent_sd, NULL, sl, S_IFLNK|S_IRWXUGO, - SYSFS_KOBJ_LINK); - if (!error) - return 0; - - kobject_put(target); - kfree(sl->link_name); -exit2: - kfree(sl); -exit1: - return error; -} - /** * sysfs_create_link - create symlink between two objects. * @kobj: object whose directory we're creating the link in. @@ -84,24 +52,57 @@ exit1: */ int sysfs_create_link(struct kobject * kobj, struct kobject * target, const char * name) { - struct dentry *dentry = NULL; - int error = -EEXIST; + struct sysfs_dirent *parent_sd = NULL; + struct sysfs_dirent *target_sd = NULL; + struct sysfs_dirent *sd = NULL; + struct sysfs_addrm_cxt acxt; + int error; BUG_ON(!name); if (!kobj) { if (sysfs_mount && sysfs_mount->mnt_sb) - dentry = sysfs_mount->mnt_sb->s_root; + parent_sd = sysfs_mount->mnt_sb->s_root->d_fsdata; } else - dentry = kobj->dentry; + parent_sd = kobj->sd; + + error = -EFAULT; + if (!parent_sd) + goto out_put; + + /* target->sd can go away beneath us but is protected with + * sysfs_assoc_lock. Fetch target_sd from it. + */ + spin_lock(&sysfs_assoc_lock); + if (target->sd) + target_sd = sysfs_get(target->sd); + spin_unlock(&sysfs_assoc_lock); + + error = -ENOENT; + if (!target_sd) + goto out_put; + + error = -ENOMEM; + sd = sysfs_new_dirent(name, S_IFLNK|S_IRWXUGO, SYSFS_KOBJ_LINK); + if (!sd) + goto out_put; + sd->s_elem.symlink.target_sd = target_sd; - if (!dentry) - return -EFAULT; + sysfs_addrm_start(&acxt, parent_sd); - mutex_lock(&dentry->d_inode->i_mutex); - if (!sysfs_dirent_exist(dentry->d_fsdata, name)) - error = sysfs_add_link(dentry, name, target); - mutex_unlock(&dentry->d_inode->i_mutex); + if (!sysfs_find_dirent(parent_sd, name)) { + sysfs_add_one(&acxt, sd); + sysfs_link_sibling(sd); + } + + if (sysfs_addrm_finish(&acxt)) + return 0; + + error = -EEXIST; + /* fall through */ + out_put: + sysfs_put(target_sd); + sysfs_put(sd); return error; } @@ -114,17 +115,17 @@ int sysfs_create_link(struct kobject * kobj, struct kobject * target, const char void sysfs_remove_link(struct kobject * kobj, const char * name) { - sysfs_hash_and_remove(kobj->dentry,name); + sysfs_hash_and_remove(kobj->sd, name); } -static int sysfs_get_target_path(struct kobject * kobj, struct kobject * target, - 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; - depth = object_depth(kobj); - size = object_path_length(target) + depth * 3 - 1; + depth = object_depth(parent_sd); + size = object_path_length(target_sd) + depth * 3 - 1; if (size > PATH_MAX) return -ENAMETOOLONG; @@ -133,7 +134,7 @@ static int sysfs_get_target_path(struct kobject * kobj, struct kobject * target, for (s = path; depth--; s += 3) strcpy(s,"../"); - fill_object_path(target, path, size); + fill_object_path(target_sd, path, size); pr_debug("%s: path = '%s'\n", __FUNCTION__, path); return 0; @@ -141,27 +142,16 @@ static int sysfs_get_target_path(struct kobject * kobj, struct kobject * target, static int sysfs_getlink(struct dentry *dentry, char * path) { - struct kobject *kobj, *target_kobj; - int error = 0; + struct sysfs_dirent *sd = dentry->d_fsdata; + struct sysfs_dirent *parent_sd = sd->s_parent; + struct sysfs_dirent *target_sd = sd->s_elem.symlink.target_sd; + int error; - kobj = sysfs_get_kobject(dentry->d_parent); - if (!kobj) - return -EINVAL; + mutex_lock(&sysfs_mutex); + error = sysfs_get_target_path(parent_sd, target_sd, path); + mutex_unlock(&sysfs_mutex); - target_kobj = sysfs_get_kobject(dentry); - if (!target_kobj) { - kobject_put(kobj); - return -EINVAL; - } - - down_read(&sysfs_rename_sem); - error = sysfs_get_target_path(kobj, target_kobj, path); - up_read(&sysfs_rename_sem); - - kobject_put(kobj); - kobject_put(target_kobj); return error; - } static void *sysfs_follow_link(struct dentry *dentry, struct nameidata *nd) diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h index 502c949c402..6a37f2386a8 100644 --- a/fs/sysfs/sysfs.h +++ b/fs/sysfs/sysfs.h @@ -1,9 +1,40 @@ +struct sysfs_elem_dir { + struct kobject * kobj; +}; + +struct sysfs_elem_symlink { + struct sysfs_dirent * target_sd; +}; + +struct sysfs_elem_attr { + struct attribute * attr; +}; + +struct sysfs_elem_bin_attr { + struct bin_attribute * bin_attr; +}; + +/* + * As long as s_count reference is held, the sysfs_dirent itself is + * accessible. Dereferencing s_elem or any other outer entity + * requires s_active reference. + */ struct sysfs_dirent { atomic_t s_count; - struct list_head s_sibling; - struct list_head s_children; - void * s_element; - int s_type; + atomic_t s_active; + struct sysfs_dirent * s_parent; + struct sysfs_dirent * s_sibling; + struct sysfs_dirent * s_children; + const char * s_name; + + union { + struct sysfs_elem_dir dir; + struct sysfs_elem_symlink symlink; + struct sysfs_elem_attr attr; + struct sysfs_elem_bin_attr bin_attr; + } s_elem; + + unsigned int s_flags; umode_t s_mode; ino_t s_ino; struct dentry * s_dentry; @@ -11,30 +42,60 @@ struct sysfs_dirent { atomic_t s_event; }; +#define SD_DEACTIVATED_BIAS INT_MIN + +struct sysfs_addrm_cxt { + struct sysfs_dirent *parent_sd; + struct inode *parent_inode; + struct sysfs_dirent *removed; + int cnt; +}; + extern struct vfsmount * sysfs_mount; +extern struct sysfs_dirent sysfs_root; extern struct kmem_cache *sysfs_dir_cachep; -extern void sysfs_delete_inode(struct inode *inode); -extern struct inode * sysfs_new_inode(mode_t mode, struct sysfs_dirent *); -extern int sysfs_create(struct dentry *, int mode, int (*init)(struct inode *)); +extern struct dentry *sysfs_get_dentry(struct sysfs_dirent *sd); +extern void sysfs_link_sibling(struct sysfs_dirent *sd); +extern void sysfs_unlink_sibling(struct sysfs_dirent *sd); +extern struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd); +extern void sysfs_put_active(struct sysfs_dirent *sd); +extern struct sysfs_dirent *sysfs_get_active_two(struct sysfs_dirent *sd); +extern void sysfs_put_active_two(struct sysfs_dirent *sd); +extern void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt, + struct sysfs_dirent *parent_sd); +extern void sysfs_add_one(struct sysfs_addrm_cxt *acxt, + struct sysfs_dirent *sd); +extern void sysfs_remove_one(struct sysfs_addrm_cxt *acxt, + struct sysfs_dirent *sd); +extern int sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt); -extern int sysfs_dirent_exist(struct sysfs_dirent *, const unsigned char *); -extern int sysfs_make_dirent(struct sysfs_dirent *, struct dentry *, void *, - umode_t, int); - -extern int sysfs_add_file(struct dentry *, const struct attribute *, int); -extern int sysfs_hash_and_remove(struct dentry * dir, const char * name); +extern void sysfs_delete_inode(struct inode *inode); +extern void sysfs_init_inode(struct sysfs_dirent *sd, struct inode *inode); +extern struct inode * sysfs_get_inode(struct sysfs_dirent *sd); +extern void sysfs_instantiate(struct dentry *dentry, struct inode *inode); + +extern void release_sysfs_dirent(struct sysfs_dirent * sd); +extern struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd, + const unsigned char *name); +extern struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd, + const unsigned char *name); +extern struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, + int type); + +extern int sysfs_add_file(struct sysfs_dirent *dir_sd, + const struct attribute *attr, int type); +extern int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const char *name); extern struct sysfs_dirent *sysfs_find(struct sysfs_dirent *dir, const char * name); -extern int sysfs_create_subdir(struct kobject *, const char *, struct dentry **); -extern void sysfs_remove_subdir(struct dentry *); +extern int sysfs_create_subdir(struct kobject *kobj, const char *name, + struct sysfs_dirent **p_sd); +extern void sysfs_remove_subdir(struct sysfs_dirent *sd); -extern const unsigned char * sysfs_get_name(struct sysfs_dirent *sd); -extern void sysfs_drop_dentry(struct sysfs_dirent *sd, struct dentry *parent); extern int sysfs_setattr(struct dentry *dentry, struct iattr *iattr); -extern spinlock_t sysfs_lock; -extern struct rw_semaphore sysfs_rename_sem; +extern spinlock_t sysfs_assoc_lock; +extern struct mutex sysfs_mutex; extern struct super_block * sysfs_sb; extern const struct file_operations sysfs_dir_operations; extern const struct file_operations sysfs_file_operations; @@ -42,73 +103,9 @@ extern const struct file_operations bin_fops; extern const struct inode_operations sysfs_dir_inode_operations; extern const struct inode_operations sysfs_symlink_inode_operations; -struct sysfs_symlink { - char * link_name; - struct kobject * target_kobj; -}; - -struct sysfs_buffer { - struct list_head associates; - size_t count; - loff_t pos; - char * page; - struct sysfs_ops * ops; - struct semaphore sem; - int orphaned; - int needs_read_fill; - int event; -}; - -struct sysfs_buffer_collection { - struct list_head associates; -}; - -static inline struct kobject * to_kobj(struct dentry * dentry) -{ - struct sysfs_dirent * sd = dentry->d_fsdata; - return ((struct kobject *) sd->s_element); -} - -static inline struct attribute * to_attr(struct dentry * dentry) +static inline unsigned int sysfs_type(struct sysfs_dirent *sd) { - struct sysfs_dirent * sd = dentry->d_fsdata; - return ((struct attribute *) sd->s_element); -} - -static inline struct bin_attribute * to_bin_attr(struct dentry * dentry) -{ - struct sysfs_dirent * sd = dentry->d_fsdata; - return ((struct bin_attribute *) sd->s_element); -} - -static inline struct kobject *sysfs_get_kobject(struct dentry *dentry) -{ - struct kobject * kobj = NULL; - - spin_lock(&dcache_lock); - if (!d_unhashed(dentry)) { - struct sysfs_dirent * sd = dentry->d_fsdata; - if (sd->s_type & SYSFS_KOBJ_LINK) { - struct sysfs_symlink * sl = sd->s_element; - kobj = kobject_get(sl->target_kobj); - } else - kobj = kobject_get(sd->s_element); - } - spin_unlock(&dcache_lock); - - return kobj; -} - -static inline void release_sysfs_dirent(struct sysfs_dirent * sd) -{ - if (sd->s_type & SYSFS_KOBJ_LINK) { - struct sysfs_symlink * sl = sd->s_element; - kfree(sl->link_name); - kobject_put(sl->target_kobj); - kfree(sl); - } - kfree(sd->s_iattr); - kmem_cache_free(sysfs_dir_cachep, sd); + return sd->s_flags & SYSFS_TYPE_MASK; } static inline struct sysfs_dirent * sysfs_get(struct sysfs_dirent * sd) @@ -122,7 +119,7 @@ static inline struct sysfs_dirent * sysfs_get(struct sysfs_dirent * sd) static inline void sysfs_put(struct sysfs_dirent * sd) { - if (atomic_dec_and_test(&sd->s_count)) + if (sd && atomic_dec_and_test(&sd->s_count)) release_sysfs_dirent(sd); } diff --git a/fs/sysv/file.c b/fs/sysv/file.c index 0732ddb9020..589be21d884 100644 --- a/fs/sysv/file.c +++ b/fs/sysv/file.c @@ -27,7 +27,7 @@ const struct file_operations sysv_file_operations = { .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .fsync = sysv_sync_file, - .sendfile = generic_file_sendfile, + .splice_read = generic_file_splice_read, }; const struct inode_operations sysv_file_inode_operations = { diff --git a/fs/udf/file.c b/fs/udf/file.c index 51b5764685e..df070bee8d4 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -261,7 +261,7 @@ const struct file_operations udf_file_operations = { .aio_write = udf_file_aio_write, .release = udf_release_file, .fsync = udf_fsync_file, - .sendfile = generic_file_sendfile, + .splice_read = generic_file_splice_read, }; const struct inode_operations udf_file_inode_operations = { diff --git a/fs/ufs/file.c b/fs/ufs/file.c index 1e096323bad..6705d74c6d2 100644 --- a/fs/ufs/file.c +++ b/fs/ufs/file.c @@ -60,5 +60,5 @@ const struct file_operations ufs_file_operations = { .mmap = generic_file_mmap, .open = generic_file_open, .fsync = ufs_sync_file, - .sendfile = generic_file_sendfile, + .splice_read = generic_file_splice_read, }; diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c index cb51dc96135..8c43cd2e237 100644 --- a/fs/xfs/linux-2.6/xfs_file.c +++ b/fs/xfs/linux-2.6/xfs_file.c @@ -124,30 +124,6 @@ xfs_file_aio_write_invis( } STATIC ssize_t -xfs_file_sendfile( - struct file *filp, - loff_t *pos, - size_t count, - read_actor_t actor, - void *target) -{ - return bhv_vop_sendfile(vn_from_inode(filp->f_path.dentry->d_inode), - filp, pos, 0, count, actor, target, NULL); -} - -STATIC ssize_t -xfs_file_sendfile_invis( - struct file *filp, - loff_t *pos, - size_t count, - read_actor_t actor, - void *target) -{ - return bhv_vop_sendfile(vn_from_inode(filp->f_path.dentry->d_inode), - filp, pos, IO_INVIS, count, actor, target, NULL); -} - -STATIC ssize_t xfs_file_splice_read( struct file *infilp, loff_t *ppos, @@ -452,7 +428,6 @@ const struct file_operations xfs_file_operations = { .write = do_sync_write, .aio_read = xfs_file_aio_read, .aio_write = xfs_file_aio_write, - .sendfile = xfs_file_sendfile, .splice_read = xfs_file_splice_read, .splice_write = xfs_file_splice_write, .unlocked_ioctl = xfs_file_ioctl, @@ -475,7 +450,6 @@ const struct file_operations xfs_invis_file_operations = { .write = do_sync_write, .aio_read = xfs_file_aio_read_invis, .aio_write = xfs_file_aio_write_invis, - .sendfile = xfs_file_sendfile_invis, .splice_read = xfs_file_splice_read_invis, .splice_write = xfs_file_splice_write_invis, .unlocked_ioctl = xfs_file_ioctl_invis, diff --git a/fs/xfs/linux-2.6/xfs_linux.h b/fs/xfs/linux-2.6/xfs_linux.h index 715adad7dd4..af24a457d3a 100644 --- a/fs/xfs/linux-2.6/xfs_linux.h +++ b/fs/xfs/linux-2.6/xfs_linux.h @@ -101,7 +101,6 @@ * Feature macros (disable/enable) */ #undef HAVE_REFCACHE /* reference cache not needed for NFS in 2.6 */ -#define HAVE_SENDFILE /* sendfile(2) exists in 2.6, but not in 2.4 */ #define HAVE_SPLICE /* a splice(2) exists in 2.6, but not in 2.4 */ #ifdef CONFIG_SMP #define HAVE_PERCPU_SB /* per cpu superblock counters are a 2.6 feature */ diff --git a/fs/xfs/linux-2.6/xfs_lrw.c b/fs/xfs/linux-2.6/xfs_lrw.c index ed90403f0ee..765ec16a6e3 100644 --- a/fs/xfs/linux-2.6/xfs_lrw.c +++ b/fs/xfs/linux-2.6/xfs_lrw.c @@ -287,50 +287,6 @@ xfs_read( } ssize_t -xfs_sendfile( - bhv_desc_t *bdp, - struct file *filp, - loff_t *offset, - int ioflags, - size_t count, - read_actor_t actor, - void *target, - cred_t *credp) -{ - xfs_inode_t *ip = XFS_BHVTOI(bdp); - xfs_mount_t *mp = ip->i_mount; - ssize_t ret; - - XFS_STATS_INC(xs_read_calls); - if (XFS_FORCED_SHUTDOWN(mp)) - return -EIO; - - xfs_ilock(ip, XFS_IOLOCK_SHARED); - - if (DM_EVENT_ENABLED(BHV_TO_VNODE(bdp)->v_vfsp, ip, DM_EVENT_READ) && - (!(ioflags & IO_INVIS))) { - bhv_vrwlock_t locktype = VRWLOCK_READ; - int error; - - error = XFS_SEND_DATA(mp, DM_EVENT_READ, BHV_TO_VNODE(bdp), - *offset, count, - FILP_DELAY_FLAG(filp), &locktype); - if (error) { - xfs_iunlock(ip, XFS_IOLOCK_SHARED); - return -error; - } - } - xfs_rw_enter_trace(XFS_SENDFILE_ENTER, &ip->i_iocore, - (void *)(unsigned long)target, count, *offset, ioflags); - ret = generic_file_sendfile(filp, offset, count, actor, target); - if (ret > 0) - XFS_STATS_ADD(xs_read_bytes, ret); - - xfs_iunlock(ip, XFS_IOLOCK_SHARED); - return ret; -} - -ssize_t xfs_splice_read( bhv_desc_t *bdp, struct file *infilp, diff --git a/fs/xfs/linux-2.6/xfs_lrw.h b/fs/xfs/linux-2.6/xfs_lrw.h index 7ac51b1d216..7c60a1eed88 100644 --- a/fs/xfs/linux-2.6/xfs_lrw.h +++ b/fs/xfs/linux-2.6/xfs_lrw.h @@ -90,9 +90,6 @@ extern ssize_t xfs_read(struct bhv_desc *, struct kiocb *, extern ssize_t xfs_write(struct bhv_desc *, struct kiocb *, const struct iovec *, unsigned int, loff_t *, int, struct cred *); -extern ssize_t xfs_sendfile(struct bhv_desc *, struct file *, - loff_t *, int, size_t, read_actor_t, - void *, struct cred *); extern ssize_t xfs_splice_read(struct bhv_desc *, struct file *, loff_t *, struct pipe_inode_info *, size_t, int, int, struct cred *); diff --git a/fs/xfs/linux-2.6/xfs_vnode.h b/fs/xfs/linux-2.6/xfs_vnode.h index d1b2d01843d..013048a9264 100644 --- a/fs/xfs/linux-2.6/xfs_vnode.h +++ b/fs/xfs/linux-2.6/xfs_vnode.h @@ -139,9 +139,6 @@ typedef ssize_t (*vop_read_t)(bhv_desc_t *, struct kiocb *, typedef ssize_t (*vop_write_t)(bhv_desc_t *, struct kiocb *, const struct iovec *, unsigned int, loff_t *, int, struct cred *); -typedef ssize_t (*vop_sendfile_t)(bhv_desc_t *, struct file *, - loff_t *, int, size_t, read_actor_t, - void *, struct cred *); typedef ssize_t (*vop_splice_read_t)(bhv_desc_t *, struct file *, loff_t *, struct pipe_inode_info *, size_t, int, int, struct cred *); @@ -206,7 +203,6 @@ typedef struct bhv_vnodeops { vop_close_t vop_close; vop_read_t vop_read; vop_write_t vop_write; - vop_sendfile_t vop_sendfile; vop_splice_read_t vop_splice_read; vop_splice_write_t vop_splice_write; vop_ioctl_t vop_ioctl; @@ -254,8 +250,6 @@ typedef struct bhv_vnodeops { VOP(vop_read, vp)(VNHEAD(vp),file,iov,segs,offset,ioflags,cr) #define bhv_vop_write(vp,file,iov,segs,offset,ioflags,cr) \ VOP(vop_write, vp)(VNHEAD(vp),file,iov,segs,offset,ioflags,cr) -#define bhv_vop_sendfile(vp,f,off,ioflags,cnt,act,targ,cr) \ - VOP(vop_sendfile, vp)(VNHEAD(vp),f,off,ioflags,cnt,act,targ,cr) #define bhv_vop_splice_read(vp,f,o,pipe,cnt,fl,iofl,cr) \ VOP(vop_splice_read, vp)(VNHEAD(vp),f,o,pipe,cnt,fl,iofl,cr) #define bhv_vop_splice_write(vp,f,o,pipe,cnt,fl,iofl,cr) \ diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c index de17aed578f..70bc82f6531 100644 --- a/fs/xfs/xfs_vnodeops.c +++ b/fs/xfs/xfs_vnodeops.c @@ -4680,9 +4680,6 @@ bhv_vnodeops_t xfs_vnodeops = { .vop_open = xfs_open, .vop_close = xfs_close, .vop_read = xfs_read, -#ifdef HAVE_SENDFILE - .vop_sendfile = xfs_sendfile, -#endif #ifdef HAVE_SPLICE .vop_splice_read = xfs_splice_read, .vop_splice_write = xfs_splice_write, |