diff options
Diffstat (limited to 'fs')
100 files changed, 2644 insertions, 1243 deletions
diff --git a/fs/adfs/file.c b/fs/adfs/file.c index f544a2855923..36e381c6a99a 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 c8796906f584..c314a35f0918 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 9c0e721d9fc2..aede7eb66dd4 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 329ee473eede..521ff7caadbd 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 ef4d1fa04e65..24310e9ee05a 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 ea1480a16f51..b3e9bfa748cf 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 7c04752b76cb..8b0cbf4a4ad0 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 5ef2b609ec7d..99dbe866816d 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/dlm/Makefile b/fs/dlm/Makefile index 604cf7dc5f39..d248e60951ba 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 822abdcd1434..5069b2cb5a1f 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 967cc3d72e5e..a3170fe22090 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 61ba670b9e02..12c3bfd5e660 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 30994d68f6a0..74901e981e10 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 d8d6e729f96b..b455919c1998 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 64fc4ec40668..1720313c22df 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 a677b2a5eed4..1dc72105ab12 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 27970a58d29b..0553a6158dcb 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 162fbae58fe5..eca2907f2386 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 85e2897bd740..073599dced2a 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 000000000000..863b87d0dc71 --- /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 6bfbd6153809..e3a1527cbdbe 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 3cb636d60249..66575997861c 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 b0201ec325a7..6438941ab1f8 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 59288d817078..94f456fe4d9b 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/ext2/file.c b/fs/ext2/file.c index 566d4e2d3852..04afeecaaef3 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 1e6f13864536..acc4913d3019 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 3c6c1fd2be90..d4c8186aed64 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 55d3c7461c5b..69a83b59dce8 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 adf7995232b8..f79de7c8cdfa 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 e3f1ada643ac..04ad0caebedb 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 c53a5d2d0590..cd805a66880d 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 683cb5bda870..3548d9f31e0d 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 a96fa07b3f3b..2beb2f401aa2 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 48fe89046bba..8a468cac9328 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 5b83ca6acab1..2a7435b5c4dc 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 1815429a2978..3f0974e1afef 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 b3e152db70c8..7721ca3fff9e 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 7b82657a9910..777ca46010e8 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 d995441373ab..170ba93829c0 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 df0b8b3018b9..34f7bcdea1e9 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 b57f448b15bc..4517ac82c01c 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 c305255bfe8a..542a797ac89a 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 d074c6e6f9bf..24d70f73b651 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 1d8faa3da8af..41c5b04caaba 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 f82495e18c2d..fba1f1d87e4f 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 9cf1f168eaf8..1aca51e45092 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 291415ddfe51..f49a12e24086 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 f82d84d05d23..aff70f0698fd 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 965bc65c7c64..41a00df75587 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 e62d4f620c58..8da343b34ae7 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 e037425bc042..527bf19d9690 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 4864659555d4..6f006a804db3 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 d9ecfd23a49e..000000000000 --- 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 30c15622174f..26c888890c24 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 35aaee4aa7e1..fa1b5b3d28b9 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 a6fdc52f554a..793e334d098e 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 aad918337a46..99ea5659bc2c 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 f925a955b3b8..000000000000 --- 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 064df8804582..196d83266e34 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 2c5f8e7def0d..cf5aa5050548 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 7cc2c296271b..407029b3b2b3 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 d85f6e05cb95..911c115b5c6c 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 485ce3d49923..603d940f1159 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 aa0dbd2aac1b..404b7cc9f8c4 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 c186857e48a8..6e546ee8f3d4 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 8bc182c7e2ef..5ada38c99a2c 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 1727f5012efe..e4e040625153 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 b01e0cfc99b5..b4c6adfc6f2e 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 4fdda974dc83..f916b9740c75 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 e590b2df11dc..60a870e430be 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 601eaa1b9ed6..424a0774eda8 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 9a934db0bd8a..bc835f272a6e 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 45dab5d6cc10..409ce5429c91 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 8286491dbf31..c77862032e84 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 b4eafc0f1e54..5b53e5c5d8df 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 99871279a1ed..c2530197be0c 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/file.c b/fs/jfs/file.c index f7f8eff19b7b..87eb93694af7 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/minix/file.c b/fs/minix/file.c index f92baa1d7570..17765f697e50 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 9eb8eb4e4a08..8689b736fdd9 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 7e6aa245b5d5..8604e35bd48e 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 7ed56390b582..ffcc504a1667 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/file.c b/fs/ocfs2/file.c index ac6c96431bbc..4979b6675717 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/pipe.c b/fs/pipe.c index 3a89592bdf57..d007830d9c87 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/qnx4/file.c b/fs/qnx4/file.c index 44649981bbc8..867f42b02035 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 2f14774a124f..97bdc0b2f9d2 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 5d258c40a2fd..cad2b7ace630 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 4d03008f015b..507ddff48a9a 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 9e451a68580f..30eebfb1b2d8 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/smbfs/file.c b/fs/smbfs/file.c index aea3f8aa54c0..c5d78a7e492b 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 e7d7080de2f9..ed2ce995475c 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> @@ -29,22 +29,6 @@ #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 */ -}; - /* * Attempt to steal a page from a pipe buffer. This should perhaps go into * a vm helper function, it's already simplified quite a bit by the @@ -101,8 +85,12 @@ 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 +131,7 @@ 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 +151,25 @@ 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 +196,7 @@ 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 +292,15 @@ __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 +462,16 @@ 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, @@ -528,11 +525,11 @@ 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 +563,7 @@ 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 +573,7 @@ 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 +660,37 @@ 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 +702,10 @@ 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 +717,7 @@ ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, do_wakeup = 1; } - if (!sd.total_len) + if (!sd->total_len) break; } @@ -732,7 +730,7 @@ 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 +764,32 @@ 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 +798,7 @@ 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 +808,14 @@ 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 +824,12 @@ 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 +837,7 @@ 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 +867,13 @@ 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 +924,15 @@ 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, @@ -956,14 +986,27 @@ static long do_splice_to(struct file *in, loff_t *ppos, 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 @@ -999,7 +1042,13 @@ 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; + + /* + * Don't block on output, we have to drain the direct pipe. + */ + sd->flags &= ~SPLICE_F_NONBLOCK; while (len) { size_t read_len, max_read_len; @@ -1009,19 +1058,19 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, */ max_read_len = min(len, (size_t)(PIPE_BUFFERS*PAGE_SIZE)); - ret = do_splice_to(in, ppos, pipe, max_read_len, flags); + ret = do_splice_to(in, &sd->pos, pipe, max_read_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); + ret = actor(pipe, sd); if (unlikely(ret < 0)) goto out_release; @@ -1066,6 +1115,48 @@ 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, + }; + size_t ret; + + ret = splice_direct_to_actor(in, &sd, direct_splice_actor); + *ppos = sd.pos; + return ret; } /* @@ -1248,28 +1339,131 @@ 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 +1478,6 @@ 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 +1487,22 @@ 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 +1510,18 @@ 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/sysv/file.c b/fs/sysv/file.c index 0732ddb9020b..589be21d884e 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 51b5764685e7..df070bee8d4f 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 1e096323bad4..6705d74c6d2d 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 cb51dc961355..8c43cd2e237a 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 715adad7dd4d..af24a457d3a3 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 ed90403f0ee7..765ec16a6e39 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 7ac51b1d2161..7c60a1eed88b 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 d1b2d01843d1..013048a92643 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 de17aed578f0..70bc82f65311 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, |