diff options
Diffstat (limited to 'fs')
37 files changed, 601 insertions, 206 deletions
diff --git a/fs/cramfs/Kconfig b/fs/cramfs/Kconfig index cd06466f365e..11b29d491b7c 100644 --- a/fs/cramfs/Kconfig +++ b/fs/cramfs/Kconfig @@ -1,5 +1,5 @@ config CRAMFS - tristate "Compressed ROM file system support (cramfs)" + tristate "Compressed ROM file system support (cramfs) (OBSOLETE)" depends on BLOCK select ZLIB_INFLATE help @@ -16,4 +16,7 @@ config CRAMFS cramfs. Note that the root file system (the one containing the directory /) cannot be compiled as a module. + This filesystem is obsoleted by SquashFS, which is much better + in terms of performance and features. + If unsure, say N. diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index c7c83ff0f752..9c0444cccbe1 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -566,8 +566,7 @@ void debugfs_remove_recursive(struct dentry *dentry) mutex_lock(&parent->d_inode->i_mutex); if (child != dentry) { - next = list_entry(child->d_u.d_child.next, struct dentry, - d_u.d_child); + next = list_next_entry(child, d_u.d_child); goto up; } diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 073d30b9d1ac..a726b9f29cb7 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -498,6 +498,7 @@ static void devpts_kill_sb(struct super_block *sb) { struct pts_fs_info *fsi = DEVPTS_SB(sb); + ida_destroy(&fsi->allocated_ptys); kfree(fsi); kill_litter_super(sb); } diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 983e3960abff..79b65c3b9e87 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -41,6 +41,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/compat.h> +#include <linux/rculist.h> /* * LOCKING: @@ -133,8 +134,12 @@ struct nested_calls { * of these on a server and we do not want this to take another cache line. */ struct epitem { - /* RB tree node used to link this structure to the eventpoll RB tree */ - struct rb_node rbn; + union { + /* RB tree node links this structure to the eventpoll RB tree */ + struct rb_node rbn; + /* Used to free the struct epitem */ + struct rcu_head rcu; + }; /* List header used to link this structure to the eventpoll ready list */ struct list_head rdllink; @@ -580,14 +585,14 @@ static inline void ep_pm_stay_awake_rcu(struct epitem *epi) * @sproc: Pointer to the scan callback. * @priv: Private opaque data passed to the @sproc callback. * @depth: The current depth of recursive f_op->poll calls. + * @ep_locked: caller already holds ep->mtx * * Returns: The same integer error code returned by the @sproc callback. */ static int ep_scan_ready_list(struct eventpoll *ep, int (*sproc)(struct eventpoll *, struct list_head *, void *), - void *priv, - int depth) + void *priv, int depth, bool ep_locked) { int error, pwake = 0; unsigned long flags; @@ -598,7 +603,9 @@ static int ep_scan_ready_list(struct eventpoll *ep, * We need to lock this because we could be hit by * eventpoll_release_file() and epoll_ctl(). */ - mutex_lock_nested(&ep->mtx, depth); + + if (!ep_locked) + mutex_lock_nested(&ep->mtx, depth); /* * Steal the ready list, and re-init the original one to the @@ -662,7 +669,8 @@ static int ep_scan_ready_list(struct eventpoll *ep, } spin_unlock_irqrestore(&ep->lock, flags); - mutex_unlock(&ep->mtx); + if (!ep_locked) + mutex_unlock(&ep->mtx); /* We have to call this outside the lock */ if (pwake) @@ -671,6 +679,12 @@ static int ep_scan_ready_list(struct eventpoll *ep, return error; } +static void epi_rcu_free(struct rcu_head *head) +{ + struct epitem *epi = container_of(head, struct epitem, rcu); + kmem_cache_free(epi_cache, epi); +} + /* * Removes a "struct epitem" from the eventpoll RB tree and deallocates * all the associated resources. Must be called with "mtx" held. @@ -692,8 +706,7 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi) /* Remove the current item from the list of epoll hooks */ spin_lock(&file->f_lock); - if (ep_is_linked(&epi->fllink)) - list_del_init(&epi->fllink); + list_del_rcu(&epi->fllink); spin_unlock(&file->f_lock); rb_erase(&epi->rbn, &ep->rbr); @@ -704,9 +717,14 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi) spin_unlock_irqrestore(&ep->lock, flags); wakeup_source_unregister(ep_wakeup_source(epi)); - - /* At this point it is safe to free the eventpoll item */ - kmem_cache_free(epi_cache, epi); + /* + * At this point it is safe to free the eventpoll item. Use the union + * field epi->rcu, since we are trying to minimize the size of + * 'struct epitem'. The 'rbn' field is no longer in use. Protected by + * ep->mtx. The rcu read side, reverse_path_check_proc(), does not make + * use of the rbn field. + */ + call_rcu(&epi->rcu, epi_rcu_free); atomic_long_dec(&ep->user->epoll_watches); @@ -807,15 +825,34 @@ static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head, return 0; } +static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead, + poll_table *pt); + +struct readyevents_arg { + struct eventpoll *ep; + bool locked; +}; + static int ep_poll_readyevents_proc(void *priv, void *cookie, int call_nests) { - return ep_scan_ready_list(priv, ep_read_events_proc, NULL, call_nests + 1); + struct readyevents_arg *arg = priv; + + return ep_scan_ready_list(arg->ep, ep_read_events_proc, NULL, + call_nests + 1, arg->locked); } static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait) { int pollflags; struct eventpoll *ep = file->private_data; + struct readyevents_arg arg; + + /* + * During ep_insert() we already hold the ep->mtx for the tfile. + * Prevent re-aquisition. + */ + arg.locked = wait && (wait->_qproc == ep_ptable_queue_proc); + arg.ep = ep; /* Insert inside our poll wait queue */ poll_wait(file, &ep->poll_wait, wait); @@ -827,7 +864,7 @@ static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait) * could re-enter here. */ pollflags = ep_call_nested(&poll_readywalk_ncalls, EP_MAX_NESTS, - ep_poll_readyevents_proc, ep, ep, current); + ep_poll_readyevents_proc, &arg, ep, current); return pollflags != -1 ? pollflags : 0; } @@ -872,7 +909,6 @@ static const struct file_operations eventpoll_fops = { */ void eventpoll_release_file(struct file *file) { - struct list_head *lsthead = &file->f_ep_links; struct eventpoll *ep; struct epitem *epi; @@ -890,17 +926,12 @@ void eventpoll_release_file(struct file *file) * Besides, ep_remove() acquires the lock, so we can't hold it here. */ mutex_lock(&epmutex); - - while (!list_empty(lsthead)) { - epi = list_first_entry(lsthead, struct epitem, fllink); - + list_for_each_entry_rcu(epi, &file->f_ep_links, fllink) { ep = epi->ep; - list_del_init(&epi->fllink); mutex_lock_nested(&ep->mtx, 0); ep_remove(ep, epi); mutex_unlock(&ep->mtx); } - mutex_unlock(&epmutex); } @@ -1138,7 +1169,9 @@ static int reverse_path_check_proc(void *priv, void *cookie, int call_nests) struct file *child_file; struct epitem *epi; - list_for_each_entry(epi, &file->f_ep_links, fllink) { + /* CTL_DEL can remove links here, but that can't increase our count */ + rcu_read_lock(); + list_for_each_entry_rcu(epi, &file->f_ep_links, fllink) { child_file = epi->ep->file; if (is_file_epoll(child_file)) { if (list_empty(&child_file->f_ep_links)) { @@ -1160,6 +1193,7 @@ static int reverse_path_check_proc(void *priv, void *cookie, int call_nests) "file is not an ep!\n"); } } + rcu_read_unlock(); return error; } @@ -1231,7 +1265,7 @@ static noinline void ep_destroy_wakeup_source(struct epitem *epi) * Must be called with "mtx" held. */ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, - struct file *tfile, int fd) + struct file *tfile, int fd, int full_check) { int error, revents, pwake = 0; unsigned long flags; @@ -1286,7 +1320,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, /* Add the current item to the list of active epoll hook for this file */ spin_lock(&tfile->f_lock); - list_add_tail(&epi->fllink, &tfile->f_ep_links); + list_add_tail_rcu(&epi->fllink, &tfile->f_ep_links); spin_unlock(&tfile->f_lock); /* @@ -1297,7 +1331,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, /* now check if we've created too many backpaths */ error = -EINVAL; - if (reverse_path_check()) + if (full_check && reverse_path_check()) goto error_remove_epi; /* We have to drop the new item inside our item list to keep track of it */ @@ -1327,8 +1361,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, error_remove_epi: spin_lock(&tfile->f_lock); - if (ep_is_linked(&epi->fllink)) - list_del_init(&epi->fllink); + list_del_rcu(&epi->fllink); spin_unlock(&tfile->f_lock); rb_erase(&epi->rbn, &ep->rbr); @@ -1521,7 +1554,7 @@ static int ep_send_events(struct eventpoll *ep, esed.maxevents = maxevents; esed.events = events; - return ep_scan_ready_list(ep, ep_send_events_proc, &esed, 0); + return ep_scan_ready_list(ep, ep_send_events_proc, &esed, 0, false); } static inline struct timespec ep_set_mstimeout(long ms) @@ -1791,11 +1824,12 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, struct epoll_event __user *, event) { int error; - int did_lock_epmutex = 0; + int full_check = 0; struct fd f, tf; struct eventpoll *ep; struct epitem *epi; struct epoll_event epds; + struct eventpoll *tep = NULL; error = -EFAULT; if (ep_op_has_event(op) && @@ -1844,26 +1878,40 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, * and hang them on the tfile_check_list, so we can check that we * haven't created too many possible wakeup paths. * - * We need to hold the epmutex across both ep_insert and ep_remove - * b/c we want to make sure we are looking at a coherent view of - * epoll network. + * We do not need to take the global 'epumutex' on EPOLL_CTL_ADD when + * the epoll file descriptor is attaching directly to a wakeup source, + * unless the epoll file descriptor is nested. The purpose of taking the + * 'epmutex' on add is to prevent complex toplogies such as loops and + * deep wakeup paths from forming in parallel through multiple + * EPOLL_CTL_ADD operations. */ - if (op == EPOLL_CTL_ADD || op == EPOLL_CTL_DEL) { - mutex_lock(&epmutex); - did_lock_epmutex = 1; - } + mutex_lock_nested(&ep->mtx, 0); if (op == EPOLL_CTL_ADD) { - if (is_file_epoll(tf.file)) { - error = -ELOOP; - if (ep_loop_check(ep, tf.file) != 0) { - clear_tfile_check_list(); - goto error_tgt_fput; + if (!list_empty(&f.file->f_ep_links) || + is_file_epoll(tf.file)) { + full_check = 1; + mutex_unlock(&ep->mtx); + mutex_lock(&epmutex); + if (is_file_epoll(tf.file)) { + error = -ELOOP; + if (ep_loop_check(ep, tf.file) != 0) { + clear_tfile_check_list(); + goto error_tgt_fput; + } + } else + list_add(&tf.file->f_tfile_llink, + &tfile_check_list); + mutex_lock_nested(&ep->mtx, 0); + if (is_file_epoll(tf.file)) { + tep = tf.file->private_data; + mutex_lock_nested(&tep->mtx, 1); } - } else - list_add(&tf.file->f_tfile_llink, &tfile_check_list); + } + } + if (op == EPOLL_CTL_DEL && is_file_epoll(tf.file)) { + tep = tf.file->private_data; + mutex_lock_nested(&tep->mtx, 1); } - - mutex_lock_nested(&ep->mtx, 0); /* * Try to lookup the file inside our RB tree, Since we grabbed "mtx" @@ -1877,10 +1925,11 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, case EPOLL_CTL_ADD: if (!epi) { epds.events |= POLLERR | POLLHUP; - error = ep_insert(ep, &epds, tf.file, fd); + error = ep_insert(ep, &epds, tf.file, fd, full_check); } else error = -EEXIST; - clear_tfile_check_list(); + if (full_check) + clear_tfile_check_list(); break; case EPOLL_CTL_DEL: if (epi) @@ -1896,10 +1945,12 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, error = -ENOENT; break; } + if (tep != NULL) + mutex_unlock(&tep->mtx); mutex_unlock(&ep->mtx); error_tgt_fput: - if (did_lock_epmutex) + if (full_check) mutex_unlock(&epmutex); fdput(tf); diff --git a/fs/exec.c b/fs/exec.c index be4c81c7251c..977319fd77f3 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1664,6 +1664,12 @@ int __get_dumpable(unsigned long mm_flags) return (ret > SUID_DUMP_USER) ? SUID_DUMP_ROOT : ret; } +/* + * This returns the actual value of the suid_dumpable flag. For things + * that are using this for checking for privilege transitions, it must + * test against SUID_DUMP_USER rather than treating it as a boolean + * value. + */ int get_dumpable(struct mm_struct *mm) { return __get_dumpable(mm->flags); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 09c11329a17c..1f4a10ece2f1 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -40,13 +40,18 @@ struct wb_writeback_work { long nr_pages; struct super_block *sb; - unsigned long *older_than_this; + /* + * Write only inodes dirtied before this time. Don't forget to set + * older_than_this_is_set when you set this. + */ + unsigned long older_than_this; enum writeback_sync_modes sync_mode; unsigned int tagged_writepages:1; unsigned int for_kupdate:1; unsigned int range_cyclic:1; unsigned int for_background:1; unsigned int for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ + unsigned int older_than_this_is_set:1; enum wb_reason reason; /* why was writeback initiated? */ struct list_head list; /* pending work list */ @@ -247,10 +252,10 @@ static int move_expired_inodes(struct list_head *delaying_queue, int do_sb_sort = 0; int moved = 0; + WARN_ON_ONCE(!work->older_than_this_is_set); while (!list_empty(delaying_queue)) { inode = wb_inode(delaying_queue->prev); - if (work->older_than_this && - inode_dirtied_after(inode, *work->older_than_this)) + if (inode_dirtied_after(inode, work->older_than_this)) break; list_move(&inode->i_wb_list, &tmp); moved++; @@ -734,6 +739,8 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = reason, + .older_than_this = jiffies, + .older_than_this_is_set = 1, }; spin_lock(&wb->list_lock); @@ -792,12 +799,13 @@ static long wb_writeback(struct bdi_writeback *wb, { unsigned long wb_start = jiffies; long nr_pages = work->nr_pages; - unsigned long oldest_jif; struct inode *inode; long progress; - oldest_jif = jiffies; - work->older_than_this = &oldest_jif; + if (!work->older_than_this_is_set) { + work->older_than_this = jiffies; + work->older_than_this_is_set = 1; + } spin_lock(&wb->list_lock); for (;;) { @@ -831,10 +839,10 @@ static long wb_writeback(struct bdi_writeback *wb, * safe. */ if (work->for_kupdate) { - oldest_jif = jiffies - + work->older_than_this = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); } else if (work->for_background) - oldest_jif = jiffies; + work->older_than_this = jiffies; trace_writeback_start(wb->bdi, work); if (list_empty(&wb->b_io)) @@ -1346,18 +1354,21 @@ EXPORT_SYMBOL(try_to_writeback_inodes_sb); /** * sync_inodes_sb - sync sb inode pages - * @sb: the superblock + * @sb: the superblock + * @older_than_this: timestamp * * This function writes and waits on any dirty inode belonging to this - * super_block. + * superblock that has been dirtied before given timestamp. */ -void sync_inodes_sb(struct super_block *sb) +void sync_inodes_sb(struct super_block *sb, unsigned long older_than_this) { DECLARE_COMPLETION_ONSTACK(done); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_ALL, .nr_pages = LONG_MAX, + .older_than_this = older_than_this, + .older_than_this_is_set = 1, .range_cyclic = 0, .done = &done, .reason = WB_REASON_SYNC, diff --git a/fs/hfs/btree.h b/fs/hfs/btree.h index 2a1d712f85dc..f6bd266d70b5 100644 --- a/fs/hfs/btree.h +++ b/fs/hfs/btree.h @@ -153,11 +153,6 @@ struct hfs_btree_header_rec { u32 reserved3[16]; } __packed; -#define HFS_NODE_INDEX 0x00 /* An internal (index) node */ -#define HFS_NODE_HEADER 0x01 /* The tree header node (node 0) */ -#define HFS_NODE_MAP 0x02 /* Holds part of the bitmap of used nodes */ -#define HFS_NODE_LEAF 0xFF /* A leaf (ndNHeight==1) node */ - #define BTREE_ATTR_BADCLOSE 0x00000001 /* b-tree not closed properly. not used by hfsplus. */ #define HFS_TREE_BIGKEYS 0x00000002 /* key length is u16 instead of u8. diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c index 0c6540c91167..0fcec8b2a90b 100644 --- a/fs/hfsplus/btree.c +++ b/fs/hfsplus/btree.c @@ -15,6 +15,118 @@ #include "hfsplus_fs.h" #include "hfsplus_raw.h" +/* + * Initial source code of clump size calculation is gotten + * from http://opensource.apple.com/tarballs/diskdev_cmds/ + */ +#define CLUMP_ENTRIES 15 + +static short clumptbl[CLUMP_ENTRIES * 3] = { +/* + * Volume Attributes Catalog Extents + * Size Clump (MB) Clump (MB) Clump (MB) + */ + /* 1GB */ 4, 4, 4, + /* 2GB */ 6, 6, 4, + /* 4GB */ 8, 8, 4, + /* 8GB */ 11, 11, 5, + /* + * For volumes 16GB and larger, we want to make sure that a full OS + * install won't require fragmentation of the Catalog or Attributes + * B-trees. We do this by making the clump sizes sufficiently large, + * and by leaving a gap after the B-trees for them to grow into. + * + * For SnowLeopard 10A298, a FullNetInstall with all packages selected + * results in: + * Catalog B-tree Header + * nodeSize: 8192 + * totalNodes: 31616 + * freeNodes: 1978 + * (used = 231.55 MB) + * Attributes B-tree Header + * nodeSize: 8192 + * totalNodes: 63232 + * freeNodes: 958 + * (used = 486.52 MB) + * + * We also want Time Machine backup volumes to have a sufficiently + * large clump size to reduce fragmentation. + * + * The series of numbers for Catalog and Attribute form a geometric + * series. For Catalog (16GB to 512GB), each term is 8**(1/5) times + * the previous term. For Attributes (16GB to 512GB), each term is + * 4**(1/5) times the previous term. For 1TB to 16TB, each term is + * 2**(1/5) times the previous term. + */ + /* 16GB */ 64, 32, 5, + /* 32GB */ 84, 49, 6, + /* 64GB */ 111, 74, 7, + /* 128GB */ 147, 111, 8, + /* 256GB */ 194, 169, 9, + /* 512GB */ 256, 256, 11, + /* 1TB */ 294, 294, 14, + /* 2TB */ 338, 338, 16, + /* 4TB */ 388, 388, 20, + /* 8TB */ 446, 446, 25, + /* 16TB */ 512, 512, 32 +}; + +u32 hfsplus_calc_btree_clump_size(u32 block_size, u32 node_size, + u64 sectors, int file_id) +{ + u32 mod = max(node_size, block_size); + u32 clump_size; + int column; + int i; + + /* Figure out which column of the above table to use for this file. */ + switch (file_id) { + case HFSPLUS_ATTR_CNID: + column = 0; + break; + case HFSPLUS_CAT_CNID: + column = 1; + break; + default: + column = 2; + break; + } + + /* + * The default clump size is 0.8% of the volume size. And + * it must also be a multiple of the node and block size. + */ + if (sectors < 0x200000) { + clump_size = sectors << 2; /* 0.8 % */ + if (clump_size < (8 * node_size)) + clump_size = 8 * node_size; + } else { + /* turn exponent into table index... */ + for (i = 0, sectors = sectors >> 22; + sectors && (i < CLUMP_ENTRIES - 1); + ++i, sectors = sectors >> 1) { + /* empty body */ + } + + clump_size = clumptbl[column + (i) * 3] * 1024 * 1024; + } + + /* + * Round the clump size to a multiple of node and block size. + * NOTE: This rounds down. + */ + clump_size /= mod; + clump_size *= mod; + + /* + * Rounding down could have rounded down to 0 if the block size was + * greater than the clump size. If so, just use one block or node. + */ + if (clump_size == 0) + clump_size = mod; + + return clump_size; +} /* Get a reference to a B*Tree and do some initial checks */ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id) diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index 2b9cd01696e2..08846425b67f 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -127,6 +127,14 @@ struct hfs_bnode { #define HFS_BNODE_DELETED 4 /* + * Attributes file states + */ +#define HFSPLUS_EMPTY_ATTR_TREE 0 +#define HFSPLUS_CREATING_ATTR_TREE 1 +#define HFSPLUS_VALID_ATTR_TREE 2 +#define HFSPLUS_FAILED_ATTR_TREE 3 + +/* * HFS+ superblock info (built from Volume Header on disk) */ @@ -141,6 +149,7 @@ struct hfsplus_sb_info { struct hfs_btree *ext_tree; struct hfs_btree *cat_tree; struct hfs_btree *attr_tree; + atomic_t attr_tree_state; struct inode *alloc_file; struct inode *hidden_dir; struct nls_table *nls; @@ -380,6 +389,7 @@ int hfsplus_block_allocate(struct super_block *, u32, u32, u32 *); int hfsplus_block_free(struct super_block *, u32, u32); /* btree.c */ +u32 hfsplus_calc_btree_clump_size(u32, u32, u64, int); struct hfs_btree *hfs_btree_open(struct super_block *, u32); void hfs_btree_close(struct hfs_btree *); int hfs_btree_write(struct hfs_btree *); diff --git a/fs/hfsplus/hfsplus_raw.h b/fs/hfsplus/hfsplus_raw.h index 452ede01b036..8ffb3a8ffe75 100644 --- a/fs/hfsplus/hfsplus_raw.h +++ b/fs/hfsplus/hfsplus_raw.h @@ -156,10 +156,10 @@ struct hfs_bnode_desc { } __packed; /* HFS+ BTree node types */ -#define HFS_NODE_INDEX 0x00 -#define HFS_NODE_HEADER 0x01 -#define HFS_NODE_MAP 0x02 -#define HFS_NODE_LEAF 0xFF +#define HFS_NODE_INDEX 0x00 /* An internal (index) node */ +#define HFS_NODE_HEADER 0x01 /* The tree header node (node 0) */ +#define HFS_NODE_MAP 0x02 /* Holds part of the bitmap of used nodes */ +#define HFS_NODE_LEAF 0xFF /* A leaf (ndNHeight==1) node */ /* HFS+ BTree header */ struct hfs_btree_header_rec { @@ -187,6 +187,9 @@ struct hfs_btree_header_rec { /* HFS+ BTree misc info */ #define HFSPLUS_TREE_HEAD 0 #define HFSPLUS_NODE_MXSZ 32768 +#define HFSPLUS_ATTR_TREE_NODE_SIZE 8192 +#define HFSPLUS_BTREE_HDR_NODE_RECS_COUNT 3 +#define HFSPLUS_BTREE_HDR_USER_BYTES 128 /* Some special File ID numbers (stolen from hfs.h) */ #define HFSPLUS_POR_CNID 1 /* Parent Of the Root */ diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 4c4d142cf890..80875aa640ef 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -474,12 +474,14 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) pr_err("failed to load catalog file\n"); goto out_close_ext_tree; } + atomic_set(&sbi->attr_tree_state, HFSPLUS_EMPTY_ATTR_TREE); if (vhdr->attr_file.total_blocks != 0) { sbi->attr_tree = hfs_btree_open(sb, HFSPLUS_ATTR_CNID); if (!sbi->attr_tree) { pr_err("failed to load attributes file\n"); goto out_close_cat_tree; } + atomic_set(&sbi->attr_tree_state, HFSPLUS_VALID_ATTR_TREE); } sb->s_xattr = hfsplus_xattr_handlers; diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c index bd8471fb9a6a..efc85b1377cc 100644 --- a/fs/hfsplus/xattr.c +++ b/fs/hfsplus/xattr.c @@ -127,6 +127,208 @@ static int can_set_xattr(struct inode *inode, const char *name, return 0; } +static void hfsplus_init_header_node(struct inode *attr_file, + u32 clump_size, + char *buf, size_t node_size) +{ + struct hfs_bnode_desc *desc; + struct hfs_btree_header_rec *head; + u16 offset; + __be16 *rec_offsets; + u32 hdr_node_map_rec_bits; + char *bmp; + u32 used_nodes; + u32 used_bmp_bytes; + + hfs_dbg(ATTR_MOD, "init_hdr_attr_file: clump %u, node_size %zu\n", + clump_size, node_size); + + /* The end of the node contains list of record offsets */ + rec_offsets = (__be16 *)(buf + node_size); + + desc = (struct hfs_bnode_desc *)buf; + desc->type = HFS_NODE_HEADER; + desc->num_recs = cpu_to_be16(HFSPLUS_BTREE_HDR_NODE_RECS_COUNT); + offset = sizeof(struct hfs_bnode_desc); + *--rec_offsets = cpu_to_be16(offset); + + head = (struct hfs_btree_header_rec *)(buf + offset); + head->node_size = cpu_to_be16(node_size); + head->node_count = cpu_to_be32(i_size_read(attr_file) / node_size); + head->free_nodes = cpu_to_be32(be32_to_cpu(head->node_count) - 1); + head->clump_size = cpu_to_be32(clump_size); + head->attributes |= cpu_to_be32(HFS_TREE_BIGKEYS | HFS_TREE_VARIDXKEYS); + head->max_key_len = cpu_to_be16(HFSPLUS_ATTR_KEYLEN - sizeof(u16)); + offset += sizeof(struct hfs_btree_header_rec); + *--rec_offsets = cpu_to_be16(offset); + offset += HFSPLUS_BTREE_HDR_USER_BYTES; + *--rec_offsets = cpu_to_be16(offset); + + hdr_node_map_rec_bits = 8 * (node_size - offset - (4 * sizeof(u16))); + if (be32_to_cpu(head->node_count) > hdr_node_map_rec_bits) { + u32 map_node_bits; + u32 map_nodes; + + desc->next = cpu_to_be32(be32_to_cpu(head->leaf_tail) + 1); + map_node_bits = 8 * (node_size - sizeof(struct hfs_bnode_desc) - + (2 * sizeof(u16)) - 2); + map_nodes = (be32_to_cpu(head->node_count) - + hdr_node_map_rec_bits + + (map_node_bits - 1)) / map_node_bits; + be32_add_cpu(&head->free_nodes, 0 - map_nodes); + } + + bmp = buf + offset; + used_nodes = + be32_to_cpu(head->node_count) - be32_to_cpu(head->free_nodes); + used_bmp_bytes = used_nodes / 8; + if (used_bmp_bytes) { + memset(bmp, 0xFF, used_bmp_bytes); + bmp += used_bmp_bytes; + used_nodes %= 8; + } + *bmp = ~(0xFF >> used_nodes); + offset += hdr_node_map_rec_bits / 8; + *--rec_offsets = cpu_to_be16(offset); +} + +static int hfsplus_create_attributes_file(struct super_block *sb) +{ + int err = 0; + struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); + struct inode *attr_file; + struct hfsplus_inode_info *hip; + u32 clump_size; + u16 node_size = HFSPLUS_ATTR_TREE_NODE_SIZE; + char *buf; + int index, written; + struct address_space *mapping; + struct page *page; + int old_state = HFSPLUS_EMPTY_ATTR_TREE; + + hfs_dbg(ATTR_MOD, "create_attr_file: ino %d\n", HFSPLUS_ATTR_CNID); + +check_attr_tree_state_again: + switch (atomic_read(&sbi->attr_tree_state)) { + case HFSPLUS_EMPTY_ATTR_TREE: + if (old_state != atomic_cmpxchg(&sbi->attr_tree_state, + old_state, + HFSPLUS_CREATING_ATTR_TREE)) + goto check_attr_tree_state_again; + break; + case HFSPLUS_CREATING_ATTR_TREE: + /* + * This state means that another thread is in process + * of AttributesFile creation. Theoretically, it is + * possible to be here. But really __setxattr() method + * first of all calls hfs_find_init() for lookup in + * B-tree of CatalogFile. This method locks mutex of + * CatalogFile's B-tree. As a result, if some thread + * is inside AttributedFile creation operation then + * another threads will be waiting unlocking of + * CatalogFile's B-tree's mutex. However, if code will + * change then we will return error code (-EAGAIN) from + * here. Really, it means that first try to set of xattr + * fails with error but second attempt will have success. + */ + return -EAGAIN; + case HFSPLUS_VALID_ATTR_TREE: + return 0; + case HFSPLUS_FAILED_ATTR_TREE: + return -EOPNOTSUPP; + default: + BUG(); + } + + attr_file = hfsplus_iget(sb, HFSPLUS_ATTR_CNID); + if (IS_ERR(attr_file)) { + pr_err("failed to load attributes file\n"); + return PTR_ERR(attr_file); + } + + BUG_ON(i_size_read(attr_file) != 0); + + hip = HFSPLUS_I(attr_file); + + clump_size = hfsplus_calc_btree_clump_size(sb->s_blocksize, + node_size, + sbi->sect_count, + HFSPLUS_ATTR_CNID); + + mutex_lock(&hip->extents_lock); + hip->clump_blocks = clump_size >> sbi->alloc_blksz_shift; + mutex_unlock(&hip->extents_lock); + + if (sbi->free_blocks <= (hip->clump_blocks << 1)) { + err = -ENOSPC; + goto end_attr_file_creation; + } + + while (hip->alloc_blocks < hip->clump_blocks) { + err = hfsplus_file_extend(attr_file); + if (unlikely(err)) { + pr_err("failed to extend attributes file\n"); + goto end_attr_file_creation; + } + hip->phys_size = attr_file->i_size = + (loff_t)hip->alloc_blocks << sbi->alloc_blksz_shift; + hip->fs_blocks = hip->alloc_blocks << sbi->fs_shift; + inode_set_bytes(attr_file, attr_file->i_size); + } + + buf = kzalloc(node_size, GFP_NOFS); + if (!buf) { + pr_err("failed to allocate memory for header node\n"); + err = -ENOMEM; + goto end_attr_file_creation; + } + + hfsplus_init_header_node(attr_file, clump_size, buf, node_size); + + mapping = attr_file->i_mapping; + + index = 0; + written = 0; + for (; written < node_size; index++, written += PAGE_CACHE_SIZE) { + void *kaddr; + + page = read_mapping_page(mapping, index, NULL); + if (IS_ERR(page)) { + err = PTR_ERR(page); + goto failed_header_node_init; + } + + kaddr = kmap_atomic(page); + memcpy(kaddr, buf + written, + min_t(size_t, PAGE_CACHE_SIZE, node_size - written)); + kunmap_atomic(kaddr); + + set_page_dirty(page); + page_cache_release(page); + } + + hfsplus_mark_inode_dirty(attr_file, HFSPLUS_I_ATTR_DIRTY); + + sbi->attr_tree = hfs_btree_open(sb, HFSPLUS_ATTR_CNID); + if (!sbi->attr_tree) + pr_err("failed to load attributes file\n"); + +failed_header_node_init: + kfree(buf); + +end_attr_file_creation: + iput(attr_file); + + if (!err) + atomic_set(&sbi->attr_tree_state, HFSPLUS_VALID_ATTR_TREE); + else if (err == -ENOSPC) + atomic_set(&sbi->attr_tree_state, HFSPLUS_EMPTY_ATTR_TREE); + else + atomic_set(&sbi->attr_tree_state, HFSPLUS_FAILED_ATTR_TREE); + + return err; +} + int __hfsplus_setxattr(struct inode *inode, const char *name, const void *value, size_t size, int flags) { @@ -211,8 +413,9 @@ int __hfsplus_setxattr(struct inode *inode, const char *name, } if (!HFSPLUS_SB(inode->i_sb)->attr_tree) { - err = -EOPNOTSUPP; - goto end_setxattr; + err = hfsplus_create_attributes_file(inode->i_sb); + if (unlikely(err)) + goto end_setxattr; } if (hfsplus_attr_exists(inode, name)) { diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 17e6bdde96c5..dc7411fe185d 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -1025,7 +1025,7 @@ static int ocfs2_create_new_meta_bhs(handle_t *handle, for(i = count; i < (num_got + count); i++) { bhs[i] = sb_getblk(osb->sb, first_blkno); if (bhs[i] == NULL) { - status = -EIO; + status = -ENOMEM; mlog_errno(status); goto bail; } diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index f37d3c0e2053..aeb44e879c51 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -80,6 +80,7 @@ static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock, if ((u64)iblock >= ocfs2_clusters_to_blocks(inode->i_sb, le32_to_cpu(fe->i_clusters))) { + err = -ENOMEM; mlog(ML_ERROR, "block offset is outside the allocated size: " "%llu\n", (unsigned long long)iblock); goto bail; @@ -92,6 +93,7 @@ static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock, iblock; buffer_cache_bh = sb_getblk(osb->sb, blkno); if (!buffer_cache_bh) { + err = -ENOMEM; mlog(ML_ERROR, "couldn't getblock for symlink!\n"); goto bail; } @@ -592,26 +594,11 @@ static void ocfs2_dio_end_io(struct kiocb *iocb, ocfs2_rw_unlock(inode, level); } -/* - * ocfs2_invalidatepage() and ocfs2_releasepage() are shamelessly stolen - * from ext3. PageChecked() bits have been removed as OCFS2 does not - * do journalled data. - */ -static void ocfs2_invalidatepage(struct page *page, unsigned int offset, - unsigned int length) -{ - journal_t *journal = OCFS2_SB(page->mapping->host->i_sb)->journal->j_journal; - - jbd2_journal_invalidatepage(journal, page, offset, length); -} - static int ocfs2_releasepage(struct page *page, gfp_t wait) { - journal_t *journal = OCFS2_SB(page->mapping->host->i_sb)->journal->j_journal; - if (!page_has_buffers(page)) return 0; - return jbd2_journal_try_to_free_buffers(journal, page, wait); + return try_to_free_buffers(page); } static ssize_t ocfs2_direct_IO(int rw, @@ -1802,8 +1789,7 @@ try_again: data_ac->ac_resv = &OCFS2_I(inode)->ip_la_data_resv; credits = ocfs2_calc_extend_credits(inode->i_sb, - &di->id2.i_list, - clusters_to_alloc); + &di->id2.i_list); } @@ -1897,10 +1883,14 @@ out_commit: out: ocfs2_free_write_ctxt(wc); - if (data_ac) + if (data_ac) { ocfs2_free_alloc_context(data_ac); - if (meta_ac) + data_ac = NULL; + } + if (meta_ac) { ocfs2_free_alloc_context(meta_ac); + meta_ac = NULL; + } if (ret == -ENOSPC && try_free) { /* @@ -2087,7 +2077,7 @@ const struct address_space_operations ocfs2_aops = { .write_end = ocfs2_write_end, .bmap = ocfs2_bmap, .direct_IO = ocfs2_direct_IO, - .invalidatepage = ocfs2_invalidatepage, + .invalidatepage = block_invalidatepage, .releasepage = ocfs2_releasepage, .migratepage = buffer_migrate_page, .is_partially_uptodate = block_is_partially_uptodate, diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c index 5d18ad10c27f..5b704c63a103 100644 --- a/fs/ocfs2/buffer_head_io.c +++ b/fs/ocfs2/buffer_head_io.c @@ -115,7 +115,7 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block, if (bhs[i] == NULL) { bhs[i] = sb_getblk(osb->sb, block++); if (bhs[i] == NULL) { - status = -EIO; + status = -ENOMEM; mlog_errno(status); goto bail; } @@ -214,7 +214,7 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, bhs[i] = sb_getblk(sb, block++); if (bhs[i] == NULL) { ocfs2_metadata_cache_io_unlock(ci); - status = -EIO; + status = -ENOMEM; mlog_errno(status); goto bail; } diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 363f0dcc924f..73920ffda05b 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -35,6 +35,7 @@ #include <linux/time.h> #include <linux/debugfs.h> #include <linux/slab.h> +#include <linux/bitmap.h> #include "heartbeat.h" #include "tcp.h" @@ -282,15 +283,6 @@ struct o2hb_bio_wait_ctxt { int wc_error; }; -static int o2hb_pop_count(void *map, int count) -{ - int i = -1, pop = 0; - - while ((i = find_next_bit(map, count, i + 1)) < count) - pop++; - return pop; -} - static void o2hb_write_timeout(struct work_struct *work) { int failed, quorum; @@ -307,9 +299,9 @@ static void o2hb_write_timeout(struct work_struct *work) spin_lock_irqsave(&o2hb_live_lock, flags); if (test_bit(reg->hr_region_num, o2hb_quorum_region_bitmap)) set_bit(reg->hr_region_num, o2hb_failed_region_bitmap); - failed = o2hb_pop_count(&o2hb_failed_region_bitmap, + failed = bitmap_weight(o2hb_failed_region_bitmap, O2NM_MAX_REGIONS); - quorum = o2hb_pop_count(&o2hb_quorum_region_bitmap, + quorum = bitmap_weight(o2hb_quorum_region_bitmap, O2NM_MAX_REGIONS); spin_unlock_irqrestore(&o2hb_live_lock, flags); @@ -765,7 +757,7 @@ static void o2hb_set_quorum_device(struct o2hb_region *reg) * If global heartbeat active, unpin all regions if the * region count > CUT_OFF */ - if (o2hb_pop_count(&o2hb_quorum_region_bitmap, + if (bitmap_weight(o2hb_quorum_region_bitmap, O2NM_MAX_REGIONS) > O2HB_PIN_CUT_OFF) o2hb_region_unpin(NULL); unlock: @@ -954,23 +946,9 @@ out: return changed; } -/* This could be faster if we just implmented a find_last_bit, but I - * don't think the circumstances warrant it. */ -static int o2hb_highest_node(unsigned long *nodes, - int numbits) +static int o2hb_highest_node(unsigned long *nodes, int numbits) { - int highest, node; - - highest = numbits; - node = -1; - while ((node = find_next_bit(nodes, numbits, node + 1)) != -1) { - if (node >= numbits) - break; - - highest = node; - } - - return highest; + return find_last_bit(nodes, numbits); } static int o2hb_do_disk_heartbeat(struct o2hb_region *reg) @@ -1829,7 +1807,7 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg, live_threshold = O2HB_LIVE_THRESHOLD; if (o2hb_global_heartbeat_active()) { spin_lock(&o2hb_live_lock); - if (o2hb_pop_count(&o2hb_region_bitmap, O2NM_MAX_REGIONS) == 1) + if (bitmap_weight(o2hb_region_bitmap, O2NM_MAX_REGIONS) == 1) live_threshold <<= 1; spin_unlock(&o2hb_live_lock); } @@ -2180,7 +2158,7 @@ static void o2hb_heartbeat_group_drop_item(struct config_group *group, if (!o2hb_dependent_users) goto unlock; - if (o2hb_pop_count(&o2hb_quorum_region_bitmap, + if (bitmap_weight(o2hb_quorum_region_bitmap, O2NM_MAX_REGIONS) <= O2HB_PIN_CUT_OFF) o2hb_region_pin(NULL); @@ -2480,7 +2458,7 @@ static int o2hb_region_inc_user(const char *region_uuid) if (o2hb_dependent_users > 1) goto unlock; - if (o2hb_pop_count(&o2hb_quorum_region_bitmap, + if (bitmap_weight(o2hb_quorum_region_bitmap, O2NM_MAX_REGIONS) <= O2HB_PIN_CUT_OFF) ret = o2hb_region_pin(NULL); diff --git a/fs/ocfs2/cluster/masklog.h b/fs/ocfs2/cluster/masklog.h index baa2b9ef7eef..2260fb9e6508 100644 --- a/fs/ocfs2/cluster/masklog.h +++ b/fs/ocfs2/cluster/masklog.h @@ -199,7 +199,8 @@ extern struct mlog_bits mlog_and_bits, mlog_not_bits; #define mlog_errno(st) do { \ int _st = (st); \ if (_st != -ERESTARTSYS && _st != -EINTR && \ - _st != AOP_TRUNCATED_PAGE && _st != -ENOSPC) \ + _st != AOP_TRUNCATED_PAGE && _st != -ENOSPC && \ + _st != -EDQUOT) \ mlog(ML_ERROR, "status = %lld\n", (long long)_st); \ } while (0) diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 30544ce8e9f7..91a7e85ac8fd 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -2349,7 +2349,7 @@ static int ocfs2_dx_dir_attach_index(struct ocfs2_super *osb, dx_root_bh = sb_getblk(osb->sb, dr_blkno); if (dx_root_bh == NULL) { - ret = -EIO; + ret = -ENOMEM; goto out; } ocfs2_set_new_buffer_uptodate(INODE_CACHE(dir), dx_root_bh); @@ -2422,7 +2422,7 @@ static int ocfs2_dx_dir_format_cluster(struct ocfs2_super *osb, for (i = 0; i < num_dx_leaves; i++) { bh = sb_getblk(osb->sb, start_blk + i); if (bh == NULL) { - ret = -EIO; + ret = -ENOMEM; goto out; } dx_leaves[i] = bh; @@ -2929,7 +2929,7 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh, blkno = ocfs2_clusters_to_blocks(dir->i_sb, bit_off); dirdata_bh = sb_getblk(sb, blkno); if (!dirdata_bh) { - ret = -EIO; + ret = -ENOMEM; mlog_errno(ret); goto out_commit; } @@ -3159,7 +3159,7 @@ static int ocfs2_do_extend_dir(struct super_block *sb, *new_bh = sb_getblk(sb, p_blkno); if (!*new_bh) { - status = -EIO; + status = -ENOMEM; mlog_errno(status); goto bail; } @@ -3284,7 +3284,7 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb, if (ocfs2_dir_resv_allowed(osb)) data_ac->ac_resv = &OCFS2_I(dir)->ip_la_data_resv; - credits = ocfs2_calc_extend_credits(sb, el, 1); + credits = ocfs2_calc_extend_credits(sb, el); } else { spin_unlock(&OCFS2_I(dir)->ip_lock); credits = OCFS2_SIMPLE_DIR_EXTEND_CREDITS; @@ -3716,7 +3716,7 @@ static int ocfs2_dx_dir_rebalance_credits(struct ocfs2_super *osb, { int credits = ocfs2_clusters_to_blocks(osb->sb, 2); - credits += ocfs2_calc_extend_credits(osb->sb, &dx_root->dr_list, 1); + credits += ocfs2_calc_extend_credits(osb->sb, &dx_root->dr_list); credits += ocfs2_quota_trans_credits(osb->sb); return credits; } diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index cf0f103963b1..af3f7aa73e13 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -1885,8 +1885,10 @@ ok: * up nodes that this node contacted */ while ((nn = find_next_bit (mle->response_map, O2NM_MAX_NODES, nn+1)) < O2NM_MAX_NODES) { - if (nn != dlm->node_num && nn != assert->node_idx) + if (nn != dlm->node_num && nn != assert->node_idx) { master_request = 1; + break; + } } } mle->master = assert->node_idx; @@ -2354,6 +2356,10 @@ static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm, assert_spin_locked(&res->spinlock); + /* delay migration when the lockres is in MIGRATING state */ + if (res->state & DLM_LOCK_RES_MIGRATING) + return 0; + if (res->owner != dlm->node_num) return 0; diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 0b5adca1b178..7035af09cc03 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -1886,6 +1886,13 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm, if (ml->type == LKM_NLMODE) goto skip_lvb; + /* + * If the lock is in the blocked list it can't have a valid lvb, + * so skip it + */ + if (ml->list == DLM_BLOCKED_LIST) + goto skip_lvb; + if (!dlm_lvb_is_empty(mres->lvb)) { if (lksb->flags & DLM_LKSB_PUT_LVB) { /* other node was trying to update diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index d71903c6068b..6fff128cad16 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -580,7 +580,7 @@ static int __ocfs2_extend_allocation(struct inode *inode, u32 logical_start, int did_quota = 0; /* - * This function only exists for file systems which don't + * Unwritten extent only exists for file systems which * support holes. */ BUG_ON(mark_unwritten && !ocfs2_sparse_alloc(osb)); @@ -603,8 +603,7 @@ restart_all: goto leave; } - credits = ocfs2_calc_extend_credits(osb->sb, &fe->id2.i_list, - clusters_to_add); + credits = ocfs2_calc_extend_credits(osb->sb, &fe->id2.i_list); handle = ocfs2_start_trans(osb, credits); if (IS_ERR(handle)) { status = PTR_ERR(handle); diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h index 0b479bab3671..9ff4e8cf9d97 100644 --- a/fs/ocfs2/journal.h +++ b/fs/ocfs2/journal.h @@ -524,8 +524,7 @@ static inline int ocfs2_calc_dxi_expand_credits(struct super_block *sb) * the result may be wrong. */ static inline int ocfs2_calc_extend_credits(struct super_block *sb, - struct ocfs2_extent_list *root_el, - u32 bits_wanted) + struct ocfs2_extent_list *root_el) { int bitmap_blocks, sysfile_bitmap_blocks, extent_blocks; diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 3d3f3c83065c..631a98213474 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -201,8 +201,7 @@ static int ocfs2_lock_allocators_move_extents(struct inode *inode, } } - *credits += ocfs2_calc_extend_credits(osb->sb, et->et_root_el, - clusters_to_move + 2); + *credits += ocfs2_calc_extend_credits(osb->sb, et->et_root_el); mlog(0, "reserve metadata_blocks: %d, data_clusters: %u, credits: %d\n", extra_blocks, clusters_to_move, *credits); @@ -1067,8 +1066,10 @@ int ocfs2_ioctl_move_extents(struct file *filp, void __user *argp) if (status) return status; - if ((!S_ISREG(inode->i_mode)) || !(filp->f_mode & FMODE_WRITE)) + if ((!S_ISREG(inode->i_mode)) || !(filp->f_mode & FMODE_WRITE)) { + status = -EPERM; goto out_drop; + } if (inode->i_flags & (S_IMMUTABLE|S_APPEND)) { status = -EPERM; @@ -1090,8 +1091,10 @@ int ocfs2_ioctl_move_extents(struct file *filp, void __user *argp) goto out_free; } - if (range.me_start > i_size_read(inode)) + if (range.me_start > i_size_read(inode)) { + status = -EINVAL; goto out_free; + } if (range.me_start + range.me_len > i_size_read(inode)) range.me_len = i_size_read(inode) - range.me_start; diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index be3f8676a438..4f791f6d27d0 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -489,7 +489,7 @@ static int __ocfs2_mknod_locked(struct inode *dir, *new_fe_bh = sb_getblk(osb->sb, fe_blkno); if (!*new_fe_bh) { - status = -EIO; + status = -ENOMEM; mlog_errno(status); goto leave; } diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index bf4dfc14bb2c..55767e1ba724 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -612,6 +612,11 @@ static int ocfs2_create_refcount_tree(struct inode *inode, } new_bh = sb_getblk(inode->i_sb, first_blkno); + if (!new_bh) { + ret = -ENOMEM; + mlog_errno(ret); + goto out_commit; + } ocfs2_set_new_buffer_uptodate(&new_tree->rf_ci, new_bh); ret = ocfs2_journal_access_rb(handle, &new_tree->rf_ci, new_bh, @@ -1310,7 +1315,7 @@ static int ocfs2_expand_inline_ref_root(handle_t *handle, new_bh = sb_getblk(sb, blkno); if (new_bh == NULL) { - ret = -EIO; + ret = -ENOMEM; mlog_errno(ret); goto out; } @@ -1561,7 +1566,7 @@ static int ocfs2_new_leaf_refcount_block(handle_t *handle, new_bh = sb_getblk(sb, blkno); if (new_bh == NULL) { - ret = -EIO; + ret = -ENOMEM; mlog_errno(ret); goto out; } @@ -2502,8 +2507,7 @@ static int ocfs2_calc_refcount_meta_credits(struct super_block *sb, ocfs2_init_refcount_extent_tree(&et, ci, ref_root_bh); *meta_add += ocfs2_extend_meta_needed(et.et_root_el); *credits += ocfs2_calc_extend_credits(sb, - et.et_root_el, - ref_blocks); + et.et_root_el); } else { *credits += OCFS2_EXPAND_REFCOUNT_TREE_CREDITS; *meta_add += 1; @@ -2874,8 +2878,7 @@ static int ocfs2_lock_refcount_allocators(struct super_block *sb, meta_add = ocfs2_extend_meta_needed(et->et_root_el); - *credits += ocfs2_calc_extend_credits(sb, et->et_root_el, - num_clusters + 2); + *credits += ocfs2_calc_extend_credits(sb, et->et_root_el); ret = ocfs2_calc_refcount_meta_credits(sb, ref_ci, ref_root_bh, p_cluster, num_clusters, @@ -3031,7 +3034,7 @@ int ocfs2_duplicate_clusters_by_jbd(handle_t *handle, for (i = 0; i < blocks; i++, old_block++, new_block++) { new_bh = sb_getblk(osb->sb, new_block); if (new_bh == NULL) { - ret = -EIO; + ret = -ENOMEM; mlog_errno(ret); break; } @@ -3625,8 +3628,7 @@ int ocfs2_refcounted_xattr_delete_need(struct inode *inode, ocfs2_init_refcount_extent_tree(&et, ref_ci, ref_root_bh); *credits += ocfs2_calc_extend_credits(inode->i_sb, - et.et_root_el, - ref_blocks); + et.et_root_el); } out: diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c index ec55add7604a..822ebc10f281 100644 --- a/fs/ocfs2/resize.c +++ b/fs/ocfs2/resize.c @@ -469,6 +469,7 @@ int ocfs2_group_add(struct inode *inode, struct ocfs2_new_group_input *input) struct ocfs2_chain_list *cl; struct ocfs2_chain_rec *cr; u16 cl_bpc; + u64 bg_ptr; if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) return -EROFS; @@ -513,7 +514,7 @@ int ocfs2_group_add(struct inode *inode, struct ocfs2_new_group_input *input) ret = ocfs2_verify_group_and_input(main_bm_inode, fe, input, group_bh); if (ret) { mlog_errno(ret); - goto out_unlock; + goto out_free_group_bh; } trace_ocfs2_group_add((unsigned long long)input->group, @@ -523,7 +524,7 @@ int ocfs2_group_add(struct inode *inode, struct ocfs2_new_group_input *input) if (IS_ERR(handle)) { mlog_errno(PTR_ERR(handle)); ret = -EINVAL; - goto out_unlock; + goto out_free_group_bh; } cl_bpc = le16_to_cpu(fe->id2.i_chain.cl_bpc); @@ -538,12 +539,14 @@ int ocfs2_group_add(struct inode *inode, struct ocfs2_new_group_input *input) } group = (struct ocfs2_group_desc *)group_bh->b_data; + bg_ptr = le64_to_cpu(group->bg_next_group); group->bg_next_group = cr->c_blkno; ocfs2_journal_dirty(handle, group_bh); ret = ocfs2_journal_access_di(handle, INODE_CACHE(main_bm_inode), main_bm_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret < 0) { + group->bg_next_group = cpu_to_le64(bg_ptr); mlog_errno(ret); goto out_commit; } @@ -574,8 +577,11 @@ int ocfs2_group_add(struct inode *inode, struct ocfs2_new_group_input *input) out_commit: ocfs2_commit_trans(osb, handle); -out_unlock: + +out_free_group_bh: brelse(group_bh); + +out_unlock: brelse(main_bm_bh); ocfs2_inode_unlock(main_bm_inode, 1); diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index 39abf89697ed..cb7ec0b63ddc 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -643,7 +643,7 @@ error: #define FS_OCFS2_NM 1 -static ctl_table ocfs2_nm_table[] = { +static struct ctl_table ocfs2_nm_table[] = { { .procname = "hb_ctl_path", .data = ocfs2_hb_ctl_path, @@ -654,7 +654,7 @@ static ctl_table ocfs2_nm_table[] = { { } }; -static ctl_table ocfs2_mod_table[] = { +static struct ctl_table ocfs2_mod_table[] = { { .procname = "nm", .data = NULL, @@ -665,7 +665,7 @@ static ctl_table ocfs2_mod_table[] = { { } }; -static ctl_table ocfs2_kern_table[] = { +static struct ctl_table ocfs2_kern_table[] = { { .procname = "ocfs2", .data = NULL, @@ -676,7 +676,7 @@ static ctl_table ocfs2_kern_table[] = { { } }; -static ctl_table ocfs2_root_table[] = { +static struct ctl_table ocfs2_root_table[] = { { .procname = "fs", .data = NULL, diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 5397c07ce608..2c91452c4047 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -481,7 +481,7 @@ ocfs2_block_group_alloc_contig(struct ocfs2_super *osb, handle_t *handle, bg_bh = sb_getblk(osb->sb, bg_blkno); if (!bg_bh) { - status = -EIO; + status = -ENOMEM; mlog_errno(status); goto bail; } @@ -661,7 +661,7 @@ ocfs2_block_group_alloc_discontig(handle_t *handle, bg_bh = sb_getblk(osb->sb, bg_blkno); if (!bg_bh) { - status = -EIO; + status = -ENOMEM; mlog_errno(status); goto bail; } diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index d4e81e4a9b04..c41492957aa5 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1848,8 +1848,8 @@ static int ocfs2_get_sector(struct super_block *sb, *bh = sb_getblk(sb, block); if (!*bh) { - mlog_errno(-EIO); - return -EIO; + mlog_errno(-ENOMEM); + return -ENOMEM; } lock_buffer(*bh); if (!buffer_dirty(*bh)) diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 6ce0686eab72..f0a1326d9bba 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -377,7 +377,7 @@ static int ocfs2_init_xattr_bucket(struct ocfs2_xattr_bucket *bucket, bucket->bu_bhs[i] = sb_getblk(bucket->bu_inode->i_sb, xb_blkno + i); if (!bucket->bu_bhs[i]) { - rc = -EIO; + rc = -ENOMEM; mlog_errno(rc); break; } @@ -754,8 +754,7 @@ static int ocfs2_xattr_extend_allocation(struct inode *inode, BUG_ON(why == RESTART_META); credits = ocfs2_calc_extend_credits(inode->i_sb, - &vb->vb_xv->xr_list, - clusters_to_add); + &vb->vb_xv->xr_list); status = ocfs2_extend_trans(handle, credits); if (status < 0) { status = -ENOMEM; @@ -2865,6 +2864,12 @@ static int ocfs2_create_xattr_block(struct inode *inode, } new_bh = sb_getblk(inode->i_sb, first_blkno); + if (!new_bh) { + ret = -ENOMEM; + mlog_errno(ret); + goto end; + } + ocfs2_set_new_buffer_uptodate(INODE_CACHE(inode), new_bh); ret = ocfs2_journal_access_xb(ctxt->handle, INODE_CACHE(inode), @@ -3040,8 +3045,7 @@ static int ocfs2_calc_xattr_set_need(struct inode *inode, if (xi->xi_value_len > OCFS2_XATTR_INLINE_SIZE) { clusters_add += new_clusters; credits += ocfs2_calc_extend_credits(inode->i_sb, - &def_xv.xv.xr_list, - new_clusters); + &def_xv.xv.xr_list); } goto meta_guess; @@ -3106,8 +3110,7 @@ static int ocfs2_calc_xattr_set_need(struct inode *inode, if (!ocfs2_xattr_is_local(xe)) credits += ocfs2_calc_extend_credits( inode->i_sb, - &def_xv.xv.xr_list, - new_clusters); + &def_xv.xv.xr_list); goto out; } } @@ -3132,9 +3135,7 @@ static int ocfs2_calc_xattr_set_need(struct inode *inode, meta_add += ocfs2_extend_meta_needed(&xv->xr_list); clusters_add += new_clusters - old_clusters; credits += ocfs2_calc_extend_credits(inode->i_sb, - &xv->xr_list, - new_clusters - - old_clusters); + &xv->xr_list); if (value_size >= OCFS2_XATTR_ROOT_SIZE) goto out; } @@ -3180,7 +3181,7 @@ meta_guess: &xb->xb_attrs.xb_root.xt_list; meta_add += ocfs2_extend_meta_needed(el); credits += ocfs2_calc_extend_credits(inode->i_sb, - el, 1); + el); } else credits += OCFS2_SUBALLOC_ALLOC + 1; @@ -6216,8 +6217,7 @@ static int ocfs2_value_metas_in_xattr_header(struct super_block *sb, le16_to_cpu(xv->xr_list.l_next_free_rec); *credits += ocfs2_calc_extend_credits(sb, - &def_xv.xv.xr_list, - le32_to_cpu(xv->xr_clusters)); + &def_xv.xv.xr_list); /* * If the value is a tree with depth > 1, We don't go deep @@ -6782,7 +6782,7 @@ static int ocfs2_lock_reflink_xattr_rec_allocators( metas.num_metas += ocfs2_extend_meta_needed(xt_et->et_root_el); *credits += ocfs2_calc_extend_credits(osb->sb, - xt_et->et_root_el, len); + xt_et->et_root_el); if (metas.num_metas) { ret = ocfs2_reserve_new_metadata_blocks(osb, metas.num_metas, diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index 15af6222f8a4..2183fcf41d59 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -31,6 +31,10 @@ config PROC_FS config PROC_KCORE bool "/proc/kcore support" if !ARM depends on PROC_FS && MMU + help + Provides a virtual ELF core file of the live kernel. This can + be read with gdb and other ELF tools. No modifications can be + made using this mechanism. config PROC_VMCORE bool "/proc/vmcore support" diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 8eaa1ba793fc..28955d4b7218 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -285,19 +285,23 @@ static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma) return rv; } -static unsigned long proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr, unsigned long len, unsigned long pgoff, unsigned long flags) +static unsigned long +proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr, + unsigned long len, unsigned long pgoff, + unsigned long flags) { struct proc_dir_entry *pde = PDE(file_inode(file)); unsigned long rv = -EIO; - unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long) = NULL; + unsigned long (*get_area)(struct file *, unsigned long, unsigned long, + unsigned long, unsigned long) = NULL; if (use_pde(pde)) { #ifdef CONFIG_MMU - get_unmapped_area = current->mm->get_unmapped_area; + get_area = current->mm->get_unmapped_area; #endif if (pde->proc_fops->get_unmapped_area) - get_unmapped_area = pde->proc_fops->get_unmapped_area; - if (get_unmapped_area) - rv = get_unmapped_area(file, orig_addr, len, pgoff, flags); + get_area = pde->proc_fops->get_unmapped_area; + if (get_area) + rv = get_area(file, orig_addr, len, pgoff, flags); unuse_pde(pde); } return rv; diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 06ea155e1a59..5ed0e52d6aa0 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -255,8 +255,7 @@ static int kcore_update_ram(void) end_pfn = 0; for_each_node_state(nid, N_MEMORY) { unsigned long node_end; - node_end = NODE_DATA(nid)->node_start_pfn + - NODE_DATA(nid)->node_spanned_pages; + node_end = node_end_pfn(nid); if (end_pfn < node_end) end_pfn = node_end; } diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 59d85d608898..c805d5b69ba1 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -24,7 +24,6 @@ static int meminfo_proc_show(struct seq_file *m, void *v) { struct sysinfo i; unsigned long committed; - unsigned long allowed; struct vmalloc_info vmi; long cached; unsigned long pages[NR_LRU_LISTS]; @@ -37,8 +36,6 @@ static int meminfo_proc_show(struct seq_file *m, void *v) si_meminfo(&i); si_swapinfo(&i); committed = percpu_counter_read_positive(&vm_committed_as); - allowed = ((totalram_pages - hugetlb_total_pages()) - * sysctl_overcommit_ratio / 100) + total_swap_pages; cached = global_page_state(NR_FILE_PAGES) - total_swapcache_pages() - i.bufferram; @@ -147,7 +144,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) K(global_page_state(NR_UNSTABLE_NFS)), K(global_page_state(NR_BOUNCE)), K(global_page_state(NR_WRITEBACK_TEMP)), - K(allowed), + K(vm_commit_limit()), K(committed), (unsigned long)VMALLOC_TOTAL >> 10, vmi.used >> 10, diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 390bdab01c3c..abbe825d20ff 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -561,6 +561,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) [ilog2(VM_NONLINEAR)] = "nl", [ilog2(VM_ARCH_1)] = "ar", [ilog2(VM_DONTDUMP)] = "dd", +#ifdef CONFIG_MEM_SOFT_DIRTY + [ilog2(VM_SOFTDIRTY)] = "sd", +#endif [ilog2(VM_MIXEDMAP)] = "mm", [ilog2(VM_HUGEPAGE)] = "hg", [ilog2(VM_NOHUGEPAGE)] = "nh", @@ -1387,8 +1390,8 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) struct mm_struct *mm = vma->vm_mm; struct mm_walk walk = {}; struct mempolicy *pol; - int n; - char buffer[50]; + char buffer[64]; + int nid; if (!mm) return 0; @@ -1404,10 +1407,8 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) walk.mm = mm; pol = get_vma_policy(task, vma, vma->vm_start); - n = mpol_to_str(buffer, sizeof(buffer), pol); + mpol_to_str(buffer, sizeof(buffer), pol); mpol_cond_put(pol); - if (n < 0) - return n; seq_printf(m, "%08lx %s", vma->vm_start, buffer); @@ -1460,9 +1461,9 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) if (md->writeback) seq_printf(m, " writeback=%lu", md->writeback); - for_each_node_state(n, N_MEMORY) - if (md->node[n]) - seq_printf(m, " N%d=%lu", n, md->node[n]); + for_each_node_state(nid, N_MEMORY) + if (md->node[nid]) + seq_printf(m, " N%d=%lu", nid, md->node[nid]); out: seq_putc(m, '\n'); diff --git a/fs/sync.c b/fs/sync.c index 6c0ca3b75758..f15537452231 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -27,10 +27,11 @@ * wait == 1 case since in that case write_inode() functions do * sync_dirty_buffer() and thus effectively write one block at a time. */ -static int __sync_filesystem(struct super_block *sb, int wait) +static int __sync_filesystem(struct super_block *sb, int wait, + unsigned long start) { if (wait) - sync_inodes_sb(sb); + sync_inodes_sb(sb, start); else writeback_inodes_sb(sb, WB_REASON_SYNC); @@ -47,6 +48,7 @@ static int __sync_filesystem(struct super_block *sb, int wait) int sync_filesystem(struct super_block *sb) { int ret; + unsigned long start = jiffies; /* * We need to be protected against the filesystem going from @@ -60,17 +62,17 @@ int sync_filesystem(struct super_block *sb) if (sb->s_flags & MS_RDONLY) return 0; - ret = __sync_filesystem(sb, 0); + ret = __sync_filesystem(sb, 0, start); if (ret < 0) return ret; - return __sync_filesystem(sb, 1); + return __sync_filesystem(sb, 1, start); } EXPORT_SYMBOL_GPL(sync_filesystem); static void sync_inodes_one_sb(struct super_block *sb, void *arg) { if (!(sb->s_flags & MS_RDONLY)) - sync_inodes_sb(sb); + sync_inodes_sb(sb, *((unsigned long *)arg)); } static void sync_fs_one_sb(struct super_block *sb, void *arg) @@ -102,9 +104,10 @@ static void fdatawait_one_bdev(struct block_device *bdev, void *arg) SYSCALL_DEFINE0(sync) { int nowait = 0, wait = 1; + unsigned long start = jiffies; wakeup_flusher_threads(0, WB_REASON_SYNC); - iterate_supers(sync_inodes_one_sb, NULL); + iterate_supers(sync_inodes_one_sb, &start); iterate_supers(sync_fs_one_sb, &nowait); iterate_supers(sync_fs_one_sb, &wait); iterate_bdevs(fdatawrite_one_bdev, NULL); diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 15188cc99449..8968f5036fa1 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -918,7 +918,7 @@ xfs_flush_inodes( struct super_block *sb = mp->m_super; if (down_read_trylock(&sb->s_umount)) { - sync_inodes_sb(sb); + sync_inodes_sb(sb, jiffies); up_read(&sb->s_umount); } } |