diff options
Diffstat (limited to 'fs')
34 files changed, 506 insertions, 214 deletions
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 51db118..a2fceba 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -507,7 +507,7 @@ out: #define INTERPRETER_ELF 2 #ifndef STACK_RND_MASK -#define STACK_RND_MASK 0x7ff /* with 4K pages 8MB of VA */ +#define STACK_RND_MASK (0x7ff >> (PAGE_SHIFT - 12)) /* 8MB of VA */ #endif static unsigned long randomize_stack_top(unsigned long stack_top) diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h index e894545..4d8948e 100644 --- a/fs/cifs/cifspdu.h +++ b/fs/cifs/cifspdu.h @@ -220,7 +220,7 @@ */ #define CIFS_NO_HANDLE 0xFFFF -#define NO_CHANGE_64 0xFFFFFFFFFFFFFFFFULL +#define NO_CHANGE_64 cpu_to_le64(0xFFFFFFFFFFFFFFFFULL) #define NO_CHANGE_32 0xFFFFFFFFUL /* IPC$ in ASCII */ diff --git a/fs/compat.c b/fs/compat.c index 0ec70e3..040a8be 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -48,6 +48,7 @@ #include <linux/highmem.h> #include <linux/poll.h> #include <linux/mm.h> +#include <linux/eventpoll.h> #include <net/sock.h> /* siocdevprivate_ioctl */ @@ -2235,3 +2236,102 @@ long asmlinkage compat_sys_nfsservctl(int cmd, void *notused, void *notused2) return sys_ni_syscall(); } #endif + +#ifdef CONFIG_EPOLL + +#ifdef CONFIG_HAS_COMPAT_EPOLL_EVENT +asmlinkage long compat_sys_epoll_ctl(int epfd, int op, int fd, + struct compat_epoll_event __user *event) +{ + long err = 0; + struct compat_epoll_event user; + struct epoll_event __user *kernel = NULL; + + if (event) { + if (copy_from_user(&user, event, sizeof(user))) + return -EFAULT; + kernel = compat_alloc_user_space(sizeof(struct epoll_event)); + err |= __put_user(user.events, &kernel->events); + err |= __put_user(user.data, &kernel->data); + } + + return err ? err : sys_epoll_ctl(epfd, op, fd, kernel); +} + + +asmlinkage long compat_sys_epoll_wait(int epfd, + struct compat_epoll_event __user *events, + int maxevents, int timeout) +{ + long i, ret, err = 0; + struct epoll_event __user *kbuf; + struct epoll_event ev; + + if ((maxevents <= 0) || + (maxevents > (INT_MAX / sizeof(struct epoll_event)))) + return -EINVAL; + kbuf = compat_alloc_user_space(sizeof(struct epoll_event) * maxevents); + ret = sys_epoll_wait(epfd, kbuf, maxevents, timeout); + for (i = 0; i < ret; i++) { + err |= __get_user(ev.events, &kbuf[i].events); + err |= __get_user(ev.data, &kbuf[i].data); + err |= __put_user(ev.events, &events->events); + err |= __put_user_unaligned(ev.data, &events->data); + events++; + } + + return err ? -EFAULT: ret; +} +#endif /* CONFIG_HAS_COMPAT_EPOLL_EVENT */ + +#ifdef TIF_RESTORE_SIGMASK +asmlinkage long compat_sys_epoll_pwait(int epfd, + struct compat_epoll_event __user *events, + int maxevents, int timeout, + const compat_sigset_t __user *sigmask, + compat_size_t sigsetsize) +{ + long err; + compat_sigset_t csigmask; + sigset_t ksigmask, sigsaved; + + /* + * If the caller wants a certain signal mask to be set during the wait, + * we apply it here. + */ + if (sigmask) { + if (sigsetsize != sizeof(compat_sigset_t)) + return -EINVAL; + if (copy_from_user(&csigmask, sigmask, sizeof(csigmask))) + return -EFAULT; + sigset_from_compat(&ksigmask, &csigmask); + sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP)); + sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); + } + +#ifdef CONFIG_HAS_COMPAT_EPOLL_EVENT + err = compat_sys_epoll_wait(epfd, events, maxevents, timeout); +#else + err = sys_epoll_wait(epfd, events, maxevents, timeout); +#endif + + /* + * If we changed the signal mask, we need to restore the original one. + * In case we've got a signal while waiting, we do not restore the + * signal mask yet, and we allow do_signal() to deliver the signal on + * the way back to userspace, before the signal mask is restored. + */ + if (sigmask) { + if (err == -EINTR) { + memcpy(¤t->saved_sigmask, &sigsaved, + sizeof(sigsaved)); + set_thread_flag(TIF_RESTORE_SIGMASK); + } else + sigprocmask(SIG_SETMASK, &sigsaved, NULL); + } + + return err; +} +#endif /* TIF_RESTORE_SIGMASK */ + +#endif /* CONFIG_EPOLL */ diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index 34750d5..5e6e37e 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -1141,25 +1141,22 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys) err = -ENOMEM; dentry = d_alloc(configfs_sb->s_root, &name); - if (!dentry) - goto out_release; - - d_add(dentry, NULL); + if (dentry) { + d_add(dentry, NULL); - err = configfs_attach_group(sd->s_element, &group->cg_item, - dentry); - if (!err) - dentry = NULL; - else - d_delete(dentry); + err = configfs_attach_group(sd->s_element, &group->cg_item, + dentry); + if (err) { + d_delete(dentry); + dput(dentry); + } + } mutex_unlock(&configfs_sb->s_root->d_inode->i_mutex); - if (dentry) { - dput(dentry); -out_release: - unlink_group(group); - configfs_release_fs(); + if (err) { + unlink_group(group); + configfs_release_fs(); } return err; diff --git a/fs/ecryptfs/dentry.c b/fs/ecryptfs/dentry.c index 329efcd..cb20b96 100644 --- a/fs/ecryptfs/dentry.c +++ b/fs/ecryptfs/dentry.c @@ -78,18 +78,13 @@ struct kmem_cache *ecryptfs_dentry_info_cache; */ static void ecryptfs_d_release(struct dentry *dentry) { - struct dentry *lower_dentry; - - lower_dentry = ecryptfs_dentry_to_lower(dentry); - if (ecryptfs_dentry_to_private(dentry)) + if (ecryptfs_dentry_to_private(dentry)) { + if (ecryptfs_dentry_to_lower(dentry)) { + mntput(ecryptfs_dentry_to_lower_mnt(dentry)); + dput(ecryptfs_dentry_to_lower(dentry)); + } kmem_cache_free(ecryptfs_dentry_info_cache, ecryptfs_dentry_to_private(dentry)); - if (lower_dentry) { - struct vfsmount *lower_mnt = - ecryptfs_dentry_to_lower_mnt(dentry); - - mntput(lower_mnt); - dput(lower_dentry); } return; } diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index e62f3fc..1548be2 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -38,7 +38,7 @@ static struct dentry *lock_parent(struct dentry *dentry) struct dentry *dir; dir = dget(dentry->d_parent); - mutex_lock(&(dir->d_inode->i_mutex)); + mutex_lock_nested(&(dir->d_inode->i_mutex), I_MUTEX_PARENT); return dir; } diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index e965eb1..9baf697 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -47,7 +47,7 @@ struct dentry_operations hostfs_dentry_ops = { }; /* Changed in hostfs_args before the kernel starts running */ -static char *root_ino = "/"; +static char *root_ino = ""; static int append = 0; #define HOSTFS_SUPER_MAGIC 0x00c0ffee @@ -947,15 +947,17 @@ static int hostfs_fill_sb_common(struct super_block *sb, void *d, int silent) sb->s_magic = HOSTFS_SUPER_MAGIC; sb->s_op = &hostfs_sbops; - if((data == NULL) || (*data == '\0')) - data = root_ino; + /* NULL is printed as <NULL> by sprintf: avoid that. */ + if (data == NULL) + data = ""; err = -ENOMEM; - name = kmalloc(strlen(data) + 1, GFP_KERNEL); + name = kmalloc(strlen(root_ino) + 1 + + strlen(data) + 1, GFP_KERNEL); if(name == NULL) goto out; - strcpy(name, data); + sprintf(name, "%s/%s", root_ino, data); root_inode = iget(sb, 0); if(root_inode == NULL) @@ -966,6 +968,9 @@ static int hostfs_fill_sb_common(struct super_block *sb, void *d, int silent) goto out_put; HOSTFS_I(root_inode)->host_filename = name; + /* Avoid that in the error path, iput(root_inode) frees again name through + * hostfs_destroy_inode! */ + name = NULL; err = -ENOMEM; sb->s_root = d_alloc_root(root_inode); @@ -977,7 +982,7 @@ static int hostfs_fill_sb_common(struct super_block *sb, void *d, int silent) /* No iput in this case because the dput does that for us */ dput(sb->s_root); sb->s_root = NULL; - goto out_free; + goto out; } return(0); diff --git a/fs/jffs2/background.c b/fs/jffs2/background.c index 6eb3dae..888f236 100644 --- a/fs/jffs2/background.c +++ b/fs/jffs2/background.c @@ -99,7 +99,13 @@ static int jffs2_garbage_collect_thread(void *_c) if (try_to_freeze()) continue; - cond_resched(); + /* This thread is purely an optimisation. But if it runs when + other things could be running, it actually makes things a + lot worse. Use yield() and put it at the back of the runqueue + every time. Especially during boot, pulling an inode in + with read_inode() is much preferable to having the GC thread + get there first. */ + yield(); /* Put_super will send a SIGKILL and then wait on the sem. */ diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c index 58a0b912..717a48c 100644 --- a/fs/jffs2/readinode.c +++ b/fs/jffs2/readinode.c @@ -373,7 +373,14 @@ free_out: static inline int read_unknown(struct jffs2_sb_info *c, struct jffs2_raw_node_ref *ref, struct jffs2_unknown_node *un) { /* We don't mark unknown nodes as REF_UNCHECKED */ - BUG_ON(ref_flags(ref) == REF_UNCHECKED); + if (ref_flags(ref) == REF_UNCHECKED) { + JFFS2_ERROR("REF_UNCHECKED but unknown node at %#08x\n", + ref_offset(ref)); + JFFS2_ERROR("Node is {%04x,%04x,%08x,%08x}. Please report this error.\n", + je16_to_cpu(un->magic), je16_to_cpu(un->nodetype), + je32_to_cpu(un->totlen), je32_to_cpu(un->hdr_crc)); + return 1; + } un->nodetype = cpu_to_je16(JFFS2_NODE_ACCURATE | je16_to_cpu(un->nodetype)); @@ -576,6 +583,13 @@ static int jffs2_get_inode_nodes(struct jffs2_sb_info *c, struct jffs2_inode_inf jffs2_mark_node_obsolete(c, ref); goto cont; } + /* Due to poor choice of crc32 seed, an all-zero node will have a correct CRC */ + if (!je32_to_cpu(node->u.hdr_crc) && !je16_to_cpu(node->u.nodetype) && + !je16_to_cpu(node->u.magic) && !je32_to_cpu(node->u.totlen)) { + JFFS2_NOTICE("All zero node header at %#08x.\n", ref_offset(ref)); + jffs2_mark_node_obsolete(c, ref); + goto cont; + } switch (je16_to_cpu(node->u.nodetype)) { diff --git a/fs/jffs2/scan.c b/fs/jffs2/scan.c index 31c1475..7fb45bd4 100644 --- a/fs/jffs2/scan.c +++ b/fs/jffs2/scan.c @@ -734,6 +734,15 @@ scan_more: ofs += 4; continue; } + /* Due to poor choice of crc32 seed, an all-zero node will have a correct CRC */ + if (!je32_to_cpu(node->hdr_crc) && !je16_to_cpu(node->nodetype) && + !je16_to_cpu(node->magic) && !je32_to_cpu(node->totlen)) { + noisy_printk(&noise, "jffs2_scan_eraseblock(): All zero node header at 0x%08x.\n", ofs); + if ((err = jffs2_scan_dirty_space(c, jeb, 4))) + return err; + ofs += 4; + continue; + } if (ofs + je32_to_cpu(node->totlen) > jeb->offset + c->sector_size) { diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c index de718e3..4fac6dd 100644 --- a/fs/jffs2/wbuf.c +++ b/fs/jffs2/wbuf.c @@ -238,7 +238,10 @@ static void jffs2_wbuf_recover(struct jffs2_sb_info *c) jeb = &c->blocks[c->wbuf_ofs / c->sector_size]; spin_lock(&c->erase_completion_lock); - jffs2_block_refile(c, jeb, REFILE_NOTEMPTY); + if (c->wbuf_ofs % c->mtd->erasesize) + jffs2_block_refile(c, jeb, REFILE_NOTEMPTY); + else + jffs2_block_refile(c, jeb, REFILE_ANYWAY); spin_unlock(&c->erase_completion_lock); BUG_ON(!ref_obsolete(jeb->last_node)); @@ -1087,7 +1090,7 @@ int jffs2_write_nand_badblock(struct jffs2_sb_info *c, struct jffs2_eraseblock * if (!c->mtd->block_markbad) return 1; // What else can we do? - D1(printk(KERN_WARNING "jffs2_write_nand_badblock(): Marking bad block at %08x\n", bad_offset)); + printk(KERN_WARNING "JFFS2: marking eraseblock at %08x\n as bad", bad_offset); ret = c->mtd->block_markbad(c->mtd, bad_offset); if (ret) { diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index af53c02..93d046c 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -429,7 +429,8 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) int err; /* Flush out writes to the server in order to update c/mtime */ - nfs_sync_mapping_range(inode->i_mapping, 0, 0, FLUSH_NOCOMMIT); + if (S_ISREG(inode->i_mode)) + nfs_sync_mapping_range(inode->i_mapping, 0, 0, FLUSH_NOCOMMIT); /* * We may force a getattr if the user cares about atime. diff --git a/fs/nfs/super.c b/fs/nfs/super.c index bb516a2..f1eae44 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -151,10 +151,10 @@ int __init register_nfs_fs(void) if (ret < 0) goto error_0; -#ifdef CONFIG_NFS_V4 ret = nfs_register_sysctl(); if (ret < 0) goto error_1; +#ifdef CONFIG_NFS_V4 ret = register_filesystem(&nfs4_fs_type); if (ret < 0) goto error_2; @@ -165,9 +165,9 @@ int __init register_nfs_fs(void) #ifdef CONFIG_NFS_V4 error_2: nfs_unregister_sysctl(); +#endif error_1: unregister_filesystem(&nfs_fs_type); -#endif error_0: return ret; } diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c index fcdcafb..b62481da 100644 --- a/fs/nfs/sysctl.c +++ b/fs/nfs/sysctl.c @@ -50,6 +50,14 @@ static ctl_table nfs_cb_sysctls[] = { .proc_handler = &proc_dointvec_jiffies, .strategy = &sysctl_jiffies, }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "nfs_congestion_kb", + .data = &nfs_congestion_kb, + .maxlen = sizeof(nfs_congestion_kb), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, { .ctl_name = 0 } }; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index febdade..2867e6b 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -12,6 +12,7 @@ #include <linux/pagemap.h> #include <linux/file.h> #include <linux/writeback.h> +#include <linux/swap.h> #include <linux/sunrpc/clnt.h> #include <linux/nfs_fs.h> @@ -38,7 +39,6 @@ static struct nfs_page * nfs_update_request(struct nfs_open_context*, struct page *, unsigned int, unsigned int); static void nfs_mark_request_dirty(struct nfs_page *req); -static int nfs_wait_on_write_congestion(struct address_space *, int); static long nfs_flush_mapping(struct address_space *mapping, struct writeback_control *wbc, int how); static const struct rpc_call_ops nfs_write_partial_ops; static const struct rpc_call_ops nfs_write_full_ops; @@ -48,8 +48,6 @@ static struct kmem_cache *nfs_wdata_cachep; static mempool_t *nfs_wdata_mempool; static mempool_t *nfs_commit_mempool; -static DECLARE_WAIT_QUEUE_HEAD(nfs_write_congestion); - struct nfs_write_data *nfs_commit_alloc(void) { struct nfs_write_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOFS); @@ -211,6 +209,40 @@ static int wb_priority(struct writeback_control *wbc) } /* + * NFS congestion control + */ + +int nfs_congestion_kb; + +#define NFS_CONGESTION_ON_THRESH (nfs_congestion_kb >> (PAGE_SHIFT-10)) +#define NFS_CONGESTION_OFF_THRESH \ + (NFS_CONGESTION_ON_THRESH - (NFS_CONGESTION_ON_THRESH >> 2)) + +static void nfs_set_page_writeback(struct page *page) +{ + if (!test_set_page_writeback(page)) { + struct inode *inode = page->mapping->host; + struct nfs_server *nfss = NFS_SERVER(inode); + + if (atomic_inc_return(&nfss->writeback) > + NFS_CONGESTION_ON_THRESH) + set_bdi_congested(&nfss->backing_dev_info, WRITE); + } +} + +static void nfs_end_page_writeback(struct page *page) +{ + struct inode *inode = page->mapping->host; + struct nfs_server *nfss = NFS_SERVER(inode); + + end_page_writeback(page); + if (atomic_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH) { + clear_bdi_congested(&nfss->backing_dev_info, WRITE); + congestion_end(WRITE); + } +} + +/* * Find an associated nfs write request, and prepare to flush it out * Returns 1 if there was no write request, or if the request was * already tagged by nfs_set_page_dirty.Returns 0 if the request @@ -247,7 +279,7 @@ static int nfs_page_mark_flush(struct page *page) spin_unlock(req_lock); if (test_and_set_bit(PG_FLUSHING, &req->wb_flags) == 0) { nfs_mark_request_dirty(req); - set_page_writeback(page); + nfs_set_page_writeback(page); } ret = test_bit(PG_NEED_FLUSH, &req->wb_flags); nfs_unlock_request(req); @@ -302,13 +334,8 @@ int nfs_writepage(struct page *page, struct writeback_control *wbc) return err; } -/* - * Note: causes nfs_update_request() to block on the assumption - * that the writeback is generated due to memory pressure. - */ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc) { - struct backing_dev_info *bdi = mapping->backing_dev_info; struct inode *inode = mapping->host; int err; @@ -317,20 +344,12 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc) err = generic_writepages(mapping, wbc); if (err) return err; - while (test_and_set_bit(BDI_write_congested, &bdi->state) != 0) { - if (wbc->nonblocking) - return 0; - nfs_wait_on_write_congestion(mapping, 0); - } err = nfs_flush_mapping(mapping, wbc, wb_priority(wbc)); if (err < 0) goto out; nfs_add_stats(inode, NFSIOS_WRITEPAGES, err); err = 0; out: - clear_bit(BDI_write_congested, &bdi->state); - wake_up_all(&nfs_write_congestion); - congestion_end(WRITE); return err; } @@ -360,7 +379,7 @@ static int nfs_inode_add_request(struct inode *inode, struct nfs_page *req) } /* - * Insert a write request into an inode + * Remove a write request from an inode */ static void nfs_inode_remove_request(struct nfs_page *req) { @@ -531,10 +550,10 @@ static inline int nfs_scan_commit(struct inode *inode, struct list_head *dst, un } #endif -static int nfs_wait_on_write_congestion(struct address_space *mapping, int intr) +static int nfs_wait_on_write_congestion(struct address_space *mapping) { + struct inode *inode = mapping->host; struct backing_dev_info *bdi = mapping->backing_dev_info; - DEFINE_WAIT(wait); int ret = 0; might_sleep(); @@ -542,31 +561,23 @@ static int nfs_wait_on_write_congestion(struct address_space *mapping, int intr) if (!bdi_write_congested(bdi)) return 0; - nfs_inc_stats(mapping->host, NFSIOS_CONGESTIONWAIT); + nfs_inc_stats(inode, NFSIOS_CONGESTIONWAIT); - if (intr) { - struct rpc_clnt *clnt = NFS_CLIENT(mapping->host); + do { + struct rpc_clnt *clnt = NFS_CLIENT(inode); sigset_t oldset; rpc_clnt_sigmask(clnt, &oldset); - prepare_to_wait(&nfs_write_congestion, &wait, TASK_INTERRUPTIBLE); - if (bdi_write_congested(bdi)) { - if (signalled()) - ret = -ERESTARTSYS; - else - schedule(); - } + ret = congestion_wait_interruptible(WRITE, HZ/10); rpc_clnt_sigunmask(clnt, &oldset); - } else { - prepare_to_wait(&nfs_write_congestion, &wait, TASK_UNINTERRUPTIBLE); - if (bdi_write_congested(bdi)) - schedule(); - } - finish_wait(&nfs_write_congestion, &wait); + if (ret == -ERESTARTSYS) + break; + ret = 0; + } while (bdi_write_congested(bdi)); + return ret; } - /* * Try to update any existing write request, or create one if there is none. * In order to match, the request's credentials must match those of @@ -577,14 +588,15 @@ static int nfs_wait_on_write_congestion(struct address_space *mapping, int intr) static struct nfs_page * nfs_update_request(struct nfs_open_context* ctx, struct page *page, unsigned int offset, unsigned int bytes) { - struct inode *inode = page->mapping->host; + struct address_space *mapping = page->mapping; + struct inode *inode = mapping->host; struct nfs_inode *nfsi = NFS_I(inode); struct nfs_page *req, *new = NULL; unsigned long rqend, end; end = offset + bytes; - if (nfs_wait_on_write_congestion(page->mapping, NFS_SERVER(inode)->flags & NFS_MOUNT_INTR)) + if (nfs_wait_on_write_congestion(mapping)) return ERR_PTR(-ERESTARTSYS); for (;;) { /* Loop over all inode entries and see if we find @@ -727,7 +739,7 @@ int nfs_updatepage(struct file *file, struct page *page, static void nfs_writepage_release(struct nfs_page *req) { - end_page_writeback(req->wb_page); + nfs_end_page_writeback(req->wb_page); #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) if (!PageError(req->wb_page)) { @@ -1042,12 +1054,12 @@ static void nfs_writeback_done_full(struct rpc_task *task, void *calldata) if (task->tk_status < 0) { nfs_set_pageerror(page); req->wb_context->error = task->tk_status; - end_page_writeback(page); + nfs_end_page_writeback(page); nfs_inode_remove_request(req); dprintk(", error = %d\n", task->tk_status); goto next; } - end_page_writeback(page); + nfs_end_page_writeback(page); #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) if (data->args.stable != NFS_UNSTABLE || data->verf.committed == NFS_FILE_SYNC) { @@ -1514,6 +1526,26 @@ int __init nfs_init_writepagecache(void) if (nfs_commit_mempool == NULL) return -ENOMEM; + /* + * NFS congestion size, scale with available memory. + * + * 64MB: 8192k + * 128MB: 11585k + * 256MB: 16384k + * 512MB: 23170k + * 1GB: 32768k + * 2GB: 46340k + * 4GB: 65536k + * 8GB: 92681k + * 16GB: 131072k + * + * This allows larger machines to have larger/more transfers. + * Limit the default to 256M + */ + nfs_congestion_kb = (16*int_sqrt(totalram_pages)) << (PAGE_SHIFT-10); + if (nfs_congestion_kb > 256*1024) + nfs_congestion_kb = 256*1024; + return 0; } diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index c2660cb..8d995bc 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -17,7 +17,6 @@ #include <linux/stat.h> #include <linux/dcache.h> #include <linux/mount.h> -#include <asm/pgtable.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/svc.h> diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 93628b0..875c114 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -614,6 +614,27 @@ static void ocfs2_dio_end_io(struct kiocb *iocb, ocfs2_rw_unlock(inode, 0); } +/* + * 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 long offset) +{ + journal_t *journal = OCFS2_SB(page->mapping->host->i_sb)->journal->j_journal; + + journal_invalidatepage(journal, page, offset); +} + +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 journal_try_to_free_buffers(journal, page, wait); +} + static ssize_t ocfs2_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, @@ -661,5 +682,8 @@ const struct address_space_operations ocfs2_aops = { .commit_write = ocfs2_commit_write, .bmap = ocfs2_bmap, .sync_page = block_sync_page, - .direct_IO = ocfs2_direct_IO + .direct_IO = ocfs2_direct_IO, + .invalidatepage = ocfs2_invalidatepage, + .releasepage = ocfs2_releasepage, + .migratepage = buffer_migrate_page, }; diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 5a9779b..eba282d 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -1234,6 +1234,7 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg, const char *page, size_t count) { + struct task_struct *hb_task; long fd; int sectsize; char *p = (char *)page; @@ -1319,20 +1320,28 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg, */ atomic_set(®->hr_steady_iterations, O2HB_LIVE_THRESHOLD + 1); - reg->hr_task = kthread_run(o2hb_thread, reg, "o2hb-%s", - reg->hr_item.ci_name); - if (IS_ERR(reg->hr_task)) { - ret = PTR_ERR(reg->hr_task); + hb_task = kthread_run(o2hb_thread, reg, "o2hb-%s", + reg->hr_item.ci_name); + if (IS_ERR(hb_task)) { + ret = PTR_ERR(hb_task); mlog_errno(ret); - reg->hr_task = NULL; goto out; } + spin_lock(&o2hb_live_lock); + reg->hr_task = hb_task; + spin_unlock(&o2hb_live_lock); + ret = wait_event_interruptible(o2hb_steady_queue, atomic_read(®->hr_steady_iterations) == 0); if (ret) { - kthread_stop(reg->hr_task); + spin_lock(&o2hb_live_lock); + hb_task = reg->hr_task; reg->hr_task = NULL; + spin_unlock(&o2hb_live_lock); + + if (hb_task) + kthread_stop(hb_task); goto out; } @@ -1354,10 +1363,17 @@ out: static ssize_t o2hb_region_pid_read(struct o2hb_region *reg, char *page) { - if (!reg->hr_task) + pid_t pid = 0; + + spin_lock(&o2hb_live_lock); + if (reg->hr_task) + pid = reg->hr_task->pid; + spin_unlock(&o2hb_live_lock); + + if (!pid) return 0; - return sprintf(page, "%u\n", reg->hr_task->pid); + return sprintf(page, "%u\n", pid); } struct o2hb_region_attribute { @@ -1495,13 +1511,17 @@ out: static void o2hb_heartbeat_group_drop_item(struct config_group *group, struct config_item *item) { + struct task_struct *hb_task; struct o2hb_region *reg = to_o2hb_region(item); /* stop the thread when the user removes the region dir */ - if (reg->hr_task) { - kthread_stop(reg->hr_task); - reg->hr_task = NULL; - } + spin_lock(&o2hb_live_lock); + hb_task = reg->hr_task; + reg->hr_task = NULL; + spin_unlock(&o2hb_live_lock); + + if (hb_task) + kthread_stop(hb_task); config_item_put(item); } @@ -1682,7 +1702,7 @@ out: } EXPORT_SYMBOL_GPL(o2hb_register_callback); -int o2hb_unregister_callback(struct o2hb_callback_func *hc) +void o2hb_unregister_callback(struct o2hb_callback_func *hc) { BUG_ON(hc->hc_magic != O2HB_CB_MAGIC); @@ -1690,15 +1710,13 @@ int o2hb_unregister_callback(struct o2hb_callback_func *hc) __builtin_return_address(0), hc); if (list_empty(&hc->hc_item)) - return 0; + return; down_write(&o2hb_callback_sem); list_del_init(&hc->hc_item); up_write(&o2hb_callback_sem); - - return 0; } EXPORT_SYMBOL_GPL(o2hb_unregister_callback); diff --git a/fs/ocfs2/cluster/heartbeat.h b/fs/ocfs2/cluster/heartbeat.h index cac6223..cc6d40b 100644 --- a/fs/ocfs2/cluster/heartbeat.h +++ b/fs/ocfs2/cluster/heartbeat.h @@ -70,7 +70,7 @@ void o2hb_setup_callback(struct o2hb_callback_func *hc, void *data, int priority); int o2hb_register_callback(struct o2hb_callback_func *hc); -int o2hb_unregister_callback(struct o2hb_callback_func *hc); +void o2hb_unregister_callback(struct o2hb_callback_func *hc); void o2hb_fill_node_map(unsigned long *map, unsigned bytes); void o2hb_init(void); diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 1718215..69caf3e 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -1638,17 +1638,8 @@ static void o2net_hb_node_up_cb(struct o2nm_node *node, int node_num, void o2net_unregister_hb_callbacks(void) { - int ret; - - ret = o2hb_unregister_callback(&o2net_hb_up); - if (ret < 0) - mlog(ML_ERROR, "Status return %d unregistering heartbeat up " - "callback!\n", ret); - - ret = o2hb_unregister_callback(&o2net_hb_down); - if (ret < 0) - mlog(ML_ERROR, "Status return %d unregistering heartbeat down " - "callback!\n", ret); + o2hb_unregister_callback(&o2net_hb_up); + o2hb_unregister_callback(&o2net_hb_down); } int o2net_register_hb_callbacks(void) diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 77e4e61..9229e04 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -2730,14 +2730,17 @@ int dlm_empty_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res) int ret; int lock_dropped = 0; + spin_lock(&res->spinlock); if (res->owner != dlm->node_num) { if (!__dlm_lockres_unused(res)) { mlog(ML_ERROR, "%s:%.*s: this node is not master, " "trying to free this but locks remain\n", dlm->name, res->lockname.len, res->lockname.name); } + spin_unlock(&res->spinlock); goto leave; } + spin_unlock(&res->spinlock); /* Wheee! Migrate lockres here! Will sleep so drop spinlock. */ spin_unlock(&dlm->spinlock); diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c index 8ffa091..6421a8f 100644 --- a/fs/ocfs2/dlm/dlmthread.c +++ b/fs/ocfs2/dlm/dlmthread.c @@ -265,8 +265,10 @@ static void dlm_run_purge_list(struct dlm_ctxt *dlm, /* This may drop and reacquire the dlm spinlock if it * has to do migration. */ mlog(0, "calling dlm_purge_lockres!\n"); + dlm_lockres_get(lockres); if (dlm_purge_lockres(dlm, lockres)) BUG(); + dlm_lockres_put(lockres); mlog(0, "DONE calling dlm_purge_lockres!\n"); /* Avoid adding any scheduling latencies */ diff --git a/fs/ocfs2/heartbeat.c b/fs/ocfs2/heartbeat.c index 8fc52d6..b25ef63 100644 --- a/fs/ocfs2/heartbeat.c +++ b/fs/ocfs2/heartbeat.c @@ -164,8 +164,10 @@ int ocfs2_register_hb_callbacks(struct ocfs2_super *osb) } status = o2hb_register_callback(&osb->osb_hb_up); - if (status < 0) + if (status < 0) { mlog_errno(status); + o2hb_unregister_callback(&osb->osb_hb_down); + } bail: return status; @@ -173,18 +175,11 @@ bail: void ocfs2_clear_hb_callbacks(struct ocfs2_super *osb) { - int status; - if (ocfs2_mount_local(osb)) return; - status = o2hb_unregister_callback(&osb->osb_hb_down); - if (status < 0) - mlog_errno(status); - - status = o2hb_unregister_callback(&osb->osb_hb_up); - if (status < 0) - mlog_errno(status); + o2hb_unregister_callback(&osb->osb_hb_down); + o2hb_unregister_callback(&osb->osb_hb_up); } void ocfs2_stop_heartbeat(struct ocfs2_super *osb) diff --git a/fs/partitions/Kconfig b/fs/partitions/Kconfig index 74552c6..6e8bb66 100644 --- a/fs/partitions/Kconfig +++ b/fs/partitions/Kconfig @@ -235,5 +235,4 @@ config EFI_PARTITION select CRC32 help Say Y here if you would like to use hard disks under Linux which - were partitioned using EFI GPT. Presently only useful on the - IA-64 platform. + were partitioned using EFI GPT. diff --git a/fs/partitions/check.c b/fs/partitions/check.c index 22d38ff..8a7d003 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -180,7 +180,7 @@ check_partition(struct gendisk *hd, struct block_device *bdev) } if (res > 0) return state; - if (!err) + if (err) /* The partition is unrecognized. So report I/O errors if there were any */ res = err; if (!res) @@ -541,7 +541,7 @@ int rescan_partitions(struct gendisk *disk, struct block_device *bdev) if (!get_capacity(disk) || !(state = check_partition(disk, bdev))) return 0; if (IS_ERR(state)) /* I/O error reading the partition table */ - return PTR_ERR(state); + return -EIO; for (p = 1; p < state->limit; p++) { sector_t size = state->parts[p].size; sector_t from = state->parts[p].from; diff --git a/fs/proc/base.c b/fs/proc/base.c index 01f7769..989af5e 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1558,29 +1558,20 @@ static ssize_t proc_pid_attr_read(struct file * file, char __user * buf, size_t count, loff_t *ppos) { struct inode * inode = file->f_path.dentry->d_inode; - unsigned long page; + char *p = NULL; ssize_t length; struct task_struct *task = get_proc_task(inode); - length = -ESRCH; if (!task) - goto out_no_task; - - if (count > PAGE_SIZE) - count = PAGE_SIZE; - length = -ENOMEM; - if (!(page = __get_free_page(GFP_KERNEL))) - goto out; + return -ESRCH; length = security_getprocattr(task, (char*)file->f_path.dentry->d_name.name, - (void*)page, count); - if (length >= 0) - length = simple_read_from_buffer(buf, count, ppos, (char *)page, length); - free_page(page); -out: + &p); put_task_struct(task); -out_no_task: + if (length > 0) + length = simple_read_from_buffer(buf, count, ppos, p, length); + kfree(p); return length; } diff --git a/fs/smbfs/request.c b/fs/smbfs/request.c index 42261db..723f7c6 100644 --- a/fs/smbfs/request.c +++ b/fs/smbfs/request.c @@ -181,6 +181,7 @@ static int smb_setup_request(struct smb_request *req) req->rq_errno = 0; req->rq_fragment = 0; kfree(req->rq_trans2buffer); + req->rq_trans2buffer = NULL; return 0; } diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 8d4d839..fc46333 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -168,12 +168,12 @@ sysfs_read_file(struct file *file, char __user *buf, size_t count, loff_t *ppos) ssize_t retval = 0; down(&buffer->sem); - if (buffer->orphaned) { - retval = -ENODEV; - goto out; - } if (buffer->needs_read_fill) { - if ((retval = fill_read_buffer(file->f_path.dentry,buffer))) + if (buffer->orphaned) + retval = -ENODEV; + else + retval = fill_read_buffer(file->f_path.dentry,buffer); + if (retval) goto out; } pr_debug("%s: count = %zd, ppos = %lld, buf = %s\n", @@ -629,6 +629,60 @@ void sysfs_remove_file_from_group(struct kobject *kobj, } EXPORT_SYMBOL_GPL(sysfs_remove_file_from_group); +struct sysfs_schedule_callback_struct { + struct kobject *kobj; + void (*func)(void *); + void *data; + struct work_struct work; +}; + +static void sysfs_schedule_callback_work(struct work_struct *work) +{ + struct sysfs_schedule_callback_struct *ss = container_of(work, + struct sysfs_schedule_callback_struct, work); + + (ss->func)(ss->data); + kobject_put(ss->kobj); + kfree(ss); +} + +/** + * sysfs_schedule_callback - helper to schedule a callback for a kobject + * @kobj: object we're acting for. + * @func: callback function to invoke later. + * @data: argument to pass to @func. + * + * sysfs attribute methods must not unregister themselves or their parent + * kobject (which would amount to the same thing). Attempts to do so will + * deadlock, since unregistration is mutually exclusive with driver + * callbacks. + * + * Instead methods can call this routine, which will attempt to allocate + * and schedule a workqueue request to call back @func with @data as its + * argument in the workqueue's process context. @kobj will be pinned + * until @func returns. + * + * Returns 0 if the request was submitted, -ENOMEM if storage could not + * be allocated. + */ +int sysfs_schedule_callback(struct kobject *kobj, void (*func)(void *), + void *data) +{ + struct sysfs_schedule_callback_struct *ss; + + ss = kmalloc(sizeof(*ss), GFP_KERNEL); + if (!ss) + return -ENOMEM; + kobject_get(kobj); + ss->kobj = kobj; + ss->func = func; + ss->data = data; + INIT_WORK(&ss->work, sysfs_schedule_callback_work); + schedule_work(&ss->work); + return 0; +} +EXPORT_SYMBOL_GPL(sysfs_schedule_callback); + EXPORT_SYMBOL_GPL(sysfs_create_file); EXPORT_SYMBOL_GPL(sysfs_remove_file); diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c index ccb7d72..4de5c6b 100644 --- a/fs/sysfs/inode.c +++ b/fs/sysfs/inode.c @@ -222,13 +222,17 @@ const unsigned char * sysfs_get_name(struct sysfs_dirent *sd) static inline void orphan_all_buffers(struct inode *node) { - struct sysfs_buffer_collection *set = node->i_private; + struct sysfs_buffer_collection *set; struct sysfs_buffer *buf; mutex_lock_nested(&node->i_mutex, I_MUTEX_CHILD); - if (node->i_private) { - list_for_each_entry(buf, &set->associates, associates) + set = node->i_private; + if (set) { + list_for_each_entry(buf, &set->associates, associates) { + down(&buf->sem); buf->orphaned = 1; + up(&buf->sem); + } } mutex_unlock(&node->i_mutex); } diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c index bcc4408..841ac25 100644 --- a/fs/ufs/balloc.c +++ b/fs/ufs/balloc.c @@ -244,62 +244,87 @@ failed: * We can come here from ufs_writepage or ufs_prepare_write, * locked_page is argument of these functions, so we already lock it. */ -static void ufs_change_blocknr(struct inode *inode, unsigned int beg, - unsigned int count, unsigned int oldb, - unsigned int newb, struct page *locked_page) +static void ufs_change_blocknr(struct inode *inode, sector_t beg, + unsigned int count, sector_t oldb, + sector_t newb, struct page *locked_page) { - const unsigned mask = (1 << (PAGE_CACHE_SHIFT - inode->i_blkbits)) - 1; + const unsigned blks_per_page = + 1 << (PAGE_CACHE_SHIFT - inode->i_blkbits); + const unsigned mask = blks_per_page - 1; struct address_space * const mapping = inode->i_mapping; - pgoff_t index, cur_index; - unsigned end, pos, j; + pgoff_t index, cur_index, last_index; + unsigned pos, j, lblock; + sector_t end, i; struct page *page; struct buffer_head *head, *bh; - UFSD("ENTER, ino %lu, count %u, oldb %u, newb %u\n", - inode->i_ino, count, oldb, newb); + UFSD("ENTER, ino %lu, count %u, oldb %llu, newb %llu\n", + inode->i_ino, count, + (unsigned long long)oldb, (unsigned long long)newb); BUG_ON(!locked_page); BUG_ON(!PageLocked(locked_page)); cur_index = locked_page->index; - - for (end = count + beg; beg < end; beg = (beg | mask) + 1) { - index = beg >> (PAGE_CACHE_SHIFT - inode->i_blkbits); + end = count + beg; + last_index = end >> (PAGE_CACHE_SHIFT - inode->i_blkbits); + for (i = beg; i < end; i = (i | mask) + 1) { + index = i >> (PAGE_CACHE_SHIFT - inode->i_blkbits); if (likely(cur_index != index)) { page = ufs_get_locked_page(mapping, index); - if (!page || IS_ERR(page)) /* it was truncated or EIO */ + if (!page)/* it was truncated */ + continue; + if (IS_ERR(page)) {/* or EIO */ + ufs_error(inode->i_sb, __FUNCTION__, + "read of page %llu failed\n", + (unsigned long long)index); continue; + } } else page = locked_page; head = page_buffers(page); bh = head; - pos = beg & mask; + pos = i & mask; for (j = 0; j < pos; ++j) bh = bh->b_this_page; - j = 0; + + + if (unlikely(index == last_index)) + lblock = end & mask; + else + lblock = blks_per_page; + do { - if (buffer_mapped(bh)) { - pos = bh->b_blocknr - oldb; - if (pos < count) { - UFSD(" change from %llu to %llu\n", - (unsigned long long)pos + oldb, - (unsigned long long)pos + newb); - bh->b_blocknr = newb + pos; - unmap_underlying_metadata(bh->b_bdev, - bh->b_blocknr); - mark_buffer_dirty(bh); - ++j; + if (j >= lblock) + break; + pos = (i - beg) + j; + + if (!buffer_mapped(bh)) + map_bh(bh, inode->i_sb, oldb + pos); + if (!buffer_uptodate(bh)) { + ll_rw_block(READ, 1, &bh); + wait_on_buffer(bh); + if (!buffer_uptodate(bh)) { + ufs_error(inode->i_sb, __FUNCTION__, + "read of block failed\n"); + break; } } + UFSD(" change from %llu to %llu, pos %u\n", + (unsigned long long)pos + oldb, + (unsigned long long)pos + newb, pos); + + bh->b_blocknr = newb + pos; + unmap_underlying_metadata(bh->b_bdev, + bh->b_blocknr); + mark_buffer_dirty(bh); + ++j; bh = bh->b_this_page; } while (bh != head); - if (j) - set_page_dirty(page); - if (likely(cur_index != index)) ufs_put_locked_page(page); } @@ -457,8 +482,9 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, if (result) { ufs_clear_frags(inode, result + oldcount, newcount - oldcount, locked_page != NULL); - ufs_change_blocknr(inode, fragment - oldcount, oldcount, tmp, - result, locked_page); + ufs_change_blocknr(inode, fragment - oldcount, oldcount, + uspi->s_sbbase + tmp, + uspi->s_sbbase + result, locked_page); ufs_cpu_to_data_ptr(sb, p, result); *err = 0; UFS_I(inode)->i_lastfrag = max_t(u32, UFS_I(inode)->i_lastfrag, fragment + count); diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c index b868878..c28a8b6 100644 --- a/fs/ufs/ialloc.c +++ b/fs/ufs/ialloc.c @@ -343,9 +343,8 @@ cg_found: lock_buffer(bh); ufs2_inode = (struct ufs2_inode *)bh->b_data; ufs2_inode += ufs_inotofsbo(inode->i_ino); - ufs2_inode->ui_birthtime.tv_sec = - cpu_to_fs32(sb, CURRENT_TIME_SEC.tv_sec); - ufs2_inode->ui_birthtime.tv_usec = 0; + ufs2_inode->ui_birthtime = cpu_to_fs64(sb, CURRENT_TIME.tv_sec); + ufs2_inode->ui_birthnsec = cpu_to_fs32(sb, CURRENT_TIME.tv_nsec); mark_buffer_dirty(bh); unlock_buffer(bh); if (sb->s_flags & MS_SYNCHRONOUS) diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index fb34ad0..013d7af 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -212,7 +212,7 @@ repeat: brelse (result); goto repeat; } else { - *phys = tmp + blockoff; + *phys = uspi->s_sbbase + tmp + blockoff; return NULL; } } @@ -282,9 +282,9 @@ repeat: } if (!phys) { - result = sb_getblk(sb, tmp + blockoff); + result = sb_getblk(sb, uspi->s_sbbase + tmp + blockoff); } else { - *phys = tmp + blockoff; + *phys = uspi->s_sbbase + tmp + blockoff; result = NULL; *err = 0; *new = 1; @@ -368,7 +368,7 @@ repeat: brelse (result); goto repeat; } else { - *phys = tmp + blockoff; + *phys = uspi->s_sbbase + tmp + blockoff; goto out; } } @@ -389,9 +389,9 @@ repeat: if (!phys) { - result = sb_getblk(sb, tmp + blockoff); + result = sb_getblk(sb, uspi->s_sbbase + tmp + blockoff); } else { - *phys = tmp + blockoff; + *phys = uspi->s_sbbase + tmp + blockoff; *new = 1; } @@ -668,12 +668,12 @@ static void ufs2_read_inode(struct inode *inode, struct ufs2_inode *ufs2_inode) inode->i_gid = fs32_to_cpu(sb, ufs2_inode->ui_gid); inode->i_size = fs64_to_cpu(sb, ufs2_inode->ui_size); - inode->i_atime.tv_sec = fs32_to_cpu(sb, ufs2_inode->ui_atime.tv_sec); - inode->i_ctime.tv_sec = fs32_to_cpu(sb, ufs2_inode->ui_ctime.tv_sec); - inode->i_mtime.tv_sec = fs32_to_cpu(sb, ufs2_inode->ui_mtime.tv_sec); - inode->i_mtime.tv_nsec = 0; - inode->i_atime.tv_nsec = 0; - inode->i_ctime.tv_nsec = 0; + inode->i_atime.tv_sec = fs64_to_cpu(sb, ufs2_inode->ui_atime); + inode->i_ctime.tv_sec = fs64_to_cpu(sb, ufs2_inode->ui_ctime); + inode->i_mtime.tv_sec = fs64_to_cpu(sb, ufs2_inode->ui_mtime); + inode->i_atime.tv_nsec = fs32_to_cpu(sb, ufs2_inode->ui_atimensec); + inode->i_ctime.tv_nsec = fs32_to_cpu(sb, ufs2_inode->ui_ctimensec); + inode->i_mtime.tv_nsec = fs32_to_cpu(sb, ufs2_inode->ui_mtimensec); inode->i_blocks = fs64_to_cpu(sb, ufs2_inode->ui_blocks); inode->i_generation = fs32_to_cpu(sb, ufs2_inode->ui_gen); ufsi->i_flags = fs32_to_cpu(sb, ufs2_inode->ui_flags); @@ -803,12 +803,12 @@ static void ufs2_update_inode(struct inode *inode, struct ufs2_inode *ufs_inode) ufs_inode->ui_gid = cpu_to_fs32(sb, inode->i_gid); ufs_inode->ui_size = cpu_to_fs64(sb, inode->i_size); - ufs_inode->ui_atime.tv_sec = cpu_to_fs32(sb, inode->i_atime.tv_sec); - ufs_inode->ui_atime.tv_usec = 0; - ufs_inode->ui_ctime.tv_sec = cpu_to_fs32(sb, inode->i_ctime.tv_sec); - ufs_inode->ui_ctime.tv_usec = 0; - ufs_inode->ui_mtime.tv_sec = cpu_to_fs32(sb, inode->i_mtime.tv_sec); - ufs_inode->ui_mtime.tv_usec = 0; + ufs_inode->ui_atime = cpu_to_fs64(sb, inode->i_atime.tv_sec); + ufs_inode->ui_atimensec = cpu_to_fs32(sb, inode->i_atime.tv_nsec); + ufs_inode->ui_ctime = cpu_to_fs64(sb, inode->i_ctime.tv_sec); + ufs_inode->ui_ctimensec = cpu_to_fs32(sb, inode->i_ctime.tv_nsec); + ufs_inode->ui_mtime = cpu_to_fs64(sb, inode->i_mtime.tv_sec); + ufs_inode->ui_mtimensec = cpu_to_fs32(sb, inode->i_mtime.tv_nsec); ufs_inode->ui_blocks = cpu_to_fs64(sb, inode->i_blocks); ufs_inode->ui_flags = cpu_to_fs32(sb, ufsi->i_flags); diff --git a/fs/ufs/truncate.c b/fs/ufs/truncate.c index 749581f..79c54c85 100644 --- a/fs/ufs/truncate.c +++ b/fs/ufs/truncate.c @@ -74,7 +74,7 @@ static int ufs_trunc_direct(struct inode *inode) unsigned i, tmp; int retry; - UFSD("ENTER\n"); + UFSD("ENTER: ino %lu\n", inode->i_ino); sb = inode->i_sb; uspi = UFS_SB(sb)->s_uspi; @@ -96,8 +96,8 @@ static int ufs_trunc_direct(struct inode *inode) block2 = ufs_fragstoblks (frag3); } - UFSD("frag1 %llu, frag2 %llu, block1 %llu, block2 %llu, frag3 %llu," - " frag4 %llu\n", + UFSD("ino %lu, frag1 %llu, frag2 %llu, block1 %llu, block2 %llu," + " frag3 %llu, frag4 %llu\n", inode->i_ino, (unsigned long long)frag1, (unsigned long long)frag2, (unsigned long long)block1, (unsigned long long)block2, (unsigned long long)frag3, (unsigned long long)frag4); @@ -163,7 +163,7 @@ next1: mark_inode_dirty(inode); next3: - UFSD("EXIT\n"); + UFSD("EXIT: ino %lu\n", inode->i_ino); return retry; } @@ -248,7 +248,7 @@ static int ufs_trunc_indirect(struct inode *inode, u64 offset, void *p) } ubh_brelse (ind_ubh); - UFSD("EXIT\n"); + UFSD("EXIT: ino %lu\n", inode->i_ino); return retry; } @@ -262,7 +262,7 @@ static int ufs_trunc_dindirect(struct inode *inode, u64 offset, void *p) void *dind; int retry = 0; - UFSD("ENTER\n"); + UFSD("ENTER: ino %lu\n", inode->i_ino); sb = inode->i_sb; uspi = UFS_SB(sb)->s_uspi; @@ -312,7 +312,7 @@ static int ufs_trunc_dindirect(struct inode *inode, u64 offset, void *p) } ubh_brelse (dind_bh); - UFSD("EXIT\n"); + UFSD("EXIT: ino %lu\n", inode->i_ino); return retry; } @@ -327,7 +327,7 @@ static int ufs_trunc_tindirect(struct inode *inode) void *tind, *p; int retry; - UFSD("ENTER\n"); + UFSD("ENTER: ino %lu\n", inode->i_ino); retry = 0; @@ -348,7 +348,7 @@ static int ufs_trunc_tindirect(struct inode *inode) } for (i = tindirect_block ; i < uspi->s_apb ; i++) { - tind = ubh_get_addr32 (tind_bh, i); + tind = ubh_get_data_ptr(uspi, tind_bh, i); retry |= ufs_trunc_dindirect(inode, UFS_NDADDR + uspi->s_apb + ((i + 1) << uspi->s_2apbshift), tind); ubh_mark_buffer_dirty(tind_bh); @@ -372,19 +372,21 @@ static int ufs_trunc_tindirect(struct inode *inode) } ubh_brelse (tind_bh); - UFSD("EXIT\n"); + UFSD("EXIT: ino %lu\n", inode->i_ino); return retry; } static int ufs_alloc_lastblock(struct inode *inode) { int err = 0; + struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; - struct ufs_sb_private_info *uspi = UFS_SB(inode->i_sb)->s_uspi; + struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi; unsigned i, end; sector_t lastfrag; struct page *lastpage; struct buffer_head *bh; + u64 phys64; lastfrag = (i_size_read(inode) + uspi->s_fsize - 1) >> uspi->s_fshift; @@ -424,6 +426,20 @@ static int ufs_alloc_lastblock(struct inode *inode) set_page_dirty(lastpage); } + if (lastfrag >= UFS_IND_FRAGMENT) { + end = uspi->s_fpb - ufs_fragnum(lastfrag) - 1; + phys64 = bh->b_blocknr + 1; + for (i = 0; i < end; ++i) { + bh = sb_getblk(sb, i + phys64); + lock_buffer(bh); + memset(bh->b_data, 0, sb->s_blocksize); + set_buffer_uptodate(bh); + mark_buffer_dirty(bh); + unlock_buffer(bh); + sync_dirty_buffer(bh); + brelse(bh); + } + } out_unlock: ufs_put_locked_page(lastpage); out: diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index e2bea6a..69e9e80 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -1829,11 +1829,11 @@ xfs_buf_init(void) if (!xfs_buf_zone) goto out_free_trace_buf; - xfslogd_workqueue = create_freezeable_workqueue("xfslogd"); + xfslogd_workqueue = create_workqueue("xfslogd"); if (!xfslogd_workqueue) goto out_free_buf_zone; - xfsdatad_workqueue = create_freezeable_workqueue("xfsdatad"); + xfsdatad_workqueue = create_workqueue("xfsdatad"); if (!xfsdatad_workqueue) goto out_destroy_xfslogd_workqueue; |
