diff options
Diffstat (limited to 'fs')
67 files changed, 736 insertions, 537 deletions
diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h index 8ada4c5c5d70..6a82d39dc498 100644 --- a/fs/9p/v9fs_vfs.h +++ b/fs/9p/v9fs_vfs.h @@ -40,7 +40,6 @@ extern struct file_system_type v9fs_fs_type; extern const struct address_space_operations v9fs_addr_operations; extern const struct file_operations v9fs_file_operations; -extern const struct file_operations v9fs_cached_file_operations; extern const struct file_operations v9fs_dir_operations; extern struct dentry_operations v9fs_dentry_operations; extern struct dentry_operations v9fs_cached_dentry_operations; diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 653dfa5b2531..c7b677253843 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -42,6 +42,8 @@ #include "v9fs_vfs.h" #include "fid.h" +static const struct file_operations v9fs_cached_file_operations; + /** * v9fs_file_open - open a file (or directory) * @inode: inode to be opened @@ -245,7 +247,7 @@ v9fs_file_write(struct file *filp, const char __user * data, return total; } -const struct file_operations v9fs_cached_file_operations = { +static const struct file_operations v9fs_cached_file_operations = { .llseek = generic_file_llseek, .read = do_sync_read, .aio_read = generic_file_aio_read, @@ -136,7 +136,6 @@ static int aio_setup_ring(struct kioctx *ctx) 0); if (IS_ERR((void *)info->mmap_base)) { up_write(&ctx->mm->mmap_sem); - printk("mmap err: %ld\n", -info->mmap_base); info->mmap_size = 0; aio_free_ring(ctx); return -EAGAIN; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 51db1182b27e..9cc4f0a8aaae 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) @@ -1704,7 +1704,10 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file) DUMP_SEEK(PAGE_SIZE); } else { if (page == ZERO_PAGE(addr)) { - DUMP_SEEK(PAGE_SIZE); + if (!dump_seek(file, PAGE_SIZE)) { + page_cache_release(page); + goto end_coredump; + } } else { void *kaddr; flush_cache_page(vma, addr, diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 5810aa1339fd..f3ddca4a387b 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -179,6 +179,8 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm, int executable_stack; int retval, i; + kdebug("____ LOAD %d ____", current->pid); + memset(&exec_params, 0, sizeof(exec_params)); memset(&interp_params, 0, sizeof(interp_params)); @@ -941,8 +943,11 @@ static int elf_fdpic_map_file_constdisp_on_uclinux( if (mm) { if (phdr->p_flags & PF_X) { - mm->start_code = seg->addr; - mm->end_code = seg->addr + phdr->p_memsz; + if (!mm->start_code) { + mm->start_code = seg->addr; + mm->end_code = seg->addr + + phdr->p_memsz; + } } else if (!mm->start_data) { mm->start_data = seg->addr; #ifndef CONFIG_MMU @@ -1123,8 +1128,10 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params, if (mm) { if (phdr->p_flags & PF_X) { - mm->start_code = maddr; - mm->end_code = maddr + phdr->p_memsz; + if (!mm->start_code) { + mm->start_code = maddr; + mm->end_code = maddr + phdr->p_memsz; + } } else if (!mm->start_data) { mm->start_data = maddr; mm->end_data = maddr + phdr->p_memsz; @@ -1473,8 +1480,8 @@ static int elf_fdpic_dump_segments(struct file *file, struct mm_struct *mm, DUMP_SEEK(file->f_pos + PAGE_SIZE); } else if (page == ZERO_PAGE(addr)) { - DUMP_SEEK(file->f_pos + PAGE_SIZE); page_cache_release(page); + DUMP_SEEK(file->f_pos + PAGE_SIZE); } else { void *kaddr; diff --git a/fs/char_dev.c b/fs/char_dev.c index 78ced721554d..164a45cdaf5f 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -109,8 +109,6 @@ __register_chrdev_region(unsigned int major, unsigned int baseminor, /* temporary */ if (major == 0) { for (i = ARRAY_SIZE(chrdevs)-1; i > 0; i--) { - if (is_lanana_major(i)) - continue; if (chrdevs[i] == NULL) break; } diff --git a/fs/cifs/CHANGES b/fs/cifs/CHANGES index 6247628bdaed..5d1f4873d701 100644 --- a/fs/cifs/CHANGES +++ b/fs/cifs/CHANGES @@ -4,6 +4,12 @@ Fix mtime bouncing around from local idea of last write times to remote time. Fix hang (in i_size_read) when simultaneous size update of same remote file on smp system corrupts sequence number. Do not reread unnecessarily partial page (which we are about to overwrite anyway) when writing out file opened rw. +When DOS attribute of file on non-Unix server's file changes on the server side +from read-only back to read-write, reflect this change in default file mode +(we had been leaving a file's mode read-only until the inode were reloaded). +Allow setting of attribute back to ATTR_NORMAL (removing readonly dos attribute +when archive dos attribute not set and we are changing mode back to writeable +on server which does not support the Unix Extensions). Version 1.47 ------------ diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h index 0efdf35aab2c..4d8948e8762c 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 */ @@ -1887,7 +1887,13 @@ typedef struct { calls including posix open and posix unlink */ #ifdef CONFIG_CIFS_POSIX -#define CIFS_UNIX_CAP_MASK 0x0000003b +/* Can not set pathnames cap yet until we send new posix create SMB since + otherwise server can treat such handles opened with older ntcreatex + (by a new client which knows how to send posix path ops) + as non-posix handles (can affect write behavior with byte range locks. + We can add back in POSIX_PATH_OPS cap when Posix Create/Mkdir finished */ +/* #define CIFS_UNIX_CAP_MASK 0x0000003b */ +#define CIFS_UNIX_CAP_MASK 0x0000001b #else #define CIFS_UNIX_CAP_MASK 0x00000013 #endif /* CONFIG_CIFS_POSIX */ diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 86b9dbbd8441..f414526e476a 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -494,6 +494,12 @@ int cifs_get_inode_info(struct inode **pinode, mode e.g. 555 */ if (cifsInfo->cifsAttrs & ATTR_READONLY) inode->i_mode &= ~(S_IWUGO); + else if ((inode->i_mode & S_IWUGO) == 0) + /* the ATTR_READONLY flag may have been */ + /* changed on server -- set any w bits */ + /* allowed by mnt_file_mode */ + inode->i_mode |= (S_IWUGO & + cifs_sb->mnt_file_mode); /* BB add code here - validate if device or weird share or device type? */ } @@ -1190,6 +1196,7 @@ int cifs_setattr(struct dentry *direntry, struct iattr *attrs) struct cifsFileInfo *open_file = NULL; FILE_BASIC_INFO time_buf; int set_time = FALSE; + int set_dosattr = FALSE; __u64 mode = 0xFFFFFFFFFFFFFFFFULL; __u64 uid = 0xFFFFFFFFFFFFFFFFULL; __u64 gid = 0xFFFFFFFFFFFFFFFFULL; @@ -1326,15 +1333,23 @@ int cifs_setattr(struct dentry *direntry, struct iattr *attrs) else if (attrs->ia_valid & ATTR_MODE) { rc = 0; if ((mode & S_IWUGO) == 0) /* not writeable */ { - if ((cifsInode->cifsAttrs & ATTR_READONLY) == 0) + if ((cifsInode->cifsAttrs & ATTR_READONLY) == 0) { + set_dosattr = TRUE; time_buf.Attributes = cpu_to_le32(cifsInode->cifsAttrs | ATTR_READONLY); + } } else if ((mode & S_IWUGO) == S_IWUGO) { - if (cifsInode->cifsAttrs & ATTR_READONLY) + if (cifsInode->cifsAttrs & ATTR_READONLY) { + set_dosattr = TRUE; time_buf.Attributes = cpu_to_le32(cifsInode->cifsAttrs & (~ATTR_READONLY)); + /* Windows ignores set to zero */ + if(time_buf.Attributes == 0) + time_buf.Attributes |= + cpu_to_le32(ATTR_NORMAL); + } } /* BB to be implemented - via Windows security descriptors or streams */ @@ -1372,7 +1387,7 @@ int cifs_setattr(struct dentry *direntry, struct iattr *attrs) } else time_buf.ChangeTime = 0; - if (set_time || time_buf.Attributes) { + if (set_time || set_dosattr) { time_buf.CreationTime = 0; /* do not change */ /* In the future we should experiment - try setting timestamps via Handle (SetFileInfo) instead of by path */ diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 44cfb528797d..2a374d5215ab 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -219,6 +219,10 @@ static void fill_in_inode(struct inode *tmp_inode, int new_buf_type, tmp_inode->i_mode |= S_IFREG; if (attr & ATTR_READONLY) tmp_inode->i_mode &= ~(S_IWUGO); + else if ((tmp_inode->i_mode & S_IWUGO) == 0) + /* the ATTR_READONLY flag may have been changed on */ + /* server -- set any w bits allowed by mnt_file_mode */ + tmp_inode->i_mode |= (S_IWUGO & cifs_sb->mnt_file_mode); } /* could add code here - to validate if device or weird share type? */ /* can not fill in nlink here as in qpathinfo version and Unx search */ diff --git a/fs/compat.c b/fs/compat.c index 0ec70e3cee0a..040a8be38a48 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/compat_ioctl.c b/fs/compat_ioctl.c index c81c958b3e1d..8b1c5d8bf4ef 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -2553,11 +2553,15 @@ HANDLE_IOCTL(I2C_RDWR, do_i2c_rdwr_ioctl) HANDLE_IOCTL(I2C_SMBUS, do_i2c_smbus_ioctl) /* wireless */ HANDLE_IOCTL(SIOCGIWRANGE, do_wireless_ioctl) +HANDLE_IOCTL(SIOCGIWPRIV, do_wireless_ioctl) +HANDLE_IOCTL(SIOCGIWSTATS, do_wireless_ioctl) HANDLE_IOCTL(SIOCSIWSPY, do_wireless_ioctl) HANDLE_IOCTL(SIOCGIWSPY, do_wireless_ioctl) HANDLE_IOCTL(SIOCSIWTHRSPY, do_wireless_ioctl) HANDLE_IOCTL(SIOCGIWTHRSPY, do_wireless_ioctl) +HANDLE_IOCTL(SIOCSIWMLME, do_wireless_ioctl) HANDLE_IOCTL(SIOCGIWAPLIST, do_wireless_ioctl) +HANDLE_IOCTL(SIOCSIWSCAN, do_wireless_ioctl) HANDLE_IOCTL(SIOCGIWSCAN, do_wireless_ioctl) HANDLE_IOCTL(SIOCSIWESSID, do_wireless_ioctl) HANDLE_IOCTL(SIOCGIWESSID, do_wireless_ioctl) @@ -2565,6 +2569,11 @@ HANDLE_IOCTL(SIOCSIWNICKN, do_wireless_ioctl) HANDLE_IOCTL(SIOCGIWNICKN, do_wireless_ioctl) HANDLE_IOCTL(SIOCSIWENCODE, do_wireless_ioctl) HANDLE_IOCTL(SIOCGIWENCODE, do_wireless_ioctl) +HANDLE_IOCTL(SIOCSIWGENIE, do_wireless_ioctl) +HANDLE_IOCTL(SIOCGIWGENIE, do_wireless_ioctl) +HANDLE_IOCTL(SIOCSIWENCODEEXT, do_wireless_ioctl) +HANDLE_IOCTL(SIOCGIWENCODEEXT, do_wireless_ioctl) +HANDLE_IOCTL(SIOCSIWPMKSA, do_wireless_ioctl) HANDLE_IOCTL(SIOCSIFBR, old_bridge_ioctl) HANDLE_IOCTL(SIOCGIFBR, old_bridge_ioctl) HANDLE_IOCTL(RTC_IRQP_READ32, rtc_ioctl) diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index 34750d5e4ff2..5e6e37e58f36 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/dlm/user.c b/fs/dlm/user.c index 40db61dc95f2..3870150b83a4 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -22,6 +22,7 @@ #include "lockspace.h" #include "lock.h" #include "lvb_table.h" +#include "user.h" static const char *name_prefix="dlm"; static struct miscdevice ctl_device; diff --git a/fs/ecryptfs/dentry.c b/fs/ecryptfs/dentry.c index 329efcd3d8c9..cb20b964419f 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 e62f3fc7241e..1548be26b5e6 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/ext3/inode.c b/fs/ext3/inode.c index 8a824f4ce5c6..a5b150f7e8a2 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -1148,102 +1148,37 @@ static int do_journal_get_write_access(handle_t *handle, return ext3_journal_get_write_access(handle, bh); } -/* - * The idea of this helper function is following: - * if prepare_write has allocated some blocks, but not all of them, the - * transaction must include the content of the newly allocated blocks. - * This content is expected to be set to zeroes by block_prepare_write(). - * 2006/10/14 SAW - */ -static int ext3_prepare_failure(struct file *file, struct page *page, - unsigned from, unsigned to) -{ - struct address_space *mapping; - struct buffer_head *bh, *head, *next; - unsigned block_start, block_end; - unsigned blocksize; - int ret; - handle_t *handle = ext3_journal_current_handle(); - - mapping = page->mapping; - if (ext3_should_writeback_data(mapping->host)) { - /* optimization: no constraints about data */ -skip: - return ext3_journal_stop(handle); - } - - head = page_buffers(page); - blocksize = head->b_size; - for ( bh = head, block_start = 0; - bh != head || !block_start; - block_start = block_end, bh = next) - { - next = bh->b_this_page; - block_end = block_start + blocksize; - if (block_end <= from) - continue; - if (block_start >= to) { - block_start = to; - break; - } - if (!buffer_mapped(bh)) - /* prepare_write failed on this bh */ - break; - if (ext3_should_journal_data(mapping->host)) { - ret = do_journal_get_write_access(handle, bh); - if (ret) { - ext3_journal_stop(handle); - return ret; - } - } - /* - * block_start here becomes the first block where the current iteration - * of prepare_write failed. - */ - } - if (block_start <= from) - goto skip; - - /* commit allocated and zeroed buffers */ - return mapping->a_ops->commit_write(file, page, from, block_start); -} - static int ext3_prepare_write(struct file *file, struct page *page, unsigned from, unsigned to) { struct inode *inode = page->mapping->host; - int ret, ret2; - int needed_blocks = ext3_writepage_trans_blocks(inode); + int ret, needed_blocks = ext3_writepage_trans_blocks(inode); handle_t *handle; int retries = 0; retry: handle = ext3_journal_start(inode, needed_blocks); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out; + } if (test_opt(inode->i_sb, NOBH) && ext3_should_writeback_data(inode)) ret = nobh_prepare_write(page, from, to, ext3_get_block); else ret = block_prepare_write(page, from, to, ext3_get_block); if (ret) - goto failure; + goto prepare_write_failed; if (ext3_should_journal_data(inode)) { ret = walk_page_buffers(handle, page_buffers(page), from, to, NULL, do_journal_get_write_access); - if (ret) - /* fatal error, just put the handle and return */ - journal_stop(handle); } - return ret; - -failure: - ret2 = ext3_prepare_failure(file, page, from, to); - if (ret2 < 0) - return ret2; +prepare_write_failed: + if (ret) + ext3_journal_stop(handle); if (ret == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries)) goto retry; - /* retry number exceeded, or other error like -EDQUOT */ +out: return ret; } diff --git a/fs/ext3/xattr.c b/fs/ext3/xattr.c index 12f7dda1232c..f58cbb26323e 100644 --- a/fs/ext3/xattr.c +++ b/fs/ext3/xattr.c @@ -495,7 +495,8 @@ ext3_xattr_release_block(handle_t *handle, struct inode *inode, BHDR(bh)->h_refcount = cpu_to_le32( le32_to_cpu(BHDR(bh)->h_refcount) - 1); error = ext3_journal_dirty_metadata(handle, bh); - handle->h_sync = 1; + if (IS_SYNC(inode)) + handle->h_sync = 1; DQUOT_FREE_BLOCK(inode, 1); ea_bdebug(bh, "refcount now=%d; releasing", le32_to_cpu(BHDR(bh)->h_refcount)); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index fbff4b9e122a..810b6d6474bf 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1147,102 +1147,37 @@ static int do_journal_get_write_access(handle_t *handle, return ext4_journal_get_write_access(handle, bh); } -/* - * The idea of this helper function is following: - * if prepare_write has allocated some blocks, but not all of them, the - * transaction must include the content of the newly allocated blocks. - * This content is expected to be set to zeroes by block_prepare_write(). - * 2006/10/14 SAW - */ -static int ext4_prepare_failure(struct file *file, struct page *page, - unsigned from, unsigned to) -{ - struct address_space *mapping; - struct buffer_head *bh, *head, *next; - unsigned block_start, block_end; - unsigned blocksize; - int ret; - handle_t *handle = ext4_journal_current_handle(); - - mapping = page->mapping; - if (ext4_should_writeback_data(mapping->host)) { - /* optimization: no constraints about data */ -skip: - return ext4_journal_stop(handle); - } - - head = page_buffers(page); - blocksize = head->b_size; - for ( bh = head, block_start = 0; - bh != head || !block_start; - block_start = block_end, bh = next) - { - next = bh->b_this_page; - block_end = block_start + blocksize; - if (block_end <= from) - continue; - if (block_start >= to) { - block_start = to; - break; - } - if (!buffer_mapped(bh)) - /* prepare_write failed on this bh */ - break; - if (ext4_should_journal_data(mapping->host)) { - ret = do_journal_get_write_access(handle, bh); - if (ret) { - ext4_journal_stop(handle); - return ret; - } - } - /* - * block_start here becomes the first block where the current iteration - * of prepare_write failed. - */ - } - if (block_start <= from) - goto skip; - - /* commit allocated and zeroed buffers */ - return mapping->a_ops->commit_write(file, page, from, block_start); -} - static int ext4_prepare_write(struct file *file, struct page *page, unsigned from, unsigned to) { struct inode *inode = page->mapping->host; - int ret, ret2; - int needed_blocks = ext4_writepage_trans_blocks(inode); + int ret, needed_blocks = ext4_writepage_trans_blocks(inode); handle_t *handle; int retries = 0; retry: handle = ext4_journal_start(inode, needed_blocks); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out; + } if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode)) ret = nobh_prepare_write(page, from, to, ext4_get_block); else ret = block_prepare_write(page, from, to, ext4_get_block); if (ret) - goto failure; + goto prepare_write_failed; if (ext4_should_journal_data(inode)) { ret = walk_page_buffers(handle, page_buffers(page), from, to, NULL, do_journal_get_write_access); - if (ret) - /* fatal error, just put the handle and return */ - ext4_journal_stop(handle); } - return ret; - -failure: - ret2 = ext4_prepare_failure(file, page, from, to); - if (ret2 < 0) - return ret2; +prepare_write_failed: + if (ret) + ext4_journal_stop(handle); if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry; - /* retry number exceeded, or other error like -EDQUOT */ +out: return ret; } diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 406bf61ed510..8890eba1db52 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -195,7 +195,7 @@ static struct dentry_operations fuse_dentry_operations = { .d_revalidate = fuse_dentry_revalidate, }; -static int valid_mode(int m) +int fuse_valid_type(int m) { return S_ISREG(m) || S_ISDIR(m) || S_ISLNK(m) || S_ISCHR(m) || S_ISBLK(m) || S_ISFIFO(m) || S_ISSOCK(m); @@ -248,7 +248,8 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, fuse_put_request(fc, req); /* Zero nodeid is same as -ENOENT, but with valid timeout */ if (!err && outarg.nodeid && - (invalid_nodeid(outarg.nodeid) || !valid_mode(outarg.attr.mode))) + (invalid_nodeid(outarg.nodeid) || + !fuse_valid_type(outarg.attr.mode))) err = -EIO; if (!err && outarg.nodeid) { inode = fuse_iget(dir->i_sb, outarg.nodeid, outarg.generation, diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index b98b20de7405..68ae87cbafab 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -552,3 +552,8 @@ int fuse_ctl_add_conn(struct fuse_conn *fc); * Remove connection from control filesystem */ void fuse_ctl_remove_conn(struct fuse_conn *fc); + +/** + * Is file type valid? + */ +int fuse_valid_type(int m); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 5ab8e50e7808..608db81219a0 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -330,6 +330,8 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev) case OPT_ROOTMODE: if (match_octal(&args[0], &value)) return 0; + if (!fuse_valid_type(value)) + return 0; d->rootmode = value; d->rootmode_present = 1; break; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 6618c1190252..12accb08fe02 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -20,6 +20,7 @@ #include <linux/list.h> #include <linux/lm_interface.h> #include <linux/wait.h> +#include <linux/module.h> #include <linux/rwsem.h> #include <asm/uaccess.h> @@ -953,9 +954,6 @@ static void drop_bh(struct gfs2_glock *gl, unsigned int ret) spin_unlock(&gl->gl_spin); } - if (glops->go_drop_bh) - glops->go_drop_bh(gl); - spin_lock(&gl->gl_spin); gl->gl_req_gh = NULL; gl->gl_req_bh = NULL; diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 46af55355513..39c8ae23bd9c 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -245,7 +245,6 @@ static void inode_go_inval(struct gfs2_glock *gl, int flags) if (ip && S_ISREG(ip->i_inode.i_mode)) { truncate_inode_pages(ip->i_inode.i_mapping, 0); - gfs2_assert_withdraw(GFS2_SB(&ip->i_inode), !ip->i_inode.i_mapping->nrpages); clear_bit(GIF_PAGED, &ip->i_flags); } } @@ -459,6 +458,8 @@ const struct gfs2_glock_operations gfs2_inode_glops = { }; const struct gfs2_glock_operations gfs2_rgrp_glops = { + .go_xmote_th = meta_go_sync, + .go_drop_th = meta_go_sync, .go_inval = meta_go_inval, .go_demote_ok = rgrp_go_demote_ok, .go_lock = rgrp_go_lock, diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 12c80fd28db5..49f0dbf40d86 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -104,7 +104,6 @@ struct gfs2_glock_operations { void (*go_xmote_th) (struct gfs2_glock *gl); void (*go_xmote_bh) (struct gfs2_glock *gl); void (*go_drop_th) (struct gfs2_glock *gl); - void (*go_drop_bh) (struct gfs2_glock *gl); void (*go_inval) (struct gfs2_glock *gl, int flags); int (*go_demote_ok) (struct gfs2_glock *gl); int (*go_lock) (struct gfs2_holder *gh); @@ -416,7 +415,6 @@ struct gfs2_tune { unsigned int gt_stall_secs; /* Detects trouble! */ unsigned int gt_complain_secs; unsigned int gt_reclaim_limit; /* Max num of glocks in reclaim list */ - unsigned int gt_entries_per_readdir; unsigned int gt_statfs_quantum; unsigned int gt_statfs_slow; }; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 0d6831a40565..df0b8b3018b9 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -43,7 +43,8 @@ static int iget_test(struct inode *inode, void *opaque) struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_inum_host *inum = opaque; - if (ip->i_num.no_addr == inum->no_addr) + if (ip->i_num.no_addr == inum->no_addr && + inode->i_private != NULL) return 1; return 0; @@ -61,13 +62,13 @@ static int iget_set(struct inode *inode, void *opaque) struct inode *gfs2_ilookup(struct super_block *sb, struct gfs2_inum_host *inum) { - return ilookup5(sb, (unsigned long)inum->no_formal_ino, + return ilookup5(sb, (unsigned long)inum->no_addr, iget_test, inum); } static struct inode *gfs2_iget(struct super_block *sb, struct gfs2_inum_host *inum) { - return iget5_locked(sb, (unsigned long)inum->no_formal_ino, + return iget5_locked(sb, (unsigned long)inum->no_addr, iget_test, iget_set, inum); } diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/ops_address.c index 56e33590b656..b3b7e8475359 100644 --- a/fs/gfs2/ops_address.c +++ b/fs/gfs2/ops_address.c @@ -266,9 +266,11 @@ skip_lock: out: return error; out_unlock: - if (error == GLR_TRYFAILED) - error = AOP_TRUNCATED_PAGE; unlock_page(page); + if (error == GLR_TRYFAILED) { + error = AOP_TRUNCATED_PAGE; + yield(); + } if (do_unlock) gfs2_holder_uninit(&gh); goto out; @@ -364,6 +366,7 @@ static int gfs2_prepare_write(struct file *file, struct page *page, if (error == GLR_TRYFAILED) { unlock_page(page); error = AOP_TRUNCATED_PAGE; + yield(); } goto out_uninit; } diff --git a/fs/gfs2/ops_export.c b/fs/gfs2/ops_export.c index 1de05b63d43a..aad918337a46 100644 --- a/fs/gfs2/ops_export.c +++ b/fs/gfs2/ops_export.c @@ -38,14 +38,11 @@ static struct dentry *gfs2_decode_fh(struct super_block *sb, struct gfs2_fh_obj fh_obj; struct gfs2_inum_host *this, parent; - if (fh_type != fh_len) - return NULL; - this = &fh_obj.this; fh_obj.imode = DT_UNKNOWN; memset(&parent, 0, sizeof(struct gfs2_inum)); - switch (fh_type) { + switch (fh_len) { case GFS2_LARGE_FH_SIZE: parent.no_formal_ino = ((u64)be32_to_cpu(fh[4])) << 32; parent.no_formal_ino |= be32_to_cpu(fh[5]); diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index ee80b8a5e7bc..ee54cb667083 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -840,7 +840,7 @@ static struct super_block* get_gfs2_sb(const char *dev_name) } printk(KERN_WARNING "GFS2: Unrecognized block device or " - "mount point %s", dev_name); + "mount point %s\n", dev_name); free_nd: path_release(&nd); diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index d0db881b55d2..c186857e48a8 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -279,7 +279,7 @@ static int bh_get(struct gfs2_quota_data *qd) (bh->b_data + sizeof(struct gfs2_meta_header) + offset * sizeof(struct gfs2_quota_change)); - mutex_lock(&sdp->sd_quota_mutex); + mutex_unlock(&sdp->sd_quota_mutex); return 0; diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 70f424fcf1cd..4fdda974dc83 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -76,7 +76,6 @@ void gfs2_tune_init(struct gfs2_tune *gt) gt->gt_stall_secs = 600; gt->gt_complain_secs = 10; gt->gt_reclaim_limit = 5000; - gt->gt_entries_per_readdir = 32; gt->gt_statfs_quantum = 30; gt->gt_statfs_slow = 0; } diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index e965eb11d76f..fd301a910122 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -20,7 +20,6 @@ #include "hostfs.h" #include "kern_util.h" #include "kern.h" -#include "user_util.h" #include "init.h" struct hostfs_inode_info { @@ -47,7 +46,7 @@ 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 @@ -939,7 +938,7 @@ static const struct address_space_operations hostfs_link_aops = { static int hostfs_fill_sb_common(struct super_block *sb, void *d, int silent) { struct inode *root_inode; - char *name, *data = d; + char *host_root_path, *req_root = d; int err; sb->s_blocksize = 1024; @@ -947,15 +946,17 @@ 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 (req_root == NULL) + req_root = ""; err = -ENOMEM; - name = kmalloc(strlen(data) + 1, GFP_KERNEL); - if(name == NULL) + host_root_path = kmalloc(strlen(root_ino) + 1 + + strlen(req_root) + 1, GFP_KERNEL); + if(host_root_path == NULL) goto out; - strcpy(name, data); + sprintf(host_root_path, "%s/%s", root_ino, req_root); root_inode = iget(sb, 0); if(root_inode == NULL) @@ -965,7 +966,10 @@ static int hostfs_fill_sb_common(struct super_block *sb, void *d, int silent) if(err) goto out_put; - HOSTFS_I(root_inode)->host_filename = name; + HOSTFS_I(root_inode)->host_filename = host_root_path; + /* Avoid that in the error path, iput(root_inode) frees again + * host_root_path through hostfs_destroy_inode! */ + host_root_path = NULL; err = -ENOMEM; sb->s_root = d_alloc_root(root_inode); @@ -977,7 +981,7 @@ 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); @@ -985,7 +989,7 @@ static int hostfs_fill_sb_common(struct super_block *sb, void *d, int silent) out_put: iput(root_inode); out_free: - kfree(name); + kfree(host_root_path); out: return(err); } diff --git a/fs/jffs2/background.c b/fs/jffs2/background.c index 6eb3daebd563..888f236e5494 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 58a0b912e9d0..717a48cf7df2 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 31c1475d922a..7fb45bd4915c 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 de718e3a1692..4fac6dd53954 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 af53c02f473b..93d046c85f52 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 bb516a2cfbaf..f1eae44b9a1a 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 fcdcafbb3293..b62481dabae9 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 febdade91670..2867e6b7096f 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/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 6f677988c71d..7e4bb0af24d7 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -859,8 +859,8 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp, #define NFS3_ENTRY_BAGGAGE (2 + 1 + 2 + 1) #define NFS3_ENTRYPLUS_BAGGAGE (1 + 21 + 1 + (NFS3_FHSIZE >> 2)) static int -encode_entry(struct readdir_cd *ccd, const char *name, - int namlen, off_t offset, ino_t ino, unsigned int d_type, int plus) +encode_entry(struct readdir_cd *ccd, const char *name, int namlen, + loff_t offset, ino_t ino, unsigned int d_type, int plus) { struct nfsd3_readdirres *cd = container_of(ccd, struct nfsd3_readdirres, common); @@ -880,7 +880,7 @@ encode_entry(struct readdir_cd *ccd, const char *name, *cd->offset1 = htonl(offset64 & 0xffffffff); cd->offset1 = NULL; } else { - xdr_encode_hyper(cd->offset, (u64) offset); + xdr_encode_hyper(cd->offset, offset64); } } diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c index 832673b14587..673a53c014a3 100644 --- a/fs/nfsd/nfs4acl.c +++ b/fs/nfsd/nfs4acl.c @@ -228,7 +228,7 @@ _posix_to_nfsv4_one(struct posix_acl *pacl, struct nfs4_acl *acl, struct posix_acl_summary pas; unsigned short deny; int eflag = ((flags & NFS4_ACL_TYPE_DEFAULT) ? - NFS4_INHERITANCE_FLAGS : 0); + NFS4_INHERITANCE_FLAGS | NFS4_ACE_INHERIT_ONLY_ACE : 0); BUG_ON(pacl->a_count < 3); summarize_posix_acl(pacl, &pas); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 9e4067999209..af360705e551 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -750,9 +750,8 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfserr_clid_inuse; if (!cmp_creds(&conf->cl_cred, &rqstp->rq_cred) || conf->cl_addr != sin->sin_addr.s_addr) { - printk("NFSD: setclientid: string in use by client" - "(clientid %08x/%08x)\n", - conf->cl_clientid.cl_boot, conf->cl_clientid.cl_id); + dprintk("NFSD: setclientid: string in use by client" + "at %u.%u.%u.%u\n", NIPQUAD(conf->cl_addr)); goto out; } } @@ -3261,7 +3260,6 @@ __nfs4_state_shutdown(void) unhash_delegation(dp); } - cancel_delayed_work(&laundromat_work); nfsd4_shutdown_recdir(); nfs4_init = 0; } diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index c2660cbfcd96..8d995bcef806 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 93628b02ef5d..875c11443817 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 5a9779bb9236..eba282da500e 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 cac6223206a9..cc6d40b39771 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 1718215fc018..69caf3e12fea 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/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index 6087c4749fee..c558442a0b44 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -138,8 +138,10 @@ static void dlm_unregister_domain_handlers(struct dlm_ctxt *dlm); void __dlm_unhash_lockres(struct dlm_lock_resource *lockres) { - hlist_del_init(&lockres->hash_node); - dlm_lockres_put(lockres); + if (!hlist_unhashed(&lockres->hash_node)) { + hlist_del_init(&lockres->hash_node); + dlm_lockres_put(lockres); + } } void __dlm_insert_lockres(struct dlm_ctxt *dlm, @@ -655,6 +657,8 @@ void dlm_unregister_domain(struct dlm_ctxt *dlm) dlm_kick_thread(dlm, NULL); while (dlm_migrate_all_locks(dlm)) { + /* Give dlm_thread time to purge the lockres' */ + msleep(500); mlog(0, "%s: more migration to do\n", dlm->name); } dlm_mark_domain_leaving(dlm); diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 77e4e6169a0d..6edffca99d98 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -2424,6 +2424,57 @@ static void dlm_deref_lockres_worker(struct dlm_work_item *item, void *data) dlm_lockres_put(res); } +/* Checks whether the lockres can be migrated. Returns 0 if yes, < 0 + * if not. If 0, numlocks is set to the number of locks in the lockres. + */ +static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm, + struct dlm_lock_resource *res, + int *numlocks) +{ + int ret; + int i; + int count = 0; + struct list_head *queue, *iter; + struct dlm_lock *lock; + + assert_spin_locked(&res->spinlock); + + ret = -EINVAL; + if (res->owner == DLM_LOCK_RES_OWNER_UNKNOWN) { + mlog(0, "cannot migrate lockres with unknown owner!\n"); + goto leave; + } + + if (res->owner != dlm->node_num) { + mlog(0, "cannot migrate lockres this node doesn't own!\n"); + goto leave; + } + + ret = 0; + queue = &res->granted; + for (i = 0; i < 3; i++) { + list_for_each(iter, queue) { + lock = list_entry(iter, struct dlm_lock, list); + ++count; + if (lock->ml.node == dlm->node_num) { + mlog(0, "found a lock owned by this node still " + "on the %s queue! will not migrate this " + "lockres\n", (i == 0 ? "granted" : + (i == 1 ? "converting" : + "blocked"))); + ret = -ENOTEMPTY; + goto leave; + } + } + queue++; + } + + *numlocks = count; + mlog(0, "migrateable lockres having %d locks\n", *numlocks); + +leave: + return ret; +} /* * DLM_MIGRATE_LOCKRES @@ -2437,14 +2488,12 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm, struct dlm_master_list_entry *mle = NULL; struct dlm_master_list_entry *oldmle = NULL; struct dlm_migratable_lockres *mres = NULL; - int ret = -EINVAL; + int ret = 0; const char *name; unsigned int namelen; int mle_added = 0; - struct list_head *queue, *iter; - int i; - struct dlm_lock *lock; - int empty = 1, wake = 0; + int numlocks; + int wake = 0; if (!dlm_grab(dlm)) return -EINVAL; @@ -2458,42 +2507,16 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm, * ensure this lockres is a proper candidate for migration */ spin_lock(&res->spinlock); - if (res->owner == DLM_LOCK_RES_OWNER_UNKNOWN) { - mlog(0, "cannot migrate lockres with unknown owner!\n"); - spin_unlock(&res->spinlock); - goto leave; - } - if (res->owner != dlm->node_num) { - mlog(0, "cannot migrate lockres this node doesn't own!\n"); + ret = dlm_is_lockres_migrateable(dlm, res, &numlocks); + if (ret < 0) { spin_unlock(&res->spinlock); goto leave; } - mlog(0, "checking queues...\n"); - queue = &res->granted; - for (i=0; i<3; i++) { - list_for_each(iter, queue) { - lock = list_entry (iter, struct dlm_lock, list); - empty = 0; - if (lock->ml.node == dlm->node_num) { - mlog(0, "found a lock owned by this node " - "still on the %s queue! will not " - "migrate this lockres\n", - i==0 ? "granted" : - (i==1 ? "converting" : "blocked")); - spin_unlock(&res->spinlock); - ret = -ENOTEMPTY; - goto leave; - } - } - queue++; - } - mlog(0, "all locks on this lockres are nonlocal. continuing\n"); spin_unlock(&res->spinlock); /* no work to do */ - if (empty) { + if (numlocks == 0) { mlog(0, "no locks were found on this lockres! done!\n"); - ret = 0; goto leave; } @@ -2729,15 +2752,26 @@ int dlm_empty_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res) { int ret; int lock_dropped = 0; + int numlocks; + 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; + } + + /* No need to migrate a lockres having no locks */ + ret = dlm_is_lockres_migrateable(dlm, res, &numlocks); + if (ret >= 0 && numlocks == 0) { + 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 8ffa0916eb86..2b264c6ba039 100644 --- a/fs/ocfs2/dlm/dlmthread.c +++ b/fs/ocfs2/dlm/dlmthread.c @@ -256,18 +256,14 @@ static void dlm_run_purge_list(struct dlm_ctxt *dlm, break; } - mlog(0, "removing lockres %.*s:%p from purgelist\n", - lockres->lockname.len, lockres->lockname.name, lockres); - list_del_init(&lockres->purge); - dlm_lockres_put(lockres); - dlm->purge_count--; + dlm_lockres_get(lockres); /* This may drop and reacquire the dlm spinlock if it * has to do migration. */ - mlog(0, "calling dlm_purge_lockres!\n"); if (dlm_purge_lockres(dlm, lockres)) BUG(); - mlog(0, "DONE calling dlm_purge_lockres!\n"); + + dlm_lockres_put(lockres); /* Avoid adding any scheduling latencies */ cond_resched_lock(&dlm->spinlock); diff --git a/fs/ocfs2/heartbeat.c b/fs/ocfs2/heartbeat.c index 8fc52d6d0ce7..b25ef63781ba 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 74552c60b671..6e8bb66fe619 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 22d38ffc9ef0..8a7d0035ad7a 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/Makefile b/fs/proc/Makefile index a6b3a8f878f0..bce38e3f06cb 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -8,8 +8,9 @@ proc-y := nommu.o task_nommu.o proc-$(CONFIG_MMU) := mmu.o task_mmu.o proc-y += inode.o root.o base.o generic.o array.o \ - proc_tty.o proc_misc.o proc_sysctl.o + proc_tty.o proc_misc.o +proc-$(CONFIG_PROC_SYSCTL) += proc_sysctl.o proc-$(CONFIG_PROC_KCORE) += kcore.o proc-$(CONFIG_PROC_VMCORE) += vmcore.o proc-$(CONFIG_PROC_DEVICETREE) += proc_devtree.o diff --git a/fs/proc/base.c b/fs/proc/base.c index 01f7769da8e6..989af5e55d1b 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/proc/internal.h b/fs/proc/internal.h index c932aa65e198..f771889183c3 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -11,7 +11,11 @@ #include <linux/proc_fs.h> +#ifdef CONFIG_PROC_SYSCTL extern int proc_sys_init(void); +#else +static inline void proc_sys_init(void) { } +#endif struct vmalloc_info { unsigned long used; diff --git a/fs/proc/root.c b/fs/proc/root.c index 5834a744c2a9..41f17037f738 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -79,9 +79,7 @@ void __init proc_root_init(void) proc_device_tree_init(); #endif proc_bus = proc_mkdir("bus", NULL); -#ifdef CONFIG_SYSCTL proc_sys_init(); -#endif } static int proc_root_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat diff --git a/fs/smbfs/request.c b/fs/smbfs/request.c index 42261dbdf60f..723f7c667661 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/splice.c b/fs/splice.c index 2fca6ebf4cc2..5428b0ff3b6f 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -576,76 +576,21 @@ static int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf, if (this_len + offset > PAGE_CACHE_SIZE) this_len = PAGE_CACHE_SIZE - offset; - /* - * Reuse buf page, if SPLICE_F_MOVE is set and we are doing a full - * page. - */ - if ((sd->flags & SPLICE_F_MOVE) && this_len == PAGE_CACHE_SIZE) { - /* - * If steal succeeds, buf->page is now pruned from the - * pagecache and we can reuse it. The page will also be - * locked on successful return. - */ - if (buf->ops->steal(pipe, buf)) - goto find_page; - - page = buf->page; - if (add_to_page_cache(page, mapping, index, GFP_KERNEL)) { - unlock_page(page); - goto find_page; - } - - page_cache_get(page); - - if (!(buf->flags & PIPE_BUF_FLAG_LRU)) - lru_cache_add(page); - } else { find_page: - page = find_lock_page(mapping, index); - if (!page) { - ret = -ENOMEM; - page = page_cache_alloc_cold(mapping); - if (unlikely(!page)) - goto out_ret; - - /* - * This will also lock the page - */ - ret = add_to_page_cache_lru(page, mapping, index, - GFP_KERNEL); - if (unlikely(ret)) - goto out; - } + page = find_lock_page(mapping, index); + if (!page) { + ret = -ENOMEM; + page = page_cache_alloc_cold(mapping); + if (unlikely(!page)) + goto out_ret; /* - * We get here with the page locked. If the page is also - * uptodate, we don't need to do more. If it isn't, we - * may need to bring it in if we are not going to overwrite - * the full page. + * This will also lock the page */ - if (!PageUptodate(page)) { - if (this_len < PAGE_CACHE_SIZE) { - ret = mapping->a_ops->readpage(file, page); - if (unlikely(ret)) - goto out; - - lock_page(page); - - if (!PageUptodate(page)) { - /* - * Page got invalidated, repeat. - */ - if (!page->mapping) { - unlock_page(page); - page_cache_release(page); - goto find_page; - } - ret = -EIO; - goto out; - } - } else - SetPageUptodate(page); - } + ret = add_to_page_cache_lru(page, mapping, index, + GFP_KERNEL); + if (unlikely(ret)) + goto out; } ret = mapping->a_ops->prepare_write(file, page, offset, offset+this_len); @@ -682,18 +627,25 @@ find_page: } ret = mapping->a_ops->commit_write(file, page, offset, offset+this_len); - if (!ret) { + if (ret) { + if (ret == AOP_TRUNCATED_PAGE) { + page_cache_release(page); + goto find_page; + } + if (ret < 0) + goto out; /* - * Return the number of bytes written and mark page as - * accessed, we are now done! + * Partial write has happened, so 'ret' already initialized by + * number of bytes written, Where is nothing we have to do here. */ + } else ret = this_len; - mark_page_accessed(page); - balance_dirty_pages_ratelimited(mapping); - } else if (ret == AOP_TRUNCATED_PAGE) { - page_cache_release(page); - goto find_page; - } + /* + * Return the number of bytes written and mark page as + * accessed, we are now done! + */ + mark_page_accessed(page); + balance_dirty_pages_ratelimited(mapping); out: page_cache_release(page); unlock_page(page); @@ -706,9 +658,9 @@ out_ret: * key here is the 'actor' worker passed in that actually moves the data * to the wanted destination. See pipe_to_file/pipe_to_sendpage above. */ -static ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, - struct file *out, loff_t *ppos, size_t len, - unsigned int flags, splice_actor *actor) +ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, + struct file *out, loff_t *ppos, size_t len, + unsigned int flags, splice_actor *actor) { int ret, do_wakeup, err; struct splice_desc sd; @@ -802,6 +754,7 @@ static ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, return ret; } +EXPORT_SYMBOL(__splice_from_pipe); ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags, diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 8d4d839a9d88..fc4633378dc0 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 ccb7d722c558..4de5c6b89918 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 bcc44084e004..841ac25fd950 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 b868878009b6..c28a8b6f2feb 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 fb34ad03e224..013d7afe7cde 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 749581fa7729..79c54c85fb58 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 e2bea6a661f0..69e9e80735d2 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; |
