diff options
Diffstat (limited to 'fs')
-rw-r--r-- | fs/afs/internal.h | 2 | ||||
-rw-r--r-- | fs/binfmt_flat.c | 2 | ||||
-rw-r--r-- | fs/compat.c | 17 | ||||
-rw-r--r-- | fs/compat_ioctl.c | 33 | ||||
-rw-r--r-- | fs/ecryptfs/file.c | 59 | ||||
-rw-r--r-- | fs/ecryptfs/mmap.c | 38 | ||||
-rw-r--r-- | fs/exec.c | 3 | ||||
-rw-r--r-- | fs/ext4/balloc.c | 6 | ||||
-rw-r--r-- | fs/ext4/extents.c | 148 | ||||
-rw-r--r-- | fs/ext4/inode.c | 4 | ||||
-rw-r--r-- | fs/ext4/namei.c | 4 | ||||
-rw-r--r-- | fs/ext4/super.c | 2 | ||||
-rw-r--r-- | fs/fuse/dir.c | 2 | ||||
-rw-r--r-- | fs/fuse/file.c | 4 | ||||
-rw-r--r-- | fs/fuse/inode.c | 1 | ||||
-rw-r--r-- | fs/ioctl.c | 14 | ||||
-rw-r--r-- | fs/jffs2/readinode.c | 22 | ||||
-rw-r--r-- | fs/jffs2/super.c | 194 | ||||
-rw-r--r-- | fs/jffs2/xattr.c | 6 | ||||
-rw-r--r-- | fs/nfs/direct.c | 65 | ||||
-rw-r--r-- | fs/nfs/pagelist.c | 20 | ||||
-rw-r--r-- | fs/nfs/write.c | 6 | ||||
-rw-r--r-- | fs/ntfs/inode.c | 2 | ||||
-rw-r--r-- | fs/ocfs2/aops.c | 31 | ||||
-rw-r--r-- | fs/ocfs2/cluster/masklog.c | 3 | ||||
-rw-r--r-- | fs/ocfs2/file.c | 33 | ||||
-rw-r--r-- | fs/ocfs2/localalloc.c | 7 | ||||
-rw-r--r-- | fs/ramfs/file-nommu.c | 7 | ||||
-rw-r--r-- | fs/reiserfs/dir.c | 2 | ||||
-rw-r--r-- | fs/signalfd.c | 120 | ||||
-rw-r--r-- | fs/splice.c | 70 | ||||
-rw-r--r-- | fs/udf/inode.c | 12 | ||||
-rw-r--r-- | fs/udf/super.c | 2 | ||||
-rw-r--r-- | fs/xfs/linux-2.6/xfs_aops.c | 26 |
34 files changed, 475 insertions, 492 deletions
diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 2dac3ad..2c55dd9 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -17,6 +17,8 @@ #include <linux/rxrpc.h> #include <linux/key.h> #include <linux/workqueue.h> +#include <linux/sched.h> + #include "afs.h" #include "afs_vl.h" diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 7b0265d..861141b 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -558,7 +558,7 @@ static int load_flat_file(struct linux_binprm * bprm, if (!realdatastart) realdatastart = (unsigned long) -ENOMEM; printk("Unable to allocate RAM for process data, errno %d\n", - (int)-datapos); + (int)-realdatastart); do_munmap(current->mm, textpos, text_len); ret = realdatastart; goto err; diff --git a/fs/compat.c b/fs/compat.c index 1de2331..4db6216 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1544,9 +1544,10 @@ int compat_core_sys_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, s64 *timeout) { fd_set_bits fds; - char *bits; + void *bits; int size, max_fds, ret = -EINVAL; struct fdtable *fdt; + long stack_fds[SELECT_STACK_ALLOC/sizeof(long)]; if (n < 0) goto out_nofds; @@ -1564,11 +1565,14 @@ int compat_core_sys_select(int n, compat_ulong_t __user *inp, * since we used fdset we need to allocate memory in units of * long-words. */ - ret = -ENOMEM; size = FDS_BYTES(n); - bits = kmalloc(6 * size, GFP_KERNEL); - if (!bits) - goto out_nofds; + bits = stack_fds; + if (size > sizeof(stack_fds) / 6) { + bits = kmalloc(6 * size, GFP_KERNEL); + ret = -ENOMEM; + if (!bits) + goto out_nofds; + } fds.in = (unsigned long *) bits; fds.out = (unsigned long *) (bits + size); fds.ex = (unsigned long *) (bits + 2*size); @@ -1600,7 +1604,8 @@ int compat_core_sys_select(int n, compat_ulong_t __user *inp, compat_set_fd_set(n, exp, fds.res_ex)) ret = -EFAULT; out: - kfree(bits); + if (bits != stack_fds) + kfree(bits); out_nofds: return ret; } diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 65643de..6b44cdc 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -1194,6 +1194,7 @@ static int vt_check(struct file *file) { struct tty_struct *tty; struct inode *inode = file->f_path.dentry->d_inode; + struct vc_data *vc; if (file->f_op->ioctl != tty_ioctl) return -EINVAL; @@ -1204,12 +1205,16 @@ static int vt_check(struct file *file) if (tty->driver->ioctl != vt_ioctl) return -EINVAL; - + + vc = (struct vc_data *)tty->driver_data; + if (!vc_cons_allocated(vc->vc_num)) /* impossible? */ + return -ENOIOCTLCMD; + /* * To have permissions to do most of the vt ioctls, we either have - * to be the owner of the tty, or super-user. + * to be the owner of the tty, or have CAP_SYS_TTY_CONFIG. */ - if (current->signal->tty == tty || capable(CAP_SYS_ADMIN)) + if (current->signal->tty == tty || capable(CAP_SYS_TTY_CONFIG)) return 1; return 0; } @@ -1310,16 +1315,28 @@ static int do_unimap_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg, struct unimapdesc32 tmp; struct unimapdesc32 __user *user_ud = compat_ptr(arg); int perm = vt_check(file); - - if (perm < 0) return perm; + struct vc_data *vc; + + if (perm < 0) + return perm; if (copy_from_user(&tmp, user_ud, sizeof tmp)) return -EFAULT; + if (tmp.entries) + if (!access_ok(VERIFY_WRITE, compat_ptr(tmp.entries), + tmp.entry_ct*sizeof(struct unipair))) + return -EFAULT; + vc = ((struct tty_struct *)file->private_data)->driver_data; switch (cmd) { case PIO_UNIMAP: - if (!perm) return -EPERM; - return con_set_unimap(vc_cons[fg_console].d, tmp.entry_ct, compat_ptr(tmp.entries)); + if (!perm) + return -EPERM; + return con_set_unimap(vc, tmp.entry_ct, + compat_ptr(tmp.entries)); case GIO_UNIMAP: - return con_get_unimap(vc_cons[fg_console].d, tmp.entry_ct, &(user_ud->entry_ct), compat_ptr(tmp.entries)); + if (!perm && fg_console != vc->vc_num) + return -EPERM; + return con_get_unimap(vc, tmp.entry_ct, &(user_ud->entry_ct), + compat_ptr(tmp.entries)); } return 0; } diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index 9881b5c..59288d8 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -33,63 +33,6 @@ #include "ecryptfs_kernel.h" /** - * ecryptfs_llseek - * @file: File we are seeking in - * @offset: The offset to seek to - * @origin: 2 - offset from i_size; 1 - offset from f_pos - * - * Returns the position we have seeked to, or negative on error - */ -static loff_t ecryptfs_llseek(struct file *file, loff_t offset, int origin) -{ - loff_t rv; - loff_t new_end_pos; - int rc; - int expanding_file = 0; - struct inode *inode = file->f_mapping->host; - - /* If our offset is past the end of our file, we're going to - * need to grow it so we have a valid length of 0's */ - new_end_pos = offset; - switch (origin) { - case 2: - new_end_pos += i_size_read(inode); - expanding_file = 1; - break; - case 1: - new_end_pos += file->f_pos; - if (new_end_pos > i_size_read(inode)) { - ecryptfs_printk(KERN_DEBUG, "new_end_pos(=[0x%.16x]) " - "> i_size_read(inode)(=[0x%.16x])\n", - new_end_pos, i_size_read(inode)); - expanding_file = 1; - } - break; - default: - if (new_end_pos > i_size_read(inode)) { - ecryptfs_printk(KERN_DEBUG, "new_end_pos(=[0x%.16x]) " - "> i_size_read(inode)(=[0x%.16x])\n", - new_end_pos, i_size_read(inode)); - expanding_file = 1; - } - } - ecryptfs_printk(KERN_DEBUG, "new_end_pos = [0x%.16x]\n", new_end_pos); - if (expanding_file) { - rc = ecryptfs_truncate(file->f_path.dentry, new_end_pos); - if (rc) { - rv = rc; - ecryptfs_printk(KERN_ERR, "Error on attempt to " - "truncate to (higher) offset [0x%.16x];" - " rc = [%d]\n", new_end_pos, rc); - goto out; - } - } - rv = generic_file_llseek(file, offset, origin); -out: - return rv; -} - -/** * ecryptfs_read_update_atime * * generic_file_read updates the atime of upper layer inode. But, it @@ -425,7 +368,7 @@ const struct file_operations ecryptfs_dir_fops = { }; const struct file_operations ecryptfs_main_fops = { - .llseek = ecryptfs_llseek, + .llseek = generic_file_llseek, .read = do_sync_read, .aio_read = ecryptfs_read_update_atime, .write = do_sync_write, diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c index 88ea669..55cec98 100644 --- a/fs/ecryptfs/mmap.c +++ b/fs/ecryptfs/mmap.c @@ -376,9 +376,31 @@ out: return 0; } +/** + * eCryptfs does not currently support holes. When writing after a + * seek past the end of the file, eCryptfs fills in 0's through to the + * current location. The code to fill in the 0's to all the + * intermediate pages calls ecryptfs_prepare_write_no_truncate(). + */ +static int +ecryptfs_prepare_write_no_truncate(struct file *file, struct page *page, + unsigned from, unsigned to) +{ + int rc = 0; + + if (from == 0 && to == PAGE_CACHE_SIZE) + goto out; /* If we are writing a full page, it will be + up to date. */ + if (!PageUptodate(page)) + rc = ecryptfs_do_readpage(file, page, page->index); +out: + return rc; +} + static int ecryptfs_prepare_write(struct file *file, struct page *page, unsigned from, unsigned to) { + loff_t pos; int rc = 0; if (from == 0 && to == PAGE_CACHE_SIZE) @@ -386,6 +408,16 @@ static int ecryptfs_prepare_write(struct file *file, struct page *page, up to date. */ if (!PageUptodate(page)) rc = ecryptfs_do_readpage(file, page, page->index); + pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to; + if (pos > i_size_read(page->mapping->host)) { + rc = ecryptfs_truncate(file->f_path.dentry, pos); + if (rc) { + printk(KERN_ERR "Error on attempt to " + "truncate to (higher) offset [%lld];" + " rc = [%d]\n", pos, rc); + goto out; + } + } out: return rc; } @@ -744,10 +776,10 @@ int write_zeros(struct file *file, pgoff_t index, int start, int num_zeros) rc = PTR_ERR(tmp_page); goto out; } - rc = ecryptfs_prepare_write(file, tmp_page, start, start + num_zeros); - if (rc) { + if ((rc = ecryptfs_prepare_write_no_truncate(file, tmp_page, start, + (start + num_zeros)))) { ecryptfs_printk(KERN_ERR, "Error preparing to write zero's " - "to remainder of page at index [0x%.16x]\n", + "to page at index [0x%.16x]\n", index); page_cache_release(tmp_page); goto out; @@ -134,6 +134,9 @@ asmlinkage long sys_uselib(const char __user * library) if (error) goto out; + error = -EACCES; + if (nd.mnt->mnt_flags & MNT_NOEXEC) + goto exit; error = -EINVAL; if (!S_ISREG(nd.dentry->d_inode->i_mode)) goto exit; diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 8a23483..3b64bb1 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -30,15 +30,15 @@ void ext4_get_group_no_and_offset(struct super_block *sb, ext4_fsblk_t blocknr, unsigned long *blockgrpp, ext4_grpblk_t *offsetp) { - struct ext4_super_block *es = EXT4_SB(sb)->s_es; + struct ext4_super_block *es = EXT4_SB(sb)->s_es; ext4_grpblk_t offset; - blocknr = blocknr - le32_to_cpu(es->s_first_data_block); + blocknr = blocknr - le32_to_cpu(es->s_first_data_block); offset = do_div(blocknr, EXT4_BLOCKS_PER_GROUP(sb)); if (offsetp) *offsetp = offset; if (blockgrpp) - *blockgrpp = blocknr; + *blockgrpp = blocknr; } diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index a0f0c04..b9ce241 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -374,7 +374,7 @@ ext4_ext_binsearch_idx(struct inode *inode, struct ext4_ext_path *path, int bloc le32_to_cpu(ix[-1].ei_block)); } BUG_ON(k && le32_to_cpu(ix->ei_block) - <= le32_to_cpu(ix[-1].ei_block)); + <= le32_to_cpu(ix[-1].ei_block)); if (block < le32_to_cpu(ix->ei_block)) break; chix = ix; @@ -423,8 +423,8 @@ ext4_ext_binsearch(struct inode *inode, struct ext4_ext_path *path, int block) path->p_ext = l - 1; ext_debug(" -> %d:%llu:%d ", - le32_to_cpu(path->p_ext->ee_block), - ext_pblock(path->p_ext), + le32_to_cpu(path->p_ext->ee_block), + ext_pblock(path->p_ext), le16_to_cpu(path->p_ext->ee_len)); #ifdef CHECK_BINSEARCH @@ -435,7 +435,7 @@ ext4_ext_binsearch(struct inode *inode, struct ext4_ext_path *path, int block) chex = ex = EXT_FIRST_EXTENT(eh); for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ex++) { BUG_ON(k && le32_to_cpu(ex->ee_block) - <= le32_to_cpu(ex[-1].ee_block)); + <= le32_to_cpu(ex[-1].ee_block)); if (block < le32_to_cpu(ex->ee_block)) break; chex = ex; @@ -577,7 +577,7 @@ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, curp->p_hdr->eh_entries = cpu_to_le16(le16_to_cpu(curp->p_hdr->eh_entries)+1); BUG_ON(le16_to_cpu(curp->p_hdr->eh_entries) - > le16_to_cpu(curp->p_hdr->eh_max)); + > le16_to_cpu(curp->p_hdr->eh_max)); BUG_ON(ix > EXT_LAST_INDEX(curp->p_hdr)); err = ext4_ext_dirty(handle, inode, curp); @@ -621,12 +621,12 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, border = path[depth].p_ext[1].ee_block; ext_debug("leaf will be split." " next leaf starts at %d\n", - le32_to_cpu(border)); + le32_to_cpu(border)); } else { border = newext->ee_block; ext_debug("leaf will be added." " next leaf starts at %d\n", - le32_to_cpu(border)); + le32_to_cpu(border)); } /* @@ -684,9 +684,9 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, while (path[depth].p_ext <= EXT_MAX_EXTENT(path[depth].p_hdr)) { ext_debug("move %d:%llu:%d in new leaf %llu\n", - le32_to_cpu(path[depth].p_ext->ee_block), - ext_pblock(path[depth].p_ext), - le16_to_cpu(path[depth].p_ext->ee_len), + le32_to_cpu(path[depth].p_ext->ee_block), + ext_pblock(path[depth].p_ext), + le16_to_cpu(path[depth].p_ext->ee_len), newblock); /*memmove(ex++, path[depth].p_ext++, sizeof(struct ext4_extent)); @@ -765,9 +765,9 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, EXT_LAST_INDEX(path[i].p_hdr)); while (path[i].p_idx <= EXT_MAX_INDEX(path[i].p_hdr)) { ext_debug("%d: move %d:%d in new index %llu\n", i, - le32_to_cpu(path[i].p_idx->ei_block), - idx_pblock(path[i].p_idx), - newblock); + le32_to_cpu(path[i].p_idx->ei_block), + idx_pblock(path[i].p_idx), + newblock); /*memmove(++fidx, path[i].p_idx++, sizeof(struct ext4_extent_idx)); neh->eh_entries++; @@ -1128,6 +1128,55 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1, } /* + * check if a portion of the "newext" extent overlaps with an + * existing extent. + * + * If there is an overlap discovered, it updates the length of the newext + * such that there will be no overlap, and then returns 1. + * If there is no overlap found, it returns 0. + */ +unsigned int ext4_ext_check_overlap(struct inode *inode, + struct ext4_extent *newext, + struct ext4_ext_path *path) +{ + unsigned long b1, b2; + unsigned int depth, len1; + unsigned int ret = 0; + + b1 = le32_to_cpu(newext->ee_block); + len1 = le16_to_cpu(newext->ee_len); + depth = ext_depth(inode); + if (!path[depth].p_ext) + goto out; + b2 = le32_to_cpu(path[depth].p_ext->ee_block); + + /* + * get the next allocated block if the extent in the path + * is before the requested block(s) + */ + if (b2 < b1) { + b2 = ext4_ext_next_allocated_block(path); + if (b2 == EXT_MAX_BLOCK) + goto out; + } + + /* check for wrap through zero */ + if (b1 + len1 < b1) { + len1 = EXT_MAX_BLOCK - b1; + newext->ee_len = cpu_to_le16(len1); + ret = 1; + } + + /* check for overlap */ + if (b1 + len1 > b2) { + newext->ee_len = cpu_to_le16(b2 - b1); + ret = 1; + } +out: + return ret; +} + +/* * ext4_ext_insert_extent: * tries to merge requsted extent into the existing extent or * inserts requested extent as new one into the tree, @@ -1212,12 +1261,12 @@ has_space: if (!nearex) { /* there is no extent in this leaf, create first one */ ext_debug("first extent in the leaf: %d:%llu:%d\n", - le32_to_cpu(newext->ee_block), - ext_pblock(newext), - le16_to_cpu(newext->ee_len)); + le32_to_cpu(newext->ee_block), + ext_pblock(newext), + le16_to_cpu(newext->ee_len)); path[depth].p_ext = EXT_FIRST_EXTENT(eh); } else if (le32_to_cpu(newext->ee_block) - > le32_to_cpu(nearex->ee_block)) { + > le32_to_cpu(nearex->ee_block)) { /* BUG_ON(newext->ee_block == nearex->ee_block); */ if (nearex != EXT_LAST_EXTENT(eh)) { len = EXT_MAX_EXTENT(eh) - nearex; @@ -1225,9 +1274,9 @@ has_space: len = len < 0 ? 0 : len; ext_debug("insert %d:%llu:%d after: nearest 0x%p, " "move %d from 0x%p to 0x%p\n", - le32_to_cpu(newext->ee_block), - ext_pblock(newext), - le16_to_cpu(newext->ee_len), + le32_to_cpu(newext->ee_block), + ext_pblock(newext), + le16_to_cpu(newext->ee_len), nearex, len, nearex + 1, nearex + 2); memmove(nearex + 2, nearex + 1, len); } @@ -1358,9 +1407,9 @@ int ext4_ext_walk_space(struct inode *inode, unsigned long block, cbex.ec_start = 0; cbex.ec_type = EXT4_EXT_CACHE_GAP; } else { - cbex.ec_block = le32_to_cpu(ex->ee_block); - cbex.ec_len = le16_to_cpu(ex->ee_len); - cbex.ec_start = ext_pblock(ex); + cbex.ec_block = le32_to_cpu(ex->ee_block); + cbex.ec_len = le16_to_cpu(ex->ee_len); + cbex.ec_start = ext_pblock(ex); cbex.ec_type = EXT4_EXT_CACHE_EXTENT; } @@ -1431,16 +1480,16 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path, len = le32_to_cpu(ex->ee_block) - block; ext_debug("cache gap(before): %lu [%lu:%lu]", (unsigned long) block, - (unsigned long) le32_to_cpu(ex->ee_block), - (unsigned long) le16_to_cpu(ex->ee_len)); + (unsigned long) le32_to_cpu(ex->ee_block), + (unsigned long) le16_to_cpu(ex->ee_len)); } else if (block >= le32_to_cpu(ex->ee_block) - + le16_to_cpu(ex->ee_len)) { - lblock = le32_to_cpu(ex->ee_block) - + le16_to_cpu(ex->ee_len); + + le16_to_cpu(ex->ee_len)) { + lblock = le32_to_cpu(ex->ee_block) + + le16_to_cpu(ex->ee_len); len = ext4_ext_next_allocated_block(path); ext_debug("cache gap(after): [%lu:%lu] %lu", - (unsigned long) le32_to_cpu(ex->ee_block), - (unsigned long) le16_to_cpu(ex->ee_len), + (unsigned long) le32_to_cpu(ex->ee_block), + (unsigned long) le16_to_cpu(ex->ee_len), (unsigned long) block); BUG_ON(len == lblock); len = len - lblock; @@ -1468,9 +1517,9 @@ ext4_ext_in_cache(struct inode *inode, unsigned long block, BUG_ON(cex->ec_type != EXT4_EXT_CACHE_GAP && cex->ec_type != EXT4_EXT_CACHE_EXTENT); if (block >= cex->ec_block && block < cex->ec_block + cex->ec_len) { - ex->ee_block = cpu_to_le32(cex->ec_block); + ex->ee_block = cpu_to_le32(cex->ec_block); ext4_ext_store_pblock(ex, cex->ec_start); - ex->ee_len = cpu_to_le16(cex->ec_len); + ex->ee_len = cpu_to_le16(cex->ec_len); ext_debug("%lu cached by %lu:%lu:%llu\n", (unsigned long) block, (unsigned long) cex->ec_block, @@ -1956,9 +2005,9 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, /* we should allocate requested block */ } else if (goal == EXT4_EXT_CACHE_EXTENT) { /* block is already allocated */ - newblock = iblock - - le32_to_cpu(newex.ee_block) - + ext_pblock(&newex); + newblock = iblock + - le32_to_cpu(newex.ee_block) + + ext_pblock(&newex); /* number of remaining blocks in the extent */ allocated = le16_to_cpu(newex.ee_len) - (iblock - le32_to_cpu(newex.ee_block)); @@ -1987,7 +2036,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, ex = path[depth].p_ext; if (ex) { - unsigned long ee_block = le32_to_cpu(ex->ee_block); + unsigned long ee_block = le32_to_cpu(ex->ee_block); ext4_fsblk_t ee_start = ext_pblock(ex); unsigned short ee_len = le16_to_cpu(ex->ee_len); @@ -2000,7 +2049,7 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, if (ee_len > EXT_MAX_LEN) goto out2; /* if found extent covers block, simply return it */ - if (iblock >= ee_block && iblock < ee_block + ee_len) { + if (iblock >= ee_block && iblock < ee_block + ee_len) { newblock = iblock - ee_block + ee_start; /* number of remaining blocks in the extent */ allocated = ee_len - (iblock - ee_block); @@ -2031,7 +2080,15 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, /* allocate new block */ goal = ext4_ext_find_goal(inode, path, iblock); - allocated = max_blocks; + + /* Check if we can really insert (iblock)::(iblock+max_blocks) extent */ + newex.ee_block = cpu_to_le32(iblock); + newex.ee_len = cpu_to_le16(max_blocks); + err = ext4_ext_check_overlap(inode, &newex, path); + if (err) + allocated = le16_to_cpu(newex.ee_len); + else + allocated = max_blocks; newblock = ext4_new_blocks(handle, inode, goal, &allocated, &err); if (!newblock) goto out2; @@ -2039,12 +2096,15 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode, goal, newblock, allocated); /* try to insert new extent into found leaf and return */ - newex.ee_block = cpu_to_le32(iblock); ext4_ext_store_pblock(&newex, newblock); newex.ee_len = cpu_to_le16(allocated); err = ext4_ext_insert_extent(handle, inode, path, &newex); - if (err) + if (err) { + /* free data blocks we just allocated */ + ext4_free_blocks(handle, inode, ext_pblock(&newex), + le16_to_cpu(newex.ee_len)); goto out2; + } if (extend_disksize && inode->i_size > EXT4_I(inode)->i_disksize) EXT4_I(inode)->i_disksize = inode->i_size; @@ -2157,11 +2217,3 @@ int ext4_ext_writepage_trans_blocks(struct inode *inode, int num) return needed; } - -EXPORT_SYMBOL(ext4_mark_inode_dirty); -EXPORT_SYMBOL(ext4_ext_invalidate_cache); -EXPORT_SYMBOL(ext4_ext_insert_extent); -EXPORT_SYMBOL(ext4_ext_walk_space); -EXPORT_SYMBOL(ext4_ext_find_goal); -EXPORT_SYMBOL(ext4_ext_calc_credits_for_insert); - diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index b34182b..0bcf62a 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -255,8 +255,8 @@ static int verify_chain(Indirect *from, Indirect *to) * @inode: inode in question (we are only interested in its superblock) * @i_block: block number to be parsed * @offsets: array to store the offsets in - * @boundary: set this non-zero if the referred-to block is likely to be - * followed (on disk) by an indirect block. + * @boundary: set this non-zero if the referred-to block is likely to be + * followed (on disk) by an indirect block. * * To store the locations of file's data ext4 uses a data structure common * for UNIX filesystems - tree of pointers anchored in the inode, with diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 4ec57be..2811e57 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -46,7 +46,7 @@ */ #define NAMEI_RA_CHUNKS 2 #define NAMEI_RA_BLOCKS 4 -#define NAMEI_RA_SIZE (NAMEI_RA_CHUNKS * NAMEI_RA_BLOCKS) +#define NAMEI_RA_SIZE (NAMEI_RA_CHUNKS * NAMEI_RA_BLOCKS) #define NAMEI_RA_INDEX(c,b) (((c) * NAMEI_RA_BLOCKS) + (b)) static struct buffer_head *ext4_append(handle_t *handle, @@ -241,7 +241,7 @@ static inline unsigned dx_node_limit (struct inode *dir) static void dx_show_index (char * label, struct dx_entry *entries) { int i, n = dx_get_count (entries); - printk("%s index ", label); + printk("%s index ", label); for (i = 0; i < n; i++) { printk("%x->%u ", i? dx_get_hash(entries + i) : 0, dx_get_block(entries + i)); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index cb9afdd..175b68c 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1985,7 +1985,7 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, if (bd_claim(bdev, sb)) { printk(KERN_ERR - "EXT4: failed to claim external journal device.\n"); + "EXT4: failed to claim external journal device.\n"); blkdev_put(bdev); return NULL; } diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 8890eba..bd5a772 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -485,7 +485,7 @@ static int fuse_mknod(struct inode *dir, struct dentry *entry, int mode, static int fuse_create(struct inode *dir, struct dentry *entry, int mode, struct nameidata *nd) { - if (nd && (nd->flags & LOOKUP_CREATE)) { + if (nd && (nd->flags & LOOKUP_OPEN)) { int err = fuse_create_open(dir, entry, mode, nd); if (err != -ENOSYS) return err; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index d0ed60b..adf7995 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -610,7 +610,9 @@ static ssize_t fuse_direct_write(struct file *file, const char __user *buf, ssize_t res; /* Don't allow parallel writes to the same file */ mutex_lock(&inode->i_mutex); - res = fuse_direct_io(file, buf, count, ppos, 1); + res = generic_write_checks(file, ppos, &count, 0); + if (!res) + res = fuse_direct_io(file, buf, count, ppos, 1); mutex_unlock(&inode->i_mutex); return res; } diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 78f7a1d..9804c0c 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -454,6 +454,7 @@ static const struct super_operations fuse_super_operations = { .destroy_inode = fuse_destroy_inode, .read_inode = fuse_read_inode, .clear_inode = fuse_clear_inode, + .drop_inode = generic_delete_inode, .remount_fs = fuse_remount_fs, .put_super = fuse_put_super, .umount_begin = fuse_umount_begin, @@ -12,6 +12,7 @@ #include <linux/fs.h> #include <linux/security.h> #include <linux/module.h> +#include <linux/kallsyms.h> #include <asm/uaccess.h> #include <asm/ioctls.h> @@ -20,6 +21,7 @@ static long do_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { int error = -ENOTTY; + void *f; if (!filp->f_op) goto out; @@ -29,10 +31,16 @@ static long do_ioctl(struct file *filp, unsigned int cmd, if (error == -ENOIOCTLCMD) error = -EINVAL; goto out; - } else if (filp->f_op->ioctl) { + } else if ((f = filp->f_op->ioctl)) { lock_kernel(); - error = filp->f_op->ioctl(filp->f_path.dentry->d_inode, - filp, cmd, arg); + if (!filp->f_op->ioctl) { + printk("%s: ioctl %p disappeared\n", __FUNCTION__, f); + print_symbol("symbol: %s\n", (unsigned long)f); + dump_stack(); + } else { + error = filp->f_op->ioctl(filp->f_path.dentry->d_inode, + filp, cmd, arg); + } unlock_kernel(); } diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c index 4884d5e..12e83f6 100644 --- a/fs/jffs2/readinode.c +++ b/fs/jffs2/readinode.c @@ -229,9 +229,16 @@ static int jffs2_add_tn_to_tree(struct jffs2_sb_info *c, check anyway. */ if (!tn->fn->size) { if (rii->mdata_tn) { - /* We had a candidate mdata node already */ - dbg_readinode("kill old mdata with ver %d\n", rii->mdata_tn->version); - jffs2_kill_tn(c, rii->mdata_tn); + if (rii->mdata_tn->version < tn->version) { + /* We had a candidate mdata node already */ + dbg_readinode("kill old mdata with ver %d\n", rii->mdata_tn->version); + jffs2_kill_tn(c, rii->mdata_tn); + } else { + dbg_readinode("kill new mdata with ver %d (older than existing %d\n", + tn->version, rii->mdata_tn->version); + jffs2_kill_tn(c, tn); + return 0; + } } rii->mdata_tn = tn; dbg_readinode("keep new mdata with ver %d\n", tn->version); @@ -1044,7 +1051,8 @@ static int jffs2_get_inode_nodes(struct jffs2_sb_info *c, struct jffs2_inode_inf case JFFS2_NODETYPE_DIRENT: - if (JFFS2_MIN_NODE_HEADER < sizeof(struct jffs2_raw_dirent)) { + if (JFFS2_MIN_NODE_HEADER < sizeof(struct jffs2_raw_dirent) && + len < sizeof(struct jffs2_raw_dirent)) { err = read_more(c, ref, sizeof(struct jffs2_raw_dirent), &len, buf); if (unlikely(err)) goto free_out; @@ -1058,7 +1066,8 @@ static int jffs2_get_inode_nodes(struct jffs2_sb_info *c, struct jffs2_inode_inf case JFFS2_NODETYPE_INODE: - if (JFFS2_MIN_NODE_HEADER < sizeof(struct jffs2_raw_inode)) { + if (JFFS2_MIN_NODE_HEADER < sizeof(struct jffs2_raw_inode) && + len < sizeof(struct jffs2_raw_inode)) { err = read_more(c, ref, sizeof(struct jffs2_raw_inode), &len, buf); if (unlikely(err)) goto free_out; @@ -1071,7 +1080,8 @@ static int jffs2_get_inode_nodes(struct jffs2_sb_info *c, struct jffs2_inode_inf break; default: - if (JFFS2_MIN_NODE_HEADER < sizeof(struct jffs2_unknown_node)) { + if (JFFS2_MIN_NODE_HEADER < sizeof(struct jffs2_unknown_node) && + len < sizeof(struct jffs2_unknown_node)) { err = read_more(c, ref, sizeof(struct jffs2_unknown_node), &len, buf); if (unlikely(err)) goto free_out; diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index 6488af4..e220d3b 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -19,7 +19,7 @@ #include <linux/mount.h> #include <linux/jffs2.h> #include <linux/pagemap.h> -#include <linux/mtd/mtd.h> +#include <linux/mtd/super.h> #include <linux/ctype.h> #include <linux/namei.h> #include "compr.h" @@ -75,69 +75,27 @@ static const struct super_operations jffs2_super_operations = .sync_fs = jffs2_sync_fs, }; -static int jffs2_sb_compare(struct super_block *sb, void *data) -{ - struct jffs2_sb_info *p = data; - struct jffs2_sb_info *c = JFFS2_SB_INFO(sb); - - /* The superblocks are considered to be equivalent if the underlying MTD - device is the same one */ - if (c->mtd == p->mtd) { - D1(printk(KERN_DEBUG "jffs2_sb_compare: match on device %d (\"%s\")\n", p->mtd->index, p->mtd->name)); - return 1; - } else { - D1(printk(KERN_DEBUG "jffs2_sb_compare: No match, device %d (\"%s\"), device %d (\"%s\")\n", - c->mtd->index, c->mtd->name, p->mtd->index, p->mtd->name)); - return 0; - } -} - -static int jffs2_sb_set(struct super_block *sb, void *data) -{ - struct jffs2_sb_info *p = data; - - /* For persistence of NFS exports etc. we use the same s_dev - each time we mount the device, don't just use an anonymous - device */ - sb->s_fs_info = p; - p->os_priv = sb; - sb->s_dev = MKDEV(MTD_BLOCK_MAJOR, p->mtd->index); - - return 0; -} - -static int jffs2_get_sb_mtd(struct file_system_type *fs_type, - int flags, const char *dev_name, - void *data, struct mtd_info *mtd, - struct vfsmount *mnt) +/* + * fill in the superblock + */ +static int jffs2_fill_super(struct super_block *sb, void *data, int silent) { - struct super_block *sb; struct jffs2_sb_info *c; - int ret; + + D1(printk(KERN_DEBUG "jffs2_get_sb_mtd():" + " New superblock for device %d (\"%s\")\n", + sb->s_mtd->index, sb->s_mtd->name)); c = kzalloc(sizeof(*c), GFP_KERNEL); if (!c) return -ENOMEM; - c->mtd = mtd; - - sb = sget(fs_type, jffs2_sb_compare, jffs2_sb_set, c); - - if (IS_ERR(sb)) - goto out_error; - - if (sb->s_root) { - /* New mountpoint for JFFS2 which is already mounted */ - D1(printk(KERN_DEBUG "jffs2_get_sb_mtd(): Device %d (\"%s\") is already mounted\n", - mtd->index, mtd->name)); - ret = simple_set_mnt(mnt, sb); - goto out_put; - } - D1(printk(KERN_DEBUG "jffs2_get_sb_mtd(): New superblock for device %d (\"%s\")\n", - mtd->index, mtd->name)); + c->mtd = sb->s_mtd; + c->os_priv = sb; + sb->s_fs_info = c; - /* Initialize JFFS2 superblock locks, the further initialization will be - * done later */ + /* Initialize JFFS2 superblock locks, the further initialization will + * be done later */ init_MUTEX(&c->alloc_sem); init_MUTEX(&c->erase_free_sem); init_waitqueue_head(&c->erase_wait); @@ -146,133 +104,20 @@ static int jffs2_get_sb_mtd(struct file_system_type *fs_type, spin_lock_init(&c->inocache_lock); sb->s_op = &jffs2_super_operations; - sb->s_flags = flags | MS_NOATIME; + sb->s_flags = sb->s_flags | MS_NOATIME; sb->s_xattr = jffs2_xattr_handlers; #ifdef CONFIG_JFFS2_FS_POSIX_ACL sb->s_flags |= MS_POSIXACL; #endif - ret = jffs2_do_fill_super(sb, data, flags & MS_SILENT ? 1 : 0); - - if (ret) { - /* Failure case... */ - up_write(&sb->s_umount); - deactivate_super(sb); - return ret; - } - - sb->s_flags |= MS_ACTIVE; - return simple_set_mnt(mnt, sb); - -out_error: - ret = PTR_ERR(sb); - out_put: - kfree(c); - put_mtd_device(mtd); - - return ret; -} - -static int jffs2_get_sb_mtdnr(struct file_system_type *fs_type, - int flags, const char *dev_name, - void *data, int mtdnr, - struct vfsmount *mnt) -{ - struct mtd_info *mtd; - - mtd = get_mtd_device(NULL, mtdnr); - if (IS_ERR(mtd)) { - D1(printk(KERN_DEBUG "jffs2: MTD device #%u doesn't appear to exist\n", mtdnr)); - return PTR_ERR(mtd); - } - - return jffs2_get_sb_mtd(fs_type, flags, dev_name, data, mtd, mnt); + return jffs2_do_fill_super(sb, data, silent); } static int jffs2_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, struct vfsmount *mnt) { - int err; - struct nameidata nd; - int mtdnr; - - if (!dev_name) - return -EINVAL; - - D1(printk(KERN_DEBUG "jffs2_get_sb(): dev_name \"%s\"\n", dev_name)); - - /* The preferred way of mounting in future; especially when - CONFIG_BLK_DEV is implemented - we specify the underlying - MTD device by number or by name, so that we don't require - block device support to be present in the kernel. */ - - /* FIXME: How to do the root fs this way? */ - - if (dev_name[0] == 'm' && dev_name[1] == 't' && dev_name[2] == 'd') { - /* Probably mounting without the blkdev crap */ - if (dev_name[3] == ':') { - struct mtd_info *mtd; - - /* Mount by MTD device name */ - D1(printk(KERN_DEBUG "jffs2_get_sb(): mtd:%%s, name \"%s\"\n", dev_name+4)); - for (mtdnr = 0; mtdnr < MAX_MTD_DEVICES; mtdnr++) { - mtd = get_mtd_device(NULL, mtdnr); - if (!IS_ERR(mtd)) { - if (!strcmp(mtd->name, dev_name+4)) - return jffs2_get_sb_mtd(fs_type, flags, dev_name, data, mtd, mnt); - put_mtd_device(mtd); - } - } - printk(KERN_NOTICE "jffs2_get_sb(): MTD device with name \"%s\" not found.\n", dev_name+4); - } else if (isdigit(dev_name[3])) { - /* Mount by MTD device number name */ - char *endptr; - - mtdnr = simple_strtoul(dev_name+3, &endptr, 0); - if (!*endptr) { - /* It was a valid number */ - D1(printk(KERN_DEBUG "jffs2_get_sb(): mtd%%d, mtdnr %d\n", mtdnr)); - return jffs2_get_sb_mtdnr(fs_type, flags, dev_name, data, mtdnr, mnt); - } - } - } - - /* Try the old way - the hack where we allowed users to mount - /dev/mtdblock$(n) but didn't actually _use_ the blkdev */ - - err = path_lookup(dev_name, LOOKUP_FOLLOW, &nd); - - D1(printk(KERN_DEBUG "jffs2_get_sb(): path_lookup() returned %d, inode %p\n", - err, nd.dentry->d_inode)); - - if (err) - return err; - - err = -EINVAL; - - if (!S_ISBLK(nd.dentry->d_inode->i_mode)) - goto out; - - if (nd.mnt->mnt_flags & MNT_NODEV) { - err = -EACCES; - goto out; - } - - if (imajor(nd.dentry->d_inode) != MTD_BLOCK_MAJOR) { - if (!(flags & MS_SILENT)) - printk(KERN_NOTICE "Attempt to mount non-MTD device \"%s\" as JFFS2\n", - dev_name); - goto out; - } - - mtdnr = iminor(nd.dentry->d_inode); - path_release(&nd); - - return jffs2_get_sb_mtdnr(fs_type, flags, dev_name, data, mtdnr, mnt); - -out: - path_release(&nd); - return err; + return get_sb_mtd(fs_type, flags, dev_name, data, jffs2_fill_super, + mnt); } static void jffs2_put_super (struct super_block *sb) @@ -307,8 +152,7 @@ static void jffs2_kill_sb(struct super_block *sb) struct jffs2_sb_info *c = JFFS2_SB_INFO(sb); if (!(sb->s_flags & MS_RDONLY)) jffs2_stop_garbage_collect_thread(c); - generic_shutdown_super(sb); - put_mtd_device(c->mtd); + kill_mtd_super(sb); kfree(c); } diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c index 78fc088..e486659 100644 --- a/fs/jffs2/xattr.c +++ b/fs/jffs2/xattr.c @@ -754,6 +754,10 @@ void jffs2_clear_xattr_subsystem(struct jffs2_sb_info *c) list_del(&xd->xindex); jffs2_free_xattr_datum(xd); } + list_for_each_entry_safe(xd, _xd, &c->xattr_unchecked, xindex) { + list_del(&xd->xindex); + jffs2_free_xattr_datum(xd); + } } #define XREF_TMPHASH_SIZE (128) @@ -825,7 +829,7 @@ void jffs2_build_xattr_subsystem(struct jffs2_sb_info *c) ref->xd and ref->ic are not valid yet. */ xd = jffs2_find_xattr_datum(c, ref->xid); ic = jffs2_get_ino_cache(c, ref->ino); - if (!xd || !ic) { + if (!xd || !ic || !ic->nlink) { dbg_xattr("xref(ino=%u, xid=%u, xseqno=%u) is orphan.\n", ref->ino, ref->xid, ref->xseqno); ref->xseqno |= XREF_DELETE_MARKER; diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 345aa5c..00eee87 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -122,19 +122,25 @@ ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_ return -EINVAL; } -static void nfs_direct_dirty_pages(struct page **pages, int npages) +static void nfs_direct_dirty_pages(struct page **pages, unsigned int pgbase, size_t count) { - int i; + unsigned int npages; + unsigned int i; + + if (count == 0) + return; + pages += (pgbase >> PAGE_SHIFT); + npages = (count + (pgbase & ~PAGE_MASK) + PAGE_SIZE - 1) >> PAGE_SHIFT; for (i = 0; i < npages; i++) { struct page *page = pages[i]; if (!PageCompound(page)) - set_page_dirty_lock(page); + set_page_dirty(page); } } -static void nfs_direct_release_pages(struct page **pages, int npages) +static void nfs_direct_release_pages(struct page **pages, unsigned int npages) { - int i; + unsigned int i; for (i = 0; i < npages; i++) page_cache_release(pages[i]); } @@ -162,7 +168,7 @@ static inline struct nfs_direct_req *nfs_direct_req_alloc(void) return dreq; } -static void nfs_direct_req_release(struct kref *kref) +static void nfs_direct_req_free(struct kref *kref) { struct nfs_direct_req *dreq = container_of(kref, struct nfs_direct_req, kref); @@ -171,6 +177,11 @@ static void nfs_direct_req_release(struct kref *kref) kmem_cache_free(nfs_direct_cachep, dreq); } +static void nfs_direct_req_release(struct nfs_direct_req *dreq) +{ + kref_put(&dreq->kref, nfs_direct_req_free); +} + /* * Collects and returns the final error value/byte-count. */ @@ -190,7 +201,6 @@ static ssize_t nfs_direct_wait(struct nfs_direct_req *dreq) result = dreq->count; out: - kref_put(&dreq->kref, nfs_direct_req_release); return (ssize_t) result; } @@ -208,7 +218,7 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq) } complete_all(&dreq->completion); - kref_put(&dreq->kref, nfs_direct_req_release); + nfs_direct_req_release(dreq); } /* @@ -224,17 +234,18 @@ static void nfs_direct_read_result(struct rpc_task *task, void *calldata) if (nfs_readpage_result(task, data) != 0) return; - nfs_direct_dirty_pages(data->pagevec, data->npages); - nfs_direct_release_pages(data->pagevec, data->npages); - spin_lock(&dreq->lock); - - if (likely(task->tk_status >= 0)) - dreq->count += data->res.count; - else + if (unlikely(task->tk_status < 0)) { dreq->error = task->tk_status; - - spin_unlock(&dreq->lock); + spin_unlock(&dreq->lock); + } else { + dreq->count += data->res.count; + spin_unlock(&dreq->lock); + nfs_direct_dirty_pages(data->pagevec, + data->args.pgbase, + data->res.count); + } + nfs_direct_release_pages(data->pagevec, data->npages); if (put_dreq(dreq)) nfs_direct_complete(dreq); @@ -279,9 +290,12 @@ static ssize_t nfs_direct_read_schedule(struct nfs_direct_req *dreq, unsigned lo result = get_user_pages(current, current->mm, user_addr, data->npages, 1, 0, data->pagevec, NULL); up_read(¤t->mm->mmap_sem); - if (unlikely(result < data->npages)) { - if (result > 0) - nfs_direct_release_pages(data->pagevec, result); + if (result < 0) { + nfs_readdata_release(data); + break; + } + if ((unsigned)result < data->npages) { + nfs_direct_release_pages(data->pagevec, result); nfs_readdata_release(data); break; } @@ -359,6 +373,7 @@ static ssize_t nfs_direct_read(struct kiocb *iocb, unsigned long user_addr, size if (!result) result = nfs_direct_wait(dreq); rpc_clnt_sigunmask(clnt, &oldset); + nfs_direct_req_release(dreq); return result; } @@ -610,9 +625,12 @@ static ssize_t nfs_direct_write_schedule(struct nfs_direct_req *dreq, unsigned l result = get_user_pages(current, current->mm, user_addr, data->npages, 0, 0, data->pagevec, NULL); up_read(¤t->mm->mmap_sem); - if (unlikely(result < data->npages)) { - if (result > 0) - nfs_direct_release_pages(data->pagevec, result); + if (result < 0) { + nfs_writedata_release(data); + break; + } + if ((unsigned)result < data->npages) { + nfs_direct_release_pages(data->pagevec, result); nfs_writedata_release(data); break; } @@ -703,6 +721,7 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, unsigned long user_addr, siz if (!result) result = nfs_direct_wait(dreq); rpc_clnt_sigunmask(clnt, &oldset); + nfs_direct_req_release(dreq); return result; } diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index cbdd1c6..c5bb51a 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -355,6 +355,26 @@ void nfs_pageio_complete(struct nfs_pageio_descriptor *desc) nfs_pageio_doio(desc); } +/** + * nfs_pageio_cond_complete - Conditional I/O completion + * @desc: pointer to io descriptor + * @index: page index + * + * It is important to ensure that processes don't try to take locks + * on non-contiguous ranges of pages as that might deadlock. This + * function should be called before attempting to wait on a locked + * nfs_page. It will complete the I/O if the page index 'index' + * is not contiguous with the existing list of pages in 'desc'. + */ +void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *desc, pgoff_t index) +{ + if (!list_empty(&desc->pg_list)) { + struct nfs_page *prev = nfs_list_entry(desc->pg_list.prev); + if (index != prev->wb_index + 1) + nfs_pageio_doio(desc); + } +} + #define NFS_SCAN_MAXENTRIES 16 /** * nfs_scan_list - Scan a list for matching requests diff --git a/fs/nfs/write.c b/fs/nfs/write.c index b084c03..af344a1 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -273,8 +273,6 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, * request as dirty (in which case we don't care). */ spin_unlock(req_lock); - /* Prevent deadlock! */ - nfs_pageio_complete(pgio); ret = nfs_wait_on_request(req); nfs_release_request(req); if (ret != 0) @@ -321,6 +319,8 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc pgio = &mypgio; } + nfs_pageio_cond_complete(pgio, page->index); + err = nfs_page_async_flush(pgio, page); if (err <= 0) goto out; @@ -329,6 +329,8 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc if (!offset) goto out; + nfs_pageio_cond_complete(pgio, page->index); + ctx = nfs_find_open_context(inode, NULL, FMODE_WRITE); if (ctx == NULL) { err = -EBADF; diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index 074791c..b532a73 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -140,7 +140,7 @@ static int ntfs_init_locked_inode(struct inode *vi, ntfs_attr *na) if (!ni->name) return -ENOMEM; memcpy(ni->name, na->name, i); - ni->name[i] = 0; + ni->name[na->name_len] = 0; } return 0; } diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 8e7cafb..a480b09 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -222,7 +222,10 @@ static int ocfs2_readpage(struct file *file, struct page *page) goto out; } - down_read(&OCFS2_I(inode)->ip_alloc_sem); + if (down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem) == 0) { + ret = AOP_TRUNCATED_PAGE; + goto out_meta_unlock; + } /* * i_size might have just been updated as we grabed the meta lock. We @@ -235,10 +238,7 @@ static int ocfs2_readpage(struct file *file, struct page *page) * XXX sys_readahead() seems to get that wrong? */ if (start >= i_size_read(inode)) { - char *addr = kmap(page); - memset(addr, 0, PAGE_SIZE); - flush_dcache_page(page); - kunmap(page); + zero_user_page(page, 0, PAGE_SIZE, KM_USER0); SetPageUptodate(page); ret = 0; goto out_alloc; @@ -258,6 +258,7 @@ static int ocfs2_readpage(struct file *file, struct page *page) ocfs2_data_unlock(inode, 0); out_alloc: up_read(&OCFS2_I(inode)->ip_alloc_sem); +out_meta_unlock: ocfs2_meta_unlock(inode, 0); out: if (unlock) @@ -797,6 +798,11 @@ int ocfs2_map_and_write_splice_data(struct inode *inode, } to = from + bytes; + BUG_ON(from > PAGE_CACHE_SIZE); + BUG_ON(to > PAGE_CACHE_SIZE); + BUG_ON(from < cluster_start); + BUG_ON(to > cluster_end); + if (wc->w_this_page_new) ret = ocfs2_map_page_blocks(wc->w_this_page, p_blkno, inode, cluster_start, cluster_end, 1); @@ -808,11 +814,6 @@ int ocfs2_map_and_write_splice_data(struct inode *inode, goto out; } - BUG_ON(from > PAGE_CACHE_SIZE); - BUG_ON(to > PAGE_CACHE_SIZE); - BUG_ON(from > osb->s_clustersize); - BUG_ON(to > osb->s_clustersize); - src = buf->ops->map(sp->s_pipe, buf, 1); dst = kmap_atomic(wc->w_this_page, KM_USER1); memcpy(dst + from, src + src_from, bytes); @@ -889,6 +890,11 @@ int ocfs2_map_and_write_user_data(struct inode *inode, to = from + bytes; + BUG_ON(from > PAGE_CACHE_SIZE); + BUG_ON(to > PAGE_CACHE_SIZE); + BUG_ON(from < cluster_start); + BUG_ON(to > cluster_end); + if (wc->w_this_page_new) ret = ocfs2_map_page_blocks(wc->w_this_page, p_blkno, inode, cluster_start, cluster_end, 1); @@ -900,11 +906,6 @@ int ocfs2_map_and_write_user_data(struct inode *inode, goto out; } - BUG_ON(from > PAGE_CACHE_SIZE); - BUG_ON(to > PAGE_CACHE_SIZE); - BUG_ON(from > osb->s_clustersize); - BUG_ON(to > osb->s_clustersize); - dst = kmap(wc->w_this_page); memcpy(dst + from, bp->b_src_buf + src_from, bytes); kunmap(wc->w_this_page); diff --git a/fs/ocfs2/cluster/masklog.c b/fs/ocfs2/cluster/masklog.c index a93620c..2b205f5 100644 --- a/fs/ocfs2/cluster/masklog.c +++ b/fs/ocfs2/cluster/masklog.c @@ -144,8 +144,7 @@ static struct kobj_type mlog_ktype = { }; static struct kset mlog_kset = { - .kobj = {.name = "logmask"}, - .ktype = &mlog_ktype + .kobj = {.name = "logmask", .ktype = &mlog_ktype}, }; int mlog_sys_init(struct kset *o2cb_subsys) diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 9395b4f..ac6c964 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -326,6 +326,7 @@ static int ocfs2_truncate_file(struct inode *inode, (unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)new_i_size); + unmap_mapping_range(inode->i_mapping, new_i_size + PAGE_SIZE - 1, 0, 1); truncate_inode_pages(inode->i_mapping, new_i_size); fe = (struct ocfs2_dinode *) di_bh->b_data; @@ -1418,36 +1419,6 @@ out: return total ? total : ret; } -static int ocfs2_check_iovec(const struct iovec *iov, size_t *counted, - unsigned long *nr_segs) -{ - size_t ocount; /* original count */ - unsigned long seg; - - ocount = 0; - for (seg = 0; seg < *nr_segs; seg++) { - const struct iovec *iv = &iov[seg]; - - /* - * If any segment has a negative length, or the cumulative - * length ever wraps negative then return -EINVAL. - */ - ocount += iv->iov_len; - if (unlikely((ssize_t)(ocount|iv->iov_len) < 0)) - return -EINVAL; - if (access_ok(VERIFY_READ, iv->iov_base, iv->iov_len)) - continue; - if (seg == 0) - return -EFAULT; - *nr_segs = seg; - ocount -= iv->iov_len; /* This segment is no good */ - break; - } - - *counted = ocount; - return 0; -} - static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, @@ -1470,7 +1441,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, if (iocb->ki_left == 0) return 0; - ret = ocfs2_check_iovec(iov, &ocount, &nr_segs); + ret = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ); if (ret) return ret; diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index 4dedd97..545f789 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -471,9 +471,6 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb, mutex_lock(&local_alloc_inode->i_mutex); - ac->ac_inode = local_alloc_inode; - ac->ac_which = OCFS2_AC_USE_LOCAL; - if (osb->local_alloc_state != OCFS2_LA_ENABLED) { status = -ENOSPC; goto bail; @@ -511,10 +508,14 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb, } } + ac->ac_inode = local_alloc_inode; + ac->ac_which = OCFS2_AC_USE_LOCAL; get_bh(osb->local_alloc_bh); ac->ac_bh = osb->local_alloc_bh; status = 0; bail: + if (status < 0 && local_alloc_inode) + iput(local_alloc_inode); mlog_exit(status); return status; diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index 3b481d5..5d258c4 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -179,7 +179,7 @@ static int ramfs_nommu_resize(struct inode *inode, loff_t newsize, loff_t size) return ret; } - ret = vmtruncate(inode, size); + ret = vmtruncate(inode, newsize); return ret; } @@ -195,6 +195,11 @@ static int ramfs_nommu_setattr(struct dentry *dentry, struct iattr *ia) unsigned int old_ia_valid = ia->ia_valid; int ret = 0; + /* POSIX UID/GID verification for setting inode attributes */ + ret = inode_change_ok(inode, ia); + if (ret) + return ret; + /* by providing our own setattr() method, we skip this quotaism */ if ((old_ia_valid & ATTR_UID && ia->ia_uid != inode->i_uid) || (old_ia_valid & ATTR_GID && ia->ia_gid != inode->i_gid)) diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c index 9c23fee..ffbfc2c 100644 --- a/fs/reiserfs/dir.c +++ b/fs/reiserfs/dir.c @@ -10,7 +10,7 @@ #include <linux/buffer_head.h> #include <asm/uaccess.h> -extern struct reiserfs_key MIN_KEY; +extern const struct reiserfs_key MIN_KEY; static int reiserfs_readdir(struct file *, void *, filldir_t); static int reiserfs_dir_fsync(struct file *filp, struct dentry *dentry, diff --git a/fs/signalfd.c b/fs/signalfd.c index 7cfeab4..f1da892 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -11,6 +11,8 @@ * Now using anonymous inode source. * Thanks to Oleg Nesterov for useful code review and suggestions. * More comments and suggestions from Arnd Bergmann. + * Sat May 19, 2007: Davi E. M. Arnaut <davi@haxent.com.br> + * Retrieve multiple signals with one read() call */ #include <linux/file.h> @@ -206,6 +208,59 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, return err ? -EFAULT: sizeof(*uinfo); } +static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, siginfo_t *info, + int nonblock) +{ + ssize_t ret; + struct signalfd_lockctx lk; + DECLARE_WAITQUEUE(wait, current); + + if (!signalfd_lock(ctx, &lk)) + return 0; + + ret = dequeue_signal(lk.tsk, &ctx->sigmask, info); + switch (ret) { + case 0: + if (!nonblock) + break; + ret = -EAGAIN; + default: + signalfd_unlock(&lk); + return ret; + } + + add_wait_queue(&ctx->wqh, &wait); + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); + ret = dequeue_signal(lk.tsk, &ctx->sigmask, info); + signalfd_unlock(&lk); + if (ret != 0) + break; + if (signal_pending(current)) { + ret = -ERESTARTSYS; + break; + } + schedule(); + ret = signalfd_lock(ctx, &lk); + if (unlikely(!ret)) { + /* + * Let the caller read zero byte, ala socket + * recv() when the peer disconnect. This test + * must be done before doing a dequeue_signal(), + * because if the sighand has been orphaned, + * the dequeue_signal() call is going to crash + * because ->sighand will be long gone. + */ + break; + } + } + + remove_wait_queue(&ctx->wqh, &wait); + __set_current_state(TASK_RUNNING); + + return ret; +} + /* * Returns either the size of a "struct signalfd_siginfo", or zero if the * sighand we are attached to, has been orphaned. The "count" parameter @@ -215,55 +270,30 @@ static ssize_t signalfd_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct signalfd_ctx *ctx = file->private_data; - ssize_t res = 0; - int locked, signo; + struct signalfd_siginfo __user *siginfo; + int nonblock = file->f_flags & O_NONBLOCK; + ssize_t ret, total = 0; siginfo_t info; - struct signalfd_lockctx lk; - DECLARE_WAITQUEUE(wait, current); - if (count < sizeof(struct signalfd_siginfo)) + count /= sizeof(struct signalfd_siginfo); + if (!count) return -EINVAL; - locked = signalfd_lock(ctx, &lk); - if (!locked) - return 0; - res = -EAGAIN; - signo = dequeue_signal(lk.tsk, &ctx->sigmask, &info); - if (signo == 0 && !(file->f_flags & O_NONBLOCK)) { - add_wait_queue(&ctx->wqh, &wait); - for (;;) { - set_current_state(TASK_INTERRUPTIBLE); - signo = dequeue_signal(lk.tsk, &ctx->sigmask, &info); - if (signo != 0) - break; - if (signal_pending(current)) { - res = -ERESTARTSYS; - break; - } - signalfd_unlock(&lk); - schedule(); - locked = signalfd_lock(ctx, &lk); - if (unlikely(!locked)) { - /* - * Let the caller read zero byte, ala socket - * recv() when the peer disconnect. This test - * must be done before doing a dequeue_signal(), - * because if the sighand has been orphaned, - * the dequeue_signal() call is going to crash. - */ - res = 0; - break; - } - } - remove_wait_queue(&ctx->wqh, &wait); - __set_current_state(TASK_RUNNING); - } - if (likely(locked)) - signalfd_unlock(&lk); - if (likely(signo)) - res = signalfd_copyinfo((struct signalfd_siginfo __user *) buf, - &info); - return res; + siginfo = (struct signalfd_siginfo __user *) buf; + + do { + ret = signalfd_dequeue(ctx, &info, nonblock); + if (unlikely(ret <= 0)) + break; + ret = signalfd_copyinfo(siginfo, &info); + if (ret < 0) + break; + siginfo++; + total += ret; + nonblock = 1; + } while (--count); + + return total ? total : ret; } static const struct file_operations signalfd_fops = { diff --git a/fs/splice.c b/fs/splice.c index 12f2828..cb21136 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -272,7 +272,6 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, struct page *page; pgoff_t index, end_index; loff_t isize; - size_t total_len; int error, page_nr; struct splice_pipe_desc spd = { .pages = pages, @@ -298,7 +297,6 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, * Now fill in the holes: */ error = 0; - total_len = 0; /* * Lookup the (hopefully) full range of pages we need. @@ -415,43 +413,47 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, break; } + } +fill_it: + /* + * i_size must be checked after PageUptodate. + */ + isize = i_size_read(mapping->host); + end_index = (isize - 1) >> PAGE_CACHE_SHIFT; + if (unlikely(!isize || index > end_index)) + break; + + /* + * if this is the last page, see if we need to shrink + * the length and stop + */ + if (end_index == index) { + unsigned int plen; /* - * i_size must be checked after ->readpage(). + * max good bytes in this page */ - isize = i_size_read(mapping->host); - end_index = (isize - 1) >> PAGE_CACHE_SHIFT; - if (unlikely(!isize || index > end_index)) + plen = ((isize - 1) & ~PAGE_CACHE_MASK) + 1; + if (plen <= loff) break; /* - * if this is the last page, see if we need to shrink - * the length and stop + * force quit after adding this page */ - if (end_index == index) { - loff = PAGE_CACHE_SIZE - (isize & ~PAGE_CACHE_MASK); - if (total_len + loff > isize) - break; - /* - * force quit after adding this page - */ - len = this_len; - this_len = min(this_len, loff); - loff = 0; - } + this_len = min(this_len, plen - loff); + len = this_len; } -fill_it: + partial[page_nr].offset = loff; partial[page_nr].len = this_len; len -= this_len; - total_len += this_len; loff = 0; spd.nr_pages++; index++; } /* - * Release any pages at the end, if we quit early. 'i' is how far + * Release any pages at the end, if we quit early. 'page_nr' is how far * we got, 'nr_pages' is how many pages are in the map. */ while (page_nr < nr_pages) @@ -478,10 +480,18 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos, { ssize_t spliced; int ret; + loff_t isize, left; + + isize = i_size_read(in->f_mapping->host); + if (unlikely(*ppos >= isize)) + return 0; + + left = isize - *ppos; + if (unlikely(left < len)) + len = left; ret = 0; spliced = 0; - while (len) { ret = __generic_file_splice_read(in, ppos, pipe, len, flags); @@ -644,7 +654,6 @@ find_page: * accessed, we are now done! */ mark_page_accessed(page); - balance_dirty_pages_ratelimited(mapping); out: page_cache_release(page); unlock_page(page); @@ -815,6 +824,7 @@ generic_file_splice_write_nolock(struct pipe_inode_info *pipe, struct file *out, if (err) ret = err; } + balance_dirty_pages_ratelimited(mapping); } return ret; @@ -868,6 +878,7 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out, if (err) ret = err; } + balance_dirty_pages_ratelimited(mapping); } return ret; @@ -922,7 +933,6 @@ static long do_splice_to(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { - loff_t isize, left; int ret; if (unlikely(!in->f_op || !in->f_op->splice_read)) @@ -935,14 +945,6 @@ static long do_splice_to(struct file *in, loff_t *ppos, if (unlikely(ret < 0)) return ret; - isize = i_size_read(in->f_mapping->host); - if (unlikely(*ppos >= isize)) - return 0; - - left = isize - *ppos; - if (unlikely(left < len)) - len = left; - return in->f_op->splice_read(in, ppos, pipe, len, flags); } @@ -1058,8 +1060,6 @@ out_release: return ret; } -EXPORT_SYMBOL(do_splice_direct); - /* * After the inode slimming patch, i_pipe/i_bdev/i_cdev share the same * location, so checking ->i_pipe is not enough to verify that this is a diff --git a/fs/udf/inode.c b/fs/udf/inode.c index c846155..1f01294 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -460,8 +460,8 @@ static struct buffer_head * inode_getblk(struct inode * inode, sector_t block, kernel_long_ad laarr[EXTENT_MERGE_SIZE]; struct extent_position prev_epos, cur_epos, next_epos; int count = 0, startnum = 0, endnum = 0; - uint32_t elen = 0; - kernel_lb_addr eloc; + uint32_t elen = 0, tmpelen; + kernel_lb_addr eloc, tmpeloc; int c = 1; loff_t lbcount = 0, b_off = 0; uint32_t newblocknum, newblock; @@ -520,8 +520,12 @@ static struct buffer_head * inode_getblk(struct inode * inode, sector_t block, b_off -= lbcount; offset = b_off >> inode->i_sb->s_blocksize_bits; - /* Move into indirect extent if we are at a pointer to it */ - udf_next_aext(inode, &prev_epos, &eloc, &elen, 0); + /* + * Move prev_epos and cur_epos into indirect extent if we are at + * the pointer to it + */ + udf_next_aext(inode, &prev_epos, &tmpeloc, &tmpelen, 0); + udf_next_aext(inode, &cur_epos, &tmpeloc, &tmpelen, 0); /* if the extent is allocated and recorded, return the block if the extent is not a multiple of the blocksize, round up */ diff --git a/fs/udf/super.c b/fs/udf/super.c index 3a743d8..6658afb 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -1351,7 +1351,7 @@ udf_load_partition(struct super_block *sb, kernel_lb_addr *fileset) for (i=0; i<UDF_SB_NUMPARTS(sb); i++) { - switch UDF_SB_PARTTYPE(sb, i) + switch (UDF_SB_PARTTYPE(sb, i)) { case UDF_VIRTUAL_MAP15: case UDF_VIRTUAL_MAP20: diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c index 4475588..7361861 100644 --- a/fs/xfs/linux-2.6/xfs_aops.c +++ b/fs/xfs/linux-2.6/xfs_aops.c @@ -701,7 +701,7 @@ xfs_is_delayed_page( else if (buffer_delay(bh)) acceptable = (type == IOMAP_DELAY); else if (buffer_dirty(bh) && buffer_mapped(bh)) - acceptable = (type == 0); + acceptable = (type == IOMAP_NEW); else break; } while ((bh = bh->b_this_page) != head); @@ -810,7 +810,7 @@ xfs_convert_page( page_dirty--; count++; } else { - type = 0; + type = IOMAP_NEW; if (buffer_mapped(bh) && all_bh && startio) { lock_buffer(bh); xfs_add_to_ioend(inode, bh, offset, @@ -968,8 +968,8 @@ xfs_page_state_convert( bh = head = page_buffers(page); offset = page_offset(page); - flags = -1; - type = IOMAP_READ; + flags = BMAPI_READ; + type = IOMAP_NEW; /* TODO: cleanup count and page_dirty */ @@ -999,14 +999,14 @@ xfs_page_state_convert( * * Third case, an unmapped buffer was found, and we are * in a path where we need to write the whole page out. - */ + */ if (buffer_unwritten(bh) || buffer_delay(bh) || ((buffer_uptodate(bh) || PageUptodate(page)) && !buffer_mapped(bh) && (unmapped || startio))) { - /* + /* * Make sure we don't use a read-only iomap */ - if (flags == BMAPI_READ) + if (flags == BMAPI_READ) iomap_valid = 0; if (buffer_unwritten(bh)) { @@ -1055,7 +1055,7 @@ xfs_page_state_convert( * That means it must already have extents allocated * underneath it. Map the extent by reading it. */ - if (!iomap_valid || type != IOMAP_READ) { + if (!iomap_valid || flags != BMAPI_READ) { flags = BMAPI_READ; size = xfs_probe_cluster(inode, page, bh, head, 1); @@ -1066,7 +1066,15 @@ xfs_page_state_convert( iomap_valid = xfs_iomap_valid(&iomap, offset); } - type = IOMAP_READ; + /* + * We set the type to IOMAP_NEW in case we are doing a + * small write at EOF that is extending the file but + * without needing an allocation. We need to update the + * file size on I/O completion in this case so it is + * the same case as having just allocated a new extent + * that we are writing into for the first time. + */ + type = IOMAP_NEW; if (!test_and_set_bit(BH_Lock, &bh->b_state)) { ASSERT(buffer_mapped(bh)); if (iomap_valid) |