From 57f0f512b273f60d52568b8c6b77e17f5636edc0 Mon Sep 17 00:00:00 2001 From: André Fabian Silva Delgado Date: Wed, 5 Aug 2015 17:04:01 -0300 Subject: Initial import --- fs/ext2/Kconfig | 44 ++ fs/ext2/Makefile | 12 + fs/ext2/acl.c | 257 ++++++++ fs/ext2/acl.h | 71 +++ fs/ext2/balloc.c | 1536 ++++++++++++++++++++++++++++++++++++++++++++ fs/ext2/dir.c | 730 +++++++++++++++++++++ fs/ext2/ext2.h | 820 ++++++++++++++++++++++++ fs/ext2/file.c | 121 ++++ fs/ext2/ialloc.c | 675 ++++++++++++++++++++ fs/ext2/inode.c | 1573 +++++++++++++++++++++++++++++++++++++++++++++ fs/ext2/ioctl.c | 188 ++++++ fs/ext2/namei.c | 431 +++++++++++++ fs/ext2/super.c | 1580 ++++++++++++++++++++++++++++++++++++++++++++++ fs/ext2/symlink.c | 54 ++ fs/ext2/xattr.c | 1029 ++++++++++++++++++++++++++++++ fs/ext2/xattr.h | 125 ++++ fs/ext2/xattr_security.c | 74 +++ fs/ext2/xattr_trusted.c | 54 ++ fs/ext2/xattr_user.c | 61 ++ 19 files changed, 9435 insertions(+) create mode 100644 fs/ext2/Kconfig create mode 100644 fs/ext2/Makefile create mode 100644 fs/ext2/acl.c create mode 100644 fs/ext2/acl.h create mode 100644 fs/ext2/balloc.c create mode 100644 fs/ext2/dir.c create mode 100644 fs/ext2/ext2.h create mode 100644 fs/ext2/file.c create mode 100644 fs/ext2/ialloc.c create mode 100644 fs/ext2/inode.c create mode 100644 fs/ext2/ioctl.c create mode 100644 fs/ext2/namei.c create mode 100644 fs/ext2/super.c create mode 100644 fs/ext2/symlink.c create mode 100644 fs/ext2/xattr.c create mode 100644 fs/ext2/xattr.h create mode 100644 fs/ext2/xattr_security.c create mode 100644 fs/ext2/xattr_trusted.c create mode 100644 fs/ext2/xattr_user.c (limited to 'fs/ext2') diff --git a/fs/ext2/Kconfig b/fs/ext2/Kconfig new file mode 100644 index 000000000..c634874e1 --- /dev/null +++ b/fs/ext2/Kconfig @@ -0,0 +1,44 @@ +config EXT2_FS + tristate "Second extended fs support" + help + Ext2 is a standard Linux file system for hard disks. + + To compile this file system support as a module, choose M here: the + module will be called ext2. + + If unsure, say Y. + +config EXT2_FS_XATTR + bool "Ext2 extended attributes" + depends on EXT2_FS + help + Extended attributes are name:value pairs associated with inodes by + the kernel or by users (see the attr(5) manual page, or visit + for details). + + If unsure, say N. + +config EXT2_FS_POSIX_ACL + bool "Ext2 POSIX Access Control Lists" + depends on EXT2_FS_XATTR + select FS_POSIX_ACL + help + Posix Access Control Lists (ACLs) support permissions for users and + groups beyond the owner/group/world scheme. + + To learn more about Access Control Lists, visit the Posix ACLs for + Linux website . + + If you don't know what Access Control Lists are, say N + +config EXT2_FS_SECURITY + bool "Ext2 Security Labels" + depends on EXT2_FS_XATTR + help + Security labels support alternative access control models + implemented by security modules like SELinux. This option + enables an extended attribute handler for file security + labels in the ext2 filesystem. + + If you are not using a security module that requires using + extended attributes for file security labels, say N. diff --git a/fs/ext2/Makefile b/fs/ext2/Makefile new file mode 100644 index 000000000..445b0e996 --- /dev/null +++ b/fs/ext2/Makefile @@ -0,0 +1,12 @@ +# +# Makefile for the linux ext2-filesystem routines. +# + +obj-$(CONFIG_EXT2_FS) += ext2.o + +ext2-y := balloc.o dir.o file.o ialloc.o inode.o \ + ioctl.o namei.o super.o symlink.o + +ext2-$(CONFIG_EXT2_FS_XATTR) += xattr.o xattr_user.o xattr_trusted.o +ext2-$(CONFIG_EXT2_FS_POSIX_ACL) += acl.o +ext2-$(CONFIG_EXT2_FS_SECURITY) += xattr_security.o diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c new file mode 100644 index 000000000..27695e6f4 --- /dev/null +++ b/fs/ext2/acl.c @@ -0,0 +1,257 @@ +/* + * linux/fs/ext2/acl.c + * + * Copyright (C) 2001-2003 Andreas Gruenbacher, + */ + +#include +#include +#include +#include +#include "ext2.h" +#include "xattr.h" +#include "acl.h" + +/* + * Convert from filesystem to in-memory representation. + */ +static struct posix_acl * +ext2_acl_from_disk(const void *value, size_t size) +{ + const char *end = (char *)value + size; + int n, count; + struct posix_acl *acl; + + if (!value) + return NULL; + if (size < sizeof(ext2_acl_header)) + return ERR_PTR(-EINVAL); + if (((ext2_acl_header *)value)->a_version != + cpu_to_le32(EXT2_ACL_VERSION)) + return ERR_PTR(-EINVAL); + value = (char *)value + sizeof(ext2_acl_header); + count = ext2_acl_count(size); + if (count < 0) + return ERR_PTR(-EINVAL); + if (count == 0) + return NULL; + acl = posix_acl_alloc(count, GFP_KERNEL); + if (!acl) + return ERR_PTR(-ENOMEM); + for (n=0; n < count; n++) { + ext2_acl_entry *entry = + (ext2_acl_entry *)value; + if ((char *)value + sizeof(ext2_acl_entry_short) > end) + goto fail; + acl->a_entries[n].e_tag = le16_to_cpu(entry->e_tag); + acl->a_entries[n].e_perm = le16_to_cpu(entry->e_perm); + switch(acl->a_entries[n].e_tag) { + case ACL_USER_OBJ: + case ACL_GROUP_OBJ: + case ACL_MASK: + case ACL_OTHER: + value = (char *)value + + sizeof(ext2_acl_entry_short); + break; + + case ACL_USER: + value = (char *)value + sizeof(ext2_acl_entry); + if ((char *)value > end) + goto fail; + acl->a_entries[n].e_uid = + make_kuid(&init_user_ns, + le32_to_cpu(entry->e_id)); + break; + case ACL_GROUP: + value = (char *)value + sizeof(ext2_acl_entry); + if ((char *)value > end) + goto fail; + acl->a_entries[n].e_gid = + make_kgid(&init_user_ns, + le32_to_cpu(entry->e_id)); + break; + + default: + goto fail; + } + } + if (value != end) + goto fail; + return acl; + +fail: + posix_acl_release(acl); + return ERR_PTR(-EINVAL); +} + +/* + * Convert from in-memory to filesystem representation. + */ +static void * +ext2_acl_to_disk(const struct posix_acl *acl, size_t *size) +{ + ext2_acl_header *ext_acl; + char *e; + size_t n; + + *size = ext2_acl_size(acl->a_count); + ext_acl = kmalloc(sizeof(ext2_acl_header) + acl->a_count * + sizeof(ext2_acl_entry), GFP_KERNEL); + if (!ext_acl) + return ERR_PTR(-ENOMEM); + ext_acl->a_version = cpu_to_le32(EXT2_ACL_VERSION); + e = (char *)ext_acl + sizeof(ext2_acl_header); + for (n=0; n < acl->a_count; n++) { + const struct posix_acl_entry *acl_e = &acl->a_entries[n]; + ext2_acl_entry *entry = (ext2_acl_entry *)e; + entry->e_tag = cpu_to_le16(acl_e->e_tag); + entry->e_perm = cpu_to_le16(acl_e->e_perm); + switch(acl_e->e_tag) { + case ACL_USER: + entry->e_id = cpu_to_le32( + from_kuid(&init_user_ns, acl_e->e_uid)); + e += sizeof(ext2_acl_entry); + break; + case ACL_GROUP: + entry->e_id = cpu_to_le32( + from_kgid(&init_user_ns, acl_e->e_gid)); + e += sizeof(ext2_acl_entry); + break; + + case ACL_USER_OBJ: + case ACL_GROUP_OBJ: + case ACL_MASK: + case ACL_OTHER: + e += sizeof(ext2_acl_entry_short); + break; + + default: + goto fail; + } + } + return (char *)ext_acl; + +fail: + kfree(ext_acl); + return ERR_PTR(-EINVAL); +} + +/* + * inode->i_mutex: don't care + */ +struct posix_acl * +ext2_get_acl(struct inode *inode, int type) +{ + int name_index; + char *value = NULL; + struct posix_acl *acl; + int retval; + + switch (type) { + case ACL_TYPE_ACCESS: + name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS; + break; + case ACL_TYPE_DEFAULT: + name_index = EXT2_XATTR_INDEX_POSIX_ACL_DEFAULT; + break; + default: + BUG(); + } + retval = ext2_xattr_get(inode, name_index, "", NULL, 0); + if (retval > 0) { + value = kmalloc(retval, GFP_KERNEL); + if (!value) + return ERR_PTR(-ENOMEM); + retval = ext2_xattr_get(inode, name_index, "", value, retval); + } + if (retval > 0) + acl = ext2_acl_from_disk(value, retval); + else if (retval == -ENODATA || retval == -ENOSYS) + acl = NULL; + else + acl = ERR_PTR(retval); + kfree(value); + + if (!IS_ERR(acl)) + set_cached_acl(inode, type, acl); + + return acl; +} + +/* + * inode->i_mutex: down + */ +int +ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type) +{ + int name_index; + void *value = NULL; + size_t size = 0; + int error; + + switch(type) { + case ACL_TYPE_ACCESS: + name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS; + if (acl) { + error = posix_acl_equiv_mode(acl, &inode->i_mode); + if (error < 0) + return error; + else { + inode->i_ctime = CURRENT_TIME_SEC; + mark_inode_dirty(inode); + if (error == 0) + acl = NULL; + } + } + break; + + case ACL_TYPE_DEFAULT: + name_index = EXT2_XATTR_INDEX_POSIX_ACL_DEFAULT; + if (!S_ISDIR(inode->i_mode)) + return acl ? -EACCES : 0; + break; + + default: + return -EINVAL; + } + if (acl) { + value = ext2_acl_to_disk(acl, &size); + if (IS_ERR(value)) + return (int)PTR_ERR(value); + } + + error = ext2_xattr_set(inode, name_index, "", value, size, 0); + + kfree(value); + if (!error) + set_cached_acl(inode, type, acl); + return error; +} + +/* + * Initialize the ACLs of a new inode. Called from ext2_new_inode. + * + * dir->i_mutex: down + * inode->i_mutex: up (access to inode is still exclusive) + */ +int +ext2_init_acl(struct inode *inode, struct inode *dir) +{ + struct posix_acl *default_acl, *acl; + int error; + + error = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl); + if (error) + return error; + + if (default_acl) { + error = ext2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); + posix_acl_release(default_acl); + } + if (acl) { + if (!error) + error = ext2_set_acl(inode, acl, ACL_TYPE_ACCESS); + posix_acl_release(acl); + } + return error; +} diff --git a/fs/ext2/acl.h b/fs/ext2/acl.h new file mode 100644 index 000000000..44937f9fc --- /dev/null +++ b/fs/ext2/acl.h @@ -0,0 +1,71 @@ +/* + File: fs/ext2/acl.h + + (C) 2001 Andreas Gruenbacher, +*/ + +#include + +#define EXT2_ACL_VERSION 0x0001 + +typedef struct { + __le16 e_tag; + __le16 e_perm; + __le32 e_id; +} ext2_acl_entry; + +typedef struct { + __le16 e_tag; + __le16 e_perm; +} ext2_acl_entry_short; + +typedef struct { + __le32 a_version; +} ext2_acl_header; + +static inline size_t ext2_acl_size(int count) +{ + if (count <= 4) { + return sizeof(ext2_acl_header) + + count * sizeof(ext2_acl_entry_short); + } else { + return sizeof(ext2_acl_header) + + 4 * sizeof(ext2_acl_entry_short) + + (count - 4) * sizeof(ext2_acl_entry); + } +} + +static inline int ext2_acl_count(size_t size) +{ + ssize_t s; + size -= sizeof(ext2_acl_header); + s = size - 4 * sizeof(ext2_acl_entry_short); + if (s < 0) { + if (size % sizeof(ext2_acl_entry_short)) + return -1; + return size / sizeof(ext2_acl_entry_short); + } else { + if (s % sizeof(ext2_acl_entry)) + return -1; + return s / sizeof(ext2_acl_entry) + 4; + } +} + +#ifdef CONFIG_EXT2_FS_POSIX_ACL + +/* acl.c */ +extern struct posix_acl *ext2_get_acl(struct inode *inode, int type); +extern int ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type); +extern int ext2_init_acl (struct inode *, struct inode *); + +#else +#include +#define ext2_get_acl NULL +#define ext2_set_acl NULL + +static inline int ext2_init_acl (struct inode *inode, struct inode *dir) +{ + return 0; +} +#endif + diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c new file mode 100644 index 000000000..9f9992b37 --- /dev/null +++ b/fs/ext2/balloc.c @@ -0,0 +1,1536 @@ +/* + * linux/fs/ext2/balloc.c + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * Enhanced block allocation by Stephen Tweedie (sct@redhat.com), 1993 + * Big-endian to little-endian byte-swapping/bitmaps by + * David S. Miller (davem@caip.rutgers.edu), 1995 + */ + +#include "ext2.h" +#include +#include +#include +#include +#include + +/* + * balloc.c contains the blocks allocation and deallocation routines + */ + +/* + * The free blocks are managed by bitmaps. A file system contains several + * blocks groups. Each group contains 1 bitmap block for blocks, 1 bitmap + * block for inodes, N blocks for the inode table and data blocks. + * + * The file system contains group descriptors which are located after the + * super block. Each descriptor contains the number of the bitmap block and + * the free blocks count in the block. The descriptors are loaded in memory + * when a file system is mounted (see ext2_fill_super). + */ + + +#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1) + +struct ext2_group_desc * ext2_get_group_desc(struct super_block * sb, + unsigned int block_group, + struct buffer_head ** bh) +{ + unsigned long group_desc; + unsigned long offset; + struct ext2_group_desc * desc; + struct ext2_sb_info *sbi = EXT2_SB(sb); + + if (block_group >= sbi->s_groups_count) { + ext2_error (sb, "ext2_get_group_desc", + "block_group >= groups_count - " + "block_group = %d, groups_count = %lu", + block_group, sbi->s_groups_count); + + return NULL; + } + + group_desc = block_group >> EXT2_DESC_PER_BLOCK_BITS(sb); + offset = block_group & (EXT2_DESC_PER_BLOCK(sb) - 1); + if (!sbi->s_group_desc[group_desc]) { + ext2_error (sb, "ext2_get_group_desc", + "Group descriptor not loaded - " + "block_group = %d, group_desc = %lu, desc = %lu", + block_group, group_desc, offset); + return NULL; + } + + desc = (struct ext2_group_desc *) sbi->s_group_desc[group_desc]->b_data; + if (bh) + *bh = sbi->s_group_desc[group_desc]; + return desc + offset; +} + +static int ext2_valid_block_bitmap(struct super_block *sb, + struct ext2_group_desc *desc, + unsigned int block_group, + struct buffer_head *bh) +{ + ext2_grpblk_t offset; + ext2_grpblk_t next_zero_bit; + ext2_fsblk_t bitmap_blk; + ext2_fsblk_t group_first_block; + + group_first_block = ext2_group_first_block_no(sb, block_group); + + /* check whether block bitmap block number is set */ + bitmap_blk = le32_to_cpu(desc->bg_block_bitmap); + offset = bitmap_blk - group_first_block; + if (!ext2_test_bit(offset, bh->b_data)) + /* bad block bitmap */ + goto err_out; + + /* check whether the inode bitmap block number is set */ + bitmap_blk = le32_to_cpu(desc->bg_inode_bitmap); + offset = bitmap_blk - group_first_block; + if (!ext2_test_bit(offset, bh->b_data)) + /* bad block bitmap */ + goto err_out; + + /* check whether the inode table block number is set */ + bitmap_blk = le32_to_cpu(desc->bg_inode_table); + offset = bitmap_blk - group_first_block; + next_zero_bit = ext2_find_next_zero_bit(bh->b_data, + offset + EXT2_SB(sb)->s_itb_per_group, + offset); + if (next_zero_bit >= offset + EXT2_SB(sb)->s_itb_per_group) + /* good bitmap for inode tables */ + return 1; + +err_out: + ext2_error(sb, __func__, + "Invalid block bitmap - " + "block_group = %d, block = %lu", + block_group, bitmap_blk); + return 0; +} + +/* + * Read the bitmap for a given block_group,and validate the + * bits for block/inode/inode tables are set in the bitmaps + * + * Return buffer_head on success or NULL in case of failure. + */ +static struct buffer_head * +read_block_bitmap(struct super_block *sb, unsigned int block_group) +{ + struct ext2_group_desc * desc; + struct buffer_head * bh = NULL; + ext2_fsblk_t bitmap_blk; + + desc = ext2_get_group_desc(sb, block_group, NULL); + if (!desc) + return NULL; + bitmap_blk = le32_to_cpu(desc->bg_block_bitmap); + bh = sb_getblk(sb, bitmap_blk); + if (unlikely(!bh)) { + ext2_error(sb, __func__, + "Cannot read block bitmap - " + "block_group = %d, block_bitmap = %u", + block_group, le32_to_cpu(desc->bg_block_bitmap)); + return NULL; + } + if (likely(bh_uptodate_or_lock(bh))) + return bh; + + if (bh_submit_read(bh) < 0) { + brelse(bh); + ext2_error(sb, __func__, + "Cannot read block bitmap - " + "block_group = %d, block_bitmap = %u", + block_group, le32_to_cpu(desc->bg_block_bitmap)); + return NULL; + } + + ext2_valid_block_bitmap(sb, desc, block_group, bh); + /* + * file system mounted not to panic on error, continue with corrupt + * bitmap + */ + return bh; +} + +static void group_adjust_blocks(struct super_block *sb, int group_no, + struct ext2_group_desc *desc, struct buffer_head *bh, int count) +{ + if (count) { + struct ext2_sb_info *sbi = EXT2_SB(sb); + unsigned free_blocks; + + spin_lock(sb_bgl_lock(sbi, group_no)); + free_blocks = le16_to_cpu(desc->bg_free_blocks_count); + desc->bg_free_blocks_count = cpu_to_le16(free_blocks + count); + spin_unlock(sb_bgl_lock(sbi, group_no)); + mark_buffer_dirty(bh); + } +} + +/* + * The reservation window structure operations + * -------------------------------------------- + * Operations include: + * dump, find, add, remove, is_empty, find_next_reservable_window, etc. + * + * We use a red-black tree to represent per-filesystem reservation + * windows. + * + */ + +/** + * __rsv_window_dump() -- Dump the filesystem block allocation reservation map + * @rb_root: root of per-filesystem reservation rb tree + * @verbose: verbose mode + * @fn: function which wishes to dump the reservation map + * + * If verbose is turned on, it will print the whole block reservation + * windows(start, end). Otherwise, it will only print out the "bad" windows, + * those windows that overlap with their immediate neighbors. + */ +#if 1 +static void __rsv_window_dump(struct rb_root *root, int verbose, + const char *fn) +{ + struct rb_node *n; + struct ext2_reserve_window_node *rsv, *prev; + int bad; + +restart: + n = rb_first(root); + bad = 0; + prev = NULL; + + printk("Block Allocation Reservation Windows Map (%s):\n", fn); + while (n) { + rsv = rb_entry(n, struct ext2_reserve_window_node, rsv_node); + if (verbose) + printk("reservation window 0x%p " + "start: %lu, end: %lu\n", + rsv, rsv->rsv_start, rsv->rsv_end); + if (rsv->rsv_start && rsv->rsv_start >= rsv->rsv_end) { + printk("Bad reservation %p (start >= end)\n", + rsv); + bad = 1; + } + if (prev && prev->rsv_end >= rsv->rsv_start) { + printk("Bad reservation %p (prev->end >= start)\n", + rsv); + bad = 1; + } + if (bad) { + if (!verbose) { + printk("Restarting reservation walk in verbose mode\n"); + verbose = 1; + goto restart; + } + } + n = rb_next(n); + prev = rsv; + } + printk("Window map complete.\n"); + BUG_ON(bad); +} +#define rsv_window_dump(root, verbose) \ + __rsv_window_dump((root), (verbose), __func__) +#else +#define rsv_window_dump(root, verbose) do {} while (0) +#endif + +/** + * goal_in_my_reservation() + * @rsv: inode's reservation window + * @grp_goal: given goal block relative to the allocation block group + * @group: the current allocation block group + * @sb: filesystem super block + * + * Test if the given goal block (group relative) is within the file's + * own block reservation window range. + * + * If the reservation window is outside the goal allocation group, return 0; + * grp_goal (given goal block) could be -1, which means no specific + * goal block. In this case, always return 1. + * If the goal block is within the reservation window, return 1; + * otherwise, return 0; + */ +static int +goal_in_my_reservation(struct ext2_reserve_window *rsv, ext2_grpblk_t grp_goal, + unsigned int group, struct super_block * sb) +{ + ext2_fsblk_t group_first_block, group_last_block; + + group_first_block = ext2_group_first_block_no(sb, group); + group_last_block = group_first_block + EXT2_BLOCKS_PER_GROUP(sb) - 1; + + if ((rsv->_rsv_start > group_last_block) || + (rsv->_rsv_end < group_first_block)) + return 0; + if ((grp_goal >= 0) && ((grp_goal + group_first_block < rsv->_rsv_start) + || (grp_goal + group_first_block > rsv->_rsv_end))) + return 0; + return 1; +} + +/** + * search_reserve_window() + * @rb_root: root of reservation tree + * @goal: target allocation block + * + * Find the reserved window which includes the goal, or the previous one + * if the goal is not in any window. + * Returns NULL if there are no windows or if all windows start after the goal. + */ +static struct ext2_reserve_window_node * +search_reserve_window(struct rb_root *root, ext2_fsblk_t goal) +{ + struct rb_node *n = root->rb_node; + struct ext2_reserve_window_node *rsv; + + if (!n) + return NULL; + + do { + rsv = rb_entry(n, struct ext2_reserve_window_node, rsv_node); + + if (goal < rsv->rsv_start) + n = n->rb_left; + else if (goal > rsv->rsv_end) + n = n->rb_right; + else + return rsv; + } while (n); + /* + * We've fallen off the end of the tree: the goal wasn't inside + * any particular node. OK, the previous node must be to one + * side of the interval containing the goal. If it's the RHS, + * we need to back up one. + */ + if (rsv->rsv_start > goal) { + n = rb_prev(&rsv->rsv_node); + rsv = rb_entry(n, struct ext2_reserve_window_node, rsv_node); + } + return rsv; +} + +/* + * ext2_rsv_window_add() -- Insert a window to the block reservation rb tree. + * @sb: super block + * @rsv: reservation window to add + * + * Must be called with rsv_lock held. + */ +void ext2_rsv_window_add(struct super_block *sb, + struct ext2_reserve_window_node *rsv) +{ + struct rb_root *root = &EXT2_SB(sb)->s_rsv_window_root; + struct rb_node *node = &rsv->rsv_node; + ext2_fsblk_t start = rsv->rsv_start; + + struct rb_node ** p = &root->rb_node; + struct rb_node * parent = NULL; + struct ext2_reserve_window_node *this; + + while (*p) + { + parent = *p; + this = rb_entry(parent, struct ext2_reserve_window_node, rsv_node); + + if (start < this->rsv_start) + p = &(*p)->rb_left; + else if (start > this->rsv_end) + p = &(*p)->rb_right; + else { + rsv_window_dump(root, 1); + BUG(); + } + } + + rb_link_node(node, parent, p); + rb_insert_color(node, root); +} + +/** + * rsv_window_remove() -- unlink a window from the reservation rb tree + * @sb: super block + * @rsv: reservation window to remove + * + * Mark the block reservation window as not allocated, and unlink it + * from the filesystem reservation window rb tree. Must be called with + * rsv_lock held. + */ +static void rsv_window_remove(struct super_block *sb, + struct ext2_reserve_window_node *rsv) +{ + rsv->rsv_start = EXT2_RESERVE_WINDOW_NOT_ALLOCATED; + rsv->rsv_end = EXT2_RESERVE_WINDOW_NOT_ALLOCATED; + rsv->rsv_alloc_hit = 0; + rb_erase(&rsv->rsv_node, &EXT2_SB(sb)->s_rsv_window_root); +} + +/* + * rsv_is_empty() -- Check if the reservation window is allocated. + * @rsv: given reservation window to check + * + * returns 1 if the end block is EXT2_RESERVE_WINDOW_NOT_ALLOCATED. + */ +static inline int rsv_is_empty(struct ext2_reserve_window *rsv) +{ + /* a valid reservation end block could not be 0 */ + return (rsv->_rsv_end == EXT2_RESERVE_WINDOW_NOT_ALLOCATED); +} + +/** + * ext2_init_block_alloc_info() + * @inode: file inode structure + * + * Allocate and initialize the reservation window structure, and + * link the window to the ext2 inode structure at last + * + * The reservation window structure is only dynamically allocated + * and linked to ext2 inode the first time the open file + * needs a new block. So, before every ext2_new_block(s) call, for + * regular files, we should check whether the reservation window + * structure exists or not. In the latter case, this function is called. + * Fail to do so will result in block reservation being turned off for that + * open file. + * + * This function is called from ext2_get_blocks_handle(), also called + * when setting the reservation window size through ioctl before the file + * is open for write (needs block allocation). + * + * Needs truncate_mutex protection prior to calling this function. + */ +void ext2_init_block_alloc_info(struct inode *inode) +{ + struct ext2_inode_info *ei = EXT2_I(inode); + struct ext2_block_alloc_info *block_i; + struct super_block *sb = inode->i_sb; + + block_i = kmalloc(sizeof(*block_i), GFP_NOFS); + if (block_i) { + struct ext2_reserve_window_node *rsv = &block_i->rsv_window_node; + + rsv->rsv_start = EXT2_RESERVE_WINDOW_NOT_ALLOCATED; + rsv->rsv_end = EXT2_RESERVE_WINDOW_NOT_ALLOCATED; + + /* + * if filesystem is mounted with NORESERVATION, the goal + * reservation window size is set to zero to indicate + * block reservation is off + */ + if (!test_opt(sb, RESERVATION)) + rsv->rsv_goal_size = 0; + else + rsv->rsv_goal_size = EXT2_DEFAULT_RESERVE_BLOCKS; + rsv->rsv_alloc_hit = 0; + block_i->last_alloc_logical_block = 0; + block_i->last_alloc_physical_block = 0; + } + ei->i_block_alloc_info = block_i; +} + +/** + * ext2_discard_reservation() + * @inode: inode + * + * Discard(free) block reservation window on last file close, or truncate + * or at last iput(). + * + * It is being called in three cases: + * ext2_release_file(): last writer closes the file + * ext2_clear_inode(): last iput(), when nobody links to this file. + * ext2_truncate(): when the block indirect map is about to change. + */ +void ext2_discard_reservation(struct inode *inode) +{ + struct ext2_inode_info *ei = EXT2_I(inode); + struct ext2_block_alloc_info *block_i = ei->i_block_alloc_info; + struct ext2_reserve_window_node *rsv; + spinlock_t *rsv_lock = &EXT2_SB(inode->i_sb)->s_rsv_window_lock; + + if (!block_i) + return; + + rsv = &block_i->rsv_window_node; + if (!rsv_is_empty(&rsv->rsv_window)) { + spin_lock(rsv_lock); + if (!rsv_is_empty(&rsv->rsv_window)) + rsv_window_remove(inode->i_sb, rsv); + spin_unlock(rsv_lock); + } +} + +/** + * ext2_free_blocks() -- Free given blocks and update quota and i_blocks + * @inode: inode + * @block: start physical block to free + * @count: number of blocks to free + */ +void ext2_free_blocks (struct inode * inode, unsigned long block, + unsigned long count) +{ + struct buffer_head *bitmap_bh = NULL; + struct buffer_head * bh2; + unsigned long block_group; + unsigned long bit; + unsigned long i; + unsigned long overflow; + struct super_block * sb = inode->i_sb; + struct ext2_sb_info * sbi = EXT2_SB(sb); + struct ext2_group_desc * desc; + struct ext2_super_block * es = sbi->s_es; + unsigned freed = 0, group_freed; + + if (block < le32_to_cpu(es->s_first_data_block) || + block + count < block || + block + count > le32_to_cpu(es->s_blocks_count)) { + ext2_error (sb, "ext2_free_blocks", + "Freeing blocks not in datazone - " + "block = %lu, count = %lu", block, count); + goto error_return; + } + + ext2_debug ("freeing block(s) %lu-%lu\n", block, block + count - 1); + +do_more: + overflow = 0; + block_group = (block - le32_to_cpu(es->s_first_data_block)) / + EXT2_BLOCKS_PER_GROUP(sb); + bit = (block - le32_to_cpu(es->s_first_data_block)) % + EXT2_BLOCKS_PER_GROUP(sb); + /* + * Check to see if we are freeing blocks across a group + * boundary. + */ + if (bit + count > EXT2_BLOCKS_PER_GROUP(sb)) { + overflow = bit + count - EXT2_BLOCKS_PER_GROUP(sb); + count -= overflow; + } + brelse(bitmap_bh); + bitmap_bh = read_block_bitmap(sb, block_group); + if (!bitmap_bh) + goto error_return; + + desc = ext2_get_group_desc (sb, block_group, &bh2); + if (!desc) + goto error_return; + + if (in_range (le32_to_cpu(desc->bg_block_bitmap), block, count) || + in_range (le32_to_cpu(desc->bg_inode_bitmap), block, count) || + in_range (block, le32_to_cpu(desc->bg_inode_table), + sbi->s_itb_per_group) || + in_range (block + count - 1, le32_to_cpu(desc->bg_inode_table), + sbi->s_itb_per_group)) { + ext2_error (sb, "ext2_free_blocks", + "Freeing blocks in system zones - " + "Block = %lu, count = %lu", + block, count); + goto error_return; + } + + for (i = 0, group_freed = 0; i < count; i++) { + if (!ext2_clear_bit_atomic(sb_bgl_lock(sbi, block_group), + bit + i, bitmap_bh->b_data)) { + ext2_error(sb, __func__, + "bit already cleared for block %lu", block + i); + } else { + group_freed++; + } + } + + mark_buffer_dirty(bitmap_bh); + if (sb->s_flags & MS_SYNCHRONOUS) + sync_dirty_buffer(bitmap_bh); + + group_adjust_blocks(sb, block_group, desc, bh2, group_freed); + freed += group_freed; + + if (overflow) { + block += count; + count = overflow; + goto do_more; + } +error_return: + brelse(bitmap_bh); + if (freed) { + percpu_counter_add(&sbi->s_freeblocks_counter, freed); + dquot_free_block_nodirty(inode, freed); + mark_inode_dirty(inode); + } +} + +/** + * bitmap_search_next_usable_block() + * @start: the starting block (group relative) of the search + * @bh: bufferhead contains the block group bitmap + * @maxblocks: the ending block (group relative) of the reservation + * + * The bitmap search --- search forward through the actual bitmap on disk until + * we find a bit free. + */ +static ext2_grpblk_t +bitmap_search_next_usable_block(ext2_grpblk_t start, struct buffer_head *bh, + ext2_grpblk_t maxblocks) +{ + ext2_grpblk_t next; + + next = ext2_find_next_zero_bit(bh->b_data, maxblocks, start); + if (next >= maxblocks) + return -1; + return next; +} + +/** + * find_next_usable_block() + * @start: the starting block (group relative) to find next + * allocatable block in bitmap. + * @bh: bufferhead contains the block group bitmap + * @maxblocks: the ending block (group relative) for the search + * + * Find an allocatable block in a bitmap. We perform the "most + * appropriate allocation" algorithm of looking for a free block near + * the initial goal; then for a free byte somewhere in the bitmap; + * then for any free bit in the bitmap. + */ +static ext2_grpblk_t +find_next_usable_block(int start, struct buffer_head *bh, int maxblocks) +{ + ext2_grpblk_t here, next; + char *p, *r; + + if (start > 0) { + /* + * The goal was occupied; search forward for a free + * block within the next XX blocks. + * + * end_goal is more or less random, but it has to be + * less than EXT2_BLOCKS_PER_GROUP. Aligning up to the + * next 64-bit boundary is simple.. + */ + ext2_grpblk_t end_goal = (start + 63) & ~63; + if (end_goal > maxblocks) + end_goal = maxblocks; + here = ext2_find_next_zero_bit(bh->b_data, end_goal, start); + if (here < end_goal) + return here; + ext2_debug("Bit not found near goal\n"); + } + + here = start; + if (here < 0) + here = 0; + + p = ((char *)bh->b_data) + (here >> 3); + r = memscan(p, 0, ((maxblocks + 7) >> 3) - (here >> 3)); + next = (r - ((char *)bh->b_data)) << 3; + + if (next < maxblocks && next >= here) + return next; + + here = bitmap_search_next_usable_block(here, bh, maxblocks); + return here; +} + +/** + * ext2_try_to_allocate() + * @sb: superblock + * @group: given allocation block group + * @bitmap_bh: bufferhead holds the block bitmap + * @grp_goal: given target block within the group + * @count: target number of blocks to allocate + * @my_rsv: reservation window + * + * Attempt to allocate blocks within a give range. Set the range of allocation + * first, then find the first free bit(s) from the bitmap (within the range), + * and at last, allocate the blocks by claiming the found free bit as allocated. + * + * To set the range of this allocation: + * if there is a reservation window, only try to allocate block(s) + * from the file's own reservation window; + * Otherwise, the allocation range starts from the give goal block, + * ends at the block group's last block. + * + * If we failed to allocate the desired block then we may end up crossing to a + * new bitmap. + */ +static int +ext2_try_to_allocate(struct super_block *sb, int group, + struct buffer_head *bitmap_bh, ext2_grpblk_t grp_goal, + unsigned long *count, + struct ext2_reserve_window *my_rsv) +{ + ext2_fsblk_t group_first_block; + ext2_grpblk_t start, end; + unsigned long num = 0; + + /* we do allocation within the reservation window if we have a window */ + if (my_rsv) { + group_first_block = ext2_group_first_block_no(sb, group); + if (my_rsv->_rsv_start >= group_first_block) + start = my_rsv->_rsv_start - group_first_block; + else + /* reservation window cross group boundary */ + start = 0; + end = my_rsv->_rsv_end - group_first_block + 1; + if (end > EXT2_BLOCKS_PER_GROUP(sb)) + /* reservation window crosses group boundary */ + end = EXT2_BLOCKS_PER_GROUP(sb); + if ((start <= grp_goal) && (grp_goal < end)) + start = grp_goal; + else + grp_goal = -1; + } else { + if (grp_goal > 0) + start = grp_goal; + else + start = 0; + end = EXT2_BLOCKS_PER_GROUP(sb); + } + + BUG_ON(start > EXT2_BLOCKS_PER_GROUP(sb)); + +repeat: + if (grp_goal < 0) { + grp_goal = find_next_usable_block(start, bitmap_bh, end); + if (grp_goal < 0) + goto fail_access; + if (!my_rsv) { + int i; + + for (i = 0; i < 7 && grp_goal > start && + !ext2_test_bit(grp_goal - 1, + bitmap_bh->b_data); + i++, grp_goal--) + ; + } + } + start = grp_goal; + + if (ext2_set_bit_atomic(sb_bgl_lock(EXT2_SB(sb), group), grp_goal, + bitmap_bh->b_data)) { + /* + * The block was allocated by another thread, or it was + * allocated and then freed by another thread + */ + start++; + grp_goal++; + if (start >= end) + goto fail_access; + goto repeat; + } + num++; + grp_goal++; + while (num < *count && grp_goal < end + && !ext2_set_bit_atomic(sb_bgl_lock(EXT2_SB(sb), group), + grp_goal, bitmap_bh->b_data)) { + num++; + grp_goal++; + } + *count = num; + return grp_goal - num; +fail_access: + *count = num; + return -1; +} + +/** + * find_next_reservable_window(): + * find a reservable space within the given range. + * It does not allocate the reservation window for now: + * alloc_new_reservation() will do the work later. + * + * @search_head: the head of the searching list; + * This is not necessarily the list head of the whole filesystem + * + * We have both head and start_block to assist the search + * for the reservable space. The list starts from head, + * but we will shift to the place where start_block is, + * then start from there, when looking for a reservable space. + * + * @size: the target new reservation window size + * + * @group_first_block: the first block we consider to start + * the real search from + * + * @last_block: + * the maximum block number that our goal reservable space + * could start from. This is normally the last block in this + * group. The search will end when we found the start of next + * possible reservable space is out of this boundary. + * This could handle the cross boundary reservation window + * request. + * + * basically we search from the given range, rather than the whole + * reservation double linked list, (start_block, last_block) + * to find a free region that is of my size and has not + * been reserved. + * + */ +static int find_next_reservable_window( + struct ext2_reserve_window_node *search_head, + struct ext2_reserve_window_node *my_rsv, + struct super_block * sb, + ext2_fsblk_t start_block, + ext2_fsblk_t last_block) +{ + struct rb_node *next; + struct ext2_reserve_window_node *rsv, *prev; + ext2_fsblk_t cur; + int size = my_rsv->rsv_goal_size; + + /* TODO: make the start of the reservation window byte-aligned */ + /* cur = *start_block & ~7;*/ + cur = start_block; + rsv = search_head; + if (!rsv) + return -1; + + while (1) { + if (cur <= rsv->rsv_end) + cur = rsv->rsv_end + 1; + + /* TODO? + * in the case we could not find a reservable space + * that is what is expected, during the re-search, we could + * remember what's the largest reservable space we could have + * and return that one. + * + * For now it will fail if we could not find the reservable + * space with expected-size (or more)... + */ + if (cur > last_block) + return -1; /* fail */ + + prev = rsv; + next = rb_next(&rsv->rsv_node); + rsv = rb_entry(next,struct ext2_reserve_window_node,rsv_node); + + /* + * Reached the last reservation, we can just append to the + * previous one. + */ + if (!next) + break; + + if (cur + size <= rsv->rsv_start) { + /* + * Found a reserveable space big enough. We could + * have a reservation across the group boundary here + */ + break; + } + } + /* + * we come here either : + * when we reach the end of the whole list, + * and there is empty reservable space after last entry in the list. + * append it to the end of the list. + * + * or we found one reservable space in the middle of the list, + * return the reservation window that we could append to. + * succeed. + */ + + if ((prev != my_rsv) && (!rsv_is_empty(&my_rsv->rsv_window))) + rsv_window_remove(sb, my_rsv); + + /* + * Let's book the whole available window for now. We will check the + * disk bitmap later and then, if there are free blocks then we adjust + * the window size if it's larger than requested. + * Otherwise, we will remove this node from the tree next time + * call find_next_reservable_window. + */ + my_rsv->rsv_start = cur; + my_rsv->rsv_end = cur + size - 1; + my_rsv->rsv_alloc_hit = 0; + + if (prev != my_rsv) + ext2_rsv_window_add(sb, my_rsv); + + return 0; +} + +/** + * alloc_new_reservation()--allocate a new reservation window + * + * To make a new reservation, we search part of the filesystem + * reservation list (the list that inside the group). We try to + * allocate a new reservation window near the allocation goal, + * or the beginning of the group, if there is no goal. + * + * We first find a reservable space after the goal, then from + * there, we check the bitmap for the first free block after + * it. If there is no free block until the end of group, then the + * whole group is full, we failed. Otherwise, check if the free + * block is inside the expected reservable space, if so, we + * succeed. + * If the first free block is outside the reservable space, then + * start from the first free block, we search for next available + * space, and go on. + * + * on succeed, a new reservation will be found and inserted into the list + * It contains at least one free block, and it does not overlap with other + * reservation windows. + * + * failed: we failed to find a reservation window in this group + * + * @rsv: the reservation + * + * @grp_goal: The goal (group-relative). It is where the search for a + * free reservable space should start from. + * if we have a goal(goal >0 ), then start from there, + * no goal(goal = -1), we start from the first block + * of the group. + * + * @sb: the super block + * @group: the group we are trying to allocate in + * @bitmap_bh: the block group block bitmap + * + */ +static int alloc_new_reservation(struct ext2_reserve_window_node *my_rsv, + ext2_grpblk_t grp_goal, struct super_block *sb, + unsigned int group, struct buffer_head *bitmap_bh) +{ + struct ext2_reserve_window_node *search_head; + ext2_fsblk_t group_first_block, group_end_block, start_block; + ext2_grpblk_t first_free_block; + struct rb_root *fs_rsv_root = &EXT2_SB(sb)->s_rsv_window_root; + unsigned long size; + int ret; + spinlock_t *rsv_lock = &EXT2_SB(sb)->s_rsv_window_lock; + + group_first_block = ext2_group_first_block_no(sb, group); + group_end_block = group_first_block + (EXT2_BLOCKS_PER_GROUP(sb) - 1); + + if (grp_goal < 0) + start_block = group_first_block; + else + start_block = grp_goal + group_first_block; + + size = my_rsv->rsv_goal_size; + + if (!rsv_is_empty(&my_rsv->rsv_window)) { + /* + * if the old reservation is cross group boundary + * and if the goal is inside the old reservation window, + * we will come here when we just failed to allocate from + * the first part of the window. We still have another part + * that belongs to the next group. In this case, there is no + * point to discard our window and try to allocate a new one + * in this group(which will fail). we should + * keep the reservation window, just simply move on. + * + * Maybe we could shift the start block of the reservation + * window to the first block of next group. + */ + + if ((my_rsv->rsv_start <= group_end_block) && + (my_rsv->rsv_end > group_end_block) && + (start_block >= my_rsv->rsv_start)) + return -1; + + if ((my_rsv->rsv_alloc_hit > + (my_rsv->rsv_end - my_rsv->rsv_start + 1) / 2)) { + /* + * if the previously allocation hit ratio is + * greater than 1/2, then we double the size of + * the reservation window the next time, + * otherwise we keep the same size window + */ + size = size * 2; + if (size > EXT2_MAX_RESERVE_BLOCKS) + size = EXT2_MAX_RESERVE_BLOCKS; + my_rsv->rsv_goal_size= size; + } + } + + spin_lock(rsv_lock); + /* + * shift the search start to the window near the goal block + */ + search_head = search_reserve_window(fs_rsv_root, start_block); + + /* + * find_next_reservable_window() simply finds a reservable window + * inside the given range(start_block, group_end_block). + * + * To make sure the reservation window has a free bit inside it, we + * need to check the bitmap after we found a reservable window. + */ +retry: + ret = find_next_reservable_window(search_head, my_rsv, sb, + start_block, group_end_block); + + if (ret == -1) { + if (!rsv_is_empty(&my_rsv->rsv_window)) + rsv_window_remove(sb, my_rsv); + spin_unlock(rsv_lock); + return -1; + } + + /* + * On success, find_next_reservable_window() returns the + * reservation window where there is a reservable space after it. + * Before we reserve this reservable space, we need + * to make sure there is at least a free block inside this region. + * + * Search the first free bit on the block bitmap. Search starts from + * the start block of the reservable space we just found. + */ + spin_unlock(rsv_lock); + first_free_block = bitmap_search_next_usable_block( + my_rsv->rsv_start - group_first_block, + bitmap_bh, group_end_block - group_first_block + 1); + + if (first_free_block < 0) { + /* + * no free block left on the bitmap, no point + * to reserve the space. return failed. + */ + spin_lock(rsv_lock); + if (!rsv_is_empty(&my_rsv->rsv_window)) + rsv_window_remove(sb, my_rsv); + spin_unlock(rsv_lock); + return -1; /* failed */ + } + + start_block = first_free_block + group_first_block; + /* + * check if the first free block is within the + * free space we just reserved + */ + if (start_block >= my_rsv->rsv_start && start_block <= my_rsv->rsv_end) + return 0; /* success */ + /* + * if the first free bit we found is out of the reservable space + * continue search for next reservable space, + * start from where the free block is, + * we also shift the list head to where we stopped last time + */ + search_head = my_rsv; + spin_lock(rsv_lock); + goto retry; +} + +/** + * try_to_extend_reservation() + * @my_rsv: given reservation window + * @sb: super block + * @size: the delta to extend + * + * Attempt to expand the reservation window large enough to have + * required number of free blocks + * + * Since ext2_try_to_allocate() will always allocate blocks within + * the reservation window range, if the window size is too small, + * multiple blocks allocation has to stop at the end of the reservation + * window. To make this more efficient, given the total number of + * blocks needed and the current size of the window, we try to + * expand the reservation window size if necessary on a best-effort + * basis before ext2_new_blocks() tries to allocate blocks. + */ +static void try_to_extend_reservation(struct ext2_reserve_window_node *my_rsv, + struct super_block *sb, int size) +{ + struct ext2_reserve_window_node *next_rsv; + struct rb_node *next; + spinlock_t *rsv_lock = &EXT2_SB(sb)->s_rsv_window_lock; + + if (!spin_trylock(rsv_lock)) + return; + + next = rb_next(&my_rsv->rsv_node); + + if (!next) + my_rsv->rsv_end += size; + else { + next_rsv = rb_entry(next, struct ext2_reserve_window_node, rsv_node); + + if ((next_rsv->rsv_start - my_rsv->rsv_end - 1) >= size) + my_rsv->rsv_end += size; + else + my_rsv->rsv_end = next_rsv->rsv_start - 1; + } + spin_unlock(rsv_lock); +} + +/** + * ext2_try_to_allocate_with_rsv() + * @sb: superblock + * @group: given allocation block group + * @bitmap_bh: bufferhead holds the block bitmap + * @grp_goal: given target block within the group + * @count: target number of blocks to allocate + * @my_rsv: reservation window + * + * This is the main function used to allocate a new block and its reservation + * window. + * + * Each time when a new block allocation is need, first try to allocate from + * its own reservation. If it does not have a reservation window, instead of + * looking for a free bit on bitmap first, then look up the reservation list to + * see if it is inside somebody else's reservation window, we try to allocate a + * reservation window for it starting from the goal first. Then do the block + * allocation within the reservation window. + * + * This will avoid keeping on searching the reservation list again and + * again when somebody is looking for a free block (without + * reservation), and there are lots of free blocks, but they are all + * being reserved. + * + * We use a red-black tree for the per-filesystem reservation list. + */ +static ext2_grpblk_t +ext2_try_to_allocate_with_rsv(struct super_block *sb, unsigned int group, + struct buffer_head *bitmap_bh, ext2_grpblk_t grp_goal, + struct ext2_reserve_window_node * my_rsv, + unsigned long *count) +{ + ext2_fsblk_t group_first_block, group_last_block; + ext2_grpblk_t ret = 0; + unsigned long num = *count; + + /* + * we don't deal with reservation when + * filesystem is mounted without reservation + * or the file is not a regular file + * or last attempt to allocate a block with reservation turned on failed + */ + if (my_rsv == NULL) { + return ext2_try_to_allocate(sb, group, bitmap_bh, + grp_goal, count, NULL); + } + /* + * grp_goal is a group relative block number (if there is a goal) + * 0 <= grp_goal < EXT2_BLOCKS_PER_GROUP(sb) + * first block is a filesystem wide block number + * first block is the block number of the first block in this group + */ + group_first_block = ext2_group_first_block_no(sb, group); + group_last_block = group_first_block + (EXT2_BLOCKS_PER_GROUP(sb) - 1); + + /* + * Basically we will allocate a new block from inode's reservation + * window. + * + * We need to allocate a new reservation window, if: + * a) inode does not have a reservation window; or + * b) last attempt to allocate a block from existing reservation + * failed; or + * c) we come here with a goal and with a reservation window + * + * We do not need to allocate a new reservation window if we come here + * at the beginning with a goal and the goal is inside the window, or + * we don't have a goal but already have a reservation window. + * then we could go to allocate from the reservation window directly. + */ + while (1) { + if (rsv_is_empty(&my_rsv->rsv_window) || (ret < 0) || + !goal_in_my_reservation(&my_rsv->rsv_window, + grp_goal, group, sb)) { + if (my_rsv->rsv_goal_size < *count) + my_rsv->rsv_goal_size = *count; + ret = alloc_new_reservation(my_rsv, grp_goal, sb, + group, bitmap_bh); + if (ret < 0) + break; /* failed */ + + if (!goal_in_my_reservation(&my_rsv->rsv_window, + grp_goal, group, sb)) + grp_goal = -1; + } else if (grp_goal >= 0) { + int curr = my_rsv->rsv_end - + (grp_goal + group_first_block) + 1; + + if (curr < *count) + try_to_extend_reservation(my_rsv, sb, + *count - curr); + } + + if ((my_rsv->rsv_start > group_last_block) || + (my_rsv->rsv_end < group_first_block)) { + rsv_window_dump(&EXT2_SB(sb)->s_rsv_window_root, 1); + BUG(); + } + ret = ext2_try_to_allocate(sb, group, bitmap_bh, grp_goal, + &num, &my_rsv->rsv_window); + if (ret >= 0) { + my_rsv->rsv_alloc_hit += num; + *count = num; + break; /* succeed */ + } + num = *count; + } + return ret; +} + +/** + * ext2_has_free_blocks() + * @sbi: in-core super block structure. + * + * Check if filesystem has at least 1 free block available for allocation. + */ +static int ext2_has_free_blocks(struct ext2_sb_info *sbi) +{ + ext2_fsblk_t free_blocks, root_blocks; + + free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter); + root_blocks = le32_to_cpu(sbi->s_es->s_r_blocks_count); + if (free_blocks < root_blocks + 1 && !capable(CAP_SYS_RESOURCE) && + !uid_eq(sbi->s_resuid, current_fsuid()) && + (gid_eq(sbi->s_resgid, GLOBAL_ROOT_GID) || + !in_group_p (sbi->s_resgid))) { + return 0; + } + return 1; +} + +/* + * ext2_new_blocks() -- core block(s) allocation function + * @inode: file inode + * @goal: given target block(filesystem wide) + * @count: target number of blocks to allocate + * @errp: error code + * + * ext2_new_blocks uses a goal block to assist allocation. If the goal is + * free, or there is a free block within 32 blocks of the goal, that block + * is allocated. Otherwise a forward search is made for a free block; within + * each block group the search first looks for an entire free byte in the block + * bitmap, and then for any free bit if that fails. + * This function also updates quota and i_blocks field. + */ +ext2_fsblk_t ext2_new_blocks(struct inode *inode, ext2_fsblk_t goal, + unsigned long *count, int *errp) +{ + struct buffer_head *bitmap_bh = NULL; + struct buffer_head *gdp_bh; + int group_no; + int goal_group; + ext2_grpblk_t grp_target_blk; /* blockgroup relative goal block */ + ext2_grpblk_t grp_alloc_blk; /* blockgroup-relative allocated block*/ + ext2_fsblk_t ret_block; /* filesyetem-wide allocated block */ + int bgi; /* blockgroup iteration index */ + int performed_allocation = 0; + ext2_grpblk_t free_blocks; /* number of free blocks in a group */ + struct super_block *sb; + struct ext2_group_desc *gdp; + struct ext2_super_block *es; + struct ext2_sb_info *sbi; + struct ext2_reserve_window_node *my_rsv = NULL; + struct ext2_block_alloc_info *block_i; + unsigned short windowsz = 0; + unsigned long ngroups; + unsigned long num = *count; + int ret; + + *errp = -ENOSPC; + sb = inode->i_sb; + + /* + * Check quota for allocation of this block. + */ + ret = dquot_alloc_block(inode, num); + if (ret) { + *errp = ret; + return 0; + } + + sbi = EXT2_SB(sb); + es = EXT2_SB(sb)->s_es; + ext2_debug("goal=%lu.\n", goal); + /* + * Allocate a block from reservation only when + * filesystem is mounted with reservation(default,-o reservation), and + * it's a regular file, and + * the desired window size is greater than 0 (One could use ioctl + * command EXT2_IOC_SETRSVSZ to set the window size to 0 to turn off + * reservation on that particular file) + */ + block_i = EXT2_I(inode)->i_block_alloc_info; + if (block_i) { + windowsz = block_i->rsv_window_node.rsv_goal_size; + if (windowsz > 0) + my_rsv = &block_i->rsv_window_node; + } + + if (!ext2_has_free_blocks(sbi)) { + *errp = -ENOSPC; + goto out; + } + + /* + * First, test whether the goal block is free. + */ + if (goal < le32_to_cpu(es->s_first_data_block) || + goal >= le32_to_cpu(es->s_blocks_count)) + goal = le32_to_cpu(es->s_first_data_block); + group_no = (goal - le32_to_cpu(es->s_first_data_block)) / + EXT2_BLOCKS_PER_GROUP(sb); + goal_group = group_no; +retry_alloc: + gdp = ext2_get_group_desc(sb, group_no, &gdp_bh); + if (!gdp) + goto io_error; + + free_blocks = le16_to_cpu(gdp->bg_free_blocks_count); + /* + * if there is not enough free blocks to make a new resevation + * turn off reservation for this allocation + */ + if (my_rsv && (free_blocks < windowsz) + && (free_blocks > 0) + && (rsv_is_empty(&my_rsv->rsv_window))) + my_rsv = NULL; + + if (free_blocks > 0) { + grp_target_blk = ((goal - le32_to_cpu(es->s_first_data_block)) % + EXT2_BLOCKS_PER_GROUP(sb)); + bitmap_bh = read_block_bitmap(sb, group_no); + if (!bitmap_bh) + goto io_error; + grp_alloc_blk = ext2_try_to_allocate_with_rsv(sb, group_no, + bitmap_bh, grp_target_blk, + my_rsv, &num); + if (grp_alloc_blk >= 0) + goto allocated; + } + + ngroups = EXT2_SB(sb)->s_groups_count; + smp_rmb(); + + /* + * Now search the rest of the groups. We assume that + * group_no and gdp correctly point to the last group visited. + */ + for (bgi = 0; bgi < ngroups; bgi++) { + group_no++; + if (group_no >= ngroups) + group_no = 0; + gdp = ext2_get_group_desc(sb, group_no, &gdp_bh); + if (!gdp) + goto io_error; + + free_blocks = le16_to_cpu(gdp->bg_free_blocks_count); + /* + * skip this group (and avoid loading bitmap) if there + * are no free blocks + */ + if (!free_blocks) + continue; + /* + * skip this group if the number of + * free blocks is less than half of the reservation + * window size. + */ + if (my_rsv && (free_blocks <= (windowsz/2))) + continue; + + brelse(bitmap_bh); + bitmap_bh = read_block_bitmap(sb, group_no); + if (!bitmap_bh) + goto io_error; + /* + * try to allocate block(s) from this group, without a goal(-1). + */ + grp_alloc_blk = ext2_try_to_allocate_with_rsv(sb, group_no, + bitmap_bh, -1, my_rsv, &num); + if (grp_alloc_blk >= 0) + goto allocated; + } + /* + * We may end up a bogus earlier ENOSPC error due to + * filesystem is "full" of reservations, but + * there maybe indeed free blocks available on disk + * In this case, we just forget about the reservations + * just do block allocation as without reservations. + */ + if (my_rsv) { + my_rsv = NULL; + windowsz = 0; + group_no = goal_group; + goto retry_alloc; + } + /* No space left on the device */ + *errp = -ENOSPC; + goto out; + +allocated: + + ext2_debug("using block group %d(%d)\n", + group_no, gdp->bg_free_blocks_count); + + ret_block = grp_alloc_blk + ext2_group_first_block_no(sb, group_no); + + if (in_range(le32_to_cpu(gdp->bg_block_bitmap), ret_block, num) || + in_range(le32_to_cpu(gdp->bg_inode_bitmap), ret_block, num) || + in_range(ret_block, le32_to_cpu(gdp->bg_inode_table), + EXT2_SB(sb)->s_itb_per_group) || + in_range(ret_block + num - 1, le32_to_cpu(gdp->bg_inode_table), + EXT2_SB(sb)->s_itb_per_group)) { + ext2_error(sb, "ext2_new_blocks", + "Allocating block in system zone - " + "blocks from "E2FSBLK", length %lu", + ret_block, num); + /* + * ext2_try_to_allocate marked the blocks we allocated as in + * use. So we may want to selectively mark some of the blocks + * as free + */ + goto retry_alloc; + } + + performed_allocation = 1; + + if (ret_block + num - 1 >= le32_to_cpu(es->s_blocks_count)) { + ext2_error(sb, "ext2_new_blocks", + "block("E2FSBLK") >= blocks count(%d) - " + "block_group = %d, es == %p ", ret_block, + le32_to_cpu(es->s_blocks_count), group_no, es); + goto out; + } + + group_adjust_blocks(sb, group_no, gdp, gdp_bh, -num); + percpu_counter_sub(&sbi->s_freeblocks_counter, num); + + mark_buffer_dirty(bitmap_bh); + if (sb->s_flags & MS_SYNCHRONOUS) + sync_dirty_buffer(bitmap_bh); + + *errp = 0; + brelse(bitmap_bh); + if (num < *count) { + dquot_free_block_nodirty(inode, *count-num); + mark_inode_dirty(inode); + *count = num; + } + return ret_block; + +io_error: + *errp = -EIO; +out: + /* + * Undo the block allocation + */ + if (!performed_allocation) { + dquot_free_block_nodirty(inode, *count); + mark_inode_dirty(inode); + } + brelse(bitmap_bh); + return 0; +} + +ext2_fsblk_t ext2_new_block(struct inode *inode, unsigned long goal, int *errp) +{ + unsigned long count = 1; + + return ext2_new_blocks(inode, goal, &count, errp); +} + +#ifdef EXT2FS_DEBUG + +unsigned long ext2_count_free(struct buffer_head *map, unsigned int numchars) +{ + return numchars * BITS_PER_BYTE - memweight(map->b_data, numchars); +} + +#endif /* EXT2FS_DEBUG */ + +unsigned long ext2_count_free_blocks (struct super_block * sb) +{ + struct ext2_group_desc * desc; + unsigned long desc_count = 0; + int i; +#ifdef EXT2FS_DEBUG + unsigned long bitmap_count, x; + struct ext2_super_block *es; + + es = EXT2_SB(sb)->s_es; + desc_count = 0; + bitmap_count = 0; + desc = NULL; + for (i = 0; i < EXT2_SB(sb)->s_groups_count; i++) { + struct buffer_head *bitmap_bh; + desc = ext2_get_group_desc (sb, i, NULL); + if (!desc) + continue; + desc_count += le16_to_cpu(desc->bg_free_blocks_count); + bitmap_bh = read_block_bitmap(sb, i); + if (!bitmap_bh) + continue; + + x = ext2_count_free(bitmap_bh, sb->s_blocksize); + printk ("group %d: stored = %d, counted = %lu\n", + i, le16_to_cpu(desc->bg_free_blocks_count), x); + bitmap_count += x; + brelse(bitmap_bh); + } + printk("ext2_count_free_blocks: stored = %lu, computed = %lu, %lu\n", + (long)le32_to_cpu(es->s_free_blocks_count), + desc_count, bitmap_count); + return bitmap_count; +#else + for (i = 0; i < EXT2_SB(sb)->s_groups_count; i++) { + desc = ext2_get_group_desc (sb, i, NULL); + if (!desc) + continue; + desc_count += le16_to_cpu(desc->bg_free_blocks_count); + } + return desc_count; +#endif +} + +static inline int test_root(int a, int b) +{ + int num = b; + + while (a > num) + num *= b; + return num == a; +} + +static int ext2_group_sparse(int group) +{ + if (group <= 1) + return 1; + return (test_root(group, 3) || test_root(group, 5) || + test_root(group, 7)); +} + +/** + * ext2_bg_has_super - number of blocks used by the superblock in group + * @sb: superblock for filesystem + * @group: group number to check + * + * Return the number of blocks used by the superblock (primary or backup) + * in this group. Currently this will be only 0 or 1. + */ +int ext2_bg_has_super(struct super_block *sb, int group) +{ + if (EXT2_HAS_RO_COMPAT_FEATURE(sb,EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER)&& + !ext2_group_sparse(group)) + return 0; + return 1; +} + +/** + * ext2_bg_num_gdb - number of blocks used by the group table in group + * @sb: superblock for filesystem + * @group: group number to check + * + * Return the number of blocks used by the group descriptor table + * (primary or backup) in this group. In the future there may be a + * different number of descriptor blocks in each group. + */ +unsigned long ext2_bg_num_gdb(struct super_block *sb, int group) +{ + return ext2_bg_has_super(sb, group) ? EXT2_SB(sb)->s_gdb_count : 0; +} + diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c new file mode 100644 index 000000000..796b491e6 --- /dev/null +++ b/fs/ext2/dir.c @@ -0,0 +1,730 @@ +/* + * linux/fs/ext2/dir.c + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/fs/minix/dir.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * ext2 directory handling functions + * + * Big-endian to little-endian byte-swapping/bitmaps by + * David S. Miller (davem@caip.rutgers.edu), 1995 + * + * All code that works with directory layout had been switched to pagecache + * and moved here. AV + */ + +#include "ext2.h" +#include +#include +#include + +typedef struct ext2_dir_entry_2 ext2_dirent; + +/* + * Tests against MAX_REC_LEN etc were put in place for 64k block + * sizes; if that is not possible on this arch, we can skip + * those tests and speed things up. + */ +static inline unsigned ext2_rec_len_from_disk(__le16 dlen) +{ + unsigned len = le16_to_cpu(dlen); + +#if (PAGE_CACHE_SIZE >= 65536) + if (len == EXT2_MAX_REC_LEN) + return 1 << 16; +#endif + return len; +} + +static inline __le16 ext2_rec_len_to_disk(unsigned len) +{ +#if (PAGE_CACHE_SIZE >= 65536) + if (len == (1 << 16)) + return cpu_to_le16(EXT2_MAX_REC_LEN); + else + BUG_ON(len > (1 << 16)); +#endif + return cpu_to_le16(len); +} + +/* + * ext2 uses block-sized chunks. Arguably, sector-sized ones would be + * more robust, but we have what we have + */ +static inline unsigned ext2_chunk_size(struct inode *inode) +{ + return inode->i_sb->s_blocksize; +} + +static inline void ext2_put_page(struct page *page) +{ + kunmap(page); + page_cache_release(page); +} + +static inline unsigned long dir_pages(struct inode *inode) +{ + return (inode->i_size+PAGE_CACHE_SIZE-1)>>PAGE_CACHE_SHIFT; +} + +/* + * Return the offset into page `page_nr' of the last valid + * byte in that page, plus one. + */ +static unsigned +ext2_last_byte(struct inode *inode, unsigned long page_nr) +{ + unsigned last_byte = inode->i_size; + + last_byte -= page_nr << PAGE_CACHE_SHIFT; + if (last_byte > PAGE_CACHE_SIZE) + last_byte = PAGE_CACHE_SIZE; + return last_byte; +} + +static int ext2_commit_chunk(struct page *page, loff_t pos, unsigned len) +{ + struct address_space *mapping = page->mapping; + struct inode *dir = mapping->host; + int err = 0; + + dir->i_version++; + block_write_end(NULL, mapping, pos, len, len, page, NULL); + + if (pos+len > dir->i_size) { + i_size_write(dir, pos+len); + mark_inode_dirty(dir); + } + + if (IS_DIRSYNC(dir)) { + err = write_one_page(page, 1); + if (!err) + err = sync_inode_metadata(dir, 1); + } else { + unlock_page(page); + } + + return err; +} + +static void ext2_check_page(struct page *page, int quiet) +{ + struct inode *dir = page->mapping->host; + struct super_block *sb = dir->i_sb; + unsigned chunk_size = ext2_chunk_size(dir); + char *kaddr = page_address(page); + u32 max_inumber = le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count); + unsigned offs, rec_len; + unsigned limit = PAGE_CACHE_SIZE; + ext2_dirent *p; + char *error; + + if ((dir->i_size >> PAGE_CACHE_SHIFT) == page->index) { + limit = dir->i_size & ~PAGE_CACHE_MASK; + if (limit & (chunk_size - 1)) + goto Ebadsize; + if (!limit) + goto out; + } + for (offs = 0; offs <= limit - EXT2_DIR_REC_LEN(1); offs += rec_len) { + p = (ext2_dirent *)(kaddr + offs); + rec_len = ext2_rec_len_from_disk(p->rec_len); + + if (unlikely(rec_len < EXT2_DIR_REC_LEN(1))) + goto Eshort; + if (unlikely(rec_len & 3)) + goto Ealign; + if (unlikely(rec_len < EXT2_DIR_REC_LEN(p->name_len))) + goto Enamelen; + if (unlikely(((offs + rec_len - 1) ^ offs) & ~(chunk_size-1))) + goto Espan; + if (unlikely(le32_to_cpu(p->inode) > max_inumber)) + goto Einumber; + } + if (offs != limit) + goto Eend; +out: + SetPageChecked(page); + return; + + /* Too bad, we had an error */ + +Ebadsize: + if (!quiet) + ext2_error(sb, __func__, + "size of directory #%lu is not a multiple " + "of chunk size", dir->i_ino); + goto fail; +Eshort: + error = "rec_len is smaller than minimal"; + goto bad_entry; +Ealign: + error = "unaligned directory entry"; + goto bad_entry; +Enamelen: + error = "rec_len is too small for name_len"; + goto bad_entry; +Espan: + error = "directory entry across blocks"; + goto bad_entry; +Einumber: + error = "inode out of bounds"; +bad_entry: + if (!quiet) + ext2_error(sb, __func__, "bad entry in directory #%lu: : %s - " + "offset=%lu, inode=%lu, rec_len=%d, name_len=%d", + dir->i_ino, error, (page->index<inode), + rec_len, p->name_len); + goto fail; +Eend: + if (!quiet) { + p = (ext2_dirent *)(kaddr + offs); + ext2_error(sb, "ext2_check_page", + "entry in directory #%lu spans the page boundary" + "offset=%lu, inode=%lu", + dir->i_ino, (page->index<inode)); + } +fail: + SetPageChecked(page); + SetPageError(page); +} + +static struct page * ext2_get_page(struct inode *dir, unsigned long n, + int quiet) +{ + struct address_space *mapping = dir->i_mapping; + struct page *page = read_mapping_page(mapping, n, NULL); + if (!IS_ERR(page)) { + kmap(page); + if (!PageChecked(page)) + ext2_check_page(page, quiet); + if (PageError(page)) + goto fail; + } + return page; + +fail: + ext2_put_page(page); + return ERR_PTR(-EIO); +} + +/* + * NOTE! unlike strncmp, ext2_match returns 1 for success, 0 for failure. + * + * len <= EXT2_NAME_LEN and de != NULL are guaranteed by caller. + */ +static inline int ext2_match (int len, const char * const name, + struct ext2_dir_entry_2 * de) +{ + if (len != de->name_len) + return 0; + if (!de->inode) + return 0; + return !memcmp(name, de->name, len); +} + +/* + * p is at least 6 bytes before the end of page + */ +static inline ext2_dirent *ext2_next_entry(ext2_dirent *p) +{ + return (ext2_dirent *)((char *)p + + ext2_rec_len_from_disk(p->rec_len)); +} + +static inline unsigned +ext2_validate_entry(char *base, unsigned offset, unsigned mask) +{ + ext2_dirent *de = (ext2_dirent*)(base + offset); + ext2_dirent *p = (ext2_dirent*)(base + (offset&mask)); + while ((char*)p < (char*)de) { + if (p->rec_len == 0) + break; + p = ext2_next_entry(p); + } + return (char *)p - base; +} + +static unsigned char ext2_filetype_table[EXT2_FT_MAX] = { + [EXT2_FT_UNKNOWN] = DT_UNKNOWN, + [EXT2_FT_REG_FILE] = DT_REG, + [EXT2_FT_DIR] = DT_DIR, + [EXT2_FT_CHRDEV] = DT_CHR, + [EXT2_FT_BLKDEV] = DT_BLK, + [EXT2_FT_FIFO] = DT_FIFO, + [EXT2_FT_SOCK] = DT_SOCK, + [EXT2_FT_SYMLINK] = DT_LNK, +}; + +#define S_SHIFT 12 +static unsigned char ext2_type_by_mode[S_IFMT >> S_SHIFT] = { + [S_IFREG >> S_SHIFT] = EXT2_FT_REG_FILE, + [S_IFDIR >> S_SHIFT] = EXT2_FT_DIR, + [S_IFCHR >> S_SHIFT] = EXT2_FT_CHRDEV, + [S_IFBLK >> S_SHIFT] = EXT2_FT_BLKDEV, + [S_IFIFO >> S_SHIFT] = EXT2_FT_FIFO, + [S_IFSOCK >> S_SHIFT] = EXT2_FT_SOCK, + [S_IFLNK >> S_SHIFT] = EXT2_FT_SYMLINK, +}; + +static inline void ext2_set_de_type(ext2_dirent *de, struct inode *inode) +{ + umode_t mode = inode->i_mode; + if (EXT2_HAS_INCOMPAT_FEATURE(inode->i_sb, EXT2_FEATURE_INCOMPAT_FILETYPE)) + de->file_type = ext2_type_by_mode[(mode & S_IFMT)>>S_SHIFT]; + else + de->file_type = 0; +} + +static int +ext2_readdir(struct file *file, struct dir_context *ctx) +{ + loff_t pos = ctx->pos; + struct inode *inode = file_inode(file); + struct super_block *sb = inode->i_sb; + unsigned int offset = pos & ~PAGE_CACHE_MASK; + unsigned long n = pos >> PAGE_CACHE_SHIFT; + unsigned long npages = dir_pages(inode); + unsigned chunk_mask = ~(ext2_chunk_size(inode)-1); + unsigned char *types = NULL; + int need_revalidate = file->f_version != inode->i_version; + + if (pos > inode->i_size - EXT2_DIR_REC_LEN(1)) + return 0; + + if (EXT2_HAS_INCOMPAT_FEATURE(sb, EXT2_FEATURE_INCOMPAT_FILETYPE)) + types = ext2_filetype_table; + + for ( ; n < npages; n++, offset = 0) { + char *kaddr, *limit; + ext2_dirent *de; + struct page *page = ext2_get_page(inode, n, 0); + + if (IS_ERR(page)) { + ext2_error(sb, __func__, + "bad page in #%lu", + inode->i_ino); + ctx->pos += PAGE_CACHE_SIZE - offset; + return PTR_ERR(page); + } + kaddr = page_address(page); + if (unlikely(need_revalidate)) { + if (offset) { + offset = ext2_validate_entry(kaddr, offset, chunk_mask); + ctx->pos = (n<f_version = inode->i_version; + need_revalidate = 0; + } + de = (ext2_dirent *)(kaddr+offset); + limit = kaddr + ext2_last_byte(inode, n) - EXT2_DIR_REC_LEN(1); + for ( ;(char*)de <= limit; de = ext2_next_entry(de)) { + if (de->rec_len == 0) { + ext2_error(sb, __func__, + "zero-length directory entry"); + ext2_put_page(page); + return -EIO; + } + if (de->inode) { + unsigned char d_type = DT_UNKNOWN; + + if (types && de->file_type < EXT2_FT_MAX) + d_type = types[de->file_type]; + + if (!dir_emit(ctx, de->name, de->name_len, + le32_to_cpu(de->inode), + d_type)) { + ext2_put_page(page); + return 0; + } + } + ctx->pos += ext2_rec_len_from_disk(de->rec_len); + } + ext2_put_page(page); + } + return 0; +} + +/* + * ext2_find_entry() + * + * finds an entry in the specified directory with the wanted name. It + * returns the page in which the entry was found (as a parameter - res_page), + * and the entry itself. Page is returned mapped and unlocked. + * Entry is guaranteed to be valid. + */ +struct ext2_dir_entry_2 *ext2_find_entry (struct inode * dir, + struct qstr *child, struct page ** res_page) +{ + const char *name = child->name; + int namelen = child->len; + unsigned reclen = EXT2_DIR_REC_LEN(namelen); + unsigned long start, n; + unsigned long npages = dir_pages(dir); + struct page *page = NULL; + struct ext2_inode_info *ei = EXT2_I(dir); + ext2_dirent * de; + int dir_has_error = 0; + + if (npages == 0) + goto out; + + /* OFFSET_CACHE */ + *res_page = NULL; + + start = ei->i_dir_start_lookup; + if (start >= npages) + start = 0; + n = start; + do { + char *kaddr; + page = ext2_get_page(dir, n, dir_has_error); + if (!IS_ERR(page)) { + kaddr = page_address(page); + de = (ext2_dirent *) kaddr; + kaddr += ext2_last_byte(dir, n) - reclen; + while ((char *) de <= kaddr) { + if (de->rec_len == 0) { + ext2_error(dir->i_sb, __func__, + "zero-length directory entry"); + ext2_put_page(page); + goto out; + } + if (ext2_match (namelen, name, de)) + goto found; + de = ext2_next_entry(de); + } + ext2_put_page(page); + } else + dir_has_error = 1; + + if (++n >= npages) + n = 0; + /* next page is past the blocks we've got */ + if (unlikely(n > (dir->i_blocks >> (PAGE_CACHE_SHIFT - 9)))) { + ext2_error(dir->i_sb, __func__, + "dir %lu size %lld exceeds block count %llu", + dir->i_ino, dir->i_size, + (unsigned long long)dir->i_blocks); + goto out; + } + } while (n != start); +out: + return NULL; + +found: + *res_page = page; + ei->i_dir_start_lookup = n; + return de; +} + +struct ext2_dir_entry_2 * ext2_dotdot (struct inode *dir, struct page **p) +{ + struct page *page = ext2_get_page(dir, 0, 0); + ext2_dirent *de = NULL; + + if (!IS_ERR(page)) { + de = ext2_next_entry((ext2_dirent *) page_address(page)); + *p = page; + } + return de; +} + +ino_t ext2_inode_by_name(struct inode *dir, struct qstr *child) +{ + ino_t res = 0; + struct ext2_dir_entry_2 *de; + struct page *page; + + de = ext2_find_entry (dir, child, &page); + if (de) { + res = le32_to_cpu(de->inode); + ext2_put_page(page); + } + return res; +} + +static int ext2_prepare_chunk(struct page *page, loff_t pos, unsigned len) +{ + return __block_write_begin(page, pos, len, ext2_get_block); +} + +/* Releases the page */ +void ext2_set_link(struct inode *dir, struct ext2_dir_entry_2 *de, + struct page *page, struct inode *inode, int update_times) +{ + loff_t pos = page_offset(page) + + (char *) de - (char *) page_address(page); + unsigned len = ext2_rec_len_from_disk(de->rec_len); + int err; + + lock_page(page); + err = ext2_prepare_chunk(page, pos, len); + BUG_ON(err); + de->inode = cpu_to_le32(inode->i_ino); + ext2_set_de_type(de, inode); + err = ext2_commit_chunk(page, pos, len); + ext2_put_page(page); + if (update_times) + dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC; + EXT2_I(dir)->i_flags &= ~EXT2_BTREE_FL; + mark_inode_dirty(dir); +} + +/* + * Parent is locked. + */ +int ext2_add_link (struct dentry *dentry, struct inode *inode) +{ + struct inode *dir = d_inode(dentry->d_parent); + const char *name = dentry->d_name.name; + int namelen = dentry->d_name.len; + unsigned chunk_size = ext2_chunk_size(dir); + unsigned reclen = EXT2_DIR_REC_LEN(namelen); + unsigned short rec_len, name_len; + struct page *page = NULL; + ext2_dirent * de; + unsigned long npages = dir_pages(dir); + unsigned long n; + char *kaddr; + loff_t pos; + int err; + + /* + * We take care of directory expansion in the same loop. + * This code plays outside i_size, so it locks the page + * to protect that region. + */ + for (n = 0; n <= npages; n++) { + char *dir_end; + + page = ext2_get_page(dir, n, 0); + err = PTR_ERR(page); + if (IS_ERR(page)) + goto out; + lock_page(page); + kaddr = page_address(page); + dir_end = kaddr + ext2_last_byte(dir, n); + de = (ext2_dirent *)kaddr; + kaddr += PAGE_CACHE_SIZE - reclen; + while ((char *)de <= kaddr) { + if ((char *)de == dir_end) { + /* We hit i_size */ + name_len = 0; + rec_len = chunk_size; + de->rec_len = ext2_rec_len_to_disk(chunk_size); + de->inode = 0; + goto got_it; + } + if (de->rec_len == 0) { + ext2_error(dir->i_sb, __func__, + "zero-length directory entry"); + err = -EIO; + goto out_unlock; + } + err = -EEXIST; + if (ext2_match (namelen, name, de)) + goto out_unlock; + name_len = EXT2_DIR_REC_LEN(de->name_len); + rec_len = ext2_rec_len_from_disk(de->rec_len); + if (!de->inode && rec_len >= reclen) + goto got_it; + if (rec_len >= name_len + reclen) + goto got_it; + de = (ext2_dirent *) ((char *) de + rec_len); + } + unlock_page(page); + ext2_put_page(page); + } + BUG(); + return -EINVAL; + +got_it: + pos = page_offset(page) + + (char*)de - (char*)page_address(page); + err = ext2_prepare_chunk(page, pos, rec_len); + if (err) + goto out_unlock; + if (de->inode) { + ext2_dirent *de1 = (ext2_dirent *) ((char *) de + name_len); + de1->rec_len = ext2_rec_len_to_disk(rec_len - name_len); + de->rec_len = ext2_rec_len_to_disk(name_len); + de = de1; + } + de->name_len = namelen; + memcpy(de->name, name, namelen); + de->inode = cpu_to_le32(inode->i_ino); + ext2_set_de_type (de, inode); + err = ext2_commit_chunk(page, pos, rec_len); + dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC; + EXT2_I(dir)->i_flags &= ~EXT2_BTREE_FL; + mark_inode_dirty(dir); + /* OFFSET_CACHE */ +out_put: + ext2_put_page(page); +out: + return err; +out_unlock: + unlock_page(page); + goto out_put; +} + +/* + * ext2_delete_entry deletes a directory entry by merging it with the + * previous entry. Page is up-to-date. Releases the page. + */ +int ext2_delete_entry (struct ext2_dir_entry_2 * dir, struct page * page ) +{ + struct inode *inode = page->mapping->host; + char *kaddr = page_address(page); + unsigned from = ((char*)dir - kaddr) & ~(ext2_chunk_size(inode)-1); + unsigned to = ((char *)dir - kaddr) + + ext2_rec_len_from_disk(dir->rec_len); + loff_t pos; + ext2_dirent * pde = NULL; + ext2_dirent * de = (ext2_dirent *) (kaddr + from); + int err; + + while ((char*)de < (char*)dir) { + if (de->rec_len == 0) { + ext2_error(inode->i_sb, __func__, + "zero-length directory entry"); + err = -EIO; + goto out; + } + pde = de; + de = ext2_next_entry(de); + } + if (pde) + from = (char*)pde - (char*)page_address(page); + pos = page_offset(page) + from; + lock_page(page); + err = ext2_prepare_chunk(page, pos, to - from); + BUG_ON(err); + if (pde) + pde->rec_len = ext2_rec_len_to_disk(to - from); + dir->inode = 0; + err = ext2_commit_chunk(page, pos, to - from); + inode->i_ctime = inode->i_mtime = CURRENT_TIME_SEC; + EXT2_I(inode)->i_flags &= ~EXT2_BTREE_FL; + mark_inode_dirty(inode); +out: + ext2_put_page(page); + return err; +} + +/* + * Set the first fragment of directory. + */ +int ext2_make_empty(struct inode *inode, struct inode *parent) +{ + struct page *page = grab_cache_page(inode->i_mapping, 0); + unsigned chunk_size = ext2_chunk_size(inode); + struct ext2_dir_entry_2 * de; + int err; + void *kaddr; + + if (!page) + return -ENOMEM; + + err = ext2_prepare_chunk(page, 0, chunk_size); + if (err) { + unlock_page(page); + goto fail; + } + kaddr = kmap_atomic(page); + memset(kaddr, 0, chunk_size); + de = (struct ext2_dir_entry_2 *)kaddr; + de->name_len = 1; + de->rec_len = ext2_rec_len_to_disk(EXT2_DIR_REC_LEN(1)); + memcpy (de->name, ".\0\0", 4); + de->inode = cpu_to_le32(inode->i_ino); + ext2_set_de_type (de, inode); + + de = (struct ext2_dir_entry_2 *)(kaddr + EXT2_DIR_REC_LEN(1)); + de->name_len = 2; + de->rec_len = ext2_rec_len_to_disk(chunk_size - EXT2_DIR_REC_LEN(1)); + de->inode = cpu_to_le32(parent->i_ino); + memcpy (de->name, "..\0", 4); + ext2_set_de_type (de, inode); + kunmap_atomic(kaddr); + err = ext2_commit_chunk(page, 0, chunk_size); +fail: + page_cache_release(page); + return err; +} + +/* + * routine to check that the specified directory is empty (for rmdir) + */ +int ext2_empty_dir (struct inode * inode) +{ + struct page *page = NULL; + unsigned long i, npages = dir_pages(inode); + int dir_has_error = 0; + + for (i = 0; i < npages; i++) { + char *kaddr; + ext2_dirent * de; + page = ext2_get_page(inode, i, dir_has_error); + + if (IS_ERR(page)) { + dir_has_error = 1; + continue; + } + + kaddr = page_address(page); + de = (ext2_dirent *)kaddr; + kaddr += ext2_last_byte(inode, i) - EXT2_DIR_REC_LEN(1); + + while ((char *)de <= kaddr) { + if (de->rec_len == 0) { + ext2_error(inode->i_sb, __func__, + "zero-length directory entry"); + printk("kaddr=%p, de=%p\n", kaddr, de); + goto not_empty; + } + if (de->inode != 0) { + /* check for . and .. */ + if (de->name[0] != '.') + goto not_empty; + if (de->name_len > 2) + goto not_empty; + if (de->name_len < 2) { + if (de->inode != + cpu_to_le32(inode->i_ino)) + goto not_empty; + } else if (de->name[1] != '.') + goto not_empty; + } + de = ext2_next_entry(de); + } + ext2_put_page(page); + } + return 1; + +not_empty: + ext2_put_page(page); + return 0; +} + +const struct file_operations ext2_dir_operations = { + .llseek = generic_file_llseek, + .read = generic_read_dir, + .iterate = ext2_readdir, + .unlocked_ioctl = ext2_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = ext2_compat_ioctl, +#endif + .fsync = ext2_fsync, +}; diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h new file mode 100644 index 000000000..8d15febd0 --- /dev/null +++ b/fs/ext2/ext2.h @@ -0,0 +1,820 @@ +/* + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/include/linux/minix_fs.h + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ +#include +#include +#include +#include +#include + +/* XXX Here for now... not interested in restructing headers JUST now */ + +/* data type for block offset of block group */ +typedef int ext2_grpblk_t; + +/* data type for filesystem-wide blocks number */ +typedef unsigned long ext2_fsblk_t; + +#define E2FSBLK "%lu" + +struct ext2_reserve_window { + ext2_fsblk_t _rsv_start; /* First byte reserved */ + ext2_fsblk_t _rsv_end; /* Last byte reserved or 0 */ +}; + +struct ext2_reserve_window_node { + struct rb_node rsv_node; + __u32 rsv_goal_size; + __u32 rsv_alloc_hit; + struct ext2_reserve_window rsv_window; +}; + +struct ext2_block_alloc_info { + /* information about reservation window */ + struct ext2_reserve_window_node rsv_window_node; + /* + * was i_next_alloc_block in ext2_inode_info + * is the logical (file-relative) number of the + * most-recently-allocated block in this file. + * We use this for detecting linearly ascending allocation requests. + */ + __u32 last_alloc_logical_block; + /* + * Was i_next_alloc_goal in ext2_inode_info + * is the *physical* companion to i_next_alloc_block. + * it the the physical block number of the block which was most-recentl + * allocated to this file. This give us the goal (target) for the next + * allocation when we detect linearly ascending requests. + */ + ext2_fsblk_t last_alloc_physical_block; +}; + +#define rsv_start rsv_window._rsv_start +#define rsv_end rsv_window._rsv_end + +/* + * second extended-fs super-block data in memory + */ +struct ext2_sb_info { + unsigned long s_frag_size; /* Size of a fragment in bytes */ + unsigned long s_frags_per_block;/* Number of fragments per block */ + unsigned long s_inodes_per_block;/* Number of inodes per block */ + unsigned long s_frags_per_group;/* Number of fragments in a group */ + unsigned long s_blocks_per_group;/* Number of blocks in a group */ + unsigned long s_inodes_per_group;/* Number of inodes in a group */ + unsigned long s_itb_per_group; /* Number of inode table blocks per group */ + unsigned long s_gdb_count; /* Number of group descriptor blocks */ + unsigned long s_desc_per_block; /* Number of group descriptors per block */ + unsigned long s_groups_count; /* Number of groups in the fs */ + unsigned long s_overhead_last; /* Last calculated overhead */ + unsigned long s_blocks_last; /* Last seen block count */ + struct buffer_head * s_sbh; /* Buffer containing the super block */ + struct ext2_super_block * s_es; /* Pointer to the super block in the buffer */ + struct buffer_head ** s_group_desc; + unsigned long s_mount_opt; + unsigned long s_sb_block; + kuid_t s_resuid; + kgid_t s_resgid; + unsigned short s_mount_state; + unsigned short s_pad; + int s_addr_per_block_bits; + int s_desc_per_block_bits; + int s_inode_size; + int s_first_ino; + spinlock_t s_next_gen_lock; + u32 s_next_generation; + unsigned long s_dir_count; + u8 *s_debts; + struct percpu_counter s_freeblocks_counter; + struct percpu_counter s_freeinodes_counter; + struct percpu_counter s_dirs_counter; + struct blockgroup_lock *s_blockgroup_lock; + /* root of the per fs reservation window tree */ + spinlock_t s_rsv_window_lock; + struct rb_root s_rsv_window_root; + struct ext2_reserve_window_node s_rsv_window_head; + /* + * s_lock protects against concurrent modifications of s_mount_state, + * s_blocks_last, s_overhead_last and the content of superblock's + * buffer pointed to by sbi->s_es. + * + * Note: It is used in ext2_show_options() to provide a consistent view + * of the mount options. + */ + spinlock_t s_lock; +}; + +static inline spinlock_t * +sb_bgl_lock(struct ext2_sb_info *sbi, unsigned int block_group) +{ + return bgl_lock_ptr(sbi->s_blockgroup_lock, block_group); +} + +/* + * Define EXT2FS_DEBUG to produce debug messages + */ +#undef EXT2FS_DEBUG + +/* + * Define EXT2_RESERVATION to reserve data blocks for expanding files + */ +#define EXT2_DEFAULT_RESERVE_BLOCKS 8 +/*max window size: 1024(direct blocks) + 3([t,d]indirect blocks) */ +#define EXT2_MAX_RESERVE_BLOCKS 1027 +#define EXT2_RESERVE_WINDOW_NOT_ALLOCATED 0 +/* + * The second extended file system version + */ +#define EXT2FS_DATE "95/08/09" +#define EXT2FS_VERSION "0.5b" + +/* + * Debug code + */ +#ifdef EXT2FS_DEBUG +# define ext2_debug(f, a...) { \ + printk ("EXT2-fs DEBUG (%s, %d): %s:", \ + __FILE__, __LINE__, __func__); \ + printk (f, ## a); \ + } +#else +# define ext2_debug(f, a...) /**/ +#endif + +/* + * Special inode numbers + */ +#define EXT2_BAD_INO 1 /* Bad blocks inode */ +#define EXT2_ROOT_INO 2 /* Root inode */ +#define EXT2_BOOT_LOADER_INO 5 /* Boot loader inode */ +#define EXT2_UNDEL_DIR_INO 6 /* Undelete directory inode */ + +/* First non-reserved inode for old ext2 filesystems */ +#define EXT2_GOOD_OLD_FIRST_INO 11 + +static inline struct ext2_sb_info *EXT2_SB(struct super_block *sb) +{ + return sb->s_fs_info; +} + +/* + * Macro-instructions used to manage several block sizes + */ +#define EXT2_MIN_BLOCK_SIZE 1024 +#define EXT2_MAX_BLOCK_SIZE 4096 +#define EXT2_MIN_BLOCK_LOG_SIZE 10 +#define EXT2_BLOCK_SIZE(s) ((s)->s_blocksize) +#define EXT2_ADDR_PER_BLOCK(s) (EXT2_BLOCK_SIZE(s) / sizeof (__u32)) +#define EXT2_BLOCK_SIZE_BITS(s) ((s)->s_blocksize_bits) +#define EXT2_ADDR_PER_BLOCK_BITS(s) (EXT2_SB(s)->s_addr_per_block_bits) +#define EXT2_INODE_SIZE(s) (EXT2_SB(s)->s_inode_size) +#define EXT2_FIRST_INO(s) (EXT2_SB(s)->s_first_ino) + +/* + * Macro-instructions used to manage fragments + */ +#define EXT2_MIN_FRAG_SIZE 1024 +#define EXT2_MAX_FRAG_SIZE 4096 +#define EXT2_MIN_FRAG_LOG_SIZE 10 +#define EXT2_FRAG_SIZE(s) (EXT2_SB(s)->s_frag_size) +#define EXT2_FRAGS_PER_BLOCK(s) (EXT2_SB(s)->s_frags_per_block) + +/* + * Structure of a blocks group descriptor + */ +struct ext2_group_desc +{ + __le32 bg_block_bitmap; /* Blocks bitmap block */ + __le32 bg_inode_bitmap; /* Inodes bitmap block */ + __le32 bg_inode_table; /* Inodes table block */ + __le16 bg_free_blocks_count; /* Free blocks count */ + __le16 bg_free_inodes_count; /* Free inodes count */ + __le16 bg_used_dirs_count; /* Directories count */ + __le16 bg_pad; + __le32 bg_reserved[3]; +}; + +/* + * Macro-instructions used to manage group descriptors + */ +#define EXT2_BLOCKS_PER_GROUP(s) (EXT2_SB(s)->s_blocks_per_group) +#define EXT2_DESC_PER_BLOCK(s) (EXT2_SB(s)->s_desc_per_block) +#define EXT2_INODES_PER_GROUP(s) (EXT2_SB(s)->s_inodes_per_group) +#define EXT2_DESC_PER_BLOCK_BITS(s) (EXT2_SB(s)->s_desc_per_block_bits) + +/* + * Constants relative to the data blocks + */ +#define EXT2_NDIR_BLOCKS 12 +#define EXT2_IND_BLOCK EXT2_NDIR_BLOCKS +#define EXT2_DIND_BLOCK (EXT2_IND_BLOCK + 1) +#define EXT2_TIND_BLOCK (EXT2_DIND_BLOCK + 1) +#define EXT2_N_BLOCKS (EXT2_TIND_BLOCK + 1) + +/* + * Inode flags (GETFLAGS/SETFLAGS) + */ +#define EXT2_SECRM_FL FS_SECRM_FL /* Secure deletion */ +#define EXT2_UNRM_FL FS_UNRM_FL /* Undelete */ +#define EXT2_COMPR_FL FS_COMPR_FL /* Compress file */ +#define EXT2_SYNC_FL FS_SYNC_FL /* Synchronous updates */ +#define EXT2_IMMUTABLE_FL FS_IMMUTABLE_FL /* Immutable file */ +#define EXT2_APPEND_FL FS_APPEND_FL /* writes to file may only append */ +#define EXT2_NODUMP_FL FS_NODUMP_FL /* do not dump file */ +#define EXT2_NOATIME_FL FS_NOATIME_FL /* do not update atime */ +/* Reserved for compression usage... */ +#define EXT2_DIRTY_FL FS_DIRTY_FL +#define EXT2_COMPRBLK_FL FS_COMPRBLK_FL /* One or more compressed clusters */ +#define EXT2_NOCOMP_FL FS_NOCOMP_FL /* Don't compress */ +#define EXT2_ECOMPR_FL FS_ECOMPR_FL /* Compression error */ +/* End compression flags --- maybe not all used */ +#define EXT2_BTREE_FL FS_BTREE_FL /* btree format dir */ +#define EXT2_INDEX_FL FS_INDEX_FL /* hash-indexed directory */ +#define EXT2_IMAGIC_FL FS_IMAGIC_FL /* AFS directory */ +#define EXT2_JOURNAL_DATA_FL FS_JOURNAL_DATA_FL /* Reserved for ext3 */ +#define EXT2_NOTAIL_FL FS_NOTAIL_FL /* file tail should not be merged */ +#define EXT2_DIRSYNC_FL FS_DIRSYNC_FL /* dirsync behaviour (directories only) */ +#define EXT2_TOPDIR_FL FS_TOPDIR_FL /* Top of directory hierarchies*/ +#define EXT2_RESERVED_FL FS_RESERVED_FL /* reserved for ext2 lib */ + +#define EXT2_FL_USER_VISIBLE FS_FL_USER_VISIBLE /* User visible flags */ +#define EXT2_FL_USER_MODIFIABLE FS_FL_USER_MODIFIABLE /* User modifiable flags */ + +/* Flags that should be inherited by new inodes from their parent. */ +#define EXT2_FL_INHERITED (EXT2_SECRM_FL | EXT2_UNRM_FL | EXT2_COMPR_FL |\ + EXT2_SYNC_FL | EXT2_NODUMP_FL |\ + EXT2_NOATIME_FL | EXT2_COMPRBLK_FL |\ + EXT2_NOCOMP_FL | EXT2_JOURNAL_DATA_FL |\ + EXT2_NOTAIL_FL | EXT2_DIRSYNC_FL) + +/* Flags that are appropriate for regular files (all but dir-specific ones). */ +#define EXT2_REG_FLMASK (~(EXT2_DIRSYNC_FL | EXT2_TOPDIR_FL)) + +/* Flags that are appropriate for non-directories/regular files. */ +#define EXT2_OTHER_FLMASK (EXT2_NODUMP_FL | EXT2_NOATIME_FL) + +/* Mask out flags that are inappropriate for the given type of inode. */ +static inline __u32 ext2_mask_flags(umode_t mode, __u32 flags) +{ + if (S_ISDIR(mode)) + return flags; + else if (S_ISREG(mode)) + return flags & EXT2_REG_FLMASK; + else + return flags & EXT2_OTHER_FLMASK; +} + +/* + * ioctl commands + */ +#define EXT2_IOC_GETFLAGS FS_IOC_GETFLAGS +#define EXT2_IOC_SETFLAGS FS_IOC_SETFLAGS +#define EXT2_IOC_GETVERSION FS_IOC_GETVERSION +#define EXT2_IOC_SETVERSION FS_IOC_SETVERSION +#define EXT2_IOC_GETRSVSZ _IOR('f', 5, long) +#define EXT2_IOC_SETRSVSZ _IOW('f', 6, long) + +/* + * ioctl commands in 32 bit emulation + */ +#define EXT2_IOC32_GETFLAGS FS_IOC32_GETFLAGS +#define EXT2_IOC32_SETFLAGS FS_IOC32_SETFLAGS +#define EXT2_IOC32_GETVERSION FS_IOC32_GETVERSION +#define EXT2_IOC32_SETVERSION FS_IOC32_SETVERSION + +/* + * Structure of an inode on the disk + */ +struct ext2_inode { + __le16 i_mode; /* File mode */ + __le16 i_uid; /* Low 16 bits of Owner Uid */ + __le32 i_size; /* Size in bytes */ + __le32 i_atime; /* Access time */ + __le32 i_ctime; /* Creation time */ + __le32 i_mtime; /* Modification time */ + __le32 i_dtime; /* Deletion Time */ + __le16 i_gid; /* Low 16 bits of Group Id */ + __le16 i_links_count; /* Links count */ + __le32 i_blocks; /* Blocks count */ + __le32 i_flags; /* File flags */ + union { + struct { + __le32 l_i_reserved1; + } linux1; + struct { + __le32 h_i_translator; + } hurd1; + struct { + __le32 m_i_reserved1; + } masix1; + } osd1; /* OS dependent 1 */ + __le32 i_block[EXT2_N_BLOCKS];/* Pointers to blocks */ + __le32 i_generation; /* File version (for NFS) */ + __le32 i_file_acl; /* File ACL */ + __le32 i_dir_acl; /* Directory ACL */ + __le32 i_faddr; /* Fragment address */ + union { + struct { + __u8 l_i_frag; /* Fragment number */ + __u8 l_i_fsize; /* Fragment size */ + __u16 i_pad1; + __le16 l_i_uid_high; /* these 2 fields */ + __le16 l_i_gid_high; /* were reserved2[0] */ + __u32 l_i_reserved2; + } linux2; + struct { + __u8 h_i_frag; /* Fragment number */ + __u8 h_i_fsize; /* Fragment size */ + __le16 h_i_mode_high; + __le16 h_i_uid_high; + __le16 h_i_gid_high; + __le32 h_i_author; + } hurd2; + struct { + __u8 m_i_frag; /* Fragment number */ + __u8 m_i_fsize; /* Fragment size */ + __u16 m_pad1; + __u32 m_i_reserved2[2]; + } masix2; + } osd2; /* OS dependent 2 */ +}; + +#define i_size_high i_dir_acl + +#define i_reserved1 osd1.linux1.l_i_reserved1 +#define i_frag osd2.linux2.l_i_frag +#define i_fsize osd2.linux2.l_i_fsize +#define i_uid_low i_uid +#define i_gid_low i_gid +#define i_uid_high osd2.linux2.l_i_uid_high +#define i_gid_high osd2.linux2.l_i_gid_high +#define i_reserved2 osd2.linux2.l_i_reserved2 + +/* + * File system states + */ +#define EXT2_VALID_FS 0x0001 /* Unmounted cleanly */ +#define EXT2_ERROR_FS 0x0002 /* Errors detected */ + +/* + * Mount flags + */ +#define EXT2_MOUNT_CHECK 0x000001 /* Do mount-time checks */ +#define EXT2_MOUNT_OLDALLOC 0x000002 /* Don't use the new Orlov allocator */ +#define EXT2_MOUNT_GRPID 0x000004 /* Create files with directory's group */ +#define EXT2_MOUNT_DEBUG 0x000008 /* Some debugging messages */ +#define EXT2_MOUNT_ERRORS_CONT 0x000010 /* Continue on errors */ +#define EXT2_MOUNT_ERRORS_RO 0x000020 /* Remount fs ro on errors */ +#define EXT2_MOUNT_ERRORS_PANIC 0x000040 /* Panic on errors */ +#define EXT2_MOUNT_MINIX_DF 0x000080 /* Mimics the Minix statfs */ +#define EXT2_MOUNT_NOBH 0x000100 /* No buffer_heads */ +#define EXT2_MOUNT_NO_UID32 0x000200 /* Disable 32-bit UIDs */ +#define EXT2_MOUNT_XATTR_USER 0x004000 /* Extended user attributes */ +#define EXT2_MOUNT_POSIX_ACL 0x008000 /* POSIX Access Control Lists */ +#define EXT2_MOUNT_XIP 0x010000 /* Obsolete, use DAX */ +#define EXT2_MOUNT_USRQUOTA 0x020000 /* user quota */ +#define EXT2_MOUNT_GRPQUOTA 0x040000 /* group quota */ +#define EXT2_MOUNT_RESERVATION 0x080000 /* Preallocation */ +#ifdef CONFIG_FS_DAX +#define EXT2_MOUNT_DAX 0x100000 /* Direct Access */ +#else +#define EXT2_MOUNT_DAX 0 +#endif + + +#define clear_opt(o, opt) o &= ~EXT2_MOUNT_##opt +#define set_opt(o, opt) o |= EXT2_MOUNT_##opt +#define test_opt(sb, opt) (EXT2_SB(sb)->s_mount_opt & \ + EXT2_MOUNT_##opt) +/* + * Maximal mount counts between two filesystem checks + */ +#define EXT2_DFL_MAX_MNT_COUNT 20 /* Allow 20 mounts */ +#define EXT2_DFL_CHECKINTERVAL 0 /* Don't use interval check */ + +/* + * Behaviour when detecting errors + */ +#define EXT2_ERRORS_CONTINUE 1 /* Continue execution */ +#define EXT2_ERRORS_RO 2 /* Remount fs read-only */ +#define EXT2_ERRORS_PANIC 3 /* Panic */ +#define EXT2_ERRORS_DEFAULT EXT2_ERRORS_CONTINUE + +/* + * Structure of the super block + */ +struct ext2_super_block { + __le32 s_inodes_count; /* Inodes count */ + __le32 s_blocks_count; /* Blocks count */ + __le32 s_r_blocks_count; /* Reserved blocks count */ + __le32 s_free_blocks_count; /* Free blocks count */ + __le32 s_free_inodes_count; /* Free inodes count */ + __le32 s_first_data_block; /* First Data Block */ + __le32 s_log_block_size; /* Block size */ + __le32 s_log_frag_size; /* Fragment size */ + __le32 s_blocks_per_group; /* # Blocks per group */ + __le32 s_frags_per_group; /* # Fragments per group */ + __le32 s_inodes_per_group; /* # Inodes per group */ + __le32 s_mtime; /* Mount time */ + __le32 s_wtime; /* Write time */ + __le16 s_mnt_count; /* Mount count */ + __le16 s_max_mnt_count; /* Maximal mount count */ + __le16 s_magic; /* Magic signature */ + __le16 s_state; /* File system state */ + __le16 s_errors; /* Behaviour when detecting errors */ + __le16 s_minor_rev_level; /* minor revision level */ + __le32 s_lastcheck; /* time of last check */ + __le32 s_checkinterval; /* max. time between checks */ + __le32 s_creator_os; /* OS */ + __le32 s_rev_level; /* Revision level */ + __le16 s_def_resuid; /* Default uid for reserved blocks */ + __le16 s_def_resgid; /* Default gid for reserved blocks */ + /* + * These fields are for EXT2_DYNAMIC_REV superblocks only. + * + * Note: the difference between the compatible feature set and + * the incompatible feature set is that if there is a bit set + * in the incompatible feature set that the kernel doesn't + * know about, it should refuse to mount the filesystem. + * + * e2fsck's requirements are more strict; if it doesn't know + * about a feature in either the compatible or incompatible + * feature set, it must abort and not try to meddle with + * things it doesn't understand... + */ + __le32 s_first_ino; /* First non-reserved inode */ + __le16 s_inode_size; /* size of inode structure */ + __le16 s_block_group_nr; /* block group # of this superblock */ + __le32 s_feature_compat; /* compatible feature set */ + __le32 s_feature_incompat; /* incompatible feature set */ + __le32 s_feature_ro_compat; /* readonly-compatible feature set */ + __u8 s_uuid[16]; /* 128-bit uuid for volume */ + char s_volume_name[16]; /* volume name */ + char s_last_mounted[64]; /* directory where last mounted */ + __le32 s_algorithm_usage_bitmap; /* For compression */ + /* + * Performance hints. Directory preallocation should only + * happen if the EXT2_COMPAT_PREALLOC flag is on. + */ + __u8 s_prealloc_blocks; /* Nr of blocks to try to preallocate*/ + __u8 s_prealloc_dir_blocks; /* Nr to preallocate for dirs */ + __u16 s_padding1; + /* + * Journaling support valid if EXT3_FEATURE_COMPAT_HAS_JOURNAL set. + */ + __u8 s_journal_uuid[16]; /* uuid of journal superblock */ + __u32 s_journal_inum; /* inode number of journal file */ + __u32 s_journal_dev; /* device number of journal file */ + __u32 s_last_orphan; /* start of list of inodes to delete */ + __u32 s_hash_seed[4]; /* HTREE hash seed */ + __u8 s_def_hash_version; /* Default hash version to use */ + __u8 s_reserved_char_pad; + __u16 s_reserved_word_pad; + __le32 s_default_mount_opts; + __le32 s_first_meta_bg; /* First metablock block group */ + __u32 s_reserved[190]; /* Padding to the end of the block */ +}; + +/* + * Codes for operating systems + */ +#define EXT2_OS_LINUX 0 +#define EXT2_OS_HURD 1 +#define EXT2_OS_MASIX 2 +#define EXT2_OS_FREEBSD 3 +#define EXT2_OS_LITES 4 + +/* + * Revision levels + */ +#define EXT2_GOOD_OLD_REV 0 /* The good old (original) format */ +#define EXT2_DYNAMIC_REV 1 /* V2 format w/ dynamic inode sizes */ + +#define EXT2_CURRENT_REV EXT2_GOOD_OLD_REV +#define EXT2_MAX_SUPP_REV EXT2_DYNAMIC_REV + +#define EXT2_GOOD_OLD_INODE_SIZE 128 + +/* + * Feature set definitions + */ + +#define EXT2_HAS_COMPAT_FEATURE(sb,mask) \ + ( EXT2_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask) ) +#define EXT2_HAS_RO_COMPAT_FEATURE(sb,mask) \ + ( EXT2_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask) ) +#define EXT2_HAS_INCOMPAT_FEATURE(sb,mask) \ + ( EXT2_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask) ) +#define EXT2_SET_COMPAT_FEATURE(sb,mask) \ + EXT2_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask) +#define EXT2_SET_RO_COMPAT_FEATURE(sb,mask) \ + EXT2_SB(sb)->s_es->s_feature_ro_compat |= cpu_to_le32(mask) +#define EXT2_SET_INCOMPAT_FEATURE(sb,mask) \ + EXT2_SB(sb)->s_es->s_feature_incompat |= cpu_to_le32(mask) +#define EXT2_CLEAR_COMPAT_FEATURE(sb,mask) \ + EXT2_SB(sb)->s_es->s_feature_compat &= ~cpu_to_le32(mask) +#define EXT2_CLEAR_RO_COMPAT_FEATURE(sb,mask) \ + EXT2_SB(sb)->s_es->s_feature_ro_compat &= ~cpu_to_le32(mask) +#define EXT2_CLEAR_INCOMPAT_FEATURE(sb,mask) \ + EXT2_SB(sb)->s_es->s_feature_incompat &= ~cpu_to_le32(mask) + +#define EXT2_FEATURE_COMPAT_DIR_PREALLOC 0x0001 +#define EXT2_FEATURE_COMPAT_IMAGIC_INODES 0x0002 +#define EXT3_FEATURE_COMPAT_HAS_JOURNAL 0x0004 +#define EXT2_FEATURE_COMPAT_EXT_ATTR 0x0008 +#define EXT2_FEATURE_COMPAT_RESIZE_INO 0x0010 +#define EXT2_FEATURE_COMPAT_DIR_INDEX 0x0020 +#define EXT2_FEATURE_COMPAT_ANY 0xffffffff + +#define EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER 0x0001 +#define EXT2_FEATURE_RO_COMPAT_LARGE_FILE 0x0002 +#define EXT2_FEATURE_RO_COMPAT_BTREE_DIR 0x0004 +#define EXT2_FEATURE_RO_COMPAT_ANY 0xffffffff + +#define EXT2_FEATURE_INCOMPAT_COMPRESSION 0x0001 +#define EXT2_FEATURE_INCOMPAT_FILETYPE 0x0002 +#define EXT3_FEATURE_INCOMPAT_RECOVER 0x0004 +#define EXT3_FEATURE_INCOMPAT_JOURNAL_DEV 0x0008 +#define EXT2_FEATURE_INCOMPAT_META_BG 0x0010 +#define EXT2_FEATURE_INCOMPAT_ANY 0xffffffff + +#define EXT2_FEATURE_COMPAT_SUPP EXT2_FEATURE_COMPAT_EXT_ATTR +#define EXT2_FEATURE_INCOMPAT_SUPP (EXT2_FEATURE_INCOMPAT_FILETYPE| \ + EXT2_FEATURE_INCOMPAT_META_BG) +#define EXT2_FEATURE_RO_COMPAT_SUPP (EXT2_FEATURE_RO_COMPAT_SPARSE_SUPER| \ + EXT2_FEATURE_RO_COMPAT_LARGE_FILE| \ + EXT2_FEATURE_RO_COMPAT_BTREE_DIR) +#define EXT2_FEATURE_RO_COMPAT_UNSUPPORTED ~EXT2_FEATURE_RO_COMPAT_SUPP +#define EXT2_FEATURE_INCOMPAT_UNSUPPORTED ~EXT2_FEATURE_INCOMPAT_SUPP + +/* + * Default values for user and/or group using reserved blocks + */ +#define EXT2_DEF_RESUID 0 +#define EXT2_DEF_RESGID 0 + +/* + * Default mount options + */ +#define EXT2_DEFM_DEBUG 0x0001 +#define EXT2_DEFM_BSDGROUPS 0x0002 +#define EXT2_DEFM_XATTR_USER 0x0004 +#define EXT2_DEFM_ACL 0x0008 +#define EXT2_DEFM_UID16 0x0010 + /* Not used by ext2, but reserved for use by ext3 */ +#define EXT3_DEFM_JMODE 0x0060 +#define EXT3_DEFM_JMODE_DATA 0x0020 +#define EXT3_DEFM_JMODE_ORDERED 0x0040 +#define EXT3_DEFM_JMODE_WBACK 0x0060 + +/* + * Structure of a directory entry + */ + +struct ext2_dir_entry { + __le32 inode; /* Inode number */ + __le16 rec_len; /* Directory entry length */ + __le16 name_len; /* Name length */ + char name[]; /* File name, up to EXT2_NAME_LEN */ +}; + +/* + * The new version of the directory entry. Since EXT2 structures are + * stored in intel byte order, and the name_len field could never be + * bigger than 255 chars, it's safe to reclaim the extra byte for the + * file_type field. + */ +struct ext2_dir_entry_2 { + __le32 inode; /* Inode number */ + __le16 rec_len; /* Directory entry length */ + __u8 name_len; /* Name length */ + __u8 file_type; + char name[]; /* File name, up to EXT2_NAME_LEN */ +}; + +/* + * Ext2 directory file types. Only the low 3 bits are used. The + * other bits are reserved for now. + */ +enum { + EXT2_FT_UNKNOWN = 0, + EXT2_FT_REG_FILE = 1, + EXT2_FT_DIR = 2, + EXT2_FT_CHRDEV = 3, + EXT2_FT_BLKDEV = 4, + EXT2_FT_FIFO = 5, + EXT2_FT_SOCK = 6, + EXT2_FT_SYMLINK = 7, + EXT2_FT_MAX +}; + +/* + * EXT2_DIR_PAD defines the directory entries boundaries + * + * NOTE: It must be a multiple of 4 + */ +#define EXT2_DIR_PAD 4 +#define EXT2_DIR_ROUND (EXT2_DIR_PAD - 1) +#define EXT2_DIR_REC_LEN(name_len) (((name_len) + 8 + EXT2_DIR_ROUND) & \ + ~EXT2_DIR_ROUND) +#define EXT2_MAX_REC_LEN ((1<<16)-1) + +static inline void verify_offsets(void) +{ +#define A(x,y) BUILD_BUG_ON(x != offsetof(struct ext2_super_block, y)); + A(EXT2_SB_MAGIC_OFFSET, s_magic); + A(EXT2_SB_BLOCKS_OFFSET, s_blocks_count); + A(EXT2_SB_BSIZE_OFFSET, s_log_block_size); +#undef A +} + +/* + * ext2 mount options + */ +struct ext2_mount_options { + unsigned long s_mount_opt; + kuid_t s_resuid; + kgid_t s_resgid; +}; + +/* + * second extended file system inode data in memory + */ +struct ext2_inode_info { + __le32 i_data[15]; + __u32 i_flags; + __u32 i_faddr; + __u8 i_frag_no; + __u8 i_frag_size; + __u16 i_state; + __u32 i_file_acl; + __u32 i_dir_acl; + __u32 i_dtime; + + /* + * i_block_group is the number of the block group which contains + * this file's inode. Constant across the lifetime of the inode, + * it is used for making block allocation decisions - we try to + * place a file's data blocks near its inode block, and new inodes + * near to their parent directory's inode. + */ + __u32 i_block_group; + + /* block reservation info */ + struct ext2_block_alloc_info *i_block_alloc_info; + + __u32 i_dir_start_lookup; +#ifdef CONFIG_EXT2_FS_XATTR + /* + * Extended attributes can be read independently of the main file + * data. Taking i_mutex even when reading would cause contention + * between readers of EAs and writers of regular file data, so + * instead we synchronize on xattr_sem when reading or changing + * EAs. + */ + struct rw_semaphore xattr_sem; +#endif + rwlock_t i_meta_lock; + + /* + * truncate_mutex is for serialising ext2_truncate() against + * ext2_getblock(). It also protects the internals of the inode's + * reservation data structures: ext2_reserve_window and + * ext2_reserve_window_node. + */ + struct mutex truncate_mutex; + struct inode vfs_inode; + struct list_head i_orphan; /* unlinked but open inodes */ +#ifdef CONFIG_QUOTA + struct dquot *i_dquot[MAXQUOTAS]; +#endif +}; + +/* + * Inode dynamic state flags + */ +#define EXT2_STATE_NEW 0x00000001 /* inode is newly created */ + + +/* + * Function prototypes + */ + +/* + * Ok, these declarations are also in but none of the + * ext2 source programs needs to include it so they are duplicated here. + */ + +static inline struct ext2_inode_info *EXT2_I(struct inode *inode) +{ + return container_of(inode, struct ext2_inode_info, vfs_inode); +} + +/* balloc.c */ +extern int ext2_bg_has_super(struct super_block *sb, int group); +extern unsigned long ext2_bg_num_gdb(struct super_block *sb, int group); +extern ext2_fsblk_t ext2_new_block(struct inode *, unsigned long, int *); +extern ext2_fsblk_t ext2_new_blocks(struct inode *, unsigned long, + unsigned long *, int *); +extern void ext2_free_blocks (struct inode *, unsigned long, + unsigned long); +extern unsigned long ext2_count_free_blocks (struct super_block *); +extern unsigned long ext2_count_dirs (struct super_block *); +extern void ext2_check_blocks_bitmap (struct super_block *); +extern struct ext2_group_desc * ext2_get_group_desc(struct super_block * sb, + unsigned int block_group, + struct buffer_head ** bh); +extern void ext2_discard_reservation (struct inode *); +extern int ext2_should_retry_alloc(struct super_block *sb, int *retries); +extern void ext2_init_block_alloc_info(struct inode *); +extern void ext2_rsv_window_add(struct super_block *sb, struct ext2_reserve_window_node *rsv); + +/* dir.c */ +extern int ext2_add_link (struct dentry *, struct inode *); +extern ino_t ext2_inode_by_name(struct inode *, struct qstr *); +extern int ext2_make_empty(struct inode *, struct inode *); +extern struct ext2_dir_entry_2 * ext2_find_entry (struct inode *,struct qstr *, struct page **); +extern int ext2_delete_entry (struct ext2_dir_entry_2 *, struct page *); +extern int ext2_empty_dir (struct inode *); +extern struct ext2_dir_entry_2 * ext2_dotdot (struct inode *, struct page **); +extern void ext2_set_link(struct inode *, struct ext2_dir_entry_2 *, struct page *, struct inode *, int); + +/* ialloc.c */ +extern struct inode * ext2_new_inode (struct inode *, umode_t, const struct qstr *); +extern void ext2_free_inode (struct inode *); +extern unsigned long ext2_count_free_inodes (struct super_block *); +extern void ext2_check_inodes_bitmap (struct super_block *); +extern unsigned long ext2_count_free (struct buffer_head *, unsigned); + +/* inode.c */ +extern struct inode *ext2_iget (struct super_block *, unsigned long); +extern int ext2_write_inode (struct inode *, struct writeback_control *); +extern void ext2_evict_inode(struct inode *); +extern int ext2_get_block(struct inode *, sector_t, struct buffer_head *, int); +extern int ext2_setattr (struct dentry *, struct iattr *); +extern void ext2_set_inode_flags(struct inode *inode); +extern void ext2_get_inode_flags(struct ext2_inode_info *); +extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + u64 start, u64 len); + +/* ioctl.c */ +extern long ext2_ioctl(struct file *, unsigned int, unsigned long); +extern long ext2_compat_ioctl(struct file *, unsigned int, unsigned long); + +/* namei.c */ +struct dentry *ext2_get_parent(struct dentry *child); + +/* super.c */ +extern __printf(3, 4) +void ext2_error(struct super_block *, const char *, const char *, ...); +extern __printf(3, 4) +void ext2_msg(struct super_block *, const char *, const char *, ...); +extern void ext2_update_dynamic_rev (struct super_block *sb); +extern void ext2_write_super (struct super_block *); + +/* + * Inodes and files operations + */ + +/* dir.c */ +extern const struct file_operations ext2_dir_operations; + +/* file.c */ +extern int ext2_fsync(struct file *file, loff_t start, loff_t end, + int datasync); +extern const struct inode_operations ext2_file_inode_operations; +extern const struct file_operations ext2_file_operations; + +/* inode.c */ +extern const struct address_space_operations ext2_aops; +extern const struct address_space_operations ext2_nobh_aops; + +/* namei.c */ +extern const struct inode_operations ext2_dir_inode_operations; +extern const struct inode_operations ext2_special_inode_operations; + +/* symlink.c */ +extern const struct inode_operations ext2_fast_symlink_inode_operations; +extern const struct inode_operations ext2_symlink_inode_operations; + +static inline ext2_fsblk_t +ext2_group_first_block_no(struct super_block *sb, unsigned long group_no) +{ + return group_no * (ext2_fsblk_t)EXT2_BLOCKS_PER_GROUP(sb) + + le32_to_cpu(EXT2_SB(sb)->s_es->s_first_data_block); +} + +#define ext2_set_bit __test_and_set_bit_le +#define ext2_clear_bit __test_and_clear_bit_le +#define ext2_test_bit test_bit_le +#define ext2_find_first_zero_bit find_first_zero_bit_le +#define ext2_find_next_zero_bit find_next_zero_bit_le diff --git a/fs/ext2/file.c b/fs/ext2/file.c new file mode 100644 index 000000000..3a0a6c640 --- /dev/null +++ b/fs/ext2/file.c @@ -0,0 +1,121 @@ +/* + * linux/fs/ext2/file.c + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/fs/minix/file.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * ext2 fs regular file handling primitives + * + * 64-bit file support on 64-bit platforms by Jakub Jelinek + * (jj@sunsite.ms.mff.cuni.cz) + */ + +#include +#include +#include +#include "ext2.h" +#include "xattr.h" +#include "acl.h" + +#ifdef CONFIG_FS_DAX +static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + return dax_fault(vma, vmf, ext2_get_block); +} + +static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + return dax_mkwrite(vma, vmf, ext2_get_block); +} + +static const struct vm_operations_struct ext2_dax_vm_ops = { + .fault = ext2_dax_fault, + .page_mkwrite = ext2_dax_mkwrite, + .pfn_mkwrite = dax_pfn_mkwrite, +}; + +static int ext2_file_mmap(struct file *file, struct vm_area_struct *vma) +{ + if (!IS_DAX(file_inode(file))) + return generic_file_mmap(file, vma); + + file_accessed(file); + vma->vm_ops = &ext2_dax_vm_ops; + vma->vm_flags |= VM_MIXEDMAP; + return 0; +} +#else +#define ext2_file_mmap generic_file_mmap +#endif + +/* + * Called when filp is released. This happens when all file descriptors + * for a single struct file are closed. Note that different open() calls + * for the same file yield different struct file structures. + */ +static int ext2_release_file (struct inode * inode, struct file * filp) +{ + if (filp->f_mode & FMODE_WRITE) { + mutex_lock(&EXT2_I(inode)->truncate_mutex); + ext2_discard_reservation(inode); + mutex_unlock(&EXT2_I(inode)->truncate_mutex); + } + return 0; +} + +int ext2_fsync(struct file *file, loff_t start, loff_t end, int datasync) +{ + int ret; + struct super_block *sb = file->f_mapping->host->i_sb; + struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping; + + ret = generic_file_fsync(file, start, end, datasync); + if (ret == -EIO || test_and_clear_bit(AS_EIO, &mapping->flags)) { + /* We don't really know where the IO error happened... */ + ext2_error(sb, __func__, + "detected IO error when writing metadata buffers"); + ret = -EIO; + } + return ret; +} + +/* + * We have mostly NULL's here: the current defaults are ok for + * the ext2 filesystem. + */ +const struct file_operations ext2_file_operations = { + .llseek = generic_file_llseek, + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, + .unlocked_ioctl = ext2_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = ext2_compat_ioctl, +#endif + .mmap = ext2_file_mmap, + .open = dquot_file_open, + .release = ext2_release_file, + .fsync = ext2_fsync, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, +}; + +const struct inode_operations ext2_file_inode_operations = { +#ifdef CONFIG_EXT2_FS_XATTR + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = ext2_listxattr, + .removexattr = generic_removexattr, +#endif + .setattr = ext2_setattr, + .get_acl = ext2_get_acl, + .set_acl = ext2_set_acl, + .fiemap = ext2_fiemap, +}; diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c new file mode 100644 index 000000000..5c04a0dde --- /dev/null +++ b/fs/ext2/ialloc.c @@ -0,0 +1,675 @@ +/* + * linux/fs/ext2/ialloc.c + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * BSD ufs-inspired inode and directory allocation by + * Stephen Tweedie (sct@dcs.ed.ac.uk), 1993 + * Big-endian to little-endian byte-swapping/bitmaps by + * David S. Miller (davem@caip.rutgers.edu), 1995 + */ + +#include +#include +#include +#include +#include +#include "ext2.h" +#include "xattr.h" +#include "acl.h" + +/* + * ialloc.c contains the inodes allocation and deallocation routines + */ + +/* + * The free inodes are managed by bitmaps. A file system contains several + * blocks groups. Each group contains 1 bitmap block for blocks, 1 bitmap + * block for inodes, N blocks for the inode table and data blocks. + * + * The file system contains group descriptors which are located after the + * super block. Each descriptor contains the number of the bitmap block and + * the free blocks count in the block. + */ + + +/* + * Read the inode allocation bitmap for a given block_group, reading + * into the specified slot in the superblock's bitmap cache. + * + * Return buffer_head of bitmap on success or NULL. + */ +static struct buffer_head * +read_inode_bitmap(struct super_block * sb, unsigned long block_group) +{ + struct ext2_group_desc *desc; + struct buffer_head *bh = NULL; + + desc = ext2_get_group_desc(sb, block_group, NULL); + if (!desc) + goto error_out; + + bh = sb_bread(sb, le32_to_cpu(desc->bg_inode_bitmap)); + if (!bh) + ext2_error(sb, "read_inode_bitmap", + "Cannot read inode bitmap - " + "block_group = %lu, inode_bitmap = %u", + block_group, le32_to_cpu(desc->bg_inode_bitmap)); +error_out: + return bh; +} + +static void ext2_release_inode(struct super_block *sb, int group, int dir) +{ + struct ext2_group_desc * desc; + struct buffer_head *bh; + + desc = ext2_get_group_desc(sb, group, &bh); + if (!desc) { + ext2_error(sb, "ext2_release_inode", + "can't get descriptor for group %d", group); + return; + } + + spin_lock(sb_bgl_lock(EXT2_SB(sb), group)); + le16_add_cpu(&desc->bg_free_inodes_count, 1); + if (dir) + le16_add_cpu(&desc->bg_used_dirs_count, -1); + spin_unlock(sb_bgl_lock(EXT2_SB(sb), group)); + if (dir) + percpu_counter_dec(&EXT2_SB(sb)->s_dirs_counter); + mark_buffer_dirty(bh); +} + +/* + * NOTE! When we get the inode, we're the only people + * that have access to it, and as such there are no + * race conditions we have to worry about. The inode + * is not on the hash-lists, and it cannot be reached + * through the filesystem because the directory entry + * has been deleted earlier. + * + * HOWEVER: we must make sure that we get no aliases, + * which means that we have to call "clear_inode()" + * _before_ we mark the inode not in use in the inode + * bitmaps. Otherwise a newly created file might use + * the same inode number (not actually the same pointer + * though), and then we'd have two inodes sharing the + * same inode number and space on the harddisk. + */ +void ext2_free_inode (struct inode * inode) +{ + struct super_block * sb = inode->i_sb; + int is_directory; + unsigned long ino; + struct buffer_head *bitmap_bh; + unsigned long block_group; + unsigned long bit; + struct ext2_super_block * es; + + ino = inode->i_ino; + ext2_debug ("freeing inode %lu\n", ino); + + /* + * Note: we must free any quota before locking the superblock, + * as writing the quota to disk may need the lock as well. + */ + /* Quota is already initialized in iput() */ + dquot_free_inode(inode); + dquot_drop(inode); + + es = EXT2_SB(sb)->s_es; + is_directory = S_ISDIR(inode->i_mode); + + if (ino < EXT2_FIRST_INO(sb) || + ino > le32_to_cpu(es->s_inodes_count)) { + ext2_error (sb, "ext2_free_inode", + "reserved or nonexistent inode %lu", ino); + return; + } + block_group = (ino - 1) / EXT2_INODES_PER_GROUP(sb); + bit = (ino - 1) % EXT2_INODES_PER_GROUP(sb); + bitmap_bh = read_inode_bitmap(sb, block_group); + if (!bitmap_bh) + return; + + /* Ok, now we can actually update the inode bitmaps.. */ + if (!ext2_clear_bit_atomic(sb_bgl_lock(EXT2_SB(sb), block_group), + bit, (void *) bitmap_bh->b_data)) + ext2_error (sb, "ext2_free_inode", + "bit already cleared for inode %lu", ino); + else + ext2_release_inode(sb, block_group, is_directory); + mark_buffer_dirty(bitmap_bh); + if (sb->s_flags & MS_SYNCHRONOUS) + sync_dirty_buffer(bitmap_bh); + + brelse(bitmap_bh); +} + +/* + * We perform asynchronous prereading of the new inode's inode block when + * we create the inode, in the expectation that the inode will be written + * back soon. There are two reasons: + * + * - When creating a large number of files, the async prereads will be + * nicely merged into large reads + * - When writing out a large number of inodes, we don't need to keep on + * stalling the writes while we read the inode block. + * + * FIXME: ext2_get_group_desc() needs to be simplified. + */ +static void ext2_preread_inode(struct inode *inode) +{ + unsigned long block_group; + unsigned long offset; + unsigned long block; + struct ext2_group_desc * gdp; + struct backing_dev_info *bdi; + + bdi = inode_to_bdi(inode); + if (bdi_read_congested(bdi)) + return; + if (bdi_write_congested(bdi)) + return; + + block_group = (inode->i_ino - 1) / EXT2_INODES_PER_GROUP(inode->i_sb); + gdp = ext2_get_group_desc(inode->i_sb, block_group, NULL); + if (gdp == NULL) + return; + + /* + * Figure out the offset within the block group inode table + */ + offset = ((inode->i_ino - 1) % EXT2_INODES_PER_GROUP(inode->i_sb)) * + EXT2_INODE_SIZE(inode->i_sb); + block = le32_to_cpu(gdp->bg_inode_table) + + (offset >> EXT2_BLOCK_SIZE_BITS(inode->i_sb)); + sb_breadahead(inode->i_sb, block); +} + +/* + * There are two policies for allocating an inode. If the new inode is + * a directory, then a forward search is made for a block group with both + * free space and a low directory-to-inode ratio; if that fails, then of + * the groups with above-average free space, that group with the fewest + * directories already is chosen. + * + * For other inodes, search forward from the parent directory\'s block + * group to find a free inode. + */ +static int find_group_dir(struct super_block *sb, struct inode *parent) +{ + int ngroups = EXT2_SB(sb)->s_groups_count; + int avefreei = ext2_count_free_inodes(sb) / ngroups; + struct ext2_group_desc *desc, *best_desc = NULL; + int group, best_group = -1; + + for (group = 0; group < ngroups; group++) { + desc = ext2_get_group_desc (sb, group, NULL); + if (!desc || !desc->bg_free_inodes_count) + continue; + if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei) + continue; + if (!best_desc || + (le16_to_cpu(desc->bg_free_blocks_count) > + le16_to_cpu(best_desc->bg_free_blocks_count))) { + best_group = group; + best_desc = desc; + } + } + if (!best_desc) + return -1; + + return best_group; +} + +/* + * Orlov's allocator for directories. + * + * We always try to spread first-level directories. + * + * If there are blockgroups with both free inodes and free blocks counts + * not worse than average we return one with smallest directory count. + * Otherwise we simply return a random group. + * + * For the rest rules look so: + * + * It's OK to put directory into a group unless + * it has too many directories already (max_dirs) or + * it has too few free inodes left (min_inodes) or + * it has too few free blocks left (min_blocks) or + * it's already running too large debt (max_debt). + * Parent's group is preferred, if it doesn't satisfy these + * conditions we search cyclically through the rest. If none + * of the groups look good we just look for a group with more + * free inodes than average (starting at parent's group). + * + * Debt is incremented each time we allocate a directory and decremented + * when we allocate an inode, within 0--255. + */ + +#define INODE_COST 64 +#define BLOCK_COST 256 + +static int find_group_orlov(struct super_block *sb, struct inode *parent) +{ + int parent_group = EXT2_I(parent)->i_block_group; + struct ext2_sb_info *sbi = EXT2_SB(sb); + struct ext2_super_block *es = sbi->s_es; + int ngroups = sbi->s_groups_count; + int inodes_per_group = EXT2_INODES_PER_GROUP(sb); + int freei; + int avefreei; + int free_blocks; + int avefreeb; + int blocks_per_dir; + int ndirs; + int max_debt, max_dirs, min_blocks, min_inodes; + int group = -1, i; + struct ext2_group_desc *desc; + + freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter); + avefreei = freei / ngroups; + free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter); + avefreeb = free_blocks / ngroups; + ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter); + + if ((parent == d_inode(sb->s_root)) || + (EXT2_I(parent)->i_flags & EXT2_TOPDIR_FL)) { + struct ext2_group_desc *best_desc = NULL; + int best_ndir = inodes_per_group; + int best_group = -1; + + group = prandom_u32(); + parent_group = (unsigned)group % ngroups; + for (i = 0; i < ngroups; i++) { + group = (parent_group + i) % ngroups; + desc = ext2_get_group_desc (sb, group, NULL); + if (!desc || !desc->bg_free_inodes_count) + continue; + if (le16_to_cpu(desc->bg_used_dirs_count) >= best_ndir) + continue; + if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei) + continue; + if (le16_to_cpu(desc->bg_free_blocks_count) < avefreeb) + continue; + best_group = group; + best_ndir = le16_to_cpu(desc->bg_used_dirs_count); + best_desc = desc; + } + if (best_group >= 0) { + desc = best_desc; + group = best_group; + goto found; + } + goto fallback; + } + + if (ndirs == 0) + ndirs = 1; /* percpu_counters are approximate... */ + + blocks_per_dir = (le32_to_cpu(es->s_blocks_count)-free_blocks) / ndirs; + + max_dirs = ndirs / ngroups + inodes_per_group / 16; + min_inodes = avefreei - inodes_per_group / 4; + min_blocks = avefreeb - EXT2_BLOCKS_PER_GROUP(sb) / 4; + + max_debt = EXT2_BLOCKS_PER_GROUP(sb) / max(blocks_per_dir, BLOCK_COST); + if (max_debt * INODE_COST > inodes_per_group) + max_debt = inodes_per_group / INODE_COST; + if (max_debt > 255) + max_debt = 255; + if (max_debt == 0) + max_debt = 1; + + for (i = 0; i < ngroups; i++) { + group = (parent_group + i) % ngroups; + desc = ext2_get_group_desc (sb, group, NULL); + if (!desc || !desc->bg_free_inodes_count) + continue; + if (sbi->s_debts[group] >= max_debt) + continue; + if (le16_to_cpu(desc->bg_used_dirs_count) >= max_dirs) + continue; + if (le16_to_cpu(desc->bg_free_inodes_count) < min_inodes) + continue; + if (le16_to_cpu(desc->bg_free_blocks_count) < min_blocks) + continue; + goto found; + } + +fallback: + for (i = 0; i < ngroups; i++) { + group = (parent_group + i) % ngroups; + desc = ext2_get_group_desc (sb, group, NULL); + if (!desc || !desc->bg_free_inodes_count) + continue; + if (le16_to_cpu(desc->bg_free_inodes_count) >= avefreei) + goto found; + } + + if (avefreei) { + /* + * The free-inodes counter is approximate, and for really small + * filesystems the above test can fail to find any blockgroups + */ + avefreei = 0; + goto fallback; + } + + return -1; + +found: + return group; +} + +static int find_group_other(struct super_block *sb, struct inode *parent) +{ + int parent_group = EXT2_I(parent)->i_block_group; + int ngroups = EXT2_SB(sb)->s_groups_count; + struct ext2_group_desc *desc; + int group, i; + + /* + * Try to place the inode in its parent directory + */ + group = parent_group; + desc = ext2_get_group_desc (sb, group, NULL); + if (desc && le16_to_cpu(desc->bg_free_inodes_count) && + le16_to_cpu(desc->bg_free_blocks_count)) + goto found; + + /* + * We're going to place this inode in a different blockgroup from its + * parent. We want to cause files in a common directory to all land in + * the same blockgroup. But we want files which are in a different + * directory which shares a blockgroup with our parent to land in a + * different blockgroup. + * + * So add our directory's i_ino into the starting point for the hash. + */ + group = (group + parent->i_ino) % ngroups; + + /* + * Use a quadratic hash to find a group with a free inode and some + * free blocks. + */ + for (i = 1; i < ngroups; i <<= 1) { + group += i; + if (group >= ngroups) + group -= ngroups; + desc = ext2_get_group_desc (sb, group, NULL); + if (desc && le16_to_cpu(desc->bg_free_inodes_count) && + le16_to_cpu(desc->bg_free_blocks_count)) + goto found; + } + + /* + * That failed: try linear search for a free inode, even if that group + * has no free blocks. + */ + group = parent_group; + for (i = 0; i < ngroups; i++) { + if (++group >= ngroups) + group = 0; + desc = ext2_get_group_desc (sb, group, NULL); + if (desc && le16_to_cpu(desc->bg_free_inodes_count)) + goto found; + } + + return -1; + +found: + return group; +} + +struct inode *ext2_new_inode(struct inode *dir, umode_t mode, + const struct qstr *qstr) +{ + struct super_block *sb; + struct buffer_head *bitmap_bh = NULL; + struct buffer_head *bh2; + int group, i; + ino_t ino = 0; + struct inode * inode; + struct ext2_group_desc *gdp; + struct ext2_super_block *es; + struct ext2_inode_info *ei; + struct ext2_sb_info *sbi; + int err; + + sb = dir->i_sb; + inode = new_inode(sb); + if (!inode) + return ERR_PTR(-ENOMEM); + + ei = EXT2_I(inode); + sbi = EXT2_SB(sb); + es = sbi->s_es; + if (S_ISDIR(mode)) { + if (test_opt(sb, OLDALLOC)) + group = find_group_dir(sb, dir); + else + group = find_group_orlov(sb, dir); + } else + group = find_group_other(sb, dir); + + if (group == -1) { + err = -ENOSPC; + goto fail; + } + + for (i = 0; i < sbi->s_groups_count; i++) { + gdp = ext2_get_group_desc(sb, group, &bh2); + brelse(bitmap_bh); + bitmap_bh = read_inode_bitmap(sb, group); + if (!bitmap_bh) { + err = -EIO; + goto fail; + } + ino = 0; + +repeat_in_this_group: + ino = ext2_find_next_zero_bit((unsigned long *)bitmap_bh->b_data, + EXT2_INODES_PER_GROUP(sb), ino); + if (ino >= EXT2_INODES_PER_GROUP(sb)) { + /* + * Rare race: find_group_xx() decided that there were + * free inodes in this group, but by the time we tried + * to allocate one, they're all gone. This can also + * occur because the counters which find_group_orlov() + * uses are approximate. So just go and search the + * next block group. + */ + if (++group == sbi->s_groups_count) + group = 0; + continue; + } + if (ext2_set_bit_atomic(sb_bgl_lock(sbi, group), + ino, bitmap_bh->b_data)) { + /* we lost this inode */ + if (++ino >= EXT2_INODES_PER_GROUP(sb)) { + /* this group is exhausted, try next group */ + if (++group == sbi->s_groups_count) + group = 0; + continue; + } + /* try to find free inode in the same group */ + goto repeat_in_this_group; + } + goto got; + } + + /* + * Scanned all blockgroups. + */ + err = -ENOSPC; + goto fail; +got: + mark_buffer_dirty(bitmap_bh); + if (sb->s_flags & MS_SYNCHRONOUS) + sync_dirty_buffer(bitmap_bh); + brelse(bitmap_bh); + + ino += group * EXT2_INODES_PER_GROUP(sb) + 1; + if (ino < EXT2_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) { + ext2_error (sb, "ext2_new_inode", + "reserved inode or inode > inodes count - " + "block_group = %d,inode=%lu", group, + (unsigned long) ino); + err = -EIO; + goto fail; + } + + percpu_counter_add(&sbi->s_freeinodes_counter, -1); + if (S_ISDIR(mode)) + percpu_counter_inc(&sbi->s_dirs_counter); + + spin_lock(sb_bgl_lock(sbi, group)); + le16_add_cpu(&gdp->bg_free_inodes_count, -1); + if (S_ISDIR(mode)) { + if (sbi->s_debts[group] < 255) + sbi->s_debts[group]++; + le16_add_cpu(&gdp->bg_used_dirs_count, 1); + } else { + if (sbi->s_debts[group]) + sbi->s_debts[group]--; + } + spin_unlock(sb_bgl_lock(sbi, group)); + + mark_buffer_dirty(bh2); + if (test_opt(sb, GRPID)) { + inode->i_mode = mode; + inode->i_uid = current_fsuid(); + inode->i_gid = dir->i_gid; + } else + inode_init_owner(inode, dir, mode); + + inode->i_ino = ino; + inode->i_blocks = 0; + inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; + memset(ei->i_data, 0, sizeof(ei->i_data)); + ei->i_flags = + ext2_mask_flags(mode, EXT2_I(dir)->i_flags & EXT2_FL_INHERITED); + ei->i_faddr = 0; + ei->i_frag_no = 0; + ei->i_frag_size = 0; + ei->i_file_acl = 0; + ei->i_dir_acl = 0; + ei->i_dtime = 0; + ei->i_block_alloc_info = NULL; + ei->i_block_group = group; + ei->i_dir_start_lookup = 0; + ei->i_state = EXT2_STATE_NEW; + ext2_set_inode_flags(inode); + spin_lock(&sbi->s_next_gen_lock); + inode->i_generation = sbi->s_next_generation++; + spin_unlock(&sbi->s_next_gen_lock); + if (insert_inode_locked(inode) < 0) { + ext2_error(sb, "ext2_new_inode", + "inode number already in use - inode=%lu", + (unsigned long) ino); + err = -EIO; + goto fail; + } + + dquot_initialize(inode); + err = dquot_alloc_inode(inode); + if (err) + goto fail_drop; + + err = ext2_init_acl(inode, dir); + if (err) + goto fail_free_drop; + + err = ext2_init_security(inode, dir, qstr); + if (err) + goto fail_free_drop; + + mark_inode_dirty(inode); + ext2_debug("allocating inode %lu\n", inode->i_ino); + ext2_preread_inode(inode); + return inode; + +fail_free_drop: + dquot_free_inode(inode); + +fail_drop: + dquot_drop(inode); + inode->i_flags |= S_NOQUOTA; + clear_nlink(inode); + unlock_new_inode(inode); + iput(inode); + return ERR_PTR(err); + +fail: + make_bad_inode(inode); + iput(inode); + return ERR_PTR(err); +} + +unsigned long ext2_count_free_inodes (struct super_block * sb) +{ + struct ext2_group_desc *desc; + unsigned long desc_count = 0; + int i; + +#ifdef EXT2FS_DEBUG + struct ext2_super_block *es; + unsigned long bitmap_count = 0; + struct buffer_head *bitmap_bh = NULL; + + es = EXT2_SB(sb)->s_es; + for (i = 0; i < EXT2_SB(sb)->s_groups_count; i++) { + unsigned x; + + desc = ext2_get_group_desc (sb, i, NULL); + if (!desc) + continue; + desc_count += le16_to_cpu(desc->bg_free_inodes_count); + brelse(bitmap_bh); + bitmap_bh = read_inode_bitmap(sb, i); + if (!bitmap_bh) + continue; + + x = ext2_count_free(bitmap_bh, EXT2_INODES_PER_GROUP(sb) / 8); + printk("group %d: stored = %d, counted = %u\n", + i, le16_to_cpu(desc->bg_free_inodes_count), x); + bitmap_count += x; + } + brelse(bitmap_bh); + printk("ext2_count_free_inodes: stored = %lu, computed = %lu, %lu\n", + (unsigned long) + percpu_counter_read(&EXT2_SB(sb)->s_freeinodes_counter), + desc_count, bitmap_count); + return desc_count; +#else + for (i = 0; i < EXT2_SB(sb)->s_groups_count; i++) { + desc = ext2_get_group_desc (sb, i, NULL); + if (!desc) + continue; + desc_count += le16_to_cpu(desc->bg_free_inodes_count); + } + return desc_count; +#endif +} + +/* Called at mount-time, super-block is locked */ +unsigned long ext2_count_dirs (struct super_block * sb) +{ + unsigned long count = 0; + int i; + + for (i = 0; i < EXT2_SB(sb)->s_groups_count; i++) { + struct ext2_group_desc *gdp = ext2_get_group_desc (sb, i, NULL); + if (!gdp) + continue; + count += le16_to_cpu(gdp->bg_used_dirs_count); + } + return count; +} + diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c new file mode 100644 index 000000000..f460ae36d --- /dev/null +++ b/fs/ext2/inode.c @@ -0,0 +1,1573 @@ +/* + * linux/fs/ext2/inode.c + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/fs/minix/inode.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * Goal-directed block allocation by Stephen Tweedie + * (sct@dcs.ed.ac.uk), 1993, 1998 + * Big-endian to little-endian byte-swapping/bitmaps by + * David S. Miller (davem@caip.rutgers.edu), 1995 + * 64-bit file support on 64-bit platforms by Jakub Jelinek + * (jj@sunsite.ms.mff.cuni.cz) + * + * Assorted race fixes, rewrite of ext2_get_block() by Al Viro, 2000 + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "ext2.h" +#include "acl.h" +#include "xattr.h" + +static int __ext2_write_inode(struct inode *inode, int do_sync); + +/* + * Test whether an inode is a fast symlink. + */ +static inline int ext2_inode_is_fast_symlink(struct inode *inode) +{ + int ea_blocks = EXT2_I(inode)->i_file_acl ? + (inode->i_sb->s_blocksize >> 9) : 0; + + return (S_ISLNK(inode->i_mode) && + inode->i_blocks - ea_blocks == 0); +} + +static void ext2_truncate_blocks(struct inode *inode, loff_t offset); + +static void ext2_write_failed(struct address_space *mapping, loff_t to) +{ + struct inode *inode = mapping->host; + + if (to > inode->i_size) { + truncate_pagecache(inode, inode->i_size); + ext2_truncate_blocks(inode, inode->i_size); + } +} + +/* + * Called at the last iput() if i_nlink is zero. + */ +void ext2_evict_inode(struct inode * inode) +{ + struct ext2_block_alloc_info *rsv; + int want_delete = 0; + + if (!inode->i_nlink && !is_bad_inode(inode)) { + want_delete = 1; + dquot_initialize(inode); + } else { + dquot_drop(inode); + } + + truncate_inode_pages_final(&inode->i_data); + + if (want_delete) { + sb_start_intwrite(inode->i_sb); + /* set dtime */ + EXT2_I(inode)->i_dtime = get_seconds(); + mark_inode_dirty(inode); + __ext2_write_inode(inode, inode_needs_sync(inode)); + /* truncate to 0 */ + inode->i_size = 0; + if (inode->i_blocks) + ext2_truncate_blocks(inode, 0); + ext2_xattr_delete_inode(inode); + } + + invalidate_inode_buffers(inode); + clear_inode(inode); + + ext2_discard_reservation(inode); + rsv = EXT2_I(inode)->i_block_alloc_info; + EXT2_I(inode)->i_block_alloc_info = NULL; + if (unlikely(rsv)) + kfree(rsv); + + if (want_delete) { + ext2_free_inode(inode); + sb_end_intwrite(inode->i_sb); + } +} + +typedef struct { + __le32 *p; + __le32 key; + struct buffer_head *bh; +} Indirect; + +static inline void add_chain(Indirect *p, struct buffer_head *bh, __le32 *v) +{ + p->key = *(p->p = v); + p->bh = bh; +} + +static inline int verify_chain(Indirect *from, Indirect *to) +{ + while (from <= to && from->key == *from->p) + from++; + return (from > to); +} + +/** + * ext2_block_to_path - parse the block number into array of offsets + * @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. + * To store the locations of file's data ext2 uses a data structure common + * for UNIX filesystems - tree of pointers anchored in the inode, with + * data blocks at leaves and indirect blocks in intermediate nodes. + * This function translates the block number into path in that tree - + * return value is the path length and @offsets[n] is the offset of + * pointer to (n+1)th node in the nth one. If @block is out of range + * (negative or too large) warning is printed and zero returned. + * + * Note: function doesn't find node addresses, so no IO is needed. All + * we need to know is the capacity of indirect blocks (taken from the + * inode->i_sb). + */ + +/* + * Portability note: the last comparison (check that we fit into triple + * indirect block) is spelled differently, because otherwise on an + * architecture with 32-bit longs and 8Kb pages we might get into trouble + * if our filesystem had 8Kb blocks. We might use long long, but that would + * kill us on x86. Oh, well, at least the sign propagation does not matter - + * i_block would have to be negative in the very beginning, so we would not + * get there at all. + */ + +static int ext2_block_to_path(struct inode *inode, + long i_block, int offsets[4], int *boundary) +{ + int ptrs = EXT2_ADDR_PER_BLOCK(inode->i_sb); + int ptrs_bits = EXT2_ADDR_PER_BLOCK_BITS(inode->i_sb); + const long direct_blocks = EXT2_NDIR_BLOCKS, + indirect_blocks = ptrs, + double_blocks = (1 << (ptrs_bits * 2)); + int n = 0; + int final = 0; + + if (i_block < 0) { + ext2_msg(inode->i_sb, KERN_WARNING, + "warning: %s: block < 0", __func__); + } else if (i_block < direct_blocks) { + offsets[n++] = i_block; + final = direct_blocks; + } else if ( (i_block -= direct_blocks) < indirect_blocks) { + offsets[n++] = EXT2_IND_BLOCK; + offsets[n++] = i_block; + final = ptrs; + } else if ((i_block -= indirect_blocks) < double_blocks) { + offsets[n++] = EXT2_DIND_BLOCK; + offsets[n++] = i_block >> ptrs_bits; + offsets[n++] = i_block & (ptrs - 1); + final = ptrs; + } else if (((i_block -= double_blocks) >> (ptrs_bits * 2)) < ptrs) { + offsets[n++] = EXT2_TIND_BLOCK; + offsets[n++] = i_block >> (ptrs_bits * 2); + offsets[n++] = (i_block >> ptrs_bits) & (ptrs - 1); + offsets[n++] = i_block & (ptrs - 1); + final = ptrs; + } else { + ext2_msg(inode->i_sb, KERN_WARNING, + "warning: %s: block is too big", __func__); + } + if (boundary) + *boundary = final - 1 - (i_block & (ptrs - 1)); + + return n; +} + +/** + * ext2_get_branch - read the chain of indirect blocks leading to data + * @inode: inode in question + * @depth: depth of the chain (1 - direct pointer, etc.) + * @offsets: offsets of pointers in inode/indirect blocks + * @chain: place to store the result + * @err: here we store the error value + * + * Function fills the array of triples and returns %NULL + * if everything went OK or the pointer to the last filled triple + * (incomplete one) otherwise. Upon the return chain[i].key contains + * the number of (i+1)-th block in the chain (as it is stored in memory, + * i.e. little-endian 32-bit), chain[i].p contains the address of that + * number (it points into struct inode for i==0 and into the bh->b_data + * for i>0) and chain[i].bh points to the buffer_head of i-th indirect + * block for i>0 and NULL for i==0. In other words, it holds the block + * numbers of the chain, addresses they were taken from (and where we can + * verify that chain did not change) and buffer_heads hosting these + * numbers. + * + * Function stops when it stumbles upon zero pointer (absent block) + * (pointer to last triple returned, *@err == 0) + * or when it gets an IO error reading an indirect block + * (ditto, *@err == -EIO) + * or when it notices that chain had been changed while it was reading + * (ditto, *@err == -EAGAIN) + * or when it reads all @depth-1 indirect blocks successfully and finds + * the whole chain, all way to the data (returns %NULL, *err == 0). + */ +static Indirect *ext2_get_branch(struct inode *inode, + int depth, + int *offsets, + Indirect chain[4], + int *err) +{ + struct super_block *sb = inode->i_sb; + Indirect *p = chain; + struct buffer_head *bh; + + *err = 0; + /* i_data is not going away, no lock needed */ + add_chain (chain, NULL, EXT2_I(inode)->i_data + *offsets); + if (!p->key) + goto no_block; + while (--depth) { + bh = sb_bread(sb, le32_to_cpu(p->key)); + if (!bh) + goto failure; + read_lock(&EXT2_I(inode)->i_meta_lock); + if (!verify_chain(chain, p)) + goto changed; + add_chain(++p, bh, (__le32*)bh->b_data + *++offsets); + read_unlock(&EXT2_I(inode)->i_meta_lock); + if (!p->key) + goto no_block; + } + return NULL; + +changed: + read_unlock(&EXT2_I(inode)->i_meta_lock); + brelse(bh); + *err = -EAGAIN; + goto no_block; +failure: + *err = -EIO; +no_block: + return p; +} + +/** + * ext2_find_near - find a place for allocation with sufficient locality + * @inode: owner + * @ind: descriptor of indirect block. + * + * This function returns the preferred place for block allocation. + * It is used when heuristic for sequential allocation fails. + * Rules are: + * + if there is a block to the left of our position - allocate near it. + * + if pointer will live in indirect block - allocate near that block. + * + if pointer will live in inode - allocate in the same cylinder group. + * + * In the latter case we colour the starting block by the callers PID to + * prevent it from clashing with concurrent allocations for a different inode + * in the same block group. The PID is used here so that functionally related + * files will be close-by on-disk. + * + * Caller must make sure that @ind is valid and will stay that way. + */ + +static ext2_fsblk_t ext2_find_near(struct inode *inode, Indirect *ind) +{ + struct ext2_inode_info *ei = EXT2_I(inode); + __le32 *start = ind->bh ? (__le32 *) ind->bh->b_data : ei->i_data; + __le32 *p; + ext2_fsblk_t bg_start; + ext2_fsblk_t colour; + + /* Try to find previous block */ + for (p = ind->p - 1; p >= start; p--) + if (*p) + return le32_to_cpu(*p); + + /* No such thing, so let's try location of indirect block */ + if (ind->bh) + return ind->bh->b_blocknr; + + /* + * It is going to be referred from inode itself? OK, just put it into + * the same cylinder group then. + */ + bg_start = ext2_group_first_block_no(inode->i_sb, ei->i_block_group); + colour = (current->pid % 16) * + (EXT2_BLOCKS_PER_GROUP(inode->i_sb) / 16); + return bg_start + colour; +} + +/** + * ext2_find_goal - find a preferred place for allocation. + * @inode: owner + * @block: block we want + * @partial: pointer to the last triple within a chain + * + * Returns preferred place for a block (the goal). + */ + +static inline ext2_fsblk_t ext2_find_goal(struct inode *inode, long block, + Indirect *partial) +{ + struct ext2_block_alloc_info *block_i; + + block_i = EXT2_I(inode)->i_block_alloc_info; + + /* + * try the heuristic for sequential allocation, + * failing that at least try to get decent locality. + */ + if (block_i && (block == block_i->last_alloc_logical_block + 1) + && (block_i->last_alloc_physical_block != 0)) { + return block_i->last_alloc_physical_block + 1; + } + + return ext2_find_near(inode, partial); +} + +/** + * ext2_blks_to_allocate: Look up the block map and count the number + * of direct blocks need to be allocated for the given branch. + * + * @branch: chain of indirect blocks + * @k: number of blocks need for indirect blocks + * @blks: number of data blocks to be mapped. + * @blocks_to_boundary: the offset in the indirect block + * + * return the total number of blocks to be allocate, including the + * direct and indirect blocks. + */ +static int +ext2_blks_to_allocate(Indirect * branch, int k, unsigned long blks, + int blocks_to_boundary) +{ + unsigned long count = 0; + + /* + * Simple case, [t,d]Indirect block(s) has not allocated yet + * then it's clear blocks on that path have not allocated + */ + if (k > 0) { + /* right now don't hanel cross boundary allocation */ + if (blks < blocks_to_boundary + 1) + count += blks; + else + count += blocks_to_boundary + 1; + return count; + } + + count++; + while (count < blks && count <= blocks_to_boundary + && le32_to_cpu(*(branch[0].p + count)) == 0) { + count++; + } + return count; +} + +/** + * ext2_alloc_blocks: multiple allocate blocks needed for a branch + * @indirect_blks: the number of blocks need to allocate for indirect + * blocks + * + * @new_blocks: on return it will store the new block numbers for + * the indirect blocks(if needed) and the first direct block, + * @blks: on return it will store the total number of allocated + * direct blocks + */ +static int ext2_alloc_blocks(struct inode *inode, + ext2_fsblk_t goal, int indirect_blks, int blks, + ext2_fsblk_t new_blocks[4], int *err) +{ + int target, i; + unsigned long count = 0; + int index = 0; + ext2_fsblk_t current_block = 0; + int ret = 0; + + /* + * Here we try to allocate the requested multiple blocks at once, + * on a best-effort basis. + * To build a branch, we should allocate blocks for + * the indirect blocks(if not allocated yet), and at least + * the first direct block of this branch. That's the + * minimum number of blocks need to allocate(required) + */ + target = blks + indirect_blks; + + while (1) { + count = target; + /* allocating blocks for indirect blocks and direct blocks */ + current_block = ext2_new_blocks(inode,goal,&count,err); + if (*err) + goto failed_out; + + target -= count; + /* allocate blocks for indirect blocks */ + while (index < indirect_blks && count) { + new_blocks[index++] = current_block++; + count--; + } + + if (count > 0) + break; + } + + /* save the new block number for the first direct block */ + new_blocks[index] = current_block; + + /* total number of blocks allocated for direct blocks */ + ret = count; + *err = 0; + return ret; +failed_out: + for (i = 0; i key). Upon the exit we have the same + * picture as after the successful ext2_get_block(), except that in one + * place chain is disconnected - *branch->p is still zero (we did not + * set the last link), but branch->key contains the number that should + * be placed into *branch->p to fill that gap. + * + * If allocation fails we free all blocks we've allocated (and forget + * their buffer_heads) and return the error value the from failed + * ext2_alloc_block() (normally -ENOSPC). Otherwise we set the chain + * as described above and return 0. + */ + +static int ext2_alloc_branch(struct inode *inode, + int indirect_blks, int *blks, ext2_fsblk_t goal, + int *offsets, Indirect *branch) +{ + int blocksize = inode->i_sb->s_blocksize; + int i, n = 0; + int err = 0; + struct buffer_head *bh; + int num; + ext2_fsblk_t new_blocks[4]; + ext2_fsblk_t current_block; + + num = ext2_alloc_blocks(inode, goal, indirect_blks, + *blks, new_blocks, &err); + if (err) + return err; + + branch[0].key = cpu_to_le32(new_blocks[0]); + /* + * metadata blocks and data blocks are allocated. + */ + for (n = 1; n <= indirect_blks; n++) { + /* + * Get buffer_head for parent block, zero it out + * and set the pointer to new one, then send + * parent to disk. + */ + bh = sb_getblk(inode->i_sb, new_blocks[n-1]); + if (unlikely(!bh)) { + err = -ENOMEM; + goto failed; + } + branch[n].bh = bh; + lock_buffer(bh); + memset(bh->b_data, 0, blocksize); + branch[n].p = (__le32 *) bh->b_data + offsets[n]; + branch[n].key = cpu_to_le32(new_blocks[n]); + *branch[n].p = branch[n].key; + if ( n == indirect_blks) { + current_block = new_blocks[n]; + /* + * End of chain, update the last new metablock of + * the chain to point to the new allocated + * data blocks numbers + */ + for (i=1; i < num; i++) + *(branch[n].p + i) = cpu_to_le32(++current_block); + } + set_buffer_uptodate(bh); + unlock_buffer(bh); + mark_buffer_dirty_inode(bh, inode); + /* We used to sync bh here if IS_SYNC(inode). + * But we now rely upon generic_write_sync() + * and b_inode_buffers. But not for directories. + */ + if (S_ISDIR(inode->i_mode) && IS_DIRSYNC(inode)) + sync_dirty_buffer(bh); + } + *blks = num; + return err; + +failed: + for (i = 1; i < n; i++) + bforget(branch[i].bh); + for (i = 0; i < indirect_blks; i++) + ext2_free_blocks(inode, new_blocks[i], 1); + ext2_free_blocks(inode, new_blocks[i], num); + return err; +} + +/** + * ext2_splice_branch - splice the allocated branch onto inode. + * @inode: owner + * @block: (logical) number of block we are adding + * @where: location of missing link + * @num: number of indirect blocks we are adding + * @blks: number of direct blocks we are adding + * + * This function fills the missing link and does all housekeeping needed in + * inode (->i_blocks, etc.). In case of success we end up with the full + * chain to new block and return 0. + */ +static void ext2_splice_branch(struct inode *inode, + long block, Indirect *where, int num, int blks) +{ + int i; + struct ext2_block_alloc_info *block_i; + ext2_fsblk_t current_block; + + block_i = EXT2_I(inode)->i_block_alloc_info; + + /* XXX LOCKING probably should have i_meta_lock ?*/ + /* That's it */ + + *where->p = where->key; + + /* + * Update the host buffer_head or inode to point to more just allocated + * direct blocks blocks + */ + if (num == 0 && blks > 1) { + current_block = le32_to_cpu(where->key) + 1; + for (i = 1; i < blks; i++) + *(where->p + i ) = cpu_to_le32(current_block++); + } + + /* + * update the most recently allocated logical & physical block + * in i_block_alloc_info, to assist find the proper goal block for next + * allocation + */ + if (block_i) { + block_i->last_alloc_logical_block = block + blks - 1; + block_i->last_alloc_physical_block = + le32_to_cpu(where[num].key) + blks - 1; + } + + /* We are done with atomic stuff, now do the rest of housekeeping */ + + /* had we spliced it onto indirect block? */ + if (where->bh) + mark_buffer_dirty_inode(where->bh, inode); + + inode->i_ctime = CURRENT_TIME_SEC; + mark_inode_dirty(inode); +} + +/* + * Allocation strategy is simple: if we have to allocate something, we will + * have to go the whole way to leaf. So let's do it before attaching anything + * to tree, set linkage between the newborn blocks, write them if sync is + * required, recheck the path, free and repeat if check fails, otherwise + * set the last missing link (that will protect us from any truncate-generated + * removals - all blocks on the path are immune now) and possibly force the + * write on the parent block. + * That has a nice additional property: no special recovery from the failed + * allocations is needed - we simply release blocks and do not touch anything + * reachable from inode. + * + * `handle' can be NULL if create == 0. + * + * return > 0, # of blocks mapped or allocated. + * return = 0, if plain lookup failed. + * return < 0, error case. + */ +static int ext2_get_blocks(struct inode *inode, + sector_t iblock, unsigned long maxblocks, + struct buffer_head *bh_result, + int create) +{ + int err = -EIO; + int offsets[4]; + Indirect chain[4]; + Indirect *partial; + ext2_fsblk_t goal; + int indirect_blks; + int blocks_to_boundary = 0; + int depth; + struct ext2_inode_info *ei = EXT2_I(inode); + int count = 0; + ext2_fsblk_t first_block = 0; + + BUG_ON(maxblocks == 0); + + depth = ext2_block_to_path(inode,iblock,offsets,&blocks_to_boundary); + + if (depth == 0) + return (err); + + partial = ext2_get_branch(inode, depth, offsets, chain, &err); + /* Simplest case - block found, no allocation needed */ + if (!partial) { + first_block = le32_to_cpu(chain[depth - 1].key); + clear_buffer_new(bh_result); /* What's this do? */ + count++; + /*map more blocks*/ + while (count < maxblocks && count <= blocks_to_boundary) { + ext2_fsblk_t blk; + + if (!verify_chain(chain, chain + depth - 1)) { + /* + * Indirect block might be removed by + * truncate while we were reading it. + * Handling of that case: forget what we've + * got now, go to reread. + */ + err = -EAGAIN; + count = 0; + break; + } + blk = le32_to_cpu(*(chain[depth-1].p + count)); + if (blk == first_block + count) + count++; + else + break; + } + if (err != -EAGAIN) + goto got_it; + } + + /* Next simple case - plain lookup or failed read of indirect block */ + if (!create || err == -EIO) + goto cleanup; + + mutex_lock(&ei->truncate_mutex); + /* + * If the indirect block is missing while we are reading + * the chain(ext2_get_branch() returns -EAGAIN err), or + * if the chain has been changed after we grab the semaphore, + * (either because another process truncated this branch, or + * another get_block allocated this branch) re-grab the chain to see if + * the request block has been allocated or not. + * + * Since we already block the truncate/other get_block + * at this point, we will have the current copy of the chain when we + * splice the branch into the tree. + */ + if (err == -EAGAIN || !verify_chain(chain, partial)) { + while (partial > chain) { + brelse(partial->bh); + partial--; + } + partial = ext2_get_branch(inode, depth, offsets, chain, &err); + if (!partial) { + count++; + mutex_unlock(&ei->truncate_mutex); + if (err) + goto cleanup; + clear_buffer_new(bh_result); + goto got_it; + } + } + + /* + * Okay, we need to do block allocation. Lazily initialize the block + * allocation info here if necessary + */ + if (S_ISREG(inode->i_mode) && (!ei->i_block_alloc_info)) + ext2_init_block_alloc_info(inode); + + goal = ext2_find_goal(inode, iblock, partial); + + /* the number of blocks need to allocate for [d,t]indirect blocks */ + indirect_blks = (chain + depth) - partial - 1; + /* + * Next look up the indirect map to count the totoal number of + * direct blocks to allocate for this branch. + */ + count = ext2_blks_to_allocate(partial, indirect_blks, + maxblocks, blocks_to_boundary); + /* + * XXX ???? Block out ext2_truncate while we alter the tree + */ + err = ext2_alloc_branch(inode, indirect_blks, &count, goal, + offsets + (partial - chain), partial); + + if (err) { + mutex_unlock(&ei->truncate_mutex); + goto cleanup; + } + + if (IS_DAX(inode)) { + /* + * block must be initialised before we put it in the tree + * so that it's not found by another thread before it's + * initialised + */ + err = dax_clear_blocks(inode, le32_to_cpu(chain[depth-1].key), + 1 << inode->i_blkbits); + if (err) { + mutex_unlock(&ei->truncate_mutex); + goto cleanup; + } + } + + ext2_splice_branch(inode, iblock, partial, indirect_blks, count); + mutex_unlock(&ei->truncate_mutex); + set_buffer_new(bh_result); +got_it: + map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key)); + if (count > blocks_to_boundary) + set_buffer_boundary(bh_result); + err = count; + /* Clean up and exit */ + partial = chain + depth - 1; /* the whole chain */ +cleanup: + while (partial > chain) { + brelse(partial->bh); + partial--; + } + return err; +} + +int ext2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) +{ + unsigned max_blocks = bh_result->b_size >> inode->i_blkbits; + int ret = ext2_get_blocks(inode, iblock, max_blocks, + bh_result, create); + if (ret > 0) { + bh_result->b_size = (ret << inode->i_blkbits); + ret = 0; + } + return ret; + +} + +int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, + u64 start, u64 len) +{ + return generic_block_fiemap(inode, fieinfo, start, len, + ext2_get_block); +} + +static int ext2_writepage(struct page *page, struct writeback_control *wbc) +{ + return block_write_full_page(page, ext2_get_block, wbc); +} + +static int ext2_readpage(struct file *file, struct page *page) +{ + return mpage_readpage(page, ext2_get_block); +} + +static int +ext2_readpages(struct file *file, struct address_space *mapping, + struct list_head *pages, unsigned nr_pages) +{ + return mpage_readpages(mapping, pages, nr_pages, ext2_get_block); +} + +static int +ext2_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata) +{ + int ret; + + ret = block_write_begin(mapping, pos, len, flags, pagep, + ext2_get_block); + if (ret < 0) + ext2_write_failed(mapping, pos + len); + return ret; +} + +static int ext2_write_end(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) +{ + int ret; + + ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata); + if (ret < len) + ext2_write_failed(mapping, pos + len); + return ret; +} + +static int +ext2_nobh_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata) +{ + int ret; + + ret = nobh_write_begin(mapping, pos, len, flags, pagep, fsdata, + ext2_get_block); + if (ret < 0) + ext2_write_failed(mapping, pos + len); + return ret; +} + +static int ext2_nobh_writepage(struct page *page, + struct writeback_control *wbc) +{ + return nobh_writepage(page, ext2_get_block, wbc); +} + +static sector_t ext2_bmap(struct address_space *mapping, sector_t block) +{ + return generic_block_bmap(mapping,block,ext2_get_block); +} + +static ssize_t +ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) +{ + struct file *file = iocb->ki_filp; + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + size_t count = iov_iter_count(iter); + ssize_t ret; + + if (IS_DAX(inode)) + ret = dax_do_io(iocb, inode, iter, offset, ext2_get_block, NULL, + DIO_LOCKING); + else + ret = blockdev_direct_IO(iocb, inode, iter, offset, + ext2_get_block); + if (ret < 0 && iov_iter_rw(iter) == WRITE) + ext2_write_failed(mapping, offset + count); + return ret; +} + +static int +ext2_writepages(struct address_space *mapping, struct writeback_control *wbc) +{ + return mpage_writepages(mapping, wbc, ext2_get_block); +} + +const struct address_space_operations ext2_aops = { + .readpage = ext2_readpage, + .readpages = ext2_readpages, + .writepage = ext2_writepage, + .write_begin = ext2_write_begin, + .write_end = ext2_write_end, + .bmap = ext2_bmap, + .direct_IO = ext2_direct_IO, + .writepages = ext2_writepages, + .migratepage = buffer_migrate_page, + .is_partially_uptodate = block_is_partially_uptodate, + .error_remove_page = generic_error_remove_page, +}; + +const struct address_space_operations ext2_nobh_aops = { + .readpage = ext2_readpage, + .readpages = ext2_readpages, + .writepage = ext2_nobh_writepage, + .write_begin = ext2_nobh_write_begin, + .write_end = nobh_write_end, + .bmap = ext2_bmap, + .direct_IO = ext2_direct_IO, + .writepages = ext2_writepages, + .migratepage = buffer_migrate_page, + .error_remove_page = generic_error_remove_page, +}; + +/* + * Probably it should be a library function... search for first non-zero word + * or memcmp with zero_page, whatever is better for particular architecture. + * Linus? + */ +static inline int all_zeroes(__le32 *p, __le32 *q) +{ + while (p < q) + if (*p++) + return 0; + return 1; +} + +/** + * ext2_find_shared - find the indirect blocks for partial truncation. + * @inode: inode in question + * @depth: depth of the affected branch + * @offsets: offsets of pointers in that branch (see ext2_block_to_path) + * @chain: place to store the pointers to partial indirect blocks + * @top: place to the (detached) top of branch + * + * This is a helper function used by ext2_truncate(). + * + * When we do truncate() we may have to clean the ends of several indirect + * blocks but leave the blocks themselves alive. Block is partially + * truncated if some data below the new i_size is referred from it (and + * it is on the path to the first completely truncated data block, indeed). + * We have to free the top of that path along with everything to the right + * of the path. Since no allocation past the truncation point is possible + * until ext2_truncate() finishes, we may safely do the latter, but top + * of branch may require special attention - pageout below the truncation + * point might try to populate it. + * + * We atomically detach the top of branch from the tree, store the block + * number of its root in *@top, pointers to buffer_heads of partially + * truncated blocks - in @chain[].bh and pointers to their last elements + * that should not be removed - in @chain[].p. Return value is the pointer + * to last filled element of @chain. + * + * The work left to caller to do the actual freeing of subtrees: + * a) free the subtree starting from *@top + * b) free the subtrees whose roots are stored in + * (@chain[i].p+1 .. end of @chain[i].bh->b_data) + * c) free the subtrees growing from the inode past the @chain[0].p + * (no partially truncated stuff there). + */ + +static Indirect *ext2_find_shared(struct inode *inode, + int depth, + int offsets[4], + Indirect chain[4], + __le32 *top) +{ + Indirect *partial, *p; + int k, err; + + *top = 0; + for (k = depth; k > 1 && !offsets[k-1]; k--) + ; + partial = ext2_get_branch(inode, k, offsets, chain, &err); + if (!partial) + partial = chain + k-1; + /* + * If the branch acquired continuation since we've looked at it - + * fine, it should all survive and (new) top doesn't belong to us. + */ + write_lock(&EXT2_I(inode)->i_meta_lock); + if (!partial->key && *partial->p) { + write_unlock(&EXT2_I(inode)->i_meta_lock); + goto no_top; + } + for (p=partial; p>chain && all_zeroes((__le32*)p->bh->b_data,p->p); p--) + ; + /* + * OK, we've found the last block that must survive. The rest of our + * branch should be detached before unlocking. However, if that rest + * of branch is all ours and does not grow immediately from the inode + * it's easier to cheat and just decrement partial->p. + */ + if (p == chain + k - 1 && p > chain) { + p->p--; + } else { + *top = *p->p; + *p->p = 0; + } + write_unlock(&EXT2_I(inode)->i_meta_lock); + + while(partial > p) + { + brelse(partial->bh); + partial--; + } +no_top: + return partial; +} + +/** + * ext2_free_data - free a list of data blocks + * @inode: inode we are dealing with + * @p: array of block numbers + * @q: points immediately past the end of array + * + * We are freeing all blocks referred from that array (numbers are + * stored as little-endian 32-bit) and updating @inode->i_blocks + * appropriately. + */ +static inline void ext2_free_data(struct inode *inode, __le32 *p, __le32 *q) +{ + unsigned long block_to_free = 0, count = 0; + unsigned long nr; + + for ( ; p < q ; p++) { + nr = le32_to_cpu(*p); + if (nr) { + *p = 0; + /* accumulate blocks to free if they're contiguous */ + if (count == 0) + goto free_this; + else if (block_to_free == nr - count) + count++; + else { + ext2_free_blocks (inode, block_to_free, count); + mark_inode_dirty(inode); + free_this: + block_to_free = nr; + count = 1; + } + } + } + if (count > 0) { + ext2_free_blocks (inode, block_to_free, count); + mark_inode_dirty(inode); + } +} + +/** + * ext2_free_branches - free an array of branches + * @inode: inode we are dealing with + * @p: array of block numbers + * @q: pointer immediately past the end of array + * @depth: depth of the branches to free + * + * We are freeing all blocks referred from these branches (numbers are + * stored as little-endian 32-bit) and updating @inode->i_blocks + * appropriately. + */ +static void ext2_free_branches(struct inode *inode, __le32 *p, __le32 *q, int depth) +{ + struct buffer_head * bh; + unsigned long nr; + + if (depth--) { + int addr_per_block = EXT2_ADDR_PER_BLOCK(inode->i_sb); + for ( ; p < q ; p++) { + nr = le32_to_cpu(*p); + if (!nr) + continue; + *p = 0; + bh = sb_bread(inode->i_sb, nr); + /* + * A read failure? Report error and clear slot + * (should be rare). + */ + if (!bh) { + ext2_error(inode->i_sb, "ext2_free_branches", + "Read failure, inode=%ld, block=%ld", + inode->i_ino, nr); + continue; + } + ext2_free_branches(inode, + (__le32*)bh->b_data, + (__le32*)bh->b_data + addr_per_block, + depth); + bforget(bh); + ext2_free_blocks(inode, nr, 1); + mark_inode_dirty(inode); + } + } else + ext2_free_data(inode, p, q); +} + +static void __ext2_truncate_blocks(struct inode *inode, loff_t offset) +{ + __le32 *i_data = EXT2_I(inode)->i_data; + struct ext2_inode_info *ei = EXT2_I(inode); + int addr_per_block = EXT2_ADDR_PER_BLOCK(inode->i_sb); + int offsets[4]; + Indirect chain[4]; + Indirect *partial; + __le32 nr = 0; + int n; + long iblock; + unsigned blocksize; + blocksize = inode->i_sb->s_blocksize; + iblock = (offset + blocksize-1) >> EXT2_BLOCK_SIZE_BITS(inode->i_sb); + + n = ext2_block_to_path(inode, iblock, offsets, NULL); + if (n == 0) + return; + + /* + * From here we block out all ext2_get_block() callers who want to + * modify the block allocation tree. + */ + mutex_lock(&ei->truncate_mutex); + + if (n == 1) { + ext2_free_data(inode, i_data+offsets[0], + i_data + EXT2_NDIR_BLOCKS); + goto do_indirects; + } + + partial = ext2_find_shared(inode, n, offsets, chain, &nr); + /* Kill the top of shared branch (already detached) */ + if (nr) { + if (partial == chain) + mark_inode_dirty(inode); + else + mark_buffer_dirty_inode(partial->bh, inode); + ext2_free_branches(inode, &nr, &nr+1, (chain+n-1) - partial); + } + /* Clear the ends of indirect blocks on the shared branch */ + while (partial > chain) { + ext2_free_branches(inode, + partial->p + 1, + (__le32*)partial->bh->b_data+addr_per_block, + (chain+n-1) - partial); + mark_buffer_dirty_inode(partial->bh, inode); + brelse (partial->bh); + partial--; + } +do_indirects: + /* Kill the remaining (whole) subtrees */ + switch (offsets[0]) { + default: + nr = i_data[EXT2_IND_BLOCK]; + if (nr) { + i_data[EXT2_IND_BLOCK] = 0; + mark_inode_dirty(inode); + ext2_free_branches(inode, &nr, &nr+1, 1); + } + case EXT2_IND_BLOCK: + nr = i_data[EXT2_DIND_BLOCK]; + if (nr) { + i_data[EXT2_DIND_BLOCK] = 0; + mark_inode_dirty(inode); + ext2_free_branches(inode, &nr, &nr+1, 2); + } + case EXT2_DIND_BLOCK: + nr = i_data[EXT2_TIND_BLOCK]; + if (nr) { + i_data[EXT2_TIND_BLOCK] = 0; + mark_inode_dirty(inode); + ext2_free_branches(inode, &nr, &nr+1, 3); + } + case EXT2_TIND_BLOCK: + ; + } + + ext2_discard_reservation(inode); + + mutex_unlock(&ei->truncate_mutex); +} + +static void ext2_truncate_blocks(struct inode *inode, loff_t offset) +{ + /* + * XXX: it seems like a bug here that we don't allow + * IS_APPEND inode to have blocks-past-i_size trimmed off. + * review and fix this. + * + * Also would be nice to be able to handle IO errors and such, + * but that's probably too much to ask. + */ + if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + S_ISLNK(inode->i_mode))) + return; + if (ext2_inode_is_fast_symlink(inode)) + return; + if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) + return; + __ext2_truncate_blocks(inode, offset); +} + +static int ext2_setsize(struct inode *inode, loff_t newsize) +{ + int error; + + if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + S_ISLNK(inode->i_mode))) + return -EINVAL; + if (ext2_inode_is_fast_symlink(inode)) + return -EINVAL; + if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) + return -EPERM; + + inode_dio_wait(inode); + + if (IS_DAX(inode)) + error = dax_truncate_page(inode, newsize, ext2_get_block); + else if (test_opt(inode->i_sb, NOBH)) + error = nobh_truncate_page(inode->i_mapping, + newsize, ext2_get_block); + else + error = block_truncate_page(inode->i_mapping, + newsize, ext2_get_block); + if (error) + return error; + + truncate_setsize(inode, newsize); + __ext2_truncate_blocks(inode, newsize); + + inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC; + if (inode_needs_sync(inode)) { + sync_mapping_buffers(inode->i_mapping); + sync_inode_metadata(inode, 1); + } else { + mark_inode_dirty(inode); + } + + return 0; +} + +static struct ext2_inode *ext2_get_inode(struct super_block *sb, ino_t ino, + struct buffer_head **p) +{ + struct buffer_head * bh; + unsigned long block_group; + unsigned long block; + unsigned long offset; + struct ext2_group_desc * gdp; + + *p = NULL; + if ((ino != EXT2_ROOT_INO && ino < EXT2_FIRST_INO(sb)) || + ino > le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count)) + goto Einval; + + block_group = (ino - 1) / EXT2_INODES_PER_GROUP(sb); + gdp = ext2_get_group_desc(sb, block_group, NULL); + if (!gdp) + goto Egdp; + /* + * Figure out the offset within the block group inode table + */ + offset = ((ino - 1) % EXT2_INODES_PER_GROUP(sb)) * EXT2_INODE_SIZE(sb); + block = le32_to_cpu(gdp->bg_inode_table) + + (offset >> EXT2_BLOCK_SIZE_BITS(sb)); + if (!(bh = sb_bread(sb, block))) + goto Eio; + + *p = bh; + offset &= (EXT2_BLOCK_SIZE(sb) - 1); + return (struct ext2_inode *) (bh->b_data + offset); + +Einval: + ext2_error(sb, "ext2_get_inode", "bad inode number: %lu", + (unsigned long) ino); + return ERR_PTR(-EINVAL); +Eio: + ext2_error(sb, "ext2_get_inode", + "unable to read inode block - inode=%lu, block=%lu", + (unsigned long) ino, block); +Egdp: + return ERR_PTR(-EIO); +} + +void ext2_set_inode_flags(struct inode *inode) +{ + unsigned int flags = EXT2_I(inode)->i_flags; + + inode->i_flags &= ~(S_SYNC | S_APPEND | S_IMMUTABLE | S_NOATIME | + S_DIRSYNC | S_DAX); + if (flags & EXT2_SYNC_FL) + inode->i_flags |= S_SYNC; + if (flags & EXT2_APPEND_FL) + inode->i_flags |= S_APPEND; + if (flags & EXT2_IMMUTABLE_FL) + inode->i_flags |= S_IMMUTABLE; + if (flags & EXT2_NOATIME_FL) + inode->i_flags |= S_NOATIME; + if (flags & EXT2_DIRSYNC_FL) + inode->i_flags |= S_DIRSYNC; + if (test_opt(inode->i_sb, DAX)) + inode->i_flags |= S_DAX; +} + +/* Propagate flags from i_flags to EXT2_I(inode)->i_flags */ +void ext2_get_inode_flags(struct ext2_inode_info *ei) +{ + unsigned int flags = ei->vfs_inode.i_flags; + + ei->i_flags &= ~(EXT2_SYNC_FL|EXT2_APPEND_FL| + EXT2_IMMUTABLE_FL|EXT2_NOATIME_FL|EXT2_DIRSYNC_FL); + if (flags & S_SYNC) + ei->i_flags |= EXT2_SYNC_FL; + if (flags & S_APPEND) + ei->i_flags |= EXT2_APPEND_FL; + if (flags & S_IMMUTABLE) + ei->i_flags |= EXT2_IMMUTABLE_FL; + if (flags & S_NOATIME) + ei->i_flags |= EXT2_NOATIME_FL; + if (flags & S_DIRSYNC) + ei->i_flags |= EXT2_DIRSYNC_FL; +} + +struct inode *ext2_iget (struct super_block *sb, unsigned long ino) +{ + struct ext2_inode_info *ei; + struct buffer_head * bh; + struct ext2_inode *raw_inode; + struct inode *inode; + long ret = -EIO; + int n; + uid_t i_uid; + gid_t i_gid; + + inode = iget_locked(sb, ino); + if (!inode) + return ERR_PTR(-ENOMEM); + if (!(inode->i_state & I_NEW)) + return inode; + + ei = EXT2_I(inode); + ei->i_block_alloc_info = NULL; + + raw_inode = ext2_get_inode(inode->i_sb, ino, &bh); + if (IS_ERR(raw_inode)) { + ret = PTR_ERR(raw_inode); + goto bad_inode; + } + + inode->i_mode = le16_to_cpu(raw_inode->i_mode); + i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); + i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low); + if (!(test_opt (inode->i_sb, NO_UID32))) { + i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; + i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; + } + i_uid_write(inode, i_uid); + i_gid_write(inode, i_gid); + set_nlink(inode, le16_to_cpu(raw_inode->i_links_count)); + inode->i_size = le32_to_cpu(raw_inode->i_size); + inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime); + inode->i_ctime.tv_sec = (signed)le32_to_cpu(raw_inode->i_ctime); + inode->i_mtime.tv_sec = (signed)le32_to_cpu(raw_inode->i_mtime); + inode->i_atime.tv_nsec = inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec = 0; + ei->i_dtime = le32_to_cpu(raw_inode->i_dtime); + /* We now have enough fields to check if the inode was active or not. + * This is needed because nfsd might try to access dead inodes + * the test is that same one that e2fsck uses + * NeilBrown 1999oct15 + */ + if (inode->i_nlink == 0 && (inode->i_mode == 0 || ei->i_dtime)) { + /* this inode is deleted */ + brelse (bh); + ret = -ESTALE; + goto bad_inode; + } + inode->i_blocks = le32_to_cpu(raw_inode->i_blocks); + ei->i_flags = le32_to_cpu(raw_inode->i_flags); + ei->i_faddr = le32_to_cpu(raw_inode->i_faddr); + ei->i_frag_no = raw_inode->i_frag; + ei->i_frag_size = raw_inode->i_fsize; + ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl); + ei->i_dir_acl = 0; + if (S_ISREG(inode->i_mode)) + inode->i_size |= ((__u64)le32_to_cpu(raw_inode->i_size_high)) << 32; + else + ei->i_dir_acl = le32_to_cpu(raw_inode->i_dir_acl); + ei->i_dtime = 0; + inode->i_generation = le32_to_cpu(raw_inode->i_generation); + ei->i_state = 0; + ei->i_block_group = (ino - 1) / EXT2_INODES_PER_GROUP(inode->i_sb); + ei->i_dir_start_lookup = 0; + + /* + * NOTE! The in-memory inode i_data array is in little-endian order + * even on big-endian machines: we do NOT byteswap the block numbers! + */ + for (n = 0; n < EXT2_N_BLOCKS; n++) + ei->i_data[n] = raw_inode->i_block[n]; + + if (S_ISREG(inode->i_mode)) { + inode->i_op = &ext2_file_inode_operations; + if (test_opt(inode->i_sb, NOBH)) { + inode->i_mapping->a_ops = &ext2_nobh_aops; + inode->i_fop = &ext2_file_operations; + } else { + inode->i_mapping->a_ops = &ext2_aops; + inode->i_fop = &ext2_file_operations; + } + } else if (S_ISDIR(inode->i_mode)) { + inode->i_op = &ext2_dir_inode_operations; + inode->i_fop = &ext2_dir_operations; + if (test_opt(inode->i_sb, NOBH)) + inode->i_mapping->a_ops = &ext2_nobh_aops; + else + inode->i_mapping->a_ops = &ext2_aops; + } else if (S_ISLNK(inode->i_mode)) { + if (ext2_inode_is_fast_symlink(inode)) { + inode->i_op = &ext2_fast_symlink_inode_operations; + nd_terminate_link(ei->i_data, inode->i_size, + sizeof(ei->i_data) - 1); + } else { + inode->i_op = &ext2_symlink_inode_operations; + if (test_opt(inode->i_sb, NOBH)) + inode->i_mapping->a_ops = &ext2_nobh_aops; + else + inode->i_mapping->a_ops = &ext2_aops; + } + } else { + inode->i_op = &ext2_special_inode_operations; + if (raw_inode->i_block[0]) + init_special_inode(inode, inode->i_mode, + old_decode_dev(le32_to_cpu(raw_inode->i_block[0]))); + else + init_special_inode(inode, inode->i_mode, + new_decode_dev(le32_to_cpu(raw_inode->i_block[1]))); + } + brelse (bh); + ext2_set_inode_flags(inode); + unlock_new_inode(inode); + return inode; + +bad_inode: + iget_failed(inode); + return ERR_PTR(ret); +} + +static int __ext2_write_inode(struct inode *inode, int do_sync) +{ + struct ext2_inode_info *ei = EXT2_I(inode); + struct super_block *sb = inode->i_sb; + ino_t ino = inode->i_ino; + uid_t uid = i_uid_read(inode); + gid_t gid = i_gid_read(inode); + struct buffer_head * bh; + struct ext2_inode * raw_inode = ext2_get_inode(sb, ino, &bh); + int n; + int err = 0; + + if (IS_ERR(raw_inode)) + return -EIO; + + /* For fields not not tracking in the in-memory inode, + * initialise them to zero for new inodes. */ + if (ei->i_state & EXT2_STATE_NEW) + memset(raw_inode, 0, EXT2_SB(sb)->s_inode_size); + + ext2_get_inode_flags(ei); + raw_inode->i_mode = cpu_to_le16(inode->i_mode); + if (!(test_opt(sb, NO_UID32))) { + raw_inode->i_uid_low = cpu_to_le16(low_16_bits(uid)); + raw_inode->i_gid_low = cpu_to_le16(low_16_bits(gid)); +/* + * Fix up interoperability with old kernels. Otherwise, old inodes get + * re-used with the upper 16 bits of the uid/gid intact + */ + if (!ei->i_dtime) { + raw_inode->i_uid_high = cpu_to_le16(high_16_bits(uid)); + raw_inode->i_gid_high = cpu_to_le16(high_16_bits(gid)); + } else { + raw_inode->i_uid_high = 0; + raw_inode->i_gid_high = 0; + } + } else { + raw_inode->i_uid_low = cpu_to_le16(fs_high2lowuid(uid)); + raw_inode->i_gid_low = cpu_to_le16(fs_high2lowgid(gid)); + raw_inode->i_uid_high = 0; + raw_inode->i_gid_high = 0; + } + raw_inode->i_links_count = cpu_to_le16(inode->i_nlink); + raw_inode->i_size = cpu_to_le32(inode->i_size); + raw_inode->i_atime = cpu_to_le32(inode->i_atime.tv_sec); + raw_inode->i_ctime = cpu_to_le32(inode->i_ctime.tv_sec); + raw_inode->i_mtime = cpu_to_le32(inode->i_mtime.tv_sec); + + raw_inode->i_blocks = cpu_to_le32(inode->i_blocks); + raw_inode->i_dtime = cpu_to_le32(ei->i_dtime); + raw_inode->i_flags = cpu_to_le32(ei->i_flags); + raw_inode->i_faddr = cpu_to_le32(ei->i_faddr); + raw_inode->i_frag = ei->i_frag_no; + raw_inode->i_fsize = ei->i_frag_size; + raw_inode->i_file_acl = cpu_to_le32(ei->i_file_acl); + if (!S_ISREG(inode->i_mode)) + raw_inode->i_dir_acl = cpu_to_le32(ei->i_dir_acl); + else { + raw_inode->i_size_high = cpu_to_le32(inode->i_size >> 32); + if (inode->i_size > 0x7fffffffULL) { + if (!EXT2_HAS_RO_COMPAT_FEATURE(sb, + EXT2_FEATURE_RO_COMPAT_LARGE_FILE) || + EXT2_SB(sb)->s_es->s_rev_level == + cpu_to_le32(EXT2_GOOD_OLD_REV)) { + /* If this is the first large file + * created, add a flag to the superblock. + */ + spin_lock(&EXT2_SB(sb)->s_lock); + ext2_update_dynamic_rev(sb); + EXT2_SET_RO_COMPAT_FEATURE(sb, + EXT2_FEATURE_RO_COMPAT_LARGE_FILE); + spin_unlock(&EXT2_SB(sb)->s_lock); + ext2_write_super(sb); + } + } + } + + raw_inode->i_generation = cpu_to_le32(inode->i_generation); + if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) { + if (old_valid_dev(inode->i_rdev)) { + raw_inode->i_block[0] = + cpu_to_le32(old_encode_dev(inode->i_rdev)); + raw_inode->i_block[1] = 0; + } else { + raw_inode->i_block[0] = 0; + raw_inode->i_block[1] = + cpu_to_le32(new_encode_dev(inode->i_rdev)); + raw_inode->i_block[2] = 0; + } + } else for (n = 0; n < EXT2_N_BLOCKS; n++) + raw_inode->i_block[n] = ei->i_data[n]; + mark_buffer_dirty(bh); + if (do_sync) { + sync_dirty_buffer(bh); + if (buffer_req(bh) && !buffer_uptodate(bh)) { + printk ("IO error syncing ext2 inode [%s:%08lx]\n", + sb->s_id, (unsigned long) ino); + err = -EIO; + } + } + ei->i_state &= ~EXT2_STATE_NEW; + brelse (bh); + return err; +} + +int ext2_write_inode(struct inode *inode, struct writeback_control *wbc) +{ + return __ext2_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL); +} + +int ext2_setattr(struct dentry *dentry, struct iattr *iattr) +{ + struct inode *inode = d_inode(dentry); + int error; + + error = inode_change_ok(inode, iattr); + if (error) + return error; + + if (is_quota_modification(inode, iattr)) + dquot_initialize(inode); + if ((iattr->ia_valid & ATTR_UID && !uid_eq(iattr->ia_uid, inode->i_uid)) || + (iattr->ia_valid & ATTR_GID && !gid_eq(iattr->ia_gid, inode->i_gid))) { + error = dquot_transfer(inode, iattr); + if (error) + return error; + } + if (iattr->ia_valid & ATTR_SIZE && iattr->ia_size != inode->i_size) { + error = ext2_setsize(inode, iattr->ia_size); + if (error) + return error; + } + setattr_copy(inode, iattr); + if (iattr->ia_valid & ATTR_MODE) + error = posix_acl_chmod(inode, inode->i_mode); + mark_inode_dirty(inode); + + return error; +} diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c new file mode 100644 index 000000000..5d46c0986 --- /dev/null +++ b/fs/ext2/ioctl.c @@ -0,0 +1,188 @@ +/* + * linux/fs/ext2/ioctl.c + * + * Copyright (C) 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + */ + +#include "ext2.h" +#include +#include +#include +#include +#include +#include +#include + + +long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct ext2_inode_info *ei = EXT2_I(inode); + unsigned int flags; + unsigned short rsv_window_size; + int ret; + + ext2_debug ("cmd = %u, arg = %lu\n", cmd, arg); + + switch (cmd) { + case EXT2_IOC_GETFLAGS: + ext2_get_inode_flags(ei); + flags = ei->i_flags & EXT2_FL_USER_VISIBLE; + return put_user(flags, (int __user *) arg); + case EXT2_IOC_SETFLAGS: { + unsigned int oldflags; + + ret = mnt_want_write_file(filp); + if (ret) + return ret; + + if (!inode_owner_or_capable(inode)) { + ret = -EACCES; + goto setflags_out; + } + + if (get_user(flags, (int __user *) arg)) { + ret = -EFAULT; + goto setflags_out; + } + + flags = ext2_mask_flags(inode->i_mode, flags); + + mutex_lock(&inode->i_mutex); + /* Is it quota file? Do not allow user to mess with it */ + if (IS_NOQUOTA(inode)) { + mutex_unlock(&inode->i_mutex); + ret = -EPERM; + goto setflags_out; + } + oldflags = ei->i_flags; + + /* + * The IMMUTABLE and APPEND_ONLY flags can only be changed by + * the relevant capability. + * + * This test looks nicer. Thanks to Pauline Middelink + */ + if ((flags ^ oldflags) & (EXT2_APPEND_FL | EXT2_IMMUTABLE_FL)) { + if (!capable(CAP_LINUX_IMMUTABLE)) { + mutex_unlock(&inode->i_mutex); + ret = -EPERM; + goto setflags_out; + } + } + + flags = flags & EXT2_FL_USER_MODIFIABLE; + flags |= oldflags & ~EXT2_FL_USER_MODIFIABLE; + ei->i_flags = flags; + + ext2_set_inode_flags(inode); + inode->i_ctime = CURRENT_TIME_SEC; + mutex_unlock(&inode->i_mutex); + + mark_inode_dirty(inode); +setflags_out: + mnt_drop_write_file(filp); + return ret; + } + case EXT2_IOC_GETVERSION: + return put_user(inode->i_generation, (int __user *) arg); + case EXT2_IOC_SETVERSION: { + __u32 generation; + + if (!inode_owner_or_capable(inode)) + return -EPERM; + ret = mnt_want_write_file(filp); + if (ret) + return ret; + if (get_user(generation, (int __user *) arg)) { + ret = -EFAULT; + goto setversion_out; + } + + mutex_lock(&inode->i_mutex); + inode->i_ctime = CURRENT_TIME_SEC; + inode->i_generation = generation; + mutex_unlock(&inode->i_mutex); + + mark_inode_dirty(inode); +setversion_out: + mnt_drop_write_file(filp); + return ret; + } + case EXT2_IOC_GETRSVSZ: + if (test_opt(inode->i_sb, RESERVATION) + && S_ISREG(inode->i_mode) + && ei->i_block_alloc_info) { + rsv_window_size = ei->i_block_alloc_info->rsv_window_node.rsv_goal_size; + return put_user(rsv_window_size, (int __user *)arg); + } + return -ENOTTY; + case EXT2_IOC_SETRSVSZ: { + + if (!test_opt(inode->i_sb, RESERVATION) ||!S_ISREG(inode->i_mode)) + return -ENOTTY; + + if (!inode_owner_or_capable(inode)) + return -EACCES; + + if (get_user(rsv_window_size, (int __user *)arg)) + return -EFAULT; + + ret = mnt_want_write_file(filp); + if (ret) + return ret; + + if (rsv_window_size > EXT2_MAX_RESERVE_BLOCKS) + rsv_window_size = EXT2_MAX_RESERVE_BLOCKS; + + /* + * need to allocate reservation structure for this inode + * before set the window size + */ + /* + * XXX What lock should protect the rsv_goal_size? + * Accessed in ext2_get_block only. ext3 uses i_truncate. + */ + mutex_lock(&ei->truncate_mutex); + if (!ei->i_block_alloc_info) + ext2_init_block_alloc_info(inode); + + if (ei->i_block_alloc_info){ + struct ext2_reserve_window_node *rsv = &ei->i_block_alloc_info->rsv_window_node; + rsv->rsv_goal_size = rsv_window_size; + } + mutex_unlock(&ei->truncate_mutex); + mnt_drop_write_file(filp); + return 0; + } + default: + return -ENOTTY; + } +} + +#ifdef CONFIG_COMPAT +long ext2_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + /* These are just misnamed, they actually get/put from/to user an int */ + switch (cmd) { + case EXT2_IOC32_GETFLAGS: + cmd = EXT2_IOC_GETFLAGS; + break; + case EXT2_IOC32_SETFLAGS: + cmd = EXT2_IOC_SETFLAGS; + break; + case EXT2_IOC32_GETVERSION: + cmd = EXT2_IOC_GETVERSION; + break; + case EXT2_IOC32_SETVERSION: + cmd = EXT2_IOC_SETVERSION; + break; + default: + return -ENOIOCTLCMD; + } + return ext2_ioctl(file, cmd, (unsigned long) compat_ptr(arg)); +} +#endif diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c new file mode 100644 index 000000000..3e074a9cc --- /dev/null +++ b/fs/ext2/namei.c @@ -0,0 +1,431 @@ +/* + * linux/fs/ext2/namei.c + * + * Rewrite to pagecache. Almost all code had been changed, so blame me + * if the things go wrong. Please, send bug reports to + * viro@parcelfarce.linux.theplanet.co.uk + * + * Stuff here is basically a glue between the VFS and generic UNIXish + * filesystem that keeps everything in pagecache. All knowledge of the + * directory layout is in fs/ext2/dir.c - it turned out to be easily separatable + * and it's easier to debug that way. In principle we might want to + * generalize that a bit and turn it into a library. Or not. + * + * The only non-static object here is ext2_dir_inode_operations. + * + * TODO: get rid of kmap() use, add readahead. + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/fs/minix/namei.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * Big-endian to little-endian byte-swapping/bitmaps by + * David S. Miller (davem@caip.rutgers.edu), 1995 + */ + +#include +#include +#include "ext2.h" +#include "xattr.h" +#include "acl.h" + +static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode) +{ + int err = ext2_add_link(dentry, inode); + if (!err) { + unlock_new_inode(inode); + d_instantiate(dentry, inode); + return 0; + } + inode_dec_link_count(inode); + unlock_new_inode(inode); + iput(inode); + return err; +} + +/* + * Methods themselves. + */ + +static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, unsigned int flags) +{ + struct inode * inode; + ino_t ino; + + if (dentry->d_name.len > EXT2_NAME_LEN) + return ERR_PTR(-ENAMETOOLONG); + + ino = ext2_inode_by_name(dir, &dentry->d_name); + inode = NULL; + if (ino) { + inode = ext2_iget(dir->i_sb, ino); + if (inode == ERR_PTR(-ESTALE)) { + ext2_error(dir->i_sb, __func__, + "deleted inode referenced: %lu", + (unsigned long) ino); + return ERR_PTR(-EIO); + } + } + return d_splice_alias(inode, dentry); +} + +struct dentry *ext2_get_parent(struct dentry *child) +{ + struct qstr dotdot = QSTR_INIT("..", 2); + unsigned long ino = ext2_inode_by_name(d_inode(child), &dotdot); + if (!ino) + return ERR_PTR(-ENOENT); + return d_obtain_alias(ext2_iget(d_inode(child)->i_sb, ino)); +} + +/* + * By the time this is called, we already have created + * the directory cache entry for the new file, but it + * is so far negative - it has no inode. + * + * If the create succeeds, we fill in the inode information + * with d_instantiate(). + */ +static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode, bool excl) +{ + struct inode *inode; + + dquot_initialize(dir); + + inode = ext2_new_inode(dir, mode, &dentry->d_name); + if (IS_ERR(inode)) + return PTR_ERR(inode); + + inode->i_op = &ext2_file_inode_operations; + if (test_opt(inode->i_sb, NOBH)) { + inode->i_mapping->a_ops = &ext2_nobh_aops; + inode->i_fop = &ext2_file_operations; + } else { + inode->i_mapping->a_ops = &ext2_aops; + inode->i_fop = &ext2_file_operations; + } + mark_inode_dirty(inode); + return ext2_add_nondir(dentry, inode); +} + +static int ext2_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + struct inode *inode = ext2_new_inode(dir, mode, NULL); + if (IS_ERR(inode)) + return PTR_ERR(inode); + + inode->i_op = &ext2_file_inode_operations; + if (test_opt(inode->i_sb, NOBH)) { + inode->i_mapping->a_ops = &ext2_nobh_aops; + inode->i_fop = &ext2_file_operations; + } else { + inode->i_mapping->a_ops = &ext2_aops; + inode->i_fop = &ext2_file_operations; + } + mark_inode_dirty(inode); + d_tmpfile(dentry, inode); + unlock_new_inode(inode); + return 0; +} + +static int ext2_mknod (struct inode * dir, struct dentry *dentry, umode_t mode, dev_t rdev) +{ + struct inode * inode; + int err; + + if (!new_valid_dev(rdev)) + return -EINVAL; + + dquot_initialize(dir); + + inode = ext2_new_inode (dir, mode, &dentry->d_name); + err = PTR_ERR(inode); + if (!IS_ERR(inode)) { + init_special_inode(inode, inode->i_mode, rdev); +#ifdef CONFIG_EXT2_FS_XATTR + inode->i_op = &ext2_special_inode_operations; +#endif + mark_inode_dirty(inode); + err = ext2_add_nondir(dentry, inode); + } + return err; +} + +static int ext2_symlink (struct inode * dir, struct dentry * dentry, + const char * symname) +{ + struct super_block * sb = dir->i_sb; + int err = -ENAMETOOLONG; + unsigned l = strlen(symname)+1; + struct inode * inode; + + if (l > sb->s_blocksize) + goto out; + + dquot_initialize(dir); + + inode = ext2_new_inode (dir, S_IFLNK | S_IRWXUGO, &dentry->d_name); + err = PTR_ERR(inode); + if (IS_ERR(inode)) + goto out; + + if (l > sizeof (EXT2_I(inode)->i_data)) { + /* slow symlink */ + inode->i_op = &ext2_symlink_inode_operations; + if (test_opt(inode->i_sb, NOBH)) + inode->i_mapping->a_ops = &ext2_nobh_aops; + else + inode->i_mapping->a_ops = &ext2_aops; + err = page_symlink(inode, symname, l); + if (err) + goto out_fail; + } else { + /* fast symlink */ + inode->i_op = &ext2_fast_symlink_inode_operations; + memcpy((char*)(EXT2_I(inode)->i_data),symname,l); + inode->i_size = l-1; + } + mark_inode_dirty(inode); + + err = ext2_add_nondir(dentry, inode); +out: + return err; + +out_fail: + inode_dec_link_count(inode); + unlock_new_inode(inode); + iput (inode); + goto out; +} + +static int ext2_link (struct dentry * old_dentry, struct inode * dir, + struct dentry *dentry) +{ + struct inode *inode = d_inode(old_dentry); + int err; + + dquot_initialize(dir); + + inode->i_ctime = CURRENT_TIME_SEC; + inode_inc_link_count(inode); + ihold(inode); + + err = ext2_add_link(dentry, inode); + if (!err) { + d_instantiate(dentry, inode); + return 0; + } + inode_dec_link_count(inode); + iput(inode); + return err; +} + +static int ext2_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode) +{ + struct inode * inode; + int err; + + dquot_initialize(dir); + + inode_inc_link_count(dir); + + inode = ext2_new_inode(dir, S_IFDIR | mode, &dentry->d_name); + err = PTR_ERR(inode); + if (IS_ERR(inode)) + goto out_dir; + + inode->i_op = &ext2_dir_inode_operations; + inode->i_fop = &ext2_dir_operations; + if (test_opt(inode->i_sb, NOBH)) + inode->i_mapping->a_ops = &ext2_nobh_aops; + else + inode->i_mapping->a_ops = &ext2_aops; + + inode_inc_link_count(inode); + + err = ext2_make_empty(inode, dir); + if (err) + goto out_fail; + + err = ext2_add_link(dentry, inode); + if (err) + goto out_fail; + + unlock_new_inode(inode); + d_instantiate(dentry, inode); +out: + return err; + +out_fail: + inode_dec_link_count(inode); + inode_dec_link_count(inode); + unlock_new_inode(inode); + iput(inode); +out_dir: + inode_dec_link_count(dir); + goto out; +} + +static int ext2_unlink(struct inode * dir, struct dentry *dentry) +{ + struct inode * inode = d_inode(dentry); + struct ext2_dir_entry_2 * de; + struct page * page; + int err = -ENOENT; + + dquot_initialize(dir); + + de = ext2_find_entry (dir, &dentry->d_name, &page); + if (!de) + goto out; + + err = ext2_delete_entry (de, page); + if (err) + goto out; + + inode->i_ctime = dir->i_ctime; + inode_dec_link_count(inode); + err = 0; +out: + return err; +} + +static int ext2_rmdir (struct inode * dir, struct dentry *dentry) +{ + struct inode * inode = d_inode(dentry); + int err = -ENOTEMPTY; + + if (ext2_empty_dir(inode)) { + err = ext2_unlink(dir, dentry); + if (!err) { + inode->i_size = 0; + inode_dec_link_count(inode); + inode_dec_link_count(dir); + } + } + return err; +} + +static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry, + struct inode * new_dir, struct dentry * new_dentry ) +{ + struct inode * old_inode = d_inode(old_dentry); + struct inode * new_inode = d_inode(new_dentry); + struct page * dir_page = NULL; + struct ext2_dir_entry_2 * dir_de = NULL; + struct page * old_page; + struct ext2_dir_entry_2 * old_de; + int err = -ENOENT; + + dquot_initialize(old_dir); + dquot_initialize(new_dir); + + old_de = ext2_find_entry (old_dir, &old_dentry->d_name, &old_page); + if (!old_de) + goto out; + + if (S_ISDIR(old_inode->i_mode)) { + err = -EIO; + dir_de = ext2_dotdot(old_inode, &dir_page); + if (!dir_de) + goto out_old; + } + + if (new_inode) { + struct page *new_page; + struct ext2_dir_entry_2 *new_de; + + err = -ENOTEMPTY; + if (dir_de && !ext2_empty_dir (new_inode)) + goto out_dir; + + err = -ENOENT; + new_de = ext2_find_entry (new_dir, &new_dentry->d_name, &new_page); + if (!new_de) + goto out_dir; + ext2_set_link(new_dir, new_de, new_page, old_inode, 1); + new_inode->i_ctime = CURRENT_TIME_SEC; + if (dir_de) + drop_nlink(new_inode); + inode_dec_link_count(new_inode); + } else { + err = ext2_add_link(new_dentry, old_inode); + if (err) + goto out_dir; + if (dir_de) + inode_inc_link_count(new_dir); + } + + /* + * Like most other Unix systems, set the ctime for inodes on a + * rename. + */ + old_inode->i_ctime = CURRENT_TIME_SEC; + mark_inode_dirty(old_inode); + + ext2_delete_entry (old_de, old_page); + + if (dir_de) { + if (old_dir != new_dir) + ext2_set_link(old_inode, dir_de, dir_page, new_dir, 0); + else { + kunmap(dir_page); + page_cache_release(dir_page); + } + inode_dec_link_count(old_dir); + } + return 0; + + +out_dir: + if (dir_de) { + kunmap(dir_page); + page_cache_release(dir_page); + } +out_old: + kunmap(old_page); + page_cache_release(old_page); +out: + return err; +} + +const struct inode_operations ext2_dir_inode_operations = { + .create = ext2_create, + .lookup = ext2_lookup, + .link = ext2_link, + .unlink = ext2_unlink, + .symlink = ext2_symlink, + .mkdir = ext2_mkdir, + .rmdir = ext2_rmdir, + .mknod = ext2_mknod, + .rename = ext2_rename, +#ifdef CONFIG_EXT2_FS_XATTR + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = ext2_listxattr, + .removexattr = generic_removexattr, +#endif + .setattr = ext2_setattr, + .get_acl = ext2_get_acl, + .set_acl = ext2_set_acl, + .tmpfile = ext2_tmpfile, +}; + +const struct inode_operations ext2_special_inode_operations = { +#ifdef CONFIG_EXT2_FS_XATTR + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = ext2_listxattr, + .removexattr = generic_removexattr, +#endif + .setattr = ext2_setattr, + .get_acl = ext2_get_acl, + .set_acl = ext2_set_acl, +}; diff --git a/fs/ext2/super.c b/fs/ext2/super.c new file mode 100644 index 000000000..d0e746e96 --- /dev/null +++ b/fs/ext2/super.c @@ -0,0 +1,1580 @@ +/* + * linux/fs/ext2/super.c + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/fs/minix/inode.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * Big-endian to little-endian byte-swapping/bitmaps by + * David S. Miller (davem@caip.rutgers.edu), 1995 + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "ext2.h" +#include "xattr.h" +#include "acl.h" + +static void ext2_sync_super(struct super_block *sb, + struct ext2_super_block *es, int wait); +static int ext2_remount (struct super_block * sb, int * flags, char * data); +static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf); +static int ext2_sync_fs(struct super_block *sb, int wait); +static int ext2_freeze(struct super_block *sb); +static int ext2_unfreeze(struct super_block *sb); + +void ext2_error(struct super_block *sb, const char *function, + const char *fmt, ...) +{ + struct va_format vaf; + va_list args; + struct ext2_sb_info *sbi = EXT2_SB(sb); + struct ext2_super_block *es = sbi->s_es; + + if (!(sb->s_flags & MS_RDONLY)) { + spin_lock(&sbi->s_lock); + sbi->s_mount_state |= EXT2_ERROR_FS; + es->s_state |= cpu_to_le16(EXT2_ERROR_FS); + spin_unlock(&sbi->s_lock); + ext2_sync_super(sb, es, 1); + } + + va_start(args, fmt); + + vaf.fmt = fmt; + vaf.va = &args; + + printk(KERN_CRIT "EXT2-fs (%s): error: %s: %pV\n", + sb->s_id, function, &vaf); + + va_end(args); + + if (test_opt(sb, ERRORS_PANIC)) + panic("EXT2-fs: panic from previous error\n"); + if (test_opt(sb, ERRORS_RO)) { + ext2_msg(sb, KERN_CRIT, + "error: remounting filesystem read-only"); + sb->s_flags |= MS_RDONLY; + } +} + +void ext2_msg(struct super_block *sb, const char *prefix, + const char *fmt, ...) +{ + struct va_format vaf; + va_list args; + + va_start(args, fmt); + + vaf.fmt = fmt; + vaf.va = &args; + + printk("%sEXT2-fs (%s): %pV\n", prefix, sb->s_id, &vaf); + + va_end(args); +} + +/* + * This must be called with sbi->s_lock held. + */ +void ext2_update_dynamic_rev(struct super_block *sb) +{ + struct ext2_super_block *es = EXT2_SB(sb)->s_es; + + if (le32_to_cpu(es->s_rev_level) > EXT2_GOOD_OLD_REV) + return; + + ext2_msg(sb, KERN_WARNING, + "warning: updating to rev %d because of " + "new feature flag, running e2fsck is recommended", + EXT2_DYNAMIC_REV); + + es->s_first_ino = cpu_to_le32(EXT2_GOOD_OLD_FIRST_INO); + es->s_inode_size = cpu_to_le16(EXT2_GOOD_OLD_INODE_SIZE); + es->s_rev_level = cpu_to_le32(EXT2_DYNAMIC_REV); + /* leave es->s_feature_*compat flags alone */ + /* es->s_uuid will be set by e2fsck if empty */ + + /* + * The rest of the superblock fields should be zero, and if not it + * means they are likely already in use, so leave them alone. We + * can leave it up to e2fsck to clean up any inconsistencies there. + */ +} + +static void ext2_put_super (struct super_block * sb) +{ + int db_count; + int i; + struct ext2_sb_info *sbi = EXT2_SB(sb); + + dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); + + ext2_xattr_put_super(sb); + if (!(sb->s_flags & MS_RDONLY)) { + struct ext2_super_block *es = sbi->s_es; + + spin_lock(&sbi->s_lock); + es->s_state = cpu_to_le16(sbi->s_mount_state); + spin_unlock(&sbi->s_lock); + ext2_sync_super(sb, es, 1); + } + db_count = sbi->s_gdb_count; + for (i = 0; i < db_count; i++) + if (sbi->s_group_desc[i]) + brelse (sbi->s_group_desc[i]); + kfree(sbi->s_group_desc); + kfree(sbi->s_debts); + percpu_counter_destroy(&sbi->s_freeblocks_counter); + percpu_counter_destroy(&sbi->s_freeinodes_counter); + percpu_counter_destroy(&sbi->s_dirs_counter); + brelse (sbi->s_sbh); + sb->s_fs_info = NULL; + kfree(sbi->s_blockgroup_lock); + kfree(sbi); +} + +static struct kmem_cache * ext2_inode_cachep; + +static struct inode *ext2_alloc_inode(struct super_block *sb) +{ + struct ext2_inode_info *ei; + ei = kmem_cache_alloc(ext2_inode_cachep, GFP_KERNEL); + if (!ei) + return NULL; + ei->i_block_alloc_info = NULL; + ei->vfs_inode.i_version = 1; +#ifdef CONFIG_QUOTA + memset(&ei->i_dquot, 0, sizeof(ei->i_dquot)); +#endif + + return &ei->vfs_inode; +} + +static void ext2_i_callback(struct rcu_head *head) +{ + struct inode *inode = container_of(head, struct inode, i_rcu); + kmem_cache_free(ext2_inode_cachep, EXT2_I(inode)); +} + +static void ext2_destroy_inode(struct inode *inode) +{ + call_rcu(&inode->i_rcu, ext2_i_callback); +} + +static void init_once(void *foo) +{ + struct ext2_inode_info *ei = (struct ext2_inode_info *) foo; + + rwlock_init(&ei->i_meta_lock); +#ifdef CONFIG_EXT2_FS_XATTR + init_rwsem(&ei->xattr_sem); +#endif + mutex_init(&ei->truncate_mutex); + inode_init_once(&ei->vfs_inode); +} + +static int __init init_inodecache(void) +{ + ext2_inode_cachep = kmem_cache_create("ext2_inode_cache", + sizeof(struct ext2_inode_info), + 0, (SLAB_RECLAIM_ACCOUNT| + SLAB_MEM_SPREAD), + init_once); + if (ext2_inode_cachep == NULL) + return -ENOMEM; + return 0; +} + +static void destroy_inodecache(void) +{ + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); + kmem_cache_destroy(ext2_inode_cachep); +} + +static int ext2_show_options(struct seq_file *seq, struct dentry *root) +{ + struct super_block *sb = root->d_sb; + struct ext2_sb_info *sbi = EXT2_SB(sb); + struct ext2_super_block *es = sbi->s_es; + unsigned long def_mount_opts; + + spin_lock(&sbi->s_lock); + def_mount_opts = le32_to_cpu(es->s_default_mount_opts); + + if (sbi->s_sb_block != 1) + seq_printf(seq, ",sb=%lu", sbi->s_sb_block); + if (test_opt(sb, MINIX_DF)) + seq_puts(seq, ",minixdf"); + if (test_opt(sb, GRPID)) + seq_puts(seq, ",grpid"); + if (!test_opt(sb, GRPID) && (def_mount_opts & EXT2_DEFM_BSDGROUPS)) + seq_puts(seq, ",nogrpid"); + if (!uid_eq(sbi->s_resuid, make_kuid(&init_user_ns, EXT2_DEF_RESUID)) || + le16_to_cpu(es->s_def_resuid) != EXT2_DEF_RESUID) { + seq_printf(seq, ",resuid=%u", + from_kuid_munged(&init_user_ns, sbi->s_resuid)); + } + if (!gid_eq(sbi->s_resgid, make_kgid(&init_user_ns, EXT2_DEF_RESGID)) || + le16_to_cpu(es->s_def_resgid) != EXT2_DEF_RESGID) { + seq_printf(seq, ",resgid=%u", + from_kgid_munged(&init_user_ns, sbi->s_resgid)); + } + if (test_opt(sb, ERRORS_RO)) { + int def_errors = le16_to_cpu(es->s_errors); + + if (def_errors == EXT2_ERRORS_PANIC || + def_errors == EXT2_ERRORS_CONTINUE) { + seq_puts(seq, ",errors=remount-ro"); + } + } + if (test_opt(sb, ERRORS_CONT)) + seq_puts(seq, ",errors=continue"); + if (test_opt(sb, ERRORS_PANIC)) + seq_puts(seq, ",errors=panic"); + if (test_opt(sb, NO_UID32)) + seq_puts(seq, ",nouid32"); + if (test_opt(sb, DEBUG)) + seq_puts(seq, ",debug"); + if (test_opt(sb, OLDALLOC)) + seq_puts(seq, ",oldalloc"); + +#ifdef CONFIG_EXT2_FS_XATTR + if (test_opt(sb, XATTR_USER)) + seq_puts(seq, ",user_xattr"); + if (!test_opt(sb, XATTR_USER) && + (def_mount_opts & EXT2_DEFM_XATTR_USER)) { + seq_puts(seq, ",nouser_xattr"); + } +#endif + +#ifdef CONFIG_EXT2_FS_POSIX_ACL + if (test_opt(sb, POSIX_ACL)) + seq_puts(seq, ",acl"); + if (!test_opt(sb, POSIX_ACL) && (def_mount_opts & EXT2_DEFM_ACL)) + seq_puts(seq, ",noacl"); +#endif + + if (test_opt(sb, NOBH)) + seq_puts(seq, ",nobh"); + +#if defined(CONFIG_QUOTA) + if (sbi->s_mount_opt & EXT2_MOUNT_USRQUOTA) + seq_puts(seq, ",usrquota"); + + if (sbi->s_mount_opt & EXT2_MOUNT_GRPQUOTA) + seq_puts(seq, ",grpquota"); +#endif + +#ifdef CONFIG_FS_DAX + if (sbi->s_mount_opt & EXT2_MOUNT_XIP) + seq_puts(seq, ",xip"); + if (sbi->s_mount_opt & EXT2_MOUNT_DAX) + seq_puts(seq, ",dax"); +#endif + + if (!test_opt(sb, RESERVATION)) + seq_puts(seq, ",noreservation"); + + spin_unlock(&sbi->s_lock); + return 0; +} + +#ifdef CONFIG_QUOTA +static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off); +static ssize_t ext2_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off); +static struct dquot **ext2_get_dquots(struct inode *inode) +{ + return EXT2_I(inode)->i_dquot; +} +#endif + +static const struct super_operations ext2_sops = { + .alloc_inode = ext2_alloc_inode, + .destroy_inode = ext2_destroy_inode, + .write_inode = ext2_write_inode, + .evict_inode = ext2_evict_inode, + .put_super = ext2_put_super, + .sync_fs = ext2_sync_fs, + .freeze_fs = ext2_freeze, + .unfreeze_fs = ext2_unfreeze, + .statfs = ext2_statfs, + .remount_fs = ext2_remount, + .show_options = ext2_show_options, +#ifdef CONFIG_QUOTA + .quota_read = ext2_quota_read, + .quota_write = ext2_quota_write, + .get_dquots = ext2_get_dquots, +#endif +}; + +static struct inode *ext2_nfs_get_inode(struct super_block *sb, + u64 ino, u32 generation) +{ + struct inode *inode; + + if (ino < EXT2_FIRST_INO(sb) && ino != EXT2_ROOT_INO) + return ERR_PTR(-ESTALE); + if (ino > le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count)) + return ERR_PTR(-ESTALE); + + /* + * ext2_iget isn't quite right if the inode is currently unallocated! + * However ext2_iget currently does appropriate checks to handle stale + * inodes so everything is OK. + */ + inode = ext2_iget(sb, ino); + if (IS_ERR(inode)) + return ERR_CAST(inode); + if (generation && inode->i_generation != generation) { + /* we didn't find the right inode.. */ + iput(inode); + return ERR_PTR(-ESTALE); + } + return inode; +} + +static struct dentry *ext2_fh_to_dentry(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type) +{ + return generic_fh_to_dentry(sb, fid, fh_len, fh_type, + ext2_nfs_get_inode); +} + +static struct dentry *ext2_fh_to_parent(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type) +{ + return generic_fh_to_parent(sb, fid, fh_len, fh_type, + ext2_nfs_get_inode); +} + +static const struct export_operations ext2_export_ops = { + .fh_to_dentry = ext2_fh_to_dentry, + .fh_to_parent = ext2_fh_to_parent, + .get_parent = ext2_get_parent, +}; + +static unsigned long get_sb_block(void **data) +{ + unsigned long sb_block; + char *options = (char *) *data; + + if (!options || strncmp(options, "sb=", 3) != 0) + return 1; /* Default location */ + options += 3; + sb_block = simple_strtoul(options, &options, 0); + if (*options && *options != ',') { + printk("EXT2-fs: Invalid sb specification: %s\n", + (char *) *data); + return 1; + } + if (*options == ',') + options++; + *data = (void *) options; + return sb_block; +} + +enum { + Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid, + Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic, + Opt_err_ro, Opt_nouid32, Opt_nocheck, Opt_debug, + Opt_oldalloc, Opt_orlov, Opt_nobh, Opt_user_xattr, Opt_nouser_xattr, + Opt_acl, Opt_noacl, Opt_xip, Opt_dax, Opt_ignore, Opt_err, Opt_quota, + Opt_usrquota, Opt_grpquota, Opt_reservation, Opt_noreservation +}; + +static const match_table_t tokens = { + {Opt_bsd_df, "bsddf"}, + {Opt_minix_df, "minixdf"}, + {Opt_grpid, "grpid"}, + {Opt_grpid, "bsdgroups"}, + {Opt_nogrpid, "nogrpid"}, + {Opt_nogrpid, "sysvgroups"}, + {Opt_resgid, "resgid=%u"}, + {Opt_resuid, "resuid=%u"}, + {Opt_sb, "sb=%u"}, + {Opt_err_cont, "errors=continue"}, + {Opt_err_panic, "errors=panic"}, + {Opt_err_ro, "errors=remount-ro"}, + {Opt_nouid32, "nouid32"}, + {Opt_nocheck, "check=none"}, + {Opt_nocheck, "nocheck"}, + {Opt_debug, "debug"}, + {Opt_oldalloc, "oldalloc"}, + {Opt_orlov, "orlov"}, + {Opt_nobh, "nobh"}, + {Opt_user_xattr, "user_xattr"}, + {Opt_nouser_xattr, "nouser_xattr"}, + {Opt_acl, "acl"}, + {Opt_noacl, "noacl"}, + {Opt_xip, "xip"}, + {Opt_dax, "dax"}, + {Opt_grpquota, "grpquota"}, + {Opt_ignore, "noquota"}, + {Opt_quota, "quota"}, + {Opt_usrquota, "usrquota"}, + {Opt_reservation, "reservation"}, + {Opt_noreservation, "noreservation"}, + {Opt_err, NULL} +}; + +static int parse_options(char *options, struct super_block *sb) +{ + char *p; + struct ext2_sb_info *sbi = EXT2_SB(sb); + substring_t args[MAX_OPT_ARGS]; + int option; + kuid_t uid; + kgid_t gid; + + if (!options) + return 1; + + while ((p = strsep (&options, ",")) != NULL) { + int token; + if (!*p) + continue; + + token = match_token(p, tokens, args); + switch (token) { + case Opt_bsd_df: + clear_opt (sbi->s_mount_opt, MINIX_DF); + break; + case Opt_minix_df: + set_opt (sbi->s_mount_opt, MINIX_DF); + break; + case Opt_grpid: + set_opt (sbi->s_mount_opt, GRPID); + break; + case Opt_nogrpid: + clear_opt (sbi->s_mount_opt, GRPID); + break; + case Opt_resuid: + if (match_int(&args[0], &option)) + return 0; + uid = make_kuid(current_user_ns(), option); + if (!uid_valid(uid)) { + ext2_msg(sb, KERN_ERR, "Invalid uid value %d", option); + return 0; + + } + sbi->s_resuid = uid; + break; + case Opt_resgid: + if (match_int(&args[0], &option)) + return 0; + gid = make_kgid(current_user_ns(), option); + if (!gid_valid(gid)) { + ext2_msg(sb, KERN_ERR, "Invalid gid value %d", option); + return 0; + } + sbi->s_resgid = gid; + break; + case Opt_sb: + /* handled by get_sb_block() instead of here */ + /* *sb_block = match_int(&args[0]); */ + break; + case Opt_err_panic: + clear_opt (sbi->s_mount_opt, ERRORS_CONT); + clear_opt (sbi->s_mount_opt, ERRORS_RO); + set_opt (sbi->s_mount_opt, ERRORS_PANIC); + break; + case Opt_err_ro: + clear_opt (sbi->s_mount_opt, ERRORS_CONT); + clear_opt (sbi->s_mount_opt, ERRORS_PANIC); + set_opt (sbi->s_mount_opt, ERRORS_RO); + break; + case Opt_err_cont: + clear_opt (sbi->s_mount_opt, ERRORS_RO); + clear_opt (sbi->s_mount_opt, ERRORS_PANIC); + set_opt (sbi->s_mount_opt, ERRORS_CONT); + break; + case Opt_nouid32: + set_opt (sbi->s_mount_opt, NO_UID32); + break; + case Opt_nocheck: + clear_opt (sbi->s_mount_opt, CHECK); + break; + case Opt_debug: + set_opt (sbi->s_mount_opt, DEBUG); + break; + case Opt_oldalloc: + set_opt (sbi->s_mount_opt, OLDALLOC); + break; + case Opt_orlov: + clear_opt (sbi->s_mount_opt, OLDALLOC); + break; + case Opt_nobh: + set_opt (sbi->s_mount_opt, NOBH); + break; +#ifdef CONFIG_EXT2_FS_XATTR + case Opt_user_xattr: + set_opt (sbi->s_mount_opt, XATTR_USER); + break; + case Opt_nouser_xattr: + clear_opt (sbi->s_mount_opt, XATTR_USER); + break; +#else + case Opt_user_xattr: + case Opt_nouser_xattr: + ext2_msg(sb, KERN_INFO, "(no)user_xattr options" + "not supported"); + break; +#endif +#ifdef CONFIG_EXT2_FS_POSIX_ACL + case Opt_acl: + set_opt(sbi->s_mount_opt, POSIX_ACL); + break; + case Opt_noacl: + clear_opt(sbi->s_mount_opt, POSIX_ACL); + break; +#else + case Opt_acl: + case Opt_noacl: + ext2_msg(sb, KERN_INFO, + "(no)acl options not supported"); + break; +#endif + case Opt_xip: + ext2_msg(sb, KERN_INFO, "use dax instead of xip"); + set_opt(sbi->s_mount_opt, XIP); + /* Fall through */ + case Opt_dax: +#ifdef CONFIG_FS_DAX + set_opt(sbi->s_mount_opt, DAX); +#else + ext2_msg(sb, KERN_INFO, "dax option not supported"); +#endif + break; + +#if defined(CONFIG_QUOTA) + case Opt_quota: + case Opt_usrquota: + set_opt(sbi->s_mount_opt, USRQUOTA); + break; + + case Opt_grpquota: + set_opt(sbi->s_mount_opt, GRPQUOTA); + break; +#else + case Opt_quota: + case Opt_usrquota: + case Opt_grpquota: + ext2_msg(sb, KERN_INFO, + "quota operations not supported"); + break; +#endif + + case Opt_reservation: + set_opt(sbi->s_mount_opt, RESERVATION); + ext2_msg(sb, KERN_INFO, "reservations ON"); + break; + case Opt_noreservation: + clear_opt(sbi->s_mount_opt, RESERVATION); + ext2_msg(sb, KERN_INFO, "reservations OFF"); + break; + case Opt_ignore: + break; + default: + return 0; + } + } + return 1; +} + +static int ext2_setup_super (struct super_block * sb, + struct ext2_super_block * es, + int read_only) +{ + int res = 0; + struct ext2_sb_info *sbi = EXT2_SB(sb); + + if (le32_to_cpu(es->s_rev_level) > EXT2_MAX_SUPP_REV) { + ext2_msg(sb, KERN_ERR, + "error: revision level too high, " + "forcing read-only mode"); + res = MS_RDONLY; + } + if (read_only) + return res; + if (!(sbi->s_mount_state & EXT2_VALID_FS)) + ext2_msg(sb, KERN_WARNING, + "warning: mounting unchecked fs, " + "running e2fsck is recommended"); + else if ((sbi->s_mount_state & EXT2_ERROR_FS)) + ext2_msg(sb, KERN_WARNING, + "warning: mounting fs with errors, " + "running e2fsck is recommended"); + else if ((__s16) le16_to_cpu(es->s_max_mnt_count) >= 0 && + le16_to_cpu(es->s_mnt_count) >= + (unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count)) + ext2_msg(sb, KERN_WARNING, + "warning: maximal mount count reached, " + "running e2fsck is recommended"); + else if (le32_to_cpu(es->s_checkinterval) && + (le32_to_cpu(es->s_lastcheck) + + le32_to_cpu(es->s_checkinterval) <= get_seconds())) + ext2_msg(sb, KERN_WARNING, + "warning: checktime reached, " + "running e2fsck is recommended"); + if (!le16_to_cpu(es->s_max_mnt_count)) + es->s_max_mnt_count = cpu_to_le16(EXT2_DFL_MAX_MNT_COUNT); + le16_add_cpu(&es->s_mnt_count, 1); + if (test_opt (sb, DEBUG)) + ext2_msg(sb, KERN_INFO, "%s, %s, bs=%lu, fs=%lu, gc=%lu, " + "bpg=%lu, ipg=%lu, mo=%04lx]", + EXT2FS_VERSION, EXT2FS_DATE, sb->s_blocksize, + sbi->s_frag_size, + sbi->s_groups_count, + EXT2_BLOCKS_PER_GROUP(sb), + EXT2_INODES_PER_GROUP(sb), + sbi->s_mount_opt); + return res; +} + +static int ext2_check_descriptors(struct super_block *sb) +{ + int i; + struct ext2_sb_info *sbi = EXT2_SB(sb); + + ext2_debug ("Checking group descriptors"); + + for (i = 0; i < sbi->s_groups_count; i++) { + struct ext2_group_desc *gdp = ext2_get_group_desc(sb, i, NULL); + ext2_fsblk_t first_block = ext2_group_first_block_no(sb, i); + ext2_fsblk_t last_block; + + if (i == sbi->s_groups_count - 1) + last_block = le32_to_cpu(sbi->s_es->s_blocks_count) - 1; + else + last_block = first_block + + (EXT2_BLOCKS_PER_GROUP(sb) - 1); + + if (le32_to_cpu(gdp->bg_block_bitmap) < first_block || + le32_to_cpu(gdp->bg_block_bitmap) > last_block) + { + ext2_error (sb, "ext2_check_descriptors", + "Block bitmap for group %d" + " not in group (block %lu)!", + i, (unsigned long) le32_to_cpu(gdp->bg_block_bitmap)); + return 0; + } + if (le32_to_cpu(gdp->bg_inode_bitmap) < first_block || + le32_to_cpu(gdp->bg_inode_bitmap) > last_block) + { + ext2_error (sb, "ext2_check_descriptors", + "Inode bitmap for group %d" + " not in group (block %lu)!", + i, (unsigned long) le32_to_cpu(gdp->bg_inode_bitmap)); + return 0; + } + if (le32_to_cpu(gdp->bg_inode_table) < first_block || + le32_to_cpu(gdp->bg_inode_table) + sbi->s_itb_per_group - 1 > + last_block) + { + ext2_error (sb, "ext2_check_descriptors", + "Inode table for group %d" + " not in group (block %lu)!", + i, (unsigned long) le32_to_cpu(gdp->bg_inode_table)); + return 0; + } + } + return 1; +} + +/* + * Maximal file size. There is a direct, and {,double-,triple-}indirect + * block limit, and also a limit of (2^32 - 1) 512-byte sectors in i_blocks. + * We need to be 1 filesystem block less than the 2^32 sector limit. + */ +static loff_t ext2_max_size(int bits) +{ + loff_t res = EXT2_NDIR_BLOCKS; + int meta_blocks; + loff_t upper_limit; + + /* This is calculated to be the largest file size for a + * dense, file such that the total number of + * sectors in the file, including data and all indirect blocks, + * does not exceed 2^32 -1 + * __u32 i_blocks representing the total number of + * 512 bytes blocks of the file + */ + upper_limit = (1LL << 32) - 1; + + /* total blocks in file system block size */ + upper_limit >>= (bits - 9); + + + /* indirect blocks */ + meta_blocks = 1; + /* double indirect blocks */ + meta_blocks += 1 + (1LL << (bits-2)); + /* tripple indirect blocks */ + meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2))); + + upper_limit -= meta_blocks; + upper_limit <<= bits; + + res += 1LL << (bits-2); + res += 1LL << (2*(bits-2)); + res += 1LL << (3*(bits-2)); + res <<= bits; + if (res > upper_limit) + res = upper_limit; + + if (res > MAX_LFS_FILESIZE) + res = MAX_LFS_FILESIZE; + + return res; +} + +static unsigned long descriptor_loc(struct super_block *sb, + unsigned long logic_sb_block, + int nr) +{ + struct ext2_sb_info *sbi = EXT2_SB(sb); + unsigned long bg, first_meta_bg; + int has_super = 0; + + first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg); + + if (!EXT2_HAS_INCOMPAT_FEATURE(sb, EXT2_FEATURE_INCOMPAT_META_BG) || + nr < first_meta_bg) + return (logic_sb_block + nr + 1); + bg = sbi->s_desc_per_block * nr; + if (ext2_bg_has_super(sb, bg)) + has_super = 1; + + return ext2_group_first_block_no(sb, bg) + has_super; +} + +static int ext2_fill_super(struct super_block *sb, void *data, int silent) +{ + struct buffer_head * bh; + struct ext2_sb_info * sbi; + struct ext2_super_block * es; + struct inode *root; + unsigned long block; + unsigned long sb_block = get_sb_block(&data); + unsigned long logic_sb_block; + unsigned long offset = 0; + unsigned long def_mount_opts; + long ret = -EINVAL; + int blocksize = BLOCK_SIZE; + int db_count; + int i, j; + __le32 features; + int err; + + err = -ENOMEM; + sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); + if (!sbi) + goto failed; + + sbi->s_blockgroup_lock = + kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL); + if (!sbi->s_blockgroup_lock) { + kfree(sbi); + goto failed; + } + sb->s_fs_info = sbi; + sbi->s_sb_block = sb_block; + + spin_lock_init(&sbi->s_lock); + + /* + * See what the current blocksize for the device is, and + * use that as the blocksize. Otherwise (or if the blocksize + * is smaller than the default) use the default. + * This is important for devices that have a hardware + * sectorsize that is larger than the default. + */ + blocksize = sb_min_blocksize(sb, BLOCK_SIZE); + if (!blocksize) { + ext2_msg(sb, KERN_ERR, "error: unable to set blocksize"); + goto failed_sbi; + } + + /* + * If the superblock doesn't start on a hardware sector boundary, + * calculate the offset. + */ + if (blocksize != BLOCK_SIZE) { + logic_sb_block = (sb_block*BLOCK_SIZE) / blocksize; + offset = (sb_block*BLOCK_SIZE) % blocksize; + } else { + logic_sb_block = sb_block; + } + + if (!(bh = sb_bread(sb, logic_sb_block))) { + ext2_msg(sb, KERN_ERR, "error: unable to read superblock"); + goto failed_sbi; + } + /* + * Note: s_es must be initialized as soon as possible because + * some ext2 macro-instructions depend on its value + */ + es = (struct ext2_super_block *) (((char *)bh->b_data) + offset); + sbi->s_es = es; + sb->s_magic = le16_to_cpu(es->s_magic); + + if (sb->s_magic != EXT2_SUPER_MAGIC) + goto cantfind_ext2; + + /* Set defaults before we parse the mount options */ + def_mount_opts = le32_to_cpu(es->s_default_mount_opts); + if (def_mount_opts & EXT2_DEFM_DEBUG) + set_opt(sbi->s_mount_opt, DEBUG); + if (def_mount_opts & EXT2_DEFM_BSDGROUPS) + set_opt(sbi->s_mount_opt, GRPID); + if (def_mount_opts & EXT2_DEFM_UID16) + set_opt(sbi->s_mount_opt, NO_UID32); +#ifdef CONFIG_EXT2_FS_XATTR + if (def_mount_opts & EXT2_DEFM_XATTR_USER) + set_opt(sbi->s_mount_opt, XATTR_USER); +#endif +#ifdef CONFIG_EXT2_FS_POSIX_ACL + if (def_mount_opts & EXT2_DEFM_ACL) + set_opt(sbi->s_mount_opt, POSIX_ACL); +#endif + + if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_PANIC) + set_opt(sbi->s_mount_opt, ERRORS_PANIC); + else if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_CONTINUE) + set_opt(sbi->s_mount_opt, ERRORS_CONT); + else + set_opt(sbi->s_mount_opt, ERRORS_RO); + + sbi->s_resuid = make_kuid(&init_user_ns, le16_to_cpu(es->s_def_resuid)); + sbi->s_resgid = make_kgid(&init_user_ns, le16_to_cpu(es->s_def_resgid)); + + set_opt(sbi->s_mount_opt, RESERVATION); + + if (!parse_options((char *) data, sb)) + goto failed_mount; + + sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | + ((EXT2_SB(sb)->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ? + MS_POSIXACL : 0); + + if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV && + (EXT2_HAS_COMPAT_FEATURE(sb, ~0U) || + EXT2_HAS_RO_COMPAT_FEATURE(sb, ~0U) || + EXT2_HAS_INCOMPAT_FEATURE(sb, ~0U))) + ext2_msg(sb, KERN_WARNING, + "warning: feature flags set on rev 0 fs, " + "running e2fsck is recommended"); + /* + * Check feature flags regardless of the revision level, since we + * previously didn't change the revision level when setting the flags, + * so there is a chance incompat flags are set on a rev 0 filesystem. + */ + features = EXT2_HAS_INCOMPAT_FEATURE(sb, ~EXT2_FEATURE_INCOMPAT_SUPP); + if (features) { + ext2_msg(sb, KERN_ERR, "error: couldn't mount because of " + "unsupported optional features (%x)", + le32_to_cpu(features)); + goto failed_mount; + } + if (!(sb->s_flags & MS_RDONLY) && + (features = EXT2_HAS_RO_COMPAT_FEATURE(sb, ~EXT2_FEATURE_RO_COMPAT_SUPP))){ + ext2_msg(sb, KERN_ERR, "error: couldn't mount RDWR because of " + "unsupported optional features (%x)", + le32_to_cpu(features)); + goto failed_mount; + } + + blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size); + + if (sbi->s_mount_opt & EXT2_MOUNT_DAX) { + if (blocksize != PAGE_SIZE) { + ext2_msg(sb, KERN_ERR, + "error: unsupported blocksize for dax"); + goto failed_mount; + } + if (!sb->s_bdev->bd_disk->fops->direct_access) { + ext2_msg(sb, KERN_ERR, + "error: device does not support dax"); + goto failed_mount; + } + } + + /* If the blocksize doesn't match, re-read the thing.. */ + if (sb->s_blocksize != blocksize) { + brelse(bh); + + if (!sb_set_blocksize(sb, blocksize)) { + ext2_msg(sb, KERN_ERR, + "error: bad blocksize %d", blocksize); + goto failed_sbi; + } + + logic_sb_block = (sb_block*BLOCK_SIZE) / blocksize; + offset = (sb_block*BLOCK_SIZE) % blocksize; + bh = sb_bread(sb, logic_sb_block); + if(!bh) { + ext2_msg(sb, KERN_ERR, "error: couldn't read" + "superblock on 2nd try"); + goto failed_sbi; + } + es = (struct ext2_super_block *) (((char *)bh->b_data) + offset); + sbi->s_es = es; + if (es->s_magic != cpu_to_le16(EXT2_SUPER_MAGIC)) { + ext2_msg(sb, KERN_ERR, "error: magic mismatch"); + goto failed_mount; + } + } + + sb->s_maxbytes = ext2_max_size(sb->s_blocksize_bits); + sb->s_max_links = EXT2_LINK_MAX; + + if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV) { + sbi->s_inode_size = EXT2_GOOD_OLD_INODE_SIZE; + sbi->s_first_ino = EXT2_GOOD_OLD_FIRST_INO; + } else { + sbi->s_inode_size = le16_to_cpu(es->s_inode_size); + sbi->s_first_ino = le32_to_cpu(es->s_first_ino); + if ((sbi->s_inode_size < EXT2_GOOD_OLD_INODE_SIZE) || + !is_power_of_2(sbi->s_inode_size) || + (sbi->s_inode_size > blocksize)) { + ext2_msg(sb, KERN_ERR, + "error: unsupported inode size: %d", + sbi->s_inode_size); + goto failed_mount; + } + } + + sbi->s_frag_size = EXT2_MIN_FRAG_SIZE << + le32_to_cpu(es->s_log_frag_size); + if (sbi->s_frag_size == 0) + goto cantfind_ext2; + sbi->s_frags_per_block = sb->s_blocksize / sbi->s_frag_size; + + sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group); + sbi->s_frags_per_group = le32_to_cpu(es->s_frags_per_group); + sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group); + + if (EXT2_INODE_SIZE(sb) == 0) + goto cantfind_ext2; + sbi->s_inodes_per_block = sb->s_blocksize / EXT2_INODE_SIZE(sb); + if (sbi->s_inodes_per_block == 0 || sbi->s_inodes_per_group == 0) + goto cantfind_ext2; + sbi->s_itb_per_group = sbi->s_inodes_per_group / + sbi->s_inodes_per_block; + sbi->s_desc_per_block = sb->s_blocksize / + sizeof (struct ext2_group_desc); + sbi->s_sbh = bh; + sbi->s_mount_state = le16_to_cpu(es->s_state); + sbi->s_addr_per_block_bits = + ilog2 (EXT2_ADDR_PER_BLOCK(sb)); + sbi->s_desc_per_block_bits = + ilog2 (EXT2_DESC_PER_BLOCK(sb)); + + if (sb->s_magic != EXT2_SUPER_MAGIC) + goto cantfind_ext2; + + if (sb->s_blocksize != bh->b_size) { + if (!silent) + ext2_msg(sb, KERN_ERR, "error: unsupported blocksize"); + goto failed_mount; + } + + if (sb->s_blocksize != sbi->s_frag_size) { + ext2_msg(sb, KERN_ERR, + "error: fragsize %lu != blocksize %lu" + "(not supported yet)", + sbi->s_frag_size, sb->s_blocksize); + goto failed_mount; + } + + if (sbi->s_blocks_per_group > sb->s_blocksize * 8) { + ext2_msg(sb, KERN_ERR, + "error: #blocks per group too big: %lu", + sbi->s_blocks_per_group); + goto failed_mount; + } + if (sbi->s_frags_per_group > sb->s_blocksize * 8) { + ext2_msg(sb, KERN_ERR, + "error: #fragments per group too big: %lu", + sbi->s_frags_per_group); + goto failed_mount; + } + if (sbi->s_inodes_per_group > sb->s_blocksize * 8) { + ext2_msg(sb, KERN_ERR, + "error: #inodes per group too big: %lu", + sbi->s_inodes_per_group); + goto failed_mount; + } + + if (EXT2_BLOCKS_PER_GROUP(sb) == 0) + goto cantfind_ext2; + sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) - + le32_to_cpu(es->s_first_data_block) - 1) + / EXT2_BLOCKS_PER_GROUP(sb)) + 1; + db_count = (sbi->s_groups_count + EXT2_DESC_PER_BLOCK(sb) - 1) / + EXT2_DESC_PER_BLOCK(sb); + sbi->s_group_desc = kmalloc (db_count * sizeof (struct buffer_head *), GFP_KERNEL); + if (sbi->s_group_desc == NULL) { + ext2_msg(sb, KERN_ERR, "error: not enough memory"); + goto failed_mount; + } + bgl_lock_init(sbi->s_blockgroup_lock); + sbi->s_debts = kcalloc(sbi->s_groups_count, sizeof(*sbi->s_debts), GFP_KERNEL); + if (!sbi->s_debts) { + ext2_msg(sb, KERN_ERR, "error: not enough memory"); + goto failed_mount_group_desc; + } + for (i = 0; i < db_count; i++) { + block = descriptor_loc(sb, logic_sb_block, i); + sbi->s_group_desc[i] = sb_bread(sb, block); + if (!sbi->s_group_desc[i]) { + for (j = 0; j < i; j++) + brelse (sbi->s_group_desc[j]); + ext2_msg(sb, KERN_ERR, + "error: unable to read group descriptors"); + goto failed_mount_group_desc; + } + } + if (!ext2_check_descriptors (sb)) { + ext2_msg(sb, KERN_ERR, "group descriptors corrupted"); + goto failed_mount2; + } + sbi->s_gdb_count = db_count; + get_random_bytes(&sbi->s_next_generation, sizeof(u32)); + spin_lock_init(&sbi->s_next_gen_lock); + + /* per fileystem reservation list head & lock */ + spin_lock_init(&sbi->s_rsv_window_lock); + sbi->s_rsv_window_root = RB_ROOT; + /* + * Add a single, static dummy reservation to the start of the + * reservation window list --- it gives us a placeholder for + * append-at-start-of-list which makes the allocation logic + * _much_ simpler. + */ + sbi->s_rsv_window_head.rsv_start = EXT2_RESERVE_WINDOW_NOT_ALLOCATED; + sbi->s_rsv_window_head.rsv_end = EXT2_RESERVE_WINDOW_NOT_ALLOCATED; + sbi->s_rsv_window_head.rsv_alloc_hit = 0; + sbi->s_rsv_window_head.rsv_goal_size = 0; + ext2_rsv_window_add(sb, &sbi->s_rsv_window_head); + + err = percpu_counter_init(&sbi->s_freeblocks_counter, + ext2_count_free_blocks(sb), GFP_KERNEL); + if (!err) { + err = percpu_counter_init(&sbi->s_freeinodes_counter, + ext2_count_free_inodes(sb), GFP_KERNEL); + } + if (!err) { + err = percpu_counter_init(&sbi->s_dirs_counter, + ext2_count_dirs(sb), GFP_KERNEL); + } + if (err) { + ext2_msg(sb, KERN_ERR, "error: insufficient memory"); + goto failed_mount3; + } + /* + * set up enough so that it can read an inode + */ + sb->s_op = &ext2_sops; + sb->s_export_op = &ext2_export_ops; + sb->s_xattr = ext2_xattr_handlers; + +#ifdef CONFIG_QUOTA + sb->dq_op = &dquot_operations; + sb->s_qcop = &dquot_quotactl_ops; + sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP; +#endif + + root = ext2_iget(sb, EXT2_ROOT_INO); + if (IS_ERR(root)) { + ret = PTR_ERR(root); + goto failed_mount3; + } + if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) { + iput(root); + ext2_msg(sb, KERN_ERR, "error: corrupt root inode, run e2fsck"); + goto failed_mount3; + } + + sb->s_root = d_make_root(root); + if (!sb->s_root) { + ext2_msg(sb, KERN_ERR, "error: get root inode failed"); + ret = -ENOMEM; + goto failed_mount3; + } + if (EXT2_HAS_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_HAS_JOURNAL)) + ext2_msg(sb, KERN_WARNING, + "warning: mounting ext3 filesystem as ext2"); + if (ext2_setup_super (sb, es, sb->s_flags & MS_RDONLY)) + sb->s_flags |= MS_RDONLY; + ext2_write_super(sb); + return 0; + +cantfind_ext2: + if (!silent) + ext2_msg(sb, KERN_ERR, + "error: can't find an ext2 filesystem on dev %s.", + sb->s_id); + goto failed_mount; +failed_mount3: + percpu_counter_destroy(&sbi->s_freeblocks_counter); + percpu_counter_destroy(&sbi->s_freeinodes_counter); + percpu_counter_destroy(&sbi->s_dirs_counter); +failed_mount2: + for (i = 0; i < db_count; i++) + brelse(sbi->s_group_desc[i]); +failed_mount_group_desc: + kfree(sbi->s_group_desc); + kfree(sbi->s_debts); +failed_mount: + brelse(bh); +failed_sbi: + sb->s_fs_info = NULL; + kfree(sbi->s_blockgroup_lock); + kfree(sbi); +failed: + return ret; +} + +static void ext2_clear_super_error(struct super_block *sb) +{ + struct buffer_head *sbh = EXT2_SB(sb)->s_sbh; + + if (buffer_write_io_error(sbh)) { + /* + * Oh, dear. A previous attempt to write the + * superblock failed. This could happen because the + * USB device was yanked out. Or it could happen to + * be a transient write error and maybe the block will + * be remapped. Nothing we can do but to retry the + * write and hope for the best. + */ + ext2_msg(sb, KERN_ERR, + "previous I/O error to superblock detected\n"); + clear_buffer_write_io_error(sbh); + set_buffer_uptodate(sbh); + } +} + +static void ext2_sync_super(struct super_block *sb, struct ext2_super_block *es, + int wait) +{ + ext2_clear_super_error(sb); + spin_lock(&EXT2_SB(sb)->s_lock); + es->s_free_blocks_count = cpu_to_le32(ext2_count_free_blocks(sb)); + es->s_free_inodes_count = cpu_to_le32(ext2_count_free_inodes(sb)); + es->s_wtime = cpu_to_le32(get_seconds()); + /* unlock before we do IO */ + spin_unlock(&EXT2_SB(sb)->s_lock); + mark_buffer_dirty(EXT2_SB(sb)->s_sbh); + if (wait) + sync_dirty_buffer(EXT2_SB(sb)->s_sbh); +} + +/* + * In the second extended file system, it is not necessary to + * write the super block since we use a mapping of the + * disk super block in a buffer. + * + * However, this function is still used to set the fs valid + * flags to 0. We need to set this flag to 0 since the fs + * may have been checked while mounted and e2fsck may have + * set s_state to EXT2_VALID_FS after some corrections. + */ +static int ext2_sync_fs(struct super_block *sb, int wait) +{ + struct ext2_sb_info *sbi = EXT2_SB(sb); + struct ext2_super_block *es = EXT2_SB(sb)->s_es; + + /* + * Write quota structures to quota file, sync_blockdev() will write + * them to disk later + */ + dquot_writeback_dquots(sb, -1); + + spin_lock(&sbi->s_lock); + if (es->s_state & cpu_to_le16(EXT2_VALID_FS)) { + ext2_debug("setting valid to 0\n"); + es->s_state &= cpu_to_le16(~EXT2_VALID_FS); + } + spin_unlock(&sbi->s_lock); + ext2_sync_super(sb, es, wait); + return 0; +} + +static int ext2_freeze(struct super_block *sb) +{ + struct ext2_sb_info *sbi = EXT2_SB(sb); + + /* + * Open but unlinked files present? Keep EXT2_VALID_FS flag cleared + * because we have unattached inodes and thus filesystem is not fully + * consistent. + */ + if (atomic_long_read(&sb->s_remove_count)) { + ext2_sync_fs(sb, 1); + return 0; + } + /* Set EXT2_FS_VALID flag */ + spin_lock(&sbi->s_lock); + sbi->s_es->s_state = cpu_to_le16(sbi->s_mount_state); + spin_unlock(&sbi->s_lock); + ext2_sync_super(sb, sbi->s_es, 1); + + return 0; +} + +static int ext2_unfreeze(struct super_block *sb) +{ + /* Just write sb to clear EXT2_VALID_FS flag */ + ext2_write_super(sb); + + return 0; +} + +void ext2_write_super(struct super_block *sb) +{ + if (!(sb->s_flags & MS_RDONLY)) + ext2_sync_fs(sb, 1); +} + +static int ext2_remount (struct super_block * sb, int * flags, char * data) +{ + struct ext2_sb_info * sbi = EXT2_SB(sb); + struct ext2_super_block * es; + struct ext2_mount_options old_opts; + unsigned long old_sb_flags; + int err; + + sync_filesystem(sb); + spin_lock(&sbi->s_lock); + + /* Store the old options */ + old_sb_flags = sb->s_flags; + old_opts.s_mount_opt = sbi->s_mount_opt; + old_opts.s_resuid = sbi->s_resuid; + old_opts.s_resgid = sbi->s_resgid; + + /* + * Allow the "check" option to be passed as a remount option. + */ + if (!parse_options(data, sb)) { + err = -EINVAL; + goto restore_opts; + } + + sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | + ((sbi->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0); + + es = sbi->s_es; + if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT2_MOUNT_DAX) { + ext2_msg(sb, KERN_WARNING, "warning: refusing change of " + "dax flag with busy inodes while remounting"); + sbi->s_mount_opt ^= EXT2_MOUNT_DAX; + } + if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) { + spin_unlock(&sbi->s_lock); + return 0; + } + if (*flags & MS_RDONLY) { + if (le16_to_cpu(es->s_state) & EXT2_VALID_FS || + !(sbi->s_mount_state & EXT2_VALID_FS)) { + spin_unlock(&sbi->s_lock); + return 0; + } + + /* + * OK, we are remounting a valid rw partition rdonly, so set + * the rdonly flag and then mark the partition as valid again. + */ + es->s_state = cpu_to_le16(sbi->s_mount_state); + es->s_mtime = cpu_to_le32(get_seconds()); + spin_unlock(&sbi->s_lock); + + err = dquot_suspend(sb, -1); + if (err < 0) { + spin_lock(&sbi->s_lock); + goto restore_opts; + } + + ext2_sync_super(sb, es, 1); + } else { + __le32 ret = EXT2_HAS_RO_COMPAT_FEATURE(sb, + ~EXT2_FEATURE_RO_COMPAT_SUPP); + if (ret) { + ext2_msg(sb, KERN_WARNING, + "warning: couldn't remount RDWR because of " + "unsupported optional features (%x).", + le32_to_cpu(ret)); + err = -EROFS; + goto restore_opts; + } + /* + * Mounting a RDONLY partition read-write, so reread and + * store the current valid flag. (It may have been changed + * by e2fsck since we originally mounted the partition.) + */ + sbi->s_mount_state = le16_to_cpu(es->s_state); + if (!ext2_setup_super (sb, es, 0)) + sb->s_flags &= ~MS_RDONLY; + spin_unlock(&sbi->s_lock); + + ext2_write_super(sb); + + dquot_resume(sb, -1); + } + + return 0; +restore_opts: + sbi->s_mount_opt = old_opts.s_mount_opt; + sbi->s_resuid = old_opts.s_resuid; + sbi->s_resgid = old_opts.s_resgid; + sb->s_flags = old_sb_flags; + spin_unlock(&sbi->s_lock); + return err; +} + +static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf) +{ + struct super_block *sb = dentry->d_sb; + struct ext2_sb_info *sbi = EXT2_SB(sb); + struct ext2_super_block *es = sbi->s_es; + u64 fsid; + + spin_lock(&sbi->s_lock); + + if (test_opt (sb, MINIX_DF)) + sbi->s_overhead_last = 0; + else if (sbi->s_blocks_last != le32_to_cpu(es->s_blocks_count)) { + unsigned long i, overhead = 0; + smp_rmb(); + + /* + * Compute the overhead (FS structures). This is constant + * for a given filesystem unless the number of block groups + * changes so we cache the previous value until it does. + */ + + /* + * All of the blocks before first_data_block are + * overhead + */ + overhead = le32_to_cpu(es->s_first_data_block); + + /* + * Add the overhead attributed to the superblock and + * block group descriptors. If the sparse superblocks + * feature is turned on, then not all groups have this. + */ + for (i = 0; i < sbi->s_groups_count; i++) + overhead += ext2_bg_has_super(sb, i) + + ext2_bg_num_gdb(sb, i); + + /* + * Every block group has an inode bitmap, a block + * bitmap, and an inode table. + */ + overhead += (sbi->s_groups_count * + (2 + sbi->s_itb_per_group)); + sbi->s_overhead_last = overhead; + smp_wmb(); + sbi->s_blocks_last = le32_to_cpu(es->s_blocks_count); + } + + buf->f_type = EXT2_SUPER_MAGIC; + buf->f_bsize = sb->s_blocksize; + buf->f_blocks = le32_to_cpu(es->s_blocks_count) - sbi->s_overhead_last; + buf->f_bfree = ext2_count_free_blocks(sb); + es->s_free_blocks_count = cpu_to_le32(buf->f_bfree); + buf->f_bavail = buf->f_bfree - le32_to_cpu(es->s_r_blocks_count); + if (buf->f_bfree < le32_to_cpu(es->s_r_blocks_count)) + buf->f_bavail = 0; + buf->f_files = le32_to_cpu(es->s_inodes_count); + buf->f_ffree = ext2_count_free_inodes(sb); + es->s_free_inodes_count = cpu_to_le32(buf->f_ffree); + buf->f_namelen = EXT2_NAME_LEN; + fsid = le64_to_cpup((void *)es->s_uuid) ^ + le64_to_cpup((void *)es->s_uuid + sizeof(u64)); + buf->f_fsid.val[0] = fsid & 0xFFFFFFFFUL; + buf->f_fsid.val[1] = (fsid >> 32) & 0xFFFFFFFFUL; + spin_unlock(&sbi->s_lock); + return 0; +} + +static struct dentry *ext2_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) +{ + return mount_bdev(fs_type, flags, dev_name, data, ext2_fill_super); +} + +#ifdef CONFIG_QUOTA + +/* Read data from quotafile - avoid pagecache and such because we cannot afford + * acquiring the locks... As quota files are never truncated and quota code + * itself serializes the operations (and no one else should touch the files) + * we don't have to be afraid of races */ +static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data, + size_t len, loff_t off) +{ + struct inode *inode = sb_dqopt(sb)->files[type]; + sector_t blk = off >> EXT2_BLOCK_SIZE_BITS(sb); + int err = 0; + int offset = off & (sb->s_blocksize - 1); + int tocopy; + size_t toread; + struct buffer_head tmp_bh; + struct buffer_head *bh; + loff_t i_size = i_size_read(inode); + + if (off > i_size) + return 0; + if (off+len > i_size) + len = i_size-off; + toread = len; + while (toread > 0) { + tocopy = sb->s_blocksize - offset < toread ? + sb->s_blocksize - offset : toread; + + tmp_bh.b_state = 0; + tmp_bh.b_size = sb->s_blocksize; + err = ext2_get_block(inode, blk, &tmp_bh, 0); + if (err < 0) + return err; + if (!buffer_mapped(&tmp_bh)) /* A hole? */ + memset(data, 0, tocopy); + else { + bh = sb_bread(sb, tmp_bh.b_blocknr); + if (!bh) + return -EIO; + memcpy(data, bh->b_data+offset, tocopy); + brelse(bh); + } + offset = 0; + toread -= tocopy; + data += tocopy; + blk++; + } + return len; +} + +/* Write to quotafile */ +static ssize_t ext2_quota_write(struct super_block *sb, int type, + const char *data, size_t len, loff_t off) +{ + struct inode *inode = sb_dqopt(sb)->files[type]; + sector_t blk = off >> EXT2_BLOCK_SIZE_BITS(sb); + int err = 0; + int offset = off & (sb->s_blocksize - 1); + int tocopy; + size_t towrite = len; + struct buffer_head tmp_bh; + struct buffer_head *bh; + + while (towrite > 0) { + tocopy = sb->s_blocksize - offset < towrite ? + sb->s_blocksize - offset : towrite; + + tmp_bh.b_state = 0; + tmp_bh.b_size = sb->s_blocksize; + err = ext2_get_block(inode, blk, &tmp_bh, 1); + if (err < 0) + goto out; + if (offset || tocopy != EXT2_BLOCK_SIZE(sb)) + bh = sb_bread(sb, tmp_bh.b_blocknr); + else + bh = sb_getblk(sb, tmp_bh.b_blocknr); + if (unlikely(!bh)) { + err = -EIO; + goto out; + } + lock_buffer(bh); + memcpy(bh->b_data+offset, data, tocopy); + flush_dcache_page(bh->b_page); + set_buffer_uptodate(bh); + mark_buffer_dirty(bh); + unlock_buffer(bh); + brelse(bh); + offset = 0; + towrite -= tocopy; + data += tocopy; + blk++; + } +out: + if (len == towrite) + return err; + if (inode->i_size < off+len-towrite) + i_size_write(inode, off+len-towrite); + inode->i_version++; + inode->i_mtime = inode->i_ctime = CURRENT_TIME; + mark_inode_dirty(inode); + return len - towrite; +} + +#endif + +static struct file_system_type ext2_fs_type = { + .owner = THIS_MODULE, + .name = "ext2", + .mount = ext2_mount, + .kill_sb = kill_block_super, + .fs_flags = FS_REQUIRES_DEV, +}; +MODULE_ALIAS_FS("ext2"); + +static int __init init_ext2_fs(void) +{ + int err = init_ext2_xattr(); + if (err) + return err; + err = init_inodecache(); + if (err) + goto out1; + err = register_filesystem(&ext2_fs_type); + if (err) + goto out; + return 0; +out: + destroy_inodecache(); +out1: + exit_ext2_xattr(); + return err; +} + +static void __exit exit_ext2_fs(void) +{ + unregister_filesystem(&ext2_fs_type); + destroy_inodecache(); + exit_ext2_xattr(); +} + +MODULE_AUTHOR("Remy Card and others"); +MODULE_DESCRIPTION("Second Extended Filesystem"); +MODULE_LICENSE("GPL"); +module_init(init_ext2_fs) +module_exit(exit_ext2_fs) diff --git a/fs/ext2/symlink.c b/fs/ext2/symlink.c new file mode 100644 index 000000000..20608f17c --- /dev/null +++ b/fs/ext2/symlink.c @@ -0,0 +1,54 @@ +/* + * linux/fs/ext2/symlink.c + * + * Only fast symlinks left here - the rest is done by generic code. AV, 1999 + * + * Copyright (C) 1992, 1993, 1994, 1995 + * Remy Card (card@masi.ibp.fr) + * Laboratoire MASI - Institut Blaise Pascal + * Universite Pierre et Marie Curie (Paris VI) + * + * from + * + * linux/fs/minix/symlink.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * ext2 symlink handling code + */ + +#include "ext2.h" +#include "xattr.h" +#include + +static void *ext2_follow_link(struct dentry *dentry, struct nameidata *nd) +{ + struct ext2_inode_info *ei = EXT2_I(d_inode(dentry)); + nd_set_link(nd, (char *)ei->i_data); + return NULL; +} + +const struct inode_operations ext2_symlink_inode_operations = { + .readlink = generic_readlink, + .follow_link = page_follow_link_light, + .put_link = page_put_link, + .setattr = ext2_setattr, +#ifdef CONFIG_EXT2_FS_XATTR + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = ext2_listxattr, + .removexattr = generic_removexattr, +#endif +}; + +const struct inode_operations ext2_fast_symlink_inode_operations = { + .readlink = generic_readlink, + .follow_link = ext2_follow_link, + .setattr = ext2_setattr, +#ifdef CONFIG_EXT2_FS_XATTR + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = ext2_listxattr, + .removexattr = generic_removexattr, +#endif +}; diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c new file mode 100644 index 000000000..0b6bfd3a3 --- /dev/null +++ b/fs/ext2/xattr.c @@ -0,0 +1,1029 @@ +/* + * linux/fs/ext2/xattr.c + * + * Copyright (C) 2001-2003 Andreas Gruenbacher + * + * Fix by Harrison Xing . + * Extended attributes for symlinks and special files added per + * suggestion of Luka Renko . + * xattr consolidation Copyright (c) 2004 James Morris , + * Red Hat Inc. + * + */ + +/* + * Extended attributes are stored on disk blocks allocated outside of + * any inode. The i_file_acl field is then made to point to this allocated + * block. If all extended attributes of an inode are identical, these + * inodes may share the same extended attribute block. Such situations + * are automatically detected by keeping a cache of recent attribute block + * numbers and hashes over the block's contents in memory. + * + * + * Extended attribute block layout: + * + * +------------------+ + * | header | + * | entry 1 | | + * | entry 2 | | growing downwards + * | entry 3 | v + * | four null bytes | + * | . . . | + * | value 1 | ^ + * | value 3 | | growing upwards + * | value 2 | | + * +------------------+ + * + * The block header is followed by multiple entry descriptors. These entry + * descriptors are variable in size, and aligned to EXT2_XATTR_PAD + * byte boundaries. The entry descriptors are sorted by attribute name, + * so that two extended attribute blocks can be compared efficiently. + * + * Attribute values are aligned to the end of the block, stored in + * no specific order. They are also padded to EXT2_XATTR_PAD byte + * boundaries. No additional gaps are left between them. + * + * Locking strategy + * ---------------- + * EXT2_I(inode)->i_file_acl is protected by EXT2_I(inode)->xattr_sem. + * EA blocks are only changed if they are exclusive to an inode, so + * holding xattr_sem also means that nothing but the EA block's reference + * count will change. Multiple writers to an EA block are synchronized + * by the bh lock. No more than a single bh lock is held at any time + * to avoid deadlocks. + */ + +#include +#include +#include +#include +#include +#include +#include +#include "ext2.h" +#include "xattr.h" +#include "acl.h" + +#define HDR(bh) ((struct ext2_xattr_header *)((bh)->b_data)) +#define ENTRY(ptr) ((struct ext2_xattr_entry *)(ptr)) +#define FIRST_ENTRY(bh) ENTRY(HDR(bh)+1) +#define IS_LAST_ENTRY(entry) (*(__u32 *)(entry) == 0) + +#ifdef EXT2_XATTR_DEBUG +# define ea_idebug(inode, f...) do { \ + printk(KERN_DEBUG "inode %s:%ld: ", \ + inode->i_sb->s_id, inode->i_ino); \ + printk(f); \ + printk("\n"); \ + } while (0) +# define ea_bdebug(bh, f...) do { \ + char b[BDEVNAME_SIZE]; \ + printk(KERN_DEBUG "block %s:%lu: ", \ + bdevname(bh->b_bdev, b), \ + (unsigned long) bh->b_blocknr); \ + printk(f); \ + printk("\n"); \ + } while (0) +#else +# define ea_idebug(f...) +# define ea_bdebug(f...) +#endif + +static int ext2_xattr_set2(struct inode *, struct buffer_head *, + struct ext2_xattr_header *); + +static int ext2_xattr_cache_insert(struct buffer_head *); +static struct buffer_head *ext2_xattr_cache_find(struct inode *, + struct ext2_xattr_header *); +static void ext2_xattr_rehash(struct ext2_xattr_header *, + struct ext2_xattr_entry *); + +static struct mb_cache *ext2_xattr_cache; + +static const struct xattr_handler *ext2_xattr_handler_map[] = { + [EXT2_XATTR_INDEX_USER] = &ext2_xattr_user_handler, +#ifdef CONFIG_EXT2_FS_POSIX_ACL + [EXT2_XATTR_INDEX_POSIX_ACL_ACCESS] = &posix_acl_access_xattr_handler, + [EXT2_XATTR_INDEX_POSIX_ACL_DEFAULT] = &posix_acl_default_xattr_handler, +#endif + [EXT2_XATTR_INDEX_TRUSTED] = &ext2_xattr_trusted_handler, +#ifdef CONFIG_EXT2_FS_SECURITY + [EXT2_XATTR_INDEX_SECURITY] = &ext2_xattr_security_handler, +#endif +}; + +const struct xattr_handler *ext2_xattr_handlers[] = { + &ext2_xattr_user_handler, + &ext2_xattr_trusted_handler, +#ifdef CONFIG_EXT2_FS_POSIX_ACL + &posix_acl_access_xattr_handler, + &posix_acl_default_xattr_handler, +#endif +#ifdef CONFIG_EXT2_FS_SECURITY + &ext2_xattr_security_handler, +#endif + NULL +}; + +static inline const struct xattr_handler * +ext2_xattr_handler(int name_index) +{ + const struct xattr_handler *handler = NULL; + + if (name_index > 0 && name_index < ARRAY_SIZE(ext2_xattr_handler_map)) + handler = ext2_xattr_handler_map[name_index]; + return handler; +} + +/* + * ext2_xattr_get() + * + * Copy an extended attribute into the buffer + * provided, or compute the buffer size required. + * Buffer is NULL to compute the size of the buffer required. + * + * Returns a negative error number on failure, or the number of bytes + * used / required on success. + */ +int +ext2_xattr_get(struct inode *inode, int name_index, const char *name, + void *buffer, size_t buffer_size) +{ + struct buffer_head *bh = NULL; + struct ext2_xattr_entry *entry; + size_t name_len, size; + char *end; + int error; + + ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld", + name_index, name, buffer, (long)buffer_size); + + if (name == NULL) + return -EINVAL; + name_len = strlen(name); + if (name_len > 255) + return -ERANGE; + + down_read(&EXT2_I(inode)->xattr_sem); + error = -ENODATA; + if (!EXT2_I(inode)->i_file_acl) + goto cleanup; + ea_idebug(inode, "reading block %d", EXT2_I(inode)->i_file_acl); + bh = sb_bread(inode->i_sb, EXT2_I(inode)->i_file_acl); + error = -EIO; + if (!bh) + goto cleanup; + ea_bdebug(bh, "b_count=%d, refcount=%d", + atomic_read(&(bh->b_count)), le32_to_cpu(HDR(bh)->h_refcount)); + end = bh->b_data + bh->b_size; + if (HDR(bh)->h_magic != cpu_to_le32(EXT2_XATTR_MAGIC) || + HDR(bh)->h_blocks != cpu_to_le32(1)) { +bad_block: ext2_error(inode->i_sb, "ext2_xattr_get", + "inode %ld: bad block %d", inode->i_ino, + EXT2_I(inode)->i_file_acl); + error = -EIO; + goto cleanup; + } + + /* find named attribute */ + entry = FIRST_ENTRY(bh); + while (!IS_LAST_ENTRY(entry)) { + struct ext2_xattr_entry *next = + EXT2_XATTR_NEXT(entry); + if ((char *)next >= end) + goto bad_block; + if (name_index == entry->e_name_index && + name_len == entry->e_name_len && + memcmp(name, entry->e_name, name_len) == 0) + goto found; + entry = next; + } + if (ext2_xattr_cache_insert(bh)) + ea_idebug(inode, "cache insert failed"); + error = -ENODATA; + goto cleanup; +found: + /* check the buffer size */ + if (entry->e_value_block != 0) + goto bad_block; + size = le32_to_cpu(entry->e_value_size); + if (size > inode->i_sb->s_blocksize || + le16_to_cpu(entry->e_value_offs) + size > inode->i_sb->s_blocksize) + goto bad_block; + + if (ext2_xattr_cache_insert(bh)) + ea_idebug(inode, "cache insert failed"); + if (buffer) { + error = -ERANGE; + if (size > buffer_size) + goto cleanup; + /* return value of attribute */ + memcpy(buffer, bh->b_data + le16_to_cpu(entry->e_value_offs), + size); + } + error = size; + +cleanup: + brelse(bh); + up_read(&EXT2_I(inode)->xattr_sem); + + return error; +} + +/* + * ext2_xattr_list() + * + * Copy a list of attribute names into the buffer + * provided, or compute the buffer size required. + * Buffer is NULL to compute the size of the buffer required. + * + * Returns a negative error number on failure, or the number of bytes + * used / required on success. + */ +static int +ext2_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size) +{ + struct inode *inode = d_inode(dentry); + struct buffer_head *bh = NULL; + struct ext2_xattr_entry *entry; + char *end; + size_t rest = buffer_size; + int error; + + ea_idebug(inode, "buffer=%p, buffer_size=%ld", + buffer, (long)buffer_size); + + down_read(&EXT2_I(inode)->xattr_sem); + error = 0; + if (!EXT2_I(inode)->i_file_acl) + goto cleanup; + ea_idebug(inode, "reading block %d", EXT2_I(inode)->i_file_acl); + bh = sb_bread(inode->i_sb, EXT2_I(inode)->i_file_acl); + error = -EIO; + if (!bh) + goto cleanup; + ea_bdebug(bh, "b_count=%d, refcount=%d", + atomic_read(&(bh->b_count)), le32_to_cpu(HDR(bh)->h_refcount)); + end = bh->b_data + bh->b_size; + if (HDR(bh)->h_magic != cpu_to_le32(EXT2_XATTR_MAGIC) || + HDR(bh)->h_blocks != cpu_to_le32(1)) { +bad_block: ext2_error(inode->i_sb, "ext2_xattr_list", + "inode %ld: bad block %d", inode->i_ino, + EXT2_I(inode)->i_file_acl); + error = -EIO; + goto cleanup; + } + + /* check the on-disk data structure */ + entry = FIRST_ENTRY(bh); + while (!IS_LAST_ENTRY(entry)) { + struct ext2_xattr_entry *next = EXT2_XATTR_NEXT(entry); + + if ((char *)next >= end) + goto bad_block; + entry = next; + } + if (ext2_xattr_cache_insert(bh)) + ea_idebug(inode, "cache insert failed"); + + /* list the attribute names */ + for (entry = FIRST_ENTRY(bh); !IS_LAST_ENTRY(entry); + entry = EXT2_XATTR_NEXT(entry)) { + const struct xattr_handler *handler = + ext2_xattr_handler(entry->e_name_index); + + if (handler) { + size_t size = handler->list(dentry, buffer, rest, + entry->e_name, + entry->e_name_len, + handler->flags); + if (buffer) { + if (size > rest) { + error = -ERANGE; + goto cleanup; + } + buffer += size; + } + rest -= size; + } + } + error = buffer_size - rest; /* total size */ + +cleanup: + brelse(bh); + up_read(&EXT2_I(inode)->xattr_sem); + + return error; +} + +/* + * Inode operation listxattr() + * + * d_inode(dentry)->i_mutex: don't care + */ +ssize_t +ext2_listxattr(struct dentry *dentry, char *buffer, size_t size) +{ + return ext2_xattr_list(dentry, buffer, size); +} + +/* + * If the EXT2_FEATURE_COMPAT_EXT_ATTR feature of this file system is + * not set, set it. + */ +static void ext2_xattr_update_super_block(struct super_block *sb) +{ + if (EXT2_HAS_COMPAT_FEATURE(sb, EXT2_FEATURE_COMPAT_EXT_ATTR)) + return; + + spin_lock(&EXT2_SB(sb)->s_lock); + EXT2_SET_COMPAT_FEATURE(sb, EXT2_FEATURE_COMPAT_EXT_ATTR); + spin_unlock(&EXT2_SB(sb)->s_lock); + mark_buffer_dirty(EXT2_SB(sb)->s_sbh); +} + +/* + * ext2_xattr_set() + * + * Create, replace or remove an extended attribute for this inode. Value + * is NULL to remove an existing extended attribute, and non-NULL to + * either replace an existing extended attribute, or create a new extended + * attribute. The flags XATTR_REPLACE and XATTR_CREATE + * specify that an extended attribute must exist and must not exist + * previous to the call, respectively. + * + * Returns 0, or a negative error number on failure. + */ +int +ext2_xattr_set(struct inode *inode, int name_index, const char *name, + const void *value, size_t value_len, int flags) +{ + struct super_block *sb = inode->i_sb; + struct buffer_head *bh = NULL; + struct ext2_xattr_header *header = NULL; + struct ext2_xattr_entry *here, *last; + size_t name_len, free, min_offs = sb->s_blocksize; + int not_found = 1, error; + char *end; + + /* + * header -- Points either into bh, or to a temporarily + * allocated buffer. + * here -- The named entry found, or the place for inserting, within + * the block pointed to by header. + * last -- Points right after the last named entry within the block + * pointed to by header. + * min_offs -- The offset of the first value (values are aligned + * towards the end of the block). + * end -- Points right after the block pointed to by header. + */ + + ea_idebug(inode, "name=%d.%s, value=%p, value_len=%ld", + name_index, name, value, (long)value_len); + + if (value == NULL) + value_len = 0; + if (name == NULL) + return -EINVAL; + name_len = strlen(name); + if (name_len > 255 || value_len > sb->s_blocksize) + return -ERANGE; + down_write(&EXT2_I(inode)->xattr_sem); + if (EXT2_I(inode)->i_file_acl) { + /* The inode already has an extended attribute block. */ + bh = sb_bread(sb, EXT2_I(inode)->i_file_acl); + error = -EIO; + if (!bh) + goto cleanup; + ea_bdebug(bh, "b_count=%d, refcount=%d", + atomic_read(&(bh->b_count)), + le32_to_cpu(HDR(bh)->h_refcount)); + header = HDR(bh); + end = bh->b_data + bh->b_size; + if (header->h_magic != cpu_to_le32(EXT2_XATTR_MAGIC) || + header->h_blocks != cpu_to_le32(1)) { +bad_block: ext2_error(sb, "ext2_xattr_set", + "inode %ld: bad block %d", inode->i_ino, + EXT2_I(inode)->i_file_acl); + error = -EIO; + goto cleanup; + } + /* Find the named attribute. */ + here = FIRST_ENTRY(bh); + while (!IS_LAST_ENTRY(here)) { + struct ext2_xattr_entry *next = EXT2_XATTR_NEXT(here); + if ((char *)next >= end) + goto bad_block; + if (!here->e_value_block && here->e_value_size) { + size_t offs = le16_to_cpu(here->e_value_offs); + if (offs < min_offs) + min_offs = offs; + } + not_found = name_index - here->e_name_index; + if (!not_found) + not_found = name_len - here->e_name_len; + if (!not_found) + not_found = memcmp(name, here->e_name,name_len); + if (not_found <= 0) + break; + here = next; + } + last = here; + /* We still need to compute min_offs and last. */ + while (!IS_LAST_ENTRY(last)) { + struct ext2_xattr_entry *next = EXT2_XATTR_NEXT(last); + if ((char *)next >= end) + goto bad_block; + if (!last->e_value_block && last->e_value_size) { + size_t offs = le16_to_cpu(last->e_value_offs); + if (offs < min_offs) + min_offs = offs; + } + last = next; + } + + /* Check whether we have enough space left. */ + free = min_offs - ((char*)last - (char*)header) - sizeof(__u32); + } else { + /* We will use a new extended attribute block. */ + free = sb->s_blocksize - + sizeof(struct ext2_xattr_header) - sizeof(__u32); + here = last = NULL; /* avoid gcc uninitialized warning. */ + } + + if (not_found) { + /* Request to remove a nonexistent attribute? */ + error = -ENODATA; + if (flags & XATTR_REPLACE) + goto cleanup; + error = 0; + if (value == NULL) + goto cleanup; + } else { + /* Request to create an existing attribute? */ + error = -EEXIST; + if (flags & XATTR_CREATE) + goto cleanup; + if (!here->e_value_block && here->e_value_size) { + size_t size = le32_to_cpu(here->e_value_size); + + if (le16_to_cpu(here->e_value_offs) + size > + sb->s_blocksize || size > sb->s_blocksize) + goto bad_block; + free += EXT2_XATTR_SIZE(size); + } + free += EXT2_XATTR_LEN(name_len); + } + error = -ENOSPC; + if (free < EXT2_XATTR_LEN(name_len) + EXT2_XATTR_SIZE(value_len)) + goto cleanup; + + /* Here we know that we can set the new attribute. */ + + if (header) { + struct mb_cache_entry *ce; + + /* assert(header == HDR(bh)); */ + ce = mb_cache_entry_get(ext2_xattr_cache, bh->b_bdev, + bh->b_blocknr); + lock_buffer(bh); + if (header->h_refcount == cpu_to_le32(1)) { + ea_bdebug(bh, "modifying in-place"); + if (ce) + mb_cache_entry_free(ce); + /* keep the buffer locked while modifying it. */ + } else { + int offset; + + if (ce) + mb_cache_entry_release(ce); + unlock_buffer(bh); + ea_bdebug(bh, "cloning"); + header = kmalloc(bh->b_size, GFP_KERNEL); + error = -ENOMEM; + if (header == NULL) + goto cleanup; + memcpy(header, HDR(bh), bh->b_size); + header->h_refcount = cpu_to_le32(1); + + offset = (char *)here - bh->b_data; + here = ENTRY((char *)header + offset); + offset = (char *)last - bh->b_data; + last = ENTRY((char *)header + offset); + } + } else { + /* Allocate a buffer where we construct the new block. */ + header = kzalloc(sb->s_blocksize, GFP_KERNEL); + error = -ENOMEM; + if (header == NULL) + goto cleanup; + end = (char *)header + sb->s_blocksize; + header->h_magic = cpu_to_le32(EXT2_XATTR_MAGIC); + header->h_blocks = header->h_refcount = cpu_to_le32(1); + last = here = ENTRY(header+1); + } + + /* Iff we are modifying the block in-place, bh is locked here. */ + + if (not_found) { + /* Insert the new name. */ + size_t size = EXT2_XATTR_LEN(name_len); + size_t rest = (char *)last - (char *)here; + memmove((char *)here + size, here, rest); + memset(here, 0, size); + here->e_name_index = name_index; + here->e_name_len = name_len; + memcpy(here->e_name, name, name_len); + } else { + if (!here->e_value_block && here->e_value_size) { + char *first_val = (char *)header + min_offs; + size_t offs = le16_to_cpu(here->e_value_offs); + char *val = (char *)header + offs; + size_t size = EXT2_XATTR_SIZE( + le32_to_cpu(here->e_value_size)); + + if (size == EXT2_XATTR_SIZE(value_len)) { + /* The old and the new value have the same + size. Just replace. */ + here->e_value_size = cpu_to_le32(value_len); + memset(val + size - EXT2_XATTR_PAD, 0, + EXT2_XATTR_PAD); /* Clear pad bytes. */ + memcpy(val, value, value_len); + goto skip_replace; + } + + /* Remove the old value. */ + memmove(first_val + size, first_val, val - first_val); + memset(first_val, 0, size); + here->e_value_offs = 0; + min_offs += size; + + /* Adjust all value offsets. */ + last = ENTRY(header+1); + while (!IS_LAST_ENTRY(last)) { + size_t o = le16_to_cpu(last->e_value_offs); + if (!last->e_value_block && o < offs) + last->e_value_offs = + cpu_to_le16(o + size); + last = EXT2_XATTR_NEXT(last); + } + } + if (value == NULL) { + /* Remove the old name. */ + size_t size = EXT2_XATTR_LEN(name_len); + last = ENTRY((char *)last - size); + memmove(here, (char*)here + size, + (char*)last - (char*)here); + memset(last, 0, size); + } + } + + if (value != NULL) { + /* Insert the new value. */ + here->e_value_size = cpu_to_le32(value_len); + if (value_len) { + size_t size = EXT2_XATTR_SIZE(value_len); + char *val = (char *)header + min_offs - size; + here->e_value_offs = + cpu_to_le16((char *)val - (char *)header); + memset(val + size - EXT2_XATTR_PAD, 0, + EXT2_XATTR_PAD); /* Clear the pad bytes. */ + memcpy(val, value, value_len); + } + } + +skip_replace: + if (IS_LAST_ENTRY(ENTRY(header+1))) { + /* This block is now empty. */ + if (bh && header == HDR(bh)) + unlock_buffer(bh); /* we were modifying in-place. */ + error = ext2_xattr_set2(inode, bh, NULL); + } else { + ext2_xattr_rehash(header, here); + if (bh && header == HDR(bh)) + unlock_buffer(bh); /* we were modifying in-place. */ + error = ext2_xattr_set2(inode, bh, header); + } + +cleanup: + brelse(bh); + if (!(bh && header == HDR(bh))) + kfree(header); + up_write(&EXT2_I(inode)->xattr_sem); + + return error; +} + +/* + * Second half of ext2_xattr_set(): Update the file system. + */ +static int +ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh, + struct ext2_xattr_header *header) +{ + struct super_block *sb = inode->i_sb; + struct buffer_head *new_bh = NULL; + int error; + + if (header) { + new_bh = ext2_xattr_cache_find(inode, header); + if (new_bh) { + /* We found an identical block in the cache. */ + if (new_bh == old_bh) { + ea_bdebug(new_bh, "keeping this block"); + } else { + /* The old block is released after updating + the inode. */ + ea_bdebug(new_bh, "reusing block"); + + error = dquot_alloc_block(inode, 1); + if (error) { + unlock_buffer(new_bh); + goto cleanup; + } + le32_add_cpu(&HDR(new_bh)->h_refcount, 1); + ea_bdebug(new_bh, "refcount now=%d", + le32_to_cpu(HDR(new_bh)->h_refcount)); + } + unlock_buffer(new_bh); + } else if (old_bh && header == HDR(old_bh)) { + /* Keep this block. No need to lock the block as we + don't need to change the reference count. */ + new_bh = old_bh; + get_bh(new_bh); + ext2_xattr_cache_insert(new_bh); + } else { + /* We need to allocate a new block */ + ext2_fsblk_t goal = ext2_group_first_block_no(sb, + EXT2_I(inode)->i_block_group); + int block = ext2_new_block(inode, goal, &error); + if (error) + goto cleanup; + ea_idebug(inode, "creating block %d", block); + + new_bh = sb_getblk(sb, block); + if (unlikely(!new_bh)) { + ext2_free_blocks(inode, block, 1); + mark_inode_dirty(inode); + error = -ENOMEM; + goto cleanup; + } + lock_buffer(new_bh); + memcpy(new_bh->b_data, header, new_bh->b_size); + set_buffer_uptodate(new_bh); + unlock_buffer(new_bh); + ext2_xattr_cache_insert(new_bh); + + ext2_xattr_update_super_block(sb); + } + mark_buffer_dirty(new_bh); + if (IS_SYNC(inode)) { + sync_dirty_buffer(new_bh); + error = -EIO; + if (buffer_req(new_bh) && !buffer_uptodate(new_bh)) + goto cleanup; + } + } + + /* Update the inode. */ + EXT2_I(inode)->i_file_acl = new_bh ? new_bh->b_blocknr : 0; + inode->i_ctime = CURRENT_TIME_SEC; + if (IS_SYNC(inode)) { + error = sync_inode_metadata(inode, 1); + /* In case sync failed due to ENOSPC the inode was actually + * written (only some dirty data were not) so we just proceed + * as if nothing happened and cleanup the unused block */ + if (error && error != -ENOSPC) { + if (new_bh && new_bh != old_bh) { + dquot_free_block_nodirty(inode, 1); + mark_inode_dirty(inode); + } + goto cleanup; + } + } else + mark_inode_dirty(inode); + + error = 0; + if (old_bh && old_bh != new_bh) { + struct mb_cache_entry *ce; + + /* + * If there was an old block and we are no longer using it, + * release the old block. + */ + ce = mb_cache_entry_get(ext2_xattr_cache, old_bh->b_bdev, + old_bh->b_blocknr); + lock_buffer(old_bh); + if (HDR(old_bh)->h_refcount == cpu_to_le32(1)) { + /* Free the old block. */ + if (ce) + mb_cache_entry_free(ce); + ea_bdebug(old_bh, "freeing"); + ext2_free_blocks(inode, old_bh->b_blocknr, 1); + mark_inode_dirty(inode); + /* We let our caller release old_bh, so we + * need to duplicate the buffer before. */ + get_bh(old_bh); + bforget(old_bh); + } else { + /* Decrement the refcount only. */ + le32_add_cpu(&HDR(old_bh)->h_refcount, -1); + if (ce) + mb_cache_entry_release(ce); + dquot_free_block_nodirty(inode, 1); + mark_inode_dirty(inode); + mark_buffer_dirty(old_bh); + ea_bdebug(old_bh, "refcount now=%d", + le32_to_cpu(HDR(old_bh)->h_refcount)); + } + unlock_buffer(old_bh); + } + +cleanup: + brelse(new_bh); + + return error; +} + +/* + * ext2_xattr_delete_inode() + * + * Free extended attribute resources associated with this inode. This + * is called immediately before an inode is freed. + */ +void +ext2_xattr_delete_inode(struct inode *inode) +{ + struct buffer_head *bh = NULL; + struct mb_cache_entry *ce; + + down_write(&EXT2_I(inode)->xattr_sem); + if (!EXT2_I(inode)->i_file_acl) + goto cleanup; + bh = sb_bread(inode->i_sb, EXT2_I(inode)->i_file_acl); + if (!bh) { + ext2_error(inode->i_sb, "ext2_xattr_delete_inode", + "inode %ld: block %d read error", inode->i_ino, + EXT2_I(inode)->i_file_acl); + goto cleanup; + } + ea_bdebug(bh, "b_count=%d", atomic_read(&(bh->b_count))); + if (HDR(bh)->h_magic != cpu_to_le32(EXT2_XATTR_MAGIC) || + HDR(bh)->h_blocks != cpu_to_le32(1)) { + ext2_error(inode->i_sb, "ext2_xattr_delete_inode", + "inode %ld: bad block %d", inode->i_ino, + EXT2_I(inode)->i_file_acl); + goto cleanup; + } + ce = mb_cache_entry_get(ext2_xattr_cache, bh->b_bdev, bh->b_blocknr); + lock_buffer(bh); + if (HDR(bh)->h_refcount == cpu_to_le32(1)) { + if (ce) + mb_cache_entry_free(ce); + ext2_free_blocks(inode, EXT2_I(inode)->i_file_acl, 1); + get_bh(bh); + bforget(bh); + unlock_buffer(bh); + } else { + le32_add_cpu(&HDR(bh)->h_refcount, -1); + if (ce) + mb_cache_entry_release(ce); + ea_bdebug(bh, "refcount now=%d", + le32_to_cpu(HDR(bh)->h_refcount)); + unlock_buffer(bh); + mark_buffer_dirty(bh); + if (IS_SYNC(inode)) + sync_dirty_buffer(bh); + dquot_free_block_nodirty(inode, 1); + } + EXT2_I(inode)->i_file_acl = 0; + +cleanup: + brelse(bh); + up_write(&EXT2_I(inode)->xattr_sem); +} + +/* + * ext2_xattr_put_super() + * + * This is called when a file system is unmounted. + */ +void +ext2_xattr_put_super(struct super_block *sb) +{ + mb_cache_shrink(sb->s_bdev); +} + + +/* + * ext2_xattr_cache_insert() + * + * Create a new entry in the extended attribute cache, and insert + * it unless such an entry is already in the cache. + * + * Returns 0, or a negative error number on failure. + */ +static int +ext2_xattr_cache_insert(struct buffer_head *bh) +{ + __u32 hash = le32_to_cpu(HDR(bh)->h_hash); + struct mb_cache_entry *ce; + int error; + + ce = mb_cache_entry_alloc(ext2_xattr_cache, GFP_NOFS); + if (!ce) + return -ENOMEM; + error = mb_cache_entry_insert(ce, bh->b_bdev, bh->b_blocknr, hash); + if (error) { + mb_cache_entry_free(ce); + if (error == -EBUSY) { + ea_bdebug(bh, "already in cache (%d cache entries)", + atomic_read(&ext2_xattr_cache->c_entry_count)); + error = 0; + } + } else { + ea_bdebug(bh, "inserting [%x] (%d cache entries)", (int)hash, + atomic_read(&ext2_xattr_cache->c_entry_count)); + mb_cache_entry_release(ce); + } + return error; +} + +/* + * ext2_xattr_cmp() + * + * Compare two extended attribute blocks for equality. + * + * Returns 0 if the blocks are equal, 1 if they differ, and + * a negative error number on errors. + */ +static int +ext2_xattr_cmp(struct ext2_xattr_header *header1, + struct ext2_xattr_header *header2) +{ + struct ext2_xattr_entry *entry1, *entry2; + + entry1 = ENTRY(header1+1); + entry2 = ENTRY(header2+1); + while (!IS_LAST_ENTRY(entry1)) { + if (IS_LAST_ENTRY(entry2)) + return 1; + if (entry1->e_hash != entry2->e_hash || + entry1->e_name_index != entry2->e_name_index || + entry1->e_name_len != entry2->e_name_len || + entry1->e_value_size != entry2->e_value_size || + memcmp(entry1->e_name, entry2->e_name, entry1->e_name_len)) + return 1; + if (entry1->e_value_block != 0 || entry2->e_value_block != 0) + return -EIO; + if (memcmp((char *)header1 + le16_to_cpu(entry1->e_value_offs), + (char *)header2 + le16_to_cpu(entry2->e_value_offs), + le32_to_cpu(entry1->e_value_size))) + return 1; + + entry1 = EXT2_XATTR_NEXT(entry1); + entry2 = EXT2_XATTR_NEXT(entry2); + } + if (!IS_LAST_ENTRY(entry2)) + return 1; + return 0; +} + +/* + * ext2_xattr_cache_find() + * + * Find an identical extended attribute block. + * + * Returns a locked buffer head to the block found, or NULL if such + * a block was not found or an error occurred. + */ +static struct buffer_head * +ext2_xattr_cache_find(struct inode *inode, struct ext2_xattr_header *header) +{ + __u32 hash = le32_to_cpu(header->h_hash); + struct mb_cache_entry *ce; + + if (!header->h_hash) + return NULL; /* never share */ + ea_idebug(inode, "looking for cached blocks [%x]", (int)hash); +again: + ce = mb_cache_entry_find_first(ext2_xattr_cache, inode->i_sb->s_bdev, + hash); + while (ce) { + struct buffer_head *bh; + + if (IS_ERR(ce)) { + if (PTR_ERR(ce) == -EAGAIN) + goto again; + break; + } + + bh = sb_bread(inode->i_sb, ce->e_block); + if (!bh) { + ext2_error(inode->i_sb, "ext2_xattr_cache_find", + "inode %ld: block %ld read error", + inode->i_ino, (unsigned long) ce->e_block); + } else { + lock_buffer(bh); + if (le32_to_cpu(HDR(bh)->h_refcount) > + EXT2_XATTR_REFCOUNT_MAX) { + ea_idebug(inode, "block %ld refcount %d>%d", + (unsigned long) ce->e_block, + le32_to_cpu(HDR(bh)->h_refcount), + EXT2_XATTR_REFCOUNT_MAX); + } else if (!ext2_xattr_cmp(header, HDR(bh))) { + ea_bdebug(bh, "b_count=%d", + atomic_read(&(bh->b_count))); + mb_cache_entry_release(ce); + return bh; + } + unlock_buffer(bh); + brelse(bh); + } + ce = mb_cache_entry_find_next(ce, inode->i_sb->s_bdev, hash); + } + return NULL; +} + +#define NAME_HASH_SHIFT 5 +#define VALUE_HASH_SHIFT 16 + +/* + * ext2_xattr_hash_entry() + * + * Compute the hash of an extended attribute. + */ +static inline void ext2_xattr_hash_entry(struct ext2_xattr_header *header, + struct ext2_xattr_entry *entry) +{ + __u32 hash = 0; + char *name = entry->e_name; + int n; + + for (n=0; n < entry->e_name_len; n++) { + hash = (hash << NAME_HASH_SHIFT) ^ + (hash >> (8*sizeof(hash) - NAME_HASH_SHIFT)) ^ + *name++; + } + + if (entry->e_value_block == 0 && entry->e_value_size != 0) { + __le32 *value = (__le32 *)((char *)header + + le16_to_cpu(entry->e_value_offs)); + for (n = (le32_to_cpu(entry->e_value_size) + + EXT2_XATTR_ROUND) >> EXT2_XATTR_PAD_BITS; n; n--) { + hash = (hash << VALUE_HASH_SHIFT) ^ + (hash >> (8*sizeof(hash) - VALUE_HASH_SHIFT)) ^ + le32_to_cpu(*value++); + } + } + entry->e_hash = cpu_to_le32(hash); +} + +#undef NAME_HASH_SHIFT +#undef VALUE_HASH_SHIFT + +#define BLOCK_HASH_SHIFT 16 + +/* + * ext2_xattr_rehash() + * + * Re-compute the extended attribute hash value after an entry has changed. + */ +static void ext2_xattr_rehash(struct ext2_xattr_header *header, + struct ext2_xattr_entry *entry) +{ + struct ext2_xattr_entry *here; + __u32 hash = 0; + + ext2_xattr_hash_entry(header, entry); + here = ENTRY(header+1); + while (!IS_LAST_ENTRY(here)) { + if (!here->e_hash) { + /* Block is not shared if an entry's hash value == 0 */ + hash = 0; + break; + } + hash = (hash << BLOCK_HASH_SHIFT) ^ + (hash >> (8*sizeof(hash) - BLOCK_HASH_SHIFT)) ^ + le32_to_cpu(here->e_hash); + here = EXT2_XATTR_NEXT(here); + } + header->h_hash = cpu_to_le32(hash); +} + +#undef BLOCK_HASH_SHIFT + +int __init +init_ext2_xattr(void) +{ + ext2_xattr_cache = mb_cache_create("ext2_xattr", 6); + if (!ext2_xattr_cache) + return -ENOMEM; + return 0; +} + +void +exit_ext2_xattr(void) +{ + mb_cache_destroy(ext2_xattr_cache); +} diff --git a/fs/ext2/xattr.h b/fs/ext2/xattr.h new file mode 100644 index 000000000..60edf2986 --- /dev/null +++ b/fs/ext2/xattr.h @@ -0,0 +1,125 @@ +/* + File: linux/ext2_xattr.h + + On-disk format of extended attributes for the ext2 filesystem. + + (C) 2001 Andreas Gruenbacher, +*/ + +#include +#include + +/* Magic value in attribute blocks */ +#define EXT2_XATTR_MAGIC 0xEA020000 + +/* Maximum number of references to one attribute block */ +#define EXT2_XATTR_REFCOUNT_MAX 1024 + +/* Name indexes */ +#define EXT2_XATTR_INDEX_USER 1 +#define EXT2_XATTR_INDEX_POSIX_ACL_ACCESS 2 +#define EXT2_XATTR_INDEX_POSIX_ACL_DEFAULT 3 +#define EXT2_XATTR_INDEX_TRUSTED 4 +#define EXT2_XATTR_INDEX_LUSTRE 5 +#define EXT2_XATTR_INDEX_SECURITY 6 + +struct ext2_xattr_header { + __le32 h_magic; /* magic number for identification */ + __le32 h_refcount; /* reference count */ + __le32 h_blocks; /* number of disk blocks used */ + __le32 h_hash; /* hash value of all attributes */ + __u32 h_reserved[4]; /* zero right now */ +}; + +struct ext2_xattr_entry { + __u8 e_name_len; /* length of name */ + __u8 e_name_index; /* attribute name index */ + __le16 e_value_offs; /* offset in disk block of value */ + __le32 e_value_block; /* disk block attribute is stored on (n/i) */ + __le32 e_value_size; /* size of attribute value */ + __le32 e_hash; /* hash value of name and value */ + char e_name[0]; /* attribute name */ +}; + +#define EXT2_XATTR_PAD_BITS 2 +#define EXT2_XATTR_PAD (1<e_name_len)) ) +#define EXT2_XATTR_SIZE(size) \ + (((size) + EXT2_XATTR_ROUND) & ~EXT2_XATTR_ROUND) + +# ifdef CONFIG_EXT2_FS_XATTR + +extern const struct xattr_handler ext2_xattr_user_handler; +extern const struct xattr_handler ext2_xattr_trusted_handler; +extern const struct xattr_handler ext2_xattr_security_handler; + +extern ssize_t ext2_listxattr(struct dentry *, char *, size_t); + +extern int ext2_xattr_get(struct inode *, int, const char *, void *, size_t); +extern int ext2_xattr_set(struct inode *, int, const char *, const void *, size_t, int); + +extern void ext2_xattr_delete_inode(struct inode *); +extern void ext2_xattr_put_super(struct super_block *); + +extern int init_ext2_xattr(void); +extern void exit_ext2_xattr(void); + +extern const struct xattr_handler *ext2_xattr_handlers[]; + +# else /* CONFIG_EXT2_FS_XATTR */ + +static inline int +ext2_xattr_get(struct inode *inode, int name_index, + const char *name, void *buffer, size_t size) +{ + return -EOPNOTSUPP; +} + +static inline int +ext2_xattr_set(struct inode *inode, int name_index, const char *name, + const void *value, size_t size, int flags) +{ + return -EOPNOTSUPP; +} + +static inline void +ext2_xattr_delete_inode(struct inode *inode) +{ +} + +static inline void +ext2_xattr_put_super(struct super_block *sb) +{ +} + +static inline int +init_ext2_xattr(void) +{ + return 0; +} + +static inline void +exit_ext2_xattr(void) +{ +} + +#define ext2_xattr_handlers NULL + +# endif /* CONFIG_EXT2_FS_XATTR */ + +#ifdef CONFIG_EXT2_FS_SECURITY +extern int ext2_init_security(struct inode *inode, struct inode *dir, + const struct qstr *qstr); +#else +static inline int ext2_init_security(struct inode *inode, struct inode *dir, + const struct qstr *qstr) +{ + return 0; +} +#endif diff --git a/fs/ext2/xattr_security.c b/fs/ext2/xattr_security.c new file mode 100644 index 000000000..702fc6840 --- /dev/null +++ b/fs/ext2/xattr_security.c @@ -0,0 +1,74 @@ +/* + * linux/fs/ext2/xattr_security.c + * Handler for storing security labels as extended attributes. + */ + +#include "ext2.h" +#include +#include "xattr.h" + +static size_t +ext2_xattr_security_list(struct dentry *dentry, char *list, size_t list_size, + const char *name, size_t name_len, int type) +{ + const int prefix_len = XATTR_SECURITY_PREFIX_LEN; + const size_t total_len = prefix_len + name_len + 1; + + if (list && total_len <= list_size) { + memcpy(list, XATTR_SECURITY_PREFIX, prefix_len); + memcpy(list+prefix_len, name, name_len); + list[prefix_len + name_len] = '\0'; + } + return total_len; +} + +static int +ext2_xattr_security_get(struct dentry *dentry, const char *name, + void *buffer, size_t size, int type) +{ + if (strcmp(name, "") == 0) + return -EINVAL; + return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_SECURITY, name, + buffer, size); +} + +static int +ext2_xattr_security_set(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags, int type) +{ + if (strcmp(name, "") == 0) + return -EINVAL; + return ext2_xattr_set(d_inode(dentry), EXT2_XATTR_INDEX_SECURITY, name, + value, size, flags); +} + +static int ext2_initxattrs(struct inode *inode, const struct xattr *xattr_array, + void *fs_info) +{ + const struct xattr *xattr; + int err = 0; + + for (xattr = xattr_array; xattr->name != NULL; xattr++) { + err = ext2_xattr_set(inode, EXT2_XATTR_INDEX_SECURITY, + xattr->name, xattr->value, + xattr->value_len, 0); + if (err < 0) + break; + } + return err; +} + +int +ext2_init_security(struct inode *inode, struct inode *dir, + const struct qstr *qstr) +{ + return security_inode_init_security(inode, dir, qstr, + &ext2_initxattrs, NULL); +} + +const struct xattr_handler ext2_xattr_security_handler = { + .prefix = XATTR_SECURITY_PREFIX, + .list = ext2_xattr_security_list, + .get = ext2_xattr_security_get, + .set = ext2_xattr_security_set, +}; diff --git a/fs/ext2/xattr_trusted.c b/fs/ext2/xattr_trusted.c new file mode 100644 index 000000000..42b6e9874 --- /dev/null +++ b/fs/ext2/xattr_trusted.c @@ -0,0 +1,54 @@ +/* + * linux/fs/ext2/xattr_trusted.c + * Handler for trusted extended attributes. + * + * Copyright (C) 2003 by Andreas Gruenbacher, + */ + +#include "ext2.h" +#include "xattr.h" + +static size_t +ext2_xattr_trusted_list(struct dentry *dentry, char *list, size_t list_size, + const char *name, size_t name_len, int type) +{ + const int prefix_len = XATTR_TRUSTED_PREFIX_LEN; + const size_t total_len = prefix_len + name_len + 1; + + if (!capable(CAP_SYS_ADMIN)) + return 0; + + if (list && total_len <= list_size) { + memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len); + memcpy(list+prefix_len, name, name_len); + list[prefix_len + name_len] = '\0'; + } + return total_len; +} + +static int +ext2_xattr_trusted_get(struct dentry *dentry, const char *name, + void *buffer, size_t size, int type) +{ + if (strcmp(name, "") == 0) + return -EINVAL; + return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_TRUSTED, name, + buffer, size); +} + +static int +ext2_xattr_trusted_set(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags, int type) +{ + if (strcmp(name, "") == 0) + return -EINVAL; + return ext2_xattr_set(d_inode(dentry), EXT2_XATTR_INDEX_TRUSTED, name, + value, size, flags); +} + +const struct xattr_handler ext2_xattr_trusted_handler = { + .prefix = XATTR_TRUSTED_PREFIX, + .list = ext2_xattr_trusted_list, + .get = ext2_xattr_trusted_get, + .set = ext2_xattr_trusted_set, +}; diff --git a/fs/ext2/xattr_user.c b/fs/ext2/xattr_user.c new file mode 100644 index 000000000..ecdc46051 --- /dev/null +++ b/fs/ext2/xattr_user.c @@ -0,0 +1,61 @@ +/* + * linux/fs/ext2/xattr_user.c + * Handler for extended user attributes. + * + * Copyright (C) 2001 by Andreas Gruenbacher, + */ + +#include +#include +#include "ext2.h" +#include "xattr.h" + +static size_t +ext2_xattr_user_list(struct dentry *dentry, char *list, size_t list_size, + const char *name, size_t name_len, int type) +{ + const size_t prefix_len = XATTR_USER_PREFIX_LEN; + const size_t total_len = prefix_len + name_len + 1; + + if (!test_opt(dentry->d_sb, XATTR_USER)) + return 0; + + if (list && total_len <= list_size) { + memcpy(list, XATTR_USER_PREFIX, prefix_len); + memcpy(list+prefix_len, name, name_len); + list[prefix_len + name_len] = '\0'; + } + return total_len; +} + +static int +ext2_xattr_user_get(struct dentry *dentry, const char *name, + void *buffer, size_t size, int type) +{ + if (strcmp(name, "") == 0) + return -EINVAL; + if (!test_opt(dentry->d_sb, XATTR_USER)) + return -EOPNOTSUPP; + return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_USER, + name, buffer, size); +} + +static int +ext2_xattr_user_set(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags, int type) +{ + if (strcmp(name, "") == 0) + return -EINVAL; + if (!test_opt(dentry->d_sb, XATTR_USER)) + return -EOPNOTSUPP; + + return ext2_xattr_set(d_inode(dentry), EXT2_XATTR_INDEX_USER, + name, value, size, flags); +} + +const struct xattr_handler ext2_xattr_user_handler = { + .prefix = XATTR_USER_PREFIX, + .list = ext2_xattr_user_list, + .get = ext2_xattr_user_get, + .set = ext2_xattr_user_set, +}; -- cgit v1.2.3-54-g00ecf