blob: e3126c0510066fec7fe8bd0d46123aa1af16388c [file] [log] [blame]
/*
* linux/fs/ext4/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@redhat.com), 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 ext4_get_block() by Al Viro, 2000
*/
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/time.h>
#include <linux/jbd2.h>
#include <linux/highuid.h>
#include <linux/pagemap.h>
#include <linux/quotaops.h>
#include <linux/string.h>
#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include <linux/pagevec.h>
#include <linux/mpage.h>
#include <linux/namei.h>
#include <linux/uio.h>
#include <linux/bio.h>
#include <linux/workqueue.h>
#include <linux/kernel.h>
#include <linux/printk.h>
#include <linux/slab.h>
#include <linux/ratelimit.h>
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
#include "ext4_extents.h"
#include <trace/events/ext4.h>
#define MPAGE_DA_EXTENT_TAIL 0x01
static inline int ext4_begin_ordered_truncate(struct inode *inode,
loff_t new_size)
{
trace_ext4_begin_ordered_truncate(inode, new_size);
/*
* If jinode is zero, then we never opened the file for
* writing, so there's no need to call
* jbd2_journal_begin_ordered_truncate() since there's no
* outstanding writes we need to flush.
*/
if (!EXT4_I(inode)->jinode)
return 0;
return jbd2_journal_begin_ordered_truncate(EXT4_JOURNAL(inode),
EXT4_I(inode)->jinode,
new_size);
}
static void ext4_invalidatepage(struct page *page, unsigned long offset);
static int noalloc_get_block_write(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode);
static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate);
static int __ext4_journalled_writepage(struct page *page, unsigned int len);
static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh);
/*
* Test whether an inode is a fast symlink.
*/
static int ext4_inode_is_fast_symlink(struct inode *inode)
{
int ea_blocks = EXT4_I(inode)->i_file_acl ?
(inode->i_sb->s_blocksize >> 9) : 0;
return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0);
}
/*
* Work out how many blocks we need to proceed with the next chunk of a
* truncate transaction.
*/
static unsigned long blocks_for_truncate(struct inode *inode)
{
ext4_lblk_t needed;
needed = inode->i_blocks >> (inode->i_sb->s_blocksize_bits - 9);
/* Give ourselves just enough room to cope with inodes in which
* i_blocks is corrupt: we've seen disk corruptions in the past
* which resulted in random data in an inode which looked enough
* like a regular file for ext4 to try to delete it. Things
* will go a bit crazy if that happens, but at least we should
* try not to panic the whole kernel. */
if (needed < 2)
needed = 2;
/* But we need to bound the transaction so we don't overflow the
* journal. */
if (needed > EXT4_MAX_TRANS_DATA)
needed = EXT4_MAX_TRANS_DATA;
return EXT4_DATA_TRANS_BLOCKS(inode->i_sb) + needed;
}
/*
* Truncate transactions can be complex and absolutely huge. So we need to
* be able to restart the transaction at a conventient checkpoint to make
* sure we don't overflow the journal.
*
* start_transaction gets us a new handle for a truncate transaction,
* and extend_transaction tries to extend the existing one a bit. If
* extend fails, we need to propagate the failure up and restart the
* transaction in the top-level truncate loop. --sct
*/
static handle_t *start_transaction(struct inode *inode)
{
handle_t *result;
result = ext4_journal_start(inode, blocks_for_truncate(inode));
if (!IS_ERR(result))
return result;
ext4_std_error(inode->i_sb, PTR_ERR(result));
return result;
}
/*
* Try to extend this transaction for the purposes of truncation.
*
* Returns 0 if we managed to create more room. If we can't create more
* room, and the transaction must be restarted we return 1.
*/
static int try_to_extend_transaction(handle_t *handle, struct inode *inode)
{
if (!ext4_handle_valid(handle))
return 0;
if (ext4_handle_has_enough_credits(handle, EXT4_RESERVE_TRANS_BLOCKS+1))
return 0;
if (!ext4_journal_extend(handle, blocks_for_truncate(inode)))
return 0;
return 1;
}
/*
* Restart the transaction associated with *handle. This does a commit,
* so before we call here everything must be consistently dirtied against
* this transaction.
*/
int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode,
int nblocks)
{
int ret;
/*
* Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this
* moment, get_block can be called only for blocks inside i_size since
* page cache has been already dropped and writes are blocked by
* i_mutex. So we can safely drop the i_data_sem here.
*/
BUG_ON(EXT4_JOURNAL(inode) == NULL);
jbd_debug(2, "restarting handle %p\n", handle);
up_write(&EXT4_I(inode)->i_data_sem);
ret = ext4_journal_restart(handle, nblocks);
down_write(&EXT4_I(inode)->i_data_sem);
ext4_discard_preallocations(inode);
return ret;
}
/*
* Called at the last iput() if i_nlink is zero.
*/
void ext4_evict_inode(struct inode *inode)
{
handle_t *handle;
int err;
trace_ext4_evict_inode(inode);
if (inode->i_nlink) {
truncate_inode_pages(&inode->i_data, 0);
goto no_delete;
}
if (!is_bad_inode(inode))
dquot_initialize(inode);
if (ext4_should_order_data(inode))
ext4_begin_ordered_truncate(inode, 0);
truncate_inode_pages(&inode->i_data, 0);
if (is_bad_inode(inode))
goto no_delete;
handle = ext4_journal_start(inode, blocks_for_truncate(inode)+3);
if (IS_ERR(handle)) {
ext4_std_error(inode->i_sb, PTR_ERR(handle));
/*
* If we're going to skip the normal cleanup, we still need to
* make sure that the in-core orphan linked list is properly
* cleaned up.
*/
ext4_orphan_del(NULL, inode);
goto no_delete;
}
if (IS_SYNC(inode))
ext4_handle_sync(handle);
inode->i_size = 0;
err = ext4_mark_inode_dirty(handle, inode);
if (err) {
ext4_warning(inode->i_sb,
"couldn't mark inode dirty (err %d)", err);
goto stop_handle;
}
if (inode->i_blocks)
ext4_truncate(inode);
/*
* ext4_ext_truncate() doesn't reserve any slop when it
* restarts journal transactions; therefore there may not be
* enough credits left in the handle to remove the inode from
* the orphan list and set the dtime field.
*/
if (!ext4_handle_has_enough_credits(handle, 3)) {
err = ext4_journal_extend(handle, 3);
if (err > 0)
err = ext4_journal_restart(handle, 3);
if (err != 0) {
ext4_warning(inode->i_sb,
"couldn't extend journal (err %d)", err);
stop_handle:
ext4_journal_stop(handle);
ext4_orphan_del(NULL, inode);
goto no_delete;
}
}
/*
* Kill off the orphan record which ext4_truncate created.
* AKPM: I think this can be inside the above `if'.
* Note that ext4_orphan_del() has to be able to cope with the
* deletion of a non-existent orphan - this is because we don't
* know if ext4_truncate() actually created an orphan record.
* (Well, we could do this if we need to, but heck - it works)
*/
ext4_orphan_del(handle, inode);
EXT4_I(inode)->i_dtime = get_seconds();
/*
* One subtle ordering requirement: if anything has gone wrong
* (transaction abort, IO errors, whatever), then we can still
* do these next steps (the fs will already have been marked as
* having errors), but we can't free the inode if the mark_dirty
* fails.
*/
if (ext4_mark_inode_dirty(handle, inode))
/* If that failed, just do the required in-core inode clear. */
ext4_clear_inode(inode);
else
ext4_free_inode(handle, inode);
ext4_journal_stop(handle);
return;
no_delete:
ext4_clear_inode(inode); /* We must guarantee clearing of inode... */
}
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;
}
/**
* ext4_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 ext4 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 ext4_block_to_path(struct inode *inode,
ext4_lblk_t i_block,
ext4_lblk_t offsets[4], int *boundary)
{
int ptrs = EXT4_ADDR_PER_BLOCK(inode->i_sb);
int ptrs_bits = EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb);
const long direct_blocks = EXT4_NDIR_BLOCKS,
indirect_blocks = ptrs,
double_blocks = (1 << (ptrs_bits * 2));
int n = 0;
int final = 0;
if (i_block < direct_blocks) {
offsets[n++] = i_block;
final = direct_blocks;
} else if ((i_block -= direct_blocks) < indirect_blocks) {
offsets[n++] = EXT4_IND_BLOCK;
offsets[n++] = i_block;
final = ptrs;
} else if ((i_block -= indirect_blocks) < double_blocks) {
offsets[n++] = EXT4_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++] = EXT4_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 {
ext4_warning(inode->i_sb, "block %lu > max in inode %lu",
i_block + direct_blocks +
indirect_blocks + double_blocks, inode->i_ino);
}
if (boundary)
*boundary = final - 1 - (i_block & (ptrs - 1));
return n;
}
static int __ext4_check_blockref(const char *function, unsigned int line,
struct inode *inode,
__le32 *p, unsigned int max)
{
struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
__le32 *bref = p;
unsigned int blk;
while (bref < p+max) {
blk = le32_to_cpu(*bref++);
if (blk &&
unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb),
blk, 1))) {
es->s_last_error_block = cpu_to_le64(blk);
ext4_error_inode(inode, function, line, blk,
"invalid block");
return -EIO;
}
}
return 0;
}
#define ext4_check_indirect_blockref(inode, bh) \
__ext4_check_blockref(__func__, __LINE__, inode, \
(__le32 *)(bh)->b_data, \
EXT4_ADDR_PER_BLOCK((inode)->i_sb))
#define ext4_check_inode_blockref(inode) \
__ext4_check_blockref(__func__, __LINE__, inode, \
EXT4_I(inode)->i_data, \
EXT4_NDIR_BLOCKS)
/**
* ext4_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 <key, p, bh> 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 reads all @depth-1 indirect blocks successfully and finds
* the whole chain, all way to the data (returns %NULL, *err == 0).
*
* Need to be called with
* down_read(&EXT4_I(inode)->i_data_sem)
*/
static Indirect *ext4_get_branch(struct inode *inode, int depth,
ext4_lblk_t *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, EXT4_I(inode)->i_data + *offsets);
if (!p->key)
goto no_block;
while (--depth) {
bh = sb_getblk(sb, le32_to_cpu(p->key));
if (unlikely(!bh))
goto failure;
if (!bh_uptodate_or_lock(bh)) {
if (bh_submit_read(bh) < 0) {
put_bh(bh);
goto failure;
}
/* validate block references */
if (ext4_check_indirect_blockref(inode, bh)) {
put_bh(bh);
goto failure;
}
}
add_chain(++p, bh, (__le32 *)bh->b_data + *++offsets);
/* Reader: end */
if (!p->key)
goto no_block;
}
return NULL;
failure:
*err = -EIO;
no_block:
return p;
}
/**
* ext4_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 ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind)
{
struct ext4_inode_info *ei = EXT4_I(inode);
__le32 *start = ind->bh ? (__le32 *) ind->bh->b_data : ei->i_data;
__le32 *p;
ext4_fsblk_t bg_start;
ext4_fsblk_t last_block;
ext4_grpblk_t colour;
ext4_group_t block_group;
int flex_size = ext4_flex_bg_size(EXT4_SB(inode->i_sb));
/* 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 to from the inode itself? OK, just put it
* into the same cylinder group then.
*/
block_group = ei->i_block_group;
if (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) {
block_group &= ~(flex_size-1);
if (S_ISREG(inode->i_mode))
block_group++;
}
bg_start = ext4_group_first_block_no(inode->i_sb, block_group);
last_block = ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es) - 1;
/*
* If we are doing delayed allocation, we don't need take
* colour into account.
*/
if (test_opt(inode->i_sb, DELALLOC))
return bg_start;
if (bg_start + EXT4_BLOCKS_PER_GROUP(inode->i_sb) <= last_block)
colour = (current->pid % 16) *
(EXT4_BLOCKS_PER_GROUP(inode->i_sb) / 16);
else
colour = (current->pid % 16) * ((last_block - bg_start) / 16);
return bg_start + colour;
}
/**
* ext4_find_goal - find a preferred place for allocation.
* @inode: owner
* @block: block we want
* @partial: pointer to the last triple within a chain
*
* Normally this function find the preferred place for block allocation,
* returns it.
* Because this is only used for non-extent files, we limit the block nr
* to 32 bits.
*/
static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block,
Indirect *partial)
{
ext4_fsblk_t goal;
/*
* XXX need to get goal block from mballoc's data structures
*/
goal = ext4_find_near(inode, partial);
goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
return goal;
}
/**
* ext4_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 ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks,
int blocks_to_boundary)
{
unsigned int 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 we don't handle 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;
}
/**
* ext4_alloc_blocks: multiple allocate blocks needed for a branch
* @handle: handle for this transaction
* @inode: inode which needs allocated blocks
* @iblock: the logical block to start allocated at
* @goal: preferred physical block of allocation
* @indirect_blks: the number of blocks need to allocate for indirect
* blocks
* @blks: number of desired blocks
* @new_blocks: on return it will store the new block numbers for
* the indirect blocks(if needed) and the first direct block,
* @err: on return it will store the error code
*
* This function will return the number of blocks allocated as
* requested by the passed-in parameters.
*/
static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
ext4_lblk_t iblock, ext4_fsblk_t goal,
int indirect_blks, int blks,
ext4_fsblk_t new_blocks[4], int *err)
{
struct ext4_allocation_request ar;
int target, i;
unsigned long count = 0, blk_allocated = 0;
int index = 0;
ext4_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)
*/
/* first we try to allocate the indirect blocks */
target = indirect_blks;
while (target > 0) {
count = target;
/* allocating blocks for indirect blocks and direct blocks */
current_block = ext4_new_meta_blocks(handle, inode, goal,
0, &count, err);
if (*err)
goto failed_out;
if (unlikely(current_block + count > EXT4_MAX_BLOCK_FILE_PHYS)) {
EXT4_ERROR_INODE(inode,
"current_block %llu + count %lu > %d!",
current_block, count,
EXT4_MAX_BLOCK_FILE_PHYS);
*err = -EIO;
goto failed_out;
}
target -= count;
/* allocate blocks for indirect blocks */
while (index < indirect_blks && count) {
new_blocks[index++] = current_block++;
count--;
}
if (count > 0) {
/*
* save the new block number
* for the first direct block
*/
new_blocks[index] = current_block;
printk(KERN_INFO "%s returned more blocks than "
"requested\n", __func__);
WARN_ON(1);
break;
}
}
target = blks - count ;
blk_allocated = count;
if (!target)
goto allocated;
/* Now allocate data blocks */
memset(&ar, 0, sizeof(ar));
ar.inode = inode;
ar.goal = goal;
ar.len = target;
ar.logical = iblock;
if (S_ISREG(inode->i_mode))
/* enable in-core preallocation only for regular files */
ar.flags = EXT4_MB_HINT_DATA;
current_block = ext4_mb_new_blocks(handle, &ar, err);
if (unlikely(current_block + ar.len > EXT4_MAX_BLOCK_FILE_PHYS)) {
EXT4_ERROR_INODE(inode,
"current_block %llu + ar.len %d > %d!",
current_block, ar.len,
EXT4_MAX_BLOCK_FILE_PHYS);
*err = -EIO;
goto failed_out;
}
if (*err && (target == blks)) {
/*
* if the allocation failed and we didn't allocate
* any blocks before
*/
goto failed_out;
}
if (!*err) {
if (target == blks) {
/*
* save the new block number
* for the first direct block
*/
new_blocks[index] = current_block;
}
blk_allocated += ar.len;
}
allocated:
/* total number of blocks allocated for direct blocks */
ret = blk_allocated;
*err = 0;
return ret;
failed_out:
for (i = 0; i < index; i++)
ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0);
return ret;
}
/**
* ext4_alloc_branch - allocate and set up a chain of blocks.
* @handle: handle for this transaction
* @inode: owner
* @indirect_blks: number of allocated indirect blocks
* @blks: number of allocated direct blocks
* @goal: preferred place for allocation
* @offsets: offsets (in the blocks) to store the pointers to next.
* @branch: place to store the chain in.
*
* This function allocates blocks, zeroes out all but the last one,
* links them into chain and (if we are synchronous) writes them to disk.
* In other words, it prepares a branch that can be spliced onto the
* inode. It stores the information about that chain in the branch[], in
* the same format as ext4_get_branch() would do. We are calling it after
* we had read the existing part of chain and partial points to the last
* triple of that (one with zero ->key). Upon the exit we have the same
* picture as after the successful ext4_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
* ext4_alloc_block() (normally -ENOSPC). Otherwise we set the chain
* as described above and return 0.
*/
static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
ext4_lblk_t iblock, int indirect_blks,
int *blks, ext4_fsblk_t goal,
ext4_lblk_t *offsets, Indirect *branch)
{
int blocksize = inode->i_sb->s_blocksize;
int i, n = 0;
int err = 0;
struct buffer_head *bh;
int num;
ext4_fsblk_t new_blocks[4];
ext4_fsblk_t current_block;
num = ext4_alloc_blocks(handle, inode, iblock, 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 = -EIO;
goto failed;
}
branch[n].bh = bh;
lock_buffer(bh);
BUFFER_TRACE(bh, "call get_create_access");
err = ext4_journal_get_create_access(handle, bh);
if (err) {
/* Don't brelse(bh) here; it's done in
* ext4_journal_forget() below */
unlock_buffer(bh);
goto failed;
}
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);
}
BUFFER_TRACE(bh, "marking uptodate");
set_buffer_uptodate(bh);
unlock_buffer(bh);
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
err = ext4_handle_dirty_metadata(handle, inode, bh);
if (err)
goto failed;
}
*blks = num;
return err;
failed:
/* Allocation failed, free what we already allocated */
ext4_free_blocks(handle, inode, NULL, new_blocks[0], 1, 0);
for (i = 1; i <= n ; i++) {
/*
* branch[i].bh is newly allocated, so there is no
* need to revoke the block, which is why we don't
* need to set EXT4_FREE_BLOCKS_METADATA.
*/
ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1,
EXT4_FREE_BLOCKS_FORGET);
}
for (i = n+1; i < indirect_blks; i++)
ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0);
ext4_free_blocks(handle, inode, NULL, new_blocks[i], num, 0);
return err;
}
/**
* ext4_splice_branch - splice the allocated branch onto inode.
* @handle: handle for this transaction
* @inode: owner
* @block: (logical) number of block we are adding
* @chain: chain of indirect blocks (with a missing link - see
* ext4_alloc_branch)
* @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 int ext4_splice_branch(handle_t *handle, struct inode *inode,
ext4_lblk_t block, Indirect *where, int num,
int blks)
{
int i;
int err = 0;
ext4_fsblk_t current_block;
/*
* If we're splicing into a [td]indirect block (as opposed to the
* inode) then we need to get write access to the [td]indirect block
* before the splice.
*/
if (where->bh) {
BUFFER_TRACE(where->bh, "get_write_access");
err = ext4_journal_get_write_access(handle, where->bh);
if (err)
goto err_out;
}
/* 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++);
}
/* We are done with atomic stuff, now do the rest of housekeeping */
/* had we spliced it onto indirect block? */
if (where->bh) {
/*
* If we spliced it onto an indirect block, we haven't
* altered the inode. Note however that if it is being spliced
* onto an indirect block at the very end of the file (the
* file is growing) then we *will* alter the inode to reflect
* the new i_size. But that is not done here - it is done in
* generic_commit_write->__mark_inode_dirty->ext4_dirty_inode.
*/
jbd_debug(5, "splicing indirect only\n");
BUFFER_TRACE(where->bh, "call ext4_handle_dirty_metadata");
err = ext4_handle_dirty_metadata(handle, inode, where->bh);
if (err)
goto err_out;
} else {
/*
* OK, we spliced it into the inode itself on a direct block.
*/
ext4_mark_inode_dirty(handle, inode);
jbd_debug(5, "splicing direct\n");
}
return err;
err_out:
for (i = 1; i <= num; i++) {
/*
* branch[i].bh is newly allocated, so there is no
* need to revoke the block, which is why we don't
* need to set EXT4_FREE_BLOCKS_METADATA.
*/
ext4_free_blocks(handle, inode, where[i].bh, 0, 1,
EXT4_FREE_BLOCKS_FORGET);
}
ext4_free_blocks(handle, inode, NULL, le32_to_cpu(where[num].key),
blks, 0);
return err;
}
/*
* The ext4_ind_map_blocks() function handles non-extents inodes
* (i.e., using the traditional indirect/double-indirect i_blocks
* scheme) for ext4_map_blocks().
*
* 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.
*
* The ext4_ind_get_blocks() function should be called with
* down_write(&EXT4_I(inode)->i_data_sem) if allocating filesystem
* blocks (i.e., flags has EXT4_GET_BLOCKS_CREATE set) or
* down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system
* blocks.
*/
static int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map,
int flags)
{
int err = -EIO;
ext4_lblk_t offsets[4];
Indirect chain[4];
Indirect *partial;
ext4_fsblk_t goal;
int indirect_blks;
int blocks_to_boundary = 0;
int depth;
int count = 0;
ext4_fsblk_t first_block = 0;
trace_ext4_ind_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
J_ASSERT(!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)));
J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0);
depth = ext4_block_to_path(inode, map->m_lblk, offsets,
&blocks_to_boundary);
if (depth == 0)
goto out;
partial = ext4_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);
count++;
/*map more blocks*/
while (count < map->m_len && count <= blocks_to_boundary) {
ext4_fsblk_t blk;
blk = le32_to_cpu(*(chain[depth-1].p + count));
if (blk == first_block + count)
count++;
else
break;
}
goto got_it;
}
/* Next simple case - plain lookup or failed read of indirect block */
if ((flags & EXT4_GET_BLOCKS_CREATE) == 0 || err == -EIO)
goto cleanup;
/*
* Okay, we need to do block allocation.
*/
goal = ext4_find_goal(inode, map->m_lblk, 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 = ext4_blks_to_allocate(partial, indirect_blks,
map->m_len, blocks_to_boundary);
/*
* Block out ext4_truncate while we alter the tree
*/
err = ext4_alloc_branch(handle, inode, map->m_lblk, indirect_blks,
&count, goal,
offsets + (partial - chain), partial);
/*
* The ext4_splice_branch call will free and forget any buffers
* on the new chain if there is a failure, but that risks using
* up transaction credits, especially for bitmaps where the
* credits cannot be returned. Can we handle this somehow? We
* may need to return -EAGAIN upwards in the worst case. --sct
*/
if (!err)
err = ext4_splice_branch(handle, inode, map->m_lblk,
partial, indirect_blks, count);
if (err)
goto cleanup;
map->m_flags |= EXT4_MAP_NEW;
ext4_update_inode_fsync_trans(handle, inode, 1);
got_it:
map->m_flags |= EXT4_MAP_MAPPED;
map->m_pblk = le32_to_cpu(chain[depth-1].key);
map->m_len = count;
if (count > blocks_to_boundary)
map->m_flags |= EXT4_MAP_BOUNDARY;
err = count;
/* Clean up and exit */
partial = chain + depth - 1; /* the whole chain */
cleanup:
while (partial > chain) {
BUFFER_TRACE(partial->bh, "call brelse");
brelse(partial->bh);
partial--;
}
out:
trace_ext4_ind_map_blocks_exit(inode, map->m_lblk,
map->m_pblk, map->m_len, err);
return err;
}
#ifdef CONFIG_QUOTA
qsize_t *ext4_get_reserved_space(struct inode *inode)
{
return &EXT4_I(inode)->i_reserved_quota;
}
#endif
/*
* Calculate the number of metadata blocks need to reserve
* to allocate a new block at @lblocks for non extent file based file
*/
static int ext4_indirect_calc_metadata_amount(struct inode *inode,
sector_t lblock)
{
struct ext4_inode_info *ei = EXT4_I(inode);
sector_t dind_mask = ~((sector_t)EXT4_ADDR_PER_BLOCK(inode->i_sb) - 1);
int blk_bits;
if (lblock < EXT4_NDIR_BLOCKS)
return 0;
lblock -= EXT4_NDIR_BLOCKS;
if (ei->i_da_metadata_calc_len &&
(lblock & dind_mask) == ei->i_da_metadata_calc_last_lblock) {
ei->i_da_metadata_calc_len++;
return 0;
}
ei->i_da_metadata_calc_last_lblock = lblock & dind_mask;
ei->i_da_metadata_calc_len = 1;
blk_bits = order_base_2(lblock);
return (blk_bits / EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb)) + 1;
}
/*
* Calculate the number of metadata blocks need to reserve
* to allocate a block located at @lblock
*/
static int ext4_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock)
{
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
return ext4_ext_calc_metadata_amount(inode, lblock);
return ext4_indirect_calc_metadata_amount(inode, lblock);
}
/*
* Called with i_data_sem down, which is important since we can call
* ext4_discard_preallocations() from here.
*/
void ext4_da_update_reserve_space(struct inode *inode,
int used, int quota_claim)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
spin_lock(&ei->i_block_reservation_lock);
trace_ext4_da_update_reserve_space(inode, used);
if (unlikely(used > ei->i_reserved_data_blocks)) {
ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, used %d "
"with only %d reserved data blocks\n",
__func__, inode->i_ino, used,
ei->i_reserved_data_blocks);
WARN_ON(1);
used = ei->i_reserved_data_blocks;
}
/* Update per-inode reservations */
ei->i_reserved_data_blocks -= used;
ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks;
percpu_counter_sub(&sbi->s_dirtyblocks_counter,
used + ei->i_allocated_meta_blocks);
ei->i_allocated_meta_blocks = 0;
if (ei->i_reserved_data_blocks == 0) {
/*
* We can release all of the reserved metadata blocks
* only when we have written all of the delayed
* allocation blocks.
*/
percpu_counter_sub(&sbi->s_dirtyblocks_counter,
ei->i_reserved_meta_blocks);
ei->i_reserved_meta_blocks = 0;
ei->i_da_metadata_calc_len = 0;
}
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
/* Update quota subsystem for data blocks */
if (quota_claim)
dquot_claim_block(inode, used);
else {
/*
* We did fallocate with an offset that is already delayed
* allocated. So on delayed allocated writeback we should
* not re-claim the quota for fallocated blocks.
*/
dquot_release_reservation_block(inode, used);
}
/*
* If we have done all the pending block allocations and if
* there aren't any writers on the inode, we can discard the
* inode's preallocations.
*/
if ((ei->i_reserved_data_blocks == 0) &&
(atomic_read(&inode->i_writecount) == 0))
ext4_discard_preallocations(inode);
}
static int __check_block_validity(struct inode *inode, const char *func,
unsigned int line,
struct ext4_map_blocks *map)
{
if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk,
map->m_len)) {
ext4_error_inode(inode, func, line, map->m_pblk,
"lblock %lu mapped to illegal pblock "
"(length %d)", (unsigned long) map->m_lblk,
map->m_len);
return -EIO;
}
return 0;
}
#define check_block_validity(inode, map) \
__check_block_validity((inode), __func__, __LINE__, (map))
/*
* Return the number of contiguous dirty pages in a given inode
* starting at page frame idx.
*/
static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx,
unsigned int max_pages)
{
struct address_space *mapping = inode->i_mapping;
pgoff_t index;
struct pagevec pvec;
pgoff_t num = 0;
int i, nr_pages, done = 0;
if (max_pages == 0)
return 0;
pagevec_init(&pvec, 0);
while (!done) {
index = idx;
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_DIRTY,
(pgoff_t)PAGEVEC_SIZE);
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
struct buffer_head *bh, *head;
lock_page(page);
if (unlikely(page->mapping != mapping) ||
!PageDirty(page) ||
PageWriteback(page) ||
page->index != idx) {
done = 1;
unlock_page(page);
break;
}
if (page_has_buffers(page)) {
bh = head = page_buffers(page);
do {
if (!buffer_delay(bh) &&
!buffer_unwritten(bh))
done = 1;
bh = bh->b_this_page;
} while (!done && (bh != head));
}
unlock_page(page);
if (done)
break;
idx++;
num++;
if (num >= max_pages) {
done = 1;
break;
}
}
pagevec_release(&pvec);
}
return num;
}
/*
* The ext4_map_blocks() function tries to look up the requested blocks,
* and returns if the blocks are already mapped.
*
* Otherwise it takes the write lock of the i_data_sem and allocate blocks
* and store the allocated blocks in the result buffer head and mark it
* mapped.
*
* If file type is extents based, it will call ext4_ext_map_blocks(),
* Otherwise, call with ext4_ind_map_blocks() to handle indirect mapping
* based files
*
* On success, it returns the number of blocks being mapped or allocate.
* if create==0 and the blocks are pre-allocated and uninitialized block,
* the result buffer head is unmapped. If the create ==1, it will make sure
* the buffer head is mapped.
*
* It returns 0 if plain look up failed (blocks have not been allocated), in
* that casem, buffer head is unmapped
*
* It returns the error in case of allocation failure.
*/
int ext4_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags)
{
int retval;
map->m_flags = 0;
ext_debug("ext4_map_blocks(): inode %lu, flag %d, max_blocks %u,"
"logical block %lu\n", inode->i_ino, flags, map->m_len,
(unsigned long) map->m_lblk);
/*
* Try to see if we can get the block without requesting a new
* file system block.
*/
down_read((&EXT4_I(inode)->i_data_sem));
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
retval = ext4_ext_map_blocks(handle, inode, map, 0);
} else {
retval = ext4_ind_map_blocks(handle, inode, map, 0);
}
up_read((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
int ret = check_block_validity(inode, map);
if (ret != 0)
return ret;
}
/* If it is only a block(s) look up */
if ((flags & EXT4_GET_BLOCKS_CREATE) == 0)
return retval;
/*
* Returns if the blocks have already allocated
*
* Note that if blocks have been preallocated
* ext4_ext_get_block() returns th create = 0
* with buffer head unmapped.
*/
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
return retval;
/*
* When we call get_blocks without the create flag, the
* BH_Unwritten flag could have gotten set if the blocks
* requested were part of a uninitialized extent. We need to
* clear this flag now that we are committed to convert all or
* part of the uninitialized extent to be an initialized
* extent. This is because we need to avoid the combination
* of BH_Unwritten and BH_Mapped flags being simultaneously
* set on the buffer_head.
*/
map->m_flags &= ~EXT4_MAP_UNWRITTEN;
/*
* New blocks allocate and/or writing to uninitialized extent
* will possibly result in updating i_data, so we take
* the write lock of i_data_sem, and call get_blocks()
* with create == 1 flag.
*/
down_write((&EXT4_I(inode)->i_data_sem));
/*
* if the caller is from delayed allocation writeout path
* we have already reserved fs blocks for allocation
* let the underlying get_block() function know to
* avoid double accounting
*/
if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
ext4_set_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
/*
* We need to check for EXT4 here because migrate
* could have changed the inode type in between
*/
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
retval = ext4_ext_map_blocks(handle, inode, map, flags);
} else {
retval = ext4_ind_map_blocks(handle, inode, map, flags);
if (retval > 0 && map->m_flags & EXT4_MAP_NEW) {
/*
* We allocated new blocks which will result in
* i_data's format changing. Force the migrate
* to fail by clearing migrate flags
*/
ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
}
/*
* Update reserved blocks/metadata blocks after successful
* block allocation which had been deferred till now. We don't
* support fallocate for non extent files. So we can update
* reserve space here.
*/
if ((retval > 0) &&
(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE))
ext4_da_update_reserve_space(inode, retval, 1);
}
if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
up_write((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
int ret = check_block_validity(inode, map);
if (ret != 0)
return ret;
}
return retval;
}
/* Maximum number of blocks we map for direct IO at once. */
#define DIO_MAX_BLOCKS 4096
static int _ext4_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int flags)
{
handle_t *handle = ext4_journal_current_handle();
struct ext4_map_blocks map;
int ret = 0, started = 0;
int dio_credits;
map.m_lblk = iblock;
map.m_len = bh->b_size >> inode->i_blkbits;
if (flags && !handle) {
/* Direct IO write... */
if (map.m_len > DIO_MAX_BLOCKS)
map.m_len = DIO_MAX_BLOCKS;
dio_credits = ext4_chunk_trans_blocks(inode, map.m_len);
handle = ext4_journal_start(inode, dio_credits);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
return ret;
}
started = 1;
}
ret = ext4_map_blocks(handle, inode, &map, flags);
if (ret > 0) {
map_bh(bh, inode->i_sb, map.m_pblk);
bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
bh->b_size = inode->i_sb->s_blocksize * map.m_len;
ret = 0;
}
if (started)
ext4_journal_stop(handle);
return ret;
}
int ext4_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int create)
{
return _ext4_get_block(inode, iblock, bh,
create ? EXT4_GET_BLOCKS_CREATE : 0);
}
/*
* `handle' can be NULL if create is zero
*/
struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
ext4_lblk_t block, int create, int *errp)
{
struct ext4_map_blocks map;
struct buffer_head *bh;
int fatal = 0, err;
J_ASSERT(handle != NULL || create == 0);
map.m_lblk = block;
map.m_len = 1;
err = ext4_map_blocks(handle, inode, &map,
create ? EXT4_GET_BLOCKS_CREATE : 0);
if (err < 0)
*errp = err;
if (err <= 0)
return NULL;
*errp = 0;
bh = sb_getblk(inode->i_sb, map.m_pblk);
if (!bh) {
*errp = -EIO;
return NULL;
}
if (map.m_flags & EXT4_MAP_NEW) {
J_ASSERT(create != 0);
J_ASSERT(handle != NULL);
/*
* Now that we do not always journal data, we should
* keep in mind whether this should always journal the
* new buffer as metadata. For now, regular file
* writes use ext4_get_block instead, so it's not a
* problem.
*/
lock_buffer(bh);
BUFFER_TRACE(bh, "call get_create_access");
fatal = ext4_journal_get_create_access(handle, bh);
if (!fatal && !buffer_uptodate(bh)) {
memset(bh->b_data, 0, inode->i_sb->s_blocksize);
set_buffer_uptodate(bh);
}
unlock_buffer(bh);
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
err = ext4_handle_dirty_metadata(handle, inode, bh);
if (!fatal)
fatal = err;
} else {
BUFFER_TRACE(bh, "not a new buffer");
}
if (fatal) {
*errp = fatal;
brelse(bh);
bh = NULL;
}
return bh;
}
struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
ext4_lblk_t block, int create, int *err)
{
struct buffer_head *bh;
bh = ext4_getblk(handle, inode, block, create, err);
if (!bh)
return bh;
if (buffer_uptodate(bh))
return bh;
ll_rw_block(READ_META, 1, &bh);
wait_on_buffer(bh);
if (buffer_uptodate(bh))
return bh;
put_bh(bh);
*err = -EIO;
return NULL;
}
static int walk_page_buffers(handle_t *handle,
struct buffer_head *head,
unsigned from,
unsigned to,
int *partial,
int (*fn)(handle_t *handle,
struct buffer_head *bh))
{
struct buffer_head *bh;
unsigned block_start, block_end;
unsigned blocksize = head->b_size;
int err, ret = 0;
struct buffer_head *next;
for (bh = head, block_start = 0;
ret == 0 && (bh != head || !block_start);
block_start = block_end, bh = next) {
next = bh->b_this_page;
block_end = block_start + blocksize;
if (block_end <= from || block_start >= to) {
if (partial && !buffer_uptodate(bh))
*partial = 1;
continue;
}
err = (*fn)(handle, bh);
if (!ret)
ret = err;
}
return ret;
}
/*
* To preserve ordering, it is essential that the hole instantiation and
* the data write be encapsulated in a single transaction. We cannot
* close off a transaction and start a new one between the ext4_get_block()
* and the commit_write(). So doing the jbd2_journal_start at the start of
* prepare_write() is the right place.
*
* Also, this function can nest inside ext4_writepage() ->
* block_write_full_page(). In that case, we *know* that ext4_writepage()
* has generated enough buffer credits to do the whole page. So we won't
* block on the journal in that case, which is good, because the caller may
* be PF_MEMALLOC.
*
* By accident, ext4 can be reentered when a transaction is open via
* quota file writes. If we were to commit the transaction while thus
* reentered, there can be a deadlock - we would be holding a quota
* lock, and the commit would never complete if another thread had a
* transaction open and was blocking on the quota lock - a ranking
* violation.
*
* So what we do is to rely on the fact that jbd2_journal_stop/journal_start
* will _not_ run commit under these circumstances because handle->h_ref
* is elevated. We'll still have enough credits for the tiny quotafile
* write.
*/
static int do_journal_get_write_access(handle_t *handle,
struct buffer_head *bh)
{
int dirty = buffer_dirty(bh);
int ret;
if (!buffer_mapped(bh) || buffer_freed(bh))
return 0;
/*
* __block_write_begin() could have dirtied some buffers. Clean
* the dirty bit as jbd2_journal_get_write_access() could complain
* otherwise about fs integrity issues. Setting of the dirty bit
* by __block_write_begin() isn't a real problem here as we clear
* the bit before releasing a page lock and thus writeback cannot
* ever write the buffer.
*/
if (dirty)
clear_buffer_dirty(bh);
ret = ext4_journal_get_write_access(handle, bh);
if (!ret && dirty)
ret = ext4_handle_dirty_metadata(handle, NULL, bh);
return ret;
}
/*
* Truncate blocks that were not used by write. We have to truncate the
* pagecache as well so that corresponding buffers get properly unmapped.
*/
static void ext4_truncate_failed_write(struct inode *inode)
{
truncate_inode_pages(inode->i_mapping, inode->i_size);
ext4_truncate(inode);
}
static int ext4_get_block_write(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
static int ext4_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
struct inode *inode = mapping->host;
int ret, needed_blocks;
handle_t *handle;
int retries = 0;
struct page *page;
pgoff_t index;
unsigned from, to;
trace_ext4_write_begin(inode, pos, len, flags);
/*
* Reserve one block more for addition to orphan list in case
* we allocate blocks but write fails for some reason
*/
needed_blocks = ext4_writepage_trans_blocks(inode) + 1;
index = pos >> PAGE_CACHE_SHIFT;
from = pos & (PAGE_CACHE_SIZE - 1);
to = from + len;
retry:
handle = ext4_journal_start(inode, needed_blocks);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
goto out;
}
/* We cannot recurse into the filesystem as the transaction is already
* started */
flags |= AOP_FLAG_NOFS;
page = grab_cache_page_write_begin(mapping, index, flags);
if (!page) {
ext4_journal_stop(handle);
ret = -ENOMEM;
goto out;
}
*pagep = page;
if (ext4_should_dioread_nolock(inode))
ret = __block_write_begin(page, pos, len, ext4_get_block_write);
else
ret = __block_write_begin(page, pos, len, ext4_get_block);
if (!ret && ext4_should_journal_data(inode)) {
ret = walk_page_buffers(handle, page_buffers(page),
from, to, NULL, do_journal_get_write_access);
}
if (ret) {
unlock_page(page);
page_cache_release(page);
/*
* __block_write_begin may have instantiated a few blocks
* outside i_size. Trim these off again. Don't need
* i_size_read because we hold i_mutex.
*
* Add inode to orphan list in case we crash before
* truncate finishes
*/
if (pos + len > inode->i_size && ext4_can_truncate(inode))
ext4_orphan_add(handle, inode);
ext4_journal_stop(handle);
if (pos + len > inode->i_size) {
ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might
* still be on the orphan list; we need to
* make sure the inode is removed from the
* orphan list in that case.
*/
if (inode->i_nlink)
ext4_orphan_del(NULL, inode);
}
}
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry;
out:
return ret;
}
/* For write_end() in data=journal mode */
static int write_end_fn(handle_t *handle, struct buffer_head *bh)
{
if (!buffer_mapped(bh) || buffer_freed(bh))
return 0;
set_buffer_uptodate(bh);
return ext4_handle_dirty_metadata(handle, NULL, bh);
}
static int ext4_generic_write_end(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
int i_size_changed = 0;
struct inode *inode = mapping->host;
handle_t *handle = ext4_journal_current_handle();
copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
/*
* No need to use i_size_read() here, the i_size
* cannot change under us because we hold i_mutex.
*
* But it's important to update i_size while still holding page lock:
* page writeout could otherwise come in and zero beyond i_size.
*/
if (pos + copied > inode->i_size) {
i_size_write(inode, pos + copied);
i_size_changed = 1;
}
if (pos + copied > EXT4_I(inode)->i_disksize) {
/* We need to mark inode dirty even if
* new_i_size is less that inode->i_size
* bu greater than i_disksize.(hint delalloc)
*/
ext4_update_i_disksize(inode, (pos + copied));
i_size_changed = 1;
}
unlock_page(page);
page_cache_release(page);
/*
* Don't mark the inode dirty under page lock. First, it unnecessarily
* makes the holding time of page lock longer. Second, it forces lock
* ordering of page lock and transaction start for journaling
* filesystems.
*/
if (i_size_changed)
ext4_mark_inode_dirty(handle, inode);
return copied;
}
/*
* We need to pick up the new inode size which generic_commit_write gave us
* `file' can be NULL - eg, when called from page_symlink().
*
* ext4 never places buffers on inode->i_mapping->private_list. metadata
* buffers are managed internally.
*/
static int ext4_ordered_write_end(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
handle_t *handle = ext4_journal_current_handle();
struct inode *inode = mapping->host;
int ret = 0, ret2;
trace_ext4_ordered_write_end(inode, pos, len, copied);
ret = ext4_jbd2_file_inode(handle, inode);
if (ret == 0) {
ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
page, fsdata);
copied = ret2;
if (pos + len > inode->i_size && ext4_can_truncate(inode))
/* if we have allocated more blocks and copied
* less. We will have blocks allocated outside
* inode->i_size. So truncate them
*/
ext4_orphan_add(handle, inode);
if (ret2 < 0)
ret = ret2;
}
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
if (pos + len > inode->i_size) {
ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might still be
* on the orphan list; we need to make sure the inode
* is removed from the orphan list in that case.
*/
if (inode->i_nlink)
ext4_orphan_del(NULL, inode);
}
return ret ? ret : copied;
}
static int ext4_writeback_write_end(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
handle_t *handle = ext4_journal_current_handle();
struct inode *inode = mapping->host;
int ret = 0, ret2;
trace_ext4_writeback_write_end(inode, pos, len, copied);
ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
page, fsdata);
copied = ret2;
if (pos + len > inode->i_size && ext4_can_truncate(inode))
/* if we have allocated more blocks and copied
* less. We will have blocks allocated outside
* inode->i_size. So truncate them
*/
ext4_orphan_add(handle, inode);
if (ret2 < 0)
ret = ret2;
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
if (pos + len > inode->i_size) {
ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might still be
* on the orphan list; we need to make sure the inode
* is removed from the orphan list in that case.
*/
if (inode->i_nlink)
ext4_orphan_del(NULL, inode);
}
return ret ? ret : copied;
}
static int ext4_journalled_write_end(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
handle_t *handle = ext4_journal_current_handle();
struct inode *inode = mapping->host;
int ret = 0, ret2;
int partial = 0;
unsigned from, to;
loff_t new_i_size;
trace_ext4_journalled_write_end(inode, pos, len, copied);
from = pos & (PAGE_CACHE_SIZE - 1);
to = from + len;
if (copied < len) {
if (!PageUptodate(page))
copied = 0;
page_zero_new_buffers(page, from+copied, to);
}
ret = walk_page_buffers(handle, page_buffers(page), from,
to, &partial, write_end_fn);
if (!partial)
SetPageUptodate(page);
new_i_size = pos + copied;
if (new_i_size > inode->i_size)
i_size_write(inode, pos+copied);
ext4_set_inode_state(inode, EXT4_STATE_JDATA);
if (new_i_size > EXT4_I(inode)->i_disksize) {
ext4_update_i_disksize(inode, new_i_size);
ret2 = ext4_mark_inode_dirty(handle, inode);
if (!ret)
ret = ret2;
}
unlock_page(page);
page_cache_release(page);
if (pos + len > inode->i_size && ext4_can_truncate(inode))
/* if we have allocated more blocks and copied
* less. We will have blocks allocated outside
* inode->i_size. So truncate them
*/
ext4_orphan_add(handle, inode);
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
if (pos + len > inode->i_size) {
ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might still be
* on the orphan list; we need to make sure the inode
* is removed from the orphan list in that case.
*/
if (inode->i_nlink)
ext4_orphan_del(NULL, inode);
}
return ret ? ret : copied;
}
/*
* Reserve a single block located at lblock
*/
static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
{
int retries = 0;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned long md_needed;
int ret;
/*
* recalculate the amount of metadata blocks to reserve
* in order to allocate nrblocks
* worse case is one extent per block
*/
repeat:
spin_lock(&ei->i_block_reservation_lock);
md_needed = ext4_calc_metadata_amount(inode, lblock);
trace_ext4_da_reserve_space(inode, md_needed);
spin_unlock(&ei->i_block_reservation_lock);
/*
* We will charge metadata quota at writeout time; this saves
* us from metadata over-estimation, though we may go over by
* a small amount in the end. Here we just reserve for data.
*/
ret = dquot_reserve_block(inode, 1);
if (ret)
return ret;
/*
* We do still charge estimated metadata to the sb though;
* we cannot afford to run out of free blocks.
*/
if (ext4_claim_free_blocks(sbi, md_needed + 1, 0)) {
dquot_release_reservation_block(inode, 1);
if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
yield();
goto repeat;
}
return -ENOSPC;
}
spin_lock(&ei->i_block_reservation_lock);
ei->i_reserved_data_blocks++;
ei->i_reserved_meta_blocks += md_needed;
spin_unlock(&ei->i_block_reservation_lock);
return 0; /* success */
}
static void ext4_da_release_space(struct inode *inode, int to_free)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
if (!to_free)
return; /* Nothing to release, exit */
spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
trace_ext4_da_release_space(inode, to_free);
if (unlikely(to_free > ei->i_reserved_data_blocks)) {
/*
* if there aren't enough reserved blocks, then the
* counter is messed up somewhere. Since this
* function is called from invalidate page, it's
* harmless to return without any action.
*/
ext4_msg(inode->i_sb, KERN_NOTICE, "ext4_da_release_space: "
"ino %lu, to_free %d with only %d reserved "
"data blocks\n", inode->i_ino, to_free,
ei->i_reserved_data_blocks);
WARN_ON(1);
to_free = ei->i_reserved_data_blocks;
}
ei->i_reserved_data_blocks -= to_free;
if (ei->i_reserved_data_blocks == 0) {
/*
* We can release all of the reserved metadata blocks
* only when we have written all of the delayed
* allocation blocks.
*/
percpu_counter_sub(&sbi->s_dirtyblocks_counter,
ei->i_reserved_meta_blocks);
ei->i_reserved_meta_blocks = 0;
ei->i_da_metadata_calc_len = 0;
}
/* update fs dirty data blocks counter */
percpu_counter_sub(&sbi->s_dirtyblocks_counter, to_free);
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
dquot_release_reservation_block(inode, to_free);
}
static void ext4_da_page_release_reservation(struct page *page,
unsigned long offset)
{
int to_release = 0;
struct buffer_head *head, *bh;
unsigned int curr_off = 0;
head = page_buffers(page);
bh = head;
do {
unsigned int next_off = curr_off + bh->b_size;
if ((offset <= curr_off) && (buffer_delay(bh))) {
to_release++;
clear_buffer_delay(bh);
}
curr_off = next_off;
} while ((bh = bh->b_this_page) != head);
ext4_da_release_space(page->mapping->host, to_release);
}
/*
* Delayed allocation stuff
*/
/*
* mpage_da_submit_io - walks through extent of pages and try to write
* them with writepage() call back
*
* @mpd->inode: inode
* @mpd->first_page: first page of the extent
* @mpd->next_page: page after the last page of the extent
*
* By the time mpage_da_submit_io() is called we expect all blocks
* to be allocated. this may be wrong if allocation failed.
*
* As pages are already locked by write_cache_pages(), we can't use it
*/
static int mpage_da_submit_io(struct mpage_da_data *mpd,
struct ext4_map_blocks *map)
{
struct pagevec pvec;
unsigned long index, end;
int ret = 0, err, nr_pages, i;
struct inode *inode = mpd->inode;
struct address_space *mapping = inode->i_mapping;
loff_t size = i_size_read(inode);
unsigned int len, block_start;
struct buffer_head *bh, *page_bufs = NULL;
int journal_data = ext4_should_journal_data(inode);
sector_t pblock = 0, cur_logical = 0;
struct ext4_io_submit io_submit;
BUG_ON(mpd->next_page <= mpd->first_page);
memset(&io_submit, 0, sizeof(io_submit));
/*
* We need to start from the first_page to the next_page - 1
* to make sure we also write the mapped dirty buffer_heads.
* If we look at mpd->b_blocknr we would only be looking
* at the currently mapped buffer_heads.
*/
index = mpd->first_page;
end = mpd->next_page - 1;
pagevec_init(&pvec, 0);
while (index <= end) {
nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
int commit_write = 0, skip_page = 0;
struct page *page = pvec.pages[i];
index = page->index;
if (index > end)
break;
if (index == size >> PAGE_CACHE_SHIFT)
len = size & ~PAGE_CACHE_MASK;
else
len = PAGE_CACHE_SIZE;
if (map) {
cur_logical = index << (PAGE_CACHE_SHIFT -
inode->i_blkbits);
pblock = map->m_pblk + (cur_logical -
map->m_lblk);
}
index++;
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
/*
* If the page does not have buffers (for
* whatever reason), try to create them using
* __block_write_begin. If this fails,
* skip the page and move on.
*/
if (!page_has_buffers(page)) {
if (__block_write_begin(page, 0, len,
noalloc_get_block_write)) {
skip_page:
unlock_page(page);
continue;
}
commit_write = 1;
}
bh = page_bufs = page_buffers(page);
block_start = 0;
do {
if (!bh)
goto skip_page;
if (map && (cur_logical >= map->m_lblk) &&
(cur_logical <= (map->m_lblk +
(map->m_len - 1)))) {
if (buffer_delay(bh)) {
clear_buffer_delay(bh);
bh->b_blocknr = pblock;
}
if (buffer_unwritten(bh) ||
buffer_mapped(bh))
BUG_ON(bh->b_blocknr != pblock);
if (map->m_flags & EXT4_MAP_UNINIT)
set_buffer_uninit(bh);
clear_buffer_unwritten(bh);
}
/* skip page if block allocation undone */
if (buffer_delay(bh) || buffer_unwritten(bh))
skip_page = 1;
bh = bh->b_this_page;
block_start += bh->b_size;
cur_logical++;
pblock++;
} while (bh != page_bufs);
if (skip_page)
goto skip_page;
if (commit_write)
/* mark the buffer_heads as dirty & uptodate */
block_commit_write(page, 0, len);
clear_page_dirty_for_io(page);
/*
* Delalloc doesn't support data journalling,
* but eventually maybe we'll lift this
* restriction.
*/
if (unlikely(journal_data && PageChecked(page)))
err = __ext4_journalled_writepage(page, len);
else if (test_opt(inode->i_sb, MBLK_IO_SUBMIT))
err = ext4_bio_write_page(&io_submit, page,
len, mpd->wbc);
else
err = block_write_full_page(page,
noalloc_get_block_write, mpd->wbc);
if (!err)
mpd->pages_written++;
/*
* In error case, we have to continue because
* remaining pages are still locked
*/
if (ret == 0)
ret = err;
}
pagevec_release(&pvec);
}
ext4_io_submit(&io_submit);
return ret;
}
static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd)
{
int nr_pages, i;
pgoff_t index, end;
struct pagevec pvec;
struct inode *inode = mpd->inode;
struct address_space *mapping = inode->i_mapping;
index = mpd->first_page;
end = mpd->next_page - 1;
while (index <= end) {
nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
if (nr_pages == 0)
break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
if (page->index > end)
break;
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
block_invalidatepage(page, 0);
ClearPageUptodate(page);
unlock_page(page);
}
index = pvec.pages[nr_pages - 1]->index + 1;
pagevec_release(&pvec);
}
return;
}
static void ext4_print_free_blocks(struct inode *inode)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
printk(KERN_CRIT "Total free blocks count %lld\n",
ext4_count_free_blocks(inode->i_sb));
printk(KERN_CRIT "Free/Dirty block details\n");
printk(KERN_CRIT "free_blocks=%lld\n",
(long long) percpu_counter_sum(&sbi->s_freeblocks_counter));
printk(KERN_CRIT "dirty_blocks=%lld\n",
(long long) percpu_counter_sum(&sbi->s_dirtyblocks_counter));
printk(KERN_CRIT "Block reservation details\n");
printk(KERN_CRIT "i_reserved_data_blocks=%u\n",
EXT4_I(inode)->i_reserved_data_blocks);
printk(KERN_CRIT "i_reserved_meta_blocks=%u\n",
EXT4_I(inode)->i_reserved_meta_blocks);
return;
}
/*
* mpage_da_map_and_submit - go through given space, map them
* if necessary, and then submit them for I/O
*
* @mpd - bh describing space
*
* The function skips space we know is already mapped to disk blocks.
*
*/
static void mpage_da_map_and_submit(struct mpage_da_data *mpd)
{
int err, blks, get_blocks_flags;
struct ext4_map_blocks map, *mapp = NULL;
sector_t next = mpd->b_blocknr;
unsigned max_blocks = mpd->b_size >> mpd->inode->i_blkbits;
loff_t disksize = EXT4_I(mpd->inode)->i_disksize;
handle_t *handle = NULL;
/*
* If the blocks are mapped already, or we couldn't accumulate
* any blocks, then proceed immediately to the submission stage.
*/
if ((mpd->b_size == 0) ||
((mpd->b_state & (1 << BH_Mapped)) &&
!(mpd->b_state & (1 << BH_Delay)) &&
!(mpd->b_state & (1 << BH_Unwritten))))
goto submit_io;
handle = ext4_journal_current_handle();
BUG_ON(!handle);
/*
* Call ext4_map_blocks() to allocate any delayed allocation
* blocks, or to convert an uninitialized extent to be
* initialized (in the case where we have written into
* one or more preallocated blocks).
*
* We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE to
* indicate that we are on the delayed allocation path. This
* affects functions in many different parts of the allocation
* call path. This flag exists primarily because we don't
* want to change *many* call functions, so ext4_map_blocks()
* will set the EXT4_STATE_DELALLOC_RESERVED flag once the
* inode's allocation semaphore is taken.
*
* If the blocks in questions were delalloc blocks, set
* EXT4_GET_BLOCKS_DELALLOC_RESERVE so the delalloc accounting
* variables are updated after the blocks have been allocated.
*/
map.m_lblk = next;
map.m_len = max_blocks;
get_blocks_flags = EXT4_GET_BLOCKS_CREATE;
if (ext4_should_dioread_nolock(mpd->inode))
get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
if (mpd->b_state & (1 << BH_Delay))
get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
blks = ext4_map_blocks(handle, mpd->inode, &map, get_blocks_flags);
if (blks < 0) {
struct super_block *sb = mpd->inode->i_sb;
err = blks;
/*
* If get block returns EAGAIN or ENOSPC and there
* appears to be free blocks we will just let
* mpage_da_submit_io() unlock all of the pages.
*/
if (err == -EAGAIN)
goto submit_io;
if (err == -ENOSPC &&
ext4_count_free_blocks(sb)) {
mpd->retval = err;
goto submit_io;
}
/*
* get block failure will cause us to loop in
* writepages, because a_ops->writepage won't be able
* to make progress. The page will be redirtied by
* writepage and writepages will again try to write
* the same.
*/
if (!(EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)) {
ext4_msg(sb, KERN_CRIT,
"delayed block allocation failed for inode %lu "
"at logical offset %llu with max blocks %zd "
"with error %d", mpd->inode->i_ino,
(unsigned long long) next,
mpd->b_size >> mpd->inode->i_blkbits, err);
ext4_msg(sb, KERN_CRIT,
"This should not happen!! Data will be lost\n");
if (err == -ENOSPC)
ext4_print_free_blocks(mpd->inode);
}
/* invalidate all the pages */
ext4_da_block_invalidatepages(mpd);
/* Mark this page range as having been completed */
mpd->io_done = 1;
return;
}
BUG_ON(blks == 0);
mapp = &map;
if (map.m_flags & EXT4_MAP_NEW) {
struct block_device *bdev = mpd->inode->i_sb->s_bdev;
int i;
for (i = 0; i < map.m_len; i++)
unmap_underlying_metadata(bdev, map.m_pblk + i);
}
if (ext4_should_order_data(mpd->inode)) {
err = ext4_jbd2_file_inode(handle, mpd->inode);
if (err)
/* This only happens if the journal is aborted */
return;
}
/*
* Update on-disk size along with block allocation.
*/
disksize = ((loff_t) next + blks) << mpd->inode->i_blkbits;
if (disksize > i_size_read(mpd->inode))
disksize = i_size_read(mpd->inode);
if (disksize > EXT4_I(mpd->inode)->i_disksize) {
ext4_update_i_disksize(mpd->inode, disksize);
err = ext4_mark_inode_dirty(handle, mpd->inode);
if (err)
ext4_error(mpd->inode->i_sb,
"Failed to mark inode %lu dirty",
mpd->inode->i_ino);
}
submit_io:
mpage_da_submit_io(mpd, mapp);
mpd->io_done = 1;
}
#define BH_FLAGS ((1 << BH_Uptodate) | (1 << BH_Mapped) | \
(1 << BH_Delay) | (1 << BH_Unwritten))
/*
* mpage_add_bh_to_extent - try to add one more block to extent of blocks
*
* @mpd->lbh - extent of blocks
* @logical - logical number of the block in the file
* @bh - bh of the block (used to access block's state)
*
* the function is used to collect contig. blocks in same state
*/
static void mpage_add_bh_to_extent(struct mpage_da_data *mpd,
sector_t logical, size_t b_size,
unsigned long b_state)
{
sector_t next;
int nrblocks = mpd->b_size >> mpd->inode->i_blkbits;
/*
* XXX Don't go larger than mballoc is willing to allocate
* This is a stopgap solution. We eventually need to fold
* mpage_da_submit_io() into this function and then call
* ext4_map_blocks() multiple times in a loop
*/
if (nrblocks >= 8*1024*1024/mpd->inode->i_sb->s_blocksize)
goto flush_it;
/* check if thereserved journal credits might overflow */
if (!(ext4_test_inode_flag(mpd->inode, EXT4_INODE_EXTENTS))) {
if (nrblocks >= EXT4_MAX_TRANS_DATA) {
/*
* With non-extent format we are limited by the journal
* credit available. Total credit needed to insert
* nrblocks contiguous blocks is dependent on the
* nrblocks. So limit nrblocks.
*/
goto flush_it;
} else if ((nrblocks + (b_size >> mpd->inode->i_blkbits)) >
EXT4_MAX_TRANS_DATA) {
/*
* Adding the new buffer_head would make it cross the
* allowed limit for which we have journal credit
* reserved. So limit the new bh->b_size
*/
b_size = (EXT4_MAX_TRANS_DATA - nrblocks) <<
mpd->inode->i_blkbits;
/* we will do mpage_da_submit_io in the next loop */
}
}
/*
* First block in the extent
*/
if (mpd->b_size == 0) {
mpd->b_blocknr = logical;
mpd->b_size = b_size;
mpd->b_state = b_state & BH_FLAGS;
return;
}
next = mpd->b_blocknr + nrblocks;
/*
* Can we merge the block to our big extent?
*/
if (logical == next && (b_state & BH_FLAGS) == mpd->b_state) {
mpd->b_size += b_size;
return;
}
flush_it:
/*
* We couldn't merge the block to our extent, so we
* need to flush current extent and start new one
*/
mpage_da_map_and_submit(mpd);
return;
}
static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh)
{
return (buffer_delay(bh) || buffer_unwritten(bh)) && buffer_dirty(bh);
}
/*
* This is a special get_blocks_t callback which is used by
* ext4_da_write_begin(). It will either return mapped block or
* reserve space for a single block.
*
* For delayed buffer_head we have BH_Mapped, BH_New, BH_Delay set.
* We also have b_blocknr = -1 and b_bdev initialized properly
*
* For unwritten buffer_head we have BH_Mapped, BH_New, BH_Unwritten set.
* We also have b_blocknr = physicalblock mapping unwritten extent and b_bdev
* initialized properly.
*/
static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
struct buffer_head *bh, int create)
{
struct ext4_map_blocks map;
int ret = 0;
sector_t invalid_block = ~((sector_t) 0xffff);
if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
invalid_block = ~0;
BUG_ON(create == 0);
BUG_ON(bh->b_size != inode->i_sb->s_blocksize);
map.m_lblk = iblock;
map.m_len = 1;
/*
* first, we need to know whether the block is allocated already
* preallocated blocks are unmapped but should treated
* the same as allocated blocks.
*/
ret = ext4_map_blocks(NULL, inode, &map, 0);
if (ret < 0)
return ret;
if (ret == 0) {
if (buffer_delay(bh))
return 0; /* Not sure this could or should happen */
/*
* XXX: __block_write_begin() unmaps passed block, is it OK?
*/
ret = ext4_da_reserve_space(inode, iblock);
if (ret)
/* not enough space to reserve */
return ret;
map_bh(bh, inode->i_sb, invalid_block);
set_buffer_new(bh);
set_buffer_delay(bh);
return 0;
}
map_bh(bh, inode->i_sb, map.m_pblk);
bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
if (buffer_unwritten(bh)) {
/* A delayed write to unwritten bh should be marked
* new and mapped. Mapped ensures that we don't do
* get_block multiple times when we write to the same
* offset and new ensures that we do proper zero out
* for partial write.
*/
set_buffer_new(bh);
set_buffer_mapped(bh);
}
return 0;
}
/*
* This function is used as a standard get_block_t calback function
* when there is no desire to allocate any blocks. It is used as a
* callback function for block_write_begin() and block_write_full_page().
* These functions should only try to map a single block at a time.
*
* Since this function doesn't do block allocations even if the caller
* requests it by passing in create=1, it is critically important that
* any caller checks to make sure that any buffer heads are returned
* by this function are either all already mapped or marked for
* delayed allocation before calling block_write_full_page(). Otherwise,
* b_blocknr could be left unitialized, and the page write functions will
* be taken by surprise.
*/
static int noalloc_get_block_write(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
BUG_ON(bh_result->b_size != inode->i_sb->s_blocksize);
return _ext4_get_block(inode, iblock, bh_result, 0);
}
static int bget_one(handle_t *handle, struct buffer_head *bh)
{
get_bh(bh);
return 0;
}
static int bput_one(handle_t *handle, struct buffer_head *bh)
{
put_bh(bh);
return 0;
}
static int __ext4_journalled_writepage(struct page *page,
unsigned int len)
{
struct address_space *mapping = page->mapping;
struct inode *inode = mapping->host;
struct buffer_head *page_bufs;
handle_t *handle = NULL;
int ret = 0;
int err;
ClearPageChecked(page);
page_bufs = page_buffers(page);
BUG_ON(!page_bufs);
walk_page_buffers(handle, page_bufs, 0, len, NULL, bget_one);
/* As soon as we unlock the page, it can go away, but we have
* references to buffers so we are safe */
unlock_page(page);
handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
goto out;
}
ret = walk_page_buffers(handle, page_bufs, 0, len, NULL,
do_journal_get_write_access);
err = walk_page_buffers(handle, page_bufs, 0, len, NULL,
write_end_fn);
if (ret == 0)
ret = err;
err = ext4_journal_stop(handle);
if (!ret)
ret = err;
walk_page_buffers(handle, page_bufs, 0, len, NULL, bput_one);
ext4_set_inode_state(inode, EXT4_STATE_JDATA);
out:
return ret;
}
static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode);
static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate);
/*
* Note that we don't need to start a transaction unless we're journaling data
* because we should have holes filled from ext4_page_mkwrite(). We even don't
* need to file the inode to the transaction's list in ordered mode because if
* we are writing back data added by write(), the inode is already there and if
* we are writing back data modified via mmap(), no one guarantees in which
* transaction the data will hit the disk. In case we are journaling data, we
* cannot start transaction directly because transaction start ranks above page
* lock so we have to do some magic.
*
* This function can get called via...
* - ext4_da_writepages after taking page lock (have journal handle)
* - journal_submit_inode_data_buffers (no journal handle)
* - shrink_page_list via pdflush (no journal handle)
* - grab_page_cache when doing write_begin (have journal handle)
*
* We don't do any block allocation in this function. If we have page with
* multiple blocks we need to write those buffer_heads that are mapped. This
* is important for mmaped based write. So if we do with blocksize 1K
* truncate(f, 1024);
* a = mmap(f, 0, 4096);
* a[0] = 'a';
* truncate(f, 4096);
* we have in the page first buffer_head mapped via page_mkwrite call back
* but other bufer_heads would be unmapped but dirty(dirty done via the
* do_wp_page). So writepage should write the first block. If we modify
* the mmap area beyond 1024 we will again get a page_fault and the
* page_mkwrite callback will do the block allocation and mark the
* buffer_heads mapped.
*
* We redirty the page if we have any buffer_heads that is either delay or
* unwritten in the page.
*
* We can get recursively called as show below.
*
* ext4_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() ->
* ext4_writepage()
*
* But since we don't do any block allocation we should not deadlock.
* Page also have the dirty flag cleared so we don't get recurive page_lock.
*/
static int ext4_writepage(struct page *page,
struct writeback_control *wbc)
{
int ret = 0, commit_write = 0;
loff_t size;
unsigned int len;
struct buffer_head *page_bufs = NULL;
struct inode *inode = page->mapping->host;
trace_ext4_writepage(page);
size = i_size_read(inode);
if (page->index == size >> PAGE_CACHE_SHIFT)
len = size & ~PAGE_CACHE_MASK;
else
len = PAGE_CACHE_SIZE;
/*
* If the page does not have buffers (for whatever reason),
* try to create them using __block_write_begin. If this
* fails, redirty the page and move on.
*/
if (!page_has_buffers(page)) {
if (__block_write_begin(page, 0, len,
noalloc_get_block_write)) {
redirty_page:
redirty_page_for_writepage(wbc, page);
unlock_page(page);
return 0;
}
commit_write = 1;
}
page_bufs = page_buffers(page);
if (walk_page_buffers(NULL, page_bufs, 0, len, NULL,
ext4_bh_delay_or_unwritten)) {
/*
* We don't want to do block allocation, so redirty
* the page and return. We may reach here when we do
* a journal commit via journal_submit_inode_data_buffers.
* We can also reach here via shrink_page_list
*/
goto redirty_page;
}
if (commit_write)
/* now mark the buffer_heads as dirty and uptodate */
block_commit_write(page, 0, len);
if (PageChecked(page) && ext4_should_journal_data(inode))
/*
* It's mmapped pagecache. Add buffers and journal it. There
* doesn't seem much point in redirtying the page here.
*/
return __ext4_journalled_writepage(page, len);
if (buffer_uninit(page_bufs)) {
ext4_set_bh_endio(page_bufs, inode);
ret = block_write_full_page_endio(page, noalloc_get_block_write,
wbc, ext4_end_io_buffer_write);
} else
ret = block_write_full_page(page, noalloc_get_block_write,
wbc);
return ret;
}
/*
* This is called via ext4_da_writepages() to
* calculate the total number of credits to reserve to fit
* a single extent allocation into a single transaction,
* ext4_da_writpeages() will loop calling this before
* the block allocation.
*/
static int ext4_da_writepages_trans_blocks(struct inode *inode)
{
int max_blocks = EXT4_I(inode)->i_reserved_data_blocks;
/*
* With non-extent format the journal credit needed to
* insert nrblocks contiguous block is dependent on
* number of contiguous block. So we will limit
* number of contiguous block to a sane value
*/
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) &&
(max_blocks > EXT4_MAX_TRANS_DATA))
max_blocks = EXT4_MAX_TRANS_DATA;
return ext4_chunk_trans_blocks(inode, max_blocks);
}
/*
* write_cache_pages_da - walk the list of dirty pages of the given
* address space and accumulate pages that need writing, and call
* mpage_da_map_and_submit to map a single contiguous memory region
* and then write them.
*/
static int write_cache_pages_da(struct address_space *mapping,
struct writeback_control *wbc,
struct mpage_da_data *mpd,
pgoff_t *done_index)
{
struct buffer_head *bh, *head;
struct inode *inode = mapping->host;
struct pagevec pvec;
unsigned int nr_pages;
sector_t logical;
pgoff_t index, end;
long nr_to_write = wbc->nr_to_write;
int i, tag, ret = 0;
memset(mpd, 0, sizeof(struct mpage_da_data));
mpd->wbc = wbc;
mpd->inode = inode;
pagevec_init(&pvec, 0);
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
if (wbc->sync_mode == WB_SYNC_ALL)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
*done_index = index;
while (index <= end) {
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
if (nr_pages == 0)
return 0;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
/*
* At this point, the page may be truncated or
* invalidated (changing page->mapping to NULL), or
* even swizzled back from swapper_space to tmpfs file
* mapping. However, page->index will not change
* because we have a reference on the page.
*/
if (page->index > end)
goto out;
*done_index = page->index + 1;
/*
* If we can't merge this page, and we have
* accumulated an contiguous region, write it
*/
if ((mpd->next_page != page->index) &&
(mpd->next_page != mpd->first_page)) {
mpage_da_map_and_submit(mpd);
goto ret_extent_tail;
}
lock_page(page);
/*
* If the page is no longer dirty, or its
* mapping no longer corresponds to inode we
* are writing (which means it has been
* truncated or invalidated), or the page is
* already under writeback and we are not
* doing a data integrity writeback, skip the page
*/
if (!PageDirty(page) ||
(PageWriteback(page) &&
(wbc->sync_mode == WB_SYNC_NONE)) ||
unlikely(page->mapping != mapping)) {
unlock_page(page);
continue;
}
wait_on_page_writeback(page);
BUG_ON(PageWriteback(page));
if (mpd->next_page != page->index)
mpd->first_page = page->index;
mpd->next_page = page->index + 1;
logical = (sector_t) page->index <<
(PAGE_CACHE_SHIFT - inode->i_blkbits);
if (!page_has_buffers(page)) {
mpage_add_bh_to_extent(mpd, logical,
PAGE_CACHE_SIZE,
(1 << BH_Dirty) | (1 << BH_Uptodate));
if (mpd->io_done)
goto ret_extent_tail;
} else {
/*
* Page with regular buffer heads,
* just add all dirty ones
*/
head = page_buffers(page);
bh = head;
do {
BUG_ON(buffer_locked(bh));
/*
* We need to try to allocate
* unmapped blocks in the same page.
* Otherwise we won't make progress
* with the page in ext4_writepage
*/
if (ext4_bh_delay_or_unwritten(NULL, bh)) {
mpage_add_bh_to_extent(mpd, logical,
bh->b_size,
bh->b_state);
if (mpd->io_done)
goto ret_extent_tail;
} else if (buffer_dirty(bh) && (buffer_mapped(bh))) {
/*
* mapped dirty buffer. We need
* to update the b_state
* because we look at b_state
* in mpage_da_map_blocks. We
* don't update b_size because