*
* 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)
*
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
-#include "ext4_extents.h"
+#include "truncate.h"
#include <trace/events/ext4.h>
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
int err;
trace_ext4_evict_inode(inode);
+
+ ext4_ioend_wait(inode);
+
if (inode->i_nlink) {
+ /*
+ * When journalling data dirty buffers are tracked only in the
+ * journal. So although mm thinks everything is clean and
+ * ready for reaping the inode might still have some pages to
+ * write in the running transaction or waiting to be
+ * checkpointed. Thus calling jbd2_journal_invalidatepage()
+ * (via truncate_inode_pages()) to discard these buffers can
+ * cause data loss. Also even if we did not discard these
+ * buffers, we would have no way to find them after the inode
+ * is reaped and thus user could see stale data if he tries to
+ * read them before the transaction is checkpointed. So be
+ * careful and force everything to disk here... We use
+ * ei->i_datasync_tid to store the newest transaction
+ * containing inode's data.
+ *
+ * Note that directories do not have this problem because they
+ * don't use page cache.
+ */
+ if (ext4_should_journal_data(inode) &&
+ (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) {
+ journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
+ tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;
+
+ jbd2_log_start_commit(journal, commit_tid);
+ jbd2_log_wait_commit(journal, commit_tid);
+ filemap_write_and_wait(&inode->i_data);
+ }
truncate_inode_pages(&inode->i_data, 0);
goto no_delete;
}
if (is_bad_inode(inode))
goto no_delete;
- handle = ext4_journal_start(inode, blocks_for_truncate(inode)+3);
+ handle = ext4_journal_start(inode, ext4_blocks_for_truncate(inode)+3);
if (IS_ERR(handle)) {
ext4_std_error(inode->i_sb, PTR_ERR(handle));
/*
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)
{
}
#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
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);
+ return ext4_ind_calc_metadata_amount(inode, lblock);
}
/*
struct ext4_inode_info *ei = EXT4_I(inode);
spin_lock(&ei->i_block_reservation_lock);
- trace_ext4_da_update_reserve_space(inode, used);
+ trace_ext4_da_update_reserve_space(inode, used, quota_claim);
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",
/* 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,
+ percpu_counter_sub(&sbi->s_dirtyclusters_counter,
used + ei->i_allocated_meta_blocks);
ei->i_allocated_meta_blocks = 0;
* only when we have written all of the delayed
* allocation blocks.
*/
- percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+ percpu_counter_sub(&sbi->s_dirtyclusters_counter,
ei->i_reserved_meta_blocks);
ei->i_reserved_meta_blocks = 0;
ei->i_da_metadata_calc_len = 0;
/* Update quota subsystem for data blocks */
if (quota_claim)
- dquot_claim_block(inode, used);
+ dquot_claim_block(inode, EXT4_C2B(sbi, 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);
+ dquot_release_reservation_block(inode, EXT4_C2B(sbi, used));
}
/*
return num;
}
+/*
+ * Sets the BH_Da_Mapped bit on the buffer heads corresponding to the given map.
+ */
+static void set_buffers_da_mapped(struct inode *inode,
+ struct ext4_map_blocks *map)
+{
+ struct address_space *mapping = inode->i_mapping;
+ struct pagevec pvec;
+ int i, nr_pages;
+ pgoff_t index, end;
+
+ index = map->m_lblk >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ end = (map->m_lblk + map->m_len - 1) >>
+ (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+ pagevec_init(&pvec, 0);
+ while (index <= end) {
+ nr_pages = pagevec_lookup(&pvec, mapping, index,
+ min(end - index + 1,
+ (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;
+
+ if (unlikely(page->mapping != mapping) ||
+ !PageDirty(page))
+ break;
+
+ if (page_has_buffers(page)) {
+ bh = head = page_buffers(page);
+ do {
+ set_buffer_da_mapped(bh);
+ bh = bh->b_this_page;
+ } while (bh != head);
+ }
+ index++;
+ }
+ pagevec_release(&pvec);
+ }
+}
+
/*
* The ext4_map_blocks() function tries to look up the requested blocks,
* and returns if the blocks are already mapped.
(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE))
ext4_da_update_reserve_space(inode, retval, 1);
}
- if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
+ /* If we have successfully mapped the delayed allocated blocks,
+ * set the BH_Da_Mapped bit on them. Its important to do this
+ * under the protection of i_data_sem.
+ */
+ if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
+ set_buffers_da_mapped(inode, map);
+ }
+
up_write((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
int ret = check_block_validity(inode, map);
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,
from = pos & (PAGE_CACHE_SIZE - 1);
to = from + len;
+ BUG_ON(!ext4_handle_valid(handle));
+
if (copied < len) {
if (!PageUptodate(page))
copied = 0;
if (new_i_size > inode->i_size)
i_size_write(inode, pos+copied);
ext4_set_inode_state(inode, EXT4_STATE_JDATA);
+ EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
if (new_i_size > EXT4_I(inode)->i_disksize) {
ext4_update_i_disksize(inode, new_i_size);
ret2 = ext4_mark_inode_dirty(handle, inode);
}
/*
- * Reserve a single block located at lblock
+ * Reserve a single cluster 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;
+ unsigned int md_needed;
int ret;
/*
*/
repeat:
spin_lock(&ei->i_block_reservation_lock);
- md_needed = ext4_calc_metadata_amount(inode, lblock);
+ md_needed = EXT4_NUM_B2C(sbi,
+ ext4_calc_metadata_amount(inode, lblock));
trace_ext4_da_reserve_space(inode, md_needed);
spin_unlock(&ei->i_block_reservation_lock);
* 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);
+ ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 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_claim_free_clusters(sbi, md_needed + 1, 0)) {
+ dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
yield();
goto repeat;
* We can release all of the reserved metadata blocks
* only when we have written all of the delayed
* allocation blocks.
+ * Note that in case of bigalloc, i_reserved_meta_blocks,
+ * i_reserved_data_blocks, etc. refer to number of clusters.
*/
- percpu_counter_sub(&sbi->s_dirtyblocks_counter,
+ percpu_counter_sub(&sbi->s_dirtyclusters_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);
+ percpu_counter_sub(&sbi->s_dirtyclusters_counter, to_free);
spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
- dquot_release_reservation_block(inode, to_free);
+ dquot_release_reservation_block(inode, EXT4_C2B(sbi, to_free));
}
static void ext4_da_page_release_reservation(struct page *page,
int to_release = 0;
struct buffer_head *head, *bh;
unsigned int curr_off = 0;
+ struct inode *inode = page->mapping->host;
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ int num_clusters;
head = page_buffers(page);
bh = head;
if ((offset <= curr_off) && (buffer_delay(bh))) {
to_release++;
clear_buffer_delay(bh);
+ clear_buffer_da_mapped(bh);
}
curr_off = next_off;
} while ((bh = bh->b_this_page) != head);
- ext4_da_release_space(page->mapping->host, to_release);
+
+ /* If we have released all the blocks belonging to a cluster, then we
+ * need to release the reserved space for that cluster. */
+ num_clusters = EXT4_NUM_B2C(sbi, to_release);
+ while (num_clusters > 0) {
+ ext4_fsblk_t lblk;
+ lblk = (page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits)) +
+ ((num_clusters - 1) << sbi->s_cluster_bits);
+ if (sbi->s_cluster_ratio == 1 ||
+ !ext4_find_delalloc_cluster(inode, lblk, 1))
+ ext4_da_release_space(inode, 1);
+
+ num_clusters--;
+ }
}
/*
clear_buffer_delay(bh);
bh->b_blocknr = pblock;
}
+ if (buffer_da_mapped(bh))
+ clear_buffer_da_mapped(bh);
if (buffer_unwritten(bh) ||
buffer_mapped(bh))
BUG_ON(bh->b_blocknr != pblock);
else if (test_opt(inode->i_sb, MBLK_IO_SUBMIT))
err = ext4_bio_write_page(&io_submit, page,
len, mpd->wbc);
- else
+ else if (buffer_uninit(page_bufs)) {
+ ext4_set_bh_endio(page_bufs, inode);
+ err = block_write_full_page_endio(page,
+ noalloc_get_block_write,
+ mpd->wbc, ext4_end_io_buffer_write);
+ } else
err = block_write_full_page(page,
noalloc_get_block_write, mpd->wbc);
{
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));
+ EXT4_C2B(EXT4_SB(inode->i_sb),
+ ext4_count_free_clusters(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));
+ (long long) EXT4_C2B(EXT4_SB(inode->i_sb),
+ percpu_counter_sum(&sbi->s_freeclusters_counter)));
printk(KERN_CRIT "dirty_blocks=%lld\n",
- (long long) percpu_counter_sum(&sbi->s_dirtyblocks_counter));
+ (long long) EXT4_C2B(EXT4_SB(inode->i_sb),
+ percpu_counter_sum(&sbi->s_dirtyclusters_counter)));
printk(KERN_CRIT "Block reservation details\n");
printk(KERN_CRIT "i_reserved_data_blocks=%u\n",
EXT4_I(inode)->i_reserved_data_blocks);
if (err == -EAGAIN)
goto submit_io;
- if (err == -ENOSPC &&
- ext4_count_free_blocks(sb)) {
+ if (err == -ENOSPC && ext4_count_free_clusters(sb)) {
mpd->retval = err;
goto submit_io;
}
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;
+ if (ext4_should_order_data(mpd->inode)) {
+ err = ext4_jbd2_file_inode(handle, mpd->inode);
+ if (err)
+ /* Only if the journal is aborted */
+ return;
+ }
}
/*
return (buffer_delay(bh) || buffer_unwritten(bh)) && buffer_dirty(bh);
}
+/*
+ * This function is grabs code from the very beginning of
+ * ext4_map_blocks, but assumes that the caller is from delayed write
+ * time. This function looks up the requested blocks and sets the
+ * buffer delay bit under the protection of i_data_sem.
+ */
+static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
+ struct ext4_map_blocks *map,
+ struct buffer_head *bh)
+{
+ int retval;
+ sector_t invalid_block = ~((sector_t) 0xffff);
+
+ if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
+ invalid_block = ~0;
+
+ map->m_flags = 0;
+ ext_debug("ext4_da_map_blocks(): inode %lu, max_blocks %u,"
+ "logical block %lu\n", inode->i_ino, 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(NULL, inode, map, 0);
+ else
+ retval = ext4_ind_map_blocks(NULL, inode, map, 0);
+
+ if (retval == 0) {
+ /*
+ * XXX: __block_prepare_write() unmaps passed block,
+ * is it OK?
+ */
+ /* If the block was allocated from previously allocated cluster,
+ * then we dont need to reserve it again. */
+ if (!(map->m_flags & EXT4_MAP_FROM_CLUSTER)) {
+ retval = ext4_da_reserve_space(inode, iblock);
+ if (retval)
+ /* not enough space to reserve */
+ goto out_unlock;
+ }
+
+ /* Clear EXT4_MAP_FROM_CLUSTER flag since its purpose is served
+ * and it should not appear on the bh->b_state.
+ */
+ map->m_flags &= ~EXT4_MAP_FROM_CLUSTER;
+
+ map_bh(bh, inode->i_sb, invalid_block);
+ set_buffer_new(bh);
+ set_buffer_delay(bh);
+ }
+
+out_unlock:
+ up_read((&EXT4_I(inode)->i_data_sem));
+
+ return retval;
+}
+
/*
* This is a special get_blocks_t callback which is used by
* ext4_da_write_begin(). It will either return mapped block or
{
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);
* preallocated blocks are unmapped but should treated
* the same as allocated blocks.
*/
- ret = ext4_map_blocks(NULL, inode, &map, 0);
- if (ret < 0)
+ ret = ext4_da_map_blocks(inode, iblock, &map, bh);
+ 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;
goto out;
}
+ BUG_ON(!ext4_handle_valid(handle));
+
ret = walk_page_buffers(handle, page_bufs, 0, len, NULL,
do_journal_get_write_access);
write_end_fn);
if (ret == 0)
ret = err;
+ EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
err = ext4_journal_stop(handle);
if (!ret)
ret = err;
index = wbc->range_start >> PAGE_CACHE_SHIFT;
end = wbc->range_end >> PAGE_CACHE_SHIFT;
- if (wbc->sync_mode == WB_SYNC_ALL)
+ if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
}
retry:
- if (wbc->sync_mode == WB_SYNC_ALL)
+ if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, index, end);
while (!ret && wbc->nr_to_write > 0) {
* Delalloc need an accurate free block accounting. So switch
* to non delalloc when we are near to error range.
*/
- free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter);
- dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyblocks_counter);
+ free_blocks = EXT4_C2B(sbi,
+ percpu_counter_read_positive(&sbi->s_freeclusters_counter));
+ dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyclusters_counter);
if (2 * free_blocks < 3 * dirty_blocks ||
- free_blocks < (dirty_blocks + EXT4_FREEBLOCKS_WATERMARK)) {
+ free_blocks < (dirty_blocks + EXT4_FREECLUSTERS_WATERMARK)) {
/*
* free block count is less than 150% of dirty blocks
* or free blocks is less than watermark
pgoff_t index;
struct inode *inode = mapping->host;
handle_t *handle;
+ loff_t page_len;
index = pos >> PAGE_CACHE_SHIFT;
*/
if (pos + len > inode->i_size)
ext4_truncate_failed_write(inode);
+ } else {
+ page_len = pos & (PAGE_CACHE_SIZE - 1);
+ if (page_len > 0) {
+ ret = ext4_discard_partial_page_buffers_no_lock(handle,
+ inode, page, pos - page_len, page_len,
+ EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED);
+ }
}
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
loff_t new_i_size;
unsigned long start, end;
int write_mode = (int)(unsigned long)fsdata;
+ loff_t page_len;
if (write_mode == FALL_BACK_TO_NONDELALLOC) {
if (ext4_should_order_data(inode)) {
}
ret2 = generic_write_end(file, mapping, pos, len, copied,
page, fsdata);
+
+ page_len = PAGE_CACHE_SIZE -
+ ((pos + copied - 1) & (PAGE_CACHE_SIZE - 1));
+
+ if (page_len > 0) {
+ ret = ext4_discard_partial_page_buffers_no_lock(handle,
+ inode, page, pos + copied - 1, page_len,
+ EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED);
+ }
+
copied = ret2;
if (ret2 < 0)
ret = ret2;
return try_to_free_buffers(page);
}
-/*
- * O_DIRECT for ext3 (or indirect map) based files
- *
- * If the O_DIRECT write will extend the file then add this inode to the
- * orphan list. So recovery will truncate it back to the original size
- * if the machine crashes during the write.
- *
- * If the O_DIRECT write is intantiating holes inside i_size and the machine
- * crashes then stale disk data _may_ be exposed inside the file. But current
- * VFS code falls back into buffered path in that case so we are safe.
- */
-static ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset,
- unsigned long nr_segs)
-{
- struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_mapping->host;
- struct ext4_inode_info *ei = EXT4_I(inode);
- handle_t *handle;
- ssize_t ret;
- int orphan = 0;
- size_t count = iov_length(iov, nr_segs);
- int retries = 0;
-
- if (rw == WRITE) {
- loff_t final_size = offset + count;
-
- if (final_size > inode->i_size) {
- /* Credits for sb + inode write */
- handle = ext4_journal_start(inode, 2);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out;
- }
- ret = ext4_orphan_add(handle, inode);
- if (ret) {
- ext4_journal_stop(handle);
- goto out;
- }
- orphan = 1;
- ei->i_disksize = inode->i_size;
- ext4_journal_stop(handle);
- }
- }
-
-retry:
- if (rw == READ && ext4_should_dioread_nolock(inode))
- ret = __blockdev_direct_IO(rw, iocb, inode,
- inode->i_sb->s_bdev, iov,
- offset, nr_segs,
- ext4_get_block, NULL, NULL, 0);
- else {
- ret = blockdev_direct_IO(rw, iocb, inode,
- inode->i_sb->s_bdev, iov,
- offset, nr_segs,
- ext4_get_block, NULL);
-
- if (unlikely((rw & WRITE) && ret < 0)) {
- loff_t isize = i_size_read(inode);
- loff_t end = offset + iov_length(iov, nr_segs);
-
- if (end > isize)
- ext4_truncate_failed_write(inode);
- }
- }
- if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
- goto retry;
-
- if (orphan) {
- int err;
-
- /* Credits for sb + inode write */
- handle = ext4_journal_start(inode, 2);
- if (IS_ERR(handle)) {
- /* This is really bad luck. We've written the data
- * but cannot extend i_size. Bail out and pretend
- * the write failed... */
- ret = PTR_ERR(handle);
- if (inode->i_nlink)
- ext4_orphan_del(NULL, inode);
-
- goto out;
- }
- if (inode->i_nlink)
- ext4_orphan_del(handle, inode);
- if (ret > 0) {
- loff_t end = offset + ret;
- if (end > inode->i_size) {
- ei->i_disksize = end;
- i_size_write(inode, end);
- /*
- * We're going to return a positive `ret'
- * here due to non-zero-length I/O, so there's
- * no way of reporting error returns from
- * ext4_mark_inode_dirty() to userspace. So
- * ignore it.
- */
- ext4_mark_inode_dirty(handle, inode);
- }
- }
- err = ext4_journal_stop(handle);
- if (ret == 0)
- ret = err;
- }
-out:
- return ret;
-}
-
/*
* ext4_get_block used when preparing for a DIO write or buffer write.
* We allocate an uinitialized extent if blocks haven't been allocated.
ssize_t size, void *private, int ret,
bool is_async)
{
+ struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
ext4_io_end_t *io_end = iocb->private;
struct workqueue_struct *wq;
unsigned long flags;
out:
if (is_async)
aio_complete(iocb, ret, 0);
+ inode_dio_done(inode);
return;
}
/* queue the work to convert unwritten extents to written */
queue_work(wq, &io_end->work);
iocb->private = NULL;
+
+ /* XXX: probably should move into the real I/O completion handler */
+ inode_dio_done(inode);
}
static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
goto out;
}
- io_end->flag = EXT4_IO_END_UNWRITTEN;
+ /*
+ * It may be over-defensive here to check EXT4_IO_END_UNWRITTEN now,
+ * but being more careful is always safe for the future change.
+ */
inode = io_end->inode;
+ if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+ io_end->flag |= EXT4_IO_END_UNWRITTEN;
+ atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+ }
/* Add the io_end to per-inode completed io list*/
spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
EXT4_I(inode)->cur_aio_dio = iocb->private;
}
- ret = blockdev_direct_IO(rw, iocb, inode,
+ ret = __blockdev_direct_IO(rw, iocb, inode,
inode->i_sb->s_bdev, iov,
offset, nr_segs,
ext4_get_block_write,
- ext4_end_io_dio);
+ ext4_end_io_dio,
+ NULL,
+ DIO_LOCKING | DIO_SKIP_HOLES);
if (iocb->private)
EXT4_I(inode)->cur_aio_dio = NULL;
/*
struct inode *inode = file->f_mapping->host;
ssize_t ret;
+ /*
+ * If we are doing data journalling we don't support O_DIRECT
+ */
+ if (ext4_should_journal_data(inode))
+ return 0;
+
trace_ext4_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
ret = ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs);
.bmap = ext4_bmap,
.invalidatepage = ext4_invalidatepage,
.releasepage = ext4_releasepage,
+ .direct_IO = ext4_direct_IO,
+ .is_partially_uptodate = block_is_partially_uptodate,
+ .error_remove_page = generic_error_remove_page,
+};
+
+static const struct address_space_operations ext4_da_aops = {
+ .readpage = ext4_readpage,
+ .readpages = ext4_readpages,
+ .writepage = ext4_writepage,
+ .writepages = ext4_da_writepages,
+ .write_begin = ext4_da_write_begin,
+ .write_end = ext4_da_write_end,
+ .bmap = ext4_bmap,
+ .invalidatepage = ext4_da_invalidatepage,
+ .releasepage = ext4_releasepage,
+ .direct_IO = ext4_direct_IO,
+ .migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
};
-static const struct address_space_operations ext4_da_aops = {
- .readpage = ext4_readpage,
- .readpages = ext4_readpages,
- .writepage = ext4_writepage,
- .writepages = ext4_da_writepages,
- .write_begin = ext4_da_write_begin,
- .write_end = ext4_da_write_end,
- .bmap = ext4_bmap,
- .invalidatepage = ext4_da_invalidatepage,
- .releasepage = ext4_releasepage,
- .direct_IO = ext4_direct_IO,
- .migratepage = buffer_migrate_page,
- .is_partially_uptodate = block_is_partially_uptodate,
- .error_remove_page = generic_error_remove_page,
-};
+void ext4_set_aops(struct inode *inode)
+{
+ if (ext4_should_order_data(inode) &&
+ test_opt(inode->i_sb, DELALLOC))
+ inode->i_mapping->a_ops = &ext4_da_aops;
+ else if (ext4_should_order_data(inode))
+ inode->i_mapping->a_ops = &ext4_ordered_aops;
+ else if (ext4_should_writeback_data(inode) &&
+ test_opt(inode->i_sb, DELALLOC))
+ inode->i_mapping->a_ops = &ext4_da_aops;
+ else if (ext4_should_writeback_data(inode))
+ inode->i_mapping->a_ops = &ext4_writeback_aops;
+ else
+ inode->i_mapping->a_ops = &ext4_journalled_aops;
+}
+
+
+/*
+ * ext4_discard_partial_page_buffers()
+ * Wrapper function for ext4_discard_partial_page_buffers_no_lock.
+ * This function finds and locks the page containing the offset
+ * "from" and passes it to ext4_discard_partial_page_buffers_no_lock.
+ * Calling functions that already have the page locked should call
+ * ext4_discard_partial_page_buffers_no_lock directly.
+ */
+int ext4_discard_partial_page_buffers(handle_t *handle,
+ struct address_space *mapping, loff_t from,
+ loff_t length, int flags)
+{
+ struct inode *inode = mapping->host;
+ struct page *page;
+ int err = 0;
+
+ page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT,
+ mapping_gfp_mask(mapping) & ~__GFP_FS);
+ if (!page)
+ return -EINVAL;
+
+ err = ext4_discard_partial_page_buffers_no_lock(handle, inode, page,
+ from, length, flags);
+
+ unlock_page(page);
+ page_cache_release(page);
+ return err;
+}
+
+/*
+ * ext4_discard_partial_page_buffers_no_lock()
+ * Zeros a page range of length 'length' starting from offset 'from'.
+ * Buffer heads that correspond to the block aligned regions of the
+ * zeroed range will be unmapped. Unblock aligned regions
+ * will have the corresponding buffer head mapped if needed so that
+ * that region of the page can be updated with the partial zero out.
+ *
+ * This function assumes that the page has already been locked. The
+ * The range to be discarded must be contained with in the given page.
+ * If the specified range exceeds the end of the page it will be shortened
+ * to the end of the page that corresponds to 'from'. This function is
+ * appropriate for updating a page and it buffer heads to be unmapped and
+ * zeroed for blocks that have been either released, or are going to be
+ * released.
+ *
+ * handle: The journal handle
+ * inode: The files inode
+ * page: A locked page that contains the offset "from"
+ * from: The starting byte offset (from the begining of the file)
+ * to begin discarding
+ * len: The length of bytes to discard
+ * flags: Optional flags that may be used:
+ *
+ * EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED
+ * Only zero the regions of the page whose buffer heads
+ * have already been unmapped. This flag is appropriate
+ * for updateing the contents of a page whose blocks may
+ * have already been released, and we only want to zero
+ * out the regions that correspond to those released blocks.
+ *
+ * Returns zero on sucess or negative on failure.
+ */
+int ext4_discard_partial_page_buffers_no_lock(handle_t *handle,
+ struct inode *inode, struct page *page, loff_t from,
+ loff_t length, int flags)
+{
+ ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT;
+ unsigned int offset = from & (PAGE_CACHE_SIZE-1);
+ unsigned int blocksize, max, pos;
+ unsigned int end_of_block, range_to_discard;
+ ext4_lblk_t iblock;
+ struct buffer_head *bh;
+ int err = 0;
+
+ blocksize = inode->i_sb->s_blocksize;
+ max = PAGE_CACHE_SIZE - offset;
+
+ if (index != page->index)
+ return -EINVAL;
+
+ /*
+ * correct length if it does not fall between
+ * 'from' and the end of the page
+ */
+ if (length > max || length < 0)
+ length = max;
+
+ iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
+
+ if (!page_has_buffers(page)) {
+ /*
+ * If the range to be discarded covers a partial block
+ * we need to get the page buffers. This is because
+ * partial blocks cannot be released and the page needs
+ * to be updated with the contents of the block before
+ * we write the zeros on top of it.
+ */
+ if (!(from & (blocksize - 1)) ||
+ !((from + length) & (blocksize - 1))) {
+ create_empty_buffers(page, blocksize, 0);
+ } else {
+ /*
+ * If there are no partial blocks,
+ * there is nothing to update,
+ * so we can return now
+ */
+ return 0;
+ }
+ }
+
+ /* Find the buffer that contains "offset" */
+ bh = page_buffers(page);
+ pos = blocksize;
+ while (offset >= pos) {
+ bh = bh->b_this_page;
+ iblock++;
+ pos += blocksize;
+ }
+
+ pos = offset;
+ while (pos < offset + length) {
+ err = 0;
+
+ /* The length of space left to zero and unmap */
+ range_to_discard = offset + length - pos;
+
+ /* The length of space until the end of the block */
+ end_of_block = blocksize - (pos & (blocksize-1));
+
+ /*
+ * Do not unmap or zero past end of block
+ * for this buffer head
+ */
+ if (range_to_discard > end_of_block)
+ range_to_discard = end_of_block;
+
+
+ /*
+ * Skip this buffer head if we are only zeroing unampped
+ * regions of the page
+ */
+ if (flags & EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED &&
+ buffer_mapped(bh))
+ goto next;
+
+ /* If the range is block aligned, unmap */
+ if (range_to_discard == blocksize) {
+ clear_buffer_dirty(bh);
+ bh->b_bdev = NULL;
+ clear_buffer_mapped(bh);
+ clear_buffer_req(bh);
+ clear_buffer_new(bh);
+ clear_buffer_delay(bh);
+ clear_buffer_unwritten(bh);
+ clear_buffer_uptodate(bh);
+ zero_user(page, pos, range_to_discard);
+ BUFFER_TRACE(bh, "Buffer discarded");
+ goto next;
+ }
+
+ /*
+ * If this block is not completely contained in the range
+ * to be discarded, then it is not going to be released. Because
+ * we need to keep this block, we need to make sure this part
+ * of the page is uptodate before we modify it by writeing
+ * partial zeros on it.
+ */
+ if (!buffer_mapped(bh)) {
+ /*
+ * Buffer head must be mapped before we can read
+ * from the block
+ */
+ BUFFER_TRACE(bh, "unmapped");
+ ext4_get_block(inode, iblock, bh, 0);
+ /* unmapped? It's a hole - nothing to do */
+ if (!buffer_mapped(bh)) {
+ BUFFER_TRACE(bh, "still unmapped");
+ goto next;
+ }
+ }
+
+ /* Ok, it's mapped. Make sure it's up-to-date */
+ if (PageUptodate(page))
+ set_buffer_uptodate(bh);
+
+ if (!buffer_uptodate(bh)) {
+ err = -EIO;
+ ll_rw_block(READ, 1, &bh);
+ wait_on_buffer(bh);
+ /* Uhhuh. Read error. Complain and punt.*/
+ if (!buffer_uptodate(bh))
+ goto next;
+ }
-void ext4_set_aops(struct inode *inode)
-{
- if (ext4_should_order_data(inode) &&
- test_opt(inode->i_sb, DELALLOC))
- inode->i_mapping->a_ops = &ext4_da_aops;
- else if (ext4_should_order_data(inode))
- inode->i_mapping->a_ops = &ext4_ordered_aops;
- else if (ext4_should_writeback_data(inode) &&
- test_opt(inode->i_sb, DELALLOC))
- inode->i_mapping->a_ops = &ext4_da_aops;
- else if (ext4_should_writeback_data(inode))
- inode->i_mapping->a_ops = &ext4_writeback_aops;
- else
- inode->i_mapping->a_ops = &ext4_journalled_aops;
+ if (ext4_should_journal_data(inode)) {
+ BUFFER_TRACE(bh, "get write access");
+ err = ext4_journal_get_write_access(handle, bh);
+ if (err)
+ goto next;
+ }
+
+ zero_user(page, pos, range_to_discard);
+
+ err = 0;
+ if (ext4_should_journal_data(inode)) {
+ err = ext4_handle_dirty_metadata(handle, inode, bh);
+ } else
+ mark_buffer_dirty(bh);
+
+ BUFFER_TRACE(bh, "Partial buffer zeroed");
+next:
+ bh = bh->b_this_page;
+ iblock++;
+ pos += range_to_discard;
+ }
+
+ return err;
}
/*
err = 0;
if (ext4_should_journal_data(inode)) {
err = ext4_handle_dirty_metadata(handle, inode, bh);
- } else {
- if (ext4_should_order_data(inode) && EXT4_I(inode)->jinode)
- err = ext4_jbd2_file_inode(handle, inode);
+ } else
mark_buffer_dirty(bh);
- }
unlock:
unlock_page(page);
return err;
}
-/*
- * 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;
-}
-
-/**
- * ext4_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 ext4_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 ext4_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 ext4_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].
- * (no partially truncated stuff there). */
-
-static Indirect *ext4_find_shared(struct inode *inode, int depth,
- ext4_lblk_t offsets[4], Indirect chain[4],
- __le32 *top)
-{
- Indirect *partial, *p;
- int k, err;
-
- *top = 0;
- /* Make k index the deepest non-null offset + 1 */
- for (k = depth; k > 1 && !offsets[k-1]; k--)
- ;
- partial = ext4_get_branch(inode, k, offsets, chain, &err);
- /* Writer: pointers */
- 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.
- */
- if (!partial->key && *partial->p)
- /* Writer: end */
- 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;
- /* Nope, don't do this in ext4. Must leave the tree intact */
-#if 0
- *p->p = 0;
-#endif
- }
- /* Writer: end */
-
- while (partial > p) {
- brelse(partial->bh);
- partial--;
- }
-no_top:
- return partial;
-}
-
-/*
- * Zero a number of block pointers in either an inode or an indirect block.
- * If we restart the transaction we must again get write access to the
- * indirect block for further modification.
- *
- * We release `count' blocks on disk, but (last - first) may be greater
- * than `count' because there can be holes in there.
- *
- * Return 0 on success, 1 on invalid block range
- * and < 0 on fatal error.
- */
-static int ext4_clear_blocks(handle_t *handle, struct inode *inode,
- struct buffer_head *bh,
- ext4_fsblk_t block_to_free,
- unsigned long count, __le32 *first,
- __le32 *last)
-{
- __le32 *p;
- int flags = EXT4_FREE_BLOCKS_FORGET | EXT4_FREE_BLOCKS_VALIDATED;
- int err;
-
- if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
- flags |= EXT4_FREE_BLOCKS_METADATA;
-
- if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), block_to_free,
- count)) {
- EXT4_ERROR_INODE(inode, "attempt to clear invalid "
- "blocks %llu len %lu",
- (unsigned long long) block_to_free, count);
- return 1;
- }
-
- if (try_to_extend_transaction(handle, inode)) {
- if (bh) {
- BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
- err = ext4_handle_dirty_metadata(handle, inode, bh);
- if (unlikely(err))
- goto out_err;
- }
- err = ext4_mark_inode_dirty(handle, inode);
- if (unlikely(err))
- goto out_err;
- err = ext4_truncate_restart_trans(handle, inode,
- blocks_for_truncate(inode));
- if (unlikely(err))
- goto out_err;
- if (bh) {
- BUFFER_TRACE(bh, "retaking write access");
- err = ext4_journal_get_write_access(handle, bh);
- if (unlikely(err))
- goto out_err;
- }
- }
-
- for (p = first; p < last; p++)
- *p = 0;
-
- ext4_free_blocks(handle, inode, NULL, block_to_free, count, flags);
- return 0;
-out_err:
- ext4_std_error(inode->i_sb, err);
- return err;
-}
-
-/**
- * ext4_free_data - free a list of data blocks
- * @handle: handle for this transaction
- * @inode: inode we are dealing with
- * @this_bh: indirect buffer_head which contains *@first and *@last
- * @first: array of block numbers
- * @last: 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.
- *
- * We accumulate contiguous runs of blocks to free. Conveniently, if these
- * blocks are contiguous then releasing them at one time will only affect one
- * or two bitmap blocks (+ group descriptor(s) and superblock) and we won't
- * actually use a lot of journal space.
- *
- * @this_bh will be %NULL if @first and @last point into the inode's direct
- * block pointers.
- */
-static void ext4_free_data(handle_t *handle, struct inode *inode,
- struct buffer_head *this_bh,
- __le32 *first, __le32 *last)
-{
- ext4_fsblk_t block_to_free = 0; /* Starting block # of a run */
- unsigned long count = 0; /* Number of blocks in the run */
- __le32 *block_to_free_p = NULL; /* Pointer into inode/ind
- corresponding to
- block_to_free */
- ext4_fsblk_t nr; /* Current block # */
- __le32 *p; /* Pointer into inode/ind
- for current block */
- int err = 0;
-
- if (this_bh) { /* For indirect block */
- BUFFER_TRACE(this_bh, "get_write_access");
- err = ext4_journal_get_write_access(handle, this_bh);
- /* Important: if we can't update the indirect pointers
- * to the blocks, we can't free them. */
- if (err)
- return;
- }
-
- for (p = first; p < last; p++) {
- nr = le32_to_cpu(*p);
- if (nr) {
- /* accumulate blocks to free if they're contiguous */
- if (count == 0) {
- block_to_free = nr;
- block_to_free_p = p;
- count = 1;
- } else if (nr == block_to_free + count) {
- count++;
- } else {
- err = ext4_clear_blocks(handle, inode, this_bh,
- block_to_free, count,
- block_to_free_p, p);
- if (err)
- break;
- block_to_free = nr;
- block_to_free_p = p;
- count = 1;
- }
- }
- }
-
- if (!err && count > 0)
- err = ext4_clear_blocks(handle, inode, this_bh, block_to_free,
- count, block_to_free_p, p);
- if (err < 0)
- /* fatal error */
- return;
-
- if (this_bh) {
- BUFFER_TRACE(this_bh, "call ext4_handle_dirty_metadata");
-
- /*
- * The buffer head should have an attached journal head at this
- * point. However, if the data is corrupted and an indirect
- * block pointed to itself, it would have been detached when
- * the block was cleared. Check for this instead of OOPSing.
- */
- if ((EXT4_JOURNAL(inode) == NULL) || bh2jh(this_bh))
- ext4_handle_dirty_metadata(handle, inode, this_bh);
- else
- EXT4_ERROR_INODE(inode,
- "circular indirect block detected at "
- "block %llu",
- (unsigned long long) this_bh->b_blocknr);
- }
-}
-
-/**
- * ext4_free_branches - free an array of branches
- * @handle: JBD handle for this transaction
- * @inode: inode we are dealing with
- * @parent_bh: the buffer_head which contains *@first and *@last
- * @first: array of block numbers
- * @last: 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 ext4_free_branches(handle_t *handle, struct inode *inode,
- struct buffer_head *parent_bh,
- __le32 *first, __le32 *last, int depth)
-{
- ext4_fsblk_t nr;
- __le32 *p;
-
- if (ext4_handle_is_aborted(handle))
- return;
-
- if (depth--) {
- struct buffer_head *bh;
- int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
- p = last;
- while (--p >= first) {
- nr = le32_to_cpu(*p);
- if (!nr)
- continue; /* A hole */
-
- if (!ext4_data_block_valid(EXT4_SB(inode->i_sb),
- nr, 1)) {
- EXT4_ERROR_INODE(inode,
- "invalid indirect mapped "
- "block %lu (level %d)",
- (unsigned long) nr, depth);
- break;
- }
-
- /* Go read the buffer for the next level down */
- bh = sb_bread(inode->i_sb, nr);
-
- /*
- * A read failure? Report error and clear slot
- * (should be rare).
- */
- if (!bh) {
- EXT4_ERROR_INODE_BLOCK(inode, nr,
- "Read failure");
- continue;
- }
-
- /* This zaps the entire block. Bottom up. */
- BUFFER_TRACE(bh, "free child branches");
- ext4_free_branches(handle, inode, bh,
- (__le32 *) bh->b_data,
- (__le32 *) bh->b_data + addr_per_block,
- depth);
- brelse(bh);
-
- /*
- * Everything below this this pointer has been
- * released. Now let this top-of-subtree go.
- *
- * We want the freeing of this indirect block to be
- * atomic in the journal with the updating of the
- * bitmap block which owns it. So make some room in
- * the journal.
- *
- * We zero the parent pointer *after* freeing its
- * pointee in the bitmaps, so if extend_transaction()
- * for some reason fails to put the bitmap changes and
- * the release into the same transaction, recovery
- * will merely complain about releasing a free block,
- * rather than leaking blocks.
- */
- if (ext4_handle_is_aborted(handle))
- return;
- if (try_to_extend_transaction(handle, inode)) {
- ext4_mark_inode_dirty(handle, inode);
- ext4_truncate_restart_trans(handle, inode,
- blocks_for_truncate(inode));
- }
-
- /*
- * The forget flag here is critical because if
- * we are journaling (and not doing data
- * journaling), we have to make sure a revoke
- * record is written to prevent the journal
- * replay from overwriting the (former)
- * indirect block if it gets reallocated as a
- * data block. This must happen in the same
- * transaction where the data blocks are
- * actually freed.
- */
- ext4_free_blocks(handle, inode, NULL, nr, 1,
- EXT4_FREE_BLOCKS_METADATA|
- EXT4_FREE_BLOCKS_FORGET);
-
- if (parent_bh) {
- /*
- * The block which we have just freed is
- * pointed to by an indirect block: journal it
- */
- BUFFER_TRACE(parent_bh, "get_write_access");
- if (!ext4_journal_get_write_access(handle,
- parent_bh)){
- *p = 0;
- BUFFER_TRACE(parent_bh,
- "call ext4_handle_dirty_metadata");
- ext4_handle_dirty_metadata(handle,
- inode,
- parent_bh);
- }
- }
- }
- } else {
- /* We have reached the bottom of the tree. */
- BUFFER_TRACE(parent_bh, "free data blocks");
- ext4_free_data(handle, inode, parent_bh, first, last);
- }
-}
-
int ext4_can_truncate(struct inode *inode)
{
if (S_ISREG(inode->i_mode))
return -ENOTSUPP;
}
+ if (EXT4_SB(inode->i_sb)->s_cluster_ratio > 1) {
+ /* TODO: Add support for bigalloc file systems */
+ return -ENOTSUPP;
+ }
+
return ext4_ext_punch_hole(file, offset, length);
}
*/
void ext4_truncate(struct inode *inode)
{
- handle_t *handle;
- struct ext4_inode_info *ei = EXT4_I(inode);
- __le32 *i_data = ei->i_data;
- int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
- struct address_space *mapping = inode->i_mapping;
- ext4_lblk_t offsets[4];
- Indirect chain[4];
- Indirect *partial;
- __le32 nr = 0;
- int n = 0;
- ext4_lblk_t last_block, max_block;
- unsigned blocksize = inode->i_sb->s_blocksize;
-
trace_ext4_truncate_enter(inode);
if (!ext4_can_truncate(inode))
if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
ext4_set_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE);
- if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
ext4_ext_truncate(inode);
- trace_ext4_truncate_exit(inode);
- return;
- }
-
- handle = start_transaction(inode);
- if (IS_ERR(handle))
- return; /* AKPM: return what? */
-
- last_block = (inode->i_size + blocksize-1)
- >> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
- max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1)
- >> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
-
- if (inode->i_size & (blocksize - 1))
- if (ext4_block_truncate_page(handle, mapping, inode->i_size))
- goto out_stop;
-
- if (last_block != max_block) {
- n = ext4_block_to_path(inode, last_block, offsets, NULL);
- if (n == 0)
- goto out_stop; /* error */
- }
-
- /*
- * OK. This truncate is going to happen. We add the inode to the
- * orphan list, so that if this truncate spans multiple transactions,
- * and we crash, we will resume the truncate when the filesystem
- * recovers. It also marks the inode dirty, to catch the new size.
- *
- * Implication: the file must always be in a sane, consistent
- * truncatable state while each transaction commits.
- */
- if (ext4_orphan_add(handle, inode))
- goto out_stop;
-
- /*
- * From here we block out all ext4_get_block() callers who want to
- * modify the block allocation tree.
- */
- down_write(&ei->i_data_sem);
-
- ext4_discard_preallocations(inode);
-
- /*
- * The orphan list entry will now protect us from any crash which
- * occurs before the truncate completes, so it is now safe to propagate
- * the new, shorter inode size (held for now in i_size) into the
- * on-disk inode. We do this via i_disksize, which is the value which
- * ext4 *really* writes onto the disk inode.
- */
- ei->i_disksize = inode->i_size;
-
- if (last_block == max_block) {
- /*
- * It is unnecessary to free any data blocks if last_block is
- * equal to the indirect block limit.
- */
- goto out_unlock;
- } else if (n == 1) { /* direct blocks */
- ext4_free_data(handle, inode, NULL, i_data+offsets[0],
- i_data + EXT4_NDIR_BLOCKS);
- goto do_indirects;
- }
-
- partial = ext4_find_shared(inode, n, offsets, chain, &nr);
- /* Kill the top of shared branch (not detached) */
- if (nr) {
- if (partial == chain) {
- /* Shared branch grows from the inode */
- ext4_free_branches(handle, inode, NULL,
- &nr, &nr+1, (chain+n-1) - partial);
- *partial->p = 0;
- /*
- * We mark the inode dirty prior to restart,
- * and prior to stop. No need for it here.
- */
- } else {
- /* Shared branch grows from an indirect block */
- BUFFER_TRACE(partial->bh, "get_write_access");
- ext4_free_branches(handle, inode, partial->bh,
- partial->p,
- partial->p+1, (chain+n-1) - partial);
- }
- }
- /* Clear the ends of indirect blocks on the shared branch */
- while (partial > chain) {
- ext4_free_branches(handle, inode, partial->bh, partial->p + 1,
- (__le32*)partial->bh->b_data+addr_per_block,
- (chain+n-1) - partial);
- BUFFER_TRACE(partial->bh, "call brelse");
- brelse(partial->bh);
- partial--;
- }
-do_indirects:
- /* Kill the remaining (whole) subtrees */
- switch (offsets[0]) {
- default:
- nr = i_data[EXT4_IND_BLOCK];
- if (nr) {
- ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1);
- i_data[EXT4_IND_BLOCK] = 0;
- }
- case EXT4_IND_BLOCK:
- nr = i_data[EXT4_DIND_BLOCK];
- if (nr) {
- ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2);
- i_data[EXT4_DIND_BLOCK] = 0;
- }
- case EXT4_DIND_BLOCK:
- nr = i_data[EXT4_TIND_BLOCK];
- if (nr) {
- ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3);
- i_data[EXT4_TIND_BLOCK] = 0;
- }
- case EXT4_TIND_BLOCK:
- ;
- }
-
-out_unlock:
- up_write(&ei->i_data_sem);
- inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
- ext4_mark_inode_dirty(handle, inode);
-
- /*
- * In a multi-transaction truncate, we only make the final transaction
- * synchronous
- */
- if (IS_SYNC(inode))
- ext4_handle_sync(handle);
-out_stop:
- /*
- * If this was a simple ftruncate(), and the file will remain alive
- * then we need to clear up the orphan record which we created above.
- * However, if this was a real unlink then we were called by
- * ext4_delete_inode(), and we allow that function to clean up the
- * orphan info for us.
- */
- if (inode->i_nlink)
- ext4_orphan_del(handle, inode);
+ else
+ ext4_ind_truncate(inode);
- ext4_journal_stop(handle);
trace_ext4_truncate_exit(inode);
}
(S_ISLNK(inode->i_mode) &&
!ext4_inode_is_fast_symlink(inode))) {
/* Validate block references which are part of inode */
- ret = ext4_check_inode_blockref(inode);
+ ret = ext4_ind_check_inode(inode);
}
if (ret)
goto bad_inode;
}
if (attr->ia_valid & ATTR_SIZE) {
+ inode_dio_wait(inode);
+
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
return 0;
}
-static int ext4_indirect_trans_blocks(struct inode *inode, int nrblocks,
- int chunk)
-{
- int indirects;
-
- /* if nrblocks are contiguous */
- if (chunk) {
- /*
- * With N contiguous data blocks, we need at most
- * N/EXT4_ADDR_PER_BLOCK(inode->i_sb) + 1 indirect blocks,
- * 2 dindirect blocks, and 1 tindirect block
- */
- return DIV_ROUND_UP(nrblocks,
- EXT4_ADDR_PER_BLOCK(inode->i_sb)) + 4;
- }
- /*
- * if nrblocks are not contiguous, worse case, each block touch
- * a indirect block, and each indirect block touch a double indirect
- * block, plus a triple indirect block
- */
- indirects = nrblocks * 2 + 1;
- return indirects;
-}
-
static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
{
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
- return ext4_indirect_trans_blocks(inode, nrblocks, chunk);
+ return ext4_ind_trans_blocks(inode, nrblocks, chunk);
return ext4_ext_index_trans_blocks(inode, nrblocks, chunk);
}
struct page *page = vmf->page;
loff_t size;
unsigned long len;
- int ret = -EINVAL;
- void *fsdata;
+ int ret;
struct file *file = vma->vm_file;
struct inode *inode = file->f_path.dentry->d_inode;
struct address_space *mapping = inode->i_mapping;
+ handle_t *handle;
+ get_block_t *get_block;
+ int retries = 0;
/*
- * Get i_alloc_sem to stop truncates messing with the inode. We cannot
- * get i_mutex because we are already holding mmap_sem.
+ * This check is racy but catches the common case. We rely on
+ * __block_page_mkwrite() to do a reliable check.
*/
- down_read(&inode->i_alloc_sem);
- size = i_size_read(inode);
- if (page->mapping != mapping || size <= page_offset(page)
- || !PageUptodate(page)) {
- /* page got truncated from under us? */
- goto out_unlock;
+ vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
+ /* Delalloc case is easy... */
+ if (test_opt(inode->i_sb, DELALLOC) &&
+ !ext4_should_journal_data(inode) &&
+ !ext4_nonda_switch(inode->i_sb)) {
+ do {
+ ret = __block_page_mkwrite(vma, vmf,
+ ext4_da_get_block_prep);
+ } while (ret == -ENOSPC &&
+ ext4_should_retry_alloc(inode->i_sb, &retries));
+ goto out_ret;
}
- ret = 0;
lock_page(page);
- wait_on_page_writeback(page);
- if (PageMappedToDisk(page)) {
- up_read(&inode->i_alloc_sem);
- return VM_FAULT_LOCKED;
+ size = i_size_read(inode);
+ /* Page got truncated from under us? */
+ if (page->mapping != mapping || page_offset(page) > size) {
+ unlock_page(page);
+ ret = VM_FAULT_NOPAGE;
+ goto out;
}
if (page->index == size >> PAGE_CACHE_SHIFT)
len = size & ~PAGE_CACHE_MASK;
else
len = PAGE_CACHE_SIZE;
-
/*
- * return if we have all the buffers mapped. This avoid
- * the need to call write_begin/write_end which does a
- * journal_start/journal_stop which can block and take
- * long time
+ * Return if we have all the buffers mapped. This avoids the need to do
+ * journal_start/journal_stop which can block and take a long time
*/
if (page_has_buffers(page)) {
if (!walk_page_buffers(NULL, page_buffers(page), 0, len, NULL,
ext4_bh_unmapped)) {
- up_read(&inode->i_alloc_sem);
- return VM_FAULT_LOCKED;
+ /* Wait so that we don't change page under IO */
+ wait_on_page_writeback(page);
+ ret = VM_FAULT_LOCKED;
+ goto out;
}
}
unlock_page(page);
- /*
- * OK, we need to fill the hole... Do write_begin write_end
- * to do block allocation/reservation.We are not holding
- * inode.i__mutex here. That allow * parallel write_begin,
- * write_end call. lock_page prevent this from happening
- * on the same page though
- */
- ret = mapping->a_ops->write_begin(file, mapping, page_offset(page),
- len, AOP_FLAG_UNINTERRUPTIBLE, &page, &fsdata);
- if (ret < 0)
- goto out_unlock;
- ret = mapping->a_ops->write_end(file, mapping, page_offset(page),
- len, len, page, fsdata);
- if (ret < 0)
- goto out_unlock;
- ret = 0;
-
- /*
- * write_begin/end might have created a dirty page and someone
- * could wander in and start the IO. Make sure that hasn't
- * happened.
- */
- lock_page(page);
- wait_on_page_writeback(page);
- up_read(&inode->i_alloc_sem);
- return VM_FAULT_LOCKED;
-out_unlock:
- if (ret)
+ /* OK, we need to fill the hole... */
+ if (ext4_should_dioread_nolock(inode))
+ get_block = ext4_get_block_write;
+ else
+ get_block = ext4_get_block;
+retry_alloc:
+ handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
+ if (IS_ERR(handle)) {
ret = VM_FAULT_SIGBUS;
- up_read(&inode->i_alloc_sem);
+ goto out;
+ }
+ ret = __block_page_mkwrite(vma, vmf, get_block);
+ if (!ret && ext4_should_journal_data(inode)) {
+ if (walk_page_buffers(handle, page_buffers(page), 0,
+ PAGE_CACHE_SIZE, NULL, do_journal_get_write_access)) {
+ unlock_page(page);
+ ret = VM_FAULT_SIGBUS;
+ goto out;
+ }
+ ext4_set_inode_state(inode, EXT4_STATE_JDATA);
+ }
+ ext4_journal_stop(handle);
+ if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+ goto retry_alloc;
+out_ret:
+ ret = block_page_mkwrite_return(ret);
+out:
return ret;
}
projects / deliverable / linux.git / blobdiff