diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-08-14 08:56:02 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-08-14 08:56:02 -0700 |
commit | 781fca5b104693bc9242199cc47c690dcaf6a4cb (patch) | |
tree | d216d4299ae5715331a535c84bab390a907bebd6 /fs | |
parent | 10f3e23f07cb0c20f9bcb77a5b5a7eb2a1b2a2fe (diff) | |
parent | 01239d77b9dd978863d1a75f0d095ab942a1fe66 (diff) |
Merge tag 'xfs-4.19-merge-6' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux
Pull xfs updates from Darrick Wong:
"This is the second part of the XFS changes for 4.19.
The biggest changes are the removal of buffer heads frm XFS, a massive
reworking of the deferred transaction operations handling code, the
removal of the long defunct barrier/nobarrier mount options, and the
addition of a few more online repair functions.
Summary:
- Use extent maps to track pagecache page status instead of
bufferhead state.
- Refactor pagecache read and write paths to use the new iomap
library functions, which enable us to drop the old bufferhead code
for pagesize == blocksize filesystems.
- Set up parallel per-block-per-page metadata to track subpage
information that was tracked by buffer heads, which enables us to
drop the old bufferhead code for pagesize > blocksize filesystems.
- Tie a deferred ops control structure to a transaction so that we
can take advantage of an upper-level dfops without having to plumb
pointer passing through the code.
- Refactor the deferred ops code to track deferred ops as part of the
transaction structure (instead of as a separate data structure) so
that we can simplify the scoping rules around defer_ops.
- Refactor twisty delwri buffer submission code to avoid deadlocks.
- Shorten and fix indenting problems in the scrub code.
- Detect obviously bad summary counts at mount and fix them.
- Directly associate deferred ops control structure with a
transaction so that callers no longer have to manage it themselves.
- Remove a couple of IRIX-era inode macros.
- Remove the long-deprecated 'barrier' and 'nobarrier' mount options.
- Clean up the inode fork structure a bit.
- Check for bad fs summary counter values in the superblock.
- Reduce COW fork lookups during writeback.
- Refactor the deferred ops control structures into the transaction
structure, thereby eliminating the need for transaction users to
handle the deferred ops as a separate data structure.
- Add the ability to repair AG headers online.
- Fix a crash due to insufficient return value checking.
- Various fixes and cleanups"
* tag 'xfs-4.19-merge-6' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (155 commits)
xfs: fix a null pointer dereference in xfs_bmap_extents_to_btree
xfs: remove b_last_holder & associated macros
iomap: Switch to offset_in_page for clarity
xfs: Close race between direct IO and xfs_break_layouts()
xfs: repair the AGI
xfs: repair the AGFL
xfs: repair the AGF
xfs: remove dead error handling code in xfs_dquot_disk_alloc()
xfs: use WRITE_ONCE to update if_seq
xfs: fix a comment in xfs_log_reserve
xfs: only validate summary counts on primary superblock
xfs: substitute spaces with tabs
xfs: fold dfops into the transaction
xfs: always defer agfl block frees
xfs: pass transaction to xfs_defer_add()
xfs: replace xfs_defer_ops ->dop_pending with on-stack list
xfs: cancel dfops on xfs_defer_finish() error
xfs: clean out superfluous dfops dop params/vars
xfs: drop dop param from xfs_defer_op_type ->finish_item() callback
xfs: automatic dfops inode relogging
...
Diffstat (limited to 'fs')
117 files changed, 5640 insertions, 5332 deletions
diff --git a/fs/iomap.c b/fs/iomap.c index 530670608fc8..009071e73bc0 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -17,6 +17,7 @@ #include <linux/iomap.h> #include <linux/uaccess.h> #include <linux/gfp.h> +#include <linux/migrate.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/swap.h> @@ -104,6 +105,138 @@ iomap_sector(struct iomap *iomap, loff_t pos) return (iomap->addr + pos - iomap->offset) >> SECTOR_SHIFT; } +static struct iomap_page * +iomap_page_create(struct inode *inode, struct page *page) +{ + struct iomap_page *iop = to_iomap_page(page); + + if (iop || i_blocksize(inode) == PAGE_SIZE) + return iop; + + iop = kmalloc(sizeof(*iop), GFP_NOFS | __GFP_NOFAIL); + atomic_set(&iop->read_count, 0); + atomic_set(&iop->write_count, 0); + bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE); + set_page_private(page, (unsigned long)iop); + SetPagePrivate(page); + return iop; +} + +static void +iomap_page_release(struct page *page) +{ + struct iomap_page *iop = to_iomap_page(page); + + if (!iop) + return; + WARN_ON_ONCE(atomic_read(&iop->read_count)); + WARN_ON_ONCE(atomic_read(&iop->write_count)); + ClearPagePrivate(page); + set_page_private(page, 0); + kfree(iop); +} + +/* + * Calculate the range inside the page that we actually need to read. + */ +static void +iomap_adjust_read_range(struct inode *inode, struct iomap_page *iop, + loff_t *pos, loff_t length, unsigned *offp, unsigned *lenp) +{ + unsigned block_bits = inode->i_blkbits; + unsigned block_size = (1 << block_bits); + unsigned poff = offset_in_page(*pos); + unsigned plen = min_t(loff_t, PAGE_SIZE - poff, length); + unsigned first = poff >> block_bits; + unsigned last = (poff + plen - 1) >> block_bits; + unsigned end = offset_in_page(i_size_read(inode)) >> block_bits; + + /* + * If the block size is smaller than the page size we need to check the + * per-block uptodate status and adjust the offset and length if needed + * to avoid reading in already uptodate ranges. + */ + if (iop) { + unsigned int i; + + /* move forward for each leading block marked uptodate */ + for (i = first; i <= last; i++) { + if (!test_bit(i, iop->uptodate)) + break; + *pos += block_size; + poff += block_size; + plen -= block_size; + first++; + } + + /* truncate len if we find any trailing uptodate block(s) */ + for ( ; i <= last; i++) { + if (test_bit(i, iop->uptodate)) { + plen -= (last - i + 1) * block_size; + last = i - 1; + break; + } + } + } + + /* + * If the extent spans the block that contains the i_size we need to + * handle both halves separately so that we properly zero data in the + * page cache for blocks that are entirely outside of i_size. + */ + if (first <= end && last > end) + plen -= (last - end) * block_size; + + *offp = poff; + *lenp = plen; +} + +static void +iomap_set_range_uptodate(struct page *page, unsigned off, unsigned len) +{ + struct iomap_page *iop = to_iomap_page(page); + struct inode *inode = page->mapping->host; + unsigned first = off >> inode->i_blkbits; + unsigned last = (off + len - 1) >> inode->i_blkbits; + unsigned int i; + bool uptodate = true; + + if (iop) { + for (i = 0; i < PAGE_SIZE / i_blocksize(inode); i++) { + if (i >= first && i <= last) + set_bit(i, iop->uptodate); + else if (!test_bit(i, iop->uptodate)) + uptodate = false; + } + } + + if (uptodate && !PageError(page)) + SetPageUptodate(page); +} + +static void +iomap_read_finish(struct iomap_page *iop, struct page *page) +{ + if (!iop || atomic_dec_and_test(&iop->read_count)) + unlock_page(page); +} + +static void +iomap_read_page_end_io(struct bio_vec *bvec, int error) +{ + struct page *page = bvec->bv_page; + struct iomap_page *iop = to_iomap_page(page); + + if (unlikely(error)) { + ClearPageUptodate(page); + SetPageError(page); + } else { + iomap_set_range_uptodate(page, bvec->bv_offset, bvec->bv_len); + } + + iomap_read_finish(iop, page); +} + static void iomap_read_inline_data(struct inode *inode, struct page *page, struct iomap *iomap) @@ -132,7 +265,7 @@ iomap_read_end_io(struct bio *bio) int i; bio_for_each_segment_all(bvec, bio, i) - page_endio(bvec->bv_page, false, error); + iomap_read_page_end_io(bvec, error); bio_put(bio); } @@ -150,9 +283,10 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, { struct iomap_readpage_ctx *ctx = data; struct page *page = ctx->cur_page; - unsigned poff = pos & (PAGE_SIZE - 1); - unsigned plen = min_t(loff_t, PAGE_SIZE - poff, length); + struct iomap_page *iop = iomap_page_create(inode, page); bool is_contig = false; + loff_t orig_pos = pos; + unsigned poff, plen; sector_t sector; if (iomap->type == IOMAP_INLINE) { @@ -161,13 +295,14 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, return PAGE_SIZE;< |