diff options
| -rw-r--r-- | fs/xfs/libxfs/xfs_bmap.c | 371 | ||||
| -rw-r--r-- | fs/xfs/libxfs/xfs_bmap.h | 7 | ||||
| -rw-r--r-- | fs/xfs/libxfs/xfs_ialloc.c | 5 | ||||
| -rw-r--r-- | fs/xfs/xfs_aops.c | 77 | ||||
| -rw-r--r-- | fs/xfs/xfs_bmap_util.c | 104 | ||||
| -rw-r--r-- | fs/xfs/xfs_buf.c | 353 | ||||
| -rw-r--r-- | fs/xfs/xfs_buf.h | 15 | ||||
| -rw-r--r-- | fs/xfs/xfs_buf_item.c | 8 | ||||
| -rw-r--r-- | fs/xfs/xfs_file.c | 27 | ||||
| -rw-r--r-- | fs/xfs/xfs_fsops.c | 11 | ||||
| -rw-r--r-- | fs/xfs/xfs_inode.c | 2 | ||||
| -rw-r--r-- | fs/xfs/xfs_ioctl.c | 8 | ||||
| -rw-r--r-- | fs/xfs/xfs_log.c | 59 | ||||
| -rw-r--r-- | fs/xfs/xfs_log_recover.c | 596 | ||||
| -rw-r--r-- | fs/xfs/xfs_mount.c | 58 | ||||
| -rw-r--r-- | fs/xfs/xfs_qm.c | 1 | ||||
| -rw-r--r-- | fs/xfs/xfs_rtalloc.c | 30 | ||||
| -rw-r--r-- | fs/xfs/xfs_super.c | 3 | ||||
| -rw-r--r-- | fs/xfs/xfs_trace.h | 3 | ||||
| -rw-r--r-- | fs/xfs/xfs_trans_buf.c | 16 |
20 files changed, 983 insertions, 771 deletions
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index de2d26d32844..79c981984dca 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -5404,39 +5404,237 @@ error0: } /* + * Determine whether an extent shift can be accomplished by a merge with the + * extent that precedes the target hole of the shift. + */ +STATIC bool +xfs_bmse_can_merge( + struct xfs_bmbt_irec *left, /* preceding extent */ + struct xfs_bmbt_irec *got, /* current extent to shift */ + xfs_fileoff_t shift) /* shift fsb */ +{ + xfs_fileoff_t startoff; + + startoff = got->br_startoff - shift; + + /* + * The extent, once shifted, must be adjacent in-file and on-disk with + * the preceding extent. + */ + if ((left->br_startoff + left->br_blockcount != startoff) || + (left->br_startblock + left->br_blockcount != got->br_startblock) || + (left->br_state != got->br_state) || + (left->br_blockcount + got->br_blockcount > MAXEXTLEN)) + return false; + + return true; +} + +/* + * A bmap extent shift adjusts the file offset of an extent to fill a preceding + * hole in the file. If an extent shift would result in the extent being fully + * adjacent to the extent that currently precedes the hole, we can merge with + * the preceding extent rather than do the shift. + * + * This function assumes the caller has verified a shift-by-merge is possible + * with the provided extents via xfs_bmse_can_merge(). + */ +STATIC int +xfs_bmse_merge( + struct xfs_inode *ip, + int whichfork, + xfs_fileoff_t shift, /* shift fsb */ + int current_ext, /* idx of gotp */ + struct xfs_bmbt_rec_host *gotp, /* extent to shift */ + struct xfs_bmbt_rec_host *leftp, /* preceding extent */ + struct xfs_btree_cur *cur, + int *logflags) /* output */ +{ + struct xfs_ifork *ifp; + struct xfs_bmbt_irec got; + struct xfs_bmbt_irec left; + xfs_filblks_t blockcount; + int error, i; + + ifp = XFS_IFORK_PTR(ip, whichfork); + xfs_bmbt_get_all(gotp, &got); + xfs_bmbt_get_all(leftp, &left); + blockcount = left.br_blockcount + got.br_blockcount; + + ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); + ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); + ASSERT(xfs_bmse_can_merge(&left, &got, shift)); + + /* + * Merge the in-core extents. Note that the host record pointers and + * current_ext index are invalid once the extent has been removed via + * xfs_iext_remove(). + */ + xfs_bmbt_set_blockcount(leftp, blockcount); + xfs_iext_remove(ip, current_ext, 1, 0); + + /* + * Update the on-disk extent count, the btree if necessary and log the + * inode. + */ + XFS_IFORK_NEXT_SET(ip, whichfork, + XFS_IFORK_NEXTENTS(ip, whichfork) - 1); + *logflags |= XFS_ILOG_CORE; + if (!cur) { + *logflags |= XFS_ILOG_DEXT; + return 0; + } + + /* lookup and remove the extent to merge */ + error = xfs_bmbt_lookup_eq(cur, got.br_startoff, got.br_startblock, + got.br_blockcount, &i); + if (error) + goto out_error; + XFS_WANT_CORRUPTED_GOTO(i == 1, out_error); + + error = xfs_btree_delete(cur, &i); + if (error) + goto out_error; + XFS_WANT_CORRUPTED_GOTO(i == 1, out_error); + + /* lookup and update size of the previous extent */ + error = xfs_bmbt_lookup_eq(cur, left.br_startoff, left.br_startblock, + left.br_blockcount, &i); + if (error) + goto out_error; + XFS_WANT_CORRUPTED_GOTO(i == 1, out_error); + + left.br_blockcount = blockcount; + + error = xfs_bmbt_update(cur, left.br_startoff, left.br_startblock, + left.br_blockcount, left.br_state); + if (error) + goto out_error; + + return 0; + +out_error: + return error; +} + +/* + * Shift a single extent. + */ +STATIC int +xfs_bmse_shift_one( + struct xfs_inode *ip, + int whichfork, + xfs_fileoff_t offset_shift_fsb, + int *current_ext, + struct xfs_bmbt_rec_host *gotp, + struct xfs_btree_cur *cur, + int *logflags) +{ + struct xfs_ifork *ifp; + xfs_fileoff_t startoff; + struct xfs_bmbt_rec_host *leftp; + struct xfs_bmbt_irec got; + struct xfs_bmbt_irec left; + int error; + int i; + + ifp = XFS_IFORK_PTR(ip, whichfork); + + xfs_bmbt_get_all(gotp, &got); + startoff = got.br_startoff - offset_shift_fsb; + + /* delalloc extents should be prevented by caller */ + XFS_WANT_CORRUPTED_GOTO(!isnullstartblock(got.br_startblock), + out_error); + + /* + * If this is the first extent in the file, make sure there's enough + * room at the start of the file and jump right to the shift as there's + * no left extent to merge. + */ + if (*current_ext == 0) { + if (got.br_startoff < offset_shift_fsb) + return -EINVAL; + goto shift_extent; + } + + /* grab the left extent and check for a large enough hole */ + leftp = xfs_iext_get_ext(ifp, *current_ext - 1); + xfs_bmbt_get_all(leftp, &left); + + if (startoff < left.br_startoff + left.br_blockcount) + return -EINVAL; + + /* check whether to merge the extent or shift it down */ + if (!xfs_bmse_can_merge(&left, &got, offset_shift_fsb)) + goto shift_extent; + + return xfs_bmse_merge(ip, whichfork, offset_shift_fsb, *current_ext, + gotp, leftp, cur, logflags); + +shift_extent: + /* + * Increment the extent index for the next iteration, update the start + * offset of the in-core extent and update the btree if applicable. + */ + (*current_ext)++; + xfs_bmbt_set_startoff(gotp, startoff); + *logflags |= XFS_ILOG_CORE; + if (!cur) { + *logflags |= XFS_ILOG_DEXT; + return 0; + } + + error = xfs_bmbt_lookup_eq(cur, got.br_startoff, got.br_startblock, + got.br_blockcount, &i); + if (error) + return error; + XFS_WANT_CORRUPTED_GOTO(i == 1, out_error); + + got.br_startoff = startoff; + error = xfs_bmbt_update(cur, got.br_startoff, got.br_startblock, + got.br_blockcount, got.br_state); + if (error) + return error; + + return 0; + +out_error: + return error; +} + +/* * Shift extent records to the left to cover a hole. * - * The maximum number of extents to be shifted in a single operation - * is @num_exts, and @current_ext keeps track of the current extent - * index we have shifted. @offset_shift_fsb is the length by which each - * extent is shifted. If there is no hole to shift the extents - * into, this will be considered invalid operation and we abort immediately. + * The maximum number of extents to be shifted in a single operation is + * @num_exts. @start_fsb specifies the file offset to start the shift and the + * file offset where we've left off is returned in @next_fsb. @offset_shift_fsb + * is the length by which each extent is shifted. If there is no hole to shift + * the extents into, this will be considered invalid operation and we abort + * immediately. */ int xfs_bmap_shift_extents( struct xfs_trans *tp, struct xfs_inode *ip, - int *done, xfs_fileoff_t start_fsb, xfs_fileoff_t offset_shift_fsb, - xfs_extnum_t *current_ext, + int *done, + xfs_fileoff_t *next_fsb, xfs_fsblock_t *firstblock, struct xfs_bmap_free *flist, int num_exts) { - struct xfs_btree_cur *cur; + struct xfs_btree_cur *cur = NULL; struct xfs_bmbt_rec_host *gotp; struct xfs_bmbt_irec got; - struct xfs_bmbt_irec left; struct xfs_mount *mp = ip->i_mount; struct xfs_ifork *ifp; xfs_extnum_t nexts = 0; - xfs_fileoff_t startoff; + xfs_extnum_t current_ext; int error = 0; - int i; int whichfork = XFS_DATA_FORK; - int logflags; - xfs_filblks_t blockcount = 0; + int logflags = 0; int total_extents; if (unlikely(XFS_TEST_ERROR( @@ -5451,7 +5649,8 @@ xfs_bmap_shift_extents( if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; - ASSERT(current_ext != NULL); + ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); + ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); ifp = XFS_IFORK_PTR(ip, whichfork); if (!(ifp->if_flags & XFS_IFEXTENTS)) { @@ -5461,142 +5660,62 @@ xfs_bmap_shift_extents( return error; } - /* - * If *current_ext is 0, we would need to lookup the extent - * from where we would start shifting and store it in gotp. - */ - if (!*current_ext) { - gotp = xfs_iext_bno_to_ext(ifp, start_fsb, current_ext); - /* - * gotp can be null in 2 cases: 1) if there are no extents - * or 2) start_fsb lies in a hole beyond which there are - * no extents. Either way, we are done. - */ - if (!gotp) { - *done = 1; - return 0; - } - } - - /* We are going to change core inode */ - logflags = XFS_ILOG_CORE; if (ifp->if_flags & XFS_IFBROOT) { cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork); cur->bc_private.b.firstblock = *firstblock; cur->bc_private.b.flist = flist; cur->bc_private.b.flags = 0; - } else { - cur = NULL; - logflags |= XFS_ILOG_DEXT; + } + + /* + * Look up the extent index for the fsb where we start shifting. We can + * henceforth iterate with current_ext as extent list changes are locked + * out via ilock. + * + * gotp can be null in 2 cases: 1) if there are no extents or 2) + * start_fsb lies in a hole beyond which there are no extents. Either + * way, we are done. + */ + gotp = xfs_iext_bno_to_ext(ifp, start_fsb, ¤t_ext); + if (!gotp) { + *done = 1; + goto del_cursor; } /* * There may be delalloc extents in the data fork before the range we - * are collapsing out, so we cannot - * use the count of real extents here. Instead we have to calculate it - * from the incore fork. + * are collapsing out, so we cannot use the count of real extents here. + * Instead we have to calculate it from the incore fork. */ total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t); - while (nexts++ < num_exts && *current_ext < total_extents) { - - gotp = xfs_iext_get_ext(ifp, *current_ext); - xfs_bmbt_get_all(gotp, &got); - startoff = got.br_startoff - offset_shift_fsb; - - /* - * Before shifting extent into hole, make sure that the hole - * is large enough to accomodate the shift. - */ - if (*current_ext) { - xfs_bmbt_get_all(xfs_iext_get_ext(ifp, - *current_ext - 1), &left); - - if (startoff < left.br_startoff + left.br_blockcount) - error = -EINVAL; - } else if (offset_shift_fsb > got.br_startoff) { - /* - * When first extent is shifted, offset_shift_fsb - * should be less than the stating offset of - * the first extent. - */ - error = -EINVAL; - } - + while (nexts++ < num_exts && current_ext < total_extents) { + error = xfs_bmse_shift_one(ip, whichfork, offset_shift_fsb, + ¤t_ext, gotp, cur, &logflags); if (error) goto del_cursor; - if (cur) { - error = xfs_bmbt_lookup_eq(cur, got.br_startoff, - got.br_startblock, - got.br_blockcount, - &i); - if (error) - goto del_cursor; - XFS_WANT_CORRUPTED_GOTO(i == 1, del_cursor); - } - - /* Check if we can merge 2 adjacent extents */ - if (*current_ext && - left.br_startoff + left.br_blockcount == startoff && - left.br_startblock + left.br_blockcount == - got.br_startblock && - left.br_state == got.br_state && - left.br_blockcount + got.br_blockcount <= MAXEXTLEN) { - blockcount = left.br_blockcount + - got.br_blockcount; - xfs_iext_remove(ip, *current_ext, 1, 0); - if (cur) { - error = xfs_btree_delete(cur, &i); - if (error) - goto del_cursor; - XFS_WANT_CORRUPTED_GOTO(i == 1, del_cursor); - } - XFS_IFORK_NEXT_SET(ip, whichfork, - XFS_IFORK_NEXTENTS(ip, whichfork) - 1); - gotp = xfs_iext_get_ext(ifp, --*current_ext); - xfs_bmbt_get_all(gotp, &got); - - /* Make cursor point to the extent we will update */ - if (cur) { - error = xfs_bmbt_lookup_eq(cur, got.br_startoff, - got.br_startblock, - got.br_blockcount, - &i); - if (error) - goto del_cursor; - XFS_WANT_CORRUPTED_GOTO(i == 1, del_cursor); - } - - xfs_bmbt_set_blockcount(gotp, blockcount); - got.br_blockcount = blockcount; - } else { - /* We have to update the startoff */ - xfs_bmbt_set_startoff(gotp, startoff); - got.br_startoff = startoff; - } - - if (cur) { - error = xfs_bmbt_update(cur, got.br_startoff, - got.br_startblock, - got.br_blockcount, - got.br_state); - if (error) - goto del_cursor; - } - - (*current_ext)++; + /* update total extent count and grab the next record */ total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t); + if (current_ext >= total_extents) + break; + gotp = xfs_iext_get_ext(ifp, current_ext); } /* Check if we are done */ - if (*current_ext == total_extents) + if (current_ext == total_extents) { *done = 1; + } else if (next_fsb) { + xfs_bmbt_get_all(gotp, &got); + *next_fsb = got.br_startoff; + } del_cursor: if (cur) xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR); - xfs_trans_log_inode(tp, ip, logflags); + if (logflags) + xfs_trans_log_inode(tp, ip, logflags); + return error; } diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index b879ca56a64c..44db6db86402 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -178,9 +178,8 @@ int xfs_check_nostate_extents(struct xfs_ifork *ifp, xfs_extnum_t idx, xfs_extnum_t num); uint xfs_default_attroffset(struct xfs_inode *ip); int xfs_bmap_shift_extents(struct xfs_trans *tp, struct xfs_inode *ip, - int *done, xfs_fileoff_t start_fsb, - xfs_fileoff_t offset_shift_fsb, xfs_extnum_t *current_ext, - xfs_fsblock_t *firstblock, struct xfs_bmap_free *flist, - int num_exts); + xfs_fileoff_t start_fsb, xfs_fileoff_t offset_shift_fsb, + int *done, xfs_fileoff_t *next_fsb, xfs_fsblock_t *firstblock, + struct xfs_bmap_free *flist, int num_exts); #endif /* __XFS_BMAP_H__ */ diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index d213a2eae95e..23dcb72fc5e6 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -1076,8 +1076,8 @@ xfs_dialloc_ag_finobt_newino( int i; if (agi->agi_newino != cpu_to_be32(NULLAGINO)) { - error = xfs_inobt_lookup(cur, agi->agi_newino, XFS_LOOKUP_EQ, - &i); + error = xfs_inobt_lookup(cur, be32_to_cpu(agi->agi_newino), + XFS_LOOKUP_EQ, &i); if (error) return error; if (i == 1) { @@ -1085,7 +1085,6 @@ xfs_dialloc_ag_finobt_newino( if (error) return error; XFS_WANT_CORRUPTED_RETURN(i == 1); - return 0; } } diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index dc3e10882d1f..f5b2453a43b2 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -434,10 +434,22 @@ xfs_start_page_writeback( { ASSERT(PageLocked(page)); ASSERT(!PageWriteback(page)); - if (clear_dirty) + + /* + * if the page was not fully cleaned, we need to ensure that the higher + * layers come back to it correctly. That means we need to keep the page + * dirty, and for WB_SYNC_ALL writeback we need to ensure the + * PAGECACHE_TAG_TOWRITE index mark is not removed so another attempt to + * write this page in this writeback sweep will be made. + */ + if (clear_dirty) { clear_page_dirty_for_io(page); - set_page_writeback(page); + set_page_writeback(page); + } else + set_page_writeback_keepwrite(page); + unlock_page(page); + /* If no buffers on the page are to be written, finish it here */ if (!buffers) end_page_writeback(page); @@ -1760,11 +1772,72 @@ xfs_vm_readpages( return mpage_readpages(mapping, pages, nr_pages, xfs_get_blocks); } +/* + * This is basically a copy of __set_page_dirty_buffers() with one + * small tweak: buffers beyond EOF do not get marked dirty. If we mark them + * dirty, we'll never be able to clean them because we don't write buffers + * beyond EOF, and that means we can't invalidate pages that span EOF + * that have been marked dirty. Further, the dirty state can leak into + * the file interior if the file is extended, resulting in all sorts of + * bad things happening as the state does not match the underlying data. + * + * XXX: this really indicates that bufferheads in XFS need to die. Warts like + * this only exist because of bufferheads and how the generic code manages them. + */ +STATIC int +xfs_vm_set_page_dirty( + struct page *page) +{ + struct address_space *mapping = page->mapping; + struct inode *inode = mapping->host; + loff_t end_offset; + loff_t offset; + int newly_dirty; + + if (unlikely(!mapping)) + return !TestSetPageDirty(page); + + end_offset = i_size_read(inode); + offset = page_offset(page); + + spin_lock(&mapping->private_lock); + if (page_has_buffers(page)) { + struct buffer_head *head = page_buffers(page); + struct buffer_head *bh = head; + + do { + if (offset < end_offset) + set_buffer_dirty(bh); + bh = bh->b_this_page; + offset += 1 << inode->i_blkbits; + } while (bh != head); + } + newly_dirty = !TestSetPageDirty(page); + spin_unlock(&mapping->private_lock); + + if (newly_dirty) { + /* sigh - __set_page_dirty() is static, so copy it here, too */ + unsigned long flags; + + spin_lock_irqsave(&mapping->tree_lock, flags); + if (page->mapping) { /* Race with truncate? */ + WARN_ON_ONCE(!PageUptodate(page)); + account_page_dirtied(page, mapping); + radix_tree_tag_set(&mapping->page_tree, + page_index(page), PAGECACHE_TAG_DIRTY); + } + spin_unlock_irqrestore(&mapping->tree_lock, flags); + __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); + } + return newly_dirty; +} + const struct address_space_operations xfs_address_space_operations = { .readpage = xfs_vm_readpage, .readpages = xfs_vm_readpages, .writepage = xfs_vm_writepage, .writepages = xfs_vm_writepages, + .set_page_dirty = xfs_vm_set_page_dirty, .releasepage = xfs_vm_releasepage, .invalidatepage = xfs_vm_invalidatepage, .write_begin = xfs_vm_write_begin, diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 6f5cb63bed17..92e8f99a5857 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1122,14 +1122,6 @@ xfs_zero_remaining_bytes( if (endoff > XFS_ISIZE(ip)) endoff = XFS_ISIZE(ip); - bp = xfs_buf_get_uncached(XFS_IS_REALTIME_INODE(ip) ? - mp->m_rtdev_targp : mp->m_ddev_targp, - BTOBB(mp->m_sb.sb_blocksize), 0); - if (!bp) - return -ENOMEM; - - xfs_buf_unlock(bp); - for (offset = startoff; offset <= endoff; offset = lastoffset + 1) { uint lock_mode; @@ -1152,42 +1144,24 @@ xfs_zero_remaining_bytes( ASSERT(imap.br_startblock != DELAYSTARTBLOCK); if (imap.br_state == XFS_EXT_UNWRITTEN) continue; - XFS_BUF_UNDONE(bp); - XFS_BUF_UNWRITE(bp); - XFS_BUF_READ(bp); - XFS_BUF_SET_ADDR(bp, xfs_fsb_to_db(ip, imap.br_startblock)); - if (XFS_FORCED_SHUTDOWN(mp)) { - error = -EIO; - break; - } - xfs_buf_iorequest(bp); - error = xfs_buf_iowait(bp); - if (error) { - xfs_buf_ioerror_alert(bp, - "xfs_zero_remaining_bytes(read)"); - break; - } + error = xfs_buf_read_uncached(XFS_IS_REALTIME_INODE(ip) ? + mp->m_rtdev_targp : mp->m_ddev_targp, + xfs_fsb_to_db(ip, imap.br_startblock), + BTOBB(mp->m_sb.sb_blocksize), + 0, &bp, NULL); + if (error) + return error; + memset(bp->b_addr + - (offset - XFS_FSB_TO_B(mp, imap.br_startoff)), - 0, lastoffset - offset + 1); - XFS_BUF_UNDONE(bp); - XFS_BUF_UNREAD(bp); - XFS_BUF_WRITE(bp); - - if (XFS_FORCED_SHUTDOWN(mp)) { - error = -EIO; - break; - } - xfs_buf_iorequest(bp); - error = xfs_buf_iowait(bp); - if (error) { - xfs_buf_ioerror_alert(bp, - "xfs_zero_remaining_bytes(write)"); - break; - } + (offset - XFS_FSB_TO_B(mp, imap.br_startoff)), + 0, lastoffset - offset + 1); + + error = xfs_bwrite(bp); + xfs_buf_relse(bp); + if (error) + return error; } - xfs_buf_free(bp); return error; } @@ -1205,6 +1179,7 @@ xfs_free_file_space( xfs_bmap_free_t free_list; xfs_bmbt_irec_t imap; xfs_off_t ioffset; + xfs_off_t iendoffset; xfs_extlen_t mod=0; xfs_mount_t *mp; int nimap; @@ -1233,12 +1208,13 @@ xfs_free_file_space( inode_dio_wait(VFS_I(ip)); rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE); - ioffset = offset & ~(rounding - 1); - error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping, - ioffset, -1); + ioffset = round_down(offset, rounding); + iendoffset = round_up(offset + len, rounding) - 1; + error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping, ioffset, + iendoffset); if (error) goto out; - truncate_pagecache_range(VFS_I(ip), ioffset, -1); + truncate_pagecache_range(VFS_I(ip), ioffset, iendoffset); /* * Need to zero the stuff we're not freeing, on disk. @@ -1456,24 +1432,50 @@ xfs_collapse_file_space( struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; int error; - xfs_extnum_t current_ext = 0; struct xfs_bmap_free free_list; xfs_fsblock_t first_block; int committed; xfs_fileoff_t start_fsb; + xfs_fileoff_t next_fsb; xfs_fileoff_t shift_fsb; ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); trace_xfs_collapse_file_space(ip); - start_fsb = XFS_B_TO_FSB(mp, offset + len); + next_fsb = XFS_B_TO_FSB(mp, offset + len); shift_fsb = XFS_B_TO_FSB(mp, len); error = xfs_free_file_space(ip, offset, len); if (error) return error; + /* + * Trim eofblocks to avoid shifting uninitialized post-eof preallocation + * into the accessible region of the file. + */ + if (xfs_can_free_eofblocks(ip, true)) { + error = xfs_free_eofblocks(mp, ip, false); + if (error) + return error; + } + + /* + * Writeback and invalidate cache for the remainder of the file as we're + * about to shift down every extent from the collapse range to EOF. The + * free of the collapse range above might have already done some of + * this, but we shouldn't rely on it to do anything outside of the range + * that was freed. + */ + error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping, + offset + len, -1); + if (error) + return error; + error = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping, + (offset + len) >> PAGE_CACHE_SHIFT, -1); + if (error) + return error; + while (!error && !done) { tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT); /* @@ -1505,10 +1507,10 @@ xfs_collapse_file_space( * We are using the write transaction in which max 2 bmbt * updates are allowed */ - error = xfs_bmap_shift_extents(tp, ip, &done, start_fsb, - shift_fsb, ¤t_ext, - &first_block, &free_list, - XFS_BMAP_MAX_SHIFT_EXTENTS); + start_fsb = next_fsb; + error = xfs_bmap_shift_extents(tp, ip, start_fsb, shift_fsb, + &done, &next_fsb, &first_block, &free_list, + XFS_BMAP_MAX_SHIFT_EXTENTS); if (error) goto out; diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index ec6505056b2c..017b6afe340b 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -623,10 +623,11 @@ _xfs_buf_read( bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD); bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD); - xfs_buf_iorequest(bp); - if (flags & XBF_ASYNC) + if (flags & XBF_ASYNC) { + xfs_buf_submit(bp); return 0; - return xfs_buf_iowait(bp); + } + return xfs_buf_submit_wait(bp); } xfs_buf_t * @@ -687,34 +688,39 @@ xfs_buf_readahead_map( * Read an uncached buffer from disk. Allocates and returns a locked * buffer containing the disk contents or nothing. */ -struct xfs_buf * +int xfs_buf_read_uncached( struct xfs_buftarg *target, xfs_daddr_t daddr, size_t numblks, int flags, + struct xfs_buf **bpp, const struct xfs_buf_ops *ops) { struct xfs_buf *bp; + *bpp = NULL; + bp = xfs_buf_get_uncached(target, numblks, flags); if (!bp) - return NULL; + return -ENOMEM; /* set up the buffer for a read IO */ ASSERT(bp->b_map_count == 1); - bp->b_bn = daddr; + bp->b_bn = XFS_BUF_DADDR_NULL; /* always null for uncached buffers */ bp->b_maps[0].bm_bn = daddr; bp->b_flags |= XBF_READ; bp->b_ops = ops; - if (XFS_FORCED_SHUTDOWN(target->bt_mount)) { + xfs_buf_submit_wait(bp); + if (bp->b_error) { + int error = bp->b_error; xfs_buf_relse(bp); - return NULL; + return error; } - xfs_buf_iorequest(bp); - xfs_buf_iowait(bp); - return bp; + + *bpp = bp; + return 0; } /* @@ -998,53 +1004,56 @@ xfs_buf_wait_unpin( * Buffer Utility Routines */ -STATIC void -xfs_buf_iodone_work( - struct work_struct *work) +void +xfs_buf_ioend( + struct xfs_buf *bp) { - struct xfs_buf *bp = - container_of(work, xfs_buf_t, b_iodone_work); - bool read = !!(bp->b_flags & XBF_READ); + bool read = bp->b_flags & XBF_READ; + + trace_xfs_buf_iodone(bp, _RET_IP_); bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD); - /* only validate buffers that were read without errors */ - if (read && bp->b_ops && !bp->b_error && (bp->b_flags & XBF_DONE)) + /* + * Pull in IO completion errors now. We are guaranteed to be running + * single threaded, so we don't need the lock to read b_io_error. + */ + if (!bp->b_error && bp->b_io_error) + xfs_buf_ioerror(bp, bp->b_io_error); + + /* Only validate buffers that were read without errors */ + if (read && !bp->b_error && bp->b_ops) { + ASSERT(!bp->b_iodone); bp->b_ops->verify_read(bp); + } + + if (!bp->b_error) + bp->b_flags |= XBF_DONE; if (bp->b_iodone) (*(bp->b_iodone))(bp); else if (bp->b_flags & XBF_ASYNC) xfs_buf_relse(bp); - else { - ASSERT(read && bp->b_ops); + else complete(&bp->b_iowait); - } } -void -xfs_buf_ioend( - struct xfs_buf *bp, - int schedule) +static void +xfs_buf_ioend_work( + struct work_struct *work) { - bool read = !!(bp->b_flags & XBF_READ); - - trace_xfs_buf_iodone(bp, _RET_IP_); + struct xfs_buf *bp = + container_of(work, xfs_buf_t, b_iodone_work); - if (bp->b_error == 0) - bp->b_flags |= XBF_DONE; + xfs_buf_ioend(bp); +} - if (bp->b_iodone || (read && bp->b_ops) || (bp->b_flags & XBF_ASYNC)) { - if (schedule) { - INIT_WORK(&bp->b_iodone_work, xfs_buf_iodone_work); - queue_work(xfslogd_workqueue, &bp->b_iodone_work); - } else { - xfs_buf_iodone_work(&bp->b_iodone_work); - } - } else { - bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD); - complete(&bp->b_iowait); - } +void +xfs_buf_ioend_async( + struct xfs_buf *bp) +{ + INIT_WORK(&bp->b_iodone_work, xfs_buf_ioend_work); + queue_work(xfslogd_workqueue, &bp->b_iodone_work); } void @@ -1067,96 +1076,6 @@ xfs_buf_ioerror_alert( (__uint64_t)XFS_BUF_ADDR(bp), func, -bp->b_error, bp->b_length); } -/* - * Called when we want to stop a buffer from getting written or read. - * We attach the EIO error, muck with its flags, and call xfs_buf_ioend - * so that the proper iodone callbacks get called. - */ -STATIC int -xfs_bioerror( - xfs_buf_t *bp) -{ -#ifdef XFSERRORDEBUG - ASSERT(XFS_BUF_ISREAD(bp) || bp->b_iodone); -#endif - - /* - * No need to wait until the buffer is unpinned, we aren't flushing it. - */ - xfs_buf_ioerror(bp, -EIO); - - /* - * We're calling xfs_buf_ioend, so delete XBF_DONE flag. - */ - XFS_BUF_UNREAD(bp); - XFS_BUF_UNDONE(bp); - xfs_buf_stale(bp); - - xfs_buf_ioend(bp, 0); - - return -EIO; -} - -/* - * Same as xfs_bioerror, except that we are releasing the buffer - * here ourselves, and avoiding the xfs_buf_ioend call. - * This is meant for userdata errors; metadata bufs come with - * iodone functions attached, so that we can track down errors. - */ -int -xfs_bioerror_relse( - struct xfs_buf *bp) -{ - int64_t fl = bp->b_flags; - /* - * No need to wait until the buffer is unpinned. - * We aren't flushing it. - * - * chunkhold expects B_DONE to be set, whether - * we actually finish the I/O or not. We don't want to - * change that interface. - */ - XFS_BUF_UNREAD(bp); - XFS_BUF_DONE(bp); - xfs_buf_stale(bp); - bp->b_iodone = NULL; - if (!(fl & XBF_ASYNC)) { - /* - * Mark b_error and B_ERROR _both_. - * Lot's of chunkcache code assumes that. - * There's no reason to mark error for - * ASYNC buffers. - */ - xfs_buf_ioerror(bp, -EIO); - complete(&bp->b_iowait); - } else { - xfs_buf_relse(bp); - } - - return -EIO; -} - -STATIC int -xfs_bdstrat_cb( - struct xfs_buf *bp) -{ - if (XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) { - trace_xfs_bdstrat_shut(bp, _RET_IP_); - /* - * Metadata write that didn't get logged but - * written delayed anyway. These aren't associated - * with a transaction, and can be ignored. - */ - if (!bp->b_iodone && !XFS_BUF_ISREAD(bp)) - return xfs_bioerror_relse(bp); - else - return xfs_bioerror(bp); - } - - xfs_buf_iorequest(bp); - return 0; -} - int xfs_bwrite( struct xfs_buf *bp) @@ -1166,11 +1085,10 @@ xfs_bwrite( ASSERT(xfs_buf_islocked(bp)); bp->b_flags |= XBF_WRITE; - bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q | XBF_WRITE_FAIL); + bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q | + XBF_WRITE_FAIL | XBF_DONE); - xfs_bdstrat_cb(bp); - - error = xfs_buf_iowait(bp); + error = xfs_buf_submit_wait(bp); if (error) { xfs_force_shutdown(bp->b_target->bt_mount, SHUTDOWN_META_IO_ERROR); @@ -1179,15 +1097,6 @@ xfs_bwrite( } STATIC void -_xfs_buf_ioend( - xfs_buf_t *bp, - int schedule) -{ - if (atomic_dec_and_test(&bp->b_io_remaining) == 1) - xfs_buf_ioend(bp, schedule); -} - -STATIC void xfs_buf_bio_end_io( struct bio *bio, int error) @@ -1198,13 +1107,18 @@ xfs_buf_bio_end_io( * don't overwrite existing errors - otherwise we can lose errors on * buffers that require multiple bios to complete. */ - if (!bp->b_error) - xfs_buf_ioerror(bp, error); + if (error) { + spin_lock(&bp->b_lock); + if (!bp->b_io_error) + bp->b_io_error = error; + spin_unlock(&bp->b_lock); + } if (!bp->b_error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ)) invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp)); - _xfs_buf_ioend(bp, 1); + if (atomic_dec_and_test(&bp->b_io_remaining) == 1) + xfs_buf_ioend_async(bp); bio_put(bio); } @@ -1283,7 +1197,7 @@ next_chunk: } else { /* * This is guaranteed not to be the last io reference count - * because the caller (xfs_buf_iorequest) holds a count itself. + * because the caller (xfs_buf_submit) holds a count itself. */ atomic_dec(&bp->b_io_remaining); xfs_buf_ioerror(bp, -EIO); @@ -1373,53 +1287,131 @@ _xfs_buf_ioapply( blk_finish_plug(&plug); } +/* + * Asynchronous IO submission path. This transfers the buffer lock ownership and + * the current reference to the IO. It is not safe to reference the buffer after + * a call to this function unless the caller holds an additional reference + * itself. + */ void -xfs_buf_iorequest( - xfs_buf_t *bp) +xfs_buf_submit( + struct xfs_buf *bp) { - trace_xfs_buf_iorequest(bp, _RET_IP_); + trace_xfs_buf_submit(bp, _RET_IP_); ASSERT(!(bp->b_flags & _XBF_DELWRI_Q)); + ASSERT(bp->b_flags & XBF_ASYNC); + + /* on shutdown we stale and complete the buffer immediately */ + if (XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) { + xfs_buf_ioerror(bp, -EIO); + bp->b_flags &= ~XBF_DONE; + xfs_buf_stale(bp); + xfs_buf_ioend(bp); + return; + } if (bp->b_flags & XBF_WRITE) xfs_buf_wait_unpin(bp); + + /* clear the internal error state to avoid spurious errors */ + bp->b_io_error = 0; + + /* + * The caller's reference is released during I/O completion. + * This occurs some time after the last b_io_remaining reference is + * released, so after we drop our Io reference we have to have some + * other reference to ensure the buffer doesn't go away from underneath + * us. Take a direct reference to ensure we have safe access to the + * buffer until we are finished with it. + */ xfs_buf_hold(bp); /* - * Set the count to 1 initially, this will stop an I/O - * completion callout which happens before we have started - * all the I/O from calling xfs_buf_ioend too early. + * Set the count to 1 initially, this will stop an I/O completion + * callout which happens before we have started all the I/O from calling + * xfs_buf_ioend too early. */ atomic_set(&bp->b_io_remaining, 1); _xfs_buf_ioapply(bp); + /* - * If _xfs_buf_ioapply failed, we'll get back here with - * only the reference we took above. _xfs_buf_ioend will - * drop it to zero, so we'd better not queue it for later, - * or we'll free it before it's done. + * If _xfs_buf_ioapply failed, we can get back here with only the IO + * reference we took above. If we drop it to zero, run completion so + * that we don't return to the caller with completion still pending. */ - _xfs_buf_ioend(bp, bp->b_error ? 0 : 1); + if (atomic_dec_and_test(&bp->b_io_remaining) == 1) { + if (bp->b_error) + xfs_buf_ioend(bp); + else + xfs_buf_ioend_async(bp); + } xfs_buf_rele(bp); + /* Note: it is not safe to reference bp now we've dropped our ref */ } /* - * Waits for I/O to complete on the buffer supplied. It returns immediately if - * no I/O is pending or there is already a pending error on the buffer, in which - * case nothing will ever complete. It returns the I/O error code, if any, or - * 0 if there was no error. + * Synchronous buffer IO submission path, read or write. */ int -xfs_buf_iowait( - xfs_buf_t *bp) +xfs_buf_submit_wait( + struct xfs_buf *bp) { - trace_xfs_buf_iowait(bp, _RET_IP_); + int error; - if (!bp->b_error) - wait_for_completion(&bp->b_iowait); + trace_xfs_buf_submit_wait(bp, _RET_IP_); + + ASSERT(!(bp->b_flags & (_XBF_DELWRI_Q | XBF_ASYNC))); + + if (XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) { + xfs_buf_ioerror(bp, -EIO); + xfs_buf_stale(bp); + bp->b_flags &= ~XBF_DONE; + return -EIO; + } + + if (bp->b_flags & XBF_WRITE) + xfs_buf_wait_unpin(bp); + + /* clear the internal error state to avoid spurious errors */ + bp->b_io_error = 0; + + /* + * For synchronous IO, the IO does not inherit the submitters reference + * count, nor the buffer lock. Hence we cannot release the reference we + * are about to take until we've waited for all IO completion to occur, + * including any xfs_buf_ioend_async() work that may be pending. + */ + xfs_buf_hold(bp); + + /* + * Set the count to 1 initially, this will stop an I/O completion + * callout which happens before we have started all the I/O from calling + * xfs_buf_ioend too early. + */ + atomic_set(&bp->b_io_remaining, 1); + _xfs_buf_ioapply(bp); + + /* + * make sure we run completion synchronously if it raced with us and is + * already complete. + */ + if (atomic_dec_and_test(&bp->b_io_remaining) == 1) + xfs_buf_ioend(bp); + /* wait for completion before gathering the error from the buffer */ + trace_xfs_buf_iowait(bp, _RET_IP_); + wait_for_completion(&bp->b_iowait); trace_xfs_buf_iowait_done(bp, _RET_IP_); - return bp->b_error; + error = bp->b_error; + + /* + * all done now, we can release the hold that keeps the buffer + * referenced for the entire IO. + */ + xfs_buf_rele(bp); + return error; } xfs_caddr_t @@ -1813,13 +1805,19 @@ __xfs_buf_delwri_submit( blk_start_plug(&plug); list_for_each_entry_safe(bp, n, io_list, b_list) { bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC | XBF_WRITE_FAIL); - bp->b_flags |= XBF_WRITE; + bp->b_flags |= XBF_WRITE | XBF_ASYNC; - if (!wait) { - bp->b_flags |= XBF_ASYNC; + /* + * we do all Io submission async. This means if we need to wait + * for IO completion we need to take an extra reference so the + * buffer is still valid on the other side. + */ + if (wait) + xfs_buf_hold(bp); + else list_del_init(&bp->b_list); - } - xfs_bdstrat_cb(bp); + + xfs_buf_submit(bp); } blk_finish_plug(&plug); @@ -1866,7 +1864,10 @@ xfs_buf_delwri_submit( bp = list_first_entry(&io_list, struct xfs_buf, b_list); list_del_init(&bp->b_list); - error2 = xfs_buf_iowait(bp); + + /* locking the buffer will wait for async IO completion. */ + xfs_buf_lock(bp); + error2 = bp->b_error; xfs_buf_relse(bp); if (!error) error = error2; diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index c753183900b3..82002c00af90 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -158,6 +158,7 @@ typedef struct xfs_buf { struct list_head b_lru; /* lru list */ spinlock_t b_lock; /* internal state lock */ unsigned int b_state; /* internal state flags */ + int b_io_error; /* internal IO error state */ wait_queue_head_t b_waiters; /* unpin waiters */ struct list_head b_list; struct xfs_perag *b_pag; /* contains rbtree root */ @@ -268,9 +269,9 @@ int xfs_buf_associate_memory(struct xfs_buf *bp, void *mem, size_t length); struct xfs_buf *xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks, int flags); -struct xfs_buf *xfs_buf_read_uncached(struct xfs_buftarg *target, - xfs_daddr_t daddr, size_t numblks, int flags, - const struct xfs_buf_ops *ops); +int xfs_buf_read_uncached(struct xfs_buftarg *target, xfs_daddr_t daddr, + size_t numblks, int flags, struct xfs_buf **bpp, + const struct xfs_buf_ops *ops); void xfs_buf_hold(struct xfs_buf *bp); /* Releasing Buffers */ @@ -286,18 +287,16 @@ extern void xfs_buf_unlock(xfs_buf_t *); /* Buffer Read and Write Routines */ extern int xfs_bwrite(struct xfs_buf *bp); -extern void xfs_buf_ioend(xfs_buf_t *, int); +extern void xfs_buf_ioend(struct xfs_buf *bp); extern void xfs_buf_ioerror(xfs_buf_t *, int); extern void xfs_buf_ioerror_alert(struct xfs_buf *, const char *func); -extern void xfs_buf_iorequest(xfs_buf_t *); -extern int xfs_buf_iowait(xfs_buf_t *); +extern void xfs_buf_submit(struct xfs_buf *bp); +extern int xfs_buf_submit_wait(struct xfs_buf *bp); extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *, xfs_buf_rw_t); #define xfs_buf_zero(bp, off, len) \ xfs_buf_iomove((bp), (off), (len), NULL, XBRW_ZERO) -extern int xfs_bioerror_relse(struct xfs_buf *); - /* Buffer Utility Routines */ extern xfs_caddr_t xfs_buf_offset(xfs_buf_t *, size_t); diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 30fa5db9aea8..f15969543326 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -491,7 +491,7 @@ xfs_buf_item_unpin( xfs_buf_ioerror(bp, -EIO); XFS_BUF_UNDONE(bp); xfs_buf_stale(bp); - xfs_buf_ioend(bp, 0); + xfs_buf_ioend(bp); } } @@ -1081,7 +1081,7 @@ xfs_buf_iodone_callbacks( * a way to shut the filesystem down if the writes keep failing. * * In practice we'll shut the filesystem down soon as non-transient - * erorrs tend to affect the whole device and a failing log write + * errors tend to affect the whole device and a failing log write * will make us give up. But we really ought to do better here. */ if (XFS_BUF_ISASYNC(bp)) { @@ -1094,7 +1094,7 @@ xfs_buf_iodone_callbacks( if (!(bp->b_flags & (XBF_STALE|XBF_WRITE_FAIL))) { bp->b_flags |= XBF_WRITE | XBF_ASYNC | XBF_DONE | XBF_WRITE_FAIL; - xfs_buf_iorequest(bp); + xfs_buf_submit(bp); } else { xfs_buf_relse(bp); } @@ -1115,7 +1115,7 @@ do_callbacks: xfs_buf_do_callbacks(bp); bp->b_fspriv = NULL; bp->b_iodone = NULL; - xfs_buf_ioend(bp, 0); + xfs_buf_ioend(bp); } /* diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 0fe36e4d5cef..eb596b419942 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -291,12 +291,22 @@ xfs_file_read_iter( if (inode->i_mapping->nrpages) { ret = filemap_write_and_wait_range( VFS_I(ip)->i_mapping, - pos, -1); + pos, pos + size - 1); if (ret) { xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL); return ret; } - truncate_pagecache_range(VFS_I(ip), pos, -1); + + /* + * Invalidate whole pages. This can return an error if + * we fail to invalidate a page, but this should never + * happen on XFS. Warn if it does fail. + */ + ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping, + pos >> PAGE_CACHE_SHIFT, + (pos + size - 1) >> PAGE_CACHE_SHIFT); + WARN_ON_ONCE(ret); + ret = 0; } xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL); } @@ -632,10 +642,19 @@ xfs_file_dio_aio_write( if (mapping->nrpages) { ret = filemap_write_and_wait_range(VFS_I(ip)->i_mapping, - pos, -1); + pos, pos + count - 1); if (ret) goto out; - truncate_pagecache_range(VFS_I(ip), pos, -1); + /* + * Invalidate whole pages. This can return an error if + * we fail to invalidate a page, but this should never + * happen on XFS. Warn if it does fail. + */ + ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping, + pos >> PAGE_CACHE_SHIFT, + (pos + count - 1) >> PAGE_CACHE_SHIFT); + WARN_ON_ONCE(ret); + ret = 0; } /* diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index f91de1ef05e1..c05ac8b70fa9 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -172,16 +172,11 @@ xfs_growfs_data_private( if ((error = xfs_sb_validate_fsb_count(&mp->m_sb, nb))) return error; dpct = pct - mp->m_sb.sb_imax_pct; - bp = xfs_buf_read_uncached(mp->m_ddev_targp, + error = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_FSB_TO_BB(mp, nb) - XFS_FSS_TO_BB(mp, 1), - XFS_FSS_TO_BB(mp, 1), 0, NULL); - if (!bp) - return -EIO; - if (bp->b_error) { - error = bp->b_error; - xfs_buf_relse(bp); + XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL); + if (error) return error; - } xfs_buf_relse(bp); new = nb; /* use new as a temporary here */ diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 2f63742a25f3..8ed049d1e332 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -3062,7 +3062,7 @@ cluster_corrupt_out: XFS_BUF_UNDONE(bp); xfs_buf_stale(bp); xfs_buf_ioerror(bp, -EIO); - xfs_buf_ioend(bp, 0); + xfs_buf_ioend(bp); } else { xfs_buf_stale(bp); xfs_buf_relse(bp); diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index d6afc9f144b1..24c926b6fe85 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1361,7 +1361,7 @@ xfs_ioc_setxflags( STATIC int xfs_getbmap_format(void **ap, struct getbmapx *bmv, int *full) { - struct getbmap __user *base = *ap; + struct getbmap __user *base = (struct getbmap __user *)*ap; /* copy only getbmap portion (not getbmapx) */ if (copy_to_user(base, bmv, sizeof(struct getbmap))) @@ -1392,7 +1392,7 @@ xfs_ioc_getbmap( bmx.bmv_iflags |= BMV_IF_NO_DMAPI_READ; error = xfs_getbmap(ip, &bmx, xfs_getbmap_format, - (struct getbmap *)arg+1); + (__force struct getbmap *)arg+1); if (error) return error; @@ -1405,7 +1405,7 @@ xfs_ioc_getbmap( STATIC int xfs_getbmapx_format(void **ap, struct getbmapx *bmv, int *full) { - struct getbmapx __user *base = *ap; + struct getbmapx __user *base = (struct getbmapx __user *)*ap; if (copy_to_user(base, bmv, sizeof(struct getbmapx))) return -EFAULT; @@ -1432,7 +1432,7 @@ xfs_ioc_getbmapx( return -EINVAL; error = xfs_getbmap(ip, &bmx, xfs_getbmapx_format, - (struct getbmapx *)arg+1); + (__force struct getbmapx *)arg+1); if (error) return error; diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index ca4fd5bd8522..fe88ef67f93a 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -1678,7 +1678,7 @@ xlog_bdstrat( if (iclog->ic_state & XLOG_STATE_IOERROR) { xfs_buf_ioerror(bp, -EIO); xfs_buf_stale(bp); - xfs_buf_ioend(bp, 0); + xfs_buf_ioend(bp); /* * It would seem logical to return EIO here, but we rely on * the log state machine to propagate I/O errors instead of @@ -1688,7 +1688,7 @@ xlog_bdstrat( return 0; } - xfs_buf_iorequest(bp); + xfs_buf_submit(bp); return 0; } @@ -3867,18 +3867,17 @@ xlog_state_ioerror( * This is called from xfs_force_shutdown, when we're forcibly * shutting down the filesystem, typically because of an IO error. * Our main objectives here are to make sure that: - * a. the filesystem gets marked 'SHUTDOWN' for all interested + * a. if !logerror, flush the logs to disk. Anything modified + * after this is ignored. + * b. the filesystem gets marked 'SHUTDOWN' for all interested * parties to find out, 'atomically'. - * b. those who're sleeping on log reservations, pinned objects and + * c. those who're sleeping on log reservations, pinned objects and * other resources get woken up, and be told the bad news. - * c. nothing new gets queued up after (a) and (b) are done. - * d. if !logerror, flush the iclogs to disk, then seal them off - * for business. + * d. nothing new gets queued up after (b) and (c) are done. * - * Note: for delayed logging the !logerror case needs to flush the regions - * held in memory out to the iclogs before flushing them to disk. This needs - * to be done before the log is marked as shutdown, otherwise the flush to the - * iclogs will fail. + * Note: for the !logerror case we need to flush the regions held in memory out + * to disk first. This needs to be done before the log is marked as shutdown, + * otherwise the iclog writes will fail. */ int xfs_log_force_umount( @@ -3910,16 +3909,16 @@ xfs_log_force_umount( ASSERT(XLOG_FORCED_SHUTDOWN(log)); return 1; } - retval = 0; /* - * Flush the in memory commit item list before marking the log as - * being shut down. We need to do it in this order to ensure all the - * completed transactions are flushed to disk with the xfs_log_force() - * call below. + * Flush all the completed transactions to disk before marking the log + * being shut down. We need to do it in this order to ensure that + * completed operations are safely on disk before we shut down, and that + * we don't have to issue any buffer IO after the shutdown flags are set + * to guarantee this. */ if (!logerror) - xlog_cil_force(log); + _xfs_log_force(mp, XFS_LOG_SYNC, NULL); /* * mark the filesystem and the as in a shutdown state and wake @@ -3931,18 +3930,11 @@ xfs_log_force_umount( XFS_BUF_DONE(mp->m_sb_bp); /* - * This flag is sort of redundant because of the mount flag, but - * it's good to maintain the separation between the log and the rest - * of XFS. + * Mark the log and the iclogs with IO error flags to prevent any + * further log IO from being issued or completed. */ log->l_flags |= XLOG_IO_ERROR; - - /* - * If we hit a log error, we want to mark all the iclogs IOERROR - * while we're still holding the loglock. - */ - if (logerror) - retval = xlog_state_ioerror(log); + retval = xlog_state_ioerror(log); spin_unlock(&log->l_icloglock); /* @@ -3955,19 +3947,6 @@ xfs_log_force_umount( xlog_grant_head_wake_all(&log->l_reserve_head); xlog_grant_head_wake_all(&log->l_write_head); - if (!(log->l_iclog->ic_state & XLOG_STATE_IOERROR)) { - ASSERT(!logerror); - /* - * Force the incore logs to disk before shutting the - * log down completely. - */ - _xfs_log_force(mp, XFS_LOG_SYNC, NULL); - - spin_lock(&log->l_icloglock); - retval = xlog_state_ioerror(log); - spin_unlock(&log->l_icloglock); - } - /* * Wake up everybody waiting on xfs_log_force. Wake the CIL push first * as if the log writes were completed. The abort handling in the log diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 29e101fc32c5..00cd7f3a8f59 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -193,12 +193,8 @@ xlog_bread_noalign( bp->b_io_length = nbblks; bp->b_error = 0; - if (XFS_FORCED_SHUTDOWN(log->l_mp)) - return -EIO; - - xfs_buf_iorequest(bp); - error = xfs_buf_iowait(bp); - if (error) + error = xfs_buf_submit_wait(bp); + if (error && !XFS_FORCED_SHUTDOWN(log->l_mp)) xfs_buf_ioerror_alert(bp, __func__); return error; } @@ -378,12 +374,14 @@ xlog_recover_iodone( * We're not going to bother about retrying * this during recovery. One strike! */ - xfs_buf_ioerror_alert(bp, __func__); - xfs_force_shutdown(bp->b_target->bt_mount, - SHUTDOWN_META_IO_ERROR); + if (!XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) { + xfs_buf_ioerror_alert(bp, __func__); + xfs_force_shutdown(bp->b_target->bt_mount, + SHUTDOWN_META_IO_ERROR); + } } bp->b_iodone = NULL; - xfs_buf_ioend(bp, 0); + xfs_buf_ioend(bp); } /* @@ -1445,160 +1443,6 @@ xlog_clear_stale_blocks( ****************************************************************************** */ -STATIC xlog_recover_t * -xlog_recover_find_tid( - struct hlist_head *head, - xlog_tid_t tid) -{ - xlog_recover_t *trans; - - hlist_for_each_entry(trans, head, r_list) { - if (trans->r_log_tid == tid) - return trans; - } - return NULL; -} - -STATIC void -xlog_recover_new_tid( - struct hlist_head *head, - xlog_tid_t tid, - xfs_lsn_t lsn) -{ - xlog_recover_t *trans; - - trans = kmem_zalloc(sizeof(xlog_recover_t), KM_SLEEP); - trans->r_log_tid = tid; - trans->r_lsn = lsn; - INIT_LIST_HEAD(&trans->r_itemq); - - INIT_HLIST_NODE(&trans->r_list); - hlist_add_head(&trans->r_list, head); -} - -STATIC void -xlog_recover_add_item( - struct list_head *head) -{ - xlog_recover_item_t *item; - - item = kmem_zalloc(sizeof(xlog_recover_item_t), KM_SLEEP); - INIT_LIST_HEAD(&item->ri_list); - list_add_tail(&item->ri_list, head); -} - -STATIC int -xlog_recover_add_to_cont_trans( - struct xlog *log, - struct xlog_recover *trans, - xfs_caddr_t dp, - int len) -{ - xlog_recover_item_t *item; - xfs_caddr_t ptr, old_ptr; - int old_len; - - if (list_empty(&trans->r_itemq)) { - /* finish copying rest of trans header */ - xlog_recover_add_item(&trans->r_itemq); - ptr = (xfs_caddr_t) &trans->r_theader + - sizeof(xfs_trans_header_t) - len; - memcpy(ptr, dp, len); /* d, s, l */ - return 0; - } - /* take the tail entry */ - item = list_entry(trans->r_itemq.prev, xlog_recover_item_t, ri_list); - - old_ptr = item->ri_buf[item->ri_cnt-1].i_addr; - old_len = item->ri_buf[item->ri_cnt-1].i_len; - - ptr = kmem_realloc(old_ptr, len+old_len, old_len, KM_SLEEP); - memcpy(&ptr[old_len], dp, len); /* d, s, l */ - item->ri_buf[item->ri_cnt-1].i_len += len; - item->ri_buf[item->ri_cnt-1].i_addr = ptr; - trace_xfs_log_recover_item_add_cont(log, trans, item, 0); - return 0; -} - -/* - * The next region to add is the start of a new region. It could be - * a whole region or it could be the first part of a new region. Because - * of this, the assumption here is that the type and size fields of all - * format structures fit into the first 32 bits of the structure. - * - * This works because all regions must be 32 bit aligned. Therefore, we - * either have both fields or we have neither field. In the case we have - * neither field, the data part of the region is zero length. We only have - * a log_op_header and can throw away the header since a new one will appear - * later. If we have at least 4 bytes, then we can determine how many regions - * will appear in the current log item. - */ -STATIC int -xlog_recover_add_to_trans( - struct xlog *log, - struct xlog_recover *trans, - xfs_caddr_t dp, - int len) -{ - xfs_inode_log_format_t *in_f; /* any will do */ - xlog_recover_item_t *item; - xfs_caddr_t ptr; - - if (!len) - return 0; - if (list_empty(&trans->r_itemq)) { - /* we need to catch log corruptions here */ - if (*(uint *)dp != XFS_TRANS_HEADER_MAGIC) { - xfs_warn(log->l_mp, "%s: bad header magic number", - __func__); - ASSERT(0); - return -EIO; - } - if (len == sizeof(xfs_trans_header_t)) - xlog_recover_add_item(&trans->r_itemq); - memcpy(&trans->r_theader, dp, len); /* d, s, l */ - return 0; - } - - ptr = kmem_alloc(len, KM_SLEEP); - memcpy(ptr, dp, len); - in_f = (xfs_inode_log_format_t *)ptr; - - /* take the tail entry */ - item = list_entry(trans->r_itemq.prev, xlog_recover_item_t, ri_list); - if (item->ri_total != 0 && - item->ri_total == item->ri_cnt) { - /* tail item is in use, get a new one */ - xlog_recover_add_item(&trans->r_itemq); - item = list_entry(trans->r_itemq.prev, - xlog_recover_item_t, ri_list); - } - - if (item->ri_total == 0) { /* first region to be added */ - if (in_f->ilf_size == 0 || - in_f->ilf_size > XLOG_MAX_REGIONS_IN_ITEM) { - xfs_warn(log->l_mp, - "bad number of regions (%d) in inode log format", - in_f->ilf_size); - ASSERT(0); - kmem_free(ptr); - return -EIO; - } - - item->ri_total = in_f->ilf_size; - item->ri_buf = - kmem_zalloc(item->ri_total * sizeof(xfs_log_iovec_t), - KM_SLEEP); - } - ASSERT(item->ri_total > item->ri_cnt); - /* Description region is ri_buf[0] */ - item->ri_buf[item->ri_cnt].i_addr = ptr; - item->ri_buf[item->ri_cnt].i_len = len; - item->ri_cnt++; - trace_xfs_log_recover_item_add(log, trans, item, 0); - return 0; -} - /* * Sort the log items in the transaction. * @@ -3254,31 +3098,6 @@ xlog_recover_do_icreate_pass2( return 0; } -/* - * Free up any resources allocated by the transaction - * - * Remember that EFIs, EFDs, and IUNLINKs are handled later. - */ -STATIC void -xlog_recover_free_trans( - struct xlog_recover *trans) -{ - xlog_recover_item_t *item, *n; - int i; - - list_for_each_entry_safe(item, n, &trans->r_itemq, ri_list) { - /* Free the regions in the item. */ - list_del(&item->ri_list); - for (i = 0; i < item->ri_cnt; i++) - kmem_free(item->ri_buf[i].i_addr); - /* Free the item itself */ - kmem_free(item->ri_buf); - kmem_free(item); - } - /* Free the transaction recover structure */ - kmem_free(trans); -} - STATIC void xlog_recover_buffer_ra_pass2( struct xlog *log, @@ -3528,22 +3347,309 @@ out: if (!list_empty(&done_list)) list_splice_init(&done_list, &trans->r_itemq); - xlog_recover_free_trans(trans); - error2 = xfs_buf_delwri_submit(&buffer_list); return error ? error : error2; } +STATIC void +xlog_recover_add_item( + struct list_head *head) +{ + xlog_recover_item_t *item; + + item = kmem_zalloc(sizeof(xlog_recover_item_t), KM_SLEEP); + INIT_LIST_HEAD(&item->ri_list); + list_add_tail(&item->ri_list, head); +} + STATIC int -xlog_recover_unmount_trans( - struct xlog *log) +xlog_recover_add_to_cont_trans( + struct xlog *log, + struct xlog_recover *trans, + xfs_caddr_t dp, + int len) +{ + xlog_recover_item_t *item; + xfs_caddr_t ptr, old_ptr; + int old_len; + + if (list_empty(&trans->r_itemq)) { + /* finish copying rest of trans header */ + xlog_recover_add_item(&trans->r_itemq); + ptr = (xfs_caddr_t) &trans->r_theader + + sizeof(xfs_trans_header_t) - len; + memcpy(ptr, dp, len); + return 0; + } + /* take the tail entry */ + item = list_entry(trans->r_itemq.prev, xlog_recover_item_t, ri_list); + + old_ptr = item->ri_buf[item->ri_cnt-1].i_addr; + old_len = item->ri_buf[item->ri_cnt-1].i_len; + + ptr = kmem_realloc(old_ptr, len+old_len, old_len, KM_SLEEP); + memcpy(&ptr[old_len], dp, len); + item->ri_buf[item->ri_cnt-1].i_len += len; + item->ri_buf[item->ri_cnt-1].i_addr = ptr; + trace_xfs_log_recover_item_add_cont(log, trans, item, 0); + return 0; +} + +/* + * The next region to add is the start of a new region. It could be + * a whole region or it could be the first part of a new region. Because + * of this, the assumption here is that the type and size fields of all + * format structures fit into the first 32 bits of the structure. + * + * This works because all regions must be 32 bit aligned. Therefore, we + * either have both fields or we have neither field. In the case we have + * neither field, the data part of the region is zero length. We only have + * a log_op_header and can throw away the header since a new one will appear + * later. If we have at least 4 bytes, then we can determine how many regions + * will appear in the current log item. + */ +STATIC int +xlog_recover_add_to_trans( + struct xlog *log, + struct xlog_recover *trans, + xfs_caddr_t dp, + int len) { - /* Do nothing now */ - xfs_warn(log->l_mp, "%s: Unmount LR", __func__); + xfs_inode_log_format_t *in_f; /* any will do */ + xlog_recover_item_t *item; + xfs_caddr_t ptr; + + if (!len) + return 0; + if (list_empty(&trans->r_itemq)) { + /* we need to catch log corruptions here */ + if (*(uint *)dp != XFS_TRANS_HEADER_MAGIC) { + xfs_warn(log->l_mp, "%s: bad header magic number", + __func__); + ASSERT(0); + return -EIO; + } + if (len == sizeof(xfs_trans_header_t)) + xlog_recover_add_item(&trans->r_itemq); + memcpy(&trans->r_theader, dp, len); + return 0; + } + + ptr = kmem_alloc(len, KM_SLEEP); + memcpy(ptr, dp, len); + in_f = (xfs_inode_log_format_t *)ptr; + + /* take the tail entry */ + item = list_entry(trans->r_itemq.prev, xlog_recover_item_t, ri_list); + if (item->ri_total != 0 && + item->ri_total == item->ri_cnt) { + /* tail item is in use, get a new one */ + xlog_recover_add_item(&trans->r_itemq); + item = list_entry(trans->r_itemq.prev, + xlog_recover_item_t, ri_list); + } + + if (item->ri_total == 0) { /* first region to be added */ + if (in_f->ilf_size == 0 || + in_f->ilf_size > XLOG_MAX_REGIONS_IN_ITEM) { + xfs_warn(log->l_mp, + "bad number of regions (%d) in inode log format", + in_f->ilf_size); + ASSERT(0); + kmem_free(ptr); + return -EIO; + } + + item->ri_total = in_f->ilf_size; + item->ri_buf = + kmem_zalloc(item->ri_total * sizeof(xfs_log_iovec_t), + KM_SLEEP); + } + ASSERT(item->ri_total > item->ri_cnt); + /* Description region is ri_buf[0] */ + item->ri_buf[item->ri_cnt].i_addr = ptr; + item->ri_buf[item->ri_cnt].i_len = len; + item->ri_cnt++; + trace_xfs_log_recover_item_add(log, trans, item, 0); return 0; } /* + * Free up any resources allocated by the transaction + * + * Remember that EFIs, EFDs, and IUNLINKs are handled later. + */ +STATIC void +xlog_recover_free_trans( + struct xlog_recover *trans) +{ + xlog_recover_item_t *item, *n; + int i; + + list_for_each_entry_safe(item, n, &trans->r_itemq, ri_list) { + /* Free the regions in the item. */ + list_del(&item->ri_list); + for (i = 0; i < item->ri_cnt; i++) + kmem_free(item->ri_buf[i].i_addr); + /* Free the item itself */ + kmem_free(item->ri_buf); + kmem_free(item); + } + /* Free the transaction recover structure */ + kmem_free(trans); +} + +/* + * On error or completion, trans is freed. + */ +STATIC int +xlog_recovery_process_trans( + struct xlog *log, + struct xlog_recover *trans, + xfs_caddr_t dp, + unsigned int len, + unsigned int flags, + int pass) +{ + int error = 0; + bool freeit = false; + + /* mask off ophdr transaction container flags */ + flags &= ~XLOG_END_TRANS; + if (flags & XLOG_WAS_CONT_TRANS) + flags &= ~XLOG_CONTINUE_TRANS; + + /* + * Callees must not free the trans structure. We'll decide if we need to + * free it or not based on the operation being done and it's result. + */ + switch (flags) { + /* expected flag values */ + case 0: + case XLOG_CONTINUE_TRANS: + error = xlog_recover_add_to_trans(log, trans, dp, len); + break; + case XLOG_WAS_CONT_TRANS: + error = xlog_recover_add_to_cont_trans(log, trans, dp, len); + break; + case XLOG_COMMIT_TRANS: + error = xlog_recover_commit_trans(log, trans, pass); + /* success or fail, we are now done with this transaction. */ + freeit = true; + break; + + /* unexpected flag values */ + case XLOG_UNMOUNT_TRANS: + /* just skip trans */ + xfs_warn(log->l_mp, "%s: Unmount LR", __func__); + freeit = true; + break; + case XLOG_START_TRANS: + default: + xfs_warn(log->l_mp, "%s: bad flag 0x%x", __func__, flags); + ASSERT(0); + error = -EIO; + break; + } + if (error || freeit) + xlog_recover_free_trans(trans); + return error; +} + +/* + * Lookup the transaction recovery structure associated with the ID in the + * current ophdr. If the transaction doesn't exist and the start flag is set in + * the ophdr, then allocate a new transaction for future ID matches to find. + * Either way, return what we found during the lookup - an existing transaction + * or nothing. + */ +STATIC struct xlog_recover * +xlog_recover_ophdr_to_trans( + struct hlist_head rhash[], + struct xlog_rec_header *rhead, + struct xlog_op_header *ohead) +{ + struct xlog_recover *trans; + xlog_tid_t tid; + struct hlist_head *rhp; + + tid = be32_to_cpu(ohead->oh_tid); + rhp = &rhash[XLOG_RHASH(tid)]; + hlist_for_each_entry(trans, rhp, r_list) { + if (trans->r_log_tid == tid) + return trans; + } + + /* + * skip over non-start transaction headers - we could be + * processing slack space before the next transaction starts + */ + if (!(ohead->oh_flags & XLOG_START_TRANS)) + return NULL; + + ASSERT(be32_to_cpu(ohead->oh_len) == 0); + + /* + * This is a new transaction so allocate a new recovery container to + * hold the recovery ops that will follow. + */ + trans = kmem_zalloc(sizeof(struct xlog_recover), KM_SLEEP); + trans->r_log_tid = tid; + trans->r_lsn = be64_to_cpu(rhead->h_lsn); + INIT_LIST_HEAD(&trans->r_itemq); + INIT_HLIST_NODE(&trans->r_list); + hlist_add_head(&trans->r_list, rhp); + + /* + * Nothing more to do for this ophdr. Items to be added to this new + * transaction will be in subsequent ophdr containers. + */ + return NULL; +} + +STATIC int +xlog_recover_process_ophdr( + struct xlog *log, + struct hlist_head rhash[], + struct xlog_rec_header *rhead, + struct xlog_op_header *ohead, + xfs_caddr_t dp, + xfs_caddr_t end, + int pass) +{ + struct xlog_recover *trans; + unsigned int len; + + /* Do we understand who wrote this op? */ + if (ohead->oh_clientid != XFS_TRANSACTION && + ohead->oh_clientid != XFS_LOG) { + xfs_warn(log->l_mp, "%s: bad clientid 0x%x", + __func__, ohead->oh_clientid); + ASSERT(0); + return -EIO; + } + + /* + * Check the ophdr contains all the data it is supposed to contain. + */ + len = be32_to_cpu(ohead->oh_len); + if (dp + len > end) { + xfs_warn(log->l_mp, "%s: bad length 0x%x", __func__, len); + WARN_ON(1); + return -EIO; + } + + trans = xlog_recover_ophdr_to_trans(rhash, rhead, ohead); + if (!trans) { + /* nothing to do, so skip over this ophdr */ + return 0; + } + + return xlog_recovery_process_trans(log, trans, dp, len, + ohead->oh_flags, pass); +} + +/* * There are two valid states of the r_state field. 0 indicates that the * transaction structure is in a normal state. We have either seen the * start of the transaction or the last operation we added was not a partial @@ -3560,86 +3666,30 @@ xlog_recover_process_data( xfs_caddr_t dp, int pass) { - xfs_caddr_t lp; + struct xlog_op_header *ohead; + xfs_caddr_t end; int num_logops; - xlog_op_header_t *ohead; - xlog_recover_t *trans; - xlog_tid_t tid; int error; - unsigned long hash; - uint flags; - lp = dp + be32_to_cpu(rhead->h_len); + end = dp + be32_to_cpu(rhead->h_len); num_logops = be32_to_cpu(rhead->h_num_logops); /* check the log format matches our own - else we can't recover */ if (xlog_header_check_recover(log->l_mp, rhead)) return -EIO; - while ((dp < lp) && num_logops) { - ASSERT(dp + sizeof(xlog_op_header_t) <= lp); - ohead = (xlog_op_header_t *)dp; - dp += sizeof(xlog_op_header_t); - if (ohead->oh_clientid != XFS_TRANSACTION && - ohead->oh_clientid != XFS_LOG) { - xfs_warn(log->l_mp, "%s: bad clientid 0x%x", - __func__, ohead->oh_clientid); - ASSERT(0); - return -EIO; - } - tid = be32_to_cpu(ohead->oh_tid); - hash = XLOG_RHASH(tid); - trans = xlog_recover_find_tid(&rhash[hash], tid); - if (trans == NULL) { /* not found; add new tid */ - if (ohead->oh_flags & XLOG_START_TRANS) - xlog_recover_new_tid(&rhash[hash], tid, - be64_to_cpu(rhead->h_lsn)); - } else { - if (dp + be32_to_cpu(ohead->oh_len) > lp) { - xfs_warn(log->l_mp, "%s: bad length 0x%x", - __func__, be32_to_cpu(ohead->oh_len)); - WARN_ON(1); - return -EIO; - } - flags = ohead->oh_flags & ~XLOG_END_TRANS; - if (flags & XLOG_WAS_CONT_TRANS) - flags &= ~XLOG_CONTINUE_TRANS; - switch (flags) { - case XLOG_COMMIT_TRANS: - error = xlog_recover_commit_trans(log, - trans, pass); - break; - case XLOG_UNMOUNT_TRANS: - error = xlog_recover_unmount_trans(log); - break; - case XLOG_WAS_CONT_TRANS: - error = xlog_recover_add_to_cont_trans(log, - trans, dp, - be32_to_cpu(ohead->oh_len)); - break; - case XLOG_START_TRANS: - xfs_warn(log->l_mp, "%s: bad transaction", - __func__); - ASSERT(0); - error = -EIO; - break; - case 0: - case XLOG_CONTINUE_TRANS: - error = xlog_recover_add_to_trans(log, trans, - dp, be32_to_cpu(ohead->oh_len)); - break; - default: - xfs_warn(log->l_mp, "%s: bad flag 0x%x", - __func__, flags); - ASSERT(0); - error = -EIO; - break; - } - if (error) { - xlog_recover_free_trans(trans); - return error; - } - } + while ((dp < end) && num_logops) { + + ohead = (struct xlog_op_header *)dp; + dp += sizeof(*ohead); + ASSERT(dp <= end); + + /* errors will abort recovery */ + error = xlog_recover_process_ophdr(log, rhash, rhead, ohead, + dp, end, pass); + if (error) + return error; + dp += be32_to_cpu(ohead->oh_len); num_logops--; } @@ -4400,16 +4450,12 @@ xlog_do_recover( XFS_BUF_UNASYNC(bp); bp->b_ops = &xfs_sb_buf_ops; - if (XFS_FORCED_SHUTDOWN(log->l_mp)) { - xfs_buf_relse(bp); - return -EIO; - } - - xfs_buf_iorequest(bp); - error = xfs_buf_iowait(bp); + error = xfs_buf_submit_wait(bp); if (error) { - xfs_buf_ioerror_alert(bp, __func__); - ASSERT(0); + if (!XFS_FORCED_SHUTDOWN(log->l_mp)) { + xfs_buf_ioerror_alert(bp, __func__); + ASSERT(0); + } xfs_buf_relse(bp); return error; } diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index fbf0384a466f..51435dbce9c4 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -61,8 +61,6 @@ static DEFINE_MUTEX(xfs_uuid_table_mutex); static int xfs_uuid_table_size; static uuid_t *xfs_uuid_table; -extern struct kset *xfs_kset; - /* * See if the UUID is unique among mounted XFS filesystems. * Mount fails if UUID is nil or a FS with the same UUID is already mounted. @@ -302,21 +300,15 @@ xfs_readsb( * access to the superblock. */ reread: - bp = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR, - BTOBB(sector_size), 0, buf_ops); - if (!bp) { - if (loud) - xfs_warn(mp, "SB buffer read failed"); - return -EIO; - } - if (bp->b_error) { - error = bp->b_error; + error = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR, + BTOBB(sector_size), 0, &bp, buf_ops); + if (error) { if (loud) xfs_warn(mp, "SB validate failed with error %d.", error); /* bad CRC means corrupted metadata */ if (error == -EFSBADCRC) error = -EFSCORRUPTED; - goto release_buf; + return error; } /* @@ -546,40 +538,43 @@ xfs_set_inoalignment(xfs_mount_t *mp) * Check that the data (and log if separate) is an ok size. */ STATIC int -xfs_check_sizes(xfs_mount_t *mp) +xfs_check_sizes( + struct xfs_mount *mp) { - xfs_buf_t *bp; + struct xfs_buf *bp; xfs_daddr_t d; + int error; d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks); if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_dblocks) { xfs_warn(mp, "filesystem size mismatch detected"); return -EFBIG; } - bp = xfs_buf_read_uncached(mp->m_ddev_targp, + error = xfs_buf_read_uncached(mp->m_ddev_targp, d - XFS_FSS_TO_BB(mp, 1), - XFS_FSS_TO_BB(mp, 1), 0, NULL); - if (!bp) { + XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL); + if (error) { xfs_warn(mp, "last sector read failed"); - return -EIO; + return error; } xfs_buf_relse(bp); - if (mp->m_logdev_targp != mp->m_ddev_targp) { - d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks); - if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_logblocks) { - xfs_warn(mp, "log size mismatch detected"); - return -EFBIG; - } - bp = xfs_buf_read_uncached(mp->m_logdev_targp, + if (mp->m_logdev_targp == mp->m_ddev_targp) + return 0; + + d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks); + if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_logblocks) { + xfs_warn(mp, "log size mismatch detected"); + return -EFBIG; + } + error = xfs_buf_read_uncached(mp->m_logdev_targp, d - XFS_FSB_TO_BB(mp, 1), - XFS_FSB_TO_BB(mp, 1), 0, NULL); - if (!bp) { - xfs_warn(mp, "log device read failed"); - return -EIO; - } - xfs_buf_relse(bp); + XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL); + if (error) { + xfs_warn(mp, "log device read failed"); + return error; } + xfs_buf_relse(bp); return 0; } @@ -729,7 +724,6 @@ xfs_mountfs( xfs_set_maxicount(mp); - mp->m_kobj.kobject.kset = xfs_kset; error = xfs_sysfs_init(&mp->m_kobj, &xfs_mp_ktype, NULL, mp->m_fsname); if (error) goto out; diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 10232102b4a6..d68f23021af3 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -434,6 +434,7 @@ xfs_qm_dquot_isolate( struct list_head *item, spinlock_t *lru_lock, void *arg) + __releases(lru_lock) __acquires(lru_lock) { struct xfs_dquot *dqp = container_of(item, struct xfs_dquot, q_lru); diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index d45aebe04dde..e1175ea9b551 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -921,16 +921,11 @@ xfs_growfs_rt( /* * Read in the last block of the device, make sure it exists. */ - bp = xfs_buf_read_uncached(mp->m_rtdev_targp, + error = xfs_buf_read_uncached(mp->m_rtdev_targp, XFS_FSB_TO_BB(mp, nrblocks - 1), - XFS_FSB_TO_BB(mp, 1), 0, NULL); - if (!bp) - return -EIO; - if (bp->b_error) { - error = bp->b_error; - xfs_buf_relse(bp); + XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL); + if (error) return error; - } xfs_buf_relse(bp); /* @@ -1184,11 +1179,12 @@ xfs_rtallocate_extent( */ int /* error */ xfs_rtmount_init( - xfs_mount_t *mp) /* file system mount structure */ + struct xfs_mount *mp) /* file system mount structure */ { - xfs_buf_t *bp; /* buffer for last block of subvolume */ - xfs_daddr_t d; /* address of last block of subvolume */ - xfs_sb_t *sbp; /* filesystem superblock copy in mount */ + struct xfs_buf *bp; /* buffer for last block of subvolume */ + struct xfs_sb *sbp; /* filesystem superblock copy in mount */ + xfs_daddr_t d; /* address of last block of subvolume */ + int error; sbp = &mp->m_sb; if (sbp->sb_rblocks == 0) @@ -1214,14 +1210,12 @@ xfs_rtmount_init( (unsigned long long) mp->m_sb.sb_rblocks); return -EFBIG; } - bp = xfs_buf_read_uncached(mp->m_rtdev_targp, + error = xfs_buf_read_uncached(mp->m_rtdev_targp, d - XFS_FSB_TO_BB(mp, 1), - XFS_FSB_TO_BB(mp, 1), 0, NULL); - if (!bp || bp->b_error) { + XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL); + if (error) { xfs_warn(mp, "realtime device size check failed"); - if (bp) - xfs_buf_relse(bp); - return -EIO; + return error; } xfs_buf_relse(bp); return 0; diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index dcd4b93dccdc..9f622feda6a4 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -63,7 +63,7 @@ static const struct super_operations xfs_super_operations; static kmem_zone_t *xfs_ioend_zone; mempool_t *xfs_ioend_pool; -struct kset *xfs_kset; /* top-level xfs sysfs dir */ +static struct kset *xfs_kset; /* top-level xfs sysfs dir */ #ifdef DEBUG static struct xfs_kobj xfs_dbg_kobj; /* global debug sysfs attrs */ #endif @@ -1411,6 +1411,7 @@ xfs_fs_fill_super( atomic_set(&mp->m_active_trans, 0); INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker); INIT_DELAYED_WORK(&mp->m_eofblocks_work, xfs_eofblocks_worker); + mp->m_kobj.kobject.kset = xfs_kset; mp->m_super = sb; sb->s_fs_info = mp; diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 152f82782630..51372e34d988 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -349,7 +349,8 @@ DEFINE_BUF_EVENT(xfs_buf_free); DEFINE_BUF_EVENT(xfs_buf_hold); DEFINE_BUF_EVENT(xfs_buf_rele); DEFINE_BUF_EVENT(xfs_buf_iodone); -DEFINE_BUF_EVENT(xfs_buf_iorequest); +DEFINE_BUF_EVENT(xfs_buf_submit); +DEFINE_BUF_EVENT(xfs_buf_submit_wait); DEFINE_BUF_EVENT(xfs_buf_bawrite); DEFINE_BUF_EVENT(xfs_buf_lock); DEFINE_BUF_EVENT(xfs_buf_lock_done); diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c index 96c898e7ac9a..e2b2216b1635 100644 --- a/fs/xfs/xfs_trans_buf.c +++ b/fs/xfs/xfs_trans_buf.c @@ -318,20 +318,10 @@ xfs_trans_read_buf_map( XFS_BUF_READ(bp); bp->b_ops = ops; - /* - * XXX(hch): clean up the error handling here to be less - * of a mess.. - */ - if (XFS_FORCED_SHUTDOWN(mp)) { - trace_xfs_bdstrat_shut(bp, _RET_IP_); - xfs_bioerror_relse(bp); - } else { - xfs_buf_iorequest(bp); - } - - error = xfs_buf_iowait(bp); + error = xfs_buf_submit_wait(bp); if (error) { - xfs_buf_ioerror_alert(bp, __func__); + if (!XFS_FORCED_SHUTDOWN(mp)) + xfs_buf_ioerror_alert(bp, __func__); xfs_buf_relse(bp); /* * We can gracefully recover from most read |