From 7dc576158d7e5cdff3349f78598fdb4080536342 Mon Sep 17 00:00:00 2001 From: Peter Huewe Date: Mon, 21 Feb 2011 21:01:42 -0500 Subject: ext4: Fix sparse warning: Using plain integer as NULL pointer This patch fixes the warning "Using plain integer as NULL pointer", generated by sparse, by replacing the offending 0s with NULL. Signed-off-by: Peter Huewe Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 9f7f9e49914f..c6c6b7fcb455 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -720,7 +720,7 @@ allocated: return ret; failed_out: for (i = 0; i < index; i++) - ext4_free_blocks(handle, inode, 0, new_blocks[i], 1, 0); + ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0); return ret; } @@ -823,20 +823,20 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode, return err; failed: /* Allocation failed, free what we already allocated */ - ext4_free_blocks(handle, inode, 0, new_blocks[0], 1, 0); + 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, 0, new_blocks[i], 1, + 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, 0, new_blocks[i], 1, 0); + ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0); - ext4_free_blocks(handle, inode, 0, new_blocks[i], num, 0); + ext4_free_blocks(handle, inode, NULL, new_blocks[i], num, 0); return err; } @@ -924,7 +924,7 @@ err_out: ext4_free_blocks(handle, inode, where[i].bh, 0, 1, EXT4_FREE_BLOCKS_FORGET); } - ext4_free_blocks(handle, inode, 0, le32_to_cpu(where[num].key), + ext4_free_blocks(handle, inode, NULL, le32_to_cpu(where[num].key), blks, 0); return err; @@ -4228,7 +4228,7 @@ static int ext4_clear_blocks(handle_t *handle, struct inode *inode, for (p = first; p < last; p++) *p = 0; - ext4_free_blocks(handle, inode, 0, block_to_free, count, flags); + ext4_free_blocks(handle, inode, NULL, block_to_free, count, flags); return 0; } @@ -4416,7 +4416,7 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode, * transaction where the data blocks are * actually freed. */ - ext4_free_blocks(handle, inode, 0, nr, 1, + ext4_free_blocks(handle, inode, NULL, nr, 1, EXT4_FREE_BLOCKS_METADATA| EXT4_FREE_BLOCKS_FORGET); @@ -4875,7 +4875,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) return inode; ei = EXT4_I(inode); - iloc.bh = 0; + iloc.bh = NULL; ret = __ext4_get_inode_loc(inode, &iloc, 0); if (ret < 0) -- cgit v1.2.3-70-g09d2 From e0fd9b90765f604374c42de8ac59d6584afce264 Mon Sep 17 00:00:00 2001 From: Curt Wohlgemuth Date: Sat, 26 Feb 2011 12:25:52 -0500 Subject: ext4: mark multi-page IO complete on mapping failure In mpage_da_map_and_submit(), if we have a delayed block allocation failure from ext4_map_blocks(), we need to mark the IO as complete, by setting mpd->io_done = 1; Otherwise, we could end up submitting the pages in an outer loop; since they are unlocked on mapping failure in ext4_da_block_invalidatepages(), this will cause a bug check in mpage_da_submit_io(). I tested this by injected failures into ext4_map_blocks(). Without this patch, a simple fsstress run will bug check; with the patch, it works fine. Signed-off-by: Curt Wohlgemuth Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index c6c6b7fcb455..fd369dbce6af 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2314,6 +2314,9 @@ static void mpage_da_map_and_submit(struct mpage_da_data *mpd) /* invalidate all the pages */ ext4_da_block_invalidatepages(mpd, next, mpd->b_size >> mpd->inode->i_blkbits); + + /* Mark this page range as having been completed */ + mpd->io_done = 1; return; } BUG_ON(blks == 0); -- cgit v1.2.3-70-g09d2 From c7f5938adce6727b9d17785f289c1146bd88d678 Mon Sep 17 00:00:00 2001 From: Curt Wohlgemuth Date: Sat, 26 Feb 2011 12:27:52 -0500 Subject: ext4: fix ext4_da_block_invalidatepages() to handle page range properly If ext4_da_block_invalidatepages() is called because of a failure from ext4_map_blocks() in mpage_da_map_and_submit(), it's supposed to clean up -- including unlock -- all the pages in the mpd structure. But these values may not match up, even on a system in which block size == page size: mpd->b_blocknr != mpd->first_page mpd->b_size != (mpd->next_page - mpd->first_page) ext4_da_block_invalidatepages() has been using b_blocknr and b_size; this patch changes it to use first_page and next_page. Tested: I injected a small number (5%) of failures in ext4_map_blocks() in the case that the flags contain EXT4_GET_BLOCKS_DELALLOC_RESERVE, and ran fsstress on this kernel. Without this patch, I got hung tasks every time. With this patch, I see no hangs in many runs of fsstress. Signed-off-by: Curt Wohlgemuth Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index fd369dbce6af..e878c3a7aaf0 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2165,8 +2165,7 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd, return ret; } -static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd, - sector_t logical, long blk_cnt) +static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd) { int nr_pages, i; pgoff_t index, end; @@ -2174,9 +2173,8 @@ static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd, struct inode *inode = mpd->inode; struct address_space *mapping = inode->i_mapping; - index = logical >> (PAGE_CACHE_SHIFT - inode->i_blkbits); - end = (logical + blk_cnt - 1) >> - (PAGE_CACHE_SHIFT - inode->i_blkbits); + index = mpd->first_page; + end = mpd->next_page - 1; while (index <= end) { nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE); if (nr_pages == 0) @@ -2312,8 +2310,7 @@ static void mpage_da_map_and_submit(struct mpage_da_data *mpd) ext4_print_free_blocks(mpd->inode); } /* invalidate all the pages */ - ext4_da_block_invalidatepages(mpd, next, - mpd->b_size >> mpd->inode->i_blkbits); + ext4_da_block_invalidatepages(mpd); /* Mark this page range as having been completed */ mpd->io_done = 1; -- cgit v1.2.3-70-g09d2 From 8eb9e5ce211de1b98bc84e93258b7db0860a103c Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 26 Feb 2011 14:07:31 -0500 Subject: ext4: fold __mpage_da_writepage() into write_cache_pages_da() Fold the __mpage_da_writepage() function into write_cache_pages_da(). This will give us opportunities to clean up and simplify the resulting code. Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 206 +++++++++++++++++++++++++------------------------------- 1 file changed, 91 insertions(+), 115 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index e878c3a7aaf0..fcd08ca0643b 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2437,102 +2437,6 @@ static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh) return (buffer_delay(bh) || buffer_unwritten(bh)) && buffer_dirty(bh); } -/* - * __mpage_da_writepage - finds extent of pages and blocks - * - * @page: page to consider - * @wbc: not used, we just follow rules - * @data: context - * - * The function finds extents of pages and scan them for all blocks. - */ -static int __mpage_da_writepage(struct page *page, - struct writeback_control *wbc, - struct mpage_da_data *mpd) -{ - struct inode *inode = mpd->inode; - struct buffer_head *bh, *head; - sector_t logical; - - /* - * Can we merge this page to current extent? - */ - if (mpd->next_page != page->index) { - /* - * Nope, we can't. So, we map non-allocated blocks - * and start IO on them - */ - if (mpd->next_page != mpd->first_page) { - mpage_da_map_and_submit(mpd); - /* - * skip rest of the page in the page_vec - */ - redirty_page_for_writepage(wbc, page); - unlock_page(page); - return MPAGE_DA_EXTENT_TAIL; - } - - /* - * Start next extent of pages ... - */ - mpd->first_page = page->index; - - /* - * ... and blocks - */ - mpd->b_size = 0; - mpd->b_state = 0; - mpd->b_blocknr = 0; - } - - mpd->next_page = page->index + 1; - logical = (sector_t) page->index << - (PAGE_CACHE_SHIFT - inode->i_blkbits); - - if (!page_has_buffers(page)) { - mpage_add_bh_to_extent(mpd, logical, PAGE_CACHE_SIZE, - (1 << BH_Dirty) | (1 << BH_Uptodate)); - if (mpd->io_done) - return MPAGE_DA_EXTENT_TAIL; - } else { - /* - * Page with regular buffer heads, just add all dirty ones - */ - head = page_buffers(page); - bh = head; - do { - BUG_ON(buffer_locked(bh)); - /* - * We need to try to allocate - * unmapped blocks in the same page. - * Otherwise we won't make progress - * with the page in ext4_writepage - */ - if (ext4_bh_delay_or_unwritten(NULL, bh)) { - mpage_add_bh_to_extent(mpd, logical, - bh->b_size, - bh->b_state); - if (mpd->io_done) - return MPAGE_DA_EXTENT_TAIL; - } else if (buffer_dirty(bh) && (buffer_mapped(bh))) { - /* - * mapped dirty buffer. We need to update - * the b_state because we look at - * b_state in mpage_da_map_blocks. We don't - * update b_size because if we find an - * unmapped buffer_head later we need to - * use the b_state flag of that buffer_head. - */ - if (mpd->b_size == 0) - mpd->b_state = bh->b_state & BH_FLAGS; - } - logical++; - } while ((bh = bh->b_this_page) != head); - } - - return 0; -} - /* * This is a special get_blocks_t callback which is used by * ext4_da_write_begin(). It will either return mapped block or @@ -2811,18 +2715,17 @@ static int ext4_da_writepages_trans_blocks(struct inode *inode) /* * write_cache_pages_da - walk the list of dirty pages of the given - * address space and call the callback function (which usually writes - * the pages). - * - * This is a forked version of write_cache_pages(). Differences: - * Range cyclic is ignored. - * no_nrwrite_index_update is always presumed true + * address space and accumulate pages that need writing, and call + * mpage_da_map_and_submit to map the pages and then write them. */ static int write_cache_pages_da(struct address_space *mapping, struct writeback_control *wbc, struct mpage_da_data *mpd, pgoff_t *done_index) { + struct inode *inode = mpd->inode; + struct buffer_head *bh, *head; + sector_t logical; int ret = 0; int done = 0; struct pagevec pvec; @@ -2899,17 +2802,90 @@ continue_unlock: if (!clear_page_dirty_for_io(page)) goto continue_unlock; - ret = __mpage_da_writepage(page, wbc, mpd); - if (unlikely(ret)) { - if (ret == AOP_WRITEPAGE_ACTIVATE) { + /* BEGIN __mpage_da_writepage */ + + /* + * Can we merge this page to current extent? + */ + if (mpd->next_page != page->index) { + /* + * Nope, we can't. So, we map + * non-allocated blocks and start IO + * on them + */ + if (mpd->next_page != mpd->first_page) { + mpage_da_map_and_submit(mpd); + /* + * skip rest of the page in the page_vec + */ + redirty_page_for_writepage(wbc, page); unlock_page(page); - ret = 0; - } else { - done = 1; - break; + ret = MPAGE_DA_EXTENT_TAIL; + goto out; } + + /* + * Start next extent of pages and blocks + */ + mpd->first_page = page->index; + mpd->b_size = 0; + mpd->b_state = 0; + mpd->b_blocknr = 0; + } + + mpd->next_page = page->index + 1; + logical = (sector_t) page->index << + (PAGE_CACHE_SHIFT - inode->i_blkbits); + + if (!page_has_buffers(page)) { + mpage_add_bh_to_extent(mpd, logical, PAGE_CACHE_SIZE, + (1 << BH_Dirty) | (1 << BH_Uptodate)); + if (mpd->io_done) { + ret = MPAGE_DA_EXTENT_TAIL; + goto out; + } + } else { + /* + * Page with regular buffer heads, just add all dirty ones + */ + head = page_buffers(page); + bh = head; + do { + BUG_ON(buffer_locked(bh)); + /* + * We need to try to allocate + * unmapped blocks in the same page. + * Otherwise we won't make progress + * with the page in ext4_writepage + */ + if (ext4_bh_delay_or_unwritten(NULL, bh)) { + mpage_add_bh_to_extent(mpd, logical, + bh->b_size, + bh->b_state); + if (mpd->io_done) { + ret = MPAGE_DA_EXTENT_TAIL; + goto out; + } + } else if (buffer_dirty(bh) && (buffer_mapped(bh))) { + /* + * mapped dirty buffer. We need to update + * the b_state because we look at + * b_state in mpage_da_map_blocks. We don't + * update b_size because if we find an + * unmapped buffer_head later we need to + * use the b_state flag of that buffer_head. + */ + if (mpd->b_size == 0) + mpd->b_state = bh->b_state & BH_FLAGS; + } + logical++; + } while ((bh = bh->b_this_page) != head); } + ret = 0; + + /* END __mpage_da_writepage */ + if (nr_to_write > 0) { nr_to_write--; if (nr_to_write == 0 && @@ -2933,6 +2909,10 @@ continue_unlock: cond_resched(); } return ret; +out: + pagevec_release(&pvec); + cond_resched(); + return ret; } @@ -3059,13 +3039,9 @@ retry: } /* - * Now call __mpage_da_writepage to find the next + * Now call write_cache_pages_da() to find the next * contiguous region of logical blocks that need - * blocks to be allocated by ext4. We don't actually - * submit the blocks for I/O here, even though - * write_cache_pages thinks it will, and will set the - * pages as clean for write before calling - * __mpage_da_writepage(). + * blocks to be allocated by ext4 and submit them. */ mpd.b_size = 0; mpd.b_state = 0; -- cgit v1.2.3-70-g09d2 From 4f01b02c8c4e4111bd1adbcafb5741e8e991f5fd Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 26 Feb 2011 14:07:37 -0500 Subject: ext4: simple cleanups to write_cache_pages_da() Eliminate duplicate code, unneeded variables, etc., to make it easier to understand the code. No behavioral changes were made in this patch. Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 115 +++++++++++++++++++++++--------------------------------- 1 file changed, 48 insertions(+), 67 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index fcd08ca0643b..1e718e87f466 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2723,17 +2723,14 @@ static int write_cache_pages_da(struct address_space *mapping, struct mpage_da_data *mpd, pgoff_t *done_index) { - struct inode *inode = mpd->inode; - struct buffer_head *bh, *head; - sector_t logical; - int ret = 0; - int done = 0; - struct pagevec pvec; - unsigned nr_pages; - pgoff_t index; - pgoff_t end; /* Inclusive */ - long nr_to_write = wbc->nr_to_write; - int tag; + struct buffer_head *bh, *head; + struct inode *inode = mpd->inode; + struct pagevec pvec; + unsigned int nr_pages; + sector_t logical; + pgoff_t index, end; + long nr_to_write = wbc->nr_to_write; + int i, tag, ret = 0; pagevec_init(&pvec, 0); index = wbc->range_start >> PAGE_CACHE_SHIFT; @@ -2745,13 +2742,11 @@ static int write_cache_pages_da(struct address_space *mapping, tag = PAGECACHE_TAG_DIRTY; *done_index = index; - while (!done && (index <= end)) { - int i; - + while (index <= end) { nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag, min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); if (nr_pages == 0) - break; + return 0; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; @@ -2763,47 +2758,37 @@ static int write_cache_pages_da(struct address_space *mapping, * mapping. However, page->index will not change * because we have a reference on the page. */ - if (page->index > end) { - done = 1; - break; - } + if (page->index > end) + goto out; *done_index = page->index + 1; lock_page(page); /* - * Page truncated or invalidated. We can freely skip it - * then, even for data integrity operations: the page - * has disappeared concurrently, so there could be no - * real expectation of this data interity operation - * even if there is now a new, dirty page at the same - * pagecache address. + * If the page is no longer dirty, or its + * mapping no longer corresponds to inode we + * are writing (which means it has been + * truncated or invalidated), or the page is + * already under writeback and we are not + * doing a data integrity writeback, skip the page */ - if (unlikely(page->mapping != mapping)) { -continue_unlock: + if (!PageDirty(page) || + (PageWriteback(page) && + (wbc->sync_mode == WB_SYNC_NONE)) || + unlikely(page->mapping != mapping)) { + continue_unlock: unlock_page(page); continue; } - if (!PageDirty(page)) { - /* someone wrote it for us */ - goto continue_unlock; - } - - if (PageWriteback(page)) { - if (wbc->sync_mode != WB_SYNC_NONE) - wait_on_page_writeback(page); - else - goto continue_unlock; - } + if (PageWriteback(page)) + wait_on_page_writeback(page); BUG_ON(PageWriteback(page)); if (!clear_page_dirty_for_io(page)) goto continue_unlock; - /* BEGIN __mpage_da_writepage */ - /* * Can we merge this page to current extent? */ @@ -2820,8 +2805,7 @@ continue_unlock: */ redirty_page_for_writepage(wbc, page); unlock_page(page); - ret = MPAGE_DA_EXTENT_TAIL; - goto out; + goto ret_extent_tail; } /* @@ -2838,15 +2822,15 @@ continue_unlock: (PAGE_CACHE_SHIFT - inode->i_blkbits); if (!page_has_buffers(page)) { - mpage_add_bh_to_extent(mpd, logical, PAGE_CACHE_SIZE, + mpage_add_bh_to_extent(mpd, logical, + PAGE_CACHE_SIZE, (1 << BH_Dirty) | (1 << BH_Uptodate)); - if (mpd->io_done) { - ret = MPAGE_DA_EXTENT_TAIL; - goto out; - } + if (mpd->io_done) + goto ret_extent_tail; } else { /* - * Page with regular buffer heads, just add all dirty ones + * Page with regular buffer heads, + * just add all dirty ones */ head = page_buffers(page); bh = head; @@ -2862,18 +2846,19 @@ continue_unlock: mpage_add_bh_to_extent(mpd, logical, bh->b_size, bh->b_state); - if (mpd->io_done) { - ret = MPAGE_DA_EXTENT_TAIL; - goto out; - } + if (mpd->io_done) + goto ret_extent_tail; } else if (buffer_dirty(bh) && (buffer_mapped(bh))) { /* - * mapped dirty buffer. We need to update - * the b_state because we look at - * b_state in mpage_da_map_blocks. We don't - * update b_size because if we find an - * unmapped buffer_head later we need to - * use the b_state flag of that buffer_head. + * mapped dirty buffer. We need + * to update the b_state + * because we look at b_state + * in mpage_da_map_blocks. We + * don't update b_size because + * if we find an unmapped + * buffer_head later we need to + * use the b_state flag of that + * buffer_head. */ if (mpd->b_size == 0) mpd->b_state = bh->b_state & BH_FLAGS; @@ -2882,14 +2867,10 @@ continue_unlock: } while ((bh = bh->b_this_page) != head); } - ret = 0; - - /* END __mpage_da_writepage */ - if (nr_to_write > 0) { nr_to_write--; if (nr_to_write == 0 && - wbc->sync_mode == WB_SYNC_NONE) { + wbc->sync_mode == WB_SYNC_NONE) /* * We stop writing back only if we are * not doing integrity sync. In case of @@ -2900,15 +2881,15 @@ continue_unlock: * pages, but have not synced all of the * old dirty pages. */ - done = 1; - break; - } + goto out; } } pagevec_release(&pvec); cond_resched(); } - return ret; + return 0; +ret_extent_tail: + ret = MPAGE_DA_EXTENT_TAIL; out: pagevec_release(&pvec); cond_resched(); -- cgit v1.2.3-70-g09d2 From 9749895644a817cfd28a535bc3ae60e4267bdc50 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 26 Feb 2011 14:08:01 -0500 Subject: ext4: clear the dirty bit for a page in writeback at the last minute Move when we call clear_page_dirty_for_io() to just before we actually write the page. This simplifies the code somewhat, and avoids marking pages as clean and then needing to remark them as dirty later. Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 28 +++++++++++----------------- 1 file changed, 11 insertions(+), 17 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 1e718e87f466..ae6e2f43d873 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2060,7 +2060,7 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd, if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { - int commit_write = 0, redirty_page = 0; + int commit_write = 0, skip_page = 0; struct page *page = pvec.pages[i]; index = page->index; @@ -2086,14 +2086,12 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd, * If the page does not have buffers (for * whatever reason), try to create them using * __block_write_begin. If this fails, - * redirty the page and move on. + * skip the page and move on. */ if (!page_has_buffers(page)) { if (__block_write_begin(page, 0, len, noalloc_get_block_write)) { - redirty_page: - redirty_page_for_writepage(mpd->wbc, - page); + skip_page: unlock_page(page); continue; } @@ -2104,7 +2102,7 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd, block_start = 0; do { if (!bh) - goto redirty_page; + goto skip_page; if (map && (cur_logical >= map->m_lblk) && (cur_logical <= (map->m_lblk + (map->m_len - 1)))) { @@ -2120,22 +2118,23 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd, clear_buffer_unwritten(bh); } - /* redirty page if block allocation undone */ + /* skip page if block allocation undone */ if (buffer_delay(bh) || buffer_unwritten(bh)) - redirty_page = 1; + skip_page = 1; bh = bh->b_this_page; block_start += bh->b_size; cur_logical++; pblock++; } while (bh != page_bufs); - if (redirty_page) - goto redirty_page; + if (skip_page) + goto skip_page; if (commit_write) /* mark the buffer_heads as dirty & uptodate */ block_commit_write(page, 0, len); + clear_page_dirty_for_io(page); /* * Delalloc doesn't support data journalling, * but eventually maybe we'll lift this @@ -2277,9 +2276,8 @@ static void mpage_da_map_and_submit(struct mpage_da_data *mpd) err = blks; /* * If get block returns EAGAIN or ENOSPC and there - * appears to be free blocks we will call - * ext4_writepage() for all of the pages which will - * just redirty the pages. + * appears to be free blocks we will just let + * mpage_da_submit_io() unlock all of the pages. */ if (err == -EAGAIN) goto submit_io; @@ -2777,7 +2775,6 @@ static int write_cache_pages_da(struct address_space *mapping, (PageWriteback(page) && (wbc->sync_mode == WB_SYNC_NONE)) || unlikely(page->mapping != mapping)) { - continue_unlock: unlock_page(page); continue; } @@ -2786,8 +2783,6 @@ static int write_cache_pages_da(struct address_space *mapping, wait_on_page_writeback(page); BUG_ON(PageWriteback(page)); - if (!clear_page_dirty_for_io(page)) - goto continue_unlock; /* * Can we merge this page to current extent? @@ -2803,7 +2798,6 @@ static int write_cache_pages_da(struct address_space *mapping, /* * skip rest of the page in the page_vec */ - redirty_page_for_writepage(wbc, page); unlock_page(page); goto ret_extent_tail; } -- cgit v1.2.3-70-g09d2 From ee6ecbcc5d73672217fdea420d182ecb0cdf310c Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 26 Feb 2011 14:08:11 -0500 Subject: ext4: remove page_skipped hackery in ext4_da_writepages() Because the ext4 page writeback codepath had been prematurely calling clear_page_dirty_for_io(), if it turned out that a particular page couldn't be written out during a particular pass of write_cache_pages_da(), the page would have to get redirtied by calling redirty_pages_for_writeback(). Not only was this wasted work, but redirty_page_for_writeback() would increment wbc->pages_skipped to signal to writeback_sb_inodes() that buffers were locked, and that it should skip this inode until later. Since this signal was incorrect in ext4's case --- which was caused by ext4's historically incorrect use of write_cache_pages() --- ext4_da_writepages() saved and restored wbc->skipped_pages to avoid confusing writeback_sb_inodes(). Now that we've fixed ext4 to call clear_page_dirty_for_io() right before initiating the page I/O, we can nuke the page_skipped save/restore hackery, and breathe a sigh of relief. Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index ae6e2f43d873..617c9cbba182 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2900,7 +2900,6 @@ static int ext4_da_writepages(struct address_space *mapping, struct mpage_da_data mpd; struct inode *inode = mapping->host; int pages_written = 0; - long pages_skipped; unsigned int max_pages; int range_cyclic, cycled = 1, io_done = 0; int needed_blocks, ret = 0; @@ -2986,8 +2985,6 @@ static int ext4_da_writepages(struct address_space *mapping, mpd.wbc = wbc; mpd.inode = mapping->host; - pages_skipped = wbc->pages_skipped; - retry: if (wbc->sync_mode == WB_SYNC_ALL) tag_pages_for_writeback(mapping, index, end); @@ -3047,7 +3044,6 @@ retry: * and try again */ jbd2_journal_force_commit_nested(sbi->s_journal); - wbc->pages_skipped = pages_skipped; ret = 0; } else if (ret == MPAGE_DA_EXTENT_TAIL) { /* @@ -3055,7 +3051,6 @@ retry: * rest of the pages */ pages_written += mpd.pages_written; - wbc->pages_skipped = pages_skipped; ret = 0; io_done = 1; } else if (wbc->nr_to_write) @@ -3073,11 +3068,6 @@ retry: wbc->range_end = mapping->writeback_index - 1; goto retry; } - if (pages_skipped != wbc->pages_skipped) - ext4_msg(inode->i_sb, KERN_CRIT, - "This should not happen leaving %s " - "with nr_to_write = %ld ret = %d", - __func__, wbc->nr_to_write, ret); /* Update index */ wbc->range_cyclic = range_cyclic; -- cgit v1.2.3-70-g09d2 From 78aaced3408141bb7c836f2db0ca435790399da5 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 26 Feb 2011 14:09:14 -0500 Subject: ext4: don't lock the next page in write_cache_pages if not needed If we have accumulated a contiguous region of memory to be written out, and the next page can added to this region, don't bother locking (and then unlocking the page) before writing out the memory. In the unlikely event that the next page was being written back by some other CPU, we can also skip waiting that page to finish writeback. Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 27 ++++++++++----------------- 1 file changed, 10 insertions(+), 17 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 617c9cbba182..c2e6af338234 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2761,6 +2761,16 @@ static int write_cache_pages_da(struct address_space *mapping, *done_index = page->index + 1; + /* + * If we can't merge this page, and we have + * accumulated an contiguous region, write it + */ + if ((mpd->next_page != page->index) && + (mpd->next_page != mpd->first_page)) { + mpage_da_map_and_submit(mpd); + goto ret_extent_tail; + } + lock_page(page); /* @@ -2784,24 +2794,7 @@ static int write_cache_pages_da(struct address_space *mapping, BUG_ON(PageWriteback(page)); - /* - * Can we merge this page to current extent? - */ if (mpd->next_page != page->index) { - /* - * Nope, we can't. So, we map - * non-allocated blocks and start IO - * on them - */ - if (mpd->next_page != mpd->first_page) { - mpage_da_map_and_submit(mpd); - /* - * skip rest of the page in the page_vec - */ - unlock_page(page); - goto ret_extent_tail; - } - /* * Start next extent of pages and blocks */ -- cgit v1.2.3-70-g09d2 From 168fc0223c0e944957b1f31d88c2334fc904baf1 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 26 Feb 2011 14:09:20 -0500 Subject: ext4: move setup of the mpd structure to write_cache_pages_da() Move the initialization of all of the fields of the mpd structure to write_cache_pages_da(). This simplifies the code considerably. Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 29 +++++++---------------------- 1 file changed, 7 insertions(+), 22 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index c2e6af338234..dcc2287433b6 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2714,7 +2714,8 @@ static int ext4_da_writepages_trans_blocks(struct inode *inode) /* * write_cache_pages_da - walk the list of dirty pages of the given * address space and accumulate pages that need writing, and call - * mpage_da_map_and_submit to map the pages and then write them. + * mpage_da_map_and_submit to map a single contiguous memory region + * and then write them. */ static int write_cache_pages_da(struct address_space *mapping, struct writeback_control *wbc, @@ -2722,7 +2723,7 @@ static int write_cache_pages_da(struct address_space *mapping, pgoff_t *done_index) { struct buffer_head *bh, *head; - struct inode *inode = mpd->inode; + struct inode *inode = mapping->host; struct pagevec pvec; unsigned int nr_pages; sector_t logical; @@ -2730,6 +2731,9 @@ static int write_cache_pages_da(struct address_space *mapping, long nr_to_write = wbc->nr_to_write; int i, tag, ret = 0; + memset(mpd, 0, sizeof(struct mpage_da_data)); + mpd->wbc = wbc; + mpd->inode = inode; pagevec_init(&pvec, 0); index = wbc->range_start >> PAGE_CACHE_SHIFT; end = wbc->range_end >> PAGE_CACHE_SHIFT; @@ -2794,16 +2798,8 @@ static int write_cache_pages_da(struct address_space *mapping, BUG_ON(PageWriteback(page)); - if (mpd->next_page != page->index) { - /* - * Start next extent of pages and blocks - */ + if (mpd->next_page != page->index) mpd->first_page = page->index; - mpd->b_size = 0; - mpd->b_state = 0; - mpd->b_blocknr = 0; - } - mpd->next_page = page->index + 1; logical = (sector_t) page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits); @@ -2975,9 +2971,6 @@ static int ext4_da_writepages(struct address_space *mapping, wbc->nr_to_write = desired_nr_to_write; } - mpd.wbc = wbc; - mpd.inode = mapping->host; - retry: if (wbc->sync_mode == WB_SYNC_ALL) tag_pages_for_writeback(mapping, index, end); @@ -3008,14 +3001,6 @@ retry: * contiguous region of logical blocks that need * blocks to be allocated by ext4 and submit them. */ - mpd.b_size = 0; - mpd.b_state = 0; - mpd.b_blocknr = 0; - mpd.first_page = 0; - mpd.next_page = 0; - mpd.io_done = 0; - mpd.pages_written = 0; - mpd.retval = 0; ret = write_cache_pages_da(mapping, wbc, &mpd, &done_index); /* * If we have a contiguous extent of pages and we -- cgit v1.2.3-70-g09d2 From 8e8eaabefee3ff645b9551ee32c6c54c7d80ad19 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Sun, 27 Feb 2011 23:32:12 -0500 Subject: ext4: use the nblocks arg to ext4_truncate_restart_trans() nblocks is passed into ext4_truncate_restart_trans() from ext4_ext_truncate_extend_restart() with a value different from the default blocks_for_truncate(), but is being ignored. The two other calls to ext4_truncate_restart_trans() already pass the default value, which is then being recalculated inside the function. Fix the problem by using the passed argument. Signed-off-by: Amir Goldstein --- fs/ext4/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index dcc2287433b6..67e7a3caf9ed 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -173,7 +173,7 @@ int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode, BUG_ON(EXT4_JOURNAL(inode) == NULL); jbd_debug(2, "restarting handle %p\n", handle); up_write(&EXT4_I(inode)->i_data_sem); - ret = ext4_journal_restart(handle, blocks_for_truncate(inode)); + ret = ext4_journal_restart(handle, nblocks); down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode); -- cgit v1.2.3-70-g09d2 From d67d1218344009970ba0deb7eb15a3984518ddd0 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Sun, 20 Mar 2011 22:59:02 -0400 Subject: ext4: handle errors in ext4_clear_blocks() Checking return code from ext4_journal_get_write_access() is important with snapshots, because this function invokes COW, so may return new errors, such as ENOSPC. ext4_clear_blocks() now returns < 0 for fatal errors, in which case, ext4_free_data() is aborted. Signed-off-by: Amir Goldstein Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 46 ++++++++++++++++++++++++++-------------------- 1 file changed, 26 insertions(+), 20 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 67e7a3caf9ed..fc8c0ce84315 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4096,6 +4096,9 @@ no_top: * * 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, @@ -4122,25 +4125,21 @@ static int ext4_clear_blocks(handle_t *handle, struct inode *inode, if (bh) { BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, inode, bh); - if (unlikely(err)) { - ext4_std_error(inode->i_sb, err); - return 1; - } + if (unlikely(err)) + goto out_err; } err = ext4_mark_inode_dirty(handle, inode); - if (unlikely(err)) { - ext4_std_error(inode->i_sb, err); - return 1; - } + if (unlikely(err)) + goto out_err; err = ext4_truncate_restart_trans(handle, inode, blocks_for_truncate(inode)); - if (unlikely(err)) { - ext4_std_error(inode->i_sb, err); - return 1; - } + if (unlikely(err)) + goto out_err; if (bh) { BUFFER_TRACE(bh, "retaking write access"); - ext4_journal_get_write_access(handle, bh); + err = ext4_journal_get_write_access(handle, bh); + if (unlikely(err)) + goto out_err; } } @@ -4149,6 +4148,9 @@ static int ext4_clear_blocks(handle_t *handle, struct inode *inode, ext4_free_blocks(handle, inode, NULL, block_to_free, count, flags); return 0; +out_err: + ext4_std_error(inode->i_sb, err); + return err; } /** @@ -4182,7 +4184,7 @@ static void ext4_free_data(handle_t *handle, struct inode *inode, ext4_fsblk_t nr; /* Current block # */ __le32 *p; /* Pointer into inode/ind for current block */ - int err; + int err = 0; if (this_bh) { /* For indirect block */ BUFFER_TRACE(this_bh, "get_write_access"); @@ -4204,9 +4206,10 @@ static void ext4_free_data(handle_t *handle, struct inode *inode, } else if (nr == block_to_free + count) { count++; } else { - if (ext4_clear_blocks(handle, inode, this_bh, - block_to_free, count, - block_to_free_p, p)) + 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; @@ -4215,9 +4218,12 @@ static void ext4_free_data(handle_t *handle, struct inode *inode, } } - if (count > 0) - ext4_clear_blocks(handle, inode, this_bh, block_to_free, - count, block_to_free_p, p); + 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"); -- cgit v1.2.3-70-g09d2 From 0562e0bad483d10e9651fbb8f21dc3d0bad57374 Mon Sep 17 00:00:00 2001 From: Jiaying Zhang Date: Mon, 21 Mar 2011 21:38:05 -0400 Subject: ext4: add more tracepoints and use dev_t in the trace buffer - Add more ext4 tracepoints. - Change ext4 tracepoints to use dev_t field with MAJOR/MINOR macros so that we can save 4 bytes in the ring buffer on some platforms. - Add sync_mode to ext4_da_writepages, ext4_da_write_pages, and ext4_da_writepages_result tracepoints. Also remove for_reclaim field from ext4_da_writepages since it is usually not very useful. Signed-off-by: Jiaying Zhang Signed-off-by: "Theodore Ts'o" --- fs/ext4/balloc.c | 3 + fs/ext4/extents.c | 13 +- fs/ext4/fsync.c | 14 +- fs/ext4/ialloc.c | 1 + fs/ext4/inode.c | 24 +- fs/ext4/namei.c | 3 + include/trace/events/ext4.h | 775 +++++++++++++++++++++++++++++++++----------- include/trace/events/jbd2.h | 78 ++--- 8 files changed, 658 insertions(+), 253 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index adf96b822781..97b970e7dd13 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -21,6 +21,8 @@ #include "ext4_jbd2.h" #include "mballoc.h" +#include + /* * balloc.c contains the blocks allocation and deallocation routines */ @@ -342,6 +344,7 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group) * We do it here so the bitmap uptodate bit * get set with buffer lock held. */ + trace_ext4_read_block_bitmap_load(sb, block_group); set_bitmap_uptodate(bh); if (bh_submit_read(bh) < 0) { put_bh(bh); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 9ea1bc64ca6d..f46f6e3c02d7 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -44,6 +44,8 @@ #include "ext4_jbd2.h" #include "ext4_extents.h" +#include + static int ext4_ext_truncate_extend_restart(handle_t *handle, struct inode *inode, int needed) @@ -664,6 +666,8 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block, if (unlikely(!bh)) goto err; if (!bh_uptodate_or_lock(bh)) { + trace_ext4_ext_load_extent(inode, block, + path[ppos].p_block); if (bh_submit_read(bh) < 0) { put_bh(bh); goto err; @@ -3297,7 +3301,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, struct ext4_ext_path *path = NULL; struct ext4_extent_header *eh; struct ext4_extent newex, *ex; - ext4_fsblk_t newblock; + ext4_fsblk_t newblock = 0; int err = 0, depth, ret; unsigned int allocated = 0; struct ext4_allocation_request ar; @@ -3305,6 +3309,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, ext_debug("blocks %u/%u requested for inode %lu\n", map->m_lblk, map->m_len, inode->i_ino); + trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags); /* check in cache */ if (ext4_ext_in_cache(inode, map->m_lblk, &newex)) { @@ -3525,6 +3530,8 @@ out2: ext4_ext_drop_refs(path); kfree(path); } + trace_ext4_ext_map_blocks_exit(inode, map->m_lblk, + newblock, map->m_len, err ? err : allocated); return err ? err : allocated; } @@ -3658,6 +3665,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) return -EOPNOTSUPP; + trace_ext4_fallocate_enter(inode, offset, len, mode); map.m_lblk = offset >> blkbits; /* * We can't just convert len to max_blocks because @@ -3673,6 +3681,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) ret = inode_newsize_ok(inode, (len + offset)); if (ret) { mutex_unlock(&inode->i_mutex); + trace_ext4_fallocate_exit(inode, offset, max_blocks, ret); return ret; } retry: @@ -3717,6 +3726,8 @@ retry: goto retry; } mutex_unlock(&inode->i_mutex); + trace_ext4_fallocate_exit(inode, offset, max_blocks, + ret > 0 ? ret2 : ret); return ret > 0 ? ret2 : ret; } diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 7829b287822a..7f74019d6d77 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -164,20 +164,20 @@ int ext4_sync_file(struct file *file, int datasync) J_ASSERT(ext4_journal_current_handle() == NULL); - trace_ext4_sync_file(file, datasync); + trace_ext4_sync_file_enter(file, datasync); if (inode->i_sb->s_flags & MS_RDONLY) return 0; ret = ext4_flush_completed_IO(inode); if (ret < 0) - return ret; + goto out; if (!journal) { ret = generic_file_fsync(file, datasync); if (!ret && !list_empty(&inode->i_dentry)) ext4_sync_parent(inode); - return ret; + goto out; } /* @@ -194,8 +194,10 @@ int ext4_sync_file(struct file *file, int datasync) * (they were dirtied by commit). But that's OK - the blocks are * safe in-journal, which is all fsync() needs to ensure. */ - if (ext4_should_journal_data(inode)) - return ext4_force_commit(inode->i_sb); + if (ext4_should_journal_data(inode)) { + ret = ext4_force_commit(inode->i_sb); + goto out; + } commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid; if (jbd2_log_start_commit(journal, commit_tid)) { @@ -215,5 +217,7 @@ int ext4_sync_file(struct file *file, int datasync) ret = jbd2_log_wait_commit(journal, commit_tid); } else if (journal->j_flags & JBD2_BARRIER) blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); + out: + trace_ext4_sync_file_exit(inode, ret); return ret; } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index a679a482c986..254e6b98b5b4 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -152,6 +152,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) * We do it here so the bitmap uptodate bit * get set with buffer lock held. */ + trace_ext4_load_inode_bitmap(sb, block_group); set_bitmap_uptodate(bh); if (bh_submit_read(bh) < 0) { put_bh(bh); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index fc8c0ce84315..f44307a21136 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -973,6 +973,7 @@ static int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, 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, @@ -1058,6 +1059,8 @@ cleanup: partial--; } out: + trace_ext4_ind_map_blocks_exit(inode, map->m_lblk, + map->m_pblk, map->m_len, err); return err; } @@ -3379,6 +3382,7 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block) static int ext4_readpage(struct file *file, struct page *page) { + trace_ext4_readpage(page); return mpage_readpage(page, ext4_get_block); } @@ -3413,6 +3417,8 @@ static void ext4_invalidatepage(struct page *page, unsigned long offset) { journal_t *journal = EXT4_JOURNAL(page->mapping->host); + trace_ext4_invalidatepage(page, offset); + /* * free any io_end structure allocated for buffers to be discarded */ @@ -3434,6 +3440,8 @@ static int ext4_releasepage(struct page *page, gfp_t wait) { journal_t *journal = EXT4_JOURNAL(page->mapping->host); + trace_ext4_releasepage(page); + WARN_ON(PageChecked(page)); if (!page_has_buffers(page)) return 0; @@ -3792,11 +3800,16 @@ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb, { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; + ssize_t ret; + trace_ext4_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - return ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs); - - return ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs); + ret = ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs); + else + ret = ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs); + trace_ext4_direct_IO_exit(inode, offset, + iov_length(iov, nr_segs), rw, ret); + return ret; } /* @@ -4425,6 +4438,8 @@ void ext4_truncate(struct inode *inode) ext4_lblk_t last_block; unsigned blocksize = inode->i_sb->s_blocksize; + trace_ext4_truncate_enter(inode); + if (!ext4_can_truncate(inode)) return; @@ -4435,6 +4450,7 @@ void ext4_truncate(struct inode *inode) if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { ext4_ext_truncate(inode); + trace_ext4_truncate_exit(inode); return; } @@ -4564,6 +4580,7 @@ out_stop: ext4_orphan_del(handle, inode); ext4_journal_stop(handle); + trace_ext4_truncate_exit(inode); } /* @@ -4695,6 +4712,7 @@ make_io: * has in-inode xattrs, or we don't have this inode in memory. * Read the block from disk. */ + trace_ext4_load_inode(inode); get_bh(bh); bh->b_end_io = end_buffer_read_sync; submit_bh(READ_META, bh); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index ad87584aa8d2..f9f83878843a 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -40,6 +40,7 @@ #include "xattr.h" #include "acl.h" +#include /* * define how far ahead to read directories while searching them. */ @@ -2183,6 +2184,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) struct ext4_dir_entry_2 *de; handle_t *handle; + trace_ext4_unlink_enter(dir, dentry); /* Initialize quotas before so that eventual writes go * in separate transaction */ dquot_initialize(dir); @@ -2228,6 +2230,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) end_unlink: ext4_journal_stop(handle); brelse(bh); + trace_ext4_unlink_exit(dentry, retval); return retval; } diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index e5e345fb2a5c..e09592d2f916 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -21,8 +21,7 @@ TRACE_EVENT(ext4_free_inode, TP_ARGS(inode), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( umode_t, mode ) __field( uid_t, uid ) @@ -31,8 +30,7 @@ TRACE_EVENT(ext4_free_inode, ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->mode = inode->i_mode; __entry->uid = inode->i_uid; @@ -41,9 +39,9 @@ TRACE_EVENT(ext4_free_inode, ), TP_printk("dev %d,%d ino %lu mode 0%o uid %u gid %u blocks %llu", - __entry->dev_major, __entry->dev_minor, - (unsigned long) __entry->ino, __entry->mode, - __entry->uid, __entry->gid, + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->mode, __entry->uid, __entry->gid, (unsigned long long) __entry->blocks) ); @@ -53,21 +51,19 @@ TRACE_EVENT(ext4_request_inode, TP_ARGS(dir, mode), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, dir ) __field( umode_t, mode ) ), TP_fast_assign( - __entry->dev_major = MAJOR(dir->i_sb->s_dev); - __entry->dev_minor = MINOR(dir->i_sb->s_dev); + __entry->dev = dir->i_sb->s_dev; __entry->dir = dir->i_ino; __entry->mode = mode; ), TP_printk("dev %d,%d dir %lu mode 0%o", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->dir, __entry->mode) ); @@ -77,23 +73,21 @@ TRACE_EVENT(ext4_allocate_inode, TP_ARGS(inode, dir, mode), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( ino_t, dir ) __field( umode_t, mode ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->dir = dir->i_ino; __entry->mode = mode; ), TP_printk("dev %d,%d ino %lu dir %lu mode 0%o", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned long) __entry->dir, __entry->mode) ); @@ -104,21 +98,19 @@ TRACE_EVENT(ext4_evict_inode, TP_ARGS(inode), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( int, nlink ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->nlink = inode->i_nlink; ), TP_printk("dev %d,%d ino %lu nlink %d", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->nlink) ); @@ -128,21 +120,19 @@ TRACE_EVENT(ext4_drop_inode, TP_ARGS(inode, drop), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( int, drop ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->drop = drop; ), TP_printk("dev %d,%d ino %lu drop %d", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->drop) ); @@ -152,21 +142,19 @@ TRACE_EVENT(ext4_mark_inode_dirty, TP_ARGS(inode, IP), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field(unsigned long, ip ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->ip = IP; ), TP_printk("dev %d,%d ino %lu caller %pF", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (void *)__entry->ip) ); @@ -176,21 +164,19 @@ TRACE_EVENT(ext4_begin_ordered_truncate, TP_ARGS(inode, new_size), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, new_size ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->new_size = new_size; ), TP_printk("dev %d,%d ino %lu new_size %lld", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (long long) __entry->new_size) ); @@ -203,8 +189,7 @@ DECLARE_EVENT_CLASS(ext4__write_begin, TP_ARGS(inode, pos, len, flags), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, pos ) __field( unsigned int, len ) @@ -212,8 +197,7 @@ DECLARE_EVENT_CLASS(ext4__write_begin, ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pos = pos; __entry->len = len; @@ -221,7 +205,7 @@ DECLARE_EVENT_CLASS(ext4__write_begin, ), TP_printk("dev %d,%d ino %lu pos %llu len %u flags %u", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->pos, __entry->len, __entry->flags) ); @@ -249,8 +233,7 @@ DECLARE_EVENT_CLASS(ext4__write_end, TP_ARGS(inode, pos, len, copied), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, pos ) __field( unsigned int, len ) @@ -258,8 +241,7 @@ DECLARE_EVENT_CLASS(ext4__write_end, ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pos = pos; __entry->len = len; @@ -267,9 +249,9 @@ DECLARE_EVENT_CLASS(ext4__write_end, ), TP_printk("dev %d,%d ino %lu pos %llu len %u copied %u", - __entry->dev_major, __entry->dev_minor, - (unsigned long) __entry->ino, __entry->pos, - __entry->len, __entry->copied) + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->pos, __entry->len, __entry->copied) ); DEFINE_EVENT(ext4__write_end, ext4_ordered_write_end, @@ -310,22 +292,20 @@ TRACE_EVENT(ext4_writepage, TP_ARGS(inode, page), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( pgoff_t, index ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->index = page->index; ), TP_printk("dev %d,%d ino %lu page_index %lu", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->index) ); @@ -335,43 +315,39 @@ TRACE_EVENT(ext4_da_writepages, TP_ARGS(inode, wbc), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( long, nr_to_write ) __field( long, pages_skipped ) __field( loff_t, range_start ) __field( loff_t, range_end ) + __field( int, sync_mode ) __field( char, for_kupdate ) - __field( char, for_reclaim ) __field( char, range_cyclic ) __field( pgoff_t, writeback_index ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->nr_to_write = wbc->nr_to_write; __entry->pages_skipped = wbc->pages_skipped; __entry->range_start = wbc->range_start; __entry->range_end = wbc->range_end; + __entry->sync_mode = wbc->sync_mode; __entry->for_kupdate = wbc->for_kupdate; - __entry->for_reclaim = wbc->for_reclaim; __entry->range_cyclic = wbc->range_cyclic; __entry->writeback_index = inode->i_mapping->writeback_index; ), TP_printk("dev %d,%d ino %lu nr_to_write %ld pages_skipped %ld " - "range_start %llu range_end %llu " - "for_kupdate %d for_reclaim %d " - "range_cyclic %d writeback_index %lu", - __entry->dev_major, __entry->dev_minor, + "range_start %llu range_end %llu sync_mode %d" + "for_kupdate %d range_cyclic %d writeback_index %lu", + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->nr_to_write, __entry->pages_skipped, __entry->range_start, - __entry->range_end, - __entry->for_kupdate, __entry->for_reclaim, - __entry->range_cyclic, + __entry->range_end, __entry->sync_mode, + __entry->for_kupdate, __entry->range_cyclic, (unsigned long) __entry->writeback_index) ); @@ -381,8 +357,7 @@ TRACE_EVENT(ext4_da_write_pages, TP_ARGS(inode, mpd), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, b_blocknr ) __field( __u32, b_size ) @@ -390,11 +365,11 @@ TRACE_EVENT(ext4_da_write_pages, __field( unsigned long, first_page ) __field( int, io_done ) __field( int, pages_written ) + __field( int, sync_mode ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->b_blocknr = mpd->b_blocknr; __entry->b_size = mpd->b_size; @@ -402,14 +377,18 @@ TRACE_EVENT(ext4_da_write_pages, __entry->first_page = mpd->first_page; __entry->io_done = mpd->io_done; __entry->pages_written = mpd->pages_written; + __entry->sync_mode = mpd->wbc->sync_mode; ), - TP_printk("dev %d,%d ino %lu b_blocknr %llu b_size %u b_state 0x%04x first_page %lu io_done %d pages_written %d", - __entry->dev_major, __entry->dev_minor, + TP_printk("dev %d,%d ino %lu b_blocknr %llu b_size %u b_state 0x%04x " + "first_page %lu io_done %d pages_written %d sync_mode %d", + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->b_blocknr, __entry->b_size, __entry->b_state, __entry->first_page, - __entry->io_done, __entry->pages_written) + __entry->io_done, __entry->pages_written, + __entry->sync_mode + ) ); TRACE_EVENT(ext4_da_writepages_result, @@ -419,35 +398,100 @@ TRACE_EVENT(ext4_da_writepages_result, TP_ARGS(inode, wbc, ret, pages_written), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( int, ret ) __field( int, pages_written ) __field( long, pages_skipped ) + __field( int, sync_mode ) __field( char, more_io ) __field( pgoff_t, writeback_index ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->ret = ret; __entry->pages_written = pages_written; __entry->pages_skipped = wbc->pages_skipped; + __entry->sync_mode = wbc->sync_mode; __entry->more_io = wbc->more_io; __entry->writeback_index = inode->i_mapping->writeback_index; ), - TP_printk("dev %d,%d ino %lu ret %d pages_written %d pages_skipped %ld more_io %d writeback_index %lu", - __entry->dev_major, __entry->dev_minor, + TP_printk("dev %d,%d ino %lu ret %d pages_written %d pages_skipped %ld " + " more_io %d sync_mode %d writeback_index %lu", + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->ret, __entry->pages_written, __entry->pages_skipped, - __entry->more_io, + __entry->more_io, __entry->sync_mode, (unsigned long) __entry->writeback_index) ); +DECLARE_EVENT_CLASS(ext4__page_op, + TP_PROTO(struct page *page), + + TP_ARGS(page), + + TP_STRUCT__entry( + __field( pgoff_t, index ) + __field( ino_t, ino ) + __field( dev_t, dev ) + + ), + + TP_fast_assign( + __entry->index = page->index; + __entry->ino = page->mapping->host->i_ino; + __entry->dev = page->mapping->host->i_sb->s_dev; + ), + + TP_printk("dev %d,%d ino %lu page_index %lu", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->index) +); + +DEFINE_EVENT(ext4__page_op, ext4_readpage, + + TP_PROTO(struct page *page), + + TP_ARGS(page) +); + +DEFINE_EVENT(ext4__page_op, ext4_releasepage, + + TP_PROTO(struct page *page), + + TP_ARGS(page) +); + +TRACE_EVENT(ext4_invalidatepage, + TP_PROTO(struct page *page, unsigned long offset), + + TP_ARGS(page, offset), + + TP_STRUCT__entry( + __field( pgoff_t, index ) + __field( unsigned long, offset ) + __field( ino_t, ino ) + __field( dev_t, dev ) + + ), + + TP_fast_assign( + __entry->index = page->index; + __entry->offset = offset; + __entry->ino = page->mapping->host->i_ino; + __entry->dev = page->mapping->host->i_sb->s_dev; + ), + + TP_printk("dev %d,%d ino %lu page_index %lu offset %lu", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->index, __entry->offset) +); + TRACE_EVENT(ext4_discard_blocks, TP_PROTO(struct super_block *sb, unsigned long long blk, unsigned long long count), @@ -455,22 +499,20 @@ TRACE_EVENT(ext4_discard_blocks, TP_ARGS(sb, blk, count), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( __u64, blk ) __field( __u64, count ) ), TP_fast_assign( - __entry->dev_major = MAJOR(sb->s_dev); - __entry->dev_minor = MINOR(sb->s_dev); + __entry->dev = sb->s_dev; __entry->blk = blk; __entry->count = count; ), TP_printk("dev %d,%d blk %llu count %llu", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->blk, __entry->count) ); @@ -481,8 +523,7 @@ DECLARE_EVENT_CLASS(ext4__mb_new_pa, TP_ARGS(ac, pa), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, pa_pstart ) __field( __u32, pa_len ) @@ -491,8 +532,7 @@ DECLARE_EVENT_CLASS(ext4__mb_new_pa, ), TP_fast_assign( - __entry->dev_major = MAJOR(ac->ac_sb->s_dev); - __entry->dev_minor = MINOR(ac->ac_sb->s_dev); + __entry->dev = ac->ac_sb->s_dev; __entry->ino = ac->ac_inode->i_ino; __entry->pa_pstart = pa->pa_pstart; __entry->pa_len = pa->pa_len; @@ -500,9 +540,9 @@ DECLARE_EVENT_CLASS(ext4__mb_new_pa, ), TP_printk("dev %d,%d ino %lu pstart %llu len %u lstart %llu", - __entry->dev_major, __entry->dev_minor, - (unsigned long) __entry->ino, __entry->pa_pstart, - __entry->pa_len, __entry->pa_lstart) + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->pa_pstart, __entry->pa_len, __entry->pa_lstart) ); DEFINE_EVENT(ext4__mb_new_pa, ext4_mb_new_inode_pa, @@ -530,8 +570,7 @@ TRACE_EVENT(ext4_mb_release_inode_pa, TP_ARGS(sb, inode, pa, block, count), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, block ) __field( __u32, count ) @@ -539,16 +578,16 @@ TRACE_EVENT(ext4_mb_release_inode_pa, ), TP_fast_assign( - __entry->dev_major = MAJOR(sb->s_dev); - __entry->dev_minor = MINOR(sb->s_dev); + __entry->dev = sb->s_dev; __entry->ino = inode->i_ino; __entry->block = block; __entry->count = count; ), TP_printk("dev %d,%d ino %lu block %llu count %u", - __entry->dev_major, __entry->dev_minor, - (unsigned long) __entry->ino, __entry->block, __entry->count) + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->block, __entry->count) ); TRACE_EVENT(ext4_mb_release_group_pa, @@ -558,22 +597,20 @@ TRACE_EVENT(ext4_mb_release_group_pa, TP_ARGS(sb, pa), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( __u64, pa_pstart ) __field( __u32, pa_len ) ), TP_fast_assign( - __entry->dev_major = MAJOR(sb->s_dev); - __entry->dev_minor = MINOR(sb->s_dev); + __entry->dev = sb->s_dev; __entry->pa_pstart = pa->pa_pstart; __entry->pa_len = pa->pa_len; ), TP_printk("dev %d,%d pstart %llu len %u", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->pa_pstart, __entry->pa_len) ); @@ -583,20 +620,18 @@ TRACE_EVENT(ext4_discard_preallocations, TP_ARGS(inode), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; ), TP_printk("dev %d,%d ino %lu", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino) ); @@ -606,20 +641,19 @@ TRACE_EVENT(ext4_mb_discard_preallocations, TP_ARGS(sb, needed), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( int, needed ) ), TP_fast_assign( - __entry->dev_major = MAJOR(sb->s_dev); - __entry->dev_minor = MINOR(sb->s_dev); + __entry->dev = sb->s_dev; __entry->needed = needed; ), TP_printk("dev %d,%d needed %d", - __entry->dev_major, __entry->dev_minor, __entry->needed) + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->needed) ); TRACE_EVENT(ext4_request_blocks, @@ -628,8 +662,7 @@ TRACE_EVENT(ext4_request_blocks, TP_ARGS(ar), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( unsigned int, flags ) __field( unsigned int, len ) @@ -642,8 +675,7 @@ TRACE_EVENT(ext4_request_blocks, ), TP_fast_assign( - __entry->dev_major = MAJOR(ar->inode->i_sb->s_dev); - __entry->dev_minor = MINOR(ar->inode->i_sb->s_dev); + __entry->dev = ar->inode->i_sb->s_dev; __entry->ino = ar->inode->i_ino; __entry->flags = ar->flags; __entry->len = ar->len; @@ -655,8 +687,9 @@ TRACE_EVENT(ext4_request_blocks, __entry->pright = ar->pright; ), - TP_printk("dev %d,%d ino %lu flags %u len %u lblk %llu goal %llu lleft %llu lright %llu pleft %llu pright %llu ", - __entry->dev_major, __entry->dev_minor, + TP_printk("dev %d,%d ino %lu flags %u len %u lblk %llu goal %llu " + "lleft %llu lright %llu pleft %llu pright %llu ", + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->flags, __entry->len, (unsigned long long) __entry->logical, @@ -673,8 +706,7 @@ TRACE_EVENT(ext4_allocate_blocks, TP_ARGS(ar, block), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, block ) __field( unsigned int, flags ) @@ -688,8 +720,7 @@ TRACE_EVENT(ext4_allocate_blocks, ), TP_fast_assign( - __entry->dev_major = MAJOR(ar->inode->i_sb->s_dev); - __entry->dev_minor = MINOR(ar->inode->i_sb->s_dev); + __entry->dev = ar->inode->i_sb->s_dev; __entry->ino = ar->inode->i_ino; __entry->block = block; __entry->flags = ar->flags; @@ -702,10 +733,11 @@ TRACE_EVENT(ext4_allocate_blocks, __entry->pright = ar->pright; ), - TP_printk("dev %d,%d ino %lu flags %u len %u block %llu lblk %llu goal %llu lleft %llu lright %llu pleft %llu pright %llu ", - __entry->dev_major, __entry->dev_minor, - (unsigned long) __entry->ino, __entry->flags, - __entry->len, __entry->block, + TP_printk("dev %d,%d ino %lu flags %u len %u block %llu lblk %llu " + "goal %llu lleft %llu lright %llu pleft %llu pright %llu", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->flags, __entry->len, __entry->block, (unsigned long long) __entry->logical, (unsigned long long) __entry->goal, (unsigned long long) __entry->lleft, @@ -721,8 +753,7 @@ TRACE_EVENT(ext4_free_blocks, TP_ARGS(inode, block, count, flags), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( umode_t, mode ) __field( __u64, block ) @@ -731,8 +762,7 @@ TRACE_EVENT(ext4_free_blocks, ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->mode = inode->i_mode; __entry->block = block; @@ -741,20 +771,19 @@ TRACE_EVENT(ext4_free_blocks, ), TP_printk("dev %d,%d ino %lu mode 0%o block %llu count %lu flags %d", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->block, __entry->count, __entry->flags) ); -TRACE_EVENT(ext4_sync_file, +TRACE_EVENT(ext4_sync_file_enter, TP_PROTO(struct file *file, int datasync), TP_ARGS(file, datasync), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( ino_t, parent ) __field( int, datasync ) @@ -763,39 +792,60 @@ TRACE_EVENT(ext4_sync_file, TP_fast_assign( struct dentry *dentry = file->f_path.dentry; - __entry->dev_major = MAJOR(dentry->d_inode->i_sb->s_dev); - __entry->dev_minor = MINOR(dentry->d_inode->i_sb->s_dev); + __entry->dev = dentry->d_inode->i_sb->s_dev; __entry->ino = dentry->d_inode->i_ino; __entry->datasync = datasync; __entry->parent = dentry->d_parent->d_inode->i_ino; ), TP_printk("dev %d,%d ino %ld parent %ld datasync %d ", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned long) __entry->parent, __entry->datasync) ); +TRACE_EVENT(ext4_sync_file_exit, + TP_PROTO(struct inode *inode, int ret), + + TP_ARGS(inode, ret), + + TP_STRUCT__entry( + __field( int, ret ) + __field( ino_t, ino ) + __field( dev_t, dev ) + ), + + TP_fast_assign( + __entry->ret = ret; + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + ), + + TP_printk("dev %d,%d ino %ld ret %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->ret) +); + TRACE_EVENT(ext4_sync_fs, TP_PROTO(struct super_block *sb, int wait), TP_ARGS(sb, wait), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( int, wait ) ), TP_fast_assign( - __entry->dev_major = MAJOR(sb->s_dev); - __entry->dev_minor = MINOR(sb->s_dev); + __entry->dev = sb->s_dev; __entry->wait = wait; ), - TP_printk("dev %d,%d wait %d", __entry->dev_major, - __entry->dev_minor, __entry->wait) + TP_printk("dev %d,%d wait %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->wait) ); TRACE_EVENT(ext4_alloc_da_blocks, @@ -804,23 +854,21 @@ TRACE_EVENT(ext4_alloc_da_blocks, TP_ARGS(inode), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( unsigned int, data_blocks ) __field( unsigned int, meta_blocks ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->data_blocks = EXT4_I(inode)->i_reserved_data_blocks; __entry->meta_blocks = EXT4_I(inode)->i_reserved_meta_blocks; ), TP_printk("dev %d,%d ino %lu data_blocks %u meta_blocks %u", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->data_blocks, __entry->meta_blocks) ); @@ -831,8 +879,7 @@ TRACE_EVENT(ext4_mballoc_alloc, TP_ARGS(ac), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( __u16, found ) __field( __u16, groups ) @@ -855,8 +902,7 @@ TRACE_EVENT(ext4_mballoc_alloc, ), TP_fast_assign( - __entry->dev_major = MAJOR(ac->ac_inode->i_sb->s_dev); - __entry->dev_minor = MINOR(ac->ac_inode->i_sb->s_dev); + __entry->dev = ac->ac_inode->i_sb->s_dev; __entry->ino = ac->ac_inode->i_ino; __entry->found = ac->ac_found; __entry->flags = ac->ac_flags; @@ -881,7 +927,7 @@ TRACE_EVENT(ext4_mballoc_alloc, TP_printk("dev %d,%d inode %lu orig %u/%d/%u@%u goal %u/%d/%u@%u " "result %u/%d/%u@%u blks %u grps %u cr %u flags 0x%04x " "tail %u broken %u", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->orig_group, __entry->orig_start, __entry->orig_len, __entry->orig_logical, @@ -900,8 +946,7 @@ TRACE_EVENT(ext4_mballoc_prealloc, TP_ARGS(ac), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( __u32, orig_logical ) __field( int, orig_start ) @@ -914,8 +959,7 @@ TRACE_EVENT(ext4_mballoc_prealloc, ), TP_fast_assign( - __entry->dev_major = MAJOR(ac->ac_inode->i_sb->s_dev); - __entry->dev_minor = MINOR(ac->ac_inode->i_sb->s_dev); + __entry->dev = ac->ac_inode->i_sb->s_dev; __entry->ino = ac->ac_inode->i_ino; __entry->orig_logical = ac->ac_o_ex.fe_logical; __entry->orig_start = ac->ac_o_ex.fe_start; @@ -928,7 +972,7 @@ TRACE_EVENT(ext4_mballoc_prealloc, ), TP_printk("dev %d,%d inode %lu orig %u/%d/%u@%u result %u/%d/%u@%u", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->orig_group, __entry->orig_start, __entry->orig_len, __entry->orig_logical, @@ -946,8 +990,7 @@ DECLARE_EVENT_CLASS(ext4__mballoc, TP_ARGS(sb, inode, group, start, len), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( int, result_start ) __field( __u32, result_group ) @@ -955,8 +998,7 @@ DECLARE_EVENT_CLASS(ext4__mballoc, ), TP_fast_assign( - __entry->dev_major = MAJOR(sb->s_dev); - __entry->dev_minor = MINOR(sb->s_dev); + __entry->dev = sb->s_dev; __entry->ino = inode ? inode->i_ino : 0; __entry->result_start = start; __entry->result_group = group; @@ -964,7 +1006,7 @@ DECLARE_EVENT_CLASS(ext4__mballoc, ), TP_printk("dev %d,%d inode %lu extent %u/%d/%u ", - __entry->dev_major, __entry->dev_minor, + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->result_group, __entry->result_start, __entry->result_len) @@ -998,8 +1040,7 @@ TRACE_EVENT(ext4_forget, TP_ARGS(inode, is_metadata, block), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( umode_t, mode ) __field( int, is_metadata ) @@ -1007,8 +1048,7 @@ TRACE_EVENT(ext4_forget, ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->mode = inode->i_mode; __entry->is_metadata = is_metadata; @@ -1016,9 +1056,9 @@ TRACE_EVENT(ext4_forget, ), TP_printk("dev %d,%d ino %lu mode 0%o is_metadata %d block %llu", - __entry->dev_major, __entry->dev_minor, - (unsigned long) __entry->ino, __entry->mode, - __entry->is_metadata, __entry->block) + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->mode, __entry->is_metadata, __entry->block) ); TRACE_EVENT(ext4_da_update_reserve_space, @@ -1027,8 +1067,7 @@ TRACE_EVENT(ext4_da_update_reserve_space, TP_ARGS(inode, used_blocks), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( umode_t, mode ) __field( __u64, i_blocks ) @@ -1039,8 +1078,7 @@ TRACE_EVENT(ext4_da_update_reserve_space, ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->mode = inode->i_mode; __entry->i_blocks = inode->i_blocks; @@ -1050,10 +1088,12 @@ TRACE_EVENT(ext4_da_update_reserve_space, __entry->allocated_meta_blocks = EXT4_I(inode)->i_allocated_meta_blocks; ), - TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu used_blocks %d reserved_data_blocks %d reserved_meta_blocks %d allocated_meta_blocks %d", - __entry->dev_major, __entry->dev_minor, - (unsigned long) __entry->ino, __entry->mode, - (unsigned long long) __entry->i_blocks, + TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu used_blocks %d " + "reserved_data_blocks %d reserved_meta_blocks %d " + "allocated_meta_blocks %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->mode, (unsigned long long) __entry->i_blocks, __entry->used_blocks, __entry->reserved_data_blocks, __entry->reserved_meta_blocks, __entry->allocated_meta_blocks) ); @@ -1064,8 +1104,7 @@ TRACE_EVENT(ext4_da_reserve_space, TP_ARGS(inode, md_needed), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( umode_t, mode ) __field( __u64, i_blocks ) @@ -1075,8 +1114,7 @@ TRACE_EVENT(ext4_da_reserve_space, ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->mode = inode->i_mode; __entry->i_blocks = inode->i_blocks; @@ -1085,8 +1123,9 @@ TRACE_EVENT(ext4_da_reserve_space, __entry->reserved_meta_blocks = EXT4_I(inode)->i_reserved_meta_blocks; ), - TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu md_needed %d reserved_data_blocks %d reserved_meta_blocks %d", - __entry->dev_major, __entry->dev_minor, + TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu md_needed %d " + "reserved_data_blocks %d reserved_meta_blocks %d", + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, (unsigned long long) __entry->i_blocks, __entry->md_needed, __entry->reserved_data_blocks, @@ -1099,8 +1138,7 @@ TRACE_EVENT(ext4_da_release_space, TP_ARGS(inode, freed_blocks), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) __field( umode_t, mode ) __field( __u64, i_blocks ) @@ -1111,8 +1149,7 @@ TRACE_EVENT(ext4_da_release_space, ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->mode = inode->i_mode; __entry->i_blocks = inode->i_blocks; @@ -1122,8 +1159,10 @@ TRACE_EVENT(ext4_da_release_space, __entry->allocated_meta_blocks = EXT4_I(inode)->i_allocated_meta_blocks; ), - TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu freed_blocks %d reserved_data_blocks %d reserved_meta_blocks %d allocated_meta_blocks %d", - __entry->dev_major, __entry->dev_minor, + TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu freed_blocks %d " + "reserved_data_blocks %d reserved_meta_blocks %d " + "allocated_meta_blocks %d", + MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, (unsigned long long) __entry->i_blocks, __entry->freed_blocks, __entry->reserved_data_blocks, @@ -1136,20 +1175,19 @@ DECLARE_EVENT_CLASS(ext4__bitmap_load, TP_ARGS(sb, group), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( __u32, group ) ), TP_fast_assign( - __entry->dev_major = MAJOR(sb->s_dev); - __entry->dev_minor = MINOR(sb->s_dev); + __entry->dev = sb->s_dev; __entry->group = group; ), TP_printk("dev %d,%d group %u", - __entry->dev_major, __entry->dev_minor, __entry->group) + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->group) ); DEFINE_EVENT(ext4__bitmap_load, ext4_mb_bitmap_load, @@ -1166,6 +1204,349 @@ DEFINE_EVENT(ext4__bitmap_load, ext4_mb_buddy_bitmap_load, TP_ARGS(sb, group) ); +DEFINE_EVENT(ext4__bitmap_load, ext4_read_block_bitmap_load, + + TP_PROTO(struct super_block *sb, unsigned long group), + + TP_ARGS(sb, group) +); + +DEFINE_EVENT(ext4__bitmap_load, ext4_load_inode_bitmap, + + TP_PROTO(struct super_block *sb, unsigned long group), + + TP_ARGS(sb, group) +); + +TRACE_EVENT(ext4_direct_IO_enter, + TP_PROTO(struct inode *inode, loff_t offset, unsigned long len, int rw), + + TP_ARGS(inode, offset, len, rw), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( loff_t, pos ) + __field( unsigned long, len ) + __field( int, rw ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->pos = offset; + __entry->len = len; + __entry->rw = rw; + ), + + TP_printk("dev %d,%d ino %lu pos %llu len %lu rw %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned long long) __entry->pos, __entry->len, __entry->rw) +); + +TRACE_EVENT(ext4_direct_IO_exit, + TP_PROTO(struct inode *inode, loff_t offset, unsigned long len, int rw, int ret), + + TP_ARGS(inode, offset, len, rw, ret), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( loff_t, pos ) + __field( unsigned long, len ) + __field( int, rw ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->pos = offset; + __entry->len = len; + __entry->rw = rw; + __entry->ret = ret; + ), + + TP_printk("dev %d,%d ino %lu pos %llu len %lu rw %d ret %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned long long) __entry->pos, __entry->len, + __entry->rw, __entry->ret) +); + +TRACE_EVENT(ext4_fallocate_enter, + TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode), + + TP_ARGS(inode, offset, len, mode), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( loff_t, pos ) + __field( loff_t, len ) + __field( int, mode ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->pos = offset; + __entry->len = len; + __entry->mode = mode; + ), + + TP_printk("dev %d,%d ino %ld pos %llu len %llu mode %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned long long) __entry->pos, + (unsigned long long) __entry->len, __entry->mode) +); + +TRACE_EVENT(ext4_fallocate_exit, + TP_PROTO(struct inode *inode, loff_t offset, unsigned int max_blocks, int ret), + + TP_ARGS(inode, offset, max_blocks, ret), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( loff_t, pos ) + __field( unsigned, blocks ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->pos = offset; + __entry->blocks = max_blocks; + __entry->ret = ret; + ), + + TP_printk("dev %d,%d ino %ld pos %llu blocks %d ret %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned long long) __entry->pos, __entry->blocks, + __entry->ret) +); + +TRACE_EVENT(ext4_unlink_enter, + TP_PROTO(struct inode *parent, struct dentry *dentry), + + TP_ARGS(parent, dentry), + + TP_STRUCT__entry( + __field( ino_t, parent ) + __field( ino_t, ino ) + __field( loff_t, size ) + __field( dev_t, dev ) + ), + + TP_fast_assign( + __entry->parent = parent->i_ino; + __entry->ino = dentry->d_inode->i_ino; + __entry->size = dentry->d_inode->i_size; + __entry->dev = dentry->d_inode->i_sb->s_dev; + ), + + TP_printk("dev %d,%d ino %ld size %lld parent %ld", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, __entry->size, + (unsigned long) __entry->parent) +); + +TRACE_EVENT(ext4_unlink_exit, + TP_PROTO(struct dentry *dentry, int ret), + + TP_ARGS(dentry, ret), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->ino = dentry->d_inode->i_ino; + __entry->dev = dentry->d_inode->i_sb->s_dev; + __entry->ret = ret; + ), + + TP_printk("dev %d,%d ino %ld ret %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + __entry->ret) +); + +DECLARE_EVENT_CLASS(ext4__truncate, + TP_PROTO(struct inode *inode), + + TP_ARGS(inode), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( blkcnt_t, blocks ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->blocks = inode->i_blocks; + ), + + TP_printk("dev %d,%d ino %lu blocks %lu", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, (unsigned long) __entry->blocks) +); + +DEFINE_EVENT(ext4__truncate, ext4_truncate_enter, + + TP_PROTO(struct inode *inode), + + TP_ARGS(inode) +); + +DEFINE_EVENT(ext4__truncate, ext4_truncate_exit, + + TP_PROTO(struct inode *inode), + + TP_ARGS(inode) +); + +DECLARE_EVENT_CLASS(ext4__map_blocks_enter, + TP_PROTO(struct inode *inode, ext4_lblk_t lblk, + unsigned len, unsigned flags), + + TP_ARGS(inode, lblk, len, flags), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, lblk ) + __field( unsigned, len ) + __field( unsigned, flags ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->lblk = lblk; + __entry->len = len; + __entry->flags = flags; + ), + + TP_printk("dev %d,%d ino %lu lblk %u len %u flags %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->lblk, __entry->len, __entry->flags) +); + +DEFINE_EVENT(ext4__map_blocks_enter, ext4_ext_map_blocks_enter, + TP_PROTO(struct inode *inode, ext4_lblk_t lblk, + unsigned len, unsigned flags), + + TP_ARGS(inode, lblk, len, flags) +); + +DEFINE_EVENT(ext4__map_blocks_enter, ext4_ind_map_blocks_enter, + TP_PROTO(struct inode *inode, ext4_lblk_t lblk, + unsigned len, unsigned flags), + + TP_ARGS(inode, lblk, len, flags) +); + +DECLARE_EVENT_CLASS(ext4__map_blocks_exit, + TP_PROTO(struct inode *inode, ext4_lblk_t lblk, + ext4_fsblk_t pblk, unsigned len, int ret), + + TP_ARGS(inode, lblk, pblk, len, ret), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, lblk ) + __field( ext4_fsblk_t, pblk ) + __field( unsigned, len ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->lblk = lblk; + __entry->pblk = pblk; + __entry->len = len; + __entry->ret = ret; + ), + + TP_printk("dev %d,%d ino %lu lblk %u pblk %llu len %u ret %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->lblk, (unsigned long long) __entry->pblk, + __entry->len, __entry->ret) +); + +DEFINE_EVENT(ext4__map_blocks_exit, ext4_ext_map_blocks_exit, + TP_PROTO(struct inode *inode, ext4_lblk_t lblk, + ext4_fsblk_t pblk, unsigned len, int ret), + + TP_ARGS(inode, lblk, pblk, len, ret) +); + +DEFINE_EVENT(ext4__map_blocks_exit, ext4_ind_map_blocks_exit, + TP_PROTO(struct inode *inode, ext4_lblk_t lblk, + ext4_fsblk_t pblk, unsigned len, int ret), + + TP_ARGS(inode, lblk, pblk, len, ret) +); + +TRACE_EVENT(ext4_ext_load_extent, + TP_PROTO(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk), + + TP_ARGS(inode, lblk, pblk), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, lblk ) + __field( ext4_fsblk_t, pblk ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->lblk = lblk; + __entry->pblk = pblk; + ), + + TP_printk("dev %d,%d ino %lu lblk %u pblk %llu", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->lblk, (unsigned long long) __entry->pblk) +); + +TRACE_EVENT(ext4_load_inode, + TP_PROTO(struct inode *inode), + + TP_ARGS(inode), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + ), + + TP_printk("dev %d,%d ino %ld", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino) +); + #endif /* _TRACE_EXT4_H */ /* This part must be outside protection */ diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h index 7447ea9305b5..bf16545cc977 100644 --- a/include/trace/events/jbd2.h +++ b/include/trace/events/jbd2.h @@ -17,19 +17,17 @@ TRACE_EVENT(jbd2_checkpoint, TP_ARGS(journal, result), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( int, result ) ), TP_fast_assign( - __entry->dev_major = MAJOR(journal->j_fs_dev->bd_dev); - __entry->dev_minor = MINOR(journal->j_fs_dev->bd_dev); + __entry->dev = journal->j_fs_dev->bd_dev; __entry->result = result; ), - TP_printk("dev %d,%d result %d", - __entry->dev_major, __entry->dev_minor, __entry->result) + TP_printk("dev %s result %d", + jbd2_dev_to_name(__entry->dev), __entry->result) ); DECLARE_EVENT_CLASS(jbd2_commit, @@ -39,22 +37,20 @@ DECLARE_EVENT_CLASS(jbd2_commit, TP_ARGS(journal, commit_transaction), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( char, sync_commit ) __field( int, transaction ) ), TP_fast_assign( - __entry->dev_major = MAJOR(journal->j_fs_dev->bd_dev); - __entry->dev_minor = MINOR(journal->j_fs_dev->bd_dev); + __entry->dev = journal->j_fs_dev->bd_dev; __entry->sync_commit = commit_transaction->t_synchronous_commit; __entry->transaction = commit_transaction->t_tid; ), - TP_printk("dev %d,%d transaction %d sync %d", - __entry->dev_major, __entry->dev_minor, - __entry->transaction, __entry->sync_commit) + TP_printk("dev %s transaction %d sync %d", + jbd2_dev_to_name(__entry->dev), __entry->transaction, + __entry->sync_commit) ); DEFINE_EVENT(jbd2_commit, jbd2_start_commit, @@ -91,24 +87,22 @@ TRACE_EVENT(jbd2_end_commit, TP_ARGS(journal, commit_transaction), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( char, sync_commit ) __field( int, transaction ) __field( int, head ) ), TP_fast_assign( - __entry->dev_major = MAJOR(journal->j_fs_dev->bd_dev); - __entry->dev_minor = MINOR(journal->j_fs_dev->bd_dev); + __entry->dev = journal->j_fs_dev->bd_dev; __entry->sync_commit = commit_transaction->t_synchronous_commit; __entry->transaction = commit_transaction->t_tid; __entry->head = journal->j_tail_sequence; ), - TP_printk("dev %d,%d transaction %d sync %d head %d", - __entry->dev_major, __entry->dev_minor, - __entry->transaction, __entry->sync_commit, __entry->head) + TP_printk("dev %s transaction %d sync %d head %d", + jbd2_dev_to_name(__entry->dev), __entry->transaction, + __entry->sync_commit, __entry->head) ); TRACE_EVENT(jbd2_submit_inode_data, @@ -117,20 +111,17 @@ TRACE_EVENT(jbd2_submit_inode_data, TP_ARGS(inode), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( ino_t, ino ) ), TP_fast_assign( - __entry->dev_major = MAJOR(inode->i_sb->s_dev); - __entry->dev_minor = MINOR(inode->i_sb->s_dev); + __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; ), - TP_printk("dev %d,%d ino %lu", - __entry->dev_major, __entry->dev_minor, - (unsigned long) __entry->ino) + TP_printk("dev %s ino %lu", + jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino) ); TRACE_EVENT(jbd2_run_stats, @@ -140,8 +131,7 @@ TRACE_EVENT(jbd2_run_stats, TP_ARGS(dev, tid, stats), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( unsigned long, tid ) __field( unsigned long, wait ) __field( unsigned long, running ) @@ -154,8 +144,7 @@ TRACE_EVENT(jbd2_run_stats, ), TP_fast_assign( - __entry->dev_major = MAJOR(dev); - __entry->dev_minor = MINOR(dev); + __entry->dev = dev; __entry->tid = tid; __entry->wait = stats->rs_wait; __entry->running = stats->rs_running; @@ -167,9 +156,9 @@ TRACE_EVENT(jbd2_run_stats, __entry->blocks_logged = stats->rs_blocks_logged; ), - TP_printk("dev %d,%d tid %lu wait %u running %u locked %u flushing %u " + TP_printk("dev %s tid %lu wait %u running %u locked %u flushing %u " "logging %u handle_count %u blocks %u blocks_logged %u", - __entry->dev_major, __entry->dev_minor, __entry->tid, + jbd2_dev_to_name(__entry->dev), __entry->tid, jiffies_to_msecs(__entry->wait), jiffies_to_msecs(__entry->running), jiffies_to_msecs(__entry->locked), @@ -186,8 +175,7 @@ TRACE_EVENT(jbd2_checkpoint_stats, TP_ARGS(dev, tid, stats), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( unsigned long, tid ) __field( unsigned long, chp_time ) __field( __u32, forced_to_close ) @@ -196,8 +184,7 @@ TRACE_EVENT(jbd2_checkpoint_stats, ), TP_fast_assign( - __entry->dev_major = MAJOR(dev); - __entry->dev_minor = MINOR(dev); + __entry->dev = dev; __entry->tid = tid; __entry->chp_time = stats->cs_chp_time; __entry->forced_to_close= stats->cs_forced_to_close; @@ -205,9 +192,9 @@ TRACE_EVENT(jbd2_checkpoint_stats, __entry->dropped = stats->cs_dropped; ), - TP_printk("dev %d,%d tid %lu chp_time %u forced_to_close %u " + TP_printk("dev %s tid %lu chp_time %u forced_to_close %u " "written %u dropped %u", - __entry->dev_major, __entry->dev_minor, __entry->tid, + jbd2_dev_to_name(__entry->dev), __entry->tid, jiffies_to_msecs(__entry->chp_time), __entry->forced_to_close, __entry->written, __entry->dropped) ); @@ -220,8 +207,7 @@ TRACE_EVENT(jbd2_cleanup_journal_tail, TP_ARGS(journal, first_tid, block_nr, freed), TP_STRUCT__entry( - __field( int, dev_major ) - __field( int, dev_minor ) + __field( dev_t, dev ) __field( tid_t, tail_sequence ) __field( tid_t, first_tid ) __field(unsigned long, block_nr ) @@ -229,18 +215,16 @@ TRACE_EVENT(jbd2_cleanup_journal_tail, ), TP_fast_assign( - __entry->dev_major = MAJOR(journal->j_fs_dev->bd_dev); - __entry->dev_minor = MINOR(journal->j_fs_dev->bd_dev); + __entry->dev = journal->j_fs_dev->bd_dev; __entry->tail_sequence = journal->j_tail_sequence; __entry->first_tid = first_tid; __entry->block_nr = block_nr; __entry->freed = freed; ), - TP_printk("dev %d,%d from %u to %u offset %lu freed %lu", - __entry->dev_major, __entry->dev_minor, - __entry->tail_sequence, __entry->first_tid, - __entry->block_nr, __entry->freed) + TP_printk("dev %s from %u to %u offset %lu freed %lu", + jbd2_dev_to_name(__entry->dev), __entry->tail_sequence, + __entry->first_tid, __entry->block_nr, __entry->freed) ); #endif /* _TRACE_JBD2_H */ -- cgit v1.2.3-70-g09d2 From 6de9843dab3f2a1d4d66d80aa9e5782f80977d20 Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Wed, 23 Mar 2011 14:05:03 -0400 Subject: ext4: remove redundant set_buffer_mapped() in ext4_da_get_block_prep() The map_bh() call will have already set the buffer_head to mapped. Signed-off-by: Feng Tang Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 1 - 1 file changed, 1 deletion(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index f44307a21136..dec10e2115e0 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2502,7 +2502,6 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, * for partial write. */ set_buffer_new(bh); - set_buffer_mapped(bh); } return 0; } -- cgit v1.2.3-70-g09d2