From 10283ea525d30f2e99828978fd04d8427876a7ad Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Mon, 5 Nov 2018 22:57:24 +0000 Subject: [PATCH 1/3] gfs2: Put bitmap buffers in put_super gfs2_put_super calls gfs2_clear_rgrpd to destroy the gfs2_rgrpd objects attached to the resource group glocks. That function should release the buffers attached to the gfs2_bitmap objects (bi_bh), but the call to gfs2_rgrp_brelse for doing that is missing. When gfs2_releasepage later runs across these buffers which are still referenced, it refuses to free them. This causes the pages the buffers are attached to to remain referenced as well. With enough mount/unmount cycles, the system will eventually run out of memory. Fix this by adding the missing call to gfs2_rgrp_brelse in gfs2_clear_rgrpd. (Also fix a gfs2_rgrp_relse -> gfs2_rgrp_brelse typo in a comment.) Fixes: 39b0f1e92908 ("GFS2: Don't brelse rgrp buffer_heads every allocation") Cc: stable@vger.kernel.org # v4.2+ Signed-off-by: Andreas Gruenbacher --- fs/gfs2/rgrp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index ffe3032b1043..b08a530433ad 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -733,6 +733,7 @@ void gfs2_clear_rgrpd(struct gfs2_sbd *sdp) if (gl) { glock_clear_object(gl, rgd); + gfs2_rgrp_brelse(rgd); gfs2_glock_put(gl); } @@ -1174,7 +1175,7 @@ static u32 count_unlinked(struct gfs2_rgrpd *rgd) * @rgd: the struct gfs2_rgrpd describing the RG to read in * * Read in all of a Resource Group's header and bitmap blocks. - * Caller must eventually call gfs2_rgrp_relse() to free the bitmaps. + * Caller must eventually call gfs2_rgrp_brelse() to free the bitmaps. * * Returns: errno */ From e7445ceddfc220c1aede6d42758a5acb8844e9c3 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 8 Nov 2018 20:14:29 +0000 Subject: [PATCH 2/3] gfs2: Fix metadata read-ahead during truncate (2) The previous attempt to fix for metadata read-ahead during truncate was incorrect: for files with a height > 2 (1006989312 bytes with a block size of 4096 bytes), read-ahead requests were not being issued for some of the indirect blocks discovered while walking the metadata tree, leading to significant slow-downs when deleting large files. Fix that. In addition, only issue read-ahead requests in the first pass through the meta-data tree, while deallocating data blocks. Fixes: c3ce5aa9b0 ("gfs2: Fix metadata read-ahead during truncate") Cc: stable@vger.kernel.org # v4.16+ Signed-off-by: Andreas Gruenbacher --- fs/gfs2/bmap.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 5f3ea07ef5e2..38d88fcb6988 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1908,10 +1908,16 @@ static int punch_hole(struct gfs2_inode *ip, u64 offset, u64 length) if (ret < 0) goto out; - /* issue read-ahead on metadata */ - if (mp.mp_aheight > 1) { - for (; ret > 1; ret--) { - metapointer_range(&mp, mp.mp_aheight - ret, + /* On the first pass, issue read-ahead on metadata. */ + if (mp.mp_aheight > 1 && strip_h == ip->i_height - 1) { + unsigned int height = mp.mp_aheight - 1; + + /* No read-ahead for data blocks. */ + if (mp.mp_aheight - 1 == strip_h) + height--; + + for (; height >= mp.mp_aheight - ret; height--) { + metapointer_range(&mp, height, start_list, start_aligned, end_list, end_aligned, &start, &end); From c26b5aa8ef0d46035060fded475e6ab957b9f69f Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Sun, 11 Nov 2018 11:15:21 +0000 Subject: [PATCH 3/3] gfs2: Fix iomap buffer head reference counting bug GFS2 passes the inode buffer head (dibh) from gfs2_iomap_begin to gfs2_iomap_end in iomap->private. It sets that private pointer in gfs2_iomap_get. Users of gfs2_iomap_get other than gfs2_iomap_begin would have to release iomap->private, but this isn't done correctly, leading to a leak of buffer head references. To fix this, move the code for setting iomap->private from gfs2_iomap_get to gfs2_iomap_begin. Fixes: 64bc06bb32 ("gfs2: iomap buffered write support") Cc: stable@vger.kernel.org # v4.19+ Signed-off-by: Andreas Gruenbacher Signed-off-by: Linus Torvalds --- fs/gfs2/bmap.c | 40 +++++++++++++++++----------------------- 1 file changed, 17 insertions(+), 23 deletions(-) diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 38d88fcb6988..0d643306c255 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -826,7 +826,7 @@ static int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length, ret = gfs2_meta_inode_buffer(ip, &dibh); if (ret) goto unlock; - iomap->private = dibh; + mp->mp_bh[0] = dibh; if (gfs2_is_stuffed(ip)) { if (flags & IOMAP_WRITE) { @@ -863,9 +863,6 @@ unstuff: len = lblock_stop - lblock + 1; iomap->length = len << inode->i_blkbits; - get_bh(dibh); - mp->mp_bh[0] = dibh; - height = ip->i_height; while ((lblock + 1) * sdp->sd_sb.sb_bsize > sdp->sd_heightsize[height]) height++; @@ -898,8 +895,6 @@ out: iomap->bdev = inode->i_sb->s_bdev; unlock: up_read(&ip->i_rw_mutex); - if (ret && dibh) - brelse(dibh); return ret; do_alloc: @@ -980,9 +975,9 @@ static void gfs2_iomap_journaled_page_done(struct inode *inode, loff_t pos, static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, loff_t length, unsigned flags, - struct iomap *iomap) + struct iomap *iomap, + struct metapath *mp) { - struct metapath mp = { .mp_aheight = 1, }; struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); unsigned int data_blocks = 0, ind_blocks = 0, rblocks; @@ -996,9 +991,9 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, unstuff = gfs2_is_stuffed(ip) && pos + length > gfs2_max_stuffed_size(ip); - ret = gfs2_iomap_get(inode, pos, length, flags, iomap, &mp); + ret = gfs2_iomap_get(inode, pos, length, flags, iomap, mp); if (ret) - goto out_release; + goto out_unlock; alloc_required = unstuff || iomap->type == IOMAP_HOLE; @@ -1013,7 +1008,7 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, ret = gfs2_quota_lock_check(ip, &ap); if (ret) - goto out_release; + goto out_unlock; ret = gfs2_inplace_reserve(ip, &ap); if (ret) @@ -1038,17 +1033,15 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, ret = gfs2_unstuff_dinode(ip, NULL); if (ret) goto out_trans_end; - release_metapath(&mp); - brelse(iomap->private); - iomap->private = NULL; + release_metapath(mp); ret = gfs2_iomap_get(inode, iomap->offset, iomap->length, - flags, iomap, &mp); + flags, iomap, mp); if (ret) goto out_trans_end; } if (iomap->type == IOMAP_HOLE) { - ret = gfs2_iomap_alloc(inode, iomap, flags, &mp); + ret = gfs2_iomap_alloc(inode, iomap, flags, mp); if (ret) { gfs2_trans_end(sdp); gfs2_inplace_release(ip); @@ -1056,7 +1049,6 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, goto out_qunlock; } } - release_metapath(&mp); if (gfs2_is_jdata(ip)) iomap->page_done = gfs2_iomap_journaled_page_done; return 0; @@ -1069,10 +1061,7 @@ out_trans_fail: out_qunlock: if (alloc_required) gfs2_quota_unlock(ip); -out_release: - if (iomap->private) - brelse(iomap->private); - release_metapath(&mp); +out_unlock: gfs2_write_unlock(inode); return ret; } @@ -1088,10 +1077,10 @@ static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length, trace_gfs2_iomap_start(ip, pos, length, flags); if ((flags & IOMAP_WRITE) && !(flags & IOMAP_DIRECT)) { - ret = gfs2_iomap_begin_write(inode, pos, length, flags, iomap); + ret = gfs2_iomap_begin_write(inode, pos, length, flags, iomap, &mp); } else { ret = gfs2_iomap_get(inode, pos, length, flags, iomap, &mp); - release_metapath(&mp); + /* * Silently fall back to buffered I/O for stuffed files or if * we've hot a hole (see gfs2_file_direct_write). @@ -1100,6 +1089,11 @@ static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length, iomap->type != IOMAP_MAPPED) ret = -ENOTBLK; } + if (!ret) { + get_bh(mp.mp_bh[0]); + iomap->private = mp.mp_bh[0]; + } + release_metapath(&mp); trace_gfs2_iomap_end(ip, iomap, ret); return ret; }