From: Bob Peterson <rpeterso@redhat.com> Date: Tue, 29 Jan 2008 09:02:48 -0600 Subject: [gfs2] speed up read/write performance Message-id: 1201618968.18461.132.camel@technetium.msp.redhat.com O-Subject: [RHEL5.2 PATCH][GFS2] bz 253990: GFS2: Speed up GFS2 read/write performance Bugzilla: 253990 Hi, This is the long-awaited respin of my previous post for 253990. The previous version had some problems that are hopefully fixed. This is a combination of 20 or so upstream patches to increase performance for read/write operations for the GFS2 file system. This was done for bugzilla bug #253990 (see the bugzilla record for more details). The benchmark performance tests like iozone (and similar) were targeted. Initial tests indicate up to 25% increase in performance (mileage may vary). Regards, Bob Peterson Red Hat GFS Signed-off-by: Bob Peterson <rpeterso@redhat.com> -- Acked-by: Steven Whitehouse <swhiteho@redhat.com> diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index da0ad28..0c0fe6c 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -166,7 +166,7 @@ int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page) di->di_blocks = cpu_to_be64(ip->i_di.di_blocks); } - ip->i_di.di_height = 1; + ip->i_height = 1; di->di_height = cpu_to_be16(1); out_brelse: @@ -177,43 +177,6 @@ out: } /** - * calc_tree_height - Calculate the height of a metadata tree - * @ip: The GFS2 inode - * @size: The proposed size of the file - * - * Work out how tall a metadata tree needs to be in order to accommodate a - * file of a particular size. If size is less than the current size of - * the inode, then the current size of the inode is used instead of the - * supplied one. - * - * Returns: the height the tree should be - */ - -static unsigned int calc_tree_height(struct gfs2_inode *ip, u64 size) -{ - struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - u64 *arr; - unsigned int max, height; - - if (ip->i_di.di_size > size) - size = ip->i_di.di_size; - - if (gfs2_is_dir(ip)) { - arr = sdp->sd_jheightsize; - max = sdp->sd_max_jheight; - } else { - arr = sdp->sd_heightsize; - max = sdp->sd_max_height; - } - - for (height = 0; height < max; height++) - if (arr[height] >= size) - break; - - return height; -} - -/** * build_height - Build a metadata tree of the requested height * @ip: The GFS2 inode * @height: The height to build to @@ -225,7 +188,7 @@ static unsigned int calc_tree_height(struct gfs2_inode *ip, u64 size) static int build_height(struct inode *inode, unsigned height) { struct gfs2_inode *ip = GFS2_I(inode); - unsigned new_height = height - ip->i_di.di_height; + unsigned new_height = height - ip->i_height; struct buffer_head *dibh; struct buffer_head *blocks[GFS2_MAX_META_HEIGHT]; struct gfs2_dinode *di; @@ -234,7 +197,7 @@ static int build_height(struct inode *inode, unsigned height) u64 bn; unsigned n; - if (height <= ip->i_di.di_height) + if (height <= ip->i_height) return 0; error = gfs2_meta_inode_buffer(ip, &dibh); @@ -270,10 +233,10 @@ static int build_height(struct inode *inode, unsigned height) di = (struct gfs2_dinode *)dibh->b_data; gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode)); *(__be64 *)(di + 1) = cpu_to_be64(bn); - ip->i_di.di_height += new_height; + ip->i_height += new_height; ip->i_di.di_blocks += new_height; gfs2_set_inode_blocks(&ip->i_inode); - di->di_height = cpu_to_be16(ip->i_di.di_height); + di->di_height = cpu_to_be16(ip->i_height); di->di_blocks = cpu_to_be64(ip->i_di.di_blocks); brelse(dibh); return error; @@ -342,11 +305,10 @@ static void find_metapath(struct gfs2_inode *ip, u64 block, struct metapath *mp) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - u64 b = block; unsigned int i; - for (i = ip->i_di.di_height; i--;) - mp->mp_list[i] = do_div(b, sdp->sd_inptrs); + for (i = ip->i_height; i--;) + mp->mp_list[i] = do_div(block, sdp->sd_inptrs); } @@ -407,7 +369,7 @@ static int lookup_block(struct gfs2_inode *ip, struct buffer_head *bh, if (!create) return 0; - if (height == ip->i_di.di_height - 1 && !gfs2_is_dir(ip)) + if (height == ip->i_height - 1 && !gfs2_is_dir(ip)) *block = gfs2_alloc_data(ip); else *block = gfs2_alloc_meta(ip); @@ -452,14 +414,13 @@ static inline void bmap_unlock(struct inode *inode, int create) * Returns: errno */ -int gfs2_block_map(struct inode *inode, u64 lblock, int create, - struct buffer_head *bh_map) +int gfs2_block_map(struct inode *inode, sector_t lblock, + struct buffer_head *bh_map, int create) { struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); struct buffer_head *bh; - unsigned int bsize; - unsigned int height; + unsigned int bsize = sdp->sd_sb.sb_bsize; unsigned int end_of_metadata; unsigned int x; int error = 0; @@ -469,6 +430,8 @@ int gfs2_block_map(struct inode *inode, u64 lblock, int create, unsigned int maxlen = bh_map->b_size >> inode->i_blkbits; struct metapath mp; u64 size; + struct buffer_head *dibh = NULL; + const u64 *arr = sdp->sd_heightsize; BUG_ON(maxlen == 0); @@ -479,26 +442,30 @@ int gfs2_block_map(struct inode *inode, u64 lblock, int create, clear_buffer_mapped(bh_map); clear_buffer_new(bh_map); clear_buffer_boundary(bh_map); - bsize = gfs2_is_dir(ip) ? sdp->sd_jbsize : sdp->sd_sb.sb_bsize; + if (gfs2_is_dir(ip)) { + bsize = sdp->sd_jbsize; + arr = sdp->sd_jheightsize; + } size = (lblock + 1) * bsize; - if (size > ip->i_di.di_size) { - height = calc_tree_height(ip, size); - if (ip->i_di.di_height < height) { - if (!create) - goto out_ok; - - error = build_height(inode, height); - if (error) - goto out_fail; - } + if (size > arr[ip->i_height]) { + u8 height = ip->i_height; + if (!create) + goto out_ok; + while(size > arr[height]) + height++; + error = build_height(inode, height); + if (error) + goto out_fail; } find_metapath(ip, lblock, &mp); - end_of_metadata = ip->i_di.di_height - 1; + end_of_metadata = ip->i_height - 1; error = gfs2_meta_inode_buffer(ip, &bh); if (error) goto out_fail; + dibh = bh; + get_bh(dibh); for (x = 0; x < end_of_metadata; x++) { lookup_block(ip, bh, x, &mp, create, &new, &dblock); @@ -517,13 +484,8 @@ int gfs2_block_map(struct inode *inode, u64 lblock, int create, if (boundary) set_buffer_boundary(bh_map); if (new) { - struct buffer_head *dibh; - error = gfs2_meta_inode_buffer(ip, &dibh); - if (!error) { - gfs2_trans_add_bh(ip->i_gl, dibh, 1); - gfs2_dinode_out(ip, dibh->b_data); - brelse(dibh); - } + gfs2_trans_add_bh(ip->i_gl, dibh, 1); + gfs2_dinode_out(ip, dibh->b_data); set_buffer_new(bh_map); goto out_brelse; } @@ -544,6 +506,8 @@ out_brelse: out_ok: error = 0; out_fail: + if (dibh) + brelse(dibh); bmap_unlock(inode, create); return error; } @@ -559,7 +523,7 @@ int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsi BUG_ON(!new); bh.b_size = 1 << (inode->i_blkbits + 5); - ret = gfs2_block_map(inode, lblock, create, &bh); + ret = gfs2_block_map(inode, lblock, &bh, create); *extlen = bh.b_size >> inode->i_blkbits; *dblock = bh.b_blocknr; if (buffer_new(&bh)) @@ -621,7 +585,7 @@ static int recursive_scan(struct gfs2_inode *ip, struct buffer_head *dibh, if (error) goto out; - if (height < ip->i_di.di_height - 1) + if (height < ip->i_height - 1) for (; top < bottom; top++, first = 0) { if (!*top) continue; @@ -679,7 +643,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh, sm->sm_first = 0; } - metadata = (height != ip->i_di.di_height - 1); + metadata = (height != ip->i_height - 1); if (metadata) revokes = (height) ? sdp->sd_inptrs : sdp->sd_diptrs; @@ -713,7 +677,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh, else goto out; /* Nothing to do */ - gfs2_rlist_alloc(&rlist, LM_ST_EXCLUSIVE, 0); + gfs2_rlist_alloc(&rlist, LM_ST_EXCLUSIVE); for (x = 0; x < rlist.rl_rgrps; x++) { struct gfs2_rgrpd *rgd; @@ -804,7 +768,6 @@ static int do_grow(struct gfs2_inode *ip, u64 size) struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_alloc *al; struct buffer_head *dibh; - unsigned int h; int error; al = gfs2_alloc_get(ip); @@ -830,20 +793,24 @@ static int do_grow(struct gfs2_inode *ip, u64 size) goto out_ipres; if (size > sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)) { + const u64 *arr = sdp->sd_heightsize; + if (gfs2_is_stuffed(ip)) { error = gfs2_unstuff_dinode(ip, NULL); if (error) goto out_end_trans; } - h = calc_tree_height(ip, size); - if (ip->i_di.di_height < h) { - down_write(&ip->i_rw_mutex); - error = build_height(&ip->i_inode, h); - up_write(&ip->i_rw_mutex); - if (error) - goto out_end_trans; + down_write(&ip->i_rw_mutex); + if (size > arr[ip->i_height]) { + u8 height = ip->i_height; + while(size > arr[height]) + height++; + error = build_height(&ip->i_inode, height); } + up_write(&ip->i_rw_mutex); + if (error) + goto out_end_trans; } ip->i_di.di_size = size; @@ -910,7 +877,7 @@ static int gfs2_block_truncate_page(struct address_space *mapping) err = 0; if (!buffer_mapped(bh)) { - gfs2_get_block(inode, iblock, bh, 0); + gfs2_block_map(inode, iblock, bh, 0); /* unmapped? It's a hole - nothing to do */ if (!buffer_mapped(bh)) goto unlock; @@ -990,7 +957,7 @@ out: static int trunc_dealloc(struct gfs2_inode *ip, u64 size) { - unsigned int height = ip->i_di.di_height; + unsigned int height = ip->i_height; u64 lblock; struct metapath mp; int error; @@ -1041,7 +1008,7 @@ static int trunc_end(struct gfs2_inode *ip) goto out; if (!ip->i_di.di_size) { - ip->i_di.di_height = 0; + ip->i_height = 0; ip->i_di.di_goal_meta = ip->i_di.di_goal_data = ip->i_no_addr; @@ -1226,8 +1193,13 @@ int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset, do_div(lblock_stop, bsize); } else { unsigned int shift = sdp->sd_sb.sb_bsize_shift; + u64 end_of_file = (ip->i_di.di_size + sdp->sd_sb.sb_bsize - 1) >> shift; lblock = offset >> shift; lblock_stop = (offset + len + sdp->sd_sb.sb_bsize - 1) >> shift; + if (lblock_stop > end_of_file) { + *alloc_required = 1; + return 0; + } } for (; lblock < lblock_stop; lblock += extlen) { diff --git a/fs/gfs2/bmap.h b/fs/gfs2/bmap.h index ac2fd04..b0ce994 100644 --- a/fs/gfs2/bmap.h +++ b/fs/gfs2/bmap.h @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -15,7 +15,7 @@ struct gfs2_inode; struct page; int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page); -int gfs2_block_map(struct inode *inode, u64 lblock, int create, struct buffer_head *bh); +int gfs2_block_map(struct inode *inode, sector_t lblock, struct buffer_head *bh, int create); int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsigned *extlen); int gfs2_truncatei(struct gfs2_inode *ip, u64 size); diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index 06db257..e0fee7b 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -1894,7 +1894,7 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len, l_blocks++; } - gfs2_rlist_alloc(&rlist, LM_ST_EXCLUSIVE, 0); + gfs2_rlist_alloc(&rlist, LM_ST_EXCLUSIVE); for (x = 0; x < rlist.rl_rgrps; x++) { struct gfs2_rgrpd *rgd; diff --git a/fs/gfs2/eattr.c b/fs/gfs2/eattr.c index bee9970..7336e19 100644 --- a/fs/gfs2/eattr.c +++ b/fs/gfs2/eattr.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -1347,7 +1347,7 @@ static int ea_dealloc_indirect(struct gfs2_inode *ip) else goto out; - gfs2_rlist_alloc(&rlist, LM_ST_EXCLUSIVE, 0); + gfs2_rlist_alloc(&rlist, LM_ST_EXCLUSIVE); for (x = 0; x < rlist.rl_rgrps; x++) { struct gfs2_rgrpd *rgd; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 2df8415..12034ba 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -603,11 +603,7 @@ static void run_queue(struct gfs2_glock *gl) gh = list_entry(gl->gl_waiters1.next, struct gfs2_holder, gh_list); - if (test_bit(HIF_MUTEX, &gh->gh_iflags)) - blocked = rq_mutex(gh); - else - gfs2_assert_warn(gl->gl_sbd, 0); - + blocked = rq_mutex(gh); } else if (test_bit(GLF_DEMOTE, &gl->gl_flags)) { blocked = rq_demote(gl); if (gl->gl_waiters2 && !blocked) { @@ -641,27 +637,21 @@ static void run_queue(struct gfs2_glock *gl) static void gfs2_glmutex_lock(struct gfs2_glock *gl) { - struct gfs2_holder gh; - - gfs2_holder_init(gl, 0, 0, &gh); - set_bit(HIF_MUTEX, &gh.gh_iflags); - if (test_and_set_bit(HIF_WAIT, &gh.gh_iflags)) - BUG(); - spin_lock(&gl->gl_spin); if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) { + struct gfs2_holder gh; + + gfs2_holder_init(gl, 0, 0, &gh); + set_bit(HIF_WAIT, &gh.gh_iflags); list_add_tail(&gh.gh_list, &gl->gl_waiters1); + spin_unlock(&gl->gl_spin); + wait_on_holder(&gh); + gfs2_holder_uninit(&gh); } else { gl->gl_owner_pid = current->pid; gl->gl_ip = (unsigned long)__builtin_return_address(0); - clear_bit(HIF_WAIT, &gh.gh_iflags); - smp_mb(); - wake_up_bit(&gh.gh_iflags, HIF_WAIT); + spin_unlock(&gl->gl_spin); } - spin_unlock(&gl->gl_spin); - - wait_on_holder(&gh); - gfs2_holder_uninit(&gh); } /** @@ -1260,12 +1250,11 @@ void gfs2_glock_dq(struct gfs2_holder *gh) list_del_init(&gh->gh_list); if (list_empty(&gl->gl_holders)) { - spin_unlock(&gl->gl_spin); - - if (glops->go_unlock) + if (glops->go_unlock) { + spin_unlock(&gl->gl_spin); glops->go_unlock(gh); - - spin_lock(&gl->gl_spin); + spin_lock(&gl->gl_spin); + } gl->gl_stamp = jiffies; } @@ -1616,11 +1605,12 @@ void gfs2_glock_schedule_for_reclaim(struct gfs2_glock *gl) if (list_empty(&gl->gl_reclaim)) { gfs2_glock_hold(gl); list_add(&gl->gl_reclaim, &sdp->sd_reclaim_list); - atomic_inc(&sdp->sd_reclaim_count); + atomic_inc(&sdp->sd_reclaim_count); + spin_unlock(&sdp->sd_reclaim_lock); + wake_up(&sdp->sd_reclaim_wq); } - spin_unlock(&sdp->sd_reclaim_lock); - - wake_up(&sdp->sd_reclaim_wq); + else + spin_unlock(&sdp->sd_reclaim_lock); } /** diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 31e0084..775b66f 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -119,6 +119,27 @@ static void meta_go_sync(struct gfs2_glock *gl) } /** + * gfs2_meta_inval - Invalidate all buffers associated with a glock + * @gl: the glock + * + */ + +static void gfs2_meta_inval(struct gfs2_glock *gl) +{ + struct gfs2_sbd *sdp = gl->gl_sbd; + struct inode *aspace = gl->gl_aspace; + struct address_space *mapping = gl->gl_aspace->i_mapping; + + gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count)); + + atomic_inc(&aspace->i_writecount); + truncate_inode_pages(mapping, 0); + atomic_dec(&aspace->i_writecount); + + gfs2_assert_withdraw(sdp, !mapping->nrpages); +} + +/** * meta_go_inval - invalidate the metadata for this glock * @gl: the glock * @flags: diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index dc795b1..e193b23 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -44,7 +44,6 @@ struct gfs2_log_header_host { struct gfs2_log_operations { void (*lo_add) (struct gfs2_sbd *sdp, struct gfs2_log_element *le); - void (*lo_incore_commit) (struct gfs2_sbd *sdp, struct gfs2_trans *tr); void (*lo_before_commit) (struct gfs2_sbd *sdp); void (*lo_after_commit) (struct gfs2_sbd *sdp, struct gfs2_ail *ai); void (*lo_before_scan) (struct gfs2_jdesc *jd, @@ -142,7 +141,6 @@ struct gfs2_glock_operations { enum { /* Actions */ - HIF_MUTEX = 0, HIF_PROMOTE = 1, /* States */ @@ -252,7 +250,6 @@ struct gfs2_dinode_host { u64 di_goal_data; /* data block goal */ u64 di_generation; /* generation number for NFS */ u32 di_flags; /* GFS2_DIF_... */ - u16 di_height; /* height of metadata */ /* These only apply to directories */ u16 di_depth; /* Number of bits in the table */ u32 di_entries; /* The number of entries in the directory */ @@ -273,9 +270,8 @@ struct gfs2_inode { struct gfs2_alloc *i_alloc; u64 i_last_rg_alloc; - spinlock_t i_spin; struct rw_semaphore i_rw_mutex; - unsigned long i_last_pfault; + u8 i_height; }; /* @@ -372,8 +368,17 @@ struct gfs2_ail { u64 ai_sync_gen; }; +struct gfs2_journal_extent { + struct list_head extent_list; + + unsigned int lblock; /* First logical block */ + u64 dblock; /* First disk block */ + u64 blocks; +}; + struct gfs2_jdesc { struct list_head jd_list; + struct list_head extent_list; struct inode *jd_inode; unsigned int jd_jid; @@ -501,9 +506,9 @@ struct gfs2_sbd { u32 sd_qc_per_block; u32 sd_max_dirres; /* Max blocks needed to add a directory entry */ u32 sd_max_height; /* Max height of a file's metadata tree */ - u64 sd_heightsize[GFS2_MAX_META_HEIGHT]; + u64 sd_heightsize[GFS2_MAX_META_HEIGHT + 1]; u32 sd_max_jheight; /* Max height of journaled file's meta tree */ - u64 sd_jheightsize[GFS2_MAX_META_HEIGHT]; + u64 sd_jheightsize[GFS2_MAX_META_HEIGHT + 1]; struct gfs2_args sd_args; /* Mount arguments */ struct gfs2_tune sd_tune; /* Filesystem tuning structure */ @@ -538,7 +543,6 @@ struct gfs2_sbd { /* StatFS stuff */ spinlock_t sd_statfs_spin; - struct mutex sd_statfs_mutex; struct gfs2_statfs_change_host sd_statfs_master; struct gfs2_statfs_change_host sd_statfs_local; unsigned long sd_statfs_sync_time; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index f9cea71..8ff4b78 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -249,12 +249,10 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) { struct gfs2_dinode_host *di = &ip->i_di; const struct gfs2_dinode *str = buf; + u16 height; - if (ip->i_no_addr != be64_to_cpu(str->di_num.no_addr)) { - if (gfs2_consist_inode(ip)) - gfs2_dinode_print(ip); - return -EIO; - } + if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr))) + goto corrupt; ip->i_no_formal_ino = be64_to_cpu(str->di_num.no_formal_ino); ip->i_inode.i_mode = be32_to_cpu(str->di_mode); ip->i_inode.i_rdev = 0; @@ -291,7 +289,10 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) di->di_flags = be32_to_cpu(str->di_flags); gfs2_set_inode_flags(&ip->i_inode); - di->di_height = be16_to_cpu(str->di_height); + height = be16_to_cpu(str->di_height); + if (unlikely(height > GFS2_MAX_META_HEIGHT)) + goto corrupt; + ip->i_height = (u8)height; di->di_depth = be16_to_cpu(str->di_depth); di->di_entries = be32_to_cpu(str->di_entries); @@ -301,6 +302,10 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) gfs2_set_aops(&ip->i_inode); return 0; +corrupt: + if (gfs2_consist_inode(ip)) + gfs2_dinode_print(ip); + return -EIO; } /** @@ -860,7 +865,7 @@ static int link_dinode(struct gfs2_inode *dip, const struct qstr *name, error = alloc_required = gfs2_diradd_alloc_required(&dip->i_inode, name); if (alloc_required < 0) - goto fail; + goto fail_quota_locks; if (alloc_required) { error = gfs2_quota_check(dip, dip->i_inode.i_uid, dip->i_inode.i_gid); if (error) @@ -1401,7 +1406,7 @@ void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf) str->di_generation = cpu_to_be64(di->di_generation); str->di_flags = cpu_to_be32(di->di_flags); - str->di_height = cpu_to_be16(di->di_height); + str->di_height = cpu_to_be16(ip->i_height); str->di_payload_format = cpu_to_be32(S_ISDIR(ip->i_inode.i_mode) && !(ip->i_di.di_flags & GFS2_DIF_EXHASH) ? GFS2_FORMAT_DE : 0); @@ -1430,7 +1435,7 @@ void gfs2_dinode_print(const struct gfs2_inode *ip) printk(KERN_INFO " di_goal_data = %llu\n", (unsigned long long)di->di_goal_data); printk(KERN_INFO " di_flags = 0x%.8X\n", di->di_flags); - printk(KERN_INFO " di_height = %u\n", di->di_height); + printk(KERN_INFO " i_height = %u\n", ip->i_height); printk(KERN_INFO " di_depth = %u\n", di->di_depth); printk(KERN_INFO " di_entries = %u\n", di->di_entries); printk(KERN_INFO " di_eattr = %llu\n", diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h index 2e86984..d204643 100644 --- a/fs/gfs2/inode.h +++ b/fs/gfs2/inode.h @@ -12,7 +12,7 @@ static inline int gfs2_is_stuffed(const struct gfs2_inode *ip) { - return !ip->i_di.di_height; + return !ip->i_height; } static inline int gfs2_is_jdata(const struct gfs2_inode *ip) diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 91a50d3..ceb21f3 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -123,6 +123,7 @@ static void gfs2_ail1_start_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai) unlock_buffer(bh); brelse(bh); } + gfs2_log_lock(sdp); retry = 1; @@ -354,18 +355,14 @@ void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks) static u64 log_bmap(struct gfs2_sbd *sdp, unsigned int lbn) { - struct inode *inode = sdp->sd_jdesc->jd_inode; - int error; - struct buffer_head bh_map = { .b_state = 0, .b_blocknr = 0 }; - - bh_map.b_size = 1 << inode->i_blkbits; - error = gfs2_block_map(inode, lbn, 0, &bh_map); - if (error || !bh_map.b_blocknr) - printk(KERN_INFO "error=%d, dbn=%llu lbn=%u", error, - (unsigned long long)bh_map.b_blocknr, lbn); - gfs2_assert_withdraw(sdp, !error && bh_map.b_blocknr); - - return bh_map.b_blocknr; + struct gfs2_journal_extent *je; + + list_for_each_entry(je, &sdp->sd_jdesc->extent_list, extent_list) { + if (lbn >= je->lblock && lbn < je->lblock + je->blocks) + return je->dblock + lbn - je->lblock; + } + + return -1; } /** @@ -780,7 +777,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl) static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr) { unsigned int reserved; - unsigned int old; + unsigned int unused; gfs2_log_lock(sdp); @@ -792,19 +789,31 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr) sdp->sd_log_commited_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm; gfs2_assert_withdraw(sdp, ((int)sdp->sd_log_commited_revoke) >= 0); reserved = calc_reserved(sdp); - old = sdp->sd_log_blks_free; - sdp->sd_log_blks_free += tr->tr_reserved - - (reserved - sdp->sd_log_blks_reserved); - - gfs2_assert_withdraw(sdp, sdp->sd_log_blks_free >= old); + unused = sdp->sd_log_blks_reserved - reserved + tr->tr_reserved; + gfs2_assert_withdraw(sdp, unused >= 0); + sdp->sd_log_blks_free += unused; gfs2_assert_withdraw(sdp, sdp->sd_log_blks_free <= sdp->sd_jdesc->jd_blocks); - sdp->sd_log_blks_reserved = reserved; gfs2_log_unlock(sdp); } +static void buf_lo_incore_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) +{ + struct list_head *head = &tr->tr_list_buf; + struct gfs2_bufdata *bd; + + gfs2_log_lock(sdp); + while (!list_empty(head)) { + bd = list_entry(head->next, struct gfs2_bufdata, bd_list_tr); + list_del_init(&bd->bd_list_tr); + tr->tr_num_buf--; + } + gfs2_log_unlock(sdp); + gfs2_assert_warn(sdp, !tr->tr_num_buf); +} + /** * gfs2_log_commit - Commit a transaction to the log * @sdp: the filesystem @@ -816,7 +825,7 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr) void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) { log_refund(sdp, tr); - lops_incore_commit(sdp, tr); + buf_lo_incore_commit(sdp, tr); sdp->sd_vfs->s_dirt = 1; up_read(&sdp->sd_log_flush_lock); diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index e901f8f..f328092 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -193,21 +193,6 @@ out: unlock_buffer(bd->bd_bh); } -static void buf_lo_incore_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) -{ - struct list_head *head = &tr->tr_list_buf; - struct gfs2_bufdata *bd; - - gfs2_log_lock(sdp); - while (!list_empty(head)) { - bd = list_entry(head->next, struct gfs2_bufdata, bd_list_tr); - list_del_init(&bd->bd_list_tr); - tr->tr_num_buf--; - } - gfs2_log_unlock(sdp); - gfs2_assert_warn(sdp, !tr->tr_num_buf); -} - static void buf_lo_before_commit(struct gfs2_sbd *sdp) { struct buffer_head *bh; @@ -784,7 +769,6 @@ const struct gfs2_log_operations gfs2_glock_lops = { const struct gfs2_log_operations gfs2_buf_lops = { .lo_add = buf_lo_add, - .lo_incore_commit = buf_lo_incore_commit, .lo_before_commit = buf_lo_before_commit, .lo_after_commit = buf_lo_after_commit, .lo_before_scan = buf_lo_before_scan, @@ -810,7 +794,6 @@ const struct gfs2_log_operations gfs2_rg_lops = { const struct gfs2_log_operations gfs2_databuf_lops = { .lo_add = databuf_lo_add, - .lo_incore_commit = buf_lo_incore_commit, .lo_before_commit = databuf_lo_before_commit, .lo_after_commit = databuf_lo_after_commit, .lo_scan_elements = databuf_lo_scan_elements, diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h index 41a00df..3c0b273 100644 --- a/fs/gfs2/lops.h +++ b/fs/gfs2/lops.h @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -57,15 +57,6 @@ static inline void lops_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) le->le_ops->lo_add(sdp, le); } -static inline void lops_incore_commit(struct gfs2_sbd *sdp, - struct gfs2_trans *tr) -{ - int x; - for (x = 0; gfs2_log_ops[x]; x++) - if (gfs2_log_ops[x]->lo_incore_commit) - gfs2_log_ops[x]->lo_incore_commit(sdp, tr); -} - static inline void lops_before_commit(struct gfs2_sbd *sdp) { int x; diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index ca2c456..1674a1c 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -30,7 +30,6 @@ static void gfs2_init_inode_once(void *foo, kmem_cache_t *cachep, unsigned long if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) == SLAB_CTOR_CONSTRUCTOR) { inode_init_once(&ip->i_inode); - spin_lock_init(&ip->i_spin); init_rwsem(&ip->i_rw_mutex); ip->i_alloc = NULL; } diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index f5d6e75..232c1ff 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -87,27 +87,6 @@ void gfs2_aspace_put(struct inode *aspace) } /** - * gfs2_meta_inval - Invalidate all buffers associated with a glock - * @gl: the glock - * - */ - -void gfs2_meta_inval(struct gfs2_glock *gl) -{ - struct gfs2_sbd *sdp = gl->gl_sbd; - struct inode *aspace = gl->gl_aspace; - struct address_space *mapping = gl->gl_aspace->i_mapping; - - gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count)); - - atomic_inc(&aspace->i_writecount); - truncate_inode_pages(mapping, 0); - atomic_dec(&aspace->i_writecount); - - gfs2_assert_withdraw(sdp, !mapping->nrpages); -} - -/** * gfs2_meta_sync - Sync all buffers associated with a glock * @gl: The glock * @@ -221,13 +200,14 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags, struct buffer_head **bhp) { *bhp = getbuf(gl, blkno, CREATE); - if (!buffer_uptodate(*bhp)) + if (!buffer_uptodate(*bhp)) { ll_rw_block(READ, 1, bhp); - if (flags & DIO_WAIT) { - int error = gfs2_meta_wait(gl->gl_sbd, *bhp); - if (error) { - brelse(*bhp); - return error; + if (flags & DIO_WAIT) { + int error = gfs2_meta_wait(gl->gl_sbd, *bhp); + if (error) { + brelse(*bhp); + return error; + } } } @@ -261,42 +241,6 @@ int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh) return 0; } -/** - * gfs2_attach_bufdata - attach a struct gfs2_bufdata structure to a buffer - * @gl: the glock the buffer belongs to - * @bh: The buffer to be attached to - * @meta: Flag to indicate whether its metadata or not - */ - -void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh, - int meta) -{ - struct gfs2_bufdata *bd; - - if (meta) - lock_page(bh->b_page); - - if (bh->b_private) { - if (meta) - unlock_page(bh->b_page); - return; - } - - bd = kmem_cache_zalloc(gfs2_bufdata_cachep, GFP_NOFS | __GFP_NOFAIL), - bd->bd_bh = bh; - bd->bd_gl = gl; - - INIT_LIST_HEAD(&bd->bd_list_tr); - if (meta) - lops_init_le(&bd->bd_le, &gfs2_buf_lops); - else - lops_init_le(&bd->bd_le, &gfs2_databuf_lops); - bh->b_private = bd; - - if (meta) - unlock_page(bh->b_page); -} - void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int meta) { struct gfs2_sbd *sdp = GFS2_SB(bh->b_page->mapping->host); diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h index 73e3b1c..edea2b0 100644 --- a/fs/gfs2/meta_io.h +++ b/fs/gfs2/meta_io.h @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -40,7 +40,6 @@ static inline void gfs2_buffer_copy_tail(struct buffer_head *to_bh, struct inode *gfs2_aspace_get(struct gfs2_sbd *sdp); void gfs2_aspace_put(struct inode *aspace); -void gfs2_meta_inval(struct gfs2_glock *gl); void gfs2_meta_sync(struct gfs2_glock *gl); struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno); @@ -48,9 +47,6 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags, struct buffer_head **bhp); int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh); -void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh, - int meta); - void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int meta); diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/ops_address.c index 22ac7ee..9699278 100644 --- a/fs/gfs2/ops_address.c +++ b/fs/gfs2/ops_address.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -58,22 +58,6 @@ static void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page, } /** - * gfs2_get_block - Fills in a buffer head with details about a block - * @inode: The inode - * @lblock: The block number to look up - * @bh_result: The buffer head to return the result in - * @create: Non-zero if we may add block to the file - * - * Returns: errno - */ - -int gfs2_get_block(struct inode *inode, sector_t lblock, - struct buffer_head *bh_result, int create) -{ - return gfs2_block_map(inode, lblock, create, bh_result); -} - -/** * gfs2_get_block_noalloc - Fills in a buffer head with details about a block * @inode: The inode * @lblock: The block number to look up @@ -88,7 +72,7 @@ static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock, { int error; - error = gfs2_block_map(inode, lblock, 0, bh_result); + error = gfs2_block_map(inode, lblock, bh_result, 0); if (error) return error; if (!buffer_mapped(bh_result)) @@ -99,7 +83,7 @@ static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock, static int gfs2_get_block_direct(struct inode *inode, sector_t lblock, struct buffer_head *bh_result, int create) { - return gfs2_block_map(inode, lblock, 0, bh_result); + return gfs2_block_map(inode, lblock, bh_result, 0); } /** @@ -119,11 +103,9 @@ static int gfs2_writepage_common(struct page *page, loff_t i_size = i_size_read(inode); pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT; unsigned offset; - int ret = -EIO; if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(ip->i_gl))) goto out; - ret = 0; if (current->journal_info) goto redirty; /* Is the page fully outside i_size? (truncate in progress) */ @@ -520,7 +502,7 @@ skip_lock: error = stuffed_readpage(ip, page); unlock_page(page); } else - error = mpage_readpage(page, gfs2_get_block); + error = mpage_readpage(page, gfs2_block_map); if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) error = -EIO; @@ -553,7 +535,7 @@ out_unlock: * Any I/O we ignore at this time will be done via readpage later. * 2. We don't handle stuffed files here we let readpage do the honours. * 3. mpage_readpages() does most of the heavy lifting in the common case. - * 4. gfs2_get_block() is relied upon to set BH_Boundary in the right places. + * 4. gfs2_block_map() is relied upon to set BH_Boundary in the right places. * 5. We use LM_FLAG_TRY_1CB here, effectively we then have lock-ahead as * well as read-ahead. */ @@ -584,7 +566,7 @@ static int gfs2_readpages(struct file *file, struct address_space *mapping, } skip_lock: if (!gfs2_is_stuffed(ip)) - ret = mpage_readpages(mapping, pages, nr_pages, gfs2_get_block); + ret = mpage_readpages(mapping, pages, nr_pages, gfs2_block_map); if (do_unlock) { gfs2_glock_dq_m(1, &gh); @@ -712,7 +694,7 @@ static int gfs2_prepare_write(struct file *file, struct page *page, } prepare_write: - error = block_prepare_write(page, from, to, gfs2_get_block); + error = block_prepare_write(page, from, to, gfs2_block_map); out: if (error) { @@ -882,7 +864,7 @@ static sector_t gfs2_bmap(struct address_space *mapping, sector_t lblock) return 0; if (!gfs2_is_stuffed(ip)) - dblock = generic_block_bmap(mapping, lblock, gfs2_get_block); + dblock = generic_block_bmap(mapping, lblock, gfs2_block_map); gfs2_glock_dq_uninit(&i_gh); diff --git a/fs/gfs2/ops_address.h b/fs/gfs2/ops_address.h index 485c50a..2452e15 100644 --- a/fs/gfs2/ops_address.h +++ b/fs/gfs2/ops_address.h @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -14,8 +14,6 @@ #include <linux/buffer_head.h> #include <linux/mm.h> -extern int gfs2_get_block(struct inode *inode, sector_t lblock, - struct buffer_head *bh_result, int create); extern int gfs2_releasepage(struct page *page, gfp_t gfp_mask); extern void gfs2_set_aops(struct inode *inode); diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index b11603e..6847479 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -21,6 +21,7 @@ #include "gfs2.h" #include "incore.h" +#include "bmap.h" #include "daemon.h" #include "glock.h" #include "glops.h" @@ -60,7 +61,6 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) mutex_init(&sdp->sd_inum_mutex); spin_lock_init(&sdp->sd_statfs_spin); - mutex_init(&sdp->sd_statfs_mutex); spin_lock_init(&sdp->sd_rindex_spin); mutex_init(&sdp->sd_rindex_mutex); @@ -302,6 +302,67 @@ out: return error; } +/** + * map_journal_extents - create a reusable "extent" mapping from all logical + * blocks to all physical blocks for the given journal. This will save + * us time when writing journal blocks. Most journals will have only one + * extent that maps all their logical blocks. That's because gfs2.mkfs + * arranges the journal blocks sequentially to maximize performance. + * So the extent would map the first block for the entire file length. + * However, gfs2_jadd can happen while file activity is happening, so + * those journals may not be sequential. Less likely is the case where + * the users created their own journals by mounting the metafs and + * laying it out. But it's still possible. These journals might have + * several extents. + * + * TODO: This should be done in bigger chunks rather than one block at a time, + * but since it's only done at mount time, I'm not worried about the + * time it takes. + */ +int map_journal_extents(struct gfs2_sbd *sdp) +{ + struct gfs2_jdesc *jd = sdp->sd_jdesc; + unsigned int lb; + u64 db, prev_db; /* logical block, disk block, prev disk block */ + struct gfs2_inode *ip = GFS2_I(jd->jd_inode); + struct gfs2_journal_extent *jext = NULL; + struct buffer_head bh; + int rc = 0; + + prev_db = 0; + + for (lb = 0; lb < ip->i_di.di_size >> sdp->sd_sb.sb_bsize_shift; lb++) { + bh.b_state = 0; + bh.b_blocknr = 0; + bh.b_size = 1 << ip->i_inode.i_blkbits; + rc = gfs2_block_map(jd->jd_inode, lb, &bh, 0); + db = bh.b_blocknr; + if (rc || !db) { + printk(KERN_INFO "GFS2 journal mapping error %d: lb=" + "%u db=%llu\n", rc, lb, (unsigned long long)db); + break; + } + if (!prev_db || db != prev_db + 1) { + jext = kzalloc(sizeof(struct gfs2_journal_extent), + GFP_KERNEL); + if (!jext) { + printk(KERN_INFO "GFS2 error: out of memory " + "mapping journal extents.\n"); + rc = -ENOMEM; + break; + } + jext->dblock = db; + jext->lblock = lb; + jext->blocks = 1; + list_add_tail(&jext->extent_list, &jd->extent_list); + } else { + jext->blocks++; + } + prev_db = db; + } + return rc; +} + static int init_journal(struct gfs2_sbd *sdp, int undo) { struct gfs2_holder ji_gh; @@ -377,6 +438,8 @@ static int init_journal(struct gfs2_sbd *sdp, int undo) goto fail_jinode_gh; } sdp->sd_log_blks_free = sdp->sd_jdesc->jd_blocks; + /* Map the extents for this journal's blocks */ + map_journal_extents(sdp); } if (sdp->sd_lockstruct.ls_first) { diff --git a/fs/gfs2/ops_super.c b/fs/gfs2/ops_super.c index 12fa4b3..c5e1b67 100644 --- a/fs/gfs2/ops_super.c +++ b/fs/gfs2/ops_super.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -487,7 +487,6 @@ static struct inode *gfs2_alloc_inode(struct super_block *sb) if (ip) { ip->i_flags = 0; ip->i_gl = NULL; - ip->i_last_pfault = jiffies; } return &ip->i_inode; } diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index ad437f9..88fe784 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -274,10 +274,10 @@ static int bh_get(struct gfs2_quota_data *qd) } block = qd->qd_slot / sdp->sd_qc_per_block; - offset = qd->qd_slot % sdp->sd_qc_per_block;; + offset = qd->qd_slot % sdp->sd_qc_per_block; bh_map.b_size = 1 << ip->i_inode.i_blkbits; - error = gfs2_block_map(&ip->i_inode, block, 0, &bh_map); + error = gfs2_block_map(&ip->i_inode, block, &bh_map, 0); if (error) goto fail; error = gfs2_meta_read(ip->i_gl, bh_map.b_blocknr, DIO_WAIT, &bh); @@ -646,7 +646,7 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc, } if (!buffer_mapped(bh)) { - gfs2_get_block(inode, iblock, bh, 1); + gfs2_block_map(inode, iblock, bh, 1); if (!buffer_mapped(bh)) goto unlock; } @@ -1019,7 +1019,6 @@ void gfs2_quota_change(struct gfs2_inode *ip, s64 change, struct gfs2_alloc *al = ip->i_alloc; struct gfs2_quota_data *qd; unsigned int x; - unsigned int found = 0; if (gfs2_assert_warn(GFS2_SB(&ip->i_inode), change)) return; @@ -1032,7 +1031,6 @@ void gfs2_quota_change(struct gfs2_inode *ip, s64 change, if ((qd->qd_id == uid && test_bit(QDF_USER, &qd->qd_flags)) || (qd->qd_id == gid && !test_bit(QDF_USER, &qd->qd_flags))) { do_qc(qd, change); - found++; } } } diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index bd587d8..64723e6 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -391,7 +391,7 @@ static int clean_journal(struct gfs2_jdesc *jd, struct gfs2_log_header_host *hea lblock = head->lh_blkno; gfs2_replay_incr_blk(sdp, &lblock); bh_map.b_size = 1 << ip->i_inode.i_blkbits; - error = gfs2_block_map(&ip->i_inode, lblock, 0, &bh_map); + error = gfs2_block_map(&ip->i_inode, lblock, &bh_map, 0); if (error) return error; if (!bh_map.b_blocknr) { diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index f7f9ad4..c47db94 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -126,41 +126,43 @@ static unsigned char gfs2_testbit(struct gfs2_rgrpd *rgd, unsigned char *buffer, * Return: the block number (bitmap buffer scope) that was found */ -static u32 gfs2_bitfit(struct gfs2_rgrpd *rgd, unsigned char *buffer, - unsigned int buflen, u32 goal, - unsigned char old_state) +static u32 gfs2_bitfit(unsigned char *buffer, unsigned int buflen, u32 goal, + unsigned char old_state) { - unsigned char *byte, *end, alloc; + unsigned char *byte; u32 blk = goal; - unsigned int bit; + unsigned int bit, bitlong; + unsigned long *plong, plong55; byte = buffer + (goal / GFS2_NBBY); + plong = (unsigned long *)buffer + (goal / GFS2_NBBY); bit = (goal % GFS2_NBBY) * GFS2_BIT_SIZE; - end = buffer + buflen; - alloc = (old_state == GFS2_BLKST_FREE) ? 0x55 : 0; - - while (byte < end) { - /* If we're looking for a free block we can eliminate all - bitmap settings with 0x55, which represents four data - blocks in a row. If we're looking for a data block, we can - eliminate 0x00 which corresponds to four free blocks. */ - if ((*byte & 0x55) == alloc) { - blk += (8 - bit) >> 1; - - bit = 0; - byte++; - + bitlong = bit; +#if BITS_PER_LONG == 32 + plong55 = 0x55555555; +#else + plong55 = 0x5555555555555555; +#endif + while (byte < buffer + buflen) { + + if (bitlong == 0 && old_state == 0 && *plong == plong55) { + plong++; + byte += sizeof(unsigned long); + blk += sizeof(unsigned long) * GFS2_NBBY; continue; } - if (((*byte >> bit) & GFS2_BIT_MASK) == old_state) return blk; - bit += GFS2_BIT_SIZE; if (bit >= 8) { bit = 0; byte++; } + bitlong += GFS2_BIT_SIZE; + if (bitlong >= sizeof(unsigned long) * 8) { + bitlong = 0; + plong++; + } blk++; } @@ -1316,11 +1318,10 @@ static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal, /* The GFS2_BLKST_UNLINKED state doesn't apply to the clone bitmaps, so we must search the originals for that. */ if (old_state != GFS2_BLKST_UNLINKED && bi->bi_clone) - blk = gfs2_bitfit(rgd, bi->bi_clone + bi->bi_offset, + blk = gfs2_bitfit(bi->bi_clone + bi->bi_offset, bi->bi_len, goal, old_state); else - blk = gfs2_bitfit(rgd, - bi->bi_bh->b_data + bi->bi_offset, + blk = gfs2_bitfit(bi->bi_bh->b_data + bi->bi_offset, bi->bi_len, goal, old_state); if (blk != BFITNOENT) break; @@ -1698,8 +1699,7 @@ void gfs2_rlist_add(struct gfs2_sbd *sdp, struct gfs2_rgrp_list *rlist, * */ -void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state, - int flags) +void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state) { unsigned int x; @@ -1707,7 +1707,7 @@ void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state, GFP_NOFS | __GFP_NOFAIL); for (x = 0; x < rlist->rl_rgrps; x++) gfs2_holder_init(rlist->rl_rgd[x]->rd_gl, - state, flags, + state, 0, &rlist->rl_ghs[x]); } diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h index 149bb16..5683605 100644 --- a/fs/gfs2/rgrp.h +++ b/fs/gfs2/rgrp.h @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -64,8 +64,7 @@ struct gfs2_rgrp_list { void gfs2_rlist_add(struct gfs2_sbd *sdp, struct gfs2_rgrp_list *rlist, u64 block); -void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state, - int flags); +void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state); void gfs2_rlist_free(struct gfs2_rgrp_list *rlist); u64 gfs2_ri_total(struct gfs2_sbd *sdp); diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index c07383c..27a8348 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -325,6 +325,7 @@ int gfs2_read_sb(struct gfs2_sbd *sdp, struct gfs2_glock *gl, int silent) sdp->sd_heightsize[x] = space; } sdp->sd_max_height = x; + sdp->sd_heightsize[x] = ~0; gfs2_assert(sdp, sdp->sd_max_height <= GFS2_MAX_META_HEIGHT); sdp->sd_jheightsize[0] = sdp->sd_sb.sb_bsize - @@ -343,6 +344,7 @@ int gfs2_read_sb(struct gfs2_sbd *sdp, struct gfs2_glock *gl, int silent) sdp->sd_jheightsize[x] = space; } sdp->sd_max_jheight = x; + sdp->sd_jheightsize[x] = ~0; gfs2_assert(sdp, sdp->sd_max_jheight <= GFS2_MAX_META_HEIGHT); return 0; @@ -396,6 +398,7 @@ int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh) if (!jd) break; + INIT_LIST_HEAD(&jd->extent_list); jd->jd_inode = gfs2_lookupi(sdp->sd_jindex, &name, 1, NULL); if (!jd->jd_inode || IS_ERR(jd->jd_inode)) { if (!jd->jd_inode) @@ -425,8 +428,9 @@ int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh) void gfs2_jindex_free(struct gfs2_sbd *sdp) { - struct list_head list; + struct list_head list, *head; struct gfs2_jdesc *jd; + struct gfs2_journal_extent *jext; spin_lock(&sdp->sd_jindex_spin); list_add(&list, &sdp->sd_jindex_list); @@ -436,6 +440,14 @@ void gfs2_jindex_free(struct gfs2_sbd *sdp) while (!list_empty(&list)) { jd = list_entry(list.next, struct gfs2_jdesc, jd_list); + head = &jd->extent_list; + while (!list_empty(head)) { + jext = list_entry(head->next, + struct gfs2_journal_extent, + extent_list); + list_del(&jext->extent_list); + kfree(jext); + } list_del(&jd->jd_list); iput(jd->jd_inode); kfree(jd); @@ -688,10 +700,7 @@ void gfs2_statfs_change(struct gfs2_sbd *sdp, s64 total, s64 free, if (error) return; - mutex_lock(&sdp->sd_statfs_mutex); gfs2_trans_add_bh(l_ip->i_gl, l_bh, 1); - mutex_unlock(&sdp->sd_statfs_mutex); - spin_lock(&sdp->sd_statfs_spin); l_sc->sc_total += total; l_sc->sc_free += free; @@ -738,10 +747,7 @@ int gfs2_statfs_sync(struct gfs2_sbd *sdp) if (error) goto out_bh2; - mutex_lock(&sdp->sd_statfs_mutex); gfs2_trans_add_bh(l_ip->i_gl, l_bh, 1); - mutex_unlock(&sdp->sd_statfs_mutex); - spin_lock(&sdp->sd_statfs_spin); m_sc->sc_total += l_sc->sc_total; m_sc->sc_free += l_sc->sc_free; diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index 5fcb04e..c224ac8 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -1,6 +1,6 @@ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. - * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -120,6 +120,42 @@ void gfs2_trans_add_gl(struct gfs2_glock *gl) } /** + * gfs2_attach_bufdata - attach a struct gfs2_bufdata structure to a buffer + * @gl: the glock the buffer belongs to + * @bh: The buffer to be attached to + * @meta: Flag to indicate whether its metadata or not + */ + +static void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh, + int meta) +{ + struct gfs2_bufdata *bd; + + if (meta) + lock_page(bh->b_page); + + if (bh->b_private) { + if (meta) + unlock_page(bh->b_page); + return; + } + + bd = kmem_cache_zalloc(gfs2_bufdata_cachep, GFP_NOFS | __GFP_NOFAIL); + bd->bd_bh = bh; + bd->bd_gl = gl; + + INIT_LIST_HEAD(&bd->bd_list_tr); + if (meta) + lops_init_le(&bd->bd_le, &gfs2_buf_lops); + else + lops_init_le(&bd->bd_le, &gfs2_databuf_lops); + bh->b_private = bd; + + if (meta) + unlock_page(bh->b_page); +} + +/** * gfs2_trans_add_bh - Add a to-be-modified buffer to the current transaction * @gl: the glock the buffer belongs to * @bh: The buffer to add