GFS2: Use lvbs for storing rgrp information with mount option

Instead of reading in the resource groups when gfs2 is checking
for free space to allocate from, gfs2 can store the necessary infromation
in the resource group's lvb.  Also, instead of searching for unlinked
inodes in every resource group that's checked for free space, gfs2 can
store the number of unlinked but inodes in the lvb, and only check for
unlinked inodes if it will find some.

The first time a resource group is locked, the lvb must initialized.
Since this involves counting the unlinked inodes in the resource group,
this takes a little extra time.  But after that, if the resource group
is locked with GL_SKIP, the buffer head won't be read in unless it's
actually needed.

Enabling the resource groups lvbs is done via the rgrplvb mount option.  If
this option isn't set, the lvbs will still be set and updated, but they won't
be verfied or used by the filesystem.  To safely turn on this option, all of
the nodes mounting the filesystem must be running code with this patch, and
the filesystem must have been completely unmounted since they were updated.

Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

5 files changed, 163 insertions, 9 deletions

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 3ad8cb3eeb88..10ae1645d9a5 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -769,6 +769,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
         gl->gl_stats.stats[GFS2_LKS_DCOUNT] = 0;
         gl->gl_stats.stats[GFS2_LKS_QCOUNT] = 0;
         memset(&gl->gl_lksb, 0, sizeof(struct dlm_lksb));
+        memset(gl->gl_lvb, 0, 32 * sizeof(char));
         gl->gl_lksb.sb_lvbptr = gl->gl_lvb;
         gl->gl_tchange = jiffies;
         gl->gl_object = NULL;
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 5cda51a3e3bd..dc730700b3b4 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -89,6 +89,7 @@ struct gfs2_rgrpd {
         u64 rd_igeneration;
         struct gfs2_bitmap *rd_bits;
         struct gfs2_sbd *rd_sbd;
+        struct gfs2_rgrp_lvb *rd_rgl;
         u32 rd_last_alloc;
         u32 rd_flags;
 #define GFS2_RDF_CHECK          0x10000000 /* check for unlinked inodes */
@@ -470,6 +471,7 @@ struct gfs2_args {
         unsigned int ar_discard:1;              /* discard requests */
         unsigned int ar_errors:2;               /* errors=withdraw | panic */
         unsigned int ar_nobarrier:1;            /* do not send barriers */
+        unsigned int ar_rgrplvb:1;              /* use lvbs for rgrp info */
         int ar_commit;                          /* Commit interval */
         int ar_statfs_quantum;                  /* The fast statfs interval */
         int ar_quota_quantum;                   /* The quota interval */
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 9eca6a9cff8f..3c6f7ed16a3b 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -660,6 +660,7 @@ static int read_rindex_entry(struct gfs2_inode *ip)
                 goto fail;
 
         rgd->rd_gl->gl_object = rgd;
+        rgd->rd_rgl = (struct gfs2_rgrp_lvb *)rgd->rd_gl->gl_lvb;
         rgd->rd_flags &= ~GFS2_RDF_UPTODATE;
         if (rgd->rd_data > sdp->sd_max_rg_data)
                 sdp->sd_max_rg_data = rgd->rd_data;
@@ -769,9 +770,65 @@ static void gfs2_rgrp_out(struct gfs2_rgrpd *rgd, void *buf)
         memset(&str->rg_reserved, 0, sizeof(str->rg_reserved));
 }
 
+static int gfs2_rgrp_lvb_valid(struct gfs2_rgrpd *rgd)
+{
+        struct gfs2_rgrp_lvb *rgl = rgd->rd_rgl;
+        struct gfs2_rgrp *str = (struct gfs2_rgrp *)rgd->rd_bits[0].bi_bh->b_data;
+
+        if (rgl->rl_flags != str->rg_flags || rgl->rl_free != str->rg_free ||
+            rgl->rl_dinodes != str->rg_dinodes ||
+            rgl->rl_igeneration != str->rg_igeneration)
+                return 0;
+        return 1;
+}
+
+static void gfs2_rgrp_ondisk2lvb(struct gfs2_rgrp_lvb *rgl, const void *buf)
+{
+        const struct gfs2_rgrp *str = buf;
+
+        rgl->rl_magic = cpu_to_be32(GFS2_MAGIC);
+        rgl->rl_flags = str->rg_flags;
+        rgl->rl_free = str->rg_free;
+        rgl->rl_dinodes = str->rg_dinodes;
+        rgl->rl_igeneration = str->rg_igeneration;
+        rgl->__pad = 0UL;
+}
+
+static void update_rgrp_lvb_unlinked(struct gfs2_rgrpd *rgd, u32 change)
+{
+        struct gfs2_rgrp_lvb *rgl = rgd->rd_rgl;
+        u32 unlinked = be32_to_cpu(rgl->rl_unlinked) + change;
+        rgl->rl_unlinked = cpu_to_be32(unlinked);
+}
+
+static u32 count_unlinked(struct gfs2_rgrpd *rgd)
+{
+        struct gfs2_bitmap *bi;
+        const u32 length = rgd->rd_length;
+        const u8 *buffer = NULL;
+        u32 i, goal, count = 0;
+
+        for (i = 0, bi = rgd->rd_bits; i < length; i++, bi++) {
+                goal = 0;
+                buffer = bi->bi_bh->b_data + bi->bi_offset;
+                WARN_ON(!buffer_uptodate(bi->bi_bh));
+                while (goal < bi->bi_len * GFS2_NBBY) {
+                        goal = gfs2_bitfit(buffer, bi->bi_len, goal,
+                                           GFS2_BLKST_UNLINKED);
+                        if (goal == BFITNOENT)
+                                break;
+                        count++;
+                        goal++;
+                }
+        }
+
+        return count;
+}
+
+
 /**
- * gfs2_rgrp_go_lock - Read in a RG's header and bitmaps
- * @gh: The glock holder for the resource group
+ * gfs2_rgrp_bh_get - Read in a RG's header and bitmaps
+ * @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.
@@ -779,9 +836,8 @@ static void gfs2_rgrp_out(struct gfs2_rgrpd *rgd, void *buf)
  * Returns: errno
  */
 
-int gfs2_rgrp_go_lock(struct gfs2_holder *gh)
+int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd)
 {
-        struct gfs2_rgrpd *rgd = gh->gh_gl->gl_object;
         struct gfs2_sbd *sdp = rgd->rd_sbd;
         struct gfs2_glock *gl = rgd->rd_gl;
         unsigned int length = rgd->rd_length;
@@ -789,6 +845,9 @@ int gfs2_rgrp_go_lock(struct gfs2_holder *gh)
         unsigned int x, y;
         int error;
 
+        if (rgd->rd_bits[0].bi_bh != NULL)
+                return 0;
+
         for (x = 0; x < length; x++) {
                 bi = rgd->rd_bits + x;
                 error = gfs2_meta_read(gl, rgd->rd_addr + x, 0, &bi->bi_bh);
@@ -815,7 +874,20 @@ int gfs2_rgrp_go_lock(struct gfs2_holder *gh)
                 rgd->rd_flags |= (GFS2_RDF_UPTODATE | GFS2_RDF_CHECK);
                 rgd->rd_free_clone = rgd->rd_free;
         }
-
+        if (be32_to_cpu(GFS2_MAGIC) != rgd->rd_rgl->rl_magic) {
+                rgd->rd_rgl->rl_unlinked = cpu_to_be32(count_unlinked(rgd));
+                gfs2_rgrp_ondisk2lvb(rgd->rd_rgl,
+                                     rgd->rd_bits[0].bi_bh->b_data);
+        }
+        else if (sdp->sd_args.ar_rgrplvb) {
+                if (!gfs2_rgrp_lvb_valid(rgd)){
+                        gfs2_consist_rgrpd(rgd);
+                        error = -EIO;
+                        goto fail;
+                }
+                if (rgd->rd_rgl->rl_unlinked == 0)
+                        rgd->rd_flags &= ~GFS2_RDF_CHECK;
+        }
         return 0;
 
 fail:
@@ -829,6 +901,39 @@ fail:
         return error;
 }
 
+int update_rgrp_lvb(struct gfs2_rgrpd *rgd)
+{
+        u32 rl_flags;
+
+        if (rgd->rd_flags & GFS2_RDF_UPTODATE)
+                return 0;
+
+        if (be32_to_cpu(GFS2_MAGIC) != rgd->rd_rgl->rl_magic)
+                return gfs2_rgrp_bh_get(rgd);
+
+        rl_flags = be32_to_cpu(rgd->rd_rgl->rl_flags);
+        rl_flags &= ~GFS2_RDF_MASK;
+        rgd->rd_flags &= GFS2_RDF_MASK;
+        rgd->rd_flags |= (rl_flags | GFS2_RDF_UPTODATE | GFS2_RDF_CHECK);
+        if (rgd->rd_rgl->rl_unlinked == 0)