gfs2: fix GL_SKIP node_scope problems

Before this patch, when a glock was locked, the very first holder on the
queue would unlock the lockref and call the go_instantiate glops function
(if one existed), unless GL_SKIP was specified. When we introduced the new
node-scope concept, we allowed multiple holders to lock glocks in EX mode
and share the lock.

But node-scope introduced a new problem: if the first holder has GL_SKIP
and the next one does NOT, since it is not the first holder on the queue,
the go_instantiate op was not called. Eventually the GL_SKIP holder may
call the instantiate sub-function (e.g. gfs2_rgrp_bh_get) but there was
still a window of time in which another non-GL_SKIP holder assumes the
instantiate function had been called by the first holder. In the case of
rgrp glocks, this led to a NULL pointer dereference on the buffer_heads.

This patch tries to fix the problem by introducing two new glock flags:

GLF_INSTANTIATE_NEEDED, which keeps track of when the instantiate function
needs to be called to "fill in" or "read in" the object before it is
referenced.

GLF_INSTANTIATE_IN_PROG which is used to determine when a process is
in the process of reading in the object. Whenever a function needs to
reference the object, it checks the GLF_INSTANTIATE_NEEDED flag, and if
set, it sets GLF_INSTANTIATE_IN_PROG and calls the glops "go_instantiate"
function.

As before, the gl_lockref spin_lock is unlocked during the IO operation,
which may take a relatively long amount of time to complete. While
unlocked, if another process determines go_instantiate is still needed,
it sees GLF_INSTANTIATE_IN_PROG is set, and waits for the go_instantiate
glop operation to be completed. Once GLF_INSTANTIATE_IN_PROG is cleared,
it needs to check GLF_INSTANTIATE_NEEDED again because the other process's
go_instantiate operation may not have been successful.

Functions that previously called the instantiate sub-functions now call
directly into gfs2_instantiate so the new bits are managed properly.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>

1 files changed, 11 insertions, 10 deletions

diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index cdcbc822064d..5ee7da3a450e 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -1238,8 +1238,7 @@ static int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd)
 		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) {
+	} else if (sdp->sd_args.ar_rgrplvb) {
 		if (!gfs2_rgrp_lvb_valid(rgd)){
 			gfs2_consist_rgrpd(rgd);
 			error = -EIO;
@@ -1257,11 +1256,10 @@ fail:
 		bi->bi_bh = NULL;
 		gfs2_assert_warn(sdp, !bi->bi_clone);
 	}
-
 	return error;
 }
 
-static int update_rgrp_lvb(struct gfs2_rgrpd *rgd)
+static int update_rgrp_lvb(struct gfs2_rgrpd *rgd, struct gfs2_holder *gh)
 {
 	u32 rl_flags;
 
@@ -1269,7 +1267,7 @@ static int update_rgrp_lvb(struct gfs2_rgrpd *rgd)
 		return 0;
 
 	if (cpu_to_be32(GFS2_MAGIC) != rgd->rd_rgl->rl_magic)
-		return gfs2_rgrp_bh_get(rgd);
+		return gfs2_instantiate(gh);
 
 	rl_flags = be32_to_cpu(rgd->rd_rgl->rl_flags);
 	rl_flags &= ~GFS2_RDF_MASK;
@@ -1312,6 +1310,7 @@ void gfs2_rgrp_brelse(struct gfs2_rgrpd *rgd)
 			bi->bi_bh = NULL;
 		}
 	}
+	set_bit(GLF_INSTANTIATE_NEEDED, &rgd->rd_gl->gl_flags);
 }
 
 int gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
@@ -2110,7 +2109,8 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, struct gfs2_alloc_parms *ap)
 			    gfs2_rgrp_congested(rs->rs_rgd, loops))
 				goto skip_rgrp;
 			if (sdp->sd_args.ar_rgrplvb) {
-				error = update_rgrp_lvb(rs->rs_rgd);
+				error = update_rgrp_lvb(rs->rs_rgd,
+							&ip->i_rgd_gh);
 				if (unlikely(error)) {
 					rgrp_unlock_local(rs->rs_rgd);
 					gfs2_glock_dq_uninit(&ip->i_rgd_gh);
@@ -2125,8 +2125,11 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, struct gfs2_alloc_parms *ap)
 		    (loops == 0 && target > rs->rs_rgd->rd_extfail_pt))
 			goto skip_rgrp;
 
-		if (sdp->sd_args.ar_rgrplvb)
-			gfs2_rgrp_bh_get(rs->rs_rgd);
+		if (sdp->sd_args.ar_rgrplvb) {
+			error = gfs2_instantiate(&ip->i_rgd_gh);
+			if (error)
+				goto skip_rgrp;
+		}
 
 		/* Get a reservation if we don't already have one */
 		if (!gfs2_rs_active(rs))
@@ -2762,8 +2765,6 @@ void gfs2_rlist_free(struct gfs2_rgrp_list *rlist)
 
 void rgrp_lock_local(struct gfs2_rgrpd *rgd)
 {
-	GLOCK_BUG_ON(rgd->rd_gl, !gfs2_glock_is_held_excl(rgd->rd_gl) &&
-		     !test_bit(SDF_NORECOVERY, &rgd->rd_sbd->sd_flags));
 	mutex_lock(&rgd->rd_mutex);
 }