[PATCH RT 0/3] Linux 3.2.69-rt102-rc1

Dear RT Folks,

This is the RT stable review cycle of patch 3.2.69-rt102-rc1.

Please scream at me if I messed something up. Please test the patches too.

The -rc release will be uploaded to kernel.org and will be deleted when
the final release is out. This is just a review release (or release candidate).

The pre-releases will not be pushed to the git repository, only the
final release is.

If all goes well, this patch will be converted to the next main release
on 8/10/2015.

Enjoy,

-- Steve


To build 3.2.69-rt102-rc1 directly, the following patches should be applied:

  http://www.kernel.org/pub/linux/kernel/v3.x/linux-3.2.tar.xz

  http://www.kernel.org/pub/linux/kernel/v3.x/patch-3.2.69.xz

  http://www.kernel.org/pub/linux/kernel/projects/rt/3.2/patch-3.2.69-rt102-rc1.patch.xz

You can also build from 3.2.69-rt101 by applying the incremental patch:

http://www.kernel.org/pub/linux/kernel/projects/rt/3.2/incr/patch-3.2.69-rt101-rt102-rc1.patch.xz


Changes from 3.2.69-rt101:

---


Steven Rostedt (1):
      xfs: Disable percpu SB on PREEMPT_RT_FULL

Steven Rostedt (Red Hat) (1):
      Linux 3.2.69-rt102-rc1

Thomas Gleixner (1):
      mm/slub: move slab initialization into irq enabled region

----
 fs/xfs/xfs_linux.h |  2 +-
 localversion-rt    |  2 +-
 mm/slub.c          | 77 ++++++++++++++++++++++++++----------------------------
 3 files changed, 39 insertions(+), 42 deletions(-)

3.2.69-rt102-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>

---
 localversion-rt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/localversion-rt b/localversion-rt
index 9ea5981fa956..04456d92828d 100644
--- a/localversion-rt
+++ b/localversion-rt

@@ -1 +1 @@
--rt101
+-rt102-rc1

-- 
2.4.6

3.2.69-rt102-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Thomas Gleixner <redacted>

Initializing a new slab can introduce rather large latencies because most
of the initialization runs always with interrupts disabled.

There is no point in doing so.  The newly allocated slab is not visible
yet, so there is no reason to protect it against concurrent alloc/free.

Move the expensive parts of the initialization into allocate_slab(), so
for all allocations with GFP_WAIT set, interrupts are enabled.

Signed-off-by: Thomas Gleixner <redacted>
Acked-by: Christoph Lameter <redacted>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <redacted>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 mm/slub.c | 77 ++++++++++++++++++++++++++++++---------------------------------
 1 file changed, 37 insertions(+), 40 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 6a4c2fb83839..513c55ddbc3d 100644
--- a/mm/slub.c
+++ b/mm/slub.c

@@ -1258,6 +1258,14 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x) {}
 
 #endif /* CONFIG_SLUB_DEBUG */
 
+static void setup_object(struct kmem_cache *s, struct page *page,
+				void *object)
+{
+	setup_object_debug(s, page, object);
+	if (unlikely(s->ctor))
+		s->ctor(object);
+}
+
 /*
  * Slab allocation and freeing
  */

@@ -1279,6 +1287,8 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 	struct page *page;
 	struct kmem_cache_order_objects oo = s->oo;
 	gfp_t alloc_gfp;
+	void *start, *last, *p;
+	int idx, order;
 
 	flags &= gfp_allowed_mask;
 

@@ -1301,17 +1311,11 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 		 * Try a lower order alloc if possible
 		 */
 		page = alloc_slab_page(flags, node, oo);
-
-		if (page)
-			stat(s, ORDER_FALLBACK);
+		if (unlikely(!page))
+			goto out;
+		stat(s, ORDER_FALLBACK);
 	}
 
-	if (flags & __GFP_WAIT)
-		local_irq_disable();
-
-	if (!page)
-		return NULL;
-
 	if (kmemcheck_enabled
 		&& !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) {
 		int pages = 1 << oo_order(oo);

@@ -1329,37 +1333,6 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 	}
 
 	page->objects = oo_objects(oo);
-	mod_zone_page_state(page_zone(page),
-		(s->flags & SLAB_RECLAIM_ACCOUNT) ?
-		NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
-		1 << oo_order(oo));
-
-	return page;
-}
-
-static void setup_object(struct kmem_cache *s, struct page *page,
-				void *object)
-{
-	setup_object_debug(s, page, object);
-	if (unlikely(s->ctor))
-		s->ctor(object);
-}
-
-static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
-{
-	struct page *page;
-	void *start;
-	void *last;
-	void *p;
-
-	BUG_ON(flags & GFP_SLAB_BUG_MASK);
-
-	page = allocate_slab(s,
-		flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node);
-	if (!page)
-		goto out;
-
-	inc_slabs_node(s, page_to_nid(page), page->objects);
 	page->slab = s;
 	page->flags |= 1 << PG_slab;
 

@@ -1380,10 +1353,34 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 	page->freelist = start;
 	page->inuse = page->objects;
 	page->frozen = 1;
+
 out:
+	if (flags & __GFP_WAIT)
+		local_irq_disable();
+	if (!page)
+		return NULL;
+
+	mod_zone_page_state(page_zone(page),
+		(s->flags & SLAB_RECLAIM_ACCOUNT) ?
+		NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
+		1 << oo_order(oo));
+
+	inc_slabs_node(s, page_to_nid(page), page->objects);
+
 	return page;
 }
 
+static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
+{
+	if (unlikely(flags & GFP_SLAB_BUG_MASK)) {
+		pr_emerg("gfp: %u\n", flags & GFP_SLAB_BUG_MASK);
+		BUG();
+	}
+
+	return allocate_slab(s,
+		flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node);
+}
+
 static void __free_slab(struct kmem_cache *s, struct page *page)
 {
 	int order = compound_order(page);

-- 
2.4.6

3.2.69-rt102-rc1 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Steven Rostedt <rostedt@goodmis.org>

Running a test on a large CPU count box with xfs, I hit a live lock
with the following backtraces on several CPUs:

 Call Trace:
  [<ffffffff812c34f8>] __const_udelay+0x28/0x30
  [<ffffffffa033ab9a>] xfs_icsb_lock_cntr+0x2a/0x40 [xfs]
  [<ffffffffa033c871>] xfs_icsb_modify_counters+0x71/0x280 [xfs]
  [<ffffffffa03413e1>] xfs_trans_reserve+0x171/0x210 [xfs]
  [<ffffffffa0378cfd>] xfs_create+0x24d/0x6f0 [xfs]
  [<ffffffff8124c8eb>] ? avc_has_perm_flags+0xfb/0x1e0
  [<ffffffffa0336eeb>] xfs_vn_mknod+0xbb/0x1e0 [xfs]
  [<ffffffffa0337043>] xfs_vn_create+0x13/0x20 [xfs]
  [<ffffffff811b0edd>] vfs_create+0xcd/0x130
  [<ffffffff811b21ef>] do_last+0xb8f/0x1240
  [<ffffffff811b39b2>] path_openat+0xc2/0x490

Looking at the code I see it was stuck at:

STATIC void
xfs_icsb_lock_cntr(
	xfs_icsb_cnts_t	*icsbp)
{
	while (test_and_set_bit(XFS_ICSB_FLAG_LOCK, &icsbp->icsb_flags)) {
		ndelay(1000);
	}
}

In xfs_icsb_modify_counters() the code is fine. There's a
preempt_disable() called when taking this bit spinlock and a
preempt_enable() after it is released. The issue is that not all
locations are protected by preempt_disable() when PREEMPT_RT is set.
Namely the places that grab all CPU cntr locks.

STATIC void
xfs_icsb_lock_all_counters(
	xfs_mount_t	*mp)
{
	xfs_icsb_cnts_t *cntp;
	int		i;

	for_each_online_cpu(i) {
		cntp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, i);
		xfs_icsb_lock_cntr(cntp);
	}
}

STATIC void
xfs_icsb_disable_counter()
{
	[...]
	xfs_icsb_lock_all_counters(mp);
	[...]
	xfs_icsb_unlock_all_counters(mp);
}

STATIC void
xfs_icsb_balance_counter_locked()
{
	[...]
	xfs_icsb_disable_counter();
	[...]
}

STATIC void
xfs_icsb_balance_counter(
	xfs_mount_t	*mp,
	xfs_sb_field_t  fields,
	int		min_per_cpu)
{
	spin_lock(&mp->m_sb_lock);
	xfs_icsb_balance_counter_locked(mp, fields, min_per_cpu);
	spin_unlock(&mp->m_sb_lock);
}

Now, when PREEMPT_RT is not enabled, that spin_lock() disables
preemption. But for PREEMPT_RT, it does not. Although with my test box I
was not able to produce a task state of all tasks, but I'm assuming that
some task called the xfs_icsb_lock_all_counters() and was preempted by
an RT task and could not finish, causing all callers of that lock to
block indefinitely.

Dave Chinner has stated that the scalability of that code will probably
be negated by PREEMPT_RT, and that it is probably best to just disable
the code in question. Also, this code has been rewritten in newer kernels.

Link: http://lkml.kernel.org/r/20150504004844.GA21261@dastard

Cc: stable-rt@vger.kernel.org
Suggested-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 fs/xfs/xfs_linux.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index 828662f70d64..13d86a8dae43 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h

@@ -97,7 +97,7 @@
 /*
  * Feature macros (disable/enable)
  */
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && !defined(CONFIG_PREEMPT_RT_FULL)
 #define HAVE_PERCPU_SB	/* per cpu superblock counters are a 2.6 feature */
 #else
 #undef  HAVE_PERCPU_SB	/* per cpu superblock counters are a 2.6 feature */

-- 
2.4.6