Move xen patchset to new version's subdir.

[people/pmueller/ipfire-2.x.git] / src / patches / suse-2.6.27.31 / patches.suse / SoN-01-mm-gfp-to-alloc_flags.patch

From: Peter Zijlstra <a.p.zijlstra@chello.nl> 
Subject: mm: gfp_to_alloc_flags()
Patch-mainline: No
References: FATE#303834

Clean up the code by factoring out the gfp to alloc_flags mapping.

[neilb@suse.de says]
As the test:

-       if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE)))
-                       && !in_interrupt()) {
-               if (!(gfp_mask & __GFP_NOMEMALLOC)) {

has been replaced with a slightly weaker one:

+       if (alloc_flags & ALLOC_NO_WATERMARKS) {

we need to ensure we don't recurse when PF_MEMALLOC is set

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Neil Brown <neilb@suse.de>
Acked-by: Suresh Jayaraman <sjayaraman@suse.de>

---
 mm/page_alloc.c |   87 ++++++++++++++++++++++++++++++++++----------------------
 1 file changed, 54 insertions(+), 33 deletions(-)

--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1455,6 +1455,44 @@ try_next_zone:
 }
 
 /*
+ * get the deepest reaching allocation flags for the given gfp_mask
+ */
+static int gfp_to_alloc_flags(gfp_t gfp_mask)
+{
+	struct task_struct *p = current;
+	int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
+	const gfp_t wait = gfp_mask & __GFP_WAIT;
+
+	/*
+	 * The caller may dip into page reserves a bit more if the caller
+	 * cannot run direct reclaim, or if the caller has realtime scheduling
+	 * policy or is asking for __GFP_HIGH memory.  GFP_ATOMIC requests will
+	 * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH).
+	 */
+	if (gfp_mask & __GFP_HIGH)
+		alloc_flags |= ALLOC_HIGH;
+
+	if (!wait) {
+		alloc_flags |= ALLOC_HARDER;
+		/*
+		 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
+		 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
+		 */
+		alloc_flags &= ~ALLOC_CPUSET;
+	} else if (unlikely(rt_task(p)) && !in_interrupt())
+		alloc_flags |= ALLOC_HARDER;
+
+	if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) {
+		if (!in_interrupt() &&
+		    ((p->flags & PF_MEMALLOC) ||
+		     unlikely(test_thread_flag(TIF_MEMDIE))))
+			alloc_flags |= ALLOC_NO_WATERMARKS;
+	}
+
+	return alloc_flags;
+}
+
+/*
  * This is the 'heart' of the zoned buddy allocator.
  */
 struct page *
@@ -1512,49 +1550,28 @@ restart:
 	 * OK, we're below the kswapd watermark and have kicked background
 	 * reclaim. Now things get more complex, so set up alloc_flags according
 	 * to how we want to proceed.
-	 *
-	 * The caller may dip into page reserves a bit more if the caller
-	 * cannot run direct reclaim, or if the caller has realtime scheduling
-	 * policy or is asking for __GFP_HIGH memory.  GFP_ATOMIC requests will
-	 * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH).
 	 */
-	alloc_flags = ALLOC_WMARK_MIN;
-	if ((unlikely(rt_task(p)) && !in_interrupt()) || !wait)
-		alloc_flags |= ALLOC_HARDER;
-	if (gfp_mask & __GFP_HIGH)
-		alloc_flags |= ALLOC_HIGH;
-	if (wait)
-		alloc_flags |= ALLOC_CPUSET;
+	alloc_flags = gfp_to_alloc_flags(gfp_mask);
 
-	/*
-	 * Go through the zonelist again. Let __GFP_HIGH and allocations
-	 * coming from realtime tasks go deeper into reserves.
-	 *
-	 * This is the last chance, in general, before the goto nopage.
-	 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
-	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
-	 */
+	/* This is the last chance, in general, before the goto nopage. */
 	page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
-						high_zoneidx, alloc_flags);
+			high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS);
 	if (page)
 		goto got_pg;
 
 	/* This allocation should allow future memory freeing. */
-
 rebalance:
-	if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE)))
-			&& !in_interrupt()) {
-		if (!(gfp_mask & __GFP_NOMEMALLOC)) {
+	if (alloc_flags & ALLOC_NO_WATERMARKS) {
 nofail_alloc:
-			/* go through the zonelist yet again, ignoring mins */
-			page = get_page_from_freelist(gfp_mask, nodemask, order,
+		/* go through the zonelist yet again, ignoring mins */
+		page = get_page_from_freelist(gfp_mask, nodemask, order,
 				zonelist, high_zoneidx, ALLOC_NO_WATERMARKS);
-			if (page)
-				goto got_pg;
-			if (gfp_mask & __GFP_NOFAIL) {
-				congestion_wait(WRITE, HZ/50);
-				goto nofail_alloc;
-			}
+		if (page)
+			goto got_pg;
+
+		if (wait && (gfp_mask & __GFP_NOFAIL)) {
+			congestion_wait(WRITE, HZ/50);
+			goto nofail_alloc;
 		}
 		goto nopage;
 	}
@@ -1563,6 +1580,10 @@ nofail_alloc:
 	if (!wait)
 		goto nopage;
 
+	/* Avoid recursion of direct reclaim */
+	if (p->flags & PF_MEMALLOC)
+		goto nopage;
+
 	cond_resched();
 
 	/* We now go into synchronous reclaim */