lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:	Fri, 29 Jun 2012 14:32:34 +0100
From:	Mel Gorman <mgorman@...e.de>
To:	Andrew Morton <akpm@...ux-foundation.org>
Cc:	Linux-MM <linux-mm@...ck.org>,
	Linux-Netdev <netdev@...r.kernel.org>,
	LKML <linux-kernel@...r.kernel.org>,
	David Miller <davem@...emloft.net>, Neil Brown <neilb@...e.de>,
	Peter Zijlstra <a.p.zijlstra@...llo.nl>,
	Mike Christie <michaelc@...wisc.edu>,
	Eric B Munson <emunson@...bm.net>,
	Eric Dumazet <eric.dumazet@...il.com>,
	Sebastian Andrzej Siewior <sebastian@...akpoint.cc>,
	Mel Gorman <mgorman@...e.de>
Subject: [PATCH 03/16] mm: Introduce __GFP_MEMALLOC to allow access to emergency reserves

__GFP_MEMALLOC will allow the allocation to disregard the watermarks,
much like PF_MEMALLOC. It allows one to pass along the memalloc state
in object related allocation flags as opposed to task related flags,
such as sk->sk_allocation. This removes the need for ALLOC_PFMEMALLOC
as callers using __GFP_MEMALLOC can get the ALLOC_NO_WATERMARK flag
which is now enough to identify allocations related to page reclaim.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@...llo.nl>
Signed-off-by: Mel Gorman <mgorman@...e.de>
---
 include/linux/gfp.h             |   10 ++++++++--
 include/linux/mm_types.h        |    2 +-
 include/trace/events/gfpflags.h |    1 +
 mm/page_alloc.c                 |   22 ++++++++++------------
 mm/slab.c                       |    2 +-
 5 files changed, 21 insertions(+), 16 deletions(-)

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 1e49be4..cbd7400 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -23,6 +23,7 @@ struct vm_area_struct;
 #define ___GFP_REPEAT		0x400u
 #define ___GFP_NOFAIL		0x800u
 #define ___GFP_NORETRY		0x1000u
+#define ___GFP_MEMALLOC		0x2000u
 #define ___GFP_COMP		0x4000u
 #define ___GFP_ZERO		0x8000u
 #define ___GFP_NOMEMALLOC	0x10000u
@@ -76,9 +77,14 @@ struct vm_area_struct;
 #define __GFP_REPEAT	((__force gfp_t)___GFP_REPEAT)	/* See above */
 #define __GFP_NOFAIL	((__force gfp_t)___GFP_NOFAIL)	/* See above */
 #define __GFP_NORETRY	((__force gfp_t)___GFP_NORETRY) /* See above */
+#define __GFP_MEMALLOC	((__force gfp_t)___GFP_MEMALLOC)/* Allow access to emergency reserves */
 #define __GFP_COMP	((__force gfp_t)___GFP_COMP)	/* Add compound page metadata */
 #define __GFP_ZERO	((__force gfp_t)___GFP_ZERO)	/* Return zeroed page on success */
-#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) /* Don't use emergency reserves */
+#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) /* Don't use emergency reserves.
+							 * This takes precedence over the
+							 * __GFP_MEMALLOC flag if both are
+							 * set
+							 */
 #define __GFP_HARDWALL   ((__force gfp_t)___GFP_HARDWALL) /* Enforce hardwall cpuset memory allocs */
 #define __GFP_THISNODE	((__force gfp_t)___GFP_THISNODE)/* No fallback, no policies */
 #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) /* Page is reclaimable */
@@ -129,7 +135,7 @@ struct vm_area_struct;
 /* Control page allocator reclaim behavior */
 #define GFP_RECLAIM_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS|\
 			__GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\
-			__GFP_NORETRY|__GFP_NOMEMALLOC)
+			__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC)
 
 /* Control slab gfp mask during early boot */
 #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_WAIT|__GFP_IO|__GFP_FS))
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index ad0ad6f..8120fdc 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -55,7 +55,7 @@ struct page {
 			pgoff_t index;		/* Our offset within mapping. */
 			void *freelist;		/* slub/slob first free object */
 			bool pfmemalloc;	/* If set by the page allocator,
-						 * ALLOC_PFMEMALLOC was set
+						 * ALLOC_NO_WATERMARKS was set
 						 * and the low watermark was not
 						 * met implying that the system
 						 * is under some pressure. The
diff --git a/include/trace/events/gfpflags.h b/include/trace/events/gfpflags.h
index 9fe3a366..d6fd8e5 100644
--- a/include/trace/events/gfpflags.h
+++ b/include/trace/events/gfpflags.h
@@ -30,6 +30,7 @@
 	{(unsigned long)__GFP_COMP,		"GFP_COMP"},		\
 	{(unsigned long)__GFP_ZERO,		"GFP_ZERO"},		\
 	{(unsigned long)__GFP_NOMEMALLOC,	"GFP_NOMEMALLOC"},	\
+	{(unsigned long)__GFP_MEMALLOC,		"GFP_MEMALLOC"},	\
 	{(unsigned long)__GFP_HARDWALL,		"GFP_HARDWALL"},	\
 	{(unsigned long)__GFP_THISNODE,		"GFP_THISNODE"},	\
 	{(unsigned long)__GFP_RECLAIMABLE,	"GFP_RECLAIMABLE"},	\
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9c697e5..b6c0727 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1505,7 +1505,6 @@ failed:
 #define ALLOC_HARDER		0x10 /* try to alloc harder */
 #define ALLOC_HIGH		0x20 /* __GFP_HIGH set */
 #define ALLOC_CPUSET		0x40 /* check for correct cpuset */
-#define ALLOC_PFMEMALLOC	0x80 /* Caller has PF_MEMALLOC set */
 
 #ifdef CONFIG_FAIL_PAGE_ALLOC
 
@@ -2263,11 +2262,10 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 	} else if (unlikely(rt_task(current)) && !in_interrupt())
 		alloc_flags |= ALLOC_HARDER;
 
-	if ((current->flags & PF_MEMALLOC) ||
-			unlikely(test_thread_flag(TIF_MEMDIE))) {
-		alloc_flags |= ALLOC_PFMEMALLOC;
-
-		if (likely(!(gfp_mask & __GFP_NOMEMALLOC)) && !in_interrupt())
+	if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) {
+		if (gfp_mask & __GFP_MEMALLOC)
+			alloc_flags |= ALLOC_NO_WATERMARKS;
+		else if (likely(!(gfp_mask & __GFP_NOMEMALLOC)) && !in_interrupt())
 			alloc_flags |= ALLOC_NO_WATERMARKS;
 	}
 
@@ -2276,7 +2274,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 
 bool gfp_pfmemalloc_allowed(gfp_t gfp_mask)
 {
-	return !!(gfp_to_alloc_flags(gfp_mask) & ALLOC_PFMEMALLOC);
+	return !!(gfp_to_alloc_flags(gfp_mask) & ALLOC_NO_WATERMARKS);
 }
 
 static inline struct page *
@@ -2467,12 +2465,12 @@ nopage:
 	return page;
 got_pg:
 	/*
-	 * page->pfmemalloc is set when the caller had PFMEMALLOC set or is
-	 * been OOM killed. The expectation is that the caller is taking
-	 * steps that will free more memory. The caller should avoid the
-	 * page being used for !PFMEMALLOC purposes.
+	 * page->pfmemalloc is set when the caller had PFMEMALLOC set, is
+	 * been OOM killed or specified __GFP_MEMALLOC. The expectation is
+	 * that the caller is taking steps that will free more memory. The
+	 * caller should avoid the page being used for !PFMEMALLOC purposes.
 	 */
-	page->pfmemalloc = !!(alloc_flags & ALLOC_PFMEMALLOC);
+	page->pfmemalloc = !!(alloc_flags & ALLOC_NO_WATERMARKS);
 
 	if (kmemcheck_enabled)
 		kmemcheck_pagealloc_alloc(page, order, gfp_mask);
diff --git a/mm/slab.c b/mm/slab.c
index c0d51f1..d9fe508 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1907,7 +1907,7 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 		return NULL;
 	}
 
-	/* Record if ALLOC_PFMEMALLOC was set when allocating the slab */
+	/* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */
 	if (unlikely(page->pfmemalloc))
 		pfmemalloc_active = true;
 
-- 
1.7.9.2

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Powered by blists - more mailing lists