[PATCH 00/14] Swap-over-NBD without deadlocking v5

[PATCH 00/14] Swap-over-NBD without deadlocking v5

[Mel Gorman]

Changelog since V4
  o Update comment clarifying what protocols can be used		(Michal)
  o Rebase to 3.0-rc3

Changelog since V3
  o Propogate pfmemalloc from packet fragment pages to skb		(Neil)
  o Rebase to 3.0-rc2

Changelog since V2
  o Document that __GFP_NOMEMALLOC overrides __GFP_MEMALLOC		(Neil)
  o Use wait_event_interruptible					(Neil)
  o Use !! when casting to bool to avoid any possibilitity of type
    truncation								(Neil)
  o Nicer logic when using skb_pfmemalloc_protocol			(Neil)

Changelog since V1
  o Rebase on top of mmotm
  o Use atomic_t for memalloc_socks		(David Miller)
  o Remove use of sk_memalloc_socks in vmscan	(Neil Brown)
  o Check throttle within prepare_to_wait	(Neil Brown)
  o Add statistics on throttling instead of printk

Swapping over NBD is something that is technically possible but not
often advised. While there are number of guides on the internet
on how to configure it and nbd-client supports a -swap switch to
"prevent deadlocks", the fact of the matter is a machine using NBD
for swap can be locked up within minutes if swap is used intensively.

The problem is that network block devices do not use mempools like
normal block devices do. As the host cannot control where they receive
packets from, they cannot reliably work out in advance how much memory
they might need.

Some years ago, Peter Ziljstra developed a series of patches that
supported swap over an NFS that some distributions are carrying in
their kernels. This patch series borrows very heavily from Peter's work
to support swapping over NBD (the relatively straight-forward case)
and uses throttling instead of dynamically resized memory reserves
so the series is not too unwieldy for review.

Patch 1 serialises access to min_free_kbytes. It's not strictly needed
	by this series but as the series cares about watermarks in
	general, it's a harmless fix. It could be merged independently.

Patch 2 adds knowledge of the PFMEMALLOC reserves to SLAB and SLUB to
	preserve access to pages allocated under low memory situations
	to callers that are freeying memory.

Patch 3 introduces __GFP_MEMALLOC to allow access to the PFMEMALLOC
	reserves without setting PFMEMALLOC.

Patch 4 opens the possibility for softirqs to use PFMEMALLOC reserves
	for later use by network packet processing.

Patch 5 ignores memory policies when ALLOC_NO_WATERMARKS is set.

Patches 6-10 allows network processing to use PFMEMALLOC reserves when
	the socket has been marked as being used by the VM to clean
	pages. If packets are received and stored in pages that were
	allocated under low-memory situations and are unrelated to
	the VM, the packets are dropped.

Patch 11 is a micro-optimisation to avoid a function call in the
	common case.

Patch 12 tags NBD sockets as being SOCK_MEMALLOC so they can use
	PFMEMALLOC if necessary.

Patch 13 notes that it is still possible for the PFMEMALLOC reserve
	to be depleted. To prevent this, direct reclaimers get
	throttled on a waitqueue if 50% of the PFMEMALLOC reserves are
	depleted.  It is expected that kswapd and the direct reclaimers
	already running will clean enough pages for the low watermark
	to be reached and the throttled processes are woken up.

Patch 14 adds a statistic to track how often processes get throttled

Some basic performance testing was run using kernel builds, netperf
on loopback for UDP and TCP, hackbench (pipes and sockets), iozone
and sysbench. Each of them were expected to use the sl*b allocators
reasonably heavily but there did not appear to be significant
performance variances. Here is the results from netperf using
slab as an example

NETPERF UDP
      64   237.47 ( 0.00%)    237.34 (-0.05%) 
     128   472.69 ( 0.00%)    465.96 (-1.44%) 
     256   926.82 ( 0.00%)    948.40 ( 2.28%) 
    1024  3260.08 ( 0.00%)   3266.50 ( 0.20%) 
    2048  5535.11 ( 0.00%)   5453.55 (-1.50%) 
    3312  7496.60 ( 0.00%)*  7574.44 ( 1.03%) 
             1.12%             1.00%        
    4096  8266.35 ( 0.00%)*  8240.06 (-0.32%)*
             1.18%             1.49%        
    8192 11026.01 ( 0.00%)  11010.44 (-0.14%) 
   16384 14653.98 ( 0.00%)  14666.97 ( 0.09%) 
MMTests Statistics: duration
User/Sys Time Running Test (seconds)       2156.64   1873.27
Total Elapsed Time (seconds)               2570.09   2234.10

NETPERF TCP
                   netperf-tcp       tcp-swapnbd
                  vanilla-slab         v4r3-slab
      64  1250.76 ( 0.00%)   1256.52 ( 0.46%) 
     128  2290.70 ( 0.00%)   2336.43 ( 1.96%) 
     256  3668.42 ( 0.00%)   3751.17 ( 2.21%) 
    1024  7214.33 ( 0.00%)   7237.23 ( 0.32%) 
    2048  8230.01 ( 0.00%)   8280.02 ( 0.60%) 
    3312  8634.95 ( 0.00%)   8758.62 ( 1.41%) 
    4096  8851.18 ( 0.00%)   9045.88 ( 2.15%) 
    8192 10067.59 ( 0.00%)  10263.30 ( 1.91%) 
   16384 11523.26 ( 0.00%)  11654.78 ( 1.13%) 
MMTests Statistics: duration
User/Sys Time Running Test (seconds)       1450.23    1389.8
Total Elapsed Time (seconds)               1450.41   1390.35

Here is the equivalent test for SLUB

                   netperf-udp       udp-swapnbd
                  vanilla-slub         v4r3-slub
      64   235.33 ( 0.00%)    237.80 ( 1.04%) 
     128   465.92 ( 0.00%)    469.98 ( 0.86%) 
     256   907.16 ( 0.00%)    907.58 ( 0.05%) 
    1024  3240.25 ( 0.00%)   3255.56 ( 0.47%) 
    2048  5564.87 ( 0.00%)   5446.46 (-2.17%) 
    3312  7427.65 ( 0.00%)*  7650.00 ( 2.91%) 
             1.33%             1.00%        
    4096  8004.51 ( 0.00%)*  8132.79 ( 1.58%)*
             1.05%             1.21%        
    8192 11079.60 ( 0.00%)  10927.09 (-1.40%) 
   16384 14737.38 ( 0.00%)  15019.50 ( 1.88%) 
MMTests Statistics: duration
User/Sys Time Running Test (seconds)       2056.21   2160.38
Total Elapsed Time (seconds)               2426.09   2498.16

NETPERF TCP
                   netperf-tcp       tcp-swapnbd
                  vanilla-slub         v4r3-slub
      64  1251.64 ( 0.00%)   1262.89 ( 0.89%) 
     128  2289.88 ( 0.00%)   2332.94 ( 1.85%) 
     256  3654.34 ( 0.00%)   3736.48 ( 2.20%) 
    1024  7192.47 ( 0.00%)   7286.96 ( 1.30%) 
    2048  8243.55 ( 0.00%)   8291.50 ( 0.58%) 
    3312  8664.16 ( 0.00%)   8799.88 ( 1.54%) 
    4096  8869.13 ( 0.00%)   9018.12 ( 1.65%) 
    8192 10009.53 ( 0.00%)  10214.26 ( 2.00%) 
   16384 11470.78 ( 0.00%)  11685.20 ( 1.83%) 
MMTests Statistics: duration
User/Sys Time Running Test (seconds)       1368.28   1511.81
Total Elapsed Time (seconds)               1370.33   1510.42

Time to completion varied a lot but this can happen with netperf as
it tries to find results within a sufficiently high confidence. There
were some small gains and losses but they are close to the variances
seen between kernel releases.

For testing swap-over-NBD, a machine was booted with 2G of RAM with a
swapfile backed by NBD. 8*NUM_CPU processes were started that create
anonymous memory mappings and read them linearly in a loop. The total
size of the mappings were 4*PHYSICAL_MEMORY to use swap heavily under
memory pressure. Without the patches, the machine locks up within
minutes and runs to completion with them applied.

 drivers/block/nbd.c             |    7 +-
 include/linux/gfp.h             |   13 ++-
 include/linux/mm_types.h        |    8 ++
 include/linux/mmzone.h          |    1 +
 include/linux/sched.h           |    7 +
 include/linux/skbuff.h          |   21 +++-
 include/linux/slub_def.h        |    1 +
 include/linux/vm_event_item.h   |    1 +
 include/net/sock.h              |   19 +++
 include/trace/events/gfpflags.h |    1 +
 kernel/softirq.c                |    3 +
 mm/page_alloc.c                 |   57 +++++++--
 mm/slab.c                       |  240 +++++++++++++++++++++++++++++++++------
 mm/slub.c                       |   33 +++++-
 mm/vmscan.c                     |   55 +++++++++
 mm/vmstat.c                     |    1 +
 net/core/dev.c                  |   48 +++++++-
 net/core/filter.c               |    8 ++
 net/core/skbuff.c               |   95 +++++++++++++---
 net/core/sock.c                 |   42 +++++++
 net/ipv4/tcp.c                  |    3 +-
 net/ipv4/tcp_output.c           |   13 +-
 net/ipv6/tcp_ipv6.c             |   12 ++-
 23 files changed, 602 insertions(+), 87 deletions(-)

-- 
1.7.3.4

[PATCH 01/14] mm: Serialize access to min_free_kbytes

[Mel Gorman]

There is a race between the min_free_kbytes sysctl, memory hotplug
and transparent hugepage support enablement.  Memory hotplug uses a
zonelists_mutex to avoid a race when building zonelists. Reuse it to
serialise watermark updates.

[a.p.zijlstra@chello.nl: Older patch fixed the race with spinlock]
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/page_alloc.c |   23 +++++++++++++++--------
 1 files changed, 15 insertions(+), 8 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4e8985a..a327a72 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5045,14 +5045,7 @@ static void setup_per_zone_lowmem_reserve(void)
 	calculate_totalreserve_pages();
 }
 
-/**
- * setup_per_zone_wmarks - called when min_free_kbytes changes
- * or when memory is hot-{added|removed}
- *
- * Ensures that the watermark[min,low,high] values for each zone are set
- * correctly with respect to min_free_kbytes.
- */
-void setup_per_zone_wmarks(void)
+static void __setup_per_zone_wmarks(void)
 {
 	unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
 	unsigned long lowmem_pages = 0;
@@ -5107,6 +5100,20 @@ void setup_per_zone_wmarks(void)
 	calculate_totalreserve_pages();
 }
 
+/**
+ * setup_per_zone_wmarks - called when min_free_kbytes changes
+ * or when memory is hot-{added|removed}
+ *
+ * Ensures that the watermark[min,low,high] values for each zone are set
+ * correctly with respect to min_free_kbytes.
+ */
+void setup_per_zone_wmarks(void)
+{
+	mutex_lock(&zonelists_mutex);
+	__setup_per_zone_wmarks();
+	mutex_unlock(&zonelists_mutex);
+}
+
 /*
  * The inactive anon list should be small enough that the VM never has to
  * do too much work, but large enough that each inactive page has a chance
-- 
1.7.3.4

[PATCH 02/14] mm: sl[au]b: Add knowledge of PFMEMALLOC reserve pages

[Mel Gorman]

Allocations of pages below the min watermark run a risk of the machine
hanging due to lack of memory.  To prevent this, only callers who
have PF_MEMALLOC or TIF_MEMDIE set and not processing an interrupt
are allowed to allocate with ALLOC_NO_WATERMARKS. Once they are
allocated to a slab though, nothing prevents other callers consuming
free objects within those slabs. This patch limits access to slab
pages that were alloced from the PFMEMALLOC reserves.

Pages allocated from the reserve are returned with page->pfmemalloc
set and it's up to the caller to determine how the page should be
protected.  SLAB restricts access to any page with page->pfmemalloc set
to callers which are known to able to access the PFMEMALLOC reserve. If
one is not available, an attempt is made to allocate a new page rather
than use a reserve. SLUB is a bit more relaxed in that it only records
if the current per-CPU page was allocated from PFMEMALLOC reserve and
uses another partial slab if the caller does not have the necessary
GFP or process flags. This was found to be sufficient in tests to
avoid hangs due to SLUB generally maintaining smaller lists than SLAB.

In low-memory conditions it does mean that !PFMEMALLOC allocators
can fail a slab allocation even though free objects are available
because they are being preserved for callers that are freeing pages.

[a.p.zijlstra@chello.nl: Original implementation]
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/mm_types.h |    8 ++
 include/linux/slub_def.h |    1 +
 mm/internal.h            |    3 +
 mm/page_alloc.c          |   27 +++++-
 mm/slab.c                |  216 +++++++++++++++++++++++++++++++++++++++-------
 mm/slub.c                |   33 ++++++--
 6 files changed, 244 insertions(+), 44 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 027935c..2986426 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -71,6 +71,14 @@ struct page {
 	union {
 		pgoff_t index;		/* Our offset within mapping. */
 		void *freelist;		/* SLUB: freelist req. slab lock */
+		bool pfmemalloc;	/* If set by the page allocator,
+					 * ALLOC_PFMEMALLOC was set and the
+					 * low watermark was not met implying
+					 * that the system is under some
+					 * pressure. The caller should try
+					 * ensure this page is only used to
+					 * free other pages.
+					 */
 	};
 	struct list_head lru;		/* Pageout list, eg. active_list
 					 * protected by zone->lru_lock !
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index c8668d1..ff7eb16 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -40,6 +40,7 @@ struct kmem_cache_cpu {
 	unsigned long tid;	/* Globally unique transaction id */
 	struct page *page;	/* The slab from which we are allocating */
 	int node;		/* The node of the page (or -1 for debug) */
+	bool pfmemalloc;	/* Slab page had pfmemalloc set */
 #ifdef CONFIG_SLUB_STATS
 	unsigned stat[NR_SLUB_STAT_ITEMS];
 #endif
diff --git a/mm/internal.h b/mm/internal.h
index d071d380..a520f3b 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -193,6 +193,9 @@ static inline struct page *mem_map_next(struct page *iter,
 #define __paginginit __init
 #endif
 
+/* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */
+bool gfp_pfmemalloc_allowed(gfp_t gfp_mask);
+
 /* Memory initialisation debug and verification */
 enum mminit_level {
 	MMINIT_WARNING,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a327a72..7769a3d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -656,6 +656,7 @@ static bool free_pages_prepare(struct page *page, unsigned int order)
 	trace_mm_page_free_direct(page, order);
 	kmemcheck_free_shadow(page, order);
 
+	page->pfmemalloc = false;
 	if (PageAnon(page))
 		page->mapping = NULL;
 	for (i = 0; i < (1 << order); i++)
@@ -1174,6 +1175,7 @@ void free_hot_cold_page(struct page *page, int cold)
 
 	migratetype = get_pageblock_migratetype(page);
 	set_page_private(page, migratetype);
+	page->pfmemalloc = false;
 	local_irq_save(flags);
 	if (unlikely(wasMlocked))
 		free_page_mlock(page);
@@ -1367,6 +1369,7 @@ 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
 
@@ -2041,16 +2044,22 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 	} else if (unlikely(rt_task(current)) && !in_interrupt())
 		alloc_flags |= ALLOC_HARDER;
 
-	if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) {
-		if (!in_interrupt() &&
-		    ((current->flags & PF_MEMALLOC) ||
-		     unlikely(test_thread_flag(TIF_MEMDIE))))
+	if ((current->flags & PF_MEMALLOC) ||
+			unlikely(test_thread_flag(TIF_MEMDIE))) {
+		alloc_flags |= ALLOC_PFMEMALLOC;
+
+		if (likely(!(gfp_mask & __GFP_NOMEMALLOC)) && !in_interrupt())
 			alloc_flags |= ALLOC_NO_WATERMARKS;
 	}
 
 	return alloc_flags;
 }
 
+bool gfp_pfmemalloc_allowed(gfp_t gfp_mask)
+{
+	return !!(gfp_to_alloc_flags(gfp_mask) & ALLOC_PFMEMALLOC);
+}
+
 static inline struct page *
 __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
@@ -2223,8 +2232,16 @@ nopage:
 got_pg:
 	if (kmemcheck_enabled)
 		kmemcheck_pagealloc_alloc(page, order, gfp_mask);
-	return page;
 
+	/*
+	 * 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 = !!(alloc_flags & ALLOC_PFMEMALLOC);
+
+	return page;
 }
 
 /*
diff --git a/mm/slab.c b/mm/slab.c
index d96e223..a6480df 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -121,6 +121,8 @@
 #include	<asm/tlbflush.h>
 #include	<asm/page.h>
 
+#include	"internal.h"
+
 /*
  * DEBUG	- 1 for kmem_cache_create() to honour; SLAB_RED_ZONE & SLAB_POISON.
  *		  0 for faster, smaller code (especially in the critical paths).
@@ -227,6 +229,7 @@ struct slab {
 			unsigned int inuse;	/* num of objs active in slab */
 			kmem_bufctl_t free;
 			unsigned short nodeid;
+			bool pfmemalloc;	/* Slab had pfmemalloc set */
 		};
 		struct slab_rcu __slab_cover_slab_rcu;
 	};
@@ -248,15 +251,37 @@ struct array_cache {
 	unsigned int avail;
 	unsigned int limit;
 	unsigned int batchcount;
-	unsigned int touched;
+	bool touched;
+	bool pfmemalloc;
 	spinlock_t lock;
 	void *entry[];	/*
 			 * Must have this definition in here for the proper
 			 * alignment of array_cache. Also simplifies accessing
 			 * the entries.
+			 *
+			 * Entries should not be directly dereferenced as
+			 * entries belonging to slabs marked pfmemalloc will
+			 * have the lower bits set SLAB_OBJ_PFMEMALLOC
 			 */
 };
 
+#define SLAB_OBJ_PFMEMALLOC	1
+static inline bool is_obj_pfmemalloc(void *objp)
+{
+	return (unsigned long)objp & SLAB_OBJ_PFMEMALLOC;
+}
+
+static inline void set_obj_pfmemalloc(void **objp)
+{
+	*objp = (void *)((unsigned long)*objp | SLAB_OBJ_PFMEMALLOC);
+	return;
+}
+
+static inline void clear_obj_pfmemalloc(void **objp)
+{
+	*objp = (void *)((unsigned long)*objp & ~SLAB_OBJ_PFMEMALLOC);
+}
+
 /*
  * bootstrap: The caches do not work without cpuarrays anymore, but the
  * cpuarrays are allocated from the generic caches...
@@ -889,12 +914,100 @@ static struct array_cache *alloc_arraycache(int node, int entries,
 		nc->avail = 0;
 		nc->limit = entries;
 		nc->batchcount = batchcount;
-		nc->touched = 0;
+		nc->touched = false;
 		spin_lock_init(&nc->lock);
 	}
 	return nc;
 }
 
+/* Clears ac->pfmemalloc if no slabs have pfmalloc set */
+static void check_ac_pfmemalloc(struct kmem_cache *cachep,
+						struct array_cache *ac)
+{
+	struct kmem_list3 *l3 = cachep->nodelists[numa_mem_id()];
+	struct slab *slabp;
+
+	if (!ac->pfmemalloc)
+		return;
+
+	list_for_each_entry(slabp, &l3->slabs_full, list)
+		if (slabp->pfmemalloc)
+			return;
+
+	list_for_each_entry(slabp, &l3->slabs_partial, list)
+		if (slabp->pfmemalloc)
+			return;
+
+	list_for_each_entry(slabp, &l3->slabs_free, list)
+		if (slabp->pfmemalloc)
+			return;
+
+	ac->pfmemalloc = false;
+}
+
+static void *ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac,
+						gfp_t flags, bool force_refill)
+{
+	int i;
+	void *objp = ac->entry[--ac->avail];
+
+	/* Ensure the caller is allowed to use objects from PFMEMALLOC slab */
+	if (unlikely(is_obj_pfmemalloc(objp))) {
+		struct kmem_list3 *l3;
+
+		if (gfp_pfmemalloc_allowed(flags)) {
+			clear_obj_pfmemalloc(&objp);
+			return objp;
+		}
+
+		/* The caller cannot use PFMEMALLOC objects, find another one */
+		for (i = 1; i < ac->avail; i++) {
+			/* If a !PFMEMALLOC object is found, swap them */
+			if (!is_obj_pfmemalloc(ac->entry[i])) {
+				objp = ac->entry[i];
+				ac->entry[i] = ac->entry[ac->avail];
+				ac->entry[ac->avail] = objp;
+				return objp;
+			}
+		}
+
+		/*
+		 * If there are empty slabs on the slabs_free list and we are
+		 * being forced to refill the cache, mark this one !pfmemalloc.
+		 */
+		l3 = cachep->nodelists[numa_mem_id()];
+		if (!list_empty(&l3->slabs_free) && force_refill) {
+			struct slab *slabp = virt_to_slab(objp);
+			slabp->pfmemalloc = false;
+			clear_obj_pfmemalloc(&objp);
+			check_ac_pfmemalloc(cachep, ac);
+			return objp;
+		}
+
+		/* No !PFMEMALLOC objects available */
+		ac->avail++;
+		objp = NULL;
+	}
+
+	return objp;
+}
+
+static void ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac,
+								void *objp)
+{
+	struct slab *slabp;
+
+	/* If there are pfmemalloc slabs, check if the object is part of one */
+	if (unlikely(ac->pfmemalloc)) {
+		slabp = virt_to_slab(objp);
+
+		if (slabp->pfmemalloc)
+			set_obj_pfmemalloc(&objp);
+	}
+
+	ac->entry[ac->avail++] = objp;
+}
+
 /*
  * Transfer objects in one arraycache to another.
  * Locking must be handled by the caller.
@@ -1071,7 +1184,7 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
 			STATS_INC_ACOVERFLOW(cachep);
 			__drain_alien_cache(cachep, alien, nodeid);
 		}
-		alien->entry[alien->avail++] = objp;
+		ac_put_obj(cachep, alien, objp);
 		spin_unlock(&alien->lock);
 	} else {
 		spin_lock(&(cachep->nodelists[nodeid])->list_lock);
@@ -1678,7 +1791,8 @@ __initcall(cpucache_init);
  * did not request dmaable memory, we might get it, but that
  * would be relatively rare and ignorable.
  */
-static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
+static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid,
+		bool *pfmemalloc)
 {
 	struct page *page;
 	int nr_pages;
@@ -1699,6 +1813,7 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 	page = alloc_pages_exact_node(nodeid, flags | __GFP_NOTRACK, cachep->gfporder);
 	if (!page)
 		return NULL;
+	*pfmemalloc = page->pfmemalloc;
 
 	nr_pages = (1 << cachep->gfporder);
 	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
@@ -2131,7 +2246,7 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
 	cpu_cache_get(cachep)->avail = 0;
 	cpu_cache_get(cachep)->limit = BOOT_CPUCACHE_ENTRIES;
 	cpu_cache_get(cachep)->batchcount = 1;
-	cpu_cache_get(cachep)->touched = 0;
+	cpu_cache_get(cachep)->touched = false;
 	cachep->batchcount = 1;
 	cachep->limit = BOOT_CPUCACHE_ENTRIES;
 	return 0;
@@ -2678,6 +2793,7 @@ static struct slab *alloc_slabmgmt(struct kmem_cache *cachep, void *objp,
 	slabp->s_mem = objp + colour_off;
 	slabp->nodeid = nodeid;
 	slabp->free = 0;
+	slabp->pfmemalloc = false;
 	return slabp;
 }
 
@@ -2809,7 +2925,7 @@ static void slab_map_pages(struct kmem_cache *cache, struct slab *slab,
  * kmem_cache_alloc() when there are no active objs left in a cache.
  */
 static int cache_grow(struct kmem_cache *cachep,
-		gfp_t flags, int nodeid, void *objp)
+		gfp_t flags, int nodeid, void *objp, bool pfmemalloc)
 {
 	struct slab *slabp;
 	size_t offset;
@@ -2853,7 +2969,7 @@ static int cache_grow(struct kmem_cache *cachep,
 	 * 'nodeid'.
 	 */
 	if (!objp)
-		objp = kmem_getpages(cachep, local_flags, nodeid);
+		objp = kmem_getpages(cachep, local_flags, nodeid, &pfmemalloc);
 	if (!objp)
 		goto failed;
 
@@ -2863,6 +2979,13 @@ static int cache_grow(struct kmem_cache *cachep,
 	if (!slabp)
 		goto opps1;
 
+	/* Record if ALLOC_PFMEMALLOC was set when allocating the slab */
+	if (pfmemalloc) {
+		struct array_cache *ac = cpu_cache_get(cachep);
+		slabp->pfmemalloc = true;
+		ac->pfmemalloc = true;
+	}
+
 	slab_map_pages(cachep, slabp, objp);
 
 	cache_init_objs(cachep, slabp);
@@ -3004,16 +3127,19 @@ bad:
 #define check_slabp(x,y) do { } while(0)
 #endif
 
-static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags)
+static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags,
+							bool force_refill)
 {
 	int batchcount;
 	struct kmem_list3 *l3;
 	struct array_cache *ac;
 	int node;
 
-retry:
 	check_irq_off();
 	node = numa_mem_id();
+	if (unlikely(force_refill))
+		goto force_grow;
+retry:
 	ac = cpu_cache_get(cachep);
 	batchcount = ac->batchcount;
 	if (!ac->touched && batchcount > BATCHREFILL_LIMIT) {
@@ -3031,7 +3157,7 @@ retry:
 
 	/* See if we can refill from the shared array */
 	if (l3->shared && transfer_objects(ac, l3->shared, batchcount)) {
-		l3->shared->touched = 1;
+		l3->shared->touched = true;
 		goto alloc_done;
 	}
 
@@ -3063,8 +3189,8 @@ retry:
 			STATS_INC_ACTIVE(cachep);
 			STATS_SET_HIGH(cachep);
 
-			ac->entry[ac->avail++] = slab_get_obj(cachep, slabp,
-							    node);
+			ac_put_obj(cachep, ac, slab_get_obj(cachep, slabp,
+									node));
 		}
 		check_slabp(cachep, slabp);
 
@@ -3083,18 +3209,25 @@ alloc_done:
 
 	if (unlikely(!ac->avail)) {
 		int x;
-		x = cache_grow(cachep, flags | GFP_THISNODE, node, NULL);
+force_grow:
+		x = cache_grow(cachep, flags | GFP_THISNODE, node, NULL, false);
 
 		/* cache_grow can reenable interrupts, then ac could change. */
 		ac = cpu_cache_get(cachep);
-		if (!x && ac->avail == 0)	/* no objects in sight? abort */
+
+		/* no objects in sight? abort */
+		if (!x && (ac->avail == 0 || force_refill))
 			return NULL;
 
-		if (!ac->avail)		/* objects refilled by interrupt? */
+		/* objects refilled by interrupt? */
+		if (!ac->avail) {
+			node = numa_node_id();
 			goto retry;
+		}
 	}
-	ac->touched = 1;
-	return ac->entry[--ac->avail];
+	ac->touched = true;
+
+	return ac_get_obj(cachep, ac, flags, force_refill);
 }
 
 static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep,
@@ -3177,23 +3310,35 @@ static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
 {
 	void *objp;
 	struct array_cache *ac;
+	bool force_refill = false;
 
 	check_irq_off();
 
 	ac = cpu_cache_get(cachep);
 	if (likely(ac->avail)) {
-		STATS_INC_ALLOCHIT(cachep);
-		ac->touched = 1;
-		objp = ac->entry[--ac->avail];
-	} else {
-		STATS_INC_ALLOCMISS(cachep);
-		objp = cache_alloc_refill(cachep, flags);
+		ac->touched = true;
+		objp = ac_get_obj(cachep, ac, flags, false);
+
 		/*
-		 * the 'ac' may be updated by cache_alloc_refill(),
-		 * and kmemleak_erase() requires its correct value.
+		 * Allow for the possibility all avail objects are not allowed
+		 * by the current flags
 		 */
-		ac = cpu_cache_get(cachep);
+		if (objp) {
+			STATS_INC_ALLOCHIT(cachep);
+			goto out;
+		}
+		force_refill = true;
 	}
+
+	STATS_INC_ALLOCMISS(cachep);
+	objp = cache_alloc_refill(cachep, flags, force_refill);
+	/*
+	 * the 'ac' may be updated by cache_alloc_refill(),
+	 * and kmemleak_erase() requires its correct value.
+	 */
+	ac = cpu_cache_get(cachep);
+
+out:
 	/*
 	 * To avoid a false negative, if an object that is in one of the
 	 * per-CPU caches is leaked, we need to make sure kmemleak doesn't
@@ -3246,6 +3391,7 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
 	enum zone_type high_zoneidx = gfp_zone(flags);
 	void *obj = NULL;
 	int nid;
+	bool pfmemalloc;
 
 	if (flags & __GFP_THISNODE)
 		return NULL;
@@ -3282,7 +3428,8 @@ retry:
 		if (local_flags & __GFP_WAIT)
 			local_irq_enable();
 		kmem_flagcheck(cache, flags);
-		obj = kmem_getpages(cache, local_flags, numa_mem_id());
+		obj = kmem_getpages(cache, local_flags, numa_mem_id(),
+							&pfmemalloc);
 		if (local_flags & __GFP_WAIT)
 			local_irq_disable();
 		if (obj) {
@@ -3290,7 +3437,7 @@ retry:
 			 * Insert into the appropriate per node queues
 			 */
 			nid = page_to_nid(virt_to_page(obj));
-			if (cache_grow(cache, flags, nid, obj)) {
+			if (cache_grow(cache, flags, nid, obj, pfmemalloc)) {
 				obj = ____cache_alloc_node(cache,
 					flags | GFP_THISNODE, nid);
 				if (!obj)
@@ -3362,7 +3509,7 @@ retry:
 
 must_grow:
 	spin_unlock(&l3->list_lock);
-	x = cache_grow(cachep, flags | GFP_THISNODE, nodeid, NULL);
+	x = cache_grow(cachep, flags | GFP_THISNODE, nodeid, NULL, false);
 	if (x)
 		goto retry;
 
@@ -3512,9 +3659,12 @@ static void free_block(struct kmem_cache *cachep, void **objpp, int nr_objects,
 	struct kmem_list3 *l3;
 
 	for (i = 0; i < nr_objects; i++) {
-		void *objp = objpp[i];
+		void *objp;
 		struct slab *slabp;
 
+		clear_obj_pfmemalloc(&objpp[i]);
+		objp = objpp[i];
+
 		slabp = virt_to_slab(objp);
 		l3 = cachep->nodelists[node];
 		list_del(&slabp->list);
@@ -3627,12 +3777,12 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp,
 
 	if (likely(ac->avail < ac->limit)) {
 		STATS_INC_FREEHIT(cachep);
-		ac->entry[ac->avail++] = objp;
+		ac_put_obj(cachep, ac, objp);
 		return;
 	} else {
 		STATS_INC_FREEMISS(cachep);
 		cache_flusharray(cachep, ac);
-		ac->entry[ac->avail++] = objp;
+		ac_put_obj(cachep, ac, objp);
 	}
 }
 
@@ -4058,7 +4208,7 @@ static void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3,
 	if (!ac || !ac->avail)
 		return;
 	if (ac->touched && !force) {
-		ac->touched = 0;
+		ac->touched = false;
 	} else {
 		spin_lock_irq(&l3->list_lock);
 		if (ac->avail) {
diff --git a/mm/slub.c b/mm/slub.c
index 35f351f..dd552a5 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -30,6 +30,8 @@
 
 #include <trace/events/kmem.h>
 
+#include "internal.h"
+
 /*
  * Lock order:
  *   1. slab_lock(page)
@@ -1242,7 +1244,8 @@ static void setup_object(struct kmem_cache *s, struct page *page,
 		s->ctor(object);
 }
 
-static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
+static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node,
+							bool *pfmemalloc)
 {
 	struct page *page;
 	void *start;
@@ -1257,6 +1260,7 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 		goto out;
 
 	inc_slabs_node(s, page_to_nid(page), page->objects);
+	*pfmemalloc = page->pfmemalloc;
 	page->slab = s;
 	page->flags |= 1 << PG_slab;
 
@@ -1772,6 +1776,14 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
 	}
 }
 
+static inline bool pfmemalloc_match(struct kmem_cache_cpu *c, gfp_t gfpflags)
+{
+	if (unlikely(c->pfmemalloc))
+		return gfp_pfmemalloc_allowed(gfpflags);
+
+	return true;
+}
+
 /*
  * Slow path. The lockless freelist is empty or we need to perform
  * debugging duties.
@@ -1796,6 +1808,7 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	void **object;
 	struct page *page;
 	unsigned long flags;
+	bool pfmemalloc = false;
 
 	local_irq_save(flags);
 #ifdef CONFIG_PREEMPT
@@ -1815,7 +1828,13 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 		goto new_slab;
 
 	slab_lock(page);
-	if (unlikely(!node_match(c, node)))
+
+	/*
+	 * By rights, we should be searching for a slab page that was
+	 * PFMEMALLOC but right now, we are losing the pfmemalloc
+	 * information when the page leaves the per-cpu allocator
+	 */
+	if (unlikely(!pfmemalloc_match(c, gfpflags) || !node_match(c, node)))
 		goto another_slab;
 
 	stat(s, ALLOC_REFILL);
@@ -1853,7 +1872,7 @@ new_slab:
 	if (gfpflags & __GFP_WAIT)
 		local_irq_enable();
 
-	page = new_slab(s, gfpflags, node);
+	page = new_slab(s, gfpflags, node, &pfmemalloc);
 
 	if (gfpflags & __GFP_WAIT)
 		local_irq_disable();
@@ -1868,6 +1887,7 @@ new_slab:
 		__SetPageSlubFrozen(page);
 		c->node = page_to_nid(page);
 		c->page = page;
+		c->pfmemalloc = pfmemalloc;
 		goto load_freelist;
 	}
 	if (!(gfpflags & __GFP_NOWARN) && printk_ratelimit())
@@ -1927,8 +1947,8 @@ redo:
 	barrier();
 
 	object = c->freelist;
-	if (unlikely(!object || !node_match(c, node)))
-
+	if (unlikely(!object || !node_match(c, node) ||
+					!pfmemalloc_match(c, gfpflags)))
 		object = __slab_alloc(s, gfpflags, node, addr, c);
 
 	else {
@@ -2351,10 +2371,11 @@ static void early_kmem_cache_node_alloc(int node)
 	struct page *page;
 	struct kmem_cache_node *n;
 	unsigned long flags;
+	bool pfmemalloc;	/* Ignore this early in boot */
 
 	BUG_ON(kmem_cache_node->size < sizeof(struct kmem_cache_node));
 
-	page = new_slab(kmem_cache_node, GFP_NOWAIT, node);
+	page = new_slab(kmem_cache_node, GFP_NOWAIT, node, &pfmemalloc);
 
 	BUG_ON(!page);
 	if (page_to_nid(page) != node) {
-- 
1.7.3.4

[PATCH 03/14] mm: Introduce __GFP_MEMALLOC to allow access to emergency reserves

[Mel Gorman]

__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@chello.nl>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/gfp.h             |   10 ++++++++--
 include/linux/mm_types.h        |    2 +-
 include/trace/events/gfpflags.h |    1 +
 mm/page_alloc.c                 |   14 ++++++--------
 mm/slab.c                       |    2 +-
 5 files changed, 17 insertions(+), 12 deletions(-)

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index cb40892..faefba9 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
@@ -75,9 +76,14 @@ 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 */
@@ -127,7 +133,7 @@ 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 2986426..319a7cd 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -72,7 +72,7 @@ struct page {
 		pgoff_t index;		/* Our offset within mapping. */
 		void *freelist;		/* SLUB: freelist req. slab lock */
 		bool pfmemalloc;	/* If set by the page allocator,
-					 * ALLOC_PFMEMALLOC was set and the
+					 * ALLOC_NO_WATERMARKS was set and the
 					 * low watermark was not met implying
 					 * that the system is under some
 					 * pressure. The caller should try
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 7769a3d..27043e7 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1369,7 +1369,6 @@ 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
 
@@ -2044,11 +2043,10 @@ 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;
 	}
 
@@ -2057,7 +2055,7 @@ 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 *
@@ -2239,7 +2237,7 @@ got_pg:
 	 * 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);
 
 	return page;
 }
diff --git a/mm/slab.c b/mm/slab.c
index a6480df..fceb656 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2979,7 +2979,7 @@ static int cache_grow(struct kmem_cache *cachep,
 	if (!slabp)
 		goto opps1;
 
-	/* Record if ALLOC_PFMEMALLOC was set when allocating the slab */
+	/* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */
 	if (pfmemalloc) {
 		struct array_cache *ac = cpu_cache_get(cachep);
 		slabp->pfmemalloc = true;
-- 
1.7.3.4

[PATCH 04/14] mm: allow PF_MEMALLOC from softirq context

[Mel Gorman]

This is needed to allow network softirq packet processing to make use
of PF_MEMALLOC.

Currently softirq context cannot use PF_MEMALLOC due to it not being
associated with a task, and therefore not having task flags to fiddle with -
thus the gfp to alloc flag mapping ignores the task flags when in interrupts
(hard or soft) context.

Allowing softirqs to make use of PF_MEMALLOC therefore requires some trickery.
We basically borrow the task flags from whatever process happens to be
preempted by the softirq.

So we modify the gfp to alloc flags mapping to not exclude task flags in
softirq context, and modify the softirq code to save, clear and restore
the PF_MEMALLOC flag.

The save and clear, ensures the preempted task's PF_MEMALLOC flag doesn't
leak into the softirq. The restore ensures a softirq's PF_MEMALLOC flag
cannot leak back into the preempted process.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/sched.h |    7 +++++++
 kernel/softirq.c      |    3 +++
 mm/page_alloc.c       |    5 ++++-
 3 files changed, 14 insertions(+), 1 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index a837b20..7089cf1 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1841,6 +1841,13 @@ static inline void rcu_copy_process(struct task_struct *p)
 
 #endif
 
+static inline void tsk_restore_flags(struct task_struct *p,
+				     unsigned long pflags, unsigned long mask)
+{
+	p->flags &= ~mask;
+	p->flags |= pflags & mask;
+}
+
 #ifdef CONFIG_SMP
 extern void do_set_cpus_allowed(struct task_struct *p,
 			       const struct cpumask *new_mask);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 1396017..2817c27 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -210,6 +210,8 @@ asmlinkage void __do_softirq(void)
 	__u32 pending;
 	int max_restart = MAX_SOFTIRQ_RESTART;
 	int cpu;
+	unsigned long pflags = current->flags;
+	current->flags &= ~PF_MEMALLOC;
 
 	pending = local_softirq_pending();
 	account_system_vtime(current);
@@ -265,6 +267,7 @@ restart:
 
 	account_system_vtime(current);
 	__local_bh_enable(SOFTIRQ_OFFSET);
+	tsk_restore_flags(current, pflags, PF_MEMALLOC);
 }
 
 #ifndef __ARCH_HAS_DO_SOFTIRQ
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 27043e7..4e19606 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2046,7 +2046,10 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 	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())
+		else if (!in_irq() && (current->flags & PF_MEMALLOC))
+			alloc_flags |= ALLOC_NO_WATERMARKS;
+		else if (!in_interrupt() &&
+				unlikely(test_thread_flag(TIF_MEMDIE)))
 			alloc_flags |= ALLOC_NO_WATERMARKS;
 	}
 
-- 
1.7.3.4

[PATCH 05/14] mm: Ignore mempolicies when using ALLOC_NO_WATERMARK

[Mel Gorman]

The reserve is proportionally distributed over all !highmem zones in the
system. So we need to allow an emergency allocation access to all zones.
In order to do that we need to break out of any mempolicy boundaries we
might have.

In my opinion that does not break mempolicies as those are user oriented
and not system oriented. That is, system allocations are not guaranteed to
be within mempolicy boundaries. For instance IRQs don't even have a mempolicy.

So breaking out of mempolicy boundaries for 'rare' emergency allocations,
which are always system allocations (as opposed to user) is ok.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/page_alloc.c |    7 +++++++
 1 files changed, 7 insertions(+), 0 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4e19606..ac779f5 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2126,6 +2126,13 @@ rebalance:
 
 	/* Allocate without watermarks if the context allows */
 	if (alloc_flags & ALLOC_NO_WATERMARKS) {
+		/*
+		 * Ignore mempolicies if ALLOC_NO_WATERMARKS on the grounds
+		 * the allocation is high priority and these type of
+		 * allocations are system rather than user orientated
+		 */
+		zonelist = node_zonelist(numa_node_id(), gfp_mask);
+
 		page = __alloc_pages_high_priority(gfp_mask, order,
 				zonelist, high_zoneidx, nodemask,
 				preferred_zone, migratetype);
-- 
1.7.3.4

[PATCH 06/14] net: Introduce sk_allocation() to allow addition of GFP flags depending on the individual socket

[Mel Gorman]

Introduce sk_allocation(), this function allows to inject sock specific
flags to each sock related allocation. It is only used on allocation
paths that may be required for writing pages back to network storage.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/net/sock.h    |    5 +++++
 net/ipv4/tcp.c        |    3 ++-
 net/ipv4/tcp_output.c |   13 +++++++------
 net/ipv6/tcp_ipv6.c   |   12 +++++++++---
 4 files changed, 23 insertions(+), 10 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index f2046e4..e89c38f 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -585,6 +585,11 @@ static inline int sock_flag(struct sock *sk, enum sock_flags flag)
 	return test_bit(flag, &sk->sk_flags);
 }
 
+static inline gfp_t sk_allocation(struct sock *sk, gfp_t gfp_mask)
+{
+	return gfp_mask;
+}
+
 static inline void sk_acceptq_removed(struct sock *sk)
 {
 	sk->sk_ack_backlog--;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 054a59d..8c1a9d5 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -698,7 +698,8 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp)
 	/* The TCP header must be at least 32-bit aligned.  */
 	size = ALIGN(size, 4);
 
-	skb = alloc_skb_fclone(size + sk->sk_prot->max_header, gfp);
+	skb = alloc_skb_fclone(size + sk->sk_prot->max_header,
+			       sk_allocation(sk, gfp));
 	if (skb) {
 		if (sk_wmem_schedule(sk, skb->truesize)) {
 			/*
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 882e0b0..87b98f6 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2324,7 +2324,7 @@ void tcp_send_fin(struct sock *sk)
 		/* Socket is locked, keep trying until memory is available. */
 		for (;;) {
 			skb = alloc_skb_fclone(MAX_TCP_HEADER,
-					       sk->sk_allocation);
+					       sk_allocation(sk, GFP_KERNEL));
 			if (skb)
 				break;
 			yield();
@@ -2350,7 +2350,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority)
 	struct sk_buff *skb;
 
 	/* NOTE: No TCP options attached and we never retransmit this. */
-	skb = alloc_skb(MAX_TCP_HEADER, priority);
+	skb = alloc_skb(MAX_TCP_HEADER, sk_allocation(sk, priority));
 	if (!skb) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED);
 		return;
@@ -2423,7 +2423,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 
 	if (cvp != NULL && cvp->s_data_constant && cvp->s_data_desired)
 		s_data_desired = cvp->s_data_desired;
-	skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15 + s_data_desired, 1, GFP_ATOMIC);
+	skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15 + s_data_desired, 1,
+					sk_allocation(sk, GFP_ATOMIC));
 	if (skb == NULL)
 		return NULL;
 
@@ -2719,7 +2720,7 @@ void tcp_send_ack(struct sock *sk)
 	 * tcp_transmit_skb() will set the ownership to this
 	 * sock.
 	 */
-	buff = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC);
+	buff = alloc_skb(MAX_TCP_HEADER, sk_allocation(sk, GFP_ATOMIC));
 	if (buff == NULL) {
 		inet_csk_schedule_ack(sk);
 		inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN;
@@ -2734,7 +2735,7 @@ void tcp_send_ack(struct sock *sk)
 
 	/* Send it off, this clears delayed acks for us. */
 	TCP_SKB_CB(buff)->when = tcp_time_stamp;
-	tcp_transmit_skb(sk, buff, 0, GFP_ATOMIC);
+	tcp_transmit_skb(sk, buff, 0, sk_allocation(sk, GFP_ATOMIC));
 }
 
 /* This routine sends a packet with an out of date sequence
@@ -2754,7 +2755,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent)
 	struct sk_buff *skb;
 
 	/* We don't queue it, tcp_transmit_skb() sets ownership. */
-	skb = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC);
+	skb = alloc_skb(MAX_TCP_HEADER, sk_allocation(sk, GFP_ATOMIC));
 	if (skb == NULL)
 		return -1;
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index d1fd287..62bc424 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -597,7 +597,8 @@ static int tcp_v6_md5_do_add(struct sock *sk, const struct in6_addr *peer,
 	} else {
 		/* reallocate new list if current one is full. */
 		if (!tp->md5sig_info) {
-			tp->md5sig_info = kzalloc(sizeof(*tp->md5sig_info), GFP_ATOMIC);
+			tp->md5sig_info = kzalloc(sizeof(*tp->md5sig_info),
+					sk_allocation(sk, GFP_ATOMIC));
 			if (!tp->md5sig_info) {
 				kfree(newkey);
 				return -ENOMEM;
@@ -610,7 +611,8 @@ static int tcp_v6_md5_do_add(struct sock *sk, const struct in6_addr *peer,
 		}
 		if (tp->md5sig_info->alloced6 == tp->md5sig_info->entries6) {
 			keys = kmalloc((sizeof (tp->md5sig_info->keys6[0]) *
-				       (tp->md5sig_info->entries6 + 1)), GFP_ATOMIC);
+				       (tp->md5sig_info->entries6 + 1)),
+				       sk_allocation(sk, GFP_ATOMIC));
 
 			if (!keys) {
 				tcp_free_md5sig_pool();
@@ -734,7 +736,8 @@ static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval,
 		struct tcp_sock *tp = tcp_sk(sk);
 		struct tcp_md5sig_info *p;
 
-		p = kzalloc(sizeof(struct tcp_md5sig_info), GFP_KERNEL);
+		p = kzalloc(sizeof(struct tcp_md5sig_info),
+				   sk_allocation(sk, GFP_KERNEL));
 		if (!p)
 			return -ENOMEM;
 
@@ -1084,6 +1087,7 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb)
 	struct tcphdr *th = tcp_hdr(skb);
 	u32 seq = 0, ack_seq = 0;
 	struct tcp_md5sig_key *key = NULL;
+	gfp_t gfp_mask = GFP_ATOMIC;
 
 	if (th->rst)
 		return;
@@ -1095,6 +1099,8 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb)
 	if (sk)
 		key = tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr);
 #endif
+	if (sk)
+		gfp_mask = sk_allocation(sk, gfp_mask);
 
 	if (th->ack)
 		seq = ntohl(th->ack_seq);
-- 
1.7.3.4

[PATCH 07/14] netvm: Allow the use of __GFP_MEMALLOC by specific sockets

[Mel Gorman]

Allow specific sockets to be tagged SOCK_MEMALLOC and use __GFP_MEMALLOC
for their allocations. These sockets will be able to go below watermarks
and allocate from the emergency reserve. Such sockets are to be used
to service the VM (iow. to swap over). They must be handled kernel side,
exposing such a socket to user-space is a bug.

There is a risk that the reserves be depleted so for now, the administrator is
responsible for increasing min_free_kbytes as necessary to prevent deadlock
for their workloads.

[a.p.zijlstra@chello.nl: Original patches]
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/net/sock.h |    5 ++++-
 net/core/sock.c    |   22 ++++++++++++++++++++++
 2 files changed, 26 insertions(+), 1 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index e89c38f..046bc97 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -554,6 +554,7 @@ enum sock_flags {
 	SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */
 	SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */
 	SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */
+	SOCK_MEMALLOC, /* VM depends on this socket for swapping */
 	SOCK_TIMESTAMPING_TX_HARDWARE,  /* %SOF_TIMESTAMPING_TX_HARDWARE */
 	SOCK_TIMESTAMPING_TX_SOFTWARE,  /* %SOF_TIMESTAMPING_TX_SOFTWARE */
 	SOCK_TIMESTAMPING_RX_HARDWARE,  /* %SOF_TIMESTAMPING_RX_HARDWARE */
@@ -587,7 +588,7 @@ static inline int sock_flag(struct sock *sk, enum sock_flags flag)
 
 static inline gfp_t sk_allocation(struct sock *sk, gfp_t gfp_mask)
 {
-	return gfp_mask;
+	return gfp_mask | (sk->sk_allocation & __GFP_MEMALLOC);
 }
 
 static inline void sk_acceptq_removed(struct sock *sk)
@@ -717,6 +718,8 @@ extern int sk_stream_wait_memory(struct sock *sk, long *timeo_p);
 extern void sk_stream_wait_close(struct sock *sk, long timeo_p);
 extern int sk_stream_error(struct sock *sk, int flags, int err);
 extern void sk_stream_kill_queues(struct sock *sk);
+extern void sk_set_memalloc(struct sock *sk);
+extern void sk_clear_memalloc(struct sock *sk);
 
 extern int sk_wait_data(struct sock *sk, long *timeo);
 
diff --git a/net/core/sock.c b/net/core/sock.c
index 6e81978..c685eda 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -219,6 +219,28 @@ __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
 int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
 EXPORT_SYMBOL(sysctl_optmem_max);
 
+/**
+ * sk_set_memalloc - sets %SOCK_MEMALLOC
+ * @sk: socket to set it on
+ *
+ * Set %SOCK_MEMALLOC on a socket for access to emergency reserves.
+ * It's the responsibility of the admin to adjust min_free_kbytes
+ * to meet the requirements
+ */
+void sk_set_memalloc(struct sock *sk)
+{
+	sock_set_flag(sk, SOCK_MEMALLOC);
+	sk->sk_allocation |= __GFP_MEMALLOC;
+}
+EXPORT_SYMBOL_GPL(sk_set_memalloc);
+
+void sk_clear_memalloc(struct sock *sk)
+{
+	sock_reset_flag(sk, SOCK_MEMALLOC);
+	sk->sk_allocation &= ~__GFP_MEMALLOC;
+}
+EXPORT_SYMBOL_GPL(sk_clear_memalloc);
+
 #if defined(CONFIG_CGROUPS) && !defined(CONFIG_NET_CLS_CGROUP)
 int net_cls_subsys_id = -1;
 EXPORT_SYMBOL_GPL(net_cls_subsys_id);
-- 
1.7.3.4

[PATCH 08/14] netvm: Allow skb allocation to use PFMEMALLOC reserves

[Mel Gorman]

Change the skb allocation API to indicate RX usage and use this to fall back
to the PFMEMALLOC reserve when needed. SKBs allocated from the reserve are
tagged in skb->pfmemalloc. If an SKB is allocated from the reserve and
the socket is later found to be unrelated to page reclaim, the packet is
dropped so that the memory remains available for page reclaim. Network
protocols are expected to recover from this packet loss.

[a.p.zijlstra@chello.nl: Ideas taken from various patches]
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/gfp.h    |    3 ++
 include/linux/skbuff.h |   19 ++++++++--
 include/net/sock.h     |    6 +++
 mm/internal.h          |    3 --
 net/core/filter.c      |    8 ++++
 net/core/skbuff.c      |   95 ++++++++++++++++++++++++++++++++++++++++--------
 net/core/sock.c        |    4 ++
 7 files changed, 116 insertions(+), 22 deletions(-)

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index faefba9..3cc24bb 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -375,6 +375,9 @@ void drain_local_pages(void *dummy);
 
 extern gfp_t gfp_allowed_mask;
 
+/* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */
+bool gfp_pfmemalloc_allowed(gfp_t gfp_mask);
+
 extern void pm_restrict_gfp_mask(void);
 extern void pm_restore_gfp_mask(void);
 
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index c0a4f3a..064d8d4 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -396,6 +396,7 @@ struct sk_buff {
 #ifdef CONFIG_IPV6_NDISC_NODETYPE
 	__u8			ndisc_nodetype:2;
 #endif
+	__u8			pfmemalloc:1;
 	__u8			ooo_okay:1;
 	kmemcheck_bitfield_end(flags2);
 
@@ -434,6 +435,15 @@ struct sk_buff {
 
 #include <asm/system.h>
 
+#define SKB_ALLOC_FCLONE	0x01
+#define SKB_ALLOC_RX		0x02
+
+/* Returns true if the skb was allocated from PFMEMALLOC reserves */
+static inline bool skb_pfmemalloc(struct sk_buff *skb)
+{
+	return unlikely(skb->pfmemalloc);
+}
+
 /*
  * skb might have a dst pointer attached, refcounted or not.
  * _skb_refdst low order bit is set if refcount was _not_ taken
@@ -491,7 +501,7 @@ extern void kfree_skb(struct sk_buff *skb);
 extern void consume_skb(struct sk_buff *skb);
 extern void	       __kfree_skb(struct sk_buff *skb);
 extern struct sk_buff *__alloc_skb(unsigned int size,
-				   gfp_t priority, int fclone, int node);
+				   gfp_t priority, int flags, int node);
 static inline struct sk_buff *alloc_skb(unsigned int size,
 					gfp_t priority)
 {
@@ -501,7 +511,7 @@ static inline struct sk_buff *alloc_skb(unsigned int size,
 static inline struct sk_buff *alloc_skb_fclone(unsigned int size,
 					       gfp_t priority)
 {
-	return __alloc_skb(size, priority, 1, NUMA_NO_NODE);
+	return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, NUMA_NO_NODE);
 }
 
 extern bool skb_recycle_check(struct sk_buff *skb, int skb_size);
@@ -1532,7 +1542,8 @@ static inline void __skb_queue_purge(struct sk_buff_head *list)
 static inline struct sk_buff *__dev_alloc_skb(unsigned int length,
 					      gfp_t gfp_mask)
 {
-	struct sk_buff *skb = alloc_skb(length + NET_SKB_PAD, gfp_mask);
+	struct sk_buff *skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask,
+						SKB_ALLOC_RX, NUMA_NO_NODE);
 	if (likely(skb))
 		skb_reserve(skb, NET_SKB_PAD);
 	return skb;
@@ -1583,7 +1594,7 @@ static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev,
  */
 static inline struct page *__netdev_alloc_page(struct net_device *dev, gfp_t gfp_mask)
 {
-	return alloc_pages_node(NUMA_NO_NODE, gfp_mask, 0);
+	return alloc_pages_node(NUMA_NO_NODE, gfp_mask | __GFP_MEMALLOC, 0);
 }
 
 /**
diff --git a/include/net/sock.h b/include/net/sock.h
index 046bc97..e3aaa88 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -586,6 +586,12 @@ static inline int sock_flag(struct sock *sk, enum sock_flags flag)
 	return test_bit(flag, &sk->sk_flags);
 }
 
+extern atomic_t memalloc_socks;
+static inline int sk_memalloc_socks(void)
+{
+	return atomic_read(&memalloc_socks);
+}
+
 static inline gfp_t sk_allocation(struct sock *sk, gfp_t gfp_mask)
 {
 	return gfp_mask | (sk->sk_allocation & __GFP_MEMALLOC);
diff --git a/mm/internal.h b/mm/internal.h
index a520f3b..d071d380 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -193,9 +193,6 @@ static inline struct page *mem_map_next(struct page *iter,
 #define __paginginit __init
 #endif
 
-/* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */
-bool gfp_pfmemalloc_allowed(gfp_t gfp_mask);
-
 /* Memory initialisation debug and verification */
 enum mminit_level {
 	MMINIT_WARNING,
diff --git a/net/core/filter.c b/net/core/filter.c
index 36f975f..4ccf6f4 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -80,6 +80,14 @@ int sk_filter(struct sock *sk, struct sk_buff *skb)
 	int err;
 	struct sk_filter *filter;
 
+	/*
+	 * If the skb was allocated from pfmemalloc reserves, only
+	 * allow SOCK_MEMALLOC sockets to use it as this socket is
+	 * helping free memory
+	 */
+	if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC))
+		return -ENOMEM;
+
 	err = security_sock_rcv_skb(sk, skb);
 	if (err)
 		return err;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 46cbd28..d930b92 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -147,6 +147,43 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here)
 	BUG();
 }
 
+
+/*
+ * kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells
+ * the caller if emergency pfmemalloc reserves are being used. If it is and
+ * the socket is later found to be SOCK_MEMALLOC then PFMEMALLOC reserves
+ * may be used. Otherwise, the packet data may be discarded until enough
+ * memory is free
+ */
+#define kmalloc_reserve(size, gfp, node, pfmemalloc) \
+	 __kmalloc_reserve(size, gfp, node, _RET_IP_, pfmemalloc)
+void *__kmalloc_reserve(size_t size, gfp_t flags, int node, unsigned long ip,
+			 bool *pfmemalloc)
+{
+	void *obj;
+	bool ret_pfmemalloc = false;
+
+	/*
+	 * Try a regular allocation, when that fails and we're not entitled
+	 * to the reserves, fail.
+	 */
+	obj = kmalloc_node_track_caller(size,
+				flags | __GFP_NOMEMALLOC | __GFP_NOWARN,
+				node);
+	if (obj || !(gfp_pfmemalloc_allowed(flags)))
+		goto out;
+
+	/* Try again but now we are using pfmemalloc reserves */
+	ret_pfmemalloc = true;
+	obj = kmalloc_node_track_caller(size, flags, node);
+
+out:
+	if (pfmemalloc)
+		*pfmemalloc = ret_pfmemalloc;
+
+	return obj;
+}
+
 /* 	Allocate a new skbuff. We do this ourselves so we can fill in a few
  *	'private' fields and also do memory statistics to find all the
  *	[BEEP] leaks.
@@ -157,8 +194,10 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here)
  *	__alloc_skb	-	allocate a network buffer
  *	@size: size to allocate
  *	@gfp_mask: allocation mask
- *	@fclone: allocate from fclone cache instead of head cache
- *		and allocate a cloned (child) skb
+ *	@flags: If SKB_ALLOC_FCLONE is set, allocate from fclone cache
+ *		instead of head cache and allocate a cloned (child) skb.
+ *		If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for
+ *		allocations in case the data is required for writeback
  *	@node: numa node to allocate memory on
  *
  *	Allocate a new &sk_buff. The returned buffer has no headroom and a
@@ -169,14 +208,19 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here)
  *	%GFP_ATOMIC.
  */
 struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
-			    int fclone, int node)
+			    int flags, int node)
 {
 	struct kmem_cache *cache;
 	struct skb_shared_info *shinfo;
 	struct sk_buff *skb;
 	u8 *data;
+	bool pfmemalloc;
+
+	cache = (flags & SKB_ALLOC_FCLONE)
+		? skbuff_fclone_cache : skbuff_head_cache;
 
-	cache = fclone ? skbuff_fclone_cache : skbuff_head_cache;
+	if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX))
+		gfp_mask |= __GFP_MEMALLOC;
 
 	/* Get the HEAD */
 	skb = kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node);
@@ -185,8 +229,8 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 	prefetchw(skb);
 
 	size = SKB_DATA_ALIGN(size);
-	data = kmalloc_node_track_caller(size + sizeof(struct skb_shared_info),
-			gfp_mask, node);
+	data = kmalloc_reserve(size + sizeof(struct skb_shared_info),
+			gfp_mask, node, &pfmemalloc);
 	if (!data)
 		goto nodata;
 	prefetchw(data + size);
@@ -197,6 +241,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 	 * the tail pointer in struct sk_buff!
 	 */
 	memset(skb, 0, offsetof(struct sk_buff, tail));
+	skb->pfmemalloc = pfmemalloc;
 	skb->truesize = size + sizeof(struct sk_buff);
 	atomic_set(&skb->users, 1);
 	skb->head = data;
@@ -213,7 +258,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 	atomic_set(&shinfo->dataref, 1);
 	kmemcheck_annotate_variable(shinfo->destructor_arg);
 
-	if (fclone) {
+	if (flags & SKB_ALLOC_FCLONE) {
 		struct sk_buff *child = skb + 1;
 		atomic_t *fclone_ref = (atomic_t *) (child + 1);
 
@@ -223,6 +268,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 		atomic_set(fclone_ref, 1);
 
 		child->fclone = SKB_FCLONE_UNAVAILABLE;
+		child->pfmemalloc = pfmemalloc;
 	}
 out:
 	return skb;
@@ -251,7 +297,8 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
 {
 	struct sk_buff *skb;
 
-	skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, NUMA_NO_NODE);
+	skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask,
+						SKB_ALLOC_RX, NUMA_NO_NODE);
 	if (likely(skb)) {
 		skb_reserve(skb, NET_SKB_PAD);
 		skb->dev = dev;
@@ -527,6 +574,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 #if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
 	new->ipvs_property	= old->ipvs_property;
 #endif
+	new->pfmemalloc		= old->pfmemalloc;
 	new->protocol		= old->protocol;
 	new->mark		= old->mark;
 	new->skb_iif		= old->skb_iif;
@@ -621,6 +669,9 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
 		n->fclone = SKB_FCLONE_CLONE;
 		atomic_inc(fclone_ref);
 	} else {
+		if (skb_pfmemalloc(skb))
+			gfp_mask |= __GFP_MEMALLOC;
+
 		n = kmem_cache_alloc(skbuff_head_cache, gfp_mask);
 		if (!n)
 			return NULL;
@@ -657,6 +708,13 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 	skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type;
 }
 
+static inline int skb_alloc_rx_flag(const struct sk_buff *skb)
+{
+	if (skb_pfmemalloc((struct sk_buff *)skb))
+		return SKB_ALLOC_RX;
+	return 0;
+}
+
 /**
  *	skb_copy	-	create private copy of an sk_buff
  *	@skb: buffer to copy
@@ -678,7 +736,8 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
 {
 	int headerlen = skb_headroom(skb);
 	unsigned int size = (skb_end_pointer(skb) - skb->head) + skb->data_len;
-	struct sk_buff *n = alloc_skb(size, gfp_mask);
+	struct sk_buff *n = __alloc_skb(size, gfp_mask,
+					skb_alloc_rx_flag(skb), NUMA_NO_NODE);
 
 	if (!n)
 		return NULL;
@@ -712,7 +771,8 @@ EXPORT_SYMBOL(skb_copy);
 struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask)
 {
 	unsigned int size = skb_end_pointer(skb) - skb->head;
-	struct sk_buff *n = alloc_skb(size, gfp_mask);
+	struct sk_buff *n = __alloc_skb(size, gfp_mask,
+					skb_alloc_rx_flag(skb), NUMA_NO_NODE);
 
 	if (!n)
 		goto out;
@@ -803,7 +863,10 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
 		goto adjust_others;
 	}
 
-	data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask);
+	if (skb_pfmemalloc(skb))
+		gfp_mask |= __GFP_MEMALLOC;
+	data = kmalloc_reserve(size + sizeof(struct skb_shared_info), gfp_mask,
+			NUMA_NO_NODE, NULL);
 	if (!data)
 		goto nodata;
 
@@ -904,8 +967,9 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
 	/*
 	 *	Allocate the copy buffer
 	 */
-	struct sk_buff *n = alloc_skb(newheadroom + skb->len + newtailroom,
-				      gfp_mask);
+	struct sk_buff *n = __alloc_skb(newheadroom + skb->len + newtailroom,
+				      gfp_mask, skb_alloc_rx_flag(skb),
+				      NUMA_NO_NODE);
 	int oldheadroom = skb_headroom(skb);
 	int head_copy_len, head_copy_off;
 	int off;
@@ -2552,8 +2616,9 @@ struct sk_buff *skb_segment(struct sk_buff *skb, u32 features)
 			skb_release_head_state(nskb);
 			__skb_push(nskb, doffset);
 		} else {
-			nskb = alloc_skb(hsize + doffset + headroom,
-					 GFP_ATOMIC);
+			nskb = __alloc_skb(hsize + doffset + headroom,
+					 GFP_ATOMIC, skb_alloc_rx_flag(skb),
+					 NUMA_NO_NODE);
 
 			if (unlikely(!nskb))
 				goto err;
diff --git a/net/core/sock.c b/net/core/sock.c
index c685eda..8308609 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -219,6 +219,8 @@ __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
 int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
 EXPORT_SYMBOL(sysctl_optmem_max);
 
+atomic_t memalloc_socks __read_mostly;
+
 /**
  * sk_set_memalloc - sets %SOCK_MEMALLOC
  * @sk: socket to set it on
@@ -231,6 +233,7 @@ void sk_set_memalloc(struct sock *sk)
 {
 	sock_set_flag(sk, SOCK_MEMALLOC);
 	sk->sk_allocation |= __GFP_MEMALLOC;
+	atomic_inc(&memalloc_socks);
 }
 EXPORT_SYMBOL_GPL(sk_set_memalloc);
 
@@ -238,6 +241,7 @@ void sk_clear_memalloc(struct sock *sk)
 {
 	sock_reset_flag(sk, SOCK_MEMALLOC);
 	sk->sk_allocation &= ~__GFP_MEMALLOC;
+	atomic_dec(&memalloc_socks);
 }
 EXPORT_SYMBOL_GPL(sk_clear_memalloc);
 
-- 
1.7.3.4

[PATCH 09/14] netvm: Propagate page->pfmemalloc to skb

[Mel Gorman]

The skb->pfmemalloc flag gets set to true iff during the slab
allocation of data in __alloc_skb that the the PFMEMALLOC reserves
were used. If the packet is fragmented, it is possible that pages
will be allocated from the PFMEMALLOC reserve without propagating
this information to the skb. This patch propagates page->pfmemalloc
from pages allocated for fragments to the skb.

Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/skbuff.h |    2 ++
 1 files changed, 2 insertions(+), 0 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 064d8d4..9f44101 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1124,6 +1124,8 @@ static inline void skb_fill_page_desc(struct sk_buff *skb, int i,
 {
 	skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 
+	if (page->pfmemalloc)
+		skb->pfmemalloc	  = true;
 	frag->page		  = page;
 	frag->page_offset	  = off;
 	frag->size		  = size;
-- 
1.7.3.4

[PATCH 10/14] netvm: Set PF_MEMALLOC as appropriate during SKB processing

[Mel Gorman]

In order to make sure pfmemalloc packets receive all memory needed
to proceed, ensure processing of pfmemalloc SKBs happens under
PF_MEMALLOC. This is limited to a subset of protocols that implement
the special handling of PFMEMALLOC sockets for writing ti swap.
Taps are not allowed to use PF_MEMALLOC as these are expected to
communicate with userspace processes which could be paged out.

[a.p.zijlstra@chello.nl: Ideas taken from various patches]
[jslaby@suse.cz: Lock imbalance fix]
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/net/sock.h |    5 +++++
 net/core/dev.c     |   48 ++++++++++++++++++++++++++++++++++++++++++++----
 net/core/sock.c    |   16 ++++++++++++++++
 3 files changed, 65 insertions(+), 4 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index e3aaa88..e928880 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -668,8 +668,13 @@ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *s
 	return 0;
 }
 
+extern int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb);
+
 static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 {
+	if (skb_pfmemalloc(skb))
+		return __sk_backlog_rcv(sk, skb);
+
 	return sk->sk_backlog_rcv(sk, skb);
 }
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 9c58c1e..5aac965 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3089,6 +3089,23 @@ void netdev_rx_handler_unregister(struct net_device *dev)
 }
 EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister);
 
+/*
+ * Limit the use of PFMEMALLOC reserves to those protocols that implement
+ * the special handling of PFMEMALLOC skbs.
+ */
+static bool skb_pfmemalloc_protocol(struct sk_buff *skb)
+{
+	switch (skb->protocol) {
+	case __constant_htons(ETH_P_ARP):
+	case __constant_htons(ETH_P_IP):
+	case __constant_htons(ETH_P_IPV6):
+	case __constant_htons(ETH_P_8021Q):
+		return true;
+	default:
+		return false;
+	}
+}
+
 static int __netif_receive_skb(struct sk_buff *skb)
 {
 	struct packet_type *ptype, *pt_prev;
@@ -3098,15 +3115,28 @@ static int __netif_receive_skb(struct sk_buff *skb)
 	bool deliver_exact = false;
 	int ret = NET_RX_DROP;
 	__be16 type;
+	unsigned long pflags = current->flags;
 
 	if (!netdev_tstamp_prequeue)
 		net_timestamp_check(skb);
 
 	trace_netif_receive_skb(skb);
 
+	/*
+	 * PFMEMALLOC skbs are special, they should
+	 * - be delivered to SOCK_MEMALLOC sockets only
+	 * - stay away from userspace
+	 * - have bounded memory usage
+	 *
+	 * Use PF_MEMALLOC as this saves us from propagating the allocation
+	 * context down to all allocation sites.
+	 */
+	if (skb_pfmemalloc(skb))
+		current->flags |= PF_MEMALLOC;
+
 	/* if we've gotten here through NAPI, check netpoll */
 	if (netpoll_receive_skb(skb))
-		return NET_RX_DROP;
+		goto out;
 
 	if (!skb->skb_iif)
 		skb->skb_iif = skb->dev->ifindex;
@@ -3137,6 +3167,9 @@ another_round:
 	}
 #endif
 
+	if (skb_pfmemalloc(skb))
+		goto skip_taps;
+
 	list_for_each_entry_rcu(ptype, &ptype_all, list) {
 		if (!ptype->dev || ptype->dev == skb->dev) {
 			if (pt_prev)
@@ -3145,13 +3178,17 @@ another_round:
 		}
 	}
 
+skip_taps:
 #ifdef CONFIG_NET_CLS_ACT
 	skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
 	if (!skb)
-		goto out;
+		goto unlock;
 ncls:
 #endif
 
+	if (skb_pfmemalloc(skb) && !skb_pfmemalloc_protocol(skb))
+		goto drop;
+
 	rx_handler = rcu_dereference(skb->dev->rx_handler);
 	if (rx_handler) {
 		if (pt_prev) {
@@ -3160,7 +3197,7 @@ ncls:
 		}
 		switch (rx_handler(&skb)) {
 		case RX_HANDLER_CONSUMED:
-			goto out;
+			goto unlock;
 		case RX_HANDLER_ANOTHER:
 			goto another_round;
 		case RX_HANDLER_EXACT:
@@ -3202,6 +3239,7 @@ ncls:
 	if (pt_prev) {
 		ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
 	} else {
+drop:
 		atomic_long_inc(&skb->dev->rx_dropped);
 		kfree_skb(skb);
 		/* Jamal, now you will not able to escape explaining
@@ -3210,8 +3248,10 @@ ncls:
 		ret = NET_RX_DROP;
 	}
 
-out:
+unlock:
 	rcu_read_unlock();
+out:
+	tsk_restore_flags(current, pflags, PF_MEMALLOC);
 	return ret;
 }
 
diff --git a/net/core/sock.c b/net/core/sock.c
index 8308609..ac36807 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -245,6 +245,22 @@ void sk_clear_memalloc(struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(sk_clear_memalloc);
 
+int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
+{
+	int ret;
+	unsigned long pflags = current->flags;
+
+	/* these should have been dropped before queueing */
+	BUG_ON(!sock_flag(sk, SOCK_MEMALLOC));
+
+	current->flags |= PF_MEMALLOC;
+	ret = sk->sk_backlog_rcv(sk, skb);
+	tsk_restore_flags(current, pflags, PF_MEMALLOC);
+
+	return ret;
+}
+EXPORT_SYMBOL(__sk_backlog_rcv);
+
 #if defined(CONFIG_CGROUPS) && !defined(CONFIG_NET_CLS_CGROUP)
 int net_cls_subsys_id = -1;
 EXPORT_SYMBOL_GPL(net_cls_subsys_id);
-- 
1.7.3.4

[PATCH 11/14] mm: Micro-optimise slab to avoid a function call

[Mel Gorman]

Getting and putting objects in SLAB currently requires a function call
but the bulk of the work is related to PFMEMALLOC reserves which are
only consumed when network-backed storage is critical. Use an inline
function to determine if the function call is required.

Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 mm/slab.c |   28 ++++++++++++++++++++++++++--
 1 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/mm/slab.c b/mm/slab.c
index fceb656..839721b 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -117,6 +117,8 @@
 #include	<linux/memory.h>
 #include	<linux/prefetch.h>
 
+#include	<net/sock.h>
+
 #include	<asm/cacheflush.h>
 #include	<asm/tlbflush.h>
 #include	<asm/page.h>
@@ -945,7 +947,7 @@ static void check_ac_pfmemalloc(struct kmem_cache *cachep,
 	ac->pfmemalloc = false;
 }
 
-static void *ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac,
+static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac,
 						gfp_t flags, bool force_refill)
 {
 	int i;
@@ -992,7 +994,20 @@ static void *ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac,
 	return objp;
 }
 
-static void ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac,
+static inline void *ac_get_obj(struct kmem_cache *cachep,
+			struct array_cache *ac, gfp_t flags, bool force_refill)
+{
+	void *objp;
+
+	if (unlikely(sk_memalloc_socks()))
+		objp = __ac_get_obj(cachep, ac, flags, force_refill);
+	else
+		objp = ac->entry[--ac->avail];
+
+	return objp;
+}
+
+static void *__ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac,
 								void *objp)
 {
 	struct slab *slabp;
@@ -1005,6 +1020,15 @@ static void ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac,
 			set_obj_pfmemalloc(&objp);
 	}
 
+	return objp;
+}
+
+static inline void ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac,
+								void *objp)
+{
+	if (unlikely(sk_memalloc_socks()))
+		objp = __ac_put_obj(cachep, ac, objp);
+
 	ac->entry[ac->avail++] = objp;
 }
 
-- 
1.7.3.4

[PATCH 12/14] nbd: Set SOCK_MEMALLOC for access to PFMEMALLOC reserves

[Mel Gorman]

Set SOCK_MEMALLOC on the NBD socket to allow access to PFMEMALLOC
reserves so pages backed by NBD, particularly if swap related,
can be cleaned to prevent the machine being deadlocked. It is
still possible that the PFMEMALLOC reserves get depleted resulting
in deadlock but this can be resolved by the administrator by
increasing min_free_kbytes.

Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 drivers/block/nbd.c |    7 ++++++-
 1 files changed, 6 insertions(+), 1 deletions(-)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index f533f33..ca7cd81 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -156,6 +156,7 @@ static int sock_xmit(struct nbd_device *lo, int send, void *buf, int size,
 	struct msghdr msg;
 	struct kvec iov;
 	sigset_t blocked, oldset;
+	unsigned long pflags = current->flags;
 
 	if (unlikely(!sock)) {
 		printk(KERN_ERR "%s: Attempted %s on closed socket in sock_xmit\n",
@@ -168,8 +169,9 @@ static int sock_xmit(struct nbd_device *lo, int send, void *buf, int size,
 	siginitsetinv(&blocked, sigmask(SIGKILL));
 	sigprocmask(SIG_SETMASK, &blocked, &oldset);
 
+	current->flags |= PF_MEMALLOC;
 	do {
-		sock->sk->sk_allocation = GFP_NOIO;
+		sock->sk->sk_allocation = GFP_NOIO | __GFP_MEMALLOC;
 		iov.iov_base = buf;
 		iov.iov_len = size;
 		msg.msg_name = NULL;
@@ -215,6 +217,7 @@ static int sock_xmit(struct nbd_device *lo, int send, void *buf, int size,
 	} while (size > 0);
 
 	sigprocmask(SIG_SETMASK, &oldset, NULL);
+	tsk_restore_flags(current, pflags, PF_MEMALLOC);
 
 	return result;
 }
@@ -405,6 +408,8 @@ static int nbd_do_it(struct nbd_device *lo)
 
 	BUG_ON(lo->magic != LO_MAGIC);
 
+	sk_set_memalloc(lo->sock->sk);
+
 	lo->pid = current->pid;
 	ret = sysfs_create_file(&disk_to_dev(lo->disk)->kobj, &pid_attr.attr);
 	if (ret) {
-- 
1.7.3.4

[PATCH 13/14] mm: Throttle direct reclaimers if PF_MEMALLOC reserves are low and swap is backed by network storage

[Mel Gorman]

If swap is backed by network storage such as NBD, there is a risk that a
large number of reclaimers can hang the system by consuming all
PF_MEMALLOC reserves. To avoid these hangs, the administrator must tune
min_free_kbytes in advance. This patch will throttle direct reclaimers
if half the PF_MEMALLOC reserves are in use as the system is at risk of
hanging.

Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/mmzone.h |    1 +
 mm/page_alloc.c        |    1 +
 mm/vmscan.c            |   54 ++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 56 insertions(+), 0 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index c928dac..5b32906 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -633,6 +633,7 @@ typedef struct pglist_data {
 					     range, including holes */
 	int node_id;
 	wait_queue_head_t kswapd_wait;
+	wait_queue_head_t pfmemalloc_wait;
 	struct task_struct *kswapd;
 	int kswapd_max_order;
 	enum zone_type classzone_idx;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ac779f5..00eea0f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4288,6 +4288,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 	pgdat_resize_init(pgdat);
 	pgdat->nr_zones = 0;
 	init_waitqueue_head(&pgdat->kswapd_wait);
+	init_waitqueue_head(&pgdat->pfmemalloc_wait);
 	pgdat->kswapd_max_order = 0;
 	pgdat_page_cgroup_init(pgdat);
 	
diff --git a/mm/vmscan.c b/mm/vmscan.c
index faa0a08..fe95e4f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2154,6 +2154,45 @@ out:
 	return 0;
 }
 
+static bool pfmemalloc_watermark_ok(pg_data_t *pgdat, int high_zoneidx)
+{
+	struct zone *zone;
+	unsigned long pfmemalloc_reserve = 0;
+	unsigned long free_pages = 0;
+	int i;
+
+	for (i = 0; i <= high_zoneidx; i++) {
+		zone = &pgdat->node_zones[i];
+		pfmemalloc_reserve += min_wmark_pages(zone);
+		free_pages += zone_page_state(zone, NR_FREE_PAGES);
+	}
+
+	return (free_pages > pfmemalloc_reserve / 2) ? true : false;
+}
+
+/*
+ * Throttle direct reclaimers if backing storage is backed by the network
+ * and the PFMEMALLOC reserve for the preferred node is getting dangerously
+ * depleted. kswapd will continue to make progress and wake the processes
+ * when the low watermark is reached
+ */
+static void throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
+					nodemask_t *nodemask)
+{
+	struct zone *zone;
+	int high_zoneidx = gfp_zone(gfp_mask);
+	DEFINE_WAIT(wait);
+
+	/* Check if the pfmemalloc reserves are ok */
+	first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone);
+	if (pfmemalloc_watermark_ok(zone->zone_pgdat, high_zoneidx))
+		return;
+
+	/* Throttle */
+	wait_event_killable(zone->zone_pgdat->pfmemalloc_wait,
+		pfmemalloc_watermark_ok(zone->zone_pgdat, high_zoneidx));
+}
+
 unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 				gfp_t gfp_mask, nodemask_t *nodemask)
 {
@@ -2173,6 +2212,15 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 		.gfp_mask = sc.gfp_mask,
 	};
 
+	throttle_direct_reclaim(gfp_mask, zonelist, nodemask);
+
+	/*
+	 * Do not enter reclaim if fatal signal is pending. 1 is returned so
+	 * that the page allocator does not consider triggering OOM
+	 */
+	if (fatal_signal_pending(current))
+		return 1;
+
 	trace_mm_vmscan_direct_reclaim_begin(order,
 				sc.may_writepage,
 				gfp_mask);
@@ -2541,6 +2589,12 @@ loop_again:
 			}
 
 		}
+
+		/* Wake throttled direct reclaimers if low watermark is met */
+		if (waitqueue_active(&pgdat->pfmemalloc_wait) &&
+				pfmemalloc_watermark_ok(pgdat, MAX_NR_ZONES - 1))
+			wake_up_interruptible(&pgdat->pfmemalloc_wait);
+
 		if (all_zones_ok || (order && pgdat_balanced(pgdat, balanced, *classzone_idx)))
 			break;		/* kswapd: all done */
 		/*
-- 
1.7.3.4

[PATCH 14/14] mm: Account for the number of times direct reclaimers get throttled

[Mel Gorman]

Under significant pressure when writing back to network-backed storage,
direct reclaimers may get throttled. This is expected to be a
short-lived event and the processes get woken up again but processes do
get stalled. This patch counts how many times such stalling occurs. It's
up to the administrator whether to reduce these stalls by increasing
min_free_kbytes.

Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 include/linux/vm_event_item.h |    1 +
 mm/vmscan.c                   |    1 +
 mm/vmstat.c                   |    1 +
 3 files changed, 3 insertions(+), 0 deletions(-)

diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 03b90cdc..652e5f3 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -29,6 +29,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		FOR_ALL_ZONES(PGSTEAL),
 		FOR_ALL_ZONES(PGSCAN_KSWAPD),
 		FOR_ALL_ZONES(PGSCAN_DIRECT),
+		PGSCAN_DIRECT_THROTTLE,
 #ifdef CONFIG_NUMA
 		PGSCAN_ZONE_RECLAIM_FAILED,
 #endif
diff --git a/mm/vmscan.c b/mm/vmscan.c
index fe95e4f..f75a5f2 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2189,6 +2189,7 @@ static void throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
 		return;
 
 	/* Throttle */
+	count_vm_event(PGSCAN_DIRECT_THROTTLE);
 	wait_event_killable(zone->zone_pgdat->pfmemalloc_wait,
 		pfmemalloc_watermark_ok(zone->zone_pgdat, high_zoneidx));
 }
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 20c18b7..0ab4a3d 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -740,6 +740,7 @@ const char * const vmstat_text[] = {
 	TEXTS_FOR_ZONES("pgsteal")
 	TEXTS_FOR_ZONES("pgscan_kswapd")
 	TEXTS_FOR_ZONES("pgscan_direct")
+	"pgscan_direct_throttle",
 
 #ifdef CONFIG_NUMA
 	"zone_reclaim_failed",
-- 
1.7.3.4

Re: [PATCH 01/14] mm: Serialize access to min_free_kbytes

[Andrew Morton]

On Mon, 20 Jun 2011 14:12:07 +0100
Mel Gorman <mgorman@suse.de> wrote:

> There is a race between the min_free_kbytes sysctl, memory hotplug
> and transparent hugepage support enablement.  Memory hotplug uses a
> zonelists_mutex to avoid a race when building zonelists. Reuse it to
> serialise watermark updates.

This patch appears to be a standalone fix, unrelated to the overall
patch series?

How does one trigger the race and what happens when it hits, btw?

Re: [PATCH 00/14] Swap-over-NBD without deadlocking v5

[Andrew Morton]

On Mon, 20 Jun 2011 14:12:06 +0100
Mel Gorman <mgorman@suse.de> wrote:

> Swapping over NBD is something that is technically possible but not
> often advised. While there are number of guides on the internet
> on how to configure it and nbd-client supports a -swap switch to
> "prevent deadlocks", the fact of the matter is a machine using NBD
> for swap can be locked up within minutes if swap is used intensively.
> 
> The problem is that network block devices do not use mempools like
> normal block devices do. As the host cannot control where they receive
> packets from, they cannot reliably work out in advance how much memory
> they might need.
> 
> Some years ago, Peter Ziljstra developed a series of patches that
> supported swap over an NFS that some distributions are carrying in
> their kernels. This patch series borrows very heavily from Peter's work
> to support swapping over NBD (the relatively straight-forward case)
> and uses throttling instead of dynamically resized memory reserves
> so the series is not too unwieldy for review.

I have to say, I look over these patches and my mind wants to turn to
things like puppies.  And ice cream.

There's quite some complexity added here in areas which are already
reliably unreliable and afaik swap-over-NBD is not a thing which a lot
of people want to do.  I can see that swap-over-NFS would be useful to
some people, and the fact that distros are carrying swap-over-NFS
patches has weight.

Do these patches lead on to swap-over-NFS?  If so, how much more
additional complexity are we buying into for that?

Re: [PATCH 01/14] mm: Serialize access to min_free_kbytes

[Mel Gorman]

On Wed, Jul 06, 2011 at 04:44:47PM -0700, Andrew Morton wrote:
> On Mon, 20 Jun 2011 14:12:07 +0100
> Mel Gorman <mgorman@suse.de> wrote:
> 
> > There is a race between the min_free_kbytes sysctl, memory hotplug
> > and transparent hugepage support enablement.  Memory hotplug uses a
> > zonelists_mutex to avoid a race when building zonelists. Reuse it to
> > serialise watermark updates.
> 
> This patch appears to be a standalone fix, unrelated to the overall
> patch series?
> 

Yes. In the original series this would have been a more serious problem
as min_free_kbytes was potentially adjusted more frequently.

> How does one trigger the race and what happens when it hits, btw?

One could trigger the trace by having multiple processes on different
CPUs write to min_free_kbytes. One could add memory hotplug events
to that for extra fun but it is unnecessary to trigger the race.

The consequences are that the value for min_free_kbytes and the zone
watermarks get out of sync. Whether the zone watermarks will be too
high or too low would depend on the timing. For the most part, the
consequence will simply be that the min free level for some zones will
be wrong. A more serious consequence is that totalreserve_pages could
get out of sync and strict no memory overcommit could fail a mmap when
it should have succeeded for the value of min_free_kbytes or suspend
fail because it did not preallocate enough pages.

It's not exactly earth shattering.

-- 
Mel Gorman
SUSE Labs

Re: [PATCH 00/14] Swap-over-NBD without deadlocking v5

[Mel Gorman]

On Wed, Jul 06, 2011 at 04:51:46PM -0700, Andrew Morton wrote:
> On Mon, 20 Jun 2011 14:12:06 +0100
> Mel Gorman <mgorman@suse.de> wrote:
> 
> > Swapping over NBD is something that is technically possible but not
> > often advised. While there are number of guides on the internet
> > on how to configure it and nbd-client supports a -swap switch to
> > "prevent deadlocks", the fact of the matter is a machine using NBD
> > for swap can be locked up within minutes if swap is used intensively.
> > 
> > The problem is that network block devices do not use mempools like
> > normal block devices do. As the host cannot control where they receive
> > packets from, they cannot reliably work out in advance how much memory
> > they might need.
> > 
> > Some years ago, Peter Ziljstra developed a series of patches that
> > supported swap over an NFS that some distributions are carrying in
> > their kernels. This patch series borrows very heavily from Peter's work
> > to support swapping over NBD (the relatively straight-forward case)
> > and uses throttling instead of dynamically resized memory reserves
> > so the series is not too unwieldy for review.
> 
> I have to say, I look over these patches and my mind wants to turn to
> things like puppies.  And ice cream.
> 

People do love puppies and ice cream!

> There's quite some complexity added here in areas which are already
> reliably unreliable and afaik swap-over-NBD is not a thing which a lot
> of people want to do. I can see that swap-over-NFS would be useful to
> some people, and the fact that distros are carrying swap-over-NFS
> patches has weight.
> 
> Do these patches lead on to swap-over-NFS?  If so, how much more
> additional complexity are we buying into for that?

Swap-over-NFS is the primary motivation. As you say, distributions are
carrying this and have been for some time. Based on my asking about the
background, the primary user is clusters of blades that are diskless
or have extremely limited storage with no possibility of expansion (be
it due to physical dimensions or maintenance overhead). They require
an amount of infrequently used swap for their workloads. They are
connected to some sort of SAN that may or may not be running Linux
but that exports NFS so they want to stick a swapfile on it.

Swap-over-NBD is the simplier case that can be used if the SAN
is running Linux. Almost all of the compexity required to support
swap-over-NBD is reused for swap-over-NFS (obviously the NBD-specific
bits are not reused).

Additional complexity is required for swap-over-NFS but affects the
core kernel far less than this series. I do not have a series prepared
but from what's in a distro kernel, supporting NFS requires extending
address_space_operations for swapfile activation/deactivation with
some minor helpers and the bulk of the remaining complexity within
NFS itself.

-- 
Mel Gorman
SUSE Labs

Re: [PATCH 00/14] Swap-over-NBD without deadlocking v5

[Christoph Hellwig]

On Thu, Jul 07, 2011 at 10:47:37AM +0100, Mel Gorman wrote:
> Additional complexity is required for swap-over-NFS but affects the
> core kernel far less than this series. I do not have a series prepared
> but from what's in a distro kernel, supporting NFS requires extending
> address_space_operations for swapfile activation/deactivation with
> some minor helpers and the bulk of the remaining complexity within
> NFS itself.

The biggest addition for swap over NFS is to add proper support for
a filesystem interface to do I/O on random kernel pages instead of
the current nasty bmap hack the swapfile code is using.  Splitting
that work from all the required VM infrastructure should make life
easier for everyone involved and allows merging it independeny as
both bits have other uses case as well.

Re: [PATCH 00/14] Swap-over-NBD without deadlocking v5

[Mel Gorman]

On Thu, Jul 07, 2011 at 08:58:31AM -0400, Christoph Hellwig wrote:
> On Thu, Jul 07, 2011 at 10:47:37AM +0100, Mel Gorman wrote:
> > Additional complexity is required for swap-over-NFS but affects the
> > core kernel far less than this series. I do not have a series prepared
> > but from what's in a distro kernel, supporting NFS requires extending
> > address_space_operations for swapfile activation/deactivation with
> > some minor helpers and the bulk of the remaining complexity within
> > NFS itself.
> 
> The biggest addition for swap over NFS is to add proper support for
> a filesystem interface to do I/O on random kernel pages instead of
> the current nasty bmap hack the swapfile code is using. Splitting
> that work from all the required VM infrastructure should make life
> easier for everyone involved and allows merging it independeny as
> both bits have other uses case as well.
> 

The swap-over-nfs patches allows this possibility. There is a swapon
interface added that could be used by the filesystem to ensure the
underlying blocks are allocated and a swap_out/swap_in interface that
takes a struct file, struct page and writeback_control. This would
be an alternative to bmap being used to record the blocks backing
each extent.

Any objection to the swap-over-NBD stuff going ahead to get part of the
complexity out of the way?

-- 
Mel Gorman
SUSE Labs

Re: [PATCH 00/14] Swap-over-NBD without deadlocking v5

[Christoph Hellwig]

On Fri, Jul 15, 2011 at 03:10:21PM +0100, Mel Gorman wrote:
> Any objection to the swap-over-NBD stuff going ahead to get part of the
> complexity out of the way?

Sure, that's what I was advocating for.  The filesystem interfaces in
the current swap over nbd patches on the other hand are complete crap
and need to be redone, but we've already discussed that a lot of times.