mm, page_alloc: distinguish between being unable to sleep, unwilling to sleep and avoiding waking kswapd

__GFP_WAIT has been used to identify atomic context in callers that hold
spinlocks or are in interrupts.  They are expected to be high priority and
have access one of two watermarks lower than "min" which can be referred
to as the "atomic reserve".  __GFP_HIGH users get access to the first
lower watermark and can be called the "high priority reserve".

Over time, callers had a requirement to not block when fallback options
were available.  Some have abused __GFP_WAIT leading to a situation where
an optimisitic allocation with a fallback option can access atomic
reserves.

This patch uses __GFP_ATOMIC to identify callers that are truely atomic,
cannot sleep and have no alternative.  High priority users continue to use
__GFP_HIGH.  __GFP_DIRECT_RECLAIM identifies callers that can sleep and
are willing to enter direct reclaim.  __GFP_KSWAPD_RECLAIM to identify
callers that want to wake kswapd for background reclaim.  __GFP_WAIT is
redefined as a caller that is willing to enter direct reclaim and wake
kswapd for background reclaim.

This patch then converts a number of sites

o __GFP_ATOMIC is used by callers that are high priority and have memory
  pools for those requests. GFP_ATOMIC uses this flag.

o Callers that have a limited mempool to guarantee forward progress clear
  __GFP_DIRECT_RECLAIM but keep __GFP_KSWAPD_RECLAIM. bio allocations fall
  into this category where kswapd will still be woken but atomic reserves
  are not used as there is a one-entry mempool to guarantee progress.

o Callers that are checking if they are non-blocking should use the
  helper gfpflags_allow_blocking() where possible. This is because
  checking for __GFP_WAIT as was done historically now can trigger false
  positives. Some exceptions like dm-crypt.c exist where the code intent
  is clearer if __GFP_DIRECT_RECLAIM is used instead of the helper due to
  flag manipulations.

o Callers that built their own GFP flags instead of starting with GFP_KERNEL
  and friends now also need to specify __GFP_KSWAPD_RECLAIM.

The first key hazard to watch out for is callers that removed __GFP_WAIT
and was depending on access to atomic reserves for inconspicuous reasons.
In some cases it may be appropriate for them to use __GFP_HIGH.

The second key hazard is callers that assembled their own combination of
GFP flags instead of starting with something like GFP_KERNEL.  They may
now wish to specify __GFP_KSWAPD_RECLAIM.  It's almost certainly harmless
if it's missed in most cases as other activity will wake kswapd.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Vitaly Wool <vitalywool@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 40 insertions, 19 deletions

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 440fca3e7e5d..b56e811b6f7c 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -29,12 +29,13 @@ struct vm_area_struct;
 #define ___GFP_NOMEMALLOC	0x10000u
 #define ___GFP_HARDWALL		0x20000u
 #define ___GFP_THISNODE		0x40000u
-#define ___GFP_WAIT		0x80000u
+#define ___GFP_ATOMIC		0x80000u
 #define ___GFP_NOACCOUNT	0x100000u
 #define ___GFP_NOTRACK		0x200000u
-#define ___GFP_NO_KSWAPD	0x400000u
+#define ___GFP_DIRECT_RECLAIM	0x400000u
 #define ___GFP_OTHER_NODE	0x800000u
 #define ___GFP_WRITE		0x1000000u
+#define ___GFP_KSWAPD_RECLAIM	0x2000000u
 /* If the above are modified, __GFP_BITS_SHIFT may need updating */
 
 /*
@@ -71,7 +72,7 @@ struct vm_area_struct;
  * __GFP_MOVABLE: Flag that this page will be movable by the page migration
  * mechanism or reclaimed
  */
-#define __GFP_WAIT	((__force gfp_t)___GFP_WAIT)	/* Can wait and reschedule? */
+#define __GFP_ATOMIC	((__force gfp_t)___GFP_ATOMIC)  /* Caller cannot wait or reschedule */
 #define __GFP_HIGH	((__force gfp_t)___GFP_HIGH)	/* Should access emergency pools? */
 #define __GFP_IO	((__force gfp_t)___GFP_IO)	/* Can start physical IO? */
 #define __GFP_FS	((__force gfp_t)___GFP_FS)	/* Can call down to low-level FS? */
@@ -94,23 +95,37 @@ struct vm_area_struct;
 #define __GFP_NOACCOUNT	((__force gfp_t)___GFP_NOACCOUNT) /* Don't account to kmemcg */
 #define __GFP_NOTRACK	((__force gfp_t)___GFP_NOTRACK)  /* Don't track with kmemcheck */
 
-#define __GFP_NO_KSWAPD	((__force gfp_t)___GFP_NO_KSWAPD)
 #define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) /* On behalf of other node */
 #define __GFP_WRITE	((__force gfp_t)___GFP_WRITE)	/* Allocator intends to dirty page */
 
 /*
+ * A caller that is willing to wait may enter direct reclaim and will
+ * wake kswapd to reclaim pages in the background until the high
+ * watermark is met. A caller may wish to clear __GFP_DIRECT_RECLAIM to
+ * avoid unnecessary delays when a fallback option is available but
+ * still allow kswapd to reclaim in the background. The kswapd flag
+ * can be cleared when the reclaiming of pages would cause unnecessary
+ * disruption.
+ */
+#define __GFP_WAIT ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM))
+#define __GFP_DIRECT_RECLAIM	((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */
+#define __GFP_KSWAPD_RECLAIM	((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */
+
+/*
  * This may seem redundant, but it's a way of annotating false positives vs.
  * allocations that simply cannot be supported (e.g. page tables).
  */
 #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK)
 
-#define __GFP_BITS_SHIFT 25	/* Room for N __GFP_FOO bits */
+#define __GFP_BITS_SHIFT 26	/* Room for N __GFP_FOO bits */
 #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
 
-/* This equals 0, but use constants in case they ever change */
-#define GFP_NOWAIT	(GFP_ATOMIC & ~__GFP_HIGH)
-/* GFP_ATOMIC means both !wait (__GFP_WAIT not set) and use emergency pool */
-#define GFP_ATOMIC	(__GFP_HIGH)
+/*
+ * GFP_ATOMIC callers can not sleep, need the allocation to succeed.
+ * A lower watermark is applied to allow access to "atomic reserves"
+ */
+#define GFP_ATOMIC	(__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM)
+#define GFP_NOWAIT	(__GFP_KSWAPD_RECLAIM)
 #define GFP_NOIO	(__GFP_WAIT)
 #define GFP_NOFS	(__GFP_WAIT | __GFP_IO)
 #define GFP_KERNEL	(__GFP_WAIT | __GFP_IO | __GFP_FS)
@@ -119,10 +134,10 @@ struct vm_area_struct;
 #define GFP_USER	(__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL)
 #define GFP_HIGHUSER	(GFP_USER | __GFP_HIGHMEM)
 #define GFP_HIGHUSER_MOVABLE	(GFP_HIGHUSER | __GFP_MOVABLE)
-#define GFP_IOFS	(__GFP_IO | __GFP_FS)
-#define GFP_TRANSHUGE	(GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
-			 __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | \
-			 __GFP_NO_KSWAPD)
+#define GFP_IOFS	(__GFP_IO | __GFP_FS | __GFP_KSWAPD_RECLAIM)
+#define GFP_TRANSHUGE	((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
+			 __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) & \
+			 ~__GFP_KSWAPD_RECLAIM)
 
 /* This mask makes up all the page movable related flags */
 #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE)
@@ -164,6 +179,11 @@ static inline int gfpflags_to_migratetype(const gfp_t gfp_flags)
 	return (gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT;
 }
 
+static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags)
+{
+	return gfp_flags & __GFP_DIRECT_RECLAIM;
+}
+
 #ifdef CONFIG_HIGHMEM
 #define OPT_ZONE_HIGHMEM ZONE_HIGHMEM
 #else
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 24f4dfd94c51..4355129fff91 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1224,7 +1224,7 @@ static inline int skb_cloned(const struct sk_buff *skb)
 
 static inline int skb_unclone(struct sk_buff *skb, gfp_t pri)
 {
-	might_sleep_if(pri & __GFP_WAIT);
+	might_sleep_if(gfpflags_allow_blocking(pri));
 
 	if (skb_cloned(skb))
 		return pskb_expand_head(skb, 0, 0, pri);
@@ -1308,7 +1308,7 @@ static inline int skb_shared(const struct sk_buff *skb)
  */
 static inline struct sk_buff *skb_share_check(struct sk_buff *skb, gfp_t pri)
 {
-	might_sleep_if(pri & __GFP_WAIT);
+	might_sleep_if(gfpflags_allow_blocking(pri));
 	if (skb_shared(skb)) {
 		struct sk_buff *nskb = skb_clone(skb, pri);
 
@@ -1344,7 +1344,7 @@ static inline struct sk_buff *skb_share_check(struct sk_buff *skb, gfp_t pri)
 static inline struct sk_buff *skb_unshare(struct sk_buff *skb,
 					  gfp_t pri)
 {
-	might_sleep_if(pri & __GFP_WAIT);
+	might_sleep_if(gfpflags_allow_blocking(pri));
 	if (skb_cloned(skb)) {
 		struct sk_buff *nskb = skb_copy(skb, pri);
 
diff --git a/include/net/sock.h b/include/net/sock.h
index f570e75e3da9..bbf7c2cf15b4 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2041,7 +2041,7 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
  */
 static inline struct page_frag *sk_page_frag(struct sock *sk)
 {
-	if (sk->sk_allocation & __GFP_WAIT)
+	if (gfpflags_allow_blocking(sk->sk_allocation))
 		return &current->task_frag;
 
 	return &sk->sk_frag;
diff --git a/include/trace/events/gfpflags.h b/include/trace/events/gfpflags.h
index d6fd8e5b14b7..dde6bf092c8a 100644
--- a/include/trace/events/gfpflags.h
+++ b/include/trace/events/gfpflags.h
@@ -20,7 +20,7 @@
 	{(unsigned long)GFP_ATOMIC,		"GFP_ATOMIC"},		\
 	{(unsigned long)GFP_NOIO,		"GFP_NOIO"},		\
 	{(unsigned long)__GFP_HIGH,		"GFP_HIGH"},		\
-	{(unsigned long)__GFP_WAIT,		"GFP_WAIT"},		\
+	{(unsigned long)__GFP_ATOMIC,		"GFP_ATOMIC"},		\
 	{(unsigned long)__GFP_IO,		"GFP_IO"},		\
 	{(unsigned long)__GFP_COLD,		"GFP_COLD"},		\
 	{(unsigned long)__GFP_NOWARN,		"GFP_NOWARN"},		\
@@ -36,7 +36,8 @@
 	{(unsigned long)__GFP_RECLAIMABLE,	"GFP_RECLAIMABLE"},	\
 	{(unsigned long)__GFP_MOVABLE,		"GFP_MOVABLE"},		\
 	{(unsigned long)__GFP_NOTRACK,		"GFP_NOTRACK"},		\
-	{(unsigned long)__GFP_NO_KSWAPD,	"GFP_NO_KSWAPD"},	\
+	{(unsigned long)__GFP_DIRECT_RECLAIM,	"GFP_DIRECT_RECLAIM"},	\
+	{(unsigned long)__GFP_KSWAPD_RECLAIM,	"GFP_KSWAPD_RECLAIM"},	\
 	{(unsigned long)__GFP_OTHER_NODE,	"GFP_OTHER_NODE"}	\
 	) : "GFP_NOWAIT"