netvm: allow skb allocation to use PFMEMALLOC reserves

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]
[davem@davemloft.net: Use static branches, coding style corrections]
[sebastian@breakpoint.cc: Avoid unnecessary cast, fix !CONFIG_NET build]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: David S. Miller <davem@davemloft.net>
Cc: Neil Brown <neilb@suse.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 30 insertions, 2 deletions

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index cbd7400e5862..4883f393f50a 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -385,6 +385,9 @@ 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 d205c4be7f5b..0336f02e3667 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -462,6 +462,7 @@ struct sk_buff {
 #ifdef CONFIG_IPV6_NDISC_NODETYPE
 	__u8			ndisc_nodetype:2;
 #endif
+	__u8			pfmemalloc:1;
 	__u8			ooo_okay:1;
 	__u8			l4_rxhash:1;
 	__u8			wifi_acked_valid:1;
@@ -502,6 +503,15 @@ struct sk_buff {
 #include <linux/slab.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(const 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
@@ -565,7 +575,7 @@ extern bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 			     bool *fragstolen, int *delta_truesize);
 
 extern struct sk_buff *__alloc_skb(unsigned int size,
-				   gfp_t priority, int fclone, int node);
+				   gfp_t priority, int flags, int node);
 extern struct sk_buff *build_skb(void *data, unsigned int frag_size);
 static inline struct sk_buff *alloc_skb(unsigned int size,
 					gfp_t priority)
@@ -576,7 +586,7 @@ 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 void skb_recycle(struct sk_buff *skb);
diff --git a/include/net/sock.h b/include/net/sock.h
index bfa7d20e6646..81198632ac2a 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -659,6 +659,21 @@ static inline bool sock_flag(const struct sock *sk, enum sock_flags flag)
 	return test_bit(flag, &sk->sk_flags);
 }
 
+#ifdef CONFIG_NET
+extern struct static_key memalloc_socks;
+static inline int sk_memalloc_socks(void)
+{
+	return static_key_false(&memalloc_socks);
+}
+#else
+
+static inline int sk_memalloc_socks(void)
+{
+	return 0;
+}
+
+#endif
+
 static inline gfp_t sk_gfp_atomic(struct sock *sk, gfp_t gfp_mask)
 {
 	return GFP_ATOMIC | (sk->sk_allocation & __GFP_MEMALLOC);