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>

1 files changed, 99 insertions, 25 deletions

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 368f65c15e4f..fe00d1208167 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -145,6 +145,43 @@ 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.
@@ -155,8 +192,10 @@ 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
@@ -167,14 +206,19 @@ 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 = fclone ? skbuff_fclone_cache : skbuff_head_cache;
+	cache = (flags & SKB_ALLOC_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);
@@ -189,7 +233,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 	 */
 	size = SKB_DATA_ALIGN(size);
 	size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-	data = kmalloc_node_track_caller(size, gfp_mask, node);
+	data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc);
 	if (!data)
 		goto nodata;
 	/* kmalloc(size) might give us more room than requested.
@@ -207,6 +251,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 	memset(skb, 0, offsetof(struct sk_buff, tail));
 	/* Account for allocated memory : skb + skb->head */
 	skb->truesize = SKB_TRUESIZE(size);
+	skb->pfmemalloc = pfmemalloc;
 	atomic_set(&skb->users, 1);
 	skb->head = data;
 	skb->data = data;
@@ -222,7 +267,7 @@ 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);
 
@@ -232,6 +277,7 @@ 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;
@@ -302,14 +348,7 @@ static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache);
 
 #define NETDEV_PAGECNT_BIAS (PAGE_SIZE / SMP_CACHE_BYTES)
 
-/**
- * netdev_alloc_frag - allocate a page fragment
- * @fragsz: fragment size
- *
- * Allocates a frag from a page for receive buffer.
- * Uses GFP_ATOMIC allocations.
- */
-void *netdev_alloc_frag(unsigned int fragsz)
+static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
 {
 	struct netdev_alloc_cache *nc;
 	void *data = NULL;
@@ -319,7 +358,7 @@ void *netdev_alloc_frag(unsigned int fragsz)
 	nc = &__get_cpu_var(netdev_alloc_cache);
 	if (unlikely(!nc->page)) {
 refill:
-		nc->page = alloc_page(GFP_ATOMIC | __GFP_COLD);
+		nc->page = alloc_page(gfp_mask);
 		if (unlikely(!nc->page))
 			goto end;
 recycle:
@@ -343,6 +382,18 @@ end:
 	local_irq_restore(flags);
 	return data;
 }
+
+/**
+ * netdev_alloc_frag - allocate a page fragment
+ * @fragsz: fragment size
+ *
+ * Allocates a frag from a page for receive buffer.
+ * Uses GFP_ATOMIC allocations.
+ */
+void *netdev_alloc_frag(unsigned int fragsz)
+{
+	return __netdev_alloc_frag(fragsz, GFP_ATOMIC | __GFP_COLD);
+}
 EXPORT_SYMBOL(netdev_alloc_frag);
 
 /**
@@ -366,7 +417,12 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
 			      SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
 	if (fragsz <= PAGE_SIZE && !(gfp_mask & (__GFP_WAIT | GFP_DMA))) {
-		void *data = netdev_alloc_frag(fragsz);
+		void *data;
+
+		if (sk_memalloc_socks())
+			gfp_mask |= __GFP_MEMALLOC;
+
+		data = __netdev_alloc_frag(fragsz, gfp_mask);
 
 		if (likely(data)) {
 			skb = build_skb(data, fragsz);
@@ -374,7 +430,8 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
 				put_page(virt_to_head_page(data));
 		}
 	} else {
-		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);
@@ -656,6 +713,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 #if IS_ENABLED(CONFIG_IP_VS)
 	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;
@@ -814,6 +872,9 @@ 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;
@@ -850,6 +911,13 @@ 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(skb))
+		return SKB_ALLOC_RX;
+	return 0;
+}
+
 /**
  *	skb_copy	-	create private copy of an sk_buff
  *	@skb: buffer to copy
@@ -871,7 +939,8 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
 {
 	int headerlen = skb_headroom(skb);
 	unsigned int size = skb_end_offset(skb) + 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;
@@ -906,7 +975,8 @@ EXPORT_SYMBOL(skb_copy);
 struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask)
 {
 	unsigned int size = skb_headlen(skb) + headroom;
-	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;
@@ -979,8 +1049,10 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
 
 	size = SKB_DATA_ALIGN(size);
 
-	data = kmalloc(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
-		       gfp_mask);
+	if (skb_pfmemalloc(skb))
+		gfp_mask |= __GFP_MEMALLOC;
+	data = kmalloc_reserve(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
+			       gfp_mask, NUMA_NO_NODE, NULL);
 	if (!data)
 		goto nodata;
 	size = SKB_WITH_OVERHEAD(ksize(data));
@@ -1092,8 +1164,9 @@ 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;
@@ -2775,8 +2848,9 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t 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;