[PATCH 00/17] Swap-over-NBD without deadlocking V10

@@ -4976,14 +4976,7 @@ 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;

@@ -5038,6 +5031,20 @@ 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

@@ -2043,8 +2043,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 
 		page = get_page_from_freelist(gfp_mask, nodemask,
 				order, zonelist, high_zoneidx,
-				alloc_flags, preferred_zone,
-				migratetype);
+				alloc_flags & ~ALLOC_NO_WATERMARKS,
+				preferred_zone, migratetype);
 		if (page) {
 			preferred_zone->compact_considered = 0;
 			preferred_zone->compact_defer_shift = 0;

@@ -2124,8 +2124,8 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
 retry:
 	page = get_page_from_freelist(gfp_mask, nodemask, order,
 					zonelist, high_zoneidx,
-					alloc_flags, preferred_zone,
-					migratetype);
+					alloc_flags & ~ALLOC_NO_WATERMARKS,
+					preferred_zone, migratetype);
 
 	/*
 	 * If an allocation failed after direct reclaim, it could be because

@@ -2296,8 +2296,17 @@ rebalance:
 		page = __alloc_pages_high_priority(gfp_mask, order,
 				zonelist, high_zoneidx, nodemask,
 				preferred_zone, migratetype);
-		if (page)
+		if (page) {
+			/*
+			 * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was
+			 * necessary to allocate the page. 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 = true;
 			goto got_pg;
+		}
 	}
 
 	/* Atomic allocations - we can't balance anything */

@@ -2414,14 +2423,6 @@ nopage:
 	warn_alloc_failed(gfp_mask, order, NULL);
 	return page;
 got_pg:
-	/*
-	 * page->pfmemalloc is set when the caller had PFMEMALLOC set, is
-	 * been OOM killed or specified __GFP_MEMALLOC. The expectation is
-	 * that the caller is taking steps that will free more memory. The
-	 * caller should avoid the page being used for !PFMEMALLOC purposes.
-	 */
-	page->pfmemalloc = !!(alloc_flags & ALLOC_NO_WATERMARKS);
-
 	if (kmemcheck_enabled)
 		kmemcheck_pagealloc_alloc(page, order, gfp_mask);
 

@@ -2293,6 +2293,13 @@ 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);

@@ -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);
 

@@ -465,6 +465,7 @@ 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;

@@ -504,6 +505,15 @@ 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(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

@@ -561,7 +571,7 @@ 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);
 extern struct sk_buff *build_skb(void *data);
 static inline struct sk_buff *alloc_skb(unsigned int size,
 					gfp_t priority)

@@ -572,7 +582,7 @@ 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);

@@ -1679,7 +1689,8 @@ 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;

@@ -645,6 +645,12 @@ 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);

@@ -239,9 +239,6 @@ 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,

@@ -82,6 +82,14 @@ 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;

@@ -146,6 +146,43 @@ 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.

@@ -156,8 +193,10 @@ 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

@@ -168,14 +207,19 @@ 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);

@@ -190,7 +234,7 @@ 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.

@@ -208,6 +252,7 @@ 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;

@@ -223,7 +268,7 @@ 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);
 

@@ -233,6 +278,7 @@ 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;

@@ -310,7 +356,8 @@ 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;

@@ -605,6 +652,7 @@ 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;

@@ -763,6 +811,9 @@ 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;

@@ -799,6 +850,13 @@ 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

@@ -820,7 +878,8 @@ 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;

@@ -855,7 +914,8 @@ 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;

@@ -952,8 +1012,10 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
 		goto adjust_others;
 	}
 
-	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));

@@ -1062,8 +1124,9 @@ 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;

@@ -2729,8 +2792,9 @@ 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;

@@ -266,6 +266,8 @@ __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

@@ -278,6 +280,7 @@ 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);
 

@@ -285,6 +288,7 @@ 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);
 

@@ -1229,6 +1229,17 @@ static inline void __skb_fill_page_desc(struct sk_buff *skb, int i,
 {
 	skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 
+	/*
+	 * Propagate page->pfmemalloc to the skb if we can. The problem is
+	 * that not all callers have unique ownership of the page. If
+	 * pfmemalloc is set, we check the mapping as a mapping implies
+	 * page->index is set (index and pfmemalloc share space).
+	 * If it's a valid mapping, we cannot use page->pfmemalloc but we
+	 * do not lose pfmemalloc information as the pages would not be
+	 * allocated using __GFP_MEMALLOC.
+	 */
+	if (page->pfmemalloc && !page->mapping)
+		skb->pfmemalloc	= true;
 	frag->page.p		  = page;
 	frag->page_offset	  = off;
 	skb_frag_size_set(frag, size);

@@ -528,7 +528,7 @@ static unsigned int refill_fl(struct adapter *adap, struct sge_fl *q, int n,
 #endif
 
 	while (n--) {
-		pg = alloc_page(gfp);
+		pg = __netdev_alloc_page(gfp, NULL);
 		if (unlikely(!pg)) {
 			q->alloc_failed++;
 			break;

@@ -653,7 +653,7 @@ static unsigned int refill_fl(struct adapter *adapter, struct sge_fl *fl,
 
 alloc_small_pages:
 	while (n--) {
-		page = alloc_page(gfp | __GFP_NOWARN | __GFP_COLD);
+		page = __netdev_alloc_page(gfp | __GFP_NOWARN, NULL);
 		if (unlikely(!page)) {
 			fl->alloc_failed++;
 			break;

@@ -6229,7 +6229,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
 		return true;
 
 	if (!page) {
-		page = alloc_page(GFP_ATOMIC | __GFP_COLD);
+		page = __netdev_alloc_page(GFP_ATOMIC, bi->skb);
 		bi->page = page;
 		if (unlikely(!page)) {
 			rx_ring->rx_stats.alloc_failed++;

@@ -1126,7 +1126,7 @@ static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring,
 
 	/* alloc new page for storage */
 	if (likely(!page)) {
-		page = alloc_pages(GFP_ATOMIC | __GFP_COLD,
+		page = __netdev_alloc_pages(GFP_ATOMIC, bi->skb,
 				   ixgbe_rx_pg_order(rx_ring));
 		if (unlikely(!page)) {
 			rx_ring->rx_stats.alloc_rx_page_failed++;

@@ -369,7 +369,7 @@ static void ixgbevf_alloc_rx_buffers(struct ixgbevf_adapter *adapter,
 		if (!bi->page_dma &&
 		    (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED)) {
 			if (!bi->page) {
-				bi->page = alloc_page(GFP_ATOMIC | __GFP_COLD);
+				bi->page = __netdev_alloc_page(GFP_ATOMIC, NULL);
 				if (!bi->page) {
 					adapter->alloc_rx_page_failed++;
 					goto no_buffers;

@@ -403,6 +403,7 @@ static void ixgbevf_alloc_rx_buffers(struct ixgbevf_adapter *adapter,
 			 */
 			skb_reserve(skb, NET_IP_ALIGN);
 
+			propagate_pfmemalloc_skb(bi->page_dma, skb);
 			bi->skb = skb;
 		}
 		if (!bi->dma) {

@@ -130,7 +130,7 @@ static int rx_submit(struct usbpn_dev *pnd, struct urb *req, gfp_t gfp_flags)
 	struct page *page;
 	int err;
 
-	page = alloc_page(gfp_flags);
+	page = __netdev_alloc_page(gfp_flags | __GFP_NOMEMALLOC, NULL);
 	if (!page)
 		return -ENOMEM;
 

@@ -301,7 +301,7 @@ pn_rx_submit(struct f_phonet *fp, struct usb_request *req, gfp_t gfp_flags)
 	struct page *page;
 	int err;
 
-	page = alloc_page(gfp_flags);
+	page = __netdev_alloc_page(gfp_flags | __GFP_NOMEMALLOC, NULL);
 	if (!page)
 		return -ENOMEM;
 

@@ -1747,6 +1747,61 @@ static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev,
 	return __netdev_alloc_skb_ip_align(dev, length, GFP_ATOMIC);
 }
 
+/*
+ *	__netdev_alloc_page - allocate a page for ps-rx on a specific device
+ *	@gfp_mask: alloc_pages_node mask. Set __GFP_NOMEMALLOC if not for network packet RX
+ *	@skb: skb to set pfmemalloc on if __GFP_MEMALLOC is used
+ *	@order: size of the allocation
+ *
+ * 	Allocate a new page. dev currently unused.
+ *
+ * 	%NULL is returned if there is no free memory.
+*/
+static inline struct page *__netdev_alloc_pages(gfp_t gfp_mask,
+						struct sk_buff *skb,
+						unsigned int order)
+{
+	struct page *page;
+
+	gfp_mask |= __GFP_COLD;
+
+	if (!(gfp_mask & __GFP_NOMEMALLOC))
+		gfp_mask |= __GFP_MEMALLOC;
+
+	page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, order);
+	if (skb && page && page->pfmemalloc)
+		skb->pfmemalloc = true;
+
+	return page;
+}
+
+/**
+ *	__netdev_alloc_page - allocate a page for ps-rx on a specific device
+ *	@gfp_mask: alloc_pages_node mask. Set __GFP_NOMEMALLOC if not for network packet RX
+ *	@skb: skb to set pfmemalloc on if __GFP_MEMALLOC is used
+ *
+ * 	Allocate a new page. dev currently unused.
+ *
+ * 	%NULL is returned if there is no free memory.
+ */
+static inline struct page *__netdev_alloc_page(gfp_t gfp_mask,
+						struct sk_buff *skb)
+{
+	return __netdev_alloc_pages(gfp_mask, skb, 0);
+}
+
+/**
+ *	propagate_pfmemalloc_skb - Propagate pfmemalloc if skb is allocated after RX page
+ *	@page: The page that was allocated from netdev_alloc_page
+ *	@skb: The skb that may need pfmemalloc set
+ */
+static inline void propagate_pfmemalloc_skb(struct page *page,
+						struct sk_buff *skb)
+{
+	if (page && page->pfmemalloc)
+		skb->pfmemalloc = true;
+}
+
 /**
  * skb_frag_page - retrieve the page refered to by a paged fragment
  * @frag: the paged fragment

@@ -729,8 +729,13 @@ 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);
 }
 

@@ -3173,6 +3173,23 @@ 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;

@@ -3182,14 +3199,27 @@ 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;
 
 	net_timestamp_check(!netdev_tstamp_prequeue, 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;

@@ -3210,7 +3240,7 @@ another_round:
 	if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
 		skb = vlan_untag(skb);
 		if (unlikely(!skb))
-			goto out;
+			goto unlock;
 	}
 
 #ifdef CONFIG_NET_CLS_ACT

@@ -3220,6 +3250,9 @@ 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)

@@ -3228,13 +3261,17 @@ 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 (vlan_tx_tag_present(skb)) {
 		if (pt_prev) {

@@ -3244,7 +3281,7 @@ ncls:
 		if (vlan_do_receive(&skb, !rx_handler))
 			goto another_round;
 		else if (unlikely(!skb))
-			goto out;
+			goto unlock;
 	}
 
 	if (rx_handler) {

@@ -3254,7 +3291,7 @@ ncls:
 		}
 		switch (rx_handler(&skb)) {
 		case RX_HANDLER_CONSUMED:
-			goto out;
+			goto unlock;
 		case RX_HANDLER_ANOTHER:
 			goto another_round;
 		case RX_HANDLER_EXACT:

@@ -3284,6 +3321,7 @@ 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

@@ -3292,8 +3330,10 @@ ncls:
 		ret = NET_RX_DROP;
 	}
 
-out:
+unlock:
 	rcu_read_unlock();
+out:
+	tsk_restore_flags(current, pflags, PF_MEMALLOC);
 	return ret;
 }
 

@@ -292,6 +292,22 @@ 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)
 #if !defined(CONFIG_NET_CLS_CGROUP)
 int net_cls_subsys_id = -1;

@@ -30,6 +30,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		FOR_ALL_ZONES(PGSTEAL_DIRECT),
 		FOR_ALL_ZONES(PGSCAN_KSWAPD),
 		FOR_ALL_ZONES(PGSCAN_DIRECT),
+		PGSCAN_DIRECT_THROTTLE,
 #ifdef CONFIG_NUMA
 		PGSCAN_ZONE_RECLAIM_FAILED,
 #endif

@@ -2486,6 +2486,9 @@ static void throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
 	if (pfmemalloc_watermark_ok(pgdat))
 		return;
 
+	/* Account for the throttling */
+	count_vm_event(PGSCAN_DIRECT_THROTTLE);
+
 	/*
 	 * If the caller cannot enter the filesystem, it's possible that it
 	 * is due to the caller holding an FS lock or performing a journal

@@ -742,6 +742,7 @@ const char * const vmstat_text[] = {
 	TEXTS_FOR_ZONES("pgsteal_direct")
 	TEXTS_FOR_ZONES("pgscan_kswapd")
 	TEXTS_FOR_ZONES("pgscan_direct")
+	"pgscan_direct_throttle",
 
 #ifdef CONFIG_NUMA
 	"zone_reclaim_failed",

@@ -663,6 +663,7 @@ 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;

@@ -4326,6 +4326,7 @@ 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);
 	

@@ -2431,6 +2431,80 @@ out:
 	return 0;
 }
 
+static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
+{
+	struct zone *zone;
+	unsigned long pfmemalloc_reserve = 0;
+	unsigned long free_pages = 0;
+	int i;
+	bool wmark_ok;
+
+	for (i = 0; i <= ZONE_NORMAL; i++) {
+		zone = &pgdat->node_zones[i];
+		pfmemalloc_reserve += min_wmark_pages(zone);
+		free_pages += zone_page_state(zone, NR_FREE_PAGES);
+	}
+
+	wmark_ok = free_pages > pfmemalloc_reserve / 2;
+
+	/* kswapd must be awake if processes are being throttled */
+	if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
+		pgdat->classzone_idx = min(pgdat->classzone_idx,
+						(enum zone_type)ZONE_NORMAL);
+		wake_up_interruptible(&pgdat->kswapd_wait);
+	}
+
+	return wmark_ok;
+}
+
+/*
+ * 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);
+	pg_data_t *pgdat;
+
+	/*
+	 * Kernel threads should not be throttled as they may be indirectly
+	 * responsible for cleaning pages necessary for reclaim to make forward
+	 * progress. kjournald for example may enter direct reclaim while
+	 * committing a transaction where throttling it could forcing other
+	 * processes to block on log_wait_commit().
+	 */
+	if (current->flags & PF_KTHREAD)
+		return;
+
+	/* Check if the pfmemalloc reserves are ok */
+	first_zones_zonelist(zonelist, high_zoneidx, NULL, &zone);
+	pgdat = zone->zone_pgdat;
+	if (pfmemalloc_watermark_ok(pgdat))
+		return;
+
+	/*
+	 * If the caller cannot enter the filesystem, it's possible that it
+	 * is due to the caller holding an FS lock or performing a journal
+	 * transaction in the case of a filesystem like ext[3|4]. In this case,
+	 * it is not safe to block on pfmemalloc_wait as kswapd could be
+	 * blocked waiting on the same lock. Instead, throttle for up to a
+	 * second before continuing.
+	 */
+	if (!(gfp_mask & __GFP_FS)) {
+		wait_event_interruptible_timeout(pgdat->pfmemalloc_wait,
+			pfmemalloc_watermark_ok(pgdat), HZ);
+		return;
+	}
+
+	/* Throttle until kswapd wakes the process */
+	wait_event_killable(zone->zone_pgdat->pfmemalloc_wait,
+		pfmemalloc_watermark_ok(pgdat));
+}
+
 unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 				gfp_t gfp_mask, nodemask_t *nodemask)
 {