netvm: propagate page->pfmemalloc from skb_alloc_page to skb

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
page splitting is used, 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.

It works by reintroducing and expanding the skb_alloc_page() API to take
an skb.  If the page was allocated from pfmemalloc reserves, it is
automatically copied.  If the driver allocates the page before the skb, it
should call skb_propagate_pfmemalloc() after the skb is allocated to
ensure the flag is copied properly.

Failure to do so is not critical.  The resulting driver may perform slower
if it is used for swap-over-NBD or swap-over-NFS but it should not result
in failure.

[davem@davemloft.net: API rename and consistency]
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>

drivers/net/ethernet/chelsio/cxgb4/sge.c

@@ -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 = __skb_alloc_page(gfp, NULL);
 		if (unlikely(!pg)) {
 			q->alloc_failed++;
 			break;

drivers/net/ethernet/chelsio/cxgb4vf/sge.c

@@ -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 = __skb_alloc_page(gfp | __GFP_NOWARN, NULL);
 		if (unlikely(!page)) {
 			fl->alloc_failed++;
 			break;

drivers/net/ethernet/intel/igb/igb_main.c

@@ -6235,7 +6235,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
 		return true;
 
 	if (!page) {
-		page = alloc_page(GFP_ATOMIC | __GFP_COLD);
+		page = __skb_alloc_page(GFP_ATOMIC, bi->skb);
 		bi->page = page;
 		if (unlikely(!page)) {
 			rx_ring->rx_stats.alloc_failed++;

drivers/net/ethernet/intel/ixgbe/ixgbe_main.c

@@ -1141,8 +1141,8 @@ 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 | __GFP_COMP,
-				   ixgbe_rx_pg_order(rx_ring));
+		page = __skb_alloc_pages(GFP_ATOMIC | __GFP_COLD | __GFP_COMP,
+					 bi->skb, ixgbe_rx_pg_order(rx_ring));
 		if (unlikely(!page)) {
 			rx_ring->rx_stats.alloc_rx_page_failed++;
 			return false;

drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c

@@ -352,7 +352,6 @@ static void ixgbevf_alloc_rx_buffers(struct ixgbevf_adapter *adapter,
 				adapter->alloc_rx_buff_failed++;
 				goto no_buffers;
 			}
-
 			bi->skb = skb;
 		}
 		if (!bi->dma) {

drivers/net/usb/cdc-phonet.c

@@ -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 = __skb_alloc_page(gfp_flags | __GFP_NOMEMALLOC, NULL);
 	if (!page)
 		return -ENOMEM;
 

drivers/usb/gadget/f_phonet.c

@@ -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 = __skb_alloc_page(gfp_flags | __GFP_NOMEMALLOC, NULL);
 	if (!page)
 		return -ENOMEM;
 

include/linux/skbuff.h

@@ -1774,6 +1774,61 @@ static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev,
 	return __netdev_alloc_skb_ip_align(dev, length, GFP_ATOMIC);
 }
 
+/*
+ *	__skb_alloc_page - allocate pages for ps-rx on a skb and preserve pfmemalloc data
+ *	@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.
+ *
+ * 	%NULL is returned if there is no free memory.
+*/
+static inline struct page *__skb_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;
+}
+
+/**
+ *	__skb_alloc_page - allocate a page for ps-rx for a given skb and preserve pfmemalloc data
+ *	@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.
+ *
+ * 	%NULL is returned if there is no free memory.
+ */
+static inline struct page *__skb_alloc_page(gfp_t gfp_mask,
+					     struct sk_buff *skb)
+{
+	return __skb_alloc_pages(gfp_mask, skb, 0);
+}
+
+/**
+ *	skb_propagate_pfmemalloc - Propagate pfmemalloc if skb is allocated after RX page
+ *	@page: The page that was allocated from skb_alloc_page
+ *	@skb: The skb that may need pfmemalloc set
+ */
+static inline void skb_propagate_pfmemalloc(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