From: Mel Gorman <mgorman@suse.de>
Date: Thu, 13 Oct 2011 11:04:56 +0100
Subject: [PATCH] netvm: Propagate page->pfmemalloc from netdev_alloc_page to skb
References: Swap over NFS (fate#304949, bnc#718352)
Patch-mainline: no

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 expanding the netdev_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 propagate_pfmemalloc_skb() 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.

Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 drivers/net/cxgb4/sge.c            |    2 +-
 drivers/net/cxgb4vf/sge.c          |    2 +-
 drivers/net/igb/igb_main.c         |    1 +
 drivers/net/ixgbe/ixgbe_main.c     |    2 +-
 drivers/net/ixgbevf/ixgbevf_main.c |    1 +
 drivers/net/usb/cdc-phonet.c       |    2 +-
 drivers/usb/gadget/f_phonet.c      |    2 +-
 include/linux/skbuff.h             |   37 +++++++++++++++++++++++++++++------
 8 files changed, 37 insertions(+), 12 deletions(-)

diff --git a/drivers/net/cxgb4/sge.c b/drivers/net/cxgb4/sge.c
index 56adf44..ca78d77 100644
--- a/drivers/net/cxgb4/sge.c
+++ b/drivers/net/cxgb4/sge.c
@@ -527,7 +527,7 @@ static unsigned int refill_fl(struct adapter *adap, struct sge_fl *q, int n,
 #endif
 
 	while (n--) {
-		pg = __netdev_alloc_page(adap->port[0], gfp);
+		pg = __netdev_alloc_page(adap->port[0], gfp, NULL);
 		if (unlikely(!pg)) {
 			q->alloc_failed++;
 			break;
diff --git a/drivers/net/cxgb4vf/sge.c b/drivers/net/cxgb4vf/sge.c
index 5fd75fd..97e6cc0 100644
--- a/drivers/net/cxgb4vf/sge.c
+++ b/drivers/net/cxgb4vf/sge.c
@@ -654,7 +654,7 @@ static unsigned int refill_fl(struct adapter *adapter, struct sge_fl *fl,
 alloc_small_pages:
 	while (n--) {
 		page = __netdev_alloc_page(adapter->port[0],
-					   gfp | __GFP_NOWARN);
+					   gfp | __GFP_NOWARN, NULL);
 		if (unlikely(!page)) {
 			fl->alloc_failed++;
 			break;
diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index fd57787..06d1e2a 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -5944,7 +5944,7 @@ void igb_alloc_rx_buffers_adv(struct igb_ring *rx_ring, int cleaned_count)
 
 		if ((bufsz < IGB_RXBUFFER_1024) && !buffer_info->page_dma) {
 			if (!buffer_info->page) {
-				buffer_info->page = netdev_alloc_page(netdev);
+				buffer_info->page = netdev_alloc_page(netdev, NULL);
 				if (unlikely(!buffer_info->page)) {
 					u64_stats_update_begin(&rx_ring->rx_syncp);
 					rx_ring->rx_stats.alloc_failed++;
@@ -5980,6 +5980,7 @@ void igb_alloc_rx_buffers_adv(struct igb_ring *rx_ring, int cleaned_count)
 				goto no_buffers;
 			}
 
+			propagate_pfmemalloc_skb(buffer_info->page, skb);
 			buffer_info->skb = skb;
 		}
 		if (!buffer_info->dma) {
diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index 3464d4f..7d36c85 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -1240,7 +1240,7 @@ void ixgbe_alloc_rx_buffers(struct ixgbe_ring *rx_ring, u16 cleaned_count)
 
 		if (ring_is_ps_enabled(rx_ring)) {
 			if (!bi->page) {
-				bi->page = netdev_alloc_page(rx_ring->netdev);
+				bi->page = netdev_alloc_page(rx_ring->netdev, skb);
 				if (!bi->page) {
 					rx_ring->rx_stats.alloc_rx_page_failed++;
 					goto no_buffers;
diff --git a/drivers/net/ixgbevf/ixgbevf_main.c b/drivers/net/ixgbevf/ixgbevf_main.c
index 28d3cb2..2f8b488 100644
--- a/drivers/net/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ixgbevf/ixgbevf_main.c
@@ -364,7 +364,7 @@ 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 = netdev_alloc_page(adapter->netdev);
+				bi->page = netdev_alloc_page(adapter->netdev, NULL);
 				if (!bi->page) {
 					adapter->alloc_rx_page_failed++;
 					goto no_buffers;
@@ -398,6 +398,7 @@ 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) {
diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c
index f967913..fce1289 100644
--- a/drivers/net/usb/cdc-phonet.c
+++ b/drivers/net/usb/cdc-phonet.c
@@ -129,7 +129,7 @@ static int rx_submit(struct usbpn_dev *pnd, struct urb *req, gfp_t gfp_flags)
 	struct page *page;
 	int err;
 
-	page = __netdev_alloc_page(dev, gfp_flags);
+	page = __netdev_alloc_page(dev, gfp_flags | __GFP_NOMEMALLOC, NULL);
 	if (!page)
 		return -ENOMEM;
 
diff --git a/drivers/usb/gadget/f_phonet.c b/drivers/usb/gadget/f_phonet.c
index 5e14950..b38f3c4 100644
--- a/drivers/usb/gadget/f_phonet.c
+++ b/drivers/usb/gadget/f_phonet.c
@@ -311,7 +311,7 @@ pn_rx_submit(struct f_phonet *fp, struct usb_request *req, gfp_t gfp_flags)
 	struct page *page;
 	int err;
 
-	page = __netdev_alloc_page(dev, gfp_flags);
+	page = __netdev_alloc_page(dev, gfp_flags | __GFP_NOMEMALLOC, NULL);
 	if (!page)
 		return -ENOMEM;
 
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 9f44101..c4dd520 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1588,28 +1586,53 @@ static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev,
 /**
  *	__netdev_alloc_page - allocate a page for ps-rx on a specific device
  *	@dev: network device to receive on
- *	@gfp_mask: alloc_pages_node mask
+ *	@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(struct net_device *dev, gfp_t gfp_mask)
+static inline struct page *__netdev_alloc_page(struct net_device *dev,
+					gfp_t gfp_mask, struct sk_buff *skb)
 {
-	return alloc_pages_node(NUMA_NO_NODE, gfp_mask | __GFP_MEMALLOC, 0);
+	struct page *page;
+
+	if (!(gfp_mask & __GFP_NOMEMALLOC))
+		gfp_mask |= __GFP_MEMALLOC;
+
+	page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, 0);
+	if (skb && page->pfmemalloc)
+		skb->pfmemalloc = true;
+
+	return page;
+}
+
+/**
+ *	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->pfmemalloc)
+		skb->pfmemalloc = true;
 }
 
 /**
  *	netdev_alloc_page - allocate a page for ps-rx on a specific device
  *	@dev: network device to receive on
+ *	@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(struct net_device *dev)
+static inline struct page *netdev_alloc_page(struct net_device *dev,
+					struct sk_buff *skb)
 {
-	return __netdev_alloc_page(dev, GFP_ATOMIC);
+	return __netdev_alloc_page(dev, GFP_ATOMIC, skb);
 }
 
 static inline void netdev_free_page(struct net_device *dev, struct page *page)