linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: Linus Torvalds <torvalds@linux-foundation.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	netdev@vger.kernel.org, trond.myklebust@fys.uio.no,
	Daniel Lezcano <dlezcano@fr.ibm.com>,
	Pekka Enberg <penberg@cs.helsinki.fi>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Neil Brown <neilb@suse.de>
Subject: [PATCH 15/30] net: packet split receive api
Date: Thu, 24 Jul 2008 16:00:57 +0200	[thread overview]
Message-ID: <20080724141530.344513717@chello.nl> (raw)
In-Reply-To: <20080724140042.408642539@chello.nl>

[-- Attachment #1: net-ps_rx.patch --]
[-- Type: text/plain, Size: 9952 bytes --]

Add some packet-split receive hooks.

For one this allows to do NUMA node affine page allocs. Later on these hooks
will be extended to do emergency reserve allocations for fragments.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 drivers/net/bnx2.c             |    8 +++-----
 drivers/net/e1000/e1000_main.c |    8 ++------
 drivers/net/e1000e/netdev.c    |    7 ++-----
 drivers/net/igb/igb_main.c     |    8 ++------
 drivers/net/ixgbe/ixgbe_main.c |   10 +++-------
 drivers/net/sky2.c             |   16 ++++++----------
 include/linux/skbuff.h         |   23 +++++++++++++++++++++++
 net/core/skbuff.c              |   20 ++++++++++++++++++++
 8 files changed, 61 insertions(+), 39 deletions(-)

Index: linux-2.6/drivers/net/e1000/e1000_main.c
===================================================================
--- linux-2.6.orig/drivers/net/e1000/e1000_main.c
+++ linux-2.6/drivers/net/e1000/e1000_main.c
@@ -4492,12 +4492,8 @@ e1000_clean_rx_irq_ps(struct e1000_adapt
 			pci_unmap_page(pdev, ps_page_dma->ps_page_dma[j],
 					PAGE_SIZE, PCI_DMA_FROMDEVICE);
 			ps_page_dma->ps_page_dma[j] = 0;
-			skb_fill_page_desc(skb, j, ps_page->ps_page[j], 0,
-			                   length);
+			skb_add_rx_frag(skb, j, ps_page->ps_page[j], 0, length);
 			ps_page->ps_page[j] = NULL;
-			skb->len += length;
-			skb->data_len += length;
-			skb->truesize += length;
 		}
 
 		/* strip the ethernet crc, problem is we're using pages now so
@@ -4705,7 +4701,7 @@ e1000_alloc_rx_buffers_ps(struct e1000_a
 			if (j < adapter->rx_ps_pages) {
 				if (likely(!ps_page->ps_page[j])) {
 					ps_page->ps_page[j] =
-						alloc_page(GFP_ATOMIC);
+						netdev_alloc_page(netdev);
 					if (unlikely(!ps_page->ps_page[j])) {
 						adapter->alloc_rx_buff_failed++;
 						goto no_buffers;
Index: linux-2.6/include/linux/skbuff.h
===================================================================
--- linux-2.6.orig/include/linux/skbuff.h
+++ linux-2.6/include/linux/skbuff.h
@@ -824,6 +824,9 @@ static inline void skb_fill_page_desc(st
 	skb_shinfo(skb)->nr_frags = i + 1;
 }
 
+extern void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page,
+			    int off, int size);
+
 #define SKB_PAGE_ASSERT(skb) 	BUG_ON(skb_shinfo(skb)->nr_frags)
 #define SKB_FRAG_ASSERT(skb) 	BUG_ON(skb_shinfo(skb)->frag_list)
 #define SKB_LINEAR_ASSERT(skb)  BUG_ON(skb_is_nonlinear(skb))
@@ -1238,6 +1241,26 @@ static inline struct sk_buff *netdev_all
 	return __netdev_alloc_skb(dev, length, GFP_ATOMIC);
 }
 
+extern struct page *__netdev_alloc_page(struct net_device *dev, gfp_t gfp_mask);
+
+/**
+ *	netdev_alloc_page - allocate a page for ps-rx on a specific device
+ *	@dev: network device to receive on
+ *
+ * 	Allocate a new page node local to the specified device.
+ *
+ * 	%NULL is returned if there is no free memory.
+ */
+static inline struct page *netdev_alloc_page(struct net_device *dev)
+{
+	return __netdev_alloc_page(dev, GFP_ATOMIC);
+}
+
+static inline void netdev_free_page(struct net_device *dev, struct page *page)
+{
+	__free_page(page);
+}
+
 /**
  *	skb_clone_writable - is the header of a clone writable
  *	@skb: buffer to check
Index: linux-2.6/net/core/skbuff.c
===================================================================
--- linux-2.6.orig/net/core/skbuff.c
+++ linux-2.6/net/core/skbuff.c
@@ -263,6 +263,26 @@ struct sk_buff *__netdev_alloc_skb(struc
 	return skb;
 }
 
+struct page *__netdev_alloc_page(struct net_device *dev, gfp_t gfp_mask)
+{
+	int node = dev->dev.parent ? dev_to_node(dev->dev.parent) : -1;
+	struct page *page;
+
+	page = alloc_pages_node(node, gfp_mask, 0);
+	return page;
+}
+EXPORT_SYMBOL(__netdev_alloc_page);
+
+void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
+		int size)
+{
+	skb_fill_page_desc(skb, i, page, off, size);
+	skb->len += size;
+	skb->data_len += size;
+	skb->truesize += size;
+}
+EXPORT_SYMBOL(skb_add_rx_frag);
+
 /**
  *	dev_alloc_skb - allocate an skbuff for receiving
  *	@length: length to allocate
Index: linux-2.6/drivers/net/sky2.c
===================================================================
--- linux-2.6.orig/drivers/net/sky2.c
+++ linux-2.6/drivers/net/sky2.c
@@ -1343,7 +1343,7 @@ static struct sk_buff *sky2_rx_alloc(str
 	}
 
 	for (i = 0; i < sky2->rx_nfrags; i++) {
-		struct page *page = alloc_page(GFP_ATOMIC);
+		struct page *page = netdev_alloc_page(sky2->netdev);
 
 		if (!page)
 			goto free_partial;
@@ -2217,8 +2217,8 @@ static struct sk_buff *receive_copy(stru
 }
 
 /* Adjust length of skb with fragments to match received data */
-static void skb_put_frags(struct sk_buff *skb, unsigned int hdr_space,
-			  unsigned int length)
+static void skb_put_frags(struct sky2_port *sky2, struct sk_buff *skb,
+			  unsigned int hdr_space, unsigned int length)
 {
 	int i, num_frags;
 	unsigned int size;
@@ -2235,15 +2235,11 @@ static void skb_put_frags(struct sk_buff
 
 		if (length == 0) {
 			/* don't need this page */
-			__free_page(frag->page);
+			netdev_free_page(sky2->netdev, frag->page);
 			--skb_shinfo(skb)->nr_frags;
 		} else {
 			size = min(length, (unsigned) PAGE_SIZE);
-
-			frag->size = size;
-			skb->data_len += size;
-			skb->truesize += size;
-			skb->len += size;
+			skb_add_rx_frag(skb, i, frag->page, 0, size);
 			length -= size;
 		}
 	}
@@ -2270,7 +2266,7 @@ static struct sk_buff *receive_new(struc
 	sky2_rx_map_skb(sky2->hw->pdev, re, hdr_space);
 
 	if (skb_shinfo(skb)->nr_frags)
-		skb_put_frags(skb, hdr_space, length);
+		skb_put_frags(sky2, skb, hdr_space, length);
 	else
 		skb_put(skb, length);
 	return skb;
Index: linux-2.6/drivers/net/bnx2.c
===================================================================
--- linux-2.6.orig/drivers/net/bnx2.c
+++ linux-2.6/drivers/net/bnx2.c
@@ -2466,7 +2466,7 @@ bnx2_alloc_rx_page(struct bnx2 *bp, stru
 	struct sw_pg *rx_pg = &rxr->rx_pg_ring[index];
 	struct rx_bd *rxbd =
 		&rxr->rx_pg_desc_ring[RX_RING(index)][RX_IDX(index)];
-	struct page *page = alloc_page(GFP_ATOMIC);
+	struct page *page = netdev_alloc_page(bp->dev);
 
 	if (!page)
 		return -ENOMEM;
@@ -2491,7 +2491,7 @@ bnx2_free_rx_page(struct bnx2 *bp, struc
 	pci_unmap_page(bp->pdev, pci_unmap_addr(rx_pg, mapping), PAGE_SIZE,
 		       PCI_DMA_FROMDEVICE);
 
-	__free_page(page);
+	netdev_free_page(bp->dev, page);
 	rx_pg->page = NULL;
 }
 
@@ -2816,9 +2816,7 @@ bnx2_rx_skb(struct bnx2 *bp, struct bnx2
 			}
 
 			frag_size -= frag_len;
-			skb->data_len += frag_len;
-			skb->truesize += frag_len;
-			skb->len += frag_len;
+			skb_add_rx_frag(skb, i, rx_pg->page, 0, frag_len);
 
 			pg_prod = NEXT_RX_BD(pg_prod);
 			pg_cons = RX_PG_RING_IDX(NEXT_RX_BD(pg_cons));
Index: linux-2.6/drivers/net/e1000e/netdev.c
===================================================================
--- linux-2.6.orig/drivers/net/e1000e/netdev.c
+++ linux-2.6/drivers/net/e1000e/netdev.c
@@ -257,7 +257,7 @@ static void e1000_alloc_rx_buffers_ps(st
 				continue;
 			}
 			if (!ps_page->page) {
-				ps_page->page = alloc_page(GFP_ATOMIC);
+				ps_page->page = netdev_alloc_page(netdev);
 				if (!ps_page->page) {
 					adapter->alloc_rx_buff_failed++;
 					goto no_buffers;
@@ -816,11 +816,8 @@ static bool e1000_clean_rx_irq_ps(struct
 			pci_unmap_page(pdev, ps_page->dma, PAGE_SIZE,
 				       PCI_DMA_FROMDEVICE);
 			ps_page->dma = 0;
-			skb_fill_page_desc(skb, j, ps_page->page, 0, length);
+			skb_add_rx_frag(skb, j, ps_page->page, 0, length);
 			ps_page->page = NULL;
-			skb->len += length;
-			skb->data_len += length;
-			skb->truesize += length;
 		}
 
 copydone:
Index: linux-2.6/drivers/net/igb/igb_main.c
===================================================================
--- linux-2.6.orig/drivers/net/igb/igb_main.c
+++ linux-2.6/drivers/net/igb/igb_main.c
@@ -3526,13 +3526,9 @@ static bool igb_clean_rx_irq_adv(struct 
 			pci_unmap_page(pdev, buffer_info->page_dma,
 				PAGE_SIZE, PCI_DMA_FROMDEVICE);
 			buffer_info->page_dma = 0;
-			skb_fill_page_desc(skb, j, buffer_info->page,
-						0, length);
+			skb_add_rx_frag(skb, j, buffer_info->page, 0, length);
 			buffer_info->page = NULL;
 
-			skb->len += length;
-			skb->data_len += length;
-			skb->truesize += length;
 			rx_desc->wb.upper.status_error = 0;
 			if (staterr & E1000_RXD_STAT_EOP)
 				break;
@@ -3634,7 +3630,7 @@ static void igb_alloc_rx_buffers_adv(str
 		rx_desc = E1000_RX_DESC_ADV(*rx_ring, i);
 
 		if (adapter->rx_ps_hdr_size && !buffer_info->page) {
-			buffer_info->page = alloc_page(GFP_ATOMIC);
+			buffer_info->page = netdev_alloc_page(netdev);
 			if (!buffer_info->page) {
 				adapter->alloc_rx_buff_failed++;
 				goto no_buffers;
Index: linux-2.6/drivers/net/ixgbe/ixgbe_main.c
===================================================================
--- linux-2.6.orig/drivers/net/ixgbe/ixgbe_main.c
+++ linux-2.6/drivers/net/ixgbe/ixgbe_main.c
@@ -486,7 +486,7 @@ static void ixgbe_alloc_rx_buffers(struc
 
 		if (!rx_buffer_info->page &&
 				(adapter->flags & IXGBE_FLAG_RX_PS_ENABLED)) {
-			rx_buffer_info->page = alloc_page(GFP_ATOMIC);
+			rx_buffer_info->page = netdev_alloc_page(netdev);
 			if (!rx_buffer_info->page) {
 				adapter->alloc_rx_page_failed++;
 				goto no_buffers;
@@ -607,13 +607,9 @@ static bool ixgbe_clean_rx_irq(struct ix
 			pci_unmap_page(pdev, rx_buffer_info->page_dma,
 				       PAGE_SIZE, PCI_DMA_FROMDEVICE);
 			rx_buffer_info->page_dma = 0;
-			skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags,
-					   rx_buffer_info->page, 0, upper_len);
+			skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+					rx_buffer_info->page, 0, upper_len);
 			rx_buffer_info->page = NULL;
-
-			skb->len += upper_len;
-			skb->data_len += upper_len;
-			skb->truesize += upper_len;
 		}
 
 		i++;

-- 

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  parent reply	other threads:[~2008-07-24 14:00 UTC|newest]

Thread overview: 74+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-07-24 14:00 [PATCH 00/30] Swap over NFS -v18 Peter Zijlstra
2008-07-24 14:00 ` [PATCH 01/30] swap over network documentation Peter Zijlstra, Neil Brown
2008-07-24 14:00 ` [PATCH 02/30] mm: gfp_to_alloc_flags() Peter Zijlstra
2008-08-12  5:01   ` Neil Brown
2008-08-12  7:33     ` Peter Zijlstra
2008-08-12  9:33       ` Neil Brown
2008-07-24 14:00 ` [PATCH 03/30] mm: tag reseve pages Peter Zijlstra
2008-07-24 14:00 ` [PATCH 04/30] mm: slub: trivial cleanups Peter Zijlstra
2008-07-28  9:43   ` Pekka Enberg
2008-07-28 10:19     ` Peter Zijlstra
2008-07-30 13:59       ` Christoph Lameter
2008-07-30 14:13         ` Peter Zijlstra
2008-07-29 22:15   ` Pekka Enberg
2008-07-24 14:00 ` [PATCH 05/30] mm: slb: add knowledge of reserve pages Peter Zijlstra
2008-08-12  5:35   ` Neil Brown
2008-08-12  7:22     ` Peter Zijlstra
2008-08-12  9:35       ` Neil Brown
2008-08-12 10:23         ` Peter Zijlstra
2008-07-24 14:00 ` [PATCH 06/30] mm: kmem_alloc_estimate() Peter Zijlstra
2008-07-30 12:21   ` Pekka Enberg
2008-07-30 13:31     ` Peter Zijlstra
2008-07-30 20:02       ` Christoph Lameter
2008-07-24 14:00 ` [PATCH 07/30] mm: allow PF_MEMALLOC from softirq context Peter Zijlstra
2008-07-24 14:00 ` [PATCH 08/30] mm: serialize access to min_free_kbytes Peter Zijlstra
2008-07-30 12:36   ` Pekka Enberg
2008-07-24 14:00 ` [PATCH 09/30] mm: emergency pool Peter Zijlstra
2008-07-24 14:00 ` [PATCH 10/30] mm: system wide ALLOC_NO_WATERMARK Peter Zijlstra
2008-07-24 14:00 ` [PATCH 11/30] mm: __GFP_MEMALLOC Peter Zijlstra
2008-07-25  9:29   ` KOSAKI Motohiro
2008-07-25  9:35     ` Peter Zijlstra
2008-07-25  9:39       ` KOSAKI Motohiro
2008-07-24 14:00 ` [PATCH 12/30] mm: memory reserve management Peter Zijlstra
2008-07-28 10:06   ` Pekka Enberg
2008-07-28 10:17     ` Peter Zijlstra
2008-07-28 10:29       ` Pekka Enberg
2008-07-28 10:39         ` Peter Zijlstra
2008-07-28 10:41           ` Pekka Enberg
2008-07-28 16:59           ` Matt Mackall
2008-07-28 17:13             ` Peter Zijlstra
2008-07-28 16:49     ` Matt Mackall
2008-07-28 17:13       ` Peter Zijlstra
2008-08-12  6:23   ` Neil Brown
2008-08-12  8:10     ` Peter Zijlstra
2008-08-12  7:46   ` Neil Brown
2008-08-12  8:12     ` Peter Zijlstra
2008-07-24 14:00 ` [PATCH 13/30] selinux: tag avc cache alloc as non-critical Peter Zijlstra
2008-07-24 14:00 ` [PATCH 14/30] net: wrap sk->sk_backlog_rcv() Peter Zijlstra
2008-07-24 14:00 ` Peter Zijlstra [this message]
2008-07-24 14:00 ` [PATCH 16/30] net: sk_allocation() - concentrate socket related allocations Peter Zijlstra
2008-07-24 14:00 ` [PATCH 17/30] netvm: network reserve infrastructure Peter Zijlstra
2008-07-24 14:01 ` [PATCH 18/30] netvm: INET reserves Peter Zijlstra
2008-10-01 11:38   ` Daniel Lezcano
2008-10-01 18:56     ` Peter Zijlstra
2008-07-24 14:01 ` [PATCH 19/30] netvm: hook skb allocation to reserves Peter Zijlstra
2008-07-24 14:01 ` [PATCH 20/30] netvm: filter emergency skbs Peter Zijlstra
2008-07-24 14:01 ` [PATCH 21/30] netvm: prevent a stream specific deadlock Peter Zijlstra
2008-07-24 14:01 ` [PATCH 22/30] netfilter: NF_QUEUE vs emergency skbs Peter Zijlstra
2008-07-24 14:01 ` [PATCH 23/30] netvm: skb processing Peter Zijlstra
2008-07-24 14:01 ` [PATCH 24/30] mm: add support for non block device backed swap files Peter Zijlstra
2008-07-24 14:01 ` [PATCH 25/30] mm: methods for teaching filesystems about PG_swapcache pages Peter Zijlstra
2008-07-24 14:01 ` [PATCH 26/30] nfs: remove mempools Peter Zijlstra
2008-07-24 14:46   ` Nick Piggin
2008-07-24 14:53     ` Peter Zijlstra
2008-07-24 14:01 ` [PATCH 27/30] nfs: teach the NFS client how to treat PG_swapcache pages Peter Zijlstra
2008-07-24 14:01 ` [PATCH 28/30] nfs: disable data cache revalidation for swapfiles Peter Zijlstra
2008-07-24 14:01 ` [PATCH 29/30] nfs: enable swap on NFS Peter Zijlstra
2008-07-24 14:01 ` [PATCH 30/30] nfs: fix various memory recursions possible with swap over NFS Peter Zijlstra
2008-07-25 10:46   ` KOSAKI Motohiro
2008-07-25 10:57     ` Peter Zijlstra
2008-07-25 11:15       ` KOSAKI Motohiro
2008-07-25 11:19         ` Peter Zijlstra
2008-09-30 12:41 ` [PATCH 00/30] Swap over NFS -v18 Peter Zijlstra
2008-09-30 15:46   ` Daniel Lezcano
  -- strict thread matches above, loose matches on Subject: below --
2008-03-20 20:10 [PATCH 00/30] Swap over NFS -v17 Peter Zijlstra
2008-03-20 20:10 ` [PATCH 15/30] net: packet split receive api Peter Zijlstra

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20080724141530.344513717@chello.nl \
    --to=a.p.zijlstra@chello.nl \
    --cc=akpm@linux-foundation.org \
    --cc=dlezcano@fr.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=neilb@suse.de \
    --cc=netdev@vger.kernel.org \
    --cc=penberg@cs.helsinki.fi \
    --cc=torvalds@linux-foundation.org \
    --cc=trond.myklebust@fys.uio.no \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox