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
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Subject: [PATCH 13/28] net: packet split receive api
Date: Wed, 20 Feb 2008 15:46:23 +0100 [thread overview]
Message-ID: <20080220150306.945681000@chello.nl> (raw)
In-Reply-To: 20080220144610.548202000@chello.nl
[-- Attachment #1: net-ps_rx.patch --]
[-- Type: text/plain, Size: 9946 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
@@ -4478,12 +4478,8 @@ 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
@@ -4691,7 +4687,7 @@ 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
@@ -846,6 +846,9 @@ 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))
@@ -1339,6 +1342,26 @@ 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);
+
static void skb_drop_list(struct sk_buff **listp)
{
struct sk_buff *list = *listp;
Index: linux-2.6/drivers/net/sky2.c
===================================================================
--- linux-2.6.orig/drivers/net/sky2.c
+++ linux-2.6/drivers/net/sky2.c
@@ -1216,7 +1216,7 @@ 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;
@@ -2088,8 +2088,8 @@ 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;
@@ -2106,15 +2106,11 @@ 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;
}
}
@@ -2141,7 +2137,7 @@ 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
@@ -2356,7 +2356,7 @@ bnx2_alloc_rx_page(struct bnx2 *bp, u16
struct sw_pg *rx_pg = &bp->rx_pg_ring[index];
struct rx_bd *rxbd =
&bp->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;
@@ -2381,7 +2381,7 @@ bnx2_free_rx_page(struct bnx2 *bp, u16 i
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;
}
@@ -2705,9 +2705,7 @@ 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
@@ -252,7 +252,7 @@ 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;
@@ -714,11 +714,8 @@ 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
@@ -3506,13 +3506,9 @@ 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;
@@ -3614,7 +3610,7 @@ 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
@@ -367,7 +367,7 @@ 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;
@@ -490,13 +490,9 @@ 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>
next prev parent reply other threads:[~2008-02-20 14:46 UTC|newest]
Thread overview: 73+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-02-20 14:46 [PATCH 00/28] Swap over NFS -v16 Peter Zijlstra
2008-02-20 14:46 ` [PATCH 01/28] mm: gfp_to_alloc_flags() Peter Zijlstra
2008-02-20 14:46 ` [PATCH 02/28] mm: tag reseve pages Peter Zijlstra
2008-02-20 14:46 ` [PATCH 03/28] mm: slb: add knowledge of reserve pages Peter Zijlstra
2008-02-20 14:46 ` [PATCH 04/28] mm: kmem_estimate_pages() Peter Zijlstra
2008-02-23 8:05 ` Andrew Morton
2008-02-20 14:46 ` [PATCH 05/28] mm: allow PF_MEMALLOC from softirq context Peter Zijlstra
2008-02-23 8:05 ` Andrew Morton
2008-02-20 14:46 ` [PATCH 06/28] mm: serialize access to min_free_kbytes Peter Zijlstra
2008-02-20 14:46 ` [PATCH 07/28] mm: emergency pool Peter Zijlstra
2008-02-23 8:05 ` Andrew Morton
2008-02-20 14:46 ` [PATCH 08/28] mm: system wide ALLOC_NO_WATERMARK Peter Zijlstra
2008-02-23 8:05 ` Andrew Morton
2008-02-20 14:46 ` [PATCH 09/28] mm: __GFP_MEMALLOC Peter Zijlstra
2008-02-23 8:06 ` Andrew Morton
2008-02-20 14:46 ` [PATCH 10/28] mm: memory reserve management Peter Zijlstra
2008-02-23 8:06 ` Andrew Morton
2008-02-20 14:46 ` [PATCH 11/28] selinux: tag avc cache alloc as non-critical Peter Zijlstra
2008-02-20 14:46 ` [PATCH 12/28] net: wrap sk->sk_backlog_rcv() Peter Zijlstra
2008-02-20 14:46 ` Peter Zijlstra [this message]
2008-02-20 14:46 ` [PATCH 14/28] net: sk_allocation() - concentrate socket related allocations Peter Zijlstra
2008-02-20 14:46 ` [PATCH 15/28] netvm: network reserve infrastructure Peter Zijlstra
2008-02-23 8:06 ` Andrew Morton
2008-02-24 6:52 ` Mike Snitzer
2008-02-20 14:46 ` [PATCH 16/28] netvm: INET reserves Peter Zijlstra
2008-02-20 14:46 ` [PATCH 17/28] netvm: hook skb allocation to reserves Peter Zijlstra
2008-02-23 8:06 ` Andrew Morton
2008-02-20 14:46 ` [PATCH 18/28] netvm: filter emergency skbs Peter Zijlstra
2008-02-20 14:46 ` [PATCH 19/28] netvm: prevent a stream specific deadlock Peter Zijlstra
2008-02-20 14:46 ` [PATCH 20/28] netfilter: NF_QUEUE vs emergency skbs Peter Zijlstra
2008-02-20 14:46 ` [PATCH 21/28] netvm: skb processing Peter Zijlstra
2008-02-20 14:46 ` [PATCH 22/28] mm: add support for non block device backed swap files Peter Zijlstra
2008-02-20 16:30 ` Randy Dunlap
2008-02-20 16:46 ` Peter Zijlstra
2008-02-26 12:45 ` Miklos Szeredi
2008-02-26 12:58 ` Peter Zijlstra
2008-02-20 14:46 ` [PATCH 23/28] mm: methods for teaching filesystems about PG_swapcache pages Peter Zijlstra
2008-02-20 14:46 ` [PATCH 24/28] nfs: remove mempools Peter Zijlstra
2008-02-20 14:46 ` [PATCH 25/28] nfs: teach the NFS client how to treat PG_swapcache pages Peter Zijlstra
2008-02-20 14:46 ` [PATCH 26/28] nfs: disable data cache revalidation for swapfiles Peter Zijlstra
2008-02-20 14:46 ` [PATCH 27/28] nfs: enable swap on NFS Peter Zijlstra
2008-02-20 14:46 ` [PATCH 28/28] nfs: fix various memory recursions possible with swap over NFS Peter Zijlstra
2008-02-23 8:06 ` [PATCH 00/28] Swap over NFS -v16 Andrew Morton
2008-02-26 6:03 ` Neil Brown
2008-02-26 10:50 ` Peter Zijlstra
2008-02-26 12:00 ` Peter Zijlstra
2008-02-26 15:29 ` Miklos Szeredi
2008-02-26 15:41 ` Peter Zijlstra
2008-02-26 15:43 ` Peter Zijlstra
2008-02-26 15:47 ` Miklos Szeredi
2008-02-26 17:56 ` Andrew Morton
2008-02-27 5:51 ` Neil Brown
2008-02-27 7:58 ` Peter Zijlstra
2008-02-27 8:05 ` Pekka Enberg
2008-02-27 8:14 ` Peter Zijlstra
2008-02-27 8:33 ` Peter Zijlstra
2008-02-27 8:43 ` Pekka J Enberg
2008-02-29 11:51 ` Peter Zijlstra
2008-02-29 11:58 ` Pekka Enberg
2008-02-29 12:18 ` Peter Zijlstra
2008-02-29 12:29 ` Pekka Enberg
2008-02-29 1:29 ` Neil Brown
2008-02-29 10:21 ` Peter Zijlstra
2008-03-02 22:18 ` Neil Brown
2008-03-02 23:33 ` Peter Zijlstra
2008-03-03 23:41 ` Neil Brown
2008-03-04 10:28 ` Peter Zijlstra
[not found] ` <1837 <1204626509.6241.39.camel@lappy>
2008-03-07 3:33 ` Neil Brown
2008-03-07 11:17 ` Peter Zijlstra
2008-03-07 11:55 ` Peter Zijlstra
2008-03-10 5:15 ` Neil Brown
2008-03-10 9:17 ` Peter Zijlstra
2008-03-14 5:22 ` Neil Brown
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=20080220150306.945681000@chello.nl \
--to=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=netdev@vger.kernel.org \
--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;
as well as URLs for NNTP newsgroup(s).