summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
authorAlexander Duyck <alexander.h.duyck@intel.com>2012-07-12 14:23:50 (GMT)
committerDavid S. Miller <davem@davemloft.net>2012-07-13 12:48:36 (GMT)
commit540eb7bf0bbedb65277d68ab89ae43cdec3fd6ba (patch)
tree2217ac3c443baa30d63a02f321b61d762065dbdc /net/core
parent391e5c22f5f4e55817f8ba18a08ea717ed2d4a1f (diff)
downloadlinux-540eb7bf0bbedb65277d68ab89ae43cdec3fd6ba.tar.xz
net: Update alloc frag to reduce get/put page usage and recycle pages
This patch is meant to help improve performance by reducing the number of locked operations required to allocate a frag on x86 and other platforms. This is accomplished by using atomic_set operations on the page count instead of calling get_page and put_page. It is based on work originally provided by Eric Dumazet. In addition it also helps to reduce memory overhead when using TCP. This is done by recycling the page if the only holder of the frame is the netdev_alloc_frag call itself. This can occur when skb heads are stolen by either GRO or TCP and the driver providing the packets is using paged frags to store all of the data for the packets. Cc: Eric Dumazet <edumazet@google.com> Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/core')
-rw-r--r--net/core/skbuff.c28
1 files changed, 20 insertions, 8 deletions
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 506f678..8b6d38f 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -296,9 +296,12 @@ EXPORT_SYMBOL(build_skb);
struct netdev_alloc_cache {
struct page *page;
unsigned int offset;
+ unsigned int pagecnt_bias;
};
static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache);
+#define NETDEV_PAGECNT_BIAS (PAGE_SIZE / SMP_CACHE_BYTES)
+
/**
* netdev_alloc_frag - allocate a page fragment
* @fragsz: fragment size
@@ -317,17 +320,26 @@ void *netdev_alloc_frag(unsigned int fragsz)
if (unlikely(!nc->page)) {
refill:
nc->page = alloc_page(GFP_ATOMIC | __GFP_COLD);
+ if (unlikely(!nc->page))
+ goto end;
+recycle:
+ atomic_set(&nc->page->_count, NETDEV_PAGECNT_BIAS);
+ nc->pagecnt_bias = NETDEV_PAGECNT_BIAS;
nc->offset = 0;
}
- if (likely(nc->page)) {
- if (nc->offset + fragsz > PAGE_SIZE) {
- put_page(nc->page);
- goto refill;
- }
- data = page_address(nc->page) + nc->offset;
- nc->offset += fragsz;
- get_page(nc->page);
+
+ if (nc->offset + fragsz > PAGE_SIZE) {
+ /* avoid unnecessary locked operations if possible */
+ if ((atomic_read(&nc->page->_count) == nc->pagecnt_bias) ||
+ atomic_sub_and_test(nc->pagecnt_bias, &nc->page->_count))
+ goto recycle;
+ goto refill;
}
+
+ data = page_address(nc->page) + nc->offset;
+ nc->offset += fragsz;
+ nc->pagecnt_bias--;
+end:
local_irq_restore(flags);
return data;
}