@@ -365,6 +365,7 @@ extern void __free_pages(struct page *page, unsigned int order);
extern void free_pages(unsigned long addr, unsigned int order);
extern void free_hot_cold_page(struct page *page, bool cold);
extern void free_hot_cold_page_list(struct list_head *list, bool cold);
+extern void __free_pages_ok(struct page *page, unsigned int order);
extern void __free_kmem_pages(struct page *page, unsigned int order);
extern void free_kmem_pages(unsigned long addr, unsigned int order);
@@ -2186,6 +2186,7 @@ static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev,
return __netdev_alloc_skb_ip_align(dev, length, GFP_ATOMIC);
}
+void skb_free_frag(void *head);
void *napi_alloc_frag(unsigned int fragsz);
struct sk_buff *__napi_alloc_skb(struct napi_struct *napi,
unsigned int length, gfp_t gfp_mask);
@@ -165,8 +165,6 @@ bool pm_suspended_storage(void)
int pageblock_order __read_mostly;
#endif
-static void __free_pages_ok(struct page *page, unsigned int order);
-
/*
* results with 256, 32 in the lowmem_reserve sysctl:
* 1G machine -> (16M dma, 800M-16M normal, 1G-800M high)
@@ -815,7 +813,7 @@ static bool free_pages_prepare(struct page *page, unsigned int order)
return true;
}
-static void __free_pages_ok(struct page *page, unsigned int order)
+void __free_pages_ok(struct page *page, unsigned int order)
{
unsigned long flags;
int migratetype;
@@ -428,6 +428,27 @@ refill:
return page_address(page) + offset;
}
+/**
+ * skb_free_frag - free a page fragment
+ * @head: virtual address of page fragment
+ *
+ * Frees a page fragment allocated out of either a compound or order 0 page.
+ * The function itself is a hybrid between free_pages and free_compound_page
+ * which can be found in mm/page_alloc.c
+ */
+void skb_free_frag(void *head)
+{
+ struct page *page = virt_to_head_page(head);
+
+ if (unlikely(put_page_testzero(page))) {
+ if (likely(PageHead(page)))
+ __free_pages_ok(page, compound_order(page));
+ else
+ free_hot_cold_page(page, false);
+ }
+}
+EXPORT_SYMBOL(skb_free_frag);
+
static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
{
unsigned long flags;
@@ -499,7 +520,7 @@ static struct sk_buff *__alloc_rx_skb(unsigned int length, gfp_t gfp_mask,
if (likely(data)) {
skb = build_skb(data, fragsz);
if (unlikely(!skb))
- put_page(virt_to_head_page(data));
+ skb_free_frag(data);
}
} else {
skb = __alloc_skb(length, gfp_mask,
@@ -611,10 +632,12 @@ static void skb_clone_fraglist(struct sk_buff *skb)
static void skb_free_head(struct sk_buff *skb)
{
+ unsigned char *head = skb->head;
+
if (skb->head_frag)
- put_page(virt_to_head_page(skb->head));
+ skb_free_frag(head);
else
- kfree(skb->head);
+ kfree(head);
}
static void skb_release_data(struct sk_buff *skb)
This change adds a function called skb_free_frag which is meant to compliment the function __alloc_page_frag. The general idea is to enable a more lightweight version of page freeing since we don't actually need all the overhead of a put_page, and we don't quite fit the model of __free_pages. The model for this is based off of __free_pages since we don't actually need to deal with all of the cases that put_page handles. I incorporated the virt_to_head_page call and compound_order into the function as it actually allows for a signficant size reduction by reducing code duplication. In order to enable the function it was necessary to move __free_pages_ok from being a statically defined function so that I could use it in skbuff.c. Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com> --- include/linux/gfp.h | 1 + include/linux/skbuff.h | 1 + mm/page_alloc.c | 4 +--- net/core/skbuff.c | 29 ++++++++++++++++++++++++++--- 4 files changed, 29 insertions(+), 6 deletions(-) -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html