[PATCH net-next 2/4] net: Introduce {netdev,napi}_alloc_frag_align()

[Kevin Hao <haokexin@gmail.com>]

In the current implementation of {netdev,napi}_alloc_frag(), it doesn't
have any align guarantee for the returned buffer address, But for some
hardwares they do require the DMA buffer to be aligned correctly,
so we would have to use some workarounds like below if the buffers
allocated by the {netdev,napi}_alloc_frag() are used by these hardwares
for DMA.
    buf = napi_alloc_frag(really_needed_size + align);
    buf = PTR_ALIGN(buf, align);

These codes seems ugly and would waste a lot of memories if the buffers
are used in a network driver for the TX/RX. We have added the align
support for the page_frag functions, so add the corresponding
{netdev,napi}_frag functions.

Signed-off-by: Kevin Hao <haokexin@gmail.com>
---
 include/linux/skbuff.h |  2 ++
 net/core/skbuff.c      | 40 ++++++++++++++++++++++++++--------------
 2 files changed, 28 insertions(+), 14 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 5f60c9e907c9..71e704732b6f 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2808,6 +2808,7 @@ void skb_queue_purge(struct sk_buff_head *list);
 
 unsigned int skb_rbtree_purge(struct rb_root *root);
 
+void *netdev_alloc_frag_align(unsigned int fragsz, int align);
 void *netdev_alloc_frag(unsigned int fragsz);
 
 struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int length,
@@ -2867,6 +2868,7 @@ static inline void skb_free_frag(void *addr)
 	page_frag_free(addr);
 }
 
+void *napi_alloc_frag_align(unsigned int fragsz, int align);
 void *napi_alloc_frag(unsigned int fragsz);
 struct sk_buff *__napi_alloc_skb(struct napi_struct *napi,
 				 unsigned int length, gfp_t gfp_mask);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 785daff48030..d01ecb4f0de4 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -374,29 +374,28 @@ struct napi_alloc_cache {
 static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache);
 static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache);
 
-static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
+static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask, int align)
 {
 	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
 
-	return page_frag_alloc(&nc->page, fragsz, gfp_mask);
+	return page_frag_alloc_align(&nc->page, fragsz, gfp_mask, align);
 }
 
-void *napi_alloc_frag(unsigned int fragsz)
+void *napi_alloc_frag_align(unsigned int fragsz, int align)
 {
 	fragsz = SKB_DATA_ALIGN(fragsz);
 
-	return __napi_alloc_frag(fragsz, GFP_ATOMIC);
+	return __napi_alloc_frag(fragsz, GFP_ATOMIC, align);
+}
+EXPORT_SYMBOL(napi_alloc_frag_align);
+
+void *napi_alloc_frag(unsigned int fragsz)
+{
+	return napi_alloc_frag_align(fragsz, 0);
 }
 EXPORT_SYMBOL(napi_alloc_frag);
 
-/**
- * netdev_alloc_frag - allocate a page fragment
- * @fragsz: fragment size
- *
- * Allocates a frag from a page for receive buffer.
- * Uses GFP_ATOMIC allocations.
- */
-void *netdev_alloc_frag(unsigned int fragsz)
+void *netdev_alloc_frag_align(unsigned int fragsz, int align)
 {
 	struct page_frag_cache *nc;
 	void *data;
@@ -404,14 +403,27 @@ void *netdev_alloc_frag(unsigned int fragsz)
 	fragsz = SKB_DATA_ALIGN(fragsz);
 	if (in_irq() || irqs_disabled()) {
 		nc = this_cpu_ptr(&netdev_alloc_cache);
-		data = page_frag_alloc(nc, fragsz, GFP_ATOMIC);
+		data = page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, align);
 	} else {
 		local_bh_disable();
-		data = __napi_alloc_frag(fragsz, GFP_ATOMIC);
+		data = __napi_alloc_frag(fragsz, GFP_ATOMIC, align);
 		local_bh_enable();
 	}
 	return data;
 }
+EXPORT_SYMBOL(netdev_alloc_frag_align);
+
+/**
+ * netdev_alloc_frag - allocate a page fragment
+ * @fragsz: fragment size
+ *
+ * Allocates a frag from a page for receive buffer.
+ * Uses GFP_ATOMIC allocations.
+ */
+void *netdev_alloc_frag(unsigned int fragsz)
+{
+	return netdev_alloc_frag_align(fragsz, 0);
+}
 EXPORT_SYMBOL(netdev_alloc_frag);
 
 /**
-- 
2.29.2