net: add alloc_skb_with_frags() helper

Extract from sock_alloc_send_pskb() code building skb with frags,
so that we can reuse this in other contexts.

Intent is to use it from tcp_send_rcvq(), tcp_collapse(), ...

We also want to replace some skb_linearize() calls to a more reliable
strategy in pathological cases where we need to reduce number of frags.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 756e3d0..f1bfa37 100644 (file)
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -769,6 +769,12 @@ static inline struct sk_buff *alloc_skb(unsigned int size,
        return __alloc_skb(size, priority, 0, NUMA_NO_NODE);
 }
 
+struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
+                                    unsigned long data_len,
+                                    int max_page_order,
+                                    int *errcode,
+                                    gfp_t gfp_mask);
+
 static inline struct sk_buff *alloc_skb_fclone(unsigned int size,
                                               gfp_t priority)
 {

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 29f7f01..06a8feb 100644 (file)
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4102,3 +4102,81 @@ err_free:
        return NULL;
 }
 EXPORT_SYMBOL(skb_vlan_untag);
+
+/**
+ * alloc_skb_with_frags - allocate skb with page frags
+ *
+ * header_len: size of linear part
+ * data_len: needed length in frags
+ * max_page_order: max page order desired.
+ * errcode: pointer to error code if any
+ * gfp_mask: allocation mask
+ *
+ * This can be used to allocate a paged skb, given a maximal order for frags.
+ */
+struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
+                                    unsigned long data_len,
+                                    int max_page_order,
+                                    int *errcode,
+                                    gfp_t gfp_mask)
+{
+       int npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
+       unsigned long chunk;
+       struct sk_buff *skb;
+       struct page *page;
+       gfp_t gfp_head;
+       int i;
+
+       *errcode = -EMSGSIZE;
+       /* Note this test could be relaxed, if we succeed to allocate
+        * high order pages...
+        */
+       if (npages > MAX_SKB_FRAGS)
+               return NULL;
+
+       gfp_head = gfp_mask;
+       if (gfp_head & __GFP_WAIT)
+               gfp_head |= __GFP_REPEAT;
+
+       *errcode = -ENOBUFS;
+       skb = alloc_skb(header_len, gfp_head);
+       if (!skb)
+               return NULL;
+
+       skb->truesize += npages << PAGE_SHIFT;
+
+       for (i = 0; npages > 0; i++) {
+               int order = max_page_order;
+
+               while (order) {
+                       if (npages >= 1 << order) {
+                               page = alloc_pages(gfp_mask |
+                                                  __GFP_COMP |
+                                                  __GFP_NOWARN |
+                                                  __GFP_NORETRY,
+                                                  order);
+                               if (page)
+                                       goto fill_page;
+                               /* Do not retry other high order allocations */
+                               order = 1;
+                               max_page_order = 0;
+                       }
+                       order--;
+               }
+               page = alloc_page(gfp_mask);
+               if (!page)
+                       goto failure;
+fill_page:
+               chunk = min_t(unsigned long, data_len,
+                             PAGE_SIZE << order);
+               skb_fill_page_desc(skb, i, page, 0, chunk);
+               data_len -= chunk;
+               npages -= 1 << order;
+       }
+       return skb;
+
+failure:
+       kfree_skb(skb);
+       return NULL;
+}
+EXPORT_SYMBOL(alloc_skb_with_frags);

diff --git a/net/core/sock.c b/net/core/sock.c
index 6f436b5..de887c4 100644 (file)
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1762,21 +1762,12 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
                                     unsigned long data_len, int noblock,
                                     int *errcode, int max_page_order)
 {
-       struct sk_buff *skb = NULL;
-       unsigned long chunk;
-       gfp_t gfp_mask;
+       struct sk_buff *skb;
        long timeo;
        int err;
-       int npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
-       struct page *page;
-       int i;
-
-       err = -EMSGSIZE;
-       if (npages > MAX_SKB_FRAGS)
-               goto failure;
 
        timeo = sock_sndtimeo(sk, noblock);
-       while (!skb) {
+       for (;;) {
                err = sock_error(sk);
                if (err != 0)
                        goto failure;
@@ -1785,66 +1776,27 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
                if (sk->sk_shutdown & SEND_SHUTDOWN)
                        goto failure;
 
-               if (atomic_read(&sk->sk_wmem_alloc) >= sk->sk_sndbuf) {
-                       set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
-                       set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
-                       err = -EAGAIN;
-                       if (!timeo)
-                               goto failure;
-                       if (signal_pending(current))
-                               goto interrupted;
-                       timeo = sock_wait_for_wmem(sk, timeo);
-                       continue;
-               }
-
-               err = -ENOBUFS;
-               gfp_mask = sk->sk_allocation;
-               if (gfp_mask & __GFP_WAIT)
-                       gfp_mask |= __GFP_REPEAT;
+               if (sk_wmem_alloc_get(sk) < sk->sk_sndbuf)
+                       break;
 
-               skb = alloc_skb(header_len, gfp_mask);
-               if (!skb)
+               set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+               set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+               err = -EAGAIN;
+               if (!timeo)
                        goto failure;
-
-               skb->truesize += data_len;
-
-               for (i = 0; npages > 0; i++) {
-                       int order = max_page_order;
-
-                       while (order) {
-                               if (npages >= 1 << order) {
-                                       page = alloc_pages(sk->sk_allocation |
-                                                          __GFP_COMP |
-                                                          __GFP_NOWARN |
-                                                          __GFP_NORETRY,
-                                                          order);
-                                       if (page)
-                                               goto fill_page;
-                                       /* Do not retry other high order allocations */
-                                       order = 1;
-                                       max_page_order = 0;
-                               }
-                               order--;
-                       }
-                       page = alloc_page(sk->sk_allocation);
-                       if (!page)
-                               goto failure;
-fill_page:
-                       chunk = min_t(unsigned long, data_len,
-                                     PAGE_SIZE << order);
-                       skb_fill_page_desc(skb, i, page, 0, chunk);
-                       data_len -= chunk;
-                       npages -= 1 << order;
-               }
+               if (signal_pending(current))
+                       goto interrupted;
+               timeo = sock_wait_for_wmem(sk, timeo);
        }
-
-       skb_set_owner_w(skb, sk);
+       skb = alloc_skb_with_frags(header_len, data_len, max_page_order,
+                                  errcode, sk->sk_allocation);
+       if (skb)
+               skb_set_owner_w(skb, sk);
        return skb;
 
 interrupted:
        err = sock_intr_errno(timeo);
 failure:
-       kfree_skb(skb);
        *errcode = err;
        return NULL;
 }