diff mbox series

[4.14,2/2] gro: ensure frag0 meets IP header alignment

Message ID 20210729184733.3217814-3-matthieu.baerts@tessares.net
State Superseded
Headers show
Series Backport fixes for 3226b158e67c | expand

Commit Message

Matthieu Baerts July 29, 2021, 6:47 p.m. UTC 
From: Eric Dumazet <edumazet@google.com>

[ Upstream commit 38ec4944b593fd90c5ef42aaaa53e66ae5769d04 ]

After commit 0f6925b3e8da ("virtio_net: Do not pull payload in skb->head")
Guenter Roeck reported one failure in his tests using sh architecture.

After much debugging, we have been able to spot silent unaligned accesses
in inet_gro_receive()

The issue at hand is that upper networking stacks assume their header
is word-aligned. Low level drivers are supposed to reserve NET_IP_ALIGN
bytes before the Ethernet header to make that happen.

This patch hardens skb_gro_reset_offset() to not allow frag0 fast-path
if the fragment is not properly aligned.

Some arches like x86, arm64 and powerpc do not care and define NET_IP_ALIGN
as 0, this extra check will be a NOP for them.

Note that if frag0 is not used, GRO will call pskb_may_pull()
as many times as needed to pull network and transport headers.

[ Backport note ]

    A small conflict has been reported:

        ++<<<<<<< HEAD
         +      if (skb_mac_header(skb) == skb_tail_pointer(skb) &&
         +          pinfo->nr_frags &&
         +          !PageHighMem(skb_frag_page(frag0))) {
        ++=======
        +       if (!skb_headlen(skb) && pinfo->nr_frags &&
        +           !PageHighMem(skb_frag_page(frag0)) &&
        +           (!NET_IP_ALIGN || !(skb_frag_off(frag0) & 3))) {
        ++>>>>>>> 38ec4944b593 (gro: ensure frag0 meets IP header alignment)

    This is expected because older kernels are missing
    commit 8aef998df3979 ("net: core: allow fast GRO for skbs with Ethernet header in head").
    This commit modifies the beginning of the 'if' statement.

    The resolution was easy: the patch we want to backport here is
    adding new conditions to the 'if' statement:

        && (!NET_IP_ALIGN || !(skb_frag_off(frag0) & 3))

    We simply append these new conditions to it on older kernels.

    Another issue had to be resolved: skb_frag_off() is used in this
    patch we want to backport but this function is not defined in
    kernels < 5.4. It has then been extracted and imported from
    commit 7240b60c98d63 ("linux: Add skb_frag_t page_offset accessors").

Fixes: 0f6925b3e8da ("virtio_net: Do not pull payload in skb->head")
Fixes: 78a478d0efd9 ("gro: Inline skb_gro_header and cache frag0 virtual address")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Guenter Roeck <linux@roeck-us.net>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
---
 include/linux/skbuff.h | 9 +++++++++
 net/core/dev.c         | 3 ++-
 2 files changed, 11 insertions(+), 1 deletion(-)
diff mbox series

Patch

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index de3e59329b02..2f303454a323 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2784,6 +2784,15 @@  static inline void skb_propagate_pfmemalloc(struct page *page,
 		skb->pfmemalloc = true;
 }
 
+/**
+ * skb_frag_off() - Returns the offset of a skb fragment
+ * @frag: the paged fragment
+ */
+static inline unsigned int skb_frag_off(const skb_frag_t *frag)
+{
+	return frag->page_offset;
+}
+
 /**
  * skb_frag_page - retrieve the page referred to by a paged fragment
  * @frag: the paged fragment
diff --git a/net/core/dev.c b/net/core/dev.c
index aa419f3162b8..ea09e0809c12 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4763,7 +4763,8 @@  static void skb_gro_reset_offset(struct sk_buff *skb)
 
 	if (skb_mac_header(skb) == skb_tail_pointer(skb) &&
 	    pinfo->nr_frags &&
-	    !PageHighMem(skb_frag_page(frag0))) {
+	    !PageHighMem(skb_frag_page(frag0)) &&
+	    (!NET_IP_ALIGN || !(skb_frag_off(frag0) & 3))) {
 		NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
 		NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int,
 						    skb_frag_size(frag0),