lkml.org 
[lkml]   [2019]   [Feb]   [28]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
SubjectRE: [PATCH] xen-netback: fix occasional leak of grant ref mappings under memory pressure
Date
> -----Original Message-----
> From: Igor Druzhinin [mailto:igor.druzhinin@citrix.com]
> Sent: 28 February 2019 02:03
> To: xen-devel@lists.xenproject.org; netdev@vger.kernel.org; linux-kernel@vger.kernel.org
> Cc: Wei Liu <wei.liu2@citrix.com>; Paul Durrant <Paul.Durrant@citrix.com>; davem@davemloft.net; Igor
> Druzhinin <igor.druzhinin@citrix.com>
> Subject: [PATCH] xen-netback: fix occasional leak of grant ref mappings under memory pressure
>
> Zero-copy callback flag is not yet set on frag list skb at the moment
> xenvif_handle_frag_list() returns -ENOMEM. This eventually results in
> leaking grant ref mappings since xenvif_zerocopy_callback() is never
> called for these fragments. Those eventually build up and cause Xen
> to kill Dom0 as the slots get reused for new mappings.
>
> That behavior is observed under certain workloads where sudden spikes
> of page cache usage for writes coexist with active atomic skb allocations.
>
> Signed-off-by: Igor Druzhinin <igor.druzhinin@citrix.com>
> ---
> drivers/net/xen-netback/netback.c | 3 +++
> 1 file changed, 3 insertions(+)
>
> diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
> index 80aae3a..2023317 100644
> --- a/drivers/net/xen-netback/netback.c
> +++ b/drivers/net/xen-netback/netback.c
> @@ -1146,9 +1146,12 @@ static int xenvif_tx_submit(struct xenvif_queue *queue)
>
> if (unlikely(skb_has_frag_list(skb))) {
> if (xenvif_handle_frag_list(queue, skb)) {
> + struct sk_buff *nskb =
> + skb_shinfo(skb)->frag_list;
> if (net_ratelimit())
> netdev_err(queue->vif->dev,
> "Not enough memory to consolidate frag_list!\n");
> + xenvif_skb_zerocopy_prepare(queue, nskb);
> xenvif_skb_zerocopy_prepare(queue, skb);
> kfree_skb(skb);
> continue;

Whilst this fix will do the job, I think it would be better to get rid of the kfree_skb() from inside xenvif_handle_frag_list() and always deal with it here rather than having it happen in two different places. Something like the following...

---8<---
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 80aae3a32c2a..093c7b860772 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -1027,13 +1027,13 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
/* Consolidate skb with a frag_list into a brand new one with local pages on
* frags. Returns 0 or -ENOMEM if can't allocate new pages.
*/
-static int xenvif_handle_frag_list(struct xenvif_queue *queue, struct sk_buff *skb)
+static int xenvif_handle_frag_list(struct xenvif_queue *queue, struct sk_buff *diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 80aae3a32c2a..093c7b860772 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -1027,13 +1027,13 @@ static void xenvif_tx_build_gops(struct xenvif_queue *qu
eue,
/* Consolidate skb with a frag_list into a brand new one with local pages on
* frags. Returns 0 or -ENOMEM if can't allocate new pages.
*/
-static int xenvif_handle_frag_list(struct xenvif_queue *queue, struct sk_buff *
skb)
+static int xenvif_handle_frag_list(struct xenvif_queue *queue, struct sk_buff *
skb,
+ struct sk_buff *nskb)
{
unsigned int offset = skb_headlen(skb);
skb_frag_t frags[MAX_SKB_FRAGS];
int i, f;
struct ubuf_info *uarg;
- struct sk_buff *nskb = skb_shinfo(skb)->frag_list;

queue->stats.tx_zerocopy_sent += 2;
queue->stats.tx_frag_overflow++;
@@ -1072,11 +1072,6 @@ static int xenvif_handle_frag_list(struct xenvif_queue *q
ueue, struct sk_buff *s
skb_frag_size_set(&frags[i], len);
}

- /* Copied all the bits from the frag list -- free it. */
- skb_frag_list_init(skb);
- xenvif_skb_zerocopy_prepare(queue, nskb);
- kfree_skb(nskb);
-
/* Release all the original (foreign) frags. */
for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
skb_frag_unref(skb, f);
@@ -1145,7 +1140,11 @@ static int xenvif_tx_submit(struct xenvif_queue *queue)
xenvif_fill_frags(queue, skb);

if (unlikely(skb_has_frag_list(skb))) {
- if (xenvif_handle_frag_list(queue, skb)) {
+ struct sk_buff *nskb = skb_shinfo(skb)->frag_list;
+
+ xenvif_skb_zerocopy_prepare(queue, nskb);
+
+ if (xenvif_handle_frag_list(queue, skb, nskb)) {
if (net_ratelimit())
netdev_err(queue->vif->dev,
"Not enough memory to consolidate frag_list!\n");
@@ -1153,6 +1152,10 @@ static int xenvif_tx_submit(struct xenvif_queue *queue)
kfree_skb(skb);
continue;
}
+
+ /* Copied all the bits from the frag list. */
+ skb_frag_list_init(skb);
+ kfree(nskb);
}

skb->dev = queue->vif->dev;
---8<---
What do you think?

Paul

> --
> 2.7.4

\
 
 \ /
  Last update: 2019-02-28 10:48    [W:0.054 / U:0.672 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site