From: Steven Caron <hidden> Date: 2016-06-13 14:02:05
As the ip fragment offset field counts 8-byte chunks, non-final ip
fragments must be multiples of 8 bytes of payload. Depending on the
mtu and ip option sizes, ip_append_page wasn't respecting this,
notably when running NFS under UDP.
Signed-off-by: Steven Caron <redacted>
---
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 124bf0a..21ec54e 100644--- a/net/ipv4/ip_output.c+++ b/net/ipv4/ip_output.c
From: Eric Dumazet <hidden> Date: 2016-06-13 15:16:49
On Mon, 2016-06-13 at 14:01 +0000, Steven Caron wrote:
As the ip fragment offset field counts 8-byte chunks, non-final ip
fragments must be multiples of 8 bytes of payload. Depending on the
mtu and ip option sizes, ip_append_page wasn't respecting this,
notably when running NFS under UDP.
Signed-off-by: Steven Caron <redacted>
---
From: Hannes Frederic Sowa <hidden> Date: 2016-06-13 19:27:23
On 13.06.2016 16:01, Steven Caron wrote:
As the ip fragment offset field counts 8-byte chunks, non-final ip
fragments must be multiples of 8 bytes of payload. Depending on the
mtu and ip option sizes, ip_append_page wasn't respecting this,
notably when running NFS under UDP.
Signed-off-by: Steven Caron <redacted>
Awesome!
Acked-by: Hannes Frederic Sowa <redacted>
From: David Miller <davem@davemloft.net> Date: 2016-06-15 05:49:33
From: Steven Caron <redacted>
Date: Mon, 13 Jun 2016 14:01:19 +0000
As the ip fragment offset field counts 8-byte chunks, non-final ip
fragments must be multiples of 8 bytes of payload. Depending on the
mtu and ip option sizes, ip_append_page wasn't respecting this,
notably when running NFS under UDP.
Signed-off-by: Steven Caron <redacted>
This seems to have DOS newlines or something strange like that.
Please fix your email client to send clean patches.
Thanks.