On Tue, Apr 26, 2011 at 09:08:15AM -0700, Stephen Hemminger wrote: > This is a longterm stable bug, not in upstream. > > Herbert what is the commit id?
I think it is 26cde9f7e2747b6d254b704594eed87ab959afa5: commit 26cde9f7e2747b6d254b704594eed87ab959afa5 Author: Herbert Xu <[email protected]> Date: Tue Jun 15 01:52:25 2010 +0000 udp: Fix bogus UFO packet generation It has been reported that the new UFO software fallback path fails under certain conditions with NFS. I tracked the problem down to the generation of UFO packets that are smaller than the MTU. The software fallback path simply discards these packets. This patch fixes the problem by not generating such packets on the UFO path. Signed-off-by: Herbert Xu <[email protected]> Reviewed-by: Michael S. Tsirkin <[email protected]> Signed-off-by: David S. Miller <[email protected]> Any objection to me queueing this up for the .32-stable tree? thanks, greg k-h > > Begin forwarded message: > > Date: Tue, 26 Apr 2011 11:46:06 GMT > From: [email protected] > To: [email protected] > Subject: [Bug 33972] New: Bogus UDP Fragmentation Offload packet generation > > > https://bugzilla.kernel.org/show_bug.cgi?id=33972 > > Summary: Bogus UDP Fragmentation Offload packet generation > Product: Networking > Version: 2.5 > Kernel Version: 2.6.32.x > Platform: All > OS/Version: Linux > Tree: Mainline > Status: NEW > Severity: high > Priority: P1 > Component: IPV4 > AssignedTo: [email protected] > ReportedBy: [email protected] > Regression: Yes > > > Created an attachment (id=55552) > --> (https://bugzilla.kernel.org/attachment.cgi?id=55552) > udp: Fix bogus UFO packet generation > > The new UFO software fallback path fails under certain conditions with NFS and > causes partial connectivity loss due to generation of UFO packets smaller than > the MTU, which are then discarded by the software fallback path. > > How to reproduce: copy a large file to an NFS mount with UFO enabled and going > through the software fallback path, e.g. on a KVM guest with virtio-net and > qdev device syntax: > > -device virtio-net-pci,netdev=tap1,mac=ab:cd:ef:01:23:45 \ > -netdev type=tap,id=tap1,ifname=tap1 > > All NFS mounts immediately stall and processes go into D state, stuck > on nfs_wait_bit_uninterruptible. There is no further communication between > the client and the server. > > It has been fixed in 2.6.35-rc4 by Herbert Xu (patch for net/ipv4/ip_output.c > attached). However, it's still not in 2.6.32.x longterm (as of 2.6.32.39). > > -- > Configure bugmail: https://bugzilla.kernel.org/userprefs.cgi?tab=email > ------- You are receiving this mail because: ------- > You are the assignee for the bug. > > > -- _______________________________________________ stable mailing list [email protected] http://linux.kernel.org/mailman/listinfo/stable
