linux.git/drivers/infiniband, branch v2.6.17 Linux kernel source tree IPoIB: Fix AH leak at interface down 2006-06-05T16:51:36+00:00 Eli Cohen eli@mellanox.co.il 2006-06-05T16:51:36+00:00 959eb39297e8c82f61fbfc283ad4ff11c883bf1e When ipoib_stop() is called it first calls netif_stop_queue() to stop the kernel from passing more packets to the network driver. However, the completion handler may call netif_wake_queue() re-enabling packet transfer. This might result in leaks (we see AH leaks which we think can be attributed to this bug) as new packets get posted while the interface is going down. Signed-off-by: Eli Cohen <eli@mellanox.co.il> Signed-off-by: Michael Tsirkin <mst@mellanox.co.il> Signed-off-by: Roland Dreier <rolandd@cisco.com> 
When ipoib_stop() is called it first calls netif_stop_queue() to stop
the kernel from passing more packets to the network driver. However,
the completion handler may call netif_wake_queue() re-enabling packet
transfer.

This might result in leaks (we see AH leaks which we think can be
attributed to this bug) as new packets get posted while the interface
is going down.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Michael Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
IB/mthca: Fix posting lists of 256 receive requests to SRQ for Tavor 2006-05-24T20:43:37+00:00 Michael S. Tsirkin mst@mellanox.co.il 2006-05-24T15:27:07+00:00 ab28b171eabc0a414e0404844453c11af3caed10 If we post a list of length exactly a multiple of 256, nreq in doorbell gets set to 256 which is wrong: it should be encoded by 0. This is because we only zero it out on the next WR, which may not be there. The solution is to ring the doorbell after posting a WQE, not before posting the next one. This is the same bug that we just fixed for QPs with non-shared RQ. Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il> Signed-off-by: Roland Dreier <rolandd@cisco.com> 
If we post a list of length exactly a multiple of 256, nreq in
doorbell gets set to 256 which is wrong: it should be encoded by 0.
This is because we only zero it out on the next WR, which may not be
there.  The solution is to ring the doorbell after posting a WQE, not
before posting the next one.

This is the same bug that we just fixed for QPs with non-shared RQ.

Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
IB/ipath: deref correct pointer when using kernel SMA 2006-05-23T20:29:35+00:00 Bryan O'Sullivan bos@pathscale.com 2006-05-23T18:32:38+00:00 09b74de9fff056a0a4058a0f14508acba89ea6fc At this point, the core QP structure hasn't been initialized, so what's in there isn't valid. Get the same information elsewhere. Signed-off-by: Bryan O'Sullivan <bos@pathscale.com> Signed-off-by: Roland Dreier <rolandd@cisco.com> 
At this point, the core QP structure hasn't been initialized, so what's
in there isn't valid.  Get the same information elsewhere.

Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
IB/ipath: fix null deref during rdma ops 2006-05-23T20:29:35+00:00 Bryan O'Sullivan bos@pathscale.com 2006-05-23T18:32:37+00:00 3977026462314dfbb237adf6a964d0f683b8e45d The problem was that node A's sending thread, which handles sending RDMA read response data, would write the trigger word, the last packet would be sent, node B would send a new RDMA read request, node A's interrupt handler would initialize s_rdma_sge, then node A's sending thread would update s_rdma_sge. This didn't happen very often naturally but was more frequent with 1 byte RDMA reads. Rather than adding more locking or increasing the QP structure size and copying sge data, I modified the copy routine to update the pointers before writing the trigger word to avoid the update race. Signed-off-by: Ralph Campbell <ralphc@pathscale.com> Signed-off-by: Bryan O'Sullivan <bos@pathscale.com> Signed-off-by: Roland Dreier <rolandd@cisco.com> 
The problem was that node A's sending thread, which handles sending RDMA
read response data, would write the trigger word, the last packet would
be sent, node B would send a new RDMA read request, node A's interrupt
handler would initialize s_rdma_sge, then node A's sending thread would
update s_rdma_sge.  This didn't happen very often naturally but was more
frequent with 1 byte RDMA reads.  Rather than adding more locking or
increasing the QP structure size and copying sge data, I modified the
copy routine to update the pointers before writing the trigger word to
avoid the update race.

Signed-off-by: Ralph Campbell <ralphc@pathscale.com>
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
IB/ipath: register as IB device owner 2006-05-23T20:29:35+00:00 Bryan O'Sullivan bos@pathscale.com 2006-05-23T18:32:36+00:00 41c75a19bf4a0102f49763a686fb7e39780349f3 This fixes an oops. Signed-off-by: Bryan O'Sullivan <bos@pathscale.com> Signed-off-by: Roland Dreier <rolandd@cisco.com> 
This fixes an oops.

Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
IB/ipath: enable PE800 receive interrupts on user ports 2006-05-23T20:29:35+00:00 Bryan O'Sullivan bos@pathscale.com 2006-05-23T18:32:35+00:00 9dcc0e58e2913f7e6ffba64c27fe5c2f2c7b845c Fixed so it works on the PE-800. It had not previously been updated to match PE-800 receive interrupt differences from HT-400. Signed-off-by: Bryan O'Sullivan <bos@pathscale.com> Signed-off-by: Roland Dreier <rolandd@cisco.com> 
Fixed so it works on the PE-800.  It had not previously been updated to
match PE-800 receive interrupt differences from HT-400.

Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
IB/ipath: enable GPIO interrupt on HT-460 2006-05-23T20:29:34+00:00 Bryan O'Sullivan bos@pathscale.com 2006-05-23T18:32:34+00:00 f2080fa3c6098dedfb9b599bdaedd07be2ea4646 This is required for even semi-decent performance on OpenIB. Signed-off-by: Bryan O'Sullivan <bos@pathscale.com> Signed-off-by: Roland Dreier <rolandd@cisco.com> 
This is required for even semi-decent performance on OpenIB.

Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
IB/ipath: fix NULL dereference during cleanup 2006-05-23T20:27:06+00:00 Bryan O'Sullivan bos@pathscale.com 2006-05-23T18:32:33+00:00 b0ff7c2005f7ec8dec10fb15e62b8e1acc172bbf Fix NULL deref due to pcidev being clobbered before dd->ipath_f_cleanup() was called. Signed-off-by: Bryan O'Sullivan <bos@pathscale.com> Signed-off-by: Roland Dreier <rolandd@cisco.com> 
Fix NULL deref due to pcidev being clobbered before dd->ipath_f_cleanup()
was called.

Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
IB/ipath: replace uses of LIST_POISON 2006-05-23T20:27:06+00:00 Bryan O'Sullivan bos@pathscale.com 2006-05-23T18:32:32+00:00 94b8d9f98d7f535037eb9845b81396f667b4f727 Per Andrew's request. Signed-off-by: Bryan O'Sullivan <bos@pathscale.com> Signed-off-by: Roland Dreier <rolandd@cisco.com> 
Per Andrew's request.

Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
IB/ipath: fix reporting of driver version to userspace 2006-05-23T20:27:06+00:00 Bryan O'Sullivan bos@pathscale.com 2006-05-23T18:32:31+00:00 eaf6733bc176742fb08def2269441684e963c275 Fix the interface version that gets exported to userspace. Signed-off-by: Bryan O'Sullivan <bos@pathscale.com> Signed-off-by: Roland Dreier <rolandd@cisco.com> 
Fix the interface version that gets exported to userspace.

Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>