kernel/git/stable/linux.git/drivers/infiniband/ulp, branch linux-4.0.y

IB/srp: Fix reconnection failure handling

2015-07-21T17:10:14+00:00

commit a44074f14ba1ea0747ea737026eb929b81993dc3 upstream. Although it is possible to let SRP I/O continue if a reconnect results in a reduction of the number of channels, the current code does not handle this scenario correctly. Instead of making the reconnect code more complex, consider this as a reconnection failure. Signed-off-by: Bart Van Assche Cc: Sagi Grimberg Cc: Sebastian Parschauer Signed-off-by: Doug Ledford Signed-off-by: Greg Kroah-Hartman

IB/srp: Fix connection state tracking

2015-07-21T17:10:14+00:00

commit c014c8cd31b161e12deb81c0f7f477811bd1eddc upstream. Reception of a DREQ message only causes the state of a single channel to change. Hence move the 'connected' member variable from the target to the channel data structure. This patch avoids that following false positive warning can be reported by srp_destroy_qp(): WARNING: at drivers/infiniband/ulp/srp/ib_srp.c:617 srp_destroy_qp+0xa6/0x120 [ib_srp]() Call Trace: [] warn_slowpath_common+0x7f/0xc0 [] warn_slowpath_null+0x1a/0x20 [] srp_destroy_qp+0xa6/0x120 [ib_srp] [] srp_free_ch_ib+0x82/0x1e0 [ib_srp] [] srp_create_target+0x7ab/0x998 [ib_srp] [] dev_attr_store+0x20/0x30 [] sysfs_write_file+0xef/0x170 [] vfs_write+0xc8/0x190 [] sys_write+0x51/0x90 Signed-off-by: Bart Van Assche Cc: Sagi Grimberg Cc: Sebastian Parschauer Signed-off-by: Doug Ledford Signed-off-by: Greg Kroah-Hartman

IB/srp: Fix a connection setup race

2015-07-21T17:10:14+00:00

commit 8de9fe3a1d4ac8c3e4953fa4b7d81f863f5196ad upstream. Avoid that receiving a DREQ while RDMA channels are being established causes target->qp_in_error to be reset. Signed-off-by: Bart Van Assche Cc: Sagi Grimberg Cc: Sebastian Parschauer Signed-off-by: Doug Ledford Signed-off-by: Greg Kroah-Hartman

IB/srp: Remove an extraneous scsi_host_put() from an error path

2015-07-21T17:10:14+00:00

commit fb49c8bbaae70b14fea2b4590a90a21539f88526 upstream. Fix a scsi_get_host() / scsi_host_put() imbalance in the error path of srp_create_target(). See also patch "IB/srp: Avoid that I/O hangs due to a cable pull during LUN scanning" (commit ID 34aa654ecb8e). Signed-off-by: Bart Van Assche Reviewed-by: Sagi Grimberg Cc: Sebastian Parschauer Signed-off-by: Doug Ledford Signed-off-by: Greg Kroah-Hartman

iser-target: release stale iser connections

2015-07-21T17:10:13+00:00

commit 2f1b6b7d9a815f341b18dfd26a363f37d4d3c96a upstream. When receiving a new iser connect request we serialize the pending requests by adding the newly created iser connection to the np accept list and let the login thread process the connect request one by one (np_accept_wait). In case we received a disconnect request before the iser_conn has begun processing (still linked in np_accept_list) we should detach it from the list and clean it up and not have the login thread process a stale connection. We do it only when the connection state is not already terminating (initiator driven disconnect) as this might lead us to access np_accept_mutex after the np was released in live shutdown scenarios. Signed-off-by: Sagi Grimberg Signed-off-by: Jenny Falkovich Signed-off-by: Nicholas Bellinger Signed-off-by: Greg Kroah-Hartman

iser-target: Fix possible use-after-free

2015-06-29T19:29:07+00:00

commit 524630d5824c7a75aab568c6bd1423fd748cd3bb upstream. iser connection termination process happens in 2 stages: - isert_wait_conn: - resumes rdma disconnect - wait for session commands - wait for flush completions (post a marked wr to signal we are done) - wait for logout completion - queue work for connection cleanup (depends on disconnected/timewait events) - isert_free_conn - last reference put on the connection In case we are terminating during IOs, we might be posting send/recv requests after we posted the last work request which might lead to a use-after-free condition in isert_handle_wc. After we posted the last wr in isert_wait_conn we are guaranteed that no successful completions will follow (meaning no new work request posts may happen) but other flush errors might still come. So before we put the last reference on the connection, we repeat the process of posting a marked work request (isert_wait4flush) in order to make sure all pending completions were flushed. Signed-off-by: Sagi Grimberg Signed-off-by: Jenny Falkovich Signed-off-by: Nicholas Bellinger Signed-off-by: Greg Kroah-Hartman

iser-target: Fix variable-length response error completion

2015-06-29T19:29:07+00:00

commit 9253e667ab50fd4611a60e1cdd6a6e05a1d91cf1 upstream. Since commit "2426bd456a6 target: Report correct response ..." we might get a command with data_size that does not fit to the number of allocated data sg elements. Given that we rely on cmd t_data_nents which might be different than the data_size, we sometimes receive local length error completion. The correct approach would be to take the command data_size into account when constructing the ib sg_list. Signed-off-by: Sagi Grimberg Signed-off-by: Jenny Falkovich Signed-off-by: Nicholas Bellinger Signed-off-by: Greg Kroah-Hartman

IB/iser: Fix wrong calculation of protection buffer length

2015-05-06T20:04:01+00:00

commit a065fe6aa25ba6ba93c02dc13486131bb3c64d5f upstream. This length miss-calculation may cause a silent data corruption in the DIX case and cause the device to reference unmapped area. Fixes: d77e65350f2d ('libiscsi, iser: Adjust data_length to include protection information') Signed-off-by: Sagi Grimberg Signed-off-by: Doug Ledford Signed-off-by: Greg Kroah-Hartman

iser-target: Fix possible deadlock in RDMA_CM connection error

2015-05-06T20:03:53+00:00

commit 4a579da2586bd3b79b025947ea24ede2bbfede62 upstream. Before we reach to connection established we may get an error event. In this case the core won't teardown this connection (never established it), so we take care of freeing it ourselves. Signed-off-by: Sagi Grimberg Signed-off-by: Nicholas Bellinger Signed-off-by: Greg Kroah-Hartman

iser-target: Fix session hang in case of an rdma read DIF error

2015-05-06T20:03:53+00:00

commit 364189f0ada5478e4faf8a552d6071a650d757cd upstream. This hang was a result of a missing command put when a DIF error occurred during a rdma read (and we sent an CHECK_CONDITION error without passing it to the backend). Signed-off-by: Sagi Grimberg Signed-off-by: Nicholas Bellinger Signed-off-by: Greg Kroah-Hartman