BMC/Intel-BMC/linux.git/drivers/infiniband/ulp/srp, branch dev-4.6

IB/srp: Fix srp_create_target() error handling

2016-06-01T19:18:04+00:00

commit f83b2561a6d4ff12959660ad597580097b744941 upstream. Avoid that the following kernel oops occurs if memory pool allocation fails: BUG: unable to handle kernel NULL pointer dereference at (null) IP: [] ib_drain_rq+0x0/0x20 [ib_core] Call Trace: [] srp_create_target+0xca6/0x13a9 [ib_srp] [] dev_attr_store+0x13/0x20 [] sysfs_kf_write+0x40/0x50 [] kernfs_fop_write+0x13c/0x180 [] __vfs_write+0x23/0xf0 [] vfs_write+0xa4/0x1a0 [] SyS_write+0x44/0xa0 [] entry_SYSCALL_64_fastpath+0x1c/0xac Fixes: 1dc7b1f10dcb ("IB/srp: use the new CQ API") Signed-off-by: Bart Van Assche Reviewed-by: Leon Romanovsky Tested-by: Laurence Oberman Cc: Christoph Hellwig Cc: Sagi Grimberg Signed-off-by: Doug Ledford Signed-off-by: Greg Kroah-Hartman

IB/srp: Fix a debug kernel crash

2016-06-01T19:18:04+00:00

commit 54f5c9c52d69afa55abf2b034df8d45f588466c3 upstream. Avoid that the following BUG() is triggered against a debug kernel: kernel BUG at include/linux/scatterlist.h:92! RIP: 0010:[] [] srp_map_idb+0x199/0x1a0 [ib_srp] Call Trace: [] srp_map_data+0x84a/0x890 [ib_srp] [] srp_queuecommand+0x1e4/0x610 [ib_srp] [] scsi_dispatch_cmd+0x9e/0x180 [] scsi_request_fn+0x477/0x610 [] __blk_run_queue+0x2e/0x40 [] blk_delay_work+0x20/0x30 [] process_one_work+0x197/0x480 [] worker_thread+0x49/0x490 [] kthread+0xea/0x100 [] ret_from_fork+0x22/0x40 Fixes: f7f7aab1a5c0 ("IB/srp: Convert to new registration API") Signed-off-by: Bart Van Assche Cc: Sagi Grimberg Cc: Christoph Hellwig Reviewed-by: Max Gurtovoy Reviewed-by: Sagi Grimberg Signed-off-by: Doug Ledford Signed-off-by: Greg Kroah-Hartman

IB/srp: Use ib_drain_rq()

2016-02-29T22:10:27+00:00

Signed-off-by: Steve Wise Reviewed-by: Bart Van Assche Signed-off-by: Doug Ledford

Merge branches '4.5/Or-cleanup' and '4.5/rdma-cq' into k.o/for-4.5

2015-12-22T22:03:15+00:00

Signed-off-by: Doug Ledford Conflicts: drivers/infiniband/ulp/iser/iser_verbs.c

IB/ulps: Avoid calling ib_query_device

2015-12-22T19:39:00+00:00

Instead, use the cached copy of the attributes present on the device. Signed-off-by: Or Gerlitz Signed-off-by: Doug Ledford

Merge branch 'rdma-cq.2' of git://git.infradead.org/users/hch/rdma into 4.5/rdma-cq

2015-12-15T19:10:44+00:00

Signed-off-by: Doug Ledford Conflicts: drivers/infiniband/ulp/srp/ib_srp.c - Conflicts with changes in ib_srp.c introduced during 4.4-rc updates

IB/srp: use the new CQ API

2015-12-11T22:10:49+00:00

This also moves recv completion handling from hardirq context into softirq context. Signed-off-by: Christoph Hellwig

IB: add a proper completion queue abstraction

2015-12-11T22:10:43+00:00

This adds an abstraction that allows ULPs to simply pass a completion object and completion callback with each submitted WR and let the RDMA core handle the nitty gritty details of how to handle completion interrupts and poll the CQ. In detail there is a new ib_cqe structure which just contains the completion callback, and which can be used to get at the containing object using container_of. It is pointed to by the WR and WC as an alternative to the wr_id field, similar to how many ULPs already use the field to store a pointer using casts. A driver using the new completion callbacks allocates it's CQs using the new ib_create_cq API, which in addition to the number of CQEs and the completion vectors also takes a mode on how we poll for CQEs. Three modes are available: direct for drivers that never take CQ interrupts and just poll for them, softirq to poll from softirq context using the to be renamed blk-iopoll infrastructure which takes care of rearming and budgeting, or a workqueue for consumer who want to be called from user context. Thanks a lot to Sagi Grimberg who helped reviewing the API, wrote the current version of the workqueue code because my two previous attempts sucked too much and converted the iSER initiator to the new API. Signed-off-by: Christoph Hellwig

IB/srp: Fix srp_map_sg_fr()

2015-12-07T22:20:11+00:00

After dma_map_sg() has been called the return value of that function must be used as the number of elements in the scatterlist instead of scsi_sg_count(). Fixes: commit f7f7aab1a5c0 ("IB/srp: Convert to new registration API") Reported-by: Christoph Hellwig Signed-off-by: Bart Van Assche Cc: stable # v4.4+ Cc: Sagi Grimberg Cc: Sebastian Parschauer Reviewed-by: Sagi Grimberg Signed-off-by: Doug Ledford

IB/srp: Fix indirect data buffer rkey endianness

2015-12-07T22:20:11+00:00

Detected by sparse. Fixes: commit 330179f2fa93 ("IB/srp: Register the indirect data buffer descriptor") Signed-off-by: Bart Van Assche Cc: stable # v4.3+ Cc: Sagi Grimberg Cc: Christoph Hellwig Cc: Sebastian Parschauer Reviewed-by: Christoph Hellwig Signed-off-by: Doug Ledford