kernel/linux.git/drivers/infiniband/ulp, branch v5.4.50

IB/ipoib: Fix double free of skb in case of multicast traffic in CM mode

2020-06-03T06:21:26+00:00

[ Upstream commit 1acba6a817852d4aa7916d5c4f2c82f702ee9224 ] When connected mode is set, and we have connected and datagram traffic in parallel, ipoib might crash with double free of datagram skb. The current mechanism assumes that the order in the completion queue is the same as the order of sent packets for all QPs. Order is kept only for specific QP, in case of mixed UD and CM traffic we have few QPs (one UD and few CM's) in parallel. The problem: ---------------------------------------------------------- Transmit queue: ----------------- UD skb pointer kept in queue itself, CM skb kept in spearate queue and uses transmit queue as a placeholder to count the number of total transmitted packets. 0 1 2 3 4 5 6 7 8 9 10 11 12 13 .........127 ------------------------------------------------------------ NL ud1 UD2 CM1 ud3 cm2 cm3 ud4 cm4 ud5 NL NL NL ........... ------------------------------------------------------------ ^ ^ tail head Completion queue (problematic scenario) - the order not the same as in the transmit queue: 1 2 3 4 5 6 7 8 9 ------------------------------------ ud1 CM1 UD2 ud3 cm2 cm3 ud4 cm4 ud5 ------------------------------------ 1. CM1 'wc' processing - skb freed in cm separate ring. - tx_tail of transmit queue increased although UD2 is not freed. Now driver assumes UD2 index is already freed and it could be used for new transmitted skb. 0 1 2 3 4 5 6 7 8 9 10 11 12 13 .........127 ------------------------------------------------------------ NL NL UD2 CM1 ud3 cm2 cm3 ud4 cm4 ud5 NL NL NL ........... ------------------------------------------------------------ ^ ^ ^ (Bad)tail head (Bad - Could be used for new SKB) In this case (due to heavy load) UD2 skb pointer could be replaced by new transmitted packet UD_NEW, as the driver assumes its free. At this point we will have to process two 'wc' with same index but we have only one pointer to free. During second attempt to free the same skb we will have NULL pointer exception. 2. UD2 'wc' processing - skb freed according the index we got from 'wc', but it was already overwritten by mistake. So actually the skb that was released is the skb of the new transmitted packet and not the original one. 3. UD_NEW 'wc' processing - attempt to free already freed skb. NUll pointer exception. The fix: ----------------------------------------------------------------------- The fix is to stop using the UD ring as a placeholder for CM packets, the cyclic ring variables tx_head and tx_tail will manage the UD tx_ring, a new cyclic variables global_tx_head and global_tx_tail are introduced for managing and counting the overall outstanding sent packets, then the send queue will be stopped and waken based on these variables only. Note that no locking is needed since global_tx_head is updated in the xmit flow and global_tx_tail is updated in the NAPI flow only. A previous attempt tried to use one variable to count the outstanding sent packets, but it did not work since xmit and NAPI flows can run at the same time and the counter will be updated wrongly. Thus, we use the same simple cyclic head and tail scheme that we have today for the UD tx_ring. Fixes: 2c104ea68350 ("IB/ipoib: Get rid of the tx_outstanding variable in all modes") Link: https://lore.kernel.org/r/20200527134705.480068-1-leon@kernel.org Signed-off-by: Valentine Fatiev Signed-off-by: Alaa Hleihel Signed-off-by: Leon Romanovsky Acked-by: Doug Ledford Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin

scsi: Revert "RDMA/isert: Fix a recently introduced regression related to logout"

2020-02-28T16:22:25+00:00

commit 76261ada16dcc3be610396a46d35acc3efbda682 upstream. Since commit 04060db41178 introduces soft lockups when toggling network interfaces, revert it. Link: https://marc.info/?l=target-devel&m=158157054906196 Cc: Rahul Kundu Cc: Mike Marciniszyn Cc: Sagi Grimberg Reported-by: Dakshaja Uppalapati Fixes: 04060db41178 ("scsi: RDMA/isert: Fix a recently introduced regression related to logout") Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman

IB/srp: Never use immediate data if it is disabled by a user

2020-02-14T21:34:07+00:00

commit 0fbb37dd82998b5c83355997b3bdba2806968ac7 upstream. Some SRP targets that do not support specification SRP-2, put the garbage to the reserved bits of the SRP login response. The problem was not detected for a long time because the SRP initiator ignored those bits. But now one of them is used as SRP_LOGIN_RSP_IMMED_SUPP. And it causes a critical error on the target when the initiator sends immediate data. The ib_srp module has a use_imm_date parameter to enable or disable immediate data manually. But it does not help in the above case, because use_imm_date is ignored at handling the SRP login response. The problem is definitely caused by a bug on the target side, but the initiator's behavior also does not look correct. The initiator should not use immediate data if use_imm_date is disabled by a user. This commit adds an additional checking of use_imm_date at the handling of SRP login response to avoid unexpected use of immediate data. Fixes: 882981f4a411 ("RDMA/srp: Add support for immediate data") Link: https://lore.kernel.org/r/20200115133055.30232-1-sergeygo@mellanox.com Signed-off-by: Sergey Gorenko Reviewed-by: Bart Van Assche Signed-off-by: Jason Gunthorpe Signed-off-by: Greg Kroah-Hartman

scsi: RDMA/isert: Fix a recently introduced regression related to logout

2020-01-29T15:45:30+00:00

commit 04060db41178c7c244f2c7dcd913e7fd331de915 upstream. iscsit_close_connection() calls isert_wait_conn(). Due to commit e9d3009cb936 both functions call target_wait_for_sess_cmds() although that last function should be called only once. Fix this by removing the target_wait_for_sess_cmds() call from isert_wait_conn() and by only calling isert_wait_conn() after target_wait_for_sess_cmds(). Fixes: e9d3009cb936 ("scsi: target: iscsi: Wait for all commands to finish before freeing a session"). Link: https://lore.kernel.org/r/20200116044737.19507-1-bvanassche@acm.org Reported-by: Rahul Kundu Signed-off-by: Bart Van Assche Tested-by: Mike Marciniszyn Acked-by: Sagi Grimberg Signed-off-by: Martin K. Petersen Signed-off-by: Greg Kroah-Hartman

RDMA/srpt: Report the SCSI residual to the initiator

2020-01-17T18:48:40+00:00

commit e88982ad1bb12db699de96fbc07096359ef6176c upstream. The code added by this patch is similar to the code that already exists in ibmvscsis_determine_resid(). This patch has been tested by running the following command: strace sg_raw -r 1k /dev/sdb 12 00 00 00 60 00 -o inquiry.bin |& grep resid= Link: https://lore.kernel.org/r/20191105214632.183302-1-bvanassche@acm.org Fixes: a42d985bd5b2 ("ib_srpt: Initial SRP Target merge for v3.3-rc1") Signed-off-by: Bart Van Assche Acked-by: Honggang Li Signed-off-by: Jason Gunthorpe Signed-off-by: Greg Kroah-Hartman

IB/iser: bound protection_sg size by data_sg size

2019-12-31T15:43:15+00:00

[ Upstream commit 7718cf03c3ce4b6ebd90107643ccd01c952a1fce ] In case we don't set the sg_prot_tablesize, the scsi layer assign the default size (65535 entries). We should limit this size since we should take into consideration the underlaying device capability. This cap is considered when calculating the sg_tablesize. Otherwise, for example, we can get that /sys/block/sdb/queue/max_segments is 128 and /sys/block/sdb/queue/max_integrity_segments is 65535. Link: https://lore.kernel.org/r/1569359027-10987-1-git-send-email-maxg@mellanox.com Signed-off-by: Max Gurtovoy Reviewed-by: Sagi Grimberg Signed-off-by: Jason Gunthorpe Signed-off-by: Sasha Levin

Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

2019-09-21T17:26:24+00:00

Pull RDMA subsystem updates from Jason Gunthorpe: "This cycle mainly saw lots of bug fixes and clean up code across the core code and several drivers, few new functional changes were made. - Many cleanup and bug fixes for hns - Various small bug fixes and cleanups in hfi1, mlx5, usnic, qed, bnxt_re, efa - Share the query_port code between all the iWarp drivers - General rework and cleanup of the ODP MR umem code to fit better with the mmu notifier get/put scheme - Support rdma netlink in non init_net name spaces - mlx5 support for XRC devx and DC ODP" * tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (99 commits) RDMA: Fix double-free in srq creation error flow RDMA/efa: Fix incorrect error print IB/mlx5: Free mpi in mp_slave mode IB/mlx5: Use the original address for the page during free_pages RDMA/bnxt_re: Fix spelling mistake "missin_resp" -> "missing_resp" RDMA/hns: Package operations of rq inline buffer into separate functions RDMA/hns: Optimize cmd init and mode selection for hip08 IB/hfi1: Define variables as unsigned long to fix KASAN warning IB/{rdmavt, hfi1, qib}: Add a counter for credit waits IB/hfi1: Add traces for TID RDMA READ RDMA/siw: Relax from kmap_atomic() use in TX path IB/iser: Support up to 16MB data transfer in a single command RDMA/siw: Fix page address mapping in TX path RDMA: Fix goto target to release the allocated memory RDMA/usnic: Avoid overly large buffers on stack RDMA/odp: Add missing cast for 32 bit RDMA/hns: Use devm_platform_ioremap_resource() to simplify code Documentation/infiniband: update name of some functions RDMA/cma: Fix false error message RDMA/hns: Fix wrong assignment of qp_access_flags ...

IB/iser: Support up to 16MB data transfer in a single command

2019-09-13T19:55:55+00:00

Maximum supported IO size is 8MB for the iSER driver. The current value is limited by the ISCSI_ISER_MAX_SG_TABLESIZE macro. But the driver is able to handle 16MB IOs without any significant changes. Increasing this limit can be useful for the storage arrays which are fine tuned for IOs larger than 8 MB. This commit allows to configure maximum IO size up to 16MB using the max_sectors module parameter. Link: https://lore.kernel.org/r/20190912103534.18210-1-sergeygo@mellanox.com Signed-off-by: Sergey Gorenko Reviewed-by: Max Gurtovoy Acked-by: Sagi Grimberg Signed-off-by: Jason Gunthorpe

rdma: Enable ib_alloc_cq to spread work over a device's comp_vectors

2019-08-05T15:50:32+00:00

Send and Receive completion is handled on a single CPU selected at the time each Completion Queue is allocated. Typically this is when an initiator instantiates an RDMA transport, or when a target accepts an RDMA connection. Some ULPs cannot open a connection per CPU to spread completion workload across available CPUs and MSI vectors. For such ULPs, provide an API that allows the RDMA core to select a completion vector based on the device's complement of available comp_vecs. ULPs that invoke ib_alloc_cq() with only comp_vector 0 are converted to use the new API so that their completion workloads interfere less with each other. Suggested-by: Håkon Bugge Signed-off-by: Chuck Lever Reviewed-by: Leon Romanovsky Cc: Cc: Link: https://lore.kernel.org/r/20190729171923.13428.52555.stgit@manet.1015granger.net Signed-off-by: Doug Ledford

net: Use skb_frag_off accessors

2019-07-30T21:21:32+00:00

Use accessor functions for skb fragment's page_offset instead of direct references, in preparation for bvec conversion. Signed-off-by: Jonathan Lemon Signed-off-by: David S. Miller