linux.git/drivers/infiniband/ulp/iser/iser_memory.c, branch v5.4.93

IB/iser: Always check sig MR before putting it to the free pool

2020-10-01T11:17:50+00:00

[ Upstream commit 26e28deb813eed908cf31a6052870b6493ec0e86 ]

libiscsi calls the check_protection transport handler only if SCSI-Respose
is received. So, the handler is never called if iSCSI task is completed
for some other reason like a timeout or error handling. And this behavior
looks correct. But the iSER does not handle this case properly because it
puts a non-checked signature MR to the free pool. Then the error occurs at
reusing the MR because it is not allowed to invalidate a signature MR
without checking.

This commit adds an extra check to iser_unreg_mem_fastreg(), which is a
part of the task cleanup flow. Now the signature MR is checked there if it
is needed.

Link: https://lore.kernel.org/r/20200325151210.1548-1-sergeygo@mellanox.com
Signed-off-by: Sergey Gorenko 
Reviewed-by: Max Gurtovoy 
Signed-off-by: Jason Gunthorpe 
Signed-off-by: Sasha Levin

IB/iser: Unwind WR union at iser_tx_desc

2019-06-24T14:49:27+00:00

After decreasing WRs array size from 7 to 3 it is more
readable to give each WR a descriptive name.

Signed-off-by: Israel Rukshin 
Reviewed-by: Max Gurtovoy 
Reviewed-by: Christoph Hellwig 
Reviewed-by: Sagi Grimberg 
Signed-off-by: Jason Gunthorpe

IB/iser: Use IB_WR_REG_MR_INTEGRITY for PI handover

2019-06-24T14:49:27+00:00

Using this new API reduces iSER code complexity.
It also reduces the maximum number of work requests per task and the need
of dealing with multiple MRs (and their registrations and invalidations)
per task. It is done by using a single WR and a special MR type
(IB_MR_TYPE_INTEGRITY) for PI operation.

The setup of the tested benchmark:
 - 2 servers with 24 cores (1 initiator and 1 target)
 - 24 target sessions with 1 LUN each
 - ramdisk backstore
 - PI active

Performance results running fio (24 jobs, 128 iodepth) using
write_generate=0 and read_verify=0 (w/w.o patch):

bs      IOPS(read)        IOPS(write)
----    ----------        ----------
512     1236.6K/1164.3K   1357.2K/1332.8K
1k      1196.5K/1163.8K   1348.4K/1262.7K
2k      1016.7K/921950    1003.7K/931230
4k      662728/600545     595423/501513
8k      385954/384345     333775/277090
16k     222864/222820     170317/170671
32k     116869/114896     82331/82244
64k     55205/54931       40264/40021

Using write_generate=1 and read_verify=1 (w/w.o patch):

bs      IOPS(read)        IOPS(write)
----    ----------        ----------
512     1090.1K/1030.9K   1303.9K/1101.4K
1k      1057.7K/904583    1318.4K/988085
2k      965226/638799     1008.6K/692514
4k      555479/410151     542414/414517
8k      298675/224964     264729/237508
16k     133485/122481     164625/138647
32k     74329/67615       80143/78743
64k     35716/35519       39294/37334

We get performance improvement at all block sizes.
The most significant improvement is when writing 4k bs (almost 30% more
iops).

Signed-off-by: Israel Rukshin 
Reviewed-by: Max Gurtovoy 
Reviewed-by: Christoph Hellwig 
Reviewed-by: Sagi Grimberg 
Signed-off-by: Jason Gunthorpe

IB/iser: Remove unused sig_attrs argument

2019-05-21T18:01:05+00:00

Signed-off-by: Israel Rukshin 
Reviewed-by: Max Gurtovoy 
Reviewed-by: Christoph Hellwig 
Signed-off-by: Jason Gunthorpe

IB/core: Remove ib_sg_dma_address() and ib_sg_dma_len()

2019-02-04T21:34:07+00:00

Keeping single line wrapper functions is not useful. Hence remove the
ib_sg_dma_address() and ib_sg_dma_len() functions. This patch does not
change any functionality.

Signed-off-by: Bart Van Assche 
Signed-off-by: Jason Gunthorpe

IB/iser: Pass the correct number of entries for dma mapped SGL

2019-01-18T21:12:24+00:00

ib_dma_map_sg() augments the SGL into a 'dma mapped SGL'. This process may
change the number of entries and the lengths of each entry.

Code that touches dma_address is iterating over the 'dma mapped SGL' and
must use dma_nents which returned from ib_dma_map_sg().

ib_sg_to_pages() and ib_map_mr_sg() are using dma_address so they must use
dma_nents.

Fixes: 39405885005a ("IB/iser: Port to new fast registration API")
Fixes: bfe066e256d5 ("IB/iser: Reuse ib_sg_to_pages")
Signed-off-by: Israel Rukshin 
Reviewed-by: Max Gurtovoy 
Acked-by: Sagi Grimberg 
Signed-off-by: Jason Gunthorpe

RDMA: Start use ib_device_ops

2018-12-12T14:40:16+00:00

Make all the required change to start use the ib_device_ops structure.

Signed-off-by: Kamal Heib 
Signed-off-by: Jason Gunthorpe

IB/core: Make function ib_fmr_pool_unmap return void

2018-11-21T23:13:02+00:00

Since the function always returns 0 make it void.

Reported-by: Håkon Bugge 
Signed-off-by: Yuval Shaia 
Reviewed-by: Leon Romanovsky 
Acked-by: Sagi Grimberg 
Signed-off-by: Jason Gunthorpe

Merge branch 'linus/master' into rdma.git for-next

2018-08-16T20:21:29+00:00

rdma.git merge resolution for the 4.19 merge window

Conflicts:
 drivers/infiniband/core/rdma_core.c
   - Use the rdma code and revise with the new spelling for
     atomic_fetch_add_unless
 drivers/nvme/host/rdma.c
   - Replace max_sge with max_send_sge in new blk code
 drivers/nvme/target/rdma.c
   - Use the blk code and revise to use NULL for ib_post_recv when
     appropriate
   - Replace max_sge with max_recv_sge in new blk code
 net/rds/ib_send.c
   - Use the net code and revise to use NULL for ib_post_recv when
     appropriate

Signed-off-by: Jason Gunthorpe

IB/iser: Inline two work request conversion functions

2018-07-31T01:59:40+00:00

Since the next patch will change the return type of these functions into a
const pointer and since the iSER driver modifies the work request these
functions return a pointer two, inline two work request conversion
function calls. This patch does not change any functionality.

Signed-off-by: Bart Van Assche 
Reviewed-by: Sagi Grimberg 
Reviewed-by: Max Gurtovoy 
Signed-off-by: Jason Gunthorpe