<feed xmlns='http://www.w3.org/2005/Atom'>
<title>wireguard-linux/drivers/infiniband/ulp/iser/iser_verbs.c, branch jd/unified-crypt-queue</title>
<subtitle>WireGuard for the Linux kernel</subtitle>
<id>https://git.zx2c4.com/wireguard-linux/atom/drivers/infiniband/ulp/iser/iser_verbs.c?h=jd%2Funified-crypt-queue</id>
<link rel='self' href='https://git.zx2c4.com/wireguard-linux/atom/drivers/infiniband/ulp/iser/iser_verbs.c?h=jd%2Funified-crypt-queue'/>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/wireguard-linux/'/>
<updated>2020-01-03T23:13:59Z</updated>
<entry>
<title>IB/iser: use true,false for bool variable</title>
<updated>2020-01-03T23:13:59Z</updated>
<author>
<name>zhengbin</name>
<email>zhengbin13@huawei.com</email>
</author>
<published>2019-12-24T08:40:10Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/wireguard-linux/commit/?id=c934833e772396e20e40715e01144a92faf11735'/>
<id>urn:sha1:c934833e772396e20e40715e01144a92faf11735</id>
<content type='text'>
Fixes coccicheck warning:

drivers/infiniband/ulp/iser/iser_memory.c:530:2-21: WARNING: Assignment of 0/1 to bool variable
drivers/infiniband/ulp/iser/iser_verbs.c:1096:2-21: WARNING: Assignment of 0/1 to bool variable

Link: https://lore.kernel.org/r/1577176812-2238-4-git-send-email-zhengbin13@huawei.com
Reported-by: Hulk Robot &lt;hulkci@huawei.com&gt;
Signed-off-by: zhengbin &lt;zhengbin13@huawei.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
</content>
</entry>
<entry>
<title>infiniband: fix ulp/iser/iser_verbs.c kernel-doc notation</title>
<updated>2019-10-22T17:52:56Z</updated>
<author>
<name>rd.dunlab@gmail.com</name>
<email>rd.dunlab@gmail.com</email>
</author>
<published>2019-10-10T03:52:47Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/wireguard-linux/commit/?id=134a42a66b3aa474cbe3cea6a96956ed9817962d'/>
<id>urn:sha1:134a42a66b3aa474cbe3cea6a96956ed9817962d</id>
<content type='text'>
Various kernel-doc fixes:

- fix typos
- don't use /** for internal structs or functions
- fix Return: kernel-doc formatting
- add kernel-doc notation for missing function parameters

../drivers/infiniband/ulp/iser/iser_verbs.c:159: warning: Function parameter or member 'ib_conn' not described in 'iser_alloc_fmr_pool'
../drivers/infiniband/ulp/iser/iser_verbs.c:159: warning: Function parameter or member 'cmds_max' not described in 'iser_alloc_fmr_pool'
../drivers/infiniband/ulp/iser/iser_verbs.c:159: warning: Function parameter or member 'size' not described in 'iser_alloc_fmr_pool'
../drivers/infiniband/ulp/iser/iser_verbs.c:221: warning: Function parameter or member 'ib_conn' not described in 'iser_free_fmr_pool'
../drivers/infiniband/ulp/iser/iser_verbs.c:304: warning: Function parameter or member 'ib_conn' not described in 'iser_alloc_fastreg_pool'
../drivers/infiniband/ulp/iser/iser_verbs.c:304: warning: Function parameter or member 'cmds_max' not described in 'iser_alloc_fastreg_pool'
../drivers/infiniband/ulp/iser/iser_verbs.c:304: warning: Function parameter or member 'size' not described in 'iser_alloc_fastreg_pool'
../drivers/infiniband/ulp/iser/iser_verbs.c:338: warning: Function parameter or member 'ib_conn' not described in 'iser_free_fastreg_pool'
../drivers/infiniband/ulp/iser/iser_verbs.c:568: warning: Function parameter or member 'iser_conn' not described in 'iser_conn_release'
../drivers/infiniband/ulp/iser/iser_verbs.c:603: warning: Function parameter or member 'iser_conn' not described in 'iser_conn_terminate'
../drivers/infiniband/ulp/iser/iser_verbs.c:1040: warning: Function parameter or member 'signal' not described in 'iser_post_send'
../drivers/infiniband/ulp/iser/iser_verbs.c:1040: warning: Function parameter or member 'ib_conn' not described in 'iser_post_send'
../drivers/infiniband/ulp/iser/iser_verbs.c:1040: warning: Function parameter or member 'tx_desc' not described in 'iser_post_send'

Link: https://lore.kernel.org/r/20191010035240.070520193@gmail.com
Signed-off-by: Randy Dunlap &lt;rd.dunlab@gmail.com&gt;
Reviewed-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
</content>
</entry>
<entry>
<title>RDMA/iser: Use iser_err instead of pr_err for logging</title>
<updated>2019-10-08T19:35:52Z</updated>
<author>
<name>Max Gurtovoy</name>
<email>maxg@mellanox.com</email>
</author>
<published>2019-10-06T12:56:20Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/wireguard-linux/commit/?id=3466c060ef6adffefc8aaa45d1fe01b64cd6007d'/>
<id>urn:sha1:3466c060ef6adffefc8aaa45d1fe01b64cd6007d</id>
<content type='text'>
Make sure all the debug prints in ib_iser module use the common driver
logger.

Link: https://lore.kernel.org/r/1570366580-24097-1-git-send-email-maxg@mellanox.com
Signed-off-by: Max Gurtovoy &lt;maxg@mellanox.com&gt;
Reviewed-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
</content>
</entry>
<entry>
<title>IB/iser: remove redundant macro definitions</title>
<updated>2019-10-01T14:27:13Z</updated>
<author>
<name>Max Gurtovoy</name>
<email>maxg@mellanox.com</email>
</author>
<published>2019-09-24T21:05:48Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/wireguard-linux/commit/?id=6eeff06db999bf9b17aaa52fddda4fd449726a64'/>
<id>urn:sha1:6eeff06db999bf9b17aaa52fddda4fd449726a64</id>
<content type='text'>
Use the general linux definition for 4K and retrieve the rest from it.

Link: https://lore.kernel.org/r/1569359148-12312-1-git-send-email-maxg@mellanox.com
Signed-off-by: Max Gurtovoy &lt;maxg@mellanox.com&gt;
Reviewed-by: Sagi Grimberg &lt;sagi@grimberg.me&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
</content>
</entry>
<entry>
<title>IB/iser: add unlikely checks in the fast path</title>
<updated>2019-10-01T14:23:22Z</updated>
<author>
<name>Max Gurtovoy</name>
<email>maxg@mellanox.com</email>
</author>
<published>2019-09-23T21:32:49Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/wireguard-linux/commit/?id=70bcc63f84eaa08c53a14e669550cffc947ca3b7'/>
<id>urn:sha1:70bcc63f84eaa08c53a14e669550cffc947ca3b7</id>
<content type='text'>
ib_post_send, ib_post_recv and ib_dma_map_sg  operations should succeed
unless something unusual happened to the ib device.

Link: https://lore.kernel.org/r/1569274369-29217-1-git-send-email-maxg@mellanox.com
Signed-off-by: Max Gurtovoy &lt;maxg@mellanox.com&gt;
Acked-by: Sagi Grimberg &lt;sagi@grimberg.me&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
</content>
</entry>
<entry>
<title>RDMA/core: Rename signature qp create flag and signature device capability</title>
<updated>2019-06-24T14:49:27Z</updated>
<author>
<name>Israel Rukshin</name>
<email>israelr@mellanox.com</email>
</author>
<published>2019-06-11T15:52:50Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/wireguard-linux/commit/?id=c0a6cbb9cbccffc249743afa16e64f16c46c80b2'/>
<id>urn:sha1:c0a6cbb9cbccffc249743afa16e64f16c46c80b2</id>
<content type='text'>
Rename IB_QP_CREATE_SIGNATURE_EN to IB_QP_CREATE_INTEGRITY_EN
and IB_DEVICE_SIGNATURE_HANDOVER to IB_DEVICE_INTEGRITY_HANDOVER.

Signed-off-by: Israel Rukshin &lt;israelr@mellanox.com&gt;
Reviewed-by: Max Gurtovoy &lt;maxg@mellanox.com&gt;
Reviewed-by: Christoph Hellwig &lt;hch@lst.de&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
</content>
</entry>
<entry>
<title>IB/iser: Unwind WR union at iser_tx_desc</title>
<updated>2019-06-24T14:49:27Z</updated>
<author>
<name>Israel Rukshin</name>
<email>israelr@mellanox.com</email>
</author>
<published>2019-06-11T15:52:48Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/wireguard-linux/commit/?id=b9294f8b7c4bfdad35f4eb8330974892aedd1aaf'/>
<id>urn:sha1:b9294f8b7c4bfdad35f4eb8330974892aedd1aaf</id>
<content type='text'>
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 &lt;israelr@mellanox.com&gt;
Reviewed-by: Max Gurtovoy &lt;maxg@mellanox.com&gt;
Reviewed-by: Christoph Hellwig &lt;hch@lst.de&gt;
Reviewed-by: Sagi Grimberg &lt;sagi@grimberg.me&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
</content>
</entry>
<entry>
<title>IB/iser: Use IB_WR_REG_MR_INTEGRITY for PI handover</title>
<updated>2019-06-24T14:49:27Z</updated>
<author>
<name>Israel Rukshin</name>
<email>israelr@mellanox.com</email>
</author>
<published>2019-06-11T15:52:47Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/wireguard-linux/commit/?id=b76a439982f8483beb2ffcfe93be50026940030a'/>
<id>urn:sha1:b76a439982f8483beb2ffcfe93be50026940030a</id>
<content type='text'>
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 &lt;israelr@mellanox.com&gt;
Reviewed-by: Max Gurtovoy &lt;maxg@mellanox.com&gt;
Reviewed-by: Christoph Hellwig &lt;hch@lst.de&gt;
Reviewed-by: Sagi Grimberg &lt;sagi@grimberg.me&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
</content>
</entry>
<entry>
<title>iser: set sector for ambiguous mr status errors</title>
<updated>2018-11-21T23:03:43Z</updated>
<author>
<name>Sagi Grimberg</name>
<email>sagi@grimberg.me</email>
</author>
<published>2018-11-14T18:17:01Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/wireguard-linux/commit/?id=24c3456c8d5ee6fc1933ca40f7b4406130682668'/>
<id>urn:sha1:24c3456c8d5ee6fc1933ca40f7b4406130682668</id>
<content type='text'>
If for some reason we failed to query the mr status, we need to make sure
to provide sufficient information for an ambiguous error (guard error on
sector 0).

Fixes: 0a7a08ad6f5f ("IB/iser: Implement check_protection")
Cc: &lt;stable@vger.kernel.org&gt;
Reported-by: Dan Carpenter &lt;dan.carpenter@oracle.com&gt;
Signed-off-by: Sagi Grimberg &lt;sagi@grimberg.me&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
</content>
</entry>
<entry>
<title>RDMA/ulp: Use dev_name instead of ibdev-&gt;name</title>
<updated>2018-09-26T19:51:48Z</updated>
<author>
<name>Jason Gunthorpe</name>
<email>jgg@mellanox.com</email>
</author>
<published>2018-09-20T22:42:27Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/wireguard-linux/commit/?id=6c8541118bd53bc90b6c2473e289e5541de80376'/>
<id>urn:sha1:6c8541118bd53bc90b6c2473e289e5541de80376</id>
<content type='text'>
These return the same thing but dev_name is a more conventional use of the
kernel API.

Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
Reviewed-by: Steve Wise &lt;swise@opengridcomputing.com&gt;
Reviewed-by: Sagi Grimberg &lt;sagi@grimberg.me&gt;
Reviewed-by: Dennis Dalessandro &lt;dennis.dalessandro@intel.com&gt;
</content>
</entry>
</feed>
