<feed xmlns='http://www.w3.org/2005/Atom'>
<title>kernel/git/next/linux-next.git/drivers/ntb/test, branch akpm</title>
<subtitle>The linux-next integration testing tree</subtitle>
<id>https://git.rulkc.org/pub/scm/linux/kernel/git/next/linux-next.git/atom?h=akpm</id>
<link rel='self' href='https://git.rulkc.org/pub/scm/linux/kernel/git/next/linux-next.git/atom?h=akpm'/>
<link rel='alternate' type='text/html' href='https://git.rulkc.org/pub/scm/linux/kernel/git/next/linux-next.git/'/>
<updated>2022-06-27T16:30:06+00:00</updated>
<entry>
<title>drivers/ntb/test: avoid 64-bit modulus operation</title>
<updated>2022-06-27T16:30:06+00:00</updated>
<author>
<name>Max Filippov</name>
<email>jcmvbkbc@gmail.com</email>
</author>
<published>2022-06-27T15:57:10+00:00</published>
<link rel='alternate' type='text/html' href='https://git.rulkc.org/pub/scm/linux/kernel/git/next/linux-next.git/commit/?id=9297e01b038b5932590f4bebda0361d210432ee2'/>
<id>urn:sha1:9297e01b038b5932590f4bebda0361d210432ee2</id>
<content type='text'>
Redefine RESCHEDULE_RATIO to a closest power of 2 so that the following
code in the perf_run_latency

	/* Avoid processor soft lock-ups */
	if (!(pthr-&gt;tries % RESCHEDULE_RATIO))
		schedule();

doesn't do 64-bit modulus operation.
This fixes the following build failures on 32-bit architectures visible
in linux-next:

  ERROR: modpost: "__umoddi3" [drivers/ntb/test/ntb_perf.ko] undefined!

Fixes: dc150dfb081f ("ntb_perf: extend with burst latency measurement")
Signed-off-by: Max Filippov &lt;jcmvbkbc@gmail.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</content>
</entry>
<entry>
<title>ntb_perf: extend with doorbell latency measurement</title>
<updated>2022-06-20T13:16:40+00:00</updated>
<author>
<name>Alexander Fomichev</name>
<email>a.fomichev@yadro.com</email>
</author>
<published>2022-05-13T19:37:04+00:00</published>
<link rel='alternate' type='text/html' href='https://git.rulkc.org/pub/scm/linux/kernel/git/next/linux-next.git/commit/?id=d3b4b9c2142ca288f81a373841989f592f138934'/>
<id>urn:sha1:d3b4b9c2142ca288f81a373841989f592f138934</id>
<content type='text'>
Doorbell latency is a delay between start to ring an NTB doorbell
and receiving the confirmation. The remote system needs to be run in server
mode beforehand. Then the server waits for a doorbell event and immediately
rings self doorbell to confirm.

Thanks-to: Guo Zhengkui &lt;guozhengkui@vivo.com&gt;
Signed-off-by: Alexander Fomichev &lt;a.fomichev@yadro.com&gt;
Reviewed-by: Dave Jiang &lt;dave.jiang@intel.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</content>
</entry>
<entry>
<title>ntb_perf: extend with poll latency measurement</title>
<updated>2022-06-20T13:16:36+00:00</updated>
<author>
<name>Alexander Fomichev</name>
<email>a.fomichev@yadro.com</email>
</author>
<published>2022-05-13T19:37:03+00:00</published>
<link rel='alternate' type='text/html' href='https://git.rulkc.org/pub/scm/linux/kernel/git/next/linux-next.git/commit/?id=9ace38ad4e8adffeb5ac292b8ceb74fb4f564452'/>
<id>urn:sha1:9ace38ad4e8adffeb5ac292b8ceb74fb4f564452</id>
<content type='text'>
Poll latency is a delay between start to send 1 byte to the
remote system and receiving the confirmation. The remote system needs to
be run in server mode beforehand. Then the server polls the input buffer
and on receiving data immediately sends the confirmation back.

Signed-off-by: Alexander Fomichev &lt;a.fomichev@yadro.com&gt;
Reviewed-by: Dave Jiang &lt;dave.jiang@intel.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</content>
</entry>
<entry>
<title>ntb_perf: extend with burst latency measurement</title>
<updated>2022-06-20T13:16:26+00:00</updated>
<author>
<name>Alexander Fomichev</name>
<email>a.fomichev@yadro.com</email>
</author>
<published>2022-05-13T19:37:02+00:00</published>
<link rel='alternate' type='text/html' href='https://git.rulkc.org/pub/scm/linux/kernel/git/next/linux-next.git/commit/?id=dc150dfb081fcd17f8ecfa07d94813e4c445d808'/>
<id>urn:sha1:dc150dfb081fcd17f8ecfa07d94813e4c445d808</id>
<content type='text'>
Burst latency is a delay between start to send 1 byte to the
remote system and hardware readiness to send another byte. The
measurement performed within bandwidth test procedure. The DMA Engine is
off. Data integrity is not checked. This mode can be disabled by
'perf_latency=N' module parameter.

Signed-off-by: Alexander Fomichev &lt;a.fomichev@yadro.com&gt;
Reviewed-by: Dave Jiang &lt;dave.jiang@intel.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</content>
</entry>
<entry>
<title>ntb: ntb_pingpong: remove redundant initialization of variables msg_data and spad_data</title>
<updated>2021-09-05T22:04:46+00:00</updated>
<author>
<name>Colin Ian King</name>
<email>colin.king@canonical.com</email>
</author>
<published>2021-06-09T11:21:28+00:00</published>
<link rel='alternate' type='text/html' href='https://git.rulkc.org/pub/scm/linux/kernel/git/next/linux-next.git/commit/?id=e631548027cae026486300fe93542949df73a87d'/>
<id>urn:sha1:e631548027cae026486300fe93542949df73a87d</id>
<content type='text'>
The variables msg_data and spad_data are being initialized with values
that are never read, they are being updated later on. The initializations
are redundant and can be removed.

Addresses-Coverity: ("Unused value")
Signed-off-by: Colin Ian King &lt;colin.king@canonical.com&gt;
Acked-by: Serge Semin &lt;fancer.lancer@gmail.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</content>
</entry>
<entry>
<title>NTB: perf: Fix an error code in perf_setup_inbuf()</title>
<updated>2021-09-04T22:36:04+00:00</updated>
<author>
<name>Yang Li</name>
<email>yang.lee@linux.alibaba.com</email>
</author>
<published>2021-06-07T08:40:36+00:00</published>
<link rel='alternate' type='text/html' href='https://git.rulkc.org/pub/scm/linux/kernel/git/next/linux-next.git/commit/?id=0097ae5f7af5684f961a5f803ff7ad3e6f933668'/>
<id>urn:sha1:0097ae5f7af5684f961a5f803ff7ad3e6f933668</id>
<content type='text'>
When the function IS_ALIGNED() returns false, the value of ret is 0.
So, we set ret to -EINVAL to indicate this error.

Clean up smatch warning:
drivers/ntb/test/ntb_perf.c:602 perf_setup_inbuf() warn: missing error
code 'ret'.

Reported-by: Abaci Robot &lt;abaci@linux.alibaba.com&gt;
Signed-off-by: Yang Li &lt;yang.lee@linux.alibaba.com&gt;
Reviewed-by: Serge Semin &lt;fancer.lancer@gmail.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</content>
</entry>
<entry>
<title>NTB: Fix an error code in ntb_msit_probe()</title>
<updated>2021-09-04T22:36:04+00:00</updated>
<author>
<name>Yang Li</name>
<email>yang.lee@linux.alibaba.com</email>
</author>
<published>2021-06-07T05:56:20+00:00</published>
<link rel='alternate' type='text/html' href='https://git.rulkc.org/pub/scm/linux/kernel/git/next/linux-next.git/commit/?id=319f83ac98d7afaabab84ce5281a819a358b9895'/>
<id>urn:sha1:319f83ac98d7afaabab84ce5281a819a358b9895</id>
<content type='text'>
When the value of nm-&gt;isr_ctx is false, the value of ret is 0.
So, we set ret to -ENOMEM to indicate this error.

Clean up smatch warning:
drivers/ntb/test/ntb_msi_test.c:373 ntb_msit_probe() warn: missing
error code 'ret'.

Reported-by: Abaci Robot &lt;abaci@linux.alibaba.com&gt;
Signed-off-by: Yang Li &lt;yang.lee@linux.alibaba.com&gt;
Reviewed-by: Logan Gunthorpe &lt;logang@deltatee.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</content>
</entry>
<entry>
<title>NTB: Use struct_size() helper in devm_kzalloc()</title>
<updated>2020-08-24T14:58:06+00:00</updated>
<author>
<name>Gustavo A. R. Silva</name>
<email>gustavoars@kernel.org</email>
</author>
<published>2020-06-19T17:25:14+00:00</published>
<link rel='alternate' type='text/html' href='https://git.rulkc.org/pub/scm/linux/kernel/git/next/linux-next.git/commit/?id=b8e2c8bbdf7778c6e3c65db21ababb1dfa794282'/>
<id>urn:sha1:b8e2c8bbdf7778c6e3c65db21ababb1dfa794282</id>
<content type='text'>
Make use of the struct_size() helper instead of an open-coded version
in order to avoid any potential type mistakes. Also, remove unnecessary
variable _struct_size_.

This code was detected with the help of Coccinelle and, audited and
fixed manually.

Addresses-KSPP-ID: https://github.com/KSPP/linux/issues/83
Signed-off-by: Gustavo A. R. Silva &lt;gustavoars@kernel.org&gt;
Reviewed-by: Logan Gunthorpe &lt;logang@deltatee.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</content>
</entry>
<entry>
<title>NTB: perf: Fix race condition when run with ntb_test</title>
<updated>2020-06-06T00:02:09+00:00</updated>
<author>
<name>Logan Gunthorpe</name>
<email>logang@deltatee.com</email>
</author>
<published>2019-01-09T19:22:32+00:00</published>
<link rel='alternate' type='text/html' href='https://git.rulkc.org/pub/scm/linux/kernel/git/next/linux-next.git/commit/?id=34d8673a01b053b6231a995a4eec9341163d63be'/>
<id>urn:sha1:34d8673a01b053b6231a995a4eec9341163d63be</id>
<content type='text'>
When running ntb_test, the script tries to run the ntb_perf test
immediately after probing the modules. Since adding multi-port support,
this fails seeing the new initialization procedure in ntb_perf
can not complete instantly.

To fix this we add a completion which is waited on when a test is
started. In this way, run can be written any time after the module is
loaded and it will wait for the initialization to complete instead of
sending an error.

Fixes: 5648e56d03fa ("NTB: ntb_perf: Add full multi-port NTB API support")
Signed-off-by: Logan Gunthorpe &lt;logang@deltatee.com&gt;
Acked-by: Allen Hubbe &lt;allenbh@gmail.com&gt;
Tested-by: Alexander Fomichev &lt;fomichev.ru@gmail.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</content>
</entry>
<entry>
<title>NTB: perf: Fix support for hardware that doesn't have port numbers</title>
<updated>2020-06-06T00:02:09+00:00</updated>
<author>
<name>Logan Gunthorpe</name>
<email>logang@deltatee.com</email>
</author>
<published>2019-01-09T19:22:31+00:00</published>
<link rel='alternate' type='text/html' href='https://git.rulkc.org/pub/scm/linux/kernel/git/next/linux-next.git/commit/?id=b54369a248c2e033bfcf5d6917e08cf9d73d54a6'/>
<id>urn:sha1:b54369a248c2e033bfcf5d6917e08cf9d73d54a6</id>
<content type='text'>
Legacy drivers do not have port numbers (but is reliably only two ports)
and was broken by the recent commit that added mult-port support to
ntb_perf. This is especially important to support the cross link
topology which is perfectly symmetric and cannot assign unique port
numbers easily.

Hardware that returns zero for both the local port and the peer should
just always use gidx=0 for the only peer.

Fixes: 5648e56d03fa ("NTB: ntb_perf: Add full multi-port NTB API support")
Signed-off-by: Logan Gunthorpe &lt;logang@deltatee.com&gt;
Acked-by: Allen Hubbe &lt;allenbh@gmail.com&gt;
Tested-by: Alexander Fomichev &lt;fomichev.ru@gmail.com&gt;
Signed-off-by: Jon Mason &lt;jdmason@kudzu.us&gt;
</content>
</entry>
</feed>
