<feed xmlns='http://www.w3.org/2005/Atom'>
<title>src/sys/dev/mlx4/mlx4_core, branch main</title>
<subtitle>FreeBSD source tree</subtitle>
<link rel='alternate' type='text/html' href='http://cgit.freebsd.org/src/'/>
<entry>
<title>mlx(4): Fix a typo in a source code comment</title>
<updated>2026-02-08T12:01:27+00:00</updated>
<author>
<name>Gordon Bergling</name>
<email>gbe@FreeBSD.org</email>
</author>
<published>2026-02-08T12:01:27+00:00</published>
<link rel='alternate' type='text/html' href='http://cgit.freebsd.org/src/commit/?id=3e46676638ac089c71e8424961449895c0babcfb'/>
<id>3e46676638ac089c71e8424961449895c0babcfb</id>
<content type='text'>
- s/segements/segments/

MFC after:	3 days
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
- s/segements/segments/

MFC after:	3 days
</pre>
</div>
</content>
</entry>
<entry>
<title>mlx4ib(4): Fix some typos in device messages</title>
<updated>2025-02-05T10:31:12+00:00</updated>
<author>
<name>Gordon Bergling</name>
<email>gbe@FreeBSD.org</email>
</author>
<published>2025-02-05T10:31:12+00:00</published>
<link rel='alternate' type='text/html' href='http://cgit.freebsd.org/src/commit/?id=84e3ffac12a8dcfeae0a5e0b25afe447ff2d5fa8'/>
<id>84e3ffac12a8dcfeae0a5e0b25afe447ff2d5fa8</id>
<content type='text'>
- s/availible/available/

MFC after:	5 days
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
- s/availible/available/

MFC after:	5 days
</pre>
</div>
</content>
</entry>
<entry>
<title>mlx4: use is_power_of_2</title>
<updated>2024-09-28T21:23:17+00:00</updated>
<author>
<name>Doug Moore</name>
<email>dougm@FreeBSD.org</email>
</author>
<published>2024-09-28T21:23:17+00:00</published>
<link rel='alternate' type='text/html' href='http://cgit.freebsd.org/src/commit/?id=3873b9a8b3a51731e5db92ab0c5c59797e416015'/>
<id>3873b9a8b3a51731e5db92ab0c5c59797e416015</id>
<content type='text'>
It's faster to use is_power_of_2 than it is to compute
roundup_power_of_two and then compare.  So do that.

Reviewed by:	kib
Differential Revision:	https://reviews.freebsd.org/D46838
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
It's faster to use is_power_of_2 than it is to compute
roundup_power_of_two and then compare.  So do that.

Reviewed by:	kib
Differential Revision:	https://reviews.freebsd.org/D46838
</pre>
</div>
</content>
</entry>
<entry>
<title>mlx4en(4): add missing newline to debug messages</title>
<updated>2023-06-18T04:14:41+00:00</updated>
<author>
<name>Kevin Lo</name>
<email>kevlo@FreeBSD.org</email>
</author>
<published>2023-06-18T04:14:41+00:00</published>
<link rel='alternate' type='text/html' href='http://cgit.freebsd.org/src/commit/?id=4d5842c020a0d3ef64e34ce8f3a00d8dcb550bfa'/>
<id>4d5842c020a0d3ef64e34ce8f3a00d8dcb550bfa</id>
<content type='text'>
Add newline to debug messages after dumping uar_page_shift and reserved_uars.

Reviewed by:	hselasky
MFC after:	1 week
Differential Revision:	https://reviews.freebsd.org/D40582
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Add newline to debug messages after dumping uar_page_shift and reserved_uars.

Reviewed by:	hselasky
MFC after:	1 week
Differential Revision:	https://reviews.freebsd.org/D40582
</pre>
</div>
</content>
</entry>
<entry>
<title>Revert "mlx4: Move DEFINE_MUTEX() outside function body."</title>
<updated>2023-05-22T10:53:38+00:00</updated>
<author>
<name>Hans Petter Selasky</name>
<email>hselasky@FreeBSD.org</email>
</author>
<published>2023-05-22T10:52:10+00:00</published>
<link rel='alternate' type='text/html' href='http://cgit.freebsd.org/src/commit/?id=47c887be4af7553a3fae05009516a904dfa2617e'/>
<id>47c887be4af7553a3fae05009516a904dfa2617e</id>
<content type='text'>
Requested by:	jrtc27@

This reverts commit 805d759338a2be939fffc8bf3f25cfaab981a9be.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Requested by:	jrtc27@

This reverts commit 805d759338a2be939fffc8bf3f25cfaab981a9be.
</pre>
</div>
</content>
</entry>
<entry>
<title>mlx4: Move DEFINE_MUTEX() outside function body.</title>
<updated>2023-05-21T16:20:16+00:00</updated>
<author>
<name>Hans Petter Selasky</name>
<email>hselasky@FreeBSD.org</email>
</author>
<published>2023-05-21T11:25:28+00:00</published>
<link rel='alternate' type='text/html' href='http://cgit.freebsd.org/src/commit/?id=805d759338a2be939fffc8bf3f25cfaab981a9be'/>
<id>805d759338a2be939fffc8bf3f25cfaab981a9be</id>
<content type='text'>
Move static mutex declaration outside function body, to avoid global
variables being declared on the stack, when using SYSINITs.

MFC after:	1 week
Sponsored by:	NVIDIA Networking
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Move static mutex declaration outside function body, to avoid global
variables being declared on the stack, when using SYSINITs.

MFC after:	1 week
Sponsored by:	NVIDIA Networking
</pre>
</div>
</content>
</entry>
<entry>
<title>mlx4core: Use-after-free causes a resource leak in flow-steering detach</title>
<updated>2022-06-07T14:28:32+00:00</updated>
<author>
<name>Hans Petter Selasky</name>
<email>hselasky@FreeBSD.org</email>
</author>
<published>2022-06-07T14:27:53+00:00</published>
<link rel='alternate' type='text/html' href='http://cgit.freebsd.org/src/commit/?id=dd2a8c8f72d369440c36f10512324d42ecedb5c7'/>
<id>dd2a8c8f72d369440c36f10512324d42ecedb5c7</id>
<content type='text'>
mlx4_QP_FLOW_STEERING_DETACH_wrapper first removes the steering
rule (which results in freeing the rule structure), and then
references a field in this struct (the qp number) when releasing the
busy-status on the rule's qp.

Since this memory was freed, it could reallocated and changed.
Therefore, the qp number in the struct may be incorrect,
so that we are releasing the incorrect qp. This leaves the rule's qp
in the busy state (and could possibly release an incorrect qp as well).

Fix this by saving the qp number in a local variable, for use after
removing the steering rule.

Linux commit:
3b01fe7f91c8e4f9afc4fae3c5af72c14958d2d8

PR:	     	264469
MFC after:	1 week
Sponsored by:	NVIDIA Networking
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
mlx4_QP_FLOW_STEERING_DETACH_wrapper first removes the steering
rule (which results in freeing the rule structure), and then
references a field in this struct (the qp number) when releasing the
busy-status on the rule's qp.

Since this memory was freed, it could reallocated and changed.
Therefore, the qp number in the struct may be incorrect,
so that we are releasing the incorrect qp. This leaves the rule's qp
in the busy state (and could possibly release an incorrect qp as well).

Fix this by saving the qp number in a local variable, for use after
removing the steering rule.

Linux commit:
3b01fe7f91c8e4f9afc4fae3c5af72c14958d2d8

PR:	     	264469
MFC after:	1 week
Sponsored by:	NVIDIA Networking
</pre>
</div>
</content>
</entry>
<entry>
<title>mlx4core: Fix a memory leak when deleting slave's resources</title>
<updated>2022-05-30T18:22:18+00:00</updated>
<author>
<name>Hans Petter Selasky</name>
<email>hselasky@FreeBSD.org</email>
</author>
<published>2022-05-30T18:11:50+00:00</published>
<link rel='alternate' type='text/html' href='http://cgit.freebsd.org/src/commit/?id=f29c9901a41fb650d46fd48f4880a894f54aa737'/>
<id>f29c9901a41fb650d46fd48f4880a894f54aa737</id>
<content type='text'>
mlx4_delete_all_resources_for_slave() in the resource tracker should free
all memory allocated for a slave. While releasing memory of fs_rule,
it misses releasing memory of fs_rule-&gt;mirr_mbox.

Linux commit:
461d5f1b59490ce0096dfda45e10038c122a7892

PR:		264249
MFC after:	1 week
Sponsored by:	NVIDIA Networking
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
mlx4_delete_all_resources_for_slave() in the resource tracker should free
all memory allocated for a slave. While releasing memory of fs_rule,
it misses releasing memory of fs_rule-&gt;mirr_mbox.

Linux commit:
461d5f1b59490ce0096dfda45e10038c122a7892

PR:		264249
MFC after:	1 week
Sponsored by:	NVIDIA Networking
</pre>
</div>
</content>
</entry>
<entry>
<title>mlx4: Fix a memory leak bug.</title>
<updated>2022-05-19T08:13:06+00:00</updated>
<author>
<name>Hans Petter Selasky</name>
<email>hselasky@FreeBSD.org</email>
</author>
<published>2022-05-19T08:10:48+00:00</published>
<link rel='alternate' type='text/html' href='http://cgit.freebsd.org/src/commit/?id=527762b2f776381569bd662ce236d2845234c0a7'/>
<id>527762b2f776381569bd662ce236d2845234c0a7</id>
<content type='text'>
In function mlx4_opreq_action(), pointer "mailbox" is not released,
when mlx4_cmd_box() return and error, causing a memory leak bug.
Fix this issue by going to "out" label, mlx4_free_cmd_mailbox() can
free this pointer.

Linux commit:
febfd9d3c7f74063e8e630b15413ca91b567f963

PR:		264056
MFC after:	1 week
Sponsored by:	NVIDIA Networking
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
In function mlx4_opreq_action(), pointer "mailbox" is not released,
when mlx4_cmd_box() return and error, causing a memory leak bug.
Fix this issue by going to "out" label, mlx4_free_cmd_mailbox() can
free this pointer.

Linux commit:
febfd9d3c7f74063e8e630b15413ca91b567f963

PR:		264056
MFC after:	1 week
Sponsored by:	NVIDIA Networking
</pre>
</div>
</content>
</entry>
<entry>
<title>mlx4: Remove a variable only used in commented-out code.</title>
<updated>2022-04-09T00:25:13+00:00</updated>
<author>
<name>John Baldwin</name>
<email>jhb@FreeBSD.org</email>
</author>
<published>2022-04-09T00:25:13+00:00</published>
<link rel='alternate' type='text/html' href='http://cgit.freebsd.org/src/commit/?id=516243545e72684b2281b1a8c14b2870a306f6d1'/>
<id>516243545e72684b2281b1a8c14b2870a306f6d1</id>
<content type='text'>
Reviewed by:	hselasky
Differential Revision:	https://reviews.freebsd.org/D34825
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Reviewed by:	hselasky
Differential Revision:	https://reviews.freebsd.org/D34825
</pre>
</div>
</content>
</entry>
</feed>
