<feed xmlns='http://www.w3.org/2005/Atom'>
<title>src/sys/dev/nvme, branch releng/12.2</title>
<subtitle>FreeBSD source tree</subtitle>
<id>https://cgit-dev.freebsd.org/src/atom?h=releng%2F12.2</id>
<link rel='self' href='https://cgit-dev.freebsd.org/src/atom?h=releng%2F12.2'/>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/'/>
<updated>2020-09-28T00:53:45Z</updated>
<entry>
<title>MFS r366179: Make nvmecontrol work with nda like it does with nvd, and</title>
<updated>2020-09-28T00:53:45Z</updated>
<author>
<name>Colin Percival</name>
<email>cperciva@FreeBSD.org</email>
</author>
<published>2020-09-28T00:53:45Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=88afe3774d72804d7cb88f554ba3b5cda371b2ee'/>
<id>urn:sha1:88afe3774d72804d7cb88f554ba3b5cda371b2ee</id>
<content type='text'>
associated bits.

Approved by:	re (delphij)
Sponsored by:	https://www.patreon.com/cperciva
</content>
</entry>
<entry>
<title>MFC r362630: Fix few panics on NVMe's timing out initialization requests.</title>
<updated>2020-07-02T01:02:40Z</updated>
<author>
<name>Alexander Motin</name>
<email>mav@FreeBSD.org</email>
</author>
<published>2020-07-02T01:02:40Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=8e9f86cc2db73350c4bdbecadd86e3f636b2a157'/>
<id>urn:sha1:8e9f86cc2db73350c4bdbecadd86e3f636b2a157</id>
<content type='text'>
</content>
</entry>
<entry>
<title>MFC r362337: Make polled request timeout less invasive.</title>
<updated>2020-06-24T13:49:30Z</updated>
<author>
<name>Alexander Motin</name>
<email>mav@FreeBSD.org</email>
</author>
<published>2020-06-24T13:49:30Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=fbe54dc6b759d148a3b28935915e38e4f9e0d370'/>
<id>urn:sha1:fbe54dc6b759d148a3b28935915e38e4f9e0d370</id>
<content type='text'>
Instead of panic after one second of polling, make the normal timeout
handler to activate, reset the controller and abort the outstanding
requests.  If all of it won't happen within 10 seconds then something
in the driver is likely stuck bad and panic is the only way out.

In particular this fixed device hot unplug during execution of those
polled commands, allowing clean device detach instead of panic.
</content>
</entry>
<entry>
<title>MFC r362282: Fix admin qpair leak if detached during initial reset.</title>
<updated>2020-06-24T13:48:16Z</updated>
<author>
<name>Alexander Motin</name>
<email>mav@FreeBSD.org</email>
</author>
<published>2020-06-24T13:48:16Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=7dee70cb4b61555c329a4c47c7c4c061605164c4'/>
<id>urn:sha1:7dee70cb4b61555c329a4c47c7c4c061605164c4</id>
<content type='text'>
</content>
</entry>
<entry>
<title>MFC r362100: Fix config_intrhook leak on initial reset failure.</title>
<updated>2020-06-19T00:45:29Z</updated>
<author>
<name>Alexander Motin</name>
<email>mav@FreeBSD.org</email>
</author>
<published>2020-06-19T00:45:29Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=8ffd0d1181740e9d78b6bcce794a2a21c73030e8'/>
<id>urn:sha1:8ffd0d1181740e9d78b6bcce794a2a21c73030e8</id>
<content type='text'>
</content>
</entry>
<entry>
<title>MFC r360504 (by imp): Style(9) nit: put function name at start of line.</title>
<updated>2020-06-18T20:25:42Z</updated>
<author>
<name>Alexander Motin</name>
<email>mav@FreeBSD.org</email>
</author>
<published>2020-06-18T20:25:42Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=f6feee5020003fb50389244c55630abf4fae7d60'/>
<id>urn:sha1:f6feee5020003fb50389244c55630abf4fae7d60</id>
<content type='text'>
</content>
</entry>
<entry>
<title>MFC r360503 (by imp): Move / reword a comment.</title>
<updated>2020-06-18T20:23:46Z</updated>
<author>
<name>Alexander Motin</name>
<email>mav@FreeBSD.org</email>
</author>
<published>2020-06-18T20:23:46Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=871703f478320d59b58d335b8d5c4af36dff314d'/>
<id>urn:sha1:871703f478320d59b58d335b8d5c4af36dff314d</id>
<content type='text'>
Explain what we're doing with mapping CAM's notion of a LUN to NVMe's
notion of a namespace.
</content>
</entry>
<entry>
<title>MFC r360568:</title>
<updated>2020-05-14T12:52:08Z</updated>
<author>
<name>David Bright</name>
<email>dab@FreeBSD.org</email>
</author>
<published>2020-05-14T12:52:08Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=561d716baea2f7aac3ce52d732b92ffe44f08370'/>
<id>urn:sha1:561d716baea2f7aac3ce52d732b92ffe44f08370</id>
<content type='text'>
Fix various Coverity-detected errors in nvme driver

This fixes several Coverity-detected errors in the nvme driver.

CIDs addressed: 1008344, 1009377, 1009380, 1193740, 1305470, 1403975,
1403980

Sponsored by:	Dell EMC Isilon
</content>
</entry>
<entry>
<title>MFC r356474, r356480, r356482, r356506:</title>
<updated>2020-01-22T01:08:27Z</updated>
<author>
<name>Alexander Motin</name>
<email>mav@FreeBSD.org</email>
</author>
<published>2020-01-22T01:08:27Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=0b4a11a999d80604c63d5f55b1a73ce4c44c261b'/>
<id>urn:sha1:0b4a11a999d80604c63d5f55b1a73ce4c44c261b</id>
<content type='text'>
Add Host Memory Buffer support to nvme(4).

This allows cheapest DRAM-less NVMe SSDs to use some of host RAM (about
1MB per 1GB on the devices I have) for its metadata cache, significantly
improving random I/O performance.  Device reports minimal and preferable
size of the buffer.  The code limits it to 5% of physical RAM by default.
If the buffer can not be allocated or below minimal size, the device will
just have to work without it.
</content>
</entry>
<entry>
<title>MFC r355774 (by mmel): Properly synchronize completion DMA buffers.</title>
<updated>2020-01-22T00:48:54Z</updated>
<author>
<name>Alexander Motin</name>
<email>mav@FreeBSD.org</email>
</author>
<published>2020-01-22T00:48:54Z</published>
<link rel='alternate' type='text/html' href='https://cgit-dev.freebsd.org/src/commit/?id=5b5fbdc00c86f7a2c5c184839247f572b741d9c1'/>
<id>urn:sha1:5b5fbdc00c86f7a2c5c184839247f572b741d9c1</id>
<content type='text'>
Within command completion processing the callback function may access
DMAed data buffer. Synchronize it before use, not after.
This allows to use NVMe disk on non-DMA coherent arm64 system.
</content>
</entry>
</feed>
