<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux-dev/drivers/misc/habanalabs/goya, branch master</title>
<subtitle>Linux kernel development work - see feature branches</subtitle>
<id>https://git.zx2c4.com/linux-dev/atom/drivers/misc/habanalabs/goya?h=master</id>
<link rel='self' href='https://git.zx2c4.com/linux-dev/atom/drivers/misc/habanalabs/goya?h=master'/>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/'/>
<updated>2022-09-19T12:08:37Z</updated>
<entry>
<title>habanalabs: send device active message to f/w</title>
<updated>2022-09-19T12:08:37Z</updated>
<author>
<name>farah kassabri</name>
<email>fkassabri@habana.ai</email>
</author>
<published>2022-08-17T14:43:43Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=4745b2f0d0d4b291ec69619c815f53fd8a968d9a'/>
<id>urn:sha1:4745b2f0d0d4b291ec69619c815f53fd8a968d9a</id>
<content type='text'>
As part of the RAS that is done by the f/w, we should send a message
to the f/w when a user either acquires or releases the device.

Signed-off-by: farah kassabri &lt;fkassabri@habana.ai&gt;
Reviewed-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
Signed-off-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
</content>
</entry>
<entry>
<title>habanalabs: perform context switch flow only if needed</title>
<updated>2022-09-18T10:29:53Z</updated>
<author>
<name>Ofir Bitton</name>
<email>obitton@habana.ai</email>
</author>
<published>2022-08-22T07:59:34Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=c38f72370b615d48c7eb44389b229105f07a70e2'/>
<id>urn:sha1:c38f72370b615d48c7eb44389b229105f07a70e2</id>
<content type='text'>
Except Goya, none of our ASICs require context switch flow, hence we
enable this flow only where it is needed.

Signed-off-by: Ofir Bitton &lt;obitton@habana.ai&gt;
Reviewed-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
Signed-off-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
</content>
</entry>
<entry>
<title>habanalabs: unify hwmon resources clean up</title>
<updated>2022-09-18T10:29:51Z</updated>
<author>
<name>Dani Liberman</name>
<email>dliberman@habana.ai</email>
</author>
<published>2022-06-27T19:06:51Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=07ecaa0d85decb73a2907a4b419cfa7739517d5e'/>
<id>urn:sha1:07ecaa0d85decb73a2907a4b419cfa7739517d5e</id>
<content type='text'>
Since hwmon fini code is common for all asics, unified it to common
function.

Signed-off-by: Dani Liberman &lt;dliberman@habana.ai&gt;
Reviewed-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
Signed-off-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
</content>
</entry>
<entry>
<title>habanalabs: remove all kdma locks</title>
<updated>2022-09-18T10:29:50Z</updated>
<author>
<name>Oded Gabbay</name>
<email>ogabbay@kernel.org</email>
</author>
<published>2022-07-19T09:16:01Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=5f92c1e2961912e2a7a10d8e7b998b7cd9dd1d0e'/>
<id>urn:sha1:5f92c1e2961912e2a7a10d8e7b998b7cd9dd1d0e</id>
<content type='text'>
We don't use KDMA concurrently in the driver. The only use is through
debugfs and we don't protect concurrent access through it.

Reported-by: Dan Carpenter &lt;dan.carpenter@oracle.com&gt;
Signed-off-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
</content>
</entry>
<entry>
<title>habanalabs: rename non_hard_reset to compute_reset</title>
<updated>2022-09-18T10:29:49Z</updated>
<author>
<name>Ofir Bitton</name>
<email>obitton@habana.ai</email>
</author>
<published>2022-07-13T12:08:09Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=bc9b271e6c92b5f3bfe25f73b11e8e878f386075'/>
<id>urn:sha1:bc9b271e6c92b5f3bfe25f73b11e8e878f386075</id>
<content type='text'>
In order to be more explicit we should use the term compute_reset
for describing the reset in which only the compute engines gets
reset.

Signed-off-by: Ofir Bitton &lt;obitton@habana.ai&gt;
Reviewed-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
Signed-off-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
</content>
</entry>
<entry>
<title>habanalabs: removed seq_file parameter from is_idle asic functions</title>
<updated>2022-09-18T10:29:49Z</updated>
<author>
<name>Dani Liberman</name>
<email>dliberman@habana.ai</email>
</author>
<published>2022-07-03T14:40:57Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=71386e11f262f5fc66000c0d83b4fd8cbbaf9d38'/>
<id>urn:sha1:71386e11f262f5fc66000c0d83b4fd8cbbaf9d38</id>
<content type='text'>
Change is_idle functions so it would be more usable outside debugfs.

Do this by replacing seq_file parameter with regular string.

Signed-off-by: Dani Liberman &lt;dliberman@habana.ai&gt;
Reviewed-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
Signed-off-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
</content>
</entry>
<entry>
<title>habanalabs: move h/w dirty message to debug</title>
<updated>2022-07-12T06:09:31Z</updated>
<author>
<name>Oded Gabbay</name>
<email>ogabbay@kernel.org</email>
</author>
<published>2022-07-10T11:14:04Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=a919b823abba8cb84bb99e007ea8a01ed9f5410a'/>
<id>urn:sha1:a919b823abba8cb84bb99e007ea8a01ed9f5410a</id>
<content type='text'>
H/W being dirty during initialization is completely expected in case
f/w tools are used before loading the driver. As it is not an error,
and as it doesn't give any meaningful information to the user,
no point of printing it.

Signed-off-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
</content>
</entry>
<entry>
<title>habanalabs: rename soft reset to compute reset</title>
<updated>2022-07-12T06:09:31Z</updated>
<author>
<name>Oded Gabbay</name>
<email>ogabbay@kernel.org</email>
</author>
<published>2022-07-07T09:00:24Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=0b0ae024402954d3547ac187cac5e3c6884571f4'/>
<id>urn:sha1:0b0ae024402954d3547ac187cac5e3c6884571f4</id>
<content type='text'>
Doing compute reset can be the traditional inference soft reset
that is supported only in Goya.

Or it can be the new reset upon device release, which is supported
in Gaudi2 and above.

Therefore, wherever suitable, use the terminology of compute reset
instead of soft reset.

Signed-off-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
</content>
</entry>
<entry>
<title>habanalabs: add a value field to hl_fw_send_pci_access_msg()</title>
<updated>2022-07-12T06:09:30Z</updated>
<author>
<name>Tomer Tayar</name>
<email>ttayar@habana.ai</email>
</author>
<published>2022-07-06T07:20:54Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=af2e650b36a9a0c0e127dde20c394cbbf318e729'/>
<id>urn:sha1:af2e650b36a9a0c0e127dde20c394cbbf318e729</id>
<content type='text'>
For gaudi2 we need to send a value to F/W as part of the
PCI_ACCESS packet.
As a preparation, modify hl_fw_send_pci_access_msg() to have a 'value'
field.

Signed-off-by: Tomer Tayar &lt;ttayar@habana.ai&gt;
Reviewed-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
Signed-off-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
</content>
</entry>
<entry>
<title>habanalabs: wait for preboot ready after hard reset</title>
<updated>2022-07-12T06:09:28Z</updated>
<author>
<name>Ohad Sharabi</name>
<email>osharabi@habana.ai</email>
</author>
<published>2022-06-28T09:09:21Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=2b9e583d0aadcf6578e2595c07d3b1e898013d17'/>
<id>urn:sha1:2b9e583d0aadcf6578e2595c07d3b1e898013d17</id>
<content type='text'>
Currently we are not waiting for preboot ready after hard reset.
This leads to a race in which COMMs protocol begins but will get no
response from the f/w.

Signed-off-by: Ohad Sharabi &lt;osharabi@habana.ai&gt;
Reviewed-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
Signed-off-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
</content>
</entry>
</feed>
