<feed xmlns='http://www.w3.org/2005/Atom'>
<title>user/sven/linux.git/drivers/accel, branch v6.8.6</title>
<subtitle>Linux Kernel
</subtitle>
<id>https://git.stealer.net/cgit.cgi/user/sven/linux.git/atom?h=v6.8.6</id>
<link rel='self' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/atom?h=v6.8.6'/>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/'/>
<updated>2024-04-13T11:10:06Z</updated>
<entry>
<title>accel/habanalabs: increase HL_MAX_STR to 64 bytes to avoid warnings</title>
<updated>2024-04-13T11:10:06Z</updated>
<author>
<name>Koby Elbaz</name>
<email>kelbaz@habana.ai</email>
</author>
<published>2023-12-11T08:03:29Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/commit/?id=88d6a73fc19cb823a5793f069e5eb7e67766bedb'/>
<id>urn:sha1:88d6a73fc19cb823a5793f069e5eb7e67766bedb</id>
<content type='text'>
[ Upstream commit 8c075401f2dbda43600c61f780a165abde77877a ]

Fix a warning of a buffer overflow:
‘snprintf’ output between 38 and 47 bytes into a destination of size 32

Signed-off-by: Koby Elbaz &lt;kelbaz@habana.ai&gt;
Reviewed-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
Signed-off-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
Signed-off-by: Sasha Levin &lt;sashal@kernel.org&gt;
</content>
</entry>
<entry>
<title>accel/ivpu: Don't enable any tiles by default on VPU40xx</title>
<updated>2024-02-20T15:56:21Z</updated>
<author>
<name>Andrzej Kacprowski</name>
<email>Andrzej.Kacprowski@intel.com</email>
</author>
<published>2024-02-20T13:16:24Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/commit/?id=eb0d253ff9c74dee30aa92fe460b825eb28acd73'/>
<id>urn:sha1:eb0d253ff9c74dee30aa92fe460b825eb28acd73</id>
<content type='text'>
There is no point in requesting 1 tile on VPU40xx as the FW will
probably need more tiles to run workloads, so it will have to
reconfigure PLL anyway. Don't enable any tiles and allow the FW to
perform initial tile configuration.

This improves NPU boot stability as the tiles are always enabled only
by the FW from the same initial state.

Fixes: 79cdc56c4a54 ("accel/ivpu: Add initial support for VPU 4")
Cc: stable@vger.kernel.org
Signed-off-by: Andrzej Kacprowski &lt;Andrzej.Kacprowski@intel.com&gt;
Signed-off-by: Jacek Lawrynowicz &lt;jacek.lawrynowicz@linux.intel.com&gt;
Reviewed-by: Jeffrey Hugo &lt;quic_jhugo@quicinc.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20240220131624.1447813-1-jacek.lawrynowicz@linux.intel.com
</content>
</entry>
<entry>
<title>accel/ivpu: Fix DevTLB errors on suspend/resume and recovery</title>
<updated>2024-02-12T08:00:44Z</updated>
<author>
<name>Jacek Lawrynowicz</name>
<email>jacek.lawrynowicz@linux.intel.com</email>
</author>
<published>2024-02-07T10:24:46Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/commit/?id=28083ff18d3f65ecd64857f4495623135dd1f132'/>
<id>urn:sha1:28083ff18d3f65ecd64857f4495623135dd1f132</id>
<content type='text'>
Issue IP reset before shutdown in order to
complete all upstream requests to the SOC.
Without this DevTLB is complaining about
incomplete transactions and NPU cannot resume from
suspend.
This problem is only happening on recent IFWI
releases.

IP reset in rare corner cases can mess up PCI
configuration, so save it before the reset.
After this happens it is also impossible to
issue PLL requests and D0-&gt;D3-&gt;D0 cycle is needed
to recover the NPU. Add WP 0 request on power up,
so the PUNIT is always notified about NPU reset.

Use D0/D3 cycle for recovery as it can recover
from failed IP reset and FLR cannot.

Fixes: 3f7c0634926d ("accel/ivpu/37xx: Fix hangs related to MMIO reset")
Signed-off-by: Jacek Lawrynowicz &lt;jacek.lawrynowicz@linux.intel.com&gt;
Reviewed-by: Jeffrey Hugo &lt;quic_jhugo@quicinc.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20240207102446.3126981-1-jacek.lawrynowicz@linux.intel.com
</content>
</entry>
<entry>
<title>accel/ivpu: Add job status for jobs aborted by the driver</title>
<updated>2024-02-06T12:37:34Z</updated>
<author>
<name>Grzegorz Trzebiatowski</name>
<email>grzegorz.trzebiatowski@intel.com</email>
</author>
<published>2024-01-26T12:28:04Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/commit/?id=5f8408aca66772d3aa9b4831577b2ac5ec41bcd9'/>
<id>urn:sha1:5f8408aca66772d3aa9b4831577b2ac5ec41bcd9</id>
<content type='text'>
Add DRM_IVPU_JOB_STATUS_ABORTED to indicate that the job was aborted
by the driver due to e.g. TDR or user context MMU faults.

This will help UMD and tests distinguish if job was aborted by the FW
or the driver.

Signed-off-by: Grzegorz Trzebiatowski &lt;grzegorz.trzebiatowski@intel.com&gt;
Signed-off-by: Jacek Lawrynowicz &lt;jacek.lawrynowicz@linux.intel.com&gt;
Reviewed-by: Jeffrey Hugo &lt;quic_jhugo@quicinc.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-8-jacek.lawrynowicz@linux.intel.com
</content>
</entry>
<entry>
<title>accel/ivpu/40xx: Stop passing SKU boot parameters to FW</title>
<updated>2024-02-06T12:37:34Z</updated>
<author>
<name>Krystian Pradzynski</name>
<email>krystian.pradzynski@intel.com</email>
</author>
<published>2024-01-26T12:28:03Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/commit/?id=553099da45397914a995dce6307d6c26523c2567'/>
<id>urn:sha1:553099da45397914a995dce6307d6c26523c2567</id>
<content type='text'>
This parameter was never used by the 40xx FW.

Signed-off-by: Krystian Pradzynski &lt;krystian.pradzynski@intel.com&gt;
Signed-off-by: Jacek Lawrynowicz &lt;jacek.lawrynowicz@linux.intel.com&gt;
Reviewed-by: Jeffrey Hugo &lt;quic_jhugo@quicinc.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-7-jacek.lawrynowicz@linux.intel.com
</content>
</entry>
<entry>
<title>accel/ivpu/40xx: Enable D0i3 message</title>
<updated>2024-02-06T12:37:20Z</updated>
<author>
<name>Krystian Pradzynski</name>
<email>krystian.pradzynski@intel.com</email>
</author>
<published>2024-01-26T12:28:02Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/commit/?id=a939c03d37788e4a9a645c88d5e5b6a475ba0fd5'/>
<id>urn:sha1:a939c03d37788e4a9a645c88d5e5b6a475ba0fd5</id>
<content type='text'>
All recent 40xx firmware already supports D0i3 entry message and this
WA is no longer needed.

Signed-off-by: Krystian Pradzynski &lt;krystian.pradzynski@intel.com&gt;
Signed-off-by: Jacek Lawrynowicz &lt;jacek.lawrynowicz@linux.intel.com&gt;
Reviewed-by: Jacek Lawrynowicz &lt;jacek.lawrynowicz@linux.intel.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-6-jacek.lawrynowicz@linux.intel.com
</content>
</entry>
<entry>
<title>accel/ivpu: Disable d3hot_delay on all NPU generations</title>
<updated>2024-02-06T12:36:33Z</updated>
<author>
<name>Jacek Lawrynowicz</name>
<email>jacek.lawrynowicz@linux.intel.com</email>
</author>
<published>2024-01-26T12:28:00Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/commit/?id=a7f31091ddf457352e3dd7ac183fdbd26b4dcd04'/>
<id>urn:sha1:a7f31091ddf457352e3dd7ac183fdbd26b4dcd04</id>
<content type='text'>
NPU does not require this delay regardless of the generation.
All generations are integrated into the SOC.

Signed-off-by: Jacek Lawrynowicz &lt;jacek.lawrynowicz@linux.intel.com&gt;
Reviewed-by: Jeffrey Hugo &lt;quic_jhugo@quicinc.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-4-jacek.lawrynowicz@linux.intel.com
</content>
</entry>
<entry>
<title>accel/ivpu: Correct MMU queue size checking functions</title>
<updated>2024-02-06T12:36:33Z</updated>
<author>
<name>Wachowski, Karol</name>
<email>karol.wachowski@intel.com</email>
</author>
<published>2024-01-26T12:27:59Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/commit/?id=b039f1c4d3727c3e44a7e89ff79e7e8533e1beec'/>
<id>urn:sha1:b039f1c4d3727c3e44a7e89ff79e7e8533e1beec</id>
<content type='text'>
Do not use kernel CIRC_SPACE and CIRC_CNT that
incorrectly return space of a queue when wrap bit was set.
Use correct implementation that compares producer, consumer and
wrap bit values.

Without this fix it was possible to lose events in case when event
queue was full.

Signed-off-by: Wachowski, Karol &lt;karol.wachowski@intel.com&gt;
Signed-off-by: Jacek Lawrynowicz &lt;jacek.lawrynowicz@linux.intel.com&gt;
Reviewed-by: Jeffrey Hugo &lt;quic_jhugo@quicinc.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-3-jacek.lawrynowicz@linux.intel.com
</content>
</entry>
<entry>
<title>accel/ivpu: Force snooping for MMU writes</title>
<updated>2024-02-06T12:36:32Z</updated>
<author>
<name>Wachowski, Karol</name>
<email>karol.wachowski@intel.com</email>
</author>
<published>2024-01-26T12:27:58Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/commit/?id=c9da9a1f17bf4fa96b115950fd389c917b583c1c'/>
<id>urn:sha1:c9da9a1f17bf4fa96b115950fd389c917b583c1c</id>
<content type='text'>
Set AW_SNOOP_OVERRIDE bit in VPU_37/40XX_HOST_IF_TCU_PTW_OVERRIDES
to force snooping for MMU write accesses (setting event queue events).

MMU event queue buffer is the only buffer written by MMU and
mapped as write-back which break cache coherency. Force write
transactions to be snooped solving the problem.

Signed-off-by: Wachowski, Karol &lt;karol.wachowski@intel.com&gt;
Signed-off-by: Jacek Lawrynowicz &lt;jacek.lawrynowicz@linux.intel.com&gt;
Reviewed-by: Jeffrey Hugo &lt;quic_jhugo@quicinc.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20240126122804.2169129-2-jacek.lawrynowicz@linux.intel.com
</content>
</entry>
<entry>
<title>accel/ivpu: Improve recovery and reset support</title>
<updated>2024-01-25T09:17:37Z</updated>
<author>
<name>Jacek Lawrynowicz</name>
<email>jacek.lawrynowicz@linux.intel.com</email>
</author>
<published>2024-01-22T12:09:45Z</published>
<link rel='alternate' type='text/html' href='https://git.stealer.net/cgit.cgi/user/sven/linux.git/commit/?id=27d19268cf394f2c78db732be0cb31852eeadb0a'/>
<id>urn:sha1:27d19268cf394f2c78db732be0cb31852eeadb0a</id>
<content type='text'>
  - Synchronize job submission with reset/recovery using reset_lock
  - Always print recovery reason and call diagnose_failure()
  - Don't allow for autosupend during recovery
  - Prevent immediate autosuspend after reset/recovery
  - Prevent force_recovery for issuing TDR when device is suspended
  - Reset VPU instead triggering recovery after changing debugfs params

Signed-off-by: Jacek Lawrynowicz &lt;jacek.lawrynowicz@linux.intel.com&gt;
Reviewed-by: Wachowski, Karol &lt;karol.wachowski@intel.com&gt;
Link: https://patchwork.freedesktop.org/patch/msgid/20240122120945.1150728-4-jacek.lawrynowicz@linux.intel.com
</content>
</entry>
</feed>
