<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux-dev/drivers/misc/habanalabs, branch linus/master</title>
<subtitle>Linux kernel development work - see feature branches</subtitle>
<id>https://git.zx2c4.com/linux-dev/atom/drivers/misc/habanalabs?h=linus%2Fmaster</id>
<link rel='self' href='https://git.zx2c4.com/linux-dev/atom/drivers/misc/habanalabs?h=linus%2Fmaster'/>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/'/>
<updated>2022-05-22T19:01:21Z</updated>
<entry>
<title>habanalabs: use separate structure info for each error collect data</title>
<updated>2022-05-22T19:01:21Z</updated>
<author>
<name>Tal Cohen</name>
<email>talcohen@habana.ai</email>
</author>
<published>2022-05-11T13:50:30Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=90de6805267f8c79cd2b1a36805071e257c39b5c'/>
<id>urn:sha1:90de6805267f8c79cd2b1a36805071e257c39b5c</id>
<content type='text'>
Create separate info structure for each error type.
The structures shall be used inside the large structure that contains
the last session error.
This is more scalable for adding more errors in the future.

Signed-off-by: Tal Cohen &lt;talcohen@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: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
<entry>
<title>habanalabs: fix missing handle shift during mmap</title>
<updated>2022-05-22T19:01:21Z</updated>
<author>
<name>Yuri Nudelman</name>
<email>ynudelman@habana.ai</email>
</author>
<published>2022-05-15T10:46:37Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=f873a27fd50d161111d0e52087af0f5b2111c5c4'/>
<id>urn:sha1:f873a27fd50d161111d0e52087af0f5b2111c5c4</id>
<content type='text'>
During mmap operation on the unified memory manager buffer, the vma
page offset is shifted to extract the handle value. Due to a typo, it
was not shifted back at the end. That could cause the offset to be
modified after mmap operation, that may affect subsequent operations.
In addition, in allocation flow, in case of out of memory error, idr
would not be correctly destroyed, again because of a missing shift.

Signed-off-by: Yuri Nudelman &lt;ynudelman@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: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
<entry>
<title>habanalabs: remove hdev from hl_ctx_get args</title>
<updated>2022-05-22T19:01:21Z</updated>
<author>
<name>Ohad Sharabi</name>
<email>osharabi@habana.ai</email>
</author>
<published>2022-05-11T10:28:39Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=e31dd9362f01682192d80221cc4339e4f7140f30'/>
<id>urn:sha1:e31dd9362f01682192d80221cc4339e4f7140f30</id>
<content type='text'>
This argument is unused by the function.

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;
Signed-off-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
<entry>
<title>habanalabs: do MMU prefetch as deferred work</title>
<updated>2022-05-22T19:01:21Z</updated>
<author>
<name>Ohad Sharabi</name>
<email>osharabi@habana.ai</email>
</author>
<published>2022-04-11T06:31:32Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=9e495e24003eec491141c80a9bd8fb4ea5edc171'/>
<id>urn:sha1:9e495e24003eec491141c80a9bd8fb4ea5edc171</id>
<content type='text'>
When user requests to prefetch the MMU translations, the driver will
not block the user until prefetch is done.
Instead, the prefetch work will be delegated to a WQ which will do it
in the background.
This way, the prefetch may progress without blocking the user at all.

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;
Signed-off-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
<entry>
<title>habanalabs: order memory manager messages</title>
<updated>2022-05-22T19:01:21Z</updated>
<author>
<name>Yuri Nudelman</name>
<email>ynudelman@habana.ai</email>
</author>
<published>2022-05-11T11:50:02Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=83617f5a87f4ad8403bf1177708fedc98b0a1059'/>
<id>urn:sha1:83617f5a87f4ad8403bf1177708fedc98b0a1059</id>
<content type='text'>
Changing format of memory manager messages to make it more readable. In
addition, reducing the priority of a warning on missing handle during
put. This scenario is not an indication of a problem and may happen in
a legal flow, when handle is put from multiple flows. For example, in
timeout and completion.

Signed-off-by: Yuri Nudelman &lt;ynudelman@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: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
<entry>
<title>habanalabs: return -EFAULT on copy_to_user error</title>
<updated>2022-05-22T19:01:20Z</updated>
<author>
<name>Oded Gabbay</name>
<email>ogabbay@kernel.org</email>
</author>
<published>2022-05-11T09:55:30Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=804d514d7977adbdacb3d4b23bc7d35914fe8930'/>
<id>urn:sha1:804d514d7977adbdacb3d4b23bc7d35914fe8930</id>
<content type='text'>
If copy_to_user failed in info ioctl, we always return -EFAULT so the
user will know there was an error.

Reported-by: kernel test robot &lt;lkp@intel.com&gt;
Reported-by: Dan Carpenter &lt;dan.carpenter@oracle.com&gt;
Signed-off-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
Signed-off-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
<entry>
<title>habanalabs: use NULL for eventfd</title>
<updated>2022-05-22T19:01:20Z</updated>
<author>
<name>Oded Gabbay</name>
<email>ogabbay@kernel.org</email>
</author>
<published>2022-05-11T07:06:39Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=49d2a8af97a20d65d09ac85b57e525b32fdaa0e4'/>
<id>urn:sha1:49d2a8af97a20d65d09ac85b57e525b32fdaa0e4</id>
<content type='text'>
eventfd is pointer. As such, it should be initialized to NULL, not to 0.

In addition, no need to initialize it after creation because the
entire structure is zeroed-out. Also, no need to initialize it before
release because the entire structure is freed.

Reported-by: kernel test robot &lt;lkp@intel.com&gt;
Signed-off-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
Signed-off-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
<entry>
<title>habanalabs: update firmware header</title>
<updated>2022-05-22T19:01:20Z</updated>
<author>
<name>Oded Gabbay</name>
<email>ogabbay@kernel.org</email>
</author>
<published>2022-05-09T11:20:13Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=368b0b4fd6971b63ab9eb0a969b5847755d09493'/>
<id>urn:sha1:368b0b4fd6971b63ab9eb0a969b5847755d09493</id>
<content type='text'>
Update cpucp_if.h to latest version.

Signed-off-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
Signed-off-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
<entry>
<title>habanalabs: add support for notification via eventfd</title>
<updated>2022-05-22T19:01:20Z</updated>
<author>
<name>Tal Cohen</name>
<email>talcohen@habana.ai</email>
</author>
<published>2022-04-28T10:45:18Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=422ef171038d4855ffe938137039a8f3b3e84293'/>
<id>urn:sha1:422ef171038d4855ffe938137039a8f3b3e84293</id>
<content type='text'>
The driver will be able to send notification events towards
a user process, using user's registered event file descriptor.
The driver uses the notification mechanism to inform the
user about an occurred event.
A user thread can wait until a notification is received from
the driver.

The driver stores the occurred event until the user reads it,
using HL_INFO_GET_EVENTS - new ioctl opcode in the INFO ioctl.

Gaudi specific implementation includes sending a notification
on a TPC assertion event that is received from f/w.

Signed-off-by: Tal Cohen &lt;talcohen@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: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
<entry>
<title>habanalabs: add topic to memory manager buffer</title>
<updated>2022-05-22T19:01:20Z</updated>
<author>
<name>Yuri Nudelman</name>
<email>ynudelman@habana.ai</email>
</author>
<published>2022-05-02T10:41:11Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=f2daa2d97ec16766bc36fc2b6218d0acb47885ed'/>
<id>urn:sha1:f2daa2d97ec16766bc36fc2b6218d0acb47885ed</id>
<content type='text'>
Currently, buffers from multiple flows pass through the same infra.
This way, in logs, we are unable to distinguish between buffers that
came from separate flows.
To address this problem, add a "topic" to buffer behavior
descriptor - a string identifier that will be used to identify in logs
the flow this buffer relates to.

Signed-off-by: Yuri Nudelman &lt;ynudelman@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: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
</content>
</entry>
</feed>
