<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux-dev/drivers/misc/habanalabs, branch master</title>
<subtitle>Linux kernel development work - see feature branches</subtitle>
<id>https://git.zx2c4.com/linux-dev/atom/drivers/misc/habanalabs?h=master</id>
<link rel='self' href='https://git.zx2c4.com/linux-dev/atom/drivers/misc/habanalabs?h=master'/>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/'/>
<updated>2022-10-11T23:42:58Z</updated>
<entry>
<title>treewide: use get_random_u32() when possible</title>
<updated>2022-10-11T23:42:58Z</updated>
<author>
<name>Jason A. Donenfeld</name>
<email>Jason@zx2c4.com</email>
</author>
<published>2022-10-05T15:43:22Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=a251c17aa558d8e3128a528af5cf8b9d7caae4fd'/>
<id>urn:sha1:a251c17aa558d8e3128a528af5cf8b9d7caae4fd</id>
<content type='text'>
The prandom_u32() function has been a deprecated inline wrapper around
get_random_u32() for several releases now, and compiles down to the
exact same code. Replace the deprecated wrapper with a direct call to
the real function. The same also applies to get_random_int(), which is
just a wrapper around get_random_u32(). This was done as a basic find
and replace.

Reviewed-by: Greg Kroah-Hartman &lt;gregkh@linuxfoundation.org&gt;
Reviewed-by: Kees Cook &lt;keescook@chromium.org&gt;
Reviewed-by: Yury Norov &lt;yury.norov@gmail.com&gt;
Reviewed-by: Jan Kara &lt;jack@suse.cz&gt; # for ext4
Acked-by: Toke Høiland-Jørgensen &lt;toke@toke.dk&gt; # for sch_cake
Acked-by: Chuck Lever &lt;chuck.lever@oracle.com&gt; # for nfsd
Acked-by: Jakub Kicinski &lt;kuba@kernel.org&gt;
Acked-by: Mika Westerberg &lt;mika.westerberg@linux.intel.com&gt; # for thunderbolt
Acked-by: Darrick J. Wong &lt;djwong@kernel.org&gt; # for xfs
Acked-by: Helge Deller &lt;deller@gmx.de&gt; # for parisc
Acked-by: Heiko Carstens &lt;hca@linux.ibm.com&gt; # for s390
Signed-off-by: Jason A. Donenfeld &lt;Jason@zx2c4.com&gt;
</content>
</entry>
<entry>
<title>habanalabs: eliminate aggregate use warning</title>
<updated>2022-09-20T12:52:27Z</updated>
<author>
<name>Oded Gabbay</name>
<email>ogabbay@kernel.org</email>
</author>
<published>2022-09-19T21:08:40Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=259cee1c2422bcff7ba6bb4e8179faadb52ebdee'/>
<id>urn:sha1:259cee1c2422bcff7ba6bb4e8179faadb52ebdee</id>
<content type='text'>
When doing sizeof() and giving as argument a dereference of
a pointer-to-a-pointer object, clang will issue a warning.

Eliminate the warning by passing struct &lt;name&gt;*

Signed-off-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
</content>
</entry>
<entry>
<title>habanalabs/gaudi: use 8KB aligned address for TPC kernels</title>
<updated>2022-09-20T12:51:54Z</updated>
<author>
<name>Tomer Tayar</name>
<email>ttayar@habana.ai</email>
</author>
<published>2022-09-19T15:46:03Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=e403856468456aeaff68a5cb0a851d945c133ed9'/>
<id>urn:sha1:e403856468456aeaff68a5cb0a851d945c133ed9</id>
<content type='text'>
I$ prefetch is enabled when sending a TPC kernel to initialize the TPC
memory, and it has a restriction that the base address will be aligned
to 8KB.
Currently the base address is 128 bytes from the start address of the
device SRAM, so prefetching will start 128 bytes before the actual
kernel memory.
Modify the kernel address to be 8KB aligned.

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: remove some f/w descriptor validations</title>
<updated>2022-09-20T12:46:45Z</updated>
<author>
<name>farah kassabri</name>
<email>fkassabri@habana.ai</email>
</author>
<published>2022-08-30T10:01:03Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=6b9b9e244fdd0d6c5ee21b7b9d74282d9e43733a'/>
<id>urn:sha1:6b9b9e244fdd0d6c5ee21b7b9d74282d9e43733a</id>
<content type='text'>
To be forward-backward compatible with the firmware in the initial
communication during preboot, we need to remove the validation of the
header size. This will allow us to add more fields to the
lkd_fw_comms_desc structure.

Instead of the validation of the header size, we just print warning
when some mismatch in descriptor has been revealed, and we calculate
the CRC base on descriptor size reported by the firmware instead of
calculating it ourselves.

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: build ASICs from new to old</title>
<updated>2022-09-20T12:42:08Z</updated>
<author>
<name>Ohad Sharabi</name>
<email>osharabi@habana.ai</email>
</author>
<published>2022-09-15T06:19:03Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=8412bb69ed789464adadf7f0906971c7be29e204'/>
<id>urn:sha1:8412bb69ed789464adadf7f0906971c7be29e204</id>
<content type='text'>
Newer ASICs code changes more often, has more chance to fail
compilation. So, let's compile them first so errors in those files
will fail compilation sooner.

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>
<entry>
<title>habanalabs/gaudi2: allow user to flush PCIE by read</title>
<updated>2022-09-19T12:10:01Z</updated>
<author>
<name>Ofir Bitton</name>
<email>obitton@habana.ai</email>
</author>
<published>2022-09-15T08:10:56Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=bb677d527e14184d89012ce332128f3767fa9925'/>
<id>urn:sha1:bb677d527e14184d89012ce332128f3767fa9925</id>
<content type='text'>
In order for the user to flush PCIE he needs to read some register
from PCIE block. The chosen register is SPECIAL_GLBL_SPARE_0 and
hence needs to be unsecured.

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: failure to open device due to reset is debug level</title>
<updated>2022-09-19T12:09:04Z</updated>
<author>
<name>Oded Gabbay</name>
<email>ogabbay@kernel.org</email>
</author>
<published>2022-09-19T08:30:03Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=4f3ce5e0d0f85d6be0a2bc3a2aa75ba3b649c7c6'/>
<id>urn:sha1:4f3ce5e0d0f85d6be0a2bc3a2aa75ba3b649c7c6</id>
<content type='text'>
If the user wants to open the device, and the device is currently in
reset, the user will get an error from the open().

We don't need to display an error in the dmesg for that as it is
not a real error and we can spam the kernel log with this message.

Signed-off-by: Oded Gabbay &lt;ogabbay@kernel.org&gt;
</content>
</entry>
<entry>
<title>habanalabs/gaudi2: Remove unnecessary (void*) conversions</title>
<updated>2022-09-19T12:08:40Z</updated>
<author>
<name>Li zeming</name>
<email>zeming@nfschina.com</email>
</author>
<published>2022-09-19T02:20:54Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=006fd8cb659bb02789dc1ec48836fff5f348ba8d'/>
<id>urn:sha1:006fd8cb659bb02789dc1ec48836fff5f348ba8d</id>
<content type='text'>
The void pointer object can be directly assigned to different structure
objects, it does not need to be cast.

Signed-off-by: Li zeming &lt;zeming@nfschina.com&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/gaudi2: add secured attestation info uapi</title>
<updated>2022-09-19T12:08:40Z</updated>
<author>
<name>Dani Liberman</name>
<email>dliberman@habana.ai</email>
</author>
<published>2022-08-01T12:23:44Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=0c88760f8f5e13e32f624a1da71144b240b05125'/>
<id>urn:sha1:0c88760f8f5e13e32f624a1da71144b240b05125</id>
<content type='text'>
User will provide a nonce via the ioctl, and will retrieve
secured attestation data of the boot, generated using given
nonce.

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/gaudi2: add handling to pmmu events in eqe handler</title>
<updated>2022-09-19T12:08:39Z</updated>
<author>
<name>Dani Liberman</name>
<email>dliberman@habana.ai</email>
</author>
<published>2022-09-08T15:24:41Z</published>
<link rel='alternate' type='text/html' href='https://git.zx2c4.com/linux-dev/commit/?id=43657dadfeffbec63b9ed358e6f82e9c64ff334c'/>
<id>urn:sha1:43657dadfeffbec63b9ed358e6f82e9c64ff334c</id>
<content type='text'>
In order to get the error cause and the captured address in case of
page fault, added pmmu events to eqe handler.

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>
</feed>
