<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux-toradex.git/include/uapi/rdma, branch toradex_5.0.y</title>
<subtitle>Linux kernel for Apalis and Colibri modules</subtitle>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/'/>
<entry>
<title>IB/mlx5: Fix scatter to CQE in DCT QP creation</title>
<updated>2019-05-16T17:40:23+00:00</updated>
<author>
<name>Guy Levi</name>
<email>guyle@mellanox.com</email>
</author>
<published>2019-04-10T07:59:45+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=143c8279955e7a8c614d5912d001e2478b1af271'/>
<id>143c8279955e7a8c614d5912d001e2478b1af271</id>
<content type='text'>
[ Upstream commit 7249c8ea227a582c14f63e9e8853eb7369122f10 ]

When scatter to CQE is enabled on a DCT QP it corrupts the mailbox command
since it tried to treat it as as QP create mailbox command instead of a
DCT create command.

The corrupted mailbox command causes userspace to malfunction as the
device doesn't create the QP as expected.

A new mlx5 capability is exposed to user-space which ensures that it will
not enable the feature on DCT without this fix in the kernel.

Fixes: 5d6ff1babe78 ("IB/mlx5: Support scatter to CQE for DC transport type")
Signed-off-by: Guy Levi &lt;guyle@mellanox.com&gt;
Signed-off-by: Leon Romanovsky &lt;leonro@mellanox.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
Signed-off-by: Sasha Levin &lt;sashal@kernel.org&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
[ Upstream commit 7249c8ea227a582c14f63e9e8853eb7369122f10 ]

When scatter to CQE is enabled on a DCT QP it corrupts the mailbox command
since it tried to treat it as as QP create mailbox command instead of a
DCT create command.

The corrupted mailbox command causes userspace to malfunction as the
device doesn't create the QP as expected.

A new mlx5 capability is exposed to user-space which ensures that it will
not enable the feature on DCT without this fix in the kernel.

Fixes: 5d6ff1babe78 ("IB/mlx5: Support scatter to CQE for DC transport type")
Signed-off-by: Guy Levi &lt;guyle@mellanox.com&gt;
Signed-off-by: Leon Romanovsky &lt;leonro@mellanox.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
Signed-off-by: Sasha Levin &lt;sashal@kernel.org&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>RDMA/hns: Update the kernel header file of hns</title>
<updated>2019-01-25T16:55:48+00:00</updated>
<author>
<name>Lijun Ou</name>
<email>oulijun@huawei.com</email>
</author>
<published>2019-01-23T02:09:27+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=9d9d4ff788845fad1626b80164e43a1f0f17ccbc'/>
<id>9d9d4ff788845fad1626b80164e43a1f0f17ccbc</id>
<content type='text'>
The hns_roce_ib_create_srq_resp is used to interact with the user for
data, this was open coded to use a u32 directly, instead use a properly
sized structure.

Fixes: c7bcb13442e1 ("RDMA/hns: Add SRQ support for hip08 kernel mode")
Signed-off-by: Lijun Ou &lt;oulijun@huawei.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The hns_roce_ib_create_srq_resp is used to interact with the user for
data, this was open coded to use a u32 directly, instead use a properly
sized structure.

Fixes: c7bcb13442e1 ("RDMA/hns: Add SRQ support for hip08 kernel mode")
Signed-off-by: Lijun Ou &lt;oulijun@huawei.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>RDMA/vmw_pvrdma: Return the correct opcode when creating WR</title>
<updated>2019-01-11T00:00:28+00:00</updated>
<author>
<name>Adit Ranadive</name>
<email>aditr@vmware.com</email>
</author>
<published>2019-01-09T23:08:49+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=6325e01b6cdf4636b721cf7259c1616e3cf28ce2'/>
<id>6325e01b6cdf4636b721cf7259c1616e3cf28ce2</id>
<content type='text'>
Since the IB_WR_REG_MR opcode value changed, let's set the PVRDMA device
opcodes explicitly.

Reported-by: Ruishuang Wang &lt;ruishuangw@vmware.com&gt;
Fixes: 9a59739bd01f ("IB/rxe: Revise the ib_wr_opcode enum")
Cc: stable@vger.kernel.org
Reviewed-by: Bryan Tan &lt;bryantan@vmware.com&gt;
Reviewed-by: Ruishuang Wang &lt;ruishuangw@vmware.com&gt;
Reviewed-by: Vishnu Dasa &lt;vdasa@vmware.com&gt;
Signed-off-by: Adit Ranadive &lt;aditr@vmware.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Since the IB_WR_REG_MR opcode value changed, let's set the PVRDMA device
opcodes explicitly.

Reported-by: Ruishuang Wang &lt;ruishuangw@vmware.com&gt;
Fixes: 9a59739bd01f ("IB/rxe: Revise the ib_wr_opcode enum")
Cc: stable@vger.kernel.org
Reviewed-by: Bryan Tan &lt;bryantan@vmware.com&gt;
Reviewed-by: Ruishuang Wang &lt;ruishuangw@vmware.com&gt;
Reviewed-by: Vishnu Dasa &lt;vdasa@vmware.com&gt;
Signed-off-by: Adit Ranadive &lt;aditr@vmware.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>IB/core: Move query port to ioctl</title>
<updated>2018-12-20T22:18:24+00:00</updated>
<author>
<name>Michael Guralnik</name>
<email>michaelgur@mellanox.com</email>
</author>
<published>2018-12-09T09:58:06+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=641d1207d2ed0ef21ff5ad61e067d630028e2f62'/>
<id>641d1207d2ed0ef21ff5ad61e067d630028e2f62</id>
<content type='text'>
Add a method for query port under the uverbs global methods.  Current
ib_port_attr struct is passed as a single attribute and port_cap_flags2 is
added as a new attribute to the function.

Signed-off-by: Michael Guralnik &lt;michaelgur@mellanox.com&gt;
Signed-off-by: Leon Romanovsky &lt;leonro@mellanox.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Add a method for query port under the uverbs global methods.  Current
ib_port_attr struct is passed as a single attribute and port_cap_flags2 is
added as a new attribute to the function.

Signed-off-by: Michael Guralnik &lt;michaelgur@mellanox.com&gt;
Signed-off-by: Leon Romanovsky &lt;leonro@mellanox.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>RDMA/nldev: Expose port_cap_flags2</title>
<updated>2018-12-20T22:18:24+00:00</updated>
<author>
<name>Michael Guralnik</name>
<email>michaelgur@mellanox.com</email>
</author>
<published>2018-12-09T09:58:05+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=4fa2813d26c82680216e535c18a690ca0c4e860a'/>
<id>4fa2813d26c82680216e535c18a690ca0c4e860a</id>
<content type='text'>
port_cap_flags2 represents IBTA PortInfo:CapabilityMask2.

The field safely extends the RDMA_NLDEV_ATTR_CAP_FLAGS operand as it was
exported as 64 bit to allow this kind of extension.

Signed-off-by: Michael Guralnik &lt;michaelgur@mellanox.com&gt;
Signed-off-by: Leon Romanovsky &lt;leonro@mellanox.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
port_cap_flags2 represents IBTA PortInfo:CapabilityMask2.

The field safely extends the RDMA_NLDEV_ATTR_CAP_FLAGS operand as it was
exported as 64 bit to allow this kind of extension.

Signed-off-by: Michael Guralnik &lt;michaelgur@mellanox.com&gt;
Signed-off-by: Leon Romanovsky &lt;leonro@mellanox.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>IB/uverbs: Add support to advise_mr</title>
<updated>2018-12-18T22:19:46+00:00</updated>
<author>
<name>Moni Shoua</name>
<email>monis@mellanox.com</email>
</author>
<published>2018-12-11T11:37:52+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=ad8a4496757f6f7344011a20a07195bd27e3989c'/>
<id>ad8a4496757f6f7344011a20a07195bd27e3989c</id>
<content type='text'>
Add new ioctl method for the MR object - ADVISE_MR.

This command can be used by users to give an advice or directions to the
kernel about an address range that belongs to memory regions.

A new ib_device callback, advise_mr(), is introduced here to suupport the
new command. This command takes the following arguments:

- pd:		The protection domain to which all memory regions belong
- advice: 	The type of the advice
	  	* IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH - Pre-fetch a range of
		an on-demand paging MR
	  	* IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_WRITE - Pre-fetch a range
		of an on-demand paging MR with write intention
- flags:	The properties of the advice
		* IB_UVERBS_ADVISE_MR_FLAG_FLUSH - Operation must end before
		return to the caller
- sg_list:	The list of memory ranges
- num_sge:	The number of memory ranges in the list
- attrs:	More attributes to be parsed by the provider

Signed-off-by: Moni Shoua &lt;monis@mellanox.com&gt;
Reviewed-by: Guy Levi &lt;guyle@mellanox.com&gt;
Signed-off-by: Leon Romanovsky &lt;leonro@mellanox.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Add new ioctl method for the MR object - ADVISE_MR.

This command can be used by users to give an advice or directions to the
kernel about an address range that belongs to memory regions.

A new ib_device callback, advise_mr(), is introduced here to suupport the
new command. This command takes the following arguments:

- pd:		The protection domain to which all memory regions belong
- advice: 	The type of the advice
	  	* IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH - Pre-fetch a range of
		an on-demand paging MR
	  	* IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_WRITE - Pre-fetch a range
		of an on-demand paging MR with write intention
- flags:	The properties of the advice
		* IB_UVERBS_ADVISE_MR_FLAG_FLUSH - Operation must end before
		return to the caller
- sg_list:	The list of memory ranges
- num_sge:	The number of memory ranges in the list
- attrs:	More attributes to be parsed by the provider

Signed-off-by: Moni Shoua &lt;monis@mellanox.com&gt;
Reviewed-by: Guy Levi &lt;guyle@mellanox.com&gt;
Signed-off-by: Leon Romanovsky &lt;leonro@mellanox.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>RDMA/uverbs: Add an ioctl method to destroy an object</title>
<updated>2018-12-18T21:59:57+00:00</updated>
<author>
<name>Parav Pandit</name>
<email>parav@mellanox.com</email>
</author>
<published>2018-11-30T11:16:48+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=bbc13cda37711eb7baa4091017887a57074f5410'/>
<id>bbc13cda37711eb7baa4091017887a57074f5410</id>
<content type='text'>
Add an ioctl method to destroy the PD, MR, MW, AH, flow, RWQ indirection
table and XRCD objects by handle which doesn't require any output response
during destruction.

Signed-off-by: Parav Pandit &lt;parav@mellanox.com&gt;
Signed-off-by: Leon Romanovsky &lt;leonro@mellanox.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Add an ioctl method to destroy the PD, MR, MW, AH, flow, RWQ indirection
table and XRCD objects by handle which doesn't require any output response
during destruction.

Signed-off-by: Parav Pandit &lt;parav@mellanox.com&gt;
Signed-off-by: Leon Romanovsky &lt;leonro@mellanox.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>RDMA/uverbs: Add a method to introspect handles in a context</title>
<updated>2018-12-18T21:54:54+00:00</updated>
<author>
<name>Jason Gunthorpe</name>
<email>jgg@mellanox.com</email>
</author>
<published>2018-11-30T11:16:47+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=149d3845f4a548dbc83932fab3491aeb0b070b3a'/>
<id>149d3845f4a548dbc83932fab3491aeb0b070b3a</id>
<content type='text'>
Introduce a helper function gather_objects_handle() to copy object handles
under a spin lock.

Expose these objects handles via the uverbs ioctl interface.

Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
Signed-off-by: Parav Pandit &lt;parav@mellanox.com&gt;
Signed-off-by: Leon Romanovsky &lt;leonro@mellanox.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Introduce a helper function gather_objects_handle() to copy object handles
under a spin lock.

Expose these objects handles via the uverbs ioctl interface.

Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
Signed-off-by: Parav Pandit &lt;parav@mellanox.com&gt;
Signed-off-by: Leon Romanovsky &lt;leonro@mellanox.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>RDMA/uverbs: Implement an ioctl that can call write and write_ex handlers</title>
<updated>2018-12-18T19:12:48+00:00</updated>
<author>
<name>Jason Gunthorpe</name>
<email>jgg@mellanox.com</email>
</author>
<published>2018-11-30T11:06:21+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=4785860e04bc8d7e244b25257168e1cf8a5529ab'/>
<id>4785860e04bc8d7e244b25257168e1cf8a5529ab</id>
<content type='text'>
Now that the handlers do not process their own udata we can make a
sensible ioctl that wrappers them. The ioctl follows the same format as
the write_ex() and has the user explicitly specify the core and driver
in/out opaque structures and a command number.

This works for all forms of write commands.

Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
Signed-off-by: Leon Romanovsky &lt;leonro@mellanox.com&gt;
Signed-off-by: Doug Ledford &lt;dledford@redhat.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Now that the handlers do not process their own udata we can make a
sensible ioctl that wrappers them. The ioctl follows the same format as
the write_ex() and has the user explicitly specify the core and driver
in/out opaque structures and a command number.

This works for all forms of write commands.

Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
Signed-off-by: Leon Romanovsky &lt;leonro@mellanox.com&gt;
Signed-off-by: Doug Ledford &lt;dledford@redhat.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>Merge branch 'mlx5-packet-credit-fc' into rdma.git</title>
<updated>2018-12-07T20:25:12+00:00</updated>
<author>
<name>Jason Gunthorpe</name>
<email>jgg@mellanox.com</email>
</author>
<published>2018-12-07T20:25:12+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=fe15bcc6e23f4d5273dfbc056bae8710723f03d0'/>
<id>fe15bcc6e23f4d5273dfbc056bae8710723f03d0</id>
<content type='text'>
Danit Goldberg says:

Packet based credit mode

Packet based credit mode is an alternative end-to-end credit mode for QPs
set during their creation. Credits are transported from the responder to
the requester to optimize the use of its receive resources.  In
packet-based credit mode, credits are issued on a per packet basis.

The advantage of this feature comes while sending large RDMA messages
through switches that are short in memory.

The first commit exposes QP creation flag and the HCA capability. The
second commit adds support for a new DV QP creation flag. The last commit
report packet based credit mode capability via the MLX5DV device
capabilities.

* branch 'mlx5-packet-credit-fc':
  IB/mlx5: Report packet based credit mode device capability
  IB/mlx5: Add packet based credit mode support
  net/mlx5: Expose packet based credit mode

Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Danit Goldberg says:

Packet based credit mode

Packet based credit mode is an alternative end-to-end credit mode for QPs
set during their creation. Credits are transported from the responder to
the requester to optimize the use of its receive resources.  In
packet-based credit mode, credits are issued on a per packet basis.

The advantage of this feature comes while sending large RDMA messages
through switches that are short in memory.

The first commit exposes QP creation flag and the HCA capability. The
second commit adds support for a new DV QP creation flag. The last commit
report packet based credit mode capability via the MLX5DV device
capabilities.

* branch 'mlx5-packet-credit-fc':
  IB/mlx5: Report packet based credit mode device capability
  IB/mlx5: Add packet based credit mode support
  net/mlx5: Expose packet based credit mode

Signed-off-by: Jason Gunthorpe &lt;jgg@mellanox.com&gt;
</pre>
</div>
</content>
</entry>
</feed>
