<feed xmlns='http://www.w3.org/2005/Atom'>
<title>kernel/linux.git/include/uapi/rdma, branch v6.6.132</title>
<subtitle>Linux kernel stable tree (mirror)</subtitle>
<id>https://git.radix-linux.su/kernel/linux.git/atom?h=v6.6.132</id>
<link rel='self' href='https://git.radix-linux.su/kernel/linux.git/atom?h=v6.6.132'/>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/'/>
<updated>2025-03-07T15:45:37+00:00</updated>
<entry>
<title>IB/core: Add support for XDR link speed</title>
<updated>2025-03-07T15:45:37+00:00</updated>
<author>
<name>Or Har-Toov</name>
<email>ohartoov@nvidia.com</email>
</author>
<published>2023-09-20T10:07:40+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=b993c450f94de40bce624c082597bbeaa93145b8'/>
<id>urn:sha1:b993c450f94de40bce624c082597bbeaa93145b8</id>
<content type='text'>
[ Upstream commit 703289ce43f740b0096724300107df82d008552f ]

Add new IBTA speed XDR, the new rate that was added to Infiniband spec
as part of XDR and supporting signaling rate of 200Gb.

In order to report that value to rdma-core, add new u32 field to
query_port response.

Signed-off-by: Or Har-Toov &lt;ohartoov@nvidia.com&gt;
Reviewed-by: Mark Zhang &lt;markzhang@nvidia.com&gt;
Link: https://lore.kernel.org/r/9d235fc600a999e8274010f0e18b40fa60540e6c.1695204156.git.leon@kernel.org
Reviewed-by: Jacob Keller &lt;jacob.e.keller@intel.com&gt;
Signed-off-by: Leon Romanovsky &lt;leon@kernel.org&gt;
Stable-dep-of: c534ffda781f ("RDMA/mlx5: Fix AH static rate parsing")
Signed-off-by: Sasha Levin &lt;sashal@kernel.org&gt;
</content>
</entry>
<entry>
<title>RDMA/bnxt_re: Adds MSN table capability for Gen P7 adapters</title>
<updated>2024-06-12T09:12:10+00:00</updated>
<author>
<name>Selvin Xavier</name>
<email>selvin.xavier@broadcom.com</email>
</author>
<published>2023-12-07T10:47:40+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=29feea56dedfb0a56e38ffc9c0b3ad5b6f66cd99'/>
<id>urn:sha1:29feea56dedfb0a56e38ffc9c0b3ad5b6f66cd99</id>
<content type='text'>
[ Upstream commit 07f830ae4913d0b986c8c0ff88a7d597948b9bd8 ]

GenP7 HW expects an MSN table instead of PSN table. Check
for the HW retransmission capability and populate the MSN
table if HW retansmission is supported.

Signed-off-by: Damodharam Ammepalli &lt;damodharam.ammepalli@broadcom.com&gt;
Signed-off-by: Selvin Xavier &lt;selvin.xavier@broadcom.com&gt;
Link: https://lore.kernel.org/r/1701946060-13931-7-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky &lt;leon@kernel.org&gt;
Stable-dep-of: 78cfd17142ef ("bnxt_re: avoid shift undefined behavior in bnxt_qplib_alloc_init_hwq")
Signed-off-by: Sasha Levin &lt;sashal@kernel.org&gt;
</content>
</entry>
<entry>
<title>RDMA/bnxt_re: Remove roundup_pow_of_two depth for all hardware queue resources</title>
<updated>2024-06-12T09:12:10+00:00</updated>
<author>
<name>Chandramohan Akula</name>
<email>chandramohan.akula@broadcom.com</email>
</author>
<published>2023-10-23T14:03:23+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=e300b1b95c9352d78c0192d34122f9cca4b004d4'/>
<id>urn:sha1:e300b1b95c9352d78c0192d34122f9cca4b004d4</id>
<content type='text'>
[ Upstream commit 48f996d4adf15a0a0af8b8184d3ec6042a684ea4 ]

Rounding up the queue depth to power of two is not a hardware requirement.
In order to optimize the per connection memory usage, removing drivers
implementation which round up to the queue depths to the power of 2.

Implements a mask to maintain backward compatibility with older
library.

Signed-off-by: Chandramohan Akula &lt;chandramohan.akula@broadcom.com&gt;
Signed-off-by: Selvin Xavier &lt;selvin.xavier@broadcom.com&gt;
Link: https://lore.kernel.org/r/1698069803-1787-3-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky &lt;leon@kernel.org&gt;
Stable-dep-of: 78cfd17142ef ("bnxt_re: avoid shift undefined behavior in bnxt_qplib_alloc_init_hwq")
Signed-off-by: Sasha Levin &lt;sashal@kernel.org&gt;
</content>
</entry>
<entry>
<title>RDMA/irdma: Use HW specific minimum WQ size</title>
<updated>2023-07-30T12:43:00+00:00</updated>
<author>
<name>Sindhu Devale</name>
<email>sindhu.devale@intel.com</email>
</author>
<published>2023-07-25T15:55:25+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=72d422c2465e93d5de622173f04d666cb9854c5f'/>
<id>urn:sha1:72d422c2465e93d5de622173f04d666cb9854c5f</id>
<content type='text'>
HW GEN1 and GEN2 have different min WQ sizes but they are
currently set to the same value.

Use a gen specific attribute min_hw_wq_size and extend ABI to
pass it to user-space.

Signed-off-by: Sindhu Devale &lt;sindhu.devale@intel.com&gt;
Signed-off-by: Shiraz Saleem &lt;shiraz.saleem@intel.com&gt;
Link: https://lore.kernel.org/r/20230725155525.1081-3-shiraz.saleem@intel.com
Signed-off-by: Leon Romanovsky &lt;leon@kernel.org&gt;
</content>
</entry>
<entry>
<title>RDMA/irdma: Allow accurate reporting on QP max send/recv WR</title>
<updated>2023-07-30T12:43:00+00:00</updated>
<author>
<name>Sindhu Devale</name>
<email>sindhu.devale@intel.com</email>
</author>
<published>2023-07-25T15:55:24+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=3a8498720450174b8db450d3375a04dca81b3534'/>
<id>urn:sha1:3a8498720450174b8db450d3375a04dca81b3534</id>
<content type='text'>
Currently the attribute cap.max_send_wr and cap.max_recv_wr
sent from user-space during create QP are the provider computed
SQ/RQ depth as opposed to raw values passed from application.
This inhibits computation of an accurate value for max_send_wr
and max_recv_wr for this QP in the kernel which matches the value
returned in user create QP. Also these capabilities needs to be
reported from the driver in query QP.

Add support by extending the ABI to allow the raw cap.max_send_wr and
cap.max_recv_wr to be passed from user-space, while keeping compatibility
for the older scheme.

The internal HW depth and shift needed for the WQs needs to be computed
now for both kernel and user-mode QPs. Add new helpers to assist with this:
irdma_uk_calc_depth_shift_sq, irdma_uk_calc_depth_shift_rq and
irdma_uk_calc_depth_shift_wq.

Consolidate all the user mode QP setup into a new function
irdma_setup_umode_qp which keeps it with its counterpart
irdma_setup_kmode_qp.

Signed-off-by: Youvaraj Sagar &lt;youvaraj.sagar@intel.com&gt;
Signed-off-by: Sindhu Devale &lt;sindhu.devale@intel.com&gt;
Signed-off-by: Shiraz Saleem &lt;shiraz.saleem@intel.com&gt;
Link: https://lore.kernel.org/r/20230725155525.1081-2-shiraz.saleem@intel.com
Signed-off-by: Leon Romanovsky &lt;leon@kernel.org&gt;
</content>
</entry>
<entry>
<title>RDMA/bnxt_re: Add a new uapi for driver notification</title>
<updated>2023-07-21T19:15:33+00:00</updated>
<author>
<name>Chandramohan Akula</name>
<email>chandramohan.akula@broadcom.com</email>
</author>
<published>2023-07-19T05:02:57+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=61a8118f60e9dde64be4f3a6e07c15014a8bfbd2'/>
<id>urn:sha1:61a8118f60e9dde64be4f3a6e07c15014a8bfbd2</id>
<content type='text'>
Add driver notify uapi for application notifying
the driver about the doorbell FIFO congestion.

Link: https://lore.kernel.org/r/1689742977-9128-8-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Chandramohan Akula &lt;chandramohan.akula@broadcom.com&gt;
Signed-off-by: Selvin Xavier &lt;selvin.xavier@broadcom.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@nvidia.com&gt;
</content>
</entry>
<entry>
<title>RDMA/bnxt_re: Update alloc_page uapi for pacing</title>
<updated>2023-07-21T19:15:32+00:00</updated>
<author>
<name>Chandramohan Akula</name>
<email>chandramohan.akula@broadcom.com</email>
</author>
<published>2023-07-19T05:02:55+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=ea222485788208cd79bad42d25aae9232b33a934'/>
<id>urn:sha1:ea222485788208cd79bad42d25aae9232b33a934</id>
<content type='text'>
Update the alloc_page uapi functionality for handling the
mapping of doorbell pacing shared page and bar address.

Link: https://lore.kernel.org/r/1689742977-9128-6-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Chandramohan Akula &lt;chandramohan.akula@broadcom.com&gt;
Signed-off-by: Selvin Xavier &lt;selvin.xavier@broadcom.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@nvidia.com&gt;
</content>
</entry>
<entry>
<title>RDMA/bnxt_re: Enable pacing support for the user apps</title>
<updated>2023-07-21T19:15:32+00:00</updated>
<author>
<name>Chandramohan Akula</name>
<email>chandramohan.akula@broadcom.com</email>
</author>
<published>2023-07-19T05:02:54+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=fa8fad92ddddfc0cfb6fd9e9f645cf53a5ee78a6'/>
<id>urn:sha1:fa8fad92ddddfc0cfb6fd9e9f645cf53a5ee78a6</id>
<content type='text'>
Report the pacing capability to the user applications.

Link: https://lore.kernel.org/r/1689742977-9128-5-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Chandramohan Akula &lt;chandramohan.akula@broadcom.com&gt;
Signed-off-by: Selvin Xavier &lt;selvin.xavier@broadcom.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@nvidia.com&gt;
</content>
</entry>
<entry>
<title>RDMA/bnxt_re: Enable low latency push</title>
<updated>2023-06-21T17:13:17+00:00</updated>
<author>
<name>Selvin Xavier</name>
<email>selvin.xavier@broadcom.com</email>
</author>
<published>2023-06-13T18:12:23+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=360da60d6c6edb9740de7a8e6d8969d62ceff956'/>
<id>urn:sha1:360da60d6c6edb9740de7a8e6d8969d62ceff956</id>
<content type='text'>
Introduce driver specific uapi functionalites. Added a alloc_page
functionality for user library to allocate specific pages. Currently added
support for allocating write combine pages for push functinality. This
interface shall be extended for other page allocations.

Allocate a WC page using the uapi hook for enabling the low latency push
in Gen P5 adapters for small packets. This is supported only for the user
space QPs.

Link: https://lore.kernel.org/r/1686679943-17117-8-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Selvin Xavier &lt;selvin.xavier@broadcom.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@nvidia.com&gt;
</content>
</entry>
<entry>
<title>RDMA/efa: Add rdma write capability to device caps</title>
<updated>2023-04-21T22:18:58+00:00</updated>
<author>
<name>Yonatan Nachum</name>
<email>ynachum@amazon.com</email>
</author>
<published>2023-04-04T15:43:13+00:00</published>
<link rel='alternate' type='text/html' href='https://git.radix-linux.su/kernel/linux.git/commit/?id=531094dc7164718d28ebb581d729807d7e846363'/>
<id>urn:sha1:531094dc7164718d28ebb581d729807d7e846363</id>
<content type='text'>
Add rdma write capability that is propagated from the device to rdma-core.
Enable MR creation with remote write permissions according to this device
capability.

Link: https://lore.kernel.org/r/20230404154313.35194-1-ynachum@amazon.com
Reviewed-by: Firas Jahjah &lt;firasj@amazon.com&gt;
Reviewed-by: Michael Margolin &lt;mrgolin@amazon.com&gt;
Signed-off-by: Yonatan Nachum &lt;ynachum@amazon.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@nvidia.com&gt;
</content>
</entry>
</feed>
