<feed xmlns='http://www.w3.org/2005/Atom'>
<title>kernel/include/uapi/rdma/efa-abi.h, branch linux-6.16.y</title>
<subtitle>Hosts the 0x221E linux distro kernel.</subtitle>
<id>https://universe.0xinfinity.dev/distro/kernel/atom?h=linux-6.16.y</id>
<link rel='self' href='https://universe.0xinfinity.dev/distro/kernel/atom?h=linux-6.16.y'/>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/'/>
<updated>2024-10-21T16:58:07Z</updated>
<entry>
<title>RDMA/efa: Add option to set QP service level on create</title>
<updated>2024-10-21T16:58:07Z</updated>
<author>
<name>Michael Margolin</name>
<email>mrgolin@amazon.com</email>
</author>
<published>2024-10-15T17:42:42Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=48931f65e9f785b65244550cc8f0c8bf9eab7acd'/>
<id>urn:sha1:48931f65e9f785b65244550cc8f0c8bf9eab7acd</id>
<content type='text'>
Using modify QP with AH attributes and IB_QP_AV flag set doesn't make
much sense for connectionless QP types like SRD. Add SL parameter to EFA
create QP user ABI and pass it to the device.

Link: https://patch.msgid.link/r/20241015174242.3490-3-mrgolin@amazon.com
Reviewed-by: Firas Jahjah &lt;firasj@amazon.com&gt;
Reviewed-by: Yonatan Nachum &lt;ynachum@amazon.com&gt;
Signed-off-by: Michael Margolin &lt;mrgolin@amazon.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@nvidia.com&gt;
</content>
</entry>
<entry>
<title>RDMA/efa: Support QP with unsolicited write w/ imm. receive</title>
<updated>2024-05-08T08:18:26Z</updated>
<author>
<name>Michael Margolin</name>
<email>mrgolin@amazon.com</email>
</author>
<published>2024-05-06T15:18:29Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=2b8af5001abdf583da3a63201cc6137553019515'/>
<id>urn:sha1:2b8af5001abdf583da3a63201cc6137553019515</id>
<content type='text'>
Add a new EFA flags attribute for QP creation, and support unsolicited
write with immediate flag. QPs created with this flag set will not
consume receive work requests for incoming RDMA write with immediate.
Expose device capability bit for this feature support.

Reviewed-by: Daniel Kranzdorf &lt;dkkranzd@amazon.com&gt;
Reviewed-by: Firas Jahjah &lt;firasj@amazon.com&gt;
Signed-off-by: Michael Margolin &lt;mrgolin@amazon.com&gt;
Link: https://lore.kernel.org/r/20240506151829.6475-1-mrgolin@amazon.com
Signed-off-by: Leon Romanovsky &lt;leon@kernel.org&gt;
</content>
</entry>
<entry>
<title>RDMA/efa: Add EFA query MR support</title>
<updated>2024-01-07T10:02:27Z</updated>
<author>
<name>Michael Margolin</name>
<email>mrgolin@amazon.com</email>
</author>
<published>2024-01-04T09:51:55Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=2307157c85096026043ba11f9ad8393c31515c45'/>
<id>urn:sha1:2307157c85096026043ba11f9ad8393c31515c45</id>
<content type='text'>
Add EFA driver uapi definitions and register a new query MR method that
currently returns the physical interconnects the device is using to
reach the MR. Update admin definitions and efa-abi accordingly.

Reviewed-by: Anas Mousa &lt;anasmous@amazon.com&gt;
Reviewed-by: Firas Jahjah &lt;firasj@amazon.com&gt;
Signed-off-by: Michael Margolin &lt;mrgolin@amazon.com&gt;
Link: https://lore.kernel.org/r/20240104095155.10676-1-mrgolin@amazon.com
Signed-off-by: Leon Romanovsky &lt;leon@kernel.org&gt;
</content>
</entry>
<entry>
<title>RDMA/efa: Add rdma write capability to device caps</title>
<updated>2023-04-21T22:18:58Z</updated>
<author>
<name>Yonatan Nachum</name>
<email>ynachum@amazon.com</email>
</author>
<published>2023-04-04T15:43:13Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/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>
<entry>
<title>RDMA/efa: Add data polling capability feature bit</title>
<updated>2023-03-22T17:41:58Z</updated>
<author>
<name>Yonatan Nachum</name>
<email>ynachum@amazon.com</email>
</author>
<published>2023-02-19T08:13:28Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=6dddd93938b3651cfeba7158ac179b4e6d3c1553'/>
<id>urn:sha1:6dddd93938b3651cfeba7158ac179b4e6d3c1553</id>
<content type='text'>
Add feature bit to existing device caps field. EFA supports data polling
of 128 bytes blocks.

The flag indicates that the NIC guarentees that a 128 byte aligned block
is written in order, ie that observing the last 8 bits of the block mean
the prior 127 bytes are also written.

It is useful for "last data polling" acceleration techniques.

Link: https://lore.kernel.org/r/20230219081328.10419-1-mrgolin@amazon.com
Reviewed-by: Yehuda Yitschak &lt;yehuday@amazon.com&gt;
Reviewed-by: Yossi Leybovich &lt;sleybo@amazon.com&gt;
Signed-off-by: Yonatan Nachum &lt;ynachum@amazon.com&gt;
Signed-off-by: Michael Margolin &lt;mrgolin@amazon.com&gt;
Acked-by: Gal Pressman &lt;gal.pressman@linux.dev&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@nvidia.com&gt;
</content>
</entry>
<entry>
<title>RDMA/efa: Support CQ receive entries with source GID</title>
<updated>2022-08-21T09:35:59Z</updated>
<author>
<name>Michael Margolin</name>
<email>mrgolin@amazon.com</email>
</author>
<published>2022-08-18T14:04:49Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=dc13fbf79ec8f983fc398cd200ed12973f390957'/>
<id>urn:sha1:dc13fbf79ec8f983fc398cd200ed12973f390957</id>
<content type='text'>
Add a parameter for create CQ admin command to set source address on
receive completion descriptors. Report capability for this feature
through query device verb.

Link: https://lore.kernel.org/r/20220818140449.414-1-mrgolin@amazon.com
Reviewed-by: Firas Jahjah &lt;firasj@amazon.com&gt;
Reviewed-by: Yossi Leybovich &lt;sleybo@amazon.com&gt;
Signed-off-by: Daniel Kranzdorf &lt;dkkranzd@amazon.com&gt;
Signed-off-by: Michael Margolin &lt;mrgolin@amazon.com&gt;
Signed-off-by: Leon Romanovsky &lt;leon@kernel.org&gt;
</content>
</entry>
<entry>
<title>RDMA/efa: CQ notifications</title>
<updated>2021-10-06T22:47:18Z</updated>
<author>
<name>Gal Pressman</name>
<email>galpress@amazon.com</email>
</author>
<published>2021-10-03T10:56:04Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=2a152512a155aaf27c3e67834ffafaed9525a7b5'/>
<id>urn:sha1:2a152512a155aaf27c3e67834ffafaed9525a7b5</id>
<content type='text'>
This patch adds support for CQ notifications through the standard verbs
api.

In order to achieve that, a new event queue (EQ) object is introduced,
which is in charge of reporting completion events to the driver.  On
driver load, EQs are allocated and their affinity is set to a single
cpu. When a user app creates a CQ with a completion channel, the
completion vector number is converted to a EQ number, which is in charge
of reporting the CQ events.

In addition, the CQ creation admin command now returns an offset for the
CQ doorbell, which is mapped to the userspace provider and is used to arm
the CQ when requested by the user.

The EQs use a single doorbell (located on the registers BAR), which
encodes the EQ number and arm as part of the doorbell value.  The EQs are
polled by the driver on each new EQE, and arm it when the poll is
completed.

Link: https://lore.kernel.org/r/20211003105605.29222-1-galpress@amazon.com
Reviewed-by: Firas JahJah &lt;firasj@amazon.com&gt;
Reviewed-by: Yossi Leybovich &lt;sleybo@amazon.com&gt;
Signed-off-by: Gal Pressman &lt;galpress@amazon.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@nvidia.com&gt;
</content>
</entry>
<entry>
<title>RDMA/efa: Introduce SRD RNR retry</title>
<updated>2020-08-18T17:52:45Z</updated>
<author>
<name>Gal Pressman</name>
<email>galpress@amazon.com</email>
</author>
<published>2020-07-31T06:04:20Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=a4e6a1dd57469d6ecee084db1507d3e37908d1e2'/>
<id>urn:sha1:a4e6a1dd57469d6ecee084db1507d3e37908d1e2</id>
<content type='text'>
This patch introduces the ability to configure SRD QPs with the RNR retry
parameter when issuing a modify QP command.

In addition, a capability bit was added to report support to the userspace
library.

Link: https://lore.kernel.org/r/20200731060420.17053-5-galpress@amazon.com
Reviewed-by: Firas JahJah &lt;firasj@amazon.com&gt;
Reviewed-by: Yossi Leybovich &lt;sleybo@amazon.com&gt;
Signed-off-by: Gal Pressman &lt;galpress@amazon.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@nvidia.com&gt;
</content>
</entry>
<entry>
<title>RDMA/efa: User/kernel compatibility handshake mechanism</title>
<updated>2020-07-29T12:23:40Z</updated>
<author>
<name>Gal Pressman</name>
<email>galpress@amazon.com</email>
</author>
<published>2020-07-22T14:03:11Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=a5d87b698547233321466b2dc91271f5855a4df6'/>
<id>urn:sha1:a5d87b698547233321466b2dc91271f5855a4df6</id>
<content type='text'>
Introduce a mechanism that performs an handshake between the userspace
provider and kernel driver which verifies that the user supports all
required features in order to operate correctly.

The handshake verifies the needed functionality by comparing the reported
device caps and the provider caps. If the device reports a non-zero
capability the appropriate comp mask is required from the userspace
provider in order to allocate the context.

Link: https://lore.kernel.org/r/20200722140312.3651-4-galpress@amazon.com
Reviewed-by: Shadi Ammouri &lt;sammouri@amazon.com&gt;
Reviewed-by: Yossi Leybovich &lt;sleybo@amazon.com&gt;
Signed-off-by: Gal Pressman &lt;galpress@amazon.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@nvidia.com&gt;
</content>
</entry>
<entry>
<title>RDMA/efa: Expose minimum SQ size</title>
<updated>2020-07-29T12:23:39Z</updated>
<author>
<name>Gal Pressman</name>
<email>galpress@amazon.com</email>
</author>
<published>2020-07-22T14:03:10Z</published>
<link rel='alternate' type='text/html' href='https://universe.0xinfinity.dev/distro/kernel/commit/?id=da2924bdca99768442c5e0ed0a9024ae79d62765'/>
<id>urn:sha1:da2924bdca99768442c5e0ed0a9024ae79d62765</id>
<content type='text'>
The device reports the minimum SQ size required for creation.

This patch queries the min SQ size and reports it back to the userspace
library.

Link: https://lore.kernel.org/r/20200722140312.3651-3-galpress@amazon.com
Reviewed-by: Firas JahJah &lt;firasj@amazon.com&gt;
Reviewed-by: Shadi Ammouri &lt;sammouri@amazon.com&gt;
Signed-off-by: Gal Pressman &lt;galpress@amazon.com&gt;
Signed-off-by: Jason Gunthorpe &lt;jgg@nvidia.com&gt;
</content>
</entry>
</feed>
