When cleaning up unaccepted mptcp socket still laying inside
the listener queue at listener close time, such sockets will
go through a regular close, waiting for a timeout before
shutting down the subflows.

There is no need to keep the kernel resources in use for
such a possibly long time: short-circuit to fast-close.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

In the long run this will simplify the mptcp code and will
allow for more consistent behavior. Move the first subflow
allocation out of the sock->init ops into the __mptcp_nmpc_socket()
helper.

Since the first subflow creation can now happen after the first
setsockopt() we additionally need to invoke mptcp_sockopt_sync()
on it.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

So that we can avoid a bunch of check in fastpath. Additionally we
can specialize such check according to the specific fastopen method
- defer_connect vs MSG_FASTOPEN.

The latter bits will simplify the next patches.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

In a few spots, the mptcp code invokes the __mptcp_nmpc_socket() helper
multiple times under the same socket lock scope. Additionally, in such
places, the socket status ensures that there is no MP capable handshake
running.

Under the above condition we can replace the later __mptcp_nmpc_socket()
helper invocation with direct access to the msk->subflow pointer and
better document such access is not supposed to fail with WARN().
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

After commit 3a236aef ("mptcp: refactor passive socket initialization"),
every mptcp_pm_fully_established() call is always invoked with a
GFP_ATOMIC argument. We can then drop it.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

mlx5-updates-2023-04-14

Yevgeny Kliteynik Says:
=======================

SW Steering: Support pattern/args modify_header actions

The following patch series adds support for a new pattern/arguments type
of modify_header actions.

Starting with ConnectX-6 DX, we use a new design of modify_header FW object.
The current modify_header object allows for having only limited number of
these FW objects, which means that we are limited in the number of offloaded
flows that require modify_header action.

The new approach comprises of two types of objects: pattern and argument.
Pattern holds header modification templates, later used with corresponding
argument object to create complete header modification actions.
The pattern indicates which headers are modified, while the arguments
provide the specific values.
Therefore a single pattern can be used with different arguments in different
flows, enabling offloading of large number of modify_header flows.

 - Patch 1, 2: Add ICM pool for modify-header-pattern objects and implement
   patterns cache, allowing patterns reuse for different flows
 - Patch 3: Allow for chunk allocation separately for STEv0 and STEv1
 - Patch 4: Read related device capabilities
 - Patch 5: Add create/destroy functions for the new general object type
 - Patch 6: Add support for writing modify header argument to ICM
 - Patch 7, 8: Some required fixes to support pattern/arg - separate read
   buffer from the write buffer and fix QP continuous allocation
 - Patch 9: Add pool for modify header arg objects
 - Patch 10, 11, 12: Implement MODIFY_HEADER and TNL_L3_TO_L2 actions with
   the new patterns/args design
 - Patch 13: Optimization - set modify header action of size 1 directly on
   the STE instead of separate pattern/args combination
 - Patch 14: Adjust debug dump for patterns/args
 - Patch 15: Enable patterns and arguments for supporting devices

=======================

Aaron Conole says:

====================
selftests: openvswitch: add support for testing upcall interface

The existing selftest suite for openvswitch will work for regression
testing the datapath feature bits, but won't test things like adding
interfaces, or the upcall interface.  Here, we add some additional
test facilities.

First, extend the ovs-dpctl.py python module to support the OVS_FLOW
and OVS_PACKET netlink families, with some associated messages.  These
can be extended over time, but the initial support is for more well
known cases (output, userspace, and CT).

Next, extend the test suite to test upcalls by adding a datapath,
monitoring the upcall socket associated with the datapath, and then
dumping any upcalls that are received.  Compare with expected ARP
upcall via arping.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

The upcall socket interface can be exercised now to make sure that
future feature adjustments to the field can maintain backwards
compatibility.
Signed-off-by: Aaron Conole <aconole@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Add a basic set of fields to print in a 'dpflow' format.  This will be
used by future commits to check for flow fields after parsing, as
well as verifying the flow fields pushed into the kernel from
userspace.
Signed-off-by: Aaron Conole <aconole@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Includes an associated test to generate netns and connect
interfaces, with the option to include packet tracing.

This will be used in the future when flow support is added
for additional test cases.
Signed-off-by: Aaron Conole <aconole@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

If the 1PPS output was enabled and then lan8841 was configured to be a
follower, then target clock which is used to generate the 1PPS was not
configure correctly. The problem was that for each adjustments of the
time, also the nanosecond part of the target clock was changed.
Therefore the initial nanosecond part of the target clock was changed.
The issue can be observed if both the leader and the follower are
generating 1PPS and see that their PPS are not aligned even if the time
is allined.
The fix consists of not modifying the nanosecond part of the target
clock when adjusting the time. In this way the 1PPS get also aligned.

Fixes: e4ed8ba0 ("net: phy: micrel: Add support for PTP_PF_PEROUT for lan8841")
Signed-off-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Jakub Kicinski says:

====================
page_pool: allow caching from safely localized NAPI

I went back to the explicit "are we in NAPI method", mostly
because I don't like having both around :( (even tho I maintain
that in_softirq() && !in_hardirq() is as safe, as softirqs do
not nest).

Still returning the skbs to a CPU, tho, not to the NAPI instance.
I reckon we could create a small refcounted struct per NAPI instance
which would allow sockets and other users so hold a persisent
and safe reference. But that's a bigger change, and I get 90+%
recycling thru the cache with just these patches (for RR and
streaming tests with 100% CPU use it's almost 100%).

Some numbers for streaming test with 100% CPU use (from previous version,
but really they perform the same):

		HW-GRO				page=page
		before		after		before		after
recycle:
cached:			0	138669686		0	150197505
cache_full:		0	   223391		0	    74582
ring:		138551933         9997191	149299454		0
ring_full: 		0             488	     3154	   127590
released_refcnt:	0		0		0		0

alloc:
fast:		136491361	148615710	146969587	150322859
slow:		     1772	     1799	      144	      105
slow_high_order:	0		0		0		0
empty:		     1772	     1799	      144	      105
refill:		  2165245	   156302	  2332880	     2128
waive:			0		0		0		0

v1: https://lore.kernel.org/all/20230411201800.596103-1-kuba@kernel.org/
rfcv2: https://lore.kernel.org/all/20230405232100.103392-1-kuba@kernel.org/
====================

Link: https://lore.kernel.org/r/20230413042605.895677-1-kuba@kernel.orgSigned-off-by: Jakub Kicinski <kuba@kernel.org>

bnxt has 1:1 mapping of page pools and NAPIs, so it's safe
to hoook them up together.
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Tested-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Recent patches to mlx5 mentioned a regression when moving from
driver local page pool to only using the generic page pool code.
Page pool has two recycling paths (1) direct one, which runs in
safe NAPI context (basically consumer context, so producing
can be lockless); and (2) via a ptr_ring, which takes a spin
lock because the freeing can happen from any CPU; producer
and consumer may run concurrently.

Since the page pool code was added, Eric introduced a revised version
of deferred skb freeing. TCP skbs are now usually returned to the CPU
which allocated them, and freed in softirq context. This places the
freeing (producing of pages back to the pool) enticingly close to
the allocation (consumer).

If we can prove that we're freeing in the same softirq context in which
the consumer NAPI will run - lockless use of the cache is perfectly fine,
no need for the lock.

Let drivers link the page pool to a NAPI instance. If the NAPI instance
is scheduled on the same CPU on which we're freeing - place the pages
in the direct cache.

With that and patched bnxt (XDP enabled to engage the page pool, sigh,
bnxt really needs page pool work :() I see a 2.6% perf boost with
a TCP stream test (app on a different physical core than softirq).

The CPU use of relevant functions decreases as expected:

  page_pool_refill_alloc_cache   1.17% -> 0%
  _raw_spin_lock                 2.41% -> 0.98%

Only consider lockless path to be safe when NAPI is scheduled
- in practice this should cover majority if not all of steady state
workloads. It's usually the NAPI kicking in that causes the skb flush.

The main case we'll miss out on is when application runs on the same
CPU as NAPI. In that case we don't use the deferred skb free path.
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Tested-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

We maintain a NAPI-local cache of skbs which is fed by napi_consume_skb().
Going forward we will also try to cache head and data pages.
Plumb the "are we in a normal NAPI context" information thru
deeper into the freeing path, up to skb_release_data() and
skb_free_head()/skb_pp_recycle(). The "not normal NAPI context"
comes from netpoll which passes budget of 0 to try to reap
the Tx completions but not perform any Rx.

Use "bool napi_safe" rather than bare "int budget",
the further we get from NAPI the more confusing the budget
argument may seem (particularly whether 0 or MAX is the
correct value to pass in when not in NAPI).
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Tested-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Check if patterns and arguments for modify header action
are supported and enable them accordingly.
Signed-off-by: Muhammad Sammar <muhammads@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

Support the pattern/args-based MODIFY_HDR and TNL_L3_TO_L2 actions in dbg dump
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

Set modify header action of size 1 directly on the STE for supporting
devices, thus reducing number of hops and cache misses.
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

Use the new accelerated action for decap L3 on RX side:
use the mechanism of pattern and argument same as in
modify-header action.
Signed-off-by: Erez Shitrit <erezsh@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

If there is support for pattern/args, use the new accelerated modify
header action for modify header and decap L3 actions.
Otherwise fall back to the old modify-header implementation.
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

While building the actions, add the pointer of the arguments for
accelerated modify list action into the action's attributes.
This will be used later on while building the specific STE
for this action.
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

Added new mechanism for handling arguments for modify-header action.
The new action "accelerated modify-header" asks for the arguments from
separated area from the pattern, this area accessed via general objects.
Handling of these object is done via the pool-manager struct.

When the new header patterns are supported, while loading the domain,
a few pools for argument creations will be created. The requests for
allocating/deallocating arg objects are done via the pool manager API.
Signed-off-by: Muhammad Sammar <muhammads@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

When allocating a QP we allocate an RQ and an SQ, the RQ is stored first
in memory and followed by the SQ.
This allocation is not physically continiuos - it may span across different
physical pages. SW Steering code always writes in pairs: 1BB write + 1BB read,
or 2 continuous BBs of GTA WQE.

This lead to an issue where RQ allocation was 4x16 which is equal to 1 WQE BB,
causing 1 BB offset in the page and splitting the GTA WQE between different
physical pages.

The solution was to create the RQ with a even number of BBs and to have the
RQ aligned to a page.
Signed-off-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

Instead of using the write buffer for reading we will use a dedicated
buffer only for reading ICM memory.
Due to the new support for args, we can have a case with pending_wc
being odd number, and with reading into the same write buffer, it is
possible to overwrite next write on the same slot.
For example:
pending_wc is 17 so the buffer for write is:
   | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
and we have requests as follows:
   r wr wr wr wr wr wr wr wr
Now, the first read will be written into the last write because we use
the same buffer for read and write, before it was written to the HW and
we will have a wrong data in the ICM area.
Signed-off-by: Erez Shitrit <erezsh@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

The accelerated modify header arguments are written in the HW area
with special WQE and specific data format.
New function was added to support writing of new argument type.
Note that GTA WQE is larger than READ and WRITE, so the queue
management logic was updated to support this.
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

Add functions for creation/destruction of the new type of general object.
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

This way we are able to allocate chunk for modify_headers from 2 types:
STEv0 that is allocated from the action area, and STEv1 that is allocating
the chunks from the special area for patterns.
Signed-off-by: Muhammad Sammar <muhammads@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

Starting with ConnectX-6 Dx, we use new design of modify_header FW object.
The current modify_header object allows for having only limited number
of FW objects, so the new design of pattern and argument allows pattern
reuse, saving memory, and having a large number of modify_header objects.
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

Move ACTION_CACHE_LINE_SIZE macro to header to be used by
the pattern functions as well.
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Alex Vesker <valex@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

Kevin Brodsky says:

====================
net: Finish up ->msg_control{,_user} split

Commit 1f466e1f ("net: cleanly handle kernel vs user buffers for
->msg_control") introduced the msg_control_user and
msg_control_is_user fields in struct msghdr, to ensure that user
pointers are represented as such. It also took care of converting most
users of struct msghdr::msg_control where user pointers are involved. It
did however miss a number of cases, and some code using msg_control
inappropriately has also appeared in the meantime.

This series is attempting to complete the split, by eliminating the
remaining cases where msg_control is used when in fact a user
pointer is stored in the union (patch 1).

It also addresses a couple of issues with msg_control_is_user: one where
it is not updated as it should (patch 2), and one where it is not
initialised (patch 3).

v1..v2:
* Split out the msg_control_is_user fixes into separate patches.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

do_ipv6_setsockopt() makes use of struct msghdr::msg_control in the
IPV6_2292PKTOPTIONS case. Make sure to initialise
msg_control_is_user accordingly.

Cc: Christoph Hellwig <hch@lst.de>
Cc: Eric Dumazet <edumazet@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Kevin Brodsky <kevin.brodsky@arm.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

cmsghdr_from_user_compat_to_kern() is an unusual case w.r.t. how
the kmsg->msg_control* fields are used. The input struct msghdr
holds a pointer to a user buffer, i.e. ksmg->msg_control_user is
active. However, upon success, a kernel pointer is stored in
kmsg->msg_control. kmsg->msg_control_is_user should therefore be
updated accordingly.

Cc: Christoph Hellwig <hch@lst.de>
Cc: Eric Dumazet <edumazet@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Kevin Brodsky <kevin.brodsky@arm.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

Since commit 1f466e1f ("net: cleanly handle kernel vs user
buffers for ->msg_control"), pointers to user buffers should be
stored in struct msghdr::msg_control_user, instead of the
msg_control field.  Most users of msg_control have already been
converted (where user buffers are involved), but not all of them.

This patch attempts to address the remaining cases. An exception is
made for null checks, as it should be safe to use msg_control
unconditionally for that purpose.

Cc: Christoph Hellwig <hch@lst.de>
Cc: Eric Dumazet <edumazet@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Kevin Brodsky <kevin.brodsky@arm.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

This replaces 'skb_queue_tail()' with 'virtio_vsock_skb_queue_tail()'.
The first one uses 'spin_lock_irqsave()', second uses 'spin_lock_bh()'.
There is no need to disable interrupts in the loopback transport as
there is no access to the queue with skbs from interrupt context. Both
virtio and vhost transports work in the same way.
Signed-off-by: Arseniy Krasnov <AVKrasnov@sberdevices.ru>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Haiyang Zhang says:

====================
net: mana: Add support for jumbo frame

The set adds support for jumbo frame,
with some optimization for the RX path.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

During probe, get the hardware-allowed max MTU by querying the device
configuration. Users can select MTU up to the device limit.
When XDP is in use, limit MTU settings so the buffer size is within
one page. And, when MTU is set to a too large value, XDP is not allowed
to run.
Also, to prevent changing MTU fails, and leaves the NIC in a bad state,
pre-allocate all buffers before starting the change. So in low memory
condition, it will return error, without affecting the NIC.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Update RX data path to allocate and use RX queue DMA buffers with
proper size based on potentially various MTU sizes.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Move out common buffer allocation code from mana_process_rx_cqe() and
mana_alloc_rx_wqe() to helper functions.
Refactor related variables so they can be changed in one place, and buffer
sizes are in sync.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Use napi_build_skb() instead of build_skb() to take advantage of the
NAPI percpu caches to obtain skbuff_head.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>