Add a selftest for io_uring zero copy Rx. This test cannot run locally
and requires a remote host to be configured in net.config. The remote
host must have hardware support for zero copy Rx as listed in the
documentation page. The test will restore the NIC config back to before
the test and is idempotent.
liburing is required to compile the test and be installed on the remote
host running the test.
Signed-off-by: David Wei <dw@davidwei.uk>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20250215000947.789731-12-dw@davidwei.uk
Signed-off-by: Jens Axboe <axboe@kernel.dk>
There are scenarios in which the zerocopy path can get a kernel buffer
instead of a net_iov and needs to copy it to the user, whether it is
because of mis-steering or simply getting an skb with the linear part.
In this case, grab a net_iov, copy into it and return it to the user as
normally.
At the moment the user doesn't get any indication whether there was a
copy or not, which is left for follow up work.
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: David Wei <dw@davidwei.uk>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20250215000947.789731-10-dw@davidwei.uk
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_zc_rx_tcp_recvmsg() continues until it fails or there is nothing to
receive. If the other side sends fast enough, we might get stuck in
io_zc_rx_tcp_recvmsg() producing more and more CQEs but not letting the
user to handle them leading to unbound latencies.
Break out of it based on an arbitrarily chosen limit, the upper layer
will either return to userspace or requeue the request.
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: David Wei <dw@davidwei.uk>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20250215000947.789731-9-dw@davidwei.uk
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Set the page pool memory provider for the rx queue configured for zero
copy to io_uring. Then the rx queue is reset using
netdev_rx_queue_restart() and netdev core + page pool will take care of
filling the rx queue from the io_uring zero copy memory provider.
For now, there is only one ifq so its destruction happens implicitly
during io_uring cleanup.
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: David Wei <dw@davidwei.uk>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20250215000947.789731-8-dw@davidwei.uk
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add io_uring opcode OP_RECV_ZC for doing zero copy reads out of a
socket. Only the connection should be land on the specific rx queue set
up for zero copy, and the socket must be handled by the io_uring
instance that the rx queue was registered for zero copy with. That's
because neither net_iovs / buffers from our queue can be read by outside
applications, nor zero copy is possible if traffic for the zero copy
connection goes to another queue. This coordination is outside of the
scope of this patch series. Also, any traffic directed to the zero copy
enabled queue is immediately visible to the application, which is why
CAP_NET_ADMIN is required at the registration step.
Of course, no data is actually read out of the socket, it has already
been copied by the netdev into userspace memory via DMA. OP_RECV_ZC
reads skbs out of the socket and checks that its frags are indeed
net_iovs that belong to io_uring. A cqe is queued for each one of these
frags.
Recall that each cqe is a big cqe, with the top half being an
io_uring_zcrx_cqe. The cqe res field contains the len or error. The
lower IORING_ZCRX_AREA_SHIFT bits of the struct io_uring_zcrx_cqe::off
field contain the offset relative to the start of the zero copy area.
The upper part of the off field is trivially zero, and will be used
to carry the area id.
For now, there is no limit as to how much work each OP_RECV_ZC request
does. It will attempt to drain a socket of all available data. This
request always operates in multishot mode.
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: David Wei <dw@davidwei.uk>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20250215000947.789731-7-dw@davidwei.uk
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Implement a page pool memory provider for io_uring to receieve in a
zero copy fashion. For that, the provider allocates user pages wrapped
around into struct net_iovs, that are stored in a previously registered
struct net_iov_area.
Unlike the traditional receive, that frees pages and returns them back
to the page pool right after data was copied to the user, e.g. inside
recv(2), we extend the lifetime until the user space confirms that it's
done processing the data. That's done by taking a net_iov reference.
When the user is done with the buffer, it must return it back to the
kernel by posting an entry into the refill ring, which is usually polled
off the io_uring memory provider callback in the page pool's netmem
allocation path.
There is also a separate set of per net_iov "user" references accounting
whether a buffer is currently given to the user (including possible
fragmentation).
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: David Wei <dw@davidwei.uk>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20250215000947.789731-5-dw@davidwei.uk
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add io_zcrx_area that represents a region of userspace memory that is
used for zero copy. During ifq registration, userspace passes in the
uaddr and len of userspace memory, which is then pinned by the kernel.
Each net_iov is mapped to one of these pages.
The freelist is a spinlock protected list that keeps track of all the
net_iovs/pages that aren't used.
For now, there is only one area per ifq and area registration happens
implicitly as part of ifq registration. There is no API for
adding/removing areas yet. The struct for area registration is there for
future extensibility once we support multiple areas and TCP devmem.
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: David Wei <dw@davidwei.uk>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20250215000947.789731-3-dw@davidwei.uk
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add a new object called an interface queue (ifq) that represents a net
rx queue that has been configured for zero copy. Each ifq is registered
using a new registration opcode IORING_REGISTER_ZCRX_IFQ.
The refill queue is allocated by the kernel and mapped by userspace
using a new offset IORING_OFF_RQ_RING, in a similar fashion to the main
SQ/CQ. It is used by userspace to return buffers that it is done with,
which will then be re-used by the netdev again.
The main CQ ring is used to notify userspace of received data by using
the upper 16 bytes of a big CQE as a new struct io_uring_zcrx_cqe. Each
entry contains the offset + len to the data.
For now, each io_uring instance only has a single ifq.
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: David Wei <dw@davidwei.uk>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20250215000947.789731-2-dw@davidwei.uk
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Merge networking zerocopy receive tree, to get the prep patches for
the io_uring rx zc support.
* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (63 commits)
net: add helpers for setting a memory provider on an rx queue
net: page_pool: add memory provider helpers
net: prepare for non devmem TCP memory providers
net: page_pool: add a mp hook to unregister_netdevice*
net: page_pool: add callback for mp info printing
netdev: add io_uring memory provider info
net: page_pool: create hooks for custom memory providers
net: generalise net_iov chunk owners
net: prefix devmem specific helpers
net: page_pool: don't cast mp param to devmem
tools: ynl: add all headers to makefile deps
eth: fbnic: set IFF_UNICAST_FLT to avoid enabling promiscuous mode when adding unicast addrs
eth: fbnic: add MAC address TCAM to debugfs
tools: ynl-gen: support limits using definitions
tools: ynl-gen: don't output external constants
net/mlx5e: Avoid WARN_ON when configuring MQPRIO with HTB offload enabled
net/mlx5e: Remove unused mlx5e_tc_flow_action struct
net/mlx5: Remove stray semicolon in LAG port selection table creation
net/mlx5e: Support FEC settings for 200G per lane link modes
net/mlx5: Add support for 200Gbps per lane link modes
...
8e5b3b89ec ("io_uring: remove struct io_tw_state::locked") removed the
only field of io_tw_state but kept it as a task work callback argument
to "forc[e] users not to invoke them carelessly out of a wrong context".
Passing the struct io_tw_state * argument adds a few instructions to all
callers that can't inline the functions and see the argument is unused.
So pass struct io_tw_state by value instead. Since it's a 0-sized value,
it can be passed without any instructions needed to initialize it.
Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
Link: https://lore.kernel.org/r/20250217022511.1150145-2-csander@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In preparation for changing how io_tw_state is passed, introduce a type
alias io_tw_token_t for struct io_tw_state *. This allows for changing
the representation in one place, without having to update the many
functions that just forward their struct io_tw_state * argument.
Also add a comment to struct io_tw_state to explain its purpose.
Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
Link: https://lore.kernel.org/r/20250217022511.1150145-1-csander@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Most callers of io_put_rsrc_node() already check that node is non-NULL:
- io_rsrc_data_free()
- io_sqe_buffer_register()
- io_reset_rsrc_node()
- io_req_put_rsrc_nodes() (REQ_F_BUF_NODE indicates non-NULL buf_node)
Only io_splice_cleanup() can call io_put_rsrc_node() with a NULL node.
So move the NULL check there.
Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
Link: https://lore.kernel.org/r/20250216225900.1075446-1-csander@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Current recv bundles are only supported for multishot receives, and
additionally they also always post at least 2 CQEs if more data is
available than what a buffer will hold. This happens because the initial
bundle recv will do a single buffer, and then do the rest of what is in
the socket as a followup receive. As shown in a test program, if 1k
buffers are available and 32k is available to receive in the socket,
you'd get the following completions:
bundle=1, mshot=0
cqe res 1024
cqe res 1024
[...]
cqe res 1024
bundle=1, mshot=1
cqe res 1024
cqe res 31744
where bundle=1 && mshot=0 will post 32 1k completions, and bundle=1 &&
mshot=1 will post a 1k completion and then a 31k completion.
To support bundle recv without multishot, it's possible to simply retry
the recv immediately and post a single completion, rather than split it
into two completions. With the below patch, the same test looks as
follows:
bundle=1, mshot=0
cqe res 32768
bundle=1, mshot=1
cqe res 32768
where mshot=0 works fine for bundles, and both of them post just a
single 32k completion rather than split it into separate completions.
Posting fewer completions is always a nice win, and not needing
multishot for proper bundle efficiency is nice for cases that can't
necessarily use multishot.
Reported-by: Norman Maurer <norman_maurer@apple.com>
Link: https://lore.kernel.org/r/184f9f92-a682-4205-a15d-89e18f664502@kernel.dk
Fixes: 2f9c9515bd ("io_uring/net: support bundles for recv")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Don't implement our own loop rolling and checking, just use the generic
helper to find and cancel requests.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Don't implement our own loop rolling and checking, just use the generic
helper to find and cancel requests.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Any opcode that is cancelable ends up defining its own cancel helper
for finding and canceling a specific request. Add a generic helper that
can be used for this purpose.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Any opcode that is cancelable ends up defining its own remove all
helper, which iterates the pending list and cancels matches. Add a
generic helper for it, which can be used by them.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Previously, the `hash` variable was initialized with `-1` and only
updated by io_get_next_work() if the current work was hashed. Commit
60cf46ae60 ("io-wq: hash dependent work") changed this to always
call io_get_work_hash() even if the work was not hashed. This caused
the `hash != -1U` check to always be true, adding some overhead for
the `hash->wait` code.
This patch fixes the regression by checking the `IO_WQ_WORK_HASHED`
flag.
Perf diff for a flood of `IORING_OP_NOP` with `IOSQE_ASYNC`:
38.55% -1.57% [kernel.kallsyms] [k] queued_spin_lock_slowpath
6.86% -0.72% [kernel.kallsyms] [k] io_worker_handle_work
0.10% +0.67% [kernel.kallsyms] [k] put_prev_entity
1.96% +0.59% [kernel.kallsyms] [k] io_nop_prep
3.31% -0.51% [kernel.kallsyms] [k] try_to_wake_up
7.18% -0.47% [kernel.kallsyms] [k] io_wq_free_work
Fixes: 60cf46ae60 ("io-wq: hash dependent work")
Cc: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Max Kellermann <max.kellermann@ionos.com>
Link: https://lore.kernel.org/r/20250128133927.3989681-6-max.kellermann@ionos.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Have separate linked lists for bounded and unbounded workers. This
way, io_acct_activate_free_worker() sees only workers relevant to it
and doesn't need to skip irrelevant ones. This speeds up the
linked list traversal (under acct->lock).
The `io_wq.lock` field is moved to `io_wq_acct.workers_lock`. It did
not actually protect "access to elements below", that is, not all of
them; it only protected access to the worker lists. By having two
locks instead of one, contention on this lock is reduced.
Signed-off-by: Max Kellermann <max.kellermann@ionos.com>
Link: https://lore.kernel.org/r/20250128133927.3989681-4-max.kellermann@ionos.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This replaces the `IO_WORKER_F_BOUND` flag. All code that checks this
flag is not interested in knowing whether this is a "bound" worker;
all it does with this flag is determine the `io_wq_acct` pointer. At
the cost of an extra pointer field, we can eliminate some fragile
pointer arithmetic. In turn, the `create_index` and `index` fields
are not needed anymore.
Signed-off-by: Max Kellermann <max.kellermann@ionos.com>
Link: https://lore.kernel.org/r/20250128133927.3989681-3-max.kellermann@ionos.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pull Kbuild fixes from Masahiro Yamada:
- Fix annoying logs when building tools in parallel
- Fix the Debian linux-headers package build again
- Fix the target triple detection for userspace programs on Clang
* tag 'kbuild-fixes-v6.14-2' of git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild:
modpost: Fix a few typos in a comment
kbuild: userprogs: fix bitsize and target detection on clang
kbuild: fix linux-headers package build when $(CC) cannot link userspace
tools: fix annoying "mkdir -p ..." logs when building tools in parallel
Pull driver core api addition from Greg KH:
"Here is a driver core new api for 6.14-rc3 that is being added to
allow platform devices from stop being abused.
It adds a new 'faux_device' structure and bus and api to allow almost
a straight or simpler conversion from platform devices that were not
really a platform device. It also comes with a binding for rust, with
an example driver in rust showing how it's used.
I'm adding this now so that the patches that convert the different
drivers and subsystems can all start flowing into linux-next now
through their different development trees, in time for 6.15-rc1.
We have a number that are already reviewed and tested, but adding
those conversions now doesn't seem right. For now, no one is using
this, and it passes all build tests from 0-day and linux-next, so all
should be good"
* tag 'driver-core-6.14-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core:
rust/kernel: Add faux device bindings
driver core: add a faux bus for use when a simple device/bus is needed
Pull serial driver fixes from Greg KH:
"Here are some small serial driver fixes for some reported problems.
Nothing major, just:
- sc16is7xx irq check fix
- 8250 fifo underflow fix
- serial_port and 8250 iotype fixes
Most of these have been in linux-next already, and all have passed
0-day testing"
* tag 'tty-6.14-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty:
serial: 8250: Fix fifo underflow on flush
serial: 8250_pnp: Remove unneeded ->iotype assignment
serial: 8250_platform: Remove unneeded ->iotype assignment
serial: 8250_of: Remove unneeded ->iotype assignment
serial: port: Make ->iotype validation global in __uart_read_properties()
serial: port: Always update ->iotype in __uart_read_properties()
serial: port: Assign ->iotype correctly when ->iobase is set
serial: sc16is7xx: Fix IRQ number check behavior
Pull USB fixes from Greg KH:
"Here are some small USB driver fixes, and new device ids, for
6.14-rc3. Lots of tiny stuff for reported problems, including:
- new device ids and quirks
- usb hub crash fix found by syzbot
- dwc2 driver fix
- dwc3 driver fixes
- uvc gadget driver fix
- cdc-acm driver fixes for a variety of different issues
- other tiny bugfixes
Almost all of these have been in linux-next this week, and all have
passed 0-day testing"
* tag 'usb-6.14-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb: (25 commits)
usb: typec: tcpm: PSSourceOffTimer timeout in PR_Swap enters ERROR_RECOVERY
usb: roles: set switch registered flag early on
usb: gadget: uvc: Fix unstarted kthread worker
USB: quirks: add USB_QUIRK_NO_LPM quirk for Teclast dist
usb: gadget: core: flush gadget workqueue after device removal
USB: gadget: f_midi: f_midi_complete to call queue_work
usb: core: fix pipe creation for get_bMaxPacketSize0
usb: dwc3: Fix timeout issue during controller enter/exit from halt state
USB: Add USB_QUIRK_NO_LPM quirk for sony xperia xz1 smartphone
USB: cdc-acm: Fill in Renesas R-Car D3 USB Download mode quirk
usb: cdc-acm: Fix handling of oversized fragments
usb: cdc-acm: Check control transfer buffer size before access
usb: xhci: Restore xhci_pci support for Renesas HCs
USB: pci-quirks: Fix HCCPARAMS register error for LS7A EHCI
USB: serial: option: drop MeiG Smart defines
USB: serial: option: fix Telit Cinterion FN990A name
USB: serial: option: add Telit Cinterion FN990B compositions
USB: serial: option: add MeiG Smart SLM828
usb: gadget: f_midi: fix MIDI Streaming descriptor lengths
usb: dwc2: gadget: remove of_node reference upon udc_stop
...
