Hi,
Here is the v3 patch to support polling on event 'hist' file.
The previous version is here;
https://lore.kernel.org/all/171998475175.54594.7244942110355338359.stgit@de…
This version is rebased on the v6.11-rc3.
Background
----------
There has been interest in allowing user programs to monitor kernel
events in real time. Ftrace provides `trace_pipe` interface to wait
on events in the ring buffer, but it is needed to wait until filling
up a page with events in the ring buffer. We can also peek the
`trace` file periodically, but that is inefficient way to monitor
a randomely happening event.
Overview
--------
This patch set allows user to `poll`(or `select`, `epoll`) on event
histogram interface. As you know each event has its own `hist` file
which shows histograms generated by trigger action. So user can set
a new hist trigger on any event you want to monitor, and poll on the
`hist` file until it is updated.
There are 2 poll events are supported, POLLIN and POLLPRI. POLLIN
means that there are any readable update on `hist` file and this
event will be flashed only when you call read(). So, this is
useful if you want to read the histogram periodically.
The other POLLPRI event is for monitoring trace event. Like the
POLLIN, this will be returned when the histogram is updated, but
you don't need to read() the file and use poll() again.
Note that this waits for histogram update (not event arrival), thus
you must set a histogram on the event at first.
Usage
-----
Here is an example usage:
----
TRACEFS=/sys/kernel/tracing
EVENT=$TRACEFS/events/sched/sched_process_free
# setup histogram trigger and enable event
echo "hist:key=comm" >> $EVENT/trigger
echo 1 > $EVENT/enable
# Wait for update
poll pri $EVENT/hist
# Event arrived.
echo "process free event is comming"
tail $TRACEFS/trace
----
The 'poll' command is in the selftest patch.
You can take this series also from here;
https://git.kernel.org/pub/scm/linux/kernel/git/mhiramat/linux.git/log/?h=t…
Thank you,
---
Masami Hiramatsu (Google) (3):
tracing/hist: Add poll(POLLIN) support on hist file
tracing/hist: Support POLLPRI event for poll on histogram
selftests/tracing: Add hist poll() support test
include/linux/trace_events.h | 5 +
kernel/trace/trace_events.c | 18 ++++
kernel/trace/trace_events_hist.c | 101 +++++++++++++++++++-
tools/testing/selftests/ftrace/Makefile | 2
tools/testing/selftests/ftrace/poll.c | 62 ++++++++++++
.../ftrace/test.d/trigger/trigger-hist-poll.tc | 74 +++++++++++++++
6 files changed, 259 insertions(+), 3 deletions(-)
create mode 100644 tools/testing/selftests/ftrace/poll.c
create mode 100644 tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-poll.tc
--
Masami Hiramatsu (Google) <mhiramat(a)kernel.org>
Change the parameter expected_buf from (const void *) to (const char *)
in the function __recvpair() as per the feedback in v1.
Add Fixes tag as per feedback in v1.
This change fixes the below warnings during test compilation:
```
In file included from msg_oob.c:14:
msg_oob.c: In function ‘__recvpair’:
../../kselftest_harness.h:106:40: warning: format ‘%s’ expects argument
of type ‘char *’,but argument 6 has type ‘const void *’ [-Wformat=]
../../kselftest_harness.h:101:17: note: in expansion of macro ‘__TH_LOG’
msg_oob.c:235:17: note: in expansion of macro ‘TH_LOG’
../../kselftest_harness.h:106:40: warning: format ‘%s’ expects argument
of type ‘char *’,but argument 6 has type ‘const void *’ [-Wformat=]
../../kselftest_harness.h:101:17: note: in expansion of macro ‘__TH_LOG’
msg_oob.c:259:25: note: in expansion of macro ‘TH_LOG’
```
v1:
lore.kernel.org/netdev/20240810134037.669765-1-jain.abhinav177@gmail.com
Fixes: d098d77232c3 ("selftest: af_unix: Add msg_oob.c.")
Signed-off-by: Abhinav Jain <jain.abhinav177(a)gmail.com>
---
tools/testing/selftests/net/af_unix/msg_oob.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/testing/selftests/net/af_unix/msg_oob.c b/tools/testing/selftests/net/af_unix/msg_oob.c
index 16d0c172eaeb..535eb2c3d7d1 100644
--- a/tools/testing/selftests/net/af_unix/msg_oob.c
+++ b/tools/testing/selftests/net/af_unix/msg_oob.c
@@ -209,7 +209,7 @@ static void __sendpair(struct __test_metadata *_metadata,
static void __recvpair(struct __test_metadata *_metadata,
FIXTURE_DATA(msg_oob) *self,
- const void *expected_buf, int expected_len,
+ const char *expected_buf, int expected_len,
int buf_len, int flags)
{
int i, ret[2], recv_errno[2], expected_errno = 0;
--
2.34.1
There are 2 issues for the current udpgro test. The first one is the testing
doesn't record all the failures, which may report pass but the test actually
failed. e.g.
https://netdev-3.bots.linux.dev/vmksft-net/results/725661/45-udpgro-sh/stdo…
The other one is after commit d7db7775ea2e ("net: veth: do not manipulate
GRO when using XDP"), there is no need to load xdp program to enable GRO
on veth device.
Hangbin Liu (2):
selftests: udpgro: report error when receive failed
selftests: udpgro: no need to load xdp for gro
tools/testing/selftests/net/udpgro.sh | 50 +++++++++++++--------------
1 file changed, 25 insertions(+), 25 deletions(-)
--
2.45.0
Add documentation outlining the usage and details of devmem TCP.
Signed-off-by: Mina Almasry <almasrymina(a)google.com>
Reviewed-by: Bagas Sanjaya <bagasdotme(a)gmail.com>
Reviewed-by: Donald Hunter <donald.hunter(a)gmail.com>
---
v16:
- Add documentation on unbinding the NIC from dmabuf (Donald).
- Add note that any dmabuf should work (Donald).
v9: https://lore.kernel.org/netdev/20240403002053.2376017-14-almasrymina@google…
- Bagas doc suggestions.
v8:
- Applied docs suggestions (Randy). Thanks!
v7:
- Applied docs suggestions (Jakub).
v2:
- Missing spdx (simon)
- add to index.rst (simon)
---
Documentation/networking/devmem.rst | 269 ++++++++++++++++++++++++++++
Documentation/networking/index.rst | 1 +
2 files changed, 270 insertions(+)
create mode 100644 Documentation/networking/devmem.rst
diff --git a/Documentation/networking/devmem.rst b/Documentation/networking/devmem.rst
new file mode 100644
index 000000000000..417fc977844e
--- /dev/null
+++ b/Documentation/networking/devmem.rst
@@ -0,0 +1,269 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=================
+Device Memory TCP
+=================
+
+
+Intro
+=====
+
+Device memory TCP (devmem TCP) enables receiving data directly into device
+memory (dmabuf). The feature is currently implemented for TCP sockets.
+
+
+Opportunity
+-----------
+
+A large number of data transfers have device memory as the source and/or
+destination. Accelerators drastically increased the prevalence of such
+transfers. Some examples include:
+
+- Distributed training, where ML accelerators, such as GPUs on different hosts,
+ exchange data.
+
+- Distributed raw block storage applications transfer large amounts of data with
+ remote SSDs. Much of this data does not require host processing.
+
+Typically the Device-to-Device data transfers in the network are implemented as
+the following low-level operations: Device-to-Host copy, Host-to-Host network
+transfer, and Host-to-Device copy.
+
+The flow involving host copies is suboptimal, especially for bulk data transfers,
+and can put significant strains on system resources such as host memory
+bandwidth and PCIe bandwidth.
+
+Devmem TCP optimizes this use case by implementing socket APIs that enable
+the user to receive incoming network packets directly into device memory.
+
+Packet payloads go directly from the NIC to device memory.
+
+Packet headers go to host memory and are processed by the TCP/IP stack
+normally. The NIC must support header split to achieve this.
+
+Advantages:
+
+- Alleviate host memory bandwidth pressure, compared to existing
+ network-transfer + device-copy semantics.
+
+- Alleviate PCIe bandwidth pressure, by limiting data transfer to the lowest
+ level of the PCIe tree, compared to the traditional path which sends data
+ through the root complex.
+
+
+More Info
+---------
+
+ slides, video
+ https://netdevconf.org/0x17/sessions/talk/device-memory-tcp.html
+
+ patchset
+ [RFC PATCH v6 00/12] Device Memory TCP
+ https://lore.kernel.org/netdev/20240305020153.2787423-1-almasrymina@google.…
+
+
+Interface
+=========
+
+
+Example
+-------
+
+tools/testing/selftests/net/ncdevmem.c:do_server shows an example of setting up
+the RX path of this API.
+
+
+NIC Setup
+---------
+
+Header split, flow steering, & RSS are required features for devmem TCP.
+
+Header split is used to split incoming packets into a header buffer in host
+memory, and a payload buffer in device memory.
+
+Flow steering & RSS are used to ensure that only flows targeting devmem land on
+an RX queue bound to devmem.
+
+Enable header split & flow steering::
+
+ # enable header split
+ ethtool -G eth1 tcp-data-split on
+
+
+ # enable flow steering
+ ethtool -K eth1 ntuple on
+
+Configure RSS to steer all traffic away from the target RX queue (queue 15 in
+this example)::
+
+ ethtool --set-rxfh-indir eth1 equal 15
+
+
+The user must bind a dmabuf to any number of RX queues on a given NIC using
+the netlink API::
+
+ /* Bind dmabuf to NIC RX queue 15 */
+ struct netdev_queue *queues;
+ queues = malloc(sizeof(*queues) * 1);
+
+ queues[0]._present.type = 1;
+ queues[0]._present.idx = 1;
+ queues[0].type = NETDEV_RX_QUEUE_TYPE_RX;
+ queues[0].idx = 15;
+
+ *ys = ynl_sock_create(&ynl_netdev_family, &yerr);
+
+ req = netdev_bind_rx_req_alloc();
+ netdev_bind_rx_req_set_ifindex(req, 1 /* ifindex */);
+ netdev_bind_rx_req_set_dmabuf_fd(req, dmabuf_fd);
+ __netdev_bind_rx_req_set_queues(req, queues, n_queue_index);
+
+ rsp = netdev_bind_rx(*ys, req);
+
+ dmabuf_id = rsp->dmabuf_id;
+
+
+The netlink API returns a dmabuf_id: a unique ID that refers to this dmabuf
+that has been bound.
+
+The user can unbind the dmabuf from the netdevice by closing the netlink socket
+that established the binding. We do this so that the binding is automatically
+unbound even if the userspace process crashes.
+
+Note that any reasonably well-behaved dmabuf from any exporter should work with
+devmem TCP, even if the dmabuf is not actually backed by devmem. An example of
+this is udmabuf, which wraps user memory (non-devmem) in a dmabuf.
+
+
+Socket Setup
+------------
+
+The socket must be flow steered to the dmabuf bound RX queue::
+
+ ethtool -N eth1 flow-type tcp4 ... queue 15,
+
+
+Receiving data
+--------------
+
+The user application must signal to the kernel that it is capable of receiving
+devmem data by passing the MSG_SOCK_DEVMEM flag to recvmsg::
+
+ ret = recvmsg(fd, &msg, MSG_SOCK_DEVMEM);
+
+Applications that do not specify the MSG_SOCK_DEVMEM flag will receive an EFAULT
+on devmem data.
+
+Devmem data is received directly into the dmabuf bound to the NIC in 'NIC
+Setup', and the kernel signals such to the user via the SCM_DEVMEM_* cmsgs::
+
+ for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) {
+ if (cm->cmsg_level != SOL_SOCKET ||
+ (cm->cmsg_type != SCM_DEVMEM_DMABUF &&
+ cm->cmsg_type != SCM_DEVMEM_LINEAR))
+ continue;
+
+ dmabuf_cmsg = (struct dmabuf_cmsg *)CMSG_DATA(cm);
+
+ if (cm->cmsg_type == SCM_DEVMEM_DMABUF) {
+ /* Frag landed in dmabuf.
+ *
+ * dmabuf_cmsg->dmabuf_id is the dmabuf the
+ * frag landed on.
+ *
+ * dmabuf_cmsg->frag_offset is the offset into
+ * the dmabuf where the frag starts.
+ *
+ * dmabuf_cmsg->frag_size is the size of the
+ * frag.
+ *
+ * dmabuf_cmsg->frag_token is a token used to
+ * refer to this frag for later freeing.
+ */
+
+ struct dmabuf_token token;
+ token.token_start = dmabuf_cmsg->frag_token;
+ token.token_count = 1;
+ continue;
+ }
+
+ if (cm->cmsg_type == SCM_DEVMEM_LINEAR)
+ /* Frag landed in linear buffer.
+ *
+ * dmabuf_cmsg->frag_size is the size of the
+ * frag.
+ */
+ continue;
+
+ }
+
+Applications may receive 2 cmsgs:
+
+- SCM_DEVMEM_DMABUF: this indicates the fragment landed in the dmabuf indicated
+ by dmabuf_id.
+
+- SCM_DEVMEM_LINEAR: this indicates the fragment landed in the linear buffer.
+ This typically happens when the NIC is unable to split the packet at the
+ header boundary, such that part (or all) of the payload landed in host
+ memory.
+
+Applications may receive no SO_DEVMEM_* cmsgs. That indicates non-devmem,
+regular TCP data that landed on an RX queue not bound to a dmabuf.
+
+
+Freeing frags
+-------------
+
+Frags received via SCM_DEVMEM_DMABUF are pinned by the kernel while the user
+processes the frag. The user must return the frag to the kernel via
+SO_DEVMEM_DONTNEED::
+
+ ret = setsockopt(client_fd, SOL_SOCKET, SO_DEVMEM_DONTNEED, &token,
+ sizeof(token));
+
+The user must ensure the tokens are returned to the kernel in a timely manner.
+Failure to do so will exhaust the limited dmabuf that is bound to the RX queue
+and will lead to packet drops.
+
+
+Implementation & Caveats
+========================
+
+Unreadable skbs
+---------------
+
+Devmem payloads are inaccessible to the kernel processing the packets. This
+results in a few quirks for payloads of devmem skbs:
+
+- Loopback is not functional. Loopback relies on copying the payload, which is
+ not possible with devmem skbs.
+
+- Software checksum calculation fails.
+
+- TCP Dump and bpf can't access devmem packet payloads.
+
+
+Testing
+=======
+
+More realistic example code can be found in the kernel source under
+tools/testing/selftests/net/ncdevmem.c
+
+ncdevmem is a devmem TCP netcat. It works very similarly to netcat, but
+receives data directly into a udmabuf.
+
+To run ncdevmem, you need to run it on a server on the machine under test, and
+you need to run netcat on a peer to provide the TX data.
+
+ncdevmem has a validation mode as well that expects a repeating pattern of
+incoming data and validates it as such. For example, you can launch
+ncdevmem on the server by::
+
+ ncdevmem -s <server IP> -c <client IP> -f eth1 -d 3 -n 0000:06:00.0 -l \
+ -p 5201 -v 7
+
+On client side, use regular netcat to send TX data to ncdevmem process
+on the server::
+
+ yes $(echo -e \\x01\\x02\\x03\\x04\\x05\\x06) | \
+ tr \\n \\0 | head -c 5G | nc <server IP> 5201 -p 5201
diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index d1af04b952f8..0be9924db642 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -49,6 +49,7 @@ Contents:
cdc_mbim
dccp
dctcp
+ devmem
dns_resolver
driver
eql
--
2.46.0.76.ge559c4bf1a-goog