Implemented XDP transmit hardware timestamp metadata for igc driver.
This patchset is tested with tools/testing/selftests/bpf/xdp_hw_metadata
on Intel ADL-S platform. Below are the test steps and results.
Test Step 1: Run xdp_hw_metadata app
sudo ./xdp_hw_metadata > /dev/shm/result.log
Test St
In current ping-pong design, xdp_hw_metadata will wait until the packet
transmition completely done, then only start to receive the next packet.
The current sleep interval is 10ms, which is unnecessary large. Typically,
a NIC does not need such a long time to transmit a packet. Furthermore,
during
This patch adds support to per-packet Tx hardware timestamp request to
AF_XDP zero-copy packet via XDP Tx metadata framework. Please note that
user needs to enable Tx HW timestamp capability via igc_ioctl() with
SIOCSHWTSTAMP cmd before sending xsk Tx hardware timestamp request.
Same as implementa
On Sun, Mar 3, 2024 at 3:30 AM Randy Dunlap wrote:
> On 3/2/24 14:10, Guenter Roeck wrote:
> > On Thu, Feb 29, 2024 at 12:21 PM Linus Torvalds
> > wrote:
> >> On Thu, 29 Feb 2024 at 01:23, Nikolai Kondrashov wrote:
> >>>
> >>> However, I think a better approach would be *not* to add the
> >>> .
CROSS_COMPILE
-CC := $(LLVM_PREFIX)clang$(LLVM_SUFFIX) $(CLANG_FLAGS) -fintegrated-as
+CC := $(CLANG) $(CLANG_FLAGS) -fintegrated-as
else
CC := $(CROSS_COMPILE)gcc
endif # LLVM
---
base-commit: d206a76d7d2726f3b096037f2079ce0bd3ba329b
change-id: 20240303-selftests-libmk-llvm-rfc-5fe3cfa9f094
Best regards,
--
Valentin Obst
On Thu, 29 Feb 2024 22:41:34 -0500
Steven Rostedt wrote:
> On Thu, 29 Feb 2024 17:52:16 +0900
> Masami Hiramatsu (Google) wrote:
>
> > Lol, I haven't allocate the entry data size when initialize rethook.
> > That's a bug.
> > Please try below.
>
> I'll wait to review patches 5,6,7 as I'm guess
Perhaps we can also add a section about these tests to the new
`Documentation/rust/testing.rst` [1]. We could mention that they exist,
how to run them, and link to the kselftest documentation for further
information.
Not necessary to resend, perhaps we can do that in a separate patch when
this pat
On Thu, 29 Feb 2024 22:37:53 -0500
Steven Rostedt wrote:
> On Mon, 26 Feb 2024 12:58:23 +0900
> "Masami Hiramatsu (Google)" wrote:
>
> > From: Masami Hiramatsu (Google)
> >
> > Instead of incrementing the trace_probe::nr_args, init it at
> > trace_probe_init().
> > This is a cleanup, so the
On Tue, Dec 12, 2023 at 12:46:25PM -0800, Sagi Shahar wrote:
> From: Erdem Aktas
>
> Verifies TDVMCALL READ and WRITE operations.
>
> Signed-off-by: Erdem Aktas
> Signed-off-by: Sagi Shahar
> Signed-off-by: Ackerley Tng
> Signed-off-by: Ryan Afranji
> ---
> .../kvm/include/x86_64/tdx/test_u
Hi,
Here is version 3 series of patches to support accessing function entry data
from function *return* probes (including kretprobe and fprobe-exit event).
The previous version is here;
https://lore.kernel.org/all/170891987362.609861.6767830614537418260.stgit@devnote2/
In this version, [1/8] is
From: Masami Hiramatsu (Google)
Fix to allocate fprobe::entry_data_size buffer with rethook instances.
If fprobe doesn't allocate entry_data_size buffer for each rethook instance,
fprobe entry handler can cause a buffer overrun when storing entry data in
entry handler.
Link:
https://lore.kernel
From: Masami Hiramatsu (Google)
Despite the fprobe event, "Kretprobe" was commented. So fix it.
Signed-off-by: Masami Hiramatsu (Google)
Reviewed-by: Steven Rostedt (Google)
---
kernel/trace/trace_fprobe.c |2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/trace/tr
From: Masami Hiramatsu (Google)
Cleanup traceprobe_parse_probe_arg_body() to split out the
type parser and post-processing part of fetch_insn.
This makes no functional change.
Signed-off-by: Masami Hiramatsu (Google)
Reviewed-by: Steven Rostedt (Google)
---
kernel/trace/trace_probe.c | 230 +
From: Masami Hiramatsu (Google)
Instead of incrementing the trace_probe::nr_args, init it at
trace_probe_init(). Without this change, there is no way to get the number
of trace_probe arguments while parsing it.
This is a cleanup, so the behavior is not changed.
Signed-off-by: Masami Hiramatsu (G
From: Masami Hiramatsu (Google)
Remove redundant #else block for BTF args from README message.
This is a cleanup, so no change on the message.
Signed-off-by: Masami Hiramatsu (Google)
Reviewed-by: Steven Rostedt (Google)
---
kernel/trace/trace.c |4 +---
1 file changed, 1 insertion(+), 3
From: Masami Hiramatsu (Google)
Support accessing $argN in the return probe events. This will help users to
record entry data in function return (exit) event for simplfing the function
entry/exit information in one event, and record the result values (e.g.
allocated object/initialized object) at
From: Masami Hiramatsu (Google)
Add kretprobe and function exit probe test cases for checking whether
those can access entry arguments at function exit correctly.
Signed-off-by: Masami Hiramatsu (Google)
---
.../ftrace/test.d/dynevent/fprobe_entry_arg.tc | 18 ++
.../ftra
From: Masami Hiramatsu (Google)
Add a notes about the entry argument access at function exit probes for
kprobes and fprobe trace event.
Signed-off-by: Masami Hiramatsu (Google)
---
Changes in v3:
- Add usage example in fprobetrace.rst.
---
Documentation/trace/fprobetrace.rst | 31
On 03.03.2024 15:48, Valentin Obst wrote:
Perhaps we can also add a section about these tests to the new
`Documentation/rust/testing.rst` [1]. We could mention that they exist,
how to run them, and link to the kselftest documentation for further
information.
Not necessary to resend, perhaps we c
19 matches
Mail list logo
