- Linux-kselftest-mirror - lists.linaro.org

[PATCH] kunit: tool: Build compile_commands.json

by Brendan Jackman

compile_commands.json is used by clangd[1] to provide code navigation and completion functionality to editors. See [2] for an example configuration that includes this functionality for VSCode. It can currently be built manually when using kunit.py, by running: ./scripts/clang-tools/gen_compile_commands.py -d .kunit With this change however, it's built automatically so you don't need to manually keep it up to date. Unlike the manual approach, having make build the compile_commands.json means that it appears in the build output tree instead of at the root of the source tree, so you'll need to add --compile-commands-dir= to your clangd args for it to be found. [1] https://clangd.llvm.org/ [2] https://github.com/FlorentRevest/linux-kernel-vscode Signed-off-by: Brendan Jackman <jackmanb(a)google.com> --- tools/testing/kunit/kunit_kernel.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index 7254c110ff23..61931c4926fd 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -72,7 +72,8 @@ class LinuxSourceTreeOperations: raise ConfigError(e.output.decode()) def make(self, jobs: int, build_dir: str, make_options: Optional[List[str]]) -> None: - command = ['make', 'ARCH=' + self._linux_arch, 'O=' + build_dir, '--jobs=' + str(jobs)] + command = ['make', 'all', 'compile_commands.json', 'ARCH=' + self._linux_arch, + 'O=' + build_dir, '--jobs=' + str(jobs)] if make_options: command.extend(make_options) if self._cross_compile: --- base-commit: 3c999d1ae3c75991902a1a7dad0cb62c2a3008b4 change-id: 20240516-kunit-compile-commands-d994074fc2be Best regards, -- Brendan Jackman <jackmanb(a)google.com>

9 months, 3 weeks

3
2
0 0

[PATCH v5] lib/math: Add int_pow test suite

by Luis Felipe Hernandez

Adds test suite for integer based power function. Signed-off-by: Luis Felipe Hernandez <luis.hernandez093(a)gmail.com> --- Changes in v5: - Fix kernel test bot warning - Rebase with latest Changes in v4: - Address checkpatch warning and make kconfig description longer - Use GPL-2.0-only for consistency - Spelling fix fith -> fifth Changes in v3: - Fix compiler warning: explicitly define constant as unsigned int - Add changes in patch revisions Changes in v2: - Address review feedback - Add kconfig entry - Use correct dir and file convention for KUnit - Fix typo - Remove unused static_stub header - Refactor test suite to use paramerterized test cases - Add close to max allowable value to in large_result test case - Add test case with non-power of two exponent - Fix module license --- lib/Kconfig.debug | 16 +++++++++++ lib/math/Makefile | 1 + lib/math/tests/Makefile | 3 ++ lib/math/tests/int_pow_kunit.c | 52 ++++++++++++++++++++++++++++++++++ 4 files changed, 72 insertions(+) create mode 100644 lib/math/tests/Makefile create mode 100644 lib/math/tests/int_pow_kunit.c diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index a30c03a66172..c415f8ca43a7 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -3051,3 +3051,19 @@ config RUST_KERNEL_DOCTESTS endmenu # "Rust" endmenu # Kernel hacking + +config INT_POW_TEST + tristate "Integer exponentiation (int_pow) test" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS + help + This option enables the KUnit test suite for the int_pow function, + which performs integer exponentiation. The test suite is designed to + verify that the implementation of int_pow correctly computes the power + of a given base raised to a given exponent. + + Enabling this option will include tests that check various scenarios + and edge cases to ensure the accuracy and reliability of the exponentiation + function. + + If unsure, say N diff --git a/lib/math/Makefile b/lib/math/Makefile index 91fcdb0c9efe..3c1f92a7459d 100644 --- a/lib/math/Makefile +++ b/lib/math/Makefile @@ -5,5 +5,6 @@ obj-$(CONFIG_CORDIC) += cordic.o obj-$(CONFIG_PRIME_NUMBERS) += prime_numbers.o obj-$(CONFIG_RATIONAL) += rational.o +obj-$(CONFIG_INT_POW_TEST) += tests/int_pow_kunit.o obj-$(CONFIG_TEST_DIV64) += test_div64.o obj-$(CONFIG_RATIONAL_KUNIT_TEST) += rational-test.o diff --git a/lib/math/tests/Makefile b/lib/math/tests/Makefile new file mode 100644 index 000000000000..6a169123320a --- /dev/null +++ b/lib/math/tests/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only + +obj-$(CONFIG_INT_POW_TEST) += int_pow_kunit.o diff --git a/lib/math/tests/int_pow_kunit.c b/lib/math/tests/int_pow_kunit.c new file mode 100644 index 000000000000..34b33677d458 --- /dev/null +++ b/lib/math/tests/int_pow_kunit.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <kunit/test.h> +#include <linux/math.h> + +struct test_case_params { + u64 base; + unsigned int exponent; + u64 expected_result; + const char *name; +}; + +static const struct test_case_params params[] = { + { 64, 0, 1, "Power of zero" }, + { 64, 1, 64, "Power of one"}, + { 0, 5, 0, "Base zero" }, + { 1, 64, 1, "Base one" }, + { 2, 2, 4, "Two squared"}, + { 2, 3, 8, "Two cubed"}, + { 5, 5, 3125, "Five raised to the fifth power" }, + { U64_MAX, 1, U64_MAX, "Max base" }, + { 2, 63, 9223372036854775808ULL, "Large result"}, +}; + +static void get_desc(const struct test_case_params *tc, char *desc) +{ + strscpy(desc, tc->name, KUNIT_PARAM_DESC_SIZE); +} + +KUNIT_ARRAY_PARAM(int_pow, params, get_desc); + +static void int_pow_test(struct kunit *test) +{ + const struct test_case_params *tc = (const struct test_case_params *)test->param_value; + + KUNIT_EXPECT_EQ(test, tc->expected_result, int_pow(tc->base, tc->exponent)); +} + +static struct kunit_case math_int_pow_test_cases[] = { + KUNIT_CASE_PARAM(int_pow_test, int_pow_gen_params), + {} +}; + +static struct kunit_suite int_pow_test_suite = { + .name = "math-int_pow", + .test_cases = math_int_pow_test_cases, +}; + +kunit_test_suites(&int_pow_test_suite); + +MODULE_DESCRIPTION("math.int_pow KUnit test suite"); +MODULE_LICENSE("GPL"); -- 2.46.0

9 months, 3 weeks

3
2
0 0

[PATCH v2 0/3] selftests: kvm: s390: Add ucontrol memory selftests

by Christoph Schlameuss

This patch series adds a some not yet picked selftests to the kvm s390x selftest suite. The additional test cases are covering: * Assert KVM_EXIT_S390_UCONTROL exit on not mapped memory access * Assert functionality of storage keys in ucontrol VM * Assert that memory region operations are rejected for ucontrol VMs Running the test cases requires sys_admin capabilities to start the ucontrol VM. This can be achieved by running as root or with a command like: sudo setpriv --reuid nobody --inh-caps -all,+sys_admin \ --ambient-caps -all,+sys_admin --bounding-set -all,+sys_admin \ ./ucontrol_test --- The patches in this series have been part of the previous patch series. The test cases added here do depend on the fixture added in the earlier patches. From v5 PATCH 7-9 the segment and page table generation has been removed and DAT has been disabled. Since DAT is not necessary to validate the KVM code. https://lore.kernel.org/kvm/20240807154512.316936-1-schlameuss@linux.ibm.co… v2: - Reenable KSS intercept and handle it within skey test. - Modify the checked register between storing (sske) and reading (iske) it within the test program to make sure the. - Add an additional state assertion in the end of uc_skey - Fix some typos and white spaces. v1: - Remove segment and page table generation and disable DAT. This is not necessary to validate the KVM code. Christoph Schlameuss (3): selftests: kvm: s390: Add uc_map_unmap VM test case selftests: kvm: s390: Add uc_skey VM test case selftests: kvm: s390: Verify reject memory region operations for ucontrol VMs .../selftests/kvm/s390x/ucontrol_test.c | 232 +++++++++++++++++- 1 file changed, 230 insertions(+), 2 deletions(-) -- 2.46.0

9 months, 3 weeks

2
6
0 0

[PATCH v2] selftest/powerpc/benchmark: remove requirement libc-dev

by Madhavan Srinivasan

Currently exec-target.c file is linked as static and this post a requirement to install libc dev package to build. Without it, build-break when compiling selftest/powerpc/benchmark. CC exec_target /usr/bin/ld: cannot find -lc: No such file or directory collect2: error: ld returned 1 exit status exec_target.c is using "syscall" library function which could be replaced with a inline assembly and the same is proposed as a fix here. Suggested-by: Michael Ellerman <mpe(a)ellerman.id.au> Signed-off-by: Madhavan Srinivasan <maddy(a)linux.ibm.com> --- Chnagelog v1: - Add comment for clobber register and proper list of clobber registers as suggested by Michael Ellerman and Christophe Leroy .../selftests/powerpc/benchmarks/Makefile | 2 +- .../selftests/powerpc/benchmarks/exec_target.c | 16 ++++++++++++++-- 2 files changed, 15 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/powerpc/benchmarks/Makefile b/tools/testing/selftests/powerpc/benchmarks/Makefile index 1321922038d0..ca4483c238b9 100644 --- a/tools/testing/selftests/powerpc/benchmarks/Makefile +++ b/tools/testing/selftests/powerpc/benchmarks/Makefile @@ -18,4 +18,4 @@ $(OUTPUT)/context_switch: LDLIBS += -lpthread $(OUTPUT)/fork: LDLIBS += -lpthread -$(OUTPUT)/exec_target: CFLAGS += -static -nostartfiles +$(OUTPUT)/exec_target: CFLAGS += -nostartfiles diff --git a/tools/testing/selftests/powerpc/benchmarks/exec_target.c b/tools/testing/selftests/powerpc/benchmarks/exec_target.c index c14b0fc1edde..a6408d3f26cd 100644 --- a/tools/testing/selftests/powerpc/benchmarks/exec_target.c +++ b/tools/testing/selftests/powerpc/benchmarks/exec_target.c @@ -7,10 +7,22 @@ */ #define _GNU_SOURCE -#include <unistd.h> #include <sys/syscall.h> void _start(void) { - syscall(SYS_exit, 0); + asm volatile ( + "li %%r0, %[sys_exit];" + "li %%r3, 0;" + "sc;" + : + : [sys_exit] "i" (SYS_exit) + /* + * "sc" will clobber r0, r3-r13, cr0, ctr, xer and memory. + * Even though sys_exit never returns, handle clobber + * registers. + */ + : "r0", "r3", "r4", "r5", "r6", "r7", "r8", "r9", "r10", + "r11", "r12", "r13", "cr0", "ctr", "xer", "memory" + ); } -- 2.45.2

9 months, 3 weeks

3
2
0 0

[PATCH RESEND v2 00/19] random: Resolve circular include dependency and include <linux/percpu.h>

by Uros Bizjak

Resent due to missing linux-kernel@ mailing list inclusion. There were several attempts to resolve circular include dependency after the addition of percpu.h: 1c9df907da83 ("random: fix circular include dependency on arm64 after addition of percpu.h"), c0842fbc1b18 ("random32: move the pseudo-random 32-bit definitions to prandom.h") and finally d9f29deb7fe8 ("prandom: Remove unused include") that completely removes the inclusion of <linux/percpu.h>. Due to legacy reasons, <linux/random.h> includes <linux/prandom.h>, but with the commit entry remark: --quote-- A further cleanup step would be to remove this from <linux/random.h> entirely, and make people who use the prandom infrastructure include just the new header file. That's a bit of a churn patch, but grepping for "prandom_" and "next_pseudo_random32" "struct rnd_state" should catch most users. But it turns out that that nice cleanup step is fairly painful, because a _lot_ of code currently seems to depend on the implicit include of <linux/random.h>, which can currently come in a lot of ways, including such fairly core headfers as <linux/net.h>. So the "nice cleanup" part may or may never happen. --/quote-- We would like to include <linux/percpu.h> in <linux/prandom.h>. In [1] we would like to repurpose __percpu tag as a named address space qualifier, where __percpu macro uses defines from <linux/percpu.h>. The major roadblock to inclusion of <linux/percpu.h> is the above mentioned legacy inclusion of <linux/prandom.h> in <linux/random.h> that causes circular include dependency that prevents <linux/percpu.h> inclusion. This patch series is the "nice cleanup" part that: a) Substitutes the inclusion of <linux/random.h> with the inclusion of <linux/prandom.h> where needed (patches 1 - 17). b) Removes legacy inclusion of <linux/prandom.h> from <linux/random.h> (patch 18). c) Includes <linux/percpu.h> in <linux/prandom.h> (patch 19). The whole series was tested by compiling the kernel for x86_64 allconfig and some popular architectures, namely arm64 defconfig, powerpc defconfig and loongarch defconfig. [1] https://lore.kernel.org/lkml/20240812115945.484051-4-ubizjak@gmail.com/ Cc: Dave Hansen <dave.hansen(a)linux.intel.com> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Borislav Petkov <bp(a)alien8.de> Cc: x86(a)kernel.org Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: Jani Nikula <jani.nikula(a)linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen(a)linux.intel.com> Cc: Rodrigo Vivi <rodrigo.vivi(a)intel.com> Cc: Tvrtko Ursulin <tursulin(a)ursulin.net> Cc: David Airlie <airlied(a)gmail.com> Cc: Daniel Vetter <daniel(a)ffwll.ch> Cc: Maarten Lankhorst <maarten.lankhorst(a)linux.intel.com> Cc: Maxime Ripard <mripard(a)kernel.org> Cc: Thomas Zimmermann <tzimmermann(a)suse.de> Cc: Hans Verkuil <hverkuil(a)xs4all.nl> Cc: Mauro Carvalho Chehab <mchehab(a)kernel.org> Cc: Miquel Raynal <miquel.raynal(a)bootlin.com> Cc: Richard Weinberger <richard(a)nod.at> Cc: Vignesh Raghavendra <vigneshr(a)ti.com> Cc: Eric Biggers <ebiggers(a)kernel.org> Cc: "Theodore Y. Ts'o" <tytso(a)mit.edu> Cc: Jaegeuk Kim <jaegeuk(a)kernel.org> Cc: "Jason A. Donenfeld" <Jason(a)zx2c4.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Hannes Reinecke <hare(a)suse.de> Cc: "James E.J. Bottomley" <James.Bottomley(a)HansenPartnership.com> Cc: "Martin K. Petersen" <martin.petersen(a)oracle.com> Cc: Alexei Starovoitov <ast(a)kernel.org> Cc: Daniel Borkmann <daniel(a)iogearbox.net> Cc: John Fastabend <john.fastabend(a)gmail.com> Cc: Andrii Nakryiko <andrii(a)kernel.org> Cc: Martin KaFai Lau <martin.lau(a)linux.dev> Cc: Eduard Zingerman <eddyz87(a)gmail.com> Cc: Song Liu <song(a)kernel.org> Cc: Yonghong Song <yonghong.song(a)linux.dev> Cc: KP Singh <kpsingh(a)kernel.org> Cc: Stanislav Fomichev <sdf(a)fomichev.me> Cc: Hao Luo <haoluo(a)google.com> Cc: Jiri Olsa <jolsa(a)kernel.org> Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Brendan Higgins <brendan.higgins(a)linux.dev> Cc: David Gow <davidgow(a)google.com> Cc: Rae Moar <rmoar(a)google.com> Cc: "David S. Miller" <davem(a)davemloft.net> Cc: Eric Dumazet <edumazet(a)google.com> Cc: Jakub Kicinski <kuba(a)kernel.org> Cc: Paolo Abeni <pabeni(a)redhat.com> Cc: Jiri Pirko <jiri(a)resnulli.us> Cc: Petr Mladek <pmladek(a)suse.com> Cc: Steven Rostedt <rostedt(a)goodmis.org> Cc: Andy Shevchenko <andriy.shevchenko(a)linux.intel.com> Cc: Rasmus Villemoes <linux(a)rasmusvillemoes.dk> Cc: Sergey Senozhatsky <senozhatsky(a)chromium.org> Cc: Stephen Hemminger <stephen(a)networkplumber.org> Cc: Jamal Hadi Salim <jhs(a)mojatatu.com> Cc: Cong Wang <xiyou.wangcong(a)gmail.com> Cc: Kent Overstreet <kent.overstreet(a)linux.dev> --- v2: - Reword commit messages to mention the removal of legacy inclusion of <linux/prandom.h> from <linux/random.h> - Add missing substitution in crypto/testmgr.c (reported by kernel test robot) - Add Acked-by:. Uros Bizjak (19): x86/kaslr: Include <linux/prandom.h> instead of <linux/random.h> crypto: testmgr: Include <linux/prandom.h> instead of <linux/random.h> drm/i915/selftests: Include <linux/prandom.h> instead of <linux/random.h> drm/lib: Include <linux/prandom.h> instead of <linux/random.h> media: vivid: Include <linux/prandom.h> in vivid-vid-cap.c mtd: tests: Include <linux/prandom.h> instead of <linux/random.h> fscrypt: Include <linux/once.h> in fs/crypto/keyring.c scsi: libfcoe: Include <linux/prandom.h> instead of <linux/random.h> bpf: Include <linux/prandom.h> instead of <linux/random.h> lib/interval_tree_test.c: Include <linux/prandom.h> instead of <linux/random.h> kunit: string-stream-test: Include <linux/prandom.h> instead of <linux/random.h> random32: Include <linux/prandom.h> instead of <linux/random.h> lib/rbtree-test: Include <linux/prandom.h> instead of <linux/random.h> bpf/tests: Include <linux/prandom.h> instead of <linux/random.h> lib/test_parman: Include <linux/prandom.h> instead of <linux/random.h> lib/test_scanf: Include <linux/prandom.h> instead of <linux/random.h> netem: Include <linux/prandom.h> in sch_netem.c random: Do not include <linux/prandom.h> in <linux/random.h> prandom: Include <linux/percpu.h> in <linux/prandom.h> arch/x86/mm/kaslr.c | 2 +- crypto/testmgr.c | 2 +- drivers/gpu/drm/i915/selftests/i915_gem.c | 2 +- drivers/gpu/drm/i915/selftests/i915_random.h | 2 +- drivers/gpu/drm/i915/selftests/scatterlist.c | 2 +- drivers/gpu/drm/lib/drm_random.h | 2 +- drivers/media/test-drivers/vivid/vivid-vid-cap.c | 1 + drivers/mtd/tests/oobtest.c | 2 +- drivers/mtd/tests/pagetest.c | 2 +- drivers/mtd/tests/subpagetest.c | 2 +- fs/crypto/keyring.c | 1 + include/linux/prandom.h | 1 + include/linux/random.h | 7 ------- include/scsi/libfcoe.h | 2 +- kernel/bpf/core.c | 2 +- lib/interval_tree_test.c | 2 +- lib/kunit/string-stream-test.c | 1 + lib/random32.c | 2 +- lib/rbtree_test.c | 2 +- lib/test_bpf.c | 2 +- lib/test_parman.c | 2 +- lib/test_scanf.c | 2 +- net/sched/sch_netem.c | 1 + 23 files changed, 22 insertions(+), 24 deletions(-) -- 2.46.0

9 months, 3 weeks

8
28
0 0

[PATCH net-next v26 00/13] Device Memory TCP

by Mina Almasry

v26: https://patchwork.kernel.org/project/netdevbpf/list/?series=888227&state=* ==== No major changes. Only applied Reviewed-by tags from Jakub and addressed reported nits. v25: https://patchwork.kernel.org/project/netdevbpf/list/?series=885396&state=* === Major changes: - Moved devmem.h and mp_dmabuf_devmem.h to internal header files. - Changed the page_pool_params to take in a queue_idx rather than a struct netdev_rx_queue. - Added WARN_ON_ONCE around __skb_checksum readability check and added check to skb_checksum_help(). Other more minor feedback addressed as well. v24: https://patchwork.kernel.org/project/netdevbpf/list/?series=884556&state=* ==== No major changes. Mostly addressing issues in the error paths of dmabuf binding, and code cleanups/improvements from reviewers: Changes: - Fix failing ynl regen error. - Error path fixes & extack error messages in dmabuf binding. - Code cleanup in introspection. - gitignore ynl.d generated file. Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v24/ v23: https://patchwork.kernel.org/project/netdevbpf/list/?series=882978&state=* ==== Fixing relatively minor issues called out in v22. (thanks again!) Mostly code cleanups, extack error messages, and minor reworks. Nothing major really changed, so the exact changes per commit is called in the commit messages. Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v23/ v22: https://patchwork.kernel.org/project/netdevbpf/list/?series=881158&state=* ==== v22 aims to resolve the pending issue pointed to in v21, which is the interaction with xdp. In this series I rebase on top of the minor refactor which refactors propagating xdp configuration to slave devices: https://patchwork.kernel.org/project/netdevbpf/list/?series=881994&state=* I then disable setting xdp on devices using memory providers, and propagating xdp configuration to devices using memory providers. Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v22/ v21: https://patchwork.kernel.org/project/netdevbpf/list/?series=880735&state=* ==== v20 addressed some comments and resolved a test failure, but introduced an unfortunate build error with a config edge case I wasn't testing. v21 simply resolves that error. Major Changes: - Resolve build error with CONFIG_PAGE_POOL=n && CONFIG_NET=y Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v21/ v20: https://patchwork.kernel.org/project/netdevbpf/list/?series=879373&state=* ==== v20 aims to resolve a couple of bug reports against v19, and addresses some review comments around the page_pool_check_memory_provider mechanism. Major changes: - Test edge cases such as header split disabled in selftest. - Change `offset = 0` back to `offset = offset - start` to resolve issue found in RX path by Taehee (thanks!) - Address a few comments around page_pool_check_memory_provider() from Pavel & Jakub. - Removed some unnecessary includes across various patches in the series. - Removed unnecessary EXPORT_SYMBOL(page_pool_mem_providers) (Jakub). - Fix regression caused by incorrect dev_get_max_mp_channel check, along with rename (Jakub). Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v20/ v19: https://patchwork.kernel.org/project/netdevbpf/list/?series=876852&state=* ==== v18 got a thorough review (thanks!), and this iteration addresses the feedback. Major changes: - Prevent deactivating mp bound queues. - Prevent installing xdp on mp bound netdevs, or installing mps on xdp installed netdevs. - Fix corner cases in netlink API vis-a-vis missing attributes. - Iron out the unreadable netmem driver support story. To be honest, the conversation with Jakub & Pavel got a bit confusing for me. I've implemented an approach in this set that makes sense to me, and AFAICT, addresses the requirements. It may be good as-is, or it may be a conversation starter/continuer. To be honest IMO there are many ways to skin this cat and I don't see an extremely strong reason to go for one approach over another. Here is one approach you may like. - Don't reset niov dma_addr on allocation & free. - Add some tests to the selftest that catches some of the issues around missing netlink attributes or deactivating mp-bound queues. Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v19/ v18: https://patchwork.kernel.org/project/netdevbpf/list/?series=874848&state=* ==== v17 got minor feedback: (a) to beef up the description on patch 1 and (b) to remove the leading underscores in the header definition. I applied (a). (b) seems to be against current conventions so I did not apply before further discussion. Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v17/ v17: https://patchwork.kernel.org/project/netdevbpf/list/?series=869900&state=* ==== v16 also got a very thorough review and some testing (thanks again!). Thes version addresses all the concerns reported on v15, in terms of feedback and issues reported. Major changes: - Use ASSERT_RTNL. - Moved around some of the page_pool helpers definitions so I can hide some netmem helpers in private files as Jakub suggested. - Don't make every net_iov hold a ref on the binding as Jakub suggested. - Fix issue reported by Taehee where we access queues after they have been freed. Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v17/ v16: https://patchwork.kernel.org/project/netdevbpf/list/?series=866353&state=* ==== v15 got a thorough review and some testing, and this version addresses almost all the feedback. Some more minor comments where the authors said it could be done later, I left out. Major changes: - Addition of dma-buf introspection to page-pool-get and queue-get. - Fixes to selftests suggested by Taehee. - Fixes to documentation suggested by Donald. - A couple of suggestions and fixes to TCP patches by Eric and David. - Fixes to number assignements suggested by Arnd. - Use rtnl_lock()ing to guard against queue reconfiguration while the page_pool initialization is happening. (Jakub). - Fixes to a few warnings reproduced by Taehee. - Fixes to dma-buf binding suggested by Taehee and Jakub. - Fixes to netlink UAPI suggested by Jakub - Applied a number of Reviewed-bys and Acked-bys (including ones I lost from v13+). Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v16/ One caveat: Taehee reproduced a KASAN warning and reported it here: https://lore.kernel.org/netdev/CAMArcTUdCxOBYGF3vpbq=eBvqZfnc44KBaQTN7H-wqd… I estimate the issue to be minor and easily fixable: https://lore.kernel.org/netdev/CAHS8izNgaqC--GGE2xd85QB=utUnOHmioCsDd1TNxJW… I hope to be able to follow up with a fix to net tree as net-next closes imminently, but if this iteration doesn't make it in, I will repost with a fix squashed after net-next reopens, no problem. v15: https://patchwork.kernel.org/project/netdevbpf/list/?series=865481&state=* ==== No material changes in this version, only a fix to linking against libynl.a from the last version. Per Jakub's instructions I've pulled one of his patches into this series, and now use the new libynl.a correctly, I hope. As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v15/ v14: https://patchwork.kernel.org/project/netdevbpf/list/?series=865135&archive=… ==== No material changes in this version. Only rebase and re-verification on top of net-next. v13, I think, raced with commit ebad6d0334793 ("net/ipv4: Use nested-BH locking for ipv4_tcp_sk.") being merged to net-next that caused a patchwork failure to apply. This series should apply cleanly on commit c4532232fa2a4 ("selftests: net: remove unneeded IP_GRE config"). I did not wait the customary 24hr as Jakub said it's OK to repost as soon as I build test the rebased version: https://lore.kernel.org/netdev/20240625075926.146d769d@kernel.org/ v13: https://patchwork.kernel.org/project/netdevbpf/list/?series=861406&archive=… ==== Major changes: -------------- This iteration addresses Pavel's review comments, applies his reviewed-by's, and seeks to fix the patchwork build error (sorry!). As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v13/ v12: https://patchwork.kernel.org/project/netdevbpf/list/?series=859747&state=* ==== Major changes: -------------- This iteration only addresses one minor comment from Pavel with regards to the trace printing of netmem, and the patchwork build error introduced in v11 because I missed doing an allmodconfig build, sorry. Other than that v11, AFAICT, received no feedback. There is one discussion about how the specifics of plugging io uring memory through the page pool, but not relevant to content in this particular patchset, AFAICT. As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v12/ v11: https://patchwork.kernel.org/project/netdevbpf/list/?series=857457&state=* ==== Major Changes: -------------- v11 addresses feedback received in v10. The major change is the removal of the memory provider ops as requested by Christoph. We still accomplish the same thing, but utilizing direct function calls with if statements rather than generic ops. Additionally address sparse warnings, bugs and review comments from folks that reviewed. As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v11/ Detailed changelog: ------------------- - Fixes in netdev_rx_queue_restart() from Pavel & David. - Remove commit e650e8c3a36f5 ("net: page_pool: create hooks for custom page providers") from the series to address Christoph's feedback and rebased other patches on the series on this change. - Fixed build errors with CONFIG_DMA_SHARED_BUFFER && !CONFIG_GENERIC_ALLOCATOR build. - Fixed sparse warnings pointed out by Paolo. - Drop unnecessary gro_pull_from_frag0 checks. - Added Bagas reviewed-by to docs. v10: https://patchwork.kernel.org/project/netdevbpf/list/?series=852422&state=* ==== Major Changes: -------------- v9 was sent right before the merge window closed (sorry!). v10 is almost a re-send of the series now that the merge window re-opened. Only rebased to latest net-next and addressed some minor iterative comments received on v9. As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v10/ Detailed changelog: ------------------- - Fixed tokens leaking in DONTNEED setsockopt (Nikolay). - Moved net_iov_dma_addr() to devmem.c and made it a devmem specific helpers (David). - Rename hook alloc_pages to alloc_netmems as alloc_pages is now preprocessor macro defined and causes a build error. v9: === Major Changes: -------------- GVE queue API has been merged. Submitting this version as non-RFC after rebasing on top of the merged API, and dropped the out of tree queue API I was carrying on github. Addressed the little feedback v8 has received. Detailed changelog: ------------------ - Added new patch from David Wei to this series for netdev_rx_queue_restart() - Fixed sparse error. - Removed CONFIG_ checks in netmem_is_net_iov() - Flipped skb->readable to skb->unreadable - Minor fixes to selftests & docs. RFC v8: ======= Major Changes: -------------- - Fixed build error generated by patch-by-patch build. - Applied docs suggestions from Randy. RFC v7: ======= Major Changes: -------------- This revision largely rebases on top of net-next and addresses the feedback RFCv6 received from folks, namely Jakub, Yunsheng, Arnd, David, & Pavel. The series remains in RFC because the queue-API ndos defined in this series are not yet implemented. I have a GVE implementation I carry out of tree for my testing. A upstreamable GVE implementation is in the works. Aside from that, in my estimation all the patches are ready for review/merge. Please do take a look. As usual the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v7/ Detailed changelog: - Use admin-perm in netlink API. - Addressed feedback from Jakub with regards to netlink API implementation. - Renamed devmem.c functions to something more appropriate for that file. - Improve the performance seen through the page_pool benchmark. - Fix the value definition of all the SO_DEVMEM_* uapi. - Various fixes to documentation. Perf - page-pool benchmark: --------------------------- Improved performance of bench_page_pool_simple.ko tests compared to v6: https://pastebin.com/raw/v5dYRg8L net-next base: 8 cycle fast path. RFC v6: 10 cycle fast path. RFC v7: 9 cycle fast path. RFC v7 with CONFIG_DMA_SHARED_BUFFER disabled: 8 cycle fast path, same as baseline. Perf - Devmem TCP benchmark: --------------------- Perf is about the same regardless of the changes in v7, namely the removal of the static_branch_unlikely to improve the page_pool benchmark performance: 189/200gbps bi-directional throughput with RX devmem TCP and regular TCP TX i.e. ~95% line rate. RFC v6: ======= Major Changes: -------------- This revision largely rebases on top of net-next and addresses the little feedback RFCv5 received. The series remains in RFC because the queue-API ndos defined in this series are not yet implemented. I have a GVE implementation I carry out of tree for my testing. A upstreamable GVE implementation is in the works. Aside from that, in my estimation all the patches are ready for review/merge. Please do take a look. As usual the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v6/ This version also comes with some performance data recorded in the cover letter (see below changelog). Detailed changelog: - Rebased on top of the merged netmem_ref changes. - Converted skb->dmabuf to skb->readable (Pavel). Pavel's original suggestion was to remove the skb->dmabuf flag entirely, but when I looked into it closely, I found the issue that if we remove the flag we have to dereference the shinfo(skb) pointer to obtain the first frag to tell whether an skb is readable or not. This can cause a performance regression if it dirties the cache line when the shinfo(skb) was not really needed. Instead, I converted the skb->dmabuf flag into a generic skb->readable flag which can be re-used by io_uring 0-copy RX. - Squashed a few locking optimizations from Eric Dumazet in the RX path and the DEVMEM_DONTNEED setsockopt. - Expanded the tests a bit. Added validation for invalid scenarios and added some more coverage. Perf - page-pool benchmark: --------------------------- bench_page_pool_simple.ko tests with and without these changes: https://pastebin.com/raw/ncHDwAbn AFAIK the number that really matters in the perf tests is the 'tasklet_page_pool01_fast_path Per elem'. This one measures at about 8 cycles without the changes but there is some 1 cycle noise in some results. With the patches this regresses to 9 cycles with the changes but there is 1 cycle noise occasionally running this test repeatedly. Lastly I tried disable the static_branch_unlikely() in netmem_is_net_iov() check. To my surprise disabling the static_branch_unlikely() check reduces the fast path back to 8 cycles, but the 1 cycle noise remains. Perf - Devmem TCP benchmark: --------------------- 189/200gbps bi-directional throughput with RX devmem TCP and regular TCP TX i.e. ~95% line rate. Major changes in RFC v5: ======================== 1. Rebased on top of 'Abstract page from net stack' series and used the new netmem type to refer to LSB set pointers instead of re-using struct page. 2. Downgraded this series back to RFC and called it RFC v5. This is because this series is now dependent on 'Abstract page from net stack'[1] and the queue API. Both are removed from the series to reduce the patch # and those bits are fairly independent or pre-requisite work. 3. Reworked the page_pool devmem support to use netmem and for some more unified handling. 4. Reworked the reference counting of net_iov (renamed from page_pool_iov) to use pp_ref_count for refcounting. The full changes including the dependent series and GVE page pool support is here: https://github.com/mina/linux/commits/tcpdevmem-rfcv5/ [1] https://patchwork.kernel.org/project/netdevbpf/list/?series=810774 Major changes in v1: ==================== 1. Implemented MVP queue API ndos to remove the userspace-visible driver reset. 2. Fixed issues in the napi_pp_put_page() devmem frag unref path. 3. Removed RFC tag. Many smaller addressed comments across all the patches (patches have individual change log). Full tree including the rest of the GVE driver changes: https://github.com/mina/linux/commits/tcpdevmem-v1 Changes in RFC v3: ================== 1. Pulled in the memory-provider dependency from Jakub's RFC[1] to make the series reviewable and mergeable. 2. Implemented multi-rx-queue binding which was a todo in v2. 3. Fix to cmsg handling. The sticking point in RFC v2[2] was the device reset required to refill the device rx-queues after the dmabuf bind/unbind. The solution suggested as I understand is a subset of the per-queue management ops Jakub suggested or similar: https://lore.kernel.org/netdev/20230815171638.4c057dcd@kernel.org/ This is not addressed in this revision, because: 1. This point was discussed at netconf & netdev and there is openness to using the current approach of requiring a device reset. 2. Implementing individual queue resetting seems to be difficult for my test bed with GVE. My prototype to test this ran into issues with the rx-queues not coming back up properly if reset individually. At the moment I'm unsure if it's a mistake in the POC or a genuine issue in the virtualization stack behind GVE, which currently doesn't test individual rx-queue restart. 3. Our usecases are not bothered by requiring a device reset to refill the buffer queues, and we'd like to support NICs that run into this limitation with resetting individual queues. My thought is that drivers that have trouble with per-queue configs can use the support in this series, while drivers that support new netdev ops to reset individual queues can automatically reset the queue as part of the dma-buf bind/unbind. The same approach with device resets is presented again for consideration with other sticking points addressed. This proposal includes the rx devmem path only proposed for merge. For a snapshot of my entire tree which includes the GVE POC page pool support & device memory support: https://github.com/torvalds/linux/compare/master...mina:linux:tcpdevmem-v3 [1] https://lore.kernel.org/netdev/f8270765-a27b-6ccf-33ea-cda097168d79@redhat.… [2] https://lore.kernel.org/netdev/CAHS8izOVJGJH5WF68OsRWFKJid1_huzzUK+hpKbLcL4… Changes in RFC v2: ================== The sticking point in RFC v1[1] was the dma-buf pages approach we used to deliver the device memory to the TCP stack. RFC v2 is a proof-of-concept that attempts to resolve this by implementing scatterlist support in the networking stack, such that we can import the dma-buf scatterlist directly. This is the approach proposed at a high level here[2]. Detailed changes: 1. Replaced dma-buf pages approach with importing scatterlist into the page pool. 2. Replace the dma-buf pages centric API with a netlink API. 3. Removed the TX path implementation - there is no issue with implementing the TX path with scatterlist approach, but leaving out the TX path makes it easier to review. 4. Functionality is tested with this proposal, but I have not conducted perf testing yet. I'm not sure there are regressions, but I removed perf claims from the cover letter until they can be re-confirmed. 5. Added Signed-off-by: contributors to the implementation. 6. Fixed some bugs with the RX path since RFC v1. Any feedback welcome, but specifically the biggest pending questions needing feedback IMO are: 1. Feedback on the scatterlist-based approach in general. 2. Netlink API (Patch 1 & 2). 3. Approach to handle all the drivers that expect to receive pages from the page pool (Patch 6). [1] https://lore.kernel.org/netdev/dfe4bae7-13a0-3c5d-d671-f61b375cb0b4@gmail.c… [2] https://lore.kernel.org/netdev/CAHS8izPm6XRS54LdCDZVd0C75tA1zHSu6jLVO8nzTLX… ================== * TL;DR: Device memory TCP (devmem TCP) is a proposal for transferring data to and/or from device memory efficiently, without bouncing the data to a host memory buffer. * Problem: A large amount of data transfers have device memory as the source and/or destination. Accelerators drastically increased the volume of such transfers. Some examples include: - ML accelerators transferring large amounts of training data from storage into GPU/TPU memory. In some cases ML training setup time can be as long as 50% of TPU compute time, improving data transfer throughput & efficiency can help improving GPU/TPU utilization. - Distributed training, where ML accelerators, such as GPUs on different hosts, exchange data among them. - Distributed raw block storage applications transfer large amounts of data with remote SSDs, much of this data does not require host processing. Today, the majority of the Device-to-Device data transfers 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 implementation is suboptimal, especially for bulk data transfers, and can put significant strains on system resources, such as host memory bandwidth, PCIe bandwidth, etc. One important reason behind the current state is the kernel’s lack of semantics to express device to network transfers. * Proposal: In this patch series we attempt to optimize this use case by implementing socket APIs that enable the user to: 1. send device memory across the network directly, and 2. receive incoming network packets directly into device memory. Packet _payloads_ go directly from the NIC to device memory for receive and from device memory to NIC for transmit. Packet _headers_ go to/from 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 BW pressure, by limiting data transfer to the lowest level of the PCIe tree, compared to traditional path which sends data through the root complex. * Patch overview: ** Part 1: netlink API Gives user ability to bind dma-buf to an RX queue. ** Part 2: scatterlist support Currently the standard for device memory sharing is DMABUF, which doesn't generate struct pages. On the other hand, networking stack (skbs, drivers, and page pool) operate on pages. We have 2 options: 1. Generate struct pages for dmabuf device memory, or, 2. Modify the networking stack to process scatterlist. Approach #1 was attempted in RFC v1. RFC v2 implements approach #2. ** part 3: page pool support We piggy back on page pool memory providers proposal: https://github.com/kuba-moo/linux/tree/pp-providers It allows the page pool to define a memory provider that provides the page allocation and freeing. It helps abstract most of the device memory TCP changes from the driver. ** part 4: support for unreadable skb frags Page pool iovs are not accessible by the host; we implement changes throughput the networking stack to correctly handle skbs with unreadable frags. ** Part 5: recvmsg() APIs We define user APIs for the user to send and receive device memory. Not included with this series is the GVE devmem TCP support, just to simplify the review. Code available here if desired: https://github.com/mina/linux/tree/tcpdevmem This series is built on top of net-next with Jakub's pp-providers changes cherry-picked. * NIC dependencies: 1. (strict) Devmem TCP require the NIC to support header split, i.e. the capability to split incoming packets into a header + payload and to put each into a separate buffer. Devmem TCP works by using device memory for the packet payload, and host memory for the packet headers. 2. (optional) Devmem TCP works better with flow steering support & RSS support, i.e. the NIC's ability to steer flows into certain rx queues. This allows the sysadmin to enable devmem TCP on a subset of the rx queues, and steer devmem TCP traffic onto these queues and non devmem TCP elsewhere. The NIC I have access to with these properties is the GVE with DQO support running in Google Cloud, but any NIC that supports these features would suffice. I may be able to help reviewers bring up devmem TCP on their NICs. * Testing: The series includes a udmabuf kselftest that show a simple use case of devmem TCP and validates the entire data path end to end without a dependency on a specific dmabuf provider. ** Test Setup Kernel: net-next with this series and memory provider API cherry-picked locally. Hardware: Google Cloud A3 VMs. NIC: GVE with header split & RSS & flow steering support. Cc: Pavel Begunkov <asml.silence(a)gmail.com> Cc: David Wei <dw(a)davidwei.uk> Cc: Jason Gunthorpe <jgg(a)ziepe.ca> Cc: Yunsheng Lin <linyunsheng(a)huawei.com> Cc: Shailend Chand <shailend(a)google.com> Cc: Harshitha Ramamurthy <hramamurthy(a)google.com> Cc: Shakeel Butt <shakeel.butt(a)linux.dev> Cc: Jeroen de Borst <jeroendb(a)google.com> Cc: Praveen Kaligineedi <pkaligineedi(a)google.com> Cc: Bagas Sanjaya <bagasdotme(a)gmail.com> Cc: Steven Rostedt <rostedt(a)goodmis.org> Cc: Christoph Hellwig <hch(a)infradead.org> Cc: Nikolay Aleksandrov <razor(a)blackwall.org> Cc: Taehee Yoo <ap420073(a)gmail.com> Cc: Donald Hunter <donald.hunter(a)gmail.com> Mina Almasry (13): netdev: add netdev_rx_queue_restart() net: netdev netlink api to bind dma-buf to a net device netdev: support binding dma-buf to netdevice netdev: netdevice devmem allocator page_pool: devmem support memory-provider: dmabuf devmem memory provider net: support non paged skb frags net: add support for skbs with unreadable frags tcp: RX path for devmem TCP net: add SO_DEVMEM_DONTNEED setsockopt to release RX frags net: add devmem TCP documentation selftests: add ncdevmem, netcat for devmem TCP netdev: add dmabuf introspection Documentation/netlink/specs/netdev.yaml | 61 +++ Documentation/networking/devmem.rst | 269 +++++++++++ Documentation/networking/index.rst | 1 + arch/alpha/include/uapi/asm/socket.h | 6 + arch/mips/include/uapi/asm/socket.h | 6 + arch/parisc/include/uapi/asm/socket.h | 6 + arch/sparc/include/uapi/asm/socket.h | 6 + include/linux/netdevice.h | 2 + include/linux/skbuff.h | 61 ++- include/linux/skbuff_ref.h | 9 +- include/linux/socket.h | 1 + include/net/netdev_rx_queue.h | 5 + include/net/netmem.h | 132 +++++- include/net/page_pool/helpers.h | 39 +- include/net/page_pool/types.h | 23 +- include/net/sock.h | 2 + include/net/tcp.h | 3 +- include/trace/events/page_pool.h | 12 +- include/uapi/asm-generic/socket.h | 6 + include/uapi/linux/netdev.h | 13 + include/uapi/linux/uio.h | 18 + net/Kconfig | 5 + net/core/Makefile | 2 + net/core/datagram.c | 6 + net/core/dev.c | 33 +- net/core/devmem.c | 389 ++++++++++++++++ net/core/devmem.h | 180 ++++++++ net/core/gro.c | 3 +- net/core/mp_dmabuf_devmem.h | 44 ++ net/core/netdev-genl-gen.c | 23 + net/core/netdev-genl-gen.h | 6 + net/core/netdev-genl.c | 139 +++++- net/core/netdev_rx_queue.c | 81 ++++ net/core/netmem_priv.h | 31 ++ net/core/page_pool.c | 119 +++-- net/core/page_pool_priv.h | 46 ++ net/core/page_pool_user.c | 32 +- net/core/skbuff.c | 77 +++- net/core/sock.c | 68 +++ net/ethtool/common.c | 8 + net/ipv4/esp4.c | 3 +- net/ipv4/tcp.c | 263 ++++++++++- net/ipv4/tcp_input.c | 13 +- net/ipv4/tcp_ipv4.c | 16 + net/ipv4/tcp_minisocks.c | 2 + net/ipv4/tcp_output.c | 5 +- net/ipv6/esp6.c | 3 +- net/packet/af_packet.c | 4 +- net/xdp/xsk_buff_pool.c | 5 + tools/include/uapi/linux/netdev.h | 13 + tools/net/ynl/lib/.gitignore | 1 + tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 9 + tools/testing/selftests/net/ncdevmem.c | 570 ++++++++++++++++++++++++ 54 files changed, 2757 insertions(+), 124 deletions(-) create mode 100644 Documentation/networking/devmem.rst create mode 100644 net/core/devmem.c create mode 100644 net/core/devmem.h create mode 100644 net/core/mp_dmabuf_devmem.h create mode 100644 net/core/netdev_rx_queue.c create mode 100644 net/core/netmem_priv.h create mode 100644 tools/testing/selftests/net/ncdevmem.c -- 2.46.0.598.g6f2099f65c-goog

9 months, 3 weeks

2
14
0 0

[PATCH net 0/3] selftests: mptcp: misc. small fixes

by Matthieu Baerts (NGI0)

Here are some various fixes for the MPTCP selftests. Patch 1 fixes a recently modified test to continue to work as expected on older kernels. This is a fix for a recent fix that can be backported up to v5.15. Patch 2 and 3 include dependences when exporting or installing the tests. Two fixes for v6.11-rc1. Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Matthieu Baerts (NGI0) (3): selftests: mptcp: join: restrict fullmesh endp on 1st sf selftests: mptcp: include lib.sh file selftests: mptcp: include net_helper.sh file tools/testing/selftests/net/mptcp/Makefile | 2 ++ tools/testing/selftests/net/mptcp/mptcp_join.sh | 4 +++- 2 files changed, 5 insertions(+), 1 deletion(-) --- base-commit: 48aa361c5db0b380c2b75c24984c0d3e7c1e8c09 change-id: 20240910-net-selftests-mptcp-fix-install-2b82ae5a99c8 Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

9 months, 3 weeks

2
4
0 0

[PATCH] selftests: kselftest: Use strerror() on nolibc

by zhangjiao2

From: zhang jiao <zhangjiao2(a)cmss.chinamobile.com> Nolibc gained an implementation of strerror() recently. Use it and drop the ifndef. Signed-off-by: zhang jiao <zhangjiao2(a)cmss.chinamobile.com> --- tools/testing/selftests/kselftest.h | 8 -------- 1 file changed, 8 deletions(-) diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index e195ec156859..29fedf609611 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -373,15 +373,7 @@ static inline __noreturn __printf(1, 2) void ksft_exit_fail_msg(const char *msg, static inline __noreturn void ksft_exit_fail_perror(const char *msg) { -#ifndef NOLIBC ksft_exit_fail_msg("%s: %s (%d)\n", msg, strerror(errno), errno); -#else - /* - * nolibc doesn't provide strerror() and it seems - * inappropriate to add one, just print the errno. - */ - ksft_exit_fail_msg("%s: %d)\n", msg, errno); -#endif } static inline __noreturn void ksft_exit_xfail(void) -- 2.33.0

9 months, 3 weeks

3
3
0 0

[for-next][PATCH 2/2] selftests/ring-buffer: Handle meta-page bigger than the system

by Steven Rostedt

From: Vincent Donnefort <vdonnefort(a)google.com> Handle the case where the meta-page content is bigger than the system page-size. This prepares the ground for extending features covered by the meta-page. Cc: Shuah Khan <skhan(a)linuxfoundation.org> Cc: linux-kselftest(a)vger.kernel.org Link: https://lore.kernel.org/20240910162335.2993310-3-vdonnefort@google.com Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Vincent Donnefort <vdonnefort(a)google.com> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- tools/testing/selftests/ring-buffer/map_test.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/tools/testing/selftests/ring-buffer/map_test.c b/tools/testing/selftests/ring-buffer/map_test.c index ba12fd31de87..d10a847130fb 100644 --- a/tools/testing/selftests/ring-buffer/map_test.c +++ b/tools/testing/selftests/ring-buffer/map_test.c @@ -92,12 +92,22 @@ int tracefs_cpu_map(struct tracefs_cpu_map_desc *desc, int cpu) if (desc->cpu_fd < 0) return -ENODEV; +again: map = mmap(NULL, page_size, PROT_READ, MAP_SHARED, desc->cpu_fd, 0); if (map == MAP_FAILED) return -errno; desc->meta = (struct trace_buffer_meta *)map; + /* the meta-page is bigger than the original mapping */ + if (page_size < desc->meta->meta_struct_len) { + int meta_page_size = desc->meta->meta_page_size; + + munmap(desc->meta, page_size); + page_size = meta_page_size; + goto again; + } + return 0; } -- 2.45.2

9 months, 3 weeks

1
0
0 0

[for-next][PATCH 1/2] selftests/ring-buffer: Verify the entire meta-page padding

by Steven Rostedt

From: Vincent Donnefort <vdonnefort(a)google.com> Improve the ring-buffer meta-page test coverage by checking for the entire padding region to be 0 instead of just looking at the first 4 bytes. Cc: linux-kselftest(a)vger.kernel.org Link: https://lore.kernel.org/20240910162335.2993310-2-vdonnefort@google.com Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Vincent Donnefort <vdonnefort(a)google.com> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- tools/testing/selftests/ring-buffer/map_test.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/ring-buffer/map_test.c b/tools/testing/selftests/ring-buffer/map_test.c index 4bb0192e43f3..ba12fd31de87 100644 --- a/tools/testing/selftests/ring-buffer/map_test.c +++ b/tools/testing/selftests/ring-buffer/map_test.c @@ -231,15 +231,15 @@ TEST_F(map, data_mmap) /* Verify meta-page padding */ if (desc->meta->meta_page_size > getpagesize()) { - void *addr; - data_len = desc->meta->meta_page_size; data = mmap(NULL, data_len, PROT_READ, MAP_SHARED, desc->cpu_fd, 0); ASSERT_NE(data, MAP_FAILED); - addr = (void *)((unsigned long)data + getpagesize()); - ASSERT_EQ(*((int *)addr), 0); + for (int i = desc->meta->meta_struct_len; + i < desc->meta->meta_page_size; i += sizeof(int)) + ASSERT_EQ(*(int *)(data + i), 0); + munmap(data, data_len); } } -- 2.45.2

9 months, 3 weeks

1
0
0 0

[PATCH RESEND 2/2] ring-buffer/selftest: Handle meta-page bigger than the system

by Vincent Donnefort

Handle the case where the meta-page content is bigger than the system page-size. This prepares the ground for extending features covered by the meta-page. Cc: Shuah Khan <skhan(a)linuxfoundation.org> Cc: linux-kselftest(a)vger.kernel.org Signed-off-by: Vincent Donnefort <vdonnefort(a)google.com> diff --git a/tools/testing/selftests/ring-buffer/map_test.c b/tools/testing/selftests/ring-buffer/map_test.c index ba12fd31de87..d10a847130fb 100644 --- a/tools/testing/selftests/ring-buffer/map_test.c +++ b/tools/testing/selftests/ring-buffer/map_test.c @@ -92,12 +92,22 @@ int tracefs_cpu_map(struct tracefs_cpu_map_desc *desc, int cpu) if (desc->cpu_fd < 0) return -ENODEV; +again: map = mmap(NULL, page_size, PROT_READ, MAP_SHARED, desc->cpu_fd, 0); if (map == MAP_FAILED) return -errno; desc->meta = (struct trace_buffer_meta *)map; + /* the meta-page is bigger than the original mapping */ + if (page_size < desc->meta->meta_struct_len) { + int meta_page_size = desc->meta->meta_page_size; + + munmap(desc->meta, page_size); + page_size = meta_page_size; + goto again; + } + return 0; } -- 2.46.0.598.g6f2099f65c-goog

9 months, 3 weeks

3
4
0 0

[PATCH RESEND 1/2] ring-buffer/selftest: Verify the entire meta-page padding

by Vincent Donnefort

Improve the ring-buffer meta-page test coverage by checking for the entire padding region to be 0 instead of just looking at the first 4 bytes. Cc: Shuah Khan <skhan(a)linuxfoundation.org> Cc: linux-kselftest(a)vger.kernel.org Signed-off-by: Vincent Donnefort <vdonnefort(a)google.com> diff --git a/tools/testing/selftests/ring-buffer/map_test.c b/tools/testing/selftests/ring-buffer/map_test.c index 4bb0192e43f3..ba12fd31de87 100644 --- a/tools/testing/selftests/ring-buffer/map_test.c +++ b/tools/testing/selftests/ring-buffer/map_test.c @@ -231,15 +231,15 @@ TEST_F(map, data_mmap) /* Verify meta-page padding */ if (desc->meta->meta_page_size > getpagesize()) { - void *addr; - data_len = desc->meta->meta_page_size; data = mmap(NULL, data_len, PROT_READ, MAP_SHARED, desc->cpu_fd, 0); ASSERT_NE(data, MAP_FAILED); - addr = (void *)((unsigned long)data + getpagesize()); - ASSERT_EQ(*((int *)addr), 0); + for (int i = desc->meta->meta_struct_len; + i < desc->meta->meta_page_size; i += sizeof(int)) + ASSERT_EQ(*(int *)(data + i), 0); + munmap(data, data_len); } } -- 2.46.0.598.g6f2099f65c-goog

9 months, 3 weeks

3
5
0 0

[PATCH 0/2] selftests: vDSO: s390 fixes

by Heiko Carstens

Two s390 fixes to make vdso selftests running on s390. Jason, given that you carry already a lot of changes for vdso selftests I guess these should be routed via the random tree. Patches apply on top of current random.git master branch. Thanks, Heiko Heiko Carstens (1): selftests: vDSO: fix vdso_config for s390 Jens Remus (1): selftests: vDSO: fix ELF hash table entry size for s390x tools/testing/selftests/vDSO/parse_vdso.c | 14 ++++++++++---- tools/testing/selftests/vDSO/vdso_config.h | 4 ++-- 2 files changed, 12 insertions(+), 6 deletions(-) -- 2.43.0

9 months, 3 weeks

2
4
0 0

[PATCH net-next] page_pool: add a test module for page_pool

by Yunsheng Lin

The testing is done by ensuring that the page allocated from the page_pool instance is pushed into a ptr_ring instance in a kthread/napi binded to a specified cpu, and a kthread/napi binded to a specified cpu will pop the page from the ptr_ring and free it back to the page_pool. Signed-off-by: Yunsheng Lin <linyunsheng(a)huawei.com> --- tools/testing/selftests/net/Makefile | 3 + .../testing/selftests/net/page_pool/Makefile | 18 + .../selftests/net/page_pool/page_pool_test.c | 433 ++++++++++++++++++ tools/testing/selftests/net/test_page_pool.sh | 175 +++++++ 4 files changed, 629 insertions(+) create mode 100644 tools/testing/selftests/net/page_pool/Makefile create mode 100644 tools/testing/selftests/net/page_pool/page_pool_test.c create mode 100755 tools/testing/selftests/net/test_page_pool.sh diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 27362e40eb37..4d4ddd853ef8 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -6,6 +6,8 @@ CFLAGS += -I../../../../usr/include/ $(KHDR_INCLUDES) # Additional include paths needed by kselftest.h CFLAGS += -I../ +TEST_GEN_MODS_DIR := page_pool + TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh \ rtnetlink.sh xfrm_policy.sh test_blackhole_dev.sh TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh @@ -96,6 +98,7 @@ TEST_PROGS += fdb_flush.sh TEST_PROGS += fq_band_pktlimit.sh TEST_PROGS += vlan_hw_filter.sh TEST_PROGS += bpf_offload.py +TEST_PROGS += test_page_pool.sh TEST_FILES := settings TEST_FILES += in_netns.sh lib.sh net_helper.sh setup_loopback.sh setup_veth.sh diff --git a/tools/testing/selftests/net/page_pool/Makefile b/tools/testing/selftests/net/page_pool/Makefile new file mode 100644 index 000000000000..4380a70d6391 --- /dev/null +++ b/tools/testing/selftests/net/page_pool/Makefile @@ -0,0 +1,18 @@ +PAGE_POOL_TEST_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) +KDIR ?= $(abspath $(PAGE_POOL_TEST_DIR)/../../../../..) + +ifeq ($(V),1) +Q = +else +Q = @ +endif + +MODULES = page_pool_test.ko + +obj-m += page_pool_test.o + +all: + +$(Q)make -C $(KDIR) M=$(PAGE_POOL_TEST_DIR) modules + +clean: + +$(Q)make -C $(KDIR) M=$(PAGE_POOL_TEST_DIR) clean diff --git a/tools/testing/selftests/net/page_pool/page_pool_test.c b/tools/testing/selftests/net/page_pool/page_pool_test.c new file mode 100644 index 000000000000..475b64f21b78 --- /dev/null +++ b/tools/testing/selftests/net/page_pool/page_pool_test.c @@ -0,0 +1,433 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Test module for page_pool + * + * Copyright (C) 2024 Yunsheng Lin <linyunsheng(a)huawei.com> + */ + +#include <linux/module.h> +#include <linux/cpumask.h> +#include <linux/completion.h> +#include <linux/device.h> +#include <linux/etherdevice.h> +#include <linux/ptr_ring.h> +#include <linux/kthread.h> +#include <net/page_pool/helpers.h> + +static struct ptr_ring ptr_ring; +static int nr_objs = 512; +static atomic_t nthreads; +static struct completion wait; +static struct page_pool *test_pool; +static struct device *dev; +static u64 dma_mask = DMA_BIT_MASK(64); + +static int nr_test = 2000000; +module_param(nr_test, int, 0); +MODULE_PARM_DESC(nr_test, "number of iterations to test"); + +static bool test_frag; +module_param(test_frag, bool, 0); +MODULE_PARM_DESC(test_frag, "use frag API for testing"); + +static bool test_dma; +module_param(test_dma, bool, 0); +MODULE_PARM_DESC(test_dma, "enable dma mapping for testing"); + +static bool test_napi; +module_param(test_napi, bool, 0); +MODULE_PARM_DESC(test_napi, "use NAPI softirq for testing"); + +static bool test_direct; +module_param(test_direct, bool, 0); +MODULE_PARM_DESC(test_direct, "enable direct recycle for testing"); + +static int test_alloc_len = 2048; +module_param(test_alloc_len, int, 0); +MODULE_PARM_DESC(test_alloc_len, "alloc len for testing"); + +static int test_push_cpu; +module_param(test_push_cpu, int, 0); +MODULE_PARM_DESC(test_push_cpu, "test cpu for pushing page"); + +static int test_pop_cpu; +module_param(test_pop_cpu, int, 0); +MODULE_PARM_DESC(test_pop_cpu, "test cpu for popping page"); + +static void page_pool_test_dev_release(struct device *dev) +{ + kfree(dev); +} + +static struct page_pool *page_pool_test_create(void) +{ + struct page_pool_params page_pool_params = { + .pool_size = nr_objs, + .flags = 0, + .nid = cpu_to_mem(test_push_cpu), + }; + int ret; + + if (test_dma) { + dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) + return ERR_PTR(-ENOMEM); + + dev->release = page_pool_test_dev_release; + dev->dma_mask = &dma_mask; + device_initialize(dev); + + ret = dev_set_name(dev, "page_pool_dev"); + if (ret) { + pr_err("page_pool_test dev_set_name() failed: %d\n", + ret); + goto err_out; + } + + ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); + if (ret) { + pr_err("page_pool_test set dma mask failed: %d\n", + ret); + goto err_out; + } + + ret = device_add(dev); + if (ret) { + pr_err("page_pool_test device_add() failed: %d\n", ret); + goto err_out; + } + + page_pool_params.dev = dev; + page_pool_params.flags |= PP_FLAG_DMA_MAP; + page_pool_params.dma_dir = DMA_FROM_DEVICE; + } + + return page_pool_create(&page_pool_params); +err_out: + put_device(dev); + return ERR_PTR(ret); +} + +static void page_pool_test_destroy(struct page_pool *pool) +{ + page_pool_destroy(pool); + + if (test_dma) { + device_del(dev); + put_device(dev); + } +} + +static int test_pushed; +static int test_popped; +static int page_pool_pop_thread(void *arg) +{ + struct ptr_ring *ring = arg; + + pr_info("page_pool pop test thread begins on cpu %d\n", + smp_processor_id()); + + while (test_popped < nr_test) { + void *obj = __ptr_ring_consume(ring); + + if (obj) { + test_popped++; + page_pool_put_full_page(test_pool, obj, false); + } else { + cond_resched(); + } + } + + if (atomic_dec_and_test(&nthreads)) + complete(&wait); + + pr_info("page_pool pop test thread exits on cpu %d\n", + smp_processor_id()); + + return 0; +} + +static int page_pool_push_thread(void *arg) +{ + struct ptr_ring *ring = arg; + + pr_info("page_pool push test thread begins on cpu %d\n", + smp_processor_id()); + + while (test_pushed < nr_test) { + struct page *page; + int ret; + + if (test_frag) { + unsigned int offset; + + page = page_pool_dev_alloc_frag(test_pool, &offset, + test_alloc_len); + } else { + page = page_pool_dev_alloc_pages(test_pool); + } + + if (!page) + continue; + + ret = __ptr_ring_produce(ring, page); + if (ret) { + page_pool_put_full_page(test_pool, page, true); + cond_resched(); + } else { + test_pushed++; + } + } + + pr_info("page_pool push test thread exits on cpu %d\n", + smp_processor_id()); + + if (atomic_dec_and_test(&nthreads)) + complete(&wait); + + return 0; +} + +static int page_pool_push_poll(struct napi_struct *napi, int budget) +{ + static bool print = true; + int processed = 0; + + if (unlikely(print)) { + pr_info("page_pool push test napi begins on cpu %d\n", + smp_processor_id()); + print = false; + } + + while (processed < budget && test_pushed < nr_test) { + struct page *page; + int ret; + + if (test_frag) { + unsigned int offset; + + page = page_pool_dev_alloc_frag(test_pool, &offset, + test_alloc_len); + } else { + page = page_pool_dev_alloc_pages(test_pool); + } + + if (!page) + return budget; + + ret = __ptr_ring_produce(&ptr_ring, page); + if (ret) { + page_pool_put_full_page(test_pool, page, true); + return budget; + } + + processed++; + test_pushed++; + } + + if (test_pushed < nr_test) + return budget; + + pr_info("page_pool push test napi exits on cpu %d\n", + smp_processor_id()); + + napi_complete(napi); + if (atomic_dec_and_test(&nthreads)) + complete(&wait); + + return 0; +} + +static int page_pool_pop_poll(struct napi_struct *napi, int budget) +{ + static bool print = true; + int processed = 0; + + if (unlikely(print)) { + pr_info("page_pool pop test napi begins on cpu %d\n", + smp_processor_id()); + print = false; + } + + while (processed < budget && test_popped < nr_test) { + void *obj = __ptr_ring_consume(&ptr_ring); + + if (obj) { + processed++; + test_popped++; + page_pool_put_full_page(test_pool, obj, test_direct); + } else { + return budget; + } + } + + if (test_popped < nr_test) + return budget; + + if (atomic_dec_and_test(&nthreads)) + complete(&wait); + + napi_complete(napi); + pr_info("page_pool pop test napi exits on cpu %d\n", + smp_processor_id()); + + return 0; +} + +static int page_pool_create_test_thread(void) +{ + struct task_struct *tsk_push, *tsk_pop; + + tsk_push = kthread_create_on_cpu(page_pool_push_thread, &ptr_ring, + test_push_cpu, "page_pool_push"); + if (IS_ERR(tsk_push)) + return PTR_ERR(tsk_push); + + tsk_pop = kthread_create_on_cpu(page_pool_pop_thread, &ptr_ring, + test_pop_cpu, "page_pool_pop"); + if (IS_ERR(tsk_pop)) { + kthread_stop(tsk_push); + return PTR_ERR(tsk_pop); + } + + wake_up_process(tsk_push); + wake_up_process(tsk_pop); + + return 0; +} + +static struct napi_struct *pop_napi, *push_napi; +static struct net_device *netdev; +static int page_pool_schedule_napi(void *arg) +{ + struct napi_struct *napi = arg; + + napi_schedule_irqoff(napi); + + return 0; +} + +static int page_pool_create_test_napi(void) +{ + struct task_struct *push_tsk, *pop_tsk; + int ret; + + netdev = alloc_etherdev(sizeof(struct napi_struct) * 2); + if (!netdev) + return -ENOMEM; + + pop_napi = netdev_priv(netdev); + push_napi = pop_napi + 1; + + netif_napi_add(netdev, push_napi, page_pool_push_poll); + netif_napi_add(netdev, pop_napi, page_pool_pop_poll); + + napi_enable(push_napi); + napi_enable(pop_napi); + + push_tsk = kthread_create_on_cpu(page_pool_schedule_napi, push_napi, + test_push_cpu, "page_pool_push_napi"); + if (IS_ERR(push_tsk)) { + ret = PTR_ERR(push_tsk); + goto err_alloc_etherdev; + } + + pop_tsk = kthread_create_on_cpu(page_pool_schedule_napi, pop_napi, + test_pop_cpu, "page_pool_pop_napi"); + if (IS_ERR(pop_tsk)) { + ret = PTR_ERR(pop_tsk); + goto err_push_thread; + } + + wake_up_process(push_tsk); + wake_up_process(pop_tsk); + return 0; + +err_push_thread: + kthread_stop(push_tsk); +err_alloc_etherdev: + free_netdev(netdev); + return ret; +} + +static void page_pool_destroy_test_napi(void) +{ + napi_disable(push_napi); + napi_disable(pop_napi); + + netif_napi_del(push_napi); + netif_napi_del(pop_napi); + + free_netdev(netdev); +} + +static int __init page_pool_test_init(void) +{ + ktime_t start; + u64 duration; + int ret; + + if (test_alloc_len > PAGE_SIZE || test_alloc_len <= 0 || + !cpu_active(test_push_cpu) || !cpu_active(test_pop_cpu) || + (test_direct && (test_push_cpu != test_pop_cpu || !test_napi))) + return -EINVAL; + + ret = ptr_ring_init(&ptr_ring, nr_objs, GFP_KERNEL); + if (ret) + return ret; + + test_pool = page_pool_test_create(); + if (IS_ERR(test_pool)) { + ret = PTR_ERR(test_pool); + goto err_ptr_ring_init; + } + + atomic_set(&nthreads, 2); + init_completion(&wait); + + if (test_napi) + ret = page_pool_create_test_napi(); + else + ret = page_pool_create_test_thread(); + if (ret) + goto err_pool_create; + + start = ktime_get(); + pr_info("waiting for test to complete\n"); + + while (!wait_for_completion_timeout(&wait, msecs_to_jiffies(20000))) + pr_info("page_pool_test progress: pushed = %d, popped = %d\n", + test_pushed, test_popped); + + duration = (u64)ktime_us_delta(ktime_get(), start); + pr_info("%d of iterations for %s%s%s%s testing took: %lluus\n", + nr_test, test_napi ? "napi" : "thread", + test_direct ? " direct" : "", test_dma ? " dma" : "", + test_frag ? " frag" : "", duration); + + ptr_ring_cleanup(&ptr_ring, NULL); + page_pool_test_destroy(test_pool); + + if (test_napi) + page_pool_destroy_test_napi(); + + return -EAGAIN; + +err_pool_create: + page_pool_test_destroy(test_pool); +err_ptr_ring_init: + ptr_ring_cleanup(&ptr_ring, NULL); + return ret; +} + +static void __exit page_pool_test_exit(void) +{ +} + +module_init(page_pool_test_init); +module_exit(page_pool_test_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Yunsheng Lin <linyunsheng(a)huawei.com>"); +MODULE_DESCRIPTION("Test module for page_pool"); diff --git a/tools/testing/selftests/net/test_page_pool.sh b/tools/testing/selftests/net/test_page_pool.sh new file mode 100755 index 000000000000..b9b422f5449d --- /dev/null +++ b/tools/testing/selftests/net/test_page_pool.sh @@ -0,0 +1,175 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (C) 2024 Yunsheng Lin <linyunsheng(a)huawei.com> +# Copyright (C) 2018 Uladzislau Rezki (Sony) <urezki(a)gmail.com> +# +# This is a test script for the kernel test driver to test the +# correctness and performance of page_pool's implementation. +# Therefore it is just a kernel module loader. You can specify +# and pass different parameters in order to: +# a) analyse performance of page_pool; +# b) stressing and stability check of page_pool subsystem. + +DRIVER="./page_pool/page_pool_test.ko" +CPU_LIST=$(grep -m 2 processor /proc/cpuinfo | cut -d ' ' -f 2) +CPU_CNT=$(echo $CPU_LIST | wc -w) +TEST_CPU_0=$(echo $CPU_LIST | awk '{print $1}') + +if [ $CPU_CNT -gt 1 ]; then + TEST_CPU_1=$(echo $CPU_LIST | awk '{print $2}') + NR_TEST=100000000 +else + TEST_CPU_1=$TEST_CPU_0 + NR_TEST=1000000 +fi + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +# +# Static templates for testing of page_pool APIs. +# Also it is possible to pass any supported parameters manually. +# +SMOKE_0_PARAM="test_push_cpu=$TEST_CPU_0 test_pop_cpu=$TEST_CPU_0" +SMOKE_1_PARAM="test_push_cpu=$TEST_CPU_0 test_pop_cpu=$TEST_CPU_1" +NONFRAG_PARAM="$SMOKE_1_PARAM nr_test=$NR_TEST" +FRAG_PARAM="$NONFRAG_PARAM test_alloc_len=2048 test_frag=1" +NONFRAG_DMA_PARAM="$NONFRAG_PARAM test_dma=1" +FRAG_DMA_PARAM="$FRAG_PARAM test_dma=1" +NONFRAG_NAPI_PARAM="$NONFRAG_PARAM test_napi=1" +FRAG_NAPI_PARAM="$FRAG_PARAM test_napi=1" +NAPI_PARAM="$SMOKE_0_PARAM test_napi=1" +NAPI_DIRECT_PARAM="$NAPI_PARAM test_direct=1" + +check_test_requirements() +{ + uid=$(id -u) + if [ $uid -ne 0 ]; then + echo "$0: Must be run as root" + exit $ksft_skip + fi + + if ! which insmod > /dev/null 2>&1; then + echo "$0: You need insmod installed" + exit $ksft_skip + fi + + if [ ! -f $DRIVER ]; then + echo "$0: You need to compile page_pool_test module" + exit $ksft_skip + fi +} + +run_nonfrag_check() +{ + echo "Run performance tests to evaluate how fast nonaligned alloc API is." + + insmod $DRIVER $NONFRAG_PARAM > /dev/null 2>&1 + echo "Done." + echo "Check the kernel ring buffer to see the summary." +} + +run_frag_check() +{ + echo "Run performance tests to evaluate how fast aligned alloc API is." + + insmod $DRIVER $FRAG_PARAM > /dev/null 2>&1 + echo "Done." + echo "Check the kernel ring buffer to see the summary." +} + +run_nonfrag_dma_check() +{ + echo "Run performance tests to evaluate nonaligned alloc API with dma mapping." + + insmod $DRIVER $NONFRAG_DMA_PARAM > /dev/null 2>&1 + echo "Done." + echo "Check the kernel ring buffer to see the summary." +} + +run_frag_dma_check() +{ + echo "Run performance tests to evaluate aligned alloc API with dma mapping." + + insmod $DRIVER $FRAG_DMA_PARAM > /dev/null 2>&1 + echo "Done." + echo "Check the kernel ring buffer to see the summary." +} + +run_nonfrag_napi_check() +{ + echo "Run performance tests to evaluate nonaligned alloc API in NAPI testing mode." + + insmod $DRIVER $NONFRAG_NAPI_PARAM > /dev/null 2>&1 + echo "Done." + echo "Check the kernel ring buffer to see the summary." +} + +run_frag_napi_check() +{ + echo "Run performance tests to evaluate aligned alloc API in NAPI testing mode." + + insmod $DRIVER $FRAG_NAPI_PARAM > /dev/null 2>&1 + echo "Done." + echo "Check the kernel ring buffer to see the summary." +} + +run_napi_check() +{ + echo "Run performance in NAPI testing mode." + + insmod $DRIVER $NAPI_PARAM > /dev/null 2>&1 + echo "Done." + echo "Check the kernel ring buffer to see the summary." +} + +run_napi_direct_check() +{ + echo "Run performance tests in NAPI and direct recycle testing mode." + + insmod $DRIVER $NAPI_DIRECT_PARAM > /dev/null 2>&1 + echo "Done." + echo "Check the kernel ring buffer to see the summary." +} + +run_smoke_0_check() +{ + echo "Run smoke_0 test." + + insmod $DRIVER $SMOKE_0_PARAM > /dev/null 2>&1 + echo "Done." + echo "Check the kernel ring buffer to see the summary." +} + +run_smoke_1_check() +{ + echo "Run smoke_1 test." + + insmod $DRIVER $SMOKE_1_PARAM > /dev/null 2>&1 + echo "Done." + echo "Check the kernel ring buffer to see the summary." +} + + +function run_test() +{ + run_smoke_0_check + run_napi_check + run_napi_direct_check + + if [ $CPU_CNT -gt 1 ]; then + run_smoke_1_check + run_nonfrag_check + run_frag_check + run_nonfrag_dma_check + run_frag_dma_check + run_nonfrag_napi_check + run_frag_napi_check + fi +} + +check_test_requirements +run_test + +exit 0 -- 2.33.0

9 months, 3 weeks

3
4
0 0

[PATCH net] selftests: net: csum: Fix checksums for packets with non-zero padding

by Sean Anderson

Padding is not included in UDP and TCP checksums. Therefore, reduce the length of the checksummed data to include only the data in the IP payload. This fixes spurious reported checksum failures like rx: pkt: sport=33000 len=26 csum=0xc850 verify=0xf9fe pkt: bad csum Technically it is possible for there to be trailing bytes after the UDP data but before the Ethernet padding (e.g. if sizeof(ip) + sizeof(udp) + udp.len < ip.len). However, we don't generate such packets. Fixes: 91a7de85600d ("selftests/net: add csum offload test") Signed-off-by: Sean Anderson <sean.anderson(a)linux.dev> --- Found while testing for this very bug in hardware checksum offloads. tools/testing/selftests/net/lib/csum.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/lib/csum.c b/tools/testing/selftests/net/lib/csum.c index b9f3fc3c3426..e0a34e5e8dd5 100644 --- a/tools/testing/selftests/net/lib/csum.c +++ b/tools/testing/selftests/net/lib/csum.c @@ -654,10 +654,16 @@ static int recv_verify_packet_ipv4(void *nh, int len) { struct iphdr *iph = nh; uint16_t proto = cfg_encap ? IPPROTO_UDP : cfg_proto; + uint16_t ip_len; if (len < sizeof(*iph) || iph->protocol != proto) return -1; + ip_len = ntohs(iph->tot_len); + if (ip_len > len || ip_len < sizeof(*iph)) + return -1; + + len = ip_len; iph_addr_p = &iph->saddr; if (proto == IPPROTO_TCP) return recv_verify_packet_tcp(iph + 1, len - sizeof(*iph)); @@ -669,16 +675,22 @@ static int recv_verify_packet_ipv6(void *nh, int len) { struct ipv6hdr *ip6h = nh; uint16_t proto = cfg_encap ? IPPROTO_UDP : cfg_proto; + uint16_t ip_len; if (len < sizeof(*ip6h) || ip6h->nexthdr != proto) return -1; + ip_len = ntohs(ip6h->payload_len); + if (ip_len > len - sizeof(*ip6h)) + return -1; + + len = ip_len; iph_addr_p = &ip6h->saddr; if (proto == IPPROTO_TCP) - return recv_verify_packet_tcp(ip6h + 1, len - sizeof(*ip6h)); + return recv_verify_packet_tcp(ip6h + 1, len); else - return recv_verify_packet_udp(ip6h + 1, len - sizeof(*ip6h)); + return recv_verify_packet_udp(ip6h + 1, len); } /* return whether auxdata includes TP_STATUS_CSUM_VALID */ -- 2.35.1.1320.gc452695387.dirty

9 months, 3 weeks

5
12
0 0

[PATCH net-next v2 0/2] selftests/net: add packetdrill

by Willem de Bruijn

From: Willem de Bruijn <willemb(a)google.com> Lay the groundwork to import into kselftests the over 150 packetdrill TCP/IP conformance tests on github.com/google/packetdrill. 1/2: add kselftest infra for TEST_PROGS that need an interpreter 2/2: add the specific packetdrill tests Both can go through net-next, I imagine. But let me know if the core infra should go through linux-kselftest. Willem de Bruijn (2): selftests: support interpreted scripts with ksft_runner.sh selftests/net: integrate packetdrill with ksft tools/testing/selftests/Makefile | 5 +- tools/testing/selftests/kselftest/runner.sh | 7 ++- .../selftests/net/packetdrill/Makefile | 9 +++ .../testing/selftests/net/packetdrill/config | 5 ++ .../selftests/net/packetdrill/defaults.sh | 63 +++++++++++++++++++ .../selftests/net/packetdrill/ksft_runner.sh | 41 ++++++++++++ .../net/packetdrill/tcp_inq_client.pkt | 51 +++++++++++++++ .../net/packetdrill/tcp_inq_server.pkt | 51 +++++++++++++++ .../tcp_md5_md5-only-on-client-ack.pkt | 28 +++++++++ 9 files changed, 256 insertions(+), 4 deletions(-) create mode 100644 tools/testing/selftests/net/packetdrill/Makefile create mode 100644 tools/testing/selftests/net/packetdrill/config create mode 100755 tools/testing/selftests/net/packetdrill/defaults.sh create mode 100755 tools/testing/selftests/net/packetdrill/ksft_runner.sh create mode 100644 tools/testing/selftests/net/packetdrill/tcp_inq_client.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_inq_server.pkt create mode 100644 tools/testing/selftests/net/packetdrill/tcp_md5_md5-only-on-client-ack.pkt -- 2.46.0.469.g59c65b2a67-goog

9 months, 3 weeks

4
14
0 0

[PATCH v2 0/2] Exposing nice CPU usage to userspace

by Joshua Hahn

From: Joshua Hahn <joshua.hahn6(a)gmail.com> v1 -> v2: Edited commit messages for clarity. Niced CPU usage is a metric reported in host-level /prot/stat, but is not reported in cgroup-level statistics in cpu.stat. However, when a host contains multiple tasks across different workloads, it becomes difficult to gauge how much of the task is being spent on niced processes based on /proc/stat alone, since host-level metrics do not provide this cgroup-level granularity. Exposing this metric will allow users to accurately probe the niced CPU metric for each workload, and make more informed decisions when directing higher priority tasks. Joshua Hahn (2): Tracking cgroup-level niced CPU time Selftests for niced CPU statistics include/linux/cgroup-defs.h | 1 + kernel/cgroup/rstat.c | 16 ++++- tools/testing/selftests/cgroup/test_cpu.c | 72 +++++++++++++++++++++++ 3 files changed, 86 insertions(+), 3 deletions(-) -- 2.43.5

9 months, 3 weeks

3
6
0 0

[PATCH bpf-next/net v5 0/3] selftests/bpf: new MPTCP subflow subtest

by Matthieu Baerts (NGI0)

In this series from Geliang, modifying MPTCP BPF selftests, we have: - A new MPTCP subflow BPF program setting socket options per subflow: it looks better to have this old test program in the BPF selftests to track regressions and to serve as example. Note: Nicolas is no longer working at Tessares, but he did this work while working for them, and his email address is no longer available. - A new hook in the same BPF program to do the verification step. - A new MPTCP BPF subtest validating the new BPF program added in the first patch, with the help of the new hook added in the second patch. Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Changes in v5: - See the individual changelog for more details about them - Patch 1/3: set TCP on the 2nd subflow - Patch 2/3: new - Patch 3/3: use the BPF program from patch 2/3 to do the validation instead of using ss. - Link to v4: https://lore.kernel.org/r/20240805-upstream-bpf-next-20240506-mptcp-subflow… Changes in v4: - Drop former patch 2/3: MPTCP's pm_nl_ctl requires a new header file: - I will check later if it is possible to avoid having duplicated header files in tools/include/uapi, but no need to block this series for that. Patch 2/3 can be added later if needed. - Patch 2/2: skip the test if 'ip mptcp' is not available. - Link to v3: https://lore.kernel.org/r/20240703-upstream-bpf-next-20240506-mptcp-subflow… Changes in v3: - Sorry for the delay between v2 and v3, this series was conflicting with the "add netns helpers", but it looks like it is on hold: https://lore.kernel.org/cover.1715821541.git.tanggeliang@kylinos.cn - Patch 1/3 includes "bpf_tracing_net.h", introduced in between. - New patch 2/3: "selftests/bpf: Add mptcp pm_nl_ctl link". - Patch 3/3: use the tool introduced in patch 2/3 + SYS_NOFAIL() helper. - Link to v2: https://lore.kernel.org/r/20240509-upstream-bpf-next-20240506-mptcp-subflow… Changes in v2: - Previous patches 1/4 and 2/4 have been dropped from this series: - 1/4: "selftests/bpf: Handle SIGINT when creating netns": - A new version, more generic and no longer specific to MPTCP BPF selftest will be sent later, as part of a new series. (Alexei) - 2/4: "selftests/bpf: Add RUN_MPTCP_TEST macro": - Removed, not to hide helper functions in macros. (Alexei) - The commit message of patch 1/2 has been clarified to avoid some possible confusions spot by Alexei. - Link to v1: https://lore.kernel.org/r/20240507-upstream-bpf-next-20240506-mptcp-subflow… --- Geliang Tang (2): selftests/bpf: Add getsockopt to inspect mptcp subflow selftests/bpf: Add mptcp subflow subtest Nicolas Rybowski (1): selftests/bpf: Add mptcp subflow example MAINTAINERS | 2 +- tools/testing/selftests/bpf/prog_tests/mptcp.c | 126 +++++++++++++++++++++ tools/testing/selftests/bpf/progs/mptcp_bpf.h | 42 +++++++ tools/testing/selftests/bpf/progs/mptcp_subflow.c | 128 ++++++++++++++++++++++ 4 files changed, 297 insertions(+), 1 deletion(-) --- base-commit: 6b083650a37318112fb60c65fbb6070584f53d93 change-id: 20240506-upstream-bpf-next-20240506-mptcp-subflow-test-faef6654bfa3 Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

9 months, 3 weeks

2
4
0 0

[PATCH v7 8/8] selftests/pcie_bwctrl: Create selftests

by Ilpo Järvinen

Create selftests for PCIe BW control through the PCIe cooling device sysfs interface. First, the BW control selftest finds the PCIe Port to test with. By default, the PCIe Port with the highest Link Speed is selected but another PCIe Port can be provided with -d parameter. The actual test steps the cur_state of the cooling device one-by-one from max_state to what the cur_state was initially. The speed change is confirmed by observing the current_link_speed for the corresponding PCIe Port. Signed-off-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com> --- MAINTAINERS | 1 + tools/testing/selftests/Makefile | 1 + tools/testing/selftests/pcie_bwctrl/Makefile | 2 + .../pcie_bwctrl/set_pcie_cooling_state.sh | 122 ++++++++++++++++++ .../selftests/pcie_bwctrl/set_pcie_speed.sh | 67 ++++++++++ 5 files changed, 193 insertions(+) create mode 100644 tools/testing/selftests/pcie_bwctrl/Makefile create mode 100755 tools/testing/selftests/pcie_bwctrl/set_pcie_cooling_state.sh create mode 100755 tools/testing/selftests/pcie_bwctrl/set_pcie_speed.sh diff --git a/MAINTAINERS b/MAINTAINERS index 47542dcb9259..dc601dcab8c6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17676,6 +17676,7 @@ S: Supported F: drivers/pci/pcie/bwctrl.c F: drivers/thermal/pcie_cooling.c F: include/linux/pci-bwctrl.h +F: tools/testing/selftests/pcie_bwctrl/ PCIE DRIVER FOR AMAZON ANNAPURNA LABS M: Jonathan Chocron <jonnyc(a)amazon.com> diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index bc8fe9e8f7f2..086af950930c 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -69,6 +69,7 @@ TARGETS += net/openvswitch TARGETS += net/tcp_ao TARGETS += net/netfilter TARGETS += nsfs +TARGETS += pcie_bwctrl TARGETS += perf_events TARGETS += pidfd TARGETS += pid_namespace diff --git a/tools/testing/selftests/pcie_bwctrl/Makefile b/tools/testing/selftests/pcie_bwctrl/Makefile new file mode 100644 index 000000000000..3e84e26341d1 --- /dev/null +++ b/tools/testing/selftests/pcie_bwctrl/Makefile @@ -0,0 +1,2 @@ +TEST_PROGS = set_pcie_cooling_state.sh +include ../lib.mk diff --git a/tools/testing/selftests/pcie_bwctrl/set_pcie_cooling_state.sh b/tools/testing/selftests/pcie_bwctrl/set_pcie_cooling_state.sh new file mode 100755 index 000000000000..9df606552af3 --- /dev/null +++ b/tools/testing/selftests/pcie_bwctrl/set_pcie_cooling_state.sh @@ -0,0 +1,122 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0-or-later + +SYSFS= +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +retval=0 +skipmsg="skip all tests:" + +PCIEPORTTYPE="PCIe_Port_Link_Speed" + +prerequisite() +{ + local ports + + if [ $UID != 0 ]; then + echo $skipmsg must be run as root >&2 + exit $ksft_skip + fi + + SYSFS=`mount -t sysfs | head -1 | awk '{ print $3 }'` + + if [ ! -d "$SYSFS" ]; then + echo $skipmsg sysfs is not mounted >&2 + exit $ksft_skip + fi + + if ! ls $SYSFS/class/thermal/cooling_device* > /dev/null 2>&1; then + echo $skipmsg thermal cooling devices missing >&2 + exit $ksft_skip + fi + + ports=`grep -e "^$PCIEPORTTYPE" $SYSFS/class/thermal/cooling_device*/type | wc -l` + if [ $ports -eq 0 ]; then + echo $skipmsg pcie cooling devices missing >&2 + exit $ksft_skip + fi +} + +testport= +find_pcie_port() +{ + local patt="$1" + local pcieports + local max + local cur + local delta + local bestdelta=-1 + + pcieports=`grep -l -F -e "$patt" /sys/class/thermal/cooling_device*/type` + if [ -z "$pcieports" ]; then + return + fi + pcieports=${pcieports//\/type/} + # Find the port with the highest PCIe Link Speed + for port in $pcieports; do + max=`cat $port/max_state` + cur=`cat $port/cur_state` + delta=$((max-cur)) + if [ $delta -gt $bestdelta ]; then + testport="$port" + bestdelta=$delta + fi + done +} + +sysfspcidev= +find_sysfs_pci_dev() +{ + local typefile="$1/type" + local pcidir + + pcidir="$SYSFS/bus/pci/devices/`sed -e "s|^${PCIEPORTTYPE}_||g" $typefile`" + + if [ -r "$pcidir/current_link_speed" ]; then + sysfspcidev="$pcidir/current_link_speed" + fi +} + +usage() +{ + echo "Usage $0 [ -d dev ]" + echo -e "\t-d: PCIe port BDF string (e.g., 0000:00:04.0)" +} + +pattern="$PCIEPORTTYPE" +parse_arguments() +{ + while getopts d:h opt; do + case $opt in + h) + usage "$0" + exit 0 + ;; + d) + pattern="$PCIEPORTTYPE_$OPTARG" + ;; + *) + usage "$0" + exit 0 + ;; + esac + done +} + +parse_arguments "$@" +prerequisite +find_pcie_port "$pattern" +if [ -z "$testport" ]; then + echo $skipmsg "pcie cooling device not found from sysfs" >&2 + exit $ksft_skip +fi +find_sysfs_pci_dev "$testport" +if [ -z "$sysfspcidev" ]; then + echo $skipmsg "PCIe port device not found from sysfs" >&2 + exit $ksft_skip +fi + +./set_pcie_speed.sh "$testport" "$sysfspcidev" +retval=$? + +exit $retval diff --git a/tools/testing/selftests/pcie_bwctrl/set_pcie_speed.sh b/tools/testing/selftests/pcie_bwctrl/set_pcie_speed.sh new file mode 100755 index 000000000000..584596949312 --- /dev/null +++ b/tools/testing/selftests/pcie_bwctrl/set_pcie_speed.sh @@ -0,0 +1,67 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0-or-later + +set -e + +TESTNAME=set_pcie_speed + +declare -a PCIELINKSPEED=( + "2.5 GT/s PCIe" + "5.0 GT/s PCIe" + "8.0 GT/s PCIe" + "16.0 GT/s PCIe" + "32.0 GT/s PCIe" + "64.0 GT/s PCIe" +) + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +retval=0 + +coolingdev="$1" +statefile="$coolingdev/cur_state" +maxfile="$coolingdev/max_state" +linkspeedfile="$2" + +oldstate=`cat $statefile` +maxstate=`cat $maxfile` + +set_state() +{ + local state=$1 + local linkspeed + local expected_linkspeed + + echo $state > $statefile + + sleep 1 + + linkspeed="`cat $linkspeedfile`" + expected_linkspeed=$((maxstate-state)) + expected_str="${PCIELINKSPEED[$expected_linkspeed]}" + if [ ! "${expected_str}" = "${linkspeed}" ]; then + echo "$TESTNAME failed: expected: ${expected_str}; got ${linkspeed}" + retval=1 + fi +} + +cleanup_skip () +{ + set_state $oldstate + exit $ksft_skip +} + +trap cleanup_skip EXIT + +echo "$TESTNAME: testing states $maxstate .. $oldstate with $coolingdev" +for i in $(seq $maxstate -1 $oldstate); do + set_state "$i" +done + +trap EXIT +if [ $retval -eq 0 ]; then + echo "$TESTNAME [PASS]" +else + echo "$TESTNAME [FAIL]" +fi +exit $retval -- 2.39.2

9 months, 3 weeks

1
0
0 0

[PATCH net v3 0/2] bpf: devmap: provide rxq after redirect

by Florian Kauer

rxq contains a pointer to the device from where the redirect happened. Currently, the BPF program that was executed after a redirect via BPF_MAP_TYPE_DEVMAP* does not have it set. Add bugfix and related selftest. Signed-off-by: Florian Kauer <florian.kauer(a)linutronix.de> --- Changes in v3: - initialize skel to NULL, thanks Stanislav - Link to v2: https://lore.kernel.org/r/20240906-devel-koalo-fix-ingress-ifindex-v2-0-4ca… Changes in v2: - changed fixes tag - added selftest - Link to v1: https://lore.kernel.org/r/20240905-devel-koalo-fix-ingress-ifindex-v1-1-d12… --- Florian Kauer (2): bpf: devmap: provide rxq after redirect bpf: selftests: send packet to devmap redirect XDP kernel/bpf/devmap.c | 11 +- .../selftests/bpf/prog_tests/xdp_devmap_attach.c | 114 +++++++++++++++++++-- 2 files changed, 115 insertions(+), 10 deletions(-) --- base-commit: 8e69c96df771ab469cec278edb47009351de4da6 change-id: 20240905-devel-koalo-fix-ingress-ifindex-b9293d471db6 Best regards, -- Florian Kauer <florian.kauer(a)linutronix.de>

9 months, 3 weeks

2
3
0 0

[PATCH bpf-next] selftests/bpf: convert test_xdp_features.sh to test_progs

by Alexis Lothoré (eBPF Foundation)

test_xdp_features.sh is a shell script allowing to test that xdp features advertised by an interface are indeed delivered. The test works by starting two instance of the same program, both attaching specific xdp programs to each side of a veth link, and then make those programs manage packets and collect stats to check whether tested XDP feature is indeed delivered or not. However this test is not integrated in test_progs framework and so can not run automatically in CI. Rewrite test_xdp_features to integrate it in test_progs so it can run automatically in CI. The main changes brought by the rewrite are the following: - instead of running to separated processes (each one managing either the tester veth or the DUT vet), run a single process - slightly change testing direction (v0 is the tester in local namespace, v1 is the Device Under Test in remote namespace) - group all tests previously managed by test_xdp_features as subtests (one per tested XDP feature). As a consequence, run only once some steps instead of once per subtest (eg: starting/stopping the udp server). On the contrary, make sure that each subtest properly cleans up its state (ie detach xdp programs, reset test stats, etc) - since there is now a single process, get rid of the "control" tcp channel used to configure DUT. Configuring the DUT now only consists in switching to DUT network namespace and run the relevant commands - since there is no more control channel, get rid of TLVs, keep only the CMD_ECHO packet type, and set it as a magic - simplify network setup: use only ipv6 instead of both ipv4 and ipv6, force static neighbours instead of waiting for autoconfiguration, do not force gro (fetch xdp features only once xdp programs are loaded instead) The existing XDP programs are reused, with some minor changes: - tester and dut stats maps are converted to global variables for easier usage - programs do not use TLV struct anymore but the magic replacing the echo command - avoid to accidentally make tests pass: drop packets instead of forwarding them to userspace when they do not match the expected payload Signed-off-by: Alexis Lothoré (eBPF Foundation) <alexis.lothore(a)bootlin.com> --- The xdp_features rewrite has been tested in a x86_64 qemu environment on my machine and in CI. In my environment, the test takes a bit less than 2s to execute. # ./test_progs -a xdp_features #561/1 xdp_features/XDP_PASS:OK #561/2 xdp_features/XDP_DROP:OK #561/3 xdp_features/XDP_ABORTED:OK #561/4 xdp_features/XDP_TX:OK #561/5 xdp_features/XDP_REDIRECT:OK #561/6 xdp_features/XDP_NDO_XMIT:OK #561 xdp_features:OK Summary: 1/6 PASSED, 0 SKIPPED, 0 FAILED --- tools/testing/selftests/bpf/.gitignore | 1 - tools/testing/selftests/bpf/Makefile | 10 +- .../selftests/bpf/prog_tests/xdp_features.c | 446 +++++++++++++ tools/testing/selftests/bpf/progs/xdp_features.c | 49 +- tools/testing/selftests/bpf/test_xdp_features.sh | 107 --- tools/testing/selftests/bpf/xdp_features.c | 718 --------------------- tools/testing/selftests/bpf/xdp_features.h | 17 +- 7 files changed, 462 insertions(+), 886 deletions(-) diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index e6533b3400de..93bf35213042 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -48,4 +48,3 @@ xskxceiver xdp_redirect_multi xdp_synproxy xdp_hw_metadata -xdp_features diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 04716a5e43f1..db4a802c3e06 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -145,8 +145,7 @@ TEST_PROGS := test_kmod.sh \ test_bpftool.sh \ test_bpftool_metadata.sh \ test_doc_build.sh \ - test_xsk.sh \ - test_xdp_features.sh + test_xsk.sh TEST_PROGS_EXTENDED := with_addr.sh \ with_tunnels.sh ima_setup.sh verify_sig_setup.sh \ @@ -157,7 +156,7 @@ TEST_GEN_PROGS_EXTENDED = \ flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \ test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \ xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata \ - xdp_features bpf_test_no_cfi.ko + bpf_test_no_cfi.ko TEST_GEN_FILES += liburandom_read.so urandom_read sign-file uprobe_multi @@ -519,7 +518,6 @@ test_subskeleton_lib.skel.h-deps := test_subskeleton_lib2.bpf.o test_subskeleton test_usdt.skel.h-deps := test_usdt.bpf.o test_usdt_multispec.bpf.o xsk_xdp_progs.skel.h-deps := xsk_xdp_progs.bpf.o xdp_hw_metadata.skel.h-deps := xdp_hw_metadata.bpf.o -xdp_features.skel.h-deps := xdp_features.bpf.o LINKED_BPF_OBJS := $(foreach skel,$(LINKED_SKELS),$($(skel)-deps)) LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.c,$(LINKED_BPF_OBJS)) @@ -787,10 +785,6 @@ $(OUTPUT)/xdp_hw_metadata: xdp_hw_metadata.c $(OUTPUT)/network_helpers.o $(OUTPU $(call msg,BINARY,,$@) $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@ -$(OUTPUT)/xdp_features: xdp_features.c $(OUTPUT)/network_helpers.o $(OUTPUT)/xdp_features.skel.h | $(OUTPUT) - $(call msg,BINARY,,$@) - $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@ - # Make sure we are able to include and link libbpf against c++. $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ) $(call msg,CXX,,$@) diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_features.c b/tools/testing/selftests/bpf/prog_tests/xdp_features.c new file mode 100644 index 000000000000..0daf868dd478 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_features.c @@ -0,0 +1,446 @@ +// SPDX-License-Identifier: GPL-2.0 + +/** + * Test XDP features + * + * Sets up a veth pair, and for each xdp feature under test: + * - asks the tested interface its xdp capabilities through bpf_xdp_query + * - attach and run some specific programs on both interfaces to check if + * announced capability is respected + */ +#include <pthread.h> +#include <linux/if_link.h> +#include <linux/netdev.h> +#include <linux/if_link.h> +#include <sys/socket.h> +#include "test_progs.h" +#include "network_helpers.h" +#include "xdp_features.skel.h" +#include "xdp_features.h" + +#define TESTER_VETH "v0" +#define TESTER_MAC "00:11:22:33:44:55" +#define TESTER_VETH_IPV6 "2001:db8::1" +#define DUT_NS "xdp_features_ns" +#define DUT_VETH "v1" +#define DUT_MAC "aa:bb:cc:dd:ee:ff" +#define DUT_VETH_IPV6 "2001:db8::11" +#define IP6_MASK 64 +#define LOOP_DELAY_US 10000 +#define TEST_NAME_MAX_LEN 32 +#define TEST_PACKET_COUNT 10 + +struct test_data { + struct xdp_features *skel; + pthread_t dut_echo_thread; + int echo_server_sock; + int tester_ifindex; + int dut_ifindex; + struct sockaddr_storage tester_addr; + struct sockaddr_storage dut_addr; + bool quit_dut_echo_thread; +}; + +static void *run_dut_echo_thread(void *arg) +{ + struct test_data *t = (struct test_data *)arg; + __u32 magic; + + while (!t->quit_dut_echo_thread) { + struct sockaddr_storage addr; + socklen_t addrlen; + size_t n; + + n = recvfrom(t->echo_server_sock, &magic, sizeof(magic), + MSG_WAITALL, (struct sockaddr *)&addr, &addrlen); + if (n != sizeof(magic)) { + usleep(LOOP_DELAY_US); + continue; + } + + if (htonl(magic) != CMD_ECHO) + continue; + + /* Answer echo command with the very same message */ + sendto(t->echo_server_sock, &magic, sizeof(magic), + MSG_NOSIGNAL | MSG_CONFIRM, (struct sockaddr *)&addr, + addrlen); + } + pthread_exit(NULL); +} + +static int dut_start_echo_server(struct test_data *t) +{ + struct nstoken *token; + int err = 0, flags; + + token = open_netns(DUT_NS); + if (!ASSERT_OK_PTR(token, "open dut ns")) + return -EINVAL; + + t->echo_server_sock = + start_server(AF_INET6, SOCK_DGRAM, NULL, DUT_ECHO_PORT, 0); + if (!ASSERT_OK_FD(t->echo_server_sock, "start dut echo server")) { + err = t->echo_server_sock; + goto restore_ns; + } + + flags = fcntl(t->echo_server_sock, F_GETFL, 0); + err = fcntl(t->echo_server_sock, F_SETFL, flags | O_NONBLOCK); + if (!ASSERT_OK(err, "set non-blocking socket")) + goto close_server; + + err = pthread_create(&t->dut_echo_thread, NULL, run_dut_echo_thread, t); + if (!ASSERT_OK(err, "start dut echo thread")) + goto close_server; + + close_netns(token); + return 0; + +close_server: + close(t->echo_server_sock); +restore_ns: + close_netns(token); + return err; +} + +static void dut_stop_echo_server(struct test_data *t) +{ + struct nstoken *token; + + token = open_netns(DUT_NS); + if (!ASSERT_OK_PTR(token, "open dut ns")) + return; + + t->quit_dut_echo_thread = true; + pthread_join(t->dut_echo_thread, NULL); + + close(t->echo_server_sock); + close_netns(token); +} + +static int dut_attach_xdp_prog(struct test_data *t, int flags, + enum netdev_xdp_act drv_feature, + enum xdp_action action) +{ + struct bpf_program *prog; + unsigned int key = 0; + int err, fd = 0; + + if (drv_feature == NETDEV_XDP_ACT_NDO_XMIT) { + struct bpf_devmap_val entry = { .ifindex = t->dut_ifindex }; + + err = bpf_map__update_elem(t->skel->maps.dev_map, &key, + sizeof(key), &entry, sizeof(entry), + 0); + if (!ASSERT_OK(err, "update dev map")) + return err; + + fd = bpf_program__fd(t->skel->progs.xdp_do_redirect_cpumap); + action = XDP_REDIRECT; + } + + switch (action) { + case XDP_TX: + prog = t->skel->progs.xdp_do_tx; + break; + case XDP_DROP: + prog = t->skel->progs.xdp_do_drop; + break; + case XDP_ABORTED: + prog = t->skel->progs.xdp_do_aborted; + break; + case XDP_PASS: + prog = t->skel->progs.xdp_do_pass; + break; + case XDP_REDIRECT: { + struct bpf_cpumap_val entry = { + .qsize = 4096, + .bpf_prog.fd = fd, + }; + + err = bpf_map__update_elem(t->skel->maps.cpu_map, &key, + sizeof(key), &entry, sizeof(entry), + 0); + if (!ASSERT_OK(err, "update cpu map")) + return err; + + prog = t->skel->progs.xdp_do_redirect; + break; + } + default: + return -ENOTSUP; + } + + err = bpf_xdp_attach(t->dut_ifindex, bpf_program__fd(prog), flags, + NULL); + ASSERT_OK(err, "attach xdp prog to dut"); + return err; +} + +static int dut_start_test(struct test_data *t, enum netdev_xdp_act drv_feature, + enum xdp_action action) +{ + int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE; + struct nstoken *token = open_netns(DUT_NS); + int err; + + if (!ASSERT_OK_PTR(token, "open dut ns")) + return -EINVAL; + + err = dut_attach_xdp_prog(t, flags, drv_feature, action); + ASSERT_OK(err, "attach xdp program to dut"); + close_netns(token); + + return err; +} + +static void dut_stop_test(struct test_data *t) +{ + int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE; + struct nstoken *token = open_netns(DUT_NS); + + if (!ASSERT_OK_PTR(token, "open dut ns")) + return; + + bpf_xdp_detach(t->dut_ifindex, flags, NULL); + close_netns(token); +} + +static int dut_get_xdp_features(struct test_data *t, __u64 *xdp_features) +{ + struct nstoken *token = open_netns(DUT_NS); + int err; + + if (!ASSERT_OK_PTR(token, "open dut ns")) + return -EINVAL; + + LIBBPF_OPTS(bpf_xdp_query_opts, opts); + err = bpf_xdp_query(t->dut_ifindex, XDP_FLAGS_DRV_MODE, &opts); + close_netns(token); + + if (ASSERT_OK(err, "get dut interface xdp features")) + *xdp_features = opts.feature_flags; + + return err; +} + +static int send_echo_msg(struct test_data *t) +{ + __u32 magic = htonl(CMD_ECHO); + int sockfd, n; + + sockfd = socket(AF_INET6, SOCK_DGRAM, 0); + if (!ASSERT_OK_FD(sockfd, "open tester socket")) + return sockfd; + + n = sendto(sockfd, &magic, sizeof(magic), MSG_NOSIGNAL | MSG_CONFIRM, + (struct sockaddr *)&t->dut_addr, + sizeof(struct sockaddr_storage)); + close(sockfd); + + return n == sizeof(magic) ? 0 : -EINVAL; +} + +static bool tester_collect_detected_cap(struct test_data *t, + enum netdev_xdp_act drv_feature, + enum xdp_action action) +{ + if (!t->skel->bss->dut_stats) + return false; + + if (drv_feature == NETDEV_XDP_ACT_NDO_XMIT) + return t->skel->bss->tester_stats > 0; + + switch (action) { + case XDP_PASS: + case XDP_TX: + case XDP_REDIRECT: + return t->skel->bss->tester_stats > 0; + case XDP_DROP: + case XDP_ABORTED: + return t->skel->bss->tester_stats == 0; + default: + break; + } + + return false; +} + +static void reset_test_stats(struct test_data *t, + struct sockaddr_storage *tester_addr, + struct sockaddr_storage *dut_addr) +{ + t->skel->bss->tester_stats = 0; + t->skel->bss->dut_stats = 0; +} + +static int setup_network(struct test_data *t) +{ + struct nstoken *token; + int err; + + err = make_sockaddr(AF_INET6, DUT_VETH_IPV6, DUT_ECHO_PORT, + &t->dut_addr, NULL); + if (!ASSERT_OK(err, "dut data addr")) + return -1; + + err = make_sockaddr(AF_INET6, TESTER_VETH_IPV6, 0, &t->tester_addr, + NULL); + if (!ASSERT_OK(err, "tester addr")) + return -1; + + /* Create interfaces and testing namespace */ + SYS(fail, "ip netns add %s", DUT_NS); + SYS(cleanup_ns, + "ip link add %s address %s type veth peer name %s netns %s address %s", + TESTER_VETH, TESTER_MAC, DUT_VETH, DUT_NS, DUT_MAC); + + /* Configure tester side in local namespace */ + SYS(cleanup_interfaces, "ip a add %s/%d nodad dev %s", TESTER_VETH_IPV6, + IP6_MASK, TESTER_VETH); + SYS(cleanup_interfaces, "ip link set %s up", TESTER_VETH); + SYS(cleanup_interfaces, + "ethtool -K %s tx-checksumming off > /dev/null 2>&1", TESTER_VETH); + SYS(cleanup_interfaces, "ip neigh add %s dev %s lladdr %s", + DUT_VETH_IPV6, TESTER_VETH, DUT_MAC); + t->tester_ifindex = if_nametoindex(TESTER_VETH); + if (!ASSERT_NEQ(t->tester_ifindex, 0, + "get tester veth interface index")) + goto cleanup_interfaces; + + /* Configure dut side in remote namespace */ + token = open_netns(DUT_NS); + if (!ASSERT_OK_PTR(token, "switch to dut ns")) + goto cleanup_interfaces; + SYS(restore_ns, "ip link set %s up", DUT_VETH); + SYS(restore_ns, "ip a add %s/%d nodad dev %s", DUT_VETH_IPV6, IP6_MASK, + DUT_VETH); + SYS(restore_ns, "ethtool -K %s tx-checksumming off > /dev/null 2>&1", + DUT_VETH); + SYS(restore_ns, "ip neigh add %s dev %s lladdr %s", TESTER_VETH_IPV6, + DUT_VETH, TESTER_MAC); + t->dut_ifindex = if_nametoindex(DUT_VETH); + if (!ASSERT_NEQ(t->dut_ifindex, 0, "get dut veth interface index")) + goto restore_ns; + close_netns(token); + + return 0; + +restore_ns: + close_netns(token); +cleanup_interfaces: + SYS_NOFAIL("ip link del %s", TESTER_VETH); +cleanup_ns: + SYS_NOFAIL("ip netns del %s", DUT_NS); +fail: + return 1; +} + +static void cleanup_network(void) +{ + SYS_NOFAIL("ip netns del %s", DUT_NS); + SYS_NOFAIL("ip link del %s", TESTER_VETH); +} + +static int tester_run(char *name, struct test_data *t, + enum netdev_xdp_act drv_feature, enum xdp_action action) +{ + int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE; + unsigned long long advertised_feature; + + char test_name[TEST_NAME_MAX_LEN]; + struct bpf_program *prog; + int i, err = -EINVAL; + bool detected_cap; + + if (drv_feature == NETDEV_XDP_ACT_NDO_XMIT || action == XDP_TX) + prog = t->skel->progs.xdp_tester_check_tx; + else + prog = t->skel->progs.xdp_tester_check_rx; + + err = bpf_xdp_attach(t->tester_ifindex, bpf_program__fd(prog), flags, + NULL); + if (!ASSERT_OK(err, "attach xdp program to tester")) + goto out; + + err = dut_start_test(t, drv_feature, action); + if (!ASSERT_OK(err, "send CMD_START to DUT")) + goto out; + + err = dut_get_xdp_features(t, &advertised_feature); + if (!ASSERT_OK(err, "get tester XDP capabilities")) + goto out; + + for (i = 0; i < TEST_PACKET_COUNT; i++) { + err = send_echo_msg(t); + if (!ASSERT_OK(err, "send echo message")) + goto out; + + usleep(LOOP_DELAY_US); + } + dut_stop_test(t); + + detected_cap = tester_collect_detected_cap(t, drv_feature, action); + + snprintf(test_name, TEST_NAME_MAX_LEN, "%s advertised capabilities", + name); + ASSERT_EQ(advertised_feature & drv_feature, drv_feature, test_name); + snprintf(test_name, TEST_NAME_MAX_LEN, "%s detected capabilities", + name); + ASSERT_TRUE(detected_cap, test_name); +out: + reset_test_stats(t, &t->tester_addr, &t->dut_addr); + bpf_xdp_detach(t->tester_ifindex, flags, NULL); + return err < 0 ? err : 0; +} + +void serial_test_xdp_features(void) +{ + struct test_data t = { 0 }; + + if (!ASSERT_OK(setup_network(&t), "setup network")) + return; + + t.skel = xdp_features__open(); + if (!ASSERT_OK_PTR(t.skel, "open skel")) + goto cleanup_network; + t.skel->rodata->tester_addr = + ((struct sockaddr_in6 *)&t.tester_addr)->sin6_addr; + t.skel->rodata->dut_addr = + ((struct sockaddr_in6 *)&t.dut_addr)->sin6_addr; + if (!ASSERT_OK(xdp_features__load(t.skel), "load progs")) + goto cleanup_progs; + if (!ASSERT_OK(xdp_features__attach(t.skel), "attach progs")) + goto cleanup_progs; + + if (!ASSERT_OK(dut_start_echo_server(&t), "start DUT main thread")) + goto cleanup_progs; + + if (test__start_subtest("XDP_PASS")) + tester_run("XDP_PASS", &t, NETDEV_XDP_ACT_BASIC, XDP_PASS); + + if (test__start_subtest("XDP_DROP")) + tester_run("XDP_DROP", &t, NETDEV_XDP_ACT_BASIC, XDP_DROP); + + if (test__start_subtest("XDP_ABORTED")) + tester_run("XDP_ABORTED", &t, NETDEV_XDP_ACT_BASIC, + XDP_ABORTED); + + if (test__start_subtest("XDP_TX")) + tester_run("XDP_TX", &t, NETDEV_XDP_ACT_BASIC, XDP_TX); + + if (test__start_subtest("XDP_REDIRECT")) + tester_run("XDP_REDIRECT", &t, NETDEV_XDP_ACT_REDIRECT, + XDP_REDIRECT); + + if (test__start_subtest("XDP_NDO_XMIT")) + tester_run("XDP_NDO_XMIT", &t, NETDEV_XDP_ACT_NDO_XMIT, 0); + + dut_stop_echo_server(&t); + +cleanup_progs: + xdp_features__destroy(t.skel); +cleanup_network: + cleanup_network(); +} diff --git a/tools/testing/selftests/bpf/progs/xdp_features.c b/tools/testing/selftests/bpf/progs/xdp_features.c index 67424084a38a..451e8fc79534 100644 --- a/tools/testing/selftests/bpf/progs/xdp_features.c +++ b/tools/testing/selftests/bpf/progs/xdp_features.c @@ -30,19 +30,9 @@ struct xdp_cpumap_stats { unsigned int drop; }; -struct { - __uint(type, BPF_MAP_TYPE_ARRAY); - __type(key, __u32); - __type(value, __u32); - __uint(max_entries, 1); -} stats SEC(".maps"); +__u32 tester_stats; +__u32 dut_stats; -struct { - __uint(type, BPF_MAP_TYPE_ARRAY); - __type(key, __u32); - __type(value, __u32); - __uint(max_entries, 1); -} dut_stats SEC(".maps"); struct { __uint(type, BPF_MAP_TYPE_CPUMAP); @@ -67,7 +57,7 @@ xdp_process_echo_packet(struct xdp_md *xdp, bool dut) void *data_end = (void *)(long)xdp->data_end; void *data = (void *)(long)xdp->data; struct ethhdr *eh = data; - struct tlv_hdr *tlv; + __u32 *magic; struct udphdr *uh; __be16 port; @@ -124,28 +114,23 @@ xdp_process_echo_packet(struct xdp_md *xdp, bool dut) if (port != bpf_htons(DUT_ECHO_PORT)) return -EINVAL; - tlv = (struct tlv_hdr *)(uh + 1); - if (tlv + 1 > data_end) + magic = (__u32 *)(uh + 1); + if (magic + 1 > data_end) return -EINVAL; - return bpf_htons(tlv->type) == CMD_ECHO ? 0 : -EINVAL; + return bpf_htonl(*magic) == CMD_ECHO ? 0 : -EINVAL; } static __always_inline int xdp_update_stats(struct xdp_md *xdp, bool tx, bool dut) { - __u32 *val, key = 0; - if (xdp_process_echo_packet(xdp, tx)) return -EINVAL; if (dut) - val = bpf_map_lookup_elem(&dut_stats, &key); + __sync_add_and_fetch(&dut_stats, 1); else - val = bpf_map_lookup_elem(&stats, &key); - - if (val) - __sync_add_and_fetch(val, 1); + __sync_add_and_fetch(&tester_stats, 1); return 0; } @@ -204,7 +189,7 @@ int xdp_do_tx(struct xdp_md *xdp) __u8 tmp_mac[ETH_ALEN]; if (xdp_update_stats(xdp, true, true)) - return XDP_PASS; + return XDP_DROP; __builtin_memcpy(tmp_mac, eh->h_source, ETH_ALEN); __builtin_memcpy(eh->h_source, eh->h_dest, ETH_ALEN); @@ -217,7 +202,7 @@ SEC("xdp") int xdp_do_redirect(struct xdp_md *xdp) { if (xdp_process_echo_packet(xdp, true)) - return XDP_PASS; + return XDP_DROP; return bpf_redirect_map(&cpu_map, 0, 0); } @@ -226,11 +211,7 @@ SEC("tp_btf/xdp_exception") int BPF_PROG(xdp_exception, const struct net_device *dev, const struct bpf_prog *xdp, __u32 act) { - __u32 *val, key = 0; - - val = bpf_map_lookup_elem(&dut_stats, &key); - if (val) - __sync_add_and_fetch(val, 1); + __sync_add_and_fetch(&dut_stats, 1); return 0; } @@ -239,11 +220,7 @@ SEC("tp_btf/xdp_cpumap_kthread") int BPF_PROG(tp_xdp_cpumap_kthread, int map_id, unsigned int processed, unsigned int drops, int sched, struct xdp_cpumap_stats *xdp_stats) { - __u32 *val, key = 0; - - val = bpf_map_lookup_elem(&dut_stats, &key); - if (val) - __sync_add_and_fetch(val, 1); + __sync_add_and_fetch(&dut_stats, 1); return 0; } @@ -256,7 +233,7 @@ int xdp_do_redirect_cpumap(struct xdp_md *xdp) __u8 tmp_mac[ETH_ALEN]; if (xdp_process_echo_packet(xdp, true)) - return XDP_PASS; + return XDP_DROP; __builtin_memcpy(tmp_mac, eh->h_source, ETH_ALEN); __builtin_memcpy(eh->h_source, eh->h_dest, ETH_ALEN); diff --git a/tools/testing/selftests/bpf/test_xdp_features.sh b/tools/testing/selftests/bpf/test_xdp_features.sh deleted file mode 100755 index 0aa71c4455c0..000000000000 --- a/tools/testing/selftests/bpf/test_xdp_features.sh +++ /dev/null @@ -1,107 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -readonly NS="ns1-$(mktemp -u XXXXXX)" -readonly V0_IP4=10.10.0.11 -readonly V1_IP4=10.10.0.1 -readonly V0_IP6=2001:db8::11 -readonly V1_IP6=2001:db8::1 - -ret=1 - -setup() { - { - ip netns add ${NS} - - ip link add v1 type veth peer name v0 netns ${NS} - - ip link set v1 up - ip addr add $V1_IP4/24 dev v1 - ip addr add $V1_IP6/64 nodad dev v1 - ip -n ${NS} link set dev v0 up - ip -n ${NS} addr add $V0_IP4/24 dev v0 - ip -n ${NS} addr add $V0_IP6/64 nodad dev v0 - - # Enable XDP mode and disable checksum offload - ethtool -K v1 gro on - ethtool -K v1 tx-checksumming off - ip netns exec ${NS} ethtool -K v0 gro on - ip netns exec ${NS} ethtool -K v0 tx-checksumming off - } > /dev/null 2>&1 -} - -cleanup() { - ip link del v1 2> /dev/null - ip netns del ${NS} 2> /dev/null - [ "$(pidof xdp_features)" = "" ] || kill $(pidof xdp_features) 2> /dev/null -} - -wait_for_dut_server() { - while sleep 1; do - ss -tlp | grep -q xdp_features - [ $? -eq 0 ] && break - done -} - -test_xdp_features() { - setup - - ## XDP_PASS - ./xdp_features -f XDP_PASS -D $V1_IP6 -T $V0_IP6 v1 & - wait_for_dut_server - ip netns exec ${NS} ./xdp_features -t -f XDP_PASS \ - -D $V1_IP6 -C $V1_IP6 \ - -T $V0_IP6 v0 - [ $? -ne 0 ] && exit - - ## XDP_DROP - ./xdp_features -f XDP_DROP -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1 & - wait_for_dut_server - ip netns exec ${NS} ./xdp_features -t -f XDP_DROP \ - -D ::ffff:$V1_IP4 \ - -C ::ffff:$V1_IP4 \ - -T ::ffff:$V0_IP4 v0 - [ $? -ne 0 ] && exit - - ## XDP_ABORTED - ./xdp_features -f XDP_ABORTED -D $V1_IP6 -T $V0_IP6 v1 & - wait_for_dut_server - ip netns exec ${NS} ./xdp_features -t -f XDP_ABORTED \ - -D $V1_IP6 -C $V1_IP6 \ - -T $V0_IP6 v0 - [ $? -ne 0 ] && exit - - ## XDP_TX - ./xdp_features -f XDP_TX -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1 & - wait_for_dut_server - ip netns exec ${NS} ./xdp_features -t -f XDP_TX \ - -D ::ffff:$V1_IP4 \ - -C ::ffff:$V1_IP4 \ - -T ::ffff:$V0_IP4 v0 - [ $? -ne 0 ] && exit - - ## XDP_REDIRECT - ./xdp_features -f XDP_REDIRECT -D $V1_IP6 -T $V0_IP6 v1 & - wait_for_dut_server - ip netns exec ${NS} ./xdp_features -t -f XDP_REDIRECT \ - -D $V1_IP6 -C $V1_IP6 \ - -T $V0_IP6 v0 - [ $? -ne 0 ] && exit - - ## XDP_NDO_XMIT - ./xdp_features -f XDP_NDO_XMIT -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1 & - wait_for_dut_server - ip netns exec ${NS} ./xdp_features -t -f XDP_NDO_XMIT \ - -D ::ffff:$V1_IP4 \ - -C ::ffff:$V1_IP4 \ - -T ::ffff:$V0_IP4 v0 - ret=$? - cleanup -} - -set -e -trap cleanup 2 3 6 9 - -test_xdp_features - -exit $ret diff --git a/tools/testing/selftests/bpf/xdp_features.c b/tools/testing/selftests/bpf/xdp_features.c deleted file mode 100644 index 595c79141cf3..000000000000 --- a/tools/testing/selftests/bpf/xdp_features.c +++ /dev/null @@ -1,718 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <uapi/linux/bpf.h> -#include <uapi/linux/netdev.h> -#include <linux/if_link.h> -#include <signal.h> -#include <argp.h> -#include <net/if.h> -#include <sys/socket.h> -#include <netinet/in.h> -#include <netinet/tcp.h> -#include <unistd.h> -#include <arpa/inet.h> -#include <bpf/bpf.h> -#include <bpf/libbpf.h> -#include <pthread.h> - -#include <network_helpers.h> - -#include "xdp_features.skel.h" -#include "xdp_features.h" - -#define RED(str) "\033[0;31m" str "\033[0m" -#define GREEN(str) "\033[0;32m" str "\033[0m" -#define YELLOW(str) "\033[0;33m" str "\033[0m" - -static struct env { - bool verbosity; - char ifname[IF_NAMESIZE]; - int ifindex; - bool is_tester; - struct { - enum netdev_xdp_act drv_feature; - enum xdp_action action; - } feature; - struct sockaddr_storage dut_ctrl_addr; - struct sockaddr_storage dut_addr; - struct sockaddr_storage tester_addr; -} env; - -#define BUFSIZE 128 - -void test__fail(void) { /* for network_helpers.c */ } - -static int libbpf_print_fn(enum libbpf_print_level level, - const char *format, va_list args) -{ - if (level == LIBBPF_DEBUG && !env.verbosity) - return 0; - return vfprintf(stderr, format, args); -} - -static volatile bool exiting; - -static void sig_handler(int sig) -{ - exiting = true; -} - -const char *argp_program_version = "xdp-features 0.0"; -const char argp_program_doc[] = -"XDP features detection application.\n" -"\n" -"XDP features application checks the XDP advertised features match detected ones.\n" -"\n" -"USAGE: ./xdp-features [-vt] [-f <xdp-feature>] [-D <dut-data-ip>] [-T <tester-data-ip>] [-C <dut-ctrl-ip>] <iface-name>\n" -"\n" -"dut-data-ip, tester-data-ip, dut-ctrl-ip: IPv6 or IPv4-mapped-IPv6 addresses;\n" -"\n" -"XDP features\n:" -"- XDP_PASS\n" -"- XDP_DROP\n" -"- XDP_ABORTED\n" -"- XDP_REDIRECT\n" -"- XDP_NDO_XMIT\n" -"- XDP_TX\n"; - -static const struct argp_option opts[] = { - { "verbose", 'v', NULL, 0, "Verbose debug output" }, - { "tester", 't', NULL, 0, "Tester mode" }, - { "feature", 'f', "XDP-FEATURE", 0, "XDP feature to test" }, - { "dut_data_ip", 'D', "DUT-DATA-IP", 0, "DUT IP data channel" }, - { "dut_ctrl_ip", 'C', "DUT-CTRL-IP", 0, "DUT IP control channel" }, - { "tester_data_ip", 'T', "TESTER-DATA-IP", 0, "Tester IP data channel" }, - {}, -}; - -static int get_xdp_feature(const char *arg) -{ - if (!strcmp(arg, "XDP_PASS")) { - env.feature.action = XDP_PASS; - env.feature.drv_feature = NETDEV_XDP_ACT_BASIC; - } else if (!strcmp(arg, "XDP_DROP")) { - env.feature.drv_feature = NETDEV_XDP_ACT_BASIC; - env.feature.action = XDP_DROP; - } else if (!strcmp(arg, "XDP_ABORTED")) { - env.feature.drv_feature = NETDEV_XDP_ACT_BASIC; - env.feature.action = XDP_ABORTED; - } else if (!strcmp(arg, "XDP_TX")) { - env.feature.drv_feature = NETDEV_XDP_ACT_BASIC; - env.feature.action = XDP_TX; - } else if (!strcmp(arg, "XDP_REDIRECT")) { - env.feature.drv_feature = NETDEV_XDP_ACT_REDIRECT; - env.feature.action = XDP_REDIRECT; - } else if (!strcmp(arg, "XDP_NDO_XMIT")) { - env.feature.drv_feature = NETDEV_XDP_ACT_NDO_XMIT; - } else { - return -EINVAL; - } - - return 0; -} - -static char *get_xdp_feature_str(void) -{ - switch (env.feature.action) { - case XDP_PASS: - return YELLOW("XDP_PASS"); - case XDP_DROP: - return YELLOW("XDP_DROP"); - case XDP_ABORTED: - return YELLOW("XDP_ABORTED"); - case XDP_TX: - return YELLOW("XDP_TX"); - case XDP_REDIRECT: - return YELLOW("XDP_REDIRECT"); - default: - break; - } - - if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT) - return YELLOW("XDP_NDO_XMIT"); - - return ""; -} - -static error_t parse_arg(int key, char *arg, struct argp_state *state) -{ - switch (key) { - case 'v': - env.verbosity = true; - break; - case 't': - env.is_tester = true; - break; - case 'f': - if (get_xdp_feature(arg) < 0) { - fprintf(stderr, "Invalid xdp feature: %s\n", arg); - argp_usage(state); - return ARGP_ERR_UNKNOWN; - } - break; - case 'D': - if (make_sockaddr(AF_INET6, arg, DUT_ECHO_PORT, - &env.dut_addr, NULL)) { - fprintf(stderr, - "Invalid address assigned to the Device Under Test: %s\n", - arg); - return ARGP_ERR_UNKNOWN; - } - break; - case 'C': - if (make_sockaddr(AF_INET6, arg, DUT_CTRL_PORT, - &env.dut_ctrl_addr, NULL)) { - fprintf(stderr, - "Invalid address assigned to the Device Under Test: %s\n", - arg); - return ARGP_ERR_UNKNOWN; - } - break; - case 'T': - if (make_sockaddr(AF_INET6, arg, 0, &env.tester_addr, NULL)) { - fprintf(stderr, - "Invalid address assigned to the Tester device: %s\n", - arg); - return ARGP_ERR_UNKNOWN; - } - break; - case ARGP_KEY_ARG: - errno = 0; - if (strlen(arg) >= IF_NAMESIZE) { - fprintf(stderr, "Invalid device name: %s\n", arg); - argp_usage(state); - return ARGP_ERR_UNKNOWN; - } - - env.ifindex = if_nametoindex(arg); - if (!env.ifindex) - env.ifindex = strtoul(arg, NULL, 0); - if (!env.ifindex || !if_indextoname(env.ifindex, env.ifname)) { - fprintf(stderr, - "Bad interface index or name (%d): %s\n", - errno, strerror(errno)); - argp_usage(state); - return ARGP_ERR_UNKNOWN; - } - break; - default: - return ARGP_ERR_UNKNOWN; - } - - return 0; -} - -static const struct argp argp = { - .options = opts, - .parser = parse_arg, - .doc = argp_program_doc, -}; - -static void set_env_default(void) -{ - env.feature.drv_feature = NETDEV_XDP_ACT_NDO_XMIT; - env.feature.action = -EINVAL; - env.ifindex = -ENODEV; - strcpy(env.ifname, "unknown"); - make_sockaddr(AF_INET6, "::ffff:127.0.0.1", DUT_CTRL_PORT, - &env.dut_ctrl_addr, NULL); - make_sockaddr(AF_INET6, "::ffff:127.0.0.1", DUT_ECHO_PORT, - &env.dut_addr, NULL); - make_sockaddr(AF_INET6, "::ffff:127.0.0.1", 0, &env.tester_addr, NULL); -} - -static void *dut_echo_thread(void *arg) -{ - unsigned char buf[sizeof(struct tlv_hdr)]; - int sockfd = *(int *)arg; - - while (!exiting) { - struct tlv_hdr *tlv = (struct tlv_hdr *)buf; - struct sockaddr_storage addr; - socklen_t addrlen; - size_t n; - - n = recvfrom(sockfd, buf, sizeof(buf), MSG_WAITALL, - (struct sockaddr *)&addr, &addrlen); - if (n != ntohs(tlv->len)) - continue; - - if (ntohs(tlv->type) != CMD_ECHO) - continue; - - sendto(sockfd, buf, sizeof(buf), MSG_NOSIGNAL | MSG_CONFIRM, - (struct sockaddr *)&addr, addrlen); - } - - pthread_exit((void *)0); - close(sockfd); - - return NULL; -} - -static int dut_run_echo_thread(pthread_t *t, int *sockfd) -{ - int err; - - sockfd = start_reuseport_server(AF_INET6, SOCK_DGRAM, NULL, - DUT_ECHO_PORT, 0, 1); - if (!sockfd) { - fprintf(stderr, - "Failed creating data UDP socket on device %s\n", - env.ifname); - return -errno; - } - - /* start echo channel */ - err = pthread_create(t, NULL, dut_echo_thread, sockfd); - if (err) { - fprintf(stderr, - "Failed creating data UDP thread on device %s: %s\n", - env.ifname, strerror(-err)); - free_fds(sockfd, 1); - return -EINVAL; - } - - return 0; -} - -static int dut_attach_xdp_prog(struct xdp_features *skel, int flags) -{ - enum xdp_action action = env.feature.action; - struct bpf_program *prog; - unsigned int key = 0; - int err, fd = 0; - - if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT) { - struct bpf_devmap_val entry = { - .ifindex = env.ifindex, - }; - - err = bpf_map__update_elem(skel->maps.dev_map, - &key, sizeof(key), - &entry, sizeof(entry), 0); - if (err < 0) - return err; - - fd = bpf_program__fd(skel->progs.xdp_do_redirect_cpumap); - action = XDP_REDIRECT; - } - - switch (action) { - case XDP_TX: - prog = skel->progs.xdp_do_tx; - break; - case XDP_DROP: - prog = skel->progs.xdp_do_drop; - break; - case XDP_ABORTED: - prog = skel->progs.xdp_do_aborted; - break; - case XDP_PASS: - prog = skel->progs.xdp_do_pass; - break; - case XDP_REDIRECT: { - struct bpf_cpumap_val entry = { - .qsize = 2048, - .bpf_prog.fd = fd, - }; - - err = bpf_map__update_elem(skel->maps.cpu_map, - &key, sizeof(key), - &entry, sizeof(entry), 0); - if (err < 0) - return err; - - prog = skel->progs.xdp_do_redirect; - break; - } - default: - return -EINVAL; - } - - err = bpf_xdp_attach(env.ifindex, bpf_program__fd(prog), flags, NULL); - if (err) - fprintf(stderr, "Failed attaching XDP program to device %s\n", - env.ifname); - return err; -} - -static int recv_msg(int sockfd, void *buf, size_t bufsize, void *val, - size_t val_size) -{ - struct tlv_hdr *tlv = (struct tlv_hdr *)buf; - size_t len; - - len = recv(sockfd, buf, bufsize, 0); - if (len != ntohs(tlv->len) || len < sizeof(*tlv)) - return -EINVAL; - - if (val) { - len -= sizeof(*tlv); - if (len > val_size) - return -ENOMEM; - - memcpy(val, tlv->data, len); - } - - return 0; -} - -static int dut_run(struct xdp_features *skel) -{ - int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE; - int state, err = 0, *sockfd, ctrl_sockfd, echo_sockfd; - struct sockaddr_storage ctrl_addr; - pthread_t dut_thread = 0; - socklen_t addrlen; - - sockfd = start_reuseport_server(AF_INET6, SOCK_STREAM, NULL, - DUT_CTRL_PORT, 0, 1); - if (!sockfd) { - fprintf(stderr, - "Failed creating control socket on device %s\n", env.ifname); - return -errno; - } - - ctrl_sockfd = accept(*sockfd, (struct sockaddr *)&ctrl_addr, &addrlen); - if (ctrl_sockfd < 0) { - fprintf(stderr, - "Failed accepting connections on device %s control socket\n", - env.ifname); - free_fds(sockfd, 1); - return -errno; - } - - /* CTRL loop */ - while (!exiting) { - unsigned char buf[BUFSIZE] = {}; - struct tlv_hdr *tlv = (struct tlv_hdr *)buf; - - err = recv_msg(ctrl_sockfd, buf, BUFSIZE, NULL, 0); - if (err) - continue; - - switch (ntohs(tlv->type)) { - case CMD_START: { - if (state == CMD_START) - continue; - - state = CMD_START; - /* Load the XDP program on the DUT */ - err = dut_attach_xdp_prog(skel, flags); - if (err) - goto out; - - err = dut_run_echo_thread(&dut_thread, &echo_sockfd); - if (err < 0) - goto out; - - tlv->type = htons(CMD_ACK); - tlv->len = htons(sizeof(*tlv)); - err = send(ctrl_sockfd, buf, sizeof(*tlv), 0); - if (err < 0) - goto end_thread; - break; - } - case CMD_STOP: - if (state != CMD_START) - break; - - state = CMD_STOP; - - exiting = true; - bpf_xdp_detach(env.ifindex, flags, NULL); - - tlv->type = htons(CMD_ACK); - tlv->len = htons(sizeof(*tlv)); - err = send(ctrl_sockfd, buf, sizeof(*tlv), 0); - goto end_thread; - case CMD_GET_XDP_CAP: { - LIBBPF_OPTS(bpf_xdp_query_opts, opts); - unsigned long long val; - size_t n; - - err = bpf_xdp_query(env.ifindex, XDP_FLAGS_DRV_MODE, - &opts); - if (err) { - fprintf(stderr, - "Failed querying XDP cap for device %s\n", - env.ifname); - goto end_thread; - } - - tlv->type = htons(CMD_ACK); - n = sizeof(*tlv) + sizeof(opts.feature_flags); - tlv->len = htons(n); - - val = htobe64(opts.feature_flags); - memcpy(tlv->data, &val, sizeof(val)); - - err = send(ctrl_sockfd, buf, n, 0); - if (err < 0) - goto end_thread; - break; - } - case CMD_GET_STATS: { - unsigned int key = 0, val; - size_t n; - - err = bpf_map__lookup_elem(skel->maps.dut_stats, - &key, sizeof(key), - &val, sizeof(val), 0); - if (err) { - fprintf(stderr, - "bpf_map_lookup_elem failed (%d)\n", err); - goto end_thread; - } - - tlv->type = htons(CMD_ACK); - n = sizeof(*tlv) + sizeof(val); - tlv->len = htons(n); - - val = htonl(val); - memcpy(tlv->data, &val, sizeof(val)); - - err = send(ctrl_sockfd, buf, n, 0); - if (err < 0) - goto end_thread; - break; - } - default: - break; - } - } - -end_thread: - pthread_join(dut_thread, NULL); -out: - bpf_xdp_detach(env.ifindex, flags, NULL); - close(ctrl_sockfd); - free_fds(sockfd, 1); - - return err; -} - -static bool tester_collect_detected_cap(struct xdp_features *skel, - unsigned int dut_stats) -{ - unsigned int err, key = 0, val; - - if (!dut_stats) - return false; - - err = bpf_map__lookup_elem(skel->maps.stats, &key, sizeof(key), - &val, sizeof(val), 0); - if (err) { - fprintf(stderr, "bpf_map_lookup_elem failed (%d)\n", err); - return false; - } - - switch (env.feature.action) { - case XDP_PASS: - case XDP_TX: - case XDP_REDIRECT: - return val > 0; - case XDP_DROP: - case XDP_ABORTED: - return val == 0; - default: - break; - } - - if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT) - return val > 0; - - return false; -} - -static int send_and_recv_msg(int sockfd, enum test_commands cmd, void *val, - size_t val_size) -{ - unsigned char buf[BUFSIZE] = {}; - struct tlv_hdr *tlv = (struct tlv_hdr *)buf; - int err; - - tlv->type = htons(cmd); - tlv->len = htons(sizeof(*tlv)); - - err = send(sockfd, buf, sizeof(*tlv), 0); - if (err < 0) - return err; - - err = recv_msg(sockfd, buf, BUFSIZE, val, val_size); - if (err < 0) - return err; - - return ntohs(tlv->type) == CMD_ACK ? 0 : -EINVAL; -} - -static int send_echo_msg(void) -{ - unsigned char buf[sizeof(struct tlv_hdr)]; - struct tlv_hdr *tlv = (struct tlv_hdr *)buf; - int sockfd, n; - - sockfd = socket(AF_INET6, SOCK_DGRAM, 0); - if (sockfd < 0) { - fprintf(stderr, - "Failed creating data UDP socket on device %s\n", - env.ifname); - return -errno; - } - - tlv->type = htons(CMD_ECHO); - tlv->len = htons(sizeof(*tlv)); - - n = sendto(sockfd, buf, sizeof(*tlv), MSG_NOSIGNAL | MSG_CONFIRM, - (struct sockaddr *)&env.dut_addr, sizeof(env.dut_addr)); - close(sockfd); - - return n == ntohs(tlv->len) ? 0 : -EINVAL; -} - -static int tester_run(struct xdp_features *skel) -{ - int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE; - unsigned long long advertised_feature; - struct bpf_program *prog; - unsigned int stats; - int i, err, sockfd; - bool detected_cap; - - sockfd = socket(AF_INET6, SOCK_STREAM, 0); - if (sockfd < 0) { - fprintf(stderr, - "Failed creating tester service control socket\n"); - return -errno; - } - - if (settimeo(sockfd, 1000) < 0) - return -EINVAL; - - err = connect(sockfd, (struct sockaddr *)&env.dut_ctrl_addr, - sizeof(env.dut_ctrl_addr)); - if (err) { - fprintf(stderr, - "Failed connecting to the Device Under Test control socket\n"); - return -errno; - } - - err = send_and_recv_msg(sockfd, CMD_GET_XDP_CAP, &advertised_feature, - sizeof(advertised_feature)); - if (err < 0) { - close(sockfd); - return err; - } - - advertised_feature = be64toh(advertised_feature); - - if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT || - env.feature.action == XDP_TX) - prog = skel->progs.xdp_tester_check_tx; - else - prog = skel->progs.xdp_tester_check_rx; - - err = bpf_xdp_attach(env.ifindex, bpf_program__fd(prog), flags, NULL); - if (err) { - fprintf(stderr, "Failed attaching XDP program to device %s\n", - env.ifname); - goto out; - } - - err = send_and_recv_msg(sockfd, CMD_START, NULL, 0); - if (err) - goto out; - - for (i = 0; i < 10 && !exiting; i++) { - err = send_echo_msg(); - if (err < 0) - goto out; - - sleep(1); - } - - err = send_and_recv_msg(sockfd, CMD_GET_STATS, &stats, sizeof(stats)); - if (err) - goto out; - - /* stop the test */ - err = send_and_recv_msg(sockfd, CMD_STOP, NULL, 0); - /* send a new echo message to wake echo thread of the dut */ - send_echo_msg(); - - detected_cap = tester_collect_detected_cap(skel, ntohl(stats)); - - fprintf(stdout, "Feature %s: [%s][%s]\n", get_xdp_feature_str(), - detected_cap ? GREEN("DETECTED") : RED("NOT DETECTED"), - env.feature.drv_feature & advertised_feature ? GREEN("ADVERTISED") - : RED("NOT ADVERTISED")); -out: - bpf_xdp_detach(env.ifindex, flags, NULL); - close(sockfd); - return err < 0 ? err : 0; -} - -int main(int argc, char **argv) -{ - struct xdp_features *skel; - int err; - - libbpf_set_strict_mode(LIBBPF_STRICT_ALL); - libbpf_set_print(libbpf_print_fn); - - signal(SIGINT, sig_handler); - signal(SIGTERM, sig_handler); - - set_env_default(); - - /* Parse command line arguments */ - err = argp_parse(&argp, argc, argv, 0, NULL, NULL); - if (err) - return err; - - if (env.ifindex < 0) { - fprintf(stderr, "Invalid device name %s\n", env.ifname); - return -ENODEV; - } - - /* Load and verify BPF application */ - skel = xdp_features__open(); - if (!skel) { - fprintf(stderr, "Failed to open and load BPF skeleton\n"); - return -EINVAL; - } - - skel->rodata->tester_addr = - ((struct sockaddr_in6 *)&env.tester_addr)->sin6_addr; - skel->rodata->dut_addr = - ((struct sockaddr_in6 *)&env.dut_addr)->sin6_addr; - - /* Load & verify BPF programs */ - err = xdp_features__load(skel); - if (err) { - fprintf(stderr, "Failed to load and verify BPF skeleton\n"); - goto cleanup; - } - - err = xdp_features__attach(skel); - if (err) { - fprintf(stderr, "Failed to attach BPF skeleton\n"); - goto cleanup; - } - - if (env.is_tester) { - /* Tester */ - fprintf(stdout, "Starting tester service on device %s\n", - env.ifname); - err = tester_run(skel); - } else { - /* DUT */ - fprintf(stdout, "Starting test on device %s\n", env.ifname); - err = dut_run(skel); - } - -cleanup: - xdp_features__destroy(skel); - - return err < 0 ? -err : 0; -} diff --git a/tools/testing/selftests/bpf/xdp_features.h b/tools/testing/selftests/bpf/xdp_features.h index 2670c541713b..2fa7a2e156c7 100644 --- a/tools/testing/selftests/bpf/xdp_features.h +++ b/tools/testing/selftests/bpf/xdp_features.h @@ -1,20 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* test commands */ -enum test_commands { - CMD_STOP, /* CMD */ - CMD_START, /* CMD */ - CMD_ECHO, /* CMD */ - CMD_ACK, /* CMD + data */ - CMD_GET_XDP_CAP, /* CMD */ - CMD_GET_STATS, /* CMD */ -}; +#define CMD_ECHO 0x4543484F /* 4 bytes magic */ -#define DUT_CTRL_PORT 12345 #define DUT_ECHO_PORT 12346 - -struct tlv_hdr { - __be16 type; - __be16 len; - __u8 data[]; -}; --- base-commit: 33a4c81d04d3011e79f70fbc2d68a4d6cb12b9a5 change-id: 20240730-convert_xdp_tests-ccd66bfe33db Best regards, -- Alexis Lothoré, Bootlin Embedded Linux and Kernel engineering https://bootlin.com

9 months, 3 weeks

3
2
0 0

[PATCH] list: test: Mending tests for list_cut_position()

by I Hsin Cheng

Mending test for list_cut_position*() for the missing check of integer "i" after the second loop. The variable should be checked for second time to make sure both lists after the cut operation are formed as expected. Signed-off-by: I Hsin Cheng <richard120310(a)gmail.com> --- lib/list-test.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/lib/list-test.c b/lib/list-test.c index 37cbc33e9fdb..f59188fc2aca 100644 --- a/lib/list-test.c +++ b/lib/list-test.c @@ -404,10 +404,13 @@ static void list_test_list_cut_position(struct kunit *test) KUNIT_EXPECT_EQ(test, i, 2); + i = 0; list_for_each(cur, &list1) { KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); i++; } + + KUNIT_EXPECT_EQ(test, i, 1); } static void list_test_list_cut_before(struct kunit *test) @@ -432,10 +435,13 @@ static void list_test_list_cut_before(struct kunit *test) KUNIT_EXPECT_EQ(test, i, 1); + i = 0; list_for_each(cur, &list1) { KUNIT_EXPECT_PTR_EQ(test, cur, &entries[i]); i++; } + + KUNIT_EXPECT_EQ(i, 2); } static void list_test_list_splice(struct kunit *test) -- 2.43.0

9 months, 3 weeks

1
0
0 0

[PATCH] list: test: Increasing coverage of list_test_list_replace*()

by I Hsin Cheng

Increase the test coverage of list_test_list_replace*() by adding the checks to compare the pointer of "a_new.next" and "a_new.prev" to make sure a perfect circular doubly linked list is formed after the replacement. Signed-off-by: I Hsin Cheng <richard120310(a)gmail.com> --- lib/list-test.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/lib/list-test.c b/lib/list-test.c index 37cbc33e9fdb..e207c4c98d70 100644 --- a/lib/list-test.c +++ b/lib/list-test.c @@ -102,6 +102,8 @@ static void list_test_list_replace(struct kunit *test) /* now: [list] -> a_new -> b */ KUNIT_EXPECT_PTR_EQ(test, list.next, &a_new); KUNIT_EXPECT_PTR_EQ(test, b.prev, &a_new); + KUNIT_EXPECT_PTR_EQ(test, a_new.next, &b); + KUNIT_EXPECT_PTR_EQ(test, a_new.prev, &list); } static void list_test_list_replace_init(struct kunit *test) @@ -118,6 +120,8 @@ static void list_test_list_replace_init(struct kunit *test) /* now: [list] -> a_new -> b */ KUNIT_EXPECT_PTR_EQ(test, list.next, &a_new); KUNIT_EXPECT_PTR_EQ(test, b.prev, &a_new); + KUNIT_EXPECT_PTR_EQ(test, a_new.next, &b); + KUNIT_EXPECT_PTR_EQ(test, a_new.prev, &list); /* check a_old is empty (initialized) */ KUNIT_EXPECT_TRUE(test, list_empty_careful(&a_old)); -- 2.43.0

9 months, 3 weeks

1
0
0 0

[PATCH net-next v2] selftests: return failure when timestamps can't be reported

by Jason Xing

From: Jason Xing <kernelxing(a)tencent.com> When I was trying to modify the tx timestamping feature, I found that running "./txtimestamp -4 -C -L 127.0.0.1" didn't reflect the error: I succeeded to generate timestamp stored in the skb but later failed to report it to the userspace (which means failed to put css into cmsg). It can happen when someone writes buggy codes in __sock_recv_timestamp(), for example. After adding the check so that running ./txtimestamp will reflect the result correctly like this if there is a bug in the reporting phase: protocol: TCP payload: 10 server port: 9000 family: INET test SND USR: 1725458477 s 667997 us (seq=0, len=0) Failed to report timestamps USR: 1725458477 s 718128 us (seq=0, len=0) Failed to report timestamps USR: 1725458477 s 768273 us (seq=0, len=0) Failed to report timestamps USR: 1725458477 s 818416 us (seq=0, len=0) Failed to report timestamps ... In the future, it will help us detect whether the new coming patch has bugs or not. Signed-off-by: Jason Xing <kernelxing(a)tencent.com> --- v2 Link: https://lore.kernel.org/all/20240904144446.41274-1-kerneljasonxing@gmail.co… 1. mainly change from "parse" to "report", update the commit message. --- tools/testing/selftests/net/txtimestamp.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/txtimestamp.c b/tools/testing/selftests/net/txtimestamp.c index ec60a16c9307..d626f22f9550 100644 --- a/tools/testing/selftests/net/txtimestamp.c +++ b/tools/testing/selftests/net/txtimestamp.c @@ -356,8 +356,12 @@ static void __recv_errmsg_cmsg(struct msghdr *msg, int payload_len) } } - if (batch > 1) + if (batch > 1) { fprintf(stderr, "batched %d timestamps\n", batch); + } else if (!batch) { + fprintf(stderr, "Failed to report timestamps\n"); + test_failed = true; + } } static int recv_errmsg(int fd) -- 2.37.3

9 months, 3 weeks

4
3
0 0

[PATCH net-next v2 0/5] selftests: mptcp: add time per subtests in TAP output

by Matthieu Baerts (NGI0)

Patches here add 'time=<N>ms' in the diagnostic data of the TAP output, e.g. ok 1 - pm_netlink: defaults addr list # time=9ms This addition is useful to quickly identify which subtests are taking a longer time than the others, or more than expected. Note that there are no specific formats to follow to show this time according to the TAP 13, TAP 14 and KTAP specifications, but we follow the format being parsed by NIPA [1]. Patch 1 modifies mptcp_lib.sh to add this support to all MPTCP selftests. Patch 2 removes the now duplicated info in mptcp_connect.sh Patch 3 slightly improves the precision of the first subtests in all MPTCP subtests. Patches 4 and 5 remove duplicated spaces in TAP output, for the TAP parsers that cannot handle them properly. Link: https://github.com/linux-netdev/nipa/pull/36 Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Changes in v2: - Typo in the commit message of patch 2 (Jakub) - Two additional patches to remove duplicated spaces in TAP output - Link to v1: https://lore.kernel.org/r/20240902-net-next-mptcp-ksft-subtest-time-v1-0-f1… --- Matthieu Baerts (NGI0) (5): selftests: mptcp: lib: add time per subtests in TAP output selftests: mptcp: connect: remote time in TAP output selftests: mptcp: reset the last TS before the first test selftests: mptcp: diag: remove trailing whitespace selftests: mptcp: connect: remove duplicated spaces in TAP output tools/testing/selftests/net/mptcp/diag.sh | 2 +- tools/testing/selftests/net/mptcp/mptcp_connect.sh | 17 ++++++++++------- tools/testing/selftests/net/mptcp/mptcp_join.sh | 3 ++- tools/testing/selftests/net/mptcp/mptcp_lib.sh | 17 ++++++++++++++++- tools/testing/selftests/net/mptcp/mptcp_sockopt.sh | 1 + tools/testing/selftests/net/mptcp/pm_netlink.sh | 2 ++ tools/testing/selftests/net/mptcp/simult_flows.sh | 1 + tools/testing/selftests/net/mptcp/userspace_pm.sh | 1 + 8 files changed, 34 insertions(+), 10 deletions(-) --- base-commit: 52fc70a32573707f70d6b1b5c5fe85cc91457393 change-id: 20240902-net-next-mptcp-ksft-subtest-time-a83cec43d894 Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

9 months, 3 weeks

2
6
0 0

[PATCH bpf] bpf: Fix error message on kfunc arg type mismatch

by Maxim Mikityanskiy

When "arg#%d expected pointer to ctx, but got %s" error is printed, both template parts actually point to the type of the argument, therefore, it will also say "but got PTR", regardless of what was the actual register type. Fix the message to print the register type in the second part of the template, change the existing test to adapt to the new format, and add a new test to test the case when arg is a pointer to context, but reg is a scalar. Fixes: 00b85860feb8 ("bpf: Rewrite kfunc argument handling") Signed-off-by: Maxim Mikityanskiy <maxim(a)isovalent.com> --- kernel/bpf/verifier.c | 3 ++- tools/testing/selftests/bpf/prog_tests/kfunc_call.c | 1 + tools/testing/selftests/bpf/progs/kfunc_call_fail.c | 7 +++++++ tools/testing/selftests/bpf/verifier/calls.c | 2 +- 4 files changed, 11 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d8520095ca03..8b9f0a2981d4 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -11948,7 +11948,8 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ switch (kf_arg_type) { case KF_ARG_PTR_TO_CTX: if (reg->type != PTR_TO_CTX) { - verbose(env, "arg#%d expected pointer to ctx, but got %s\n", i, btf_type_str(t)); + verbose(env, "arg#%d expected pointer to ctx, but got %s\n", + i, reg_type_str(env, reg->type)); return -EINVAL; } diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c index 5b743212292f..f79c8e53cb3e 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c @@ -68,6 +68,7 @@ static struct kfunc_test_params kfunc_tests[] = { TC_FAIL(kfunc_call_test_get_mem_fail_oob, 0, "min value is outside of the allowed memory range"), TC_FAIL(kfunc_call_test_get_mem_fail_not_const, 0, "is not a const"), TC_FAIL(kfunc_call_test_mem_acquire_fail, 0, "acquire kernel function does not return PTR_TO_BTF_ID"), + TC_FAIL(kfunc_call_test_pointer_arg_type_mismatch, 0, "arg#0 expected pointer to ctx, but got scalar"), /* success cases */ TC_TEST(kfunc_call_test1, 12), diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_fail.c b/tools/testing/selftests/bpf/progs/kfunc_call_fail.c index 4b0b7b79cdfb..08fae306539c 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_fail.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_fail.c @@ -150,4 +150,11 @@ int kfunc_call_test_mem_acquire_fail(struct __sk_buff *skb) return ret; } +SEC("?tc") +int kfunc_call_test_pointer_arg_type_mismatch(struct __sk_buff *skb) +{ + bpf_kfunc_call_test_pass_ctx((void *)10); + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index d0cdd156cd55..7afc2619ab14 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -76,7 +76,7 @@ }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, - .errstr = "arg#0 expected pointer to ctx, but got PTR", + .errstr = "arg#0 expected pointer to ctx, but got fp", .fixup_kfunc_btf_id = { { "bpf_kfunc_call_test_pass_ctx", 2 }, }, -- 2.46.0

9 months, 3 weeks

4
3
0 0

[PATCH v2 0/1] Add KUnit tests for llist

by Artur Alves

Hi all, This is part of a hackathon organized by LKCAMP[1], focused on writing tests using KUnit. We reached out a while ago asking for advice on what would be a useful contribution[2] and ended up choosing data structures that did not yet have tests. This patch adds tests for the llist data structure, defined in include/linux/llist.h, and is inspired by the KUnit tests for the doubly linked list in lib/list-test.c[3]. It is important to note that this patch depends on the patch referenced in [4], as it utilizes the newly created lib/tests/ subdirectory. [1] https://lkcamp.dev/about/ [2] https://lore.kernel.org/all/Zktnt7rjKryTh9-N@arch/ [3] https://elixir.bootlin.com/linux/latest/source/lib/list-test.c [4] https://lore.kernel.org/all/20240720181025.work.002-kees@kernel.org/ --- Changes in v2: - Add MODULE_DESCRIPTION() - Move the tests from lib/llist_kunit.c to lib/tests/llist_kunit.c - Change the license from "GPL v2" to "GPL" Artur Alves (1): lib/llist_kunit.c: add KUnit tests for llist lib/Kconfig.debug | 11 ++ lib/tests/Makefile | 1 + lib/tests/llist_kunit.c | 361 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 373 insertions(+) create mode 100644 lib/tests/llist_kunit.c -- 2.46.0

9 months, 3 weeks

3
3
0 0

[PATCH v4] lib/math: Add int_pow test suite

by Luis Felipe Hernandez

Adds test suite for integer based power function. Signed-off-by: Luis Felipe Hernandez <luis.hernandez093(a)gmail.com> --- Changes in v4: - Address checkpatch warning and make kconfig description longer - Use GPL-2.0-only for consistency - Spelling fix fith -> fifth Changes in v3: - Fix compiler warning: explicitly define constant as unsigned int - Add changes in patch revisions Changes in v2: - Address review feedback - Add kconfig entry - Use correct dir and file convention for KUnit - Fix typo - Remove unused static_stub header - Refactor test suite to use paramerterized test cases - Add close to max allowable value to in large_result test case - Add test case with non-power of two exponent - Fix module license --- lib/Kconfig.debug | 9 ++++++ lib/math/Makefile | 1 + lib/math/tests/Makefile | 3 ++ lib/math/tests/int_pow_kunit.c | 52 ++++++++++++++++++++++++++++++++++ 4 files changed, 65 insertions(+) create mode 100644 lib/math/tests/Makefile create mode 100644 lib/math/tests/int_pow_kunit.c diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index a30c03a66172..0f98f73d4322 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -3051,3 +3051,12 @@ config RUST_KERNEL_DOCTESTS endmenu # "Rust" endmenu # Kernel hacking + +config INT_POW_TEST + tristate "Integer exponentiation (int_pow) test" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS + help + This option enables the KUnit test suite for the int_pow function, + which performs integer exponentiation. The test suite is designed to + verify that the implementation of int_pow correctly computes the power + of a given base raised to a given exponent. + + Enabling this option will include tests that check various scenarios + and edge cases to ensure the accuracy and reliability of the exponentiation + function. + + If unsure, say N diff --git a/lib/math/Makefile b/lib/math/Makefile index 91fcdb0c9efe..3c1f92a7459d 100644 --- a/lib/math/Makefile +++ b/lib/math/Makefile @@ -5,5 +5,6 @@ obj-$(CONFIG_CORDIC) += cordic.o obj-$(CONFIG_PRIME_NUMBERS) += prime_numbers.o obj-$(CONFIG_RATIONAL) += rational.o +obj-$(CONFIG_INT_POW_TEST) += tests/int_pow_kunit.o obj-$(CONFIG_TEST_DIV64) += test_div64.o obj-$(CONFIG_RATIONAL_KUNIT_TEST) += rational-test.o diff --git a/lib/math/tests/Makefile b/lib/math/tests/Makefile new file mode 100644 index 000000000000..6a169123320a --- /dev/null +++ b/lib/math/tests/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only + +obj-$(CONFIG_INT_POW_TEST) += int_pow_kunit.o diff --git a/lib/math/tests/int_pow_kunit.c b/lib/math/tests/int_pow_kunit.c new file mode 100644 index 000000000000..7b6a5ae70eb4 --- /dev/null +++ b/lib/math/tests/int_pow_kunit.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <kunit/test.h> +#include <linux/math.h> + +struct test_case_params { + u64 base; + unsigned int exponent; + u64 expected_result; + const char *name; +}; + +static const struct test_case_params params[] = { + { 64, 0, 1, "Power of zero" }, + { 64, 1, 64, "Power of one"}, + { 0, 5, 0, "Base zero" }, + { 1, 64, 1, "Base one" }, + { 2, 2, 4, "Two squared"}, + { 2, 3, 8, "Two cubed"}, + { 5, 5, 3125, "Five raised to the fifth power" }, + { U64_MAX, 1, U64_MAX, "Max base" }, + { 2, 63, 9223372036854775808, "Large result"}, +}; + +static void get_desc(const struct test_case_params *tc, char *desc) +{ + strscpy(desc, tc->name, KUNIT_PARAM_DESC_SIZE); +} + +KUNIT_ARRAY_PARAM(int_pow, params, get_desc); + +static void int_pow_test(struct kunit *test) +{ + const struct test_case_params *tc = (const struct test_case_params *)test->param_value; + + KUNIT_EXPECT_EQ(test, tc->expected_result, int_pow(tc->base, tc->exponent)); +} + +static struct kunit_case math_int_pow_test_cases[] = { + KUNIT_CASE_PARAM(int_pow_test, int_pow_gen_params), + {} +}; + +static struct kunit_suite int_pow_test_suite = { + .name = "math-int_pow", + .test_cases = math_int_pow_test_cases, +}; + +kunit_test_suites(&int_pow_test_suite); + +MODULE_DESCRIPTION("math.int_pow KUnit test suite"); +MODULE_LICENSE("GPL"); -- 2.46.0

9 months, 3 weeks

2
2
0 0

[PATCH net-next 0/3] lan743x: This series of patches are for lan743x driver testing

by Mohan Prasad J

This series of patches are for testing the lan743x network driver. Testing comprises autonegotiation, speed, duplex and throughput checks. Tools such as ethtool, iperf3 are used in the testing process. Performance test is done for TCP streams at different speeds. Signed-off-by: Mohan Prasad J <mohan.prasad(a)microchip.com> Mohan Prasad J (3): selftests: lan743x: Add testfile for lan743x network driver selftests: lan743x: Add testcase to check speed and duplex state of lan743x selftests: lan743x: Add testcase to check throughput of lan743x MAINTAINERS | 2 + tools/testing/selftests/Makefile | 2 +- .../drivers/net/hw/microchip/lan743x/Makefile | 7 ++ .../net/hw/microchip/lan743x/lan743x.py | 117 ++++++++++++++++++ .../hw/microchip/lan743x/lib/py/__init__.py | 16 +++ 5 files changed, 143 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/drivers/net/hw/microchip/lan743x/Makefile create mode 100755 tools/testing/selftests/drivers/net/hw/microchip/lan743x/lan743x.py create mode 100644 tools/testing/selftests/drivers/net/hw/microchip/lan743x/lib/py/__init__.py -- 2.43.0

9 months, 3 weeks

4
14
0 0

[PATCH 0/6] selftests/resctrl: Support diverse platforms with MBM and MBA tests

by Reinette Chatre

The resctrl selftests for Memory Bandwidth Allocation (MBA) and Memory Bandwidth Monitoring (MBM) are failing on some (for example [1]) Emerald Rapids systems. The test failures result from the following two properties of these systems: 1) Emerald Rapids systems can have up to 320MB L3 cache. The resctrl MBA and MBM selftests measure memory traffic for which a hardcoded 250MB buffer has been sufficient so far. On platforms with L3 cache larger than the buffer, the buffer fits in the L3 cache and thus no/very little memory traffic is generated during the "memory bandwidth" tests. 2) Some platform features, for example RAS features or memory performance features that generate memory traffic may drive accesses that are counted differently by performance counters and MBM respectively, for instance generating "overhead" traffic which is not counted against any specific RMID. Until now these counting differences have always been "in the noise". On Emerald Rapids systems the maximum MBA throttling (10% memory bandwidth) throttles memory bandwidth to where memory accesses by these other platform features push the memory bandwidth difference between memory controller performance counters and resctrl (MBM) beyond the tests' hardcoded tolerance. Make the tests more robust against platform variations: 1) Let the buffer used by memory bandwidth tests be guided by the size of the L3 cache. 2) Larger buffers require longer initialization time before the buffer can be used to measurement. Rework the tests to ensure that buffer initialization is complete before measurements start. 3) Do not compare performance counters and MBM measurements at low bandwidth. The value of "low" is hardcoded to 750MiB based on measurements on Emerald Rapids, Sapphire Rapids, and Ice Lake systems. This limit is not applicable to AMD systems since it only applies to the MBA and MBM tests that are isolated to Intel. [1] https://ark.intel.com/content/www/us/en/ark/products/237261/intel-xeon-plat… Reinette Chatre (6): selftests/resctrl: Fix sparse warnings selftests/resctrl: Ensure measurements skip initialization of default benchmark selftests/resctrl: Simplify benchmark parameter passing selftests/resctrl: Use cache size to determine "fill_buf" buffer size selftests/resctrl: Do not compare performance counters and resctrl at low bandwidth selftests/resctrl: Keep results from first test run tools/testing/selftests/resctrl/cmt_test.c | 33 +-- tools/testing/selftests/resctrl/fill_buf.c | 19 +- tools/testing/selftests/resctrl/mba_test.c | 26 +- tools/testing/selftests/resctrl/mbm_test.c | 25 +- tools/testing/selftests/resctrl/resctrl.h | 57 +++-- .../testing/selftests/resctrl/resctrl_tests.c | 15 +- tools/testing/selftests/resctrl/resctrl_val.c | 223 +++++------------- 7 files changed, 152 insertions(+), 246 deletions(-) -- 2.46.0

9 months, 3 weeks

2
29
0 0

[PATCH v2 00/19] random: Resolve circular include dependency and include <linux/percpu.h>

by Uros Bizjak

There were several attempts to resolve circular include dependency after the addition of percpu.h: 1c9df907da83 ("random: fix circular include dependency on arm64 after addition of percpu.h"), c0842fbc1b18 ("random32: move the pseudo-random 32-bit definitions to prandom.h") and finally d9f29deb7fe8 ("prandom: Remove unused include") that completely removes the inclusion of <linux/percpu.h>. Due to legacy reasons, <linux/random.h> includes <linux/prandom.h>, but with the commit entry remark: --quote-- A further cleanup step would be to remove this from <linux/random.h> entirely, and make people who use the prandom infrastructure include just the new header file. That's a bit of a churn patch, but grepping for "prandom_" and "next_pseudo_random32" "struct rnd_state" should catch most users. But it turns out that that nice cleanup step is fairly painful, because a _lot_ of code currently seems to depend on the implicit include of <linux/random.h>, which can currently come in a lot of ways, including such fairly core headfers as <linux/net.h>. So the "nice cleanup" part may or may never happen. --/quote-- We would like to include <linux/percpu.h> in <linux/prandom.h>. In [1] we would like to repurpose __percpu tag as a named address space qualifier, where __percpu macro uses defines from <linux/percpu.h>. The major roadblock to inclusion of <linux/percpu.h> is the above mentioned legacy inclusion of <linux/prandom.h> in <linux/random.h> that causes circular include dependency that prevents <linux/percpu.h> inclusion. This patch series is the "nice cleanup" part that: a) Substitutes the inclusion of <linux/random.h> with the inclusion of <linux/prandom.h> where needed (patches 1 - 17). b) Removes legacy inclusion of <linux/prandom.h> from <linux/random.h> (patch 18). c) Includes <linux/percpu.h> in <linux/prandom.h> (patch 19). The whole series was tested by compiling the kernel for x86_64 allconfig and some popular architectures, namely arm64 defconfig, powerpc defconfig and loongarch defconfig. [1] https://lore.kernel.org/lkml/20240812115945.484051-4-ubizjak@gmail.com/ Cc: Dave Hansen <dave.hansen(a)linux.intel.com> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Borislav Petkov <bp(a)alien8.de> Cc: x86(a)kernel.org Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: Jani Nikula <jani.nikula(a)linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen(a)linux.intel.com> Cc: Rodrigo Vivi <rodrigo.vivi(a)intel.com> Cc: Tvrtko Ursulin <tursulin(a)ursulin.net> Cc: David Airlie <airlied(a)gmail.com> Cc: Daniel Vetter <daniel(a)ffwll.ch> Cc: Maarten Lankhorst <maarten.lankhorst(a)linux.intel.com> Cc: Maxime Ripard <mripard(a)kernel.org> Cc: Thomas Zimmermann <tzimmermann(a)suse.de> Cc: Hans Verkuil <hverkuil(a)xs4all.nl> Cc: Mauro Carvalho Chehab <mchehab(a)kernel.org> Cc: Miquel Raynal <miquel.raynal(a)bootlin.com> Cc: Richard Weinberger <richard(a)nod.at> Cc: Vignesh Raghavendra <vigneshr(a)ti.com> Cc: Eric Biggers <ebiggers(a)kernel.org> Cc: "Theodore Y. Ts'o" <tytso(a)mit.edu> Cc: Jaegeuk Kim <jaegeuk(a)kernel.org> Cc: "Jason A. Donenfeld" <Jason(a)zx2c4.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Hannes Reinecke <hare(a)suse.de> Cc: "James E.J. Bottomley" <James.Bottomley(a)HansenPartnership.com> Cc: "Martin K. Petersen" <martin.petersen(a)oracle.com> Cc: Alexei Starovoitov <ast(a)kernel.org> Cc: Daniel Borkmann <daniel(a)iogearbox.net> Cc: John Fastabend <john.fastabend(a)gmail.com> Cc: Andrii Nakryiko <andrii(a)kernel.org> Cc: Martin KaFai Lau <martin.lau(a)linux.dev> Cc: Eduard Zingerman <eddyz87(a)gmail.com> Cc: Song Liu <song(a)kernel.org> Cc: Yonghong Song <yonghong.song(a)linux.dev> Cc: KP Singh <kpsingh(a)kernel.org> Cc: Stanislav Fomichev <sdf(a)fomichev.me> Cc: Hao Luo <haoluo(a)google.com> Cc: Jiri Olsa <jolsa(a)kernel.org> Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Brendan Higgins <brendan.higgins(a)linux.dev> Cc: David Gow <davidgow(a)google.com> Cc: Rae Moar <rmoar(a)google.com> Cc: "David S. Miller" <davem(a)davemloft.net> Cc: Eric Dumazet <edumazet(a)google.com> Cc: Jakub Kicinski <kuba(a)kernel.org> Cc: Paolo Abeni <pabeni(a)redhat.com> Cc: Jiri Pirko <jiri(a)resnulli.us> Cc: Petr Mladek <pmladek(a)suse.com> Cc: Steven Rostedt <rostedt(a)goodmis.org> Cc: Andy Shevchenko <andriy.shevchenko(a)linux.intel.com> Cc: Rasmus Villemoes <linux(a)rasmusvillemoes.dk> Cc: Sergey Senozhatsky <senozhatsky(a)chromium.org> Cc: Stephen Hemminger <stephen(a)networkplumber.org> Cc: Jamal Hadi Salim <jhs(a)mojatatu.com> Cc: Cong Wang <xiyou.wangcong(a)gmail.com> Cc: Kent Overstreet <kent.overstreet(a)linux.dev> --- v2: - Reword commit messages to mention the removal of legacy inclusion of <linux/prandom.h> from <linux/random.h> - Add missing substitution in crypto/testmgr.c (reported by kernel test robot) - Add Acked-by:. Uros Bizjak (19): x86/kaslr: Include <linux/prandom.h> instead of <linux/random.h> crypto: testmgr: Include <linux/prandom.h> instead of <linux/random.h> drm/i915/selftests: Include <linux/prandom.h> instead of <linux/random.h> drm/lib: Include <linux/prandom.h> instead of <linux/random.h> media: vivid: Include <linux/prandom.h> in vivid-vid-cap.c mtd: tests: Include <linux/prandom.h> instead of <linux/random.h> fscrypt: Include <linux/once.h> in fs/crypto/keyring.c scsi: libfcoe: Include <linux/prandom.h> instead of <linux/random.h> bpf: Include <linux/prandom.h> instead of <linux/random.h> lib/interval_tree_test.c: Include <linux/prandom.h> instead of <linux/random.h> kunit: string-stream-test: Include <linux/prandom.h> instead of <linux/random.h> random32: Include <linux/prandom.h> instead of <linux/random.h> lib/rbtree-test: Include <linux/prandom.h> instead of <linux/random.h> bpf/tests: Include <linux/prandom.h> instead of <linux/random.h> lib/test_parman: Include <linux/prandom.h> instead of <linux/random.h> lib/test_scanf: Include <linux/prandom.h> instead of <linux/random.h> netem: Include <linux/prandom.h> in sch_netem.c random: Do not include <linux/prandom.h> in <linux/random.h> prandom: Include <linux/percpu.h> in <linux/prandom.h> arch/x86/mm/kaslr.c | 2 +- crypto/testmgr.c | 2 +- drivers/gpu/drm/i915/selftests/i915_gem.c | 2 +- drivers/gpu/drm/i915/selftests/i915_random.h | 2 +- drivers/gpu/drm/i915/selftests/scatterlist.c | 2 +- drivers/gpu/drm/lib/drm_random.h | 2 +- drivers/media/test-drivers/vivid/vivid-vid-cap.c | 1 + drivers/mtd/tests/oobtest.c | 2 +- drivers/mtd/tests/pagetest.c | 2 +- drivers/mtd/tests/subpagetest.c | 2 +- fs/crypto/keyring.c | 1 + include/linux/prandom.h | 1 + include/linux/random.h | 7 ------- include/scsi/libfcoe.h | 2 +- kernel/bpf/core.c | 2 +- lib/interval_tree_test.c | 2 +- lib/kunit/string-stream-test.c | 1 + lib/random32.c | 2 +- lib/rbtree_test.c | 2 +- lib/test_bpf.c | 2 +- lib/test_parman.c | 2 +- lib/test_scanf.c | 2 +- net/sched/sch_netem.c | 1 + 23 files changed, 22 insertions(+), 24 deletions(-) -- 2.46.0

9 months, 3 weeks

1
19
0 0

[PATCH net-next v24 00/13] Device Memory TCP

by Mina Almasry

v24: https://patchwork.kernel.org/project/netdevbpf/list/?series=884556&state=* ==== Changes: - Fix failing ynl regen error. - Error path fixes & extack error messages in dmabuf binding. Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v24/ v23: https://patchwork.kernel.org/project/netdevbpf/list/?series=882978&state=* ==== Fixing relatively minor issues called out in v22. (thanks again!) Mostly code cleanups, extack error messages, and minor reworks. Nothing major really changed, so the exact changes per commit is called in the commit messages. Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v23/ v22: https://patchwork.kernel.org/project/netdevbpf/list/?series=881158&state=* ==== v22 aims to resolve the pending issue pointed to in v21, which is the interaction with xdp. In this series I rebase on top of the minor refactor which refactors propagating xdp configuration to slave devices: https://patchwork.kernel.org/project/netdevbpf/list/?series=881994&state=* I then disable setting xdp on devices using memory providers, and propagating xdp configuration to devices using memory providers. Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v22/ v21: https://patchwork.kernel.org/project/netdevbpf/list/?series=880735&state=* ==== v20 addressed some comments and resolved a test failure, but introduced an unfortunate build error with a config edge case I wasn't testing. v21 simply resolves that error. Major Changes: - Resolve build error with CONFIG_PAGE_POOL=n && CONFIG_NET=y Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v21/ v20: https://patchwork.kernel.org/project/netdevbpf/list/?series=879373&state=* ==== v20 aims to resolve a couple of bug reports against v19, and addresses some review comments around the page_pool_check_memory_provider mechanism. Major changes: - Test edge cases such as header split disabled in selftest. - Change `offset = 0` back to `offset = offset - start` to resolve issue found in RX path by Taehee (thanks!) - Address a few comments around page_pool_check_memory_provider() from Pavel & Jakub. - Removed some unnecessary includes across various patches in the series. - Removed unnecessary EXPORT_SYMBOL(page_pool_mem_providers) (Jakub). - Fix regression caused by incorrect dev_get_max_mp_channel check, along with rename (Jakub). Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v20/ v19: https://patchwork.kernel.org/project/netdevbpf/list/?series=876852&state=* ==== v18 got a thorough review (thanks!), and this iteration addresses the feedback. Major changes: - Prevent deactivating mp bound queues. - Prevent installing xdp on mp bound netdevs, or installing mps on xdp installed netdevs. - Fix corner cases in netlink API vis-a-vis missing attributes. - Iron out the unreadable netmem driver support story. To be honest, the conversation with Jakub & Pavel got a bit confusing for me. I've implemented an approach in this set that makes sense to me, and AFAICT, addresses the requirements. It may be good as-is, or it may be a conversation starter/continuer. To be honest IMO there are many ways to skin this cat and I don't see an extremely strong reason to go for one approach over another. Here is one approach you may like. - Don't reset niov dma_addr on allocation & free. - Add some tests to the selftest that catches some of the issues around missing netlink attributes or deactivating mp-bound queues. Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v19/ v18: https://patchwork.kernel.org/project/netdevbpf/list/?series=874848&state=* ==== v17 got minor feedback: (a) to beef up the description on patch 1 and (b) to remove the leading underscores in the header definition. I applied (a). (b) seems to be against current conventions so I did not apply before further discussion. Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v17/ v17: https://patchwork.kernel.org/project/netdevbpf/list/?series=869900&state=* ==== v16 also got a very thorough review and some testing (thanks again!). Thes version addresses all the concerns reported on v15, in terms of feedback and issues reported. Major changes: - Use ASSERT_RTNL. - Moved around some of the page_pool helpers definitions so I can hide some netmem helpers in private files as Jakub suggested. - Don't make every net_iov hold a ref on the binding as Jakub suggested. - Fix issue reported by Taehee where we access queues after they have been freed. Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v17/ v16: https://patchwork.kernel.org/project/netdevbpf/list/?series=866353&state=* ==== v15 got a thorough review and some testing, and this version addresses almost all the feedback. Some more minor comments where the authors said it could be done later, I left out. Major changes: - Addition of dma-buf introspection to page-pool-get and queue-get. - Fixes to selftests suggested by Taehee. - Fixes to documentation suggested by Donald. - A couple of suggestions and fixes to TCP patches by Eric and David. - Fixes to number assignements suggested by Arnd. - Use rtnl_lock()ing to guard against queue reconfiguration while the page_pool initialization is happening. (Jakub). - Fixes to a few warnings reproduced by Taehee. - Fixes to dma-buf binding suggested by Taehee and Jakub. - Fixes to netlink UAPI suggested by Jakub - Applied a number of Reviewed-bys and Acked-bys (including ones I lost from v13+). Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v16/ One caveat: Taehee reproduced a KASAN warning and reported it here: https://lore.kernel.org/netdev/CAMArcTUdCxOBYGF3vpbq=eBvqZfnc44KBaQTN7H-wqd… I estimate the issue to be minor and easily fixable: https://lore.kernel.org/netdev/CAHS8izNgaqC--GGE2xd85QB=utUnOHmioCsDd1TNxJW… I hope to be able to follow up with a fix to net tree as net-next closes imminently, but if this iteration doesn't make it in, I will repost with a fix squashed after net-next reopens, no problem. v15: https://patchwork.kernel.org/project/netdevbpf/list/?series=865481&state=* ==== No material changes in this version, only a fix to linking against libynl.a from the last version. Per Jakub's instructions I've pulled one of his patches into this series, and now use the new libynl.a correctly, I hope. As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v15/ v14: https://patchwork.kernel.org/project/netdevbpf/list/?series=865135&archive=… ==== No material changes in this version. Only rebase and re-verification on top of net-next. v13, I think, raced with commit ebad6d0334793 ("net/ipv4: Use nested-BH locking for ipv4_tcp_sk.") being merged to net-next that caused a patchwork failure to apply. This series should apply cleanly on commit c4532232fa2a4 ("selftests: net: remove unneeded IP_GRE config"). I did not wait the customary 24hr as Jakub said it's OK to repost as soon as I build test the rebased version: https://lore.kernel.org/netdev/20240625075926.146d769d@kernel.org/ v13: https://patchwork.kernel.org/project/netdevbpf/list/?series=861406&archive=… ==== Major changes: -------------- This iteration addresses Pavel's review comments, applies his reviewed-by's, and seeks to fix the patchwork build error (sorry!). As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v13/ v12: https://patchwork.kernel.org/project/netdevbpf/list/?series=859747&state=* ==== Major changes: -------------- This iteration only addresses one minor comment from Pavel with regards to the trace printing of netmem, and the patchwork build error introduced in v11 because I missed doing an allmodconfig build, sorry. Other than that v11, AFAICT, received no feedback. There is one discussion about how the specifics of plugging io uring memory through the page pool, but not relevant to content in this particular patchset, AFAICT. As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v12/ v11: https://patchwork.kernel.org/project/netdevbpf/list/?series=857457&state=* ==== Major Changes: -------------- v11 addresses feedback received in v10. The major change is the removal of the memory provider ops as requested by Christoph. We still accomplish the same thing, but utilizing direct function calls with if statements rather than generic ops. Additionally address sparse warnings, bugs and review comments from folks that reviewed. As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v11/ Detailed changelog: ------------------- - Fixes in netdev_rx_queue_restart() from Pavel & David. - Remove commit e650e8c3a36f5 ("net: page_pool: create hooks for custom page providers") from the series to address Christoph's feedback and rebased other patches on the series on this change. - Fixed build errors with CONFIG_DMA_SHARED_BUFFER && !CONFIG_GENERIC_ALLOCATOR build. - Fixed sparse warnings pointed out by Paolo. - Drop unnecessary gro_pull_from_frag0 checks. - Added Bagas reviewed-by to docs. v10: https://patchwork.kernel.org/project/netdevbpf/list/?series=852422&state=* ==== Major Changes: -------------- v9 was sent right before the merge window closed (sorry!). v10 is almost a re-send of the series now that the merge window re-opened. Only rebased to latest net-next and addressed some minor iterative comments received on v9. As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v10/ Detailed changelog: ------------------- - Fixed tokens leaking in DONTNEED setsockopt (Nikolay). - Moved net_iov_dma_addr() to devmem.c and made it a devmem specific helpers (David). - Rename hook alloc_pages to alloc_netmems as alloc_pages is now preprocessor macro defined and causes a build error. v9: === Major Changes: -------------- GVE queue API has been merged. Submitting this version as non-RFC after rebasing on top of the merged API, and dropped the out of tree queue API I was carrying on github. Addressed the little feedback v8 has received. Detailed changelog: ------------------ - Added new patch from David Wei to this series for netdev_rx_queue_restart() - Fixed sparse error. - Removed CONFIG_ checks in netmem_is_net_iov() - Flipped skb->readable to skb->unreadable - Minor fixes to selftests & docs. RFC v8: ======= Major Changes: -------------- - Fixed build error generated by patch-by-patch build. - Applied docs suggestions from Randy. RFC v7: ======= Major Changes: -------------- This revision largely rebases on top of net-next and addresses the feedback RFCv6 received from folks, namely Jakub, Yunsheng, Arnd, David, & Pavel. The series remains in RFC because the queue-API ndos defined in this series are not yet implemented. I have a GVE implementation I carry out of tree for my testing. A upstreamable GVE implementation is in the works. Aside from that, in my estimation all the patches are ready for review/merge. Please do take a look. As usual the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v7/ Detailed changelog: - Use admin-perm in netlink API. - Addressed feedback from Jakub with regards to netlink API implementation. - Renamed devmem.c functions to something more appropriate for that file. - Improve the performance seen through the page_pool benchmark. - Fix the value definition of all the SO_DEVMEM_* uapi. - Various fixes to documentation. Perf - page-pool benchmark: --------------------------- Improved performance of bench_page_pool_simple.ko tests compared to v6: https://pastebin.com/raw/v5dYRg8L net-next base: 8 cycle fast path. RFC v6: 10 cycle fast path. RFC v7: 9 cycle fast path. RFC v7 with CONFIG_DMA_SHARED_BUFFER disabled: 8 cycle fast path, same as baseline. Perf - Devmem TCP benchmark: --------------------- Perf is about the same regardless of the changes in v7, namely the removal of the static_branch_unlikely to improve the page_pool benchmark performance: 189/200gbps bi-directional throughput with RX devmem TCP and regular TCP TX i.e. ~95% line rate. RFC v6: ======= Major Changes: -------------- This revision largely rebases on top of net-next and addresses the little feedback RFCv5 received. The series remains in RFC because the queue-API ndos defined in this series are not yet implemented. I have a GVE implementation I carry out of tree for my testing. A upstreamable GVE implementation is in the works. Aside from that, in my estimation all the patches are ready for review/merge. Please do take a look. As usual the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v6/ This version also comes with some performance data recorded in the cover letter (see below changelog). Detailed changelog: - Rebased on top of the merged netmem_ref changes. - Converted skb->dmabuf to skb->readable (Pavel). Pavel's original suggestion was to remove the skb->dmabuf flag entirely, but when I looked into it closely, I found the issue that if we remove the flag we have to dereference the shinfo(skb) pointer to obtain the first frag to tell whether an skb is readable or not. This can cause a performance regression if it dirties the cache line when the shinfo(skb) was not really needed. Instead, I converted the skb->dmabuf flag into a generic skb->readable flag which can be re-used by io_uring 0-copy RX. - Squashed a few locking optimizations from Eric Dumazet in the RX path and the DEVMEM_DONTNEED setsockopt. - Expanded the tests a bit. Added validation for invalid scenarios and added some more coverage. Perf - page-pool benchmark: --------------------------- bench_page_pool_simple.ko tests with and without these changes: https://pastebin.com/raw/ncHDwAbn AFAIK the number that really matters in the perf tests is the 'tasklet_page_pool01_fast_path Per elem'. This one measures at about 8 cycles without the changes but there is some 1 cycle noise in some results. With the patches this regresses to 9 cycles with the changes but there is 1 cycle noise occasionally running this test repeatedly. Lastly I tried disable the static_branch_unlikely() in netmem_is_net_iov() check. To my surprise disabling the static_branch_unlikely() check reduces the fast path back to 8 cycles, but the 1 cycle noise remains. Perf - Devmem TCP benchmark: --------------------- 189/200gbps bi-directional throughput with RX devmem TCP and regular TCP TX i.e. ~95% line rate. Major changes in RFC v5: ======================== 1. Rebased on top of 'Abstract page from net stack' series and used the new netmem type to refer to LSB set pointers instead of re-using struct page. 2. Downgraded this series back to RFC and called it RFC v5. This is because this series is now dependent on 'Abstract page from net stack'[1] and the queue API. Both are removed from the series to reduce the patch # and those bits are fairly independent or pre-requisite work. 3. Reworked the page_pool devmem support to use netmem and for some more unified handling. 4. Reworked the reference counting of net_iov (renamed from page_pool_iov) to use pp_ref_count for refcounting. The full changes including the dependent series and GVE page pool support is here: https://github.com/mina/linux/commits/tcpdevmem-rfcv5/ [1] https://patchwork.kernel.org/project/netdevbpf/list/?series=810774 Major changes in v1: ==================== 1. Implemented MVP queue API ndos to remove the userspace-visible driver reset. 2. Fixed issues in the napi_pp_put_page() devmem frag unref path. 3. Removed RFC tag. Many smaller addressed comments across all the patches (patches have individual change log). Full tree including the rest of the GVE driver changes: https://github.com/mina/linux/commits/tcpdevmem-v1 Changes in RFC v3: ================== 1. Pulled in the memory-provider dependency from Jakub's RFC[1] to make the series reviewable and mergeable. 2. Implemented multi-rx-queue binding which was a todo in v2. 3. Fix to cmsg handling. The sticking point in RFC v2[2] was the device reset required to refill the device rx-queues after the dmabuf bind/unbind. The solution suggested as I understand is a subset of the per-queue management ops Jakub suggested or similar: https://lore.kernel.org/netdev/20230815171638.4c057dcd@kernel.org/ This is not addressed in this revision, because: 1. This point was discussed at netconf & netdev and there is openness to using the current approach of requiring a device reset. 2. Implementing individual queue resetting seems to be difficult for my test bed with GVE. My prototype to test this ran into issues with the rx-queues not coming back up properly if reset individually. At the moment I'm unsure if it's a mistake in the POC or a genuine issue in the virtualization stack behind GVE, which currently doesn't test individual rx-queue restart. 3. Our usecases are not bothered by requiring a device reset to refill the buffer queues, and we'd like to support NICs that run into this limitation with resetting individual queues. My thought is that drivers that have trouble with per-queue configs can use the support in this series, while drivers that support new netdev ops to reset individual queues can automatically reset the queue as part of the dma-buf bind/unbind. The same approach with device resets is presented again for consideration with other sticking points addressed. This proposal includes the rx devmem path only proposed for merge. For a snapshot of my entire tree which includes the GVE POC page pool support & device memory support: https://github.com/torvalds/linux/compare/master...mina:linux:tcpdevmem-v3 [1] https://lore.kernel.org/netdev/f8270765-a27b-6ccf-33ea-cda097168d79@redhat.… [2] https://lore.kernel.org/netdev/CAHS8izOVJGJH5WF68OsRWFKJid1_huzzUK+hpKbLcL4… Changes in RFC v2: ================== The sticking point in RFC v1[1] was the dma-buf pages approach we used to deliver the device memory to the TCP stack. RFC v2 is a proof-of-concept that attempts to resolve this by implementing scatterlist support in the networking stack, such that we can import the dma-buf scatterlist directly. This is the approach proposed at a high level here[2]. Detailed changes: 1. Replaced dma-buf pages approach with importing scatterlist into the page pool. 2. Replace the dma-buf pages centric API with a netlink API. 3. Removed the TX path implementation - there is no issue with implementing the TX path with scatterlist approach, but leaving out the TX path makes it easier to review. 4. Functionality is tested with this proposal, but I have not conducted perf testing yet. I'm not sure there are regressions, but I removed perf claims from the cover letter until they can be re-confirmed. 5. Added Signed-off-by: contributors to the implementation. 6. Fixed some bugs with the RX path since RFC v1. Any feedback welcome, but specifically the biggest pending questions needing feedback IMO are: 1. Feedback on the scatterlist-based approach in general. 2. Netlink API (Patch 1 & 2). 3. Approach to handle all the drivers that expect to receive pages from the page pool (Patch 6). [1] https://lore.kernel.org/netdev/dfe4bae7-13a0-3c5d-d671-f61b375cb0b4@gmail.c… [2] https://lore.kernel.org/netdev/CAHS8izPm6XRS54LdCDZVd0C75tA1zHSu6jLVO8nzTLX… ================== * TL;DR: Device memory TCP (devmem TCP) is a proposal for transferring data to and/or from device memory efficiently, without bouncing the data to a host memory buffer. * Problem: A large amount of data transfers have device memory as the source and/or destination. Accelerators drastically increased the volume of such transfers. Some examples include: - ML accelerators transferring large amounts of training data from storage into GPU/TPU memory. In some cases ML training setup time can be as long as 50% of TPU compute time, improving data transfer throughput & efficiency can help improving GPU/TPU utilization. - Distributed training, where ML accelerators, such as GPUs on different hosts, exchange data among them. - Distributed raw block storage applications transfer large amounts of data with remote SSDs, much of this data does not require host processing. Today, the majority of the Device-to-Device data transfers 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 implementation is suboptimal, especially for bulk data transfers, and can put significant strains on system resources, such as host memory bandwidth, PCIe bandwidth, etc. One important reason behind the current state is the kernel’s lack of semantics to express device to network transfers. * Proposal: In this patch series we attempt to optimize this use case by implementing socket APIs that enable the user to: 1. send device memory across the network directly, and 2. receive incoming network packets directly into device memory. Packet _payloads_ go directly from the NIC to device memory for receive and from device memory to NIC for transmit. Packet _headers_ go to/from 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 BW pressure, by limiting data transfer to the lowest level of the PCIe tree, compared to traditional path which sends data through the root complex. * Patch overview: ** Part 1: netlink API Gives user ability to bind dma-buf to an RX queue. ** Part 2: scatterlist support Currently the standard for device memory sharing is DMABUF, which doesn't generate struct pages. On the other hand, networking stack (skbs, drivers, and page pool) operate on pages. We have 2 options: 1. Generate struct pages for dmabuf device memory, or, 2. Modify the networking stack to process scatterlist. Approach #1 was attempted in RFC v1. RFC v2 implements approach #2. ** part 3: page pool support We piggy back on page pool memory providers proposal: https://github.com/kuba-moo/linux/tree/pp-providers It allows the page pool to define a memory provider that provides the page allocation and freeing. It helps abstract most of the device memory TCP changes from the driver. ** part 4: support for unreadable skb frags Page pool iovs are not accessible by the host; we implement changes throughput the networking stack to correctly handle skbs with unreadable frags. ** Part 5: recvmsg() APIs We define user APIs for the user to send and receive device memory. Not included with this series is the GVE devmem TCP support, just to simplify the review. Code available here if desired: https://github.com/mina/linux/tree/tcpdevmem This series is built on top of net-next with Jakub's pp-providers changes cherry-picked. * NIC dependencies: 1. (strict) Devmem TCP require the NIC to support header split, i.e. the capability to split incoming packets into a header + payload and to put each into a separate buffer. Devmem TCP works by using device memory for the packet payload, and host memory for the packet headers. 2. (optional) Devmem TCP works better with flow steering support & RSS support, i.e. the NIC's ability to steer flows into certain rx queues. This allows the sysadmin to enable devmem TCP on a subset of the rx queues, and steer devmem TCP traffic onto these queues and non devmem TCP elsewhere. The NIC I have access to with these properties is the GVE with DQO support running in Google Cloud, but any NIC that supports these features would suffice. I may be able to help reviewers bring up devmem TCP on their NICs. * Testing: The series includes a udmabuf kselftest that show a simple use case of devmem TCP and validates the entire data path end to end without a dependency on a specific dmabuf provider. ** Test Setup Kernel: net-next with this series and memory provider API cherry-picked locally. Hardware: Google Cloud A3 VMs. NIC: GVE with header split & RSS & flow steering support. Cc: Pavel Begunkov <asml.silence(a)gmail.com> Cc: David Wei <dw(a)davidwei.uk> Cc: Jason Gunthorpe <jgg(a)ziepe.ca> Cc: Yunsheng Lin <linyunsheng(a)huawei.com> Cc: Shailend Chand <shailend(a)google.com> Cc: Harshitha Ramamurthy <hramamurthy(a)google.com> Cc: Shakeel Butt <shakeel.butt(a)linux.dev> Cc: Jeroen de Borst <jeroendb(a)google.com> Cc: Praveen Kaligineedi <pkaligineedi(a)google.com> Cc: Bagas Sanjaya <bagasdotme(a)gmail.com> Cc: Steven Rostedt <rostedt(a)goodmis.org> Cc: Christoph Hellwig <hch(a)infradead.org> Cc: Nikolay Aleksandrov <razor(a)blackwall.org> Cc: Taehee Yoo <ap420073(a)gmail.com> Cc: Donald Hunter <donald.hunter(a)gmail.com> Mina Almasry (13): netdev: add netdev_rx_queue_restart() net: netdev netlink api to bind dma-buf to a net device netdev: support binding dma-buf to netdevice netdev: netdevice devmem allocator page_pool: devmem support memory-provider: dmabuf devmem memory provider net: support non paged skb frags net: add support for skbs with unreadable frags tcp: RX path for devmem TCP net: add SO_DEVMEM_DONTNEED setsockopt to release RX frags net: add devmem TCP documentation selftests: add ncdevmem, netcat for devmem TCP netdev: add dmabuf introspection Documentation/netlink/specs/netdev.yaml | 61 +++ Documentation/networking/devmem.rst | 269 +++++++++++ Documentation/networking/index.rst | 1 + arch/alpha/include/uapi/asm/socket.h | 6 + arch/mips/include/uapi/asm/socket.h | 6 + arch/parisc/include/uapi/asm/socket.h | 6 + arch/sparc/include/uapi/asm/socket.h | 6 + include/linux/netdevice.h | 2 + include/linux/skbuff.h | 61 ++- include/linux/skbuff_ref.h | 9 +- include/linux/socket.h | 1 + include/net/devmem.h | 136 ++++++ include/net/mp_dmabuf_devmem.h | 44 ++ include/net/netdev_rx_queue.h | 5 + include/net/netmem.h | 163 ++++++- include/net/page_pool/helpers.h | 39 +- include/net/page_pool/types.h | 22 +- include/net/sock.h | 2 + include/net/tcp.h | 5 +- include/trace/events/page_pool.h | 12 +- include/uapi/asm-generic/socket.h | 6 + include/uapi/linux/netdev.h | 13 + include/uapi/linux/uio.h | 17 + net/Kconfig | 5 + net/core/Makefile | 2 + net/core/datagram.c | 6 + net/core/dev.c | 28 +- net/core/devmem.c | 388 ++++++++++++++++ net/core/gro.c | 3 +- net/core/netdev-genl-gen.c | 23 + net/core/netdev-genl-gen.h | 6 + net/core/netdev-genl.c | 137 +++++- net/core/netdev_rx_queue.c | 81 ++++ net/core/netmem_priv.h | 31 ++ net/core/page_pool.c | 117 +++-- net/core/page_pool_priv.h | 46 ++ net/core/page_pool_user.c | 31 +- net/core/skbuff.c | 77 +++- net/core/sock.c | 68 +++ net/ethtool/common.c | 8 + net/ipv4/esp4.c | 3 +- net/ipv4/tcp.c | 261 ++++++++++- net/ipv4/tcp_input.c | 13 +- net/ipv4/tcp_ipv4.c | 16 + net/ipv4/tcp_minisocks.c | 2 + net/ipv4/tcp_output.c | 5 +- net/ipv6/esp6.c | 3 +- net/packet/af_packet.c | 4 +- net/xdp/xsk_buff_pool.c | 5 + tools/include/uapi/linux/netdev.h | 13 + tools/net/ynl/lib/.gitignore | 1 + tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 9 + tools/testing/selftests/net/ncdevmem.c | 570 ++++++++++++++++++++++++ 54 files changed, 2731 insertions(+), 124 deletions(-) create mode 100644 Documentation/networking/devmem.rst create mode 100644 include/net/devmem.h create mode 100644 include/net/mp_dmabuf_devmem.h create mode 100644 net/core/devmem.c create mode 100644 net/core/netdev_rx_queue.c create mode 100644 net/core/netmem_priv.h create mode 100644 tools/testing/selftests/net/ncdevmem.c -- 2.46.0.469.g59c65b2a67-goog

9 months, 3 weeks

3
21
0 0

[PATCH net-next v5 0/2] net-timestamp: introduce a flag to filter out rx software and hardware report

by Jason Xing

From: Jason Xing <kernelxing(a)tencent.com> When one socket is set SOF_TIMESTAMPING_RX_SOFTWARE which means the whole system turns on the netstamp_needed_key button, other sockets that only have SOF_TIMESTAMPING_SOFTWARE will be affected and then print the rx timestamp information even without setting SOF_TIMESTAMPING_RX_SOFTWARE generation flag. How to solve it without breaking users? We introduce a new flag named SOF_TIMESTAMPING_OPT_RX_FILTER. Using it together with SOF_TIMESTAMPING_SOFTWARE can stop reporting the rx software timestamp. Similarly, we also filter out the hardware case where one process enables the rx hardware generation flag, then another process only passing SOF_TIMESTAMPING_RAW_HARDWARE gets the timestamp. So we can set both SOF_TIMESTAMPING_RAW_HARDWARE and SOF_TIMESTAMPING_OPT_RX_FILTER to stop reporting rx hardware timestamp after this patch applied. v5 Link: https://lore.kernel.org/all/20240905071738.3725-1-kerneljasonxing@gmail.com/ 1. squash the hardware case patch into this one (Willem) 2. update corresponding commit message and doc (Willem) 3. remove the limitation in sock_set_timestamping() and restore the simplification branches. (Willem) 4. add missing type and another test in selftests v4 Link: https://lore.kernel.org/all/20240830153751.86895-1-kerneljasonxing@gmail.co… 1. revise the doc and commit message (Willem) 2. add patch [2/4] to make the doc right (Willem) 3. add patch [3/4] to cover the hardware use (Willem) 4. add testcase for hardware use. Note: the reason why I split into 4 patches is try to make each commit clean, atomic, easy to review. v3 Link: https://lore.kernel.org/all/20240828160145.68805-1-kerneljasonxing@gmail.co… 1. introduce a new flag to avoid application breakage, suggested by Willem. 2. add it into the selftests. v2 Link: https://lore.kernel.org/all/20240825152440.93054-1-kerneljasonxing@gmail.co… Discussed with Willem 1. update the documentation accordingly 2. add more comments in each patch 3. remove the previous test statements in __sock_recv_timestamp() Jason Xing (2): net-timestamp: introduce SOF_TIMESTAMPING_OPT_RX_FILTER flag net-timestamp: add selftests for SOF_TIMESTAMPING_OPT_RX_FILTER Documentation/networking/timestamping.rst | 27 +++++++++++++++++++++++ include/uapi/linux/net_tstamp.h | 3 ++- net/ethtool/common.c | 1 + net/ipv4/tcp.c | 9 ++++++-- net/socket.c | 10 +++++++-- tools/testing/selftests/net/rxtimestamp.c | 18 +++++++++++++++ 6 files changed, 63 insertions(+), 5 deletions(-) -- 2.37.3

9 months, 3 weeks

2
9
0 0

[crng-random:jd/arm64-vdso] [selftests] f68b079b1d: kernel-selftests.vDSO.vdso_standalone_test_x86.fail

by kernel test robot

Hello, kernel test robot noticed "kernel-selftests.vDSO.vdso_standalone_test_x86.fail" on: commit: f68b079b1d5ec46687a097347303b616927eb9ff ("selftests: vDSO: build tests with O2 optimization") https://git.kernel.org/cgit/linux/kernel/git/crng/random.git jd/arm64-vdso in testcase: kernel-selftests version: kernel-selftests-x86_64-977d51cf-1_20240508 with following parameters: group: group-03 compiler: gcc-12 test machine: 36 threads 1 sockets Intel(R) Core(TM) i9-10980XE CPU @ 3.00GHz (Cascade Lake) with 32G memory (please refer to attached dmesg/kmsg for entire log/backtrace) If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <oliver.sang(a)intel.com> | Closes: https://lore.kernel.org/oe-lkp/202409082121.553d4c89-oliver.sang@intel.com # timeout set to 300 # selftests: vDSO: vdso_standalone_test_x86 # Segmentation fault not ok 5 selftests: vDSO: vdso_standalone_test_x86 # exit=139 The kernel config and materials to reproduce are available at: https://download.01.org/0day-ci/archive/20240908/202409082121.553d4c89-oliv… -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

9 months, 3 weeks

1
0
0 0

[PATCH v2] selftests/futex: Create test for robust list

by André Almeida

Create a test for the robust list mechanism. Signed-off-by: André Almeida <andrealmeid(a)igalia.com> --- Changes from v1: - Change futex type from int to _Atomic(unsigned int) - Use old futex(FUTEX_WAIT) instead of the new sys_futex_wait() --- .../selftests/futex/functional/.gitignore | 1 + .../selftests/futex/functional/Makefile | 3 +- .../selftests/futex/functional/robust_list.c | 448 ++++++++++++++++++ 3 files changed, 451 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/futex/functional/robust_list.c diff --git a/tools/testing/selftests/futex/functional/.gitignore b/tools/testing/selftests/futex/functional/.gitignore index fbcbdb6963b3..4726e1be7497 100644 --- a/tools/testing/selftests/futex/functional/.gitignore +++ b/tools/testing/selftests/futex/functional/.gitignore @@ -9,3 +9,4 @@ futex_wait_wouldblock futex_wait futex_requeue futex_waitv +robust_list diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile index f79f9bac7918..b8635a1ac7f6 100644 --- a/tools/testing/selftests/futex/functional/Makefile +++ b/tools/testing/selftests/futex/functional/Makefile @@ -17,7 +17,8 @@ TEST_GEN_PROGS := \ futex_wait_private_mapped_file \ futex_wait \ futex_requeue \ - futex_waitv + futex_waitv \ + robust_list TEST_PROGS := run.sh diff --git a/tools/testing/selftests/futex/functional/robust_list.c b/tools/testing/selftests/futex/functional/robust_list.c new file mode 100644 index 000000000000..9308eb189d48 --- /dev/null +++ b/tools/testing/selftests/futex/functional/robust_list.c @@ -0,0 +1,448 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2024 Igalia S.L. + * + * Robust list test by André Almeida <andrealmeid(a)igalia.com> + * + * The robust list uAPI allows userspace to create "robust" locks, in the sense + * that if the lock holder thread dies, the remaining threads that are waiting + * for the lock won't block forever, waiting for a lock that will never be + * released. + * + * This is achieve by userspace setting a list where a thread can enter all the + * locks (futexes) that it is holding. The robust list is a linked list, and + * userspace register the start of the list with the syscall set_robust_list(). + * If such thread eventually dies, the kernel will walk this list, waking up one + * thread waiting for each futex and marking the futex word with the flag + * FUTEX_OWNER_DIED. + * + * See also + * man set_robust_list + * Documententation/locking/robust-futex-ABI.rst + * Documententation/locking/robust-futexes.rst + */ + +#define _GNU_SOURCE + +#include "../../kselftest_harness.h" + +#include "futextest.h" + +#include <pthread.h> +#include <stdatomic.h> +#include <stddef.h> + +#define STACK_SIZE (1024 * 1024) + +#define FUTEX_TIMEOUT 3 + +static pthread_barrier_t barrier, barrier2; + +int set_robust_list(struct robust_list_head *head, size_t len) +{ + return syscall(SYS_set_robust_list, head, len); +} + +int get_robust_list(int pid, struct robust_list_head **head, size_t *len_ptr) +{ + return syscall(SYS_get_robust_list, pid, head, len_ptr); +} + +/* + * Basic lock struct, contains just the futex word and the robust list element + * Real implementations have also a *prev to easily walk in the list + */ +struct lock_struct { + _Atomic(unsigned int) futex; + struct robust_list list; +}; + +/* + * Helper function to spawn a child thread. Returns -1 on error, pid on success + */ +static int create_child(int (*fn)(void *arg), void *arg) +{ + char *stack; + pid_t pid; + + stack = mmap(NULL, STACK_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0); + if (stack == MAP_FAILED) + return -1; + + stack += STACK_SIZE; + + pid = clone(fn, stack, CLONE_VM | SIGCHLD, arg); + + if (pid == -1) + return -1; + + return pid; +} + +/* + * Helper function to prepare and register a robust list + */ +static int set_list(struct robust_list_head *head) +{ + int ret; + + ret = set_robust_list(head, sizeof(struct robust_list_head)); + if (ret) + return ret; + + head->futex_offset = (size_t) offsetof(struct lock_struct, futex) - + (size_t) offsetof(struct lock_struct, list); + head->list.next = &head->list; + head->list_op_pending = NULL; + + return 0; +} + +/* + * A basic (and incomplete) mutex lock function with robustness + */ +static int mutex_lock(struct lock_struct *lock, struct robust_list_head *head, bool error_inject) +{ + _Atomic(unsigned int) *futex = &lock->futex; + int zero = 0, ret = -1; + pid_t tid = gettid(); + + /* + * Set list_op_pending before starting the lock, so the kernel can catch + * the case where the thread died during the lock operation + */ + head->list_op_pending = &lock->list; + + if (atomic_compare_exchange_strong(futex, &zero, tid)) { + /* + * We took the lock, insert it in the robust list + */ + struct robust_list *list = &head->list; + + /* Error injection to test list_op_pending */ + if (error_inject) + return 0; + + while (list->next != &head->list) + list = list->next; + + list->next = &lock->list; + lock->list.next = &head->list; + + ret = 0; + } else { + /* + * We didn't take the lock, wait until the owner wakes (or dies) + */ + struct timespec to; + + clock_gettime(CLOCK_MONOTONIC, &to); + to.tv_sec = to.tv_sec + FUTEX_TIMEOUT; + + tid = atomic_load(futex); + /* Kernel ignores futexes without the waiters flag */ + tid |= FUTEX_WAITERS; + atomic_store(futex, tid); + + ret = futex_wait((futex_t *) futex, tid, &to, 0); + + /* + * A real mutex_lock() implementation would loop here to finally + * take the lock. We don't care about that, so we stop here. + */ + } + + head->list_op_pending = NULL; + + return ret; +} + +/* + * This child thread will succeed taking the lock, and then will exit holding it + */ +static int child_fn_lock(void *arg) +{ + struct lock_struct *lock = (struct lock_struct *) arg; + struct robust_list_head head; + int ret; + + ret = set_list(&head); + if (ret) + ksft_test_result_fail("set_robust_list error\n"); + + ret = mutex_lock(lock, &head, false); + if (ret) + ksft_test_result_fail("mutex_lock error\n"); + + pthread_barrier_wait(&barrier); + + /* + * There's a race here: the parent thread needs to be inside + * futex_wait() before the child thread dies, otherwise it will miss the + * wakeup from handle_futex_death() that this child will emit. We wait a + * little bit just to make sure that this happens. + */ + sleep(1); + + return 0; +} + +/* + * Spawns a child thread that will set a robust list, take the lock, register it + * in the robust list and die. The parent thread will wait on this futex, and + * should be waken up when the child exits. + */ +TEST(robustness) +{ + struct lock_struct lock = { .futex = 0 }; + struct robust_list_head head; + _Atomic(unsigned int) *futex = &lock.futex; + int ret; + + ret = set_list(&head); + ASSERT_EQ(ret, 0); + + /* + * Lets use a barrier to ensure that the child thread takes the lock + * before the parent + */ + ret = pthread_barrier_init(&barrier, NULL, 2); + ASSERT_EQ(ret, 0); + + ret = create_child(&child_fn_lock, &lock); + ASSERT_NE(ret, -1); + + pthread_barrier_wait(&barrier); + ret = mutex_lock(&lock, &head, false); + + /* + * futex_wait() should return 0 and the futex word should be marked with + * FUTEX_OWNER_DIED + */ + ASSERT_EQ(ret, 0) TH_LOG("futex wait returned %d", errno); + ASSERT_TRUE(*futex | FUTEX_OWNER_DIED); + + pthread_barrier_destroy(&barrier); +} + +/* + * The only valid value for len is sizeof(*head) + */ +TEST(set_robust_list_invalid_size) +{ + struct robust_list_head head; + size_t head_size = sizeof(struct robust_list_head); + int ret; + + ret = set_robust_list(&head, head_size); + ASSERT_EQ(ret, 0); + + ret = set_robust_list(&head, head_size * 2); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EINVAL); + + ret = set_robust_list(&head, head_size - 1); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EINVAL); + + ret = set_robust_list(&head, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EINVAL); +} + +/* + * Test get_robust_list with pid = 0, getting the list of the running thread + */ +TEST(get_robust_list_self) +{ + struct robust_list_head head, head2, *get_head; + size_t head_size = sizeof(struct robust_list_head), len_ptr; + int ret; + + ret = set_robust_list(&head, head_size); + ASSERT_EQ(ret, 0); + + ret = get_robust_list(0, &get_head, &len_ptr); + ASSERT_EQ(ret, 0); + ASSERT_EQ(get_head, &head); + ASSERT_EQ(head_size, len_ptr); + + ret = set_robust_list(&head2, head_size); + ASSERT_EQ(ret, 0); + + ret = get_robust_list(0, &get_head, &len_ptr); + ASSERT_EQ(ret, 0); + ASSERT_EQ(get_head, &head2); + ASSERT_EQ(head_size, len_ptr); +} + +static int child_list(void *arg) +{ + struct robust_list_head *head = (struct robust_list_head *) arg; + int ret; + + ret = set_robust_list(head, sizeof(struct robust_list_head)); + if (ret) + ksft_test_result_fail("set_robust_list error\n"); + + pthread_barrier_wait(&barrier); + pthread_barrier_wait(&barrier2); + + return 0; +} + +/* + * Test get_robust_list from another thread. We use two barriers here to ensure + * that: + * 1) the child thread set the list before we try to get it from the + * parent + * 2) the child thread still alive when we try to get the list from it + */ +TEST(get_robust_list_child) +{ + pid_t tid; + int ret; + struct robust_list_head head, *get_head; + size_t len_ptr; + + ret = pthread_barrier_init(&barrier, NULL, 2); + ret = pthread_barrier_init(&barrier2, NULL, 2); + ASSERT_EQ(ret, 0); + + tid = create_child(&child_list, &head); + ASSERT_NE(tid, -1); + + pthread_barrier_wait(&barrier); + + ret = get_robust_list(tid, &get_head, &len_ptr); + ASSERT_EQ(ret, 0); + ASSERT_EQ(&head, get_head); + + pthread_barrier_wait(&barrier2); + + pthread_barrier_destroy(&barrier); + pthread_barrier_destroy(&barrier2); +} + +static int child_fn_lock_with_error(void *arg) +{ + struct lock_struct *lock = (struct lock_struct *) arg; + struct robust_list_head head; + int ret; + + ret = set_list(&head); + if (ret) + ksft_test_result_fail("set_robust_list error\n"); + + ret = mutex_lock(lock, &head, true); + if (ret) + ksft_test_result_fail("mutex_lock error\n"); + + pthread_barrier_wait(&barrier); + + sleep(1); + + return 0; +} + +/* + * Same as robustness test, but inject an error where the mutex_lock() exits + * earlier, just after setting list_op_pending and taking the lock, to test the + * list_op_pending mechanism + */ +TEST(set_list_op_pending) +{ + struct lock_struct lock = { .futex = 0 }; + struct robust_list_head head; + _Atomic(unsigned int) *futex = &lock.futex; + int ret; + + ret = set_list(&head); + ASSERT_EQ(ret, 0); + + ret = pthread_barrier_init(&barrier, NULL, 2); + ASSERT_EQ(ret, 0); + + ret = create_child(&child_fn_lock_with_error, &lock); + ASSERT_NE(ret, -1); + + pthread_barrier_wait(&barrier); + ret = mutex_lock(&lock, &head, false); + + ASSERT_EQ(ret, 0) TH_LOG("futex wait returned %d", errno); + ASSERT_TRUE(*futex | FUTEX_OWNER_DIED); + + pthread_barrier_destroy(&barrier); +} + +#define CHILD_NR 10 + +static int child_lock_holder(void *arg) +{ + struct lock_struct *locks = (struct lock_struct *) arg; + struct robust_list_head head; + int i; + + set_list(&head); + + for (i = 0; i < CHILD_NR; i++) { + locks[i].futex = 0; + mutex_lock(&locks[i], &head, false); + } + + pthread_barrier_wait(&barrier); + pthread_barrier_wait(&barrier2); + + sleep(1); + return 0; +} + +static int child_wait_lock(void *arg) +{ + struct lock_struct *lock = (struct lock_struct *) arg; + struct robust_list_head head; + int ret; + + pthread_barrier_wait(&barrier2); + ret = mutex_lock(lock, &head, false); + + if (ret) + ksft_test_result_fail("mutex_lock error\n"); + + if (!(lock->futex | FUTEX_OWNER_DIED)) + ksft_test_result_fail("futex not marked with FUTEX_OWNER_DIED\n"); + + return 0; +} + +/* + * Test a robust list of more than one element. All the waiters should wake when + * the holder dies + */ +TEST(robust_list_multiple_elements) +{ + struct lock_struct locks[CHILD_NR]; + int i, ret; + + ret = pthread_barrier_init(&barrier, NULL, 2); + ASSERT_EQ(ret, 0); + ret = pthread_barrier_init(&barrier2, NULL, CHILD_NR + 1); + ASSERT_EQ(ret, 0); + + create_child(&child_lock_holder, &locks); + + /* Wait until the locker thread takes the look */ + pthread_barrier_wait(&barrier); + + for (i = 0; i < CHILD_NR; i++) + create_child(&child_wait_lock, &locks[i]); + + /* Wait for all children to return */ + while (wait(NULL) > 0); + + pthread_barrier_destroy(&barrier); + pthread_barrier_destroy(&barrier2); +} + +TEST_HARNESS_MAIN -- 2.46.0

9 months, 3 weeks

3
2
0 0

[PATCH v2] kselftest/cgroup: Add missing newline in test_zswap.c

by Mohammed Anees

Thank you for the review, I have added the changelog as requested. Changelog: - Added missing newline to the `ksft_print_msg` in `test_zswap_writeback` function. Signed-off-by: Mohammed Anees <pvmohammedanees2003(a)gmail.com> --- tools/testing/selftests/cgroup/test_zswap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/cgroup/test_zswap.c b/tools/testing/selftests/cgroup/test_zswap.c index 190096017..7c849d836 100644 --- a/tools/testing/selftests/cgroup/test_zswap.c +++ b/tools/testing/selftests/cgroup/test_zswap.c @@ -351,7 +351,7 @@ static int test_zswap_writeback(const char *root, bool wb) goto out; if (wb != !!zswpwb_after) { - ksft_print_msg("zswpwb_after is %ld while wb is %s", + ksft_print_msg("zswpwb_after is %ld while wb is %s\n", zswpwb_after, wb ? "enabled" : "disabled"); goto out; } -- 2.43.0

9 months, 3 weeks

1
0
0 0

[GIT PULL] KUnit fixes second update for Linux 6.11-rc7

by Shuah Khan

Hi Linus, Please pull the following KUnit fixes second update for Linux 6.11-rc7. This KUnit fixes update for Linux 6.11-rc7 consists of a fix to missing function parameter warning found during documentation build in linux-next. diff is attached. thanks, -- Shuah ---------------------------------------------------------------- The following changes since commit f2c6dbd220170c2396fb019ead67fbada1e23ebd: kunit: Device wrappers should also manage driver name (2024-08-26 07:03:46 -0600) are available in the Git repository at: git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest tags/linux_kselftest-kunit-fixes-6.11-rc7-2 for you to fetch changes up to 12cb32a52eb607dc4d0e45fe6f4cf946d08da0fd: kunit: Fix missing kerneldoc comment (2024-09-05 14:29:10 -0600) ---------------------------------------------------------------- linux_kselftest-kunit-fixes-6.11-rc7-2 This KUnit fixes update for Linux 6.11-rc7 consists of a fix to missing function parameter warning found during documentation build in linux-next. ---------------------------------------------------------------- David Gow (1): kunit: Fix missing kerneldoc comment include/kunit/test.h | 1 + 1 file changed, 1 insertion(+) ----------------------------------------------------------------

9 months, 4 weeks

2
1
0 0

kselftest/next kselftest-seccomp: 2 runs, 1 regressions (v6.11-rc1-20-gaf1ec38c6ccc3)

by kernelci.org bot

kselftest/next kselftest-seccomp: 2 runs, 1 regressions (v6.11-rc1-20-gaf1ec38c6ccc3) Regressions Summary ------------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/job/kselftest/branch/next/kernel/v6.11-rc1-20-gaf… Test: kselftest-seccomp Tree: kselftest Branch: next Describe: v6.11-rc1-20-gaf1ec38c6ccc3 URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git SHA: af1ec38c6ccc31ec963ac4bcf8f6a7d8f44d210a Test Regressions ---------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/plan/id/66db7cf3c977f0093dc86855 Results: 0 PASS, 1 FAIL, 0 SKIP Full config: multi_v7_defconfig+kselftest Compiler: gcc-12 (arm-linux-gnueabihf-gcc (Debian 12.2.0-14) 12.2.0) Plain log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-20-gaf1ec38c6ccc3/ar… HTML log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-20-gaf1ec38c6ccc3/ar… Rootfs: http://storage.kernelci.org/images/rootfs/debian/bookworm-kselftest/2024031… * kselftest-seccomp.login: https://kernelci.org/test/case/id/66db7cf3c977f0093dc86856 failing since 38 days (last pass: v6.10-rc7-29-gdf09b0bb09ea, first fail: v6.11-rc1)

9 months, 4 weeks

1
0
0 0

kselftest/next kselftest-lib: 2 runs, 1 regressions (v6.11-rc1-20-gaf1ec38c6ccc3)

by kernelci.org bot

kselftest/next kselftest-lib: 2 runs, 1 regressions (v6.11-rc1-20-gaf1ec38c6ccc3) Regressions Summary ------------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/job/kselftest/branch/next/kernel/v6.11-rc1-20-gaf… Test: kselftest-lib Tree: kselftest Branch: next Describe: v6.11-rc1-20-gaf1ec38c6ccc3 URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git SHA: af1ec38c6ccc31ec963ac4bcf8f6a7d8f44d210a Test Regressions ---------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/plan/id/66db7fc38d2f0d735dc86865 Results: 0 PASS, 1 FAIL, 0 SKIP Full config: multi_v7_defconfig+kselftest Compiler: gcc-12 (arm-linux-gnueabihf-gcc (Debian 12.2.0-14) 12.2.0) Plain log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-20-gaf1ec38c6ccc3/ar… HTML log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-20-gaf1ec38c6ccc3/ar… Rootfs: http://storage.kernelci.org/images/rootfs/debian/bookworm-kselftest/2024031… * kselftest-lib.login: https://kernelci.org/test/case/id/66db7fc38d2f0d735dc86866 failing since 38 days (last pass: v6.10-rc7-29-gdf09b0bb09ea, first fail: v6.11-rc1)

9 months, 4 weeks

1
0
0 0

kselftest/next kselftest-lkdtm: 2 runs, 1 regressions (v6.11-rc1-20-gaf1ec38c6ccc3)

by kernelci.org bot

kselftest/next kselftest-lkdtm: 2 runs, 1 regressions (v6.11-rc1-20-gaf1ec38c6ccc3) Regressions Summary ------------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/job/kselftest/branch/next/kernel/v6.11-rc1-20-gaf… Test: kselftest-lkdtm Tree: kselftest Branch: next Describe: v6.11-rc1-20-gaf1ec38c6ccc3 URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git SHA: af1ec38c6ccc31ec963ac4bcf8f6a7d8f44d210a Test Regressions ---------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/plan/id/66db812c906848735ec8689d Results: 0 PASS, 1 FAIL, 0 SKIP Full config: multi_v7_defconfig+kselftest Compiler: gcc-12 (arm-linux-gnueabihf-gcc (Debian 12.2.0-14) 12.2.0) Plain log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-20-gaf1ec38c6ccc3/ar… HTML log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-20-gaf1ec38c6ccc3/ar… Rootfs: http://storage.kernelci.org/images/rootfs/debian/bookworm-kselftest/2024031… * kselftest-lkdtm.login: https://kernelci.org/test/case/id/66db812c906848735ec8689e failing since 38 days (last pass: v6.10-rc7-29-gdf09b0bb09ea, first fail: v6.11-rc1)

9 months, 4 weeks

1
0
0 0

kselftest/next build: 7 builds: 2 failed, 5 passed, 1 warning (v6.11-rc1-20-gaf1ec38c6ccc3)

by kernelci.org bot

kselftest/next build: 7 builds: 2 failed, 5 passed, 1 warning (v6.11-rc1-20-gaf1ec38c6ccc3) Full Build Summary: https://kernelci.org/build/kselftest/branch/next/kernel/v6.11-rc1-20-gaf1ec… Tree: kselftest Branch: next Git Describe: v6.11-rc1-20-gaf1ec38c6ccc3 Git Commit: af1ec38c6ccc31ec963ac4bcf8f6a7d8f44d210a Git URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git Built: 4 unique architectures Build Failures Detected: arm64: defconfig+kselftest+arm64-chromebook: (clang-16) FAIL defconfig+kselftest+arm64-chromebook: (gcc-12) FAIL Warnings Detected: arm64: arm: i386: x86_64: x86_64_defconfig+kselftest (clang-16): 1 warning Warnings summary: 1 vmlinux.o: warning: objtool: set_ftrace_ops_ro+0x39: relocation to !ENDBR: .text+0x14ef94 ================================================================================ Detailed per-defconfig build reports: -------------------------------------------------------------------------------- defconfig+kselftest (arm64, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- defconfig+kselftest+arm64-chromebook (arm64, gcc-12) — FAIL, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- defconfig+kselftest+arm64-chromebook (arm64, clang-16) — FAIL, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- i386_defconfig+kselftest (i386, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- multi_v7_defconfig+kselftest (arm, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- x86_64_defconfig+kselftest (x86_64, clang-16) — PASS, 0 errors, 1 warning, 0 section mismatches Warnings: vmlinux.o: warning: objtool: set_ftrace_ops_ro+0x39: relocation to !ENDBR: .text+0x14ef94 -------------------------------------------------------------------------------- x86_64_defconfig+kselftest (x86_64, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches --- For more info write to <info(a)kernelci.org>

9 months, 4 weeks

1
0
0 0

[PATCH net v2 0/2] bpf: devmap: provide rxq after redirect

by Florian Kauer

rxq contains a pointer to the device from where the redirect happened. Currently, the BPF program that was executed after a redirect via BPF_MAP_TYPE_DEVMAP* does not have it set. Add bugfix and related selftest. Signed-off-by: Florian Kauer <florian.kauer(a)linutronix.de> --- Changes in v2: - changed fixes tag - added selftest - Link to v1: https://lore.kernel.org/r/20240905-devel-koalo-fix-ingress-ifindex-v1-1-d12… --- Florian Kauer (2): bpf: devmap: provide rxq after redirect bpf: selftests: send packet to devmap redirect XDP kernel/bpf/devmap.c | 11 +- .../selftests/bpf/prog_tests/xdp_devmap_attach.c | 114 +++++++++++++++++++-- 2 files changed, 115 insertions(+), 10 deletions(-) --- base-commit: 8e69c96df771ab469cec278edb47009351de4da6 change-id: 20240905-devel-koalo-fix-ingress-ifindex-b9293d471db6 Best regards, -- Florian Kauer <florian.kauer(a)linutronix.de>

9 months, 4 weeks

3
4
0 0

[PATCH] kunit: Fix kernel-doc for EXPORT_SYMBOL_IF_KUNIT

by Michal Wajdeczko

While kunit/visibility.h is today not included in any generated kernel documentation, also likely due to the fact that none of the existing comments are correctly recognized as kernel-doc, but once we decide to add this header and fix the tool, there will be: ../include/kunit/visibility.h:61: warning: Function parameter or struct member 'symbol' not described in 'EXPORT_SYMBOL_IF_KUNIT' Signed-off-by: Michal Wajdeczko <michal.wajdeczko(a)intel.com> --- Cc: Rae Moar <rmoar(a)google.com> Cc: David Gow <davidgow(a)google.com> --- include/kunit/visibility.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/kunit/visibility.h b/include/kunit/visibility.h index 0dfe35feeec6..efff77b58dd6 100644 --- a/include/kunit/visibility.h +++ b/include/kunit/visibility.h @@ -22,6 +22,7 @@ * EXPORTED_FOR_KUNIT_TESTING namespace only if CONFIG_KUNIT is * enabled. Must use MODULE_IMPORT_NS(EXPORTED_FOR_KUNIT_TESTING) * in test file in order to use symbols. + * @symbol: the symbol identifier to export */ #define EXPORT_SYMBOL_IF_KUNIT(symbol) EXPORT_SYMBOL_NS(symbol, \ EXPORTED_FOR_KUNIT_TESTING) -- 2.43.0

9 months, 4 weeks

3
5
0 0

[PATCH v3 0/6] kunit: Add macros to help write more complex tests

by Michal Wajdeczko

v1: https://groups.google.com/g/kunit-dev/c/f4LIMLyofj8 v2: make it more complex and attempt to be thread safe s/FIXED_STUB/GLOBAL_STUB (David, Lucas) make it little more thread safe (Rae, David) wait until stub call finishes before test end (David) wait until stub call finishes before changing stub (David) allow stub deactivation (Rae) prefer kunit log (David) add simple selftest (Michal) also introduce ONLY_IF_KUNIT macro (Michal) v3: include example for DECLARE_IF_KUNIT (Lucas) rename s/ONLY_IF_KUNIT/VALUE_IF_KUNIT (Michal) and add simple usage example for it (Rae) fix s/fixed/global in comments (Lucas) improve stub sanitize flow (Lucas, Michal) reformat kernel-doc for better output (Michal) Test outputs: $ tools/testing/kunit/kunit.py run *example*.*global* \ --kunitconfig lib/kunit/.kunitconfig --raw_output KTAP version 1 1..1 # example: initializing suite KTAP version 1 # Subtest: example # module: kunit_example_test 1..1 # example_global_stub_test: initializing # example_global_stub_test: add_two: redirecting to subtract_one # example_global_stub_test: add_two: redirecting to subtract_one # example_global_stub_test: cleaning up ok 1 example_global_stub_test # example: exiting suite ok 1 example $ tools/testing/kunit/kunit.py run *global*.*global* \ --kunitconfig lib/kunit/.kunitconfig --raw_output KTAP version 1 1..1 KTAP version 1 # Subtest: kunit_global_stub # module: kunit_test 1..4 # kunit_global_stub_test_activate: real_void_func: redirecting to replacement_void_func # kunit_global_stub_test_activate: real_func: redirecting to replacement_func # kunit_global_stub_test_activate: real_func: redirecting to replacement_func # kunit_global_stub_test_activate: real_func: redirecting to other_replacement_func # kunit_global_stub_test_activate: real_func: redirecting to other_replacement_func # kunit_global_stub_test_activate: real_func: redirecting to super_replacement_func # kunit_global_stub_test_activate: real_func: redirecting to super_replacement_func ok 1 kunit_global_stub_test_activate ok 2 kunit_global_stub_test_deactivate # kunit_global_stub_test_slow_deactivate: real_func: redirecting to slow_replacement_func # kunit_global_stub_test_slow_deactivate: real_func: redirecting to slow_replacement_func # kunit_global_stub_test_slow_deactivate: waiting for slow_replacement_func # kunit_global_stub_test_slow_deactivate.speed: slow ok 3 kunit_global_stub_test_slow_deactivate # kunit_global_stub_test_slow_replace: real_func: redirecting to slow_replacement_func # kunit_global_stub_test_slow_replace: real_func: redirecting to slow_replacement_func # kunit_global_stub_test_slow_replace: waiting for slow_replacement_func # kunit_global_stub_test_slow_replace: real_func: redirecting to other_replacement_func # kunit_global_stub_test_slow_replace.speed: slow ok 4 kunit_global_stub_test_slow_replace # kunit_global_stub: pass:4 fail:0 skip:0 total:4 # Totals: pass:4 fail:0 skip:0 total:4 ok 1 kunit_global_stub Cc: Rae Moar <rmoar(a)google.com> Cc: David Gow <davidgow(a)google.com> Cc: Lucas De Marchi <lucas.demarchi(a)intel.com> Michal Wajdeczko (6): kunit: Introduce kunit_is_running() kunit: Add macro to conditionally expose declarations to tests kunit: Add macro to conditionally expose expressions to tests kunit: Allow function redirection outside of the KUnit thread kunit: Add example with alternate function redirection method kunit: Add some selftests for global stub redirection macros include/kunit/static_stub.h | 158 ++++++++++++++++++++ include/kunit/test-bug.h | 12 +- include/kunit/visibility.h | 40 ++++++ lib/kunit/kunit-example-test.c | 67 +++++++++ lib/kunit/kunit-test.c | 254 ++++++++++++++++++++++++++++++++- lib/kunit/static_stub.c | 50 +++++++ 6 files changed, 578 insertions(+), 3 deletions(-) -- 2.43.0

9 months, 4 weeks

2
7
0 0

[PATCH v2] selftests/timers: Remove unused NSEC_PER_SEC macro

by zhangjiao2

From: zhang jiao <zhangjiao2(a)cmss.chinamobile.com> By readind the code, I found the macro NSEC_PER_SEC is never referenced in the code. Just remove it. Signed-off-by: zhang jiao <zhangjiao2(a)cmss.chinamobile.com> --- v1->v2: Put together files with similar problems tools/testing/selftests/timers/change_skew.c | 3 --- tools/testing/selftests/timers/skew_consistency.c | 2 -- 2 files changed, 5 deletions(-) diff --git a/tools/testing/selftests/timers/change_skew.c b/tools/testing/selftests/timers/change_skew.c index 4421cd562c24..18e794a46c23 100644 --- a/tools/testing/selftests/timers/change_skew.c +++ b/tools/testing/selftests/timers/change_skew.c @@ -30,9 +30,6 @@ #include <time.h> #include "../kselftest.h" -#define NSEC_PER_SEC 1000000000LL - - int change_skew_test(int ppm) { struct timex tx; diff --git a/tools/testing/selftests/timers/skew_consistency.c b/tools/testing/selftests/timers/skew_consistency.c index c8e6bffe4e0a..83450145fe65 100644 --- a/tools/testing/selftests/timers/skew_consistency.c +++ b/tools/testing/selftests/timers/skew_consistency.c @@ -36,8 +36,6 @@ #include <sys/wait.h> #include "../kselftest.h" -#define NSEC_PER_SEC 1000000000LL - int main(int argc, char **argv) { struct timex tx; -- 2.33.0

9 months, 4 weeks

3
3
0 0

kselftest/next kselftest-seccomp: 2 runs, 1 regressions (v6.11-rc1-19-g7beaf1da074f7)

by kernelci.org bot

kselftest/next kselftest-seccomp: 2 runs, 1 regressions (v6.11-rc1-19-g7beaf1da074f7) Regressions Summary ------------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/job/kselftest/branch/next/kernel/v6.11-rc1-19-g7b… Test: kselftest-seccomp Tree: kselftest Branch: next Describe: v6.11-rc1-19-g7beaf1da074f7 URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git SHA: 7beaf1da074f7ea25454d6c11da142c3892d3c4e Test Regressions ---------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/plan/id/66db52a8b348d6369bc86855 Results: 0 PASS, 1 FAIL, 0 SKIP Full config: multi_v7_defconfig+kselftest Compiler: gcc-12 (arm-linux-gnueabihf-gcc (Debian 12.2.0-14) 12.2.0) Plain log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-19-g7beaf1da074f7/ar… HTML log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-19-g7beaf1da074f7/ar… Rootfs: http://storage.kernelci.org/images/rootfs/debian/bookworm-kselftest/2024031… * kselftest-seccomp.login: https://kernelci.org/test/case/id/66db52a8b348d6369bc86856 failing since 38 days (last pass: v6.10-rc7-29-gdf09b0bb09ea, first fail: v6.11-rc1)

9 months, 4 weeks

1
0
0 0

kselftest/next kselftest-lkdtm: 1 runs, 1 regressions (v6.11-rc1-19-g7beaf1da074f7)

by kernelci.org bot

kselftest/next kselftest-lkdtm: 1 runs, 1 regressions (v6.11-rc1-19-g7beaf1da074f7) Regressions Summary ------------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/job/kselftest/branch/next/kernel/v6.11-rc1-19-g7b… Test: kselftest-lkdtm Tree: kselftest Branch: next Describe: v6.11-rc1-19-g7beaf1da074f7 URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git SHA: 7beaf1da074f7ea25454d6c11da142c3892d3c4e Test Regressions ---------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/plan/id/66db55c87f15679370c8685b Results: 0 PASS, 1 FAIL, 0 SKIP Full config: multi_v7_defconfig+kselftest Compiler: gcc-12 (arm-linux-gnueabihf-gcc (Debian 12.2.0-14) 12.2.0) Plain log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-19-g7beaf1da074f7/ar… HTML log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-19-g7beaf1da074f7/ar… Rootfs: http://storage.kernelci.org/images/rootfs/debian/bookworm-kselftest/2024031… * kselftest-lkdtm.login: https://kernelci.org/test/case/id/66db55c87f15679370c8685c failing since 38 days (last pass: v6.10-rc7-29-gdf09b0bb09ea, first fail: v6.11-rc1)

9 months, 4 weeks

1
0
0 0

kselftest/next kselftest-lib: 2 runs, 1 regressions (v6.11-rc1-19-g7beaf1da074f7)

by kernelci.org bot

kselftest/next kselftest-lib: 2 runs, 1 regressions (v6.11-rc1-19-g7beaf1da074f7) Regressions Summary ------------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/job/kselftest/branch/next/kernel/v6.11-rc1-19-g7b… Test: kselftest-lib Tree: kselftest Branch: next Describe: v6.11-rc1-19-g7beaf1da074f7 URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git SHA: 7beaf1da074f7ea25454d6c11da142c3892d3c4e Test Regressions ---------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/plan/id/66db4e5b83c6242e5ac86855 Results: 0 PASS, 1 FAIL, 0 SKIP Full config: multi_v7_defconfig+kselftest Compiler: gcc-12 (arm-linux-gnueabihf-gcc (Debian 12.2.0-14) 12.2.0) Plain log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-19-g7beaf1da074f7/ar… HTML log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-19-g7beaf1da074f7/ar… Rootfs: http://storage.kernelci.org/images/rootfs/debian/bookworm-kselftest/2024031… * kselftest-lib.login: https://kernelci.org/test/case/id/66db4e5b83c6242e5ac86856 failing since 38 days (last pass: v6.10-rc7-29-gdf09b0bb09ea, first fail: v6.11-rc1)

9 months, 4 weeks

1
0
0 0

kselftest/next build: 7 builds: 2 failed, 5 passed, 1 warning (v6.11-rc1-19-g7beaf1da074f7)

by kernelci.org bot

kselftest/next build: 7 builds: 2 failed, 5 passed, 1 warning (v6.11-rc1-19-g7beaf1da074f7) Full Build Summary: https://kernelci.org/build/kselftest/branch/next/kernel/v6.11-rc1-19-g7beaf… Tree: kselftest Branch: next Git Describe: v6.11-rc1-19-g7beaf1da074f7 Git Commit: 7beaf1da074f7ea25454d6c11da142c3892d3c4e Git URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git Built: 4 unique architectures Build Failures Detected: arm64: defconfig+kselftest+arm64-chromebook: (clang-16) FAIL defconfig+kselftest+arm64-chromebook: (gcc-12) FAIL Warnings Detected: arm64: arm: i386: x86_64: x86_64_defconfig+kselftest (clang-16): 1 warning Warnings summary: 1 vmlinux.o: warning: objtool: set_ftrace_ops_ro+0x39: relocation to !ENDBR: .text+0x14ef94 ================================================================================ Detailed per-defconfig build reports: -------------------------------------------------------------------------------- defconfig+kselftest (arm64, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- defconfig+kselftest+arm64-chromebook (arm64, gcc-12) — FAIL, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- defconfig+kselftest+arm64-chromebook (arm64, clang-16) — FAIL, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- i386_defconfig+kselftest (i386, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- multi_v7_defconfig+kselftest (arm, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- x86_64_defconfig+kselftest (x86_64, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- x86_64_defconfig+kselftest (x86_64, clang-16) — PASS, 0 errors, 1 warning, 0 section mismatches Warnings: vmlinux.o: warning: objtool: set_ftrace_ops_ro+0x39: relocation to !ENDBR: .text+0x14ef94 --- For more info write to <info(a)kernelci.org>

9 months, 4 weeks

1
0
0 0

[PATCH] selftests/bpf: Add valid flag to bpf_cookie selftest's res

by Yuan Chen

From: Yuan Chen <chenyuan(a)kylinos.cn> This patch identifies whether a test item is valid by adding a valid flag to res. When we test the bpf_cookies/perf_event sub-test item of test_progs, there is a probability failure of the test item. In fact, this is not a problem, because the corresponding perf event is not collected. This should not output the test failure, and it is more reasonable to output SKIP. Therefore, add a valid identifier to res to distinguish whether the test item is valid, and skip the test item if it is invalid. Signed-off-by: Yuan Chen <chenyuan(a)kylinos.cn> --- .../testing/selftests/bpf/prog_tests/bpf_cookie.c | 15 +++++++++++++++ .../testing/selftests/bpf/progs/test_bpf_cookie.c | 2 ++ 2 files changed, 17 insertions(+) diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c index 070c52c312e5..e5bf4b385501 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c @@ -456,6 +456,7 @@ static void pe_subtest(struct test_bpf_cookie *skel) if (!ASSERT_GE(pfd, 0, "perf_fd")) goto cleanup; + skel->bss->res_valid = false; opts.bpf_cookie = 0x100000; link = bpf_program__attach_perf_event_opts(skel->progs.handle_pe, pfd, &opts); if (!ASSERT_OK_PTR(link, "link1")) @@ -463,6 +464,12 @@ static void pe_subtest(struct test_bpf_cookie *skel) burn_cpu(); /* trigger BPF prog */ + if (!skel->bss->res_valid) { + printf("%s:SKIP:the corresponding perf event was not sampled.\n", + __func__); + test__skip(); + goto cleanup; + } ASSERT_EQ(skel->bss->pe_res, 0x100000, "pe_res1"); /* prevent bpf_link__destroy() closing pfd itself */ @@ -474,6 +481,7 @@ static void pe_subtest(struct test_bpf_cookie *skel) link = NULL; kern_sync_rcu(); skel->bss->pe_res = 0; + skel->bss->res_valid = false; opts.bpf_cookie = 0x200000; link = bpf_program__attach_perf_event_opts(skel->progs.handle_pe, pfd, &opts); @@ -482,6 +490,13 @@ static void pe_subtest(struct test_bpf_cookie *skel) burn_cpu(); /* trigger BPF prog */ + if (!skel->bss->res_valid) { + printf("%s:SKIP:the corresponding perf event was not sampled.\n", + __func__); + test__skip(); + goto cleanup; + } + ASSERT_EQ(skel->bss->pe_res, 0x200000, "pe_res2"); cleanup: diff --git a/tools/testing/selftests/bpf/progs/test_bpf_cookie.c b/tools/testing/selftests/bpf/progs/test_bpf_cookie.c index c83142b55f47..28d0ae6810d9 100644 --- a/tools/testing/selftests/bpf/progs/test_bpf_cookie.c +++ b/tools/testing/selftests/bpf/progs/test_bpf_cookie.c @@ -7,6 +7,7 @@ #include <errno.h> int my_tid; +bool res_valid; __u64 kprobe_res; __u64 kprobe_multi_res; @@ -27,6 +28,7 @@ static void update(void *ctx, __u64 *res) if (my_tid != (u32)bpf_get_current_pid_tgid()) return; + res_valid = true; *res |= bpf_get_attach_cookie(ctx); } -- 2.46.0

9 months, 4 weeks

2
3
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror