July 2024 - Linux-kselftest-mirror

[PATCH v2] selftest: acct: Add selftest for the acct() syscall

by Abdulrasaq Lawani

Noticed that there was no selftest for the acct() syscall which enables the kernel to record terminated processes into a specified file. The acct() system call enables or disables process accounting. If accounting is turned on, records for each terminating process are appended to a specified filename as it terminates. An argument of NULL causes accounting to be turned off. This patch provides a test for the acct() syscall. References: https://man7.org/linux/man-pages/man2/acct.2.html Signed-off-by: Abdulrasaq Lawani <abdulrasaqolawani(a)gmail.com> --- Changes in v2: Add testcases to test error conditions. Add kselftest function for reporting results. - Link to v1: https://lore.kernel.org/r/20240622-kselftest-acct-syscall-v1-1-d270b5be8d37… --- tools/testing/selftests/Makefile | 1 + tools/testing/selftests/acct/.gitignore | 2 + tools/testing/selftests/acct/Makefile | 4 ++ tools/testing/selftests/acct/acct_syscall.c | 89 +++++++++++++++++++++++++++++ 4 files changed, 96 insertions(+) diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 9039f3709aff..45a58ef5ad92 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 +TARGETS += acct TARGETS += alsa TARGETS += amd-pstate TARGETS += arm64 diff --git a/tools/testing/selftests/acct/.gitignore b/tools/testing/selftests/acct/.gitignore new file mode 100644 index 000000000000..8ab358d81bd2 --- /dev/null +++ b/tools/testing/selftests/acct/.gitignore @@ -0,0 +1,2 @@ +acct_syscall +config \ No newline at end of file diff --git a/tools/testing/selftests/acct/Makefile b/tools/testing/selftests/acct/Makefile new file mode 100644 index 000000000000..ff3e238c5634 --- /dev/null +++ b/tools/testing/selftests/acct/Makefile @@ -0,0 +1,4 @@ +TEST_GEN_PROGS := acct_syscall +CFLAGS += -Wall + +include ../lib.mk \ No newline at end of file diff --git a/tools/testing/selftests/acct/acct_syscall.c b/tools/testing/selftests/acct/acct_syscall.c new file mode 100644 index 000000000000..4fa00a88a1bd --- /dev/null +++ b/tools/testing/selftests/acct/acct_syscall.c @@ -0,0 +1,89 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* kselftest for acct() system call + * The acct() system call enables or disables process accounting. + */ + +#include <stdio.h> +#include <errno.h> +#include <string.h> +#include <sys/wait.h> + +#include "../kselftest.h" + +int main(void) +{ + // Setting up kselftest framework + ksft_print_header(); + ksft_set_plan(1); + + // Create file to log closed processes + char filename[] = "process_log"; + FILE *fp; + + fp = fopen(filename, "w"); + + int i = acct(filename); + + // Handle error conditions + if (i) { + switch (errno) { + case EPERM: + ksft_test_result_error("%s. Please run the test as root.\n", + strerror(errno)); + break; + + case EACCES: + ksft_test_result_error("Insufficient privilege.\n"); + break; + + case EIO: + ksft_test_result_error("Error writing to the file: %s.\n", filename); + break; + + default: + ksft_test_result_error("%s.\n", strerror(errno)); + break; + } + + remove(filename); + fclose(fp); + ksft_finished(); + return 1; + } + + // Create child process and wait for it to terminate. + pid_t child_pid; + + child_pid = fork(); + + if (child_pid < 0) { + ksft_test_result_error("Process failed\n"); + ksft_finished(); + return 1; + } else if (child_pid == 0) { + ksft_print_msg("Child process successfully created!\n"); + } else { + wait(NULL); + fseek(fp, 0L, SEEK_END); + int sz = ftell(fp); + + ksft_print_msg("Parent process successfully created!\n"); + + i = acct(NULL); + + if (sz <= 0) { + ksft_test_result_fail("Terminated child process not logged"); + ksft_exit_fail(); + return 1; + } + + ksft_test_result_pass("Successfully logged terminated process.\n"); + remove(filename); + fclose(fp); + ksft_exit_pass(); + return 0; + } + + return 1; +} --- base-commit: 50736169ecc8387247fe6a00932852ce7b057083 change-id: 20240622-kselftest-acct-syscall-2d90f7666b1e Best regards, -- Abdulrasaq Lawani <abdulrasaqolawani(a)gmail.com>

5 months

2
1
0 0

[PATCH v3] selftests/timers: remove unused irqcount variable

by John Hubbard

When building with clang, via: make LLVM=1 -C tools/testing/selftest ...clang warns about an unused irqcount variable. clang is correct: the variable is incremented and then ignored. Fix this by deleting the irqcount variable. Signed-off-by: John Hubbard <jhubbard(a)nvidia.com> --- Changes since v2: 1) Rebased onto Linux 6.10-rc6+ Changes since the first version: 1) Rebased onto Linux 6.10-rc1 thanks, John Hubbard tools/testing/selftests/timers/rtcpie.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/tools/testing/selftests/timers/rtcpie.c b/tools/testing/selftests/timers/rtcpie.c index 4ef2184f1558..7c07edd0d450 100644 --- a/tools/testing/selftests/timers/rtcpie.c +++ b/tools/testing/selftests/timers/rtcpie.c @@ -29,7 +29,7 @@ static const char default_rtc[] = "/dev/rtc0"; int main(int argc, char **argv) { - int i, fd, retval, irqcount = 0; + int i, fd, retval; unsigned long tmp, data, old_pie_rate; const char *rtc = default_rtc; struct timeval start, end, diff; @@ -120,7 +120,6 @@ int main(int argc, char **argv) fprintf(stderr, " %d",i); fflush(stderr); - irqcount++; } /* Disable periodic interrupts */ base-commit: 8a9c6c40432e265600232b864f97d7c675e8be52 -- 2.45.2

5 months

4
3
0 0

[PATCH net-next 0/3] selftests: openvswitch: Address some flakes in the CI environment

by Aaron Conole

These patches aim to make using the openvswitch testsuite more reliable. These should address the major sources of flakiness in the openvswitch test suite allowing the CI infrastructure to exercise the openvswitch module for patch series. There should be no change for users who simply run the tests (except that patch 3/3 does make some of the debugging a bit easier by making some output more verbose). Aaron Conole (3): selftests: openvswitch: Bump timeout to 15 minutes. selftests: openvswitch: Attempt to autoload module. selftests: openvswitch: Be more verbose with selftest debugging. .../selftests/net/openvswitch/openvswitch.sh | 23 ++++++++++++------- .../selftests/net/openvswitch/settings | 1 + 2 files changed, 16 insertions(+), 8 deletions(-) create mode 100644 tools/testing/selftests/net/openvswitch/settings -- 2.45.1

5 months

5
11
0 0

Re: [PATCH net-next v9 00/10] net: openvswitch: Add sample multicasting.

by Adrián Moreno

On Fri, Jul 05, 2024 at 11:49:28AM GMT, Adrián Moreno wrote: > On Thu, Jul 04, 2024 at 10:56:51AM GMT, Adrian Moreno wrote: > > ** Background ** > > Currently, OVS supports several packet sampling mechanisms (sFlow, > > per-bridge IPFIX, per-flow IPFIX). These end up being translated into a > > userspace action that needs to be handled by ovs-vswitchd's handler > > threads only to be forwarded to some third party application that > > will somehow process the sample and provide observability on the > > datapath. > > > > A particularly interesting use-case is controller-driven > > per-flow IPFIX sampling where the OpenFlow controller can add metadata > > to samples (via two 32bit integers) and this metadata is then available > > to the sample-collecting system for correlation. > > > > ** Problem ** > > The fact that sampled traffic share netlink sockets and handler thread > > time with upcalls, apart from being a performance bottleneck in the > > sample extraction itself, can severely compromise the datapath, > > yielding this solution unfit for highly loaded production systems. > > > > Users are left with little options other than guessing what sampling > > rate will be OK for their traffic pattern and system load and dealing > > with the lost accuracy. > > > > Looking at available infrastructure, an obvious candidated would be > > to use psample. However, it's current state does not help with the > > use-case at stake because sampled packets do not contain user-defined > > metadata. > > > > ** Proposal ** > > This series is an attempt to fix this situation by extending the > > existing psample infrastructure to carry a variable length > > user-defined cookie. > > > > The main existing user of psample is tc's act_sample. It is also > > extended to forward the action's cookie to psample. > > > > Finally, a new OVS action (OVS_SAMPLE_ATTR_PSAMPLE) is created. > > It accepts a group and an optional cookie and uses psample to > > multicast the packet and the metadata. > > > > -- > > v8 -> v9: > > - Rebased. > > > > v7 -> v8: > > - Rebased > > - Redirect flow insertion to /dev/null to avoid spat in test. > > - Removed inline keyword in stub execute_psample_action function. > > > > v6 -> v7: > > - Rebased > > - Fixed typo in comment. > > > > v5 -> v6: > > - Renamed emit_sample -> psample > > - Addressed unused variable and conditionally compilation of function. > > > > v4 -> v5: > > - Rebased. > > - Removed lefover enum value and wrapped some long lines in selftests. > > > > v3 -> v4: > > - Rebased. > > - Addressed Jakub's comment on private and unused nla attributes. > > > > v2 -> v3: > > - Addressed comments from Simon, Aaron and Ilya. > > - Dropped probability propagation in nested sample actions. > > - Dropped patch v2's 7/9 in favor of a userspace implementation and > > consume skb if emit_sample is the last action, same as we do with > > userspace. > > - Split ovs-dpctl.py features in independent patches. > > > > v1 -> v2: > > - Create a new action ("emit_sample") rather than reuse existing > > "sample" one. > > - Add probability semantics to psample's sampling rate. > > - Store sampling probability in skb's cb area and use it in emit_sample. > > - Test combining "emit_sample" with "trunc" > > - Drop group_id filtering and tracepoint in psample. > > > > rfc_v2 -> v1: > > - Accommodate Ilya's comments. > > - Split OVS's attribute in two attributes and simplify internal > > handling of psample arguments. > > - Extend psample and tc with a user-defined cookie. > > - Add a tracepoint to psample to facilitate troubleshooting. > > > > rfc_v1 -> rfc_v2: > > - Use psample instead of a new OVS-only multicast group. > > - Extend psample and tc with a user-defined cookie. > > > > Adrian Moreno (10): > > net: psample: add user cookie > > net: sched: act_sample: add action cookie to sample > > net: psample: skip packet copy if no listeners > > net: psample: allow using rate as probability > > net: openvswitch: add psample action > > net: openvswitch: store sampling probability in cb. > > selftests: openvswitch: add psample action > > selftests: openvswitch: add userspace parsing > > selftests: openvswitch: parse trunc action > > selftests: openvswitch: add psample test > > > > Documentation/netlink/specs/ovs_flow.yaml | 17 ++ > > include/net/psample.h | 5 +- > > include/uapi/linux/openvswitch.h | 31 +- > > include/uapi/linux/psample.h | 11 +- > > net/openvswitch/Kconfig | 1 + > > net/openvswitch/actions.c | 66 ++++- > > net/openvswitch/datapath.h | 3 + > > net/openvswitch/flow_netlink.c | 32 ++- > > net/openvswitch/vport.c | 1 + > > net/psample/psample.c | 16 +- > > net/sched/act_sample.c | 12 + > > .../selftests/net/openvswitch/openvswitch.sh | 115 +++++++- > > .../selftests/net/openvswitch/ovs-dpctl.py | 272 +++++++++++++++++- > > 13 files changed, 566 insertions(+), 16 deletions(-) > > > > -- > > 2.45.2 > > > > Hi, > > Simon Horman has spotted that openvswitch.sh tests are failing in the > debug executor: > > https://netdev.bots.linux.dev/contest.html?test=openvswitch-sh > > The failing tests are two: psample and upcall_interfaces. These two > tests have a known source of instability (they use "sleep") that make > them specially unreliable in slow systems. > > Aaron and I already discussed this and I'm working on a patch to make > both tests more robust by adding a wait-and-retry mechanism. > > I hope this series can be considered regardless of this flaky tests. > Adding more context to explain our situation. This series has a counterpart in OVS [1]. The state of this other series is still RFC just because the kernel bits have not yet been merged. OVS 3.4 "softfreeze" was declared last monday, which excludes from the release any series that is stil in RFC state. Given the kernel parts seemed very close to be merged, an exception was given to the series so we can consider it for inclusion [2]. I hate to put any pressure on already busy maintainers but I would also dislike missing this OVS release by just one or two days and having to wait 6 months (OVS release cadence) for it to be available. Again, I don't want to put pressure on maintainers. If it's not possible, that's it. I just wanted to voice our timeline constraints. Thanks for your understanding. Adrián [1] https://patchwork.ozlabs.org/project/openvswitch/cover/20240704085710.35384… [2] https://mail.openvswitch.org/pipermail/ovs-dev/2024-July/415261.html

5 months

1
0
0 0

[PATCH] selftests/net: do_setcpu function not need to have a return value

by Liu Jing

in the do_setcpu, this function does not need to have a return value, which is meaningless Signed-off-by: Liu Jing <liujing(a)cmss.chinamobile.com> --- tools/testing/selftests/net/msg_zerocopy.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c index bdc03a2097e8..0b54f2011449 100644 --- a/tools/testing/selftests/net/msg_zerocopy.c +++ b/tools/testing/selftests/net/msg_zerocopy.c @@ -118,7 +118,7 @@ static uint16_t get_ip_csum(const uint16_t *start, int num_words) return ~sum; } -static int do_setcpu(int cpu) +static void do_setcpu(int cpu) { cpu_set_t mask; @@ -129,7 +129,6 @@ static int do_setcpu(int cpu) else if (cfg_verbose) fprintf(stderr, "cpu: %u\n", cpu); - return 0; } static void do_setsockopt(int fd, int level, int optname, int val) -- 2.33.0

5 months

1
0
0 0

[PATCH 0/1] KVM: selftests: pmu_counters_test: increase robustness of LLC cache misses

by Maxim Levitsky

Recent CI failures brought my attention to the fact that pmu_counters_test sometimes fails because it doesn't get any LLC cache misses. It apparently happens because CLFLUSH can race with CPU prediction. To attempt to fix this, implement a more aggressive cache flushing - now it is flushed on each iteration of the measured loop which should at least reduce by order of magnitude the chance of this happening. This patch survived more that a day of running in a loop on a Comet Lake machine, where the test used to fail after about 10-20 minites. Best regards, Maxim Levitsky Maxim Levitsky (1): KVM: selftests: pmu_counters_test: increase robustness of LLC cache misses .../selftests/kvm/x86_64/pmu_counters_test.c | 20 +++++++++---------- 1 file changed, 9 insertions(+), 11 deletions(-) -- 2.26.3

5 months

2
4
0 0

[PATCH bpf-next v7 0/9] use network helpers, part 8

by Geliang Tang

From: Geliang Tang <tanggeliang(a)kylinos.cn> v7: - address Martin's comments in v6. (thanks) - use MAX(opts->backlog, 0) instead of opts->backlog. - use connect_to_fd_opts instead connect_to_fd. - more ASSERT_* to check errors. v6: - update patch 6 as Daniel suggested. (thanks) v5: - keep make_server and make_client as Eduard suggested. v4: - a new patch to use make_sockaddr in sockmap_ktls. - a new patch to close fd in error path in drop_on_reuseport. - drop make_server() in patch 7. - drop make_client() too in patch 9. v3: - a new patch to add backlog for network_helper_opts. - use start_server_str in sockmap_ktls now, not start_server. v2: - address Eduard's comments in v1. (thanks) - fix errors reported by CI. This patch set uses network helpers in sockmap_ktls and sk_lookup, and drop three local helpers tcp_server(), inetaddr_len() and make_socket() in them. Geliang Tang (9): selftests/bpf: Add backlog for network_helper_opts selftests/bpf: Use start_server_str in sockmap_ktls selftests/bpf: Use connect_to_fd_opts in sockmap_ktls selftests/bpf: Use make_sockaddr in sockmap_ktls selftests/bpf: Close fd in error path in drop_on_reuseport selftests/bpf: Use start_server_str in sk_lookup selftests/bpf: Use connect_to_fd_opts in sk_lookup selftests/bpf: Use connect_to_addr in sk_lookup selftests/bpf: Drop make_socket in sk_lookup tools/testing/selftests/bpf/network_helpers.c | 2 +- tools/testing/selftests/bpf/network_helpers.h | 4 + .../selftests/bpf/prog_tests/sk_lookup.c | 150 ++++++++---------- .../selftests/bpf/prog_tests/sockmap_ktls.c | 53 ++----- 4 files changed, 77 insertions(+), 132 deletions(-) -- 2.43.0

5 months

1
10
0 0

[GIT PULL] Kselftest fixes for v6.10

by Mickaël Salaün

Hi Linus, This PR fixes a few kselftests [1]. This has been in linux-next for a week and rebased to add Mark Brown's Tested-by. The race condition found while writing this fix is not new and seems specific to UML's hostfs (I also tested against ext4 and btrfs without being able to trigger this issue). Feel free to take this PR if you see fit. Regards, Mickaël [1] https://lore.kernel.org/r/9341d4db-5e21-418c-bf9e-9ae2da7877e1@sirena.org.uk -- The following changes since commit f2661062f16b2de5d7b6a5c42a9a5c96326b8454: Linux 6.10-rc5 (2024-06-23 17:08:54 -0400) are available in the Git repository at: https://git.kernel.org/pub/scm/linux/kernel/git/mic/linux.git tags/kselftest-fix-2024-07-04 for you to fetch changes up to 130e42806773013e9cf32d211922c935ae2df86c: selftests/harness: Fix tests timeout and race condition (2024-06-28 16:06:03 +0200) ---------------------------------------------------------------- Fix Kselftests timeout and race condition ---------------------------------------------------------------- Mickaël Salaün (1): selftests/harness: Fix tests timeout and race condition tools/testing/selftests/kselftest_harness.h | 43 ++++++++++++++++------------- 1 file changed, 24 insertions(+), 19 deletions(-)

5 months

2
1
0 0

[RFC PATCH] selftests: introduce and use SELFTESTS_CC_IS_CLANG instead of LLVM

by John Hubbard

Current practice in the selftests Makefiles is to use $(LLVM) as a way to decide if clang is being used as the compiler (and/or the linker front end). Unfortunately, this does not cover all of the use cases: 1) CC could have been set within selftests/lib.mk, by inferring it from LLVM==1, or 2) CC could have been set externally, such as when cross compiling. Solution: In order to allow subsystem selftests to more accurately control clang-specific behavior, such as compiler options, provide a new Makefile variable: SELFTESTS_CC_IS_CLANG. If $(CC) contains an invocation of clang in any form, then SELFTESTS_CC_IS_CLANG will be non-empty. SELFTESTS_CC_IS_CLANG does not specify which linker is being used. However, it can still help with linker options, because $(CC) is often used to do both the compile and link steps (often in the same step). Signed-off-by: John Hubbard <jhubbard(a)nvidia.com> --- Hi, If this looks reasonable, I'll break it up into separate patches and post it as a non-RFC. thanks, John Hubbard tools/testing/selftests/bpf/Makefile | 2 +- tools/testing/selftests/fchmodat2/Makefile | 12 +++++++----- tools/testing/selftests/hid/Makefile | 2 +- tools/testing/selftests/lib.mk | 15 +++++++++++++++ tools/testing/selftests/openat2/Makefile | 16 +++++++++------- 5 files changed, 33 insertions(+), 14 deletions(-) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index dd49c1d23a60..6b924297ab71 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -55,7 +55,7 @@ progs/test_sk_lookup.c-CFLAGS := -fno-strict-aliasing progs/timer_crash.c-CFLAGS := -fno-strict-aliasing progs/test_global_func9.c-CFLAGS := -fno-strict-aliasing -ifneq ($(LLVM),) +ifeq ($(SELFTESTS_CC_IS_CLANG),) # Silence some warnings when compiled with clang CFLAGS += -Wno-unused-command-line-argument endif diff --git a/tools/testing/selftests/fchmodat2/Makefile b/tools/testing/selftests/fchmodat2/Makefile index 4373cea79b79..d00b01be5d96 100644 --- a/tools/testing/selftests/fchmodat2/Makefile +++ b/tools/testing/selftests/fchmodat2/Makefile @@ -2,14 +2,16 @@ CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined $(KHDR_INCLUDES) +TEST_GEN_PROGS := fchmodat2_test + +include ../lib.mk + # gcc requires -static-libasan in order to ensure that Address Sanitizer's # library is the first one loaded. However, clang already statically links the # Address Sanitizer if -fsanitize is specified. Therefore, simply omit # -static-libasan for clang builds. -ifeq ($(LLVM),) +# This check must be done after including ../lib.mk, in order to pick up the +# correct value of SELFTESTS_CC_IS_CLANG. +ifeq ($(SELFTESTS_CC_IS_CLANG),) CFLAGS += -static-libasan endif - -TEST_GEN_PROGS := fchmodat2_test - -include ../lib.mk diff --git a/tools/testing/selftests/hid/Makefile b/tools/testing/selftests/hid/Makefile index 2b5ea18bde38..734a53dc8ad9 100644 --- a/tools/testing/selftests/hid/Makefile +++ b/tools/testing/selftests/hid/Makefile @@ -27,7 +27,7 @@ CFLAGS += -I$(OUTPUT)/tools/include LDLIBS += -lelf -lz -lrt -lpthread # Silence some warnings when compiled with clang -ifneq ($(LLVM),) +ifeq ($(SELFTESTS_CC_IS_CLANG),) CFLAGS += -Wno-unused-command-line-argument endif diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 429535816dbd..f321ad5a1d0c 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -43,6 +43,21 @@ else CC := $(CROSS_COMPILE)gcc endif # LLVM +# SELFTESTS_CC_IS_CLANG allows subsystem selftests to more accurately control +# clang-specific behavior, such as compiler options. If CC is an invocation of +# clang in any form, then SELFTESTS_CC_IS_CLANG will be non-empty. Notes: +# +# 1) CC could have been set above, by inferring it from LLVM==1, or externally, +# from the CC shell environment variable. +# +# 2) SELFTESTS_CC_IS_CLANG does not specify which linker is being used. However, +# it can still help with linker options, if clang or gcc is used for the +# linker front end. +SELFTESTS_CC_IS_CLANG := +ifeq ($(findstring clang,$(CC)),clang) + SELFTESTS_CC_IS_CLANG := 1 +endif + ifeq (0,$(MAKELEVEL)) ifeq ($(OUTPUT),) OUTPUT := $(shell pwd) diff --git a/tools/testing/selftests/openat2/Makefile b/tools/testing/selftests/openat2/Makefile index 185dc76ebb5f..7acb85a8f2ac 100644 --- a/tools/testing/selftests/openat2/Makefile +++ b/tools/testing/selftests/openat2/Makefile @@ -3,16 +3,18 @@ CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined TEST_GEN_PROGS := openat2_test resolve_test rename_attack_test +LOCAL_HDRS += helpers.h + +include ../lib.mk + +$(TEST_GEN_PROGS): helpers.c + # gcc requires -static-libasan in order to ensure that Address Sanitizer's # library is the first one loaded. However, clang already statically links the # Address Sanitizer if -fsanitize is specified. Therefore, simply omit # -static-libasan for clang builds. -ifeq ($(LLVM),) +# This check must be done after including ../lib.mk, in order to pick up the +# correct value of SELFTESTS_CC_IS_CLANG. +ifeq ($(SELFTESTS_CC_IS_CLANG),) CFLAGS += -static-libasan endif - -LOCAL_HDRS += helpers.h - -include ../lib.mk - -$(TEST_GEN_PROGS): helpers.c base-commit: 9a5cd459be8a425d70cda1fa1c89af7875a35d17 -- 2.45.2

5 months

3
3
0 0

[PATCH bpf-next] arm64, bpf: Add 12-argument support for bpf trampoline

by Puranjay Mohan

The arm64 bpf JIT currently supports attaching the trampoline to functions with <= 8 arguments. This is because up to 8 arguments can be passed in registers r0-r7. If there are more than 8 arguments then the 9th and later arguments are passed on the stack, with SP pointing to the first stacked argument. See aapcs64[1] for more details. Add the support of storing and restoring arguments passed on the stack to the arm64 bpf trampoline. This will allow attaching the trampoline to functions that take 12 arguments. [1] https://github.com/ARM-software/abi-aa/blob/main/aapcs64/aapcs64.rst#parame… Signed-off-by: Puranjay Mohan <puranjay(a)kernel.org> --- arch/arm64/net/bpf_jit_comp.c | 113 +++++++++++++------ tools/testing/selftests/bpf/DENYLIST.aarch64 | 2 - 2 files changed, 81 insertions(+), 34 deletions(-) diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 751331f5ba90..ebc148596e59 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -30,6 +30,8 @@ #define TMP_REG_3 (MAX_BPF_JIT_REG + 3) #define FP_BOTTOM (MAX_BPF_JIT_REG + 4) #define ARENA_VM_START (MAX_BPF_JIT_REG + 5) +/* Up to eight function arguments are passed in registers r0-r7 */ +#define ARM64_MAX_REG_ARGS 8 #define check_imm(bits, imm) do { \ if ((((imm) > 0) && ((imm) >> (bits))) || \ @@ -2001,26 +2003,51 @@ static void invoke_bpf_mod_ret(struct jit_ctx *ctx, struct bpf_tramp_links *tl, } } -static void save_args(struct jit_ctx *ctx, int args_off, int nregs) +static void save_args(struct jit_ctx *ctx, int args_off, int orig_sp_off, + int nargs) { + const u8 tmp = bpf2a64[TMP_REG_1]; + int arg_pos; int i; - for (i = 0; i < nregs; i++) { - emit(A64_STR64I(i, A64_SP, args_off), ctx); + for (i = 0; i < nargs; i++) { + if (i < ARM64_MAX_REG_ARGS) { + emit(A64_STR64I(i, A64_SP, args_off), ctx); + } else { + arg_pos = orig_sp_off + (i - ARM64_MAX_REG_ARGS) * 8; + emit(A64_LDR64I(tmp, A64_SP, arg_pos), ctx); + emit(A64_STR64I(tmp, A64_SP, args_off), ctx); + } args_off += 8; } } -static void restore_args(struct jit_ctx *ctx, int args_off, int nregs) +static void restore_args(struct jit_ctx *ctx, int args_off, int nargs) { int i; - for (i = 0; i < nregs; i++) { + for (i = 0; i < nargs; i++) { emit(A64_LDR64I(i, A64_SP, args_off), ctx); args_off += 8; } } +static void restore_stack_args(struct jit_ctx *ctx, int args_off, int stk_arg_off, + int nr_stack_args) +{ + const u8 tmp = bpf2a64[TMP_REG_1]; + int arg_pos; + int i; + + for (i = ARM64_MAX_REG_ARGS; i < nr_stack_args; i++) { + arg_pos = args_off + i * 8; + emit(A64_LDR64I(tmp, A64_SP, arg_pos), ctx); + emit(A64_STR64I(tmp, A64_SP, stk_arg_off), ctx); + + stk_arg_off += 8; + } +} + /* Based on the x86's implementation of arch_prepare_bpf_trampoline(). * * bpf prog and function entry before bpf trampoline hooked: @@ -2034,15 +2061,17 @@ static void restore_args(struct jit_ctx *ctx, int args_off, int nregs) */ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, struct bpf_tramp_links *tlinks, void *func_addr, - int nregs, u32 flags) + int nargs, u32 flags) { int i; int stack_size; + int stk_arg_off; + int orig_sp_off; int retaddr_off; int regs_off; int retval_off; int args_off; - int nregs_off; + int nargs_off; int ip_off; int run_ctx_off; struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY]; @@ -2052,6 +2081,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, __le32 **branches = NULL; /* trampoline stack layout: + * SP + orig_sp_off [ first stack arg ] if nargs > ARM64_MAX_REG_ARGS * [ parent ip ] * [ FP ] * SP + retaddr_off [ self ip ] @@ -2069,14 +2099,23 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, * [ ... ] * SP + args_off [ arg reg 1 ] * - * SP + nregs_off [ arg regs count ] + * SP + nargs_off [ arg count ] * * SP + ip_off [ traced function ] BPF_TRAMP_F_IP_ARG flag * * SP + run_ctx_off [ bpf_tramp_run_ctx ] + * + * [ stack_argN ] + * [ ... ] + * SP + stk_arg_off [ stack_arg1 ] BPF_TRAMP_F_CALL_ORIG */ stack_size = 0; + stk_arg_off = stack_size; + /* room for saving arguments passed on stack */ + if (nargs - ARM64_MAX_REG_ARGS > 0) + stack_size += (nargs - ARM64_MAX_REG_ARGS) * 8; + run_ctx_off = stack_size; /* room for bpf_tramp_run_ctx */ stack_size += round_up(sizeof(struct bpf_tramp_run_ctx), 8); @@ -2086,13 +2125,13 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, if (flags & BPF_TRAMP_F_IP_ARG) stack_size += 8; - nregs_off = stack_size; + nargs_off = stack_size; /* room for args count */ stack_size += 8; args_off = stack_size; /* room for args */ - stack_size += nregs * 8; + stack_size += nargs * 8; /* room for return value */ retval_off = stack_size; @@ -2110,6 +2149,11 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, /* return address locates above FP */ retaddr_off = stack_size + 8; + /* original SP position + * stack_size + parent function frame + patched function frame + */ + orig_sp_off = stack_size + 32; + /* bpf trampoline may be invoked by 3 instruction types: * 1. bl, attached to bpf prog or kernel function via short jump * 2. br, attached to bpf prog or kernel function via long jump @@ -2135,12 +2179,12 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, emit(A64_STR64I(A64_R(10), A64_SP, ip_off), ctx); } - /* save arg regs count*/ - emit(A64_MOVZ(1, A64_R(10), nregs, 0), ctx); - emit(A64_STR64I(A64_R(10), A64_SP, nregs_off), ctx); + /* save arg count */ + emit(A64_MOVZ(1, A64_R(10), nargs, 0), ctx); + emit(A64_STR64I(A64_R(10), A64_SP, nargs_off), ctx); - /* save arg regs */ - save_args(ctx, args_off, nregs); + /* save arguments passed in regs and on the stack */ + save_args(ctx, args_off, orig_sp_off, nargs); /* save callee saved registers */ emit(A64_STR64I(A64_R(19), A64_SP, regs_off), ctx); @@ -2167,7 +2211,11 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, } if (flags & BPF_TRAMP_F_CALL_ORIG) { - restore_args(ctx, args_off, nregs); + /* restore arguments that were passed in registers */ + restore_args(ctx, args_off, + min_t(int, nargs, ARM64_MAX_REG_ARGS)); + /* restore arguments that were passed on the stack */ + restore_stack_args(ctx, args_off, stk_arg_off, nargs); /* call original func */ emit(A64_LDR64I(A64_R(10), A64_SP, retaddr_off), ctx); emit(A64_ADR(A64_LR, AARCH64_INSN_SIZE * 2), ctx); @@ -2196,7 +2244,8 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, } if (flags & BPF_TRAMP_F_RESTORE_REGS) - restore_args(ctx, args_off, nregs); + restore_args(ctx, args_off, + min_t(int, nargs, ARM64_MAX_REG_ARGS)); /* restore callee saved register x19 and x20 */ emit(A64_LDR64I(A64_R(19), A64_SP, regs_off), ctx); @@ -2228,19 +2277,19 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, return ctx->idx; } -static int btf_func_model_nregs(const struct btf_func_model *m) +static int btf_func_model_nargs(const struct btf_func_model *m) { - int nregs = m->nr_args; + int nargs = m->nr_args; int i; - /* extra registers needed for struct argument */ + /* extra registers or stack slots needed for struct argument */ for (i = 0; i < MAX_BPF_FUNC_ARGS; i++) { /* The arg_size is at most 16 bytes, enforced by the verifier. */ if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) - nregs += (m->arg_size[i] + 7) / 8 - 1; + nargs += (m->arg_size[i] + 7) / 8 - 1; } - return nregs; + return nargs; } int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, @@ -2251,14 +2300,14 @@ int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, .idx = 0, }; struct bpf_tramp_image im; - int nregs, ret; + int nargs, ret; - nregs = btf_func_model_nregs(m); - /* the first 8 registers are used for arguments */ - if (nregs > 8) + nargs = btf_func_model_nargs(m); + /* the first 8 arguments are in registers and others are on stack */ + if (nargs > MAX_BPF_FUNC_ARGS) return -ENOTSUPP; - ret = prepare_trampoline(&ctx, &im, tlinks, func_addr, nregs, flags); + ret = prepare_trampoline(&ctx, &im, tlinks, func_addr, nargs, flags); if (ret < 0) return ret; @@ -2285,7 +2334,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image, u32 flags, struct bpf_tramp_links *tlinks, void *func_addr) { - int ret, nregs; + int ret, nargs; void *image, *tmp; u32 size = ro_image_end - ro_image; @@ -2302,13 +2351,13 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image, .idx = 0, }; - nregs = btf_func_model_nregs(m); - /* the first 8 registers are used for arguments */ - if (nregs > 8) + nargs = btf_func_model_nargs(m); + /* the first 8 arguments are in registers and others are on stack */ + if (nargs > MAX_BPF_FUNC_ARGS) return -ENOTSUPP; jit_fill_hole(image, (unsigned int)(ro_image_end - ro_image)); - ret = prepare_trampoline(&ctx, im, tlinks, func_addr, nregs, flags); + ret = prepare_trampoline(&ctx, im, tlinks, func_addr, nargs, flags); if (ret > 0 && validate_code(&ctx) < 0) { ret = -EINVAL; diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64 index 3c7c3e79aa93..0b17bc0dea7a 100644 --- a/tools/testing/selftests/bpf/DENYLIST.aarch64 +++ b/tools/testing/selftests/bpf/DENYLIST.aarch64 @@ -4,8 +4,6 @@ fexit_sleep # The test never returns. The r kprobe_multi_bench_attach # needs CONFIG_FPROBE kprobe_multi_test # needs CONFIG_FPROBE module_attach # prog 'kprobe_multi': failed to auto-attach: -95 -fentry_test/fentry_many_args # fentry_many_args:FAIL:fentry_many_args_attach unexpected error: -524 -fexit_test/fexit_many_args # fexit_many_args:FAIL:fexit_many_args_attach unexpected error: -524 tracing_struct/struct_many_args # struct_many_args:FAIL:tracing_struct_many_args__attach unexpected error: -524 fill_link_info/kprobe_multi_link_info # bpf_program__attach_kprobe_multi_opts unexpected error: -95 fill_link_info/kretprobe_multi_link_info # bpf_program__attach_kprobe_multi_opts unexpected error: -95 -- 2.40.1

5 months

2
1
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror July 2024