August 2025 - Linux-kselftest-mirror

[PATCH] selftests/futex: Check for shmget support at runtime

by Wake Liu

The futex tests `futex_wait.c` and `futex_waitv.c` rely on the `shmget()` syscall, which may not be available if the kernel is built without System V IPC support (CONFIG_SYSVIPC=n). This can lead to test failures on such systems. This patch modifies the tests to check for `shmget()` support at runtime by calling it and checking for an `ENOSYS` error. If `shmget()` is not supported, the tests are skipped with a clear message, improving the user experience and preventing false negatives. This approach is more robust than relying on compile-time checks and ensures that the tests run only when the required kernel features are present. Signed-off-by: Wake Liu <wakel(a)google.com> --- .../selftests/futex/functional/futex_wait.c | 49 ++++++------ .../selftests/futex/functional/futex_waitv.c | 78 +++++++++++-------- 2 files changed, 72 insertions(+), 55 deletions(-) diff --git a/tools/testing/selftests/futex/functional/futex_wait.c b/tools/testing/selftests/futex/functional/futex_wait.c index 685140d9b93d..17a465313a59 100644 --- a/tools/testing/selftests/futex/functional/futex_wait.c +++ b/tools/testing/selftests/futex/functional/futex_wait.c @@ -48,7 +48,7 @@ static void *waiterfn(void *arg) int main(int argc, char *argv[]) { int res, ret = RET_PASS, fd, c, shm_id; - u_int32_t f_private = 0, *shared_data; + u_int32_t f_private = 0, *shared_data = NULL; unsigned int flags = FUTEX_PRIVATE_FLAG; pthread_t waiter; void *shm; @@ -96,32 +96,35 @@ int main(int argc, char *argv[]) /* Testing an anon page shared memory */ shm_id = shmget(IPC_PRIVATE, 4096, IPC_CREAT | 0666); if (shm_id < 0) { - perror("shmget"); - exit(1); - } - - shared_data = shmat(shm_id, NULL, 0); + if (errno == ENOSYS) { + ksft_test_result_skip("Kernel does not support System V shared memory\n"); + } else { + ksft_test_result_fail("shmget() failed with error: %s\n", strerror(errno)); + ret = RET_FAIL; + } + } else { + shared_data = shmat(shm_id, NULL, 0); - *shared_data = 0; - futex = shared_data; + *shared_data = 0; + futex = shared_data; - info("Calling shared (page anon) futex_wait on futex: %p\n", futex); - if (pthread_create(&waiter, NULL, waiterfn, NULL)) - error("pthread_create failed\n", errno); + info("Calling shared (page anon) futex_wait on futex: %p\n", futex); + if (pthread_create(&waiter, NULL, waiterfn, NULL)) + error("pthread_create failed\n", errno); - usleep(WAKE_WAIT_US); + usleep(WAKE_WAIT_US); - info("Calling shared (page anon) futex_wake on futex: %p\n", futex); - res = futex_wake(futex, 1, 0); - if (res != 1) { - ksft_test_result_fail("futex_wake shared (page anon) returned: %d %s\n", - errno, strerror(errno)); - ret = RET_FAIL; - } else { - ksft_test_result_pass("futex_wake shared (page anon) succeeds\n"); + info("Calling shared (page anon) futex_wake on futex: %p\n", futex); + res = futex_wake(futex, 1, 0); + if (res != 1) { + ksft_test_result_fail("futex_wake shared (page anon) returned: %d %s\n", + errno, strerror(errno)); + ret = RET_FAIL; + } else { + ksft_test_result_pass("futex_wake shared (page anon) succeeds\n"); + } } - /* Testing a file backed shared memory */ fd = open(SHM_PATH, O_RDWR | O_CREAT, S_IRUSR | S_IWUSR); if (fd < 0) { @@ -161,7 +164,8 @@ int main(int argc, char *argv[]) } /* Freeing resources */ - shmdt(shared_data); + if (shared_data) + shmdt(shared_data); munmap(shm, sizeof(f_private)); remove(SHM_PATH); close(fd); @@ -169,3 +173,4 @@ int main(int argc, char *argv[]) ksft_print_cnts(); return ret; } + diff --git a/tools/testing/selftests/futex/functional/futex_waitv.c b/tools/testing/selftests/futex/functional/futex_waitv.c index a94337f677e1..3baf5142b434 100644 --- a/tools/testing/selftests/futex/functional/futex_waitv.c +++ b/tools/testing/selftests/futex/functional/futex_waitv.c @@ -104,46 +104,62 @@ int main(int argc, char *argv[]) ksft_test_result_fail("futex_wake private returned: %d %s\n", res ? errno : res, res ? strerror(errno) : ""); - ret = RET_FAIL; } else { ksft_test_result_pass("futex_waitv private\n"); } /* Shared waitv */ - for (i = 0; i < NR_FUTEXES; i++) { - int shm_id = shmget(IPC_PRIVATE, 4096, IPC_CREAT | 0666); - - if (shm_id < 0) { - perror("shmget"); - exit(1); + bool shm_supported = true; + int shm_id = shmget(IPC_PRIVATE, 4096, IPC_CREAT | 0666); + + if (shm_id < 0) { + if (errno == ENOSYS) { + shm_supported = false; + ksft_test_result_skip("Kernel does not support System V shared memory\n"); + } else { + ksft_test_result_fail("shmget() failed with error: %s\n", strerror(errno)); + ret = RET_FAIL; + shm_supported = false; } + } else { + shmctl(shm_id, IPC_RMID, NULL); + } - unsigned int *shared_data = shmat(shm_id, NULL, 0); + if (shm_supported) { + for (i = 0; i < NR_FUTEXES; i++) { + int shm_id = shmget(IPC_PRIVATE, 4096, IPC_CREAT | 0666); - *shared_data = 0; - waitv[i].uaddr = (uintptr_t)shared_data; - waitv[i].flags = FUTEX_32; - waitv[i].val = 0; - waitv[i].__reserved = 0; - } + if (shm_id < 0) { + perror("shmget"); + exit(1); + } - if (pthread_create(&waiter, NULL, waiterfn, NULL)) - error("pthread_create failed\n", errno); + unsigned int *shared_data = shmat(shm_id, NULL, 0); - usleep(WAKE_WAIT_US); + *shared_data = 0; + waitv[i].uaddr = (uintptr_t)shared_data; + waitv[i].flags = FUTEX_32; + waitv[i].val = 0; + waitv[i].__reserved = 0; + } - res = futex_wake(u64_to_ptr(waitv[NR_FUTEXES - 1].uaddr), 1, 0); - if (res != 1) { - ksft_test_result_fail("futex_wake shared returned: %d %s\n", - res ? errno : res, - res ? strerror(errno) : ""); - ret = RET_FAIL; - } else { - ksft_test_result_pass("futex_waitv shared\n"); - } + if (pthread_create(&waiter, NULL, waiterfn, NULL)) + error("pthread_create failed\n", errno); - for (i = 0; i < NR_FUTEXES; i++) - shmdt(u64_to_ptr(waitv[i].uaddr)); + usleep(WAKE_WAIT_US); + + res = futex_wake(u64_to_ptr(waitv[NR_FUTEXES - 1].uaddr), 1, 0); + if (res != 1) { + ksft_test_result_fail("futex_wake shared returned: %d %s\n", + res ? errno : res, + res ? strerror(errno) : ""); + } else { + ksft_test_result_pass("futex_waitv shared\n"); + } + + for (i = 0; i < NR_FUTEXES; i++) + shmdt(u64_to_ptr(waitv[i].uaddr)); + } /* Testing a waiter without FUTEX_32 flag */ waitv[0].flags = FUTEX_PRIVATE_FLAG; @@ -158,7 +174,6 @@ int main(int argc, char *argv[]) ksft_test_result_fail("futex_waitv private returned: %d %s\n", res ? errno : res, res ? strerror(errno) : ""); - ret = RET_FAIL; } else { ksft_test_result_pass("futex_waitv without FUTEX_32\n"); } @@ -177,7 +192,6 @@ int main(int argc, char *argv[]) ksft_test_result_fail("futex_wake private returned: %d %s\n", res ? errno : res, res ? strerror(errno) : ""); - ret = RET_FAIL; } else { ksft_test_result_pass("futex_waitv with an unaligned address\n"); } @@ -195,7 +209,6 @@ int main(int argc, char *argv[]) ksft_test_result_fail("futex_waitv private returned: %d %s\n", res ? errno : res, res ? strerror(errno) : ""); - ret = RET_FAIL; } else { ksft_test_result_pass("futex_waitv NULL address in waitv.uaddr\n"); } @@ -211,7 +224,6 @@ int main(int argc, char *argv[]) ksft_test_result_fail("futex_waitv private returned: %d %s\n", res ? errno : res, res ? strerror(errno) : ""); - ret = RET_FAIL; } else { ksft_test_result_pass("futex_waitv NULL address in *waiters\n"); } @@ -227,7 +239,6 @@ int main(int argc, char *argv[]) ksft_test_result_fail("futex_waitv private returned: %d %s\n", res ? errno : res, res ? strerror(errno) : ""); - ret = RET_FAIL; } else { ksft_test_result_pass("futex_waitv invalid clockid\n"); } @@ -235,3 +246,4 @@ int main(int argc, char *argv[]) ksft_print_cnts(); return ret; } + -- 2.50.1.703.g449372360f-goog

3 months, 2 weeks

1
0
0 0

[PATCH] selftests/net: Ensure assert() triggers in psock_tpacket.c

by Wake Liu

The get_next_frame() function in psock_tpacket.c was missing a return statement in its default switch case, leading to a compiler warning. This was caused by a `bug_on(1)` call, which is defined as an `assert()`, being compiled out because NDEBUG is defined during the build. Instead of adding a `return NULL;` which would silently hide the error and could lead to crashes later, this change restores the original author's intent. By adding `#undef NDEBUG` before including <assert.h>, we ensure the assertion is active and will cause the test to abort if this unreachable code is ever executed. Signed-off-by: Wake Liu <wakel(a)google.com> --- tools/testing/selftests/net/psock_tpacket.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/net/psock_tpacket.c b/tools/testing/selftests/net/psock_tpacket.c index 0dd909e325d9..a54f2eb754ce 100644 --- a/tools/testing/selftests/net/psock_tpacket.c +++ b/tools/testing/selftests/net/psock_tpacket.c @@ -38,6 +38,7 @@ #include <arpa/inet.h> #include <stdint.h> #include <string.h> +#undef NDEBUG #include <assert.h> #include <net/if.h> #include <inttypes.h> -- 2.50.1.703.g449372360f-goog

3 months, 2 weeks

1
0
0 0

[PATCH v3 0/3] execute PROCMAP_QUERY ioctl under per-vma lock

by Suren Baghdasaryan

With /proc/pid/maps now being read under per-vma lock protection we can reuse parts of that code to execute PROCMAP_QUERY ioctl also without taking mmap_lock. The change is designed to reduce mmap_lock contention and prevent PROCMAP_QUERY ioctl calls from blocking address space updates. This patchset was split out of the original patchset [1] that introduced per-vma lock usage for /proc/pid/maps reading. It contains PROCMAP_QUERY tests, code refactoring patch to simplify the main change and the actual transition to per-vma lock. Changes since v2 [2] - Added Reviewed-by, per Vlastimil Babka - Fixed query_vma_find_by_addr() to handle lock_ctx->mmap_locked case, per Vlastimil Babka [1] https://lore.kernel.org/all/20250704060727.724817-1-surenb@google.com/ [2] https://lore.kernel.org/all/20250804231552.1217132-1-surenb@google.com/ Suren Baghdasaryan (3): selftests/proc: test PROCMAP_QUERY ioctl while vma is concurrently modified fs/proc/task_mmu: factor out proc_maps_private fields used by PROCMAP_QUERY fs/proc/task_mmu: execute PROCMAP_QUERY ioctl under per-vma locks fs/proc/internal.h | 15 +- fs/proc/task_mmu.c | 152 ++++++++++++------ fs/proc/task_nommu.c | 14 +- tools/testing/selftests/proc/proc-maps-race.c | 65 ++++++++ 4 files changed, 184 insertions(+), 62 deletions(-) base-commit: 8e7e0c6d09502e44aa7a8fce0821e042a6ec03d1 -- 2.50.1.565.gc32cd1483b-goog

3 months, 2 weeks

3
10
0 0

[PATCH -next] selftests/bpf: Fix warning comparing pointer to 0

by Jiapeng Chong

Avoid pointer type value compared with 0 to make code clear. ./tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c:221:10-11: WARNING comparing pointer to 0. Reported-by: Abaci Robot <abaci(a)linux.alibaba.com> Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=23403 Signed-off-by: Jiapeng Chong <jiapeng.chong(a)linux.alibaba.com> --- tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c b/tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c index 4f94c971ae86..6b725725b2bf 100644 --- a/tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c +++ b/tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c @@ -218,7 +218,7 @@ int null_check(void *ctx) int *p; p = bpf_rdonly_cast(0, 0); - if (p == 0) + if (!p) /* make this a function call to avoid compiler * moving r0 assignment before check. */ -- 2.43.5

3 months, 2 weeks

2
1
0 0

[PATCH v5] selftests: riscv: add misaligned access testing

by Clément Léger

This selftest tests all the currently emulated instructions (except for the RV32 compressed ones which are left as a future exercise for a RV32 user). For the FPU instructions, all the FPU registers are tested. Signed-off-by: Clément Léger <cleger(a)rivosinc.com> --- This commits needs [1] for the test to be passed or it will fail due to missing sign extension. Note: This test can be executed using an SBI that support FWFT or that delegates misaligned traps by default. If using QEMU, you will need the patches mentioned at [2] so that misaligned accesses will generate a trap. Note: This commit was part of a series [3] that was partially merged. Note: the remaining checkpatch errors are not applicable to this tests which is a userspace one and does not use the kernel headers. Macros with complex values can not be enclosed in do while loop since they are generating functions. Link: https://lore.kernel.org/linux-riscv/mvmikk0goil.fsf@suse.de/ [1] Link: https://lore.kernel.org/all/20241211211933.198792-1-fkonrad@amd.com/ [2] Link: https://lore.kernel.org/linux-riscv/20250422162324.956065-1-cleger@rivosinc… [3] V5: - Sign extend LWU return value - Added sign extensions tests - Tests multiples values for GP load/store V4: - Fixed a typo in test name s/load/store V3: - Fixed a segfault and a sign extension error found when compiling with -O<x>, x != 0 (Alex) - Use inline assembly to generate the sigbus and avoid GCC optimizations V2: - Fix commit description - Fix a few errors reported by checkpatch.pl --- tools/testing/selftests/riscv/Makefile | 2 +- .../selftests/riscv/misaligned/.gitignore | 1 + .../selftests/riscv/misaligned/Makefile | 12 + .../selftests/riscv/misaligned/common.S | 33 ++ .../testing/selftests/riscv/misaligned/fpu.S | 180 +++++++++++ tools/testing/selftests/riscv/misaligned/gp.S | 113 +++++++ .../selftests/riscv/misaligned/misaligned.c | 288 ++++++++++++++++++ 7 files changed, 628 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/riscv/misaligned/.gitignore create mode 100644 tools/testing/selftests/riscv/misaligned/Makefile create mode 100644 tools/testing/selftests/riscv/misaligned/common.S create mode 100644 tools/testing/selftests/riscv/misaligned/fpu.S create mode 100644 tools/testing/selftests/riscv/misaligned/gp.S create mode 100644 tools/testing/selftests/riscv/misaligned/misaligned.c diff --git a/tools/testing/selftests/riscv/Makefile b/tools/testing/selftests/riscv/Makefile index 099b8c1f46f8..95a98ceeb3b3 100644 --- a/tools/testing/selftests/riscv/Makefile +++ b/tools/testing/selftests/riscv/Makefile @@ -5,7 +5,7 @@ ARCH ?= $(shell uname -m 2>/dev/null || echo not) ifneq (,$(filter $(ARCH),riscv)) -RISCV_SUBTARGETS ?= abi hwprobe mm sigreturn vector +RISCV_SUBTARGETS ?= abi hwprobe mm sigreturn vector misaligned else RISCV_SUBTARGETS := endif diff --git a/tools/testing/selftests/riscv/misaligned/.gitignore b/tools/testing/selftests/riscv/misaligned/.gitignore new file mode 100644 index 000000000000..5eff15a1f981 --- /dev/null +++ b/tools/testing/selftests/riscv/misaligned/.gitignore @@ -0,0 +1 @@ +misaligned diff --git a/tools/testing/selftests/riscv/misaligned/Makefile b/tools/testing/selftests/riscv/misaligned/Makefile new file mode 100644 index 000000000000..1aa40110c50d --- /dev/null +++ b/tools/testing/selftests/riscv/misaligned/Makefile @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright (C) 2021 ARM Limited +# Originally tools/testing/arm64/abi/Makefile + +CFLAGS += -I$(top_srcdir)/tools/include + +TEST_GEN_PROGS := misaligned + +include ../../lib.mk + +$(OUTPUT)/misaligned: misaligned.c fpu.S gp.S + $(CC) -g3 -static -o$@ -march=rv64imafdc $(CFLAGS) $(LDFLAGS) $^ diff --git a/tools/testing/selftests/riscv/misaligned/common.S b/tools/testing/selftests/riscv/misaligned/common.S new file mode 100644 index 000000000000..8fa00035bd5d --- /dev/null +++ b/tools/testing/selftests/riscv/misaligned/common.S @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2025 Rivos Inc. + * + * Authors: + * Clément Léger <cleger(a)rivosinc.com> + */ + +.macro lb_sb temp, offset, src, dst + lb \temp, \offset(\src) + sb \temp, \offset(\dst) +.endm + +.macro copy_long_to temp, src, dst + lb_sb \temp, 0, \src, \dst, + lb_sb \temp, 1, \src, \dst, + lb_sb \temp, 2, \src, \dst, + lb_sb \temp, 3, \src, \dst, + lb_sb \temp, 4, \src, \dst, + lb_sb \temp, 5, \src, \dst, + lb_sb \temp, 6, \src, \dst, + lb_sb \temp, 7, \src, \dst, +.endm + +.macro sp_stack_prologue offset + addi sp, sp, -8 + sub sp, sp, \offset +.endm + +.macro sp_stack_epilogue offset + add sp, sp, \offset + addi sp, sp, 8 +.endm diff --git a/tools/testing/selftests/riscv/misaligned/fpu.S b/tools/testing/selftests/riscv/misaligned/fpu.S new file mode 100644 index 000000000000..a7ad4430a424 --- /dev/null +++ b/tools/testing/selftests/riscv/misaligned/fpu.S @@ -0,0 +1,180 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2025 Rivos Inc. + * + * Authors: + * Clément Léger <cleger(a)rivosinc.com> + */ + +#include "common.S" + +#define CASE_ALIGN 4 + +.macro fpu_load_inst fpreg, inst, precision, load_reg +.align CASE_ALIGN + \inst \fpreg, 0(\load_reg) + fmv.\precision fa0, \fpreg + j 2f +.endm + +#define flw(__fpreg) fpu_load_inst __fpreg, flw, s, a4 +#define fld(__fpreg) fpu_load_inst __fpreg, fld, d, a4 +#define c_flw(__fpreg) fpu_load_inst __fpreg, c.flw, s, a4 +#define c_fld(__fpreg) fpu_load_inst __fpreg, c.fld, d, a4 +#define c_fldsp(__fpreg) fpu_load_inst __fpreg, c.fldsp, d, sp + +.macro fpu_store_inst fpreg, inst, precision, store_reg +.align CASE_ALIGN + fmv.\precision \fpreg, fa0 + \inst \fpreg, 0(\store_reg) + j 2f +.endm + +#define fsw(__fpreg) fpu_store_inst __fpreg, fsw, s, a4 +#define fsd(__fpreg) fpu_store_inst __fpreg, fsd, d, a4 +#define c_fsw(__fpreg) fpu_store_inst __fpreg, c.fsw, s, a4 +#define c_fsd(__fpreg) fpu_store_inst __fpreg, c.fsd, d, a4 +#define c_fsdsp(__fpreg) fpu_store_inst __fpreg, c.fsdsp, d, sp + +.macro fp_test_prologue + move a4, a1 + /* + * Compute jump offset to store the correct FP register since we don't + * have indirect FP register access (or at least we don't use this + * extension so that works on all archs) + */ + sll t0, a0, CASE_ALIGN + la t2, 1f + add t0, t0, t2 + jr t0 +.align CASE_ALIGN +1: +.endm + +.macro fp_test_prologue_compressed + /* FP registers for compressed instructions starts from 8 to 16 */ + addi a0, a0, -8 + fp_test_prologue +.endm + +#define fp_test_body_compressed(__inst_func) \ + __inst_func(f8); \ + __inst_func(f9); \ + __inst_func(f10); \ + __inst_func(f11); \ + __inst_func(f12); \ + __inst_func(f13); \ + __inst_func(f14); \ + __inst_func(f15); \ +2: + +#define fp_test_body(__inst_func) \ + __inst_func(f0); \ + __inst_func(f1); \ + __inst_func(f2); \ + __inst_func(f3); \ + __inst_func(f4); \ + __inst_func(f5); \ + __inst_func(f6); \ + __inst_func(f7); \ + __inst_func(f8); \ + __inst_func(f9); \ + __inst_func(f10); \ + __inst_func(f11); \ + __inst_func(f12); \ + __inst_func(f13); \ + __inst_func(f14); \ + __inst_func(f15); \ + __inst_func(f16); \ + __inst_func(f17); \ + __inst_func(f18); \ + __inst_func(f19); \ + __inst_func(f20); \ + __inst_func(f21); \ + __inst_func(f22); \ + __inst_func(f23); \ + __inst_func(f24); \ + __inst_func(f25); \ + __inst_func(f26); \ + __inst_func(f27); \ + __inst_func(f28); \ + __inst_func(f29); \ + __inst_func(f30); \ + __inst_func(f31); \ +2: +.text + +#define __gen_test_inst(__inst, __suffix) \ +.global test_ ## __inst; \ +test_ ## __inst:; \ + fp_test_prologue ## __suffix; \ + fp_test_body ## __suffix(__inst); \ + ret + +#define gen_test_inst_compressed(__inst) \ + .option arch,+c; \ + __gen_test_inst(c_ ## __inst, _compressed) + +#define gen_test_inst(__inst) \ + .balign 16; \ + .option push; \ + .option arch,-c; \ + __gen_test_inst(__inst, ); \ + .option pop + +.macro fp_test_prologue_load_compressed_sp + copy_long_to t0, a1, sp +.endm + +.macro fp_test_epilogue_load_compressed_sp +.endm + +.macro fp_test_prologue_store_compressed_sp +.endm + +.macro fp_test_epilogue_store_compressed_sp + copy_long_to t0, sp, a1 +.endm + +#define gen_inst_compressed_sp(__inst, __type) \ + .global test_c_ ## __inst ## sp; \ + test_c_ ## __inst ## sp:; \ + sp_stack_prologue a2; \ + fp_test_prologue_## __type ## _compressed_sp; \ + fp_test_prologue_compressed; \ + fp_test_body_compressed(c_ ## __inst ## sp); \ + fp_test_epilogue_## __type ## _compressed_sp; \ + sp_stack_epilogue a2; \ + ret + +#define gen_test_load_compressed_sp(__inst) gen_inst_compressed_sp(__inst, load) +#define gen_test_store_compressed_sp(__inst) gen_inst_compressed_sp(__inst, store) + +/* + * float_fsw_reg - Set a FP register from a register containing the value + * a0 = FP register index to be set + * a1 = addr where to store register value + * a2 = address offset + * a3 = value to be store + */ +gen_test_inst(fsw) + +/* + * float_flw_reg - Get a FP register value and return it + * a0 = FP register index to be retrieved + * a1 = addr to load register from + * a2 = address offset + */ +gen_test_inst(flw) + +gen_test_inst(fsd) +#ifdef __riscv_compressed +gen_test_inst_compressed(fsd) +gen_test_store_compressed_sp(fsd) +#endif + +gen_test_inst(fld) +#ifdef __riscv_compressed +gen_test_inst_compressed(fld) +gen_test_load_compressed_sp(fld) +#endif diff --git a/tools/testing/selftests/riscv/misaligned/gp.S b/tools/testing/selftests/riscv/misaligned/gp.S new file mode 100644 index 000000000000..5abec5ccc828 --- /dev/null +++ b/tools/testing/selftests/riscv/misaligned/gp.S @@ -0,0 +1,113 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2025 Rivos Inc. + * + * Authors: + * Clément Léger <cleger(a)rivosinc.com> + */ + +#include "common.S" + +.text + +.macro __gen_test_inst inst, src_reg + \inst a2, 0(\src_reg) + move a0, a2 +.endm + +.macro gen_func_header func_name, rvc + .option arch,\rvc + .global test_\func_name + test_\func_name: +.endm + +.macro gen_test_inst inst + .option push + gen_func_header \inst, -c + __gen_test_inst \inst, a0 + .option pop + ret +.endm + +.macro gen_test_lwu + .option push + gen_func_header lwu, -c + __gen_test_inst lwu, a0 + .option pop + # RISC-V ABI states that C expect a sign extended 32 bits integer + sext.w a0, a0 + ret +.endm + +.macro __gen_test_inst_c name, src_reg + .option push + gen_func_header c_\name, +c + __gen_test_inst c.\name, \src_reg + .option pop + ret +.endm + +.macro gen_test_inst_c name + __gen_test_inst_c \name, a0 +.endm + + +.macro gen_test_inst_c_ldsp + .option push + gen_func_header c_ldsp, +c + sp_stack_prologue a1 + copy_long_to t0, a0, sp + c.ldsp a0, 0(sp) + sp_stack_epilogue a1 + .option pop + ret +.endm + +.macro lb_sp_sb_a0 reg, offset + lb_sb \reg, \offset, sp, a0 +.endm + +.macro gen_test_inst_c_sdsp + .option push + gen_func_header c_sdsp, +c + /* Misalign stack pointer */ + sp_stack_prologue a1 + /* Misalign access */ + c.sdsp a2, 0(sp) + copy_long_to t0, sp, a0 + sp_stack_epilogue a1 + .option pop + ret +.endm + + + /* + * a0 = addr to load from + * a1 = address offset + * a2 = value to be loaded + */ +gen_test_inst lh +gen_test_inst lhu +gen_test_inst lw +gen_test_lwu +gen_test_inst ld +#ifdef __riscv_compressed +gen_test_inst_c lw +gen_test_inst_c ld +gen_test_inst_c_ldsp +#endif + +/* + * a0 = addr where to store value + * a1 = address offset + * a2 = value to be stored + */ +gen_test_inst sh +gen_test_inst sw +gen_test_inst sd +#ifdef __riscv_compressed +gen_test_inst_c sw +gen_test_inst_c sd +gen_test_inst_c_sdsp +#endif + diff --git a/tools/testing/selftests/riscv/misaligned/misaligned.c b/tools/testing/selftests/riscv/misaligned/misaligned.c new file mode 100644 index 000000000000..57ddcbdc947c --- /dev/null +++ b/tools/testing/selftests/riscv/misaligned/misaligned.c @@ -0,0 +1,288 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2025 Rivos Inc. + * + * Authors: + * Clément Léger <cleger(a)rivosinc.com> + */ +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <linux/ptrace.h> +#include "../../kselftest_harness.h" + +#include <stdlib.h> +#include <stdio.h> +#include <stdint.h> +#include <float.h> +#include <errno.h> +#include <math.h> +#include <string.h> +#include <signal.h> +#include <stdbool.h> +#include <unistd.h> +#include <inttypes.h> +#include <ucontext.h> + +#include <sys/prctl.h> + +#define stringify(s) __stringify(s) +#define __stringify(s) #s + +#define U8_MAX ((u8)~0U) +#define S8_MAX ((s8)(U8_MAX >> 1)) +#define S8_MIN ((s8)(-S8_MAX - 1)) +#define U16_MAX ((u16)~0U) +#define S16_MAX ((s16)(U16_MAX >> 1)) +#define S16_MIN ((s16)(-S16_MAX - 1)) +#define U32_MAX ((u32)~0U) +#define U32_MIN ((u32)0) +#define S32_MAX ((s32)(U32_MAX >> 1)) +#define S32_MIN ((s32)(-S32_MAX - 1)) +#define U64_MAX ((u64)~0ULL) +#define S64_MAX ((s64)(U64_MAX >> 1)) +#define S64_MIN ((s64)(-S64_MAX - 1)) + +#define int16_TEST_VALUES {S16_MIN, S16_MIN/2, -1, 1, S16_MAX/2, S16_MAX} +#define int32_TEST_VALUES {S32_MIN, S32_MIN/2, -1, 1, S32_MAX/2, S32_MAX} +#define int64_TEST_VALUES {S64_MIN, S64_MIN/2, -1, 1, S64_MAX/2, S64_MAX} +#define uint16_TEST_VALUES {0, U16_MAX/2, U16_MAX} +#define uint32_TEST_VALUES {0, U32_MAX/2, U32_MAX} + +#define float_TEST_VALUES {FLT_MIN, FLT_MIN/2, FLT_MAX/2, FLT_MAX} +#define double_TEST_VALUES {DBL_MIN, DBL_MIN/2, DBL_MAX/2, DBL_MAX} + +static bool float_equal(float a, float b) +{ + float scaled_epsilon; + float difference = fabsf(a - b); + + // Scale to the largest value. + a = fabsf(a); + b = fabsf(b); + if (a > b) + scaled_epsilon = FLT_EPSILON * a; + else + scaled_epsilon = FLT_EPSILON * b; + + return difference <= scaled_epsilon; +} + +static bool double_equal(double a, double b) +{ + double scaled_epsilon; + double difference = fabsl(a - b); + + // Scale to the largest value. + a = fabs(a); + b = fabs(b); + if (a > b) + scaled_epsilon = DBL_EPSILON * a; + else + scaled_epsilon = DBL_EPSILON * b; + + return difference <= scaled_epsilon; +} + +#define fpu_load_proto(__inst, __type) \ +extern __type test_ ## __inst(unsigned long fp_reg, void *addr, unsigned long offset, __type value) + +fpu_load_proto(flw, float); +fpu_load_proto(fld, double); +fpu_load_proto(c_flw, float); +fpu_load_proto(c_fld, double); +fpu_load_proto(c_fldsp, double); + +#define fpu_store_proto(__inst, __type) \ +extern void test_ ## __inst(unsigned long fp_reg, void *addr, unsigned long offset, __type value) + +fpu_store_proto(fsw, float); +fpu_store_proto(fsd, double); +fpu_store_proto(c_fsw, float); +fpu_store_proto(c_fsd, double); +fpu_store_proto(c_fsdsp, double); + +#define gp_load_proto(__inst, __type) \ +extern __type test_ ## __inst(void *addr, unsigned long offset, __type value) + +gp_load_proto(lh, int16_t); +gp_load_proto(lhu, uint16_t); +gp_load_proto(lw, int32_t); +gp_load_proto(lwu, uint32_t); +gp_load_proto(ld, int64_t); +gp_load_proto(c_lw, int32_t); +gp_load_proto(c_ld, int64_t); +gp_load_proto(c_ldsp, int64_t); + +#define gp_store_proto(__inst, __type) \ +extern void test_ ## __inst(void *addr, unsigned long offset, __type value) + +gp_store_proto(sh, int16_t); +gp_store_proto(sw, int32_t); +gp_store_proto(sd, int64_t); +gp_store_proto(c_sw, int32_t); +gp_store_proto(c_sd, int64_t); +gp_store_proto(c_sdsp, int64_t); + +#define TEST_GP_LOAD(__inst, __type_size, __type) \ +TEST(gp_load_ ## __inst) \ +{ \ + int offset, ret, val_i; \ + uint8_t buf[16] __attribute__((aligned(16))); \ + __type ## __type_size ## _t test_val[] = __type ## __type_size ## _TEST_VALUES; \ + \ + ret = prctl(PR_SET_UNALIGN, PR_UNALIGN_NOPRINT); \ + ASSERT_EQ(ret, 0); \ + \ + for (offset = 1; offset < (__type_size) / 8; offset++) { \ + for (val_i = 0; val_i < ARRAY_SIZE(test_val); val_i++) { \ + __type ## __type_size ## _t ref_val = test_val[val_i]; \ + __type ## __type_size ## _t *ptr = \ + (__type ## __type_size ## _t *)(buf + offset); \ + memcpy(ptr, &ref_val, sizeof(ref_val)); \ + __type ## __type_size ## _t val = \ + test_ ## __inst(ptr, offset, ref_val); \ + EXPECT_EQ(ref_val, val); \ + } \ + } \ +} + +TEST_GP_LOAD(lh, 16, int) +TEST_GP_LOAD(lhu, 16, uint) +TEST_GP_LOAD(lw, 32, int) +TEST_GP_LOAD(lwu, 32, uint) +TEST_GP_LOAD(ld, 64, int) +#ifdef __riscv_compressed +TEST_GP_LOAD(c_lw, 32, int) +TEST_GP_LOAD(c_ld, 64, int) +TEST_GP_LOAD(c_ldsp, 64, int) +#endif + +#define TEST_GP_STORE(__inst, __type_size, __type) \ +TEST(gp_store_ ## __inst) \ +{ \ + int offset, ret, val_i; \ + uint8_t buf[16] __attribute__((aligned(16))); \ + __type ## __type_size ## _t test_val[] = \ + __type ## __type_size ## _TEST_VALUES; \ + \ + ret = prctl(PR_SET_UNALIGN, PR_UNALIGN_NOPRINT); \ + ASSERT_EQ(ret, 0); \ + \ + for (val_i = 0; val_i < ARRAY_SIZE(test_val); val_i++) { \ + __type ## __type_size ## _t ref_val = test_val[val_i]; \ + for (offset = 1; offset < (__type_size) / 8; offset++) { \ + __type ## __type_size ## _t val = ref_val; \ + __type ## __type_size ## _t *ptr = \ + (__type ## __type_size ## _t *)(buf + offset); \ + memset(ptr, 0, sizeof(val)); \ + test_ ## __inst(ptr, offset, val); \ + memcpy(&val, ptr, sizeof(val)); \ + EXPECT_EQ(ref_val, val); \ + } \ + } \ +} + +TEST_GP_STORE(sh, 16, int) +TEST_GP_STORE(sw, 32, int) +TEST_GP_STORE(sd, 64, int) +#ifdef __riscv_compressed +TEST_GP_STORE(c_sw, 32, int) +TEST_GP_STORE(c_sd, 64, int) +TEST_GP_STORE(c_sdsp, 64, int) +#endif + +#define __TEST_FPU_LOAD(__type, __inst, __reg_start, __reg_end) \ +TEST(fpu_load_ ## __inst) \ +{ \ + int ret, offset, fp_reg, val_i; \ + uint8_t buf[16] __attribute__((aligned(16))); \ + __type test_val[] = __type ## _TEST_VALUES; \ + \ + ret = prctl(PR_SET_UNALIGN, PR_UNALIGN_NOPRINT); \ + ASSERT_EQ(ret, 0); \ + \ + for (fp_reg = __reg_start; fp_reg < __reg_end; fp_reg++) { \ + for (offset = 1; offset < 4; offset++) { \ + for (val_i = 0; val_i < ARRAY_SIZE(test_val); val_i++) { \ + __type val, ref_val = test_val[val_i]; \ + void *load_addr = (buf + offset); \ + \ + memcpy(load_addr, &ref_val, sizeof(ref_val)); \ + val = test_ ## __inst(fp_reg, load_addr, offset, ref_val); \ + EXPECT_TRUE(__type ##_equal(val, ref_val)); \ + } \ + } \ + } \ +} + +#define TEST_FPU_LOAD(__type, __inst) \ + __TEST_FPU_LOAD(__type, __inst, 0, 32) +#define TEST_FPU_LOAD_COMPRESSED(__type, __inst) \ + __TEST_FPU_LOAD(__type, __inst, 8, 16) + +TEST_FPU_LOAD(float, flw) +TEST_FPU_LOAD(double, fld) +#ifdef __riscv_compressed +TEST_FPU_LOAD_COMPRESSED(double, c_fld) +TEST_FPU_LOAD_COMPRESSED(double, c_fldsp) +#endif + +#define __TEST_FPU_STORE(__type, __inst, __reg_start, __reg_end) \ +TEST(fpu_store_ ## __inst) \ +{ \ + int ret, offset, fp_reg, val_i; \ + uint8_t buf[16] __attribute__((aligned(16))); \ + __type test_val[] = __type ## _TEST_VALUES; \ + \ + ret = prctl(PR_SET_UNALIGN, PR_UNALIGN_NOPRINT); \ + ASSERT_EQ(ret, 0); \ + \ + for (fp_reg = __reg_start; fp_reg < __reg_end; fp_reg++) { \ + for (offset = 1; offset < 4; offset++) { \ + for (val_i = 0; val_i < ARRAY_SIZE(test_val); val_i++) { \ + __type val, ref_val = test_val[val_i]; \ + \ + void *store_addr = (buf + offset); \ + \ + test_ ## __inst(fp_reg, store_addr, offset, ref_val); \ + memcpy(&val, store_addr, sizeof(val)); \ + EXPECT_TRUE(__type ## _equal(val, ref_val)); \ + } \ + } \ + } \ +} +#define TEST_FPU_STORE(__type, __inst) \ + __TEST_FPU_STORE(__type, __inst, 0, 32) +#define TEST_FPU_STORE_COMPRESSED(__type, __inst) \ + __TEST_FPU_STORE(__type, __inst, 8, 16) + +TEST_FPU_STORE(float, fsw) +TEST_FPU_STORE(double, fsd) +#ifdef __riscv_compressed +TEST_FPU_STORE_COMPRESSED(double, c_fsd) +TEST_FPU_STORE_COMPRESSED(double, c_fsdsp) +#endif + +TEST_SIGNAL(gen_sigbus, SIGBUS) +{ + uint32_t val = 0xDEADBEEF; + uint8_t buf[16] __attribute__((aligned(16))); + int ret; + + ret = prctl(PR_SET_UNALIGN, PR_UNALIGN_SIGBUS); + ASSERT_EQ(ret, 0); + + asm volatile("sw %0, 1(%1)" : : "r"(val), "r"(buf) : "memory"); +} + +int main(int argc, char **argv) +{ + int ret, val; + + ret = prctl(PR_GET_UNALIGN, &val); + if (ret == -1 && errno == EINVAL) + ksft_exit_skip("SKIP GET_UNALIGN_CTL not supported\n"); + + exit(test_harness_run(argc, argv)); +} -- 2.43.0

3 months, 2 weeks

3
2
0 0

[PATCH] selftests/drivers/net: replace typeof() with __auto_type

by Pranav Tyagi

Replace typeof() with __auto_type in iou-zcrx.c. __auto_type was introduced in GCC 4.9 and reduces the compile time for all compilers. No functional changes intended. Signed-off-by: Pranav Tyagi <pranav.tyagi03(a)gmail.com> --- tools/testing/selftests/drivers/net/hw/iou-zcrx.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/drivers/net/hw/iou-zcrx.c b/tools/testing/selftests/drivers/net/hw/iou-zcrx.c index 62456df947bc..85551594bf0f 100644 --- a/tools/testing/selftests/drivers/net/hw/iou-zcrx.c +++ b/tools/testing/selftests/drivers/net/hw/iou-zcrx.c @@ -42,8 +42,8 @@ static long page_size; #define SEND_SIZE (512 * 4096) #define min(a, b) \ ({ \ - typeof(a) _a = (a); \ - typeof(b) _b = (b); \ + __auto_type _a = (a); \ + __auto_type _b = (b); \ _a < _b ? _a : _b; \ }) #define min_t(t, a, b) \ -- 2.49.0

3 months, 2 weeks

2
2
0 0

[PATCH] selftests/bpf/progs: use __auto_type in swap() macro

by Pranav Tyagi

Replace typeof() with __auto_type in xdp_synproxy_kern.c. __auto_type was introduced in GCC 4.9 and reduces the compile time for all compilers. No functional changes intended. Signed-off-by: Pranav Tyagi <pranav.tyagi03(a)gmail.com> --- tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c index 62b8e29ced9f..b08738f9a0e6 100644 --- a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c +++ b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c @@ -58,7 +58,7 @@ #define MAX_PACKET_OFF 0xffff #define swap(a, b) \ - do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) + do { __auto_type __tmp = (a); (a) = (b); (b) = __tmp; } while (0) #define __get_unaligned_t(type, ptr) ({ \ const struct { type x; } __attribute__((__packed__)) *__pptr = (typeof(__pptr))(ptr); \ -- 2.49.0

3 months, 2 weeks

2
2
0 0

[PATCH] selftests/mm: fix FORCE_READ to read input value correctly.

by Zi Yan

FORCE_READ() converts input value x to its pointer type then reads from address x. This is wrong. If x is a non-pointer, it would be caught it easily. But all FORCE_READ() callers are trying to read from a pointer and FORCE_READ() basically reads a pointer to a pointer instead of the original typed pointer. Almost no access violation was found, except the one from split_huge_page_test. Fix it by implementing a simplified READ_ONCE() instead. Fixes: 3f6bfd4789a0 ("selftests/mm: reuse FORCE_READ to replace "asm volatile("" : "+r" (XXX));"") Signed-off-by: Zi Yan <ziy(a)nvidia.com> --- FORCE_READ() comes from commit 876320d71f51 ("selftests/mm: add self tests for guard page feature"). I will a separate patch to stable tree. tools/testing/selftests/mm/cow.c | 4 ++-- tools/testing/selftests/mm/guard-regions.c | 2 +- tools/testing/selftests/mm/hugetlb-madvise.c | 4 +++- tools/testing/selftests/mm/migration.c | 2 +- tools/testing/selftests/mm/pagemap_ioctl.c | 2 +- tools/testing/selftests/mm/split_huge_page_test.c | 7 +++++-- tools/testing/selftests/mm/vm_util.h | 2 +- 7 files changed, 14 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index d30625c18259..c744c603d688 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -1554,8 +1554,8 @@ static void run_with_zeropage(non_anon_test_fn fn, const char *desc) } /* Read from the page to populate the shared zeropage. */ - FORCE_READ(mem); - FORCE_READ(smem); + FORCE_READ(*mem); + FORCE_READ(*smem); fn(mem, smem, pagesize); munmap: diff --git a/tools/testing/selftests/mm/guard-regions.c b/tools/testing/selftests/mm/guard-regions.c index b0d42eb04e3a..8dd81c0a4a5a 100644 --- a/tools/testing/selftests/mm/guard-regions.c +++ b/tools/testing/selftests/mm/guard-regions.c @@ -145,7 +145,7 @@ static bool try_access_buf(char *ptr, bool write) if (write) *ptr = 'x'; else - FORCE_READ(ptr); + FORCE_READ(*ptr); } signal_jump_set = false; diff --git a/tools/testing/selftests/mm/hugetlb-madvise.c b/tools/testing/selftests/mm/hugetlb-madvise.c index 1afe14b9dc0c..c5940c0595be 100644 --- a/tools/testing/selftests/mm/hugetlb-madvise.c +++ b/tools/testing/selftests/mm/hugetlb-madvise.c @@ -50,8 +50,10 @@ void read_fault_pages(void *addr, unsigned long nr_pages) unsigned long i; for (i = 0; i < nr_pages; i++) { + unsigned long *addr2 = + ((unsigned long *)(addr + (i * huge_page_size))); /* Prevent the compiler from optimizing out the entire loop: */ - FORCE_READ(((unsigned long *)(addr + (i * huge_page_size)))); + FORCE_READ(*addr2); } } diff --git a/tools/testing/selftests/mm/migration.c b/tools/testing/selftests/mm/migration.c index c5a73617796a..ea945eebec2f 100644 --- a/tools/testing/selftests/mm/migration.c +++ b/tools/testing/selftests/mm/migration.c @@ -110,7 +110,7 @@ void *access_mem(void *ptr) * the memory access actually happens and prevents the compiler * from optimizing away this entire loop. */ - FORCE_READ((uint64_t *)ptr); + FORCE_READ(*(uint64_t *)ptr); } return NULL; diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c index 0d4209eef0c3..e6face7c0166 100644 --- a/tools/testing/selftests/mm/pagemap_ioctl.c +++ b/tools/testing/selftests/mm/pagemap_ioctl.c @@ -1525,7 +1525,7 @@ void zeropfn_tests(void) ret = madvise(mem, hpage_size, MADV_HUGEPAGE); if (!ret) { - FORCE_READ(mem); + FORCE_READ(*mem); ret = pagemap_ioctl(mem, hpage_size, &vec, 1, 0, 0, PAGE_IS_PFNZERO, 0, 0, PAGE_IS_PFNZERO); diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index 718daceb5282..3c761228e451 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -440,8 +440,11 @@ int create_pagecache_thp_and_fd(const char *testfile, size_t fd_size, int *fd, } madvise(*addr, fd_size, MADV_HUGEPAGE); - for (size_t i = 0; i < fd_size; i++) - FORCE_READ((*addr + i)); + for (size_t i = 0; i < fd_size; i++) { + char *addr2 = *addr + i; + + FORCE_READ(*addr2); + } if (!check_huge_file(*addr, fd_size / pmd_pagesize, pmd_pagesize)) { ksft_print_msg("No large pagecache folio generated, please provide a filesystem supporting large folio\n"); diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index c20298ae98ea..b55d1809debc 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -23,7 +23,7 @@ * anything with it in order to trigger a read page fault. We therefore must use * volatile to stop the compiler from optimising this away. */ -#define FORCE_READ(x) (*(volatile typeof(x) *)x) +#define FORCE_READ(x) (*(const volatile typeof(x) *)&(x)) extern unsigned int __page_size; extern unsigned int __page_shift; -- 2.47.2

3 months, 2 weeks

7
11
0 0

[PATCH] selftests/filesystems: replace typeof() with __auto_type

by Pranav Tyagi

Replace typeof() with __auto_type in utils.c. __auto_type was introduced in GCC 4.9 and reduces the compile time for all compilers. No functional changes intended. Signed-off-by: Pranav Tyagi <pranav.tyagi03(a)gmail.com> --- tools/testing/selftests/filesystems/utils.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/filesystems/utils.c b/tools/testing/selftests/filesystems/utils.c index c43a69dffd83..95f202e2bfb7 100644 --- a/tools/testing/selftests/filesystems/utils.c +++ b/tools/testing/selftests/filesystems/utils.c @@ -34,7 +34,7 @@ #define syserror_set(__ret__, format, ...) \ ({ \ - typeof(__ret__) __internal_ret__ = (__ret__); \ + __auto_type __internal_ret__ = (__ret__); \ errno = labs(__ret__); \ fprintf(stderr, "%m - " format "\n", ##__VA_ARGS__); \ __internal_ret__; \ -- 2.49.0

3 months, 2 weeks

1
0
0 0

[PATCH v6 0/2] libbpf: fix USDT SIB argument handling causing unrecognized register error

by Jiawei Zhao

When using GCC on x86-64 to compile an usdt prog with -O1 or higher optimization, the compiler will generate SIB addressing mode for global array and PC-relative addressing mode for global variable, e.g. "1@-96(%rbp,%rax,8)" and "-1@4+t1(%rip)". The current USDT implementation in libbpf cannot parse these two formats, causing `bpf_program__attach_usdt()` to fail with -ENOENT (unrecognized register). This patch series adds support for SIB addressing mode in USDT probes. The main changes include: - add correct handling logic for SIB-addressed arguments in `parse_usdt_arg`. - force -O2 optimization for usdt.test.o to generate SIB addressing usdt argument spec. - change the global variable t1 to a local variable, to avoid compiler generating PC-relative addressing mode for it. Testing shows that the SIB probe correctly generates 8@(%rcx,%rax,8) argument spec and passes all validation checks. The modification history of this patch series: Change since v1: - refactor the code to make it more readable - modify the commit message to explain why and how Change since v2: - fix the `scale` uninitialized error Change since v3: - force -O2 optimization for usdt.test.o to generate SIB addressing usdt and pass all test cases. Change since v4: - split the patch into two parts, one for the fix and the other for the test Change since v5: - Only enable optimization for x86 architecture to generate SIB addressing usdt argument spec. Do we need to add support for PC-relative USDT argument spec handling in libbpf? I have some interest in this question, but currently have no ideas. Getting offsets based on symbols requires dependency on the symbol table. However, once the binary file is stripped, the symtab will also be removed, which will cause this approach to fail. Does anyone have any thoughts on this? Jiawei Zhao (2): libbpf: fix USDT SIB argument handling causing unrecognized register error selftests/bpf: Force -O2 for USDT selftests to cover SIB handling logic tools/lib/bpf/usdt.bpf.h | 33 +++++++++++++- tools/lib/bpf/usdt.c | 43 ++++++++++++++++--- tools/testing/selftests/bpf/Makefile | 8 ++++ tools/testing/selftests/bpf/prog_tests/usdt.c | 18 +++++--- 4 files changed, 89 insertions(+), 13 deletions(-) -- 2.43.0

3 months, 2 weeks

4
6
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror August 2025